diff --git a/.gitignore b/.gitignore index 0bbae167bf93e9..d1a8ab3f98aaf1 100644 --- a/.gitignore +++ b/.gitignore @@ -135,7 +135,6 @@ GTAGS # id-utils files ID -*.orig *~ \#*# diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block index 1fe9a553c37b71..f0025d1c3d5acd 100644 --- a/Documentation/ABI/stable/sysfs-block +++ b/Documentation/ABI/stable/sysfs-block @@ -101,6 +101,16 @@ Description: devices that support receiving integrity metadata. +What: /sys/block//partscan +Date: May 2024 +Contact: Christoph Hellwig +Description: + The /sys/block//partscan files reports if partition + scanning is enabled for the disk. It returns "1" if partition + scanning is enabled, or "0" if not. The value type is a 32-bit + unsigned integer, but only "0" and "1" are valid values. + + What: /sys/block///alignment_offset Date: April 2009 Contact: Martin K. Petersen diff --git a/Documentation/ABI/testing/sysfs-bus-iio-filter-admv8818 b/Documentation/ABI/testing/sysfs-bus-iio-filter-admv8818 index 31dbb390573ff2..c431f0a13cf502 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio-filter-admv8818 +++ b/Documentation/ABI/testing/sysfs-bus-iio-filter-admv8818 @@ -3,7 +3,7 @@ KernelVersion: Contact: linux-iio@vger.kernel.org Description: Reading this returns the valid values that can be written to the - on_altvoltage0_mode attribute: + filter_mode attribute: - auto -> Adjust bandpass filter to track changes in input clock rate. - manual -> disable/unregister the clock rate notifier / input clock tracking. diff --git a/Documentation/ABI/testing/sysfs-bus-optee-devices b/Documentation/ABI/testing/sysfs-bus-optee-devices index 0f58701367b66a..af31e5a22d89fc 100644 --- a/Documentation/ABI/testing/sysfs-bus-optee-devices +++ b/Documentation/ABI/testing/sysfs-bus-optee-devices @@ -6,3 +6,12 @@ Description: OP-TEE bus provides reference to registered drivers under this directory. The matches Trusted Application (TA) driver and corresponding TA in secure OS. Drivers are free to create needed API under optee-ta- directory. + +What: /sys/bus/tee/devices/optee-ta-/need_supplicant +Date: November 2023 +KernelVersion: 6.7 +Contact: op-tee@lists.trustedfirmware.org +Description: + Allows to distinguish whether an OP-TEE based TA/device requires user-space + tee-supplicant to function properly or not. This attribute will be present for + devices which depend on tee-supplicant to be running. diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq index 5e6b74f304062a..1e7e0bb4c14ecb 100644 --- a/Documentation/ABI/testing/sysfs-class-devfreq +++ b/Documentation/ABI/testing/sysfs-class-devfreq @@ -52,6 +52,9 @@ Description: echo 0 > /sys/class/devfreq/.../trans_stat + If the transition table is bigger than PAGE_SIZE, reading + this will return an -EFBIG error. + What: /sys/class/devfreq/.../available_frequencies Date: October 2012 Contact: Nishanth Menon diff --git a/Documentation/ABI/testing/sysfs-class-led b/Documentation/ABI/testing/sysfs-class-led index b2ff0012c0f2b8..2e24ac3bd7efa4 100644 --- a/Documentation/ABI/testing/sysfs-class-led +++ b/Documentation/ABI/testing/sysfs-class-led @@ -59,15 +59,6 @@ Description: brightness. Reading this file when no hw brightness change event has happened will return an ENODATA error. -What: /sys/class/leds//color -Date: June 2023 -KernelVersion: 6.5 -Description: - Color of the LED. - - This is a read-only file. Reading this file returns the color - of the LED as a string (e.g: "red", "green", "multicolor"). - What: /sys/class/leds//trigger Date: March 2006 KernelVersion: 2.6.17 diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues index 906ff3ca928ac1..5bff64d256c207 100644 --- a/Documentation/ABI/testing/sysfs-class-net-queues +++ b/Documentation/ABI/testing/sysfs-class-net-queues @@ -1,4 +1,4 @@ -What: /sys/class//queues/rx-/rps_cpus +What: /sys/class/net//queues/rx-/rps_cpus Date: March 2010 KernelVersion: 2.6.35 Contact: netdev@vger.kernel.org @@ -8,7 +8,7 @@ Description: network device queue. Possible values depend on the number of available CPU(s) in the system. -What: /sys/class//queues/rx-/rps_flow_cnt +What: /sys/class/net//queues/rx-/rps_flow_cnt Date: April 2010 KernelVersion: 2.6.35 Contact: netdev@vger.kernel.org @@ -16,7 +16,7 @@ Description: Number of Receive Packet Steering flows being currently processed by this particular network device receive queue. -What: /sys/class//queues/tx-/tx_timeout +What: /sys/class/net//queues/tx-/tx_timeout Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -24,7 +24,7 @@ Description: Indicates the number of transmit timeout events seen by this network interface transmit queue. -What: /sys/class//queues/tx-/tx_maxrate +What: /sys/class/net//queues/tx-/tx_maxrate Date: March 2015 KernelVersion: 4.1 Contact: netdev@vger.kernel.org @@ -32,7 +32,7 @@ Description: A Mbps max-rate set for the queue, a value of zero means disabled, default is disabled. -What: /sys/class//queues/tx-/xps_cpus +What: /sys/class/net//queues/tx-/xps_cpus Date: November 2010 KernelVersion: 2.6.38 Contact: netdev@vger.kernel.org @@ -42,7 +42,7 @@ Description: network device transmit queue. Possible values depend on the number of available CPU(s) in the system. -What: /sys/class//queues/tx-/xps_rxqs +What: /sys/class/net//queues/tx-/xps_rxqs Date: June 2018 KernelVersion: 4.18.0 Contact: netdev@vger.kernel.org @@ -53,7 +53,7 @@ Description: number of available receive queue(s) in the network device. Default is disabled. -What: /sys/class//queues/tx-/byte_queue_limits/hold_time +What: /sys/class/net//queues/tx-/byte_queue_limits/hold_time Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -62,7 +62,7 @@ Description: of this particular network device transmit queue. Default value is 1000. -What: /sys/class//queues/tx-/byte_queue_limits/inflight +What: /sys/class/net//queues/tx-/byte_queue_limits/inflight Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -70,7 +70,7 @@ Description: Indicates the number of bytes (objects) in flight on this network device transmit queue. -What: /sys/class//queues/tx-/byte_queue_limits/limit +What: /sys/class/net//queues/tx-/byte_queue_limits/limit Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -79,7 +79,7 @@ Description: on this network device transmit queue. This value is clamped to be within the bounds defined by limit_max and limit_min. -What: /sys/class//queues/tx-/byte_queue_limits/limit_max +What: /sys/class/net//queues/tx-/byte_queue_limits/limit_max Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -88,7 +88,7 @@ Description: queued on this network device transmit queue. See include/linux/dynamic_queue_limits.h for the default value. -What: /sys/class//queues/tx-/byte_queue_limits/limit_min +What: /sys/class/net//queues/tx-/byte_queue_limits/limit_min Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org diff --git a/Documentation/ABI/testing/sysfs-class-net-statistics b/Documentation/ABI/testing/sysfs-class-net-statistics index 55db27815361b2..53e508c6936a51 100644 --- a/Documentation/ABI/testing/sysfs-class-net-statistics +++ b/Documentation/ABI/testing/sysfs-class-net-statistics @@ -1,4 +1,4 @@ -What: /sys/class//statistics/collisions +What: /sys/class/net//statistics/collisions Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -6,7 +6,7 @@ Description: Indicates the number of collisions seen by this network device. This value might not be relevant with all MAC layers. -What: /sys/class//statistics/multicast +What: /sys/class/net//statistics/multicast Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -14,7 +14,7 @@ Description: Indicates the number of multicast packets received by this network device. -What: /sys/class//statistics/rx_bytes +What: /sys/class/net//statistics/rx_bytes Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -23,7 +23,7 @@ Description: See the network driver for the exact meaning of when this value is incremented. -What: /sys/class//statistics/rx_compressed +What: /sys/class/net//statistics/rx_compressed Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -32,7 +32,7 @@ Description: network device. This value might only be relevant for interfaces that support packet compression (e.g: PPP). -What: /sys/class//statistics/rx_crc_errors +What: /sys/class/net//statistics/rx_crc_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -41,7 +41,7 @@ Description: by this network device. Note that the specific meaning might depend on the MAC layer used by the interface. -What: /sys/class//statistics/rx_dropped +What: /sys/class/net//statistics/rx_dropped Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -51,7 +51,7 @@ Description: packet processing. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_errors +What: /sys/class/net//statistics/rx_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -59,7 +59,7 @@ Description: Indicates the number of receive errors on this network device. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_fifo_errors +What: /sys/class/net//statistics/rx_fifo_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -68,7 +68,7 @@ Description: network device. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_frame_errors +What: /sys/class/net//statistics/rx_frame_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -78,7 +78,7 @@ Description: on the MAC layer protocol used. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_length_errors +What: /sys/class/net//statistics/rx_length_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -87,7 +87,7 @@ Description: error, oversized or undersized. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_missed_errors +What: /sys/class/net//statistics/rx_missed_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -96,7 +96,7 @@ Description: due to lack of capacity in the receive side. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_nohandler +What: /sys/class/net//statistics/rx_nohandler Date: February 2016 KernelVersion: 4.6 Contact: netdev@vger.kernel.org @@ -104,7 +104,7 @@ Description: Indicates the number of received packets that were dropped on an inactive device by the network core. -What: /sys/class//statistics/rx_over_errors +What: /sys/class/net//statistics/rx_over_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -114,7 +114,7 @@ Description: (e.g: larger than MTU). See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_packets +What: /sys/class/net//statistics/rx_packets Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -122,7 +122,7 @@ Description: Indicates the total number of good packets received by this network device. -What: /sys/class//statistics/tx_aborted_errors +What: /sys/class/net//statistics/tx_aborted_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -132,7 +132,7 @@ Description: a medium collision). See the network driver for the exact meaning of this value. -What: /sys/class//statistics/tx_bytes +What: /sys/class/net//statistics/tx_bytes Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -143,7 +143,7 @@ Description: transmitted packets or all packets that have been queued for transmission. -What: /sys/class//statistics/tx_carrier_errors +What: /sys/class/net//statistics/tx_carrier_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -152,7 +152,7 @@ Description: because of carrier errors (e.g: physical link down). See the network driver for the exact meaning of this value. -What: /sys/class//statistics/tx_compressed +What: /sys/class/net//statistics/tx_compressed Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -161,7 +161,7 @@ Description: this might only be relevant for devices that support compression (e.g: PPP). -What: /sys/class//statistics/tx_dropped +What: /sys/class/net//statistics/tx_dropped Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -170,7 +170,7 @@ Description: See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_errors +What: /sys/class/net//statistics/tx_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -179,7 +179,7 @@ Description: a network device. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_fifo_errors +What: /sys/class/net//statistics/tx_fifo_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -188,7 +188,7 @@ Description: FIFO error. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_heartbeat_errors +What: /sys/class/net//statistics/tx_heartbeat_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -197,7 +197,7 @@ Description: reported as heartbeat errors. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_packets +What: /sys/class/net//statistics/tx_packets Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -206,7 +206,7 @@ Description: device. See the driver for whether this reports the number of all attempted or successful transmissions. -What: /sys/class//statistics/tx_window_errors +What: /sys/class/net//statistics/tx_window_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 7ecd5c8161a610..657bdee28d845a 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -519,6 +519,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/mds /sys/devices/system/cpu/vulnerabilities/meltdown /sys/devices/system/cpu/vulnerabilities/mmio_stale_data + /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling /sys/devices/system/cpu/vulnerabilities/retbleed /sys/devices/system/cpu/vulnerabilities/spec_store_bypass /sys/devices/system/cpu/vulnerabilities/spectre_v1 @@ -564,7 +565,8 @@ Description: Control Symmetric Multi Threading (SMT) ================ ========================================= If control status is "forceoff" or "notsupported" writes - are rejected. + are rejected. Note that enabling SMT on PowerPC skips + offline cores. What: /sys/devices/system/cpu/cpuX/power/energy_perf_bias Date: March 2019 diff --git a/Documentation/ABI/testing/sysfs-driver-qat b/Documentation/ABI/testing/sysfs-driver-qat index ef6d6c57105efb..96834d103a09e2 100644 --- a/Documentation/ABI/testing/sysfs-driver-qat +++ b/Documentation/ABI/testing/sysfs-driver-qat @@ -29,6 +29,8 @@ Description: (RW) Reports the current configuration of the QAT device. services * asym;sym: identical to sym;asym * dc: the device is configured for running compression services + * dcc: identical to dc but enables the dc chaining feature, + hash then compression. If this is not required chose dc * sym: the device is configured for running symmetric crypto services * asym: the device is configured for running asymmetric crypto diff --git a/Documentation/admin-guide/abi-obsolete.rst b/Documentation/admin-guide/abi-obsolete.rst index d095867899c59a..594e697aa1b2f4 100644 --- a/Documentation/admin-guide/abi-obsolete.rst +++ b/Documentation/admin-guide/abi-obsolete.rst @@ -7,5 +7,5 @@ marked to be removed at some later point in time. The description of the interface will document the reason why it is obsolete and when it can be expected to be removed. -.. kernel-abi:: $srctree/Documentation/ABI/obsolete +.. kernel-abi:: ABI/obsolete :rst: diff --git a/Documentation/admin-guide/abi-removed.rst b/Documentation/admin-guide/abi-removed.rst index f7e9e43023c136..f9e000c81828e5 100644 --- a/Documentation/admin-guide/abi-removed.rst +++ b/Documentation/admin-guide/abi-removed.rst @@ -1,5 +1,5 @@ ABI removed symbols =================== -.. kernel-abi:: $srctree/Documentation/ABI/removed +.. kernel-abi:: ABI/removed :rst: diff --git a/Documentation/admin-guide/abi-stable.rst b/Documentation/admin-guide/abi-stable.rst index 70490736e0d301..fc3361d847b123 100644 --- a/Documentation/admin-guide/abi-stable.rst +++ b/Documentation/admin-guide/abi-stable.rst @@ -10,5 +10,5 @@ for at least 2 years. Most interfaces (like syscalls) are expected to never change and always be available. -.. kernel-abi:: $srctree/Documentation/ABI/stable +.. kernel-abi:: ABI/stable :rst: diff --git a/Documentation/admin-guide/abi-testing.rst b/Documentation/admin-guide/abi-testing.rst index b205b16a72d08a..19767926b34407 100644 --- a/Documentation/admin-guide/abi-testing.rst +++ b/Documentation/admin-guide/abi-testing.rst @@ -16,5 +16,5 @@ Programs that use these interfaces are strongly encouraged to add their name to the description of these interfaces, so that the kernel developers can easily notify them if any changes occur. -.. kernel-abi:: $srctree/Documentation/ABI/testing +.. kernel-abi:: ABI/testing :rst: diff --git a/Documentation/admin-guide/cifs/usage.rst b/Documentation/admin-guide/cifs/usage.rst index 5f936b4b601881..3de599cf0779a9 100644 --- a/Documentation/admin-guide/cifs/usage.rst +++ b/Documentation/admin-guide/cifs/usage.rst @@ -722,40 +722,26 @@ Configuration pseudo-files: ======================= ======================================================= SecurityFlags Flags which control security negotiation and also packet signing. Authentication (may/must) - flags (e.g. for NTLM and/or NTLMv2) may be combined with + flags (e.g. for NTLMv2) may be combined with the signing flags. Specifying two different password hashing mechanisms (as "must use") on the other hand does not make much sense. Default flags are:: - 0x07007 - - (NTLM, NTLMv2 and packet signing allowed). The maximum - allowable flags if you want to allow mounts to servers - using weaker password hashes is 0x37037 (lanman, - plaintext, ntlm, ntlmv2, signing allowed). Some - SecurityFlags require the corresponding menuconfig - options to be enabled. Enabling plaintext - authentication currently requires also enabling - lanman authentication in the security flags - because the cifs module only supports sending - laintext passwords using the older lanman dialect - form of the session setup SMB. (e.g. for authentication - using plain text passwords, set the SecurityFlags - to 0x30030):: + 0x00C5 + + (NTLMv2 and packet signing allowed). Some SecurityFlags + may require enabling a corresponding menuconfig option. may use packet signing 0x00001 must use packet signing 0x01001 - may use NTLM (most common password hash) 0x00002 - must use NTLM 0x02002 may use NTLMv2 0x00004 must use NTLMv2 0x04004 - may use Kerberos security 0x00008 - must use Kerberos 0x08008 - may use lanman (weak) password hash 0x00010 - must use lanman password hash 0x10010 - may use plaintext passwords 0x00020 - must use plaintext passwords 0x20020 - (reserved for future packet encryption) 0x00040 + may use Kerberos security (krb5) 0x00008 + must use Kerberos 0x08008 + may use NTLMSSP 0x00080 + must use NTLMSSP 0x80080 + seal (packet encryption) 0x00040 + must seal 0x40040 cifsFYI If set to non-zero value, additional debug information will be logged to the system error log. This field diff --git a/Documentation/admin-guide/features.rst b/Documentation/admin-guide/features.rst index 8c167082a84f9e..7651eca38227d0 100644 --- a/Documentation/admin-guide/features.rst +++ b/Documentation/admin-guide/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features +.. kernel-feat:: features diff --git a/Documentation/admin-guide/hw-vuln/core-scheduling.rst b/Documentation/admin-guide/hw-vuln/core-scheduling.rst index cf1eeefdfc32f3..a92e10ec402e7d 100644 --- a/Documentation/admin-guide/hw-vuln/core-scheduling.rst +++ b/Documentation/admin-guide/hw-vuln/core-scheduling.rst @@ -67,8 +67,8 @@ arg4: will be performed for all tasks in the task group of ``pid``. arg5: - userspace pointer to an unsigned long for storing the cookie returned by - ``PR_SCHED_CORE_GET`` command. Should be 0 for all other commands. + userspace pointer to an unsigned long long for storing the cookie returned + by ``PR_SCHED_CORE_GET`` command. Should be 0 for all other commands. In order for a process to push a cookie to, or pull a cookie from a process, it is required to have the ptrace access mode: `PTRACE_MODE_READ_REALCREDS` to the diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index de99caabf65a3f..ff0b440ef2dc90 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -21,3 +21,4 @@ are configurable at compile, boot or run time. cross-thread-rsb srso gather_data_sampling + reg-file-data-sampling diff --git a/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst new file mode 100644 index 00000000000000..0585d02b9a6cbc --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst @@ -0,0 +1,104 @@ +================================== +Register File Data Sampling (RFDS) +================================== + +Register File Data Sampling (RFDS) is a microarchitectural vulnerability that +only affects Intel Atom parts(also branded as E-cores). RFDS may allow +a malicious actor to infer data values previously used in floating point +registers, vector registers, or integer registers. RFDS does not provide the +ability to choose which data is inferred. CVE-2023-28746 is assigned to RFDS. + +Affected Processors +=================== +Below is the list of affected Intel processors [#f1]_: + + =================== ============ + Common name Family_Model + =================== ============ + ATOM_GOLDMONT 06_5CH + ATOM_GOLDMONT_D 06_5FH + ATOM_GOLDMONT_PLUS 06_7AH + ATOM_TREMONT_D 06_86H + ATOM_TREMONT 06_96H + ALDERLAKE 06_97H + ALDERLAKE_L 06_9AH + ATOM_TREMONT_L 06_9CH + RAPTORLAKE 06_B7H + RAPTORLAKE_P 06_BAH + ATOM_GRACEMONT 06_BEH + RAPTORLAKE_S 06_BFH + =================== ============ + +As an exception to this table, Intel Xeon E family parts ALDERLAKE(06_97H) and +RAPTORLAKE(06_B7H) codenamed Catlow are not affected. They are reported as +vulnerable in Linux because they share the same family/model with an affected +part. Unlike their affected counterparts, they do not enumerate RFDS_CLEAR or +CPUID.HYBRID. This information could be used to distinguish between the +affected and unaffected parts, but it is deemed not worth adding complexity as +the reporting is fixed automatically when these parts enumerate RFDS_NO. + +Mitigation +========== +Intel released a microcode update that enables software to clear sensitive +information using the VERW instruction. Like MDS, RFDS deploys the same +mitigation strategy to force the CPU to clear the affected buffers before an +attacker can extract the secrets. This is achieved by using the otherwise +unused and obsolete VERW instruction in combination with a microcode update. +The microcode clears the affected CPU buffers when the VERW instruction is +executed. + +Mitigation points +----------------- +VERW is executed by the kernel before returning to user space, and by KVM +before VMentry. None of the affected cores support SMT, so VERW is not required +at C-state transitions. + +New bits in IA32_ARCH_CAPABILITIES +---------------------------------- +Newer processors and microcode update on existing affected processors added new +bits to IA32_ARCH_CAPABILITIES MSR. These bits can be used to enumerate +vulnerability and mitigation capability: + +- Bit 27 - RFDS_NO - When set, processor is not affected by RFDS. +- Bit 28 - RFDS_CLEAR - When set, processor is affected by RFDS, and has the + microcode that clears the affected buffers on VERW execution. + +Mitigation control on the kernel command line +--------------------------------------------- +The kernel command line allows to control RFDS mitigation at boot time with the +parameter "reg_file_data_sampling=". The valid arguments are: + + ========== ================================================================= + on If the CPU is vulnerable, enable mitigation; CPU buffer clearing + on exit to userspace and before entering a VM. + off Disables mitigation. + ========== ================================================================= + +Mitigation default is selected by CONFIG_MITIGATION_RFDS. + +Mitigation status information +----------------------------- +The Linux kernel provides a sysfs interface to enumerate the current +vulnerability status of the system: whether the system is vulnerable, and +which mitigations are active. The relevant sysfs file is: + + /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling + +The possible values in this file are: + + .. list-table:: + + * - 'Not affected' + - The processor is not vulnerable + * - 'Vulnerable' + - The processor is vulnerable, but no mitigation enabled + * - 'Vulnerable: No microcode' + - The processor is vulnerable but microcode is not updated. + * - 'Mitigation: Clear Register File' + - The processor is vulnerable and the CPU buffer clearing mitigation is + enabled. + +References +---------- +.. [#f1] Affected Processors + https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index 32a8893e561776..e0a1be97fa7598 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -138,11 +138,10 @@ associated with the source address of the indirect branch. Specifically, the BHB might be shared across privilege levels even in the presence of Enhanced IBRS. -Currently the only known real-world BHB attack vector is via -unprivileged eBPF. Therefore, it's highly recommended to not enable -unprivileged eBPF, especially when eIBRS is used (without retpolines). -For a full mitigation against BHB attacks, it's recommended to use -retpolines (or eIBRS combined with retpolines). +Previously the only known real-world BHB attack vector was via unprivileged +eBPF. Further research has found attacks that don't require unprivileged eBPF. +For a full mitigation against BHB attacks it is recommended to set BHI_DIS_S or +use the BHB clearing sequence. Attack scenarios ---------------- @@ -430,6 +429,23 @@ The possible values in this file are: 'PBRSB-eIBRS: Not affected' CPU is not affected by PBRSB =========================== ======================================================= + - Branch History Injection (BHI) protection status: + +.. list-table:: + + * - BHI: Not affected + - System is not affected + * - BHI: Retpoline + - System is protected by retpoline + * - BHI: BHI_DIS_S + - System is protected by BHI_DIS_S + * - BHI: SW loop, KVM SW loop + - System is protected by software clearing sequence + * - BHI: Vulnerable + - System is vulnerable to BHI + * - BHI: Vulnerable, KVM: SW loop + - System is vulnerable; KVM is protected by software clearing sequence + Full mitigation might require a microcode update from the CPU vendor. When the necessary microcode is not available, the kernel will report vulnerability. @@ -484,7 +500,11 @@ Spectre variant 2 Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at boot, by setting the IBRS bit, and they're automatically protected against - Spectre v2 variant attacks. + some Spectre v2 variant attacks. The BHB can still influence the choice of + indirect branch predictor entry, and although branch predictor entries are + isolated between modes when eIBRS is enabled, the BHB itself is not isolated + between modes. Systems which support BHI_DIS_S will set it to protect against + BHI attacks. On Intel's enhanced IBRS systems, this includes cross-thread branch target injections on SMT systems (STIBP). In other words, Intel eIBRS enables @@ -638,6 +658,18 @@ kernel command line. spectre_v2=off. Spectre variant 1 mitigations cannot be disabled. + spectre_bhi= + + [X86] Control mitigation of Branch History Injection + (BHI) vulnerability. This setting affects the deployment + of the HW BHI control and the SW BHB clearing sequence. + + on + (default) Enable the HW or SW mitigation as + needed. + off + Disable the mitigation. + For spectre_v2_user see Documentation/admin-guide/kernel-parameters.txt Mitigation selection guide diff --git a/Documentation/admin-guide/hw-vuln/srso.rst b/Documentation/admin-guide/hw-vuln/srso.rst index b6cfb51cb0b469..e715bfc09879a7 100644 --- a/Documentation/admin-guide/hw-vuln/srso.rst +++ b/Documentation/admin-guide/hw-vuln/srso.rst @@ -46,12 +46,22 @@ The possible values in this file are: The processor is not vulnerable - * 'Vulnerable: no microcode': +* 'Vulnerable': + + The processor is vulnerable and no mitigations have been applied. + + * 'Vulnerable: No microcode': The processor is vulnerable, no microcode extending IBPB functionality to address the vulnerability has been applied. - * 'Mitigation: microcode': + * 'Vulnerable: Safe RET, no microcode': + + The "Safe RET" mitigation (see below) has been applied to protect the + kernel, but the IBPB-extending microcode has not been applied. User + space tasks may still be vulnerable. + + * 'Vulnerable: Microcode, no safe RET': Extended IBPB functionality microcode patch has been applied. It does not address User->Kernel and Guest->Host transitions protection but it @@ -72,11 +82,11 @@ The possible values in this file are: (spec_rstack_overflow=microcode) - * 'Mitigation: safe RET': + * 'Mitigation: Safe RET': - Software-only mitigation. It complements the extended IBPB microcode - patch functionality by addressing User->Kernel and Guest->Host - transitions protection. + Combined microcode/software mitigation. It complements the + extended IBPB microcode patch functionality by addressing + User->Kernel and Guest->Host transitions protection. Selected by default or by spec_rstack_overflow=safe-ret @@ -129,7 +139,7 @@ an indrect branch prediction barrier after having applied the required microcode patch for one's system. This mitigation comes also at a performance cost. -Mitigation: safe RET +Mitigation: Safe RET -------------------- The mitigation works by ensuring all RET instructions speculate to diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst index 599e8d3bcbc318..9235cf4fbabff0 100644 --- a/Documentation/admin-guide/kdump/vmcoreinfo.rst +++ b/Documentation/admin-guide/kdump/vmcoreinfo.rst @@ -172,7 +172,7 @@ variables. Offset of the free_list's member. This value is used to compute the number of free pages. -Each zone has a free_area structure array called free_area[MAX_ORDER + 1]. +Each zone has a free_area structure array called free_area[NR_PAGE_ORDERS]. The free_list represents a linked list of free page blocks. (list_head, next|prev) @@ -189,8 +189,8 @@ Offsets of the vmap_area's members. They carry vmalloc-specific information. Makedumpfile gets the start address of the vmalloc region from this. -(zone.free_area, MAX_ORDER + 1) -------------------------------- +(zone.free_area, NR_PAGE_ORDERS) +-------------------------------- Free areas descriptor. User-space tools use this value to iterate the free_area ranges. MAX_ORDER is used by the zone buddy allocator. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 0a1731a0f0ef37..d83a3f47e20074 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -664,12 +664,6 @@ loops can be debugged more effectively on production systems. - clocksource.max_cswd_read_retries= [KNL] - Number of clocksource_watchdog() retries due to - external delays before the clock will be marked - unstable. Defaults to two retries, that is, - three attempts to read the clock under test. - clocksource.verify_n_cpus= [KNL] Limit the number of CPUs checked for clocksources marked with CLOCK_SOURCE_VERIFY_PERCPU that @@ -1133,6 +1127,26 @@ The filter can be disabled or changed to another driver later using sysfs. + reg_file_data_sampling= + [X86] Controls mitigation for Register File Data + Sampling (RFDS) vulnerability. RFDS is a CPU + vulnerability which may allow userspace to infer + kernel data values previously stored in floating point + registers, vector registers, or integer registers. + RFDS only affects Intel Atom processors. + + on: Turns ON the mitigation. + off: Turns OFF the mitigation. + + This parameter overrides the compile time default set + by CONFIG_MITIGATION_RFDS. Mitigation cannot be + disabled when other VERW based mitigations (like MDS) + are enabled. In order to disable RFDS mitigation all + VERW based mitigations need to be disabled. + + For details see: + Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst + driver_async_probe= [KNL] List of driver names to be probed asynchronously. * matches with all driver names. If * is specified, the @@ -3249,9 +3263,7 @@ mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control Valid arguments: on, off - Default (depends on kernel configuration option): - on (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) - off (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=n) + Default: off mem_encrypt=on: Activate SME mem_encrypt=off: Do not activate SME @@ -3305,6 +3317,9 @@ arch-independent options, each of which is an aggregation of existing arch-specific options. + Note, "mitigations" is supported if and only if the + kernel was built with CPU_MITIGATIONS=y. + off Disable all optional CPU mitigations. This improves system performance, but it may also @@ -3322,8 +3337,10 @@ nospectre_bhb [ARM64] nospectre_v1 [X86,PPC] nospectre_v2 [X86,PPC,S390,ARM64] + reg_file_data_sampling=off [X86] retbleed=off [X86] spec_store_bypass_disable=off [X86,PPC] + spectre_bhi=off [X86] spectre_v2_user=off [X86] srbds=off [X86,INTEL] ssbd=force-off [ARM64] @@ -4622,6 +4639,16 @@ printk.time= Show timing data prefixed to each printk message line Format: (1/Y/y=enable, 0/N/n=disable) + proc_mem.force_override= [KNL] + Format: {always | ptrace | never} + Traditionally /proc/pid/mem allows memory permissions to be + overridden without restrictions. This option may be set to + restrict that. Can be one of: + - 'always': traditional behavior always allows mem overrides. + - 'ptrace': only allow mem overrides for active ptracers. + - 'never': never allow mem overrides. + If not specified, default is the CONFIG_PROC_MEM_* choice. + processor.max_cstate= [HW,ACPI] Limit processor to maximum C-state max_cstate=9 overrides any DMI blacklist limit. @@ -4632,11 +4659,9 @@ profile= [KNL] Enable kernel profiling via /proc/profile Format: [,] - Param: : "schedule", "sleep", or "kvm" + Param: : "schedule" or "kvm" [defaults to kernel profiling] Param: "schedule" - profile schedule points. - Param: "sleep" - profile D-state sleeping (millisecs). - Requires CONFIG_SCHEDSTATS Param: "kvm" - profile VM exits. Param: - step/bucket size as a power of 2 for statistical time based profiling. @@ -5858,6 +5883,13 @@ This feature may be more efficiently disabled using the csdlock_debug- kernel parameter. + smp.panic_on_ipistall= [KNL] + If a csd_lock_timeout extends for more than + the specified number of milliseconds, panic the + system. By default, let CSD-lock acquisition + take as long as they take. Specifying 300,000 + for this value provides a 5-minute timeout. + smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port smsc-ircc2.ircc_sir= [HW] SIR base I/O port @@ -5894,6 +5926,15 @@ sonypi.*= [HW] Sony Programmable I/O Control Device driver See Documentation/admin-guide/laptops/sonypi.rst + spectre_bhi= [X86] Control mitigation of Branch History Injection + (BHI) vulnerability. This setting affects the + deployment of the HW BHI control and the SW BHB + clearing sequence. + + on - (default) Enable the HW or SW mitigation + as needed. + off - Disable the mitigation. + spectre_v2= [X86] Control mitigation of Spectre variant 2 (indirect branch speculation) vulnerability. The default operation protects the kernel from @@ -6817,6 +6858,9 @@ pause after every control message); o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra delay after resetting its port); + p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT + (Reduce timeout of the SET_ADDRESS + request from 5000 ms to 500 ms); Example: quirks=0781:5580:bk,0a5c:5834:gij usbhid.mousepoll= diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst index 8da1b728182733..9285f69f4f7355 100644 --- a/Documentation/admin-guide/mm/damon/usage.rst +++ b/Documentation/admin-guide/mm/damon/usage.rst @@ -389,7 +389,7 @@ pages of all memory cgroups except ``/having_care_already``.:: # # further filter out all cgroups except one at '/having_care_already' echo memcg > 1/type echo /having_care_already > 1/memcg_path - echo N > 1/matching + echo Y > 1/matching Note that ``anon`` and ``memcg`` filters are currently supported only when ``paddr`` `implementation ` is being used. diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 4877563241f3bd..5f1748f33d9a20 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -205,6 +205,11 @@ Will increase power usage. Default: 0 (off) +mem_pcpu_rsv +------------ + +Per-cpu reserved forward alloc cache size in page units. Default 1MB per CPU. + rmem_default ------------ diff --git a/Documentation/arch/arc/features.rst b/Documentation/arch/arc/features.rst index b793583d688a46..49ff446ff744cc 100644 --- a/Documentation/arch/arc/features.rst +++ b/Documentation/arch/arc/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features arc +.. kernel-feat:: features arc diff --git a/Documentation/arch/arm/features.rst b/Documentation/arch/arm/features.rst index 7414ec03dd157c..0e76aaf68ecab2 100644 --- a/Documentation/arch/arm/features.rst +++ b/Documentation/arch/arm/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features arm +.. kernel-feat:: features arm diff --git a/Documentation/arch/arm64/features.rst b/Documentation/arch/arm64/features.rst index dfa4cb3cd3efa5..03321f4309d0be 100644 --- a/Documentation/arch/arm64/features.rst +++ b/Documentation/arch/arm64/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features arm64 +.. kernel-feat:: features arm64 diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst index f47f63bcf67c91..3cf806733083c7 100644 --- a/Documentation/arch/arm64/silicon-errata.rst +++ b/Documentation/arch/arm64/silicon-errata.rst @@ -54,6 +54,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Ampere | AmpereOne | AC03_CPU_38 | AMPERE_ERRATUM_AC03_CPU_38 | +----------------+-----------------+-----------------+-----------------------------+ +| Ampere | AmpereOne AC04 | AC04_CPU_10 | AMPERE_ERRATUM_AC03_CPU_38 | ++----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2457168 | ARM64_ERRATUM_2457168 | +----------------+-----------------+-----------------+-----------------------------+ @@ -71,6 +73,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2658417 | ARM64_ERRATUM_2658417 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A510 | #3117295 | ARM64_ERRATUM_3117295 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A520 | #2966298 | ARM64_ERRATUM_2966298 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A53 | #826319 | ARM64_ERRATUM_826319 | @@ -117,32 +121,72 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A76 | #1463225 | ARM64_ERRATUM_1463225 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A76 | #3324349 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A77 | #1508412 | ARM64_ERRATUM_1508412 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A77 | #3324348 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A78 | #3324344 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A78C | #3324346,3324347| ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A710 | #2119858 | ARM64_ERRATUM_2119858 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A710 | #2054223 | ARM64_ERRATUM_2054223 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A710 | #2224489 | ARM64_ERRATUM_2224489 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A710 | #3324338 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A715 | #2645198 | ARM64_ERRATUM_2645198 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A715 | #3456084 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A720 | #3456091 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A725 | #3456106 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X1 | #3324344 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X1C | #3324346 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-X2 | #2119858 | ARM64_ERRATUM_2119858 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-X2 | #2224489 | ARM64_ERRATUM_2224489 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X2 | #3324338 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X3 | #3324335 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X4 | #3194386 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X925 | #3324334 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1349291 | N/A | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1542419 | ARM64_ERRATUM_1542419 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N1 | #3324349 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #2139208 | ARM64_ERRATUM_2139208 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #2067961 | ARM64_ERRATUM_2067961 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #2253138 | ARM64_ERRATUM_2253138 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N2 | #3324339 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N3 | #3456111 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-V1 | #3324341 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-V2 | #3324336 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-500 | #841119,826419 | N/A | +----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-600 | #1076982,1209401| N/A | @@ -233,3 +277,12 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ASR | ASR8601 | #8601001 | N/A | +----------------+-----------------+-----------------+-----------------------------+ ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2139208 | ARM64_ERRATUM_2139208 | ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2067961 | ARM64_ERRATUM_2067961 | ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2253138 | ARM64_ERRATUM_2253138 | ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #3324339 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/arch/ia64/features.rst b/Documentation/arch/ia64/features.rst index d7226fdcf5f8c0..056838d2ab55c5 100644 --- a/Documentation/arch/ia64/features.rst +++ b/Documentation/arch/ia64/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features ia64 +.. kernel-feat:: features ia64 diff --git a/Documentation/arch/loongarch/features.rst b/Documentation/arch/loongarch/features.rst index ebacade3ea454e..009f44c7951f8a 100644 --- a/Documentation/arch/loongarch/features.rst +++ b/Documentation/arch/loongarch/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features loongarch +.. kernel-feat:: features loongarch diff --git a/Documentation/arch/m68k/features.rst b/Documentation/arch/m68k/features.rst index 5107a21194724e..de7f0ccf7fc8ed 100644 --- a/Documentation/arch/m68k/features.rst +++ b/Documentation/arch/m68k/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features m68k +.. kernel-feat:: features m68k diff --git a/Documentation/arch/mips/features.rst b/Documentation/arch/mips/features.rst index 1973d729b29a98..6e0ffe3e735400 100644 --- a/Documentation/arch/mips/features.rst +++ b/Documentation/arch/mips/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features mips +.. kernel-feat:: features mips diff --git a/Documentation/arch/nios2/features.rst b/Documentation/arch/nios2/features.rst index 8449e63f69b2b4..89913810ccb5a0 100644 --- a/Documentation/arch/nios2/features.rst +++ b/Documentation/arch/nios2/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features nios2 +.. kernel-feat:: features nios2 diff --git a/Documentation/arch/openrisc/features.rst b/Documentation/arch/openrisc/features.rst index 3f7c40d219f2cc..bae2e25adfd642 100644 --- a/Documentation/arch/openrisc/features.rst +++ b/Documentation/arch/openrisc/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features openrisc +.. kernel-feat:: features openrisc diff --git a/Documentation/arch/parisc/features.rst b/Documentation/arch/parisc/features.rst index 501d7c45003790..b3aa4d243b9362 100644 --- a/Documentation/arch/parisc/features.rst +++ b/Documentation/arch/parisc/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features parisc +.. kernel-feat:: features parisc diff --git a/Documentation/arch/s390/features.rst b/Documentation/arch/s390/features.rst index 57c296a9d8f30d..2883dc95068173 100644 --- a/Documentation/arch/s390/features.rst +++ b/Documentation/arch/s390/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features s390 +.. kernel-feat:: features s390 diff --git a/Documentation/arch/sh/features.rst b/Documentation/arch/sh/features.rst index f722af3b6c9934..fae48fe81e9bd0 100644 --- a/Documentation/arch/sh/features.rst +++ b/Documentation/arch/sh/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features sh +.. kernel-feat:: features sh diff --git a/Documentation/arch/sparc/features.rst b/Documentation/arch/sparc/features.rst index c0c92468b0fe90..96835b6d598a1a 100644 --- a/Documentation/arch/sparc/features.rst +++ b/Documentation/arch/sparc/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features sparc +.. kernel-feat:: features sparc diff --git a/Documentation/arch/x86/amd-memory-encryption.rst b/Documentation/arch/x86/amd-memory-encryption.rst index 934310ce725829..bace87cc9ca2ce 100644 --- a/Documentation/arch/x86/amd-memory-encryption.rst +++ b/Documentation/arch/x86/amd-memory-encryption.rst @@ -87,14 +87,14 @@ The state of SME in the Linux kernel can be documented as follows: kernel is non-zero). SME can also be enabled and activated in the BIOS. If SME is enabled and -activated in the BIOS, then all memory accesses will be encrypted and it will -not be necessary to activate the Linux memory encryption support. If the BIOS -merely enables SME (sets bit 23 of the MSR_AMD64_SYSCFG), then Linux can activate -memory encryption by default (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) or -by supplying mem_encrypt=on on the kernel command line. However, if BIOS does -not enable SME, then Linux will not be able to activate memory encryption, even -if configured to do so by default or the mem_encrypt=on command line parameter -is specified. +activated in the BIOS, then all memory accesses will be encrypted and it +will not be necessary to activate the Linux memory encryption support. + +If the BIOS merely enables SME (sets bit 23 of the MSR_AMD64_SYSCFG), +then memory encryption can be enabled by supplying mem_encrypt=on on the +kernel command line. However, if BIOS does not enable SME, then Linux +will not be able to activate memory encryption, even if configured to do +so by default or the mem_encrypt=on command line parameter is specified. Secure Nested Paging (SNP) ========================== diff --git a/Documentation/arch/x86/features.rst b/Documentation/arch/x86/features.rst index b663f15053ce85..a33616346a388c 100644 --- a/Documentation/arch/x86/features.rst +++ b/Documentation/arch/x86/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features x86 +.. kernel-feat:: features x86 diff --git a/Documentation/arch/x86/mds.rst b/Documentation/arch/x86/mds.rst index e73fdff62c0aa1..c58c72362911cd 100644 --- a/Documentation/arch/x86/mds.rst +++ b/Documentation/arch/x86/mds.rst @@ -95,6 +95,9 @@ The kernel provides a function to invoke the buffer clearing: mds_clear_cpu_buffers() +Also macro CLEAR_CPU_BUFFERS can be used in ASM late in exit-to-user path. +Other than CFLAGS.ZF, this macro doesn't clobber any registers. + The mitigation is invoked on kernel/userspace, hypervisor/guest and C-state (idle) transitions. @@ -138,17 +141,30 @@ Mitigation points When transitioning from kernel to user space the CPU buffers are flushed on affected CPUs when the mitigation is not disabled on the kernel - command line. The migitation is enabled through the static key - mds_user_clear. - - The mitigation is invoked in prepare_exit_to_usermode() which covers - all but one of the kernel to user space transitions. The exception - is when we return from a Non Maskable Interrupt (NMI), which is - handled directly in do_nmi(). - - (The reason that NMI is special is that prepare_exit_to_usermode() can - enable IRQs. In NMI context, NMIs are blocked, and we don't want to - enable IRQs with NMIs blocked.) + command line. The mitigation is enabled through the feature flag + X86_FEATURE_CLEAR_CPU_BUF. + + The mitigation is invoked just before transitioning to userspace after + user registers are restored. This is done to minimize the window in + which kernel data could be accessed after VERW e.g. via an NMI after + VERW. + + **Corner case not handled** + Interrupts returning to kernel don't clear CPUs buffers since the + exit-to-user path is expected to do that anyways. But, there could be + a case when an NMI is generated in kernel after the exit-to-user path + has cleared the buffers. This case is not handled and NMI returning to + kernel don't clear CPU buffers because: + + 1. It is rare to get an NMI after VERW, but before returning to userspace. + 2. For an unprivileged user, there is no known way to make that NMI + less rare or target it. + 3. It would take a large number of these precisely-timed NMIs to mount + an actual attack. There's presumably not enough bandwidth. + 4. The NMI in question occurs after a VERW, i.e. when user state is + restored and most interesting data is already scrubbed. Whats left + is only the data that NMI touches, and that may or may not be of + any interest. 2. C-State transition diff --git a/Documentation/arch/xtensa/features.rst b/Documentation/arch/xtensa/features.rst index 6b92c7bfa19daa..28dcce1759be4b 100644 --- a/Documentation/arch/xtensa/features.rst +++ b/Documentation/arch/xtensa/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features xtensa +.. kernel-feat:: features xtensa diff --git a/Documentation/bpf/map_lpm_trie.rst b/Documentation/bpf/map_lpm_trie.rst index 74d64a30f50073..f9cd579496c9ce 100644 --- a/Documentation/bpf/map_lpm_trie.rst +++ b/Documentation/bpf/map_lpm_trie.rst @@ -17,7 +17,7 @@ significant byte. LPM tries may be created with a maximum prefix length that is a multiple of 8, in the range from 8 to 2048. The key used for lookup and update -operations is a ``struct bpf_lpm_trie_key``, extended by +operations is a ``struct bpf_lpm_trie_key_u8``, extended by ``max_prefixlen/8`` bytes. - For IPv4 addresses the data length is 4 bytes diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst index 7964fe134277b8..6c1303cff159e1 100644 --- a/Documentation/cdrom/cdrom-standard.rst +++ b/Documentation/cdrom/cdrom-standard.rst @@ -217,7 +217,7 @@ current *struct* is:: int (*media_changed)(struct cdrom_device_info *, int); int (*tray_move)(struct cdrom_device_info *, int); int (*lock_door)(struct cdrom_device_info *, int); - int (*select_speed)(struct cdrom_device_info *, int); + int (*select_speed)(struct cdrom_device_info *, unsigned long); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn)(struct cdrom_device_info *, struct cdrom_mcn *); @@ -396,7 +396,7 @@ action need be taken, and the return value should be 0. :: - int select_speed(struct cdrom_device_info *cdi, int speed) + int select_speed(struct cdrom_device_info *cdi, unsigned long speed) Some CD-ROM drives are capable of changing their head-speed. There are several reasons for changing the speed of a CD-ROM drive. Badly diff --git a/Documentation/conf.py b/Documentation/conf.py index d4fdf6a3875a83..e385e24fe9e72e 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -345,9 +345,9 @@ sys.stderr.write("Using %s theme\n" % html_theme) html_static_path = ['sphinx-static'] # If true, Docutils "smart quotes" will be used to convert quotes and dashes -# to typographically correct entities. This will convert "--" to "—", -# which is not always what we want, so disable it. -smartquotes = False +# to typographically correct entities. However, conversion of "--" to "—" +# is not always what we want, so enable only quotes. +smartquotes_action = 'q' # Custom sidebar templates, maps document names to template names. # Note that the RTD theme ignores this @@ -383,6 +383,12 @@ latex_elements = { verbatimhintsturnover=false, ''', + # + # Some of our authors are fond of deep nesting; tell latex to + # cope. + # + 'maxlistdepth': '10', + # For CJK One-half spacing, need to be in front of hyperref 'extrapackages': r'\usepackage{setspace}', diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst index deede972f25479..3ae1b3677d7f3a 100644 --- a/Documentation/dev-tools/kselftest.rst +++ b/Documentation/dev-tools/kselftest.rst @@ -255,9 +255,21 @@ Contributing new tests (details) TEST_PROGS_EXTENDED, TEST_GEN_PROGS_EXTENDED mean it is the executable which is not tested by default. + TEST_FILES, TEST_GEN_FILES mean it is the file which is used by test. + TEST_INCLUDES is similar to TEST_FILES, it lists files which should be + included when exporting or installing the tests, with the following + differences: + + * symlinks to files in other directories are preserved + * the part of paths below tools/testing/selftests/ is preserved when + copying the files to the output directory + + TEST_INCLUDES is meant to list dependencies located in other directories of + the selftests hierarchy. + * First use the headers inside the kernel source and/or git repo, and then the system headers. Headers for the kernel release as opposed to headers installed by the distro on the system should be the primary focus to be able diff --git a/Documentation/devicetree/bindings/arm/qcom.yaml b/Documentation/devicetree/bindings/arm/qcom.yaml index adbfaea3234354..90f31beb80c224 100644 --- a/Documentation/devicetree/bindings/arm/qcom.yaml +++ b/Documentation/devicetree/bindings/arm/qcom.yaml @@ -136,7 +136,7 @@ description: | There are many devices in the list below that run the standard ChromeOS bootloader setup and use the open source depthcharge bootloader to boot the OS. These devices do not use the scheme described above. For details, see: - https://docs.kernel.org/arm/google/chromebook-boot-flow.html + https://docs.kernel.org/arch/arm/google/chromebook-boot-flow.html properties: $nodename: diff --git a/Documentation/devicetree/bindings/display/msm/qcom,mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,mdss.yaml index 0999ea07f47bb6..e4576546bf0dbb 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,mdss.yaml @@ -127,6 +127,7 @@ patternProperties: - qcom,dsi-phy-20nm - qcom,dsi-phy-28nm-8226 - qcom,dsi-phy-28nm-hpm + - qcom,dsi-phy-28nm-hpm-fam-b - qcom,dsi-phy-28nm-lp - qcom,hdmi-phy-8084 - qcom,hdmi-phy-8660 diff --git a/Documentation/devicetree/bindings/dma/fsl,edma.yaml b/Documentation/devicetree/bindings/dma/fsl,edma.yaml index 437db0c62339fa..e1b4b910044b0e 100644 --- a/Documentation/devicetree/bindings/dma/fsl,edma.yaml +++ b/Documentation/devicetree/bindings/dma/fsl,edma.yaml @@ -47,8 +47,8 @@ properties: - 3 dma-channels: - minItems: 1 - maxItems: 64 + minimum: 1 + maximum: 64 clocks: minItems: 1 diff --git a/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml b/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml index c1060e5fcef3a9..d3d8a2e143ed25 100644 --- a/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml +++ b/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml @@ -126,7 +126,7 @@ examples: - | #include - gpio@e000a000 { + gpio@a0020000 { compatible = "xlnx,xps-gpio-1.00.a"; reg = <0xa0020000 0x10000>; #gpio-cells = <2>; diff --git a/Documentation/devicetree/bindings/i2c/atmel,at91sam-i2c.yaml b/Documentation/devicetree/bindings/i2c/atmel,at91sam-i2c.yaml index 6adedd3ec399b9..c22e459c175abf 100644 --- a/Documentation/devicetree/bindings/i2c/atmel,at91sam-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/atmel,at91sam-i2c.yaml @@ -75,7 +75,7 @@ required: - clocks allOf: - - $ref: i2c-controller.yaml + - $ref: /schemas/i2c/i2c-controller.yaml# - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml b/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml index ab151c9db21913..580003cdfff59e 100644 --- a/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml +++ b/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml @@ -21,7 +21,7 @@ description: | google,cros-ec-spi or google,cros-ec-i2c. allOf: - - $ref: i2c-controller.yaml# + - $ref: /schemas/i2c/i2c-controller.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/iio/adc/adi,axi-adc.yaml b/Documentation/devicetree/bindings/iio/adc/adi,axi-adc.yaml index 9996dd93f84b29..e1f450b80db278 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,axi-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,axi-adc.yaml @@ -28,6 +28,9 @@ properties: reg: maxItems: 1 + clocks: + maxItems: 1 + dmas: maxItems: 1 @@ -39,12 +42,16 @@ properties: $ref: /schemas/types.yaml#/definitions/phandle description: A reference to a the actual ADC to which this FPGA ADC interfaces to. + deprecated: true + + '#io-backend-cells': + const: 0 required: - compatible - dmas - reg - - adi,adc-dev + - clocks additionalProperties: false @@ -55,7 +62,7 @@ examples: reg = <0x44a00000 0x10000>; dmas = <&rx_dma 0>; dma-names = "rx"; - - adi,adc-dev = <&spi_adc>; + clocks = <&axi_clk>; + #io-backend-cells = <0>; }; ... diff --git a/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml b/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml index c13c10c8d65da2..eed0df9d3a2322 100644 --- a/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml +++ b/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml @@ -42,7 +42,7 @@ allOf: properties: compatible: contains: - const: maxim,max30100 + const: maxim,max30102 then: properties: maxim,green-led-current-microamp: false diff --git a/Documentation/devicetree/bindings/iio/magnetometer/asahi-kasei,ak8975.yaml b/Documentation/devicetree/bindings/iio/magnetometer/asahi-kasei,ak8975.yaml index 9790f75fc669ef..fe5145d3b73cf2 100644 --- a/Documentation/devicetree/bindings/iio/magnetometer/asahi-kasei,ak8975.yaml +++ b/Documentation/devicetree/bindings/iio/magnetometer/asahi-kasei,ak8975.yaml @@ -23,7 +23,6 @@ properties: - ak8963 - ak09911 - ak09912 - - ak09916 deprecated: true reg: diff --git a/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml b/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml index 509d20c091af82..6a206111d4e0f0 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml @@ -62,6 +62,9 @@ properties: - description: MPM pin number - description: GIC SPI number for the MPM pin + '#power-domain-cells': + const: 0 + required: - compatible - reg @@ -93,4 +96,5 @@ examples: <86 183>, <90 260>, <91 260>; + #power-domain-cells = <0>; }; diff --git a/Documentation/devicetree/bindings/media/i2c/ovti,ov2680.yaml b/Documentation/devicetree/bindings/media/i2c/ovti,ov2680.yaml index cf456f8d9ddcb8..c87677f5e2a250 100644 --- a/Documentation/devicetree/bindings/media/i2c/ovti,ov2680.yaml +++ b/Documentation/devicetree/bindings/media/i2c/ovti,ov2680.yaml @@ -37,15 +37,15 @@ properties: active low. maxItems: 1 - dovdd-supply: + DOVDD-supply: description: Definition of the regulator used as interface power supply. - avdd-supply: + AVDD-supply: description: Definition of the regulator used as analog power supply. - dvdd-supply: + DVDD-supply: description: Definition of the regulator used as digital power supply. @@ -59,9 +59,9 @@ required: - reg - clocks - clock-names - - dovdd-supply - - avdd-supply - - dvdd-supply + - DOVDD-supply + - AVDD-supply + - DVDD-supply - reset-gpios - port @@ -82,9 +82,9 @@ examples: clock-names = "xvclk"; reset-gpios = <&gpio1 3 GPIO_ACTIVE_LOW>; - dovdd-supply = <&sw2_reg>; - dvdd-supply = <&sw2_reg>; - avdd-supply = <®_peri_3p15v>; + DOVDD-supply = <&sw2_reg>; + DVDD-supply = <&sw2_reg>; + AVDD-supply = <®_peri_3p15v>; port { ov2680_to_mipi: endpoint { diff --git a/Documentation/devicetree/bindings/media/mediatek,mdp3-rdma.yaml b/Documentation/devicetree/bindings/media/mediatek,mdp3-rdma.yaml index 7032c7e1503900..3e128733ef535b 100644 --- a/Documentation/devicetree/bindings/media/mediatek,mdp3-rdma.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,mdp3-rdma.yaml @@ -61,6 +61,9 @@ properties: - description: used for 1st data pipe from RDMA - description: used for 2nd data pipe from RDMA + '#dma-cells': + const: 1 + required: - compatible - reg @@ -70,6 +73,7 @@ required: - clocks - iommus - mboxes + - '#dma-cells' additionalProperties: false @@ -80,16 +84,17 @@ examples: #include #include - mdp3_rdma0: mdp3-rdma0@14001000 { - compatible = "mediatek,mt8183-mdp3-rdma"; - reg = <0x14001000 0x1000>; - mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>; - mediatek,gce-events = , - ; - power-domains = <&spm MT8183_POWER_DOMAIN_DISP>; - clocks = <&mmsys CLK_MM_MDP_RDMA0>, - <&mmsys CLK_MM_MDP_RSZ1>; - iommus = <&iommu>; - mboxes = <&gce 20 CMDQ_THR_PRIO_LOWEST>, - <&gce 21 CMDQ_THR_PRIO_LOWEST>; + dma-controller@14001000 { + compatible = "mediatek,mt8183-mdp3-rdma"; + reg = <0x14001000 0x1000>; + mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>; + mediatek,gce-events = , + ; + power-domains = <&spm MT8183_POWER_DOMAIN_DISP>; + clocks = <&mmsys CLK_MM_MDP_RDMA0>, + <&mmsys CLK_MM_MDP_RSZ1>; + iommus = <&iommu>; + mboxes = <&gce 20 CMDQ_THR_PRIO_LOWEST>, + <&gce 21 CMDQ_THR_PRIO_LOWEST>; + #dma-cells = <1>; }; diff --git a/Documentation/devicetree/bindings/media/mediatek,mdp3-wrot.yaml b/Documentation/devicetree/bindings/media/mediatek,mdp3-wrot.yaml index 0baa77198fa217..64ea98aa05928e 100644 --- a/Documentation/devicetree/bindings/media/mediatek,mdp3-wrot.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,mdp3-wrot.yaml @@ -50,6 +50,9 @@ properties: iommus: maxItems: 1 + '#dma-cells': + const: 1 + required: - compatible - reg @@ -58,6 +61,7 @@ required: - power-domains - clocks - iommus + - '#dma-cells' additionalProperties: false @@ -68,13 +72,14 @@ examples: #include #include - mdp3_wrot0: mdp3-wrot0@14005000 { - compatible = "mediatek,mt8183-mdp3-wrot"; - reg = <0x14005000 0x1000>; - mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x5000 0x1000>; - mediatek,gce-events = , - ; - power-domains = <&spm MT8183_POWER_DOMAIN_DISP>; - clocks = <&mmsys CLK_MM_MDP_WROT0>; - iommus = <&iommu>; + dma-controller@14005000 { + compatible = "mediatek,mt8183-mdp3-wrot"; + reg = <0x14005000 0x1000>; + mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x5000 0x1000>; + mediatek,gce-events = , + ; + power-domains = <&spm MT8183_POWER_DOMAIN_DISP>; + clocks = <&mmsys CLK_MM_MDP_WROT0>; + iommus = <&iommu>; + #dma-cells = <1>; }; diff --git a/Documentation/devicetree/bindings/media/rockchip-isp1.yaml b/Documentation/devicetree/bindings/media/rockchip-isp1.yaml index e466dff8286d2b..afcaa427d48b09 100644 --- a/Documentation/devicetree/bindings/media/rockchip-isp1.yaml +++ b/Documentation/devicetree/bindings/media/rockchip-isp1.yaml @@ -90,15 +90,16 @@ properties: description: connection point for input on the parallel interface properties: - bus-type: - enum: [5, 6] - endpoint: $ref: video-interfaces.yaml# unevaluatedProperties: false - required: - - bus-type + properties: + bus-type: + enum: [5, 6] + + required: + - bus-type anyOf: - required: diff --git a/Documentation/devicetree/bindings/mfd/mt6397.txt b/Documentation/devicetree/bindings/mfd/mt6397.txt index 294693a8906cf5..10540aa7afa1af 100644 --- a/Documentation/devicetree/bindings/mfd/mt6397.txt +++ b/Documentation/devicetree/bindings/mfd/mt6397.txt @@ -22,8 +22,9 @@ compatible: "mediatek,mt6323" for PMIC MT6323 "mediatek,mt6331" for PMIC MT6331 and MT6332 "mediatek,mt6357" for PMIC MT6357 - "mediatek,mt6358" for PMIC MT6358 and MT6366 + "mediatek,mt6358" for PMIC MT6358 "mediatek,mt6359" for PMIC MT6359 + "mediatek,mt6366", "mediatek,mt6358" for PMIC MT6366 "mediatek,mt6397" for PMIC MT6397 Optional subnodes: @@ -40,6 +41,7 @@ Optional subnodes: - compatible: "mediatek,mt6323-regulator" see ../regulator/mt6323-regulator.txt - compatible: "mediatek,mt6358-regulator" + - compatible: "mediatek,mt6366-regulator", "mediatek-mt6358-regulator" see ../regulator/mt6358-regulator.txt - compatible: "mediatek,mt6397-regulator" see ../regulator/mt6397-regulator.txt diff --git a/Documentation/devicetree/bindings/net/mediatek,net.yaml b/Documentation/devicetree/bindings/net/mediatek,net.yaml index e74502a0afe867..3202dc7967c5b6 100644 --- a/Documentation/devicetree/bindings/net/mediatek,net.yaml +++ b/Documentation/devicetree/bindings/net/mediatek,net.yaml @@ -337,8 +337,8 @@ allOf: minItems: 4 clocks: - minItems: 34 - maxItems: 34 + minItems: 24 + maxItems: 24 clock-names: items: @@ -351,18 +351,6 @@ allOf: - const: ethwarp_wocpu1 - const: ethwarp_wocpu0 - const: esw - - const: netsys0 - - const: netsys1 - - const: sgmii_tx250m - - const: sgmii_rx250m - - const: sgmii2_tx250m - - const: sgmii2_rx250m - - const: top_usxgmii0_sel - - const: top_usxgmii1_sel - - const: top_sgm0_sel - - const: top_sgm1_sel - - const: top_xfi_phy0_xtal_sel - - const: top_xfi_phy1_xtal_sel - const: top_eth_gmii_sel - const: top_eth_refck_50m_sel - const: top_eth_sys_200m_sel @@ -375,16 +363,10 @@ allOf: - const: top_netsys_sync_250m_sel - const: top_netsys_ppefb_250m_sel - const: top_netsys_warp_sel - - const: wocpu1 - - const: wocpu0 - const: xgp1 - const: xgp2 - const: xgp3 - mediatek,sgmiisys: - minItems: 2 - maxItems: 2 - patternProperties: "^mac@[0-1]$": type: object diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index ddf9522a5dc230..5c2769dc689af7 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -394,6 +394,11 @@ properties: When a PFC frame is received with priorities matching the bitmask, the queue is blocked from transmitting for the pause time specified in the PFC frame. + + snps,coe-unsupported: + type: boolean + description: TX checksum offload is unsupported by the TX queue. + allOf: - if: required: diff --git a/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml b/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml index 1d33d80af11c3c..652d696bc9e90b 100644 --- a/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml +++ b/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml @@ -34,6 +34,7 @@ properties: and length of the AXI DMA controller IO space, unless axistream-connected is specified, in which case the reg attribute of the node referenced by it is used. + minItems: 1 maxItems: 2 interrupts: @@ -165,7 +166,7 @@ examples: clock-names = "s_axi_lite_clk", "axis_clk", "ref_clk", "mgt_clk"; clocks = <&axi_clk>, <&axi_clk>, <&pl_enet_ref_clk>, <&mgt_clk>; phy-mode = "mii"; - reg = <0x00 0x40000000 0x00 0x40000>; + reg = <0x40000000 0x40000>; xlnx,rxcsum = <0x2>; xlnx,rxmem = <0x800>; xlnx,txcsum = <0x2>; diff --git a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml index a9b822aeaa7edb..e436650f0faf7d 100644 --- a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml +++ b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml @@ -14,9 +14,11 @@ allOf: properties: compatible: - enum: - - fsl,imx23-ocotp - - fsl,imx28-ocotp + items: + - enum: + - fsl,imx23-ocotp + - fsl,imx28-ocotp + - const: fsl,ocotp reg: maxItems: 1 @@ -34,7 +36,7 @@ unevaluatedProperties: false examples: - | ocotp: efuse@8002c000 { - compatible = "fsl,imx28-ocotp"; + compatible = "fsl,imx28-ocotp", "fsl,ocotp"; #address-cells = <1>; #size-cells = <1>; reg = <0x8002c000 0x2000>; diff --git a/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml b/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml index 8fdfbc763d7045..835b6db00c2796 100644 --- a/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml +++ b/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml @@ -68,6 +68,18 @@ properties: phy-names: const: pcie + vpcie1v5-supply: + description: The 1.5v regulator to use for PCIe. + + vpcie3v3-supply: + description: The 3.3v regulator to use for PCIe. + + vpcie12v-supply: + description: The 12v regulator to use for PCIe. + + iommu-map: true + iommu-map-mask: true + required: - compatible - reg @@ -121,5 +133,7 @@ examples: clock-names = "pcie", "pcie_bus"; power-domains = <&sysc R8A7791_PD_ALWAYS_ON>; resets = <&cpg 319>; + vpcie3v3-supply = <&pcie_3v3>; + vpcie12v-supply = <&pcie_12v>; }; }; diff --git a/Documentation/devicetree/bindings/pci/rockchip,rk3399-pcie.yaml b/Documentation/devicetree/bindings/pci/rockchip,rk3399-pcie.yaml index 531008f0b6ac32..002b728cbc7184 100644 --- a/Documentation/devicetree/bindings/pci/rockchip,rk3399-pcie.yaml +++ b/Documentation/devicetree/bindings/pci/rockchip,rk3399-pcie.yaml @@ -37,6 +37,7 @@ properties: description: This property is needed if using 24MHz OSC for RC's PHY. ep-gpios: + maxItems: 1 description: pre-reset GPIO vpcie12v-supply: diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml index d981d77e82e40a..a6244c33faf614 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml @@ -71,7 +71,6 @@ required: - reg - clocks - clock-names - - power-domains - resets - reset-names - vdda-phy-supply @@ -130,6 +129,21 @@ allOf: clock-names: maxItems: 1 + - if: + properties: + compatible: + contains: + enum: + - qcom,msm8996-qmp-ufs-phy + - qcom,msm8998-qmp-ufs-phy + then: + properties: + power-domains: + false + else: + required: + - power-domains + additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml index 9af203dc8793f3..fa7408eb74895b 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml @@ -62,12 +62,12 @@ properties: "#clock-cells": const: 1 description: - See include/dt-bindings/dt-bindings/phy/phy-qcom-qmp.h + See include/dt-bindings/phy/phy-qcom-qmp.h "#phy-cells": const: 1 description: - See include/dt-bindings/dt-bindings/phy/phy-qcom-qmp.h + See include/dt-bindings/phy/phy-qcom-qmp.h orientation-switch: description: diff --git a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-repeater.yaml b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-repeater.yaml index 029569d5fcf35f..24c733c10e0e92 100644 --- a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-repeater.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-repeater.yaml @@ -32,6 +32,27 @@ properties: vdd3-supply: true + qcom,tune-usb2-disc-thres: + $ref: /schemas/types.yaml#/definitions/uint8 + description: High-Speed disconnect threshold + minimum: 0 + maximum: 7 + default: 0 + + qcom,tune-usb2-amplitude: + $ref: /schemas/types.yaml#/definitions/uint8 + description: High-Speed trasmit amplitude + minimum: 0 + maximum: 15 + default: 8 + + qcom,tune-usb2-preem: + $ref: /schemas/types.yaml#/definitions/uint8 + description: High-Speed TX pre-emphasis tuning + minimum: 0 + maximum: 7 + default: 5 + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml b/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml index 0f200e3f97a9a3..fce7f8a19e9c0a 100644 --- a/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml @@ -15,9 +15,6 @@ description: | properties: compatible: oneOf: - - enum: - - qcom,sc8180x-usb-hs-phy - - qcom,usb-snps-femto-v2-phy - items: - enum: - qcom,sa8775p-usb-hs-phy @@ -26,6 +23,7 @@ properties: - items: - enum: - qcom,sc7280-usb-hs-phy + - qcom,sc8180x-usb-hs-phy - qcom,sdx55-usb-hs-phy - qcom,sdx65-usb-hs-phy - qcom,sm6375-usb-hs-phy diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml index bd72a326e6e069..60f30a59f3853e 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml @@ -97,7 +97,8 @@ patternProperties: then: properties: groups: - enum: [emmc, emmc_rst] + items: + enum: [emmc, emmc_rst] - if: properties: function: @@ -105,8 +106,9 @@ patternProperties: then: properties: groups: - enum: [esw, esw_p0_p1, esw_p2_p3_p4, rgmii_via_esw, - rgmii_via_gmac1, rgmii_via_gmac2, mdc_mdio] + items: + enum: [esw, esw_p0_p1, esw_p2_p3_p4, rgmii_via_esw, + rgmii_via_gmac1, rgmii_via_gmac2, mdc_mdio] - if: properties: function: @@ -123,10 +125,11 @@ patternProperties: then: properties: groups: - enum: [i2s_in_mclk_bclk_ws, i2s1_in_data, i2s2_in_data, - i2s3_in_data, i2s4_in_data, i2s_out_mclk_bclk_ws, - i2s1_out_data, i2s2_out_data, i2s3_out_data, - i2s4_out_data] + items: + enum: [i2s_in_mclk_bclk_ws, i2s1_in_data, i2s2_in_data, + i2s3_in_data, i2s4_in_data, i2s_out_mclk_bclk_ws, + i2s1_out_data, i2s2_out_data, i2s3_out_data, + i2s4_out_data] - if: properties: function: @@ -159,10 +162,11 @@ patternProperties: then: properties: groups: - enum: [pcie0_0_waken, pcie0_1_waken, pcie1_0_waken, - pcie0_0_clkreq, pcie0_1_clkreq, pcie1_0_clkreq, - pcie0_pad_perst, pcie1_pad_perst, pcie_pereset, - pcie_wake, pcie_clkreq] + items: + enum: [pcie0_0_waken, pcie0_1_waken, pcie1_0_waken, + pcie0_0_clkreq, pcie0_1_clkreq, pcie1_0_clkreq, + pcie0_pad_perst, pcie1_pad_perst, pcie_pereset, + pcie_wake, pcie_clkreq] - if: properties: function: @@ -178,11 +182,12 @@ patternProperties: then: properties: groups: - enum: [pwm_ch1_0, pwm_ch1_1, pwm_ch1_2, pwm_ch2_0, pwm_ch2_1, - pwm_ch2_2, pwm_ch3_0, pwm_ch3_1, pwm_ch3_2, pwm_ch4_0, - pwm_ch4_1, pwm_ch4_2, pwm_ch4_3, pwm_ch5_0, pwm_ch5_1, - pwm_ch5_2, pwm_ch6_0, pwm_ch6_1, pwm_ch6_2, pwm_ch6_3, - pwm_ch7_0, pwm_0, pwm_1] + items: + enum: [pwm_ch1_0, pwm_ch1_1, pwm_ch1_2, pwm_ch2_0, pwm_ch2_1, + pwm_ch2_2, pwm_ch3_0, pwm_ch3_1, pwm_ch3_2, pwm_ch4_0, + pwm_ch4_1, pwm_ch4_2, pwm_ch4_3, pwm_ch5_0, pwm_ch5_1, + pwm_ch5_2, pwm_ch6_0, pwm_ch6_1, pwm_ch6_2, pwm_ch6_3, + pwm_ch7_0, pwm_0, pwm_1] - if: properties: function: @@ -260,33 +265,34 @@ patternProperties: pins: description: An array of strings. Each string contains the name of a pin. - enum: [GPIO_A, I2S1_IN, I2S1_OUT, I2S_BCLK, I2S_WS, I2S_MCLK, TXD0, - RXD0, SPI_WP, SPI_HOLD, SPI_CLK, SPI_MOSI, SPI_MISO, SPI_CS, - I2C_SDA, I2C_SCL, I2S2_IN, I2S3_IN, I2S4_IN, I2S2_OUT, - I2S3_OUT, I2S4_OUT, GPIO_B, MDC, MDIO, G2_TXD0, G2_TXD1, - G2_TXD2, G2_TXD3, G2_TXEN, G2_TXC, G2_RXD0, G2_RXD1, G2_RXD2, - G2_RXD3, G2_RXDV, G2_RXC, NCEB, NWEB, NREB, NDL4, NDL5, NDL6, - NDL7, NRB, NCLE, NALE, NDL0, NDL1, NDL2, NDL3, MDI_TP_P0, - MDI_TN_P0, MDI_RP_P0, MDI_RN_P0, MDI_TP_P1, MDI_TN_P1, - MDI_RP_P1, MDI_RN_P1, MDI_RP_P2, MDI_RN_P2, MDI_TP_P2, - MDI_TN_P2, MDI_TP_P3, MDI_TN_P3, MDI_RP_P3, MDI_RN_P3, - MDI_RP_P4, MDI_RN_P4, MDI_TP_P4, MDI_TN_P4, PMIC_SCL, - PMIC_SDA, SPIC1_CLK, SPIC1_MOSI, SPIC1_MISO, SPIC1_CS, - GPIO_D, WATCHDOG, RTS3_N, CTS3_N, TXD3, RXD3, PERST0_N, - PERST1_N, WLED_N, EPHY_LED0_N, AUXIN0, AUXIN1, AUXIN2, - AUXIN3, TXD4, RXD4, RTS4_N, CST4_N, PWM1, PWM2, PWM3, PWM4, - PWM5, PWM6, PWM7, GPIO_E, TOP_5G_CLK, TOP_5G_DATA, - WF0_5G_HB0, WF0_5G_HB1, WF0_5G_HB2, WF0_5G_HB3, WF0_5G_HB4, - WF0_5G_HB5, WF0_5G_HB6, XO_REQ, TOP_RST_N, SYS_WATCHDOG, - EPHY_LED0_N_JTDO, EPHY_LED1_N_JTDI, EPHY_LED2_N_JTMS, - EPHY_LED3_N_JTCLK, EPHY_LED4_N_JTRST_N, WF2G_LED_N, - WF5G_LED_N, GPIO_9, GPIO_10, GPIO_11, GPIO_12, UART1_TXD, - UART1_RXD, UART1_CTS, UART1_RTS, UART2_TXD, UART2_RXD, - UART2_CTS, UART2_RTS, SMI_MDC, SMI_MDIO, PCIE_PERESET_N, - PWM_0, GPIO_0, GPIO_1, GPIO_2, GPIO_3, GPIO_4, GPIO_5, - GPIO_6, GPIO_7, GPIO_8, UART0_TXD, UART0_RXD, TOP_2G_CLK, - TOP_2G_DATA, WF0_2G_HB0, WF0_2G_HB1, WF0_2G_HB2, WF0_2G_HB3, - WF0_2G_HB4, WF0_2G_HB5, WF0_2G_HB6] + items: + enum: [GPIO_A, I2S1_IN, I2S1_OUT, I2S_BCLK, I2S_WS, I2S_MCLK, TXD0, + RXD0, SPI_WP, SPI_HOLD, SPI_CLK, SPI_MOSI, SPI_MISO, SPI_CS, + I2C_SDA, I2C_SCL, I2S2_IN, I2S3_IN, I2S4_IN, I2S2_OUT, + I2S3_OUT, I2S4_OUT, GPIO_B, MDC, MDIO, G2_TXD0, G2_TXD1, + G2_TXD2, G2_TXD3, G2_TXEN, G2_TXC, G2_RXD0, G2_RXD1, G2_RXD2, + G2_RXD3, G2_RXDV, G2_RXC, NCEB, NWEB, NREB, NDL4, NDL5, NDL6, + NDL7, NRB, NCLE, NALE, NDL0, NDL1, NDL2, NDL3, MDI_TP_P0, + MDI_TN_P0, MDI_RP_P0, MDI_RN_P0, MDI_TP_P1, MDI_TN_P1, + MDI_RP_P1, MDI_RN_P1, MDI_RP_P2, MDI_RN_P2, MDI_TP_P2, + MDI_TN_P2, MDI_TP_P3, MDI_TN_P3, MDI_RP_P3, MDI_RN_P3, + MDI_RP_P4, MDI_RN_P4, MDI_TP_P4, MDI_TN_P4, PMIC_SCL, + PMIC_SDA, SPIC1_CLK, SPIC1_MOSI, SPIC1_MISO, SPIC1_CS, + GPIO_D, WATCHDOG, RTS3_N, CTS3_N, TXD3, RXD3, PERST0_N, + PERST1_N, WLED_N, EPHY_LED0_N, AUXIN0, AUXIN1, AUXIN2, + AUXIN3, TXD4, RXD4, RTS4_N, CST4_N, PWM1, PWM2, PWM3, PWM4, + PWM5, PWM6, PWM7, GPIO_E, TOP_5G_CLK, TOP_5G_DATA, + WF0_5G_HB0, WF0_5G_HB1, WF0_5G_HB2, WF0_5G_HB3, WF0_5G_HB4, + WF0_5G_HB5, WF0_5G_HB6, XO_REQ, TOP_RST_N, SYS_WATCHDOG, + EPHY_LED0_N_JTDO, EPHY_LED1_N_JTDI, EPHY_LED2_N_JTMS, + EPHY_LED3_N_JTCLK, EPHY_LED4_N_JTRST_N, WF2G_LED_N, + WF5G_LED_N, GPIO_9, GPIO_10, GPIO_11, GPIO_12, UART1_TXD, + UART1_RXD, UART1_CTS, UART1_RTS, UART2_TXD, UART2_RXD, + UART2_CTS, UART2_RTS, SMI_MDC, SMI_MDIO, PCIE_PERESET_N, + PWM_0, GPIO_0, GPIO_1, GPIO_2, GPIO_3, GPIO_4, GPIO_5, + GPIO_6, GPIO_7, GPIO_8, UART0_TXD, UART0_RXD, TOP_2G_CLK, + TOP_2G_DATA, WF0_2G_HB0, WF0_2G_HB1, WF0_2G_HB2, WF0_2G_HB3, + WF0_2G_HB4, WF0_2G_HB5, WF0_2G_HB6] bias-disable: true diff --git a/Documentation/devicetree/bindings/serial/rs485.yaml b/Documentation/devicetree/bindings/serial/rs485.yaml index 303a443d9e29b2..9418fd66a8e95a 100644 --- a/Documentation/devicetree/bindings/serial/rs485.yaml +++ b/Documentation/devicetree/bindings/serial/rs485.yaml @@ -29,6 +29,10 @@ properties: default: 0 maximum: 100 + rs485-rts-active-high: + description: drive RTS high when sending (this is the default). + $ref: /schemas/types.yaml#/definitions/flag + rs485-rts-active-low: description: drive RTS low when sending (default is high). $ref: /schemas/types.yaml#/definitions/flag diff --git a/Documentation/devicetree/bindings/serial/serial.yaml b/Documentation/devicetree/bindings/serial/serial.yaml index ea277560a59664..5727bd549deca4 100644 --- a/Documentation/devicetree/bindings/serial/serial.yaml +++ b/Documentation/devicetree/bindings/serial/serial.yaml @@ -96,7 +96,7 @@ then: rts-gpios: false patternProperties: - "^bluetooth|gnss|gps|mcu$": + "^(bluetooth|gnss|gps|mcu)$": if: type: object then: diff --git a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml index e4fa6a07b4fa2c..be6ffec2b07497 100644 --- a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml +++ b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml @@ -163,6 +163,7 @@ allOf: unevaluatedProperties: false pcie-phy: + type: object description: Documentation/devicetree/bindings/phy/rockchip-pcie-phy.txt diff --git a/Documentation/devicetree/bindings/sound/rt5645.txt b/Documentation/devicetree/bindings/sound/rt5645.txt index 41a62fd2ae1ffb..c1fa379f5f3ea1 100644 --- a/Documentation/devicetree/bindings/sound/rt5645.txt +++ b/Documentation/devicetree/bindings/sound/rt5645.txt @@ -20,6 +20,11 @@ Optional properties: a GPIO spec for the external headphone detect pin. If jd-mode = 0, we will get the JD status by getting the value of hp-detect-gpios. +- cbj-sleeve-gpios: + a GPIO spec to control the external combo jack circuit to tie the sleeve/ring2 + contacts to the ground or floating. It could avoid some electric noise from the + active speaker jacks. + - realtek,in2-differential Boolean. Indicate MIC2 input are differential, rather than single-ended. @@ -68,6 +73,7 @@ codec: rt5650@1a { compatible = "realtek,rt5650"; reg = <0x1a>; hp-detect-gpios = <&gpio 19 0>; + cbj-sleeve-gpios = <&gpio 20 0>; interrupt-parent = <&gpio>; interrupts = <7 IRQ_TYPE_EDGE_FALLING>; realtek,dmic-en = "true"; diff --git a/Documentation/devicetree/bindings/spi/spi-nxp-fspi.yaml b/Documentation/devicetree/bindings/spi/spi-nxp-fspi.yaml index 7fd59114548001..902db92da83207 100644 --- a/Documentation/devicetree/bindings/spi/spi-nxp-fspi.yaml +++ b/Documentation/devicetree/bindings/spi/spi-nxp-fspi.yaml @@ -15,12 +15,19 @@ allOf: properties: compatible: - enum: - - nxp,imx8dxl-fspi - - nxp,imx8mm-fspi - - nxp,imx8mp-fspi - - nxp,imx8qxp-fspi - - nxp,lx2160a-fspi + oneOf: + - enum: + - nxp,imx8dxl-fspi + - nxp,imx8mm-fspi + - nxp,imx8mp-fspi + - nxp,imx8qxp-fspi + - nxp,imx8ulp-fspi + - nxp,lx2160a-fspi + - items: + - enum: + - nxp,imx93-fspi + - nxp,imx95-fspi + - const: nxp,imx8mm-fspi reg: items: diff --git a/Documentation/devicetree/bindings/spmi/hisilicon,hisi-spmi-controller.yaml b/Documentation/devicetree/bindings/spmi/hisilicon,hisi-spmi-controller.yaml index f882903769f954..eee7c8d4cf4a29 100644 --- a/Documentation/devicetree/bindings/spmi/hisilicon,hisi-spmi-controller.yaml +++ b/Documentation/devicetree/bindings/spmi/hisilicon,hisi-spmi-controller.yaml @@ -14,7 +14,7 @@ description: | It is a MIPI System Power Management (SPMI) controller. The PMIC part is provided by - ./Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml. + Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml. allOf: - $ref: spmi.yaml# @@ -48,7 +48,7 @@ patternProperties: PMIC properties, which are specific to the used SPMI PMIC device(s). When used in combination with HiSilicon 6421v600, the properties are documented at - drivers/staging/hikey9xx/hisilicon,hi6421-spmi-pmic.yaml. + Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/thermal/loongson,ls2k-thermal.yaml b/Documentation/devicetree/bindings/thermal/loongson,ls2k-thermal.yaml index 7538469997f9e1..ca81c8afba79c6 100644 --- a/Documentation/devicetree/bindings/thermal/loongson,ls2k-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/loongson,ls2k-thermal.yaml @@ -10,28 +10,55 @@ maintainers: - zhanghongchen - Yinbo Zhu +allOf: + - $ref: /schemas/thermal/thermal-sensor.yaml# + properties: compatible: oneOf: - enum: - loongson,ls2k1000-thermal + - loongson,ls2k2000-thermal - items: - enum: - - loongson,ls2k2000-thermal + - loongson,ls2k0500-thermal - const: loongson,ls2k1000-thermal reg: - maxItems: 1 + minItems: 1 + maxItems: 2 interrupts: maxItems: 1 + '#thermal-sensor-cells': + const: 1 + required: - compatible - reg - interrupts + - '#thermal-sensor-cells' + +if: + properties: + compatible: + contains: + enum: + - loongson,ls2k2000-thermal + +then: + properties: + reg: + minItems: 2 + maxItems: 2 + +else: + properties: + reg: + maxItems: 1 -additionalProperties: false +unevaluatedProperties: false examples: - | @@ -41,4 +68,5 @@ examples: reg = <0x1fe01500 0x30>; interrupt-parent = <&liointc0>; interrupts = <7 IRQ_TYPE_LEVEL_LOW>; + #thermal-sensor-cells = <1>; }; diff --git a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml index 4f3acdc4dec0ef..98cdd98212c495 100644 --- a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml +++ b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml @@ -49,7 +49,10 @@ properties: to take when the temperature crosses those thresholds. patternProperties: - "^[a-zA-Z][a-zA-Z0-9\\-]{1,12}-thermal$": + # Node name is limited in size due to Linux kernel requirements - 19 + # characters in total (see THERMAL_NAME_LENGTH, including terminating NUL + # byte): + "^[a-zA-Z][a-zA-Z0-9\\-]{1,10}-thermal$": type: object description: Each thermal zone node contains information about how frequently it diff --git a/Documentation/devicetree/bindings/timer/renesas,rz-mtu3.yaml b/Documentation/devicetree/bindings/timer/renesas,rz-mtu3.yaml index bffdab0b01859b..fbac40b958ddea 100644 --- a/Documentation/devicetree/bindings/timer/renesas,rz-mtu3.yaml +++ b/Documentation/devicetree/bindings/timer/renesas,rz-mtu3.yaml @@ -169,27 +169,27 @@ properties: - const: tgib0 - const: tgic0 - const: tgid0 - - const: tgiv0 + - const: tciv0 - const: tgie0 - const: tgif0 - const: tgia1 - const: tgib1 - - const: tgiv1 - - const: tgiu1 + - const: tciv1 + - const: tciu1 - const: tgia2 - const: tgib2 - - const: tgiv2 - - const: tgiu2 + - const: tciv2 + - const: tciu2 - const: tgia3 - const: tgib3 - const: tgic3 - const: tgid3 - - const: tgiv3 + - const: tciv3 - const: tgia4 - const: tgib4 - const: tgic4 - const: tgid4 - - const: tgiv4 + - const: tciv4 - const: tgiu5 - const: tgiv5 - const: tgiw5 @@ -197,18 +197,18 @@ properties: - const: tgib6 - const: tgic6 - const: tgid6 - - const: tgiv6 + - const: tciv6 - const: tgia7 - const: tgib7 - const: tgic7 - const: tgid7 - - const: tgiv7 + - const: tciv7 - const: tgia8 - const: tgib8 - const: tgic8 - const: tgid8 - - const: tgiv8 - - const: tgiu8 + - const: tciv8 + - const: tciu8 clocks: maxItems: 1 @@ -285,16 +285,16 @@ examples: , , ; - interrupt-names = "tgia0", "tgib0", "tgic0", "tgid0", "tgiv0", "tgie0", + interrupt-names = "tgia0", "tgib0", "tgic0", "tgid0", "tciv0", "tgie0", "tgif0", - "tgia1", "tgib1", "tgiv1", "tgiu1", - "tgia2", "tgib2", "tgiv2", "tgiu2", - "tgia3", "tgib3", "tgic3", "tgid3", "tgiv3", - "tgia4", "tgib4", "tgic4", "tgid4", "tgiv4", + "tgia1", "tgib1", "tciv1", "tciu1", + "tgia2", "tgib2", "tciv2", "tciu2", + "tgia3", "tgib3", "tgic3", "tgid3", "tciv3", + "tgia4", "tgib4", "tgic4", "tgid4", "tciv4", "tgiu5", "tgiv5", "tgiw5", - "tgia6", "tgib6", "tgic6", "tgid6", "tgiv6", - "tgia7", "tgib7", "tgic7", "tgid7", "tgiv7", - "tgia8", "tgib8", "tgic8", "tgid8", "tgiv8", "tgiu8"; + "tgia6", "tgib6", "tgic6", "tgid6", "tciv6", + "tgia7", "tgib7", "tgic7", "tgid7", "tciv7", + "tgia8", "tgib8", "tgic8", "tgid8", "tciv8", "tciu8"; clocks = <&cpg CPG_MOD R9A07G044_MTU_X_MCK_MTU3>; power-domains = <&cpg>; resets = <&cpg R9A07G044_MTU_X_PRESET_MTU3>; diff --git a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml index ff3a1707ef570f..6d4cfd943f5847 100644 --- a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml +++ b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml @@ -36,7 +36,11 @@ properties: vdd-supply: description: - VDD power supply to the hub + 3V3 power supply to the hub + + vdd2-supply: + description: + 1V2 power supply to the hub peer-hub: $ref: /schemas/types.yaml#/definitions/phandle @@ -62,6 +66,7 @@ allOf: properties: reset-gpios: false vdd-supply: false + vdd2-supply: false peer-hub: false i2c-bus: false else: diff --git a/Documentation/driver-api/fpga/fpga-bridge.rst b/Documentation/driver-api/fpga/fpga-bridge.rst index 60420853409533..833f68fb070089 100644 --- a/Documentation/driver-api/fpga/fpga-bridge.rst +++ b/Documentation/driver-api/fpga/fpga-bridge.rst @@ -6,9 +6,12 @@ API to implement a new FPGA bridge * struct fpga_bridge - The FPGA Bridge structure * struct fpga_bridge_ops - Low level Bridge driver ops -* fpga_bridge_register() - Create and register a bridge +* __fpga_bridge_register() - Create and register a bridge * fpga_bridge_unregister() - Unregister a bridge +The helper macro ``fpga_bridge_register()`` automatically sets +the module that registers the FPGA bridge as the owner. + .. kernel-doc:: include/linux/fpga/fpga-bridge.h :functions: fpga_bridge @@ -16,7 +19,7 @@ API to implement a new FPGA bridge :functions: fpga_bridge_ops .. kernel-doc:: drivers/fpga/fpga-bridge.c - :functions: fpga_bridge_register + :functions: __fpga_bridge_register .. kernel-doc:: drivers/fpga/fpga-bridge.c :functions: fpga_bridge_unregister diff --git a/Documentation/driver-api/fpga/fpga-mgr.rst b/Documentation/driver-api/fpga/fpga-mgr.rst index 49c0a951265320..8d2b79f696c1fb 100644 --- a/Documentation/driver-api/fpga/fpga-mgr.rst +++ b/Documentation/driver-api/fpga/fpga-mgr.rst @@ -24,7 +24,8 @@ How to support a new FPGA device -------------------------------- To add another FPGA manager, write a driver that implements a set of ops. The -probe function calls fpga_mgr_register() or fpga_mgr_register_full(), such as:: +probe function calls ``fpga_mgr_register()`` or ``fpga_mgr_register_full()``, +such as:: static const struct fpga_manager_ops socfpga_fpga_ops = { .write_init = socfpga_fpga_ops_configure_init, @@ -69,10 +70,11 @@ probe function calls fpga_mgr_register() or fpga_mgr_register_full(), such as:: } Alternatively, the probe function could call one of the resource managed -register functions, devm_fpga_mgr_register() or devm_fpga_mgr_register_full(). -When these functions are used, the parameter syntax is the same, but the call -to fpga_mgr_unregister() should be removed. In the above example, the -socfpga_fpga_remove() function would not be required. +register functions, ``devm_fpga_mgr_register()`` or +``devm_fpga_mgr_register_full()``. When these functions are used, the +parameter syntax is the same, but the call to ``fpga_mgr_unregister()`` should be +removed. In the above example, the ``socfpga_fpga_remove()`` function would not be +required. The ops will implement whatever device specific register writes are needed to do the programming sequence for this particular FPGA. These ops return 0 for @@ -125,15 +127,19 @@ API for implementing a new FPGA Manager driver * struct fpga_manager - the FPGA manager struct * struct fpga_manager_ops - Low level FPGA manager driver ops * struct fpga_manager_info - Parameter structure for fpga_mgr_register_full() -* fpga_mgr_register_full() - Create and register an FPGA manager using the +* __fpga_mgr_register_full() - Create and register an FPGA manager using the fpga_mgr_info structure to provide the full flexibility of options -* fpga_mgr_register() - Create and register an FPGA manager using standard +* __fpga_mgr_register() - Create and register an FPGA manager using standard arguments -* devm_fpga_mgr_register_full() - Resource managed version of - fpga_mgr_register_full() -* devm_fpga_mgr_register() - Resource managed version of fpga_mgr_register() +* __devm_fpga_mgr_register_full() - Resource managed version of + __fpga_mgr_register_full() +* __devm_fpga_mgr_register() - Resource managed version of __fpga_mgr_register() * fpga_mgr_unregister() - Unregister an FPGA manager +Helper macros ``fpga_mgr_register_full()``, ``fpga_mgr_register()``, +``devm_fpga_mgr_register_full()``, and ``devm_fpga_mgr_register()`` are available +to ease the registration. + .. kernel-doc:: include/linux/fpga/fpga-mgr.h :functions: fpga_mgr_states @@ -147,16 +153,16 @@ API for implementing a new FPGA Manager driver :functions: fpga_manager_info .. kernel-doc:: drivers/fpga/fpga-mgr.c - :functions: fpga_mgr_register_full + :functions: __fpga_mgr_register_full .. kernel-doc:: drivers/fpga/fpga-mgr.c - :functions: fpga_mgr_register + :functions: __fpga_mgr_register .. kernel-doc:: drivers/fpga/fpga-mgr.c - :functions: devm_fpga_mgr_register_full + :functions: __devm_fpga_mgr_register_full .. kernel-doc:: drivers/fpga/fpga-mgr.c - :functions: devm_fpga_mgr_register + :functions: __devm_fpga_mgr_register .. kernel-doc:: drivers/fpga/fpga-mgr.c :functions: fpga_mgr_unregister diff --git a/Documentation/driver-api/fpga/fpga-region.rst b/Documentation/driver-api/fpga/fpga-region.rst index dc55d60a0b4a51..2d03b5fb765755 100644 --- a/Documentation/driver-api/fpga/fpga-region.rst +++ b/Documentation/driver-api/fpga/fpga-region.rst @@ -46,13 +46,16 @@ API to add a new FPGA region ---------------------------- * struct fpga_region - The FPGA region struct -* struct fpga_region_info - Parameter structure for fpga_region_register_full() -* fpga_region_register_full() - Create and register an FPGA region using the +* struct fpga_region_info - Parameter structure for __fpga_region_register_full() +* __fpga_region_register_full() - Create and register an FPGA region using the fpga_region_info structure to provide the full flexibility of options -* fpga_region_register() - Create and register an FPGA region using standard +* __fpga_region_register() - Create and register an FPGA region using standard arguments * fpga_region_unregister() - Unregister an FPGA region +Helper macros ``fpga_region_register()`` and ``fpga_region_register_full()`` +automatically set the module that registers the FPGA region as the owner. + The FPGA region's probe function will need to get a reference to the FPGA Manager it will be using to do the programming. This usually would happen during the region's probe function. @@ -82,10 +85,10 @@ following APIs to handle building or tearing down that list. :functions: fpga_region_info .. kernel-doc:: drivers/fpga/fpga-region.c - :functions: fpga_region_register_full + :functions: __fpga_region_register_full .. kernel-doc:: drivers/fpga/fpga-region.c - :functions: fpga_region_register + :functions: __fpga_region_register .. kernel-doc:: drivers/fpga/fpga-region.c :functions: fpga_region_unregister diff --git a/Documentation/driver-api/ipmi.rst b/Documentation/driver-api/ipmi.rst index e224e47b6b0944..dfa021eacd63c4 100644 --- a/Documentation/driver-api/ipmi.rst +++ b/Documentation/driver-api/ipmi.rst @@ -540,7 +540,7 @@ at module load time (for a module) with:: alerts_broken The addresses are normal I2C addresses. The adapter is the string -name of the adapter, as shown in /sys/class/i2c-adapter/i2c-/name. +name of the adapter, as shown in /sys/bus/i2c/devices/i2c-/name. It is *NOT* i2c- itself. Also, the comparison is done ignoring spaces, so if the name is "This is an I2C chip" you can say adapter_name=ThisisanI2cchip. This is because it's hard to pass in diff --git a/Documentation/driver-api/pci/p2pdma.rst b/Documentation/driver-api/pci/p2pdma.rst index 44deb52beeb476..d0b241628cf13d 100644 --- a/Documentation/driver-api/pci/p2pdma.rst +++ b/Documentation/driver-api/pci/p2pdma.rst @@ -83,19 +83,9 @@ this to include other types of resources like doorbells. Client Drivers -------------- -A client driver typically only has to conditionally change its DMA map -routine to use the mapping function :c:func:`pci_p2pdma_map_sg()` instead -of the usual :c:func:`dma_map_sg()` function. Memory mapped in this -way does not need to be unmapped. - -The client may also, optionally, make use of -:c:func:`is_pci_p2pdma_page()` to determine when to use the P2P mapping -functions and when to use the regular mapping functions. In some -situations, it may be more appropriate to use a flag to indicate a -given request is P2P memory and map appropriately. It is important to -ensure that struct pages that back P2P memory stay out of code that -does not have support for them as other code may treat the pages as -regular memory which may not be appropriate. +A client driver only has to use the mapping API :c:func:`dma_map_sg()` +and :c:func:`dma_unmap_sg()` functions as usual, and the implementation +will do the right thing for the P2P capable memory. Orchestrator Drivers diff --git a/Documentation/driver-api/pwm.rst b/Documentation/driver-api/pwm.rst index 3fdc95f7a1d159..ed5ec98165381f 100644 --- a/Documentation/driver-api/pwm.rst +++ b/Documentation/driver-api/pwm.rst @@ -41,7 +41,7 @@ the getter, devm_pwm_get() and devm_fwnode_pwm_get(), also exist. After being requested, a PWM has to be configured using:: - int pwm_apply_state(struct pwm_device *pwm, struct pwm_state *state); + int pwm_apply_might_sleep(struct pwm_device *pwm, struct pwm_state *state); This API controls both the PWM period/duty_cycle config and the enable/disable state. @@ -57,13 +57,13 @@ If supported by the driver, the signal can be optimized, for example to improve EMI by phase shifting the individual channels of a chip. The pwm_config(), pwm_enable() and pwm_disable() functions are just wrappers -around pwm_apply_state() and should not be used if the user wants to change +around pwm_apply_might_sleep() and should not be used if the user wants to change several parameter at once. For example, if you see pwm_config() and pwm_{enable,disable}() calls in the same function, this probably means you -should switch to pwm_apply_state(). +should switch to pwm_apply_might_sleep(). The PWM user API also allows one to query the PWM state that was passed to the -last invocation of pwm_apply_state() using pwm_get_state(). Note this is +last invocation of pwm_apply_might_sleep() using pwm_get_state(). Note this is different to what the driver has actually implemented if the request cannot be satisfied exactly with the hardware in use. There is currently no way for consumers to get the actually implemented settings. diff --git a/Documentation/filesystems/directory-locking.rst b/Documentation/filesystems/directory-locking.rst index dccd61c7c5c3be..193c22687851a7 100644 --- a/Documentation/filesystems/directory-locking.rst +++ b/Documentation/filesystems/directory-locking.rst @@ -22,13 +22,16 @@ exclusive. 3) object removal. Locking rules: caller locks parent, finds victim, locks victim and calls the method. Locks are exclusive. -4) rename() that is _not_ cross-directory. Locking rules: caller locks the -parent and finds source and target. We lock both (provided they exist). If we -need to lock two inodes of different type (dir vs non-dir), we lock directory -first. If we need to lock two inodes of the same type, lock them in inode -pointer order. Then call the method. All locks are exclusive. -NB: we might get away with locking the source (and target in exchange -case) shared. +4) rename() that is _not_ cross-directory. Locking rules: caller locks +the parent and finds source and target. Then we decide which of the +source and target need to be locked. Source needs to be locked if it's a +non-directory; target - if it's a non-directory or about to be removed. +Take the locks that need to be taken, in inode pointer order if need +to take both (that can happen only when both source and target are +non-directories - the source because it wouldn't be locked otherwise +and the target because mixing directory and non-directory is allowed +only with RENAME_EXCHANGE, and that won't be removing the target). +After the locks had been taken, call the method. All locks are exclusive. 5) link creation. Locking rules: @@ -44,20 +47,17 @@ rules: * lock the filesystem * lock parents in "ancestors first" order. If one is not ancestor of - the other, lock them in inode pointer order. + the other, lock the parent of source first. * find source and target. * if old parent is equal to or is a descendent of target fail with -ENOTEMPTY * if new parent is equal to or is a descendent of source fail with -ELOOP - * Lock both the source and the target provided they exist. If we - need to lock two inodes of different type (dir vs non-dir), we lock - the directory first. If we need to lock two inodes of the same type, - lock them in inode pointer order. + * Lock subdirectories involved (source before target). + * Lock non-directories involved, in inode pointer order. * call the method. -All ->i_rwsem are taken exclusive. Again, we might get away with locking -the source (and target in exchange case) shared. +All ->i_rwsem are taken exclusive. The rules above obviously guarantee that all directories that are going to be read, modified or removed by method will be locked by caller. @@ -67,6 +67,7 @@ If no directory is its own ancestor, the scheme above is deadlock-free. Proof: +[XXX: will be updated once we are done massaging the lock_rename()] First of all, at any moment we have a linear ordering of the objects - A < B iff (A is an ancestor of B) or (B is not an ancestor of A and ptr(A) < ptr(B)). diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst index d32c6209685d64..dbfbbe9ab28b12 100644 --- a/Documentation/filesystems/f2fs.rst +++ b/Documentation/filesystems/f2fs.rst @@ -126,9 +126,7 @@ norecovery Disable the roll-forward recovery routine, mounted read- discard/nodiscard Enable/disable real-time discard in f2fs, if discard is enabled, f2fs will issue discard/TRIM commands when a segment is cleaned. -no_heap Disable heap-style segment allocation which finds free - segments for data from the beginning of main area, while - for node from the end of main area. +heap/no_heap Deprecated. nouser_xattr Disable Extended User Attributes. Note: xattr is enabled by default if CONFIG_F2FS_FS_XATTR is selected. noacl Disable POSIX Access Control List. Note: acl is enabled @@ -228,8 +226,6 @@ mode=%s Control block allocation mode which supports "adaptive" option for more randomness. Please, use these options for your experiments and we strongly recommend to re-format the filesystem after using these options. -io_bits=%u Set the bit size of write IO requests. It should be set - with "mode=lfs". usrquota Enable plain user disk quota accounting. grpquota Enable plain group disk quota accounting. prjquota Enable plain project quota accounting. diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 7be2900806c853..bd12f2f850ad3a 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -101,7 +101,7 @@ symlink: exclusive mkdir: exclusive unlink: exclusive (both) rmdir: exclusive (both)(see below) -rename: exclusive (all) (see below) +rename: exclusive (both parents, some children) (see below) readlink: no get_link: no setattr: exclusive @@ -123,6 +123,9 @@ get_offset_ctx no Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_rwsem exclusive on victim. cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem. + ->unlink() and ->rename() have ->i_rwsem exclusive on all non-directories + involved. + ->rename() has ->i_rwsem exclusive on any subdirectory that changes parent. See Documentation/filesystems/directory-locking.rst for more detailed discussion of the locking scheme for directory operations. diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst index 5b93268e400f4c..56a5ad7a4fbd20 100644 --- a/Documentation/filesystems/overlayfs.rst +++ b/Documentation/filesystems/overlayfs.rst @@ -344,10 +344,11 @@ escaping the colons with a single backslash. For example: mount -t overlay overlay -olowerdir=/a\:lower\:\:dir /merged -Since kernel version v6.5, directory names containing colons can also -be provided as lower layer using the fsconfig syscall from new mount api: +Since kernel version v6.8, directory names containing colons can also +be configured as lower layer using the "lowerdir+" mount options and the +fsconfig syscall from new mount api. For example: - fsconfig(fs_fd, FSCONFIG_SET_STRING, "lowerdir", "/a:lower::dir", 0); + fsconfig(fs_fd, FSCONFIG_SET_STRING, "lowerdir+", "/a:lower::dir", 0); In the latter case, colons in lower layer directory names will be escaped as an octal characters (\072) when displayed in /proc/self/mountinfo. @@ -416,6 +417,16 @@ Only the data of the files in the "data-only" lower layers may be visible when a "metacopy" file in one of the lower layers above it, has a "redirect" to the absolute path of the "lower data" file in the "data-only" lower layer. +Since kernel version v6.8, "data-only" lower layers can also be added using +the "datadir+" mount options and the fsconfig syscall from new mount api. +For example: + + fsconfig(fs_fd, FSCONFIG_SET_STRING, "lowerdir+", "/l1", 0); + fsconfig(fs_fd, FSCONFIG_SET_STRING, "lowerdir+", "/l2", 0); + fsconfig(fs_fd, FSCONFIG_SET_STRING, "lowerdir+", "/l3", 0); + fsconfig(fs_fd, FSCONFIG_SET_STRING, "datadir+", "/do1", 0); + fsconfig(fs_fd, FSCONFIG_SET_STRING, "datadir+", "/do2", 0); + fs-verity support ---------------------- diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index 4d05b9862451ea..41d964b48e6578 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -1045,3 +1045,21 @@ filesystem type is now moved to a later point when the devices are closed: As this is a VFS level change it has no practical consequences for filesystems other than that all of them must use one of the provided kill_litter_super(), kill_anon_super(), or kill_block_super() helpers. + +--- + +**mandatory** + +If ->rename() update of .. on cross-directory move needs an exclusion with +directory modifications, do *not* lock the subdirectory in question in your +->rename() - it's done by the caller now [that item should've been added in +28eceeda130f "fs: Lock moved directories"]. + +--- + +**mandatory** + +On same-directory ->rename() the (tautological) update of .. is not protected +by any locks; just don't do it if the old parent is the same as the new one. +We really can't lock two subdirectories in same-directory rename - not without +deadlocks. diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst index a0c83fc481264e..690d2ffe720eff 100644 --- a/Documentation/gpu/drm-kms.rst +++ b/Documentation/gpu/drm-kms.rst @@ -546,6 +546,8 @@ Plane Composition Properties .. kernel-doc:: drivers/gpu/drm/drm_blend.c :doc: overview +.. _damage_tracking_properties: + Damage Tracking Properties -------------------------- diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst index 03fe5d1247be28..85bbe05436098a 100644 --- a/Documentation/gpu/todo.rst +++ b/Documentation/gpu/todo.rst @@ -337,8 +337,8 @@ connector register/unregister fixes Level: Intermediate -Remove load/unload callbacks from all non-DRIVER_LEGACY drivers ---------------------------------------------------------------- +Remove load/unload callbacks +---------------------------- The load/unload callbacks in struct &drm_driver are very much midlayers, plus for historical reasons they get the ordering wrong (and we can't fix that) @@ -347,8 +347,7 @@ between setting up the &drm_driver structure and calling drm_dev_register(). - Rework drivers to no longer use the load/unload callbacks, directly coding the load/unload sequence into the driver's probe function. -- Once all non-DRIVER_LEGACY drivers are converted, disallow the load/unload - callbacks for all modern drivers. +- Once all drivers are converted, remove the load/unload callbacks. Contact: Daniel Vetter diff --git a/Documentation/hwmon/corsair-psu.rst b/Documentation/hwmon/corsair-psu.rst index 16db34d464dd6b..7ed794087f8489 100644 --- a/Documentation/hwmon/corsair-psu.rst +++ b/Documentation/hwmon/corsair-psu.rst @@ -15,11 +15,11 @@ Supported devices: Corsair HX850i - Corsair HX1000i (Series 2022 and 2023) + Corsair HX1000i (Legacy and Series 2023) - Corsair HX1200i + Corsair HX1200i (Legacy and Series 2023) - Corsair HX1500i (Series 2022 and 2023) + Corsair HX1500i (Legacy and Series 2023) Corsair RM550i diff --git a/Documentation/i2c/busses/i2c-i801.rst b/Documentation/i2c/busses/i2c-i801.rst index e76e68ccf7182c..10eced6c2e4625 100644 --- a/Documentation/i2c/busses/i2c-i801.rst +++ b/Documentation/i2c/busses/i2c-i801.rst @@ -47,6 +47,7 @@ Supported adapters: * Intel Alder Lake (PCH) * Intel Raptor Lake (PCH) * Intel Meteor Lake (SOC and PCH) + * Intel Birch Stream (SOC) Datasheets: Publicly available at the Intel website diff --git a/Documentation/kbuild/modules.rst b/Documentation/kbuild/modules.rst index a1f3eb7a43e235..131863142cbb35 100644 --- a/Documentation/kbuild/modules.rst +++ b/Documentation/kbuild/modules.rst @@ -128,7 +128,7 @@ executed to make module versioning work. modules_install Install the external module(s). The default location is - /lib/modules//extra/, but a prefix may + /lib/modules//updates/, but a prefix may be added with INSTALL_MOD_PATH (discussed in section 5). clean @@ -417,7 +417,7 @@ directory: And external modules are installed in: - /lib/modules/$(KERNELRELEASE)/extra/ + /lib/modules/$(KERNELRELEASE)/updates/ 5.1 INSTALL_MOD_PATH -------------------- @@ -438,10 +438,10 @@ And external modules are installed in: ------------------- External modules are by default installed to a directory under - /lib/modules/$(KERNELRELEASE)/extra/, but you may wish to + /lib/modules/$(KERNELRELEASE)/updates/, but you may wish to locate modules for a specific functionality in a separate directory. For this purpose, use INSTALL_MOD_DIR to specify an - alternative name to "extra.":: + alternative name to "updates.":: $ make INSTALL_MOD_DIR=gandalf -C $KDIR \ M=$PWD modules_install diff --git a/Documentation/locking/hwspinlock.rst b/Documentation/locking/hwspinlock.rst index 6f03713b700390..2ffaa3cbd63f16 100644 --- a/Documentation/locking/hwspinlock.rst +++ b/Documentation/locking/hwspinlock.rst @@ -85,6 +85,17 @@ is already free). Should be called from a process context (might sleep). +:: + + int hwspin_lock_bust(struct hwspinlock *hwlock, unsigned int id); + +After verifying the owner of the hwspinlock, release a previously acquired +hwspinlock; returns 0 on success, or an appropriate error code on failure +(e.g. -EOPNOTSUPP if the bust operation is not defined for the specific +hwspinlock). + +Should be called from a process context (might sleep). + :: int hwspin_lock_timeout(struct hwspinlock *hwlock, unsigned int timeout); diff --git a/Documentation/mm/arch_pgtable_helpers.rst b/Documentation/mm/arch_pgtable_helpers.rst index c82e3ee20e51ee..8c71249e7c4d05 100644 --- a/Documentation/mm/arch_pgtable_helpers.rst +++ b/Documentation/mm/arch_pgtable_helpers.rst @@ -142,7 +142,8 @@ PMD Page Table Helpers +---------------------------+--------------------------------------------------+ | pmd_swp_clear_soft_dirty | Clears a soft dirty swapped PMD | +---------------------------+--------------------------------------------------+ -| pmd_mkinvalid | Invalidates a mapped PMD [1] | +| pmd_mkinvalid | Invalidates a present PMD; do not call for | +| | non-present PMD [1] | +---------------------------+--------------------------------------------------+ | pmd_set_huge | Creates a PMD huge mapping | +---------------------------+--------------------------------------------------+ @@ -198,7 +199,8 @@ PUD Page Table Helpers +---------------------------+--------------------------------------------------+ | pud_mkdevmap | Creates a ZONE_DEVICE mapped PUD | +---------------------------+--------------------------------------------------+ -| pud_mkinvalid | Invalidates a mapped PUD [1] | +| pud_mkinvalid | Invalidates a present PUD; do not call for | +| | non-present PUD [1] | +---------------------------+--------------------------------------------------+ | pud_set_huge | Creates a PUD huge mapping | +---------------------------+--------------------------------------------------+ diff --git a/Documentation/mm/page_table_check.rst b/Documentation/mm/page_table_check.rst index c12838ce6b8de2..c59f22eb6a0f9a 100644 --- a/Documentation/mm/page_table_check.rst +++ b/Documentation/mm/page_table_check.rst @@ -14,7 +14,7 @@ Page table check performs extra verifications at the time when new pages become accessible from the userspace by getting their page table entries (PTEs PMDs etc.) added into the table. -In case of detected corruption, the kernel is crashed. There is a small +In case of most detected corruption, the kernel is crashed. There is a small performance and memory overhead associated with the page table check. Therefore, it is disabled by default, but can be optionally enabled on systems where the extra hardening outweighs the performance costs. Also, because page table check @@ -22,6 +22,13 @@ is synchronous, it can help with debugging double map memory corruption issues, by crashing kernel at the time wrong mapping occurs instead of later which is often the case with memory corruptions bugs. +It can also be used to do page table entry checks over various flags, dump +warnings when illegal combinations of entry flags are detected. Currently, +userfaultfd is the only user of such to sanity check wr-protect bit against +any writable flags. Illegal flag combinations will not directly cause data +corruption in this case immediately, but that will cause read-only data to +be writable, leading to corrupt when the page content is later modified. + Double mapping detection logic ============================== diff --git a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst index 5eaa3ab6c73e7f..b842bcb14255b5 100644 --- a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst +++ b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst @@ -54,6 +54,7 @@ ena_common_defs.h Common definitions for ena_com layer. ena_regs_defs.h Definition of ENA PCI memory-mapped (MMIO) registers. ena_netdev.[ch] Main Linux kernel driver. ena_ethtool.c ethtool callbacks. +ena_xdp.[ch] XDP files ena_pci_id_tbl.h Supported device IDs. ================= ====================================================== diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index e33ad2401ad70c..562f46b4127449 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -126,7 +126,7 @@ Users may also set the RoCE capability of the function using `devlink port function set roce` command. Users may also set the function as migratable using -'devlink port function set migratable' command. +`devlink port function set migratable` command. Users may also set the IPsec crypto capability of the function using `devlink port function set ipsec_crypto` command. diff --git a/Documentation/powerpc/features.rst b/Documentation/powerpc/features.rst index aeae73df86b0c5..ee4b95e04202d3 100644 --- a/Documentation/powerpc/features.rst +++ b/Documentation/powerpc/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features powerpc +.. kernel-feat:: features powerpc diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index b48da698d6f253..bb96ca0f774b9a 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -31,7 +31,7 @@ you probably needn't concern yourself with pcmciautils. ====================== =============== ======================================== GNU C 5.1 gcc --version Clang/LLVM (optional) 11.0.0 clang --version -Rust (optional) 1.71.1 rustc --version +Rust (optional) 1.73.0 rustc --version bindgen (optional) 0.65.1 bindgen --version GNU make 3.82 make --version bash 4.2 bash --version diff --git a/Documentation/riscv/features.rst b/Documentation/riscv/features.rst index c70ef6ac2368c9..36e90144adabd1 100644 --- a/Documentation/riscv/features.rst +++ b/Documentation/riscv/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features riscv +.. kernel-feat:: features riscv diff --git a/Documentation/sound/soc/dapm.rst b/Documentation/sound/soc/dapm.rst index 8e44107933abf5..c3154ce6e1b273 100644 --- a/Documentation/sound/soc/dapm.rst +++ b/Documentation/sound/soc/dapm.rst @@ -234,7 +234,7 @@ corresponding soft power control. In this case it is necessary to create a virtual widget - a widget with no control bits e.g. :: - SND_SOC_DAPM_MIXER("AC97 Mixer", SND_SOC_DAPM_NOPM, 0, 0, NULL, 0), + SND_SOC_DAPM_MIXER("AC97 Mixer", SND_SOC_NOPM, 0, 0, NULL, 0), This can be used to merge to signal paths together in software. diff --git a/Documentation/sphinx/cdomain.py b/Documentation/sphinx/cdomain.py index a99716bf44b553..de5d132d94c595 100644 --- a/Documentation/sphinx/cdomain.py +++ b/Documentation/sphinx/cdomain.py @@ -93,7 +93,7 @@ def markup_ctype_refs(match): # RE_expr = re.compile(r':c:(expr|texpr):`([^\`]+)`') def markup_c_expr(match): - return '\ ``' + match.group(2) + '``\ ' + return '\\ ``' + match.group(2) + '``\\ ' # # Parse Sphinx 3.x C markups, replacing them by backward-compatible ones diff --git a/Documentation/sphinx/kernel_abi.py b/Documentation/sphinx/kernel_abi.py index b5feb5b1d90548..5911bd0d796571 100644 --- a/Documentation/sphinx/kernel_abi.py +++ b/Documentation/sphinx/kernel_abi.py @@ -39,8 +39,6 @@ import sys import re import kernellog -from os import path - from docutils import nodes, statemachine from docutils.statemachine import ViewList from docutils.parsers.rst import directives, Directive @@ -73,60 +71,26 @@ class KernelCmd(Directive): } def run(self): - doc = self.state.document if not doc.settings.file_insertion_enabled: raise self.warning("docutils: file insertion disabled") - env = doc.settings.env - cwd = path.dirname(doc.current_source) - cmd = "get_abi.pl rest --enable-lineno --dir " - cmd += self.arguments[0] - - if 'rst' in self.options: - cmd += " --rst-source" + srctree = os.path.abspath(os.environ["srctree"]) - srctree = path.abspath(os.environ["srctree"]) + args = [ + os.path.join(srctree, 'scripts/get_abi.pl'), + 'rest', + '--enable-lineno', + '--dir', os.path.join(srctree, 'Documentation', self.arguments[0]), + ] - fname = cmd - - # extend PATH with $(srctree)/scripts - path_env = os.pathsep.join([ - srctree + os.sep + "scripts", - os.environ["PATH"] - ]) - shell_env = os.environ.copy() - shell_env["PATH"] = path_env - shell_env["srctree"] = srctree + if 'rst' in self.options: + args.append('--rst-source') - lines = self.runCmd(cmd, shell=True, cwd=cwd, env=shell_env) + lines = subprocess.check_output(args, cwd=os.path.dirname(doc.current_source)).decode('utf-8') nodeList = self.nestedParse(lines, self.arguments[0]) return nodeList - def runCmd(self, cmd, **kwargs): - u"""Run command ``cmd`` and return its stdout as unicode.""" - - try: - proc = subprocess.Popen( - cmd - , stdout = subprocess.PIPE - , stderr = subprocess.PIPE - , **kwargs - ) - out, err = proc.communicate() - - out, err = codecs.decode(out, 'utf-8'), codecs.decode(err, 'utf-8') - - if proc.returncode != 0: - raise self.severe( - u"command '%s' failed with return code %d" - % (cmd, proc.returncode) - ) - except OSError as exc: - raise self.severe(u"problems with '%s' directive: %s." - % (self.name, ErrorString(exc))) - return out - def nestedParse(self, lines, fname): env = self.state.document.settings.env content = ViewList() @@ -138,7 +102,7 @@ class KernelCmd(Directive): code_block += "\n " + l lines = code_block + "\n\n" - line_regex = re.compile("^\.\. LINENO (\S+)\#([0-9]+)$") + line_regex = re.compile(r"^\.\. LINENO (\S+)\#([0-9]+)$") ln = 0 n = 0 f = fname diff --git a/Documentation/sphinx/kernel_feat.py b/Documentation/sphinx/kernel_feat.py index 27b701ed3681ed..03ace5f01b5c02 100644 --- a/Documentation/sphinx/kernel_feat.py +++ b/Documentation/sphinx/kernel_feat.py @@ -37,8 +37,6 @@ import re import subprocess import sys -from os import path - from docutils import nodes, statemachine from docutils.statemachine import ViewList from docutils.parsers.rst import directives, Directive @@ -76,35 +74,28 @@ class KernelFeat(Directive): self.state.document.settings.env.app.warn(message, prefix="") def run(self): - doc = self.state.document if not doc.settings.file_insertion_enabled: raise self.warning("docutils: file insertion disabled") env = doc.settings.env - cwd = path.dirname(doc.current_source) - cmd = "get_feat.pl rest --enable-fname --dir " - cmd += self.arguments[0] - - if len(self.arguments) > 1: - cmd += " --arch " + self.arguments[1] - srctree = path.abspath(os.environ["srctree"]) + srctree = os.path.abspath(os.environ["srctree"]) - fname = cmd + args = [ + os.path.join(srctree, 'scripts/get_feat.pl'), + 'rest', + '--enable-fname', + '--dir', + os.path.join(srctree, 'Documentation', self.arguments[0]), + ] - # extend PATH with $(srctree)/scripts - path_env = os.pathsep.join([ - srctree + os.sep + "scripts", - os.environ["PATH"] - ]) - shell_env = os.environ.copy() - shell_env["PATH"] = path_env - shell_env["srctree"] = srctree + if len(self.arguments) > 1: + args.extend(['--arch', self.arguments[1]]) - lines = self.runCmd(cmd, shell=True, cwd=cwd, env=shell_env) + lines = subprocess.check_output(args, cwd=os.path.dirname(doc.current_source)).decode('utf-8') - line_regex = re.compile("^\.\. FILE (\S+)$") + line_regex = re.compile(r"^\.\. FILE (\S+)$") out_lines = "" @@ -118,33 +109,9 @@ class KernelFeat(Directive): else: out_lines += line + "\n" - nodeList = self.nestedParse(out_lines, fname) + nodeList = self.nestedParse(out_lines, self.arguments[0]) return nodeList - def runCmd(self, cmd, **kwargs): - u"""Run command ``cmd`` and return its stdout as unicode.""" - - try: - proc = subprocess.Popen( - cmd - , stdout = subprocess.PIPE - , stderr = subprocess.PIPE - , **kwargs - ) - out, err = proc.communicate() - - out, err = codecs.decode(out, 'utf-8'), codecs.decode(err, 'utf-8') - - if proc.returncode != 0: - raise self.severe( - u"command '%s' failed with return code %d" - % (cmd, proc.returncode) - ) - except OSError as exc: - raise self.severe(u"problems with '%s' directive: %s." - % (self.name, ErrorString(exc))) - return out - def nestedParse(self, lines, fname): content = ViewList() node = nodes.section() diff --git a/Documentation/sphinx/kernel_include.py b/Documentation/sphinx/kernel_include.py index abe7680883771d..6387624423363d 100755 --- a/Documentation/sphinx/kernel_include.py +++ b/Documentation/sphinx/kernel_include.py @@ -97,7 +97,6 @@ class KernelInclude(Include): # HINT: this is the only line I had to change / commented out: #path = utils.relative_path(None, path) - path = nodes.reprunicode(path) encoding = self.options.get( 'encoding', self.state.document.settings.input_encoding) e_handler=self.state.document.settings.input_encoding_error_handler diff --git a/Documentation/sphinx/kerneldoc.py b/Documentation/sphinx/kerneldoc.py index 9395892c7ba38b..8dc134904b9077 100644 --- a/Documentation/sphinx/kerneldoc.py +++ b/Documentation/sphinx/kerneldoc.py @@ -130,7 +130,7 @@ class KernelDocDirective(Directive): result = ViewList() lineoffset = 0; - line_regex = re.compile("^\.\. LINENO ([0-9]+)$") + line_regex = re.compile(r"^\.\. LINENO ([0-9]+)$") for line in lines: match = line_regex.search(line) if match: diff --git a/Documentation/sphinx/maintainers_include.py b/Documentation/sphinx/maintainers_include.py index 328b3631a585cd..dcad0fff4723ee 100755 --- a/Documentation/sphinx/maintainers_include.py +++ b/Documentation/sphinx/maintainers_include.py @@ -77,7 +77,7 @@ class MaintainersInclude(Include): line = line.rstrip() # Linkify all non-wildcard refs to ReST files in Documentation/. - pat = '(Documentation/([^\s\?\*]*)\.rst)' + pat = r'(Documentation/([^\s\?\*]*)\.rst)' m = re.search(pat, line) if m: # maintainers.rst is in a subdirectory, so include "../". @@ -90,11 +90,11 @@ class MaintainersInclude(Include): output = "| %s" % (line.replace("\\", "\\\\")) # Look for and record field letter to field name mappings: # R: Designated *reviewer*: FullName - m = re.search("\s(\S):\s", line) + m = re.search(r"\s(\S):\s", line) if m: field_letter = m.group(1) if field_letter and not field_letter in fields: - m = re.search("\*([^\*]+)\*", line) + m = re.search(r"\*([^\*]+)\*", line) if m: fields[field_letter] = m.group(1) elif subsystems: @@ -112,7 +112,7 @@ class MaintainersInclude(Include): field_content = "" # Collapse whitespace in subsystem name. - heading = re.sub("\s+", " ", line) + heading = re.sub(r"\s+", " ", line) output = output + "%s\n%s" % (heading, "~" * len(heading)) field_prev = "" else: diff --git a/Documentation/translations/zh_CN/arch/loongarch/features.rst b/Documentation/translations/zh_CN/arch/loongarch/features.rst index 82bfac180bdc04..cec38dda8298c1 100644 --- a/Documentation/translations/zh_CN/arch/loongarch/features.rst +++ b/Documentation/translations/zh_CN/arch/loongarch/features.rst @@ -5,4 +5,4 @@ :Original: Documentation/arch/loongarch/features.rst :Translator: Huacai Chen -.. kernel-feat:: $srctree/Documentation/features loongarch +.. kernel-feat:: features loongarch diff --git a/Documentation/translations/zh_CN/arch/mips/features.rst b/Documentation/translations/zh_CN/arch/mips/features.rst index da1b956e4a40f6..0d6df97db069bb 100644 --- a/Documentation/translations/zh_CN/arch/mips/features.rst +++ b/Documentation/translations/zh_CN/arch/mips/features.rst @@ -10,4 +10,4 @@ .. _cn_features: -.. kernel-feat:: $srctree/Documentation/features mips +.. kernel-feat:: features mips diff --git a/Documentation/translations/zh_TW/dev-tools/index.rst b/Documentation/translations/zh_TW/dev-tools/index.rst new file mode 100644 index 00000000000000..8f101db5a07fff --- /dev/null +++ b/Documentation/translations/zh_TW/dev-tools/index.rst @@ -0,0 +1,40 @@ +.. include:: ../disclaimer-zh_TW.rst + +:Original: Documentation/dev-tools/index.rst +:Translator: Min-Hua Chen + +============ +內核開發工具 +============ + +本文檔是有關內核開發工具文檔的合集。 +目前這些文檔已經整理在一起，不需要再花費額外的精力。 +歡迎任何補丁。 + +有關測試專用工具的簡要概述，參見 +Documentation/dev-tools/testing-overview.rst + +.. class:: toc-title + + 目錄 + +.. toctree:: + :maxdepth: 2 + + sparse + +Todolist: + + - coccinelle + - kcov + - ubsan + - kmemleak + - kcsan + - kfence + - kgdb + - kselftest + - kunit/index + - testing-overview + - gcov + - kasan + - gdb-kernel-debugging diff --git a/Documentation/translations/zh_TW/dev-tools/sparse.txt b/Documentation/translations/zh_TW/dev-tools/sparse.txt new file mode 100644 index 00000000000000..35d3d1d748e6f1 --- /dev/null +++ b/Documentation/translations/zh_TW/dev-tools/sparse.txt @@ -0,0 +1,91 @@ +Chinese translated version of Documentation/dev-tools/sparse.rst + +If you have any comment or update to the content, please contact the +original document maintainer directly. However, if you have a problem +communicating in English you can also ask the Chinese maintainer for +help. Contact the Chinese maintainer if this translation is outdated +or if there is a problem with the translation. + +Traditional Chinese maintainer: Hu Haowen +--------------------------------------------------------------------- +Documentation/dev-tools/sparse.rst 的繁體中文翻譯 + +如果想評論或更新本文的內容，請直接聯繫原文檔的維護者。如果你使用英文 +交流有困難的話，也可以向繁體中文版維護者求助。如果本翻譯更新不及時或 +者翻譯存在問題，請聯繫繁體中文版維護者。 + +繁體中文版維護者： 胡皓文 Hu Haowen +繁體中文版翻譯者： 胡皓文 Hu Haowen + +以下爲正文 +--------------------------------------------------------------------- + +Copyright 2004 Linus Torvalds +Copyright 2004 Pavel Machek +Copyright 2006 Bob Copeland + +使用 sparse 工具做類型檢查 +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +"__bitwise" 是一種類型屬性，所以你應該這樣使用它： + + typedef int __bitwise pm_request_t; + + enum pm_request { + PM_SUSPEND = (__force pm_request_t) 1, + PM_RESUME = (__force pm_request_t) 2 + }; + +這樣會使 PM_SUSPEND 和 PM_RESUME 成爲位方式(bitwise)整數（使用"__force" +是因爲 sparse 會抱怨改變位方式的類型轉換，但是這裡我們確實需要強制進行轉 +換）。而且因爲所有枚舉值都使用了相同的類型，這裡的"enum pm_request"也將 +會使用那個類型做爲底層實現。 + +而且使用 gcc 編譯的時候，所有的 __bitwise/__force 都會消失，最後在 gcc +看來它們只不過是普通的整數。 + +坦白來說，你並不需要使用枚舉類型。上面那些實際都可以濃縮成一個特殊的"int +__bitwise"類型。 + +所以更簡單的辦法只要這樣做： + + typedef int __bitwise pm_request_t; + + #define PM_SUSPEND ((__force pm_request_t) 1) + #define PM_RESUME ((__force pm_request_t) 2) + +現在你就有了嚴格的類型檢查所需要的所有基礎架構。 + +一個小提醒：常數整數"0"是特殊的。你可以直接把常數零當作位方式整數使用而 +不用擔心 sparse 會抱怨。這是因爲"bitwise"（恰如其名）是用來確保不同位方 +式類型不會被弄混（小尾模式，大尾模式，cpu尾模式，或者其他），對他們來說 +常數"0"確實是特殊的。 + +獲取 sparse 工具 +~~~~~~~~~~~~~~~~ + +你可以從 Sparse 的主頁獲取最新的發布版本： + + https://www.kernel.org/pub/software/devel/sparse/dist/ + +或者，你也可以使用 git 克隆最新的 sparse 開發版本： + + git://git.kernel.org/pub/scm/devel/sparse/sparse.git + +一旦你下載了源碼，只要以普通用戶身份運行： + + make + make install + +它將會被自動安裝到你的 ~/bin 目錄下。 + +使用 sparse 工具 +~~~~~~~~~~~~~~~~ + +用"make C=1"命令來編譯內核，會對所有重新編譯的 C 文件使用 sparse 工具。 +或者使用"make C=2"命令，無論文件是否被重新編譯都會對其使用 sparse 工具。 +如果你已經編譯了內核，用後一種方式可以很快地檢查整個源碼樹。 + +make 的可選變量 CHECKFLAGS 可以用來向 sparse 工具傳遞參數。編譯系統會自 +動向 sparse 工具傳遞 -Wbitwise 參數。 + diff --git a/Documentation/translations/zh_TW/index.rst b/Documentation/translations/zh_TW/index.rst index d1cf0b4d8e46d9..ffcaf3272fe70a 100644 --- a/Documentation/translations/zh_TW/index.rst +++ b/Documentation/translations/zh_TW/index.rst @@ -55,11 +55,11 @@ TODOList: :maxdepth: 1 process/license-rules + dev-tools/index TODOList: * doc-guide/index -* dev-tools/index * dev-tools/testing-overview * kernel-hacking/index * rust/index diff --git a/Documentation/translations/zh_TW/sparse.txt b/Documentation/translations/zh_TW/sparse.txt deleted file mode 100644 index 35d3d1d748e6f1..00000000000000 --- a/Documentation/translations/zh_TW/sparse.txt +++ /dev/null @@ -1,91 +0,0 @@ -Chinese translated version of Documentation/dev-tools/sparse.rst - -If you have any comment or update to the content, please contact the -original document maintainer directly. However, if you have a problem -communicating in English you can also ask the Chinese maintainer for -help. Contact the Chinese maintainer if this translation is outdated -or if there is a problem with the translation. - -Traditional Chinese maintainer: Hu Haowen ---------------------------------------------------------------------- -Documentation/dev-tools/sparse.rst 的繁體中文翻譯 - -如果想評論或更新本文的內容，請直接聯繫原文檔的維護者。如果你使用英文 -交流有困難的話，也可以向繁體中文版維護者求助。如果本翻譯更新不及時或 -者翻譯存在問題，請聯繫繁體中文版維護者。 - -繁體中文版維護者： 胡皓文 Hu Haowen -繁體中文版翻譯者： 胡皓文 Hu Haowen - -以下爲正文 ---------------------------------------------------------------------- - -Copyright 2004 Linus Torvalds -Copyright 2004 Pavel Machek -Copyright 2006 Bob Copeland - -使用 sparse 工具做類型檢查 -~~~~~~~~~~~~~~~~~~~~~~~~~~ - -"__bitwise" 是一種類型屬性，所以你應該這樣使用它： - - typedef int __bitwise pm_request_t; - - enum pm_request { - PM_SUSPEND = (__force pm_request_t) 1, - PM_RESUME = (__force pm_request_t) 2 - }; - -這樣會使 PM_SUSPEND 和 PM_RESUME 成爲位方式(bitwise)整數（使用"__force" -是因爲 sparse 會抱怨改變位方式的類型轉換，但是這裡我們確實需要強制進行轉 -換）。而且因爲所有枚舉值都使用了相同的類型，這裡的"enum pm_request"也將 -會使用那個類型做爲底層實現。 - -而且使用 gcc 編譯的時候，所有的 __bitwise/__force 都會消失，最後在 gcc -看來它們只不過是普通的整數。 - -坦白來說，你並不需要使用枚舉類型。上面那些實際都可以濃縮成一個特殊的"int -__bitwise"類型。 - -所以更簡單的辦法只要這樣做： - - typedef int __bitwise pm_request_t; - - #define PM_SUSPEND ((__force pm_request_t) 1) - #define PM_RESUME ((__force pm_request_t) 2) - -現在你就有了嚴格的類型檢查所需要的所有基礎架構。 - -一個小提醒：常數整數"0"是特殊的。你可以直接把常數零當作位方式整數使用而 -不用擔心 sparse 會抱怨。這是因爲"bitwise"（恰如其名）是用來確保不同位方 -式類型不會被弄混（小尾模式，大尾模式，cpu尾模式，或者其他），對他們來說 -常數"0"確實是特殊的。 - -獲取 sparse 工具 -~~~~~~~~~~~~~~~~ - -你可以從 Sparse 的主頁獲取最新的發布版本： - - https://www.kernel.org/pub/software/devel/sparse/dist/ - -或者，你也可以使用 git 克隆最新的 sparse 開發版本： - - git://git.kernel.org/pub/scm/devel/sparse/sparse.git - -一旦你下載了源碼，只要以普通用戶身份運行： - - make - make install - -它將會被自動安裝到你的 ~/bin 目錄下。 - -使用 sparse 工具 -~~~~~~~~~~~~~~~~ - -用"make C=1"命令來編譯內核，會對所有重新編譯的 C 文件使用 sparse 工具。 -或者使用"make C=2"命令，無論文件是否被重新編譯都會對其使用 sparse 工具。 -如果你已經編譯了內核，用後一種方式可以很快地檢查整個源碼樹。 - -make 的可選變量 CHECKFLAGS 可以用來向 sparse 工具傳遞參數。編譯系統會自 -動向 sparse 工具傳遞 -Wbitwise 參數。 - diff --git a/Documentation/userspace-api/media/mediactl/media-types.rst b/Documentation/userspace-api/media/mediactl/media-types.rst index 0ffeece1e0c8e9..6332e8395263b0 100644 --- a/Documentation/userspace-api/media/mediactl/media-types.rst +++ b/Documentation/userspace-api/media/mediactl/media-types.rst @@ -375,12 +375,11 @@ Types and flags used to represent the media graph elements are origins of links. * - ``MEDIA_PAD_FL_MUST_CONNECT`` - - If this flag is set and the pad is linked to any other pad, then - at least one of those links must be enabled for the entity to be - able to stream. There could be temporary reasons (e.g. device - configuration dependent) for the pad to need enabled links even - when this flag isn't set; the absence of the flag doesn't imply - there is none. + - If this flag is set, then for this pad to be able to stream, it must + be connected by at least one enabled link. There could be temporary + reasons (e.g. device configuration dependent) for the pad to need + enabled links even when this flag isn't set; the absence of the flag + doesn't imply there is none. One and only one of ``MEDIA_PAD_FL_SINK`` and ``MEDIA_PAD_FL_SOURCE`` diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 3a034db5e55f89..887d9d2fed492b 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -9,7 +9,7 @@ KVM Lock Overview The acquisition orders for mutexes are as follows: -- cpus_read_lock() is taken outside kvm_lock +- cpus_read_lock() is taken outside kvm_lock and kvm_usage_lock - kvm->lock is taken outside vcpu->mutex @@ -24,6 +24,13 @@ The acquisition orders for mutexes are as follows: are taken on the waiting side when modifying memslots, so MMU notifiers must not take either kvm->slots_lock or kvm->slots_arch_lock. +cpus_read_lock() vs kvm_lock: + +- Taking cpus_read_lock() outside of kvm_lock is problematic, despite that + being the official ordering, as it is quite easy to unknowingly trigger + cpus_read_lock() while holding kvm_lock. Use caution when walking vm_list, + e.g. avoid complex operations when possible. + For SRCU: - ``synchronize_srcu(&kvm->srcu)`` is called inside critical sections @@ -228,10 +235,17 @@ time it will be set using the Dirty tracking mechanism described above. :Type: mutex :Arch: any :Protects: - vm_list - - kvm_usage_count + +``kvm_usage_lock`` +^^^^^^^^^^^^^^^^^^ + +:Type: mutex +:Arch: any +:Protects: - kvm_usage_count - hardware virtualization enable/disable -:Comment: KVM also disables CPU hotplug via cpus_read_lock() during - enable/disable. +:Comment: Exists because using kvm_lock leads to deadlock (see earlier comment + on cpus_read_lock() vs kvm_lock). Note, KVM also disables CPU hotplug via + cpus_read_lock() when enabling/disabling virtualization. ``kvm->mn_invalidate_lock`` ^^^^^^^^^^^^^^^^^^^^^^^^^^^ @@ -291,11 +305,12 @@ time it will be set using the Dirty tracking mechanism described above. wakeup. ``vendor_module_lock`` -^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +^^^^^^^^^^^^^^^^^^^^^^ :Type: mutex :Arch: x86 :Protects: loading a vendor module (kvm_amd or kvm_intel) -:Comment: Exists because using kvm_lock leads to deadlock. cpu_hotplug_lock is - taken outside of kvm_lock, e.g. in KVM's CPU online/offline callbacks, and - many operations need to take cpu_hotplug_lock when loading a vendor module, - e.g. updating static calls. +:Comment: Exists because using kvm_lock leads to deadlock. kvm_lock is taken + in notifiers, e.g. __kvmclock_cpufreq_notifier(), that may be invoked while + cpu_hotplug_lock is held, e.g. from cpufreq_boost_trigger_state(), and many + operations need to take cpu_hotplug_lock when loading a vendor module, e.g. + updating static calls. diff --git a/MAINTAINERS b/MAINTAINERS index dd5de540ec0b52..ae4c0cec507360 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8142,7 +8142,7 @@ M: Geoffrey D. Bennett L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git -F: sound/usb/mixer_scarlett_gen2.c +F: sound/usb/mixer_scarlett2.c FORCEDETH GIGABIT ETHERNET DRIVER M: Rain River @@ -10157,6 +10157,14 @@ L: linux-media@vger.kernel.org S: Maintained F: drivers/media/rc/iguanair.c +IIO BACKEND FRAMEWORK +M: Nuno Sa +R: Olivier Moysan +L: linux-iio@vger.kernel.org +S: Maintained +F: drivers/iio/industrialio-backend.c +F: include/linux/iio/backend.h + IIO DIGITAL POTENTIOMETER DAC M: Peter Rosin L: linux-iio@vger.kernel.org @@ -13694,7 +13702,7 @@ M: Mathieu Desnoyers M: "Paul E. McKenney" L: linux-kernel@vger.kernel.org S: Supported -F: arch/powerpc/include/asm/membarrier.h +F: arch/*/include/asm/membarrier.h F: include/uapi/linux/membarrier.h F: kernel/sched/membarrier.c @@ -17380,7 +17388,7 @@ F: drivers/video/backlight/pwm_bl.c F: include/dt-bindings/pwm/ F: include/linux/pwm.h F: include/linux/pwm_backlight.h -K: pwm_(config|apply_state|ops) +K: pwm_(config|apply_might_sleep|ops) PXA GPIO DRIVER M: Robert Jarzmik @@ -23630,6 +23638,7 @@ F: include/xen/arm/swiotlb-xen.h F: include/xen/swiotlb-xen.h XFS FILESYSTEM +M: Catherine Hoang M: Chandan Babu R R: Darrick J. Wong L: linux-xfs@vger.kernel.org diff --git a/Makefile b/Makefile index 5c418efbe89b6c..f80e78c7cf2006 100644 --- a/Makefile +++ b/Makefile @@ -1,9 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 6 -SUBLEVEL = 0 +SUBLEVEL = 58 EXTRAVERSION = -NAME = Hurr durr I'ma ninja sloth +NAME = Pinguïn Aangedreven # *DOCUMENTATION* # To see a list of typical targets execute "make help" @@ -951,7 +951,6 @@ endif ifdef CONFIG_LTO_CLANG ifdef CONFIG_LTO_CLANG_THIN CC_FLAGS_LTO := -flto=thin -fsplit-lto-unit -KBUILD_LDFLAGS += --thinlto-cache-dir=$(extmod_prefix).thinlto-cache else CC_FLAGS_LTO := -flto endif @@ -1317,6 +1316,14 @@ scripts_unifdef: scripts_basic quiet_cmd_install = INSTALL $(INSTALL_PATH) cmd_install = unset sub_make_done; $(srctree)/scripts/install.sh +# --------------------------------------------------------------------------- +# vDSO install + +PHONY += vdso_install +vdso_install: export INSTALL_FILES = $(vdso-install-y) +vdso_install: + $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.vdsoinst + # --------------------------------------------------------------------------- # Tools @@ -1474,7 +1481,7 @@ endif # CONFIG_MODULES # Directories & files removed with 'make clean' CLEAN_FILES += vmlinux.symvers modules-only.symvers \ modules.builtin modules.builtin.modinfo modules.nsdeps \ - compile_commands.json .thinlto-cache rust/test \ + compile_commands.json rust/test \ rust-project.json .vmlinux.objs .vmlinux.export.c # Directories & files removed with 'make mrproper' @@ -1560,6 +1567,7 @@ help: @echo '* vmlinux - Build the bare kernel' @echo '* modules - Build all modules' @echo ' modules_install - Install all modules to INSTALL_MOD_PATH (default: /)' + @echo ' vdso_install - Install unstripped vdso to INSTALL_MOD_PATH (default: /)' @echo ' dir/ - Build all files in dir and below' @echo ' dir/file.[ois] - Build specified target only' @echo ' dir/file.ll - Build the LLVM assembly file' @@ -1777,7 +1785,7 @@ PHONY += compile_commands.json clean-dirs := $(KBUILD_EXTMOD) clean: rm-files := $(KBUILD_EXTMOD)/Module.symvers $(KBUILD_EXTMOD)/modules.nsdeps \ - $(KBUILD_EXTMOD)/compile_commands.json $(KBUILD_EXTMOD)/.thinlto-cache + $(KBUILD_EXTMOD)/compile_commands.json PHONY += prepare # now expand this into a simple variable to reduce the cost of shell evaluations diff --git a/arch/Kconfig b/arch/Kconfig index 12d51495caec18..09603e0bc2cc16 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -9,6 +9,14 @@ # source "arch/$(SRCARCH)/Kconfig" +config ARCH_CONFIGURES_CPU_MITIGATIONS + bool + +if !ARCH_CONFIGURES_CPU_MITIGATIONS +config CPU_MITIGATIONS + def_bool y +endif + menu "General architecture-dependent options" config ARCH_HAS_SUBPAGE_FAULTS @@ -681,6 +689,7 @@ config SHADOW_CALL_STACK bool "Shadow Call Stack" depends on ARCH_SUPPORTS_SHADOW_CALL_STACK depends on DYNAMIC_FTRACE_WITH_ARGS || DYNAMIC_FTRACE_WITH_REGS || !FUNCTION_GRAPH_TRACER + depends on MMU help This option enables the compiler's Shadow Call Stack, which uses a shadow stack to protect function return addresses from diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c index fb3025396ac964..cfdf90bc8b3f86 100644 --- a/arch/alpha/kernel/rtc.c +++ b/arch/alpha/kernel/rtc.c @@ -80,7 +80,7 @@ init_rtc_epoch(void) static int alpha_rtc_read_time(struct device *dev, struct rtc_time *tm) { - int ret = mc146818_get_time(tm); + int ret = mc146818_get_time(tm, 10); if (ret < 0) { dev_err_ratelimited(dev, "unable to read current time\n"); diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index c80258ec332ffe..85a679ce061c25 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -131,6 +131,7 @@ static void determine_cpu_caches (unsigned int); static char __initdata command_line[COMMAND_LINE_SIZE]; +#ifdef CONFIG_VGA_CONSOLE /* * The format of "screen_info" is strange, and due to early * i386-setup code. This is just enough to make the console @@ -147,6 +148,7 @@ struct screen_info screen_info = { }; EXPORT_SYMBOL(screen_info); +#endif /* * The direct map I/O window, if any. This should be the same diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c index 7c420d8dac53d9..7de8a5d2d20667 100644 --- a/arch/alpha/kernel/sys_sio.c +++ b/arch/alpha/kernel/sys_sio.c @@ -57,11 +57,13 @@ sio_init_irq(void) static inline void __init alphabook1_init_arch(void) { +#ifdef CONFIG_VGA_CONSOLE /* The AlphaBook1 has LCD video fixed at 800x600, 37 rows and 100 cols. */ screen_info.orig_y = 37; screen_info.orig_video_cols = 100; screen_info.orig_video_lines = 37; +#endif lca_init_arch(); } diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 6691f425507788..41b980df862b14 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -205,7 +205,6 @@ dmac_cfg_clk: dmac-gpu-cfg-clk { }; gmac: ethernet@8000 { - #interrupt-cells = <1>; compatible = "snps,dwmac"; reg = <0x8000 0x2000>; interrupts = <10>; diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h index bd5b1a9a054402..6fc74500a9f52a 100644 --- a/arch/arc/include/asm/cacheflush.h +++ b/arch/arc/include/asm/cacheflush.h @@ -40,6 +40,7 @@ void dma_cache_wback(phys_addr_t start, unsigned long sz); /* TBD: optimize this */ #define flush_cache_vmap(start, end) flush_cache_all() +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) flush_cache_all() #define flush_cache_dup_mm(mm) /* called on fork (VIVT only) */ diff --git a/arch/arc/include/asm/jump_label.h b/arch/arc/include/asm/jump_label.h index 9d96180797396b..a339223d9e052b 100644 --- a/arch/arc/include/asm/jump_label.h +++ b/arch/arc/include/asm/jump_label.h @@ -31,7 +31,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" + asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" "1: \n" "nop \n" ".pushsection __jump_table, \"aw\" \n" @@ -47,7 +47,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" + asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" "1: \n" "b %l[l_yes] \n" ".pushsection __jump_table, \"aw\" \n" diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 4dcf8589b708ac..d08a5092c2b4d4 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -153,7 +153,7 @@ static int arcv2_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len) { int n = 0; #ifdef CONFIG_ISA_ARCV2 - const char *release, *cpu_nm, *isa_nm = "ARCv2"; + const char *release = "", *cpu_nm = "HS38", *isa_nm = "ARCv2"; int dual_issue = 0, dual_enb = 0, mpy_opt, present; int bpu_full, bpu_cache, bpu_pred, bpu_ret_stk; char mpy_nm[16], lpb_nm[32]; @@ -172,8 +172,6 @@ static int arcv2_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len) * releases only update it. */ - cpu_nm = "HS38"; - if (info->arcver > 0x50 && info->arcver <= 0x53) { release = arc_hs_rel[info->arcver - 0x51].str; } else { diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 0b3bb529d24632..8f6f4a5429646f 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -62,7 +62,7 @@ struct rt_sigframe { unsigned int sigret_magic; }; -static int save_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs) +static int save_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs) { int err = 0; #ifndef CONFIG_ISA_ARCOMPACT @@ -75,12 +75,12 @@ static int save_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs) #else v2abi.r58 = v2abi.r59 = 0; #endif - err = __copy_to_user(&mctx->v2abi, &v2abi, sizeof(v2abi)); + err = __copy_to_user(&mctx->v2abi, (void const *)&v2abi, sizeof(v2abi)); #endif return err; } -static int restore_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs) +static int restore_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs) { int err = 0; #ifndef CONFIG_ISA_ARCOMPACT diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 9557808e8937b1..57c0448d017a13 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -589,8 +589,8 @@ source "arch/arm/mm/Kconfig" config IWMMXT bool "Enable iWMMXt support" - depends on CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_PJ4 || CPU_PJ4B - default y if PXA27x || PXA3xx || ARCH_MMP || CPU_PJ4 || CPU_PJ4B + depends on CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK + default y if PXA27x || PXA3xx || ARCH_MMP help Enable support for iWMMXt context switching at run time if running on a CPU that supports it. diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 547e5856eaa0d3..5ba42f69f8ce0c 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -304,11 +304,7 @@ $(INSTALL_TARGETS): KBUILD_IMAGE = $(boot)/$(patsubst %install,%Image,$@) $(INSTALL_TARGETS): $(call cmd,install) -PHONY += vdso_install -vdso_install: -ifeq ($(CONFIG_VDSO),y) - $(Q)$(MAKE) $(build)=arch/arm/vdso $@ -endif +vdso-install-$(CONFIG_VDSO) += arch/arm/vdso/vdso.so.dbg # My testing targets (bypasses dependencies) bp:; $(Q)$(MAKE) $(build)=$(boot) $(boot)/bootpImage @@ -331,7 +327,6 @@ define archhelp echo ' Install using (your) ~/bin/$(INSTALLKERNEL) or' echo ' (distribution) /sbin/$(INSTALLKERNEL) or' echo ' install to $$(INSTALL_PATH) and run lilo' - echo ' vdso_install - Install unstripped vdso.so to $$(INSTALL_MOD_PATH)/vdso' echo echo ' multi_v7_lpae_defconfig - multi_v7_defconfig with CONFIG_ARM_LPAE enabled' endef diff --git a/arch/arm/boot/dts/allwinner/Makefile b/arch/arm/boot/dts/allwinner/Makefile index eebb5a0c873ad4..296be33ec93465 100644 --- a/arch/arm/boot/dts/allwinner/Makefile +++ b/arch/arm/boot/dts/allwinner/Makefile @@ -259,68 +259,6 @@ dtb-$(CONFIG_MACH_SUN8I) += \ sun8i-v3s-licheepi-zero.dtb \ sun8i-v3s-licheepi-zero-dock.dtb \ sun8i-v40-bananapi-m2-berry.dtb -dtb-$(CONFIG_MACH_SUN8I) += \ - sun8i-a23-evb.dtb \ - sun8i-a23-gt90h-v4.dtb \ - sun8i-a23-inet86dz.dtb \ - sun8i-a23-ippo-q8h-v5.dtb \ - sun8i-a23-ippo-q8h-v1.2.dtb \ - sun8i-a23-polaroid-mid2407pxe03.dtb \ - sun8i-a23-polaroid-mid2809pxe04.dtb \ - sun8i-a23-q8-tablet.dtb \ - sun8i-a33-et-q8-v1.6.dtb \ - sun8i-a33-ga10h-v1.1.dtb \ - sun8i-a33-inet-d978-rev2.dtb \ - sun8i-a33-ippo-q8h-v1.2.dtb \ - sun8i-a33-olinuxino.dtb \ - sun8i-a33-q8-tablet.dtb \ - sun8i-a33-sinlinx-sina33.dtb \ - sun8i-a83t-allwinner-h8homlet-v2.dtb \ - sun8i-a83t-bananapi-m3.dtb \ - sun8i-a83t-cubietruck-plus.dtb \ - sun8i-a83t-tbs-a711.dtb \ - sun8i-h2-plus-bananapi-m2-zero.dtb \ - sun8i-h2-plus-libretech-all-h3-cc.dtb \ - sun8i-h2-plus-orangepi-r1.dtb \ - sun8i-h2-plus-orangepi-zero.dtb \ - sun8i-h3-bananapi-m2-plus.dtb \ - sun8i-h3-bananapi-m2-plus-v1.2.dtb \ - sun8i-h3-beelink-x2.dtb \ - sun8i-h3-libretech-all-h3-cc.dtb \ - sun8i-h3-mapleboard-mp130.dtb \ - sun8i-h3-nanopi-duo2.dtb \ - sun8i-h3-nanopi-m1.dtb\ - \ - sun8i-h3-nanopi-m1-plus.dtb \ - sun8i-h3-nanopi-neo.dtb \ - sun8i-h3-nanopi-neo-air.dtb \ - sun8i-h3-nanopi-r1.dtb \ - sun8i-h3-orangepi-2.dtb \ - sun8i-h3-orangepi-lite.dtb \ - sun8i-h3-orangepi-one.dtb \ - sun8i-h3-orangepi-pc.dtb \ - sun8i-h3-orangepi-pc-plus.dtb \ - sun8i-h3-orangepi-plus.dtb \ - sun8i-h3-orangepi-plus2e.dtb \ - sun8i-h3-orangepi-zero-plus2.dtb \ - sun8i-h3-rervision-dvk.dtb \ - sun8i-h3-zeropi.dtb \ - sun8i-h3-emlid-neutis-n5h3-devboard.dtb \ - sun8i-r16-bananapi-m2m.dtb \ - sun8i-r16-nintendo-nes-classic.dtb \ - sun8i-r16-nintendo-super-nes-classic.dtb \ - sun8i-r16-parrot.dtb \ - sun8i-r40-bananapi-m2-ultra.dtb \ - sun8i-r40-oka40i-c.dtb \ - sun8i-s3-elimo-initium.dtb \ - sun8i-s3-lichee-zero-plus.dtb \ - sun8i-s3-pinecube.dtb \ - sun8i-t113s-mangopi-mq-r-t113.dtb \ - sun8i-t3-cqa3t-bv3.dtb \ - sun8i-v3-sl631-imx179.dtb \ - sun8i-v3s-licheepi-zero.dtb \ - sun8i-v3s-licheepi-zero-dock.dtb \ - sun8i-v40-bananapi-m2-berry.dtb dtb-$(CONFIG_MACH_SUN9I) += \ sun9i-a80-optimus.dtb \ sun9i-a80-cubieboard4.dtb diff --git a/arch/arm/boot/dts/amazon/alpine.dtsi b/arch/arm/boot/dts/amazon/alpine.dtsi index ff68dfb4eb7874..90bd12feac0101 100644 --- a/arch/arm/boot/dts/amazon/alpine.dtsi +++ b/arch/arm/boot/dts/amazon/alpine.dtsi @@ -167,7 +167,6 @@ pcie@fbc00000 { msix: msix@fbe00000 { compatible = "al,alpine-msix"; reg = <0x0 0xfbe00000 0x0 0x100000>; - interrupt-controller; msi-controller; al,msi-base-spi = <96>; al,msi-num-spis = <64>; diff --git a/arch/arm/boot/dts/arm/arm-realview-pb1176.dts b/arch/arm/boot/dts/arm/arm-realview-pb1176.dts index efed325af88d20..d99bac02232b37 100644 --- a/arch/arm/boot/dts/arm/arm-realview-pb1176.dts +++ b/arch/arm/boot/dts/arm/arm-realview-pb1176.dts @@ -451,7 +451,7 @@ pb1176_serial3: serial@1010f000 { /* Direct-mapped development chip ROM */ pb1176_rom@10200000 { - compatible = "direct-mapped"; + compatible = "mtd-rom"; reg = <0x10200000 0x4000>; bank-width = <1>; }; diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-bletchley.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-bletchley.dts index e899de681f4752..5be0e8fd2633c2 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-bletchley.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-bletchley.dts @@ -45,8 +45,8 @@ spi1_gpio: spi1-gpio { num-chipselects = <1>; cs-gpios = <&gpio0 ASPEED_GPIO(Z, 0) GPIO_ACTIVE_LOW>; - tpmdev@0 { - compatible = "tcg,tpm_tis-spi"; + tpm@0 { + compatible = "infineon,slb9670", "tcg,tpm_tis-spi"; spi-max-frequency = <33000000>; reg = <0>; }; diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-wedge400.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-wedge400.dts index a677c827e758fe..5a8169bbda8792 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-wedge400.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-wedge400.dts @@ -80,8 +80,8 @@ spi_gpio: spi { gpio-miso = <&gpio ASPEED_GPIO(R, 5) GPIO_ACTIVE_HIGH>; num-chipselects = <1>; - tpmdev@0 { - compatible = "tcg,tpm_tis-spi"; + tpm@0 { + compatible = "infineon,slb9670", "tcg,tpm_tis-spi"; spi-max-frequency = <33000000>; reg = <0>; }; diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-opp-tacoma.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-opp-tacoma.dts index 3f6010ef2b86f2..213023bc5aec41 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-opp-tacoma.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-opp-tacoma.dts @@ -456,7 +456,7 @@ &i2c1 { status = "okay"; tpm: tpm@2e { - compatible = "tcg,tpm-tis-i2c"; + compatible = "nuvoton,npct75x", "tcg,tpm-tis-i2c"; reg = <0x2e>; }; }; diff --git a/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi b/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi index 530491ae5eb260..857cb26ed6d7e8 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi +++ b/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi @@ -466,7 +466,6 @@ i2c_ic: interrupt-controller@0 { i2c0: i2c-bus@40 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x40 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -482,7 +481,6 @@ i2c0: i2c-bus@40 { i2c1: i2c-bus@80 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x80 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -498,7 +496,6 @@ i2c1: i2c-bus@80 { i2c2: i2c-bus@c0 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0xc0 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -515,7 +512,6 @@ i2c2: i2c-bus@c0 { i2c3: i2c-bus@100 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x100 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -532,7 +528,6 @@ i2c3: i2c-bus@100 { i2c4: i2c-bus@140 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x140 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -549,7 +544,6 @@ i2c4: i2c-bus@140 { i2c5: i2c-bus@180 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x180 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -566,7 +560,6 @@ i2c5: i2c-bus@180 { i2c6: i2c-bus@1c0 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x1c0 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -583,7 +576,6 @@ i2c6: i2c-bus@1c0 { i2c7: i2c-bus@300 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x300 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -600,7 +592,6 @@ i2c7: i2c-bus@300 { i2c8: i2c-bus@340 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x340 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -617,7 +608,6 @@ i2c8: i2c-bus@340 { i2c9: i2c-bus@380 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x380 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -634,7 +624,6 @@ i2c9: i2c-bus@380 { i2c10: i2c-bus@3c0 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x3c0 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -651,7 +640,6 @@ i2c10: i2c-bus@3c0 { i2c11: i2c-bus@400 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x400 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -668,7 +656,6 @@ i2c11: i2c-bus@400 { i2c12: i2c-bus@440 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x440 0x40>; compatible = "aspeed,ast2400-i2c-bus"; @@ -685,7 +672,6 @@ i2c12: i2c-bus@440 { i2c13: i2c-bus@480 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x480 0x40>; compatible = "aspeed,ast2400-i2c-bus"; diff --git a/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi b/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi index 04f98d1dbb97c8..e6f3cf3c721e57 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi +++ b/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi @@ -363,6 +363,7 @@ sgpio: sgpio@1e780200 { interrupts = <40>; reg = <0x1e780200 0x0100>; clocks = <&syscon ASPEED_CLK_APB>; + #interrupt-cells = <2>; interrupt-controller; bus-frequency = <12000000>; pinctrl-names = "default"; @@ -594,7 +595,6 @@ i2c_ic: interrupt-controller@0 { i2c0: i2c-bus@40 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x40 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -610,7 +610,6 @@ i2c0: i2c-bus@40 { i2c1: i2c-bus@80 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x80 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -626,7 +625,6 @@ i2c1: i2c-bus@80 { i2c2: i2c-bus@c0 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0xc0 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -643,7 +641,6 @@ i2c2: i2c-bus@c0 { i2c3: i2c-bus@100 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x100 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -660,7 +657,6 @@ i2c3: i2c-bus@100 { i2c4: i2c-bus@140 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x140 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -677,7 +673,6 @@ i2c4: i2c-bus@140 { i2c5: i2c-bus@180 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x180 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -694,7 +689,6 @@ i2c5: i2c-bus@180 { i2c6: i2c-bus@1c0 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x1c0 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -711,7 +705,6 @@ i2c6: i2c-bus@1c0 { i2c7: i2c-bus@300 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x300 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -728,7 +721,6 @@ i2c7: i2c-bus@300 { i2c8: i2c-bus@340 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x340 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -745,7 +737,6 @@ i2c8: i2c-bus@340 { i2c9: i2c-bus@380 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x380 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -762,7 +753,6 @@ i2c9: i2c-bus@380 { i2c10: i2c-bus@3c0 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x3c0 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -779,7 +769,6 @@ i2c10: i2c-bus@3c0 { i2c11: i2c-bus@400 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x400 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -796,7 +785,6 @@ i2c11: i2c-bus@400 { i2c12: i2c-bus@440 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x440 0x40>; compatible = "aspeed,ast2500-i2c-bus"; @@ -813,7 +801,6 @@ i2c12: i2c-bus@440 { i2c13: i2c-bus@480 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x480 0x40>; compatible = "aspeed,ast2500-i2c-bus"; diff --git a/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi b/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi index c4d1faade8be33..29f94696d8b189 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi +++ b/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi @@ -474,6 +474,7 @@ sgpiom0: sgpiom@1e780500 { reg = <0x1e780500 0x100>; interrupts = ; clocks = <&syscon ASPEED_CLK_APB2>; + #interrupt-cells = <2>; interrupt-controller; bus-frequency = <12000000>; pinctrl-names = "default"; @@ -488,6 +489,7 @@ sgpiom1: sgpiom@1e780600 { reg = <0x1e780600 0x100>; interrupts = ; clocks = <&syscon ASPEED_CLK_APB2>; + #interrupt-cells = <2>; interrupt-controller; bus-frequency = <12000000>; pinctrl-names = "default"; @@ -902,7 +904,6 @@ &i2c { i2c0: i2c-bus@80 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x80 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -917,7 +918,6 @@ i2c0: i2c-bus@80 { i2c1: i2c-bus@100 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x100 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -932,7 +932,6 @@ i2c1: i2c-bus@100 { i2c2: i2c-bus@180 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x180 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -947,7 +946,6 @@ i2c2: i2c-bus@180 { i2c3: i2c-bus@200 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x200 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -962,7 +960,6 @@ i2c3: i2c-bus@200 { i2c4: i2c-bus@280 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x280 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -977,7 +974,6 @@ i2c4: i2c-bus@280 { i2c5: i2c-bus@300 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x300 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -992,7 +988,6 @@ i2c5: i2c-bus@300 { i2c6: i2c-bus@380 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x380 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1007,7 +1002,6 @@ i2c6: i2c-bus@380 { i2c7: i2c-bus@400 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x400 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1022,7 +1016,6 @@ i2c7: i2c-bus@400 { i2c8: i2c-bus@480 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x480 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1037,7 +1030,6 @@ i2c8: i2c-bus@480 { i2c9: i2c-bus@500 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x500 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1052,7 +1044,6 @@ i2c9: i2c-bus@500 { i2c10: i2c-bus@580 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x580 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1067,7 +1058,6 @@ i2c10: i2c-bus@580 { i2c11: i2c-bus@600 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x600 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1082,7 +1072,6 @@ i2c11: i2c-bus@600 { i2c12: i2c-bus@680 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x680 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1097,7 +1086,6 @@ i2c12: i2c-bus@680 { i2c13: i2c-bus@700 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x700 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1112,7 +1100,6 @@ i2c13: i2c-bus@700 { i2c14: i2c-bus@780 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x780 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; @@ -1127,7 +1114,6 @@ i2c14: i2c-bus@780 { i2c15: i2c-bus@800 { #address-cells = <1>; #size-cells = <0>; - #interrupt-cells = <1>; reg = <0x800 0x80>; compatible = "aspeed,ast2600-i2c-bus"; clocks = <&syscon ASPEED_CLK_APB2>; diff --git a/arch/arm/boot/dts/aspeed/ast2600-facebook-netbmc-common.dtsi b/arch/arm/boot/dts/aspeed/ast2600-facebook-netbmc-common.dtsi index 31590d3186a2e0..00e5887c926f18 100644 --- a/arch/arm/boot/dts/aspeed/ast2600-facebook-netbmc-common.dtsi +++ b/arch/arm/boot/dts/aspeed/ast2600-facebook-netbmc-common.dtsi @@ -35,8 +35,8 @@ spi_gpio: spi { gpio-mosi = <&gpio0 ASPEED_GPIO(X, 4) GPIO_ACTIVE_HIGH>; gpio-miso = <&gpio0 ASPEED_GPIO(X, 5) GPIO_ACTIVE_HIGH>; - tpmdev@0 { - compatible = "tcg,tpm_tis-spi"; + tpm@0 { + compatible = "infineon,slb9670", "tcg,tpm_tis-spi"; spi-max-frequency = <33000000>; reg = <0>; }; diff --git a/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi b/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi index f9f79ed825181b..07ca0d993c9fdb 100644 --- a/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi @@ -167,6 +167,7 @@ gpio_crmu: gpio@3024800 { #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&mailbox>; interrupts = <0>; }; @@ -247,6 +248,7 @@ gpio_ccm: gpio@1800a000 { gpio-controller; interrupts = ; interrupt-controller; + #interrupt-cells = <2>; }; i2c1: i2c@1800b000 { @@ -518,6 +520,7 @@ gpio_asiu: gpio@180a5000 { gpio-controller; interrupt-controller; + #interrupt-cells = <2>; interrupts = ; gpio-ranges = <&pinctrl 0 42 1>, <&pinctrl 1 44 3>, diff --git a/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi b/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi index 788a6806191a33..75545b10ef2fa6 100644 --- a/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi @@ -200,6 +200,7 @@ gpiob: gpio@30000 { gpio-controller; ngpios = <4>; interrupt-controller; + #interrupt-cells = <2>; interrupts = ; }; diff --git a/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi b/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi index 9d20ba3b1ffb13..6a4482c9316741 100644 --- a/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi @@ -180,6 +180,7 @@ gpioa: gpio@20 { gpio-controller; ngpios = <32>; interrupt-controller; + #interrupt-cells = <2>; interrupts = ; gpio-ranges = <&pinctrl 0 0 32>; }; @@ -352,6 +353,7 @@ gpiob: gpio@30000 { gpio-controller; ngpios = <4>; interrupt-controller; + #interrupt-cells = <2>; interrupts = ; }; diff --git a/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts b/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts index 1ab8184302db44..5a2869a18bd555 100644 --- a/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts +++ b/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts @@ -36,9 +36,7 @@ &led_pwr { gpios = <&gpio 42 GPIO_ACTIVE_HIGH>; }; -&leds { - /delete-node/ led_act; -}; +/delete-node/ &led_act; &pm { /delete-property/ system-power-controller; diff --git a/arch/arm/boot/dts/broadcom/bcm4708-buffalo-wzr-1166dhp-common.dtsi b/arch/arm/boot/dts/broadcom/bcm4708-buffalo-wzr-1166dhp-common.dtsi index 42bcbf10957c40..9f9084269ef58b 100644 --- a/arch/arm/boot/dts/broadcom/bcm4708-buffalo-wzr-1166dhp-common.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm4708-buffalo-wzr-1166dhp-common.dtsi @@ -181,5 +181,13 @@ port@4 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm4708-luxul-xap-1510.dts b/arch/arm/boot/dts/broadcom/bcm4708-luxul-xap-1510.dts index e04d2e5ea51aa4..72e960c888ac86 100644 --- a/arch/arm/boot/dts/broadcom/bcm4708-luxul-xap-1510.dts +++ b/arch/arm/boot/dts/broadcom/bcm4708-luxul-xap-1510.dts @@ -85,5 +85,13 @@ port@4 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm4708-luxul-xwc-1000.dts b/arch/arm/boot/dts/broadcom/bcm4708-luxul-xwc-1000.dts index a399800139d9ce..750e17482371cf 100644 --- a/arch/arm/boot/dts/broadcom/bcm4708-luxul-xwc-1000.dts +++ b/arch/arm/boot/dts/broadcom/bcm4708-luxul-xwc-1000.dts @@ -88,5 +88,13 @@ port@4 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm4708-netgear-r6250.dts b/arch/arm/boot/dts/broadcom/bcm4708-netgear-r6250.dts index fad3473810a2e5..2bdbc7d18b0eb1 100644 --- a/arch/arm/boot/dts/broadcom/bcm4708-netgear-r6250.dts +++ b/arch/arm/boot/dts/broadcom/bcm4708-netgear-r6250.dts @@ -122,5 +122,13 @@ port@4 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm4708-smartrg-sr400ac.dts b/arch/arm/boot/dts/broadcom/bcm4708-smartrg-sr400ac.dts index 5b2b7b8b3b123f..b226bef3369cf7 100644 --- a/arch/arm/boot/dts/broadcom/bcm4708-smartrg-sr400ac.dts +++ b/arch/arm/boot/dts/broadcom/bcm4708-smartrg-sr400ac.dts @@ -145,6 +145,14 @@ port@4 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm47081-buffalo-wzr-600dhp2.dts b/arch/arm/boot/dts/broadcom/bcm47081-buffalo-wzr-600dhp2.dts index d0a26b643b82fe..192b8db5a89c39 100644 --- a/arch/arm/boot/dts/broadcom/bcm47081-buffalo-wzr-600dhp2.dts +++ b/arch/arm/boot/dts/broadcom/bcm47081-buffalo-wzr-600dhp2.dts @@ -145,5 +145,13 @@ port@4 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm47081-luxul-xap-1410.dts b/arch/arm/boot/dts/broadcom/bcm47081-luxul-xap-1410.dts index 9f21d6d6d35b75..0198b5f9e4a750 100644 --- a/arch/arm/boot/dts/broadcom/bcm47081-luxul-xap-1410.dts +++ b/arch/arm/boot/dts/broadcom/bcm47081-luxul-xap-1410.dts @@ -81,5 +81,13 @@ port@4 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm47081-luxul-xwr-1200.dts b/arch/arm/boot/dts/broadcom/bcm47081-luxul-xwr-1200.dts index 2561072917021c..73ff1694a4a0b3 100644 --- a/arch/arm/boot/dts/broadcom/bcm47081-luxul-xwr-1200.dts +++ b/arch/arm/boot/dts/broadcom/bcm47081-luxul-xwr-1200.dts @@ -148,5 +148,13 @@ port@4 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm4709-netgear-r8000.dts b/arch/arm/boot/dts/broadcom/bcm4709-netgear-r8000.dts index 707c561703ed81..55fc9f44cbc7f5 100644 --- a/arch/arm/boot/dts/broadcom/bcm4709-netgear-r8000.dts +++ b/arch/arm/boot/dts/broadcom/bcm4709-netgear-r8000.dts @@ -227,6 +227,14 @@ port@4 { label = "wan"; }; + port@5 { + status = "disabled"; + }; + + port@7 { + status = "disabled"; + }; + port@8 { label = "cpu"; }; diff --git a/arch/arm/boot/dts/broadcom/bcm47094-dlink-dir-885l.dts b/arch/arm/boot/dts/broadcom/bcm47094-dlink-dir-885l.dts index c914569ddd5ecc..e6d26987865d02 100644 --- a/arch/arm/boot/dts/broadcom/bcm47094-dlink-dir-885l.dts +++ b/arch/arm/boot/dts/broadcom/bcm47094-dlink-dir-885l.dts @@ -144,6 +144,14 @@ port@4 { label = "wan"; }; + port@5 { + status = "disabled"; + }; + + port@7 { + status = "disabled"; + }; + port@8 { label = "cpu"; }; diff --git a/arch/arm/boot/dts/broadcom/bcm47094-dlink-dir-890l.dts b/arch/arm/boot/dts/broadcom/bcm47094-dlink-dir-890l.dts index f050acbea0b207..3124dfd01b9447 100644 --- a/arch/arm/boot/dts/broadcom/bcm47094-dlink-dir-890l.dts +++ b/arch/arm/boot/dts/broadcom/bcm47094-dlink-dir-890l.dts @@ -192,6 +192,14 @@ port@4 { label = "wan"; }; + port@5 { + status = "disabled"; + }; + + port@7 { + status = "disabled"; + }; + port@8 { label = "cpu"; phy-mode = "rgmii"; diff --git a/arch/arm/boot/dts/broadcom/bcm47094-luxul-abr-4500.dts b/arch/arm/boot/dts/broadcom/bcm47094-luxul-abr-4500.dts index e8991d4e248ce2..e374062eb5b762 100644 --- a/arch/arm/boot/dts/broadcom/bcm47094-luxul-abr-4500.dts +++ b/arch/arm/boot/dts/broadcom/bcm47094-luxul-abr-4500.dts @@ -107,5 +107,13 @@ port@4 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm47094-luxul-xap-1610.dts b/arch/arm/boot/dts/broadcom/bcm47094-luxul-xap-1610.dts index afc635c8cdebbc..badafa024d24c5 100644 --- a/arch/arm/boot/dts/broadcom/bcm47094-luxul-xap-1610.dts +++ b/arch/arm/boot/dts/broadcom/bcm47094-luxul-xap-1610.dts @@ -120,5 +120,13 @@ port@1 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm47094-luxul-xbr-4500.dts b/arch/arm/boot/dts/broadcom/bcm47094-luxul-xbr-4500.dts index 7cfa4607ef311f..cf95af9db1e66d 100644 --- a/arch/arm/boot/dts/broadcom/bcm47094-luxul-xbr-4500.dts +++ b/arch/arm/boot/dts/broadcom/bcm47094-luxul-xbr-4500.dts @@ -107,5 +107,13 @@ port@4 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm47094-luxul-xwc-2000.dts b/arch/arm/boot/dts/broadcom/bcm47094-luxul-xwc-2000.dts index d55e10095eae79..992c19e1cfa173 100644 --- a/arch/arm/boot/dts/broadcom/bcm47094-luxul-xwc-2000.dts +++ b/arch/arm/boot/dts/broadcom/bcm47094-luxul-xwc-2000.dts @@ -75,5 +75,13 @@ port@0 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm47094-luxul-xwr-3100.dts b/arch/arm/boot/dts/broadcom/bcm47094-luxul-xwr-3100.dts index ccf031c0e276d6..4d0ba315a2049e 100644 --- a/arch/arm/boot/dts/broadcom/bcm47094-luxul-xwr-3100.dts +++ b/arch/arm/boot/dts/broadcom/bcm47094-luxul-xwr-3100.dts @@ -147,5 +147,13 @@ port@4 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm47094-luxul-xwr-3150-v1.dts b/arch/arm/boot/dts/broadcom/bcm47094-luxul-xwr-3150-v1.dts index e28f7a3501179f..83c429afc2974d 100644 --- a/arch/arm/boot/dts/broadcom/bcm47094-luxul-xwr-3150-v1.dts +++ b/arch/arm/boot/dts/broadcom/bcm47094-luxul-xwr-3150-v1.dts @@ -158,5 +158,13 @@ port@4 { port@5 { label = "cpu"; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm53015-meraki-mr26.dts b/arch/arm/boot/dts/broadcom/bcm53015-meraki-mr26.dts index 03ad614e6b7214..0bf5106f7012c9 100644 --- a/arch/arm/boot/dts/broadcom/bcm53015-meraki-mr26.dts +++ b/arch/arm/boot/dts/broadcom/bcm53015-meraki-mr26.dts @@ -124,6 +124,14 @@ fixed-link { full-duplex; }; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm53016-meraki-mr32.dts b/arch/arm/boot/dts/broadcom/bcm53016-meraki-mr32.dts index 26c12bfb0bdd4a..25eeacf6a2484c 100644 --- a/arch/arm/boot/dts/broadcom/bcm53016-meraki-mr32.dts +++ b/arch/arm/boot/dts/broadcom/bcm53016-meraki-mr32.dts @@ -185,6 +185,14 @@ fixed-link { full-duplex; }; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/broadcom/bcm953012er.dts b/arch/arm/boot/dts/broadcom/bcm953012er.dts index 4fe3b365337670..d939ec9f4a9e79 100644 --- a/arch/arm/boot/dts/broadcom/bcm953012er.dts +++ b/arch/arm/boot/dts/broadcom/bcm953012er.dts @@ -84,6 +84,14 @@ port@5 { label = "cpu"; ethernet = <&gmac0>; }; + + port@7 { + status = "disabled"; + }; + + port@8 { + status = "disabled"; + }; }; }; diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts index 4d70f6afd13ab5..6d5e69035f94dc 100644 --- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts +++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts @@ -60,6 +60,8 @@ pci@c0000000 { * We have slots (IDSEL) 1 and 2 with one assigned IRQ * each handling all IRQs. */ + #interrupt-cells = <1>; + interrupt-map-mask = <0xf800 0 0 7>; interrupt-map = /* IDSEL 1 */ <0x0800 0 0 1 &gpio0 11 IRQ_TYPE_LEVEL_LOW>, /* INT A on slot 1 is irq 11 */ diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts index 9ec0169bacf8c2..5f4c849915db71 100644 --- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts +++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts @@ -89,6 +89,8 @@ pci@c0000000 { * The slots have Ethernet, Ethernet, NEC and MPCI. * The IDSELs are 11, 12, 13, 14. */ + #interrupt-cells = <1>; + interrupt-map-mask = <0xf800 0 0 7>; interrupt-map = /* IDSEL 11 - Ethernet A */ <0x5800 0 0 1 &gpio0 4 IRQ_TYPE_LEVEL_LOW>, /* INT A on slot 11 is irq 4 */ diff --git a/arch/arm/boot/dts/marvell/kirkwood-l-50.dts b/arch/arm/boot/dts/marvell/kirkwood-l-50.dts index dffb9f84e67c50..c841eb8e7fb1d0 100644 --- a/arch/arm/boot/dts/marvell/kirkwood-l-50.dts +++ b/arch/arm/boot/dts/marvell/kirkwood-l-50.dts @@ -65,6 +65,7 @@ i2c@11000 { gpio2: gpio-expander@20 { #gpio-cells = <2>; #interrupt-cells = <2>; + interrupt-controller; compatible = "semtech,sx1505q"; reg = <0x20>; @@ -79,6 +80,7 @@ gpio2: gpio-expander@20 { gpio3: gpio-expander@21 { #gpio-cells = <2>; #interrupt-cells = <2>; + interrupt-controller; compatible = "semtech,sx1505q"; reg = <0x21>; diff --git a/arch/arm/boot/dts/marvell/mmp2-brownstone.dts b/arch/arm/boot/dts/marvell/mmp2-brownstone.dts index 04f1ae1382e7a3..bc64348b821851 100644 --- a/arch/arm/boot/dts/marvell/mmp2-brownstone.dts +++ b/arch/arm/boot/dts/marvell/mmp2-brownstone.dts @@ -28,7 +28,7 @@ &uart3 { &twsi1 { status = "okay"; pmic: max8925@3c { - compatible = "maxium,max8925"; + compatible = "maxim,max8925"; reg = <0x3c>; interrupts = <1>; interrupt-parent = <&intcmux4>; diff --git a/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts b/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts index 217e9b96c61e5d..20b2497657ae48 100644 --- a/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts +++ b/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts @@ -293,7 +293,7 @@ vddcore: VDD_CORE { regulator-state-standby { regulator-on-in-suspend; - regulator-suspend-voltage = <1150000>; + regulator-suspend-microvolt = <1150000>; regulator-mode = <4>; }; @@ -314,7 +314,7 @@ vddcpu: VDD_OTHER { regulator-state-standby { regulator-on-in-suspend; - regulator-suspend-voltage = <1050000>; + regulator-suspend-microvolt = <1050000>; regulator-mode = <4>; }; @@ -331,7 +331,7 @@ vldo1: LDO1 { regulator-always-on; regulator-state-standby { - regulator-suspend-voltage = <1800000>; + regulator-suspend-microvolt = <1800000>; regulator-on-in-suspend; }; @@ -346,7 +346,7 @@ vldo2: LDO2 { regulator-max-microvolt = <3700000>; regulator-state-standby { - regulator-suspend-voltage = <1800000>; + regulator-suspend-microvolt = <1800000>; regulator-on-in-suspend; }; diff --git a/arch/arm/boot/dts/microchip/sam9x60.dtsi b/arch/arm/boot/dts/microchip/sam9x60.dtsi index 73d570a172690c..1705c96f4221e8 100644 --- a/arch/arm/boot/dts/microchip/sam9x60.dtsi +++ b/arch/arm/boot/dts/microchip/sam9x60.dtsi @@ -1312,7 +1312,7 @@ rtt: rtc@fffffe20 { compatible = "microchip,sam9x60-rtt", "atmel,at91sam9260-rtt"; reg = <0xfffffe20 0x20>; interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>; - clocks = <&clk32k 0>; + clocks = <&clk32k 1>; }; pit: timer@fffffe40 { @@ -1338,7 +1338,7 @@ rtc: rtc@fffffea8 { compatible = "microchip,sam9x60-rtc", "atmel,at91sam9x5-rtc"; reg = <0xfffffea8 0x100>; interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>; - clocks = <&clk32k 0>; + clocks = <&clk32k 1>; }; watchdog: watchdog@ffffff80 { diff --git a/arch/arm/boot/dts/microchip/sama7g5.dtsi b/arch/arm/boot/dts/microchip/sama7g5.dtsi index 269e0a3ca269cd..7a95464bb78d83 100644 --- a/arch/arm/boot/dts/microchip/sama7g5.dtsi +++ b/arch/arm/boot/dts/microchip/sama7g5.dtsi @@ -272,7 +272,7 @@ rtt: rtc@e001d020 { compatible = "microchip,sama7g5-rtt", "microchip,sam9x60-rtt", "atmel,at91sam9260-rtt"; reg = <0xe001d020 0x30>; interrupts = ; - clocks = <&clk32k 0>; + clocks = <&clk32k 1>; }; clk32k: clock-controller@e001d050 { diff --git a/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi b/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi index fd671c7a1e5d64..6e1f0f164cb4f5 100644 --- a/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi +++ b/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi @@ -120,6 +120,7 @@ gpio0: gpio@0 { interrupts = <2 IRQ_TYPE_LEVEL_HIGH>, <3 IRQ_TYPE_LEVEL_HIGH>, <4 IRQ_TYPE_LEVEL_HIGH>; + #interrupt-cells = <2>; interrupt-controller; }; @@ -128,6 +129,7 @@ gpio1: gpio@1 { gpio-controller; #gpio-cells = <2>; interrupts = <5 IRQ_TYPE_LEVEL_HIGH>; + #interrupt-cells = <2>; interrupt-controller; }; diff --git a/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi b/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi index 1640763fd4af22..ff0d684622f74d 100644 --- a/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi +++ b/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi @@ -997,7 +997,6 @@ touchscreen@41 { compatible = "st,stmpe811"; reg = <0x41>; irq-gpio = <&gpio TEGRA_GPIO(V, 0) GPIO_ACTIVE_LOW>; - interrupt-controller; id = <0>; blocks = <0x5>; irq-trigger = <0x1>; diff --git a/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi b/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi index 3b6fad273cabf1..d38f1dd38a9068 100644 --- a/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi +++ b/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi @@ -980,7 +980,6 @@ touchscreen@41 { compatible = "st,stmpe811"; reg = <0x41>; irq-gpio = <&gpio TEGRA_GPIO(V, 0) GPIO_ACTIVE_LOW>; - interrupt-controller; id = <0>; blocks = <0x5>; irq-trigger = <0x1>; diff --git a/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi b/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi index 4eb526fe9c5588..81c8a5fd92ccea 100644 --- a/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi +++ b/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi @@ -861,7 +861,6 @@ touchscreen@41 { compatible = "st,stmpe811"; reg = <0x41>; irq-gpio = <&gpio TEGRA_GPIO(V, 0) GPIO_ACTIVE_LOW>; - interrupt-controller; id = <0>; blocks = <0x5>; irq-trigger = <0x1>; diff --git a/arch/arm/boot/dts/nxp/imx/imx1-ads.dts b/arch/arm/boot/dts/nxp/imx/imx1-ads.dts index 5833fb6f15d88a..2c817c4a4c68f8 100644 --- a/arch/arm/boot/dts/nxp/imx/imx1-ads.dts +++ b/arch/arm/boot/dts/nxp/imx/imx1-ads.dts @@ -65,7 +65,7 @@ &weim { pinctrl-0 = <&pinctrl_weim>; status = "okay"; - nor: nor@0,0 { + nor: flash@0,0 { compatible = "cfi-flash"; reg = <0 0x00000000 0x02000000>; bank-width = <4>; diff --git a/arch/arm/boot/dts/nxp/imx/imx1-apf9328.dts b/arch/arm/boot/dts/nxp/imx/imx1-apf9328.dts index 1f11e9542a72de..e66eef87a7a4fd 100644 --- a/arch/arm/boot/dts/nxp/imx/imx1-apf9328.dts +++ b/arch/arm/boot/dts/nxp/imx/imx1-apf9328.dts @@ -45,7 +45,7 @@ &weim { pinctrl-0 = <&pinctrl_weim>; status = "okay"; - nor: nor@0,0 { + nor: flash@0,0 { compatible = "cfi-flash"; reg = <0 0x00000000 0x02000000>; bank-width = <2>; diff --git a/arch/arm/boot/dts/nxp/imx/imx1.dtsi b/arch/arm/boot/dts/nxp/imx/imx1.dtsi index e312f1e74e2fe6..4aeb74479f44e9 100644 --- a/arch/arm/boot/dts/nxp/imx/imx1.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx1.dtsi @@ -268,9 +268,12 @@ weim: weim@220000 { status = "disabled"; }; - esram: esram@300000 { + esram: sram@300000 { compatible = "mmio-sram"; reg = <0x00300000 0x20000>; + ranges = <0 0x00300000 0x20000>; + #address-cells = <1>; + #size-cells = <1>; }; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-cpuimx25.dtsi b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-cpuimx25.dtsi index 0703f62d10d1cb..93a6e4e680b451 100644 --- a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-cpuimx25.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-cpuimx25.dtsi @@ -27,7 +27,7 @@ &i2c1 { pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; - pcf8563@51 { + rtc@51 { compatible = "nxp,pcf8563"; reg = <0x51>; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts index fc8a502fc957f0..6cddb2cc36fe2a 100644 --- a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts +++ b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts @@ -16,7 +16,7 @@ cmo_qvga: display { bus-width = <18>; display-timings { native-mode = <&qvga_timings>; - qvga_timings: 320x240 { + qvga_timings: timing0 { clock-frequency = <6500000>; hactive = <320>; vactive = <240>; diff --git a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts index 80a7f96de4c6ac..64b2ffac463b2a 100644 --- a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts +++ b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts @@ -16,7 +16,7 @@ dvi_svga: display { bus-width = <18>; display-timings { native-mode = <&dvi_svga_timings>; - dvi_svga_timings: 800x600 { + dvi_svga_timings: timing0 { clock-frequency = <40000000>; hactive = <800>; vactive = <600>; diff --git a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts index 24027a1fb46d11..fb074bfdaa8dc2 100644 --- a/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts +++ b/arch/arm/boot/dts/nxp/imx/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts @@ -16,7 +16,7 @@ dvi_vga: display { bus-width = <18>; display-timings { native-mode = <&dvi_vga_timings>; - dvi_vga_timings: 640x480 { + dvi_vga_timings: timing0 { clock-frequency = <31250000>; hactive = <640>; vactive = <480>; diff --git a/arch/arm/boot/dts/nxp/imx/imx25-pdk.dts b/arch/arm/boot/dts/nxp/imx/imx25-pdk.dts index 04f4b127a17257..e93bf3b7115fac 100644 --- a/arch/arm/boot/dts/nxp/imx/imx25-pdk.dts +++ b/arch/arm/boot/dts/nxp/imx/imx25-pdk.dts @@ -68,7 +68,7 @@ wvga: display { bus-width = <18>; display-timings { native-mode = <&wvga_timings>; - wvga_timings: 640x480 { + wvga_timings: timing0 { hactive = <640>; vactive = <480>; hback-porch = <45>; diff --git a/arch/arm/boot/dts/nxp/imx/imx25.dtsi b/arch/arm/boot/dts/nxp/imx/imx25.dtsi index 5f90d72b840b0e..5ac4549286bd7f 100644 --- a/arch/arm/boot/dts/nxp/imx/imx25.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx25.dtsi @@ -543,7 +543,7 @@ pwm1: pwm@53fe0000 { }; iim: efuse@53ff0000 { - compatible = "fsl,imx25-iim", "fsl,imx27-iim"; + compatible = "fsl,imx25-iim"; reg = <0x53ff0000 0x4000>; interrupts = <19>; clocks = <&clks 99>; diff --git a/arch/arm/boot/dts/nxp/imx/imx27-apf27dev.dts b/arch/arm/boot/dts/nxp/imx/imx27-apf27dev.dts index a21f1f7c24b88d..849306cb4532db 100644 --- a/arch/arm/boot/dts/nxp/imx/imx27-apf27dev.dts +++ b/arch/arm/boot/dts/nxp/imx/imx27-apf27dev.dts @@ -16,7 +16,7 @@ display: display { fsl,pcr = <0xfae80083>; /* non-standard but required */ display-timings { native-mode = <&timing0>; - timing0: 800x480 { + timing0: timing0 { clock-frequency = <33000033>; hactive = <800>; vactive = <480>; @@ -47,7 +47,7 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - user { + led-user { label = "Heartbeat"; gpios = <&gpio6 14 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/nxp/imx/imx27-eukrea-cpuimx27.dtsi b/arch/arm/boot/dts/nxp/imx/imx27-eukrea-cpuimx27.dtsi index 74110bbcd9d4f2..c7e92358487826 100644 --- a/arch/arm/boot/dts/nxp/imx/imx27-eukrea-cpuimx27.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx27-eukrea-cpuimx27.dtsi @@ -33,7 +33,7 @@ &i2c1 { pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; - pcf8563@51 { + rtc@51 { compatible = "nxp,pcf8563"; reg = <0x51>; }; @@ -90,7 +90,7 @@ &usbotg { &weim { status = "okay"; - nor: nor@0,0 { + nor: flash@0,0 { #address-cells = <1>; #size-cells = <1>; compatible = "cfi-flash"; diff --git a/arch/arm/boot/dts/nxp/imx/imx27-eukrea-mbimxsd27-baseboard.dts b/arch/arm/boot/dts/nxp/imx/imx27-eukrea-mbimxsd27-baseboard.dts index 145e459625b32d..d78793601306cf 100644 --- a/arch/arm/boot/dts/nxp/imx/imx27-eukrea-mbimxsd27-baseboard.dts +++ b/arch/arm/boot/dts/nxp/imx/imx27-eukrea-mbimxsd27-baseboard.dts @@ -16,7 +16,7 @@ display0: CMO-QVGA { display-timings { native-mode = <&timing0>; - timing0: 320x240 { + timing0: timing0 { clock-frequency = <6500000>; hactive = <320>; vactive = <240>; diff --git a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycard-s-rdk.dts b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycard-s-rdk.dts index 25442eba21c1e0..27c93b9fe0499f 100644 --- a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycard-s-rdk.dts +++ b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycard-s-rdk.dts @@ -19,7 +19,7 @@ display: display { fsl,pcr = <0xf0c88080>; /* non-standard but required */ display-timings { native-mode = <&timing0>; - timing0: 640x480 { + timing0: timing0 { hactive = <640>; vactive = <480>; hback-porch = <112>; diff --git a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dts b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dts index 7f0cd4d3ec2de4..67b235044b708c 100644 --- a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dts +++ b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dts @@ -19,7 +19,7 @@ display0: LQ035Q7 { display-timings { native-mode = <&timing0>; - timing0: 240x320 { + timing0: timing0 { clock-frequency = <5500000>; hactive = <240>; vactive = <320>; diff --git a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-som.dtsi b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-som.dtsi index 7191e10712b956..efce284b57969b 100644 --- a/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-som.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-som.dtsi @@ -314,7 +314,7 @@ &usbotg { &weim { status = "okay"; - nor: nor@0,0 { + nor: flash@0,0 { compatible = "cfi-flash"; reg = <0 0x00000000 0x02000000>; bank-width = <2>; diff --git a/arch/arm/boot/dts/nxp/imx/imx27.dtsi b/arch/arm/boot/dts/nxp/imx/imx27.dtsi index faba12ee7465eb..cac4b3d68986a0 100644 --- a/arch/arm/boot/dts/nxp/imx/imx27.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx27.dtsi @@ -588,6 +588,9 @@ weim: weim@d8002000 { iram: sram@ffff4c00 { compatible = "mmio-sram"; reg = <0xffff4c00 0xb400>; + ranges = <0 0xffff4c00 0xb400>; + #address-cells = <1>; + #size-cells = <1>; }; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-yapp4-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx6dl-yapp4-common.dtsi index 3be38a3c4bb11c..c32ea040fecdda 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6dl-yapp4-common.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6dl-yapp4-common.dtsi @@ -117,17 +117,9 @@ mdio { #address-cells = <1>; #size-cells = <0>; - phy_port2: phy@1 { - reg = <1>; - }; - - phy_port3: phy@2 { - reg = <2>; - }; - switch@10 { compatible = "qca,qca8334"; - reg = <10>; + reg = <0x10>; reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; switch_ports: ports { @@ -149,15 +141,30 @@ fixed-link { eth2: port@2 { reg = <2>; label = "eth2"; + phy-mode = "internal"; phy-handle = <&phy_port2>; }; eth1: port@3 { reg = <3>; label = "eth1"; + phy-mode = "internal"; phy-handle = <&phy_port3>; }; }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + phy_port2: ethernet-phy@1 { + reg = <1>; + }; + + phy_port3: ethernet-phy@2 { + reg = <2>; + }; + }; }; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-yapp43-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx6dl-yapp43-common.dtsi index 52a0f6ee426f97..bcf4d9c870ec97 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6dl-yapp43-common.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6dl-yapp43-common.dtsi @@ -274,24 +274,24 @@ leds: led-controller@30 { led@0 { chan-name = "R"; - led-cur = /bits/ 8 <0x20>; - max-cur = /bits/ 8 <0x60>; + led-cur = /bits/ 8 <0x6e>; + max-cur = /bits/ 8 <0xc8>; reg = <0>; color = ; }; led@1 { chan-name = "G"; - led-cur = /bits/ 8 <0x20>; - max-cur = /bits/ 8 <0x60>; + led-cur = /bits/ 8 <0xbe>; + max-cur = /bits/ 8 <0xc8>; reg = <1>; color = ; }; led@2 { chan-name = "B"; - led-cur = /bits/ 8 <0x20>; - max-cur = /bits/ 8 <0x60>; + led-cur = /bits/ 8 <0xbe>; + max-cur = /bits/ 8 <0xc8>; reg = <2>; color = ; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-apalis-ixora-v1.2.dts b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-ixora-v1.2.dts index 717decda0cebd5..3ac7a45016205a 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6q-apalis-ixora-v1.2.dts +++ b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-ixora-v1.2.dts @@ -76,6 +76,7 @@ reg_can1_supply: regulator-can1-supply { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enable_can1_power>; regulator-name = "can1_supply"; + startup-delay-us = <1000>; }; reg_can2_supply: regulator-can2-supply { @@ -85,6 +86,7 @@ reg_can2_supply: regulator-can2-supply { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enable_can2_power>; regulator-name = "can2_supply"; + startup-delay-us = <1000>; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts b/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts index db8c332df6a1d5..cad112e054758f 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts +++ b/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts @@ -227,7 +227,6 @@ bridge@1,0 { #address-cells = <3>; #size-cells = <2>; - #interrupt-cells = <1>; bridge@2,1 { compatible = "pci10b5,8605"; @@ -235,7 +234,6 @@ bridge@2,1 { #address-cells = <3>; #size-cells = <2>; - #interrupt-cells = <1>; /* Intel Corporation I210 Gigabit Network Connection */ ethernet@3,0 { @@ -250,7 +248,6 @@ bridge@2,2 { #address-cells = <3>; #size-cells = <2>; - #interrupt-cells = <1>; /* Intel Corporation I210 Gigabit Network Connection */ switch_nic: ethernet@4,0 { diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi index 99f4f6ac71d4a1..c1ae7c47b44227 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi @@ -245,6 +245,7 @@ pca9539: pca9539@74 { reg = <0x74>; gpio-controller; #gpio-cells = <2>; + #interrupt-cells = <2>; interrupt-controller; interrupt-parent = <&gpio2>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; @@ -390,7 +391,6 @@ pci_root: root@0,0 { #address-cells = <3>; #size-cells = <2>; - #interrupt-cells = <1>; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-kontron-samx6i.dtsi b/arch/arm/boot/dts/nxp/imx/imx6q-kontron-samx6i.dtsi index 4d6a0c3e8455f9..ff062f4fd726eb 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6q-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6q-kontron-samx6i.dtsi @@ -5,31 +5,8 @@ #include "imx6q.dtsi" #include "imx6qdl-kontron-samx6i.dtsi" -#include / { model = "Kontron SMARC sAMX6i Quad/Dual"; compatible = "kontron,imx6q-samx6i", "fsl,imx6q"; }; - -/* Quad/Dual SoMs have 3 chip-select signals */ -&ecspi4 { - cs-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>, - <&gpio3 29 GPIO_ACTIVE_LOW>, - <&gpio3 25 GPIO_ACTIVE_LOW>; -}; - -&pinctrl_ecspi4 { - fsl,pins = < - MX6QDL_PAD_EIM_D21__ECSPI4_SCLK 0x100b1 - MX6QDL_PAD_EIM_D28__ECSPI4_MOSI 0x100b1 - MX6QDL_PAD_EIM_D22__ECSPI4_MISO 0x100b1 - - /* SPI4_IMX_CS2# - connected to internal flash */ - MX6QDL_PAD_EIM_D24__GPIO3_IO24 0x1b0b0 - /* SPI4_IMX_CS0# - connected to SMARC SPI0_CS0# */ - MX6QDL_PAD_EIM_D29__GPIO3_IO29 0x1b0b0 - /* SPI4_CS3# - connected to SMARC SPI0_CS1# */ - MX6QDL_PAD_EIM_D25__GPIO3_IO25 0x1b0b0 - >; -}; diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts b/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts index a3f247c722b438..0342a79ccd5db2 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts +++ b/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts @@ -37,9 +37,9 @@ panel_in: endpoint { &clks { assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>, - <&clks IMX6QDL_CLK_LDB_DI1_SEL>; + <&clks IMX6QDL_CLK_LDB_DI1_SEL>, <&clks IMX6QDL_CLK_ENET_REF_SEL>; assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, - <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>; + <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, <&clk50m_phy>; }; &hdmi { diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi index 4cc965277c5219..dcb4f6a32f8092 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi @@ -619,7 +619,6 @@ stmpe811@41 { blocks = <0x5>; id = <0>; interrupts = <10 IRQ_TYPE_LEVEL_LOW>; - interrupt-controller; interrupt-parent = <&gpio4>; irq-trigger = <0x1>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi index 11d9c7a2dacb14..6cc4d6fd5f28be 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi @@ -543,7 +543,6 @@ stmpe811@41 { blocks = <0x5>; interrupts = <20 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&gpio6>; - interrupt-controller; id = <0>; irq-trigger = <0x1>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi index a63e73adc1fc53..42b2ba23aefc9e 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi @@ -225,7 +225,6 @@ da9063: pmic@58 { pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio2>; interrupts = <8 IRQ_TYPE_LEVEL_LOW>; - interrupt-controller; onkey { compatible = "dlg,da9063-onkey"; diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-kontron-samx6i.dtsi index 85aeebc9485dd3..668d33d1ff0c1c 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-kontron-samx6i.dtsi @@ -244,7 +244,8 @@ &ecspi4 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_ecspi4>; cs-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>, - <&gpio3 29 GPIO_ACTIVE_LOW>; + <&gpio3 29 GPIO_ACTIVE_LOW>, + <&gpio3 25 GPIO_ACTIVE_LOW>; status = "okay"; /* default boot source: workaround #1 for errata ERR006282 */ @@ -259,7 +260,7 @@ smarc_flash: flash@0 { &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-connection-type = "rgmii-id"; phy-handle = <ðphy>; mdio { @@ -269,7 +270,7 @@ mdio { ethphy: ethernet-phy@1 { compatible = "ethernet-phy-ieee802.3-c22"; reg = <1>; - reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; + reset-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>; reset-assert-us = <1000>; }; }; @@ -464,6 +465,8 @@ MX6QDL_PAD_EIM_D22__ECSPI4_MISO 0x100b1 MX6QDL_PAD_EIM_D24__GPIO3_IO24 0x1b0b0 /* SPI_IMX_CS0# - connected to SMARC SPI0_CS0# */ MX6QDL_PAD_EIM_D29__GPIO3_IO29 0x1b0b0 + /* SPI4_CS3# - connected to SMARC SPI0_CS1# */ + MX6QDL_PAD_EIM_D25__GPIO3_IO25 0x1b0b0 >; }; @@ -516,7 +519,7 @@ MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b0b0 MX6QDL_PAD_ENET_MDIO__ENET_MDIO 0x1b0b0 MX6QDL_PAD_ENET_MDC__ENET_MDC 0x1b0b0 MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK 0x1b0b0 - MX6QDL_PAD_ENET_CRS_DV__GPIO1_IO25 0x1b0b0 /* RST_GBE0_PHY# */ + MX6QDL_PAD_NANDF_D1__GPIO2_IO01 0x1b0b0 /* RST_GBE0_PHY# */ >; }; @@ -729,7 +732,7 @@ &pcie { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pcie>; wake-up-gpio = <&gpio6 18 GPIO_ACTIVE_HIGH>; - reset-gpio = <&gpio3 13 GPIO_ACTIVE_HIGH>; + reset-gpio = <&gpio3 13 GPIO_ACTIVE_LOW>; }; /* LCD_BKLT_PWM */ @@ -817,5 +820,6 @@ &wdog1 { /* CPLD is feeded by watchdog (hardwired) */ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_wdog1>; + fsl,ext-reset-output; status = "okay"; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi index 113974520d544b..c0c47adc5866e3 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi @@ -124,6 +124,7 @@ pmic@58 { reg = <0x58>; interrupt-parent = <&gpio2>; interrupts = <9 IRQ_TYPE_LEVEL_LOW>; /* active-low GPIO2_9 */ + #interrupt-cells = <2>; interrupt-controller; regulators { diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi index 86b4269e0e0117..85e278eb201610 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi @@ -100,6 +100,7 @@ pmic: pmic@58 { interrupt-parent = <&gpio1>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; gpio-controller; #gpio-cells = <2>; diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts b/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts index 875ae699c5cb80..ce9f4c22672939 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts +++ b/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts @@ -366,7 +366,7 @@ MX6UL_PAD_ENET1_RX_ER__PWM8_OUT 0x110b0 }; pinctrl_tsc: tscgrp { - fsl,pin = < + fsl,pins = < MX6UL_PAD_GPIO1_IO01__GPIO1_IO01 0xb0 MX6UL_PAD_GPIO1_IO02__GPIO1_IO02 0xb0 MX6UL_PAD_GPIO1_IO03__GPIO1_IO03 0xb0 diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi index 4ffe99ed55ca2c..07dcecbe485dca 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi @@ -121,6 +121,8 @@ ethphy1: ethernet-phy@1 { max-speed = <100>; interrupt-parent = <&gpio5>; interrupts = <6 IRQ_TYPE_LEVEL_LOW>; + clocks = <&clks IMX6UL_CLK_ENET_REF>; + clock-names = "rmii-ref"; }; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-phytec-tauri.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-phytec-tauri.dtsi index ea627638e40cf6..7dd1fe5a2fb768 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6ull-phytec-tauri.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6ull-phytec-tauri.dtsi @@ -121,7 +121,7 @@ &ecspi1 { tpm_tis: tpm@1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_tpm>; - compatible = "tcg,tpm_tis-spi"; + compatible = "infineon,slb9670", "tcg,tpm_tis-spi"; reg = <1>; spi-max-frequency = <20000000>; interrupt-parent = <&gpio5>; diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi index 3fdece5bd31f9d..5248a058230c86 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi @@ -805,6 +805,7 @@ &usbotg1 { &pinctrl_usb_pwr>; dr_mode = "host"; power-active-high; + over-current-active-low; disable-over-current; status = "okay"; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-flex-concentrator.dts b/arch/arm/boot/dts/nxp/imx/imx7d-flex-concentrator.dts index 3a723843d5626f..9984b343cdf0ca 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7d-flex-concentrator.dts +++ b/arch/arm/boot/dts/nxp/imx/imx7d-flex-concentrator.dts @@ -130,7 +130,7 @@ &ecspi4 { * TCG specification - Section 6.4.1 Clocking: * TPM shall support a SPI clock frequency range of 10-24 MHz. */ - st33htph: tpm-tis@0 { + st33htph: tpm@0 { compatible = "st,st33htpm-spi", "tcg,tpm_tis-spi"; reg = <0>; spi-max-frequency = <24000000>; diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts b/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts index 12361fcbe24aff..1b965652291bfa 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts +++ b/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts @@ -63,6 +63,7 @@ pca9554: io-expander@25 { gpio-controller; #gpio-cells = <2>; #interrupt-cells = <2>; + interrupt-controller; reg = <0x25>; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-zii-rmu2.dts b/arch/arm/boot/dts/nxp/imx/imx7d-zii-rmu2.dts index 521493342fe972..8f5566027c25a2 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7d-zii-rmu2.dts +++ b/arch/arm/boot/dts/nxp/imx/imx7d-zii-rmu2.dts @@ -350,7 +350,7 @@ MX7D_PAD_SD3_RESET_B__SD3_RESET_B 0x59 &iomuxc_lpsr { pinctrl_enet1_phy_interrupt: enet1phyinterruptgrp { - fsl,phy = < + fsl,pins = < MX7D_PAD_LPSR_GPIO1_IO02__GPIO1_IO2 0x08 >; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx7d.dtsi b/arch/arm/boot/dts/nxp/imx/imx7d.dtsi index 4b94b8afb55d91..0484e349e064e4 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7d.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx7d.dtsi @@ -217,9 +217,6 @@ fec2: ethernet@30bf0000 { }; &ca_funnel_in_ports { - #address-cells = <1>; - #size-cells = <0>; - port@1 { reg = <1>; ca_funnel_in_port1: endpoint { diff --git a/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts b/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts index ba7231b364bb8c..7bab113ca6da79 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts +++ b/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts @@ -210,6 +210,7 @@ ov2680_to_mipi: endpoint { remote-endpoint = <&mipi_from_sensor>; clock-lanes = <0>; data-lanes = <1>; + link-frequencies = /bits/ 64 <330000000>; }; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi index e152d08f27d49e..39e9f1411ebb80 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi @@ -190,7 +190,11 @@ funnel@30041000 { clock-names = "apb_pclk"; ca_funnel_in_ports: in-ports { - port { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; ca_funnel_in_port0: endpoint { remote-endpoint = <&etm0_out_port>; }; @@ -454,7 +458,7 @@ iomuxc_lpsr: pinctrl@302c0000 { }; gpt1: timer@302d0000 { - compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; + compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt"; reg = <0x302d0000 0x10000>; interrupts = ; clocks = <&clks IMX7D_GPT1_ROOT_CLK>, @@ -463,7 +467,7 @@ gpt1: timer@302d0000 { }; gpt2: timer@302e0000 { - compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; + compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt"; reg = <0x302e0000 0x10000>; interrupts = ; clocks = <&clks IMX7D_GPT2_ROOT_CLK>, @@ -473,7 +477,7 @@ gpt2: timer@302e0000 { }; gpt3: timer@302f0000 { - compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; + compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt"; reg = <0x302f0000 0x10000>; interrupts = ; clocks = <&clks IMX7D_GPT3_ROOT_CLK>, @@ -483,7 +487,7 @@ gpt3: timer@302f0000 { }; gpt4: timer@30300000 { - compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; + compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt"; reg = <0x30300000 0x10000>; interrupts = ; clocks = <&clks IMX7D_GPT4_ROOT_CLK>, @@ -814,7 +818,7 @@ csi_from_csi_mux: endpoint { }; lcdif: lcdif@30730000 { - compatible = "fsl,imx7d-lcdif", "fsl,imx28-lcdif"; + compatible = "fsl,imx7d-lcdif", "fsl,imx6sx-lcdif"; reg = <0x30730000 0x10000>; interrupts = ; clocks = <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>, @@ -1278,7 +1282,7 @@ dma_apbh: dma-controller@33000000 { gpmi: nand-controller@33002000 { compatible = "fsl,imx7d-gpmi-nand"; #address-cells = <1>; - #size-cells = <1>; + #size-cells = <0>; reg = <0x33002000 0x2000>, <0x33004000 0x4000>; reg-names = "gpmi-nand", "bch"; interrupts = ; diff --git a/arch/arm/boot/dts/nxp/mxs/imx23-sansa.dts b/arch/arm/boot/dts/nxp/mxs/imx23-sansa.dts index 46057d9bf555b6..c2efcc20ae8026 100644 --- a/arch/arm/boot/dts/nxp/mxs/imx23-sansa.dts +++ b/arch/arm/boot/dts/nxp/mxs/imx23-sansa.dts @@ -175,10 +175,8 @@ i2c-0 { #address-cells = <1>; #size-cells = <0>; compatible = "i2c-gpio"; - gpios = < - &gpio1 24 0 /* SDA */ - &gpio1 22 0 /* SCL */ - >; + sda-gpios = <&gpio1 24 0>; + scl-gpios = <&gpio1 22 0>; i2c-gpio,delay-us = <2>; /* ~100 kHz */ }; @@ -186,10 +184,8 @@ i2c-1 { #address-cells = <1>; #size-cells = <0>; compatible = "i2c-gpio"; - gpios = < - &gpio0 31 0 /* SDA */ - &gpio0 30 0 /* SCL */ - >; + sda-gpios = <&gpio0 31 0>; + scl-gpios = <&gpio0 30 0>; i2c-gpio,delay-us = <2>; /* ~100 kHz */ touch: touch@20 { diff --git a/arch/arm/boot/dts/nxp/mxs/imx23.dtsi b/arch/arm/boot/dts/nxp/mxs/imx23.dtsi index 5eca942a52fd44..14c07b585f8220 100644 --- a/arch/arm/boot/dts/nxp/mxs/imx23.dtsi +++ b/arch/arm/boot/dts/nxp/mxs/imx23.dtsi @@ -412,7 +412,7 @@ emi@80020000 { status = "disabled"; }; - dma_apbx: dma-apbx@80024000 { + dma_apbx: dma-controller@80024000 { compatible = "fsl,imx23-dma-apbx"; reg = <0x80024000 0x2000>; interrupts = <7>, <5>, <9>, <26>, diff --git a/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts b/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts index a400c108f66a2d..6c5e6856648af9 100644 --- a/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts +++ b/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts @@ -8,6 +8,7 @@ #include "imx28-lwe.dtsi" / { + model = "Liebherr XEA board"; compatible = "lwn,imx28-xea", "fsl,imx28"; }; diff --git a/arch/arm/boot/dts/nxp/mxs/imx28.dtsi b/arch/arm/boot/dts/nxp/mxs/imx28.dtsi index 763adeb995ee76..9b73130887ea14 100644 --- a/arch/arm/boot/dts/nxp/mxs/imx28.dtsi +++ b/arch/arm/boot/dts/nxp/mxs/imx28.dtsi @@ -990,7 +990,7 @@ etm: etm@80022000 { status = "disabled"; }; - dma_apbx: dma-apbx@80024000 { + dma_apbx: dma-controller@80024000 { compatible = "fsl,imx28-dma-apbx"; reg = <0x80024000 0x2000>; interrupts = <78>, <79>, <66>, <0>, diff --git a/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts index 16b4e06c4efad3..a248b8a4534210 100644 --- a/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts +++ b/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts @@ -338,6 +338,7 @@ gpio6: io-expander@22 { reg = <0x22>; gpio-controller; #gpio-cells = <2>; + #interrupt-cells = <2>; interrupt-controller; interrupt-parent = <&gpio3>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; diff --git a/arch/arm/boot/dts/qcom/pm8226.dtsi b/arch/arm/boot/dts/qcom/pm8226.dtsi new file mode 100644 index 00000000000000..2413778f371507 --- /dev/null +++ b/arch/arm/boot/dts/qcom/pm8226.dtsi @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: BSD-3-Clause +#include +#include +#include +#include + +/ { + thermal-zones { + pm8226-thermal { + polling-delay-passive = <100>; + polling-delay = <0>; + thermal-sensors = <&pm8226_temp>; + + trips { + trip0 { + temperature = <105000>; + hysteresis = <2000>; + type = "passive"; + }; + + trip1 { + temperature = <125000>; + hysteresis = <2000>; + type = "hot"; + }; + + crit { + temperature = <145000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + }; + }; +}; + +&spmi_bus { + pm8226_0: pm8226@0 { + compatible = "qcom,pm8226", "qcom,spmi-pmic"; + reg = <0x0 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pon@800 { + compatible = "qcom,pm8916-pon"; + reg = <0x800>; + + pwrkey { + compatible = "qcom,pm8941-pwrkey"; + interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>; + debounce = <15625>; + bias-pull-up; + linux,code = ; + }; + + pm8226_resin: resin { + compatible = "qcom,pm8941-resin"; + interrupts = <0x0 0x8 1 IRQ_TYPE_EDGE_BOTH>; + debounce = <15625>; + bias-pull-up; + status = "disabled"; + }; + }; + + smbb: charger@1000 { + compatible = "qcom,pm8226-charger"; + reg = <0x1000>; + interrupts = <0x0 0x10 7 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x10 5 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x10 4 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x12 1 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x12 0 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x13 2 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x13 1 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x14 1 IRQ_TYPE_EDGE_BOTH>; + interrupt-names = "chg-done", + "chg-fast", + "chg-trkl", + "bat-temp-ok", + "bat-present", + "chg-gone", + "usb-valid", + "dc-valid"; + + chg_otg: otg-vbus { }; + }; + + pm8226_temp: temp-alarm@2400 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0x2400>; + interrupts = <0 0x24 0 IRQ_TYPE_EDGE_RISING>; + io-channels = <&pm8226_vadc VADC_DIE_TEMP>; + io-channel-names = "thermal"; + #thermal-sensor-cells = <0>; + }; + + pm8226_vadc: adc@3100 { + compatible = "qcom,spmi-vadc"; + reg = <0x3100>; + interrupts = <0x0 0x31 0x0 IRQ_TYPE_EDGE_RISING>; + #address-cells = <1>; + #size-cells = <0>; + #io-channel-cells = <1>; + + channel@7 { + reg = ; + qcom,pre-scaling = <1 3>; + label = "vph_pwr"; + }; + channel@8 { + reg = ; + label = "die_temp"; + }; + channel@9 { + reg = ; + label = "ref_625mv"; + }; + channel@a { + reg = ; + label = "ref_1250mv"; + }; + channel@e { + reg = ; + }; + channel@f { + reg = ; + }; + }; + + pm8226_iadc: adc@3600 { + compatible = "qcom,pm8226-iadc", "qcom,spmi-iadc"; + reg = <0x3600>; + interrupts = <0x0 0x36 0x0 IRQ_TYPE_EDGE_RISING>; + }; + + rtc@6000 { + compatible = "qcom,pm8941-rtc"; + reg = <0x6000>, <0x6100>; + reg-names = "rtc", "alarm"; + interrupts = <0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>; + }; + + pm8226_mpps: mpps@a000 { + compatible = "qcom,pm8226-mpp", "qcom,spmi-mpp"; + reg = <0xa000>; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pm8226_mpps 0 0 8>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + pm8226_gpios: gpio@c000 { + compatible = "qcom,pm8226-gpio", "qcom,spmi-gpio"; + reg = <0xc000>; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pm8226_gpios 0 0 8>; + interrupt-controller; + #interrupt-cells = <2>; + }; + }; + + pm8226_1: pm8226@1 { + compatible = "qcom,pm8226", "qcom,spmi-pmic"; + reg = <0x1 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pm8226_spmi_regulators: regulators { + compatible = "qcom,pm8226-regulators"; + }; + + pm8226_vib: vibrator@c000 { + compatible = "qcom,pm8916-vib"; + reg = <0xc000>; + status = "disabled"; + }; + }; +}; diff --git a/arch/arm/boot/dts/qcom/pm8841.dtsi b/arch/arm/boot/dts/qcom/pm8841.dtsi new file mode 100644 index 00000000000000..3bf2ce5c86a641 --- /dev/null +++ b/arch/arm/boot/dts/qcom/pm8841.dtsi @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include + + +/ { + thermal-zones { + pm8841-thermal { + polling-delay-passive = <100>; + polling-delay = <0>; + thermal-sensors = <&pm8841_temp>; + + trips { + trip0 { + temperature = <105000>; + hysteresis = <2000>; + type = "passive"; + }; + + trip1 { + temperature = <125000>; + hysteresis = <2000>; + type = "hot"; + }; + + crit { + temperature = <140000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + }; + }; +}; + +&spmi_bus { + + pm8841_0: pm8841@4 { + compatible = "qcom,pm8841", "qcom,spmi-pmic"; + reg = <0x4 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pm8841_mpps: mpps@a000 { + compatible = "qcom,pm8841-mpp", "qcom,spmi-mpp"; + reg = <0xa000>; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pm8841_mpps 0 0 4>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + pm8841_temp: temp-alarm@2400 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0x2400>; + interrupts = <4 0x24 0 IRQ_TYPE_EDGE_RISING>; + #thermal-sensor-cells = <0>; + }; + }; + + pm8841_1: pm8841@5 { + compatible = "qcom,pm8841", "qcom,spmi-pmic"; + reg = <0x5 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + }; +}; diff --git a/arch/arm/boot/dts/qcom/pm8941.dtsi b/arch/arm/boot/dts/qcom/pm8941.dtsi new file mode 100644 index 00000000000000..ed0ba591c75581 --- /dev/null +++ b/arch/arm/boot/dts/qcom/pm8941.dtsi @@ -0,0 +1,254 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include + + +/ { + thermal-zones { + pm8941-thermal { + polling-delay-passive = <100>; + polling-delay = <0>; + thermal-sensors = <&pm8941_temp>; + + trips { + trip0 { + temperature = <105000>; + hysteresis = <2000>; + type = "passive"; + }; + + trip1 { + temperature = <125000>; + hysteresis = <2000>; + type = "hot"; + }; + + crit { + temperature = <145000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + }; + }; +}; + +&spmi_bus { + + pm8941_0: pm8941@0 { + compatible = "qcom,pm8941", "qcom,spmi-pmic"; + reg = <0x0 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + rtc@6000 { + compatible = "qcom,pm8941-rtc"; + reg = <0x6000>, + <0x6100>; + reg-names = "rtc", "alarm"; + interrupts = <0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>; + }; + + pon@800 { + compatible = "qcom,pm8941-pon"; + reg = <0x800>; + + pwrkey { + compatible = "qcom,pm8941-pwrkey"; + interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>; + debounce = <15625>; + bias-pull-up; + }; + + pm8941_resin: resin { + compatible = "qcom,pm8941-resin"; + interrupts = <0x0 0x8 1 IRQ_TYPE_EDGE_BOTH>; + debounce = <15625>; + bias-pull-up; + status = "disabled"; + }; + }; + + usb_id: usb-detect@900 { + compatible = "qcom,pm8941-misc"; + reg = <0x900>; + interrupts = <0x0 0x9 0 IRQ_TYPE_EDGE_BOTH>; + interrupt-names = "usb_id"; + }; + + smbb: charger@1000 { + compatible = "qcom,pm8941-charger"; + reg = <0x1000>; + interrupts = <0x0 0x10 7 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x10 5 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x10 4 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x12 1 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x12 0 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x13 2 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x13 1 IRQ_TYPE_EDGE_BOTH>, + <0x0 0x14 1 IRQ_TYPE_EDGE_BOTH>; + interrupt-names = "chg-done", + "chg-fast", + "chg-trkl", + "bat-temp-ok", + "bat-present", + "chg-gone", + "usb-valid", + "dc-valid"; + + usb-otg-in-supply = <&pm8941_5vs1>; + + chg_otg: otg-vbus { }; + }; + + pm8941_gpios: gpio@c000 { + compatible = "qcom,pm8941-gpio", "qcom,spmi-gpio"; + reg = <0xc000>; + gpio-controller; + gpio-ranges = <&pm8941_gpios 0 0 36>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + + boost_bypass_n_pin: boost-bypass-state { + pins = "gpio21"; + function = "normal"; + }; + }; + + pm8941_mpps: mpps@a000 { + compatible = "qcom,pm8941-mpp", "qcom,spmi-mpp"; + reg = <0xa000>; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pm8941_mpps 0 0 8>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + pm8941_temp: temp-alarm@2400 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0x2400>; + interrupts = <0 0x24 0 IRQ_TYPE_EDGE_RISING>; + io-channels = <&pm8941_vadc VADC_DIE_TEMP>; + io-channel-names = "thermal"; + #thermal-sensor-cells = <0>; + }; + + pm8941_vadc: adc@3100 { + compatible = "qcom,spmi-vadc"; + reg = <0x3100>; + interrupts = <0x0 0x31 0x0 IRQ_TYPE_EDGE_RISING>; + #address-cells = <1>; + #size-cells = <0>; + #io-channel-cells = <1>; + + + channel@6 { + reg = ; + }; + + channel@8 { + reg = ; + }; + + channel@9 { + reg = ; + }; + + channel@a { + reg = ; + }; + + channel@e { + reg = ; + }; + + channel@f { + reg = ; + }; + + channel@30 { + reg = ; + }; + }; + + pm8941_iadc: adc@3600 { + compatible = "qcom,pm8941-iadc", "qcom,spmi-iadc"; + reg = <0x3600>; + interrupts = <0x0 0x36 0x0 IRQ_TYPE_EDGE_RISING>; + qcom,external-resistor-micro-ohms = <10000>; + }; + + pm8941_coincell: charger@2800 { + compatible = "qcom,pm8941-coincell"; + reg = <0x2800>; + status = "disabled"; + }; + }; + + pm8941_1: pm8941@1 { + compatible = "qcom,pm8941", "qcom,spmi-pmic"; + reg = <0x1 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pm8941_lpg: pwm { + compatible = "qcom,pm8941-lpg"; + + #address-cells = <1>; + #size-cells = <0>; + #pwm-cells = <2>; + + status = "disabled"; + }; + + pm8941_vib: vibrator@c000 { + compatible = "qcom,pm8916-vib"; + reg = <0xc000>; + status = "disabled"; + }; + + pm8941_wled: wled@d800 { + compatible = "qcom,pm8941-wled"; + reg = <0xd800>; + label = "backlight"; + + status = "disabled"; + }; + + regulators { + compatible = "qcom,pm8941-regulators"; + interrupts = <0x1 0x83 0x2 0>, <0x1 0x84 0x2 0>; + interrupt-names = "ocp-5vs1", "ocp-5vs2"; + vin_5vs-supply = <&pm8941_5v>; + + pm8941_5v: s4 { + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-enable-ramp-delay = <500>; + }; + + pm8941_5vs1: 5vs1 { + regulator-enable-ramp-delay = <1000>; + regulator-pull-down; + regulator-over-current-protection; + qcom,ocp-max-retries = <10>; + qcom,ocp-retry-delay = <30>; + qcom,vs-soft-start-strength = <0>; + regulator-initial-mode = <1>; + }; + + pm8941_5vs2: 5vs2 { + regulator-enable-ramp-delay = <1000>; + regulator-pull-down; + regulator-over-current-protection; + qcom,ocp-max-retries = <10>; + qcom,ocp-retry-delay = <30>; + qcom,vs-soft-start-strength = <0>; + regulator-initial-mode = <1>; + }; + }; + }; +}; diff --git a/arch/arm/boot/dts/qcom/pma8084.dtsi b/arch/arm/boot/dts/qcom/pma8084.dtsi new file mode 100644 index 00000000000000..2985f4805b93ee --- /dev/null +++ b/arch/arm/boot/dts/qcom/pma8084.dtsi @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include + +&spmi_bus { + + pma8084_0: pma8084@0 { + compatible = "qcom,pma8084", "qcom,spmi-pmic"; + reg = <0x0 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + rtc@6000 { + compatible = "qcom,pm8941-rtc"; + reg = <0x6000>, + <0x6100>; + reg-names = "rtc", "alarm"; + interrupts = <0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>; + }; + + pwrkey@800 { + compatible = "qcom,pm8941-pwrkey"; + reg = <0x800>; + interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>; + debounce = <15625>; + bias-pull-up; + }; + + pma8084_gpios: gpio@c000 { + compatible = "qcom,pma8084-gpio", "qcom,spmi-gpio"; + reg = <0xc000>; + gpio-controller; + gpio-ranges = <&pma8084_gpios 0 0 22>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + pma8084_mpps: mpps@a000 { + compatible = "qcom,pma8084-mpp", "qcom,spmi-mpp"; + reg = <0xa000>; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pma8084_mpps 0 0 8>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + pma8084_temp: temp-alarm@2400 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0x2400>; + interrupts = <0 0x24 0 IRQ_TYPE_EDGE_RISING>; + #thermal-sensor-cells = <0>; + io-channels = <&pma8084_vadc VADC_DIE_TEMP>; + io-channel-names = "thermal"; + }; + + pma8084_vadc: adc@3100 { + compatible = "qcom,spmi-vadc"; + reg = <0x3100>; + interrupts = <0x0 0x31 0x0 IRQ_TYPE_EDGE_RISING>; + #address-cells = <1>; + #size-cells = <0>; + #io-channel-cells = <1>; + + channel@8 { + reg = ; + }; + + channel@9 { + reg = ; + }; + + channel@a { + reg = ; + }; + + channel@c { + reg = ; + }; + + channel@e { + reg = ; + }; + + channel@f { + reg = ; + }; + }; + }; + + pma8084_1: pma8084@1 { + compatible = "qcom,pma8084", "qcom,spmi-pmic"; + reg = <0x1 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + }; +}; diff --git a/arch/arm/boot/dts/qcom/pmx55.dtsi b/arch/arm/boot/dts/qcom/pmx55.dtsi new file mode 100644 index 00000000000000..da0851173c6997 --- /dev/null +++ b/arch/arm/boot/dts/qcom/pmx55.dtsi @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: BSD-3-Clause + +/* + * Copyright (c) 2018-2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2020, Linaro Limited + */ + +#include +#include +#include + +&spmi_bus { + pmic@8 { + compatible = "qcom,pmx55", "qcom,spmi-pmic"; + reg = <0x8 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pon@800 { + compatible = "qcom,pm8916-pon"; + reg = <0x0800>; + + status = "disabled"; + }; + + pmx55_temp: temp-alarm@2400 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0x2400>; + interrupts = <0x8 0x24 0x0 IRQ_TYPE_EDGE_BOTH>; + io-channels = <&pmx55_adc ADC5_DIE_TEMP>; + io-channel-names = "thermal"; + #thermal-sensor-cells = <0>; + }; + + pmx55_adc: adc@3100 { + compatible = "qcom,spmi-adc5"; + reg = <0x3100>; + #address-cells = <1>; + #size-cells = <0>; + #io-channel-cells = <1>; + interrupts = <0x8 0x31 0x0 IRQ_TYPE_EDGE_RISING>; + + channel@0 { + reg = ; + qcom,pre-scaling = <1 1>; + label = "ref_gnd"; + }; + + channel@1 { + reg = ; + qcom,pre-scaling = <1 1>; + label = "vref_1p25"; + }; + + channel@6 { + reg = ; + qcom,pre-scaling = <1 1>; + label = "die_temp"; + }; + + channel@9 { + reg = ; + qcom,pre-scaling = <1 1>; + label = "chg_temp"; + }; + }; + + pmx55_gpios: gpio@c000 { + compatible = "qcom,pmx55-gpio", "qcom,spmi-gpio"; + reg = <0xc000>; + gpio-controller; + gpio-ranges = <&pmx55_gpios 0 0 11>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + }; + + pmic@9 { + compatible = "qcom,pmx55", "qcom,spmi-pmic"; + reg = <0x9 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + }; +}; diff --git a/arch/arm/boot/dts/qcom/pmx65.dtsi b/arch/arm/boot/dts/qcom/pmx65.dtsi new file mode 100644 index 00000000000000..1c7fdf59c1f56a --- /dev/null +++ b/arch/arm/boot/dts/qcom/pmx65.dtsi @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include + +&spmi_bus { + pmic@1 { + compatible = "qcom,pmx65", "qcom,spmi-pmic"; + reg = <1 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + pmx65_temp: temp-alarm@a00 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0xa00>; + interrupts = <0x1 0xa 0x0 IRQ_TYPE_EDGE_BOTH>; + #thermal-sensor-cells = <0>; + }; + + pmx65_gpios: gpio@8800 { + compatible = "qcom,pmx65-gpio", "qcom,spmi-gpio"; + reg = <0x8800>; + gpio-controller; + gpio-ranges = <&pmx65_gpios 0 0 16>; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + }; +}; diff --git a/arch/arm/boot/dts/qcom/qcom-apq8026-asus-sparrow.dts b/arch/arm/boot/dts/qcom/qcom-apq8026-asus-sparrow.dts index aa0e0e8d2a973e..a39f5a161b03bb 100644 --- a/arch/arm/boot/dts/qcom/qcom-apq8026-asus-sparrow.dts +++ b/arch/arm/boot/dts/qcom/qcom-apq8026-asus-sparrow.dts @@ -6,7 +6,7 @@ /dts-v1/; #include "qcom-msm8226.dtsi" -#include "qcom-pm8226.dtsi" +#include "pm8226.dtsi" /delete-node/ &adsp_region; diff --git a/arch/arm/boot/dts/qcom/qcom-apq8026-huawei-sturgeon.dts b/arch/arm/boot/dts/qcom/qcom-apq8026-huawei-sturgeon.dts index de19640efe5538..59b218042d32dd 100644 --- a/arch/arm/boot/dts/qcom/qcom-apq8026-huawei-sturgeon.dts +++ b/arch/arm/boot/dts/qcom/qcom-apq8026-huawei-sturgeon.dts @@ -6,7 +6,7 @@ /dts-v1/; #include "qcom-msm8226.dtsi" -#include "qcom-pm8226.dtsi" +#include "pm8226.dtsi" #include /delete-node/ &adsp_region; diff --git a/arch/arm/boot/dts/qcom/qcom-apq8026-lg-lenok.dts b/arch/arm/boot/dts/qcom/qcom-apq8026-lg-lenok.dts index b887e5361ec3a2..feb78afef3a6e0 100644 --- a/arch/arm/boot/dts/qcom/qcom-apq8026-lg-lenok.dts +++ b/arch/arm/boot/dts/qcom/qcom-apq8026-lg-lenok.dts @@ -6,7 +6,7 @@ /dts-v1/; #include "qcom-msm8226.dtsi" -#include "qcom-pm8226.dtsi" +#include "pm8226.dtsi" /delete-node/ &adsp_region; diff --git a/arch/arm/boot/dts/qcom/qcom-apq8026-samsung-matisse-wifi.dts b/arch/arm/boot/dts/qcom/qcom-apq8026-samsung-matisse-wifi.dts index 884d99297d4cf1..cffc069712b2f1 100644 --- a/arch/arm/boot/dts/qcom/qcom-apq8026-samsung-matisse-wifi.dts +++ b/arch/arm/boot/dts/qcom/qcom-apq8026-samsung-matisse-wifi.dts @@ -7,7 +7,7 @@ #include #include "qcom-msm8226.dtsi" -#include "qcom-pm8226.dtsi" +#include "pm8226.dtsi" /delete-node/ &adsp_region; /delete-node/ &smem_region; @@ -45,11 +45,11 @@ gpio-hall-sensor { event-hall-sensor { label = "Hall Effect Sensor"; - gpios = <&tlmm 110 GPIO_ACTIVE_HIGH>; - interrupts = <&tlmm 110 IRQ_TYPE_EDGE_FALLING>; + gpios = <&tlmm 110 GPIO_ACTIVE_LOW>; linux,input-type = ; linux,code = ; debounce-interval = <15>; + linux,can-disable; wakeup-source; }; }; diff --git a/arch/arm/boot/dts/qcom/qcom-apq8060-dragonboard.dts b/arch/arm/boot/dts/qcom/qcom-apq8060-dragonboard.dts index db4c791b2e2fb2..48fd1a1feea342 100644 --- a/arch/arm/boot/dts/qcom/qcom-apq8060-dragonboard.dts +++ b/arch/arm/boot/dts/qcom/qcom-apq8060-dragonboard.dts @@ -72,7 +72,7 @@ cm3605 { /* Trig on both edges - getting close or far away */ interrupts-extended = <&pm8058_gpio 34 IRQ_TYPE_EDGE_BOTH>; /* MPP05 analog input to the XOADC */ - io-channels = <&xoadc 0x00 0x05>; + io-channels = <&pm8058_xoadc 0x00 0x05>; io-channel-names = "aout"; pinctrl-names = "default"; pinctrl-0 = <&dragon_cm3605_gpios>, <&dragon_cm3605_mpps>; @@ -945,7 +945,7 @@ irq-pins { }; }; -&xoadc { +&pm8058_xoadc { /* Reference voltage 2.2 V */ xoadc-ref-supply = <&pm8058_l18>; diff --git a/arch/arm/boot/dts/qcom/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom/qcom-apq8064.dtsi index 516f0d2495e2d0..950adb63af7016 100644 --- a/arch/arm/boot/dts/qcom/qcom-apq8064.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-apq8064.dtsi @@ -738,7 +738,7 @@ pwrkey@1c { xoadc: xoadc@197 { compatible = "qcom,pm8921-adc"; - reg = <197>; + reg = <0x197>; interrupts-extended = <&pmicintc 78 IRQ_TYPE_EDGE_RISING>; #address-cells = <2>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/qcom/qcom-apq8074-dragonboard.dts b/arch/arm/boot/dts/qcom/qcom-apq8074-dragonboard.dts index 6d1b2439ae3ace..950fa652f9856a 100644 --- a/arch/arm/boot/dts/qcom/qcom-apq8074-dragonboard.dts +++ b/arch/arm/boot/dts/qcom/qcom-apq8074-dragonboard.dts @@ -4,8 +4,8 @@ #include #include #include "qcom-msm8974.dtsi" -#include "qcom-pm8841.dtsi" -#include "qcom-pm8941.dtsi" +#include "pm8841.dtsi" +#include "pm8941.dtsi" /delete-node/ &mpss_region; diff --git a/arch/arm/boot/dts/qcom/qcom-apq8084-ifc6540.dts b/arch/arm/boot/dts/qcom/qcom-apq8084-ifc6540.dts index 116e59a3b76d01..1df24c922be9f3 100644 --- a/arch/arm/boot/dts/qcom/qcom-apq8084-ifc6540.dts +++ b/arch/arm/boot/dts/qcom/qcom-apq8084-ifc6540.dts @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "qcom-apq8084.dtsi" -#include "qcom-pma8084.dtsi" +#include "pma8084.dtsi" / { model = "Qualcomm APQ8084/IFC6540"; diff --git a/arch/arm/boot/dts/qcom/qcom-apq8084-mtp.dts b/arch/arm/boot/dts/qcom/qcom-apq8084-mtp.dts index c6b6680248a69e..d4e6aee034afd1 100644 --- a/arch/arm/boot/dts/qcom/qcom-apq8084-mtp.dts +++ b/arch/arm/boot/dts/qcom/qcom-apq8084-mtp.dts @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "qcom-apq8084.dtsi" -#include "qcom-pma8084.dtsi" +#include "pma8084.dtsi" / { model = "Qualcomm APQ 8084-MTP"; diff --git a/arch/arm/boot/dts/qcom/qcom-mdm9615-wp8548.dtsi b/arch/arm/boot/dts/qcom/qcom-mdm9615-wp8548.dtsi index 92c8003dac252d..dac3aa793f7115 100644 --- a/arch/arm/boot/dts/qcom/qcom-mdm9615-wp8548.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-mdm9615-wp8548.dtsi @@ -76,7 +76,7 @@ reset-out-pins { }; }; -&pmicgpio { +&pm8018_gpio { usb_vbus_5v_pins: usb-vbus-5v-state { pins = "gpio4"; function = "normal"; diff --git a/arch/arm/boot/dts/qcom/qcom-mdm9615.dtsi b/arch/arm/boot/dts/qcom/qcom-mdm9615.dtsi index fc4f52f9e9f7dc..c0a60bae703b11 100644 --- a/arch/arm/boot/dts/qcom/qcom-mdm9615.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-mdm9615.dtsi @@ -47,14 +47,12 @@ cxo_board: cxo_board { }; }; - regulators { - vsdcc_fixed: vsdcc-regulator { - compatible = "regulator-fixed"; - regulator-name = "SDCC Power"; - regulator-min-microvolt = <2700000>; - regulator-max-microvolt = <2700000>; - regulator-always-on; - }; + vsdcc_fixed: vsdcc-regulator { + compatible = "regulator-fixed"; + regulator-name = "SDCC Power"; + regulator-min-microvolt = <2700000>; + regulator-max-microvolt = <2700000>; + regulator-always-on; }; soc: soc { @@ -263,7 +261,7 @@ qcom,ssbi@500000 { reg = <0x500000 0x1000>; qcom,controller-type = "pmic-arbiter"; - pmicintc: pmic { + pm8018: pmic { compatible = "qcom,pm8018", "qcom,pm8921"; interrupts = ; #interrupt-cells = <2>; @@ -274,38 +272,38 @@ pmicintc: pmic { pwrkey@1c { compatible = "qcom,pm8018-pwrkey", "qcom,pm8921-pwrkey"; reg = <0x1c>; - interrupt-parent = <&pmicintc>; + interrupt-parent = <&pm8018>; interrupts = <50 IRQ_TYPE_EDGE_RISING>, <51 IRQ_TYPE_EDGE_RISING>; debounce = <15625>; pull-up; }; - pmicmpp: mpps@50 { + pm8018_mpps: mpps@50 { compatible = "qcom,pm8018-mpp", "qcom,ssbi-mpp"; interrupt-controller; #interrupt-cells = <2>; reg = <0x50>; gpio-controller; #gpio-cells = <2>; - gpio-ranges = <&pmicmpp 0 0 6>; + gpio-ranges = <&pm8018_mpps 0 0 6>; }; rtc@11d { compatible = "qcom,pm8018-rtc", "qcom,pm8921-rtc"; - interrupt-parent = <&pmicintc>; + interrupt-parent = <&pm8018>; interrupts = <39 IRQ_TYPE_EDGE_RISING>; reg = <0x11d>; allow-set-time; }; - pmicgpio: gpio@150 { + pm8018_gpio: gpio@150 { compatible = "qcom,pm8018-gpio", "qcom,ssbi-gpio"; reg = <0x150>; interrupt-controller; #interrupt-cells = <2>; gpio-controller; - gpio-ranges = <&pmicgpio 0 0 6>; + gpio-ranges = <&pm8018_gpio 0 0 6>; #gpio-cells = <2>; }; }; diff --git a/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi index 44f3f0127fd709..78738371f634cf 100644 --- a/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi @@ -404,8 +404,8 @@ mmcc: clock-controller@fd8c0000 { <&gcc GPLL0_VOTE>, <&gcc GPLL1_VOTE>, <&rpmcc RPM_SMD_GFX3D_CLK_SRC>, - <0>, - <0>; + <&mdss_dsi0_phy 1>, + <&mdss_dsi0_phy 0>; clock-names = "xo", "mmss_gpll0_vote", "gpll0_vote", diff --git a/arch/arm/boot/dts/qcom/qcom-msm8660.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8660.dtsi index 78023ed2fdf71f..9217ced108c42f 100644 --- a/arch/arm/boot/dts/qcom/qcom-msm8660.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-msm8660.dtsi @@ -80,13 +80,13 @@ sleep-clk { */ iio-hwmon { compatible = "iio-hwmon"; - io-channels = <&xoadc 0x00 0x01>, /* Battery */ - <&xoadc 0x00 0x02>, /* DC in (charger) */ - <&xoadc 0x00 0x04>, /* VPH the main system voltage */ - <&xoadc 0x00 0x0b>, /* Die temperature */ - <&xoadc 0x00 0x0c>, /* Reference voltage 1.25V */ - <&xoadc 0x00 0x0d>, /* Reference voltage 0.625V */ - <&xoadc 0x00 0x0e>; /* Reference voltage 0.325V */ + io-channels = <&pm8058_xoadc 0x00 0x01>, /* Battery */ + <&pm8058_xoadc 0x00 0x02>, /* DC in (charger) */ + <&pm8058_xoadc 0x00 0x04>, /* VPH the main system voltage */ + <&pm8058_xoadc 0x00 0x0b>, /* Die temperature */ + <&pm8058_xoadc 0x00 0x0c>, /* Reference voltage 1.25V */ + <&pm8058_xoadc 0x00 0x0d>, /* Reference voltage 0.625V */ + <&pm8058_xoadc 0x00 0x0e>; /* Reference voltage 0.325V */ }; soc: soc { @@ -390,7 +390,7 @@ pm8058_keypad: keypad@148 { row-hold = <91500>; }; - xoadc: xoadc@197 { + pm8058_xoadc: xoadc@197 { compatible = "qcom,pm8058-adc"; reg = <0x197>; interrupts-extended = <&pm8058 76 IRQ_TYPE_EDGE_RISING>; diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974-lge-nexus5-hammerhead.dts b/arch/arm/boot/dts/qcom/qcom-msm8974-lge-nexus5-hammerhead.dts index 60bdfddeae69eb..da99f770d4f57b 100644 --- a/arch/arm/boot/dts/qcom/qcom-msm8974-lge-nexus5-hammerhead.dts +++ b/arch/arm/boot/dts/qcom/qcom-msm8974-lge-nexus5-hammerhead.dts @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "qcom-msm8974.dtsi" -#include "qcom-pm8841.dtsi" -#include "qcom-pm8941.dtsi" +#include "pm8841.dtsi" +#include "pm8941.dtsi" #include #include #include diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974-sony-xperia-rhine.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8974-sony-xperia-rhine.dtsi index 68a2f9094e536f..23ae474698aa7b 100644 --- a/arch/arm/boot/dts/qcom/qcom-msm8974-sony-xperia-rhine.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-msm8974-sony-xperia-rhine.dtsi @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "qcom-msm8974.dtsi" -#include "qcom-pm8841.dtsi" -#include "qcom-pm8941.dtsi" +#include "pm8841.dtsi" +#include "pm8941.dtsi" #include #include #include diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi index 706fef53767e10..4a8eb8b423290f 100644 --- a/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi @@ -1194,7 +1194,7 @@ restart@fc4ab000 { qfprom: qfprom@fc4bc000 { compatible = "qcom,msm8974-qfprom", "qcom,qfprom"; - reg = <0xfc4bc000 0x1000>; + reg = <0xfc4bc000 0x2100>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974pro-fairphone-fp2.dts b/arch/arm/boot/dts/qcom/qcom-msm8974pro-fairphone-fp2.dts index 42d253b75dad02..6c4153689b39e5 100644 --- a/arch/arm/boot/dts/qcom/qcom-msm8974pro-fairphone-fp2.dts +++ b/arch/arm/boot/dts/qcom/qcom-msm8974pro-fairphone-fp2.dts @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "qcom-msm8974pro.dtsi" -#include "qcom-pm8841.dtsi" -#include "qcom-pm8941.dtsi" +#include "pm8841.dtsi" +#include "pm8941.dtsi" #include #include #include diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974pro-oneplus-bacon.dts b/arch/arm/boot/dts/qcom/qcom-msm8974pro-oneplus-bacon.dts index 8230d0e1d95d1d..c0ca264d8140db 100644 --- a/arch/arm/boot/dts/qcom/qcom-msm8974pro-oneplus-bacon.dts +++ b/arch/arm/boot/dts/qcom/qcom-msm8974pro-oneplus-bacon.dts @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "qcom-msm8974pro.dtsi" -#include "qcom-pm8841.dtsi" -#include "qcom-pm8941.dtsi" +#include "pm8841.dtsi" +#include "pm8941.dtsi" #include #include diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974pro-samsung-klte.dts b/arch/arm/boot/dts/qcom/qcom-msm8974pro-samsung-klte.dts index 3e2c86591ee2f7..325feb89b343ab 100644 --- a/arch/arm/boot/dts/qcom/qcom-msm8974pro-samsung-klte.dts +++ b/arch/arm/boot/dts/qcom/qcom-msm8974pro-samsung-klte.dts @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "qcom-msm8974pro.dtsi" -#include "qcom-pma8084.dtsi" +#include "pma8084.dtsi" #include #include #include diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974pro-sony-xperia-shinano-castor.dts b/arch/arm/boot/dts/qcom/qcom-msm8974pro-sony-xperia-shinano-castor.dts index 11468d1409f722..0798cce3dbea01 100644 --- a/arch/arm/boot/dts/qcom/qcom-msm8974pro-sony-xperia-shinano-castor.dts +++ b/arch/arm/boot/dts/qcom/qcom-msm8974pro-sony-xperia-shinano-castor.dts @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "qcom-msm8974pro.dtsi" -#include "qcom-pm8841.dtsi" -#include "qcom-pm8941.dtsi" +#include "pm8841.dtsi" +#include "pm8941.dtsi" #include #include #include diff --git a/arch/arm/boot/dts/qcom/qcom-pm8226.dtsi b/arch/arm/boot/dts/qcom/qcom-pm8226.dtsi deleted file mode 100644 index 2413778f371507..00000000000000 --- a/arch/arm/boot/dts/qcom/qcom-pm8226.dtsi +++ /dev/null @@ -1,180 +0,0 @@ -// SPDX-License-Identifier: BSD-3-Clause -#include -#include -#include -#include - -/ { - thermal-zones { - pm8226-thermal { - polling-delay-passive = <100>; - polling-delay = <0>; - thermal-sensors = <&pm8226_temp>; - - trips { - trip0 { - temperature = <105000>; - hysteresis = <2000>; - type = "passive"; - }; - - trip1 { - temperature = <125000>; - hysteresis = <2000>; - type = "hot"; - }; - - crit { - temperature = <145000>; - hysteresis = <2000>; - type = "critical"; - }; - }; - }; - }; -}; - -&spmi_bus { - pm8226_0: pm8226@0 { - compatible = "qcom,pm8226", "qcom,spmi-pmic"; - reg = <0x0 SPMI_USID>; - #address-cells = <1>; - #size-cells = <0>; - - pon@800 { - compatible = "qcom,pm8916-pon"; - reg = <0x800>; - - pwrkey { - compatible = "qcom,pm8941-pwrkey"; - interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>; - debounce = <15625>; - bias-pull-up; - linux,code = ; - }; - - pm8226_resin: resin { - compatible = "qcom,pm8941-resin"; - interrupts = <0x0 0x8 1 IRQ_TYPE_EDGE_BOTH>; - debounce = <15625>; - bias-pull-up; - status = "disabled"; - }; - }; - - smbb: charger@1000 { - compatible = "qcom,pm8226-charger"; - reg = <0x1000>; - interrupts = <0x0 0x10 7 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x10 5 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x10 4 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x12 1 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x12 0 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x13 2 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x13 1 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x14 1 IRQ_TYPE_EDGE_BOTH>; - interrupt-names = "chg-done", - "chg-fast", - "chg-trkl", - "bat-temp-ok", - "bat-present", - "chg-gone", - "usb-valid", - "dc-valid"; - - chg_otg: otg-vbus { }; - }; - - pm8226_temp: temp-alarm@2400 { - compatible = "qcom,spmi-temp-alarm"; - reg = <0x2400>; - interrupts = <0 0x24 0 IRQ_TYPE_EDGE_RISING>; - io-channels = <&pm8226_vadc VADC_DIE_TEMP>; - io-channel-names = "thermal"; - #thermal-sensor-cells = <0>; - }; - - pm8226_vadc: adc@3100 { - compatible = "qcom,spmi-vadc"; - reg = <0x3100>; - interrupts = <0x0 0x31 0x0 IRQ_TYPE_EDGE_RISING>; - #address-cells = <1>; - #size-cells = <0>; - #io-channel-cells = <1>; - - channel@7 { - reg = ; - qcom,pre-scaling = <1 3>; - label = "vph_pwr"; - }; - channel@8 { - reg = ; - label = "die_temp"; - }; - channel@9 { - reg = ; - label = "ref_625mv"; - }; - channel@a { - reg = ; - label = "ref_1250mv"; - }; - channel@e { - reg = ; - }; - channel@f { - reg = ; - }; - }; - - pm8226_iadc: adc@3600 { - compatible = "qcom,pm8226-iadc", "qcom,spmi-iadc"; - reg = <0x3600>; - interrupts = <0x0 0x36 0x0 IRQ_TYPE_EDGE_RISING>; - }; - - rtc@6000 { - compatible = "qcom,pm8941-rtc"; - reg = <0x6000>, <0x6100>; - reg-names = "rtc", "alarm"; - interrupts = <0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>; - }; - - pm8226_mpps: mpps@a000 { - compatible = "qcom,pm8226-mpp", "qcom,spmi-mpp"; - reg = <0xa000>; - gpio-controller; - #gpio-cells = <2>; - gpio-ranges = <&pm8226_mpps 0 0 8>; - interrupt-controller; - #interrupt-cells = <2>; - }; - - pm8226_gpios: gpio@c000 { - compatible = "qcom,pm8226-gpio", "qcom,spmi-gpio"; - reg = <0xc000>; - gpio-controller; - #gpio-cells = <2>; - gpio-ranges = <&pm8226_gpios 0 0 8>; - interrupt-controller; - #interrupt-cells = <2>; - }; - }; - - pm8226_1: pm8226@1 { - compatible = "qcom,pm8226", "qcom,spmi-pmic"; - reg = <0x1 SPMI_USID>; - #address-cells = <1>; - #size-cells = <0>; - - pm8226_spmi_regulators: regulators { - compatible = "qcom,pm8226-regulators"; - }; - - pm8226_vib: vibrator@c000 { - compatible = "qcom,pm8916-vib"; - reg = <0xc000>; - status = "disabled"; - }; - }; -}; diff --git a/arch/arm/boot/dts/qcom/qcom-pm8841.dtsi b/arch/arm/boot/dts/qcom/qcom-pm8841.dtsi deleted file mode 100644 index 3bf2ce5c86a641..00000000000000 --- a/arch/arm/boot/dts/qcom/qcom-pm8841.dtsi +++ /dev/null @@ -1,68 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include - - -/ { - thermal-zones { - pm8841-thermal { - polling-delay-passive = <100>; - polling-delay = <0>; - thermal-sensors = <&pm8841_temp>; - - trips { - trip0 { - temperature = <105000>; - hysteresis = <2000>; - type = "passive"; - }; - - trip1 { - temperature = <125000>; - hysteresis = <2000>; - type = "hot"; - }; - - crit { - temperature = <140000>; - hysteresis = <2000>; - type = "critical"; - }; - }; - }; - }; -}; - -&spmi_bus { - - pm8841_0: pm8841@4 { - compatible = "qcom,pm8841", "qcom,spmi-pmic"; - reg = <0x4 SPMI_USID>; - #address-cells = <1>; - #size-cells = <0>; - - pm8841_mpps: mpps@a000 { - compatible = "qcom,pm8841-mpp", "qcom,spmi-mpp"; - reg = <0xa000>; - gpio-controller; - #gpio-cells = <2>; - gpio-ranges = <&pm8841_mpps 0 0 4>; - interrupt-controller; - #interrupt-cells = <2>; - }; - - pm8841_temp: temp-alarm@2400 { - compatible = "qcom,spmi-temp-alarm"; - reg = <0x2400>; - interrupts = <4 0x24 0 IRQ_TYPE_EDGE_RISING>; - #thermal-sensor-cells = <0>; - }; - }; - - pm8841_1: pm8841@5 { - compatible = "qcom,pm8841", "qcom,spmi-pmic"; - reg = <0x5 SPMI_USID>; - #address-cells = <1>; - #size-cells = <0>; - }; -}; diff --git a/arch/arm/boot/dts/qcom/qcom-pm8941.dtsi b/arch/arm/boot/dts/qcom/qcom-pm8941.dtsi deleted file mode 100644 index ed0ba591c75581..00000000000000 --- a/arch/arm/boot/dts/qcom/qcom-pm8941.dtsi +++ /dev/null @@ -1,254 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include - - -/ { - thermal-zones { - pm8941-thermal { - polling-delay-passive = <100>; - polling-delay = <0>; - thermal-sensors = <&pm8941_temp>; - - trips { - trip0 { - temperature = <105000>; - hysteresis = <2000>; - type = "passive"; - }; - - trip1 { - temperature = <125000>; - hysteresis = <2000>; - type = "hot"; - }; - - crit { - temperature = <145000>; - hysteresis = <2000>; - type = "critical"; - }; - }; - }; - }; -}; - -&spmi_bus { - - pm8941_0: pm8941@0 { - compatible = "qcom,pm8941", "qcom,spmi-pmic"; - reg = <0x0 SPMI_USID>; - #address-cells = <1>; - #size-cells = <0>; - - rtc@6000 { - compatible = "qcom,pm8941-rtc"; - reg = <0x6000>, - <0x6100>; - reg-names = "rtc", "alarm"; - interrupts = <0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>; - }; - - pon@800 { - compatible = "qcom,pm8941-pon"; - reg = <0x800>; - - pwrkey { - compatible = "qcom,pm8941-pwrkey"; - interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>; - debounce = <15625>; - bias-pull-up; - }; - - pm8941_resin: resin { - compatible = "qcom,pm8941-resin"; - interrupts = <0x0 0x8 1 IRQ_TYPE_EDGE_BOTH>; - debounce = <15625>; - bias-pull-up; - status = "disabled"; - }; - }; - - usb_id: usb-detect@900 { - compatible = "qcom,pm8941-misc"; - reg = <0x900>; - interrupts = <0x0 0x9 0 IRQ_TYPE_EDGE_BOTH>; - interrupt-names = "usb_id"; - }; - - smbb: charger@1000 { - compatible = "qcom,pm8941-charger"; - reg = <0x1000>; - interrupts = <0x0 0x10 7 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x10 5 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x10 4 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x12 1 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x12 0 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x13 2 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x13 1 IRQ_TYPE_EDGE_BOTH>, - <0x0 0x14 1 IRQ_TYPE_EDGE_BOTH>; - interrupt-names = "chg-done", - "chg-fast", - "chg-trkl", - "bat-temp-ok", - "bat-present", - "chg-gone", - "usb-valid", - "dc-valid"; - - usb-otg-in-supply = <&pm8941_5vs1>; - - chg_otg: otg-vbus { }; - }; - - pm8941_gpios: gpio@c000 { - compatible = "qcom,pm8941-gpio", "qcom,spmi-gpio"; - reg = <0xc000>; - gpio-controller; - gpio-ranges = <&pm8941_gpios 0 0 36>; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - - boost_bypass_n_pin: boost-bypass-state { - pins = "gpio21"; - function = "normal"; - }; - }; - - pm8941_mpps: mpps@a000 { - compatible = "qcom,pm8941-mpp", "qcom,spmi-mpp"; - reg = <0xa000>; - gpio-controller; - #gpio-cells = <2>; - gpio-ranges = <&pm8941_mpps 0 0 8>; - interrupt-controller; - #interrupt-cells = <2>; - }; - - pm8941_temp: temp-alarm@2400 { - compatible = "qcom,spmi-temp-alarm"; - reg = <0x2400>; - interrupts = <0 0x24 0 IRQ_TYPE_EDGE_RISING>; - io-channels = <&pm8941_vadc VADC_DIE_TEMP>; - io-channel-names = "thermal"; - #thermal-sensor-cells = <0>; - }; - - pm8941_vadc: adc@3100 { - compatible = "qcom,spmi-vadc"; - reg = <0x3100>; - interrupts = <0x0 0x31 0x0 IRQ_TYPE_EDGE_RISING>; - #address-cells = <1>; - #size-cells = <0>; - #io-channel-cells = <1>; - - - channel@6 { - reg = ; - }; - - channel@8 { - reg = ; - }; - - channel@9 { - reg = ; - }; - - channel@a { - reg = ; - }; - - channel@e { - reg = ; - }; - - channel@f { - reg = ; - }; - - channel@30 { - reg = ; - }; - }; - - pm8941_iadc: adc@3600 { - compatible = "qcom,pm8941-iadc", "qcom,spmi-iadc"; - reg = <0x3600>; - interrupts = <0x0 0x36 0x0 IRQ_TYPE_EDGE_RISING>; - qcom,external-resistor-micro-ohms = <10000>; - }; - - pm8941_coincell: charger@2800 { - compatible = "qcom,pm8941-coincell"; - reg = <0x2800>; - status = "disabled"; - }; - }; - - pm8941_1: pm8941@1 { - compatible = "qcom,pm8941", "qcom,spmi-pmic"; - reg = <0x1 SPMI_USID>; - #address-cells = <1>; - #size-cells = <0>; - - pm8941_lpg: pwm { - compatible = "qcom,pm8941-lpg"; - - #address-cells = <1>; - #size-cells = <0>; - #pwm-cells = <2>; - - status = "disabled"; - }; - - pm8941_vib: vibrator@c000 { - compatible = "qcom,pm8916-vib"; - reg = <0xc000>; - status = "disabled"; - }; - - pm8941_wled: wled@d800 { - compatible = "qcom,pm8941-wled"; - reg = <0xd800>; - label = "backlight"; - - status = "disabled"; - }; - - regulators { - compatible = "qcom,pm8941-regulators"; - interrupts = <0x1 0x83 0x2 0>, <0x1 0x84 0x2 0>; - interrupt-names = "ocp-5vs1", "ocp-5vs2"; - vin_5vs-supply = <&pm8941_5v>; - - pm8941_5v: s4 { - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - regulator-enable-ramp-delay = <500>; - }; - - pm8941_5vs1: 5vs1 { - regulator-enable-ramp-delay = <1000>; - regulator-pull-down; - regulator-over-current-protection; - qcom,ocp-max-retries = <10>; - qcom,ocp-retry-delay = <30>; - qcom,vs-soft-start-strength = <0>; - regulator-initial-mode = <1>; - }; - - pm8941_5vs2: 5vs2 { - regulator-enable-ramp-delay = <1000>; - regulator-pull-down; - regulator-over-current-protection; - qcom,ocp-max-retries = <10>; - qcom,ocp-retry-delay = <30>; - qcom,vs-soft-start-strength = <0>; - regulator-initial-mode = <1>; - }; - }; - }; -}; diff --git a/arch/arm/boot/dts/qcom/qcom-pma8084.dtsi b/arch/arm/boot/dts/qcom/qcom-pma8084.dtsi deleted file mode 100644 index 2985f4805b93ee..00000000000000 --- a/arch/arm/boot/dts/qcom/qcom-pma8084.dtsi +++ /dev/null @@ -1,99 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include - -&spmi_bus { - - pma8084_0: pma8084@0 { - compatible = "qcom,pma8084", "qcom,spmi-pmic"; - reg = <0x0 SPMI_USID>; - #address-cells = <1>; - #size-cells = <0>; - - rtc@6000 { - compatible = "qcom,pm8941-rtc"; - reg = <0x6000>, - <0x6100>; - reg-names = "rtc", "alarm"; - interrupts = <0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>; - }; - - pwrkey@800 { - compatible = "qcom,pm8941-pwrkey"; - reg = <0x800>; - interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>; - debounce = <15625>; - bias-pull-up; - }; - - pma8084_gpios: gpio@c000 { - compatible = "qcom,pma8084-gpio", "qcom,spmi-gpio"; - reg = <0xc000>; - gpio-controller; - gpio-ranges = <&pma8084_gpios 0 0 22>; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - }; - - pma8084_mpps: mpps@a000 { - compatible = "qcom,pma8084-mpp", "qcom,spmi-mpp"; - reg = <0xa000>; - gpio-controller; - #gpio-cells = <2>; - gpio-ranges = <&pma8084_mpps 0 0 8>; - interrupt-controller; - #interrupt-cells = <2>; - }; - - pma8084_temp: temp-alarm@2400 { - compatible = "qcom,spmi-temp-alarm"; - reg = <0x2400>; - interrupts = <0 0x24 0 IRQ_TYPE_EDGE_RISING>; - #thermal-sensor-cells = <0>; - io-channels = <&pma8084_vadc VADC_DIE_TEMP>; - io-channel-names = "thermal"; - }; - - pma8084_vadc: adc@3100 { - compatible = "qcom,spmi-vadc"; - reg = <0x3100>; - interrupts = <0x0 0x31 0x0 IRQ_TYPE_EDGE_RISING>; - #address-cells = <1>; - #size-cells = <0>; - #io-channel-cells = <1>; - - channel@8 { - reg = ; - }; - - channel@9 { - reg = ; - }; - - channel@a { - reg = ; - }; - - channel@c { - reg = ; - }; - - channel@e { - reg = ; - }; - - channel@f { - reg = ; - }; - }; - }; - - pma8084_1: pma8084@1 { - compatible = "qcom,pma8084", "qcom,spmi-pmic"; - reg = <0x1 SPMI_USID>; - #address-cells = <1>; - #size-cells = <0>; - }; -}; diff --git a/arch/arm/boot/dts/qcom/qcom-pmx55.dtsi b/arch/arm/boot/dts/qcom/qcom-pmx55.dtsi deleted file mode 100644 index da0851173c6997..00000000000000 --- a/arch/arm/boot/dts/qcom/qcom-pmx55.dtsi +++ /dev/null @@ -1,85 +0,0 @@ -// SPDX-License-Identifier: BSD-3-Clause - -/* - * Copyright (c) 2018-2020, The Linux Foundation. All rights reserved. - * Copyright (c) 2020, Linaro Limited - */ - -#include -#include -#include - -&spmi_bus { - pmic@8 { - compatible = "qcom,pmx55", "qcom,spmi-pmic"; - reg = <0x8 SPMI_USID>; - #address-cells = <1>; - #size-cells = <0>; - - pon@800 { - compatible = "qcom,pm8916-pon"; - reg = <0x0800>; - - status = "disabled"; - }; - - pmx55_temp: temp-alarm@2400 { - compatible = "qcom,spmi-temp-alarm"; - reg = <0x2400>; - interrupts = <0x8 0x24 0x0 IRQ_TYPE_EDGE_BOTH>; - io-channels = <&pmx55_adc ADC5_DIE_TEMP>; - io-channel-names = "thermal"; - #thermal-sensor-cells = <0>; - }; - - pmx55_adc: adc@3100 { - compatible = "qcom,spmi-adc5"; - reg = <0x3100>; - #address-cells = <1>; - #size-cells = <0>; - #io-channel-cells = <1>; - interrupts = <0x8 0x31 0x0 IRQ_TYPE_EDGE_RISING>; - - channel@0 { - reg = ; - qcom,pre-scaling = <1 1>; - label = "ref_gnd"; - }; - - channel@1 { - reg = ; - qcom,pre-scaling = <1 1>; - label = "vref_1p25"; - }; - - channel@6 { - reg = ; - qcom,pre-scaling = <1 1>; - label = "die_temp"; - }; - - channel@9 { - reg = ; - qcom,pre-scaling = <1 1>; - label = "chg_temp"; - }; - }; - - pmx55_gpios: gpio@c000 { - compatible = "qcom,pmx55-gpio", "qcom,spmi-gpio"; - reg = <0xc000>; - gpio-controller; - gpio-ranges = <&pmx55_gpios 0 0 11>; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - }; - }; - - pmic@9 { - compatible = "qcom,pmx55", "qcom,spmi-pmic"; - reg = <0x9 SPMI_USID>; - #address-cells = <1>; - #size-cells = <0>; - }; -}; diff --git a/arch/arm/boot/dts/qcom/qcom-pmx65.dtsi b/arch/arm/boot/dts/qcom/qcom-pmx65.dtsi deleted file mode 100644 index 1c7fdf59c1f56a..00000000000000 --- a/arch/arm/boot/dts/qcom/qcom-pmx65.dtsi +++ /dev/null @@ -1,33 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved. - */ - -#include -#include - -&spmi_bus { - pmic@1 { - compatible = "qcom,pmx65", "qcom,spmi-pmic"; - reg = <1 SPMI_USID>; - #address-cells = <1>; - #size-cells = <0>; - - pmx65_temp: temp-alarm@a00 { - compatible = "qcom,spmi-temp-alarm"; - reg = <0xa00>; - interrupts = <0x1 0xa 0x0 IRQ_TYPE_EDGE_BOTH>; - #thermal-sensor-cells = <0>; - }; - - pmx65_gpios: gpio@8800 { - compatible = "qcom,pmx65-gpio", "qcom,spmi-gpio"; - reg = <0x8800>; - gpio-controller; - gpio-ranges = <&pmx65_gpios 0 0 16>; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - }; - }; -}; diff --git a/arch/arm/boot/dts/qcom/qcom-sdx55-mtp.dts b/arch/arm/boot/dts/qcom/qcom-sdx55-mtp.dts index 7e97ad5803d87b..2470693619090b 100644 --- a/arch/arm/boot/dts/qcom/qcom-sdx55-mtp.dts +++ b/arch/arm/boot/dts/qcom/qcom-sdx55-mtp.dts @@ -9,7 +9,7 @@ #include "qcom-sdx55.dtsi" #include #include -#include "qcom-pmx55.dtsi" +#include "pmx55.dtsi" / { model = "Qualcomm Technologies, Inc. SDX55 MTP"; diff --git a/arch/arm/boot/dts/qcom/qcom-sdx55-t55.dts b/arch/arm/boot/dts/qcom/qcom-sdx55-t55.dts index 51058b06527979..082f7ed1a01fb8 100644 --- a/arch/arm/boot/dts/qcom/qcom-sdx55-t55.dts +++ b/arch/arm/boot/dts/qcom/qcom-sdx55-t55.dts @@ -8,7 +8,7 @@ #include #include #include "qcom-sdx55.dtsi" -#include "qcom-pmx55.dtsi" +#include "pmx55.dtsi" / { model = "Thundercomm T55 Development Kit"; diff --git a/arch/arm/boot/dts/qcom/qcom-sdx55-telit-fn980-tlb.dts b/arch/arm/boot/dts/qcom/qcom-sdx55-telit-fn980-tlb.dts index 8fadc6e70692a5..e336a15b45c4c6 100644 --- a/arch/arm/boot/dts/qcom/qcom-sdx55-telit-fn980-tlb.dts +++ b/arch/arm/boot/dts/qcom/qcom-sdx55-telit-fn980-tlb.dts @@ -8,7 +8,7 @@ #include #include #include "qcom-sdx55.dtsi" -#include "qcom-pmx55.dtsi" +#include "pmx55.dtsi" / { model = "Telit FN980 TLB"; diff --git a/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi b/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi index 55ce87b7525394..f9ad5abfbd28bf 100644 --- a/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi @@ -345,10 +345,10 @@ pcie_rc: pcie@1c00000 { "msi8"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; - interrupt-map = <0 0 0 1 &intc 0 0 0 141 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ - <0 0 0 2 &intc 0 0 0 142 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ - <0 0 0 3 &intc 0 0 0 143 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ - <0 0 0 4 &intc 0 0 0 144 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ + interrupt-map = <0 0 0 1 &intc 0 141 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ + <0 0 0 2 &intc 0 142 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ + <0 0 0 3 &intc 0 143 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ + <0 0 0 4 &intc 0 144 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ clocks = <&gcc GCC_PCIE_PIPE_CLK>, <&gcc GCC_PCIE_AUX_CLK>, @@ -592,10 +592,10 @@ usb: usb@a6f8800 { <&gcc GCC_USB30_MASTER_CLK>; assigned-clock-rates = <19200000>, <200000000>; - interrupts = , - , - , - ; + interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 51 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 11 IRQ_TYPE_EDGE_BOTH>, + <&pdc 10 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -619,7 +619,7 @@ pdc: interrupt-controller@b210000 { compatible = "qcom,sdx55-pdc", "qcom,pdc"; reg = <0x0b210000 0x30000>; qcom,pdc-ranges = <0 179 52>; - #interrupt-cells = <3>; + #interrupt-cells = <2>; interrupt-parent = <&intc>; interrupt-controller; }; diff --git a/arch/arm/boot/dts/qcom/qcom-sdx65-mtp.dts b/arch/arm/boot/dts/qcom/qcom-sdx65-mtp.dts index fcf1c51c5e7a7a..b87c5434cc29e4 100644 --- a/arch/arm/boot/dts/qcom/qcom-sdx65-mtp.dts +++ b/arch/arm/boot/dts/qcom/qcom-sdx65-mtp.dts @@ -8,7 +8,7 @@ #include #include #include -#include "qcom-pmx65.dtsi" +#include "pmx65.dtsi" / { model = "Qualcomm Technologies, Inc. SDX65 MTP"; diff --git a/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi b/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi index 1a3583029a649e..271899c861c01c 100644 --- a/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi @@ -338,7 +338,7 @@ pcie_ep: pcie-ep@1c00000 { power-domains = <&gcc PCIE_GDSC>; phys = <&pcie_phy>; - phy-names = "pcie-phy"; + phy-names = "pciephy"; max-link-speed = <3>; num-lanes = <2>; @@ -530,7 +530,7 @@ restart@c264000 { reg = <0x0c264000 0x1000>; }; - spmi_bus: qcom,spmi@c440000 { + spmi_bus: spmi@c440000 { compatible = "qcom,spmi-pmic-arb"; reg = <0xc440000 0xd00>, <0xc600000 0x2000000>, diff --git a/arch/arm/boot/dts/renesas/r8a73a4-ape6evm.dts b/arch/arm/boot/dts/renesas/r8a73a4-ape6evm.dts index e81a7213d30477..4282bafbb50431 100644 --- a/arch/arm/boot/dts/renesas/r8a73a4-ape6evm.dts +++ b/arch/arm/boot/dts/renesas/r8a73a4-ape6evm.dts @@ -209,6 +209,18 @@ &cmt1 { status = "okay"; }; +&extal1_clk { + clock-frequency = <26000000>; +}; + +&extal2_clk { + clock-frequency = <48000000>; +}; + +&extalr_clk { + clock-frequency = <32768>; +}; + &pfc { scifa0_pins: scifa0 { groups = "scifa0_data"; diff --git a/arch/arm/boot/dts/renesas/r8a73a4.dtsi b/arch/arm/boot/dts/renesas/r8a73a4.dtsi index c39066967053f0..d1f4cbd099efb4 100644 --- a/arch/arm/boot/dts/renesas/r8a73a4.dtsi +++ b/arch/arm/boot/dts/renesas/r8a73a4.dtsi @@ -450,17 +450,20 @@ clocks { extalr_clk: extalr { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <32768>; + /* This value must be overridden by the board. */ + clock-frequency = <0>; }; extal1_clk: extal1 { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <25000000>; + /* This value must be overridden by the board. */ + clock-frequency = <0>; }; extal2_clk: extal2 { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <48000000>; + /* This value must be overridden by the board. */ + clock-frequency = <0>; }; fsiack_clk: fsiack { compatible = "fixed-clock"; diff --git a/arch/arm/boot/dts/renesas/r8a7790-lager.dts b/arch/arm/boot/dts/renesas/r8a7790-lager.dts index 5ad5349a50dc9b..ab7e9fa90b9fe2 100644 --- a/arch/arm/boot/dts/renesas/r8a7790-lager.dts +++ b/arch/arm/boot/dts/renesas/r8a7790-lager.dts @@ -437,6 +437,7 @@ pmic@58 { interrupt-parent = <&irqc0>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; rtc { compatible = "dlg,da9063-rtc"; diff --git a/arch/arm/boot/dts/renesas/r8a7790-stout.dts b/arch/arm/boot/dts/renesas/r8a7790-stout.dts index fe14727eefe1ec..25956661a87541 100644 --- a/arch/arm/boot/dts/renesas/r8a7790-stout.dts +++ b/arch/arm/boot/dts/renesas/r8a7790-stout.dts @@ -332,6 +332,7 @@ pmic@58 { interrupt-parent = <&irqc0>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; onkey { compatible = "dlg,da9063-onkey"; diff --git a/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts b/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts index 26a40782cc899b..4a76be68887b43 100644 --- a/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts +++ b/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts @@ -800,6 +800,7 @@ pmic@58 { interrupt-parent = <&irqc0>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; rtc { compatible = "dlg,da9063-rtc"; diff --git a/arch/arm/boot/dts/renesas/r8a7791-porter.dts b/arch/arm/boot/dts/renesas/r8a7791-porter.dts index ec0a20d5130d6f..fcc9a2313e1dfd 100644 --- a/arch/arm/boot/dts/renesas/r8a7791-porter.dts +++ b/arch/arm/boot/dts/renesas/r8a7791-porter.dts @@ -389,6 +389,7 @@ pmic@5a { interrupt-parent = <&irqc0>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; watchdog { compatible = "dlg,da9063-watchdog"; diff --git a/arch/arm/boot/dts/renesas/r8a7792-blanche.dts b/arch/arm/boot/dts/renesas/r8a7792-blanche.dts index c66de9dd12dfca..20963c9bbf0ada 100644 --- a/arch/arm/boot/dts/renesas/r8a7792-blanche.dts +++ b/arch/arm/boot/dts/renesas/r8a7792-blanche.dts @@ -239,7 +239,7 @@ du1_pins: du1 { }; keyboard_pins: keyboard { - pins = "GP_3_10", "GP_3_11", "GP_3_12", "GP_3_15", "GP_11_02"; + pins = "GP_3_10", "GP_3_11", "GP_3_12", "GP_3_15", "GP_11_2"; bias-pull-up; }; @@ -330,6 +330,7 @@ pmic@58 { interrupt-parent = <&irqc>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; rtc { compatible = "dlg,da9063-rtc"; diff --git a/arch/arm/boot/dts/renesas/r8a7793-gose.dts b/arch/arm/boot/dts/renesas/r8a7793-gose.dts index 79b537b2464266..9358fc7d0e9f6f 100644 --- a/arch/arm/boot/dts/renesas/r8a7793-gose.dts +++ b/arch/arm/boot/dts/renesas/r8a7793-gose.dts @@ -735,6 +735,7 @@ pmic@58 { interrupt-parent = <&irqc0>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; rtc { compatible = "dlg,da9063-rtc"; diff --git a/arch/arm/boot/dts/renesas/r8a7794-alt.dts b/arch/arm/boot/dts/renesas/r8a7794-alt.dts index 4d93319674c6ef..3a9db455ddec94 100644 --- a/arch/arm/boot/dts/renesas/r8a7794-alt.dts +++ b/arch/arm/boot/dts/renesas/r8a7794-alt.dts @@ -458,6 +458,7 @@ pmic@58 { interrupt-parent = <&gpio3>; interrupts = <31 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; rtc { compatible = "dlg,da9063-rtc"; diff --git a/arch/arm/boot/dts/renesas/r8a7794-silk.dts b/arch/arm/boot/dts/renesas/r8a7794-silk.dts index b7af1befa126ba..b825f2e25dd060 100644 --- a/arch/arm/boot/dts/renesas/r8a7794-silk.dts +++ b/arch/arm/boot/dts/renesas/r8a7794-silk.dts @@ -424,6 +424,7 @@ pmic@58 { interrupt-parent = <&gpio3>; interrupts = <31 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; onkey { compatible = "dlg,da9063-onkey"; diff --git a/arch/arm/boot/dts/rockchip/rk3036.dtsi b/arch/arm/boot/dts/rockchip/rk3036.dtsi index 78686fc72ce69a..c420c7c642cb0b 100644 --- a/arch/arm/boot/dts/rockchip/rk3036.dtsi +++ b/arch/arm/boot/dts/rockchip/rk3036.dtsi @@ -402,12 +402,20 @@ hdmi: hdmi@20034000 { pinctrl-0 = <&hdmi_ctl>; status = "disabled"; - hdmi_in: port { + ports { #address-cells = <1>; #size-cells = <0>; - hdmi_in_vop: endpoint@0 { + + hdmi_in: port@0 { reg = <0>; - remote-endpoint = <&vop_out_hdmi>; + + hdmi_in_vop: endpoint { + remote-endpoint = <&vop_out_hdmi>; + }; + }; + + hdmi_out: port@1 { + reg = <1>; }; }; }; diff --git a/arch/arm/boot/dts/rockchip/rk3066a.dtsi b/arch/arm/boot/dts/rockchip/rk3066a.dtsi index de9915d946f74f..b98d5e357baf35 100644 --- a/arch/arm/boot/dts/rockchip/rk3066a.dtsi +++ b/arch/arm/boot/dts/rockchip/rk3066a.dtsi @@ -123,6 +123,7 @@ hdmi: hdmi@10116000 { pinctrl-0 = <&hdmii2c_xfer>, <&hdmi_hpd>; power-domains = <&power RK3066_PD_VIO>; rockchip,grf = <&grf>; + #sound-dai-cells = <0>; status = "disabled"; ports { diff --git a/arch/arm/boot/dts/rockchip/rk3128.dtsi b/arch/arm/boot/dts/rockchip/rk3128.dtsi index 88a4b0d6d928d4..80d81af5fe0efe 100644 --- a/arch/arm/boot/dts/rockchip/rk3128.dtsi +++ b/arch/arm/boot/dts/rockchip/rk3128.dtsi @@ -795,7 +795,7 @@ sdmmc_wp: sdmmc-wp { }; sdmmc_pwren: sdmmc-pwren { - rockchip,pins = <1 RK_PB6 1 &pcfg_pull_default>; + rockchip,pins = <1 RK_PB6 RK_FUNC_GPIO &pcfg_pull_default>; }; sdmmc_bus4: sdmmc-bus4 { diff --git a/arch/arm/boot/dts/rockchip/rk322x.dtsi b/arch/arm/boot/dts/rockchip/rk322x.dtsi index ffc16d6b97e1bd..03d9baddcbabaa 100644 --- a/arch/arm/boot/dts/rockchip/rk322x.dtsi +++ b/arch/arm/boot/dts/rockchip/rk322x.dtsi @@ -732,14 +732,20 @@ hdmi: hdmi@200a0000 { status = "disabled"; ports { - hdmi_in: port { - #address-cells = <1>; - #size-cells = <0>; - hdmi_in_vop: endpoint@0 { - reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; + + hdmi_in_vop: endpoint { remote-endpoint = <&vop_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm/boot/dts/rockchip/rk3288.dtsi b/arch/arm/boot/dts/rockchip/rk3288.dtsi index cb9cdaddffd429..8593a835993767 100644 --- a/arch/arm/boot/dts/rockchip/rk3288.dtsi +++ b/arch/arm/boot/dts/rockchip/rk3288.dtsi @@ -1231,27 +1231,37 @@ hdmi: hdmi@ff980000 { compatible = "rockchip,rk3288-dw-hdmi"; reg = <0x0 0xff980000 0x0 0x20000>; reg-io-width = <4>; - #sound-dai-cells = <0>; - rockchip,grf = <&grf>; interrupts = ; clocks = <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_HDCP>, <&cru SCLK_HDMI_CEC>; clock-names = "iahb", "isfr", "cec"; power-domains = <&power RK3288_PD_VIO>; + rockchip,grf = <&grf>; + #sound-dai-cells = <0>; status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; #address-cells = <1>; #size-cells = <0>; + hdmi_in_vopb: endpoint@0 { reg = <0>; remote-endpoint = <&vopb_out_hdmi>; }; + hdmi_in_vopl: endpoint@1 { reg = <1>; remote-endpoint = <&vopl_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm/boot/dts/rockchip/rv1108.dtsi b/arch/arm/boot/dts/rockchip/rv1108.dtsi index abf3006f0a8424..f3291f3bbc6fd2 100644 --- a/arch/arm/boot/dts/rockchip/rv1108.dtsi +++ b/arch/arm/boot/dts/rockchip/rv1108.dtsi @@ -196,7 +196,6 @@ spi: spi@10270000 { pwm4: pwm@10280000 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x10280000 0x10>; - interrupts = ; clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -208,7 +207,6 @@ pwm4: pwm@10280000 { pwm5: pwm@10280010 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x10280010 0x10>; - interrupts = ; clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -220,7 +218,6 @@ pwm5: pwm@10280010 { pwm6: pwm@10280020 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x10280020 0x10>; - interrupts = ; clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -232,7 +229,6 @@ pwm6: pwm@10280020 { pwm7: pwm@10280030 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x10280030 0x10>; - interrupts = ; clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -386,7 +382,6 @@ i2c0: i2c@20000000 { pwm0: pwm@20040000 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x20040000 0x10>; - interrupts = ; clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -398,7 +393,6 @@ pwm0: pwm@20040000 { pwm1: pwm@20040010 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x20040010 0x10>; - interrupts = ; clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -410,7 +404,6 @@ pwm1: pwm@20040010 { pwm2: pwm@20040020 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x20040020 0x10>; - interrupts = ; clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; @@ -422,7 +415,6 @@ pwm2: pwm@20040020 { pwm3: pwm@20040030 { compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm"; reg = <0x20040030 0x10>; - interrupts = ; clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>; clock-names = "pwm", "pclk"; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/samsung/exynos4.dtsi b/arch/arm/boot/dts/samsung/exynos4.dtsi index f775b9377a38b5..7f981b5c0d64b5 100644 --- a/arch/arm/boot/dts/samsung/exynos4.dtsi +++ b/arch/arm/boot/dts/samsung/exynos4.dtsi @@ -203,16 +203,16 @@ dsi_0: dsi@11c80000 { camera: camera@11800000 { compatible = "samsung,fimc"; + ranges = <0x0 0x11800000 0xa0000>; status = "disabled"; #address-cells = <1>; #size-cells = <1>; #clock-cells = <1>; clock-output-names = "cam_a_clkout", "cam_b_clkout"; - ranges; - fimc_0: fimc@11800000 { + fimc_0: fimc@0 { compatible = "samsung,exynos4210-fimc"; - reg = <0x11800000 0x1000>; + reg = <0x0 0x1000>; interrupts = ; clocks = <&clock CLK_FIMC0>, <&clock CLK_SCLK_FIMC0>; @@ -223,9 +223,9 @@ fimc_0: fimc@11800000 { status = "disabled"; }; - fimc_1: fimc@11810000 { + fimc_1: fimc@10000 { compatible = "samsung,exynos4210-fimc"; - reg = <0x11810000 0x1000>; + reg = <0x00010000 0x1000>; interrupts = ; clocks = <&clock CLK_FIMC1>, <&clock CLK_SCLK_FIMC1>; @@ -236,9 +236,9 @@ fimc_1: fimc@11810000 { status = "disabled"; }; - fimc_2: fimc@11820000 { + fimc_2: fimc@20000 { compatible = "samsung,exynos4210-fimc"; - reg = <0x11820000 0x1000>; + reg = <0x00020000 0x1000>; interrupts = ; clocks = <&clock CLK_FIMC2>, <&clock CLK_SCLK_FIMC2>; @@ -249,9 +249,9 @@ fimc_2: fimc@11820000 { status = "disabled"; }; - fimc_3: fimc@11830000 { + fimc_3: fimc@30000 { compatible = "samsung,exynos4210-fimc"; - reg = <0x11830000 0x1000>; + reg = <0x00030000 0x1000>; interrupts = ; clocks = <&clock CLK_FIMC3>, <&clock CLK_SCLK_FIMC3>; @@ -262,9 +262,9 @@ fimc_3: fimc@11830000 { status = "disabled"; }; - csis_0: csis@11880000 { + csis_0: csis@80000 { compatible = "samsung,exynos4210-csis"; - reg = <0x11880000 0x4000>; + reg = <0x00080000 0x4000>; interrupts = ; clocks = <&clock CLK_CSIS0>, <&clock CLK_SCLK_CSIS0>; @@ -278,9 +278,9 @@ csis_0: csis@11880000 { #size-cells = <0>; }; - csis_1: csis@11890000 { + csis_1: csis@90000 { compatible = "samsung,exynos4210-csis"; - reg = <0x11890000 0x4000>; + reg = <0x00090000 0x4000>; interrupts = ; clocks = <&clock CLK_CSIS1>, <&clock CLK_SCLK_CSIS1>; diff --git a/arch/arm/boot/dts/samsung/exynos4210-i9100.dts b/arch/arm/boot/dts/samsung/exynos4210-i9100.dts index a9ec1f6c1dea15..a076a1dfe41f8f 100644 --- a/arch/arm/boot/dts/samsung/exynos4210-i9100.dts +++ b/arch/arm/boot/dts/samsung/exynos4210-i9100.dts @@ -527,6 +527,14 @@ vtcam_reg: LDO12 { regulator-name = "VT_CAM_1.8V"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + + /* + * Force-enable this regulator; otherwise the + * kernel hangs very early in the boot process + * for about 12 seconds, without apparent + * reason. + */ + regulator-always-on; }; vcclcd_reg: LDO13 { diff --git a/arch/arm/boot/dts/samsung/exynos4210-smdkv310.dts b/arch/arm/boot/dts/samsung/exynos4210-smdkv310.dts index b566f878ed84f9..18f4f494093ba8 100644 --- a/arch/arm/boot/dts/samsung/exynos4210-smdkv310.dts +++ b/arch/arm/boot/dts/samsung/exynos4210-smdkv310.dts @@ -88,7 +88,7 @@ eeprom@52 { &keypad { samsung,keypad-num-rows = <2>; samsung,keypad-num-columns = <8>; - linux,keypad-no-autorepeat; + linux,input-no-autorepeat; wakeup-source; pinctrl-names = "default"; pinctrl-0 = <&keypad_rows &keypad_cols>; diff --git a/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi b/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi index ce81e42bf5eb3d..39469b708f910b 100644 --- a/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi +++ b/arch/arm/boot/dts/samsung/exynos4212-tab3.dtsi @@ -435,6 +435,7 @@ &exynos_usbphy { }; &fimd { + samsung,invert-vclk; status = "okay"; }; diff --git a/arch/arm/boot/dts/samsung/exynos4412-origen.dts b/arch/arm/boot/dts/samsung/exynos4412-origen.dts index 23b151645d6686..10ab7bc90f502f 100644 --- a/arch/arm/boot/dts/samsung/exynos4412-origen.dts +++ b/arch/arm/boot/dts/samsung/exynos4412-origen.dts @@ -453,7 +453,7 @@ buck9_reg: BUCK9 { &keypad { samsung,keypad-num-rows = <3>; samsung,keypad-num-columns = <2>; - linux,keypad-no-autorepeat; + linux,input-no-autorepeat; wakeup-source; pinctrl-0 = <&keypad_rows &keypad_cols>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/samsung/exynos4412-smdk4412.dts b/arch/arm/boot/dts/samsung/exynos4412-smdk4412.dts index 715dfcba141743..e16df9e75fcb0d 100644 --- a/arch/arm/boot/dts/samsung/exynos4412-smdk4412.dts +++ b/arch/arm/boot/dts/samsung/exynos4412-smdk4412.dts @@ -69,7 +69,7 @@ cooling_map1: map1 { &keypad { samsung,keypad-num-rows = <3>; samsung,keypad-num-columns = <8>; - linux,keypad-no-autorepeat; + linux,input-no-autorepeat; wakeup-source; pinctrl-0 = <&keypad_rows &keypad_cols>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/samsung/exynos4x12.dtsi b/arch/arm/boot/dts/samsung/exynos4x12.dtsi index 84c1db221c984b..83d9d0a0a61754 100644 --- a/arch/arm/boot/dts/samsung/exynos4x12.dtsi +++ b/arch/arm/boot/dts/samsung/exynos4x12.dtsi @@ -451,14 +451,15 @@ &combiner { }; &camera { + ranges = <0x0 0x11800000 0xba1000>; clocks = <&clock CLK_SCLK_CAM0>, <&clock CLK_SCLK_CAM1>, <&clock CLK_PIXELASYNCM0>, <&clock CLK_PIXELASYNCM1>; clock-names = "sclk_cam0", "sclk_cam1", "pxl_async0", "pxl_async1"; /* fimc_[0-3] are configured outside, under phandles */ - fimc_lite_0: fimc-lite@12390000 { + fimc_lite_0: fimc-lite@b90000 { compatible = "samsung,exynos4212-fimc-lite"; - reg = <0x12390000 0x1000>; + reg = <0x00b90000 0x1000>; interrupts = ; power-domains = <&pd_isp>; clocks = <&isp_clock CLK_ISP_FIMC_LITE0>; @@ -467,9 +468,9 @@ fimc_lite_0: fimc-lite@12390000 { status = "disabled"; }; - fimc_lite_1: fimc-lite@123a0000 { + fimc_lite_1: fimc-lite@ba0000 { compatible = "samsung,exynos4212-fimc-lite"; - reg = <0x123a0000 0x1000>; + reg = <0x00ba0000 0x1000>; interrupts = ; power-domains = <&pd_isp>; clocks = <&isp_clock CLK_ISP_FIMC_LITE1>; @@ -478,9 +479,9 @@ fimc_lite_1: fimc-lite@123a0000 { status = "disabled"; }; - fimc_is: fimc-is@12000000 { + fimc_is: fimc-is@800000 { compatible = "samsung,exynos4212-fimc-is"; - reg = <0x12000000 0x260000>; + reg = <0x00800000 0x260000>; interrupts = , ; power-domains = <&pd_isp>; @@ -525,9 +526,9 @@ pmu@10020000 { reg = <0x10020000 0x3000>; }; - i2c1_isp: i2c-isp@12140000 { + i2c1_isp: i2c-isp@940000 { compatible = "samsung,exynos4212-i2c-isp"; - reg = <0x12140000 0x100>; + reg = <0x00940000 0x100>; clocks = <&isp_clock CLK_ISP_I2C1_ISP>; clock-names = "i2c_isp"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/samsung/s5pv210.dtsi b/arch/arm/boot/dts/samsung/s5pv210.dtsi index f7de5b5f2f3837..ed560c9a3aa1ef 100644 --- a/arch/arm/boot/dts/samsung/s5pv210.dtsi +++ b/arch/arm/boot/dts/samsung/s5pv210.dtsi @@ -549,17 +549,17 @@ i2c1: i2c@fab00000 { camera: camera@fa600000 { compatible = "samsung,fimc"; + ranges = <0x0 0xfa600000 0xe01000>; clocks = <&clocks SCLK_CAM0>, <&clocks SCLK_CAM1>; clock-names = "sclk_cam0", "sclk_cam1"; #address-cells = <1>; #size-cells = <1>; #clock-cells = <1>; clock-output-names = "cam_a_clkout", "cam_b_clkout"; - ranges; - csis0: csis@fa600000 { + csis0: csis@0 { compatible = "samsung,s5pv210-csis"; - reg = <0xfa600000 0x4000>; + reg = <0x00000000 0x4000>; interrupt-parent = <&vic2>; interrupts = <29>; clocks = <&clocks CLK_CSIS>, @@ -572,9 +572,9 @@ csis0: csis@fa600000 { #size-cells = <0>; }; - fimc0: fimc@fb200000 { + fimc0: fimc@c00000 { compatible = "samsung,s5pv210-fimc"; - reg = <0xfb200000 0x1000>; + reg = <0x00c00000 0x1000>; interrupts = <5>; interrupt-parent = <&vic2>; clocks = <&clocks CLK_FIMC0>, @@ -586,9 +586,9 @@ fimc0: fimc@fb200000 { samsung,cam-if; }; - fimc1: fimc@fb300000 { + fimc1: fimc@d00000 { compatible = "samsung,s5pv210-fimc"; - reg = <0xfb300000 0x1000>; + reg = <0x00d00000 0x1000>; interrupt-parent = <&vic2>; interrupts = <6>; clocks = <&clocks CLK_FIMC1>, @@ -602,9 +602,9 @@ fimc1: fimc@fb300000 { samsung,lcd-wb; }; - fimc2: fimc@fb400000 { + fimc2: fimc@e00000 { compatible = "samsung,s5pv210-fimc"; - reg = <0xfb400000 0x1000>; + reg = <0x00e00000 0x1000>; interrupt-parent = <&vic2>; interrupts = <7>; clocks = <&clocks CLK_FIMC2>, diff --git a/arch/arm/boot/dts/st/stm32429i-eval.dts b/arch/arm/boot/dts/st/stm32429i-eval.dts index 576235ec3c516e..afa417b34b25ff 100644 --- a/arch/arm/boot/dts/st/stm32429i-eval.dts +++ b/arch/arm/boot/dts/st/stm32429i-eval.dts @@ -222,7 +222,6 @@ stmpe1600: stmpe1600@42 { reg = <0x42>; interrupts = <8 3>; interrupt-parent = <&gpioi>; - interrupt-controller; wakeup-source; stmpegpio: stmpe_gpio { diff --git a/arch/arm/boot/dts/st/stm32f7-pinctrl.dtsi b/arch/arm/boot/dts/st/stm32f7-pinctrl.dtsi index 65480a9f5cc4e1..842f2b17c4a81c 100644 --- a/arch/arm/boot/dts/st/stm32f7-pinctrl.dtsi +++ b/arch/arm/boot/dts/st/stm32f7-pinctrl.dtsi @@ -376,7 +376,6 @@ pins2 { }; }; - ltdc_pins_a: ltdc-0 { pins { pinmux = , /* LCD_B0 */ diff --git a/arch/arm/boot/dts/st/stm32mp151.dtsi b/arch/arm/boot/dts/st/stm32mp151.dtsi index 61508917521c36..aec7fa5ab5d8c6 100644 --- a/arch/arm/boot/dts/st/stm32mp151.dtsi +++ b/arch/arm/boot/dts/st/stm32mp151.dtsi @@ -50,6 +50,7 @@ timer { , ; interrupt-parent = <&intc>; + arm,no-tick-in-suspend; }; clocks { diff --git a/arch/arm/boot/dts/st/stm32mp157a-dk1-scmi.dts b/arch/arm/boot/dts/st/stm32mp157a-dk1-scmi.dts index afcd6285890cc0..c27963898b5e6c 100644 --- a/arch/arm/boot/dts/st/stm32mp157a-dk1-scmi.dts +++ b/arch/arm/boot/dts/st/stm32mp157a-dk1-scmi.dts @@ -11,7 +11,7 @@ / { model = "STMicroelectronics STM32MP157A-DK1 SCMI Discovery Board"; - compatible = "st,stm32mp157a-dk1-scmi", "st,stm32mp157a-dk1", "st,stm32mp157"; + compatible = "st,stm32mp157a-dk1-scmi", "st,stm32mp157"; reserved-memory { optee@de000000 { diff --git a/arch/arm/boot/dts/st/stm32mp157c-dk2-scmi.dts b/arch/arm/boot/dts/st/stm32mp157c-dk2-scmi.dts index 39358d90200031..62261894313407 100644 --- a/arch/arm/boot/dts/st/stm32mp157c-dk2-scmi.dts +++ b/arch/arm/boot/dts/st/stm32mp157c-dk2-scmi.dts @@ -11,7 +11,7 @@ / { model = "STMicroelectronics STM32MP157C-DK2 SCMI Discovery Board"; - compatible = "st,stm32mp157c-dk2-scmi", "st,stm32mp157c-dk2", "st,stm32mp157"; + compatible = "st,stm32mp157c-dk2-scmi", "st,stm32mp157"; reserved-memory { optee@de000000 { diff --git a/arch/arm/boot/dts/st/stm32mp157c-dk2.dts b/arch/arm/boot/dts/st/stm32mp157c-dk2.dts index 510cca5acb79ca..7a701f7ef0c704 100644 --- a/arch/arm/boot/dts/st/stm32mp157c-dk2.dts +++ b/arch/arm/boot/dts/st/stm32mp157c-dk2.dts @@ -64,7 +64,6 @@ touchscreen@38 { reg = <0x38>; interrupts = <2 2>; interrupt-parent = <&gpiof>; - interrupt-controller; touchscreen-size-x = <480>; touchscreen-size-y = <800>; status = "okay"; diff --git a/arch/arm/boot/dts/st/stm32mp157c-ed1-scmi.dts b/arch/arm/boot/dts/st/stm32mp157c-ed1-scmi.dts index 07ea765a4553a5..c7c4d7e89d6123 100644 --- a/arch/arm/boot/dts/st/stm32mp157c-ed1-scmi.dts +++ b/arch/arm/boot/dts/st/stm32mp157c-ed1-scmi.dts @@ -11,7 +11,7 @@ / { model = "STMicroelectronics STM32MP157C-ED1 SCMI eval daughter"; - compatible = "st,stm32mp157c-ed1-scmi", "st,stm32mp157c-ed1", "st,stm32mp157"; + compatible = "st,stm32mp157c-ed1-scmi", "st,stm32mp157"; reserved-memory { optee@fe000000 { diff --git a/arch/arm/boot/dts/st/stm32mp157c-ev1-scmi.dts b/arch/arm/boot/dts/st/stm32mp157c-ev1-scmi.dts index 813086ec248959..2ab77e64f1bbb9 100644 --- a/arch/arm/boot/dts/st/stm32mp157c-ev1-scmi.dts +++ b/arch/arm/boot/dts/st/stm32mp157c-ev1-scmi.dts @@ -11,8 +11,7 @@ / { model = "STMicroelectronics STM32MP157C-EV1 SCMI eval daughter on eval mother"; - compatible = "st,stm32mp157c-ev1-scmi", "st,stm32mp157c-ev1", "st,stm32mp157c-ed1", - "st,stm32mp157"; + compatible = "st,stm32mp157c-ev1-scmi", "st,stm32mp157c-ed1", "st,stm32mp157"; reserved-memory { optee@fe000000 { diff --git a/arch/arm/boot/dts/ti/omap/am335x-moxa-uc-2100-common.dtsi b/arch/arm/boot/dts/ti/omap/am335x-moxa-uc-2100-common.dtsi index b8730aa52ce6fe..a59331aa58e55e 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-moxa-uc-2100-common.dtsi +++ b/arch/arm/boot/dts/ti/omap/am335x-moxa-uc-2100-common.dtsi @@ -217,7 +217,7 @@ &spi1 { pinctrl-names = "default"; pinctrl-0 = <&spi1_pins>; - tpm_spi_tis@0 { + tpm@0 { compatible = "tcg,tpm_tis-spi"; reg = <0>; spi-max-frequency = <500000>; diff --git a/arch/arm/boot/dts/ti/omap/am33xx.dtsi b/arch/arm/boot/dts/ti/omap/am33xx.dtsi index 1a2cd5baf40210..5b9e01a8aa5d5a 100644 --- a/arch/arm/boot/dts/ti/omap/am33xx.dtsi +++ b/arch/arm/boot/dts/ti/omap/am33xx.dtsi @@ -359,6 +359,7 @@ usb: target-module@47400000 { , , ; + ti,sysc-delay-us = <2>; clocks = <&l3s_clkctrl AM3_L3S_USB_OTG_HS_CLKCTRL 0>; clock-names = "fck"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/ti/omap/am3517-evm.dts b/arch/arm/boot/dts/ti/omap/am3517-evm.dts index af9df15274bed1..866f68c5b504dc 100644 --- a/arch/arm/boot/dts/ti/omap/am3517-evm.dts +++ b/arch/arm/boot/dts/ti/omap/am3517-evm.dts @@ -271,13 +271,6 @@ OMAP3_CORE1_IOPAD(0x21c4, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_sda */ >; }; - leds_pins: leds-pins { - pinctrl-single,pins = < - OMAP3_WKUP_IOPAD(0x2a24, PIN_OUTPUT_PULLUP | MUX_MODE4) /* jtag_emu0.gpio_11 */ - OMAP3_WKUP_IOPAD(0x2a26, PIN_OUTPUT_PULLUP | MUX_MODE4) /* jtag_emu1.gpio_31 */ - >; - }; - mmc1_pins: mmc1-pins { pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x2144, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc1_clk.sdmmc1_clk */ @@ -355,3 +348,12 @@ OMAP3430_CORE2_IOPAD(0x25e2, PIN_INPUT | MUX_MODE3) /* etk_d3.hsusb1_data7 */ >; }; }; + +&omap3_pmx_wkup { + leds_pins: leds-pins { + pinctrl-single,pins = < + OMAP3_WKUP_IOPAD(0x2a24, PIN_OUTPUT_PULLUP | MUX_MODE4) /* jtag_emu0.gpio_11 */ + OMAP3_WKUP_IOPAD(0x2a26, PIN_OUTPUT_PULLUP | MUX_MODE4) /* jtag_emu1.gpio_31 */ + >; + }; +}; diff --git a/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts b/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts index 9a234dc1431d12..5b240769d300e5 100644 --- a/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts +++ b/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts @@ -415,7 +415,6 @@ stmpe811@41 { reg = <0x41>; interrupts = <30 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&gpio2>; - interrupt-controller; id = <0>; blocks = <0x5>; irq-trigger = <0x1>; diff --git a/arch/arm/boot/dts/ti/omap/dra7.dtsi b/arch/arm/boot/dts/ti/omap/dra7.dtsi index 3f3e52e3b37526..6509c742fb58c9 100644 --- a/arch/arm/boot/dts/ti/omap/dra7.dtsi +++ b/arch/arm/boot/dts/ti/omap/dra7.dtsi @@ -147,7 +147,7 @@ ocp: ocp { l3-noc@44000000 { compatible = "ti,dra7-l3-noc"; - reg = <0x44000000 0x1000>, + reg = <0x44000000 0x1000000>, <0x45000000 0x1000>; interrupts-extended = <&crossbar_mpu GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>, <&wakeupgen GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/boot/dts/ti/omap/omap3-n900.dts b/arch/arm/boot/dts/ti/omap/omap3-n900.dts index d3348534125173..036e472b77bebb 100644 --- a/arch/arm/boot/dts/ti/omap/omap3-n900.dts +++ b/arch/arm/boot/dts/ti/omap/omap3-n900.dts @@ -781,7 +781,7 @@ accelerometer@1d { mount-matrix = "-1", "0", "0", "0", "1", "0", - "0", "0", "1"; + "0", "0", "-1"; }; cam1: camera@3e { diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 0a90583f9f017e..8f9dbe8d90291e 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -297,6 +297,7 @@ CONFIG_FB_MODE_HELPERS=y CONFIG_LCD_CLASS_DEVICE=y CONFIG_LCD_L4F00242T03=y CONFIG_LCD_PLATFORM=y +CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_BACKLIGHT_PWM=y CONFIG_BACKLIGHT_GPIO=y CONFIG_FRAMEBUFFER_CONSOLE=y diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig index bddc82f7894211..a83d29fed17563 100644 --- a/arch/arm/configs/sunxi_defconfig +++ b/arch/arm/configs/sunxi_defconfig @@ -110,6 +110,7 @@ CONFIG_DRM_PANEL_LVDS=y CONFIG_DRM_PANEL_SIMPLE=y CONFIG_DRM_PANEL_EDP=y CONFIG_DRM_SIMPLE_BRIDGE=y +CONFIG_DRM_DW_HDMI=y CONFIG_DRM_LIMA=y CONFIG_FB_SIMPLE=y CONFIG_BACKLIGHT_CLASS_DEVICE=y diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c index b668c97663ec0c..f5b66f4cf45d96 100644 --- a/arch/arm/crypto/aes-ce-glue.c +++ b/arch/arm/crypto/aes-ce-glue.c @@ -711,7 +711,7 @@ static int __init aes_init(void) algname = aes_algs[i].base.cra_name + 2; drvname = aes_algs[i].base.cra_driver_name + 2; basename = aes_algs[i].base.cra_driver_name; - simd = simd_skcipher_create_compat(algname, drvname, basename); + simd = simd_skcipher_create_compat(aes_algs + i, algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) goto unregister_simds; diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c index f00f042ef3570e..0ca94b90bc4ec5 100644 --- a/arch/arm/crypto/aes-neonbs-glue.c +++ b/arch/arm/crypto/aes-neonbs-glue.c @@ -539,7 +539,7 @@ static int __init aes_init(void) algname = aes_algs[i].base.cra_name + 2; drvname = aes_algs[i].base.cra_driver_name + 2; basename = aes_algs[i].base.cra_driver_name; - simd = simd_skcipher_create_compat(algname, drvname, basename); + simd = simd_skcipher_create_compat(aes_algs + i, algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) goto unregister_simds; diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c index 433ee4ddce6c81..f85933fdec75fd 100644 --- a/arch/arm/crypto/sha256_glue.c +++ b/arch/arm/crypto/sha256_glue.c @@ -24,8 +24,8 @@ #include "sha256_glue.h" -asmlinkage void sha256_block_data_order(u32 *digest, const void *data, - unsigned int num_blks); +asmlinkage void sha256_block_data_order(struct sha256_state *state, + const u8 *data, int num_blks); int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data, unsigned int len) @@ -33,23 +33,20 @@ int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data, /* make sure casting to sha256_block_fn() is safe */ BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0); - return sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_block_data_order); + return sha256_base_do_update(desc, data, len, sha256_block_data_order); } EXPORT_SYMBOL(crypto_sha256_arm_update); static int crypto_sha256_arm_final(struct shash_desc *desc, u8 *out) { - sha256_base_do_finalize(desc, - (sha256_block_fn *)sha256_block_data_order); + sha256_base_do_finalize(desc, sha256_block_data_order); return sha256_base_finish(desc, out); } int crypto_sha256_arm_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_block_data_order); + sha256_base_do_update(desc, data, len, sha256_block_data_order); return crypto_sha256_arm_final(desc, out); } EXPORT_SYMBOL(crypto_sha256_arm_finup); diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c index 0635a65aa488ba..1be5bd498af36f 100644 --- a/arch/arm/crypto/sha512-glue.c +++ b/arch/arm/crypto/sha512-glue.c @@ -25,27 +25,25 @@ MODULE_ALIAS_CRYPTO("sha512"); MODULE_ALIAS_CRYPTO("sha384-arm"); MODULE_ALIAS_CRYPTO("sha512-arm"); -asmlinkage void sha512_block_data_order(u64 *state, u8 const *src, int blocks); +asmlinkage void sha512_block_data_order(struct sha512_state *state, + u8 const *src, int blocks); int sha512_arm_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - return sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_block_data_order); + return sha512_base_do_update(desc, data, len, sha512_block_data_order); } static int sha512_arm_final(struct shash_desc *desc, u8 *out) { - sha512_base_do_finalize(desc, - (sha512_block_fn *)sha512_block_data_order); + sha512_base_do_finalize(desc, sha512_block_data_order); return sha512_base_finish(desc, out); } int sha512_arm_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_block_data_order); + sha512_base_do_update(desc, data, len, sha512_block_data_order); return sha512_arm_final(desc, out); } diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h index 72529f5e2bed95..a41b503b7dcde0 100644 --- a/arch/arm/include/asm/arm_pmuv3.h +++ b/arch/arm/include/asm/arm_pmuv3.h @@ -23,6 +23,8 @@ #define PMUSERENR __ACCESS_CP15(c9, 0, c14, 0) #define PMINTENSET __ACCESS_CP15(c9, 0, c14, 1) #define PMINTENCLR __ACCESS_CP15(c9, 0, c14, 2) +#define PMCEID2 __ACCESS_CP15(c9, 0, c14, 4) +#define PMCEID3 __ACCESS_CP15(c9, 0, c14, 5) #define PMMIR __ACCESS_CP15(c9, 0, c14, 6) #define PMCCFILTR __ACCESS_CP15(c14, 0, c15, 7) @@ -150,21 +152,6 @@ static inline u64 read_pmccntr(void) return read_sysreg(PMCCNTR); } -static inline void write_pmxevcntr(u32 val) -{ - write_sysreg(val, PMXEVCNTR); -} - -static inline u32 read_pmxevcntr(void) -{ - return read_sysreg(PMXEVCNTR); -} - -static inline void write_pmxevtyper(u32 val) -{ - write_sysreg(val, PMXEVTYPER); -} - static inline void write_pmcntenset(u32 val) { write_sysreg(val, PMCNTENSET); @@ -205,16 +192,6 @@ static inline void write_pmuserenr(u32 val) write_sysreg(val, PMUSERENR); } -static inline u32 read_pmceid0(void) -{ - return read_sysreg(PMCEID0); -} - -static inline u32 read_pmceid1(void) -{ - return read_sysreg(PMCEID1); -} - static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {} static inline void kvm_clr_pmu_events(u32 clr) {} static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr) @@ -231,6 +208,7 @@ static inline void kvm_vcpu_pmu_resync_el0(void) {} /* PMU Version in DFR Register */ #define ARMV8_PMU_DFR_VER_NI 0 +#define ARMV8_PMU_DFR_VER_V3P1 0x4 #define ARMV8_PMU_DFR_VER_V3P4 0x5 #define ARMV8_PMU_DFR_VER_V3P5 0x6 #define ARMV8_PMU_DFR_VER_IMP_DEF 0xF @@ -251,4 +229,24 @@ static inline bool is_pmuv3p5(int pmuver) return pmuver >= ARMV8_PMU_DFR_VER_V3P5; } +static inline u64 read_pmceid0(void) +{ + u64 val = read_sysreg(PMCEID0); + + if (read_pmuver() >= ARMV8_PMU_DFR_VER_V3P1) + val |= (u64)read_sysreg(PMCEID2) << 32; + + return val; +} + +static inline u64 read_pmceid1(void) +{ + u64 val = read_sysreg(PMCEID1); + + if (read_pmuver() >= ARMV8_PMU_DFR_VER_V3P1) + val |= (u64)read_sysreg(PMCEID3) << 32; + + return val; +} + #endif diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index f6181f69577fe5..1075534b0a2eeb 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -340,6 +340,8 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end) dsb(ishst); } +#define flush_cache_vmap_early(start, end) do { } while (0) + static inline void flush_cache_vunmap(unsigned long start, unsigned long end) { if (!cache_is_vipt_nonaliasing()) diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h index c6aded1b069cf0..e2a1916013e75e 100644 --- a/arch/arm/include/asm/dma.h +++ b/arch/arm/include/asm/dma.h @@ -12,6 +12,9 @@ extern phys_addr_t arm_dma_zone_size; \ arm_dma_zone_size && arm_dma_zone_size < (0x100000000ULL - PAGE_OFFSET) ? \ (PAGE_OFFSET + arm_dma_zone_size) : 0xffffffffUL; }) + +extern phys_addr_t arm_dma_limit; +#define ARCH_LOW_ADDRESS_LIMIT arm_dma_limit #endif #ifdef CONFIG_ISA_DMA_API diff --git a/arch/arm/include/asm/exception.h b/arch/arm/include/asm/exception.h index 58e039a851af03..3c82975d46db35 100644 --- a/arch/arm/include/asm/exception.h +++ b/arch/arm/include/asm/exception.h @@ -10,10 +10,6 @@ #include -#ifdef CONFIG_FUNCTION_GRAPH_TRACER #define __exception_irq_entry __irq_entry -#else -#define __exception_irq_entry -#endif #endif /* __ASM_ARM_EXCEPTION_H */ diff --git a/arch/arm/include/asm/irq_work.h b/arch/arm/include/asm/irq_work.h index 3149e4dc1b5405..8895999834cc0b 100644 --- a/arch/arm/include/asm/irq_work.h +++ b/arch/arm/include/asm/irq_work.h @@ -9,6 +9,4 @@ static inline bool arch_irq_work_has_interrupt(void) return is_smp(); } -extern void arch_irq_work_raise(void); - #endif /* _ASM_ARM_IRQ_WORK_H */ diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h index e12d7d096fc034..e4eb54f6cd9fef 100644 --- a/arch/arm/include/asm/jump_label.h +++ b/arch/arm/include/asm/jump_label.h @@ -11,7 +11,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" WASM(nop) "\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" @@ -25,7 +25,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" WASM(b) " %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" diff --git a/arch/arm/include/asm/kexec.h b/arch/arm/include/asm/kexec.h index e62832dcba7600..a8287e7ab9d41a 100644 --- a/arch/arm/include/asm/kexec.h +++ b/arch/arm/include/asm/kexec.h @@ -2,8 +2,6 @@ #ifndef _ARM_KEXEC_H #define _ARM_KEXEC_H -#ifdef CONFIG_KEXEC - /* Maximum physical address we can use pages from */ #define KEXEC_SOURCE_MEMORY_LIMIT (-1UL) /* Maximum address we can reach in physical address mode */ @@ -82,6 +80,4 @@ static inline struct page *boot_pfn_to_page(unsigned long boot_pfn) #endif /* __ASSEMBLY__ */ -#endif /* CONFIG_KEXEC */ - #endif /* _ARM_KEXEC_H */ diff --git a/arch/arm/include/asm/mman.h b/arch/arm/include/asm/mman.h new file mode 100644 index 00000000000000..2189e507c8e08b --- /dev/null +++ b/arch/arm/include/asm/mman.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MMAN_H__ +#define __ASM_MMAN_H__ + +#include +#include + +static inline bool arch_memory_deny_write_exec_supported(void) +{ + return cpu_architecture() >= CPU_ARCH_ARMv6; +} +#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported + +#endif /* __ASM_MMAN_H__ */ diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 16b02f44c7d312..d657b84b6bf706 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -151,6 +151,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; +#define pgdp_get(pgpd) READ_ONCE(*pgdp) + #define pud_page(pud) pmd_page(__pmd(pud_val(pud))) #define pud_write(pud) pmd_write(__pmd(pud_val(pud))) diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index bb5c8182311774..c28f5ec21e417b 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -109,16 +109,6 @@ extern int __get_user_64t_1(void *); extern int __get_user_64t_2(void *); extern int __get_user_64t_4(void *); -#define __GUP_CLOBBER_1 "lr", "cc" -#ifdef CONFIG_CPU_USE_DOMAINS -#define __GUP_CLOBBER_2 "ip", "lr", "cc" -#else -#define __GUP_CLOBBER_2 "lr", "cc" -#endif -#define __GUP_CLOBBER_4 "lr", "cc" -#define __GUP_CLOBBER_32t_8 "lr", "cc" -#define __GUP_CLOBBER_8 "lr", "cc" - #define __get_user_x(__r2, __p, __e, __l, __s) \ __asm__ __volatile__ ( \ __asmeq("%0", "r0") __asmeq("%1", "r2") \ @@ -126,7 +116,7 @@ extern int __get_user_64t_4(void *); "bl __get_user_" #__s \ : "=&r" (__e), "=r" (__r2) \ : "0" (__p), "r" (__l) \ - : __GUP_CLOBBER_##__s) + : "ip", "lr", "cc") /* narrowing a double-word get into a single 32bit word register: */ #ifdef __ARMEB__ @@ -148,7 +138,7 @@ extern int __get_user_64t_4(void *); "bl __get_user_64t_" #__s \ : "=&r" (__e), "=r" (__r2) \ : "0" (__p), "r" (__l) \ - : __GUP_CLOBBER_##__s) + : "ip", "lr", "cc") #else #define __get_user_x_64t __get_user_x #endif diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index d53f56d6f84085..ae2f2b2b4e5abc 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -59,7 +59,7 @@ obj-$(CONFIG_FUNCTION_TRACER) += entry-ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o insn.o patch.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o insn.o patch.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o insn.o patch.o -obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o +obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o # Main staffs in KPROBES are in arch/arm/probes/ . obj-$(CONFIG_KPROBES) += patch.o insn.o obj-$(CONFIG_OABI_COMPAT) += sys_oabi-compat.o @@ -75,8 +75,6 @@ obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_CPU_XSCALE) += xscale-cp0.o obj-$(CONFIG_CPU_XSC3) += xscale-cp0.o obj-$(CONFIG_CPU_MOHAWK) += xscale-cp0.o -obj-$(CONFIG_CPU_PJ4) += pj4-cp0.o -obj-$(CONFIG_CPU_PJ4B) += pj4-cp0.o obj-$(CONFIG_IWMMXT) += iwmmxt.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o obj-$(CONFIG_HW_PERF_EVENTS) += perf_event_xscale.o perf_event_v6.o \ diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S index a0218c4867b9b6..4a335d3c59690b 100644 --- a/arch/arm/kernel/iwmmxt.S +++ b/arch/arm/kernel/iwmmxt.S @@ -18,18 +18,6 @@ #include #include "iwmmxt.h" -#if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B) -#define PJ4(code...) code -#define XSC(code...) -#elif defined(CONFIG_CPU_MOHAWK) || \ - defined(CONFIG_CPU_XSC3) || \ - defined(CONFIG_CPU_XSCALE) -#define PJ4(code...) -#define XSC(code...) code -#else -#error "Unsupported iWMMXt architecture" -#endif - #define MMX_WR0 (0x00) #define MMX_WR1 (0x08) #define MMX_WR2 (0x10) @@ -81,17 +69,13 @@ ENDPROC(iwmmxt_undef_handler) ENTRY(iwmmxt_task_enable) inc_preempt_count r10, r3 - XSC(mrc p15, 0, r2, c15, c1, 0) - PJ4(mrc p15, 0, r2, c1, c0, 2) + mrc p15, 0, r2, c15, c1, 0 @ CP0 and CP1 accessible? - XSC(tst r2, #0x3) - PJ4(tst r2, #0xf) + tst r2, #0x3 bne 4f @ if so no business here @ enable access to CP0 and CP1 - XSC(orr r2, r2, #0x3) - XSC(mcr p15, 0, r2, c15, c1, 0) - PJ4(orr r2, r2, #0xf) - PJ4(mcr p15, 0, r2, c1, c0, 2) + orr r2, r2, #0x3 + mcr p15, 0, r2, c15, c1, 0 ldr r3, =concan_owner ldr r2, [r0, #S_PC] @ current task pc value @@ -218,12 +202,9 @@ ENTRY(iwmmxt_task_disable) bne 1f @ no: quit @ enable access to CP0 and CP1 - XSC(mrc p15, 0, r4, c15, c1, 0) - XSC(orr r4, r4, #0x3) - XSC(mcr p15, 0, r4, c15, c1, 0) - PJ4(mrc p15, 0, r4, c1, c0, 2) - PJ4(orr r4, r4, #0xf) - PJ4(mcr p15, 0, r4, c1, c0, 2) + mrc p15, 0, r4, c15, c1, 0 + orr r4, r4, #0x3 + mcr p15, 0, r4, c15, c1, 0 mov r0, #0 @ nothing to load str r0, [r3] @ no more current owner @@ -232,10 +213,8 @@ ENTRY(iwmmxt_task_disable) bl concan_save @ disable access to CP0 and CP1 - XSC(bic r4, r4, #0x3) - XSC(mcr p15, 0, r4, c15, c1, 0) - PJ4(bic r4, r4, #0xf) - PJ4(mcr p15, 0, r4, c1, c0, 2) + bic r4, r4, #0x3 + mcr p15, 0, r4, c15, c1, 0 mrc p15, 0, r2, c2, c0, 0 mov r2, r2 @ cpwait @@ -330,11 +309,9 @@ ENDPROC(iwmmxt_task_restore) */ ENTRY(iwmmxt_task_switch) - XSC(mrc p15, 0, r1, c15, c1, 0) - PJ4(mrc p15, 0, r1, c1, c0, 2) + mrc p15, 0, r1, c15, c1, 0 @ CP0 and CP1 accessible? - XSC(tst r1, #0x3) - PJ4(tst r1, #0xf) + tst r1, #0x3 bne 1f @ yes: block them for next task ldr r2, =concan_owner @@ -344,10 +321,8 @@ ENTRY(iwmmxt_task_switch) retne lr @ no: leave Concan disabled 1: @ flip Concan access - XSC(eor r1, r1, #0x3) - XSC(mcr p15, 0, r1, c15, c1, 0) - PJ4(eor r1, r1, #0xf) - PJ4(mcr p15, 0, r1, c1, c0, 2) + eor r1, r1, #0x3 + mcr p15, 0, r1, c15, c1, 0 mrc p15, 0, r1, c2, c0, 0 sub pc, lr, r1, lsr #32 @ cpwait and return diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c index 7147edbe56c67c..1d230ac9d0eb5c 100644 --- a/arch/arm/kernel/perf_callchain.c +++ b/arch/arm/kernel/perf_callchain.c @@ -85,8 +85,7 @@ static bool callchain_trace(void *data, unsigned long pc) { struct perf_callchain_entry_ctx *entry = data; - perf_callchain_store(entry, pc); - return true; + return perf_callchain_store(entry, pc) == 0; } void diff --git a/arch/arm/kernel/pj4-cp0.c b/arch/arm/kernel/pj4-cp0.c deleted file mode 100644 index 4bca8098c4ff55..00000000000000 --- a/arch/arm/kernel/pj4-cp0.c +++ /dev/null @@ -1,135 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * linux/arch/arm/kernel/pj4-cp0.c - * - * PJ4 iWMMXt coprocessor context switching and handling - * - * Copyright (c) 2010 Marvell International Inc. - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -static int iwmmxt_do(struct notifier_block *self, unsigned long cmd, void *t) -{ - struct thread_info *thread = t; - - switch (cmd) { - case THREAD_NOTIFY_FLUSH: - /* - * flush_thread() zeroes thread->fpstate, so no need - * to do anything here. - * - * FALLTHROUGH: Ensure we don't try to overwrite our newly - * initialised state information on the first fault. - */ - - case THREAD_NOTIFY_EXIT: - iwmmxt_task_release(thread); - break; - - case THREAD_NOTIFY_SWITCH: - iwmmxt_task_switch(thread); - break; - } - - return NOTIFY_DONE; -} - -static struct notifier_block __maybe_unused iwmmxt_notifier_block = { - .notifier_call = iwmmxt_do, -}; - - -static u32 __init pj4_cp_access_read(void) -{ - u32 value; - - __asm__ __volatile__ ( - "mrc p15, 0, %0, c1, c0, 2\n\t" - : "=r" (value)); - return value; -} - -static void __init pj4_cp_access_write(u32 value) -{ - u32 temp; - - __asm__ __volatile__ ( - "mcr p15, 0, %1, c1, c0, 2\n\t" -#ifdef CONFIG_THUMB2_KERNEL - "isb\n\t" -#else - "mrc p15, 0, %0, c1, c0, 2\n\t" - "mov %0, %0\n\t" - "sub pc, pc, #4\n\t" -#endif - : "=r" (temp) : "r" (value)); -} - -static int __init pj4_get_iwmmxt_version(void) -{ - u32 cp_access, wcid; - - cp_access = pj4_cp_access_read(); - pj4_cp_access_write(cp_access | 0xf); - - /* check if coprocessor 0 and 1 are available */ - if ((pj4_cp_access_read() & 0xf) != 0xf) { - pj4_cp_access_write(cp_access); - return -ENODEV; - } - - /* read iWMMXt coprocessor id register p1, c0 */ - __asm__ __volatile__ ("mrc p1, 0, %0, c0, c0, 0\n" : "=r" (wcid)); - - pj4_cp_access_write(cp_access); - - /* iWMMXt v1 */ - if ((wcid & 0xffffff00) == 0x56051000) - return 1; - /* iWMMXt v2 */ - if ((wcid & 0xffffff00) == 0x56052000) - return 2; - - return -EINVAL; -} - -/* - * Disable CP0/CP1 on boot, and let call_fpe() and the iWMMXt lazy - * switch code handle iWMMXt context switching. - */ -static int __init pj4_cp0_init(void) -{ - u32 __maybe_unused cp_access; - int vers; - - if (!cpu_is_pj4()) - return 0; - - vers = pj4_get_iwmmxt_version(); - if (vers < 0) - return 0; - -#ifndef CONFIG_IWMMXT - pr_info("PJ4 iWMMXt coprocessor detected, but kernel support is missing.\n"); -#else - cp_access = pj4_cp_access_read() & ~0xf; - pj4_cp_access_write(cp_access); - - pr_info("PJ4 iWMMXt v%d coprocessor enabled.\n", vers); - elf_hwcap |= HWCAP_IWMMXT; - thread_register_notifier(&iwmmxt_notifier_block); - register_iwmmxt_undef_handler(); -#endif - - return 0; -} - -late_initcall(pj4_cp0_init); diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index a86a1d4f34618c..93afd1005b43c9 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -127,6 +127,10 @@ cpu_resume_after_mmu: instr_sync #endif bl cpu_init @ restore the und/abt/irq banked regs +#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) + mov r0, sp + bl kasan_unpoison_task_stack_below +#endif mov r0, #0 @ return zero on success ldmfd sp!, {r4 - r11, pc} ENDPROC(cpu_resume_after_mmu) diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S index d71ab61430b261..de75ae4d5ab41c 100644 --- a/arch/arm/lib/memset.S +++ b/arch/arm/lib/memset.S @@ -17,6 +17,7 @@ ENTRY(__memset) ENTRY(mmioset) WEAK(memset) UNWIND( .fnstart ) + and r1, r1, #255 @ cast to unsigned char ands r3, r0, #3 @ 1 unaligned? mov ip, r0 @ preserve r0 as return value bne 6f @ 1 diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig index 4316e1370627cf..2a8a9fe46586d2 100644 --- a/arch/arm/mach-davinci/Kconfig +++ b/arch/arm/mach-davinci/Kconfig @@ -4,12 +4,14 @@ menuconfig ARCH_DAVINCI bool "TI DaVinci" depends on ARCH_MULTI_V5 depends on CPU_LITTLE_ENDIAN + select CPU_ARM926T select DAVINCI_TIMER select ZONE_DMA select PM_GENERIC_DOMAINS if PM select PM_GENERIC_DOMAINS_OF if PM && OF select REGMAP_MMIO select RESET_CONTROLLER + select PINCTRL select PINCTRL_SINGLE if ARCH_DAVINCI diff --git a/arch/arm/mach-davinci/pm.c b/arch/arm/mach-davinci/pm.c index 8aa39db095d761..2c5155bd376ba8 100644 --- a/arch/arm/mach-davinci/pm.c +++ b/arch/arm/mach-davinci/pm.c @@ -61,7 +61,7 @@ static void davinci_pm_suspend(void) /* Configure sleep count in deep sleep register */ val = __raw_readl(pm_config.deepsleep_reg); - val &= ~DEEPSLEEP_SLEEPCOUNT_MASK, + val &= ~DEEPSLEEP_SLEEPCOUNT_MASK; val |= pm_config.sleepcount; __raw_writel(val, pm_config.deepsleep_reg); diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c index 85a496ddc6197e..e9f72a529b5089 100644 --- a/arch/arm/mach-ep93xx/clock.c +++ b/arch/arm/mach-ep93xx/clock.c @@ -359,7 +359,7 @@ static unsigned long ep93xx_div_recalc_rate(struct clk_hw *hw, u32 val = __raw_readl(psc->reg); u8 index = (val & psc->mask) >> psc->shift; - if (index > psc->num_div) + if (index >= psc->num_div) return 0; return DIV_ROUND_UP_ULL(parent_rate, psc->div[index]); diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c index 71b1139764204c..8b1ec60a9a467a 100644 --- a/arch/arm/mach-ep93xx/core.c +++ b/arch/arm/mach-ep93xx/core.c @@ -339,6 +339,7 @@ static struct gpiod_lookup_table ep93xx_i2c_gpiod_table = { GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), GPIO_LOOKUP_IDX("G", 0, NULL, 1, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), + { } }, }; diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c index 2157493b78a9bd..df69af9323754f 100644 --- a/arch/arm/mach-imx/mmdc.c +++ b/arch/arm/mach-imx/mmdc.c @@ -501,6 +501,10 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "mmdc%d", ret); + if (!name) { + ret = -ENOMEM; + goto pmu_release_id; + } pmu_mmdc->mmdc_ipg_clk = mmdc_ipg_clk; pmu_mmdc->devtype_data = (struct fsl_mmdc_devtype_data *)of_id->data; @@ -523,9 +527,10 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b pmu_register_err: pr_warn("MMDC Perf PMU failed (%d), disabled\n", ret); - ida_simple_remove(&mmdc_ida, pmu_mmdc->id); cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node); hrtimer_cancel(&pmu_mmdc->hrtimer); +pmu_release_id: + ida_simple_remove(&mmdc_ida, pmu_mmdc->id); pmu_free: kfree(pmu_mmdc); return ret; diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c index 8e3b5068d4ab07..b45a3879eb344c 100644 --- a/arch/arm/mach-omap2/board-n8x0.c +++ b/arch/arm/mach-omap2/board-n8x0.c @@ -79,10 +79,8 @@ static struct musb_hdrc_platform_data tusb_data = { static struct gpiod_lookup_table tusb_gpio_table = { .dev_id = "musb-tusb", .table = { - GPIO_LOOKUP("gpio-0-15", 0, "enable", - GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("gpio-48-63", 10, "int", - GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio-0-31", 0, "enable", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio-32-63", 26, "int", GPIO_ACTIVE_HIGH), { } }, }; @@ -140,12 +138,11 @@ static int slot1_cover_open; static int slot2_cover_open; static struct device *mmc_device; -static struct gpiod_lookup_table nokia8xx_mmc_gpio_table = { +static struct gpiod_lookup_table nokia800_mmc_gpio_table = { .dev_id = "mmci-omap.0", .table = { /* Slot switch, GPIO 96 */ - GPIO_LOOKUP("gpio-80-111", 16, - "switch", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio-96-127", 0, "switch", GPIO_ACTIVE_HIGH), { } }, }; @@ -153,12 +150,12 @@ static struct gpiod_lookup_table nokia8xx_mmc_gpio_table = { static struct gpiod_lookup_table nokia810_mmc_gpio_table = { .dev_id = "mmci-omap.0", .table = { + /* Slot switch, GPIO 96 */ + GPIO_LOOKUP("gpio-96-127", 0, "switch", GPIO_ACTIVE_HIGH), /* Slot index 1, VSD power, GPIO 23 */ - GPIO_LOOKUP_IDX("gpio-16-31", 7, - "vsd", 1, GPIO_ACTIVE_HIGH), + GPIO_LOOKUP_IDX("gpio-0-31", 23, "vsd", 1, GPIO_ACTIVE_HIGH), /* Slot index 1, VIO power, GPIO 9 */ - GPIO_LOOKUP_IDX("gpio-0-15", 9, - "vio", 1, GPIO_ACTIVE_HIGH), + GPIO_LOOKUP_IDX("gpio-0-31", 9, "vio", 1, GPIO_ACTIVE_HIGH), { } }, }; @@ -415,8 +412,6 @@ static struct omap_mmc_platform_data *mmc_data[OMAP24XX_NR_MMC]; static void __init n8x0_mmc_init(void) { - gpiod_add_lookup_table(&nokia8xx_mmc_gpio_table); - if (board_is_n810()) { mmc1_data.slots[0].name = "external"; @@ -429,6 +424,8 @@ static void __init n8x0_mmc_init(void) mmc1_data.slots[1].name = "internal"; mmc1_data.slots[1].ban_openended = 1; gpiod_add_lookup_table(&nokia810_mmc_gpio_table); + } else { + gpiod_add_lookup_table(&nokia800_mmc_gpio_table); } mmc1_data.nr_slots = 2; diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 98999aa8cc0c09..7f387706368a68 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -793,11 +793,16 @@ void __init omap_soc_device_init(void) soc_dev_attr->machine = soc_name; soc_dev_attr->family = omap_get_family(); + if (!soc_dev_attr->family) { + kfree(soc_dev_attr); + return; + } soc_dev_attr->revision = soc_rev; soc_dev_attr->custom_attr_group = omap_soc_groups[0]; soc_dev = soc_device_register(soc_dev_attr); if (IS_ERR(soc_dev)) { + kfree(soc_dev_attr->family); kfree(soc_dev_attr); return; } diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c index c1c0121f478d66..b947bacf23a376 100644 --- a/arch/arm/mach-omap2/pdata-quirks.c +++ b/arch/arm/mach-omap2/pdata-quirks.c @@ -275,9 +275,19 @@ static struct platform_device pandora_backlight = { .id = -1, }; +static struct gpiod_lookup_table pandora_soc_audio_gpios = { + .dev_id = "soc-audio", + .table = { + GPIO_LOOKUP("gpio-112-127", 6, "dac", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio-0-15", 14, "amp", GPIO_ACTIVE_HIGH), + { } + }, +}; + static void __init omap3_pandora_legacy_init(void) { platform_device_register(&pandora_backlight); + gpiod_add_lookup_table(&pandora_soc_audio_gpios); } #endif /* CONFIG_ARCH_OMAP3 */ diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index cc691b199429ca..a42417de53f74d 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -520,10 +520,8 @@ static struct gpiod_lookup_table spitz_ads7846_gpio_table = { static struct gpiod_lookup_table spitz_lcdcon_gpio_table = { .dev_id = "spi2.1", .table = { - GPIO_LOOKUP("gpio-pxa", SPITZ_GPIO_BACKLIGHT_CONT, - "BL_CONT", GPIO_ACTIVE_LOW), - GPIO_LOOKUP("gpio-pxa", SPITZ_GPIO_BACKLIGHT_ON, - "BL_ON", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.1", 6, "BL_CONT", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("sharp-scoop.1", 7, "BL_ON", GPIO_ACTIVE_HIGH), { }, }, }; @@ -531,10 +529,8 @@ static struct gpiod_lookup_table spitz_lcdcon_gpio_table = { static struct gpiod_lookup_table akita_lcdcon_gpio_table = { .dev_id = "spi2.1", .table = { - GPIO_LOOKUP("gpio-pxa", AKITA_GPIO_BACKLIGHT_CONT, - "BL_CONT", GPIO_ACTIVE_LOW), - GPIO_LOOKUP("gpio-pxa", AKITA_GPIO_BACKLIGHT_ON, - "BL_ON", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("i2c-max7310", 3, "BL_ON", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("i2c-max7310", 4, "BL_CONT", GPIO_ACTIVE_LOW), { }, }, }; @@ -941,12 +937,9 @@ static inline void spitz_i2c_init(void) {} static struct gpiod_lookup_table spitz_audio_gpio_table = { .dev_id = "spitz-audio", .table = { - GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_L - SPITZ_SCP_GPIO_BASE, - "mute-l", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_R - SPITZ_SCP_GPIO_BASE, - "mute-r", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("sharp-scoop.1", SPITZ_GPIO_MIC_BIAS - SPITZ_SCP2_GPIO_BASE, - "mic", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", 3, "mute-l", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", 4, "mute-r", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.1", 8, "mic", GPIO_ACTIVE_HIGH), { }, }, }; @@ -954,12 +947,9 @@ static struct gpiod_lookup_table spitz_audio_gpio_table = { static struct gpiod_lookup_table akita_audio_gpio_table = { .dev_id = "spitz-audio", .table = { - GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_L - SPITZ_SCP_GPIO_BASE, - "mute-l", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_R - SPITZ_SCP_GPIO_BASE, - "mute-r", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("i2c-max7310", AKITA_GPIO_MIC_BIAS - AKITA_IOEXP_GPIO_BASE, - "mic", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", 3, "mute-l", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", 4, "mute-r", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("i2c-max7310", 2, "mic", GPIO_ACTIVE_HIGH), { }, }, }; diff --git a/arch/arm/mach-sunxi/mc_smp.c b/arch/arm/mach-sunxi/mc_smp.c index cb63921232a6f8..277f6aa8e6c25f 100644 --- a/arch/arm/mach-sunxi/mc_smp.c +++ b/arch/arm/mach-sunxi/mc_smp.c @@ -803,16 +803,16 @@ static int __init sunxi_mc_smp_init(void) for (i = 0; i < ARRAY_SIZE(sunxi_mc_smp_data); i++) { ret = of_property_match_string(node, "enable-method", sunxi_mc_smp_data[i].enable_method); - if (!ret) + if (ret >= 0) break; } - is_a83t = sunxi_mc_smp_data[i].is_a83t; - of_node_put(node); - if (ret) + if (ret < 0) return -ENODEV; + is_a83t = sunxi_mc_smp_data[i].is_a83t; + if (!sunxi_mc_smp_cpu_table_init()) return -EINVAL; diff --git a/arch/arm/mach-versatile/platsmp-realview.c b/arch/arm/mach-versatile/platsmp-realview.c index 5d363385c80192..059d796b26bc8e 100644 --- a/arch/arm/mach-versatile/platsmp-realview.c +++ b/arch/arm/mach-versatile/platsmp-realview.c @@ -66,6 +66,7 @@ static void __init realview_smp_prepare_cpus(unsigned int max_cpus) return; } map = syscon_node_to_regmap(np); + of_node_put(np); if (IS_ERR(map)) { pr_err("PLATSMP: No syscon regmap\n"); return; diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index d19d140a10c7d5..0749cf8a66371b 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -296,6 +296,9 @@ void __sync_icache_dcache(pte_t pteval) return; folio = page_folio(pfn_to_page(pfn)); + if (folio_test_reserved(folio)) + return; + if (cache_is_vipt_aliasing()) mapping = folio_flush_mapping(folio); else diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile index 515ca33b854c1a..d761bd2e2f4072 100644 --- a/arch/arm/vdso/Makefile +++ b/arch/arm/vdso/Makefile @@ -63,28 +63,3 @@ quiet_cmd_vdsold_and_vdso_check = LD $@ quiet_cmd_vdsomunge = MUNGE $@ cmd_vdsomunge = $(objtree)/$(obj)/vdsomunge $< $@ - -# -# Install the unstripped copy of vdso.so.dbg. If our toolchain -# supports build-id, install .build-id links as well. -# -# Cribbed from arch/x86/vdso/Makefile. -# -quiet_cmd_vdso_install = INSTALL $< -define cmd_vdso_install - cp $< "$(MODLIB)/vdso/vdso.so"; \ - if readelf -n $< | grep -q 'Build ID'; then \ - buildid=`readelf -n $< |grep 'Build ID' |sed -e 's/^.*Build ID: \(.*\)$$/\1/'`; \ - first=`echo $$buildid | cut -b-2`; \ - last=`echo $$buildid | cut -b3-`; \ - mkdir -p "$(MODLIB)/vdso/.build-id/$$first"; \ - ln -sf "../../vdso.so" "$(MODLIB)/vdso/.build-id/$$first/$$last.debug"; \ - fi -endef - -$(MODLIB)/vdso: FORCE - @mkdir -p $(MODLIB)/vdso - -PHONY += vdso_install -vdso_install: $(obj)/vdso.so.dbg $(MODLIB)/vdso - $(call cmd,vdso_install) diff --git a/arch/arm/vfp/vfpinstr.h b/arch/arm/vfp/vfpinstr.h index 3c7938fd40aad6..32090b0fb250b8 100644 --- a/arch/arm/vfp/vfpinstr.h +++ b/arch/arm/vfp/vfpinstr.h @@ -64,33 +64,37 @@ #ifdef CONFIG_AS_VFP_VMRS_FPINST -#define fmrx(_vfp_) ({ \ - u32 __v; \ - asm(".fpu vfpv2\n" \ - "vmrs %0, " #_vfp_ \ - : "=r" (__v) : : "cc"); \ - __v; \ - }) - -#define fmxr(_vfp_,_var_) \ - asm(".fpu vfpv2\n" \ - "vmsr " #_vfp_ ", %0" \ - : : "r" (_var_) : "cc") +#define fmrx(_vfp_) ({ \ + u32 __v; \ + asm volatile (".fpu vfpv2\n" \ + "vmrs %0, " #_vfp_ \ + : "=r" (__v) : : "cc"); \ + __v; \ +}) + +#define fmxr(_vfp_, _var_) ({ \ + asm volatile (".fpu vfpv2\n" \ + "vmsr " #_vfp_ ", %0" \ + : : "r" (_var_) : "cc"); \ +}) #else #define vfpreg(_vfp_) #_vfp_ -#define fmrx(_vfp_) ({ \ - u32 __v; \ - asm("mrc p10, 7, %0, " vfpreg(_vfp_) ", cr0, 0 @ fmrx %0, " #_vfp_ \ - : "=r" (__v) : : "cc"); \ - __v; \ - }) - -#define fmxr(_vfp_,_var_) \ - asm("mcr p10, 7, %0, " vfpreg(_vfp_) ", cr0, 0 @ fmxr " #_vfp_ ", %0" \ - : : "r" (_var_) : "cc") +#define fmrx(_vfp_) ({ \ + u32 __v; \ + asm volatile ("mrc p10, 7, %0, " vfpreg(_vfp_) "," \ + "cr0, 0 @ fmrx %0, " #_vfp_ \ + : "=r" (__v) : : "cc"); \ + __v; \ +}) + +#define fmxr(_vfp_, _var_) ({ \ + asm volatile ("mcr p10, 7, %0, " vfpreg(_vfp_) "," \ + "cr0, 0 @ fmxr " #_vfp_ ", %0" \ + : : "r" (_var_) : "cc"); \ +}) #endif diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index c392e18f1e4317..a395b6c0aae2a9 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -164,9 +164,6 @@ static int xen_starting_cpu(unsigned int cpu) BUG_ON(err); per_cpu(xen_vcpu, cpu) = vcpup; - if (!xen_kernel_unmapped_at_usr()) - xen_setup_runstate_info(cpu); - after_register_vcpu_info: enable_percpu_irq(xen_events_irq, 0); return 0; @@ -487,7 +484,8 @@ static int __init xen_guest_init(void) * for secondary CPUs as they are brought up. * For uniformity we use VCPUOP_register_vcpu_info even on cpu0. */ - xen_vcpu_info = alloc_percpu(struct vcpu_info); + xen_vcpu_info = __alloc_percpu(sizeof(struct vcpu_info), + 1 << fls(sizeof(struct vcpu_info) - 1)); if (xen_vcpu_info == NULL) return -ENOMEM; @@ -523,9 +521,6 @@ static int __init xen_guest_init(void) return -EINVAL; } - if (!xen_kernel_unmapped_at_usr()) - xen_time_setup_guest(); - if (xen_initial_domain()) pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); @@ -535,7 +530,13 @@ static int __init xen_guest_init(void) } early_initcall(xen_guest_init); -static int __init xen_pm_init(void) +static int xen_starting_runstate_cpu(unsigned int cpu) +{ + xen_setup_runstate_info(cpu); + return 0; +} + +static int __init xen_late_init(void) { if (!xen_domain()) return -ENODEV; @@ -548,9 +549,16 @@ static int __init xen_pm_init(void) do_settimeofday64(&ts); } - return 0; + if (xen_kernel_unmapped_at_usr()) + return 0; + + xen_time_setup_guest(); + + return cpuhp_setup_state(CPUHP_AP_ARM_XEN_RUNSTATE_STARTING, + "arm/xen_runstate:starting", + xen_starting_runstate_cpu, NULL); } -late_initcall(xen_pm_init); +late_initcall(xen_late_init); /* empty stubs */ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 78f20e6327120e..eab866d6903347 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -191,12 +191,13 @@ config ARM64 select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_ARGS \ - if $(cc-option,-fpatchable-function-entry=2) + if (GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS || \ + CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS) select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS \ if DYNAMIC_FTRACE_WITH_ARGS && DYNAMIC_FTRACE_WITH_CALL_OPS select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \ if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG && \ - !CC_OPTIMIZE_FOR_SIZE) + (CC_IS_CLANG || !CC_OPTIMIZE_FOR_SIZE)) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_ARGS select HAVE_SAMPLE_FTRACE_DIRECT @@ -262,12 +263,10 @@ config CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS def_bool CC_IS_CLANG # https://github.com/ClangBuiltLinux/linux/issues/1507 depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600)) - select HAVE_DYNAMIC_FTRACE_WITH_ARGS config GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS def_bool CC_IS_GCC depends on $(cc-option,-fpatchable-function-entry=2) - select HAVE_DYNAMIC_FTRACE_WITH_ARGS config 64BIT def_bool y @@ -420,7 +419,7 @@ config AMPERE_ERRATUM_AC03_CPU_38 default y help This option adds an alternative code sequence to work around Ampere - erratum AC03_CPU_38 on AmpereOne. + errata AC03_CPU_38 and AC04_CPU_10 on AmpereOne. The affected design reports FEAT_HAFDBS as not implemented in ID_AA64MMFR1_EL1.HAFDBS, but (V)TCR_ELx.{HA,HD} are not RES0 @@ -1037,8 +1036,12 @@ config ARM64_ERRATUM_2645198 If unsure, say Y. +config ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD + bool + config ARM64_ERRATUM_2966298 bool "Cortex-A520: 2966298: workaround for speculatively executed unprivileged load" + select ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD default y help This option adds the workaround for ARM Cortex-A520 erratum 2966298. @@ -1050,6 +1053,60 @@ config ARM64_ERRATUM_2966298 If unsure, say Y. +config ARM64_ERRATUM_3117295 + bool "Cortex-A510: 3117295: workaround for speculatively executed unprivileged load" + select ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD + default y + help + This option adds the workaround for ARM Cortex-A510 erratum 3117295. + + On an affected Cortex-A510 core, a speculatively executed unprivileged + load might leak data from a privileged level via a cache side channel. + + Work around this problem by executing a TLBI before returning to EL0. + + If unsure, say Y. + +config ARM64_ERRATUM_3194386 + bool "Cortex-*/Neoverse-*: workaround for MSR SSBS not self-synchronizing" + default y + help + This option adds the workaround for the following errata: + + * ARM Cortex-A76 erratum 3324349 + * ARM Cortex-A77 erratum 3324348 + * ARM Cortex-A78 erratum 3324344 + * ARM Cortex-A78C erratum 3324346 + * ARM Cortex-A78C erratum 3324347 + * ARM Cortex-A710 erratam 3324338 + * ARM Cortex-A715 errartum 3456084 + * ARM Cortex-A720 erratum 3456091 + * ARM Cortex-A725 erratum 3456106 + * ARM Cortex-X1 erratum 3324344 + * ARM Cortex-X1C erratum 3324346 + * ARM Cortex-X2 erratum 3324338 + * ARM Cortex-X3 erratum 3324335 + * ARM Cortex-X4 erratum 3194386 + * ARM Cortex-X925 erratum 3324334 + * ARM Neoverse-N1 erratum 3324349 + * ARM Neoverse N2 erratum 3324339 + * ARM Neoverse-N3 erratum 3456111 + * ARM Neoverse-V1 erratum 3324341 + * ARM Neoverse V2 erratum 3324336 + * ARM Neoverse-V3 erratum 3312417 + + On affected cores "MSR SSBS, #0" instructions may not affect + subsequent speculative instructions, which may permit unexepected + speculative store bypassing. + + Work around this problem by placing a Speculation Barrier (SB) or + Instruction Synchronization Barrier (ISB) after kernel changes to + SSBS. The presence of the SSBS special-purpose register is hidden + from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such that userspace + will use the PR_SPEC_STORE_BYPASS prctl to change SSBS. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y @@ -1368,6 +1425,8 @@ choice config CPU_BIG_ENDIAN bool "Build big-endian kernel" depends on !LD_IS_LLD || LLD_VERSION >= 130000 + # https://github.com/llvm/llvm-project/commit/1379b150991f70a5782e9a143c2ba5308da1161c + depends on AS_IS_GNU || AS_VERSION >= 150000 help Say Y if you plan on running a kernel with a big-endian userspace. diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 2d49aea0ff67a8..9a2d3723cd0fa9 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -158,7 +158,7 @@ endif all: $(notdir $(KBUILD_IMAGE)) - +vmlinuz.efi: Image Image vmlinuz.efi: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ @@ -169,12 +169,6 @@ install: KBUILD_IMAGE := $(boot)/Image install zinstall: $(call cmd,install) -PHONY += vdso_install -vdso_install: - $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@ - $(if $(CONFIG_COMPAT_VDSO), \ - $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@) - archprepare: $(Q)$(MAKE) $(build)=arch/arm64/tools kapi ifeq ($(CONFIG_ARM64_ERRATUM_843419),y) @@ -205,6 +199,9 @@ ifdef CONFIG_COMPAT_VDSO endif endif +vdso-install-y += arch/arm64/kernel/vdso/vdso.so.dbg +vdso-install-$(CONFIG_COMPAT_VDSO) += arch/arm64/kernel/vdso32/vdso.so.dbg:vdso32.so + include $(srctree)/scripts/Makefile.defconf PHONY += virtconfig diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts index 9ec49ac2f6fd5d..381d58cea092d9 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts @@ -291,6 +291,8 @@ sw { }; &spdif { + pinctrl-names = "default"; + pinctrl-0 = <&spdif_tx_pin>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi index 4903d6358112de..855b7d43bc503a 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi @@ -166,6 +166,8 @@ &r_ir { }; &spdif { + pinctrl-names = "default"; + pinctrl-0 = <&spdif_tx_pin>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi index ca1d287a0a01d9..d11e5041bae9a4 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi @@ -406,6 +406,7 @@ spi1_cs_pin: spi1-cs-pin { function = "spi1"; }; + /omit-if-no-ref/ spdif_tx_pin: spdif-tx-pin { pins = "PH7"; function = "spdif"; @@ -655,10 +656,8 @@ spdif: spdif@5093000 { clocks = <&ccu CLK_BUS_SPDIF>, <&ccu CLK_SPDIF>; clock-names = "apb", "spdif"; resets = <&ccu RST_BUS_SPDIF>; - dmas = <&dma 2>; - dma-names = "tx"; - pinctrl-names = "default"; - pinctrl-0 = <&spdif_tx_pin>; + dmas = <&dma 2>, <&dma 2>; + dma-names = "rx", "tx"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi index 15290e6892fca4..fc7315b9440659 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi @@ -68,10 +68,7 @@ &ehci1 { &emac0 { pinctrl-names = "default"; pinctrl-0 = <&ext_rgmii_pins>; - phy-mode = "rgmii"; phy-handle = <&ext_rgmii_phy>; - allwinner,rx-delay-ps = <3100>; - allwinner,tx-delay-ps = <700>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts index d83852e72f0634..b5d713926a341a 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts @@ -13,6 +13,9 @@ / { }; &emac0 { + allwinner,rx-delay-ps = <3100>; + allwinner,tx-delay-ps = <700>; + phy-mode = "rgmii"; phy-supply = <®_dcdce>; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts b/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts index 00fe28caac939a..b3b1b8692125f9 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts @@ -13,6 +13,8 @@ / { }; &emac0 { + allwinner,tx-delay-ps = <700>; + phy-mode = "rgmii-rxid"; phy-supply = <®_dldo1>; }; diff --git a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi index dccbba6e7f98e4..dbf2dce8d1d68a 100644 --- a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi +++ b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi @@ -145,7 +145,6 @@ pci@fbc00000 { msix: msix@fbe00000 { compatible = "al,alpine-msix"; reg = <0x0 0xfbe00000 0x0 0x100000>; - interrupt-controller; msi-controller; al,msi-base-spi = <160>; al,msi-num-spis = <160>; diff --git a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi index 39481d7fd7d4da..3ea178acdddfe2 100644 --- a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi +++ b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi @@ -355,7 +355,6 @@ pcie@fbd00000 { msix: msix@fbe00000 { compatible = "al,alpine-msix"; reg = <0x0 0xfbe00000 0x0 0x100000>; - interrupt-controller; msi-controller; al,msi-base-spi = <336>; al,msi-num-spis = <959>; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index ff68b911b72971..0ff0d090548d0e 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -215,6 +215,11 @@ hdmi_tx: hdmi-tx@0 { #sound-dai-cells = <0>; status = "disabled"; + assigned-clocks = <&clkc CLKID_HDMI_SEL>, + <&clkc CLKID_HDMI>; + assigned-clock-parents = <&xtal>, <0>; + assigned-clock-rates = <0>, <24000000>; + /* VPU VENC Input */ hdmi_tx_venc_port: port@0 { reg = <0>; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12.dtsi index 6a1f4dcf64885f..7b655e07e80cf6 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12.dtsi @@ -367,6 +367,10 @@ ðmac { power-domains = <&pwrc PWRC_G12A_ETH_ID>; }; +&hdmi_tx { + power-domains = <&pwrc PWRC_G12A_VPU_ID>; +}; + &vpu { power-domains = <&pwrc PWRC_G12A_VPU_ID>; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi index 12ef6e81c8bd63..ed00e67e6923a0 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi @@ -311,10 +311,16 @@ &hdmi_tx { <&reset RESET_HDMI_SYSTEM_RESET>, <&reset RESET_HDMI_TX>; reset-names = "hdmitx_apb", "hdmitx", "hdmitx_phy"; - clocks = <&clkc CLKID_HDMI_PCLK>, - <&clkc CLKID_CLK81>, + clocks = <&clkc CLKID_HDMI>, + <&clkc CLKID_HDMI_PCLK>, <&clkc CLKID_GCLK_VENCI_INT0>; clock-names = "isfr", "iahb", "venci"; + power-domains = <&pwrc PWRC_GXBB_VPU_ID>; + + assigned-clocks = <&clkc CLKID_HDMI_SEL>, + <&clkc CLKID_HDMI>; + assigned-clock-parents = <&xtal>, <0>; + assigned-clock-rates = <0>, <24000000>; }; &sysctrl { diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index 17bcfa4702e170..f58d1790de1cb4 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -323,10 +323,16 @@ &hdmi_tx { <&reset RESET_HDMI_SYSTEM_RESET>, <&reset RESET_HDMI_TX>; reset-names = "hdmitx_apb", "hdmitx", "hdmitx_phy"; - clocks = <&clkc CLKID_HDMI_PCLK>, - <&clkc CLKID_CLK81>, + clocks = <&clkc CLKID_HDMI>, + <&clkc CLKID_HDMI_PCLK>, <&clkc CLKID_GCLK_VENCI_INT0>; clock-names = "isfr", "iahb", "venci"; + power-domains = <&pwrc PWRC_GXBB_VPU_ID>; + + assigned-clocks = <&clkc CLKID_HDMI_SEL>, + <&clkc CLKID_HDMI>; + assigned-clock-parents = <&xtal>, <0>; + assigned-clock-rates = <0>, <24000000>; }; &sysctrl { diff --git a/arch/arm64/boot/dts/amlogic/meson-s4-s805x2-aq222.dts b/arch/arm64/boot/dts/amlogic/meson-s4-s805x2-aq222.dts index 8ffbcb2b1ac594..bbd3c05cbd9089 100644 --- a/arch/arm64/boot/dts/amlogic/meson-s4-s805x2-aq222.dts +++ b/arch/arm64/boot/dts/amlogic/meson-s4-s805x2-aq222.dts @@ -15,7 +15,7 @@ / { #size-cells = <2>; aliases { - serial0 = &uart_B; + serial0 = &uart_b; }; memory@0 { @@ -25,6 +25,6 @@ memory@0 { }; -&uart_B { +&uart_b { status = "okay"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi index f24460186d3d82..a781eabe21f04a 100644 --- a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi @@ -61,10 +61,15 @@ xtal: xtal-clk { #clock-cells = <0>; }; - pwrc: power-controller { - compatible = "amlogic,meson-s4-pwrc"; - #power-domain-cells = <1>; - status = "okay"; + firmware { + sm: secure-monitor { + compatible = "amlogic,meson-gxbb-sm"; + + pwrc: power-controller { + compatible = "amlogic,meson-s4-pwrc"; + #power-domain-cells = <1>; + }; + }; }; soc { @@ -118,14 +123,14 @@ gpio_intc: interrupt-controller@4080 { <10 11 12 13 14 15 16 17 18 19 20 21>; }; - uart_B: serial@7a000 { + uart_b: serial@7a000 { compatible = "amlogic,meson-s4-uart", "amlogic,meson-ao-uart"; reg = <0x0 0x7a000 0x0 0x18>; interrupts = ; - status = "disabled"; clocks = <&xtal>, <&xtal>, <&xtal>; clock-names = "xtal", "pclk", "baud"; + status = "disabled"; }; reset: reset-controller@2000 { diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi index 643f94d9d08e10..13e742ba00bea0 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi @@ -339,7 +339,7 @@ tdmin_lb: audio-controller@3c0 { }; spdifin: audio-controller@400 { - compatible = "amlogic,g12a-spdifin", + compatible = "amlogic,sm1-spdifin", "amlogic,axg-spdifin"; reg = <0x0 0x400 0x0 0x30>; #sound-dai-cells = <0>; @@ -353,7 +353,7 @@ spdifin: audio-controller@400 { }; spdifout_a: audio-controller@480 { - compatible = "amlogic,g12a-spdifout", + compatible = "amlogic,sm1-spdifout", "amlogic,axg-spdifout"; reg = <0x0 0x480 0x0 0x50>; #sound-dai-cells = <0>; @@ -518,6 +518,10 @@ &gpio_intc { "amlogic,meson-gpio-intc"; }; +&hdmi_tx { + power-domains = <&pwrc PWRC_SM1_VPU_ID>; +}; + &pcie { power-domains = <&pwrc PWRC_SM1_PCIE_ID>; }; diff --git a/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi b/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi index 2f124b027bbf0a..aadfa0ae052526 100644 --- a/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi @@ -227,9 +227,6 @@ ethernet-switch@0 { brcm,num-gphy = <5>; brcm,num-rgmii-ports = <2>; - #address-cells = <1>; - #size-cells = <0>; - ports: ports { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi index 9dcd25ec2c0418..896d1f33b5b617 100644 --- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi +++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi @@ -586,6 +586,7 @@ gpio_g: gpio@660a0000 { #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; interrupts = ; }; diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi index f049687d6b96d2..d8516ec0dae745 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi @@ -450,6 +450,7 @@ gpio_hsls: gpio@d0000 { #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; interrupts = ; gpio-ranges = <&pinmux 0 0 16>, <&pinmux 16 71 2>, diff --git a/arch/arm64/boot/dts/exynos/exynos7885-jackpotlte.dts b/arch/arm64/boot/dts/exynos/exynos7885-jackpotlte.dts index 47a389d9ff7d71..9d74fa6bfed9fb 100644 --- a/arch/arm64/boot/dts/exynos/exynos7885-jackpotlte.dts +++ b/arch/arm64/boot/dts/exynos/exynos7885-jackpotlte.dts @@ -32,7 +32,7 @@ memory@80000000 { device_type = "memory"; reg = <0x0 0x80000000 0x3da00000>, <0x0 0xc0000000 0x40000000>, - <0x8 0x80000000 0x40000000>; + <0x8 0x80000000 0x80000000>; }; gpio-keys { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi index d2f5345d056007..717288bbdb8b63 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi @@ -1186,26 +1186,34 @@ sata1: sata@3210000 { dma-coherent; }; - usb0: usb@3100000 { - status = "disabled"; - compatible = "snps,dwc3"; - reg = <0x0 0x3100000 0x0 0x10000>; - interrupts = <0 80 0x4>; /* Level high type */ - dr_mode = "host"; - snps,quirk-frame-length-adjustment = <0x20>; - snps,dis_rxdet_inp3_quirk; - snps,incr-burst-type-adjustment = <1>, <4>, <8>, <16>; - }; + bus: bus { + #address-cells = <2>; + #size-cells = <2>; + compatible = "simple-bus"; + ranges; + dma-ranges = <0x0 0x0 0x0 0x0 0x100 0x00000000>; + + usb0: usb@3100000 { + compatible = "snps,dwc3"; + reg = <0x0 0x3100000 0x0 0x10000>; + interrupts = <0 80 0x4>; /* Level high type */ + dr_mode = "host"; + snps,quirk-frame-length-adjustment = <0x20>; + snps,dis_rxdet_inp3_quirk; + snps,incr-burst-type-adjustment = <1>, <4>, <8>, <16>; + status = "disabled"; + }; - usb1: usb@3110000 { - status = "disabled"; - compatible = "snps,dwc3"; - reg = <0x0 0x3110000 0x0 0x10000>; - interrupts = <0 81 0x4>; /* Level high type */ - dr_mode = "host"; - snps,quirk-frame-length-adjustment = <0x20>; - snps,dis_rxdet_inp3_quirk; - snps,incr-burst-type-adjustment = <1>, <4>, <8>, <16>; + usb1: usb@3110000 { + compatible = "snps,dwc3"; + reg = <0x0 0x3110000 0x0 0x10000>; + interrupts = <0 81 0x4>; /* Level high type */ + dr_mode = "host"; + snps,quirk-frame-length-adjustment = <0x20>; + snps,dis_rxdet_inp3_quirk; + snps,incr-burst-type-adjustment = <1>, <4>, <8>, <16>; + status = "disabled"; + }; }; ccn@4000000 { diff --git a/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi b/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi index 9b1b522517f8ef..0878a15acc1ba5 100644 --- a/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi @@ -82,12 +82,9 @@ reg_module_wifi: regulator-module-wifi { pinctrl-0 = <&pinctrl_wifi_pdn>; gpio = <&lsio_gpio1 28 GPIO_ACTIVE_HIGH>; enable-active-high; + regulator-always-on; regulator-name = "wifi_pwrdn_fake_regulator"; regulator-settling-time-us = <100>; - - regulator-state-mem { - regulator-off-in-suspend; - }; }; reg_pcie_switch: regulator-pcie-switch { diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi index fc1a5d34382b7e..49298cd9eb0da0 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi @@ -41,7 +41,7 @@ usbotg1: usb@5b0d0000 { interrupts = ; fsl,usbphy = <&usbphy1>; fsl,usbmisc = <&usbmisc1 0>; - clocks = <&usb2_lpcg 0>; + clocks = <&usb2_lpcg IMX_LPCG_CLK_6>; ahb-burst-config = <0x0>; tx-burst-size-dword = <0x10>; rx-burst-size-dword = <0x10>; @@ -58,7 +58,7 @@ usbmisc1: usbmisc@5b0d0200 { usbphy1: usbphy@5b100000 { compatible = "fsl,imx7ulp-usbphy"; reg = <0x5b100000 0x1000>; - clocks = <&usb2_lpcg 1>; + clocks = <&usb2_lpcg IMX_LPCG_CLK_7>; power-domains = <&pd IMX_SC_R_USB_0_PHY>; status = "disabled"; }; @@ -67,8 +67,8 @@ usdhc1: mmc@5b010000 { interrupts = ; reg = <0x5b010000 0x10000>; clocks = <&sdhc0_lpcg IMX_LPCG_CLK_4>, - <&sdhc0_lpcg IMX_LPCG_CLK_0>, - <&sdhc0_lpcg IMX_LPCG_CLK_5>; + <&sdhc0_lpcg IMX_LPCG_CLK_5>, + <&sdhc0_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_0>; status = "disabled"; @@ -78,8 +78,8 @@ usdhc2: mmc@5b020000 { interrupts = ; reg = <0x5b020000 0x10000>; clocks = <&sdhc1_lpcg IMX_LPCG_CLK_4>, - <&sdhc1_lpcg IMX_LPCG_CLK_0>, - <&sdhc1_lpcg IMX_LPCG_CLK_5>; + <&sdhc1_lpcg IMX_LPCG_CLK_5>, + <&sdhc1_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_1>; fsl,tuning-start-tap = <20>; @@ -91,8 +91,8 @@ usdhc3: mmc@5b030000 { interrupts = ; reg = <0x5b030000 0x10000>; clocks = <&sdhc2_lpcg IMX_LPCG_CLK_4>, - <&sdhc2_lpcg IMX_LPCG_CLK_0>, - <&sdhc2_lpcg IMX_LPCG_CLK_5>; + <&sdhc2_lpcg IMX_LPCG_CLK_5>, + <&sdhc2_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_2>; status = "disabled"; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi index adb98a72bdfd91..89857e14c46140 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi @@ -27,8 +27,8 @@ lpspi0: spi@5a000000 { #size-cells = <0>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&spi0_lpcg 0>, - <&spi0_lpcg 1>; + clocks = <&spi0_lpcg IMX_LPCG_CLK_0>, + <&spi0_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_SPI_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <60000000>; @@ -43,8 +43,8 @@ lpspi1: spi@5a010000 { #size-cells = <0>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&spi1_lpcg 0>, - <&spi1_lpcg 1>; + clocks = <&spi1_lpcg IMX_LPCG_CLK_0>, + <&spi1_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_SPI_1 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <60000000>; @@ -59,8 +59,8 @@ lpspi2: spi@5a020000 { #size-cells = <0>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&spi2_lpcg 0>, - <&spi2_lpcg 1>; + clocks = <&spi2_lpcg IMX_LPCG_CLK_0>, + <&spi2_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_SPI_2 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <60000000>; @@ -75,8 +75,8 @@ lpspi3: spi@5a030000 { #size-cells = <0>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&spi3_lpcg 0>, - <&spi3_lpcg 1>; + clocks = <&spi3_lpcg IMX_LPCG_CLK_0>, + <&spi3_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_SPI_3 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <60000000>; @@ -282,8 +282,8 @@ adc0: adc@5a880000 { reg = <0x5a880000 0x10000>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&adc0_lpcg 0>, - <&adc0_lpcg 1>; + clocks = <&adc0_lpcg IMX_LPCG_CLK_0>, + <&adc0_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_ADC_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; @@ -297,8 +297,8 @@ adc1: adc@5a890000 { reg = <0x5a890000 0x10000>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&adc1_lpcg 0>, - <&adc1_lpcg 1>; + clocks = <&adc1_lpcg IMX_LPCG_CLK_0>, + <&adc1_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_ADC_1 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; @@ -311,8 +311,8 @@ flexcan1: can@5a8d0000 { reg = <0x5a8d0000 0x10000>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&can0_lpcg 1>, - <&can0_lpcg 0>; + clocks = <&can0_lpcg IMX_LPCG_CLK_4>, + <&can0_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "per"; assigned-clocks = <&clk IMX_SC_R_CAN_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <40000000>; @@ -332,8 +332,8 @@ flexcan2: can@5a8e0000 { * CAN1 shares CAN0's clock and to enable CAN0's clock it * has to be powered on. */ - clocks = <&can0_lpcg 1>, - <&can0_lpcg 0>; + clocks = <&can0_lpcg IMX_LPCG_CLK_4>, + <&can0_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "per"; assigned-clocks = <&clk IMX_SC_R_CAN_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <40000000>; @@ -353,8 +353,8 @@ flexcan3: can@5a8f0000 { * CAN2 shares CAN0's clock and to enable CAN0's clock it * has to be powered on. */ - clocks = <&can0_lpcg 1>, - <&can0_lpcg 0>; + clocks = <&can0_lpcg IMX_LPCG_CLK_4>, + <&can0_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "per"; assigned-clocks = <&clk IMX_SC_R_CAN_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <40000000>; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi index ea8c93757521b3..c66449798efce1 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi @@ -32,11 +32,12 @@ lsio_pwm0: pwm@5d000000 { compatible = "fsl,imx27-pwm"; reg = <0x5d000000 0x10000>; clock-names = "ipg", "per"; - clocks = <&pwm0_lpcg 4>, - <&pwm0_lpcg 1>; + clocks = <&pwm0_lpcg IMX_LPCG_CLK_6>, + <&pwm0_lpcg IMX_LPCG_CLK_1>; assigned-clocks = <&clk IMX_SC_R_PWM_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; - #pwm-cells = <2>; + #pwm-cells = <3>; + interrupts = ; status = "disabled"; }; @@ -44,11 +45,12 @@ lsio_pwm1: pwm@5d010000 { compatible = "fsl,imx27-pwm"; reg = <0x5d010000 0x10000>; clock-names = "ipg", "per"; - clocks = <&pwm1_lpcg 4>, - <&pwm1_lpcg 1>; + clocks = <&pwm1_lpcg IMX_LPCG_CLK_6>, + <&pwm1_lpcg IMX_LPCG_CLK_1>; assigned-clocks = <&clk IMX_SC_R_PWM_1 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; - #pwm-cells = <2>; + #pwm-cells = <3>; + interrupts = ; status = "disabled"; }; @@ -56,11 +58,12 @@ lsio_pwm2: pwm@5d020000 { compatible = "fsl,imx27-pwm"; reg = <0x5d020000 0x10000>; clock-names = "ipg", "per"; - clocks = <&pwm2_lpcg 4>, - <&pwm2_lpcg 1>; + clocks = <&pwm2_lpcg IMX_LPCG_CLK_6>, + <&pwm2_lpcg IMX_LPCG_CLK_1>; assigned-clocks = <&clk IMX_SC_R_PWM_2 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; - #pwm-cells = <2>; + #pwm-cells = <3>; + interrupts = ; status = "disabled"; }; @@ -68,11 +71,12 @@ lsio_pwm3: pwm@5d030000 { compatible = "fsl,imx27-pwm"; reg = <0x5d030000 0x10000>; clock-names = "ipg", "per"; - clocks = <&pwm3_lpcg 4>, - <&pwm3_lpcg 1>; + clocks = <&pwm3_lpcg IMX_LPCG_CLK_6>, + <&pwm3_lpcg IMX_LPCG_CLK_1>; assigned-clocks = <&clk IMX_SC_R_PWM_3 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; - #pwm-cells = <2>; + #pwm-cells = <3>; + interrupts = ; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts index 8b16bd68576c0b..d9fa0deea7002e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts @@ -294,8 +294,8 @@ MX8MM_IOMUXC_SAI3_MCLK_GPIO5_IO2 0x19 pinctrl_i2c4: i2c4grp { fsl,pins = < - MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL 0x400001c3 - MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA 0x400001c3 + MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL 0x40000083 + MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA 0x40000083 >; }; @@ -313,19 +313,19 @@ MX8MM_IOMUXC_SAI5_MCLK_GPIO3_IO25 0x19 pinctrl_uart1: uart1grp { fsl,pins = < - MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX 0x140 - MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX 0x140 - MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B 0x140 - MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B 0x140 + MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX 0x0 + MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX 0x0 + MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B 0x0 + MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B 0x0 >; }; pinctrl_uart2: uart2grp { fsl,pins = < - MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX 0x140 - MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX 0x140 - MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B 0x140 - MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B 0x140 + MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX 0x0 + MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX 0x0 + MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B 0x0 + MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B 0x0 >; }; @@ -337,40 +337,40 @@ MX8MM_IOMUXC_NAND_CE1_B_GPIO3_IO2 0x19 pinctrl_usdhc2: usdhc2grp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x190 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x90 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d0 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d0 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d0 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d0 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d0 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x194 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x94 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d4 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d4 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d4 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d4 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d4 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x196 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x96 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d6 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d6 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d6 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d6 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d6 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts index dcec57c20399ed..aab8e24216501e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts @@ -279,8 +279,8 @@ MX8MM_IOMUXC_SAI3_MCLK_GPIO5_IO2 0x19 pinctrl_i2c4: i2c4grp { fsl,pins = < - MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL 0x400001c3 - MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA 0x400001c3 + MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL 0x40000083 + MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA 0x40000083 >; }; @@ -292,19 +292,19 @@ MX8MM_IOMUXC_SPDIF_RX_PWM2_OUT 0x19 pinctrl_uart1: uart1grp { fsl,pins = < - MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX 0x140 - MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX 0x140 - MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B 0x140 - MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B 0x140 + MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX 0x0 + MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX 0x0 + MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B 0x0 + MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B 0x0 >; }; pinctrl_uart2: uart2grp { fsl,pins = < - MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX 0x140 - MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX 0x140 - MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B 0x140 - MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B 0x140 + MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX 0x0 + MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX 0x0 + MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B 0x0 + MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B 0x0 >; }; @@ -316,40 +316,40 @@ MX8MM_IOMUXC_NAND_CE1_B_GPIO3_IO2 0x19 pinctrl_usdhc2: usdhc2grp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x190 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x90 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d0 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d0 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d0 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d0 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d0 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x194 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x94 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d4 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d4 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d4 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d4 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d4 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x196 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x96 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d6 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d6 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d6 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d6 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d6 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi index 6e75ab879bf59c..60abcb636cedf3 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi @@ -210,7 +210,7 @@ rv3028: rtc@52 { reg = <0x52>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_rtc>; - interrupts-extended = <&gpio4 1 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&gpio4 1 IRQ_TYPE_LEVEL_LOW>; trickle-diode-disable; }; }; @@ -252,8 +252,8 @@ MX8MM_IOMUXC_ECSPI1_SS0_GPIO5_IO9 0x19 pinctrl_i2c1: i2c1grp { fsl,pins = < - MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL 0x400001c3 - MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA 0x400001c3 + MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL 0x40000083 + MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA 0x40000083 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi index 1f8326613ee9e3..2076148e08627a 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi @@ -237,8 +237,8 @@ MX8MM_IOMUXC_ECSPI1_SS0_GPIO5_IO9 0x19 pinctrl_i2c1: i2c1grp { fsl,pins = < - MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL 0x400001c3 - MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA 0x400001c3 + MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL 0x40000083 + MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA 0x40000083 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi index 0ce60ad9c7d50f..26d4afdbca6f40 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi @@ -47,17 +47,6 @@ pps { gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; status = "okay"; }; - - reg_usb_otg1_vbus: regulator-usb-otg1 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_reg_usb1_en>; - compatible = "regulator-fixed"; - regulator-name = "usb_otg1_vbus"; - gpio = <&gpio1 10 GPIO_ACTIVE_HIGH>; - enable-active-high; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - }; }; /* off-board header */ @@ -145,9 +134,10 @@ &uart3 { }; &usbotg1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usbotg1>; dr_mode = "otg"; over-current-active-low; - vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; @@ -205,14 +195,6 @@ MX8MM_IOMUXC_GPIO1_IO15_GPIO1_IO15 0x41 >; }; - pinctrl_reg_usb1_en: regusb1grp { - fsl,pins = < - MX8MM_IOMUXC_GPIO1_IO10_GPIO1_IO10 0x41 - MX8MM_IOMUXC_GPIO1_IO12_GPIO1_IO12 0x141 - MX8MM_IOMUXC_GPIO1_IO13_USB1_OTG_OC 0x41 - >; - }; - pinctrl_spi2: spi2grp { fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 @@ -235,4 +217,11 @@ MX8MM_IOMUXC_UART3_RXD_UART3_DCE_RX 0x140 MX8MM_IOMUXC_UART3_TXD_UART3_DCE_TX 0x140 >; }; + + pinctrl_usbotg1: usbotg1grp { + fsl,pins = < + MX8MM_IOMUXC_GPIO1_IO12_GPIO1_IO12 0x141 + MX8MM_IOMUXC_GPIO1_IO13_USB1_OTG_OC 0x41 + >; + }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index 6f0811587142d2..14d20a33af8e15 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -929,7 +929,7 @@ pinctrl_gpio8: gpio8grp { /* Verdin GPIO_9_DSI (pulled-up as active-low) */ pinctrl_gpio_9_dsi: gpio9dsigrp { fsl,pins = - ; /* SODIMM 17 */ + ; /* SODIMM 17 */ }; /* Verdin GPIO_10_DSI (pulled-up as active-low) */ diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index 236fe44f779df3..54faf83cb436e5 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -399,6 +399,7 @@ micfil: audio-controller@30080000 { "pll8k", "pll11k", "clkext3"; dmas = <&sdma2 24 25 0x80000000>; dma-names = "rx"; + #sound-dai-cells = <0>; status = "disabled"; }; @@ -1407,7 +1408,7 @@ gpu_3d: gpu@38000000 { assigned-clocks = <&clk IMX8MM_CLK_GPU3D_CORE>, <&clk IMX8MM_GPU_PLL_OUT>; assigned-clock-parents = <&clk IMX8MM_GPU_PLL_OUT>; - assigned-clock-rates = <0>, <1000000000>; + assigned-clock-rates = <0>, <800000000>; power-domains = <&pgc_gpu>; }; @@ -1422,7 +1423,7 @@ gpu_2d: gpu@38008000 { assigned-clocks = <&clk IMX8MM_CLK_GPU2D_CORE>, <&clk IMX8MM_GPU_PLL_OUT>; assigned-clock-parents = <&clk IMX8MM_GPU_PLL_OUT>; - assigned-clock-rates = <0>, <1000000000>; + assigned-clock-rates = <0>, <800000000>; power-domains = <&pgc_gpu>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index aa38dd6dc9ba54..1bb1d0c1bae4de 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -371,6 +371,7 @@ micfil: audio-controller@30080000 { "pll8k", "pll11k", "clkext3"; dmas = <&sdma2 24 25 0x80000000>; dma-names = "rx"; + #sound-dai-cells = <0>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts index acd265d8b58ed9..e094f409028ddb 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts @@ -163,13 +163,12 @@ sound-wm8962 { simple-audio-card,cpu { sound-dai = <&sai3>; + frame-master; + bitclock-master; }; simple-audio-card,codec { sound-dai = <&wm8962>; - clocks = <&clk IMX8MP_CLK_IPP_DO_CLKO1>; - frame-master; - bitclock-master; }; }; }; @@ -381,10 +380,9 @@ &pcie_phy { &sai3 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_sai3>; - assigned-clocks = <&clk IMX8MP_CLK_SAI3>, - <&clk IMX8MP_AUDIO_PLL2> ; - assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>; - assigned-clock-rates = <12288000>, <361267200>; + assigned-clocks = <&clk IMX8MP_CLK_SAI3>; + assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL1_OUT>; + assigned-clock-rates = <12288000>; fsl,sai-mclk-direction-output; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts index 13674dc64be9d3..cd44bf83745cae 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts @@ -121,7 +121,7 @@ &ecspi1 { flash@0 { /* W25Q128JVEI */ compatible = "jedec,spi-nor"; reg = <0>; - spi-max-frequency = <100000000>; /* Up to 133 MHz */ + spi-max-frequency = <40000000>; spi-tx-bus-width = <1>; spi-rx-bus-width = <1>; }; @@ -484,7 +484,7 @@ &uart3 { /* A53 Debug */ &uart4 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_uart4>; - status = "okay"; + status = "disabled"; }; &usb3_phy0 { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-debix-model-a.dts b/arch/arm64/boot/dts/freescale/imx8mp-debix-model-a.dts index 28db9349ed62c4..267ceffc02d840 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-debix-model-a.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-debix-model-a.dts @@ -284,7 +284,6 @@ &usb_dwc3_1 { usb_hub_2_x: hub@1 { compatible = "usbbda,5411"; reg = <1>; - reset-gpios = <&gpio4 25 GPIO_ACTIVE_LOW>; vdd-supply = <®_usb_hub>; peer-hub = <&usb_hub_3_x>; }; @@ -293,7 +292,6 @@ usb_hub_2_x: hub@1 { usb_hub_3_x: hub@2 { compatible = "usbbda,411"; reg = <2>; - reset-gpios = <&gpio4 25 GPIO_ACTIVE_LOW>; vdd-supply = <®_usb_hub>; peer-hub = <&usb_hub_2_x>; }; @@ -443,7 +441,6 @@ MX8MP_IOMUXC_UART4_TXD__UART4_DCE_TX 0x49 pinctrl_usb1: usb1grp { fsl,pins = < MX8MP_IOMUXC_GPIO1_IO14__USB2_OTG_PWR 0x10 - MX8MP_IOMUXC_SAI2_TXC__GPIO4_IO25 0x19 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi index cb1953d14aa907..eae39c1cb98568 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi @@ -251,8 +251,8 @@ tc_bridge: bridge@f { <&clk IMX8MP_CLK_CLKOUT2>, <&clk IMX8MP_AUDIO_PLL2_OUT>; assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>; - assigned-clock-rates = <13000000>, <13000000>, <156000000>; - reset-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; + assigned-clock-rates = <13000000>, <13000000>, <208000000>; + reset-gpios = <&gpio4 1 GPIO_ACTIVE_HIGH>; status = "disabled"; ports { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts index cc9d468b43ab8d..92f8cc05fe9da1 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts @@ -23,7 +23,7 @@ hdmi-connector { port { hdmi_connector_in: endpoint { - remote-endpoint = <&adv7533_out>; + remote-endpoint = <&adv7535_out>; }; }; }; @@ -107,6 +107,13 @@ reg_usdhc2_vmmc: regulator-usdhc2 { enable-active-high; }; + reg_vext_3v3: regulator-vext-3v3 { + compatible = "regulator-fixed"; + regulator-name = "VEXT_3V3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + sound { compatible = "simple-audio-card"; simple-audio-card,name = "wm8960-audio"; @@ -342,7 +349,7 @@ BUCK4 { regulator-always-on; }; - BUCK5 { + reg_buck5: BUCK5 { regulator-name = "BUCK5"; regulator-min-microvolt = <1650000>; regulator-max-microvolt = <1950000>; @@ -393,14 +400,16 @@ &i2c2 { hdmi@3d { compatible = "adi,adv7535"; - reg = <0x3d>, <0x3c>, <0x3e>, <0x3f>; - reg-names = "main", "cec", "edid", "packet"; + reg = <0x3d>; + interrupt-parent = <&gpio1>; + interrupts = <9 IRQ_TYPE_EDGE_FALLING>; adi,dsi-lanes = <4>; - adi,input-depth = <8>; - adi,input-colorspace = "rgb"; - adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; + avdd-supply = <®_buck5>; + dvdd-supply = <®_buck5>; + pvdd-supply = <®_buck5>; + a2vdd-supply = <®_buck5>; + v3p3-supply = <®_vext_3v3>; + v1p2-supply = <®_buck5>; ports { #address-cells = <1>; @@ -409,7 +418,7 @@ ports { port@0 { reg = <0>; - adv7533_in: endpoint { + adv7535_in: endpoint { remote-endpoint = <&dsi_out>; }; }; @@ -417,7 +426,7 @@ adv7533_in: endpoint { port@1 { reg = <1>; - adv7533_out: endpoint { + adv7535_out: endpoint { remote-endpoint = <&hdmi_connector_in>; }; }; @@ -502,7 +511,7 @@ port@1 { reg = <1>; dsi_out: endpoint { - remote-endpoint = <&adv7533_in>; + remote-endpoint = <&adv7535_in>; data-lanes = <1 2 3 4>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts index 4240e20d38ac32..258e90cc16ff3a 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts @@ -168,6 +168,13 @@ reg_vcc_12v0: regulator-12v0 { enable-active-high; }; + reg_vcc_1v8: regulator-1v8 { + compatible = "regulator-fixed"; + regulator-name = "VCC_1V8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + reg_vcc_3v3: regulator-3v3 { compatible = "regulator-fixed"; regulator-name = "VCC_3V3"; @@ -464,7 +471,7 @@ tlv320aic3x04: audio-codec@18 { clock-names = "mclk"; clocks = <&audio_blk_ctrl IMX8MP_CLK_AUDIOMIX_SAI3_MCLK1>; reset-gpios = <&gpio4 29 GPIO_ACTIVE_LOW>; - iov-supply = <®_vcc_3v3>; + iov-supply = <®_vcc_1v8>; ldoin-supply = <®_vcc_3v3>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi index 68c62def4c06e1..d27bfba1b4b8c4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi @@ -161,7 +161,7 @@ &uart3 { bluetooth { compatible = "brcm,bcm4330-bt"; - shutdown-gpios = <&gpio4 16 GPIO_ACTIVE_HIGH>; + shutdown-gpios = <&gpio1 3 GPIO_ACTIVE_HIGH>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index 83d907294fbc73..d1488ebfef3f02 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -785,6 +785,23 @@ pgc_usb2_phy: power-domain@3 { reg = ; }; + pgc_mlmix: power-domain@4 { + #power-domain-cells = <0>; + reg = ; + clocks = <&clk IMX8MP_CLK_ML_AXI>, + <&clk IMX8MP_CLK_ML_AHB>, + <&clk IMX8MP_CLK_NPU_ROOT>; + assigned-clocks = <&clk IMX8MP_CLK_ML_CORE>, + <&clk IMX8MP_CLK_ML_AXI>, + <&clk IMX8MP_CLK_ML_AHB>; + assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>, + <&clk IMX8MP_SYS_PLL1_800M>, + <&clk IMX8MP_SYS_PLL1_800M>; + assigned-clock-rates = <800000000>, + <800000000>, + <300000000>; + }; + pgc_audio: power-domain@5 { #power-domain-cells = <0>; reg = ; @@ -817,6 +834,12 @@ pgc_gpumix: power-domain@7 { assigned-clock-rates = <800000000>, <400000000>; }; + pgc_vpumix: power-domain@8 { + #power-domain-cells = <0>; + reg = ; + clocks = <&clk IMX8MP_CLK_VPU_ROOT>; + }; + pgc_gpu3d: power-domain@9 { #power-domain-cells = <0>; reg = ; @@ -832,60 +855,64 @@ pgc_mediamix: power-domain@10 { <&clk IMX8MP_CLK_MEDIA_APB_ROOT>; }; - pgc_mipi_phy2: power-domain@16 { + pgc_vpu_g1: power-domain@11 { #power-domain-cells = <0>; - reg = ; + power-domains = <&pgc_vpumix>; + reg = ; + clocks = <&clk IMX8MP_CLK_VPU_G1_ROOT>; }; - pgc_hsiomix: power-domain@17 { + pgc_vpu_g2: power-domain@12 { #power-domain-cells = <0>; - reg = ; - clocks = <&clk IMX8MP_CLK_HSIO_AXI>, - <&clk IMX8MP_CLK_HSIO_ROOT>; - assigned-clocks = <&clk IMX8MP_CLK_HSIO_AXI>; - assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_500M>; - assigned-clock-rates = <500000000>; + power-domains = <&pgc_vpumix>; + reg = ; + clocks = <&clk IMX8MP_CLK_VPU_G2_ROOT>; + }; - pgc_ispdwp: power-domain@18 { + pgc_vpu_vc8000e: power-domain@13 { #power-domain-cells = <0>; - reg = ; - clocks = <&clk IMX8MP_CLK_MEDIA_ISP_ROOT>; + power-domains = <&pgc_vpumix>; + reg = ; + clocks = <&clk IMX8MP_CLK_VPU_VC8KE_ROOT>; }; - pgc_vpumix: power-domain@19 { + pgc_hdmimix: power-domain@14 { #power-domain-cells = <0>; - reg = ; - clocks = <&clk IMX8MP_CLK_VPU_ROOT>; + reg = ; + clocks = <&clk IMX8MP_CLK_HDMI_ROOT>, + <&clk IMX8MP_CLK_HDMI_APB>; + assigned-clocks = <&clk IMX8MP_CLK_HDMI_AXI>, + <&clk IMX8MP_CLK_HDMI_APB>; + assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_500M>, + <&clk IMX8MP_SYS_PLL1_133M>; + assigned-clock-rates = <500000000>, <133000000>; }; - pgc_vpu_g1: power-domain@20 { + pgc_hdmi_phy: power-domain@15 { #power-domain-cells = <0>; - power-domains = <&pgc_vpumix>; - reg = ; - clocks = <&clk IMX8MP_CLK_VPU_G1_ROOT>; + reg = ; }; - pgc_vpu_g2: power-domain@21 { + pgc_mipi_phy2: power-domain@16 { #power-domain-cells = <0>; - power-domains = <&pgc_vpumix>; - reg = ; - clocks = <&clk IMX8MP_CLK_VPU_G2_ROOT>; + reg = ; }; - pgc_vpu_vc8000e: power-domain@22 { + pgc_hsiomix: power-domain@17 { #power-domain-cells = <0>; - power-domains = <&pgc_vpumix>; - reg = ; - clocks = <&clk IMX8MP_CLK_VPU_VC8KE_ROOT>; + reg = ; + clocks = <&clk IMX8MP_CLK_HSIO_AXI>, + <&clk IMX8MP_CLK_HSIO_ROOT>; + assigned-clocks = <&clk IMX8MP_CLK_HSIO_AXI>; + assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_500M>; + assigned-clock-rates = <500000000>; }; - pgc_mlmix: power-domain@24 { + pgc_ispdwp: power-domain@18 { #power-domain-cells = <0>; - reg = ; - clocks = <&clk IMX8MP_CLK_ML_AXI>, - <&clk IMX8MP_CLK_ML_AHB>, - <&clk IMX8MP_CLK_NPU_ROOT>; + reg = ; + clocks = <&clk IMX8MP_CLK_MEDIA_ISP_ROOT>; }; }; }; @@ -1831,6 +1858,27 @@ hsio_blk_ctrl: blk-ctrl@32f10000 { #power-domain-cells = <1>; #clock-cells = <0>; }; + + hdmi_blk_ctrl: blk-ctrl@32fc0000 { + compatible = "fsl,imx8mp-hdmi-blk-ctrl", "syscon"; + reg = <0x32fc0000 0x1000>; + clocks = <&clk IMX8MP_CLK_HDMI_APB>, + <&clk IMX8MP_CLK_HDMI_ROOT>, + <&clk IMX8MP_CLK_HDMI_REF_266M>, + <&clk IMX8MP_CLK_HDMI_24M>, + <&clk IMX8MP_CLK_HDMI_FDCC_TST>; + clock-names = "apb", "axi", "ref_266m", "ref_24m", "fdcc"; + power-domains = <&pgc_hdmimix>, <&pgc_hdmimix>, + <&pgc_hdmimix>, <&pgc_hdmimix>, + <&pgc_hdmimix>, <&pgc_hdmimix>, + <&pgc_hdmimix>, <&pgc_hdmi_phy>, + <&pgc_hdmimix>, <&pgc_hdmimix>; + power-domain-names = "bus", "irqsteer", "lcdif", + "pai", "pvi", "trng", + "hdmi-tx", "hdmi-tx-phy", + "hdcp", "hrv"; + #power-domain-cells = <1>; + }; }; pcie: pcie@33800000 { @@ -1970,6 +2018,18 @@ vpumix_blk_ctrl: blk-ctrl@38330000 { interconnect-names = "g1", "g2", "vc8000e"; }; + npu: npu@38500000 { + compatible = "vivante,gc"; + reg = <0x38500000 0x200000>; + interrupts = ; + clocks = <&clk IMX8MP_CLK_NPU_ROOT>, + <&clk IMX8MP_CLK_NPU_ROOT>, + <&clk IMX8MP_CLK_ML_AXI>, + <&clk IMX8MP_CLK_ML_AHB>; + clock-names = "core", "shader", "bus", "reg"; + power-domains = <&pgc_mlmix>; + }; + gic: interrupt-controller@38800000 { compatible = "arm,gic-v3"; reg = <0x38800000 0x10000>, @@ -2030,6 +2090,7 @@ usb_dwc3_0: usb@38100000 { phys = <&usb3_phy0>, <&usb3_phy0>; phy-names = "usb2-phy", "usb3-phy"; snps,gfladj-refclk-lpm-sel-quirk; + snps,parkmode-disable-ss-quirk; }; }; @@ -2072,6 +2133,7 @@ usb_dwc3_1: usb@38200000 { phys = <&usb3_phy1>, <&usb3_phy1>; phy-names = "usb2-phy", "usb3-phy"; snps,gfladj-refclk-lpm-sel-quirk; + snps,parkmode-disable-ss-quirk; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 35f07dfb4ca8df..052ba9baa400f8 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -1649,6 +1649,7 @@ usb_dwc3_0: usb@38100000 { phys = <&usb3_phy0>, <&usb3_phy0>; phy-names = "usb2-phy", "usb3-phy"; power-domains = <&pgc_otg1>; + snps,parkmode-disable-ss-quirk; status = "disabled"; }; @@ -1680,6 +1681,7 @@ usb_dwc3_1: usb@38200000 { phys = <&usb3_phy1>, <&usb3_phy1>; phy-names = "usb2-phy", "usb3-phy"; power-domains = <&pgc_otg2>; + snps,parkmode-disable-ss-quirk; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts index 0b34cc2250e14c..a9ab87699f3d56 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts +++ b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts @@ -36,7 +36,7 @@ reg_usdhc2_vmmc: usdhc2-vmmc { regulator-name = "SD1_SPWR"; regulator-min-microvolt = <3000000>; regulator-max-microvolt = <3000000>; - gpio = <&lsio_gpio4 19 GPIO_ACTIVE_HIGH>; + gpio = <&lsio_gpio4 7 GPIO_ACTIVE_HIGH>; enable-active-high; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi index e9b198c13b2fd8..d896135f31fcd8 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi @@ -49,15 +49,15 @@ &flexcan1 { }; &flexcan2 { - clocks = <&can1_lpcg 1>, - <&can1_lpcg 0>; + clocks = <&can1_lpcg IMX_LPCG_CLK_4>, + <&can1_lpcg IMX_LPCG_CLK_0>; assigned-clocks = <&clk IMX_SC_R_CAN_1 IMX_SC_PM_CLK_PER>; fsl,clk-source = /bits/ 8 <1>; }; &flexcan3 { - clocks = <&can2_lpcg 1>, - <&can2_lpcg 0>; + clocks = <&can2_lpcg IMX_LPCG_CLK_4>, + <&can2_lpcg IMX_LPCG_CLK_0>; assigned-clocks = <&clk IMX_SC_R_CAN_2 IMX_SC_PM_CLK_PER>; fsl,clk-source = /bits/ 8 <1>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-img.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-img.dtsi index 7764b4146e0ab4..2bbdacb1313f9d 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-ss-img.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-img.dtsi @@ -8,5 +8,5 @@ &jpegdec { }; &jpegenc { - compatible = "nxp,imx8qm-jpgdec", "nxp,imx8qxp-jpgenc"; + compatible = "nxp,imx8qm-jpgenc", "nxp,imx8qxp-jpgenc"; }; diff --git a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts index cafd39130eb887..a06ca740f540c7 100644 --- a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts @@ -168,7 +168,6 @@ &usdhc2 { vmmc-supply = <®_usdhc2_vmmc>; bus-width = <4>; status = "okay"; - no-sdio; no-mmc; }; diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts index f06139bdff97e3..aaf9685ef0fbbb 100644 --- a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts +++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts @@ -437,7 +437,7 @@ &usdhc2 { pinctrl-0 = <&pinctrl_usdhc2_hs>, <&pinctrl_usdhc2_gpio>; pinctrl-1 = <&pinctrl_usdhc2_uhs>, <&pinctrl_usdhc2_gpio>; pinctrl-2 = <&pinctrl_usdhc2_uhs>, <&pinctrl_usdhc2_gpio>; - cd-gpios = <&gpio3 00 GPIO_ACTIVE_LOW>; + cd-gpios = <&gpio3 0 GPIO_ACTIVE_LOW>; vmmc-supply = <®_usdhc2_vmmc>; bus-width = <4>; no-sdio; @@ -577,7 +577,7 @@ pinctrl_uart2: uart2grp { fsl,pins = < MX93_PAD_UART2_TXD__LPUART2_TX 0x31e MX93_PAD_UART2_RXD__LPUART2_RX 0x31e - MX93_PAD_SAI1_TXD0__LPUART2_RTS_B 0x31e + MX93_PAD_SAI1_TXD0__LPUART2_RTS_B 0x51e >; }; diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi index f6e422dc2663e9..b6f3c076fe54a1 100644 --- a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi +++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi @@ -19,7 +19,7 @@ reserved-memory { linux,cma { compatible = "shared-dma-pool"; reusable; - alloc-ranges = <0 0x60000000 0 0x40000000>; + alloc-ranges = <0 0x80000000 0 0x40000000>; size = <0 0x10000000>; linux,cma-default; }; diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi index dcf6e4846ac9de..35155b009dd249 100644 --- a/arch/arm64/boot/dts/freescale/imx93.dtsi +++ b/arch/arm64/boot/dts/freescale/imx93.dtsi @@ -373,7 +373,7 @@ mediamix: power-domain@44462400 { compatible = "fsl,imx93-src-slice"; reg = <0x44462400 0x400>, <0x44465800 0x400>; #power-domain-cells = <0>; - clocks = <&clk IMX93_CLK_MEDIA_AXI>, + clocks = <&clk IMX93_CLK_NIC_MEDIA_GATE>, <&clk IMX93_CLK_MEDIA_APB>; }; }; @@ -786,6 +786,8 @@ fec: ethernet@42890000 { fsl,num-tx-queues = <3>; fsl,num-rx-queues = <3>; fsl,stop-mode = <&wakeupmix_gpr 0x0c 1>; + nvmem-cells = <ð_mac1>; + nvmem-cell-names = "mac-address"; status = "disabled"; }; @@ -807,7 +809,9 @@ eqos: ethernet@428a0000 { <&clk IMX93_CLK_SYS_PLL_PFD0_DIV2>; assigned-clock-rates = <100000000>, <250000000>; intf_mode = <&wakeupmix_gpr 0x28>; - snps,clk-csr = <0>; + snps,clk-csr = <6>; + nvmem-cells = <ð_mac2>; + nvmem-cell-names = "mac-address"; status = "disabled"; }; @@ -888,6 +892,15 @@ ocotp: efuse@47510000 { reg = <0x47510000 0x10000>; #address-cells = <1>; #size-cells = <1>; + + eth_mac1: mac-address@4ec { + reg = <0x4ec 0x6>; + }; + + eth_mac2: mac-address@4f2 { + reg = <0x4f2 0x6>; + }; + }; s4muap: mailbox@47520000 { diff --git a/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi b/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi index ed1b5a7a606786..d01023401d7e3f 100644 --- a/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi +++ b/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi @@ -58,7 +58,7 @@ cpu@3 { gic: interrupt-controller@f1001000 { compatible = "arm,gic-400"; reg = <0x0 0xf1001000 0x0 0x1000>, /* GICD */ - <0x0 0xf1002000 0x0 0x100>; /* GICC */ + <0x0 0xf1002000 0x0 0x2000>; /* GICC */ #address-cells = <0>; #interrupt-cells = <3>; interrupt-controller; diff --git a/arch/arm64/boot/dts/hisilicon/hikey970-pmic.dtsi b/arch/arm64/boot/dts/hisilicon/hikey970-pmic.dtsi index 970047f2dabd51..c06e011a6c3ffc 100644 --- a/arch/arm64/boot/dts/hisilicon/hikey970-pmic.dtsi +++ b/arch/arm64/boot/dts/hisilicon/hikey970-pmic.dtsi @@ -25,9 +25,6 @@ pmic: pmic@0 { gpios = <&gpio28 0 0>; regulators { - #address-cells = <1>; - #size-cells = <0>; - ldo3: ldo3 { /* HDMI */ regulator-name = "ldo3"; regulator-min-microvolt = <1500000>; diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi index 48ec4ebec0a83e..b864ffa74ea8b6 100644 --- a/arch/arm64/boot/dts/lg/lg1312.dtsi +++ b/arch/arm64/boot/dts/lg/lg1312.dtsi @@ -126,7 +126,6 @@ eth0: ethernet@c1b00000 { amba { #address-cells = <2>; #size-cells = <1>; - #interrupt-cells = <3>; compatible = "simple-bus"; interrupt-parent = <&gic>; diff --git a/arch/arm64/boot/dts/lg/lg1313.dtsi b/arch/arm64/boot/dts/lg/lg1313.dtsi index 3869460aa5dcb5..996fb39bb50c1f 100644 --- a/arch/arm64/boot/dts/lg/lg1313.dtsi +++ b/arch/arm64/boot/dts/lg/lg1313.dtsi @@ -126,7 +126,6 @@ eth0: ethernet@c3700000 { amba { #address-cells = <2>; #size-cells = <1>; - #interrupt-cells = <3>; compatible = "simple-bus"; interrupt-parent = <&gic>; diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts index 9eab2bb221348a..805ef2d79b4012 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts @@ -130,7 +130,7 @@ rtc@6f { compatible = "microchip,mcp7940x"; reg = <0x6f>; interrupt-parent = <&gpiosb>; - interrupts = <5 0>; /* GPIO2_5 */ + interrupts = <5 IRQ_TYPE_EDGE_FALLING>; /* GPIO2_5 */ }; }; diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index e300145ad1a6f5..1cc3fa1c354de8 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -431,14 +431,14 @@ xor11 { crypto: crypto@90000 { compatible = "inside-secure,safexcel-eip97ies"; reg = <0x90000 0x20000>; - interrupts = , - , + interrupts = , , , , - ; - interrupt-names = "mem", "ring0", "ring1", - "ring2", "ring3", "eip"; + , + ; + interrupt-names = "ring0", "ring1", "ring2", + "ring3", "eip", "mem"; clocks = <&nb_periph_clk 15>; }; diff --git a/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi b/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi index 2c920e22cec2b5..7ec7c789d87eff 100644 --- a/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi @@ -138,7 +138,6 @@ pmu { odmi: odmi@300000 { compatible = "marvell,odmi-controller"; - interrupt-controller; msi-controller; marvell,odmi-frames = <4>; reg = <0x300000 0x4000>, diff --git a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi index 4ec1aae0a3a9c3..7e595ac80043aa 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi @@ -511,14 +511,14 @@ CP11X_LABEL(sdhci0): mmc@780000 { CP11X_LABEL(crypto): crypto@800000 { compatible = "inside-secure,safexcel-eip197b"; reg = <0x800000 0x200000>; - interrupts = <87 IRQ_TYPE_LEVEL_HIGH>, - <88 IRQ_TYPE_LEVEL_HIGH>, + interrupts = <88 IRQ_TYPE_LEVEL_HIGH>, <89 IRQ_TYPE_LEVEL_HIGH>, <90 IRQ_TYPE_LEVEL_HIGH>, <91 IRQ_TYPE_LEVEL_HIGH>, - <92 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "mem", "ring0", "ring1", - "ring2", "ring3", "eip"; + <92 IRQ_TYPE_LEVEL_HIGH>, + <87 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "ring0", "ring1", "ring2", "ring3", + "eip", "mem"; clock-names = "core", "reg"; clocks = <&CP11X_LABEL(clk) 1 26>, <&CP11X_LABEL(clk) 1 17>; diff --git a/arch/arm64/boot/dts/marvell/cn9130-crb.dtsi b/arch/arm64/boot/dts/marvell/cn9130-crb.dtsi index 32cfb3e2efc3a4..47d45ff3d6f578 100644 --- a/arch/arm64/boot/dts/marvell/cn9130-crb.dtsi +++ b/arch/arm64/boot/dts/marvell/cn9130-crb.dtsi @@ -120,7 +120,7 @@ cp0_sdhci_pins: cp0-sdhi-pins-0 { "mpp59", "mpp60", "mpp61"; marvell,function = "sdio"; }; - cp0_spi0_pins: cp0-spi-pins-0 { + cp0_spi1_pins: cp0-spi-pins-1 { marvell,pins = "mpp13", "mpp14", "mpp15", "mpp16"; marvell,function = "spi1"; }; @@ -170,7 +170,7 @@ &cp0_sdhci0 { &cp0_spi1 { pinctrl-names = "default"; - pinctrl-0 = <&cp0_spi0_pins>; + pinctrl-0 = <&cp0_spi1_pins>; reg = <0x700680 0x50>, /* control */ <0x2000000 0x1000000>; /* CS0 */ status = "okay"; diff --git a/arch/arm64/boot/dts/marvell/cn9130-db.dtsi b/arch/arm64/boot/dts/marvell/cn9130-db.dtsi index c7de1ea0d470a9..6eb6a175de38d5 100644 --- a/arch/arm64/boot/dts/marvell/cn9130-db.dtsi +++ b/arch/arm64/boot/dts/marvell/cn9130-db.dtsi @@ -307,7 +307,7 @@ &cp0_sdhci0 { &cp0_spi1 { status = "disabled"; pinctrl-names = "default"; - pinctrl-0 = <&cp0_spi0_pins>; + pinctrl-0 = <&cp0_spi1_pins>; reg = <0x700680 0x50>; flash@0 { @@ -371,7 +371,7 @@ cp0_sdhci_pins: cp0-sdhi-pins-0 { "mpp59", "mpp60", "mpp61"; marvell,function = "sdio"; }; - cp0_spi0_pins: cp0-spi-pins-0 { + cp0_spi1_pins: cp0-spi-pins-1 { marvell,pins = "mpp13", "mpp14", "mpp15", "mpp16"; marvell,function = "spi1"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts index fffdb7bbf889e4..2d0ef6f23b3a93 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts @@ -129,7 +129,7 @@ ethernet_phy0: ethernet-phy@5 { }; &pio { - eth_default: eth_default { + eth_default: eth-default-pins { tx_pins { pinmux = , , @@ -156,7 +156,7 @@ mdio_pins { }; }; - eth_sleep: eth_sleep { + eth_sleep: eth-sleep-pins { tx_pins { pinmux = , , @@ -182,14 +182,14 @@ mdio_pins { }; }; - usb0_id_pins_float: usb0_iddig { + usb0_id_pins_float: usb0-iddig-pins { pins_iddig { pinmux = ; bias-pull-up; }; }; - usb1_id_pins_float: usb1_iddig { + usb1_id_pins_float: usb1-iddig-pins { pins_iddig { pinmux = ; bias-pull-up; diff --git a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi index ed1a9d31941530..f767f921bdee16 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi @@ -249,10 +249,11 @@ topckgen: syscon@10000000 { #clock-cells = <1>; }; - infracfg: syscon@10001000 { + infracfg: clock-controller@10001000 { compatible = "mediatek,mt2712-infracfg", "syscon"; reg = <0 0x10001000 0 0x1000>; #clock-cells = <1>; + #reset-cells = <1>; }; pericfg: syscon@10003000 { diff --git a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts index 86cedb0bf1a900..15838c1ee8cc33 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts @@ -73,8 +73,9 @@ led-1 { }; }; - memory { + memory@40000000 { reg = <0 0x40000000 0 0x40000000>; + device_type = "memory"; }; reg_1p8v: regulator-1p8v { @@ -317,8 +318,8 @@ asm_sel { /* eMMC is shared pin with parallel NAND */ emmc_pins_default: emmc-pins-default { mux { - function = "emmc", "emmc_rst"; - groups = "emmc"; + function = "emmc"; + groups = "emmc", "emmc_rst"; }; /* "NDL0","NDL1","NDL2","NDL3","NDL4","NDL5","NDL6","NDL7", diff --git a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts index dad8e683aac5bc..0a14ef1da60de8 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts @@ -55,8 +55,9 @@ key-wps { }; }; - memory { + memory@40000000 { reg = <0 0x40000000 0 0x20000000>; + device_type = "memory"; }; reg_1p8v: regulator-1p8v { @@ -243,8 +244,8 @@ &pio { /* eMMC is shared pin with parallel NAND */ emmc_pins_default: emmc-pins-default { mux { - function = "emmc", "emmc_rst"; - groups = "emmc"; + function = "emmc"; + groups = "emmc", "emmc_rst"; }; /* "NDL0","NDL1","NDL2","NDL3","NDL4","NDL5","NDL6","NDL7", diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi index 3ee9266fa8e985..917fa39a74f8d7 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi @@ -252,7 +252,7 @@ scpsys: power-controller@10006000 { clock-names = "hif_sel"; }; - cir: cir@10009000 { + cir: ir-receiver@10009000 { compatible = "mediatek,mt7622-cir"; reg = <0 0x10009000 0 0x1000>; interrupts = ; @@ -283,16 +283,14 @@ thermal_calibration: calib@198 { }; }; - apmixedsys: apmixedsys@10209000 { - compatible = "mediatek,mt7622-apmixedsys", - "syscon"; + apmixedsys: clock-controller@10209000 { + compatible = "mediatek,mt7622-apmixedsys"; reg = <0 0x10209000 0 0x1000>; #clock-cells = <1>; }; - topckgen: topckgen@10210000 { - compatible = "mediatek,mt7622-topckgen", - "syscon"; + topckgen: clock-controller@10210000 { + compatible = "mediatek,mt7622-topckgen"; reg = <0 0x10210000 0 0x1000>; #clock-cells = <1>; }; @@ -515,7 +513,6 @@ thermal: thermal@1100b000 { <&pericfg CLK_PERI_AUXADC_PD>; clock-names = "therm", "auxadc"; resets = <&pericfg MT7622_PERI_THERM_SW_RST>; - reset-names = "therm"; mediatek,auxadc = <&auxadc>; mediatek,apmixedsys = <&apmixedsys>; nvmem-cells = <&thermal_calibration>; @@ -734,9 +731,8 @@ wmac: wmac@18000000 { power-domains = <&scpsys MT7622_POWER_DOMAIN_WB>; }; - ssusbsys: ssusbsys@1a000000 { - compatible = "mediatek,mt7622-ssusbsys", - "syscon"; + ssusbsys: clock-controller@1a000000 { + compatible = "mediatek,mt7622-ssusbsys"; reg = <0 0x1a000000 0 0x1000>; #clock-cells = <1>; #reset-cells = <1>; @@ -793,9 +789,8 @@ u2port1: usb-phy@1a0c5000 { }; }; - pciesys: pciesys@1a100800 { - compatible = "mediatek,mt7622-pciesys", - "syscon"; + pciesys: clock-controller@1a100800 { + compatible = "mediatek,mt7622-pciesys"; reg = <0 0x1a100800 0 0x1000>; #clock-cells = <1>; #reset-cells = <1>; @@ -921,12 +916,13 @@ sata_port: sata-phy@1a243000 { }; }; - hifsys: syscon@1af00000 { - compatible = "mediatek,mt7622-hifsys", "syscon"; + hifsys: clock-controller@1af00000 { + compatible = "mediatek,mt7622-hifsys"; reg = <0 0x1af00000 0 0x70>; + #clock-cells = <1>; }; - ethsys: syscon@1b000000 { + ethsys: clock-controller@1b000000 { compatible = "mediatek,mt7622-ethsys", "syscon"; reg = <0 0x1b000000 0 0x1000>; @@ -966,9 +962,7 @@ wed1: wed@1020b000 { }; eth: ethernet@1b100000 { - compatible = "mediatek,mt7622-eth", - "mediatek,mt2701-eth", - "syscon"; + compatible = "mediatek,mt7622-eth"; reg = <0 0x1b100000 0 0x20000>; interrupts = , , diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts index af4a4309bda4b9..aba6686eb34a3a 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts +++ b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts @@ -43,7 +43,7 @@ fan: pwm-fan { #cooling-cells = <2>; /* cooling level (0, 1, 2) - pwm inverted */ cooling-levels = <255 96 0>; - pwms = <&pwm 0 10000 0>; + pwms = <&pwm 0 10000>; status = "okay"; }; @@ -126,6 +126,7 @@ sfp1: sfp-1 { compatible = "sff,sfp"; i2c-bus = <&i2c_sfp1>; los-gpios = <&pio 46 GPIO_ACTIVE_HIGH>; + maximum-power-milliwatt = <3000>; mod-def0-gpios = <&pio 49 GPIO_ACTIVE_LOW>; tx-disable-gpios = <&pio 20 GPIO_ACTIVE_HIGH>; tx-fault-gpios = <&pio 7 GPIO_ACTIVE_HIGH>; @@ -137,6 +138,7 @@ sfp2: sfp-2 { i2c-bus = <&i2c_sfp2>; los-gpios = <&pio 31 GPIO_ACTIVE_HIGH>; mod-def0-gpios = <&pio 47 GPIO_ACTIVE_LOW>; + maximum-power-milliwatt = <3000>; tx-disable-gpios = <&pio 15 GPIO_ACTIVE_HIGH>; tx-fault-gpios = <&pio 48 GPIO_ACTIVE_HIGH>; }; @@ -144,22 +146,22 @@ sfp2: sfp-2 { &cpu_thermal { cooling-maps { - cpu-active-high { + map-cpu-active-high { /* active: set fan to cooling level 2 */ cooling-device = <&fan 2 2>; trip = <&cpu_trip_active_high>; }; - cpu-active-low { + map-cpu-active-med { /* active: set fan to cooling level 1 */ cooling-device = <&fan 1 1>; - trip = <&cpu_trip_active_low>; + trip = <&cpu_trip_active_med>; }; - cpu-passive { - /* passive: set fan to cooling level 0 */ + map-cpu-active-low { + /* active: set fan to cooling level 0 */ cooling-device = <&fan 0 0>; - trip = <&cpu_trip_passive>; + trip = <&cpu_trip_active_low>; }; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-rfb.dts b/arch/arm64/boot/dts/mediatek/mt7986a-rfb.dts index 3ef371ca254e81..2f884c24f1eb46 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986a-rfb.dts +++ b/arch/arm64/boot/dts/mediatek/mt7986a-rfb.dts @@ -237,12 +237,13 @@ &spi0 { pinctrl-0 = <&spi_flash_pins>; cs-gpios = <0>, <0>; status = "okay"; - spi_nand: spi_nand@0 { + + spi_nand: flash@0 { compatible = "spi-nand"; reg = <0>; spi-max-frequency = <10000000>; - spi-tx-buswidth = <4>; - spi-rx-buswidth = <4>; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi index 24eda00e320d3a..559990dcd1d179 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi @@ -16,49 +16,49 @@ / { #address-cells = <2>; #size-cells = <2>; - clk40m: oscillator-40m { - compatible = "fixed-clock"; - clock-frequency = <40000000>; - #clock-cells = <0>; - clock-output-names = "clkxtal"; - }; - cpus { #address-cells = <1>; #size-cells = <0>; cpu0: cpu@0 { - device_type = "cpu"; compatible = "arm,cortex-a53"; - enable-method = "psci"; reg = <0x0>; + device_type = "cpu"; + enable-method = "psci"; #cooling-cells = <2>; }; cpu1: cpu@1 { - device_type = "cpu"; compatible = "arm,cortex-a53"; - enable-method = "psci"; reg = <0x1>; + device_type = "cpu"; + enable-method = "psci"; #cooling-cells = <2>; }; cpu2: cpu@2 { - device_type = "cpu"; compatible = "arm,cortex-a53"; - enable-method = "psci"; reg = <0x2>; + device_type = "cpu"; + enable-method = "psci"; #cooling-cells = <2>; }; cpu3: cpu@3 { - device_type = "cpu"; - enable-method = "psci"; compatible = "arm,cortex-a53"; reg = <0x3>; + device_type = "cpu"; + enable-method = "psci"; #cooling-cells = <2>; }; }; + clk40m: oscillator-40m { + compatible = "fixed-clock"; + clock-frequency = <40000000>; + #clock-cells = <0>; + clock-output-names = "clkxtal"; + }; + psci { compatible = "arm,psci-0.2"; method = "smc"; @@ -121,38 +121,30 @@ wo_boot: wo-boot@15194000 { }; - timer { - compatible = "arm,armv8-timer"; - interrupt-parent = <&gic>; - interrupts = , - , - , - ; - }; - soc { - #address-cells = <2>; - #size-cells = <2>; compatible = "simple-bus"; ranges; + #address-cells = <2>; + #size-cells = <2>; gic: interrupt-controller@c000000 { compatible = "arm,gic-v3"; - #interrupt-cells = <3>; - interrupt-parent = <&gic>; - interrupt-controller; reg = <0 0x0c000000 0 0x10000>, /* GICD */ <0 0x0c080000 0 0x80000>, /* GICR */ <0 0x0c400000 0 0x2000>, /* GICC */ <0 0x0c410000 0 0x1000>, /* GICH */ <0 0x0c420000 0 0x2000>; /* GICV */ + interrupt-parent = <&gic>; interrupts = ; + interrupt-controller; + #interrupt-cells = <3>; }; infracfg: infracfg@10001000 { compatible = "mediatek,mt7986-infracfg", "syscon"; reg = <0 0x10001000 0 0x1000>; #clock-cells = <1>; + #reset-cells = <1>; }; wed_pcie: wed-pcie@10003000 { @@ -202,6 +194,19 @@ pio: pinctrl@1001f000 { #interrupt-cells = <2>; }; + pwm: pwm@10048000 { + compatible = "mediatek,mt7986-pwm"; + reg = <0 0x10048000 0 0x1000>; + #pwm-cells = <2>; + interrupts = ; + clocks = <&topckgen CLK_TOP_PWM_SEL>, + <&infracfg CLK_INFRA_PWM_STA>, + <&infracfg CLK_INFRA_PWM1_CK>, + <&infracfg CLK_INFRA_PWM2_CK>; + clock-names = "top", "main", "pwm1", "pwm2"; + status = "disabled"; + }; + sgmiisys0: syscon@10060000 { compatible = "mediatek,mt7986-sgmiisys_0", "syscon"; @@ -234,26 +239,11 @@ crypto: crypto@10320000 { ; interrupt-names = "ring0", "ring1", "ring2", "ring3"; clocks = <&infracfg CLK_INFRA_EIP97_CK>; - clock-names = "infra_eip97_ck"; assigned-clocks = <&topckgen CLK_TOP_EIP_B_SEL>; assigned-clock-parents = <&apmixedsys CLK_APMIXED_NET2PLL>; status = "disabled"; }; - pwm: pwm@10048000 { - compatible = "mediatek,mt7986-pwm"; - reg = <0 0x10048000 0 0x1000>; - #clock-cells = <1>; - #pwm-cells = <2>; - interrupts = ; - clocks = <&topckgen CLK_TOP_PWM_SEL>, - <&infracfg CLK_INFRA_PWM_STA>, - <&infracfg CLK_INFRA_PWM1_CK>, - <&infracfg CLK_INFRA_PWM2_CK>; - clock-names = "top", "main", "pwm1", "pwm2"; - status = "disabled"; - }; - uart0: serial@11002000 { compatible = "mediatek,mt7986-uart", "mediatek,mt6577-uart"; @@ -311,9 +301,9 @@ i2c0: i2c@11008000 { spi0: spi@1100a000 { compatible = "mediatek,mt7986-spi-ipm", "mediatek,spi-ipm"; + reg = <0 0x1100a000 0 0x100>; #address-cells = <1>; #size-cells = <0>; - reg = <0 0x1100a000 0 0x100>; interrupts = ; clocks = <&topckgen CLK_TOP_MPLL_D2>, <&topckgen CLK_TOP_SPI_SEL>, @@ -325,9 +315,9 @@ spi0: spi@1100a000 { spi1: spi@1100b000 { compatible = "mediatek,mt7986-spi-ipm", "mediatek,spi-ipm"; + reg = <0 0x1100b000 0 0x100>; #address-cells = <1>; #size-cells = <0>; - reg = <0 0x1100b000 0 0x100>; interrupts = ; clocks = <&topckgen CLK_TOP_MPLL_D2>, <&topckgen CLK_TOP_SPIM_MST_SEL>, @@ -337,6 +327,20 @@ spi1: spi@1100b000 { status = "disabled"; }; + thermal: thermal@1100c800 { + compatible = "mediatek,mt7986-thermal"; + reg = <0 0x1100c800 0 0x800>; + interrupts = ; + clocks = <&infracfg CLK_INFRA_THERM_CK>, + <&infracfg CLK_INFRA_ADC_26M_CK>; + clock-names = "therm", "auxadc"; + nvmem-cells = <&thermal_calibration>; + nvmem-cell-names = "calibration-data"; + #thermal-sensor-cells = <1>; + mediatek,auxadc = <&auxadc>; + mediatek,apmixedsys = <&apmixedsys>; + }; + auxadc: adc@1100d000 { compatible = "mediatek,mt7986-auxadc"; reg = <0 0x1100d000 0 0x1000>; @@ -374,6 +378,10 @@ mmc0: mmc@11230000 { reg = <0 0x11230000 0 0x1000>, <0 0x11c20000 0 0x1000>; interrupts = ; + assigned-clocks = <&topckgen CLK_TOP_EMMC_416M_SEL>, + <&topckgen CLK_TOP_EMMC_250M_SEL>; + assigned-clock-parents = <&apmixedsys CLK_APMIXED_MPLL>, + <&topckgen CLK_TOP_NET1PLL_D5_D2>; clocks = <&topckgen CLK_TOP_EMMC_416M_SEL>, <&infracfg CLK_INFRA_MSDC_HCK_CK>, <&infracfg CLK_INFRA_MSDC_CK>, @@ -384,39 +392,23 @@ mmc0: mmc@11230000 { status = "disabled"; }; - thermal: thermal@1100c800 { - #thermal-sensor-cells = <1>; - compatible = "mediatek,mt7986-thermal"; - reg = <0 0x1100c800 0 0x800>; - interrupts = ; - clocks = <&infracfg CLK_INFRA_THERM_CK>, - <&infracfg CLK_INFRA_ADC_26M_CK>, - <&infracfg CLK_INFRA_ADC_FRC_CK>; - clock-names = "therm", "auxadc", "adc_32k"; - mediatek,auxadc = <&auxadc>; - mediatek,apmixedsys = <&apmixedsys>; - nvmem-cells = <&thermal_calibration>; - nvmem-cell-names = "calibration-data"; - }; - pcie: pcie@11280000 { compatible = "mediatek,mt7986-pcie", "mediatek,mt8192-pcie"; + reg = <0x00 0x11280000 0x00 0x4000>; + reg-names = "pcie-mac"; + ranges = <0x82000000 0x00 0x20000000 0x00 + 0x20000000 0x00 0x10000000>; device_type = "pci"; #address-cells = <3>; #size-cells = <2>; - reg = <0x00 0x11280000 0x00 0x4000>; - reg-names = "pcie-mac"; interrupts = ; bus-range = <0x00 0xff>; - ranges = <0x82000000 0x00 0x20000000 0x00 - 0x20000000 0x00 0x10000000>; clocks = <&infracfg CLK_INFRA_IPCIE_PIPE_CK>, <&infracfg CLK_INFRA_IPCIE_CK>, <&infracfg CLK_INFRA_IPCIER_CK>, <&infracfg CLK_INFRA_IPCIEB_CK>; clock-names = "pl_250m", "tl_26m", "peri_26m", "top_133m"; - status = "disabled"; phys = <&pcie_port PHY_TYPE_PCIE>; phy-names = "pcie-phy"; @@ -427,6 +419,8 @@ pcie: pcie@11280000 { <0 0 0 2 &pcie_intc 1>, <0 0 0 3 &pcie_intc 2>, <0 0 0 4 &pcie_intc 3>; + status = "disabled"; + pcie_intc: interrupt-controller { #address-cells = <0>; #interrupt-cells = <1>; @@ -437,9 +431,9 @@ pcie_intc: interrupt-controller { pcie_phy: t-phy { compatible = "mediatek,mt7986-tphy", "mediatek,generic-tphy-v2"; + ranges; #address-cells = <2>; #size-cells = <2>; - ranges; status = "disabled"; pcie_port: pcie-phy@11c00000 { @@ -464,9 +458,9 @@ thermal_calibration: calib@274 { usb_phy: t-phy@11e10000 { compatible = "mediatek,mt7986-tphy", "mediatek,generic-tphy-v2"; + ranges = <0 0 0x11e10000 0x1700>; #address-cells = <1>; #size-cells = <1>; - ranges = <0 0 0x11e10000 0x1700>; status = "disabled"; u2port0: usb-phy@0 { @@ -494,8 +488,6 @@ u2port1: usb-phy@1000 { }; ethsys: syscon@15000000 { - #address-cells = <1>; - #size-cells = <1>; compatible = "mediatek,mt7986-ethsys", "syscon"; reg = <0 0x15000000 0 0x1000>; @@ -529,20 +521,6 @@ wed1: wed@15011000 { mediatek,wo-ccif = <&wo_ccif1>; }; - wo_ccif0: syscon@151a5000 { - compatible = "mediatek,mt7986-wo-ccif", "syscon"; - reg = <0 0x151a5000 0 0x1000>; - interrupt-parent = <&gic>; - interrupts = ; - }; - - wo_ccif1: syscon@151ad000 { - compatible = "mediatek,mt7986-wo-ccif", "syscon"; - reg = <0 0x151ad000 0 0x1000>; - interrupt-parent = <&gic>; - interrupts = ; - }; - eth: ethernet@15100000 { compatible = "mediatek,mt7986-eth"; reg = <0 0x15100000 0 0x80000>; @@ -575,26 +553,39 @@ eth: ethernet@15100000 { <&topckgen CLK_TOP_SGM_325M_SEL>; assigned-clock-parents = <&apmixedsys CLK_APMIXED_NET2PLL>, <&apmixedsys CLK_APMIXED_SGMPLL>; + #address-cells = <1>; + #size-cells = <0>; mediatek,ethsys = <ðsys>; mediatek,sgmiisys = <&sgmiisys0>, <&sgmiisys1>; mediatek,wed-pcie = <&wed_pcie>; mediatek,wed = <&wed0>, <&wed1>; - #reset-cells = <1>; - #address-cells = <1>; - #size-cells = <0>; status = "disabled"; }; + wo_ccif0: syscon@151a5000 { + compatible = "mediatek,mt7986-wo-ccif", "syscon"; + reg = <0 0x151a5000 0 0x1000>; + interrupt-parent = <&gic>; + interrupts = ; + }; + + wo_ccif1: syscon@151ad000 { + compatible = "mediatek,mt7986-wo-ccif", "syscon"; + reg = <0 0x151ad000 0 0x1000>; + interrupt-parent = <&gic>; + interrupts = ; + }; + wifi: wifi@18000000 { compatible = "mediatek,mt7986-wmac"; + reg = <0 0x18000000 0 0x1000000>, + <0 0x10003000 0 0x1000>, + <0 0x11d10000 0 0x1000>; resets = <&watchdog MT7986_TOPRGU_CONSYS_SW_RST>; reset-names = "consys"; clocks = <&topckgen CLK_TOP_CONN_MCUSYS_SEL>, <&topckgen CLK_TOP_AP2CNN_HOST_SEL>; clock-names = "mcu", "ap2conn"; - reg = <0 0x18000000 0 0x1000000>, - <0 0x10003000 0 0x1000>, - <0 0x11d10000 0 0x1000>; interrupts = , , , @@ -610,24 +601,45 @@ cpu_thermal: cpu-thermal { thermal-sensors = <&thermal 0>; trips { + cpu_trip_crit: crit { + temperature = <125000>; + hysteresis = <2000>; + type = "critical"; + }; + + cpu_trip_hot: hot { + temperature = <120000>; + hysteresis = <2000>; + type = "hot"; + }; + cpu_trip_active_high: active-high { temperature = <115000>; hysteresis = <2000>; type = "active"; }; - cpu_trip_active_low: active-low { + cpu_trip_active_med: active-med { temperature = <85000>; hysteresis = <2000>; type = "active"; }; - cpu_trip_passive: passive { - temperature = <40000>; + cpu_trip_active_low: active-low { + temperature = <60000>; hysteresis = <2000>; - type = "passive"; + type = "active"; }; }; }; }; + + timer { + compatible = "arm,armv8-timer"; + interrupt-parent = <&gic>; + interrupts = , + , + , + ; + }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt7986b-rfb.dts b/arch/arm64/boot/dts/mediatek/mt7986b-rfb.dts index dde190442e3866..57dcaeef31d7fc 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986b-rfb.dts +++ b/arch/arm64/boot/dts/mediatek/mt7986b-rfb.dts @@ -152,12 +152,13 @@ &spi0 { pinctrl-0 = <&spi_flash_pins>; cs-gpios = <0>, <0>; status = "okay"; - spi_nand: spi_nand@0 { + + spi_nand: flash@0 { compatible = "spi-nand"; reg = <0>; spi-max-frequency = <10000000>; - spi-tx-buswidth = <4>; - spi-rx-buswidth = <4>; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts index 5122963d8743ab..d258c80213b264 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts @@ -44,7 +44,7 @@ extcon_usb: extcon_iddig { id-gpio = <&pio 16 GPIO_ACTIVE_HIGH>; }; - usb_p1_vbus: regulator@0 { + usb_p1_vbus: regulator-usb-p1 { compatible = "regulator-fixed"; regulator-name = "usb_vbus"; regulator-min-microvolt = <5000000>; @@ -53,7 +53,7 @@ usb_p1_vbus: regulator@0 { enable-active-high; }; - usb_p0_vbus: regulator@1 { + usb_p0_vbus: regulator-usb-p0 { compatible = "regulator-fixed"; regulator-name = "vbus"; regulator-min-microvolt = <5000000>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-evb.dts b/arch/arm64/boot/dts/mediatek/mt8183-evb.dts index d8bd5180768327..77f9ab94c00bd9 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt8183-evb.dts @@ -31,14 +31,14 @@ reserved-memory { #address-cells = <2>; #size-cells = <2>; ranges; - scp_mem_reserved: scp_mem_region { + scp_mem_reserved: memory@50000000 { compatible = "shared-dma-pool"; reg = <0 0x50000000 0 0x2900000>; no-map; }; }; - ntc@0 { + thermal-sensor { compatible = "murata,ncp03wf104"; pullup-uv = <1800000>; pullup-ohm = <390000>; @@ -155,8 +155,8 @@ &mt6358_vsram_gpu_reg { }; &pio { - i2c_pins_0: i2c0{ - pins_i2c{ + i2c_pins_0: i2c0 { + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -164,8 +164,8 @@ pins_i2c{ }; }; - i2c_pins_1: i2c1{ - pins_i2c{ + i2c_pins_1: i2c1 { + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -173,8 +173,8 @@ pins_i2c{ }; }; - i2c_pins_2: i2c2{ - pins_i2c{ + i2c_pins_2: i2c2 { + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -182,8 +182,8 @@ pins_i2c{ }; }; - i2c_pins_3: i2c3{ - pins_i2c{ + i2c_pins_3: i2c3 { + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -191,8 +191,8 @@ pins_i2c{ }; }; - i2c_pins_4: i2c4{ - pins_i2c{ + i2c_pins_4: i2c4 { + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -200,8 +200,8 @@ pins_i2c{ }; }; - i2c_pins_5: i2c5{ - pins_i2c{ + i2c_pins_5: i2c5 { + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -209,8 +209,8 @@ pins_i2c{ }; }; - spi_pins_0: spi0{ - pins_spi{ + spi_pins_0: spi0 { + pins_spi { pinmux = , , , @@ -324,8 +324,8 @@ pins_clk { }; }; - spi_pins_1: spi1{ - pins_spi{ + spi_pins_1: spi1 { + pins_spi { pinmux = , , , @@ -334,8 +334,8 @@ pins_spi{ }; }; - spi_pins_2: spi2{ - pins_spi{ + spi_pins_2: spi2 { + pins_spi { pinmux = , , , @@ -344,8 +344,8 @@ pins_spi{ }; }; - spi_pins_3: spi3{ - pins_spi{ + spi_pins_3: spi3 { + pins_spi { pinmux = , , , @@ -354,8 +354,8 @@ pins_spi{ }; }; - spi_pins_4: spi4{ - pins_spi{ + spi_pins_4: spi4 { + pins_spi { pinmux = , , , @@ -364,8 +364,8 @@ pins_spi{ }; }; - spi_pins_5: spi5{ - pins_spi{ + spi_pins_5: spi5 { + pins_spi { pinmux = , , , diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-da7219.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-da7219.dtsi index 2c69e7658dba6d..b9a6fd4f86d4a0 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-da7219.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-da7219.dtsi @@ -28,7 +28,7 @@ da7219_aad { dlg,btn-cfg = <50>; dlg,mic-det-thr = <500>; dlg,jack-ins-deb = <20>; - dlg,jack-det-rate = "32ms_64ms"; + dlg,jack-det-rate = "32_64"; dlg,jack-rem-deb = <1>; dlg,a-d-btn-thr = <0xa>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi index bf97b60ae4d17e..32f6899f885ef7 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi @@ -91,6 +91,8 @@ cros_ec_pwm: pwm { &dsi0 { status = "okay"; + /delete-property/#size-cells; + /delete-property/#address-cells; /delete-node/panel@0; ports { port { @@ -154,21 +156,24 @@ anx_bridge: anx7625@58 { vdd18-supply = <&pp1800_mipibrdg>; vdd33-supply = <&vddio_mipibrdg>; - #address-cells = <1>; - #size-cells = <0>; - port@0 { - reg = <0>; + ports { + #address-cells = <1>; + #size-cells = <0>; - anx7625_in: endpoint { - remote-endpoint = <&dsi_out>; + port@0 { + reg = <0>; + + anx7625_in: endpoint { + remote-endpoint = <&dsi_out>; + }; }; - }; - port@1 { - reg = <1>; + port@1 { + reg = <1>; - anx7625_out: endpoint { - remote-endpoint = <&panel_in>; + anx7625_out: endpoint { + remote-endpoint = <&panel_in>; + }; }; }; @@ -441,20 +446,20 @@ pins2 { }; touchscreen_pins: touchscreen-pins { - touch_int_odl { + touch-int-odl { pinmux = ; input-enable; bias-pull-up; }; - touch_rst_l { + touch-rst-l { pinmux = ; output-high; }; }; trackpad_pins: trackpad-pins { - trackpad_int { + trackpad-int { pinmux = ; input-enable; bias-disable; /* pulled externally */ diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi index a11adeb29b1f2e..0d3c7b8162ff0b 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi @@ -373,6 +373,10 @@ pen_eject { }; &cros_ec { + cbas { + compatible = "google,cros-cbas"; + }; + keyboard-controller { compatible = "google,cros-ec-keyb-switches"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi index 4864c39e53a4fd..e73113cb51f538 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi @@ -340,6 +340,10 @@ touch_pin_reset: pin_reset { }; &cros_ec { + cbas { + compatible = "google,cros-cbas"; + }; + keyboard-controller { compatible = "google,cros-ec-keyb-switches"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi index d5f41c6c98814a..181da69d18f46a 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi @@ -344,6 +344,10 @@ rst_pin { }; &cros_ec { + cbas { + compatible = "google,cros-cbas"; + }; + keyboard-controller { compatible = "google,cros-ec-keyb-switches"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi index 6ce16a265e0530..2c6587f260f82b 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi @@ -108,7 +108,7 @@ reserved_memory: reserved-memory { #size-cells = <2>; ranges; - scp_mem_reserved: scp_mem_region { + scp_mem_reserved: memory@50000000 { compatible = "shared-dma-pool"; reg = <0 0x50000000 0 0x2900000>; no-map; @@ -405,7 +405,6 @@ &mt6358codec { }; &mt6358_vgpu_reg { - regulator-min-microvolt = <625000>; regulator-max-microvolt = <900000>; regulator-coupled-with = <&mt6358_vsram_gpu_reg>; @@ -432,7 +431,7 @@ &mt6358_vsram_gpu_reg { &pio { aud_pins_default: audiopins { - pins_bus { + pins-bus { pinmux = , , , @@ -454,7 +453,7 @@ pins_bus { }; aud_pins_tdm_out_on: audiotdmouton { - pins_bus { + pins-bus { pinmux = , , , @@ -466,7 +465,7 @@ pins_bus { }; aud_pins_tdm_out_off: audiotdmoutoff { - pins_bus { + pins-bus { pinmux = , , , @@ -480,13 +479,13 @@ pins_bus { }; bt_pins: bt-pins { - pins_bt_en { + pins-bt-en { pinmux = ; output-low; }; }; - ec_ap_int_odl: ec_ap_int_odl { + ec_ap_int_odl: ec-ap-int-odl { pins1 { pinmux = ; input-enable; @@ -494,7 +493,7 @@ pins1 { }; }; - h1_int_od_l: h1_int_od_l { + h1_int_od_l: h1-int-od-l { pins1 { pinmux = ; input-enable; @@ -502,7 +501,7 @@ pins1 { }; i2c0_pins: i2c0 { - pins_bus { + pins-bus { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -511,7 +510,7 @@ pins_bus { }; i2c1_pins: i2c1 { - pins_bus { + pins-bus { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -520,7 +519,7 @@ pins_bus { }; i2c2_pins: i2c2 { - pins_bus { + pins-bus { pinmux = , ; bias-disable; @@ -529,7 +528,7 @@ pins_bus { }; i2c3_pins: i2c3 { - pins_bus { + pins-bus { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -538,7 +537,7 @@ pins_bus { }; i2c4_pins: i2c4 { - pins_bus { + pins-bus { pinmux = , ; bias-disable; @@ -547,7 +546,7 @@ pins_bus { }; i2c5_pins: i2c5 { - pins_bus { + pins-bus { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -556,7 +555,7 @@ pins_bus { }; i2c6_pins: i2c6 { - pins_bus { + pins-bus { pinmux = , ; bias-disable; @@ -564,7 +563,7 @@ pins_bus { }; mmc0_pins_default: mmc0-pins-default { - pins_cmd_dat { + pins-cmd-dat { pinmux = , , , @@ -579,13 +578,13 @@ pins_cmd_dat { mediatek,pull-up-adv = <01>; }; - pins_clk { + pins-clk { pinmux = ; drive-strength = ; mediatek,pull-down-adv = <10>; }; - pins_rst { + pins-rst { pinmux = ; drive-strength = ; mediatek,pull-down-adv = <01>; @@ -593,7 +592,7 @@ pins_rst { }; mmc0_pins_uhs: mmc0-pins-uhs { - pins_cmd_dat { + pins-cmd-dat { pinmux = , , , @@ -608,19 +607,19 @@ pins_cmd_dat { mediatek,pull-up-adv = <01>; }; - pins_clk { + pins-clk { pinmux = ; drive-strength = ; mediatek,pull-down-adv = <10>; }; - pins_ds { + pins-ds { pinmux = ; drive-strength = ; mediatek,pull-down-adv = <10>; }; - pins_rst { + pins-rst { pinmux = ; drive-strength = ; mediatek,pull-up-adv = <01>; @@ -628,7 +627,7 @@ pins_rst { }; mmc1_pins_default: mmc1-pins-default { - pins_cmd_dat { + pins-cmd-dat { pinmux = , , , @@ -638,7 +637,7 @@ pins_cmd_dat { mediatek,pull-up-adv = <10>; }; - pins_clk { + pins-clk { pinmux = ; input-enable; mediatek,pull-down-adv = <10>; @@ -646,7 +645,7 @@ pins_clk { }; mmc1_pins_uhs: mmc1-pins-uhs { - pins_cmd_dat { + pins-cmd-dat { pinmux = , , , @@ -657,7 +656,7 @@ pins_cmd_dat { mediatek,pull-up-adv = <10>; }; - pins_clk { + pins-clk { pinmux = ; drive-strength = ; mediatek,pull-down-adv = <10>; @@ -665,15 +664,15 @@ pins_clk { }; }; - panel_pins_default: panel_pins_default { - panel_reset { + panel_pins_default: panel-pins-default { + panel-reset { pinmux = ; output-low; bias-pull-up; }; }; - pwm0_pin_default: pwm0_pin_default { + pwm0_pin_default: pwm0-pin-default { pins1 { pinmux = ; output-high; @@ -685,14 +684,14 @@ pins2 { }; scp_pins: scp { - pins_scp_uart { + pins-scp-uart { pinmux = , ; }; }; spi0_pins: spi0 { - pins_spi{ + pins-spi { pinmux = , , , @@ -702,7 +701,7 @@ pins_spi{ }; spi1_pins: spi1 { - pins_spi{ + pins-spi { pinmux = , , , @@ -712,20 +711,20 @@ pins_spi{ }; spi2_pins: spi2 { - pins_spi{ + pins-spi { pinmux = , , ; bias-disable; }; - pins_spi_mi { + pins-spi-mi { pinmux = ; mediatek,pull-down-adv = <00>; }; }; spi3_pins: spi3 { - pins_spi{ + pins-spi { pinmux = , , , @@ -735,7 +734,7 @@ pins_spi{ }; spi4_pins: spi4 { - pins_spi{ + pins-spi { pinmux = , , , @@ -745,7 +744,7 @@ pins_spi{ }; spi5_pins: spi5 { - pins_spi{ + pins-spi { pinmux = , , , @@ -755,63 +754,61 @@ pins_spi{ }; uart0_pins_default: uart0-pins-default { - pins_rx { + pins-rx { pinmux = ; input-enable; bias-pull-up; }; - pins_tx { + pins-tx { pinmux = ; }; }; uart1_pins_default: uart1-pins-default { - pins_rx { + pins-rx { pinmux = ; input-enable; bias-pull-up; }; - pins_tx { + pins-tx { pinmux = ; }; - pins_rts { + pins-rts { pinmux = ; - output-enable; }; - pins_cts { + pins-cts { pinmux = ; input-enable; }; }; uart1_pins_sleep: uart1-pins-sleep { - pins_rx { + pins-rx { pinmux = ; input-enable; bias-pull-up; }; - pins_tx { + pins-tx { pinmux = ; }; - pins_rts { + pins-rts { pinmux = ; - output-enable; }; - pins_cts { + pins-cts { pinmux = ; input-enable; }; }; wifi_pins_pwrseq: wifi-pins-pwrseq { - pins_wifi_enable { + pins-wifi-enable { pinmux = ; output-low; }; }; wifi_pins_wakeup: wifi-pins-wakeup { - pins_wifi_wakeup { + pins-wifi-wakeup { pinmux = ; input-enable; }; @@ -907,10 +904,6 @@ usbc_extcon: extcon0 { google,usb-port-id = <0>; }; - cbas { - compatible = "google,cros-cbas"; - }; - typec { compatible = "google,cros-ec-typec"; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts b/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts index 526bcae7a3f8ff..b5784a60c315d3 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts +++ b/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts @@ -193,7 +193,7 @@ &mt6358_vsram_gpu_reg { &pio { i2c_pins_0: i2c0 { - pins_i2c{ + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -202,7 +202,7 @@ pins_i2c{ }; i2c_pins_1: i2c1 { - pins_i2c{ + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -211,7 +211,7 @@ pins_i2c{ }; i2c_pins_2: i2c2 { - pins_i2c{ + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -220,7 +220,7 @@ pins_i2c{ }; i2c_pins_3: i2c3 { - pins_i2c{ + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -229,7 +229,7 @@ pins_i2c{ }; i2c_pins_4: i2c4 { - pins_i2c{ + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -238,7 +238,7 @@ pins_i2c{ }; i2c_pins_5: i2c5 { - pins_i2c{ + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi index 5169779d01dfb4..8721a5ffca30a7 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi @@ -1210,127 +1210,6 @@ thermal: thermal@1100b000 { nvmem-cell-names = "calibration-data"; }; - thermal_zones: thermal-zones { - cpu_thermal: cpu-thermal { - polling-delay-passive = <100>; - polling-delay = <500>; - thermal-sensors = <&thermal 0>; - sustainable-power = <5000>; - - trips { - threshold: trip-point0 { - temperature = <68000>; - hysteresis = <2000>; - type = "passive"; - }; - - target: trip-point1 { - temperature = <80000>; - hysteresis = <2000>; - type = "passive"; - }; - - cpu_crit: cpu-crit { - temperature = <115000>; - hysteresis = <2000>; - type = "critical"; - }; - }; - - cooling-maps { - map0 { - trip = <&target>; - cooling-device = <&cpu0 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>, - <&cpu1 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>, - <&cpu2 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>, - <&cpu3 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>; - contribution = <3072>; - }; - map1 { - trip = <&target>; - cooling-device = <&cpu4 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>, - <&cpu5 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>, - <&cpu6 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>, - <&cpu7 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>; - contribution = <1024>; - }; - }; - }; - - /* The tzts1 ~ tzts6 don't need to polling */ - /* The tzts1 ~ tzts6 don't need to thermal throttle */ - - tzts1: tzts1 { - polling-delay-passive = <0>; - polling-delay = <0>; - thermal-sensors = <&thermal 1>; - sustainable-power = <5000>; - trips {}; - cooling-maps {}; - }; - - tzts2: tzts2 { - polling-delay-passive = <0>; - polling-delay = <0>; - thermal-sensors = <&thermal 2>; - sustainable-power = <5000>; - trips {}; - cooling-maps {}; - }; - - tzts3: tzts3 { - polling-delay-passive = <0>; - polling-delay = <0>; - thermal-sensors = <&thermal 3>; - sustainable-power = <5000>; - trips {}; - cooling-maps {}; - }; - - tzts4: tzts4 { - polling-delay-passive = <0>; - polling-delay = <0>; - thermal-sensors = <&thermal 4>; - sustainable-power = <5000>; - trips {}; - cooling-maps {}; - }; - - tzts5: tzts5 { - polling-delay-passive = <0>; - polling-delay = <0>; - thermal-sensors = <&thermal 5>; - sustainable-power = <5000>; - trips {}; - cooling-maps {}; - }; - - tztsABB: tztsABB { - polling-delay-passive = <0>; - polling-delay = <0>; - thermal-sensors = <&thermal 6>; - sustainable-power = <5000>; - trips {}; - cooling-maps {}; - }; - }; - pwm0: pwm@1100e000 { compatible = "mediatek,mt8183-disp-pwm"; reg = <0 0x1100e000 0 0x1000>; @@ -1749,6 +1628,7 @@ mfgcfg: syscon@13000000 { compatible = "mediatek,mt8183-mfgcfg", "syscon"; reg = <0 0x13000000 0 0x1000>; #clock-cells = <1>; + power-domains = <&spm MT8183_POWER_DOMAIN_MFG_ASYNC>; }; gpu: gpu@13040000 { @@ -1781,7 +1661,7 @@ mmsys: syscon@14000000 { mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0 0x1000>; }; - mdp3-rdma0@14001000 { + dma-controller0@14001000 { compatible = "mediatek,mt8183-mdp3-rdma"; reg = <0 0x14001000 0 0x1000>; mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>; @@ -1793,6 +1673,7 @@ mdp3-rdma0@14001000 { iommus = <&iommu M4U_PORT_MDP_RDMA0>; mboxes = <&gce 20 CMDQ_THR_PRIO_LOWEST 0>, <&gce 21 CMDQ_THR_PRIO_LOWEST 0>; + #dma-cells = <1>; }; mdp3-rsz0@14003000 { @@ -1813,7 +1694,7 @@ mdp3-rsz1@14004000 { clocks = <&mmsys CLK_MM_MDP_RSZ1>; }; - mdp3-wrot0@14005000 { + dma-controller@14005000 { compatible = "mediatek,mt8183-mdp3-wrot"; reg = <0 0x14005000 0 0x1000>; mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x5000 0x1000>; @@ -1822,6 +1703,7 @@ mdp3-wrot0@14005000 { power-domains = <&spm MT8183_POWER_DOMAIN_DISP>; clocks = <&mmsys CLK_MM_MDP_WROT0>; iommus = <&iommu M4U_PORT_MDP_WROT0>; + #dma-cells = <1>; }; mdp3-wdma@14006000 { @@ -2105,4 +1987,125 @@ larb3: larb@1a002000 { power-domains = <&spm MT8183_POWER_DOMAIN_CAM>; }; }; + + thermal_zones: thermal-zones { + cpu_thermal: cpu-thermal { + polling-delay-passive = <100>; + polling-delay = <500>; + thermal-sensors = <&thermal 0>; + sustainable-power = <5000>; + + trips { + threshold: trip-point0 { + temperature = <68000>; + hysteresis = <2000>; + type = "passive"; + }; + + target: trip-point1 { + temperature = <80000>; + hysteresis = <2000>; + type = "passive"; + }; + + cpu_crit: cpu-crit { + temperature = <115000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + + cooling-maps { + map0 { + trip = <&target>; + cooling-device = <&cpu0 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>, + <&cpu1 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>, + <&cpu2 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>, + <&cpu3 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>; + contribution = <3072>; + }; + map1 { + trip = <&target>; + cooling-device = <&cpu4 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>, + <&cpu5 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>, + <&cpu6 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>, + <&cpu7 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>; + contribution = <1024>; + }; + }; + }; + + /* The tzts1 ~ tzts6 don't need to polling */ + /* The tzts1 ~ tzts6 don't need to thermal throttle */ + + tzts1: tzts1 { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 1>; + sustainable-power = <5000>; + trips {}; + cooling-maps {}; + }; + + tzts2: tzts2 { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 2>; + sustainable-power = <5000>; + trips {}; + cooling-maps {}; + }; + + tzts3: tzts3 { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 3>; + sustainable-power = <5000>; + trips {}; + cooling-maps {}; + }; + + tzts4: tzts4 { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 4>; + sustainable-power = <5000>; + trips {}; + cooling-maps {}; + }; + + tzts5: tzts5 { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 5>; + sustainable-power = <5000>; + trips {}; + cooling-maps {}; + }; + + tztsABB: tztsABB { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 6>; + sustainable-power = <5000>; + trips {}; + cooling-maps {}; + }; + }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8186.dtsi b/arch/arm64/boot/dts/mediatek/mt8186.dtsi index f04ae70c470aa3..2c184f9e0fc390 100644 --- a/arch/arm64/boot/dts/mediatek/mt8186.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8186.dtsi @@ -22,7 +22,7 @@ / { aliases { ovl0 = &ovl0; - ovl_2l0 = &ovl_2l0; + ovl-2l0 = &ovl_2l0; rdma0 = &rdma0; rdma1 = &rdma1; }; @@ -731,7 +731,7 @@ opp-850000000 { opp-900000000-3 { opp-hz = /bits/ 64 <900000000>; opp-microvolt = <850000>; - opp-supported-hw = <0x8>; + opp-supported-hw = <0xcf>; }; opp-900000000-4 { @@ -743,13 +743,13 @@ opp-900000000-4 { opp-900000000-5 { opp-hz = /bits/ 64 <900000000>; opp-microvolt = <825000>; - opp-supported-hw = <0x30>; + opp-supported-hw = <0x20>; }; opp-950000000-3 { opp-hz = /bits/ 64 <950000000>; opp-microvolt = <900000>; - opp-supported-hw = <0x8>; + opp-supported-hw = <0xcf>; }; opp-950000000-4 { @@ -761,13 +761,13 @@ opp-950000000-4 { opp-950000000-5 { opp-hz = /bits/ 64 <950000000>; opp-microvolt = <850000>; - opp-supported-hw = <0x30>; + opp-supported-hw = <0x20>; }; opp-1000000000-3 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <950000>; - opp-supported-hw = <0x8>; + opp-supported-hw = <0xcf>; }; opp-1000000000-4 { @@ -779,7 +779,7 @@ opp-1000000000-4 { opp-1000000000-5 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <875000>; - opp-supported-hw = <0x30>; + opp-supported-hw = <0x20>; }; }; @@ -924,17 +924,24 @@ power-domain@MT8186_POWER_DOMAIN_CSIRX_TOP { reg = ; clocks = <&topckgen CLK_TOP_SENINF>, <&topckgen CLK_TOP_SENINF1>; - clock-names = "csirx_top0", "csirx_top1"; + clock-names = "subsys-csirx-top0", + "subsys-csirx-top1"; #power-domain-cells = <0>; }; power-domain@MT8186_POWER_DOMAIN_SSUSB { reg = ; + clocks = <&topckgen CLK_TOP_USB_TOP>, + <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_REF>; + clock-names = "sys_ck", "ref_ck"; #power-domain-cells = <0>; }; power-domain@MT8186_POWER_DOMAIN_SSUSB_P1 { reg = ; + clocks = <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_SYS>, + <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_REF>; + clock-names = "sys_ck", "ref_ck"; #power-domain-cells = <0>; }; @@ -942,7 +949,8 @@ power-domain@MT8186_POWER_DOMAIN_ADSP_AO { reg = ; clocks = <&topckgen CLK_TOP_AUDIODSP>, <&topckgen CLK_TOP_ADSP_BUS>; - clock-names = "audioadsp", "adsp_bus"; + clock-names = "audioadsp", + "subsys-adsp-bus"; #address-cells = <1>; #size-cells = <0>; #power-domain-cells = <1>; @@ -975,8 +983,11 @@ power-domain@MT8186_POWER_DOMAIN_DIS { <&mmsys CLK_MM_SMI_COMMON>, <&mmsys CLK_MM_SMI_GALS>, <&mmsys CLK_MM_SMI_IOMMU>; - clock-names = "disp", "mdp", "smi_infra", "smi_common", - "smi_gals", "smi_iommu"; + clock-names = "disp", "mdp", + "subsys-smi-infra", + "subsys-smi-common", + "subsys-smi-gals", + "subsys-smi-iommu"; mediatek,infracfg = <&infracfg_ao>; #address-cells = <1>; #size-cells = <0>; @@ -993,15 +1004,17 @@ power-domain@MT8186_POWER_DOMAIN_VDEC { power-domain@MT8186_POWER_DOMAIN_CAM { reg = ; - clocks = <&topckgen CLK_TOP_CAM>, - <&topckgen CLK_TOP_SENINF>, + clocks = <&topckgen CLK_TOP_SENINF>, <&topckgen CLK_TOP_SENINF1>, <&topckgen CLK_TOP_SENINF2>, <&topckgen CLK_TOP_SENINF3>, + <&camsys CLK_CAM2MM_GALS>, <&topckgen CLK_TOP_CAMTM>, - <&camsys CLK_CAM2MM_GALS>; - clock-names = "cam-top", "cam0", "cam1", "cam2", - "cam3", "cam-tm", "gals"; + <&topckgen CLK_TOP_CAM>; + clock-names = "cam0", "cam1", "cam2", + "cam3", "gals", + "subsys-cam-tm", + "subsys-cam-top"; mediatek,infracfg = <&infracfg_ao>; #address-cells = <1>; #size-cells = <0>; @@ -1020,9 +1033,9 @@ power-domain@MT8186_POWER_DOMAIN_CAM_RAWA { power-domain@MT8186_POWER_DOMAIN_IMG { reg = ; - clocks = <&topckgen CLK_TOP_IMG1>, - <&imgsys1 CLK_IMG1_GALS_IMG1>; - clock-names = "img-top", "gals"; + clocks = <&imgsys1 CLK_IMG1_GALS_IMG1>, + <&topckgen CLK_TOP_IMG1>; + clock-names = "gals", "subsys-img-top"; mediatek,infracfg = <&infracfg_ao>; #address-cells = <1>; #size-cells = <0>; @@ -1041,8 +1054,11 @@ power-domain@MT8186_POWER_DOMAIN_IPE { <&ipesys CLK_IPE_LARB20>, <&ipesys CLK_IPE_SMI_SUBCOM>, <&ipesys CLK_IPE_GALS_IPE>; - clock-names = "ipe-top", "ipe-larb0", "ipe-larb1", - "ipe-smi", "ipe-gals"; + clock-names = "subsys-ipe-top", + "subsys-ipe-larb0", + "subsys-ipe-larb1", + "subsys-ipe-smi", + "subsys-ipe-gals"; mediatek,infracfg = <&infracfg_ao>; #power-domain-cells = <0>; }; @@ -1051,7 +1067,7 @@ power-domain@MT8186_POWER_DOMAIN_VENC { reg = ; clocks = <&topckgen CLK_TOP_VENC>, <&vencsys CLK_VENC_CKE1_VENC>; - clock-names = "venc0", "larb"; + clock-names = "venc0", "subsys-larb"; mediatek,infracfg = <&infracfg_ao>; #power-domain-cells = <0>; }; @@ -1061,7 +1077,9 @@ power-domain@MT8186_POWER_DOMAIN_WPE { clocks = <&topckgen CLK_TOP_WPE>, <&wpesys CLK_WPE_SMI_LARB8_CK_EN>, <&wpesys CLK_WPE_SMI_LARB8_PCLK_EN>; - clock-names = "wpe0", "larb-ck", "larb-pclk"; + clock-names = "wpe0", + "subsys-larb-ck", + "subsys-larb-pclk"; mediatek,infracfg = <&infracfg_ao>; #power-domain-cells = <0>; }; @@ -1148,14 +1166,14 @@ adsp: adsp@10680000 { status = "disabled"; }; - adsp_mailbox0: mailbox@10686000 { + adsp_mailbox0: mailbox@10686100 { compatible = "mediatek,mt8186-adsp-mbox"; #mbox-cells = <0>; reg = <0 0x10686100 0 0x1000>; interrupts = ; }; - adsp_mailbox1: mailbox@10687000 { + adsp_mailbox1: mailbox@10687100 { compatible = "mediatek,mt8186-adsp-mbox"; #mbox-cells = <0>; reg = <0 0x10687100 0 0x1000>; @@ -1518,8 +1536,9 @@ ssusb0: usb@11201000 { clocks = <&topckgen CLK_TOP_USB_TOP>, <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_REF>, <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_HCLK>, - <&infracfg_ao CLK_INFRA_AO_ICUSB>; - clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck"; + <&infracfg_ao CLK_INFRA_AO_ICUSB>, + <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_XHCI>; + clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck", "xhci_ck"; interrupts = ; phys = <&u2port0 PHY_TYPE_USB2>; power-domains = <&spm MT8186_POWER_DOMAIN_SSUSB>; @@ -1583,8 +1602,9 @@ ssusb1: usb@11281000 { clocks = <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_SYS>, <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_REF>, <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_HCLK>, - <&clk26m>; - clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck"; + <&clk26m>, + <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_XHCI>; + clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck", "xhci_ck"; interrupts = ; phys = <&u2port1 PHY_TYPE_USB2>, <&u3port1 PHY_TYPE_USB3>; power-domains = <&spm MT8186_POWER_DOMAIN_SSUSB_P1>; @@ -1656,7 +1676,7 @@ efuse: efuse@11cb0000 { #address-cells = <1>; #size-cells = <1>; - gpu_speedbin: gpu-speed-bin@59c { + gpu_speedbin: gpu-speedbin@59c { reg = <0x59c 0x4>; bits = <0 3>; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi index 0e8b341170907d..6b4b7a7cd35efb 100644 --- a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi @@ -147,6 +147,7 @@ pp3300_mipibrdg: regulator-3v3-mipibrdg { regulator-boot-on; gpio = <&pio 127 GPIO_ACTIVE_HIGH>; vin-supply = <&pp3300_g>; + off-on-delay-us = <500000>; }; /* separately switched 3.3V power rail */ @@ -1308,10 +1309,6 @@ cros_ec: ec@0 { #address-cells = <1>; #size-cells = <0>; - base_detection: cbas { - compatible = "google,cros-cbas"; - }; - cros_ec_pwm: pwm { compatible = "google,cros-ec-pwm"; #pwm-cells = <1>; @@ -1396,7 +1393,7 @@ regulators { mt6315_6_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vbcpu"; - regulator-min-microvolt = <300000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-allowed-modes = <0 1 2>; @@ -1406,7 +1403,7 @@ mt6315_6_vbuck1: vbuck1 { mt6315_6_vbuck3: vbuck3 { regulator-compatible = "vbuck3"; regulator-name = "Vlcpu"; - regulator-min-microvolt = <300000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-allowed-modes = <0 1 2>; @@ -1423,7 +1420,7 @@ regulators { mt6315_7_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vgpu"; - regulator-min-microvolt = <606250>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <800000>; regulator-enable-ramp-delay = <256>; regulator-allowed-modes = <0 1 2>; diff --git a/arch/arm64/boot/dts/mediatek/mt8192.dtsi b/arch/arm64/boot/dts/mediatek/mt8192.dtsi index 69f4cded5dbbf2..b1443adc55aab5 100644 --- a/arch/arm64/boot/dts/mediatek/mt8192.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8192.dtsi @@ -1412,6 +1412,7 @@ mutex: mutex@14001000 { reg = <0 0x14001000 0 0x1000>; interrupts = ; clocks = <&mmsys CLK_MM_DISP_MUTEX0>; + mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>; mediatek,gce-events = , ; power-domains = <&spm MT8192_POWER_DOMAIN_DISP>; @@ -1770,7 +1771,7 @@ vcodec_enc: vcodec@17020000 { mediatek,scp = <&scp>; power-domains = <&spm MT8192_POWER_DOMAIN_VENC>; clocks = <&vencsys CLK_VENC_SET1_VENC>; - clock-names = "venc-set1"; + clock-names = "venc_sel"; assigned-clocks = <&topckgen CLK_TOP_VENC_SEL>; assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D4>; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts index 2d5e8f371b6def..a82d716f10d449 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts @@ -23,3 +23,7 @@ &sound { &ts_10 { status = "okay"; }; + +&watchdog { + /delete-property/ mediatek,disable-extrst; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts index 2586c32ce6e6fe..2fe20e0dad836d 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts @@ -43,3 +43,7 @@ &sound { &ts_10 { status = "okay"; }; + +&watchdog { + /delete-property/ mediatek,disable-extrst; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts index f54f9477b99dad..dd294ca98194cc 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts @@ -44,3 +44,7 @@ &sound { &ts_10 { status = "okay"; }; + +&watchdog { + /delete-property/ mediatek,disable-extrst; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi index 37a3e9de90ff70..34e18eb5d7f450 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi @@ -114,6 +114,77 @@ ppvar_sys: regulator-ppvar-sys { regulator-boot-on; }; + /* Murata NCP03WF104F05RL */ + tboard_thermistor1: thermal-sensor-t1 { + compatible = "generic-adc-thermal"; + #thermal-sensor-cells = <0>; + io-channels = <&auxadc 0>; + io-channel-names = "sensor-channel"; + temperature-lookup-table = < (-10000) 1553 + (-5000) 1485 + 0 1406 + 5000 1317 + 10000 1219 + 15000 1115 + 20000 1007 + 25000 900 + 30000 796 + 35000 697 + 40000 605 + 45000 523 + 50000 449 + 55000 384 + 60000 327 + 65000 279 + 70000 237 + 75000 202 + 80000 172 + 85000 147 + 90000 125 + 95000 107 + 100000 92 + 105000 79 + 110000 68 + 115000 59 + 120000 51 + 125000 44>; + }; + + tboard_thermistor2: thermal-sensor-t2 { + compatible = "generic-adc-thermal"; + #thermal-sensor-cells = <0>; + io-channels = <&auxadc 1>; + io-channel-names = "sensor-channel"; + temperature-lookup-table = < (-10000) 1553 + (-5000) 1485 + 0 1406 + 5000 1317 + 10000 1219 + 15000 1115 + 20000 1007 + 25000 900 + 30000 796 + 35000 697 + 40000 605 + 45000 523 + 50000 449 + 55000 384 + 60000 327 + 65000 279 + 70000 237 + 75000 202 + 80000 172 + 85000 147 + 90000 125 + 95000 107 + 100000 92 + 105000 79 + 110000 68 + 115000 59 + 120000 51 + 125000 44>; + }; + usb_vbus: regulator-5v0-usb-vbus { compatible = "regulator-fixed"; regulator-name = "usb-vbus"; @@ -176,6 +247,42 @@ &afe { memory-region = <&afe_mem>; }; +&auxadc { + status = "okay"; +}; + +&cpu0 { + cpu-supply = <&mt6359_vcore_buck_reg>; +}; + +&cpu1 { + cpu-supply = <&mt6359_vcore_buck_reg>; +}; + +&cpu2 { + cpu-supply = <&mt6359_vcore_buck_reg>; +}; + +&cpu3 { + cpu-supply = <&mt6359_vcore_buck_reg>; +}; + +&cpu4 { + cpu-supply = <&mt6315_6_vbuck1>; +}; + +&cpu5 { + cpu-supply = <&mt6315_6_vbuck1>; +}; + +&cpu6 { + cpu-supply = <&mt6315_6_vbuck1>; +}; + +&cpu7 { + cpu-supply = <&mt6315_6_vbuck1>; +}; + &dp_intf0 { status = "okay"; @@ -362,7 +469,7 @@ &i2c7 { pinctrl-0 = <&i2c7_pins>; pmic@34 { - #interrupt-cells = <1>; + #interrupt-cells = <2>; compatible = "mediatek,mt6360"; reg = <0x34>; interrupt-controller; @@ -1098,7 +1205,7 @@ regulators { mt6315_6_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vbcpu"; - regulator-min-microvolt = <300000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-ramp-delay = <6250>; @@ -1116,7 +1223,7 @@ regulators { mt6315_7_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vgpu"; - regulator-min-microvolt = <625000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-ramp-delay = <6250>; @@ -1127,6 +1234,36 @@ mt6315_7_vbuck1: vbuck1 { }; }; +&thermal_zones { + soc-area-thermal { + polling-delay = <1000>; + polling-delay-passive = <250>; + thermal-sensors = <&tboard_thermistor1>; + + trips { + trip-crit { + temperature = <84000>; + hysteresis = <1000>; + type = "critical"; + }; + }; + }; + + pmic-area-thermal { + polling-delay = <1000>; + polling-delay-passive = <0>; + thermal-sensors = <&tboard_thermistor2>; + + trips { + trip-crit { + temperature = <84000>; + hysteresis = <1000>; + type = "critical"; + }; + }; + }; +}; + &u3phy0 { status = "okay"; }; @@ -1175,6 +1312,7 @@ &xhci3 { usb2-lpm-disable; vusb33-supply = <&mt6359_vusb_ldo_reg>; vbus-supply = <&usb_vbus>; + mediatek,u3p-dis-msk = <1>; }; #include diff --git a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts index 5d635085fe3fd0..9079e48aea23ea 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts +++ b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts @@ -128,6 +128,7 @@ mt6360: pmic@34 { compatible = "mediatek,mt6360"; reg = <0x34>; interrupt-controller; + #interrupt-cells = <1>; interrupts-extended = <&pio 101 IRQ_TYPE_EDGE_FALLING>; interrupt-names = "IRQB"; diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi index 54c674c45b49a2..d21ba00a5bd5df 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi @@ -627,6 +627,8 @@ power-domain@MT8195_POWER_DOMAIN_VDEC1 { power-domain@MT8195_POWER_DOMAIN_VENC_CORE1 { reg = ; + clocks = <&vencsys_core1 CLK_VENC_CORE1_LARB>; + clock-names = "venc1-larb"; mediatek,infracfg = <&infracfg_ao>; #power-domain-cells = <0>; }; @@ -689,6 +691,8 @@ power-domain@MT8195_POWER_DOMAIN_VDEC2 { power-domain@MT8195_POWER_DOMAIN_VENC { reg = ; + clocks = <&vencsys CLK_VENC_LARB>; + clock-names = "venc0-larb"; mediatek,infracfg = <&infracfg_ao>; #power-domain-cells = <0>; }; @@ -1959,6 +1963,7 @@ vppsys0: syscon@14000000 { compatible = "mediatek,mt8195-vppsys0", "syscon"; reg = <0 0x14000000 0 0x1000>; #clock-cells = <1>; + mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0 0x1000>; }; mutex@1400f000 { @@ -2073,6 +2078,7 @@ vppsys1: syscon@14f00000 { compatible = "mediatek,mt8195-vppsys1", "syscon"; reg = <0 0x14f00000 0 0x1000>; #clock-cells = <1>; + mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0 0x1000>; }; mutex@14f01000 { @@ -2619,6 +2625,7 @@ vdosys0: syscon@1c01a000 { reg = <0 0x1c01a000 0 0x1000>; mboxes = <&gce0 0 CMDQ_THR_PRIO_4>; #clock-cells = <1>; + mediatek,gce-client-reg = <&gce0 SUBSYS_1c01XXXX 0xa000 0x1000>; }; @@ -2665,7 +2672,7 @@ larb20: larb@1b010000 { reg = <0 0x1b010000 0 0x1000>; mediatek,larb-id = <20>; mediatek,smi = <&smi_common_vpp>; - clocks = <&vencsys_core1 CLK_VENC_CORE1_LARB>, + clocks = <&vencsys_core1 CLK_VENC_CORE1_VENC>, <&vencsys_core1 CLK_VENC_CORE1_GALS>, <&vppsys0 CLK_VPP0_GALS_VDO0_VDO1_VENCSYS_CORE1>; clock-names = "apb", "smi", "gals"; @@ -2759,10 +2766,10 @@ dp_intf0: dp-intf@1c015000 { compatible = "mediatek,mt8195-dp-intf"; reg = <0 0x1c015000 0 0x1000>; interrupts = ; - clocks = <&vdosys0 CLK_VDO0_DP_INTF0>, - <&vdosys0 CLK_VDO0_DP_INTF0_DP_INTF>, + clocks = <&vdosys0 CLK_VDO0_DP_INTF0_DP_INTF>, + <&vdosys0 CLK_VDO0_DP_INTF0>, <&apmixedsys CLK_APMIXED_TVDPLL1>; - clock-names = "engine", "pixel", "pll"; + clock-names = "pixel", "engine", "pll"; status = "disabled"; }; @@ -2772,6 +2779,7 @@ mutex: mutex@1c016000 { interrupts = ; power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS0>; clocks = <&vdosys0 CLK_VDO0_DISP_MUTEX0>; + mediatek,gce-client-reg = <&gce0 SUBSYS_1c01XXXX 0x6000 0x1000>; mediatek,gce-events = ; }; @@ -2842,6 +2850,7 @@ mutex1: mutex@1c101000 { power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; clocks = <&vdosys1 CLK_VDO1_DISP_MUTEX>; clock-names = "vdo1_mutex"; + mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x1000 0x1000>; mediatek,gce-events = ; }; @@ -2869,7 +2878,7 @@ larb3: larb@1c103000 { power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; }; - vdo1_rdma0: rdma@1c104000 { + vdo1_rdma0: dma-controller@1c104000 { compatible = "mediatek,mt8195-vdo1-rdma"; reg = <0 0x1c104000 0 0x1000>; interrupts = ; @@ -2877,9 +2886,10 @@ vdo1_rdma0: rdma@1c104000 { power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; iommus = <&iommu_vdo M4U_PORT_L2_MDP_RDMA0>; mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x4000 0x1000>; + #dma-cells = <1>; }; - vdo1_rdma1: rdma@1c105000 { + vdo1_rdma1: dma-controller@1c105000 { compatible = "mediatek,mt8195-vdo1-rdma"; reg = <0 0x1c105000 0 0x1000>; interrupts = ; @@ -2887,9 +2897,10 @@ vdo1_rdma1: rdma@1c105000 { power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; iommus = <&iommu_vpp M4U_PORT_L3_MDP_RDMA1>; mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x5000 0x1000>; + #dma-cells = <1>; }; - vdo1_rdma2: rdma@1c106000 { + vdo1_rdma2: dma-controller@1c106000 { compatible = "mediatek,mt8195-vdo1-rdma"; reg = <0 0x1c106000 0 0x1000>; interrupts = ; @@ -2897,9 +2908,10 @@ vdo1_rdma2: rdma@1c106000 { power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; iommus = <&iommu_vdo M4U_PORT_L2_MDP_RDMA2>; mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x6000 0x1000>; + #dma-cells = <1>; }; - vdo1_rdma3: rdma@1c107000 { + vdo1_rdma3: dma-controller@1c107000 { compatible = "mediatek,mt8195-vdo1-rdma"; reg = <0 0x1c107000 0 0x1000>; interrupts = ; @@ -2907,9 +2919,10 @@ vdo1_rdma3: rdma@1c107000 { power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; iommus = <&iommu_vpp M4U_PORT_L3_MDP_RDMA3>; mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x7000 0x1000>; + #dma-cells = <1>; }; - vdo1_rdma4: rdma@1c108000 { + vdo1_rdma4: dma-controller@1c108000 { compatible = "mediatek,mt8195-vdo1-rdma"; reg = <0 0x1c108000 0 0x1000>; interrupts = ; @@ -2917,9 +2930,10 @@ vdo1_rdma4: rdma@1c108000 { power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; iommus = <&iommu_vdo M4U_PORT_L2_MDP_RDMA4>; mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x8000 0x1000>; + #dma-cells = <1>; }; - vdo1_rdma5: rdma@1c109000 { + vdo1_rdma5: dma-controller@1c109000 { compatible = "mediatek,mt8195-vdo1-rdma"; reg = <0 0x1c109000 0 0x1000>; interrupts = ; @@ -2927,9 +2941,10 @@ vdo1_rdma5: rdma@1c109000 { power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; iommus = <&iommu_vpp M4U_PORT_L3_MDP_RDMA5>; mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x9000 0x1000>; + #dma-cells = <1>; }; - vdo1_rdma6: rdma@1c10a000 { + vdo1_rdma6: dma-controller@1c10a000 { compatible = "mediatek,mt8195-vdo1-rdma"; reg = <0 0x1c10a000 0 0x1000>; interrupts = ; @@ -2937,9 +2952,10 @@ vdo1_rdma6: rdma@1c10a000 { power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; iommus = <&iommu_vdo M4U_PORT_L2_MDP_RDMA6>; mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xa000 0x1000>; + #dma-cells = <1>; }; - vdo1_rdma7: rdma@1c10b000 { + vdo1_rdma7: dma-controller@1c10b000 { compatible = "mediatek,mt8195-vdo1-rdma"; reg = <0 0x1c10b000 0 0x1000>; interrupts = ; @@ -2947,6 +2963,7 @@ vdo1_rdma7: rdma@1c10b000 { power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; iommus = <&iommu_vpp M4U_PORT_L3_MDP_RDMA7>; mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xb000 0x1000>; + #dma-cells = <1>; }; merge1: vpp-merge@1c10c000 { @@ -3019,10 +3036,10 @@ dp_intf1: dp-intf@1c113000 { reg = <0 0x1c113000 0 0x1000>; interrupts = ; power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; - clocks = <&vdosys1 CLK_VDO1_DP_INTF0_MM>, - <&vdosys1 CLK_VDO1_DPINTF>, + clocks = <&vdosys1 CLK_VDO1_DPINTF>, + <&vdosys1 CLK_VDO1_DP_INTF0_MM>, <&apmixedsys CLK_APMIXED_TVDPLL2>; - clock-names = "engine", "pixel", "pll"; + clock-names = "pixel", "engine", "pll"; status = "disabled"; }; @@ -3378,7 +3395,7 @@ vpu1_crit: trip-crit { }; }; - gpu0-thermal { + gpu-thermal { polling-delay = <1000>; polling-delay-passive = <250>; thermal-sensors = <&lvts_ap MT8195_AP_GPU0>; diff --git a/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts b/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts index bbc2e9bef08da5..441216eda487f8 100644 --- a/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts +++ b/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts @@ -9,8 +9,8 @@ / { compatible = "nvidia,norrin", "nvidia,tegra132", "nvidia,tegra124"; aliases { - rtc0 = "/i2c@7000d000/as3722@40"; - rtc1 = "/rtc@7000e000"; + rtc0 = &as3722; + rtc1 = &tegra_rtc; serial0 = &uarta; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra132.dtsi b/arch/arm64/boot/dts/nvidia/tegra132.dtsi index 8b78be8f4f9d0b..4b5435f5832344 100644 --- a/arch/arm64/boot/dts/nvidia/tegra132.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra132.dtsi @@ -570,7 +570,7 @@ spi@7000de00 { status = "disabled"; }; - rtc@7000e000 { + tegra_rtc: rtc@7000e000 { compatible = "nvidia,tegra124-rtc", "nvidia,tegra20-rtc"; reg = <0x0 0x7000e000 0x0 0x100>; interrupts = ; diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts index 4413a9b6da87a2..bf2ccc8ff93c4b 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts @@ -174,7 +174,7 @@ ethernet@6800000 { status = "okay"; phy-handle = <&mgbe0_phy>; - phy-mode = "usxgmii"; + phy-mode = "10gbase-r"; mdio { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3767.dtsi b/arch/arm64/boot/dts/nvidia/tegra234-p3767.dtsi index 5f592f1d81e2ee..fe08e131b7b9ef 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234-p3767.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra234-p3767.dtsi @@ -28,7 +28,7 @@ spi@3270000 { flash@0 { compatible = "jedec,spi-nor"; reg = <0>; - spi-max-frequency = <136000000>; + spi-max-frequency = <102000000>; spi-tx-bus-width = <4>; spi-rx-bus-width = <4>; }; @@ -42,7 +42,7 @@ flash@0 { mmc@3400000 { status = "okay"; bus-width = <4>; - cd-gpios = <&gpio TEGRA234_MAIN_GPIO(G, 7) GPIO_ACTIVE_HIGH>; + cd-gpios = <&gpio TEGRA234_MAIN_GPIO(G, 7) GPIO_ACTIVE_LOW>; disable-wp; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi index 95524e5bce8262..ac69eacf8a6ba9 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi @@ -43,12 +43,12 @@ timer@2080000 { , , , - , - , - , - , - , - ; + , + , + , + , + , + ; status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/apq8016-sbc.dts b/arch/arm64/boot/dts/qcom/apq8016-sbc.dts index 4f5541e9be0e98..dabe9f42a63ade 100644 --- a/arch/arm64/boot/dts/qcom/apq8016-sbc.dts +++ b/arch/arm64/boot/dts/qcom/apq8016-sbc.dts @@ -172,6 +172,9 @@ adv_bridge: bridge@39 { pd-gpios = <&tlmm 32 GPIO_ACTIVE_HIGH>; avdd-supply = <&pm8916_l6>; + a2vdd-supply = <&pm8916_l6>; + dvdd-supply = <&pm8916_l6>; + pvdd-supply = <&pm8916_l6>; v1p2-supply = <&pm8916_l6>; v3p3-supply = <&pm8916_l17>; diff --git a/arch/arm64/boot/dts/qcom/ipq5332.dtsi b/arch/arm64/boot/dts/qcom/ipq5332.dtsi index 8bfc2db44624af..e40c55adff23d1 100644 --- a/arch/arm64/boot/dts/qcom/ipq5332.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq5332.dtsi @@ -135,7 +135,7 @@ smem@4a800000 { reg = <0x0 0x4a800000 0x0 0x100000>; no-map; - hwlocks = <&tcsr_mutex 0>; + hwlocks = <&tcsr_mutex 3>; }; }; diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi index 47b8b1d6730ac6..fea16f3271c007 100644 --- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi @@ -211,7 +211,7 @@ q6_region: memory@4ab00000 { smem { compatible = "qcom,smem"; memory-region = <&smem_region>; - hwlocks = <&tcsr_mutex 0>; + hwlocks = <&tcsr_mutex 3>; }; soc: soc@0 { @@ -393,7 +393,7 @@ gcc: gcc@1800000 { tcsr_mutex: hwlock@1905000 { compatible = "qcom,ipq6018-tcsr-mutex", "qcom,tcsr-mutex"; - reg = <0x0 0x01905000 0x0 0x1000>; + reg = <0x0 0x01905000 0x0 0x20000>; #hwlock-cells = <1>; }; @@ -565,7 +565,7 @@ usb3: usb@8af8800 { <&gcc GCC_USB0_MOCK_UTMI_CLK>; assigned-clock-rates = <133330000>, <133330000>, - <20000000>; + <24000000>; resets = <&gcc GCC_USB0_BCR>; status = "disabled"; @@ -579,6 +579,7 @@ dwc_0: usb@8a00000 { clocks = <&xo>; clock-names = "ref"; tx-fifo-resize; + snps,parkmode-disable-ss-quirk; snps,is-utmi-l1-suspend; snps,hird-threshold = /bits/ 8 <0x0>; snps,dis_u2_susphy_quirk; @@ -767,10 +768,10 @@ pcie0: pci@20000000 { #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; - interrupt-map = <0 0 0 1 &intc 0 75 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ - <0 0 0 2 &intc 0 78 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ - <0 0 0 3 &intc 0 79 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ - <0 0 0 4 &intc 0 83 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ + interrupt-map = <0 0 0 1 &intc 0 0 0 75 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ + <0 0 0 2 &intc 0 0 0 78 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ + <0 0 0 3 &intc 0 0 0 79 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ + <0 0 0 4 &intc 0 0 0 83 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ clocks = <&gcc GCC_SYS_NOC_PCIE0_AXI_CLK>, <&gcc GCC_PCIE0_AXI_M_CLK>, diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index 00ed71936b4723..e5993a365870c1 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -101,7 +101,7 @@ smem@4ab00000 { reg = <0x0 0x4ab00000 0x0 0x100000>; no-map; - hwlocks = <&tcsr_mutex 0>; + hwlocks = <&tcsr_mutex 3>; }; memory@4ac00000 { @@ -641,6 +641,7 @@ dwc_0: usb@8a00000 { interrupts = ; phys = <&qusb_phy_0>, <&usb0_ssphy>; phy-names = "usb2-phy", "usb3-phy"; + snps,parkmode-disable-ss-quirk; snps,is-utmi-l1-suspend; snps,hird-threshold = /bits/ 8 <0x0>; snps,dis_u2_susphy_quirk; @@ -683,6 +684,7 @@ dwc_1: usb@8c00000 { interrupts = ; phys = <&qusb_phy_1>, <&usb1_ssphy>; phy-names = "usb2-phy", "usb3-phy"; + snps,parkmode-disable-ss-quirk; snps,is-utmi-l1-suspend; snps,hird-threshold = /bits/ 8 <0x0>; snps,dis_u2_susphy_quirk; @@ -817,13 +819,13 @@ pcie1: pci@10000000 { interrupt-names = "msi"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; - interrupt-map = <0 0 0 1 &intc 0 142 + interrupt-map = <0 0 0 1 &intc 0 0 142 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ - <0 0 0 2 &intc 0 143 + <0 0 0 2 &intc 0 0 143 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ - <0 0 0 3 &intc 0 144 + <0 0 0 3 &intc 0 0 144 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ - <0 0 0 4 &intc 0 145 + <0 0 0 4 &intc 0 0 145 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ clocks = <&gcc GCC_SYS_NOC_PCIE1_AXI_CLK>, @@ -879,13 +881,13 @@ pcie0: pci@20000000 { interrupt-names = "msi"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; - interrupt-map = <0 0 0 1 &intc 0 75 + interrupt-map = <0 0 0 1 &intc 0 0 75 IRQ_TYPE_LEVEL_HIGH>, /* int_a */ - <0 0 0 2 &intc 0 78 + <0 0 0 2 &intc 0 0 78 IRQ_TYPE_LEVEL_HIGH>, /* int_b */ - <0 0 0 3 &intc 0 79 + <0 0 0 3 &intc 0 0 79 IRQ_TYPE_LEVEL_HIGH>, /* int_c */ - <0 0 0 4 &intc 0 83 + <0 0 0 4 &intc 0 0 83 IRQ_TYPE_LEVEL_HIGH>; /* int_d */ clocks = <&gcc GCC_SYS_NOC_PCIE0_AXI_CLK>, diff --git a/arch/arm64/boot/dts/qcom/ipq9574.dtsi b/arch/arm64/boot/dts/qcom/ipq9574.dtsi index 51aba071c1eb30..8a72ad4afd0320 100644 --- a/arch/arm64/boot/dts/qcom/ipq9574.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq9574.dtsi @@ -195,7 +195,7 @@ tz_region: tz@4a600000 { smem@4aa00000 { compatible = "qcom,smem"; reg = <0x0 0x4aa00000 0x0 0x100000>; - hwlocks = <&tcsr_mutex 0>; + hwlocks = <&tcsr_mutex 3>; no-map; }; }; diff --git a/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8150.dts b/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8150.dts index 3892ad4f639a8f..4efc534b1d6e74 100644 --- a/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8150.dts +++ b/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8150.dts @@ -88,6 +88,7 @@ led-controller@45 { #size-cells = <0>; vcc-supply = <&pm8916_l17>; + vio-supply = <&pm8916_l6>; led@0 { reg = <0>; diff --git a/arch/arm64/boot/dts/qcom/msm8916-wingtech-wt88047.dts b/arch/arm64/boot/dts/qcom/msm8916-wingtech-wt88047.dts index 8e238976ab1cef..43078b890d8605 100644 --- a/arch/arm64/boot/dts/qcom/msm8916-wingtech-wt88047.dts +++ b/arch/arm64/boot/dts/qcom/msm8916-wingtech-wt88047.dts @@ -118,6 +118,7 @@ led-controller@45 { #size-cells = <0>; vcc-supply = <&pm8916_l16>; + vio-supply = <&pm8916_l5>; led@0 { reg = <0>; diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi index 33fb65d7310461..961ceb83a91fae 100644 --- a/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -1813,7 +1813,7 @@ apps_iommu: iommu@1ef0000 { #size-cells = <1>; #iommu-cells = <1>; compatible = "qcom,msm8916-iommu", "qcom,msm-iommu-v1"; - ranges = <0 0x01e20000 0x40000>; + ranges = <0 0x01e20000 0x20000>; reg = <0x01ef0000 0x3000>; clocks = <&gcc GCC_SMMU_CFG_CLK>, <&gcc GCC_APSS_TCU_CLK>; @@ -2085,6 +2085,7 @@ blsp_dma: dma-controller@7884000 { clock-names = "bam_clk"; #dma-cells = <1>; qcom,ee = <0>; + qcom,controlled-remotely; }; blsp_uart1: serial@78af000 { diff --git a/arch/arm64/boot/dts/qcom/msm8939.dtsi b/arch/arm64/boot/dts/qcom/msm8939.dtsi index 6e24f0f2374fe5..3fd64cafe99c5f 100644 --- a/arch/arm64/boot/dts/qcom/msm8939.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8939.dtsi @@ -1447,7 +1447,7 @@ opp-19200000 { apps_iommu: iommu@1ef0000 { compatible = "qcom,msm8916-iommu", "qcom,msm-iommu-v1"; reg = <0x01ef0000 0x3000>; - ranges = <0 0x01e20000 0x40000>; + ranges = <0 0x01e20000 0x20000>; clocks = <&gcc GCC_SMMU_CFG_CLK>, <&gcc GCC_APSS_TCU_CLK>; clock-names = "iface", "bus"; @@ -1661,6 +1661,7 @@ blsp_dma: dma-controller@7884000 { clock-names = "bam_clk"; #dma-cells = <1>; qcom,ee = <0>; + qcom,controlled-remotely; }; blsp_uart1: serial@78af000 { diff --git a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-mido.dts b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-mido.dts index ed95d09cedb1e3..6b9245cd8b0c3f 100644 --- a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-mido.dts +++ b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-mido.dts @@ -111,6 +111,7 @@ led-controller@45 { reg = <0x45>; vcc-supply = <&pm8953_l10>; + vio-supply = <&pm8953_l5>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-tissot.dts b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-tissot.dts index 61ff629c9bf345..9ac4f507e321a6 100644 --- a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-tissot.dts +++ b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-tissot.dts @@ -104,6 +104,7 @@ led-controller@45 { reg = <0x45>; vcc-supply = <&pm8953_l10>; + vio-supply = <&pm8953_l5>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts index 1a1d3f92a51168..b0588f30f8f1a7 100644 --- a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts +++ b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts @@ -113,6 +113,7 @@ led-controller@45 { reg = <0x45>; vcc-supply = <&pm8953_l10>; + vio-supply = <&pm8953_l5>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/qcom/msm8976.dtsi b/arch/arm64/boot/dts/qcom/msm8976.dtsi index f9f5afbcc52bba..4c5be22b47feea 100644 --- a/arch/arm64/boot/dts/qcom/msm8976.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8976.dtsi @@ -379,7 +379,7 @@ adsp_smp2p_in: slave-kernel { smp2p-modem { compatible = "qcom,smp2p"; interrupts = ; - qcom,ipc = <&apcs 8 13>; + qcom,ipc = <&apcs 8 14>; qcom,local-pid = <0>; qcom,remote-pid = <1>; @@ -402,7 +402,7 @@ modem_smp2p_in: slave-kernel { smp2p-wcnss { compatible = "qcom,smp2p"; interrupts = ; - qcom,ipc = <&apcs 8 17>; + qcom,ipc = <&apcs 8 18>; qcom,local-pid = <0>; qcom,remote-pid = <4>; @@ -428,9 +428,9 @@ smsm { #address-cells = <1>; #size-cells = <0>; - qcom,ipc-1 = <&apcs 8 12>; + qcom,ipc-1 = <&apcs 8 13>; qcom,ipc-2 = <&apcs 8 9>; - qcom,ipc-3 = <&apcs 8 18>; + qcom,ipc-3 = <&apcs 8 19>; apps_smsm: apps@0 { reg = <0>; diff --git a/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts b/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts index fcca1ba94da699..5fe5de9ceef99f 100644 --- a/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts +++ b/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts @@ -109,11 +109,6 @@ rmtfs_mem: rmtfs@ca100000 { qcom,client-id = <1>; }; - audio_mem: audio@cb400000 { - reg = <0 0xcb000000 0 0x400000>; - no-mem; - }; - qseecom_mem: qseecom@cb400000 { reg = <0 0xcb400000 0 0x1c00000>; no-mem; diff --git a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi index 06f8ff624181fc..d5b35ff0175cd4 100644 --- a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi @@ -405,7 +405,6 @@ &usb3_dwc3 { &hsusb_phy1 { status = "okay"; - extcon = <&typec>; vdda-pll-supply = <&vreg_l12a_1p8>; vdda-phy-dpdm-supply = <&vreg_l24a_3p075>; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index c8e0986425ab4f..1f7cbb35886db5 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -443,6 +443,19 @@ memory@80000000 { reg = <0x0 0x80000000 0x0 0x0>; }; + etm { + compatible = "qcom,coresight-remote-etm"; + + out-ports { + port { + modem_etm_out_funnel_in2: endpoint { + remote-endpoint = + <&funnel_in2_in_modem_etm>; + }; + }; + }; + }; + psci { compatible = "arm,psci-1.0"; method = "smc"; @@ -2077,7 +2090,7 @@ ufshc: ufshc@624000 { <&gcc GCC_UFS_RX_SYMBOL_0_CLK>; freq-table-hz = <100000000 200000000>, - <0 0>, + <100000000 200000000>, <0 0>, <0 0>, <0 0>, @@ -2643,6 +2656,14 @@ funnel@3023000 { clocks = <&rpmcc RPM_QDSS_CLK>, <&rpmcc RPM_QDSS_A_CLK>; clock-names = "apb_pclk", "atclk"; + in-ports { + port { + funnel_in2_in_modem_etm: endpoint { + remote-endpoint = + <&modem_etm_out_funnel_in2>; + }; + }; + }; out-ports { port { @@ -3061,6 +3082,7 @@ usb3_dwc3: usb@6a00000 { snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; snps,is-utmi-l1-suspend; + snps,parkmode-disable-ss-quirk; tx-fifo-resize; }; }; diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi index f180047cacb057..7fcc15b6946ae8 100644 --- a/arch/arm64/boot/dts/qcom/msm8998.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi @@ -1588,7 +1588,6 @@ adreno_smmu: iommu@5040000 { * SoC VDDMX RPM Power Domain in the Adreno driver. */ power-domains = <&gpucc GPU_GX_GDSC>; - status = "disabled"; }; gpucc: clock-controller@5065000 { @@ -2034,9 +2033,11 @@ etm5: etm@7c40000 { cpu = <&CPU4>; - port { - etm4_out: endpoint { - remote-endpoint = <&apss_funnel_in4>; + out-ports { + port { + etm4_out: endpoint { + remote-endpoint = <&apss_funnel_in4>; + }; }; }; }; @@ -2051,9 +2052,11 @@ etm6: etm@7d40000 { cpu = <&CPU5>; - port { - etm5_out: endpoint { - remote-endpoint = <&apss_funnel_in5>; + out-ports { + port { + etm5_out: endpoint { + remote-endpoint = <&apss_funnel_in5>; + }; }; }; }; @@ -2068,9 +2071,11 @@ etm7: etm@7e40000 { cpu = <&CPU6>; - port { - etm6_out: endpoint { - remote-endpoint = <&apss_funnel_in6>; + out-ports { + port { + etm6_out: endpoint { + remote-endpoint = <&apss_funnel_in6>; + }; }; }; }; @@ -2085,9 +2090,11 @@ etm8: etm@7f40000 { cpu = <&CPU7>; - port { - etm7_out: endpoint { - remote-endpoint = <&apss_funnel_in7>; + out-ports { + port { + etm7_out: endpoint { + remote-endpoint = <&apss_funnel_in7>; + }; }; }; }; @@ -2152,7 +2159,8 @@ usb3_dwc3: usb@a800000 { interrupts = ; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; - phys = <&qusb2phy>, <&usb1_ssphy>; + snps,parkmode-disable-ss-quirk; + phys = <&qusb2phy>, <&usb3phy>; phy-names = "usb2-phy", "usb3-phy"; snps,has-lpm-erratum; snps,hird-threshold = /bits/ 8 <0x10>; @@ -2161,33 +2169,26 @@ usb3_dwc3: usb@a800000 { usb3phy: phy@c010000 { compatible = "qcom,msm8998-qmp-usb3-phy"; - reg = <0x0c010000 0x18c>; - status = "disabled"; - #address-cells = <1>; - #size-cells = <1>; - ranges; + reg = <0x0c010000 0x1000>; clocks = <&gcc GCC_USB3_PHY_AUX_CLK>, + <&gcc GCC_USB3_CLKREF_CLK>, <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>, - <&gcc GCC_USB3_CLKREF_CLK>; - clock-names = "aux", "cfg_ahb", "ref"; + <&gcc GCC_USB3_PHY_PIPE_CLK>; + clock-names = "aux", + "ref", + "cfg_ahb", + "pipe"; + clock-output-names = "usb3_phy_pipe_clk_src"; + #clock-cells = <0>; + #phy-cells = <0>; resets = <&gcc GCC_USB3_PHY_BCR>, <&gcc GCC_USB3PHY_PHY_BCR>; - reset-names = "phy", "common"; + reset-names = "phy", + "phy_phy"; - usb1_ssphy: phy@c010200 { - reg = <0xc010200 0x128>, - <0xc010400 0x200>, - <0xc010c00 0x20c>, - <0xc010600 0x128>, - <0xc010800 0x200>; - #phy-cells = <0>; - #clock-cells = <0>; - clocks = <&gcc GCC_USB3_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb3_phy_pipe_clk_src"; - }; + status = "disabled"; }; qusb2phy: phy@c012000 { diff --git a/arch/arm64/boot/dts/qcom/qcm2290.dtsi b/arch/arm64/boot/dts/qcom/qcm2290.dtsi index d46e591e72b5c9..40a8506553ef5d 100644 --- a/arch/arm64/boot/dts/qcom/qcm2290.dtsi +++ b/arch/arm64/boot/dts/qcom/qcm2290.dtsi @@ -418,6 +418,11 @@ tcsr_mutex: hwlock@340000 { #hwlock-cells = <1>; }; + tcsr_regs: syscon@3c0000 { + compatible = "qcom,qcm2290-tcsr", "syscon"; + reg = <0x0 0x003c0000 0x0 0x40000>; + }; + tlmm: pinctrl@500000 { compatible = "qcom,qcm2290-tlmm"; reg = <0x0 0x00500000 0x0 0x300000>; @@ -665,6 +670,8 @@ usb_qmpphy: phy@1615000 { #phy-cells = <0>; + qcom,tcsr-reg = <&tcsr_regs 0xb244>; + status = "disabled"; }; diff --git a/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi b/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi index 10655401528e4e..a22b4501ce1ef5 100644 --- a/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi +++ b/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi @@ -62,7 +62,7 @@ bluetooth { vddrf-supply = <&vreg_l1_1p3>; vddch0-supply = <&vdd_ch0_3p3>; - local-bd-address = [ 02 00 00 00 5a ad ]; + local-bd-address = [ 00 00 00 00 00 00 ]; max-speed = <3200000>; }; diff --git a/arch/arm64/boot/dts/qcom/qdu1000.dtsi b/arch/arm64/boot/dts/qcom/qdu1000.dtsi index 1c0e5d271e91bb..dbdc06be6260b7 100644 --- a/arch/arm64/boot/dts/qcom/qdu1000.dtsi +++ b/arch/arm64/boot/dts/qcom/qdu1000.dtsi @@ -1452,7 +1452,21 @@ system-cache-controller@19200000 { "llcc_broadcast_base", "multi_channel_register"; interrupts = ; - multi-ch-bit-off = <24 2>; + + nvmem-cells = <&multi_chan_ddr>; + nvmem-cell-names = "multi-chan-ddr"; + }; + + sec_qfprom: efuse@221c8000 { + compatible = "qcom,qdu1000-sec-qfprom", "qcom,sec-qfprom"; + reg = <0 0x221c8000 0 0x1000>; + #address-cells = <1>; + #size-cells = <1>; + + multi_chan_ddr: multi-chan-ddr@12b { + reg = <0x12b 0x1>; + bits = <0 2>; + }; }; }; diff --git a/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts b/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts index eadba066972e87..37abb83ea46476 100644 --- a/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts +++ b/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts @@ -13,7 +13,7 @@ / { compatible = "qcom,qrb2210-rb1", "qcom,qrb2210", "qcom,qcm2290"; aliases { - serial0 = &uart0; + serial0 = &uart4; sdhc1 = &sdhc_1; sdhc2 = &sdhc_2; }; @@ -150,15 +150,15 @@ regulators { pm2250_s3: s3 { /* 0.4V-1.6625V -> 1.3V (Power tree requirements) */ - regulator-min-microvolts = <1350000>; - regulator-max-microvolts = <1350000>; + regulator-min-microvolt = <1352000>; + regulator-max-microvolt = <1352000>; regulator-boot-on; }; pm2250_s4: s4 { /* 1.2V-2.35V -> 2.05V (Power tree requirements) */ - regulator-min-microvolts = <2072000>; - regulator-max-microvolts = <2072000>; + regulator-min-microvolt = <2072000>; + regulator-max-microvolt = <2072000>; regulator-boot-on; }; @@ -166,47 +166,47 @@ pm2250_s4: s4 { pm2250_l2: l2 { /* LPDDR4X VDD2 */ - regulator-min-microvolts = <1136000>; - regulator-max-microvolts = <1136000>; + regulator-min-microvolt = <1136000>; + regulator-max-microvolt = <1136000>; regulator-always-on; regulator-boot-on; }; pm2250_l3: l3 { /* LPDDR4X VDDQ */ - regulator-min-microvolts = <616000>; - regulator-max-microvolts = <616000>; + regulator-min-microvolt = <616000>; + regulator-max-microvolt = <616000>; regulator-always-on; regulator-boot-on; }; pm2250_l4: l4 { - /* max = 3.05V -> max = just below 3V (SDHCI2) */ - regulator-min-microvolts = <1648000>; - regulator-max-microvolts = <2992000>; + /* max = 3.05V -> max = 2.7 to disable 3V signaling (SDHCI2) */ + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2700000>; regulator-allow-set-load; }; pm2250_l5: l5 { /* CSI/DSI */ - regulator-min-microvolts = <1232000>; - regulator-max-microvolts = <1232000>; + regulator-min-microvolt = <1232000>; + regulator-max-microvolt = <1232000>; regulator-allow-set-load; regulator-boot-on; }; pm2250_l6: l6 { /* DRAM PLL */ - regulator-min-microvolts = <928000>; - regulator-max-microvolts = <928000>; + regulator-min-microvolt = <928000>; + regulator-max-microvolt = <928000>; regulator-always-on; regulator-boot-on; }; pm2250_l7: l7 { /* Wi-Fi CX/MX */ - regulator-min-microvolts = <664000>; - regulator-max-microvolts = <664000>; + regulator-min-microvolt = <664000>; + regulator-max-microvolt = <664000>; }; /* @@ -216,37 +216,37 @@ pm2250_l7: l7 { pm2250_l10: l10 { /* Wi-Fi RFA */ - regulator-min-microvolts = <1300000>; - regulator-max-microvolts = <1300000>; + regulator-min-microvolt = <1304000>; + regulator-max-microvolt = <1304000>; }; pm2250_l11: l11 { /* GPS RF1 */ - regulator-min-microvolts = <1000000>; - regulator-max-microvolts = <1000000>; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1000000>; regulator-boot-on; }; pm2250_l12: l12 { /* USB PHYs */ - regulator-min-microvolts = <928000>; - regulator-max-microvolts = <928000>; + regulator-min-microvolt = <928000>; + regulator-max-microvolt = <928000>; regulator-allow-set-load; regulator-boot-on; }; pm2250_l13: l13 { /* USB/QFPROM/PLLs */ - regulator-min-microvolts = <1800000>; - regulator-max-microvolts = <1800000>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; regulator-allow-set-load; regulator-boot-on; }; pm2250_l14: l14 { /* SDHCI1 VQMMC */ - regulator-min-microvolts = <1800000>; - regulator-max-microvolts = <1800000>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; regulator-allow-set-load; /* Broken hardware, never turn it off! */ regulator-always-on; @@ -254,8 +254,8 @@ pm2250_l14: l14 { pm2250_l15: l15 { /* WCD/DSI/BT VDDIO */ - regulator-min-microvolts = <1800000>; - regulator-max-microvolts = <1800000>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; regulator-allow-set-load; regulator-always-on; regulator-boot-on; @@ -263,47 +263,47 @@ pm2250_l15: l15 { pm2250_l16: l16 { /* GPS RF2 */ - regulator-min-microvolts = <1800000>; - regulator-max-microvolts = <1800000>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; regulator-boot-on; }; pm2250_l17: l17 { - regulator-min-microvolts = <3000000>; - regulator-max-microvolts = <3000000>; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3000000>; }; pm2250_l18: l18 { /* VDD_PXn */ - regulator-min-microvolts = <1800000>; - regulator-max-microvolts = <1800000>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; }; pm2250_l19: l19 { /* VDD_PXn */ - regulator-min-microvolts = <1800000>; - regulator-max-microvolts = <1800000>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; }; pm2250_l20: l20 { /* SDHCI1 VMMC */ - regulator-min-microvolts = <2856000>; - regulator-max-microvolts = <2856000>; + regulator-min-microvolt = <2400000>; + regulator-max-microvolt = <3600000>; regulator-allow-set-load; }; pm2250_l21: l21 { /* SDHCI2 VMMC */ - regulator-min-microvolts = <2960000>; - regulator-max-microvolts = <3300000>; + regulator-min-microvolt = <2960000>; + regulator-max-microvolt = <3300000>; regulator-allow-set-load; regulator-boot-on; }; pm2250_l22: l22 { /* Wi-Fi */ - regulator-min-microvolts = <3312000>; - regulator-max-microvolts = <3312000>; + regulator-min-microvolt = <3312000>; + regulator-max-microvolt = <3312000>; }; }; }; @@ -357,7 +357,7 @@ key_volp_n: key-volp-n-state { }; /* UART connected to the Micro-USB port via a FTDI chip */ -&uart0 { +&uart4 { compatible = "qcom,geni-debug-uart"; status = "okay"; }; @@ -366,6 +366,16 @@ &usb { status = "okay"; }; +&usb_qmpphy { + vdda-phy-supply = <&pm2250_l12>; + vdda-pll-supply = <&pm2250_l13>; + status = "okay"; +}; + +&usb_dwc3 { + dr_mode = "host"; +}; + &usb_hsphy { vdd-supply = <&pm2250_l12>; vdda-pll-supply = <&pm2250_l13>; diff --git a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts index a7278a9472ed9b..5def8c1154ceb3 100644 --- a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts +++ b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts @@ -57,6 +57,17 @@ hdmi_con: endpoint { }; }; + i2c2_gpio: i2c { + compatible = "i2c-gpio"; + + sda-gpios = <&tlmm 6 GPIO_ACTIVE_HIGH>; + scl-gpios = <&tlmm 7 GPIO_ACTIVE_HIGH>; + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + }; + leds { compatible = "gpio-leds"; @@ -187,7 +198,7 @@ zap-shader { }; }; -&i2c2 { +&i2c2_gpio { clock-frequency = <400000>; status = "okay"; @@ -353,6 +364,8 @@ vreg_l8a_0p664: l8 { vreg_l9a_1p8: l9 { regulator-min-microvolt = <1800000>; regulator-max-microvolt = <2000000>; + regulator-always-on; + regulator-boot-on; }; vreg_l10a_1p8: l10 { @@ -518,7 +531,6 @@ &usb { &usb_dwc3 { maximum-speed = "super-speed"; - dr_mode = "peripheral"; }; &usb_hsphy { diff --git a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts index dfa8ee5c75af63..e95a004c33919a 100644 --- a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts +++ b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts @@ -63,8 +63,8 @@ led-user4 { function = LED_FUNCTION_INDICATOR; color = ; gpios = <&pm8150_gpios 10 GPIO_ACTIVE_HIGH>; - linux,default-trigger = "panic-indicator"; default-state = "off"; + panic-indicator; }; led-wlan { diff --git a/arch/arm64/boot/dts/qcom/sa8155p-adp.dts b/arch/arm64/boot/dts/qcom/sa8155p-adp.dts index 5e4287f8c8cd19..b2cf2c988336c0 100644 --- a/arch/arm64/boot/dts/qcom/sa8155p-adp.dts +++ b/arch/arm64/boot/dts/qcom/sa8155p-adp.dts @@ -367,6 +367,16 @@ queue0 { }; }; +&pmm8155au_1_gpios { + pmm8155au_1_sdc2_cd: sdc2-cd-default-state { + pins = "gpio4"; + function = "normal"; + input-enable; + bias-pull-up; + power-source = <0>; + }; +}; + &qupv3_id_1 { status = "okay"; }; @@ -384,10 +394,10 @@ &remoteproc_cdsp { &sdhc_2 { status = "okay"; - cd-gpios = <&tlmm 4 GPIO_ACTIVE_LOW>; + cd-gpios = <&pmm8155au_1_gpios 4 GPIO_ACTIVE_LOW>; pinctrl-names = "default", "sleep"; - pinctrl-0 = <&sdc2_on>; - pinctrl-1 = <&sdc2_off>; + pinctrl-0 = <&sdc2_on &pmm8155au_1_sdc2_cd>; + pinctrl-1 = <&sdc2_off &pmm8155au_1_sdc2_cd>; vqmmc-supply = <&vreg_l13c_2p96>; /* IO line power */ vmmc-supply = <&vreg_l17a_2p96>; /* Card power line */ bus-width = <4>; @@ -505,13 +515,6 @@ data-pins { bias-pull-up; /* pull up */ drive-strength = <16>; /* 16 MA */ }; - - sd-cd-pins { - pins = "gpio96"; - function = "gpio"; - bias-pull-up; /* pull up */ - drive-strength = <2>; /* 2 MA */ - }; }; sdc2_off: sdc2-off-state { @@ -532,13 +535,6 @@ data-pins { bias-pull-up; /* pull up */ drive-strength = <2>; /* 2 MA */ }; - - sd-cd-pins { - pins = "gpio96"; - function = "gpio"; - bias-pull-up; /* pull up */ - drive-strength = <2>; /* 2 MA */ - }; }; usb2phy_ac_en1_default: usb2phy-ac-en1-default-state { diff --git a/arch/arm64/boot/dts/qcom/sa8540p.dtsi b/arch/arm64/boot/dts/qcom/sa8540p.dtsi index 96b2c59ad02b4d..23888029cc1179 100644 --- a/arch/arm64/boot/dts/qcom/sa8540p.dtsi +++ b/arch/arm64/boot/dts/qcom/sa8540p.dtsi @@ -168,6 +168,9 @@ opp-2592000000 { }; &gpucc { + /* SA8295P and SA8540P doesn't provide gfx.lvl */ + /delete-property/ power-domains; + status = "disabled"; }; diff --git a/arch/arm64/boot/dts/qcom/sa8775p.dtsi b/arch/arm64/boot/dts/qcom/sa8775p.dtsi index 9f4f58e831a4a6..f6766fa8df34d3 100644 --- a/arch/arm64/boot/dts/qcom/sa8775p.dtsi +++ b/arch/arm64/boot/dts/qcom/sa8775p.dtsi @@ -1602,8 +1602,8 @@ usb_0: usb@a6f8800 { assigned-clock-rates = <19200000>, <200000000>; interrupts-extended = <&intc GIC_SPI 287 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 14 IRQ_TYPE_EDGE_RISING>, - <&pdc 15 IRQ_TYPE_EDGE_RISING>, + <&pdc 14 IRQ_TYPE_EDGE_BOTH>, + <&pdc 15 IRQ_TYPE_EDGE_BOTH>, <&pdc 12 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "pwr_event", "dp_hs_phy_irq", @@ -1689,8 +1689,8 @@ usb_1: usb@a8f8800 { assigned-clock-rates = <19200000>, <200000000>; interrupts-extended = <&intc GIC_SPI 352 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 8 IRQ_TYPE_EDGE_RISING>, - <&pdc 7 IRQ_TYPE_EDGE_RISING>, + <&pdc 8 IRQ_TYPE_EDGE_BOTH>, + <&pdc 7 IRQ_TYPE_EDGE_BOTH>, <&pdc 13 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "pwr_event", "dp_hs_phy_irq", @@ -1752,8 +1752,8 @@ usb_2: usb@a4f8800 { assigned-clock-rates = <19200000>, <200000000>; interrupts-extended = <&intc GIC_SPI 444 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 10 IRQ_TYPE_EDGE_RISING>, - <&pdc 9 IRQ_TYPE_EDGE_RISING>; + <&pdc 10 IRQ_TYPE_EDGE_BOTH>, + <&pdc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "pwr_event", "dp_hs_phy_irq", "dm_hs_phy_irq"; @@ -1951,6 +1951,7 @@ apps_smmu: iommu@15000000 { reg = <0x0 0x15000000 0x0 0x100000>; #iommu-cells = <2>; #global-interrupts = <2>; + dma-coherent; interrupts = , , @@ -2089,6 +2090,7 @@ pcie_smmu: iommu@15200000 { reg = <0x0 0x15200000 0x0 0x80000>; #iommu-cells = <2>; #global-interrupts = <2>; + dma-coherent; interrupts = , , @@ -2173,7 +2175,7 @@ watchdog@17c10000 { compatible = "qcom,apss-wdt-sa8775p", "qcom,kpss-wdt"; reg = <0x0 0x17c10000 0x0 0x1000>; clocks = <&sleep_clk>; - interrupts = ; + interrupts = ; }; memtimer: timer@17c20000 { @@ -2350,6 +2352,7 @@ ethernet1: ethernet@23000000 { phy-names = "serdes"; iommus = <&apps_smmu 0x140 0xf>; + dma-coherent; snps,tso; snps,pbl = <32>; @@ -2383,6 +2386,7 @@ ethernet0: ethernet@23040000 { phy-names = "serdes"; iommus = <&apps_smmu 0x120 0xf>; + dma-coherent; snps,tso; snps,pbl = <32>; @@ -2398,7 +2402,7 @@ arch_timer: timer { interrupts = , , , - ; + ; }; pcie0: pci@1c00000{ diff --git a/arch/arm64/boot/dts/qcom/sc7180-acer-aspire1.dts b/arch/arm64/boot/dts/qcom/sc7180-acer-aspire1.dts index dbb48934d49950..3342cb0480385f 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-acer-aspire1.dts +++ b/arch/arm64/boot/dts/qcom/sc7180-acer-aspire1.dts @@ -209,9 +209,22 @@ alc5682: codec@1a { AVDD-supply = <&vreg_l15a_1p8>; MICVDD-supply = <®_codec_3p3>; VBAT-supply = <®_codec_3p3>; + DBVDD-supply = <&vreg_l15a_1p8>; + LDO1-IN-supply = <&vreg_l15a_1p8>; + + /* + * NOTE: The board has a path from this codec to the + * DMIC microphones in the lid, however some of the option + * resistors are absent and the microphones are connected + * to the SoC instead. + * + * If the resistors were to be changed by the user to + * connect the codec, the following could be used: + * + * realtek,dmic1-data-pin = <1>; + * realtek,dmic1-clk-pin = <1>; + */ - realtek,dmic1-data-pin = <1>; - realtek,dmic1-clk-pin = <1>; realtek,jd-src = <1>; }; }; diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi index 5a33e16a8b6776..c2f5e9f6679d69 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi @@ -970,6 +970,8 @@ bluetooth: bluetooth { vddrf-supply = <&pp1300_l2c>; vddch0-supply = <&pp3300_l10c>; max-speed = <3200000>; + + qcom,local-bd-address-broken; }; }; diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi index a79c0f2e18799c..68b1c017a9fd5f 100644 --- a/arch/arm64/boot/dts/qcom/sc7180.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -2795,49 +2796,28 @@ usb_1_hsphy: phy@88e3000 { nvmem-cells = <&qusb2p_hstx_trim>; }; - usb_1_qmpphy: phy-wrapper@88e9000 { + usb_1_qmpphy: phy@88e8000 { compatible = "qcom,sc7180-qmp-usb3-dp-phy"; - reg = <0 0x088e9000 0 0x18c>, - <0 0x088e8000 0 0x3c>, - <0 0x088ea000 0 0x18c>; + reg = <0 0x088e8000 0 0x3000>; status = "disabled"; - #address-cells = <2>; - #size-cells = <2>; - ranges; clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>, - <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>, <&gcc GCC_USB3_PRIM_CLKREF_CLK>, - <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>; - clock-names = "aux", "cfg_ahb", "ref", "com_aux"; + <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>, + <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>; + clock-names = "aux", + "ref", + "com_aux", + "usb3_pipe", + "cfg_ahb"; resets = <&gcc GCC_USB3_PHY_PRIM_BCR>, <&gcc GCC_USB3_DP_PHY_PRIM_BCR>; reset-names = "phy", "common"; - usb_1_ssphy: usb3-phy@88e9200 { - reg = <0 0x088e9200 0 0x128>, - <0 0x088e9400 0 0x200>, - <0 0x088e9c00 0 0x218>, - <0 0x088e9600 0 0x128>, - <0 0x088e9800 0 0x200>, - <0 0x088e9a00 0 0x18>; - #clock-cells = <0>; - #phy-cells = <0>; - clocks = <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb3_phy_pipe_clk_src"; - }; - - dp_phy: dp-phy@88ea200 { - reg = <0 0x088ea200 0 0x200>, - <0 0x088ea400 0 0x200>, - <0 0x088eaa00 0 0x200>, - <0 0x088ea600 0 0x200>, - <0 0x088ea800 0 0x200>; - #clock-cells = <1>; - #phy-cells = <0>; - }; + #clock-cells = <1>; + #phy-cells = <1>; }; pmu@90b6300 { @@ -2978,8 +2958,8 @@ usb_1: usb@a6f8800 { interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 8 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 9 IRQ_TYPE_LEVEL_HIGH>; + <&pdc 8 IRQ_TYPE_EDGE_BOTH>, + <&pdc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -3001,7 +2981,8 @@ usb_1_dwc3: usb@a600000 { iommus = <&apps_smmu 0x540 0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; - phys = <&usb_1_hsphy>, <&usb_1_ssphy>; + snps,parkmode-disable-ss-quirk; + phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; maximum-speed = "super-speed"; }; @@ -3307,8 +3288,9 @@ mdss_dp: displayport-controller@ae90000 { "ctrl_link_iface", "stream_pixel"; assigned-clocks = <&dispcc DISP_CC_MDSS_DP_LINK_CLK_SRC>, <&dispcc DISP_CC_MDSS_DP_PIXEL_CLK_SRC>; - assigned-clock-parents = <&dp_phy 0>, <&dp_phy 1>; - phys = <&dp_phy>; + assigned-clock-parents = <&usb_1_qmpphy QMP_USB43DP_DP_LINK_CLK>, + <&usb_1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>; + phys = <&usb_1_qmpphy QMP_USB43DP_DP_PHY>; phy-names = "dp"; operating-points-v2 = <&dp_opp_table>; @@ -3365,8 +3347,8 @@ dispcc: clock-controller@af00000 { <&gcc GCC_DISP_GPLL0_CLK_SRC>, <&mdss_dsi0_phy 0>, <&mdss_dsi0_phy 1>, - <&dp_phy 0>, - <&dp_phy 1>; + <&usb_1_qmpphy QMP_USB43DP_DP_LINK_CLK>, + <&usb_1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>; clock-names = "bi_tcxo", "gcc_disp_gpll0_clk_src", "dsi0_phy_pll_out_byteclk", @@ -3587,7 +3569,7 @@ watchdog@17c10000 { compatible = "qcom,apss-wdt-sc7180", "qcom,kpss-wdt"; reg = <0 0x17c10000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = ; + interrupts = ; }; timer@17c20000 { diff --git a/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi b/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi index 2e1cd219fc1822..5d462ae14ba122 100644 --- a/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi @@ -46,6 +46,26 @@ wpss_mem: memory@9ae00000 { }; }; +&lpass_aon { + status = "okay"; +}; + +&lpass_core { + status = "okay"; +}; + +&lpass_hm { + status = "okay"; +}; + +&lpasscc { + status = "okay"; +}; + +&pdc_reset { + status = "okay"; +}; + /* The PMIC PON code isn't compatible w/ how Chrome EC/BIOS handle things. */ &pmk8350_pon { status = "disabled"; @@ -84,6 +104,10 @@ &scm { dma-coherent; }; +&watchdog { + status = "okay"; +}; + &wifi { status = "okay"; diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi index 925428a5f6aea2..149c7962f2cbb7 100644 --- a/arch/arm64/boot/dts/qcom/sc7280.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -649,18 +650,6 @@ cpu7_opp_3014mhz: opp-3014400000 { }; }; - eud_typec: connector { - compatible = "usb-c-connector"; - - ports { - port@0 { - con_eud: endpoint { - remote-endpoint = <&eud_con>; - }; - }; - }; - }; - memory@80000000 { device_type = "memory"; /* We expect the bootloader to fill in the size */ @@ -869,7 +858,8 @@ gcc: clock-controller@100000 { clocks = <&rpmhcc RPMH_CXO_CLK>, <&rpmhcc RPMH_CXO_CLK_A>, <&sleep_clk>, <0>, <&pcie1_lane>, - <0>, <0>, <0>, <0>; + <0>, <0>, <0>, + <&usb_1_qmpphy QMP_USB43DP_USB3_PIPE_CLK>; clock-names = "bi_tcxo", "bi_tcxo_ao", "sleep_clk", "pcie_0_pipe_clk", "pcie_1_pipe_clk", "ufs_phy_rx_symbol_0_clk", "ufs_phy_rx_symbol_1_clk", @@ -936,6 +926,7 @@ sdhc_1: mmc@7c4000 { bus-width = <8>; supports-cqe; + dma-coherent; qcom,dll-config = <0x0007642c>; qcom,ddr-config = <0x80040868>; @@ -2108,8 +2099,16 @@ pcie1: pci@1c08000 { ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>, <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>; - interrupts = ; - interrupt-names = "msi"; + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "msi0", "msi1", "msi2", "msi3", + "msi4", "msi5", "msi6", "msi7"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; interrupt-map = <0 0 0 1 &intc 0 0 0 434 IRQ_TYPE_LEVEL_HIGH>, @@ -2266,6 +2265,7 @@ lpasscc: lpasscc@3000000 { clocks = <&gcc GCC_CFG_NOC_LPASS_CLK>; clock-names = "iface"; #clock-cells = <1>; + status = "reserved"; /* Owned by ADSP firmware */ }; lpass_rx_macro: codec@3200000 { @@ -2417,6 +2417,7 @@ lpass_aon: clock-controller@3380000 { clock-names = "bi_tcxo", "bi_tcxo_ao", "iface"; #clock-cells = <1>; #power-domain-cells = <1>; + status = "reserved"; /* Owned by ADSP firmware */ }; lpass_core: clock-controller@3900000 { @@ -2427,6 +2428,7 @@ lpass_core: clock-controller@3900000 { power-domains = <&lpass_hm LPASS_CORE_CC_LPASS_CORE_HM_GDSC>; #clock-cells = <1>; #power-domain-cells = <1>; + status = "reserved"; /* Owned by ADSP firmware */ }; lpass_cpu: audio@3987000 { @@ -2497,6 +2499,7 @@ lpass_hm: clock-controller@3c00000 { clock-names = "bi_tcxo"; #clock-cells = <1>; #power-domain-cells = <1>; + status = "reserved"; /* Owned by ADSP firmware */ }; lpass_ag_noc: interconnect@3c40000 { @@ -2565,7 +2568,8 @@ gpu: gpu@3d00000 { "cx_mem", "cx_dbgc"; interrupts = ; - iommus = <&adreno_smmu 0 0x401>; + iommus = <&adreno_smmu 0 0x400>, + <&adreno_smmu 1 0x400>; operating-points-v2 = <&gpu_opp_table>; qcom,gmu = <&gmu>; interconnects = <&gem_noc MASTER_GFX3D 0 &mc_virt SLAVE_EBI1 0>; @@ -2739,6 +2743,7 @@ adreno_smmu: iommu@3da0000 { "gpu_cc_hub_aon_clk"; power-domains = <&gpucc GPU_CC_CX_GDSC>; + dma-coherent; }; remoteproc_mpss: remoteproc@4080000 { @@ -3296,6 +3301,7 @@ sdhc_2: mmc@8804000 { operating-points-v2 = <&sdhc2_opp_table>; bus-width = <4>; + dma-coherent; qcom,dll-config = <0x0007642c>; @@ -3346,49 +3352,26 @@ usb_2_hsphy: phy@88e4000 { resets = <&gcc GCC_QUSB2PHY_SEC_BCR>; }; - usb_1_qmpphy: phy-wrapper@88e9000 { - compatible = "qcom,sc7280-qmp-usb3-dp-phy", - "qcom,sm8250-qmp-usb3-dp-phy"; - reg = <0 0x088e9000 0 0x200>, - <0 0x088e8000 0 0x40>, - <0 0x088ea000 0 0x200>; + usb_1_qmpphy: phy@88e8000 { + compatible = "qcom,sc7280-qmp-usb3-dp-phy"; + reg = <0 0x088e8000 0 0x3000>; status = "disabled"; - #address-cells = <2>; - #size-cells = <2>; - ranges; clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>, <&rpmhcc RPMH_CXO_CLK>, - <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>; - clock-names = "aux", "ref_clk_src", "com_aux"; + <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; + clock-names = "aux", + "ref", + "com_aux", + "usb3_pipe"; resets = <&gcc GCC_USB3_DP_PHY_PRIM_BCR>, <&gcc GCC_USB3_PHY_PRIM_BCR>; reset-names = "phy", "common"; - usb_1_ssphy: usb3-phy@88e9200 { - reg = <0 0x088e9200 0 0x200>, - <0 0x088e9400 0 0x200>, - <0 0x088e9c00 0 0x400>, - <0 0x088e9600 0 0x200>, - <0 0x088e9800 0 0x200>, - <0 0x088e9a00 0 0x100>; - #clock-cells = <0>; - #phy-cells = <0>; - clocks = <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb3_phy_pipe_clk_src"; - }; - - dp_phy: dp-phy@88ea200 { - reg = <0 0x088ea200 0 0x200>, - <0 0x088ea400 0 0x200>, - <0 0x088eaa00 0 0x200>, - <0 0x088ea600 0 0x200>, - <0 0x088ea800 0 0x200>; - #phy-cells = <0>; - #clock-cells = <1>; - }; + #clock-cells = <1>; + #phy-cells = <1>; }; usb_2: usb@8cf8800 { @@ -3416,8 +3399,8 @@ usb_2: usb@8cf8800 { assigned-clock-rates = <19200000>, <200000000>; interrupts-extended = <&intc GIC_SPI 240 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 12 IRQ_TYPE_EDGE_RISING>, - <&pdc 13 IRQ_TYPE_EDGE_RISING>; + <&pdc 12 IRQ_TYPE_EDGE_BOTH>, + <&pdc 13 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "dp_hs_phy_irq", "dm_hs_phy_irq"; @@ -3624,6 +3607,8 @@ eud: eud@88e0000 { <0 0x88e2000 0 0x1000>; interrupts-extended = <&pdc 11 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + ports { #address-cells = <1>; #size-cells = <0>; @@ -3634,13 +3619,6 @@ eud_ep: endpoint { remote-endpoint = <&usb2_role_switch>; }; }; - - port@1 { - reg = <1>; - eud_con: endpoint { - remote-endpoint = <&con_eud>; - }; - }; }; }; @@ -3676,9 +3654,9 @@ usb_1: usb@a6f8800 { assigned-clock-rates = <19200000>, <200000000>; interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 14 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 14 IRQ_TYPE_EDGE_BOTH>, <&pdc 15 IRQ_TYPE_EDGE_BOTH>, - <&pdc 17 IRQ_TYPE_EDGE_BOTH>; + <&pdc 17 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "hs_phy_irq", "dp_hs_phy_irq", "dm_hs_phy_irq", @@ -3702,7 +3680,8 @@ usb_1_dwc3: usb@a600000 { iommus = <&apps_smmu 0xe0 0x0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; - phys = <&usb_1_hsphy>, <&usb_1_ssphy>; + snps,parkmode-disable-ss-quirk; + phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; maximum-speed = "super-speed"; }; @@ -3807,8 +3786,8 @@ dispcc: clock-controller@af00000 { <&gcc GCC_DISP_GPLL0_CLK_SRC>, <&mdss_dsi_phy 0>, <&mdss_dsi_phy 1>, - <&dp_phy 0>, - <&dp_phy 1>, + <&usb_1_qmpphy QMP_USB43DP_DP_LINK_CLK>, + <&usb_1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>, <&mdss_edp_phy 0>, <&mdss_edp_phy 1>; clock-names = "bi_tcxo", @@ -4144,8 +4123,9 @@ mdss_dp: displayport-controller@ae90000 { "stream_pixel"; assigned-clocks = <&dispcc DISP_CC_MDSS_DP_LINK_CLK_SRC>, <&dispcc DISP_CC_MDSS_DP_PIXEL_CLK_SRC>; - assigned-clock-parents = <&dp_phy 0>, <&dp_phy 1>; - phys = <&dp_phy>; + assigned-clock-parents = <&usb_1_qmpphy QMP_USB43DP_DP_LINK_CLK>, + <&usb_1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>; + phys = <&usb_1_qmpphy QMP_USB43DP_DP_PHY>; phy-names = "dp"; operating-points-v2 = <&dp_opp_table>; @@ -4215,6 +4195,7 @@ pdc_reset: reset-controller@b5e0000 { compatible = "qcom,sc7280-pdc-global"; reg = <0 0x0b5e0000 0 0x20000>; #reset-cells = <1>; + status = "reserved"; /* Owned by firmware */ }; tsens0: thermal-sensor@c263000 { @@ -5211,11 +5192,12 @@ msi-controller@17a40000 { }; }; - watchdog@17c10000 { + watchdog: watchdog@17c10000 { compatible = "qcom,apss-wdt-sc7280", "qcom,kpss-wdt"; reg = <0 0x17c10000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = ; + interrupts = ; + status = "reserved"; /* Owned by Gunyah hyp */ }; timer@17c20000 { @@ -5363,6 +5345,14 @@ cpufreq_hw: cpufreq@18591000 { reg = <0 0x18591000 0 0x1000>, <0 0x18592000 0 0x1000>, <0 0x18593000 0 0x1000>; + + interrupts = , + , + ; + interrupt-names = "dcvsh-irq-0", + "dcvsh-irq-1", + "dcvsh-irq-2"; + clocks = <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_GPLL0>; clock-names = "xo", "alternate"; #freq-domain-cells = <1>; diff --git a/arch/arm64/boot/dts/qcom/sc8180x-primus.dts b/arch/arm64/boot/dts/qcom/sc8180x-primus.dts index 834e6f9fb7c825..ae008c3b0aed93 100644 --- a/arch/arm64/boot/dts/qcom/sc8180x-primus.dts +++ b/arch/arm64/boot/dts/qcom/sc8180x-primus.dts @@ -42,7 +42,7 @@ gpio-keys { pinctrl-0 = <&hall_int_active_state>; lid-switch { - gpios = <&tlmm 121 GPIO_ACTIVE_HIGH>; + gpios = <&tlmm 121 GPIO_ACTIVE_LOW>; linux,input-type = ; linux,code = ; wakeup-source; diff --git a/arch/arm64/boot/dts/qcom/sc8180x.dtsi b/arch/arm64/boot/dts/qcom/sc8180x.dtsi index 486f7ffef43b2d..92b85de7706d39 100644 --- a/arch/arm64/boot/dts/qcom/sc8180x.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8180x.dtsi @@ -289,7 +289,7 @@ LITTLE_CPU_SLEEP_0: cpu-sleep-0-0 { BIG_CPU_SLEEP_0: cpu-sleep-1-0 { compatible = "arm,idle-state"; arm,psci-suspend-param = <0x40000004>; - entry-latency-us = <241>; + entry-latency-us = <2411>; exit-latency-us = <1461>; min-residency-us = <4488>; local-timer-stop; @@ -297,7 +297,15 @@ BIG_CPU_SLEEP_0: cpu-sleep-1-0 { }; domain-idle-states { - CLUSTER_SLEEP_0: cluster-sleep-0 { + CLUSTER_SLEEP_APSS_OFF: cluster-sleep-0 { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x41000044>; + entry-latency-us = <3300>; + exit-latency-us = <3300>; + min-residency-us = <6000>; + }; + + CLUSTER_SLEEP_AOSS_SLEEP: cluster-sleep-1 { compatible = "domain-idle-state"; arm,psci-suspend-param = <0x4100a344>; entry-latency-us = <3263>; @@ -581,7 +589,7 @@ CPU_PD7: power-domain-cpu7 { CLUSTER_PD: power-domain-cpu-cluster0 { #power-domain-cells = <0>; - domain-idle-states = <&CLUSTER_SLEEP_0>; + domain-idle-states = <&CLUSTER_SLEEP_APSS_OFF &CLUSTER_SLEEP_AOSS_SLEEP>; }; }; @@ -781,6 +789,7 @@ gcc: clock-controller@100000 { clock-names = "bi_tcxo", "bi_tcxo_ao", "sleep_clk"; + power-domains = <&rpmhpd SC8180X_CX>; }; qupv3_id_0: geniqup@8c0000 { @@ -1749,23 +1758,29 @@ pcie0: pci@1c00000 { <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_PCIE_0 0>; interconnect-names = "pcie-mem", "cpu-pcie"; - phys = <&pcie0_lane>; + phys = <&pcie0_phy>; phy-names = "pciephy"; + dma-coherent; status = "disabled"; }; - pcie0_phy: phy-wrapper@1c06000 { + pcie0_phy: phy@1c06000 { compatible = "qcom,sc8180x-qmp-pcie-phy"; - reg = <0 0x1c06000 0 0x1c0>; - #address-cells = <2>; - #size-cells = <2>; - ranges; + reg = <0 0x01c06000 0 0x1000>; clocks = <&gcc GCC_PCIE_PHY_AUX_CLK>, <&gcc GCC_PCIE_0_CFG_AHB_CLK>, <&gcc GCC_PCIE_0_CLKREF_CLK>, - <&gcc GCC_PCIE1_PHY_REFGEN_CLK>; - clock-names = "aux", "cfg_ahb", "ref", "refgen"; + <&gcc GCC_PCIE0_PHY_REFGEN_CLK>, + <&gcc GCC_PCIE_0_PIPE_CLK>; + clock-names = "aux", + "cfg_ahb", + "ref", + "refgen", + "pipe"; + #clock-cells = <0>; + clock-output-names = "pcie_0_pipe_clk"; + #phy-cells = <0>; resets = <&gcc GCC_PCIE_0_PHY_BCR>; reset-names = "phy"; @@ -1774,21 +1789,6 @@ pcie0_phy: phy-wrapper@1c06000 { assigned-clock-rates = <100000000>; status = "disabled"; - - pcie0_lane: phy@1c06200 { - reg = <0 0x1c06200 0 0x170>, /* tx0 */ - <0 0x1c06400 0 0x200>, /* rx0 */ - <0 0x1c06a00 0 0x1f0>, /* pcs */ - <0 0x1c06600 0 0x170>, /* tx1 */ - <0 0x1c06800 0 0x200>, /* rx1 */ - <0 0x1c06e00 0 0xf4>; /* pcs_com */ - clocks = <&gcc GCC_PCIE_0_PIPE_CLK>; - clock-names = "pipe0"; - - #clock-cells = <0>; - clock-output-names = "pcie_0_pipe_clk"; - #phy-cells = <0>; - }; }; pcie3: pci@1c08000 { @@ -1853,26 +1853,33 @@ pcie3: pci@1c08000 { power-domains = <&gcc PCIE_3_GDSC>; interconnects = <&aggre2_noc MASTER_PCIE_3 0 &mc_virt SLAVE_EBI_CH0 0>, - <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_PCIE_0 0>; + <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_PCIE_3 0>; interconnect-names = "pcie-mem", "cpu-pcie"; - phys = <&pcie3_lane>; + phys = <&pcie3_phy>; phy-names = "pciephy"; + dma-coherent; status = "disabled"; }; - pcie3_phy: phy-wrapper@1c0c000 { + pcie3_phy: phy@1c0c000 { compatible = "qcom,sc8180x-qmp-pcie-phy"; - reg = <0 0x1c0c000 0 0x1c0>; - #address-cells = <2>; - #size-cells = <2>; - ranges; + reg = <0 0x01c0c000 0 0x1000>; clocks = <&gcc GCC_PCIE_PHY_AUX_CLK>, <&gcc GCC_PCIE_3_CFG_AHB_CLK>, <&gcc GCC_PCIE_3_CLKREF_CLK>, - <&gcc GCC_PCIE2_PHY_REFGEN_CLK>; - clock-names = "aux", "cfg_ahb", "ref", "refgen"; + <&gcc GCC_PCIE3_PHY_REFGEN_CLK>, + <&gcc GCC_PCIE_3_PIPE_CLK>; + clock-names = "aux", + "cfg_ahb", + "ref", + "refgen", + "pipe"; + #clock-cells = <0>; + clock-output-names = "pcie_3_pipe_clk"; + + #phy-cells = <0>; resets = <&gcc GCC_PCIE_3_PHY_BCR>; reset-names = "phy"; @@ -1881,21 +1888,6 @@ pcie3_phy: phy-wrapper@1c0c000 { assigned-clock-rates = <100000000>; status = "disabled"; - - pcie3_lane: phy@1c0c200 { - reg = <0 0x1c0c200 0 0x170>, /* tx0 */ - <0 0x1c0c400 0 0x200>, /* rx0 */ - <0 0x1c0ca00 0 0x1f0>, /* pcs */ - <0 0x1c0c600 0 0x170>, /* tx1 */ - <0 0x1c0c800 0 0x200>, /* rx1 */ - <0 0x1c0ce00 0 0xf4>; /* pcs_com */ - clocks = <&gcc GCC_PCIE_3_PIPE_CLK>; - clock-names = "pipe0"; - - #clock-cells = <0>; - clock-output-names = "pcie_3_pipe_clk"; - #phy-cells = <0>; - }; }; pcie1: pci@1c10000 { @@ -1960,26 +1952,33 @@ pcie1: pci@1c10000 { power-domains = <&gcc PCIE_1_GDSC>; interconnects = <&aggre2_noc MASTER_PCIE_1 0 &mc_virt SLAVE_EBI_CH0 0>, - <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_PCIE_0 0>; + <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_PCIE_1 0>; interconnect-names = "pcie-mem", "cpu-pcie"; - phys = <&pcie1_lane>; + phys = <&pcie1_phy>; phy-names = "pciephy"; + dma-coherent; status = "disabled"; }; - pcie1_phy: phy-wrapper@1c16000 { + pcie1_phy: phy@1c16000 { compatible = "qcom,sc8180x-qmp-pcie-phy"; - reg = <0 0x1c16000 0 0x1c0>; - #address-cells = <2>; - #size-cells = <2>; - ranges; + reg = <0 0x01c16000 0 0x1000>; clocks = <&gcc GCC_PCIE_PHY_AUX_CLK>, <&gcc GCC_PCIE_1_CFG_AHB_CLK>, <&gcc GCC_PCIE_1_CLKREF_CLK>, - <&gcc GCC_PCIE1_PHY_REFGEN_CLK>; - clock-names = "aux", "cfg_ahb", "ref", "refgen"; + <&gcc GCC_PCIE1_PHY_REFGEN_CLK>, + <&gcc GCC_PCIE_1_PIPE_CLK>; + clock-names = "aux", + "cfg_ahb", + "ref", + "refgen", + "pipe"; + #clock-cells = <0>; + clock-output-names = "pcie_1_pipe_clk"; + + #phy-cells = <0>; resets = <&gcc GCC_PCIE_1_PHY_BCR>; reset-names = "phy"; @@ -1988,21 +1987,6 @@ pcie1_phy: phy-wrapper@1c16000 { assigned-clock-rates = <100000000>; status = "disabled"; - - pcie1_lane: phy@1c0e200 { - reg = <0 0x1c16200 0 0x170>, /* tx0 */ - <0 0x1c16400 0 0x200>, /* rx0 */ - <0 0x1c16a00 0 0x1f0>, /* pcs */ - <0 0x1c16600 0 0x170>, /* tx1 */ - <0 0x1c16800 0 0x200>, /* rx1 */ - <0 0x1c16e00 0 0xf4>; /* pcs_com */ - clocks = <&gcc GCC_PCIE_1_PIPE_CLK>; - clock-names = "pipe0"; - #clock-cells = <0>; - clock-output-names = "pcie_1_pipe_clk"; - - #phy-cells = <0>; - }; }; pcie2: pci@1c18000 { @@ -2067,26 +2051,33 @@ pcie2: pci@1c18000 { power-domains = <&gcc PCIE_2_GDSC>; interconnects = <&aggre2_noc MASTER_PCIE_2 0 &mc_virt SLAVE_EBI_CH0 0>, - <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_PCIE_0 0>; + <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_PCIE_2 0>; interconnect-names = "pcie-mem", "cpu-pcie"; - phys = <&pcie2_lane>; + phys = <&pcie2_phy>; phy-names = "pciephy"; + dma-coherent; status = "disabled"; }; - pcie2_phy: phy-wrapper@1c1c000 { + pcie2_phy: phy@1c1c000 { compatible = "qcom,sc8180x-qmp-pcie-phy"; - reg = <0 0x1c1c000 0 0x1c0>; - #address-cells = <2>; - #size-cells = <2>; - ranges; + reg = <0 0x01c1c000 0 0x1000>; clocks = <&gcc GCC_PCIE_PHY_AUX_CLK>, <&gcc GCC_PCIE_2_CFG_AHB_CLK>, <&gcc GCC_PCIE_2_CLKREF_CLK>, - <&gcc GCC_PCIE2_PHY_REFGEN_CLK>; - clock-names = "aux", "cfg_ahb", "ref", "refgen"; + <&gcc GCC_PCIE2_PHY_REFGEN_CLK>, + <&gcc GCC_PCIE_2_PIPE_CLK>; + clock-names = "aux", + "cfg_ahb", + "ref", + "refgen", + "pipe"; + #clock-cells = <0>; + clock-output-names = "pcie_2_pipe_clk"; + + #phy-cells = <0>; resets = <&gcc GCC_PCIE_2_PHY_BCR>; reset-names = "phy"; @@ -2095,22 +2086,6 @@ pcie2_phy: phy-wrapper@1c1c000 { assigned-clock-rates = <100000000>; status = "disabled"; - - pcie2_lane: phy@1c0e200 { - reg = <0 0x1c1c200 0 0x170>, /* tx0 */ - <0 0x1c1c400 0 0x200>, /* rx0 */ - <0 0x1c1ca00 0 0x1f0>, /* pcs */ - <0 0x1c1c600 0 0x170>, /* tx1 */ - <0 0x1c1c800 0 0x200>, /* rx1 */ - <0 0x1c1ce00 0 0xf4>; /* pcs_com */ - clocks = <&gcc GCC_PCIE_2_PIPE_CLK>; - clock-names = "pipe0"; - - #clock-cells = <0>; - clock-output-names = "pcie_2_pipe_clk"; - - #phy-cells = <0>; - }; }; ufs_mem_hc: ufshc@1d84000 { @@ -2118,7 +2093,7 @@ ufs_mem_hc: ufshc@1d84000 { "jedec,ufs-2.0"; reg = <0 0x01d84000 0 0x2500>; interrupts = ; - phys = <&ufs_mem_phy_lanes>; + phys = <&ufs_mem_phy>; phy-names = "ufsphy"; lanes-per-direction = <2>; #reset-cells = <1>; @@ -2157,10 +2132,8 @@ ufs_mem_hc: ufshc@1d84000 { ufs_mem_phy: phy-wrapper@1d87000 { compatible = "qcom,sc8180x-qmp-ufs-phy"; - reg = <0 0x01d87000 0 0x1c0>; - #address-cells = <2>; - #size-cells = <2>; - ranges; + reg = <0 0x01d87000 0 0x1000>; + clocks = <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_UFS_PHY_PHY_AUX_CLK>; clock-names = "ref", @@ -2168,16 +2141,12 @@ ufs_mem_phy: phy-wrapper@1d87000 { resets = <&ufs_mem_hc 0>; reset-names = "ufsphy"; - status = "disabled"; - ufs_mem_phy_lanes: phy@1d87400 { - reg = <0 0x01d87400 0 0x108>, - <0 0x01d87600 0 0x1e0>, - <0 0x01d87c00 0 0x1dc>, - <0 0x01d87800 0 0x108>, - <0 0x01d87a00 0 0x1e0>; - #phy-cells = <0>; - }; + power-domains = <&gcc UFS_PHY_GDSC>; + + #phy-cells = <0>; + + status = "disabled"; }; ipa_virt: interconnect@1e00000 { @@ -2576,11 +2545,14 @@ usb_sec_dpphy: dp-phy@88ef200 { system-cache-controller@9200000 { compatible = "qcom,sc8180x-llcc"; - reg = <0 0x09200000 0 0x50000>, <0 0x09280000 0 0x50000>, - <0 0x09300000 0 0x50000>, <0 0x09380000 0 0x50000>, - <0 0x09600000 0 0x50000>; + reg = <0 0x09200000 0 0x58000>, <0 0x09280000 0 0x58000>, + <0 0x09300000 0 0x58000>, <0 0x09380000 0 0x58000>, + <0 0x09400000 0 0x58000>, <0 0x09480000 0 0x58000>, + <0 0x09500000 0 0x58000>, <0 0x09580000 0 0x58000>, + <0 0x09600000 0 0x58000>; reg-names = "llcc0_base", "llcc1_base", "llcc2_base", - "llcc3_base", "llcc_broadcast_base"; + "llcc3_base", "llcc4_base", "llcc5_base", + "llcc6_base", "llcc7_base", "llcc_broadcast_base"; interrupts = ; }; @@ -2594,10 +2566,10 @@ gem_noc: interconnect@9680000 { usb_prim: usb@a6f8800 { compatible = "qcom,sc8180x-dwc3", "qcom,dwc3"; reg = <0 0x0a6f8800 0 0x400>; - interrupts = , - , - , - ; + interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 8 IRQ_TYPE_EDGE_BOTH>, + <&pdc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", @@ -2668,10 +2640,10 @@ usb_sec: usb@a8f8800 { "xo"; resets = <&gcc GCC_USB30_SEC_BCR>; power-domains = <&gcc USB30_SEC_GDSC>; - interrupts = , - , - , - ; + interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 40 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 10 IRQ_TYPE_EDGE_BOTH>, + <&pdc 11 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -2756,10 +2728,8 @@ mdss_mdp: mdp@ae01000 { "core", "vsync"; - assigned-clocks = <&dispcc DISP_CC_MDSS_MDP_CLK>, - <&dispcc DISP_CC_MDSS_VSYNC_CLK>; - assigned-clock-rates = <460000000>, - <19200000>; + assigned-clocks = <&dispcc DISP_CC_MDSS_VSYNC_CLK>; + assigned-clock-rates = <19200000>; operating-points-v2 = <&mdp_opp_table>; power-domains = <&rpmhpd SC8180X_MMCX>; @@ -3219,7 +3189,7 @@ edp_phy: phy@aec2a00 { <&dispcc DISP_CC_MDSS_AHB_CLK>; clock-names = "aux", "cfg_ahb"; - power-domains = <&dispcc MDSS_GDSC>; + power-domains = <&rpmhpd SC8180X_MX>; #clock-cells = <1>; #phy-cells = <0>; @@ -3245,6 +3215,7 @@ dispcc: clock-controller@af00000 { "edp_phy_pll_link_clk", "edp_phy_pll_vco_div_clk"; power-domains = <&rpmhpd SC8180X_MMCX>; + required-opps = <&rpmhpd_opp_low_svs>; #clock-cells = <1>; #reset-cells = <1>; #power-domain-cells = <1>; @@ -3283,7 +3254,7 @@ tsens1: thermal-sensor@c265000 { aoss_qmp: power-controller@c300000 { compatible = "qcom,sc8180x-aoss-qmp", "qcom,aoss-qmp"; - reg = <0x0 0x0c300000 0x0 0x100000>; + reg = <0x0 0x0c300000 0x0 0x400>; interrupts = ; mboxes = <&apss_shared 0>; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts index e4861c61a65bdc..ffc4406422ae2f 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts @@ -458,6 +458,8 @@ mdss0_dp3_out: endpoint { }; &mdss0_dp3_phy { + compatible = "qcom,sc8280xp-edp-phy"; + vdda-phy-supply = <&vreg_l6b>; vdda-pll-supply = <&vreg_l3b>; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts index 38edaf51aa3457..5c2894fcfa4a08 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts @@ -82,6 +82,9 @@ switch-lid { leds { compatible = "gpio-leds"; + pinctrl-names = "default"; + pinctrl-0 = <&cam_indicator_en>; + led-camera-indicator { label = "white:camera-indicator"; function = LED_FUNCTION_INDICATOR; @@ -601,6 +604,7 @@ mdss0_dp3_out: endpoint { }; &mdss0_dp3_phy { + compatible = "qcom,sc8280xp-edp-phy"; vdda-phy-supply = <&vreg_l6b>; vdda-pll-supply = <&vreg_l3b>; @@ -615,15 +619,16 @@ &i2c4 { status = "okay"; - /* FIXME: verify */ touchscreen@10 { - compatible = "hid-over-i2c"; + compatible = "elan,ekth5015m", "elan,ekth6915"; reg = <0x10>; - hid-descr-addr = <0x1>; interrupts-extended = <&tlmm 175 IRQ_TYPE_LEVEL_LOW>; - vdd-supply = <&vreg_misc_3p3>; - vddl-supply = <&vreg_s10b>; + reset-gpios = <&tlmm 99 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>; + no-reset-on-power-off; + + vcc33-supply = <&vreg_misc_3p3>; + vccio-supply = <&vreg_misc_3p3>; pinctrl-names = "default"; pinctrl-0 = <&ts0_default>; @@ -717,6 +722,8 @@ &pcie3a_phy { }; &pcie4 { + max-link-speed = <2>; + perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>; wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>; @@ -1277,6 +1284,13 @@ hstp-sw-ctrl-pins { }; }; + cam_indicator_en: cam-indicator-en-state { + pins = "gpio28"; + function = "gpio"; + drive-strength = <2>; + bias-disable; + }; + edp_reg_en: edp-reg-en-state { pins = "gpio25"; function = "gpio"; @@ -1438,8 +1452,8 @@ int-n-pins { reset-n-pins { pins = "gpio99"; function = "gpio"; - output-high; - drive-strength = <16>; + drive-strength = <2>; + bias-disable; }; }; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi index cad59af7ccef1b..6425c74edd60cc 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi @@ -1773,6 +1773,7 @@ pcie4: pcie@1c00000 { reset-names = "pci"; power-domains = <&gcc PCIE_4_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie4_phy>; phy-names = "pciephy"; @@ -1797,6 +1798,7 @@ pcie4_phy: phy@1c06000 { assigned-clock-rates = <100000000>; power-domains = <&gcc PCIE_4_GDSC>; + required-opps = <&rpmhpd_opp_nom>; resets = <&gcc GCC_PCIE_4_PHY_BCR>; reset-names = "phy"; @@ -1871,6 +1873,7 @@ pcie3b: pcie@1c08000 { reset-names = "pci"; power-domains = <&gcc PCIE_3B_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie3b_phy>; phy-names = "pciephy"; @@ -1895,6 +1898,7 @@ pcie3b_phy: phy@1c0e000 { assigned-clock-rates = <100000000>; power-domains = <&gcc PCIE_3B_GDSC>; + required-opps = <&rpmhpd_opp_nom>; resets = <&gcc GCC_PCIE_3B_PHY_BCR>; reset-names = "phy"; @@ -1969,6 +1973,7 @@ pcie3a: pcie@1c10000 { reset-names = "pci"; power-domains = <&gcc PCIE_3A_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie3a_phy>; phy-names = "pciephy"; @@ -1994,6 +1999,7 @@ pcie3a_phy: phy@1c14000 { assigned-clock-rates = <100000000>; power-domains = <&gcc PCIE_3A_GDSC>; + required-opps = <&rpmhpd_opp_nom>; resets = <&gcc GCC_PCIE_3A_PHY_BCR>; reset-names = "phy"; @@ -2070,6 +2076,7 @@ pcie2b: pcie@1c18000 { reset-names = "pci"; power-domains = <&gcc PCIE_2B_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie2b_phy>; phy-names = "pciephy"; @@ -2094,6 +2101,7 @@ pcie2b_phy: phy@1c1e000 { assigned-clock-rates = <100000000>; power-domains = <&gcc PCIE_2B_GDSC>; + required-opps = <&rpmhpd_opp_nom>; resets = <&gcc GCC_PCIE_2B_PHY_BCR>; reset-names = "phy"; @@ -2168,6 +2176,7 @@ pcie2a: pcie@1c20000 { reset-names = "pci"; power-domains = <&gcc PCIE_2A_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie2a_phy>; phy-names = "pciephy"; @@ -2193,6 +2202,7 @@ pcie2a_phy: phy@1c24000 { assigned-clock-rates = <100000000>; power-domains = <&gcc PCIE_2A_GDSC>; + required-opps = <&rpmhpd_opp_nom>; resets = <&gcc GCC_PCIE_2A_PHY_BCR>; reset-names = "phy"; @@ -4225,7 +4235,7 @@ watchdog@17c10000 { compatible = "qcom,apss-wdt-sc8280xp", "qcom,kpss-wdt"; reg = <0 0x17c10000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = ; + interrupts = ; }; timer@17c20000 { diff --git a/arch/arm64/boot/dts/qcom/sdm630.dtsi b/arch/arm64/boot/dts/qcom/sdm630.dtsi index ec6003212c4d5f..0f3f57fb860ec8 100644 --- a/arch/arm64/boot/dts/qcom/sdm630.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm630.dtsi @@ -1258,6 +1258,7 @@ usb3_dwc3: usb@a800000 { interrupts = ; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,parkmode-disable-ss-quirk; /* * SDM630 technically supports USB3 but I diff --git a/arch/arm64/boot/dts/qcom/sdm670.dtsi b/arch/arm64/boot/dts/qcom/sdm670.dtsi index 84cd2e39266fed..730c8351bcaa33 100644 --- a/arch/arm64/boot/dts/qcom/sdm670.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm670.dtsi @@ -1295,10 +1295,10 @@ usb_1: usb@a6f8800 { <&gcc GCC_USB30_PRIM_MASTER_CLK>; assigned-clock-rates = <19200000>, <150000000>; - interrupts = , - , - , - ; + interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 8 IRQ_TYPE_EDGE_BOTH>, + <&pdc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -1328,7 +1328,8 @@ pdc: interrupt-controller@b220000 { compatible = "qcom,sdm670-pdc", "qcom,pdc"; reg = <0 0x0b220000 0 0x30000>; qcom,pdc-ranges = <0 480 40>, <41 521 7>, <49 529 4>, - <54 534 24>, <79 559 30>, <115 630 7>; + <54 534 24>, <79 559 15>, <94 609 15>, + <115 630 7>; #interrupt-cells = <2>; interrupt-parent = <&intc>; interrupt-controller; diff --git a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi index f86e7acdfd99f4..0ab5e8f53ac9f8 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi @@ -143,16 +143,20 @@ panel_in_edp: endpoint { }; }; +&cpufreq_hw { + /delete-property/ interrupts-extended; /* reference to lmh_cluster[01] */ +}; + &psci { - /delete-node/ cpu0; - /delete-node/ cpu1; - /delete-node/ cpu2; - /delete-node/ cpu3; - /delete-node/ cpu4; - /delete-node/ cpu5; - /delete-node/ cpu6; - /delete-node/ cpu7; - /delete-node/ cpu-cluster0; + /delete-node/ power-domain-cpu0; + /delete-node/ power-domain-cpu1; + /delete-node/ power-domain-cpu2; + /delete-node/ power-domain-cpu3; + /delete-node/ power-domain-cpu4; + /delete-node/ power-domain-cpu5; + /delete-node/ power-domain-cpu6; + /delete-node/ power-domain-cpu7; + /delete-node/ power-domain-cluster; }; &cpus { @@ -275,6 +279,14 @@ &BIG_CPU_SLEEP_1 &CLUSTER_SLEEP_0>; }; +&lmh_cluster0 { + status = "disabled"; +}; + +&lmh_cluster1 { + status = "disabled"; +}; + /* * Reserved memory changes * @@ -338,6 +350,8 @@ flash@0 { &apps_rsc { + /delete-property/ power-domains; + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts index c7eba6c491be2b..0a891a0122446c 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts @@ -67,8 +67,8 @@ led-0 { function = LED_FUNCTION_INDICATOR; color = ; gpios = <&pm8998_gpios 13 GPIO_ACTIVE_HIGH>; - linux,default-trigger = "panic-indicator"; default-state = "off"; + panic-indicator; }; led-1 { @@ -580,7 +580,7 @@ &mss_pil { &pcie0 { status = "okay"; perst-gpios = <&tlmm 35 GPIO_ACTIVE_LOW>; - enable-gpio = <&tlmm 134 GPIO_ACTIVE_HIGH>; + wake-gpios = <&tlmm 134 GPIO_ACTIVE_HIGH>; vddpe-3v3-supply = <&pcie0_3p3v_dual>; diff --git a/arch/arm64/boot/dts/qcom/sdm845-mtp.dts b/arch/arm64/boot/dts/qcom/sdm845-mtp.dts index b3c27a5247429f..1516113391edc3 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-mtp.dts @@ -716,6 +716,8 @@ &wifi { vdd-1.8-xo-supply = <&vreg_l7a_1p8>; vdd-1.3-rfa-supply = <&vreg_l17a_1p3>; vdd-3.3-ch0-supply = <&vreg_l25a_3p3>; + + qcom,snoc-host-cap-8bit-quirk; }; /* PINCTRL - additions to nodes defined in sdm845.dtsi */ diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi index 122c7128dea9da..9322b92a1e6825 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi @@ -485,13 +485,13 @@ &pmi8998_charger { }; &q6afedai { - qi2s@22 { - reg = <22>; + dai@22 { + reg = ; qcom,sd-lines = <1>; }; - qi2s@23 { - reg = <23>; + dai@23 { + reg = ; qcom,sd-lines = <0>; }; }; diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 055ca80c007578..dcdc8a0cd1819f 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -2634,6 +2635,8 @@ ufs_mem_phy: phy@1d87000 { clocks = <&gcc GCC_UFS_MEM_CLKREF_CLK>, <&gcc GCC_UFS_PHY_PHY_AUX_CLK>; + power-domains = <&gcc UFS_PHY_GDSC>; + resets = <&ufs_mem_hc 0>; reset-names = "ufsphy"; status = "disabled"; @@ -3363,8 +3366,8 @@ slpi_pas: remoteproc@5c00000 { qcom,qmp = <&aoss_qmp>; - power-domains = <&rpmhpd SDM845_CX>, - <&rpmhpd SDM845_MX>; + power-domains = <&rpmhpd SDM845_LCX>, + <&rpmhpd SDM845_LMX>; power-domain-names = "lcx", "lmx"; memory-region = <&slpi_mem>; @@ -3555,11 +3558,8 @@ etf_out: endpoint { }; in-ports { - #address-cells = <1>; - #size-cells = <0>; - port@1 { - reg = <1>; + port { etf_in: endpoint { remote-endpoint = <&merge_funnel_out>; @@ -3984,80 +3984,54 @@ usb_2_hsphy: phy@88e3000 { nvmem-cells = <&qusb2s_hstx_trim>; }; - usb_1_qmpphy: phy@88e9000 { + usb_1_qmpphy: phy@88e8000 { compatible = "qcom,sdm845-qmp-usb3-dp-phy"; - reg = <0 0x088e9000 0 0x18c>, - <0 0x088e8000 0 0x38>, - <0 0x088ea000 0 0x40>; + reg = <0 0x088e8000 0 0x3000>; status = "disabled"; - #address-cells = <2>; - #size-cells = <2>; - ranges; clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>, - <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>, <&gcc GCC_USB3_PRIM_CLKREF_CLK>, - <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>; - clock-names = "aux", "cfg_ahb", "ref", "com_aux"; + <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>, + <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>; + clock-names = "aux", + "ref", + "com_aux", + "usb3_pipe", + "cfg_ahb"; resets = <&gcc GCC_USB3_PHY_PRIM_BCR>, <&gcc GCC_USB3_DP_PHY_PRIM_BCR>; reset-names = "phy", "common"; - usb_1_ssphy: usb3-phy@88e9200 { - reg = <0 0x088e9200 0 0x128>, - <0 0x088e9400 0 0x200>, - <0 0x088e9c00 0 0x218>, - <0 0x088e9600 0 0x128>, - <0 0x088e9800 0 0x200>, - <0 0x088e9a00 0 0x100>; - #clock-cells = <0>; - #phy-cells = <0>; - clocks = <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb3_phy_pipe_clk_src"; - }; - - dp_phy: dp-phy@88ea200 { - reg = <0 0x088ea200 0 0x200>, - <0 0x088ea400 0 0x200>, - <0 0x088eaa00 0 0x200>, - <0 0x088ea600 0 0x200>, - <0 0x088ea800 0 0x200>; - #clock-cells = <1>; - #phy-cells = <0>; - }; + #clock-cells = <1>; + #phy-cells = <1>; }; usb_2_qmpphy: phy@88eb000 { compatible = "qcom,sdm845-qmp-usb3-uni-phy"; - reg = <0 0x088eb000 0 0x18c>; - status = "disabled"; - #address-cells = <2>; - #size-cells = <2>; - ranges; + reg = <0 0x088eb000 0 0x1000>; clocks = <&gcc GCC_USB3_SEC_PHY_AUX_CLK>, <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>, <&gcc GCC_USB3_SEC_CLKREF_CLK>, - <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>; - clock-names = "aux", "cfg_ahb", "ref", "com_aux"; + <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>; + clock-names = "aux", + "cfg_ahb", + "ref", + "com_aux", + "pipe"; + clock-output-names = "usb3_uni_phy_pipe_clk_src"; + #clock-cells = <0>; + #phy-cells = <0>; - resets = <&gcc GCC_USB3PHY_PHY_SEC_BCR>, - <&gcc GCC_USB3_PHY_SEC_BCR>; - reset-names = "phy", "common"; + resets = <&gcc GCC_USB3_PHY_SEC_BCR>, + <&gcc GCC_USB3PHY_PHY_SEC_BCR>; + reset-names = "phy", + "phy_phy"; - usb_2_ssphy: phy@88eb200 { - reg = <0 0x088eb200 0 0x128>, - <0 0x088eb400 0 0x1fc>, - <0 0x088eb800 0 0x218>, - <0 0x088eb600 0 0x70>; - #clock-cells = <0>; - #phy-cells = <0>; - clocks = <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb3_uni_phy_pipe_clk_src"; - }; + status = "disabled"; }; usb_1: usb@a6f8800 { @@ -4084,10 +4058,10 @@ usb_1: usb@a6f8800 { <&gcc GCC_USB30_PRIM_MASTER_CLK>; assigned-clock-rates = <19200000>, <150000000>; - interrupts = , - , - , - ; + interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 6 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 8 IRQ_TYPE_EDGE_BOTH>, + <&pdc_intc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -4106,7 +4080,8 @@ usb_1_dwc3: usb@a600000 { iommus = <&apps_smmu 0x740 0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; - phys = <&usb_1_hsphy>, <&usb_1_ssphy>; + snps,parkmode-disable-ss-quirk; + phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; }; }; @@ -4135,10 +4110,10 @@ usb_2: usb@a8f8800 { <&gcc GCC_USB30_SEC_MASTER_CLK>; assigned-clock-rates = <19200000>, <150000000>; - interrupts = , - , - , - ; + interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 7 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 10 IRQ_TYPE_EDGE_BOTH>, + <&pdc_intc 11 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -4157,7 +4132,8 @@ usb_2_dwc3: usb@a800000 { iommus = <&apps_smmu 0x760 0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; - phys = <&usb_2_hsphy>, <&usb_2_ssphy>; + snps,parkmode-disable-ss-quirk; + phys = <&usb_2_hsphy>, <&usb_2_qmpphy>; phy-names = "usb2-phy", "usb3-phy"; }; }; @@ -4574,8 +4550,9 @@ mdss_dp: displayport-controller@ae90000 { "ctrl_link_iface", "stream_pixel"; assigned-clocks = <&dispcc DISP_CC_MDSS_DP_LINK_CLK_SRC>, <&dispcc DISP_CC_MDSS_DP_PIXEL_CLK_SRC>; - assigned-clock-parents = <&dp_phy 0>, <&dp_phy 1>; - phys = <&dp_phy>; + assigned-clock-parents = <&usb_1_qmpphy QMP_USB43DP_DP_LINK_CLK>, + <&usb_1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>; + phys = <&usb_1_qmpphy QMP_USB43DP_DP_PHY>; phy-names = "dp"; operating-points-v2 = <&dp_opp_table>; @@ -4913,8 +4890,8 @@ dispcc: clock-controller@af00000 { <&mdss_dsi0_phy 1>, <&mdss_dsi1_phy 0>, <&mdss_dsi1_phy 1>, - <&dp_phy 0>, - <&dp_phy 1>; + <&usb_1_qmpphy QMP_USB43DP_DP_LINK_CLK>, + <&usb_1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>; clock-names = "bi_tcxo", "gcc_disp_gpll0_clk_src", "gcc_disp_gpll0_div_clk_src", @@ -5118,7 +5095,7 @@ watchdog@17980000 { compatible = "qcom,apss-wdt-sdm845", "qcom,kpss-wdt"; reg = <0 0x17980000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = ; + interrupts = ; }; apss_shared: mailbox@17990000 { diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts index 92a812b5f4238e..fe5c12da666e40 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts @@ -488,6 +488,7 @@ ecsh: hid@5c { &ipa { qcom,gsi-loader = "self"; memory-region = <&ipa_fw_mem>; + firmware-name = "qcom/sdm850/LENOVO/81JL/ipa_fws.elf"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sdx75-idp.dts b/arch/arm64/boot/dts/qcom/sdx75-idp.dts index 10d15871f2c48e..a14e0650c4a8aa 100644 --- a/arch/arm64/boot/dts/qcom/sdx75-idp.dts +++ b/arch/arm64/boot/dts/qcom/sdx75-idp.dts @@ -44,7 +44,7 @@ vreg_bob_3p3: pmx75-bob { }; &apps_rsc { - pmx75-rpmh-regulators { + regulators-0 { compatible = "qcom,pmx75-rpmh-regulators"; qcom,pmic-id = "b"; diff --git a/arch/arm64/boot/dts/qcom/sm6115.dtsi b/arch/arm64/boot/dts/qcom/sm6115.dtsi index 839c6035124034..821db9b8518557 100644 --- a/arch/arm64/boot/dts/qcom/sm6115.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6115.dtsi @@ -591,6 +591,11 @@ tcsr_mutex: hwlock@340000 { #hwlock-cells = <1>; }; + tcsr_regs: syscon@3c0000 { + compatible = "qcom,sm6115-tcsr", "syscon"; + reg = <0x0 0x003c0000 0x0 0x40000>; + }; + tlmm: pinctrl@500000 { compatible = "qcom,sm6115-tlmm"; reg = <0x0 0x00500000 0x0 0x400000>, @@ -856,6 +861,8 @@ usb_qmpphy: phy@1615000 { #phy-cells = <0>; + qcom,tcsr-reg = <&tcsr_regs 0xb244>; + status = "disabled"; }; @@ -1036,6 +1043,8 @@ ufs_mem_phy: phy@4807000 { clocks = <&gcc GCC_UFS_CLKREF_CLK>, <&gcc GCC_UFS_PHY_PHY_AUX_CLK>; clock-names = "ref", "ref_aux"; + power-domains = <&gcc GCC_UFS_PHY_GDSC>; + resets = <&ufs_mem_hc 0>; reset-names = "ufsphy"; status = "disabled"; diff --git a/arch/arm64/boot/dts/qcom/sm6125.dtsi b/arch/arm64/boot/dts/qcom/sm6125.dtsi index d7c1a40617c647..07081088ba1463 100644 --- a/arch/arm64/boot/dts/qcom/sm6125.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6125.dtsi @@ -1165,6 +1165,10 @@ usb3: usb@4ef8800 { <&gcc GCC_USB30_PRIM_MASTER_CLK>; assigned-clock-rates = <19200000>, <66666667>; + interrupts = , + ; + interrupt-names = "hs_phy_irq", "ss_phy_irq"; + power-domains = <&gcc USB30_PRIM_GDSC>; qcom,select-utmi-as-pipe-clk; status = "disabled"; @@ -1208,7 +1212,7 @@ spmi_bus: spmi@1c40000 { apps_smmu: iommu@c600000 { compatible = "qcom,sm6125-smmu-500", "qcom,smmu-500", "arm,mmu-500"; - reg = <0xc600000 0x80000>; + reg = <0x0c600000 0x80000>; interrupts = , , , diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi index 8fd6f4d0349001..2efceb49a3218e 100644 --- a/arch/arm64/boot/dts/qcom/sm6350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi @@ -1197,6 +1197,8 @@ ufs_mem_phy: phy@1d87000 { clocks = <&gcc GCC_UFS_MEM_CLKREF_CLK>, <&gcc GCC_UFS_PHY_PHY_AUX_CLK>; + power-domains = <&gcc UFS_PHY_GDSC>; + resets = <&ufs_mem_hc 0>; reset-names = "ufsphy"; @@ -1297,6 +1299,7 @@ fastrpc { compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "adsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; @@ -1557,6 +1560,7 @@ fastrpc { compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "cdsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; @@ -1864,6 +1868,7 @@ usb_1_dwc3: usb@a600000 { snps,dis_enblslpm_quirk; snps,has-lpm-erratum; snps,hird-threshold = /bits/ 8 <0x10>; + snps,parkmode-disable-ss-quirk; phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; }; @@ -2524,7 +2529,7 @@ watchdog@17c10000 { compatible = "qcom,apss-wdt-sm6350", "qcom,kpss-wdt"; reg = <0 0x17c10000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = ; + interrupts = ; }; timer@17c20000 { diff --git a/arch/arm64/boot/dts/qcom/sm6375.dtsi b/arch/arm64/boot/dts/qcom/sm6375.dtsi index e7ff55443da702..e56f7ea4ebc6ae 100644 --- a/arch/arm64/boot/dts/qcom/sm6375.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6375.dtsi @@ -311,6 +311,25 @@ scm { }; }; + mpm: interrupt-controller { + compatible = "qcom,mpm"; + qcom,rpm-msg-ram = <&apss_mpm>; + interrupts = ; + mboxes = <&ipcc IPCC_CLIENT_AOP IPCC_MPROC_SIGNAL_SMP2P>; + interrupt-controller; + #interrupt-cells = <2>; + #power-domain-cells = <0>; + interrupt-parent = <&intc>; + qcom,mpm-pin-count = <96>; + qcom,mpm-pin-map = <5 296>, /* Soundwire wake_irq */ + <12 422>, /* DWC3 ss_phy_irq */ + <86 183>, /* MPM wake, SPMI */ + <89 314>, /* TSENS0 0C */ + <90 315>, /* TSENS1 0C */ + <93 164>, /* DWC3 dm_hs_phy_irq */ + <94 165>; /* DWC3 dp_hs_phy_irq */ + }; + memory@80000000 { device_type = "memory"; /* We expect the bootloader to fill in the size */ @@ -486,6 +505,7 @@ CPU_PD7: power-domain-cpu7 { CLUSTER_PD: power-domain-cpu-cluster0 { #power-domain-cells = <0>; + power-domains = <&mpm>; domain-idle-states = <&CLUSTER_SLEEP_0>; }; }; @@ -808,7 +828,7 @@ tlmm: pinctrl@500000 { reg = <0 0x00500000 0 0x800000>; interrupts = ; gpio-ranges = <&tlmm 0 0 157>; - /* TODO: Hook up MPM as wakeup-parent when it's there */ + wakeup-parent = <&mpm>; interrupt-controller; gpio-controller; #interrupt-cells = <2>; @@ -930,7 +950,7 @@ spmi_bus: spmi@1c40000 { <0 0x01c0a000 0 0x26000>; reg-names = "core", "chnls", "obsrvr", "intr", "cnfg"; interrupt-names = "periph_irq"; - interrupts = ; + interrupts-extended = <&mpm 86 IRQ_TYPE_LEVEL_HIGH>; qcom,ee = <0>; qcom,channel = <0>; #address-cells = <2>; @@ -962,8 +982,15 @@ tsens1: thermal-sensor@4413000 { }; rpm_msg_ram: sram@45f0000 { - compatible = "qcom,rpm-msg-ram"; + compatible = "qcom,rpm-msg-ram", "mmio-sram"; reg = <0 0x045f0000 0 0x7000>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x0 0x045f0000 0x7000>; + + apss_mpm: sram@1b8 { + reg = <0x1b8 0x48>; + }; }; sram@4690000 { @@ -1360,10 +1387,10 @@ usb_1: usb@4ef8800 { <&gcc GCC_USB30_PRIM_MASTER_CLK>; assigned-clock-rates = <19200000>, <133333333>; - interrupts = , - , - , - ; + interrupts-extended = <&intc GIC_SPI 302 IRQ_TYPE_LEVEL_HIGH>, + <&mpm 12 IRQ_TYPE_LEVEL_HIGH>, + <&mpm 93 IRQ_TYPE_EDGE_BOTH>, + <&mpm 94 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", diff --git a/arch/arm64/boot/dts/qcom/sm8150-hdk.dts b/arch/arm64/boot/dts/qcom/sm8150-hdk.dts index bb161b536da466..f4c6e1309a7e99 100644 --- a/arch/arm64/boot/dts/qcom/sm8150-hdk.dts +++ b/arch/arm64/boot/dts/qcom/sm8150-hdk.dts @@ -127,8 +127,6 @@ vdda_qrefs_0p875_5: vdda_sp_sensor: vdda_ufs_2ln_core_1: vdda_ufs_2ln_core_2: - vdda_usb_ss_dp_core_1: - vdda_usb_ss_dp_core_2: vdda_qlink_lv: vdda_qlink_lv_ck: vreg_l5a_0p875: ldo5 { @@ -210,6 +208,12 @@ vreg_l17a_3p0: ldo17 { regulator-max-microvolt = <3008000>; regulator-initial-mode = ; }; + + vreg_l18a_0p8: ldo18 { + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <880000>; + regulator-initial-mode = ; + }; }; regulators-1 { @@ -445,13 +449,13 @@ &usb_2_hsphy { &usb_1_qmpphy { status = "okay"; vdda-phy-supply = <&vreg_l3c_1p2>; - vdda-pll-supply = <&vdda_usb_ss_dp_core_1>; + vdda-pll-supply = <&vreg_l18a_0p8>; }; &usb_2_qmpphy { status = "okay"; vdda-phy-supply = <&vreg_l3c_1p2>; - vdda-pll-supply = <&vdda_usb_ss_dp_core_1>; + vdda-pll-supply = <&vreg_l5a_0p875>; }; &usb_1 { diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi index 06c53000bb74d4..73ef228ff26891 100644 --- a/arch/arm64/boot/dts/qcom/sm8150.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi @@ -1876,8 +1876,8 @@ pcie0: pci@1c00000 { phys = <&pcie0_lane>; phy-names = "pciephy"; - perst-gpio = <&tlmm 35 GPIO_ACTIVE_HIGH>; - enable-gpio = <&tlmm 37 GPIO_ACTIVE_HIGH>; + perst-gpios = <&tlmm 35 GPIO_ACTIVE_HIGH>; + wake-gpios = <&tlmm 37 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&pcie0_default_state>; @@ -1893,8 +1893,12 @@ pcie0_phy: phy@1c06000 { ranges; clocks = <&gcc GCC_PCIE_PHY_AUX_CLK>, <&gcc GCC_PCIE_0_CFG_AHB_CLK>, + <&gcc GCC_PCIE_0_CLKREF_CLK>, <&gcc GCC_PCIE0_PHY_REFGEN_CLK>; - clock-names = "aux", "cfg_ahb", "refgen"; + clock-names = "aux", + "cfg_ahb", + "ref", + "refgen"; resets = <&gcc GCC_PCIE_0_PHY_BCR>; reset-names = "phy"; @@ -1974,7 +1978,7 @@ pcie1: pci@1c08000 { phys = <&pcie1_lane>; phy-names = "pciephy"; - perst-gpio = <&tlmm 102 GPIO_ACTIVE_HIGH>; + perst-gpios = <&tlmm 102 GPIO_ACTIVE_HIGH>; enable-gpio = <&tlmm 104 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; @@ -1991,8 +1995,12 @@ pcie1_phy: phy@1c0e000 { ranges; clocks = <&gcc GCC_PCIE_PHY_AUX_CLK>, <&gcc GCC_PCIE_1_CFG_AHB_CLK>, + <&gcc GCC_PCIE_1_CLKREF_CLK>, <&gcc GCC_PCIE1_PHY_REFGEN_CLK>; - clock-names = "aux", "cfg_ahb", "refgen"; + clock-names = "aux", + "cfg_ahb", + "ref", + "refgen"; resets = <&gcc GCC_PCIE_1_PHY_BCR>; reset-names = "phy"; @@ -2965,11 +2973,8 @@ replicator1_out: endpoint { }; in-ports { - #address-cells = <1>; - #size-cells = <0>; - port@1 { - reg = <1>; + port { replicator1_in: endpoint { remote-endpoint = <&replicator_out1>; }; @@ -3584,10 +3589,10 @@ usb_1: usb@a6f8800 { <&gcc GCC_USB30_PRIM_MASTER_CLK>; assigned-clock-rates = <19200000>, <200000000>; - interrupts = , - , - , - ; + interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 8 IRQ_TYPE_EDGE_BOTH>, + <&pdc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -3637,10 +3642,10 @@ usb_2: usb@a8f8800 { <&gcc GCC_USB30_SEC_MASTER_CLK>; assigned-clock-rates = <19200000>, <200000000>; - interrupts = , - , - , - ; + interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 7 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 10 IRQ_TYPE_EDGE_BOTH>, + <&pdc 11 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -3951,6 +3956,7 @@ dispcc: clock-controller@af00000 { "dp_phy_pll_link_clk", "dp_phy_pll_vco_div_clk"; power-domains = <&rpmhpd SM8150_MMCX>; + required-opps = <&rpmhpd_opp_low_svs>; #clock-cells = <1>; #reset-cells = <1>; #power-domain-cells = <1>; @@ -4189,7 +4195,7 @@ watchdog@17c10000 { compatible = "qcom,apss-wdt-sm8150", "qcom,kpss-wdt"; reg = <0 0x17c10000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = ; + interrupts = ; }; timer@17c20000 { diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index a4e58ad731c34f..b522d19f3a1327 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -2169,7 +2169,7 @@ ufs_mem_hc: ufshc@1d84000 { "jedec,ufs-2.0"; reg = <0 0x01d84000 0 0x3000>; interrupts = ; - phys = <&ufs_mem_phy_lanes>; + phys = <&ufs_mem_phy>; phy-names = "ufsphy"; lanes-per-direction = <2>; #reset-cells = <1>; @@ -2217,10 +2217,8 @@ ufs_mem_hc: ufshc@1d84000 { ufs_mem_phy: phy@1d87000 { compatible = "qcom,sm8250-qmp-ufs-phy"; - reg = <0 0x01d87000 0 0x1c0>; - #address-cells = <2>; - #size-cells = <2>; - ranges; + reg = <0 0x01d87000 0 0x1000>; + clock-names = "ref", "ref_aux"; clocks = <&rpmhcc RPMH_CXO_CLK>, @@ -2228,16 +2226,12 @@ ufs_mem_phy: phy@1d87000 { resets = <&ufs_mem_hc 0>; reset-names = "ufsphy"; - status = "disabled"; - ufs_mem_phy_lanes: phy@1d87400 { - reg = <0 0x01d87400 0 0x16c>, - <0 0x01d87600 0 0x200>, - <0 0x01d87c00 0 0x200>, - <0 0x01d87800 0 0x16c>, - <0 0x01d87a00 0 0x200>; - #phy-cells = <0>; - }; + power-domains = <&gcc UFS_PHY_GDSC>; + + #phy-cells = <0>; + + status = "disabled"; }; cryptobam: dma-controller@1dc4000 { @@ -2830,11 +2824,8 @@ tpda@6004000 { clock-names = "apb_pclk"; out-ports { - #address-cells = <1>; - #size-cells = <0>; - port@0 { - reg = <0>; + port { tpda_out_funnel_qatb: endpoint { remote-endpoint = <&funnel_qatb_in_tpda>; }; @@ -2877,11 +2868,7 @@ funnel_qatb_out_funnel_in0: endpoint { }; in-ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; + port { funnel_qatb_in_tpda: endpoint { remote-endpoint = <&tpda_out_funnel_qatb>; }; @@ -3090,11 +3077,8 @@ etf_out: endpoint { }; in-ports { - #address-cells = <1>; - #size-cells = <0>; - port@0 { - reg = <0>; + port { etf_in_funnel_swao_out: endpoint { remote-endpoint = <&funnel_swao_out_etf>; }; @@ -3178,8 +3162,6 @@ funnel@6c2d000 { clock-names = "apb_pclk"; out-ports { - #address-cells = <1>; - #size-cells = <0>; port { tpdm_mm_out_tpda9: endpoint { remote-endpoint = <&tpda_9_in_tpdm_mm>; @@ -3445,11 +3427,7 @@ funnel_apss_merg_out_funnel_in1: endpoint { }; in-ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; + port { funnel_apss_merg_in_funnel_apss: endpoint { remote-endpoint = <&funnel_apss_out_funnel_apss_merg>; }; @@ -5664,7 +5642,7 @@ watchdog@17c10000 { compatible = "qcom,apss-wdt-sm8250", "qcom,kpss-wdt"; reg = <0 0x17c10000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = ; + interrupts = ; }; timer@17c20000 { diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi index 00604bf7724f42..d4f1b36c7aebe4 100644 --- a/arch/arm64/boot/dts/qcom/sm8350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi @@ -918,9 +918,9 @@ spi19: spi@894000 { }; }; - gpi_dma0: dma-controller@9800000 { + gpi_dma0: dma-controller@900000 { compatible = "qcom,sm8350-gpi-dma", "qcom,sm6350-gpi-dma"; - reg = <0 0x09800000 0 0x60000>; + reg = <0 0x00900000 0 0x60000>; interrupts = , , , @@ -1731,6 +1731,8 @@ ufs_mem_phy: phy@1d87000 { clocks = <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_UFS_PHY_PHY_AUX_CLK>; + power-domains = <&gcc UFS_PHY_GDSC>; + resets = <&ufs_mem_hc 0>; reset-names = "ufsphy"; status = "disabled"; @@ -2020,7 +2022,7 @@ mpss: remoteproc@4080000 { compatible = "qcom,sm8350-mpss-pas"; reg = <0x0 0x04080000 0x0 0x4040>; - interrupts-extended = <&intc GIC_SPI 264 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 264 IRQ_TYPE_EDGE_RISING>, <&smp2p_modem_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_modem_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_modem_in 2 IRQ_TYPE_EDGE_RISING>, @@ -2062,7 +2064,7 @@ slpi: remoteproc@5c00000 { compatible = "qcom,sm8350-slpi-pas"; reg = <0 0x05c00000 0 0x4000>; - interrupts-extended = <&pdc 9 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&pdc 9 IRQ_TYPE_EDGE_RISING>, <&smp2p_slpi_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_slpi_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_slpi_in 2 IRQ_TYPE_EDGE_RISING>, @@ -2964,7 +2966,7 @@ qup_uart6_default: qup-uart6-default-state { }; qup_uart18_default: qup-uart18-default-state { - pins = "gpio58", "gpio59"; + pins = "gpio68", "gpio69"; function = "qup18"; drive-strength = <2>; bias-disable; @@ -3206,7 +3208,7 @@ adsp: remoteproc@17300000 { compatible = "qcom,sm8350-adsp-pas"; reg = <0 0x17300000 0 0x100>; - interrupts-extended = <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, @@ -3511,7 +3513,7 @@ cdsp: remoteproc@98900000 { compatible = "qcom,sm8350-cdsp-pas"; reg = <0 0x98900000 0 0x1400000>; - interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 2 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi index 2a60cf8bd891c2..a34f460240a076 100644 --- a/arch/arm64/boot/dts/qcom/sm8450.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi @@ -1025,6 +1025,12 @@ uart20: serial@894000 { pinctrl-names = "default"; pinctrl-0 = <&qup_uart20_default>; interrupts = ; + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; status = "disabled"; }; @@ -1417,6 +1423,12 @@ uart7: serial@99c000 { pinctrl-names = "default"; pinctrl-0 = <&qup_uart7_tx>, <&qup_uart7_rx>; interrupts = ; + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; status = "disabled"; }; }; @@ -1762,12 +1774,8 @@ pcie0: pci@1c00000 { ranges = <0x01000000 0x0 0x00000000 0x0 0x60200000 0x0 0x100000>, <0x02000000 0x0 0x60300000 0x0 0x60300000 0x0 0x3d00000>; - /* - * MSIs for BDF (1:0.0) only works with Device ID 0x5980. - * Hence, the IDs are swapped. - */ - msi-map = <0x0 &gic_its 0x5981 0x1>, - <0x100 &gic_its 0x5980 0x1>; + msi-map = <0x0 &gic_its 0x5980 0x1>, + <0x100 &gic_its 0x5981 0x1>; msi-map-mask = <0xff00>; interrupts = ; interrupt-names = "msi"; @@ -1876,12 +1884,8 @@ pcie1: pci@1c08000 { ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>, <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>; - /* - * MSIs for BDF (1:0.0) only works with Device ID 0x5a00. - * Hence, the IDs are swapped. - */ - msi-map = <0x0 &gic_its 0x5a01 0x1>, - <0x100 &gic_its 0x5a00 0x1>; + msi-map = <0x0 &gic_its 0x5a00 0x1>, + <0x100 &gic_its 0x5a01 0x1>; msi-map-mask = <0xff00>; interrupts = ; interrupt-names = "msi"; @@ -2176,7 +2180,7 @@ wsa2macro: codec@31e0000 { #sound-dai-cells = <1>; }; - swr4: soundwire-controller@31f0000 { + swr4: soundwire@31f0000 { compatible = "qcom,soundwire-v1.7.0"; reg = <0 0x031f0000 0 0x2000>; interrupts = ; @@ -2224,7 +2228,7 @@ rxmacro: codec@3200000 { #sound-dai-cells = <1>; }; - swr1: soundwire-controller@3210000 { + swr1: soundwire@3210000 { compatible = "qcom,soundwire-v1.7.0"; reg = <0 0x03210000 0 0x2000>; interrupts = ; @@ -2291,7 +2295,7 @@ wsamacro: codec@3240000 { #sound-dai-cells = <1>; }; - swr0: soundwire-controller@3250000 { + swr0: soundwire@3250000 { compatible = "qcom,soundwire-v1.7.0"; reg = <0 0x03250000 0 0x2000>; interrupts = ; @@ -2318,14 +2322,14 @@ swr0: soundwire-controller@3250000 { status = "disabled"; }; - swr2: soundwire-controller@33b0000 { + swr2: soundwire@33b0000 { compatible = "qcom,soundwire-v1.7.0"; reg = <0 0x033b0000 0 0x2000>; interrupts = , ; interrupt-names = "core", "wakeup"; - clocks = <&vamacro>; + clocks = <&txmacro>; clock-names = "iface"; label = "TX"; @@ -4196,6 +4200,8 @@ ufs_mem_phy: phy@1d87000 { <&gcc GCC_UFS_PHY_PHY_AUX_CLK>, <&gcc GCC_UFS_0_CLKREF_EN>; + power-domains = <&gcc UFS_PHY_GDSC>; + resets = <&ufs_mem_hc 0>; reset-names = "ufsphy"; status = "disabled"; diff --git a/arch/arm64/boot/dts/qcom/sm8550-mtp.dts b/arch/arm64/boot/dts/qcom/sm8550-mtp.dts index f29cce5186acd5..c4bfe43471f7ca 100644 --- a/arch/arm64/boot/dts/qcom/sm8550-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8550-mtp.dts @@ -743,7 +743,7 @@ &swr2 { wcd_tx: codec@0,3 { compatible = "sdw20217010d00"; reg = <0 3>; - qcom,tx-port-mapping = <1 1 2 3>; + qcom,tx-port-mapping = <2 2 3 4>; }; }; diff --git a/arch/arm64/boot/dts/qcom/sm8550-qrd.dts b/arch/arm64/boot/dts/qcom/sm8550-qrd.dts index 2c09ce8aeafd9b..7a70cc59427979 100644 --- a/arch/arm64/boot/dts/qcom/sm8550-qrd.dts +++ b/arch/arm64/boot/dts/qcom/sm8550-qrd.dts @@ -835,7 +835,7 @@ &swr2 { wcd_tx: codec@0,3 { compatible = "sdw20217010d00"; reg = <0 3>; - qcom,tx-port-mapping = <1 1 2 3>; + qcom,tx-port-mapping = <2 2 3 4>; }; }; diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi index d115960bdeec8a..90e6cd239f5699 100644 --- a/arch/arm64/boot/dts/qcom/sm8550.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi @@ -283,9 +283,9 @@ LITTLE_CPU_SLEEP_0: cpu-sleep-0-0 { compatible = "arm,idle-state"; idle-state-name = "silver-rail-power-collapse"; arm,psci-suspend-param = <0x40000004>; - entry-latency-us = <800>; + entry-latency-us = <550>; exit-latency-us = <750>; - min-residency-us = <4090>; + min-residency-us = <6700>; local-timer-stop; }; @@ -294,8 +294,18 @@ BIG_CPU_SLEEP_0: cpu-sleep-1-0 { idle-state-name = "gold-rail-power-collapse"; arm,psci-suspend-param = <0x40000004>; entry-latency-us = <600>; - exit-latency-us = <1550>; - min-residency-us = <4791>; + exit-latency-us = <1300>; + min-residency-us = <8136>; + local-timer-stop; + }; + + PRIME_CPU_SLEEP_0: cpu-sleep-2-0 { + compatible = "arm,idle-state"; + idle-state-name = "goldplus-rail-power-collapse"; + arm,psci-suspend-param = <0x40000004>; + entry-latency-us = <500>; + exit-latency-us = <1350>; + min-residency-us = <7480>; local-timer-stop; }; }; @@ -304,17 +314,17 @@ domain-idle-states { CLUSTER_SLEEP_0: cluster-sleep-0 { compatible = "domain-idle-state"; arm,psci-suspend-param = <0x41000044>; - entry-latency-us = <1050>; - exit-latency-us = <2500>; - min-residency-us = <5309>; + entry-latency-us = <750>; + exit-latency-us = <2350>; + min-residency-us = <9144>; }; CLUSTER_SLEEP_1: cluster-sleep-1 { compatible = "domain-idle-state"; arm,psci-suspend-param = <0x4100c344>; - entry-latency-us = <2700>; - exit-latency-us = <3500>; - min-residency-us = <13959>; + entry-latency-us = <2800>; + exit-latency-us = <4400>; + min-residency-us = <10150>; }; }; }; @@ -398,7 +408,7 @@ CPU_PD6: power-domain-cpu6 { CPU_PD7: power-domain-cpu7 { #power-domain-cells = <0>; power-domains = <&CLUSTER_PD>; - domain-idle-states = <&BIG_CPU_SLEEP_0>; + domain-idle-states = <&PRIME_CPU_SLEEP_0>; }; CLUSTER_PD: power-domain-cluster { @@ -2034,7 +2044,7 @@ lpass_wsa2macro: codec@6aa0000 { #sound-dai-cells = <1>; }; - swr3: soundwire-controller@6ab0000 { + swr3: soundwire@6ab0000 { compatible = "qcom,soundwire-v2.0.0"; reg = <0 0x06ab0000 0 0x10000>; interrupts = ; @@ -2080,7 +2090,7 @@ lpass_rxmacro: codec@6ac0000 { #sound-dai-cells = <1>; }; - swr1: soundwire-controller@6ad0000 { + swr1: soundwire@6ad0000 { compatible = "qcom,soundwire-v2.0.0"; reg = <0 0x06ad0000 0 0x10000>; interrupts = ; @@ -2145,7 +2155,7 @@ lpass_wsamacro: codec@6b00000 { #sound-dai-cells = <1>; }; - swr0: soundwire-controller@6b10000 { + swr0: soundwire@6b10000 { compatible = "qcom,soundwire-v2.0.0"; reg = <0 0x06b10000 0 0x10000>; interrupts = ; @@ -2172,13 +2182,13 @@ swr0: soundwire-controller@6b10000 { status = "disabled"; }; - swr2: soundwire-controller@6d30000 { + swr2: soundwire@6d30000 { compatible = "qcom,soundwire-v2.0.0"; reg = <0 0x06d30000 0 0x10000>; interrupts = , ; interrupt-names = "core", "wakeup"; - clocks = <&lpass_vamacro>; + clocks = <&lpass_txmacro>; clock-names = "iface"; label = "TX"; @@ -2893,8 +2903,8 @@ usb_1: usb@a6f8800 { interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>, <&pdc 17 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 15 IRQ_TYPE_EDGE_RISING>, - <&pdc 14 IRQ_TYPE_EDGE_RISING>; + <&pdc 15 IRQ_TYPE_EDGE_BOTH>, + <&pdc 14 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", @@ -3007,7 +3017,7 @@ sram@c3f0000 { spmi_bus: spmi@c400000 { compatible = "qcom,spmi-pmic-arb"; reg = <0 0x0c400000 0 0x3000>, - <0 0x0c500000 0 0x4000000>, + <0 0x0c500000 0 0x400000>, <0 0x0c440000 0 0x80000>, <0 0x0c4c0000 0 0x20000>, <0 0x0c42d000 0 0x4000>; diff --git a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi index 4e67a03564971b..84e0eb48a1b8ac 100644 --- a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi @@ -658,7 +658,7 @@ channel7 { avb0: ethernet@e6800000 { compatible = "renesas,etheravb-r8a779a0", "renesas,etheravb-rcar-gen4"; - reg = <0 0xe6800000 0 0x800>; + reg = <0 0xe6800000 0 0x1000>; interrupts = , , , @@ -706,7 +706,7 @@ avb0: ethernet@e6800000 { avb1: ethernet@e6810000 { compatible = "renesas,etheravb-r8a779a0", "renesas,etheravb-rcar-gen4"; - reg = <0 0xe6810000 0 0x800>; + reg = <0 0xe6810000 0 0x1000>; interrupts = , , , @@ -2910,6 +2910,9 @@ timer { interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>, <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>, <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>, - <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>; + <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sec-phys", "phys", "virt", "hyp-phys", + "hyp-virt"; }; }; diff --git a/arch/arm64/boot/dts/renesas/r8a779f0.dtsi b/arch/arm64/boot/dts/renesas/r8a779f0.dtsi index ecdd5a523fa344..555fff9364e35c 100644 --- a/arch/arm64/boot/dts/renesas/r8a779f0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779f0.dtsi @@ -1181,7 +1181,10 @@ timer { interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>, <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>, <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>, - <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>; + <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sec-phys", "phys", "virt", "hyp-phys", + "hyp-virt"; }; ufs30_clk: ufs30-clk { diff --git a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi index bb4a5270f71b6a..913f70fe6c5cd2 100644 --- a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi @@ -187,6 +187,9 @@ &extalr_clk { }; &hscif0 { + pinctrl-0 = <&hscif0_pins>; + pinctrl-names = "default"; + status = "okay"; }; diff --git a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi index d3d25e077c5d50..87fbc53316906c 100644 --- a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi @@ -161,11 +161,6 @@ L3_CA76_1: cache-controller-1 { }; }; - psci { - compatible = "arm,psci-1.0", "arm,psci-0.2"; - method = "smc"; - }; - extal_clk: extal { compatible = "fixed-clock"; #clock-cells = <0>; @@ -185,13 +180,24 @@ pmu_a76 { interrupts-extended = <&gic GIC_PPI 7 IRQ_TYPE_LEVEL_LOW>; }; - /* External SCIF clock - to be overridden by boards that provide it */ + psci { + compatible = "arm,psci-1.0", "arm,psci-0.2"; + method = "smc"; + }; + + /* External SCIF clocks - to be overridden by boards that provide them */ scif_clk: scif { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <0>; }; + scif_clk2: scif2 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + soc: soc { compatible = "simple-bus"; interrupt-parent = <&gic>; @@ -681,7 +687,7 @@ hscif2: serial@e6560000 { interrupts = ; clocks = <&cpg CPG_MOD 516>, <&cpg CPG_CORE R8A779G0_CLK_SASYNCPERD1>, - <&scif_clk>; + <&scif_clk2>; clock-names = "fck", "brg_int", "scif_clk"; dmas = <&dmac0 0x35>, <&dmac0 0x34>, <&dmac1 0x35>, <&dmac1 0x34>; @@ -761,7 +767,7 @@ channel7 { avb0: ethernet@e6800000 { compatible = "renesas,etheravb-r8a779g0", "renesas,etheravb-rcar-gen4"; - reg = <0 0xe6800000 0 0x800>; + reg = <0 0xe6800000 0 0x1000>; interrupts = , , , @@ -808,7 +814,7 @@ avb0: ethernet@e6800000 { avb1: ethernet@e6810000 { compatible = "renesas,etheravb-r8a779g0", "renesas,etheravb-rcar-gen4"; - reg = <0 0xe6810000 0 0x800>; + reg = <0 0xe6810000 0 0x1000>; interrupts = , , , @@ -1057,7 +1063,7 @@ scif4: serial@e6c40000 { interrupts = ; clocks = <&cpg CPG_MOD 705>, <&cpg CPG_CORE R8A779G0_CLK_SASYNCPERD1>, - <&scif_clk>; + <&scif_clk2>; clock-names = "fck", "brg_int", "scif_clk"; dmas = <&dmac0 0x59>, <&dmac0 0x58>, <&dmac1 0x59>, <&dmac1 0x58>; @@ -1777,6 +1783,37 @@ ssi0: ssi-0 { }; }; + mmc0: mmc@ee140000 { + compatible = "renesas,sdhi-r8a779g0", + "renesas,rcar-gen4-sdhi"; + reg = <0 0xee140000 0 0x2000>; + interrupts = ; + clocks = <&cpg CPG_MOD 706>, + <&cpg CPG_CORE R8A779G0_CLK_SD0H>; + clock-names = "core", "clkh"; + power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>; + resets = <&cpg 706>; + max-frequency = <200000000>; + iommus = <&ipmmu_ds0 32>; + status = "disabled"; + }; + + rpc: spi@ee200000 { + compatible = "renesas,r8a779g0-rpc-if", + "renesas,rcar-gen4-rpc-if"; + reg = <0 0xee200000 0 0x200>, + <0 0x08000000 0 0x04000000>, + <0 0xee208000 0 0x100>; + reg-names = "regs", "dirmap", "wbuf"; + interrupts = ; + clocks = <&cpg CPG_MOD 629>; + power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>; + resets = <&cpg 629>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + ipmmu_rt0: iommu@ee480000 { compatible = "renesas,ipmmu-r8a779g0", "renesas,rcar-gen4-ipmmu-vmsa"; @@ -1886,37 +1923,6 @@ ipmmu_mm: iommu@eefc0000 { #iommu-cells = <1>; }; - mmc0: mmc@ee140000 { - compatible = "renesas,sdhi-r8a779g0", - "renesas,rcar-gen4-sdhi"; - reg = <0 0xee140000 0 0x2000>; - interrupts = ; - clocks = <&cpg CPG_MOD 706>, - <&cpg CPG_CORE R8A779G0_CLK_SD0H>; - clock-names = "core", "clkh"; - power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>; - resets = <&cpg 706>; - max-frequency = <200000000>; - iommus = <&ipmmu_ds0 32>; - status = "disabled"; - }; - - rpc: spi@ee200000 { - compatible = "renesas,r8a779g0-rpc-if", - "renesas,rcar-gen4-rpc-if"; - reg = <0 0xee200000 0 0x200>, - <0 0x08000000 0 0x04000000>, - <0 0xee208000 0 0x100>; - reg-names = "regs", "dirmap", "wbuf"; - interrupts = ; - clocks = <&cpg CPG_MOD 629>; - power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>; - resets = <&cpg 629>; - #address-cells = <1>; - #size-cells = <0>; - status = "disabled"; - }; - gic: interrupt-controller@f1000000 { compatible = "arm,gic-v3"; #interrupt-cells = <3>; @@ -2344,6 +2350,9 @@ timer { interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>, <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>, <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>, - <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>; + <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sec-phys", "phys", "virt", "hyp-phys", + "hyp-virt"; }; }; diff --git a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi index 2ab231572d95ff..71d51febabc1e8 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi @@ -50,7 +50,10 @@ timer { interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>, <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>, <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>, - <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>; + <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sec-phys", "phys", "virt", "hyp-phys", + "hyp-virt"; }; }; @@ -109,7 +112,13 @@ irqc: interrupt-controller@110a0000 { , , , - ; + , + , + , + , + , + , + ; interrupt-names = "nmi", "irq0", "irq1", "irq2", "irq3", "irq4", "irq5", "irq6", "irq7", @@ -121,7 +130,9 @@ irqc: interrupt-controller@110a0000 { "tint20", "tint21", "tint22", "tint23", "tint24", "tint25", "tint26", "tint27", "tint28", "tint29", "tint30", "tint31", - "bus-err"; + "bus-err", "ec7tie1-0", "ec7tie2-0", + "ec7tiovf-0", "ec7tie1-1", "ec7tie2-1", + "ec7tiovf-1"; clocks = <&cpg CPG_MOD R9A07G043_IA55_CLK>, <&cpg CPG_MOD R9A07G043_IA55_PCLK>; clock-names = "clk", "pclk"; @@ -134,8 +145,8 @@ gic: interrupt-controller@11900000 { #interrupt-cells = <3>; #address-cells = <0>; interrupt-controller; - reg = <0x0 0x11900000 0 0x40000>, - <0x0 0x11940000 0 0x60000>; + reg = <0x0 0x11900000 0 0x20000>, + <0x0 0x11940000 0 0x40000>; interrupts = ; }; }; diff --git a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi index 66f68fc2b24118..edc942c8463959 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi @@ -905,7 +905,27 @@ irqc: interrupt-controller@110a0000 { , , , - ; + , + , + , + , + , + , + , + ; + interrupt-names = "nmi", "irq0", "irq1", "irq2", "irq3", + "irq4", "irq5", "irq6", "irq7", + "tint0", "tint1", "tint2", "tint3", + "tint4", "tint5", "tint6", "tint7", + "tint8", "tint9", "tint10", "tint11", + "tint12", "tint13", "tint14", "tint15", + "tint16", "tint17", "tint18", "tint19", + "tint20", "tint21", "tint22", "tint23", + "tint24", "tint25", "tint26", "tint27", + "tint28", "tint29", "tint30", "tint31", + "bus-err", "ec7tie1-0", "ec7tie2-0", + "ec7tiovf-0", "ec7tie1-1", "ec7tie2-1", + "ec7tiovf-1"; clocks = <&cpg CPG_MOD R9A07G044_IA55_CLK>, <&cpg CPG_MOD R9A07G044_IA55_PCLK>; clock-names = "clk", "pclk"; @@ -977,8 +997,8 @@ gic: interrupt-controller@11900000 { #interrupt-cells = <3>; #address-cells = <0>; interrupt-controller; - reg = <0x0 0x11900000 0 0x40000>, - <0x0 0x11940000 0 0x60000>; + reg = <0x0 0x11900000 0 0x20000>, + <0x0 0x11940000 0 0x40000>; interrupts = ; }; @@ -1268,6 +1288,9 @@ timer { interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>, <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>, <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>, - <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>; + <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sec-phys", "phys", "virt", "hyp-phys", + "hyp-virt"; }; }; diff --git a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi index 1f1d481dc7830d..d61f7894e55cdd 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi @@ -912,7 +912,27 @@ irqc: interrupt-controller@110a0000 { , , , - ; + , + , + , + , + , + , + , + ; + interrupt-names = "nmi", "irq0", "irq1", "irq2", "irq3", + "irq4", "irq5", "irq6", "irq7", + "tint0", "tint1", "tint2", "tint3", + "tint4", "tint5", "tint6", "tint7", + "tint8", "tint9", "tint10", "tint11", + "tint12", "tint13", "tint14", "tint15", + "tint16", "tint17", "tint18", "tint19", + "tint20", "tint21", "tint22", "tint23", + "tint24", "tint25", "tint26", "tint27", + "tint28", "tint29", "tint30", "tint31", + "bus-err", "ec7tie1-0", "ec7tie2-0", + "ec7tiovf-0", "ec7tie1-1", "ec7tie2-1", + "ec7tiovf-1"; clocks = <&cpg CPG_MOD R9A07G054_IA55_CLK>, <&cpg CPG_MOD R9A07G054_IA55_PCLK>; clock-names = "clk", "pclk"; @@ -984,8 +1004,8 @@ gic: interrupt-controller@11900000 { #interrupt-cells = <3>; #address-cells = <0>; interrupt-controller; - reg = <0x0 0x11900000 0 0x40000>, - <0x0 0x11940000 0 0x60000>; + reg = <0x0 0x11900000 0 0x20000>, + <0x0 0x11940000 0 0x40000>; interrupts = ; }; @@ -1275,6 +1295,9 @@ timer { interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>, <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>, <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>, - <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>; + <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sec-phys", "phys", "virt", "hyp-phys", + "hyp-virt"; }; }; diff --git a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi index 3885ef3454ff6e..50de17e4fb3f25 100644 --- a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi +++ b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi @@ -234,6 +234,7 @@ gpio_exp_74: gpio@74 { gpio-controller; #gpio-cells = <2>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&gpio6>; interrupts = <8 IRQ_TYPE_EDGE_FALLING>; @@ -294,6 +295,7 @@ gpio_exp_75: gpio@75 { gpio-controller; #gpio-cells = <2>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&gpio6>; interrupts = <4 IRQ_TYPE_EDGE_FALLING>; }; @@ -314,6 +316,7 @@ gpio_exp_76: gpio@76 { gpio-controller; #gpio-cells = <2>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&gpio7>; interrupts = <3 IRQ_TYPE_EDGE_FALLING>; }; @@ -324,6 +327,7 @@ gpio_exp_77: gpio@77 { gpio-controller; #gpio-cells = <2>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&gpio5>; interrupts = <9 IRQ_TYPE_EDGE_FALLING>; }; diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi index 42ce78beb4134d..20955556b624d0 100644 --- a/arch/arm64/boot/dts/rockchip/px30.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30.dtsi @@ -632,6 +632,7 @@ spi0: spi@ff1d0000 { clock-names = "spiclk", "apb_pclk"; dmas = <&dmac 12>, <&dmac 13>; dma-names = "tx", "rx"; + num-cs = <2>; pinctrl-names = "default"; pinctrl-0 = <&spi0_clk &spi0_csn &spi0_miso &spi0_mosi>; #address-cells = <1>; @@ -647,6 +648,7 @@ spi1: spi@ff1d8000 { clock-names = "spiclk", "apb_pclk"; dmas = <&dmac 14>, <&dmac 15>; dma-names = "tx", "rx"; + num-cs = <2>; pinctrl-names = "default"; pinctrl-0 = <&spi1_clk &spi1_csn0 &spi1_csn1 &spi1_miso &spi1_mosi>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts b/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts index e9810d2f04071c..5ca0cc19f92c84 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts +++ b/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts @@ -5,6 +5,8 @@ */ /dts-v1/; + +#include #include "rk3308.dtsi" / { @@ -15,6 +17,7 @@ aliases { ethernet0 = &gmac; mmc0 = &emmc; mmc1 = &sdmmc; + mmc2 = &sdio; }; chosen { @@ -24,17 +27,21 @@ chosen { leds { compatible = "gpio-leds"; pinctrl-names = "default"; - pinctrl-0 = <&green_led_gio>, <&heartbeat_led_gpio>; + pinctrl-0 = <&green_led>, <&heartbeat_led>; green-led { + color = ; default-state = "on"; + function = LED_FUNCTION_POWER; gpios = <&gpio0 RK_PA6 GPIO_ACTIVE_HIGH>; label = "rockpis:green:power"; linux,default-trigger = "default-on"; }; blue-led { + color = ; default-state = "on"; + function = LED_FUNCTION_HEARTBEAT; gpios = <&gpio0 RK_PA5 GPIO_ACTIVE_HIGH>; label = "rockpis:blue:user"; linux,default-trigger = "heartbeat"; @@ -126,21 +133,37 @@ &cpu0 { }; &emmc { - bus-width = <4>; cap-mmc-highspeed; - mmc-hs200-1_8v; + cap-sd-highspeed; + no-sdio; non-removable; + pinctrl-names = "default"; + pinctrl-0 = <&emmc_bus8 &emmc_clk &emmc_cmd>; vmmc-supply = <&vcc_io>; status = "okay"; }; &gmac { clock_in_out = "output"; + phy-handle = <&rtl8201f>; phy-supply = <&vcc_io>; - snps,reset-gpio = <&gpio0 RK_PA7 GPIO_ACTIVE_LOW>; - snps,reset-active-low; - snps,reset-delays-us = <0 50000 50000>; status = "okay"; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + rtl8201f: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + pinctrl-names = "default"; + pinctrl-0 = <&mac_rst>; + reset-assert-us = <20000>; + reset-deassert-us = <50000>; + reset-gpios = <&gpio0 RK_PA7 GPIO_ACTIVE_LOW>; + }; + }; }; &i2c1 { @@ -151,12 +174,32 @@ &pinctrl { pinctrl-names = "default"; pinctrl-0 = <&rtc_32k>; + bluetooth { + bt_reg_on: bt-reg-on { + rockchip,pins = <4 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + bt_wake_host: bt-wake-host { + rockchip,pins = <4 RK_PB4 RK_FUNC_GPIO &pcfg_pull_down>; + }; + + host_wake_bt: host-wake-bt { + rockchip,pins = <4 RK_PB2 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + gmac { + mac_rst: mac-rst { + rockchip,pins = <0 RK_PA7 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + leds { - green_led_gio: green-led-gpio { + green_led: green-led { rockchip,pins = <0 RK_PA6 RK_FUNC_GPIO &pcfg_pull_none>; }; - heartbeat_led_gpio: heartbeat-led-gpio { + heartbeat_led: heartbeat-led { rockchip,pins = <0 RK_PA5 RK_FUNC_GPIO &pcfg_pull_none>; }; }; @@ -194,15 +237,31 @@ &sdio { cap-sd-highspeed; cap-sdio-irq; keep-power-in-suspend; - max-frequency = <1000000>; + max-frequency = <100000000>; mmc-pwrseq = <&sdio_pwrseq>; + no-mmc; + no-sd; non-removable; - sd-uhs-sdr104; + sd-uhs-sdr50; + vmmc-supply = <&vcc_io>; + vqmmc-supply = <&vcc_1v8>; status = "okay"; + + rtl8723ds: wifi@1 { + reg = <1>; + interrupt-parent = <&gpio0>; + interrupts = ; + interrupt-names = "host-wake"; + pinctrl-names = "default"; + pinctrl-0 = <&wifi_host_wake>; + }; }; &sdmmc { + cap-mmc-highspeed; cap-sd-highspeed; + disable-wp; + vmmc-supply = <&vcc_io>; status = "okay"; }; @@ -221,16 +280,22 @@ u2phy_otg: otg-port { }; &uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_xfer>; status = "okay"; }; &uart4 { + uart-has-rtscts; status = "okay"; bluetooth { - compatible = "realtek,rtl8723bs-bt"; - device-wake-gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_HIGH>; + compatible = "realtek,rtl8723ds-bt"; + device-wake-gpios = <&gpio4 RK_PB2 GPIO_ACTIVE_HIGH>; + enable-gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_HIGH>; host-wake-gpios = <&gpio4 RK_PB4 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&bt_reg_on &bt_wake_host &host_wake_bt>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts index 5d7d567283e525..4237f2ee8fee33 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts @@ -26,9 +26,11 @@ yt8531c: ethernet-phy@0 { compatible = "ethernet-phy-ieee802.3-c22"; reg = <0>; + motorcomm,auto-sleep-disabled; motorcomm,clk-out-frequency-hz = <125000000>; motorcomm,keep-pll-enabled; - motorcomm,auto-sleep-disabled; + motorcomm,rx-clk-drv-microamp = <5020>; + motorcomm,rx-data-drv-microamp = <5020>; pinctrl-0 = <ð_phy_reset_pin>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts index 018a3a5075c72e..66443d52cd34d8 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts @@ -186,8 +186,8 @@ &i2c1 { rk805: pmic@18 { compatible = "rockchip,rk805"; reg = <0x18>; - interrupt-parent = <&gpio2>; - interrupts = <6 IRQ_TYPE_LEVEL_LOW>; + interrupt-parent = <&gpio0>; + interrupts = <2 IRQ_TYPE_LEVEL_LOW>; #clock-cells = <1>; clock-output-names = "xin32k", "rk805-clkout2"; gpio-controller; @@ -332,7 +332,7 @@ led_pin: led-pin { pmic { pmic_int_l: pmic-int-l { - rockchip,pins = <2 RK_PA6 RK_FUNC_GPIO &pcfg_pull_up>; + rockchip,pins = <0 RK_PA2 RK_FUNC_GPIO &pcfg_pull_up>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index e729e7a22b23a6..126165ba1ea260 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -668,7 +668,7 @@ vpu_mmu: iommu@ff350800 { vdec: video-codec@ff360000 { compatible = "rockchip,rk3328-vdec", "rockchip,rk3399-vdec"; - reg = <0x0 0xff360000 0x0 0x400>; + reg = <0x0 0xff360000 0x0 0x480>; interrupts = ; clocks = <&cru ACLK_RKVDEC>, <&cru HCLK_RKVDEC>, <&cru SCLK_VDEC_CABAC>, <&cru SCLK_VDEC_CORE>; @@ -743,11 +743,20 @@ hdmi: hdmi@ff3c0000 { status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; + hdmi_in_vop: endpoint { remote-endpoint = <&vop_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; @@ -813,8 +822,8 @@ cru: clock-controller@ff440000 { <0>, <24000000>, <24000000>, <24000000>, <15000000>, <15000000>, - <100000000>, <100000000>, - <100000000>, <100000000>, + <300000000>, <100000000>, + <400000000>, <100000000>, <50000000>, <100000000>, <100000000>, <100000000>, <50000000>, <50000000>, diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index a4c5aaf1f45794..cac58ad951b2e3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -790,6 +790,7 @@ spdif: spdif@ff880000 { dma-names = "tx"; pinctrl-names = "default"; pinctrl-0 = <&spdif_tx>; + #sound-dai-cells = <0>; status = "disabled"; }; @@ -801,6 +802,7 @@ i2s_2ch: i2s-2ch@ff890000 { clocks = <&cru SCLK_I2S_2CH>, <&cru HCLK_I2S_2CH>; dmas = <&dmac_bus 6>, <&dmac_bus 7>; dma-names = "tx", "rx"; + #sound-dai-cells = <0>; status = "disabled"; }; @@ -814,6 +816,7 @@ i2s_8ch: i2s-8ch@ff898000 { dma-names = "tx", "rx"; pinctrl-names = "default"; pinctrl-0 = <&i2s_8ch_bus>; + #sound-dai-cells = <0>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi index 5c1929d41cc0b7..cacbad35cfc854 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi @@ -509,8 +509,7 @@ wacky_spi_audio: spi2@0 { &pci_rootport { mvl_wifi: wifi@0,0 { compatible = "pci1b4b,2b42"; - reg = <0x83010000 0x0 0x00000000 0x0 0x00100000 - 0x83010000 0x0 0x00100000 0x0 0x00100000>; + reg = <0x0000 0x0 0x0 0x0 0x0>; interrupt-parent = <&gpio0>; interrupts = <8 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts index 853e88455e750e..9e4b12ed62cbed 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts @@ -34,8 +34,8 @@ &mipi_panel { &pci_rootport { wifi@0,0 { compatible = "qcom,ath10k"; - reg = <0x00010000 0x0 0x00000000 0x0 0x00000000>, - <0x03010010 0x0 0x00000000 0x0 0x00200000>; + reg = <0x00000000 0x0 0x00000000 0x0 0x00000000>, + <0x03000010 0x0 0x00000000 0x0 0x00200000>; qcom,ath10k-calibration-variant = "GO_DUMO"; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi index c9bf1d5c3a4264..3cd63d1e8f15bb 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi @@ -450,7 +450,7 @@ da7219_aad { dlg,btn-cfg = <50>; dlg,mic-det-thr = <500>; dlg,jack-ins-deb = <20>; - dlg,jack-det-rate = "32ms_64ms"; + dlg,jack-det-rate = "32_64"; dlg,jack-rem-deb = <1>; dlg,a-d-btn-thr = <0xa>; @@ -489,6 +489,7 @@ pci_rootport: pcie@0,0 { #address-cells = <3>; #size-cells = <2>; ranges; + device_type = "pci"; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts index 054c6a4d1a45f7..f5e124b235c83c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts @@ -32,12 +32,12 @@ chosen { backlight: edp-backlight { compatible = "pwm-backlight"; power-supply = <&vcc_12v>; - pwms = <&pwm0 0 740740 0>; + pwms = <&pwm0 0 125000 0>; }; bat: battery { compatible = "simple-battery"; - charge-full-design-microamp-hours = <9800000>; + charge-full-design-microamp-hours = <10000000>; voltage-max-design-microvolt = <4350000>; voltage-min-design-microvolt = <3000000>; }; @@ -779,7 +779,6 @@ &pcie_phy { }; &pcie0 { - bus-scan-delay-ms = <1000>; ep-gpios = <&gpio2 RK_PD4 GPIO_ACTIVE_HIGH>; num-lanes = <4>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index 20e3f41efe97fa..aba2748fe54c77 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -119,6 +119,22 @@ &emmc_phy { drive-impedance-ohm = <33>; }; +&gpio3 { + /* + * The Qseven BIOS_DISABLE signal on the RK3399-Q7 keeps the on-module + * eMMC and SPI flash powered-down initially (in fact it keeps the + * reset signal asserted). BIOS_DISABLE_OVERRIDE pin allows to override + * that signal so that eMMC and SPI can be used regardless of the state + * of the signal. + */ + bios-disable-override-hog { + gpios = ; + gpio-hog; + line-name = "bios_disable_override"; + output-high; + }; +}; + &gmac { assigned-clocks = <&cru SCLK_RMII_SRC>; assigned-clock-parents = <&clkin_gmac>; @@ -374,6 +390,7 @@ vdd_cpu_b: regulator@60 { &i2s0 { pinctrl-0 = <&i2s0_2ch_bus>; + pinctrl-1 = <&i2s0_2ch_bus_bclk_off>; rockchip,playback-channels = <2>; rockchip,capture-channels = <2>; status = "okay"; @@ -382,8 +399,8 @@ &i2s0 { /* * As Q7 does not specify neither a global nor a RX clock for I2S these * signals are not used. Furthermore I2S0_LRCK_RX is used as GPIO. - * Therefore we have to redefine the i2s0_2ch_bus definition to prevent - * conflicts. + * Therefore we have to redefine the i2s0_2ch_bus and i2s0_2ch_bus_bclk_off + * definitions to prevent conflicts. */ &i2s0_2ch_bus { rockchip,pins = @@ -393,6 +410,14 @@ &i2s0_2ch_bus { <3 RK_PD7 1 &pcfg_pull_none>; }; +&i2s0_2ch_bus_bclk_off { + rockchip,pins = + <3 RK_PD0 RK_FUNC_GPIO &pcfg_pull_none>, + <3 RK_PD2 1 &pcfg_pull_none>, + <3 RK_PD3 1 &pcfg_pull_none>, + <3 RK_PD7 1 &pcfg_pull_none>; +}; + &io_domains { status = "okay"; bt656-supply = <&vcc_1v8>; @@ -401,16 +426,27 @@ &io_domains { gpio1830-supply = <&vcc_1v8>; }; -&pmu_io_domains { - status = "okay"; - pmu1830-supply = <&vcc_1v8>; -}; - -&pwm2 { - status = "okay"; +&pcie_clkreqn_cpm { + rockchip,pins = + <2 RK_PD2 RK_FUNC_GPIO &pcfg_pull_up>; }; &pinctrl { + pinctrl-names = "default"; + pinctrl-0 = <&q7_thermal_pin &bios_disable_override_hog_pin>; + + gpios { + bios_disable_override_hog_pin: bios-disable-override-hog-pin { + rockchip,pins = + <3 RK_PD5 RK_FUNC_GPIO &pcfg_pull_down>; + }; + + q7_thermal_pin: q7-thermal-pin { + rockchip,pins = + <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; + i2c8 { i2c8_xfer_a: i2c8-xfer { rockchip,pins = @@ -443,11 +479,20 @@ vcc5v0_host_en: vcc5v0-host-en { usb3 { usb3_id: usb3-id { rockchip,pins = - <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>; + <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_up>; }; }; }; +&pmu_io_domains { + status = "okay"; + pmu1830-supply = <&vcc_1v8>; +}; + +&pwm2 { + status = "okay"; +}; + &sdhci { /* * Signal integrity isn't great at 200MHz but 100MHz has proven stable diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 5bc2d4faeea6df..fb1ea84c2b14fe 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1109,7 +1109,9 @@ power-domain@RK3399_PD_VCODEC { power-domain@RK3399_PD_VDU { reg = ; clocks = <&cru ACLK_VDU>, - <&cru HCLK_VDU>; + <&cru HCLK_VDU>, + <&cru SCLK_VDU_CA>, + <&cru SCLK_VDU_CORE>; pm_qos = <&qos_video_m1_r>, <&qos_video_m1_w>; #power-domain-cells = <0>; @@ -1385,7 +1387,7 @@ vpu_mmu: iommu@ff650800 { vdec: video-codec@ff660000 { compatible = "rockchip,rk3399-vdec"; - reg = <0x0 0xff660000 0x0 0x400>; + reg = <0x0 0xff660000 0x0 0x480>; interrupts = ; clocks = <&cru ACLK_VDU>, <&cru HCLK_VDU>, <&cru SCLK_VDU_CA>, <&cru SCLK_VDU_CORE>; @@ -1951,6 +1953,7 @@ simple-audio-card,codec { hdmi: hdmi@ff940000 { compatible = "rockchip,rk3399-dw-hdmi"; reg = <0x0 0xff940000 0x0 0x20000>; + reg-io-width = <4>; interrupts = ; clocks = <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_SFR>, @@ -1959,13 +1962,16 @@ hdmi: hdmi@ff940000 { <&cru PLL_VPLL>; clock-names = "iahb", "isfr", "cec", "grf", "ref"; power-domains = <&power RK3399_PD_HDCP>; - reg-io-width = <4>; rockchip,grf = <&grf>; #sound-dai-cells = <0>; status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; #address-cells = <1>; #size-cells = <0>; @@ -1978,6 +1984,10 @@ hdmi_in_vopl: endpoint@1 { remote-endpoint = <&vopl_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts index 1c6d83b47cd217..6ecdf5d283390a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts @@ -455,7 +455,7 @@ &pcie2x1 { &pinctrl { leds { sys_led_pin: sys-status-led-pin { - rockchip,pins = <0 RK_PC7 RK_FUNC_GPIO &pcfg_pull_none>; + rockchip,pins = <0 RK_PC5 RK_FUNC_GPIO &pcfg_pull_none>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts index 2d92713be2a09f..6195937aa6dc5f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts @@ -289,7 +289,7 @@ vdd_gpu: DCDC_REG2 { regulator-name = "vdd_gpu"; regulator-always-on; regulator-boot-on; - regulator-min-microvolt = <900000>; + regulator-min-microvolt = <500000>; regulator-max-microvolt = <1350000>; regulator-ramp-delay = <6001>; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts b/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts index 938092fce18661..68a72ac24cd4b4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts @@ -268,7 +268,7 @@ rk809: pmic@20 { vcc9-supply = <&vcc3v3_sys>; codec { - mic-in-differential; + rockchip,mic-in-differential; }; regulators { diff --git a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts index f9127ddfbb7dfd..dc5892d25c1000 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts @@ -416,6 +416,8 @@ regulator-state-mem { vccio_sd: LDO_REG5 { regulator-name = "vccio_sd"; + regulator-always-on; + regulator-boot-on; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; @@ -525,9 +527,9 @@ &mdio0 { #address-cells = <1>; #size-cells = <0>; - switch@0 { + switch@1f { compatible = "mediatek,mt7531"; - reg = <0>; + reg = <0x1f>; ports { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts index 19f8fc369b1308..8c3ab07d380797 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts @@ -475,7 +475,7 @@ regulator-state-mem { }; codec { - mic-in-differential; + rockchip,mic-in-differential; }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dts b/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dts index 58ab7e9971dbce..b5e67990dd0f8b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dts @@ -11,6 +11,10 @@ aliases { }; }; +&pmu_io_domains { + vccio3-supply = <&vccio_sd>; +}; + &sdmmc0 { bus-width = <4>; cap-mmc-highspeed; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dtsi b/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dtsi index 89e84e3a92629a..25c49bdbadbcba 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dtsi @@ -39,9 +39,9 @@ status_led: led-status { }; }; - dc_12v: dc-12v-regulator { + vcc12v_dcin: vcc12v-dcin-regulator { compatible = "regulator-fixed"; - regulator-name = "dc_12v"; + regulator-name = "vcc12v_dcin"; regulator-always-on; regulator-boot-on; regulator-min-microvolt = <12000000>; @@ -65,7 +65,7 @@ vcc3v3_sys: vcc3v3-sys-regulator { regulator-boot-on; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; - vin-supply = <&dc_12v>; + vin-supply = <&vcc12v_dcin>; }; vcc5v0_sys: vcc5v0-sys-regulator { @@ -75,16 +75,7 @@ vcc5v0_sys: vcc5v0-sys-regulator { regulator-boot-on; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; - vin-supply = <&dc_12v>; - }; - - vcc5v0_usb_host: vcc5v0-usb-host-regulator { - compatible = "regulator-fixed"; - regulator-name = "vcc5v0_usb_host"; - regulator-always-on; - regulator-boot-on; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; + vin-supply = <&vcc12v_dcin>; }; vcc5v0_usb_otg: vcc5v0-usb-otg-regulator { @@ -94,8 +85,9 @@ vcc5v0_usb_otg: vcc5v0-usb-otg-regulator { pinctrl-names = "default"; pinctrl-0 = <&vcc5v0_usb_otg_en>; regulator-name = "vcc5v0_usb_otg"; - regulator-always-on; - regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vcc5v0_sys>; }; }; @@ -123,6 +115,10 @@ &cpu3 { cpu-supply = <&vdd_cpu>; }; +&display_subsystem { + status = "disabled"; +}; + &gpu { mali-supply = <&vdd_gpu>; status = "okay"; @@ -405,8 +401,8 @@ vcc5v0_usb_otg_en: vcc5v0-usb-otg-en { &pmu_io_domains { pmuio1-supply = <&vcc3v3_pmu>; pmuio2-supply = <&vcc3v3_pmu>; - vccio1-supply = <&vccio_acodec>; - vccio3-supply = <&vccio_sd>; + vccio1-supply = <&vcc_3v3>; + vccio2-supply = <&vcc_1v8>; vccio4-supply = <&vcc_1v8>; vccio5-supply = <&vcc_3v3>; vccio6-supply = <&vcc_1v8>; @@ -429,28 +425,12 @@ &uart2 { status = "okay"; }; -&usb_host0_ehci { - status = "okay"; -}; - -&usb_host0_ohci { - status = "okay"; -}; - &usb_host0_xhci { dr_mode = "host"; extcon = <&usb2phy0>; status = "okay"; }; -&usb_host1_ehci { - status = "okay"; -}; - -&usb_host1_ohci { - status = "okay"; -}; - &usb_host1_xhci { status = "okay"; }; @@ -460,7 +440,7 @@ &usb2phy0 { }; &usb2phy0_host { - phy-supply = <&vcc5v0_usb_host>; + phy-supply = <&vcc5v0_sys>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r68s.dts b/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r68s.dts index e1fe5e442689a0..ce2a5e1ccefc3f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r68s.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r68s.dts @@ -39,7 +39,7 @@ &gmac0_tx_bus2 &gmac0_rx_bus2 &gmac0_rgmii_clk &gmac0_rgmii_bus>; - snps,reset-gpio = <&gpio0 RK_PB0 GPIO_ACTIVE_LOW>; + snps,reset-gpio = <&gpio1 RK_PB0 GPIO_ACTIVE_LOW>; snps,reset-active-low; /* Reset time is 15ms, 50ms for rtl8211f */ snps,reset-delays-us = <0 15000 50000>; @@ -61,7 +61,7 @@ &gmac1m1_tx_bus2 &gmac1m1_rx_bus2 &gmac1m1_rgmii_clk &gmac1m1_rgmii_bus>; - snps,reset-gpio = <&gpio0 RK_PB1 GPIO_ACTIVE_LOW>; + snps,reset-gpio = <&gpio1 RK_PB1 GPIO_ACTIVE_LOW>; snps,reset-active-low; /* Reset time is 15ms, 50ms for rtl8211f */ snps,reset-delays-us = <0 15000 50000>; @@ -71,18 +71,18 @@ &gmac1m1_rgmii_clk }; &mdio0 { - rgmii_phy0: ethernet-phy@0 { + rgmii_phy0: ethernet-phy@1 { compatible = "ethernet-phy-ieee802.3-c22"; - reg = <0>; + reg = <0x1>; pinctrl-0 = <ð_phy0_reset_pin>; pinctrl-names = "default"; }; }; &mdio1 { - rgmii_phy1: ethernet-phy@0 { + rgmii_phy1: ethernet-phy@1 { compatible = "ethernet-phy-ieee802.3-c22"; - reg = <0>; + reg = <0x1>; pinctrl-0 = <ð_phy1_reset_pin>; pinctrl-names = "default"; }; @@ -102,6 +102,10 @@ eth_phy1_reset_pin: eth-phy1-reset-pin { }; }; +&pmu_io_domains { + vccio3-supply = <&vcc_3v3>; +}; + &sdhci { bus-width = <8>; max-frequency = <200000000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts index a337f547caf538..6a02db4f073f29 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts @@ -13,7 +13,7 @@ / { model = "Hardkernel ODROID-M1"; - compatible = "rockchip,rk3568-odroid-m1", "rockchip,rk3568"; + compatible = "hardkernel,odroid-m1", "rockchip,rk3568"; aliases { ethernet0 = &gmac0; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts index e05ab11981f554..17830e8c9a59be 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts @@ -530,10 +530,6 @@ regulator-state-mem { }; }; }; - - codec { - mic-in-differential; - }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk356x.dtsi b/arch/arm64/boot/dts/rockchip/rk356x.dtsi index abee88911982d4..2f885bc3665b5c 100644 --- a/arch/arm64/boot/dts/rockchip/rk356x.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk356x.dtsi @@ -597,6 +597,7 @@ vpu: video-codec@fdea0400 { compatible = "rockchip,rk3568-vpu"; reg = <0x0 0xfdea0000 0x0 0x800>; interrupts = ; + interrupt-names = "vdpu"; clocks = <&cru ACLK_VPU>, <&cru HCLK_VPU>; clock-names = "aclk", "hclk"; iommus = <&vdpu_mmu>; @@ -748,6 +749,7 @@ vop_mmu: iommu@fe043e00 { clocks = <&cru ACLK_VOP>, <&cru HCLK_VOP>; clock-names = "aclk", "iface"; #iommu-cells = <0>; + power-domains = <&power RK3568_PD_VO>; status = "disabled"; }; @@ -970,7 +972,7 @@ pcie2x1: pcie@fe260000 { , , ; - interrupt-names = "sys", "pmc", "msi", "legacy", "err"; + interrupt-names = "sys", "pmc", "msg", "legacy", "err"; bus-range = <0x0 0xf>; clocks = <&cru ACLK_PCIE20_MST>, <&cru ACLK_PCIE20_SLV>, <&cru ACLK_PCIE20_DBI>, <&cru PCLK_PCIE20>, @@ -1116,7 +1118,7 @@ i2s2_2ch: i2s@fe420000 { dmas = <&dmac1 4>, <&dmac1 5>; dma-names = "tx", "rx"; resets = <&cru SRST_M_I2S2_2CH>; - reset-names = "m"; + reset-names = "tx-m"; rockchip,grf = <&grf>; pinctrl-names = "default"; pinctrl-0 = <&i2s2m0_sclktx diff --git a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts index 229a9111f5eb05..fa8286a325af74 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts @@ -215,6 +215,7 @@ pmic@0 { <&rk806_dvs2_null>, <&rk806_dvs3_null>; pinctrl-names = "default"; spi-max-frequency = <1000000>; + system-power-controller; vcc1-supply = <&vcc5v0_sys>; vcc2-supply = <&vcc5v0_sys>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts index 0bd80e51575448..97af4f91282854 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts @@ -137,6 +137,18 @@ vbus5v0_typec: vbus5v0-typec-regulator { vin-supply = <&vcc5v0_sys>; }; + vcc3v3_pcie2x1l0: vcc3v3-pcie2x1l0-regulator { + compatible = "regulator-fixed"; + enable-active-high; + gpio = <&gpio4 RK_PC2 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&pcie_m2_1_pwren>; + regulator-name = "vcc3v3_pcie2x1l0"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc5v0_sys>; + }; + vcc3v3_pcie30: vcc3v3-pcie30-regulator { compatible = "regulator-fixed"; enable-active-high; @@ -421,6 +433,14 @@ &pcie2x1l0 { status = "okay"; }; +&pcie2x1l1 { + reset-gpios = <&gpio4 RK_PA2 GPIO_ACTIVE_HIGH>; + vpcie3v3-supply = <&vcc3v3_pcie2x1l0>; + pinctrl-names = "default"; + pinctrl-0 = <&pcie2_1_rst>; + status = "okay"; +}; + &pcie2x1l2 { reset-gpios = <&gpio4 RK_PA4 GPIO_ACTIVE_HIGH>; vpcie3v3-supply = <&vcc_3v3_pcie20>; @@ -467,6 +487,10 @@ pcie2_0_rst: pcie2-0-rst { rockchip,pins = <4 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>; }; + pcie2_1_rst: pcie2-1-rst { + rockchip,pins = <4 RK_PA2 RK_FUNC_GPIO &pcfg_pull_none>; + }; + pcie2_2_rst: pcie2-2-rst { rockchip,pins = <4 RK_PA4 RK_FUNC_GPIO &pcfg_pull_none>; }; @@ -474,6 +498,10 @@ pcie2_2_rst: pcie2-2-rst { pcie_m2_0_pwren: pcie-m20-pwren { rockchip,pins = <2 RK_PC5 RK_FUNC_GPIO &pcfg_pull_none>; }; + + pcie_m2_1_pwren: pcie-m21-pwren { + rockchip,pins = <4 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>; + }; }; usb { diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts index d1503a4b233a39..9299fa7e3e2150 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts @@ -163,13 +163,13 @@ &gpio0 { &gpio1 { gpio-line-names = /* GPIO1 A0-A7 */ - "HEADER_27_3v3", "HEADER_28_3v3", "", "", + "HEADER_27_3v3", "", "", "", "HEADER_29_1v8", "", "HEADER_7_1v8", "", /* GPIO1 B0-B7 */ "", "HEADER_31_1v8", "HEADER_33_1v8", "", "HEADER_11_1v8", "HEADER_13_1v8", "", "", /* GPIO1 C0-C7 */ - "", "", "", "", + "", "HEADER_28_3v3", "", "", "", "", "", "", /* GPIO1 D0-D7 */ "", "", "", "", @@ -193,11 +193,11 @@ &gpio3 { &gpio4 { gpio-line-names = /* GPIO4 A0-A7 */ - "", "", "HEADER_37_3v3", "HEADER_32_3v3", - "HEADER_36_3v3", "", "HEADER_35_3v3", "HEADER_38_3v3", + "", "", "HEADER_37_3v3", "HEADER_8_3v3", + "HEADER_10_3v3", "", "HEADER_32_3v3", "HEADER_35_3v3", /* GPIO4 B0-B7 */ "", "", "", "HEADER_40_3v3", - "HEADER_8_3v3", "HEADER_10_3v3", "", "", + "HEADER_38_3v3", "HEADER_36_3v3", "", "", /* GPIO4 C0-C7 */ "", "", "", "", "", "", "", "", diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi index 48181671eacb0d..0933652bafc301 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi @@ -369,7 +369,7 @@ emmc_cmd: emmc-cmd { emmc_data_strobe: emmc-data-strobe { rockchip,pins = /* emmc_data_strobe */ - <2 RK_PA2 1 &pcfg_pull_none>; + <2 RK_PA2 1 &pcfg_pull_down>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts index 8347adcbd00301..68763714f7f7bc 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts @@ -390,6 +390,7 @@ pmic@0 { pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>, <&rk806_dvs2_null>, <&rk806_dvs3_null>; spi-max-frequency = <1000000>; + system-power-controller; vcc1-supply = <&vcc5v0_sys>; vcc2-supply = <&vcc5v0_sys>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi index 5544f66c6ff411..aa18cf1d1afaa1 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi @@ -890,6 +890,7 @@ power-domain@RK3588_PD_USB { reg = ; clocks = <&cru PCLK_PHP_ROOT>, <&cru ACLK_USB_ROOT>, + <&cru ACLK_USB>, <&cru HCLK_USB_ROOT>, <&cru HCLK_HOST0>, <&cru HCLK_HOST_ARB0>, @@ -1541,7 +1542,6 @@ i2s2_2ch: i2s@fe490000 { dmas = <&dmac1 0>, <&dmac1 1>; dma-names = "tx", "rx"; power-domains = <&power RK3588_PD_AUDIO>; - rockchip,trcm-sync-tx-only; pinctrl-names = "default"; pinctrl-0 = <&i2s2m1_lrck &i2s2m1_sclk @@ -1562,7 +1562,6 @@ i2s3_2ch: i2s@fe4a0000 { dmas = <&dmac1 2>, <&dmac1 3>; dma-names = "tx", "rx"; power-domains = <&power RK3588_PD_AUDIO>; - rockchip,trcm-sync-tx-only; pinctrl-names = "default"; pinctrl-0 = <&i2s3_lrck &i2s3_sclk diff --git a/arch/arm64/boot/dts/sprd/ums512.dtsi b/arch/arm64/boot/dts/sprd/ums512.dtsi index 024be594c47d17..cc4459551e05e1 100644 --- a/arch/arm64/boot/dts/sprd/ums512.dtsi +++ b/arch/arm64/boot/dts/sprd/ums512.dtsi @@ -96,7 +96,7 @@ CPU5: cpu@500 { CPU6: cpu@600 { device_type = "cpu"; - compatible = "arm,cortex-a55"; + compatible = "arm,cortex-a75"; reg = <0x0 0x600>; enable-method = "psci"; cpu-idle-states = <&CORE_PD>; @@ -104,7 +104,7 @@ CPU6: cpu@600 { CPU7: cpu@700 { device_type = "cpu"; - compatible = "arm,cortex-a55"; + compatible = "arm,cortex-a75"; reg = <0x0 0x700>; enable-method = "psci"; cpu-idle-states = <&CORE_PD>; @@ -113,7 +113,7 @@ CPU7: cpu@700 { idle-states { entry-method = "psci"; - CORE_PD: core-pd { + CORE_PD: cpu-pd { compatible = "arm,idle-state"; entry-latency-us = <4000>; exit-latency-us = <4000>; @@ -291,6 +291,7 @@ anlg_phy_gc_regs: syscon@323e0000 { pll2: clock-controller@0 { compatible = "sprd,ums512-gc-pll"; reg = <0x0 0x100>; + clocks = <&ext_26m>; clock-names = "ext-26m"; #clock-cells = <1>; }; diff --git a/arch/arm64/boot/dts/ti/Makefile b/arch/arm64/boot/dts/ti/Makefile index e7b8e2e7f083db..8bd5acc6d68351 100644 --- a/arch/arm64/boot/dts/ti/Makefile +++ b/arch/arm64/boot/dts/ti/Makefile @@ -9,6 +9,8 @@ # alphabetically. # Boards with AM62x SoC +k3-am625-sk-hdmi-audio-dtbs := k3-am625-sk.dtb k3-am62x-sk-hdmi-audio.dtbo +k3-am62-lp-sk-hdmi-audio-dtbs := k3-am62-lp-sk.dtb k3-am62x-sk-hdmi-audio.dtbo dtb-$(CONFIG_ARCH_K3) += k3-am625-beagleplay.dtb dtb-$(CONFIG_ARCH_K3) += k3-am625-phyboard-lyra-rdk.dtb dtb-$(CONFIG_ARCH_K3) += k3-am625-sk.dtb @@ -19,7 +21,8 @@ dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-wifi-dahlia.dtb dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-wifi-dev.dtb dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-wifi-yavia.dtb dtb-$(CONFIG_ARCH_K3) += k3-am62-lp-sk.dtb -dtb-$(CONFIG_ARCH_K3) += k3-am62x-sk-hdmi-audio.dtbo +dtb-$(CONFIG_ARCH_K3) += k3-am625-sk-hdmi-audio.dtb +dtb-$(CONFIG_ARCH_K3) += k3-am62-lp-sk-hdmi-audio.dtb # Boards with AM62Ax SoC dtb-$(CONFIG_ARCH_K3) += k3-am62a7-sk.dtb @@ -66,6 +69,8 @@ dtb-$(CONFIG_ARCH_K3) += k3-j721e-sk.dtb dtb-$(CONFIG_ARCH_K3) += k3-am68-sk-base-board.dtb dtb-$(CONFIG_ARCH_K3) += k3-j721s2-common-proc-board.dtb dtb-$(CONFIG_ARCH_K3) += k3-j721s2-evm-gesi-exp-board.dtbo +k3-j721s2-evm-dtbs := k3-j721s2-common-proc-board.dtb k3-j721s2-evm-gesi-exp-board.dtbo +dtb-$(CONFIG_ARCH_K3) += k3-j721s2-evm.dtb # Boards with J784s4 SoC dtb-$(CONFIG_ARCH_K3) += k3-am69-sk.dtb diff --git a/arch/arm64/boot/dts/ti/k3-am62-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62-main.dtsi index 284b90c94da8a2..a9b47ab92a02c7 100644 --- a/arch/arm64/boot/dts/ti/k3-am62-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62-main.dtsi @@ -613,6 +613,8 @@ usb0: usb@31000000 { interrupt-names = "host", "peripheral"; maximum-speed = "high-speed"; dr_mode = "otg"; + snps,usb2-gadget-lpm-disable; + snps,usb2-lpm-disable; }; }; @@ -636,6 +638,8 @@ usb1: usb@31100000 { interrupt-names = "host", "peripheral"; maximum-speed = "high-speed"; dr_mode = "otg"; + snps,usb2-gadget-lpm-disable; + snps,usb2-lpm-disable; }; }; @@ -743,9 +747,10 @@ dss: dss@30200000 { <0x00 0x30207000 0x00 0x1000>, /* ovr1 */ <0x00 0x30208000 0x00 0x1000>, /* ovr2 */ <0x00 0x3020a000 0x00 0x1000>, /* vp1: Used for OLDI */ - <0x00 0x3020b000 0x00 0x1000>; /* vp2: Used as DPI Out */ + <0x00 0x3020b000 0x00 0x1000>, /* vp2: Used as DPI Out */ + <0x00 0x30201000 0x00 0x1000>; /* common1 */ reg-names = "common", "vidl1", "vid", - "ovr1", "ovr2", "vp1", "vp2"; + "ovr1", "ovr2", "vp1", "vp2", "common1"; power-domains = <&k3_pds 186 TI_SCI_PD_EXCLUSIVE>; clocks = <&k3_clks 186 6>, <&dss_vp1_clk>, diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi index 40992e7e4c3084..0a5634ca005dfb 100644 --- a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi @@ -60,7 +60,7 @@ verdin_key_wakeup: key-wakeup { memory@80000000 { device_type = "memory"; - reg = <0x00000000 0x80000000 0x00000000 0x40000000>; /* 1G RAM */ + reg = <0x00000000 0x80000000 0x00000000 0x80000000>; /* 2G RAM */ }; opp-table { @@ -1061,6 +1061,7 @@ dsi_bridge: dsi@e { vddc-supply = <®_1v2_dsi>; vddmipi-supply = <®_1v2_dsi>; vddio-supply = <®_1v8_dsi>; + status = "disabled"; dsi_bridge_ports: ports { #address-cells = <1>; @@ -1308,8 +1309,6 @@ &mcasp0 { 0 0 0 0 >; tdm-slots = <2>; - rx-num-evt = <32>; - tx-num-evt = <32>; #sound-dai-cells = <0>; status = "disabled"; }; @@ -1326,8 +1325,6 @@ &mcasp1 { 0 0 0 0 >; tdm-slots = <2>; - rx-num-evt = <32>; - tx-num-evt = <32>; #sound-dai-cells = <0>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts index 7cfdf562b53bfe..3560349d630513 100644 --- a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts +++ b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts @@ -58,7 +58,7 @@ reserved-memory { ramoops: ramoops@9ca00000 { compatible = "ramoops"; - reg = <0x00 0x9c700000 0x00 0x00100000>; + reg = <0x00 0x9ca00000 0x00 0x00100000>; record-size = <0x8000>; console-size = <0x8000>; ftrace-size = <0x00>; @@ -903,6 +903,4 @@ &mcasp1 { 0 0 0 0 0 0 0 0 >; - tx-num-evt = <32>; - rx-num-evt = <32>; }; diff --git a/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi index 3198af08fb9fad..de36abb243f104 100644 --- a/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi @@ -462,7 +462,7 @@ main_gpio0: gpio@600000 { <193>, <194>, <195>; interrupt-controller; #interrupt-cells = <2>; - ti,ngpio = <87>; + ti,ngpio = <92>; ti,davinci-gpio-unbanked = <0>; power-domains = <&k3_pds 77 TI_SCI_PD_EXCLUSIVE>; clocks = <&k3_clks 77 0>; @@ -480,7 +480,7 @@ main_gpio1: gpio@601000 { <183>, <184>, <185>; interrupt-controller; #interrupt-cells = <2>; - ti,ngpio = <88>; + ti,ngpio = <52>; ti,davinci-gpio-unbanked = <0>; power-domains = <&k3_pds 78 TI_SCI_PD_EXCLUSIVE>; clocks = <&k3_clks 78 0>; diff --git a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts index cff283c75f8ecd..99f2878de4c677 100644 --- a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts @@ -250,7 +250,7 @@ &main_i2c1 { status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&main_i2c1_pins_default>; - clock-frequency = <400000>; + clock-frequency = <100000>; exp1: gpio@22 { compatible = "ti,tca6424"; diff --git a/arch/arm64/boot/dts/ti/k3-am62p.dtsi b/arch/arm64/boot/dts/ti/k3-am62p.dtsi index 294ab73ec98b7b..dc0a8e94e9ace0 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62p.dtsi @@ -71,7 +71,7 @@ cbass_main: bus@f0000 { <0x00 0x43600000 0x00 0x43600000 0x00 0x00010000>, /* SA3 sproxy data */ <0x00 0x44043000 0x00 0x44043000 0x00 0x00000fe0>, /* TI SCI DEBUG */ <0x00 0x44860000 0x00 0x44860000 0x00 0x00040000>, /* SA3 sproxy config */ - <0x00 0x48000000 0x00 0x48000000 0x00 0x06400000>, /* DMSS */ + <0x00 0x48000000 0x00 0x48000000 0x00 0x06408000>, /* DMSS */ <0x00 0x60000000 0x00 0x60000000 0x00 0x08000000>, /* FSS0 DAT1 */ <0x00 0x70000000 0x00 0x70000000 0x00 0x00010000>, /* OCSRAM */ <0x01 0x00000000 0x01 0x00000000 0x00 0x00310000>, /* A53 PERIPHBASE */ diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi index 677ff8de4b6ecf..0f8c0f6a0f573e 100644 --- a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi @@ -481,8 +481,6 @@ &mcasp1 { 0 0 0 0 0 0 0 0 >; - tx-num-evt = <32>; - rx-num-evt = <32>; }; &dss { diff --git a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi index 0df54a74182474..064eb062bb54a0 100644 --- a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi @@ -612,6 +612,10 @@ sdhci0: mmc@fa10000 { ti,otap-del-sel-mmc-hs = <0x0>; ti,otap-del-sel-ddr52 = <0x6>; ti,otap-del-sel-hs200 = <0x7>; + ti,itap-del-sel-legacy = <0x10>; + ti,itap-del-sel-mmc-hs = <0xa>; + ti,itap-del-sel-ddr52 = <0x3>; + status = "disabled"; }; sdhci1: mmc@fa00000 { @@ -623,13 +627,18 @@ sdhci1: mmc@fa00000 { clock-names = "clk_ahb", "clk_xin"; ti,trm-icp = <0x2>; ti,otap-del-sel-legacy = <0x0>; - ti,otap-del-sel-sd-hs = <0xf>; + ti,otap-del-sel-sd-hs = <0x0>; ti,otap-del-sel-sdr12 = <0xf>; ti,otap-del-sel-sdr25 = <0xf>; ti,otap-del-sel-sdr50 = <0xc>; ti,otap-del-sel-sdr104 = <0x6>; ti,otap-del-sel-ddr50 = <0x9>; + ti,itap-del-sel-legacy = <0x0>; + ti,itap-del-sel-sd-hs = <0x0>; + ti,itap-del-sel-sdr12 = <0x0>; + ti,itap-del-sel-sdr25 = <0x0>; ti,clkbuf-sel = <0x7>; + status = "disabled"; }; cpsw3g: ethernet@8000000 { diff --git a/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi b/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi index 1c2c8f0daca9ff..1dcbf1fe7fae47 100644 --- a/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi @@ -200,6 +200,7 @@ flash@0 { }; &sdhci0 { + status = "okay"; bus-width = <8>; non-removable; ti,driver-strength-ohm = <50>; diff --git a/arch/arm64/boot/dts/ti/k3-am642-evm.dts b/arch/arm64/boot/dts/ti/k3-am642-evm.dts index b4a1f73d4fb17a..91d726ef7594a3 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-evm.dts +++ b/arch/arm64/boot/dts/ti/k3-am642-evm.dts @@ -35,6 +35,7 @@ aliases { }; memory@80000000 { + bootph-all; device_type = "memory"; /* 2G RAM */ reg = <0x00000000 0x80000000 0x00000000 0x80000000>; @@ -108,6 +109,7 @@ rtos_ipc_memory_region: ipc-memories@a5000000 { evm_12v0: regulator-0 { /* main DC jack */ + bootph-all; compatible = "regulator-fixed"; regulator-name = "evm_12v0"; regulator-min-microvolt = <12000000>; @@ -129,6 +131,7 @@ vsys_5v0: regulator-1 { vsys_3v3: regulator-2 { /* output of LM5140 */ + bootph-all; compatible = "regulator-fixed"; regulator-name = "vsys_3v3"; regulator-min-microvolt = <3300000>; @@ -140,6 +143,7 @@ vsys_3v3: regulator-2 { vdd_mmc1: regulator-3 { /* TPS2051BD */ + bootph-all; compatible = "regulator-fixed"; regulator-name = "vdd_mmc1"; regulator-min-microvolt = <3300000>; @@ -161,6 +165,7 @@ vddb: regulator-4 { }; vtt_supply: regulator-5 { + bootph-all; compatible = "regulator-fixed"; regulator-name = "vtt"; pinctrl-names = "default"; @@ -251,6 +256,7 @@ AM64X_IOPAD(0x0244, PIN_OUTPUT, 0) /* (E14) UART1_TXD */ }; main_uart0_pins_default: main-uart0-default-pins { + bootph-all; pinctrl-single,pins = < AM64X_IOPAD(0x0238, PIN_INPUT, 0) /* (B16) UART0_CTSn */ AM64X_IOPAD(0x023c, PIN_OUTPUT, 0) /* (A16) UART0_RTSn */ @@ -269,6 +275,7 @@ AM64X_IOPAD(0x0218, PIN_INPUT, 0) /* (A14) SPI0_D1 */ }; main_i2c0_pins_default: main-i2c0-default-pins { + bootph-all; pinctrl-single,pins = < AM64X_IOPAD(0x0260, PIN_INPUT_PULLUP, 0) /* (A18) I2C0_SCL */ AM64X_IOPAD(0x0264, PIN_INPUT_PULLUP, 0) /* (B18) I2C0_SDA */ @@ -276,6 +283,7 @@ AM64X_IOPAD(0x0264, PIN_INPUT_PULLUP, 0) /* (B18) I2C0_SDA */ }; main_i2c1_pins_default: main-i2c1-default-pins { + bootph-all; pinctrl-single,pins = < AM64X_IOPAD(0x0268, PIN_INPUT_PULLUP, 0) /* (C18) I2C1_SCL */ AM64X_IOPAD(0x026c, PIN_INPUT_PULLUP, 0) /* (B19) I2C1_SDA */ @@ -283,6 +291,7 @@ AM64X_IOPAD(0x026c, PIN_INPUT_PULLUP, 0) /* (B19) I2C1_SDA */ }; mdio1_pins_default: mdio1-default-pins { + bootph-all; pinctrl-single,pins = < AM64X_IOPAD(0x01fc, PIN_OUTPUT, 4) /* (R2) PRG0_PRU1_GPO19.MDIO0_MDC */ AM64X_IOPAD(0x01f8, PIN_INPUT, 4) /* (P5) PRG0_PRU1_GPO18.MDIO0_MDIO */ @@ -290,6 +299,7 @@ AM64X_IOPAD(0x01f8, PIN_INPUT, 4) /* (P5) PRG0_PRU1_GPO18.MDIO0_MDIO */ }; rgmii1_pins_default: rgmii1-default-pins { + bootph-all; pinctrl-single,pins = < AM64X_IOPAD(0x01cc, PIN_INPUT, 4) /* (W5) PRG0_PRU1_GPO7.RGMII1_RD0 */ AM64X_IOPAD(0x01d4, PIN_INPUT, 4) /* (Y5) PRG0_PRU1_GPO9.RGMII1_RD1 */ @@ -307,6 +317,7 @@ AM64X_IOPAD(0x00dc, PIN_OUTPUT, 4) /* (U15) PRG1_PRU0_GPO9.RGMII1_TX_CTL */ }; rgmii2_pins_default: rgmii2-default-pins { + bootph-all; pinctrl-single,pins = < AM64X_IOPAD(0x0108, PIN_INPUT, 4) /* (W11) PRG1_PRU1_GPO0.RGMII2_RD0 */ AM64X_IOPAD(0x010c, PIN_INPUT, 4) /* (V11) PRG1_PRU1_GPO1.RGMII2_RD1 */ @@ -324,6 +335,7 @@ AM64X_IOPAD(0x0144, PIN_OUTPUT, 4) /* (Y11) PRG1_PRU1_GPO15.RGMII2_TX_CTL */ }; main_usb0_pins_default: main-usb0-default-pins { + bootph-all; pinctrl-single,pins = < AM64X_IOPAD(0x02a8, PIN_OUTPUT, 0) /* (E19) USB0_DRVVBUS */ >; @@ -366,6 +378,7 @@ AM64X_IOPAD(0x0258, PIN_OUTPUT, 0) /* (C17) MCAN1_TX */ }; ddr_vtt_pins_default: ddr-vtt-default-pins { + bootph-all; pinctrl-single,pins = < AM64X_IOPAD(0x0030, PIN_OUTPUT_PULLUP, 7) /* (L18) OSPI0_CSN1.GPIO0_12 */ >; @@ -373,6 +386,7 @@ AM64X_IOPAD(0x0030, PIN_OUTPUT_PULLUP, 7) /* (L18) OSPI0_CSN1.GPIO0_12 */ }; &main_uart0 { + bootph-all; status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&main_uart0_pins_default>; @@ -387,6 +401,7 @@ &main_uart1 { }; &main_i2c0 { + bootph-all; status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&main_i2c0_pins_default>; @@ -400,12 +415,14 @@ eeprom@50 { }; &main_i2c1 { + bootph-all; status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&main_i2c1_pins_default>; clock-frequency = <400000>; exp1: gpio@22 { + bootph-all; compatible = "ti,tca6424"; reg = <0x22>; gpio-controller; @@ -438,6 +455,10 @@ display@3c { }; }; +&main_gpio0 { + bootph-all; +}; + /* mcu_gpio0 is reserved for mcu firmware usage */ &mcu_gpio0 { status = "reserved"; @@ -457,16 +478,19 @@ eeprom@0 { }; }; +/* eMMC */ &sdhci0 { - /* emmc */ + status = "okay"; bus-width = <8>; non-removable; ti,driver-strength-ohm = <50>; disable-wp; }; +/* SD/MMC */ &sdhci1 { - /* SD/MMC */ + bootph-all; + status = "okay"; vmmc-supply = <&vdd_mmc1>; pinctrl-names = "default"; bus-width = <4>; @@ -476,11 +500,13 @@ &sdhci1 { }; &usbss0 { + bootph-all; ti,vbus-divider; ti,usb2-only; }; &usb0 { + bootph-all; dr_mode = "otg"; maximum-speed = "high-speed"; pinctrl-names = "default"; @@ -488,11 +514,13 @@ &usb0 { }; &cpsw3g { + bootph-all; pinctrl-names = "default"; pinctrl-0 = <&rgmii1_pins_default>, <&rgmii2_pins_default>; }; &cpsw_port1 { + bootph-all; phy-mode = "rgmii-rxid"; phy-handle = <&cpsw3g_phy0>; }; @@ -503,11 +531,13 @@ &cpsw_port2 { }; &cpsw3g_mdio { + bootph-all; status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&mdio1_pins_default>; cpsw3g_phy0: ethernet-phy@0 { + bootph-all; reg = <0>; ti,rx-internal-delay = ; ti,fifo-depth = ; diff --git a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts index 9175e96842d821..53b64e55413f99 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts +++ b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts @@ -264,6 +264,7 @@ &main_uart1 { }; &sdhci1 { + status = "okay"; vmmc-supply = <&vcc_3v3_mmc>; pinctrl-names = "default"; pinctrl-0 = <&main_mmc1_pins_default>; diff --git a/arch/arm64/boot/dts/ti/k3-am642-sk.dts b/arch/arm64/boot/dts/ti/k3-am642-sk.dts index 722fd285a34eca..bffbd234f715ad 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-am642-sk.dts @@ -34,6 +34,7 @@ aliases { }; memory@80000000 { + bootph-pre-ram; device_type = "memory"; /* 2G RAM */ reg = <0x00000000 0x80000000 0x00000000 0x80000000>; @@ -107,6 +108,7 @@ rtos_ipc_memory_region: ipc-memories@a5000000 { vusb_main: regulator-0 { /* USB MAIN INPUT 5V DC */ + bootph-all; compatible = "regulator-fixed"; regulator-name = "vusb_main5v0"; regulator-min-microvolt = <5000000>; @@ -117,6 +119,7 @@ vusb_main: regulator-0 { vcc_3v3_sys: regulator-1 { /* output of LP8733xx */ + bootph-all; compatible = "regulator-fixed"; regulator-name = "vcc_3v3_sys"; regulator-min-microvolt = <3300000>; @@ -128,6 +131,7 @@ vcc_3v3_sys: regulator-1 { vdd_mmc1: regulator-2 { /* TPS2051BD */ + bootph-all; compatible = "regulator-fixed"; regulator-name = "vdd_mmc1"; regulator-min-microvolt = <3300000>; @@ -234,6 +238,7 @@ led-7 { &main_pmx0 { main_mmc1_pins_default: main-mmc1-default-pins { + bootph-all; pinctrl-single,pins = < AM64X_IOPAD(0x029c, PIN_INPUT_PULLUP, 0) /* (C20) MMC1_SDWP */ AM64X_IOPAD(0x0298, PIN_INPUT_PULLUP, 0) /* (D19) MMC1_SDCD */ @@ -248,6 +253,7 @@ AM64X_IOPAD(0x027c, PIN_INPUT_PULLUP, 0) /* (K18) MMC1_DAT3 */ }; main_uart0_pins_default: main-uart0-default-pins { + bootph-all; pinctrl-single,pins = < AM64X_IOPAD(0x0238, PIN_INPUT, 0) /* (B16) UART0_CTSn */ AM64X_IOPAD(0x023c, PIN_OUTPUT, 0) /* (A16) UART0_RTSn */ @@ -257,6 +263,7 @@ AM64X_IOPAD(0x0234, PIN_OUTPUT, 0) /* (C16) UART0_TXD */ }; main_uart1_pins_default: main-uart1-default-pins { + bootph-pre-ram; pinctrl-single,pins = < AM64X_IOPAD(0x0248, PIN_INPUT, 0) /* (D16) UART1_CTSn */ AM64X_IOPAD(0x024c, PIN_OUTPUT, 0) /* (E16) UART1_RTSn */ @@ -266,12 +273,14 @@ AM64X_IOPAD(0x0244, PIN_OUTPUT, 0) /* (E14) UART1_TXD */ }; main_usb0_pins_default: main-usb0-default-pins { + bootph-all; pinctrl-single,pins = < AM64X_IOPAD(0x02a8, PIN_OUTPUT, 0) /* (E19) USB0_DRVVBUS */ >; }; main_i2c0_pins_default: main-i2c0-default-pins { + bootph-all; pinctrl-single,pins = < AM64X_IOPAD(0x0260, PIN_INPUT_PULLUP, 0) /* (A18) I2C0_SCL */ AM64X_IOPAD(0x0264, PIN_INPUT_PULLUP, 0) /* (B18) I2C0_SDA */ @@ -279,6 +288,7 @@ AM64X_IOPAD(0x0264, PIN_INPUT_PULLUP, 0) /* (B18) I2C0_SDA */ }; main_i2c1_pins_default: main-i2c1-default-pins { + bootph-all; pinctrl-single,pins = < AM64X_IOPAD(0x0268, PIN_INPUT_PULLUP, 0) /* (C18) I2C1_SCL */ AM64X_IOPAD(0x026c, PIN_INPUT_PULLUP, 0) /* (B19) I2C1_SDA */ @@ -367,6 +377,7 @@ AM64X_IOPAD(0x00bc, PIN_INPUT, 7) /* (U8) GPIO0_46 */ }; &main_uart0 { + bootph-all; status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&main_uart0_pins_default>; @@ -375,12 +386,14 @@ &main_uart0 { &main_uart1 { /* main_uart1 is reserved for firmware usage */ + bootph-pre-ram; status = "reserved"; pinctrl-names = "default"; pinctrl-0 = <&main_uart1_pins_default>; }; &main_i2c0 { + bootph-all; status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&main_i2c0_pins_default>; @@ -393,12 +406,14 @@ eeprom@51 { }; &main_i2c1 { + bootph-all; status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&main_i2c1_pins_default>; clock-frequency = <400000>; exp1: gpio@70 { + bootph-all; compatible = "nxp,pca9538"; reg = <0x70>; gpio-controller; @@ -424,6 +439,7 @@ &mcu_gpio0 { }; &sdhci0 { + status = "okay"; vmmc-supply = <&wlan_en>; bus-width = <4>; non-removable; @@ -443,8 +459,10 @@ wlcore: wlcore@2 { }; }; +/* SD/MMC */ &sdhci1 { - /* SD/MMC */ + bootph-all; + status = "okay"; vmmc-supply = <&vdd_mmc1>; pinctrl-names = "default"; bus-width = <4>; @@ -454,11 +472,22 @@ &sdhci1 { }; &serdes_ln_ctrl { + bootph-all; idle-states = ; }; +&serdes_refclk { + bootph-all; +}; + +&serdes_wiz0 { + bootph-all; +}; + &serdes0 { + bootph-all; serdes0_usb_link: phy@0 { + bootph-all; reg = <0>; cdns,num-lanes = <1>; #phy-cells = <0>; @@ -468,10 +497,12 @@ serdes0_usb_link: phy@0 { }; &usbss0 { + bootph-all; ti,vbus-divider; }; &usb0 { + bootph-all; dr_mode = "host"; maximum-speed = "super-speed"; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts b/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts index 04c15b64f0b776..76ff44e71ec177 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts +++ b/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts @@ -420,7 +420,6 @@ &sdhci1 { ti,driver-strength-ohm = <50>; ti,fails-without-test-cd; /* Enabled by overlay */ - status = "disabled"; }; &tscadc0 { diff --git a/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl.dtsi b/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl.dtsi index 6229849b5d9682..65dbbff64ed961 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl.dtsi @@ -207,6 +207,7 @@ partitions { }; &sdhci0 { + status = "okay"; non-removable; disable-wp; no-sdio; diff --git a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common.dtsi b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common.dtsi index ba1c14a54acf48..b849648d51f91b 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common.dtsi @@ -14,6 +14,16 @@ / { aliases { + serial0 = &wkup_uart0; + serial1 = &mcu_uart0; + serial2 = &main_uart0; + serial3 = &main_uart1; + i2c0 = &wkup_i2c0; + i2c1 = &mcu_i2c0; + i2c2 = &main_i2c0; + i2c3 = &main_i2c1; + i2c4 = &main_i2c2; + i2c5 = &main_i2c3; spi0 = &mcu_spi0; mmc0 = &sdhci1; mmc1 = &sdhci0; diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi index bc460033a37a86..57befcce93b976 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi @@ -1013,9 +1013,10 @@ dss: dss@4a00000 { <0x0 0x04a07000 0x0 0x1000>, /* ovr1 */ <0x0 0x04a08000 0x0 0x1000>, /* ovr2 */ <0x0 0x04a0a000 0x0 0x1000>, /* vp1 */ - <0x0 0x04a0b000 0x0 0x1000>; /* vp2 */ + <0x0 0x04a0b000 0x0 0x1000>, /* vp2 */ + <0x0 0x04a01000 0x0 0x1000>; /* common1 */ reg-names = "common", "vidl1", "vid", - "ovr1", "ovr2", "vp1", "vp2"; + "ovr1", "ovr2", "vp1", "vp2", "common1"; ti,am65x-oldi-io-ctrl = <&dss_oldi_io_ctrl>; @@ -1034,7 +1035,7 @@ dss: dss@4a00000 { assigned-clocks = <&k3_clks 67 2>; assigned-clock-parents = <&k3_clks 67 5>; - interrupts = ; + interrupts = ; dma-coherent; diff --git a/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts index cee2b4b0eb87da..7a0c599f2b1c35 100644 --- a/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts +++ b/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts @@ -91,24 +91,25 @@ vdd_sd_dv: gpio-regulator-TLV71033 { }; &wkup_pmx0 { +}; + +&wkup_pmx2 { mcu_uart0_pins_default: mcu-uart0-default-pins { pinctrl-single,pins = < - J721E_WKUP_IOPAD(0xf4, PIN_INPUT, 0) /* (D20) MCU_UART0_RXD */ - J721E_WKUP_IOPAD(0xf0, PIN_OUTPUT, 0) /* (D19) MCU_UART0_TXD */ - J721E_WKUP_IOPAD(0xf8, PIN_INPUT, 0) /* (E20) MCU_UART0_CTSn */ - J721E_WKUP_IOPAD(0xfc, PIN_OUTPUT, 0) /* (E21) MCU_UART0_RTSn */ + J721E_WKUP_IOPAD(0x90, PIN_INPUT, 0) /* (E20) MCU_UART0_CTSn */ + J721E_WKUP_IOPAD(0x94, PIN_OUTPUT, 0) /* (E21) MCU_UART0_RTSn */ + J721E_WKUP_IOPAD(0x8c, PIN_INPUT, 0) /* (D20) MCU_UART0_RXD */ + J721E_WKUP_IOPAD(0x88, PIN_OUTPUT, 0) /* (D19) MCU_UART0_TXD */ >; }; wkup_uart0_pins_default: wkup-uart0-default-pins { pinctrl-single,pins = < - J721E_WKUP_IOPAD(0xb0, PIN_INPUT, 0) /* (B14) WKUP_UART0_RXD */ - J721E_WKUP_IOPAD(0xb4, PIN_OUTPUT, 0) /* (A14) WKUP_UART0_TXD */ + J721E_WKUP_IOPAD(0x48, PIN_INPUT, 0) /* (B14) WKUP_UART0_RXD */ + J721E_WKUP_IOPAD(0x4c, PIN_OUTPUT, 0) /* (A14) WKUP_UART0_TXD */ >; }; -}; -&wkup_pmx2 { mcu_cpsw_pins_default: mcu-cpsw-default-pins { pinctrl-single,pins = < J721E_WKUP_IOPAD(0x0000, PIN_OUTPUT, 0) /* MCU_RGMII1_TX_CTL */ @@ -210,7 +211,6 @@ &mcu_uart0 { status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&mcu_uart0_pins_default>; - clock-frequency = <96000000>; }; &main_uart0 { diff --git a/arch/arm64/boot/dts/ti/k3-j721e-beagleboneai64.dts b/arch/arm64/boot/dts/ti/k3-j721e-beagleboneai64.dts index 2f954729f35338..7897323376a5b9 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-beagleboneai64.dts +++ b/arch/arm64/boot/dts/ti/k3-j721e-beagleboneai64.dts @@ -123,7 +123,7 @@ main_r5fss1_core1_memory_region: r5f-memory@a5100000 { no-map; }; - c66_1_dma_memory_region: c66-dma-memory@a6000000 { + c66_0_dma_memory_region: c66-dma-memory@a6000000 { compatible = "shared-dma-pool"; reg = <0x00 0xa6000000 0x00 0x100000>; no-map; @@ -135,7 +135,7 @@ c66_0_memory_region: c66-memory@a6100000 { no-map; }; - c66_0_dma_memory_region: c66-dma-memory@a7000000 { + c66_1_dma_memory_region: c66-dma-memory@a7000000 { compatible = "shared-dma-pool"; reg = <0x00 0xa7000000 0x00 0x100000>; no-map; diff --git a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts index 42fe8eee9ec8c7..ccacb65683b5b0 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts @@ -119,7 +119,7 @@ main_r5fss1_core1_memory_region: r5f-memory@a5100000 { no-map; }; - c66_1_dma_memory_region: c66-dma-memory@a6000000 { + c66_0_dma_memory_region: c66-dma-memory@a6000000 { compatible = "shared-dma-pool"; reg = <0x00 0xa6000000 0x00 0x100000>; no-map; @@ -131,7 +131,7 @@ c66_0_memory_region: c66-memory@a6100000 { no-map; }; - c66_0_dma_memory_region: c66-dma-memory@a7000000 { + c66_1_dma_memory_region: c66-dma-memory@a7000000 { compatible = "shared-dma-pool"; reg = <0x00 0xa7000000 0x00 0x100000>; no-map; diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts index c6b85bbf9a179b..1ba1f53c72d03b 100644 --- a/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts +++ b/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts @@ -190,8 +190,6 @@ J721S2_IOPAD(0x038, PIN_OUTPUT, 0) /* (AB28) MCASP0_ACLKX.MCAN5_TX */ &wkup_pmx2 { wkup_uart0_pins_default: wkup-uart0-default-pins { pinctrl-single,pins = < - J721S2_WKUP_IOPAD(0x070, PIN_INPUT, 0) /* (E25) WKUP_GPIO0_6.WKUP_UART0_CTSn */ - J721S2_WKUP_IOPAD(0x074, PIN_OUTPUT, 0) /* (F28) WKUP_GPIO0_7.WKUP_UART0_RTSn */ J721S2_WKUP_IOPAD(0x048, PIN_INPUT, 0) /* (D28) WKUP_UART0_RXD */ J721S2_WKUP_IOPAD(0x04c, PIN_OUTPUT, 0) /* (D27) WKUP_UART0_TXD */ >; diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi index 2ddad931855416..71324fec415ae2 100644 --- a/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi @@ -652,7 +652,7 @@ wkup_vtm0: temperature-sensor@42040000 { compatible = "ti,j7200-vtm"; reg = <0x00 0x42040000 0x0 0x350>, <0x00 0x42050000 0x0 0x350>; - power-domains = <&k3_pds 154 TI_SCI_PD_SHARED>; + power-domains = <&k3_pds 180 TI_SCI_PD_SHARED>; #thermal-sensor-cells = <1>; }; }; diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts b/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts index 5991c2e1d994c8..39f99ee39dab99 100644 --- a/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts +++ b/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts @@ -296,8 +296,6 @@ &wkup_pmx2 { wkup_uart0_pins_default: wkup-uart0-default-pins { bootph-all; pinctrl-single,pins = < - J721S2_WKUP_IOPAD(0x070, PIN_INPUT, 0) /* (L37) WKUP_GPIO0_6.WKUP_UART0_CTSn */ - J721S2_WKUP_IOPAD(0x074, PIN_INPUT, 0) /* (L36) WKUP_GPIO0_7.WKUP_UART0_RTSn */ J721S2_WKUP_IOPAD(0x048, PIN_INPUT, 0) /* (K35) WKUP_UART0_RXD */ J721S2_WKUP_IOPAD(0x04c, PIN_INPUT, 0) /* (K34) WKUP_UART0_TXD */ >; diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi index 4ab4018d369538..8d26daf7fa3d12 100644 --- a/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi @@ -616,7 +616,7 @@ wkup_vtm0: temperature-sensor@42040000 { compatible = "ti,j7200-vtm"; reg = <0x00 0x42040000 0x00 0x350>, <0x00 0x42050000 0x00 0x350>; - power-domains = <&k3_pds 154 TI_SCI_PD_SHARED>; + power-domains = <&k3_pds 243 TI_SCI_PD_SHARED>; #thermal-sensor-cells = <1>; }; diff --git a/arch/arm64/boot/dts/xilinx/Makefile b/arch/arm64/boot/dts/xilinx/Makefile index 5e40c0b4fa0a90..1068b0fa8e9847 100644 --- a/arch/arm64/boot/dts/xilinx/Makefile +++ b/arch/arm64/boot/dts/xilinx/Makefile @@ -22,11 +22,10 @@ dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-sm-k26-revA.dtb dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-smk-k26-revA.dtb zynqmp-sm-k26-revA-sck-kv-g-revA-dtbs := zynqmp-sm-k26-revA.dtb zynqmp-sck-kv-g-revA.dtbo +dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-sm-k26-revA-sck-kv-g-revA.dtb zynqmp-sm-k26-revA-sck-kv-g-revB-dtbs := zynqmp-sm-k26-revA.dtb zynqmp-sck-kv-g-revB.dtbo +dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-sm-k26-revA-sck-kv-g-revB.dtb zynqmp-smk-k26-revA-sck-kv-g-revA-dtbs := zynqmp-smk-k26-revA.dtb zynqmp-sck-kv-g-revA.dtbo +dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-smk-k26-revA-sck-kv-g-revA.dtb zynqmp-smk-k26-revA-sck-kv-g-revB-dtbs := zynqmp-smk-k26-revA.dtb zynqmp-sck-kv-g-revB.dtbo - -zynqmp-sm-k26-revA-sck-kr-g-revA-dtbs := zynqmp-sm-k26-revA.dtb zynqmp-sck-kr-g-revA.dtbo -zynqmp-sm-k26-revA-sck-kr-g-revB-dtbs := zynqmp-sm-k26-revA.dtb zynqmp-sck-kr-g-revB.dtbo -zynqmp-smk-k26-revA-sck-kr-g-revA-dtbs := zynqmp-smk-k26-revA.dtb zynqmp-sck-kr-g-revA.dtbo -zynqmp-smk-k26-revA-sck-kr-g-revB-dtbs := zynqmp-smk-k26-revA.dtb zynqmp-sck-kr-g-revB.dtbo +dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-smk-k26-revA-sck-kv-g-revB.dtb diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revA.dtso b/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revA.dtso index ae1b9b2bdbee27..92f4190d564db1 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revA.dtso +++ b/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revA.dtso @@ -21,57 +21,57 @@ /dts-v1/; /plugin/; -&i2c1 { /* I2C_SCK C23/C24 - MIO from SOM */ - #address-cells = <1>; - #size-cells = <0>; - pinctrl-names = "default", "gpio"; - pinctrl-0 = <&pinctrl_i2c1_default>; - pinctrl-1 = <&pinctrl_i2c1_gpio>; - scl-gpios = <&gpio 24 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; - sda-gpios = <&gpio 25 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; - - /* u14 - 0x40 - ina260 */ - /* u27 - 0xe0 - STDP4320 DP/HDMI splitter */ -}; - -&amba { - si5332_0: si5332_0 { /* u17 */ +&{/} { + si5332_0: si5332-0 { /* u17 */ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <125000000>; }; - si5332_1: si5332_1 { /* u17 */ + si5332_1: si5332-1 { /* u17 */ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <25000000>; }; - si5332_2: si5332_2 { /* u17 */ + si5332_2: si5332-2 { /* u17 */ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <48000000>; }; - si5332_3: si5332_3 { /* u17 */ + si5332_3: si5332-3 { /* u17 */ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <24000000>; }; - si5332_4: si5332_4 { /* u17 */ + si5332_4: si5332-4 { /* u17 */ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <26000000>; }; - si5332_5: si5332_5 { /* u17 */ + si5332_5: si5332-5 { /* u17 */ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <27000000>; }; }; +&i2c1 { /* I2C_SCK C23/C24 - MIO from SOM */ + #address-cells = <1>; + #size-cells = <0>; + pinctrl-names = "default", "gpio"; + pinctrl-0 = <&pinctrl_i2c1_default>; + pinctrl-1 = <&pinctrl_i2c1_gpio>; + scl-gpios = <&gpio 24 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + sda-gpios = <&gpio 25 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + + /* u14 - 0x40 - ina260 */ + /* u27 - 0xe0 - STDP4320 DP/HDMI splitter */ +}; + /* DP/USB 3.0 and SATA */ &psgtr { status = "okay"; diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revB.dtso b/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revB.dtso index b59e48be6465a5..f88b71f5b07a63 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revB.dtso +++ b/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revB.dtso @@ -16,58 +16,58 @@ /dts-v1/; /plugin/; -&i2c1 { /* I2C_SCK C23/C24 - MIO from SOM */ - #address-cells = <1>; - #size-cells = <0>; - pinctrl-names = "default", "gpio"; - pinctrl-0 = <&pinctrl_i2c1_default>; - pinctrl-1 = <&pinctrl_i2c1_gpio>; - scl-gpios = <&gpio 24 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; - sda-gpios = <&gpio 25 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; - - /* u14 - 0x40 - ina260 */ - /* u43 - 0x2d - usb5744 */ - /* u27 - 0xe0 - STDP4320 DP/HDMI splitter */ -}; - -&amba { - si5332_0: si5332_0 { /* u17 */ +&{/} { + si5332_0: si5332-0 { /* u17 */ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <125000000>; }; - si5332_1: si5332_1 { /* u17 */ + si5332_1: si5332-1 { /* u17 */ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <25000000>; }; - si5332_2: si5332_2 { /* u17 */ + si5332_2: si5332-2 { /* u17 */ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <48000000>; }; - si5332_3: si5332_3 { /* u17 */ + si5332_3: si5332-3 { /* u17 */ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <24000000>; }; - si5332_4: si5332_4 { /* u17 */ + si5332_4: si5332-4 { /* u17 */ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <26000000>; }; - si5332_5: si5332_5 { /* u17 */ + si5332_5: si5332-5 { /* u17 */ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <27000000>; }; }; +&i2c1 { /* I2C_SCK C23/C24 - MIO from SOM */ + #address-cells = <1>; + #size-cells = <0>; + pinctrl-names = "default", "gpio"; + pinctrl-0 = <&pinctrl_i2c1_default>; + pinctrl-1 = <&pinctrl_i2c1_gpio>; + scl-gpios = <&gpio 24 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + sda-gpios = <&gpio 25 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; + + /* u14 - 0x40 - ina260 */ + /* u43 - 0x2d - usb5744 */ + /* u27 - 0xe0 - STDP4320 DP/HDMI splitter */ +}; + /* DP/USB 3.0 */ &psgtr { status = "okay"; diff --git a/arch/arm64/boot/install.sh b/arch/arm64/boot/install.sh index 7399d706967a4f..9b7a09808a3dda 100755 --- a/arch/arm64/boot/install.sh +++ b/arch/arm64/boot/install.sh @@ -17,7 +17,8 @@ # $3 - kernel map file # $4 - default install path (blank if root directory) -if [ "$(basename $2)" = "Image.gz" ]; then +if [ "$(basename $2)" = "Image.gz" ] || [ "$(basename $2)" = "vmlinuz.efi" ] +then # Compressed install echo "Installing compressed kernel" base=vmlinuz diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index a789119e6483b5..60af93c04b45a7 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -623,6 +623,7 @@ CONFIG_GPIO_RCAR=y CONFIG_GPIO_UNIPHIER=y CONFIG_GPIO_VISCONTI=y CONFIG_GPIO_WCD934X=m +CONFIG_GPIO_VF610=y CONFIG_GPIO_XGENE=y CONFIG_GPIO_XGENE_SB=y CONFIG_GPIO_MAX732X=y diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c index bac4cabef6073e..467ac2f768ac2b 100644 --- a/arch/arm64/crypto/aes-neonbs-glue.c +++ b/arch/arm64/crypto/aes-neonbs-glue.c @@ -227,8 +227,19 @@ static int ctr_encrypt(struct skcipher_request *req) src += blocks * AES_BLOCK_SIZE; } if (nbytes && walk.nbytes == walk.total) { + u8 buf[AES_BLOCK_SIZE]; + u8 *d = dst; + + if (unlikely(nbytes < AES_BLOCK_SIZE)) + src = dst = memcpy(buf + sizeof(buf) - nbytes, + src, nbytes); + neon_aes_ctr_encrypt(dst, src, ctx->enc, ctx->key.rounds, nbytes, walk.iv); + + if (unlikely(nbytes < AES_BLOCK_SIZE)) + memcpy(d, dst, nbytes); + nbytes = 0; } kernel_neon_end(); diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index 6792a1f83f2ad4..a407f9cd549edc 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -119,6 +119,18 @@ static inline u32 get_acpi_id_for_cpu(unsigned int cpu) return acpi_cpu_get_madt_gicc(cpu)->uid; } +static inline int get_cpu_for_acpi_id(u32 uid) +{ + int cpu; + + for (cpu = 0; cpu < nr_cpu_ids; cpu++) + if (acpi_cpu_get_madt_gicc(cpu) && + uid == get_acpi_id_for_cpu(cpu)) + return cpu; + + return -EINVAL; +} + static inline void arch_fix_phys_package_id(int num, u32 slot) { } void __init acpi_init_cpus(void); int apei_claim_sea(struct pt_regs *regs); diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h index 94b486192e1f15..a3652b6bb740d9 100644 --- a/arch/arm64/include/asm/alternative-macros.h +++ b/arch/arm64/include/asm/alternative-macros.h @@ -229,7 +229,7 @@ alternative_has_cap_likely(const unsigned long cpucap) compiletime_assert(cpucap < ARM64_NCAPS, "cpucap must be < ARM64_NCAPS"); - asm_volatile_goto( + asm goto( ALTERNATIVE_CB("b %l[l_no]", %[cpucap], alt_cb_patch_nops) : : [cpucap] "i" (cpucap) @@ -247,7 +247,7 @@ alternative_has_cap_unlikely(const unsigned long cpucap) compiletime_assert(cpucap < ARM64_NCAPS, "cpucap must be < ARM64_NCAPS"); - asm_volatile_goto( + asm goto( ALTERNATIVE("nop", "b %l[l_yes]", %[cpucap]) : : [cpucap] "i" (cpucap) diff --git a/arch/arm64/include/asm/arm_pmuv3.h b/arch/arm64/include/asm/arm_pmuv3.h index 18dc2fb3d7b7b2..c27404fa4418ad 100644 --- a/arch/arm64/include/asm/arm_pmuv3.h +++ b/arch/arm64/include/asm/arm_pmuv3.h @@ -46,12 +46,12 @@ static inline u32 read_pmuver(void) ID_AA64DFR0_EL1_PMUVer_SHIFT); } -static inline void write_pmcr(u32 val) +static inline void write_pmcr(u64 val) { write_sysreg(val, pmcr_el0); } -static inline u32 read_pmcr(void) +static inline u64 read_pmcr(void) { return read_sysreg(pmcr_el0); } @@ -71,21 +71,6 @@ static inline u64 read_pmccntr(void) return read_sysreg(pmccntr_el0); } -static inline void write_pmxevcntr(u32 val) -{ - write_sysreg(val, pmxevcntr_el0); -} - -static inline u32 read_pmxevcntr(void) -{ - return read_sysreg(pmxevcntr_el0); -} - -static inline void write_pmxevtyper(u32 val) -{ - write_sysreg(val, pmxevtyper_el0); -} - static inline void write_pmcntenset(u32 val) { write_sysreg(val, pmcntenset_el0); @@ -106,7 +91,7 @@ static inline void write_pmintenclr(u32 val) write_sysreg(val, pmintenclr_el1); } -static inline void write_pmccfiltr(u32 val) +static inline void write_pmccfiltr(u64 val) { write_sysreg(val, pmccfiltr_el0); } @@ -126,12 +111,12 @@ static inline void write_pmuserenr(u32 val) write_sysreg(val, pmuserenr_el0); } -static inline u32 read_pmceid0(void) +static inline u64 read_pmceid0(void) { return read_sysreg(pmceid0_el0); } -static inline u32 read_pmceid1(void) +static inline u64 read_pmceid1(void) { return read_sysreg(pmceid1_el0); } diff --git a/arch/arm64/include/asm/asm-bug.h b/arch/arm64/include/asm/asm-bug.h index c762038ba40093..6e73809f6492a2 100644 --- a/arch/arm64/include/asm/asm-bug.h +++ b/arch/arm64/include/asm/asm-bug.h @@ -28,6 +28,7 @@ 14470: .long 14471f - .; \ _BUGVERBOSE_LOCATION(__FILE__, __LINE__) \ .short flags; \ + .align 2; \ .popsection; \ 14471: #else diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index cf2987464c1860..1ca947d5c93963 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -40,6 +40,10 @@ */ #define dgh() asm volatile("hint #6" : : : "memory") +#define spec_bar() asm volatile(ALTERNATIVE("dsb nsh\nisb\n", \ + SB_BARRIER_INSN"nop\n", \ + ARM64_HAS_SB)) + #ifdef CONFIG_ARM64_PSEUDO_NMI #define pmr_sync() \ do { \ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 74d00feb62f03e..488f8e75134959 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -61,6 +61,7 @@ #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 #define ARM_CPU_IMP_AMPERE 0xC0 +#define ARM_CPU_IMP_MICROSOFT 0x6D #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -85,8 +86,18 @@ #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B - -#define APM_CPU_PART_POTENZA 0x000 +#define ARM_CPU_PART_CORTEX_X1C 0xD4C +#define ARM_CPU_PART_CORTEX_X3 0xD4E +#define ARM_CPU_PART_NEOVERSE_V2 0xD4F +#define ARM_CPU_PART_CORTEX_A720 0xD81 +#define ARM_CPU_PART_CORTEX_X4 0xD82 +#define ARM_CPU_PART_NEOVERSE_V3 0xD84 +#define ARM_CPU_PART_CORTEX_X925 0xD85 +#define ARM_CPU_PART_CORTEX_A725 0xD87 +#define ARM_CPU_PART_NEOVERSE_N3 0xD8E + +#define APM_CPU_PART_XGENE 0x000 +#define APM_CPU_VAR_POTENZA 0x00 #define CAVIUM_CPU_PART_THUNDERX 0x0A1 #define CAVIUM_CPU_PART_THUNDERX_81XX 0x0A2 @@ -133,6 +144,9 @@ #define APPLE_CPU_PART_M2_AVALANCHE_MAX 0x039 #define AMPERE_CPU_PART_AMPERE1 0xAC3 +#define AMPERE_CPU_PART_AMPERE1A 0xAC4 + +#define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */ #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) @@ -155,6 +169,15 @@ #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C) +#define MIDR_CORTEX_X3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X3) +#define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) +#define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720) +#define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) +#define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) +#define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925) +#define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725) +#define MIDR_NEOVERSE_N3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N3) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) @@ -192,6 +215,8 @@ #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) +#define MIDR_AMPERE1A MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1A) +#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index ae35939f395bb1..1cdae1b4f03bee 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -10,63 +10,63 @@ #include #include -#define ESR_ELx_EC_UNKNOWN (0x00) -#define ESR_ELx_EC_WFx (0x01) +#define ESR_ELx_EC_UNKNOWN UL(0x00) +#define ESR_ELx_EC_WFx UL(0x01) /* Unallocated EC: 0x02 */ -#define ESR_ELx_EC_CP15_32 (0x03) -#define ESR_ELx_EC_CP15_64 (0x04) -#define ESR_ELx_EC_CP14_MR (0x05) -#define ESR_ELx_EC_CP14_LS (0x06) -#define ESR_ELx_EC_FP_ASIMD (0x07) -#define ESR_ELx_EC_CP10_ID (0x08) /* EL2 only */ -#define ESR_ELx_EC_PAC (0x09) /* EL2 and above */ +#define ESR_ELx_EC_CP15_32 UL(0x03) +#define ESR_ELx_EC_CP15_64 UL(0x04) +#define ESR_ELx_EC_CP14_MR UL(0x05) +#define ESR_ELx_EC_CP14_LS UL(0x06) +#define ESR_ELx_EC_FP_ASIMD UL(0x07) +#define ESR_ELx_EC_CP10_ID UL(0x08) /* EL2 only */ +#define ESR_ELx_EC_PAC UL(0x09) /* EL2 and above */ /* Unallocated EC: 0x0A - 0x0B */ -#define ESR_ELx_EC_CP14_64 (0x0C) -#define ESR_ELx_EC_BTI (0x0D) -#define ESR_ELx_EC_ILL (0x0E) +#define ESR_ELx_EC_CP14_64 UL(0x0C) +#define ESR_ELx_EC_BTI UL(0x0D) +#define ESR_ELx_EC_ILL UL(0x0E) /* Unallocated EC: 0x0F - 0x10 */ -#define ESR_ELx_EC_SVC32 (0x11) -#define ESR_ELx_EC_HVC32 (0x12) /* EL2 only */ -#define ESR_ELx_EC_SMC32 (0x13) /* EL2 and above */ +#define ESR_ELx_EC_SVC32 UL(0x11) +#define ESR_ELx_EC_HVC32 UL(0x12) /* EL2 only */ +#define ESR_ELx_EC_SMC32 UL(0x13) /* EL2 and above */ /* Unallocated EC: 0x14 */ -#define ESR_ELx_EC_SVC64 (0x15) -#define ESR_ELx_EC_HVC64 (0x16) /* EL2 and above */ -#define ESR_ELx_EC_SMC64 (0x17) /* EL2 and above */ -#define ESR_ELx_EC_SYS64 (0x18) -#define ESR_ELx_EC_SVE (0x19) -#define ESR_ELx_EC_ERET (0x1a) /* EL2 only */ +#define ESR_ELx_EC_SVC64 UL(0x15) +#define ESR_ELx_EC_HVC64 UL(0x16) /* EL2 and above */ +#define ESR_ELx_EC_SMC64 UL(0x17) /* EL2 and above */ +#define ESR_ELx_EC_SYS64 UL(0x18) +#define ESR_ELx_EC_SVE UL(0x19) +#define ESR_ELx_EC_ERET UL(0x1a) /* EL2 only */ /* Unallocated EC: 0x1B */ -#define ESR_ELx_EC_FPAC (0x1C) /* EL1 and above */ -#define ESR_ELx_EC_SME (0x1D) +#define ESR_ELx_EC_FPAC UL(0x1C) /* EL1 and above */ +#define ESR_ELx_EC_SME UL(0x1D) /* Unallocated EC: 0x1E */ -#define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */ -#define ESR_ELx_EC_IABT_LOW (0x20) -#define ESR_ELx_EC_IABT_CUR (0x21) -#define ESR_ELx_EC_PC_ALIGN (0x22) +#define ESR_ELx_EC_IMP_DEF UL(0x1f) /* EL3 only */ +#define ESR_ELx_EC_IABT_LOW UL(0x20) +#define ESR_ELx_EC_IABT_CUR UL(0x21) +#define ESR_ELx_EC_PC_ALIGN UL(0x22) /* Unallocated EC: 0x23 */ -#define ESR_ELx_EC_DABT_LOW (0x24) -#define ESR_ELx_EC_DABT_CUR (0x25) -#define ESR_ELx_EC_SP_ALIGN (0x26) -#define ESR_ELx_EC_MOPS (0x27) -#define ESR_ELx_EC_FP_EXC32 (0x28) +#define ESR_ELx_EC_DABT_LOW UL(0x24) +#define ESR_ELx_EC_DABT_CUR UL(0x25) +#define ESR_ELx_EC_SP_ALIGN UL(0x26) +#define ESR_ELx_EC_MOPS UL(0x27) +#define ESR_ELx_EC_FP_EXC32 UL(0x28) /* Unallocated EC: 0x29 - 0x2B */ -#define ESR_ELx_EC_FP_EXC64 (0x2C) +#define ESR_ELx_EC_FP_EXC64 UL(0x2C) /* Unallocated EC: 0x2D - 0x2E */ -#define ESR_ELx_EC_SERROR (0x2F) -#define ESR_ELx_EC_BREAKPT_LOW (0x30) -#define ESR_ELx_EC_BREAKPT_CUR (0x31) -#define ESR_ELx_EC_SOFTSTP_LOW (0x32) -#define ESR_ELx_EC_SOFTSTP_CUR (0x33) -#define ESR_ELx_EC_WATCHPT_LOW (0x34) -#define ESR_ELx_EC_WATCHPT_CUR (0x35) +#define ESR_ELx_EC_SERROR UL(0x2F) +#define ESR_ELx_EC_BREAKPT_LOW UL(0x30) +#define ESR_ELx_EC_BREAKPT_CUR UL(0x31) +#define ESR_ELx_EC_SOFTSTP_LOW UL(0x32) +#define ESR_ELx_EC_SOFTSTP_CUR UL(0x33) +#define ESR_ELx_EC_WATCHPT_LOW UL(0x34) +#define ESR_ELx_EC_WATCHPT_CUR UL(0x35) /* Unallocated EC: 0x36 - 0x37 */ -#define ESR_ELx_EC_BKPT32 (0x38) +#define ESR_ELx_EC_BKPT32 UL(0x38) /* Unallocated EC: 0x39 */ -#define ESR_ELx_EC_VECTOR32 (0x3A) /* EL2 only */ +#define ESR_ELx_EC_VECTOR32 UL(0x3A) /* EL2 only */ /* Unallocated EC: 0x3B */ -#define ESR_ELx_EC_BRK64 (0x3C) +#define ESR_ELx_EC_BRK64 UL(0x3C) /* Unallocated EC: 0x3D - 0x3F */ -#define ESR_ELx_EC_MAX (0x3F) +#define ESR_ELx_EC_MAX UL(0x3F) #define ESR_ELx_EC_SHIFT (26) #define ESR_ELx_EC_WIDTH (6) diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 8df46f186c64b8..7415c63b41874d 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -36,13 +36,13 @@ * When we defined the maximum SVE vector length we defined the ABI so * that the maximum vector length included all the reserved for future * expansion bits in ZCR rather than those just currently defined by - * the architecture. While SME follows a similar pattern the fact that - * it includes a square matrix means that any allocations that attempt - * to cover the maximum potential vector length (such as happen with - * the regset used for ptrace) end up being extremely large. Define - * the much lower actual limit for use in such situations. + * the architecture. Using this length to allocate worst size buffers + * results in excessively large allocations, and this effect is even + * more pronounced for SME due to ZA. Define more suitable VLs for + * these situations. */ -#define SME_VQ_MAX 16 +#define ARCH_SVE_VQ_MAX ((ZCR_ELx_LEN_MASK >> ZCR_ELx_LEN_SHIFT) + 1) +#define SME_VQ_MAX ((SMCR_ELx_LEN_MASK >> SMCR_ELx_LEN_SHIFT) + 1) struct task_struct; @@ -360,6 +360,7 @@ extern void sme_alloc(struct task_struct *task, bool flush); extern unsigned int sme_get_vl(void); extern int sme_set_current_vl(unsigned long arg); extern int sme_get_current_vl(void); +extern void sme_suspend_exit(void); /* * Return how many bytes of memory are required to store the full SME @@ -395,6 +396,7 @@ static inline int sme_max_vl(void) { return 0; } static inline int sme_max_virtualisable_vl(void) { return 0; } static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } static inline int sme_get_current_vl(void) { return -EINVAL; } +static inline void sme_suspend_exit(void) { } static inline size_t sme_state_size(struct task_struct const *task) { diff --git a/arch/arm64/include/asm/irq_work.h b/arch/arm64/include/asm/irq_work.h index 81bbfa3a035bd2..a1020285ea7504 100644 --- a/arch/arm64/include/asm/irq_work.h +++ b/arch/arm64/include/asm/irq_work.h @@ -2,8 +2,6 @@ #ifndef __ASM_IRQ_WORK_H #define __ASM_IRQ_WORK_H -extern void arch_irq_work_raise(void); - static inline bool arch_irq_work_has_interrupt(void) { return true; diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index 48ddc0f45d2283..4b99159150829b 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -13,12 +13,13 @@ #include #include +#define HAVE_JUMP_LABEL_BATCH #define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( "1: nop \n\t" " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" @@ -35,7 +36,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( "1: b %l[l_yes] \n\t" " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 7f7d9b1df4e5ad..07bdf5dd8ebef5 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -826,6 +826,12 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); + /* + * If we end up clearing hw dirtiness for a sw-dirty PTE, set hardware + * dirtiness again. + */ + if (pte_sw_dirty(pte)) + pte = pte_mkdirty(pte); return pte; } diff --git a/arch/arm64/include/asm/setup.h b/arch/arm64/include/asm/setup.h index f4af547ef54caa..2e4d7da74fb87a 100644 --- a/arch/arm64/include/asm/setup.h +++ b/arch/arm64/include/asm/setup.h @@ -21,9 +21,22 @@ static inline bool arch_parse_debug_rodata(char *arg) extern bool rodata_enabled; extern bool rodata_full; - if (arg && !strcmp(arg, "full")) { + if (!arg) + return false; + + if (!strcmp(arg, "full")) { + rodata_enabled = rodata_full = true; + return true; + } + + if (!strcmp(arg, "off")) { + rodata_enabled = rodata_full = false; + return true; + } + + if (!strcmp(arg, "on")) { rodata_enabled = true; - rodata_full = true; + rodata_full = false; return true; } diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h index 17f687510c4851..7a0e7b59be9b9f 100644 --- a/arch/arm64/include/asm/syscall_wrapper.h +++ b/arch/arm64/include/asm/syscall_wrapper.h @@ -44,9 +44,6 @@ return sys_ni_syscall(); \ } -#define COMPAT_SYS_NI(name) \ - SYSCALL_ALIAS(__arm64_compat_sys_##name, sys_ni_posix_timers); - #endif /* CONFIG_COMPAT */ #define __SYSCALL_DEFINEx(x, name, ...) \ @@ -82,6 +79,5 @@ } asmlinkage long __arm64_sys_ni_syscall(const struct pt_regs *__unused); -#define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers); #endif /* __ASM_SYSCALL_WRAPPER_H */ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index b149cf9f91bc96..b73baaf8ae47be 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -152,12 +152,18 @@ static inline unsigned long get_trans_granule(void) #define MAX_TLBI_RANGE_PAGES __TLBI_RANGE_PAGES(31, 3) /* - * Generate 'num' values from -1 to 30 with -1 rejected by the - * __flush_tlb_range() loop below. + * Generate 'num' values from -1 to 31 with -1 rejected by the + * __flush_tlb_range() loop below. Its return value is only + * significant for a maximum of MAX_TLBI_RANGE_PAGES pages. If + * 'pages' is more than that, you must iterate over the overall + * range. */ -#define TLBI_RANGE_MASK GENMASK_ULL(4, 0) -#define __TLBI_RANGE_NUM(pages, scale) \ - ((((pages) >> (5 * (scale) + 1)) & TLBI_RANGE_MASK) - 1) +#define __TLBI_RANGE_NUM(pages, scale) \ + ({ \ + int __pages = min((pages), \ + __TLBI_RANGE_PAGES(31, (scale))); \ + (__pages >> (5 * (scale) + 1)) - 1; \ + }) /* * TLB Invalidation @@ -351,29 +357,25 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) * entries one by one at the granularity of 'stride'. If the TLB * range ops are supported, then: * - * 1. If 'pages' is odd, flush the first page through non-range - * operations; - * - * 2. For remaining pages: the minimum range granularity is decided - * by 'scale', so multiple range TLBI operations may be required. - * Start from scale = 0, flush the corresponding number of pages - * ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it - * until no pages left. + * 1. The minimum range granularity is decided by 'scale', so multiple range + * TLBI operations may be required. Start from scale = 3, flush the largest + * possible number of pages ((num+1)*2^(5*scale+1)) that fit into the + * requested range, then decrement scale and continue until one or zero pages + * are left. * - * Note that certain ranges can be represented by either num = 31 and - * scale or num = 0 and scale + 1. The loop below favours the latter - * since num is limited to 30 by the __TLBI_RANGE_NUM() macro. + * 2. If there is 1 page remaining, flush it through non-range operations. Range + * operations can only span an even number of pages. */ #define __flush_tlb_range_op(op, start, pages, stride, \ asid, tlb_level, tlbi_user) \ do { \ int num = 0; \ - int scale = 0; \ + int scale = 3; \ unsigned long addr; \ \ while (pages > 0) { \ if (!system_supports_tlb_range() || \ - pages % 2 == 1) { \ + pages == 1) { \ addr = __TLBI_VADDR(start, asid); \ __tlbi_level(op, addr, tlb_level); \ if (tlbi_user) \ @@ -393,7 +395,7 @@ do { \ start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \ pages -= __TLBI_RANGE_PAGES(num, scale); \ } \ - scale++; \ + scale--; \ } \ } while (0) diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 78b68311ec8192..545a4a7b5371ce 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -840,7 +840,7 @@ __SYSCALL(__NR_pselect6_time64, compat_sys_pselect6_time64) #define __NR_ppoll_time64 414 __SYSCALL(__NR_ppoll_time64, compat_sys_ppoll_time64) #define __NR_io_pgetevents_time64 416 -__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents) +__SYSCALL(__NR_io_pgetevents_time64, compat_sys_io_pgetevents_time64) #define __NR_recvmmsg_time64 417 __SYSCALL(__NR_recvmmsg_time64, compat_sys_recvmmsg_time64) #define __NR_mq_timedsend_time64 418 diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h index 2b09495499c618..014b02897f8e22 100644 --- a/arch/arm64/include/asm/uprobes.h +++ b/arch/arm64/include/asm/uprobes.h @@ -10,11 +10,9 @@ #include #include -#define MAX_UINSN_BYTES AARCH64_INSN_SIZE - #define UPROBE_SWBP_INSN cpu_to_le32(BRK64_OPCODE_UPROBES) #define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE -#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES +#define UPROBE_XOL_SLOT_BYTES AARCH64_INSN_SIZE typedef __le32 uprobe_opcode_t; @@ -23,8 +21,8 @@ struct arch_uprobe_task { struct arch_uprobe { union { - u8 insn[MAX_UINSN_BYTES]; - u8 ixol[MAX_UINSN_BYTES]; + __le32 insn; + __le32 ixol; }; struct arch_probe_insn api; bool simulate; diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index f23c1dc3f002fe..8f003db7a6967a 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -312,10 +312,10 @@ struct zt_context { ((sizeof(struct za_context) + (__SVE_VQ_BYTES - 1)) \ / __SVE_VQ_BYTES * __SVE_VQ_BYTES) -#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) +#define ZA_SIG_REGS_SIZE(vq) (((vq) * __SVE_VQ_BYTES) * ((vq) * __SVE_VQ_BYTES)) #define ZA_SIG_ZAV_OFFSET(vq, n) (ZA_SIG_REGS_OFFSET + \ - (SVE_SIG_ZREG_SIZE(vq) * n)) + (SVE_SIG_ZREG_SIZE(vq) * (n))) #define ZA_SIG_CONTEXT_SIZE(vq) \ (ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq)) @@ -326,7 +326,7 @@ struct zt_context { #define ZT_SIG_REGS_OFFSET sizeof(struct zt_context) -#define ZT_SIG_REGS_SIZE(n) (ZT_SIG_REG_BYTES * n) +#define ZT_SIG_REGS_SIZE(n) (ZT_SIG_REG_BYTES * (n)) #define ZT_SIG_CONTEXT_SIZE(n) \ (sizeof(struct zt_context) + ZT_SIG_REGS_SIZE(n)) diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c index e51535a5f939a9..2465f291c7e17c 100644 --- a/arch/arm64/kernel/acpi_numa.c +++ b/arch/arm64/kernel/acpi_numa.c @@ -27,24 +27,13 @@ #include -static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE }; +static int acpi_early_node_map[NR_CPUS] __initdata = { [0 ... NR_CPUS - 1] = NUMA_NO_NODE }; int __init acpi_numa_get_nid(unsigned int cpu) { return acpi_early_node_map[cpu]; } -static inline int get_cpu_for_acpi_id(u32 uid) -{ - int cpu; - - for (cpu = 0; cpu < nr_cpu_ids; cpu++) - if (uid == get_acpi_id_for_cpu(cpu)) - return cpu; - - return -EINVAL; -} - static int __init acpi_parse_gicc_pxm(union acpi_subtable_headers *header, const unsigned long end) { diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index e459cfd3371171..d6b711e56df972 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -464,6 +464,9 @@ static int run_all_insn_set_hw_mode(unsigned int cpu) for (int i = 0; i < ARRAY_SIZE(insn_emulations); i++) { struct insn_emulation *insn = insn_emulations[i]; bool enable = READ_ONCE(insn->current_mode) == INSN_HW; + if (insn->status == INSN_UNAVAILABLE) + continue; + if (insn->set_hw_mode && insn->set_hw_mode(enable)) { pr_warn("CPU[%u] cannot support the emulation of %s", cpu, insn->name); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 5706e74c55786a..463b48d0f92500 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -390,6 +390,7 @@ static const struct midr_range erratum_1463225[] = { static const struct midr_range trbe_overwrite_fill_mode_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2139208 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2119858 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), @@ -403,6 +404,7 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = { static const struct midr_range tsb_flush_fail_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2067961 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2054223 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), @@ -415,6 +417,7 @@ static const struct midr_range tsb_flush_fail_cpus[] = { static struct midr_range trbe_write_out_of_range_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2253138 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2224489 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), @@ -432,6 +435,54 @@ static struct midr_range broken_aarch32_aes[] = { }; #endif /* CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE */ +#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD +static const struct midr_range erratum_spec_unpriv_load_list[] = { +#ifdef CONFIG_ARM64_ERRATUM_3117295 + MIDR_ALL_VERSIONS(MIDR_CORTEX_A510), +#endif +#ifdef CONFIG_ARM64_ERRATUM_2966298 + /* Cortex-A520 r0p0 to r0p1 */ + MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1), +#endif + {}, +}; +#endif + +#ifdef CONFIG_ARM64_ERRATUM_3194386 +static const struct midr_range erratum_spec_ssbs_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A76), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A77), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A715), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A720), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A725), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X2), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X3), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X4), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X925), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N3), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), + {} +}; +#endif + +#ifdef CONFIG_AMPERE_ERRATUM_AC03_CPU_38 +static const struct midr_range erratum_ac03_cpu_38_list[] = { + MIDR_ALL_VERSIONS(MIDR_AMPERE1), + MIDR_ALL_VERSIONS(MIDR_AMPERE1A), + {}, +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -730,19 +781,26 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .cpu_enable = cpu_clear_bf16_from_user_emulation, }, #endif -#ifdef CONFIG_ARM64_ERRATUM_2966298 +#ifdef CONFIG_ARM64_ERRATUM_3194386 + { + .desc = "SSBS not fully self-synchronizing", + .capability = ARM64_WORKAROUND_SPECULATIVE_SSBS, + ERRATA_MIDR_RANGE_LIST(erratum_spec_ssbs_list), + }, +#endif +#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD { - .desc = "ARM erratum 2966298", - .capability = ARM64_WORKAROUND_2966298, + .desc = "ARM errata 2966298, 3117295", + .capability = ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD, /* Cortex-A520 r0p0 - r0p1 */ - ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1), + ERRATA_MIDR_RANGE_LIST(erratum_spec_unpriv_load_list), }, #endif #ifdef CONFIG_AMPERE_ERRATUM_AC03_CPU_38 { .desc = "AmpereOne erratum AC03_CPU_38", .capability = ARM64_WORKAROUND_AMPERE_AC03_CPU_38, - ERRATA_MIDR_ALL_VERSIONS(MIDR_AMPERE1), + ERRATA_MIDR_RANGE_LIST(erratum_ac03_cpu_38_list), }, #endif { diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 444a73c2e63858..7e96604559004b 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2190,6 +2190,17 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) } #endif /* CONFIG_ARM64_MTE */ +static void user_feature_fixup(void) +{ + if (cpus_have_cap(ARM64_WORKAROUND_SPECULATIVE_SSBS)) { + struct arm64_ftr_reg *regp; + + regp = get_arm64_ftr_reg(SYS_ID_AA64PFR1_EL1); + if (regp) + regp->user_mask &= ~ID_AA64PFR1_EL1_SSBS_MASK; + } +} + static void elf_hwcap_fixup(void) { #ifdef CONFIG_ARM64_ERRATUM_1742098 @@ -3345,6 +3356,7 @@ void __init setup_cpu_features(void) u32 cwg; setup_system_capabilities(); + user_feature_fixup(); setup_elf_hwcaps(arm64_elf_hwcaps); if (system_supports_32bit_el0()) { diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index a6030913cd58c4..7fcbee0f6c0e4e 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -428,16 +428,9 @@ alternative_else_nop_endif ldp x28, x29, [sp, #16 * 14] .if \el == 0 -alternative_if ARM64_WORKAROUND_2966298 - tlbi vale1, xzr - dsb nsh -alternative_else_nop_endif -alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 - ldr lr, [sp, #S_LR] - add sp, sp, #PT_REGS_SIZE // restore sp - eret -alternative_else_nop_endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 + alternative_insn "b .L_skip_tramp_exit_\@", nop, ARM64_UNMAP_KERNEL_AT_EL0 + msr far_el1, x29 ldr_this_cpu x30, this_cpu_vector, x29 @@ -446,7 +439,18 @@ alternative_else_nop_endif ldr lr, [sp, #S_LR] // restore x30 add sp, sp, #PT_REGS_SIZE // restore sp br x29 + +.L_skip_tramp_exit_\@: #endif + ldr lr, [sp, #S_LR] + add sp, sp, #PT_REGS_SIZE // restore sp + + /* This must be after the last explicit memory access */ +alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD + tlbi vale1, xzr + dsb nsh +alternative_else_nop_endif + eret .else ldr lr, [sp, #S_LR] add sp, sp, #PT_REGS_SIZE // restore sp diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 91e44ac7150f90..5cdfcc9e3e54b9 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1280,8 +1280,10 @@ void fpsimd_release_task(struct task_struct *dead_task) */ void sme_alloc(struct task_struct *task, bool flush) { - if (task->thread.sme_state && flush) { - memset(task->thread.sme_state, 0, sme_state_size(task)); + if (task->thread.sme_state) { + if (flush) + memset(task->thread.sme_state, 0, + sme_state_size(task)); return; } @@ -1404,6 +1406,22 @@ void __init sme_setup(void) get_sme_default_vl()); } +void sme_suspend_exit(void) +{ + u64 smcr = 0; + + if (!system_supports_sme()) + return; + + if (system_supports_fa64()) + smcr |= SMCR_ELx_FA64; + if (system_supports_sme2()) + smcr |= SMCR_ELx_EZT0; + + write_sysreg_s(smcr, SYS_SMCR_EL1); + write_sysreg_s(0, SYS_SMPRI_EL1); +} + #endif /* CONFIG_ARM64_SME */ static void sve_init_regs(void) @@ -1684,7 +1702,7 @@ void fpsimd_preserve_current_state(void) void fpsimd_signal_preserve_current_state(void) { fpsimd_preserve_current_state(); - if (test_thread_flag(TIF_SVE)) + if (current->thread.fp_type == FP_STATE_SVE) sve_to_fpsimd(current); } diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 7b236994f0e150..6517bf2644a08b 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -569,6 +569,11 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) adr_l x1, __hyp_text_end adr_l x2, dcache_clean_poc blr x2 + + mov_q x0, INIT_SCTLR_EL2_MMU_OFF + pre_disable_mmu_workaround + msr sctlr_el2, x0 + isb 0: mov_q x0, HCR_HOST_NVHE_FLAGS msr hcr_el2, x0 diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 6ad5c6ef532962..85087e2df56498 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -47,17 +48,17 @@ static void init_irq_scs(void) for_each_possible_cpu(cpu) per_cpu(irq_shadow_call_stack_ptr, cpu) = - scs_alloc(cpu_to_node(cpu)); + scs_alloc(early_cpu_to_node(cpu)); } #ifdef CONFIG_VMAP_STACK -static void init_irq_stacks(void) +static void __init init_irq_stacks(void) { int cpu; unsigned long *p; for_each_possible_cpu(cpu) { - p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu)); + p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, early_cpu_to_node(cpu)); per_cpu(irq_stack_ptr, cpu) = p; } } diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c index faf88ec9c48e8a..f63ea915d6ad25 100644 --- a/arch/arm64/kernel/jump_label.c +++ b/arch/arm64/kernel/jump_label.c @@ -7,11 +7,12 @@ */ #include #include +#include #include #include -void arch_jump_label_transform(struct jump_entry *entry, - enum jump_label_type type) +bool arch_jump_label_transform_queue(struct jump_entry *entry, + enum jump_label_type type) { void *addr = (void *)jump_entry_code(entry); u32 insn; @@ -25,4 +26,10 @@ void arch_jump_label_transform(struct jump_entry *entry, } aarch64_insn_patch_text_nosync(addr, insn); + return true; +} + +void arch_jump_label_transform_apply(void) +{ + kick_all_cpus_sync(); } diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index bd69a4e7cd6055..79200f21e12393 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -167,9 +167,6 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, switch (ELF64_R_TYPE(rela[i].r_info)) { case R_AARCH64_JUMP26: case R_AARCH64_CALL26: - if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) - break; - /* * We only have to consider branch targets that resolve * to symbols that are defined in a different section. @@ -269,9 +266,6 @@ static int partition_branch_plt_relas(Elf64_Sym *syms, Elf64_Rela *rela, { int i = 0, j = numrels - 1; - if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) - return 0; - while (i < j) { if (branch_rela_needs_plt(syms, &rela[i], dstidx)) i++; diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c index 968d5fffe23302..3496d6169e59b2 100644 --- a/arch/arm64/kernel/probes/decode-insn.c +++ b/arch/arm64/kernel/probes/decode-insn.c @@ -99,10 +99,6 @@ arm_probe_decode_insn(probe_opcode_t insn, struct arch_probe_insn *api) aarch64_insn_is_blr(insn) || aarch64_insn_is_ret(insn)) { api->handler = simulate_br_blr_ret; - } else if (aarch64_insn_is_ldr_lit(insn)) { - api->handler = simulate_ldr_literal; - } else if (aarch64_insn_is_ldrsw_lit(insn)) { - api->handler = simulate_ldrsw_literal; } else { /* * Instruction cannot be stepped out-of-line and we don't @@ -140,6 +136,17 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi) probe_opcode_t insn = le32_to_cpu(*addr); probe_opcode_t *scan_end = NULL; unsigned long size = 0, offset = 0; + struct arch_probe_insn *api = &asi->api; + + if (aarch64_insn_is_ldr_lit(insn)) { + api->handler = simulate_ldr_literal; + decoded = INSN_GOOD_NO_SLOT; + } else if (aarch64_insn_is_ldrsw_lit(insn)) { + api->handler = simulate_ldrsw_literal; + decoded = INSN_GOOD_NO_SLOT; + } else { + decoded = arm_probe_decode_insn(insn, &asi->api); + } /* * If there's a symbol defined in front of and near enough to @@ -157,7 +164,6 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi) else scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE; } - decoded = arm_probe_decode_insn(insn, &asi->api); if (decoded != INSN_REJECTED && scan_end) if (is_probed_address_atomic(addr - 1, scan_end)) diff --git a/arch/arm64/kernel/probes/simulate-insn.c b/arch/arm64/kernel/probes/simulate-insn.c index 22d0b32524763e..b65334ab79d2b0 100644 --- a/arch/arm64/kernel/probes/simulate-insn.c +++ b/arch/arm64/kernel/probes/simulate-insn.c @@ -171,17 +171,15 @@ simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs) void __kprobes simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs) { - u64 *load_addr; + unsigned long load_addr; int xn = opcode & 0x1f; - int disp; - disp = ldr_displacement(opcode); - load_addr = (u64 *) (addr + disp); + load_addr = addr + ldr_displacement(opcode); if (opcode & (1 << 30)) /* x0-x30 */ - set_x_reg(regs, xn, *load_addr); + set_x_reg(regs, xn, READ_ONCE(*(u64 *)load_addr)); else /* w0-w30 */ - set_w_reg(regs, xn, *load_addr); + set_w_reg(regs, xn, READ_ONCE(*(u32 *)load_addr)); instruction_pointer_set(regs, instruction_pointer(regs) + 4); } @@ -189,14 +187,12 @@ simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs) void __kprobes simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs) { - s32 *load_addr; + unsigned long load_addr; int xn = opcode & 0x1f; - int disp; - disp = ldr_displacement(opcode); - load_addr = (s32 *) (addr + disp); + load_addr = addr + ldr_displacement(opcode); - set_x_reg(regs, xn, *load_addr); + set_x_reg(regs, xn, READ_ONCE(*(s32 *)load_addr)); instruction_pointer_set(regs, instruction_pointer(regs) + 4); } diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c index d49aef2657cdf7..a2f137a595fc1c 100644 --- a/arch/arm64/kernel/probes/uprobes.c +++ b/arch/arm64/kernel/probes/uprobes.c @@ -42,7 +42,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE)) return -EINVAL; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); switch (arm_probe_decode_insn(insn, &auprobe->api)) { case INSN_REJECTED: @@ -108,7 +108,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) if (!auprobe->simulate) return false; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); addr = instruction_pointer(regs); if (auprobe->api.handler) diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 05f40c4e18fda2..57503dc4b22faf 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -558,6 +558,18 @@ static enum mitigation_state spectre_v4_enable_hw_mitigation(void) /* SCTLR_EL1.DSSBS was initialised to 0 during boot */ set_pstate_ssbs(0); + + /* + * SSBS is self-synchronizing and is intended to affect subsequent + * speculative instructions, but some CPUs can speculate with a stale + * value of SSBS. + * + * Mitigate this with an unconditional speculation barrier, as CPUs + * could mis-speculate branches and bypass a conditional barrier. + */ + if (IS_ENABLED(CONFIG_ARM64_ERRATUM_3194386)) + spec_bar(); + return SPECTRE_MITIGATED; } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 20d7ef82de90aa..d95416b93a9dd5 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -728,7 +728,6 @@ static void sve_init_header_from_task(struct user_sve_header *header, { unsigned int vq; bool active; - bool fpsimd_only; enum vec_type task_type; memset(header, 0, sizeof(*header)); @@ -744,12 +743,10 @@ static void sve_init_header_from_task(struct user_sve_header *header, case ARM64_VEC_SVE: if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) header->flags |= SVE_PT_VL_INHERIT; - fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE); break; case ARM64_VEC_SME: if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) header->flags |= SVE_PT_VL_INHERIT; - fpsimd_only = false; break; default: WARN_ON_ONCE(1); @@ -757,7 +754,7 @@ static void sve_init_header_from_task(struct user_sve_header *header, } if (active) { - if (fpsimd_only) { + if (target->thread.fp_type == FP_STATE_FPSIMD) { header->flags |= SVE_PT_REGS_FPSIMD; } else { header->flags |= SVE_PT_REGS_SVE; @@ -1107,12 +1104,13 @@ static int za_set(struct task_struct *target, } } - /* Allocate/reinit ZA storage */ - sme_alloc(target, true); - if (!target->thread.sme_state) { - ret = -ENOMEM; - goto out; - } + /* + * Only flush the storage if PSTATE.ZA was not already set, + * otherwise preserve any existing data. + */ + sme_alloc(target, !thread_za_enabled(&target->thread)); + if (!target->thread.sme_state) + return -ENOMEM; /* If there is no data then disable ZA */ if (!count) { @@ -1498,7 +1496,8 @@ static const struct user_regset aarch64_regsets[] = { #ifdef CONFIG_ARM64_SVE [REGSET_SVE] = { /* Scalable Vector Extension */ .core_note_type = NT_ARM_SVE, - .n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE), + .n = DIV_ROUND_UP(SVE_PT_SIZE(ARCH_SVE_VQ_MAX, + SVE_PT_REGS_SVE), SVE_VQ_BYTES), .size = SVE_VQ_BYTES, .align = SVE_VQ_BYTES, diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 417a8a86b2db59..c583d1f335f8c7 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -371,9 +371,6 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) smp_init_cpus(); smp_build_mpidr_hash(); - /* Init percpu seeds for random tags after cpus are set up. */ - kasan_init_sw_tags(); - #ifdef CONFIG_ARM64_SW_TTBR0_PAN /* * Make sure init_thread_info.ttbr0 always generates translation diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 0e8beb3349ea2a..425b1bc17a3f6d 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -242,7 +242,7 @@ static int preserve_sve_context(struct sve_context __user *ctx) vl = task_get_sme_vl(current); vq = sve_vq_from_vl(vl); flags |= SVE_SIG_FLAG_SM; - } else if (test_thread_flag(TIF_SVE)) { + } else if (current->thread.fp_type == FP_STATE_SVE) { vq = sve_vq_from_vl(vl); } @@ -878,7 +878,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, if (system_supports_sve() || system_supports_sme()) { unsigned int vq = 0; - if (add_all || test_thread_flag(TIF_SVE) || + if (add_all || current->thread.fp_type == FP_STATE_SVE || thread_sm_enabled(¤t->thread)) { int vl = max(sve_max_vl(), sme_max_vl()); diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 960b98b43506dd..14365ef8424402 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -459,6 +459,8 @@ void __init smp_prepare_boot_cpu(void) init_gic_priority_masking(); kasan_init_hw_tags(); + /* Init percpu seeds for random tags after cpus are set up. */ + kasan_init_sw_tags(); } /* diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 0fbdf5fe64d8da..045af2bfd656a0 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -80,6 +81,8 @@ void notrace __cpu_suspend_exit(void) */ spectre_v4_enable_mitigation(NULL); + sme_suspend_exit(); + /* Restore additional feature-specific configuration */ ptrauth_suspend_exit(); } diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 9a70d9746b661b..f090e39f69bc4a 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -56,17 +56,15 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno, syscall_set_return_value(current, regs, 0, ret); /* - * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), - * but not enough for arm64 stack utilization comfort. To keep - * reasonable stack head room, reduce the maximum offset to 9 bits. + * This value will get limited by KSTACK_OFFSET_MAX(), which is 10 + * bits. The actual entropy will be further reduced by the compiler + * when applying stack alignment constraints: the AAPCS mandates a + * 16-byte aligned SP at function boundaries, which will remove the + * 4 low bits from any entropy chosen here. * - * The actual entropy will be further reduced by the compiler when - * applying stack alignment constraints: the AAPCS mandates a - * 16-byte (i.e. 4-bit) aligned SP at function boundaries. - * - * The resulting 5 bits of entropy is seen in SP[8:4]. + * The resulting 6 bits of entropy is seen in SP[9:4]. */ - choose_random_kstack_offset(get_random_u16() & 0x1FF); + choose_random_kstack_offset(get_random_u16()); } static inline bool has_syscall_work(unsigned long flags) diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index fe7a53c6781f15..8818287f10955c 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -78,13 +78,3 @@ include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE # Actual build commands quiet_cmd_vdsold_and_vdso_check = LD $@ cmd_vdsold_and_vdso_check = $(cmd_ld); $(cmd_vdso_check) - -# Install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso.so: $(obj)/vdso.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso.so diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 2f73e5bca213f8..1f911a76c5af39 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -172,13 +172,3 @@ gen-vdsosym := $(srctree)/$(src)/../vdso/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ # The AArch64 nm should be able to read an AArch32 binary cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ - -# Install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL32 $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/vdso32.so - -vdso.so: $(obj)/vdso.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso.so diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 4866b3f7b4ea38..685cc436146a5a 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -407,7 +407,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); kvm_timer_vcpu_terminate(vcpu); kvm_pmu_vcpu_destroy(vcpu); - + kvm_vgic_vcpu_destroy(vcpu); kvm_arm_vcpu_destroy(vcpu); } diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 95f6945c443252..efe82cc86bd1f3 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -251,6 +251,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) case PSR_AA32_MODE_SVC: case PSR_AA32_MODE_ABT: case PSR_AA32_MODE_UND: + case PSR_AA32_MODE_SYS: if (!vcpu_el1_is_32bit(vcpu)) return -EINVAL; break; @@ -276,7 +277,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) { int i, nr_reg; - switch (*vcpu_cpsr(vcpu)) { + switch (*vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK) { /* * Either we are dealing with user mode, and only the * first 15 registers (+ PC) must be narrowed to 32bit. @@ -874,7 +875,7 @@ u32 __attribute_const__ kvm_target_cpu(void) break; case ARM_CPU_IMP_APM: switch (part_number) { - case APM_CPU_PART_POTENZA: + case APM_CPU_PART_XGENE: return KVM_ARM_TARGET_XGENE_POTENZA; } break; diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c index f98cbe2626a1cb..19efb41aab805d 100644 --- a/arch/arm64/kvm/hyp/aarch32.c +++ b/arch/arm64/kvm/hyp/aarch32.c @@ -50,9 +50,23 @@ bool kvm_condition_valid32(const struct kvm_vcpu *vcpu) u32 cpsr_cond; int cond; - /* Top two bits non-zero? Unconditional. */ - if (kvm_vcpu_get_esr(vcpu) >> 30) + /* + * These are the exception classes that could fire with a + * conditional instruction. + */ + switch (kvm_vcpu_trap_get_class(vcpu)) { + case ESR_ELx_EC_CP15_32: + case ESR_ELx_EC_CP15_64: + case ESR_ELx_EC_CP14_MR: + case ESR_ELx_EC_CP14_LS: + case ESR_ELx_EC_FP_ASIMD: + case ESR_ELx_EC_CP10_ID: + case ESR_ELx_EC_CP14_64: + case ESR_ELx_EC_SVC32: + break; + default: return true; + } /* Is condition field valid? */ cond = kvm_vcpu_get_condition(vcpu); diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h index fe5472a184a37d..97c527ef53c2ad 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h +++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h @@ -16,7 +16,7 @@ struct hyp_pool { * API at EL2. */ hyp_spinlock_t lock; - struct list_head free_area[MAX_ORDER + 1]; + struct list_head free_area[NR_PAGE_ORDERS]; phys_addr_t range_start; phys_addr_t range_end; unsigned short max_order; diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c index 6e4dba9eadef52..8d21ab904f1a98 100644 --- a/arch/arm64/kvm/hyp/nvhe/ffa.c +++ b/arch/arm64/kvm/hyp/nvhe/ffa.c @@ -415,9 +415,9 @@ static void do_ffa_mem_frag_tx(struct arm_smccc_res *res, return; } -static __always_inline void do_ffa_mem_xfer(const u64 func_id, - struct arm_smccc_res *res, - struct kvm_cpu_context *ctxt) +static void __do_ffa_mem_xfer(const u64 func_id, + struct arm_smccc_res *res, + struct kvm_cpu_context *ctxt) { DECLARE_REG(u32, len, ctxt, 1); DECLARE_REG(u32, fraglen, ctxt, 2); @@ -428,9 +428,6 @@ static __always_inline void do_ffa_mem_xfer(const u64 func_id, u32 offset, nr_ranges; int ret = 0; - BUILD_BUG_ON(func_id != FFA_FN64_MEM_SHARE && - func_id != FFA_FN64_MEM_LEND); - if (addr_mbz || npages_mbz || fraglen > len || fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) { ret = FFA_RET_INVALID_PARAMETERS; @@ -449,6 +446,11 @@ static __always_inline void do_ffa_mem_xfer(const u64 func_id, goto out_unlock; } + if (len > ffa_desc_buf.len) { + ret = FFA_RET_NO_MEMORY; + goto out_unlock; + } + buf = hyp_buffers.tx; memcpy(buf, host_buffers.tx, fraglen); @@ -498,6 +500,13 @@ static __always_inline void do_ffa_mem_xfer(const u64 func_id, goto out_unlock; } +#define do_ffa_mem_xfer(fid, res, ctxt) \ + do { \ + BUILD_BUG_ON((fid) != FFA_FN64_MEM_SHARE && \ + (fid) != FFA_FN64_MEM_LEND); \ + __do_ffa_mem_xfer((fid), (res), (ctxt)); \ + } while (0); + static void do_ffa_mem_reclaim(struct arm_smccc_res *res, struct kvm_cpu_context *ctxt) { diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index f155b8c9e98c7f..ca0bf0b92ca09e 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -523,7 +523,7 @@ static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, kvm_clear_pte(ctx->ptep); dsb(ishst); - __tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), ctx->level); + __tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), 0); } else { if (ctx->end - ctx->addr < granule) return -EINVAL; @@ -805,12 +805,15 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx, * Perform the appropriate TLB invalidation based on the * evicted pte value (if any). */ - if (kvm_pte_table(ctx->old, ctx->level)) - kvm_tlb_flush_vmid_range(mmu, ctx->addr, - kvm_granule_size(ctx->level)); - else if (kvm_pte_valid(ctx->old)) + if (kvm_pte_table(ctx->old, ctx->level)) { + u64 size = kvm_granule_size(ctx->level); + u64 addr = ALIGN_DOWN(ctx->addr, size); + + kvm_tlb_flush_vmid_range(mmu, addr, size); + } else if (kvm_pte_valid(ctx->old)) { kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level); + } } if (stage2_pte_is_counted(ctx->old)) @@ -858,9 +861,13 @@ static void stage2_unmap_put_pte(const struct kvm_pgtable_visit_ctx *ctx, if (kvm_pte_valid(ctx->old)) { kvm_clear_pte(ctx->ptep); - if (!stage2_unmap_defer_tlb_flush(pgt)) - kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, - ctx->addr, ctx->level); + if (kvm_pte_table(ctx->old, ctx->level)) { + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, + 0); + } else if (!stage2_unmap_defer_tlb_flush(pgt)) { + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, + ctx->level); + } } mm_ops->put_page(ctx->ptep); diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c index 6ff3ec18c92584..b2c8084cdb95de 100644 --- a/arch/arm64/kvm/pkvm.c +++ b/arch/arm64/kvm/pkvm.c @@ -101,6 +101,17 @@ void __init kvm_hyp_reserve(void) hyp_mem_base); } +static void __pkvm_destroy_hyp_vm(struct kvm *host_kvm) +{ + if (host_kvm->arch.pkvm.handle) { + WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm, + host_kvm->arch.pkvm.handle)); + } + + host_kvm->arch.pkvm.handle = 0; + free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc); +} + /* * Allocates and donates memory for hypervisor VM structs at EL2. * @@ -181,7 +192,7 @@ static int __pkvm_create_hyp_vm(struct kvm *host_kvm) return 0; destroy_vm: - pkvm_destroy_hyp_vm(host_kvm); + __pkvm_destroy_hyp_vm(host_kvm); return ret; free_vm: free_pages_exact(hyp_vm, hyp_vm_sz); @@ -194,23 +205,19 @@ int pkvm_create_hyp_vm(struct kvm *host_kvm) { int ret = 0; - mutex_lock(&host_kvm->lock); + mutex_lock(&host_kvm->arch.config_lock); if (!host_kvm->arch.pkvm.handle) ret = __pkvm_create_hyp_vm(host_kvm); - mutex_unlock(&host_kvm->lock); + mutex_unlock(&host_kvm->arch.config_lock); return ret; } void pkvm_destroy_hyp_vm(struct kvm *host_kvm) { - if (host_kvm->arch.pkvm.handle) { - WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm, - host_kvm->arch.pkvm.handle)); - } - - host_kvm->arch.pkvm.handle = 0; - free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc); + mutex_lock(&host_kvm->arch.config_lock); + __pkvm_destroy_hyp_vm(host_kvm); + mutex_unlock(&host_kvm->arch.config_lock); } int pkvm_init_host_vm(struct kvm *host_kvm) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 0afd6136e2759c..b233a64df2956a 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -32,6 +32,7 @@ #include #include "sys_regs.h" +#include "vgic/vgic.h" #include "trace.h" @@ -301,6 +302,11 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu, { bool g1; + if (!kvm_has_gicv3(vcpu->kvm)) { + kvm_inject_undefined(vcpu); + return false; + } + if (!p->is_write) return read_from_write_only(vcpu, p, r); diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index c8c3cb81278321..a2b439ad387c80 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -355,7 +355,7 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm) if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list) - vgic_v3_free_redist_region(rdreg); + vgic_v3_free_redist_region(kvm, rdreg); INIT_LIST_HEAD(&dist->rd_regions); } else { dist->vgic_cpu_base = VGIC_ADDR_UNDEF; @@ -368,7 +368,7 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm) vgic_v4_teardown(kvm); } -void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) +static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; @@ -379,29 +379,39 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) vgic_flush_pending_lpis(vcpu); INIT_LIST_HEAD(&vgic_cpu->ap_list_head); - vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { + vgic_unregister_redist_iodev(vcpu); + vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; + } } -static void __kvm_vgic_destroy(struct kvm *kvm) +void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + mutex_lock(&kvm->slots_lock); + __kvm_vgic_vcpu_destroy(vcpu); + mutex_unlock(&kvm->slots_lock); +} + +void kvm_vgic_destroy(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; - lockdep_assert_held(&kvm->arch.config_lock); + mutex_lock(&kvm->slots_lock); vgic_debug_destroy(kvm); kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vgic_vcpu_destroy(vcpu); + __kvm_vgic_vcpu_destroy(vcpu); + + mutex_lock(&kvm->arch.config_lock); kvm_vgic_dist_destroy(kvm); -} -void kvm_vgic_destroy(struct kvm *kvm) -{ - mutex_lock(&kvm->arch.config_lock); - __kvm_vgic_destroy(kvm); mutex_unlock(&kvm->arch.config_lock); + mutex_unlock(&kvm->slots_lock); } /** @@ -469,25 +479,26 @@ int kvm_vgic_map_resources(struct kvm *kvm) type = VGIC_V3; } - if (ret) { - __kvm_vgic_destroy(kvm); + if (ret) goto out; - } + dist->ready = true; dist_base = dist->vgic_dist_base; mutex_unlock(&kvm->arch.config_lock); ret = vgic_register_dist_iodev(kvm, dist_base, type); - if (ret) { + if (ret) kvm_err("Unable to register VGIC dist MMIO regions\n"); - kvm_vgic_destroy(kvm); - } - mutex_unlock(&kvm->slots_lock); - return ret; + goto out_slots; out: mutex_unlock(&kvm->arch.config_lock); +out_slots: mutex_unlock(&kvm->slots_lock); + + if (ret) + kvm_vgic_destroy(kvm); + return ret; } diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 5fe2365a629f25..4f9084ba7949c0 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -462,6 +462,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) } irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]); + if (!irq) + continue; + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = pendmask & (1U << bit_nr); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); @@ -584,7 +587,11 @@ static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db, unsigned long flags; raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); + irq = __vgic_its_check_cache(dist, db, devid, eventid); + if (irq) + vgic_get_irq_kref(irq); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); return irq; @@ -763,6 +770,7 @@ int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi) raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = true; vgic_queue_irq_unlock(kvm, irq, flags); + vgic_put_irq(kvm, irq); return 0; } @@ -1422,6 +1430,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its, for (i = 0; i < irq_count; i++) { irq = vgic_get_irq(kvm, NULL, intids[i]); + if (!irq) + continue; update_affinity(irq, vcpu2); diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index 212b73a715c1c2..2f9e8c611f6421 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -337,16 +337,12 @@ int kvm_register_vgic_device(unsigned long type) int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr) { - int cpuid; + int cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr); - cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >> - KVM_DEV_ARM_VGIC_CPUID_SHIFT; - - if (cpuid >= atomic_read(&dev->kvm->online_vcpus)) - return -EINVAL; - - reg_attr->vcpu = kvm_get_vcpu(dev->kvm, cpuid); reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; + reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid); + if (!reg_attr->vcpu) + return -EINVAL; return 0; } diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 188d2187eede93..48e8b60ff1e338 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -365,19 +365,26 @@ static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu, struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (test_bit(i, &val)) { - /* - * pending_latch is set irrespective of irq type - * (level or edge) to avoid dependency that VM should - * restore irq config before pending info. - */ - irq->pending_latch = true; - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - } else { + + /* + * pending_latch is set irrespective of irq type + * (level or edge) to avoid dependency that VM should + * restore irq config before pending info. + */ + irq->pending_latch = test_bit(i, &val); + + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + irq->pending_latch); irq->pending_latch = false; - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } + if (irq->pending_latch) + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + else + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); } @@ -820,7 +827,7 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) return ret; } -static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) +void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) { struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; @@ -935,8 +942,19 @@ static int vgic_v3_alloc_redist_region(struct kvm *kvm, uint32_t index, return ret; } -void vgic_v3_free_redist_region(struct vgic_redist_region *rdreg) +void vgic_v3_free_redist_region(struct kvm *kvm, struct vgic_redist_region *rdreg) { + struct kvm_vcpu *vcpu; + unsigned long c; + + lockdep_assert_held(&kvm->arch.config_lock); + + /* Garbage collect the region */ + kvm_for_each_vcpu(c, vcpu, kvm) { + if (vcpu->arch.vgic_cpu.rdreg == rdreg) + vcpu->arch.vgic_cpu.rdreg = NULL; + } + list_del(&rdreg->list); kfree(rdreg); } @@ -961,7 +979,7 @@ int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) mutex_lock(&kvm->arch.config_lock); rdreg = vgic_v3_rdist_region_from_index(kvm, index); - vgic_v3_free_redist_region(rdreg); + vgic_v3_free_redist_region(kvm, rdreg); mutex_unlock(&kvm->arch.config_lock); return ret; } diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 0ab09b0d44404b..07e48f8a4f23b3 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -241,6 +241,7 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq); int vgic_v3_save_pending_tables(struct kvm *kvm); int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count); int vgic_register_redist_iodev(struct kvm_vcpu *vcpu); +void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu); bool vgic_v3_check_base(struct kvm *kvm); void vgic_v3_load(struct kvm_vcpu *vcpu); @@ -309,7 +310,7 @@ vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg) struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, u32 index); -void vgic_v3_free_redist_region(struct vgic_redist_region *rdreg); +void vgic_v3_free_redist_region(struct kvm *kvm, struct vgic_redist_region *rdreg); bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size); @@ -342,4 +343,11 @@ void vgic_v4_configure_vsgis(struct kvm *kvm); void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val); int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq); +static inline bool kvm_has_gicv3(struct kvm *kvm) +{ + return (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) && + irqchip_in_kernel(kvm) && + kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3); +} + #endif diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 8e2017ba5f1b11..0a62f458c5cb02 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -29,8 +29,8 @@ bool can_set_direct_map(void) * * KFENCE pool requires page-granular mapping if initialized late. */ - return (rodata_enabled && rodata_full) || debug_pagealloc_enabled() || - arm64_kfence_can_set_direct_map(); + return rodata_full || debug_pagealloc_enabled() || + arm64_kfence_can_set_direct_map(); } static int change_page_range(pte_t *ptep, unsigned long addr, void *data) @@ -105,8 +105,7 @@ static int change_memory_common(unsigned long addr, int numpages, * If we are manipulating read-only permissions, apply the same * change to the linear mapping of the pages that back this VM area. */ - if (rodata_enabled && - rodata_full && (pgprot_val(set_mask) == PTE_RDONLY || + if (rodata_full && (pgprot_val(set_mask) == PTE_RDONLY || pgprot_val(clear_mask) == PTE_RDONLY)) { for (i = 0; i < area->nr_pages; i++) { __change_memory_common((u64)page_address(area->pages[i]), @@ -220,9 +219,6 @@ bool kernel_page_present(struct page *page) pte_t *ptep; unsigned long addr = (unsigned long)page_address(page); - if (!can_set_direct_map()) - return true; - pgdp = pgd_offset_k(addr); if (pgd_none(READ_ONCE(*pgdp))) return false; diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 150d1c6543f7f1..166619348b98e4 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -876,7 +876,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit(A64_UXTH(is64, dst, dst), ctx); break; case 32: - emit(A64_REV32(is64, dst, dst), ctx); + emit(A64_REV32(0, dst, dst), ctx); /* upper 32 bits already cleared */ break; case 64: @@ -1189,7 +1189,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, } else { emit_a64_mov_i(1, tmp, off, ctx); if (sign_extend) - emit(A64_LDRSW(dst, src_adj, off_adj), ctx); + emit(A64_LDRSW(dst, src, tmp), ctx); else emit(A64_LDR32(dst, src, tmp), ctx); } @@ -1738,15 +1738,15 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l, emit_call(enter_prog, ctx); + /* save return value to callee saved register x20 */ + emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx); + /* if (__bpf_prog_enter(prog) == 0) * goto skip_exec_of_prog; */ branch = ctx->image + ctx->idx; emit(A64_NOP, ctx); - /* save return value to callee saved register x20 */ - emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx); - emit(A64_ADD_I(1, A64_R(0), A64_SP, args_off), ctx); if (!p->jited) emit_addr_mov_i64(A64_R(1), (const u64)p->insnsi, ctx); diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index dea3dc89234b02..c251ef3caae560 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -84,7 +84,6 @@ WORKAROUND_2077057 WORKAROUND_2457168 WORKAROUND_2645198 WORKAROUND_2658417 -WORKAROUND_2966298 WORKAROUND_AMPERE_AC03_CPU_38 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE @@ -100,3 +99,5 @@ WORKAROUND_NVIDIA_CARMEL_CNP WORKAROUND_QCOM_FALKOR_E1003 WORKAROUND_REPEAT_TLBI WORKAROUND_SPECULATIVE_AT +WORKAROUND_SPECULATIVE_SSBS +WORKAROUND_SPECULATIVE_UNPRIV_LOAD diff --git a/arch/csky/abiv1/inc/abi/cacheflush.h b/arch/csky/abiv1/inc/abi/cacheflush.h index 908d8b0bc4fdc6..d011a81575d21e 100644 --- a/arch/csky/abiv1/inc/abi/cacheflush.h +++ b/arch/csky/abiv1/inc/abi/cacheflush.h @@ -43,6 +43,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma, */ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); #define flush_cache_vmap(start, end) cache_wbinv_all() +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) cache_wbinv_all() #define flush_icache_range(start, end) cache_wbinv_range(start, end) diff --git a/arch/csky/abiv2/inc/abi/cacheflush.h b/arch/csky/abiv2/inc/abi/cacheflush.h index 40be16907267d6..6513ac5d257888 100644 --- a/arch/csky/abiv2/inc/abi/cacheflush.h +++ b/arch/csky/abiv2/inc/abi/cacheflush.h @@ -41,6 +41,7 @@ void flush_icache_mm_range(struct mm_struct *mm, void flush_icache_deferred(struct mm_struct *mm); #define flush_cache_vmap(start, end) do { } while (0) +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) #define copy_to_user_page(vma, page, vaddr, dst, src, len) \ diff --git a/arch/csky/include/asm/irq_work.h b/arch/csky/include/asm/irq_work.h index 33aaf39d6f94f6..d39fcc1f5395f6 100644 --- a/arch/csky/include/asm/irq_work.h +++ b/arch/csky/include/asm/irq_work.h @@ -7,5 +7,5 @@ static inline bool arch_irq_work_has_interrupt(void) { return true; } -extern void arch_irq_work_raise(void); + #endif /* __ASM_CSKY_IRQ_WORK_H */ diff --git a/arch/csky/include/asm/jump_label.h b/arch/csky/include/asm/jump_label.h index d488ba6084bc6b..ef2e37a10a0feb 100644 --- a/arch/csky/include/asm/jump_label.h +++ b/arch/csky/include/asm/jump_label.h @@ -12,7 +12,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: nop32 \n" " .pushsection __jump_table, \"aw\" \n" " .align 2 \n" @@ -29,7 +29,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: bsr32 %l[label] \n" " .pushsection __jump_table, \"aw\" \n" " .align 2 \n" @@ -43,5 +43,10 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, return true; } +enum jump_label_type; +void arch_jump_label_transform_static(struct jump_entry *entry, + enum jump_label_type type); +#define arch_jump_label_transform_static arch_jump_label_transform_static + #endif /* __ASSEMBLY__ */ #endif /* __ASM_CSKY_JUMP_LABEL_H */ diff --git a/arch/csky/include/uapi/asm/unistd.h b/arch/csky/include/uapi/asm/unistd.h index 7ff6a2466af10d..e0594b6370a658 100644 --- a/arch/csky/include/uapi/asm/unistd.h +++ b/arch/csky/include/uapi/asm/unistd.h @@ -6,6 +6,7 @@ #define __ARCH_WANT_SYS_CLONE3 #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS +#define __ARCH_WANT_SYNC_FILE_RANGE2 #include #define __NR_set_thread_area (__NR_arch_specific_syscall + 0) diff --git a/arch/csky/kernel/probes/ftrace.c b/arch/csky/kernel/probes/ftrace.c index 834cffcfbce320..7ba4b98076de1e 100644 --- a/arch/csky/kernel/probes/ftrace.c +++ b/arch/csky/kernel/probes/ftrace.c @@ -12,6 +12,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe_ctlblk *kcb; struct pt_regs *regs; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/hexagon/include/asm/syscalls.h b/arch/hexagon/include/asm/syscalls.h new file mode 100644 index 00000000000000..40f2d08bec92cc --- /dev/null +++ b/arch/hexagon/include/asm/syscalls.h @@ -0,0 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include + +asmlinkage long sys_hexagon_fadvise64_64(int fd, int advice, + u32 a2, u32 a3, u32 a4, u32 a5); diff --git a/arch/hexagon/include/uapi/asm/unistd.h b/arch/hexagon/include/uapi/asm/unistd.h index 432c4db1b62392..21ae22306b5dce 100644 --- a/arch/hexagon/include/uapi/asm/unistd.h +++ b/arch/hexagon/include/uapi/asm/unistd.h @@ -36,5 +36,6 @@ #define __ARCH_WANT_SYS_VFORK #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_TIME32_SYSCALLS +#define __ARCH_WANT_SYNC_FILE_RANGE2 #include diff --git a/arch/hexagon/kernel/syscalltab.c b/arch/hexagon/kernel/syscalltab.c index 0fadd582cfc77f..5d98bdc494ec29 100644 --- a/arch/hexagon/kernel/syscalltab.c +++ b/arch/hexagon/kernel/syscalltab.c @@ -14,6 +14,13 @@ #undef __SYSCALL #define __SYSCALL(nr, call) [nr] = (call), +SYSCALL_DEFINE6(hexagon_fadvise64_64, int, fd, int, advice, + SC_ARG64(offset), SC_ARG64(len)) +{ + return ksys_fadvise64_64(fd, SC_VAL64(loff_t, offset), SC_VAL64(loff_t, len), advice); +} +#define sys_fadvise64_64 sys_hexagon_fadvise64_64 + void *sys_call_table[__NR_syscalls] = { #include }; diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S index 1140051a0c455d..1150b77fa281ce 100644 --- a/arch/hexagon/kernel/vmlinux.lds.S +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -63,6 +63,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG ELF_DETAILS + .hexagon.attributes 0 : { *(.hexagon.attributes) } DISCARDS } diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 5a55ac82c13a47..d2c66efdde560e 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -86,9 +86,13 @@ EXPORT_SYMBOL(local_per_cpu_offset); #endif unsigned long ia64_cycles_per_usec; struct ia64_boot_param *ia64_boot_param; +#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_EFI) struct screen_info screen_info; +#endif +#ifdef CONFIG_VGA_CONSOLE unsigned long vga_console_iobase; unsigned long vga_console_membase; +#endif static struct resource data_resource = { .name = "Kernel data", @@ -497,6 +501,7 @@ early_console_setup (char *cmdline) static void __init screen_info_setup(void) { +#ifdef CONFIG_VGA_CONSOLE unsigned int orig_x, orig_y, num_cols, num_rows, font_height; memset(&screen_info, 0, sizeof(screen_info)); @@ -525,6 +530,7 @@ screen_info_setup(void) screen_info.orig_video_mode = 3; /* XXX fake */ screen_info.orig_video_isVGA = 1; /* XXX fake */ screen_info.orig_video_ega_bx = 3; /* XXX fake */ +#endif } static inline void diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index e14396a2ddcbfc..9fd8644a9a4c6a 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -11,6 +11,7 @@ config LOONGARCH select ARCH_DISABLE_KASAN_INLINE select ARCH_ENABLE_MEMORY_HOTPLUG select ARCH_ENABLE_MEMORY_HOTREMOVE + select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_FORTIFY_SOURCE @@ -97,6 +98,7 @@ config LOONGARCH select HAVE_ARCH_KFENCE select HAVE_ARCH_KGDB if PERF_EVENTS select HAVE_ARCH_MMAP_RND_BITS if MMU + select HAVE_ARCH_SECCOMP select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE @@ -603,23 +605,6 @@ config RANDOMIZE_BASE_MAX_OFFSET This is limited by the size of the lower address memory, 256MB. -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - depends on PROC_FS - default y - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via /proc//seccomp, it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. Only embedded should say N here. - endmenu config ARCH_SELECT_MEMORY_MODEL @@ -638,10 +623,6 @@ config ARCH_SPARSEMEM_ENABLE or have huge holes in the physical address space for other reasons. See for more. -config ARCH_ENABLE_THP_MIGRATION - def_bool y - depends on TRANSPARENT_HUGEPAGE - config ARCH_MEMORY_PROBE def_bool y depends on MEMORY_HOTPLUG diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index fb0fada43197e4..81e8089c9c4f18 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -80,7 +80,7 @@ endif ifeq ($(CONFIG_RELOCATABLE),y) KBUILD_CFLAGS_KERNEL += -fPIE -LDFLAGS_vmlinux += -static -pie --no-dynamic-linker -z notext +LDFLAGS_vmlinux += -static -pie --no-dynamic-linker -z notext $(call ld-option, --apply-dynamic-relocs) endif cflags-y += $(call cc-option, -mno-check-zero-division) @@ -136,12 +136,12 @@ vdso_prepare: prepare0 $(Q)$(MAKE) $(build)=arch/loongarch/vdso include/generated/vdso-offsets.h endif -PHONY += vdso_install -vdso_install: - $(Q)$(MAKE) $(build)=arch/loongarch/vdso $@ +vdso-install-y += arch/loongarch/vdso/vdso.so.dbg all: $(notdir $(KBUILD_IMAGE)) +vmlinuz.efi: vmlinux.efi + vmlinux.elf vmlinux.efi vmlinuz.efi: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(bootvars-y) $(boot)/$@ diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig index a3b52aaa83b336..e5f70642ed2062 100644 --- a/arch/loongarch/configs/loongson3_defconfig +++ b/arch/loongarch/configs/loongson3_defconfig @@ -83,7 +83,6 @@ CONFIG_ZPOOL=y CONFIG_ZSWAP=y CONFIG_ZSWAP_COMPRESSOR_DEFAULT_ZSTD=y CONFIG_ZBUD=y -CONFIG_Z3FOLD=y CONFIG_ZSMALLOC=m # CONFIG_COMPAT_BRK is not set CONFIG_MEMORY_HOTPLUG=y diff --git a/arch/loongarch/crypto/crc32-loongarch.c b/arch/loongarch/crypto/crc32-loongarch.c index 1f2a2c3839bcbf..1e8ff57a46ca6d 100644 --- a/arch/loongarch/crypto/crc32-loongarch.c +++ b/arch/loongarch/crypto/crc32-loongarch.c @@ -44,7 +44,6 @@ static u32 crc32_loongarch_hw(u32 crc_, const u8 *p, unsigned int len) CRC32(crc, value, w); p += sizeof(u32); - len -= sizeof(u32); } if (len & sizeof(u16)) { @@ -80,7 +79,6 @@ static u32 crc32c_loongarch_hw(u32 crc_, const u8 *p, unsigned int len) CRC32C(crc, value, w); p += sizeof(u32); - len -= sizeof(u32); } if (len & sizeof(u16)) { diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild index 93783fa24f6e9b..dede0b422cfb91 100644 --- a/arch/loongarch/include/asm/Kbuild +++ b/arch/loongarch/include/asm/Kbuild @@ -4,6 +4,7 @@ generic-y += mcs_spinlock.h generic-y += parport.h generic-y += early_ioremap.h generic-y += qrwlock.h +generic-y += qspinlock.h generic-y += rwsem.h generic-y += segment.h generic-y += user.h diff --git a/arch/loongarch/include/asm/acpi.h b/arch/loongarch/include/asm/acpi.h index 8de6c4b83a61a8..49e29b29996f0f 100644 --- a/arch/loongarch/include/asm/acpi.h +++ b/arch/loongarch/include/asm/acpi.h @@ -32,8 +32,10 @@ static inline bool acpi_has_cpu_in_madt(void) return true; } +#define MAX_CORE_PIC 256 + extern struct list_head acpi_wakeup_device_list; -extern struct acpi_madt_core_pic acpi_core_pic[NR_CPUS]; +extern struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC]; extern int __init parse_acpi_topology(void); diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h index c9544f358c3399..655db7d7a42796 100644 --- a/arch/loongarch/include/asm/asmmacro.h +++ b/arch/loongarch/include/asm/asmmacro.h @@ -609,8 +609,7 @@ lu32i.d \reg, 0 lu52i.d \reg, \reg, 0 .pushsection ".la_abs", "aw", %progbits - 768: - .dword 768b-766b + .dword 766b .dword \sym .popsection #endif diff --git a/arch/loongarch/include/asm/dma-direct.h b/arch/loongarch/include/asm/dma-direct.h deleted file mode 100644 index 75ccd808a2af39..00000000000000 --- a/arch/loongarch/include/asm/dma-direct.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2020-2022 Loongson Technology Corporation Limited - */ -#ifndef _LOONGARCH_DMA_DIRECT_H -#define _LOONGARCH_DMA_DIRECT_H - -dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr); -phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr); - -#endif /* _LOONGARCH_DMA_DIRECT_H */ diff --git a/arch/loongarch/include/asm/efi.h b/arch/loongarch/include/asm/efi.h index 091897d40b0375..eddc8e79b3fae7 100644 --- a/arch/loongarch/include/asm/efi.h +++ b/arch/loongarch/include/asm/efi.h @@ -32,6 +32,4 @@ static inline unsigned long efi_get_kimg_min_align(void) #define EFI_KIMG_PREFERRED_ADDRESS PHYSADDR(VMLINUX_LOAD_ADDRESS) -unsigned long kernel_entry_address(void); - #endif /* _ASM_LOONGARCH_EFI_H */ diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h index b9a4ab54285c11..f16bd42456e4cc 100644 --- a/arch/loongarch/include/asm/elf.h +++ b/arch/loongarch/include/asm/elf.h @@ -241,8 +241,6 @@ void loongarch_dump_regs64(u64 *uregs, const struct pt_regs *regs); do { \ current->thread.vdso = &vdso_info; \ \ - loongarch_set_personality_fcsr(state); \ - \ if (personality(current->personality) != PER_LINUX) \ set_personality(PER_LINUX); \ } while (0) @@ -259,7 +257,6 @@ do { \ clear_thread_flag(TIF_32BIT_ADDR); \ \ current->thread.vdso = &vdso_info; \ - loongarch_set_personality_fcsr(state); \ \ p = personality(current->personality); \ if (p != PER_LINUX32 && p != PER_LINUX) \ @@ -293,7 +290,7 @@ extern const char *__elf_platform; #define ELF_PLAT_INIT(_r, load_addr) do { \ _r->regs[1] = _r->regs[2] = _r->regs[3] = _r->regs[4] = 0; \ _r->regs[5] = _r->regs[6] = _r->regs[7] = _r->regs[8] = 0; \ - _r->regs[9] = _r->regs[10] = _r->regs[11] = _r->regs[12] = 0; \ + _r->regs[9] = _r->regs[10] /* syscall n */ = _r->regs[12] = 0; \ _r->regs[13] = _r->regs[14] = _r->regs[15] = _r->regs[16] = 0; \ _r->regs[17] = _r->regs[18] = _r->regs[19] = _r->regs[20] = 0; \ _r->regs[21] = _r->regs[22] = _r->regs[23] = _r->regs[24] = 0; \ @@ -340,6 +337,4 @@ extern int arch_elf_pt_proc(void *ehdr, void *phdr, struct file *elf, extern int arch_check_elf(void *ehdr, bool has_interpreter, void *interp_ehdr, struct arch_elf_state *state); -extern void loongarch_set_personality_fcsr(struct arch_elf_state *state); - #endif /* _ASM_ELF_H */ diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h index 21447fb1efc778..d78330916bd18a 100644 --- a/arch/loongarch/include/asm/hw_breakpoint.h +++ b/arch/loongarch/include/asm/hw_breakpoint.h @@ -75,6 +75,8 @@ do { \ #define CSR_MWPC_NUM 0x3f #define CTRL_PLV_ENABLE 0x1e +#define CTRL_PLV0_ENABLE 0x02 +#define CTRL_PLV3_ENABLE 0x10 #define MWPnCFG3_LoadEn 8 #define MWPnCFG3_StoreEn 9 @@ -101,7 +103,7 @@ struct perf_event; struct perf_event_attr; extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, - int *gen_len, int *gen_type, int *offset); + int *gen_len, int *gen_type); extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); extern int hw_breakpoint_arch_parse(struct perf_event *bp, const struct perf_event_attr *attr, diff --git a/arch/loongarch/include/asm/hw_irq.h b/arch/loongarch/include/asm/hw_irq.h index af4f4e8fbd858f..8156ffb6741591 100644 --- a/arch/loongarch/include/asm/hw_irq.h +++ b/arch/loongarch/include/asm/hw_irq.h @@ -9,6 +9,8 @@ extern atomic_t irq_err_count; +#define ARCH_IRQ_INIT_FLAGS IRQ_NOPROBE + /* * interrupt-retrigger: NOP for now. This may not be appropriate for all * machines, we'll see ... diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index c486c2341b6623..4a8adcca329b81 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -71,6 +71,8 @@ extern void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t #define memcpy_fromio(a, c, l) __memcpy_fromio((a), (c), (l)) #define memcpy_toio(c, a, l) __memcpy_toio((c), (a), (l)) +#define __io_aw() mmiowb() + #include #define ARCH_HAS_VALID_PHYS_ADDR_RANGE diff --git a/arch/loongarch/include/asm/jump_label.h b/arch/loongarch/include/asm/jump_label.h index 3cea299a5ef583..29acfe3de3faae 100644 --- a/arch/loongarch/include/asm/jump_label.h +++ b/arch/loongarch/include/asm/jump_label.h @@ -22,7 +22,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( "1: nop \n\t" JUMP_TABLE_ENTRY : : "i"(&((char *)key)[branch]) : : l_yes); @@ -35,7 +35,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, co static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( "1: b %l[l_yes] \n\t" JUMP_TABLE_ENTRY : : "i"(&((char *)key)[branch]) : : l_yes); diff --git a/arch/loongarch/include/asm/numa.h b/arch/loongarch/include/asm/numa.h index 27f319b4986257..b5f9de9f102e44 100644 --- a/arch/loongarch/include/asm/numa.h +++ b/arch/loongarch/include/asm/numa.h @@ -56,6 +56,7 @@ extern int early_cpu_to_node(int cpu); static inline void early_numa_add_cpu(int cpuid, s16 node) { } static inline void numa_add_cpu(unsigned int cpu) { } static inline void numa_remove_cpu(unsigned int cpu) { } +static inline void set_cpuid_to_node(int cpuid, s16 node) { } static inline int early_cpu_to_node(int cpu) { diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h index b9f567e6601668..7e804140500f15 100644 --- a/arch/loongarch/include/asm/percpu.h +++ b/arch/loongarch/include/asm/percpu.h @@ -29,10 +29,15 @@ static inline void set_my_cpu_offset(unsigned long off) __my_cpu_offset = off; csr_write64(off, PERCPU_BASE_KS); } -#define __my_cpu_offset __my_cpu_offset + +#define __my_cpu_offset \ +({ \ + __asm__ __volatile__("":"+r"(__my_cpu_offset)); \ + __my_cpu_offset; \ +}) #define PERCPU_OP(op, asm_op, c_op) \ -static inline unsigned long __percpu_##op(void *ptr, \ +static __always_inline unsigned long __percpu_##op(void *ptr, \ unsigned long val, int size) \ { \ unsigned long ret; \ @@ -63,7 +68,7 @@ PERCPU_OP(and, and, &) PERCPU_OP(or, or, |) #undef PERCPU_OP -static inline unsigned long __percpu_read(void *ptr, int size) +static __always_inline unsigned long __percpu_read(void *ptr, int size) { unsigned long ret; @@ -100,7 +105,7 @@ static inline unsigned long __percpu_read(void *ptr, int size) return ret; } -static inline void __percpu_write(void *ptr, unsigned long val, int size) +static __always_inline void __percpu_write(void *ptr, unsigned long val, int size) { switch (size) { case 1: @@ -132,8 +137,8 @@ static inline void __percpu_write(void *ptr, unsigned long val, int size) } } -static inline unsigned long __percpu_xchg(void *ptr, unsigned long val, - int size) +static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, + int size) { switch (size) { case 1: diff --git a/arch/loongarch/include/asm/perf_event.h b/arch/loongarch/include/asm/perf_event.h index 2a35a0bc2aaabf..f948a0676daf80 100644 --- a/arch/loongarch/include/asm/perf_event.h +++ b/arch/loongarch/include/asm/perf_event.h @@ -7,6 +7,13 @@ #ifndef __LOONGARCH_PERF_EVENT_H__ #define __LOONGARCH_PERF_EVENT_H__ +#include + #define perf_arch_bpf_user_pt_regs(regs) (struct user_pt_regs *)regs +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->csr_era = (__ip); \ + (regs)->regs[3] = (unsigned long) __builtin_frame_address(0); \ +} + #endif /* __LOONGARCH_PERF_EVENT_H__ */ diff --git a/arch/loongarch/include/asm/qspinlock.h b/arch/loongarch/include/asm/qspinlock.h deleted file mode 100644 index 34f43f8ad5912b..00000000000000 --- a/arch/loongarch/include/asm/qspinlock.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_QSPINLOCK_H -#define _ASM_QSPINLOCK_H - -#include - -#define queued_spin_unlock queued_spin_unlock - -static inline void queued_spin_unlock(struct qspinlock *lock) -{ - compiletime_assert_atomic_type(lock->locked); - c_sync(); - WRITE_ONCE(lock->locked, 0); -} - -#include - -#endif /* _ASM_QSPINLOCK_H */ diff --git a/arch/loongarch/include/asm/setup.h b/arch/loongarch/include/asm/setup.h index a0bc159ce8bdc0..ee52fb1e996316 100644 --- a/arch/loongarch/include/asm/setup.h +++ b/arch/loongarch/include/asm/setup.h @@ -25,7 +25,7 @@ extern void set_merr_handler(unsigned long offset, void *addr, unsigned long len #ifdef CONFIG_RELOCATABLE struct rela_la_abs { - long offset; + long pc; long symvalue; }; diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h index 4fb1e6408b982a..efc8c42290d019 100644 --- a/arch/loongarch/include/asm/stackframe.h +++ b/arch/loongarch/include/asm/stackframe.h @@ -41,7 +41,7 @@ .macro JUMP_VIRT_ADDR temp1 temp2 li.d \temp1, CACHE_BASE pcaddi \temp2, 0 - or \temp1, \temp1, \temp2 + bstrins.d \temp1, \temp2, (DMW_PABITS - 1), 0 jirl zero, \temp1, 0xc .endm diff --git a/arch/loongarch/include/uapi/asm/unistd.h b/arch/loongarch/include/uapi/asm/unistd.h index fcb668984f0336..b344b1f917153b 100644 --- a/arch/loongarch/include/uapi/asm/unistd.h +++ b/arch/loongarch/include/uapi/asm/unistd.h @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SYS_CLONE #define __ARCH_WANT_SYS_CLONE3 diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index 8e00a754e54894..55d6a48c76a821 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -29,11 +29,9 @@ int disabled_cpus; u64 acpi_saved_sp; -#define MAX_CORE_PIC 256 - #define PREFIX "ACPI: " -struct acpi_madt_core_pic acpi_core_pic[NR_CPUS]; +struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC]; void __init __iomem * __acpi_map_table(unsigned long phys, unsigned long size) { diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c index 9fc10cea21e10e..de4f3def4af0b9 100644 --- a/arch/loongarch/kernel/efi.c +++ b/arch/loongarch/kernel/efi.c @@ -66,6 +66,12 @@ void __init efi_runtime_init(void) set_bit(EFI_RUNTIME_SERVICES, &efi.flags); } +bool efi_poweroff_required(void) +{ + return efi_enabled(EFI_RUNTIME_SERVICES) && + (acpi_gbl_reduced_hardware || acpi_no_s5); +} + unsigned long __initdata screen_info_table = EFI_INVALID_TABLE_ADDR; static void __init init_screen_info(void) diff --git a/arch/loongarch/kernel/elf.c b/arch/loongarch/kernel/elf.c index 183e94fc9c69ce..0fa81ced28dcdd 100644 --- a/arch/loongarch/kernel/elf.c +++ b/arch/loongarch/kernel/elf.c @@ -23,8 +23,3 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, void *_interp_ehdr, { return 0; } - -void loongarch_set_personality_fcsr(struct arch_elf_state *state) -{ - current->thread.fpu.fcsr = boot_cpu_data.fpu_csr0; -} diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c index 73858c9029cc9e..bff058317062e3 100644 --- a/arch/loongarch/kernel/ftrace_dyn.c +++ b/arch/loongarch/kernel/ftrace_dyn.c @@ -287,6 +287,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe *p; struct kprobe_ctlblk *kcb; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index 53b883db078620..e336fbc4eb9675 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -22,7 +22,7 @@ _head: .word MZ_MAGIC /* "MZ", MS-DOS header */ .org 0x8 - .dword kernel_entry /* Kernel entry point */ + .dword _kernel_entry /* Kernel entry point (physical address) */ .dword _kernel_asize /* Kernel image effective size */ .quad PHYS_LINK_KADDR /* Kernel image load offset from start of RAM */ .org 0x38 /* 0x20 ~ 0x37 reserved */ @@ -34,7 +34,6 @@ pe_header: SYM_DATA(kernel_asize, .long _kernel_asize); SYM_DATA(kernel_fsize, .long _kernel_fsize); -SYM_DATA(kernel_offset, .long _kernel_offset); #endif diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c index fc55c4de2a11ff..a6e4b605bfa8d6 100644 --- a/arch/loongarch/kernel/hw_breakpoint.c +++ b/arch/loongarch/kernel/hw_breakpoint.c @@ -174,11 +174,21 @@ void flush_ptrace_hw_breakpoint(struct task_struct *tsk) static int hw_breakpoint_control(struct perf_event *bp, enum hw_breakpoint_ops ops) { - u32 ctrl; + u32 ctrl, privilege; int i, max_slots, enable; + struct pt_regs *regs; struct perf_event **slots; struct arch_hw_breakpoint *info = counter_arch_bp(bp); + if (arch_check_bp_in_kernelspace(info)) + privilege = CTRL_PLV0_ENABLE; + else + privilege = CTRL_PLV3_ENABLE; + + /* Whether bp belongs to a task. */ + if (bp->hw.target) + regs = task_pt_regs(bp->hw.target); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { /* Breakpoint */ slots = this_cpu_ptr(bp_on_reg); @@ -197,31 +207,38 @@ static int hw_breakpoint_control(struct perf_event *bp, switch (ops) { case HW_BREAKPOINT_INSTALL: /* Set the FWPnCFG/MWPnCFG 1~4 register. */ - write_wb_reg(CSR_CFG_ADDR, i, 0, info->address); - write_wb_reg(CSR_CFG_ADDR, i, 1, info->address); - write_wb_reg(CSR_CFG_MASK, i, 0, info->mask); - write_wb_reg(CSR_CFG_MASK, i, 1, info->mask); - write_wb_reg(CSR_CFG_ASID, i, 0, 0); - write_wb_reg(CSR_CFG_ASID, i, 1, 0); if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { - write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE); + write_wb_reg(CSR_CFG_ADDR, i, 0, info->address); + write_wb_reg(CSR_CFG_MASK, i, 0, info->mask); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + write_wb_reg(CSR_CFG_CTRL, i, 0, privilege); } else { + write_wb_reg(CSR_CFG_ADDR, i, 1, info->address); + write_wb_reg(CSR_CFG_MASK, i, 1, info->mask); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); ctrl = encode_ctrl_reg(info->ctrl); - write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | CTRL_PLV_ENABLE); + write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | privilege); } enable = csr_read64(LOONGARCH_CSR_CRMD); csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD); + if (bp->hw.target && test_tsk_thread_flag(bp->hw.target, TIF_LOAD_WATCH)) + regs->csr_prmd |= CSR_PRMD_PWE; break; case HW_BREAKPOINT_UNINSTALL: /* Reset the FWPnCFG/MWPnCFG 1~4 register. */ - write_wb_reg(CSR_CFG_ADDR, i, 0, 0); - write_wb_reg(CSR_CFG_ADDR, i, 1, 0); - write_wb_reg(CSR_CFG_MASK, i, 0, 0); - write_wb_reg(CSR_CFG_MASK, i, 1, 0); - write_wb_reg(CSR_CFG_CTRL, i, 0, 0); - write_wb_reg(CSR_CFG_CTRL, i, 1, 0); - write_wb_reg(CSR_CFG_ASID, i, 0, 0); - write_wb_reg(CSR_CFG_ASID, i, 1, 0); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { + write_wb_reg(CSR_CFG_ADDR, i, 0, 0); + write_wb_reg(CSR_CFG_MASK, i, 0, 0); + write_wb_reg(CSR_CFG_CTRL, i, 0, 0); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + } else { + write_wb_reg(CSR_CFG_ADDR, i, 1, 0); + write_wb_reg(CSR_CFG_MASK, i, 1, 0); + write_wb_reg(CSR_CFG_CTRL, i, 1, 0); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); + } + if (bp->hw.target) + regs->csr_prmd &= ~CSR_PRMD_PWE; break; } @@ -283,7 +300,7 @@ int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) * to generic breakpoint descriptions. */ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, - int *gen_len, int *gen_type, int *offset) + int *gen_len, int *gen_type) { /* Type */ switch (ctrl.type) { @@ -303,11 +320,6 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, return -EINVAL; } - if (!ctrl.len) - return -EINVAL; - - *offset = __ffs(ctrl.len); - /* Len */ switch (ctrl.len) { case LOONGARCH_BREAKPOINT_LEN_1: @@ -386,21 +398,17 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, struct arch_hw_breakpoint *hw) { int ret; - u64 alignment_mask, offset; + u64 alignment_mask; /* Build the arch_hw_breakpoint. */ ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; - if (hw->ctrl.type != LOONGARCH_BREAKPOINT_EXECUTE) - alignment_mask = 0x7; - else + if (hw->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { alignment_mask = 0x3; - offset = hw->address & alignment_mask; - - hw->address &= ~alignment_mask; - hw->ctrl.len <<= offset; + hw->address &= ~alignment_mask; + } return 0; } @@ -471,12 +479,15 @@ void breakpoint_handler(struct pt_regs *regs) slots = this_cpu_ptr(bp_on_reg); for (i = 0; i < boot_cpu_data.watch_ireg_count; ++i) { - bp = slots[i]; - if (bp == NULL) - continue; - perf_bp_event(bp, regs); + if ((csr_read32(LOONGARCH_CSR_FWPS) & (0x1 << i))) { + bp = slots[i]; + if (bp == NULL) + continue; + perf_bp_event(bp, regs); + csr_write32(0x1 << i, LOONGARCH_CSR_FWPS); + update_bp_registers(regs, 0, 0); + } } - update_bp_registers(regs, 0, 0); } NOKPROBE_SYMBOL(breakpoint_handler); @@ -488,12 +499,15 @@ void watchpoint_handler(struct pt_regs *regs) slots = this_cpu_ptr(wp_on_reg); for (i = 0; i < boot_cpu_data.watch_dreg_count; ++i) { - wp = slots[i]; - if (wp == NULL) - continue; - perf_bp_event(wp, regs); + if ((csr_read32(LOONGARCH_CSR_MWPS) & (0x1 << i))) { + wp = slots[i]; + if (wp == NULL) + continue; + perf_bp_event(wp, regs); + csr_write32(0x1 << i, LOONGARCH_CSR_MWPS); + update_bp_registers(regs, 0, 1); + } } - update_bp_registers(regs, 0, 1); } NOKPROBE_SYMBOL(watchpoint_handler); diff --git a/arch/loongarch/kernel/image-vars.h b/arch/loongarch/kernel/image-vars.h index e561989d02de93..b12f8810f19916 100644 --- a/arch/loongarch/kernel/image-vars.h +++ b/arch/loongarch/kernel/image-vars.h @@ -11,7 +11,6 @@ __efistub_strcmp = strcmp; __efistub_kernel_entry = kernel_entry; __efistub_kernel_asize = kernel_asize; __efistub_kernel_fsize = kernel_fsize; -__efistub_kernel_offset = kernel_offset; __efistub_screen_info = screen_info; #endif diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index 883e5066ae445f..df42c063f6c430 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -122,9 +122,6 @@ void __init init_IRQ(void) panic("IPI IRQ request failed\n"); #endif - for (i = 0; i < NR_IRQS; i++) - irq_set_noprobe(i); - for_each_possible_cpu(i) { page = alloc_pages_node(cpu_to_node(i), GFP_KERNEL, order); diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c index 0491bf453cd496..cac7cba81b65f7 100644 --- a/arch/loongarch/kernel/perf_event.c +++ b/arch/loongarch/kernel/perf_event.c @@ -884,4 +884,4 @@ static int __init init_hw_perf_events(void) return 0; } -early_initcall(init_hw_perf_events); +pure_initcall(init_hw_perf_events); diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index 767d94cce0de07..f2ff8b5d591e4f 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -85,6 +85,7 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) regs->csr_euen = euen; lose_fpu(0); lose_lbt(0); + current->thread.fpu.fcsr = boot_cpu_data.fpu_csr0; clear_thread_flag(TIF_LSX_CTX_LIVE); clear_thread_flag(TIF_LASX_CTX_LIVE); diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index c114c5ef13325a..19dc6eff45ccc8 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -494,28 +494,14 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, struct arch_hw_breakpoint_ctrl ctrl, struct perf_event_attr *attr) { - int err, len, type, offset; + int err, len, type; - err = arch_bp_generic_fields(ctrl, &len, &type, &offset); + err = arch_bp_generic_fields(ctrl, &len, &type); if (err) return err; - switch (note_type) { - case NT_LOONGARCH_HW_BREAK: - if ((type & HW_BREAKPOINT_X) != type) - return -EINVAL; - break; - case NT_LOONGARCH_HW_WATCH: - if ((type & HW_BREAKPOINT_RW) != type) - return -EINVAL; - break; - default: - return -EINVAL; - } - attr->bp_len = len; attr->bp_type = type; - attr->bp_addr += offset; return 0; } @@ -603,16 +589,36 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type, struct perf_event *bp; struct perf_event_attr attr; struct arch_hw_breakpoint_ctrl ctrl; + struct thread_info *ti = task_thread_info(tsk); bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) return PTR_ERR(bp); attr = bp->attr; - decode_ctrl_reg(uctrl, &ctrl); - err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); - if (err) - return err; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + ctrl.type = LOONGARCH_BREAKPOINT_EXECUTE; + ctrl.len = LOONGARCH_BREAKPOINT_LEN_4; + break; + case NT_LOONGARCH_HW_WATCH: + decode_ctrl_reg(uctrl, &ctrl); + break; + default: + return -EINVAL; + } + + if (uctrl & CTRL_PLV_ENABLE) { + err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); + if (err) + return err; + attr.disabled = 0; + set_ti_thread_flag(ti, TIF_LOAD_WATCH); + } else { + attr.disabled = 1; + clear_ti_thread_flag(ti, TIF_LOAD_WATCH); + } return modify_user_hw_breakpoint(bp, &attr); } @@ -643,6 +649,10 @@ static int ptrace_hbp_set_addr(unsigned int note_type, struct perf_event *bp; struct perf_event_attr attr; + /* Kernel-space address cannot be monitored by user-space */ + if ((unsigned long)addr >= XKPRANGE) + return -EINVAL; + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) return PTR_ERR(bp); diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c index 6c3eff9af9fb1e..0eddd4a66b8745 100644 --- a/arch/loongarch/kernel/relocate.c +++ b/arch/loongarch/kernel/relocate.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -52,7 +53,7 @@ static inline void __init relocate_absolute(long random_offset) for (p = begin; (void *)p < end; p++) { long v = p->symvalue; uint32_t lu12iw, ori, lu32id, lu52id; - union loongarch_instruction *insn = (void *)p - p->offset; + union loongarch_instruction *insn = (void *)p->pc; lu12iw = (v >> 12) & 0xfffff; ori = v & 0xfff; @@ -102,6 +103,14 @@ static inline __init unsigned long get_random_boot(void) return hash; } +static int __init nokaslr(char *p) +{ + pr_info("KASLR is disabled.\n"); + + return 0; /* Print a notice and silence the boot warning */ +} +early_param("nokaslr", nokaslr); + static inline __init bool kaslr_disabled(void) { char *str; @@ -162,7 +171,7 @@ unsigned long __init relocate_kernel(void) unsigned long kernel_length; unsigned long random_offset = 0; void *location_new = _text; /* Default to original kernel start */ - char *cmdline = early_ioremap(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */ + char *cmdline = early_memremap_ro(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */ strscpy(boot_command_line, cmdline, COMMAND_LINE_SIZE); @@ -174,6 +183,7 @@ unsigned long __init relocate_kernel(void) random_offset = (unsigned long)location_new - (unsigned long)(_text); #endif reloc_offset = (unsigned long)_text - VMLINUX_LOAD_ADDRESS; + early_memunmap(cmdline, COMMAND_LINE_SIZE); if (random_offset) { kernel_length = (long)(_end) - (long)(_text); diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index aed65915e932e2..6748d7f3f22198 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -57,7 +57,9 @@ #define SMBIOS_CORE_PACKAGE_OFFSET 0x23 #define LOONGSON_EFI_ENABLE (1 << 3) +#ifdef CONFIG_EFI struct screen_info screen_info __section(".data"); +#endif unsigned long fw_arg0, fw_arg1, fw_arg2; DEFINE_PER_CPU(unsigned long, kernelsp); @@ -367,6 +369,8 @@ void __init platform_init(void) acpi_gbl_use_default_register_widths = false; acpi_boot_table_init(); #endif + + early_init_fdt_scan_reserved_mem(); unflatten_and_copy_device_tree(); #ifdef CONFIG_NUMA @@ -400,8 +404,6 @@ static void __init arch_mem_init(char **cmdline_p) check_kernel_sections_mem(); - early_init_fdt_scan_reserved_mem(); - /* * In order to reduce the possibility of kernel panic when failed to * get IO TLB memory under CONFIG_SWIOTLB, it is better to allocate diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index ef35c871244f08..d74dfe1206ed04 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -88,6 +88,73 @@ void show_ipi_list(struct seq_file *p, int prec) } } +static inline void set_cpu_core_map(int cpu) +{ + int i; + + cpumask_set_cpu(cpu, &cpu_core_setup_map); + + for_each_cpu(i, &cpu_core_setup_map) { + if (cpu_data[cpu].package == cpu_data[i].package) { + cpumask_set_cpu(i, &cpu_core_map[cpu]); + cpumask_set_cpu(cpu, &cpu_core_map[i]); + } + } +} + +static inline void set_cpu_sibling_map(int cpu) +{ + int i; + + cpumask_set_cpu(cpu, &cpu_sibling_setup_map); + + for_each_cpu(i, &cpu_sibling_setup_map) { + if (cpus_are_siblings(cpu, i)) { + cpumask_set_cpu(i, &cpu_sibling_map[cpu]); + cpumask_set_cpu(cpu, &cpu_sibling_map[i]); + } + } +} + +static inline void clear_cpu_sibling_map(int cpu) +{ + int i; + + for_each_cpu(i, &cpu_sibling_setup_map) { + if (cpus_are_siblings(cpu, i)) { + cpumask_clear_cpu(i, &cpu_sibling_map[cpu]); + cpumask_clear_cpu(cpu, &cpu_sibling_map[i]); + } + } + + cpumask_clear_cpu(cpu, &cpu_sibling_setup_map); +} + +/* + * Calculate a new cpu_foreign_map mask whenever a + * new cpu appears or disappears. + */ +void calculate_cpu_foreign_map(void) +{ + int i, k, core_present; + cpumask_t temp_foreign_map; + + /* Re-calculate the mask */ + cpumask_clear(&temp_foreign_map); + for_each_online_cpu(i) { + core_present = 0; + for_each_cpu(k, &temp_foreign_map) + if (cpus_are_siblings(i, k)) + core_present = 1; + if (!core_present) + cpumask_set_cpu(i, &temp_foreign_map); + } + + for_each_online_cpu(i) + cpumask_andnot(&cpu_foreign_map[i], + &temp_foreign_map, &cpu_sibling_map[i]); +} + /* Send mailbox buffer via Mail_Send */ static void csr_mail_send(uint64_t data, int cpu, int mailbox) { @@ -195,7 +262,6 @@ static void __init fdt_smp_setup(void) if (cpuid == loongson_sysconf.boot_cpu_id) { cpu = 0; - numa_add_cpu(cpu); } else { cpu = cpumask_next_zero(-1, cpu_present_mask); } @@ -205,6 +271,9 @@ static void __init fdt_smp_setup(void) set_cpu_present(cpu, true); __cpu_number_map[cpuid] = cpu; __cpu_logical_map[cpu] = cpuid; + + early_numa_add_cpu(cpu, 0); + set_cpuid_to_node(cpuid, 0); } loongson_sysconf.nr_cpus = num_processors; @@ -300,6 +369,7 @@ int loongson_cpu_disable(void) numa_remove_cpu(cpu); #endif set_cpu_online(cpu, false); + clear_cpu_sibling_map(cpu); calculate_cpu_foreign_map(); local_irq_save(flags); irq_migrate_all_off_this_cpu(); @@ -334,6 +404,7 @@ void __noreturn arch_cpu_idle_dead(void) addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0); } while (addr == 0); + local_irq_disable(); init_fn = (void *)TO_CACHE(addr); iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR); @@ -376,59 +447,6 @@ static int __init ipi_pm_init(void) core_initcall(ipi_pm_init); #endif -static inline void set_cpu_sibling_map(int cpu) -{ - int i; - - cpumask_set_cpu(cpu, &cpu_sibling_setup_map); - - for_each_cpu(i, &cpu_sibling_setup_map) { - if (cpus_are_siblings(cpu, i)) { - cpumask_set_cpu(i, &cpu_sibling_map[cpu]); - cpumask_set_cpu(cpu, &cpu_sibling_map[i]); - } - } -} - -static inline void set_cpu_core_map(int cpu) -{ - int i; - - cpumask_set_cpu(cpu, &cpu_core_setup_map); - - for_each_cpu(i, &cpu_core_setup_map) { - if (cpu_data[cpu].package == cpu_data[i].package) { - cpumask_set_cpu(i, &cpu_core_map[cpu]); - cpumask_set_cpu(cpu, &cpu_core_map[i]); - } - } -} - -/* - * Calculate a new cpu_foreign_map mask whenever a - * new cpu appears or disappears. - */ -void calculate_cpu_foreign_map(void) -{ - int i, k, core_present; - cpumask_t temp_foreign_map; - - /* Re-calculate the mask */ - cpumask_clear(&temp_foreign_map); - for_each_online_cpu(i) { - core_present = 0; - for_each_cpu(k, &temp_foreign_map) - if (cpus_are_siblings(i, k)) - core_present = 1; - if (!core_present) - cpumask_set_cpu(i, &temp_foreign_map); - } - - for_each_online_cpu(i) - cpumask_andnot(&cpu_foreign_map[i], - &temp_foreign_map, &cpu_sibling_map[i]); -} - /* Preload SMP state for boot cpu */ void smp_prepare_boot_cpu(void) { @@ -437,6 +455,7 @@ void smp_prepare_boot_cpu(void) set_cpu_possible(0, true); set_cpu_online(0, true); set_my_cpu_offset(per_cpu_offset(0)); + numa_add_cpu(0); rr_node = first_node(node_online_map); for_each_possible_cpu(cpu) { @@ -504,7 +523,7 @@ asmlinkage void start_secondary(void) unsigned int cpu; sync_counter(); - cpu = smp_processor_id(); + cpu = raw_smp_processor_id(); set_my_cpu_offset(per_cpu_offset(cpu)); cpu_probe(); diff --git a/arch/loongarch/kernel/stacktrace.c b/arch/loongarch/kernel/stacktrace.c index 92270f14db9482..f623feb2129f12 100644 --- a/arch/loongarch/kernel/stacktrace.c +++ b/arch/loongarch/kernel/stacktrace.c @@ -32,7 +32,7 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, } for (unwind_start(&state, task, regs); - !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) { + !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); if (!addr || !consume_entry(cookie, addr)) break; diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index 3064af94db9c2e..e7015f7b70e37c 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -58,14 +58,16 @@ static int constant_set_state_oneshot(struct clock_event_device *evt) return 0; } -static int constant_set_state_oneshot_stopped(struct clock_event_device *evt) +static int constant_set_state_periodic(struct clock_event_device *evt) { + unsigned long period; unsigned long timer_config; raw_spin_lock(&state_lock); - timer_config = csr_read64(LOONGARCH_CSR_TCFG); - timer_config &= ~CSR_TCFG_EN; + period = const_clock_freq / HZ; + timer_config = period & CSR_TCFG_VAL; + timer_config |= (CSR_TCFG_PERIOD | CSR_TCFG_EN); csr_write64(timer_config, LOONGARCH_CSR_TCFG); raw_spin_unlock(&state_lock); @@ -73,16 +75,14 @@ static int constant_set_state_oneshot_stopped(struct clock_event_device *evt) return 0; } -static int constant_set_state_periodic(struct clock_event_device *evt) +static int constant_set_state_shutdown(struct clock_event_device *evt) { - unsigned long period; unsigned long timer_config; raw_spin_lock(&state_lock); - period = const_clock_freq / HZ; - timer_config = period & CSR_TCFG_VAL; - timer_config |= (CSR_TCFG_PERIOD | CSR_TCFG_EN); + timer_config = csr_read64(LOONGARCH_CSR_TCFG); + timer_config &= ~CSR_TCFG_EN; csr_write64(timer_config, LOONGARCH_CSR_TCFG); raw_spin_unlock(&state_lock); @@ -90,11 +90,6 @@ static int constant_set_state_periodic(struct clock_event_device *evt) return 0; } -static int constant_set_state_shutdown(struct clock_event_device *evt) -{ - return 0; -} - static int constant_timer_next_event(unsigned long delta, struct clock_event_device *evt) { unsigned long timer_config; @@ -161,7 +156,7 @@ int constant_clockevent_init(void) cd->rating = 320; cd->cpumask = cpumask_of(cpu); cd->set_state_oneshot = constant_set_state_oneshot; - cd->set_state_oneshot_stopped = constant_set_state_oneshot_stopped; + cd->set_state_oneshot_stopped = constant_set_state_shutdown; cd->set_state_periodic = constant_set_state_periodic; cd->set_state_shutdown = constant_set_state_shutdown; cd->set_next_event = constant_timer_next_event; diff --git a/arch/loongarch/kernel/unwind.c b/arch/loongarch/kernel/unwind.c index ba324ba76fa156..a463d6961344c0 100644 --- a/arch/loongarch/kernel/unwind.c +++ b/arch/loongarch/kernel/unwind.c @@ -28,6 +28,5 @@ bool default_next_frame(struct unwind_state *state) } while (!get_stack_info(state->sp, state->task, info)); - state->error = true; return false; } diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c index 55afc27320e12a..929ae240280a5f 100644 --- a/arch/loongarch/kernel/unwind_prologue.c +++ b/arch/loongarch/kernel/unwind_prologue.c @@ -227,7 +227,7 @@ static bool next_frame(struct unwind_state *state) } while (!get_stack_info(state->sp, state->task, info)); out: - state->error = true; + state->stack_info.type = STACK_TYPE_UNKNOWN; return false; } diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index bb2ec86f37a8eb..d5afd0c80a4999 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -5,6 +5,7 @@ #define PAGE_SIZE _PAGE_SIZE #define RO_EXCEPTION_TABLE_ALIGN 4 +#define PHYSADDR_MASK 0xffffffffffff /* 48-bit */ /* * Put .bss..swapper_pg_dir as the first thing in .bss. This will @@ -139,11 +140,11 @@ SECTIONS #ifdef CONFIG_EFI_STUB /* header symbols */ - _kernel_asize = _end - _text; - _kernel_fsize = _edata - _text; - _kernel_vsize = _end - __initdata_begin; - _kernel_rsize = _edata - __initdata_begin; - _kernel_offset = kernel_offset - _text; + _kernel_entry = ABSOLUTE(kernel_entry & PHYSADDR_MASK); + _kernel_asize = ABSOLUTE(_end - _text); + _kernel_fsize = ABSOLUTE(_edata - _text); + _kernel_vsize = ABSOLUTE(_end - __initdata_begin); + _kernel_rsize = ABSOLUTE(_edata - __initdata_begin); #endif .gptab.sdata : { diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c index 1fc2f6813ea027..97b40defde0608 100644 --- a/arch/loongarch/mm/fault.c +++ b/arch/loongarch/mm/fault.c @@ -202,10 +202,10 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, if (!(vma->vm_flags & VM_WRITE)) goto bad_area; } else { - if (!(vma->vm_flags & VM_READ) && address != exception_era(regs)) - goto bad_area; if (!(vma->vm_flags & VM_EXEC) && address == exception_era(regs)) goto bad_area; + if (!(vma->vm_flags & (VM_READ | VM_WRITE)) && address != exception_era(regs)) + goto bad_area; } /* diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c index cc3e81fe0186f4..c608adc9984581 100644 --- a/arch/loongarch/mm/kasan_init.c +++ b/arch/loongarch/mm/kasan_init.c @@ -44,6 +44,9 @@ void *kasan_mem_to_shadow(const void *addr) unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff; unsigned long offset = 0; + if (maddr >= FIXADDR_START) + return (void *)(kasan_early_shadow_page); + maddr &= XRANGE_SHADOW_MASK; switch (xrange) { case XKPRANGE_CC_SEG: diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c index 71d0539e2d0b02..2aae72e638713a 100644 --- a/arch/loongarch/mm/pgtable.c +++ b/arch/loongarch/mm/pgtable.c @@ -13,13 +13,13 @@ struct page *dmw_virt_to_page(unsigned long kaddr) { return pfn_to_page(virt_to_pfn(kaddr)); } -EXPORT_SYMBOL_GPL(dmw_virt_to_page); +EXPORT_SYMBOL(dmw_virt_to_page); struct page *tlb_virt_to_page(unsigned long kaddr) { return pfn_to_page(pte_pfn(*virt_to_kpte(kaddr))); } -EXPORT_SYMBOL_GPL(tlb_virt_to_page); +EXPORT_SYMBOL(tlb_virt_to_page); pgd_t *pgd_alloc(struct mm_struct *mm) { diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c index 2c0a411f23aa77..56bf1dd5358aa1 100644 --- a/arch/loongarch/mm/tlb.c +++ b/arch/loongarch/mm/tlb.c @@ -284,12 +284,16 @@ static void setup_tlb_handler(int cpu) set_handler(EXCCODE_TLBNR * VECSIZE, handle_tlb_protect, VECSIZE); set_handler(EXCCODE_TLBNX * VECSIZE, handle_tlb_protect, VECSIZE); set_handler(EXCCODE_TLBPE * VECSIZE, handle_tlb_protect, VECSIZE); - } + } else { + int vec_sz __maybe_unused; + void *addr __maybe_unused; + struct page *page __maybe_unused; + + /* Avoid lockdep warning */ + rcu_cpu_starting(cpu); + #ifdef CONFIG_NUMA - else { - void *addr; - struct page *page; - const int vec_sz = sizeof(exception_handlers); + vec_sz = sizeof(exception_handlers); if (pcpu_handlers[cpu]) return; @@ -305,8 +309,8 @@ static void setup_tlb_handler(int cpu) csr_write64(pcpu_handlers[cpu], LOONGARCH_CSR_EENTRY); csr_write64(pcpu_handlers[cpu], LOONGARCH_CSR_MERRENTRY); csr_write64(pcpu_handlers[cpu] + 80*VECSIZE, LOONGARCH_CSR_TLBRENTRY); - } #endif + } } void tlb_init(int cpu) diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index db9342b2d0e660..9eb7753d117dfb 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -461,7 +461,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext const u8 dst = regmap[insn->dst_reg]; const s16 off = insn->off; const s32 imm = insn->imm; - const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm; const bool is32 = BPF_CLASS(insn->code) == BPF_ALU || BPF_CLASS(insn->code) == BPF_JMP32; switch (code) { @@ -855,8 +854,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext /* function return */ case BPF_JMP | BPF_EXIT: - emit_sext_32(ctx, regmap[BPF_REG_0], true); - if (i == ctx->prog->len - 1) break; @@ -867,8 +864,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext /* dst = imm64 */ case BPF_LD | BPF_IMM | BPF_DW: + { + const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm; + move_imm(ctx, dst, imm64, is32); return 1; + } /* dst = *(size *)(src + off) */ case BPF_LDX | BPF_MEM | BPF_B: @@ -907,14 +908,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext } break; case BPF_DW: - if (is_signed_imm12(off)) { - emit_insn(ctx, ldd, dst, src, off); - } else if (is_signed_imm14(off)) { - emit_insn(ctx, ldptrd, dst, src, off); - } else { - move_imm(ctx, t1, off, is32); - emit_insn(ctx, ldxd, dst, src, t1); - } + move_imm(ctx, t1, off, is32); + emit_insn(ctx, ldxd, dst, src, t1); break; } diff --git a/arch/loongarch/pci/acpi.c b/arch/loongarch/pci/acpi.c index 365f7de771cbb9..1da4dc46df43e5 100644 --- a/arch/loongarch/pci/acpi.c +++ b/arch/loongarch/pci/acpi.c @@ -225,6 +225,7 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) if (bus) { memcpy(bus->sysdata, info->cfg, sizeof(struct pci_config_window)); kfree(info); + kfree(root_ops); } else { struct pci_bus *child; diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile index 5c97d146332821..f597cd08a96be0 100644 --- a/arch/loongarch/vdso/Makefile +++ b/arch/loongarch/vdso/Makefile @@ -2,6 +2,7 @@ # Objects to go into the VDSO. KASAN_SANITIZE := n +UBSAN_SANITIZE := n KCOV_INSTRUMENT := n # Include the generic Makefile to check the built vdso. @@ -83,13 +84,3 @@ $(obj)/vdso.so: $(obj)/vdso.so.dbg FORCE obj-y += vdso.o $(obj)/vdso.o : $(obj)/vdso.so - -# install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso.so: $(obj)/vdso.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso.so diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c index 3137b45750dfce..b7cb28f5ee290a 100644 --- a/arch/m68k/amiga/config.c +++ b/arch/m68k/amiga/config.c @@ -180,6 +180,15 @@ int __init amiga_parse_bootinfo(const struct bi_record *record) dev->slotsize = be16_to_cpu(cd->cd_SlotSize); dev->boardaddr = be32_to_cpu(cd->cd_BoardAddr); dev->boardsize = be32_to_cpu(cd->cd_BoardSize); + + /* CS-LAB Warp 1260 workaround */ + if (be16_to_cpu(dev->rom.er_Manufacturer) == ZORRO_MANUF(ZORRO_PROD_CSLAB_WARP_1260) && + dev->rom.er_Product == ZORRO_PROD(ZORRO_PROD_CSLAB_WARP_1260)) { + + /* turn off all interrupts */ + pr_info("Warp 1260 card detected: applying interrupt storm workaround\n"); + *(uint32_t *)(dev->boardaddr + 0x1000) = 0xfff; + } } else pr_warn("amiga_parse_bootinfo: too many AutoConfig devices\n"); #endif /* CONFIG_ZORRO */ diff --git a/arch/m68k/atari/ataints.c b/arch/m68k/atari/ataints.c index 56f02ea2c248d8..715d1e0d973e61 100644 --- a/arch/m68k/atari/ataints.c +++ b/arch/m68k/atari/ataints.c @@ -302,11 +302,7 @@ void __init atari_init_IRQ(void) if (ATARIHW_PRESENT(SCU)) { /* init the SCU if present */ - tt_scu.sys_mask = 0x10; /* enable VBL (for the cursor) and - * disable HSYNC interrupts (who - * needs them?) MFP and SCC are - * enabled in VME mask - */ + tt_scu.sys_mask = 0x0; /* disable all interrupts */ tt_scu.vme_mask = 0x60; /* enable MFP and SCC ints */ } else { /* If no SCU and no Hades, the HSYNC interrupt needs to be diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h index ed12358c4783b4..9a71b0148461a4 100644 --- a/arch/m68k/include/asm/cacheflush_mm.h +++ b/arch/m68k/include/asm/cacheflush_mm.h @@ -191,6 +191,7 @@ extern void cache_push_v(unsigned long vaddr, int len); #define flush_cache_all() __flush_cache_all() #define flush_cache_vmap(start, end) flush_cache_all() +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) flush_cache_all() static inline void flush_cache_mm(struct mm_struct *mm) diff --git a/arch/m68k/include/asm/cmpxchg.h b/arch/m68k/include/asm/cmpxchg.h index d7f3de9c5d6f79..4ba14f3535fcbe 100644 --- a/arch/m68k/include/asm/cmpxchg.h +++ b/arch/m68k/include/asm/cmpxchg.h @@ -32,7 +32,7 @@ static inline unsigned long __arch_xchg(unsigned long x, volatile void * ptr, in x = tmp; break; default: - tmp = __invalid_xchg_size(x, ptr, size); + x = __invalid_xchg_size(x, ptr, size); break; } diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S index 4dd2fd7acba9ea..2e1e9ad4f98ca7 100644 --- a/arch/m68k/kernel/entry.S +++ b/arch/m68k/kernel/entry.S @@ -433,7 +433,9 @@ resume: movec %a0,%dfc /* restore status register */ - movew %a1@(TASK_THREAD+THREAD_SR),%sr + movew %a1@(TASK_THREAD+THREAD_SR),%d0 + oriw #0x0700,%d0 + movew %d0,%sr rts diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index e06ce147c0b7fc..fb87219fc3b469 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -116,7 +116,7 @@ asmlinkage int m68k_clone(struct pt_regs *regs) { /* regs will be equal to current_pt_regs() */ struct kernel_clone_args args = { - .flags = regs->d1 & ~CSIGNAL, + .flags = (u32)(regs->d1) & ~CSIGNAL, .pidfd = (int __user *)regs->d3, .child_tid = (int __user *)regs->d4, .parent_tid = (int __user *)regs->d3, diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index c7cb29f0ff0163..29e06f46ab511f 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -451,30 +451,18 @@ void mac_poweroff(void) void mac_reset(void) { - if (macintosh_config->adb_type == MAC_ADB_II && - macintosh_config->ident != MAC_MODEL_SE30) { - /* need ROMBASE in booter */ - /* indeed, plus need to MAP THE ROM !! */ - - if (mac_bi_data.rombase == 0) - mac_bi_data.rombase = 0x40800000; - - /* works on some */ - rom_reset = (void *) (mac_bi_data.rombase + 0xa); - - local_irq_disable(); - rom_reset(); #ifdef CONFIG_ADB_CUDA - } else if (macintosh_config->adb_type == MAC_ADB_EGRET || - macintosh_config->adb_type == MAC_ADB_CUDA) { + if (macintosh_config->adb_type == MAC_ADB_EGRET || + macintosh_config->adb_type == MAC_ADB_CUDA) { cuda_restart(); + } else #endif #ifdef CONFIG_ADB_PMU - } else if (macintosh_config->adb_type == MAC_ADB_PB2) { + if (macintosh_config->adb_type == MAC_ADB_PB2) { pmu_restart(); + } else #endif - } else if (CPU_IS_030) { - + if (CPU_IS_030) { /* 030-specific reset routine. The idea is general, but the * specific registers to reset are '030-specific. Until I * have a non-030 machine, I can't test anything else. @@ -522,6 +510,18 @@ void mac_reset(void) "jmp %/a0@\n\t" /* jump to the reset vector */ ".chip 68k" : : "r" (offset), "a" (rombase) : "a0"); + } else { + /* need ROMBASE in booter */ + /* indeed, plus need to MAP THE ROM !! */ + + if (mac_bi_data.rombase == 0) + mac_bi_data.rombase = 0x40800000; + + /* works on some */ + rom_reset = (void *)(mac_bi_data.rombase + 0xa); + + local_irq_disable(); + rom_reset(); } /* should never get here */ diff --git a/arch/microblaze/kernel/Makefile b/arch/microblaze/kernel/Makefile index 4393bee64eaf80..85c4d29ef43e9e 100644 --- a/arch/microblaze/kernel/Makefile +++ b/arch/microblaze/kernel/Makefile @@ -7,7 +7,6 @@ ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code and low level code CFLAGS_REMOVE_timer.o = -pg CFLAGS_REMOVE_intc.o = -pg -CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_process.o = -pg endif diff --git a/arch/microblaze/kernel/cpu/cpuinfo-static.c b/arch/microblaze/kernel/cpu/cpuinfo-static.c index 85dbda4a08a81f..03da36dc6d9c92 100644 --- a/arch/microblaze/kernel/cpu/cpuinfo-static.c +++ b/arch/microblaze/kernel/cpu/cpuinfo-static.c @@ -18,7 +18,7 @@ static const char family_string[] = CONFIG_XILINX_MICROBLAZE0_FAMILY; static const char cpu_ver_string[] = CONFIG_XILINX_MICROBLAZE0_HW_VER; #define err_printk(x) \ - early_printk("ERROR: Microblaze " x "-different for kernel and DTS\n"); + pr_err("ERROR: Microblaze " x "-different for kernel and DTS\n"); void __init set_cpuinfo_static(struct cpuinfo *ci, struct device_node *cpu) { diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 3827dc76edd823..4520c57415797f 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -193,11 +193,6 @@ asmlinkage void __init mmu_init(void) { unsigned int kstart, ksize; - if (!memblock.reserved.cnt) { - pr_emerg("Error memory count\n"); - machine_restart(NULL); - } - if ((u32) memblock.memory.regions[0].size < 0x400000) { pr_emerg("Memory must be greater than 4MB\n"); machine_restart(NULL); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index bc8421859006fa..91c3a502156b31 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -482,6 +482,7 @@ config MACH_LOONGSON2EF config MACH_LOONGSON64 bool "Loongson 64-bit family of machines" + select ARCH_DMA_DEFAULT_COHERENT select ARCH_SPARSEMEM_ENABLE select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO @@ -1273,6 +1274,7 @@ config CPU_LOONGSON64 select CPU_SUPPORTS_MSA select CPU_DIEI_BROKEN if !LOONGSON3_ENHANCEMENT select CPU_MIPSR2_IRQ_VI + select DMA_NONCOHERENT select WEAK_ORDERING select WEAK_REORDERING_BEYOND_LLSC select MIPS_ASID_BITS_VARIABLE diff --git a/arch/mips/alchemy/devboards/db1200.c b/arch/mips/alchemy/devboards/db1200.c index f521874ebb07b2..67f067706af273 100644 --- a/arch/mips/alchemy/devboards/db1200.c +++ b/arch/mips/alchemy/devboards/db1200.c @@ -847,7 +847,7 @@ int __init db1200_dev_setup(void) i2c_register_board_info(0, db1200_i2c_devs, ARRAY_SIZE(db1200_i2c_devs)); spi_register_board_info(db1200_spi_devs, - ARRAY_SIZE(db1200_i2c_devs)); + ARRAY_SIZE(db1200_spi_devs)); /* SWITCHES: S6.8 I2C/SPI selector (OFF=I2C ON=SPI) * S6.7 AC97/I2S selector (OFF=AC97 ON=I2S) diff --git a/arch/mips/alchemy/devboards/db1550.c b/arch/mips/alchemy/devboards/db1550.c index fd91d9c9a2525d..6c6837181f5555 100644 --- a/arch/mips/alchemy/devboards/db1550.c +++ b/arch/mips/alchemy/devboards/db1550.c @@ -589,7 +589,7 @@ int __init db1550_dev_setup(void) i2c_register_board_info(0, db1550_i2c_devs, ARRAY_SIZE(db1550_i2c_devs)); spi_register_board_info(db1550_spi_devs, - ARRAY_SIZE(db1550_i2c_devs)); + ARRAY_SIZE(db1550_spi_devs)); c = clk_get(NULL, "psc0_intclk"); if (!IS_ERR(c)) { diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index ec180ab92eaa83..66a8ba19c28722 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -110,7 +110,8 @@ static void bcm6358_quirks(void) * RAC flush causes kernel panics on BCM6358 when booting from TP1 * because the bootloader is not initializing it properly. */ - bmips_rac_flush_disable = !!(read_c0_brcm_cmt_local() & (1 << 31)); + bmips_rac_flush_disable = !!(read_c0_brcm_cmt_local() & (1 << 31)) || + !!BMIPS_GET_CBR(); } static void bcm6368_quirks(void) diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi index f878f47e4501bc..cc7747c5f21f35 100644 --- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi +++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi @@ -23,14 +23,6 @@ cpu0: cpu@0 { }; }; - memory@200000 { - compatible = "memory"; - device_type = "memory"; - reg = <0x00000000 0x00200000 0x00000000 0x0ee00000>, /* 238 MB at 2 MB */ - <0x00000000 0x20000000 0x00000000 0x1f000000>, /* 496 MB at 512 MB */ - <0x00000001 0x10000000 0x00000001 0xb0000000>; /* 6912 MB at 4352MB */ - }; - cpu_clk: cpu_clk { #clock-cells = <0>; compatible = "fixed-clock"; @@ -52,6 +44,13 @@ package0: bus@10000000 { 0 0x40000000 0 0x40000000 0 0x40000000 0xfe 0x00000000 0xfe 0x00000000 0 0x40000000>; + isa@18000000 { + compatible = "isa"; + #size-cells = <1>; + #address-cells = <2>; + ranges = <1 0x0 0x0 0x18000000 0x4000>; + }; + pm: reset-controller@1fe07000 { compatible = "loongson,ls2k-pm"; reg = <0 0x1fe07000 0 0x422>; @@ -100,8 +99,8 @@ liointc1: interrupt-controller@1fe11440 { rtc0: rtc@1fe07800 { compatible = "loongson,ls2k1000-rtc"; reg = <0 0x1fe07800 0 0x78>; - interrupt-parent = <&liointc0>; - interrupts = <60 IRQ_TYPE_LEVEL_LOW>; + interrupt-parent = <&liointc1>; + interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; }; uart0: serial@1fe00000 { @@ -109,7 +108,7 @@ uart0: serial@1fe00000 { reg = <0 0x1fe00000 0 0x8>; clock-frequency = <125000000>; interrupt-parent = <&liointc0>; - interrupts = <0 IRQ_TYPE_LEVEL_LOW>; + interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; no-loopback-test; }; @@ -118,7 +117,6 @@ pci@1a000000 { device_type = "pci"; #address-cells = <3>; #size-cells = <2>; - #interrupt-cells = <2>; reg = <0 0x1a000000 0 0x02000000>, <0xfe 0x00000000 0 0x20000000>; @@ -130,15 +128,15 @@ gmac@3,0 { compatible = "pci0014,7a03.0", "pci0014,7a03", "pciclass0c0320", - "pciclass0c03", - "loongson, pci-gmac"; + "pciclass0c03"; reg = <0x1800 0x0 0x0 0x0 0x0>; - interrupts = <12 IRQ_TYPE_LEVEL_LOW>, - <13 IRQ_TYPE_LEVEL_LOW>; + interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, + <13 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; interrupt-parent = <&liointc0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; + phy-handle = <&phy1>; mdio { #address-cells = <1>; #size-cells = <0>; @@ -157,11 +155,12 @@ gmac@3,1 { "loongson, pci-gmac"; reg = <0x1900 0x0 0x0 0x0 0x0>; - interrupts = <14 IRQ_TYPE_LEVEL_LOW>, - <15 IRQ_TYPE_LEVEL_LOW>; + interrupts = <14 IRQ_TYPE_LEVEL_HIGH>, + <15 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; interrupt-parent = <&liointc0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; + phy-handle = <&phy1>; mdio { #address-cells = <1>; #size-cells = <0>; @@ -179,7 +178,7 @@ ehci@4,1 { "pciclass0c03"; reg = <0x2100 0x0 0x0 0x0 0x0>; - interrupts = <18 IRQ_TYPE_LEVEL_LOW>; + interrupts = <18 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; }; @@ -190,7 +189,7 @@ ohci@4,2 { "pciclass0c03"; reg = <0x2200 0x0 0x0 0x0 0x0>; - interrupts = <19 IRQ_TYPE_LEVEL_LOW>; + interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; }; @@ -201,97 +200,121 @@ sata@8,0 { "pciclass0106"; reg = <0x4000 0x0 0x0 0x0 0x0>; - interrupts = <19 IRQ_TYPE_LEVEL_LOW>; + interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc0>; }; - pci_bridge@9,0 { + pcie@9,0 { compatible = "pci0014,7a19.0", "pci0014,7a19", "pciclass060400", "pciclass0604"; reg = <0x4800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <0 IRQ_TYPE_LEVEL_LOW>; + interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 0 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 0 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@a,0 { + pcie@a,0 { compatible = "pci0014,7a09.0", "pci0014,7a09", "pciclass060400", "pciclass0604"; reg = <0x5000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + interrupts = <1 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 1 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 1 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@b,0 { + pcie@b,0 { compatible = "pci0014,7a09.0", "pci0014,7a09", "pciclass060400", "pciclass0604"; reg = <0x5800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <2 IRQ_TYPE_LEVEL_LOW>; + interrupts = <2 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 2 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 2 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@c,0 { + pcie@c,0 { compatible = "pci0014,7a09.0", "pci0014,7a09", "pciclass060400", "pciclass0604"; reg = <0x6000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <3 IRQ_TYPE_LEVEL_LOW>; + interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 3 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 3 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@d,0 { + pcie@d,0 { compatible = "pci0014,7a19.0", "pci0014,7a19", "pciclass060400", "pciclass0604"; reg = <0x6800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <4 IRQ_TYPE_LEVEL_LOW>; + interrupts = <4 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 4 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 4 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@e,0 { + pcie@e,0 { compatible = "pci0014,7a09.0", "pci0014,7a09", "pciclass060400", "pciclass0604"; reg = <0x7000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <5 IRQ_TYPE_LEVEL_LOW>; + interrupts = <5 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 5 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 5 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; diff --git a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi index 7c69e8245c2f10..cce9428afc41fc 100644 --- a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi +++ b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi @@ -193,8 +193,7 @@ gmac@3,0 { compatible = "pci0014,7a03.0", "pci0014,7a03", "pciclass020000", - "pciclass0200", - "loongson, pci-gmac"; + "pciclass0200"; reg = <0x1800 0x0 0x0 0x0 0x0>; interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index f36c2519ed9768..1f14132b3fc98a 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -97,6 +97,8 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end) __flush_cache_vmap(); } +#define flush_cache_vmap_early(start, end) do { } while (0) + extern void (*__flush_cache_vunmap)(void); static inline void flush_cache_vunmap(unsigned long start, unsigned long end) diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h index 4044eaf989ac7d..0921ddda11a4b3 100644 --- a/arch/mips/include/asm/checksum.h +++ b/arch/mips/include/asm/checksum.h @@ -241,7 +241,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " .set pop" : "=&r" (sum), "=&r" (tmp) : "r" (saddr), "r" (daddr), - "0" (htonl(len)), "r" (htonl(proto)), "r" (sum)); + "0" (htonl(len)), "r" (htonl(proto)), "r" (sum) + : "memory"); return csum_fold(sum); } diff --git a/arch/mips/include/asm/dmi.h b/arch/mips/include/asm/dmi.h index 27415a288adf56..dc397f630c6608 100644 --- a/arch/mips/include/asm/dmi.h +++ b/arch/mips/include/asm/dmi.h @@ -5,7 +5,7 @@ #include #include -#define dmi_early_remap(x, l) ioremap_cache(x, l) +#define dmi_early_remap(x, l) ioremap(x, l) #define dmi_early_unmap(x, l) iounmap(x) #define dmi_remap(x, l) ioremap_cache(x, l) #define dmi_unmap(x) iounmap(x) diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h index c5c6864e64bc43..405c85173f2c16 100644 --- a/arch/mips/include/asm/jump_label.h +++ b/arch/mips/include/asm/jump_label.h @@ -36,7 +36,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\t" B_INSN " 2f\n\t" + asm goto("1:\t" B_INSN " 2f\n\t" "2:\t.insn\n\t" ".pushsection __jump_table, \"aw\"\n\t" WORD_INSN " 1b, %l[l_yes], %0\n\t" @@ -50,7 +50,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\t" J_INSN " %l[l_yes]\n\t" + asm goto("1:\t" J_INSN " %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" WORD_INSN " 1b, %l[l_yes], %0\n\t" ".popsection\n\t" diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h index 035b1a69e2d00d..9218b3ae338322 100644 --- a/arch/mips/include/asm/mach-loongson64/boot_param.h +++ b/arch/mips/include/asm/mach-loongson64/boot_param.h @@ -14,7 +14,11 @@ #define ADAPTER_ROM 8 #define ACPI_TABLE 9 #define SMBIOS_TABLE 10 -#define MAX_MEMORY_TYPE 11 +#define UMA_VIDEO_RAM 11 +#define VUMA_VIDEO_RAM 12 +#define MAX_MEMORY_TYPE 13 + +#define MEM_SIZE_IS_IN_BYTES (1 << 31) #define LOONGSON3_BOOT_MEM_MAP_MAX 128 struct efi_memory_map_loongson { @@ -38,12 +42,14 @@ enum loongson_cpu_type { Legacy_1B = 0x5, Legacy_2G = 0x6, Legacy_2H = 0x7, + Legacy_2K = 0x8, Loongson_1A = 0x100, Loongson_1B = 0x101, Loongson_2E = 0x200, Loongson_2F = 0x201, Loongson_2G = 0x202, Loongson_2H = 0x203, + Loongson_2K = 0x204, Loongson_3A = 0x300, Loongson_3B = 0x301 }; @@ -117,7 +123,8 @@ struct irq_source_routing_table { u64 pci_io_start_addr; u64 pci_io_end_addr; u64 pci_config_addr; - u32 dma_mask_bits; + u16 dma_mask_bits; + u16 dma_noncoherent; } __packed; struct interface_info { diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h index 23c67c0871b17c..696b40beb774f5 100644 --- a/arch/mips/include/asm/mips-cm.h +++ b/arch/mips/include/asm/mips-cm.h @@ -228,6 +228,10 @@ GCR_ACCESSOR_RO(32, 0x0d0, gic_status) GCR_ACCESSOR_RO(32, 0x0f0, cpc_status) #define CM_GCR_CPC_STATUS_EX BIT(0) +/* GCR_ACCESS - Controls core/IOCU access to GCRs */ +GCR_ACCESSOR_RW(32, 0x120, access_cm3) +#define CM_GCR_ACCESS_ACCESSEN GENMASK(7, 0) + /* GCR_L2_CONFIG - Indicates L2 cache configuration when Config5.L2C=1 */ GCR_ACCESSOR_RW(32, 0x130, l2_config) #define CM_GCR_L2_CONFIG_BYPASS BIT(20) diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index daf3cf244ea972..4a2b40ce39e091 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -60,6 +60,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { regs->cp0_epc = val; + regs->cp0_cause &= ~CAUSEF_BD; } /* Query offset/name of register from its name/offset */ @@ -154,9 +155,11 @@ static inline long regs_return_value(struct pt_regs *regs) } #define instruction_pointer(regs) ((regs)->cp0_epc) +extern unsigned long exception_ip(struct pt_regs *regs); +#define exception_ip(regs) exception_ip(regs) #define profile_pc(regs) instruction_pointer(regs) -extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall); +extern asmlinkage long syscall_trace_enter(struct pt_regs *regs); extern asmlinkage void syscall_trace_leave(struct pt_regs *regs); extern void die(const char *, struct pt_regs *) __noreturn; diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index d1b11f66f748f0..cb1045ebab0621 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -101,6 +101,7 @@ void output_thread_info_defines(void) OFFSET(TI_CPU, thread_info, cpu); OFFSET(TI_PRE_COUNT, thread_info, preempt_count); OFFSET(TI_REGS, thread_info, regs); + OFFSET(TI_SYSCALL, thread_info, syscall); DEFINE(_THREAD_SIZE, THREAD_SIZE); DEFINE(_THREAD_MASK, THREAD_MASK); DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE); diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index 368e8475870f08..5f6e9e2ebbdbb8 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -303,13 +303,6 @@ int r4k_clockevent_init(void) if (!c0_compare_int_usable()) return -ENXIO; - /* - * With vectored interrupts things are getting platform specific. - * get_c0_compare_int is a hook to allow a platform to return the - * interrupt number of its liking. - */ - irq = get_c0_compare_int(); - cd = &per_cpu(mips_clockevent_device, cpu); cd->name = "MIPS"; @@ -320,7 +313,6 @@ int r4k_clockevent_init(void) min_delta = calculate_min_delta(); cd->rating = 300; - cd->irq = irq; cd->cpumask = cpumask_of(cpu); cd->set_next_event = mips_next_event; cd->event_handler = mips_event_handler; @@ -332,6 +324,13 @@ int r4k_clockevent_init(void) cp0_timer_irq_installed = 1; + /* + * With vectored interrupts things are getting platform specific. + * get_c0_compare_int is a hook to allow a platform to return the + * interrupt number of its liking. + */ + irq = get_c0_compare_int(); + if (request_irq(irq, c0_compare_interrupt, flags, "timer", c0_compare_interrupt)) pr_err("Failed to request irq %d (timer)\n", irq); diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index b406d8bfb15a36..c7fee72ea60679 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1725,12 +1725,16 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM | MIPS_ASE_LOONGSON_EXT | MIPS_ASE_LOONGSON_EXT2); c->ases &= ~MIPS_ASE_VZ; /* VZ of Loongson-3A2000/3000 is incomplete */ + change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER, + LOONGSON_CONF6_INTIMER); break; case PRID_IMP_LOONGSON_64G: __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); decode_cpucfg(c); + change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER, + LOONGSON_CONF6_INTIMER); break; default: panic("Unknown Loongson Processor ID!"); diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c index 5582a4ca1e9e36..7aa2c2360ff602 100644 --- a/arch/mips/kernel/elf.c +++ b/arch/mips/kernel/elf.c @@ -11,6 +11,7 @@ #include #include +#include #ifdef CONFIG_MIPS_FP_SUPPORT @@ -309,6 +310,11 @@ void mips_set_personality_nan(struct arch_elf_state *state) struct cpuinfo_mips *c = &boot_cpu_data; struct task_struct *t = current; + /* Do this early so t->thread.fpu.fcr31 won't be clobbered in case + * we are preempted before the lose_fpu(0) in start_thread. + */ + lose_fpu(0); + t->thread.fpu.fcr31 = c->fpu_csr31; switch (state->nan_2008) { case 0: diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 5387ed0a51862b..b630604c577f9f 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -121,6 +121,19 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) /* Put the stack after the struct pt_regs. */ childksp = (unsigned long) childregs; p->thread.cp0_status = (read_c0_status() & ~(ST0_CU2|ST0_CU1)) | ST0_KERNEL_CUMASK; + + /* + * New tasks lose permission to use the fpu. This accelerates context + * switching for most programs since they don't use the fpu. + */ + clear_tsk_thread_flag(p, TIF_USEDFPU); + clear_tsk_thread_flag(p, TIF_USEDMSA); + clear_tsk_thread_flag(p, TIF_MSA_CTX_LIVE); + +#ifdef CONFIG_MIPS_MT_FPAFF + clear_tsk_thread_flag(p, TIF_FPUBOUND); +#endif /* CONFIG_MIPS_MT_FPAFF */ + if (unlikely(args->fn)) { /* kernel thread */ unsigned long status = p->thread.cp0_status; @@ -149,20 +162,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.reg29 = (unsigned long) childregs; p->thread.reg31 = (unsigned long) ret_from_fork; - /* - * New tasks lose permission to use the fpu. This accelerates context - * switching for most programs since they don't use the fpu. - */ childregs->cp0_status &= ~(ST0_CU2|ST0_CU1); - clear_tsk_thread_flag(p, TIF_USEDFPU); - clear_tsk_thread_flag(p, TIF_USEDMSA); - clear_tsk_thread_flag(p, TIF_MSA_CTX_LIVE); - -#ifdef CONFIG_MIPS_MT_FPAFF - clear_tsk_thread_flag(p, TIF_FPUBOUND); -#endif /* CONFIG_MIPS_MT_FPAFF */ - #ifdef CONFIG_MIPS_FP_SUPPORT atomic_set(&p->thread.bd_emu_frame, BD_EMUFRAME_NONE); #endif diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index d9df543f7e2c4c..61503a36067e9e 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -31,6 +31,7 @@ #include #include +#include #include #include #include @@ -48,6 +49,12 @@ #define CREATE_TRACE_POINTS #include +unsigned long exception_ip(struct pt_regs *regs) +{ + return exception_epc(regs); +} +EXPORT_SYMBOL(exception_ip); + /* * Called by kernel/ptrace.c when detaching.. * @@ -1310,16 +1317,13 @@ long arch_ptrace(struct task_struct *child, long request, * Notification of system call entry/exit * - triggered by current->work.syscall_trace */ -asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) +asmlinkage long syscall_trace_enter(struct pt_regs *regs) { user_exit(); - current_thread_info()->syscall = syscall; - if (test_thread_flag(TIF_SYSCALL_TRACE)) { if (ptrace_report_syscall_entry(regs)) return -1; - syscall = current_thread_info()->syscall; } #ifdef CONFIG_SECCOMP @@ -1328,7 +1332,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) struct seccomp_data sd; unsigned long args[6]; - sd.nr = syscall; + sd.nr = current_thread_info()->syscall; sd.arch = syscall_get_arch(current); syscall_get_arguments(current, regs, args); for (i = 0; i < 6; i++) @@ -1338,23 +1342,23 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) ret = __secure_computing(&sd); if (ret == -1) return ret; - syscall = current_thread_info()->syscall; } #endif if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->regs[2]); - audit_syscall_entry(syscall, regs->regs[4], regs->regs[5], + audit_syscall_entry(current_thread_info()->syscall, + regs->regs[4], regs->regs[5], regs->regs[6], regs->regs[7]); /* * Negative syscall numbers are mistaken for rejected syscalls, but * won't have had the return value set appropriately, so we do so now. */ - if (syscall < 0) + if (current_thread_info()->syscall < 0) syscall_set_return_value(current, regs, -ENOSYS, 0); - return syscall; + return current_thread_info()->syscall; } /* diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 18dc9b34505614..2c604717e63080 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -77,6 +77,18 @@ loads_done: PTR_WD load_a7, bad_stack_a7 .previous + /* + * syscall number is in v0 unless we called syscall(__NR_###) + * where the real syscall number is in a0 + */ + subu t2, v0, __NR_O32_Linux + bnez t2, 1f /* __NR_syscall at offset 0 */ + LONG_S a0, TI_SYSCALL($28) # Save a0 as syscall number + b 2f +1: + LONG_S v0, TI_SYSCALL($28) # Save v0 as syscall number +2: + lw t0, TI_FLAGS($28) # syscall tracing enabled? li t1, _TIF_WORK_SYSCALL_ENTRY and t0, t1 @@ -114,16 +126,7 @@ syscall_trace_entry: SAVE_STATIC move a0, sp - /* - * syscall number is in v0 unless we called syscall(__NR_###) - * where the real syscall number is in a0 - */ - move a1, v0 - subu t2, v0, __NR_O32_Linux - bnez t2, 1f /* __NR_syscall at offset 0 */ - lw a1, PT_R4(sp) - -1: jal syscall_trace_enter + jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 97456b2ca7dc32..97788859238c34 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -44,6 +44,8 @@ NESTED(handle_sysn32, PT_SIZE, sp) sd a3, PT_R26(sp) # save a3 for syscall restarting + LONG_S v0, TI_SYSCALL($28) # Store syscall number + li t1, _TIF_WORK_SYSCALL_ENTRY LONG_L t0, TI_FLAGS($28) # syscall tracing enabled? and t0, t1, t0 @@ -72,7 +74,6 @@ syscall_common: n32_syscall_trace_entry: SAVE_STATIC move a0, sp - move a1, v0 jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/scall64-n64.S b/arch/mips/kernel/scall64-n64.S index e6264aa62e457f..be11ea5cc67e04 100644 --- a/arch/mips/kernel/scall64-n64.S +++ b/arch/mips/kernel/scall64-n64.S @@ -46,6 +46,8 @@ NESTED(handle_sys64, PT_SIZE, sp) sd a3, PT_R26(sp) # save a3 for syscall restarting + LONG_S v0, TI_SYSCALL($28) # Store syscall number + li t1, _TIF_WORK_SYSCALL_ENTRY LONG_L t0, TI_FLAGS($28) # syscall tracing enabled? and t0, t1, t0 @@ -82,7 +84,6 @@ n64_syscall_exit: syscall_trace_entry: SAVE_STATIC move a0, sp - move a1, v0 jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index d3c2616cba2269..7a5abb73e53127 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -79,6 +79,22 @@ loads_done: PTR_WD load_a7, bad_stack_a7 .previous + /* + * absolute syscall number is in v0 unless we called syscall(__NR_###) + * where the real syscall number is in a0 + * note: NR_syscall is the first O32 syscall but the macro is + * only defined when compiling with -mabi=32 (CONFIG_32BIT) + * therefore __NR_O32_Linux is used (4000) + */ + + subu t2, v0, __NR_O32_Linux + bnez t2, 1f /* __NR_syscall at offset 0 */ + LONG_S a0, TI_SYSCALL($28) # Save a0 as syscall number + b 2f +1: + LONG_S v0, TI_SYSCALL($28) # Save v0 as syscall number +2: + li t1, _TIF_WORK_SYSCALL_ENTRY LONG_L t0, TI_FLAGS($28) # syscall tracing enabled? and t0, t1, t0 @@ -113,22 +129,7 @@ trace_a_syscall: sd a7, PT_R11(sp) # For indirect syscalls move a0, sp - /* - * absolute syscall number is in v0 unless we called syscall(__NR_###) - * where the real syscall number is in a0 - * note: NR_syscall is the first O32 syscall but the macro is - * only defined when compiling with -mabi=32 (CONFIG_32BIT) - * therefore __NR_O32_Linux is used (4000) - */ - .set push - .set reorder - subu t1, v0, __NR_O32_Linux - move a1, v0 - bnez t1, 1f /* __NR_syscall at offset 0 */ - ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ - .set pop - -1: jal syscall_trace_enter + jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index cb871eb784a7c1..3f45b72561db9c 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -54,7 +54,7 @@ struct cpuinfo_mips cpu_data[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_data); -#ifdef CONFIG_VT +#ifdef CONFIG_VGA_CONSOLE struct screen_info screen_info; #endif @@ -326,11 +326,11 @@ static void __init bootmem_init(void) panic("Incorrect memory mapping !!!"); if (max_pfn > PFN_DOWN(HIGHMEM_START)) { + max_low_pfn = PFN_DOWN(HIGHMEM_START); #ifdef CONFIG_HIGHMEM - highstart_pfn = PFN_DOWN(HIGHMEM_START); + highstart_pfn = max_low_pfn; highend_pfn = max_pfn; #else - max_low_pfn = PFN_DOWN(HIGHMEM_START); max_pfn = max_low_pfn; #endif } diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index dd55d59b88db34..d445f8e849abdc 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -222,7 +222,10 @@ static void boot_core(unsigned int core, unsigned int vpe_id) write_gcr_co_reset_ext_base(CM_GCR_Cx_RESET_EXT_BASE_UEB); /* Ensure the core can access the GCRs */ - set_gcr_access(1 << core); + if (mips_cm_revision() < CM_REV_CM3) + set_gcr_access(1 << core); + else + set_gcr_access_cm3(1 << core); if (mips_cpc_present()) { /* Reset the core */ diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 8fbef537fb8859..81f6c4f8fbc154 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -351,10 +351,11 @@ early_initcall(mips_smp_ipi_init); */ asmlinkage void start_secondary(void) { - unsigned int cpu; + unsigned int cpu = raw_smp_processor_id(); cpu_probe(); per_cpu_trap_init(false); + rcu_cpu_starting(cpu); mips_clockevent_init(); mp_ops->init_secondary(); cpu_report(); @@ -366,7 +367,6 @@ asmlinkage void start_secondary(void) */ calibrate_delay(); - cpu = smp_processor_id(); cpu_data[cpu].udelay_val = loops_per_jiffy; set_cpu_sibling_map(cpu); diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 152034b8e0a0f3..4a296124604a15 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -354,7 +354,7 @@ 412 n32 utimensat_time64 sys_utimensat 413 n32 pselect6_time64 compat_sys_pselect6_time64 414 n32 ppoll_time64 compat_sys_ppoll_time64 -416 n32 io_pgetevents_time64 sys_io_pgetevents +416 n32 io_pgetevents_time64 compat_sys_io_pgetevents_time64 417 n32 recvmmsg_time64 compat_sys_recvmmsg_time64 418 n32 mq_timedsend_time64 sys_mq_timedsend 419 n32 mq_timedreceive_time64 sys_mq_timedreceive diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 1a646813afdca4..1ee62a861380a2 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -27,7 +27,7 @@ 17 o32 break sys_ni_syscall # 18 was sys_stat 18 o32 unused18 sys_ni_syscall -19 o32 lseek sys_lseek +19 o32 lseek sys_lseek compat_sys_lseek 20 o32 getpid sys_getpid 21 o32 mount sys_mount 22 o32 umount sys_oldumount @@ -403,7 +403,7 @@ 412 o32 utimensat_time64 sys_utimensat sys_utimensat 413 o32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 o32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 o32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +416 o32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 o32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 o32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend 419 o32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 246c6a6b02614c..5b778995d44831 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -2007,7 +2007,13 @@ unsigned long vi_handlers[64]; void reserve_exception_space(phys_addr_t addr, unsigned long size) { - memblock_reserve(addr, size); + /* + * reserve exception space on CPUs other than CPU0 + * is too late, since memblock is unavailable when APs + * up + */ + if (smp_processor_id() == 0) + memblock_reserve(addr, size); } void __init *set_except_vector(int n, void *addr) diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c index a3cf293658581e..0c45767eacf674 100644 --- a/arch/mips/lantiq/prom.c +++ b/arch/mips/lantiq/prom.c @@ -108,10 +108,9 @@ void __init prom_init(void) prom_init_cmdline(); #if defined(CONFIG_MIPS_MT_SMP) - if (cpu_has_mipsmt) { - lantiq_smp_ops = vsmp_smp_ops; + lantiq_smp_ops = vsmp_smp_ops; + if (cpu_has_mipsmt) lantiq_smp_ops.init_secondary = lantiq_init_secondary; - register_smp_ops(&lantiq_smp_ops); - } + register_smp_ops(&lantiq_smp_ops); #endif } diff --git a/arch/mips/loongson64/env.c b/arch/mips/loongson64/env.c index c961e2999f15ac..09ff052698614d 100644 --- a/arch/mips/loongson64/env.c +++ b/arch/mips/loongson64/env.c @@ -13,6 +13,8 @@ * Copyright (C) 2009 Lemote Inc. * Author: Wu Zhangjin, wuzhangjin@gmail.com */ + +#include #include #include #include @@ -86,6 +88,12 @@ void __init prom_lefi_init_env(void) cpu_clock_freq = ecpu->cpu_clock_freq; loongson_sysconf.cputype = ecpu->cputype; switch (ecpu->cputype) { + case Legacy_2K: + case Loongson_2K: + smp_group[0] = 0x900000001fe11000; + loongson_sysconf.cores_per_node = 2; + loongson_sysconf.cores_per_package = 2; + break; case Legacy_3A: case Loongson_3A: loongson_sysconf.cores_per_node = 4; @@ -147,8 +155,14 @@ void __init prom_lefi_init_env(void) loongson_sysconf.dma_mask_bits = eirq_source->dma_mask_bits; if (loongson_sysconf.dma_mask_bits < 32 || - loongson_sysconf.dma_mask_bits > 64) + loongson_sysconf.dma_mask_bits > 64) { loongson_sysconf.dma_mask_bits = 32; + dma_default_coherent = true; + } else { + dma_default_coherent = !eirq_source->dma_noncoherent; + } + + pr_info("Firmware: Coherent DMA: %s\n", dma_default_coherent ? "on" : "off"); loongson_sysconf.restart_addr = boot_p->reset_system.ResetWarm; loongson_sysconf.poweroff_addr = boot_p->reset_system.Shutdown; @@ -213,6 +227,8 @@ void __init prom_lefi_init_env(void) default: break; } + } else if ((read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64R) { + loongson_fdt_blob = __dtb_loongson64_2core_2k1000_begin; } else if ((read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64G) { if (loongson_sysconf.bridgetype == LS7A) loongson_fdt_blob = __dtb_loongson64g_4core_ls7a_begin; diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c index ee8de1735b7c04..f25caa6aa9d306 100644 --- a/arch/mips/loongson64/init.c +++ b/arch/mips/loongson64/init.c @@ -49,8 +49,7 @@ void virtual_early_config(void) void __init szmem(unsigned int node) { u32 i, mem_type; - static unsigned long num_physpages; - u64 node_id, node_psize, start_pfn, end_pfn, mem_start, mem_size; + phys_addr_t node_id, mem_start, mem_size; /* Otherwise come from DTB */ if (loongson_sysconf.fw_interface != LOONGSON_LEFI) @@ -64,30 +63,46 @@ void __init szmem(unsigned int node) mem_type = loongson_memmap->map[i].mem_type; mem_size = loongson_memmap->map[i].mem_size; - mem_start = loongson_memmap->map[i].mem_start; + + /* Memory size comes in MB if MEM_SIZE_IS_IN_BYTES not set */ + if (mem_size & MEM_SIZE_IS_IN_BYTES) + mem_size &= ~MEM_SIZE_IS_IN_BYTES; + else + mem_size = mem_size << 20; + + mem_start = (node_id << 44) | loongson_memmap->map[i].mem_start; switch (mem_type) { case SYSTEM_RAM_LOW: case SYSTEM_RAM_HIGH: - start_pfn = ((node_id << 44) + mem_start) >> PAGE_SHIFT; - node_psize = (mem_size << 20) >> PAGE_SHIFT; - end_pfn = start_pfn + node_psize; - num_physpages += node_psize; - pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n", - (u32)node_id, mem_type, mem_start, mem_size); - pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", - start_pfn, end_pfn, num_physpages); - memblock_add_node(PFN_PHYS(start_pfn), - PFN_PHYS(node_psize), node, + case UMA_VIDEO_RAM: + pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes usable\n", + (u32)node_id, mem_type, &mem_start, &mem_size); + memblock_add_node(mem_start, mem_size, node, MEMBLOCK_NONE); break; case SYSTEM_RAM_RESERVED: - pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n", - (u32)node_id, mem_type, mem_start, mem_size); - memblock_reserve(((node_id << 44) + mem_start), mem_size << 20); + case VIDEO_ROM: + case ADAPTER_ROM: + case ACPI_TABLE: + case SMBIOS_TABLE: + pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes reserved\n", + (u32)node_id, mem_type, &mem_start, &mem_size); + memblock_reserve(mem_start, mem_size); + break; + /* We should not reserve VUMA_VIDEO_RAM as it overlaps with MMIO */ + case VUMA_VIDEO_RAM: + default: + pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes unhandled\n", + (u32)node_id, mem_type, &mem_start, &mem_size); break; } } + + /* Reserve vgabios if it comes from firmware */ + if (loongson_sysconf.vgabios_addr) + memblock_reserve(virt_to_phys((void *)loongson_sysconf.vgabios_addr), + SZ_256K); } #ifndef CONFIG_NUMA diff --git a/arch/mips/loongson64/reset.c b/arch/mips/loongson64/reset.c index e420800043b089..2a8e4cd72605d0 100644 --- a/arch/mips/loongson64/reset.c +++ b/arch/mips/loongson64/reset.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -21,36 +22,21 @@ #include #include -static void loongson_restart(char *command) +static int firmware_restart(struct sys_off_data *unusedd) { void (*fw_restart)(void) = (void *)loongson_sysconf.restart_addr; fw_restart(); - while (1) { - if (cpu_wait) - cpu_wait(); - } + return NOTIFY_DONE; } -static void loongson_poweroff(void) +static int firmware_poweroff(struct sys_off_data *unused) { void (*fw_poweroff)(void) = (void *)loongson_sysconf.poweroff_addr; fw_poweroff(); - while (1) { - if (cpu_wait) - cpu_wait(); - } -} - -static void loongson_halt(void) -{ - pr_notice("\n\n** You can safely turn off the power now **\n\n"); - while (1) { - if (cpu_wait) - cpu_wait(); - } + return NOTIFY_DONE; } #ifdef CONFIG_KEXEC @@ -154,9 +140,17 @@ static void loongson_crash_shutdown(struct pt_regs *regs) static int __init mips_reboot_setup(void) { - _machine_restart = loongson_restart; - _machine_halt = loongson_halt; - pm_power_off = loongson_poweroff; + if (loongson_sysconf.restart_addr) { + register_sys_off_handler(SYS_OFF_MODE_RESTART, + SYS_OFF_PRIO_FIRMWARE, + firmware_restart, NULL); + } + + if (loongson_sysconf.poweroff_addr) { + register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, + SYS_OFF_PRIO_FIRMWARE, + firmware_poweroff, NULL); + } #ifdef CONFIG_KEXEC kexec_argv = kmalloc(KEXEC_ARGV_SIZE, GFP_KERNEL); diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c index e015a26a40f7a5..979993679d913e 100644 --- a/arch/mips/loongson64/smp.c +++ b/arch/mips/loongson64/smp.c @@ -466,12 +466,25 @@ static void loongson3_smp_finish(void) static void __init loongson3_smp_setup(void) { int i = 0, num = 0; /* i: physical id, num: logical id */ + int max_cpus = 0; init_cpu_possible(cpu_none_mask); + for (i = 0; i < ARRAY_SIZE(smp_group); i++) { + if (!smp_group[i]) + break; + max_cpus += loongson_sysconf.cores_per_node; + } + + if (max_cpus < loongson_sysconf.nr_cpus) { + pr_err("SMP Groups are less than the number of CPUs\n"); + loongson_sysconf.nr_cpus = max_cpus ? max_cpus : 1; + } + /* For unified kernel, NR_CPUS is the maximum possible value, * loongson_sysconf.nr_cpus is the really present value */ + i = 0; while (i < loongson_sysconf.nr_cpus) { if (loongson_sysconf.reserved_cpus_mask & (1< PAGE_SHIFT)); -#ifdef CONFIG_HIGHMEM - max_mapnr = highend_pfn ? highend_pfn : max_low_pfn; -#else - max_mapnr = max_low_pfn; -#endif - high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); - maar_init(); memblock_free_all(); setup_zero_pages(); /* Setup zeroed pages. */ diff --git a/arch/mips/pci/ops-rc32434.c b/arch/mips/pci/ops-rc32434.c index 874ed6df97683a..34b9323bdabb0e 100644 --- a/arch/mips/pci/ops-rc32434.c +++ b/arch/mips/pci/ops-rc32434.c @@ -112,8 +112,8 @@ static int read_config_dword(struct pci_bus *bus, unsigned int devfn, * gives them time to settle */ if (where == PCI_VENDOR_ID) { - if (ret == 0xffffffff || ret == 0x00000000 || - ret == 0x0000ffff || ret == 0xffff0000) { + if (*val == 0xffffffff || *val == 0x00000000 || + *val == 0x0000ffff || *val == 0xffff0000) { if (delay > 4) return 0; delay *= 2; diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c index c9edd3fb380df5..9eaacd3d338805 100644 --- a/arch/mips/pci/pcie-octeon.c +++ b/arch/mips/pci/pcie-octeon.c @@ -230,12 +230,18 @@ static inline uint64_t __cvmx_pcie_build_config_addr(int pcie_port, int bus, { union cvmx_pcie_address pcie_addr; union cvmx_pciercx_cfg006 pciercx_cfg006; + union cvmx_pciercx_cfg032 pciercx_cfg032; pciercx_cfg006.u32 = cvmx_pcie_cfgx_read(pcie_port, CVMX_PCIERCX_CFG006(pcie_port)); if ((bus <= pciercx_cfg006.s.pbnum) && (dev != 0)) return 0; + pciercx_cfg032.u32 = + cvmx_pcie_cfgx_read(pcie_port, CVMX_PCIERCX_CFG032(pcie_port)); + if ((pciercx_cfg032.s.dlla == 0) || (pciercx_cfg032.s.lt == 1)) + return 0; + pcie_addr.u64 = 0; pcie_addr.config.upper = 2; pcie_addr.config.io = 1; diff --git a/arch/mips/sgi-ip30/ip30-console.c b/arch/mips/sgi-ip30/ip30-console.c index b91f8c4fdc7860..a087b7ebe12936 100644 --- a/arch/mips/sgi-ip30/ip30-console.c +++ b/arch/mips/sgi-ip30/ip30-console.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index 76683993cdd3ad..37df504d3ecbb0 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -129,7 +129,7 @@ void __init plat_mem_setup(void) if (m41t81_probe()) swarm_rtc_type = RTC_M41T81; -#ifdef CONFIG_VT +#ifdef CONFIG_VGA_CONSOLE screen_info = (struct screen_info) { .orig_video_page = 52, .orig_video_mode = 3, diff --git a/arch/mips/sni/setup.c b/arch/mips/sni/setup.c index efad85c8c823b9..9984cf91be7d04 100644 --- a/arch/mips/sni/setup.c +++ b/arch/mips/sni/setup.c @@ -38,7 +38,7 @@ extern void sni_machine_power_off(void); static void __init sni_display_setup(void) { -#if defined(CONFIG_VT) && defined(CONFIG_VGA_CONSOLE) && defined(CONFIG_FW_ARC) +#if defined(CONFIG_VGA_CONSOLE) && defined(CONFIG_FW_ARC) struct screen_info *si = &screen_info; DISPLAY_STATUS *di; diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h index 348cea0977927a..81484a776b333a 100644 --- a/arch/nios2/include/asm/cacheflush.h +++ b/arch/nios2/include/asm/cacheflush.h @@ -38,6 +38,7 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page, #define flush_icache_pages flush_icache_pages #define flush_cache_vmap(start, end) flush_dcache_range(start, end) +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) flush_dcache_range(start, end) extern void copy_to_user_page(struct vm_area_struct *vma, struct page *page, diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c index 9cf7fb60441f89..be56eaafc8b957 100644 --- a/arch/openrisc/kernel/setup.c +++ b/arch/openrisc/kernel/setup.c @@ -255,6 +255,9 @@ void calibrate_delay(void) void __init setup_arch(char **cmdline_p) { + /* setup memblock allocator */ + setup_memory(); + unflatten_and_copy_device_tree(); setup_cpuinfo(); @@ -278,9 +281,6 @@ void __init setup_arch(char **cmdline_p) } #endif - /* setup memblock allocator */ - setup_memory(); - /* paging_init() sets up the MMU and marks all pages as reserved */ paging_init(); diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index 9370888c9a7e31..90554a5558fbca 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -180,29 +180,39 @@ asmlinkage void unhandled_exception(struct pt_regs *regs, int ea, int vector) asmlinkage void do_fpe_trap(struct pt_regs *regs, unsigned long address) { - int code = FPE_FLTUNK; - unsigned long fpcsr = regs->fpcsr; - - if (fpcsr & SPR_FPCSR_IVF) - code = FPE_FLTINV; - else if (fpcsr & SPR_FPCSR_OVF) - code = FPE_FLTOVF; - else if (fpcsr & SPR_FPCSR_UNF) - code = FPE_FLTUND; - else if (fpcsr & SPR_FPCSR_DZF) - code = FPE_FLTDIV; - else if (fpcsr & SPR_FPCSR_IXF) - code = FPE_FLTRES; - - /* Clear all flags */ - regs->fpcsr &= ~SPR_FPCSR_ALLF; - - force_sig_fault(SIGFPE, code, (void __user *)regs->pc); + if (user_mode(regs)) { + int code = FPE_FLTUNK; + unsigned long fpcsr = regs->fpcsr; + + if (fpcsr & SPR_FPCSR_IVF) + code = FPE_FLTINV; + else if (fpcsr & SPR_FPCSR_OVF) + code = FPE_FLTOVF; + else if (fpcsr & SPR_FPCSR_UNF) + code = FPE_FLTUND; + else if (fpcsr & SPR_FPCSR_DZF) + code = FPE_FLTDIV; + else if (fpcsr & SPR_FPCSR_IXF) + code = FPE_FLTRES; + + /* Clear all flags */ + regs->fpcsr &= ~SPR_FPCSR_ALLF; + + force_sig_fault(SIGFPE, code, (void __user *)regs->pc); + } else { + pr_emerg("KERNEL: Illegal fpe exception 0x%.8lx\n", regs->pc); + die("Die:", regs, SIGFPE); + } } asmlinkage void do_trap(struct pt_regs *regs, unsigned long address) { - force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc); + if (user_mode(regs)) { + force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc); + } else { + pr_emerg("KERNEL: Illegal trap exception 0x%.8lx\n", regs->pc); + die("Die:", regs, SIGILL); + } } asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address) diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index a15ab147af2e07..a077e6bf9475f5 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -14,9 +14,11 @@ config PARISC select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAS_PTE_SPECIAL select ARCH_NO_SG_CHAIN + select ARCH_SPLIT_ARG64 if !64BIT select ARCH_SUPPORTS_HUGETLBFS if PA20 select ARCH_SUPPORTS_MEMORY_FAILURE select ARCH_STACKWALK + select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_DEBUG_VM_PGTABLE select HAVE_RELIABLE_STACKTRACE select DMA_OPS @@ -24,7 +26,6 @@ config PARISC select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE select BUG - select BUILDTIME_TABLE_SORT select HAVE_PCI select HAVE_PERF_EVENTS select HAVE_KERNEL_BZIP2 @@ -83,6 +84,7 @@ config PARISC select HAVE_SOFTIRQ_ON_OWN_STACK if IRQSTACKS select TRACE_IRQFLAGS_SUPPORT select HAVE_FUNCTION_DESCRIPTORS if 64BIT + select PCI_MSI_ARCH_FALLBACKS if PCI_MSI help The PA-RISC microprocessor is designed by Hewlett-Packard and used @@ -113,9 +115,12 @@ config ARCH_HAS_ILOG2_U64 default n config GENERIC_BUG - bool - default y + def_bool y depends on BUG + select GENERIC_BUG_RELATIVE_POINTERS if 64BIT + +config GENERIC_BUG_RELATIVE_POINTERS + bool config GENERIC_HWEIGHT bool @@ -138,11 +143,11 @@ config ARCH_MMAP_RND_COMPAT_BITS_MIN default 8 config ARCH_MMAP_RND_BITS_MAX - default 24 if 64BIT - default 17 + default 18 if 64BIT + default 13 config ARCH_MMAP_RND_COMPAT_BITS_MAX - default 17 + default 13 # unless you want to implement ACPI on PA-RISC ... ;-) config PM diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 968ebe17494c5f..920db57b6b4cc8 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -177,12 +177,8 @@ vdso_prepare: prepare0 $(Q)$(MAKE) $(build)=arch/parisc/kernel/vdso32 include/generated/vdso32-offsets.h endif -PHONY += vdso_install - -vdso_install: - $(Q)$(MAKE) $(build)=arch/parisc/kernel/vdso $@ - $(if $(CONFIG_COMPAT_VDSO), \ - $(Q)$(MAKE) $(build)=arch/parisc/kernel/vdso32 $@) +vdso-install-y += arch/parisc/kernel/vdso32/vdso32.so +vdso-install-$(CONFIG_64BIT) += arch/parisc/kernel/vdso64/vdso64.so install: KBUILD_IMAGE := vmlinux zinstall: KBUILD_IMAGE := vmlinuz diff --git a/arch/parisc/include/asm/alternative.h b/arch/parisc/include/asm/alternative.h index 1ed45fd085d3b8..1eb488f25b8380 100644 --- a/arch/parisc/include/asm/alternative.h +++ b/arch/parisc/include/asm/alternative.h @@ -34,7 +34,8 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end, /* Alternative SMP implementation. */ #define ALTERNATIVE(cond, replacement) "!0:" \ - ".section .altinstructions, \"aw\" !" \ + ".section .altinstructions, \"a\" !" \ + ".align 4 !" \ ".word (0b-4-.) !" \ ".hword 1, " __stringify(cond) " !" \ ".word " __stringify(replacement) " !" \ @@ -44,7 +45,8 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end, /* to replace one single instructions by a new instruction */ #define ALTERNATIVE(from, to, cond, replacement)\ - .section .altinstructions, "aw" ! \ + .section .altinstructions, "a" ! \ + .align 4 ! \ .word (from - .) ! \ .hword (to - from)/4, cond ! \ .word replacement ! \ @@ -52,7 +54,8 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end, /* to replace multiple instructions by new code */ #define ALTERNATIVE_CODE(from, num_instructions, cond, new_instr_ptr)\ - .section .altinstructions, "aw" ! \ + .section .altinstructions, "a" ! \ + .align 4 ! \ .word (from - .) ! \ .hword -num_instructions, cond ! \ .word (new_instr_ptr - .) ! \ diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index 75677b526b2bb7..000a28e1c5e8d4 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -97,26 +97,28 @@ * version takes two arguments: a src and destination register. * However, the source and destination registers can not be * the same register. + * + * We use add,l to avoid clobbering the C/B bits in the PSW. */ .macro tophys grvirt, grphys - ldil L%(__PAGE_OFFSET), \grphys - sub \grvirt, \grphys, \grphys + ldil L%(-__PAGE_OFFSET), \grphys + addl \grvirt, \grphys, \grphys .endm - + .macro tovirt grphys, grvirt ldil L%(__PAGE_OFFSET), \grvirt - add \grphys, \grvirt, \grvirt + addl \grphys, \grvirt, \grvirt .endm .macro tophys_r1 gr - ldil L%(__PAGE_OFFSET), %r1 - sub \gr, %r1, \gr + ldil L%(-__PAGE_OFFSET), %r1 + addl \gr, %r1, \gr .endm - + .macro tovirt_r1 gr ldil L%(__PAGE_OFFSET), %r1 - add \gr, %r1, \gr + addl \gr, %r1, \gr .endm .macro delay value @@ -574,7 +576,9 @@ */ #define ASM_EXCEPTIONTABLE_ENTRY(fault_addr, except_addr) \ .section __ex_table,"aw" ! \ + .align 4 ! \ .word (fault_addr - .), (except_addr - .) ! \ + or %r0,%r0,%r0 ! \ .previous diff --git a/arch/parisc/include/asm/bug.h b/arch/parisc/include/asm/bug.h index 4b6d60b941247e..833555f74ffa72 100644 --- a/arch/parisc/include/asm/bug.h +++ b/arch/parisc/include/asm/bug.h @@ -17,24 +17,27 @@ #define PARISC_BUG_BREAK_ASM "break 0x1f, 0x1fff" #define PARISC_BUG_BREAK_INSN 0x03ffe01f /* PARISC_BUG_BREAK_ASM */ -#if defined(CONFIG_64BIT) -#define ASM_WORD_INSN ".dword\t" +#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS +# define __BUG_REL(val) ".word " __stringify(val) " - ." #else -#define ASM_WORD_INSN ".word\t" +# define __BUG_REL(val) ".word " __stringify(val) #endif + #ifdef CONFIG_DEBUG_BUGVERBOSE #define BUG() \ do { \ asm volatile("\n" \ "1:\t" PARISC_BUG_BREAK_ASM "\n" \ - "\t.pushsection __bug_table,\"aw\"\n" \ - "2:\t" ASM_WORD_INSN "1b, %c0\n" \ - "\t.short %c1, %c2\n" \ - "\t.org 2b+%c3\n" \ + "\t.pushsection __bug_table,\"a\"\n" \ + "\t.align 4\n" \ + "2:\t" __BUG_REL(1b) "\n" \ + "\t" __BUG_REL(%c0) "\n" \ + "\t.short %1, %2\n" \ + "\t.blockz %3-2*4-2*2\n" \ "\t.popsection" \ : : "i" (__FILE__), "i" (__LINE__), \ - "i" (0), "i" (sizeof(struct bug_entry)) ); \ + "i" (0), "i" (sizeof(struct bug_entry)) ); \ unreachable(); \ } while(0) @@ -51,10 +54,12 @@ do { \ asm volatile("\n" \ "1:\t" PARISC_BUG_BREAK_ASM "\n" \ - "\t.pushsection __bug_table,\"aw\"\n" \ - "2:\t" ASM_WORD_INSN "1b, %c0\n" \ - "\t.short %c1, %c2\n" \ - "\t.org 2b+%c3\n" \ + "\t.pushsection __bug_table,\"a\"\n" \ + "\t.align 4\n" \ + "2:\t" __BUG_REL(1b) "\n" \ + "\t" __BUG_REL(%c0) "\n" \ + "\t.short %1, %2\n" \ + "\t.blockz %3-2*4-2*2\n" \ "\t.popsection" \ : : "i" (__FILE__), "i" (__LINE__), \ "i" (BUGFLAG_WARNING|(flags)), \ @@ -65,10 +70,11 @@ do { \ asm volatile("\n" \ "1:\t" PARISC_BUG_BREAK_ASM "\n" \ - "\t.pushsection __bug_table,\"aw\"\n" \ - "2:\t" ASM_WORD_INSN "1b\n" \ - "\t.short %c0\n" \ - "\t.org 2b+%c1\n" \ + "\t.pushsection __bug_table,\"a\"\n" \ + "\t.align 4\n" \ + "2:\t" __BUG_REL(1b) "\n" \ + "\t.short %0\n" \ + "\t.blockz %1-4-2\n" \ "\t.popsection" \ : : "i" (BUGFLAG_WARNING|(flags)), \ "i" (sizeof(struct bug_entry)) ); \ diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h index 2a60d7a72f1fa8..a3f0f100f21949 100644 --- a/arch/parisc/include/asm/cache.h +++ b/arch/parisc/include/asm/cache.h @@ -20,7 +20,16 @@ #define SMP_CACHE_BYTES L1_CACHE_BYTES -#define ARCH_DMA_MINALIGN L1_CACHE_BYTES +#ifdef CONFIG_PA20 +#define ARCH_DMA_MINALIGN 128 +#else +#define ARCH_DMA_MINALIGN 32 +#endif +#define ARCH_KMALLOC_MINALIGN 16 /* ldcw requires 16-byte alignment */ + +#define arch_slab_minalign() ((unsigned)dcache_stride) +#define cache_line_size() dcache_stride +#define dma_get_cache_alignment cache_line_size #define __read_mostly __section(".data..read_mostly") diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index b4006f2a97052d..8394718870e1a2 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -31,17 +31,17 @@ void flush_cache_all_local(void); void flush_cache_all(void); void flush_cache_mm(struct mm_struct *mm); -void flush_kernel_dcache_page_addr(const void *addr); - #define flush_kernel_dcache_range(start,size) \ flush_kernel_dcache_range_asm((start), (start)+(size)); +/* The only way to flush a vmap range is to flush whole cache */ #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 void flush_kernel_vmap_range(void *vaddr, int size); void invalidate_kernel_vmap_range(void *vaddr, int size); -#define flush_cache_vmap(start, end) flush_cache_all() -#define flush_cache_vunmap(start, end) flush_cache_all() +void flush_cache_vmap(unsigned long start, unsigned long end); +#define flush_cache_vmap_early(start, end) do { } while (0) +void flush_cache_vunmap(unsigned long start, unsigned long end); void flush_dcache_folio(struct folio *folio); #define flush_dcache_folio flush_dcache_folio @@ -76,17 +76,11 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); -/* defined in pacache.S exported in cache.c used by flush_anon_page */ -void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); - #define ARCH_HAS_FLUSH_ANON_PAGE void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr); #define ARCH_HAS_FLUSH_ON_KUNMAP -static inline void kunmap_flush_on_unmap(const void *addr) -{ - flush_kernel_dcache_page_addr(addr); -} +void kunmap_flush_on_unmap(const void *addr); #endif /* _PARISC_CACHEFLUSH_H */ diff --git a/arch/parisc/include/asm/checksum.h b/arch/parisc/include/asm/checksum.h index 3c43baca7b397d..2aceebcd695c80 100644 --- a/arch/parisc/include/asm/checksum.h +++ b/arch/parisc/include/asm/checksum.h @@ -40,7 +40,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) " addc %0, %5, %0\n" " addc %0, %3, %0\n" "1: ldws,ma 4(%1), %3\n" -" addib,< 0, %2, 1b\n" +" addib,> -1, %2, 1b\n" " addc %0, %3, %0\n" "\n" " extru %0, 31, 16, %4\n" @@ -126,6 +126,7 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, ** Try to keep 4 registers with "live" values ahead of the ALU. */ +" depdi 0, 31, 32, %0\n"/* clear upper half of incoming checksum */ " ldd,ma 8(%1), %4\n" /* get 1st saddr word */ " ldd,ma 8(%2), %5\n" /* get 1st daddr word */ " add %4, %0, %0\n" @@ -137,8 +138,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " add,dc %3, %0, %0\n" /* fold in proto+len | carry bit */ " extrd,u %0, 31, 32, %4\n"/* copy upper half down */ " depdi 0, 31, 32, %0\n"/* clear upper half */ -" add %4, %0, %0\n" /* fold into 32-bits */ -" addc 0, %0, %0\n" /* add carry */ +" add,dc %4, %0, %0\n" /* fold into 32-bits, plus carry */ +" addc 0, %0, %0\n" /* add final carry */ #else @@ -163,7 +164,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " ldw,ma 4(%2), %7\n" /* 4th daddr */ " addc %6, %0, %0\n" " addc %7, %0, %0\n" -" addc %3, %0, %0\n" /* fold in proto+len, catch carry */ +" addc %3, %0, %0\n" /* fold in proto+len */ +" addc 0, %0, %0\n" /* add carry */ #endif : "=r" (sum), "=r" (saddr), "=r" (daddr), "=r" (len), diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h index 140eaa97bf215d..2d73d3c3cd37f8 100644 --- a/arch/parisc/include/asm/elf.h +++ b/arch/parisc/include/asm/elf.h @@ -349,15 +349,7 @@ struct pt_regs; /* forward declaration... */ #define ELF_HWCAP 0 -/* Masks for stack and mmap randomization */ -#define BRK_RND_MASK (is_32bit_task() ? 0x07ffUL : 0x3ffffUL) -#define MMAP_RND_MASK (is_32bit_task() ? 0x1fffUL : 0x3ffffUL) -#define STACK_RND_MASK MMAP_RND_MASK - -struct mm_struct; -extern unsigned long arch_randomize_brk(struct mm_struct *); -#define arch_randomize_brk arch_randomize_brk - +#define STACK_RND_MASK 0x7ff /* 8MB of VA */ #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 struct linux_binprm; diff --git a/arch/parisc/include/asm/extable.h b/arch/parisc/include/asm/extable.h new file mode 100644 index 00000000000000..4ea23e3d79dc90 --- /dev/null +++ b/arch/parisc/include/asm/extable.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PARISC_EXTABLE_H +#define __PARISC_EXTABLE_H + +#include +#include + +/* + * The exception table consists of three addresses: + * + * - A relative address to the instruction that is allowed to fault. + * - A relative address at which the program should continue (fixup routine) + * - An asm statement which specifies which CPU register will + * receive -EFAULT when an exception happens if the lowest bit in + * the fixup address is set. + * + * Note: The register specified in the err_opcode instruction will be + * modified at runtime if a fault happens. Register %r0 will be ignored. + * + * Since relative addresses are used, 32bit values are sufficient even on + * 64bit kernel. + */ + +struct pt_regs; +int fixup_exception(struct pt_regs *regs); + +#define ARCH_HAS_RELATIVE_EXTABLE +struct exception_table_entry { + int insn; /* relative address of insn that is allowed to fault. */ + int fixup; /* relative address of fixup routine */ + int err_opcode; /* sample opcode with register which holds error code */ +}; + +#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr, opcode )\ + ".section __ex_table,\"aw\"\n" \ + ".align 4\n" \ + ".word (" #fault_addr " - .), (" #except_addr " - .)\n" \ + opcode "\n" \ + ".previous\n" + +/* + * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry + * (with lowest bit set) for which the fault handler in fixup_exception() will + * load -EFAULT on fault into the register specified by the err_opcode instruction, + * and zeroes the target register in case of a read fault in get_user(). + */ +#define ASM_EXCEPTIONTABLE_VAR(__err_var) \ + int __err_var = 0 +#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr, register )\ + ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1, "or %%r0,%%r0," register) + +static inline void swap_ex_entry_fixup(struct exception_table_entry *a, + struct exception_table_entry *b, + struct exception_table_entry tmp, + int delta) +{ + a->fixup = b->fixup + delta; + b->fixup = tmp.fixup - delta; + a->err_opcode = b->err_opcode; + b->err_opcode = tmp.err_opcode; +} +#define swap_ex_entry_fixup swap_ex_entry_fixup + +#endif diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h index af2a598bc0f819..317ebc5edc9fe9 100644 --- a/arch/parisc/include/asm/jump_label.h +++ b/arch/parisc/include/asm/jump_label.h @@ -12,13 +12,15 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" + ".align %1\n\t" ".word 1b - ., %l[l_yes] - .\n\t" __stringify(ASM_ULONG_INSN) " %c0 - .\n\t" ".popsection\n\t" - : : "i" (&((char *)key)[branch]) : : l_yes); + : : "i" (&((char *)key)[branch]), "i" (sizeof(long)) + : : l_yes); return false; l_yes: @@ -27,13 +29,15 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b,n %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" + ".align %1\n\t" ".word 1b - ., %l[l_yes] - .\n\t" __stringify(ASM_ULONG_INSN) " %c0 - .\n\t" ".popsection\n\t" - : : "i" (&((char *)key)[branch]) : : l_yes); + : : "i" (&((char *)key)[branch]), "i" (sizeof(long)) + : : l_yes); return false; l_yes: diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h index ee9e071859b2f4..47ebc4c91eaff3 100644 --- a/arch/parisc/include/asm/ldcw.h +++ b/arch/parisc/include/asm/ldcw.h @@ -55,7 +55,7 @@ }) #ifdef CONFIG_SMP -# define __lock_aligned __section(".data..lock_aligned") +# define __lock_aligned __section(".data..lock_aligned") __aligned(16) #endif #endif /* __PARISC_LDCW_H */ diff --git a/arch/parisc/include/asm/mman.h b/arch/parisc/include/asm/mman.h new file mode 100644 index 00000000000000..89b6beeda0b869 --- /dev/null +++ b/arch/parisc/include/asm/mman.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MMAN_H__ +#define __ASM_MMAN_H__ + +#include + +/* PARISC cannot allow mdwe as it needs writable stacks */ +static inline bool arch_memory_deny_write_exec_supported(void) +{ + return false; +} +#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported + +static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) +{ + /* + * The stack on parisc grows upwards, so if userspace requests memory + * for a stack, mark it with VM_GROWSUP so that the stack expansion in + * the fault handler will work. + */ + if (flags & MAP_STACK) + return VM_GROWSUP; + + return 0; +} +#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags) + +#endif /* __ASM_MMAN_H__ */ diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h index 667e703c0e8f69..d6ad1812866a08 100644 --- a/arch/parisc/include/asm/page.h +++ b/arch/parisc/include/asm/page.h @@ -16,6 +16,7 @@ #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) +#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA #ifndef __ASSEMBLY__ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 974accac05cd34..babf65751e8180 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -448,14 +448,17 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) return pte; } +static inline pte_t ptep_get(pte_t *ptep) +{ + return READ_ONCE(*ptep); +} +#define ptep_get ptep_get + static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t pte; - if (!pte_young(*ptep)) - return 0; - - pte = *ptep; + pte = ptep_get(ptep); if (!pte_young(pte)) { return 0; } @@ -463,17 +466,10 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned return 1; } -struct mm_struct; -static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) -{ - pte_t old_pte; - - old_pte = *ptep; - set_pte(ptep, __pte(0)); - - return old_pte; -} +int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +struct mm_struct; static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { set_pte(ptep, pte_wrprotect(*ptep)); @@ -511,7 +507,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +#define __HAVE_ARCH_PTEP_CLEAR_FLUSH #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define __HAVE_ARCH_PTE_SAME diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index ff6cbdb6903bca..ece4b3046515c6 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -47,6 +47,8 @@ #ifndef __ASSEMBLY__ +struct rlimit; +unsigned long mmap_upper_limit(struct rlimit *rlim_stack); unsigned long calc_max_stack_size(unsigned long stack_max); /* diff --git a/arch/parisc/include/asm/signal.h b/arch/parisc/include/asm/signal.h index 715c96ba2ec81c..e84883c6b4c7a0 100644 --- a/arch/parisc/include/asm/signal.h +++ b/arch/parisc/include/asm/signal.h @@ -4,23 +4,11 @@ #include -#define _NSIG 64 -/* bits-per-word, where word apparently means 'long' not 'int' */ -#define _NSIG_BPW BITS_PER_LONG -#define _NSIG_WORDS (_NSIG / _NSIG_BPW) - # ifndef __ASSEMBLY__ /* Most things should be clean enough to redefine this at will, if care is taken to make libc match. */ -typedef unsigned long old_sigset_t; /* at least 32 bits */ - -typedef struct { - /* next_signal() assumes this is a long - no choice */ - unsigned long sig[_NSIG_WORDS]; -} sigset_t; - #include #endif /* !__ASSEMBLY */ diff --git a/arch/parisc/include/asm/special_insns.h b/arch/parisc/include/asm/special_insns.h index c822bd0c0e3c6c..51f40eaf778065 100644 --- a/arch/parisc/include/asm/special_insns.h +++ b/arch/parisc/include/asm/special_insns.h @@ -8,7 +8,8 @@ "copy %%r0,%0\n" \ "8:\tlpa %%r0(%1),%0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY(8b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY(8b, 9b, \ + "or %%r0,%%r0,%%r0") \ : "=&r" (pa) \ : "r" (va) \ : "memory" \ @@ -22,7 +23,8 @@ "copy %%r0,%0\n" \ "8:\tlpa %%r0(%%sr3,%1),%0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY(8b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY(8b, 9b, \ + "or %%r0,%%r0,%%r0") \ : "=&r" (pa) \ : "r" (va) \ : "memory" \ diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 2bf660eabe421e..88d0ae5769dde5 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -7,6 +7,7 @@ */ #include #include +#include #include #include @@ -26,36 +27,6 @@ #define STD_USER(sr, x, ptr) __put_user_asm(sr, "std", x, ptr) #endif -/* - * The exception table contains two values: the first is the relative offset to - * the address of the instruction that is allowed to fault, and the second is - * the relative offset to the address of the fixup routine. Since relative - * addresses are used, 32bit values are sufficient even on 64bit kernel. - */ - -#define ARCH_HAS_RELATIVE_EXTABLE -struct exception_table_entry { - int insn; /* relative address of insn that is allowed to fault. */ - int fixup; /* relative address of fixup routine */ -}; - -#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\ - ".section __ex_table,\"aw\"\n" \ - ".word (" #fault_addr " - .), (" #except_addr " - .)\n\t" \ - ".previous\n" - -/* - * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry - * (with lowest bit set) for which the fault handler in fixup_exception() will - * load -EFAULT into %r29 for a read or write fault, and zeroes the target - * register in case of a read fault in get_user(). - */ -#define ASM_EXCEPTIONTABLE_REG 29 -#define ASM_EXCEPTIONTABLE_VAR(__variable) \ - register long __variable __asm__ ("r29") = 0 -#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr )\ - ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1) - #define __get_user_internal(sr, val, ptr) \ ({ \ ASM_EXCEPTIONTABLE_VAR(__gu_err); \ @@ -82,7 +53,7 @@ struct exception_table_entry { \ __asm__("1: " ldx " 0(%%sr%2,%3),%0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1") \ : "=r"(__gu_val), "+r"(__gu_err) \ : "i"(sr), "r"(ptr)); \ \ @@ -114,8 +85,8 @@ struct exception_table_entry { "1: ldw 0(%%sr%2,%3),%0\n" \ "2: ldw 4(%%sr%2,%3),%R0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1") \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%1") \ : "=&r"(__gu_tmp.l), "+r"(__gu_err) \ : "i"(sr), "r"(ptr)); \ \ @@ -173,7 +144,7 @@ struct exception_table_entry { __asm__ __volatile__ ( \ "1: " stx " %1,0(%%sr%2,%3)\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0") \ : "+r"(__pu_err) \ : "r"(x), "i"(sr), "r"(ptr)) @@ -185,15 +156,14 @@ struct exception_table_entry { "1: stw %1,0(%%sr%2,%3)\n" \ "2: stw %R1,4(%%sr%2,%3)\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0") \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%0") \ : "+r"(__pu_err) \ : "r"(__val), "i"(sr), "r"(ptr)); \ } while (0) #endif /* !defined(CONFIG_64BIT) */ - /* * Complex access routines -- external declarations */ @@ -215,7 +185,4 @@ unsigned long __must_check raw_copy_from_user(void *dst, const void __user *src, #define INLINE_COPY_TO_USER #define INLINE_COPY_FROM_USER -struct pt_regs; -int fixup_exception(struct pt_regs *regs); - #endif /* __PARISC_UACCESS_H */ diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h index 87245c584784ec..8d94739d75c67c 100644 --- a/arch/parisc/include/uapi/asm/errno.h +++ b/arch/parisc/include/uapi/asm/errno.h @@ -75,7 +75,6 @@ /* We now return you to your regularly scheduled HPUX. */ -#define ENOSYM 215 /* symbol does not exist in executable */ #define ENOTSOCK 216 /* Socket operation on non-socket */ #define EDESTADDRREQ 217 /* Destination address required */ #define EMSGSIZE 218 /* Message too long */ @@ -101,7 +100,6 @@ #define ETIMEDOUT 238 /* Connection timed out */ #define ECONNREFUSED 239 /* Connection refused */ #define EREFUSED ECONNREFUSED /* for HP's NFS apparently */ -#define EREMOTERELEASE 240 /* Remote peer released connection */ #define EHOSTDOWN 241 /* Host is down */ #define EHOSTUNREACH 242 /* No route to host */ diff --git a/arch/parisc/include/uapi/asm/pdc.h b/arch/parisc/include/uapi/asm/pdc.h index 7a90070136e823..8e38a86996fc60 100644 --- a/arch/parisc/include/uapi/asm/pdc.h +++ b/arch/parisc/include/uapi/asm/pdc.h @@ -472,6 +472,7 @@ struct pdc_model { /* for PDC_MODEL */ unsigned long arch_rev; unsigned long pot_key; unsigned long curr_key; + unsigned long width; /* default of PSW_W bit (1=enabled) */ }; struct pdc_cache_cf { /* for PDC_CACHE (I/D-caches) */ diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h index 8e4895c5ea5d37..40d7a574c5dd19 100644 --- a/arch/parisc/include/uapi/asm/signal.h +++ b/arch/parisc/include/uapi/asm/signal.h @@ -57,10 +57,20 @@ #include +#define _NSIG 64 +#define _NSIG_BPW (sizeof(unsigned long) * 8) +#define _NSIG_WORDS (_NSIG / _NSIG_BPW) + # ifndef __ASSEMBLY__ # include +typedef unsigned long old_sigset_t; /* at least 32 bits */ + +typedef struct { + unsigned long sig[_NSIG_WORDS]; +} sigset_t; + /* Avoid too many header ordering problems. */ struct siginfo; diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 268d90a9325b46..f7953b0391cf60 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -31,20 +32,31 @@ #include #include +#define PTR_PAGE_ALIGN_DOWN(addr) PTR_ALIGN_DOWN(addr, PAGE_SIZE) + +/* + * When nonzero, use _PAGE_ACCESSED bit to try to reduce the number + * of page flushes done flush_cache_page_if_present. There are some + * pros and cons in using this option. It may increase the risk of + * random segmentation faults. + */ +#define CONFIG_FLUSH_PAGE_ACCESSED 0 + int split_tlb __ro_after_init; int dcache_stride __ro_after_init; int icache_stride __ro_after_init; EXPORT_SYMBOL(dcache_stride); +/* Internal implementation in arch/parisc/kernel/pacache.S */ void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); EXPORT_SYMBOL(flush_dcache_page_asm); void purge_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); void flush_icache_page_asm(unsigned long phys_addr, unsigned long vaddr); - -/* Internal implementation in arch/parisc/kernel/pacache.S */ void flush_data_cache_local(void *); /* flushes local data-cache only */ void flush_instruction_cache_local(void); /* flushes local code-cache only */ +static void flush_kernel_dcache_page_addr(const void *addr); + /* On some machines (i.e., ones with the Merced bus), there can be * only a single PxTLB broadcast at a time; this must be guaranteed * by software. We need a spinlock around all TLB flushes to ensure @@ -58,7 +70,7 @@ int pa_serialize_tlb_flushes __ro_after_init; struct pdc_cache_info cache_info __ro_after_init; #ifndef CONFIG_PA20 -struct pdc_btlb_info btlb_info __ro_after_init; +struct pdc_btlb_info btlb_info; #endif DEFINE_STATIC_KEY_TRUE(parisc_has_cache); @@ -317,6 +329,18 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, { if (!static_branch_likely(&parisc_has_cache)) return; + + /* + * The TLB is the engine of coherence on parisc. The CPU is + * entitled to speculate any page with a TLB mapping, so here + * we kill the mapping then flush the page along a special flush + * only alias mapping. This guarantees that the page is no-longer + * in the cache for any process and nor may it be speculatively + * read in (until the user or kernel specifically accesses it, + * of course). + */ + flush_tlb_page(vma, vmaddr); + preempt_disable(); flush_dcache_page_asm(physaddr, vmaddr); if (vma->vm_flags & VM_EXEC) @@ -324,46 +348,44 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, preempt_enable(); } -static void flush_user_cache_page(struct vm_area_struct *vma, unsigned long vmaddr) +static void flush_kernel_dcache_page_addr(const void *addr) { - unsigned long flags, space, pgd, prot; -#ifdef CONFIG_TLB_PTLOCK - unsigned long pgd_lock; -#endif + unsigned long vaddr = (unsigned long)addr; + unsigned long flags; - vmaddr &= PAGE_MASK; + /* Purge TLB entry to remove translation on all CPUs */ + purge_tlb_start(flags); + pdtlb(SR_KERNEL, addr); + purge_tlb_end(flags); + /* Use tmpalias flush to prevent data cache move-in */ preempt_disable(); + flush_dcache_page_asm(__pa(vaddr), vaddr); + preempt_enable(); +} - /* Set context for flush */ - local_irq_save(flags); - prot = mfctl(8); - space = mfsp(SR_USER); - pgd = mfctl(25); -#ifdef CONFIG_TLB_PTLOCK - pgd_lock = mfctl(28); -#endif - switch_mm_irqs_off(NULL, vma->vm_mm, NULL); - local_irq_restore(flags); - - flush_user_dcache_range_asm(vmaddr, vmaddr + PAGE_SIZE); - if (vma->vm_flags & VM_EXEC) - flush_user_icache_range_asm(vmaddr, vmaddr + PAGE_SIZE); - flush_tlb_page(vma, vmaddr); +static void flush_kernel_icache_page_addr(const void *addr) +{ + unsigned long vaddr = (unsigned long)addr; + unsigned long flags; - /* Restore previous context */ - local_irq_save(flags); -#ifdef CONFIG_TLB_PTLOCK - mtctl(pgd_lock, 28); -#endif - mtctl(pgd, 25); - mtsp(space, SR_USER); - mtctl(prot, 8); - local_irq_restore(flags); + /* Purge TLB entry to remove translation on all CPUs */ + purge_tlb_start(flags); + pdtlb(SR_KERNEL, addr); + purge_tlb_end(flags); + /* Use tmpalias flush to prevent instruction cache move-in */ + preempt_disable(); + flush_icache_page_asm(__pa(vaddr), vaddr); preempt_enable(); } +void kunmap_flush_on_unmap(const void *addr) +{ + flush_kernel_dcache_page_addr(addr); +} +EXPORT_SYMBOL(kunmap_flush_on_unmap); + void flush_icache_pages(struct vm_area_struct *vma, struct page *page, unsigned int nr) { @@ -371,13 +393,16 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page, for (;;) { flush_kernel_dcache_page_addr(kaddr); - flush_kernel_icache_page(kaddr); + flush_kernel_icache_page_addr(kaddr); if (--nr == 0) break; kaddr += PAGE_SIZE; } } +/* + * Walk page directory for MM to find PTEP pointer for address ADDR. + */ static inline pte_t *get_ptep(struct mm_struct *mm, unsigned long addr) { pte_t *ptep = NULL; @@ -406,6 +431,41 @@ static inline bool pte_needs_flush(pte_t pte) == (_PAGE_PRESENT | _PAGE_ACCESSED); } +/* + * Return user physical address. Returns 0 if page is not present. + */ +static inline unsigned long get_upa(struct mm_struct *mm, unsigned long addr) +{ + unsigned long flags, space, pgd, prot, pa; +#ifdef CONFIG_TLB_PTLOCK + unsigned long pgd_lock; +#endif + + /* Save context */ + local_irq_save(flags); + prot = mfctl(8); + space = mfsp(SR_USER); + pgd = mfctl(25); +#ifdef CONFIG_TLB_PTLOCK + pgd_lock = mfctl(28); +#endif + + /* Set context for lpa_user */ + switch_mm_irqs_off(NULL, mm, NULL); + pa = lpa_user(addr); + + /* Restore previous context */ +#ifdef CONFIG_TLB_PTLOCK + mtctl(pgd_lock, 28); +#endif + mtctl(pgd, 25); + mtsp(space, SR_USER); + mtctl(prot, 8); + local_irq_restore(flags); + + return pa; +} + void flush_dcache_folio(struct folio *folio) { struct address_space *mapping = folio_flush_mapping(folio); @@ -454,50 +514,23 @@ void flush_dcache_folio(struct folio *folio) if (addr + nr * PAGE_SIZE > vma->vm_end) nr = (vma->vm_end - addr) / PAGE_SIZE; - if (parisc_requires_coherency()) { - for (i = 0; i < nr; i++) { - pte_t *ptep = get_ptep(vma->vm_mm, - addr + i * PAGE_SIZE); - if (!ptep) - continue; - if (pte_needs_flush(*ptep)) - flush_user_cache_page(vma, - addr + i * PAGE_SIZE); - /* Optimise accesses to the same table? */ - pte_unmap(ptep); - } - } else { + if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) + != (addr & (SHM_COLOUR - 1))) { + for (i = 0; i < nr; i++) + __flush_cache_page(vma, + addr + i * PAGE_SIZE, + (pfn + i) * PAGE_SIZE); /* - * The TLB is the engine of coherence on parisc: - * The CPU is entitled to speculate any page - * with a TLB mapping, so here we kill the - * mapping then flush the page along a special - * flush only alias mapping. This guarantees that - * the page is no-longer in the cache for any - * process and nor may it be speculatively read - * in (until the user or kernel specifically - * accesses it, of course) + * Software is allowed to have any number + * of private mappings to a page. */ - for (i = 0; i < nr; i++) - flush_tlb_page(vma, addr + i * PAGE_SIZE); - if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) - != (addr & (SHM_COLOUR - 1))) { - for (i = 0; i < nr; i++) - __flush_cache_page(vma, - addr + i * PAGE_SIZE, - (pfn + i) * PAGE_SIZE); - /* - * Software is allowed to have any number - * of private mappings to a page. - */ - if (!(vma->vm_flags & VM_SHARED)) - continue; - if (old_addr) - pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", - old_addr, addr, vma->vm_file); - if (nr == folio_nr_pages(folio)) - old_addr = addr; - } + if (!(vma->vm_flags & VM_SHARED)) + continue; + if (old_addr) + pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", + old_addr, addr, vma->vm_file); + if (nr == folio_nr_pages(folio)) + old_addr = addr; } WARN_ON(++count == 4096); } @@ -587,35 +620,28 @@ extern void purge_kernel_dcache_page_asm(unsigned long); extern void clear_user_page_asm(void *, unsigned long); extern void copy_user_page_asm(void *, void *, unsigned long); -void flush_kernel_dcache_page_addr(const void *addr) -{ - unsigned long flags; - - flush_kernel_dcache_page_asm(addr); - purge_tlb_start(flags); - pdtlb(SR_KERNEL, addr); - purge_tlb_end(flags); -} -EXPORT_SYMBOL(flush_kernel_dcache_page_addr); - static void flush_cache_page_if_present(struct vm_area_struct *vma, - unsigned long vmaddr, unsigned long pfn) + unsigned long vmaddr) { +#if CONFIG_FLUSH_PAGE_ACCESSED bool needs_flush = false; - pte_t *ptep; + pte_t *ptep, pte; - /* - * The pte check is racy and sometimes the flush will trigger - * a non-access TLB miss. Hopefully, the page has already been - * flushed. - */ ptep = get_ptep(vma->vm_mm, vmaddr); if (ptep) { - needs_flush = pte_needs_flush(*ptep); + pte = ptep_get(ptep); + needs_flush = pte_needs_flush(pte); pte_unmap(ptep); } if (needs_flush) - flush_cache_page(vma, vmaddr, pfn); + __flush_cache_page(vma, vmaddr, PFN_PHYS(pte_pfn(pte))); +#else + struct mm_struct *mm = vma->vm_mm; + unsigned long physaddr = get_upa(mm, vmaddr); + + if (physaddr) + __flush_cache_page(vma, vmaddr, PAGE_ALIGN_DOWN(physaddr)); +#endif } void copy_user_highpage(struct page *to, struct page *from, @@ -625,7 +651,7 @@ void copy_user_highpage(struct page *to, struct page *from, kfrom = kmap_local_page(from); kto = kmap_local_page(to); - flush_cache_page_if_present(vma, vaddr, page_to_pfn(from)); + __flush_cache_page(vma, vaddr, PFN_PHYS(page_to_pfn(from))); copy_page_asm(kto, kfrom); kunmap_local(kto); kunmap_local(kfrom); @@ -634,16 +660,17 @@ void copy_user_highpage(struct page *to, struct page *from, void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long user_vaddr, void *dst, void *src, int len) { - flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + __flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page))); memcpy(dst, src, len); - flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); + flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(dst)); } void copy_from_user_page(struct vm_area_struct *vma, struct page *page, unsigned long user_vaddr, void *dst, void *src, int len) { - flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + __flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page))); memcpy(dst, src, len); + flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(src)); } /* __flush_tlb_range() @@ -677,32 +704,10 @@ int __flush_tlb_range(unsigned long sid, unsigned long start, static void flush_cache_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - unsigned long addr, pfn; - pte_t *ptep; - - for (addr = start; addr < end; addr += PAGE_SIZE) { - bool needs_flush = false; - /* - * The vma can contain pages that aren't present. Although - * the pte search is expensive, we need the pte to find the - * page pfn and to check whether the page should be flushed. - */ - ptep = get_ptep(vma->vm_mm, addr); - if (ptep) { - needs_flush = pte_needs_flush(*ptep); - pfn = pte_pfn(*ptep); - pte_unmap(ptep); - } - if (needs_flush) { - if (parisc_requires_coherency()) { - flush_user_cache_page(vma, addr); - } else { - if (WARN_ON(!pfn_valid(pfn))) - return; - __flush_cache_page(vma, addr, PFN_PHYS(pfn)); - } - } - } + unsigned long addr; + + for (addr = start; addr < end; addr += PAGE_SIZE) + flush_cache_page_if_present(vma, addr); } static inline unsigned long mm_total_size(struct mm_struct *mm) @@ -753,21 +758,19 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) return; flush_tlb_range(vma, start, end); - flush_cache_all(); + if (vma->vm_flags & VM_EXEC) + flush_cache_all(); + else + flush_data_cache(); return; } - flush_cache_pages(vma, start, end); + flush_cache_pages(vma, start & PAGE_MASK, end); } void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { - if (WARN_ON(!pfn_valid(pfn))) - return; - if (parisc_requires_coherency()) - flush_user_cache_page(vma, vmaddr); - else - __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); + __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); } void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) @@ -775,34 +778,133 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned lon if (!PageAnon(page)) return; - if (parisc_requires_coherency()) { - if (vma->vm_flags & VM_SHARED) - flush_data_cache(); - else - flush_user_cache_page(vma, vmaddr); + __flush_cache_page(vma, vmaddr, PFN_PHYS(page_to_pfn(page))); +} + +int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + pte_t pte = ptep_get(ptep); + + if (!pte_young(pte)) + return 0; + set_pte(ptep, pte_mkold(pte)); +#if CONFIG_FLUSH_PAGE_ACCESSED + __flush_cache_page(vma, addr, PFN_PHYS(pte_pfn(pte))); +#endif + return 1; +} + +/* + * After a PTE is cleared, we have no way to flush the cache for + * the physical page. On PA8800 and PA8900 processors, these lines + * can cause random cache corruption. Thus, we must flush the cache + * as well as the TLB when clearing a PTE that's valid. + */ +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + struct mm_struct *mm = (vma)->vm_mm; + pte_t pte = ptep_get_and_clear(mm, addr, ptep); + unsigned long pfn = pte_pfn(pte); + + if (pfn_valid(pfn)) + __flush_cache_page(vma, addr, PFN_PHYS(pfn)); + else if (pte_accessible(mm, pte)) + flush_tlb_page(vma, addr); + + return pte; +} + +/* + * The physical address for pages in the ioremap case can be obtained + * from the vm_struct struct. I wasn't able to successfully handle the + * vmalloc and vmap cases. We have an array of struct page pointers in + * the uninitialized vmalloc case but the flush failed using page_to_pfn. + */ +void flush_cache_vmap(unsigned long start, unsigned long end) +{ + unsigned long addr, physaddr; + struct vm_struct *vm; + + /* Prevent cache move-in */ + flush_tlb_kernel_range(start, end); + + if (end - start >= parisc_cache_flush_threshold) { + flush_cache_all(); return; } - flush_tlb_page(vma, vmaddr); - preempt_disable(); - flush_dcache_page_asm(page_to_phys(page), vmaddr); - preempt_enable(); + if (WARN_ON_ONCE(!is_vmalloc_addr((void *)start))) { + flush_cache_all(); + return; + } + + vm = find_vm_area((void *)start); + if (WARN_ON_ONCE(!vm)) { + flush_cache_all(); + return; + } + + /* The physical addresses of IOREMAP regions are contiguous */ + if (vm->flags & VM_IOREMAP) { + physaddr = vm->phys_addr; + for (addr = start; addr < end; addr += PAGE_SIZE) { + preempt_disable(); + flush_dcache_page_asm(physaddr, start); + flush_icache_page_asm(physaddr, start); + preempt_enable(); + physaddr += PAGE_SIZE; + } + return; + } + + flush_cache_all(); } +EXPORT_SYMBOL(flush_cache_vmap); +/* + * The vm_struct has been retired and the page table is set up. The + * last page in the range is a guard page. Its physical address can't + * be determined using lpa, so there is no way to flush the range + * using flush_dcache_page_asm. + */ +void flush_cache_vunmap(unsigned long start, unsigned long end) +{ + /* Prevent cache move-in */ + flush_tlb_kernel_range(start, end); + flush_data_cache(); +} +EXPORT_SYMBOL(flush_cache_vunmap); + +/* + * On systems with PA8800/PA8900 processors, there is no way to flush + * a vmap range other than using the architected loop to flush the + * entire cache. The page directory is not set up, so we can't use + * fdc, etc. FDCE/FICE don't work to flush a portion of the cache. + * L2 is physically indexed but FDCE/FICE instructions in virtual + * mode output their virtual address on the core bus, not their + * real address. As a result, the L2 cache index formed from the + * virtual address will most likely not be the same as the L2 index + * formed from the real address. + */ void flush_kernel_vmap_range(void *vaddr, int size) { unsigned long start = (unsigned long)vaddr; unsigned long end = start + size; - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - (unsigned long)size >= parisc_cache_flush_threshold) { - flush_tlb_kernel_range(start, end); - flush_data_cache(); + flush_tlb_kernel_range(start, end); + + if (!static_branch_likely(&parisc_has_dcache)) + return; + + /* If interrupts are disabled, we can only do local flush */ + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) { + flush_data_cache_local(NULL); return; } - flush_kernel_dcache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_data_cache(); } EXPORT_SYMBOL(flush_kernel_vmap_range); @@ -814,15 +916,18 @@ void invalidate_kernel_vmap_range(void *vaddr, int size) /* Ensure DMA is complete */ asm_syncdma(); - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - (unsigned long)size >= parisc_cache_flush_threshold) { - flush_tlb_kernel_range(start, end); - flush_data_cache(); + flush_tlb_kernel_range(start, end); + + if (!static_branch_likely(&parisc_has_dcache)) + return; + + /* If interrupts are disabled, we can only do local flush */ + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) { + flush_data_cache_local(NULL); return; } - purge_kernel_dcache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_data_cache(); } EXPORT_SYMBOL(invalidate_kernel_vmap_range); @@ -850,7 +955,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes, #endif " fic,m %3(%4,%0)\n" "2: sync\n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1") : "+r" (start), "+r" (error) : "r" (end), "r" (dcache_stride), "i" (SR_USER)); } @@ -865,7 +970,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes, #endif " fdc,m %3(%4,%0)\n" "2: sync\n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1") : "+r" (start), "+r" (error) : "r" (end), "r" (icache_stride), "i" (SR_USER)); } diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index ed8b759480614b..8be4558ef33c0e 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -1004,6 +1004,9 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data) pr_info("\n"); + /* Prevent hung task messages when printing on serial console */ + cond_resched(); + pr_info("#define HPA_%08lx_DESCRIPTION \"%s\"\n", hpa, parisc_hardware_description(&dev->id)); diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index ae03b8679696e7..ea57bcc21dc5fe 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -36,6 +36,24 @@ .level 2.0 #endif +/* + * We need seven instructions after a TLB insert for it to take effect. + * The PA8800/PA8900 processors are an exception and need 12 instructions. + * The RFI changes both IAOQ_Back and IAOQ_Front, so it counts as one. + */ +#ifdef CONFIG_64BIT +#define NUM_PIPELINE_INSNS 12 +#else +#define NUM_PIPELINE_INSNS 7 +#endif + + /* Insert num nops */ + .macro insert_nops num + .rept \num + nop + .endr + .endm + /* Get aligned page_table_lock address for this mm from cr28/tr4 */ .macro get_ptl reg mfctl %cr28,\reg @@ -415,24 +433,20 @@ 3: .endm - /* Release page_table_lock without reloading lock address. - We use an ordered store to ensure all prior accesses are - performed prior to releasing the lock. */ - .macro ptl_unlock0 spc,tmp,tmp2 + /* Release page_table_lock if for user space. We use an ordered + store to ensure all prior accesses are performed prior to + releasing the lock. Note stw may not be executed, so we + provide one extra nop when CONFIG_TLB_PTLOCK is defined. */ + .macro ptl_unlock spc,tmp,tmp2 #ifdef CONFIG_TLB_PTLOCK -98: ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, \tmp2 +98: get_ptl \tmp + ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, \tmp2 or,COND(=) %r0,\spc,%r0 stw,ma \tmp2,0(\tmp) 99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP) -#endif - .endm - - /* Release page_table_lock. */ - .macro ptl_unlock1 spc,tmp,tmp2 -#ifdef CONFIG_TLB_PTLOCK -98: get_ptl \tmp - ptl_unlock0 \spc,\tmp,\tmp2 -99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP) + insert_nops NUM_PIPELINE_INSNS - 4 +#else + insert_nops NUM_PIPELINE_INSNS - 1 #endif .endm @@ -461,13 +475,13 @@ * to a CPU TLB 4k PFN (4k => 12 bits to shift) */ #define PAGE_ADD_SHIFT (PAGE_SHIFT-12) #define PAGE_ADD_HUGE_SHIFT (REAL_HPAGE_SHIFT-12) + #define PFN_START_BIT (63-ASM_PFN_PTE_SHIFT+(63-58)-PAGE_ADD_SHIFT) /* Drop prot bits and convert to page addr for iitlbt and idtlbt */ .macro convert_for_tlb_insert20 pte,tmp #ifdef CONFIG_HUGETLB_PAGE copy \pte,\tmp - extrd,u \tmp,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\ - 64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte + extrd,u \tmp,PFN_START_BIT,PFN_START_BIT+1,\pte depdi _PAGE_SIZE_ENCODING_DEFAULT,63,\ (63-58)+PAGE_ADD_SHIFT,\pte @@ -475,8 +489,7 @@ depdi _HUGE_PAGE_SIZE_ENCODING_DEFAULT,63,\ (63-58)+PAGE_ADD_HUGE_SHIFT,\pte #else /* Huge pages disabled */ - extrd,u \pte,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\ - 64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte + extrd,u \pte,PFN_START_BIT,PFN_START_BIT+1,\pte depdi _PAGE_SIZE_ENCODING_DEFAULT,63,\ (63-58)+PAGE_ADD_SHIFT,\pte #endif @@ -1038,8 +1051,7 @@ ENTRY_CFI(intr_save) /* for os_hpmc */ STREG %r16, PT_ISR(%r29) STREG %r17, PT_IOR(%r29) -#if 0 && defined(CONFIG_64BIT) - /* Revisit when we have 64-bit code above 4Gb */ +#if defined(CONFIG_64BIT) b,n intr_save2 skip_save_ior: @@ -1047,8 +1059,7 @@ skip_save_ior: * need to adjust iasq/iaoq here in the same way we adjusted isr/ior * above. */ - extrd,u,* %r8,PSW_W_BIT,1,%r1 - cmpib,COND(=),n 1,%r1,intr_save2 + bb,COND(>=),n %r8,PSW_W_BIT,intr_save2 LDREG PT_IASQ0(%r29), %r16 LDREG PT_IAOQ0(%r29), %r17 /* adjust iasq/iaoq */ @@ -1124,7 +1135,7 @@ dtlb_miss_20w: idtlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1133,6 +1144,7 @@ dtlb_check_alias_20w: idtlbt pte,prot + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1150,7 +1162,7 @@ nadtlb_miss_20w: idtlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1159,6 +1171,7 @@ nadtlb_check_alias_20w: idtlbt pte,prot + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1184,7 +1197,7 @@ dtlb_miss_11: mtsp t1, %sr1 /* Restore sr1 */ - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1194,6 +1207,7 @@ dtlb_check_alias_11: idtlba pte,(va) idtlbp prot,(va) + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1217,7 +1231,7 @@ nadtlb_miss_11: mtsp t1, %sr1 /* Restore sr1 */ - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1227,6 +1241,7 @@ nadtlb_check_alias_11: idtlba pte,(va) idtlbp prot,(va) + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1246,7 +1261,7 @@ dtlb_miss_20: idtlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1255,6 +1270,7 @@ dtlb_check_alias_20: idtlbt pte,prot + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1274,7 +1290,7 @@ nadtlb_miss_20: idtlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1283,6 +1299,7 @@ nadtlb_check_alias_20: idtlbt pte,prot + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1319,7 +1336,7 @@ itlb_miss_20w: iitlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1343,7 +1360,7 @@ naitlb_miss_20w: iitlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1352,6 +1369,7 @@ naitlb_check_alias_20w: iitlbt pte,prot + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1377,7 +1395,7 @@ itlb_miss_11: mtsp t1, %sr1 /* Restore sr1 */ - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1401,7 +1419,7 @@ naitlb_miss_11: mtsp t1, %sr1 /* Restore sr1 */ - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1411,6 +1429,7 @@ naitlb_check_alias_11: iitlba pte,(%sr0, va) iitlbp prot,(%sr0, va) + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1431,7 +1450,7 @@ itlb_miss_20: iitlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1451,7 +1470,7 @@ naitlb_miss_20: iitlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1460,6 +1479,7 @@ naitlb_check_alias_20: iitlbt pte,prot + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1481,7 +1501,7 @@ dbit_trap_20w: idtlbt pte,prot - ptl_unlock0 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop #else @@ -1507,7 +1527,7 @@ dbit_trap_11: mtsp t1, %sr1 /* Restore sr1 */ - ptl_unlock0 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1527,7 +1547,7 @@ dbit_trap_20: idtlbt pte,prot - ptl_unlock0 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop #endif diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 81078abec521a7..56e694f6acc2d7 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -123,10 +123,10 @@ static unsigned long f_extend(unsigned long address) #ifdef CONFIG_64BIT if(unlikely(parisc_narrow_firmware)) { if((address & 0xff000000) == 0xf0000000) - return 0xf0f0f0f000000000UL | (u32)address; + return (0xfffffff0UL << 32) | (u32)address; if((address & 0xf0000000) == 0xf0000000) - return 0xffffffff00000000UL | (u32)address; + return (0xffffffffUL << 32) | (u32)address; } #endif return address; diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index d1defb9ede70c0..c91f9c2e61ed25 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -78,7 +78,7 @@ asmlinkage void notrace __hot ftrace_function_trampoline(unsigned long parent, #endif } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_FUNCTION_GRAPH_TRACER) int ftrace_enable_ftrace_graph_caller(void) { static_key_enable(&ftrace_graph_enable.key); @@ -206,6 +206,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe *p; int bit; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index a171bf3c6b318d..96e0264ac96163 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -70,9 +70,8 @@ $bss_loop: stw,ma %arg2,4(%r1) stw,ma %arg3,4(%r1) -#if !defined(CONFIG_64BIT) && defined(CONFIG_PA20) - /* This 32-bit kernel was compiled for PA2.0 CPUs. Check current CPU - * and halt kernel if we detect a PA1.x CPU. */ +#if defined(CONFIG_PA20) + /* check for 64-bit capable CPU as required by current kernel */ ldi 32,%r10 mtctl %r10,%cr11 .level 2.0 diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index 2f81bfd4f15e17..dff66be65d2900 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -498,7 +498,7 @@ asmlinkage void do_cpu_irq_mask(struct pt_regs *regs) old_regs = set_irq_regs(regs); local_irq_disable(); - irq_enter(); + irq_enter_rcu(); eirr_val = mfctl(23) & cpu_eiem & per_cpu(local_ack_eiem, cpu); if (!eirr_val) @@ -533,7 +533,7 @@ asmlinkage void do_cpu_irq_mask(struct pt_regs *regs) #endif /* CONFIG_IRQSTACKS */ out: - irq_exit(); + irq_exit_rcu(); set_irq_regs(old_regs); return; diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 6f0c92e8149d82..dcf61cbd314708 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -22,6 +22,7 @@ EXPORT_SYMBOL(memset); #include EXPORT_SYMBOL(__xchg8); EXPORT_SYMBOL(__xchg32); +EXPORT_SYMBOL(__cmpxchg_u8); EXPORT_SYMBOL(__cmpxchg_u32); EXPORT_SYMBOL(__cmpxchg_u64); #ifdef CONFIG_SMP diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 1fc89fa2c2d214..e37c48770b5854 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -172,7 +172,6 @@ static int __init processor_probe(struct parisc_device *dev) p->cpu_num = cpu_info.cpu_num; p->cpu_loc = cpu_info.cpu_loc; - set_cpu_possible(cpuid, true); store_cpu_topology(cpuid); #ifdef CONFIG_SMP @@ -474,13 +473,6 @@ static struct parisc_driver cpu_driver __refdata = { */ void __init processor_init(void) { - unsigned int cpu; - reset_cpu_topology(); - - /* reset possible mask. We will mark those which are possible. */ - for_each_possible_cpu(cpu) - set_cpu_possible(cpu, false); - register_parisc_driver(&cpu_driver); } diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index ab896eff7a1de9..98af719d5f85b2 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -77,7 +77,7 @@ unsigned long calc_max_stack_size(unsigned long stack_max) * indicating that "current" should be used instead of a passed-in * value from the exec bprm as done with arch_pick_mmap_layout(). */ -static unsigned long mmap_upper_limit(struct rlimit *rlim_stack) +unsigned long mmap_upper_limit(struct rlimit *rlim_stack) { unsigned long stack_base; diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index 2a12a547b447bd..826c8e51b5853b 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -23,12 +23,3 @@ asmlinkage long sys32_unimplemented(int r26, int r25, int r24, int r23, current->comm, current->pid, r20); return -ENOSYS; } - -asmlinkage long sys32_fanotify_mark(compat_int_t fanotify_fd, compat_uint_t flags, - compat_uint_t mask0, compat_uint_t mask1, compat_int_t dfd, - const char __user * pathname) -{ - return sys_fanotify_mark(fanotify_fd, flags, - ((__u64)mask1 << 32) | mask0, - dfd, pathname); -} diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 1f51aa9c8230cc..0fa81bf1466b15 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -243,10 +243,10 @@ linux_gateway_entry: #ifdef CONFIG_64BIT ldil L%sys_call_table, %r1 - or,= %r2,%r2,%r2 - addil L%(sys_call_table64-sys_call_table), %r1 + or,ev %r2,%r2,%r2 + ldil L%sys_call_table64, %r1 ldo R%sys_call_table(%r1), %r19 - or,= %r2,%r2,%r2 + or,ev %r2,%r2,%r2 ldo R%sys_call_table64(%r1), %r19 #else load32 sys_call_table, %r19 @@ -379,10 +379,10 @@ tracesys_next: extrd,u %r19,63,1,%r2 /* W hidden in bottom bit */ ldil L%sys_call_table, %r1 - or,= %r2,%r2,%r2 - addil L%(sys_call_table64-sys_call_table), %r1 + or,ev %r2,%r2,%r2 + ldil L%sys_call_table64, %r1 ldo R%sys_call_table(%r1), %r19 - or,= %r2,%r2,%r2 + or,ev %r2,%r2,%r2 ldo R%sys_call_table64(%r1), %r19 #else load32 sys_call_table, %r19 @@ -1327,6 +1327,8 @@ ENTRY(sys_call_table) END(sys_call_table) #ifdef CONFIG_64BIT +#undef __SYSCALL_WITH_COMPAT +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) .align 8 ENTRY(sys_call_table64) #include /* 64-bit syscalls */ diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index e97c175b56f965..73f560e309573a 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -108,7 +108,7 @@ 95 common fchown sys_fchown 96 common getpriority sys_getpriority 97 common setpriority sys_setpriority -98 common recv sys_recv +98 common recv sys_recv compat_sys_recv 99 common statfs sys_statfs compat_sys_statfs 100 common fstatfs sys_fstatfs compat_sys_fstatfs 101 common stat64 sys_stat64 @@ -135,7 +135,7 @@ 120 common clone sys_clone_wrapper 121 common setdomainname sys_setdomainname 122 common sendfile sys_sendfile compat_sys_sendfile -123 common recvfrom sys_recvfrom +123 common recvfrom sys_recvfrom compat_sys_recvfrom 124 32 adjtimex sys_adjtimex_time32 124 64 adjtimex sys_adjtimex 125 common mprotect sys_mprotect @@ -364,7 +364,7 @@ 320 common accept4 sys_accept4 321 common prlimit64 sys_prlimit64 322 common fanotify_init sys_fanotify_init -323 common fanotify_mark sys_fanotify_mark sys32_fanotify_mark +323 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark 324 32 clock_adjtime sys_clock_adjtime32 324 64 clock_adjtime sys_clock_adjtime 325 common name_to_handle_at sys_name_to_handle_at diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index ce25acfe4889d0..a8e75e5b884a70 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -120,8 +120,8 @@ static int emulate_ldh(struct pt_regs *regs, int toreg) "2: ldbs 1(%%sr1,%3), %0\n" " depw %2, 23, 24, %0\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1") : "+r" (val), "+r" (ret), "=&r" (temp1) : "r" (saddr), "r" (regs->isr) ); @@ -152,8 +152,8 @@ static int emulate_ldw(struct pt_regs *regs, int toreg, int flop) " mtctl %2,11\n" " vshd %0,%3,%0\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1") : "+r" (val), "+r" (ret), "=&r" (temp1), "=&r" (temp2) : "r" (saddr), "r" (regs->isr) ); @@ -169,6 +169,7 @@ static int emulate_ldw(struct pt_regs *regs, int toreg, int flop) static int emulate_ldd(struct pt_regs *regs, int toreg, int flop) { unsigned long saddr = regs->ior; + unsigned long shift, temp1; __u64 val = 0; ASM_EXCEPTIONTABLE_VAR(ret); @@ -180,25 +181,22 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop) #ifdef CONFIG_64BIT __asm__ __volatile__ ( -" depd,z %3,60,3,%%r19\n" /* r19=(ofs&7)*8 */ -" mtsp %4, %%sr1\n" -" depd %%r0,63,3,%3\n" -"1: ldd 0(%%sr1,%3),%0\n" -"2: ldd 8(%%sr1,%3),%%r20\n" -" subi 64,%%r19,%%r19\n" -" mtsar %%r19\n" -" shrpd %0,%%r20,%%sar,%0\n" +" depd,z %2,60,3,%3\n" /* shift=(ofs&7)*8 */ +" mtsp %5, %%sr1\n" +" depd %%r0,63,3,%2\n" +"1: ldd 0(%%sr1,%2),%0\n" +"2: ldd 8(%%sr1,%2),%4\n" +" subi 64,%3,%3\n" +" mtsar %3\n" +" shrpd %0,%4,%%sar,%0\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) - : "=r" (val), "+r" (ret) - : "0" (val), "r" (saddr), "r" (regs->isr) - : "r19", "r20" ); + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1") + : "+r" (val), "+r" (ret), "+r" (saddr), "=&r" (shift), "=&r" (temp1) + : "r" (regs->isr) ); #else - { - unsigned long shift, temp1; __asm__ __volatile__ ( -" zdep %2,29,2,%3\n" /* r19=(ofs&3)*8 */ +" zdep %2,29,2,%3\n" /* shift=(ofs&3)*8 */ " mtsp %5, %%sr1\n" " dep %%r0,31,2,%2\n" "1: ldw 0(%%sr1,%2),%0\n" @@ -209,12 +207,11 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop) " vshd %0,%R0,%0\n" " vshd %R0,%4,%R0\n" "4: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b, "%1") : "+r" (val), "+r" (ret), "+r" (saddr), "=&r" (shift), "=&r" (temp1) : "r" (regs->isr) ); - } #endif DPRINTF("val = 0x%llx\n", val); @@ -244,8 +241,8 @@ static int emulate_sth(struct pt_regs *regs, int frreg) "1: stb %1, 0(%%sr1, %3)\n" "2: stb %2, 1(%%sr1, %3)\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0") : "+r" (ret), "=&r" (temp1) : "r" (val), "r" (regs->ior), "r" (regs->isr) ); @@ -285,8 +282,8 @@ static int emulate_stw(struct pt_regs *regs, int frreg, int flop) " stw %%r20,0(%%sr1,%2)\n" " stw %%r21,4(%%sr1,%2)\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0") : "+r" (ret) : "r" (val), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r22", "r1" ); @@ -329,10 +326,10 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop) "3: std %%r20,0(%%sr1,%2)\n" "4: std %%r21,8(%%sr1,%2)\n" "5: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b, "%0") : "+r" (ret) : "r" (val), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r22", "r1" ); @@ -357,11 +354,11 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop) "4: stw %%r1,4(%%sr1,%2)\n" "5: stw %R1,8(%%sr1,%2)\n" "6: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b, "%0") : "+r" (ret) : "r" (val), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r1" ); diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c index 27ae40a443b80c..f7e0fee5ee55a3 100644 --- a/arch/parisc/kernel/unwind.c +++ b/arch/parisc/kernel/unwind.c @@ -228,10 +228,8 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int #ifdef CONFIG_IRQSTACKS extern void * const _call_on_stack; #endif /* CONFIG_IRQSTACKS */ - void *ptr; - ptr = dereference_kernel_function_descriptor(&handle_interruption); - if (pc_is_kernel_fn(pc, ptr)) { + if (pc_is_kernel_fn(pc, handle_interruption)) { struct pt_regs *regs = (struct pt_regs *)(info->sp - frame_size - PT_SZ_ALGN); dbg("Unwinding through handle_interruption()\n"); info->prev_sp = regs->gr[30]; @@ -239,13 +237,13 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int return 1; } - if (pc_is_kernel_fn(pc, ret_from_kernel_thread) || - pc_is_kernel_fn(pc, syscall_exit)) { + if (pc == (unsigned long)&ret_from_kernel_thread || + pc == (unsigned long)&syscall_exit) { info->prev_sp = info->prev_ip = 0; return 1; } - if (pc_is_kernel_fn(pc, intr_return)) { + if (pc == (unsigned long)&intr_return) { struct pt_regs *regs; dbg("Found intr_return()\n"); @@ -257,14 +255,14 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int } if (pc_is_kernel_fn(pc, _switch_to) || - pc_is_kernel_fn(pc, _switch_to_ret)) { + pc == (unsigned long)&_switch_to_ret) { info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE; info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET); return 1; } #ifdef CONFIG_IRQSTACKS - if (pc_is_kernel_fn(pc, _call_on_stack)) { + if (pc == (unsigned long)&_call_on_stack) { info->prev_sp = *(unsigned long *)(info->sp - FRAME_SIZE - REG_SZ); info->prev_ip = *(unsigned long *)(info->sp - FRAME_SIZE - RP_OFFSET); return 1; diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index 58694d1989c233..548051b0b4aff6 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -130,6 +130,7 @@ SECTIONS RO_DATA(8) /* unwind info */ + . = ALIGN(4); .PARISC.unwind : { __start___unwind = .; *(.PARISC.unwind) diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 2fe5b44986e092..c39de84e98b051 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -150,11 +150,16 @@ int fixup_exception(struct pt_regs *regs) * Fix up get_user() and put_user(). * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() sets the least-significant * bit in the relative address of the fixup routine to indicate - * that gr[ASM_EXCEPTIONTABLE_REG] should be loaded with - * -EFAULT to report a userspace access error. + * that the register encoded in the "or %r0,%r0,register" + * opcode should be loaded with -EFAULT to report a userspace + * access error. */ if (fix->fixup & 1) { - regs->gr[ASM_EXCEPTIONTABLE_REG] = -EFAULT; + int fault_error_reg = fix->err_opcode & 0x1f; + if (!WARN_ON(!fault_error_reg)) + regs->gr[fault_error_reg] = -EFAULT; + pr_debug("Unalignment fixup of register %d at %pS\n", + fault_error_reg, (void*)regs->iaoq[0]); /* zero target register for get_user() */ if (parisc_acctyp(0, regs->iir) == VM_READ) { diff --git a/arch/parisc/net/bpf_jit_core.c b/arch/parisc/net/bpf_jit_core.c index d6ee2fd4555037..7b9cb3cda27eeb 100644 --- a/arch/parisc/net/bpf_jit_core.c +++ b/arch/parisc/net/bpf_jit_core.c @@ -114,7 +114,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) jit_data->header = bpf_jit_binary_alloc(prog_size + extable_size, &jit_data->image, - sizeof(u32), + sizeof(long), bpf_fill_ill_insns); if (!jit_data->header) { prog = orig_prog; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d5d5388973ac76..2fe51e0ad63713 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -607,10 +607,10 @@ config ARCH_SUPPORTS_KEXEC def_bool PPC_BOOK3S || PPC_E500 || (44x && !SMP) config ARCH_SUPPORTS_KEXEC_FILE - def_bool PPC64 && CRYPTO=y && CRYPTO_SHA256=y + def_bool PPC64 config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SELECTS_KEXEC_FILE def_bool y @@ -857,6 +857,7 @@ config THREAD_SHIFT int "Thread shift" if EXPERT range 13 15 default "15" if PPC_256K_PAGES + default "15" if PPC_PSERIES || PPC_POWERNV default "14" if PPC64 default "13" help diff --git a/arch/powerpc/boot/simple_alloc.c b/arch/powerpc/boot/simple_alloc.c index 267d6524caac47..d07796fdf91aa7 100644 --- a/arch/powerpc/boot/simple_alloc.c +++ b/arch/powerpc/boot/simple_alloc.c @@ -112,8 +112,11 @@ static void *simple_realloc(void *ptr, unsigned long size) return ptr; new = simple_malloc(size); - memcpy(new, ptr, p->size); - simple_free(ptr); + if (new) { + memcpy(new, ptr, p->size); + simple_free(ptr); + } + return new; } diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config index 524db76f47b737..8aff8321739778 100644 --- a/arch/powerpc/configs/85xx-hw.config +++ b/arch/powerpc/configs/85xx-hw.config @@ -24,6 +24,7 @@ CONFIG_FS_ENET=y CONFIG_FSL_CORENET_CF=y CONFIG_FSL_DMA=y CONFIG_FSL_HV_MANAGER=y +CONFIG_FSL_IFC=y CONFIG_FSL_PQ_MDIO=y CONFIG_FSL_RIO=y CONFIG_FSL_XGMAC_MDIO=y @@ -58,6 +59,7 @@ CONFIG_INPUT_FF_MEMLESS=m CONFIG_MARVELL_PHY=y CONFIG_MDIO_BUS_MUX_GPIO=y CONFIG_MDIO_BUS_MUX_MMIOREG=y +CONFIG_MEMORY=y CONFIG_MMC_SDHCI_OF_ESDHC=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_SDHCI=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 6e7b9e8fd2251a..65e518dde2c2fe 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -81,7 +81,6 @@ CONFIG_MODULE_SIG_SHA512=y CONFIG_PARTITION_ADVANCED=y CONFIG_BINFMT_MISC=m CONFIG_ZSWAP=y -CONFIG_Z3FOLD=y CONFIG_ZSMALLOC=y # CONFIG_SLAB_MERGE_DEFAULT is not set CONFIG_SLAB_FREELIST_RANDOM=y diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 8d3eacb50d5601..9d44e6630908d2 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -301,7 +301,6 @@ CONFIG_WQ_WATCHDOG=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_DEBUG_CREDENTIALS=y # CONFIG_FTRACE is not set CONFIG_XMON=y # CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig index 6fc2248ca56166..fccf742c55c2c3 100644 --- a/arch/powerpc/crypto/Kconfig +++ b/arch/powerpc/crypto/Kconfig @@ -96,6 +96,7 @@ config CRYPTO_AES_PPC_SPE config CRYPTO_AES_GCM_P10 tristate "Stitched AES/GCM acceleration support on P10 or later CPU (PPC)" + depends on BROKEN depends on PPC64 && CPU_LITTLE_ENDIAN && VSX select CRYPTO_LIB_AES select CRYPTO_ALGAPI diff --git a/arch/powerpc/crypto/aes-gcm-p10-glue.c b/arch/powerpc/crypto/aes-gcm-p10-glue.c index 4b6e899895e7be..f62ee54076c06d 100644 --- a/arch/powerpc/crypto/aes-gcm-p10-glue.c +++ b/arch/powerpc/crypto/aes-gcm-p10-glue.c @@ -37,7 +37,7 @@ asmlinkage void aes_p10_gcm_encrypt(u8 *in, u8 *out, size_t len, void *rkey, u8 *iv, void *Xi); asmlinkage void aes_p10_gcm_decrypt(u8 *in, u8 *out, size_t len, void *rkey, u8 *iv, void *Xi); -asmlinkage void gcm_init_htable(unsigned char htable[256], unsigned char Xi[16]); +asmlinkage void gcm_init_htable(unsigned char htable[], unsigned char Xi[]); asmlinkage void gcm_ghash_p10(unsigned char *Xi, unsigned char *Htable, unsigned char *aad, unsigned int alen); diff --git a/arch/powerpc/crypto/chacha-p10-glue.c b/arch/powerpc/crypto/chacha-p10-glue.c index 74fb86b0d2097c..7c728755852e1a 100644 --- a/arch/powerpc/crypto/chacha-p10-glue.c +++ b/arch/powerpc/crypto/chacha-p10-glue.c @@ -197,6 +197,9 @@ static struct skcipher_alg algs[] = { static int __init chacha_p10_init(void) { + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return 0; + static_branch_enable(&have_p10); return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); @@ -204,10 +207,13 @@ static int __init chacha_p10_init(void) static void __exit chacha_p10_exit(void) { + if (!static_branch_likely(&have_p10)) + return; + crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); } -module_cpu_feature_match(PPC_MODULE_FEATURE_P10, chacha_p10_init); +module_init(chacha_p10_init); module_exit(chacha_p10_exit); MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (P10 accelerated)"); diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h index 2bc53c646ccd7d..83848b534cb171 100644 --- a/arch/powerpc/include/asm/asm-compat.h +++ b/arch/powerpc/include/asm/asm-compat.h @@ -39,6 +39,12 @@ #define STDX_BE stringify_in_c(stdbrx) #endif +#ifdef CONFIG_CC_IS_CLANG +#define DS_FORM_CONSTRAINT "Z<>" +#else +#define DS_FORM_CONSTRAINT "YZ<>" +#endif + #else /* 32-bit */ /* operations for longs and pointers */ diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 5bf6a4d49268c7..d1ea554c33ed7e 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -11,6 +11,7 @@ #include #include #include +#include /* * Since *_return_relaxed and {cmp}xchg_relaxed are implemented with @@ -197,7 +198,7 @@ static __inline__ s64 arch_atomic64_read(const atomic64_t *v) if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) __asm__ __volatile__("ld %0,0(%1)" : "=r"(t) : "b"(&v->counter)); else - __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); + __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : DS_FORM_CONSTRAINT (v->counter)); return t; } @@ -208,7 +209,7 @@ static __inline__ void arch_atomic64_set(atomic64_t *v, s64 i) if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) __asm__ __volatile__("std %1,0(%2)" : "=m"(v->counter) : "r"(i), "b"(&v->counter)); else - __asm__ __volatile__("std%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); + __asm__ __volatile__("std%U0%X0 %1,%0" : "=" DS_FORM_CONSTRAINT (v->counter) : "r"(i)); } #define ATOMIC64_OP(op, asm_op) \ diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index 9e5a39b6a3114b..107fc5a4845696 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -20,14 +20,6 @@ #ifndef __ASSEMBLY__ extern void _mcount(void); -static inline unsigned long ftrace_call_adjust(unsigned long addr) -{ - if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) - addr += MCOUNT_INSN_SIZE; - - return addr; -} - unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp); @@ -142,8 +134,10 @@ static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; } #ifdef CONFIG_FUNCTION_TRACER extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[]; void ftrace_free_init_tramp(void); +unsigned long ftrace_call_adjust(unsigned long addr); #else static inline void ftrace_free_init_tramp(void) { } +static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; } #endif #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index c099780385dd3d..218488407ac00e 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -494,7 +494,7 @@ long plpar_hcall_norets_notrace(unsigned long opcode, ...); * Used for all but the craziest of phyp interfaces (see plpar_hcall9) */ #define PLPAR_HCALL_BUFSIZE 4 -long plpar_hcall(unsigned long opcode, unsigned long *retbuf, ...); +long plpar_hcall(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL_BUFSIZE], ...); /** * plpar_hcall_raw: - Make a hypervisor call without calculating hcall stats @@ -508,7 +508,7 @@ long plpar_hcall(unsigned long opcode, unsigned long *retbuf, ...); * plpar_hcall, but plpar_hcall_raw works in real mode and does not * calculate hypervisor call statistics. */ -long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...); +long plpar_hcall_raw(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL_BUFSIZE], ...); /** * plpar_hcall9: - Make a pseries hypervisor call with up to 9 return arguments @@ -519,8 +519,8 @@ long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...); * PLPAR_HCALL9_BUFSIZE to size the return argument buffer. */ #define PLPAR_HCALL9_BUFSIZE 9 -long plpar_hcall9(unsigned long opcode, unsigned long *retbuf, ...); -long plpar_hcall9_raw(unsigned long opcode, unsigned long *retbuf, ...); +long plpar_hcall9(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL9_BUFSIZE], ...); +long plpar_hcall9_raw(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL9_BUFSIZE], ...); /* pseries hcall tracing */ extern struct static_key hcall_tracepoint_key; @@ -540,7 +540,7 @@ struct hvcall_mpp_data { unsigned long backing_mem; }; -int h_get_mpp(struct hvcall_mpp_data *); +long h_get_mpp(struct hvcall_mpp_data *mpp_data); struct hvcall_mpp_x_data { unsigned long coalesced_bytes; diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index a4196ab1d0167c..5f9d61b2159cc5 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -336,6 +336,14 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte if (IS_ENABLED(CONFIG_KASAN)) return; + /* + * Likewise, do not use it in real mode if percpu first chunk is not + * embedded. With CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK enabled there + * are chances where percpu allocation can come from vmalloc area. + */ + if (percpu_first_chunk_is_paged) + return; + /* Otherwise, it should be safe to call it */ nmi_enter(); } @@ -351,6 +359,8 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter // no nmi_exit for a pseries hash guest taking a real mode exception } else if (IS_ENABLED(CONFIG_KASAN)) { // no nmi_exit for KASAN in real mode + } else if (percpu_first_chunk_is_paged) { + // no nmi_exit if percpu first chunk is not embedded } else { nmi_exit(); } diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 0732b743e09962..99419e87f5556e 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -37,7 +37,7 @@ extern struct pci_dev *isa_bridge_pcidev; * define properly based on the platform */ #ifndef CONFIG_PCI -#define _IO_BASE 0 +#define _IO_BASE POISON_POINTER_DELTA #define _ISA_MEM_BASE 0 #define PCI_DRAM_OFFSET 0 #elif defined(CONFIG_PPC32) @@ -585,12 +585,12 @@ __do_out_asm(_rec_outl, "stwbrx") #define __do_inw(port) _rec_inw(port) #define __do_inl(port) _rec_inl(port) #else /* CONFIG_PPC32 */ -#define __do_outb(val, port) writeb(val,(PCI_IO_ADDR)_IO_BASE+port); -#define __do_outw(val, port) writew(val,(PCI_IO_ADDR)_IO_BASE+port); -#define __do_outl(val, port) writel(val,(PCI_IO_ADDR)_IO_BASE+port); -#define __do_inb(port) readb((PCI_IO_ADDR)_IO_BASE + port); -#define __do_inw(port) readw((PCI_IO_ADDR)_IO_BASE + port); -#define __do_inl(port) readl((PCI_IO_ADDR)_IO_BASE + port); +#define __do_outb(val, port) writeb(val,(PCI_IO_ADDR)(_IO_BASE+port)); +#define __do_outw(val, port) writew(val,(PCI_IO_ADDR)(_IO_BASE+port)); +#define __do_outl(val, port) writel(val,(PCI_IO_ADDR)(_IO_BASE+port)); +#define __do_inb(port) readb((PCI_IO_ADDR)(_IO_BASE + port)); +#define __do_inw(port) readw((PCI_IO_ADDR)(_IO_BASE + port)); +#define __do_inl(port) readl((PCI_IO_ADDR)(_IO_BASE + port)); #endif /* !CONFIG_PPC32 */ #ifdef CONFIG_EEH @@ -606,12 +606,12 @@ __do_out_asm(_rec_outl, "stwbrx") #define __do_writesw(a, b, n) _outsw(PCI_FIX_ADDR(a),(b),(n)) #define __do_writesl(a, b, n) _outsl(PCI_FIX_ADDR(a),(b),(n)) -#define __do_insb(p, b, n) readsb((PCI_IO_ADDR)_IO_BASE+(p), (b), (n)) -#define __do_insw(p, b, n) readsw((PCI_IO_ADDR)_IO_BASE+(p), (b), (n)) -#define __do_insl(p, b, n) readsl((PCI_IO_ADDR)_IO_BASE+(p), (b), (n)) -#define __do_outsb(p, b, n) writesb((PCI_IO_ADDR)_IO_BASE+(p),(b),(n)) -#define __do_outsw(p, b, n) writesw((PCI_IO_ADDR)_IO_BASE+(p),(b),(n)) -#define __do_outsl(p, b, n) writesl((PCI_IO_ADDR)_IO_BASE+(p),(b),(n)) +#define __do_insb(p, b, n) readsb((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n)) +#define __do_insw(p, b, n) readsw((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n)) +#define __do_insl(p, b, n) readsl((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n)) +#define __do_outsb(p, b, n) writesb((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n)) +#define __do_outsw(p, b, n) writesw((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n)) +#define __do_outsl(p, b, n) writesl((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n)) #define __do_memset_io(addr, c, n) \ _memset_io(PCI_FIX_ADDR(addr), c, n) diff --git a/arch/powerpc/include/asm/irq_work.h b/arch/powerpc/include/asm/irq_work.h index b8b0be8f1a07ee..c6d3078bd8c3b4 100644 --- a/arch/powerpc/include/asm/irq_work.h +++ b/arch/powerpc/include/asm/irq_work.h @@ -6,6 +6,5 @@ static inline bool arch_irq_work_has_interrupt(void) { return true; } -extern void arch_irq_work_raise(void); #endif /* _ASM_POWERPC_IRQ_WORK_H */ diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h index 93ce3ec253877d..2f2a86ed2280aa 100644 --- a/arch/powerpc/include/asm/jump_label.h +++ b/arch/powerpc/include/asm/jump_label.h @@ -17,7 +17,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop # arch_static_branch\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".long 1b - ., %l[l_yes] - .\n\t" @@ -32,7 +32,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b %l[l_yes] # arch_static_branch_jump\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".long 1b - ., %l[l_yes] - .\n\t" diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 52cc25864a1be2..d8b7e246a32f59 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -412,5 +412,9 @@ extern void *abatron_pteptrs[2]; #include #endif +#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP) +#define __HAVE_ARCH_RESERVED_KERNEL_PAGES +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MMU_H_ */ diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 4c6c6dbd182f45..da827d2d08666e 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -42,14 +42,6 @@ u64 memory_hotplug_max(void); #else #define memory_hotplug_max() memblock_end_of_DRAM() #endif /* CONFIG_NUMA */ -#ifdef CONFIG_FA_DUMP -#define __HAVE_ARCH_RESERVED_KERNEL_PAGES -#endif - -#ifdef CONFIG_MEMORY_HOTPLUG -extern int create_section_mapping(unsigned long start, unsigned long end, - int nid, pgprot_t prot); -#endif #endif /* __KERNEL__ */ #endif /* _ASM_MMZONE_H_ */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-40x.h b/arch/powerpc/include/asm/nohash/32/pte-40x.h index 6fe46e7545566c..0b4e5f8ce3e8a9 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-40x.h +++ b/arch/powerpc/include/asm/nohash/32/pte-40x.h @@ -69,9 +69,6 @@ #define _PTE_NONE_MASK 0 -/* Until my rework is finished, 40x still needs atomic PTE updates */ -#define PTE_ATOMIC_UPDATES 1 - #define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) #define _PAGE_BASE (_PAGE_BASE_NC) diff --git a/arch/powerpc/include/asm/nohash/mmu-e500.h b/arch/powerpc/include/asm/nohash/mmu-e500.h index 6ddced0415cb5c..7dc24b8632d7c2 100644 --- a/arch/powerpc/include/asm/nohash/mmu-e500.h +++ b/arch/powerpc/include/asm/nohash/mmu-e500.h @@ -303,8 +303,7 @@ extern unsigned long linear_map_top; extern int book3e_htw_mode; #define PPC_HTW_NONE 0 -#define PPC_HTW_IBM 1 -#define PPC_HTW_E6500 2 +#define PPC_HTW_E6500 1 /* * 64-bit booke platforms don't load the tlb in the tlb miss handler code. diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h index 8e5b7d0b851c61..634970ce13c6b9 100644 --- a/arch/powerpc/include/asm/percpu.h +++ b/arch/powerpc/include/asm/percpu.h @@ -15,6 +15,16 @@ #endif /* CONFIG_SMP */ #endif /* __powerpc64__ */ +#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) && defined(CONFIG_SMP) +#include +DECLARE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged); + +#define percpu_first_chunk_is_paged \ + (static_key_enabled(&__percpu_first_chunk_is_paged.key)) +#else +#define percpu_first_chunk_is_paged false +#endif /* CONFIG_PPC64 && CONFIG_SMP */ + #include #include diff --git a/arch/powerpc/include/asm/plpks.h b/arch/powerpc/include/asm/plpks.h index 23b77027c91637..7a84069759b032 100644 --- a/arch/powerpc/include/asm/plpks.h +++ b/arch/powerpc/include/asm/plpks.h @@ -44,9 +44,8 @@ #define PLPKS_MAX_DATA_SIZE 4000 // Timeouts for PLPKS operations -#define PLPKS_MAX_TIMEOUT 5000 // msec -#define PLPKS_FLUSH_SLEEP 10 // msec -#define PLPKS_FLUSH_SLEEP_RANGE 400 +#define PLPKS_MAX_TIMEOUT (5 * USEC_PER_SEC) +#define PLPKS_FLUSH_SLEEP 10000 // usec struct plpks_var { char *component; diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index d9fcff5750271d..2689e7139b9ea7 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -30,6 +30,16 @@ void *pci_traverse_device_nodes(struct device_node *start, void *data); extern void pci_devs_phb_init_dynamic(struct pci_controller *phb); +#if defined(CONFIG_IOMMU_API) && (defined(CONFIG_PPC_PSERIES) || \ + defined(CONFIG_PPC_POWERNV)) +extern void ppc_iommu_register_device(struct pci_controller *phb); +extern void ppc_iommu_unregister_device(struct pci_controller *phb); +#else +static inline void ppc_iommu_register_device(struct pci_controller *phb) { } +static inline void ppc_iommu_unregister_device(struct pci_controller *phb) { } +#endif + + /* From rtas_pci.h */ extern void init_pci_config_tokens (void); extern unsigned long get_phb_buid (struct device_node *); diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 4ae4ab9090a2d4..ade5f094dbd222 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -617,6 +617,8 @@ #endif #define SPRN_HID2 0x3F8 /* Hardware Implementation Register 2 */ #define SPRN_HID2_GEKKO 0x398 /* Gekko HID2 Register */ +#define SPRN_HID2_G2_LE 0x3F3 /* G2_LE HID2 Register */ +#define HID2_G2_LE_HBE (1<<18) /* High BAT Enable (G2_LE) */ #define SPRN_IABR 0x3F2 /* Instruction Address Breakpoint Register */ #define SPRN_IABR2 0x3FA /* 83xx */ #define SPRN_IBCR 0x135 /* 83xx Insn Breakpoint Control Reg */ diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h index a21f529c43d96b..8359c06d92d9f8 100644 --- a/arch/powerpc/include/asm/reg_fsl_emb.h +++ b/arch/powerpc/include/asm/reg_fsl_emb.h @@ -12,9 +12,16 @@ #ifndef __ASSEMBLY__ /* Performance Monitor Registers */ #define mfpmr(rn) ({unsigned int rval; \ - asm volatile("mfpmr %0," __stringify(rn) \ + asm volatile(".machine push; " \ + ".machine e300; " \ + "mfpmr %0," __stringify(rn) ";" \ + ".machine pop; " \ : "=r" (rval)); rval;}) -#define mtpmr(rn, v) asm volatile("mtpmr " __stringify(rn) ",%0" : : "r" (v)) +#define mtpmr(rn, v) asm volatile(".machine push; " \ + ".machine e300; " \ + "mtpmr " __stringify(rn) ",%0; " \ + ".machine pop; " \ + : : "r" (v)) #endif /* __ASSEMBLY__ */ /* Freescale Book E Performance Monitor APU Registers */ diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index c697c3c746946d..33024a2874a691 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -68,7 +68,7 @@ enum rtas_function_index { RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE, RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2, RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW, - RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS, + RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW, RTAS_FNIDX__IBM_SCAN_LOG_DUMP, RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR, RTAS_FNIDX__IBM_SET_EEH_OPTION, @@ -163,7 +163,7 @@ typedef struct { #define RTAS_FN_IBM_READ_SLOT_RESET_STATE rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE) #define RTAS_FN_IBM_READ_SLOT_RESET_STATE2 rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2) #define RTAS_FN_IBM_REMOVE_PE_DMA_WINDOW rtas_fn_handle(RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW) -#define RTAS_FN_IBM_RESET_PE_DMA_WINDOWS rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS) +#define RTAS_FN_IBM_RESET_PE_DMA_WINDOW rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW) #define RTAS_FN_IBM_SCAN_LOG_DUMP rtas_fn_handle(RTAS_FNIDX__IBM_SCAN_LOG_DUMP) #define RTAS_FN_IBM_SET_DYNAMIC_INDICATOR rtas_fn_handle(RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR) #define RTAS_FN_IBM_SET_EEH_OPTION rtas_fn_handle(RTAS_FNIDX__IBM_SET_EEH_OPTION) diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index ea26665f82cfc8..f43f3a6b0051cf 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -14,6 +14,7 @@ typedef struct func_desc func_desc_t; extern char __head_end[]; extern char __srwx_boundary[]; +extern char __exittext_begin[], __exittext_end[]; /* Patch sites */ extern s32 patch__call_flush_branch_caches1; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index bf5dde1a411471..15c5691dd21844 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -14,7 +14,7 @@ #ifdef __KERNEL__ -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN) && CONFIG_THREAD_SHIFT < 15 #define MIN_THREAD_SHIFT (CONFIG_THREAD_SHIFT + 1) #else #define MIN_THREAD_SHIFT CONFIG_THREAD_SHIFT diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index f4e6f2dd04b731..16bacfe8c7a2ca 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -145,6 +145,7 @@ static inline int cpu_to_coregroup_id(int cpu) #ifdef CONFIG_HOTPLUG_SMT #include +#include #include static inline bool topology_is_primary_thread(unsigned int cpu) @@ -156,6 +157,18 @@ static inline bool topology_smt_thread_allowed(unsigned int cpu) { return cpu_thread_in_core(cpu) < cpu_smt_num_threads; } + +#define topology_is_core_online topology_is_core_online +static inline bool topology_is_core_online(unsigned int cpu) +{ + int i, first_cpu = cpu_first_thread_sibling(cpu); + + for (i = first_cpu; i < first_cpu + threads_per_core; ++i) { + if (cpu_online(i)) + return true; + } + return false; +} #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index fb725ec77926e1..a81bd825087cda 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -6,6 +6,7 @@ #include #include #include +#include #ifdef __powerpc64__ /* We use TASK_SIZE_USER64 as TASK_SIZE is not constant */ @@ -74,7 +75,7 @@ __pu_failed: \ /* -mprefixed can generate offsets beyond range, fall back hack */ #ifdef CONFIG_PPC_KERNEL_PREFIXED #define __put_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm goto( \ "1: " op " %0,0(%1) # put_user\n" \ EX_TABLE(1b, %l2) \ : \ @@ -83,7 +84,7 @@ __pu_failed: \ : label) #else #define __put_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm goto( \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ @@ -93,11 +94,21 @@ __pu_failed: \ #endif #ifdef __powerpc64__ +#ifdef CONFIG_PPC_KERNEL_PREFIXED #define __put_user_asm2_goto(x, ptr, label) \ __put_user_asm_goto(x, ptr, label, "std") +#else +#define __put_user_asm2_goto(x, addr, label) \ + asm goto ("1: std%U1%X1 %0,%1 # put_user\n" \ + EX_TABLE(1b, %l2) \ + : \ + : "r" (x), DS_FORM_CONSTRAINT (*addr) \ + : \ + : label) +#endif // CONFIG_PPC_KERNEL_PREFIXED #else /* __powerpc64__ */ #define __put_user_asm2_goto(x, addr, label) \ - asm_volatile_goto( \ + asm goto( \ "1: stw%X1 %0, %1\n" \ "2: stw%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ @@ -146,7 +157,7 @@ do { \ /* -mprefixed can generate offsets beyond range, fall back hack */ #ifdef CONFIG_PPC_KERNEL_PREFIXED #define __get_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: "op" %0,0(%1) # get_user\n" \ EX_TABLE(1b, %l2) \ : "=r" (x) \ @@ -155,7 +166,7 @@ do { \ : label) #else #define __get_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: "op"%U1%X1 %0, %1 # get_user\n" \ EX_TABLE(1b, %l2) \ : "=r" (x) \ @@ -169,7 +180,7 @@ do { \ __get_user_asm_goto(x, addr, label, "ld") #else /* __powerpc64__ */ #define __get_user_asm2_goto(x, addr, label) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: lwz%X1 %0, %1\n" \ "2: lwz%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index a585c8e538ff0f..939daf6b695ef1 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -111,6 +111,21 @@ extern struct vdso_arch_data *vdso_data; addi \ptr, \ptr, (_vdso_datapage - 999b)@l .endm +#include +#include + +.macro get_realdatapage ptr scratch + get_datapage \ptr +#ifdef CONFIG_TIME_NS + lwz \scratch, VDSO_CLOCKMODE_OFFSET(\ptr) + xoris \scratch, \scratch, VDSO_CLOCKMODE_TIMENS@h + xori \scratch, \scratch, VDSO_CLOCKMODE_TIMENS@l + cntlzw \scratch, \scratch + rlwinm \scratch, \scratch, PAGE_SHIFT - 5, 1 << PAGE_SHIFT + add \ptr, \ptr, \scratch +#endif +.endm + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/vmalloc.h b/arch/powerpc/include/asm/vmalloc.h index 4c69ece52a31e5..59ed89890c902b 100644 --- a/arch/powerpc/include/asm/vmalloc.h +++ b/arch/powerpc/include/asm/vmalloc.h @@ -7,14 +7,14 @@ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP #define arch_vmap_pud_supported arch_vmap_pud_supported -static inline bool arch_vmap_pud_supported(pgprot_t prot) +static __always_inline bool arch_vmap_pud_supported(pgprot_t prot) { /* HPT does not cope with large pages in the vmalloc area */ return radix_enabled(); } #define arch_vmap_pmd_supported arch_vmap_pmd_supported -static inline bool arch_vmap_pmd_supported(pgprot_t prot) +static __always_inline bool arch_vmap_pmd_supported(pgprot_t prot) { return radix_enabled(); } diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 9f14d95b8b32fd..2affd30468bc4c 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -348,6 +348,8 @@ int main(void) #else OFFSET(CFG_SYSCALL_MAP32, vdso_arch_data, syscall_map); #endif + OFFSET(VDSO_CLOCKMODE_OFFSET, vdso_arch_data, data[0].clock_mode); + DEFINE(VDSO_CLOCKMODE_TIMENS, VDSO_CLOCKMODE_TIMENS); #ifdef CONFIG_BUG DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry)); diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S index f29ce3dd6140f4..bfd3f442e5eb9d 100644 --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -26,6 +26,15 @@ BEGIN_FTR_SECTION bl __init_fpu_registers END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE) bl setup_common_caches + + /* + * This assumes that all cores using __setup_cpu_603 with + * MMU_FTR_USE_HIGH_BATS are G2_LE compatible + */ +BEGIN_MMU_FTR_SECTION + bl setup_g2_le_hid2 +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) + mtlr r5 blr _GLOBAL(__setup_cpu_604) @@ -115,6 +124,16 @@ SYM_FUNC_START_LOCAL(setup_604_hid0) blr SYM_FUNC_END(setup_604_hid0) +/* Enable high BATs for G2_LE and derivatives like e300cX */ +SYM_FUNC_START_LOCAL(setup_g2_le_hid2) + mfspr r11,SPRN_HID2_G2_LE + oris r11,r11,HID2_G2_LE_HBE@h + mtspr SPRN_HID2_G2_LE,r11 + sync + isync + blr +SYM_FUNC_END(setup_g2_le_hid2) + /* 7400 <= rev 2.7 and 7410 rev = 1.0 suffer from some * erratas we work around here. * Moto MPC710CE.pdf describes them, those are errata @@ -495,4 +514,3 @@ _GLOBAL(__restore_cpu_setup) mtcr r7 blr _ASM_NOKPROBE_SYMBOL(__restore_cpu_setup) - diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h index ceb06b109f8313..2ae8e9a7b461c8 100644 --- a/arch/powerpc/kernel/cpu_specs_e500mc.h +++ b/arch/powerpc/kernel/cpu_specs_e500mc.h @@ -8,7 +8,8 @@ #ifdef CONFIG_PPC64 #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ - PPC_FEATURE_HAS_FPU | PPC_FEATURE_64) + PPC_FEATURE_HAS_FPU | PPC_FEATURE_64 | \ + PPC_FEATURE_BOOKE) #else #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ PPC_FEATURE_BOOKE) diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index e0ce812796241a..7d1b50599dd6c2 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -849,6 +849,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) { struct eeh_dev *edev; struct pci_dev *pdev; + struct pci_bus *bus = NULL; if (pe->type & EEH_PE_PHB) return pe->phb->bus; @@ -859,9 +860,11 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) /* Retrieve the parent PCI bus of first (top) PCI device */ edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry); + pci_lock_rescan_remove(); pdev = eeh_dev_to_pci_dev(edev); if (pdev) - return pdev->bus; + bus = pdev->bus; + pci_unlock_rescan_remove(); - return NULL; + return bus; } diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 6a9acfb690c9f5..2f8f3f93cbb67e 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -23,6 +23,15 @@ #include #ifdef CONFIG_VSX +#define __REST_1FPVSR(n,c,base) \ +BEGIN_FTR_SECTION \ + b 2f; \ +END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ + REST_FPR(n,base); \ + b 3f; \ +2: REST_VSR(n,c,base); \ +3: + #define __REST_32FPVSRS(n,c,base) \ BEGIN_FTR_SECTION \ b 2f; \ @@ -41,9 +50,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ 2: SAVE_32VSRS(n,c,base); \ 3: #else +#define __REST_1FPVSR(n,b,base) REST_FPR(n, base) #define __REST_32FPVSRS(n,b,base) REST_32FPRS(n, base) #define __SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base) #endif +#define REST_1FPVSR(n,c,base) __REST_1FPVSR(n,__REG_##c,__REG_##base) #define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base) #define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base) @@ -67,6 +78,7 @@ _GLOBAL(store_fp_state) SAVE_32FPVSRS(0, R4, R3) mffs fr0 stfd fr0,FPSTATE_FPSCR(r3) + REST_1FPVSR(0, R4, R3) blr EXPORT_SYMBOL(store_fp_state) @@ -138,4 +150,5 @@ _GLOBAL(save_fpu) 2: SAVE_32FPVSRS(0, R4, R6) mffs fr0 stfd fr0,FPSTATE_FPSCR(r6) + REST_1FPVSR(0, R4, R6) blr diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 4690c219bfa4df..63432a33ec49ac 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -647,8 +647,9 @@ __after_prom_start: * Note: This process overwrites the OF exception vectors. */ LOAD_REG_IMMEDIATE(r3, PAGE_OFFSET) - mr. r4,r26 /* In some cases the loader may */ - beq 9f /* have already put us at zero */ + mr r4,r26 /* Load the virtual source address into r4 */ + cmpld r3,r4 /* Check if source == dest */ + beq 9f /* If so skip the copy */ li r6,0x100 /* Start offset, the first 0x100 */ /* bytes were copied earlier. */ diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 647b0b445e89db..0c94db8e2bdedb 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -41,12 +41,12 @@ #include "head_32.h" .macro compare_to_kernel_boundary scratch, addr -#if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000 +#if CONFIG_TASK_SIZE <= 0x80000000 && MODULES_VADDR >= 0x80000000 /* By simply checking Address >= 0x80000000, we know if its a kernel address */ not. \scratch, \addr #else rlwinm \scratch, \addr, 16, 0xfff8 - cmpli cr0, \scratch, PAGE_OFFSET@h + cmpli cr0, \scratch, TASK_SIZE@h #endif .endm @@ -404,7 +404,7 @@ FixupDAR:/* Entry point for dcbx workaround. */ mfspr r10, SPRN_SRR0 mtspr SPRN_MD_EPN, r10 rlwinm r11, r10, 16, 0xfff8 - cmpli cr1, r11, PAGE_OFFSET@h + cmpli cr1, r11, TASK_SIZE@h mfspr r11, SPRN_M_TWB /* Get level 1 table */ blt+ cr1, 3f diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index bd863702d81218..1ad059a9e2fef3 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -52,7 +52,8 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) - std r11,_NIP(r1) + std r11,_LINK(r1) + std r11,_NIP(r1) /* Saved LR is also the next instruction */ std r12,_MSR(r1) std r0,GPR0(r1) std r10,GPR1(r1) @@ -70,7 +71,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) std r9,GPR13(r1) SAVE_NVGPRS(r1) std r11,_XER(r1) - std r11,_LINK(r1) std r11,_CTR(r1) li r11,\trapnr diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 14251bc5219eba..efaca0c6eff9d0 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1344,7 +1344,7 @@ static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev) struct pci_controller *hose; if (!dev_is_pci(dev)) - return ERR_PTR(-EPERM); + return ERR_PTR(-ENODEV); pdev = to_pci_dev(dev); hose = pdev->bus->sysdata; @@ -1393,6 +1393,21 @@ static const struct attribute_group *spapr_tce_iommu_groups[] = { NULL, }; +void ppc_iommu_register_device(struct pci_controller *phb) +{ + iommu_device_sysfs_add(&phb->iommu, phb->parent, + spapr_tce_iommu_groups, "iommu-phb%04x", + phb->global_number); + iommu_device_register(&phb->iommu, &spapr_tce_iommu_ops, + phb->parent); +} + +void ppc_iommu_unregister_device(struct pci_controller *phb) +{ + iommu_device_unregister(&phb->iommu); + iommu_device_sysfs_remove(&phb->iommu); +} + /* * This registers IOMMU devices of PHBs. This needs to happen * after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and @@ -1403,11 +1418,7 @@ static int __init spapr_tce_setup_phb_iommus_initcall(void) struct pci_controller *hose; list_for_each_entry(hose, &hose_list, list_node) { - iommu_device_sysfs_add(&hose->iommu, hose->parent, - spapr_tce_iommu_groups, "iommu-phb%04x", - hose->global_number); - iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops, - hose->parent); + ppc_iommu_register_device(hose); } return 0; } diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c index 938e66829eae65..d5c48d1b0a31ea 100644 --- a/arch/powerpc/kernel/irq_64.c +++ b/arch/powerpc/kernel/irq_64.c @@ -230,7 +230,7 @@ notrace __no_kcsan void arch_local_irq_restore(unsigned long mask) * This allows interrupts to be unmasked without hard disabling, and * also without new hard interrupts coming in ahead of pending ones. */ - asm_volatile_goto( + asm goto( "1: \n" " lbz 9,%0(13) \n" " cmpwi 9,0 \n" diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c index 072ebe7f290ba7..f8208c027148fd 100644 --- a/arch/powerpc/kernel/kprobes-ftrace.c +++ b/arch/powerpc/kernel/kprobes-ftrace.c @@ -21,6 +21,9 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, struct pt_regs *regs; int bit; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(nip, parent_nip); if (bit < 0) return; diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index b68898ac07e199..9452a54d356c97 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1198,11 +1198,11 @@ void kvmppc_save_user_regs(void) usermsr = current->thread.regs->msr; + /* Caller has enabled FP/VEC/VSX/TM in MSR */ if (usermsr & MSR_FP) - save_fpu(current); - + __giveup_fpu(current); if (usermsr & MSR_VEC) - save_altivec(current); + __giveup_altivec(current); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (usermsr & MSR_TM) { @@ -2258,6 +2258,22 @@ unsigned long __get_wchan(struct task_struct *p) return ret; } +static bool empty_user_regs(struct pt_regs *regs, struct task_struct *tsk) +{ + unsigned long stack_page; + + // A non-empty pt_regs should never have a zero MSR or TRAP value. + if (regs->msr || regs->trap) + return false; + + // Check it sits at the very base of the stack + stack_page = (unsigned long)task_stack_page(tsk); + if ((unsigned long)(regs + 1) != stack_page + THREAD_SIZE) + return false; + + return true; +} + static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH; void __no_sanitize_address show_stack(struct task_struct *tsk, @@ -2322,9 +2338,13 @@ void __no_sanitize_address show_stack(struct task_struct *tsk, lr = regs->link; printk("%s--- interrupt: %lx at %pS\n", loglvl, regs->trap, (void *)regs->nip); - __show_regs(regs); - printk("%s--- interrupt: %lx\n", - loglvl, regs->trap); + + // Detect the case of an empty pt_regs at the very base + // of the stack and suppress showing it in full. + if (!empty_user_regs(regs, tsk)) { + __show_regs(regs); + printk("%s--- interrupt: %lx\n", loglvl, regs->trap); + } firstframe = 1; } diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 0b5878c3125b1c..bf6d8ad3819e99 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -327,6 +327,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node, void *data) { const char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const __be32 *cpu_version = NULL; const __be32 *prop; const __be32 *intserv; int i, nthreads; @@ -375,6 +376,18 @@ static int __init early_init_dt_scan_cpus(unsigned long node, if (IS_ENABLED(CONFIG_PPC64)) boot_cpu_hwid = be32_to_cpu(intserv[found_thread]); + if (nr_cpu_ids % nthreads != 0) { + set_nr_cpu_ids(ALIGN(nr_cpu_ids, nthreads)); + pr_warn("nr_cpu_ids was not a multiple of threads_per_core, adjusted to %d\n", + nr_cpu_ids); + } + + if (boot_cpuid >= nr_cpu_ids) { + set_nr_cpu_ids(min(CONFIG_NR_CPUS, ALIGN(boot_cpuid + 1, nthreads))); + pr_warn("Boot CPU %d >= nr_cpu_ids, adjusted nr_cpu_ids to %d\n", + boot_cpuid, nr_cpu_ids); + } + /* * PAPR defines "logical" PVR values for cpus that * meet various levels of the architecture: @@ -398,7 +411,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node, prop = of_get_flat_dt_prop(node, "cpu-version", NULL); if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) { identify_cpu(0, be32_to_cpup(prop)); - seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(prop)); + cpu_version = prop; } check_cpu_feature_properties(node); @@ -409,6 +422,12 @@ static int __init early_init_dt_scan_cpus(unsigned long node, } identical_pvr_fixup(node); + + // We can now add the CPU name & PVR to the hardware description + seq_buf_printf(&ppc_hw_desc, "%s 0x%04lx ", cur_cpu_spec->cpu_name, mfspr(SPRN_PVR)); + if (cpu_version) + seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(cpu_version)); + init_mmu_slb_size(node); #ifdef CONFIG_PPC64 @@ -846,9 +865,6 @@ void __init early_init_devtree(void *params) dt_cpu_ftrs_scan(); - // We can now add the CPU name & PVR to the hardware description - seq_buf_printf(&ppc_hw_desc, "%s 0x%04lx ", cur_cpu_spec->cpu_name, mfspr(SPRN_PVR)); - /* Retrieve CPU related informations from the flat tree * (altivec support, boot CPU ID, ...) */ diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index eddc031c4b95f4..46b9476d758249 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -310,8 +310,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = { [RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW] = { .name = "ibm,remove-pe-dma-window", }, - [RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS] = { - .name = "ibm,reset-pe-dma-windows", + [RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW] = { + /* + * Note: PAPR+ v2.13 7.3.31.4.1 spells this as + * "ibm,reset-pe-dma-windows" (plural), but RTAS + * implementations use the singular form in practice. + */ + .name = "ibm,reset-pe-dma-window", }, [RTAS_FNIDX__IBM_SCAN_LOG_DUMP] = { .name = "ibm,scan-log-dump", @@ -544,6 +549,21 @@ static int __init rtas_token_to_function_xarray_init(void) } arch_initcall(rtas_token_to_function_xarray_init); +/* + * For use by sys_rtas(), where the token value is provided by user + * space and we don't want to warn on failed lookups. + */ +static const struct rtas_function *rtas_token_to_function_untrusted(s32 token) +{ + return xa_load(&rtas_token_to_function_xarray, token); +} + +/* + * Reverse lookup for deriving the function descriptor from a + * known-good token value in contexts where the former is not already + * available. @token must be valid, e.g. derived from the result of a + * prior lookup against the function table. + */ static const struct rtas_function *rtas_token_to_function(s32 token) { const struct rtas_function *func; @@ -551,7 +571,7 @@ static const struct rtas_function *rtas_token_to_function(s32 token) if (WARN_ONCE(token < 0, "invalid token %d", token)) return NULL; - func = xa_load(&rtas_token_to_function_xarray, token); + func = rtas_token_to_function_untrusted(token); if (WARN_ONCE(!func, "unexpected failed lookup for token %d", token)) return NULL; @@ -1726,7 +1746,7 @@ static bool block_rtas_call(int token, int nargs, * If this token doesn't correspond to a function the kernel * understands, you're not allowed to call it. */ - func = rtas_token_to_function(token); + func = rtas_token_to_function_untrusted(token); if (!func) goto err; /* diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 20f72cd1d8138d..03eaad5949f141 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -950,6 +950,7 @@ void __init setup_arch(char **cmdline_p) mem_topology_setup(); /* Set max_mapnr before paging_init() */ set_max_mapnr(max_pfn); + high_memory = (void *)__va(max_low_pfn * PAGE_SIZE); /* * Release secondary cpus out of their spinloops at 0x60 now that diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 246201d0d879ef..394f209536cee0 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -834,6 +834,7 @@ static __init int pcpu_cpu_to_node(int cpu) unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); +DEFINE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged); void __init setup_per_cpu_areas(void) { @@ -876,6 +877,7 @@ void __init setup_per_cpu_areas(void) if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); + static_key_enable(&__percpu_first_chunk_is_paged.key); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) { __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 20e50586e8a26c..40f6751271d3d8 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -230,8 +230,10 @@ 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64 179 64 pread64 sys_pread64 +179 spu pread64 sys_pread64 180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64 180 64 pwrite64 sys_pwrite64 +180 spu pwrite64 sys_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -246,6 +248,7 @@ 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit 191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead 191 64 readahead sys_readahead +191 spu readahead sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64 194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64 @@ -293,6 +296,7 @@ 232 nospu set_tid_address sys_set_tid_address 233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64 233 64 fadvise64 sys_fadvise64 +233 spu fadvise64 sys_fadvise64 234 nospu exit_group sys_exit_group 235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie 236 common epoll_create sys_epoll_create @@ -502,7 +506,7 @@ 412 32 utimensat_time64 sys_utimensat sys_utimensat 413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend 419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 82010629cf887c..d8d6b4fd9a14cb 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -27,10 +27,22 @@ #include #include #include +#include #define NUM_FTRACE_TRAMPS 2 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS]; +unsigned long ftrace_call_adjust(unsigned long addr) +{ + if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end) + return 0; + + if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) + addr += MCOUNT_INSN_SIZE; + + return addr; +} + static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr, int link) { ppc_inst_t op; diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c index 7b85c3b460a3c0..12fab1803bcf45 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_pg.c +++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c @@ -37,6 +37,11 @@ #define NUM_FTRACE_TRAMPS 8 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS]; +unsigned long ftrace_call_adjust(unsigned long addr) +{ + return addr; +} + static ppc_inst_t ftrace_call_replace(unsigned long ip, unsigned long addr, int link) { diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S index 90701885762cf1..40677416d7b262 100644 --- a/arch/powerpc/kernel/trace/ftrace_entry.S +++ b/arch/powerpc/kernel/trace/ftrace_entry.S @@ -62,7 +62,7 @@ .endif /* Save previous stack pointer (r1) */ - addi r8, r1, SWITCH_FRAME_SIZE + addi r8, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE PPC_STL r8, GPR1(r1) .if \allregs == 1 @@ -182,7 +182,7 @@ ftrace_no_trace: mflr r3 mtctr r3 REST_GPR(3, r1) - addi r1, r1, SWITCH_FRAME_SIZE + addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE mtlr r0 bctr #endif diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 64ff37721fd06f..2de7f6dcd32b06 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1164,6 +1164,7 @@ void emulate_single_step(struct pt_regs *regs) __single_step_exception(regs); } +#ifdef CONFIG_PPC_FPU_REGS static inline int __parse_fpscr(unsigned long fpscr) { int ret = FPE_FLTUNK; @@ -1190,6 +1191,7 @@ static inline int __parse_fpscr(unsigned long fpscr) return ret; } +#endif static void parse_fpe(struct pt_regs *regs) { @@ -1437,10 +1439,12 @@ static int emulate_instruction(struct pt_regs *regs) return -EINVAL; } +#ifdef CONFIG_GENERIC_BUG int is_valid_bugaddr(unsigned long addr) { return is_kernel_addr(addr); } +#endif #ifdef CONFIG_MATH_EMULATION static int emulate_math(struct pt_regs *regs) diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S index 0085ae464dac9c..3b2479bd2f9a1d 100644 --- a/arch/powerpc/kernel/vdso/cacheflush.S +++ b/arch/powerpc/kernel/vdso/cacheflush.S @@ -30,7 +30,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) #ifdef CONFIG_PPC64 mflr r12 .cfi_register lr,r12 - get_datapage r10 + get_realdatapage r10, r11 mtlr r12 .cfi_restore lr #endif diff --git a/arch/powerpc/kernel/vdso/datapage.S b/arch/powerpc/kernel/vdso/datapage.S index db8e167f01667e..2b19b6201a33a8 100644 --- a/arch/powerpc/kernel/vdso/datapage.S +++ b/arch/powerpc/kernel/vdso/datapage.S @@ -28,7 +28,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) mflr r12 .cfi_register lr,r12 mr. r4,r3 - get_datapage r3 + get_realdatapage r3, r11 mtlr r12 #ifdef __powerpc64__ addi r3,r3,CFG_SYSCALL_MAP64 @@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq) .cfi_startproc mflr r12 .cfi_register lr,r12 - get_datapage r3 + get_realdatapage r3, r11 #ifndef __powerpc64__ lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3) #endif diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S index 48fc6658053aa4..894cb939cd2b31 100644 --- a/arch/powerpc/kernel/vdso/gettimeofday.S +++ b/arch/powerpc/kernel/vdso/gettimeofday.S @@ -38,11 +38,7 @@ .else addi r4, r5, VDSO_DATA_OFFSET .endif -#ifdef __powerpc64__ bl CFUNC(DOTSYM(\funct)) -#else - bl \funct -#endif PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) #ifdef __powerpc64__ PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1) diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S index 426e1ccc6971a3..8f57107000a247 100644 --- a/arch/powerpc/kernel/vdso/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso/vdso32.lds.S @@ -74,6 +74,8 @@ SECTIONS .got : { *(.got) } :text .plt : { *(.plt) } + .rela.dyn : { *(.rela .rela*) } + _end = .; __end = .; PROVIDE(end = .); @@ -87,7 +89,7 @@ SECTIONS *(.branch_lt) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) - *(.got1 .glink .iplt .rela*) + *(.got1 .glink .iplt) } } diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S index bda6c8cdd459c0..400819258c06b7 100644 --- a/arch/powerpc/kernel/vdso/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso/vdso64.lds.S @@ -69,7 +69,7 @@ SECTIONS .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr .eh_frame : { KEEP (*(.eh_frame)) } :text .gcc_except_table : { *(.gcc_except_table) } - .rela.dyn ALIGN(8) : { *(.rela.dyn) } + .rela.dyn ALIGN(8) : { *(.rela .rela*) } .got ALIGN(8) : { *(.got .toc) } @@ -86,7 +86,7 @@ SECTIONS *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) *(.opd) - *(.glink .iplt .plt .rela*) + *(.glink .iplt .plt) } } diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 4094e4c4c77a77..80b3f6e476b66b 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -33,6 +33,7 @@ _GLOBAL(store_vr_state) mfvscr v0 li r4, VRSTATE_VSCR stvx v0, r4, r3 + lvx v0, 0, r3 blr EXPORT_SYMBOL(store_vr_state) @@ -109,6 +110,7 @@ _GLOBAL(save_altivec) mfvscr v0 li r4,VRSTATE_VSCR stvx v0,r4,r7 + lvx v0,0,r7 blr #ifdef CONFIG_VSX diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 1c5970df323366..f420df7888a75c 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -281,7 +281,9 @@ SECTIONS * to deal with references from __bug_table */ .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) { + __exittext_begin = .; EXIT_TEXT + __exittext_end = .; } . = ALIGN(PAGE_SIZE); diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c index de64c796299121..005269ac3244c4 100644 --- a/arch/powerpc/kexec/core.c +++ b/arch/powerpc/kexec/core.c @@ -74,6 +74,9 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_STRUCT_SIZE(mmu_psize_def); VMCOREINFO_OFFSET(mmu_psize_def, shift); #endif + VMCOREINFO_SYMBOL(cur_cpu_spec); + VMCOREINFO_OFFSET(cpu_spec, mmu_features); + vmcoreinfo_append_str("NUMBER(RADIX_MMU)=%d\n", early_radix_enabled()); vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); } diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index a79e28c91e2be3..e465e448773768 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -26,6 +26,7 @@ #include #include #include /* _end */ +#include #include #include #include @@ -316,6 +317,16 @@ void default_machine_kexec(struct kimage *image) if (!kdump_in_progress()) kexec_prepare_cpus(); +#ifdef CONFIG_PPC_PSERIES + /* + * This must be done after other CPUs have shut down, otherwise they + * could execute the 'scv' instruction, which is not supported with + * reloc disabled (see configure_exceptions()). + */ + if (firmware_has_feature(FW_FEATURE_SET_MODE)) + pseries_disable_reloc_on_exc(); +#endif + printk("kexec: Starting switchover sequence.\n"); /* switch to a staticly allocated stack. Based on irq stack code. diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index efd0ebf70a5e60..fdfc2a62dd67df 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -28,6 +28,7 @@ #include #include "book3s.h" +#include "book3s_hv.h" #include "trace_hv.h" //#define DEBUG_RESIZE_HPT 1 @@ -347,7 +348,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, unsigned long v, orig_v, gr; __be64 *hptep; long int index; - int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR); + int virtmode = __kvmppc_get_msr_hv(vcpu) & (data ? MSR_DR : MSR_IR); if (kvm_is_radix(vcpu->kvm)) return kvmppc_mmu_radix_xlate(vcpu, eaddr, gpte, data, iswrite); @@ -385,7 +386,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, /* Get PP bits and key for permission check */ pp = gr & (HPTE_R_PP0 | HPTE_R_PP); - key = (vcpu->arch.shregs.msr & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS; + key = (__kvmppc_get_msr_hv(vcpu) & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS; key &= slb_v; /* Calculate permissions */ diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 572707858d65d4..10aacbf92466a5 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -15,6 +15,7 @@ #include #include +#include "book3s_hv.h" #include #include #include @@ -294,9 +295,9 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, } else { if (!(pte & _PAGE_PRIVILEGED)) { /* Check AMR/IAMR to see if strict mode is in force */ - if (vcpu->arch.amr & (1ul << 62)) + if (kvmppc_get_amr_hv(vcpu) & (1ul << 62)) gpte->may_read = 0; - if (vcpu->arch.amr & (1ul << 63)) + if (kvmppc_get_amr_hv(vcpu) & (1ul << 63)) gpte->may_write = 0; if (vcpu->arch.iamr & (1ul << 62)) gpte->may_execute = 0; diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 93b695b289e99a..395659f2f4c8ef 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -129,14 +129,16 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, } rcu_read_unlock(); - fdput(f); - - if (!found) + if (!found) { + fdput(f); return -EINVAL; + } table_group = iommu_group_get_iommudata(grp); - if (WARN_ON(!table_group)) + if (WARN_ON(!table_group)) { + fdput(f); return -EFAULT; + } for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { struct iommu_table *tbltmp = table_group->tables[i]; @@ -157,8 +159,10 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, break; } } - if (!tbl) + if (!tbl) { + fdput(f); return -EINVAL; + } rcu_read_lock(); list_for_each_entry_rcu(stit, &stt->iommu_tables, next) { @@ -169,6 +173,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, /* stit is being destroyed */ iommu_tce_table_put(tbl); rcu_read_unlock(); + fdput(f); return -ENOTTY; } /* @@ -176,6 +181,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, * its KVM reference counter and can return. */ rcu_read_unlock(); + fdput(f); return 0; } rcu_read_unlock(); @@ -183,6 +189,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, stit = kzalloc(sizeof(*stit), GFP_KERNEL); if (!stit) { iommu_tce_table_put(tbl); + fdput(f); return -ENOMEM; } @@ -191,6 +198,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, list_add_rcu(&stit->next, &stt->iommu_tables); + fdput(f); return 0; } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 130bafdb143088..1bb00c72154407 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -868,7 +868,7 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, /* Guests can't breakpoint the hypervisor */ if ((value1 & CIABR_PRIV) == CIABR_PRIV_HYPER) return H_P3; - vcpu->arch.ciabr = value1; + kvmppc_set_ciabr_hv(vcpu, value1); return H_SUCCESS; case H_SET_MODE_RESOURCE_SET_DAWR0: if (!kvmppc_power8_compatible(vcpu)) @@ -879,8 +879,8 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, return H_UNSUPPORTED_FLAG_START; if (value2 & DABRX_HYP) return H_P4; - vcpu->arch.dawr0 = value1; - vcpu->arch.dawrx0 = value2; + kvmppc_set_dawr0_hv(vcpu, value1); + kvmppc_set_dawrx0_hv(vcpu, value2); return H_SUCCESS; case H_SET_MODE_RESOURCE_SET_DAWR1: if (!kvmppc_power8_compatible(vcpu)) @@ -895,8 +895,8 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, return H_UNSUPPORTED_FLAG_START; if (value2 & DABRX_HYP) return H_P4; - vcpu->arch.dawr1 = value1; - vcpu->arch.dawrx1 = value2; + kvmppc_set_dawr1_hv(vcpu, value1); + kvmppc_set_dawrx1_hv(vcpu, value2); return H_SUCCESS; case H_SET_MODE_RESOURCE_ADDR_TRANS_MODE: /* @@ -1370,7 +1370,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) */ static void kvmppc_cede(struct kvm_vcpu *vcpu) { - vcpu->arch.shregs.msr |= MSR_EE; + __kvmppc_set_msr_hv(vcpu, __kvmppc_get_msr_hv(vcpu) | MSR_EE); vcpu->arch.ceded = 1; smp_mb(); if (vcpu->arch.prodded) { @@ -1544,7 +1544,7 @@ static int kvmppc_pmu_unavailable(struct kvm_vcpu *vcpu) if (!(vcpu->arch.hfscr_permitted & HFSCR_PM)) return EMULATE_FAIL; - vcpu->arch.hfscr |= HFSCR_PM; + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_PM); return RESUME_GUEST; } @@ -1554,7 +1554,7 @@ static int kvmppc_ebb_unavailable(struct kvm_vcpu *vcpu) if (!(vcpu->arch.hfscr_permitted & HFSCR_EBB)) return EMULATE_FAIL; - vcpu->arch.hfscr |= HFSCR_EBB; + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_EBB); return RESUME_GUEST; } @@ -1564,7 +1564,7 @@ static int kvmppc_tm_unavailable(struct kvm_vcpu *vcpu) if (!(vcpu->arch.hfscr_permitted & HFSCR_TM)) return EMULATE_FAIL; - vcpu->arch.hfscr |= HFSCR_TM; + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_TM); return RESUME_GUEST; } @@ -1585,7 +1585,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * That can happen due to a bug, or due to a machine check * occurring at just the wrong time. */ - if (vcpu->arch.shregs.msr & MSR_HV) { + if (__kvmppc_get_msr_hv(vcpu) & MSR_HV) { printk(KERN_EMERG "KVM trap in HV mode!\n"); printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n", vcpu->arch.trap, kvmppc_get_pc(vcpu), @@ -1636,7 +1636,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * so that it knows that the machine check occurred. */ if (!vcpu->kvm->arch.fwnmi_enabled) { - ulong flags = (vcpu->arch.shregs.msr & 0x083c0000) | + ulong flags = (__kvmppc_get_msr_hv(vcpu) & 0x083c0000) | (kvmppc_get_msr(vcpu) & SRR1_PREFIXED); kvmppc_core_queue_machine_check(vcpu, flags); r = RESUME_GUEST; @@ -1666,7 +1666,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * as a result of a hypervisor emulation interrupt * (e40) getting turned into a 700 by BML RTAS. */ - flags = (vcpu->arch.shregs.msr & 0x1f0000ull) | + flags = (__kvmppc_get_msr_hv(vcpu) & 0x1f0000ull) | (kvmppc_get_msr(vcpu) & SRR1_PREFIXED); kvmppc_core_queue_program(vcpu, flags); r = RESUME_GUEST; @@ -1676,7 +1676,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, { int i; - if (unlikely(vcpu->arch.shregs.msr & MSR_PR)) { + if (unlikely(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) { /* * Guest userspace executed sc 1. This can only be * reached by the P9 path because the old path @@ -1754,7 +1754,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, break; } - if (!(vcpu->arch.shregs.msr & MSR_DR)) + if (!(__kvmppc_get_msr_hv(vcpu) & MSR_DR)) vsid = vcpu->kvm->arch.vrma_slb_v; else vsid = vcpu->arch.fault_gpa; @@ -1778,7 +1778,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, long err; vcpu->arch.fault_dar = kvmppc_get_pc(vcpu); - vcpu->arch.fault_dsisr = vcpu->arch.shregs.msr & + vcpu->arch.fault_dsisr = __kvmppc_get_msr_hv(vcpu) & DSISR_SRR1_MATCH_64S; if (kvm_is_radix(vcpu->kvm) || !cpu_has_feature(CPU_FTR_ARCH_300)) { /* @@ -1787,7 +1787,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * hash fault handling below is v3 only (it uses ASDR * via fault_gpa). */ - if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE) + if (__kvmppc_get_msr_hv(vcpu) & HSRR1_HISI_WRITE) vcpu->arch.fault_dsisr |= DSISR_ISSTORE; r = RESUME_PAGE_FAULT; break; @@ -1801,7 +1801,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, break; } - if (!(vcpu->arch.shregs.msr & MSR_IR)) + if (!(__kvmppc_get_msr_hv(vcpu) & MSR_IR)) vsid = vcpu->kvm->arch.vrma_slb_v; else vsid = vcpu->arch.fault_gpa; @@ -1863,7 +1863,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * Otherwise, we just generate a program interrupt to the guest. */ case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: { - u64 cause = vcpu->arch.hfscr >> 56; + u64 cause = kvmppc_get_hfscr_hv(vcpu) >> 56; r = EMULATE_FAIL; if (cpu_has_feature(CPU_FTR_ARCH_300)) { @@ -1891,7 +1891,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, kvmppc_dump_regs(vcpu); printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n", vcpu->arch.trap, kvmppc_get_pc(vcpu), - vcpu->arch.shregs.msr); + __kvmppc_get_msr_hv(vcpu)); run->hw.hardware_exit_reason = vcpu->arch.trap; r = RESUME_HOST; break; @@ -1915,11 +1915,11 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) * That can happen due to a bug, or due to a machine check * occurring at just the wrong time. */ - if (vcpu->arch.shregs.msr & MSR_HV) { + if (__kvmppc_get_msr_hv(vcpu) & MSR_HV) { pr_emerg("KVM trap in HV mode while nested!\n"); pr_emerg("trap=0x%x | pc=0x%lx | msr=0x%llx\n", vcpu->arch.trap, kvmppc_get_pc(vcpu), - vcpu->arch.shregs.msr); + __kvmppc_get_msr_hv(vcpu)); kvmppc_dump_regs(vcpu); return RESUME_HOST; } @@ -1976,7 +1976,7 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) vcpu->arch.fault_dar = kvmppc_get_pc(vcpu); vcpu->arch.fault_dsisr = kvmppc_get_msr(vcpu) & DSISR_SRR1_MATCH_64S; - if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE) + if (__kvmppc_get_msr_hv(vcpu) & HSRR1_HISI_WRITE) vcpu->arch.fault_dsisr |= DSISR_ISSTORE; srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvmhv_nested_page_fault(vcpu); @@ -2207,64 +2207,64 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.dabrx); break; case KVM_REG_PPC_DSCR: - *val = get_reg_val(id, vcpu->arch.dscr); + *val = get_reg_val(id, kvmppc_get_dscr_hv(vcpu)); break; case KVM_REG_PPC_PURR: - *val = get_reg_val(id, vcpu->arch.purr); + *val = get_reg_val(id, kvmppc_get_purr_hv(vcpu)); break; case KVM_REG_PPC_SPURR: - *val = get_reg_val(id, vcpu->arch.spurr); + *val = get_reg_val(id, kvmppc_get_spurr_hv(vcpu)); break; case KVM_REG_PPC_AMR: - *val = get_reg_val(id, vcpu->arch.amr); + *val = get_reg_val(id, kvmppc_get_amr_hv(vcpu)); break; case KVM_REG_PPC_UAMOR: - *val = get_reg_val(id, vcpu->arch.uamor); + *val = get_reg_val(id, kvmppc_get_uamor_hv(vcpu)); break; case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1: i = id - KVM_REG_PPC_MMCR0; - *val = get_reg_val(id, vcpu->arch.mmcr[i]); + *val = get_reg_val(id, kvmppc_get_mmcr_hv(vcpu, i)); break; case KVM_REG_PPC_MMCR2: - *val = get_reg_val(id, vcpu->arch.mmcr[2]); + *val = get_reg_val(id, kvmppc_get_mmcr_hv(vcpu, 2)); break; case KVM_REG_PPC_MMCRA: - *val = get_reg_val(id, vcpu->arch.mmcra); + *val = get_reg_val(id, kvmppc_get_mmcra_hv(vcpu)); break; case KVM_REG_PPC_MMCRS: *val = get_reg_val(id, vcpu->arch.mmcrs); break; case KVM_REG_PPC_MMCR3: - *val = get_reg_val(id, vcpu->arch.mmcr[3]); + *val = get_reg_val(id, kvmppc_get_mmcr_hv(vcpu, 3)); break; case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8: i = id - KVM_REG_PPC_PMC1; - *val = get_reg_val(id, vcpu->arch.pmc[i]); + *val = get_reg_val(id, kvmppc_get_pmc_hv(vcpu, i)); break; case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2: i = id - KVM_REG_PPC_SPMC1; *val = get_reg_val(id, vcpu->arch.spmc[i]); break; case KVM_REG_PPC_SIAR: - *val = get_reg_val(id, vcpu->arch.siar); + *val = get_reg_val(id, kvmppc_get_siar_hv(vcpu)); break; case KVM_REG_PPC_SDAR: - *val = get_reg_val(id, vcpu->arch.sdar); + *val = get_reg_val(id, kvmppc_get_sdar_hv(vcpu)); break; case KVM_REG_PPC_SIER: - *val = get_reg_val(id, vcpu->arch.sier[0]); + *val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 0)); break; case KVM_REG_PPC_SIER2: - *val = get_reg_val(id, vcpu->arch.sier[1]); + *val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 1)); break; case KVM_REG_PPC_SIER3: - *val = get_reg_val(id, vcpu->arch.sier[2]); + *val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 2)); break; case KVM_REG_PPC_IAMR: - *val = get_reg_val(id, vcpu->arch.iamr); + *val = get_reg_val(id, kvmppc_get_iamr_hv(vcpu)); break; case KVM_REG_PPC_PSPB: - *val = get_reg_val(id, vcpu->arch.pspb); + *val = get_reg_val(id, kvmppc_get_pspb_hv(vcpu)); break; case KVM_REG_PPC_DPDES: /* @@ -2282,19 +2282,19 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.vcore->vtb); break; case KVM_REG_PPC_DAWR: - *val = get_reg_val(id, vcpu->arch.dawr0); + *val = get_reg_val(id, kvmppc_get_dawr0_hv(vcpu)); break; case KVM_REG_PPC_DAWRX: - *val = get_reg_val(id, vcpu->arch.dawrx0); + *val = get_reg_val(id, kvmppc_get_dawrx0_hv(vcpu)); break; case KVM_REG_PPC_DAWR1: - *val = get_reg_val(id, vcpu->arch.dawr1); + *val = get_reg_val(id, kvmppc_get_dawr1_hv(vcpu)); break; case KVM_REG_PPC_DAWRX1: - *val = get_reg_val(id, vcpu->arch.dawrx1); + *val = get_reg_val(id, kvmppc_get_dawrx1_hv(vcpu)); break; case KVM_REG_PPC_CIABR: - *val = get_reg_val(id, vcpu->arch.ciabr); + *val = get_reg_val(id, kvmppc_get_ciabr_hv(vcpu)); break; case KVM_REG_PPC_CSIGR: *val = get_reg_val(id, vcpu->arch.csigr); @@ -2312,7 +2312,7 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.acop); break; case KVM_REG_PPC_WORT: - *val = get_reg_val(id, vcpu->arch.wort); + *val = get_reg_val(id, kvmppc_get_wort_hv(vcpu)); break; case KVM_REG_PPC_TIDR: *val = get_reg_val(id, vcpu->arch.tid); @@ -2345,7 +2345,7 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.vcore->lpcr); break; case KVM_REG_PPC_PPR: - *val = get_reg_val(id, vcpu->arch.ppr); + *val = get_reg_val(id, kvmppc_get_ppr_hv(vcpu)); break; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM case KVM_REG_PPC_TFHAR: @@ -2425,6 +2425,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_PTCR: *val = get_reg_val(id, vcpu->kvm->arch.l1_ptcr); break; + case KVM_REG_PPC_FSCR: + *val = get_reg_val(id, kvmppc_get_fscr_hv(vcpu)); + break; default: r = -EINVAL; break; @@ -2453,64 +2456,64 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, vcpu->arch.dabrx = set_reg_val(id, *val) & ~DABRX_HYP; break; case KVM_REG_PPC_DSCR: - vcpu->arch.dscr = set_reg_val(id, *val); + kvmppc_set_dscr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_PURR: - vcpu->arch.purr = set_reg_val(id, *val); + kvmppc_set_purr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_SPURR: - vcpu->arch.spurr = set_reg_val(id, *val); + kvmppc_set_spurr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_AMR: - vcpu->arch.amr = set_reg_val(id, *val); + kvmppc_set_amr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_UAMOR: - vcpu->arch.uamor = set_reg_val(id, *val); + kvmppc_set_uamor_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1: i = id - KVM_REG_PPC_MMCR0; - vcpu->arch.mmcr[i] = set_reg_val(id, *val); + kvmppc_set_mmcr_hv(vcpu, i, set_reg_val(id, *val)); break; case KVM_REG_PPC_MMCR2: - vcpu->arch.mmcr[2] = set_reg_val(id, *val); + kvmppc_set_mmcr_hv(vcpu, 2, set_reg_val(id, *val)); break; case KVM_REG_PPC_MMCRA: - vcpu->arch.mmcra = set_reg_val(id, *val); + kvmppc_set_mmcra_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_MMCRS: vcpu->arch.mmcrs = set_reg_val(id, *val); break; case KVM_REG_PPC_MMCR3: - *val = get_reg_val(id, vcpu->arch.mmcr[3]); + kvmppc_set_mmcr_hv(vcpu, 3, set_reg_val(id, *val)); break; case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8: i = id - KVM_REG_PPC_PMC1; - vcpu->arch.pmc[i] = set_reg_val(id, *val); + kvmppc_set_pmc_hv(vcpu, i, set_reg_val(id, *val)); break; case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2: i = id - KVM_REG_PPC_SPMC1; vcpu->arch.spmc[i] = set_reg_val(id, *val); break; case KVM_REG_PPC_SIAR: - vcpu->arch.siar = set_reg_val(id, *val); + kvmppc_set_siar_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_SDAR: - vcpu->arch.sdar = set_reg_val(id, *val); + kvmppc_set_sdar_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_SIER: - vcpu->arch.sier[0] = set_reg_val(id, *val); + kvmppc_set_sier_hv(vcpu, 0, set_reg_val(id, *val)); break; case KVM_REG_PPC_SIER2: - vcpu->arch.sier[1] = set_reg_val(id, *val); + kvmppc_set_sier_hv(vcpu, 1, set_reg_val(id, *val)); break; case KVM_REG_PPC_SIER3: - vcpu->arch.sier[2] = set_reg_val(id, *val); + kvmppc_set_sier_hv(vcpu, 2, set_reg_val(id, *val)); break; case KVM_REG_PPC_IAMR: - vcpu->arch.iamr = set_reg_val(id, *val); + kvmppc_set_iamr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_PSPB: - vcpu->arch.pspb = set_reg_val(id, *val); + kvmppc_set_pspb_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DPDES: if (cpu_has_feature(CPU_FTR_ARCH_300)) @@ -2522,22 +2525,22 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, vcpu->arch.vcore->vtb = set_reg_val(id, *val); break; case KVM_REG_PPC_DAWR: - vcpu->arch.dawr0 = set_reg_val(id, *val); + kvmppc_set_dawr0_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DAWRX: - vcpu->arch.dawrx0 = set_reg_val(id, *val) & ~DAWRX_HYP; + kvmppc_set_dawrx0_hv(vcpu, set_reg_val(id, *val) & ~DAWRX_HYP); break; case KVM_REG_PPC_DAWR1: - vcpu->arch.dawr1 = set_reg_val(id, *val); + kvmppc_set_dawr1_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DAWRX1: - vcpu->arch.dawrx1 = set_reg_val(id, *val) & ~DAWRX_HYP; + kvmppc_set_dawrx1_hv(vcpu, set_reg_val(id, *val) & ~DAWRX_HYP); break; case KVM_REG_PPC_CIABR: - vcpu->arch.ciabr = set_reg_val(id, *val); + kvmppc_set_ciabr_hv(vcpu, set_reg_val(id, *val)); /* Don't allow setting breakpoints in hypervisor code */ - if ((vcpu->arch.ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER) - vcpu->arch.ciabr &= ~CIABR_PRIV; /* disable */ + if ((kvmppc_get_ciabr_hv(vcpu) & CIABR_PRIV) == CIABR_PRIV_HYPER) + kvmppc_set_ciabr_hv(vcpu, kvmppc_get_ciabr_hv(vcpu) & ~CIABR_PRIV); break; case KVM_REG_PPC_CSIGR: vcpu->arch.csigr = set_reg_val(id, *val); @@ -2555,7 +2558,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, vcpu->arch.acop = set_reg_val(id, *val); break; case KVM_REG_PPC_WORT: - vcpu->arch.wort = set_reg_val(id, *val); + kvmppc_set_wort_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_TIDR: vcpu->arch.tid = set_reg_val(id, *val); @@ -2615,7 +2618,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), false); break; case KVM_REG_PPC_PPR: - vcpu->arch.ppr = set_reg_val(id, *val); + kvmppc_set_ppr_hv(vcpu, set_reg_val(id, *val)); break; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM case KVM_REG_PPC_TFHAR: @@ -2699,6 +2702,9 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_PTCR: vcpu->kvm->arch.l1_ptcr = set_reg_val(id, *val); break; + case KVM_REG_PPC_FSCR: + kvmppc_set_fscr_hv(vcpu, set_reg_val(id, *val)); + break; default: r = -EINVAL; break; @@ -2916,19 +2922,20 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) vcpu->arch.shared_big_endian = false; #endif #endif - vcpu->arch.mmcr[0] = MMCR0_FC; + kvmppc_set_mmcr_hv(vcpu, 0, MMCR0_FC); + if (cpu_has_feature(CPU_FTR_ARCH_31)) { - vcpu->arch.mmcr[0] |= MMCR0_PMCCEXT; - vcpu->arch.mmcra = MMCRA_BHRB_DISABLE; + kvmppc_set_mmcr_hv(vcpu, 0, kvmppc_get_mmcr_hv(vcpu, 0) | MMCR0_PMCCEXT); + kvmppc_set_mmcra_hv(vcpu, MMCRA_BHRB_DISABLE); } - vcpu->arch.ctrl = CTRL_RUNLATCH; + kvmppc_set_ctrl_hv(vcpu, CTRL_RUNLATCH); /* default to host PVR, since we can't spoof it */ kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR)); spin_lock_init(&vcpu->arch.vpa_update_lock); spin_lock_init(&vcpu->arch.tbacct_lock); vcpu->arch.busy_preempt = TB_NIL; - vcpu->arch.shregs.msr = MSR_ME; + __kvmppc_set_msr_hv(vcpu, MSR_ME); vcpu->arch.intr_msr = MSR_SF | MSR_ME; /* @@ -2938,29 +2945,30 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) * don't set the HFSCR_MSGP bit, and that causes those instructions * to trap and then we emulate them. */ - vcpu->arch.hfscr = HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB | - HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP; + kvmppc_set_hfscr_hv(vcpu, HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB | + HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP); /* On POWER10 and later, allow prefixed instructions */ if (cpu_has_feature(CPU_FTR_ARCH_31)) - vcpu->arch.hfscr |= HFSCR_PREFIX; + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_PREFIX); if (cpu_has_feature(CPU_FTR_HVMODE)) { - vcpu->arch.hfscr &= mfspr(SPRN_HFSCR); + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) & mfspr(SPRN_HFSCR)); + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) - vcpu->arch.hfscr |= HFSCR_TM; + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_TM); #endif } if (cpu_has_feature(CPU_FTR_TM_COMP)) vcpu->arch.hfscr |= HFSCR_TM; - vcpu->arch.hfscr_permitted = vcpu->arch.hfscr; + vcpu->arch.hfscr_permitted = kvmppc_get_hfscr_hv(vcpu); /* * PM, EBB, TM are demand-faulted so start with it clear. */ - vcpu->arch.hfscr &= ~(HFSCR_PM | HFSCR_EBB | HFSCR_TM); + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) & ~(HFSCR_PM | HFSCR_EBB | HFSCR_TM)); kvmppc_mmu_book3s_hv_init(vcpu); @@ -4176,7 +4184,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, __this_cpu_write(cpu_in_guest, NULL); if (trap == BOOK3S_INTERRUPT_SYSCALL && - !(vcpu->arch.shregs.msr & MSR_PR)) { + !(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) { unsigned long req = kvmppc_get_gpr(vcpu, 3); /* @@ -4655,13 +4663,19 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, if (!nested) { kvmppc_core_prepare_to_enter(vcpu); - if (vcpu->arch.shregs.msr & MSR_EE) { - if (xive_interrupt_pending(vcpu)) + if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, + &vcpu->arch.pending_exceptions) || + xive_interrupt_pending(vcpu)) { + /* + * For nested HV, don't synthesize but always pass MER, + * the L0 will be able to optimise that more + * effectively than manipulating registers directly. + */ + if (!kvmhv_on_pseries() && (__kvmppc_get_msr_hv(vcpu) & MSR_EE)) kvmppc_inject_interrupt_hv(vcpu, - BOOK3S_INTERRUPT_EXTERNAL, 0); - } else if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, - &vcpu->arch.pending_exceptions)) { - lpcr |= LPCR_MER; + BOOK3S_INTERRUPT_EXTERNAL, 0); + else + lpcr |= LPCR_MER; } } else if (vcpu->arch.pending_exceptions || vcpu->arch.doorbell_request || @@ -4844,7 +4858,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) msr |= MSR_VSX; if ((cpu_has_feature(CPU_FTR_TM) || cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) && - (vcpu->arch.hfscr & HFSCR_TM)) + (kvmppc_get_hfscr_hv(vcpu) & HFSCR_TM)) msr |= MSR_TM; msr = msr_check_and_set(msr); @@ -4868,7 +4882,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) if (run->exit_reason == KVM_EXIT_PAPR_HCALL) { accumulate_time(vcpu, &vcpu->arch.hcall); - if (WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_PR)) { + if (WARN_ON_ONCE(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) { /* * These should have been caught reflected * into the guest by now. Final sanity check: diff --git a/arch/powerpc/kvm/book3s_hv.h b/arch/powerpc/kvm/book3s_hv.h index 2f2e59d7d433a6..95241764dfb4eb 100644 --- a/arch/powerpc/kvm/book3s_hv.h +++ b/arch/powerpc/kvm/book3s_hv.h @@ -50,3 +50,71 @@ void accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next); #define start_timing(vcpu, next) do {} while (0) #define end_timing(vcpu) do {} while (0) #endif + +static inline void __kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 val) +{ + vcpu->arch.shregs.msr = val; +} + +static inline u64 __kvmppc_get_msr_hv(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.shregs.msr; +} + +#define KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_SET(reg, size) \ +static inline void kvmppc_set_##reg ##_hv(struct kvm_vcpu *vcpu, u##size val) \ +{ \ + vcpu->arch.reg = val; \ +} + +#define KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_GET(reg, size) \ +static inline u##size kvmppc_get_##reg ##_hv(struct kvm_vcpu *vcpu) \ +{ \ + return vcpu->arch.reg; \ +} + +#define KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(reg, size) \ + KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_SET(reg, size) \ + KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_GET(reg, size) \ + +#define KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_SET(reg, size) \ +static inline void kvmppc_set_##reg ##_hv(struct kvm_vcpu *vcpu, int i, u##size val) \ +{ \ + vcpu->arch.reg[i] = val; \ +} + +#define KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_GET(reg, size) \ +static inline u##size kvmppc_get_##reg ##_hv(struct kvm_vcpu *vcpu, int i) \ +{ \ + return vcpu->arch.reg[i]; \ +} + +#define KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(reg, size) \ + KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_SET(reg, size) \ + KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_GET(reg, size) \ + +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(mmcra, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(hfscr, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(fscr, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dscr, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(purr, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(spurr, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(amr, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(uamor, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(siar, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(sdar, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(iamr, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawr0, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawr1, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawrx0, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawrx1, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ciabr, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(wort, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ppr, 64) +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ctrl, 64) + +KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(mmcr, 64) +KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(sier, 64) +KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(pmc, 32) + +KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(pspb, 32) diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 0f5b021fa5590b..663f5222f3d06d 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -32,6 +32,7 @@ #include "book3s_xics.h" #include "book3s_xive.h" +#include "book3s_hv.h" /* * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206) @@ -510,7 +511,7 @@ void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr) */ if ((msr & MSR_TS_MASK) == MSR_TS_MASK) msr &= ~MSR_TS_MASK; - vcpu->arch.shregs.msr = msr; + __kvmppc_set_msr_hv(vcpu, msr); kvmppc_end_cede(vcpu); } EXPORT_SYMBOL_GPL(kvmppc_set_msr_hv); @@ -548,7 +549,7 @@ static void inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags) kvmppc_set_srr0(vcpu, pc); kvmppc_set_srr1(vcpu, (msr & SRR1_MSR_BITS) | srr1_flags); kvmppc_set_pc(vcpu, new_pc); - vcpu->arch.shregs.msr = new_msr; + __kvmppc_set_msr_hv(vcpu, new_msr); } void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 7197c8256668b8..6cef200c2404df 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -1990,8 +1990,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, break; r = -ENXIO; - if (!xive_enabled()) + if (!xive_enabled()) { + fdput(f); break; + } r = -EPERM; dev = kvm_device_from_filp(f.file); diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 51ad0397c17abf..0ab65eeb93ee3a 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -45,7 +45,7 @@ obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o # so it is only needed for modules, and only for older linkers which # do not support --save-restore-funcs ifndef CONFIG_LD_IS_BFD -extra-$(CONFIG_PPC64) += crtsavres.o +always-$(CONFIG_PPC64) += crtsavres.o endif obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \ @@ -76,7 +76,7 @@ obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o obj-$(CONFIG_ALTIVEC) += xor_vmx.o xor_vmx_glue.o -CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec) +CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec) # Enable CFLAGS_xor_vmx.o += -isystem $(shell $(CC) -print-file-name=include) diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c index 6dd2f46bd3ef64..8830267789c9c0 100644 --- a/arch/powerpc/lib/qspinlock.c +++ b/arch/powerpc/lib/qspinlock.c @@ -715,7 +715,15 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b } release: - qnodesp->count--; /* release the node */ + /* + * Clear the lock before releasing the node, as another CPU might see stale + * values if an interrupt occurs after we increment qnodesp->count + * but before node->lock is initialized. The barrier ensures that + * there are no further stores to the node after it has been released. + */ + node->lock = NULL; + barrier(); + qnodesp->count--; } void queued_spin_lock_slowpath(struct qspinlock *lock) diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index a4ab8625061a66..6af97dc0f6d5a8 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -586,6 +586,8 @@ static int do_fp_load(struct instruction_op *op, unsigned long ea, } u; nb = GETSIZE(op->type); + if (nb > sizeof(u)) + return -EINVAL; if (!address_ok(regs, ea, nb)) return -EFAULT; rn = op->reg; @@ -636,6 +638,8 @@ static int do_fp_store(struct instruction_op *op, unsigned long ea, } u; nb = GETSIZE(op->type); + if (nb > sizeof(u)) + return -EINVAL; if (!address_ok(regs, ea, nb)) return -EFAULT; rn = op->reg; @@ -680,6 +684,9 @@ static nokprobe_inline int do_vec_load(int rn, unsigned long ea, u8 b[sizeof(__vector128)]; } u = {}; + if (size > sizeof(u)) + return -EINVAL; + if (!address_ok(regs, ea & ~0xfUL, 16)) return -EFAULT; /* align to multiple of size */ @@ -707,6 +714,9 @@ static nokprobe_inline int do_vec_store(int rn, unsigned long ea, u8 b[sizeof(__vector128)]; } u; + if (size > sizeof(u)) + return -EINVAL; + if (!address_ok(regs, ea & ~0xfUL, 16)) return -EFAULT; /* align to multiple of size */ diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 8f8a62d3ff4de4..5b4cbb25d9cf77 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -130,7 +130,7 @@ void set_pud_at(struct mm_struct *mm, unsigned long addr, WARN_ON(pte_hw_valid(pud_pte(*pudp))); assert_spin_locked(pud_lockptr(mm, pudp)); - WARN_ON(!(pud_large(pud))); + WARN_ON(!(pud_leaf(pud))); #endif trace_hugepage_set_pud(addr, pud_val(pud)); return set_pte_at(mm, addr, pudp_ptep(pudp), pud_pte(pud)); @@ -170,6 +170,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, { unsigned long old_pmd; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, _PAGE_INVALID); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return __pmd(old_pmd); @@ -542,6 +543,7 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, set_pte_at(vma->vm_mm, addr, ptep, pte); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * For hash translation mode, we use the deposited table to store hash slot * information and they are stored at PTRS_PER_PMD offset from related pmd @@ -563,6 +565,7 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, return true; } +#endif /* * Does the CPU support tlbie? diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c index 119ef491f79760..d3a7726ecf512c 100644 --- a/arch/powerpc/mm/init-common.c +++ b/arch/powerpc/mm/init-common.c @@ -126,7 +126,7 @@ void pgtable_cache_add(unsigned int shift) * as to leave enough 0 bits in the address to contain it. */ unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1, HUGEPD_SHIFT_MASK + 1); - struct kmem_cache *new; + struct kmem_cache *new = NULL; /* It would be nice if this was a BUILD_BUG_ON(), but at the * moment, gcc doesn't seem to recognize is_power_of_2 as a @@ -139,7 +139,8 @@ void pgtable_cache_add(unsigned int shift) align = max_t(unsigned long, align, minalign); name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift); - new = kmem_cache_create(name, table_size, align, 0, ctor(shift)); + if (name) + new = kmem_cache_create(name, table_size, align, 0, ctor(shift)); if (!new) panic("Could not allocate pgtable cache for order %d", shift); diff --git a/arch/powerpc/mm/kasan/init_32.c b/arch/powerpc/mm/kasan/init_32.c index a70828a6d9357d..aa9aa11927b2f8 100644 --- a/arch/powerpc/mm/kasan/init_32.c +++ b/arch/powerpc/mm/kasan/init_32.c @@ -64,6 +64,7 @@ int __init __weak kasan_init_region(void *start, size_t size) if (ret) return ret; + k_start = k_start & PAGE_MASK; block = memblock_alloc(k_end - k_start, PAGE_SIZE); if (!block) return -ENOMEM; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 07e8f4f1e07f89..9dbef559af4cbf 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -287,8 +287,6 @@ void __init mem_init(void) swiotlb_init(ppc_swiotlb_enable, ppc_swiotlb_flags); #endif - high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - kasan_late_init(); memblock_free_all(); diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index 7f9ff0640124af..72341b9fb5521f 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -181,3 +181,8 @@ static inline bool debug_pagealloc_enabled_or_kfence(void) { return IS_ENABLED(CONFIG_KFENCE) || debug_pagealloc_enabled(); } + +#ifdef CONFIG_MEMORY_HOTPLUG +int create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot); +#endif diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c index a642a79298929d..a947dff35d6517 100644 --- a/arch/powerpc/mm/nohash/8xx.c +++ b/arch/powerpc/mm/nohash/8xx.c @@ -92,7 +92,8 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa, return -EINVAL; set_huge_pte_at(&init_mm, va, ptep, - pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)), psize); + pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)), + 1UL << mmu_psize_to_shift(psize)); return 0; } @@ -148,11 +149,11 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) mmu_mapin_immr(); - mmu_mapin_ram_chunk(0, boundary, PAGE_KERNEL_TEXT, true); + mmu_mapin_ram_chunk(0, boundary, PAGE_KERNEL_X, true); if (debug_pagealloc_enabled_or_kfence()) { top = boundary; } else { - mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL_TEXT, true); + mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL_X, true); mmu_mapin_ram_chunk(einittext8, top, PAGE_KERNEL, true); } diff --git a/arch/powerpc/mm/nohash/Makefile b/arch/powerpc/mm/nohash/Makefile index f3894e79d5f700..24b445a5fcaccd 100644 --- a/arch/powerpc/mm/nohash/Makefile +++ b/arch/powerpc/mm/nohash/Makefile @@ -3,7 +3,7 @@ ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) obj-y += mmu_context.o tlb.o tlb_low.o kup.o -obj-$(CONFIG_PPC_BOOK3E_64) += tlb_low_64e.o book3e_pgtable.o +obj-$(CONFIG_PPC_BOOK3E_64) += tlb_64e.o tlb_low_64e.o book3e_pgtable.o obj-$(CONFIG_40x) += 40x.o obj-$(CONFIG_44x) += 44x.o obj-$(CONFIG_PPC_8xx) += 8xx.o diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c index 5ffa0af4328af8..f57dc721d0636a 100644 --- a/arch/powerpc/mm/nohash/tlb.c +++ b/arch/powerpc/mm/nohash/tlb.c @@ -110,28 +110,6 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = { }; #endif -/* The variables below are currently only used on 64-bit Book3E - * though this will probably be made common with other nohash - * implementations at some point - */ -#ifdef CONFIG_PPC64 - -int mmu_pte_psize; /* Page size used for PTE pages */ -int mmu_vmemmap_psize; /* Page size used for the virtual mem map */ -int book3e_htw_mode; /* HW tablewalk? Value is PPC_HTW_* */ -unsigned long linear_map_top; /* Top of linear mapping */ - - -/* - * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug - * exceptions. This is used for bolted and e6500 TLB miss handlers which - * do not modify this SPRG in the TLB miss code; for other TLB miss handlers, - * this is set to zero. - */ -int extlb_level_exc; - -#endif /* CONFIG_PPC64 */ - #ifdef CONFIG_PPC_E500 /* next_tlbcam_idx is used to round-robin tlbcam entry assignment */ DEFINE_PER_CPU(int, next_tlbcam_idx); @@ -358,381 +336,7 @@ void tlb_flush(struct mmu_gather *tlb) flush_tlb_mm(tlb->mm); } -/* - * Below are functions specific to the 64-bit variant of Book3E though that - * may change in the future - */ - -#ifdef CONFIG_PPC64 - -/* - * Handling of virtual linear page tables or indirect TLB entries - * flushing when PTE pages are freed - */ -void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address) -{ - int tsize = mmu_psize_defs[mmu_pte_psize].enc; - - if (book3e_htw_mode != PPC_HTW_NONE) { - unsigned long start = address & PMD_MASK; - unsigned long end = address + PMD_SIZE; - unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift; - - /* This isn't the most optimal, ideally we would factor out the - * while preempt & CPU mask mucking around, or even the IPI but - * it will do for now - */ - while (start < end) { - __flush_tlb_page(tlb->mm, start, tsize, 1); - start += size; - } - } else { - unsigned long rmask = 0xf000000000000000ul; - unsigned long rid = (address & rmask) | 0x1000000000000000ul; - unsigned long vpte = address & ~rmask; - - vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful; - vpte |= rid; - __flush_tlb_page(tlb->mm, vpte, tsize, 0); - } -} - -static void __init setup_page_sizes(void) -{ - unsigned int tlb0cfg; - unsigned int tlb0ps; - unsigned int eptcfg; - int i, psize; - -#ifdef CONFIG_PPC_E500 - unsigned int mmucfg = mfspr(SPRN_MMUCFG); - int fsl_mmu = mmu_has_feature(MMU_FTR_TYPE_FSL_E); - - if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) { - unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG); - unsigned int min_pg, max_pg; - - min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT; - max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT; - - for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { - struct mmu_psize_def *def; - unsigned int shift; - - def = &mmu_psize_defs[psize]; - shift = def->shift; - - if (shift == 0 || shift & 1) - continue; - - /* adjust to be in terms of 4^shift Kb */ - shift = (shift - 10) >> 1; - - if ((shift >= min_pg) && (shift <= max_pg)) - def->flags |= MMU_PAGE_SIZE_DIRECT; - } - - goto out; - } - - if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) { - u32 tlb1cfg, tlb1ps; - - tlb0cfg = mfspr(SPRN_TLB0CFG); - tlb1cfg = mfspr(SPRN_TLB1CFG); - tlb1ps = mfspr(SPRN_TLB1PS); - eptcfg = mfspr(SPRN_EPTCFG); - - if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT)) - book3e_htw_mode = PPC_HTW_E6500; - - /* - * We expect 4K subpage size and unrestricted indirect size. - * The lack of a restriction on indirect size is a Freescale - * extension, indicated by PSn = 0 but SPSn != 0. - */ - if (eptcfg != 2) - book3e_htw_mode = PPC_HTW_NONE; - - for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { - struct mmu_psize_def *def = &mmu_psize_defs[psize]; - - if (!def->shift) - continue; - - if (tlb1ps & (1U << (def->shift - 10))) { - def->flags |= MMU_PAGE_SIZE_DIRECT; - - if (book3e_htw_mode && psize == MMU_PAGE_2M) - def->flags |= MMU_PAGE_SIZE_INDIRECT; - } - } - - goto out; - } -#endif - - tlb0cfg = mfspr(SPRN_TLB0CFG); - tlb0ps = mfspr(SPRN_TLB0PS); - eptcfg = mfspr(SPRN_EPTCFG); - - /* Look for supported direct sizes */ - for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { - struct mmu_psize_def *def = &mmu_psize_defs[psize]; - - if (tlb0ps & (1U << (def->shift - 10))) - def->flags |= MMU_PAGE_SIZE_DIRECT; - } - - /* Indirect page sizes supported ? */ - if ((tlb0cfg & TLBnCFG_IND) == 0 || - (tlb0cfg & TLBnCFG_PT) == 0) - goto out; - - book3e_htw_mode = PPC_HTW_IBM; - - /* Now, we only deal with one IND page size for each - * direct size. Hopefully all implementations today are - * unambiguous, but we might want to be careful in the - * future. - */ - for (i = 0; i < 3; i++) { - unsigned int ps, sps; - - sps = eptcfg & 0x1f; - eptcfg >>= 5; - ps = eptcfg & 0x1f; - eptcfg >>= 5; - if (!ps || !sps) - continue; - for (psize = 0; psize < MMU_PAGE_COUNT; psize++) { - struct mmu_psize_def *def = &mmu_psize_defs[psize]; - - if (ps == (def->shift - 10)) - def->flags |= MMU_PAGE_SIZE_INDIRECT; - if (sps == (def->shift - 10)) - def->ind = ps + 10; - } - } - -out: - /* Cleanup array and print summary */ - pr_info("MMU: Supported page sizes\n"); - for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { - struct mmu_psize_def *def = &mmu_psize_defs[psize]; - const char *__page_type_names[] = { - "unsupported", - "direct", - "indirect", - "direct & indirect" - }; - if (def->flags == 0) { - def->shift = 0; - continue; - } - pr_info(" %8ld KB as %s\n", 1ul << (def->shift - 10), - __page_type_names[def->flags & 0x3]); - } -} - -static void __init setup_mmu_htw(void) -{ - /* - * If we want to use HW tablewalk, enable it by patching the TLB miss - * handlers to branch to the one dedicated to it. - */ - - switch (book3e_htw_mode) { - case PPC_HTW_IBM: - patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e); - patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e); - break; -#ifdef CONFIG_PPC_E500 - case PPC_HTW_E6500: - extlb_level_exc = EX_TLB_SIZE; - patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e); - patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e); - break; -#endif - } - pr_info("MMU: Book3E HW tablewalk %s\n", - book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported"); -} - -/* - * Early initialization of the MMU TLB code - */ -static void early_init_this_mmu(void) -{ - unsigned int mas4; - - /* Set MAS4 based on page table setting */ - - mas4 = 0x4 << MAS4_WIMGED_SHIFT; - switch (book3e_htw_mode) { - case PPC_HTW_E6500: - mas4 |= MAS4_INDD; - mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT; - mas4 |= MAS4_TLBSELD(1); - mmu_pte_psize = MMU_PAGE_2M; - break; - - case PPC_HTW_IBM: - mas4 |= MAS4_INDD; - mas4 |= BOOK3E_PAGESZ_1M << MAS4_TSIZED_SHIFT; - mmu_pte_psize = MMU_PAGE_1M; - break; - - case PPC_HTW_NONE: - mas4 |= BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT; - mmu_pte_psize = mmu_virtual_psize; - break; - } - mtspr(SPRN_MAS4, mas4); - -#ifdef CONFIG_PPC_E500 - if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { - unsigned int num_cams; - bool map = true; - - /* use a quarter of the TLBCAM for bolted linear map */ - num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4; - - /* - * Only do the mapping once per core, or else the - * transient mapping would cause problems. - */ -#ifdef CONFIG_SMP - if (hweight32(get_tensr()) > 1) - map = false; -#endif - - if (map) - linear_map_top = map_mem_in_cams(linear_map_top, - num_cams, false, true); - } -#endif - - /* A sync won't hurt us after mucking around with - * the MMU configuration - */ - mb(); -} - -static void __init early_init_mmu_global(void) -{ - /* XXX This should be decided at runtime based on supported - * page sizes in the TLB, but for now let's assume 16M is - * always there and a good fit (which it probably is) - * - * Freescale booke only supports 4K pages in TLB0, so use that. - */ - if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) - mmu_vmemmap_psize = MMU_PAGE_4K; - else - mmu_vmemmap_psize = MMU_PAGE_16M; - - /* XXX This code only checks for TLB 0 capabilities and doesn't - * check what page size combos are supported by the HW. It - * also doesn't handle the case where a separate array holds - * the IND entries from the array loaded by the PT. - */ - /* Look for supported page sizes */ - setup_page_sizes(); - - /* Look for HW tablewalk support */ - setup_mmu_htw(); - -#ifdef CONFIG_PPC_E500 - if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { - if (book3e_htw_mode == PPC_HTW_NONE) { - extlb_level_exc = EX_TLB_SIZE; - patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e); - patch_exception(0x1e0, - exc_instruction_tlb_miss_bolted_book3e); - } - } -#endif - - /* Set the global containing the top of the linear mapping - * for use by the TLB miss code - */ - linear_map_top = memblock_end_of_DRAM(); - - ioremap_bot = IOREMAP_BASE; -} - -static void __init early_mmu_set_memory_limit(void) -{ -#ifdef CONFIG_PPC_E500 - if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { - /* - * Limit memory so we dont have linear faults. - * Unlike memblock_set_current_limit, which limits - * memory available during early boot, this permanently - * reduces the memory available to Linux. We need to - * do this because highmem is not supported on 64-bit. - */ - memblock_enforce_memory_limit(linear_map_top); - } -#endif - - memblock_set_current_limit(linear_map_top); -} - -/* boot cpu only */ -void __init early_init_mmu(void) -{ - early_init_mmu_global(); - early_init_this_mmu(); - early_mmu_set_memory_limit(); -} - -void early_init_mmu_secondary(void) -{ - early_init_this_mmu(); -} - -void setup_initial_memory_limit(phys_addr_t first_memblock_base, - phys_addr_t first_memblock_size) -{ - /* On non-FSL Embedded 64-bit, we adjust the RMA size to match - * the bolted TLB entry. We know for now that only 1G - * entries are supported though that may eventually - * change. - * - * on FSL Embedded 64-bit, usually all RAM is bolted, but with - * unusual memory sizes it's possible for some RAM to not be mapped - * (such RAM is not used at all by Linux, since we don't support - * highmem on 64-bit). We limit ppc64_rma_size to what would be - * mappable if this memblock is the only one. Additional memblocks - * can only increase, not decrease, the amount that ends up getting - * mapped. We still limit max to 1G even if we'll eventually map - * more. This is due to what the early init code is set up to do. - * - * We crop it to the size of the first MEMBLOCK to - * avoid going over total available memory just in case... - */ -#ifdef CONFIG_PPC_E500 - if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { - unsigned long linear_sz; - unsigned int num_cams; - - /* use a quarter of the TLBCAM for bolted linear map */ - num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4; - - linear_sz = map_mem_in_cams(first_memblock_size, num_cams, - true, true); - - ppc64_rma_size = min_t(u64, linear_sz, 0x40000000); - } else -#endif - ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000); - - /* Finally limit subsequent allocations */ - memblock_set_current_limit(first_memblock_base + ppc64_rma_size); -} -#else /* ! CONFIG_PPC64 */ +#ifndef CONFIG_PPC64 void __init early_init_mmu(void) { unsigned long root = of_get_flat_dt_root(); diff --git a/arch/powerpc/mm/nohash/tlb_64e.c b/arch/powerpc/mm/nohash/tlb_64e.c new file mode 100644 index 00000000000000..b6af3ec4d001dc --- /dev/null +++ b/arch/powerpc/mm/nohash/tlb_64e.c @@ -0,0 +1,361 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright 2008,2009 Ben Herrenschmidt + * IBM Corp. + * + * Derived from arch/ppc/mm/init.c: + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au) + * and Cort Dougan (PReP) (cort@cs.nmt.edu) + * Copyright (C) 1996 Paul Mackerras + * + * Derived from "arch/i386/mm/init.c" + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + */ + +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include + +/* The variables below are currently only used on 64-bit Book3E + * though this will probably be made common with other nohash + * implementations at some point + */ +static int mmu_pte_psize; /* Page size used for PTE pages */ +int mmu_vmemmap_psize; /* Page size used for the virtual mem map */ +int book3e_htw_mode; /* HW tablewalk? Value is PPC_HTW_* */ +unsigned long linear_map_top; /* Top of linear mapping */ + + +/* + * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug + * exceptions. This is used for bolted and e6500 TLB miss handlers which + * do not modify this SPRG in the TLB miss code; for other TLB miss handlers, + * this is set to zero. + */ +int extlb_level_exc; + +/* + * Handling of virtual linear page tables or indirect TLB entries + * flushing when PTE pages are freed + */ +void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address) +{ + int tsize = mmu_psize_defs[mmu_pte_psize].enc; + + if (book3e_htw_mode != PPC_HTW_NONE) { + unsigned long start = address & PMD_MASK; + unsigned long end = address + PMD_SIZE; + unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift; + + /* This isn't the most optimal, ideally we would factor out the + * while preempt & CPU mask mucking around, or even the IPI but + * it will do for now + */ + while (start < end) { + __flush_tlb_page(tlb->mm, start, tsize, 1); + start += size; + } + } else { + unsigned long rmask = 0xf000000000000000ul; + unsigned long rid = (address & rmask) | 0x1000000000000000ul; + unsigned long vpte = address & ~rmask; + + vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful; + vpte |= rid; + __flush_tlb_page(tlb->mm, vpte, tsize, 0); + } +} + +static void __init setup_page_sizes(void) +{ + unsigned int tlb0cfg; + unsigned int eptcfg; + int psize; + +#ifdef CONFIG_PPC_E500 + unsigned int mmucfg = mfspr(SPRN_MMUCFG); + int fsl_mmu = mmu_has_feature(MMU_FTR_TYPE_FSL_E); + + if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) { + unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG); + unsigned int min_pg, max_pg; + + min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT; + max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT; + + for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { + struct mmu_psize_def *def; + unsigned int shift; + + def = &mmu_psize_defs[psize]; + shift = def->shift; + + if (shift == 0 || shift & 1) + continue; + + /* adjust to be in terms of 4^shift Kb */ + shift = (shift - 10) >> 1; + + if ((shift >= min_pg) && (shift <= max_pg)) + def->flags |= MMU_PAGE_SIZE_DIRECT; + } + + goto out; + } + + if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) { + u32 tlb1cfg, tlb1ps; + + tlb0cfg = mfspr(SPRN_TLB0CFG); + tlb1cfg = mfspr(SPRN_TLB1CFG); + tlb1ps = mfspr(SPRN_TLB1PS); + eptcfg = mfspr(SPRN_EPTCFG); + + if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT)) + book3e_htw_mode = PPC_HTW_E6500; + + /* + * We expect 4K subpage size and unrestricted indirect size. + * The lack of a restriction on indirect size is a Freescale + * extension, indicated by PSn = 0 but SPSn != 0. + */ + if (eptcfg != 2) + book3e_htw_mode = PPC_HTW_NONE; + + for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { + struct mmu_psize_def *def = &mmu_psize_defs[psize]; + + if (!def->shift) + continue; + + if (tlb1ps & (1U << (def->shift - 10))) { + def->flags |= MMU_PAGE_SIZE_DIRECT; + + if (book3e_htw_mode && psize == MMU_PAGE_2M) + def->flags |= MMU_PAGE_SIZE_INDIRECT; + } + } + + goto out; + } +#endif +out: + /* Cleanup array and print summary */ + pr_info("MMU: Supported page sizes\n"); + for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { + struct mmu_psize_def *def = &mmu_psize_defs[psize]; + const char *__page_type_names[] = { + "unsupported", + "direct", + "indirect", + "direct & indirect" + }; + if (def->flags == 0) { + def->shift = 0; + continue; + } + pr_info(" %8ld KB as %s\n", 1ul << (def->shift - 10), + __page_type_names[def->flags & 0x3]); + } +} + +static void __init setup_mmu_htw(void) +{ + /* + * If we want to use HW tablewalk, enable it by patching the TLB miss + * handlers to branch to the one dedicated to it. + */ + + switch (book3e_htw_mode) { +#ifdef CONFIG_PPC_E500 + case PPC_HTW_E6500: + extlb_level_exc = EX_TLB_SIZE; + patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e); + patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e); + break; +#endif + } + pr_info("MMU: Book3E HW tablewalk %s\n", + book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported"); +} + +/* + * Early initialization of the MMU TLB code + */ +static void early_init_this_mmu(void) +{ + unsigned int mas4; + + /* Set MAS4 based on page table setting */ + + mas4 = 0x4 << MAS4_WIMGED_SHIFT; + switch (book3e_htw_mode) { + case PPC_HTW_E6500: + mas4 |= MAS4_INDD; + mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT; + mas4 |= MAS4_TLBSELD(1); + mmu_pte_psize = MMU_PAGE_2M; + break; + + case PPC_HTW_NONE: + mas4 |= BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT; + mmu_pte_psize = mmu_virtual_psize; + break; + } + mtspr(SPRN_MAS4, mas4); + +#ifdef CONFIG_PPC_E500 + if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { + unsigned int num_cams; + bool map = true; + + /* use a quarter of the TLBCAM for bolted linear map */ + num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4; + + /* + * Only do the mapping once per core, or else the + * transient mapping would cause problems. + */ +#ifdef CONFIG_SMP + if (hweight32(get_tensr()) > 1) + map = false; +#endif + + if (map) + linear_map_top = map_mem_in_cams(linear_map_top, + num_cams, false, true); + } +#endif + + /* A sync won't hurt us after mucking around with + * the MMU configuration + */ + mb(); +} + +static void __init early_init_mmu_global(void) +{ + /* XXX This should be decided at runtime based on supported + * page sizes in the TLB, but for now let's assume 16M is + * always there and a good fit (which it probably is) + * + * Freescale booke only supports 4K pages in TLB0, so use that. + */ + if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) + mmu_vmemmap_psize = MMU_PAGE_4K; + else + mmu_vmemmap_psize = MMU_PAGE_16M; + + /* XXX This code only checks for TLB 0 capabilities and doesn't + * check what page size combos are supported by the HW. It + * also doesn't handle the case where a separate array holds + * the IND entries from the array loaded by the PT. + */ + /* Look for supported page sizes */ + setup_page_sizes(); + + /* Look for HW tablewalk support */ + setup_mmu_htw(); + +#ifdef CONFIG_PPC_E500 + if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { + if (book3e_htw_mode == PPC_HTW_NONE) { + extlb_level_exc = EX_TLB_SIZE; + patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e); + patch_exception(0x1e0, + exc_instruction_tlb_miss_bolted_book3e); + } + } +#endif + + /* Set the global containing the top of the linear mapping + * for use by the TLB miss code + */ + linear_map_top = memblock_end_of_DRAM(); + + ioremap_bot = IOREMAP_BASE; +} + +static void __init early_mmu_set_memory_limit(void) +{ +#ifdef CONFIG_PPC_E500 + if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { + /* + * Limit memory so we dont have linear faults. + * Unlike memblock_set_current_limit, which limits + * memory available during early boot, this permanently + * reduces the memory available to Linux. We need to + * do this because highmem is not supported on 64-bit. + */ + memblock_enforce_memory_limit(linear_map_top); + } +#endif + + memblock_set_current_limit(linear_map_top); +} + +/* boot cpu only */ +void __init early_init_mmu(void) +{ + early_init_mmu_global(); + early_init_this_mmu(); + early_mmu_set_memory_limit(); +} + +void early_init_mmu_secondary(void) +{ + early_init_this_mmu(); +} + +void setup_initial_memory_limit(phys_addr_t first_memblock_base, + phys_addr_t first_memblock_size) +{ + /* On non-FSL Embedded 64-bit, we adjust the RMA size to match + * the bolted TLB entry. We know for now that only 1G + * entries are supported though that may eventually + * change. + * + * on FSL Embedded 64-bit, usually all RAM is bolted, but with + * unusual memory sizes it's possible for some RAM to not be mapped + * (such RAM is not used at all by Linux, since we don't support + * highmem on 64-bit). We limit ppc64_rma_size to what would be + * mappable if this memblock is the only one. Additional memblocks + * can only increase, not decrease, the amount that ends up getting + * mapped. We still limit max to 1G even if we'll eventually map + * more. This is due to what the early init code is set up to do. + * + * We crop it to the size of the first MEMBLOCK to + * avoid going over total available memory just in case... + */ +#ifdef CONFIG_PPC_E500 + if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { + unsigned long linear_sz; + unsigned int num_cams; + + /* use a quarter of the TLBCAM for bolted linear map */ + num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4; + + linear_sz = map_mem_in_cams(first_memblock_size, num_cams, + true, true); + + ppc64_rma_size = min_t(u64, linear_sz, 0x40000000); + } else +#endif + ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000); + + /* Finally limit subsequent allocations */ + memblock_set_current_limit(first_memblock_base + ppc64_rma_size); +} diff --git a/arch/powerpc/mm/nohash/tlb_low_64e.S b/arch/powerpc/mm/nohash/tlb_low_64e.S index 7e0b8fe1c27975..b0eb3f7eaed149 100644 --- a/arch/powerpc/mm/nohash/tlb_low_64e.S +++ b/arch/powerpc/mm/nohash/tlb_low_64e.S @@ -893,201 +893,6 @@ virt_page_table_tlb_miss_whacko_fault: TLB_MISS_EPILOG_ERROR b exc_data_storage_book3e - -/************************************************************** - * * - * TLB miss handling for Book3E with hw page table support * - * * - **************************************************************/ - - -/* Data TLB miss */ - START_EXCEPTION(data_tlb_miss_htw) - TLB_MISS_PROLOG - - /* Now we handle the fault proper. We only save DEAR in normal - * fault case since that's the only interesting values here. - * We could probably also optimize by not saving SRR0/1 in the - * linear mapping case but I'll leave that for later - */ - mfspr r14,SPRN_ESR - mfspr r16,SPRN_DEAR /* get faulting address */ - srdi r11,r16,44 /* get region */ - xoris r11,r11,0xc - cmpldi cr0,r11,0 /* linear mapping ? */ - beq tlb_load_linear /* yes -> go to linear map load */ - cmpldi cr1,r11,1 /* vmalloc mapping ? */ - - /* We do the user/kernel test for the PID here along with the RW test - */ - srdi. r11,r16,60 /* Check for user region */ - ld r15,PACAPGD(r13) /* Load user pgdir */ - beq htw_tlb_miss - - /* XXX replace the RMW cycles with immediate loads + writes */ -1: mfspr r10,SPRN_MAS1 - rlwinm r10,r10,0,16,1 /* Clear TID */ - mtspr SPRN_MAS1,r10 - ld r15,PACA_KERNELPGD(r13) /* Load kernel pgdir */ - beq+ cr1,htw_tlb_miss - - /* We got a crappy address, just fault with whatever DEAR and ESR - * are here - */ - TLB_MISS_EPILOG_ERROR - b exc_data_storage_book3e - -/* Instruction TLB miss */ - START_EXCEPTION(instruction_tlb_miss_htw) - TLB_MISS_PROLOG - - /* If we take a recursive fault, the second level handler may need - * to know whether we are handling a data or instruction fault in - * order to get to the right store fault handler. We provide that - * info by keeping a crazy value for ESR in r14 - */ - li r14,-1 /* store to exception frame is done later */ - - /* Now we handle the fault proper. We only save DEAR in the non - * linear mapping case since we know the linear mapping case will - * not re-enter. We could indeed optimize and also not save SRR0/1 - * in the linear mapping case but I'll leave that for later - * - * Faulting address is SRR0 which is already in r16 - */ - srdi r11,r16,44 /* get region */ - xoris r11,r11,0xc - cmpldi cr0,r11,0 /* linear mapping ? */ - beq tlb_load_linear /* yes -> go to linear map load */ - cmpldi cr1,r11,1 /* vmalloc mapping ? */ - - /* We do the user/kernel test for the PID here along with the RW test - */ - srdi. r11,r16,60 /* Check for user region */ - ld r15,PACAPGD(r13) /* Load user pgdir */ - beq htw_tlb_miss - - /* XXX replace the RMW cycles with immediate loads + writes */ -1: mfspr r10,SPRN_MAS1 - rlwinm r10,r10,0,16,1 /* Clear TID */ - mtspr SPRN_MAS1,r10 - ld r15,PACA_KERNELPGD(r13) /* Load kernel pgdir */ - beq+ htw_tlb_miss - - /* We got a crappy address, just fault */ - TLB_MISS_EPILOG_ERROR - b exc_instruction_storage_book3e - - -/* - * This is the guts of the second-level TLB miss handler for direct - * misses. We are entered with: - * - * r16 = virtual page table faulting address - * r15 = PGD pointer - * r14 = ESR - * r13 = PACA - * r12 = TLB exception frame in PACA - * r11 = crap (free to use) - * r10 = crap (free to use) - * - * It can be re-entered by the linear mapping miss handler. However, to - * avoid too much complication, it will save/restore things for us - */ -htw_tlb_miss: -#ifdef CONFIG_PPC_KUAP - mfspr r10,SPRN_MAS1 - rlwinm. r10,r10,0,0x3fff0000 - beq- htw_tlb_miss_fault /* KUAP fault */ -#endif - /* Search if we already have a TLB entry for that virtual address, and - * if we do, bail out. - * - * MAS1:IND should be already set based on MAS4 - */ - PPC_TLBSRX_DOT(0,R16) - beq htw_tlb_miss_done - - /* Now, we need to walk the page tables. First check if we are in - * range. - */ - rldicl. r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4 - bne- htw_tlb_miss_fault - - /* Get the PGD pointer */ - cmpldi cr0,r15,0 - beq- htw_tlb_miss_fault - - /* Get to PGD entry */ - rldicl r11,r16,64-(PGDIR_SHIFT-3),64-PGD_INDEX_SIZE-3 - clrrdi r10,r11,3 - ldx r15,r10,r15 - cmpdi cr0,r15,0 - bge htw_tlb_miss_fault - - /* Get to PUD entry */ - rldicl r11,r16,64-(PUD_SHIFT-3),64-PUD_INDEX_SIZE-3 - clrrdi r10,r11,3 - ldx r15,r10,r15 - cmpdi cr0,r15,0 - bge htw_tlb_miss_fault - - /* Get to PMD entry */ - rldicl r11,r16,64-(PMD_SHIFT-3),64-PMD_INDEX_SIZE-3 - clrrdi r10,r11,3 - ldx r15,r10,r15 - cmpdi cr0,r15,0 - bge htw_tlb_miss_fault - - /* Ok, we're all right, we can now create an indirect entry for - * a 1M or 256M page. - * - * The last trick is now that because we use "half" pages for - * the HTW (1M IND is 2K and 256M IND is 32K) we need to account - * for an added LSB bit to the RPN. For 64K pages, there is no - * problem as we already use 32K arrays (half PTE pages), but for - * 4K page we need to extract a bit from the virtual address and - * insert it into the "PA52" bit of the RPN. - */ - rlwimi r15,r16,32-9,20,20 - /* Now we build the MAS: - * - * MAS 0 : Fully setup with defaults in MAS4 and TLBnCFG - * MAS 1 : Almost fully setup - * - PID already updated by caller if necessary - * - TSIZE for now is base ind page size always - * MAS 2 : Use defaults - * MAS 3+7 : Needs to be done - */ - ori r10,r15,(BOOK3E_PAGESZ_4K << MAS3_SPSIZE_SHIFT) - - srdi r16,r10,32 - mtspr SPRN_MAS3,r10 - mtspr SPRN_MAS7,r16 - - tlbwe - -htw_tlb_miss_done: - /* We don't bother with restoring DEAR or ESR since we know we are - * level 0 and just going back to userland. They are only needed - * if you are going to take an access fault - */ - TLB_MISS_EPILOG_SUCCESS - rfi - -htw_tlb_miss_fault: - /* We need to check if it was an instruction miss. We know this - * though because r14 would contain -1 - */ - cmpdi cr0,r14,-1 - beq 1f - mtspr SPRN_DEAR,r16 - mtspr SPRN_ESR,r14 - TLB_MISS_EPILOG_ERROR - b exc_data_storage_book3e -1: TLB_MISS_EPILOG_ERROR - b exc_instruction_storage_book3e - /* * This is the guts of "any" level TLB miss handler for kernel linear * mapping misses. We are entered with: diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index 7f91ea064c0874..06f886850a9327 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -851,6 +851,15 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * /* Get offset into TMP_REG */ EMIT(PPC_RAW_LI(tmp_reg, off)); + /* + * Enforce full ordering for operations with BPF_FETCH by emitting a 'sync' + * before and after the operation. + * + * This is a requirement in the Linux Kernel Memory Model. + * See __cmpxchg_u32() in asm/cmpxchg.h as an example. + */ + if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP)) + EMIT(PPC_RAW_SYNC()); tmp_idx = ctx->idx * 4; /* load value from memory into r0 */ EMIT(PPC_RAW_LWARX(_R0, tmp_reg, dst_reg, 0)); @@ -904,6 +913,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * /* For the BPF_FETCH variant, get old data into src_reg */ if (imm & BPF_FETCH) { + /* Emit 'sync' to enforce full ordering */ + if (IS_ENABLED(CONFIG_SMP)) + EMIT(PPC_RAW_SYNC()); EMIT(PPC_RAW_MR(ret_reg, ax_reg)); if (!fp->aux->verifier_zext) EMIT(PPC_RAW_LI(ret_reg - 1, 0)); /* higher 32-bit */ diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 0f8048f6dad630..2239ce5e8501cd 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -803,6 +803,15 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * /* Get offset into TMP_REG_1 */ EMIT(PPC_RAW_LI(tmp1_reg, off)); + /* + * Enforce full ordering for operations with BPF_FETCH by emitting a 'sync' + * before and after the operation. + * + * This is a requirement in the Linux Kernel Memory Model. + * See __cmpxchg_u64() in asm/cmpxchg.h as an example. + */ + if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP)) + EMIT(PPC_RAW_SYNC()); tmp_idx = ctx->idx * 4; /* load value from memory into TMP_REG_2 */ if (size == BPF_DW) @@ -865,6 +874,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * PPC_BCC_SHORT(COND_NE, tmp_idx); if (imm & BPF_FETCH) { + /* Emit 'sync' to enforce full ordering */ + if (IS_ENABLED(CONFIG_SMP)) + EMIT(PPC_RAW_SYNC()); EMIT(PPC_RAW_MR(ret_reg, _R0)); /* * Skip unnecessary zero-extension for 32-bit cmpxchg. diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 8c1f7def596e4a..10b946e9c6e756 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1371,8 +1371,7 @@ static void power_pmu_disable(struct pmu *pmu) /* * Disable instruction sampling if it was enabled */ - if (cpuhw->mmcr.mmcra & MMCRA_SAMPLE_ENABLE) - val &= ~MMCRA_SAMPLE_ENABLE; + val &= ~MMCRA_SAMPLE_ENABLE; /* Disable BHRB via mmcra (BHRBRD) for p10 */ if (ppmu->flags & PPMU_ARCH_31) @@ -1383,7 +1382,7 @@ static void power_pmu_disable(struct pmu *pmu) * instruction sampling or BHRB. */ if (val != mmcra) { - mtspr(SPRN_MMCRA, mmcra); + mtspr(SPRN_MMCRA, val); mb(); isync(); } diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 39dbe6b348df28..241551d1282f80 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -534,6 +534,9 @@ static ssize_t affinity_domain_via_partition_show(struct device *dev, struct dev if (!ret) goto parse_result; + if (ret && (ret != H_PARAMETER)) + goto out; + /* * ret value as 'H_PARAMETER' implies that the current buffer size * can't accommodate all the information, and a partial buffer @@ -692,6 +695,20 @@ static unsigned long single_gpci_request(u32 req, u32 starting_index, ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE); + + /* + * ret value as 'H_PARAMETER' with detail_rc as 'GEN_BUF_TOO_SMALL', + * specifies that the current buffer size cannot accommodate + * all the information and a partial buffer returned. + * Since in this function we are only accessing data for a given starting index, + * we don't need to accommodate whole data and can get required count by + * accessing first entry data. + * Hence hcall fails only incase the ret value is other than H_SUCCESS or + * H_PARAMETER with detail_rc value as GEN_BUF_TOO_SMALL(0x1B). + */ + if (ret == H_PARAMETER && be32_to_cpu(arg->params.detail_rc) == 0x1B) + ret = 0; + if (ret) { pr_devel("hcall failed: 0x%lx\n", ret); goto out; @@ -756,6 +773,7 @@ static int h_gpci_event_init(struct perf_event *event) { u64 count; u8 length; + unsigned long ret; /* Not our event */ if (event->attr.type != event->pmu->type) @@ -786,13 +804,23 @@ static int h_gpci_event_init(struct perf_event *event) } /* check if the request works... */ - if (single_gpci_request(event_get_request(event), + ret = single_gpci_request(event_get_request(event), event_get_starting_index(event), event_get_secondary_index(event), event_get_counter_info_version(event), event_get_offset(event), length, - &count)) { + &count); + + /* + * ret value as H_AUTHORITY implies that partition is not permitted to retrieve + * performance information, and required to set + * "Enable Performance Information Collection" option. + */ + if (ret == H_AUTHORITY) + return -EPERM; + + if (ret) { pr_devel("gpci hcall failed\n"); return -EINVAL; } diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 9d229ef7f86efa..56d82f7f9734e0 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -51,7 +51,7 @@ static int trace_imc_mem_size; * core and trace-imc */ static struct imc_pmu_ref imc_global_refc = { - .lock = __SPIN_LOCK_INITIALIZER(imc_global_refc.lock), + .lock = __SPIN_LOCK_UNLOCKED(imc_global_refc.lock), .id = 0, .refc = 0, }; @@ -299,6 +299,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu) attr_group->attrs = attrs; do { ev_val_str = kasprintf(GFP_KERNEL, "event=0x%x", pmu->events[i].value); + if (!ev_val_str) + continue; dev_str = device_str_attr_create(pmu->events[i].name, ev_val_str); if (!dev_str) continue; @@ -306,6 +308,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu) attrs[j++] = dev_str; if (pmu->events[i].scale) { ev_scale_str = kasprintf(GFP_KERNEL, "%s.scale", pmu->events[i].name); + if (!ev_scale_str) + continue; dev_str = device_str_attr_create(ev_scale_str, pmu->events[i].scale); if (!dev_str) continue; @@ -315,6 +319,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu) if (pmu->events[i].unit) { ev_unit_str = kasprintf(GFP_KERNEL, "%s.unit", pmu->events[i].name); + if (!ev_unit_str) + continue; dev_str = device_str_attr_create(ev_unit_str, pmu->events[i].unit); if (!dev_str) continue; diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index 1624ebf95497ba..35a1f4b9f8272b 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -173,6 +173,7 @@ config ISS4xx config CURRITUCK bool "IBM Currituck (476fpe) Support" depends on PPC_47x + select I2C select SWIOTLB select 476FPE select FORCE_PCI diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c index 77ea9335fd049c..f381b177ea06ad 100644 --- a/arch/powerpc/platforms/book3s/vas-api.c +++ b/arch/powerpc/platforms/book3s/vas-api.c @@ -4,6 +4,8 @@ * Copyright (C) 2019 Haren Myneni, IBM Corp */ +#define pr_fmt(fmt) "vas-api: " fmt + #include #include #include @@ -78,7 +80,7 @@ int get_vas_user_win_ref(struct vas_user_win_ref *task_ref) task_ref->mm = get_task_mm(current); if (!task_ref->mm) { put_pid(task_ref->pid); - pr_err("VAS: pid(%d): mm_struct is not found\n", + pr_err("pid(%d): mm_struct is not found\n", current->pid); return -EPERM; } @@ -235,8 +237,7 @@ void vas_update_csb(struct coprocessor_request_block *crb, rc = kill_pid_info(SIGSEGV, &info, pid); rcu_read_unlock(); - pr_devel("%s(): pid %d kill_proc_info() rc %d\n", __func__, - pid_vnr(pid), rc); + pr_devel("pid %d kill_proc_info() rc %d\n", pid_vnr(pid), rc); } void vas_dump_crb(struct coprocessor_request_block *crb) @@ -294,7 +295,7 @@ static int coproc_ioc_tx_win_open(struct file *fp, unsigned long arg) rc = copy_from_user(&uattr, uptr, sizeof(uattr)); if (rc) { - pr_err("%s(): copy_from_user() returns %d\n", __func__, rc); + pr_err("copy_from_user() returns %d\n", rc); return -EFAULT; } @@ -311,7 +312,7 @@ static int coproc_ioc_tx_win_open(struct file *fp, unsigned long arg) txwin = cp_inst->coproc->vops->open_win(uattr.vas_id, uattr.flags, cp_inst->coproc->cop_type); if (IS_ERR(txwin)) { - pr_err("%s() VAS window open failed, %ld\n", __func__, + pr_err_ratelimited("VAS window open failed rc=%ld\n", PTR_ERR(txwin)); return PTR_ERR(txwin); } @@ -405,8 +406,7 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf) * window is not opened. Shouldn't expect this error. */ if (!cp_inst || !cp_inst->txwin) { - pr_err("%s(): Unexpected fault on paste address with TX window closed\n", - __func__); + pr_err("Unexpected fault on paste address with TX window closed\n"); return VM_FAULT_SIGBUS; } @@ -421,8 +421,7 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf) * issue NX request. */ if (txwin->task_ref.vma != vmf->vma) { - pr_err("%s(): No previous mapping with paste address\n", - __func__); + pr_err("No previous mapping with paste address\n"); return VM_FAULT_SIGBUS; } @@ -481,19 +480,19 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma) txwin = cp_inst->txwin; if ((vma->vm_end - vma->vm_start) > PAGE_SIZE) { - pr_debug("%s(): size 0x%zx, PAGE_SIZE 0x%zx\n", __func__, + pr_debug("size 0x%zx, PAGE_SIZE 0x%zx\n", (vma->vm_end - vma->vm_start), PAGE_SIZE); return -EINVAL; } /* Ensure instance has an open send window */ if (!txwin) { - pr_err("%s(): No send window open?\n", __func__); + pr_err("No send window open?\n"); return -EINVAL; } if (!cp_inst->coproc->vops || !cp_inst->coproc->vops->paste_addr) { - pr_err("%s(): VAS API is not registered\n", __func__); + pr_err("VAS API is not registered\n"); return -EACCES; } @@ -510,14 +509,14 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma) */ mutex_lock(&txwin->task_ref.mmap_mutex); if (txwin->status != VAS_WIN_ACTIVE) { - pr_err("%s(): Window is not active\n", __func__); + pr_err("Window is not active\n"); rc = -EACCES; goto out; } paste_addr = cp_inst->coproc->vops->paste_addr(txwin); if (!paste_addr) { - pr_err("%s(): Window paste address failed\n", __func__); + pr_err("Window paste address failed\n"); rc = -EINVAL; goto out; } @@ -533,8 +532,8 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma) rc = remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff, vma->vm_end - vma->vm_start, prot); - pr_devel("%s(): paste addr %llx at %lx, rc %d\n", __func__, - paste_addr, vma->vm_start, rc); + pr_devel("paste addr %llx at %lx, rc %d\n", paste_addr, + vma->vm_start, rc); txwin->task_ref.vma = vma; vma->vm_ops = &vas_vm_ops; @@ -609,8 +608,7 @@ int vas_register_coproc_api(struct module *mod, enum vas_cop_type cop_type, goto err; } - pr_devel("%s: Added dev [%d,%d]\n", __func__, MAJOR(devno), - MINOR(devno)); + pr_devel("Added dev [%d,%d]\n", MAJOR(devno), MINOR(devno)); return 0; diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c index 9c10aac40c7b11..e265f026eee2a9 100644 --- a/arch/powerpc/platforms/embedded6xx/linkstation.c +++ b/arch/powerpc/platforms/embedded6xx/linkstation.c @@ -99,9 +99,6 @@ static void __init linkstation_init_IRQ(void) mpic_init(mpic); } -extern void avr_uart_configure(void); -extern void avr_uart_send(const char); - static void __noreturn linkstation_restart(char *cmd) { local_irq_disable(); diff --git a/arch/powerpc/platforms/embedded6xx/mpc10x.h b/arch/powerpc/platforms/embedded6xx/mpc10x.h index 5ad12023e56280..ebc258fa4858d0 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc10x.h +++ b/arch/powerpc/platforms/embedded6xx/mpc10x.h @@ -156,4 +156,7 @@ int mpc10x_disable_store_gathering(struct pci_controller *hose); /* For MPC107 boards that use the built-in openpic */ void mpc10x_set_openpic(void); +void avr_uart_configure(void); +void avr_uart_send(const char c); + #endif /* __PPC_KERNEL_MPC10X_H */ diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c index f9a7001dacb7a1..56a1f7ce78d2c7 100644 --- a/arch/powerpc/platforms/powernv/opal-irqchip.c +++ b/arch/powerpc/platforms/powernv/opal-irqchip.c @@ -275,6 +275,8 @@ int __init opal_event_init(void) else name = kasprintf(GFP_KERNEL, "opal"); + if (!name) + continue; /* Install interrupt handler */ rc = request_irq(r->start, opal_interrupt, r->flags & IRQD_TRIGGER_MASK, name, NULL); diff --git a/arch/powerpc/platforms/powernv/opal-powercap.c b/arch/powerpc/platforms/powernv/opal-powercap.c index 7bfe4cbeb35a99..ea917266aa1725 100644 --- a/arch/powerpc/platforms/powernv/opal-powercap.c +++ b/arch/powerpc/platforms/powernv/opal-powercap.c @@ -196,6 +196,12 @@ void __init opal_powercap_init(void) j = 0; pcaps[i].pg.name = kasprintf(GFP_KERNEL, "%pOFn", node); + if (!pcaps[i].pg.name) { + kfree(pcaps[i].pattrs); + kfree(pcaps[i].pg.attrs); + goto out_pcaps_pattrs; + } + if (has_min) { powercap_add_attr(min, "powercap-min", &pcaps[i].pattrs[j]); diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c index 262cd6fac90714..748c2b97fa5370 100644 --- a/arch/powerpc/platforms/powernv/opal-xscom.c +++ b/arch/powerpc/platforms/powernv/opal-xscom.c @@ -165,6 +165,11 @@ static int scom_debug_init_one(struct dentry *root, struct device_node *dn, ent->chip = chip; snprintf(ent->name, 16, "%08x", chip); ent->path.data = (void *)kasprintf(GFP_KERNEL, "%pOF", dn); + if (!ent->path.data) { + kfree(ent); + return -ENOMEM; + } + ent->path.size = strlen((char *)ent->path.data); dir = debugfs_create_dir(ent->name, root); diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig index a44869e5ea70f8..1bd1b0b49bc62a 100644 --- a/arch/powerpc/platforms/ps3/Kconfig +++ b/arch/powerpc/platforms/ps3/Kconfig @@ -67,6 +67,7 @@ config PS3_VUART config PS3_PS3AV depends on PPC_PS3 tristate "PS3 AV settings driver" if PS3_ADVANCED + select VIDEO select PS3_VUART default y help diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index 47f8eabd1bee31..9873b916b23704 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -334,23 +334,6 @@ int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog) { int rc; - /* pseries error logs are in BE format, convert to cpu type */ - switch (hp_elog->id_type) { - case PSERIES_HP_ELOG_ID_DRC_COUNT: - hp_elog->_drc_u.drc_count = - be32_to_cpu(hp_elog->_drc_u.drc_count); - break; - case PSERIES_HP_ELOG_ID_DRC_INDEX: - hp_elog->_drc_u.drc_index = - be32_to_cpu(hp_elog->_drc_u.drc_index); - break; - case PSERIES_HP_ELOG_ID_DRC_IC: - hp_elog->_drc_u.ic.count = - be32_to_cpu(hp_elog->_drc_u.ic.count); - hp_elog->_drc_u.ic.index = - be32_to_cpu(hp_elog->_drc_u.ic.index); - } - switch (hp_elog->resource) { case PSERIES_HP_ELOG_RESOURCE_MEM: rc = dlpar_memory(hp_elog); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index e62835a12d73fc..6838a0fcda296b 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -757,7 +757,7 @@ int dlpar_cpu(struct pseries_hp_errorlog *hp_elog) u32 drc_index; int rc; - drc_index = hp_elog->_drc_u.drc_index; + drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index); lock_device_hotplug(); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index aa4042dcd6d40e..95ff84c55cb144 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -435,14 +435,15 @@ static int dlpar_memory_remove_by_index(u32 drc_index) } } - if (!lmb_found) + if (!lmb_found) { + pr_debug("Failed to look up LMB for drc index %x\n", drc_index); rc = -EINVAL; - - if (rc) + } else if (rc) { pr_debug("Failed to hot-remove memory at %llx\n", lmb->base_addr); - else + } else { pr_debug("Memory at %llx was hot-removed\n", lmb->base_addr); + } return rc; } @@ -810,16 +811,16 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) case PSERIES_HP_ELOG_ACTION_ADD: switch (hp_elog->id_type) { case PSERIES_HP_ELOG_ID_DRC_COUNT: - count = hp_elog->_drc_u.drc_count; + count = be32_to_cpu(hp_elog->_drc_u.drc_count); rc = dlpar_memory_add_by_count(count); break; case PSERIES_HP_ELOG_ID_DRC_INDEX: - drc_index = hp_elog->_drc_u.drc_index; + drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index); rc = dlpar_memory_add_by_index(drc_index); break; case PSERIES_HP_ELOG_ID_DRC_IC: - count = hp_elog->_drc_u.ic.count; - drc_index = hp_elog->_drc_u.ic.index; + count = be32_to_cpu(hp_elog->_drc_u.ic.count); + drc_index = be32_to_cpu(hp_elog->_drc_u.ic.index); rc = dlpar_memory_add_by_ic(count, drc_index); break; default: @@ -831,16 +832,16 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) case PSERIES_HP_ELOG_ACTION_REMOVE: switch (hp_elog->id_type) { case PSERIES_HP_ELOG_ID_DRC_COUNT: - count = hp_elog->_drc_u.drc_count; + count = be32_to_cpu(hp_elog->_drc_u.drc_count); rc = dlpar_memory_remove_by_count(count); break; case PSERIES_HP_ELOG_ID_DRC_INDEX: - drc_index = hp_elog->_drc_u.drc_index; + drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index); rc = dlpar_memory_remove_by_index(drc_index); break; case PSERIES_HP_ELOG_ID_DRC_IC: - count = hp_elog->_drc_u.ic.count; - drc_index = hp_elog->_drc_u.ic.index; + count = be32_to_cpu(hp_elog->_drc_u.ic.count); + drc_index = be32_to_cpu(hp_elog->_drc_u.ic.index); rc = dlpar_memory_remove_by_ic(count, drc_index); break; default: diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 16d93b580f61f1..b1e6d275cda9eb 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -574,29 +574,6 @@ static void iommu_table_setparms(struct pci_controller *phb, struct iommu_table_ops iommu_table_lpar_multi_ops; -/* - * iommu_table_setparms_lpar - * - * Function: On pSeries LPAR systems, return TCE table info, given a pci bus. - */ -static void iommu_table_setparms_lpar(struct pci_controller *phb, - struct device_node *dn, - struct iommu_table *tbl, - struct iommu_table_group *table_group, - const __be32 *dma_window) -{ - unsigned long offset, size, liobn; - - of_parse_dma_window(dn, dma_window, &liobn, &offset, &size); - - iommu_table_setparms_common(tbl, phb->bus->number, liobn, offset, size, IOMMU_PAGE_SHIFT_4K, NULL, - &iommu_table_lpar_multi_ops); - - - table_group->tce32_start = offset; - table_group->tce32_size = size; -} - struct iommu_table_ops iommu_table_pseries_ops = { .set = tce_build_pSeries, .clear = tce_free_pSeries, @@ -724,26 +701,71 @@ struct iommu_table_ops iommu_table_lpar_multi_ops = { * dynamic 64bit DMA window, walking up the device tree. */ static struct device_node *pci_dma_find(struct device_node *dn, - const __be32 **dma_window) + struct dynamic_dma_window_prop *prop) { - const __be32 *dw = NULL; + const __be32 *default_prop = NULL; + const __be32 *ddw_prop = NULL; + struct device_node *rdn = NULL; + bool default_win = false, ddw_win = false; for ( ; dn && PCI_DN(dn); dn = dn->parent) { - dw = of_get_property(dn, "ibm,dma-window", NULL); - if (dw) { - if (dma_window) - *dma_window = dw; - return dn; + default_prop = of_get_property(dn, "ibm,dma-window", NULL); + if (default_prop) { + rdn = dn; + default_win = true; } - dw = of_get_property(dn, DIRECT64_PROPNAME, NULL); - if (dw) - return dn; - dw = of_get_property(dn, DMA64_PROPNAME, NULL); - if (dw) - return dn; + ddw_prop = of_get_property(dn, DIRECT64_PROPNAME, NULL); + if (ddw_prop) { + rdn = dn; + ddw_win = true; + break; + } + ddw_prop = of_get_property(dn, DMA64_PROPNAME, NULL); + if (ddw_prop) { + rdn = dn; + ddw_win = true; + break; + } + + /* At least found default window, which is the case for normal boot */ + if (default_win) + break; } - return NULL; + /* For PCI devices there will always be a DMA window, either on the device + * or parent bus + */ + WARN_ON(!(default_win | ddw_win)); + + /* caller doesn't want to get DMA window property */ + if (!prop) + return rdn; + + /* parse DMA window property. During normal system boot, only default + * DMA window is passed in OF. But, for kdump, a dedicated adapter might + * have both default and DDW in FDT. In this scenario, DDW takes precedence + * over default window. + */ + if (ddw_win) { + struct dynamic_dma_window_prop *p; + + p = (struct dynamic_dma_window_prop *)ddw_prop; + prop->liobn = p->liobn; + prop->dma_base = p->dma_base; + prop->tce_shift = p->tce_shift; + prop->window_shift = p->window_shift; + } else if (default_win) { + unsigned long offset, size, liobn; + + of_parse_dma_window(rdn, default_prop, &liobn, &offset, &size); + + prop->liobn = cpu_to_be32((u32)liobn); + prop->dma_base = cpu_to_be64(offset); + prop->tce_shift = cpu_to_be32(IOMMU_PAGE_SHIFT_4K); + prop->window_shift = cpu_to_be32(order_base_2(size)); + } + + return rdn; } static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) @@ -751,17 +773,28 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) struct iommu_table *tbl; struct device_node *dn, *pdn; struct pci_dn *ppci; - const __be32 *dma_window = NULL; + struct dynamic_dma_window_prop prop; dn = pci_bus_to_OF_node(bus); pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n", dn); - pdn = pci_dma_find(dn, &dma_window); + pdn = pci_dma_find(dn, &prop); + + /* In PPC architecture, there will always be DMA window on bus or one of the + * parent bus. During reboot, there will be ibm,dma-window property to + * define DMA window. For kdump, there will at least be default window or DDW + * or both. + * There is an exception to the above. In case the PE goes into frozen + * state, firmware may not provide ibm,dma-window property at the time + * of LPAR boot up. + */ - if (dma_window == NULL) + if (!pdn) { pr_debug(" no ibm,dma-window property !\n"); + return; + } ppci = PCI_DN(pdn); @@ -771,13 +804,24 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) if (!ppci->table_group) { ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node); tbl = ppci->table_group->tables[0]; - if (dma_window) { - iommu_table_setparms_lpar(ppci->phb, pdn, tbl, - ppci->table_group, dma_window); - if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) - panic("Failed to initialize iommu table"); - } + iommu_table_setparms_common(tbl, ppci->phb->bus->number, + be32_to_cpu(prop.liobn), + be64_to_cpu(prop.dma_base), + 1ULL << be32_to_cpu(prop.window_shift), + be32_to_cpu(prop.tce_shift), NULL, + &iommu_table_lpar_multi_ops); + + /* Only for normal boot with default window. Doesn't matter even + * if we set these with DDW which is 64bit during kdump, since + * these will not be used during kdump. + */ + ppci->table_group->tce32_start = be64_to_cpu(prop.dma_base); + ppci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift); + + if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) + panic("Failed to initialize iommu table"); + iommu_register_group(ppci->table_group, pci_domain_nr(bus), 0); pr_debug(" created table: %p\n", ppci->table_group); @@ -914,7 +958,8 @@ static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_ return 0; } -static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift) +static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift, + bool *direct_mapping) { struct dma_win *window; const struct dynamic_dma_window_prop *dma64; @@ -927,6 +972,7 @@ static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *windo dma64 = window->prop; *dma_addr = be64_to_cpu(dma64->dma_base); *window_shift = be32_to_cpu(dma64->window_shift); + *direct_mapping = window->direct; found = true; break; } @@ -966,6 +1012,12 @@ static void find_existing_ddw_windows_named(const char *name) continue; } + /* If at the time of system initialization, there are DDWs in OF, + * it means this is during kexec. DDW could be direct or dynamic. + * We will just mark DDWs as "dynamic" since this is kdump path, + * no need to worry about perforance. ddw_list_new_entry() will + * set window->direct = false. + */ window = ddw_list_new_entry(pdn, dma64); if (!window) { of_node_put(pdn); @@ -1270,10 +1322,8 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) mutex_lock(&dma_win_init_mutex); - if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len)) { - direct_mapping = (len >= max_ram_len); + if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len, &direct_mapping)) goto out_unlock; - } /* * If we already went through this for a previous function of @@ -1524,8 +1574,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) { struct device_node *pdn, *dn; struct iommu_table *tbl; - const __be32 *dma_window = NULL; struct pci_dn *pci; + struct dynamic_dma_window_prop prop; pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev)); @@ -1538,7 +1588,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) dn = pci_device_to_OF_node(dev); pr_debug(" node is %pOF\n", dn); - pdn = pci_dma_find(dn, &dma_window); + pdn = pci_dma_find(dn, &prop); if (!pdn || !PCI_DN(pdn)) { printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: " "no DMA window found for pci dev=%s dn=%pOF\n", @@ -1551,8 +1601,20 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) if (!pci->table_group) { pci->table_group = iommu_pseries_alloc_group(pci->phb->node); tbl = pci->table_group->tables[0]; - iommu_table_setparms_lpar(pci->phb, pdn, tbl, - pci->table_group, dma_window); + + iommu_table_setparms_common(tbl, pci->phb->bus->number, + be32_to_cpu(prop.liobn), + be64_to_cpu(prop.dma_base), + 1ULL << be32_to_cpu(prop.window_shift), + be32_to_cpu(prop.tce_shift), NULL, + &iommu_table_lpar_multi_ops); + + /* Only for normal boot with default window. Doesn't matter even + * if we set these with DDW which is 64bit during kdump, since + * these will not be used during kdump. + */ + pci->table_group->tce32_start = be64_to_cpu(prop.dma_base); + pci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift); iommu_init_table(tbl, pci->phb->node, 0, 0); iommu_register_group(pci->table_group, diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c index 096d09ed89f673..431be156ca9bb3 100644 --- a/arch/powerpc/platforms/pseries/kexec.c +++ b/arch/powerpc/platforms/pseries/kexec.c @@ -61,11 +61,3 @@ void pseries_kexec_cpu_down(int crash_shutdown, int secondary) } else xics_kexec_teardown_cpu(secondary); } - -void pseries_machine_kexec(struct kimage *image) -{ - if (firmware_has_feature(FW_FEATURE_SET_MODE)) - pseries_disable_reloc_on_exc(); - - default_machine_kexec(image); -} diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index f2cb62148f36f4..c3585e90c6db6b 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -526,8 +526,10 @@ static ssize_t vcpudispatch_stats_write(struct file *file, const char __user *p, if (cmd) { rc = init_cpu_associativity(); - if (rc) + if (rc) { + destroy_cpu_associativity(); goto out; + } for_each_possible_cpu(cpu) { disp = per_cpu_ptr(&vcpu_disp_data, cpu); @@ -660,8 +662,12 @@ u64 pseries_paravirt_steal_clock(int cpu) { struct lppaca *lppaca = &lppaca_of(cpu); - return be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) + - be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb)); + /* + * VPA steal time counters are reported at TB frequency. Hence do a + * conversion to ns before returning + */ + return tb_to_ns(be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) + + be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb))); } #endif @@ -1880,10 +1886,10 @@ notrace void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf) * h_get_mpp * H_GET_MPP hcall returns info in 7 parms */ -int h_get_mpp(struct hvcall_mpp_data *mpp_data) +long h_get_mpp(struct hvcall_mpp_data *mpp_data) { - int rc; - unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; + long rc; rc = plpar_hcall9(H_GET_MPP, retbuf); diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index 1c151d77e74b34..11d5208817b9d4 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -113,8 +113,8 @@ struct hvcall_ppp_data { */ static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data) { - unsigned long rc; - unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; + long rc; rc = plpar_hcall9(H_GET_PPP, retbuf); @@ -193,7 +193,7 @@ static void parse_ppp_data(struct seq_file *m) struct hvcall_ppp_data ppp_data; struct device_node *root; const __be32 *perf_level; - int rc; + long rc; rc = h_get_ppp(&ppp_data); if (rc) @@ -357,8 +357,8 @@ static int read_dt_lpar_name(struct seq_file *m) static void read_lpar_name(struct seq_file *m) { - if (read_rtas_lpar_name(m) && read_dt_lpar_name(m)) - pr_err_once("Error can't get the LPAR name"); + if (read_rtas_lpar_name(m)) + read_dt_lpar_name(m); } #define SPLPAR_MAXLENGTH 1026*(sizeof(char)) diff --git a/arch/powerpc/platforms/pseries/papr-sysparm.c b/arch/powerpc/platforms/pseries/papr-sysparm.c index fedc61599e6cc7..a1e7aeac741616 100644 --- a/arch/powerpc/platforms/pseries/papr-sysparm.c +++ b/arch/powerpc/platforms/pseries/papr-sysparm.c @@ -23,6 +23,46 @@ void papr_sysparm_buf_free(struct papr_sysparm_buf *buf) kfree(buf); } +static size_t papr_sysparm_buf_get_length(const struct papr_sysparm_buf *buf) +{ + return be16_to_cpu(buf->len); +} + +static void papr_sysparm_buf_set_length(struct papr_sysparm_buf *buf, size_t length) +{ + WARN_ONCE(length > sizeof(buf->val), + "bogus length %zu, clamping to safe value", length); + length = min(sizeof(buf->val), length); + buf->len = cpu_to_be16(length); +} + +/* + * For use on buffers returned from ibm,get-system-parameter before + * returning them to callers. Ensures the encoded length of valid data + * cannot overrun buf->val[]. + */ +static void papr_sysparm_buf_clamp_length(struct papr_sysparm_buf *buf) +{ + papr_sysparm_buf_set_length(buf, papr_sysparm_buf_get_length(buf)); +} + +/* + * Perform some basic diligence on the system parameter buffer before + * submitting it to RTAS. + */ +static bool papr_sysparm_buf_can_submit(const struct papr_sysparm_buf *buf) +{ + /* + * Firmware ought to reject buffer lengths that exceed the + * maximum specified in PAPR, but there's no reason for the + * kernel to allow them either. + */ + if (papr_sysparm_buf_get_length(buf) > sizeof(buf->val)) + return false; + + return true; +} + /** * papr_sysparm_get() - Retrieve the value of a PAPR system parameter. * @param: PAPR system parameter token as described in @@ -63,6 +103,9 @@ int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf) if (token == RTAS_UNKNOWN_SERVICE) return -ENOENT; + if (!papr_sysparm_buf_can_submit(buf)) + return -EINVAL; + work_area = rtas_work_area_alloc(sizeof(*buf)); memcpy(rtas_work_area_raw_buf(work_area), buf, sizeof(*buf)); @@ -77,6 +120,7 @@ int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf) case 0: ret = 0; memcpy(buf, rtas_work_area_raw_buf(work_area), sizeof(*buf)); + papr_sysparm_buf_clamp_length(buf); break; case -3: /* parameter not implemented */ ret = -EOPNOTSUPP; @@ -115,6 +159,9 @@ int papr_sysparm_set(papr_sysparm_t param, const struct papr_sysparm_buf *buf) if (token == RTAS_UNKNOWN_SERVICE) return -ENOENT; + if (!papr_sysparm_buf_can_submit(buf)) + return -EINVAL; + work_area = rtas_work_area_alloc(sizeof(*buf)); memcpy(rtas_work_area_raw_buf(work_area), buf, sizeof(*buf)); diff --git a/arch/powerpc/platforms/pseries/papr_platform_attributes.c b/arch/powerpc/platforms/pseries/papr_platform_attributes.c index 526c621b098bec..eea2041b270b54 100644 --- a/arch/powerpc/platforms/pseries/papr_platform_attributes.c +++ b/arch/powerpc/platforms/pseries/papr_platform_attributes.c @@ -101,10 +101,12 @@ static int papr_get_attr(u64 id, struct energy_scale_attribute *esi) esi_buf_size = ESI_HDR_SIZE + (CURR_MAX_ESI_ATTRS * max_esi_attrs); temp_buf = krealloc(buf, esi_buf_size, GFP_KERNEL); - if (temp_buf) + if (temp_buf) { buf = temp_buf; - else - return -ENOMEM; + } else { + ret = -ENOMEM; + goto out_buf; + } goto retry; } diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 4ba82456811921..4448386268d991 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -35,6 +35,8 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) pseries_msi_allocate_domains(phb); + ppc_iommu_register_device(phb); + /* Create EEH devices for the PHB */ eeh_phb_pe_create(phb); @@ -76,6 +78,8 @@ int remove_phb_dynamic(struct pci_controller *phb) } } + ppc_iommu_unregister_device(phb); + pseries_msi_free_domains(phb); /* Keep a reference so phb isn't freed yet */ diff --git a/arch/powerpc/platforms/pseries/plpks.c b/arch/powerpc/platforms/pseries/plpks.c index 2d40304eb6c164..ed492d38f6ad6b 100644 --- a/arch/powerpc/platforms/pseries/plpks.c +++ b/arch/powerpc/platforms/pseries/plpks.c @@ -415,8 +415,7 @@ static int plpks_confirm_object_flushed(struct label *label, break; } - usleep_range(PLPKS_FLUSH_SLEEP, - PLPKS_FLUSH_SLEEP + PLPKS_FLUSH_SLEEP_RANGE); + fsleep(PLPKS_FLUSH_SLEEP); timeout = timeout + PLPKS_FLUSH_SLEEP; } while (timeout < PLPKS_MAX_TIMEOUT); @@ -464,9 +463,10 @@ int plpks_signed_update_var(struct plpks_var *var, u64 flags) continuetoken = retbuf[0]; if (pseries_status_to_err(rc) == -EBUSY) { - int delay_ms = get_longbusy_msecs(rc); - mdelay(delay_ms); - timeout += delay_ms; + int delay_us = get_longbusy_msecs(rc) * 1000; + + fsleep(delay_us); + timeout += delay_us; } rc = pseries_status_to_err(rc); } while (rc == -EBUSY && timeout < PLPKS_MAX_TIMEOUT); diff --git a/arch/powerpc/platforms/pseries/pmem.c b/arch/powerpc/platforms/pseries/pmem.c index 3c290b9ed01b39..0f1d45f32e4a44 100644 --- a/arch/powerpc/platforms/pseries/pmem.c +++ b/arch/powerpc/platforms/pseries/pmem.c @@ -121,7 +121,7 @@ int dlpar_hp_pmem(struct pseries_hp_errorlog *hp_elog) return -EINVAL; } - drc_index = hp_elog->_drc_u.drc_index; + drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index); lock_device_hotplug(); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 8376f03f932a45..dd6c569f680687 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -38,7 +38,6 @@ static inline void smp_init_pseries(void) { } #endif extern void pseries_kexec_cpu_down(int crash_shutdown, int secondary); -void pseries_machine_kexec(struct kimage *image); extern void pSeries_final_fixup(void); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index ecea85c74c43fa..1feb6b919bd970 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -343,8 +343,8 @@ static int alloc_dispatch_log_kmem_cache(void) { void (*ctor)(void *) = get_dtl_cache_ctor(); - dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES, - DISPATCH_LOG_BYTES, 0, ctor); + dtl_cache = kmem_cache_create_usercopy("dtl", DISPATCH_LOG_BYTES, + DISPATCH_LOG_BYTES, 0, 0, DISPATCH_LOG_BYTES, ctor); if (!dtl_cache) { pr_warn("Failed to create dispatch trace log buffer cache\n"); pr_warn("Stolen time statistics will be unreliable\n"); @@ -1153,7 +1153,6 @@ define_machine(pseries) { .machine_check_exception = pSeries_machine_check_exception, .machine_check_log_err = pSeries_machine_check_log_err, #ifdef CONFIG_KEXEC_CORE - .machine_kexec = pseries_machine_kexec, .kexec_cpu_down = pseries_kexec_cpu_down, #endif #ifdef CONFIG_MEMORY_HOTPLUG diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index e25ac52acf5073..71d52a670d951b 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -341,7 +341,7 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, if (atomic_inc_return(&cop_feat_caps->nr_used_credits) > atomic_read(&cop_feat_caps->nr_total_credits)) { - pr_err("Credits are not available to allocate window\n"); + pr_err_ratelimited("Credits are not available to allocate window\n"); rc = -EINVAL; goto out; } @@ -385,11 +385,15 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, * same fault IRQ is not freed by the OS before. */ mutex_lock(&vas_pseries_mutex); - if (migration_in_progress) + if (migration_in_progress) { rc = -EBUSY; - else + } else { rc = allocate_setup_window(txwin, (u64 *)&domain[0], cop_feat_caps->win_type); + if (!rc) + caps->nr_open_wins_progress++; + } + mutex_unlock(&vas_pseries_mutex); if (rc) goto out; @@ -404,8 +408,17 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, goto out_free; txwin->win_type = cop_feat_caps->win_type; - mutex_lock(&vas_pseries_mutex); + /* + * The migration SUSPEND thread sets migration_in_progress and + * closes all open windows from the list. But the window is + * added to the list after open and modify HCALLs. So possible + * that migration_in_progress is set before modify HCALL which + * may cause some windows are still open when the hypervisor + * initiates the migration. + * So checks the migration_in_progress flag again and close all + * open windows. + * * Possible to lose the acquired credit with DLPAR core * removal after the window is opened. So if there are any * closed windows (means with lost credits), do not give new @@ -413,9 +426,11 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, * after the existing windows are reopened when credits are * available. */ - if (!caps->nr_close_wins) { + mutex_lock(&vas_pseries_mutex); + if (!caps->nr_close_wins && !migration_in_progress) { list_add(&txwin->win_list, &caps->list); caps->nr_open_windows++; + caps->nr_open_wins_progress--; mutex_unlock(&vas_pseries_mutex); vas_user_win_add_mm_context(&txwin->vas_win.task_ref); return &txwin->vas_win; @@ -424,7 +439,7 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, put_vas_user_win_ref(&txwin->vas_win.task_ref); rc = -EBUSY; - pr_err("No credit is available to allocate window\n"); + pr_err_ratelimited("No credit is available to allocate window\n"); out_free: /* @@ -433,6 +448,12 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, */ free_irq_setup(txwin); h_deallocate_vas_window(txwin->vas_win.winid); + /* + * Hold mutex and reduce nr_open_wins_progress counter. + */ + mutex_lock(&vas_pseries_mutex); + caps->nr_open_wins_progress--; + mutex_unlock(&vas_pseries_mutex); out: atomic_dec(&cop_feat_caps->nr_used_credits); kfree(txwin); @@ -937,14 +958,14 @@ int vas_migration_handler(int action) struct vas_caps *vcaps; int i, rc = 0; + pr_info("VAS migration event %d\n", action); + /* * NX-GZIP is not enabled. Nothing to do for migration. */ if (!copypaste_feat) return rc; - mutex_lock(&vas_pseries_mutex); - if (action == VAS_SUSPEND) migration_in_progress = true; else @@ -990,12 +1011,27 @@ int vas_migration_handler(int action) switch (action) { case VAS_SUSPEND: + mutex_lock(&vas_pseries_mutex); rc = reconfig_close_windows(vcaps, vcaps->nr_open_windows, true); + /* + * Windows are included in the list after successful + * open. So wait for closing these in-progress open + * windows in vas_allocate_window() which will be + * done if the migration_in_progress is set. + */ + while (vcaps->nr_open_wins_progress) { + mutex_unlock(&vas_pseries_mutex); + msleep(10); + mutex_lock(&vas_pseries_mutex); + } + mutex_unlock(&vas_pseries_mutex); break; case VAS_RESUME: + mutex_lock(&vas_pseries_mutex); atomic_set(&caps->nr_total_credits, new_nr_creds); rc = reconfig_open_windows(vcaps, new_nr_creds, true); + mutex_unlock(&vas_pseries_mutex); break; default: /* should not happen */ @@ -1011,8 +1047,9 @@ int vas_migration_handler(int action) goto out; } + pr_info("VAS migration event (%d) successful\n", action); + out: - mutex_unlock(&vas_pseries_mutex); return rc; } diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h index 7115043ec48830..45567cd1317837 100644 --- a/arch/powerpc/platforms/pseries/vas.h +++ b/arch/powerpc/platforms/pseries/vas.h @@ -91,6 +91,8 @@ struct vas_cop_feat_caps { struct vas_caps { struct vas_cop_feat_caps caps; struct list_head list; /* List of open windows */ + int nr_open_wins_progress; /* Number of open windows in */ + /* progress. Used in migration */ int nr_close_wins; /* closed windows in the hypervisor for DLPAR */ int nr_open_windows; /* Number of successful open windows */ u8 feat; /* Feature type */ diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 57978a44d55b69..ce9895633c4e0f 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -568,10 +568,12 @@ static const struct fsl_msi_feature ipic_msi_feature = { .msiir_offset = 0x38, }; +#ifdef CONFIG_EPAPR_PARAVIRT static const struct fsl_msi_feature vmpic_msi_feature = { .fsl_pic_ip = FSL_PIC_IP_VMPIC, .msiir_offset = 0, }; +#endif static const struct of_device_id fsl_of_msi_ids[] = { { diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c index f6ec6dba92dcbc..700b67476a7d8d 100644 --- a/arch/powerpc/sysdev/xics/icp-native.c +++ b/arch/powerpc/sysdev/xics/icp-native.c @@ -236,6 +236,8 @@ static int __init icp_native_map_one_cpu(int hw_id, unsigned long addr, rname = kasprintf(GFP_KERNEL, "CPU %d [0x%x] Interrupt Presentation", cpu, hw_id); + if (!rname) + return -ENOMEM; if (!request_mem_region(addr, size, rname)) { pr_warn("icp_native: Could not reserve ICP MMIO for CPU %d, interrupt server #0x%x\n", cpu, hw_id); diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index 9f0af4d795d886..f1c0fa6ece21d0 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -802,7 +802,7 @@ int xive_native_get_queue_info(u32 vp_id, u32 prio, if (out_qpage) *out_qpage = be64_to_cpu(qpage); if (out_qsize) - *out_qsize = be32_to_cpu(qsize); + *out_qsize = be64_to_cpu(qsize); if (out_qeoi_page) *out_qeoi_page = be64_to_cpu(qeoi_page); if (out_escalate_irq) diff --git a/arch/powerpc/xmon/ppc-dis.c b/arch/powerpc/xmon/ppc-dis.c index 75fa98221d485d..af105e1bc3fca4 100644 --- a/arch/powerpc/xmon/ppc-dis.c +++ b/arch/powerpc/xmon/ppc-dis.c @@ -122,32 +122,21 @@ int print_insn_powerpc (unsigned long insn, unsigned long memaddr) bool insn_is_short; ppc_cpu_t dialect; - dialect = PPC_OPCODE_PPC | PPC_OPCODE_COMMON - | PPC_OPCODE_64 | PPC_OPCODE_POWER4 | PPC_OPCODE_ALTIVEC; + dialect = PPC_OPCODE_PPC | PPC_OPCODE_COMMON; - if (cpu_has_feature(CPU_FTRS_POWER5)) - dialect |= PPC_OPCODE_POWER5; + if (IS_ENABLED(CONFIG_PPC64)) + dialect |= PPC_OPCODE_64 | PPC_OPCODE_POWER4 | PPC_OPCODE_CELL | + PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 | PPC_OPCODE_POWER8 | + PPC_OPCODE_POWER9; - if (cpu_has_feature(CPU_FTRS_CELL)) - dialect |= (PPC_OPCODE_CELL | PPC_OPCODE_ALTIVEC); + if (cpu_has_feature(CPU_FTR_TM)) + dialect |= PPC_OPCODE_HTM; - if (cpu_has_feature(CPU_FTRS_POWER6)) - dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_ALTIVEC); + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + dialect |= PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2; - if (cpu_has_feature(CPU_FTRS_POWER7)) - dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 - | PPC_OPCODE_ALTIVEC | PPC_OPCODE_VSX); - - if (cpu_has_feature(CPU_FTRS_POWER8)) - dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 - | PPC_OPCODE_POWER8 | PPC_OPCODE_HTM - | PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2 | PPC_OPCODE_VSX); - - if (cpu_has_feature(CPU_FTRS_POWER9)) - dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 - | PPC_OPCODE_POWER8 | PPC_OPCODE_POWER9 | PPC_OPCODE_HTM - | PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2 - | PPC_OPCODE_VSX | PPC_OPCODE_VSX3); + if (cpu_has_feature(CPU_FTR_VSX)) + dialect |= PPC_OPCODE_VSX | PPC_OPCODE_VSX3; /* Get the major opcode of the insn. */ opcode = NULL; diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index b3b94cd3771373..1d815405a3b4f2 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1352,7 +1352,7 @@ static int cpu_cmd(void) } termch = cpu; - if (!scanhex(&cpu)) { + if (!scanhex(&cpu) || cpu >= num_possible_cpus()) { /* print cpus waiting or in xmon */ printf("cpus stopped:"); last_cpu = first_cpu = NR_CPUS; @@ -2774,7 +2774,7 @@ static void dump_pacas(void) termch = c; /* Put c back, it wasn't 'a' */ - if (scanhex(&num)) + if (scanhex(&num) && num < num_possible_cpus()) dump_one_paca(num); else dump_one_paca(xmon_owner); @@ -2847,7 +2847,7 @@ static void dump_xives(void) termch = c; /* Put c back, it wasn't 'a' */ - if (scanhex(&num)) + if (scanhex(&num) && num < num_possible_cpus()) dump_one_xive(num); else dump_one_xive(xmon_owner); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 9c48fecc671918..1304992232adbe 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -27,6 +27,7 @@ config RISCV select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV + select ARCH_HAS_MEMBARRIER_CALLBACKS select ARCH_HAS_MMIOWB select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PMEM_API @@ -258,6 +259,11 @@ config GENERIC_HWEIGHT config FIX_EARLYCON_MEM def_bool MMU +config ILLEGAL_POINTER_VALUE + hex + default 0 if 32BIT + default 0xdead000000000000 if 64BIT + config PGTABLE_LEVELS int default 5 if 64BIT @@ -287,7 +293,6 @@ config AS_HAS_OPTION_ARCH # https://reviews.llvm.org/D123515 def_bool y depends on $(as-instr, .option arch$(comma) +m) - depends on !$(as-instr, .option arch$(comma) -i) source "arch/riscv/Kconfig.socs" source "arch/riscv/Kconfig.errata" @@ -490,8 +495,8 @@ config RISCV_ISA_SVPBMT config TOOLCHAIN_HAS_V bool default y - depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64iv) - depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32iv) + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64imv) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32imv) depends on LLD_VERSION >= 140000 || LD_VERSION >= 23800 depends on AS_HAS_OPTION_ARCH @@ -628,8 +633,7 @@ config IRQ_STACKS config THREAD_SIZE_ORDER int "Kernel stack size (in power-of-two numbers of page size)" if VMAP_STACK && EXPERT range 0 4 - default 1 if 32BIT && !KASAN - default 3 if 64BIT && KASAN + default 1 if 32BIT default 2 help Specify the Pages of thread stack size (from 4KB to 64KB), which also @@ -669,7 +673,7 @@ config RISCV_BOOT_SPINWAIT If unsure what to do here, say N. config ARCH_SUPPORTS_KEXEC - def_bool MMU + def_bool y config ARCH_SELECTS_KEXEC def_bool y @@ -677,7 +681,7 @@ config ARCH_SELECTS_KEXEC select HOTPLUG_CPU if SMP config ARCH_SUPPORTS_KEXEC_FILE - def_bool 64BIT && MMU + def_bool 64BIT config ARCH_SELECTS_KEXEC_FILE def_bool y @@ -686,9 +690,7 @@ config ARCH_SELECTS_KEXEC_FILE select KEXEC_ELF config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE - depends on CRYPTO=y - depends on CRYPTO_SHA256=y + def_bool ARCH_SUPPORTS_KEXEC_FILE config ARCH_SUPPORTS_CRASH_DUMP def_bool y diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 6833d01e2e707b..30fd6a51282853 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -29,6 +29,7 @@ config SOC_STARFIVE bool "StarFive SoCs" select PINCTRL select RESET_CONTROLLER + select ARM_AMBA help This enables support for StarFive SoC platform hardware. diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index b43a6bb7e4dcb6..4d06f340267401 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -130,12 +130,6 @@ endif libs-y += arch/riscv/lib/ libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a -PHONY += vdso_install -vdso_install: - $(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@ - $(if $(CONFIG_COMPAT),$(Q)$(MAKE) \ - $(build)=arch/riscv/kernel/compat_vdso compat_$@) - ifeq ($(KBUILD_EXTMOD),) ifeq ($(CONFIG_MMU),y) prepare: vdso_prepare @@ -147,6 +141,9 @@ vdso_prepare: prepare0 endif endif +vdso-install-y += arch/riscv/kernel/vdso/vdso.so.dbg +vdso-install-$(CONFIG_COMPAT) += arch/riscv/kernel/compat_vdso/compat_vdso.so.dbg:../compat_vdso/compat_vdso.so + ifneq ($(CONFIG_XIP_KERNEL),y) ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_ARCH_CANAAN),yy) KBUILD_IMAGE := $(boot)/loader.bin diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile index 22b13947bd131e..8e7fc0edf21d3e 100644 --- a/arch/riscv/boot/Makefile +++ b/arch/riscv/boot/Makefile @@ -17,6 +17,7 @@ KCOV_INSTRUMENT := n OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S +OBJCOPYFLAGS_loader.bin :=-O binary OBJCOPYFLAGS_xipImage :=-O binary -R .note -R .note.gnu.build-id -R .comment -S targets := Image Image.* loader loader.o loader.lds loader.bin diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi b/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi index 8275630af977d2..b8684312593e5b 100644 --- a/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi @@ -30,7 +30,6 @@ cpu0: cpu@0 { cpu0_intc: interrupt-controller { compatible = "riscv,cpu-intc"; interrupt-controller; - #address-cells = <0>; #interrupt-cells = <1>; }; }; diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index 07387f9c135ca7..72b87b08ab444e 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -123,6 +123,7 @@ pmic@58 { interrupt-parent = <&gpio>; interrupts = <1 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; onkey { compatible = "dlg,da9063-onkey"; diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi index 2c02358abd711a..4874e3bb42ab10 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi @@ -162,7 +162,6 @@ &i2c5 { axp15060: pmic@36 { compatible = "x-powers,axp15060"; reg = <0x36>; - interrupts = <0>; interrupt-controller; #interrupt-cells = <1>; @@ -205,6 +204,8 @@ &i2c6 { &mmc0 { max-frequency = <100000000>; + assigned-clocks = <&syscrg JH7110_SYSCLK_SDIO0_SDCARD>; + assigned-clock-rates = <50000000>; bus-width = <8>; cap-mmc-highspeed; mmc-ddr-1_8v; @@ -221,6 +222,8 @@ &mmc0 { &mmc1 { max-frequency = <100000000>; + assigned-clocks = <&syscrg JH7110_SYSCLK_SDIO1_SDCARD>; + assigned-clock-rates = <50000000>; bus-width = <4>; no-sdio; no-mmc; @@ -440,40 +443,6 @@ GPOEN_ENABLE, }; }; - tdm_pins: tdm-0 { - tx-pins { - pinmux = ; - bias-pull-up; - drive-strength = <2>; - input-disable; - input-schmitt-disable; - slew-rate = <0>; - }; - - rx-pins { - pinmux = ; - input-enable; - }; - - sync-pins { - pinmux = ; - input-enable; - }; - - pcmclk-pins { - pinmux = ; - input-enable; - }; - }; - uart0_pins: uart0-0 { tx-pins { pinmux = ; - status = "okay"; -}; - &uart0 { pinctrl-names = "default"; pinctrl-0 = <&uart0_pins>; diff --git a/arch/riscv/errata/andes/errata.c b/arch/riscv/errata/andes/errata.c index 197db68cc8daf7..17a90486972468 100644 --- a/arch/riscv/errata/andes/errata.c +++ b/arch/riscv/errata/andes/errata.c @@ -38,29 +38,35 @@ static long ax45mp_iocp_sw_workaround(void) return ret.error ? 0 : ret.value; } -static bool errata_probe_iocp(unsigned int stage, unsigned long arch_id, unsigned long impid) +static void errata_probe_iocp(unsigned int stage, unsigned long arch_id, unsigned long impid) { + static bool done; + if (!IS_ENABLED(CONFIG_ERRATA_ANDES_CMO)) - return false; + return; + + if (done) + return; + + done = true; if (arch_id != ANDESTECH_AX45MP_MARCHID || impid != ANDESTECH_AX45MP_MIMPID) - return false; + return; if (!ax45mp_iocp_sw_workaround()) - return false; + return; /* Set this just to make core cbo code happy */ riscv_cbom_block_size = 1; riscv_noncoherent_supported(); - - return true; } void __init_or_module andes_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, unsigned long archid, unsigned long impid, unsigned int stage) { - errata_probe_iocp(stage, archid, impid); + if (stage == RISCV_ALTERNATIVES_BOOT) + errata_probe_iocp(stage, archid, impid); /* we have nothing to patch here ATM so just return back */ } diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h index 61ba8ed43d8feb..36b955c762ba08 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -25,7 +25,6 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s); DECLARE_DO_ERROR_INFO(do_trap_ecall_m); DECLARE_DO_ERROR_INFO(do_trap_break); -asmlinkage unsigned long get_overflow_stack(void); asmlinkage void handle_bad_stack(struct pt_regs *regs); asmlinkage void do_page_fault(struct pt_regs *regs); asmlinkage void do_irq(struct pt_regs *regs); diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index 114bbadaef41eb..b5b84c6be01e16 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -82,6 +82,28 @@ .endr .endm +#ifdef CONFIG_SMP +#ifdef CONFIG_32BIT +#define PER_CPU_OFFSET_SHIFT 2 +#else +#define PER_CPU_OFFSET_SHIFT 3 +#endif + +.macro asm_per_cpu dst sym tmp + REG_L \tmp, TASK_TI_CPU_NUM(tp) + slli \tmp, \tmp, PER_CPU_OFFSET_SHIFT + la \dst, __per_cpu_offset + add \dst, \dst, \tmp + REG_L \tmp, 0(\dst) + la \dst, \sym + add \dst, \dst, \tmp +.endm +#else /* CONFIG_SMP */ +.macro asm_per_cpu dst sym tmp + la \dst, \sym +.endm +#endif /* CONFIG_SMP */ + /* save all GPs except x1 ~ x5 */ .macro save_from_x6_to_x31 REG_S x6, PT_T1(sp) @@ -142,6 +164,16 @@ REG_L x31, PT_T6(sp) .endm +/* Annotate a function as being unsuitable for kprobes. */ +#ifdef CONFIG_KPROBES +#define ASM_NOKPROBE(name) \ + .pushsection "_kprobe_blacklist", "aw"; \ + RISCV_PTR name; \ + .popsection +#else +#define ASM_NOKPROBE(name) +#endif + #endif /* __ASSEMBLY__ */ #endif /* _ASM_RISCV_ASM_H */ diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 3cb53c4df27cfe..a129dac4521d35 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -37,7 +37,8 @@ static inline void flush_dcache_page(struct page *page) flush_icache_mm(vma->vm_mm, 0) #ifdef CONFIG_64BIT -#define flush_cache_vmap(start, end) flush_tlb_kernel_range(start, end) +#define flush_cache_vmap(start, end) flush_tlb_kernel_range(start, end) +#define flush_cache_vmap_early(start, end) local_flush_tlb_kernel_range(start, end) #endif #ifndef CONFIG_SMP diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h index b55b434f005910..d3f3c237adad74 100644 --- a/arch/riscv/include/asm/errata_list.h +++ b/arch/riscv/include/asm/errata_list.h @@ -44,11 +44,21 @@ ALTERNATIVE(__stringify(RISCV_PTR do_page_fault), \ CONFIG_ERRATA_SIFIVE_CIP_453) #else /* !__ASSEMBLY__ */ -#define ALT_FLUSH_TLB_PAGE(x) \ +#define ALT_SFENCE_VMA_ASID(asid) \ +asm(ALTERNATIVE("sfence.vma x0, %0", "sfence.vma", SIFIVE_VENDOR_ID, \ + ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200) \ + : : "r" (asid) : "memory") + +#define ALT_SFENCE_VMA_ADDR(addr) \ asm(ALTERNATIVE("sfence.vma %0", "sfence.vma", SIFIVE_VENDOR_ID, \ ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200) \ : : "r" (addr) : "memory") +#define ALT_SFENCE_VMA_ADDR_ASID(addr, asid) \ +asm(ALTERNATIVE("sfence.vma %0, %1", "sfence.vma", SIFIVE_VENDOR_ID, \ + ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200) \ + : : "r" (addr), "r" (asid) : "memory") + /* * _val is marked as "will be overwritten", so need to set it to 0 * in the default case. diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 2b2f5df7ef2c7d..42777f91a9c580 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -25,6 +25,11 @@ #define ARCH_SUPPORTS_FTRACE_OPS 1 #ifndef __ASSEMBLY__ + +extern void *return_address(unsigned int level); + +#define ftrace_return_address(n) return_address(n) + void MCOUNT_NAME(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index 4c5b0e929890fa..22deb7a2a6ec4e 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -11,6 +11,11 @@ static inline void arch_clear_hugepage_flags(struct page *page) } #define arch_clear_hugepage_flags arch_clear_hugepage_flags +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION +bool arch_hugetlb_migration_supported(struct hstate *h); +#define arch_hugetlb_migration_supported arch_hugetlb_migration_supported +#endif + #ifdef CONFIG_RISCV_ISA_SVNAPOT #define __HAVE_ARCH_HUGE_PTE_CLEAR void huge_pte_clear(struct mm_struct *mm, unsigned long addr, diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index b7b58258f6c7c0..f4157034efa9cb 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -98,7 +98,7 @@ riscv_has_extension_likely(const unsigned long ext) "ext must be < RISCV_ISA_EXT_MAX"); if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { - asm_volatile_goto( + asm goto( ALTERNATIVE("j %l[l_no]", "nop", 0, %[ext], 1) : : [ext] "i" (ext) @@ -121,7 +121,7 @@ riscv_has_extension_unlikely(const unsigned long ext) "ext must be < RISCV_ISA_EXT_MAX"); if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { - asm_volatile_goto( + asm goto( ALTERNATIVE("nop", "j %l[l_yes]", 0, %[ext], 1) : : [ext] "i" (ext) diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index 78936f4ff51330..7cad513538d8d0 100644 --- a/arch/riscv/include/asm/hwprobe.h +++ b/arch/riscv/include/asm/hwprobe.h @@ -10,4 +10,9 @@ #define RISCV_HWPROBE_MAX_KEY 5 +static inline bool riscv_hwprobe_key_is_valid(__s64 key) +{ + return key >= 0 && key <= RISCV_HWPROBE_MAX_KEY; +} + #endif diff --git a/arch/riscv/include/asm/insn.h b/arch/riscv/include/asm/insn.h index 06e439eeef9ada..09fde95a5e8f75 100644 --- a/arch/riscv/include/asm/insn.h +++ b/arch/riscv/include/asm/insn.h @@ -145,7 +145,7 @@ /* parts of opcode for RVF, RVD and RVQ */ #define RVFDQ_FL_FS_WIDTH_OFF 12 -#define RVFDQ_FL_FS_WIDTH_MASK GENMASK(3, 0) +#define RVFDQ_FL_FS_WIDTH_MASK GENMASK(2, 0) #define RVFDQ_FL_FS_WIDTH_W 2 #define RVFDQ_FL_FS_WIDTH_D 3 #define RVFDQ_LS_FS_WIDTH_Q 4 diff --git a/arch/riscv/include/asm/irq_work.h b/arch/riscv/include/asm/irq_work.h index b53891964ae037..b27a4d64fc6a04 100644 --- a/arch/riscv/include/asm/irq_work.h +++ b/arch/riscv/include/asm/irq_work.h @@ -6,5 +6,5 @@ static inline bool arch_irq_work_has_interrupt(void) { return IS_ENABLED(CONFIG_SMP); } -extern void arch_irq_work_raise(void); + #endif /* _ASM_RISCV_IRQ_WORK_H */ diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h index 14a5ea8d8ef0f4..4a35d787c01914 100644 --- a/arch/riscv/include/asm/jump_label.h +++ b/arch/riscv/include/asm/jump_label.h @@ -17,7 +17,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( " .align 2 \n\t" " .option push \n\t" " .option norelax \n\t" @@ -39,7 +39,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( " .align 2 \n\t" " .option push \n\t" " .option norelax \n\t" diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h index 0bbffd528096d9..7388edd88986f9 100644 --- a/arch/riscv/include/asm/kfence.h +++ b/arch/riscv/include/asm/kfence.h @@ -18,9 +18,9 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) pte_t *pte = virt_to_kpte(addr); if (protect) - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT)); + set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~_PAGE_PRESENT)); else - set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT)); + set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT)); flush_tlb_kernel_range(addr, addr + PAGE_SIZE); diff --git a/arch/riscv/include/asm/kvm_vcpu_pmu.h b/arch/riscv/include/asm/kvm_vcpu_pmu.h index 395518a1664e00..a50a1d23523fea 100644 --- a/arch/riscv/include/asm/kvm_vcpu_pmu.h +++ b/arch/riscv/include/asm/kvm_vcpu_pmu.h @@ -10,6 +10,7 @@ #define __KVM_VCPU_RISCV_PMU_H #include +#include #include #ifdef CONFIG_RISCV_PMU_SBI @@ -57,11 +58,11 @@ struct kvm_pmu { #if defined(CONFIG_32BIT) #define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ -{.base = CSR_CYCLEH, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, \ -{.base = CSR_CYCLE, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, +{.base = CSR_CYCLEH, .count = 32, .func = kvm_riscv_vcpu_pmu_read_hpm }, \ +{.base = CSR_CYCLE, .count = 32, .func = kvm_riscv_vcpu_pmu_read_hpm }, #else #define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ -{.base = CSR_CYCLE, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, +{.base = CSR_CYCLE, .count = 32, .func = kvm_riscv_vcpu_pmu_read_hpm }, #endif int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid); @@ -92,8 +93,20 @@ void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu); struct kvm_pmu { }; +static inline int kvm_riscv_vcpu_pmu_read_legacy(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask) +{ + if (csr_num == CSR_CYCLE || csr_num == CSR_INSTRET) { + *val = 0; + return KVM_INSN_CONTINUE_NEXT_SEPC; + } else { + return KVM_INSN_ILLEGAL_TRAP; + } +} + #define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ -{.base = 0, .count = 0, .func = NULL }, +{.base = CSR_CYCLE, .count = 3, .func = kvm_riscv_vcpu_pmu_read_legacy }, static inline void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) {} static inline int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid) diff --git a/arch/riscv/include/asm/membarrier.h b/arch/riscv/include/asm/membarrier.h new file mode 100644 index 00000000000000..6c016ebb5020af --- /dev/null +++ b/arch/riscv/include/asm/membarrier.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_RISCV_MEMBARRIER_H +#define _ASM_RISCV_MEMBARRIER_H + +static inline void membarrier_arch_switch_mm(struct mm_struct *prev, + struct mm_struct *next, + struct task_struct *tsk) +{ + /* + * Only need the full barrier when switching between processes. + * Barrier when switching from kernel to userspace is not + * required here, given that it is implied by mmdrop(). Barrier + * when switching from userspace to kernel is not needed after + * store to rq->curr. + */ + if (IS_ENABLED(CONFIG_SMP) && + likely(!(atomic_read(&next->membarrier_state) & + (MEMBARRIER_STATE_PRIVATE_EXPEDITED | + MEMBARRIER_STATE_GLOBAL_EXPEDITED)) || !prev)) + return; + + /* + * The membarrier system call requires a full memory barrier + * after storing to rq->curr, before going back to user-space. + * Matches a full barrier in the proximity of the membarrier + * system call entry. + */ + smp_mb(); +} + +#endif /* _ASM_RISCV_MEMBARRIER_H */ diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 5488ecc337b63f..94b3d6930fc370 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -33,8 +33,8 @@ #define PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL) #endif /* - * By default, CONFIG_PAGE_OFFSET value corresponds to SV48 address space so - * define the PAGE_OFFSET value for SV39. + * By default, CONFIG_PAGE_OFFSET value corresponds to SV57 address space so + * define the PAGE_OFFSET value for SV48 and SV39. */ #define PAGE_OFFSET_L4 _AC(0xffffaf8000000000, UL) #define PAGE_OFFSET_L3 _AC(0xffffffd800000000, UL) @@ -89,7 +89,7 @@ typedef struct page *pgtable_t; #define PTE_FMT "%08lx" #endif -#ifdef CONFIG_64BIT +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) /* * We override this value as its generic definition uses __pa too early in * the boot process (before kernel_map.va_pa_offset is set). diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index 7a5097202e1570..3272ca7a5270bf 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -198,7 +198,7 @@ static inline int pud_user(pud_t pud) static inline void set_pud(pud_t *pudp, pud_t pud) { - *pudp = pud; + WRITE_ONCE(*pudp, pud); } static inline void pud_clear(pud_t *pudp) @@ -274,7 +274,7 @@ static inline unsigned long _pmd_pfn(pmd_t pmd) static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) { if (pgtable_l4_enabled) - *p4dp = p4d; + WRITE_ONCE(*p4dp, p4d); else set_pud((pud_t *)p4dp, (pud_t){ p4d_val(p4d) }); } @@ -336,18 +336,12 @@ static inline struct page *p4d_page(p4d_t p4d) #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) #define pud_offset pud_offset -static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) -{ - if (pgtable_l4_enabled) - return p4d_pgtable(*p4d) + pud_index(address); - - return (pud_t *)p4d; -} +pud_t *pud_offset(p4d_t *p4d, unsigned long address); static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) { if (pgtable_l5_enabled) - *pgdp = pgd; + WRITE_ONCE(*pgdp, pgd); else set_p4d((p4d_t *)pgdp, (p4d_t){ pgd_val(pgd) }); } @@ -400,12 +394,6 @@ static inline struct page *pgd_page(pgd_t pgd) #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) #define p4d_offset p4d_offset -static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) -{ - if (pgtable_l5_enabled) - return pgd_pgtable(*pgd) + p4d_index(address); - - return (p4d_t *)pgd; -} +p4d_t *p4d_offset(pgd_t *pgd, unsigned long address); #endif /* _ASM_RISCV_PGTABLE_64_H */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index b2ba3f79cfe9a7..37829dab4a0a48 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -84,7 +84,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START) +#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)) #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START @@ -248,7 +248,7 @@ static inline int pmd_leaf(pmd_t pmd) static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); } static inline void pmd_clear(pmd_t *pmdp) @@ -438,6 +438,12 @@ static inline pte_t pte_mkhuge(pte_t pte) return pte; } +#ifdef CONFIG_RISCV_ISA_SVNAPOT +#define pte_leaf_size(pte) (pte_napot(pte) ? \ + napot_cont_size(napot_cont_order(pte)) :\ + PAGE_SIZE) +#endif + #ifdef CONFIG_NUMA_BALANCING /* * See the comment in include/asm-generic/pgtable.h @@ -509,7 +515,7 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b) */ static inline void set_pte(pte_t *ptep, pte_t pteval) { - *ptep = pteval; + WRITE_ONCE(*ptep, pteval); } void flush_icache_pte(pte_t pte); @@ -543,19 +549,12 @@ static inline void pte_clear(struct mm_struct *mm, __set_pte_at(ptep, __pte(0)); } -#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -static inline int ptep_set_access_flags(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, - pte_t entry, int dirty) -{ - if (!pte_same(*ptep, entry)) - __set_pte_at(ptep, entry); - /* - * update_mmu_cache will unconditionally execute, handling both - * the case that the PTE changed and the spurious fault case. - */ - return true; -} +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS /* defined in mm/pgtable.c */ +extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, pte_t entry, int dirty); +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG /* defined in mm/pgtable.c */ +extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep); #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, @@ -568,16 +567,6 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, return pte; } -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, - pte_t *ptep) -{ - if (!pte_young(*ptep)) - return 0; - return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep)); -} - #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) @@ -880,7 +869,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) #define TASK_SIZE_MIN (PGDIR_SIZE_L3 * PTRS_PER_PGD / 2) #ifdef CONFIG_COMPAT -#define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE) +#define TASK_SIZE_32 (_AC(0x80000000, UL)) #define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \ TASK_SIZE_32 : TASK_SIZE_64) #else @@ -897,8 +886,8 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) #define PAGE_SHARED __pgprot(0) #define PAGE_KERNEL __pgprot(0) #define swapper_pg_dir NULL -#define TASK_SIZE 0xffffffffUL -#define VMALLOC_START 0 +#define TASK_SIZE _AC(-1, UL) +#define VMALLOC_START _AC(0, UL) #define VMALLOC_END TASK_SIZE #endif /* !CONFIG_MMU */ diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 3e23e1786d0521..4f6af8c6cfa060 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -15,7 +15,7 @@ #ifdef CONFIG_64BIT #define DEFAULT_MAP_WINDOW (UL(1) << (MMAP_VA_BITS - 1)) -#define STACK_TOP_MAX TASK_SIZE_64 +#define STACK_TOP_MAX TASK_SIZE #define arch_get_mmap_end(addr, len, flags) \ ({ \ diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 5b4a1bf5f4395c..3ed853b8a8c858 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -273,9 +273,6 @@ void sbi_set_timer(uint64_t stime_value); void sbi_shutdown(void); void sbi_send_ipi(unsigned int cpu); int sbi_remote_fence_i(const struct cpumask *cpu_mask); -int sbi_remote_sfence_vma(const struct cpumask *cpu_mask, - unsigned long start, - unsigned long size); int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask, unsigned long start, @@ -330,6 +327,8 @@ static inline int sbi_remote_fence_i(const struct cpumask *cpu_mask) { return -1 static inline void sbi_init(void) {} #endif /* CONFIG_RISCV_SBI */ +unsigned long riscv_get_mvendorid(void); +unsigned long riscv_get_marchid(void); unsigned long riscv_cached_mvendorid(unsigned int cpu_id); unsigned long riscv_cached_marchid(unsigned int cpu_id); unsigned long riscv_cached_mimpid(unsigned int cpu_id); diff --git a/arch/riscv/include/asm/sections.h b/arch/riscv/include/asm/sections.h index 32336e8a17cb07..a393d5035c5433 100644 --- a/arch/riscv/include/asm/sections.h +++ b/arch/riscv/include/asm/sections.h @@ -13,6 +13,7 @@ extern char _start_kernel[]; extern char __init_data_begin[], __init_data_end[]; extern char __init_text_begin[], __init_text_end[]; extern char __alt_start[], __alt_end[]; +extern char __exittext_begin[], __exittext_end[]; static inline bool is_va_kernel_text(uintptr_t va) { diff --git a/arch/riscv/include/asm/sparsemem.h b/arch/riscv/include/asm/sparsemem.h index 63acaecc337478..2f901a410586d0 100644 --- a/arch/riscv/include/asm/sparsemem.h +++ b/arch/riscv/include/asm/sparsemem.h @@ -7,7 +7,7 @@ #ifdef CONFIG_64BIT #define MAX_PHYSMEM_BITS 56 #else -#define MAX_PHYSMEM_BITS 34 +#define MAX_PHYSMEM_BITS 32 #endif /* CONFIG_64BIT */ #define SECTION_SIZE_BITS 27 #endif /* CONFIG_SPARSEMEM */ diff --git a/arch/riscv/include/asm/stacktrace.h b/arch/riscv/include/asm/stacktrace.h index f7e8ef2418b99f..b1495a7e06ce69 100644 --- a/arch/riscv/include/asm/stacktrace.h +++ b/arch/riscv/include/asm/stacktrace.h @@ -21,4 +21,9 @@ static inline bool on_thread_stack(void) return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1)); } + +#ifdef CONFIG_VMAP_STACK +DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack); +#endif /* CONFIG_VMAP_STACK */ + #endif /* _ASM_RISCV_STACKTRACE_H */ diff --git a/arch/riscv/include/asm/syscall_wrapper.h b/arch/riscv/include/asm/syscall_wrapper.h index 1d7942c8a6cbae..eeec04b7dae67b 100644 --- a/arch/riscv/include/asm/syscall_wrapper.h +++ b/arch/riscv/include/asm/syscall_wrapper.h @@ -46,9 +46,6 @@ asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *); return sys_ni_syscall(); \ } -#define COMPAT_SYS_NI(name) \ - SYSCALL_ALIAS(__riscv_compat_sys_##name, sys_ni_posix_timers); - #endif /* CONFIG_COMPAT */ #define __SYSCALL_DEFINEx(x, name, ...) \ @@ -82,6 +79,4 @@ asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *); return sys_ni_syscall(); \ } -#define SYS_NI(name) SYSCALL_ALIAS(__riscv_sys_##name, sys_ni_posix_timers); - #endif /* __ASM_SYSCALL_WRAPPER_H */ diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 1833beb00489c3..8c72d1bcdf141e 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -12,7 +12,12 @@ #include /* thread information allocation */ -#define THREAD_SIZE_ORDER CONFIG_THREAD_SIZE_ORDER +#ifdef CONFIG_KASAN +#define KASAN_STACK_ORDER 1 +#else +#define KASAN_STACK_ORDER 0 +#endif +#define THREAD_SIZE_ORDER (CONFIG_THREAD_SIZE_ORDER + KASAN_STACK_ORDER) #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) /* @@ -28,15 +33,11 @@ #define THREAD_SHIFT (PAGE_SHIFT + THREAD_SIZE_ORDER) #define OVERFLOW_STACK_SIZE SZ_4K -#define SHADOW_OVERFLOW_STACK_SIZE (1024) #define IRQ_STACK_SIZE THREAD_SIZE #ifndef __ASSEMBLY__ -extern long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE / sizeof(long)]; -extern unsigned long spin_shadow_stack; - #include #include diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h index 120bcf2ed8a878..50b63b5c15bd8b 100644 --- a/arch/riscv/include/asm/tlb.h +++ b/arch/riscv/include/asm/tlb.h @@ -15,7 +15,13 @@ static void tlb_flush(struct mmu_gather *tlb); static inline void tlb_flush(struct mmu_gather *tlb) { - flush_tlb_mm(tlb->mm); +#ifdef CONFIG_MMU + if (tlb->fullmm || tlb->need_flush_all || tlb->freed_tables) + flush_tlb_mm(tlb->mm); + else + flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, + tlb_get_unmap_size(tlb)); +#endif } #endif /* _ASM_RISCV_TLB_H */ diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index a09196f8de688e..97711d5bd8ef9a 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -11,6 +11,9 @@ #include #include +#define FLUSH_TLB_MAX_SIZE ((unsigned long)-1) +#define FLUSH_TLB_NO_ASID ((unsigned long)-1) + #ifdef CONFIG_MMU extern unsigned long asid_mask; @@ -19,10 +22,27 @@ static inline void local_flush_tlb_all(void) __asm__ __volatile__ ("sfence.vma" : : : "memory"); } +static inline void local_flush_tlb_all_asid(unsigned long asid) +{ + if (asid != FLUSH_TLB_NO_ASID) + ALT_SFENCE_VMA_ASID(asid); + else + local_flush_tlb_all(); +} + /* Flush one page from local TLB */ static inline void local_flush_tlb_page(unsigned long addr) { - ALT_FLUSH_TLB_PAGE(__asm__ __volatile__ ("sfence.vma %0" : : "r" (addr) : "memory")); + ALT_SFENCE_VMA_ADDR(addr); +} + +static inline void local_flush_tlb_page_asid(unsigned long addr, + unsigned long asid) +{ + if (asid != FLUSH_TLB_NO_ASID) + ALT_SFENCE_VMA_ADDR_ASID(addr, asid); + else + local_flush_tlb_page(addr); } #else /* CONFIG_MMU */ #define local_flush_tlb_all() do { } while (0) @@ -32,9 +52,13 @@ static inline void local_flush_tlb_page(unsigned long addr) #if defined(CONFIG_SMP) && defined(CONFIG_MMU) void flush_tlb_all(void); void flush_tlb_mm(struct mm_struct *mm); +void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, + unsigned long end, unsigned int page_size); void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr); void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); +void flush_tlb_kernel_range(unsigned long start, unsigned long end); +void local_flush_tlb_kernel_range(unsigned long start, unsigned long end); #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, @@ -51,14 +75,16 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, local_flush_tlb_all(); } -#define flush_tlb_mm(mm) flush_tlb_all() -#endif /* !CONFIG_SMP || !CONFIG_MMU */ - /* Flush a range of kernel pages */ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) { - flush_tlb_all(); + local_flush_tlb_all(); } +#define flush_tlb_mm(mm) flush_tlb_all() +#define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all() +#define local_flush_tlb_kernel_range(start, end) flush_tlb_all() +#endif /* !CONFIG_SMP || !CONFIG_MMU */ + #endif /* _ASM_RISCV_TLBFLUSH_H */ diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index ec0cab9fbddd0d..72ec1d9bd3f312 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -319,7 +319,7 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n) #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \ if (unlikely(__kr_err)) \ @@ -328,7 +328,7 @@ do { \ #define __put_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \ if (unlikely(__kr_err)) \ diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h index 14f5d27783b858..96b65a5396dfcf 100644 --- a/arch/riscv/include/asm/vdso/processor.h +++ b/arch/riscv/include/asm/vdso/processor.h @@ -14,7 +14,7 @@ static inline void cpu_relax(void) __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy)); #endif -#ifdef __riscv_zihintpause +#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE /* * Reduce instruction retirement. * This assumes the PC changes. diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h index 924d01b56c9a1e..51f6dfe19745aa 100644 --- a/arch/riscv/include/asm/vmalloc.h +++ b/arch/riscv/include/asm/vmalloc.h @@ -19,65 +19,6 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot) return true; } -#ifdef CONFIG_RISCV_ISA_SVNAPOT -#include +#endif -#define arch_vmap_pte_range_map_size arch_vmap_pte_range_map_size -static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, - u64 pfn, unsigned int max_page_shift) -{ - unsigned long map_size = PAGE_SIZE; - unsigned long size, order; - - if (!has_svnapot()) - return map_size; - - for_each_napot_order_rev(order) { - if (napot_cont_shift(order) > max_page_shift) - continue; - - size = napot_cont_size(order); - if (end - addr < size) - continue; - - if (!IS_ALIGNED(addr, size)) - continue; - - if (!IS_ALIGNED(PFN_PHYS(pfn), size)) - continue; - - map_size = size; - break; - } - - return map_size; -} - -#define arch_vmap_pte_supported_shift arch_vmap_pte_supported_shift -static inline int arch_vmap_pte_supported_shift(unsigned long size) -{ - int shift = PAGE_SHIFT; - unsigned long order; - - if (!has_svnapot()) - return shift; - - WARN_ON_ONCE(size >= PMD_SIZE); - - for_each_napot_order_rev(order) { - if (napot_cont_size(order) > size) - continue; - - if (!IS_ALIGNED(size, napot_cont_size(order))) - continue; - - shift = napot_cont_shift(order); - break; - } - - return shift; -} - -#endif /* CONFIG_RISCV_ISA_SVNAPOT */ -#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #endif /* _ASM_RISCV_VMALLOC_H */ diff --git a/arch/riscv/include/asm/xip_fixup.h b/arch/riscv/include/asm/xip_fixup.h index d4ffc3c37649ff..b65bf6306f69c6 100644 --- a/arch/riscv/include/asm/xip_fixup.h +++ b/arch/riscv/include/asm/xip_fixup.h @@ -13,7 +13,7 @@ add \reg, \reg, t0 .endm .macro XIP_FIXUP_FLASH_OFFSET reg - la t1, __data_loc + la t0, __data_loc REG_L t1, _xip_phys_offset sub \reg, \reg, t1 add \reg, \reg, t0 diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h index 10aaa83db89ef7..95050ebe9ad00b 100644 --- a/arch/riscv/include/uapi/asm/auxvec.h +++ b/arch/riscv/include/uapi/asm/auxvec.h @@ -34,7 +34,7 @@ #define AT_L3_CACHEGEOMETRY 47 /* entries in ARCH_DLINFO */ -#define AT_VECTOR_SIZE_ARCH 9 +#define AT_VECTOR_SIZE_ARCH 10 #define AT_MINSIGSTKSZ 51 #endif /* _UAPI_ASM_RISCV_AUXVEC_H */ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 95cf25d484052e..03968c06258ceb 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -7,6 +7,7 @@ ifdef CONFIG_FTRACE CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) endif CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,) @@ -46,6 +47,7 @@ obj-y += irq.o obj-y += process.o obj-y += ptrace.o obj-y += reset.o +obj-y += return_address.o obj-y += setup.o obj-y += signal.o obj-y += syscall_table.o diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index d6a75aac1d27a5..9f535d5de33f93 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -39,6 +39,7 @@ void asm_offsets(void) OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp); OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp); + OFFSET(TASK_TI_CPU_NUM, task_struct, thread_info.cpu); OFFSET(TASK_THREAD_F0, task_struct, thread.fstate.f[0]); OFFSET(TASK_THREAD_F1, task_struct, thread.fstate.f[1]); OFFSET(TASK_THREAD_F2, task_struct, thread.fstate.f[2]); diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile index b86e5e2c3aea94..62fa393b2eb2ea 100644 --- a/arch/riscv/kernel/compat_vdso/Makefile +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -76,13 +76,3 @@ quiet_cmd_compat_vdsold = VDSOLD $@ # actual build commands quiet_cmd_compat_vdsoas = VDSOAS $@ cmd_compat_vdsoas = $(COMPAT_CC) $(a_flags) $(COMPAT_CC_FLAGS) -c -o $@ $< - -# install commands for the unstripped file -quiet_cmd_compat_vdso_install = INSTALL $@ - cmd_compat_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/compat_vdso/$@ - -compat_vdso.so: $(obj)/compat_vdso.so.dbg - @mkdir -p $(MODLIB)/compat_vdso - $(call cmd,compat_vdso_install) - -compat_vdso_install: compat_vdso.so diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index c17dacb1141cb3..88732abecd0230 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -125,19 +125,48 @@ int __init riscv_early_of_processor_hartid(struct device_node *node, unsigned lo */ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid) { - int rc; - for (; node; node = node->parent) { if (of_device_is_compatible(node, "riscv")) { - rc = riscv_of_processor_hartid(node, hartid); - if (!rc) - return 0; + *hartid = (unsigned long)of_get_cpu_hwid(node, 0); + if (*hartid == ~0UL) { + pr_warn("Found CPU without hart ID\n"); + return -ENODEV; + } + return 0; } } return -1; } +unsigned long __init riscv_get_marchid(void) +{ + struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); + +#if IS_ENABLED(CONFIG_RISCV_SBI) + ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); +#elif IS_ENABLED(CONFIG_RISCV_M_MODE) + ci->marchid = csr_read(CSR_MARCHID); +#else + ci->marchid = 0; +#endif + return ci->marchid; +} + +unsigned long __init riscv_get_mvendorid(void) +{ + struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); + +#if IS_ENABLED(CONFIG_RISCV_SBI) + ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); +#elif IS_ENABLED(CONFIG_RISCV_M_MODE) + ci->mvendorid = csr_read(CSR_MVENDORID); +#else + ci->mvendorid = 0; +#endif + return ci->mvendorid; +} + DEFINE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); unsigned long riscv_cached_mvendorid(unsigned int cpu_id) @@ -169,12 +198,16 @@ static int riscv_cpuinfo_starting(unsigned int cpu) struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); #if IS_ENABLED(CONFIG_RISCV_SBI) - ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); - ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); + if (!ci->mvendorid) + ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); + if (!ci->marchid) + ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); ci->mimpid = sbi_spec_is_0_1() ? 0 : sbi_get_mimpid(); #elif IS_ENABLED(CONFIG_RISCV_M_MODE) - ci->mvendorid = csr_read(CSR_MVENDORID); - ci->marchid = csr_read(CSR_MARCHID); + if (!ci->mvendorid) + ci->mvendorid = csr_read(CSR_MVENDORID); + if (!ci->marchid) + ci->marchid = csr_read(CSR_MARCHID); ci->mimpid = csr_read(CSR_MIMPID); #else ci->mvendorid = 0; diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c index efa0f0816634c4..93cbc38d180571 100644 --- a/arch/riscv/kernel/cpu_ops_sbi.c +++ b/arch/riscv/kernel/cpu_ops_sbi.c @@ -72,7 +72,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle) /* Make sure tidle is updated */ smp_mb(); bdata->task_ptr = tidle; - bdata->stack_ptr = task_stack_page(tidle) + THREAD_SIZE; + bdata->stack_ptr = task_pt_regs(tidle); /* Make sure boot data is updated */ smp_mb(); hsm_data = __pa(bdata); diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c index d98d19226b5f51..691e0c5366d2bd 100644 --- a/arch/riscv/kernel/cpu_ops_spinwait.c +++ b/arch/riscv/kernel/cpu_ops_spinwait.c @@ -34,8 +34,7 @@ static void cpu_update_secondary_bootdata(unsigned int cpuid, /* Make sure tidle is updated */ smp_mb(); - WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid], - task_stack_page(tidle) + THREAD_SIZE); + WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid], task_pt_regs(tidle)); WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle); } diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 1cfbba65d11ae3..bb5fb2b820a21e 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include "copy-unaligned.h" @@ -350,6 +351,8 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) struct acpi_table_header *rhct; acpi_status status; unsigned int cpu; + u64 boot_vendorid; + u64 boot_archid; if (!acpi_disabled) { status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); @@ -357,6 +360,9 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) return; } + boot_vendorid = riscv_get_mvendorid(); + boot_archid = riscv_get_marchid(); + for_each_possible_cpu(cpu) { struct riscv_isainfo *isainfo = &hart_isa[cpu]; unsigned long this_hwcap = 0; @@ -396,6 +402,19 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) set_bit(RISCV_ISA_EXT_ZIHPM, isainfo->isa); } + /* + * "V" in ISA strings is ambiguous in practice: it should mean + * just the standard V-1.0 but vendors aren't well behaved. + * Many vendors with T-Head CPU cores which implement the 0.7.1 + * version of the vector specification put "v" into their DTs. + * CPU cores with the ratified spec will contain non-zero + * marchid. + */ + if (acpi_disabled && boot_vendorid == THEAD_VENDOR_ID && boot_archid == 0x0) { + this_hwcap &= ~isa2hwcap[RISCV_ISA_EXT_v]; + clear_bit(RISCV_ISA_EXT_v, isainfo->isa); + } + /* * All "okay" hart should have same isa. Set HWCAP based on * common capabilities of every "okay" hart, in case they don't @@ -568,6 +587,10 @@ void check_unaligned_access(int cpu) void *src; long speed = RISCV_HWPROBE_MISALIGNED_SLOW; + /* We are already set since the last check */ + if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN) + return; + page = alloc_pages(GFP_NOWAIT, get_order(MISALIGNED_BUFFER_SIZE)); if (!page) { pr_warn("Can't alloc pages to measure memcpy performance"); diff --git a/arch/riscv/kernel/crash_core.c b/arch/riscv/kernel/crash_core.c index 55f1d7856b5448..8706736fd4e2dc 100644 --- a/arch/riscv/kernel/crash_core.c +++ b/arch/riscv/kernel/crash_core.c @@ -5,17 +5,19 @@ void arch_crash_save_vmcoreinfo(void) { - VMCOREINFO_NUMBER(VA_BITS); VMCOREINFO_NUMBER(phys_ram_base); vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET); vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", VMALLOC_START); vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END); +#ifdef CONFIG_MMU + VMCOREINFO_NUMBER(VA_BITS); vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START); vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END); #ifdef CONFIG_64BIT vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR); vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); +#endif #endif vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR); vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n", diff --git a/arch/riscv/kernel/efi.c b/arch/riscv/kernel/efi.c index aa6209a74c83ff..b64bf1624a0529 100644 --- a/arch/riscv/kernel/efi.c +++ b/arch/riscv/kernel/efi.c @@ -60,7 +60,7 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) { efi_memory_desc_t *md = data; - pte_t pte = READ_ONCE(*ptep); + pte_t pte = ptep_get(ptep); unsigned long val; if (md->attribute & EFI_MEMORY_RO) { diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index e60fbd8660c4a5..8c32bf1eedda08 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -444,6 +444,12 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, *(u32 *)loc = CLEAN_IMM(CJTYPE, *(u32 *)loc) | ENCODE_CJTYPE_IMM(val - addr); break; + case R_RISCV_ADD16: + *(u16 *)loc += val; + break; + case R_RISCV_SUB16: + *(u16 *)loc -= val; + break; case R_RISCV_ADD32: *(u32 *)loc += val; break; diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 143a2bb3e69760..1f90fee24a8ba8 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -10,9 +10,13 @@ #include #include #include +#include #include #include #include +#include + + .section .irqentry.text, "ax" SYM_CODE_START(handle_exception) /* @@ -101,6 +105,7 @@ _save_context: 1: tail do_trap_unknown SYM_CODE_END(handle_exception) +ASM_NOKPROBE(handle_exception) /* * The ret_from_exception must be called with interrupt disabled. Here is the @@ -167,70 +172,19 @@ SYM_CODE_START_NOALIGN(ret_from_exception) sret #endif SYM_CODE_END(ret_from_exception) +ASM_NOKPROBE(ret_from_exception) #ifdef CONFIG_VMAP_STACK SYM_CODE_START_LOCAL(handle_kernel_stack_overflow) - /* - * Takes the psuedo-spinlock for the shadow stack, in case multiple - * harts are concurrently overflowing their kernel stacks. We could - * store any value here, but since we're overflowing the kernel stack - * already we only have SP to use as a scratch register. So we just - * swap in the address of the spinlock, as that's definately non-zero. - * - * Pairs with a store_release in handle_bad_stack(). - */ -1: la sp, spin_shadow_stack - REG_AMOSWAP_AQ sp, sp, (sp) - bnez sp, 1b - - la sp, shadow_stack - addi sp, sp, SHADOW_OVERFLOW_STACK_SIZE - - //save caller register to shadow stack - addi sp, sp, -(PT_SIZE_ON_STACK) - REG_S x1, PT_RA(sp) - REG_S x5, PT_T0(sp) - REG_S x6, PT_T1(sp) - REG_S x7, PT_T2(sp) - REG_S x10, PT_A0(sp) - REG_S x11, PT_A1(sp) - REG_S x12, PT_A2(sp) - REG_S x13, PT_A3(sp) - REG_S x14, PT_A4(sp) - REG_S x15, PT_A5(sp) - REG_S x16, PT_A6(sp) - REG_S x17, PT_A7(sp) - REG_S x28, PT_T3(sp) - REG_S x29, PT_T4(sp) - REG_S x30, PT_T5(sp) - REG_S x31, PT_T6(sp) + /* we reach here from kernel context, sscratch must be 0 */ + csrrw x31, CSR_SCRATCH, x31 + asm_per_cpu sp, overflow_stack, x31 + li x31, OVERFLOW_STACK_SIZE + add sp, sp, x31 + /* zero out x31 again and restore x31 */ + xor x31, x31, x31 + csrrw x31, CSR_SCRATCH, x31 - la ra, restore_caller_reg - tail get_overflow_stack - -restore_caller_reg: - //save per-cpu overflow stack - REG_S a0, -8(sp) - //restore caller register from shadow_stack - REG_L x1, PT_RA(sp) - REG_L x5, PT_T0(sp) - REG_L x6, PT_T1(sp) - REG_L x7, PT_T2(sp) - REG_L x10, PT_A0(sp) - REG_L x11, PT_A1(sp) - REG_L x12, PT_A2(sp) - REG_L x13, PT_A3(sp) - REG_L x14, PT_A4(sp) - REG_L x15, PT_A5(sp) - REG_L x16, PT_A6(sp) - REG_L x17, PT_A7(sp) - REG_L x28, PT_T3(sp) - REG_L x29, PT_T4(sp) - REG_L x30, PT_T5(sp) - REG_L x31, PT_T6(sp) - - //load per-cpu overflow stack - REG_L sp, -8(sp) addi sp, sp, -(PT_SIZE_ON_STACK) //save context to overflow stack @@ -254,6 +208,7 @@ restore_caller_reg: move a0, sp tail handle_bad_stack SYM_CODE_END(handle_kernel_stack_overflow) +ASM_NOKPROBE(handle_kernel_stack_overflow) #endif SYM_CODE_START(ret_from_fork) @@ -264,8 +219,8 @@ SYM_CODE_START(ret_from_fork) jalr s0 1: move a0, sp /* pt_regs */ - la ra, ret_from_exception - tail syscall_exit_to_user_mode + call syscall_exit_to_user_mode + j ret_from_exception SYM_CODE_END(ret_from_fork) /* diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 3710ea5d160f30..9691fa8f2faa7b 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -88,6 +88,7 @@ relocate_enable_mmu: /* Compute satp for kernel page tables, but don't load it yet */ srl a2, a0, PAGE_SHIFT la a1, satp_mode + XIP_FIXUP_OFFSET a1 REG_L a1, 0(a1) or a2, a2, a1 @@ -304,6 +305,9 @@ clear_bss_done: #else mv a0, a1 #endif /* CONFIG_BUILTIN_DTB */ + /* Set trap vector to spin forever to help debug */ + la a3, .Lsecondary_park + csrw CSR_TVEC, a3 call setup_vm #ifdef CONFIG_MMU la a0, early_pg_dir diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c index 2d139b724bc842..ccb0c5d5c63c42 100644 --- a/arch/riscv/kernel/machine_kexec.c +++ b/arch/riscv/kernel/machine_kexec.c @@ -147,20 +147,12 @@ static void machine_kexec_mask_interrupts(void) for_each_irq_desc(i, desc) { struct irq_chip *chip; - int ret; chip = irq_desc_get_chip(desc); if (!chip) continue; - /* - * First try to remove the active state. If this - * fails, try to EOI the interrupt. - */ - ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false); - - if (ret && irqd_irq_inprogress(&desc->irq_data) && - chip->irq_eoi) + if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) chip->irq_eoi(&desc->irq_data); if (chip->irq_mask) diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 7c651d55fcbd2f..df4f6fec5d1740 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -440,7 +440,8 @@ void *module_alloc(unsigned long size) { return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, GFP_KERNEL, - PAGE_KERNEL, 0, NUMA_NO_NODE, + PAGE_KERNEL, VM_FLUSH_RESET_PERMS, + NUMA_NO_NODE, __builtin_return_address(0)); } #endif diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 13ee7bf589a15e..30e12b310cab73 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -14,6 +14,7 @@ #include #include #include +#include struct patch_insn { void *addr; @@ -25,6 +26,14 @@ struct patch_insn { int riscv_patch_in_stop_machine = false; #ifdef CONFIG_MMU + +static inline bool is_kernel_exittext(uintptr_t addr) +{ + return system_state < SYSTEM_RUNNING && + addr >= (uintptr_t)__exittext_begin && + addr < (uintptr_t)__exittext_end; +} + /* * The fix_to_virt(, idx) needs a const value (not a dynamic variable of * reg-a0) or BUILD_BUG_ON failed with "idx >= __end_of_fixed_addresses". @@ -35,7 +44,7 @@ static __always_inline void *patch_map(void *addr, const unsigned int fixmap) uintptr_t uintaddr = (uintptr_t) addr; struct page *page; - if (core_kernel_text(uintaddr)) + if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr)) page = phys_to_page(__pa_symbol(addr)); else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) page = vmalloc_to_page(addr); @@ -71,6 +80,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len) */ lockdep_assert_held(&text_mutex); + preempt_disable(); + if (across_pages) patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1); @@ -83,6 +94,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len) if (across_pages) patch_unmap(FIX_TEXT_POKE1); + preempt_enable(); + return 0; } NOKPROBE_SYMBOL(__patch_insn_set); @@ -113,6 +126,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len) if (!riscv_patch_in_stop_machine) lockdep_assert_held(&text_mutex); + preempt_disable(); + if (across_pages) patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1); @@ -125,6 +140,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len) if (across_pages) patch_unmap(FIX_TEXT_POKE1); + preempt_enable(); + return ret; } NOKPROBE_SYMBOL(__patch_insn_write); diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c index 3348a61de7d998..2932791e938821 100644 --- a/arch/riscv/kernel/perf_callchain.c +++ b/arch/riscv/kernel/perf_callchain.c @@ -62,7 +62,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, perf_callchain_store(entry, regs->epc); fp = user_backtrace(entry, fp, regs->ra); - while (fp && !(fp & 0x3) && entry->nr < entry->max_stack) + while (fp && !(fp & 0x7) && entry->nr < entry->max_stack) fp = user_backtrace(entry, fp, 0); } diff --git a/arch/riscv/kernel/pi/cmdline_early.c b/arch/riscv/kernel/pi/cmdline_early.c index 68e786c84c949b..f6d4dedffb8422 100644 --- a/arch/riscv/kernel/pi/cmdline_early.c +++ b/arch/riscv/kernel/pi/cmdline_early.c @@ -38,8 +38,7 @@ static char *get_early_cmdline(uintptr_t dtb_pa) if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) || IS_ENABLED(CONFIG_CMDLINE_FORCE) || fdt_cmdline_size == 0 /* CONFIG_CMDLINE_FALLBACK */) { - strncat(early_cmdline, CONFIG_CMDLINE, - COMMAND_LINE_SIZE - fdt_cmdline_size); + strlcat(early_cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE); } return early_cmdline; diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c index 7142ec42e889f9..a69dfa610aa857 100644 --- a/arch/riscv/kernel/probes/ftrace.c +++ b/arch/riscv/kernel/probes/ftrace.c @@ -11,6 +11,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe_ctlblk *kcb; int bit; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index 2f08c14a933d05..fecbbcf40ac3fe 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -28,9 +28,8 @@ static void __kprobes arch_prepare_ss_slot(struct kprobe *p) p->ainsn.api.restore = (unsigned long)p->addr + offset; - patch_text(p->ainsn.api.insn, &p->opcode, 1); - patch_text((void *)((unsigned long)(p->ainsn.api.insn) + offset), - &insn, 1); + patch_text_nosync(p->ainsn.api.insn, &p->opcode, 1); + patch_text_nosync(p->ainsn.api.insn + offset, &insn, 1); } static void __kprobes arch_prepare_simulate(struct kprobe *p) diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c index d3099d67816d05..6c166029079c42 100644 --- a/arch/riscv/kernel/probes/simulate-insn.c +++ b/arch/riscv/kernel/probes/simulate-insn.c @@ -24,7 +24,7 @@ static inline bool rv_insn_reg_set_val(struct pt_regs *regs, u32 index, unsigned long val) { if (index == 0) - return false; + return true; else if (index <= 31) *((unsigned long *)regs + index) = val; else diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c index 194f166b2cc40e..4b3dc8beaf77d3 100644 --- a/arch/riscv/kernel/probes/uprobes.c +++ b/arch/riscv/kernel/probes/uprobes.c @@ -3,6 +3,7 @@ #include #include #include +#include #include "decode-insn.h" @@ -17,6 +18,11 @@ bool is_swbp_insn(uprobe_opcode_t *insn) #endif } +bool is_trap_insn(uprobe_opcode_t *insn) +{ + return riscv_insn_is_ebreak(*insn) || riscv_insn_is_c_ebreak(*insn); +} + unsigned long uprobe_get_swbp_addr(struct pt_regs *regs) { return instruction_pointer(regs); diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index e32d737e039fd4..83e223318822ae 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -26,8 +26,6 @@ #include #include -register unsigned long gp_in_global __asm__("gp"); - #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) #include unsigned long __stack_chk_guard __read_mostly; @@ -186,7 +184,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (unlikely(args->fn)) { /* Kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); - childregs->gp = gp_in_global; /* Supervisor/Machine, irqs on: */ childregs->status = SR_PP | SR_PIE; diff --git a/arch/riscv/kernel/return_address.c b/arch/riscv/kernel/return_address.c new file mode 100644 index 00000000000000..c8115ec8fb304b --- /dev/null +++ b/arch/riscv/kernel/return_address.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This code come from arch/arm64/kernel/return_address.c + * + * Copyright (C) 2023 SiFive. + */ + +#include +#include +#include + +struct return_address_data { + unsigned int level; + void *addr; +}; + +static bool save_return_addr(void *d, unsigned long pc) +{ + struct return_address_data *data = d; + + if (!data->level) { + data->addr = (void *)pc; + return false; + } + + --data->level; + + return true; +} +NOKPROBE_SYMBOL(save_return_addr); + +noinline void *return_address(unsigned int level) +{ + struct return_address_data data; + + data.level = level + 3; + data.addr = NULL; + + arch_stack_walk(save_return_addr, &data, current, NULL); + + if (!data.level) + return data.addr; + else + return NULL; + +} +EXPORT_SYMBOL_GPL(return_address); +NOKPROBE_SYMBOL(return_address); diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index c672c8ba9a2a6b..5a62ed1da45332 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -11,6 +11,7 @@ #include #include #include +#include /* default SBI version is 0.1 */ unsigned long sbi_spec_version __ro_after_init = SBI_SPEC_VERSION_DEFAULT; @@ -376,32 +377,15 @@ int sbi_remote_fence_i(const struct cpumask *cpu_mask) } EXPORT_SYMBOL(sbi_remote_fence_i); -/** - * sbi_remote_sfence_vma() - Execute SFENCE.VMA instructions on given remote - * harts for the specified virtual address range. - * @cpu_mask: A cpu mask containing all the target harts. - * @start: Start of the virtual address - * @size: Total size of the virtual address range. - * - * Return: 0 on success, appropriate linux error code otherwise. - */ -int sbi_remote_sfence_vma(const struct cpumask *cpu_mask, - unsigned long start, - unsigned long size) -{ - return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA, - cpu_mask, start, size, 0, 0); -} -EXPORT_SYMBOL(sbi_remote_sfence_vma); - /** * sbi_remote_sfence_vma_asid() - Execute SFENCE.VMA instructions on given - * remote harts for a virtual address range belonging to a specific ASID. + * remote harts for a virtual address range belonging to a specific ASID or not. * * @cpu_mask: A cpu mask containing all the target harts. * @start: Start of the virtual address * @size: Total size of the virtual address range. - * @asid: The value of address space identifier (ASID). + * @asid: The value of address space identifier (ASID), or FLUSH_TLB_NO_ASID + * for flushing all address spaces. * * Return: 0 on success, appropriate linux error code otherwise. */ @@ -410,8 +394,12 @@ int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask, unsigned long size, unsigned long asid) { - return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID, - cpu_mask, start, size, asid, 0); + if (asid == FLUSH_TLB_NO_ASID) + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA, + cpu_mask, start, size, 0, 0); + else + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID, + cpu_mask, start, size, asid, 0); } EXPORT_SYMBOL(sbi_remote_sfence_vma_asid); diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index aac853ae4eb74e..ddadee6621f0da 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -40,15 +40,8 @@ #include "head.h" -#if defined(CONFIG_DUMMY_CONSOLE) || defined(CONFIG_EFI) -struct screen_info screen_info __section(".data") = { - .orig_video_lines = 30, - .orig_video_cols = 80, - .orig_video_mode = 0, - .orig_video_ega_bx = 0, - .orig_video_isVGA = 1, - .orig_video_points = 8 -}; +#if defined(CONFIG_EFI) +struct screen_info screen_info __section(".data"); #endif /* @@ -173,6 +166,19 @@ static void __init init_resources(void) if (ret < 0) goto error; +#ifdef CONFIG_KEXEC_CORE + if (crashk_res.start != crashk_res.end) { + ret = add_resource(&iomem_resource, &crashk_res); + if (ret < 0) + goto error; + } + if (crashk_low_res.start != crashk_low_res.end) { + ret = add_resource(&iomem_resource, &crashk_low_res); + if (ret < 0) + goto error; + } +#endif + #ifdef CONFIG_CRASH_DUMP if (elfcorehdr_size > 0) { elfcorehdr_res.start = elfcorehdr_addr; diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 21a4d0e111bc5f..88b6220b260879 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -384,30 +384,6 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) sigset_t *oldset = sigmask_to_save(); int ret; - /* Are we from a system call? */ - if (regs->cause == EXC_SYSCALL) { - /* Avoid additional syscall restarting via ret_from_exception */ - regs->cause = -1UL; - /* If so, check system call restarting.. */ - switch (regs->a0) { - case -ERESTART_RESTARTBLOCK: - case -ERESTARTNOHAND: - regs->a0 = -EINTR; - break; - - case -ERESTARTSYS: - if (!(ksig->ka.sa.sa_flags & SA_RESTART)) { - regs->a0 = -EINTR; - break; - } - fallthrough; - case -ERESTARTNOINTR: - regs->a0 = regs->orig_a0; - regs->epc -= 0x4; - break; - } - } - rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ @@ -421,35 +397,66 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) void arch_do_signal_or_restart(struct pt_regs *regs) { + unsigned long continue_addr = 0, restart_addr = 0; + int retval = 0; struct ksignal ksig; + bool syscall = (regs->cause == EXC_SYSCALL); - if (get_signal(&ksig)) { - /* Actually deliver the signal */ - handle_signal(&ksig, regs); - return; - } + /* If we were from a system call, check for system call restarting */ + if (syscall) { + continue_addr = regs->epc; + restart_addr = continue_addr - 4; + retval = regs->a0; - /* Did we come from a system call? */ - if (regs->cause == EXC_SYSCALL) { /* Avoid additional syscall restarting via ret_from_exception */ regs->cause = -1UL; - /* Restart the system call - no handlers present */ - switch (regs->a0) { + /* + * Prepare for system call restart. We do this here so that a + * debugger will see the already changed PC. + */ + switch (retval) { case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: - regs->a0 = regs->orig_a0; - regs->epc -= 0x4; - break; case -ERESTART_RESTARTBLOCK: - regs->a0 = regs->orig_a0; - regs->a7 = __NR_restart_syscall; - regs->epc -= 0x4; + regs->a0 = regs->orig_a0; + regs->epc = restart_addr; break; } } + /* + * Get the signal to deliver. When running under ptrace, at this point + * the debugger may change all of our registers. + */ + if (get_signal(&ksig)) { + /* + * Depending on the signal settings, we may need to revert the + * decision to restart the system call, but skip this if a + * debugger has chosen to restart at a different PC. + */ + if (regs->epc == restart_addr && + (retval == -ERESTARTNOHAND || + retval == -ERESTART_RESTARTBLOCK || + (retval == -ERESTARTSYS && + !(ksig.ka.sa.sa_flags & SA_RESTART)))) { + regs->a0 = -EINTR; + regs->epc = continue_addr; + } + + /* Actually deliver the signal */ + handle_signal(&ksig, regs); + return; + } + + /* + * Handle restarting a different system call. As above, if a debugger + * has chosen to restart at a different PC, ignore the restart. + */ + if (syscall && regs->epc == restart_addr && retval == -ERESTART_RESTARTBLOCK) + regs->a7 = __NR_restart_syscall; + /* * If there is no signal to deliver, we just put the saved * sigmask back. diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 64a9c093aef93a..10e311b2759d39 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -18,10 +18,21 @@ extern asmlinkage void ret_from_exception(void); +static inline int fp_is_valid(unsigned long fp, unsigned long sp) +{ + unsigned long low, high; + + low = sp + sizeof(struct stackframe); + high = ALIGN(sp, THREAD_SIZE); + + return !(fp < low || fp > high || fp & 0x07); +} + void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(void *, unsigned long), void *arg) { unsigned long fp, sp, pc; + int graph_idx = 0; int level = 0; if (regs) { @@ -41,26 +52,24 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, } for (;;) { - unsigned long low, high; struct stackframe *frame; if (unlikely(!__kernel_text_address(pc) || (level++ >= 0 && !fn(arg, pc)))) break; - /* Validate frame pointer */ - low = sp + sizeof(struct stackframe); - high = ALIGN(sp, THREAD_SIZE); - if (unlikely(fp < low || fp > high || fp & 0x7)) + if (unlikely(!fp_is_valid(fp, sp))) break; + /* Unwind stack frame */ frame = (struct stackframe *)fp - 1; sp = fp; - if (regs && (regs->epc == pc) && (frame->fp & 0x7)) { + if (regs && (regs->epc == pc) && fp_is_valid(frame->ra, sp)) { + /* We hit function where ra is not saved on the stack */ fp = frame->ra; pc = regs->ra; } else { fp = frame->fp; - pc = ftrace_graph_ret_addr(current, NULL, frame->ra, + pc = ftrace_graph_ret_addr(current, &graph_idx, frame->ra, &frame->ra); if (pc == (unsigned long)ret_from_exception) { if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc))) @@ -148,7 +157,7 @@ unsigned long __get_wchan(struct task_struct *task) return pc; } -noinline void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, +noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) { walk_stackframe(task, regs, consume_entry, cookie); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index fae8f610d867fd..2158b7a65d74f7 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -311,6 +311,7 @@ asmlinkage __visible __trap_section void do_trap_ecall_u(struct pt_regs *regs) regs->epc += 4; regs->orig_a0 = regs->a0; + regs->a0 = -ENOSYS; riscv_v_vstate_discard(regs); @@ -318,8 +319,6 @@ asmlinkage __visible __trap_section void do_trap_ecall_u(struct pt_regs *regs) if (syscall >= 0 && syscall < NR_syscalls) syscall_handler(regs, syscall); - else if (syscall != -1) - regs->a0 = -ENOSYS; syscall_exit_to_user_mode(regs); } else { @@ -410,48 +409,14 @@ int is_valid_bugaddr(unsigned long pc) #endif /* CONFIG_GENERIC_BUG */ #ifdef CONFIG_VMAP_STACK -/* - * Extra stack space that allows us to provide panic messages when the kernel - * has overflowed its stack. - */ -static DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], +DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack)__aligned(16); -/* - * A temporary stack for use by handle_kernel_stack_overflow. This is used so - * we can call into C code to get the per-hart overflow stack. Usage of this - * stack must be protected by spin_shadow_stack. - */ -long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE/sizeof(long)] __aligned(16); - -/* - * A pseudo spinlock to protect the shadow stack from being used by multiple - * harts concurrently. This isn't a real spinlock because the lock side must - * be taken without a valid stack and only a single register, it's only taken - * while in the process of panicing anyway so the performance and error - * checking a proper spinlock gives us doesn't matter. - */ -unsigned long spin_shadow_stack; - -asmlinkage unsigned long get_overflow_stack(void) -{ - return (unsigned long)this_cpu_ptr(overflow_stack) + - OVERFLOW_STACK_SIZE; -} asmlinkage void handle_bad_stack(struct pt_regs *regs) { unsigned long tsk_stk = (unsigned long)current->stack; unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack); - /* - * We're done with the shadow stack by this point, as we're on the - * overflow stack. Tell any other concurrent overflowing harts that - * they can proceed with panicing by releasing the pseudo-spinlock. - * - * This pairs with an amoswap.aq in handle_kernel_stack_overflow. - */ - smp_store_release(&spin_shadow_stack, 0); - console_verbose(); pr_emerg("Insufficient stack space to handle exception!\n"); diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index 378f5b15144356..e867fe465164e2 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -151,51 +151,19 @@ #define PRECISION_S 0 #define PRECISION_D 1 -#define DECLARE_UNPRIVILEGED_LOAD_FUNCTION(type, insn) \ -static inline type load_##type(const type *addr) \ -{ \ - type val; \ - asm (#insn " %0, %1" \ - : "=&r" (val) : "m" (*addr)); \ - return val; \ -} - -#define DECLARE_UNPRIVILEGED_STORE_FUNCTION(type, insn) \ -static inline void store_##type(type *addr, type val) \ -{ \ - asm volatile (#insn " %0, %1\n" \ - : : "r" (val), "m" (*addr)); \ -} +static inline u8 load_u8(const u8 *addr) +{ + u8 val; -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u8, lbu) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u16, lhu) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s8, lb) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s16, lh) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s32, lw) -DECLARE_UNPRIVILEGED_STORE_FUNCTION(u8, sb) -DECLARE_UNPRIVILEGED_STORE_FUNCTION(u16, sh) -DECLARE_UNPRIVILEGED_STORE_FUNCTION(u32, sw) -#if defined(CONFIG_64BIT) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lwu) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u64, ld) -DECLARE_UNPRIVILEGED_STORE_FUNCTION(u64, sd) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, ld) -#else -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lw) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, lw) + asm volatile("lbu %0, %1" : "=&r" (val) : "m" (*addr)); -static inline u64 load_u64(const u64 *addr) -{ - return load_u32((u32 *)addr) - + ((u64)load_u32((u32 *)addr + 1) << 32); + return val; } -static inline void store_u64(u64 *addr, u64 val) +static inline void store_u8(u8 *addr, u8 val) { - store_u32((u32 *)addr, val); - store_u32((u32 *)addr + 1, val >> 32); + asm volatile ("sb %0, %1\n" : : "r" (val), "m" (*addr)); } -#endif static inline ulong get_insn(ulong mepc) { @@ -342,16 +310,14 @@ int handle_misaligned_store(struct pt_regs *regs) } else if ((insn & INSN_MASK_C_SD) == INSN_MATCH_C_SD) { len = 8; val.data_ulong = GET_RS2S(insn, regs); - } else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP && - ((insn >> SH_RD) & 0x1f)) { + } else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP) { len = 8; val.data_ulong = GET_RS2C(insn, regs); #endif } else if ((insn & INSN_MASK_C_SW) == INSN_MATCH_C_SW) { len = 4; val.data_ulong = GET_RS2S(insn, regs); - } else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP && - ((insn >> SH_RD) & 0x1f)) { + } else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP) { len = 4; val.data_ulong = GET_RS2C(insn, regs); } else { diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 6b1dba11bf6dcd..e8aa7c38000755 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -73,13 +73,3 @@ quiet_cmd_vdsold = VDSOLD $@ cmd_vdsold = $(LD) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \ $(OBJCOPY) $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \ rm $@.tmp - -# install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso.so: $(obj)/vdso.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso.so diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c index d40bec6ac07866..cadf725ef79837 100644 --- a/arch/riscv/kernel/vdso/hwprobe.c +++ b/arch/riscv/kernel/vdso/hwprobe.c @@ -37,7 +37,7 @@ int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, /* This is something we can handle, fill out the pairs. */ while (p < end) { - if (p->key <= RISCV_HWPROBE_MAX_KEY) { + if (riscv_hwprobe_key_is_valid(p->key)) { p->value = avd->all_cpu_hwprobe_values[p->key]; } else { diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S index 50767647fbc649..8c3daa1b05313a 100644 --- a/arch/riscv/kernel/vmlinux-xip.lds.S +++ b/arch/riscv/kernel/vmlinux-xip.lds.S @@ -29,10 +29,12 @@ SECTIONS HEAD_TEXT_SECTION INIT_TEXT_SECTION(PAGE_SIZE) /* we have to discard exit text and such at runtime, not link time */ + __exittext_begin = .; .exit.text : { EXIT_TEXT } + __exittext_end = .; .text : { _text = .; diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 492dd4b8f3d69a..002ca58dd998cb 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -69,10 +69,12 @@ SECTIONS __soc_builtin_dtb_table_end = .; } /* we have to discard exit text and such at runtime, not link time */ + __exittext_begin = .; .exit.text : { EXIT_TEXT } + __exittext_end = .; __init_text_end = .; . = ALIGN(SECTION_ALIGN); diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c index 39e72aa016a4cc..b467ba5ed91000 100644 --- a/arch/riscv/kvm/aia_aplic.c +++ b/arch/riscv/kvm/aia_aplic.c @@ -137,11 +137,21 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending) raw_spin_lock_irqsave(&irqd->lock, flags); sm = irqd->sourcecfg & APLIC_SOURCECFG_SM_MASK; - if (!pending && - ((sm == APLIC_SOURCECFG_SM_LEVEL_HIGH) || - (sm == APLIC_SOURCECFG_SM_LEVEL_LOW))) + if (sm == APLIC_SOURCECFG_SM_INACTIVE) goto skip_write_pending; + if (sm == APLIC_SOURCECFG_SM_LEVEL_HIGH || + sm == APLIC_SOURCECFG_SM_LEVEL_LOW) { + if (!pending) + goto skip_write_pending; + if ((irqd->state & APLIC_IRQ_STATE_INPUT) && + sm == APLIC_SOURCECFG_SM_LEVEL_LOW) + goto skip_write_pending; + if (!(irqd->state & APLIC_IRQ_STATE_INPUT) && + sm == APLIC_SOURCECFG_SM_LEVEL_HIGH) + goto skip_write_pending; + } + if (pending) irqd->state |= APLIC_IRQ_STATE_PENDING; else @@ -187,16 +197,31 @@ static void aplic_write_enabled(struct aplic *aplic, u32 irq, bool enabled) static bool aplic_read_input(struct aplic *aplic, u32 irq) { - bool ret; - unsigned long flags; + u32 sourcecfg, sm, raw_input, irq_inverted; struct aplic_irq *irqd; + unsigned long flags; + bool ret = false; if (!irq || aplic->nr_irqs <= irq) return false; irqd = &aplic->irqs[irq]; raw_spin_lock_irqsave(&irqd->lock, flags); - ret = (irqd->state & APLIC_IRQ_STATE_INPUT) ? true : false; + + sourcecfg = irqd->sourcecfg; + if (sourcecfg & APLIC_SOURCECFG_D) + goto skip; + + sm = sourcecfg & APLIC_SOURCECFG_SM_MASK; + if (sm == APLIC_SOURCECFG_SM_INACTIVE) + goto skip; + + raw_input = (irqd->state & APLIC_IRQ_STATE_INPUT) ? 1 : 0; + irq_inverted = (sm == APLIC_SOURCECFG_SM_LEVEL_LOW || + sm == APLIC_SOURCECFG_SM_EDGE_FALL) ? 1 : 0; + ret = !!(raw_input ^ irq_inverted); + +skip: raw_spin_unlock_irqrestore(&irqd->lock, flags); return ret; diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c index 0eb689351b7d04..5cd407c6a8e4f8 100644 --- a/arch/riscv/kvm/aia_device.c +++ b/arch/riscv/kvm/aia_device.c @@ -237,10 +237,11 @@ static gpa_t aia_imsic_ppn(struct kvm_aia *aia, gpa_t addr) static u32 aia_imsic_hart_index(struct kvm_aia *aia, gpa_t addr) { - u32 hart, group = 0; + u32 hart = 0, group = 0; - hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) & - GENMASK_ULL(aia->nr_hart_bits - 1, 0); + if (aia->nr_hart_bits) + hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) & + GENMASK_ULL(aia->nr_hart_bits - 1, 0); if (aia->nr_group_bits) group = (addr >> aia->nr_group_shift) & GENMASK_ULL(aia->nr_group_bits - 1, 0); diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c index 6cf23b8adb7129..e808723a85f1b1 100644 --- a/arch/riscv/kvm/aia_imsic.c +++ b/arch/riscv/kvm/aia_imsic.c @@ -55,6 +55,7 @@ struct imsic { /* IMSIC SW-file */ struct imsic_mrif *swfile; phys_addr_t swfile_pa; + spinlock_t swfile_extirq_lock; }; #define imsic_vs_csr_read(__c) \ @@ -613,12 +614,23 @@ static void imsic_swfile_extirq_update(struct kvm_vcpu *vcpu) { struct imsic *imsic = vcpu->arch.aia_context.imsic_state; struct imsic_mrif *mrif = imsic->swfile; + unsigned long flags; + + /* + * The critical section is necessary during external interrupt + * updates to avoid the risk of losing interrupts due to potential + * interruptions between reading topei and updating pending status. + */ + + spin_lock_irqsave(&imsic->swfile_extirq_lock, flags); if (imsic_mrif_atomic_read(mrif, &mrif->eidelivery) && imsic_mrif_topei(mrif, imsic->nr_eix, imsic->nr_msis)) kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_VS_EXT); else kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT); + + spin_unlock_irqrestore(&imsic->swfile_extirq_lock, flags); } static void imsic_swfile_read(struct kvm_vcpu *vcpu, bool clear, @@ -1039,6 +1051,7 @@ int kvm_riscv_vcpu_aia_imsic_init(struct kvm_vcpu *vcpu) } imsic->swfile = page_to_virt(swfile_page); imsic->swfile_pa = page_to_phys(swfile_page); + spin_lock_init(&imsic->swfile_extirq_lock); /* Setup IO device */ kvm_iodevice_init(&imsic->iodev, &imsic_iodoev_ops); diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 068c7459387102..a9e2fd7245e1e9 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -103,7 +103,7 @@ static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr, *ptep_level = current_level; ptep = (pte_t *)kvm->arch.pgd; ptep = &ptep[gstage_pte_index(addr, current_level)]; - while (ptep && pte_val(*ptep)) { + while (ptep && pte_val(ptep_get(ptep))) { if (gstage_pte_leaf(ptep)) { *ptep_level = current_level; *ptepp = ptep; @@ -113,7 +113,7 @@ static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr, if (current_level) { current_level--; *ptep_level = current_level; - ptep = (pte_t *)gstage_pte_page_vaddr(*ptep); + ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); ptep = &ptep[gstage_pte_index(addr, current_level)]; } else { ptep = NULL; @@ -149,25 +149,25 @@ static int gstage_set_pte(struct kvm *kvm, u32 level, if (gstage_pte_leaf(ptep)) return -EEXIST; - if (!pte_val(*ptep)) { + if (!pte_val(ptep_get(ptep))) { if (!pcache) return -ENOMEM; next_ptep = kvm_mmu_memory_cache_alloc(pcache); if (!next_ptep) return -ENOMEM; - *ptep = pfn_pte(PFN_DOWN(__pa(next_ptep)), - __pgprot(_PAGE_TABLE)); + set_pte(ptep, pfn_pte(PFN_DOWN(__pa(next_ptep)), + __pgprot(_PAGE_TABLE))); } else { if (gstage_pte_leaf(ptep)) return -EEXIST; - next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep); + next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); } current_level--; ptep = &next_ptep[gstage_pte_index(addr, current_level)]; } - *ptep = *new_pte; + set_pte(ptep, *new_pte); if (gstage_pte_leaf(ptep)) gstage_remote_tlb_flush(kvm, current_level, addr); @@ -239,11 +239,11 @@ static void gstage_op_pte(struct kvm *kvm, gpa_t addr, BUG_ON(addr & (page_size - 1)); - if (!pte_val(*ptep)) + if (!pte_val(ptep_get(ptep))) return; if (ptep_level && !gstage_pte_leaf(ptep)) { - next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep); + next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); next_ptep_level = ptep_level - 1; ret = gstage_level_to_page_size(next_ptep_level, &next_page_size); @@ -261,7 +261,7 @@ static void gstage_op_pte(struct kvm *kvm, gpa_t addr, if (op == GSTAGE_OP_CLEAR) set_pte(ptep, __pte(0)); else if (op == GSTAGE_OP_WP) - set_pte(ptep, __pte(pte_val(*ptep) & ~_PAGE_WRITE)); + set_pte(ptep, __pte(pte_val(ptep_get(ptep)) & ~_PAGE_WRITE)); gstage_remote_tlb_flush(kvm, ptep_level, addr); } } @@ -603,7 +603,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) &ptep, &ptep_level)) return false; - return pte_young(*ptep); + return pte_young(ptep_get(ptep)); } int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index b7e0e03c69b1e5..d520b25d856167 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -614,9 +614,9 @@ static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu, switch (reg_subtype) { case KVM_REG_RISCV_ISA_SINGLE: return riscv_vcpu_set_isa_ext_single(vcpu, reg_num, reg_val); - case KVM_REG_RISCV_SBI_MULTI_EN: + case KVM_REG_RISCV_ISA_MULTI_EN: return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, true); - case KVM_REG_RISCV_SBI_MULTI_DIS: + case KVM_REG_RISCV_ISA_MULTI_DIS: return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, false); default: return -ENOENT; diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index 86391a5061dda9..cee1b9ca4ec481 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -39,7 +39,7 @@ static u64 kvm_pmu_get_sample_period(struct kvm_pmc *pmc) u64 sample_period; if (!pmc->counter_val) - sample_period = counter_val_mask + 1; + sample_period = counter_val_mask; else sample_period = (-pmc->counter_val) & counter_val_mask; diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 9cd97091c72330..7a7fe40d0930be 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -91,8 +91,8 @@ void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run) run->riscv_sbi.args[3] = cp->a3; run->riscv_sbi.args[4] = cp->a4; run->riscv_sbi.args[5] = cp->a5; - run->riscv_sbi.ret[0] = cp->a0; - run->riscv_sbi.ret[1] = cp->a1; + run->riscv_sbi.ret[0] = SBI_ERR_NOT_SUPPORTED; + run->riscv_sbi.ret[1] = 0; } void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile index 9c454f90fd3da2..2c869f8026a889 100644 --- a/arch/riscv/mm/Makefile +++ b/arch/riscv/mm/Makefile @@ -13,10 +13,9 @@ endif KCOV_INSTRUMENT_init.o := n obj-y += init.o -obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o +obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o pgtable.o obj-y += cacheflush.o obj-y += context.o -obj-y += pgtable.o obj-y += pmem.o ifeq ($(CONFIG_MMU),y) @@ -36,3 +35,4 @@ endif obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o obj-$(CONFIG_RISCV_DMA_NONCOHERENT) += dma-noncoherent.o +obj-$(CONFIG_RISCV_NONSTANDARD_CACHE_OPS) += cache-ops.o diff --git a/arch/riscv/mm/cache-ops.c b/arch/riscv/mm/cache-ops.c new file mode 100644 index 00000000000000..a993ad11d0eca9 --- /dev/null +++ b/arch/riscv/mm/cache-ops.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + */ + +#include + +struct riscv_nonstd_cache_ops noncoherent_cache_ops __ro_after_init; + +void +riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops) +{ + if (!ops) + return; + noncoherent_cache_ops = *ops; +} +EXPORT_SYMBOL_GPL(riscv_noncoherent_register_cache_ops); diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c index 217fd4de613422..ba8eb3944687cf 100644 --- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -323,6 +323,8 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, if (unlikely(prev == next)) return; + membarrier_arch_switch_mm(prev, next, task); + /* * Mark the current MM context as inactive, and the next as * active. This is at least used by the icache flushing diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c index b76e7e192eb183..341bd6706b4c56 100644 --- a/arch/riscv/mm/dma-noncoherent.c +++ b/arch/riscv/mm/dma-noncoherent.c @@ -15,12 +15,6 @@ static bool noncoherent_supported __ro_after_init; int dma_cache_alignment __ro_after_init = ARCH_DMA_MINALIGN; EXPORT_SYMBOL_GPL(dma_cache_alignment); -struct riscv_nonstd_cache_ops noncoherent_cache_ops __ro_after_init = { - .wback = NULL, - .inv = NULL, - .wback_inv = NULL, -}; - static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size) { void *vaddr = phys_to_virt(paddr); @@ -162,12 +156,3 @@ void __init riscv_set_dma_cache_alignment(void) if (!noncoherent_supported) dma_cache_alignment = 1; } - -void riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops) -{ - if (!ops) - return; - - noncoherent_cache_ops = *ops; -} -EXPORT_SYMBOL_GPL(riscv_noncoherent_register_cache_ops); diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 90d4ba36d1d062..8960f4c844976f 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -61,26 +61,27 @@ static inline void no_context(struct pt_regs *regs, unsigned long addr) static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault) { + if (!user_mode(regs)) { + no_context(regs, addr); + return; + } + if (fault & VM_FAULT_OOM) { /* * We ran out of memory, call the OOM killer, and return the userspace * (which will retry the fault, or kill us if we got oom-killed). */ - if (!user_mode(regs)) { - no_context(regs, addr); - return; - } pagefault_out_of_memory(); return; } else if (fault & (VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) { /* Kernel mode? Handle exceptions or die */ - if (!user_mode(regs)) { - no_context(regs, addr); - return; - } do_trap(regs, SIGBUS, BUS_ADRERR, addr); return; + } else if (fault & VM_FAULT_SIGSEGV) { + do_trap(regs, SIGSEGV, SEGV_MAPERR, addr); + return; } + BUG(); } @@ -136,24 +137,24 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a pgd = (pgd_t *)pfn_to_virt(pfn) + index; pgd_k = init_mm.pgd + index; - if (!pgd_present(*pgd_k)) { + if (!pgd_present(pgdp_get(pgd_k))) { no_context(regs, addr); return; } - set_pgd(pgd, *pgd_k); + set_pgd(pgd, pgdp_get(pgd_k)); p4d_k = p4d_offset(pgd_k, addr); - if (!p4d_present(*p4d_k)) { + if (!p4d_present(p4dp_get(p4d_k))) { no_context(regs, addr); return; } pud_k = pud_offset(p4d_k, addr); - if (!pud_present(*pud_k)) { + if (!pud_present(pudp_get(pud_k))) { no_context(regs, addr); return; } - if (pud_leaf(*pud_k)) + if (pud_leaf(pudp_get(pud_k))) goto flush_tlb; /* @@ -161,11 +162,11 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a * to copy individual PTEs */ pmd_k = pmd_offset(pud_k, addr); - if (!pmd_present(*pmd_k)) { + if (!pmd_present(pmdp_get(pmd_k))) { no_context(regs, addr); return; } - if (pmd_leaf(*pmd_k)) + if (pmd_leaf(pmdp_get(pmd_k))) goto flush_tlb; /* @@ -175,7 +176,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a * silently loop forever. */ pte_k = pte_offset_kernel(pmd_k, addr); - if (!pte_present(*pte_k)) { + if (!pte_present(ptep_get(pte_k))) { no_context(regs, addr); return; } diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index b52f0210481fac..5ef2a6891158a6 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -54,7 +54,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, } if (sz == PMD_SIZE) { - if (want_pmd_share(vma, addr) && pud_none(*pud)) + if (want_pmd_share(vma, addr) && pud_none(pudp_get(pud))) pte = huge_pmd_share(mm, vma, addr, pud); else pte = (pte_t *)pmd_alloc(mm, pud, addr); @@ -93,11 +93,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, pmd_t *pmd; pgd = pgd_offset(mm, addr); - if (!pgd_present(*pgd)) + if (!pgd_present(pgdp_get(pgd))) return NULL; p4d = p4d_offset(pgd, addr); - if (!p4d_present(*p4d)) + if (!p4d_present(p4dp_get(p4d))) return NULL; pud = pud_offset(p4d, addr); @@ -105,7 +105,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, /* must be pud huge, non-present or none */ return (pte_t *)pud; - if (!pud_present(*pud)) + if (!pud_present(pudp_get(pud))) return NULL; pmd = pmd_offset(pud, addr); @@ -113,7 +113,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, /* must be pmd huge, non-present or none */ return (pte_t *)pmd; - if (!pmd_present(*pmd)) + if (!pmd_present(pmdp_get(pmd))) return NULL; for_each_napot_order(order) { @@ -125,6 +125,26 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return pte; } +unsigned long hugetlb_mask_last_page(struct hstate *h) +{ + unsigned long hp_size = huge_page_size(h); + + switch (hp_size) { +#ifndef __PAGETABLE_PMD_FOLDED + case PUD_SIZE: + return P4D_SIZE - PUD_SIZE; +#endif + case PMD_SIZE: + return PUD_SIZE - PMD_SIZE; + case napot_cont_size(NAPOT_CONT64KB_ORDER): + return PMD_SIZE - napot_cont_size(NAPOT_CONT64KB_ORDER); + default: + break; + } + + return 0UL; +} + static pte_t get_clear_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, @@ -177,13 +197,36 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) return entry; } +static void clear_flush(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, + unsigned long pgsize, + unsigned long ncontig) +{ + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); + unsigned long i, saddr = addr; + + for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) + ptep_get_and_clear(mm, addr, ptep); + + flush_tlb_range(&vma, saddr, addr); +} + +/* + * When dealing with NAPOT mappings, the privileged specification indicates that + * "if an update needs to be made, the OS generally should first mark all of the + * PTEs invalid, then issue SFENCE.VMA instruction(s) covering all 4 KiB regions + * within the range, [...] then update the PTE(s), as described in Section + * 4.2.1.". That's the equivalent of the Break-Before-Make approach used by + * arm64. + */ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { - unsigned long hugepage_shift; + unsigned long hugepage_shift, pgsize; int i, pte_num; if (sz >= PGDIR_SIZE) @@ -198,7 +241,22 @@ void set_huge_pte_at(struct mm_struct *mm, hugepage_shift = PAGE_SHIFT; pte_num = sz >> hugepage_shift; - for (i = 0; i < pte_num; i++, ptep++, addr += (1 << hugepage_shift)) + pgsize = 1 << hugepage_shift; + + if (!pte_present(pte)) { + for (i = 0; i < pte_num; i++, ptep++, addr += pgsize) + set_ptes(mm, addr, ptep, pte, 1); + return; + } + + if (!pte_napot(pte)) { + set_ptes(mm, addr, ptep, pte, 1); + return; + } + + clear_flush(mm, addr, ptep, pgsize, pte_num); + + for (i = 0; i < pte_num; i++, ptep++, addr += pgsize) set_pte_at(mm, addr, ptep, pte); } @@ -293,7 +351,7 @@ void huge_pte_clear(struct mm_struct *mm, pte_t *ptep, unsigned long sz) { - pte_t pte = READ_ONCE(*ptep); + pte_t pte = ptep_get(ptep); int i, pte_num; if (!pte_napot(pte)) { @@ -306,7 +364,7 @@ void huge_pte_clear(struct mm_struct *mm, pte_clear(mm, addr, ptep); } -static __init bool is_napot_size(unsigned long size) +static bool is_napot_size(unsigned long size) { unsigned long order; @@ -334,7 +392,7 @@ arch_initcall(napot_hugetlbpages_init); #else -static __init bool is_napot_size(unsigned long size) +static bool is_napot_size(unsigned long size) { return false; } @@ -351,7 +409,7 @@ int pmd_huge(pmd_t pmd) return pmd_leaf(pmd); } -bool __init arch_hugetlb_valid_size(unsigned long size) +static bool __hugetlb_valid_size(unsigned long size) { if (size == HPAGE_SIZE) return true; @@ -363,6 +421,18 @@ bool __init arch_hugetlb_valid_size(unsigned long size) return false; } +bool __init arch_hugetlb_valid_size(unsigned long size) +{ + return __hugetlb_valid_size(size); +} + +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION +bool arch_hugetlb_migration_supported(struct hstate *h) +{ + return __hugetlb_valid_size(huge_page_size(h)); +} +#endif + #ifdef CONFIG_CONTIG_ALLOC static __init int gigantic_pages_init(void) { diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 0798bd861dcb9a..3245bb525212e3 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -172,6 +172,9 @@ void __init mem_init(void) /* Limit the memory size via mem. */ static phys_addr_t memory_limit; +#ifdef CONFIG_XIP_KERNEL +#define memory_limit (*(phys_addr_t *)XIP_FIXUP(&memory_limit)) +#endif /* CONFIG_XIP_KERNEL */ static int __init early_mem(char *p) { @@ -214,8 +217,6 @@ static void __init setup_bootmem(void) */ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); - phys_ram_end = memblock_end_of_DRAM(); - /* * Make sure we align the start of the memory on a PMD boundary so that * at worst, we map the linear mapping with PMD mappings. @@ -227,24 +228,36 @@ static void __init setup_bootmem(void) * In 64-bit, any use of __va/__pa before this point is wrong as we * did not know the start of DRAM before. */ - if (IS_ENABLED(CONFIG_64BIT)) + if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU)) kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base; /* - * memblock allocator is not aware of the fact that last 4K bytes of - * the addressable memory can not be mapped because of IS_ERR_VALUE - * macro. Make sure that last 4k bytes are not usable by memblock - * if end of dram is equal to maximum addressable memory. For 64-bit - * kernel, this problem can't happen here as the end of the virtual - * address space is occupied by the kernel mapping then this check must - * be done as soon as the kernel mapping base address is determined. + * The size of the linear page mapping may restrict the amount of + * usable RAM. + */ + if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU)) { + max_mapped_addr = __pa(PAGE_OFFSET) + KERN_VIRT_SIZE; + memblock_cap_memory_range(phys_ram_base, + max_mapped_addr - phys_ram_base); + } + + /* + * Reserve physical address space that would be mapped to virtual + * addresses greater than (void *)(-PAGE_SIZE) because: + * - This memory would overlap with ERR_PTR + * - This memory belongs to high memory, which is not supported + * + * This is not applicable to 64-bit kernel, because virtual addresses + * after (void *)(-PAGE_SIZE) are not linearly mapped: they are + * occupied by kernel mapping. Also it is unrealistic for high memory + * to exist on 64-bit platforms. */ if (!IS_ENABLED(CONFIG_64BIT)) { - max_mapped_addr = __pa(~(ulong)0); - if (max_mapped_addr == (phys_ram_end - 1)) - memblock_set_current_limit(max_mapped_addr - 4096); + max_mapped_addr = __va_to_pa_nodebug(-PAGE_SIZE); + memblock_reserve(max_mapped_addr, (phys_addr_t)-max_mapped_addr); } + phys_ram_end = memblock_end_of_DRAM(); min_low_pfn = PFN_UP(phys_ram_base); max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end); high_memory = (void *)(__va(PFN_PHYS(max_low_pfn))); @@ -664,16 +677,19 @@ void __init create_pgd_mapping(pgd_t *pgdp, static uintptr_t __init best_map_size(phys_addr_t pa, uintptr_t va, phys_addr_t size) { - if (!(pa & (PGDIR_SIZE - 1)) && !(va & (PGDIR_SIZE - 1)) && size >= PGDIR_SIZE) - return PGDIR_SIZE; + if (debug_pagealloc_enabled()) + return PAGE_SIZE; - if (!(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE) + if (pgtable_l5_enabled && + !(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE) return P4D_SIZE; - if (!(pa & (PUD_SIZE - 1)) && !(va & (PUD_SIZE - 1)) && size >= PUD_SIZE) + if (pgtable_l4_enabled && + !(pa & (PUD_SIZE - 1)) && !(va & (PUD_SIZE - 1)) && size >= PUD_SIZE) return PUD_SIZE; - if (!(pa & (PMD_SIZE - 1)) && !(va & (PMD_SIZE - 1)) && size >= PMD_SIZE) + if (IS_ENABLED(CONFIG_64BIT) && + !(pa & (PMD_SIZE - 1)) && !(va & (PMD_SIZE - 1)) && size >= PMD_SIZE) return PMD_SIZE; return PAGE_SIZE; @@ -896,7 +912,7 @@ static void __init create_kernel_page_table(pgd_t *pgdir, PMD_SIZE, PAGE_KERNEL_EXEC); /* Map the data in RAM */ - end_va = kernel_map.virt_addr + XIP_OFFSET + kernel_map.size; + end_va = kernel_map.virt_addr + kernel_map.size; for (va = kernel_map.virt_addr + XIP_OFFSET; va < end_va; va += PMD_SIZE) create_pgd_mapping(pgdir, va, kernel_map.phys_addr + (va - (kernel_map.virt_addr + XIP_OFFSET)), @@ -950,7 +966,7 @@ static void __init create_fdt_early_page_table(uintptr_t fix_fdt_va, * setup_vm_final installs the linear mapping. For 32-bit kernel, as the * kernel is mapped in the linear mapping, that makes no difference. */ - dtb_early_va = kernel_mapping_pa_to_va(XIP_FIXUP(dtb_pa)); + dtb_early_va = kernel_mapping_pa_to_va(dtb_pa); #endif dtb_early_pa = dtb_pa; @@ -1053,18 +1069,23 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) #endif kernel_map.virt_addr = KERNEL_LINK_ADDR + kernel_map.virt_offset; - kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL); #ifdef CONFIG_XIP_KERNEL +#ifdef CONFIG_64BIT + kernel_map.page_offset = PAGE_OFFSET_L3; +#else + kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL); +#endif kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR; kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom); phys_ram_base = CONFIG_PHYS_RAM_BASE; kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE; - kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata); + kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start); kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom; #else + kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL); kernel_map.phys_addr = (uintptr_t)(&_start); kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr; #endif @@ -1257,8 +1278,6 @@ static void __init create_linear_mapping_page_table(void) if (start <= __pa(PAGE_OFFSET) && __pa(PAGE_OFFSET) < end) start = __pa(PAGE_OFFSET); - if (end >= __pa(PAGE_OFFSET) + memory_limit) - end = __pa(PAGE_OFFSET) + memory_limit; create_linear_mapping_range(start, end, 0); } @@ -1494,6 +1513,10 @@ void __init misc_mem_init(void) early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT); arch_numa_init(); sparse_init(); +#ifdef CONFIG_SPARSEMEM_VMEMMAP + /* The entire VMEMMAP region has been populated. Flush TLB for this region */ + local_flush_tlb_kernel_range(VMEMMAP_START, VMEMMAP_END); +#endif zone_sizes_init(); reserve_crashkernel(); memblock_dump_all(); diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 5e39dcf23fdbc1..e962518530373d 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -31,7 +31,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned phys_addr_t phys_addr; pte_t *ptep, *p; - if (pmd_none(*pmd)) { + if (pmd_none(pmdp_get(pmd))) { p = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -39,7 +39,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned ptep = pte_offset_kernel(pmd, vaddr); do { - if (pte_none(*ptep)) { + if (pte_none(ptep_get(ptep))) { phys_addr = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); set_pte(ptep, pfn_pte(PFN_DOWN(phys_addr), PAGE_KERNEL)); memset(__va(phys_addr), KASAN_SHADOW_INIT, PAGE_SIZE); @@ -53,7 +53,7 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned pmd_t *pmdp, *p; unsigned long next; - if (pud_none(*pud)) { + if (pud_none(pudp_get(pud))) { p = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); set_pud(pud, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -63,7 +63,8 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned do { next = pmd_addr_end(vaddr, end); - if (pmd_none(*pmdp) && IS_ALIGNED(vaddr, PMD_SIZE) && (next - vaddr) >= PMD_SIZE) { + if (pmd_none(pmdp_get(pmdp)) && IS_ALIGNED(vaddr, PMD_SIZE) && + (next - vaddr) >= PMD_SIZE) { phys_addr = memblock_phys_alloc(PMD_SIZE, PMD_SIZE); if (phys_addr) { set_pmd(pmdp, pfn_pmd(PFN_DOWN(phys_addr), PAGE_KERNEL)); @@ -83,7 +84,7 @@ static void __init kasan_populate_pud(p4d_t *p4d, pud_t *pudp, *p; unsigned long next; - if (p4d_none(*p4d)) { + if (p4d_none(p4dp_get(p4d))) { p = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); set_p4d(p4d, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -93,7 +94,8 @@ static void __init kasan_populate_pud(p4d_t *p4d, do { next = pud_addr_end(vaddr, end); - if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) { + if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) && + (next - vaddr) >= PUD_SIZE) { phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE); if (phys_addr) { set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL)); @@ -113,7 +115,7 @@ static void __init kasan_populate_p4d(pgd_t *pgd, p4d_t *p4dp, *p; unsigned long next; - if (pgd_none(*pgd)) { + if (pgd_none(pgdp_get(pgd))) { p = memblock_alloc(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE); set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -123,7 +125,8 @@ static void __init kasan_populate_p4d(pgd_t *pgd, do { next = p4d_addr_end(vaddr, end); - if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE) { + if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) && + (next - vaddr) >= P4D_SIZE) { phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE); if (phys_addr) { set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL)); @@ -145,7 +148,7 @@ static void __init kasan_populate_pgd(pgd_t *pgdp, do { next = pgd_addr_end(vaddr, end); - if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) && + if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) { phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE); if (phys_addr) { @@ -168,7 +171,7 @@ static void __init kasan_early_clear_pud(p4d_t *p4dp, if (!pgtable_l4_enabled) { pudp = (pud_t *)p4dp; } else { - base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp))); + base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp)))); pudp = base_pud + pud_index(vaddr); } @@ -193,7 +196,7 @@ static void __init kasan_early_clear_p4d(pgd_t *pgdp, if (!pgtable_l5_enabled) { p4dp = (p4d_t *)pgdp; } else { - base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp))); + base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp)))); p4dp = base_p4d + p4d_index(vaddr); } @@ -239,14 +242,14 @@ static void __init kasan_early_populate_pud(p4d_t *p4dp, if (!pgtable_l4_enabled) { pudp = (pud_t *)p4dp; } else { - base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp))); + base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp)))); pudp = base_pud + pud_index(vaddr); } do { next = pud_addr_end(vaddr, end); - if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && + if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) { phys_addr = __pa((uintptr_t)kasan_early_shadow_pmd); set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE)); @@ -277,14 +280,14 @@ static void __init kasan_early_populate_p4d(pgd_t *pgdp, if (!pgtable_l5_enabled) { p4dp = (p4d_t *)pgdp; } else { - base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp))); + base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp)))); p4dp = base_p4d + p4d_index(vaddr); } do { next = p4d_addr_end(vaddr, end); - if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) && + if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE) { phys_addr = __pa((uintptr_t)kasan_early_shadow_pud); set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE)); @@ -305,7 +308,7 @@ static void __init kasan_early_populate_pgd(pgd_t *pgdp, do { next = pgd_addr_end(vaddr, end); - if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) && + if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) { phys_addr = __pa((uintptr_t)kasan_early_shadow_p4d); set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE)); @@ -381,7 +384,7 @@ static void __init kasan_shallow_populate_pud(p4d_t *p4d, do { next = pud_addr_end(vaddr, end); - if (pud_none(*pud_k)) { + if (pud_none(pudp_get(pud_k))) { p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); set_pud(pud_k, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; @@ -401,7 +404,7 @@ static void __init kasan_shallow_populate_p4d(pgd_t *pgd, do { next = p4d_addr_end(vaddr, end); - if (p4d_none(*p4d_k)) { + if (p4d_none(p4dp_get(p4d_k))) { p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); set_p4d(p4d_k, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; @@ -420,7 +423,7 @@ static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long do { next = pgd_addr_end(vaddr, end); - if (pgd_none(*pgd_k)) { + if (pgd_none(pgdp_get(pgd_k))) { p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; @@ -451,7 +454,7 @@ static void __init create_tmp_mapping(void) /* Copy the last p4d since it is shared with the kernel mapping. */ if (pgtable_l5_enabled) { - ptr = (p4d_t *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END)); + ptr = (p4d_t *)pgd_page_vaddr(pgdp_get(pgd_offset_k(KASAN_SHADOW_END))); memcpy(tmp_p4d, ptr, sizeof(p4d_t) * PTRS_PER_P4D); set_pgd(&tmp_pg_dir[pgd_index(KASAN_SHADOW_END)], pfn_pgd(PFN_DOWN(__pa(tmp_p4d)), PAGE_TABLE)); @@ -462,7 +465,7 @@ static void __init create_tmp_mapping(void) /* Copy the last pud since it is shared with the kernel mapping. */ if (pgtable_l4_enabled) { - ptr = (pud_t *)p4d_page_vaddr(*(base_p4d + p4d_index(KASAN_SHADOW_END))); + ptr = (pud_t *)p4d_page_vaddr(p4dp_get(base_p4d + p4d_index(KASAN_SHADOW_END))); memcpy(tmp_pud, ptr, sizeof(pud_t) * PTRS_PER_PUD); set_p4d(&base_p4d[p4d_index(KASAN_SHADOW_END)], pfn_p4d(PFN_DOWN(__pa(tmp_pud)), PAGE_TABLE)); diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index 161d0b34c2cb28..271d01a5ba4da1 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -5,6 +5,7 @@ #include #include +#include #include #include #include @@ -25,23 +26,10 @@ static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk) return new_val; } -static int pageattr_pgd_entry(pgd_t *pgd, unsigned long addr, - unsigned long next, struct mm_walk *walk) -{ - pgd_t val = READ_ONCE(*pgd); - - if (pgd_leaf(val)) { - val = __pgd(set_pageattr_masks(pgd_val(val), walk)); - set_pgd(pgd, val); - } - - return 0; -} - static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr, unsigned long next, struct mm_walk *walk) { - p4d_t val = READ_ONCE(*p4d); + p4d_t val = p4dp_get(p4d); if (p4d_leaf(val)) { val = __p4d(set_pageattr_masks(p4d_val(val), walk)); @@ -54,7 +42,7 @@ static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr, static int pageattr_pud_entry(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk) { - pud_t val = READ_ONCE(*pud); + pud_t val = pudp_get(pud); if (pud_leaf(val)) { val = __pud(set_pageattr_masks(pud_val(val), walk)); @@ -67,7 +55,7 @@ static int pageattr_pud_entry(pud_t *pud, unsigned long addr, static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { - pmd_t val = READ_ONCE(*pmd); + pmd_t val = pmdp_get(pmd); if (pmd_leaf(val)) { val = __pmd(set_pageattr_masks(pmd_val(val), walk)); @@ -80,7 +68,7 @@ static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr, static int pageattr_pte_entry(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { - pte_t val = READ_ONCE(*pte); + pte_t val = ptep_get(pte); val = __pte(set_pageattr_masks(pte_val(val), walk)); set_pte(pte, val); @@ -96,7 +84,6 @@ static int pageattr_pte_hole(unsigned long addr, unsigned long next, } static const struct mm_walk_ops pageattr_ops = { - .pgd_entry = pageattr_pgd_entry, .p4d_entry = pageattr_p4d_entry, .pud_entry = pageattr_pud_entry, .pmd_entry = pageattr_pmd_entry, @@ -105,12 +92,181 @@ static const struct mm_walk_ops pageattr_ops = { .walk_lock = PGWALK_RDLOCK, }; +#ifdef CONFIG_64BIT +static int __split_linear_mapping_pmd(pud_t *pudp, + unsigned long vaddr, unsigned long end) +{ + pmd_t *pmdp; + unsigned long next; + + pmdp = pmd_offset(pudp, vaddr); + + do { + next = pmd_addr_end(vaddr, end); + + if (next - vaddr >= PMD_SIZE && + vaddr <= (vaddr & PMD_MASK) && end >= next) + continue; + + if (pmd_leaf(pmdp_get(pmdp))) { + struct page *pte_page; + unsigned long pfn = _pmd_pfn(pmdp_get(pmdp)); + pgprot_t prot = __pgprot(pmd_val(pmdp_get(pmdp)) & ~_PAGE_PFN_MASK); + pte_t *ptep_new; + int i; + + pte_page = alloc_page(GFP_KERNEL); + if (!pte_page) + return -ENOMEM; + + ptep_new = (pte_t *)page_address(pte_page); + for (i = 0; i < PTRS_PER_PTE; ++i, ++ptep_new) + set_pte(ptep_new, pfn_pte(pfn + i, prot)); + + smp_wmb(); + + set_pmd(pmdp, pfn_pmd(page_to_pfn(pte_page), PAGE_TABLE)); + } + } while (pmdp++, vaddr = next, vaddr != end); + + return 0; +} + +static int __split_linear_mapping_pud(p4d_t *p4dp, + unsigned long vaddr, unsigned long end) +{ + pud_t *pudp; + unsigned long next; + int ret; + + pudp = pud_offset(p4dp, vaddr); + + do { + next = pud_addr_end(vaddr, end); + + if (next - vaddr >= PUD_SIZE && + vaddr <= (vaddr & PUD_MASK) && end >= next) + continue; + + if (pud_leaf(pudp_get(pudp))) { + struct page *pmd_page; + unsigned long pfn = _pud_pfn(pudp_get(pudp)); + pgprot_t prot = __pgprot(pud_val(pudp_get(pudp)) & ~_PAGE_PFN_MASK); + pmd_t *pmdp_new; + int i; + + pmd_page = alloc_page(GFP_KERNEL); + if (!pmd_page) + return -ENOMEM; + + pmdp_new = (pmd_t *)page_address(pmd_page); + for (i = 0; i < PTRS_PER_PMD; ++i, ++pmdp_new) + set_pmd(pmdp_new, + pfn_pmd(pfn + ((i * PMD_SIZE) >> PAGE_SHIFT), prot)); + + smp_wmb(); + + set_pud(pudp, pfn_pud(page_to_pfn(pmd_page), PAGE_TABLE)); + } + + ret = __split_linear_mapping_pmd(pudp, vaddr, next); + if (ret) + return ret; + } while (pudp++, vaddr = next, vaddr != end); + + return 0; +} + +static int __split_linear_mapping_p4d(pgd_t *pgdp, + unsigned long vaddr, unsigned long end) +{ + p4d_t *p4dp; + unsigned long next; + int ret; + + p4dp = p4d_offset(pgdp, vaddr); + + do { + next = p4d_addr_end(vaddr, end); + + /* + * If [vaddr; end] contains [vaddr & P4D_MASK; next], we don't + * need to split, we'll change the protections on the whole P4D. + */ + if (next - vaddr >= P4D_SIZE && + vaddr <= (vaddr & P4D_MASK) && end >= next) + continue; + + if (p4d_leaf(p4dp_get(p4dp))) { + struct page *pud_page; + unsigned long pfn = _p4d_pfn(p4dp_get(p4dp)); + pgprot_t prot = __pgprot(p4d_val(p4dp_get(p4dp)) & ~_PAGE_PFN_MASK); + pud_t *pudp_new; + int i; + + pud_page = alloc_page(GFP_KERNEL); + if (!pud_page) + return -ENOMEM; + + /* + * Fill the pud level with leaf puds that have the same + * protections as the leaf p4d. + */ + pudp_new = (pud_t *)page_address(pud_page); + for (i = 0; i < PTRS_PER_PUD; ++i, ++pudp_new) + set_pud(pudp_new, + pfn_pud(pfn + ((i * PUD_SIZE) >> PAGE_SHIFT), prot)); + + /* + * Make sure the pud filling is not reordered with the + * p4d store which could result in seeing a partially + * filled pud level. + */ + smp_wmb(); + + set_p4d(p4dp, pfn_p4d(page_to_pfn(pud_page), PAGE_TABLE)); + } + + ret = __split_linear_mapping_pud(p4dp, vaddr, next); + if (ret) + return ret; + } while (p4dp++, vaddr = next, vaddr != end); + + return 0; +} + +static int __split_linear_mapping_pgd(pgd_t *pgdp, + unsigned long vaddr, + unsigned long end) +{ + unsigned long next; + int ret; + + do { + next = pgd_addr_end(vaddr, end); + /* We never use PGD mappings for the linear mapping */ + ret = __split_linear_mapping_p4d(pgdp, vaddr, next); + if (ret) + return ret; + } while (pgdp++, vaddr = next, vaddr != end); + + return 0; +} + +static int split_linear_mapping(unsigned long start, unsigned long end) +{ + return __split_linear_mapping_pgd(pgd_offset_k(start), start, end); +} +#endif /* CONFIG_64BIT */ + static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, pgprot_t clear_mask) { int ret; unsigned long start = addr; unsigned long end = start + PAGE_SIZE * numpages; + unsigned long __maybe_unused lm_start; + unsigned long __maybe_unused lm_end; struct pageattr_masks masks = { .set_mask = set_mask, .clear_mask = clear_mask @@ -120,11 +276,72 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, return 0; mmap_write_lock(&init_mm); + +#ifdef CONFIG_64BIT + /* + * We are about to change the permissions of a kernel mapping, we must + * apply the same changes to its linear mapping alias, which may imply + * splitting a huge mapping. + */ + + if (is_vmalloc_or_module_addr((void *)start)) { + struct vm_struct *area = NULL; + int i, page_start; + + area = find_vm_area((void *)start); + page_start = (start - (unsigned long)area->addr) >> PAGE_SHIFT; + + for (i = page_start; i < page_start + numpages; ++i) { + lm_start = (unsigned long)page_address(area->pages[i]); + lm_end = lm_start + PAGE_SIZE; + + ret = split_linear_mapping(lm_start, lm_end); + if (ret) + goto unlock; + + ret = walk_page_range_novma(&init_mm, lm_start, lm_end, + &pageattr_ops, NULL, &masks); + if (ret) + goto unlock; + } + } else if (is_kernel_mapping(start) || is_linear_mapping(start)) { + if (is_kernel_mapping(start)) { + lm_start = (unsigned long)lm_alias(start); + lm_end = (unsigned long)lm_alias(end); + } else { + lm_start = start; + lm_end = end; + } + + ret = split_linear_mapping(lm_start, lm_end); + if (ret) + goto unlock; + + ret = walk_page_range_novma(&init_mm, lm_start, lm_end, + &pageattr_ops, NULL, &masks); + if (ret) + goto unlock; + } + ret = walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL, &masks); + +unlock: + mmap_write_unlock(&init_mm); + + /* + * We can't use flush_tlb_kernel_range() here as we may have split a + * hugepage that is larger than that, so let's flush everything. + */ + flush_tlb_all(); +#else + ret = walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL, + &masks); + mmap_write_unlock(&init_mm); flush_tlb_kernel_range(start, end); +#endif return ret; } @@ -159,50 +376,44 @@ int set_memory_nx(unsigned long addr, int numpages) int set_direct_map_invalid_noflush(struct page *page) { - int ret; - unsigned long start = (unsigned long)page_address(page); - unsigned long end = start + PAGE_SIZE; - struct pageattr_masks masks = { - .set_mask = __pgprot(0), - .clear_mask = __pgprot(_PAGE_PRESENT) - }; - - mmap_read_lock(&init_mm); - ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks); - mmap_read_unlock(&init_mm); - - return ret; + return __set_memory((unsigned long)page_address(page), 1, + __pgprot(0), __pgprot(_PAGE_PRESENT)); } int set_direct_map_default_noflush(struct page *page) { - int ret; - unsigned long start = (unsigned long)page_address(page); - unsigned long end = start + PAGE_SIZE; - struct pageattr_masks masks = { - .set_mask = PAGE_KERNEL, - .clear_mask = __pgprot(0) - }; + return __set_memory((unsigned long)page_address(page), 1, + PAGE_KERNEL, __pgprot(_PAGE_EXEC)); +} - mmap_read_lock(&init_mm); - ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks); - mmap_read_unlock(&init_mm); +#ifdef CONFIG_DEBUG_PAGEALLOC +static int debug_pagealloc_set_page(pte_t *pte, unsigned long addr, void *data) +{ + int enable = *(int *)data; - return ret; + unsigned long val = pte_val(ptep_get(pte)); + + if (enable) + val |= _PAGE_PRESENT; + else + val &= ~_PAGE_PRESENT; + + set_pte(pte, __pte(val)); + + return 0; } -#ifdef CONFIG_DEBUG_PAGEALLOC void __kernel_map_pages(struct page *page, int numpages, int enable) { if (!debug_pagealloc_enabled()) return; - if (enable) - __set_memory((unsigned long)page_address(page), numpages, - __pgprot(_PAGE_PRESENT), __pgprot(0)); - else - __set_memory((unsigned long)page_address(page), numpages, - __pgprot(0), __pgprot(_PAGE_PRESENT)); + unsigned long start = (unsigned long)page_address(page); + unsigned long size = PAGE_SIZE * numpages; + + apply_to_existing_page_range(&init_mm, start, size, debug_pagealloc_set_page, &enable); + + flush_tlb_kernel_range(start, start + size); } #endif @@ -216,29 +427,29 @@ bool kernel_page_present(struct page *page) pte_t *pte; pgd = pgd_offset_k(addr); - if (!pgd_present(*pgd)) + if (!pgd_present(pgdp_get(pgd))) return false; - if (pgd_leaf(*pgd)) + if (pgd_leaf(pgdp_get(pgd))) return true; p4d = p4d_offset(pgd, addr); - if (!p4d_present(*p4d)) + if (!p4d_present(p4dp_get(p4d))) return false; - if (p4d_leaf(*p4d)) + if (p4d_leaf(p4dp_get(p4d))) return true; pud = pud_offset(p4d, addr); - if (!pud_present(*pud)) + if (!pud_present(pudp_get(pud))) return false; - if (pud_leaf(*pud)) + if (pud_leaf(pudp_get(pud))) return true; pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) + if (!pmd_present(pmdp_get(pmd))) return false; - if (pmd_leaf(*pmd)) + if (pmd_leaf(pmdp_get(pmd))) return true; pte = pte_offset_kernel(pmd, addr); - return pte_present(*pte); + return pte_present(ptep_get(pte)); } diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c index fef4e7328e4905..ef887efcb67900 100644 --- a/arch/riscv/mm/pgtable.c +++ b/arch/riscv/mm/pgtable.c @@ -5,6 +5,47 @@ #include #include +int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty) +{ + if (!pte_same(ptep_get(ptep), entry)) + __set_pte_at(ptep, entry); + /* + * update_mmu_cache will unconditionally execute, handling both + * the case that the PTE changed and the spurious fault case. + */ + return true; +} + +int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pte_t *ptep) +{ + if (!pte_young(ptep_get(ptep))) + return 0; + return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep)); +} +EXPORT_SYMBOL_GPL(ptep_test_and_clear_young); + +#ifdef CONFIG_64BIT +pud_t *pud_offset(p4d_t *p4d, unsigned long address) +{ + if (pgtable_l4_enabled) + return p4d_pgtable(p4dp_get(p4d)) + pud_index(address); + + return (pud_t *)p4d; +} + +p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) +{ + if (pgtable_l5_enabled) + return pgd_pgtable(pgdp_get(pgd)) + p4d_index(address); + + return (p4d_t *)pgd; +} +#endif + #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { @@ -25,7 +66,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot) int pud_clear_huge(pud_t *pud) { - if (!pud_leaf(READ_ONCE(*pud))) + if (!pud_leaf(pudp_get(pud))) return 0; pud_clear(pud); return 1; @@ -33,7 +74,7 @@ int pud_clear_huge(pud_t *pud) int pud_free_pmd_page(pud_t *pud, unsigned long addr) { - pmd_t *pmd = pud_pgtable(*pud); + pmd_t *pmd = pud_pgtable(pudp_get(pud)); int i; pud_clear(pud); @@ -63,7 +104,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot) int pmd_clear_huge(pmd_t *pmd) { - if (!pmd_leaf(READ_ONCE(*pmd))) + if (!pmd_leaf(pmdp_get(pmd))) return 0; pmd_clear(pmd); return 1; @@ -71,7 +112,7 @@ int pmd_clear_huge(pmd_t *pmd) int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { - pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd); + pte_t *pte = (pte_t *)pmd_page_vaddr(pmdp_get(pmd)); pmd_clear(pmd); @@ -88,7 +129,7 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); VM_BUG_ON(address & ~HPAGE_PMD_MASK); - VM_BUG_ON(pmd_trans_huge(*pmdp)); + VM_BUG_ON(pmd_trans_huge(pmdp_get(pmdp))); /* * When leaf PTE entries (regular pages) are collapsed into a leaf * PMD entry (huge page), a valid non-leaf PTE is converted into a diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c index 20a9f991a6d746..e9090b38f8117c 100644 --- a/arch/riscv/mm/ptdump.c +++ b/arch/riscv/mm/ptdump.c @@ -384,6 +384,9 @@ static int __init ptdump_init(void) kernel_ptd_info.base_addr = KERN_VIRT_START; + pg_level[1].name = pgtable_l5_enabled ? "P4D" : "PGD"; + pg_level[2].name = pgtable_l4_enabled ? "PUD" : "PGD"; + for (i = 0; i < ARRAY_SIZE(pg_level); i++) for (j = 0; j < ARRAY_SIZE(pte_bits); j++) pg_level[i].mask |= pte_bits[j].mask; diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index 77be59aadc735e..324e8cd9b50228 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -6,30 +6,29 @@ #include #include -static inline void local_flush_tlb_all_asid(unsigned long asid) +/* + * Flush entire TLB if number of entries to be flushed is greater + * than the threshold below. + */ +static unsigned long tlb_flush_all_threshold __read_mostly = 64; + +static void local_flush_tlb_range_threshold_asid(unsigned long start, + unsigned long size, + unsigned long stride, + unsigned long asid) { - __asm__ __volatile__ ("sfence.vma x0, %0" - : - : "r" (asid) - : "memory"); -} + unsigned long nr_ptes_in_range = DIV_ROUND_UP(size, stride); + int i; -static inline void local_flush_tlb_page_asid(unsigned long addr, - unsigned long asid) -{ - __asm__ __volatile__ ("sfence.vma %0, %1" - : - : "r" (addr), "r" (asid) - : "memory"); -} + if (nr_ptes_in_range > tlb_flush_all_threshold) { + local_flush_tlb_all_asid(asid); + return; + } -static inline void local_flush_tlb_range(unsigned long start, - unsigned long size, unsigned long stride) -{ - if (size <= stride) - local_flush_tlb_page(start); - else - local_flush_tlb_all(); + for (i = 0; i < nr_ptes_in_range; ++i) { + local_flush_tlb_page_asid(start, asid); + start += stride; + } } static inline void local_flush_tlb_range_asid(unsigned long start, @@ -37,8 +36,16 @@ static inline void local_flush_tlb_range_asid(unsigned long start, { if (size <= stride) local_flush_tlb_page_asid(start, asid); - else + else if (size == FLUSH_TLB_MAX_SIZE) local_flush_tlb_all_asid(asid); + else + local_flush_tlb_range_threshold_asid(start, size, stride, asid); +} + +/* Flush a range of kernel pages without broadcasting */ +void local_flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID); } static void __ipi_flush_tlb_all(void *info) @@ -51,7 +58,7 @@ void flush_tlb_all(void) if (riscv_use_ipi_for_rfence()) on_each_cpu(__ipi_flush_tlb_all, NULL, 1); else - sbi_remote_sfence_vma(NULL, 0, -1); + sbi_remote_sfence_vma_asid(NULL, 0, FLUSH_TLB_MAX_SIZE, FLUSH_TLB_NO_ASID); } struct flush_tlb_range_data { @@ -68,68 +75,62 @@ static void __ipi_flush_tlb_range_asid(void *info) local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid); } -static void __ipi_flush_tlb_range(void *info) -{ - struct flush_tlb_range_data *d = info; - - local_flush_tlb_range(d->start, d->size, d->stride); -} - static void __flush_tlb_range(struct mm_struct *mm, unsigned long start, unsigned long size, unsigned long stride) { struct flush_tlb_range_data ftd; - struct cpumask *cmask = mm_cpumask(mm); - unsigned int cpuid; + const struct cpumask *cmask; + unsigned long asid = FLUSH_TLB_NO_ASID; bool broadcast; - if (cpumask_empty(cmask)) - return; + if (mm) { + unsigned int cpuid; - cpuid = get_cpu(); - /* check if the tlbflush needs to be sent to other CPUs */ - broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids; - if (static_branch_unlikely(&use_asid_allocator)) { - unsigned long asid = atomic_long_read(&mm->context.id) & asid_mask; - - if (broadcast) { - if (riscv_use_ipi_for_rfence()) { - ftd.asid = asid; - ftd.start = start; - ftd.size = size; - ftd.stride = stride; - on_each_cpu_mask(cmask, - __ipi_flush_tlb_range_asid, - &ftd, 1); - } else - sbi_remote_sfence_vma_asid(cmask, - start, size, asid); - } else { - local_flush_tlb_range_asid(start, size, stride, asid); - } + cmask = mm_cpumask(mm); + if (cpumask_empty(cmask)) + return; + + cpuid = get_cpu(); + /* check if the tlbflush needs to be sent to other CPUs */ + broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids; + + if (static_branch_unlikely(&use_asid_allocator)) + asid = atomic_long_read(&mm->context.id) & asid_mask; } else { - if (broadcast) { - if (riscv_use_ipi_for_rfence()) { - ftd.asid = 0; - ftd.start = start; - ftd.size = size; - ftd.stride = stride; - on_each_cpu_mask(cmask, - __ipi_flush_tlb_range, - &ftd, 1); - } else - sbi_remote_sfence_vma(cmask, start, size); - } else { - local_flush_tlb_range(start, size, stride); - } + cmask = cpu_online_mask; + broadcast = true; } - put_cpu(); + if (broadcast) { + if (riscv_use_ipi_for_rfence()) { + ftd.asid = asid; + ftd.start = start; + ftd.size = size; + ftd.stride = stride; + on_each_cpu_mask(cmask, + __ipi_flush_tlb_range_asid, + &ftd, 1); + } else + sbi_remote_sfence_vma_asid(cmask, + start, size, asid); + } else { + local_flush_tlb_range_asid(start, size, stride, asid); + } + + if (mm) + put_cpu(); } void flush_tlb_mm(struct mm_struct *mm) { - __flush_tlb_range(mm, 0, -1, PAGE_SIZE); + __flush_tlb_range(mm, 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE); +} + +void flush_tlb_mm_range(struct mm_struct *mm, + unsigned long start, unsigned long end, + unsigned int page_size) +{ + __flush_tlb_range(mm, start, end - start, page_size); } void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) @@ -142,6 +143,12 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, { __flush_tlb_range(vma->vm_mm, start, end - start, PAGE_SIZE); } + +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + __flush_tlb_range(NULL, start, end - start, PAGE_SIZE); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 8581693e62d396..2f041b5cea970e 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -516,33 +516,33 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, break; /* src_reg = atomic_fetch_(dst_reg + off16, src_reg) */ case BPF_ADD | BPF_FETCH: - emit(is64 ? rv_amoadd_d(rs, rs, rd, 0, 0) : - rv_amoadd_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoadd_d(rs, rs, rd, 1, 1) : + rv_amoadd_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zext_32(rs, ctx); break; case BPF_AND | BPF_FETCH: - emit(is64 ? rv_amoand_d(rs, rs, rd, 0, 0) : - rv_amoand_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoand_d(rs, rs, rd, 1, 1) : + rv_amoand_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zext_32(rs, ctx); break; case BPF_OR | BPF_FETCH: - emit(is64 ? rv_amoor_d(rs, rs, rd, 0, 0) : - rv_amoor_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoor_d(rs, rs, rd, 1, 1) : + rv_amoor_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zext_32(rs, ctx); break; case BPF_XOR | BPF_FETCH: - emit(is64 ? rv_amoxor_d(rs, rs, rd, 0, 0) : - rv_amoxor_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoxor_d(rs, rs, rd, 1, 1) : + rv_amoxor_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zext_32(rs, ctx); break; /* src_reg = atomic_xchg(dst_reg + off16, src_reg); */ case BPF_XCHG: - emit(is64 ? rv_amoswap_d(rs, rs, rd, 0, 0) : - rv_amoswap_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoswap_d(rs, rs, rd, 1, 1) : + rv_amoswap_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zext_32(rs, ctx); break; @@ -740,6 +740,9 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of if (ret) return ret; + /* store prog start time */ + emit_mv(RV_REG_S1, RV_REG_A0, ctx); + /* if (__bpf_prog_enter(prog) == 0) * goto skip_exec_of_prog; */ @@ -747,9 +750,6 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of /* nop reserved for conditional jump */ emit(rv_nop(), ctx); - /* store prog start time */ - emit_mv(RV_REG_S1, RV_REG_A0, ctx); - /* arg1: &args_off */ emit_addi(RV_REG_A0, RV_REG_FP, -args_off, ctx); if (!p->jited) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index ae29e4392664ad..bd4782f23f66df 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -252,13 +252,13 @@ config ARCH_SUPPORTS_KEXEC def_bool y config ARCH_SUPPORTS_KEXEC_FILE - def_bool CRYPTO && CRYPTO_SHA256 && CRYPTO_SHA256_S390 + def_bool y config ARCH_SUPPORTS_KEXEC_SIG def_bool MODULE_SIG_FORMAT config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SUPPORTS_CRASH_DUMP def_bool y diff --git a/arch/s390/Makefile b/arch/s390/Makefile index a53a36ee0731bb..73873e4516866a 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -138,9 +138,6 @@ bzImage: vmlinux zfcpdump: $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ -vdso_install: - $(Q)$(MAKE) $(build)=arch/$(ARCH)/kernel/vdso64 $@ - archheaders: $(Q)$(MAKE) $(build)=$(syscalls) uapi @@ -160,6 +157,9 @@ vdso_prepare: prepare0 $(if $(CONFIG_COMPAT),$(Q)$(MAKE) \ $(build)=arch/s390/kernel/vdso32 include/generated/vdso32-offsets.h) +vdso-install-y += arch/s390/kernel/vdso64/vdso64.so.dbg +vdso-install-$(CONFIG_COMPAT) += arch/s390/kernel/vdso32/vdso32.so.dbg + ifdef CONFIG_EXPOLINE_EXTERN modules_prepare: expoline_prepare expoline_prepare: scripts diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index 7b7521762633f9..4230144645bc5d 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -272,7 +272,7 @@ void parse_boot_command_line(void) memory_limit = round_down(memparse(val, NULL), PAGE_SIZE); if (!strcmp(param, "vmalloc") && val) { - vmalloc_size = round_up(memparse(val, NULL), PAGE_SIZE); + vmalloc_size = round_up(memparse(val, NULL), _SEGMENT_SIZE); vmalloc_size_set = 1; } diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index d3e48bd9c3944f..655bbcff81ffda 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -31,7 +31,6 @@ unsigned long __bootdata_preserved(max_mappable); unsigned long __bootdata(ident_map_size); u64 __bootdata_preserved(stfle_fac_list[16]); -u64 __bootdata_preserved(alt_stfle_fac_list[16]); struct oldmem_data __bootdata_preserved(oldmem_data); struct machine_info machine; @@ -212,7 +211,8 @@ static unsigned long setup_kernel_memory_layout(void) VMALLOC_END = MODULES_VADDR; /* allow vmalloc area to occupy up to about 1/2 of the rest virtual space left */ - vmalloc_size = min(vmalloc_size, round_down(VMALLOC_END / 2, _REGION3_SIZE)); + vsize = round_down(VMALLOC_END / 2, _SEGMENT_SIZE); + vmalloc_size = min(vmalloc_size, vsize); VMALLOC_START = VMALLOC_END - vmalloc_size; /* split remaining virtual space between 1:1 mapping & vmemmap array */ diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 442a74f113cbfd..14e1a73ffcfe63 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -360,7 +360,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e } pmd = boot_crst_alloc(_SEGMENT_ENTRY_EMPTY); pud_populate(&init_mm, pud, pmd); - } else if (pud_large(*pud)) { + } else if (pud_leaf(*pud)) { continue; } pgtable_pmd_populate(pud, addr, next, mode); diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 438cd92e60801b..dd06086293106e 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -834,7 +834,6 @@ CONFIG_DEBUG_IRQFLAGS=y CONFIG_DEBUG_LIST=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y -CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index c773820e4af90a..c6fe5405de4a4c 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -597,7 +597,9 @@ static int ctr_aes_crypt(struct skcipher_request *req) * final block may be < AES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { - cpacf_kmctr(sctx->fc, sctx->key, buf, walk.src.virt.addr, + memset(buf, 0, AES_BLOCK_SIZE); + memcpy(buf, walk.src.virt.addr, nbytes); + cpacf_kmctr(sctx->fc, sctx->key, buf, buf, AES_BLOCK_SIZE, walk.iv); memcpy(walk.dst.virt.addr, buf, nbytes); crypto_inc(walk.iv, AES_BLOCK_SIZE); diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 8b541e44151d4d..55ee5567a5ea92 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -693,9 +693,11 @@ static int ctr_paes_crypt(struct skcipher_request *req) * final block may be < AES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { + memset(buf, 0, AES_BLOCK_SIZE); + memcpy(buf, walk.src.virt.addr, nbytes); while (1) { if (cpacf_kmctr(ctx->fc, ¶m, buf, - walk.src.virt.addr, AES_BLOCK_SIZE, + buf, AES_BLOCK_SIZE, walk.iv) == AES_BLOCK_SIZE) break; if (__paes_convert_key(ctx)) diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h index b378e2b57ad875..c786538e397c08 100644 --- a/arch/s390/include/asm/cpacf.h +++ b/arch/s390/include/asm/cpacf.h @@ -166,28 +166,86 @@ typedef struct { unsigned char bytes[16]; } cpacf_mask_t; -/** - * cpacf_query() - check if a specific CPACF function is available - * @opcode: the opcode of the crypto instruction - * @func: the function code to test for - * - * Executes the query function for the given crypto instruction @opcode - * and checks if @func is available - * - * Returns 1 if @func is available for @opcode, 0 otherwise +/* + * Prototype for a not existing function to produce a link + * error if __cpacf_query() or __cpacf_check_opcode() is used + * with an invalid compile time const opcode. */ -static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask) +void __cpacf_bad_opcode(void); + +static __always_inline void __cpacf_query_rre(u32 opc, u8 r1, u8 r2, + cpacf_mask_t *mask) { asm volatile( - " lghi 0,0\n" /* query function */ - " lgr 1,%[mask]\n" - " spm 0\n" /* pckmo doesn't change the cc */ - /* Parameter regs are ignored, but must be nonzero and unique */ - "0: .insn rrf,%[opc] << 16,2,4,6,0\n" - " brc 1,0b\n" /* handle partial completion */ - : "=m" (*mask) - : [mask] "d" ((unsigned long)mask), [opc] "i" (opcode) - : "cc", "0", "1"); + " la %%r1,%[mask]\n" + " xgr %%r0,%%r0\n" + " .insn rre,%[opc] << 16,%[r1],%[r2]\n" + : [mask] "=R" (*mask) + : [opc] "i" (opc), + [r1] "i" (r1), [r2] "i" (r2) + : "cc", "r0", "r1"); +} + +static __always_inline void __cpacf_query_rrf(u32 opc, + u8 r1, u8 r2, u8 r3, u8 m4, + cpacf_mask_t *mask) +{ + asm volatile( + " la %%r1,%[mask]\n" + " xgr %%r0,%%r0\n" + " .insn rrf,%[opc] << 16,%[r1],%[r2],%[r3],%[m4]\n" + : [mask] "=R" (*mask) + : [opc] "i" (opc), [r1] "i" (r1), [r2] "i" (r2), + [r3] "i" (r3), [m4] "i" (m4) + : "cc", "r0", "r1"); +} + +static __always_inline void __cpacf_query(unsigned int opcode, + cpacf_mask_t *mask) +{ + switch (opcode) { + case CPACF_KDSA: + __cpacf_query_rre(CPACF_KDSA, 0, 2, mask); + break; + case CPACF_KIMD: + __cpacf_query_rre(CPACF_KIMD, 0, 2, mask); + break; + case CPACF_KLMD: + __cpacf_query_rre(CPACF_KLMD, 0, 2, mask); + break; + case CPACF_KM: + __cpacf_query_rre(CPACF_KM, 2, 4, mask); + break; + case CPACF_KMA: + __cpacf_query_rrf(CPACF_KMA, 2, 4, 6, 0, mask); + break; + case CPACF_KMAC: + __cpacf_query_rre(CPACF_KMAC, 0, 2, mask); + break; + case CPACF_KMC: + __cpacf_query_rre(CPACF_KMC, 2, 4, mask); + break; + case CPACF_KMCTR: + __cpacf_query_rrf(CPACF_KMCTR, 2, 4, 6, 0, mask); + break; + case CPACF_KMF: + __cpacf_query_rre(CPACF_KMF, 2, 4, mask); + break; + case CPACF_KMO: + __cpacf_query_rre(CPACF_KMO, 2, 4, mask); + break; + case CPACF_PCC: + __cpacf_query_rre(CPACF_PCC, 0, 0, mask); + break; + case CPACF_PCKMO: + __cpacf_query_rre(CPACF_PCKMO, 0, 0, mask); + break; + case CPACF_PRNO: + __cpacf_query_rre(CPACF_PRNO, 2, 4, mask); + break; + default: + __cpacf_bad_opcode(); + } } static __always_inline int __cpacf_check_opcode(unsigned int opcode) @@ -211,10 +269,21 @@ static __always_inline int __cpacf_check_opcode(unsigned int opcode) case CPACF_KMA: return test_facility(146); /* check for MSA8 */ default: - BUG(); + __cpacf_bad_opcode(); + return 0; } } +/** + * cpacf_query() - check if a specific CPACF function is available + * @opcode: the opcode of the crypto instruction + * @func: the function code to test for + * + * Executes the query function for the given crypto instruction @opcode + * and checks if @func is available + * + * Returns 1 if @func is available for @opcode, 0 otherwise + */ static __always_inline int cpacf_query(unsigned int opcode, cpacf_mask_t *mask) { if (__cpacf_check_opcode(opcode)) { diff --git a/arch/s390/include/asm/dwarf.h b/arch/s390/include/asm/dwarf.h index 4f21ae561e4ddc..390906b8e386e6 100644 --- a/arch/s390/include/asm/dwarf.h +++ b/arch/s390/include/asm/dwarf.h @@ -9,6 +9,7 @@ #define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset #define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset #define CFI_RESTORE .cfi_restore +#define CFI_REL_OFFSET .cfi_rel_offset #ifdef CONFIG_AS_CFI_VAL_OFFSET #define CFI_VAL_OFFSET .cfi_val_offset diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h index fdd319a622b065..622cd08e5f50fd 100644 --- a/arch/s390/include/asm/entry-common.h +++ b/arch/s390/include/asm/entry-common.h @@ -55,7 +55,7 @@ static __always_inline void arch_exit_to_user_mode(void) static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, unsigned long ti_work) { - choose_random_kstack_offset(get_tod_clock_fast() & 0xff); + choose_random_kstack_offset(get_tod_clock_fast()); } #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h index 94b6919026dfb8..953d42205ea83e 100644 --- a/arch/s390/include/asm/facility.h +++ b/arch/s390/include/asm/facility.h @@ -60,8 +60,10 @@ static inline int test_facility(unsigned long nr) unsigned long facilities_als[] = { FACILITIES_ALS }; if (__builtin_constant_p(nr) && nr < sizeof(facilities_als) * 8) { - if (__test_facility(nr, &facilities_als)) - return 1; + if (__test_facility(nr, &facilities_als)) { + if (!__is_defined(__DECOMPRESSOR)) + return 1; + } } return __test_facility(nr, &stfle_fac_list); } diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h index b714ed0ef68853..9acf48e53a87fb 100644 --- a/arch/s390/include/asm/fpu/api.h +++ b/arch/s390/include/asm/fpu/api.h @@ -79,7 +79,7 @@ static inline int test_fp_ctl(u32 fpc) #define KERNEL_VXR_HIGH (KERNEL_VXR_V16V23|KERNEL_VXR_V24V31) #define KERNEL_VXR (KERNEL_VXR_LOW|KERNEL_VXR_HIGH) -#define KERNEL_FPR (KERNEL_FPC|KERNEL_VXR_V0V7) +#define KERNEL_FPR (KERNEL_FPC|KERNEL_VXR_LOW) struct kernel_fpu; diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h index 5cc46e0dde620d..9725586f42597c 100644 --- a/arch/s390/include/asm/gmap.h +++ b/arch/s390/include/asm/gmap.h @@ -146,7 +146,7 @@ int gmap_mprotect_notify(struct gmap *, unsigned long start, void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4], unsigned long gaddr, unsigned long vmaddr); -int gmap_mark_unmergeable(void); +int s390_disable_cow_sharing(void); void s390_unlist_old_asce(struct gmap *gmap); int s390_replace_asce(struct gmap *gmap); void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns); diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index 4453ad7c11aced..36a9c7740c437a 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -16,8 +16,10 @@ #include #define xlate_dev_mem_ptr xlate_dev_mem_ptr +#define kc_xlate_dev_mem_ptr xlate_dev_mem_ptr void *xlate_dev_mem_ptr(phys_addr_t phys); #define unxlate_dev_mem_ptr unxlate_dev_mem_ptr +#define kc_unxlate_dev_mem_ptr unxlate_dev_mem_ptr void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); #define IO_SPACE_LIMIT 0 diff --git a/arch/s390/include/asm/irq_work.h b/arch/s390/include/asm/irq_work.h index 603783766d0abb..f00c9f610d5a8e 100644 --- a/arch/s390/include/asm/irq_work.h +++ b/arch/s390/include/asm/irq_work.h @@ -7,6 +7,4 @@ static inline bool arch_irq_work_has_interrupt(void) return true; } -void arch_irq_work_raise(void); - #endif /* _ASM_S390_IRQ_WORK_H */ diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index 895f774bbcc553..bf78cf381dfcda 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -25,7 +25,7 @@ */ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("0: brcl 0,%l[label]\n" + asm goto("0: brcl 0,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" ".balign 8\n" ".long 0b-.,%l[label]-.\n" @@ -39,7 +39,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("0: brcl 15,%l[label]\n" + asm goto("0: brcl 15,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" ".balign 8\n" ".long 0b-.,%l[label]-.\n" diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 427f9528a7b694..b039881c277a79 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -427,6 +427,7 @@ struct kvm_vcpu_stat { u64 instruction_io_other; u64 instruction_lpsw; u64 instruction_lpswe; + u64 instruction_lpswey; u64 instruction_pfmf; u64 instruction_ptff; u64 instruction_sck; @@ -777,6 +778,13 @@ struct kvm_vm_stat { u64 inject_service_signal; u64 inject_virtio; u64 aen_forward; + u64 gmap_shadow_create; + u64 gmap_shadow_reuse; + u64 gmap_shadow_r1_entry; + u64 gmap_shadow_r2_entry; + u64 gmap_shadow_r3_entry; + u64 gmap_shadow_sg_entry; + u64 gmap_shadow_pg_entry; }; struct kvm_arch_memory_slot { diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index 829d68e2c68582..a9e5db0f2836e4 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -33,6 +33,11 @@ typedef struct { unsigned int uses_skeys:1; /* The mmu context uses CMM. */ unsigned int uses_cmm:1; + /* + * The mmu context allows COW-sharing of memory pages (KSM, zeropage). + * Note that COW-sharing during fork() is currently always allowed. + */ + unsigned int allow_cow_sharing:1; /* The gmaps associated with this context are allowed to use huge pages. */ unsigned int allow_gmap_hpage_1m:1; } mm_context_t; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 2a38af5a00c2df..8df6d09e9ca871 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -36,6 +36,7 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.has_pgste = 0; mm->context.uses_skeys = 0; mm->context.uses_cmm = 0; + mm->context.allow_cow_sharing = 1; mm->context.allow_gmap_hpage_1m = 0; #endif switch (mm->context.asce_limit) { diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index 287bb88f76986e..2686bee800e3d5 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -11,6 +11,8 @@ /* I/O size constraints */ #define ZPCI_MAX_READ_SIZE 8 #define ZPCI_MAX_WRITE_SIZE 128 +#define ZPCI_BOUNDARY_SIZE (1 << 12) +#define ZPCI_BOUNDARY_MASK (ZPCI_BOUNDARY_SIZE - 1) /* I/O Map */ #define ZPCI_IOMAP_SHIFT 48 @@ -125,16 +127,18 @@ static inline int zpci_read_single(void *dst, const volatile void __iomem *src, int zpci_write_block(volatile void __iomem *dst, const void *src, unsigned long len); -static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max) +static inline int zpci_get_max_io_size(u64 src, u64 dst, int len, int max) { - int count = len > max ? max : len, size = 1; + int offset = dst & ZPCI_BOUNDARY_MASK; + int size; - while (!(src & 0x1) && !(dst & 0x1) && ((size << 1) <= count)) { - dst = dst >> 1; - src = src >> 1; - size = size << 1; - } - return size; + size = min3(len, ZPCI_BOUNDARY_SIZE - offset, max); + if (IS_ALIGNED(src, 8) && IS_ALIGNED(dst, 8) && IS_ALIGNED(size, 8)) + return size; + + if (size >= 8) + return 8; + return rounddown_pow_of_two(size); } static inline int zpci_memcpy_fromio(void *dst, @@ -144,9 +148,9 @@ static inline int zpci_memcpy_fromio(void *dst, int size, rc = 0; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) src, - (u64) dst, n, - ZPCI_MAX_READ_SIZE); + size = zpci_get_max_io_size((u64 __force) src, + (u64) dst, n, + ZPCI_MAX_READ_SIZE); rc = zpci_read_single(dst, src, size); if (rc) break; @@ -166,9 +170,9 @@ static inline int zpci_memcpy_toio(volatile void __iomem *dst, return -EINVAL; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) dst, - (u64) src, n, - ZPCI_MAX_WRITE_SIZE); + size = zpci_get_max_io_size((u64 __force) dst, + (u64) src, n, + ZPCI_MAX_WRITE_SIZE); if (size > 8) /* main path */ rc = zpci_write_block(dst, src, size); else diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index fb3ee7758b7650..da2e91b5b19250 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -565,10 +565,20 @@ static inline pud_t set_pud_bit(pud_t pud, pgprot_t prot) } /* - * In the case that a guest uses storage keys - * faults should no longer be backed by zero pages + * As soon as the guest uses storage keys or enables PV, we deduplicate all + * mapped shared zeropages and prevent new shared zeropages from getting + * mapped. */ -#define mm_forbids_zeropage mm_has_pgste +#define mm_forbids_zeropage mm_forbids_zeropage +static inline int mm_forbids_zeropage(struct mm_struct *mm) +{ +#ifdef CONFIG_PGSTE + if (!mm->context.allow_cow_sharing) + return 1; +#endif + return 0; +} + static inline int mm_uses_skeys(struct mm_struct *mm) { #ifdef CONFIG_PGSTE @@ -729,7 +739,7 @@ static inline int pud_bad(pud_t pud) { unsigned long type = pud_val(pud) & _REGION_ENTRY_TYPE_MASK; - if (type > _REGION_ENTRY_TYPE_R3 || pud_large(pud)) + if (type > _REGION_ENTRY_TYPE_R3 || pud_leaf(pud)) return 1; if (type < _REGION_ENTRY_TYPE_R3) return 0; @@ -1396,7 +1406,7 @@ static inline unsigned long pud_deref(pud_t pud) unsigned long origin_mask; origin_mask = _REGION_ENTRY_ORIGIN; - if (pud_large(pud)) + if (pud_leaf(pud)) origin_mask = _REGION3_ENTRY_ORIGIN_LARGE; return (unsigned long)__va(pud_val(pud) & origin_mask); } @@ -1764,8 +1774,10 @@ static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, static inline pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { - pmd_t pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID); + pmd_t pmd; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); + pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID); return pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd); } diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index dc17896a001a92..e7338ed540d8fc 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -308,8 +308,8 @@ static inline void __load_psw(psw_t psw) */ static __always_inline void __load_psw_mask(unsigned long mask) { + psw_t psw __uninitialized; unsigned long addr; - psw_t psw; psw.mask = mask; diff --git a/arch/s390/include/asm/syscall_wrapper.h b/arch/s390/include/asm/syscall_wrapper.h index 9286430fe7290b..35c1d1b860d88a 100644 --- a/arch/s390/include/asm/syscall_wrapper.h +++ b/arch/s390/include/asm/syscall_wrapper.h @@ -63,10 +63,6 @@ cond_syscall(__s390x_sys_##name); \ cond_syscall(__s390_sys_##name) -#define SYS_NI(name) \ - SYSCALL_ALIAS(__s390x_sys_##name, sys_ni_posix_timers); \ - SYSCALL_ALIAS(__s390_sys_##name, sys_ni_posix_timers) - #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ long __s390_compat_sys##name(struct pt_regs *regs); \ ALLOW_ERROR_INJECTION(__s390_compat_sys##name, ERRNO); \ @@ -85,15 +81,11 @@ /* * As some compat syscalls may not be implemented, we need to expand - * COND_SYSCALL_COMPAT in kernel/sys_ni.c and COMPAT_SYS_NI in - * kernel/time/posix-stubs.c to cover this case as well. + * COND_SYSCALL_COMPAT in kernel/sys_ni.c to cover this case as well. */ #define COND_SYSCALL_COMPAT(name) \ cond_syscall(__s390_compat_sys_##name) -#define COMPAT_SYS_NI(name) \ - SYSCALL_ALIAS(__s390_compat_sys_##name, sys_ni_posix_timers) - #define __S390_SYS_STUBx(x, name, ...) \ long __s390_sys##name(struct pt_regs *regs); \ ALLOW_ERROR_INJECTION(__s390_sys##name, ERRNO); \ @@ -124,9 +116,6 @@ #define COND_SYSCALL(name) \ cond_syscall(__s390x_sys_##name) -#define SYS_NI(name) \ - SYSCALL_ALIAS(__s390x_sys_##name, sys_ni_posix_timers) - #define __S390_SYS_STUBx(x, fullname, name, ...) #endif /* CONFIG_COMPAT */ diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 0e7bd3873907f7..b2e2f9a4163c5c 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -442,7 +442,10 @@ static inline int share(unsigned long addr, u16 cmd) if (!uv_call(0, (u64)&uvcb)) return 0; - return -EINVAL; + pr_err("%s UVC failed (rc: 0x%x, rrc: 0x%x), possible hypervisor bug.\n", + uvcb.header.cmd == UVC_CMD_SET_SHARED_ACCESS ? "Share" : "Unshare", + uvcb.header.rc, uvcb.header.rrc); + panic("System security cannot be guaranteed unless the system panics now.\n"); } /* diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c index 56254fa06f9906..4f266903022091 100644 --- a/arch/s390/kernel/cache.c +++ b/arch/s390/kernel/cache.c @@ -166,5 +166,6 @@ int populate_cache_leaves(unsigned int cpu) ci_leaf_init(this_leaf++, pvt, ctype, level, cpu); } } + this_cpu_ci->cpu_map_populated = true; return 0; } diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 442ce0489e1a1e..3a54733e4fc65b 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -258,15 +258,9 @@ static inline void save_vector_registers(void) #endif } -static inline void setup_control_registers(void) +static inline void setup_low_address_protection(void) { - unsigned long reg; - - __ctl_store(reg, 0, 0); - reg |= CR0_LOW_ADDRESS_PROTECTION; - reg |= CR0_EMERGENCY_SIGNAL_SUBMASK; - reg |= CR0_EXTERNAL_CALL_SUBMASK; - __ctl_load(reg, 0, 0); + __ctl_set_bit(0, 28); } static inline void setup_access_registers(void) @@ -314,7 +308,7 @@ void __init startup_init(void) save_vector_registers(); setup_topology(); sclp_early_detect(); - setup_control_registers(); + setup_low_address_protection(); setup_access_registers(); lockdep_on(); } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 49a11f6dd7ae9a..26c08ee8774077 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -653,6 +653,7 @@ SYM_DATA_START_LOCAL(daton_psw) SYM_DATA_END(daton_psw) .section .rodata, "a" + .balign 8 #define SYSCALL(esame,emu) .quad __s390x_ ## esame SYM_DATA_START(sys_call_table) #include "asm/syscall_table.h" diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index c46381ea04ecb1..7f6f8c438c2654 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -296,6 +296,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe *p; int bit; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 05e51666db033f..a3d3cb39b021a7 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -666,6 +666,7 @@ static int __init ipl_init(void) &ipl_ccw_attr_group_lpar); break; case IPL_TYPE_ECKD: + case IPL_TYPE_ECKD_DUMP: rc = sysfs_create_group(&ipl_kset->kobj, &ipl_eckd_attr_group); break; case IPL_TYPE_FCP: @@ -961,8 +962,8 @@ static ssize_t reipl_nvme_scpdata_write(struct file *filp, struct kobject *kobj, scpdata_len += padding; } - reipl_block_nvme->hdr.len = IPL_BP_FCP_LEN + scpdata_len; - reipl_block_nvme->nvme.len = IPL_BP0_FCP_LEN + scpdata_len; + reipl_block_nvme->hdr.len = IPL_BP_NVME_LEN + scpdata_len; + reipl_block_nvme->nvme.len = IPL_BP0_NVME_LEN + scpdata_len; reipl_block_nvme->nvme.scp_data_len = scpdata_len; return count; @@ -1857,9 +1858,9 @@ static int __init dump_nvme_init(void) } dump_block_nvme->hdr.len = IPL_BP_NVME_LEN; dump_block_nvme->hdr.version = IPL_PARM_BLOCK_VERSION; - dump_block_nvme->fcp.len = IPL_BP0_NVME_LEN; - dump_block_nvme->fcp.pbt = IPL_PBT_NVME; - dump_block_nvme->fcp.opt = IPL_PB0_NVME_OPT_DUMP; + dump_block_nvme->nvme.len = IPL_BP0_NVME_LEN; + dump_block_nvme->nvme.pbt = IPL_PBT_NVME; + dump_block_nvme->nvme.opt = IPL_PB0_NVME_OPT_DUMP; dump_capabilities |= DUMP_TYPE_NVME; return 0; } diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 850c11ea631a6b..5466e7bada03d2 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -556,25 +556,31 @@ static int cfdiag_diffctr(struct cpu_cf_events *cpuhw, unsigned long auth) struct cf_trailer_entry *trailer_start, *trailer_stop; struct cf_ctrset_entry *ctrstart, *ctrstop; size_t offset = 0; + int i; - auth &= (1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1; - do { + for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) { ctrstart = (struct cf_ctrset_entry *)(cpuhw->start + offset); ctrstop = (struct cf_ctrset_entry *)(cpuhw->stop + offset); + /* Counter set not authorized */ + if (!(auth & cpumf_ctr_ctl[i])) + continue; + /* Counter set size zero was not saved */ + if (!cpum_cf_read_setsize(i)) + continue; + if (memcmp(ctrstop, ctrstart, sizeof(*ctrstop))) { pr_err_once("cpum_cf_diag counter set compare error " "in set %i\n", ctrstart->set); return 0; } - auth &= ~cpumf_ctr_ctl[ctrstart->set]; if (ctrstart->def == CF_DIAG_CTRSET_DEF) { cfdiag_diffctrset((u64 *)(ctrstart + 1), (u64 *)(ctrstop + 1), ctrstart->ctr); offset += ctrstart->ctr * sizeof(u64) + sizeof(*ctrstart); } - } while (ctrstart->def && auth); + } /* Save time_stamp from start of event in stop's trailer */ trailer_start = (struct cf_trailer_entry *)(cpuhw->start + offset); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 06efad5b4f931b..a3169193775f71 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1463,7 +1463,7 @@ static int aux_output_begin(struct perf_output_handle *handle, unsigned long range, i, range_scan, idx, head, base, offset; struct hws_trailer_entry *te; - if (WARN_ON_ONCE(handle->head & ~PAGE_MASK)) + if (handle->head & ~PAGE_MASK) return -EINVAL; aux->head = handle->head >> PAGE_SHIFT; @@ -1642,7 +1642,7 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw) unsigned long num_sdb; aux = perf_get_aux(handle); - if (WARN_ON_ONCE(!aux)) + if (!aux) return; /* Inform user space new data arrived */ @@ -1661,7 +1661,7 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw) num_sdb); break; } - if (WARN_ON_ONCE(!aux)) + if (!aux) return; /* Update head and alert_mark to new position */ @@ -1896,12 +1896,8 @@ static void cpumsf_pmu_start(struct perf_event *event, int flags) { struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf); - if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + if (!(event->hw.state & PERF_HES_STOPPED)) return; - - if (flags & PERF_EF_RELOAD) - WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); - perf_pmu_disable(event->pmu); event->hw.state = 0; cpuhw->lsctl.cs = 1; diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index fe7d1774ded184..4a4e914c283c80 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -646,7 +646,7 @@ static int __init attr_event_init(void) for (i = 0; i < ARRAY_SIZE(paicrypt_ctrnames); i++) { ret = attr_event_init_one(attrs, i); if (ret) { - attr_event_free(attrs, i - 1); + attr_event_free(attrs, i); return ret; } } diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index c57c1a203256fb..b5febe22d05464 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -607,7 +607,7 @@ static int __init attr_event_init(void) for (i = 0; i < ARRAY_SIZE(paiext_ctrnames); i++) { ret = attr_event_init_one(attrs, i); if (ret) { - attr_event_free(attrs, i - 1); + attr_event_free(attrs, i); return ret; } } diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index ea244a73efad9d..512b8147375935 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -385,6 +385,7 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) /* * floating point control reg. is in the thread structure */ + save_fpu_regs(); if ((unsigned int) data != 0 || test_fp_ctl(data >> (BITS_PER_LONG - 32))) return -EINVAL; @@ -741,6 +742,7 @@ static int __poke_user_compat(struct task_struct *child, /* * floating point control reg. is in the thread structure */ + save_fpu_regs(); if (test_fp_ctl(tmp)) return -EINVAL; child->thread.fpu.fpc = data; @@ -904,9 +906,7 @@ static int s390_fpregs_set(struct task_struct *target, int rc = 0; freg_t fprs[__NUM_FPRS]; - if (target == current) - save_fpu_regs(); - + save_fpu_regs(); if (MACHINE_HAS_VX) convert_vx_to_fp(fprs, target->thread.fpu.vxrs); else diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index de6ad0fb2328a1..d48c7afe97e628 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -155,7 +155,7 @@ unsigned int __bootdata_preserved(zlib_dfltcc_support); EXPORT_SYMBOL(zlib_dfltcc_support); u64 __bootdata_preserved(stfle_fac_list[16]); EXPORT_SYMBOL(stfle_fac_list); -u64 __bootdata_preserved(alt_stfle_fac_list[16]); +u64 alt_stfle_fac_list[16]; struct oldmem_data __bootdata_preserved(oldmem_data); unsigned long VMALLOC_START; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index a4edb7ea66ea76..c63be2efd68952 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -1013,12 +1013,12 @@ void __init smp_fill_possible_mask(void) void __init smp_prepare_cpus(unsigned int max_cpus) { - /* request the 0x1201 emergency signal external interrupt */ if (register_external_irq(EXT_IRQ_EMERGENCY_SIG, do_ext_call_interrupt)) panic("Couldn't request external interrupt 0x1201"); - /* request the 0x1202 external call external interrupt */ + ctl_set_bit(0, 14); if (register_external_irq(EXT_IRQ_EXTERNAL_CALL, do_ext_call_interrupt)) panic("Couldn't request external interrupt 0x1202"); + ctl_set_bit(0, 13); } void __init smp_prepare_boot_cpu(void) diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 0122cc156952cf..51cc3616d5f98a 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -418,7 +418,7 @@ 412 32 utimensat_time64 - sys_utimensat 413 32 pselect6_time64 - compat_sys_pselect6_time64 414 32 ppoll_time64 - compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 - sys_io_pgetevents +416 32 io_pgetevents_time64 - compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 - sys_mq_timedsend 419 32 mq_timedreceive_time64 - sys_mq_timedreceive diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index fc07bc39e69839..81fdee22a497df 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -181,36 +181,36 @@ int uv_convert_owned_from_secure(unsigned long paddr) } /* - * Calculate the expected ref_count for a page that would otherwise have no + * Calculate the expected ref_count for a folio that would otherwise have no * further pins. This was cribbed from similar functions in other places in * the kernel, but with some slight modifications. We know that a secure - * page can not be a huge page for example. + * folio can not be a large folio, for example. */ -static int expected_page_refs(struct page *page) +static int expected_folio_refs(struct folio *folio) { int res; - res = page_mapcount(page); - if (PageSwapCache(page)) { + res = folio_mapcount(folio); + if (folio_test_swapcache(folio)) { res++; - } else if (page_mapping(page)) { + } else if (folio_mapping(folio)) { res++; - if (page_has_private(page)) + if (folio->private) res++; } return res; } -static int make_page_secure(struct page *page, struct uv_cb_header *uvcb) +static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb) { int expected, cc = 0; - if (PageWriteback(page)) + if (folio_test_writeback(folio)) return -EAGAIN; - expected = expected_page_refs(page); - if (!page_ref_freeze(page, expected)) + expected = expected_folio_refs(folio); + if (!folio_ref_freeze(folio, expected)) return -EBUSY; - set_bit(PG_arch_1, &page->flags); + set_bit(PG_arch_1, &folio->flags); /* * If the UVC does not succeed or fail immediately, we don't want to * loop for long, or we might get stall notifications. @@ -220,9 +220,9 @@ static int make_page_secure(struct page *page, struct uv_cb_header *uvcb) * -EAGAIN and we let the callers deal with it. */ cc = __uv_call(0, (u64)uvcb); - page_ref_unfreeze(page, expected); + folio_ref_unfreeze(folio, expected); /* - * Return -ENXIO if the page was not mapped, -EINVAL for other errors. + * Return -ENXIO if the folio was not mapped, -EINVAL for other errors. * If busy or partially completed, return -EAGAIN. */ if (cc == UVC_CC_OK) @@ -277,7 +277,7 @@ int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) bool local_drain = false; spinlock_t *ptelock; unsigned long uaddr; - struct page *page; + struct folio *folio; pte_t *ptep; int rc; @@ -306,15 +306,26 @@ int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) if (!ptep) goto out; if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) { - page = pte_page(*ptep); + folio = page_folio(pte_page(*ptep)); + rc = -EINVAL; + if (folio_test_large(folio)) + goto unlock; rc = -EAGAIN; - if (trylock_page(page)) { + if (folio_trylock(folio)) { if (should_export_before_import(uvcb, gmap->mm)) - uv_convert_from_secure(page_to_phys(page)); - rc = make_page_secure(page, uvcb); - unlock_page(page); + uv_convert_from_secure(PFN_PHYS(folio_pfn(folio))); + rc = make_folio_secure(folio, uvcb); + folio_unlock(folio); } + + /* + * Once we drop the PTL, the folio may get unmapped and + * freed immediately. We need a temporary reference. + */ + if (rc == -EAGAIN) + folio_get(folio); } +unlock: pte_unmap_unlock(ptep, ptelock); out: mmap_read_unlock(gmap->mm); @@ -324,10 +335,11 @@ int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) * If we are here because the UVC returned busy or partial * completion, this is just a useless check, but it is safe. */ - wait_on_page_writeback(page); + folio_wait_writeback(folio); + folio_put(folio); } else if (rc == -EBUSY) { /* - * If we have tried a local drain and the page refcount + * If we have tried a local drain and the folio refcount * still does not match our expected safe value, try with a * system wide drain. This is needed if the pagevecs holding * the page are on a different CPU. @@ -338,7 +350,7 @@ int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) return -EAGAIN; } /* - * We are here if the page refcount does not match the + * We are here if the folio refcount does not match the * expected safe value. The main culprits are usually * pagevecs. With lru_add_drain() we drain the pagevecs * on the local CPU so that hopefully the refcount will diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index 23e868b79a6c99..4800d80decee69 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -19,10 +19,12 @@ KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS)) KBUILD_AFLAGS_32 += -m31 -s KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS)) +KBUILD_CFLAGS_32 := $(filter-out -mpacked-stack,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_32 := $(filter-out -mno-pic-data-is-text-relative,$(KBUILD_CFLAGS_32)) -KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin +KBUILD_CFLAGS_32 := $(filter-out -fno-asynchronous-unwind-tables,$(KBUILD_CFLAGS_32)) +KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin -fasynchronous-unwind-tables -LDFLAGS_vdso32.so.dbg += -fPIC -shared -soname=linux-vdso32.so.1 \ +LDFLAGS_vdso32.so.dbg += -shared -soname=linux-vdso32.so.1 \ --hash-style=both --build-id=sha1 -melf_s390 -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) @@ -61,16 +63,6 @@ quiet_cmd_vdso32as = VDSO32A $@ quiet_cmd_vdso32cc = VDSO32C $@ cmd_vdso32cc = $(CC) $(c_flags) -c -o $@ $< -# install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso32.so: $(obj)/vdso32.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso32.so - # Generate VDSO offsets using helper script gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index fc1c6ff8178f59..2f2e4e997030c3 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -24,9 +24,12 @@ KBUILD_AFLAGS_64 := $(filter-out -m64,$(KBUILD_AFLAGS)) KBUILD_AFLAGS_64 += -m64 KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS)) +KBUILD_CFLAGS_64 := $(filter-out -mpacked-stack,$(KBUILD_CFLAGS_64)) KBUILD_CFLAGS_64 := $(filter-out -mno-pic-data-is-text-relative,$(KBUILD_CFLAGS_64)) -KBUILD_CFLAGS_64 += -m64 -fPIC -fno-common -fno-builtin -ldflags-y := -fPIC -shared -soname=linux-vdso64.so.1 \ +KBUILD_CFLAGS_64 := $(filter-out -munaligned-symbols,$(KBUILD_CFLAGS_64)) +KBUILD_CFLAGS_64 := $(filter-out -fno-asynchronous-unwind-tables,$(KBUILD_CFLAGS_64)) +KBUILD_CFLAGS_64 += -m64 -fPIC -fno-common -fno-builtin -fasynchronous-unwind-tables +ldflags-y := -shared -soname=linux-vdso64.so.1 \ --hash-style=both --build-id=sha1 -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64) @@ -70,16 +73,6 @@ quiet_cmd_vdso64as = VDSO64A $@ quiet_cmd_vdso64cc = VDSO64C $@ cmd_vdso64cc = $(CC) $(c_flags) -c -o $@ $< -# install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso64.so: $(obj)/vdso64.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso64.so - # Generate VDSO offsets using helper script gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S index 57f62596e53b95..85247ef5a41b89 100644 --- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S +++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S @@ -24,8 +24,10 @@ __kernel_\func: CFI_DEF_CFA_OFFSET (STACK_FRAME_OVERHEAD + WRAPPER_FRAME_SIZE) CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD stg %r14,STACK_FRAME_OVERHEAD(%r15) + CFI_REL_OFFSET 14, STACK_FRAME_OVERHEAD brasl %r14,__s390_vdso_\func lg %r14,STACK_FRAME_OVERHEAD(%r15) + CFI_RESTORE 14 aghi %r15,WRAPPER_FRAME_SIZE CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD CFI_RESTORE 15 diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 2ae201ebf90b97..de5f9f623f5b27 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -71,6 +71,15 @@ SECTIONS . = ALIGN(PAGE_SIZE); __end_ro_after_init = .; + .data.rel.ro : { + *(.data.rel.ro .data.rel.ro.*) + } + .got : { + __got_start = .; + *(.got) + __got_end = .; + } + RW_DATA(0x100, PAGE_SIZE, THREAD_SIZE) BOOT_DATA_PRESERVED diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index e0a88dcaf5cb7a..24a18e5ef6e8e3 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -210,13 +210,13 @@ void vtime_flush(struct task_struct *tsk) virt_timer_expire(); steal = S390_lowcore.steal_timer; - avg_steal = S390_lowcore.avg_steal_timer / 2; + avg_steal = S390_lowcore.avg_steal_timer; if ((s64) steal > 0) { S390_lowcore.steal_timer = 0; account_steal_time(cputime_to_nsecs(steal)); avg_steal += steal; } - S390_lowcore.avg_steal_timer = avg_steal; + S390_lowcore.avg_steal_timer = avg_steal / 2; } static u64 vtime_delta(void) diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 3c65b8258ae67a..2cc3ec034046c9 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -77,7 +77,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu) vcpu->stat.instruction_diagnose_258++; if (vcpu->run->s.regs.gprs[rx] & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm)); + rc = read_guest_real(vcpu, vcpu->run->s.regs.gprs[rx], &parm, sizeof(parm)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); if (parm.parm_version != 2 || parm.parm_len < 5 || parm.code != 0x258) diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 6d6bc19b37dcbd..090dc38334336b 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -1001,6 +1001,8 @@ static int access_guest_page(struct kvm *kvm, enum gacc_mode mode, gpa_t gpa, const gfn_t gfn = gpa_to_gfn(gpa); int rc; + if (!gfn_to_memslot(kvm, gfn)) + return PGM_ADDRESSING; if (mode == GACC_STORE) rc = kvm_write_guest_page(kvm, gfn, data, offset, len); else @@ -1158,6 +1160,8 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, gra += fragment_len; data += fragment_len; } + if (rc > 0) + vcpu->arch.pgm.code = rc; return rc; } @@ -1382,6 +1386,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, unsigned long *pgt, int *dat_protection, int *fake) { + struct kvm *kvm; struct gmap *parent; union asce asce; union vaddress vaddr; @@ -1390,6 +1395,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, *fake = 0; *dat_protection = 0; + kvm = sg->private; parent = sg->parent; vaddr.addr = saddr; asce.val = sg->orig_asce; @@ -1450,6 +1456,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, rc = gmap_shadow_r2t(sg, saddr, rfte.val, *fake); if (rc) return rc; + kvm->stat.gmap_shadow_r1_entry++; } fallthrough; case ASCE_TYPE_REGION2: { @@ -1478,6 +1485,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, rc = gmap_shadow_r3t(sg, saddr, rste.val, *fake); if (rc) return rc; + kvm->stat.gmap_shadow_r2_entry++; } fallthrough; case ASCE_TYPE_REGION3: { @@ -1515,6 +1523,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, rc = gmap_shadow_sgt(sg, saddr, rtte.val, *fake); if (rc) return rc; + kvm->stat.gmap_shadow_r3_entry++; } fallthrough; case ASCE_TYPE_SEGMENT: { @@ -1548,6 +1557,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, rc = gmap_shadow_pgt(sg, saddr, ste.val, *fake); if (rc) return rc; + kvm->stat.gmap_shadow_sg_entry++; } } /* Return the parent address of the page table */ @@ -1618,6 +1628,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg, pte.p |= dat_protection; if (!rc) rc = gmap_shadow_page(sg, saddr, __pte(pte.val)); + vcpu->kvm->stat.gmap_shadow_pg_entry++; ipte_unlock(vcpu->kvm); mmap_read_unlock(sg->mm); return rc; diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index b320d12aa04934..3fde45a151f22e 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -405,11 +405,12 @@ int read_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data, * @len: number of bytes to copy * * Copy @len bytes from @data (kernel space) to @gra (guest real address). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest low address and key protection are not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying from @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to guest memory. */ @@ -428,11 +429,12 @@ int write_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, * @len: number of bytes to copy * * Copy @len bytes from @gra (guest real address) to @data (kernel space). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest key protection is not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying to @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to kernel space. */ diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index b3f17e014cab5d..348d030d2660ca 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -66,7 +66,14 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = { STATS_DESC_COUNTER(VM, inject_pfault_done), STATS_DESC_COUNTER(VM, inject_service_signal), STATS_DESC_COUNTER(VM, inject_virtio), - STATS_DESC_COUNTER(VM, aen_forward) + STATS_DESC_COUNTER(VM, aen_forward), + STATS_DESC_COUNTER(VM, gmap_shadow_reuse), + STATS_DESC_COUNTER(VM, gmap_shadow_create), + STATS_DESC_COUNTER(VM, gmap_shadow_r1_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_r2_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_r3_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_sg_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_pg_entry), }; const struct kvm_stats_header kvm_vm_stats_header = { @@ -125,6 +132,7 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, instruction_io_other), STATS_DESC_COUNTER(VCPU, instruction_lpsw), STATS_DESC_COUNTER(VCPU, instruction_lpswe), + STATS_DESC_COUNTER(VCPU, instruction_lpswey), STATS_DESC_COUNTER(VCPU, instruction_pfmf), STATS_DESC_COUNTER(VCPU, instruction_ptff), STATS_DESC_COUNTER(VCPU, instruction_sck), @@ -2625,9 +2633,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) if (r) break; - mmap_write_lock(current->mm); - r = gmap_mark_unmergeable(); - mmap_write_unlock(current->mm); + r = s390_disable_cow_sharing(); if (r) break; @@ -4307,10 +4313,6 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) vcpu_load(vcpu); - if (test_fp_ctl(fpu->fpc)) { - ret = -EINVAL; - goto out; - } vcpu->run->s.regs.fpc = fpu->fpc; if (MACHINE_HAS_VX) convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs, @@ -4318,7 +4320,6 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) else memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs)); -out: vcpu_put(vcpu); return ret; } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index a7ea80cfa445e1..0c0f47ec634477 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -120,6 +120,21 @@ static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, u8 *ar) return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; } +static inline u64 kvm_s390_get_base_disp_siy(struct kvm_vcpu *vcpu, u8 *ar) +{ + u32 base1 = vcpu->arch.sie_block->ipb >> 28; + s64 disp1; + + /* The displacement is a 20bit _SIGNED_ value */ + disp1 = sign_extend64(((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) + + ((vcpu->arch.sie_block->ipb & 0xff00) << 4), 19); + + if (ar) + *ar = base1; + + return (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1; +} + static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu, u64 *address1, u64 *address2, u8 *ar_b1, u8 *ar_b2) @@ -234,7 +249,12 @@ static inline unsigned long kvm_s390_get_gfn_end(struct kvm_memslots *slots) static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm) { - u32 gd = virt_to_phys(kvm->arch.gisa_int.origin); + u32 gd; + + if (!kvm->arch.gisa_int.origin) + return 0; + + gd = virt_to_phys(kvm->arch.gisa_int.origin); if (gd && sclp.has_gisaf) gd |= GISA_FORMAT1; diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index dc4cfa8795c08c..e5b220e686b09a 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -793,6 +793,36 @@ static int handle_lpswe(struct kvm_vcpu *vcpu) return 0; } +static int handle_lpswey(struct kvm_vcpu *vcpu) +{ + psw_t new_psw; + u64 addr; + int rc; + u8 ar; + + vcpu->stat.instruction_lpswey++; + + if (!test_kvm_facility(vcpu->kvm, 193)) + return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + addr = kvm_s390_get_base_disp_siy(vcpu, &ar); + if (addr & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + + vcpu->arch.sie_block->gpsw = new_psw; + if (!is_valid_psw(&vcpu->arch.sie_block->gpsw)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + return 0; +} + static int handle_stidp(struct kvm_vcpu *vcpu) { u64 stidp_data = vcpu->kvm->arch.model.cpuid; @@ -1458,6 +1488,8 @@ int kvm_s390_handle_eb(struct kvm_vcpu *vcpu) case 0x61: case 0x62: return handle_ri(vcpu); + case 0x71: + return handle_lpswey(vcpu); default: return -EOPNOTSUPP; } diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 61499293c2ac3b..db9a180de65f1f 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -587,10 +587,6 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start, if (!gmap_is_shadow(gmap)) return; - if (start >= 1UL << 31) - /* We are only interested in prefix pages */ - return; - /* * Only new shadow blocks are added to the list during runtime, * therefore we can safely reference them all the time. @@ -1214,15 +1210,17 @@ static int acquire_gmap_shadow(struct kvm_vcpu *vcpu, * we're holding has been unshadowed. If the gmap is still valid, * we can safely reuse it. */ - if (vsie_page->gmap && gmap_shadow_valid(vsie_page->gmap, asce, edat)) + if (vsie_page->gmap && gmap_shadow_valid(vsie_page->gmap, asce, edat)) { + vcpu->kvm->stat.gmap_shadow_reuse++; return 0; + } /* release the old shadow - if any, and mark the prefix as unmapped */ release_gmap_shadow(vsie_page); gmap = gmap_shadow(vcpu->arch.gmap, asce, edat); if (IS_ERR(gmap)) return PTR_ERR(gmap); - gmap->private = vcpu->kvm; + vcpu->kvm->stat.gmap_shadow_create++; WRITE_ONCE(vsie_page->gmap, gmap); return 0; } diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index f47515313226c4..9af4d829649444 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -95,11 +95,12 @@ static long cmm_alloc_pages(long nr, long *counter, (*counter)++; spin_unlock(&cmm_lock); nr--; + cond_resched(); } return nr; } -static long cmm_free_pages(long nr, long *counter, struct cmm_page_array **list) +static long __cmm_free_pages(long nr, long *counter, struct cmm_page_array **list) { struct cmm_page_array *pa; unsigned long addr; @@ -123,6 +124,21 @@ static long cmm_free_pages(long nr, long *counter, struct cmm_page_array **list) return nr; } +static long cmm_free_pages(long nr, long *counter, struct cmm_page_array **list) +{ + long inc = 0; + + while (nr) { + inc = min(256L, nr); + nr -= inc; + inc = __cmm_free_pages(inc, counter, list); + if (inc) + break; + cond_resched(); + } + return nr + inc; +} + static int cmm_oom_notify(struct notifier_block *self, unsigned long dummy, void *parm) { diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index b678295931c315..1a231181a413bd 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -331,14 +331,16 @@ static noinline void do_fault_error(struct pt_regs *regs, vm_fault_t fault) do_no_context(regs, fault); else do_sigsegv(regs, SEGV_MAPERR); - } else if (fault & VM_FAULT_SIGBUS) { + } else if (fault & (VM_FAULT_SIGBUS | VM_FAULT_HWPOISON)) { /* Kernel mode? Handle exceptions or die */ if (!user_mode(regs)) do_no_context(regs, fault); else do_sigbus(regs); - } else + } else { + pr_emerg("Unexpected fault flags: %08x\n", fault); BUG(); + } break; } } diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 906a7bfc2a7874..1a656db09c9fe3 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -21,10 +21,22 @@ #include #include +#include #include #define GMAP_SHADOW_FAKE_TABLE 1ULL +static struct page *gmap_alloc_crst(void) +{ + struct page *page; + + page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + if (!page) + return NULL; + arch_set_page_dat(page, CRST_ALLOC_ORDER); + return page; +} + /** * gmap_alloc - allocate and initialize a guest address space * @limit: maximum address of the gmap address space @@ -67,7 +79,7 @@ static struct gmap *gmap_alloc(unsigned long limit) spin_lock_init(&gmap->guest_table_lock); spin_lock_init(&gmap->shadow_lock); refcount_set(&gmap->ref_count, 1); - page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + page = gmap_alloc_crst(); if (!page) goto out_free; page->index = 0; @@ -308,7 +320,7 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table, unsigned long *new; /* since we dont free the gmap table until gmap_free we can unlock */ - page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + page = gmap_alloc_crst(); if (!page) return -ENOMEM; new = page_to_virt(page); @@ -584,7 +596,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) pud = pud_offset(p4d, vmaddr); VM_BUG_ON(pud_none(*pud)); /* large puds cannot yet be handled */ - if (pud_large(*pud)) + if (pud_leaf(*pud)) return -EFAULT; pmd = pmd_offset(pud, vmaddr); VM_BUG_ON(pmd_none(*pmd)); @@ -1679,6 +1691,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, return ERR_PTR(-ENOMEM); new->mm = parent->mm; new->parent = gmap_get(parent); + new->private = parent->private; new->orig_asce = asce; new->edat_level = edat_level; new->initialized = false; @@ -1759,7 +1772,7 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t, BUG_ON(!gmap_is_shadow(sg)); /* Allocate a shadow region second table */ - page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + page = gmap_alloc_crst(); if (!page) return -ENOMEM; page->index = r2t & _REGION_ENTRY_ORIGIN; @@ -1843,7 +1856,7 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, BUG_ON(!gmap_is_shadow(sg)); /* Allocate a shadow region second table */ - page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + page = gmap_alloc_crst(); if (!page) return -ENOMEM; page->index = r3t & _REGION_ENTRY_ORIGIN; @@ -1927,7 +1940,7 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt, BUG_ON(!gmap_is_shadow(sg) || (sgt & _REGION3_ENTRY_LARGE)); /* Allocate a shadow segment table */ - page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + page = gmap_alloc_crst(); if (!page) return -ENOMEM; page->index = sgt & _REGION_ENTRY_ORIGIN; @@ -2534,41 +2547,6 @@ static inline void thp_split_mm(struct mm_struct *mm) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -/* - * Remove all empty zero pages from the mapping for lazy refaulting - * - This must be called after mm->context.has_pgste is set, to avoid - * future creation of zero pages - * - This must be called after THP was disabled. - * - * mm contracts with s390, that even if mm were to remove a page table, - * racing with the loop below and so causing pte_offset_map_lock() to fail, - * it will never insert a page table containing empty zero pages once - * mm_forbids_zeropage(mm) i.e. mm->context.has_pgste is set. - */ -static int __zap_zero_pages(pmd_t *pmd, unsigned long start, - unsigned long end, struct mm_walk *walk) -{ - unsigned long addr; - - for (addr = start; addr != end; addr += PAGE_SIZE) { - pte_t *ptep; - spinlock_t *ptl; - - ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); - if (!ptep) - break; - if (is_zero_pfn(pte_pfn(*ptep))) - ptep_xchg_direct(walk->mm, addr, ptep, __pte(_PAGE_INVALID)); - pte_unmap_unlock(ptep, ptl); - } - return 0; -} - -static const struct mm_walk_ops zap_zero_walk_ops = { - .pmd_entry = __zap_zero_pages, - .walk_lock = PGWALK_WRLOCK, -}; - /* * switch on pgstes for its userspace process (for kvm) */ @@ -2586,22 +2564,142 @@ int s390_enable_sie(void) mm->context.has_pgste = 1; /* split thp mappings and disable thp for future mappings */ thp_split_mm(mm); - walk_page_range(mm, 0, TASK_SIZE, &zap_zero_walk_ops, NULL); mmap_write_unlock(mm); return 0; } EXPORT_SYMBOL_GPL(s390_enable_sie); -int gmap_mark_unmergeable(void) +static int find_zeropage_pte_entry(pte_t *pte, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + unsigned long *found_addr = walk->private; + + /* Return 1 of the page is a zeropage. */ + if (is_zero_pfn(pte_pfn(*pte))) { + /* + * Shared zeropage in e.g., a FS DAX mapping? We cannot do the + * right thing and likely don't care: FAULT_FLAG_UNSHARE + * currently only works in COW mappings, which is also where + * mm_forbids_zeropage() is checked. + */ + if (!is_cow_mapping(walk->vma->vm_flags)) + return -EFAULT; + + *found_addr = addr; + return 1; + } + return 0; +} + +static const struct mm_walk_ops find_zeropage_ops = { + .pte_entry = find_zeropage_pte_entry, + .walk_lock = PGWALK_WRLOCK, +}; + +/* + * Unshare all shared zeropages, replacing them by anonymous pages. Note that + * we cannot simply zap all shared zeropages, because this could later + * trigger unexpected userfaultfd missing events. + * + * This must be called after mm->context.allow_cow_sharing was + * set to 0, to avoid future mappings of shared zeropages. + * + * mm contracts with s390, that even if mm were to remove a page table, + * and racing with walk_page_range_vma() calling pte_offset_map_lock() + * would fail, it will never insert a page table containing empty zero + * pages once mm_forbids_zeropage(mm) i.e. + * mm->context.allow_cow_sharing is set to 0. + */ +static int __s390_unshare_zeropages(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, 0); + unsigned long addr; + vm_fault_t fault; + int rc; + + for_each_vma(vmi, vma) { + /* + * We could only look at COW mappings, but it's more future + * proof to catch unexpected zeropages in other mappings and + * fail. + */ + if ((vma->vm_flags & VM_PFNMAP) || is_vm_hugetlb_page(vma)) + continue; + addr = vma->vm_start; + +retry: + rc = walk_page_range_vma(vma, addr, vma->vm_end, + &find_zeropage_ops, &addr); + if (rc < 0) + return rc; + else if (!rc) + continue; + + /* addr was updated by find_zeropage_pte_entry() */ + fault = handle_mm_fault(vma, addr, + FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE, + NULL); + if (fault & VM_FAULT_OOM) + return -ENOMEM; + /* + * See break_ksm(): even after handle_mm_fault() returned 0, we + * must start the lookup from the current address, because + * handle_mm_fault() may back out if there's any difficulty. + * + * VM_FAULT_SIGBUS and VM_FAULT_SIGSEGV are unexpected but + * maybe they could trigger in the future on concurrent + * truncation. In that case, the shared zeropage would be gone + * and we can simply retry and make progress. + */ + cond_resched(); + goto retry; + } + + return 0; +} + +static int __s390_disable_cow_sharing(struct mm_struct *mm) { + int rc; + + if (!mm->context.allow_cow_sharing) + return 0; + + mm->context.allow_cow_sharing = 0; + + /* Replace all shared zeropages by anonymous pages. */ + rc = __s390_unshare_zeropages(mm); /* * Make sure to disable KSM (if enabled for the whole process or * individual VMAs). Note that nothing currently hinders user space * from re-enabling it. */ - return ksm_disable(current->mm); + if (!rc) + rc = ksm_disable(mm); + if (rc) + mm->context.allow_cow_sharing = 1; + return rc; } -EXPORT_SYMBOL_GPL(gmap_mark_unmergeable); + +/* + * Disable most COW-sharing of memory pages for the whole process: + * (1) Disable KSM and unmerge/unshare any KSM pages. + * (2) Disallow shared zeropages and unshare any zerpages that are mapped. + * + * Not that we currently don't bother with COW-shared pages that are shared + * with parent/child processes due to fork(). + */ +int s390_disable_cow_sharing(void) +{ + int rc; + + mmap_write_lock(current->mm); + rc = __s390_disable_cow_sharing(current->mm); + mmap_write_unlock(current->mm); + return rc; +} +EXPORT_SYMBOL_GPL(s390_disable_cow_sharing); /* * Enable storage key handling from now on and initialize the storage @@ -2646,7 +2744,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr, return 0; start = pmd_val(*pmd) & HPAGE_MASK; - end = start + HPAGE_SIZE - 1; + end = start + HPAGE_SIZE; __storage_key_init_range(start, end); set_bit(PG_arch_1, &page->flags); cond_resched(); @@ -2670,7 +2768,7 @@ int s390_enable_skey(void) goto out_up; mm->context.uses_skeys = 1; - rc = gmap_mark_unmergeable(); + rc = __s390_disable_cow_sharing(mm); if (rc) { mm->context.uses_skeys = 0; goto out_up; @@ -2855,7 +2953,7 @@ int s390_replace_asce(struct gmap *gmap) if ((gmap->asce & _ASCE_TYPE_MASK) == _ASCE_TYPE_SEGMENT) return -EINVAL; - page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + page = gmap_alloc_crst(); if (!page) return -ENOMEM; page->index = 0; diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 297a6d897d5a0c..763469e518eec8 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -139,7 +139,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste) } if (!test_and_set_bit(PG_arch_1, &page->flags)) - __storage_key_init_range(paddr, paddr + size - 1); + __storage_key_init_range(paddr, paddr + size); } void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, @@ -224,7 +224,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, if (p4d_present(*p4dp)) { pudp = pud_offset(p4dp, addr); if (pud_present(*pudp)) { - if (pud_large(*pudp)) + if (pud_leaf(*pudp)) return (pte_t *) pudp; pmdp = pmd_offset(pudp, addr); } @@ -240,7 +240,7 @@ int pmd_huge(pmd_t pmd) int pud_huge(pud_t pud) { - return pud_large(pud); + return pud_leaf(pud); } bool __init arch_hugetlb_valid_size(unsigned long size) diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c index 1e2ea706aa2289..79a037f49f7070 100644 --- a/arch/s390/mm/page-states.c +++ b/arch/s390/mm/page-states.c @@ -121,7 +121,7 @@ static void mark_kernel_pud(p4d_t *p4d, unsigned long addr, unsigned long end) continue; if (!pud_folded(*pud)) { page = phys_to_page(pud_val(*pud)); - for (i = 0; i < 3; i++) + for (i = 0; i < 4; i++) set_bit(PG_arch_1, &page[i].flags); } mark_kernel_pmd(pud, addr, next); @@ -142,7 +142,7 @@ static void mark_kernel_p4d(pgd_t *pgd, unsigned long addr, unsigned long end) continue; if (!p4d_folded(*p4d)) { page = phys_to_page(p4d_val(*p4d)); - for (i = 0; i < 3; i++) + for (i = 0; i < 4; i++) set_bit(PG_arch_1, &page[i].flags); } mark_kernel_pud(p4d, addr, next); @@ -164,7 +164,7 @@ static void mark_kernel_pgd(void) continue; if (!pgd_folded(*pgd)) { page = phys_to_page(pgd_val(*pgd)); - for (i = 0; i < 3; i++) + for (i = 0; i < 4; i++) set_bit(PG_arch_1, &page[i].flags); } mark_kernel_p4d(pgd, addr, next); @@ -181,6 +181,12 @@ void __init cmma_init_nodat(void) return; /* Mark pages used in kernel page tables */ mark_kernel_pgd(); + page = virt_to_page(&swapper_pg_dir); + for (i = 0; i < 4; i++) + set_bit(PG_arch_1, &page[i].flags); + page = virt_to_page(&invalid_pg_dir); + for (i = 0; i < 4; i++) + set_bit(PG_arch_1, &page[i].flags); /* Set all kernel pages not used for page tables to stable/no-dat */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) { diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index b87e96c64b61d2..441f654d048d20 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -274,7 +274,7 @@ static int walk_pud_level(p4d_t *p4d, unsigned long addr, unsigned long end, if (pud_none(*pudp)) return -EINVAL; next = pud_addr_end(addr, end); - if (pud_large(*pudp)) { + if (pud_leaf(*pudp)) { need_split = !!(flags & SET_MEMORY_4K); need_split |= !!(addr & ~PUD_MASK); need_split |= !!(addr + PUD_SIZE > next); diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 07fc660a24aa2f..9355fbe5f51e94 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -53,6 +53,8 @@ unsigned long *crst_table_alloc(struct mm_struct *mm) void crst_table_free(struct mm_struct *mm, unsigned long *table) { + if (!table) + return; pagetable_free(virt_to_ptdesc(table)); } @@ -146,6 +148,7 @@ struct page *page_table_alloc_pgste(struct mm_struct *mm) ptdesc = pagetable_alloc(GFP_KERNEL, 0); if (ptdesc) { table = (u64 *)ptdesc_to_virt(ptdesc); + arch_set_page_dat(virt_to_page(table), 0); memset64(table, _PAGE_INVALID, PTRS_PER_PTE); memset64(table + PTRS_PER_PTE, 0, PTRS_PER_PTE); } @@ -499,6 +502,8 @@ static unsigned long *base_crst_alloc(unsigned long val) static void base_crst_free(unsigned long *table) { + if (!table) + return; pagetable_free(virt_to_ptdesc(table)); } diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 3bd2ab2a9a3449..5e349869590a83 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -479,7 +479,7 @@ static int pmd_lookup(struct mm_struct *mm, unsigned long addr, pmd_t **pmdp) return -ENOENT; /* Large PUDs are not supported yet. */ - if (pud_large(*pud)) + if (pud_leaf(*pud)) return -EFAULT; *pmdp = pmd_offset(pud, addr); @@ -756,7 +756,7 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr, pte_clear(mm, addr, ptep); } if (reset) - pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK; + pgste_val(pgste) &= ~(_PGSTE_GPS_USAGE_MASK | _PGSTE_GPS_NODAT); pgste_set_unlock(ptep, pgste); preempt_enable(); } diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 6957d2ed97bf0e..2d3f65da56eeaa 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -45,8 +46,11 @@ void *vmem_crst_alloc(unsigned long val) unsigned long *table; table = vmem_alloc_pages(CRST_ALLOC_ORDER); - if (table) - crst_table_init(table, val); + if (!table) + return NULL; + crst_table_init(table, val); + if (slab_is_available()) + arch_set_page_dat(virt_to_page(table), CRST_ALLOC_ORDER); return table; } @@ -318,7 +322,7 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end, if (!add) { if (pud_none(*pud)) continue; - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { if (IS_ALIGNED(addr, PUD_SIZE) && IS_ALIGNED(next, PUD_SIZE)) { pud_clear(pud); @@ -339,7 +343,7 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end, if (!pmd) goto out; pud_populate(&init_mm, pud, pmd); - } else if (pud_large(*pud)) { + } else if (pud_leaf(*pud)) { continue; } ret = modify_pmd_table(pud, addr, next, add, direct); @@ -582,7 +586,7 @@ pte_t *vmem_get_alloc_pte(unsigned long addr, bool alloc) if (!pmd) goto out; pud_populate(&init_mm, pud, pmd); - } else if (WARN_ON_ONCE(pud_large(*pud))) { + } else if (WARN_ON_ONCE(pud_leaf(*pud))) { goto out; } pmd = pmd_offset(pud, addr); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index e507692e51e71e..62ee557d4b4996 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -516,11 +516,12 @@ static void bpf_skip(struct bpf_jit *jit, int size) * PLT for hotpatchable calls. The calling convention is the same as for the * ftrace hotpatch trampolines: %r0 is return address, %r1 is clobbered. */ -extern const char bpf_plt[]; -extern const char bpf_plt_ret[]; -extern const char bpf_plt_target[]; -extern const char bpf_plt_end[]; -#define BPF_PLT_SIZE 32 +struct bpf_plt { + char code[16]; + void *ret; + void *target; +} __packed; +extern const struct bpf_plt bpf_plt; asm( ".pushsection .rodata\n" " .balign 8\n" @@ -531,15 +532,14 @@ asm( " .balign 8\n" "bpf_plt_ret: .quad 0\n" "bpf_plt_target: .quad 0\n" - "bpf_plt_end:\n" " .popsection\n" ); -static void bpf_jit_plt(void *plt, void *ret, void *target) +static void bpf_jit_plt(struct bpf_plt *plt, void *ret, void *target) { - memcpy(plt, bpf_plt, BPF_PLT_SIZE); - *(void **)((char *)plt + (bpf_plt_ret - bpf_plt)) = ret; - *(void **)((char *)plt + (bpf_plt_target - bpf_plt)) = target ?: ret; + memcpy(plt, &bpf_plt, sizeof(*plt)); + plt->ret = ret; + plt->target = target; } /* @@ -662,9 +662,9 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) jit->prg = ALIGN(jit->prg, 8); jit->prologue_plt = jit->prg; if (jit->prg_buf) - bpf_jit_plt(jit->prg_buf + jit->prg, + bpf_jit_plt((struct bpf_plt *)(jit->prg_buf + jit->prg), jit->prg_buf + jit->prologue_plt_ret, NULL); - jit->prg += BPF_PLT_SIZE; + jit->prg += sizeof(struct bpf_plt); } static int get_probe_mem_regno(const u8 *insn) @@ -1311,8 +1311,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT6_DISP_LH(0xeb000000, is32 ? (op32) : (op64), \ (insn->imm & BPF_FETCH) ? src_reg : REG_W0, \ src_reg, dst_reg, off); \ - if (is32 && (insn->imm & BPF_FETCH)) \ - EMIT_ZERO(src_reg); \ + if (insn->imm & BPF_FETCH) { \ + /* bcr 14,0 - see atomic_fetch_{add,and,or,xor}() */ \ + _EMIT2(0x07e0); \ + if (is32) \ + EMIT_ZERO(src_reg); \ + } \ } while (0) case BPF_ADD: case BPF_ADD | BPF_FETCH: @@ -1901,9 +1905,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) struct bpf_jit jit; int pass; - if (WARN_ON_ONCE(bpf_plt_end - bpf_plt != BPF_PLT_SIZE)) - return orig_fp; - if (!fp->jit_requested) return orig_fp; @@ -2009,14 +2010,11 @@ bool bpf_jit_supports_far_kfunc_call(void) int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *old_addr, void *new_addr) { + struct bpf_plt expected_plt, current_plt, new_plt, *plt; struct { u16 opc; s32 disp; } __packed insn; - char expected_plt[BPF_PLT_SIZE]; - char current_plt[BPF_PLT_SIZE]; - char new_plt[BPF_PLT_SIZE]; - char *plt; char *ret; int err; @@ -2035,18 +2033,18 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, */ } else { /* Verify the PLT. */ - plt = (char *)ip + (insn.disp << 1); - err = copy_from_kernel_nofault(current_plt, plt, BPF_PLT_SIZE); + plt = ip + (insn.disp << 1); + err = copy_from_kernel_nofault(¤t_plt, plt, + sizeof(current_plt)); if (err < 0) return err; ret = (char *)ip + 6; - bpf_jit_plt(expected_plt, ret, old_addr); - if (memcmp(current_plt, expected_plt, BPF_PLT_SIZE)) + bpf_jit_plt(&expected_plt, ret, old_addr); + if (memcmp(¤t_plt, &expected_plt, sizeof(current_plt))) return -EINVAL; /* Adjust the call address. */ - bpf_jit_plt(new_plt, ret, new_addr); - s390_kernel_write(plt + (bpf_plt_target - bpf_plt), - new_plt + (bpf_plt_target - bpf_plt), + bpf_jit_plt(&new_plt, ret, new_addr); + s390_kernel_write(&plt->target, &new_plt.target, sizeof(void *)); } diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index d34d5813d00660..777362cb4ea80b 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -241,7 +241,7 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, /* combine single writes by using store-block insn */ void __iowrite64_copy(void __iomem *to, const void *from, size_t count) { - zpci_memcpy_toio(to, from, count); + zpci_memcpy_toio(to, from, count * 8); } void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index ff8f24854c6462..84482a92133220 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -268,33 +268,20 @@ static void zpci_floating_irq_handler(struct airq_struct *airq, } } -int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) +static int __alloc_airq(struct zpci_dev *zdev, int msi_vecs, + unsigned long *bit) { - struct zpci_dev *zdev = to_zpci(pdev); - unsigned int hwirq, msi_vecs, cpu; - unsigned long bit; - struct msi_desc *msi; - struct msi_msg msg; - int cpu_addr; - int rc, irq; - - zdev->aisb = -1UL; - zdev->msi_first_bit = -1U; - if (type == PCI_CAP_ID_MSI && nvec > 1) - return 1; - msi_vecs = min_t(unsigned int, nvec, zdev->max_msi); - if (irq_delivery == DIRECTED) { /* Allocate cpu vector bits */ - bit = airq_iv_alloc(zpci_ibv[0], msi_vecs); - if (bit == -1UL) + *bit = airq_iv_alloc(zpci_ibv[0], msi_vecs); + if (*bit == -1UL) return -EIO; } else { /* Allocate adapter summary indicator bit */ - bit = airq_iv_alloc_bit(zpci_sbv); - if (bit == -1UL) + *bit = airq_iv_alloc_bit(zpci_sbv); + if (*bit == -1UL) return -EIO; - zdev->aisb = bit; + zdev->aisb = *bit; /* Create adapter interrupt vector */ zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK, NULL); @@ -302,27 +289,66 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) return -ENOMEM; /* Wire up shortcut pointer */ - zpci_ibv[bit] = zdev->aibv; + zpci_ibv[*bit] = zdev->aibv; /* Each function has its own interrupt vector */ - bit = 0; + *bit = 0; } + return 0; +} - /* Request MSI interrupts */ +int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) +{ + unsigned int hwirq, msi_vecs, irqs_per_msi, i, cpu; + struct zpci_dev *zdev = to_zpci(pdev); + struct msi_desc *msi; + struct msi_msg msg; + unsigned long bit; + int cpu_addr; + int rc, irq; + + zdev->aisb = -1UL; + zdev->msi_first_bit = -1U; + + msi_vecs = min_t(unsigned int, nvec, zdev->max_msi); + if (msi_vecs < nvec) { + pr_info("%s requested %d irqs, allocate system limit of %d", + pci_name(pdev), nvec, zdev->max_msi); + } + + rc = __alloc_airq(zdev, msi_vecs, &bit); + if (rc < 0) + return rc; + + /* + * Request MSI interrupts: + * When using MSI, nvec_used interrupt sources and their irq + * descriptors are controlled through one msi descriptor. + * Thus the outer loop over msi descriptors shall run only once, + * while two inner loops iterate over the interrupt vectors. + * When using MSI-X, each interrupt vector/irq descriptor + * is bound to exactly one msi descriptor (nvec_used is one). + * So the inner loops are executed once, while the outer iterates + * over the MSI-X descriptors. + */ hwirq = bit; msi_for_each_desc(msi, &pdev->dev, MSI_DESC_NOTASSOCIATED) { - rc = -EIO; if (hwirq - bit >= msi_vecs) break; - irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE, - (irq_delivery == DIRECTED) ? - msi->affinity : NULL); + irqs_per_msi = min_t(unsigned int, msi_vecs, msi->nvec_used); + irq = __irq_alloc_descs(-1, 0, irqs_per_msi, 0, THIS_MODULE, + (irq_delivery == DIRECTED) ? + msi->affinity : NULL); if (irq < 0) return -ENOMEM; - rc = irq_set_msi_desc(irq, msi); - if (rc) - return rc; - irq_set_chip_and_handler(irq, &zpci_irq_chip, - handle_percpu_irq); + + for (i = 0; i < irqs_per_msi; i++) { + rc = irq_set_msi_desc_off(irq, i, msi); + if (rc) + return rc; + irq_set_chip_and_handler(irq + i, &zpci_irq_chip, + handle_percpu_irq); + } + msg.data = hwirq - bit; if (irq_delivery == DIRECTED) { if (msi->affinity) @@ -335,31 +361,35 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) msg.address_lo |= (cpu_addr << 8); for_each_possible_cpu(cpu) { - airq_iv_set_data(zpci_ibv[cpu], hwirq, irq); + for (i = 0; i < irqs_per_msi; i++) + airq_iv_set_data(zpci_ibv[cpu], + hwirq + i, irq + i); } } else { msg.address_lo = zdev->msi_addr & 0xffffffff; - airq_iv_set_data(zdev->aibv, hwirq, irq); + for (i = 0; i < irqs_per_msi; i++) + airq_iv_set_data(zdev->aibv, hwirq + i, irq + i); } msg.address_hi = zdev->msi_addr >> 32; pci_write_msi_msg(irq, &msg); - hwirq++; + hwirq += irqs_per_msi; } zdev->msi_first_bit = bit; - zdev->msi_nr_irqs = msi_vecs; + zdev->msi_nr_irqs = hwirq - bit; rc = zpci_set_irq(zdev); if (rc) return rc; - return (msi_vecs == nvec) ? 0 : msi_vecs; + return (zdev->msi_nr_irqs == nvec) ? 0 : zdev->msi_nr_irqs; } void arch_teardown_msi_irqs(struct pci_dev *pdev) { struct zpci_dev *zdev = to_zpci(pdev); struct msi_desc *msi; + unsigned int i; int rc; /* Disable interrupts */ @@ -369,8 +399,10 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) /* Release MSI interrupts */ msi_for_each_desc(msi, &pdev->dev, MSI_DESC_ASSOCIATED) { - irq_set_msi_desc(msi->irq, NULL); - irq_free_desc(msi->irq); + for (i = 0; i < msi->nvec_used; i++) { + irq_set_msi_desc(msi->irq + i, NULL); + irq_free_desc(msi->irq + i); + } msi->msg.address_lo = 0; msi->msg.address_hi = 0; msi->msg.data = 0; @@ -410,7 +442,7 @@ static void __init cpu_enable_directed_irq(void *unused) union zpci_sic_iib iib = {{0}}; union zpci_sic_iib ziib = {{0}}; - iib.cdiib.dibv_addr = (u64) zpci_ibv[smp_processor_id()]->vector; + iib.cdiib.dibv_addr = virt_to_phys(zpci_ibv[smp_processor_id()]->vector); zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib); zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC, &ziib); diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index 5880893329310d..a90499c087f0c5 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -97,9 +97,9 @@ static inline int __memcpy_toio_inuser(void __iomem *dst, return -EINVAL; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) dst, - (u64 __force) src, n, - ZPCI_MAX_WRITE_SIZE); + size = zpci_get_max_io_size((u64 __force) dst, + (u64 __force) src, n, + ZPCI_MAX_WRITE_SIZE); if (size > 8) /* main path */ rc = __pcistb_mio_inuser(dst, src, size, &status); else @@ -242,9 +242,9 @@ static inline int __memcpy_fromio_inuser(void __user *dst, u8 status; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) src, - (u64 __force) dst, n, - ZPCI_MAX_READ_SIZE); + size = zpci_get_max_io_size((u64 __force) src, + (u64 __force) dst, n, + ZPCI_MAX_READ_SIZE); rc = __pcilg_mio_inuser(dst, src, size, &status); if (rc) break; diff --git a/arch/sh/Kconfig.debug b/arch/sh/Kconfig.debug index c449e7c1b20ff5..8bcd6c1431a95b 100644 --- a/arch/sh/Kconfig.debug +++ b/arch/sh/Kconfig.debug @@ -22,6 +22,17 @@ config STACK_DEBUG every function call and will therefore incur a major performance hit. Most users should say N. +config EARLY_PRINTK + bool "Early printk" + depends on SH_STANDARD_BIOS + help + Say Y here to redirect kernel printk messages to the serial port + used by the SH-IPL bootloader, starting very early in the boot + process and ending when the kernel's serial console is initialised. + This option is only useful while porting the kernel to a new machine, + when the kernel may crash or hang before the serial console is + initialised. If unsure, say N. + config 4KSTACKS bool "Use 4Kb for kernel stacks instead of 8Kb" depends on DEBUG_KERNEL && (MMU || BROKEN) && !PAGE_SIZE_64KB diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index 3be293335de545..7a788d44cc7349 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -1220,7 +1220,7 @@ static int __init arch_setup(void) lcdc_info.ch[0].num_modes = ARRAY_SIZE(ecovec_dvi_modes); /* No backlight */ - gpio_backlight_data.fbdev = NULL; + gpio_backlight_data.dev = NULL; gpio_set_value(GPIO_PTA2, 1); gpio_set_value(GPIO_PTU1, 1); diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index 878b6b551bd2d0..51112f54552b32 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -90,6 +90,7 @@ extern void copy_from_user_page(struct vm_area_struct *vma, unsigned long len); #define flush_cache_vmap(start, end) local_flush_cache_all(NULL) +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) local_flush_cache_all(NULL) #define flush_dcache_mmap_lock(mapping) do { } while (0) diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index aed1ea8e2c2f06..74051b8ddf3e7b 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -44,17 +44,12 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) if (OPCODE_RTE(opcode)) return -EFAULT; /* Bad breakpoint */ + memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); p->opcode = opcode; return 0; } -void __kprobes arch_copy_kprobe(struct kprobe *p) -{ - memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); - p->opcode = *p->addr; -} - void __kprobes arch_arm_kprobe(struct kprobe *p) { *p->addr = BREAKPOINT_INSTRUCTION; diff --git a/arch/sh/kernel/sys_sh32.c b/arch/sh/kernel/sys_sh32.c index 9dca568509a5e5..d6f4afcb0e8705 100644 --- a/arch/sh/kernel/sys_sh32.c +++ b/arch/sh/kernel/sys_sh32.c @@ -59,3 +59,14 @@ asmlinkage int sys_fadvise64_64_wrapper(int fd, u32 offset0, u32 offset1, (u64)len0 << 32 | len1, advice); #endif } + +/* + * swap the arguments the way that libc wants them instead of + * moving flags ahead of the 64-bit nbytes argument + */ +SYSCALL_DEFINE6(sh_sync_file_range6, int, fd, SC_ARG64(offset), + SC_ARG64(nbytes), unsigned int, flags) +{ + return ksys_sync_file_range(fd, SC_VAL64(loff_t, offset), + SC_VAL64(loff_t, nbytes), flags); +} diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index e90d585c4d3e73..7e1ceb2ba57211 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -321,7 +321,7 @@ 311 common set_robust_list sys_set_robust_list 312 common get_robust_list sys_get_robust_list 313 common splice sys_splice -314 common sync_file_range sys_sync_file_range +314 common sync_file_range sys_sh_sync_file_range6 315 common tee sys_tee 316 common vmsplice sys_vmsplice 317 common move_pages sys_move_pages @@ -395,6 +395,7 @@ 385 common pkey_alloc sys_pkey_alloc 386 common pkey_free sys_pkey_free 387 common rseq sys_rseq +388 common sync_file_range2 sys_sync_file_range2 # room for arch specific syscalls 393 common semget sys_semget 394 common semctl sys_semctl diff --git a/arch/sh/lib/checksum.S b/arch/sh/lib/checksum.S index 3e07074e009813..06fed5a21e8baa 100644 --- a/arch/sh/lib/checksum.S +++ b/arch/sh/lib/checksum.S @@ -33,7 +33,8 @@ */ /* - * asmlinkage __wsum csum_partial(const void *buf, int len, __wsum sum); + * unsigned int csum_partial(const unsigned char *buf, int len, + * unsigned int sum); */ .text @@ -45,31 +46,11 @@ ENTRY(csum_partial) * Fortunately, it is easy to convert 2-byte alignment to 4-byte * alignment for the unrolled loop. */ + mov r5, r1 mov r4, r0 - tst #3, r0 ! Check alignment. - bt/s 2f ! Jump if alignment is ok. - mov r4, r7 ! Keep a copy to check for alignment + tst #2, r0 ! Check alignment. + bt 2f ! Jump if alignment is ok. ! - tst #1, r0 ! Check alignment. - bt 21f ! Jump if alignment is boundary of 2bytes. - - ! buf is odd - tst r5, r5 - add #-1, r5 - bt 9f - mov.b @r4+, r0 - extu.b r0, r0 - addc r0, r6 ! t=0 from previous tst - mov r6, r0 - shll8 r6 - shlr16 r0 - shlr8 r0 - or r0, r6 - mov r4, r0 - tst #2, r0 - bt 2f -21: - ! buf is 2 byte aligned (len could be 0) add #-2, r5 ! Alignment uses up two bytes. cmp/pz r5 ! bt/s 1f ! Jump if we had at least two bytes. @@ -77,17 +58,16 @@ ENTRY(csum_partial) bra 6f add #2, r5 ! r5 was < 2. Deal with it. 1: + mov r5, r1 ! Save new len for later use. mov.w @r4+, r0 extu.w r0, r0 addc r0, r6 bf 2f add #1, r6 2: - ! buf is 4 byte aligned (len could be 0) - mov r5, r1 mov #-5, r0 - shld r0, r1 - tst r1, r1 + shld r0, r5 + tst r5, r5 bt/s 4f ! if it's =0, go to 4f clrt .align 2 @@ -109,31 +89,30 @@ ENTRY(csum_partial) addc r0, r6 addc r2, r6 movt r0 - dt r1 + dt r5 bf/s 3b cmp/eq #1, r0 - ! here, we know r1==0 - addc r1, r6 ! add carry to r6 + ! here, we know r5==0 + addc r5, r6 ! add carry to r6 4: - mov r5, r0 + mov r1, r0 and #0x1c, r0 tst r0, r0 - bt 6f - ! 4 bytes or more remaining - mov r0, r1 - shlr2 r1 + bt/s 6f + mov r0, r5 + shlr2 r5 mov #0, r2 5: addc r2, r6 mov.l @r4+, r2 movt r0 - dt r1 + dt r5 bf/s 5b cmp/eq #1, r0 addc r2, r6 - addc r1, r6 ! r1==0 here, so it means add carry-bit + addc r5, r6 ! r5==0 here, so it means add carry-bit 6: - ! 3 bytes or less remaining + mov r1, r5 mov #3, r0 and r0, r5 tst r5, r5 @@ -159,16 +138,6 @@ ENTRY(csum_partial) mov #0, r0 addc r0, r6 9: - ! Check if the buffer was misaligned, if so realign sum - mov r7, r0 - tst #1, r0 - bt 10f - mov r6, r0 - shll8 r6 - shlr16 r0 - shlr8 r0 - or r0, r6 -10: rts mov r6, r0 diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile index 7417345c6639a3..2a03daa68f2857 100644 --- a/arch/sparc/Makefile +++ b/arch/sparc/Makefile @@ -60,7 +60,7 @@ libs-y += arch/sparc/prom/ libs-y += arch/sparc/lib/ drivers-$(CONFIG_PM) += arch/sparc/power/ -drivers-$(CONFIG_FB) += arch/sparc/video/ +drivers-$(CONFIG_FB_CORE) += arch/sparc/video/ boot := arch/sparc/boot @@ -76,9 +76,8 @@ install: archheaders: $(Q)$(MAKE) $(build)=arch/sparc/kernel/syscalls all -PHONY += vdso_install -vdso_install: - $(Q)$(MAKE) $(build)=arch/sparc/vdso $@ +vdso-install-$(CONFIG_SPARC64) += arch/sparc/vdso/vdso64.so.dbg +vdso-install-$(CONFIG_COMPAT) += arch/sparc/vdso/vdso32.so.dbg # This is the image used for packaging KBUILD_IMAGE := $(boot)/zImage diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h index f3b7270bf71b26..9fee0ccfccb8e1 100644 --- a/arch/sparc/include/asm/cacheflush_32.h +++ b/arch/sparc/include/asm/cacheflush_32.h @@ -48,6 +48,7 @@ static inline void flush_dcache_page(struct page *page) #define flush_dcache_mmap_unlock(mapping) do { } while (0) #define flush_cache_vmap(start, end) flush_cache_all() +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) flush_cache_all() /* When a context switch happens we must flush all user windows so that diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h index 0e879004efff16..2b1261b77ecd1b 100644 --- a/arch/sparc/include/asm/cacheflush_64.h +++ b/arch/sparc/include/asm/cacheflush_64.h @@ -75,6 +75,7 @@ void flush_ptrace_access(struct vm_area_struct *, struct page *, #define flush_dcache_mmap_unlock(mapping) do { } while (0) #define flush_cache_vmap(start, end) do { } while (0) +#define flush_cache_vmap_early(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) #endif /* !__ASSEMBLY__ */ diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h index 94eb529dcb7762..2718cbea826a7d 100644 --- a/arch/sparc/include/asm/jump_label.h +++ b/arch/sparc/include/asm/jump_label.h @@ -10,7 +10,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" @@ -26,7 +26,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b %l[l_yes]\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h index a67abebd43592f..1b86d02a84556a 100644 --- a/arch/sparc/include/asm/oplib_64.h +++ b/arch/sparc/include/asm/oplib_64.h @@ -247,6 +247,7 @@ void prom_sun4v_guest_soft_state(void); int prom_ihandle2path(int handle, char *buffer, int bufsize); /* Client interface level routines. */ +void prom_cif_init(void *cif_handler); void p1275_cmd_direct(unsigned long *); #endif /* !(__SPARC64_OPLIB_H) */ diff --git a/arch/sparc/include/asm/parport.h b/arch/sparc/include/asm/parport.h index 0a7ffcfd59cda0..e2eed8f97665fb 100644 --- a/arch/sparc/include/asm/parport.h +++ b/arch/sparc/include/asm/parport.h @@ -1,256 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* parport.h: sparc64 specific parport initialization and dma. - * - * Copyright (C) 1999 Eddie C. Dost (ecd@skynet.be) - */ +#ifndef ___ASM_SPARC_PARPORT_H +#define ___ASM_SPARC_PARPORT_H -#ifndef _ASM_SPARC64_PARPORT_H -#define _ASM_SPARC64_PARPORT_H 1 - -#include -#include - -#include -#include -#include - -#define PARPORT_PC_MAX_PORTS PARPORT_MAX - -/* - * While sparc64 doesn't have an ISA DMA API, we provide something that looks - * close enough to make parport_pc happy - */ -#define HAS_DMA - -#ifdef CONFIG_PARPORT_PC_FIFO -static DEFINE_SPINLOCK(dma_spin_lock); - -#define claim_dma_lock() \ -({ unsigned long flags; \ - spin_lock_irqsave(&dma_spin_lock, flags); \ - flags; \ -}) - -#define release_dma_lock(__flags) \ - spin_unlock_irqrestore(&dma_spin_lock, __flags); +#if defined(__sparc__) && defined(__arch64__) +#include +#else +#include +#endif #endif -static struct sparc_ebus_info { - struct ebus_dma_info info; - unsigned int addr; - unsigned int count; - int lock; - - struct parport *port; -} sparc_ebus_dmas[PARPORT_PC_MAX_PORTS]; - -static DECLARE_BITMAP(dma_slot_map, PARPORT_PC_MAX_PORTS); - -static inline int request_dma(unsigned int dmanr, const char *device_id) -{ - if (dmanr >= PARPORT_PC_MAX_PORTS) - return -EINVAL; - if (xchg(&sparc_ebus_dmas[dmanr].lock, 1) != 0) - return -EBUSY; - return 0; -} - -static inline void free_dma(unsigned int dmanr) -{ - if (dmanr >= PARPORT_PC_MAX_PORTS) { - printk(KERN_WARNING "Trying to free DMA%d\n", dmanr); - return; - } - if (xchg(&sparc_ebus_dmas[dmanr].lock, 0) == 0) { - printk(KERN_WARNING "Trying to free free DMA%d\n", dmanr); - return; - } -} - -static inline void enable_dma(unsigned int dmanr) -{ - ebus_dma_enable(&sparc_ebus_dmas[dmanr].info, 1); - - if (ebus_dma_request(&sparc_ebus_dmas[dmanr].info, - sparc_ebus_dmas[dmanr].addr, - sparc_ebus_dmas[dmanr].count)) - BUG(); -} - -static inline void disable_dma(unsigned int dmanr) -{ - ebus_dma_enable(&sparc_ebus_dmas[dmanr].info, 0); -} - -static inline void clear_dma_ff(unsigned int dmanr) -{ - /* nothing */ -} - -static inline void set_dma_mode(unsigned int dmanr, char mode) -{ - ebus_dma_prepare(&sparc_ebus_dmas[dmanr].info, (mode != DMA_MODE_WRITE)); -} - -static inline void set_dma_addr(unsigned int dmanr, unsigned int addr) -{ - sparc_ebus_dmas[dmanr].addr = addr; -} - -static inline void set_dma_count(unsigned int dmanr, unsigned int count) -{ - sparc_ebus_dmas[dmanr].count = count; -} - -static inline unsigned int get_dma_residue(unsigned int dmanr) -{ - return ebus_dma_residue(&sparc_ebus_dmas[dmanr].info); -} - -static int ecpp_probe(struct platform_device *op) -{ - unsigned long base = op->resource[0].start; - unsigned long config = op->resource[1].start; - unsigned long d_base = op->resource[2].start; - unsigned long d_len; - struct device_node *parent; - struct parport *p; - int slot, err; - - parent = op->dev.of_node->parent; - if (of_node_name_eq(parent, "dma")) { - p = parport_pc_probe_port(base, base + 0x400, - op->archdata.irqs[0], PARPORT_DMA_NOFIFO, - op->dev.parent->parent, 0); - if (!p) - return -ENOMEM; - dev_set_drvdata(&op->dev, p); - return 0; - } - - for (slot = 0; slot < PARPORT_PC_MAX_PORTS; slot++) { - if (!test_and_set_bit(slot, dma_slot_map)) - break; - } - err = -ENODEV; - if (slot >= PARPORT_PC_MAX_PORTS) - goto out_err; - - spin_lock_init(&sparc_ebus_dmas[slot].info.lock); - - d_len = (op->resource[2].end - d_base) + 1UL; - sparc_ebus_dmas[slot].info.regs = - of_ioremap(&op->resource[2], 0, d_len, "ECPP DMA"); - - if (!sparc_ebus_dmas[slot].info.regs) - goto out_clear_map; - - sparc_ebus_dmas[slot].info.flags = 0; - sparc_ebus_dmas[slot].info.callback = NULL; - sparc_ebus_dmas[slot].info.client_cookie = NULL; - sparc_ebus_dmas[slot].info.irq = 0xdeadbeef; - strcpy(sparc_ebus_dmas[slot].info.name, "parport"); - if (ebus_dma_register(&sparc_ebus_dmas[slot].info)) - goto out_unmap_regs; - - ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 1); - - /* Configure IRQ to Push Pull, Level Low */ - /* Enable ECP, set bit 2 of the CTR first */ - outb(0x04, base + 0x02); - ns87303_modify(config, PCR, - PCR_EPP_ENABLE | - PCR_IRQ_ODRAIN, - PCR_ECP_ENABLE | - PCR_ECP_CLK_ENA | - PCR_IRQ_POLAR); - - /* CTR bit 5 controls direction of port */ - ns87303_modify(config, PTR, - 0, PTR_LPT_REG_DIR); - - p = parport_pc_probe_port(base, base + 0x400, - op->archdata.irqs[0], - slot, - op->dev.parent, - 0); - err = -ENOMEM; - if (!p) - goto out_disable_irq; - - dev_set_drvdata(&op->dev, p); - - return 0; - -out_disable_irq: - ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 0); - ebus_dma_unregister(&sparc_ebus_dmas[slot].info); - -out_unmap_regs: - of_iounmap(&op->resource[2], sparc_ebus_dmas[slot].info.regs, d_len); - -out_clear_map: - clear_bit(slot, dma_slot_map); - -out_err: - return err; -} - -static int ecpp_remove(struct platform_device *op) -{ - struct parport *p = dev_get_drvdata(&op->dev); - int slot = p->dma; - - parport_pc_unregister_port(p); - - if (slot != PARPORT_DMA_NOFIFO) { - unsigned long d_base = op->resource[2].start; - unsigned long d_len; - - d_len = (op->resource[2].end - d_base) + 1UL; - - ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 0); - ebus_dma_unregister(&sparc_ebus_dmas[slot].info); - of_iounmap(&op->resource[2], - sparc_ebus_dmas[slot].info.regs, - d_len); - clear_bit(slot, dma_slot_map); - } - - return 0; -} - -static const struct of_device_id ecpp_match[] = { - { - .name = "ecpp", - }, - { - .name = "parallel", - .compatible = "ecpp", - }, - { - .name = "parallel", - .compatible = "ns87317-ecpp", - }, - { - .name = "parallel", - .compatible = "pnpALI,1533,3", - }, - {}, -}; - -static struct platform_driver ecpp_driver = { - .driver = { - .name = "ecpp", - .of_match_table = ecpp_match, - }, - .probe = ecpp_probe, - .remove = ecpp_remove, -}; - -static int parport_pc_find_nonpci_ports(int autoirq, int autodma) -{ - return platform_driver_register(&ecpp_driver); -} - -#endif /* !(_ASM_SPARC64_PARPORT_H */ diff --git a/arch/sparc/include/asm/parport_64.h b/arch/sparc/include/asm/parport_64.h new file mode 100644 index 00000000000000..0a7ffcfd59cda0 --- /dev/null +++ b/arch/sparc/include/asm/parport_64.h @@ -0,0 +1,256 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* parport.h: sparc64 specific parport initialization and dma. + * + * Copyright (C) 1999 Eddie C. Dost (ecd@skynet.be) + */ + +#ifndef _ASM_SPARC64_PARPORT_H +#define _ASM_SPARC64_PARPORT_H 1 + +#include +#include + +#include +#include +#include + +#define PARPORT_PC_MAX_PORTS PARPORT_MAX + +/* + * While sparc64 doesn't have an ISA DMA API, we provide something that looks + * close enough to make parport_pc happy + */ +#define HAS_DMA + +#ifdef CONFIG_PARPORT_PC_FIFO +static DEFINE_SPINLOCK(dma_spin_lock); + +#define claim_dma_lock() \ +({ unsigned long flags; \ + spin_lock_irqsave(&dma_spin_lock, flags); \ + flags; \ +}) + +#define release_dma_lock(__flags) \ + spin_unlock_irqrestore(&dma_spin_lock, __flags); +#endif + +static struct sparc_ebus_info { + struct ebus_dma_info info; + unsigned int addr; + unsigned int count; + int lock; + + struct parport *port; +} sparc_ebus_dmas[PARPORT_PC_MAX_PORTS]; + +static DECLARE_BITMAP(dma_slot_map, PARPORT_PC_MAX_PORTS); + +static inline int request_dma(unsigned int dmanr, const char *device_id) +{ + if (dmanr >= PARPORT_PC_MAX_PORTS) + return -EINVAL; + if (xchg(&sparc_ebus_dmas[dmanr].lock, 1) != 0) + return -EBUSY; + return 0; +} + +static inline void free_dma(unsigned int dmanr) +{ + if (dmanr >= PARPORT_PC_MAX_PORTS) { + printk(KERN_WARNING "Trying to free DMA%d\n", dmanr); + return; + } + if (xchg(&sparc_ebus_dmas[dmanr].lock, 0) == 0) { + printk(KERN_WARNING "Trying to free free DMA%d\n", dmanr); + return; + } +} + +static inline void enable_dma(unsigned int dmanr) +{ + ebus_dma_enable(&sparc_ebus_dmas[dmanr].info, 1); + + if (ebus_dma_request(&sparc_ebus_dmas[dmanr].info, + sparc_ebus_dmas[dmanr].addr, + sparc_ebus_dmas[dmanr].count)) + BUG(); +} + +static inline void disable_dma(unsigned int dmanr) +{ + ebus_dma_enable(&sparc_ebus_dmas[dmanr].info, 0); +} + +static inline void clear_dma_ff(unsigned int dmanr) +{ + /* nothing */ +} + +static inline void set_dma_mode(unsigned int dmanr, char mode) +{ + ebus_dma_prepare(&sparc_ebus_dmas[dmanr].info, (mode != DMA_MODE_WRITE)); +} + +static inline void set_dma_addr(unsigned int dmanr, unsigned int addr) +{ + sparc_ebus_dmas[dmanr].addr = addr; +} + +static inline void set_dma_count(unsigned int dmanr, unsigned int count) +{ + sparc_ebus_dmas[dmanr].count = count; +} + +static inline unsigned int get_dma_residue(unsigned int dmanr) +{ + return ebus_dma_residue(&sparc_ebus_dmas[dmanr].info); +} + +static int ecpp_probe(struct platform_device *op) +{ + unsigned long base = op->resource[0].start; + unsigned long config = op->resource[1].start; + unsigned long d_base = op->resource[2].start; + unsigned long d_len; + struct device_node *parent; + struct parport *p; + int slot, err; + + parent = op->dev.of_node->parent; + if (of_node_name_eq(parent, "dma")) { + p = parport_pc_probe_port(base, base + 0x400, + op->archdata.irqs[0], PARPORT_DMA_NOFIFO, + op->dev.parent->parent, 0); + if (!p) + return -ENOMEM; + dev_set_drvdata(&op->dev, p); + return 0; + } + + for (slot = 0; slot < PARPORT_PC_MAX_PORTS; slot++) { + if (!test_and_set_bit(slot, dma_slot_map)) + break; + } + err = -ENODEV; + if (slot >= PARPORT_PC_MAX_PORTS) + goto out_err; + + spin_lock_init(&sparc_ebus_dmas[slot].info.lock); + + d_len = (op->resource[2].end - d_base) + 1UL; + sparc_ebus_dmas[slot].info.regs = + of_ioremap(&op->resource[2], 0, d_len, "ECPP DMA"); + + if (!sparc_ebus_dmas[slot].info.regs) + goto out_clear_map; + + sparc_ebus_dmas[slot].info.flags = 0; + sparc_ebus_dmas[slot].info.callback = NULL; + sparc_ebus_dmas[slot].info.client_cookie = NULL; + sparc_ebus_dmas[slot].info.irq = 0xdeadbeef; + strcpy(sparc_ebus_dmas[slot].info.name, "parport"); + if (ebus_dma_register(&sparc_ebus_dmas[slot].info)) + goto out_unmap_regs; + + ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 1); + + /* Configure IRQ to Push Pull, Level Low */ + /* Enable ECP, set bit 2 of the CTR first */ + outb(0x04, base + 0x02); + ns87303_modify(config, PCR, + PCR_EPP_ENABLE | + PCR_IRQ_ODRAIN, + PCR_ECP_ENABLE | + PCR_ECP_CLK_ENA | + PCR_IRQ_POLAR); + + /* CTR bit 5 controls direction of port */ + ns87303_modify(config, PTR, + 0, PTR_LPT_REG_DIR); + + p = parport_pc_probe_port(base, base + 0x400, + op->archdata.irqs[0], + slot, + op->dev.parent, + 0); + err = -ENOMEM; + if (!p) + goto out_disable_irq; + + dev_set_drvdata(&op->dev, p); + + return 0; + +out_disable_irq: + ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 0); + ebus_dma_unregister(&sparc_ebus_dmas[slot].info); + +out_unmap_regs: + of_iounmap(&op->resource[2], sparc_ebus_dmas[slot].info.regs, d_len); + +out_clear_map: + clear_bit(slot, dma_slot_map); + +out_err: + return err; +} + +static int ecpp_remove(struct platform_device *op) +{ + struct parport *p = dev_get_drvdata(&op->dev); + int slot = p->dma; + + parport_pc_unregister_port(p); + + if (slot != PARPORT_DMA_NOFIFO) { + unsigned long d_base = op->resource[2].start; + unsigned long d_len; + + d_len = (op->resource[2].end - d_base) + 1UL; + + ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 0); + ebus_dma_unregister(&sparc_ebus_dmas[slot].info); + of_iounmap(&op->resource[2], + sparc_ebus_dmas[slot].info.regs, + d_len); + clear_bit(slot, dma_slot_map); + } + + return 0; +} + +static const struct of_device_id ecpp_match[] = { + { + .name = "ecpp", + }, + { + .name = "parallel", + .compatible = "ecpp", + }, + { + .name = "parallel", + .compatible = "ns87317-ecpp", + }, + { + .name = "parallel", + .compatible = "pnpALI,1533,3", + }, + {}, +}; + +static struct platform_driver ecpp_driver = { + .driver = { + .name = "ecpp", + .of_match_table = ecpp_match, + }, + .probe = ecpp_probe, + .remove = ecpp_remove, +}; + +static int parport_pc_find_nonpci_ports(int autoirq, int autodma) +{ + return platform_driver_register(&ecpp_driver); +} + +#endif /* !(_ASM_SPARC64_PARPORT_H */ diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h index 505b6700805dd6..0964fede0b2cc6 100644 --- a/arch/sparc/include/asm/smp_64.h +++ b/arch/sparc/include/asm/smp_64.h @@ -47,7 +47,6 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask); int hard_smp_processor_id(void); #define raw_smp_processor_id() (current_thread_info()->cpu) -void smp_fill_in_cpu_possible_map(void); void smp_fill_in_sib_core_maps(void); void __noreturn cpu_play_dead(void); @@ -77,7 +76,6 @@ void __cpu_die(unsigned int cpu); #define smp_fill_in_sib_core_maps() do { } while (0) #define smp_fetch_global_regs() do { } while (0) #define smp_fetch_global_pmu() do { } while (0) -#define smp_fill_in_cpu_possible_map() do { } while (0) #define smp_init_cpu_poke() do { } while (0) #define scheduler_poke() do { } while (0) diff --git a/arch/sparc/include/uapi/asm/termbits.h b/arch/sparc/include/uapi/asm/termbits.h index 4321322701fcfd..0da2b1adc0f526 100644 --- a/arch/sparc/include/uapi/asm/termbits.h +++ b/arch/sparc/include/uapi/asm/termbits.h @@ -10,16 +10,6 @@ typedef unsigned int tcflag_t; typedef unsigned long tcflag_t; #endif -#define NCC 8 -struct termio { - unsigned short c_iflag; /* input mode flags */ - unsigned short c_oflag; /* output mode flags */ - unsigned short c_cflag; /* control mode flags */ - unsigned short c_lflag; /* local mode flags */ - unsigned char c_line; /* line discipline */ - unsigned char c_cc[NCC]; /* control characters */ -}; - #define NCCS 17 struct termios { tcflag_t c_iflag; /* input mode flags */ diff --git a/arch/sparc/include/uapi/asm/termios.h b/arch/sparc/include/uapi/asm/termios.h index ee86f4093d83e9..cceb32260881e7 100644 --- a/arch/sparc/include/uapi/asm/termios.h +++ b/arch/sparc/include/uapi/asm/termios.h @@ -40,5 +40,14 @@ struct winsize { unsigned short ws_ypixel; }; +#define NCC 8 +struct termio { + unsigned short c_iflag; /* input mode flags */ + unsigned short c_oflag; /* output mode flags */ + unsigned short c_cflag; /* control mode flags */ + unsigned short c_lflag; /* local mode flags */ + unsigned char c_line; /* line discipline */ + unsigned char c_cc[NCC]; /* control characters */ +}; #endif /* _UAPI_SPARC_TERMIOS_H */ diff --git a/arch/sparc/kernel/leon_pci_grpci1.c b/arch/sparc/kernel/leon_pci_grpci1.c index 8700a0e3b0df7d..b2b639bee06848 100644 --- a/arch/sparc/kernel/leon_pci_grpci1.c +++ b/arch/sparc/kernel/leon_pci_grpci1.c @@ -697,7 +697,7 @@ static int grpci1_of_probe(struct platform_device *ofdev) return err; } -static const struct of_device_id grpci1_of_match[] __initconst = { +static const struct of_device_id grpci1_of_match[] = { { .name = "GAISLER_PCIFBRG", }, diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c index 60b6bdf7761fb3..ac2acd62a24ece 100644 --- a/arch/sparc/kernel/leon_pci_grpci2.c +++ b/arch/sparc/kernel/leon_pci_grpci2.c @@ -889,7 +889,7 @@ static int grpci2_of_probe(struct platform_device *ofdev) return err; } -static const struct of_device_id grpci2_of_match[] __initconst = { +static const struct of_device_id grpci2_of_match[] = { { .name = "GAISLER_GRPCI2", }, diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 17cdfdbf1f3b78..149adc09475306 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -279,7 +279,7 @@ static int __init setup_nmi_watchdog(char *str) if (!strncmp(str, "panic", 5)) panic_on_timeout = 1; - return 0; + return 1; } __setup("nmi_watchdog=", setup_nmi_watchdog); diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c index 998aa693d49125..ba82884cb92aa3 100644 --- a/arch/sparc/kernel/prom_64.c +++ b/arch/sparc/kernel/prom_64.c @@ -483,7 +483,9 @@ static void *record_one_cpu(struct device_node *dp, int cpuid, int arg) ncpus_probed++; #ifdef CONFIG_SMP set_cpu_present(cpuid, true); - set_cpu_possible(cpuid, true); + + if (num_possible_cpus() < nr_cpu_ids) + set_cpu_possible(cpuid, true); #endif return NULL; } diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 6546ca9d4d3f1f..bda81f314bc257 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -684,7 +684,6 @@ void __init setup_arch(char **cmdline_p) paging_init(); init_sparc64_elf_hwcap(); - smp_fill_in_cpu_possible_map(); /* * Once the OF device tree and MDESC have been setup and nr_cpus has * been parsed, we know the list of possible cpus. Therefore we can diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index f3969a3600dbfe..e50c38eba2b876 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1220,20 +1220,6 @@ void __init smp_setup_processor_id(void) xcall_deliver_impl = hypervisor_xcall_deliver; } -void __init smp_fill_in_cpu_possible_map(void) -{ - int possible_cpus = num_possible_cpus(); - int i; - - if (possible_cpus > nr_cpu_ids) - possible_cpus = nr_cpu_ids; - - for (i = 0; i < possible_cpus; i++) - set_cpu_possible(i, true); - for (; i < NR_CPUS; i++) - set_cpu_possible(i, false); -} - void smp_fill_in_sib_core_maps(void) { unsigned int i; diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S index a45f0f31fe51ab..a3d308f2043e5f 100644 --- a/arch/sparc/kernel/sys32.S +++ b/arch/sparc/kernel/sys32.S @@ -18,224 +18,3 @@ sys32_mmap2: sethi %hi(sys_mmap), %g1 jmpl %g1 + %lo(sys_mmap), %g0 sllx %o5, 12, %o5 - - .align 32 - .globl sys32_socketcall -sys32_socketcall: /* %o0=call, %o1=args */ - cmp %o0, 1 - bl,pn %xcc, do_einval - cmp %o0, 18 - bg,pn %xcc, do_einval - sub %o0, 1, %o0 - sllx %o0, 5, %o0 - sethi %hi(__socketcall_table_begin), %g2 - or %g2, %lo(__socketcall_table_begin), %g2 - jmpl %g2 + %o0, %g0 - nop -do_einval: - retl - mov -EINVAL, %o0 - - .align 32 -__socketcall_table_begin: - - /* Each entry is exactly 32 bytes. */ -do_sys_socket: /* sys_socket(int, int, int) */ -1: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_socket), %g1 -2: ldswa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(sys_socket), %g0 -3: ldswa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_bind: /* sys_bind(int fd, struct sockaddr *, int) */ -4: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_bind), %g1 -5: ldswa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(sys_bind), %g0 -6: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_connect: /* sys_connect(int, struct sockaddr *, int) */ -7: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_connect), %g1 -8: ldswa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(sys_connect), %g0 -9: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_listen: /* sys_listen(int, int) */ -10: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_listen), %g1 - jmpl %g1 + %lo(sys_listen), %g0 -11: ldswa [%o1 + 0x4] %asi, %o1 - nop - nop - nop - nop -do_sys_accept: /* sys_accept(int, struct sockaddr *, int *) */ -12: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_accept), %g1 -13: lduwa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(sys_accept), %g0 -14: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_getsockname: /* sys_getsockname(int, struct sockaddr *, int *) */ -15: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_getsockname), %g1 -16: lduwa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(sys_getsockname), %g0 -17: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_getpeername: /* sys_getpeername(int, struct sockaddr *, int *) */ -18: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_getpeername), %g1 -19: lduwa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(sys_getpeername), %g0 -20: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_socketpair: /* sys_socketpair(int, int, int, int *) */ -21: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_socketpair), %g1 -22: ldswa [%o1 + 0x8] %asi, %o2 -23: lduwa [%o1 + 0xc] %asi, %o3 - jmpl %g1 + %lo(sys_socketpair), %g0 -24: ldswa [%o1 + 0x4] %asi, %o1 - nop - nop -do_sys_send: /* sys_send(int, void *, size_t, unsigned int) */ -25: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_send), %g1 -26: lduwa [%o1 + 0x8] %asi, %o2 -27: lduwa [%o1 + 0xc] %asi, %o3 - jmpl %g1 + %lo(sys_send), %g0 -28: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop -do_sys_recv: /* sys_recv(int, void *, size_t, unsigned int) */ -29: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_recv), %g1 -30: lduwa [%o1 + 0x8] %asi, %o2 -31: lduwa [%o1 + 0xc] %asi, %o3 - jmpl %g1 + %lo(sys_recv), %g0 -32: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop -do_sys_sendto: /* sys_sendto(int, u32, compat_size_t, unsigned int, u32, int) */ -33: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_sendto), %g1 -34: lduwa [%o1 + 0x8] %asi, %o2 -35: lduwa [%o1 + 0xc] %asi, %o3 -36: lduwa [%o1 + 0x10] %asi, %o4 -37: ldswa [%o1 + 0x14] %asi, %o5 - jmpl %g1 + %lo(sys_sendto), %g0 -38: lduwa [%o1 + 0x4] %asi, %o1 -do_sys_recvfrom: /* sys_recvfrom(int, u32, compat_size_t, unsigned int, u32, u32) */ -39: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_recvfrom), %g1 -40: lduwa [%o1 + 0x8] %asi, %o2 -41: lduwa [%o1 + 0xc] %asi, %o3 -42: lduwa [%o1 + 0x10] %asi, %o4 -43: lduwa [%o1 + 0x14] %asi, %o5 - jmpl %g1 + %lo(sys_recvfrom), %g0 -44: lduwa [%o1 + 0x4] %asi, %o1 -do_sys_shutdown: /* sys_shutdown(int, int) */ -45: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_shutdown), %g1 - jmpl %g1 + %lo(sys_shutdown), %g0 -46: ldswa [%o1 + 0x4] %asi, %o1 - nop - nop - nop - nop -do_sys_setsockopt: /* sys_setsockopt(int, int, int, char *, int) */ -47: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_setsockopt), %g1 -48: ldswa [%o1 + 0x8] %asi, %o2 -49: lduwa [%o1 + 0xc] %asi, %o3 -50: ldswa [%o1 + 0x10] %asi, %o4 - jmpl %g1 + %lo(sys_setsockopt), %g0 -51: ldswa [%o1 + 0x4] %asi, %o1 - nop -do_sys_getsockopt: /* sys_getsockopt(int, int, int, u32, u32) */ -52: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_getsockopt), %g1 -53: ldswa [%o1 + 0x8] %asi, %o2 -54: lduwa [%o1 + 0xc] %asi, %o3 -55: lduwa [%o1 + 0x10] %asi, %o4 - jmpl %g1 + %lo(sys_getsockopt), %g0 -56: ldswa [%o1 + 0x4] %asi, %o1 - nop -do_sys_sendmsg: /* compat_sys_sendmsg(int, struct compat_msghdr *, unsigned int) */ -57: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(compat_sys_sendmsg), %g1 -58: lduwa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(compat_sys_sendmsg), %g0 -59: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_recvmsg: /* compat_sys_recvmsg(int, struct compat_msghdr *, unsigned int) */ -60: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(compat_sys_recvmsg), %g1 -61: lduwa [%o1 + 0x8] %asi, %o2 - jmpl %g1 + %lo(compat_sys_recvmsg), %g0 -62: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - nop -do_sys_accept4: /* sys_accept4(int, struct sockaddr *, int *, int) */ -63: ldswa [%o1 + 0x0] %asi, %o0 - sethi %hi(sys_accept4), %g1 -64: lduwa [%o1 + 0x8] %asi, %o2 -65: ldswa [%o1 + 0xc] %asi, %o3 - jmpl %g1 + %lo(sys_accept4), %g0 -66: lduwa [%o1 + 0x4] %asi, %o1 - nop - nop - - .section __ex_table,"a" - .align 4 - .word 1b, __retl_efault, 2b, __retl_efault - .word 3b, __retl_efault, 4b, __retl_efault - .word 5b, __retl_efault, 6b, __retl_efault - .word 7b, __retl_efault, 8b, __retl_efault - .word 9b, __retl_efault, 10b, __retl_efault - .word 11b, __retl_efault, 12b, __retl_efault - .word 13b, __retl_efault, 14b, __retl_efault - .word 15b, __retl_efault, 16b, __retl_efault - .word 17b, __retl_efault, 18b, __retl_efault - .word 19b, __retl_efault, 20b, __retl_efault - .word 21b, __retl_efault, 22b, __retl_efault - .word 23b, __retl_efault, 24b, __retl_efault - .word 25b, __retl_efault, 26b, __retl_efault - .word 27b, __retl_efault, 28b, __retl_efault - .word 29b, __retl_efault, 30b, __retl_efault - .word 31b, __retl_efault, 32b, __retl_efault - .word 33b, __retl_efault, 34b, __retl_efault - .word 35b, __retl_efault, 36b, __retl_efault - .word 37b, __retl_efault, 38b, __retl_efault - .word 39b, __retl_efault, 40b, __retl_efault - .word 41b, __retl_efault, 42b, __retl_efault - .word 43b, __retl_efault, 44b, __retl_efault - .word 45b, __retl_efault, 46b, __retl_efault - .word 47b, __retl_efault, 48b, __retl_efault - .word 49b, __retl_efault, 50b, __retl_efault - .word 51b, __retl_efault, 52b, __retl_efault - .word 53b, __retl_efault, 54b, __retl_efault - .word 55b, __retl_efault, 56b, __retl_efault - .word 57b, __retl_efault, 58b, __retl_efault - .word 59b, __retl_efault, 60b, __retl_efault - .word 61b, __retl_efault, 62b, __retl_efault - .word 63b, __retl_efault, 64b, __retl_efault - .word 65b, __retl_efault, 66b, __retl_efault - .previous diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 4ed06c71c43fb7..d0f535230ad8ba 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -117,7 +117,7 @@ 90 common dup2 sys_dup2 91 32 setfsuid32 sys_setfsuid 92 common fcntl sys_fcntl compat_sys_fcntl -93 common select sys_select +93 common select sys_select compat_sys_select 94 32 setfsgid32 sys_setfsgid 95 common fsync sys_fsync 96 common setpriority sys_setpriority @@ -155,7 +155,7 @@ 123 32 fchown sys_fchown16 123 64 fchown sys_fchown 124 common fchmod sys_fchmod -125 common recvfrom sys_recvfrom +125 common recvfrom sys_recvfrom compat_sys_recvfrom 126 32 setreuid sys_setreuid16 126 64 setreuid sys_setreuid 127 32 setregid sys_setregid16 @@ -247,7 +247,7 @@ 204 32 readdir sys_old_readdir compat_sys_old_readdir 204 64 readdir sys_nis_syscall 205 common readahead sys_readahead compat_sys_readahead -206 common socketcall sys_socketcall sys32_socketcall +206 common socketcall sys_socketcall compat_sys_socketcall 207 common syslog sys_syslog 208 common lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie 209 common fadvise64 sys_fadvise64 compat_sys_fadvise64 @@ -461,7 +461,7 @@ 412 32 utimensat_time64 sys_utimensat sys_utimensat 413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend 419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 08ffd17d5ec340..523a6e5ee92519 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -897,7 +897,7 @@ void __init cheetah_ecache_flush_init(void) /* Now allocate error trap reporting scoreboard. */ sz = NR_CPUS * (2 * sizeof(struct cheetah_err_info)); - for (order = 0; order <= MAX_ORDER; order++) { + for (order = 0; order < NR_PAGE_ORDERS; order++) { if ((PAGE_SIZE << order) >= sz) break; } diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index f83017992eaaeb..d7db4e737218c2 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1665,7 +1665,7 @@ bool kern_addr_valid(unsigned long addr) if (pud_none(*pud)) return false; - if (pud_large(*pud)) + if (pud_leaf(*pud)) return pfn_valid(pud_pfn(*pud)); pmd = pmd_offset(pud, addr); diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index b44d79d778c718..ef69127d7e5e8b 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -249,6 +249,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, { pmd_t old, entry; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); entry = __pmd(pmd_val(*pmdp) & ~_PAGE_VALID); old = pmdp_establish(vma, address, pmdp, entry); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); diff --git a/arch/sparc/prom/init_64.c b/arch/sparc/prom/init_64.c index 103aa910431856..f7b8a1a865b8fe 100644 --- a/arch/sparc/prom/init_64.c +++ b/arch/sparc/prom/init_64.c @@ -26,9 +26,6 @@ phandle prom_chosen_node; * routines in the prom library. * It gets passed the pointer to the PROM vector. */ - -extern void prom_cif_init(void *); - void __init prom_init(void *cif_handler) { phandle node; diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c index 889aa602f8d860..51c3f984bbf728 100644 --- a/arch/sparc/prom/p1275.c +++ b/arch/sparc/prom/p1275.c @@ -49,7 +49,7 @@ void p1275_cmd_direct(unsigned long *args) local_irq_restore(flags); } -void prom_cif_init(void *cif_handler, void *cif_stack) +void prom_cif_init(void *cif_handler) { p1275buf.prom_cif_handler = (void (*)(long *))cif_handler; } diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile index 77d7b9032158c7..d08c3a0443f3a7 100644 --- a/arch/sparc/vdso/Makefile +++ b/arch/sparc/vdso/Makefile @@ -116,30 +116,3 @@ quiet_cmd_vdso = VDSO $@ VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 -Bsymbolic GCOV_PROFILE := n - -# -# Install the unstripped copies of vdso*.so. If our toolchain supports -# build-id, install .build-id links as well. -# -quiet_cmd_vdso_install = INSTALL $(@:install_%=%) -define cmd_vdso_install - cp $< "$(MODLIB)/vdso/$(@:install_%=%)"; \ - if readelf -n $< |grep -q 'Build ID'; then \ - buildid=`readelf -n $< |grep 'Build ID' |sed -e 's/^.*Build ID: \(.*\)$$/\1/'`; \ - first=`echo $$buildid | cut -b-2`; \ - last=`echo $$buildid | cut -b3-`; \ - mkdir -p "$(MODLIB)/vdso/.build-id/$$first"; \ - ln -sf "../../$(@:install_%=%)" "$(MODLIB)/vdso/.build-id/$$first/$$last.debug"; \ - fi -endef - -vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%) - -$(MODLIB)/vdso: FORCE - @mkdir -p $(MODLIB)/vdso - -$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE - $(call cmd,vdso_install) - -PHONY += vdso_install $(vdso_img_insttargets) -vdso_install: $(vdso_img_insttargets) FORCE diff --git a/arch/sparc/vdso/vma.c b/arch/sparc/vdso/vma.c index 136c78f28f8ba2..1bbf4335de4540 100644 --- a/arch/sparc/vdso/vma.c +++ b/arch/sparc/vdso/vma.c @@ -449,9 +449,8 @@ static __init int vdso_setup(char *s) unsigned long val; err = kstrtoul(s, 10, &val); - if (err) - return err; - vdso_enabled = val; - return 0; + if (!err) + vdso_enabled = val; + return 1; } __setup("vdso=", vdso_setup); diff --git a/arch/sparc/video/Makefile b/arch/sparc/video/Makefile index 6baddbd58e4db3..d4d83f1702c61f 100644 --- a/arch/sparc/video/Makefile +++ b/arch/sparc/video/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_FB) += fbdev.o +obj-$(CONFIG_FB_CORE) += fbdev.o diff --git a/arch/um/Makefile b/arch/um/Makefile index 82f05f25063480..34957dcb88b9c3 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -115,7 +115,9 @@ archprepare: $(Q)$(MAKE) $(build)=$(HOST_DIR)/um include/generated/user_constants.h LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static -LINK-$(CONFIG_LD_SCRIPT_DYN) += $(call cc-option, -no-pie) +ifdef CONFIG_LD_SCRIPT_DYN +LINK-$(call gcc-min-version, 60100)$(CONFIG_CC_IS_CLANG) += -no-pie +endif LINK-$(CONFIG_LD_SCRIPT_DYN_RPATH) += -Wl,-rpath,/lib CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \ diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index b98545f3edb503..2ba4e0d4e26b06 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -383,6 +383,7 @@ int setup_one_line(struct line *lines, int n, char *init, parse_chan_pair(NULL, line, n, opts, error_out); err = 0; } + *error_out = "configured as 'none'"; } else { char *new = kstrdup(init, GFP_KERNEL); if (!new) { @@ -406,6 +407,7 @@ int setup_one_line(struct line *lines, int n, char *init, } } if (err) { + *error_out = "failed to parse channel pair"; line->init_str = NULL; line->valid = 0; kfree(new); @@ -673,24 +675,26 @@ void register_winch_irq(int fd, int tty_fd, int pid, struct tty_port *port, goto cleanup; } - *winch = ((struct winch) { .list = LIST_HEAD_INIT(winch->list), - .fd = fd, + *winch = ((struct winch) { .fd = fd, .tty_fd = tty_fd, .pid = pid, .port = port, .stack = stack }); + spin_lock(&winch_handler_lock); + list_add(&winch->list, &winch_handlers); + spin_unlock(&winch_handler_lock); + if (um_request_irq(WINCH_IRQ, fd, IRQ_READ, winch_interrupt, IRQF_SHARED, "winch", winch) < 0) { printk(KERN_ERR "register_winch_irq - failed to register " "IRQ\n"); + spin_lock(&winch_handler_lock); + list_del(&winch->list); + spin_unlock(&winch_handler_lock); goto out_free; } - spin_lock(&winch_handler_lock); - list_add(&winch->list, &winch_handlers); - spin_unlock(&winch_handler_lock); - return; out_free: diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 3d7836c4650701..cabcc501b448a3 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -204,7 +204,7 @@ static int uml_net_close(struct net_device *dev) return 0; } -static int uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct uml_net_private *lp = netdev_priv(dev); unsigned long flags; diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 50206feac577d5..ef7b4b911a455a 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -456,43 +456,31 @@ static int bulk_req_safe_read( return n; } -/* Called without dev->lock held, and only in interrupt context. */ -static void ubd_handler(void) +static void ubd_end_request(struct io_thread_req *io_req) { - int n; - int count; - - while(1){ - n = bulk_req_safe_read( - thread_fd, - irq_req_buffer, - &irq_remainder, - &irq_remainder_size, - UBD_REQ_BUFFER_SIZE - ); - if (n < 0) { - if(n == -EAGAIN) - break; - printk(KERN_ERR "spurious interrupt in ubd_handler, " - "err = %d\n", -n); - return; - } - for (count = 0; count < n/sizeof(struct io_thread_req *); count++) { - struct io_thread_req *io_req = (*irq_req_buffer)[count]; - - if ((io_req->error == BLK_STS_NOTSUPP) && (req_op(io_req->req) == REQ_OP_DISCARD)) { - blk_queue_max_discard_sectors(io_req->req->q, 0); - blk_queue_max_write_zeroes_sectors(io_req->req->q, 0); - } - blk_mq_end_request(io_req->req, io_req->error); - kfree(io_req); - } + if (io_req->error == BLK_STS_NOTSUPP) { + if (req_op(io_req->req) == REQ_OP_DISCARD) + blk_queue_max_discard_sectors(io_req->req->q, 0); + else if (req_op(io_req->req) == REQ_OP_WRITE_ZEROES) + blk_queue_max_write_zeroes_sectors(io_req->req->q, 0); } + blk_mq_end_request(io_req->req, io_req->error); + kfree(io_req); } static irqreturn_t ubd_intr(int irq, void *dev) { - ubd_handler(); + int len, i; + + while ((len = bulk_req_safe_read(thread_fd, irq_req_buffer, + &irq_remainder, &irq_remainder_size, + UBD_REQ_BUFFER_SIZE)) >= 0) { + for (i = 0; i < len / sizeof(struct io_thread_req *); i++) + ubd_end_request((*irq_req_buffer)[i]); + } + + if (len < 0 && len != -EAGAIN) + pr_err("spurious interrupt in %s, err = %d\n", __func__, len); return IRQ_HANDLED; } @@ -1099,7 +1087,7 @@ static int __init ubd_init(void) if (irq_req_buffer == NULL) { printk(KERN_ERR "Failed to initialize ubd buffering\n"); - return -1; + return -ENOMEM; } io_req_buffer = kmalloc_array(UBD_REQ_BUFFER_SIZE, sizeof(struct io_thread_req *), @@ -1110,7 +1098,7 @@ static int __init ubd_init(void) if (io_req_buffer == NULL) { printk(KERN_ERR "Failed to initialize ubd buffering\n"); - return -1; + return -ENOMEM; } platform_driver_register(&ubd_driver); mutex_lock(&ubd_lock); diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 131b7cb2957672..94a4dfac6c2368 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -141,7 +141,7 @@ static bool get_bpf_flash(struct arglist *def) if (allow != NULL) { if (kstrtoul(allow, 10, &result) == 0) - return (allow > 0); + return result > 0; } return false; } diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c index ffe2ee8a02465b..97a37c06299721 100644 --- a/arch/um/drivers/virt-pci.c +++ b/arch/um/drivers/virt-pci.c @@ -971,7 +971,7 @@ static long um_pci_map_platform(unsigned long offset, size_t size, *ops = &um_pci_device_bar_ops; *priv = &um_pci_platform_device->resptr[0]; - return 0; + return offset; } static const struct logic_iomem_region_ops um_pci_platform_ops = { diff --git a/arch/um/include/asm/cpufeature.h b/arch/um/include/asm/cpufeature.h index 4b6d1b526bc121..66fe06db872f05 100644 --- a/arch/um/include/asm/cpufeature.h +++ b/arch/um/include/asm/cpufeature.h @@ -75,7 +75,7 @@ extern void setup_clear_cpu_cap(unsigned int bit); */ static __always_inline bool _static_cpu_has(u16 bit) { - asm_volatile_goto("1: jmp 6f\n" + asm goto("1: jmp 6f\n" "2:\n" ".skip -(((5f-4f) - (2b-1b)) > 0) * " "((5f-4f) - (2b-1b)),0x90\n" diff --git a/arch/um/include/asm/kasan.h b/arch/um/include/asm/kasan.h index 0d6547f4ec85c4..f97bb1f7b8514a 100644 --- a/arch/um/include/asm/kasan.h +++ b/arch/um/include/asm/kasan.h @@ -24,7 +24,6 @@ #ifdef CONFIG_KASAN void kasan_init(void); -void kasan_map_memory(void *start, unsigned long len); extern int kasan_um_is_ready; #ifdef CONFIG_STATIC_LINK diff --git a/arch/um/include/asm/mmu.h b/arch/um/include/asm/mmu.h index 5b072aba5b658f..a7cb380c0b5c07 100644 --- a/arch/um/include/asm/mmu.h +++ b/arch/um/include/asm/mmu.h @@ -15,8 +15,6 @@ typedef struct mm_context { struct page *stub_pages[2]; } mm_context_t; -extern void __switch_mm(struct mm_id * mm_idp); - /* Avoid tangled inclusion with asm/ldt.h */ extern long init_new_ldt(struct mm_context *to_mm, struct mm_context *from_mm); extern void free_ldt(struct mm_context *mm); diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index 7414154b8e9aea..d34169883dbf0a 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -95,7 +95,6 @@ extern struct cpuinfo_um boot_cpu_data; #define current_cpu_data boot_cpu_data #define cache_line_size() (boot_cpu_data.cache_alignment) -extern unsigned long get_thread_reg(int reg, jmp_buf *buf); #define KSTK_REG(tsk, reg) get_thread_reg(reg, &tsk->thread.switch_buf) extern unsigned long __get_wchan(struct task_struct *p); diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h index d8b8b4f07e429d..7372746c168757 100644 --- a/arch/um/include/shared/kern_util.h +++ b/arch/um/include/shared/kern_util.h @@ -50,7 +50,7 @@ extern void do_uml_exitcalls(void); * Are we disallowed to sleep? Used to choose between GFP_KERNEL and * GFP_ATOMIC. */ -extern int __cant_sleep(void); +extern int __uml_cant_sleep(void); extern int get_current_pid(void); extern int copy_from_user_proc(void *to, void *from, int size); extern char *uml_strdup(const char *string); @@ -67,4 +67,6 @@ extern void fatal_sigsegv(void) __attribute__ ((noreturn)); void um_idle_sleep(void); +void kasan_map_memory(void *start, size_t len); + #endif diff --git a/arch/um/include/shared/skas/mm_id.h b/arch/um/include/shared/skas/mm_id.h index e82e203f5f4194..92dbf727e3842a 100644 --- a/arch/um/include/shared/skas/mm_id.h +++ b/arch/um/include/shared/skas/mm_id.h @@ -15,4 +15,6 @@ struct mm_id { int kill; }; +void __switch_mm(struct mm_id *mm_idp); + #endif diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 106b7da2f8d6f7..6daffb9d8a8d74 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -220,7 +220,7 @@ void arch_cpu_idle(void) um_idle_sleep(); } -int __cant_sleep(void) { +int __uml_cant_sleep(void) { return in_atomic() || irqs_disabled() || in_interrupt(); /* Is in_interrupt() really needed? */ } diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index fddd1dec27e6d3..c8c4ef94c753f1 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -432,9 +432,29 @@ static void time_travel_update_time(unsigned long long next, bool idle) time_travel_del_event(&ne); } +static void time_travel_update_time_rel(unsigned long long offs) +{ + unsigned long flags; + + /* + * Disable interrupts before calculating the new time so + * that a real timer interrupt (signal) can't happen at + * a bad time e.g. after we read time_travel_time but + * before we've completed updating the time. + */ + local_irq_save(flags); + time_travel_update_time(time_travel_time + offs, false); + local_irq_restore(flags); +} + void time_travel_ndelay(unsigned long nsec) { - time_travel_update_time(time_travel_time + nsec, false); + /* + * Not strictly needed to use _rel() version since this is + * only used in INFCPU/EXT modes, but it doesn't hurt and + * is more readable too. + */ + time_travel_update_time_rel(nsec); } EXPORT_SYMBOL(time_travel_ndelay); @@ -568,7 +588,11 @@ static void time_travel_set_start(void) #define time_travel_time 0 #define time_travel_ext_waiting 0 -static inline void time_travel_update_time(unsigned long long ns, bool retearly) +static inline void time_travel_update_time(unsigned long long ns, bool idle) +{ +} + +static inline void time_travel_update_time_rel(unsigned long long offs) { } @@ -720,9 +744,7 @@ static u64 timer_read(struct clocksource *cs) */ if (!irqs_disabled() && !in_interrupt() && !in_softirq() && !time_travel_ext_waiting) - time_travel_update_time(time_travel_time + - TIMER_MULTIPLIER, - false); + time_travel_update_time_rel(TIMER_MULTIPLIER); return time_travel_time / TIMER_MULTIPLIER; } @@ -852,9 +874,9 @@ int setup_time_travel_start(char *str) return 1; } -__setup("time-travel-start", setup_time_travel_start); +__setup("time-travel-start=", setup_time_travel_start); __uml_help(setup_time_travel_start, -"time-travel-start=\n" +"time-travel-start=\n" "Configure the UML instance's wall clock to start at this value rather than\n" "the host's wall clock at the time of UML boot.\n"); #endif diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c index b459745f52e248..3cb8ac63be6ed9 100644 --- a/arch/um/os-Linux/helper.c +++ b/arch/um/os-Linux/helper.c @@ -46,7 +46,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv) unsigned long stack, sp; int pid, fds[2], ret, n; - stack = alloc_stack(0, __cant_sleep()); + stack = alloc_stack(0, __uml_cant_sleep()); if (stack == 0) return -ENOMEM; @@ -70,7 +70,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv) data.pre_data = pre_data; data.argv = argv; data.fd = fds[1]; - data.buf = __cant_sleep() ? uml_kmalloc(PATH_MAX, UM_GFP_ATOMIC) : + data.buf = __uml_cant_sleep() ? uml_kmalloc(PATH_MAX, UM_GFP_ATOMIC) : uml_kmalloc(PATH_MAX, UM_GFP_KERNEL); pid = clone(helper_child, (void *) sp, CLONE_VM, &data); if (pid < 0) { @@ -121,7 +121,7 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags, unsigned long stack, sp; int pid, status, err; - stack = alloc_stack(0, __cant_sleep()); + stack = alloc_stack(0, __uml_cant_sleep()); if (stack == 0) return -ENOMEM; diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c index 8530b2e086049b..c6c9495b143212 100644 --- a/arch/um/os-Linux/mem.c +++ b/arch/um/os-Linux/mem.c @@ -15,6 +15,7 @@ #include #include #include +#include #include /* diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c index 24a403a70a0201..850d21e6473eec 100644 --- a/arch/um/os-Linux/signal.c +++ b/arch/um/os-Linux/signal.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -65,9 +66,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc) int signals_enabled; #ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT -static int signals_blocked; -#else -#define signals_blocked 0 +static int signals_blocked, signals_blocked_pending; #endif static unsigned int signals_pending; static unsigned int signals_active = 0; @@ -76,14 +75,27 @@ void sig_handler(int sig, struct siginfo *si, mcontext_t *mc) { int enabled = signals_enabled; - if ((signals_blocked || !enabled) && (sig == SIGIO)) { +#ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT + if ((signals_blocked || + __atomic_load_n(&signals_blocked_pending, __ATOMIC_SEQ_CST)) && + (sig == SIGIO)) { + /* increment so unblock will do another round */ + __atomic_add_fetch(&signals_blocked_pending, 1, + __ATOMIC_SEQ_CST); + return; + } +#endif + + if (!enabled && (sig == SIGIO)) { /* * In TT_MODE_EXTERNAL, need to still call time-travel - * handlers unless signals are also blocked for the - * external time message processing. This will mark - * signals_pending by itself (only if necessary.) + * handlers. This will mark signals_pending by itself + * (only if necessary.) + * Note we won't get here if signals are hard-blocked + * (which is handled above), in that case the hard- + * unblock will handle things. */ - if (!signals_blocked && time_travel_mode == TT_MODE_EXTERNAL) + if (time_travel_mode == TT_MODE_EXTERNAL) sigio_run_timetravel_handlers(); else signals_pending |= SIGIO_MASK; @@ -380,33 +392,99 @@ int um_set_signals_trace(int enable) #ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT void mark_sigio_pending(void) { + /* + * It would seem that this should be atomic so + * it isn't a read-modify-write with a signal + * that could happen in the middle, losing the + * value set by the signal. + * + * However, this function is only called when in + * time-travel=ext simulation mode, in which case + * the only signal ever pending is SIGIO, which + * is blocked while this can be called, and the + * timer signal (SIGALRM) cannot happen. + */ signals_pending |= SIGIO_MASK; } void block_signals_hard(void) { - if (signals_blocked) - return; - signals_blocked = 1; + signals_blocked++; barrier(); } void unblock_signals_hard(void) { + static bool unblocking; + if (!signals_blocked) + panic("unblocking signals while not blocked"); + + if (--signals_blocked) return; - /* Must be set to 0 before we check the pending bits etc. */ - signals_blocked = 0; + /* + * Must be set to 0 before we check pending so the + * SIGIO handler will run as normal unless we're still + * going to process signals_blocked_pending. + */ barrier(); - if (signals_pending && signals_enabled) { - /* this is a bit inefficient, but that's not really important */ - block_signals(); - unblock_signals(); - } else if (signals_pending & SIGIO_MASK) { - /* we need to run time-travel handlers even if not enabled */ - sigio_run_timetravel_handlers(); + /* + * Note that block_signals_hard()/unblock_signals_hard() can be called + * within the unblock_signals()/sigio_run_timetravel_handlers() below. + * This would still be prone to race conditions since it's actually a + * call _within_ e.g. vu_req_read_message(), where we observed this + * issue, which loops. Thus, if the inner call handles the recorded + * pending signals, we can get out of the inner call with the real + * signal hander no longer blocked, and still have a race. Thus don't + * handle unblocking in the inner call, if it happens, but only in + * the outermost call - 'unblocking' serves as an ownership for the + * signals_blocked_pending decrement. + */ + if (unblocking) + return; + unblocking = true; + + while (__atomic_load_n(&signals_blocked_pending, __ATOMIC_SEQ_CST)) { + if (signals_enabled) { + /* signals are enabled so we can touch this */ + signals_pending |= SIGIO_MASK; + /* + * this is a bit inefficient, but that's + * not really important + */ + block_signals(); + unblock_signals(); + } else { + /* + * we need to run time-travel handlers even + * if not enabled + */ + sigio_run_timetravel_handlers(); + } + + /* + * The decrement of signals_blocked_pending must be atomic so + * that the signal handler will either happen before or after + * the decrement, not during a read-modify-write: + * - If it happens before, it can increment it and we'll + * decrement it and do another round in the loop. + * - If it happens after it'll see 0 for both signals_blocked + * and signals_blocked_pending and thus run the handler as + * usual (subject to signals_enabled, but that's unrelated.) + * + * Note that a call to unblock_signals_hard() within the calls + * to unblock_signals() or sigio_run_timetravel_handlers() above + * will do nothing due to the 'unblocking' state, so this cannot + * underflow as the only one decrementing will be the outermost + * one. + */ + if (__atomic_sub_fetch(&signals_blocked_pending, 1, + __ATOMIC_SEQ_CST) < 0) + panic("signals_blocked_pending underflow"); } + + unblocking = false; } #endif diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c index fc0f2a9dee5af9..1dca4ffbd572f7 100644 --- a/arch/um/os-Linux/util.c +++ b/arch/um/os-Linux/util.c @@ -173,23 +173,38 @@ __uml_setup("quiet", quiet_cmd_param, "quiet\n" " Turns off information messages during boot.\n\n"); +/* + * The os_info/os_warn functions will be called by helper threads. These + * have a very limited stack size and using the libc formatting functions + * may overflow the stack. + * So pull in the kernel vscnprintf and use that instead with a fixed + * on-stack buffer. + */ +int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); + void os_info(const char *fmt, ...) { + char buf[256]; va_list list; + int len; if (quiet_info) return; va_start(list, fmt); - vfprintf(stderr, fmt, list); + len = vscnprintf(buf, sizeof(buf), fmt, list); + fwrite(buf, len, 1, stderr); va_end(list); } void os_warn(const char *fmt, ...) { + char buf[256]; va_list list; + int len; va_start(list, fmt); - vfprintf(stderr, fmt, list); + len = vscnprintf(buf, sizeof(buf), fmt, list); + fwrite(buf, len, 1, stderr); va_end(list); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 66bfabae881491..82d12c93feabe6 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -62,6 +62,7 @@ config X86 select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI select ARCH_32BIT_OFF_T if X86_32 select ARCH_CLOCKSOURCE_INIT + select ARCH_CONFIGURES_CPU_MITIGATIONS select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64 @@ -1514,19 +1515,6 @@ config AMD_MEM_ENCRYPT This requires an AMD processor that supports Secure Memory Encryption (SME). -config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT - bool "Activate AMD Secure Memory Encryption (SME) by default" - depends on AMD_MEM_ENCRYPT - help - Say yes to have system memory encrypted by default if running on - an AMD processor that supports Secure Memory Encryption (SME). - - If set to Y, then the encryption of system memory can be - deactivated with the mem_encrypt=off command line option. - - If set to N, then the encryption of system memory can be - activated with the mem_encrypt=on command line option. - # Common NUMA Features config NUMA bool "NUMA Memory Allocation and Scheduler Support" @@ -2034,7 +2022,7 @@ config ARCH_SUPPORTS_KEXEC def_bool y config ARCH_SUPPORTS_KEXEC_FILE - def_bool X86_64 && CRYPTO && CRYPTO_SHA256 + def_bool X86_64 config ARCH_SELECTS_KEXEC_FILE def_bool y @@ -2042,7 +2030,7 @@ config ARCH_SELECTS_KEXEC_FILE select HAVE_IMA_KEXEC if IMA config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SUPPORTS_KEXEC_SIG def_bool y @@ -2434,17 +2422,21 @@ config PREFIX_SYMBOLS def_bool y depends on CALL_PADDING && !CFI_CLANG -menuconfig SPECULATION_MITIGATIONS - bool "Mitigations for speculative execution vulnerabilities" +menuconfig CPU_MITIGATIONS + bool "Mitigations for CPU vulnerabilities" default y help - Say Y here to enable options which enable mitigations for - speculative execution hardware vulnerabilities. + Say Y here to enable options which enable mitigations for hardware + vulnerabilities (usually related to speculative execution). + Mitigations can be disabled or restricted to SMT systems at runtime + via the "mitigations" kernel parameter. - If you say N, all mitigations will be disabled. You really - should know what you are doing to say so. + If you say N, all mitigations will be disabled. This CANNOT be + overridden at runtime. -if SPECULATION_MITIGATIONS + Say 'Y', unless you really know what you are doing. + +if CPU_MITIGATIONS config PAGE_TABLE_ISOLATION bool "Remove the kernel mapping in user mode" @@ -2568,6 +2560,27 @@ config GDS_FORCE_MITIGATION If in doubt, say N. +config MITIGATION_RFDS + bool "RFDS Mitigation" + depends on CPU_SUP_INTEL + default y + help + Enable mitigation for Register File Data Sampling (RFDS) by default. + RFDS is a hardware vulnerability which affects Intel Atom CPUs. It + allows unprivileged speculative access to stale data previously + stored in floating point, vector and integer registers. + See also + +config MITIGATION_SPECTRE_BHI + bool "Mitigate Spectre-BHB (Branch History Injection)" + depends on CPU_SUP_INTEL + default y + help + Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks + where the branch history buffer is poisoned to speculatively steer + indirect branches. + See + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler index 8ad41da301e53c..16d0b022d6fff6 100644 --- a/arch/x86/Kconfig.assembler +++ b/arch/x86/Kconfig.assembler @@ -26,6 +26,6 @@ config AS_GFNI Supported by binutils >= 2.30 and LLVM integrated assembler config AS_WRUSS - def_bool $(as-instr,wrussq %rax$(comma)(%rbx)) + def_bool $(as-instr64,wrussq %rax$(comma)(%rbx)) help Supported by binutils >= 2.31 and LLVM integrated assembler diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 00468adf180f1d..87396575cfa777 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -375,7 +375,7 @@ config X86_CMOV config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 - default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8) + default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8) default "5" if X86_32 && X86_CMPXCHG64 default "4" diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index c5d614d28a7599..74777a97e394aa 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -248,6 +248,7 @@ config UNWINDER_ORC config UNWINDER_FRAME_POINTER bool "Frame pointer unwinder" + select ARCH_WANT_FRAME_POINTERS select FRAME_POINTER help This option enables the frame pointer unwinder for unwinding kernel @@ -271,7 +272,3 @@ config UNWINDER_GUESS overhead. endchoice - -config FRAME_POINTER - depends on !UNWINDER_ORC && !UNWINDER_GUESS - bool diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5bfe5caaa444b3..3ff53a2d4ff084 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -291,9 +291,10 @@ PHONY += install install: $(call cmd,install) -PHONY += vdso_install -vdso_install: - $(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@ +vdso-install-$(CONFIG_X86_64) += arch/x86/entry/vdso/vdso64.so.dbg +vdso-install-$(CONFIG_X86_X32_ABI) += arch/x86/entry/vdso/vdsox32.so.dbg +vdso-install-$(CONFIG_X86_32) += arch/x86/entry/vdso/vdso32.so.dbg +vdso-install-$(CONFIG_IA32_EMULATION) += arch/x86/entry/vdso/vdso32.so.dbg archprepare: checkbin checkbin: diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index f33e45ed143765..3cece19b74732f 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -89,7 +89,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|efi32_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi.._stub_entry\|efi\(32\)\?_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|_e\?data\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 71fc531b95b4ee..658e9ec065c476 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -84,7 +84,7 @@ LDFLAGS_vmlinux += -T hostprogs := mkpiggy HOST_EXTRACFLAGS += -I$(srctree)/tools/include -sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p' +sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__start_rodata\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p' quiet_cmd_voffset = VOFFSET $@ cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@ @@ -116,9 +116,9 @@ vmlinux-objs-$(CONFIG_UNACCEPTED_MEMORY) += $(obj)/mem.o vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o -vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a +vmlinux-libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a -$(obj)/vmlinux: $(vmlinux-objs-y) FORCE +$(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE $(call if_changed,ld) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S diff --git a/arch/x86/boot/compressed/efi_mixed.S b/arch/x86/boot/compressed/efi_mixed.S index f4e22ef774ab6b..876fc6d46a1318 100644 --- a/arch/x86/boot/compressed/efi_mixed.S +++ b/arch/x86/boot/compressed/efi_mixed.S @@ -15,10 +15,12 @@ */ #include +#include #include #include #include #include +#include .code64 .text @@ -49,6 +51,11 @@ SYM_FUNC_START(startup_64_mixed_mode) lea efi32_boot_args(%rip), %rdx mov 0(%rdx), %edi mov 4(%rdx), %esi + + /* Switch to the firmware's stack */ + movl efi32_boot_sp(%rip), %esp + andl $~7, %esp + #ifdef CONFIG_EFI_HANDOVER_PROTOCOL mov 8(%rdx), %edx // saved bootparams pointer test %edx, %edx @@ -144,6 +151,7 @@ SYM_FUNC_END(__efi64_thunk) SYM_FUNC_START(efi32_stub_entry) call 1f 1: popl %ecx + leal (efi32_boot_args - 1b)(%ecx), %ebx /* Clear BSS */ xorl %eax, %eax @@ -158,6 +166,7 @@ SYM_FUNC_START(efi32_stub_entry) popl %ecx popl %edx popl %esi + movl %esi, 8(%ebx) jmp efi32_entry SYM_FUNC_END(efi32_stub_entry) #endif @@ -234,8 +243,6 @@ SYM_FUNC_END(efi_enter32) * * Arguments: %ecx image handle * %edx EFI system table pointer - * %esi struct bootparams pointer (or NULL when not using - * the EFI handover protocol) * * Since this is the point of no return for ordinary execution, no registers * are considered live except for the function parameters. [Note that the EFI @@ -254,13 +261,25 @@ SYM_FUNC_START_LOCAL(efi32_entry) /* Store firmware IDT descriptor */ sidtl (efi32_boot_idt - 1b)(%ebx) + /* Store firmware stack pointer */ + movl %esp, (efi32_boot_sp - 1b)(%ebx) + /* Store boot arguments */ leal (efi32_boot_args - 1b)(%ebx), %ebx movl %ecx, 0(%ebx) movl %edx, 4(%ebx) - movl %esi, 8(%ebx) movb $0x0, 12(%ebx) // efi_is64 + /* + * Allocate some memory for a temporary struct boot_params, which only + * needs the minimal pieces that startup_32() relies on. + */ + subl $PARAM_SIZE, %esp + movl %esp, %esi + movl $PAGE_SIZE, BP_kernel_alignment(%esi) + movl $_end - 1b, BP_init_size(%esi) + subl $startup_32 - 1b, BP_init_size(%esi) + /* Disable paging */ movl %cr0, %eax btrl $X86_CR0_PG_BIT, %eax @@ -286,8 +305,7 @@ SYM_FUNC_START(efi32_pe_entry) movl 8(%ebp), %ecx // image_handle movl 12(%ebp), %edx // sys_table - xorl %esi, %esi - jmp efi32_entry // pass %ecx, %edx, %esi + jmp efi32_entry // pass %ecx, %edx // no other registers remain live 2: popl %edi // restore callee-save registers @@ -318,5 +336,6 @@ SYM_DATA_END(efi32_boot_idt) SYM_DATA_LOCAL(efi32_boot_cs, .word 0) SYM_DATA_LOCAL(efi32_boot_ds, .word 0) +SYM_DATA_LOCAL(efi32_boot_sp, .long 0) SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0) SYM_DATA(efi_is64, .byte 1) diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index bf4a10a5794f1c..1dcb794c5479ed 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -398,6 +398,11 @@ SYM_CODE_START(startup_64) call sev_enable #endif + /* Preserve only the CR4 bits that must be preserved, and clear the rest */ + movq %cr4, %rax + andl $(X86_CR4_PAE | X86_CR4_MCE | X86_CR4_LA57), %eax + movq %rax, %cr4 + /* * configure_5level_paging() updates the number of paging levels using * a trampoline in 32-bit addressable memory if the current number does diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 08f93b0401bbd3..aead80ec70a0bf 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -385,3 +385,8 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) */ kernel_add_identity_map(address, end); } + +void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code) +{ + /* Empty handler to ignore NMI during early boot */ +} diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 3cdf94b4145674..d100284bbef47b 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -61,6 +61,7 @@ void load_stage2_idt(void) boot_idt_desc.address = (unsigned long)boot_idt; set_idt_entry(X86_TRAP_PF, boot_page_fault); + set_idt_entry(X86_TRAP_NMI, boot_nmi_trap); #ifdef CONFIG_AMD_MEM_ENCRYPT /* diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S index 22890e199f5b44..4d03c8562f637d 100644 --- a/arch/x86/boot/compressed/idt_handlers_64.S +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -70,6 +70,7 @@ SYM_FUNC_END(\name) .code64 EXCEPTION_HANDLER boot_page_fault do_boot_page_fault error_code=1 +EXCEPTION_HANDLER boot_nmi_trap do_boot_nmi_trap error_code=0 #ifdef CONFIG_AMD_MEM_ENCRYPT EXCEPTION_HANDLER boot_stage1_vc do_vc_no_ghcb error_code=1 diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index f711f2a85862e9..b5ecbd32a46fac 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -330,6 +330,7 @@ static size_t parse_elf(void *output) return ehdr.e_entry - LOAD_PHYSICAL_ADDR; } +const unsigned long kernel_text_size = VO___start_rodata - VO__text; const unsigned long kernel_total_size = VO__end - VO__text; static u8 boot_heap[BOOT_HEAP_SIZE] __aligned(4); @@ -357,6 +358,19 @@ unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, return entry; } +/* + * Set the memory encryption xloadflag based on the mem_encrypt= command line + * parameter, if provided. + */ +static void parse_mem_encrypt(struct setup_header *hdr) +{ + int on = cmdline_find_option_bool("mem_encrypt=on"); + int off = cmdline_find_option_bool("mem_encrypt=off"); + + if (on > off) + hdr->xloadflags |= XLF_MEM_ENCRYPTION; +} + /* * The compressed kernel image (ZO), has been moved so that its position * is against the end of the buffer used to hold the uncompressed kernel @@ -387,6 +401,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) /* Clear flags intended for solely in-kernel use. */ boot_params->hdr.loadflags &= ~KASLR_FLAG; + parse_mem_encrypt(&boot_params->hdr); + sanitize_boot_params(boot_params); if (boot_params->screen_info.orig_video_mode == 7) { diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index cc70d3fb90497e..aae1a2db425103 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -197,6 +197,7 @@ static inline void cleanup_exception_handling(void) { } /* IDT Entry Points */ void boot_page_fault(void); +void boot_nmi_trap(void); void boot_stage1_vc(void); void boot_stage2_vc(void); diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 80d76aea1f7bf1..0a49218a516a28 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -116,6 +116,9 @@ static bool fault_in_kernel_space(unsigned long address) #undef __init #define __init +#undef __head +#define __head + #define __BOOT_COMPRESSED /* Basic instruction decoding support needed */ diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index b22f34b8684a72..083ec6d7722a16 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -43,11 +43,13 @@ SECTIONS *(.rodata.*) _erodata = . ; } - .data : { + .data : ALIGN(0x1000) { _data = . ; *(.data) *(.data.*) - *(.bss.efistub) + + /* Add 4 bytes of extra space for a CRC-32 checksum */ + . = ALIGN(. + 4, 0x200); _edata = . ; } . = ALIGN(L1_CACHE_BYTES); diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index b04ca8e2b213c6..a1bbedd989e42e 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -36,66 +36,20 @@ SYSSEG = 0x1000 /* historical load address >> 4 */ #define ROOT_RDONLY 1 #endif + .set salign, 0x1000 + .set falign, 0x200 + .code16 .section ".bstext", "ax" - - .global bootsect_start -bootsect_start: #ifdef CONFIG_EFI_STUB # "MZ", MS-DOS header .word MZ_MAGIC -#endif - - # Normalize the start address - ljmp $BOOTSEG, $start2 - -start2: - movw %cs, %ax - movw %ax, %ds - movw %ax, %es - movw %ax, %ss - xorw %sp, %sp - sti - cld - - movw $bugger_off_msg, %si - -msg_loop: - lodsb - andb %al, %al - jz bs_die - movb $0xe, %ah - movw $7, %bx - int $0x10 - jmp msg_loop - -bs_die: - # Allow the user to press a key, then reboot - xorw %ax, %ax - int $0x16 - int $0x19 - - # int 0x19 should never return. In case it does anyway, - # invoke the BIOS reset code... - ljmp $0xf000,$0xfff0 - -#ifdef CONFIG_EFI_STUB .org 0x38 # # Offset to the PE header. # .long LINUX_PE_MAGIC .long pe_header -#endif /* CONFIG_EFI_STUB */ - - .section ".bsdata", "a" -bugger_off_msg: - .ascii "Use a boot loader.\r\n" - .ascii "\n" - .ascii "Remove disk and press any key to reboot...\r\n" - .byte 0 - -#ifdef CONFIG_EFI_STUB pe_header: .long PE_MAGIC @@ -124,30 +78,26 @@ optional_header: .byte 0x02 # MajorLinkerVersion .byte 0x14 # MinorLinkerVersion - # Filled in by build.c - .long 0 # SizeOfCode + .long ZO__data # SizeOfCode - .long 0 # SizeOfInitializedData + .long ZO__end - ZO__data # SizeOfInitializedData .long 0 # SizeOfUninitializedData - # Filled in by build.c - .long 0x0000 # AddressOfEntryPoint + .long setup_size + ZO_efi_pe_entry # AddressOfEntryPoint - .long 0x0200 # BaseOfCode + .long setup_size # BaseOfCode #ifdef CONFIG_X86_32 .long 0 # data #endif extra_header_fields: - # PE specification requires ImageBase to be 64k aligned - .set image_base, (LOAD_PHYSICAL_ADDR + 0xffff) & ~0xffff #ifdef CONFIG_X86_32 - .long image_base # ImageBase + .long 0 # ImageBase #else - .quad image_base # ImageBase + .quad 0 # ImageBase #endif - .long 0x20 # SectionAlignment - .long 0x20 # FileAlignment + .long salign # SectionAlignment + .long falign # FileAlignment .word 0 # MajorOperatingSystemVersion .word 0 # MinorOperatingSystemVersion .word LINUX_EFISTUB_MAJOR_VERSION # MajorImageVersion @@ -156,12 +106,9 @@ extra_header_fields: .word 0 # MinorSubsystemVersion .long 0 # Win32VersionValue - # - # The size of the bzImage is written in tools/build.c - # - .long 0 # SizeOfImage + .long setup_size + ZO__end # SizeOfImage - .long 0x200 # SizeOfHeaders + .long salign # SizeOfHeaders .long 0 # CheckSum .word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application) #ifdef CONFIG_EFI_DXE_MEM_ATTRIBUTES @@ -192,87 +139,77 @@ extra_header_fields: # Section table section_table: - # - # The offset & size fields are filled in by build.c. - # .ascii ".setup" .byte 0 .byte 0 - .long 0 - .long 0x0 # startup_{32,64} - .long 0 # Size of initialized data - # on disk - .long 0x0 # startup_{32,64} - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers - .long IMAGE_SCN_CNT_CODE | \ - IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_EXECUTE | \ - IMAGE_SCN_ALIGN_16BYTES # Characteristics + .long pecompat_fstart - salign # VirtualSize + .long salign # VirtualAddress + .long pecompat_fstart - salign # SizeOfRawData + .long salign # PointerToRawData - # - # The EFI application loader requires a relocation section - # because EFI applications must be relocatable. The .reloc - # offset & size fields are filled in by build.c. - # - .ascii ".reloc" - .byte 0 - .byte 0 - .long 0 - .long 0 - .long 0 # SizeOfRawData - .long 0 # PointerToRawData - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers + .long 0, 0, 0 .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_DISCARDABLE | \ - IMAGE_SCN_ALIGN_1BYTES # Characteristics + IMAGE_SCN_MEM_DISCARDABLE # Characteristics #ifdef CONFIG_EFI_MIXED - # - # The offset & size fields are filled in by build.c. - # .asciz ".compat" - .long 0 - .long 0x0 - .long 0 # Size of initialized data - # on disk - .long 0x0 - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers + + .long pecompat_fsize # VirtualSize + .long pecompat_fstart # VirtualAddress + .long pecompat_fsize # SizeOfRawData + .long pecompat_fstart # PointerToRawData + + .long 0, 0, 0 .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_DISCARDABLE | \ - IMAGE_SCN_ALIGN_1BYTES # Characteristics + IMAGE_SCN_MEM_DISCARDABLE # Characteristics + + /* + * Put the IA-32 machine type and the associated entry point address in + * the .compat section, so loaders can figure out which other execution + * modes this image supports. + */ + .pushsection ".pecompat", "a", @progbits + .balign salign + .globl pecompat_fstart +pecompat_fstart: + .byte 0x1 # Version + .byte 8 # Size + .word IMAGE_FILE_MACHINE_I386 # PE machine type + .long setup_size + ZO_efi32_pe_entry # Entrypoint + .byte 0x0 # Sentinel + .popsection +#else + .set pecompat_fstart, setup_size #endif - - # - # The offset & size fields are filled in by build.c. - # .ascii ".text" .byte 0 .byte 0 .byte 0 - .long 0 - .long 0x0 # startup_{32,64} - .long 0 # Size of initialized data + .long ZO__data + .long setup_size + .long ZO__data # Size of initialized data # on disk - .long 0x0 # startup_{32,64} + .long setup_size .long 0 # PointerToRelocations .long 0 # PointerToLineNumbers .word 0 # NumberOfRelocations .word 0 # NumberOfLineNumbers .long IMAGE_SCN_CNT_CODE | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_EXECUTE | \ - IMAGE_SCN_ALIGN_16BYTES # Characteristics + IMAGE_SCN_MEM_EXECUTE # Characteristics + + .ascii ".data\0\0\0" + .long ZO__end - ZO__data # VirtualSize + .long setup_size + ZO__data # VirtualAddress + .long ZO__edata - ZO__data # SizeOfRawData + .long setup_size + ZO__data # PointerToRawData + + .long 0, 0, 0 + .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_WRITE # Characteristics .set section_count, (. - section_table) / 40 #endif /* CONFIG_EFI_STUB */ @@ -286,12 +223,12 @@ sentinel: .byte 0xff, 0xff /* Used to detect broken loaders */ .globl hdr hdr: -setup_sects: .byte 0 /* Filled in by build.c */ + .byte setup_sects - 1 root_flags: .word ROOT_RDONLY -syssize: .long 0 /* Filled in by build.c */ +syssize: .long ZO__edata / 16 ram_size: .word 0 /* Obsolete */ vid_mode: .word SVGA_MODE -root_dev: .word 0 /* Filled in by build.c */ +root_dev: .word 0 /* Default to major/minor 0/0 */ boot_flag: .word 0xAA55 # offset 512, entry point @@ -579,9 +516,25 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr # define INIT_SIZE VO_INIT_SIZE #endif + .macro __handover_offset +#ifndef CONFIG_EFI_HANDOVER_PROTOCOL + .long 0 +#elif !defined(CONFIG_X86_64) + .long ZO_efi32_stub_entry +#else + /* Yes, this is really how we defined it :( */ + .long ZO_efi64_stub_entry - 0x200 +#ifdef CONFIG_EFI_MIXED + .if ZO_efi32_stub_entry != ZO_efi64_stub_entry - 0x200 + .error "32-bit and 64-bit EFI entry points do not match" + .endif +#endif +#endif + .endm + init_size: .long INIT_SIZE # kernel initialization size -handover_offset: .long 0 # Filled in by build.c -kernel_info_offset: .long 0 # Filled in by build.c +handover_offset: __handover_offset +kernel_info_offset: .long ZO_kernel_info # End of setup header ##################################################### diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index c4ea5258ab558f..9049f390d8347f 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -119,8 +119,8 @@ static void init_heap(void) char *stack_end; if (boot_params.hdr.loadflags & CAN_USE_HEAP) { - asm("leal %P1(%%esp),%0" - : "=r" (stack_end) : "i" (-STACK_SIZE)); + asm("leal %n1(%%esp),%0" + : "=r" (stack_end) : "i" (STACK_SIZE)); heap_end = (char *) ((size_t)boot_params.hdr.heap_end_ptr + 0x200); diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 49546c247ae25e..3a2d1360abb016 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -10,10 +10,11 @@ ENTRY(_start) SECTIONS { . = 0; - .bstext : { *(.bstext) } - .bsdata : { *(.bsdata) } + .bstext : { + *(.bstext) + . = 495; + } =0xffffffff - . = 495; .header : { *(.header) } .entrytext : { *(.entrytext) } .inittext : { *(.inittext) } @@ -23,6 +24,9 @@ SECTIONS .text : { *(.text .text.*) } .text32 : { *(.text32) } + .pecompat : { *(.pecompat) } + PROVIDE(pecompat_fsize = setup_size - pecompat_fstart); + . = ALIGN(16); .rodata : { *(.rodata*) } @@ -38,8 +42,10 @@ SECTIONS .signature : { setup_sig = .; LONG(0x5a5aaa55) - } + setup_size = ALIGN(ABSOLUTE(.), 4096); + setup_sects = ABSOLUTE(setup_size / 512); + } . = ALIGN(16); .bss : diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index bd247692b70174..10311d77c67f8f 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -40,10 +40,6 @@ typedef unsigned char u8; typedef unsigned short u16; typedef unsigned int u32; -#define DEFAULT_MAJOR_ROOT 0 -#define DEFAULT_MINOR_ROOT 0 -#define DEFAULT_ROOT_DEV (DEFAULT_MAJOR_ROOT << 8 | DEFAULT_MINOR_ROOT) - /* Minimal number of setup sectors */ #define SETUP_SECT_MIN 5 #define SETUP_SECT_MAX 64 @@ -51,22 +47,7 @@ typedef unsigned int u32; /* This must be large enough to hold the entire setup */ u8 buf[SETUP_SECT_MAX*512]; -#define PECOFF_RELOC_RESERVE 0x20 - -#ifdef CONFIG_EFI_MIXED -#define PECOFF_COMPAT_RESERVE 0x20 -#else -#define PECOFF_COMPAT_RESERVE 0x0 -#endif - -static unsigned long efi32_stub_entry; -static unsigned long efi64_stub_entry; -static unsigned long efi_pe_entry; -static unsigned long efi32_pe_entry; -static unsigned long kernel_info; -static unsigned long startup_64; -static unsigned long _ehead; -static unsigned long _end; +static unsigned long _edata; /*----------------------------------------------------------------------*/ @@ -152,180 +133,6 @@ static void usage(void) die("Usage: build setup system zoffset.h image"); } -#ifdef CONFIG_EFI_STUB - -static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset) -{ - unsigned int pe_header; - unsigned short num_sections; - u8 *section; - - pe_header = get_unaligned_le32(&buf[0x3c]); - num_sections = get_unaligned_le16(&buf[pe_header + 6]); - -#ifdef CONFIG_X86_32 - section = &buf[pe_header + 0xa8]; -#else - section = &buf[pe_header + 0xb8]; -#endif - - while (num_sections > 0) { - if (strncmp((char*)section, section_name, 8) == 0) { - /* section header size field */ - put_unaligned_le32(size, section + 0x8); - - /* section header vma field */ - put_unaligned_le32(vma, section + 0xc); - - /* section header 'size of initialised data' field */ - put_unaligned_le32(datasz, section + 0x10); - - /* section header 'file offset' field */ - put_unaligned_le32(offset, section + 0x14); - - break; - } - section += 0x28; - num_sections--; - } -} - -static void update_pecoff_section_header(char *section_name, u32 offset, u32 size) -{ - update_pecoff_section_header_fields(section_name, offset, size, size, offset); -} - -static void update_pecoff_setup_and_reloc(unsigned int size) -{ - u32 setup_offset = 0x200; - u32 reloc_offset = size - PECOFF_RELOC_RESERVE - PECOFF_COMPAT_RESERVE; -#ifdef CONFIG_EFI_MIXED - u32 compat_offset = reloc_offset + PECOFF_RELOC_RESERVE; -#endif - u32 setup_size = reloc_offset - setup_offset; - - update_pecoff_section_header(".setup", setup_offset, setup_size); - update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE); - - /* - * Modify .reloc section contents with a single entry. The - * relocation is applied to offset 10 of the relocation section. - */ - put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]); - put_unaligned_le32(10, &buf[reloc_offset + 4]); - -#ifdef CONFIG_EFI_MIXED - update_pecoff_section_header(".compat", compat_offset, PECOFF_COMPAT_RESERVE); - - /* - * Put the IA-32 machine type (0x14c) and the associated entry point - * address in the .compat section, so loaders can figure out which other - * execution modes this image supports. - */ - buf[compat_offset] = 0x1; - buf[compat_offset + 1] = 0x8; - put_unaligned_le16(0x14c, &buf[compat_offset + 2]); - put_unaligned_le32(efi32_pe_entry + size, &buf[compat_offset + 4]); -#endif -} - -static void update_pecoff_text(unsigned int text_start, unsigned int file_sz, - unsigned int init_sz) -{ - unsigned int pe_header; - unsigned int text_sz = file_sz - text_start; - unsigned int bss_sz = init_sz - file_sz; - - pe_header = get_unaligned_le32(&buf[0x3c]); - - /* - * The PE/COFF loader may load the image at an address which is - * misaligned with respect to the kernel_alignment field in the setup - * header. - * - * In order to avoid relocating the kernel to correct the misalignment, - * add slack to allow the buffer to be aligned within the declared size - * of the image. - */ - bss_sz += CONFIG_PHYSICAL_ALIGN; - init_sz += CONFIG_PHYSICAL_ALIGN; - - /* - * Size of code: Subtract the size of the first sector (512 bytes) - * which includes the header. - */ - put_unaligned_le32(file_sz - 512 + bss_sz, &buf[pe_header + 0x1c]); - - /* Size of image */ - put_unaligned_le32(init_sz, &buf[pe_header + 0x50]); - - /* - * Address of entry point for PE/COFF executable - */ - put_unaligned_le32(text_start + efi_pe_entry, &buf[pe_header + 0x28]); - - update_pecoff_section_header_fields(".text", text_start, text_sz + bss_sz, - text_sz, text_start); -} - -static int reserve_pecoff_reloc_section(int c) -{ - /* Reserve 0x20 bytes for .reloc section */ - memset(buf+c, 0, PECOFF_RELOC_RESERVE); - return PECOFF_RELOC_RESERVE; -} - -static void efi_stub_defaults(void) -{ - /* Defaults for old kernel */ -#ifdef CONFIG_X86_32 - efi_pe_entry = 0x10; -#else - efi_pe_entry = 0x210; - startup_64 = 0x200; -#endif -} - -static void efi_stub_entry_update(void) -{ - unsigned long addr = efi32_stub_entry; - -#ifdef CONFIG_EFI_HANDOVER_PROTOCOL -#ifdef CONFIG_X86_64 - /* Yes, this is really how we defined it :( */ - addr = efi64_stub_entry - 0x200; -#endif - -#ifdef CONFIG_EFI_MIXED - if (efi32_stub_entry != addr) - die("32-bit and 64-bit EFI entry points do not match\n"); -#endif -#endif - put_unaligned_le32(addr, &buf[0x264]); -} - -#else - -static inline void update_pecoff_setup_and_reloc(unsigned int size) {} -static inline void update_pecoff_text(unsigned int text_start, - unsigned int file_sz, - unsigned int init_sz) {} -static inline void efi_stub_defaults(void) {} -static inline void efi_stub_entry_update(void) {} - -static inline int reserve_pecoff_reloc_section(int c) -{ - return 0; -} -#endif /* CONFIG_EFI_STUB */ - -static int reserve_pecoff_compat_section(int c) -{ - /* Reserve 0x20 bytes for .compat section */ - memset(buf+c, 0, PECOFF_COMPAT_RESERVE); - return PECOFF_COMPAT_RESERVE; -} - /* * Parse zoffset.h and find the entry points. We could just #include zoffset.h * but that would mean tools/build would have to be rebuilt every time. It's @@ -354,14 +161,7 @@ static void parse_zoffset(char *fname) p = (char *)buf; while (p && *p) { - PARSE_ZOFS(p, efi32_stub_entry); - PARSE_ZOFS(p, efi64_stub_entry); - PARSE_ZOFS(p, efi_pe_entry); - PARSE_ZOFS(p, efi32_pe_entry); - PARSE_ZOFS(p, kernel_info); - PARSE_ZOFS(p, startup_64); - PARSE_ZOFS(p, _ehead); - PARSE_ZOFS(p, _end); + PARSE_ZOFS(p, _edata); p = strchr(p, '\n'); while (p && (*p == '\r' || *p == '\n')) @@ -371,17 +171,14 @@ static void parse_zoffset(char *fname) int main(int argc, char ** argv) { - unsigned int i, sz, setup_sectors, init_sz; + unsigned int i, sz, setup_sectors; int c; - u32 sys_size; struct stat sb; FILE *file, *dest; int fd; void *kernel; u32 crc = 0xffffffffUL; - efi_stub_defaults(); - if (argc != 5) usage(); parse_zoffset(argv[3]); @@ -403,72 +200,27 @@ int main(int argc, char ** argv) die("Boot block hasn't got boot flag (0xAA55)"); fclose(file); - c += reserve_pecoff_compat_section(c); - c += reserve_pecoff_reloc_section(c); - /* Pad unused space with zeros */ - setup_sectors = (c + 511) / 512; + setup_sectors = (c + 4095) / 4096; + setup_sectors *= 8; if (setup_sectors < SETUP_SECT_MIN) setup_sectors = SETUP_SECT_MIN; i = setup_sectors*512; memset(buf+c, 0, i-c); - update_pecoff_setup_and_reloc(i); - - /* Set the default root device */ - put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]); - /* Open and stat the kernel file */ fd = open(argv[2], O_RDONLY); if (fd < 0) die("Unable to open `%s': %m", argv[2]); if (fstat(fd, &sb)) die("Unable to stat `%s': %m", argv[2]); - sz = sb.st_size; + if (_edata != sb.st_size) + die("Unexpected file size `%s': %u != %u", argv[2], _edata, + sb.st_size); + sz = _edata - 4; kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0); if (kernel == MAP_FAILED) die("Unable to mmap '%s': %m", argv[2]); - /* Number of 16-byte paragraphs, including space for a 4-byte CRC */ - sys_size = (sz + 15 + 4) / 16; -#ifdef CONFIG_EFI_STUB - /* - * COFF requires minimum 32-byte alignment of sections, and - * adding a signature is problematic without that alignment. - */ - sys_size = (sys_size + 1) & ~1; -#endif - - /* Patch the setup code with the appropriate size parameters */ - buf[0x1f1] = setup_sectors-1; - put_unaligned_le32(sys_size, &buf[0x1f4]); - - init_sz = get_unaligned_le32(&buf[0x260]); -#ifdef CONFIG_EFI_STUB - /* - * The decompression buffer will start at ImageBase. When relocating - * the compressed kernel to its end, we must ensure that the head - * section does not get overwritten. The head section occupies - * [i, i + _ehead), and the destination is [init_sz - _end, init_sz). - * - * At present these should never overlap, because 'i' is at most 32k - * because of SETUP_SECT_MAX, '_ehead' is less than 1k, and the - * calculation of INIT_SIZE in boot/header.S ensures that - * 'init_sz - _end' is at least 64k. - * - * For future-proofing, increase init_sz if necessary. - */ - - if (init_sz - _end < i + _ehead) { - init_sz = (i + _ehead + _end + 4095) & ~4095; - put_unaligned_le32(init_sz, &buf[0x260]); - } -#endif - update_pecoff_text(setup_sectors * 512, i + (sys_size * 16), init_sz); - - efi_stub_entry_update(); - - /* Update kernel_info offset. */ - put_unaligned_le32(kernel_info, &buf[0x268]); crc = partial_crc32(buf, i, crc); if (fwrite(buf, 1, i, dest) != i) @@ -479,13 +231,6 @@ int main(int argc, char ** argv) if (fwrite(kernel, 1, sz, dest) != sz) die("Writing kernel failed"); - /* Add padding leaving 4 bytes for the checksum */ - while (sz++ < (sys_size*16) - 4) { - crc = partial_crc32_one('\0', crc); - if (fwrite("\0", 1, 1, dest) != 1) - die("Writing padding failed"); - } - /* Write the CRC */ put_unaligned_le32(crc, buf); if (fwrite(buf, 1, 4, dest) != 4) diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index eeec9986570ed0..ddd4efdc79d668 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -3,18 +3,22 @@ * Confidential Computing Platform Capability checks * * Copyright (C) 2021 Advanced Micro Devices, Inc. + * Copyright (C) 2024 Jason A. Donenfeld . All Rights Reserved. * * Author: Tom Lendacky */ #include #include +#include +#include +#include #include #include enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE; -static u64 cc_mask __ro_after_init; +u64 cc_mask __ro_after_init; static bool noinstr intel_cc_platform_has(enum cc_attr attr) { @@ -149,7 +153,39 @@ u64 cc_mkdec(u64 val) } EXPORT_SYMBOL_GPL(cc_mkdec); -__init void cc_set_mask(u64 mask) +__init void cc_random_init(void) { - cc_mask = mask; + /* + * The seed is 32 bytes (in units of longs), which is 256 bits, which + * is the security level that the RNG is targeting. + */ + unsigned long rng_seed[32 / sizeof(long)]; + size_t i, longs; + + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + return; + + /* + * Since the CoCo threat model includes the host, the only reliable + * source of entropy that can be neither observed nor manipulated is + * RDRAND. Usually, RDRAND failure is considered tolerable, but since + * CoCo guests have no other unobservable source of entropy, it's + * important to at least ensure the RNG gets some initial random seeds. + */ + for (i = 0; i < ARRAY_SIZE(rng_seed); i += longs) { + longs = arch_get_random_longs(&rng_seed[i], ARRAY_SIZE(rng_seed) - i); + + /* + * A zero return value means that the guest doesn't have RDRAND + * or the CPU is physically broken, and in both cases that + * means most crypto inside of the CoCo instance will be + * broken, defeating the purpose of CoCo in the first place. So + * just panic here because it's absolutely unsafe to continue + * executing. + */ + if (longs == 0) + panic("RDRAND is defective."); + } + add_device_randomness(rng_seed, sizeof(rng_seed)); + memzero_explicit(rng_seed, sizeof(rng_seed)); } diff --git a/arch/x86/coco/tdx/tdcall.S b/arch/x86/coco/tdx/tdcall.S index b193c0a1d8db38..2eca5f43734feb 100644 --- a/arch/x86/coco/tdx/tdcall.S +++ b/arch/x86/coco/tdx/tdcall.S @@ -195,6 +195,7 @@ SYM_FUNC_END(__tdx_module_call) xor %r10d, %r10d xor %r11d, %r11d xor %rdi, %rdi + xor %rsi, %rsi xor %rdx, %rdx /* Restore callee-saved GPRs as mandated by the x86_64 ABI */ diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 1d6b863c42b001..905ac8a3f7165c 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -10,9 +10,11 @@ #include #include #include +#include #include #include #include +#include /* MMIO direction */ #define EPT_READ 0 @@ -361,7 +363,6 @@ static bool mmio_read(int size, unsigned long addr, unsigned long *val) .r12 = size, .r13 = EPT_READ, .r14 = addr, - .r15 = *val, }; if (__tdx_hypercall_ret(&args)) @@ -405,6 +406,11 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) return -EINVAL; } + if (!fault_in_kernel_space(ve->gla)) { + WARN_ONCE(1, "Access to userspace address is not supported"); + return -EINVAL; + } + /* * Reject EPT violation #VEs that split pages. * diff --git a/arch/x86/crypto/nh-avx2-x86_64.S b/arch/x86/crypto/nh-avx2-x86_64.S index ef73a3ab87263e..791386d9a83aa1 100644 --- a/arch/x86/crypto/nh-avx2-x86_64.S +++ b/arch/x86/crypto/nh-avx2-x86_64.S @@ -154,5 +154,6 @@ SYM_TYPED_FUNC_START(nh_avx2) vpaddq T1, T0, T0 vpaddq T4, T0, T0 vmovdqu T0, (HASH) + vzeroupper RET SYM_FUNC_END(nh_avx2) diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index 44340a1139e0b7..959afa705e95ca 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -24,8 +24,17 @@ #include #include #include +#include #include +static const struct x86_cpu_id module_cpu_ids[] = { + X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL), + X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL), + X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids); + static int sha1_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha1_block_fn *sha1_xform) { @@ -301,6 +310,9 @@ static inline void unregister_sha1_ni(void) { } static int __init sha1_ssse3_mod_init(void) { + if (!x86_match_cpu(module_cpu_ids)) + return -ENODEV; + if (register_sha1_ssse3()) goto fail; diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 9918212faf914f..0bbec1c75cd0be 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -592,22 +592,22 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx) leaq K256+0*32(%rip), INP ## reuse INP as scratch reg vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 0*32+_XFER(%rsp, SRND) - FOUR_ROUNDS_AND_SCHED _XFER + 0*32 + FOUR_ROUNDS_AND_SCHED (_XFER + 0*32) leaq K256+1*32(%rip), INP vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 1*32+_XFER(%rsp, SRND) - FOUR_ROUNDS_AND_SCHED _XFER + 1*32 + FOUR_ROUNDS_AND_SCHED (_XFER + 1*32) leaq K256+2*32(%rip), INP vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 2*32+_XFER(%rsp, SRND) - FOUR_ROUNDS_AND_SCHED _XFER + 2*32 + FOUR_ROUNDS_AND_SCHED (_XFER + 2*32) leaq K256+3*32(%rip), INP vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 3*32+_XFER(%rsp, SRND) - FOUR_ROUNDS_AND_SCHED _XFER + 3*32 + FOUR_ROUNDS_AND_SCHED (_XFER + 3*32) add $4*32, SRND cmp $3*4*32, SRND @@ -618,12 +618,12 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx) leaq K256+0*32(%rip), INP vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 0*32+_XFER(%rsp, SRND) - DO_4ROUNDS _XFER + 0*32 + DO_4ROUNDS (_XFER + 0*32) leaq K256+1*32(%rip), INP vpaddd (INP, SRND), X1, XFER vmovdqa XFER, 1*32+_XFER(%rsp, SRND) - DO_4ROUNDS _XFER + 1*32 + DO_4ROUNDS (_XFER + 1*32) add $2*32, SRND vmovdqa X2, X0 @@ -651,8 +651,8 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx) xor SRND, SRND .align 16 .Lloop3: - DO_4ROUNDS _XFER + 0*32 + 16 - DO_4ROUNDS _XFER + 1*32 + 16 + DO_4ROUNDS (_XFER + 0*32 + 16) + DO_4ROUNDS (_XFER + 1*32 + 16) add $2*32, SRND cmp $4*4*32, SRND jb .Lloop3 @@ -716,6 +716,7 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx) popq %r13 popq %r12 popq %rbx + vzeroupper RET SYM_FUNC_END(sha256_transform_rorx) diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index 3a5f6be7dbba4e..d25235f0ccafc3 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -38,11 +38,20 @@ #include #include #include +#include #include asmlinkage void sha256_transform_ssse3(struct sha256_state *state, const u8 *data, int blocks); +static const struct x86_cpu_id module_cpu_ids[] = { + X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL), + X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL), + X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids); + static int _sha256_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha256_block_fn *sha256_xform) { @@ -366,6 +375,9 @@ static inline void unregister_sha256_ni(void) { } static int __init sha256_ssse3_mod_init(void) { + if (!x86_match_cpu(module_cpu_ids)) + return -ENODEV; + if (register_sha256_ssse3()) goto fail; diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index f08496cd68708f..24973f42c43ff4 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -680,6 +680,7 @@ SYM_TYPED_FUNC_START(sha512_transform_rorx) pop %r12 pop %rbx + vzeroupper RET SYM_FUNC_END(sha512_transform_rorx) diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 93c60c0c9d4a7a..e72dac092245a5 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -25,6 +25,7 @@ #include #endif +#include #include #include #include @@ -47,7 +48,7 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr) if (likely(unr < NR_syscalls)) { unr = array_index_nospec(unr, NR_syscalls); - regs->ax = sys_call_table[unr](regs); + regs->ax = x64_sys_call(regs, unr); return true; } return false; @@ -64,7 +65,7 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr) if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) { xnr = array_index_nospec(xnr, X32_NR_syscalls); - regs->ax = x32_sys_call_table[xnr](regs); + regs->ax = x32_sys_call(regs, xnr); return true; } return false; @@ -96,6 +97,10 @@ static __always_inline int syscall_32_enter(struct pt_regs *regs) return (int)regs->orig_ax; } +#ifdef CONFIG_IA32_EMULATION +bool __ia32_enabled __ro_after_init = true; +#endif + /* * Invoke a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. */ @@ -109,13 +114,102 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr) if (likely(unr < IA32_NR_syscalls)) { unr = array_index_nospec(unr, IA32_NR_syscalls); - regs->ax = ia32_sys_call_table[unr](regs); + regs->ax = ia32_sys_call(regs, unr); } else if (nr != -1) { regs->ax = __ia32_sys_ni_syscall(regs); } } -/* Handles int $0x80 */ +#ifdef CONFIG_IA32_EMULATION +static __always_inline bool int80_is_external(void) +{ + const unsigned int offs = (0x80 / 32) * 0x10; + const u32 bit = BIT(0x80 % 32); + + /* The local APIC on XENPV guests is fake */ + if (cpu_feature_enabled(X86_FEATURE_XENPV)) + return false; + + /* + * If vector 0x80 is set in the APIC ISR then this is an external + * interrupt. Either from broken hardware or injected by a VMM. + * + * Note: In guest mode this is only valid for secure guests where + * the secure module fully controls the vAPIC exposed to the guest. + */ + return apic_read(APIC_ISR + offs) & bit; +} + +/** + * do_int80_emulation - 32-bit legacy syscall C entry from asm + * + * This entry point can be used by 32-bit and 64-bit programs to perform + * 32-bit system calls. Instances of INT $0x80 can be found inline in + * various programs and libraries. It is also used by the vDSO's + * __kernel_vsyscall fallback for hardware that doesn't support a faster + * entry method. Restarted 32-bit system calls also fall back to INT + * $0x80 regardless of what instruction was originally used to do the + * system call. + * + * This is considered a slow path. It is not used by most libc + * implementations on modern hardware except during process startup. + * + * The arguments for the INT $0x80 based syscall are on stack in the + * pt_regs structure: + * eax: system call number + * ebx, ecx, edx, esi, edi, ebp: arg1 - arg 6 + */ +__visible noinstr void do_int80_emulation(struct pt_regs *regs) +{ + int nr; + + /* Kernel does not use INT $0x80! */ + if (unlikely(!user_mode(regs))) { + irqentry_enter(regs); + instrumentation_begin(); + panic("Unexpected external interrupt 0x80\n"); + } + + /* + * Establish kernel context for instrumentation, including for + * int80_is_external() below which calls into the APIC driver. + * Identical for soft and external interrupts. + */ + enter_from_user_mode(regs); + + instrumentation_begin(); + add_random_kstack_offset(); + + /* Validate that this is a soft interrupt to the extent possible */ + if (unlikely(int80_is_external())) + panic("Unexpected external interrupt 0x80\n"); + + /* + * The low level idtentry code pushed -1 into regs::orig_ax + * and regs::ax contains the syscall number. + * + * User tracing code (ptrace or signal handlers) might assume + * that the regs::orig_ax contains a 32-bit number on invoking + * a 32-bit syscall. + * + * Establish the syscall convention by saving the 32bit truncated + * syscall number in regs::orig_ax and by invalidating regs::ax. + */ + regs->orig_ax = regs->ax & GENMASK(31, 0); + regs->ax = -ENOSYS; + + nr = syscall_32_enter(regs); + + local_irq_enable(); + nr = syscall_enter_from_user_mode_work(regs, nr); + do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); + syscall_exit_to_user_mode(regs); +} +#else /* CONFIG_IA32_EMULATION */ + +/* Handles int $0x80 on a 32bit kernel */ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) { int nr = syscall_32_enter(regs); @@ -134,6 +228,7 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) instrumentation_end(); syscall_exit_to_user_mode(regs); } +#endif /* !CONFIG_IA32_EMULATION */ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) { diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index bfb7bcb362bcfc..34eca8015b64bc 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -6,6 +6,11 @@ #include #include #include +#include +#include +#include +#include +#include .pushsection .noinstr.text, "ax" @@ -14,9 +19,32 @@ SYM_FUNC_START(entry_ibpb) movl $PRED_CMD_IBPB, %eax xorl %edx, %edx wrmsr + + /* Make sure IBPB clears return stack preductions too. */ + FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_BUG_IBPB_NO_RET RET SYM_FUNC_END(entry_ibpb) /* For KVM */ EXPORT_SYMBOL_GPL(entry_ibpb); .popsection + +/* + * Define the VERW operand that is disguised as entry code so that + * it can be referenced with KPTI enabled. This ensure VERW can be + * used late in exit-to-user path after page tables are switched. + */ +.pushsection .entry.text, "ax" + +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_START_NOALIGN(mds_verw_sel) + UNWIND_HINT_UNDEFINED + ANNOTATE_NOENDBR + .word __KERNEL_DS +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_END(mds_verw_sel); +/* For KVM */ +EXPORT_SYMBOL_GPL(mds_verw_sel); + +.popsection + diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 6e6af42e044a20..3894acc54b79c4 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -875,6 +875,8 @@ SYM_FUNC_START(entry_SYSENTER_32) /* Now ready to switch the cr3 */ SWITCH_TO_USER_CR3 scratch_reg=%eax + /* Clobbers ZF */ + CLEAR_CPU_BUFFERS /* * Restore all flags except IF. (We restore IF separately because @@ -954,6 +956,7 @@ restore_all_switch_stack: /* Restore user state */ RESTORE_REGS pop=4 # skip orig_eax/error_code + CLEAR_CPU_BUFFERS .Lirq_return: /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -1166,6 +1169,7 @@ SYM_CODE_START(asm_exc_nmi) CHECK_AND_APPLY_ESPFIX RESTORE_ALL_NMI cr3_reg=%edi pop=4 + CLEAR_CPU_BUFFERS jmp .Lirq_return #ifdef CONFIG_X86_ESPFIX32 @@ -1207,6 +1211,7 @@ SYM_CODE_START(asm_exc_nmi) * 1 - orig_ax */ lss (1+5+6)*4(%esp), %esp # back to espfix stack + CLEAR_CPU_BUFFERS jmp .Lirq_return #endif SYM_CODE_END(asm_exc_nmi) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 43606de225117d..2192b6c33ea009 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -116,6 +116,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) /* clobbers %rax, make sure it is after saving the syscall nr */ IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY call do_syscall_64 /* returns with IRQs disabled */ @@ -166,22 +167,9 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) jne swapgs_restore_regs_and_return_to_usermode /* - * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot - * restore RF properly. If the slowpath sets it for whatever reason, we - * need to restore it correctly. - * - * SYSRET can restore TF, but unlike IRET, restoring TF results in a - * trap from userspace immediately after SYSRET. This would cause an - * infinite loop whenever #DB happens with register state that satisfies - * the opportunistic SYSRET conditions. For example, single-stepping - * this user code: - * - * movq $stuck_here, %rcx - * pushfq - * popq %r11 - * stuck_here: - * - * would never get past 'stuck_here'. + * SYSRET cannot restore RF. It can restore TF, but unlike IRET, + * restoring TF results in a trap from userspace immediately after + * SYSRET. */ testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11 jnz swapgs_restore_regs_and_return_to_usermode @@ -223,6 +211,7 @@ syscall_return_via_sysret: SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL) ANNOTATE_NOENDBR swapgs + CLEAR_CPU_BUFFERS sysretq SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR @@ -663,6 +652,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) /* Restore RDI. */ popq %rdi swapgs + CLEAR_CPU_BUFFERS jmp .Lnative_iret @@ -774,6 +764,8 @@ native_irq_return_ldt: */ popq %rax /* Restore user RAX */ + CLEAR_CPU_BUFFERS + /* * RSP now points to an ordinary IRET frame, except that the page * is read-only and RSP[31:16] are preloaded with the userspace @@ -1502,6 +1494,12 @@ nmi_restore: std movq $0, 5*8(%rsp) /* clear "NMI executing" */ + /* + * Skip CLEAR_CPU_BUFFERS here, since it only helps in rare cases like + * NMI in kernel after user state is restored. For an unprivileged user + * these conditions are hard to meet. + */ + /* * iretq reads the "iret" frame and exits the NMI stack in a * single instruction. We are returning to kernel mode, so this @@ -1516,12 +1514,13 @@ SYM_CODE_END(asm_exc_nmi) * This handles SYSCALL from 32-bit code. There is no way to program * MSRs to fully disable 32-bit SYSCALL. */ -SYM_CODE_START(ignore_sysret) +SYM_CODE_START(entry_SYSCALL32_ignore) UNWIND_HINT_END_OF_STACK ENDBR mov $-ENOSYS, %eax + CLEAR_CPU_BUFFERS sysretl -SYM_CODE_END(ignore_sysret) +SYM_CODE_END(entry_SYSCALL32_ignore) #endif .pushsection .text, "ax" @@ -1538,3 +1537,63 @@ SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead) call make_task_dead SYM_CODE_END(rewind_stack_and_make_dead) .popsection + +/* + * This sequence executes branches in order to remove user branch information + * from the branch history tracker in the Branch Predictor, therefore removing + * user influence on subsequent BTB lookups. + * + * It should be used on parts prior to Alder Lake. Newer parts should use the + * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being + * virtualized on newer hardware the VMM should protect against BHI attacks by + * setting BHI_DIS_S for the guests. + * + * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging + * and not clearing the branch history. The call tree looks like: + * + * call 1 + * call 2 + * call 2 + * call 2 + * call 2 + * call 2 + * ret + * ret + * ret + * ret + * ret + * ret + * + * This means that the stack is non-constant and ORC can't unwind it with %rsp + * alone. Therefore we unconditionally set up the frame pointer, which allows + * ORC to unwind properly. + * + * The alignment is for performance and not for safety, and may be safely + * refactored in the future if needed. + */ +SYM_FUNC_START(clear_bhb_loop) + push %rbp + mov %rsp, %rbp + movl $5, %ecx + ANNOTATE_INTRA_FUNCTION_CALL + call 1f + jmp 5f + .align 64, 0xcc + ANNOTATE_INTRA_FUNCTION_CALL +1: call 2f + RET + .align 64, 0xcc +2: movl $5, %eax +3: jmp 4f + nop +4: sub $1, %eax + jnz 3b + sub $1, %ecx + jnz 1b + RET +5: lfence + pop %rbp + RET +SYM_FUNC_END(clear_bhb_loop) +EXPORT_SYMBOL_GPL(clear_bhb_loop) +STACK_FRAME_NON_STANDARD(clear_bhb_loop) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 70150298f8bdf5..ebfccadf918cb4 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -90,9 +90,6 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) cld - IBRS_ENTER - UNTRAIN_RET - /* * SYSENTER doesn't filter flags, so we need to clear NT and AC * ourselves. To save a few cycles, we can check whether @@ -116,6 +113,16 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) jnz .Lsysenter_fix_flags .Lsysenter_flags_fixed: + /* + * CPU bugs mitigations mechanisms can call other functions. They + * should be invoked after making sure TF is cleared because + * single-step is ignored only for instructions inside the + * entry_SYSENTER_compat function. + */ + IBRS_ENTER + UNTRAIN_RET + CLEAR_BRANCH_HISTORY + movq %rsp, %rdi call do_SYSENTER_32 /* XEN PV guests always use IRET path */ @@ -209,6 +216,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY movq %rsp, %rdi call do_fast_syscall_32 @@ -271,6 +279,7 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL) xorl %r9d, %r9d xorl %r10d, %r10d swapgs + CLEAR_CPU_BUFFERS sysretl SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR @@ -278,78 +287,15 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) SYM_CODE_END(entry_SYSCALL_compat) /* - * 32-bit legacy system call entry. - * - * 32-bit x86 Linux system calls traditionally used the INT $0x80 - * instruction. INT $0x80 lands here. - * - * This entry point can be used by 32-bit and 64-bit programs to perform - * 32-bit system calls. Instances of INT $0x80 can be found inline in - * various programs and libraries. It is also used by the vDSO's - * __kernel_vsyscall fallback for hardware that doesn't support a faster - * entry method. Restarted 32-bit system calls also fall back to INT - * $0x80 regardless of what instruction was originally used to do the - * system call. - * - * This is considered a slow path. It is not used by most libc - * implementations on modern hardware except during process startup. - * - * Arguments: - * eax system call number - * ebx arg1 - * ecx arg2 - * edx arg3 - * esi arg4 - * edi arg5 - * ebp arg6 + * int 0x80 is used by 32 bit mode as a system call entry. Normally idt entries + * point to C routines, however since this is a system call interface the branch + * history needs to be scrubbed to protect against BHI attacks, and that + * scrubbing needs to take place in assembly code prior to entering any C + * routines. */ -SYM_CODE_START(entry_INT80_compat) - UNWIND_HINT_ENTRY - ENDBR - /* - * Interrupts are off on entry. - */ - ASM_CLAC /* Do this early to minimize exposure */ - ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV - - /* - * User tracing code (ptrace or signal handlers) might assume that - * the saved RAX contains a 32-bit number when we're invoking a 32-bit - * syscall. Just in case the high bits are nonzero, zero-extend - * the syscall number. (This could almost certainly be deleted - * with no ill effects.) - */ - movl %eax, %eax - - /* switch to thread stack expects orig_ax and rdi to be pushed */ - pushq %rax /* pt_regs->orig_ax */ - - /* Need to switch before accessing the thread stack. */ - SWITCH_TO_KERNEL_CR3 scratch_reg=%rax - - /* In the Xen PV case we already run on the thread stack. */ - ALTERNATIVE "", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV - - movq %rsp, %rax - movq PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp - - pushq 5*8(%rax) /* regs->ss */ - pushq 4*8(%rax) /* regs->rsp */ - pushq 3*8(%rax) /* regs->eflags */ - pushq 2*8(%rax) /* regs->cs */ - pushq 1*8(%rax) /* regs->ip */ - pushq 0*8(%rax) /* regs->orig_ax */ -.Lint80_keep_stack: - - PUSH_AND_CLEAR_REGS rax=$-ENOSYS - UNWIND_HINT_REGS - - cld - - IBRS_ENTER - UNTRAIN_RET - - movq %rsp, %rdi - call do_int80_syscall_32 - jmp swapgs_restore_regs_and_return_to_usermode -SYM_CODE_END(entry_INT80_compat) +SYM_CODE_START(int80_emulation) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + CLEAR_BRANCH_HISTORY + jmp do_int80_emulation +SYM_CODE_END(int80_emulation) diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 8cfc9bc73e7f8b..c2235bae17ef66 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -18,8 +18,25 @@ #include #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ +#ifdef CONFIG_X86_32 #define __SYSCALL(nr, sym) __ia32_##sym, - -__visible const sys_call_ptr_t ia32_sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include }; +#undef __SYSCALL +#endif + +#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs); + +long ia32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include + default: return __ia32_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index be120eec1fc9f9..33b3f09e6f151e 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -11,8 +11,23 @@ #include #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ #define __SYSCALL(nr, sym) __x64_##sym, - -asmlinkage const sys_call_ptr_t sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include }; +#undef __SYSCALL + +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); + +long x64_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include + default: return __x64_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c index bdd0e03a1265d2..03de4a93213182 100644 --- a/arch/x86/entry/syscall_x32.c +++ b/arch/x86/entry/syscall_x32.c @@ -11,8 +11,12 @@ #include #undef __SYSCALL -#define __SYSCALL(nr, sym) __x64_##sym, +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); -asmlinkage const sys_call_ptr_t x32_sys_call_table[] = { -#include +long x32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include + default: return __x64_sys_ni_syscall(regs); + } }; diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 2d0b1bd866ead6..38db5ef2329f3c 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -420,7 +420,7 @@ 412 i386 utimensat_time64 sys_utimensat 413 i386 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 i386 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 i386 io_pgetevents_time64 sys_io_pgetevents +416 i386 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 i386 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 i386 mq_timedsend_time64 sys_mq_timedsend 419 i386 mq_timedreceive_time64 sys_mq_timedreceive diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 6a1821bd7d5e9b..c197efd829228c 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -190,31 +190,4 @@ GCOV_PROFILE := n quiet_cmd_vdso_and_check = VDSO $@ cmd_vdso_and_check = $(cmd_vdso); $(cmd_vdso_check) -# -# Install the unstripped copies of vdso*.so. If our toolchain supports -# build-id, install .build-id links as well. -# -quiet_cmd_vdso_install = INSTALL $(@:install_%=%) -define cmd_vdso_install - cp $< "$(MODLIB)/vdso/$(@:install_%=%)"; \ - if readelf -n $< |grep -q 'Build ID'; then \ - buildid=`readelf -n $< |grep 'Build ID' |sed -e 's/^.*Build ID: \(.*\)$$/\1/'`; \ - first=`echo $$buildid | cut -b-2`; \ - last=`echo $$buildid | cut -b3-`; \ - mkdir -p "$(MODLIB)/vdso/.build-id/$$first"; \ - ln -sf "../../$(@:install_%=%)" "$(MODLIB)/vdso/.build-id/$$first/$$last.debug"; \ - fi -endef - -vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%) - -$(MODLIB)/vdso: FORCE - @mkdir -p $(MODLIB)/vdso - -$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso - $(call cmd,vdso_install) - -PHONY += vdso_install $(vdso_img_insttargets) -vdso_install: $(vdso_img_insttargets) - clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so* diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index e0ca8120aea876..1245000a8792fd 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -98,11 +98,6 @@ static int addr_to_vsyscall_nr(unsigned long addr) static bool write_ok_or_segv(unsigned long ptr, size_t size) { - /* - * XXX: if access_ok, get_user, and put_user handled - * sig_on_uaccess_err, this could go away. - */ - if (!access_ok((void __user *)ptr, size)) { struct thread_struct *thread = ¤t->thread; @@ -120,10 +115,8 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size) bool emulate_vsyscall(unsigned long error_code, struct pt_regs *regs, unsigned long address) { - struct task_struct *tsk; unsigned long caller; int vsyscall_nr, syscall_nr, tmp; - int prev_sig_on_uaccess_err; long ret; unsigned long orig_dx; @@ -172,8 +165,6 @@ bool emulate_vsyscall(unsigned long error_code, goto sigsegv; } - tsk = current; - /* * Check for access_ok violations and find the syscall nr. * @@ -234,12 +225,8 @@ bool emulate_vsyscall(unsigned long error_code, goto do_ret; /* skip requested */ /* - * With a real vsyscall, page faults cause SIGSEGV. We want to - * preserve that behavior to make writing exploits harder. + * With a real vsyscall, page faults cause SIGSEGV. */ - prev_sig_on_uaccess_err = current->thread.sig_on_uaccess_err; - current->thread.sig_on_uaccess_err = 1; - ret = -EFAULT; switch (vsyscall_nr) { case 0: @@ -262,23 +249,12 @@ bool emulate_vsyscall(unsigned long error_code, break; } - current->thread.sig_on_uaccess_err = prev_sig_on_uaccess_err; - check_fault: if (ret == -EFAULT) { /* Bad news -- userspace fed a bad pointer to a vsyscall. */ warn_bad_vsyscall(KERN_INFO, regs, "vsyscall fault (exploit attempt?)"); - - /* - * If we failed to generate a signal for any reason, - * generate one here. (This should be impossible.) - */ - if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) && - !sigismember(&tsk->pending.signal, SIGSEGV))) - goto sigsegv; - - return true; /* Don't emulate the ret. */ + goto sigsegv; } regs->ax = ret; diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index e24976593a298a..8ed10366c4a27b 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -250,7 +250,7 @@ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] = /* * AMD Performance Monitor Family 17h and later: */ -static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = +static const u64 amd_zen1_perfmon_event_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, @@ -262,10 +262,24 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187, }; +static const u64 amd_zen2_perfmon_event_map[PERF_COUNT_HW_MAX] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_CACHE_MISSES] = 0x0964, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a9, +}; + static u64 amd_pmu_event_map(int hw_event) { - if (boot_cpu_data.x86 >= 0x17) - return amd_f17h_perfmon_event_map[hw_event]; + if (cpu_feature_enabled(X86_FEATURE_ZEN2) || boot_cpu_data.x86 >= 0x19) + return amd_zen2_perfmon_event_map[hw_event]; + + if (cpu_feature_enabled(X86_FEATURE_ZEN1)) + return amd_zen1_perfmon_event_map[hw_event]; return amd_perfmon_event_map[hw_event]; } @@ -604,7 +618,6 @@ static void amd_pmu_cpu_dead(int cpu) kfree(cpuhw->lbr_sel); cpuhw->lbr_sel = NULL; - amd_pmu_cpu_reset(cpu); if (!x86_pmu.amd_nb_constraints) return; @@ -905,8 +918,8 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) if (!status) goto done; - /* Read branch records before unfreezing */ - if (status & GLOBAL_STATUS_LBRS_FROZEN) { + /* Read branch records */ + if (x86_pmu.lbr_nr) { amd_pmu_lbr_read(); status &= ~GLOBAL_STATUS_LBRS_FROZEN; } diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c index eb31f850841a89..5149830c7c4fa6 100644 --- a/arch/x86/events/amd/lbr.c +++ b/arch/x86/events/amd/lbr.c @@ -173,9 +173,11 @@ void amd_pmu_lbr_read(void) /* * Check if a branch has been logged; if valid = 0, spec = 0 - * then no branch was recorded + * then no branch was recorded; if reserved = 1 then an + * erroneous branch was recorded (see Erratum 1452) */ - if (!entry.to.split.valid && !entry.to.split.spec) + if ((!entry.to.split.valid && !entry.to.split.spec) || + entry.to.split.reserved) continue; perf_clear_branch_entry_bitfields(br + out); @@ -400,10 +402,12 @@ void amd_pmu_lbr_enable_all(void) wrmsrl(MSR_AMD64_LBR_SELECT, lbr_select); } - rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); - rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); + if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) { + rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); + wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + } - wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg | DBG_EXTN_CFG_LBRV2EN); } @@ -416,10 +420,12 @@ void amd_pmu_lbr_disable_all(void) return; rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); - rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); - wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN); - wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + + if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) { + rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); + wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + } } __init int amd_pmu_lbr_init(void) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 185f902e5f2859..150a365b4fbc89 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -41,6 +41,8 @@ #include #include #include +#include +#include #include "perf_event.h" @@ -1644,6 +1646,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) while (++i < cpuc->n_events) { cpuc->event_list[i-1] = cpuc->event_list[i]; cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; + cpuc->assign[i-1] = cpuc->assign[i]; } cpuc->event_constraint[i-1] = NULL; --cpuc->n_events; @@ -2546,6 +2549,7 @@ static ssize_t set_attr_rdpmc(struct device *cdev, struct device_attribute *attr, const char *buf, size_t count) { + static DEFINE_MUTEX(rdpmc_mutex); unsigned long val; ssize_t ret; @@ -2559,6 +2563,8 @@ static ssize_t set_attr_rdpmc(struct device *cdev, if (x86_pmu.attr_rdpmc_broken) return -ENOTSUPP; + guard(mutex)(&rdpmc_mutex); + if (val != x86_pmu.attr_rdpmc) { /* * Changing into or out of never available or always available, @@ -2812,6 +2818,46 @@ static unsigned long get_segment_base(unsigned int segment) return get_desc_base(desc); } +#ifdef CONFIG_UPROBES +/* + * Heuristic-based check if uprobe is installed at the function entry. + * + * Under assumption of user code being compiled with frame pointers, + * `push %rbp/%ebp` is a good indicator that we indeed are. + * + * Similarly, `endbr64` (assuming 64-bit mode) is also a common pattern. + * If we get this wrong, captured stack trace might have one extra bogus + * entry, but the rest of stack trace will still be meaningful. + */ +static bool is_uprobe_at_func_entry(struct pt_regs *regs) +{ + struct arch_uprobe *auprobe; + + if (!current->utask) + return false; + + auprobe = current->utask->auprobe; + if (!auprobe) + return false; + + /* push %rbp/%ebp */ + if (auprobe->insn[0] == 0x55) + return true; + + /* endbr64 (64-bit only) */ + if (user_64bit_mode(regs) && is_endbr(*(u32 *)auprobe->insn)) + return true; + + return false; +} + +#else +static bool is_uprobe_at_func_entry(struct pt_regs *regs) +{ + return false; +} +#endif /* CONFIG_UPROBES */ + #ifdef CONFIG_IA32_EMULATION #include @@ -2823,6 +2869,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent unsigned long ss_base, cs_base; struct stack_frame_ia32 frame; const struct stack_frame_ia32 __user *fp; + u32 ret_addr; if (user_64bit_mode(regs)) return 0; @@ -2832,6 +2879,12 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent fp = compat_ptr(ss_base + regs->bp); pagefault_disable(); + + /* see perf_callchain_user() below for why we do this */ + if (is_uprobe_at_func_entry(regs) && + !get_user(ret_addr, (const u32 __user *)regs->sp)) + perf_callchain_store(entry, ret_addr); + while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; @@ -2860,6 +2913,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs { struct stack_frame frame; const struct stack_frame __user *fp; + unsigned long ret_addr; if (perf_guest_state()) { /* TODO: We don't support guest os callchain now */ @@ -2883,6 +2937,19 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs return; pagefault_disable(); + + /* + * If we are called from uprobe handler, and we are indeed at the very + * entry to user function (which is normally a `push %rbp` instruction, + * under assumption of application being compiled with frame pointers), + * we should read return address from *regs->sp before proceeding + * to follow frame pointers, otherwise we'll skip immediate caller + * as %rbp is not yet setup. + */ + if (is_uprobe_at_func_entry(regs) && + !get_user(ret_addr, (const unsigned long __user *)regs->sp)) + perf_callchain_store(entry, ret_addr); + while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index fa355d3658a652..688550e336ce17 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4062,12 +4062,17 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data) u64 pebs_mask = cpuc->pebs_enabled & x86_pmu.pebs_capable; int global_ctrl, pebs_enable; + /* + * In addition to obeying exclude_guest/exclude_host, remove bits being + * used for PEBS when running a guest, because PEBS writes to virtual + * addresses (not physical addresses). + */ *nr = 0; global_ctrl = (*nr)++; arr[global_ctrl] = (struct perf_guest_switch_msr){ .msr = MSR_CORE_PERF_GLOBAL_CTRL, .host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask, - .guest = intel_ctrl & (~cpuc->intel_ctrl_host_mask | ~pebs_mask), + .guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask & ~pebs_mask, }; if (!x86_pmu.pebs) @@ -4460,6 +4465,25 @@ static u8 adl_get_hybrid_cpu_type(void) return hybrid_big; } +static inline bool erratum_hsw11(struct perf_event *event) +{ + return (event->hw.config & INTEL_ARCH_EVENT_MASK) == + X86_CONFIG(.event=0xc0, .umask=0x01); +} + +/* + * The HSW11 requires a period larger than 100 which is the same as the BDM11. + * A minimum period of 128 is enforced as well for the INST_RETIRED.ALL. + * + * The message 'interrupt took too long' can be observed on any counter which + * was armed with a period < 32 and two events expired in the same NMI. + * A minimum period of 32 is enforced for the rest of the events. + */ +static void hsw_limit_period(struct perf_event *event, s64 *left) +{ + *left = max(*left, erratum_hsw11(event) ? 128 : 32); +} + /* * Broadwell: * @@ -4477,8 +4501,7 @@ static u8 adl_get_hybrid_cpu_type(void) */ static void bdw_limit_period(struct perf_event *event, s64 *left) { - if ((event->hw.config & INTEL_ARCH_EVENT_MASK) == - X86_CONFIG(.event=0xc0, .umask=0x01)) { + if (erratum_hsw11(event)) { if (*left < 128) *left = 128; *left &= ~0x3fULL; @@ -6387,6 +6410,7 @@ __init int intel_pmu_init(void) x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; + x86_pmu.limit_period = hsw_limit_period; x86_pmu.lbr_double_abort = true; extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? hsw_format_attr : nhm_format_attr; diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 96fffb2d521d2a..cc6609cbfc8dad 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -80,7 +80,7 @@ * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL + * KBL,CML,ICL,TGL,RKL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 @@ -89,8 +89,7 @@ * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 - * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL,RPL,MTL + * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 @@ -582,9 +581,7 @@ static const struct cstate_model adl_cstates __initconst = { .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | BIT(PERF_CSTATE_PKG_C3_RES) | BIT(PERF_CSTATE_PKG_C6_RES) | - BIT(PERF_CSTATE_PKG_C7_RES) | BIT(PERF_CSTATE_PKG_C8_RES) | - BIT(PERF_CSTATE_PKG_C9_RES) | BIT(PERF_CSTATE_PKG_C10_RES), }; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index eb8dd8b8a1e860..b592bed9ebcc46 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1236,11 +1236,11 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu = event->pmu; /* - * Make sure we get updated with the first PEBS - * event. It will trigger also during removal, but - * that does not hurt: + * Make sure we get updated with the first PEBS event. + * During removal, ->pebs_data_cfg is still valid for + * the last PEBS event. Don't clear it. */ - if (cpuc->n_pebs == 1) + if ((cpuc->n_pebs == 1) && add) cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW; if (needed_cb != pebs_needs_sched_cb(cpuc)) { @@ -1830,8 +1830,12 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, set_linear_ip(regs, basic->ip); regs->flags = PERF_EFLAGS_EXACT; - if ((sample_type & PERF_SAMPLE_WEIGHT_STRUCT) && (x86_pmu.flags & PMU_FL_RETIRE_LATENCY)) - data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK; + if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) { + if (x86_pmu.flags & PMU_FL_RETIRE_LATENCY) + data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK; + else + data->weight.var3_w = 0; + } /* * The record for MEMINFO is in front of GP diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 42a55794004a7a..4110246aba12c3 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -877,7 +877,7 @@ static void pt_update_head(struct pt *pt) */ static void *pt_buffer_region(struct pt_buffer *buf) { - return phys_to_virt(TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT); + return phys_to_virt((phys_addr_t)TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT); } /** @@ -989,7 +989,7 @@ pt_topa_entry_for_page(struct pt_buffer *buf, unsigned int pg) * order allocations, there shouldn't be many of these. */ list_for_each_entry(topa, &buf->tables, list) { - if (topa->offset + topa->size > pg << PAGE_SHIFT) + if (topa->offset + topa->size > (unsigned long)pg << PAGE_SHIFT) goto found; } @@ -1602,6 +1602,7 @@ static void pt_event_stop(struct perf_event *event, int mode) * see comment in intel_pt_interrupt(). */ WRITE_ONCE(pt->handle_nmi, 0); + barrier(); pt_config_stop(event); @@ -1653,11 +1654,10 @@ static long pt_event_snapshot_aux(struct perf_event *event, return 0; /* - * Here, handle_nmi tells us if the tracing is on + * There is no PT interrupt in this mode, so stop the trace and it will + * remain stopped while the buffer is copied. */ - if (READ_ONCE(pt->handle_nmi)) - pt_config_stop(event); - + pt_config_stop(event); pt_read_offset(buf); pt_update_head(pt); @@ -1669,11 +1669,10 @@ static long pt_event_snapshot_aux(struct perf_event *event, ret = perf_output_copy_aux(&pt->handle, handle, from, to); /* - * If the tracing was on when we turned up, restart it. - * Compiler barrier not needed as we couldn't have been - * preempted by anything that touches pt->handle_nmi. + * Here, handle_nmi tells us if the tracing was on. + * If the tracing was on, restart it. */ - if (pt->handle_nmi) + if (READ_ONCE(pt->handle_nmi)) pt_config_start(event); return ret; diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h index 96906a62aacdad..f5e46c04c145d0 100644 --- a/arch/x86/events/intel/pt.h +++ b/arch/x86/events/intel/pt.h @@ -33,8 +33,8 @@ struct topa_entry { u64 rsvd2 : 1; u64 size : 4; u64 rsvd3 : 2; - u64 base : 36; - u64 rsvd4 : 16; + u64 base : 40; + u64 rsvd4 : 12; }; /* TSC to Core Crystal Clock Ratio */ diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 8250f0f59c2bbe..a8f11e60b98794 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -461,6 +461,7 @@ #define SPR_UBOX_DID 0x3250 /* SPR CHA */ +#define SPR_CHA_EVENT_MASK_EXT 0xffffffff #define SPR_CHA_PMON_CTL_TID_EN (1 << 16) #define SPR_CHA_PMON_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ SPR_CHA_PMON_CTL_TID_EN) @@ -477,6 +478,7 @@ DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext4, umask, "config:8-15,32-55"); +DEFINE_UNCORE_FORMAT_ATTR(umask_ext5, umask, "config:8-15,32-63"); DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); @@ -5596,7 +5598,7 @@ static int discover_upi_topology(struct intel_uncore_type *type, int ubox_did, i struct pci_dev *ubox = NULL; struct pci_dev *dev = NULL; u32 nid, gid; - int i, idx, ret = -EPERM; + int i, idx, lgc_pkg, ret = -EPERM; struct intel_uncore_topology *upi; unsigned int devfn; @@ -5614,8 +5616,13 @@ static int discover_upi_topology(struct intel_uncore_type *type, int ubox_did, i for (i = 0; i < 8; i++) { if (nid != GIDNIDMAP(gid, i)) continue; + lgc_pkg = topology_phys_to_logical_pkg(i); + if (lgc_pkg < 0) { + ret = -EPERM; + goto err; + } for (idx = 0; idx < type->num_boxes; idx++) { - upi = &type->topology[nid][idx]; + upi = &type->topology[lgc_pkg][idx]; devfn = PCI_DEVFN(dev_link0 + idx, ICX_UPI_REGS_ADDR_FUNCTION); dev = pci_get_domain_bus_and_slot(pci_domain_nr(ubox->bus), ubox->bus->number, @@ -5626,6 +5633,7 @@ static int discover_upi_topology(struct intel_uncore_type *type, int ubox_did, i goto err; } } + break; } } err: @@ -5948,7 +5956,7 @@ static struct intel_uncore_ops spr_uncore_chabox_ops = { static struct attribute *spr_uncore_cha_formats_attr[] = { &format_attr_event.attr, - &format_attr_umask_ext4.attr, + &format_attr_umask_ext5.attr, &format_attr_tid_en2.attr, &format_attr_edge.attr, &format_attr_inv.attr, @@ -5984,7 +5992,7 @@ ATTRIBUTE_GROUPS(uncore_alias); static struct intel_uncore_type spr_uncore_chabox = { .name = "cha", .event_mask = SPR_CHA_PMON_EVENT_MASK, - .event_mask_ext = SPR_RAW_EVENT_MASK_EXT, + .event_mask_ext = SPR_CHA_EVENT_MASK_EXT, .num_shared_regs = 1, .constraints = skx_uncore_chabox_constraints, .ops = &spr_uncore_chabox_ops, diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 21556ad87f4ba8..d1e2d12279e268 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -34,7 +35,6 @@ #include #include -int hyperv_init_cpuhp; u64 hv_current_partition_id = ~0ull; EXPORT_SYMBOL_GPL(hv_current_partition_id); @@ -286,15 +286,31 @@ static int hv_cpu_die(unsigned int cpu) static int __init hv_pci_init(void) { - int gen2vm = efi_enabled(EFI_BOOT); + bool gen2vm = efi_enabled(EFI_BOOT); /* - * For Generation-2 VM, we exit from pci_arch_init() by returning 0. - * The purpose is to suppress the harmless warning: + * A Generation-2 VM doesn't support legacy PCI/PCIe, so both + * raw_pci_ops and raw_pci_ext_ops are NULL, and pci_subsys_init() -> + * pcibios_init() doesn't call pcibios_resource_survey() -> + * e820__reserve_resources_late(); as a result, any emulated persistent + * memory of E820_TYPE_PRAM (12) via the kernel parameter + * memmap=nn[KMG]!ss is not added into iomem_resource and hence can't be + * detected by register_e820_pmem(). Fix this by directly calling + * e820__reserve_resources_late() here: e820__reserve_resources_late() + * depends on e820__reserve_resources(), which has been called earlier + * from setup_arch(). Note: e820__reserve_resources_late() also adds + * any memory of E820_TYPE_PMEM (7) into iomem_resource, and + * acpi_nfit_register_region() -> acpi_nfit_insert_resource() -> + * region_intersects() returns REGION_INTERSECTS, so the memory of + * E820_TYPE_PMEM won't get added twice. + * + * We return 0 here so that pci_arch_init() won't print the warning: * "PCI: Fatal: No config space access function found" */ - if (gen2vm) + if (gen2vm) { + e820__reserve_resources_late(); return 0; + } /* For Generation-1 VM, we'll proceed in pci_arch_init(). */ return 1; @@ -590,8 +606,6 @@ void __init hyperv_init(void) register_syscore_ops(&hv_syscore_ops); - hyperv_init_cpuhp = cpuhp; - if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID) hv_get_partition_id(); @@ -620,7 +634,7 @@ void __init hyperv_init(void) clean_guest_os_id: wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0); - cpuhp_remove_state(cpuhp); + cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE); free_ghcb_page: free_percpu(hv_ghcb_pg); free_vp_assist_page: diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 999f5ac82fe900..c2f78fabc865bb 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -12,10 +12,16 @@ #include #include #include +#include <../kernel/smpboot.h> extern struct boot_params boot_params; static struct real_mode_header hv_vtl_real_mode_header; +static bool __init hv_vtl_msi_ext_dest_id(void) +{ + return true; +} + void __init hv_vtl_init_platform(void) { pr_info("Linux runs in Hyper-V Virtual Trust Level\n"); @@ -38,6 +44,8 @@ void __init hv_vtl_init_platform(void) x86_platform.legacy.warm_reset = 0; x86_platform.legacy.reserve_bios_regions = 0; x86_platform.legacy.devices.pnpbios = 0; + + x86_init.hyper.msi_ext_dest_id = hv_vtl_msi_ext_dest_id; } static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc) @@ -57,7 +65,7 @@ static void hv_vtl_ap_entry(void) ((secondary_startup_64_fn)secondary_startup_64)(&boot_params, &boot_params); } -static int hv_vtl_bringup_vcpu(u32 target_vp_index, u64 eip_ignored) +static int hv_vtl_bringup_vcpu(u32 target_vp_index, int cpu, u64 eip_ignored) { u64 status; int ret = 0; @@ -71,7 +79,9 @@ static int hv_vtl_bringup_vcpu(u32 target_vp_index, u64 eip_ignored) struct ldttss_desc *ldt; struct desc_struct *gdt; - u64 rsp = current->thread.sp; + struct task_struct *idle = idle_thread_get(cpu); + u64 rsp = (unsigned long)idle->thread.sp; + u64 rip = (u64)&hv_vtl_ap_entry; native_store_gdt(&gdt_ptr); @@ -198,7 +208,15 @@ static int hv_vtl_apicid_to_vp_id(u32 apic_id) static int hv_vtl_wakeup_secondary_cpu(int apicid, unsigned long start_eip) { - int vp_id; + int vp_id, cpu; + + /* Find the logical CPU for the APIC ID */ + for_each_present_cpu(cpu) { + if (arch_match_cpu_phys_id(cpu, apicid)) + break; + } + if (cpu >= nr_cpu_ids) + return -EINVAL; pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid); vp_id = hv_vtl_apicid_to_vp_id(apicid); @@ -212,7 +230,7 @@ static int hv_vtl_wakeup_secondary_cpu(int apicid, unsigned long start_eip) return -EINVAL; } - return hv_vtl_bringup_vcpu(vp_id, start_eip); + return hv_vtl_bringup_vcpu(vp_id, cpu, start_eip); } int __init hv_vtl_early_init(void) diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index c8a7fc23f63c67..529c36a98d9ea0 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -16,6 +16,9 @@ #include #include #include +#include + +#include #ifdef CONFIG_ACPI_APEI # include @@ -127,6 +130,17 @@ static inline void arch_acpi_set_proc_cap_bits(u32 *cap) if (!cpu_has(c, X86_FEATURE_MWAIT) || boot_option_idle_override == IDLE_NOMWAIT) *cap &= ~(ACPI_PROC_CAP_C_C1_FFH | ACPI_PROC_CAP_C_C2C3_FFH); + + if (xen_initial_domain()) { + /* + * When Linux is running as Xen dom0, the hypervisor is the + * entity in charge of the processor power management, and so + * Xen needs to check the OS capabilities reported in the + * processor capabilities buffer matches what the hypervisor + * driver supports. + */ + xen_sanitize_proc_cap_bits(cap); + } } static inline bool acpi_has_cpu_in_madt(void) @@ -151,6 +165,14 @@ void acpi_generic_reduced_hw_init(void); void x86_default_set_root_pointer(u64 addr); u64 x86_default_get_root_pointer(void); +#ifdef CONFIG_XEN_PV +/* A Xen PV domain needs a special acpi_os_ioremap() handling. */ +extern void __iomem * (*acpi_os_ioremap)(acpi_physical_address phys, + acpi_size size); +void __iomem *x86_acpi_os_ioremap(acpi_physical_address phys, acpi_size size); +#define acpi_os_ioremap acpi_os_ioremap +#endif + #else /* !CONFIG_ACPI */ #define acpi_lapic 0 diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 9c4da699e11aff..cb9ce0f9e78e05 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -58,7 +58,7 @@ #define ANNOTATE_IGNORE_ALTERNATIVE \ "999:\n\t" \ ".pushsection .discard.ignore_alts\n\t" \ - ".long 999b - .\n\t" \ + ".long 999b\n\t" \ ".popsection\n\t" /* @@ -288,10 +288,10 @@ static inline int alternatives_text_reserved(void *start, void *end) * Otherwise, if CPU has feature1, newinstr1 is used. * Otherwise, oldinstr is used. */ -#define alternative_input_2(oldinstr, newinstr1, ft_flags1, newinstr2, \ - ft_flags2, input...) \ - asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, \ - newinstr2, ft_flags2) \ +#define alternative_input_2(oldinstr, newinstr1, ft_flags1, newinstr2, \ + ft_flags2, input...) \ + asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, \ + newinstr2, ft_flags2) \ : : "i" (0), ## input) /* Like alternative_input, but with a single output argument */ @@ -301,7 +301,7 @@ static inline int alternatives_text_reserved(void *start, void *end) /* Like alternative_io, but for replacing a direct call with another one. */ #define alternative_call(oldfunc, newfunc, ft_flags, output, input...) \ - asm_inline volatile (ALTERNATIVE("call %P[old]", "call %P[new]", ft_flags) \ + asm_inline volatile (ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags) \ : output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input) /* @@ -310,12 +310,12 @@ static inline int alternatives_text_reserved(void *start, void *end) * Otherwise, if CPU has feature1, function1 is used. * Otherwise, old function is used. */ -#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \ - output, input...) \ - asm_inline volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", ft_flags1,\ - "call %P[new2]", ft_flags2) \ - : output, ASM_CALL_CONSTRAINT \ - : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ +#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \ + output, input...) \ + asm_inline volatile (ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1, \ + "call %c[new2]", ft_flags2) \ + : output, ASM_CALL_CONSTRAINT \ + : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ [new2] "i" (newfunc2), ## input) /* @@ -352,7 +352,7 @@ static inline int alternatives_text_reserved(void *start, void *end) .macro ANNOTATE_IGNORE_ALTERNATIVE .Lannotate_\@: .pushsection .discard.ignore_alts - .long .Lannotate_\@ - . + .long .Lannotate_\@ .popsection .endm diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 5af4ec1a0f71cf..33aa0c31c21cf1 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -13,6 +13,7 @@ #include #include #include +#include #define ARCH_APICTIMER_STOPS_ON_C3 1 @@ -96,7 +97,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v) static inline u32 native_apic_mem_read(u32 reg) { - return *((volatile u32 *)(APIC_BASE + reg)); + return readl((void __iomem *)(APIC_BASE + reg)); } static inline void native_apic_mem_eoi(void) diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index b1a98fa38828e2..0e82074517f6b7 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -13,6 +13,7 @@ #include #include #include +#include #ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index fbcfec4dc4ccd7..ca8eed1d496ab4 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -113,6 +113,20 @@ #endif +#ifndef __ASSEMBLY__ +#ifndef __pic__ +static __always_inline __pure void *rip_rel_ptr(void *p) +{ + asm("leaq %c1(%%rip), %0" : "=r"(p) : "i"(p)); + + return p; +} +#define RIP_REL_REF(var) (*(typeof(&(var)))rip_rel_ptr(&(var))) +#else +#define RIP_REL_REF(var) (var) +#endif +#endif + /* * Macros to generate condition code outputs from inline assembly, * The output operand must be type "bool". diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 3486d91b8595f1..d510405e4e1de2 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -24,7 +24,7 @@ typedef struct { #ifdef CONFIG_X86_CMPXCHG64 #define __alternative_atomic64(f, g, out, in...) \ - asm volatile("call %P[func]" \ + asm volatile("call %c[func]" \ : out : [func] "i" (atomic64_##g##_cx8), ## in) #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8) diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 35389b2af88ee8..d0795b5fab46ad 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -79,24 +79,9 @@ do { \ #define __smp_mb__before_atomic() do { } while (0) #define __smp_mb__after_atomic() do { } while (0) -#include +/* Writing to CR3 provides a full memory barrier in switch_mm(). */ +#define smp_mb__after_switch_mm() do { } while (0) -/* - * Make previous memory operations globally visible before - * a WRMSR. - * - * MFENCE makes writes visible, but only affects load/store - * instructions. WRMSR is unfortunately not a load/store - * instruction and is unaffected by MFENCE. The LFENCE ensures - * that the WRMSR is not reordered. - * - * Most WRMSRs are full serializing instructions themselves and - * do not require this barrier. This is only required for the - * IA32_TSC_DEADLINE and X2APIC MSRs. - */ -static inline void weak_wrmsr_fence(void) -{ - asm volatile("mfence; lfence" : : : "memory"); -} +#include #endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index b3a7cfb0d99e01..c945c893c52e0a 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -81,6 +81,7 @@ #ifndef __ASSEMBLY__ extern unsigned int output_len; +extern const unsigned long kernel_text_size; extern const unsigned long kernel_total_size; unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 44b08b53ab32fc..c1d6cd58f80940 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -62,7 +62,7 @@ static __always_inline u128 arch_cmpxchg128_local(volatile u128 *ptr, u128 old, asm volatile(_lock "cmpxchg16b %[ptr]" \ CC_SET(e) \ : CC_OUT(e) (ret), \ - [ptr] "+m" (*ptr), \ + [ptr] "+m" (*(_ptr)), \ "+a" (o.low), "+d" (o.high) \ : "b" (n.low), "c" (n.high) \ : "memory"); \ diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h index 6ae2d16a7613b7..c72b3553081c3c 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_COCO_H #define _ASM_X86_COCO_H +#include #include enum cc_vendor { @@ -13,10 +14,19 @@ enum cc_vendor { extern enum cc_vendor cc_vendor; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM -void cc_set_mask(u64 mask); +extern u64 cc_mask; + +static inline void cc_set_mask(u64 mask) +{ + RIP_REL_REF(cc_mask) = mask; +} + u64 cc_mkenc(u64 val); u64 cc_mkdec(u64 val); +void cc_random_init(void); #else +static const u64 cc_mask = 0; + static inline u64 cc_mkenc(u64 val) { return val; @@ -26,6 +36,7 @@ static inline u64 cc_mkdec(u64 val) { return val; } +static inline void cc_random_init(void) { } #endif #endif /* _ASM_X86_COCO_H */ diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index eb8fcede9e3bf4..e8e3dbe7f17306 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -2,6 +2,39 @@ #ifndef _ASM_X86_CPU_DEVICE_ID #define _ASM_X86_CPU_DEVICE_ID +/* + * Can't use because it generates expressions that + * cannot be used in structure initializers. Bitfield construction + * here must match the union in struct cpuinfo_86: + * union { + * struct { + * __u8 x86_model; + * __u8 x86; + * __u8 x86_vendor; + * __u8 x86_reserved; + * }; + * __u32 x86_vfm; + * }; + */ +#define VFM_MODEL_BIT 0 +#define VFM_FAMILY_BIT 8 +#define VFM_VENDOR_BIT 16 +#define VFM_RSVD_BIT 24 + +#define VFM_MODEL_MASK GENMASK(VFM_FAMILY_BIT - 1, VFM_MODEL_BIT) +#define VFM_FAMILY_MASK GENMASK(VFM_VENDOR_BIT - 1, VFM_FAMILY_BIT) +#define VFM_VENDOR_MASK GENMASK(VFM_RSVD_BIT - 1, VFM_VENDOR_BIT) + +#define VFM_MODEL(vfm) (((vfm) & VFM_MODEL_MASK) >> VFM_MODEL_BIT) +#define VFM_FAMILY(vfm) (((vfm) & VFM_FAMILY_MASK) >> VFM_FAMILY_BIT) +#define VFM_VENDOR(vfm) (((vfm) & VFM_VENDOR_MASK) >> VFM_VENDOR_BIT) + +#define VFM_MAKE(_vendor, _family, _model) ( \ + ((_model) << VFM_MODEL_BIT) | \ + ((_family) << VFM_FAMILY_BIT) | \ + ((_vendor) << VFM_VENDOR_BIT) \ +) + /* * Declare drivers belonging to specific x86 CPUs * Similar in spirit to pci_device_id and related PCI functions @@ -20,6 +53,9 @@ #define X86_CENTAUR_FAM6_C7_D 0xd #define X86_CENTAUR_FAM6_NANO 0xf +/* x86_cpu_id::flags */ +#define X86_CPU_ID_FLAG_ENTRY_VALID BIT(0) + #define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) /** * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching @@ -46,6 +82,18 @@ .model = _model, \ .steppings = _steppings, \ .feature = _feature, \ + .flags = X86_CPU_ID_FLAG_ENTRY_VALID, \ + .driver_data = (unsigned long) _data \ +} + +#define X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \ + _steppings, _feature, _data) { \ + .vendor = _vendor, \ + .family = _family, \ + .model = _model, \ + .steppings = _steppings, \ + .feature = _feature, \ + .flags = X86_CPU_ID_FLAG_ENTRY_VALID, \ .driver_data = (unsigned long) _data \ } @@ -164,6 +212,56 @@ X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, INTEL_FAM6_##model, \ steppings, X86_FEATURE_ANY, data) +/** + * X86_MATCH_VFM - Match encoded vendor/family/model + * @vfm: Encoded 8-bits each for vendor, family, model + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is cast to unsigned long internally. + * + * Stepping and feature are set to wildcards + */ +#define X86_MATCH_VFM(vfm, data) \ + X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ + VFM_VENDOR(vfm), \ + VFM_FAMILY(vfm), \ + VFM_MODEL(vfm), \ + X86_STEPPING_ANY, X86_FEATURE_ANY, data) + +/** + * X86_MATCH_VFM_STEPPINGS - Match encoded vendor/family/model/stepping + * @vfm: Encoded 8-bits each for vendor, family, model + * @steppings: Bitmask of steppings to match + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is cast to unsigned long internally. + * + * feature is set to wildcard + */ +#define X86_MATCH_VFM_STEPPINGS(vfm, steppings, data) \ + X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ + VFM_VENDOR(vfm), \ + VFM_FAMILY(vfm), \ + VFM_MODEL(vfm), \ + steppings, X86_FEATURE_ANY, data) + +/** + * X86_MATCH_VFM_FEATURE - Match encoded vendor/family/model/feature + * @vfm: Encoded 8-bits each for vendor, family, model + * @feature: A X86_FEATURE bit + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is cast to unsigned long internally. + * + * Steppings is set to wildcard + */ +#define X86_MATCH_VFM_FEATURE(vfm, feature, data) \ + X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ + VFM_VENDOR(vfm), \ + VFM_FAMILY(vfm), \ + VFM_MODEL(vfm), \ + X86_STEPPING_ANY, feature, data) + /* * Match specific microcode revisions. * diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index a26bebbdff87ed..3508f3fc928d4d 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -33,6 +33,8 @@ enum cpuid_leafs CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, + CPUID_LNX_5, + NR_CPUID_WORDS, }; #define X86_CAP_FMT_NUM "%d:%d" @@ -91,8 +93,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -116,8 +119,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ @@ -168,8 +172,8 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); */ static __always_inline bool _static_cpu_has(u16 bit) { - asm_volatile_goto( - ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]") + asm goto( + ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]") ".pushsection .altinstr_aux,\"ax\"\n" "6:\n" " testb %[bitnum]," _ASM_RIP(%P[cap_byte]) "\n" diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 58cb9495e40f42..55d18eef6775a6 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 21 /* N 32-bit words worth of info */ +#define NCAPINTS 22 /* N 32-bit words worth of info */ #define NBUGINTS 2 /* N 32-bit bug flags */ /* @@ -97,7 +97,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ +#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ @@ -216,9 +216,9 @@ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ #define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */ #define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ -#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier without a guaranteed RSB flush */ #define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_ZEN (7*32+28) /* "" CPU based on Zen microarchitecture */ +#define X86_FEATURE_ZEN ( 7*32+28) /* "" Generic flag for all Zen and newer */ #define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ #define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ #define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */ @@ -308,10 +308,14 @@ #define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ #define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ #define X86_FEATURE_USER_SHSTK (11*32+23) /* Shadow stack support for user mode applications */ - #define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ #define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ #define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */ +#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */ +#define X86_FEATURE_ZEN2 (11*32+28) /* "" CPU based on Zen2 microarchitecture */ +#define X86_FEATURE_ZEN3 (11*32+29) /* "" CPU based on Zen3 microarchitecture */ +#define X86_FEATURE_ZEN4 (11*32+30) /* "" CPU based on Zen4 microarchitecture */ +#define X86_FEATURE_ZEN1 (11*32+31) /* "" CPU based on Zen1 microarchitecture */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ @@ -343,6 +347,7 @@ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ #define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */ #define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ +#define X86_FEATURE_AMD_IBPB_RET (13*32+30) /* "" IBPB clears return address predictor */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ @@ -452,6 +457,18 @@ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ #define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ +/* + * Extended auxiliary flags: Linux defined - for features scattered in various + * CPUID levels like 0x80000022, etc and Linux defined features. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */ +#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */ +#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ +#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ +#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ + /* * BUG word(s) */ @@ -498,4 +515,7 @@ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ +#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ +#define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 702d93fdd10e8d..88fcf08458d9cd 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -143,6 +143,7 @@ #define DISABLED_MASK18 (DISABLE_IBT) #define DISABLED_MASK19 0 #define DISABLED_MASK20 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define DISABLED_MASK21 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index c4555b269a1b24..a050d329e34bfd 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -410,7 +410,6 @@ extern int __init efi_memmap_alloc(unsigned int num_entries, struct efi_memory_map_data *data); extern void __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags); -#define __efi_memmap_free __efi_memmap_free extern int __init efi_memmap_install(struct efi_memory_map_data *data); extern int __init efi_memmap_split_count(efi_memory_desc_t *md, diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index ce8f50192ae3e4..fb2809b20b0ac4 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -73,25 +73,21 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, #endif /* - * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), - * but not enough for x86 stack utilization comfort. To keep - * reasonable stack head room, reduce the maximum offset to 8 bits. - * - * The actual entropy will be further reduced by the compiler when - * applying stack alignment constraints (see cc_stack_align4/8 in + * This value will get limited by KSTACK_OFFSET_MAX(), which is 10 + * bits. The actual entropy will be further reduced by the compiler + * when applying stack alignment constraints (see cc_stack_align4/8 in * arch/x86/Makefile), which will remove the 3 (x86_64) or 2 (ia32) * low bits from any entropy chosen here. * - * Therefore, final stack offset entropy will be 5 (x86_64) or - * 6 (ia32) bits. + * Therefore, final stack offset entropy will be 7 (x86_64) or + * 8 (ia32) bits. */ - choose_random_kstack_offset(rdtsc() & 0xFF); + choose_random_kstack_offset(rdtsc()); } #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare static __always_inline void arch_exit_to_user_mode(void) { - mds_user_clear_cpu_buffers(); amd_clear_divider(); } #define arch_exit_to_user_mode arch_exit_to_user_mode diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h index 611fa41711affd..eccc75bc9c4f3d 100644 --- a/arch/x86/include/asm/fpu/signal.h +++ b/arch/x86/include/asm/fpu/signal.h @@ -29,7 +29,7 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long fpu__get_fpstate_size(void); -extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); +extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size, u32 pkru); extern void fpu__clear_user_states(struct fpu *fpu); extern bool fpu__restore_sig(void __user *buf, int ia32_frame); diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index eb810074f1e745..fd5fb43d920b44 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -589,6 +589,13 @@ struct fpu_state_config { * even without XSAVE support, i.e. legacy features FP + SSE */ u64 legacy_features; + /* + * @independent_features: + * + * Features that are supported by XSAVES, but not managed as part of + * the FPU core, such as LBR + */ + u64 independent_features; }; /* FPU state configuration information */ diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 66837b8c67f1a9..f2e245741afc2c 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -63,7 +63,11 @@ extern u64 arch_irq_stat(void); #define local_softirq_pending_ref pcpu_hot.softirq_pending #if IS_ENABLED(CONFIG_KVM_INTEL) -static inline void kvm_set_cpu_l1tf_flush_l1d(void) +/* + * This function is called from noinstr interrupt contexts + * and must be inlined to not get instrumentation. + */ +static __always_inline void kvm_set_cpu_l1tf_flush_l1d(void) { __this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 1); } @@ -78,7 +82,7 @@ static __always_inline bool kvm_get_cpu_l1tf_flush_l1d(void) return __this_cpu_read(irq_stat.kvm_cpu_l1tf_flush_l1d); } #else /* !IS_ENABLED(CONFIG_KVM_INTEL) */ -static inline void kvm_set_cpu_l1tf_flush_l1d(void) { } +static __always_inline void kvm_set_cpu_l1tf_flush_l1d(void) { } #endif /* IS_ENABLED(CONFIG_KVM_INTEL) */ #endif /* _ASM_X86_HARDIRQ_H */ diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index fada857f0a1edf..9805629479d968 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -68,6 +68,27 @@ extern void ia32_pick_mmap_layout(struct mm_struct *mm); #endif -#endif /* CONFIG_IA32_EMULATION */ +extern bool __ia32_enabled; + +static inline bool ia32_enabled(void) +{ + return __ia32_enabled; +} + +static inline void ia32_disable(void) +{ + __ia32_enabled = false; +} + +#else /* !CONFIG_IA32_EMULATION */ + +static inline bool ia32_enabled(void) +{ + return IS_ENABLED(CONFIG_X86_32); +} + +static inline void ia32_disable(void) {} + +#endif #endif /* _ASM_X86_IA32_H */ diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 05fd175cec7d5c..10603e185111d5 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -13,15 +13,18 @@ #include +typedef void (*idtentry_t)(struct pt_regs *regs); + /** * DECLARE_IDTENTRY - Declare functions for simple IDT entry points * No error code pushed by hardware * @vector: Vector number (ignored for C) * @func: Function name of the entry point * - * Declares three functions: + * Declares four functions: * - The ASM entry point: asm_##func * - The XEN PV trap entry point: xen_##func (maybe unused) + * - The C handler called from the FRED event dispatcher (maybe unused) * - The C handler called from the ASM entry point * * Note: This is the C variant of DECLARE_IDTENTRY(). As the name says it @@ -31,6 +34,7 @@ #define DECLARE_IDTENTRY(vector, func) \ asmlinkage void asm_##func(void); \ asmlinkage void xen_asm_##func(void); \ + void fred_##func(struct pt_regs *regs); \ __visible void func(struct pt_regs *regs) /** @@ -137,6 +141,17 @@ static __always_inline void __##func(struct pt_regs *regs, \ #define DEFINE_IDTENTRY_RAW(func) \ __visible noinstr void func(struct pt_regs *regs) +/** + * DEFINE_FREDENTRY_RAW - Emit code for raw FRED entry points + * @func: Function name of the entry point + * + * @func is called from the FRED event dispatcher with interrupts disabled. + * + * See @DEFINE_IDTENTRY_RAW for further details. + */ +#define DEFINE_FREDENTRY_RAW(func) \ +noinstr void fred_##func(struct pt_regs *regs) + /** * DECLARE_IDTENTRY_RAW_ERRORCODE - Declare functions for raw IDT entry points * Error code pushed by hardware @@ -197,8 +212,8 @@ __visible noinstr void func(struct pt_regs *regs, \ irqentry_state_t state = irqentry_enter(regs); \ u32 vector = (u32)(u8)error_code; \ \ + kvm_set_cpu_l1tf_flush_l1d(); \ instrumentation_begin(); \ - kvm_set_cpu_l1tf_flush_l1d(); \ run_irq_on_irqstack_cond(__##func, regs, vector); \ instrumentation_end(); \ irqentry_exit(regs, state); \ @@ -233,17 +248,27 @@ static noinline void __##func(struct pt_regs *regs, u32 vector) #define DEFINE_IDTENTRY_SYSVEC(func) \ static void __##func(struct pt_regs *regs); \ \ +static __always_inline void instr_##func(struct pt_regs *regs) \ +{ \ + run_sysvec_on_irqstack_cond(__##func, regs); \ +} \ + \ __visible noinstr void func(struct pt_regs *regs) \ { \ irqentry_state_t state = irqentry_enter(regs); \ \ + kvm_set_cpu_l1tf_flush_l1d(); \ instrumentation_begin(); \ - kvm_set_cpu_l1tf_flush_l1d(); \ - run_sysvec_on_irqstack_cond(__##func, regs); \ + instr_##func (regs); \ instrumentation_end(); \ irqentry_exit(regs, state); \ } \ \ +void fred_##func(struct pt_regs *regs) \ +{ \ + instr_##func (regs); \ +} \ + \ static noinline void __##func(struct pt_regs *regs) /** @@ -260,19 +285,29 @@ static noinline void __##func(struct pt_regs *regs) #define DEFINE_IDTENTRY_SYSVEC_SIMPLE(func) \ static __always_inline void __##func(struct pt_regs *regs); \ \ +static __always_inline void instr_##func(struct pt_regs *regs) \ +{ \ + __irq_enter_raw(); \ + __##func (regs); \ + __irq_exit_raw(); \ +} \ + \ __visible noinstr void func(struct pt_regs *regs) \ { \ irqentry_state_t state = irqentry_enter(regs); \ \ + kvm_set_cpu_l1tf_flush_l1d(); \ instrumentation_begin(); \ - __irq_enter_raw(); \ - kvm_set_cpu_l1tf_flush_l1d(); \ - __##func (regs); \ - __irq_exit_raw(); \ + instr_##func (regs); \ instrumentation_end(); \ irqentry_exit(regs, state); \ } \ \ +void fred_##func(struct pt_regs *regs) \ +{ \ + instr_##func (regs); \ +} \ + \ static __always_inline void __##func(struct pt_regs *regs) /** @@ -410,15 +445,18 @@ __visible noinstr void func(struct pt_regs *regs, \ /* C-Code mapping */ #define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_RAW #define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_RAW +#define DEFINE_FREDENTRY_NMI DEFINE_FREDENTRY_RAW #ifdef CONFIG_X86_64 #define DECLARE_IDTENTRY_MCE DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE_USER DEFINE_IDTENTRY_NOIST +#define DEFINE_FREDENTRY_MCE DEFINE_FREDENTRY_RAW #define DECLARE_IDTENTRY_DEBUG DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG_USER DEFINE_IDTENTRY_NOIST +#define DEFINE_FREDENTRY_DEBUG DEFINE_FREDENTRY_RAW #endif #else /* !__ASSEMBLY__ */ @@ -569,6 +607,10 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_UD, exc_invalid_op); DECLARE_IDTENTRY_RAW(X86_TRAP_BP, exc_int3); DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF, exc_page_fault); +#if defined(CONFIG_IA32_EMULATION) +DECLARE_IDTENTRY_RAW(IA32_SYSCALL_VECTOR, int80_emulation); +#endif + #ifdef CONFIG_X86_MCE #ifdef CONFIG_X86_64 DECLARE_IDTENTRY_MCE(X86_TRAP_MC, exc_machine_check); @@ -651,23 +693,36 @@ DECLARE_IDTENTRY(RESCHEDULE_VECTOR, sysvec_reschedule_ipi); DECLARE_IDTENTRY_SYSVEC(REBOOT_VECTOR, sysvec_reboot); DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_SINGLE_VECTOR, sysvec_call_function_single); DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_VECTOR, sysvec_call_function); +#else +# define fred_sysvec_reschedule_ipi NULL +# define fred_sysvec_reboot NULL +# define fred_sysvec_call_function_single NULL +# define fred_sysvec_call_function NULL #endif #ifdef CONFIG_X86_LOCAL_APIC # ifdef CONFIG_X86_MCE_THRESHOLD DECLARE_IDTENTRY_SYSVEC(THRESHOLD_APIC_VECTOR, sysvec_threshold); +# else +# define fred_sysvec_threshold NULL # endif # ifdef CONFIG_X86_MCE_AMD DECLARE_IDTENTRY_SYSVEC(DEFERRED_ERROR_VECTOR, sysvec_deferred_error); +# else +# define fred_sysvec_deferred_error NULL # endif # ifdef CONFIG_X86_THERMAL_VECTOR DECLARE_IDTENTRY_SYSVEC(THERMAL_APIC_VECTOR, sysvec_thermal); +# else +# define fred_sysvec_thermal NULL # endif # ifdef CONFIG_IRQ_WORK DECLARE_IDTENTRY_SYSVEC(IRQ_WORK_VECTOR, sysvec_irq_work); +# else +# define fred_sysvec_irq_work NULL # endif #endif @@ -675,12 +730,16 @@ DECLARE_IDTENTRY_SYSVEC(IRQ_WORK_VECTOR, sysvec_irq_work); DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_VECTOR, sysvec_kvm_posted_intr_ipi); DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_WAKEUP_VECTOR, sysvec_kvm_posted_intr_wakeup_ipi); DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR, sysvec_kvm_posted_intr_nested_ipi); +#else +# define fred_sysvec_kvm_posted_intr_ipi NULL +# define fred_sysvec_kvm_posted_intr_wakeup_ipi NULL +# define fred_sysvec_kvm_posted_intr_nested_ipi NULL #endif #if IS_ENABLED(CONFIG_HYPERV) DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback); DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment); -DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0); +DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0); #endif #if IS_ENABLED(CONFIG_ACRN_GUEST) diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 5f1d3c421f6860..cc9ccf61b6bd11 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_INIT_H #define _ASM_X86_INIT_H +#define __head __section(".head.text") + struct x86_mapping_info { void *(*alloc_pgt_page)(void *); /* allocate buf for page table */ void *context; /* context for alloc_pgt_page */ diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 798183867d7896..b71ad173f8776f 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -100,7 +100,7 @@ } #define ASM_CALL_ARG0 \ - "call %P[__func] \n" \ + "call %c[__func] \n" \ ASM_REACHABLE #define ASM_CALL_ARG1 \ diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h index 800ffce0db29e3..6b4d36c9516557 100644 --- a/arch/x86/include/asm/irq_work.h +++ b/arch/x86/include/asm/irq_work.h @@ -9,7 +9,6 @@ static inline bool arch_irq_work_has_interrupt(void) { return boot_cpu_has(X86_FEATURE_APIC); } -extern void arch_irq_work_raise(void); #else static inline bool arch_irq_work_has_interrupt(void) { diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 071572e23d3a06..cbbef32517f004 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -24,7 +24,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:" + asm goto("1:" "jmp %l[l_yes] # objtool NOPs this \n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (2 | branch) : : l_yes); @@ -38,7 +38,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto("1:" + asm goto("1:" ".byte " __stringify(BYTES_NOP5) "\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); @@ -52,7 +52,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, co static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto("1:" + asm goto("1:" "jmp %l[l_yes]\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); diff --git a/arch/x86/include/asm/kmsan.h b/arch/x86/include/asm/kmsan.h index 8fa6ac0e2d7665..d91b37f5b4bb45 100644 --- a/arch/x86/include/asm/kmsan.h +++ b/arch/x86/include/asm/kmsan.h @@ -64,6 +64,7 @@ static inline bool kmsan_virt_addr_valid(void *addr) { unsigned long x = (unsigned long)addr; unsigned long y = x - __START_KERNEL_map; + bool ret; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { @@ -79,7 +80,21 @@ static inline bool kmsan_virt_addr_valid(void *addr) return false; } - return pfn_valid(x >> PAGE_SHIFT); + /* + * pfn_valid() relies on RCU, and may call into the scheduler on exiting + * the critical section. However, this would result in recursion with + * KMSAN. Therefore, disable preemption here, and re-enable preemption + * below while suppressing reschedules to avoid recursion. + * + * Note, this sacrifices occasionally breaking scheduling guarantees. + * Although, a kernel compiled with KMSAN has already given up on any + * performance guarantees due to being heavily instrumented. + */ + preempt_disable(); + ret = pfn_valid(x >> PAGE_SHIFT); + preempt_enable_no_resched(); + + return ret; } #endif /* !MODULE */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index e3054e3e46d52d..9b419f0de713cc 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -108,6 +108,7 @@ KVM_X86_OP_OPTIONAL(vcpu_blocking) KVM_X86_OP_OPTIONAL(vcpu_unblocking) KVM_X86_OP_OPTIONAL(pi_update_irte) KVM_X86_OP_OPTIONAL(pi_start_assignment) +KVM_X86_OP_OPTIONAL(apicv_pre_state_restore) KVM_X86_OP_OPTIONAL(apicv_post_state_restore) KVM_X86_OP_OPTIONAL_RET0(dy_apicv_has_pending_interrupt) KVM_X86_OP_OPTIONAL(set_hv_timer) diff --git a/arch/x86/include/asm/kvm-x86-pmu-ops.h b/arch/x86/include/asm/kvm-x86-pmu-ops.h index 6c98f4bb4228ba..058bc636356a11 100644 --- a/arch/x86/include/asm/kvm-x86-pmu-ops.h +++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h @@ -22,7 +22,7 @@ KVM_X86_PMU_OP(get_msr) KVM_X86_PMU_OP(set_msr) KVM_X86_PMU_OP(refresh) KVM_X86_PMU_OP(init) -KVM_X86_PMU_OP(reset) +KVM_X86_PMU_OP_OPTIONAL(reset) KVM_X86_PMU_OP_OPTIONAL(deliver_pmi) KVM_X86_PMU_OP_OPTIONAL(cleanup) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 70d139406bc80d..257bf2e71d0605 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -828,6 +828,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; struct kvm_hypervisor_cpuid kvm_cpuid; + bool is_amd_compatible; /* * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly @@ -1708,6 +1709,7 @@ struct kvm_x86_ops { int (*pi_update_irte)(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void (*pi_start_assignment)(struct kvm *kvm); + void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); @@ -1756,7 +1758,7 @@ struct kvm_x86_nested_ops { bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector, u32 error_code); int (*check_events)(struct kvm_vcpu *vcpu); - bool (*has_events)(struct kvm_vcpu *vcpu); + bool (*has_events)(struct kvm_vcpu *vcpu, bool for_injection); void (*triple_fault)(struct kvm_vcpu *vcpu); int (*get_state)(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 473b16d73b4710..76081a34fc231b 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -15,7 +15,8 @@ #include #include -#include +#include +struct boot_params; #ifdef CONFIG_X86_MEM_ENCRYPT void __init mem_encrypt_init(void); @@ -45,8 +46,8 @@ void __init sme_unmap_bootdata(char *real_mode_data); void __init sme_early_init(void); void __init sev_setup_arch(void); -void __init sme_encrypt_kernel(struct boot_params *bp); -void __init sme_enable(struct boot_params *bp); +void sme_encrypt_kernel(struct boot_params *bp); +void sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); @@ -57,6 +58,11 @@ void __init mem_encrypt_free_decrypted_mem(void); void __init sev_es_init_vc_handling(void); +static inline u64 sme_get_me_mask(void) +{ + return RIP_REL_REF(sme_me_mask); +} + #define __bss_decrypted __section(".bss..decrypted") #else /* !CONFIG_AMD_MEM_ENCRYPT */ @@ -75,8 +81,8 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { } static inline void __init sme_early_init(void) { } static inline void __init sev_setup_arch(void) { } -static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } -static inline void __init sme_enable(struct boot_params *bp) { } +static inline void sme_encrypt_kernel(struct boot_params *bp) { } +static inline void sme_enable(struct boot_params *bp) { } static inline void sev_es_init_vc_handling(void) { } @@ -89,6 +95,8 @@ early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool en static inline void mem_encrypt_free_decrypted_mem(void) { } +static inline u64 sme_get_me_mask(void) { return 0; } + #define __bss_decrypted #endif /* CONFIG_AMD_MEM_ENCRYPT */ @@ -106,11 +114,6 @@ void add_encrypt_protection_map(void); extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; -static inline u64 sme_get_me_mask(void) -{ - return sme_me_mask; -} - #endif /* __ASSEMBLY__ */ #endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 896445edc6a8e9..ec95d6e9f1682c 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -40,7 +40,6 @@ static inline unsigned char hv_get_nmi_reason(void) } #if IS_ENABLED(CONFIG_HYPERV) -extern int hyperv_init_cpuhp; extern bool hyperv_paravisor_present; extern void *hv_hypercall_pg; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index b37abb55e948b7..24b7bd255e9830 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -50,10 +50,13 @@ #define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ #define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) +#define SPEC_CTRL_BHI_DIS_S_SHIFT 10 /* Disable Branch History Injection behavior */ +#define SPEC_CTRL_BHI_DIS_S BIT(SPEC_CTRL_BHI_DIS_S_SHIFT) /* A mask for bits which the kernel toggles when controlling mitigations */ #define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \ - | SPEC_CTRL_RRSBA_DIS_S) + | SPEC_CTRL_RRSBA_DIS_S \ + | SPEC_CTRL_BHI_DIS_S) #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -152,6 +155,10 @@ * are restricted to targets in * kernel. */ +#define ARCH_CAP_BHI_NO BIT(20) /* + * CPU is not affected by Branch + * History Injection. + */ #define ARCH_CAP_PBRSB_NO BIT(24) /* * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. @@ -165,6 +172,14 @@ * CPU is not vulnerable to Gather * Data Sampling (GDS). */ +#define ARCH_CAP_RFDS_NO BIT(27) /* + * Not susceptible to Register + * File Data Sampling. + */ +#define ARCH_CAP_RFDS_CLEAR BIT(28) /* + * VERW clears CPU Register + * File. + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR @@ -222,6 +237,7 @@ #define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT) #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) +#define MSR_INTEGRITY_CAPS_SAF_GEN_MASK GENMASK_ULL(10, 9) #define MSR_LBR_NHM_FROM 0x00000680 #define MSR_LBR_NHM_TO 0x000006c0 @@ -553,6 +569,7 @@ #define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 +#define MSR_AMD64_TW_CFG 0xc0011023 #define MSR_AMD64_DE_CFG 0xc0011029 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT 1 diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 778df05f853918..bae83810505bf5 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -115,8 +115,15 @@ static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned lo } __monitor((void *)¤t_thread_info()->flags, 0, 0); - if (!need_resched()) - __mwait(eax, ecx); + + if (!need_resched()) { + if (ecx & 1) { + __mwait(eax, ecx); + } else { + __sti_mwait(eax, ecx); + raw_local_irq_disable(); + } + } } current_clr_polling(); } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index c55cc243592e94..ee642d26e30457 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -196,7 +196,7 @@ .macro ANNOTATE_RETPOLINE_SAFE .Lhere_\@: .pushsection .discard.retpoline_safe - .long .Lhere_\@ - . + .long .Lhere_\@ .popsection .endm @@ -271,11 +271,20 @@ .Lskip_rsb_\@: .endm -#ifdef CONFIG_CPU_UNRET_ENTRY -#define CALL_UNTRAIN_RET "call entry_untrain_ret" -#else -#define CALL_UNTRAIN_RET "" +/* + * The CALL to srso_alias_untrain_ret() must be patched in directly at + * the spot where untraining must be done, ie., srso_alias_untrain_ret() + * must be the target of a CALL instruction instead of indirectly + * jumping to a wrapper which then calls it. Therefore, this macro is + * called outside of __UNTRAIN_RET below, for the time being, before the + * kernel can support nested alternatives with arbitrary nesting. + */ +.macro CALL_UNTRAIN_RET +#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) + ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \ + "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS #endif +.endm /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the @@ -288,38 +297,24 @@ * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point * where we have a stack but before any RET instruction. */ -.macro UNTRAIN_RET -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ - defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO) +.macro __UNTRAIN_RET ibpb_feature, call_depth_insns +#if defined(CONFIG_RETHUNK) || defined(CONFIG_CPU_IBPB_ENTRY) VALIDATE_UNRET_END - ALTERNATIVE_3 "", \ - CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ - "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \ - __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH + CALL_UNTRAIN_RET + ALTERNATIVE_2 "", \ + "call entry_ibpb", \ibpb_feature, \ + __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH #endif .endm -.macro UNTRAIN_RET_VM -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ - defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO) - VALIDATE_UNRET_END - ALTERNATIVE_3 "", \ - CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ - "call entry_ibpb", X86_FEATURE_IBPB_ON_VMEXIT, \ - __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH -#endif -.endm +#define UNTRAIN_RET \ + __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH) -.macro UNTRAIN_RET_FROM_CALL -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ - defined(CONFIG_CALL_DEPTH_TRACKING) - VALIDATE_UNRET_END - ALTERNATIVE_3 "", \ - CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ - "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \ - __stringify(RESET_CALL_DEPTH_FROM_CALL), X86_FEATURE_CALL_DEPTH -#endif -.endm +#define UNTRAIN_RET_VM \ + __UNTRAIN_RET X86_FEATURE_IBPB_ON_VMEXIT, __stringify(RESET_CALL_DEPTH) + +#define UNTRAIN_RET_FROM_CALL \ + __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH_FROM_CALL) .macro CALL_DEPTH_ACCOUNT @@ -329,12 +324,45 @@ #endif .endm +/* + * Macro to execute VERW instruction that mitigate transient data sampling + * attacks such as MDS. On affected systems a microcode update overloaded VERW + * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. + * + * Note: Only the memory operand variant of VERW clears the CPU buffers. + */ +.macro CLEAR_CPU_BUFFERS +#ifdef CONFIG_X86_64 + ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF +#else + /* + * In 32bit mode, the memory operand must be a %cs reference. The data + * segments may not be usable (vm86 mode), and the stack segment may not + * be flat (ESPFIX32). + */ + ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF +#endif +.endm + +#ifdef CONFIG_X86_64 +.macro CLEAR_BRANCH_HISTORY + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP +.endm + +.macro CLEAR_BRANCH_HISTORY_VMEXIT + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT +.endm +#else +#define CLEAR_BRANCH_HISTORY +#define CLEAR_BRANCH_HISTORY_VMEXIT +#endif + #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ "999:\n\t" \ ".pushsection .discard.retpoline_safe\n\t" \ - ".long 999b - .\n\t" \ + ".long 999b\n\t" \ ".popsection\n\t" typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; @@ -348,6 +376,22 @@ extern void __x86_return_thunk(void); static inline void __x86_return_thunk(void) {} #endif +#ifdef CONFIG_CPU_UNRET_ENTRY +extern void retbleed_return_thunk(void); +#else +static inline void retbleed_return_thunk(void) {} +#endif + +extern void srso_alias_untrain_ret(void); + +#ifdef CONFIG_CPU_SRSO +extern void srso_return_thunk(void); +extern void srso_alias_return_thunk(void); +#else +static inline void srso_return_thunk(void) {} +static inline void srso_alias_return_thunk(void) {} +#endif + extern void retbleed_return_thunk(void); extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); @@ -359,6 +403,10 @@ extern void srso_alias_untrain_ret(void); extern void entry_untrain_ret(void); extern void entry_ibpb(void); +#ifdef CONFIG_X86_64 +extern void clear_bhb_loop(void); +#endif + extern void (*x86_return_thunk)(void); #ifdef CONFIG_CALL_DEPTH_TRACKING @@ -538,13 +586,14 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -DECLARE_STATIC_KEY_FALSE(mds_user_clear); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); +extern u16 mds_verw_sel; + #include /** @@ -570,17 +619,6 @@ static __always_inline void mds_clear_cpu_buffers(void) asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc"); } -/** - * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability - * - * Clear CPU buffers if the corresponding static key is enabled - */ -static __always_inline void mds_user_clear_cpu_buffers(void) -{ - if (static_branch_likely(&mds_user_clear)) - mds_clear_cpu_buffers(); -} - /** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index e3bae2b60a0db9..ef2844d691735d 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -12,13 +12,6 @@ #define NR_NODE_MEMBLKS (MAX_NUMNODES*2) -/* - * Too small node sizes may confuse the VM badly. Usually they - * result from BIOS bugs. So dont recognize nodes as standalone - * NUMA entities that have less than this amount of RAM listed: - */ -#define NODE_MIN_SIZE (4*1024*1024) - extern int numa_off; /* diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index d18e5c332cb9f4..1b93ff80b43bcc 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -66,10 +66,14 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr, * virt_addr_valid(kaddr) returns true. */ #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) -#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) extern bool __virt_addr_valid(unsigned long kaddr); #define virt_addr_valid(kaddr) __virt_addr_valid((unsigned long) (kaddr)) +static __always_inline void *pfn_to_kaddr(unsigned long pfn) +{ + return __va(pfn << PAGE_SHIFT); +} + static __always_inline u64 __canonical_address(u64 vaddr, u8 vaddr_bits) { return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index cc6b8e087192e4..9dab85aba7afd9 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -17,6 +17,7 @@ extern unsigned long phys_base; extern unsigned long page_offset_base; extern unsigned long vmalloc_base; extern unsigned long vmemmap_base; +extern unsigned long physmem_end; static __always_inline unsigned long __phys_addr_nodebug(unsigned long x) { diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index e02b179ec65989..d03fe4fb41f43c 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -387,23 +387,7 @@ static inline pte_t pte_wrprotect(pte_t pte) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { - bool wp = pte_flags(pte) & _PAGE_UFFD_WP; - -#ifdef CONFIG_DEBUG_VM - /* - * Having write bit for wr-protect-marked present ptes is fatal, - * because it means the uffd-wp bit will be ignored and write will - * just go through. - * - * Use any chance of pgtable walking to verify this (e.g., when - * page swapped out or being migrated for all purposes). It means - * something is already wrong. Tell the admin even before the - * process crashes. We also nail it with wrong pgtable setup. - */ - WARN_ON_ONCE(wp && pte_write(pte)); -#endif - - return wp; + return pte_flags(pte) & _PAGE_UFFD_WP; } static inline pte_t pte_mkuffd_wp(pte_t pte) diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 38b54b992f32e3..35c416f061552b 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -140,6 +140,10 @@ extern unsigned int ptrs_per_p4d; # define VMEMMAP_START __VMEMMAP_BASE_L4 #endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */ +#ifdef CONFIG_RANDOMIZE_MEMORY +# define PHYSMEM_END physmem_end +#endif + /* * End of the region for which vmalloc page tables are pre-allocated. * For non-KMSAN builds, this is the same as VMALLOC_END. diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 0b748ee16b3d94..b786449626267e 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -148,7 +148,7 @@ #define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | \ _PAGE_DIRTY_BITS | _PAGE_SOFT_DIRTY | \ - _PAGE_DEVMAP | _PAGE_ENC | _PAGE_UFFD_WP) + _PAGE_DEVMAP | _PAGE_CC | _PAGE_UFFD_WP) #define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT) #define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE) @@ -173,6 +173,7 @@ enum page_cache_mode { }; #endif +#define _PAGE_CC (_AT(pteval_t, cc_mask)) #define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) #define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT) @@ -566,6 +567,8 @@ static inline void update_page_count(int level, unsigned long pages) { } extern pte_t *lookup_address(unsigned long address, unsigned int *level); extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level); +pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address, + unsigned int *level, bool *nx, bool *rw); extern pmd_t *lookup_pmd_address(unsigned long address); extern phys_addr_t slow_virt_to_phys(void *__address); extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, diff --git a/arch/x86/include/asm/posted_intr.h b/arch/x86/include/asm/posted_intr.h new file mode 100644 index 00000000000000..f0324c56f7af51 --- /dev/null +++ b/arch/x86/include/asm/posted_intr.h @@ -0,0 +1,88 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_POSTED_INTR_H +#define _X86_POSTED_INTR_H + +#define POSTED_INTR_ON 0 +#define POSTED_INTR_SN 1 + +#define PID_TABLE_ENTRY_VALID 1 + +/* Posted-Interrupt Descriptor */ +struct pi_desc { + u32 pir[8]; /* Posted interrupt requested */ + union { + struct { + /* bit 256 - Outstanding Notification */ + u16 on : 1, + /* bit 257 - Suppress Notification */ + sn : 1, + /* bit 271:258 - Reserved */ + rsvd_1 : 14; + /* bit 279:272 - Notification Vector */ + u8 nv; + /* bit 287:280 - Reserved */ + u8 rsvd_2; + /* bit 319:288 - Notification Destination */ + u32 ndst; + }; + u64 control; + }; + u32 rsvd[6]; +} __aligned(64); + +static inline bool pi_test_and_set_on(struct pi_desc *pi_desc) +{ + return test_and_set_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc) +{ + return test_and_clear_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc) +{ + return test_and_clear_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) +{ + return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); +} + +static inline bool pi_is_pir_empty(struct pi_desc *pi_desc) +{ + return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS); +} + +static inline void pi_set_sn(struct pi_desc *pi_desc) +{ + set_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); +} + +static inline void pi_set_on(struct pi_desc *pi_desc) +{ + set_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline void pi_clear_on(struct pi_desc *pi_desc) +{ + clear_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline void pi_clear_sn(struct pi_desc *pi_desc) +{ + clear_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_on(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_sn(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); +} + +#endif /* _X86_POSTED_INTR_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index a3669a7774edbb..67ad64efa9263f 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -399,7 +399,7 @@ static inline unsigned long cpu_kernelmode_gs_base(int cpu) return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu); } -extern asmlinkage void ignore_sysret(void); +extern asmlinkage void entry_SYSCALL32_ignore(void); /* Save actual FS/GS selectors and bases to current->thread */ void current_save_fsgs(void); @@ -464,7 +464,6 @@ struct thread_struct { unsigned long iopl_emul; unsigned int iopl_warn:1; - unsigned int sig_on_uaccess_err:1; /* * Protection Keys Register for Userspace. Loaded immediately on @@ -734,4 +733,22 @@ bool arch_is_platform_page(u64 paddr); extern bool gds_ucode_mitigated(void); +/* + * Make previous memory operations globally visible before + * a WRMSR. + * + * MFENCE makes writes visible, but only affects load/store + * instructions. WRMSR is unfortunately not a load/store + * instruction and is unaffected by MFENCE. The LFENCE ensures + * that the WRMSR is not reordered. + * + * Most WRMSRs are full serializing instructions themselves and + * do not require this barrier. This is only required for the + * IA32_TSC_DEADLINE and X2APIC MSRs. + */ +static inline void weak_wrmsr_fence(void) +{ + alternative("mfence; lfence", "", ALT_NOT(X86_FEATURE_APIC_MSRS_FENCE)); +} + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 12ef86b19910d3..84294b66b91625 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -32,10 +32,6 @@ void entry_SYSCALL_compat(void); void entry_SYSCALL_compat_safe_stack(void); void entry_SYSRETL_compat_unsafe_stack(void); void entry_SYSRETL_compat_end(void); -void entry_INT80_compat(void); -#ifdef CONFIG_XEN_PV -void xen_entry_INT80_compat(void); -#endif #endif void x86_configure_nx(void); diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index cde8357bb226d1..e897046c5d2c63 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -66,13 +66,15 @@ static inline bool vcpu_is_preempted(long cpu) #ifdef CONFIG_PARAVIRT /* - * virt_spin_lock_key - enables (by default) the virt_spin_lock() hijack. + * virt_spin_lock_key - disables by default the virt_spin_lock() hijack. * - * Native (and PV wanting native due to vCPU pinning) should disable this key. - * It is done in this backwards fashion to only have a single direction change, - * which removes ordering between native_pv_spin_init() and HV setup. + * Native (and PV wanting native due to vCPU pinning) should keep this key + * disabled. Native does not touch the key. + * + * When in a guest then native_pv_lock_init() enables the key first and + * KVM/XEN might conditionally disable it later in the boot process again. */ -DECLARE_STATIC_KEY_TRUE(virt_spin_lock_key); +DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key); /* * Shortcut for the queued_spin_lock_slowpath() function that allows diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 7ba1726b71c7b8..e9187ddd3d1fdc 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -99,6 +99,7 @@ #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 #define REQUIRED_MASK20 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define REQUIRED_MASK21 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 4b081e0d3306b7..363266cbcadaf2 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -13,7 +13,7 @@ #define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \ ({ \ bool c = false; \ - asm_volatile_goto (fullop "; j" #cc " %l[cc_label]" \ + asm goto (fullop "; j" #cc " %l[cc_label]" \ : : [var] "m" (_var), ## __VA_ARGS__ \ : clobbers : cc_label); \ if (0) { \ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 5b4a1ce3d36808..75a5388d40681e 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -199,16 +199,16 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) struct snp_guest_request_ioctl; void setup_ghcb(void); -void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, - unsigned long npages); -void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, - unsigned long npages); -void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op); +void early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, + unsigned long npages); +void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, + unsigned long npages); void snp_set_memory_shared(unsigned long vaddr, unsigned long npages); void snp_set_memory_private(unsigned long vaddr, unsigned long npages); void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); -void __init __noreturn snp_abort(void); +void __noreturn snp_abort(void); +void snp_dmi_setup(void); int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio); void snp_accept_memory(phys_addr_t start, phys_addr_t end); u64 snp_get_unsupported_features(u64 status); @@ -227,12 +227,12 @@ static inline void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { } static inline void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned long npages) { } -static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { } static inline void snp_set_memory_shared(unsigned long vaddr, unsigned long npages) { } static inline void snp_set_memory_private(unsigned long vaddr, unsigned long npages) { } static inline void snp_set_wakeup_secondary_cpu(void) { } static inline bool snp_init(struct boot_params *bp) { return false; } static inline void snp_abort(void) { } +static inline void snp_dmi_setup(void) { } static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio) { return -ENOTTY; diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h index 42fee8959df7be..896909f306e306 100644 --- a/arch/x86/include/asm/shstk.h +++ b/arch/x86/include/asm/shstk.h @@ -21,6 +21,7 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *p, unsigned long clon void shstk_free(struct task_struct *p); int setup_signal_shadow_stack(struct ksignal *ksig); int restore_signal_shadow_stack(void); +int shstk_update_last_frame(unsigned long val); #else static inline long shstk_prctl(struct task_struct *task, int option, unsigned long arg2) { return -EINVAL; } @@ -31,6 +32,7 @@ static inline unsigned long shstk_alloc_thread_stack(struct task_struct *p, static inline void shstk_free(struct task_struct *p) {} static inline int setup_signal_shadow_stack(struct ksignal *ksig) { return 0; } static inline int restore_signal_shadow_stack(void) { return 0; } +static inline int shstk_update_last_frame(unsigned long val) { return 0; } #endif /* CONFIG_X86_USER_SHADOW_STACK */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index d6cd9344f6c78e..48f8dd47cf6882 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -205,7 +205,7 @@ static inline void clwb(volatile void *__p) #ifdef CONFIG_X86_USER_SHADOW_STACK static inline int write_user_shstk_64(u64 __user *addr, u64 val) { - asm_volatile_goto("1: wrussq %[val], (%[addr])\n" + asm goto("1: wrussq %[val], (%[addr])\n" _ASM_EXTABLE(1b, %l[fail]) :: [addr] "r" (addr), [val] "r" (val) :: fail); diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index a800abb1a99255..d8416b3bf832e4 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -12,11 +12,6 @@ /* image of the saved processor state */ struct saved_context { - /* - * On x86_32, all segment registers except gs are saved at kernel - * entry in pt_regs. - */ - u16 gs; unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; struct saved_msrs saved_msrs; @@ -27,6 +22,11 @@ struct saved_context { unsigned long tr; unsigned long safety; unsigned long return_address; + /* + * On x86_32, all segment registers except gs are saved at kernel + * entry in pt_regs. + */ + u16 gs; bool misc_enable_saved; } __attribute__((packed)); diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 4fb36fba4b5a1f..228a42585d5c97 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -16,19 +16,17 @@ #include /* for TS_COMPAT */ #include +/* This is used purely for kernel/trace/trace_syscalls.c */ typedef long (*sys_call_ptr_t)(const struct pt_regs *); extern const sys_call_ptr_t sys_call_table[]; -#if defined(CONFIG_X86_32) -#define ia32_sys_call_table sys_call_table -#else /* * These may not exist, but still put the prototypes in so we * can use IS_ENABLED(). */ -extern const sys_call_ptr_t ia32_sys_call_table[]; -extern const sys_call_ptr_t x32_sys_call_table[]; -#endif +extern long ia32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x64_sys_call(const struct pt_regs *, unsigned int nr); /* * Only the low 32 bits of orig_ax are meaningful, so we return int. @@ -84,7 +82,12 @@ static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, unsigned long *args) { - memcpy(args, ®s->bx, 6 * sizeof(args[0])); + args[0] = regs->bx; + args[1] = regs->cx; + args[2] = regs->dx; + args[3] = regs->si; + args[4] = regs->di; + args[5] = regs->bp; } static inline int syscall_get_arch(struct task_struct *task) @@ -127,6 +130,7 @@ static inline int syscall_get_arch(struct task_struct *task) } void do_syscall_64(struct pt_regs *regs, int nr); +void do_int80_emulation(struct pt_regs *regs); #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index fd2669b1cb2d95..7e88705e907f41 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -58,12 +58,29 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); ,,regs->di,,regs->si,,regs->dx \ ,,regs->r10,,regs->r8,,regs->r9) \ + +/* SYSCALL_PT_ARGS is Adapted from s390x */ +#define SYSCALL_PT_ARG6(m, t1, t2, t3, t4, t5, t6) \ + SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5), m(t6, (regs->bp)) +#define SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5) \ + SYSCALL_PT_ARG4(m, t1, t2, t3, t4), m(t5, (regs->di)) +#define SYSCALL_PT_ARG4(m, t1, t2, t3, t4) \ + SYSCALL_PT_ARG3(m, t1, t2, t3), m(t4, (regs->si)) +#define SYSCALL_PT_ARG3(m, t1, t2, t3) \ + SYSCALL_PT_ARG2(m, t1, t2), m(t3, (regs->dx)) +#define SYSCALL_PT_ARG2(m, t1, t2) \ + SYSCALL_PT_ARG1(m, t1), m(t2, (regs->cx)) +#define SYSCALL_PT_ARG1(m, t1) m(t1, (regs->bx)) +#define SYSCALL_PT_ARGS(x, ...) SYSCALL_PT_ARG##x(__VA_ARGS__) + +#define __SC_COMPAT_CAST(t, a) \ + (__typeof(__builtin_choose_expr(__TYPE_IS_L(t), 0, 0U))) \ + (unsigned int)a + /* Mapping of registers to parameters for syscalls on i386 */ #define SC_IA32_REGS_TO_ARGS(x, ...) \ - __MAP(x,__SC_ARGS \ - ,,(unsigned int)regs->bx,,(unsigned int)regs->cx \ - ,,(unsigned int)regs->dx,,(unsigned int)regs->si \ - ,,(unsigned int)regs->di,,(unsigned int)regs->bp) + SYSCALL_PT_ARGS(x, __SC_COMPAT_CAST, \ + __MAP(x, __SC_TYPE, __VA_ARGS__)) \ #define __SYS_STUB0(abi, name) \ long __##abi##_##name(const struct pt_regs *regs); \ @@ -86,9 +103,6 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); return sys_ni_syscall(); \ } -#define __SYS_NI(abi, name) \ - SYSCALL_ALIAS(__##abi##_##name, sys_ni_posix_timers); - #ifdef CONFIG_X86_64 #define __X64_SYS_STUB0(name) \ __SYS_STUB0(x64, sys_##name) @@ -100,13 +114,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #define __X64_COND_SYSCALL(name) \ __COND_SYSCALL(x64, sys_##name) -#define __X64_SYS_NI(name) \ - __SYS_NI(x64, sys_##name) #else /* CONFIG_X86_64 */ #define __X64_SYS_STUB0(name) #define __X64_SYS_STUBx(x, name, ...) #define __X64_COND_SYSCALL(name) -#define __X64_SYS_NI(name) #endif /* CONFIG_X86_64 */ #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) @@ -120,13 +131,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #define __IA32_COND_SYSCALL(name) \ __COND_SYSCALL(ia32, sys_##name) -#define __IA32_SYS_NI(name) \ - __SYS_NI(ia32, sys_##name) #else /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ #define __IA32_SYS_STUB0(name) #define __IA32_SYS_STUBx(x, name, ...) #define __IA32_COND_SYSCALL(name) -#define __IA32_SYS_NI(name) #endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ #ifdef CONFIG_IA32_EMULATION @@ -135,8 +143,7 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); * additional wrappers (aptly named __ia32_sys_xyzzy) which decode the * ia32 regs in the proper order for shared or "common" syscalls. As some * syscalls may not be implemented, we need to expand COND_SYSCALL in - * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this - * case as well. + * kernel/sys_ni.c to cover this case as well. */ #define __IA32_COMPAT_SYS_STUB0(name) \ __SYS_STUB0(ia32, compat_sys_##name) @@ -148,14 +155,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #define __IA32_COMPAT_COND_SYSCALL(name) \ __COND_SYSCALL(ia32, compat_sys_##name) -#define __IA32_COMPAT_SYS_NI(name) \ - __SYS_NI(ia32, compat_sys_##name) - #else /* CONFIG_IA32_EMULATION */ #define __IA32_COMPAT_SYS_STUB0(name) #define __IA32_COMPAT_SYS_STUBx(x, name, ...) #define __IA32_COMPAT_COND_SYSCALL(name) -#define __IA32_COMPAT_SYS_NI(name) #endif /* CONFIG_IA32_EMULATION */ @@ -175,13 +178,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #define __X32_COMPAT_COND_SYSCALL(name) \ __COND_SYSCALL(x64, compat_sys_##name) -#define __X32_COMPAT_SYS_NI(name) \ - __SYS_NI(x64, compat_sys_##name) #else /* CONFIG_X86_X32_ABI */ #define __X32_COMPAT_SYS_STUB0(name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) #define __X32_COMPAT_COND_SYSCALL(name) -#define __X32_COMPAT_SYS_NI(name) #endif /* CONFIG_X86_X32_ABI */ @@ -212,17 +212,12 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); /* * As some compat syscalls may not be implemented, we need to expand - * COND_SYSCALL_COMPAT in kernel/sys_ni.c and COMPAT_SYS_NI in - * kernel/time/posix-stubs.c to cover this case as well. + * COND_SYSCALL_COMPAT in kernel/sys_ni.c to cover this case as well. */ #define COND_SYSCALL_COMPAT(name) \ __IA32_COMPAT_COND_SYSCALL(name) \ __X32_COMPAT_COND_SYSCALL(name) -#define COMPAT_SYS_NI(name) \ - __IA32_COMPAT_SYS_NI(name) \ - __X32_COMPAT_SYS_NI(name) - #endif /* CONFIG_COMPAT */ #define __SYSCALL_DEFINEx(x, name, ...) \ @@ -243,8 +238,8 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); * As the generic SYSCALL_DEFINE0() macro does not decode any parameters for * obvious reasons, and passing struct pt_regs *regs to it in %rdi does not * hurt, we only need to re-define it here to keep the naming congruent to - * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() and SYS_NI() - * macros to work correctly. + * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() macro + * to work correctly. */ #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ @@ -257,10 +252,6 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); __X64_COND_SYSCALL(name) \ __IA32_COND_SYSCALL(name) -#define SYS_NI(name) \ - __X64_SYS_NI(name) \ - __IA32_SYS_NI(name) - /* * For VSYSCALLS, we need to declare these three syscalls with the new diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 8bae40a662827d..3a7755c1a44102 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -78,10 +78,10 @@ extern int __get_user_bad(void); int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ __chk_user_ptr(ptr); \ - asm volatile("call __" #fn "_%P4" \ + asm volatile("call __" #fn "_%c[size]" \ : "=a" (__ret_gu), "=r" (__val_gu), \ ASM_CALL_CONSTRAINT \ - : "0" (ptr), "i" (sizeof(*(ptr)))); \ + : "0" (ptr), [size] "i" (sizeof(*(ptr)))); \ instrument_get_user(__val_gu); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ @@ -133,7 +133,7 @@ extern int __get_user_bad(void); #ifdef CONFIG_X86_32 #define __put_user_goto_u64(x, addr, label) \ - asm_volatile_goto("\n" \ + asm goto("\n" \ "1: movl %%eax,0(%1)\n" \ "2: movl %%edx,4(%1)\n" \ _ASM_EXTABLE_UA(1b, %l2) \ @@ -177,7 +177,7 @@ extern void __put_user_nocheck_8(void); __chk_user_ptr(__ptr); \ __ptr_pu = __ptr; \ __val_pu = __x; \ - asm volatile("call __" #fn "_%P[size]" \ + asm volatile("call __" #fn "_%c[size]" \ : "=c" (__ret_pu), \ ASM_CALL_CONSTRAINT \ : "0" (__ptr_pu), \ @@ -295,7 +295,7 @@ do { \ } while (0) #define __get_user_asm(x, addr, itype, ltype, label) \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: mov"itype" %[umem],%[output]\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : [output] ltype(x) \ @@ -375,7 +375,7 @@ do { \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ @@ -394,7 +394,7 @@ do { \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ @@ -477,7 +477,7 @@ struct __large_struct { unsigned long buf[100]; }; * aliasing issues. */ #define __put_user_goto(x, addr, itype, ltype, label) \ - asm_volatile_goto("\n" \ + asm goto("\n" \ "1: mov"itype" %0,%1\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : : ltype(x), "m" (__m(addr)) \ @@ -496,7 +496,7 @@ copy_mc_to_kernel(void *to, const void *from, unsigned len); #define copy_mc_to_kernel copy_mc_to_kernel unsigned long __must_check -copy_mc_to_user(void *to, const void *from, unsigned len); +copy_mc_to_user(void __user *to, const void *from, unsigned len); #endif /* diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index ab60a71a8dcb98..472f0263dbc612 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -4,6 +4,7 @@ #include #include +#include #ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); @@ -24,4 +25,13 @@ static inline bool emulate_vsyscall(unsigned long error_code, } #endif +/* + * The (legacy) vsyscall page is the long page in the kernel portion + * of the address space that has user-accessible permissions. + */ +static inline bool is_vsyscall_vaddr(unsigned long vaddr) +{ + return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); +} + #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 5240d88db52a70..0fe4e482a97b17 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -30,12 +30,13 @@ struct x86_init_mpparse { * @reserve_resources: reserve the standard resources for the * platform * @memory_setup: platform specific memory setup - * + * @dmi_setup: platform specific DMI setup */ struct x86_init_resources { void (*probe_roms)(void); void (*reserve_resources)(void); char *(*memory_setup)(void); + void (*dmi_setup)(void); }; /** diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 7048dfacc04b24..64fbd2dbc5b761 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -62,6 +62,11 @@ void xen_arch_unregister_cpu(int num); #ifdef CONFIG_PVH void __init xen_pvh_init(struct boot_params *boot_params); void __init mem_map_via_hcall(struct boot_params *boot_params_p); +#ifdef CONFIG_XEN_PVH +void __init xen_reserve_extra_memory(struct boot_params *bootp); +#else +static inline void xen_reserve_extra_memory(struct boot_params *bootp) { } +#endif #endif /* Lazy mode for batching updates / context switch */ @@ -100,4 +105,13 @@ static inline void leave_lazy(enum xen_lazy_mode mode) enum xen_lazy_mode xen_get_lazy_mode(void); +#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI) +void xen_sanitize_proc_cap_bits(uint32_t *buf); +#else +static inline void xen_sanitize_proc_cap_bits(uint32_t *buf) +{ + BUG(); +} +#endif + #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 01d19fc223463d..eeea058cf6028e 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -38,6 +38,7 @@ #define XLF_EFI_KEXEC (1<<4) #define XLF_5LEVEL (1<<5) #define XLF_5LEVEL_ENABLED (1<<6) +#define XLF_MEM_ENCRYPTION (1<<7) #ifndef __ASSEMBLY__ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index c55c0ef47a187e..49c39f5dc1c992 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1901,3 +1901,14 @@ u64 x86_default_get_root_pointer(void) { return boot_params.acpi_rsdp_addr; } + +#ifdef CONFIG_XEN_PV +void __iomem *x86_acpi_os_ioremap(acpi_physical_address phys, acpi_size size) +{ + return ioremap_cache(phys, size); +} + +void __iomem * (*acpi_os_ioremap)(acpi_physical_address phys, acpi_size size) = + x86_acpi_os_ioremap; +EXPORT_SYMBOL_GPL(acpi_os_ioremap); +#endif diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index 8d8752b44f1139..ff8f25faca3dd1 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -20,7 +20,7 @@ bool cpc_supported_by_cpu(void) (boot_cpu_data.x86_model >= 0x20 && boot_cpu_data.x86_model <= 0x2f))) return true; else if (boot_cpu_data.x86 == 0x17 && - boot_cpu_data.x86_model >= 0x70 && boot_cpu_data.x86_model <= 0x7f) + boot_cpu_data.x86_model >= 0x30 && boot_cpu_data.x86_model <= 0x7f) return true; return boot_cpu_has(X86_FEATURE_CPPC); } diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 73be3931e4f060..aae7456ece0700 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -255,6 +255,16 @@ static void __init_or_module noinline optimize_nops(u8 *instr, size_t len) } } +static void __init_or_module noinline optimize_nops_inplace(u8 *instr, size_t len) +{ + unsigned long flags; + + local_irq_save(flags); + optimize_nops(instr, len); + sync_core(); + local_irq_restore(flags); +} + /* * In this context, "source" is where the instructions are placed in the * section .altinstr_replacement, for example during kernel build by the @@ -438,7 +448,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, * patch if feature is *NOT* present. */ if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) { - optimize_nops(instr, a->instrlen); + optimize_nops_inplace(instr, a->instrlen); continue; } @@ -1685,8 +1695,8 @@ void __init_or_module text_poke_early(void *addr, const void *opcode, } else { local_irq_save(flags); memcpy(addr, opcode, len); - local_irq_restore(flags); sync_core(); + local_irq_restore(flags); /* * Could also do a CLFLUSH here to speed up CPU recovery; but diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 356de955e78ddc..6dabb53f58a445 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -26,6 +26,7 @@ #define PCI_DEVICE_ID_AMD_19H_M70H_ROOT 0x14e8 #define PCI_DEVICE_ID_AMD_1AH_M00H_ROOT 0x153a #define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507 +#define PCI_DEVICE_ID_AMD_1AH_M60H_ROOT 0x1122 #define PCI_DEVICE_ID_AMD_MI200_ROOT 0x14bb #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 @@ -61,6 +62,7 @@ static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_ROOT) }, {} }; @@ -92,6 +94,8 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F3) }, {} }; @@ -112,6 +116,9 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) }, @@ -206,7 +213,14 @@ static int __amd_smn_rw(u16 node, u32 address, u32 *value, bool write) int amd_smn_read(u16 node, u32 address, u32 *value) { - return __amd_smn_rw(node, address, value, false); + int err = __amd_smn_rw(node, address, value, false); + + if (PCI_POSSIBLE_ERROR(*value)) { + err = -ENODEV; + *value = 0; + } + + return err; } EXPORT_SYMBOL_GPL(amd_smn_read); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 760adac3d1a824..00ca9c3c1d8bf8 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -36,6 +36,8 @@ #include #include +#include + #include #include #include @@ -471,7 +473,19 @@ static int lapic_timer_shutdown(struct clock_event_device *evt) v = apic_read(APIC_LVTT); v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); apic_write(APIC_LVTT, v); - apic_write(APIC_TMICT, 0); + + /* + * Setting APIC_LVT_MASKED (above) should be enough to tell + * the hardware that this timer will never fire. But AMD + * erratum 411 and some Intel CPU behavior circa 2024 say + * otherwise. Time for belt and suspenders programming: mask + * the timer _and_ zero the counter registers: + */ + if (v & APIC_LVT_TIMER_TSCDEADLINE) + wrmsrl(MSR_IA32_TSC_DEADLINE, 0); + else + apic_write(APIC_TMICT, 0); + return 0; } @@ -1722,11 +1736,11 @@ static int x2apic_state; static bool x2apic_hw_locked(void) { - u64 ia32_cap; + u64 x86_arch_cap_msr; u64 msr; - ia32_cap = x86_read_arch_cap_msr(); - if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) { + x86_arch_cap_msr = x86_read_arch_cap_msr(); + if (x86_arch_cap_msr & ARCH_CAP_XAPIC_DISABLE) { rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr); return (msr & LEGACY_XAPIC_DISABLED); } @@ -1806,16 +1820,13 @@ void x2apic_setup(void) __x2apic_enable(); } -static __init void apic_set_fixmap(void); +static __init void apic_set_fixmap(bool read_apic); static __init void x2apic_disable(void) { - u32 x2apic_id, state = x2apic_state; + u32 x2apic_id; - x2apic_mode = 0; - x2apic_state = X2APIC_DISABLED; - - if (state != X2APIC_ON) + if (x2apic_state < X2APIC_ON) return; x2apic_id = read_apic_id(); @@ -1828,7 +1839,16 @@ static __init void x2apic_disable(void) } __x2apic_disable(); - apic_set_fixmap(); + + x2apic_mode = 0; + x2apic_state = X2APIC_DISABLED; + + /* + * Don't reread the APIC ID as it was already done from + * check_x2apic() and the APIC driver still is a x2APIC variant, + * which fails to do the read after x2APIC was disabled. + */ + apic_set_fixmap(false); } static __init void x2apic_enable(void) @@ -2093,13 +2113,14 @@ void __init init_apic_mappings(void) } } -static __init void apic_set_fixmap(void) +static __init void apic_set_fixmap(bool read_apic) { set_fixmap_nocache(FIX_APIC_BASE, mp_lapic_addr); apic_mmio_base = APIC_BASE; apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n", apic_mmio_base, mp_lapic_addr); - apic_read_boot_cpu_id(false); + if (read_apic) + apic_read_boot_cpu_id(false); } void __init register_lapic_address(unsigned long address) @@ -2109,7 +2130,7 @@ void __init register_lapic_address(unsigned long address) mp_lapic_addr = address; if (!x2apic_mode) - apic_set_fixmap(); + apic_set_fixmap(true); } /* @@ -2344,6 +2365,15 @@ static int __init smp_init_primary_thread_mask(void) { unsigned int cpu; + /* + * XEN/PV provides either none or useless topology information. + * Pretend that all vCPUs are primary threads. + */ + if (xen_pv_domain()) { + cpumask_copy(&__cpu_primary_thread_mask, cpu_possible_mask); + return 0; + } + for (cpu = 0; cpu < nr_logical_cpuids; cpu++) cpu_mark_primary_thread(cpu, cpuid_to_apicid[cpu]); return 0; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 00da6cf6b07dcb..d0c5325d175102 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -352,27 +352,26 @@ static void ioapic_mask_entry(int apic, int pin) * shared ISA-space IRQs, so we have to support them. We are super * fast in the common case, and fast for shared ISA-space IRQs. */ -static int __add_pin_to_irq_node(struct mp_chip_data *data, - int node, int apic, int pin) +static bool add_pin_to_irq_node(struct mp_chip_data *data, int node, int apic, int pin) { struct irq_pin_list *entry; - /* don't allow duplicates */ - for_each_irq_pin(entry, data->irq_2_pin) + /* Don't allow duplicates */ + for_each_irq_pin(entry, data->irq_2_pin) { if (entry->apic == apic && entry->pin == pin) - return 0; + return true; + } entry = kzalloc_node(sizeof(struct irq_pin_list), GFP_ATOMIC, node); if (!entry) { - pr_err("can not alloc irq_pin_list (%d,%d,%d)\n", - node, apic, pin); - return -ENOMEM; + pr_err("Cannot allocate irq_pin_list (%d,%d,%d)\n", node, apic, pin); + return false; } + entry->apic = apic; entry->pin = pin; list_add_tail(&entry->list, &data->irq_2_pin); - - return 0; + return true; } static void __remove_pin_from_irq(struct mp_chip_data *data, int apic, int pin) @@ -387,13 +386,6 @@ static void __remove_pin_from_irq(struct mp_chip_data *data, int apic, int pin) } } -static void add_pin_to_irq_node(struct mp_chip_data *data, - int node, int apic, int pin) -{ - if (__add_pin_to_irq_node(data, node, apic, pin)) - panic("IO-APIC: failed to add irq-pin. Can not proceed\n"); -} - /* * Reroute an IRQ to a different pin. */ @@ -1002,8 +994,7 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain, if (irq_data && irq_data->parent_data) { if (!mp_check_pin_attr(irq, info)) return -EBUSY; - if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic, - info->ioapic.pin)) + if (!add_pin_to_irq_node(irq_data->chip_data, node, ioapic, info->ioapic.pin)) return -ENOMEM; } else { info->flags |= X86_IRQ_ALLOC_LEGACY; @@ -3037,10 +3028,8 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, return -ENOMEM; ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); - if (ret < 0) { - kfree(data); - return ret; - } + if (ret < 0) + goto free_data; INIT_LIST_HEAD(&data->irq_2_pin); irq_data->hwirq = info->ioapic.pin; @@ -3049,7 +3038,10 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, irq_data->chip_data = data; mp_irqdomain_get_attr(mp_pin_to_gsi(ioapic, pin), data, info); - add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin); + if (!add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin)) { + ret = -ENOMEM; + goto free_irqs; + } mp_preconfigure_entry(data); mp_register_handler(virq, data->is_level); @@ -3064,6 +3056,12 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, ioapic, mpc_ioapic_id(ioapic), pin, virq, data->is_level, data->active_low); return 0; + +free_irqs: + irq_domain_free_irqs_parent(domain, virq, nr_irqs); +free_data: + kfree(data); + return ret; } void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 6b6b711678fe03..d9651f15ae4f70 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -55,14 +55,14 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) * caused by the non-atomic update of the address/data pair. * * Direct update is possible when: - * - The MSI is maskable (remapped MSI does not use this code path)). - * The quirk bit is not set in this case. + * - The MSI is maskable (remapped MSI does not use this code path). + * The reservation mode bit is set in this case. * - The new vector is the same as the old vector * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up) * - The interrupt is not yet started up * - The new destination CPU is the same as the old destination CPU */ - if (!irqd_msi_nomask_quirk(irqd) || + if (!irqd_can_reserve(irqd) || cfg->vector == old_cfg.vector || old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR || !irqd_is_started(irqd) || @@ -215,8 +215,6 @@ static bool x86_init_dev_msi_info(struct device *dev, struct irq_domain *domain, if (WARN_ON_ONCE(domain != real_parent)) return false; info->chip->irq_set_affinity = msi_set_affinity; - /* See msi_set_affinity() for the gory details */ - info->flags |= MSI_FLAG_NOMASK_QUIRK; break; case DOMAIN_BUS_DMAR: case DOMAIN_BUS_AMDVI: diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 319448d87b99a7..218ef9072c0c61 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -1036,7 +1036,8 @@ static void __vector_schedule_cleanup(struct apic_chip_data *apicd) add_timer_on(&cl->timer, cpu); } } else { - apicd->prev_vector = 0; + pr_warn("IRQ %u schedule cleanup for offline CPU %u\n", apicd->irq, cpu); + free_moved_vector(apicd); } raw_spin_unlock(&vector_lock); } @@ -1073,6 +1074,7 @@ void irq_complete_move(struct irq_cfg *cfg) */ void irq_force_complete_move(struct irq_desc *desc) { + unsigned int cpu = smp_processor_id(); struct apic_chip_data *apicd; struct irq_data *irqd; unsigned int vector; @@ -1097,10 +1099,11 @@ void irq_force_complete_move(struct irq_desc *desc) goto unlock; /* - * If prev_vector is empty, no action required. + * If prev_vector is empty or the descriptor is neither currently + * nor previously on the outgoing CPU no action required. */ vector = apicd->prev_vector; - if (!vector) + if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu)) goto unlock; /* diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ece2b5b7b0fe4e..145c81c68394be 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -66,20 +66,6 @@ static const int amd_erratum_400[] = static const int amd_erratum_383[] = AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); -/* #1054: Instructions Retired Performance Counter May Be Inaccurate */ -static const int amd_erratum_1054[] = - AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); - -static const int amd_zenbleed[] = - AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf), - AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf), - AMD_MODEL_RANGE(0x17, 0x90, 0x0, 0x91, 0xf), - AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf)); - -static const int amd_div0[] = - AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf), - AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf)); - static const int amd_erratum_1485[] = AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x19, 0x10, 0x0, 0x1f, 0xf), AMD_MODEL_RANGE(0x19, 0x60, 0x0, 0xaf, 0xf)); @@ -620,6 +606,49 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) } resctrl_cpu_detect(c); + + /* Figure out Zen generations: */ + switch (c->x86) { + case 0x17: { + switch (c->x86_model) { + case 0x00 ... 0x2f: + case 0x50 ... 0x5f: + setup_force_cpu_cap(X86_FEATURE_ZEN1); + break; + case 0x30 ... 0x4f: + case 0x60 ... 0x7f: + case 0x90 ... 0x91: + case 0xa0 ... 0xaf: + setup_force_cpu_cap(X86_FEATURE_ZEN2); + break; + default: + goto warn; + } + break; + } + case 0x19: { + switch (c->x86_model) { + case 0x00 ... 0x0f: + case 0x20 ... 0x5f: + setup_force_cpu_cap(X86_FEATURE_ZEN3); + break; + case 0x10 ... 0x1f: + case 0x60 ... 0xaf: + setup_force_cpu_cap(X86_FEATURE_ZEN4); + break; + default: + goto warn; + } + break; + } + default: + break; + } + + return; + +warn: + WARN_ONCE(1, "Family 0x%x, model: 0x%x??\n", c->x86, c->x86_model); } static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) @@ -945,6 +974,19 @@ static void init_amd_bd(struct cpuinfo_x86 *c) clear_rdrand_cpuid_bit(c); } +static void fix_erratum_1386(struct cpuinfo_x86 *c) +{ + /* + * Work around Erratum 1386. The XSAVES instruction malfunctions in + * certain circumstances on Zen1/2 uarch, and not all parts have had + * updated microcode at the time of writing (March 2023). + * + * Affected parts all have no supervisor XSAVE states, meaning that + * the XSAVEC instruction (which works fine) is equivalent. + */ + clear_cpu_cap(c, X86_FEATURE_XSAVES); +} + void init_spectral_chicken(struct cpuinfo_x86 *c) { #ifdef CONFIG_CPU_UNRET_ENTRY @@ -965,24 +1007,19 @@ void init_spectral_chicken(struct cpuinfo_x86 *c) } } #endif - /* - * Work around Erratum 1386. The XSAVES instruction malfunctions in - * certain circumstances on Zen1/2 uarch, and not all parts have had - * updated microcode at the time of writing (March 2023). - * - * Affected parts all have no supervisor XSAVE states, meaning that - * the XSAVEC instruction (which works fine) is equivalent. - */ - clear_cpu_cap(c, X86_FEATURE_XSAVES); } static void init_amd_zn(struct cpuinfo_x86 *c) { - set_cpu_cap(c, X86_FEATURE_ZEN); - + setup_force_cpu_cap(X86_FEATURE_ZEN); #ifdef CONFIG_NUMA node_reclaim_distance = 32; #endif +} + +static void init_amd_zen1(struct cpuinfo_x86 *c) +{ + fix_erratum_1386(c); /* Fix up CPUID bits, but only if not virtualised. */ if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { @@ -999,6 +1036,9 @@ static void init_amd_zn(struct cpuinfo_x86 *c) if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO)) set_cpu_cap(c, X86_FEATURE_BTC_NO); } + + pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); + setup_force_cpu_bug(X86_BUG_DIV0); } static bool cpu_has_zenbleed_microcode(void) @@ -1006,11 +1046,11 @@ static bool cpu_has_zenbleed_microcode(void) u32 good_rev = 0; switch (boot_cpu_data.x86_model) { - case 0x30 ... 0x3f: good_rev = 0x0830107a; break; - case 0x60 ... 0x67: good_rev = 0x0860010b; break; - case 0x68 ... 0x6f: good_rev = 0x08608105; break; - case 0x70 ... 0x7f: good_rev = 0x08701032; break; - case 0xa0 ... 0xaf: good_rev = 0x08a00008; break; + case 0x30 ... 0x3f: good_rev = 0x0830107b; break; + case 0x60 ... 0x67: good_rev = 0x0860010c; break; + case 0x68 ... 0x6f: good_rev = 0x08608107; break; + case 0x70 ... 0x7f: good_rev = 0x08701033; break; + case 0xa0 ... 0xaf: good_rev = 0x08a00009; break; default: return false; @@ -1023,11 +1063,8 @@ static bool cpu_has_zenbleed_microcode(void) return true; } -static void zenbleed_check(struct cpuinfo_x86 *c) +static void zen2_zenbleed_check(struct cpuinfo_x86 *c) { - if (!cpu_has_amd_erratum(c, amd_zenbleed)) - return; - if (cpu_has(c, X86_FEATURE_HYPERVISOR)) return; @@ -1042,6 +1079,20 @@ static void zenbleed_check(struct cpuinfo_x86 *c) } } +static void init_amd_zen2(struct cpuinfo_x86 *c) +{ + fix_erratum_1386(c); + zen2_zenbleed_check(c); +} + +static void init_amd_zen3(struct cpuinfo_x86 *c) +{ +} + +static void init_amd_zen4(struct cpuinfo_x86 *c) +{ +} + static void init_amd(struct cpuinfo_x86 *c) { early_init_amd(c); @@ -1080,6 +1131,15 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x19: init_amd_zn(c); break; } + if (boot_cpu_has(X86_FEATURE_ZEN1)) + init_amd_zen1(c); + else if (boot_cpu_has(X86_FEATURE_ZEN2)) + init_amd_zen2(c); + else if (boot_cpu_has(X86_FEATURE_ZEN3)) + init_amd_zen3(c); + else if (boot_cpu_has(X86_FEATURE_ZEN4)) + init_amd_zen4(c); + /* * Enable workaround for FXSAVE leak on CPUs * without a XSaveErPtr feature @@ -1131,7 +1191,7 @@ static void init_amd(struct cpuinfo_x86 *c) * Counter May Be Inaccurate". */ if (cpu_has(c, X86_FEATURE_IRPERF) && - !cpu_has_amd_erratum(c, amd_erratum_1054)) + (boot_cpu_has(X86_FEATURE_ZEN1) && c->x86_model > 0x2f)) msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); check_null_seg_clears_base(c); @@ -1147,16 +1207,12 @@ static void init_amd(struct cpuinfo_x86 *c) cpu_has(c, X86_FEATURE_AUTOIBRS)) WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS)); - zenbleed_check(c); - - if (cpu_has_amd_erratum(c, amd_div0)) { - pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); - setup_force_cpu_bug(X86_BUG_DIV0); - } - if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has_amd_erratum(c, amd_erratum_1485)) msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT); + + /* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */ + clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); } #ifdef CONFIG_X86_32 @@ -1310,12 +1366,16 @@ static void zenbleed_check_cpu(void *unused) { struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); - zenbleed_check(c); + zen2_zenbleed_check(c); } void amd_check_microcode(void) { - on_each_cpu(zenbleed_check_cpu, NULL, 1); + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return; + + if (cpu_feature_enabled(X86_FEATURE_ZEN2)) + on_each_cpu(zenbleed_check_cpu, NULL, 1); } /* diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 10499bcd4e3962..7b5ba5b8592a25 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -61,9 +61,11 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; EXPORT_SYMBOL_GPL(x86_pred_cmd); +static u64 __ro_after_init x86_arch_cap_msr; + static DEFINE_MUTEX(spec_ctrl_mutex); -void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk; +void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk; /* Update SPEC_CTRL MSR and its cached copy unconditionally */ static void update_spec_ctrl(u64 val) @@ -111,9 +113,6 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -/* Control MDS CPU buffer clear before returning to user space */ -DEFINE_STATIC_KEY_FALSE(mds_user_clear); -EXPORT_SYMBOL_GPL(mds_user_clear); /* Control MDS CPU buffer clear before idling (halt, mwait) */ DEFINE_STATIC_KEY_FALSE(mds_idle_clear); EXPORT_SYMBOL_GPL(mds_idle_clear); @@ -147,6 +146,8 @@ void __init cpu_select_mitigations(void) x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK; } + x86_arch_cap_msr = x86_read_arch_cap_msr(); + /* Select the proper CPU mitigations before patching alternatives: */ spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); @@ -252,7 +253,7 @@ static void __init mds_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) mds_mitigation = MDS_MITIGATION_VMWERV; - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && (mds_nosmt || cpu_mitigations_auto_nosmt())) @@ -304,8 +305,6 @@ static const char * const taa_strings[] = { static void __init taa_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_TAA)) { taa_mitigation = TAA_MITIGATION_OFF; return; @@ -344,9 +343,8 @@ static void __init taa_select_mitigation(void) * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode * update is required. */ - ia32_cap = x86_read_arch_cap_msr(); - if ( (ia32_cap & ARCH_CAP_MDS_NO) && - !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + if ( (x86_arch_cap_msr & ARCH_CAP_MDS_NO) && + !(x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR)) taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; /* @@ -356,7 +354,7 @@ static void __init taa_select_mitigation(void) * For guests that can't determine whether the correct microcode is * present on host, enable the mitigation for UCODE_NEEDED as well. */ - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); @@ -404,8 +402,6 @@ static const char * const mmio_strings[] = { static void __init mmio_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) || cpu_mitigations_off()) { @@ -416,15 +412,20 @@ static void __init mmio_select_mitigation(void) if (mmio_mitigation == MMIO_MITIGATION_OFF) return; - ia32_cap = x86_read_arch_cap_msr(); - /* * Enable CPU buffer clear mitigation for host and VMM, if also affected * by MDS or TAA. Otherwise, enable mitigation for VMM only. */ if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + + /* + * X86_FEATURE_CLEAR_CPU_BUF could be enabled by other VERW based + * mitigations, disable KVM-only mitigation in that case. + */ + if (boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) + static_branch_disable(&mmio_stale_data_clear); else static_branch_enable(&mmio_stale_data_clear); @@ -433,7 +434,7 @@ static void __init mmio_select_mitigation(void) * be propagated to uncore buffers, clearing the Fill buffers on idle * is required irrespective of SMT state. */ - if (!(ia32_cap & ARCH_CAP_FBSDP_NO)) + if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) static_branch_enable(&mds_idle_clear); /* @@ -443,10 +444,10 @@ static void __init mmio_select_mitigation(void) * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS * affected systems. */ - if ((ia32_cap & ARCH_CAP_FB_CLEAR) || + if ((x86_arch_cap_msr & ARCH_CAP_FB_CLEAR) || (boot_cpu_has(X86_FEATURE_MD_CLEAR) && boot_cpu_has(X86_FEATURE_FLUSH_L1D) && - !(ia32_cap & ARCH_CAP_MDS_NO))) + !(x86_arch_cap_msr & ARCH_CAP_MDS_NO))) mmio_mitigation = MMIO_MITIGATION_VERW; else mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED; @@ -476,6 +477,57 @@ static int __init mmio_stale_data_parse_cmdline(char *str) } early_param("mmio_stale_data", mmio_stale_data_parse_cmdline); +#undef pr_fmt +#define pr_fmt(fmt) "Register File Data Sampling: " fmt + +enum rfds_mitigations { + RFDS_MITIGATION_OFF, + RFDS_MITIGATION_VERW, + RFDS_MITIGATION_UCODE_NEEDED, +}; + +/* Default mitigation for Register File Data Sampling */ +static enum rfds_mitigations rfds_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF; + +static const char * const rfds_strings[] = { + [RFDS_MITIGATION_OFF] = "Vulnerable", + [RFDS_MITIGATION_VERW] = "Mitigation: Clear Register File", + [RFDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", +}; + +static void __init rfds_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off()) { + rfds_mitigation = RFDS_MITIGATION_OFF; + return; + } + if (rfds_mitigation == RFDS_MITIGATION_OFF) + return; + + if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + else + rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED; +} + +static __init int rfds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + return 0; + + if (!strcmp(str, "off")) + rfds_mitigation = RFDS_MITIGATION_OFF; + else if (!strcmp(str, "on")) + rfds_mitigation = RFDS_MITIGATION_VERW; + + return 0; +} +early_param("reg_file_data_sampling", rfds_parse_cmdline); + #undef pr_fmt #define pr_fmt(fmt) "" fmt @@ -484,12 +536,12 @@ static void __init md_clear_update_mitigation(void) if (cpu_mitigations_off()) return; - if (!static_key_enabled(&mds_user_clear)) + if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) goto out; /* - * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data - * mitigation, if necessary. + * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO + * Stale Data mitigation, if necessary. */ if (mds_mitigation == MDS_MITIGATION_OFF && boot_cpu_has_bug(X86_BUG_MDS)) { @@ -501,11 +553,19 @@ static void __init md_clear_update_mitigation(void) taa_mitigation = TAA_MITIGATION_VERW; taa_select_mitigation(); } - if (mmio_mitigation == MMIO_MITIGATION_OFF && - boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { + /* + * MMIO_MITIGATION_OFF is not checked here so that mmio_stale_data_clear + * gets updated correctly as per X86_FEATURE_CLEAR_CPU_BUF state. + */ + if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { mmio_mitigation = MMIO_MITIGATION_VERW; mmio_select_mitigation(); } + if (rfds_mitigation == RFDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_RFDS)) { + rfds_mitigation = RFDS_MITIGATION_VERW; + rfds_select_mitigation(); + } out: if (boot_cpu_has_bug(X86_BUG_MDS)) pr_info("MDS: %s\n", mds_strings[mds_mitigation]); @@ -515,6 +575,8 @@ static void __init md_clear_update_mitigation(void) pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) pr_info("MMIO Stale Data: Unknown: No mitigations\n"); + if (boot_cpu_has_bug(X86_BUG_RFDS)) + pr_info("Register File Data Sampling: %s\n", rfds_strings[rfds_mitigation]); } static void __init md_clear_select_mitigation(void) @@ -522,11 +584,12 @@ static void __init md_clear_select_mitigation(void) mds_select_mitigation(); taa_select_mitigation(); mmio_select_mitigation(); + rfds_select_mitigation(); /* - * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update - * and print their mitigation after MDS, TAA and MMIO Stale Data - * mitigation selection is done. + * As these mitigations are inter-related and rely on VERW instruction + * to clear the microarchitural buffers, update and print their status + * after mitigation selection is done for each of these vulnerabilities. */ md_clear_update_mitigation(); } @@ -593,8 +656,6 @@ void update_srbds_msr(void) static void __init srbds_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_SRBDS)) return; @@ -603,8 +664,7 @@ static void __init srbds_select_mitigation(void) * are only exposed to SRBDS when TSX is enabled or when CPU is affected * by Processor MMIO Stale Data vulnerability. */ - ia32_cap = x86_read_arch_cap_msr(); - if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && + if ((x86_arch_cap_msr & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && !boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) srbds_mitigation = SRBDS_MITIGATION_TSX_OFF; else if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) @@ -747,7 +807,7 @@ static void __init gds_select_mitigation(void) /* Will verify below that mitigation _can_ be disabled */ /* No microcode */ - if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { + if (!(x86_arch_cap_msr & ARCH_CAP_GDS_CTRL)) { if (gds_mitigation == GDS_MITIGATION_FORCE) { /* * This only needs to be done on the boot CPU so do it @@ -1042,8 +1102,7 @@ static void __init retbleed_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_UNRET); - if (IS_ENABLED(CONFIG_RETHUNK)) - x86_return_thunk = retbleed_return_thunk; + x86_return_thunk = retbleed_return_thunk; if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) @@ -1054,8 +1113,25 @@ static void __init retbleed_select_mitigation(void) case RETBLEED_MITIGATION_IBPB: setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + + /* + * IBPB on entry already obviates the need for + * software-based untraining so clear those in case some + * other mitigation like SRSO has selected them. + */ + setup_clear_cpu_cap(X86_FEATURE_UNRET); + setup_clear_cpu_cap(X86_FEATURE_RETHUNK); + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); mitigate_smt = true; + + /* + * There is no need for RSB filling: entry_ibpb() ensures + * all predictions, including the RSB, are invalidated, + * regardless of IBPB implementation. + */ + setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT); + break; case RETBLEED_MITIGATION_STUFF: @@ -1478,20 +1554,25 @@ static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) return SPECTRE_V2_RETPOLINE; } +static bool __ro_after_init rrsba_disabled; + /* Disable in-kernel use of non-RSB RET predictors */ static void __init spec_ctrl_disable_kernel_rrsba(void) { - u64 ia32_cap; + if (rrsba_disabled) + return; - if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + if (!(x86_arch_cap_msr & ARCH_CAP_RRSBA)) { + rrsba_disabled = true; return; + } - ia32_cap = x86_read_arch_cap_msr(); + if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + return; - if (ia32_cap & ARCH_CAP_RRSBA) { - x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; - update_spec_ctrl(x86_spec_ctrl_base); - } + x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + rrsba_disabled = true; } static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode) @@ -1541,6 +1622,74 @@ static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_ dump_stack(); } +/* + * Set BHI_DIS_S to prevent indirect branches in kernel to be influenced by + * branch history in userspace. Not needed if BHI_NO is set. + */ +static bool __init spec_ctrl_bhi_dis(void) +{ + if (!boot_cpu_has(X86_FEATURE_BHI_CTRL)) + return false; + + x86_spec_ctrl_base |= SPEC_CTRL_BHI_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_HW); + + return true; +} + +enum bhi_mitigations { + BHI_MITIGATION_OFF, + BHI_MITIGATION_ON, +}; + +static enum bhi_mitigations bhi_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_SPECTRE_BHI) ? BHI_MITIGATION_ON : BHI_MITIGATION_OFF; + +static int __init spectre_bhi_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + bhi_mitigation = BHI_MITIGATION_OFF; + else if (!strcmp(str, "on")) + bhi_mitigation = BHI_MITIGATION_ON; + else + pr_err("Ignoring unknown spectre_bhi option (%s)", str); + + return 0; +} +early_param("spectre_bhi", spectre_bhi_parse_cmdline); + +static void __init bhi_select_mitigation(void) +{ + if (bhi_mitigation == BHI_MITIGATION_OFF) + return; + + /* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) { + spec_ctrl_disable_kernel_rrsba(); + if (rrsba_disabled) + return; + } + + if (spec_ctrl_bhi_dis()) + return; + + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + /* Mitigate KVM by default */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); + pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n"); + + /* Mitigate syscalls when the mitigation is forced =on */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP); + pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n"); +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -1652,6 +1801,9 @@ static void __init spectre_v2_select_mitigation(void) mode == SPECTRE_V2_RETPOLINE) spec_ctrl_disable_kernel_rrsba(); + if (boot_cpu_has(X86_BUG_BHI)) + bhi_select_mitigation(); + spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); @@ -1766,8 +1918,6 @@ static void update_indir_branch_cond(void) /* Update the static key controlling the MDS CPU buffer clear in idle */ static void update_mds_branch_idle(void) { - u64 ia32_cap = x86_read_arch_cap_msr(); - /* * Enable the idle clearing if SMT is active on CPUs which are * affected only by MSBDS and not any other MDS variant. @@ -1782,7 +1932,7 @@ static void update_mds_branch_idle(void) if (sched_smt_active()) { static_branch_enable(&mds_idle_clear); } else if (mmio_mitigation == MMIO_MITIGATION_OFF || - (ia32_cap & ARCH_CAP_FBSDP_NO)) { + (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) { static_branch_disable(&mds_idle_clear); } } @@ -2353,6 +2503,8 @@ early_param("l1tf", l1tf_cmdline); enum srso_mitigation { SRSO_MITIGATION_NONE, + SRSO_MITIGATION_UCODE_NEEDED, + SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED, SRSO_MITIGATION_MICROCODE, SRSO_MITIGATION_SAFE_RET, SRSO_MITIGATION_IBPB, @@ -2368,11 +2520,13 @@ enum srso_mitigation_cmd { }; static const char * const srso_strings[] = { - [SRSO_MITIGATION_NONE] = "Vulnerable", - [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode", - [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET", - [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", - [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only" + [SRSO_MITIGATION_NONE] = "Vulnerable", + [SRSO_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED] = "Vulnerable: Safe RET, no microcode", + [SRSO_MITIGATION_MICROCODE] = "Vulnerable: Microcode, no safe RET", + [SRSO_MITIGATION_SAFE_RET] = "Mitigation: Safe RET", + [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", + [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only" }; static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; @@ -2409,10 +2563,7 @@ static void __init srso_select_mitigation(void) if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) goto pred_cmd; - if (!has_microcode) { - pr_warn("IBPB-extending microcode not applied!\n"); - pr_warn(SRSO_NOTICE); - } else { + if (has_microcode) { /* * Zen1/2 with SMT off aren't vulnerable after the right * IBPB microcode has been applied. @@ -2421,14 +2572,17 @@ static void __init srso_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_SRSO_NO); return; } - } - if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { - if (has_microcode) { - pr_err("Retbleed IBPB mitigation enabled, using same for SRSO\n"); + if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { srso_mitigation = SRSO_MITIGATION_IBPB; - goto pred_cmd; + goto out; } + } else { + pr_warn("IBPB-extending microcode not applied!\n"); + pr_warn(SRSO_NOTICE); + + /* may be overwritten by SRSO_CMD_SAFE_RET below */ + srso_mitigation = SRSO_MITIGATION_UCODE_NEEDED; } switch (srso_cmd) { @@ -2458,7 +2612,10 @@ static void __init srso_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_SRSO); x86_return_thunk = srso_return_thunk; } - srso_mitigation = SRSO_MITIGATION_SAFE_RET; + if (has_microcode) + srso_mitigation = SRSO_MITIGATION_SAFE_RET; + else + srso_mitigation = SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED; } else { pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); goto pred_cmd; @@ -2470,6 +2627,14 @@ static void __init srso_select_mitigation(void) if (has_microcode) { setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); srso_mitigation = SRSO_MITIGATION_IBPB; + + /* + * IBPB on entry already obviates the need for + * software-based untraining so clear those in case some + * other mitigation like Retbleed has selected them. + */ + setup_clear_cpu_cap(X86_FEATURE_UNRET); + setup_clear_cpu_cap(X86_FEATURE_RETHUNK); } } else { pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); @@ -2482,6 +2647,13 @@ static void __init srso_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; + + /* + * There is no need for RSB filling: entry_ibpb() ensures + * all predictions, including the RSB, are invalidated, + * regardless of IBPB implementation. + */ + setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT); } } else { pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); @@ -2493,10 +2665,11 @@ static void __init srso_select_mitigation(void) break; } - pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode")); +out: + pr_info("%s\n", srso_strings[srso_mitigation]); pred_cmd: - if ((boot_cpu_has(X86_FEATURE_SRSO_NO) || srso_cmd == SRSO_CMD_OFF) && + if ((!boot_cpu_has_bug(X86_BUG_SRSO) || srso_cmd == SRSO_CMD_OFF) && boot_cpu_has(X86_FEATURE_SBPB)) x86_pred_cmd = PRED_CMD_SBPB; } @@ -2608,6 +2781,11 @@ static ssize_t mmio_stale_data_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t rfds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); +} + static char *stibp_state(void) { if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && @@ -2616,15 +2794,15 @@ static char *stibp_state(void) switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: - return ", STIBP: disabled"; + return "; STIBP: disabled"; case SPECTRE_V2_USER_STRICT: - return ", STIBP: forced"; + return "; STIBP: forced"; case SPECTRE_V2_USER_STRICT_PREFERRED: - return ", STIBP: always-on"; + return "; STIBP: always-on"; case SPECTRE_V2_USER_PRCTL: case SPECTRE_V2_USER_SECCOMP: if (static_key_enabled(&switch_to_cond_stibp)) - return ", STIBP: conditional"; + return "; STIBP: conditional"; } return ""; } @@ -2633,10 +2811,10 @@ static char *ibpb_state(void) { if (boot_cpu_has(X86_FEATURE_IBPB)) { if (static_key_enabled(&switch_mm_always_ibpb)) - return ", IBPB: always-on"; + return "; IBPB: always-on"; if (static_key_enabled(&switch_mm_cond_ibpb)) - return ", IBPB: conditional"; - return ", IBPB: disabled"; + return "; IBPB: conditional"; + return "; IBPB: disabled"; } return ""; } @@ -2646,14 +2824,32 @@ static char *pbrsb_eibrs_state(void) if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) || boot_cpu_has(X86_FEATURE_RSB_VMEXIT)) - return ", PBRSB-eIBRS: SW sequence"; + return "; PBRSB-eIBRS: SW sequence"; else - return ", PBRSB-eIBRS: Vulnerable"; + return "; PBRSB-eIBRS: Vulnerable"; } else { - return ", PBRSB-eIBRS: Not affected"; + return "; PBRSB-eIBRS: Not affected"; } } +static const char *spectre_bhi_state(void) +{ + if (!boot_cpu_has_bug(X86_BUG_BHI)) + return "; BHI: Not affected"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW)) + return "; BHI: BHI_DIS_S"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP)) + return "; BHI: SW loop, KVM: SW loop"; + else if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) && + rrsba_disabled) + return "; BHI: Retpoline"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT)) + return "; BHI: Vulnerable, KVM: SW loop"; + + return "; BHI: Vulnerable"; +} + static ssize_t spectre_v2_show_state(char *buf) { if (spectre_v2_enabled == SPECTRE_V2_LFENCE) @@ -2666,13 +2862,15 @@ static ssize_t spectre_v2_show_state(char *buf) spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); - return sysfs_emit(buf, "%s%s%s%s%s%s%s\n", + return sysfs_emit(buf, "%s%s%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], ibpb_state(), - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? "; IBRS_FW" : "", stibp_state(), - boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? "; RSB filling" : "", pbrsb_eibrs_state(), + spectre_bhi_state(), + /* this should always be at the end */ spectre_v2_module_string()); } @@ -2704,9 +2902,7 @@ static ssize_t srso_show_state(char *buf) if (boot_cpu_has(X86_FEATURE_SRSO_NO)) return sysfs_emit(buf, "Mitigation: SMT disabled\n"); - return sysfs_emit(buf, "%s%s\n", - srso_strings[srso_mitigation], - boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) ? "" : ", no microcode"); + return sysfs_emit(buf, "%s\n", srso_strings[srso_mitigation]); } static ssize_t gds_show_state(char *buf) @@ -2769,6 +2965,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_GDS: return gds_show_state(buf); + case X86_BUG_RFDS: + return rfds_show_state(buf); + default: break; } @@ -2843,4 +3042,9 @@ ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_GDS); } + +ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4e5ffc8b0e469d..7a1e58fb43a033 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1165,6 +1165,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_SPECTRE_V2 BIT(8) #define NO_MMIO BIT(9) #define NO_EIBRS_PBRSB BIT(10) +#define NO_BHI BIT(11) #define VULNWL(vendor, family, model, whitelist) \ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) @@ -1227,18 +1228,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), /* Zhaoxin Family 7 */ - VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), - VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), {} }; @@ -1269,6 +1270,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define SRSO BIT(5) /* CPU is affected by GDS */ #define GDS BIT(6) +/* CPU is affected by Register File Data Sampling */ +#define RFDS BIT(7) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1296,9 +1299,18 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE_L, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GRACEMONT, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), @@ -1317,28 +1329,46 @@ static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long whi u64 x86_read_arch_cap_msr(void) { - u64 ia32_cap = 0; + u64 x86_arch_cap_msr = 0; if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr); - return ia32_cap; + return x86_arch_cap_msr; } -static bool arch_cap_mmio_immune(u64 ia32_cap) +static bool arch_cap_mmio_immune(u64 x86_arch_cap_msr) { - return (ia32_cap & ARCH_CAP_FBSDP_NO && - ia32_cap & ARCH_CAP_PSDP_NO && - ia32_cap & ARCH_CAP_SBDR_SSDP_NO); + return (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO && + x86_arch_cap_msr & ARCH_CAP_PSDP_NO && + x86_arch_cap_msr & ARCH_CAP_SBDR_SSDP_NO); +} + +static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr) +{ + /* The "immunity" bit trumps everything else: */ + if (x86_arch_cap_msr & ARCH_CAP_RFDS_NO) + return false; + + /* + * VMMs set ARCH_CAP_RFDS_CLEAR for processors not in the blacklist to + * indicate that mitigation is needed because guest is running on a + * vulnerable hardware or may migrate to such hardware: + */ + if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) + return true; + + /* Only consult the blacklist when there is no enumeration: */ + return cpu_matches(cpu_vuln_blacklist, RFDS); } static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { - u64 ia32_cap = x86_read_arch_cap_msr(); + u64 x86_arch_cap_msr = x86_read_arch_cap_msr(); /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) && - !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + !(x86_arch_cap_msr & ARCH_CAP_PSCHANGE_MC_NO)) setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION)) @@ -1350,7 +1380,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_SPECTRE_V2); if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) && - !(ia32_cap & ARCH_CAP_SSB_NO) && + !(x86_arch_cap_msr & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); @@ -1358,15 +1388,15 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature * flag and protect from vendor-specific bugs via the whitelist. */ - if ((ia32_cap & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { + if ((x86_arch_cap_msr & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && - !(ia32_cap & ARCH_CAP_PBRSB_NO)) + !(x86_arch_cap_msr & ARCH_CAP_PBRSB_NO)) setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); } if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && - !(ia32_cap & ARCH_CAP_MDS_NO)) { + !(x86_arch_cap_msr & ARCH_CAP_MDS_NO)) { setup_force_cpu_bug(X86_BUG_MDS); if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY)) setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); @@ -1385,9 +1415,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * TSX_CTRL check alone is not sufficient for cases when the microcode * update is not present or running as guest that don't get TSX_CTRL. */ - if (!(ia32_cap & ARCH_CAP_TAA_NO) && + if (!(x86_arch_cap_msr & ARCH_CAP_TAA_NO) && (cpu_has(c, X86_FEATURE_RTM) || - (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) + (x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR))) setup_force_cpu_bug(X86_BUG_TAA); /* @@ -1413,7 +1443,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist, * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits. */ - if (!arch_cap_mmio_immune(ia32_cap)) { + if (!arch_cap_mmio_immune(x86_arch_cap_msr)) { if (cpu_matches(cpu_vuln_blacklist, MMIO)) setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO)) @@ -1421,7 +1451,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) } if (!cpu_has(c, X86_FEATURE_BTC_NO)) { - if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA)) + if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (x86_arch_cap_msr & ARCH_CAP_RSBA)) setup_force_cpu_bug(X86_BUG_RETBLEED); } @@ -1439,15 +1469,28 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * disabling AVX2. The only way to do this in HW is to clear XCR0[2], * which means that AVX will be disabled. */ - if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) && + if (cpu_matches(cpu_vuln_blacklist, GDS) && !(x86_arch_cap_msr & ARCH_CAP_GDS_NO) && boot_cpu_has(X86_FEATURE_AVX)) setup_force_cpu_bug(X86_BUG_GDS); + if (vulnerable_to_rfds(x86_arch_cap_msr)) + setup_force_cpu_bug(X86_BUG_RFDS); + + /* When virtualized, eIBRS could be hidden, assume vulnerable */ + if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) && + !cpu_matches(cpu_vuln_whitelist, NO_BHI) && + (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) || + boot_cpu_has(X86_FEATURE_HYPERVISOR))) + setup_force_cpu_bug(X86_BUG_BHI); + + if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET)) + setup_force_cpu_bug(X86_BUG_IBPB_NO_RET); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; /* Rogue Data Cache Load? No! */ - if (ia32_cap & ARCH_CAP_RDCL_NO) + if (x86_arch_cap_msr & ARCH_CAP_RDCL_NO) return; setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); @@ -1858,6 +1901,13 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); #endif + + /* + * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and + * Hygon will clear it in ->c_init() below. + */ + set_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); + /* * Vendor-specific initialization. In this section we * canonicalize the feature flags, meaning if there are @@ -2087,7 +2137,7 @@ void syscall_init(void) (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1)); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else - wrmsrl_cstar((unsigned long)ignore_sysret); + wrmsrl_cstar((unsigned long)entry_SYSCALL32_ignore); wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG); wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL); diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index e462c1d3800a6c..6fb6d8a57cecaf 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -44,7 +44,10 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, { X86_FEATURE_AES, X86_FEATURE_XMM2 }, { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, + { X86_FEATURE_GFNI, X86_FEATURE_XMM2 }, { X86_FEATURE_FMA, X86_FEATURE_AVX }, + { X86_FEATURE_VAES, X86_FEATURE_AVX }, + { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX }, { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, @@ -56,9 +59,6 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, - { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index defdc594be14df..6e738759779e81 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -87,8 +87,12 @@ static void hygon_get_topology(struct cpuinfo_x86 *c) if (!err) c->x86_coreid_bits = get_count_order(c->x86_max_cores); - /* Socket ID is ApicId[6] for these processors. */ - c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT; + /* + * Socket ID is ApicId[6] for the processors with model <= 0x3 + * when running on host. + */ + if (!boot_cpu_has(X86_FEATURE_HYPERVISOR) && c->x86_model <= 0x3) + c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT; cacheinfo_hygon_init_llc_id(c, cpu); } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { @@ -344,6 +348,9 @@ static void init_hygon(struct cpuinfo_x86 *c) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); check_null_seg_clears_base(c); + + /* Hygon CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */ + clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); } static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index be4045628fd33b..aa3e7ed0eb3d7f 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -184,6 +184,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) return false; } +#define MSR_IA32_TME_ACTIVATE 0x982 + +/* Helpers to access TME_ACTIVATE MSR */ +#define TME_ACTIVATE_LOCKED(x) (x & 0x1) +#define TME_ACTIVATE_ENABLED(x) (x & 0x2) + +#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ +#define TME_ACTIVATE_POLICY_AES_XTS_128 0 + +#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ + +#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ +#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 + +/* Values for mktme_status (SW only construct) */ +#define MKTME_ENABLED 0 +#define MKTME_DISABLED 1 +#define MKTME_UNINITIALIZED 2 +static int mktme_status = MKTME_UNINITIALIZED; + +static void detect_tme_early(struct cpuinfo_x86 *c) +{ + u64 tme_activate, tme_policy, tme_crypto_algs; + int keyid_bits = 0, nr_keyids = 0; + static u64 tme_activate_cpu0 = 0; + + rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); + + if (mktme_status != MKTME_UNINITIALIZED) { + if (tme_activate != tme_activate_cpu0) { + /* Broken BIOS? */ + pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); + pr_err_once("x86/tme: MKTME is not usable\n"); + mktme_status = MKTME_DISABLED; + + /* Proceed. We may need to exclude bits from x86_phys_bits. */ + } + } else { + tme_activate_cpu0 = tme_activate; + } + + if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { + pr_info_once("x86/tme: not enabled by BIOS\n"); + mktme_status = MKTME_DISABLED; + return; + } + + if (mktme_status != MKTME_UNINITIALIZED) + goto detect_keyid_bits; + + pr_info("x86/tme: enabled by BIOS\n"); + + tme_policy = TME_ACTIVATE_POLICY(tme_activate); + if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) + pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); + + tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); + if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { + pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", + tme_crypto_algs); + mktme_status = MKTME_DISABLED; + } +detect_keyid_bits: + keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); + nr_keyids = (1UL << keyid_bits) - 1; + if (nr_keyids) { + pr_info_once("x86/mktme: enabled by BIOS\n"); + pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); + } else { + pr_info_once("x86/mktme: disabled by BIOS\n"); + } + + if (mktme_status == MKTME_UNINITIALIZED) { + /* MKTME is usable */ + mktme_status = MKTME_ENABLED; + } + + /* + * KeyID bits effectively lower the number of physical address + * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + */ + c->x86_phys_bits -= keyid_bits; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -335,6 +419,13 @@ static void early_init_intel(struct cpuinfo_x86 *c) */ if (detect_extended_topology_early(c) < 0) detect_ht_early(c); + + /* + * Adjust the number of physical bits early because it affects the + * valid bits of the MTRR mask registers. + */ + if (cpu_has(c, X86_FEATURE_TME)) + detect_tme_early(c); } static void bsp_init_intel(struct cpuinfo_x86 *c) @@ -495,90 +586,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -#define MSR_IA32_TME_ACTIVATE 0x982 - -/* Helpers to access TME_ACTIVATE MSR */ -#define TME_ACTIVATE_LOCKED(x) (x & 0x1) -#define TME_ACTIVATE_ENABLED(x) (x & 0x2) - -#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ -#define TME_ACTIVATE_POLICY_AES_XTS_128 0 - -#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ - -#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ -#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 - -/* Values for mktme_status (SW only construct) */ -#define MKTME_ENABLED 0 -#define MKTME_DISABLED 1 -#define MKTME_UNINITIALIZED 2 -static int mktme_status = MKTME_UNINITIALIZED; - -static void detect_tme(struct cpuinfo_x86 *c) -{ - u64 tme_activate, tme_policy, tme_crypto_algs; - int keyid_bits = 0, nr_keyids = 0; - static u64 tme_activate_cpu0 = 0; - - rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); - - if (mktme_status != MKTME_UNINITIALIZED) { - if (tme_activate != tme_activate_cpu0) { - /* Broken BIOS? */ - pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); - pr_err_once("x86/tme: MKTME is not usable\n"); - mktme_status = MKTME_DISABLED; - - /* Proceed. We may need to exclude bits from x86_phys_bits. */ - } - } else { - tme_activate_cpu0 = tme_activate; - } - - if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { - pr_info_once("x86/tme: not enabled by BIOS\n"); - mktme_status = MKTME_DISABLED; - return; - } - - if (mktme_status != MKTME_UNINITIALIZED) - goto detect_keyid_bits; - - pr_info("x86/tme: enabled by BIOS\n"); - - tme_policy = TME_ACTIVATE_POLICY(tme_activate); - if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) - pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); - - tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); - if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { - pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", - tme_crypto_algs); - mktme_status = MKTME_DISABLED; - } -detect_keyid_bits: - keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); - nr_keyids = (1UL << keyid_bits) - 1; - if (nr_keyids) { - pr_info_once("x86/mktme: enabled by BIOS\n"); - pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); - } else { - pr_info_once("x86/mktme: disabled by BIOS\n"); - } - - if (mktme_status == MKTME_UNINITIALIZED) { - /* MKTME is usable */ - mktme_status = MKTME_ENABLED; - } - - /* - * KeyID bits effectively lower the number of physical address - * bits. Update cpuinfo_x86::x86_phys_bits accordingly. - */ - c->x86_phys_bits -= keyid_bits; -} - static void init_cpuid_fault(struct cpuinfo_x86 *c) { u64 msr; @@ -715,9 +722,6 @@ static void init_intel(struct cpuinfo_x86 *c) init_ia32_feat_ctl(c); - if (cpu_has(c, X86_FEATURE_TME)) - detect_tme(c); - init_intel_misc_features(c); split_lock_init(); diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index ad6776081e60da..ae71b8ef909c9a 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -39,9 +39,7 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match) const struct x86_cpu_id *m; struct cpuinfo_x86 *c = &boot_cpu_data; - for (m = match; - m->vendor | m->family | m->model | m->steppings | m->feature; - m++) { + for (m = match; m->flags & X86_CPU_ID_FLAG_ENTRY_VALID; m++) { if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor) continue; if (m->family != X86_FAMILY_ANY && c->x86 != m->family) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 6f35f724cc142e..e103c227acd3ae 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include @@ -233,6 +234,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) struct llist_node *pending; struct mce_evt_llist *l; int apei_err = 0; + struct page *p; /* * Allow instrumentation around external facilities usage. Not that it @@ -286,6 +288,20 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) if (!fake_panic) { if (panic_timeout == 0) panic_timeout = mca_cfg.panic_timeout; + + /* + * Kdump skips the poisoned page in order to avoid + * touching the error bits again. Poison the page even + * if the error is fatal and the machine is about to + * panic. + */ + if (kexec_crash_loaded()) { + if (final && (final->status & MCI_STATUS_ADDRV)) { + p = pfn_to_online_page(final->addr >> PAGE_SHIFT); + if (p) + SetPageHWPoison(p); + } + } panic(msg); } else pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg); @@ -2452,12 +2468,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, return -EINVAL; b = &per_cpu(mce_banks_array, s->id)[bank]; - if (!b->init) return -ENODEV; b->ctl = new; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); return size; } diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 4d8d4bcf915ddd..72f0695c3dc1dd 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -746,6 +746,7 @@ static void check_hw_inj_possible(void) wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), status); rdmsrl_safe(mca_msr_reg(bank, MCA_STATUS), &status); + wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), 0); if (!status) { hw_injection_possible = false; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 6cc7a2c181da5f..a4ebd5e0ae8287 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -208,6 +208,11 @@ static int __init save_microcode_in_initrd(void) struct cpuinfo_x86 *c = &boot_cpu_data; int ret = -EINVAL; + if (dis_ucode_ldr) { + ret = 0; + goto out; + } + switch (c->x86_vendor) { case X86_VENDOR_INTEL: if (c->x86 >= 6) @@ -221,6 +226,7 @@ static int __init save_microcode_in_initrd(void) break; } +out: initrd_gone = true; return ret; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index e6bba12c759cb7..bcb2d640a0cd85 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -199,8 +199,8 @@ static void hv_machine_shutdown(void) * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor * corrupts the old VP Assist Pages and can crash the kexec kernel. */ - if (kexec_in_progress && hyperv_init_cpuhp > 0) - cpuhp_remove_state(hyperv_init_cpuhp); + if (kexec_in_progress) + cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE); /* The function calls stop_other_cpus(). */ native_machine_shutdown(); @@ -423,6 +423,7 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { x86_platform.calibrate_tsc = hv_get_tsc_khz; x86_platform.calibrate_cpu = hv_get_tsc_khz; + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); } if (ms_hyperv.priv_high & HV_ISOLATION) { diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 767bf1c71aadda..2a2fc14955cd3b 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -609,7 +609,7 @@ void mtrr_save_state(void) { int first_cpu; - if (!mtrr_enabled()) + if (!mtrr_enabled() || !mtrr_state.have_fixed) return; first_cpu = cpumask_first(cpu_online_mask); diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 030d3b409768de..10830995eadab6 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -193,7 +193,7 @@ static inline bool rdt_get_mb_table(struct rdt_resource *r) return false; } -static bool __get_mem_config_intel(struct rdt_resource *r) +static __init bool __get_mem_config_intel(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); union cpuid_0x10_3_eax eax; @@ -227,12 +227,10 @@ static bool __get_mem_config_intel(struct rdt_resource *r) return true; } -static bool __rdt_get_mem_config_amd(struct rdt_resource *r) +static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - union cpuid_0x10_3_eax eax; - union cpuid_0x10_x_edx edx; - u32 ebx, ecx, subleaf; + u32 eax, ebx, ecx, edx, subleaf; /* * Query CPUID_Fn80000020_EDX_x01 for MBA and @@ -240,9 +238,9 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r) */ subleaf = (r->rid == RDT_RESOURCE_SMBA) ? 2 : 1; - cpuid_count(0x80000020, subleaf, &eax.full, &ebx, &ecx, &edx.full); - hw_res->num_closid = edx.split.cos_max + 1; - r->default_ctrl = MAX_MBA_BW_AMD; + cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx); + hw_res->num_closid = edx + 1; + r->default_ctrl = 1 << eax; /* AMD does not use delay */ r->membw.delay_linear = false; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 85ceaf9a31ac20..566386abb877f9 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -18,7 +18,6 @@ #define MBM_OVERFLOW_INTERVAL 1000 #define MAX_MBA_BW 100u #define MBA_IS_LINEAR 0x4 -#define MAX_MBA_BW_AMD 0x800 #define MBM_CNTR_WIDTH_OFFSET_AMD 20 #define RMID_VAL_ERROR BIT_ULL(63) @@ -296,14 +295,10 @@ struct rftype { * struct mbm_state - status for each MBM counter in each domain * @prev_bw_bytes: Previous bytes value read for bandwidth calculation * @prev_bw: The most recent bandwidth in MBps - * @delta_bw: Difference between the current and previous bandwidth - * @delta_comp: Indicates whether to compute the delta_bw */ struct mbm_state { u64 prev_bw_bytes; u32 prev_bw; - u32 delta_bw; - bool delta_comp; }; /** @@ -395,6 +390,8 @@ struct rdt_parse_data { * @msr_update: Function pointer to update QOS MSRs * @mon_scale: cqm counter * mon_scale = occupancy in bytes * @mbm_width: Monitor width, to detect and correct for overflow. + * @mbm_cfg_mask: Bandwidth sources that can be tracked when Bandwidth + * Monitoring Event Configuration (BMEC) is supported. * @cdp_enabled: CDP state of this resource * * Members of this structure are either private to the architecture @@ -409,6 +406,7 @@ struct rdt_hw_resource { struct rdt_resource *r); unsigned int mon_scale; unsigned int mbm_width; + unsigned int mbm_cfg_mask; bool cdp_enabled; }; diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index f136ac046851c8..3a6c069614eb84 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -440,9 +440,6 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) cur_bw = bytes / SZ_1M; - if (m->delta_comp) - m->delta_bw = abs(cur_bw - m->prev_bw); - m->delta_comp = false; m->prev_bw = cur_bw; } @@ -520,11 +517,11 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) { u32 closid, rmid, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; - u32 cur_bw, delta_bw, user_bw; struct rdt_resource *r_mba; struct rdt_domain *dom_mba; struct list_head *head; struct rdtgroup *entry; + u32 cur_bw, user_bw; if (!is_mbm_local_enabled()) return; @@ -543,7 +540,6 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) cur_bw = pmbm_data->prev_bw; user_bw = dom_mba->mbps_val[closid]; - delta_bw = pmbm_data->delta_bw; /* MBA resource doesn't support CDP */ cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE); @@ -555,49 +551,31 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) list_for_each_entry(entry, head, mon.crdtgrp_list) { cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; cur_bw += cmbm_data->prev_bw; - delta_bw += cmbm_data->delta_bw; } /* * Scale up/down the bandwidth linearly for the ctrl group. The * bandwidth step is the bandwidth granularity specified by the * hardware. - * - * The delta_bw is used when increasing the bandwidth so that we - * dont alternately increase and decrease the control values - * continuously. - * - * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if - * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep - * switching between 90 and 110 continuously if we only check - * cur_bw < user_bw. + * Always increase throttling if current bandwidth is above the + * target set by user. + * But avoid thrashing up and down on every poll by checking + * whether a decrease in throttling is likely to push the group + * back over target. E.g. if currently throttling to 30% of bandwidth + * on a system with 10% granularity steps, check whether moving to + * 40% would go past the limit by multiplying current bandwidth by + * "(30 + 10) / 30". */ if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) { new_msr_val = cur_msr_val - r_mba->membw.bw_gran; } else if (cur_msr_val < MAX_MBA_BW && - (user_bw > (cur_bw + delta_bw))) { + (user_bw > (cur_bw * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) { new_msr_val = cur_msr_val + r_mba->membw.bw_gran; } else { return; } resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); - - /* - * Delta values are updated dynamically package wise for each - * rdtgrp every time the throttle MSR changes value. - * - * This is because (1)the increase in bandwidth is not perfectly - * linear and only "approximately" linear even when the hardware - * says it is linear.(2)Also since MBA is a core specific - * mechanism, the delta values vary based on number of cores used - * by the rdtgrp. - */ - pmbm_data->delta_comp = true; - list_for_each_entry(entry, head, mon.crdtgrp_list) { - cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; - cmbm_data->delta_comp = true; - } } static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) @@ -813,6 +791,12 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) return ret; if (rdt_cpu_has(X86_FEATURE_BMEC)) { + u32 eax, ebx, ecx, edx; + + /* Detect list of bandwidth sources that can be tracked */ + cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx); + hw_res->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS; + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { mbm_total_event.configurable = true; mbm_config_rftype_init("mbm_total_bytes_config"); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 725344048f85da..d82d5de183b107 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1553,12 +1553,6 @@ static int mbm_config_write_domain(struct rdt_resource *r, struct mon_config_info mon_info = {0}; int ret = 0; - /* mon_config cannot be more than the supported set of events */ - if (val > MAX_EVT_CONFIG_BITS) { - rdt_last_cmd_puts("Invalid event configuration\n"); - return -EINVAL; - } - /* * Read the current config value first. If both are the same then * no need to write it again. @@ -1596,6 +1590,7 @@ static int mbm_config_write_domain(struct rdt_resource *r, static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); char *dom_str = NULL, *id_str; unsigned long dom_id, val; struct rdt_domain *d; @@ -1619,6 +1614,13 @@ static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) return -EINVAL; } + /* Value from user cannot be more than the supported set of events */ + if ((val & hw_res->mbm_cfg_mask) != val) { + rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n", + hw_res->mbm_cfg_mask); + return -EINVAL; + } + list_for_each_entry(d, &r->domains, list) { if (d->id == dom_id) { ret = mbm_config_write_domain(r, d, evtid, val); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 0dad49a09b7a9e..af5aa2c754c222 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -28,6 +28,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 }, { X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 }, + { X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 }, { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 }, @@ -49,6 +50,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 }, { X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 }, { X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 }, + { X86_FEATURE_AMD_LBR_PMC_FREEZE, CPUID_EAX, 2, 0x80000022, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 166692f2d50111..c7f8c3200e8d7f 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -474,24 +474,25 @@ struct sgx_epc_page *__sgx_alloc_epc_page(void) { struct sgx_epc_page *page; int nid_of_current = numa_node_id(); - int nid = nid_of_current; + int nid_start, nid; - if (node_isset(nid_of_current, sgx_numa_mask)) { - page = __sgx_alloc_epc_page_from_node(nid_of_current); - if (page) - return page; - } - - /* Fall back to the non-local NUMA nodes: */ - while (true) { - nid = next_node_in(nid, sgx_numa_mask); - if (nid == nid_of_current) - break; + /* + * Try local node first. If it doesn't have an EPC section, + * fall back to the non-local NUMA nodes. + */ + if (node_isset(nid_of_current, sgx_numa_mask)) + nid_start = nid_of_current; + else + nid_start = next_node_in(nid_of_current, sgx_numa_mask); + nid = nid_start; + do { page = __sgx_alloc_epc_page_from_node(nid); if (page) return page; - } + + nid = next_node_in(nid, sgx_numa_mask); + } while (nid != nid_start); return ERR_PTR(-ENOMEM); } diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 87d38f17ff5c9c..c13c9cb40b9b46 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -82,7 +82,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev) ret = pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); if (ret) - return ret; + return pcibios_err_to_errno(ret); if (!pin) return 0; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index fb8cf953380dab..b66f540de054a7 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1017,10 +1017,12 @@ void __init e820__reserve_setup_data(void) e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); /* - * SETUP_EFI and SETUP_IMA are supplied by kexec and do not need - * to be reserved. + * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by + * kexec and do not need to be reserved. */ - if (data->type != SETUP_EFI && data->type != SETUP_IMA) + if (data->type != SETUP_EFI && + data->type != SETUP_IMA && + data->type != SETUP_RNG_SEED) e820__range_update_kexec(pa_data, sizeof(*data) + data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c index e963344b044902..53935b4d62e305 100644 --- a/arch/x86/kernel/eisa.c +++ b/arch/x86/kernel/eisa.c @@ -2,6 +2,7 @@ /* * EISA specific code */ +#include #include #include #include @@ -12,7 +13,7 @@ static __init int eisa_bus_probe(void) { void __iomem *p; - if (xen_pv_domain() && !xen_initial_domain()) + if ((xen_pv_domain() && !xen_initial_domain()) || cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) return 0; p = ioremap(0x0FFFD9, 4); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index a21a4d0ecc345b..4b414b0ab0692a 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -145,8 +145,8 @@ void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask) asm volatile( "fnclex\n\t" "emms\n\t" - "fildl %P[addr]" /* set F?P to defined value */ - : : [addr] "m" (fpstate)); + "fildl %[addr]" /* set F?P to defined value */ + : : [addr] "m" (*fpstate)); } if (use_xsave()) { diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 558076dbde5bfc..2b3b9e140dd41b 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -156,7 +156,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, return !err; } -static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) +static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pkru) { if (use_xsave()) return xsave_to_user_sigframe(buf); @@ -185,7 +185,7 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) * For [f]xsave state, update the SW reserved fields in the [f]xsave frame * indicating the absence/presence of the extended state to the user. */ -bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) +bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size, u32 pkru) { struct task_struct *tsk = current; struct fpstate *fpstate = tsk->thread.fpu.fpstate; @@ -228,7 +228,7 @@ bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) fpregs_restore_userregs(); pagefault_disable(); - ret = copy_fpregs_to_sigframe(buf_fx); + ret = copy_fpregs_to_sigframe(buf_fx, pkru); pagefault_enable(); fpregs_unlock(); @@ -274,12 +274,13 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures, * Attempt to restore the FPU registers directly from user memory. * Pagefaults are handled and any errors returned are fatal. */ -static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, - bool fx_only, unsigned int size) +static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only) { struct fpu *fpu = ¤t->thread.fpu; int ret; + /* Restore enabled features only. */ + xrestore &= fpu->fpstate->user_xfeatures; retry: fpregs_lock(); /* Ensure that XFD is up to date */ @@ -309,7 +310,7 @@ static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, if (ret != X86_TRAP_PF) return false; - if (!fault_in_readable(buf, size)) + if (!fault_in_readable(buf, fpu->fpstate->user_size)) goto retry; return false; } @@ -339,7 +340,6 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, struct user_i387_ia32_struct env; bool success, fx_only = false; union fpregs_state *fpregs; - unsigned int state_size; u64 user_xfeatures = 0; if (use_xsave()) { @@ -349,17 +349,14 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, return false; fx_only = !fx_sw_user.magic1; - state_size = fx_sw_user.xstate_size; user_xfeatures = fx_sw_user.xfeatures; } else { user_xfeatures = XFEATURE_MASK_FPSSE; - state_size = fpu->fpstate->user_size; } if (likely(!ia32_fxstate)) { /* Restore the FPU registers directly from user memory. */ - return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only, - state_size); + return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only); } /* diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index ef6906107c541d..255ff8f6c52705 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -178,10 +178,11 @@ void fpu__init_cpu_xstate(void) * Must happen after CR4 setup and before xsetbv() to allow KVM * lazy passthrough. Write independent of the dynamic state static * key as that does not work on the boot CPU. This also ensures - * that any stale state is wiped out from XFD. + * that any stale state is wiped out from XFD. Reset the per CPU + * xfd cache too. */ if (cpu_feature_enabled(X86_FEATURE_XFD)) - wrmsrl(MSR_IA32_XFD, init_fpstate.xfd); + xfd_set_state(init_fpstate.xfd); /* * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features @@ -787,6 +788,9 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) goto out_disable; } + fpu_kernel_cfg.independent_features = fpu_kernel_cfg.max_features & + XFEATURE_MASK_INDEPENDENT; + /* * Clear XSAVE features that are disabled in the normal CPUID. */ diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index 3518fb26d06b02..544224611e23c5 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -64,9 +64,9 @@ static inline u64 xfeatures_mask_supervisor(void) static inline u64 xfeatures_mask_independent(void) { if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) - return XFEATURE_MASK_INDEPENDENT & ~XFEATURE_MASK_LBR; + return fpu_kernel_cfg.independent_features & ~XFEATURE_MASK_LBR; - return XFEATURE_MASK_INDEPENDENT; + return fpu_kernel_cfg.independent_features; } /* XSAVE/XRSTOR wrapper functions */ @@ -148,20 +148,26 @@ static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rs #endif #ifdef CONFIG_X86_64 +static inline void xfd_set_state(u64 xfd) +{ + wrmsrl(MSR_IA32_XFD, xfd); + __this_cpu_write(xfd_state, xfd); +} + static inline void xfd_update_state(struct fpstate *fpstate) { if (fpu_state_size_dynamic()) { u64 xfd = fpstate->xfd; - if (__this_cpu_read(xfd_state) != xfd) { - wrmsrl(MSR_IA32_XFD, xfd); - __this_cpu_write(xfd_state, xfd); - } + if (__this_cpu_read(xfd_state) != xfd) + xfd_set_state(xfd); } } extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu); #else +static inline void xfd_set_state(u64 xfd) { } + static inline void xfd_update_state(struct fpstate *fpstate) { } static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) { diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 49f7629b17f734..c58213bce294e9 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -41,6 +41,7 @@ #include #include #include +#include /* * Manage page tables very early on. @@ -80,12 +81,10 @@ static struct desc_struct startup_gdt[GDT_ENTRIES] = { * while the kernel still uses a direct mapping. */ static struct desc_ptr startup_gdt_descr = { - .size = sizeof(startup_gdt), + .size = sizeof(startup_gdt)-1, .address = 0, }; -#define __head __section(".head.text") - static void __head *fixup_pointer(void *ptr, unsigned long physaddr) { return ptr - (void *)_text + (void *)physaddr; diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index ea6995920b7aa9..e6eaee8509ceed 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -256,6 +256,22 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) testl $X2APIC_ENABLE, %eax jnz .Lread_apicid_msr +#ifdef CONFIG_X86_X2APIC + /* + * If system is in X2APIC mode then MMIO base might not be + * mapped causing the MMIO read below to fault. Faults can't + * be handled at that point. + */ + cmpl $0, x2apic_mode(%rip) + jz .Lread_apicid_mmio + + /* Force the AP into X2APIC mode. */ + orl $X2APIC_ENABLE, %eax + wrmsr + jmp .Lread_apicid_msr +#endif + +.Lread_apicid_mmio: /* Read the APIC ID from the fix-mapped MMIO space. */ movq apic_mmio_base(%rip), %rcx addq $APIC_ID, %rcx diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 1648aa0204d97d..046bc9d57e9966 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1438,7 +1438,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) memset(&curr_time, 0, sizeof(struct rtc_time)); if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) { - if (unlikely(mc146818_get_time(&curr_time) < 0)) { + if (unlikely(mc146818_get_time(&curr_time, 10) < 0)) { pr_err_ratelimited("unable to read current time from RTC\n"); return IRQ_HANDLED; } diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index b786d48f5a0faf..fc77a96040b7ea 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -117,7 +117,7 @@ static const __initconst struct idt_data def_idts[] = { SYSG(X86_TRAP_OF, asm_exc_overflow), #if defined(CONFIG_IA32_EMULATION) - SYSG(IA32_SYSCALL_VECTOR, entry_INT80_compat), + SYSG(IA32_SYSCALL_VECTOR, asm_int80_emulation), #elif defined(CONFIG_X86_32) SYSG(IA32_SYSCALL_VECTOR, entry_INT80_32), #endif diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c index 578d16fc040fa1..5481c7c5db301b 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index e8babebad7b888..a6a3475e1d6097 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -335,7 +335,16 @@ static int can_probe(unsigned long paddr) kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset, bool *on_func_entry) { - if (is_endbr(*(u32 *)addr)) { + u32 insn; + + /* + * Since 'addr' is not guaranteed to be safe to access, use + * copy_from_kernel_nofault() to read the instruction: + */ + if (copy_from_kernel_nofault(&insn, (void *)addr, sizeof(u32))) + return NULL; + + if (is_endbr(insn)) { *on_func_entry = !offset || offset == 4; if (*on_func_entry) offset = 4; @@ -576,7 +585,8 @@ static void kprobe_emulate_call_indirect(struct kprobe *p, struct pt_regs *regs) { unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg]; - int3_emulate_call(regs, regs_get_register(regs, offs)); + int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + p->ainsn.size); + int3_emulate_jmp(regs, regs_get_register(regs, offs)); } NOKPROBE_SYMBOL(kprobe_emulate_call_indirect); diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index dd2ec14adb77ba..15af7e98e161a4 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -21,6 +21,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe_ctlblk *kcb; int bit; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index fb8f52149be9ad..f2fff625576d56 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -24,8 +24,8 @@ static int kvmclock __initdata = 1; static int kvmclock_vsyscall __initdata = 1; -static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME; -static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK; +static int msr_kvm_system_time __ro_after_init; +static int msr_kvm_wall_clock __ro_after_init; static u64 kvm_sched_clock_offset __ro_after_init; static int __init parse_no_kvmclock(char *arg) @@ -195,7 +195,8 @@ static void kvm_setup_secondary_clock(void) void kvmclock_disable(void) { - native_write_msr(msr_kvm_system_time, 0, 0); + if (msr_kvm_system_time) + native_write_msr(msr_kvm_system_time, 0, 0); } static void __init kvmclock_init_mem(void) @@ -294,7 +295,10 @@ void __init kvmclock_init(void) if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) { msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW; msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW; - } else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { + } else if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { + msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; + msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK; + } else { return; } diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 1a3e2c05a8a5b6..2fa12d1dc67602 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -28,6 +28,7 @@ #include #include #include +#include #ifdef CONFIG_ACPI /* @@ -90,6 +91,8 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p) { #ifdef CONFIG_EFI unsigned long mstart, mend; + void *kaddr; + int ret; if (!efi_enabled(EFI_BOOT)) return 0; @@ -105,6 +108,30 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p) if (!mstart) return 0; + ret = kernel_ident_mapping_init(info, level4p, mstart, mend); + if (ret) + return ret; + + kaddr = memremap(mstart, mend - mstart, MEMREMAP_WB); + if (!kaddr) { + pr_err("Could not map UEFI system table\n"); + return -ENOMEM; + } + + mstart = efi_config_table; + + if (efi_enabled(EFI_64BIT)) { + efi_system_table_64_t *stbl = (efi_system_table_64_t *)kaddr; + + mend = mstart + sizeof(efi_config_table_64_t) * stbl->nr_tables; + } else { + efi_system_table_32_t *stbl = (efi_system_table_32_t *)kaddr; + + mend = mstart + sizeof(efi_config_table_32_t) * stbl->nr_tables; + } + + memunmap(kaddr); + return kernel_ident_mapping_init(info, level4p, mstart, mend); #endif return 0; @@ -298,8 +325,15 @@ void machine_kexec_cleanup(struct kimage *image) void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; - void *control_page; + unsigned int host_mem_enc_active; int save_ftrace_enabled; + void *control_page; + + /* + * This must be done before load_segments() since if call depth tracking + * is used then GS must be valid to make any function calls. + */ + host_mem_enc_active = cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) @@ -361,7 +395,7 @@ void machine_kexec(struct kimage *image) (unsigned long)page_list, image->start, image->preserve_context, - cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)); + host_mem_enc_active); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index c94dec6a18345a..1f54eedc3015e9 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index a0c551846b35f1..87aee638e1a5d8 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -507,12 +507,13 @@ DEFINE_IDTENTRY_RAW(exc_nmi) } this_cpu_write(nmi_state, NMI_EXECUTING); this_cpu_write(nmi_cr2, read_cr2()); + +nmi_restart: if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) { WRITE_ONCE(nsp->idt_seq, nsp->idt_seq + 1); WARN_ON_ONCE(!(nsp->idt_seq & 0x1)); WRITE_ONCE(nsp->recv_jiffies, jiffies); } -nmi_restart: /* * Needs to happen before DR7 is accessed, because the hypervisor can @@ -548,16 +549,13 @@ DEFINE_IDTENTRY_RAW(exc_nmi) if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) write_cr2(this_cpu_read(nmi_cr2)); - if (this_cpu_dec_return(nmi_state)) - goto nmi_restart; - - if (user_mode(regs)) - mds_user_clear_cpu_buffers(); if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) { WRITE_ONCE(nsp->idt_seq, nsp->idt_seq + 1); WARN_ON_ONCE(nsp->idt_seq & 0x1); WRITE_ONCE(nsp->recv_jiffies, jiffies); } + if (this_cpu_dec_return(nmi_state)) + goto nmi_restart; } #if IS_ENABLED(CONFIG_KVM_INTEL) @@ -631,7 +629,7 @@ void nmi_backtrace_stall_check(const struct cpumask *btp) msgp = nmi_check_stall_msg[idx]; if (nsp->idt_ignored_snap != READ_ONCE(nsp->idt_ignored) && (idx & 0x1)) modp = ", but OK because ignore_nmis was set"; - if (nmi_seq & ~0x1) + if (nmi_seq & 0x1) msghp = " (CPU currently in NMI handler function)"; else if (nsp->idt_nmi_seq_snap + 1 == nmi_seq) msghp = " (CPU exited one NMI handler function)"; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 97f1436c1a2034..8d51c86caa415f 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -71,13 +71,12 @@ DEFINE_PARAVIRT_ASM(pv_native_irq_enable, "sti", .noinstr.text); DEFINE_PARAVIRT_ASM(pv_native_read_cr2, "mov %cr2, %rax", .noinstr.text); #endif -DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); +DEFINE_STATIC_KEY_FALSE(virt_spin_lock_key); void __init native_pv_lock_init(void) { - if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) && - !boot_cpu_has(X86_FEATURE_HYPERVISOR)) - static_branch_disable(&virt_spin_lock_key); + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + static_branch_enable(&virt_spin_lock_key); } static void native_tlb_remove_table(struct mmu_gather *tlb, void *table) diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 319fef37d9dce4..cc2c34ba7228ac 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -203,16 +203,6 @@ void __init probe_roms(void) unsigned char c; int i; - /* - * The ROM memory range is not part of the e820 table and is therefore not - * pre-validated by BIOS. The kernel page table maps the ROM region as encrypted - * memory, and SNP requires encrypted memory to be validated before access. - * Do that here. - */ - snp_prep_memory(video_rom_resource.start, - ((system_rom_resource.end + 1) - video_rom_resource.start), - SNP_PAGE_STATE_PRIVATE); - /* video rom */ upper = adapter_rom_resources[0].start; for (start = video_rom_resource.start; start < upper; start += 2048) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b6f4e8399fca20..5351f293f770b5 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -1030,7 +1030,10 @@ unsigned long arch_align_stack(unsigned long sp) unsigned long arch_randomize_brk(struct mm_struct *mm) { - return randomize_page(mm->brk, 0x02000000); + if (mmap_is_ia32()) + return randomize_page(mm->brk, SZ_32M); + + return randomize_page(mm->brk, SZ_1G); } /* diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 33b268747bb7bb..d595ef7c1de05e 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -138,7 +138,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, log_lvl, d3, d6, d7); } - if (cpu_feature_enabled(X86_FEATURE_OSPKE)) + if (cr4 & X86_CR4_PKE) printk("%sPKRU: %08x\n", log_lvl, read_pkru()); } @@ -750,6 +750,27 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr) #define LAM_U57_BITS 6 +static void enable_lam_func(void *__mm) +{ + struct mm_struct *mm = __mm; + + if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm) { + write_cr3(__read_cr3() | mm->context.lam_cr3_mask); + set_tlbstate_lam_mode(mm); + } +} + +static void mm_enable_lam(struct mm_struct *mm) +{ + /* + * Even though the process must still be single-threaded at this + * point, kernel threads may be using the mm. IPI those kernel + * threads if they exist. + */ + on_each_cpu_mask(mm_cpumask(mm), enable_lam_func, mm, true); + set_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags); +} + static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits) { if (!cpu_feature_enabled(X86_FEATURE_LAM)) @@ -766,6 +787,10 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits) if (mmap_write_lock_killable(mm)) return -EINTR; + /* + * MM_CONTEXT_LOCK_LAM is set on clone. Prevent LAM from + * being enabled unless the process is single threaded: + */ if (test_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags)) { mmap_write_unlock(mm); return -EBUSY; @@ -782,9 +807,7 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits) return -EINVAL; } - write_cr3(__read_cr3() | mm->context.lam_cr3_mask); - set_tlbstate_lam_mode(mm); - set_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags); + mm_enable_lam(mm); mmap_write_unlock(mm); diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 1309b9b053386b..2e7066980f3e8b 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -67,7 +67,7 @@ void mach_get_cmos_time(struct timespec64 *now) return; } - if (mc146818_get_time(&tm)) { + if (mc146818_get_time(&tm, 1000)) { pr_err("Unable to read current time from RTC\n"); now->tv_sec = now->tv_nsec = 0; return; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b098b1fa247081..eb129277dcdd64 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include #include @@ -36,6 +35,7 @@ #include #include #include +#include #include #include #include @@ -1029,7 +1029,7 @@ void __init setup_arch(char **cmdline_p) efi_init(); reserve_ibft_region(); - dmi_setup(); + x86_init.resources.dmi_setup(); /* * VMware detection requires dmi to be available, so this @@ -1121,6 +1121,7 @@ void __init setup_arch(char **cmdline_p) * memory size. */ sev_setup_arch(); + cc_random_init(); efi_fake_memmap(); efi_find_mirror(); diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index ccb0915e84e10c..acbec4de3ec31a 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -89,7 +89,8 @@ static bool __init sev_es_check_cpu_features(void) return true; } -static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason) +static void __head __noreturn +sev_es_terminate(unsigned int set, unsigned int reason) { u64 val = GHCB_MSR_TERM_REQ; @@ -326,13 +327,7 @@ static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid */ static const struct snp_cpuid_table *snp_cpuid_get_table(void) { - void *ptr; - - asm ("lea cpuid_table_copy(%%rip), %0" - : "=r" (ptr) - : "p" (&cpuid_table_copy)); - - return ptr; + return &RIP_REL_REF(cpuid_table_copy); } /* @@ -391,7 +386,7 @@ static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted) return xsave_size; } -static bool +static bool __head snp_cpuid_get_validated_func(struct cpuid_leaf *leaf) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -528,7 +523,8 @@ static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt, * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value * should be treated as fatal by caller. */ -static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) +static int __head +snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -556,9 +552,9 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0; /* Skip post-processing for out-of-range zero leafs. */ - if (!(leaf->fn <= cpuid_std_range_max || - (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) || - (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max))) + if (!(leaf->fn <= RIP_REL_REF(cpuid_std_range_max) || + (leaf->fn >= 0x40000000 && leaf->fn <= RIP_REL_REF(cpuid_hyp_range_max)) || + (leaf->fn >= 0x80000000 && leaf->fn <= RIP_REL_REF(cpuid_ext_range_max)))) return 0; } @@ -570,7 +566,7 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le * page yet, so it only supports the MSR based communication with the * hypervisor and only the CPUID exit-code. */ -void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) +void __head do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) { unsigned int subfn = lower_bits(regs->cx, 32); unsigned int fn = lower_bits(regs->ax, 32); @@ -1016,7 +1012,8 @@ struct cc_setup_data { * Search for a Confidential Computing blob passed in as a setup_data entry * via the Linux Boot Protocol. */ -static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) +static __head +struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) { struct cc_setup_data *sd = NULL; struct setup_data *hdr; @@ -1043,7 +1040,7 @@ static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) * mapping needs to be updated in sync with all the changes to virtual memory * layout and related mapping facilities throughout the boot process. */ -static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) +static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info) { const struct snp_cpuid_table *cpuid_table_fw, *cpuid_table; int i; @@ -1063,11 +1060,11 @@ static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) const struct snp_cpuid_fn *fn = &cpuid_table->fn[i]; if (fn->eax_in == 0x0) - cpuid_std_range_max = fn->eax; + RIP_REL_REF(cpuid_std_range_max) = fn->eax; else if (fn->eax_in == 0x40000000) - cpuid_hyp_range_max = fn->eax; + RIP_REL_REF(cpuid_hyp_range_max) = fn->eax; else if (fn->eax_in == 0x80000000) - cpuid_ext_range_max = fn->eax; + RIP_REL_REF(cpuid_ext_range_max) = fn->eax; } } diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 6395bfd87b68b5..9905dc0e0b0960 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -23,8 +23,10 @@ #include #include #include +#include #include +#include #include #include #include @@ -682,8 +684,9 @@ static u64 __init get_jump_table_addr(void) return ret; } -static void early_set_pages_state(unsigned long vaddr, unsigned long paddr, - unsigned long npages, enum psc_op op) +static void __head +early_set_pages_state(unsigned long vaddr, unsigned long paddr, + unsigned long npages, enum psc_op op) { unsigned long paddr_end; u64 val; @@ -739,7 +742,7 @@ static void early_set_pages_state(unsigned long vaddr, unsigned long paddr, sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); } -void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, +void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { /* @@ -748,7 +751,7 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd * This eliminates worries about jump tables or checking boot_cpu_data * in the cc_platform_has() function. */ - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED)) return; /* @@ -767,28 +770,13 @@ void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr * This eliminates worries about jump tables or checking boot_cpu_data * in the cc_platform_has() function. */ - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED)) return; /* Ask hypervisor to mark the memory pages shared in the RMP table. */ early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED); } -void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) -{ - unsigned long vaddr, npages; - - vaddr = (unsigned long)__va(paddr); - npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; - - if (op == SNP_PAGE_STATE_PRIVATE) - early_snp_set_memory_private(vaddr, paddr, npages); - else if (op == SNP_PAGE_STATE_SHARED) - early_snp_set_memory_shared(vaddr, paddr, npages); - else - WARN(1, "invalid memory op %d\n", op); -} - static unsigned long __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr, unsigned long vaddr_end, int op) { @@ -1234,10 +1222,6 @@ void setup_ghcb(void) if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) return; - /* First make sure the hypervisor talks a supported protocol. */ - if (!sev_es_negotiate_protocol()) - sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); - /* * Check whether the runtime #VC exception handler is active. It uses * the per-CPU GHCB page which is set up by sev_es_init_vc_handling(). @@ -1254,6 +1238,13 @@ void setup_ghcb(void) return; } + /* + * Make sure the hypervisor talks a supported protocol. + * This gets called only in the BSP boot phase. + */ + if (!sev_es_negotiate_protocol()) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); + /* * Clear the boot_ghcb. The first exception comes in before the bss * section is cleared. @@ -2056,7 +2047,7 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs) * * Scan for the blob in that order. */ -static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) +static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) { struct cc_blob_sev_info *cc_info; @@ -2082,7 +2073,7 @@ static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) return cc_info; } -bool __init snp_init(struct boot_params *bp) +bool __head snp_init(struct boot_params *bp) { struct cc_blob_sev_info *cc_info; @@ -2104,11 +2095,22 @@ bool __init snp_init(struct boot_params *bp) return true; } -void __init __noreturn snp_abort(void) +void __head __noreturn snp_abort(void) { sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); } +/* + * SEV-SNP guests should only execute dmi_setup() if EFI_CONFIG_TABLES are + * enabled, as the alternative (fallback) logic for DMI probing in the legacy + * ROM region can cause a crash since this region is not pre-validated. + */ +void __init snp_dmi_setup(void) +{ + if (efi_enabled(EFI_CONFIG_TABLES)) + dmi_setup(); +} + static void dump_cpuid_table(void) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c index 59e15dd8d0f866..19e4db582fb69a 100644 --- a/arch/x86/kernel/shstk.c +++ b/arch/x86/kernel/shstk.c @@ -577,3 +577,14 @@ long shstk_prctl(struct task_struct *task, int option, unsigned long arg2) return wrss_control(true); return -EINVAL; } + +int shstk_update_last_frame(unsigned long val) +{ + unsigned long ssp; + + if (!features_enabled(ARCH_SHSTK_SHSTK)) + return 0; + + ssp = get_user_shstk_addr(); + return write_user_shstk_64((u64 __user *)ssp, (u64)val); +} diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 65fe2094da59b8..876d3b30c2c774 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -83,6 +83,7 @@ get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, unsigned long math_size = 0; unsigned long sp = regs->sp; unsigned long buf_fx = 0; + u32 pkru = read_pkru(); /* redzone */ if (!ia32_frame) @@ -138,7 +139,7 @@ get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, } /* save i387 and extended state */ - if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size)) + if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size, pkru)) return (void __user *)-1L; return (void __user *)sp; diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index cacf2ede62175d..449a6ed0b8c982 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -175,9 +175,6 @@ int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) frame = get_sigframe(ksig, regs, sizeof(struct rt_sigframe), &fp); uc_flags = frame_uc_flags(regs); - if (setup_signal_shadow_stack(ksig)) - return -EFAULT; - if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; @@ -198,6 +195,9 @@ int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) return -EFAULT; } + if (setup_signal_shadow_stack(ksig)) + return -EFAULT; + /* Set up registers for signal handler */ regs->di = ksig->sig; /* In case the signal handler was declared without prototypes */ @@ -260,13 +260,13 @@ SYSCALL_DEFINE0(rt_sigreturn) set_current_blocked(&set); - if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) + if (restore_altstack(&frame->uc.uc_stack)) goto badframe; - if (restore_signal_shadow_stack()) + if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) goto badframe; - if (restore_altstack(&frame->uc.uc_stack)) + if (restore_signal_shadow_stack()) goto badframe; return regs->ax; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2a187c0cbd5b11..ce77dac9a0202a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -60,6 +60,7 @@ #include #include #include +#include #include #include diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index e42faa792c0793..52e1f3f0b361ce 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -27,25 +27,7 @@ unsigned long profile_pc(struct pt_regs *regs) { - unsigned long pc = instruction_pointer(regs); - - if (!user_mode(regs) && in_lock_functions(pc)) { -#ifdef CONFIG_FRAME_POINTER - return *(unsigned long *)(regs->bp + sizeof(long)); -#else - unsigned long *sp = (unsigned long *)regs->sp; - /* - * Return address is either directly at stack pointer - * or above a saved flags. Eflags has bits 22-31 zero, - * kernel addresses don't. - */ - if (sp[0] >> 22) - return sp[0]; - if (sp[1] >> 22) - return sp[1]; -#endif - } - return pc; + return instruction_pointer(regs); } EXPORT_SYMBOL(profile_pc); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 1123ef3ccf9011..4334033658edfb 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -193,11 +193,9 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu) cur->warned = false; /* - * If a non-zero TSC value for socket 0 may be valid then the default - * adjusted value cannot assumed to be zero either. + * The default adjust value cannot be assumed to be zero on any socket. */ - if (tsc_async_resets) - cur->adjusted = bootval; + cur->adjusted = bootval; /* * Check whether this CPU is the first in a package to come up. In diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 6c07f6daaa227a..6402fb3089d262 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -1076,8 +1076,13 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs return orig_ret_vaddr; nleft = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize); - if (likely(!nleft)) + if (likely(!nleft)) { + if (shstk_update_last_frame(trampoline_vaddr)) { + force_sig(SIGSEGV); + return -1; + } return orig_ret_vaddr; + } if (nleft != rasize) { pr_err("return address clobbered: pid=%d, %%sp=%#lx, %%ip=%#lx\n", diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index f15fb71f280e24..54a5596adaa61e 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -139,10 +139,7 @@ SECTIONS STATIC_CALL_TEXT ALIGN_ENTRY_TEXT_BEGIN -#ifdef CONFIG_CPU_SRSO *(.text..__x86.rethunk_untrain) -#endif - ENTRY_TEXT #ifdef CONFIG_CPU_SRSO @@ -520,12 +517,12 @@ INIT_PER_CPU(irq_stack_backing_store); "fixed_percpu_data is not at start of per-cpu area"); #endif -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_CPU_UNRET_ENTRY . = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned"); -. = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); #endif #ifdef CONFIG_CPU_SRSO +. = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); /* * GNU ld cannot do XOR until 2.41. * https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=f6f78318fca803c4907fb8d7f6ded8295f1947b1 diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index a37ebd3b47736d..268627a17cf0d8 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -3,10 +3,12 @@ * * For licencing details see kernel-base/COPYING */ +#include #include #include #include #include +#include #include #include @@ -66,6 +68,7 @@ struct x86_init_ops x86_init __initdata = { .probe_roms = probe_roms, .reserve_resources = reserve_standard_io_resources, .memory_setup = e820__memory_setup_default, + .dmi_setup = dmi_setup, }, .mpparse = { diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 80e3fe184d17e6..a99ffc3f3a3fdb 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -26,6 +26,10 @@ kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \ vmx/hyperv.o vmx/nested.o vmx/posted_intr.o kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o +ifdef CONFIG_HYPERV +kvm-intel-y += vmx/vmx_onhyperv.o +endif + kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \ svm/sev.o svm/hyperv.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 773132c3bf5af7..ac042a9a61f576 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -362,6 +362,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_update_pv_runtime(vcpu); + vcpu->arch.is_amd_compatible = guest_cpuid_is_amd_or_hygon(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); @@ -677,6 +678,11 @@ void kvm_set_cpu_caps(void) F(AMX_COMPLEX) ); + kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX, + F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) | + F(BHI_CTRL) | F(MCDT_NO) + ); + kvm_cpu_cap_mask(CPUID_D_1_EAX, F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd ); @@ -956,13 +962,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) break; /* function 7 has additional index. */ case 7: - entry->eax = min(entry->eax, 1u); + max_idx = entry->eax = min(entry->eax, 2u); cpuid_entry_override(entry, CPUID_7_0_EBX); cpuid_entry_override(entry, CPUID_7_ECX); cpuid_entry_override(entry, CPUID_7_EDX); - /* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */ - if (entry->eax == 1) { + /* KVM only supports up to 0x7.2, capped above via min(). */ + if (max_idx >= 1) { entry = do_host_cpuid(array, function, 1); if (!entry) goto out; @@ -972,6 +978,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ebx = 0; entry->ecx = 0; } + if (max_idx >= 2) { + entry = do_host_cpuid(array, function, 2); + if (!entry) + goto out; + + cpuid_entry_override(entry, CPUID_7_2_EDX); + entry->ecx = 0; + entry->ebx = 0; + entry->eax = 0; + } break; case 0xa: { /* Architectural Performance Monitoring */ union cpuid10_eax eax; @@ -1196,9 +1212,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = 0; break; case 0x80000008: { - unsigned g_phys_as = (entry->eax >> 16) & 0xff; - unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); - unsigned phys_as = entry->eax & 0xff; + unsigned int virt_as = max((entry->eax >> 8) & 0xff, 48U); + unsigned int phys_as; /* * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as @@ -1206,16 +1221,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * reductions in MAXPHYADDR for memory encryption affect shadow * paging, too. * - * If TDP is enabled but an explicit guest MAXPHYADDR is not - * provided, use the raw bare metal MAXPHYADDR as reductions to - * the HPAs do not affect GPAs. + * If TDP is enabled, use the raw bare metal MAXPHYADDR as + * reductions to the HPAs do not affect GPAs. */ - if (!tdp_enabled) - g_phys_as = boot_cpu_data.x86_phys_bits; - else if (!g_phys_as) - g_phys_as = phys_as; + if (!tdp_enabled) { + phys_as = boot_cpu_data.x86_phys_bits; + } else { + phys_as = entry->eax & 0xff; + } - entry->eax = g_phys_as | (virt_as << 8); + entry->eax = phys_as | (virt_as << 8); entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 284fa4704553da..57ee789ada1411 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -125,6 +125,16 @@ static inline bool guest_cpuid_is_intel(struct kvm_vcpu *vcpu) return best && is_guest_vendor_intel(best->ebx, best->ecx, best->edx); } +static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.is_amd_compatible; +} + +static inline bool guest_cpuid_is_intel_compatible(struct kvm_vcpu *vcpu) +{ + return !guest_cpuid_is_amd_compatible(vcpu); +} + static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 7c2dac6824e262..238afd7335e46d 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -727,10 +727,12 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, stimer_cleanup(stimer); stimer->count = count; - if (stimer->count == 0) - stimer->config.enable = 0; - else if (stimer->config.auto_enable) - stimer->config.enable = 1; + if (!host) { + if (stimer->count == 0) + stimer->config.enable = 0; + else if (stimer->config.auto_enable) + stimer->config.enable = 1; + } if (stimer->config.enable) stimer_mark_pending(stimer, false); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3e977dbbf9933d..1380f34897770d 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -41,6 +41,7 @@ #include "ioapic.h" #include "trace.h" #include "x86.h" +#include "xen.h" #include "cpuid.h" #include "hyperv.h" #include "smm.h" @@ -499,8 +500,10 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) } /* Check if there are APF page ready requests pending */ - if (enabled) + if (enabled) { kvm_make_request(KVM_REQ_APF_READY, apic->vcpu); + kvm_xen_sw_enable_lapic(apic->vcpu); + } } static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id) @@ -2440,26 +2443,49 @@ void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); +#define X2APIC_ICR_RESERVED_BITS (GENMASK_ULL(31, 20) | GENMASK_ULL(17, 16) | BIT(13)) + +int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data) +{ + if (data & X2APIC_ICR_RESERVED_BITS) + return 1; + + /* + * The BUSY bit is reserved on both Intel and AMD in x2APIC mode, but + * only AMD requires it to be zero, Intel essentially just ignores the + * bit. And if IPI virtualization (Intel) or x2AVIC (AMD) is enabled, + * the CPU performs the reserved bits checks, i.e. the underlying CPU + * behavior will "win". Arbitrarily clear the BUSY bit, as there is no + * sane way to provide consistent behavior with respect to hardware. + */ + data &= ~APIC_ICR_BUSY; + + kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32)); + kvm_lapic_set_reg64(apic, APIC_ICR, data); + trace_kvm_apic_write(APIC_ICR, data); + return 0; +} + /* emulate APIC access in a trap manner */ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) { struct kvm_lapic *apic = vcpu->arch.apic; - u64 val; /* - * ICR is a single 64-bit register when x2APIC is enabled. For legacy - * xAPIC, ICR writes need to go down the common (slightly slower) path - * to get the upper half from ICR2. + * ICR is a single 64-bit register when x2APIC is enabled, all others + * registers hold 32-bit values. For legacy xAPIC, ICR writes need to + * go down the common path to get the upper half from ICR2. + * + * Note, using the write helpers may incur an unnecessary write to the + * virtual APIC state, but KVM needs to conditionally modify the value + * in certain cases, e.g. to clear the ICR busy bit. The cost of extra + * conditional branches is likely a wash relative to the cost of the + * maybe-unecessary write, and both are in the noise anyways. */ - if (apic_x2apic_mode(apic) && offset == APIC_ICR) { - val = kvm_lapic_get_reg64(apic, APIC_ICR); - kvm_apic_send_ipi(apic, (u32)val, (u32)(val >> 32)); - trace_kvm_apic_write(APIC_ICR, val); - } else { - /* TODO: optimize to just emulate side effect w/o one more write */ - val = kvm_lapic_get_reg(apic, offset); - kvm_lapic_reg_write(apic, offset, (u32)val); - } + if (apic_x2apic_mode(apic) && offset == APIC_ICR) + WARN_ON_ONCE(kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR))); + else + kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset)); } EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode); @@ -2670,6 +2696,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) u64 msr_val; int i; + static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu); + if (!init_event) { msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_reset_bsp(vcpu)) @@ -2767,7 +2795,8 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); - if (r && lvt_type == APIC_LVTPC) + if (r && lvt_type == APIC_LVTPC && + guest_cpuid_is_intel_compatible(apic->vcpu)) kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); return r; } @@ -2981,6 +3010,8 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) struct kvm_lapic *apic = vcpu->arch.apic; int r; + static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu); + kvm_lapic_set_base(vcpu, vcpu->arch.apic_base); /* set SPIV separately to get count of SW disabled APICs right */ apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV))); @@ -3145,16 +3176,6 @@ int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) return 0; } -int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data) -{ - data &= ~APIC_ICR_BUSY; - - kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32)); - kvm_lapic_set_reg64(apic, APIC_ICR, data); - trace_kvm_apic_write(APIC_ICR, data); - return 0; -} - static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data) { u32 low; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index f7901cb4d2fa4b..294775b7383b42 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3120,7 +3120,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, if (pud_none(pud) || !pud_present(pud)) goto out; - if (pud_large(pud)) { + if (pud_leaf(pud)) { level = PG_LEVEL_1G; goto out; } @@ -4788,7 +4788,7 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, context->cpu_role.base.level, is_efer_nx(context), guest_can_use(vcpu, X86_FEATURE_GBPAGES), is_cr4_pse(context), - guest_cpuid_is_amd_or_hygon(vcpu)); + guest_cpuid_is_amd_compatible(vcpu)); } static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 6cd4dd631a2fac..8eef3ed5fe04e2 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1506,6 +1506,16 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, } } +static bool tdp_mmu_need_write_protect(struct kvm_mmu_page *sp) +{ + /* + * All TDP MMU shadow pages share the same role as their root, aside + * from level, so it is valid to key off any shadow page to determine if + * write protection is needed for an entire tree. + */ + return kvm_mmu_page_ad_need_write_protect(sp) || !kvm_ad_enabled(); +} + /* * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. @@ -1516,7 +1526,8 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end) { - u64 dbit = kvm_ad_enabled() ? shadow_dirty_mask : PT_WRITABLE_MASK; + const u64 dbit = tdp_mmu_need_write_protect(root) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; bool spte_set = false; @@ -1530,7 +1541,7 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, if (!is_shadow_present_pte(iter.old_spte)) continue; - KVM_MMU_WARN_ON(kvm_ad_enabled() && + KVM_MMU_WARN_ON(dbit == shadow_dirty_mask && spte_ad_need_write_protect(iter.old_spte)); if (!(iter.old_spte & dbit)) @@ -1578,8 +1589,8 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t gfn, unsigned long mask, bool wrprot) { - u64 dbit = (wrprot || !kvm_ad_enabled()) ? PT_WRITABLE_MASK : - shadow_dirty_mask; + const u64 dbit = (wrprot || tdp_mmu_need_write_protect(root)) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; lockdep_assert_held_write(&kvm->mmu_lock); @@ -1591,7 +1602,7 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, if (!mask) break; - KVM_MMU_WARN_ON(kvm_ad_enabled() && + KVM_MMU_WARN_ON(dbit == shadow_dirty_mask && spte_ad_need_write_protect(iter.old_spte)); if (iter.level > PG_LEVEL_4K || diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 9ae07db6f0f648..da2d82e3a8735e 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -250,6 +250,24 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return true; } +static void pmc_release_perf_event(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + perf_event_release_kernel(pmc->perf_event); + pmc->perf_event = NULL; + pmc->current_config = 0; + pmc_to_pmu(pmc)->event_count--; + } +} + +static void pmc_stop_counter(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + pmc->counter = pmc_read_counter(pmc); + pmc_release_perf_event(pmc); + } +} + static int filter_cmp(const void *pa, const void *pb, u64 mask) { u64 a = *(u64 *)pa & mask; @@ -639,22 +657,79 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } -/* refresh PMU settings. This function generally is called when underlying - * settings are changed (such as changes of PMU CPUID by guest VMs), which - * should rarely happen. +void kvm_pmu_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + int i; + + pmu->need_cleanup = false; + + bitmap_zero(pmu->reprogram_pmi, X86_PMC_IDX_MAX); + + for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) { + pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i); + if (!pmc) + continue; + + pmc_stop_counter(pmc); + pmc->counter = 0; + + if (pmc_is_gp(pmc)) + pmc->eventsel = 0; + } + + pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0; + + static_call_cond(kvm_x86_pmu_reset)(vcpu); +} + + +/* + * Refresh the PMU configuration for the vCPU, e.g. if userspace changes CPUID + * and/or PERF_CAPABILITIES. */ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + if (KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm)) return; - bitmap_zero(vcpu_to_pmu(vcpu)->all_valid_pmc_idx, X86_PMC_IDX_MAX); + /* + * Stop/release all existing counters/events before realizing the new + * vPMU model. + */ + kvm_pmu_reset(vcpu); + + pmu->version = 0; + pmu->nr_arch_gp_counters = 0; + pmu->nr_arch_fixed_counters = 0; + pmu->counter_bitmask[KVM_PMC_GP] = 0; + pmu->counter_bitmask[KVM_PMC_FIXED] = 0; + pmu->reserved_bits = 0xffffffff00200000ull; + pmu->raw_event_mask = X86_RAW_EVENT_MASK; + pmu->global_ctrl_mask = ~0ull; + pmu->global_status_mask = ~0ull; + pmu->fixed_ctr_ctrl_mask = ~0ull; + pmu->pebs_enable_mask = ~0ull; + pmu->pebs_data_cfg_mask = ~0ull; + bitmap_zero(pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX); + + if (!vcpu->kvm->arch.enable_pmu) + return; + static_call(kvm_x86_pmu_refresh)(vcpu); -} -void kvm_pmu_reset(struct kvm_vcpu *vcpu) -{ - static_call(kvm_x86_pmu_reset)(vcpu); + /* + * At RESET, both Intel and AMD CPUs set all enable bits for general + * purpose counters in IA32_PERF_GLOBAL_CTRL (so that software that + * was written for v1 PMUs don't unknowingly leave GP counters disabled + * in the global controls). Emulate that behavior when refreshing the + * PMU so that userspace doesn't need to manually set PERF_GLOBAL_CTRL. + */ + if (kvm_pmu_has_perf_global_ctrl(pmu) && pmu->nr_arch_gp_counters) + pmu->global_ctrl = GENMASK_ULL(pmu->nr_arch_gp_counters - 1, 0); } void kvm_pmu_init(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 1d64113de4883e..a46aa9b25150f5 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -80,24 +80,6 @@ static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val) pmc->counter &= pmc_bitmask(pmc); } -static inline void pmc_release_perf_event(struct kvm_pmc *pmc) -{ - if (pmc->perf_event) { - perf_event_release_kernel(pmc->perf_event); - pmc->perf_event = NULL; - pmc->current_config = 0; - pmc_to_pmu(pmc)->event_count--; - } -} - -static inline void pmc_stop_counter(struct kvm_pmc *pmc) -{ - if (pmc->perf_event) { - pmc->counter = pmc_read_counter(pmc); - pmc_release_perf_event(pmc); - } -} - static inline bool pmc_is_gp(struct kvm_pmc *pmc) { return pmc->type == KVM_PMC_GP; diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index b816506783755a..2f4e155080badc 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -16,6 +16,7 @@ enum kvm_only_cpuid_leafs { CPUID_7_1_EDX, CPUID_8000_0007_EDX, CPUID_8000_0022_EAX, + CPUID_7_2_EDX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -46,6 +47,14 @@ enum kvm_only_cpuid_leafs { #define X86_FEATURE_AMX_COMPLEX KVM_X86_FEATURE(CPUID_7_1_EDX, 8) #define X86_FEATURE_PREFETCHITI KVM_X86_FEATURE(CPUID_7_1_EDX, 14) +/* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */ +#define X86_FEATURE_INTEL_PSFD KVM_X86_FEATURE(CPUID_7_2_EDX, 0) +#define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1) +#define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2) +#define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3) +#define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) +#define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) + /* CPUID level 0x80000007 (EDX). */ #define KVM_X86_FEATURE_CONSTANT_TSC KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8) @@ -80,6 +89,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_0007_EDX] = {0x80000007, 0, CPUID_EDX}, [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, [CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX}, + [CPUID_7_2_EDX] = { 7, 2, CPUID_EDX}, }; /* @@ -92,10 +102,12 @@ static const struct cpuid_reg reverse_cpuid[] = { */ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) { + BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS); BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); BUILD_BUG_ON(x86_leaf == CPUID_LNX_3); BUILD_BUG_ON(x86_leaf == CPUID_LNX_4); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_5); BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid)); BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0); } @@ -106,18 +118,20 @@ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) */ static __always_inline u32 __feature_translate(int x86_feature) { - if (x86_feature == X86_FEATURE_SGX1) - return KVM_X86_FEATURE_SGX1; - else if (x86_feature == X86_FEATURE_SGX2) - return KVM_X86_FEATURE_SGX2; - else if (x86_feature == X86_FEATURE_SGX_EDECCSSA) - return KVM_X86_FEATURE_SGX_EDECCSSA; - else if (x86_feature == X86_FEATURE_CONSTANT_TSC) - return KVM_X86_FEATURE_CONSTANT_TSC; - else if (x86_feature == X86_FEATURE_PERFMON_V2) - return KVM_X86_FEATURE_PERFMON_V2; - - return x86_feature; +#define KVM_X86_TRANSLATE_FEATURE(f) \ + case X86_FEATURE_##f: return KVM_X86_FEATURE_##f + + switch (x86_feature) { + KVM_X86_TRANSLATE_FEATURE(SGX1); + KVM_X86_TRANSLATE_FEATURE(SGX2); + KVM_X86_TRANSLATE_FEATURE(SGX_EDECCSSA); + KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC); + KVM_X86_TRANSLATE_FEATURE(PERFMON_V2); + KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); + KVM_X86_TRANSLATE_FEATURE(BHI_CTRL); + default: + return x86_feature; + } } static __always_inline u32 __feature_leaf(int x86_feature) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 3fea8c47679e68..60891b9ce25f61 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -247,18 +247,6 @@ static bool nested_svm_check_bitmap_pa(struct kvm_vcpu *vcpu, u64 pa, u32 size) kvm_vcpu_is_legal_gpa(vcpu, addr + size - 1); } -static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl) -{ - /* Nested FLUSHBYASID is not supported yet. */ - switch(tlb_ctl) { - case TLB_CONTROL_DO_NOTHING: - case TLB_CONTROL_FLUSH_ALL_ASID: - return true; - default: - return false; - } -} - static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, struct vmcb_ctrl_area_cached *control) { @@ -278,9 +266,6 @@ static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, IOPM_SIZE))) return false; - if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl))) - return false; - if (CC((control->int_ctl & V_NMI_ENABLE_MASK) && !vmcb12_is_intercept(control, INTERCEPT_NMI))) { return false; diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 373ff6a6687b3a..3fd47de14b38a3 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -233,21 +233,6 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu) } } -static void amd_pmu_reset(struct kvm_vcpu *vcpu) -{ - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - int i; - - for (i = 0; i < KVM_AMD_PMC_MAX_GENERIC; i++) { - struct kvm_pmc *pmc = &pmu->gp_counters[i]; - - pmc_stop_counter(pmc); - pmc->counter = pmc->prev_counter = pmc->eventsel = 0; - } - - pmu->global_ctrl = pmu->global_status = 0; -} - struct kvm_pmu_ops amd_pmu_ops __initdata = { .hw_event_available = amd_hw_event_available, .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, @@ -259,7 +244,6 @@ struct kvm_pmu_ops amd_pmu_ops __initdata = { .set_msr = amd_pmu_set_msr, .refresh = amd_pmu_refresh, .init = amd_pmu_init, - .reset = amd_pmu_reset, .EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT, .MAX_NR_GP_COUNTERS = KVM_AMD_PMC_MAX_GENERIC, .MIN_NR_GP_COUNTERS = AMD64_NUM_COUNTERS, diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 4900c078045acc..99e72b8a96ac0b 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -57,7 +57,7 @@ static bool sev_es_enabled = true; module_param_named(sev_es, sev_es_enabled, bool, 0444); /* enable/disable SEV-ES DebugSwap support */ -static bool sev_es_debug_swap_enabled = true; +static bool sev_es_debug_swap_enabled = false; module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444); #else #define sev_enabled false @@ -84,9 +84,10 @@ struct enc_region { }; /* Called with the sev_bitmap_lock held, or on shutdown */ -static int sev_flush_asids(int min_asid, int max_asid) +static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid) { - int ret, asid, error = 0; + int ret, error = 0; + unsigned int asid; /* Check if there are any ASIDs to reclaim before performing a flush */ asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid); @@ -116,7 +117,7 @@ static inline bool is_mirroring_enc_context(struct kvm *kvm) } /* Must be called with the sev_bitmap_lock held */ -static bool __sev_recycle_asids(int min_asid, int max_asid) +static bool __sev_recycle_asids(unsigned int min_asid, unsigned int max_asid) { if (sev_flush_asids(min_asid, max_asid)) return false; @@ -143,8 +144,20 @@ static void sev_misc_cg_uncharge(struct kvm_sev_info *sev) static int sev_asid_new(struct kvm_sev_info *sev) { - int asid, min_asid, max_asid, ret; + /* + * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. + * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. + * Note: min ASID can end up larger than the max if basic SEV support is + * effectively disabled by disallowing use of ASIDs for SEV guests. + */ + unsigned int min_asid = sev->es_active ? 1 : min_sev_asid; + unsigned int max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; + unsigned int asid; bool retry = true; + int ret; + + if (min_asid > max_asid) + return -ENOTTY; WARN_ON(sev->misc_cg); sev->misc_cg = get_current_misc_cg(); @@ -157,12 +170,6 @@ static int sev_asid_new(struct kvm_sev_info *sev) mutex_lock(&sev_bitmap_lock); - /* - * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. - * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. - */ - min_asid = sev->es_active ? 1 : min_sev_asid; - max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; again: asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid); if (asid > max_asid) { @@ -187,7 +194,7 @@ static int sev_asid_new(struct kvm_sev_info *sev) return ret; } -static int sev_get_asid(struct kvm *kvm) +static unsigned int sev_get_asid(struct kvm *kvm) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; @@ -284,8 +291,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) { + unsigned int asid = sev_get_asid(kvm); struct sev_data_activate activate; - int asid = sev_get_asid(kvm); int ret; /* activate ASID on the given handle */ @@ -612,8 +619,11 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) save->xss = svm->vcpu.arch.ia32_xss; save->dr6 = svm->vcpu.arch.dr6; - if (sev_es_debug_swap_enabled) + if (sev_es_debug_swap_enabled) { save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP; + pr_warn_once("Enabling DebugSwap with KVM_SEV_ES_INIT. " + "This will not work starting with Linux 6.10\n"); + } pr_debug("Virtual Machine Save Area (VMSA):\n"); print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false); @@ -654,6 +664,14 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, return ret; vcpu->arch.guest_state_protected = true; + + /* + * SEV-ES guest mandates LBR Virtualization to be _always_ ON. Enable it + * only after setting guest_state_protected because KVM_SET_MSRS allows + * dynamic toggling of LBRV (for performance reason) on write access to + * MSR_IA32_DEBUGCTLMSR when guest_state_protected is not set. + */ + svm_enable_lbrv(vcpu); return 0; } @@ -1975,20 +1993,22 @@ int sev_mem_enc_register_region(struct kvm *kvm, goto e_free; } - region->uaddr = range->addr; - region->size = range->size; - - list_add_tail(®ion->list, &sev->regions_list); - mutex_unlock(&kvm->lock); - /* * The guest may change the memory encryption attribute from C=0 -> C=1 * or vice versa for this memory range. Lets make sure caches are * flushed to ensure that guest data gets written into memory with - * correct C-bit. + * correct C-bit. Note, this must be done before dropping kvm->lock, + * as region and its array of pages can be freed by a different task + * once kvm->lock is released. */ sev_clflush_pages(region->pages, region->npages); + region->uaddr = range->addr; + region->size = range->size; + + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + return ret; e_free: @@ -2229,8 +2249,10 @@ void __init sev_hardware_setup(void) goto out; } - sev_asid_count = max_sev_asid - min_sev_asid + 1; - WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + if (min_sev_asid <= max_sev_asid) { + sev_asid_count = max_sev_asid - min_sev_asid + 1; + WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + } sev_supported = true; /* SEV-ES support requested? */ @@ -2250,6 +2272,12 @@ void __init sev_hardware_setup(void) if (!boot_cpu_has(X86_FEATURE_SEV_ES)) goto out; + if (!lbrv) { + WARN_ONCE(!boot_cpu_has(X86_FEATURE_LBRV), + "LBRV must be present for SEV-ES support"); + goto out; + } + /* Has the system been allocated ASIDs for SEV-ES? */ if (min_sev_asid == 1) goto out; @@ -2261,7 +2289,9 @@ void __init sev_hardware_setup(void) out: if (boot_cpu_has(X86_FEATURE_SEV)) pr_info("SEV %s (ASIDs %u - %u)\n", - sev_supported ? "enabled" : "disabled", + sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" : + "unusable" : + "disabled", min_sev_asid, max_sev_asid); if (boot_cpu_has(X86_FEATURE_SEV_ES)) pr_info("SEV-ES %s (ASIDs %u - %u)\n", @@ -2309,7 +2339,7 @@ int sev_cpu_init(struct svm_cpu_data *sd) */ static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va) { - int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid; + unsigned int asid = sev_get_asid(vcpu->kvm); /* * Note! The address must be a kernel address, as regular page walk @@ -2627,7 +2657,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) void pre_sev_run(struct vcpu_svm *svm, int cpu) { struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); - int asid = sev_get_asid(svm->vcpu.kvm); + unsigned int asid = sev_get_asid(svm->vcpu.kvm); /* Assign the asid allocated with this SEV guest */ svm->asid = asid; @@ -2972,6 +3002,25 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux); } + + /* + * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if + * the host/guest supports its use. + * + * guest_can_use() checks a number of requirements on the host/guest to + * ensure that MSR_IA32_XSS is available, but it might report true even + * if X86_FEATURE_XSAVES isn't configured in the guest to ensure host + * MSR_IA32_XSS is always properly restored. For SEV-ES, it is better + * to further check that the guest CPUID actually supports + * X86_FEATURE_XSAVES so that accesses to MSR_IA32_XSS by misbehaved + * guests will still get intercepted and caught in the normal + * kvm_emulate_rdmsr()/kvm_emulated_wrmsr() paths. + */ + if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && + guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1); + else + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0); } void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm) @@ -2994,7 +3043,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE; - svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; /* * An SEV-ES guest requires a VMSA area that is a separate from the @@ -3046,10 +3094,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) /* Clear intercepts on selected MSRs */ set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); } void sev_init_vmcb(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index beea99c8e8e05e..413f1f2aadd1a3 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -99,10 +99,12 @@ static const struct svm_direct_access_msrs { { .index = MSR_IA32_SPEC_CTRL, .always = false }, { .index = MSR_IA32_PRED_CMD, .always = false }, { .index = MSR_IA32_FLUSH_CMD, .always = false }, + { .index = MSR_IA32_DEBUGCTLMSR, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, { .index = MSR_IA32_LASTINTTOIP, .always = false }, + { .index = MSR_IA32_XSS, .always = false }, { .index = MSR_EFER, .always = false }, { .index = MSR_IA32_CR_PAT, .always = false }, { .index = MSR_AMD64_SEV_ES_GHCB, .always = true }, @@ -214,7 +216,7 @@ int vgif = true; module_param(vgif, int, 0444); /* enable/disable LBR virtualization */ -static int lbrv = true; +int lbrv = true; module_param(lbrv, int, 0444); static int tsc_scaling = true; @@ -1007,7 +1009,7 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb) vmcb_mark_dirty(to_vmcb, VMCB_LBR); } -static void svm_enable_lbrv(struct kvm_vcpu *vcpu) +void svm_enable_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1017,6 +1019,9 @@ static void svm_enable_lbrv(struct kvm_vcpu *vcpu) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); + if (sev_es_guest(vcpu->kvm)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1); + /* Move the LBR msrs to the vmcb02 so that the guest can see them. */ if (is_guest_mode(vcpu)) svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr); @@ -1026,6 +1031,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm); + svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0); @@ -1873,15 +1880,17 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) bool old_paging = is_paging(vcpu); #ifdef CONFIG_X86_64 - if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) { + if (vcpu->arch.efer & EFER_LME) { if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { vcpu->arch.efer |= EFER_LMA; - svm->vmcb->save.efer |= EFER_LMA | EFER_LME; + if (!vcpu->arch.guest_state_protected) + svm->vmcb->save.efer |= EFER_LMA | EFER_LME; } if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) { vcpu->arch.efer &= ~EFER_LMA; - svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME); + if (!vcpu->arch.guest_state_protected) + svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME); } } #endif @@ -2860,6 +2869,12 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_CSTAR: msr_info->data = svm->vmcb01.ptr->save.cstar; break; + case MSR_GS_BASE: + msr_info->data = svm->vmcb01.ptr->save.gs.base; + break; + case MSR_FS_BASE: + msr_info->data = svm->vmcb01.ptr->save.fs.base; + break; case MSR_KERNEL_GS_BASE: msr_info->data = svm->vmcb01.ptr->save.kernel_gs_base; break; @@ -3081,6 +3096,12 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_CSTAR: svm->vmcb01.ptr->save.cstar = data; break; + case MSR_GS_BASE: + svm->vmcb01.ptr->save.gs.base = data; + break; + case MSR_FS_BASE: + svm->vmcb01.ptr->save.fs.base = data; + break; case MSR_KERNEL_GS_BASE: svm->vmcb01.ptr->save.kernel_gs_base = data; break; @@ -3854,16 +3875,27 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); /* - * KVM should never request an NMI window when vNMI is enabled, as KVM - * allows at most one to-be-injected NMI and one pending NMI, i.e. if - * two NMIs arrive simultaneously, KVM will inject one and set - * V_NMI_PENDING for the other. WARN, but continue with the standard - * single-step approach to try and salvage the pending NMI. + * If NMIs are outright masked, i.e. the vCPU is already handling an + * NMI, and KVM has not yet intercepted an IRET, then there is nothing + * more to do at this time as KVM has already enabled IRET intercepts. + * If KVM has already intercepted IRET, then single-step over the IRET, + * as NMIs aren't architecturally unmasked until the IRET completes. + * + * If vNMI is enabled, KVM should never request an NMI window if NMIs + * are masked, as KVM allows at most one to-be-injected NMI and one + * pending NMI. If two NMIs arrive simultaneously, KVM will inject one + * NMI and set V_NMI_PENDING for the other, but if and only if NMIs are + * unmasked. KVM _will_ request an NMI window in some situations, e.g. + * if the vCPU is in an STI shadow or if GIF=0, KVM can't immediately + * inject the NMI. In those situations, KVM needs to single-step over + * the STI shadow or intercept STGI. */ - WARN_ON_ONCE(is_vnmi_enabled(svm)); + if (svm_get_nmi_mask(vcpu)) { + WARN_ON_ONCE(is_vnmi_enabled(svm)); - if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion) - return; /* IRET will cause a vm exit */ + if (!svm->awaiting_iret_completion) + return; /* IRET will cause a vm exit */ + } /* * SEV-ES guests are responsible for signaling when a vCPU is ready to @@ -5146,6 +5178,9 @@ static __init void svm_set_cpu_caps(void) /* CPUID 0x8000001F (SME/SEV features) */ sev_set_cpu_caps(); + + /* Don't advertise Bus Lock Detect to guest if SVM support is absent */ + kvm_cpu_cap_clear(X86_FEATURE_BUS_LOCK_DETECT); } static __init int svm_hardware_setup(void) @@ -5235,6 +5270,12 @@ static __init int svm_hardware_setup(void) nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS); + if (lbrv) { + if (!boot_cpu_has(X86_FEATURE_LBRV)) + lbrv = false; + else + pr_info("LBR virtualization supported\n"); + } /* * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which * may be modified by svm_adjust_mmio_mask()), as well as nrips. @@ -5288,14 +5329,6 @@ static __init int svm_hardware_setup(void) svm_x86_ops.set_vnmi_pending = NULL; } - - if (lbrv) { - if (!boot_cpu_has(X86_FEATURE_LBRV)) - lbrv = false; - else - pr_info("LBR virtualization supported\n"); - } - if (!enable_pmu) pr_info("PMU virtualization is disabled\n"); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index be67ab7fdd104e..37ada9808d9b57 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -30,7 +30,7 @@ #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2 -#define MAX_DIRECT_ACCESS_MSRS 46 +#define MAX_DIRECT_ACCESS_MSRS 48 #define MSRPM_OFFSETS 32 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; @@ -39,6 +39,7 @@ extern int vgif; extern bool intercept_smi; extern bool x2avic_enabled; extern bool vnmi; +extern int lbrv; /* * Clean bits in VMCB. @@ -541,6 +542,7 @@ u32 *svm_vcpu_alloc_msrpm(void); void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm); void svm_vcpu_free_msrpm(u32 *msrpm); void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb); +void svm_enable_lbrv(struct kvm_vcpu *vcpu); void svm_update_lbrv(struct kvm_vcpu *vcpu); int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer); diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h index 36c8af87a707ac..4e725854c63a10 100644 --- a/arch/x86/kvm/svm/svm_ops.h +++ b/arch/x86/kvm/svm/svm_ops.h @@ -8,7 +8,7 @@ #define svm_asm(insn, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) "\n\t" \ + asm goto("1: " __stringify(insn) "\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ ::: clobber : fault); \ return; \ @@ -18,7 +18,7 @@ fault: \ #define svm_asm1(insn, op1, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + asm goto("1: " __stringify(insn) " %0\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ :: op1 : clobber : fault); \ return; \ @@ -28,7 +28,7 @@ fault: \ #define svm_asm2(insn, op1, op2, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + asm goto("1: " __stringify(insn) " %1, %0\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ :: op1, op2 : clobber : fault); \ return; \ diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 83843379813ee3..b82e6ed4f02417 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -732,13 +732,13 @@ TRACE_EVENT(kvm_nested_intr_vmexit, * Tracepoint for nested #vmexit because of interrupt pending */ TRACE_EVENT(kvm_invlpga, - TP_PROTO(__u64 rip, int asid, u64 address), + TP_PROTO(__u64 rip, unsigned int asid, u64 address), TP_ARGS(rip, asid, address), TP_STRUCT__entry( - __field( __u64, rip ) - __field( int, asid ) - __field( __u64, address ) + __field( __u64, rip ) + __field( unsigned int, asid ) + __field( __u64, address ) ), TP_fast_assign( @@ -747,7 +747,7 @@ TRACE_EVENT(kvm_invlpga, __entry->address = address; ), - TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx", + TP_printk("rip: 0x%016llx asid: %u address: 0x%016llx", __entry->rip, __entry->asid, __entry->address) ); diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index 313b8bb5b8a7cb..de13dc14fe1d2f 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -13,111 +13,6 @@ #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK -/* - * Enlightened VMCSv1 doesn't support these: - * - * POSTED_INTR_NV = 0x00000002, - * GUEST_INTR_STATUS = 0x00000810, - * APIC_ACCESS_ADDR = 0x00002014, - * POSTED_INTR_DESC_ADDR = 0x00002016, - * EOI_EXIT_BITMAP0 = 0x0000201c, - * EOI_EXIT_BITMAP1 = 0x0000201e, - * EOI_EXIT_BITMAP2 = 0x00002020, - * EOI_EXIT_BITMAP3 = 0x00002022, - * GUEST_PML_INDEX = 0x00000812, - * PML_ADDRESS = 0x0000200e, - * VM_FUNCTION_CONTROL = 0x00002018, - * EPTP_LIST_ADDRESS = 0x00002024, - * VMREAD_BITMAP = 0x00002026, - * VMWRITE_BITMAP = 0x00002028, - * - * TSC_MULTIPLIER = 0x00002032, - * PLE_GAP = 0x00004020, - * PLE_WINDOW = 0x00004022, - * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, - * - * Currently unsupported in KVM: - * GUEST_IA32_RTIT_CTL = 0x00002814, - */ -#define EVMCS1_SUPPORTED_PINCTRL \ - (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - PIN_BASED_EXT_INTR_MASK | \ - PIN_BASED_NMI_EXITING | \ - PIN_BASED_VIRTUAL_NMIS) - -#define EVMCS1_SUPPORTED_EXEC_CTRL \ - (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - CPU_BASED_HLT_EXITING | \ - CPU_BASED_CR3_LOAD_EXITING | \ - CPU_BASED_CR3_STORE_EXITING | \ - CPU_BASED_UNCOND_IO_EXITING | \ - CPU_BASED_MOV_DR_EXITING | \ - CPU_BASED_USE_TSC_OFFSETTING | \ - CPU_BASED_MWAIT_EXITING | \ - CPU_BASED_MONITOR_EXITING | \ - CPU_BASED_INVLPG_EXITING | \ - CPU_BASED_RDPMC_EXITING | \ - CPU_BASED_INTR_WINDOW_EXITING | \ - CPU_BASED_CR8_LOAD_EXITING | \ - CPU_BASED_CR8_STORE_EXITING | \ - CPU_BASED_RDTSC_EXITING | \ - CPU_BASED_TPR_SHADOW | \ - CPU_BASED_USE_IO_BITMAPS | \ - CPU_BASED_MONITOR_TRAP_FLAG | \ - CPU_BASED_USE_MSR_BITMAPS | \ - CPU_BASED_NMI_WINDOW_EXITING | \ - CPU_BASED_PAUSE_EXITING | \ - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) - -#define EVMCS1_SUPPORTED_2NDEXEC \ - (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ - SECONDARY_EXEC_WBINVD_EXITING | \ - SECONDARY_EXEC_ENABLE_VPID | \ - SECONDARY_EXEC_ENABLE_EPT | \ - SECONDARY_EXEC_UNRESTRICTED_GUEST | \ - SECONDARY_EXEC_DESC | \ - SECONDARY_EXEC_ENABLE_RDTSCP | \ - SECONDARY_EXEC_ENABLE_INVPCID | \ - SECONDARY_EXEC_ENABLE_XSAVES | \ - SECONDARY_EXEC_RDSEED_EXITING | \ - SECONDARY_EXEC_RDRAND_EXITING | \ - SECONDARY_EXEC_TSC_SCALING | \ - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ - SECONDARY_EXEC_PT_USE_GPA | \ - SECONDARY_EXEC_PT_CONCEAL_VMX | \ - SECONDARY_EXEC_BUS_LOCK_DETECTION | \ - SECONDARY_EXEC_NOTIFY_VM_EXITING | \ - SECONDARY_EXEC_ENCLS_EXITING) - -#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) - -#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ - (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_EXIT_SAVE_DEBUG_CONTROLS | \ - VM_EXIT_ACK_INTR_ON_EXIT | \ - VM_EXIT_HOST_ADDR_SPACE_SIZE | \ - VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_EXIT_SAVE_IA32_PAT | \ - VM_EXIT_LOAD_IA32_PAT | \ - VM_EXIT_SAVE_IA32_EFER | \ - VM_EXIT_LOAD_IA32_EFER | \ - VM_EXIT_CLEAR_BNDCFGS | \ - VM_EXIT_PT_CONCEAL_PIP | \ - VM_EXIT_CLEAR_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ - (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_ENTRY_LOAD_DEBUG_CONTROLS | \ - VM_ENTRY_IA32E_MODE | \ - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_ENTRY_LOAD_IA32_PAT | \ - VM_ENTRY_LOAD_IA32_EFER | \ - VM_ENTRY_LOAD_BNDCFGS | \ - VM_ENTRY_PT_CONCEAL_PIP | \ - VM_ENTRY_LOAD_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMFUNC (0) - #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) #define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ {EVMCS1_OFFSET(name), clean_field} @@ -608,40 +503,6 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) return 0; } -#if IS_ENABLED(CONFIG_HYPERV) -DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); - -/* - * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption - * is: in case a feature has corresponding fields in eVMCS described and it was - * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a - * feature which has no corresponding eVMCS field, this likely means that KVM - * needs to be updated. - */ -#define evmcs_check_vmcs_conf(field, ctrl) \ - do { \ - typeof(vmcs_conf->field) unsupported; \ - \ - unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl; \ - if (unsupported) { \ - pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\ - (u64)unsupported); \ - vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl; \ - } \ - } \ - while (0) - -void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) -{ - evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL); - evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL); - evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC); - evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC); - evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL); - evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL); -} -#endif - int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version) { diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index 9623fe1651c48b..9401dbfaea7cef 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -14,12 +14,113 @@ #include "vmcs.h" #include "vmcs12.h" -struct vmcs_config; - -#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs)) - #define KVM_EVMCS_VERSION 1 +/* + * Enlightened VMCSv1 doesn't support these: + * + * POSTED_INTR_NV = 0x00000002, + * GUEST_INTR_STATUS = 0x00000810, + * APIC_ACCESS_ADDR = 0x00002014, + * POSTED_INTR_DESC_ADDR = 0x00002016, + * EOI_EXIT_BITMAP0 = 0x0000201c, + * EOI_EXIT_BITMAP1 = 0x0000201e, + * EOI_EXIT_BITMAP2 = 0x00002020, + * EOI_EXIT_BITMAP3 = 0x00002022, + * GUEST_PML_INDEX = 0x00000812, + * PML_ADDRESS = 0x0000200e, + * VM_FUNCTION_CONTROL = 0x00002018, + * EPTP_LIST_ADDRESS = 0x00002024, + * VMREAD_BITMAP = 0x00002026, + * VMWRITE_BITMAP = 0x00002028, + * + * TSC_MULTIPLIER = 0x00002032, + * PLE_GAP = 0x00004020, + * PLE_WINDOW = 0x00004022, + * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, + * + * Currently unsupported in KVM: + * GUEST_IA32_RTIT_CTL = 0x00002814, + */ +#define EVMCS1_SUPPORTED_PINCTRL \ + (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + PIN_BASED_EXT_INTR_MASK | \ + PIN_BASED_NMI_EXITING | \ + PIN_BASED_VIRTUAL_NMIS) + +#define EVMCS1_SUPPORTED_EXEC_CTRL \ + (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + CPU_BASED_HLT_EXITING | \ + CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING | \ + CPU_BASED_UNCOND_IO_EXITING | \ + CPU_BASED_MOV_DR_EXITING | \ + CPU_BASED_USE_TSC_OFFSETTING | \ + CPU_BASED_MWAIT_EXITING | \ + CPU_BASED_MONITOR_EXITING | \ + CPU_BASED_INVLPG_EXITING | \ + CPU_BASED_RDPMC_EXITING | \ + CPU_BASED_INTR_WINDOW_EXITING | \ + CPU_BASED_CR8_LOAD_EXITING | \ + CPU_BASED_CR8_STORE_EXITING | \ + CPU_BASED_RDTSC_EXITING | \ + CPU_BASED_TPR_SHADOW | \ + CPU_BASED_USE_IO_BITMAPS | \ + CPU_BASED_MONITOR_TRAP_FLAG | \ + CPU_BASED_USE_MSR_BITMAPS | \ + CPU_BASED_NMI_WINDOW_EXITING | \ + CPU_BASED_PAUSE_EXITING | \ + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) + +#define EVMCS1_SUPPORTED_2NDEXEC \ + (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ + SECONDARY_EXEC_WBINVD_EXITING | \ + SECONDARY_EXEC_ENABLE_VPID | \ + SECONDARY_EXEC_ENABLE_EPT | \ + SECONDARY_EXEC_UNRESTRICTED_GUEST | \ + SECONDARY_EXEC_DESC | \ + SECONDARY_EXEC_ENABLE_RDTSCP | \ + SECONDARY_EXEC_ENABLE_INVPCID | \ + SECONDARY_EXEC_ENABLE_XSAVES | \ + SECONDARY_EXEC_RDSEED_EXITING | \ + SECONDARY_EXEC_RDRAND_EXITING | \ + SECONDARY_EXEC_TSC_SCALING | \ + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ + SECONDARY_EXEC_PT_USE_GPA | \ + SECONDARY_EXEC_PT_CONCEAL_VMX | \ + SECONDARY_EXEC_BUS_LOCK_DETECTION | \ + SECONDARY_EXEC_NOTIFY_VM_EXITING | \ + SECONDARY_EXEC_ENCLS_EXITING) + +#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) + +#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_EXIT_SAVE_DEBUG_CONTROLS | \ + VM_EXIT_ACK_INTR_ON_EXIT | \ + VM_EXIT_HOST_ADDR_SPACE_SIZE | \ + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_IA32_PAT | \ + VM_EXIT_LOAD_IA32_PAT | \ + VM_EXIT_SAVE_IA32_EFER | \ + VM_EXIT_LOAD_IA32_EFER | \ + VM_EXIT_CLEAR_BNDCFGS | \ + VM_EXIT_PT_CONCEAL_PIP | \ + VM_EXIT_CLEAR_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_ENTRY_LOAD_DEBUG_CONTROLS | \ + VM_ENTRY_IA32E_MODE | \ + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_IA32_PAT | \ + VM_ENTRY_LOAD_IA32_EFER | \ + VM_ENTRY_LOAD_BNDCFGS | \ + VM_ENTRY_PT_CONCEAL_PIP | \ + VM_ENTRY_LOAD_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMFUNC (0) + struct evmcs_field { u16 offset; u16 clean_field; @@ -65,114 +166,6 @@ static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, return vmcs12_read_any((void *)evmcs, field, offset); } -#if IS_ENABLED(CONFIG_HYPERV) - -DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); - -static __always_inline bool kvm_is_using_evmcs(void) -{ - return static_branch_unlikely(&__kvm_is_using_evmcs); -} - -static __always_inline int get_evmcs_offset(unsigned long field, - u16 *clean_field) -{ - int offset = evmcs_field_offset(field, clean_field); - - WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field); - return offset; -} - -static __always_inline void evmcs_write64(unsigned long field, u64 value) -{ - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u64 *)((char *)current_evmcs + offset) = value; - - current_evmcs->hv_clean_fields &= ~clean_field; -} - -static __always_inline void evmcs_write32(unsigned long field, u32 value) -{ - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u32 *)((char *)current_evmcs + offset) = value; - current_evmcs->hv_clean_fields &= ~clean_field; -} - -static __always_inline void evmcs_write16(unsigned long field, u16 value) -{ - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u16 *)((char *)current_evmcs + offset) = value; - current_evmcs->hv_clean_fields &= ~clean_field; -} - -static __always_inline u64 evmcs_read64(unsigned long field) -{ - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u64 *)((char *)current_evmcs + offset); -} - -static __always_inline u32 evmcs_read32(unsigned long field) -{ - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u32 *)((char *)current_evmcs + offset); -} - -static __always_inline u16 evmcs_read16(unsigned long field) -{ - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u16 *)((char *)current_evmcs + offset); -} - -static inline void evmcs_load(u64 phys_addr) -{ - struct hv_vp_assist_page *vp_ap = - hv_get_vp_assist_page(smp_processor_id()); - - if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) - vp_ap->nested_control.features.directhypercall = 1; - vp_ap->current_nested_vmcs = phys_addr; - vp_ap->enlighten_vmentry = 1; -} - -void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); -#else /* !IS_ENABLED(CONFIG_HYPERV) */ -static __always_inline bool kvm_is_using_evmcs(void) { return false; } -static __always_inline void evmcs_write64(unsigned long field, u64 value) {} -static __always_inline void evmcs_write32(unsigned long field, u32 value) {} -static __always_inline void evmcs_write16(unsigned long field, u16 value) {} -static __always_inline u64 evmcs_read64(unsigned long field) { return 0; } -static __always_inline u32 evmcs_read32(unsigned long field) { return 0; } -static __always_inline u16 evmcs_read16(unsigned long field) { return 0; } -static inline void evmcs_load(u64 phys_addr) {} -#endif /* IS_ENABLED(CONFIG_HYPERV) */ - #define EVMPTR_INVALID (-1ULL) #define EVMPTR_MAP_PENDING (-2ULL) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index c5ec0ef51ff78f..0ad66b9207e85f 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -12,6 +12,7 @@ #include "mmu.h" #include "nested.h" #include "pmu.h" +#include "posted_intr.h" #include "sgx.h" #include "trace.h" #include "vmx.h" @@ -3830,8 +3831,8 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) if (!pi_test_and_clear_on(vmx->nested.pi_desc)) return 0; - max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); - if (max_irr != 256) { + max_irr = pi_find_highest_vector(vmx->nested.pi_desc); + if (max_irr > 0) { vapic_page = vmx->nested.virtual_apic_map.hva; if (!vapic_page) goto mmio_needed; @@ -3962,10 +3963,42 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu) to_vmx(vcpu)->nested.preemption_timer_expired; } -static bool vmx_has_nested_events(struct kvm_vcpu *vcpu) +static bool vmx_has_nested_events(struct kvm_vcpu *vcpu, bool for_injection) { - return nested_vmx_preemption_timer_pending(vcpu) || - to_vmx(vcpu)->nested.mtf_pending; + struct vcpu_vmx *vmx = to_vmx(vcpu); + void *vapic = vmx->nested.virtual_apic_map.hva; + int max_irr, vppr; + + if (nested_vmx_preemption_timer_pending(vcpu) || + vmx->nested.mtf_pending) + return true; + + /* + * Virtual Interrupt Delivery doesn't require manual injection. Either + * the interrupt is already in GUEST_RVI and will be recognized by CPU + * at VM-Entry, or there is a KVM_REQ_EVENT pending and KVM will move + * the interrupt from the PIR to RVI prior to entering the guest. + */ + if (for_injection) + return false; + + if (!nested_cpu_has_vid(get_vmcs12(vcpu)) || + __vmx_interrupt_blocked(vcpu)) + return false; + + if (!vapic) + return false; + + vppr = *((u32 *)(vapic + APIC_PROCPRI)); + + if (vmx->nested.pi_pending && vmx->nested.pi_desc && + pi_test_on(vmx->nested.pi_desc)) { + max_irr = pi_find_highest_vector(vmx->nested.pi_desc); + if (max_irr > 0 && (max_irr & 0xf0) > (vppr & 0xf0)) + return true; + } + + return false; } /* diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 820d3e1f6b4f82..48a2f77f62ef35 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -71,7 +71,7 @@ static int fixed_pmc_events[] = { static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) { struct kvm_pmc *pmc; - u8 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl; + u64 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl; int i; pmu->fixed_ctr_ctrl = data; @@ -493,19 +493,6 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) u64 counter_mask; int i; - pmu->nr_arch_gp_counters = 0; - pmu->nr_arch_fixed_counters = 0; - pmu->counter_bitmask[KVM_PMC_GP] = 0; - pmu->counter_bitmask[KVM_PMC_FIXED] = 0; - pmu->version = 0; - pmu->reserved_bits = 0xffffffff00200000ull; - pmu->raw_event_mask = X86_RAW_EVENT_MASK; - pmu->global_ctrl_mask = ~0ull; - pmu->global_status_mask = ~0ull; - pmu->fixed_ctr_ctrl_mask = ~0ull; - pmu->pebs_enable_mask = ~0ull; - pmu->pebs_data_cfg_mask = ~0ull; - memset(&lbr_desc->records, 0, sizeof(lbr_desc->records)); /* @@ -517,8 +504,9 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) return; entry = kvm_find_cpuid_entry(vcpu, 0xa); - if (!entry || !vcpu->kvm->arch.enable_pmu) + if (!entry) return; + eax.full = entry->eax; edx.full = entry->edx; @@ -632,26 +620,6 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) static void intel_pmu_reset(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - struct kvm_pmc *pmc = NULL; - int i; - - for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) { - pmc = &pmu->gp_counters[i]; - - pmc_stop_counter(pmc); - pmc->counter = pmc->prev_counter = pmc->eventsel = 0; - } - - for (i = 0; i < KVM_PMC_MAX_FIXED; i++) { - pmc = &pmu->fixed_counters[i]; - - pmc_stop_counter(pmc); - pmc->counter = pmc->prev_counter = 0; - } - - pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0; - intel_pmu_release_guest_lbr_event(vcpu); } diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 26992076552ef1..1715d2ab07be5d 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -2,97 +2,8 @@ #ifndef __KVM_X86_VMX_POSTED_INTR_H #define __KVM_X86_VMX_POSTED_INTR_H -#define POSTED_INTR_ON 0 -#define POSTED_INTR_SN 1 - -#define PID_TABLE_ENTRY_VALID 1 - -/* Posted-Interrupt Descriptor */ -struct pi_desc { - u32 pir[8]; /* Posted interrupt requested */ - union { - struct { - /* bit 256 - Outstanding Notification */ - u16 on : 1, - /* bit 257 - Suppress Notification */ - sn : 1, - /* bit 271:258 - Reserved */ - rsvd_1 : 14; - /* bit 279:272 - Notification Vector */ - u8 nv; - /* bit 287:280 - Reserved */ - u8 rsvd_2; - /* bit 319:288 - Notification Destination */ - u32 ndst; - }; - u64 control; - }; - u32 rsvd[6]; -} __aligned(64); - -static inline bool pi_test_and_set_on(struct pi_desc *pi_desc) -{ - return test_and_set_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc) -{ - return test_and_clear_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc) -{ - return test_and_clear_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) -{ - return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); -} - -static inline bool pi_is_pir_empty(struct pi_desc *pi_desc) -{ - return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS); -} - -static inline void pi_set_sn(struct pi_desc *pi_desc) -{ - set_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} - -static inline void pi_set_on(struct pi_desc *pi_desc) -{ - set_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline void pi_clear_on(struct pi_desc *pi_desc) -{ - clear_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline void pi_clear_sn(struct pi_desc *pi_desc) -{ - clear_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_on(struct pi_desc *pi_desc) -{ - return test_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_sn(struct pi_desc *pi_desc) -{ - return test_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} +#include +#include void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu); void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu); @@ -103,4 +14,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void vmx_pi_start_assignment(struct kvm *kvm); +static inline int pi_find_highest_vector(struct pi_desc *pi_desc) +{ + int vec; + + vec = find_last_bit((unsigned long *)pi_desc->pir, 256); + return vec < 256 ? vec : -1; +} + #endif /* __KVM_X86_VMX_POSTED_INTR_H */ diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h index edc3f16cc1896f..6a9bfdfbb6e59b 100644 --- a/arch/x86/kvm/vmx/run_flags.h +++ b/arch/x86/kvm/vmx/run_flags.h @@ -2,7 +2,10 @@ #ifndef __KVM_X86_VMX_RUN_FLAGS_H #define __KVM_X86_VMX_RUN_FLAGS_H -#define VMX_RUN_VMRESUME (1 << 0) -#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1) +#define VMX_RUN_VMRESUME_SHIFT 0 +#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1 + +#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT) +#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT) #endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index be275a0410a899..9522d46567f81b 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -139,7 +139,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - test $VMX_RUN_VMRESUME, %ebx + bt $VMX_RUN_VMRESUME_SHIFT, %ebx /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -161,8 +161,11 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Check EFLAGS.ZF from 'test VMX_RUN_VMRESUME' above */ - jz .Lvmlaunch + /* Clobbers EFLAGS.ZF */ + CLEAR_CPU_BUFFERS + + /* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */ + jnc .Lvmlaunch /* * After a successful VMRESUME/VMLAUNCH, control flow "magically" @@ -272,6 +275,8 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL) call vmx_spec_ctrl_restore_host + CLEAR_BRANCH_HISTORY_VMEXIT + /* Put return value in AX */ mov %_ASM_BX, %_ASM_AX diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 72e3943f36935c..2e0106d9d371cf 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -66,6 +66,8 @@ #include "vmx.h" #include "x86.h" #include "smm.h" +#include "vmx_onhyperv.h" +#include "posted_intr.h" MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); @@ -387,7 +389,16 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - vmx->disable_fb_clear = (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && + /* + * Disable VERW's behavior of clearing CPU buffers for the guest if the + * CPU isn't affected by MDS/TAA, and the host hasn't forcefully enabled + * the mitigation. Disabling the clearing behavior provides a + * performance boost for guests that aren't aware that manually clearing + * CPU buffers is unnecessary, at the cost of MSR accesses on VM-Entry + * and VM-Exit. + */ + vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) && + (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && !boot_cpu_has_bug(X86_BUG_MDS) && !boot_cpu_has_bug(X86_BUG_TAA); @@ -745,7 +756,7 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, */ static int kvm_cpu_vmxoff(void) { - asm_volatile_goto("1: vmxoff\n\t" + asm goto("1: vmxoff\n\t" _ASM_EXTABLE(1b, %l[fault]) ::: "cc", "memory" : fault); @@ -2789,7 +2800,7 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer) cr4_set_bits(X86_CR4_VMXE); - asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" + asm goto("1: vmxon %[vmxon_pointer]\n\t" _ASM_EXTABLE(1b, %l[fault]) : : [vmxon_pointer] "m"(vmxon_pointer) : : fault); @@ -5039,14 +5050,19 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !vmx_nmi_blocked(vcpu); } +bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu) +{ + return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) || + (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); +} + bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) return false; - return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) || - (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); + return __vmx_interrupt_blocked(vcpu); } static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) @@ -6912,7 +6928,7 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } -static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) +static void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7226,11 +7242,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, guest_state_enter_irqoff(); - /* L1D Flush includes CPU buffer clear to mitigate MDS */ + /* + * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW + * mitigation for MDS is done late in VMentry and is still + * executed in spite of L1D Flush. This is because an extra VERW + * should not matter much after the big hammer L1D Flush. + */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&mds_user_clear)) - mds_clear_cpu_buffers(); else if (static_branch_unlikely(&mmio_stale_data_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers(); @@ -7846,8 +7865,28 @@ static u64 vmx_get_perf_capabilities(void) if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; - if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4) - perf_cap &= ~PERF_CAP_PEBS_BASELINE; + + /* + * Disallow adaptive PEBS as it is functionally broken, can be + * used by the guest to read *host* LBRs, and can be used to + * bypass userspace event filters. To correctly and safely + * support adaptive PEBS, KVM needs to: + * + * 1. Account for the ADAPTIVE flag when (re)programming fixed + * counters. + * + * 2. Gain support from perf (or take direct control of counter + * programming) to support events without adaptive PEBS + * enabled for the hardware counter. + * + * 3. Ensure LBR MSRs cannot hold host data on VM-Entry with + * adaptive PEBS enabled and MSR_PEBS_DATA_CFG.LBRS=1. + * + * 4. Document which PMU events are effectively exposed to the + * guest via adaptive PEBS, and make adaptive PEBS mutually + * exclusive with KVM_SET_PMU_EVENT_FILTER if necessary. + */ + perf_cap &= ~PERF_CAP_PEBS_BASELINE; } return perf_cap; @@ -8286,7 +8325,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_post_state_restore = vmx_apicv_post_state_restore, + .apicv_pre_state_restore = vmx_apicv_pre_state_restore, .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index c2130d2c8e24bb..6be1627d888e5a 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -7,10 +7,10 @@ #include #include #include +#include #include "capabilities.h" #include "../kvm_cache_regs.h" -#include "posted_intr.h" #include "vmcs.h" #include "vmx_ops.h" #include "../cpuid.h" @@ -400,6 +400,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu); void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); bool vmx_nmi_blocked(struct kvm_vcpu *vcpu); +bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu); bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu); bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.c b/arch/x86/kvm/vmx/vmx_onhyperv.c new file mode 100644 index 00000000000000..b9a8b91166d020 --- /dev/null +++ b/arch/x86/kvm/vmx/vmx_onhyperv.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "capabilities.h" +#include "vmx_onhyperv.h" + +DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); + +/* + * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption + * is: in case a feature has corresponding fields in eVMCS described and it was + * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a + * feature which has no corresponding eVMCS field, this likely means that KVM + * needs to be updated. + */ +#define evmcs_check_vmcs_conf(field, ctrl) \ + do { \ + typeof(vmcs_conf->field) unsupported; \ + \ + unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl; \ + if (unsupported) { \ + pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\ + (u64)unsupported); \ + vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl; \ + } \ + } \ + while (0) + +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) +{ + evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL); + evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL); + evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC); + evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC); + evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL); + evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL); +} diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h new file mode 100644 index 00000000000000..11541d272dbd8c --- /dev/null +++ b/arch/x86/kvm/vmx/vmx_onhyperv.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ARCH_X86_KVM_VMX_ONHYPERV_H__ +#define __ARCH_X86_KVM_VMX_ONHYPERV_H__ + +#include + +#include + +#include "capabilities.h" +#include "hyperv.h" +#include "vmcs12.h" + +#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs)) + +#if IS_ENABLED(CONFIG_HYPERV) + +DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); + +static __always_inline bool kvm_is_using_evmcs(void) +{ + return static_branch_unlikely(&__kvm_is_using_evmcs); +} + +static __always_inline int get_evmcs_offset(unsigned long field, + u16 *clean_field) +{ + int offset = evmcs_field_offset(field, clean_field); + + WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field); + return offset; +} + +static __always_inline void evmcs_write64(unsigned long field, u64 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u64 *)((char *)current_evmcs + offset) = value; + + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline void evmcs_write32(unsigned long field, u32 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u32 *)((char *)current_evmcs + offset) = value; + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline void evmcs_write16(unsigned long field, u16 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u16 *)((char *)current_evmcs + offset) = value; + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline u64 evmcs_read64(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u64 *)((char *)current_evmcs + offset); +} + +static __always_inline u32 evmcs_read32(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u32 *)((char *)current_evmcs + offset); +} + +static __always_inline u16 evmcs_read16(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u16 *)((char *)current_evmcs + offset); +} + +static inline void evmcs_load(u64 phys_addr) +{ + struct hv_vp_assist_page *vp_ap = + hv_get_vp_assist_page(smp_processor_id()); + + if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) + vp_ap->nested_control.features.directhypercall = 1; + vp_ap->current_nested_vmcs = phys_addr; + vp_ap->enlighten_vmentry = 1; +} + +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); +#else /* !IS_ENABLED(CONFIG_HYPERV) */ +static __always_inline bool kvm_is_using_evmcs(void) { return false; } +static __always_inline void evmcs_write64(unsigned long field, u64 value) {} +static __always_inline void evmcs_write32(unsigned long field, u32 value) {} +static __always_inline void evmcs_write16(unsigned long field, u16 value) {} +static __always_inline u64 evmcs_read64(unsigned long field) { return 0; } +static __always_inline u32 evmcs_read32(unsigned long field) { return 0; } +static __always_inline u16 evmcs_read16(unsigned long field) { return 0; } +static inline void evmcs_load(u64 phys_addr) {} +#endif /* IS_ENABLED(CONFIG_HYPERV) */ + +#endif /* __ARCH_X86_KVM_VMX_ONHYPERV_H__ */ diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 33af7b4c6eb4a6..8060e5fc6dbd83 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -6,7 +6,7 @@ #include -#include "hyperv.h" +#include "vmx_onhyperv.h" #include "vmcs.h" #include "../x86.h" @@ -94,7 +94,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT - asm_volatile_goto("1: vmread %[field], %[output]\n\t" + asm_goto_output("1: vmread %[field], %[output]\n\t" "jna %l[do_fail]\n\t" _ASM_EXTABLE(1b, %l[do_exception]) @@ -188,7 +188,7 @@ static __always_inline unsigned long vmcs_readl(unsigned long field) #define vmx_asm1(insn, op1, error_args...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + asm goto("1: " __stringify(insn) " %0\n\t" \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ @@ -205,7 +205,7 @@ fault: \ #define vmx_asm2(insn, op1, op2, error_args...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + asm goto("1: " __stringify(insn) " %1, %0\n\t" \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 41cce5031126a0..50cc822e129007 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1620,7 +1620,8 @@ static bool kvm_is_immutable_feature_msr(u32 msr) ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1652,6 +1653,8 @@ static u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_SSB_NO; if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + data |= ARCH_CAP_RFDS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* @@ -3314,7 +3317,7 @@ static bool is_mci_status_msr(u32 msr) static bool can_set_mci_status(struct kvm_vcpu *vcpu) { /* McStatusWrEn enabled? */ - if (guest_cpuid_is_amd_or_hygon(vcpu)) + if (guest_cpuid_is_amd_compatible(vcpu)) return !!(vcpu->arch.msr_hwcr & BIT_ULL(18)); return false; @@ -3641,6 +3644,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_PATCH_LOADER: case MSR_AMD64_BU_CFG2: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: break; @@ -4065,6 +4069,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_BU_CFG2: case MSR_IA32_PERF_CTL: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: /* * Intel Sandy Bridge CPUs must support the RAPL (running average power @@ -5298,7 +5303,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) { vcpu->arch.nmi_pending = 0; atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending); - kvm_make_request(KVM_REQ_NMI, vcpu); + if (events->nmi.pending) + kvm_make_request(KVM_REQ_NMI, vcpu); } static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked); @@ -5823,7 +5829,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events))) break; + kvm_vcpu_srcu_read_lock(vcpu); r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); + kvm_vcpu_srcu_read_unlock(vcpu); break; } case KVM_GET_DEBUGREGS: { @@ -7834,6 +7842,16 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (r < 0) return X86EMUL_UNHANDLEABLE; + + /* + * Mark the page dirty _before_ checking whether or not the CMPXCHG was + * successful, as the old value is written back on failure. Note, for + * live migration, this is unnecessarily conservative as CMPXCHG writes + * back the original value and the access is atomic, but KVM's ABI is + * that all writes are dirty logged, regardless of the value written. + */ + kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa)); + if (r) return X86EMUL_CMPXCHG_FAILED; @@ -10238,7 +10256,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->has_events && - kvm_x86_ops.nested_ops->has_events(vcpu)) + kvm_x86_ops.nested_ops->has_events(vcpu, true)) *req_immediate_exit = true; /* @@ -10440,13 +10458,12 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256); + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); + if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); - else { - static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); - if (ioapic_in_kernel(vcpu->kvm)) - kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); - } + else if (ioapic_in_kernel(vcpu->kvm)) + kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); if (is_guest_mode(vcpu)) vcpu->arch.load_eoi_exitmap_pending = true; @@ -12867,7 +12884,7 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->has_events && - kvm_x86_ops.nested_ops->has_events(vcpu)) + kvm_x86_ops.nested_ops->has_events(vcpu, false)) return true; if (kvm_xen_has_pending_events(vcpu)) diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 40edf4d1974c53..0ea6016ad132a2 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -471,7 +471,7 @@ void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) kvm_xen_update_runstate_guest(v, state == RUNSTATE_runnable); } -static void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) +void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) { struct kvm_lapic_irq irq = { }; int r; diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index f8f1fe22d09069..f5841d9000aebd 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -18,6 +18,7 @@ extern struct static_key_false_deferred kvm_xen_enabled; int __kvm_xen_has_interrupt(struct kvm_vcpu *vcpu); void kvm_xen_inject_pending_events(struct kvm_vcpu *vcpu); +void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *vcpu); int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); @@ -36,6 +37,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm, const struct kvm_irq_routing_entry *ue); void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu); +static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu) +{ + /* + * The local APIC is being enabled. If the per-vCPU upcall vector is + * set and the vCPU's evtchn_upcall_pending flag is set, inject the + * interrupt. + */ + if (static_branch_unlikely(&kvm_xen_enabled.key) && + vcpu->arch.xen.vcpu_info_cache.active && + vcpu->arch.xen.upcall_vector && __kvm_xen_has_interrupt(vcpu)) + kvm_xen_inject_vcpu_vector(vcpu); +} + static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { return static_branch_unlikely(&kvm_xen_enabled.key) && @@ -101,6 +115,10 @@ static inline void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) { } +static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu) +{ +} + static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { return false; diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index ea3a28e7b613cc..f0dae4fb6d0716 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -14,19 +14,6 @@ ifdef CONFIG_KCSAN CFLAGS_REMOVE_delay.o = $(CC_FLAGS_FTRACE) endif -# Early boot use of cmdline; don't instrument it -ifdef CONFIG_AMD_MEM_ENCRYPT -KCOV_INSTRUMENT_cmdline.o := n -KASAN_SANITIZE_cmdline.o := n -KCSAN_SANITIZE_cmdline.o := n - -ifdef CONFIG_FUNCTION_TRACER -CFLAGS_REMOVE_cmdline.o = -pg -endif - -CFLAGS_cmdline.o := -fno-stack-protector -fno-jump-tables -endif - inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt quiet_cmd_inat_tables = GEN $@ diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c index 80efd45a776173..6e8b7e600def57 100644 --- a/arch/x86/lib/copy_mc.c +++ b/arch/x86/lib/copy_mc.c @@ -70,23 +70,23 @@ unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigne } EXPORT_SYMBOL_GPL(copy_mc_to_kernel); -unsigned long __must_check copy_mc_to_user(void *dst, const void *src, unsigned len) +unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, unsigned len) { unsigned long ret; if (copy_mc_fragile_enabled) { __uaccess_begin(); - ret = copy_mc_fragile(dst, src, len); + ret = copy_mc_fragile((__force void *)dst, src, len); __uaccess_end(); return ret; } if (static_cpu_has(X86_FEATURE_ERMS)) { __uaccess_begin(); - ret = copy_mc_enhanced_fast_string(dst, src, len); + ret = copy_mc_enhanced_fast_string((__force void *)dst, src, len); __uaccess_end(); return ret; } - return copy_user_generic(dst, src, len); + return copy_user_generic((__force void *)dst, src, len); } diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index cea25ca8b8cf69..c9dae65ac01b5a 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -11,26 +11,23 @@ #include #include -static inline unsigned short from32to16(unsigned a) +static inline __wsum csum_finalize_sum(u64 temp64) { - unsigned short b = a >> 16; - asm("addw %w2,%w0\n\t" - "adcw $0,%w0\n" - : "=r" (b) - : "0" (b), "r" (a)); - return b; + return (__force __wsum)((temp64 + ror64(temp64, 32)) >> 32); } -static inline __wsum csum_tail(u64 temp64, int odd) +static inline unsigned long update_csum_40b(unsigned long sum, const unsigned long m[5]) { - unsigned int result; - - result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff); - if (unlikely(odd)) { - result = from32to16(result); - result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); - } - return (__force __wsum)result; + asm("addq %1,%0\n\t" + "adcq %2,%0\n\t" + "adcq %3,%0\n\t" + "adcq %4,%0\n\t" + "adcq %5,%0\n\t" + "adcq $0,%0" + :"+r" (sum) + :"m" (m[0]), "m" (m[1]), "m" (m[2]), + "m" (m[3]), "m" (m[4])); + return sum; } /* @@ -47,64 +44,32 @@ static inline __wsum csum_tail(u64 temp64, int odd) __wsum csum_partial(const void *buff, int len, __wsum sum) { u64 temp64 = (__force u64)sum; - unsigned odd; - odd = 1 & (unsigned long) buff; - if (unlikely(odd)) { - if (unlikely(len == 0)) - return sum; - temp64 = ror32((__force u32)sum, 8); - temp64 += (*(unsigned char *)buff << 8); - len--; - buff++; + /* Do two 40-byte chunks in parallel to get better ILP */ + if (likely(len >= 80)) { + u64 temp64_2 = 0; + do { + temp64 = update_csum_40b(temp64, buff); + temp64_2 = update_csum_40b(temp64_2, buff + 40); + buff += 80; + len -= 80; + } while (len >= 80); + + asm("addq %1,%0\n\t" + "adcq $0,%0" + :"+r" (temp64): "r" (temp64_2)); } /* - * len == 40 is the hot case due to IPv6 headers, but annotating it likely() - * has noticeable negative affect on codegen for all other cases with - * minimal performance benefit here. + * len == 40 is the hot case due to IPv6 headers, so return + * early for that exact case without checking the tail bytes. */ - if (len == 40) { - asm("addq 0*8(%[src]),%[res]\n\t" - "adcq 1*8(%[src]),%[res]\n\t" - "adcq 2*8(%[src]),%[res]\n\t" - "adcq 3*8(%[src]),%[res]\n\t" - "adcq 4*8(%[src]),%[res]\n\t" - "adcq $0,%[res]" - : [res] "+r"(temp64) - : [src] "r"(buff), "m"(*(const char(*)[40])buff)); - return csum_tail(temp64, odd); - } - if (unlikely(len >= 64)) { - /* - * Extra accumulators for better ILP in the loop. - */ - u64 tmp_accum, tmp_carries; - - asm("xorl %k[tmp_accum],%k[tmp_accum]\n\t" - "xorl %k[tmp_carries],%k[tmp_carries]\n\t" - "subl $64, %[len]\n\t" - "1:\n\t" - "addq 0*8(%[src]),%[res]\n\t" - "adcq 1*8(%[src]),%[res]\n\t" - "adcq 2*8(%[src]),%[res]\n\t" - "adcq 3*8(%[src]),%[res]\n\t" - "adcl $0,%k[tmp_carries]\n\t" - "addq 4*8(%[src]),%[tmp_accum]\n\t" - "adcq 5*8(%[src]),%[tmp_accum]\n\t" - "adcq 6*8(%[src]),%[tmp_accum]\n\t" - "adcq 7*8(%[src]),%[tmp_accum]\n\t" - "adcl $0,%k[tmp_carries]\n\t" - "addq $64, %[src]\n\t" - "subl $64, %[len]\n\t" - "jge 1b\n\t" - "addq %[tmp_accum],%[res]\n\t" - "adcq %[tmp_carries],%[res]\n\t" - "adcq $0,%[res]" - : [tmp_accum] "=&r"(tmp_accum), - [tmp_carries] "=&r"(tmp_carries), [res] "+r"(temp64), - [len] "+r"(len), [src] "+r"(buff) - : "m"(*(const char *)buff)); + if (len >= 40) { + temp64 = update_csum_40b(temp64, buff); + len -= 40; + if (!len) + return csum_finalize_sum(temp64); + buff += 40; } if (len & 32) { @@ -143,7 +108,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum) : [res] "+r"(temp64) : [trail] "r"(trail)); } - return csum_tail(temp64, odd); + return csum_finalize_sum(temp64); } EXPORT_SYMBOL(csum_partial); diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 9c63713477bbb7..6913fbce6544fb 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -44,7 +44,11 @@ or %rdx, %rax .else cmp $TASK_SIZE_MAX-\size+1, %eax +.if \size != 8 jae .Lbad_get_user +.else + jae .Lbad_get_user_8 +.endif sbb %edx, %edx /* array_index_mask_nospec() */ and %edx, %eax .endif @@ -154,7 +158,7 @@ SYM_CODE_END(__get_user_handle_exception) #ifdef CONFIG_X86_32 SYM_CODE_START_LOCAL(__get_user_8_handle_exception) ASM_CLAC -bad_get_user_8: +.Lbad_get_user_8: xor %edx,%edx xor %ecx,%ecx mov $(-EFAULT),%_ASM_AX @@ -163,23 +167,23 @@ SYM_CODE_END(__get_user_8_handle_exception) #endif /* get_user */ - _ASM_EXTABLE(1b, __get_user_handle_exception) - _ASM_EXTABLE(2b, __get_user_handle_exception) - _ASM_EXTABLE(3b, __get_user_handle_exception) + _ASM_EXTABLE_UA(1b, __get_user_handle_exception) + _ASM_EXTABLE_UA(2b, __get_user_handle_exception) + _ASM_EXTABLE_UA(3b, __get_user_handle_exception) #ifdef CONFIG_X86_64 - _ASM_EXTABLE(4b, __get_user_handle_exception) + _ASM_EXTABLE_UA(4b, __get_user_handle_exception) #else - _ASM_EXTABLE(4b, __get_user_8_handle_exception) - _ASM_EXTABLE(5b, __get_user_8_handle_exception) + _ASM_EXTABLE_UA(4b, __get_user_8_handle_exception) + _ASM_EXTABLE_UA(5b, __get_user_8_handle_exception) #endif /* __get_user */ - _ASM_EXTABLE(6b, __get_user_handle_exception) - _ASM_EXTABLE(7b, __get_user_handle_exception) - _ASM_EXTABLE(8b, __get_user_handle_exception) + _ASM_EXTABLE_UA(6b, __get_user_handle_exception) + _ASM_EXTABLE_UA(7b, __get_user_handle_exception) + _ASM_EXTABLE_UA(8b, __get_user_handle_exception) #ifdef CONFIG_X86_64 - _ASM_EXTABLE(9b, __get_user_handle_exception) + _ASM_EXTABLE_UA(9b, __get_user_handle_exception) #else - _ASM_EXTABLE(9b, __get_user_8_handle_exception) - _ASM_EXTABLE(10b, __get_user_8_handle_exception) + _ASM_EXTABLE_UA(9b, __get_user_8_handle_exception) + _ASM_EXTABLE_UA(10b, __get_user_8_handle_exception) #endif diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c index e0411a3774d495..5eecb45d05d5da 100644 --- a/arch/x86/lib/iomem.c +++ b/arch/x86/lib/iomem.c @@ -25,6 +25,9 @@ static __always_inline void rep_movs(void *to, const void *from, size_t n) static void string_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n) { + const void *orig_to = to; + const size_t orig_n = n; + if (unlikely(!n)) return; @@ -39,7 +42,7 @@ static void string_memcpy_fromio(void *to, const volatile void __iomem *from, si } rep_movs(to, (const void *)from, n); /* KMSAN must treat values read from devices as initialized. */ - kmsan_unpoison_memory(to, n); + kmsan_unpoison_memory(orig_to, orig_n); } static void string_memcpy_toio(volatile void __iomem *to, const void *from, size_t n) diff --git a/arch/x86/lib/misc.c b/arch/x86/lib/misc.c index 92cd8ecc3a2c8c..40b81c338ae5b9 100644 --- a/arch/x86/lib/misc.c +++ b/arch/x86/lib/misc.c @@ -8,7 +8,7 @@ */ int num_digits(int val) { - int m = 10; + long long m = 10; int d = 1; if (val < 0) { diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index 235bbda6fc8230..512dc58c938b81 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -134,15 +134,15 @@ SYM_CODE_START_LOCAL(__put_user_handle_exception) RET SYM_CODE_END(__put_user_handle_exception) - _ASM_EXTABLE(1b, __put_user_handle_exception) - _ASM_EXTABLE(2b, __put_user_handle_exception) - _ASM_EXTABLE(3b, __put_user_handle_exception) - _ASM_EXTABLE(4b, __put_user_handle_exception) - _ASM_EXTABLE(5b, __put_user_handle_exception) - _ASM_EXTABLE(6b, __put_user_handle_exception) - _ASM_EXTABLE(7b, __put_user_handle_exception) - _ASM_EXTABLE(9b, __put_user_handle_exception) + _ASM_EXTABLE_UA(1b, __put_user_handle_exception) + _ASM_EXTABLE_UA(2b, __put_user_handle_exception) + _ASM_EXTABLE_UA(3b, __put_user_handle_exception) + _ASM_EXTABLE_UA(4b, __put_user_handle_exception) + _ASM_EXTABLE_UA(5b, __put_user_handle_exception) + _ASM_EXTABLE_UA(6b, __put_user_handle_exception) + _ASM_EXTABLE_UA(7b, __put_user_handle_exception) + _ASM_EXTABLE_UA(9b, __put_user_handle_exception) #ifdef CONFIG_X86_32 - _ASM_EXTABLE(8b, __put_user_handle_exception) - _ASM_EXTABLE(10b, __put_user_handle_exception) + _ASM_EXTABLE_UA(8b, __put_user_handle_exception) + _ASM_EXTABLE_UA(10b, __put_user_handle_exception) #endif diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index cd86aeb5fdd3ea..ffa51f392e17a3 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -126,12 +126,13 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) #include #undef GEN #endif -/* - * This function name is magical and is used by -mfunction-return=thunk-extern - * for the compiler to generate JMPs to it. - */ + #ifdef CONFIG_RETHUNK + .section .text..__x86.return_thunk + +#ifdef CONFIG_CPU_SRSO + /* * srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at * special addresses: @@ -147,9 +148,7 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) * * As a result, srso_alias_safe_ret() becomes a safe return. */ -#ifdef CONFIG_CPU_SRSO - .section .text..__x86.rethunk_untrain - + .pushsection .text..__x86.rethunk_untrain SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) UNWIND_HINT_FUNC ANNOTATE_NOENDBR @@ -158,17 +157,9 @@ SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) jmp srso_alias_return_thunk SYM_FUNC_END(srso_alias_untrain_ret) __EXPORT_THUNK(srso_alias_untrain_ret) + .popsection - .section .text..__x86.rethunk_safe -#else -/* dummy definition for alternatives */ -SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) - ANNOTATE_UNRET_SAFE - ret - int3 -SYM_FUNC_END(srso_alias_untrain_ret) -#endif - + .pushsection .text..__x86.rethunk_safe SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) lea 8(%_ASM_SP), %_ASM_SP UNWIND_HINT_FUNC @@ -177,14 +168,69 @@ SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) int3 SYM_FUNC_END(srso_alias_safe_ret) - .section .text..__x86.return_thunk - -SYM_CODE_START(srso_alias_return_thunk) +SYM_CODE_START_NOALIGN(srso_alias_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR call srso_alias_safe_ret ud2 SYM_CODE_END(srso_alias_return_thunk) + .popsection + +/* + * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret() + * above. On kernel entry, srso_untrain_ret() is executed which is a + * + * movabs $0xccccc30824648d48,%rax + * + * and when the return thunk executes the inner label srso_safe_ret() + * later, it is a stack manipulation and a RET which is mispredicted and + * thus a "safe" one to use. + */ + .align 64 + .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc +SYM_START(srso_untrain_ret, SYM_L_LOCAL, SYM_A_NONE) + ANNOTATE_NOENDBR + .byte 0x48, 0xb8 + +/* + * This forces the function return instruction to speculate into a trap + * (UD2 in srso_return_thunk() below). This RET will then mispredict + * and execution will continue at the return site read from the top of + * the stack. + */ +SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) + lea 8(%_ASM_SP), %_ASM_SP + ret + int3 + int3 + /* end of movabs */ + lfence + call srso_safe_ret + ud2 +SYM_CODE_END(srso_safe_ret) +SYM_FUNC_END(srso_untrain_ret) + +SYM_CODE_START(srso_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + call srso_safe_ret + ud2 +SYM_CODE_END(srso_return_thunk) + +#define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret" +#else /* !CONFIG_CPU_SRSO */ +#define JMP_SRSO_UNTRAIN_RET "ud2" +/* Dummy for the alternative in CALL_UNTRAIN_RET. */ +SYM_CODE_START(srso_alias_untrain_ret) + ANNOTATE_UNRET_SAFE + ANNOTATE_NOENDBR + ret + int3 +SYM_FUNC_END(srso_alias_untrain_ret) +__EXPORT_THUNK(srso_alias_untrain_ret) +#endif /* CONFIG_CPU_SRSO */ + +#ifdef CONFIG_CPU_UNRET_ENTRY /* * Some generic notes on the untraining sequences: @@ -266,65 +312,19 @@ SYM_CODE_END(retbleed_return_thunk) SYM_FUNC_END(retbleed_untrain_ret) __EXPORT_THUNK(retbleed_untrain_ret) -/* - * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret() - * above. On kernel entry, srso_untrain_ret() is executed which is a - * - * movabs $0xccccc30824648d48,%rax - * - * and when the return thunk executes the inner label srso_safe_ret() - * later, it is a stack manipulation and a RET which is mispredicted and - * thus a "safe" one to use. - */ - .align 64 - .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc -SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) - ANNOTATE_NOENDBR - .byte 0x48, 0xb8 - -/* - * This forces the function return instruction to speculate into a trap - * (UD2 in srso_return_thunk() below). This RET will then mispredict - * and execution will continue at the return site read from the top of - * the stack. - */ -SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) - lea 8(%_ASM_SP), %_ASM_SP - ret - int3 - int3 - /* end of movabs */ - lfence - call srso_safe_ret - ud2 -SYM_CODE_END(srso_safe_ret) -SYM_FUNC_END(srso_untrain_ret) -__EXPORT_THUNK(srso_untrain_ret) +#define JMP_RETBLEED_UNTRAIN_RET "jmp retbleed_untrain_ret" +#else /* !CONFIG_CPU_UNRET_ENTRY */ +#define JMP_RETBLEED_UNTRAIN_RET "ud2" +#endif /* CONFIG_CPU_UNRET_ENTRY */ -SYM_CODE_START(srso_return_thunk) - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - call srso_safe_ret - ud2 -SYM_CODE_END(srso_return_thunk) +#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) SYM_FUNC_START(entry_untrain_ret) - ALTERNATIVE_2 "jmp retbleed_untrain_ret", \ - "jmp srso_untrain_ret", X86_FEATURE_SRSO, \ - "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS + ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) -SYM_CODE_START(__x86_return_thunk) - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - ANNOTATE_UNRET_SAFE - ret - int3 -SYM_CODE_END(__x86_return_thunk) -EXPORT_SYMBOL(__x86_return_thunk) - -#endif /* CONFIG_RETHUNK */ +#endif /* CONFIG_CPU_UNRET_ENTRY || CONFIG_CPU_SRSO */ #ifdef CONFIG_CALL_DEPTH_TRACKING @@ -359,3 +359,22 @@ SYM_FUNC_START(__x86_return_skl) SYM_FUNC_END(__x86_return_skl) #endif /* CONFIG_CALL_DEPTH_TRACKING */ + +/* + * This function name is magical and is used by -mfunction-return=thunk-extern + * for the compiler to generate JMPs to it. + * + * This code is only used during kernel boot or module init. All + * 'JMP __x86_return_thunk' sites are changed to something else by + * apply_returns(). + */ +SYM_CODE_START(__x86_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_CODE_END(__x86_return_thunk) +EXPORT_SYMBOL(__x86_return_thunk) + +#endif /* CONFIG_RETHUNK */ diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 5168ee0360b246..d1ccd06c531278 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -148,7 +148,7 @@ AVXcode: 65: SEG=GS (Prefix) 66: Operand-Size (Prefix) 67: Address-Size (Prefix) -68: PUSH Iz (d64) +68: PUSH Iz 69: IMUL Gv,Ev,Iz 6a: PUSH Ib (d64) 6b: IMUL Gv,Ev,Ib @@ -698,10 +698,10 @@ AVXcode: 2 4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) 4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) 4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev) -50: vpdpbusd Vx,Hx,Wx (66),(ev) -51: vpdpbusds Vx,Hx,Wx (66),(ev) -52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev) -53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev) +50: vpdpbusd Vx,Hx,Wx (66) +51: vpdpbusds Vx,Hx,Wx (66) +52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev) +53: vpdpwssds Vx,Hx,Wx (66) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev) 54: vpopcntb/w Vx,Wx (66),(ev) 55: vpopcntd/q Vx,Wx (66),(ev) 58: vpbroadcastd Vx,Wx (66),(v) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index ab778eac195205..6529b3e2cff3cc 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -376,7 +376,7 @@ static void dump_pagetable(unsigned long address) goto bad; pr_cont("PUD %lx ", pud_val(*pud)); - if (!pud_present(*pud) || pud_large(*pud)) + if (!pud_present(*pud) || pud_leaf(*pud)) goto out; pmd = pmd_offset(pud, address); @@ -717,39 +717,8 @@ kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, WARN_ON_ONCE(user_mode(regs)); /* Are we prepared to handle this kernel fault? */ - if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) { - /* - * Any interrupt that takes a fault gets the fixup. This makes - * the below recursive fault logic only apply to a faults from - * task context. - */ - if (in_interrupt()) - return; - - /* - * Per the above we're !in_interrupt(), aka. task context. - * - * In this case we need to make sure we're not recursively - * faulting through the emulate_vsyscall() logic. - */ - if (current->thread.sig_on_uaccess_err && signal) { - sanitize_error_code(address, &error_code); - - set_signal_archinfo(address, error_code); - - if (si_code == SEGV_PKUERR) { - force_sig_pkuerr((void __user *)address, pkey); - } else { - /* XXX: hwpoison faults will set the wrong code. */ - force_sig_fault(signal, si_code, (void __user *)address); - } - } - - /* - * Barring that, we can do the fixup and be happy. - */ + if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) return; - } /* * AMD erratum #91 manifests as a spurious page fault on a PREFETCH @@ -798,15 +767,6 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, show_opcodes(regs, loglvl); } -/* - * The (legacy) vsyscall page is the long page in the kernel portion - * of the address space that has user-accessible permissions. - */ -static bool is_vsyscall_vaddr(unsigned long vaddr) -{ - return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); -} - static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) @@ -1046,7 +1006,7 @@ spurious_kernel_fault(unsigned long error_code, unsigned long address) if (!pud_present(*pud)) return 0; - if (pud_large(*pud)) + if (pud_leaf(*pud)) return spurious_kernel_fault_check(error_code, (pte_t *) pud); pmd = pmd_offset(pud, address); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 679893ea5e6873..6215dfa23578da 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -261,21 +261,17 @@ static void __init probe_page_size_mask(void) } } -#define INTEL_MATCH(_model) { .vendor = X86_VENDOR_INTEL, \ - .family = 6, \ - .model = _model, \ - } /* * INVLPG may not properly flush Global entries * on these CPUs when PCIDs are enabled. */ static const struct x86_cpu_id invlpg_miss_ids[] = { - INTEL_MATCH(INTEL_FAM6_ALDERLAKE ), - INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ), - INTEL_MATCH(INTEL_FAM6_ATOM_GRACEMONT ), - INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ), - INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P), - INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, 0), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 0), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, 0), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, 0), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, 0), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, 0), {} }; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a190aae8ceaf70..aa69353da49f24 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -617,7 +617,7 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, } if (!pud_none(*pud)) { - if (!pud_large(*pud)) { + if (!pud_leaf(*pud)) { pmd = pmd_offset(pud, 0); paddr_last = phys_pmd_init(pmd, paddr, paddr_end, @@ -950,8 +950,12 @@ static void update_end_of_memory_vars(u64 start, u64 size) int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, struct mhp_params *params) { + unsigned long end = ((start_pfn + nr_pages) << PAGE_SHIFT) - 1; int ret; + if (WARN_ON_ONCE(end > PHYSMEM_END)) + return -ERANGE; + ret = __add_pages(nid, start_pfn, nr_pages, params); WARN_ON_ONCE(ret); @@ -1163,7 +1167,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, if (!pud_present(*pud)) continue; - if (pud_large(*pud) && + if (pud_leaf(*pud) && IS_ALIGNED(addr, PUD_SIZE) && IS_ALIGNED(next, PUD_SIZE)) { spin_lock(&init_mm.page_table_lock); diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 0302491d799d1b..fcf508c52bdc5c 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -115,7 +115,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr, pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); - if (!pud_large(*pud)) + if (!pud_leaf(*pud)) kasan_populate_pud(pud, addr, next, nid); } while (pud++, addr = next, addr != end); } diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 37db264866b648..230f1dee4f0954 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -47,13 +47,24 @@ static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE; */ static __initdata struct kaslr_memory_region { unsigned long *base; + unsigned long *end; unsigned long size_tb; } kaslr_regions[] = { - { &page_offset_base, 0 }, - { &vmalloc_base, 0 }, - { &vmemmap_base, 0 }, + { + .base = &page_offset_base, + .end = &physmem_end, + }, + { + .base = &vmalloc_base, + }, + { + .base = &vmemmap_base, + }, }; +/* The end of the possible address space for physical memory */ +unsigned long physmem_end __ro_after_init; + /* Get size in bytes used by the memory region */ static inline unsigned long get_padding(struct kaslr_memory_region *region) { @@ -82,6 +93,8 @@ void __init kernel_randomize_memory(void) BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE); BUILD_BUG_ON(vaddr_end > __START_KERNEL_map); + /* Preset the end of the possible address space for physical memory */ + physmem_end = ((1ULL << MAX_PHYSMEM_BITS) - 1); if (!kaslr_memory_enabled()) return; @@ -128,11 +141,18 @@ void __init kernel_randomize_memory(void) vaddr += entropy; *kaslr_regions[i].base = vaddr; + /* Calculate the end of the region */ + vaddr += get_padding(&kaslr_regions[i]); /* - * Jump the region and add a minimum padding based on - * randomization alignment. + * KASLR trims the maximum possible size of the + * direct-map. Update the physmem_end boundary. + * No rounding required as the region starts + * PUD aligned and size is in units of TB. */ - vaddr += get_padding(&kaslr_regions[i]); + if (kaslr_regions[i].end) + *kaslr_regions[i].end = __pa_nodebug(vaddr - 1); + + /* Add a minimum padding based on randomization alignment. */ vaddr = round_up(vaddr + 1, PUD_SIZE); remain_entropy -= entropy; } diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c index 5a53c2cc169cc9..42115ac079cfe6 100644 --- a/arch/x86/mm/maccess.c +++ b/arch/x86/mm/maccess.c @@ -3,18 +3,37 @@ #include #include +#include + #ifdef CONFIG_X86_64 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { unsigned long vaddr = (unsigned long)unsafe_src; /* - * Range covering the highest possible canonical userspace address - * as well as non-canonical address range. For the canonical range - * we also need to include the userspace guard page. + * Do not allow userspace addresses. This disallows + * normal userspace and the userspace guard page: + */ + if (vaddr < TASK_SIZE_MAX + PAGE_SIZE) + return false; + + /* + * Reading from the vsyscall page may cause an unhandled fault in + * certain cases. Though it is at an address above TASK_SIZE_MAX, it is + * usually considered as a user space address. */ - return vaddr >= TASK_SIZE_MAX + PAGE_SIZE && - __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits); + if (is_vsyscall_vaddr(vaddr)) + return false; + + /* + * Allow everything during early boot before 'x86_virt_bits' + * is initialized. Needed for instruction decoding in early + * exception handlers. + */ + if (!boot_cpu_data.x86_virt_bits) + return true; + + return __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits); } #else bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 6faea41e99b6bb..1873a65b565578 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -34,6 +34,7 @@ #include #include #include +#include #include "mm_internal.h" @@ -517,6 +518,34 @@ void __init sme_early_init(void) */ if (sev_status & MSR_AMD64_SEV_ES_ENABLED) x86_cpuinit.parallel_bringup = false; + + /* + * The VMM is capable of injecting interrupt 0x80 and triggering the + * compatibility syscall path. + * + * By default, the 32-bit emulation is disabled in order to ensure + * the safety of the VM. + */ + if (sev_status & MSR_AMD64_SEV_ENABLED) + ia32_disable(); + + /* + * Override init functions that scan the ROM region in SEV-SNP guests, + * as this memory is not pre-validated and would thus cause a crash. + */ + if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) { + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.pci.init_irq = x86_init_noop; + x86_init.resources.probe_roms = x86_init_noop; + + /* + * DMI setup behavior for SEV-SNP guests depends on + * efi_enabled(EFI_CONFIG_TABLES), which hasn't been + * parsed yet. snp_dmi_setup() will run after that + * parsing has happened. + */ + x86_init.resources.dmi_setup = snp_dmi_setup; + } } void __init mem_encrypt_free_decrypted_mem(void) diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index d73aeb16417fcf..cc47a818a640af 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -41,9 +41,9 @@ #include #include +#include #include #include -#include #include #include @@ -95,11 +95,7 @@ struct sme_populate_pgd_data { */ static char sme_workarea[2 * PMD_SIZE] __section(".init.scratch"); -static char sme_cmdline_arg[] __initdata = "mem_encrypt"; -static char sme_cmdline_on[] __initdata = "on"; -static char sme_cmdline_off[] __initdata = "off"; - -static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) +static void __head sme_clear_pgd(struct sme_populate_pgd_data *ppd) { unsigned long pgd_start, pgd_end, pgd_size; pgd_t *pgd_p; @@ -114,7 +110,7 @@ static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) memset(pgd_p, 0, pgd_size); } -static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) +static pud_t __head *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) { pgd_t *pgd; p4d_t *p4d; @@ -145,13 +141,13 @@ static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) set_pud(pud, __pud(PUD_FLAGS | __pa(pmd))); } - if (pud_large(*pud)) + if (pud_leaf(*pud)) return NULL; return pud; } -static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) +static void __head sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) { pud_t *pud; pmd_t *pmd; @@ -167,7 +163,7 @@ static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags)); } -static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) +static void __head sme_populate_pgd(struct sme_populate_pgd_data *ppd) { pud_t *pud; pmd_t *pmd; @@ -193,7 +189,7 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) set_pte(pte, __pte(ppd->paddr | ppd->pte_flags)); } -static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) +static void __head __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) { while (ppd->vaddr < ppd->vaddr_end) { sme_populate_pgd_large(ppd); @@ -203,7 +199,7 @@ static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) } } -static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) +static void __head __sme_map_range_pte(struct sme_populate_pgd_data *ppd) { while (ppd->vaddr < ppd->vaddr_end) { sme_populate_pgd(ppd); @@ -213,7 +209,7 @@ static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) } } -static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, +static void __head __sme_map_range(struct sme_populate_pgd_data *ppd, pmdval_t pmd_flags, pteval_t pte_flags) { unsigned long vaddr_end; @@ -237,22 +233,22 @@ static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, __sme_map_range_pte(ppd); } -static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC); } -static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC); } -static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP); } -static unsigned long __init sme_pgtable_calc(unsigned long len) +static unsigned long __head sme_pgtable_calc(unsigned long len) { unsigned long entries = 0, tables = 0; @@ -289,7 +285,7 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) return entries + tables; } -void __init sme_encrypt_kernel(struct boot_params *bp) +void __head sme_encrypt_kernel(struct boot_params *bp) { unsigned long workarea_start, workarea_end, workarea_len; unsigned long execute_start, execute_end, execute_len; @@ -305,7 +301,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * instrumentation or checking boot_cpu_data in the cc_platform_has() * function. */ - if (!sme_get_me_mask() || sev_status & MSR_AMD64_SEV_ENABLED) + if (!sme_get_me_mask() || + RIP_REL_REF(sev_status) & MSR_AMD64_SEV_ENABLED) return; /* @@ -323,9 +320,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * memory from being cached. */ - /* Physical addresses gives us the identity mapped virtual addresses */ - kernel_start = __pa_symbol(_text); - kernel_end = ALIGN(__pa_symbol(_end), PMD_SIZE); + kernel_start = (unsigned long)RIP_REL_REF(_text); + kernel_end = ALIGN((unsigned long)RIP_REL_REF(_end), PMD_SIZE); kernel_len = kernel_end - kernel_start; initrd_start = 0; @@ -342,14 +338,6 @@ void __init sme_encrypt_kernel(struct boot_params *bp) } #endif - /* - * We're running identity mapped, so we must obtain the address to the - * SME encryption workarea using rip-relative addressing. - */ - asm ("lea sme_workarea(%%rip), %0" - : "=r" (workarea_start) - : "p" (sme_workarea)); - /* * Calculate required number of workarea bytes needed: * executable encryption area size: @@ -359,7 +347,7 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * pagetable structures for the encryption of the kernel * pagetable structures for workarea (in case not currently mapped) */ - execute_start = workarea_start; + execute_start = workarea_start = (unsigned long)RIP_REL_REF(sme_workarea); execute_end = execute_start + (PAGE_SIZE * 2) + PMD_SIZE; execute_len = execute_end - execute_start; @@ -502,14 +490,11 @@ void __init sme_encrypt_kernel(struct boot_params *bp) native_write_cr3(__native_read_cr3()); } -void __init sme_enable(struct boot_params *bp) +void __head sme_enable(struct boot_params *bp) { - const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off; unsigned int eax, ebx, ecx, edx; unsigned long feature_mask; - bool active_by_default; unsigned long me_mask; - char buffer[16]; bool snp; u64 msr; @@ -543,15 +528,18 @@ void __init sme_enable(struct boot_params *bp) me_mask = 1UL << (ebx & 0x3f); /* Check the SEV MSR whether SEV or SME is enabled */ - sev_status = __rdmsr(MSR_AMD64_SEV); - feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; + RIP_REL_REF(sev_status) = msr = __rdmsr(MSR_AMD64_SEV); + feature_mask = (msr & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; /* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */ - if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (snp && !(msr & MSR_AMD64_SEV_SNP_ENABLED)) snp_abort(); /* Check if memory encryption is enabled */ if (feature_mask == AMD_SME_BIT) { + if (!(bp->hdr.xloadflags & XLF_MEM_ENCRYPTION)) + return; + /* * No SME if Hypervisor bit is set. This check is here to * prevent a guest from trying to enable SME. For running as a @@ -571,48 +559,10 @@ void __init sme_enable(struct boot_params *bp) msr = __rdmsr(MSR_AMD64_SYSCFG); if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT)) return; - } else { - /* SEV state cannot be controlled by a command line option */ - sme_me_mask = me_mask; - goto out; } - /* - * Fixups have not been applied to phys_base yet and we're running - * identity mapped, so we must obtain the address to the SME command - * line argument data using rip-relative addressing. - */ - asm ("lea sme_cmdline_arg(%%rip), %0" - : "=r" (cmdline_arg) - : "p" (sme_cmdline_arg)); - asm ("lea sme_cmdline_on(%%rip), %0" - : "=r" (cmdline_on) - : "p" (sme_cmdline_on)); - asm ("lea sme_cmdline_off(%%rip), %0" - : "=r" (cmdline_off) - : "p" (sme_cmdline_off)); - - if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT)) - active_by_default = true; - else - active_by_default = false; - - cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr | - ((u64)bp->ext_cmd_line_ptr << 32)); - - if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0) - return; - - if (!strncmp(buffer, cmdline_on, sizeof(buffer))) - sme_me_mask = me_mask; - else if (!strncmp(buffer, cmdline_off, sizeof(buffer))) - sme_me_mask = 0; - else - sme_me_mask = active_by_default ? me_mask : 0; -out: - if (sme_me_mask) { - physical_mask &= ~sme_me_mask; - cc_vendor = CC_VENDOR_AMD; - cc_set_mask(sme_me_mask); - } + RIP_REL_REF(sme_me_mask) = me_mask; + physical_mask &= ~me_mask; + cc_vendor = CC_VENDOR_AMD; + cc_set_mask(me_mask); } diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 2aadb2019b4f23..c7fa5396c0f05c 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -601,13 +602,6 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) if (start >= end) continue; - /* - * Don't confuse VM with a node that doesn't have the - * minimum amount of memory: - */ - if (end && (end - start) < NODE_MIN_SIZE) - continue; - alloc_node_data(nid); } @@ -961,4 +955,78 @@ int memory_add_physaddr_to_nid(u64 start) return nid; } EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); + #endif + +static int __init cmp_memblk(const void *a, const void *b) +{ + const struct numa_memblk *ma = *(const struct numa_memblk **)a; + const struct numa_memblk *mb = *(const struct numa_memblk **)b; + + return (ma->start > mb->start) - (ma->start < mb->start); +} + +static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata; + +/** + * numa_fill_memblks - Fill gaps in numa_meminfo memblks + * @start: address to begin fill + * @end: address to end fill + * + * Find and extend numa_meminfo memblks to cover the physical + * address range @start-@end + * + * RETURNS: + * 0 : Success + * NUMA_NO_MEMBLK : No memblks exist in address range @start-@end + */ + +int __init numa_fill_memblks(u64 start, u64 end) +{ + struct numa_memblk **blk = &numa_memblk_list[0]; + struct numa_meminfo *mi = &numa_meminfo; + int count = 0; + u64 prev_end; + + /* + * Create a list of pointers to numa_meminfo memblks that + * overlap start, end. The list is used to make in-place + * changes that fill out the numa_meminfo memblks. + */ + for (int i = 0; i < mi->nr_blks; i++) { + struct numa_memblk *bi = &mi->blk[i]; + + if (memblock_addrs_overlap(start, end - start, bi->start, + bi->end - bi->start)) { + blk[count] = &mi->blk[i]; + count++; + } + } + if (!count) + return NUMA_NO_MEMBLK; + + /* Sort the list of pointers in memblk->start order */ + sort(&blk[0], count, sizeof(blk[0]), cmp_memblk, NULL); + + /* Make sure the first/last memblks include start/end */ + blk[0]->start = min(blk[0]->start, start); + blk[count - 1]->end = max(blk[count - 1]->end, end); + + /* + * Fill any gaps by tracking the previous memblks + * end address and backfilling to it if needed. + */ + prev_end = blk[0]->end; + for (int i = 1; i < count; i++) { + struct numa_memblk *curr = blk[i]; + + if (prev_end >= curr->start) { + if (prev_end < curr->end) + prev_end = curr->end; + } else { + curr->start = prev_end; + prev_end = curr->end; + } + } + return 0; +} diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index de10800cd4dd48..e7b9ac63bb02aa 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -950,6 +950,38 @@ static void free_pfn_range(u64 paddr, unsigned long size) memtype_free(paddr, paddr + size); } +static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, + pgprot_t *pgprot) +{ + unsigned long prot; + + VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT)); + + /* + * We need the starting PFN and cachemode used for track_pfn_remap() + * that covered the whole VMA. For most mappings, we can obtain that + * information from the page tables. For COW mappings, we might now + * suddenly have anon folios mapped and follow_phys() will fail. + * + * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to + * detect the PFN. If we need the cachemode as well, we're out of luck + * for now and have to fail fork(). + */ + if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) { + if (pgprot) + *pgprot = __pgprot(prot); + return 0; + } + if (is_cow_mapping(vma->vm_flags)) { + if (pgprot) + return -EINVAL; + *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; + return 0; + } + WARN_ON_ONCE(1); + return -EINVAL; +} + /* * track_pfn_copy is called when vma that is covering the pfnmap gets * copied through copy_page_range(). @@ -960,20 +992,13 @@ static void free_pfn_range(u64 paddr, unsigned long size) int track_pfn_copy(struct vm_area_struct *vma) { resource_size_t paddr; - unsigned long prot; unsigned long vma_size = vma->vm_end - vma->vm_start; pgprot_t pgprot; if (vma->vm_flags & VM_PAT) { - /* - * reserve the whole chunk covered by vma. We need the - * starting address and protection from pte. - */ - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, &pgprot)) return -EINVAL; - } - pgprot = __pgprot(prot); + /* reserve the whole chunk covered by vma. */ return reserve_pfn_range(paddr, vma_size, &pgprot, 1); } @@ -1048,7 +1073,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size, bool mm_wr_locked) { resource_size_t paddr; - unsigned long prot; if (vma && !(vma->vm_flags & VM_PAT)) return; @@ -1056,11 +1080,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, /* free the chunk starting from pfn or the whole chunk */ paddr = (resource_size_t)pfn << PAGE_SHIFT; if (!paddr && !size) { - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, NULL)) return; - } - size = vma->vm_end - vma->vm_start; } free_pfn_range(paddr, size); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index bda9f129835e95..2d850f6bae701c 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -619,7 +619,8 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long start, * Validate strict W^X semantics. */ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long start, - unsigned long pfn, unsigned long npg) + unsigned long pfn, unsigned long npg, + bool nx, bool rw) { unsigned long end; @@ -641,6 +642,10 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star if ((pgprot_val(new) & (_PAGE_RW | _PAGE_NX)) != _PAGE_RW) return new; + /* Non-leaf translation entries can disable writing or execution. */ + if (!rw || nx) + return new; + end = start + npg * PAGE_SIZE - 1; WARN_ONCE(1, "CPA detected W^X violation: %016llx -> %016llx range: 0x%016lx - 0x%016lx PFN %lx\n", (unsigned long long)pgprot_val(old), @@ -657,20 +662,26 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star /* * Lookup the page table entry for a virtual address in a specific pgd. - * Return a pointer to the entry and the level of the mapping. + * Return a pointer to the entry, the level of the mapping, and the effective + * NX and RW bits of all page table levels. */ -pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, - unsigned int *level) +pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address, + unsigned int *level, bool *nx, bool *rw) { p4d_t *p4d; pud_t *pud; pmd_t *pmd; *level = PG_LEVEL_NONE; + *nx = false; + *rw = true; if (pgd_none(*pgd)) return NULL; + *nx |= pgd_flags(*pgd) & _PAGE_NX; + *rw &= pgd_flags(*pgd) & _PAGE_RW; + p4d = p4d_offset(pgd, address); if (p4d_none(*p4d)) return NULL; @@ -679,14 +690,20 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, if (p4d_large(*p4d) || !p4d_present(*p4d)) return (pte_t *)p4d; + *nx |= p4d_flags(*p4d) & _PAGE_NX; + *rw &= p4d_flags(*p4d) & _PAGE_RW; + pud = pud_offset(p4d, address); if (pud_none(*pud)) return NULL; *level = PG_LEVEL_1G; - if (pud_large(*pud) || !pud_present(*pud)) + if (pud_leaf(*pud) || !pud_present(*pud)) return (pte_t *)pud; + *nx |= pud_flags(*pud) & _PAGE_NX; + *rw &= pud_flags(*pud) & _PAGE_RW; + pmd = pmd_offset(pud, address); if (pmd_none(*pmd)) return NULL; @@ -695,11 +712,26 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, if (pmd_large(*pmd) || !pmd_present(*pmd)) return (pte_t *)pmd; + *nx |= pmd_flags(*pmd) & _PAGE_NX; + *rw &= pmd_flags(*pmd) & _PAGE_RW; + *level = PG_LEVEL_4K; return pte_offset_kernel(pmd, address); } +/* + * Lookup the page table entry for a virtual address in a specific pgd. + * Return a pointer to the entry and the level of the mapping. + */ +pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, + unsigned int *level) +{ + bool nx, rw; + + return lookup_address_in_pgd_attr(pgd, address, level, &nx, &rw); +} + /* * Lookup the page table entry for a virtual address. Return a pointer * to the entry and the level of the mapping. @@ -715,13 +747,16 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) EXPORT_SYMBOL_GPL(lookup_address); static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, - unsigned int *level) + unsigned int *level, bool *nx, bool *rw) { - if (cpa->pgd) - return lookup_address_in_pgd(cpa->pgd + pgd_index(address), - address, level); + pgd_t *pgd; + + if (!cpa->pgd) + pgd = pgd_offset_k(address); + else + pgd = cpa->pgd + pgd_index(address); - return lookup_address(address, level); + return lookup_address_in_pgd_attr(pgd, address, level, nx, rw); } /* @@ -743,7 +778,7 @@ pmd_t *lookup_pmd_address(unsigned long address) return NULL; pud = pud_offset(p4d, address); - if (pud_none(*pud) || pud_large(*pud) || !pud_present(*pud)) + if (pud_none(*pud) || pud_leaf(*pud) || !pud_present(*pud)) return NULL; return pmd_offset(pud, address); @@ -845,12 +880,13 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address, pgprot_t old_prot, new_prot, req_prot, chk_prot; pte_t new_pte, *tmp; enum pg_level level; + bool nx, rw; /* * Check for races, another CPU might have split this page * up already: */ - tmp = _lookup_address_cpa(cpa, address, &level); + tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw); if (tmp != kpte) return 1; @@ -961,7 +997,8 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address, new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages, psize, CPA_DETECT); - new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages); + new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages, + nx, rw); /* * If there is a conflict, split the large page. @@ -1042,6 +1079,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, pte_t *pbase = (pte_t *)page_address(base); unsigned int i, level; pgprot_t ref_prot; + bool nx, rw; pte_t *tmp; spin_lock(&pgd_lock); @@ -1049,7 +1087,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, * Check for races, another CPU might have split this page * up for us already: */ - tmp = _lookup_address_cpa(cpa, address, &level); + tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw); if (tmp != kpte) { spin_unlock(&pgd_lock); return 1; @@ -1274,7 +1312,7 @@ static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end) */ while (end - start >= PUD_SIZE) { - if (pud_large(*pud)) + if (pud_leaf(*pud)) pud_clear(pud); else unmap_pmd_range(pud, start, start + PUD_SIZE); @@ -1590,10 +1628,11 @@ static int __change_page_attr(struct cpa_data *cpa, int primary) int do_split, err; unsigned int level; pte_t *kpte, old_pte; + bool nx, rw; address = __cpa_addr(cpa, cpa->curpage); repeat: - kpte = _lookup_address_cpa(cpa, address, &level); + kpte = _lookup_address_cpa(cpa, address, &level, &nx, &rw); if (!kpte) return __cpa_process_fault(cpa, address, primary); @@ -1615,7 +1654,8 @@ static int __change_page_attr(struct cpa_data *cpa, int primary) new_prot = static_protections(new_prot, address, pfn, 1, 0, CPA_PROTECT); - new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1); + new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1, + nx, rw); new_prot = pgprot_clear_protnone_bits(new_prot); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 9deadf517f14a9..b18f5a71e679e2 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -628,6 +628,8 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); + /* * No flush is necessary. Once an invalid PTE is established, the PTE's * access and dirty bits cannot be updated. @@ -774,7 +776,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) */ int pud_clear_huge(pud_t *pud) { - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { pud_clear(pud); return 1; } diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 78414c6d1b5ed1..83a6bdf0b498ef 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -217,7 +217,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) pud = pud_offset(p4d, address); /* The user page tables do not use large mappings: */ - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { WARN_ON(1); return NULL; } @@ -241,7 +241,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) * * Returns a pointer to a PTE on success, or NULL on failure. */ -static pte_t *pti_user_pagetable_walk_pte(unsigned long address) +static pte_t *pti_user_pagetable_walk_pte(unsigned long address, bool late_text) { gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); pmd_t *pmd; @@ -251,10 +251,15 @@ static pte_t *pti_user_pagetable_walk_pte(unsigned long address) if (!pmd) return NULL; - /* We can't do anything sensible if we hit a large mapping. */ + /* Large PMD mapping found */ if (pmd_large(*pmd)) { - WARN_ON(1); - return NULL; + /* Clear the PMD if we hit a large mapping from the first round */ + if (late_text) { + set_pmd(pmd, __pmd(0)); + } else { + WARN_ON_ONCE(1); + return NULL; + } } if (pmd_none(*pmd)) { @@ -283,7 +288,7 @@ static void __init pti_setup_vsyscall(void) if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte)) return; - target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR); + target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR, false); if (WARN_ON(!target_pte)) return; @@ -301,7 +306,7 @@ enum pti_clone_level { static void pti_clone_pgtable(unsigned long start, unsigned long end, - enum pti_clone_level level) + enum pti_clone_level level, bool late_text) { unsigned long addr; @@ -374,14 +379,14 @@ pti_clone_pgtable(unsigned long start, unsigned long end, */ *target_pmd = *pmd; - addr += PMD_SIZE; + addr = round_up(addr + 1, PMD_SIZE); } else if (level == PTI_CLONE_PTE) { /* Walk the page-table down to the pte level */ pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) { - addr += PAGE_SIZE; + addr = round_up(addr + 1, PAGE_SIZE); continue; } @@ -390,7 +395,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end, return; /* Allocate PTE in the user page-table */ - target_pte = pti_user_pagetable_walk_pte(addr); + target_pte = pti_user_pagetable_walk_pte(addr, late_text); if (WARN_ON(!target_pte)) return; @@ -401,7 +406,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end, /* Clone the PTE */ *target_pte = *pte; - addr += PAGE_SIZE; + addr = round_up(addr + 1, PAGE_SIZE); } else { BUG(); @@ -452,7 +457,7 @@ static void __init pti_clone_user_shared(void) phys_addr_t pa = per_cpu_ptr_to_phys((void *)va); pte_t *target_pte; - target_pte = pti_user_pagetable_walk_pte(va); + target_pte = pti_user_pagetable_walk_pte(va, false); if (WARN_ON(!target_pte)) return; @@ -475,7 +480,7 @@ static void __init pti_clone_user_shared(void) start = CPU_ENTRY_AREA_BASE; end = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES); - pti_clone_pgtable(start, end, PTI_CLONE_PMD); + pti_clone_pgtable(start, end, PTI_CLONE_PMD, false); } #endif /* CONFIG_X86_64 */ @@ -492,11 +497,11 @@ static void __init pti_setup_espfix64(void) /* * Clone the populated PMDs of the entry text and force it RO. */ -static void pti_clone_entry_text(void) +static void pti_clone_entry_text(bool late) { pti_clone_pgtable((unsigned long) __entry_text_start, (unsigned long) __entry_text_end, - PTI_CLONE_PMD); + PTI_LEVEL_KERNEL_IMAGE, late); } /* @@ -571,7 +576,7 @@ static void pti_clone_kernel_text(void) * pti_set_kernel_image_nonglobal() did to clear the * global bit. */ - pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE); + pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE, false); /* * pti_clone_pgtable() will set the global bit in any PMDs @@ -638,8 +643,15 @@ void __init pti_init(void) /* Undo all global bits from the init pagetables in head_64.S: */ pti_set_kernel_image_nonglobal(); + /* Replace some of the global bits just for shared entry text: */ - pti_clone_entry_text(); + /* + * This is very early in boot. Device and Late initcalls can do + * modprobe before free_initmem() and mark_readonly(). This + * pti_clone_entry_text() allows those user-mode-helpers to function, + * but notably the text is still RW. + */ + pti_clone_entry_text(false); pti_setup_espfix64(); pti_setup_vsyscall(); } @@ -656,10 +668,11 @@ void pti_finalize(void) if (!boot_cpu_has(X86_FEATURE_PTI)) return; /* - * We need to clone everything (again) that maps parts of the - * kernel image. + * This is after free_initmem() (all initcalls are done) and we've done + * mark_readonly(). Text is now NX which might've split some PMDs + * relative to the early clone. */ - pti_clone_entry_text(); + pti_clone_entry_text(true); pti_clone_kernel_text(); debug_checkwx_user(); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 453ea95b667dad..2fbae48f0b470a 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -497,9 +497,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, { struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm); u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); - unsigned long new_lam = mm_lam_cr3_mask(next); bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy); unsigned cpu = smp_processor_id(); + unsigned long new_lam; u64 next_tlb_gen; bool need_flush; u16 new_asid; @@ -622,9 +622,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); } - /* - * Start remote flushes and then read tlb_gen. - */ + /* Start receiving IPIs and then read tlb_gen (and LAM below) */ if (next != &init_mm) cpumask_set_cpu(cpu, mm_cpumask(next)); next_tlb_gen = atomic64_read(&next->context.tlb_gen); @@ -636,6 +634,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, barrier(); } + new_lam = mm_lam_cr3_mask(next); set_tlbstate_lam_mode(next); if (need_flush) { this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index a5930042139d3b..a50c99e9b5c01f 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -58,6 +58,56 @@ static bool is_imm8(int value) return value <= 127 && value >= -128; } +/* + * Let us limit the positive offset to be <= 123. + * This is to ensure eventual jit convergence For the following patterns: + * ... + * pass4, final_proglen=4391: + * ... + * 20e: 48 85 ff test rdi,rdi + * 211: 74 7d je 0x290 + * 213: 48 8b 77 00 mov rsi,QWORD PTR [rdi+0x0] + * ... + * 289: 48 85 ff test rdi,rdi + * 28c: 74 17 je 0x2a5 + * 28e: e9 7f ff ff ff jmp 0x212 + * 293: bf 03 00 00 00 mov edi,0x3 + * Note that insn at 0x211 is 2-byte cond jump insn for offset 0x7d (-125) + * and insn at 0x28e is 5-byte jmp insn with offset -129. + * + * pass5, final_proglen=4392: + * ... + * 20e: 48 85 ff test rdi,rdi + * 211: 0f 84 80 00 00 00 je 0x297 + * 217: 48 8b 77 00 mov rsi,QWORD PTR [rdi+0x0] + * ... + * 28d: 48 85 ff test rdi,rdi + * 290: 74 1a je 0x2ac + * 292: eb 84 jmp 0x218 + * 294: bf 03 00 00 00 mov edi,0x3 + * Note that insn at 0x211 is 6-byte cond jump insn now since its offset + * becomes 0x80 based on previous round (0x293 - 0x213 = 0x80). + * At the same time, insn at 0x292 is a 2-byte insn since its offset is + * -124. + * + * pass6 will repeat the same code as in pass4 and this will prevent + * eventual convergence. + * + * To fix this issue, we need to break je (2->6 bytes) <-> jmp (5->2 bytes) + * cycle in the above. In the above example je offset <= 0x7c should work. + * + * For other cases, je <-> je needs offset <= 0x7b to avoid no convergence + * issue. For jmp <-> je and jmp <-> jmp cases, jmp offset <= 0x7c should + * avoid no convergence issue. + * + * Overall, let us limit the positive offset for 8bit cond/uncond jmp insn + * to maximum 123 (0x7b). This way, the jit pass can eventually converge. + */ +static bool is_imm8_jmp_offset(int value) +{ + return value <= 123 && value >= -128; +} + static bool is_simm32(s64 value) { return value == (s64)(s32)value; @@ -344,7 +394,7 @@ static int emit_call(u8 **pprog, void *func, void *ip) static int emit_rsb_call(u8 **pprog, void *func, void *ip) { OPTIMIZER_HIDE_VAR(func); - x86_call_depth_emit_accounting(pprog, func); + ip += x86_call_depth_emit_accounting(pprog, func); return emit_patch(pprog, func, ip, 0xE8); } @@ -1018,6 +1068,10 @@ static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op) #define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp))) +/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ +#define RESTORE_TAIL_CALL_CNT(stack) \ + EMIT3_off32(0x48, 0x8B, 0x85, -round_up(stack, 8) - 8) + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding) { @@ -1454,36 +1508,41 @@ st: if (is_imm8(insn->off)) if (BPF_MODE(insn->code) == BPF_PROBE_MEM || BPF_MODE(insn->code) == BPF_PROBE_MEMSX) { /* Conservatively check that src_reg + insn->off is a kernel address: - * src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE - * src_reg is used as scratch for src_reg += insn->off and restored - * after emit_ldx if necessary + * src_reg + insn->off > TASK_SIZE_MAX + PAGE_SIZE + * and + * src_reg + insn->off < VSYSCALL_ADDR */ - u64 limit = TASK_SIZE_MAX + PAGE_SIZE; + u64 limit = TASK_SIZE_MAX + PAGE_SIZE - VSYSCALL_ADDR; u8 *end_of_jmp; - /* At end of these emitted checks, insn->off will have been added - * to src_reg, so no need to do relative load with insn->off offset - */ - insn_off = 0; + /* movabsq r10, VSYSCALL_ADDR */ + emit_mov_imm64(&prog, BPF_REG_AX, (long)VSYSCALL_ADDR >> 32, + (u32)(long)VSYSCALL_ADDR); - /* movabsq r11, limit */ - EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG)); - EMIT((u32)limit, 4); - EMIT(limit >> 32, 4); + /* mov src_reg, r11 */ + EMIT_mov(AUX_REG, src_reg); if (insn->off) { - /* add src_reg, insn->off */ - maybe_emit_1mod(&prog, src_reg, true); - EMIT2_off32(0x81, add_1reg(0xC0, src_reg), insn->off); + /* add r11, insn->off */ + maybe_emit_1mod(&prog, AUX_REG, true); + EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off); } - /* cmp src_reg, r11 */ - maybe_emit_mod(&prog, src_reg, AUX_REG, true); - EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG)); + /* sub r11, r10 */ + maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); + EMIT2(0x29, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); + + /* movabsq r10, limit */ + emit_mov_imm64(&prog, BPF_REG_AX, (long)limit >> 32, + (u32)(long)limit); - /* if unsigned '>=', goto load */ - EMIT2(X86_JAE, 0); + /* cmp r10, r11 */ + maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); + EMIT2(0x39, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); + + /* if unsigned '>', goto load */ + EMIT2(X86_JA, 0); end_of_jmp = prog; /* xor dst_reg, dst_reg */ @@ -1509,18 +1568,6 @@ st: if (is_imm8(insn->off)) /* populate jmp_offset for JMP above */ start_of_ldx[-1] = prog - start_of_ldx; - if (insn->off && src_reg != dst_reg) { - /* sub src_reg, insn->off - * Restore src_reg after "add src_reg, insn->off" in prev - * if statement. But if src_reg == dst_reg, emit_ldx - * above already clobbered src_reg, so no need to restore. - * If add src_reg, insn->off was unnecessary, no need to - * restore either. - */ - maybe_emit_1mod(&prog, src_reg, true); - EMIT2_off32(0x81, add_1reg(0xE8, src_reg), insn->off); - } - if (!bpf_prog->aux->extable) break; @@ -1623,9 +1670,7 @@ st: if (is_imm8(insn->off)) func = (u8 *) __bpf_call_base + imm32; if (tail_call_reachable) { - /* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ - EMIT3_off32(0x48, 0x8B, 0x85, - -round_up(bpf_prog->aux->stack_depth, 8) - 8); + RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth); if (!imm32) return -EINVAL; offs = 7 + x86_call_depth_emit_accounting(&prog, func); @@ -1779,7 +1824,7 @@ st: if (is_imm8(insn->off)) return -EFAULT; } jmp_offset = addrs[i + insn->off] - addrs[i]; - if (is_imm8(jmp_offset)) { + if (is_imm8_jmp_offset(jmp_offset)) { if (jmp_padding) { /* To keep the jmp_offset valid, the extra bytes are * padded before the jump insn, so we subtract the @@ -1861,7 +1906,7 @@ st: if (is_imm8(insn->off)) break; } emit_jmp: - if (is_imm8(jmp_offset)) { + if (is_imm8_jmp_offset(jmp_offset)) { if (jmp_padding) { /* To avoid breaking jmp_offset, the extra bytes * are padded before the actual jmp insn, so @@ -2400,6 +2445,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i * [ ... ] * [ stack_arg2 ] * RBP - arg_stack_off [ stack_arg1 ] + * RSP [ tail_call_cnt ] BPF_TRAMP_F_TAIL_CALL_CTX */ /* room for return value of orig_call or fentry prog */ @@ -2464,6 +2510,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i else /* sub rsp, stack_size */ EMIT4(0x48, 0x83, 0xEC, stack_size); + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + EMIT1(0x50); /* push rax */ /* mov QWORD PTR [rbp - rbx_off], rbx */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_6, -rbx_off); @@ -2516,9 +2564,15 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i restore_regs(m, &prog, regs_off); save_args(m, &prog, arg_stack_off, true); + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + /* Before calling the original function, restore the + * tail_call_cnt from stack to rax. + */ + RESTORE_TAIL_CALL_CNT(stack_size); + if (flags & BPF_TRAMP_F_ORIG_STACK) { - emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8); - EMIT2(0xff, 0xd0); /* call *rax */ + emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, 8); + EMIT2(0xff, 0xd3); /* call *rbx */ } else { /* call original function */ if (emit_rsb_call(&prog, orig_call, prog)) { @@ -2569,7 +2623,12 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i ret = -EINVAL; goto cleanup; } - } + } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + /* Before running the original function, restore the + * tail_call_cnt from stack to rax. + */ + RESTORE_TAIL_CALL_CNT(stack_size); + /* restore return value of orig_call or fentry prog back into RAX */ if (save_ret) emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); @@ -2913,3 +2972,49 @@ void bpf_jit_free(struct bpf_prog *prog) bpf_prog_unlock_free(prog); } + +void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, + struct bpf_prog *new, struct bpf_prog *old) +{ + u8 *old_addr, *new_addr, *old_bypass_addr; + int ret; + + old_bypass_addr = old ? NULL : poke->bypass_addr; + old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL; + new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL; + + /* + * On program loading or teardown, the program's kallsym entry + * might not be in place, so we use __bpf_arch_text_poke to skip + * the kallsyms check. + */ + if (new) { + ret = __bpf_arch_text_poke(poke->tailcall_target, + BPF_MOD_JUMP, + old_addr, new_addr); + BUG_ON(ret < 0); + if (!old) { + ret = __bpf_arch_text_poke(poke->tailcall_bypass, + BPF_MOD_JUMP, + poke->bypass_addr, + NULL); + BUG_ON(ret < 0); + } + } else { + ret = __bpf_arch_text_poke(poke->tailcall_bypass, + BPF_MOD_JUMP, + old_bypass_addr, + poke->bypass_addr); + BUG_ON(ret < 0); + /* let other CPUs finish the execution of program + * so that it will not possible to expose them + * to invalid nop, stack unwind, nop state + */ + if (!ret) + synchronize_rcu(); + ret = __bpf_arch_text_poke(poke->tailcall_target, + BPF_MOD_JUMP, + old_addr, NULL); + BUG_ON(ret < 0); + } +} diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index e3ec02e6ac9feb..98a9bb92d75c88 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -3,9 +3,11 @@ * Exceptions for specific devices. Usually work-arounds for fatal design flaws. */ +#include #include #include #include +#include #include #include #include @@ -904,3 +906,108 @@ static void chromeos_fixup_apl_pci_l1ss_capability(struct pci_dev *dev) } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x5ad6, chromeos_save_apl_pci_l1ss_capability); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, 0x5ad6, chromeos_fixup_apl_pci_l1ss_capability); + +/* + * Disable D3cold on Asus B1400 PCI-NVMe bridge + * + * On this platform with VMD off, the NVMe device cannot successfully power + * back on from D3cold. This appears to be an untested transition by the + * vendor: Windows leaves the NVMe and parent bridge in D0 during suspend. + * + * We disable D3cold on the parent bridge for simplicity, and the fact that + * both parent bridge and NVMe device share the same power resource. + * + * This is only needed on BIOS versions before 308; the newer versions flip + * StorageD3Enable from 1 to 0. + */ +static const struct dmi_system_id asus_nvme_broken_d3cold_table[] = { + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BIOS_VERSION, "B1400CEAE.304"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BIOS_VERSION, "B1400CEAE.305"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BIOS_VERSION, "B1400CEAE.306"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BIOS_VERSION, "B1400CEAE.307"), + }, + }, + {} +}; + +static void asus_disable_nvme_d3cold(struct pci_dev *pdev) +{ + if (dmi_check_system(asus_nvme_broken_d3cold_table) > 0) + pci_d3cold_disable(pdev); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x9a09, asus_disable_nvme_d3cold); + +#ifdef CONFIG_SUSPEND +/* + * Root Ports on some AMD SoCs advertise PME_Support for D3hot and D3cold, but + * if the SoC is put into a hardware sleep state by the amd-pmc driver, the + * Root Ports don't generate wakeup interrupts for USB devices. + * + * When suspending, remove D3hot and D3cold from the PME_Support advertised + * by the Root Port so we don't use those states if we're expecting wakeup + * interrupts. Restore the advertised PME_Support when resuming. + */ +static void amd_rp_pme_suspend(struct pci_dev *dev) +{ + struct pci_dev *rp; + + /* + * PM_SUSPEND_ON means we're doing runtime suspend, which means + * amd-pmc will not be involved so PMEs during D3 work as advertised. + * + * The PMEs *do* work if amd-pmc doesn't put the SoC in the hardware + * sleep state, but we assume amd-pmc is always present. + */ + if (pm_suspend_target_state == PM_SUSPEND_ON) + return; + + rp = pcie_find_root_port(dev); + if (!rp || !rp->pm_cap) + return; + + rp->pme_support &= ~((PCI_PM_CAP_PME_D3hot|PCI_PM_CAP_PME_D3cold) >> + PCI_PM_CAP_PME_SHIFT); + dev_info_once(&rp->dev, "quirk: disabling D3cold for suspend\n"); +} + +static void amd_rp_pme_resume(struct pci_dev *dev) +{ + struct pci_dev *rp; + u16 pmc; + + rp = pcie_find_root_port(dev); + if (!rp || !rp->pm_cap) + return; + + pci_read_config_word(rp, rp->pm_cap + PCI_PM_PMC, &pmc); + rp->pme_support = FIELD_GET(PCI_PM_CAP_PME_MASK, pmc); +} +/* Rembrandt (yellow_carp) */ +DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x162e, amd_rp_pme_suspend); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x162e, amd_rp_pme_resume); +DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x162f, amd_rp_pme_suspend); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x162f, amd_rp_pme_resume); +/* Phoenix (pink_sardine) */ +DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x1668, amd_rp_pme_suspend); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1668, amd_rp_pme_resume); +DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x1669, amd_rp_pme_suspend); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1669, amd_rp_pme_resume); +#endif /* CONFIG_SUSPEND */ diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 8edd6220660446..722a33be08a186 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -233,9 +233,9 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) return 0; ret = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); - if (ret < 0) { + if (ret) { dev_warn(&dev->dev, "Failed to read interrupt line: %d\n", ret); - return ret; + return pcibios_err_to_errno(ret); } id = x86_match_cpu(intel_mid_cpu_ids); diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 4b3efaa82ab7c1..8447d1e2e1961e 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -525,7 +525,36 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, static bool __ref pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early) { - if (!early && !acpi_disabled) { + struct resource *conflict; + + if (early) { + + /* + * Don't try to do this check unless configuration type 1 + * is available. How about type 2? + */ + + /* + * 946f2ee5c731 ("Check that MCFG points to an e820 + * reserved area") added this E820 check in 2006 to work + * around BIOS defects. + * + * Per PCI Firmware r3.3, sec 4.1.2, ECAM space must be + * reserved by a PNP0C02 resource, but it need not be + * mentioned in E820. Before the ACPI interpreter is + * available, we can't check for PNP0C02 resources, so + * there's no reliable way to verify the region in this + * early check. Keep it only for the old machines that + * motivated 946f2ee5c731. + */ + if (dmi_get_bios_year() < 2016 && raw_pci_ops) + return is_mmconf_reserved(e820__mapped_all, cfg, dev, + "E820 entry"); + + return true; + } + + if (!acpi_disabled) { if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, "ACPI motherboard resource")) return true; @@ -542,8 +571,17 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e &cfg->res); if (is_mmconf_reserved(is_efi_mmio, cfg, dev, - "EfiMemoryMappedIO")) + "EfiMemoryMappedIO")) { + conflict = insert_resource_conflict(&iomem_resource, + &cfg->res); + if (conflict) + pr_warn("MMCONFIG %pR conflicts with %s %pR\n", + &cfg->res, conflict->name, conflict); + else + pr_info("MMCONFIG %pR reserved to work around lack of ACPI motherboard _CRS\n", + &cfg->res); return true; + } } /* @@ -552,16 +590,7 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e * For MCFG information constructed from hotpluggable host bridge's * _CBA method, just assume it's reserved. */ - if (pci_mmcfg_running_state) - return true; - - /* Don't try to do this check unless configuration - type 1 is available. how about type 2 ?*/ - if (raw_pci_ops) - return is_mmconf_reserved(e820__mapped_all, cfg, dev, - "E820 entry"); - - return false; + return pci_mmcfg_running_state; } static void __init pci_mmcfg_reject_broken(int early) diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 652cd53e77f641..0f2fe524f60dcd 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -38,10 +38,10 @@ static int xen_pcifront_enable_irq(struct pci_dev *dev) u8 gsi; rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); - if (rc < 0) { + if (rc) { dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n", rc); - return rc; + return pcibios_err_to_errno(rc); } /* In PV DomU the Xen PCI backend puts the PIRQ in the interrupt line.*/ pirq = gsi; diff --git a/arch/x86/platform/efi/memmap.c b/arch/x86/platform/efi/memmap.c index 4ef20b49eb5e72..6ed1935504b96e 100644 --- a/arch/x86/platform/efi/memmap.c +++ b/arch/x86/platform/efi/memmap.c @@ -92,12 +92,22 @@ int __init efi_memmap_alloc(unsigned int num_entries, */ int __init efi_memmap_install(struct efi_memory_map_data *data) { + unsigned long size = efi.memmap.desc_size * efi.memmap.nr_map; + unsigned long flags = efi.memmap.flags; + u64 phys = efi.memmap.phys_map; + int ret; + efi_memmap_unmap(); if (efi_enabled(EFI_PARAVIRT)) return 0; - return __efi_memmap_init(data); + ret = __efi_memmap_init(data); + if (ret) + return ret; + + __efi_memmap_free(phys, size, flags); + return 0; } /** diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c index fdd49d70b43738..c81cea208c2c43 100644 --- a/arch/x86/platform/intel/iosf_mbi.c +++ b/arch/x86/platform/intel/iosf_mbi.c @@ -62,7 +62,7 @@ static int iosf_mbi_pci_read_mdr(u32 mcrx, u32 mcr, u32 *mdr) fail_read: dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result); - return result; + return pcibios_err_to_errno(result); } static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr) @@ -91,7 +91,7 @@ static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr) fail_write: dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result); - return result; + return pcibios_err_to_errno(result); } int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 00a92cb2c81474..a12117f3d4de72 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -74,6 +74,9 @@ static void __init init_pvh_bootparams(bool xen_guest) } else xen_raw_printk("Warning: Can fit ISA range into e820\n"); + if (xen_guest) + xen_reserve_extra_memory(&pvh_bootparams); + pvh_bootparams.hdr.cmd_line_ptr = pvh_start_info.cmdline_paddr; diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c index 6f955eb1e1631a..d8af46e6775034 100644 --- a/arch/x86/power/hibernate.c +++ b/arch/x86/power/hibernate.c @@ -170,7 +170,7 @@ int relocate_restore_code(void) goto out; } pud = pud_offset(p4d, relocated_restore_code); - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); goto out; } diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 08aa0f25f12a0f..8d1c82795ea1da 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -42,7 +42,8 @@ KCOV_INSTRUMENT := n # make up the standalone purgatory.ro PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel -PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss -g0 +PURGATORY_CFLAGS := -mcmodel=small -ffreestanding -fno-zero-initialized-in-bss -g0 +PURGATORY_CFLAGS += -fpic -fvisibility=hidden PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING PURGATORY_CFLAGS += -fno-stack-protector diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index d30949e25ebd9b..a2cfd19c11eea1 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -653,6 +653,14 @@ static void print_absolute_relocs(void) if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) { continue; } + /* + * Do not perform relocations in .notes section; any + * values there are meant for pre-boot consumption (e.g. + * startup_xen). + */ + if (sec_applies->shdr.sh_type == SHT_NOTE) { + continue; + } sh_symtab = sec_symtab->symtab; sym_strtab = sec_symtab->link->strtab; for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) { @@ -738,6 +746,15 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel, if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) { continue; } + + /* + * Do not perform relocations in .notes sections; any + * values there are meant for pre-boot consumption (e.g. + * startup_xen). + */ + if (sec_applies->shdr.sh_type == SHT_NOTE) + continue; + sh_symtab = sec_symtab->symtab; sym_strtab = sec_symtab->link->strtab; for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) { diff --git a/arch/x86/um/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp.h index 166cedbab9266f..8c81d1a604a942 100644 --- a/arch/x86/um/shared/sysdep/archsetjmp.h +++ b/arch/x86/um/shared/sysdep/archsetjmp.h @@ -1,6 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_UM_SYSDEP_ARCHSETJMP_H +#define __X86_UM_SYSDEP_ARCHSETJMP_H + #ifdef __i386__ #include "archsetjmp_32.h" #else #include "archsetjmp_64.h" #endif + +unsigned long get_thread_reg(int reg, jmp_buf *buf); + +#endif /* __X86_UM_SYSDEP_ARCHSETJMP_H */ diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 9b1ec5d8c99c8d..a65fc2ae15b496 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -9,6 +9,7 @@ config XEN select PARAVIRT_CLOCK select X86_HV_CALLBACK_VECTOR depends on X86_64 || (X86_32 && X86_PAE) + depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MCORE2 || MATOM || MK8) depends on X86_LOCAL_APIC && X86_TSC help This is the Linux Xen port. Enabling this will allow the diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 0337392a312141..b88722dfc4f867 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include @@ -33,9 +34,12 @@ EXPORT_SYMBOL_GPL(hypercall_page); * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info * but during boot it is switched to point to xen_vcpu_info. * The pointer is used in xen_evtchn_do_upcall to acknowledge pending events. + * Make sure that xen_vcpu_info doesn't cross a page boundary by making it + * cache-line aligned (the struct is guaranteed to have a size of 64 bytes, + * which matches the cache line size of 64-bit x86 processors). */ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); -DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); +DEFINE_PER_CPU_ALIGNED(struct vcpu_info, xen_vcpu_info); /* Linux <-> Xen vCPU id mapping */ DEFINE_PER_CPU(uint32_t, xen_vcpu_id); @@ -160,6 +164,7 @@ void xen_vcpu_setup(int cpu) int err; struct vcpu_info *vcpup; + BUILD_BUG_ON(sizeof(*vcpup) > SMP_CACHE_BYTES); BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); /* @@ -346,3 +351,67 @@ void xen_arch_unregister_cpu(int num) } EXPORT_SYMBOL(xen_arch_unregister_cpu); #endif + +/* Amount of extra memory space we add to the e820 ranges */ +struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; + +void __init xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns) +{ + unsigned int i; + + /* + * No need to check for zero size, should happen rarely and will only + * write a new entry regarded to be unused due to zero size. + */ + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + /* Add new region. */ + if (xen_extra_mem[i].n_pfns == 0) { + xen_extra_mem[i].start_pfn = start_pfn; + xen_extra_mem[i].n_pfns = n_pfns; + break; + } + /* Append to existing region. */ + if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns == + start_pfn) { + xen_extra_mem[i].n_pfns += n_pfns; + break; + } + } + if (i == XEN_EXTRA_MEM_MAX_REGIONS) + printk(KERN_WARNING "Warning: not enough extra memory regions\n"); + + memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); +} + +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC +int __init arch_xen_unpopulated_init(struct resource **res) +{ + unsigned int i; + + if (!xen_domain()) + return -ENODEV; + + /* Must be set strictly before calling xen_free_unpopulated_pages(). */ + *res = &iomem_resource; + + /* + * Initialize with pages from the extra memory regions (see + * arch/x86/xen/setup.c). + */ + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + unsigned int j; + + for (j = 0; j < xen_extra_mem[i].n_pfns; j++) { + struct page *pg = + pfn_to_page(xen_extra_mem[i].start_pfn + j); + + xen_free_unpopulated_pages(1, &pg); + } + + /* Zero so region is not also added to the balloon driver. */ + xen_extra_mem[i].n_pfns = 0; + } + + return 0; +} +#endif diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index bbbfdd495ebd3a..aeb33e0a3f7633 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -704,7 +704,7 @@ static struct trap_array_entry trap_array[] = { TRAP_ENTRY(exc_int3, false ), TRAP_ENTRY(exc_overflow, false ), #ifdef CONFIG_IA32_EMULATION - { entry_INT80_compat, xen_entry_INT80_compat, false }, + TRAP_ENTRY(int80_emulation, false ), #endif TRAP_ENTRY(exc_page_fault, false ), TRAP_ENTRY(exc_divide_error, false ), diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index ada3868c02c231..c28f073c1df524 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include @@ -72,3 +73,70 @@ void __init mem_map_via_hcall(struct boot_params *boot_params_p) } boot_params_p->e820_entries = memmap.nr_entries; } + +/* + * Reserve e820 UNUSABLE regions to inflate the memory balloon. + * + * On PVH dom0 the host memory map is used, RAM regions available to dom0 are + * located as the same place as in the native memory map, but since dom0 gets + * less memory than the total amount of host RAM the ranges that can't be + * populated are converted from RAM -> UNUSABLE. Use such regions (up to the + * ratio signaled in EXTRA_MEM_RATIO) in order to inflate the balloon driver at + * boot. Doing so prevents the guest (even if just temporary) from using holes + * in the memory map in order to map grants or foreign addresses, and + * hopefully limits the risk of a clash with a device MMIO region. Ideally the + * hypervisor should notify us which memory ranges are suitable for creating + * foreign mappings, but that's not yet implemented. + */ +void __init xen_reserve_extra_memory(struct boot_params *bootp) +{ + unsigned int i, ram_pages = 0, extra_pages; + + for (i = 0; i < bootp->e820_entries; i++) { + struct boot_e820_entry *e = &bootp->e820_table[i]; + + if (e->type != E820_TYPE_RAM) + continue; + ram_pages += PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr); + } + + /* Max amount of extra memory. */ + extra_pages = EXTRA_MEM_RATIO * ram_pages; + + /* + * Convert UNUSABLE ranges to RAM and reserve them for foreign mapping + * purposes. + */ + for (i = 0; i < bootp->e820_entries && extra_pages; i++) { + struct boot_e820_entry *e = &bootp->e820_table[i]; + unsigned long pages; + + if (e->type != E820_TYPE_UNUSABLE) + continue; + + pages = min(extra_pages, + PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr)); + + if (pages != (PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr))) { + struct boot_e820_entry *next; + + if (bootp->e820_entries == + ARRAY_SIZE(bootp->e820_table)) + /* No space left to split - skip region. */ + continue; + + /* Split entry. */ + next = e + 1; + memmove(next, e, + (bootp->e820_entries - i) * sizeof(*e)); + bootp->e820_entries++; + next->addr = PAGE_ALIGN(e->addr) + PFN_PHYS(pages); + e->size = next->addr - e->addr; + next->size -= e->size; + } + e->type = E820_TYPE_RAM; + extra_pages -= pages; + + xen_add_extra_mem(PFN_UP(e->addr), pages); + } +} diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index b6830554ff6905..6b201e64d8abc8 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1082,7 +1082,7 @@ static void __init xen_cleanmfnmap_pud(pud_t *pud, bool unpin) pmd_t *pmd_tbl; int i; - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { pa = pud_val(*pud) & PHYSICAL_PAGE_MASK; xen_free_ro_pages(pa, PUD_SIZE); return; @@ -1863,7 +1863,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) if (!pud_present(pud)) return 0; pa = pud_val(pud) & PTE_PFN_MASK; - if (pud_large(pud)) + if (pud_leaf(pud)) return pa + (vaddr & ~PUD_MASK); pmd = native_make_pmd(xen_read_phys_ulong(pa + pmd_index(vaddr) * @@ -2019,10 +2019,7 @@ void __init xen_reserve_special_pages(void) void __init xen_pt_check_e820(void) { - if (xen_is_e820_reserved(xen_pt_base, xen_pt_size)) { - xen_raw_console_write("Xen hypervisor allocated page table memory conflicts with E820 map\n"); - BUG(); - } + xen_chk_is_e820_usable(xen_pt_base, xen_pt_size, "page table"); } static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 9bdc3b656b2c49..11b5c042d4faef 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -70,6 +70,7 @@ #include #include #include +#include #include #include @@ -80,6 +81,7 @@ #include #include #include +#include #include "multicalls.h" #include "xen-ops.h" @@ -731,7 +733,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, * immediate unmapping. */ map_ops[i].status = GNTST_general_error; - unmap[0].host_addr = map_ops[i].host_addr, + unmap[0].host_addr = map_ops[i].host_addr; unmap[0].handle = map_ops[i].handle; map_ops[i].handle = INVALID_GRANT_HANDLE; if (map_ops[i].flags & GNTMAP_device_map) @@ -741,7 +743,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, if (kmap_ops) { kmap_ops[i].status = GNTST_general_error; - unmap[1].host_addr = kmap_ops[i].host_addr, + unmap[1].host_addr = kmap_ops[i].host_addr; unmap[1].handle = kmap_ops[i].handle; kmap_ops[i].handle = INVALID_GRANT_HANDLE; if (kmap_ops[i].flags & GNTMAP_device_map) @@ -794,6 +796,102 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, return ret; } +/* Remapped non-RAM areas */ +#define NR_NONRAM_REMAP 4 +static struct nonram_remap { + phys_addr_t maddr; + phys_addr_t paddr; + size_t size; +} xen_nonram_remap[NR_NONRAM_REMAP] __ro_after_init; +static unsigned int nr_nonram_remap __ro_after_init; + +/* + * Do the real remapping of non-RAM regions as specified in the + * xen_nonram_remap[] array. + * In case of an error just crash the system. + */ +void __init xen_do_remap_nonram(void) +{ + unsigned int i; + unsigned int remapped = 0; + const struct nonram_remap *remap = xen_nonram_remap; + unsigned long pfn, mfn, end_pfn; + + for (i = 0; i < nr_nonram_remap; i++) { + end_pfn = PFN_UP(remap->paddr + remap->size); + pfn = PFN_DOWN(remap->paddr); + mfn = PFN_DOWN(remap->maddr); + while (pfn < end_pfn) { + if (!set_phys_to_machine(pfn, mfn)) + panic("Failed to set p2m mapping for pfn=%lx mfn=%lx\n", + pfn, mfn); + + pfn++; + mfn++; + remapped++; + } + + remap++; + } + + pr_info("Remapped %u non-RAM page(s)\n", remapped); +} + +#ifdef CONFIG_ACPI +/* + * Xen variant of acpi_os_ioremap() taking potentially remapped non-RAM + * regions into account. + * Any attempt to map an area crossing a remap boundary will produce a + * WARN() splat. + * phys is related to remap->maddr on input and will be rebased to remap->paddr. + */ +static void __iomem *xen_acpi_os_ioremap(acpi_physical_address phys, + acpi_size size) +{ + unsigned int i; + const struct nonram_remap *remap = xen_nonram_remap; + + for (i = 0; i < nr_nonram_remap; i++) { + if (phys + size > remap->maddr && + phys < remap->maddr + remap->size) { + WARN_ON(phys < remap->maddr || + phys + size > remap->maddr + remap->size); + phys += remap->paddr - remap->maddr; + break; + } + } + + return x86_acpi_os_ioremap(phys, size); +} +#endif /* CONFIG_ACPI */ + +/* + * Add a new non-RAM remap entry. + * In case of no free entry found, just crash the system. + */ +void __init xen_add_remap_nonram(phys_addr_t maddr, phys_addr_t paddr, + unsigned long size) +{ + BUG_ON((maddr & ~PAGE_MASK) != (paddr & ~PAGE_MASK)); + + if (nr_nonram_remap == NR_NONRAM_REMAP) { + xen_raw_console_write("Number of required E820 entry remapping actions exceed maximum value\n"); + BUG(); + } + +#ifdef CONFIG_ACPI + /* Switch to the Xen acpi_os_ioremap() variant. */ + if (nr_nonram_remap == 0) + acpi_os_ioremap = xen_acpi_os_ioremap; +#endif + + xen_nonram_remap[nr_nonram_remap].maddr = maddr; + xen_nonram_remap[nr_nonram_remap].paddr = paddr; + xen_nonram_remap[nr_nonram_remap].size = size; + + nr_nonram_remap++; +} + #ifdef CONFIG_XEN_DEBUG_FS #include #include "debugfs.h" diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index b3e37961065a2c..dc822124cacb9c 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -15,12 +15,12 @@ #include #include #include +#include #include #include #include #include -#include #include #include #include @@ -38,9 +38,6 @@ #define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024) -/* Amount of extra memory space we add to the e820 ranges */ -struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; - /* Number of pages released from the initial allocation. */ unsigned long xen_released_pages; @@ -50,6 +47,9 @@ bool xen_pv_pci_possible; /* E820 map used during setting up memory. */ static struct e820_table xen_e820_table __initdata; +/* Number of initially usable memory pages. */ +static unsigned long ini_nr_pages __initdata; + /* * Buffer used to remap identity mapped pages. We only need the virtual space. * The physical page behind this address is remapped as needed to different @@ -64,18 +64,6 @@ static struct { } xen_remap_buf __initdata __aligned(PAGE_SIZE); static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY; -/* - * The maximum amount of extra memory compared to the base size. The - * main scaling factor is the size of struct page. At extreme ratios - * of base:extra, all the base memory can be filled with page - * structures for the extra memory, leaving no space for anything - * else. - * - * 10x seems like a reasonable balance between scaling flexibility and - * leaving a practically usable system. - */ -#define EXTRA_MEM_RATIO (10) - static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB); static void __init xen_parse_512gb(void) @@ -96,35 +84,6 @@ static void __init xen_parse_512gb(void) xen_512gb_limit = val; } -static void __init xen_add_extra_mem(unsigned long start_pfn, - unsigned long n_pfns) -{ - int i; - - /* - * No need to check for zero size, should happen rarely and will only - * write a new entry regarded to be unused due to zero size. - */ - for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { - /* Add new region. */ - if (xen_extra_mem[i].n_pfns == 0) { - xen_extra_mem[i].start_pfn = start_pfn; - xen_extra_mem[i].n_pfns = n_pfns; - break; - } - /* Append to existing region. */ - if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns == - start_pfn) { - xen_extra_mem[i].n_pfns += n_pfns; - break; - } - } - if (i == XEN_EXTRA_MEM_MAX_REGIONS) - printk(KERN_WARNING "Warning: not enough extra memory regions\n"); - - memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); -} - static void __init xen_del_extra_mem(unsigned long start_pfn, unsigned long n_pfns) { @@ -257,7 +216,7 @@ static int __init xen_free_mfn(unsigned long mfn) * as a fallback if the remapping fails. */ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, - unsigned long end_pfn, unsigned long nr_pages) + unsigned long end_pfn) { unsigned long pfn, end; int ret; @@ -265,7 +224,7 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, WARN_ON(start_pfn > end_pfn); /* Release pages first. */ - end = min(end_pfn, nr_pages); + end = min(end_pfn, ini_nr_pages); for (pfn = start_pfn; pfn < end; pfn++) { unsigned long mfn = pfn_to_mfn(pfn); @@ -386,15 +345,14 @@ static void __init xen_do_set_identity_and_remap_chunk( * to Xen and not remapped. */ static unsigned long __init xen_set_identity_and_remap_chunk( - unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages, - unsigned long remap_pfn) + unsigned long start_pfn, unsigned long end_pfn, unsigned long remap_pfn) { unsigned long pfn; unsigned long i = 0; unsigned long n = end_pfn - start_pfn; if (remap_pfn == 0) - remap_pfn = nr_pages; + remap_pfn = ini_nr_pages; while (i < n) { unsigned long cur_pfn = start_pfn + i; @@ -403,19 +361,19 @@ static unsigned long __init xen_set_identity_and_remap_chunk( unsigned long remap_range_size; /* Do not remap pages beyond the current allocation */ - if (cur_pfn >= nr_pages) { + if (cur_pfn >= ini_nr_pages) { /* Identity map remaining pages */ set_phys_range_identity(cur_pfn, cur_pfn + size); break; } - if (cur_pfn + size > nr_pages) - size = nr_pages - cur_pfn; + if (cur_pfn + size > ini_nr_pages) + size = ini_nr_pages - cur_pfn; remap_range_size = xen_find_pfn_range(&remap_pfn); if (!remap_range_size) { pr_warn("Unable to find available pfn range, not remapping identity pages\n"); xen_set_identity_and_release_chunk(cur_pfn, - cur_pfn + left, nr_pages); + cur_pfn + left); break; } /* Adjust size to fit in current e820 RAM region */ @@ -442,18 +400,18 @@ static unsigned long __init xen_set_identity_and_remap_chunk( } static unsigned long __init xen_count_remap_pages( - unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages, + unsigned long start_pfn, unsigned long end_pfn, unsigned long remap_pages) { - if (start_pfn >= nr_pages) + if (start_pfn >= ini_nr_pages) return remap_pages; - return remap_pages + min(end_pfn, nr_pages) - start_pfn; + return remap_pages + min(end_pfn, ini_nr_pages) - start_pfn; } -static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages, +static unsigned long __init xen_foreach_remap_area( unsigned long (*func)(unsigned long start_pfn, unsigned long end_pfn, - unsigned long nr_pages, unsigned long last_val)) + unsigned long last_val)) { phys_addr_t start = 0; unsigned long ret_val = 0; @@ -481,8 +439,7 @@ static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages, end_pfn = PFN_UP(entry->addr); if (start_pfn < end_pfn) - ret_val = func(start_pfn, end_pfn, nr_pages, - ret_val); + ret_val = func(start_pfn, end_pfn, ret_val); start = end; } } @@ -539,6 +496,8 @@ void __init xen_remap_memory(void) set_pte_mfn(buf, mfn_save, PAGE_KERNEL); pr_info("Remapped %ld page(s)\n", remapped); + + xen_do_remap_nonram(); } static unsigned long __init xen_get_pages_limit(void) @@ -612,7 +571,7 @@ static void __init xen_ignore_unusable(void) } } -bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size) +static bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size) { struct e820_entry *entry; unsigned mapcnt; @@ -669,6 +628,111 @@ phys_addr_t __init xen_find_free_area(phys_addr_t size) return 0; } +/* + * Swap a non-RAM E820 map entry with RAM above ini_nr_pages. + * Note that the E820 map is modified accordingly, but the P2M map isn't yet. + * The adaption of the P2M must be deferred until page allocation is possible. + */ +static void __init xen_e820_swap_entry_with_ram(struct e820_entry *swap_entry) +{ + struct e820_entry *entry; + unsigned int mapcnt; + phys_addr_t mem_end = PFN_PHYS(ini_nr_pages); + phys_addr_t swap_addr, swap_size, entry_end; + + swap_addr = PAGE_ALIGN_DOWN(swap_entry->addr); + swap_size = PAGE_ALIGN(swap_entry->addr - swap_addr + swap_entry->size); + entry = xen_e820_table.entries; + + for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) { + entry_end = entry->addr + entry->size; + if (entry->type == E820_TYPE_RAM && entry->size >= swap_size && + entry_end - swap_size >= mem_end) { + /* Reduce RAM entry by needed space (whole pages). */ + entry->size -= swap_size; + + /* Add new entry at the end of E820 map. */ + entry = xen_e820_table.entries + + xen_e820_table.nr_entries; + xen_e820_table.nr_entries++; + + /* Fill new entry (keep size and page offset). */ + entry->type = swap_entry->type; + entry->addr = entry_end - swap_size + + swap_addr - swap_entry->addr; + entry->size = swap_entry->size; + + /* Convert old entry to RAM, align to pages. */ + swap_entry->type = E820_TYPE_RAM; + swap_entry->addr = swap_addr; + swap_entry->size = swap_size; + + /* Remember PFN<->MFN relation for P2M update. */ + xen_add_remap_nonram(swap_addr, entry_end - swap_size, + swap_size); + + /* Order E820 table and merge entries. */ + e820__update_table(&xen_e820_table); + + return; + } + + entry++; + } + + xen_raw_console_write("No suitable area found for required E820 entry remapping action\n"); + BUG(); +} + +/* + * Look for non-RAM memory types in a specific guest physical area and move + * those away if possible (ACPI NVS only for now). + */ +static void __init xen_e820_resolve_conflicts(phys_addr_t start, + phys_addr_t size) +{ + struct e820_entry *entry; + unsigned int mapcnt; + phys_addr_t end; + + if (!size) + return; + + end = start + size; + entry = xen_e820_table.entries; + + for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) { + if (entry->addr >= end) + return; + + if (entry->addr + entry->size > start && + entry->type == E820_TYPE_NVS) + xen_e820_swap_entry_with_ram(entry); + + entry++; + } +} + +/* + * Check for an area in physical memory to be usable for non-movable purposes. + * An area is considered to usable if the used E820 map lists it to be RAM or + * some other type which can be moved to higher PFNs while keeping the MFNs. + * In case the area is not usable, crash the system with an error message. + */ +void __init xen_chk_is_e820_usable(phys_addr_t start, phys_addr_t size, + const char *component) +{ + xen_e820_resolve_conflicts(start, size); + + if (!xen_is_e820_reserved(start, size)) + return; + + xen_raw_console_write("Xen hypervisor allocated "); + xen_raw_console_write(component); + xen_raw_console_write(" memory conflicts with E820 map\n"); + BUG(); +} + /* * Like memcpy, but with physical addresses for dest and src. */ @@ -728,20 +792,20 @@ static void __init xen_reserve_xen_mfnlist(void) **/ char * __init xen_memory_setup(void) { - unsigned long max_pfn, pfn_s, n_pfns; + unsigned long pfn_s, n_pfns; phys_addr_t mem_end, addr, size, chunk_size; u32 type; int rc; struct xen_memory_map memmap; unsigned long max_pages; unsigned long extra_pages = 0; + unsigned long maxmem_pages; int i; int op; xen_parse_512gb(); - max_pfn = xen_get_pages_limit(); - max_pfn = min(max_pfn, xen_start_info->nr_pages); - mem_end = PFN_PHYS(max_pfn); + ini_nr_pages = min(xen_get_pages_limit(), xen_start_info->nr_pages); + mem_end = PFN_PHYS(ini_nr_pages); memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries); set_xen_guest_handle(memmap.buffer, xen_e820_table.entries); @@ -791,13 +855,35 @@ char * __init xen_memory_setup(void) /* Make sure the Xen-supplied memory map is well-ordered. */ e820__update_table(&xen_e820_table); + /* + * Check whether the kernel itself conflicts with the target E820 map. + * Failing now is better than running into weird problems later due + * to relocating (and even reusing) pages with kernel text or data. + */ + xen_chk_is_e820_usable(__pa_symbol(_text), + __pa_symbol(_end) - __pa_symbol(_text), + "kernel"); + + /* + * Check for a conflict of the xen_start_info memory with the target + * E820 map. + */ + xen_chk_is_e820_usable(__pa(xen_start_info), sizeof(*xen_start_info), + "xen_start_info"); + + /* + * Check for a conflict of the hypervisor supplied page tables with + * the target E820 map. + */ + xen_pt_check_e820(); + max_pages = xen_get_max_pages(); /* How many extra pages do we need due to remapping? */ - max_pages += xen_foreach_remap_area(max_pfn, xen_count_remap_pages); + max_pages += xen_foreach_remap_area(xen_count_remap_pages); - if (max_pages > max_pfn) - extra_pages += max_pages - max_pfn; + if (max_pages > ini_nr_pages) + extra_pages += max_pages - ini_nr_pages; /* * Clamp the amount of extra memory to a EXTRA_MEM_RATIO @@ -806,8 +892,8 @@ char * __init xen_memory_setup(void) * Make sure we have no memory above max_pages, as this area * isn't handled by the p2m management. */ - extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), - extra_pages, max_pages - max_pfn); + maxmem_pages = EXTRA_MEM_RATIO * min(ini_nr_pages, PFN_DOWN(MAXMEM)); + extra_pages = min3(maxmem_pages, extra_pages, max_pages - ini_nr_pages); i = 0; addr = xen_e820_table.entries[0].addr; size = xen_e820_table.entries[0].size; @@ -863,23 +949,6 @@ char * __init xen_memory_setup(void) e820__update_table(e820_table); - /* - * Check whether the kernel itself conflicts with the target E820 map. - * Failing now is better than running into weird problems later due - * to relocating (and even reusing) pages with kernel text or data. - */ - if (xen_is_e820_reserved(__pa_symbol(_text), - __pa_symbol(__bss_stop) - __pa_symbol(_text))) { - xen_raw_console_write("Xen hypervisor allocated kernel memory conflicts with E820 map\n"); - BUG(); - } - - /* - * Check for a conflict of the hypervisor supplied page tables with - * the target E820 map. - */ - xen_pt_check_e820(); - xen_reserve_xen_mfnlist(); /* Check for a conflict of the initrd with the target E820 map. */ @@ -907,7 +976,7 @@ char * __init xen_memory_setup(void) * Set identity map on non-RAM pages and prepare remapping the * underlying RAM. */ - xen_foreach_remap_area(max_pfn, xen_set_identity_and_remap_chunk); + xen_foreach_remap_area(xen_set_identity_and_remap_chunk); pr_info("Released %ld page(s)\n", xen_released_pages); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 4b0d6fff88de5a..1fb9a1644d944b 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -65,6 +65,8 @@ int xen_smp_intr_init(unsigned int cpu) char *resched_name, *callfunc_name, *debug_name; resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu); + if (!resched_name) + goto fail_mem; per_cpu(xen_resched_irq, cpu).name = resched_name; rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, cpu, @@ -77,6 +79,8 @@ int xen_smp_intr_init(unsigned int cpu) per_cpu(xen_resched_irq, cpu).irq = rc; callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu); + if (!callfunc_name) + goto fail_mem; per_cpu(xen_callfunc_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR, cpu, @@ -90,6 +94,9 @@ int xen_smp_intr_init(unsigned int cpu) if (!xen_fifo_events) { debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu); + if (!debug_name) + goto fail_mem; + per_cpu(xen_debug_irq, cpu).name = debug_name; rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt, @@ -101,6 +108,9 @@ int xen_smp_intr_init(unsigned int cpu) } callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu); + if (!callfunc_name) + goto fail_mem; + per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR, cpu, @@ -114,6 +124,8 @@ int xen_smp_intr_init(unsigned int cpu) return 0; + fail_mem: + rc = -ENOMEM; fail: xen_smp_intr_free(cpu); return rc; diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 9e5e680087853a..1a9cd18dfbd312 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -156,7 +156,7 @@ xen_pv_trap asm_xenpv_exc_machine_check #endif /* CONFIG_X86_MCE */ xen_pv_trap asm_exc_simd_coprocessor_error #ifdef CONFIG_IA32_EMULATION -xen_pv_trap entry_INT80_compat +xen_pv_trap asm_int80_emulation #endif xen_pv_trap asm_exc_xen_unknown_trap xen_pv_trap asm_exc_xen_hypervisor_callback diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 408a2aa66c6922..a6a21dd0552700 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -21,7 +21,7 @@ extern void *xen_initial_gdt; struct trap_info; void xen_copy_trap_info(struct trap_info *traps); -DECLARE_PER_CPU(struct vcpu_info, xen_vcpu_info); +DECLARE_PER_CPU_ALIGNED(struct vcpu_info, xen_vcpu_info); DECLARE_PER_CPU(unsigned long, xen_cr3); DECLARE_PER_CPU(unsigned long, xen_current_cr3); @@ -43,8 +43,12 @@ void xen_mm_unpin_all(void); #ifdef CONFIG_X86_64 void __init xen_relocate_p2m(void); #endif +void __init xen_do_remap_nonram(void); +void __init xen_add_remap_nonram(phys_addr_t maddr, phys_addr_t paddr, + unsigned long size); -bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size); +void __init xen_chk_is_e820_usable(phys_addr_t start, phys_addr_t size, + const char *component); unsigned long __ref xen_chk_extra_mem(unsigned long pfn); void __init xen_inv_extra_mem(void); void __init xen_remap_memory(void); @@ -163,4 +167,18 @@ void xen_hvm_post_suspend(int suspend_cancelled); static inline void xen_hvm_post_suspend(int suspend_cancelled) {} #endif +/* + * The maximum amount of extra memory compared to the base size. The + * main scaling factor is the size of struct page. At extreme ratios + * of base:extra, all the base memory can be filled with page + * structures for the extra memory, leaving no space for anything + * else. + * + * 10x seems like a reasonable balance between scaling flexibility and + * leaving a practically usable system. + */ +#define EXTRA_MEM_RATIO (10) + +void xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns); + #endif /* XEN_OPS_H */ diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h index 785a00ce83c11e..38bcecb0e457d9 100644 --- a/arch/xtensa/include/asm/cacheflush.h +++ b/arch/xtensa/include/asm/cacheflush.h @@ -116,8 +116,9 @@ void flush_cache_page(struct vm_area_struct*, #define flush_cache_mm(mm) flush_cache_all() #define flush_cache_dup_mm(mm) flush_cache_mm(mm) -#define flush_cache_vmap(start,end) flush_cache_all() -#define flush_cache_vunmap(start,end) flush_cache_all() +#define flush_cache_vmap(start,end) flush_cache_all() +#define flush_cache_vmap_early(start,end) do { } while (0) +#define flush_cache_vunmap(start,end) flush_cache_all() void flush_dcache_folio(struct folio *folio); #define flush_dcache_folio flush_dcache_folio @@ -140,6 +141,7 @@ void local_flush_cache_page(struct vm_area_struct *vma, #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_vmap(start,end) do { } while (0) +#define flush_cache_vmap_early(start,end) do { } while (0) #define flush_cache_vunmap(start,end) do { } while (0) #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 diff --git a/arch/xtensa/include/asm/jump_label.h b/arch/xtensa/include/asm/jump_label.h index c812bf85021c02..46c8596259d2d9 100644 --- a/arch/xtensa/include/asm/jump_label.h +++ b/arch/xtensa/include/asm/jump_label.h @@ -13,7 +13,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "_nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" @@ -38,7 +38,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, * make it reachable and wrap both into a no-transform block * to avoid any assembler interference with this. */ - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" ".begin no-transform\n\t" "_j %l[l_yes]\n\t" "2:\n\t" diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index d008a153a2b9f7..7ed1a2085bd728 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -115,9 +115,9 @@ #define MAKE_RA_FOR_CALL(ra,ws) (((ra) & 0x3fffffff) | (ws) << 30) /* Convert return address to a valid pc - * Note: We assume that the stack pointer is in the same 1GB ranges as the ra + * Note: 'text' is the address within the same 1GB range as the ra */ -#define MAKE_PC_FROM_RA(ra,sp) (((ra) & 0x3fffffff) | ((sp) & 0xc0000000)) +#define MAKE_PC_FROM_RA(ra, text) (((ra) & 0x3fffffff) | ((unsigned long)(text) & 0xc0000000)) #elif defined(__XTENSA_CALL0_ABI__) @@ -127,9 +127,9 @@ #define MAKE_RA_FOR_CALL(ra, ws) (ra) /* Convert return address to a valid pc - * Note: We assume that the stack pointer is in the same 1GB ranges as the ra + * Note: 'text' is not used as 'ra' is always the full address */ -#define MAKE_PC_FROM_RA(ra, sp) (ra) +#define MAKE_PC_FROM_RA(ra, text) (ra) #else #error Unsupported Xtensa ABI diff --git a/arch/xtensa/include/asm/ptrace.h b/arch/xtensa/include/asm/ptrace.h index a270467556dc84..86c70117371bb7 100644 --- a/arch/xtensa/include/asm/ptrace.h +++ b/arch/xtensa/include/asm/ptrace.h @@ -87,7 +87,7 @@ struct pt_regs { # define user_mode(regs) (((regs)->ps & 0x00000020)!=0) # define instruction_pointer(regs) ((regs)->pc) # define return_pointer(regs) (MAKE_PC_FROM_RA((regs)->areg[0], \ - (regs)->areg[1])) + (regs)->pc)) # ifndef CONFIG_SMP # define profile_pc(regs) instruction_pointer(regs) diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index a815577d25fd02..7bd66677f7b6de 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -47,6 +47,7 @@ #include #include #include +#include #include extern void ret_from_fork(void); @@ -380,7 +381,7 @@ unsigned long __get_wchan(struct task_struct *p) int count = 0; sp = p->thread.sp; - pc = MAKE_PC_FROM_RA(p->thread.ra, p->thread.sp); + pc = MAKE_PC_FROM_RA(p->thread.ra, _text); do { if (sp < stack_page + sizeof(struct task_struct) || @@ -392,7 +393,7 @@ unsigned long __get_wchan(struct task_struct *p) /* Stack layout: sp-4: ra, sp-3: sp' */ - pc = MAKE_PC_FROM_RA(SPILL_SLOT(sp, 0), sp); + pc = MAKE_PC_FROM_RA(SPILL_SLOT(sp, 0), _text); sp = SPILL_SLOT(sp, 1); } while (count++ < 16); return 0; diff --git a/arch/xtensa/kernel/stacktrace.c b/arch/xtensa/kernel/stacktrace.c index 831ffb648bda7e..ed324fdf2a2f91 100644 --- a/arch/xtensa/kernel/stacktrace.c +++ b/arch/xtensa/kernel/stacktrace.c @@ -13,6 +13,7 @@ #include #include +#include #include #include #include @@ -189,7 +190,7 @@ void walk_stackframe(unsigned long *sp, if (a1 <= (unsigned long)sp) break; - frame.pc = MAKE_PC_FROM_RA(a0, a1); + frame.pc = MAKE_PC_FROM_RA(a0, _text); frame.sp = a1; if (fn(&frame, data)) diff --git a/block/bdev.c b/block/bdev.c index f3b13aa1b7d428..5a54977518eeae 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -425,6 +425,8 @@ void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors) void bdev_add(struct block_device *bdev, dev_t dev) { + if (bdev_stable_writes(bdev)) + mapping_set_stable_writes(bdev->bd_inode->i_mapping); bdev->bd_dev = dev; bdev->bd_inode->i_rdev = dev; bdev->bd_inode->i_ino = dev; @@ -829,6 +831,25 @@ struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, } EXPORT_SYMBOL(blkdev_get_by_dev); +struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, + const struct blk_holder_ops *hops) +{ + struct bdev_handle *handle = kmalloc(sizeof(*handle), GFP_KERNEL); + struct block_device *bdev; + + if (!handle) + return ERR_PTR(-ENOMEM); + bdev = blkdev_get_by_dev(dev, mode, holder, hops); + if (IS_ERR(bdev)) { + kfree(handle); + return ERR_CAST(bdev); + } + handle->bdev = bdev; + handle->holder = holder; + return handle; +} +EXPORT_SYMBOL(bdev_open_by_dev); + /** * blkdev_get_by_path - open a block device by name * @path: path to the block device to open @@ -867,6 +888,28 @@ struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode, } EXPORT_SYMBOL(blkdev_get_by_path); +struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode, + void *holder, const struct blk_holder_ops *hops) +{ + struct bdev_handle *handle; + dev_t dev; + int error; + + error = lookup_bdev(path, &dev); + if (error) + return ERR_PTR(error); + + handle = bdev_open_by_dev(dev, mode, holder, hops); + if (!IS_ERR(handle) && (mode & BLK_OPEN_WRITE) && + bdev_read_only(handle->bdev)) { + bdev_release(handle); + return ERR_PTR(-EACCES); + } + + return handle; +} +EXPORT_SYMBOL(bdev_open_by_path); + void blkdev_put(struct block_device *bdev, void *holder) { struct gendisk *disk = bdev->bd_disk; @@ -903,6 +946,13 @@ void blkdev_put(struct block_device *bdev, void *holder) } EXPORT_SYMBOL(blkdev_put); +void bdev_release(struct bdev_handle *handle) +{ + blkdev_put(handle->bdev, handle->holder); + kfree(handle); +} +EXPORT_SYMBOL(bdev_release); + /** * lookup_bdev() - Look up a struct block_device by name. * @pathname: Name of the block device in the filesystem. diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 3cce6de464a7b7..7e0dcded5713a0 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2911,8 +2911,12 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[a_idx]; /* if a merge has already been setup, then proceed with that first */ - if (bfqq->new_bfqq) - return bfqq->new_bfqq; + new_bfqq = bfqq->new_bfqq; + if (new_bfqq) { + while (new_bfqq->new_bfqq) + new_bfqq = new_bfqq->new_bfqq; + return new_bfqq; + } /* * Check delayed stable merge for rotational or non-queueing @@ -3125,10 +3129,12 @@ void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq) bfq_put_queue(bfqq); } -static void -bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, - struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) +static struct bfq_queue *bfq_merge_bfqqs(struct bfq_data *bfqd, + struct bfq_io_cq *bic, + struct bfq_queue *bfqq) { + struct bfq_queue *new_bfqq = bfqq->new_bfqq; + bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu", (unsigned long)new_bfqq->pid); /* Save weight raising and idle window of the merged queues */ @@ -3222,6 +3228,8 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, bfq_reassign_last_bfqq(bfqq, new_bfqq); bfq_release_process_ref(bfqd, bfqq); + + return new_bfqq; } static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq, @@ -3257,14 +3265,8 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq, * fulfilled, i.e., bic can be redirected to new_bfqq * and bfqq can be put. */ - bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq, - new_bfqq); - /* - * If we get here, bio will be queued into new_queue, - * so use new_bfqq to decide whether bio and rq can be - * merged. - */ - bfqq = new_bfqq; + while (bfqq != new_bfqq) + bfqq = bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq); /* * Change also bqfd->bio_bfqq, as @@ -5699,9 +5701,7 @@ bfq_do_early_stable_merge(struct bfq_data *bfqd, struct bfq_queue *bfqq, * state before killing it. */ bfqq->bic = bic; - bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq); - - return new_bfqq; + return bfq_merge_bfqqs(bfqd, bic, bfqq); } /* @@ -6156,6 +6156,7 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq) bool waiting, idle_timer_disabled = false; if (new_bfqq) { + struct bfq_queue *old_bfqq = bfqq; /* * Release the request's reference to the old bfqq * and make sure one is taken to the shared queue. @@ -6172,18 +6173,18 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq) * new_bfqq. */ if (bic_to_bfqq(RQ_BIC(rq), true, - bfq_actuator_index(bfqd, rq->bio)) == bfqq) - bfq_merge_bfqqs(bfqd, RQ_BIC(rq), - bfqq, new_bfqq); + bfq_actuator_index(bfqd, rq->bio)) == bfqq) { + while (bfqq != new_bfqq) + bfqq = bfq_merge_bfqqs(bfqd, RQ_BIC(rq), bfqq); + } - bfq_clear_bfqq_just_created(bfqq); + bfq_clear_bfqq_just_created(old_bfqq); /* * rq is about to be enqueued into new_bfqq, * release rq reference on bfqq */ - bfq_put_queue(bfqq); + bfq_put_queue(old_bfqq); rq->elv.priv[1] = new_bfqq; - bfqq = new_bfqq; } bfq_update_io_thinktime(bfqd, bfqq); @@ -6721,7 +6722,7 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) { bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue"); - if (bfqq_process_refs(bfqq) == 1) { + if (bfqq_process_refs(bfqq) == 1 && !bfqq->new_bfqq) { bfqq->pid = current->pid; bfq_clear_bfqq_coop(bfqq); bfq_clear_bfqq_split_coop(bfqq); @@ -6819,6 +6820,31 @@ static void bfq_prepare_request(struct request *rq) rq->elv.priv[0] = rq->elv.priv[1] = NULL; } +static struct bfq_queue *bfq_waker_bfqq(struct bfq_queue *bfqq) +{ + struct bfq_queue *new_bfqq = bfqq->new_bfqq; + struct bfq_queue *waker_bfqq = bfqq->waker_bfqq; + + if (!waker_bfqq) + return NULL; + + while (new_bfqq) { + if (new_bfqq == waker_bfqq) { + /* + * If waker_bfqq is in the merge chain, and current + * is the only procress. + */ + if (bfqq_process_refs(waker_bfqq) == 1) + return NULL; + break; + } + + new_bfqq = new_bfqq->new_bfqq; + } + + return waker_bfqq; +} + /* * If needed, init rq, allocate bfq data structures associated with * rq, and increment reference counters in the destination bfq_queue @@ -6880,7 +6906,7 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) /* If the queue was seeky for too long, break it apart. */ if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq) && !bic->bfqq_data[a_idx].stably_merged) { - struct bfq_queue *old_bfqq = bfqq; + struct bfq_queue *waker_bfqq = bfq_waker_bfqq(bfqq); /* Update bic before losing reference to bfqq */ if (bfq_bfqq_in_large_burst(bfqq)) @@ -6900,7 +6926,7 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) bfqq_already_existing = true; if (!bfqq_already_existing) { - bfqq->waker_bfqq = old_bfqq->waker_bfqq; + bfqq->waker_bfqq = waker_bfqq; bfqq->tentative_waker_bfqq = NULL; /* @@ -6910,7 +6936,7 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) * woken_list of the waker. See * bfq_check_waker for details. */ - if (bfqq->waker_bfqq) + if (waker_bfqq) hlist_add_head(&bfqq->woken_list_node, &bfqq->waker_bfqq->woken_list); } @@ -6932,7 +6958,8 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) * addition, if the queue has also just been split, we have to * resume its state. */ - if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) { + if (likely(bfqq != &bfqd->oom_bfqq) && !bfqq->new_bfqq && + bfqq_process_refs(bfqq) == 1) { bfqq->bic = bic; if (split) { /* diff --git a/block/bio-integrity.c b/block/bio-integrity.c index ec8ac8cf6e1b98..15e444b2fcc123 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -217,6 +217,7 @@ bool bio_integrity_prep(struct bio *bio) unsigned long start, end; unsigned int len, nr_pages; unsigned int bytes, offset, i; + gfp_t gfp = GFP_NOIO; if (!bi) return true; @@ -239,11 +240,19 @@ bool bio_integrity_prep(struct bio *bio) if (!bi->profile->generate_fn || !(bi->flags & BLK_INTEGRITY_GENERATE)) return true; + + /* + * Zero the memory allocated to not leak uninitialized kernel + * memory to disk. For PI this only affects the app tag, but + * for non-integrity metadata it affects the entire metadata + * buffer. + */ + gfp |= __GFP_ZERO; } /* Allocate kernel buffer for protection data */ len = bio_integrity_bytes(bi, bio_sectors(bio)); - buf = kmalloc(len, GFP_NOIO); + buf = kmalloc(len, gfp); if (unlikely(buf == NULL)) { printk(KERN_ERR "could not allocate integrity buffer\n"); goto err_end_io; diff --git a/block/bio.c b/block/bio.c index 816d412c06e9b4..62419aa09d7319 100644 --- a/block/bio.c +++ b/block/bio.c @@ -944,7 +944,7 @@ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv, if ((addr1 | mask) != (addr2 | mask)) return false; - if (bv->bv_len + len > queue_max_segment_size(q)) + if (len > queue_max_segment_size(q) - bv->bv_len) return false; return bvec_try_merge_page(bv, page, len, offset, same_page); } @@ -1145,13 +1145,23 @@ EXPORT_SYMBOL(bio_add_folio); void __bio_release_pages(struct bio *bio, bool mark_dirty) { - struct bvec_iter_all iter_all; - struct bio_vec *bvec; + struct folio_iter fi; + + bio_for_each_folio_all(fi, bio) { + struct page *page; + size_t nr_pages; - bio_for_each_segment_all(bvec, bio, iter_all) { - if (mark_dirty && !PageCompound(bvec->bv_page)) - set_page_dirty_lock(bvec->bv_page); - bio_release_page(bio, bvec->bv_page); + if (mark_dirty) { + folio_lock(fi.folio); + folio_mark_dirty(fi.folio); + folio_unlock(fi.folio); + } + page = folio_page(fi.folio, fi.offset / PAGE_SIZE); + nr_pages = (fi.offset + fi.length - 1) / PAGE_SIZE - + fi.offset / PAGE_SIZE + 1; + do { + bio_release_page(bio, page++); + } while (--nr_pages != 0); } } EXPORT_SYMBOL_GPL(__bio_release_pages); @@ -1439,18 +1449,12 @@ EXPORT_SYMBOL(bio_free_pages); * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions * for performing direct-IO in BIOs. * - * The problem is that we cannot run set_page_dirty() from interrupt context + * The problem is that we cannot run folio_mark_dirty() from interrupt context * because the required locks are not interrupt-safe. So what we can do is to * mark the pages dirty _before_ performing IO. And in interrupt context, * check that the pages are still dirty. If so, fine. If not, redirty them * in process context. * - * We special-case compound pages here: normally this means reads into hugetlb - * pages. The logic in here doesn't really work right for compound pages - * because the VM does not uniformly chase down the head page in all cases. - * But dirtiness of compound pages is pretty meaningless anyway: the VM doesn't - * handle them at all. So we skip compound pages here at an early stage. - * * Note that this code is very hard to test under normal circumstances because * direct-io pins the pages with get_user_pages(). This makes * is_page_cache_freeable return false, and the VM will not clean the pages. @@ -1466,12 +1470,12 @@ EXPORT_SYMBOL(bio_free_pages); */ void bio_set_pages_dirty(struct bio *bio) { - struct bio_vec *bvec; - struct bvec_iter_all iter_all; + struct folio_iter fi; - bio_for_each_segment_all(bvec, bio, iter_all) { - if (!PageCompound(bvec->bv_page)) - set_page_dirty_lock(bvec->bv_page); + bio_for_each_folio_all(fi, bio) { + folio_lock(fi.folio); + folio_mark_dirty(fi.folio); + folio_unlock(fi.folio); } } EXPORT_SYMBOL_GPL(bio_set_pages_dirty); @@ -1515,12 +1519,11 @@ static void bio_dirty_fn(struct work_struct *work) void bio_check_pages_dirty(struct bio *bio) { - struct bio_vec *bvec; + struct folio_iter fi; unsigned long flags; - struct bvec_iter_all iter_all; - bio_for_each_segment_all(bvec, bio, iter_all) { - if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page)) + bio_for_each_folio_all(fi, bio) { + if (!folio_test_dirty(fi.folio)) goto defer; } diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 4a42ea2972ad85..4fb045d26bd5ad 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -323,6 +323,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk, blkg->q = disk->queue; INIT_LIST_HEAD(&blkg->q_node); blkg->blkcg = blkcg; + blkg->iostat.blkg = blkg; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO spin_lock_init(&blkg->async_bio_lock); bio_list_init(&blkg->async_bios); @@ -577,6 +578,7 @@ static void blkg_destroy_all(struct gendisk *disk) struct request_queue *q = disk->queue; struct blkcg_gq *blkg, *n; int count = BLKG_DESTROY_BATCH_SIZE; + int i; restart: spin_lock_irq(&q->queue_lock); @@ -602,16 +604,61 @@ static void blkg_destroy_all(struct gendisk *disk) } } + /* + * Mark policy deactivated since policy offline has been done, and + * the free is scheduled, so future blkcg_deactivate_policy() can + * be bypassed + */ + for (i = 0; i < BLKCG_MAX_POLS; i++) { + struct blkcg_policy *pol = blkcg_policy[i]; + + if (pol) + __clear_bit(pol->plid, q->blkcg_pols); + } + q->root_blkg = NULL; spin_unlock_irq(&q->queue_lock); } +static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] = src->bytes[i]; + dst->ios[i] = src->ios[i]; + } +} + +static void __blkg_clear_stat(struct blkg_iostat_set *bis) +{ + struct blkg_iostat cur = {0}; + unsigned long flags; + + flags = u64_stats_update_begin_irqsave(&bis->sync); + blkg_iostat_set(&bis->cur, &cur); + blkg_iostat_set(&bis->last, &cur); + u64_stats_update_end_irqrestore(&bis->sync, flags); +} + +static void blkg_clear_stat(struct blkcg_gq *blkg) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct blkg_iostat_set *s = per_cpu_ptr(blkg->iostat_cpu, cpu); + + __blkg_clear_stat(s); + } + __blkg_clear_stat(&blkg->iostat); +} + static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; - int i, cpu; + int i; mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); @@ -622,18 +669,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { - for_each_possible_cpu(cpu) { - struct blkg_iostat_set *bis = - per_cpu_ptr(blkg->iostat_cpu, cpu); - memset(bis, 0, sizeof(*bis)); - - /* Re-initialize the cleared blkg_iostat_set */ - u64_stats_init(&bis->sync); - bis->blkg = blkg; - } - memset(&blkg->iostat, 0, sizeof(blkg->iostat)); - u64_stats_init(&blkg->iostat.sync); - + blkg_clear_stat(blkg); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; @@ -936,16 +972,6 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx) } EXPORT_SYMBOL_GPL(blkg_conf_exit); -static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) -{ - int i; - - for (i = 0; i < BLKG_IOSTAT_NR; i++) { - dst->bytes[i] = src->bytes[i]; - dst->ios[i] = src->ios[i]; - } -} - static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; @@ -1011,7 +1037,19 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) struct blkg_iostat cur; unsigned int seq; + /* + * Order assignment of `next_bisc` from `bisc->lnode.next` in + * llist_for_each_entry_safe and clearing `bisc->lqueued` for + * avoiding to assign `next_bisc` with new next pointer added + * in blk_cgroup_bio_start() in case of re-ordering. + * + * The pair barrier is implied in llist_add() in blk_cgroup_bio_start(). + */ + smp_mb(); + WRITE_ONCE(bisc->lqueued, false); + if (bisc == &blkg->iostat) + goto propagate_up; /* propagate up to parent only */ /* fetch the current per-cpu values */ do { @@ -1021,10 +1059,24 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) blkcg_iostat_update(blkg, &cur, &bisc->last); +propagate_up: /* propagate global delta to parent (unless that's root) */ - if (parent && parent->parent) + if (parent && parent->parent) { blkcg_iostat_update(parent, &blkg->iostat.cur, &blkg->iostat.last); + /* + * Queue parent->iostat to its blkcg's lockless + * list to propagate up to the grandparent if the + * iostat hasn't been queued yet. + */ + if (!parent->iostat.lqueued) { + struct llist_head *plhead; + + plhead = per_cpu_ptr(parent->blkcg->lhead, cpu); + llist_add(&parent->iostat.lnode, plhead); + parent->iostat.lqueued = true; + } + } } raw_spin_unlock_irqrestore(&blkg_stat_lock, flags); out: @@ -1396,6 +1448,12 @@ static int blkcg_css_online(struct cgroup_subsys_state *css) return 0; } +void blkg_init_queue(struct request_queue *q) +{ + INIT_LIST_HEAD(&q->blkg_list); + mutex_init(&q->blkcg_mutex); +} + int blkcg_init_disk(struct gendisk *disk) { struct request_queue *q = disk->queue; @@ -1403,9 +1461,6 @@ int blkcg_init_disk(struct gendisk *disk) bool preloaded; int ret; - INIT_LIST_HEAD(&q->blkg_list); - mutex_init(&q->blkcg_mutex); - new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL); if (!new_blkg) return -ENOMEM; diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 624c03c8fe64e3..5b0bdc268ade9f 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -188,6 +188,7 @@ struct blkcg_policy { extern struct blkcg blkcg_root; extern bool blkcg_debug_stats; +void blkg_init_queue(struct request_queue *q); int blkcg_init_disk(struct gendisk *disk); void blkcg_exit_disk(struct gendisk *disk); @@ -249,12 +250,11 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, { struct blkcg_gq *blkg; - WARN_ON_ONCE(!rcu_read_lock_held()); - if (blkcg == &blkcg_root) return q->root_blkg; - blkg = rcu_dereference(blkcg->blkg_hint); + blkg = rcu_dereference_check(blkcg->blkg_hint, + lockdep_is_held(&q->queue_lock)); if (blkg && blkg->q == q) return blkg; @@ -482,6 +482,7 @@ struct blkcg { }; static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } +static inline void blkg_init_queue(struct request_queue *q) { } static inline int blkcg_init_disk(struct gendisk *disk) { return 0; } static inline void blkcg_exit_disk(struct gendisk *disk) { } static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } diff --git a/block/blk-core.c b/block/blk-core.c index 9d51e9894ece78..4f25d2c4bc7055 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -49,6 +49,7 @@ #include "blk-pm.h" #include "blk-cgroup.h" #include "blk-throttle.h" +#include "blk-ioprio.h" struct dentry *blk_debugfs_root; @@ -430,6 +431,8 @@ struct request_queue *blk_alloc_queue(int node_id) init_waitqueue_head(&q->mq_freeze_wq); mutex_init(&q->mq_freeze_lock); + blkg_init_queue(q); + /* * Init percpu_ref in atomic mode so that it's faster to shutdown. * See blk_register_queue() for details. @@ -501,9 +504,17 @@ static inline void bio_check_ro(struct bio *bio) if (op_is_write(bio_op(bio)) && bdev_read_only(bio->bi_bdev)) { if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return; + + if (bio->bi_bdev->bd_ro_warned) + return; + + bio->bi_bdev->bd_ro_warned = true; + /* + * Use ioctl to set underlying disk of raid/dm to read-only + * will trigger this. + */ pr_warn("Trying to write to read-only block-device %pg\n", bio->bi_bdev); - /* Older lvm-tools actually trigger this */ } } @@ -809,6 +820,14 @@ void submit_bio_noacct(struct bio *bio) } EXPORT_SYMBOL(submit_bio_noacct); +static void bio_set_ioprio(struct bio *bio) +{ + /* Nobody set ioprio so far? Initialize it based on task's nice value */ + if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE) + bio->bi_ioprio = get_current_ioprio(); + blkcg_set_ioprio(bio); +} + /** * submit_bio - submit a bio to the block device layer for I/O * @bio: The &struct bio which describes the I/O @@ -831,6 +850,7 @@ void submit_bio(struct bio *bio) count_vm_events(PGPGOUT, bio_sectors(bio)); } + bio_set_ioprio(bio); submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio); @@ -940,10 +960,11 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end) unsigned long stamp; again: stamp = READ_ONCE(part->bd_stamp); - if (unlikely(time_after(now, stamp))) { - if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now))) - __part_stat_add(part, io_ticks, end ? now - stamp : 1); - } + if (unlikely(time_after(now, stamp)) && + likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) && + (end || part_in_flight(part))) + __part_stat_add(part, io_ticks, now - stamp); + if (part->bd_partno) { part = bdev_whole(part); goto again; diff --git a/block/blk-flush.c b/block/blk-flush.c index e73dc22d05c1d1..313f0ffcce42e7 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -183,7 +183,7 @@ static void blk_flush_complete_seq(struct request *rq, /* queue for flush */ if (list_empty(pending)) fq->flush_pending_since = jiffies; - list_move_tail(&rq->queuelist, pending); + list_add_tail(&rq->queuelist, pending); break; case REQ_FSEQ_DATA: @@ -261,6 +261,7 @@ static enum rq_end_io_ret flush_end_io(struct request *flush_rq, unsigned int seq = blk_flush_cur_seq(rq); BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH); + list_del_init(&rq->queuelist); blk_flush_complete_seq(rq, fq, seq, error); } diff --git a/block/blk-integrity.c b/block/blk-integrity.c index d4e9b4556d14b2..5276c556a9df91 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -396,8 +396,6 @@ void blk_integrity_unregister(struct gendisk *disk) if (!bi->profile) return; - /* ensure all bios are off the integrity workqueue */ - blk_flush_integrity(); blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue); memset(bi, 0, sizeof(*bi)); } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 089fcb9cfce370..c3cb9c20b306cf 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1347,16 +1347,24 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); - u64 tdelta, delay, new_delay; + u64 tdelta, delay, new_delay, shift; s64 vover, vover_pct; u32 hwa; lockdep_assert_held(&iocg->waitq.lock); + /* + * If the delay is set by another CPU, we may be in the past. No need to + * change anything if so. This avoids decay calculation underflow. + */ + if (time_before64(now->now, iocg->delay_at)) + return false; + /* calculate the current delay in effect - 1/2 every second */ tdelta = now->now - iocg->delay_at; - if (iocg->delay) - delay = iocg->delay >> div64_u64(tdelta, USEC_PER_SEC); + shift = div64_u64(tdelta, USEC_PER_SEC); + if (iocg->delay && shift < BITS_PER_LONG) + delay = iocg->delay >> shift; else delay = 0; @@ -1431,8 +1439,11 @@ static void iocg_pay_debt(struct ioc_gq *iocg, u64 abs_vpay, lockdep_assert_held(&iocg->ioc->lock); lockdep_assert_held(&iocg->waitq.lock); - /* make sure that nobody messed with @iocg */ - WARN_ON_ONCE(list_empty(&iocg->active_list)); + /* + * make sure that nobody messed with @iocg. Check iocg->pd.online + * to avoid warn when removing blkcg or disk. + */ + WARN_ON_ONCE(list_empty(&iocg->active_list) && iocg->pd.online); WARN_ON_ONCE(iocg->inuse > 1); iocg->abs_vdebt -= min(abs_vpay, iocg->abs_vdebt); @@ -2065,7 +2076,7 @@ static void ioc_forgive_debts(struct ioc *ioc, u64 usage_us_sum, int nr_debtors, struct ioc_now *now) { struct ioc_gq *iocg; - u64 dur, usage_pct, nr_cycles; + u64 dur, usage_pct, nr_cycles, nr_cycles_shift; /* if no debtor, reset the cycle */ if (!nr_debtors) { @@ -2127,10 +2138,12 @@ static void ioc_forgive_debts(struct ioc *ioc, u64 usage_us_sum, int nr_debtors, old_debt = iocg->abs_vdebt; old_delay = iocg->delay; + nr_cycles_shift = min_t(u64, nr_cycles, BITS_PER_LONG - 1); if (iocg->abs_vdebt) - iocg->abs_vdebt = iocg->abs_vdebt >> nr_cycles ?: 1; + iocg->abs_vdebt = iocg->abs_vdebt >> nr_cycles_shift ?: 1; + if (iocg->delay) - iocg->delay = iocg->delay >> nr_cycles ?: 1; + iocg->delay = iocg->delay >> nr_cycles_shift ?: 1; iocg_kick_waitq(iocg, true, now); diff --git a/block/blk-map.c b/block/blk-map.c index 8584babf3ea0ca..71210cdb34426d 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -205,12 +205,19 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, /* * success */ - if ((iov_iter_rw(iter) == WRITE && - (!map_data || !map_data->null_mapped)) || - (map_data && map_data->from_user)) { + if (iov_iter_rw(iter) == WRITE && + (!map_data || !map_data->null_mapped)) { ret = bio_copy_from_iter(bio, iter); if (ret) goto cleanup; + } else if (map_data && map_data->from_user) { + struct iov_iter iter2 = *iter; + + /* This is the copy-in part of SG_DXFER_TO_FROM_DEV. */ + iter2.data_source = ITER_SOURCE; + ret = bio_copy_from_iter(bio, &iter2); + if (ret) + goto cleanup; } else { if (bmd->is_our_pages) zero_fill_bio(bio); diff --git a/block/blk-merge.c b/block/blk-merge.c index 65e75efa9bd366..07bf758c523a9c 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -783,6 +783,8 @@ static void blk_account_io_merge_request(struct request *req) if (blk_do_io_stat(req)) { part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); + part_stat_local_dec(req->part, + in_flight[op_is_write(req_op(req))]); part_stat_unlock(); } } diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index cc57e2dd9a0bb3..2cafcf11ee8bee 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -38,6 +38,7 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags, void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { unsigned int users; + unsigned long flags; struct blk_mq_tags *tags = hctx->tags; /* @@ -56,11 +57,11 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) return; } - spin_lock_irq(&tags->lock); + spin_lock_irqsave(&tags->lock, flags); users = tags->active_queues + 1; WRITE_ONCE(tags->active_queues, users); blk_mq_update_wake_batch(tags, users); - spin_unlock_irq(&tags->lock); + spin_unlock_irqrestore(&tags->lock, flags); } /* diff --git a/block/blk-mq.c b/block/blk-mq.c index 1fafd54dce3cb9..733d72f4d1cc9d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -40,7 +40,6 @@ #include "blk-stat.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" -#include "blk-ioprio.h" static DEFINE_PER_CPU(struct llist_head, blk_cpu_done); static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd); @@ -447,6 +446,10 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) if (data->cmd_flags & REQ_NOWAIT) data->flags |= BLK_MQ_REQ_NOWAIT; +retry: + data->ctx = blk_mq_get_ctx(q); + data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx); + if (q->elevator) { /* * All requests use scheduler tags when an I/O scheduler is @@ -468,13 +471,9 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) if (ops->limit_depth) ops->limit_depth(data->cmd_flags, data); } - } - -retry: - data->ctx = blk_mq_get_ctx(q); - data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx); - if (!(data->rq_flags & RQF_SCHED_TAGS)) + } else { blk_mq_tag_busy(data->hctx); + } if (data->flags & BLK_MQ_REQ_RESERVED) data->rq_flags |= RQF_RESV; @@ -994,6 +993,8 @@ static inline void blk_account_io_done(struct request *req, u64 now) update_io_ticks(req->part, jiffies, true); part_stat_inc(req->part, ios[sgrp]); part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns); + part_stat_local_dec(req->part, + in_flight[op_is_write(req_op(req))]); part_stat_unlock(); } } @@ -1016,6 +1017,8 @@ static inline void blk_account_io_start(struct request *req) part_stat_lock(); update_io_ticks(req->part, jiffies, false); + part_stat_local_inc(req->part, + in_flight[op_is_write(req_op(req))]); part_stat_unlock(); } } @@ -1511,14 +1514,26 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q, } EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list); +static bool blk_is_flush_data_rq(struct request *rq) +{ + return (rq->rq_flags & RQF_FLUSH_SEQ) && !is_flush_rq(rq); +} + static bool blk_mq_rq_inflight(struct request *rq, void *priv) { /* * If we find a request that isn't idle we know the queue is busy * as it's checked in the iter. * Return false to stop the iteration. + * + * In case of queue quiesce, if one flush data request is completed, + * don't count it as inflight given the flush sequence is suspended, + * and the original flush data request is invisible to driver, just + * like other pending requests because of quiesce */ - if (blk_mq_request_started(rq)) { + if (blk_mq_request_started(rq) && !(blk_queue_quiesced(rq->q) && + blk_is_flush_data_rq(rq) && + blk_mq_request_completed(rq))) { bool *busy = priv; *busy = true; @@ -1858,6 +1873,22 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, wait->flags &= ~WQ_FLAG_EXCLUSIVE; __add_wait_queue(wq, wait); + /* + * Add one explicit barrier since blk_mq_get_driver_tag() may + * not imply barrier in case of failure. + * + * Order adding us to wait queue and allocating driver tag. + * + * The pair is the one implied in sbitmap_queue_wake_up() which + * orders clearing sbitmap tag bits and waitqueue_active() in + * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless + * + * Otherwise, re-order of adding wait queue and getting driver tag + * may cause __sbitmap_queue_wake_up() to wake up nothing because + * the waitqueue_active() may not observe us in wait queue. + */ + smp_mb(); + /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait @@ -2875,11 +2906,8 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, }; struct request *rq; - if (unlikely(bio_queue_enter(bio))) - return NULL; - if (blk_mq_attempt_bio_merge(q, bio, nsegs)) - goto queue_exit; + return NULL; rq_qos_throttle(q, bio); @@ -2895,35 +2923,23 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, rq_qos_cleanup(q, bio); if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); -queue_exit: - blk_queue_exit(q); return NULL; } -static inline struct request *blk_mq_get_cached_request(struct request_queue *q, - struct blk_plug *plug, struct bio **bio, unsigned int nsegs) +/* return true if this @rq can be used for @bio */ +static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug, + struct bio *bio) { - struct request *rq; - enum hctx_type type, hctx_type; - - if (!plug) - return NULL; - rq = rq_list_peek(&plug->cached_rq); - if (!rq || rq->q != q) - return NULL; + enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf); + enum hctx_type hctx_type = rq->mq_hctx->type; - if (blk_mq_attempt_bio_merge(q, *bio, nsegs)) { - *bio = NULL; - return NULL; - } + WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq); - type = blk_mq_get_hctx_type((*bio)->bi_opf); - hctx_type = rq->mq_hctx->type; if (type != hctx_type && !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT)) - return NULL; - if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf)) - return NULL; + return false; + if (op_is_flush(rq->cmd_flags) != op_is_flush(bio->bi_opf)) + return false; /* * If any qos ->throttle() end up blocking, we will have flushed the @@ -2931,20 +2947,12 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q, * before we throttle. */ plug->cached_rq = rq_list_next(rq); - rq_qos_throttle(q, *bio); + rq_qos_throttle(rq->q, bio); blk_mq_rq_time_init(rq, 0); - rq->cmd_flags = (*bio)->bi_opf; + rq->cmd_flags = bio->bi_opf; INIT_LIST_HEAD(&rq->queuelist); - return rq; -} - -static void bio_set_ioprio(struct bio *bio) -{ - /* Nobody set ioprio so far? Initialize it based on task's nice value */ - if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE) - bio->bi_ioprio = get_current_ioprio(); - blkcg_set_ioprio(bio); + return true; } /** @@ -2966,31 +2974,50 @@ void blk_mq_submit_bio(struct bio *bio) struct blk_plug *plug = blk_mq_plug(bio); const int is_sync = op_is_sync(bio->bi_opf); struct blk_mq_hw_ctx *hctx; - struct request *rq; + struct request *rq = NULL; unsigned int nr_segs = 1; blk_status_t ret; bio = blk_queue_bounce(bio, q); - if (bio_may_exceed_limits(bio, &q->limits)) { - bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); - if (!bio) + + if (plug) { + rq = rq_list_peek(&plug->cached_rq); + if (rq && rq->q != q) + rq = NULL; + } + if (rq) { + if (unlikely(bio_may_exceed_limits(bio, &q->limits))) { + bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); + if (!bio) + return; + } + if (!bio_integrity_prep(bio)) + return; + if (blk_mq_attempt_bio_merge(q, bio, nr_segs)) + return; + if (blk_mq_can_use_cached_rq(rq, plug, bio)) + goto done; + percpu_ref_get(&q->q_usage_counter); + } else { + if (unlikely(bio_queue_enter(bio))) return; + if (unlikely(bio_may_exceed_limits(bio, &q->limits))) { + bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); + if (!bio) + goto fail; + } + if (!bio_integrity_prep(bio)) + goto fail; } - if (!bio_integrity_prep(bio)) + rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); + if (unlikely(!rq)) { +fail: + blk_queue_exit(q); return; - - bio_set_ioprio(bio); - - rq = blk_mq_get_cached_request(q, plug, &bio, nr_segs); - if (!rq) { - if (!bio) - return; - rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); - if (unlikely(!rq)) - return; } +done: trace_block_getrq(bio); rq_qos_track(q, rq, bio); diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index dd7310c94713c9..dc510f493ba572 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -219,8 +219,8 @@ static int rq_qos_wake_function(struct wait_queue_entry *curr, data->got_token = true; smp_wmb(); - list_del_init(&curr->entry); wake_up_process(data->task); + list_del_init_careful(&curr->entry); return 1; } diff --git a/block/blk-settings.c b/block/blk-settings.c index 0046b447268f91..7019b8e204d965 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -686,6 +686,10 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->zone_write_granularity = max(t->zone_write_granularity, b->zone_write_granularity); t->zoned = max(t->zoned, b->zoned); + if (!t->zoned) { + t->zone_write_granularity = 0; + t->max_zone_append_sectors = 0; + } return ret; } EXPORT_SYMBOL(blk_stack_limits); diff --git a/block/blk-stat.c b/block/blk-stat.c index 7ff76ae6c76a95..e42c263e53fb99 100644 --- a/block/blk-stat.c +++ b/block/blk-stat.c @@ -27,7 +27,7 @@ void blk_rq_stat_init(struct blk_rq_stat *stat) /* src is a per-cpu stat, mean isn't initialized */ void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src) { - if (!src->nr_samples) + if (dst->nr_samples + src->nr_samples <= dst->nr_samples) return; dst->min = min(dst->min, src->min); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 13e4377a8b2865..16f5766620a410 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1320,6 +1320,7 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global) tg_bps_limit(tg, READ), tg_bps_limit(tg, WRITE), tg_iops_limit(tg, READ), tg_iops_limit(tg, WRITE)); + rcu_read_lock(); /* * Update has_rules[] flags for the updated tg's subtree. A tg is * considered to have rules if either the tg itself or any of its @@ -1347,6 +1348,7 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global) this_tg->latency_target = max(this_tg->latency_target, parent_tg->latency_target); } + rcu_read_unlock(); /* * We're already holding queue_lock and know @tg is valid. Let's diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 0bb613139becbb..f8fda9cf583e1c 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -165,9 +165,9 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var) */ static bool wb_recent_wait(struct rq_wb *rwb) { - struct bdi_writeback *wb = &rwb->rqos.disk->bdi->wb; + struct backing_dev_info *bdi = rwb->rqos.disk->bdi; - return time_before(jiffies, wb->dirty_sleep + HZ); + return time_before(jiffies, bdi->last_bdp_sleep + HZ); } static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb, diff --git a/block/blk.h b/block/blk.h index 08a358bc0919e2..67915b04b3c179 100644 --- a/block/blk.h +++ b/block/blk.h @@ -344,6 +344,7 @@ static inline bool blk_do_io_stat(struct request *rq) } void update_io_ticks(struct block_device *part, unsigned long now, bool end); +unsigned int part_in_flight(struct block_device *part); static inline void req_set_nomerge(struct request_queue *q, struct request *req) { diff --git a/block/fops.c b/block/fops.c index 73e42742543f6a..1df187b3067920 100644 --- a/block/fops.c +++ b/block/fops.c @@ -387,7 +387,7 @@ static int blkdev_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->bdev = bdev; iomap->offset = ALIGN_DOWN(offset, bdev_logical_block_size(bdev)); - if (iomap->offset >= isize) + if (offset >= isize) return -EIO; iomap->type = IOMAP_MAPPED; iomap->addr = iomap->offset; diff --git a/block/genhd.c b/block/genhd.c index cc32a0c704eb84..203c880c3e1cd2 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -118,7 +118,7 @@ static void part_stat_read_all(struct block_device *part, } } -static unsigned int part_in_flight(struct block_device *part) +unsigned int part_in_flight(struct block_device *part) { unsigned int inflight = 0; int cpu; @@ -345,9 +345,7 @@ int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode) struct block_device *bdev; int ret = 0; - if (disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN)) - return -EINVAL; - if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state)) + if (!disk_has_partscan(disk)) return -EINVAL; if (disk->open_partitions) return -EBUSY; @@ -432,7 +430,9 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, DISK_MAX_PARTS); disk->minors = DISK_MAX_PARTS; } - if (disk->first_minor + disk->minors > MINORMASK + 1) + if (disk->first_minor > MINORMASK || + disk->minors > MINORMASK + 1 || + disk->first_minor + disk->minors > MINORMASK + 1) goto out_exit_elevator; } else { if (WARN_ON(disk->minors)) @@ -501,8 +501,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, goto out_unregister_bdi; /* Make sure the first partition scan will be proceed */ - if (get_capacity(disk) && !(disk->flags & GENHD_FL_NO_PART) && - !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state)) + if (get_capacity(disk) && disk_has_partscan(disk)) set_bit(GD_NEED_PART_SCAN, &disk->state); bdev_add(disk->part0, ddev->devt); @@ -542,6 +541,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, kobject_put(disk->part0->bd_holder_dir); out_del_block_link: sysfs_remove_link(block_depr, dev_name(ddev)); + pm_runtime_set_memalloc_noio(ddev, false); out_device_del: device_del(ddev); out_free_ext_minor: @@ -655,12 +655,12 @@ void del_gendisk(struct gendisk *disk) */ if (!test_bit(GD_DEAD, &disk->state)) blk_report_disk_dead(disk, false); - __blk_mark_disk_dead(disk); /* * Drop all partitions now that the disk is marked dead. */ mutex_lock(&disk->open_mutex); + __blk_mark_disk_dead(disk); xa_for_each_start(&disk->part_tbl, idx, part, 1) drop_partition(part); mutex_unlock(&disk->open_mutex); @@ -1037,6 +1037,12 @@ static ssize_t diskseq_show(struct device *dev, return sprintf(buf, "%llu\n", disk->diskseq); } +static ssize_t partscan_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", disk_has_partscan(dev_to_disk(dev))); +} + static DEVICE_ATTR(range, 0444, disk_range_show, NULL); static DEVICE_ATTR(ext_range, 0444, disk_ext_range_show, NULL); static DEVICE_ATTR(removable, 0444, disk_removable_show, NULL); @@ -1050,6 +1056,7 @@ static DEVICE_ATTR(stat, 0444, part_stat_show, NULL); static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL); static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store); static DEVICE_ATTR(diskseq, 0444, diskseq_show, NULL); +static DEVICE_ATTR(partscan, 0444, partscan_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST ssize_t part_fail_show(struct device *dev, @@ -1096,6 +1103,7 @@ static struct attribute *disk_attrs[] = { &dev_attr_events_async.attr, &dev_attr_events_poll_msecs.attr, &dev_attr_diskseq.attr, + &dev_attr_partscan.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif diff --git a/block/ioctl.c b/block/ioctl.c index d5f5cd61efd7fc..3786033342848d 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -18,10 +18,8 @@ static int blkpg_do_ioctl(struct block_device *bdev, { struct gendisk *disk = bdev->bd_disk; struct blkpg_partition p; - long long start, length; + sector_t start, length; - if (disk->flags & GENHD_FL_NO_PART) - return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (copy_from_user(&p, upart, sizeof(struct blkpg_partition))) @@ -35,14 +33,17 @@ static int blkpg_do_ioctl(struct block_device *bdev, if (op == BLKPG_DEL_PARTITION) return bdev_del_partition(disk, p.pno); + if (p.start < 0 || p.length <= 0 || LLONG_MAX - p.length < p.start) + return -EINVAL; + /* Check that the partition is aligned to the block size */ + if (!IS_ALIGNED(p.start | p.length, bdev_logical_block_size(bdev))) + return -EINVAL; + start = p.start >> SECTOR_SHIFT; length = p.length >> SECTOR_SHIFT; switch (op) { case BLKPG_ADD_PARTITION: - /* check if partition is aligned to blocksize */ - if (p.start & (bdev_logical_block_size(bdev) - 1)) - return -EINVAL; return bdev_add_partition(disk, p.pno, start, length); case BLKPG_RESIZE_PARTITION: return bdev_resize_partition(disk, p.pno, start, length); @@ -88,7 +89,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, unsigned long arg) { uint64_t range[2]; - uint64_t start, len; + uint64_t start, len, end; struct inode *inode = bdev->bd_inode; int err; @@ -109,7 +110,8 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, if (len & 511) return -EINVAL; - if (start + len > bdev_nr_bytes(bdev)) + if (check_add_overflow(start, len, &end) || + end > bdev_nr_bytes(bdev)) return -EINVAL; filemap_invalidate_lock(inode->i_mapping); diff --git a/block/mq-deadline.c b/block/mq-deadline.c index f958e79277b8bc..78a8aa204c1565 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -621,6 +621,20 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx) return rq; } +/* + * 'depth' is a number in the range 1..INT_MAX representing a number of + * requests. Scale it with a factor (1 << bt->sb.shift) / q->nr_requests since + * 1..(1 << bt->sb.shift) is the range expected by sbitmap_get_shallow(). + * Values larger than q->nr_requests have the same effect as q->nr_requests. + */ +static int dd_to_word_depth(struct blk_mq_hw_ctx *hctx, unsigned int qdepth) +{ + struct sbitmap_queue *bt = &hctx->sched_tags->bitmap_tags; + const unsigned int nrr = hctx->queue->nr_requests; + + return ((qdepth << bt->sb.shift) + nrr - 1) / nrr; +} + /* * Called by __blk_mq_alloc_request(). The shallow_depth value set by this * function is used by __blk_mq_get_tag(). @@ -637,7 +651,7 @@ static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) * Throttle asynchronous requests and writes such that these requests * do not block the allocation of synchronous requests. */ - data->shallow_depth = dd->async_depth; + data->shallow_depth = dd_to_word_depth(data->hctx, dd->async_depth); } /* Called by blk_mq_update_nr_requests(). */ @@ -646,11 +660,10 @@ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx) struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; struct blk_mq_tags *tags = hctx->sched_tags; - unsigned int shift = tags->bitmap_tags.sb.shift; - dd->async_depth = max(1U, 3 * (1U << shift) / 4); + dd->async_depth = q->nr_requests; - sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, dd->async_depth); + sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, 1); } /* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */ diff --git a/block/opal_proto.h b/block/opal_proto.h index dec7ce3a3edb70..d247a457bf6e3f 100644 --- a/block/opal_proto.h +++ b/block/opal_proto.h @@ -71,6 +71,7 @@ enum opal_response_token { #define SHORT_ATOM_BYTE 0xBF #define MEDIUM_ATOM_BYTE 0xDF #define LONG_ATOM_BYTE 0xE3 +#define EMPTY_ATOM_BYTE 0xFF #define OPAL_INVAL_PARAM 12 #define OPAL_MANUFACTURED_INACTIVE 0x08 diff --git a/block/partitions/cmdline.c b/block/partitions/cmdline.c index c03bc105e57539..152c85df92b20e 100644 --- a/block/partitions/cmdline.c +++ b/block/partitions/cmdline.c @@ -70,8 +70,8 @@ static int parse_subpart(struct cmdline_subpart **subpart, char *partdef) } if (*partdef == '(') { - int length; - char *next = strchr(++partdef, ')'); + partdef++; + char *next = strsep(&partdef, ")"); if (!next) { pr_warn("cmdline partition format is invalid."); @@ -79,11 +79,7 @@ static int parse_subpart(struct cmdline_subpart **subpart, char *partdef) goto fail; } - length = min_t(int, next - partdef, - sizeof(new_subpart->name) - 1); - strscpy(new_subpart->name, partdef, length); - - partdef = ++next; + strscpy(new_subpart->name, next, sizeof(new_subpart->name)); } else new_subpart->name[0] = '\0'; @@ -117,14 +113,12 @@ static void free_subpart(struct cmdline_parts *parts) } } -static int parse_parts(struct cmdline_parts **parts, const char *bdevdef) +static int parse_parts(struct cmdline_parts **parts, char *bdevdef) { int ret = -EINVAL; char *next; - int length; struct cmdline_subpart **next_subpart; struct cmdline_parts *newparts; - char buf[BDEVNAME_SIZE + 32 + 4]; *parts = NULL; @@ -132,28 +126,19 @@ static int parse_parts(struct cmdline_parts **parts, const char *bdevdef) if (!newparts) return -ENOMEM; - next = strchr(bdevdef, ':'); + next = strsep(&bdevdef, ":"); if (!next) { pr_warn("cmdline partition has no block device."); goto fail; } - length = min_t(int, next - bdevdef, sizeof(newparts->name) - 1); - strscpy(newparts->name, bdevdef, length); + strscpy(newparts->name, next, sizeof(newparts->name)); newparts->nr_subparts = 0; next_subpart = &newparts->subpart; - while (next && *(++next)) { - bdevdef = next; - next = strchr(bdevdef, ','); - - length = (!next) ? (sizeof(buf) - 1) : - min_t(int, next - bdevdef, sizeof(buf) - 1); - - strscpy(buf, bdevdef, length); - - ret = parse_subpart(next_subpart, buf); + while ((next = strsep(&bdevdef, ","))) { + ret = parse_subpart(next_subpart, next); if (ret) goto fail; @@ -199,24 +184,17 @@ static int cmdline_parts_parse(struct cmdline_parts **parts, *parts = NULL; - next = pbuf = buf = kstrdup(cmdline, GFP_KERNEL); + pbuf = buf = kstrdup(cmdline, GFP_KERNEL); if (!buf) return -ENOMEM; next_parts = parts; - while (next && *pbuf) { - next = strchr(pbuf, ';'); - if (next) - *next = '\0'; - - ret = parse_parts(next_parts, pbuf); + while ((next = strsep(&pbuf, ";"))) { + ret = parse_parts(next_parts, next); if (ret) goto fail; - if (next) - pbuf = ++next; - next_parts = &(*next_parts)->next_parts; } @@ -250,7 +228,6 @@ static struct cmdline_parts *bdev_parts; static int add_part(int slot, struct cmdline_subpart *subpart, struct parsed_partitions *state) { - int label_min; struct partition_meta_info *info; char tmp[sizeof(info->volname) + 4]; @@ -262,9 +239,7 @@ static int add_part(int slot, struct cmdline_subpart *subpart, info = &state->parts[slot].info; - label_min = min_t(int, sizeof(info->volname) - 1, - sizeof(subpart->name)); - strscpy(info->volname, subpart->name, label_min); + strscpy(info->volname, subpart->name, sizeof(info->volname)); snprintf(tmp, sizeof(tmp), "(%s)", info->volname); strlcat(state->pp_buf, tmp, PAGE_SIZE); diff --git a/block/partitions/core.c b/block/partitions/core.c index e137a87f4db0d3..fc0ab5d8ab705b 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -458,6 +458,11 @@ int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, goto out; } + if (disk->flags & GENHD_FL_NO_PART) { + ret = -EINVAL; + goto out; + } + if (partition_overlaps(disk, start, length, -1)) { ret = -EBUSY; goto out; @@ -569,9 +574,11 @@ static bool blk_add_partition(struct gendisk *disk, part = add_partition(disk, p, from, size, state->parts[p].flags, &state->parts[p].info); - if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) { - printk(KERN_ERR " %s: p%d could not be added: %ld\n", - disk->disk_name, p, -PTR_ERR(part)); + if (IS_ERR(part)) { + if (PTR_ERR(part) != -ENXIO) { + printk(KERN_ERR " %s: p%d could not be added: %pe\n", + disk->disk_name, p, part); + } return true; } @@ -587,10 +594,7 @@ static int blk_add_partitions(struct gendisk *disk) struct parsed_partitions *state; int ret = -EAGAIN, p; - if (disk->flags & GENHD_FL_NO_PART) - return 0; - - if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state)) + if (!disk_has_partscan(disk)) return 0; state = check_partition(disk); diff --git a/block/sed-opal.c b/block/sed-opal.c index 04f38a3f5d9597..1a1cb35bf4b798 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -313,7 +313,7 @@ static int read_sed_opal_key(const char *key_name, u_char *buffer, int buflen) &key_type_user, key_name, true); if (IS_ERR(kref)) - ret = PTR_ERR(kref); + return PTR_ERR(kref); key = key_ref_to_ptr(kref); down_read(&key->sem); @@ -1055,16 +1055,20 @@ static int response_parse(const u8 *buf, size_t length, token_length = response_parse_medium(iter, pos); else if (pos[0] <= LONG_ATOM_BYTE) /* long atom */ token_length = response_parse_long(iter, pos); + else if (pos[0] == EMPTY_ATOM_BYTE) /* empty atom */ + token_length = 1; else /* TOKEN */ token_length = response_parse_token(iter, pos); if (token_length < 0) return token_length; + if (pos[0] != EMPTY_ATOM_BYTE) + num_entries++; + pos += token_length; total -= token_length; iter++; - num_entries++; } resp->num = num_entries; diff --git a/crypto/Kconfig b/crypto/Kconfig index 650b1b3620d818..fc0f75d8be01d2 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -1291,10 +1291,11 @@ config CRYPTO_JITTERENTROPY A non-physical non-deterministic ("true") RNG (e.g., an entropy source compliant with NIST SP800-90B) intended to provide a seed to a - deterministic RNG (e.g. per NIST SP800-90C). + deterministic RNG (e.g., per NIST SP800-90C). This RNG does not perform any cryptographic whitening of the generated + random numbers. - See https://www.chronox.de/jent.html + See https://www.chronox.de/jent/ config CRYPTO_JITTERENTROPY_TESTINTERFACE bool "CPU Jitter RNG Test Interface" diff --git a/crypto/aead.c b/crypto/aead.c index d5ba204ebdbfa6..ecab683016b7df 100644 --- a/crypto/aead.c +++ b/crypto/aead.c @@ -45,8 +45,7 @@ static int setkey_unaligned(struct crypto_aead *tfm, const u8 *key, alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1); memcpy(alignbuffer, key, keylen); ret = crypto_aead_alg(tfm)->setkey(tfm, alignbuffer, keylen); - memset(alignbuffer, 0, keylen); - kfree(buffer); + kfree_sensitive(buffer); return ret; } diff --git a/crypto/af_alg.c b/crypto/af_alg.c index ea6fb8e89d0653..68cc9290cabe9a 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -1116,9 +1116,13 @@ EXPORT_SYMBOL_GPL(af_alg_sendmsg); void af_alg_free_resources(struct af_alg_async_req *areq) { struct sock *sk = areq->sk; + struct af_alg_ctx *ctx; af_alg_free_areq_sgls(areq); sock_kfree_s(sk, areq, areq->areqlen); + + ctx = alg_sk(sk)->private; + ctx->inflight = false; } EXPORT_SYMBOL_GPL(af_alg_free_resources); @@ -1188,11 +1192,19 @@ EXPORT_SYMBOL_GPL(af_alg_poll); struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk, unsigned int areqlen) { - struct af_alg_async_req *areq = sock_kmalloc(sk, areqlen, GFP_KERNEL); + struct af_alg_ctx *ctx = alg_sk(sk)->private; + struct af_alg_async_req *areq; + + /* Only one AIO request can be in flight. */ + if (ctx->inflight) + return ERR_PTR(-EBUSY); + areq = sock_kmalloc(sk, areqlen, GFP_KERNEL); if (unlikely(!areq)) return ERR_PTR(-ENOMEM); + ctx->inflight = true; + areq->areqlen = areqlen; areq->sk = sk; areq->first_rsgl.sgl.sgt.sgl = areq->first_rsgl.sgl.sgl; diff --git a/crypto/algapi.c b/crypto/algapi.c index 4fe95c44804733..85bc279b4233fa 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -341,6 +341,7 @@ __crypto_register_alg(struct crypto_alg *alg, struct list_head *algs_to_put) } if (!strcmp(q->cra_driver_name, alg->cra_name) || + !strcmp(q->cra_driver_name, alg->cra_driver_name) || !strcmp(q->cra_name, alg->cra_driver_name)) goto err; } diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 82c44d4899b967..e24c829d7a0154 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -91,13 +91,13 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg, if (!(msg->msg_flags & MSG_MORE)) { err = hash_alloc_result(sk, ctx); if (err) - goto unlock_free; + goto unlock_free_result; ahash_request_set_crypt(&ctx->req, NULL, ctx->result, 0); err = crypto_wait_req(crypto_ahash_final(&ctx->req), &ctx->wait); if (err) - goto unlock_free; + goto unlock_free_result; } goto done_more; } @@ -170,6 +170,7 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg, unlock_free: af_alg_free_sg(&ctx->sgl); +unlock_free_result: hash_free_result(sk, ctx); ctx->more = false; goto unlock; diff --git a/crypto/asymmetric_keys/Kconfig b/crypto/asymmetric_keys/Kconfig index 1ef3b46d6f6e5c..684767ab23e24d 100644 --- a/crypto/asymmetric_keys/Kconfig +++ b/crypto/asymmetric_keys/Kconfig @@ -15,6 +15,7 @@ config ASYMMETRIC_PUBLIC_KEY_SUBTYPE select MPILIB select CRYPTO_HASH_INFO select CRYPTO_AKCIPHER + select CRYPTO_SIG select CRYPTO_HASH help This option provides support for asymmetric public key type handling. @@ -76,7 +77,7 @@ config SIGNED_PE_FILE_VERIFICATION signed PE binary. config FIPS_SIGNATURE_SELFTEST - bool "Run FIPS selftests on the X.509+PKCS7 signature verification" + tristate "Run FIPS selftests on the X.509+PKCS7 signature verification" help This option causes some selftests to be run on the signature verification code, using some built in data. This is required @@ -84,5 +85,8 @@ config FIPS_SIGNATURE_SELFTEST depends on KEYS depends on ASYMMETRIC_KEY_TYPE depends on PKCS7_MESSAGE_PARSER=X509_CERTIFICATE_PARSER + depends on X509_CERTIFICATE_PARSER + depends on CRYPTO_RSA + depends on CRYPTO_SHA256 endif # ASYMMETRIC_KEY_TYPE diff --git a/crypto/asymmetric_keys/Makefile b/crypto/asymmetric_keys/Makefile index 0d1fa1b692c6b2..1a273d6df3ebf4 100644 --- a/crypto/asymmetric_keys/Makefile +++ b/crypto/asymmetric_keys/Makefile @@ -22,7 +22,8 @@ x509_key_parser-y := \ x509_cert_parser.o \ x509_loader.o \ x509_public_key.o -x509_key_parser-$(CONFIG_FIPS_SIGNATURE_SELFTEST) += selftest.o +obj-$(CONFIG_FIPS_SIGNATURE_SELFTEST) += x509_selftest.o +x509_selftest-y += selftest.o $(obj)/x509_cert_parser.o: \ $(obj)/x509.asn1.h \ diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c index a5da8ccd353ef7..43af5fa510c09f 100644 --- a/crypto/asymmetric_keys/asymmetric_type.c +++ b/crypto/asymmetric_keys/asymmetric_type.c @@ -60,17 +60,18 @@ struct key *find_asymmetric_key(struct key *keyring, char *req, *p; int len; - WARN_ON(!id_0 && !id_1 && !id_2); - if (id_0) { lookup = id_0->data; len = id_0->len; } else if (id_1) { lookup = id_1->data; len = id_1->len; - } else { + } else if (id_2) { lookup = id_2->data; len = id_2->len; + } else { + WARN_ON(1); + return ERR_PTR(-EINVAL); } /* Construct an identifier "id:". */ diff --git a/crypto/asymmetric_keys/selftest.c b/crypto/asymmetric_keys/selftest.c index fa0bf7f2428495..c50da7ef90ae99 100644 --- a/crypto/asymmetric_keys/selftest.c +++ b/crypto/asymmetric_keys/selftest.c @@ -4,10 +4,11 @@ * Written by David Howells (dhowells@redhat.com) */ -#include +#include #include +#include #include -#include +#include #include "x509_parser.h" struct certs_test { @@ -175,7 +176,7 @@ static const struct certs_test certs_tests[] __initconst = { TEST(certs_selftest_1_data, certs_selftest_1_pkcs7), }; -int __init fips_signature_selftest(void) +static int __init fips_signature_selftest(void) { struct key *keyring; int ret, i; @@ -222,3 +223,9 @@ int __init fips_signature_selftest(void) key_put(keyring); return 0; } + +late_initcall(fips_signature_selftest); + +MODULE_DESCRIPTION("X.509 self tests"); +MODULE_AUTHOR("Red Hat, Inc."); +MODULE_LICENSE("GPL"); diff --git a/crypto/asymmetric_keys/x509_parser.h b/crypto/asymmetric_keys/x509_parser.h index a299c9c56f409e..97a886cbe01c3d 100644 --- a/crypto/asymmetric_keys/x509_parser.h +++ b/crypto/asymmetric_keys/x509_parser.h @@ -40,15 +40,6 @@ struct x509_certificate { bool blacklisted; }; -/* - * selftest.c - */ -#ifdef CONFIG_FIPS_SIGNATURE_SELFTEST -extern int __init fips_signature_selftest(void); -#else -static inline int fips_signature_selftest(void) { return 0; } -#endif - /* * x509_cert_parser.c */ diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c index 7c71db3ac23d48..6a4f00be22fc10 100644 --- a/crypto/asymmetric_keys/x509_public_key.c +++ b/crypto/asymmetric_keys/x509_public_key.c @@ -262,15 +262,9 @@ static struct asymmetric_key_parser x509_key_parser = { /* * Module stuff */ -extern int __init certs_selftest(void); static int __init x509_key_init(void) { - int ret; - - ret = register_asymmetric_key_parser(&x509_key_parser); - if (ret < 0) - return ret; - return fips_signature_selftest(); + return register_asymmetric_key_parser(&x509_key_parser); } static void __exit x509_key_exit(void) diff --git a/crypto/cipher.c b/crypto/cipher.c index 47c77a3e597833..40cae908788eca 100644 --- a/crypto/cipher.c +++ b/crypto/cipher.c @@ -34,8 +34,7 @@ static int setkey_unaligned(struct crypto_cipher *tfm, const u8 *key, alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1); memcpy(alignbuffer, key, keylen); ret = cia->cia_setkey(crypto_cipher_tfm(tfm), alignbuffer, keylen); - memset(alignbuffer, 0, keylen); - kfree(buffer); + kfree_sensitive(buffer); return ret; } diff --git a/crypto/ecdh.c b/crypto/ecdh.c index 80afee3234fbe7..3049f147e0117b 100644 --- a/crypto/ecdh.c +++ b/crypto/ecdh.c @@ -33,6 +33,8 @@ static int ecdh_set_secret(struct crypto_kpp *tfm, const void *buf, params.key_size > sizeof(u64) * ctx->ndigits) return -EINVAL; + memset(ctx->private_key, 0, sizeof(ctx->private_key)); + if (!params.key || !params.key_size) return ecc_gen_privkey(ctx->curve_id, ctx->ndigits, ctx->private_key); diff --git a/crypto/ecdsa.c b/crypto/ecdsa.c index fbd76498aba834..3f9ec273a121fd 100644 --- a/crypto/ecdsa.c +++ b/crypto/ecdsa.c @@ -373,4 +373,7 @@ module_exit(ecdsa_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Stefan Berger "); MODULE_DESCRIPTION("ECDSA generic algorithm"); +MODULE_ALIAS_CRYPTO("ecdsa-nist-p192"); +MODULE_ALIAS_CRYPTO("ecdsa-nist-p256"); +MODULE_ALIAS_CRYPTO("ecdsa-nist-p384"); MODULE_ALIAS_CRYPTO("ecdsa-generic"); diff --git a/crypto/ecrdsa.c b/crypto/ecrdsa.c index f3c6b5e15e75ba..3811f3805b5d88 100644 --- a/crypto/ecrdsa.c +++ b/crypto/ecrdsa.c @@ -294,4 +294,5 @@ module_exit(ecrdsa_mod_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Vitaly Chikunov "); MODULE_DESCRIPTION("EC-RDSA generic algorithm"); +MODULE_ALIAS_CRYPTO("ecrdsa"); MODULE_ALIAS_CRYPTO("ecrdsa-generic"); diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c index 8c1d0ca412137f..d0d954fe9d54f3 100644 --- a/crypto/pcrypt.c +++ b/crypto/pcrypt.c @@ -117,6 +117,8 @@ static int pcrypt_aead_encrypt(struct aead_request *req) err = padata_do_parallel(ictx->psenc, padata, &ctx->cb_cpu); if (!err) return -EINPROGRESS; + if (err == -EBUSY) + return -EAGAIN; return err; } @@ -164,6 +166,8 @@ static int pcrypt_aead_decrypt(struct aead_request *req) err = padata_do_parallel(ictx->psdec, padata, &ctx->cb_cpu); if (!err) return -EINPROGRESS; + if (err == -EBUSY) + return -EAGAIN; return err; } diff --git a/crypto/rsa.c b/crypto/rsa.c index c79613cdce6e44..b9cd11fb7d3672 100644 --- a/crypto/rsa.c +++ b/crypto/rsa.c @@ -220,6 +220,8 @@ static int rsa_check_exponent_fips(MPI e) } e_max = mpi_alloc(0); + if (!e_max) + return -ENOMEM; mpi_set_bit(e_max, 256); if (mpi_cmp(e, e_max) >= 0) { diff --git a/crypto/scompress.c b/crypto/scompress.c index 442a82c9de7def..b108a30a760014 100644 --- a/crypto/scompress.c +++ b/crypto/scompress.c @@ -117,6 +117,7 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) struct crypto_scomp *scomp = *tfm_ctx; void **ctx = acomp_request_ctx(req); struct scomp_scratch *scratch; + unsigned int dlen; int ret; if (!req->src || !req->slen || req->slen > SCOMP_SCRATCH_SIZE) @@ -128,6 +129,8 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) if (!req->dlen || req->dlen > SCOMP_SCRATCH_SIZE) req->dlen = SCOMP_SCRATCH_SIZE; + dlen = req->dlen; + scratch = raw_cpu_ptr(&scomp_scratch); spin_lock(&scratch->lock); @@ -145,6 +148,9 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) ret = -ENOMEM; goto out; } + } else if (req->dlen > dlen) { + ret = -ENOSPC; + goto out; } scatterwalk_map_and_copy(scratch->dst, req->dst, 0, req->dlen, 1); diff --git a/crypto/simd.c b/crypto/simd.c index edaa479a1ec5e5..d109866641a265 100644 --- a/crypto/simd.c +++ b/crypto/simd.c @@ -136,27 +136,19 @@ static int simd_skcipher_init(struct crypto_skcipher *tfm) return 0; } -struct simd_skcipher_alg *simd_skcipher_create_compat(const char *algname, +struct simd_skcipher_alg *simd_skcipher_create_compat(struct skcipher_alg *ialg, + const char *algname, const char *drvname, const char *basename) { struct simd_skcipher_alg *salg; - struct crypto_skcipher *tfm; - struct skcipher_alg *ialg; struct skcipher_alg *alg; int err; - tfm = crypto_alloc_skcipher(basename, CRYPTO_ALG_INTERNAL, - CRYPTO_ALG_INTERNAL | CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) - return ERR_CAST(tfm); - - ialg = crypto_skcipher_alg(tfm); - salg = kzalloc(sizeof(*salg), GFP_KERNEL); if (!salg) { salg = ERR_PTR(-ENOMEM); - goto out_put_tfm; + goto out; } salg->ialg_name = basename; @@ -195,30 +187,16 @@ struct simd_skcipher_alg *simd_skcipher_create_compat(const char *algname, if (err) goto out_free_salg; -out_put_tfm: - crypto_free_skcipher(tfm); +out: return salg; out_free_salg: kfree(salg); salg = ERR_PTR(err); - goto out_put_tfm; + goto out; } EXPORT_SYMBOL_GPL(simd_skcipher_create_compat); -struct simd_skcipher_alg *simd_skcipher_create(const char *algname, - const char *basename) -{ - char drvname[CRYPTO_MAX_ALG_NAME]; - - if (snprintf(drvname, CRYPTO_MAX_ALG_NAME, "simd-%s", basename) >= - CRYPTO_MAX_ALG_NAME) - return ERR_PTR(-ENAMETOOLONG); - - return simd_skcipher_create_compat(algname, drvname, basename); -} -EXPORT_SYMBOL_GPL(simd_skcipher_create); - void simd_skcipher_free(struct simd_skcipher_alg *salg) { crypto_unregister_skcipher(&salg->alg); @@ -246,7 +224,7 @@ int simd_register_skciphers_compat(struct skcipher_alg *algs, int count, algname = algs[i].base.cra_name + 2; drvname = algs[i].base.cra_driver_name + 2; basename = algs[i].base.cra_driver_name; - simd = simd_skcipher_create_compat(algname, drvname, basename); + simd = simd_skcipher_create_compat(algs + i, algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) goto err_unregister; @@ -383,27 +361,19 @@ static int simd_aead_init(struct crypto_aead *tfm) return 0; } -struct simd_aead_alg *simd_aead_create_compat(const char *algname, - const char *drvname, - const char *basename) +static struct simd_aead_alg *simd_aead_create_compat(struct aead_alg *ialg, + const char *algname, + const char *drvname, + const char *basename) { struct simd_aead_alg *salg; - struct crypto_aead *tfm; - struct aead_alg *ialg; struct aead_alg *alg; int err; - tfm = crypto_alloc_aead(basename, CRYPTO_ALG_INTERNAL, - CRYPTO_ALG_INTERNAL | CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) - return ERR_CAST(tfm); - - ialg = crypto_aead_alg(tfm); - salg = kzalloc(sizeof(*salg), GFP_KERNEL); if (!salg) { salg = ERR_PTR(-ENOMEM); - goto out_put_tfm; + goto out; } salg->ialg_name = basename; @@ -442,36 +412,20 @@ struct simd_aead_alg *simd_aead_create_compat(const char *algname, if (err) goto out_free_salg; -out_put_tfm: - crypto_free_aead(tfm); +out: return salg; out_free_salg: kfree(salg); salg = ERR_PTR(err); - goto out_put_tfm; -} -EXPORT_SYMBOL_GPL(simd_aead_create_compat); - -struct simd_aead_alg *simd_aead_create(const char *algname, - const char *basename) -{ - char drvname[CRYPTO_MAX_ALG_NAME]; - - if (snprintf(drvname, CRYPTO_MAX_ALG_NAME, "simd-%s", basename) >= - CRYPTO_MAX_ALG_NAME) - return ERR_PTR(-ENAMETOOLONG); - - return simd_aead_create_compat(algname, drvname, basename); + goto out; } -EXPORT_SYMBOL_GPL(simd_aead_create); -void simd_aead_free(struct simd_aead_alg *salg) +static void simd_aead_free(struct simd_aead_alg *salg) { crypto_unregister_aead(&salg->alg); kfree(salg); } -EXPORT_SYMBOL_GPL(simd_aead_free); int simd_register_aeads_compat(struct aead_alg *algs, int count, struct simd_aead_alg **simd_algs) @@ -493,7 +447,7 @@ int simd_register_aeads_compat(struct aead_alg *algs, int count, algname = algs[i].base.cra_name + 2; drvname = algs[i].base.cra_driver_name + 2; basename = algs[i].base.cra_driver_name; - simd = simd_aead_create_compat(algname, drvname, basename); + simd = simd_aead_create_compat(algs + i, algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) goto err_unregister; diff --git a/crypto/xor.c b/crypto/xor.c index 8e72e5d5db0ded..56aa3169e87171 100644 --- a/crypto/xor.c +++ b/crypto/xor.c @@ -83,33 +83,30 @@ static void __init do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2) { int speed; - int i, j; - ktime_t min, start, diff; + unsigned long reps; + ktime_t min, start, t0; tmpl->next = template_list; template_list = tmpl; preempt_disable(); - min = (ktime_t)S64_MAX; - for (i = 0; i < 3; i++) { - start = ktime_get(); - for (j = 0; j < REPS; j++) { - mb(); /* prevent loop optimization */ - tmpl->do_2(BENCH_SIZE, b1, b2); - mb(); - } - diff = ktime_sub(ktime_get(), start); - if (diff < min) - min = diff; - } + reps = 0; + t0 = ktime_get(); + /* delay start until time has advanced */ + while ((start = ktime_get()) == t0) + cpu_relax(); + do { + mb(); /* prevent loop optimization */ + tmpl->do_2(BENCH_SIZE, b1, b2); + mb(); + } while (reps++ < REPS || (t0 = ktime_get()) == start); + min = ktime_sub(t0, start); preempt_enable(); // bytes/ns == GB/s, multiply by 1000 to get MB/s [not MiB/s] - if (!min) - min = 1; - speed = (1000 * REPS * BENCH_SIZE) / (unsigned int)ktime_to_ns(min); + speed = (1000 * reps * BENCH_SIZE) / (unsigned int)ktime_to_ns(min); tmpl->speed = speed; pr_info(" %-16s: %5d MB/sec\n", tmpl->name, speed); diff --git a/crypto/xts.c b/crypto/xts.c index 548b302c6c6a00..038f60dd512d9f 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -28,7 +28,7 @@ struct xts_tfm_ctx { struct xts_instance_ctx { struct crypto_skcipher_spawn spawn; - char name[CRYPTO_MAX_ALG_NAME]; + struct crypto_cipher_spawn tweak_spawn; }; struct xts_request_ctx { @@ -306,7 +306,7 @@ static int xts_init_tfm(struct crypto_skcipher *tfm) ctx->child = child; - tweak = crypto_alloc_cipher(ictx->name, 0, 0); + tweak = crypto_spawn_cipher(&ictx->tweak_spawn); if (IS_ERR(tweak)) { crypto_free_skcipher(ctx->child); return PTR_ERR(tweak); @@ -333,11 +333,13 @@ static void xts_free_instance(struct skcipher_instance *inst) struct xts_instance_ctx *ictx = skcipher_instance_ctx(inst); crypto_drop_skcipher(&ictx->spawn); + crypto_drop_cipher(&ictx->tweak_spawn); kfree(inst); } static int xts_create(struct crypto_template *tmpl, struct rtattr **tb) { + char name[CRYPTO_MAX_ALG_NAME]; struct skcipher_instance *inst; struct xts_instance_ctx *ctx; struct skcipher_alg *alg; @@ -363,13 +365,13 @@ static int xts_create(struct crypto_template *tmpl, struct rtattr **tb) cipher_name, 0, mask); if (err == -ENOENT) { err = -ENAMETOOLONG; - if (snprintf(ctx->name, CRYPTO_MAX_ALG_NAME, "ecb(%s)", + if (snprintf(name, CRYPTO_MAX_ALG_NAME, "ecb(%s)", cipher_name) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; err = crypto_grab_skcipher(&ctx->spawn, skcipher_crypto_instance(inst), - ctx->name, 0, mask); + name, 0, mask); } if (err) @@ -398,23 +400,28 @@ static int xts_create(struct crypto_template *tmpl, struct rtattr **tb) if (!strncmp(cipher_name, "ecb(", 4)) { int len; - len = strscpy(ctx->name, cipher_name + 4, sizeof(ctx->name)); + len = strscpy(name, cipher_name + 4, sizeof(name)); if (len < 2) goto err_free_inst; - if (ctx->name[len - 1] != ')') + if (name[len - 1] != ')') goto err_free_inst; - ctx->name[len - 1] = 0; + name[len - 1] = 0; if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, - "xts(%s)", ctx->name) >= CRYPTO_MAX_ALG_NAME) { + "xts(%s)", name) >= CRYPTO_MAX_ALG_NAME) { err = -ENAMETOOLONG; goto err_free_inst; } } else goto err_free_inst; + err = crypto_grab_cipher(&ctx->tweak_spawn, + skcipher_crypto_instance(inst), name, 0, mask); + if (err) + goto err_free_inst; + inst->alg.base.cra_priority = alg->base.cra_priority; inst->alg.base.cra_blocksize = XTS_BLOCK_SIZE; inst->alg.base.cra_alignmask = alg->base.cra_alignmask | diff --git a/drivers/accel/drm_accel.c b/drivers/accel/drm_accel.c index 4a9baf02439e42..8827cb78ca9d8c 100644 --- a/drivers/accel/drm_accel.c +++ b/drivers/accel/drm_accel.c @@ -8,7 +8,7 @@ #include #include -#include +#include #include #include @@ -17,8 +17,7 @@ #include #include -static DEFINE_SPINLOCK(accel_minor_lock); -static struct idr accel_minors_idr; +DEFINE_XARRAY_ALLOC(accel_minors_xa); static struct dentry *accel_debugfs_root; static struct class *accel_class; @@ -120,99 +119,6 @@ void accel_set_device_instance_params(struct device *kdev, int index) kdev->type = &accel_sysfs_device_minor; } -/** - * accel_minor_alloc() - Allocates a new accel minor - * - * This function access the accel minors idr and allocates from it - * a new id to represent a new accel minor - * - * Return: A new id on success or error code in case idr_alloc failed - */ -int accel_minor_alloc(void) -{ - unsigned long flags; - int r; - - spin_lock_irqsave(&accel_minor_lock, flags); - r = idr_alloc(&accel_minors_idr, NULL, 0, ACCEL_MAX_MINORS, GFP_NOWAIT); - spin_unlock_irqrestore(&accel_minor_lock, flags); - - return r; -} - -/** - * accel_minor_remove() - Remove an accel minor - * @index: The minor id to remove. - * - * This function access the accel minors idr and removes from - * it the member with the id that is passed to this function. - */ -void accel_minor_remove(int index) -{ - unsigned long flags; - - spin_lock_irqsave(&accel_minor_lock, flags); - idr_remove(&accel_minors_idr, index); - spin_unlock_irqrestore(&accel_minor_lock, flags); -} - -/** - * accel_minor_replace() - Replace minor pointer in accel minors idr. - * @minor: Pointer to the new minor. - * @index: The minor id to replace. - * - * This function access the accel minors idr structure and replaces the pointer - * that is associated with an existing id. Because the minor pointer can be - * NULL, we need to explicitly pass the index. - * - * Return: 0 for success, negative value for error - */ -void accel_minor_replace(struct drm_minor *minor, int index) -{ - unsigned long flags; - - spin_lock_irqsave(&accel_minor_lock, flags); - idr_replace(&accel_minors_idr, minor, index); - spin_unlock_irqrestore(&accel_minor_lock, flags); -} - -/* - * Looks up the given minor-ID and returns the respective DRM-minor object. The - * refence-count of the underlying device is increased so you must release this - * object with accel_minor_release(). - * - * The object can be only a drm_minor that represents an accel device. - * - * As long as you hold this minor, it is guaranteed that the object and the - * minor->dev pointer will stay valid! However, the device may get unplugged and - * unregistered while you hold the minor. - */ -static struct drm_minor *accel_minor_acquire(unsigned int minor_id) -{ - struct drm_minor *minor; - unsigned long flags; - - spin_lock_irqsave(&accel_minor_lock, flags); - minor = idr_find(&accel_minors_idr, minor_id); - if (minor) - drm_dev_get(minor->dev); - spin_unlock_irqrestore(&accel_minor_lock, flags); - - if (!minor) { - return ERR_PTR(-ENODEV); - } else if (drm_dev_is_unplugged(minor->dev)) { - drm_dev_put(minor->dev); - return ERR_PTR(-ENODEV); - } - - return minor; -} - -static void accel_minor_release(struct drm_minor *minor) -{ - drm_dev_put(minor->dev); -} - /** * accel_open - open method for ACCEL file * @inode: device inode @@ -230,7 +136,7 @@ int accel_open(struct inode *inode, struct file *filp) struct drm_minor *minor; int retcode; - minor = accel_minor_acquire(iminor(inode)); + minor = drm_minor_acquire(&accel_minors_xa, iminor(inode)); if (IS_ERR(minor)) return PTR_ERR(minor); @@ -249,7 +155,7 @@ int accel_open(struct inode *inode, struct file *filp) err_undo: atomic_dec(&dev->open_count); - accel_minor_release(minor); + drm_minor_release(minor); return retcode; } EXPORT_SYMBOL_GPL(accel_open); @@ -260,7 +166,7 @@ static int accel_stub_open(struct inode *inode, struct file *filp) struct drm_minor *minor; int err; - minor = accel_minor_acquire(iminor(inode)); + minor = drm_minor_acquire(&accel_minors_xa, iminor(inode)); if (IS_ERR(minor)) return PTR_ERR(minor); @@ -277,7 +183,7 @@ static int accel_stub_open(struct inode *inode, struct file *filp) err = 0; out: - accel_minor_release(minor); + drm_minor_release(minor); return err; } @@ -293,15 +199,13 @@ void accel_core_exit(void) unregister_chrdev(ACCEL_MAJOR, "accel"); debugfs_remove(accel_debugfs_root); accel_sysfs_destroy(); - idr_destroy(&accel_minors_idr); + WARN_ON(!xa_empty(&accel_minors_xa)); } int __init accel_core_init(void) { int ret; - idr_init(&accel_minors_idr); - ret = accel_sysfs_init(); if (ret < 0) { DRM_ERROR("Cannot create ACCEL class: %d\n", ret); diff --git a/drivers/accel/habanalabs/common/debugfs.c b/drivers/accel/habanalabs/common/debugfs.c index 9e84a47a21dcf4..7d733e4d506114 100644 --- a/drivers/accel/habanalabs/common/debugfs.c +++ b/drivers/accel/habanalabs/common/debugfs.c @@ -1645,19 +1645,19 @@ static void add_files_to_device(struct hl_device *hdev, struct hl_dbg_device_ent &hl_data64b_fops); debugfs_create_file("set_power_state", - 0200, + 0644, root, dev_entry, &hl_power_fops); debugfs_create_file("device", - 0200, + 0644, root, dev_entry, &hl_device_fops); debugfs_create_file("clk_gate", - 0200, + 0644, root, dev_entry, &hl_clk_gate_fops); @@ -1669,13 +1669,13 @@ static void add_files_to_device(struct hl_device *hdev, struct hl_dbg_device_ent &hl_stop_on_err_fops); debugfs_create_file("dump_security_violations", - 0644, + 0400, root, dev_entry, &hl_security_violations_fops); debugfs_create_file("dump_razwi_events", - 0644, + 0400, root, dev_entry, &hl_razwi_check_fops); @@ -1708,7 +1708,7 @@ static void add_files_to_device(struct hl_device *hdev, struct hl_dbg_device_ent &hdev->reset_info.skip_reset_on_timeout); debugfs_create_file("state_dump", - 0600, + 0644, root, dev_entry, &hl_state_dump_fops); @@ -1726,7 +1726,7 @@ static void add_files_to_device(struct hl_device *hdev, struct hl_dbg_device_ent for (i = 0, entry = dev_entry->entry_arr ; i < count ; i++, entry++) { debugfs_create_file(hl_debugfs_list[i].name, - 0444, + 0644, root, entry, &hl_debugfs_fops); diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c index b97339d1f7c6ea..ebef56478e1852 100644 --- a/drivers/accel/habanalabs/common/device.c +++ b/drivers/accel/habanalabs/common/device.c @@ -808,6 +808,9 @@ static int device_early_init(struct hl_device *hdev) gaudi2_set_asic_funcs(hdev); strscpy(hdev->asic_name, "GAUDI2B", sizeof(hdev->asic_name)); break; + case ASIC_GAUDI2C: + gaudi2_set_asic_funcs(hdev); + strscpy(hdev->asic_name, "GAUDI2C", sizeof(hdev->asic_name)); break; default: dev_err(hdev->dev, "Unrecognized ASIC type %d\n", diff --git a/drivers/accel/habanalabs/common/habanalabs.h b/drivers/accel/habanalabs/common/habanalabs.h index 2f027d5a820647..179e5e7013a120 100644 --- a/drivers/accel/habanalabs/common/habanalabs.h +++ b/drivers/accel/habanalabs/common/habanalabs.h @@ -1220,6 +1220,7 @@ struct hl_dec { * @ASIC_GAUDI_SEC: Gaudi secured device (HL-2000). * @ASIC_GAUDI2: Gaudi2 device. * @ASIC_GAUDI2B: Gaudi2B device. + * @ASIC_GAUDI2C: Gaudi2C device. */ enum hl_asic_type { ASIC_INVALID, @@ -1228,6 +1229,7 @@ enum hl_asic_type { ASIC_GAUDI_SEC, ASIC_GAUDI2, ASIC_GAUDI2B, + ASIC_GAUDI2C, }; struct hl_cs_parser; @@ -2506,7 +2508,7 @@ struct hl_state_dump_specs { * DEVICES */ -#define HL_STR_MAX 32 +#define HL_STR_MAX 64 #define HL_DEV_STS_MAX (HL_DEVICE_STATUS_LAST + 1) diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c index 7263e84c1a4dc3..010bf63fcca394 100644 --- a/drivers/accel/habanalabs/common/habanalabs_drv.c +++ b/drivers/accel/habanalabs/common/habanalabs_drv.c @@ -101,6 +101,9 @@ static enum hl_asic_type get_asic_type(struct hl_device *hdev) case REV_ID_B: asic_type = ASIC_GAUDI2B; break; + case REV_ID_C: + asic_type = ASIC_GAUDI2C; + break; default: break; } diff --git a/drivers/accel/habanalabs/common/habanalabs_ioctl.c b/drivers/accel/habanalabs/common/habanalabs_ioctl.c index 6a45a92344e9bd..a7f6c54c123eff 100644 --- a/drivers/accel/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/accel/habanalabs/common/habanalabs_ioctl.c @@ -682,7 +682,7 @@ static int sec_attest_info(struct hl_fpriv *hpriv, struct hl_info_args *args) if (!sec_attest_info) return -ENOMEM; - info = kmalloc(sizeof(*info), GFP_KERNEL); + info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) { rc = -ENOMEM; goto free_sec_attest_info; diff --git a/drivers/accel/habanalabs/common/irq.c b/drivers/accel/habanalabs/common/irq.c index b1010d206c2ef1..813315cea4a7b0 100644 --- a/drivers/accel/habanalabs/common/irq.c +++ b/drivers/accel/habanalabs/common/irq.c @@ -271,6 +271,9 @@ static int handle_registration_node(struct hl_device *hdev, struct hl_user_pendi free_node->cq_cb = pend->ts_reg_info.cq_cb; list_add(&free_node->free_objects_node, *free_list); + /* Mark TS record as free */ + pend->ts_reg_info.in_use = false; + return 0; } diff --git a/drivers/accel/habanalabs/common/memory.c b/drivers/accel/habanalabs/common/memory.c index 4fc72a07d2f59a..5b7d9a351133fe 100644 --- a/drivers/accel/habanalabs/common/memory.c +++ b/drivers/accel/habanalabs/common/memory.c @@ -1878,16 +1878,16 @@ static int export_dmabuf(struct hl_ctx *ctx, static int validate_export_params_common(struct hl_device *hdev, u64 device_addr, u64 size) { - if (!IS_ALIGNED(device_addr, PAGE_SIZE)) { + if (!PAGE_ALIGNED(device_addr)) { dev_dbg(hdev->dev, - "exported device memory address 0x%llx should be aligned to 0x%lx\n", + "exported device memory address 0x%llx should be aligned to PAGE_SIZE 0x%lx\n", device_addr, PAGE_SIZE); return -EINVAL; } - if (size < PAGE_SIZE) { + if (!size || !PAGE_ALIGNED(size)) { dev_dbg(hdev->dev, - "exported device memory size %llu should be equal to or greater than %lu\n", + "exported device memory size %llu should be a multiple of PAGE_SIZE %lu\n", size, PAGE_SIZE); return -EINVAL; } @@ -1938,6 +1938,13 @@ static int validate_export_params(struct hl_device *hdev, u64 device_addr, u64 s if (rc) return rc; + if (!PAGE_ALIGNED(offset)) { + dev_dbg(hdev->dev, + "exported device memory offset %llu should be a multiple of PAGE_SIZE %lu\n", + offset, PAGE_SIZE); + return -EINVAL; + } + if ((offset + size) > phys_pg_pack->total_size) { dev_dbg(hdev->dev, "offset %#llx and size %#llx exceed total map size %#llx\n", offset, size, phys_pg_pack->total_size); diff --git a/drivers/accel/habanalabs/common/mmu/mmu.c b/drivers/accel/habanalabs/common/mmu/mmu.c index b2145716c60533..b654302a68fc08 100644 --- a/drivers/accel/habanalabs/common/mmu/mmu.c +++ b/drivers/accel/habanalabs/common/mmu/mmu.c @@ -596,6 +596,7 @@ int hl_mmu_if_set_funcs(struct hl_device *hdev) break; case ASIC_GAUDI2: case ASIC_GAUDI2B: + case ASIC_GAUDI2C: /* MMUs in Gaudi2 are always host resident */ hl_mmu_v2_hr_set_funcs(hdev, &hdev->mmu_func[MMU_HR_PGT]); break; diff --git a/drivers/accel/habanalabs/common/sysfs.c b/drivers/accel/habanalabs/common/sysfs.c index 01f89f029355e6..27860637305556 100644 --- a/drivers/accel/habanalabs/common/sysfs.c +++ b/drivers/accel/habanalabs/common/sysfs.c @@ -251,6 +251,9 @@ static ssize_t device_type_show(struct device *dev, case ASIC_GAUDI2B: str = "GAUDI2B"; break; + case ASIC_GAUDI2C: + str = "GAUDI2C"; + break; default: dev_err(hdev->dev, "Unrecognized ASIC type %d\n", hdev->asic_type); diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c index 20c4583f12b0d2..31c74ca70a2e5c 100644 --- a/drivers/accel/habanalabs/gaudi2/gaudi2.c +++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c @@ -8149,11 +8149,11 @@ static int gaudi2_psoc_razwi_get_engines(struct gaudi2_razwi_info *razwi_info, u eng_id[num_of_eng] = razwi_info[i].eng_id; base[num_of_eng] = razwi_info[i].rtr_ctrl; if (!num_of_eng) - str_size += snprintf(eng_name + str_size, + str_size += scnprintf(eng_name + str_size, PSOC_RAZWI_ENG_STR_SIZE - str_size, "%s", razwi_info[i].eng_name); else - str_size += snprintf(eng_name + str_size, + str_size += scnprintf(eng_name + str_size, PSOC_RAZWI_ENG_STR_SIZE - str_size, " or %s", razwi_info[i].eng_name); num_of_eng++; diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2_security.c b/drivers/accel/habanalabs/gaudi2/gaudi2_security.c index 2742b1f801eb2a..493e556cd31b74 100644 --- a/drivers/accel/habanalabs/gaudi2/gaudi2_security.c +++ b/drivers/accel/habanalabs/gaudi2/gaudi2_security.c @@ -479,6 +479,7 @@ static const u32 gaudi2_pb_dcr0_edma0_unsecured_regs[] = { mmDCORE0_EDMA0_CORE_CTX_TE_NUMROWS, mmDCORE0_EDMA0_CORE_CTX_IDX, mmDCORE0_EDMA0_CORE_CTX_IDX_INC, + mmDCORE0_EDMA0_CORE_WR_COMP_MAX_OUTSTAND, mmDCORE0_EDMA0_CORE_RD_LBW_RATE_LIM_CFG, mmDCORE0_EDMA0_QM_CQ_CFG0_0, mmDCORE0_EDMA0_QM_CQ_CFG0_1, @@ -1601,6 +1602,7 @@ static const u32 gaudi2_pb_dcr0_tpc0_unsecured_regs[] = { mmDCORE0_TPC0_CFG_KERNEL_SRF_30, mmDCORE0_TPC0_CFG_KERNEL_SRF_31, mmDCORE0_TPC0_CFG_TPC_SB_L0CD, + mmDCORE0_TPC0_CFG_TPC_COUNT, mmDCORE0_TPC0_CFG_TPC_ID, mmDCORE0_TPC0_CFG_QM_KERNEL_ID_INC, mmDCORE0_TPC0_CFG_QM_TID_BASE_SIZE_HIGH_DIM_0, diff --git a/drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h b/drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h index f5d497dc9bdc17..4f951cada07766 100644 --- a/drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h +++ b/drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h @@ -25,6 +25,7 @@ enum hl_revision_id { REV_ID_INVALID = 0x00, REV_ID_A = 0x01, REV_ID_B = 0x02, + REV_ID_C = 0x03 }; #endif /* INCLUDE_PCI_GENERAL_H_ */ diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index 7e9359611d69ca..5619980d9edda7 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -467,9 +467,8 @@ static int ivpu_pci_init(struct ivpu_device *vdev) /* Clear any pending errors */ pcie_capability_clear_word(pdev, PCI_EXP_DEVSTA, 0x3f); - /* VPU 37XX does not require 10m D3hot delay */ - if (ivpu_hw_gen(vdev) == IVPU_HW_37XX) - pdev->d3hot_delay = 0; + /* NPU does not require 10m D3hot delay */ + pdev->d3hot_delay = 0; ret = pcim_enable_device(pdev); if (ret) { @@ -518,7 +517,7 @@ static int ivpu_dev_init(struct ivpu_device *vdev) vdev->context_xa_limit.min = IVPU_USER_CONTEXT_MIN_SSID; vdev->context_xa_limit.max = IVPU_USER_CONTEXT_MAX_SSID; atomic64_set(&vdev->unique_id_counter, 0); - xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC); + xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ); xa_init_flags(&vdev->submitted_jobs_xa, XA_FLAGS_ALLOC1); lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key); diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h index 2adc349126bb66..6853dfe1c7e585 100644 --- a/drivers/accel/ivpu/ivpu_drv.h +++ b/drivers/accel/ivpu/ivpu_drv.h @@ -76,6 +76,11 @@ #define IVPU_WA(wa_name) (vdev->wa.wa_name) +#define IVPU_PRINT_WA(wa_name) do { \ + if (IVPU_WA(wa_name)) \ + ivpu_dbg(vdev, MISC, "Using WA: " #wa_name "\n"); \ +} while (0) + struct ivpu_wa_table { bool punit_disabled; bool clear_runtime_mem; diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c index a277bbae78fc45..3b35d262ddd43a 100644 --- a/drivers/accel/ivpu/ivpu_fw.c +++ b/drivers/accel/ivpu/ivpu_fw.c @@ -55,6 +55,10 @@ static struct { { IVPU_HW_40XX, "intel/vpu/vpu_40xx_v0.0.bin" }, }; +/* Production fw_names from the table above */ +MODULE_FIRMWARE("intel/vpu/vpu_37xx_v0.0.bin"); +MODULE_FIRMWARE("intel/vpu/vpu_40xx_v0.0.bin"); + static int ivpu_fw_request(struct ivpu_device *vdev) { int ret = -ENOENT; diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c index 18be8b98e9a8b3..c0de7c0c991f56 100644 --- a/drivers/accel/ivpu/ivpu_hw_37xx.c +++ b/drivers/accel/ivpu/ivpu_hw_37xx.c @@ -53,10 +53,12 @@ #define ICB_0_1_IRQ_MASK ((((u64)ICB_1_IRQ_MASK) << 32) | ICB_0_IRQ_MASK) -#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE)) | \ - (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \ +#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \ (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, UFI_ERR))) +#define BUTTRESS_ALL_IRQ_MASK (BUTTRESS_IRQ_MASK | \ + (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE))) + #define BUTTRESS_IRQ_ENABLE_MASK ((u32)~BUTTRESS_IRQ_MASK) #define BUTTRESS_IRQ_DISABLE_MASK ((u32)-1) @@ -102,8 +104,17 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev) vdev->wa.clear_runtime_mem = false; vdev->wa.d3hot_after_power_off = true; - if (ivpu_device_id(vdev) == PCI_DEVICE_ID_MTL && ivpu_revision(vdev) < 4) + REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, BUTTRESS_ALL_IRQ_MASK); + if (REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) == BUTTRESS_ALL_IRQ_MASK) { + /* Writing 1s does not clear the interrupt status register */ vdev->wa.interrupt_clear_with_0 = true; + REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, 0x0); + } + + IVPU_PRINT_WA(punit_disabled); + IVPU_PRINT_WA(clear_runtime_mem); + IVPU_PRINT_WA(d3hot_after_power_off); + IVPU_PRINT_WA(interrupt_clear_with_0); } static void ivpu_hw_timeouts_init(struct ivpu_device *vdev) @@ -536,12 +547,22 @@ static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev) return ret; } +static int ivpu_boot_pwr_domain_disable(struct ivpu_device *vdev) +{ + ivpu_boot_dpu_active_drive(vdev, false); + ivpu_boot_pwr_island_isolation_drive(vdev, true); + ivpu_boot_pwr_island_trickle_drive(vdev, false); + ivpu_boot_pwr_island_drive(vdev, false); + + return ivpu_boot_wait_for_pwr_island_status(vdev, 0x0); +} + static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev) { u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES); val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, NOSNOOP_OVERRIDE_EN, val); - val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val); + val = REG_CLR_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val); val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val); REGV_WR32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, val); @@ -625,30 +646,26 @@ static int ivpu_hw_37xx_info_init(struct ivpu_device *vdev) ivpu_hw_init_range(&hw->ranges.shave, 0x180000000, SZ_2G); ivpu_hw_init_range(&hw->ranges.dma, 0x200000000, SZ_8G); + ivpu_hw_read_platform(vdev); + ivpu_hw_wa_init(vdev); + ivpu_hw_timeouts_init(vdev); + return 0; } static int ivpu_hw_37xx_reset(struct ivpu_device *vdev) { - int ret; - u32 val; - - if (IVPU_WA(punit_disabled)) - return 0; + int ret = 0; - ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US); - if (ret) { - ivpu_err(vdev, "Timed out waiting for TRIGGER bit\n"); - return ret; + if (ivpu_boot_pwr_domain_disable(vdev)) { + ivpu_err(vdev, "Failed to disable power domain\n"); + ret = -EIO; } - val = REGB_RD32(VPU_37XX_BUTTRESS_VPU_IP_RESET); - val = REG_SET_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, val); - REGB_WR32(VPU_37XX_BUTTRESS_VPU_IP_RESET, val); - - ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US); - if (ret) - ivpu_err(vdev, "Timed out waiting for RESET completion\n"); + if (ivpu_pll_disable(vdev)) { + ivpu_err(vdev, "Failed to disable PLL\n"); + ret = -EIO; + } return ret; } @@ -681,14 +698,6 @@ static int ivpu_hw_37xx_power_up(struct ivpu_device *vdev) { int ret; - ivpu_hw_read_platform(vdev); - ivpu_hw_wa_init(vdev); - ivpu_hw_timeouts_init(vdev); - - ret = ivpu_hw_37xx_reset(vdev); - if (ret) - ivpu_warn(vdev, "Failed to reset HW: %d\n", ret); - ret = ivpu_hw_37xx_d0i3_disable(vdev); if (ret) ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret); @@ -756,11 +765,11 @@ static int ivpu_hw_37xx_power_down(struct ivpu_device *vdev) { int ret = 0; - if (!ivpu_hw_37xx_is_idle(vdev) && ivpu_hw_37xx_reset(vdev)) - ivpu_err(vdev, "Failed to reset the VPU\n"); + if (!ivpu_hw_37xx_is_idle(vdev)) + ivpu_warn(vdev, "VPU not idle during power down\n"); - if (ivpu_pll_disable(vdev)) { - ivpu_err(vdev, "Failed to disable PLL\n"); + if (ivpu_hw_37xx_reset(vdev)) { + ivpu_err(vdev, "Failed to reset VPU\n"); ret = -EIO; } diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c index 85171a408363fa..cced6278c4f893 100644 --- a/drivers/accel/ivpu/ivpu_hw_40xx.c +++ b/drivers/accel/ivpu/ivpu_hw_40xx.c @@ -24,7 +24,7 @@ #define SKU_HW_ID_SHIFT 16u #define SKU_HW_ID_MASK 0xffff0000u -#define PLL_CONFIG_DEFAULT 0x1 +#define PLL_CONFIG_DEFAULT 0x0 #define PLL_CDYN_DEFAULT 0x80 #define PLL_EPP_DEFAULT 0x80 #define PLL_REF_CLK_FREQ (50 * 1000000) @@ -125,6 +125,10 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev) if (ivpu_hw_gen(vdev) == IVPU_HW_40XX) vdev->wa.disable_clock_relinquish = true; + + IVPU_PRINT_WA(punit_disabled); + IVPU_PRINT_WA(clear_runtime_mem); + IVPU_PRINT_WA(disable_clock_relinquish); } static void ivpu_hw_timeouts_init(struct ivpu_device *vdev) @@ -519,7 +523,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev) u32 val = REGV_RD32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES); val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, SNOOP_OVERRIDE_EN, val); - val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val); + val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val); val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val); REGV_WR32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, val); @@ -693,7 +697,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev) { struct ivpu_hw_info *hw = vdev->hw; u32 tile_disable; - u32 tile_enable; u32 fuse; fuse = REGB_RD32(VPU_40XX_BUTTRESS_TILE_FUSE); @@ -714,10 +717,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev) else ivpu_dbg(vdev, MISC, "Fuse: All %d tiles enabled\n", TILE_MAX_NUM); - tile_enable = (~tile_disable) & TILE_MAX_MASK; - - hw->sku = REG_SET_FLD_NUM(SKU, HW_ID, LNL_HW_ID, hw->sku); - hw->sku = REG_SET_FLD_NUM(SKU, TILE, tile_enable, hw->sku); hw->tile_fuse = tile_disable; hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT; @@ -728,6 +727,10 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev) ivpu_hw_init_range(&vdev->hw->ranges.shave, 0x80000000 + SZ_256M, SZ_2G - SZ_256M); ivpu_hw_init_range(&vdev->hw->ranges.dma, 0x200000000, SZ_8G); + ivpu_hw_read_platform(vdev); + ivpu_hw_wa_init(vdev); + ivpu_hw_timeouts_init(vdev); + return 0; } @@ -819,10 +822,6 @@ static int ivpu_hw_40xx_power_up(struct ivpu_device *vdev) return ret; } - ivpu_hw_read_platform(vdev); - ivpu_hw_wa_init(vdev); - ivpu_hw_timeouts_init(vdev); - ret = ivpu_hw_40xx_d0i3_disable(vdev); if (ret) ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret); diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index de9e69f70af7e2..76f468c9f761bf 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -618,6 +618,5 @@ int ivpu_job_done_thread_init(struct ivpu_device *vdev) void ivpu_job_done_thread_fini(struct ivpu_device *vdev) { - kthread_stop(vdev->job_done_thread); - put_task_struct(vdev->job_done_thread); + kthread_stop_put(vdev->job_done_thread); } diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c index baefaf7bb3cbb9..d04a28e0524855 100644 --- a/drivers/accel/ivpu/ivpu_mmu.c +++ b/drivers/accel/ivpu/ivpu_mmu.c @@ -491,7 +491,6 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev) mmu->cmdq.cons = 0; memset(mmu->evtq.base, 0, IVPU_MMU_EVTQ_SIZE); - clflush_cache_range(mmu->evtq.base, IVPU_MMU_EVTQ_SIZE); mmu->evtq.prod = 0; mmu->evtq.cons = 0; @@ -805,8 +804,6 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev) if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT)) return NULL; - clflush_cache_range(evt, IVPU_MMU_EVTQ_CMD_SIZE); - evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK; REGV_WR32(VPU_37XX_HOST_MMU_EVTQ_CONS_SEC, evtq->cons); diff --git a/drivers/accel/qaic/mhi_controller.c b/drivers/accel/qaic/mhi_controller.c index 5036e58e7235bd..1405623b03e4ee 100644 --- a/drivers/accel/qaic/mhi_controller.c +++ b/drivers/accel/qaic/mhi_controller.c @@ -404,8 +404,21 @@ static struct mhi_controller_config aic100_config = { static int mhi_read_reg(struct mhi_controller *mhi_cntrl, void __iomem *addr, u32 *out) { - u32 tmp = readl_relaxed(addr); + u32 tmp; + /* + * SOC_HW_VERSION quirk + * The SOC_HW_VERSION register (offset 0x224) is not reliable and + * may contain uninitialized values, including 0xFFFFFFFF. This could + * cause a false positive link down error. Instead, intercept any + * reads and provide the correct value of the register. + */ + if (addr - mhi_cntrl->regs == 0x224) { + *out = 0x60110200; + return 0; + } + + tmp = readl_relaxed(addr); if (tmp == U32_MAX) return -EIO; diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c index f4b06792c6f1c0..ed1a5af434f246 100644 --- a/drivers/accel/qaic/qaic_data.c +++ b/drivers/accel/qaic/qaic_data.c @@ -766,7 +766,6 @@ struct drm_gem_object *qaic_gem_prime_import(struct drm_device *dev, struct dma_ struct dma_buf_attachment *attach; struct drm_gem_object *obj; struct qaic_bo *bo; - size_t size; int ret; bo = qaic_alloc_init_bo(); @@ -784,13 +783,12 @@ struct drm_gem_object *qaic_gem_prime_import(struct drm_device *dev, struct dma_ goto attach_fail; } - size = PAGE_ALIGN(attach->dmabuf->size); - if (size == 0) { + if (!attach->dmabuf->size) { ret = -EINVAL; goto size_align_fail; } - drm_gem_private_object_init(dev, obj, size); + drm_gem_private_object_init(dev, obj, attach->dmabuf->size); /* * skipping dma_buf_map_attachment() as we do not know the direction * just yet. Once the direction is known in the subsequent IOCTL to diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c index 1fbc9b921c4fcc..f677ad2177c2f2 100644 --- a/drivers/accessibility/speakup/main.c +++ b/drivers/accessibility/speakup/main.c @@ -574,7 +574,7 @@ static u_long get_word(struct vc_data *vc) } attr_ch = get_char(vc, (u_short *)tmp_pos, &spk_attr); buf[cnt++] = attr_ch; - while (tmpx < vc->vc_cols - 1) { + while (tmpx < vc->vc_cols - 1 && cnt < ARRAY_SIZE(buf) - 1) { tmp_pos += 2; tmpx++; ch = get_char(vc, (u_short *)tmp_pos, &temp); diff --git a/drivers/accessibility/speakup/synth.c b/drivers/accessibility/speakup/synth.c index eea2a2fa4f0159..45f90610313382 100644 --- a/drivers/accessibility/speakup/synth.c +++ b/drivers/accessibility/speakup/synth.c @@ -208,8 +208,10 @@ void spk_do_flush(void) wake_up_process(speakup_task); } -void synth_write(const char *buf, size_t count) +void synth_write(const char *_buf, size_t count) { + const unsigned char *buf = (const unsigned char *) _buf; + while (count--) synth_buffer_add(*buf++); synth_start(); diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index e120a96e1eaee8..ca87a093913599 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -145,9 +145,14 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, static u32 err_seq; estatus = extlog_elog_entry_check(cpu, bank); - if (estatus == NULL || (mce->kflags & MCE_HANDLED_CEC)) + if (!estatus) return NOTIFY_DONE; + if (mce->kflags & MCE_HANDLED_CEC) { + estatus->block_status = 0; + return NOTIFY_DONE; + } + memcpy(elog_buf, (void *)estatus, ELOG_ENTRY_LEN); /* clear record status to enable BIOS to update it again */ estatus->block_status = 0; @@ -303,9 +308,10 @@ static int __init extlog_init(void) static void __exit extlog_exit(void) { mce_unregister_decode_chain(&extlog_mce_dec); - ((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN; - if (extlog_l1_addr) + if (extlog_l1_addr) { + ((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN; acpi_os_unmap_iomem(extlog_l1_addr, l1_size); + } if (elog_addr) acpi_os_unmap_iomem(elog_addr, elog_size); release_mem_region(elog_base, elog_size); diff --git a/drivers/acpi/acpi_fpdt.c b/drivers/acpi/acpi_fpdt.c index a2056c4c8cb709..271092f2700a1e 100644 --- a/drivers/acpi/acpi_fpdt.c +++ b/drivers/acpi/acpi_fpdt.c @@ -194,12 +194,19 @@ static int fpdt_process_subtable(u64 address, u32 subtable_type) record_header = (void *)subtable_header + offset; offset += record_header->length; + if (!record_header->length) { + pr_err(FW_BUG "Zero-length record found in FPTD.\n"); + result = -EINVAL; + goto err; + } + switch (record_header->type) { case RECORD_S3_RESUME: if (subtable_type != SUBTABLE_S3PT) { pr_err(FW_BUG "Invalid record %d for subtable %s\n", record_header->type, signature); - return -EINVAL; + result = -EINVAL; + goto err; } if (record_resume) { pr_err("Duplicate resume performance record found.\n"); @@ -208,7 +215,7 @@ static int fpdt_process_subtable(u64 address, u32 subtable_type) record_resume = (struct resume_performance_record *)record_header; result = sysfs_create_group(fpdt_kobj, &resume_attr_group); if (result) - return result; + goto err; break; case RECORD_S3_SUSPEND: if (subtable_type != SUBTABLE_S3PT) { @@ -223,13 +230,14 @@ static int fpdt_process_subtable(u64 address, u32 subtable_type) record_suspend = (struct suspend_performance_record *)record_header; result = sysfs_create_group(fpdt_kobj, &suspend_attr_group); if (result) - return result; + goto err; break; case RECORD_BOOT: if (subtable_type != SUBTABLE_FBPT) { pr_err(FW_BUG "Invalid %d for subtable %s\n", record_header->type, signature); - return -EINVAL; + result = -EINVAL; + goto err; } if (record_boot) { pr_err("Duplicate boot performance record found.\n"); @@ -238,7 +246,7 @@ static int fpdt_process_subtable(u64 address, u32 subtable_type) record_boot = (struct boot_performance_record *)record_header; result = sysfs_create_group(fpdt_kobj, &boot_attr_group); if (result) - return result; + goto err; break; default: @@ -247,6 +255,18 @@ static int fpdt_process_subtable(u64 address, u32 subtable_type) } } return 0; + +err: + if (record_boot) + sysfs_remove_group(fpdt_kobj, &boot_attr_group); + + if (record_suspend) + sysfs_remove_group(fpdt_kobj, &suspend_attr_group); + + if (record_resume) + sysfs_remove_group(fpdt_kobj, &resume_attr_group); + + return result; } static int __init acpi_init_fpdt(void) @@ -255,6 +275,7 @@ static int __init acpi_init_fpdt(void) struct acpi_table_header *header; struct fpdt_subtable_entry *subtable; u32 offset = sizeof(*header); + int result; status = acpi_get_table(ACPI_SIG_FPDT, 0, &header); @@ -263,8 +284,8 @@ static int __init acpi_init_fpdt(void) fpdt_kobj = kobject_create_and_add("fpdt", acpi_kobj); if (!fpdt_kobj) { - acpi_put_table(header); - return -ENOMEM; + result = -ENOMEM; + goto err_nomem; } while (offset < header->length) { @@ -272,8 +293,10 @@ static int __init acpi_init_fpdt(void) switch (subtable->type) { case SUBTABLE_FBPT: case SUBTABLE_S3PT: - fpdt_process_subtable(subtable->address, + result = fpdt_process_subtable(subtable->address, subtable->type); + if (result) + goto err_subtable; break; default: /* Other types are reserved in ACPI 6.4 spec. */ @@ -282,6 +305,12 @@ static int __init acpi_init_fpdt(void) offset += sizeof(*subtable); } return 0; +err_subtable: + kobject_put(fpdt_kobj); + +err_nomem: + acpi_put_table(header); + return result; } fs_initcall(acpi_init_fpdt); diff --git a/drivers/acpi/acpi_lpit.c b/drivers/acpi/acpi_lpit.c index c5598b6d5db8b0..794962c5c88e95 100644 --- a/drivers/acpi/acpi_lpit.c +++ b/drivers/acpi/acpi_lpit.c @@ -105,7 +105,7 @@ static void lpit_update_residency(struct lpit_residency_info *info, return; info->frequency = lpit_native->counter_frequency ? - lpit_native->counter_frequency : tsc_khz * 1000; + lpit_native->counter_frequency : mul_u32_u32(tsc_khz, 1000U); if (!info->frequency) info->frequency = 1; diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 539e700de4d289..98a2ab3b684428 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -333,6 +333,7 @@ static const struct lpss_device_desc bsw_i2c_dev_desc = { static const struct property_entry bsw_spi_properties[] = { PROPERTY_ENTRY_U32("intel,spi-pxa2xx-type", LPSS_BSW_SSP), + PROPERTY_ENTRY_U32("num-cs", 2), { } }; @@ -465,8 +466,9 @@ static int register_device_clock(struct acpi_device *adev, if (!clk_name) return -ENOMEM; clk = clk_register_fractional_divider(NULL, clk_name, parent, + 0, prv_base, 1, 15, 16, 15, CLK_FRAC_DIVIDER_POWER_OF_TWO_PS, - prv_base, 1, 15, 16, 15, 0, NULL); + NULL); parent = clk_name; clk_name = kasprintf(GFP_KERNEL, "%s-update", devname); diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c index 7a453c5ff303a9..71e25c79897628 100644 --- a/drivers/acpi/acpi_pad.c +++ b/drivers/acpi/acpi_pad.c @@ -131,8 +131,10 @@ static void exit_round_robin(unsigned int tsk_index) { struct cpumask *pad_busy_cpus = to_cpumask(pad_busy_cpus_bits); - cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus); - tsk_in_cpu[tsk_index] = -1; + if (tsk_in_cpu[tsk_index] != -1) { + cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus); + tsk_in_cpu[tsk_index] = -1; + } } static unsigned int idle_pct = 5; /* percentage */ diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index 0f5218e361df5c..7053f1b9fc1ddc 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -415,7 +415,7 @@ static int acpi_processor_add(struct acpi_device *device, result = acpi_processor_get_info(device); if (result) /* Processor is not physically present or unavailable */ - return 0; + goto err_clear_driver_data; BUG_ON(pr->id >= nr_cpu_ids); @@ -430,7 +430,7 @@ static int acpi_processor_add(struct acpi_device *device, "BIOS reported wrong ACPI id %d for the processor\n", pr->id); /* Give up, but do not abort the namespace scan. */ - goto err; + goto err_clear_driver_data; } /* * processor_device_array is not cleared on errors to allow buggy BIOS @@ -442,12 +442,12 @@ static int acpi_processor_add(struct acpi_device *device, dev = get_cpu_device(pr->id); if (!dev) { result = -ENODEV; - goto err; + goto err_clear_per_cpu; } result = acpi_bind_one(dev, device); if (result) - goto err; + goto err_clear_per_cpu; pr->dev = dev; @@ -458,10 +458,11 @@ static int acpi_processor_add(struct acpi_device *device, dev_err(dev, "Processor driver could not be attached\n"); acpi_unbind_one(dev); - err: - free_cpumask_var(pr->throttling.shared_cpu_map); - device->driver_data = NULL; + err_clear_per_cpu: per_cpu(processors, pr->id) = NULL; + err_clear_driver_data: + device->driver_data = NULL; + free_cpumask_var(pr->throttling.shared_cpu_map); err_free_pr: kfree(pr); return result; diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index b411948594ff89..a971770e24ff90 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -253,8 +253,7 @@ static const struct backlight_ops acpi_backlight_ops = { static int video_get_max_state(struct thermal_cooling_device *cooling_dev, unsigned long *state) { - struct acpi_device *device = cooling_dev->devdata; - struct acpi_video_device *video = acpi_driver_data(device); + struct acpi_video_device *video = cooling_dev->devdata; *state = video->brightness->count - ACPI_VIDEO_FIRST_LEVEL - 1; return 0; @@ -263,8 +262,7 @@ static int video_get_max_state(struct thermal_cooling_device *cooling_dev, static int video_get_cur_state(struct thermal_cooling_device *cooling_dev, unsigned long *state) { - struct acpi_device *device = cooling_dev->devdata; - struct acpi_video_device *video = acpi_driver_data(device); + struct acpi_video_device *video = cooling_dev->devdata; unsigned long long level; int offset; @@ -283,8 +281,7 @@ static int video_get_cur_state(struct thermal_cooling_device *cooling_dev, static int video_set_cur_state(struct thermal_cooling_device *cooling_dev, unsigned long state) { - struct acpi_device *device = cooling_dev->devdata; - struct acpi_video_device *video = acpi_driver_data(device); + struct acpi_video_device *video = cooling_dev->devdata; int level; if (state >= video->brightness->count - ACPI_VIDEO_FIRST_LEVEL) @@ -503,6 +500,15 @@ static const struct dmi_system_id video_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 3350"), }, }, + { + .callback = video_set_report_key_events, + .driver_data = (void *)((uintptr_t)REPORT_BRIGHTNESS_KEY_EVENTS), + .ident = "COLORFUL X15 AT 23", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "COLORFUL"), + DMI_MATCH(DMI_PRODUCT_NAME, "X15 AT 23"), + }, + }, /* * Some machines change the brightness themselves when a brightness * hotkey gets pressed, despite us telling them not to. In this case @@ -1125,7 +1131,6 @@ static int acpi_video_bus_get_one_device(struct acpi_device *device, void *arg) strcpy(acpi_device_name(device), ACPI_VIDEO_DEVICE_NAME); strcpy(acpi_device_class(device), ACPI_VIDEO_CLASS); - device->driver_data = data; data->device_id = device_id; data->video = video; @@ -1717,12 +1722,12 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device) return; count++; - acpi_get_parent(device->dev->handle, &acpi_parent); - - pdev = acpi_get_pci_dev(acpi_parent); - if (pdev) { - parent = &pdev->dev; - pci_dev_put(pdev); + if (ACPI_SUCCESS(acpi_get_parent(device->dev->handle, &acpi_parent))) { + pdev = acpi_get_pci_dev(acpi_parent); + if (pdev) { + parent = &pdev->dev; + pci_dev_put(pdev); + } } memset(&props, 0, sizeof(struct backlight_properties)); @@ -1747,8 +1752,8 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device) device->backlight->props.brightness = acpi_video_get_brightness(device->backlight); - device->cooling_dev = thermal_cooling_device_register("LCD", - device->dev, &video_cooling_ops); + device->cooling_dev = thermal_cooling_device_register("LCD", device, + &video_cooling_ops); if (IS_ERR(device->cooling_dev)) { /* * Set cooling_dev to NULL so we don't crash trying to free it. @@ -2031,7 +2036,7 @@ static int acpi_video_bus_add(struct acpi_device *device) * HP ZBook Fury 16 G10 requires ACPI video's child devices have _PS0 * evaluated to have functional panel brightness control. */ - acpi_device_fix_up_power_extended(device); + acpi_device_fix_up_power_children(device); pr_info("%s [%s] (multi-head: %s rom: %s post: %s)\n", ACPI_VIDEO_DEVICE_NAME, acpi_device_bid(device), diff --git a/drivers/acpi/acpica/Makefile b/drivers/acpi/acpica/Makefile index 30f3fc13c29d12..8d18af396de92c 100644 --- a/drivers/acpi/acpica/Makefile +++ b/drivers/acpi/acpica/Makefile @@ -5,6 +5,7 @@ ccflags-y := -D_LINUX -DBUILDING_ACPICA ccflags-$(CONFIG_ACPI_DEBUG) += -DACPI_DEBUG_OUTPUT +CFLAGS_tbfind.o += $(call cc-disable-warning, stringop-truncation) # use acpi.o to put all files here into acpi.o modparam namespace obj-y += acpi.o diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index ddd072cbc738d4..1c5218b79fc2ac 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -188,7 +188,7 @@ acpi_ev_detach_region(union acpi_operand_object *region_obj, u8 acpi_ns_is_locked); void -acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, +acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth, acpi_adr_space_type space_id, u32 function); acpi_status diff --git a/drivers/acpi/acpica/dbconvert.c b/drivers/acpi/acpica/dbconvert.c index 2b84ac093698a3..8dbab693204998 100644 --- a/drivers/acpi/acpica/dbconvert.c +++ b/drivers/acpi/acpica/dbconvert.c @@ -174,6 +174,8 @@ acpi_status acpi_db_convert_to_package(char *string, union acpi_object *object) elements = ACPI_ALLOCATE_ZEROED(DB_DEFAULT_PKG_ELEMENTS * sizeof(union acpi_object)); + if (!elements) + return (AE_NO_MEMORY); this = string; for (i = 0; i < (DB_DEFAULT_PKG_ELEMENTS - 1); i++) { diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c index b91155ea9c343c..c9131259f717b0 100644 --- a/drivers/acpi/acpica/dbnames.c +++ b/drivers/acpi/acpica/dbnames.c @@ -550,8 +550,12 @@ acpi_db_walk_for_fields(acpi_handle obj_handle, ACPI_FREE(buffer.pointer); buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER; - acpi_evaluate_object(obj_handle, NULL, NULL, &buffer); - + status = acpi_evaluate_object(obj_handle, NULL, NULL, &buffer); + if (ACPI_FAILURE(status)) { + acpi_os_printf("Could Not evaluate object %p\n", + obj_handle); + return (AE_OK); + } /* * Since this is a field unit, surround the output in braces */ diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index 18fdf2bc2d499a..cf53b9535f18e0 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -65,6 +65,7 @@ acpi_status acpi_ev_initialize_op_regions(void) acpi_gbl_default_address_spaces [i])) { acpi_ev_execute_reg_methods(acpi_gbl_root_node, + ACPI_UINT32_MAX, acpi_gbl_default_address_spaces [i], ACPI_REG_CONNECT); } @@ -672,6 +673,7 @@ acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function) * FUNCTION: acpi_ev_execute_reg_methods * * PARAMETERS: node - Namespace node for the device + * max_depth - Depth to which search for _REG * space_id - The address space ID * function - Passed to _REG: On (1) or Off (0) * @@ -683,7 +685,7 @@ acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function) ******************************************************************************/ void -acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, +acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth, acpi_adr_space_type space_id, u32 function) { struct acpi_reg_walk_info info; @@ -717,7 +719,7 @@ acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, * regions and _REG methods. (i.e. handlers must be installed for all * regions of this Space ID before we can run any _REG methods) */ - (void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, ACPI_UINT32_MAX, + (void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, max_depth, ACPI_NS_WALK_UNLOCK, acpi_ev_reg_run, NULL, &info, NULL); diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 3197e6303c5b08..95f78383bbdba1 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -85,7 +85,8 @@ acpi_install_address_space_handler_internal(acpi_handle device, /* Run all _REG methods for this address space */ if (run_reg) { - acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT); + acpi_ev_execute_reg_methods(node, ACPI_UINT32_MAX, space_id, + ACPI_REG_CONNECT); } unlock_and_exit: @@ -263,6 +264,7 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler) * FUNCTION: acpi_execute_reg_methods * * PARAMETERS: device - Handle for the device + * max_depth - Depth to which search for _REG * space_id - The address space ID * * RETURN: Status @@ -271,7 +273,8 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler) * ******************************************************************************/ acpi_status -acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id) +acpi_execute_reg_methods(acpi_handle device, u32 max_depth, + acpi_adr_space_type space_id) { struct acpi_namespace_node *node; acpi_status status; @@ -296,7 +299,8 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id) /* Run all _REG methods for this address space */ - acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT); + acpi_ev_execute_reg_methods(node, max_depth, space_id, + ACPI_REG_CONNECT); } else { status = AE_BAD_PARAMETER; } diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c index 08196fa17080e2..82b1fa2d201fed 100644 --- a/drivers/acpi/acpica/exprep.c +++ b/drivers/acpi/acpica/exprep.c @@ -437,6 +437,9 @@ acpi_status acpi_ex_prep_field_value(struct acpi_create_field_info *info) if (info->connection_node) { second_desc = info->connection_node->object; + if (second_desc == NULL) { + break; + } if (!(second_desc->common.flags & AOPOBJ_DATA_VALID)) { status = acpi_ds_get_buffer_arguments(second_desc); diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c index 8907b8bf42672a..c49b9f8de723d8 100644 --- a/drivers/acpi/acpica/exregion.c +++ b/drivers/acpi/acpica/exregion.c @@ -44,7 +44,6 @@ acpi_ex_system_memory_space_handler(u32 function, struct acpi_mem_mapping *mm = mem_info->cur_mm; u32 length; acpi_size map_length; - acpi_size page_boundary_map_length; #ifdef ACPI_MISALIGNMENT_NOT_SUPPORTED u32 remainder; #endif @@ -138,26 +137,8 @@ acpi_ex_system_memory_space_handler(u32 function, map_length = (acpi_size) ((mem_info->address + mem_info->length) - address); - /* - * If mapping the entire remaining portion of the region will cross - * a page boundary, just map up to the page boundary, do not cross. - * On some systems, crossing a page boundary while mapping regions - * can cause warnings if the pages have different attributes - * due to resource management. - * - * This has the added benefit of constraining a single mapping to - * one page, which is similar to the original code that used a 4k - * maximum window. - */ - page_boundary_map_length = (acpi_size) - (ACPI_ROUND_UP(address, ACPI_DEFAULT_PAGE_SIZE) - address); - if (page_boundary_map_length == 0) { - page_boundary_map_length = ACPI_DEFAULT_PAGE_SIZE; - } - - if (map_length > page_boundary_map_length) { - map_length = page_boundary_map_length; - } + if (map_length > ACPI_DEFAULT_PAGE_SIZE) + map_length = ACPI_DEFAULT_PAGE_SIZE; /* Create a new mapping starting at the address given */ diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c index 422c074ed2897b..28582adfc0acaf 100644 --- a/drivers/acpi/acpica/psargs.c +++ b/drivers/acpi/acpica/psargs.c @@ -25,6 +25,8 @@ acpi_ps_get_next_package_length(struct acpi_parse_state *parser_state); static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state *parser_state); +static void acpi_ps_free_field_list(union acpi_parse_object *start); + /******************************************************************************* * * FUNCTION: acpi_ps_get_next_package_length @@ -683,6 +685,39 @@ static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state return_PTR(field); } +/******************************************************************************* + * + * FUNCTION: acpi_ps_free_field_list + * + * PARAMETERS: start - First Op in field list + * + * RETURN: None. + * + * DESCRIPTION: Free all Op objects inside a field list. + * + ******************************************************************************/ + +static void acpi_ps_free_field_list(union acpi_parse_object *start) +{ + union acpi_parse_object *cur = start; + union acpi_parse_object *next; + union acpi_parse_object *arg; + + while (cur) { + next = cur->common.next; + + /* AML_INT_CONNECTION_OP can have a single argument */ + + arg = acpi_ps_get_arg(cur, 0); + if (arg) { + acpi_ps_free_op(arg); + } + + acpi_ps_free_op(cur); + cur = next; + } +} + /******************************************************************************* * * FUNCTION: acpi_ps_get_next_arg @@ -751,6 +786,10 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state, while (parser_state->aml < parser_state->pkg_end) { field = acpi_ps_get_next_field(parser_state); if (!field) { + if (arg) { + acpi_ps_free_field_list(arg); + } + return_ACPI_STATUS(AE_NO_MEMORY); } @@ -820,6 +859,10 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state, acpi_ps_get_next_namepath(walk_state, parser_state, arg, ACPI_NOT_METHOD_CALL); + if (ACPI_FAILURE(status)) { + acpi_ps_free_op(arg); + return_ACPI_STATUS(status); + } } else { /* Single complex argument, nothing returned */ @@ -854,6 +897,10 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state, acpi_ps_get_next_namepath(walk_state, parser_state, arg, ACPI_POSSIBLE_METHOD_CALL); + if (ACPI_FAILURE(status)) { + acpi_ps_free_op(arg); + return_ACPI_STATUS(status); + } if (arg->common.aml_opcode == AML_INT_METHODCALL_OP) { diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index ef59d6ea16da0f..ab2a82cb1b0b48 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -101,6 +101,20 @@ static inline bool is_hest_type_generic_v2(struct ghes *ghes) return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2; } +/* + * A platform may describe one error source for the handling of synchronous + * errors (e.g. MCE or SEA), or for handling asynchronous errors (e.g. SCI + * or External Interrupt). On x86, the HEST notifications are always + * asynchronous, so only SEA on ARM is delivered as a synchronous + * notification. + */ +static inline bool is_hest_sync_notify(struct ghes *ghes) +{ + u8 notify_type = ghes->generic->notify.type; + + return notify_type == ACPI_HEST_NOTIFY_SEA; +} + /* * This driver isn't really modular, however for the time being, * continuing to use module_param is the easiest way to remain @@ -209,6 +223,20 @@ int ghes_estatus_pool_init(unsigned int num_ghes) return -ENOMEM; } +/** + * ghes_estatus_pool_region_free - free previously allocated memory + * from the ghes_estatus_pool. + * @addr: address of memory to free. + * @size: size of memory to free. + * + * Returns none. + */ +void ghes_estatus_pool_region_free(unsigned long addr, u32 size) +{ + gen_pool_free(ghes_estatus_pool, addr, size); +} +EXPORT_SYMBOL_GPL(ghes_estatus_pool_region_free); + static int map_gen_v2(struct ghes *ghes) { return apei_map_generic_address(&ghes->generic_v2->read_ack_register); @@ -475,7 +503,7 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags) } static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, - int sev) + int sev, bool sync) { int flags = -1; int sec_sev = ghes_severity(gdata->error_severity); @@ -489,7 +517,7 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED)) flags = MF_SOFT_OFFLINE; if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE) - flags = 0; + flags = sync ? MF_ACTION_REQUIRED : 0; if (flags != -1) return ghes_do_memory_failure(mem_err->physical_addr, flags); @@ -497,9 +525,11 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, return false; } -static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev) +static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, + int sev, bool sync) { struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata); + int flags = sync ? MF_ACTION_REQUIRED : 0; bool queued = false; int sec_sev, i; char *p; @@ -524,7 +554,7 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int s * and don't filter out 'corrected' error here. */ if (is_cache && has_pa) { - queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0); + queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags); p += err_info->length; continue; } @@ -564,6 +594,7 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata) pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) { unsigned int devfn; int aer_severity; + u8 *aer_info; devfn = PCI_DEVFN(pcie_err->device_id.device, pcie_err->device_id.function); @@ -577,11 +608,17 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata) if (gdata->flags & CPER_SEC_RESET) aer_severity = AER_FATAL; + aer_info = (void *)gen_pool_alloc(ghes_estatus_pool, + sizeof(struct aer_capability_regs)); + if (!aer_info) + return; + memcpy(aer_info, pcie_err->aer_info, sizeof(struct aer_capability_regs)); + aer_recover_queue(pcie_err->device_id.segment, pcie_err->device_id.bus, devfn, aer_severity, (struct aer_capability_regs *) - pcie_err->aer_info); + aer_info); } #endif } @@ -645,6 +682,7 @@ static bool ghes_do_proc(struct ghes *ghes, const guid_t *fru_id = &guid_null; char *fru_text = ""; bool queued = false; + bool sync = is_hest_sync_notify(ghes); sev = ghes_severity(estatus->error_severity); apei_estatus_for_each_section(estatus, gdata) { @@ -662,13 +700,13 @@ static bool ghes_do_proc(struct ghes *ghes, atomic_notifier_call_chain(&ghes_report_chain, sev, mem_err); arch_apei_report_mem_error(sev, mem_err); - queued = ghes_handle_memory_failure(gdata, sev); + queued = ghes_handle_memory_failure(gdata, sev, sync); } else if (guid_equal(sec_type, &CPER_SEC_PCIE)) { ghes_handle_aer(gdata); } else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) { - queued = ghes_handle_arm_hw_error(gdata, sev); + queued = ghes_handle_arm_hw_error(gdata, sev, sync); } else { void *err = acpi_hest_get_payload(gdata); diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index 969bf81e8d546a..e3cbaf3c3bbc15 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -678,12 +678,18 @@ static ssize_t acpi_battery_alarm_store(struct device *dev, return count; } -static const struct device_attribute alarm_attr = { +static struct device_attribute alarm_attr = { .attr = {.name = "alarm", .mode = 0644}, .show = acpi_battery_alarm_show, .store = acpi_battery_alarm_store, }; +static struct attribute *acpi_battery_attrs[] = { + &alarm_attr.attr, + NULL +}; +ATTRIBUTE_GROUPS(acpi_battery); + /* * The Battery Hooking API * @@ -697,28 +703,35 @@ static LIST_HEAD(acpi_battery_list); static LIST_HEAD(battery_hook_list); static DEFINE_MUTEX(hook_mutex); -static void __battery_hook_unregister(struct acpi_battery_hook *hook, int lock) +static void battery_hook_unregister_unlocked(struct acpi_battery_hook *hook) { struct acpi_battery *battery; + /* * In order to remove a hook, we first need to * de-register all the batteries that are registered. */ - if (lock) - mutex_lock(&hook_mutex); list_for_each_entry(battery, &acpi_battery_list, list) { if (!hook->remove_battery(battery->bat, hook)) power_supply_changed(battery->bat); } - list_del(&hook->list); - if (lock) - mutex_unlock(&hook_mutex); + list_del_init(&hook->list); + pr_info("extension unregistered: %s\n", hook->name); } void battery_hook_unregister(struct acpi_battery_hook *hook) { - __battery_hook_unregister(hook, 1); + mutex_lock(&hook_mutex); + /* + * Ignore already unregistered battery hooks. This might happen + * if a battery hook was previously unloaded due to an error when + * adding a new battery. + */ + if (!list_empty(&hook->list)) + battery_hook_unregister_unlocked(hook); + + mutex_unlock(&hook_mutex); } EXPORT_SYMBOL_GPL(battery_hook_unregister); @@ -727,7 +740,6 @@ void battery_hook_register(struct acpi_battery_hook *hook) struct acpi_battery *battery; mutex_lock(&hook_mutex); - INIT_LIST_HEAD(&hook->list); list_add(&hook->list, &battery_hook_list); /* * Now that the driver is registered, we need @@ -744,7 +756,7 @@ void battery_hook_register(struct acpi_battery_hook *hook) * hooks. */ pr_err("extension failed to load: %s", hook->name); - __battery_hook_unregister(hook, 0); + battery_hook_unregister_unlocked(hook); goto end; } @@ -783,7 +795,7 @@ static void battery_hook_add_battery(struct acpi_battery *battery) */ pr_err("error in extension, unloading: %s", hook_node->name); - __battery_hook_unregister(hook_node, 0); + battery_hook_unregister_unlocked(hook_node); } } mutex_unlock(&hook_mutex); @@ -816,14 +828,17 @@ static void __exit battery_hook_exit(void) * need to remove the hooks. */ list_for_each_entry_safe(hook, ptr, &battery_hook_list, list) { - __battery_hook_unregister(hook, 1); + battery_hook_unregister(hook); } mutex_destroy(&hook_mutex); } static int sysfs_add_battery(struct acpi_battery *battery) { - struct power_supply_config psy_cfg = { .drv_data = battery, }; + struct power_supply_config psy_cfg = { + .drv_data = battery, + .attr_grp = acpi_battery_groups, + }; bool full_cap_broken = false; if (!ACPI_BATTERY_CAPACITY_VALID(battery->full_charge_capacity) && @@ -868,7 +883,7 @@ static int sysfs_add_battery(struct acpi_battery *battery) return result; } battery_hook_add_battery(battery); - return device_create_file(&battery->bat->dev, &alarm_attr); + return 0; } static void sysfs_remove_battery(struct acpi_battery *battery) @@ -879,7 +894,6 @@ static void sysfs_remove_battery(struct acpi_battery *battery) return; } battery_hook_remove_battery(battery); - device_remove_file(&battery->bat->dev, &alarm_attr); power_supply_unregister(battery->bat); battery->bat = NULL; mutex_unlock(&battery->sysfs_lock); diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 7ff269a78c2088..7aced0b9bad7cc 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -100,6 +100,11 @@ static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr); (cpc)->cpc_entry.reg.space_id == \ ACPI_ADR_SPACE_PLATFORM_COMM) +/* Check if a CPC register is in FFH */ +#define CPC_IN_FFH(cpc) ((cpc)->type == ACPI_TYPE_BUFFER && \ + (cpc)->cpc_entry.reg.space_id == \ + ACPI_ADR_SPACE_FIXED_HARDWARE) + /* Check if a CPC register is in SystemMemory */ #define CPC_IN_SYSTEM_MEMORY(cpc) ((cpc)->type == ACPI_TYPE_BUFFER && \ (cpc)->cpc_entry.reg.space_id == \ @@ -163,6 +168,16 @@ show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, nominal_freq); show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, reference_perf); show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, wraparound_time); +/* Check for valid access_width, otherwise, fallback to using bit_width */ +#define GET_BIT_WIDTH(reg) ((reg)->access_width ? (8 << ((reg)->access_width - 1)) : (reg)->bit_width) + +/* Shift and apply the mask for CPC reads/writes */ +#define MASK_VAL_READ(reg, val) (((val) >> (reg)->bit_offset) & \ + GENMASK(((reg)->bit_width) - 1, 0)) +#define MASK_VAL_WRITE(reg, prev_val, val) \ + ((((val) & GENMASK(((reg)->bit_width) - 1, 0)) << (reg)->bit_offset) | \ + ((prev_val) & ~(GENMASK(((reg)->bit_width) - 1, 0) << (reg)->bit_offset))) \ + static ssize_t show_feedback_ctrs(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -777,6 +792,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) } else if (gas_t->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { if (gas_t->address) { void __iomem *addr; + size_t access_width; if (!osc_cpc_flexible_adr_space_confirmed) { pr_debug("Flexible address space capability not supported\n"); @@ -784,7 +800,8 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) goto out_free; } - addr = ioremap(gas_t->address, gas_t->bit_width/8); + access_width = GET_BIT_WIDTH(gas_t) / 8; + addr = ioremap(gas_t->address, access_width); if (!addr) goto out_free; cpc_ptr->cpc_regs[i-2].sys_mem_vaddr = addr; @@ -843,6 +860,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) /* Store CPU Logical ID */ cpc_ptr->cpu_id = pr->id; + spin_lock_init(&cpc_ptr->rmw_lock); /* Parse PSD data for this CPU */ ret = acpi_get_psd(cpc_ptr, handle); @@ -980,6 +998,7 @@ int __weak cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val) static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) { void __iomem *vaddr = NULL; + int size; int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); struct cpc_reg *reg = ®_res->cpc_entry.reg; @@ -989,14 +1008,14 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) } *val = 0; + size = GET_BIT_WIDTH(reg); if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { - u32 width = 8 << (reg->access_width - 1); u32 val_u32; acpi_status status; status = acpi_os_read_port((acpi_io_address)reg->address, - &val_u32, width); + &val_u32, size); if (ACPI_FAILURE(status)) { pr_debug("Error: Failed to read SystemIO port %llx\n", reg->address); @@ -1005,17 +1024,24 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) *val = val_u32; return 0; - } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) { + /* + * For registers in PCC space, the register size is determined + * by the bit width field; the access size is used to indicate + * the PCC subspace id. + */ + size = reg->bit_width; vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id); + } else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) vaddr = reg_res->sys_mem_vaddr; else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) return cpc_read_ffh(cpu, reg, val); else return acpi_os_read_memory((acpi_physical_address)reg->address, - val, reg->bit_width); + val, size); - switch (reg->bit_width) { + switch (size) { case 8: *val = readb_relaxed(vaddr); break; @@ -1029,27 +1055,39 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) *val = readq_relaxed(vaddr); break; default: - pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n", - reg->bit_width, pcc_ss_id); + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { + pr_debug("Error: Cannot read %u bit width from system memory: 0x%llx\n", + size, reg->address); + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) { + pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n", + size, pcc_ss_id); + } return -EFAULT; } + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) + *val = MASK_VAL_READ(reg, *val); + return 0; } static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) { int ret_val = 0; + int size; + u64 prev_val; void __iomem *vaddr = NULL; int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); struct cpc_reg *reg = ®_res->cpc_entry.reg; + struct cpc_desc *cpc_desc; + + size = GET_BIT_WIDTH(reg); if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { - u32 width = 8 << (reg->access_width - 1); acpi_status status; status = acpi_os_write_port((acpi_io_address)reg->address, - (u32)val, width); + (u32)val, size); if (ACPI_FAILURE(status)) { pr_debug("Error: Failed to write SystemIO port %llx\n", reg->address); @@ -1057,17 +1095,53 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) } return 0; - } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) { + /* + * For registers in PCC space, the register size is determined + * by the bit width field; the access size is used to indicate + * the PCC subspace id. + */ + size = reg->bit_width; vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id); + } else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) vaddr = reg_res->sys_mem_vaddr; else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) return cpc_write_ffh(cpu, reg, val); else return acpi_os_write_memory((acpi_physical_address)reg->address, - val, reg->bit_width); + val, size); + + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { + cpc_desc = per_cpu(cpc_desc_ptr, cpu); + if (!cpc_desc) { + pr_debug("No CPC descriptor for CPU:%d\n", cpu); + return -ENODEV; + } + + spin_lock(&cpc_desc->rmw_lock); + switch (size) { + case 8: + prev_val = readb_relaxed(vaddr); + break; + case 16: + prev_val = readw_relaxed(vaddr); + break; + case 32: + prev_val = readl_relaxed(vaddr); + break; + case 64: + prev_val = readq_relaxed(vaddr); + break; + default: + spin_unlock(&cpc_desc->rmw_lock); + return -EFAULT; + } + val = MASK_VAL_WRITE(reg, prev_val, val); + val |= prev_val; + } - switch (reg->bit_width) { + switch (size) { case 8: writeb_relaxed(val, vaddr); break; @@ -1081,12 +1155,20 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) writeq_relaxed(val, vaddr); break; default: - pr_debug("Error: Cannot write %u bit width to PCC for ss: %d\n", - reg->bit_width, pcc_ss_id); + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { + pr_debug("Error: Cannot write %u bit width to system memory: 0x%llx\n", + size, reg->address); + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) { + pr_debug("Error: Cannot write %u bit width to PCC for ss: %d\n", + size, pcc_ss_id); + } ret_val = -EFAULT; break; } + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) + spin_unlock(&cpc_desc->rmw_lock); + return ret_val; } @@ -1154,6 +1236,19 @@ int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf) return cppc_get_perf(cpunum, NOMINAL_PERF, nominal_perf); } +/** + * cppc_get_highest_perf - Get the highest performance register value. + * @cpunum: CPU from which to get highest performance. + * @highest_perf: Return address. + * + * Return: 0 for success, -EIO otherwise. + */ +int cppc_get_highest_perf(int cpunum, u64 *highest_perf) +{ + return cppc_get_perf(cpunum, HIGHEST_PERF, highest_perf); +} +EXPORT_SYMBOL_GPL(cppc_get_highest_perf); + /** * cppc_get_epp_perf - Get the epp register value. * @cpunum: CPU from which to get epp preference value. @@ -1424,9 +1519,12 @@ int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable) /* after writing CPC, transfer the ownership of PCC to platform */ ret = send_pcc_cmd(pcc_ss_id, CMD_WRITE); up_write(&pcc_ss_data->pcc_lock); + } else if (osc_cpc_flexible_adr_space_confirmed && + CPC_SUPPORTED(epp_set_reg) && CPC_IN_FFH(epp_set_reg)) { + ret = cpc_write(cpu, epp_set_reg, perf_ctrls->energy_perf); } else { ret = -ENOTSUPP; - pr_debug("_CPC in PCC is not supported\n"); + pr_debug("_CPC in PCC and _CPC in FFH are not supported\n"); } return ret; diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index f007116a842762..3b4d048c494173 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -397,6 +397,19 @@ void acpi_device_fix_up_power_extended(struct acpi_device *adev) } EXPORT_SYMBOL_GPL(acpi_device_fix_up_power_extended); +/** + * acpi_device_fix_up_power_children - Force a device's children into D0. + * @adev: Parent device object whose children's power state is to be fixed up. + * + * Call acpi_device_fix_up_power() for @adev's children so long as they + * are reported as present and enabled. + */ +void acpi_device_fix_up_power_children(struct acpi_device *adev) +{ + acpi_dev_for_each_child(adev, fix_up_power_if_applicable, NULL); +} +EXPORT_SYMBOL_GPL(acpi_device_fix_up_power_children); + int acpi_device_update_power(struct acpi_device *device, int *state_p) { int state; diff --git a/drivers/acpi/device_sysfs.c b/drivers/acpi/device_sysfs.c index b9bbf074619921..6ed5e9e56be2f4 100644 --- a/drivers/acpi/device_sysfs.c +++ b/drivers/acpi/device_sysfs.c @@ -158,8 +158,8 @@ static int create_pnp_modalias(const struct acpi_device *acpi_dev, char *modalia return 0; len = snprintf(modalias, size, "acpi:"); - if (len <= 0) - return len; + if (len >= size) + return -ENOMEM; size -= len; @@ -212,8 +212,10 @@ static int create_of_modalias(const struct acpi_device *acpi_dev, char *modalias len = snprintf(modalias, size, "of:N%sT", (char *)buf.pointer); ACPI_FREE(buf.pointer); - if (len <= 0) - return len; + if (len >= size) + return -ENOMEM; + + size -= len; of_compatible = acpi_dev->data.of_compatible; if (of_compatible->type == ACPI_TYPE_PACKAGE) { @@ -542,8 +544,9 @@ int acpi_device_setup_files(struct acpi_device *dev) * If device has _STR, 'description' file is created */ if (acpi_has_method(dev->handle, "_STR")) { - status = acpi_evaluate_object(dev->handle, "_STR", - NULL, &buffer); + status = acpi_evaluate_object_typed(dev->handle, "_STR", + NULL, &buffer, + ACPI_TYPE_BUFFER); if (ACPI_FAILURE(status)) buffer.pointer = NULL; dev->pnp.str_obj = buffer.pointer; diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index c95d0edb0be9e5..115994dfefec1e 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -783,6 +783,9 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec, unsigned long tmp; int ret = 0; + if (t->rdata) + memset(t->rdata, 0, t->rlen); + /* start transaction */ spin_lock_irqsave(&ec->lock, tmp); /* Enable GPE for command processing (IBF=0/OBF=1) */ @@ -819,8 +822,6 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t) if (!ec || (!t) || (t->wlen && !t->wdata) || (t->rlen && !t->rdata)) return -EINVAL; - if (t->rdata) - memset(t->rdata, 0, t->rlen); mutex_lock(&ec->mutex); if (ec->global_lock) { @@ -847,7 +848,7 @@ static int acpi_ec_burst_enable(struct acpi_ec *ec) .wdata = NULL, .rdata = &d, .wlen = 0, .rlen = 1}; - return acpi_ec_transaction(ec, &t); + return acpi_ec_transaction_unlocked(ec, &t); } static int acpi_ec_burst_disable(struct acpi_ec *ec) @@ -857,7 +858,7 @@ static int acpi_ec_burst_disable(struct acpi_ec *ec) .wlen = 0, .rlen = 0}; return (acpi_ec_read_status(ec) & ACPI_EC_FLAG_BURST) ? - acpi_ec_transaction(ec, &t) : 0; + acpi_ec_transaction_unlocked(ec, &t) : 0; } static int acpi_ec_read(struct acpi_ec *ec, u8 address, u8 *data) @@ -873,6 +874,19 @@ static int acpi_ec_read(struct acpi_ec *ec, u8 address, u8 *data) return result; } +static int acpi_ec_read_unlocked(struct acpi_ec *ec, u8 address, u8 *data) +{ + int result; + u8 d; + struct transaction t = {.command = ACPI_EC_COMMAND_READ, + .wdata = &address, .rdata = &d, + .wlen = 1, .rlen = 1}; + + result = acpi_ec_transaction_unlocked(ec, &t); + *data = d; + return result; +} + static int acpi_ec_write(struct acpi_ec *ec, u8 address, u8 data) { u8 wdata[2] = { address, data }; @@ -883,6 +897,16 @@ static int acpi_ec_write(struct acpi_ec *ec, u8 address, u8 data) return acpi_ec_transaction(ec, &t); } +static int acpi_ec_write_unlocked(struct acpi_ec *ec, u8 address, u8 data) +{ + u8 wdata[2] = { address, data }; + struct transaction t = {.command = ACPI_EC_COMMAND_WRITE, + .wdata = wdata, .rdata = NULL, + .wlen = 2, .rlen = 0}; + + return acpi_ec_transaction_unlocked(ec, &t); +} + int ec_read(u8 addr, u8 *val) { int err; @@ -1323,6 +1347,7 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address, struct acpi_ec *ec = handler_context; int result = 0, i, bytes = bits / 8; u8 *value = (u8 *)value64; + u32 glk; if ((address > 0xFF) || !value || !handler_context) return AE_BAD_PARAMETER; @@ -1330,17 +1355,38 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address, if (function != ACPI_READ && function != ACPI_WRITE) return AE_BAD_PARAMETER; + mutex_lock(&ec->mutex); + + if (ec->global_lock) { + acpi_status status; + + status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk); + if (ACPI_FAILURE(status)) { + result = -ENODEV; + goto unlock; + } + } + if (ec->busy_polling || bits > 8) acpi_ec_burst_enable(ec); - for (i = 0; i < bytes; ++i, ++address, ++value) + for (i = 0; i < bytes; ++i, ++address, ++value) { result = (function == ACPI_READ) ? - acpi_ec_read(ec, address, value) : - acpi_ec_write(ec, address, *value); + acpi_ec_read_unlocked(ec, address, value) : + acpi_ec_write_unlocked(ec, address, *value); + if (result < 0) + break; + } if (ec->busy_polling || bits > 8) acpi_ec_burst_disable(ec); + if (ec->global_lock) + acpi_release_global_lock(glk); + +unlock: + mutex_unlock(&ec->mutex); + switch (result) { case -EINVAL: return AE_BAD_PARAMETER; @@ -1348,8 +1394,10 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address, return AE_NOT_FOUND; case -ETIME: return AE_TIME; - default: + case 0: return AE_OK; + default: + return AE_ERROR; } } @@ -1487,8 +1535,10 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, acpi_ec_start(ec, false); if (!test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { + acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle; + acpi_ec_enter_noirq(ec); - status = acpi_install_address_space_handler_no_reg(ec->handle, + status = acpi_install_address_space_handler_no_reg(scope_handle, ACPI_ADR_SPACE_EC, &acpi_ec_space_handler, NULL, ec); @@ -1497,11 +1547,10 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, return -ENODEV; } set_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags); - ec->address_space_handler_holder = ec->handle; } if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) { - acpi_execute_reg_methods(ec->handle, ACPI_ADR_SPACE_EC); + acpi_execute_reg_methods(ec->handle, ACPI_UINT32_MAX, ACPI_ADR_SPACE_EC); set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags); } @@ -1553,10 +1602,13 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, static void ec_remove_handlers(struct acpi_ec *ec) { + acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle; + if (test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { if (ACPI_FAILURE(acpi_remove_address_space_handler( - ec->address_space_handler_holder, - ACPI_ADR_SPACE_EC, &acpi_ec_space_handler))) + scope_handle, + ACPI_ADR_SPACE_EC, + &acpi_ec_space_handler))) pr_err("failed to remove space handler\n"); clear_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags); } @@ -1595,14 +1647,18 @@ static int acpi_ec_setup(struct acpi_ec *ec, struct acpi_device *device, bool ca { int ret; - ret = ec_install_handlers(ec, device, call_reg); - if (ret) - return ret; - /* First EC capable of handling transactions */ if (!first_ec) first_ec = ec; + ret = ec_install_handlers(ec, device, call_reg); + if (ret) { + if (ec == first_ec) + first_ec = NULL; + + return ret; + } + pr_info("EC_CMD/EC_SC=0x%lx, EC_DATA=0x%lx\n", ec->command_addr, ec->data_addr); @@ -1709,6 +1765,12 @@ static void acpi_ec_remove(struct acpi_device *device) } } +void acpi_ec_register_opregions(struct acpi_device *adev) +{ + if (first_ec && first_ec->handle != adev->handle) + acpi_execute_reg_methods(adev->handle, 1, ACPI_ADR_SPACE_EC); +} + static acpi_status ec_parse_io_ports(struct acpi_resource *resource, void *context) { @@ -1924,6 +1986,16 @@ static const struct dmi_system_id ec_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion Gaming Laptop 15-dk1xxx"), }, }, + { + /* + * HP 250 G7 Notebook PC + */ + .callback = ec_honor_dsdt_gpe, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP 250 G7 Notebook PC"), + }, + }, { /* * Samsung hardware diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 866c7c4ed23317..1e8ee97fc85f38 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -167,7 +167,6 @@ enum acpi_ec_event_state { struct acpi_ec { acpi_handle handle; - acpi_handle address_space_handler_holder; int gpe; int irq; unsigned long command_addr; @@ -205,6 +204,7 @@ int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit, acpi_handle handle, acpi_ec_query_func func, void *data); void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit); +void acpi_ec_register_opregions(struct acpi_device *adev); #ifdef CONFIG_PM_SLEEP void acpi_ec_flush_work(void); diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 1f4fc5f8a819d3..a44c0761fd1c06 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -183,7 +183,7 @@ static int __init slit_valid(struct acpi_table_slit *slit) int i, j; int d = slit->locality_count; for (i = 0; i < d; i++) { - for (j = 0; j < d; j++) { + for (j = 0; j < d; j++) { u8 val = slit->entry[d*i + j]; if (i == j) { if (val != LOCAL_DISTANCE) @@ -206,6 +206,11 @@ int __init srat_disabled(void) return acpi_numa < 0; } +__weak int __init numa_fill_memblks(u64 start, u64 end) +{ + return NUMA_NO_MEMBLK; +} + #if defined(CONFIG_X86) || defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) /* * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for @@ -310,11 +315,16 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header, start = cfmws->base_hpa; end = cfmws->base_hpa + cfmws->window_size; - /* Skip if the SRAT already described the NUMA details for this HPA */ - node = phys_to_target_node(start); - if (node != NUMA_NO_NODE) + /* + * The SRAT may have already described NUMA details for all, + * or a portion of, this CFMWS HPA range. Extend the memblks + * found for any portion of the window to cover the entire + * window. + */ + if (!numa_fill_memblks(start, end)) return 0; + /* No SRAT description. Create a new node. */ node = acpi_map_pxm_to_node(*fake_pxm); if (node == NUMA_NO_NODE) { @@ -527,7 +537,7 @@ int __init acpi_numa_init(void) */ /* fake_pxm is the next unused PXM value after SRAT parsing */ - for (i = 0, fake_pxm = -1; i < MAX_NUMNODES - 1; i++) { + for (i = 0, fake_pxm = -1; i < MAX_NUMNODES; i++) { if (node_to_pxm_map[i] > fake_pxm) fake_pxm = node_to_pxm_map[i]; } diff --git a/drivers/acpi/pmic/tps68470_pmic.c b/drivers/acpi/pmic/tps68470_pmic.c index ebd03e4729555a..0d1a82eeb4b0b6 100644 --- a/drivers/acpi/pmic/tps68470_pmic.c +++ b/drivers/acpi/pmic/tps68470_pmic.c @@ -376,10 +376,8 @@ static int tps68470_pmic_opregion_probe(struct platform_device *pdev) struct tps68470_pmic_opregion *opregion; acpi_status status; - if (!dev || !tps68470_regmap) { - dev_warn(dev, "dev or regmap is NULL\n"); - return -EINVAL; - } + if (!tps68470_regmap) + return dev_err_probe(dev, -EINVAL, "regmap is missing\n"); if (!handle) { dev_warn(dev, "acpi handle is NULL\n"); diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 3a34a8c425fe4a..831fa4a1215985 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -16,7 +16,6 @@ #include #include #include /* need_resched() */ -#include #include #include #include @@ -386,25 +385,24 @@ static void acpi_processor_power_verify_c3(struct acpi_processor *pr, acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, 1); } -static int acpi_cst_latency_cmp(const void *a, const void *b) +static void acpi_cst_latency_sort(struct acpi_processor_cx *states, size_t length) { - const struct acpi_processor_cx *x = a, *y = b; + int i, j, k; - if (!(x->valid && y->valid)) - return 0; - if (x->latency > y->latency) - return 1; - if (x->latency < y->latency) - return -1; - return 0; -} -static void acpi_cst_latency_swap(void *a, void *b, int n) -{ - struct acpi_processor_cx *x = a, *y = b; + for (i = 1; i < length; i++) { + if (!states[i].valid) + continue; - if (!(x->valid && y->valid)) - return; - swap(x->latency, y->latency); + for (j = i - 1, k = i; j >= 0; j--) { + if (!states[j].valid) + continue; + + if (states[j].latency > states[k].latency) + swap(states[j].latency, states[k].latency); + + k = j; + } + } } static int acpi_processor_power_verify(struct acpi_processor *pr) @@ -449,10 +447,7 @@ static int acpi_processor_power_verify(struct acpi_processor *pr) if (buggy_latency) { pr_notice("FW issue: working around C-state latencies out of order\n"); - sort(&pr->power.states[1], max_cstate, - sizeof(struct acpi_processor_cx), - acpi_cst_latency_cmp, - acpi_cst_latency_swap); + acpi_cst_latency_sort(&pr->power.states[1], max_cstate); } lapic_timer_propagate_broadcast(pr); @@ -592,7 +587,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) while (1) { if (cx->entry_method == ACPI_CSTATE_HALT) - safe_halt(); + raw_safe_halt(); else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) { io_idle(cx->address); } else @@ -1430,6 +1425,8 @@ int acpi_processor_power_exit(struct acpi_processor *pr) acpi_processor_registered--; if (acpi_processor_registered == 0) cpuidle_unregister_driver(&acpi_idle_driver); + + kfree(dev); } pr->flags.power_setup_done = 0; diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 413e4fcadcaf7b..4d958a165da058 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -851,6 +851,7 @@ static int acpi_get_ref_args(struct fwnode_reference_args *args, * @index: Index of the reference to return * @num_args: Maximum number of arguments after each reference * @args: Location to store the returned reference with optional arguments + * (may be NULL) * * Find property with @name, verifify that it is a package containing at least * one object reference and if so, store the ACPI device object pointer to the @@ -907,6 +908,9 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, if (!device) return -EINVAL; + if (!args) + return 0; + args->fwnode = acpi_fwnode_handle(device); args->nargs = 0; return 0; @@ -1102,25 +1106,26 @@ static int acpi_data_prop_read(const struct acpi_device_data *data, switch (proptype) { case DEV_PROP_STRING: break; - case DEV_PROP_U8 ... DEV_PROP_U64: + default: if (obj->type == ACPI_TYPE_BUFFER) { if (nval > obj->buffer.length) return -EOVERFLOW; - break; + } else { + if (nval > obj->package.count) + return -EOVERFLOW; } - fallthrough; - default: - if (nval > obj->package.count) - return -EOVERFLOW; break; } if (nval == 0) return -EINVAL; - if (obj->type != ACPI_TYPE_BUFFER) - items = obj->package.elements; - else + if (obj->type == ACPI_TYPE_BUFFER) { + if (proptype != DEV_PROP_U8) + return -EPROTO; items = obj; + } else { + items = obj->package.elements; + } switch (proptype) { case DEV_PROP_U8: diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 297a88587031e6..95233b413c1ac5 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -439,6 +439,13 @@ static const struct dmi_system_id asus_laptop[] = { DMI_MATCH(DMI_BOARD_NAME, "S5602ZA"), }, }, + { + /* Asus Vivobook X1704VAP */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "X1704VAP"), + }, + }, { .ident = "Asus ExpertBook B1402CBA", .matches = { @@ -446,6 +453,13 @@ static const struct dmi_system_id asus_laptop[] = { DMI_MATCH(DMI_BOARD_NAME, "B1402CBA"), }, }, + { + /* Asus ExpertBook B1402CVA */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "B1402CVA"), + }, + }, { .ident = "Asus ExpertBook B1502CBA", .matches = { @@ -495,6 +509,38 @@ static const struct dmi_system_id maingear_laptop[] = { DMI_MATCH(DMI_PRODUCT_NAME, "MG-VCP2-15A3070T"), } }, + { + /* Asus ExpertBook B2502CVA */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "B2502CVA"), + }, + }, + { + /* TongFang GMxXGxx/TUXEDO Polaris 15 Gen5 AMD */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxXGxx"), + }, + }, + { + /* TongFang GMxXGxX/TUXEDO Polaris 15 Gen5 AMD */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxXGxX"), + }, + }, + { + /* TongFang GMxXGxx sold as Eluktronics Inc. RP-15 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Eluktronics Inc."), + DMI_MATCH(DMI_BOARD_NAME, "RP-15"), + }, + }, + { + /* TongFang GM6XGxX/TUXEDO Stellaris 16 Gen5 AMD */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GM6XGxX"), + }, + }, { .ident = "MAINGEAR Vector Pro 2 17", .matches = { @@ -524,6 +570,39 @@ static const struct dmi_system_id pcspecialist_laptop[] = { DMI_MATCH(DMI_BOARD_NAME, "GM6BG0Q"), }, }, + { + /* Infinity E15-5A165-BM */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GM5RG1E0009COM"), + }, + }, + { + /* Infinity E15-5A305-1M */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GM5RGEE0016COM"), + }, + }, + { + /* Lunnen Ground 15 / AMD Ryzen 5 5500U */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Lunnen"), + DMI_MATCH(DMI_BOARD_NAME, "LLL5DAW"), + }, + }, + { + /* Lunnen Ground 16 / AMD Ryzen 7 5800U */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Lunnen"), + DMI_MATCH(DMI_BOARD_NAME, "LL6FA"), + }, + }, + { + /* MAIBENBEN X577 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MAIBENBEN"), + DMI_MATCH(DMI_BOARD_NAME, "X577"), + }, + }, { } }; @@ -535,6 +614,18 @@ static const struct dmi_system_id lg_laptop[] = { DMI_MATCH(DMI_BOARD_NAME, "17U70P"), }, }, + { + /* TongFang GXxHRXx/TUXEDO InfinityBook Pro Gen9 AMD */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GXxHRXx"), + }, + }, + { + /* TongFang GMxHGxx/TUXEDO Stellaris Slim Gen1 AMD */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxHGxx"), + }, + }, { } }; diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index 94e3c000df2e16..fdeb46ed21d69f 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -77,7 +77,6 @@ struct acpi_battery { u16 spec; u8 id; u8 present:1; - u8 have_sysfs_alarm:1; }; #define to_acpi_battery(x) power_supply_get_drvdata(x) @@ -462,12 +461,18 @@ static ssize_t acpi_battery_alarm_store(struct device *dev, return count; } -static const struct device_attribute alarm_attr = { +static struct device_attribute alarm_attr = { .attr = {.name = "alarm", .mode = 0644}, .show = acpi_battery_alarm_show, .store = acpi_battery_alarm_store, }; +static struct attribute *acpi_battery_attrs[] = { + &alarm_attr.attr, + NULL +}; +ATTRIBUTE_GROUPS(acpi_battery); + /* -------------------------------------------------------------------------- Driver Interface -------------------------------------------------------------------------- */ @@ -518,7 +523,10 @@ static int acpi_battery_read(struct acpi_battery *battery) static int acpi_battery_add(struct acpi_sbs *sbs, int id) { struct acpi_battery *battery = &sbs->battery[id]; - struct power_supply_config psy_cfg = { .drv_data = battery, }; + struct power_supply_config psy_cfg = { + .drv_data = battery, + .attr_grp = acpi_battery_groups, + }; int result; battery->id = id; @@ -548,10 +556,6 @@ static int acpi_battery_add(struct acpi_sbs *sbs, int id) goto end; } - result = device_create_file(&battery->bat->dev, &alarm_attr); - if (result) - goto end; - battery->have_sysfs_alarm = 1; end: pr_info("%s [%s]: Battery Slot [%s] (battery %s)\n", ACPI_SBS_DEVICE_NAME, acpi_device_bid(sbs->device), @@ -563,11 +567,8 @@ static void acpi_battery_remove(struct acpi_sbs *sbs, int id) { struct acpi_battery *battery = &sbs->battery[id]; - if (battery->bat) { - if (battery->have_sysfs_alarm) - device_remove_file(&battery->bat->dev, &alarm_attr); + if (battery->bat) power_supply_unregister(battery->bat); - } } static int acpi_charger_add(struct acpi_sbs *sbs) diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 691d4b7686ee7e..c0c5c5c58ae1e7 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -314,18 +314,14 @@ static int acpi_scan_device_check(struct acpi_device *adev) * again). */ if (adev->handler) { - dev_warn(&adev->dev, "Already enumerated\n"); - return -EALREADY; + dev_dbg(&adev->dev, "Already enumerated\n"); + return 0; } error = acpi_bus_scan(adev->handle); if (error) { dev_warn(&adev->dev, "Namespace scan failure\n"); return error; } - if (!adev->handler) { - dev_warn(&adev->dev, "Enumeration failure\n"); - error = -ENODEV; - } } else { error = acpi_scan_device_not_present(adev); } @@ -1568,17 +1564,22 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev, int err; const struct iommu_ops *ops; + /* Serialise to make dev->iommu stable under our potential fwspec */ + mutex_lock(&iommu_probe_device_lock); /* * If we already translated the fwspec there is nothing left to do, * return the iommu_ops. */ ops = acpi_iommu_fwspec_ops(dev); - if (ops) + if (ops) { + mutex_unlock(&iommu_probe_device_lock); return ops; + } err = iort_iommu_configure_id(dev, id_in); if (err && err != -EPROBE_DEFER) err = viot_iommu_configure(dev); + mutex_unlock(&iommu_probe_device_lock); /* * If we have reason to believe the IOMMU driver missed the initial @@ -1797,7 +1798,8 @@ static void acpi_scan_dep_init(struct acpi_device *adev) if (dep->honor_dep) adev->flags.honor_deps = 1; - adev->dep_unmet++; + if (!dep->met) + adev->dep_unmet++; } } } @@ -2196,6 +2198,8 @@ static int acpi_bus_attach(struct acpi_device *device, void *first_pass) if (device->handler) goto ok; + acpi_ec_register_opregions(device); + if (!device->flags.initialized) { device->flags.power_manageable = device->power.states[ACPI_STATE_D0].flags.valid; diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 808484d1120976..728acfeb774d83 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -385,18 +385,6 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "20GGA00L00"), }, }, - /* - * ASUS B1400CEAE hangs on resume from suspend (see - * https://bugzilla.kernel.org/show_bug.cgi?id=215742). - */ - { - .callback = init_default_s3, - .ident = "ASUS B1400CEAE", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK B1400CEAE"), - }, - }, {}, }; diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index 312730f8272eec..8263508415a8d0 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -778,9 +778,9 @@ static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz) static void acpi_thermal_unregister_thermal_zone(struct acpi_thermal *tz) { + thermal_zone_device_disable(tz->thermal_zone); acpi_thermal_zone_sysfs_remove(tz); thermal_zone_device_unregister(tz->thermal_zone); - kfree(tz->trip_table); tz->thermal_zone = NULL; } @@ -985,7 +985,7 @@ static void acpi_thermal_remove(struct acpi_device *device) flush_workqueue(acpi_thermal_pm_queue); acpi_thermal_unregister_thermal_zone(tz); - + kfree(tz->trip_table); kfree(tz); } diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 442396f6ed1f9c..e96afb1622f95f 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -130,6 +130,16 @@ static int video_detect_force_native(const struct dmi_system_id *d) return 0; } +static int video_detect_portege_r100(const struct dmi_system_id *d) +{ + struct pci_dev *dev; + /* Search for Trident CyberBlade XP4m32 to confirm Portégé R100 */ + dev = pci_get_device(PCI_VENDOR_ID_TRIDENT, 0x2100, NULL); + if (dev) + acpi_backlight_dmi = acpi_backlight_vendor; + return 0; +} + static const struct dmi_system_id video_detect_dmi_table[] = { /* * Models which should use the vendor backlight interface, @@ -250,6 +260,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "PCG-FRV35"), }, }, + { + .callback = video_detect_force_vendor, + /* Panasonic Toughbook CF-18 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Matsushita Electric Industrial"), + DMI_MATCH(DMI_PRODUCT_NAME, "CF-18"), + }, + }, /* * Toshiba models with Transflective display, these need to use @@ -270,6 +288,22 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, }, + /* + * Toshiba Portégé R100 has working both acpi_video and toshiba_acpi + * vendor driver. But none of them gets activated as it has a VGA with + * no kernel driver (Trident CyberBlade XP4m32). + * The DMI strings are generic so check for the VGA chip in callback. + */ + { + .callback = video_detect_portege_r100, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "Portable PC"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Version 1.0"), + DMI_MATCH(DMI_BOARD_NAME, "Portable PC") + }, + }, + /* * Models which need acpi_video backlight control where the GPU drivers * do not call acpi_video_register_backlight() because no internal panel @@ -479,6 +513,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "82BK"), }, }, + { + .callback = video_detect_force_native, + /* Lenovo Slim 7 16ARH7 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82UX"), + }, + }, { .callback = video_detect_force_native, /* Lenovo ThinkPad X131e (3371 AMD version) */ diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index 63d834dd381122..e035cec614dc8f 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -198,16 +198,16 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s } /* - * AMD systems from Renoir and Lucienne *require* that the NVME controller + * AMD systems from Renoir onwards *require* that the NVME controller * is put into D3 over a Modern Standby / suspend-to-idle cycle. * * This is "typically" accomplished using the `StorageD3Enable` * property in the _DSD that is checked via the `acpi_storage_d3` function - * but this property was introduced after many of these systems launched - * and most OEM systems don't have it in their BIOS. + * but some OEM systems still don't have it in their BIOS. * * The Microsoft documentation for StorageD3Enable mentioned that Windows has - * a hardcoded allowlist for D3 support, which was used for these platforms. + * a hardcoded allowlist for D3 support as well as a registry key to override + * the BIOS, which has been used for these cases. * * This allows quirking on Linux in a similar fashion. * @@ -220,19 +220,15 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s * https://bugzilla.kernel.org/show_bug.cgi?id=216773 * https://bugzilla.kernel.org/show_bug.cgi?id=217003 * 2) On at least one HP system StorageD3Enable is missing on the second NVME - disk in the system. + * disk in the system. + * 3) On at least one HP Rembrandt system StorageD3Enable is missing on the only + * NVME device. */ -static const struct x86_cpu_id storage_d3_cpu_ids[] = { - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 24, NULL), /* Picasso */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 96, NULL), /* Renoir */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 104, NULL), /* Lucienne */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 25, 80, NULL), /* Cezanne */ - {} -}; - bool force_storage_d3(void) { - return x86_match_cpu(storage_d3_cpu_ids); + if (!cpu_feature_enabled(X86_FEATURE_ZEN)) + return false; + return acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0; } /* @@ -261,9 +257,10 @@ bool force_storage_d3(void) #define ACPI_QUIRK_SKIP_I2C_CLIENTS BIT(0) #define ACPI_QUIRK_UART1_SKIP BIT(1) #define ACPI_QUIRK_UART1_TTY_UART2_SKIP BIT(2) -#define ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY BIT(3) -#define ACPI_QUIRK_USE_ACPI_AC_AND_BATTERY BIT(4) -#define ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS BIT(5) +#define ACPI_QUIRK_PNP_UART1_SKIP BIT(3) +#define ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY BIT(4) +#define ACPI_QUIRK_USE_ACPI_AC_AND_BATTERY BIT(5) +#define ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS BIT(6) static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = { /* @@ -343,6 +340,7 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = { DMI_MATCH(DMI_BIOS_VERSION, "BLADE_21"), }, .driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS | + ACPI_QUIRK_PNP_UART1_SKIP | ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY), }, { @@ -429,7 +427,7 @@ bool acpi_quirk_skip_i2c_client_enumeration(struct acpi_device *adev) } EXPORT_SYMBOL_GPL(acpi_quirk_skip_i2c_client_enumeration); -int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip) +static int acpi_dmi_skip_serdev_enumeration(struct device *controller_parent, bool *skip) { struct acpi_device *adev = ACPI_COMPANION(controller_parent); const struct dmi_system_id *dmi_id; @@ -437,20 +435,22 @@ int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *s u64 uid; int ret; - *skip = false; - ret = acpi_dev_uid_to_integer(adev, &uid); if (ret) return 0; - /* to not match on PNP enumerated debug UARTs */ - if (!dev_is_platform(controller_parent)) - return 0; - dmi_id = dmi_first_match(acpi_quirk_skip_dmi_ids); if (dmi_id) quirks = (unsigned long)dmi_id->driver_data; + if (!dev_is_platform(controller_parent)) { + /* PNP enumerated UARTs */ + if ((quirks & ACPI_QUIRK_PNP_UART1_SKIP) && uid == 1) + *skip = true; + + return 0; + } + if ((quirks & ACPI_QUIRK_UART1_SKIP) && uid == 1) *skip = true; @@ -464,7 +464,6 @@ int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *s return 0; } -EXPORT_SYMBOL_GPL(acpi_quirk_skip_serdev_enumeration); bool acpi_quirk_skip_gpio_event_handlers(void) { @@ -479,8 +478,21 @@ bool acpi_quirk_skip_gpio_event_handlers(void) return (quirks & ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS); } EXPORT_SYMBOL_GPL(acpi_quirk_skip_gpio_event_handlers); +#else +static int acpi_dmi_skip_serdev_enumeration(struct device *controller_parent, bool *skip) +{ + return 0; +} #endif +int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip) +{ + *skip = false; + + return acpi_dmi_skip_serdev_enumeration(controller_parent, skip); +} +EXPORT_SYMBOL_GPL(acpi_quirk_skip_serdev_enumeration); + /* Lists of PMIC ACPI HIDs with an (often better) native charger driver */ static const struct { const char *hid; diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 92128aae2d0601..94f10c6eb336a5 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -478,6 +478,16 @@ binder_enqueue_thread_work_ilocked(struct binder_thread *thread, { WARN_ON(!list_empty(&thread->waiting_thread_node)); binder_enqueue_work_ilocked(work, &thread->todo); + + /* (e)poll-based threads require an explicit wakeup signal when + * queuing their own work; they rely on these events to consume + * messages without I/O block. Without it, threads risk waiting + * indefinitely without handling the work. + */ + if (thread->looper & BINDER_LOOPER_STATE_POLL && + thread->pid == current->pid && !thread->process_todo) + wake_up_interruptible_sync(&thread->wait); + thread->process_todo = true; } @@ -560,9 +570,7 @@ static bool binder_has_work(struct binder_thread *thread, bool do_proc_work) static bool binder_available_for_proc_work_ilocked(struct binder_thread *thread) { return !thread->transaction_stack && - binder_worklist_empty_ilocked(&thread->todo) && - (thread->looper & (BINDER_LOOPER_STATE_ENTERED | - BINDER_LOOPER_STATE_REGISTERED)); + binder_worklist_empty_ilocked(&thread->todo); } static void binder_wakeup_poll_threads_ilocked(struct binder_proc *proc, @@ -1698,8 +1706,10 @@ static size_t binder_get_object(struct binder_proc *proc, size_t object_size = 0; read_size = min_t(size_t, sizeof(*object), buffer->data_size - offset); - if (offset > buffer->data_size || read_size < sizeof(*hdr)) + if (offset > buffer->data_size || read_size < sizeof(*hdr) || + !IS_ALIGNED(offset, sizeof(u32))) return 0; + if (u) { if (copy_from_user(object, u + offset, read_size)) return 0; @@ -3332,6 +3342,7 @@ static void binder_transaction(struct binder_proc *proc, */ copy_size = object_offset - user_offset; if (copy_size && (user_offset > object_offset || + object_offset > tr->data_size || binder_alloc_copy_user_to_buffer( &target_proc->alloc, t->buffer, user_offset, @@ -5030,7 +5041,7 @@ static __poll_t binder_poll(struct file *filp, thread = binder_get_thread(proc); if (!thread) - return POLLERR; + return EPOLLERR; binder_inner_proc_lock(thread->proc); thread->looper |= BINDER_LOOPER_STATE_POLL; @@ -5356,7 +5367,7 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) goto err; break; case BINDER_SET_MAX_THREADS: { - int max_threads; + u32 max_threads; if (copy_from_user(&max_threads, ubuf, sizeof(max_threads))) { diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index e3db8297095a2f..34c27223cb7dd2 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -271,7 +271,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, } if (mm) { mmap_write_unlock(mm); - mmput(mm); + mmput_async(mm); } return 0; @@ -304,7 +304,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, err_no_vma: if (mm) { mmap_write_unlock(mm); - mmput(mm); + mmput_async(mm); } return vma ? -ENOMEM : -ESRCH; } @@ -344,8 +344,7 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid) continue; if (!buffer->async_transaction) continue; - total_alloc_size += binder_alloc_buffer_size(alloc, buffer) - + sizeof(struct binder_buffer); + total_alloc_size += binder_alloc_buffer_size(alloc, buffer); num_buffers++; } @@ -407,17 +406,17 @@ static struct binder_buffer *binder_alloc_new_buf_locked( alloc->pid, extra_buffers_size); return ERR_PTR(-EINVAL); } - if (is_async && - alloc->free_async_space < size + sizeof(struct binder_buffer)) { + + /* Pad 0-size buffers so they get assigned unique addresses */ + size = max(size, sizeof(void *)); + + if (is_async && alloc->free_async_space < size) { binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, "%d: binder_alloc_buf size %zd failed, no async space left\n", alloc->pid, size); return ERR_PTR(-ENOSPC); } - /* Pad 0-size buffers so they get assigned unique addresses */ - size = max(size, sizeof(void *)); - while (n) { buffer = rb_entry(n, struct binder_buffer, rb_node); BUG_ON(!buffer->free); @@ -519,7 +518,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked( buffer->pid = pid; buffer->oneway_spam_suspect = false; if (is_async) { - alloc->free_async_space -= size + sizeof(struct binder_buffer); + alloc->free_async_space -= size; binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC, "%d: binder_alloc_buf size %zd async free %zd\n", alloc->pid, size, alloc->free_async_space); @@ -557,7 +556,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked( * is the sum of the three given sizes (each rounded up to * pointer-sized boundary) * - * Return: The allocated buffer or %NULL if error + * Return: The allocated buffer or %ERR_PTR(-errno) if error */ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, size_t data_size, @@ -657,8 +656,7 @@ static void binder_free_buf_locked(struct binder_alloc *alloc, BUG_ON(buffer->user_data > alloc->buffer + alloc->buffer_size); if (buffer->async_transaction) { - alloc->free_async_space += buffer_size + sizeof(struct binder_buffer); - + alloc->free_async_space += buffer_size; binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC, "%d: binder_free_buf size %zd async free %zd\n", alloc->pid, size, alloc->free_async_space); @@ -706,7 +704,7 @@ void binder_alloc_free_buf(struct binder_alloc *alloc, /* * We could eliminate the call to binder_alloc_clear_buf() * from binder_alloc_deferred_release() by moving this to - * binder_alloc_free_buf_locked(). However, that could + * binder_free_buf_locked(). However, that could * increase contention for the alloc mutex if clear_on_free * is used frequently for large buffers. The mutex is not * needed for correctness here. @@ -1005,7 +1003,9 @@ enum lru_status binder_alloc_free_page(struct list_head *item, goto err_mmget; if (!mmap_read_trylock(mm)) goto err_mmap_read_lock_failed; - vma = binder_alloc_get_vma(alloc); + vma = vma_lookup(mm, page_addr); + if (vma && vma != binder_alloc_get_vma(alloc)) + goto err_invalid_vma; list_lru_isolate(lru, item); spin_unlock(lock); @@ -1031,6 +1031,8 @@ enum lru_status binder_alloc_free_page(struct list_head *item, mutex_unlock(&alloc->mutex); return LRU_REMOVED_RETRY; +err_invalid_vma: + mmap_read_unlock(mm); err_mmap_read_lock_failed: mmput_async(mm); err_mmget: diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h index 7270d4d2220702..5b7c80b99ae865 100644 --- a/drivers/android/binder_internal.h +++ b/drivers/android/binder_internal.h @@ -421,7 +421,7 @@ struct binder_proc { struct list_head todo; struct binder_stats stats; struct list_head delivered_death; - int max_threads; + u32 max_threads; int requested_threads; int requested_threads_started; int tmp_ref; diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 08745e7db8201f..6e76780fb43083 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -48,6 +48,7 @@ enum { enum board_ids { /* board IDs by feature in alphabetical order */ board_ahci, + board_ahci_43bit_dma, board_ahci_ign_iferr, board_ahci_low_power, board_ahci_no_debounce_delay, @@ -128,6 +129,13 @@ static const struct ata_port_info ahci_port_info[] = { .udma_mask = ATA_UDMA6, .port_ops = &ahci_ops, }, + [board_ahci_43bit_dma] = { + AHCI_HFLAGS (AHCI_HFLAG_43BIT_ONLY), + .flags = AHCI_FLAG_COMMON, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_ops, + }, [board_ahci_ign_iferr] = { AHCI_HFLAGS (AHCI_HFLAG_IGN_IRQ_IF_ERR), .flags = AHCI_FLAG_COMMON, @@ -596,14 +604,19 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(PROMISE, 0x3f20), board_ahci }, /* PDC42819 */ { PCI_VDEVICE(PROMISE, 0x3781), board_ahci }, /* FastTrak TX8660 ahci-mode */ - /* Asmedia */ - { PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci }, /* ASM1060 */ - { PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci }, /* ASM1060 */ - { PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci }, /* ASM1061 */ - { PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci }, /* ASM1062 */ - { PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci }, /* ASM1061R */ - { PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci }, /* ASM1062R */ - { PCI_VDEVICE(ASMEDIA, 0x0624), board_ahci }, /* ASM1062+JMB575 */ + /* ASMedia */ + { PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci_43bit_dma }, /* ASM1060 */ + { PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci_43bit_dma }, /* ASM1060 */ + { PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci_43bit_dma }, /* ASM1061 */ + { PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci_43bit_dma }, /* ASM1061/1062 */ + { PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci_43bit_dma }, /* ASM1061R */ + { PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci_43bit_dma }, /* ASM1062R */ + { PCI_VDEVICE(ASMEDIA, 0x0624), board_ahci_43bit_dma }, /* ASM1062+JMB575 */ + { PCI_VDEVICE(ASMEDIA, 0x1062), board_ahci }, /* ASM1062A */ + { PCI_VDEVICE(ASMEDIA, 0x1064), board_ahci }, /* ASM1064 */ + { PCI_VDEVICE(ASMEDIA, 0x1164), board_ahci }, /* ASM1164 */ + { PCI_VDEVICE(ASMEDIA, 0x1165), board_ahci }, /* ASM1165 */ + { PCI_VDEVICE(ASMEDIA, 0x1166), board_ahci }, /* ASM1166 */ /* * Samsung SSDs found on some macbooks. NCQ times out if MSI is @@ -654,6 +667,87 @@ static int mobile_lpm_policy = -1; module_param(mobile_lpm_policy, int, 0644); MODULE_PARM_DESC(mobile_lpm_policy, "Default LPM policy for mobile chipsets"); +static char *ahci_mask_port_map; +module_param_named(mask_port_map, ahci_mask_port_map, charp, 0444); +MODULE_PARM_DESC(mask_port_map, + "32-bits port map masks to ignore controllers ports. " + "Valid values are: " + "\"\" to apply the same mask to all AHCI controller " + "devices, and \"=,=,...\" to " + "specify different masks for the controllers specified, " + "where is the PCI ID of an AHCI controller in the " + "form \"domain:bus:dev.func\""); + +static void ahci_apply_port_map_mask(struct device *dev, + struct ahci_host_priv *hpriv, char *mask_s) +{ + unsigned int mask; + + if (kstrtouint(mask_s, 0, &mask)) { + dev_err(dev, "Invalid port map mask\n"); + return; + } + + hpriv->mask_port_map = mask; +} + +static void ahci_get_port_map_mask(struct device *dev, + struct ahci_host_priv *hpriv) +{ + char *param, *end, *str, *mask_s; + char *name; + + if (!strlen(ahci_mask_port_map)) + return; + + str = kstrdup(ahci_mask_port_map, GFP_KERNEL); + if (!str) + return; + + /* Handle single mask case */ + if (!strchr(str, '=')) { + ahci_apply_port_map_mask(dev, hpriv, str); + goto free; + } + + /* + * Mask list case: parse the parameter to apply the mask only if + * the device name matches. + */ + param = str; + end = param + strlen(param); + while (param && param < end && *param) { + name = param; + param = strchr(name, '='); + if (!param) + break; + + *param = '\0'; + param++; + if (param >= end) + break; + + if (strcmp(dev_name(dev), name) != 0) { + param = strchr(param, ','); + if (param) + param++; + continue; + } + + mask_s = param; + param = strchr(mask_s, ','); + if (param) { + *param = '\0'; + param++; + } + + ahci_apply_port_map_mask(dev, hpriv, mask_s); + } + +free: + kfree(str); +} + static void ahci_pci_save_initial_config(struct pci_dev *pdev, struct ahci_host_priv *hpriv) { @@ -676,6 +770,10 @@ static void ahci_pci_save_initial_config(struct pci_dev *pdev, "Disabling your PATA port. Use the boot option 'ahci.marvell_enable=0' to avoid this.\n"); } + /* Handle port map masks passed as module parameter. */ + if (ahci_mask_port_map) + ahci_get_port_map_mask(&pdev->dev, hpriv); + ahci_save_initial_config(&pdev->dev, hpriv); } @@ -943,11 +1041,20 @@ static int ahci_pci_device_resume(struct device *dev) #endif /* CONFIG_PM */ -static int ahci_configure_dma_masks(struct pci_dev *pdev, int using_dac) +static int ahci_configure_dma_masks(struct pci_dev *pdev, + struct ahci_host_priv *hpriv) { - const int dma_bits = using_dac ? 64 : 32; + int dma_bits; int rc; + if (hpriv->cap & HOST_CAP_64) { + dma_bits = 64; + if (hpriv->flags & AHCI_HFLAG_43BIT_ONLY) + dma_bits = 43; + } else { + dma_bits = 32; + } + /* * If the device fixup already set the dma_mask to some non-standard * value, don't extend it here. This happens on STA2X11, for example. @@ -1868,8 +1975,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) n_ports = max(ahci_nr_ports(hpriv->cap), fls(hpriv->port_map)); host = ata_host_alloc_pinfo(&pdev->dev, ppi, n_ports); - if (!host) - return -ENOMEM; + if (!host) { + rc = -ENOMEM; + goto err_rm_sysfs_file; + } host->private_data = hpriv; if (ahci_init_msi(pdev, n_ports, hpriv) < 0) { @@ -1920,13 +2029,13 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) ahci_gtf_filter_workaround(host); /* initialize adapter */ - rc = ahci_configure_dma_masks(pdev, hpriv->cap & HOST_CAP_64); + rc = ahci_configure_dma_masks(pdev, hpriv); if (rc) - return rc; + goto err_rm_sysfs_file; rc = ahci_pci_reset_controller(host); if (rc) - return rc; + goto err_rm_sysfs_file; ahci_pci_init_controller(host); ahci_pci_print_info(host); @@ -1935,10 +2044,15 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rc = ahci_host_activate(host, &ahci_sht); if (rc) - return rc; + goto err_rm_sysfs_file; pm_runtime_put_noidle(&pdev->dev); return 0; + +err_rm_sysfs_file: + sysfs_remove_file_from_group(&pdev->dev.kobj, + &dev_attr_remapped_nvme.attr, NULL); + return rc; } static void ahci_shutdown_one(struct pci_dev *pdev) diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 4bae95b06ae3c9..df8f8a1a3a34c3 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -247,6 +247,7 @@ enum { AHCI_HFLAG_SUSPEND_PHYS = BIT(26), /* handle PHYs during suspend/resume */ AHCI_HFLAG_NO_SXS = BIT(28), /* SXS not supported */ + AHCI_HFLAG_43BIT_ONLY = BIT(29), /* 43bit DMA addr limit */ /* ap->flags bits */ diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c index 64f7f7d6ba84e0..11a2c199a7c246 100644 --- a/drivers/ata/ahci_ceva.c +++ b/drivers/ata/ahci_ceva.c @@ -88,7 +88,6 @@ struct ceva_ahci_priv { u32 axicc; bool is_cci_enabled; int flags; - struct reset_control *rst; }; static unsigned int ceva_ahci_read_id(struct ata_device *dev, @@ -189,6 +188,60 @@ static const struct scsi_host_template ahci_platform_sht = { AHCI_SHT(DRV_NAME), }; +static int ceva_ahci_platform_enable_resources(struct ahci_host_priv *hpriv) +{ + int rc, i; + + rc = ahci_platform_enable_regulators(hpriv); + if (rc) + return rc; + + rc = ahci_platform_enable_clks(hpriv); + if (rc) + goto disable_regulator; + + /* Assert the controller reset */ + rc = ahci_platform_assert_rsts(hpriv); + if (rc) + goto disable_clks; + + for (i = 0; i < hpriv->nports; i++) { + rc = phy_init(hpriv->phys[i]); + if (rc) + goto disable_rsts; + } + + /* De-assert the controller reset */ + ahci_platform_deassert_rsts(hpriv); + + for (i = 0; i < hpriv->nports; i++) { + rc = phy_power_on(hpriv->phys[i]); + if (rc) { + phy_exit(hpriv->phys[i]); + goto disable_phys; + } + } + + return 0; + +disable_rsts: + ahci_platform_deassert_rsts(hpriv); + +disable_phys: + while (--i >= 0) { + phy_power_off(hpriv->phys[i]); + phy_exit(hpriv->phys[i]); + } + +disable_clks: + ahci_platform_disable_clks(hpriv); + +disable_regulator: + ahci_platform_disable_regulators(hpriv); + + return rc; +} + static int ceva_ahci_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; @@ -203,47 +256,19 @@ static int ceva_ahci_probe(struct platform_device *pdev) return -ENOMEM; cevapriv->ahci_pdev = pdev; - - cevapriv->rst = devm_reset_control_get_optional_exclusive(&pdev->dev, - NULL); - if (IS_ERR(cevapriv->rst)) - dev_err_probe(&pdev->dev, PTR_ERR(cevapriv->rst), - "failed to get reset\n"); - hpriv = ahci_platform_get_resources(pdev, 0); if (IS_ERR(hpriv)) return PTR_ERR(hpriv); - if (!cevapriv->rst) { - rc = ahci_platform_enable_resources(hpriv); - if (rc) - return rc; - } else { - int i; + hpriv->rsts = devm_reset_control_get_optional_exclusive(&pdev->dev, + NULL); + if (IS_ERR(hpriv->rsts)) + return dev_err_probe(&pdev->dev, PTR_ERR(hpriv->rsts), + "failed to get reset\n"); - rc = ahci_platform_enable_clks(hpriv); - if (rc) - return rc; - /* Assert the controller reset */ - reset_control_assert(cevapriv->rst); - - for (i = 0; i < hpriv->nports; i++) { - rc = phy_init(hpriv->phys[i]); - if (rc) - return rc; - } - - /* De-assert the controller reset */ - reset_control_deassert(cevapriv->rst); - - for (i = 0; i < hpriv->nports; i++) { - rc = phy_power_on(hpriv->phys[i]); - if (rc) { - phy_exit(hpriv->phys[i]); - return rc; - } - } - } + rc = ceva_ahci_platform_enable_resources(hpriv); + if (rc) + return rc; if (of_property_read_bool(np, "ceva,broken-gen2")) cevapriv->flags = CEVA_FLAG_BROKEN_GEN2; @@ -252,52 +277,60 @@ static int ceva_ahci_probe(struct platform_device *pdev) if (of_property_read_u8_array(np, "ceva,p0-cominit-params", (u8 *)&cevapriv->pp2c[0], 4) < 0) { dev_warn(dev, "ceva,p0-cominit-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } if (of_property_read_u8_array(np, "ceva,p1-cominit-params", (u8 *)&cevapriv->pp2c[1], 4) < 0) { dev_warn(dev, "ceva,p1-cominit-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } /* Read OOB timing value for COMWAKE from device-tree*/ if (of_property_read_u8_array(np, "ceva,p0-comwake-params", (u8 *)&cevapriv->pp3c[0], 4) < 0) { dev_warn(dev, "ceva,p0-comwake-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } if (of_property_read_u8_array(np, "ceva,p1-comwake-params", (u8 *)&cevapriv->pp3c[1], 4) < 0) { dev_warn(dev, "ceva,p1-comwake-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } /* Read phy BURST timing value from device-tree */ if (of_property_read_u8_array(np, "ceva,p0-burst-params", (u8 *)&cevapriv->pp4c[0], 4) < 0) { dev_warn(dev, "ceva,p0-burst-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } if (of_property_read_u8_array(np, "ceva,p1-burst-params", (u8 *)&cevapriv->pp4c[1], 4) < 0) { dev_warn(dev, "ceva,p1-burst-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } /* Read phy RETRY interval timing value from device-tree */ if (of_property_read_u16_array(np, "ceva,p0-retry-params", (u16 *)&cevapriv->pp5c[0], 2) < 0) { dev_warn(dev, "ceva,p0-retry-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } if (of_property_read_u16_array(np, "ceva,p1-retry-params", (u16 *)&cevapriv->pp5c[1], 2) < 0) { dev_warn(dev, "ceva,p1-retry-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } /* @@ -335,7 +368,7 @@ static int __maybe_unused ceva_ahci_resume(struct device *dev) struct ahci_host_priv *hpriv = host->private_data; int rc; - rc = ahci_platform_enable_resources(hpriv); + rc = ceva_ahci_platform_enable_resources(hpriv); if (rc) return rc; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index d8cc1e27a125f0..4ed90d46a017a8 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2034,6 +2034,10 @@ void ata_dev_power_set_active(struct ata_device *dev) struct ata_taskfile tf; unsigned int err_mask; + /* If the device is already sleeping, do nothing. */ + if (dev->flags & ATA_DFLAG_SLEEPING) + return; + /* * Issue READ VERIFY SECTORS command for 1 sector at lba=0 only * if supported by the device. @@ -2489,7 +2493,7 @@ static void ata_dev_config_cdl(struct ata_device *dev) bool cdl_enabled; u64 val; - if (ata_id_major_version(dev->id) < 12) + if (ata_id_major_version(dev->id) < 11) goto not_supported; if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE) || @@ -5495,6 +5499,18 @@ struct ata_port *ata_port_alloc(struct ata_host *host) return ap; } +void ata_port_free(struct ata_port *ap) +{ + if (!ap) + return; + + kfree(ap->pmp_link); + kfree(ap->slave_link); + kfree(ap->ncq_sense_buf); + kfree(ap); +} +EXPORT_SYMBOL_GPL(ata_port_free); + static void ata_devres_release(struct device *gendev, void *res) { struct ata_host *host = dev_get_drvdata(gendev); @@ -5521,12 +5537,7 @@ static void ata_host_release(struct kref *kref) int i; for (i = 0; i < host->n_ports; i++) { - struct ata_port *ap = host->ports[i]; - - kfree(ap->pmp_link); - kfree(ap->slave_link); - kfree(ap->ncq_sense_buf); - kfree(ap); + ata_port_free(host->ports[i]); host->ports[i] = NULL; } kfree(host); @@ -5576,12 +5587,16 @@ struct ata_host *ata_host_alloc(struct device *dev, int max_ports) if (!host) return NULL; - if (!devres_open_group(dev, NULL, GFP_KERNEL)) - goto err_free; + if (!devres_open_group(dev, NULL, GFP_KERNEL)) { + kfree(host); + return NULL; + } dr = devres_alloc(ata_devres_release, 0, GFP_KERNEL); - if (!dr) + if (!dr) { + kfree(host); goto err_out; + } devres_add(dev, dr); dev_set_drvdata(dev, host); @@ -5609,8 +5624,6 @@ struct ata_host *ata_host_alloc(struct device *dev, int max_ports) err_out: devres_release_group(dev, NULL); - err_free: - kfree(host); return NULL; } EXPORT_SYMBOL_GPL(ata_host_alloc); @@ -5909,7 +5922,7 @@ int ata_host_register(struct ata_host *host, const struct scsi_host_template *sh * allocation time. */ for (i = host->n_ports; host->ports[i]; i++) - kfree(host->ports[i]); + ata_port_free(host->ports[i]); /* give ports names and add SCSI hosts */ for (i = 0; i < host->n_ports; i++) { diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 5686353e442cf4..a96566e1b2b84c 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -618,6 +618,14 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, list_for_each_entry_safe(scmd, tmp, eh_work_q, eh_entry) { struct ata_queued_cmd *qc; + /* + * If the scmd was added to EH, via ata_qc_schedule_eh() -> + * scsi_timeout() -> scsi_eh_scmd_add(), scsi_timeout() will + * have set DID_TIME_OUT (since libata does not have an abort + * handler). Thus, to clear DID_TIME_OUT, clear the host byte. + */ + set_host_byte(scmd, DID_OK); + ata_qc_for_each_raw(ap, qc, i) { if (qc->flags & ATA_QCFLAG_ACTIVE && qc->scsicmd == scmd) @@ -700,8 +708,10 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap) ehc->saved_ncq_enabled |= 1 << devno; /* If we are resuming, wake up the device */ - if (ap->pflags & ATA_PFLAG_RESUMING) + if (ap->pflags & ATA_PFLAG_RESUMING) { + dev->flags |= ATA_DFLAG_RESUMING; ehc->i.dev_action[devno] |= ATA_EH_SET_ACTIVE; + } } } @@ -3170,6 +3180,7 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link, return 0; err: + dev->flags &= ~ATA_DFLAG_RESUMING; *r_failed_dev = dev; return rc; } @@ -4038,10 +4049,20 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap) WARN_ON(ap->pflags & ATA_PFLAG_SUSPENDED); - /* Set all devices attached to the port in standby mode */ - ata_for_each_link(link, ap, HOST_FIRST) { - ata_for_each_dev(dev, link, ENABLED) - ata_dev_power_set_standby(dev); + /* + * We will reach this point for all of the PM events: + * PM_EVENT_SUSPEND (if runtime pm, PM_EVENT_AUTO will also be set) + * PM_EVENT_FREEZE, and PM_EVENT_HIBERNATE. + * + * We do not want to perform disk spin down for PM_EVENT_FREEZE. + * (Spin down will be performed by the subsequent PM_EVENT_HIBERNATE.) + */ + if (!(ap->pm_mesg.event & PM_EVENT_FREEZE)) { + /* Set all devices attached to the port in standby mode */ + ata_for_each_link(link, ap, HOST_FIRST) { + ata_for_each_dev(dev, link, ENABLED) + ata_dev_power_set_standby(dev); + } } /* diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 3a957c4da40927..5377d094bf7548 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -230,6 +230,87 @@ void ata_scsi_set_sense_information(struct ata_device *dev, SCSI_SENSE_BUFFERSIZE, information); } +/** + * ata_scsi_set_passthru_sense_fields - Set ATA fields in sense buffer + * @qc: ATA PASS-THROUGH command. + * + * Populates "ATA Status Return sense data descriptor" / "Fixed format + * sense data" with ATA taskfile fields. + * + * LOCKING: + * None. + */ +static void ata_scsi_set_passthru_sense_fields(struct ata_queued_cmd *qc) +{ + struct ata_device *dev = qc->dev; + struct scsi_cmnd *cmd = qc->scsicmd; + struct ata_taskfile *tf = &qc->result_tf; + unsigned char *sb = cmd->sense_buffer; + + if (!(qc->flags & ATA_QCFLAG_RTF_FILLED)) { + ata_dev_dbg(dev, + "missing result TF: can't set ATA PT sense fields\n"); + return; + } + + if ((sb[0] & 0x7f) >= 0x72) { + unsigned char *desc; + u8 len; + + /* descriptor format */ + len = sb[7]; + desc = (char *)scsi_sense_desc_find(sb, len + 8, 9); + if (!desc) { + if (SCSI_SENSE_BUFFERSIZE < len + 14) + return; + sb[7] = len + 14; + desc = sb + 8 + len; + } + desc[0] = 9; + desc[1] = 12; + /* + * Copy registers into sense buffer. + */ + desc[2] = 0x00; + desc[3] = tf->error; + desc[5] = tf->nsect; + desc[7] = tf->lbal; + desc[9] = tf->lbam; + desc[11] = tf->lbah; + desc[12] = tf->device; + desc[13] = tf->status; + + /* + * Fill in Extend bit, and the high order bytes + * if applicable. + */ + if (tf->flags & ATA_TFLAG_LBA48) { + desc[2] |= 0x01; + desc[4] = tf->hob_nsect; + desc[6] = tf->hob_lbal; + desc[8] = tf->hob_lbam; + desc[10] = tf->hob_lbah; + } + } else { + /* Fixed sense format */ + sb[0] |= 0x80; + sb[3] = tf->error; + sb[4] = tf->status; + sb[5] = tf->device; + sb[6] = tf->nsect; + if (tf->flags & ATA_TFLAG_LBA48) { + sb[8] |= 0x80; + if (tf->hob_nsect) + sb[8] |= 0x40; + if (tf->hob_lbal || tf->hob_lbam || tf->hob_lbah) + sb[8] |= 0x20; + } + sb[9] = tf->lbal; + sb[10] = tf->lbam; + sb[11] = tf->lbah; + } +} + static void ata_scsi_set_invalid_field(struct ata_device *dev, struct scsi_cmnd *cmd, u16 field, u8 bit) { @@ -837,10 +918,8 @@ static void ata_to_sense_error(unsigned id, u8 drv_stat, u8 drv_err, u8 *sk, * ata_gen_passthru_sense - Generate check condition sense block. * @qc: Command that completed. * - * This function is specific to the ATA descriptor format sense - * block specified for the ATA pass through commands. Regardless - * of whether the command errored or not, return a sense - * block. Copy all controller registers into the sense + * This function is specific to the ATA pass through commands. + * Regardless of whether the command errored or not, return a sense * block. If there was no error, we get the request from an ATA * passthrough command, so we use the following sense data: * sk = RECOVERED ERROR @@ -852,13 +931,16 @@ static void ata_to_sense_error(unsigned id, u8 drv_stat, u8 drv_err, u8 *sk, */ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc) { + struct ata_device *dev = qc->dev; struct scsi_cmnd *cmd = qc->scsicmd; struct ata_taskfile *tf = &qc->result_tf; - unsigned char *sb = cmd->sense_buffer; - unsigned char *desc = sb + 8; u8 sense_key, asc, ascq; - memset(sb, 0, SCSI_SENSE_BUFFERSIZE); + if (!(qc->flags & ATA_QCFLAG_RTF_FILLED)) { + ata_dev_dbg(dev, + "missing result TF: can't generate ATA PT sense data\n"); + return; + } /* * Use ata_to_sense_error() to map status register bits @@ -872,66 +954,18 @@ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc) } else { /* * ATA PASS-THROUGH INFORMATION AVAILABLE - * Always in descriptor format sense. + * + * Note: we are supposed to call ata_scsi_set_sense(), which + * respects the D_SENSE bit, instead of unconditionally + * generating the sense data in descriptor format. However, + * because hdparm, hddtemp, and udisks incorrectly assume sense + * data in descriptor format, without even looking at the + * RESPONSE CODE field in the returned sense data (to see which + * format the returned sense data is in), we are stuck with + * being bug compatible with older kernels. */ scsi_build_sense(cmd, 1, RECOVERED_ERROR, 0, 0x1D); } - - if ((cmd->sense_buffer[0] & 0x7f) >= 0x72) { - u8 len; - - /* descriptor format */ - len = sb[7]; - desc = (char *)scsi_sense_desc_find(sb, len + 8, 9); - if (!desc) { - if (SCSI_SENSE_BUFFERSIZE < len + 14) - return; - sb[7] = len + 14; - desc = sb + 8 + len; - } - desc[0] = 9; - desc[1] = 12; - /* - * Copy registers into sense buffer. - */ - desc[2] = 0x00; - desc[3] = tf->error; - desc[5] = tf->nsect; - desc[7] = tf->lbal; - desc[9] = tf->lbam; - desc[11] = tf->lbah; - desc[12] = tf->device; - desc[13] = tf->status; - - /* - * Fill in Extend bit, and the high order bytes - * if applicable. - */ - if (tf->flags & ATA_TFLAG_LBA48) { - desc[2] |= 0x01; - desc[4] = tf->hob_nsect; - desc[6] = tf->hob_lbal; - desc[8] = tf->hob_lbam; - desc[10] = tf->hob_lbah; - } - } else { - /* Fixed sense format */ - desc[0] = tf->error; - desc[1] = tf->status; - desc[2] = tf->device; - desc[3] = tf->nsect; - desc[7] = 0; - if (tf->flags & ATA_TFLAG_LBA48) { - desc[8] |= 0x80; - if (tf->hob_nsect) - desc[8] |= 0x40; - if (tf->hob_lbal || tf->hob_lbam || tf->hob_lbah) - desc[8] |= 0x20; - } - desc[9] = tf->lbal; - desc[10] = tf->lbam; - desc[11] = tf->lbah; - } } /** @@ -953,14 +987,19 @@ static void ata_gen_ata_sense(struct ata_queued_cmd *qc) u64 block; u8 sense_key, asc, ascq; - memset(sb, 0, SCSI_SENSE_BUFFERSIZE); - if (ata_dev_disabled(dev)) { /* Device disabled after error recovery */ /* LOGICAL UNIT NOT READY, HARD RESET REQUIRED */ ata_scsi_set_sense(dev, cmd, NOT_READY, 0x04, 0x21); return; } + + if (!(qc->flags & ATA_QCFLAG_RTF_FILLED)) { + ata_dev_dbg(dev, + "missing result TF: can't generate sense data\n"); + return; + } + /* Use ata_to_sense_error() to map status register bits * onto sense key, asc & ascq. */ @@ -1055,9 +1094,14 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) * Ask the sd driver to issue START STOP UNIT on runtime suspend * and resume and shutdown only. For system level suspend/resume, * devices power state is handled directly by libata EH. + * Given that disks are always spun up on system resume, also + * make sure that the sd driver forces runtime suspended disks + * to be resumed to correctly reflect the power state of the + * device. */ - sdev->manage_runtime_start_stop = true; - sdev->manage_shutdown = true; + sdev->manage_runtime_start_stop = 1; + sdev->manage_shutdown = 1; + sdev->force_runtime_start_on_system_start = 1; } /* @@ -1659,26 +1703,29 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) { struct scsi_cmnd *cmd = qc->scsicmd; u8 *cdb = cmd->cmnd; - int need_sense = (qc->err_mask != 0) && - !(qc->flags & ATA_QCFLAG_SENSE_VALID); + bool have_sense = qc->flags & ATA_QCFLAG_SENSE_VALID; + bool is_ata_passthru = cdb[0] == ATA_16 || cdb[0] == ATA_12; + bool is_ck_cond_request = cdb[2] & 0x20; + bool is_error = qc->err_mask != 0; /* For ATA pass thru (SAT) commands, generate a sense block if * user mandated it or if there's an error. Note that if we - * generate because the user forced us to [CK_COND =1], a check + * generate because the user forced us to [CK_COND=1], a check * condition is generated and the ATA register values are returned * whether the command completed successfully or not. If there - * was no error, we use the following sense data: + * was no error, and CK_COND=1, we use the following sense data: * sk = RECOVERED ERROR * asc,ascq = ATA PASS-THROUGH INFORMATION AVAILABLE */ - if (((cdb[0] == ATA_16) || (cdb[0] == ATA_12)) && - ((cdb[2] & 0x20) || need_sense)) - ata_gen_passthru_sense(qc); - else if (need_sense) + if (is_ata_passthru && (is_ck_cond_request || is_error || have_sense)) { + if (!have_sense) + ata_gen_passthru_sense(qc); + ata_scsi_set_passthru_sense_fields(qc); + if (is_ck_cond_request) + set_status_byte(qc->scsicmd, SAM_STAT_CHECK_CONDITION); + } else if (is_error && !have_sense) { ata_gen_ata_sense(qc); - else - /* Keep the SCSI ML and status byte, clear host byte. */ - cmd->result &= 0x0000ffff; + } ata_qc_done(qc); } @@ -2343,7 +2390,7 @@ static unsigned int ata_msense_control(struct ata_device *dev, u8 *buf, case ALL_SUB_MPAGES: n = ata_msense_control_spg0(dev, buf, changeable); n += ata_msense_control_spgt2(dev, buf + n, CDL_T2A_SUB_MPAGE); - n += ata_msense_control_spgt2(dev, buf + n, CDL_T2A_SUB_MPAGE); + n += ata_msense_control_spgt2(dev, buf + n, CDL_T2B_SUB_MPAGE); n += ata_msense_control_ata_feature(dev, buf + n); return n; default: @@ -2617,14 +2664,8 @@ static void atapi_qc_complete(struct ata_queued_cmd *qc) /* handle completion from EH */ if (unlikely(err_mask || qc->flags & ATA_QCFLAG_SENSE_VALID)) { - if (!(qc->flags & ATA_QCFLAG_SENSE_VALID)) { - /* FIXME: not quite right; we don't want the - * translation of taskfile registers into a - * sense descriptors, since that's only - * correct for ATA, not ATAPI - */ + if (!(qc->flags & ATA_QCFLAG_SENSE_VALID)) ata_gen_passthru_sense(qc); - } /* SCSI EH automatically locks door if sdev->locked is * set. Sometimes door lock request continues to @@ -4760,6 +4801,7 @@ void ata_scsi_dev_rescan(struct work_struct *work) struct ata_link *link; struct ata_device *dev; unsigned long flags; + bool do_resume; int ret = 0; mutex_lock(&ap->scsi_scan_mutex); @@ -4774,25 +4816,34 @@ void ata_scsi_dev_rescan(struct work_struct *work) * bail out. */ if (ap->pflags & ATA_PFLAG_SUSPENDED) - goto unlock; + goto unlock_ap; if (!sdev) continue; if (scsi_device_get(sdev)) continue; + do_resume = dev->flags & ATA_DFLAG_RESUMING; + spin_unlock_irqrestore(ap->lock, flags); + if (do_resume) { + ret = scsi_resume_device(sdev); + if (ret == -EWOULDBLOCK) + goto unlock_scan; + dev->flags &= ~ATA_DFLAG_RESUMING; + } ret = scsi_rescan_device(sdev); scsi_device_put(sdev); spin_lock_irqsave(ap->lock, flags); if (ret) - goto unlock; + goto unlock_ap; } } -unlock: +unlock_ap: spin_unlock_irqrestore(ap->lock, flags); +unlock_scan: mutex_unlock(&ap->scsi_scan_mutex); /* Reschedule with a delay if scsi_rescan_device() returned an error */ diff --git a/drivers/ata/pata_isapnp.c b/drivers/ata/pata_isapnp.c index 25a63d043c8e1f..0f77e042406619 100644 --- a/drivers/ata/pata_isapnp.c +++ b/drivers/ata/pata_isapnp.c @@ -82,6 +82,9 @@ static int isapnp_init_one(struct pnp_dev *idev, const struct pnp_device_id *dev if (pnp_port_valid(idev, 1)) { ctl_addr = devm_ioport_map(&idev->dev, pnp_port_start(idev, 1), 1); + if (!ctl_addr) + return -ENOMEM; + ap->ioaddr.altstatus_addr = ctl_addr; ap->ioaddr.ctl_addr = ctl_addr; ap->ops = &isapnp_port_ops; diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c index 448a511cbc179a..e7ac142c2423dd 100644 --- a/drivers/ata/pata_legacy.c +++ b/drivers/ata/pata_legacy.c @@ -173,8 +173,6 @@ static int legacy_port[NR_HOST] = { 0x1f0, 0x170, 0x1e8, 0x168, 0x1e0, 0x160 }; static struct legacy_probe probe_list[NR_HOST]; static struct legacy_data legacy_data[NR_HOST]; static struct ata_host *legacy_host[NR_HOST]; -static int nr_legacy_host; - /** * legacy_probe_add - Add interface to probe list @@ -1276,9 +1274,11 @@ static __exit void legacy_exit(void) { int i; - for (i = 0; i < nr_legacy_host; i++) { + for (i = 0; i < NR_HOST; i++) { struct legacy_data *ld = &legacy_data[i]; - ata_host_detach(legacy_host[i]); + + if (legacy_host[i]) + ata_host_detach(legacy_host[i]); platform_device_unregister(ld->platform_dev); } } diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index 17f6ccee53c7c2..ffbb2e8591cefc 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -541,7 +541,8 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc) while (sg_len) { /* table overflow should never happen */ - BUG_ON (pi++ >= MAX_DCMDS); + if (WARN_ON_ONCE(pi >= MAX_DCMDS)) + return AC_ERR_SYSTEM; len = (sg_len < MAX_DBDMA_SEG) ? sg_len : MAX_DBDMA_SEG; table->command = cpu_to_le16(write ? OUTPUT_MORE: INPUT_MORE); @@ -553,11 +554,13 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc) addr += len; sg_len -= len; ++table; + ++pi; } } /* Should never happen according to Tejun */ - BUG_ON(!pi); + if (WARN_ON_ONCE(!pi)) + return AC_ERR_SYSTEM; /* Convert the last command to an input/output */ table--; diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c index 549ff24a982311..4edddf6bcc1507 100644 --- a/drivers/ata/pata_serverworks.c +++ b/drivers/ata/pata_serverworks.c @@ -46,10 +46,11 @@ #define SVWKS_CSB5_REVISION_NEW 0x92 /* min PCI_REVISION_ID for UDMA5 (A2.0) */ #define SVWKS_CSB6_REVISION 0xa0 /* min PCI_REVISION_ID for UDMA4 (A1.0) */ -/* Seagate Barracuda ATA IV Family drives in UDMA mode 5 - * can overrun their FIFOs when used with the CSB5 */ - -static const char *csb_bad_ata100[] = { +/* + * Seagate Barracuda ATA IV Family drives in UDMA mode 5 + * can overrun their FIFOs when used with the CSB5. + */ +static const char * const csb_bad_ata100[] = { "ST320011A", "ST340016A", "ST360021A", @@ -163,10 +164,11 @@ static unsigned int serverworks_osb4_filter(struct ata_device *adev, unsigned in * @adev: ATA device * @mask: Mask of proposed modes * - * Check the blacklist and disable UDMA5 if matched + * Check the list of devices with broken UDMA5 and + * disable UDMA5 if matched. */ - -static unsigned int serverworks_csb_filter(struct ata_device *adev, unsigned int mask) +static unsigned int serverworks_csb_filter(struct ata_device *adev, + unsigned int mask) { const char *p; char model_num[ATA_ID_PROD_LEN + 1]; diff --git a/drivers/ata/sata_gemini.c b/drivers/ata/sata_gemini.c index 400b22ee99c33a..4c270999ba3ccd 100644 --- a/drivers/ata/sata_gemini.c +++ b/drivers/ata/sata_gemini.c @@ -200,7 +200,10 @@ int gemini_sata_start_bridge(struct sata_gemini *sg, unsigned int bridge) pclk = sg->sata0_pclk; else pclk = sg->sata1_pclk; - clk_enable(pclk); + ret = clk_enable(pclk); + if (ret) + return ret; + msleep(10); /* Do not keep clocking a bridge that is not online */ diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index 45e48d653c60b5..80a45e11fb5b60 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -787,37 +787,6 @@ static const struct ata_port_info mv_port_info[] = { }, }; -static const struct pci_device_id mv_pci_tbl[] = { - { PCI_VDEVICE(MARVELL, 0x5040), chip_504x }, - { PCI_VDEVICE(MARVELL, 0x5041), chip_504x }, - { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 }, - { PCI_VDEVICE(MARVELL, 0x5081), chip_508x }, - /* RocketRAID 1720/174x have different identifiers */ - { PCI_VDEVICE(TTI, 0x1720), chip_6042 }, - { PCI_VDEVICE(TTI, 0x1740), chip_6042 }, - { PCI_VDEVICE(TTI, 0x1742), chip_6042 }, - - { PCI_VDEVICE(MARVELL, 0x6040), chip_604x }, - { PCI_VDEVICE(MARVELL, 0x6041), chip_604x }, - { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 }, - { PCI_VDEVICE(MARVELL, 0x6080), chip_608x }, - { PCI_VDEVICE(MARVELL, 0x6081), chip_608x }, - - { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x }, - - /* Adaptec 1430SA */ - { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 }, - - /* Marvell 7042 support */ - { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 }, - - /* Highpoint RocketRAID PCIe series */ - { PCI_VDEVICE(TTI, 0x2300), chip_7042 }, - { PCI_VDEVICE(TTI, 0x2310), chip_7042 }, - - { } /* terminate list */ -}; - static const struct mv_hw_ops mv5xxx_ops = { .phy_errata = mv5_phy_errata, .enable_leds = mv5_enable_leds, @@ -4300,6 +4269,36 @@ static int mv_pci_init_one(struct pci_dev *pdev, static int mv_pci_device_resume(struct pci_dev *pdev); #endif +static const struct pci_device_id mv_pci_tbl[] = { + { PCI_VDEVICE(MARVELL, 0x5040), chip_504x }, + { PCI_VDEVICE(MARVELL, 0x5041), chip_504x }, + { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 }, + { PCI_VDEVICE(MARVELL, 0x5081), chip_508x }, + /* RocketRAID 1720/174x have different identifiers */ + { PCI_VDEVICE(TTI, 0x1720), chip_6042 }, + { PCI_VDEVICE(TTI, 0x1740), chip_6042 }, + { PCI_VDEVICE(TTI, 0x1742), chip_6042 }, + + { PCI_VDEVICE(MARVELL, 0x6040), chip_604x }, + { PCI_VDEVICE(MARVELL, 0x6041), chip_604x }, + { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 }, + { PCI_VDEVICE(MARVELL, 0x6080), chip_608x }, + { PCI_VDEVICE(MARVELL, 0x6081), chip_608x }, + + { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x }, + + /* Adaptec 1430SA */ + { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 }, + + /* Marvell 7042 support */ + { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 }, + + /* Highpoint RocketRAID PCIe series */ + { PCI_VDEVICE(TTI, 0x2300), chip_7042 }, + { PCI_VDEVICE(TTI, 0x2310), chip_7042 }, + + { } /* terminate list */ +}; static struct pci_driver mv_pci_driver = { .name = DRV_NAME, @@ -4312,6 +4311,7 @@ static struct pci_driver mv_pci_driver = { #endif }; +MODULE_DEVICE_TABLE(pci, mv_pci_tbl); /** * mv_print_info - Dump key info to kernel log for perusal. @@ -4484,7 +4484,6 @@ static void __exit mv_exit(void) MODULE_AUTHOR("Brett Russ"); MODULE_DESCRIPTION("SCSI low-level driver for Marvell SATA controllers"); MODULE_LICENSE("GPL v2"); -MODULE_DEVICE_TABLE(pci, mv_pci_tbl); MODULE_VERSION(DRV_VERSION); MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c index cc77c024828431..df095659bae0f5 100644 --- a/drivers/ata/sata_sil.c +++ b/drivers/ata/sata_sil.c @@ -128,7 +128,7 @@ static const struct pci_device_id sil_pci_tbl[] = { static const struct sil_drivelist { const char *product; unsigned int quirk; -} sil_blacklist [] = { +} sil_quirks[] = { { "ST320012AS", SIL_QUIRK_MOD15WRITE }, { "ST330013AS", SIL_QUIRK_MOD15WRITE }, { "ST340017AS", SIL_QUIRK_MOD15WRITE }, @@ -600,8 +600,8 @@ static void sil_thaw(struct ata_port *ap) * list, and apply the fixups to only the specific * devices/hosts/firmwares that need it. * - * 20040111 - Seagate drives affected by the Mod15Write bug are blacklisted - * The Maxtor quirk is in the blacklist, but I'm keeping the original + * 20040111 - Seagate drives affected by the Mod15Write bug are quirked + * The Maxtor quirk is in sil_quirks, but I'm keeping the original * pessimistic fix for the following reasons... * - There seems to be less info on it, only one device gleaned off the * Windows driver, maybe only one is affected. More info would be greatly @@ -620,9 +620,9 @@ static void sil_dev_config(struct ata_device *dev) ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num)); - for (n = 0; sil_blacklist[n].product; n++) - if (!strcmp(sil_blacklist[n].product, model_num)) { - quirks = sil_blacklist[n].quirk; + for (n = 0; sil_quirks[n].product; n++) + if (!strcmp(sil_quirks[n].product, model_num)) { + quirks = sil_quirks[n].quirk; break; } diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index b51d7a9d0d90ce..a482741eb181ff 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -957,8 +957,7 @@ static void pdc20621_get_from_dimm(struct ata_host *host, void *psource, offset -= (idx * window_size); idx++; - dist = ((long) (window_size - (offset + size))) >= 0 ? size : - (long) (window_size - offset); + dist = min(size, window_size - offset); memcpy_fromio(psource, dimm_mmio + offset / 4, dist); psource += dist; @@ -1005,8 +1004,7 @@ static void pdc20621_put_to_dimm(struct ata_host *host, void *psource, readl(mmio + PDC_DIMM_WINDOW_CTLR); offset -= (idx * window_size); idx++; - dist = ((long)(s32)(window_size - (offset + size))) >= 0 ? size : - (long) (window_size - offset); + dist = min(size, window_size - offset); memcpy_toio(dimm_mmio + offset / 4, psource, dist); writel(0x01, mmio + PDC_GENERAL_CTLR); readl(mmio + PDC_GENERAL_CTLR); diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index e327a0229dc173..a876024d8a05f9 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -1118,8 +1118,8 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) rpp->len += skb->len; if (stat & SAR_RSQE_EPDU) { + unsigned int len, truesize; unsigned char *l1l2; - unsigned int len; l1l2 = (unsigned char *) ((unsigned long) skb->data + skb->len - 6); @@ -1189,14 +1189,15 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) ATM_SKB(skb)->vcc = vcc; __net_timestamp(skb); + truesize = skb->truesize; vcc->push(vcc, skb); atomic_inc(&vcc->stats->rx); - if (skb->truesize > SAR_FB_SIZE_3) + if (truesize > SAR_FB_SIZE_3) add_rx_skb(card, 3, SAR_FB_SIZE_3, 1); - else if (skb->truesize > SAR_FB_SIZE_2) + else if (truesize > SAR_FB_SIZE_2) add_rx_skb(card, 2, SAR_FB_SIZE_2, 1); - else if (skb->truesize > SAR_FB_SIZE_1) + else if (truesize > SAR_FB_SIZE_1) add_rx_skb(card, 1, SAR_FB_SIZE_1, 1); else add_rx_skb(card, 0, SAR_FB_SIZE_0, 1); @@ -2930,6 +2931,8 @@ open_card_ubr0(struct idt77252_dev *card) vc->scq = alloc_scq(card, vc->class); if (!vc->scq) { printk("%s: can't get SCQ.\n", card->name); + kfree(card->vcs[0]); + card->vcs[0] = NULL; return -ENOMEM; } diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c index 32414868695305..9bba8f280a4d4c 100644 --- a/drivers/atm/iphase.c +++ b/drivers/atm/iphase.c @@ -2291,19 +2291,21 @@ static int get_esi(struct atm_dev *dev) static int reset_sar(struct atm_dev *dev) { IADEV *iadev; - int i, error = 1; + int i, error; unsigned int pci[64]; iadev = INPH_IA_DEV(dev); - for(i=0; i<64; i++) - if ((error = pci_read_config_dword(iadev->pci, - i*4, &pci[i])) != PCIBIOS_SUCCESSFUL) - return error; + for (i = 0; i < 64; i++) { + error = pci_read_config_dword(iadev->pci, i * 4, &pci[i]); + if (error != PCIBIOS_SUCCESSFUL) + return error; + } writel(0, iadev->reg+IPHASE5575_EXT_RESET); - for(i=0; i<64; i++) - if ((error = pci_write_config_dword(iadev->pci, - i*4, pci[i])) != PCIBIOS_SUCCESSFUL) - return error; + for (i = 0; i < 64; i++) { + error = pci_write_config_dword(iadev->pci, i * 4, pci[i]); + if (error != PCIBIOS_SUCCESSFUL) + return error; + } udelay(5); return 0; } diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c index 94fbc3abe60e6a..d3c30a28c410ea 100644 --- a/drivers/atm/solos-pci.c +++ b/drivers/atm/solos-pci.c @@ -449,9 +449,9 @@ static ssize_t console_show(struct device *dev, struct device_attribute *attr, struct sk_buff *skb; unsigned int len; - spin_lock(&card->cli_queue_lock); + spin_lock_bh(&card->cli_queue_lock); skb = skb_dequeue(&card->cli_queue[SOLOS_CHAN(atmdev)]); - spin_unlock(&card->cli_queue_lock); + spin_unlock_bh(&card->cli_queue_lock); if(skb == NULL) return sprintf(buf, "No data.\n"); @@ -956,14 +956,14 @@ static void pclose(struct atm_vcc *vcc) struct pkt_hdr *header; /* Remove any yet-to-be-transmitted packets from the pending queue */ - spin_lock(&card->tx_queue_lock); + spin_lock_bh(&card->tx_queue_lock); skb_queue_walk_safe(&card->tx_queue[port], skb, tmpskb) { if (SKB_CB(skb)->vcc == vcc) { skb_unlink(skb, &card->tx_queue[port]); solos_pop(vcc, skb); } } - spin_unlock(&card->tx_queue_lock); + spin_unlock_bh(&card->tx_queue_lock); skb = alloc_skb(sizeof(*header), GFP_KERNEL); if (!skb) { diff --git a/drivers/auxdisplay/ht16k33.c b/drivers/auxdisplay/ht16k33.c index 3a2d883872249e..b360ddefc4238b 100644 --- a/drivers/auxdisplay/ht16k33.c +++ b/drivers/auxdisplay/ht16k33.c @@ -507,6 +507,7 @@ static int ht16k33_led_probe(struct device *dev, struct led_classdev *led, led->max_brightness = MAX_BRIGHTNESS; err = devm_led_classdev_register_ext(dev, led, &init_data); + fwnode_handle_put(init_data.fwnode); if (err) dev_err(dev, "Failed to register LED\n"); diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index eaa31e567d1ece..5b59d133b6af4f 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -144,7 +144,7 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid) unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); -static int __init early_cpu_to_node(int cpu) +int __init early_cpu_to_node(int cpu) { return cpu_to_node_map[cpu]; } diff --git a/drivers/base/base.h b/drivers/base/base.h index eb4c0ace924201..a8e3d8165232fd 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -192,11 +192,14 @@ extern struct kset *devices_kset; void devices_kset_move_last(struct device *dev); #if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS) -void module_add_driver(struct module *mod, struct device_driver *drv); +int module_add_driver(struct module *mod, struct device_driver *drv); void module_remove_driver(struct device_driver *drv); #else -static inline void module_add_driver(struct module *mod, - struct device_driver *drv) { } +static inline int module_add_driver(struct module *mod, + struct device_driver *drv) +{ + return 0; +} static inline void module_remove_driver(struct device_driver *drv) { } #endif diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 84a21084d67d16..d4361ad3b433f5 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -152,7 +152,8 @@ static ssize_t bus_attr_show(struct kobject *kobj, struct attribute *attr, { struct bus_attribute *bus_attr = to_bus_attr(attr); struct subsys_private *subsys_priv = to_subsys_private(kobj); - ssize_t ret = 0; + /* return -EIO for reading a bus attribute without show() */ + ssize_t ret = -EIO; if (bus_attr->show) ret = bus_attr->show(subsys_priv->bus, buf); @@ -164,7 +165,8 @@ static ssize_t bus_attr_store(struct kobject *kobj, struct attribute *attr, { struct bus_attribute *bus_attr = to_bus_attr(attr); struct subsys_private *subsys_priv = to_subsys_private(kobj); - ssize_t ret = 0; + /* return -EIO for writing a bus attribute without store() */ + ssize_t ret = -EIO; if (bus_attr->store) ret = bus_attr->store(subsys_priv->bus, buf, count); @@ -674,7 +676,12 @@ int bus_add_driver(struct device_driver *drv) if (error) goto out_del_list; } - module_add_driver(drv->owner, drv); + error = module_add_driver(drv->owner, drv); + if (error) { + printk(KERN_ERR "%s: failed to create module links for %s\n", + __func__, drv->name); + goto out_detach; + } error = driver_create_file(drv, &driver_attr_uevent); if (error) { @@ -699,6 +706,8 @@ int bus_add_driver(struct device_driver *drv) return 0; +out_detach: + driver_detach(drv); out_del_list: klist_del(&priv->knode_bus); out_unregister: @@ -913,6 +922,8 @@ int bus_register(const struct bus_type *bus) bus_remove_file(bus, &bus_attr_uevent); bus_uevent_fail: kset_unregister(&priv->subsys); + /* Above kset_unregister() will kfree @priv */ + priv = NULL; out: kfree(priv); return retval; diff --git a/drivers/base/class.c b/drivers/base/class.c index 05d9df90f621be..9cd489a5770866 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -215,6 +215,7 @@ int class_register(const struct class *cls) return 0; err_out: + lockdep_unregister_key(key); kfree(cp); return error; } diff --git a/drivers/base/core.c b/drivers/base/core.c index 4d8b315c48a15a..60a0a4630a5bb2 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -44,6 +45,7 @@ static bool fw_devlink_is_permissive(void); static void __fw_devlink_link_to_consumers(struct device *dev); static bool fw_devlink_drv_reg_done; static bool fw_devlink_best_effort; +static struct workqueue_struct *device_link_wq; /** * __fwnode_link_add - Create a link between two fwnode_handles. @@ -283,10 +285,12 @@ static bool device_is_ancestor(struct device *dev, struct device *target) return false; } +#define DL_MARKER_FLAGS (DL_FLAG_INFERRED | \ + DL_FLAG_CYCLE | \ + DL_FLAG_MANAGED) static inline bool device_link_flag_is_sync_state_only(u32 flags) { - return (flags & ~(DL_FLAG_INFERRED | DL_FLAG_CYCLE)) == - (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED); + return (flags & ~DL_MARKER_FLAGS) == DL_FLAG_SYNC_STATE_ONLY; } /** @@ -529,12 +533,26 @@ static void devlink_dev_release(struct device *dev) /* * It may take a while to complete this work because of the SRCU * synchronization in device_link_release_fn() and if the consumer or - * supplier devices get deleted when it runs, so put it into the "long" - * workqueue. + * supplier devices get deleted when it runs, so put it into the + * dedicated workqueue. */ - queue_work(system_long_wq, &link->rm_work); + queue_work(device_link_wq, &link->rm_work); } +/** + * device_link_wait_removal - Wait for ongoing devlink removal jobs to terminate + */ +void device_link_wait_removal(void) +{ + /* + * devlink removal jobs are queued in the dedicated work queue. + * To be sure that all removal jobs are terminated, ensure that any + * scheduled work has run to completion. + */ + flush_workqueue(device_link_wq); +} +EXPORT_SYMBOL_GPL(device_link_wait_removal); + static struct class devlink_class = { .name = "devlink", .dev_groups = devlink_groups, @@ -2057,9 +2075,14 @@ static int fw_devlink_create_devlink(struct device *con, /* * SYNC_STATE_ONLY device links don't block probing and supports cycles. - * So cycle detection isn't necessary and shouldn't be done. + * So, one might expect that cycle detection isn't necessary for them. + * However, if the device link was marked as SYNC_STATE_ONLY because + * it's part of a cycle, then we still need to do cycle detection. This + * is because the consumer and supplier might be part of multiple cycles + * and we need to detect all those cycles. */ - if (!(flags & DL_FLAG_SYNC_STATE_ONLY)) { + if (!device_link_flag_is_sync_state_only(flags) || + flags & DL_FLAG_CYCLE) { device_links_write_lock(); if (__fw_devlink_relax_cycles(con, sup_handle)) { __fwnode_link_cycle(link); @@ -2543,6 +2566,7 @@ static const char *dev_uevent_name(const struct kobject *kobj) static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { const struct device *dev = kobj_to_dev(kobj); + struct device_driver *driver; int retval = 0; /* add device node properties if present */ @@ -2571,8 +2595,12 @@ static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) if (dev->type && dev->type->name) add_uevent_var(env, "DEVTYPE=%s", dev->type->name); - if (dev->driver) - add_uevent_var(env, "DRIVER=%s", dev->driver->name); + /* Synchronize with module_remove_driver() */ + rcu_read_lock(); + driver = READ_ONCE(dev->driver); + if (driver) + add_uevent_var(env, "DRIVER=%s", driver->name); + rcu_read_unlock(); /* Add common DT information about the device */ of_device_uevent(dev, env); @@ -4083,9 +4111,14 @@ int __init devices_init(void) sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj); if (!sysfs_dev_char_kobj) goto char_kobj_err; + device_link_wq = alloc_workqueue("device_link_wq", 0, 0); + if (!device_link_wq) + goto wq_err; return 0; + wq_err: + kobject_put(sysfs_dev_char_kobj); char_kobj_err: kobject_put(sysfs_dev_block_kobj); block_kobj_err: @@ -4452,9 +4485,11 @@ EXPORT_SYMBOL_GPL(device_destroy); */ int device_rename(struct device *dev, const char *new_name) { + struct subsys_private *sp = NULL; struct kobject *kobj = &dev->kobj; char *old_device_name = NULL; int error; + bool is_link_renamed = false; dev = get_device(dev); if (!dev) @@ -4469,7 +4504,7 @@ int device_rename(struct device *dev, const char *new_name) } if (dev->class) { - struct subsys_private *sp = class_to_subsys(dev->class); + sp = class_to_subsys(dev->class); if (!sp) { error = -EINVAL; @@ -4478,16 +4513,19 @@ int device_rename(struct device *dev, const char *new_name) error = sysfs_rename_link_ns(&sp->subsys.kobj, kobj, old_device_name, new_name, kobject_namespace(kobj)); - subsys_put(sp); if (error) goto out; + + is_link_renamed = true; } error = kobject_rename(kobj, new_name); - if (error) - goto out; - out: + if (error && is_link_renamed) + sysfs_rename_link_ns(&sp->subsys.kobj, kobj, new_name, + old_device_name, kobject_namespace(kobj)); + subsys_put(sp); + put_device(dev); kfree(old_device_name); diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 9ea22e165acd67..ef427ee787a99b 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -144,7 +144,7 @@ static DEVICE_ATTR(release, S_IWUSR, NULL, cpu_release_store); #endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ #endif /* CONFIG_HOTPLUG_CPU */ -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE #include static ssize_t crash_notes_show(struct device *dev, @@ -189,14 +189,14 @@ static const struct attribute_group crash_note_cpu_attr_group = { #endif static const struct attribute_group *common_cpu_attr_groups[] = { -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE &crash_note_cpu_attr_group, #endif NULL }; static const struct attribute_group *hotplugable_cpu_attr_groups[] = { -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE &crash_note_cpu_attr_group, #endif NULL @@ -565,6 +565,7 @@ CPU_SHOW_VULN_FALLBACK(mmio_stale_data); CPU_SHOW_VULN_FALLBACK(retbleed); CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow); CPU_SHOW_VULN_FALLBACK(gds); +CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling); static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); @@ -579,6 +580,7 @@ static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); +static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -594,6 +596,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_retbleed.attr, &dev_attr_spec_rstack_overflow.attr, &dev_attr_gather_data_sampling.attr, + &dev_attr_reg_file_data_sampling.attr, NULL }; diff --git a/drivers/base/dd.c b/drivers/base/dd.c index a528cec24264ab..0c3725c3eefa46 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -1274,8 +1274,8 @@ static void __device_release_driver(struct device *dev, struct device *parent) if (dev->bus && dev->bus->dma_cleanup) dev->bus->dma_cleanup(dev); - device_links_driver_cleanup(dev); device_unbind_cleanup(dev); + device_links_driver_cleanup(dev); klist_remove(&dev->p->knode_driver); device_pm_check_callbacks(dev); diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c index 91536ee05f144e..7e2d1f0d903a6e 100644 --- a/drivers/base/devcoredump.c +++ b/drivers/base/devcoredump.c @@ -362,6 +362,7 @@ void dev_coredumpm(struct device *dev, struct module *owner, devcd->devcd_dev.class = &devcd_class; mutex_lock(&devcd->mutex); + dev_set_uevent_suppress(&devcd->devcd_dev, true); if (device_add(&devcd->devcd_dev)) goto put_device; @@ -376,6 +377,8 @@ void dev_coredumpm(struct device *dev, struct module *owner, "devcoredump")) dev_warn(dev, "devcoredump create_link failed\n"); + dev_set_uevent_suppress(&devcd->devcd_dev, false); + kobject_uevent(&devcd->devcd_dev.kobj, KOBJ_ADD); INIT_DELAYED_WORK(&devcd->del_wk, devcd_del); schedule_delayed_work(&devcd->del_wk, DEVCD_TIMEOUT); mutex_unlock(&devcd->mutex); diff --git a/drivers/base/devres.c b/drivers/base/devres.c index 3df0025d12aa48..e9b0d94aeabd90 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -567,6 +567,7 @@ void * devres_open_group(struct device *dev, void *id, gfp_t gfp) grp->id = grp; if (id) grp->id = id; + grp->color = 0; spin_lock_irqsave(&dev->devres_lock, flags); add_dr(dev, &grp->node[0]); @@ -896,9 +897,12 @@ void *devm_krealloc(struct device *dev, void *ptr, size_t new_size, gfp_t gfp) /* * Otherwise: allocate new, larger chunk. We need to allocate before * taking the lock as most probably the caller uses GFP_KERNEL. + * alloc_dr() will call check_dr_size() to reserve extra memory + * for struct devres automatically, so size @new_size user request + * is delivered to it directly as devm_kmalloc() does. */ new_dr = alloc_dr(devm_kmalloc_release, - total_new_size, gfp, dev_to_node(dev)); + new_size, gfp, dev_to_node(dev)); if (!new_dr) return NULL; @@ -1222,7 +1226,11 @@ EXPORT_SYMBOL_GPL(__devm_alloc_percpu); */ void devm_free_percpu(struct device *dev, void __percpu *pdata) { - WARN_ON(devres_destroy(dev, devm_percpu_release, devm_percpu_match, + /* + * Use devres_release() to prevent memory leakage as + * devm_free_pages() does. + */ + WARN_ON(devres_release(dev, devm_percpu_release, devm_percpu_match, (__force void *)pdata)); } EXPORT_SYMBOL_GPL(devm_free_percpu); diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index b58c42f1b1ce65..0b18c6b46e65d8 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -844,6 +844,26 @@ static void fw_log_firmware_info(const struct firmware *fw, const char *name, {} #endif +/* + * Reject firmware file names with ".." path components. + * There are drivers that construct firmware file names from device-supplied + * strings, and we don't want some device to be able to tell us "I would like to + * be sent my firmware from ../../../etc/shadow, please". + * + * Search for ".." surrounded by either '/' or start/end of string. + * + * This intentionally only looks at the firmware name, not at the firmware base + * directory or at symlink contents. + */ +static bool name_contains_dotdot(const char *name) +{ + size_t name_len = strlen(name); + + return strcmp(name, "..") == 0 || strncmp(name, "../", 3) == 0 || + strstr(name, "/../") != NULL || + (name_len >= 3 && strcmp(name+name_len-3, "/..") == 0); +} + /* called from request_firmware() and request_firmware_work_func() */ static int _request_firmware(const struct firmware **firmware_p, const char *name, @@ -864,6 +884,14 @@ _request_firmware(const struct firmware **firmware_p, const char *name, goto out; } + if (name_contains_dotdot(name)) { + dev_warn(device, + "Firmware load for '%s' refused, path contains '..' component\n", + name); + ret = -EINVAL; + goto out; + } + ret = _request_firmware_prepare(&fw, name, device, buf, size, offset, opt_flags); if (ret <= 0) /* error or already assigned */ @@ -941,6 +969,8 @@ _request_firmware(const struct firmware **firmware_p, const char *name, * @name will be used as $FIRMWARE in the uevent environment and * should be distinctive enough not to be confused with any other * firmware image for this or any other device. + * It must not contain any ".." path components - "foo/bar..bin" is + * allowed, but "foo/../bar.bin" is not. * * Caller must hold the reference count of @device. * diff --git a/drivers/base/memory.c b/drivers/base/memory.c index f3b9a4d0fa3bb2..8a13babd826ce3 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -180,6 +180,9 @@ static inline unsigned long memblk_nr_poison(struct memory_block *mem) } #endif +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_online(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -204,10 +207,11 @@ static int memory_block_online(struct memory_block *mem) if (mem->altmap) nr_vmemmap_pages = mem->altmap->free; + mem_hotplug_begin(); if (nr_vmemmap_pages) { ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); if (ret) - return ret; + goto out; } ret = online_pages(start_pfn + nr_vmemmap_pages, @@ -215,7 +219,7 @@ static int memory_block_online(struct memory_block *mem) if (ret) { if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); - return ret; + goto out; } /* @@ -227,9 +231,14 @@ static int memory_block_online(struct memory_block *mem) nr_vmemmap_pages); mem->zone = zone; +out: + mem_hotplug_done(); return ret; } +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_offline(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -247,6 +256,7 @@ static int memory_block_offline(struct memory_block *mem) if (mem->altmap) nr_vmemmap_pages = mem->altmap->free; + mem_hotplug_begin(); if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, -nr_vmemmap_pages); @@ -258,13 +268,15 @@ static int memory_block_offline(struct memory_block *mem) if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, nr_vmemmap_pages); - return ret; + goto out; } if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); mem->zone = NULL; +out: + mem_hotplug_done(); return ret; } diff --git a/drivers/base/module.c b/drivers/base/module.c index 46ad4d636731dd..0d5c5da367f720 100644 --- a/drivers/base/module.c +++ b/drivers/base/module.c @@ -7,6 +7,7 @@ #include #include #include +#include #include "base.h" static char *make_driver_name(struct device_driver *drv) @@ -30,14 +31,14 @@ static void module_create_drivers_dir(struct module_kobject *mk) mutex_unlock(&drivers_dir_mutex); } -void module_add_driver(struct module *mod, struct device_driver *drv) +int module_add_driver(struct module *mod, struct device_driver *drv) { char *driver_name; - int no_warn; struct module_kobject *mk = NULL; + int ret; if (!drv) - return; + return 0; if (mod) mk = &mod->mkobj; @@ -56,17 +57,41 @@ void module_add_driver(struct module *mod, struct device_driver *drv) } if (!mk) - return; + return 0; + + ret = sysfs_create_link(&drv->p->kobj, &mk->kobj, "module"); + if (ret) + return ret; - /* Don't check return codes; these calls are idempotent */ - no_warn = sysfs_create_link(&drv->p->kobj, &mk->kobj, "module"); driver_name = make_driver_name(drv); - if (driver_name) { - module_create_drivers_dir(mk); - no_warn = sysfs_create_link(mk->drivers_dir, &drv->p->kobj, - driver_name); - kfree(driver_name); + if (!driver_name) { + ret = -ENOMEM; + goto out_remove_kobj; } + + module_create_drivers_dir(mk); + if (!mk->drivers_dir) { + ret = -EINVAL; + goto out_free_driver_name; + } + + ret = sysfs_create_link(mk->drivers_dir, &drv->p->kobj, driver_name); + if (ret) + goto out_remove_drivers_dir; + + kfree(driver_name); + + return 0; + +out_remove_drivers_dir: + sysfs_remove_link(mk->drivers_dir, driver_name); + +out_free_driver_name: + kfree(driver_name); + +out_remove_kobj: + sysfs_remove_link(&drv->p->kobj, "module"); + return ret; } void module_remove_driver(struct device_driver *drv) @@ -77,6 +102,9 @@ void module_remove_driver(struct device_driver *drv) if (!drv) return; + /* Synchronize with dev_uevent() */ + synchronize_rcu(); + sysfs_remove_link(&drv->p->kobj, "module"); if (drv->owner) diff --git a/drivers/base/node.c b/drivers/base/node.c index 493d533f837556..4d588f4658c85c 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -868,11 +868,15 @@ int __register_one_node(int nid) { int error; int cpu; + struct node *node; - node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL); - if (!node_devices[nid]) + node = kzalloc(sizeof(struct node), GFP_KERNEL); + if (!node) return -ENOMEM; + INIT_LIST_HEAD(&node->access_list); + node_devices[nid] = node; + error = register_node(node_devices[nid], nid); /* link cpu under this node */ @@ -881,7 +885,6 @@ int __register_one_node(int nid) register_cpu_under_node(cpu, nid); } - INIT_LIST_HEAD(&node_devices[nid]->access_list); node_init_caches(nid); return error; diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 5cb2023581d4db..582564f8dde6f9 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1102,7 +1102,7 @@ static int __init genpd_power_off_unused(void) return 0; } -late_initcall(genpd_power_off_unused); +late_initcall_sync(genpd_power_off_unused); #ifdef CONFIG_PM_SLEEP @@ -3135,7 +3135,7 @@ static int genpd_summary_one(struct seq_file *s, else snprintf(state, sizeof(state), "%s", status_lookup[genpd->status]); - seq_printf(s, "%-30s %-50s %u", genpd->name, state, genpd->performance_state); + seq_printf(s, "%-30s %-49s %u", genpd->name, state, genpd->performance_state); /* * Modifications on the list require holding locks on both diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index f85f3515c258fc..9c5a5f4dba5a6e 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -579,7 +579,7 @@ bool dev_pm_skip_resume(struct device *dev) } /** - * device_resume_noirq - Execute a "noirq resume" callback for given device. + * __device_resume_noirq - Execute a "noirq resume" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. @@ -587,7 +587,7 @@ bool dev_pm_skip_resume(struct device *dev) * The driver of @dev will not receive interrupts while this function is being * executed. */ -static int device_resume_noirq(struct device *dev, pm_message_t state, bool async) +static void __device_resume_noirq(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -655,7 +655,13 @@ static int device_resume_noirq(struct device *dev, pm_message_t state, bool asyn Out: complete_all(&dev->power.completion); TRACE_RESUME(error); - return error; + + if (error) { + suspend_stats.failed_resume_noirq++; + dpm_save_failed_step(SUSPEND_RESUME_NOIRQ); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async noirq" : " noirq", error); + } } static bool is_async(struct device *dev) @@ -668,11 +674,15 @@ static bool dpm_async_fn(struct device *dev, async_func_t func) { reinit_completion(&dev->power.completion); - if (is_async(dev)) { - get_device(dev); - async_schedule_dev(func, dev); + if (!is_async(dev)) + return false; + + get_device(dev); + + if (async_schedule_dev_nocall(func, dev)) return true; - } + + put_device(dev); return false; } @@ -680,15 +690,19 @@ static bool dpm_async_fn(struct device *dev, async_func_t func) static void async_resume_noirq(void *data, async_cookie_t cookie) { struct device *dev = data; - int error; - - error = device_resume_noirq(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error); + __device_resume_noirq(dev, pm_transition, true); put_device(dev); } +static void device_resume_noirq(struct device *dev) +{ + if (dpm_async_fn(dev, async_resume_noirq)) + return; + + __device_resume_noirq(dev, pm_transition, false); +} + static void dpm_noirq_resume_devices(pm_message_t state) { struct device *dev; @@ -698,14 +712,6 @@ static void dpm_noirq_resume_devices(pm_message_t state) mutex_lock(&dpm_list_mtx); pm_transition = state; - /* - * Advanced the async threads upfront, - * in case the starting of async threads is - * delayed by non-async resuming devices. - */ - list_for_each_entry(dev, &dpm_noirq_list, power.entry) - dpm_async_fn(dev, async_resume_noirq); - while (!list_empty(&dpm_noirq_list)) { dev = to_device(dpm_noirq_list.next); get_device(dev); @@ -713,17 +719,7 @@ static void dpm_noirq_resume_devices(pm_message_t state) mutex_unlock(&dpm_list_mtx); - if (!is_async(dev)) { - int error; - - error = device_resume_noirq(dev, state, false); - if (error) { - suspend_stats.failed_resume_noirq++; - dpm_save_failed_step(SUSPEND_RESUME_NOIRQ); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, " noirq", error); - } - } + device_resume_noirq(dev); put_device(dev); @@ -751,14 +747,14 @@ void dpm_resume_noirq(pm_message_t state) } /** - * device_resume_early - Execute an "early resume" callback for given device. + * __device_resume_early - Execute an "early resume" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. * * Runtime PM is disabled for @dev while this function is being executed. */ -static int device_resume_early(struct device *dev, pm_message_t state, bool async) +static void __device_resume_early(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -811,21 +807,31 @@ static int device_resume_early(struct device *dev, pm_message_t state, bool asyn pm_runtime_enable(dev); complete_all(&dev->power.completion); - return error; + + if (error) { + suspend_stats.failed_resume_early++; + dpm_save_failed_step(SUSPEND_RESUME_EARLY); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async early" : " early", error); + } } static void async_resume_early(void *data, async_cookie_t cookie) { struct device *dev = data; - int error; - - error = device_resume_early(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error); + __device_resume_early(dev, pm_transition, true); put_device(dev); } +static void device_resume_early(struct device *dev) +{ + if (dpm_async_fn(dev, async_resume_early)) + return; + + __device_resume_early(dev, pm_transition, false); +} + /** * dpm_resume_early - Execute "early resume" callbacks for all devices. * @state: PM transition of the system being carried out. @@ -839,14 +845,6 @@ void dpm_resume_early(pm_message_t state) mutex_lock(&dpm_list_mtx); pm_transition = state; - /* - * Advanced the async threads upfront, - * in case the starting of async threads is - * delayed by non-async resuming devices. - */ - list_for_each_entry(dev, &dpm_late_early_list, power.entry) - dpm_async_fn(dev, async_resume_early); - while (!list_empty(&dpm_late_early_list)) { dev = to_device(dpm_late_early_list.next); get_device(dev); @@ -854,17 +852,7 @@ void dpm_resume_early(pm_message_t state) mutex_unlock(&dpm_list_mtx); - if (!is_async(dev)) { - int error; - - error = device_resume_early(dev, state, false); - if (error) { - suspend_stats.failed_resume_early++; - dpm_save_failed_step(SUSPEND_RESUME_EARLY); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, " early", error); - } - } + device_resume_early(dev); put_device(dev); @@ -888,12 +876,12 @@ void dpm_resume_start(pm_message_t state) EXPORT_SYMBOL_GPL(dpm_resume_start); /** - * device_resume - Execute "resume" callbacks for given device. + * __device_resume - Execute "resume" callbacks for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. */ -static int device_resume(struct device *dev, pm_message_t state, bool async) +static void __device_resume(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -975,20 +963,30 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) TRACE_RESUME(error); - return error; + if (error) { + suspend_stats.failed_resume++; + dpm_save_failed_step(SUSPEND_RESUME); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async" : "", error); + } } static void async_resume(void *data, async_cookie_t cookie) { struct device *dev = data; - int error; - error = device_resume(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error); + __device_resume(dev, pm_transition, true); put_device(dev); } +static void device_resume(struct device *dev) +{ + if (dpm_async_fn(dev, async_resume)) + return; + + __device_resume(dev, pm_transition, false); +} + /** * dpm_resume - Execute "resume" callbacks for non-sysdev devices. * @state: PM transition of the system being carried out. @@ -1008,27 +1006,17 @@ void dpm_resume(pm_message_t state) pm_transition = state; async_error = 0; - list_for_each_entry(dev, &dpm_suspended_list, power.entry) - dpm_async_fn(dev, async_resume); - while (!list_empty(&dpm_suspended_list)) { dev = to_device(dpm_suspended_list.next); + get_device(dev); - if (!is_async(dev)) { - int error; - mutex_unlock(&dpm_list_mtx); + mutex_unlock(&dpm_list_mtx); + + device_resume(dev); - error = device_resume(dev, state, false); - if (error) { - suspend_stats.failed_resume++; - dpm_save_failed_step(SUSPEND_RESUME); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, "", error); - } + mutex_lock(&dpm_list_mtx); - mutex_lock(&dpm_list_mtx); - } if (!list_empty(&dev->power.entry)) list_move_tail(&dev->power.entry, &dpm_prepared_list); diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c index 72b7a92337b188..cd6e559648b21b 100644 --- a/drivers/base/power/trace.c +++ b/drivers/base/power/trace.c @@ -120,7 +120,7 @@ static unsigned int read_magic_time(void) struct rtc_time time; unsigned int val; - if (mc146818_get_time(&time) < 0) { + if (mc146818_get_time(&time, 1000) < 0) { pr_err("Unable to read current time from RTC\n"); return 0; } diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index 42171f766dcba6..5a5a9e978e85f3 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -313,8 +313,10 @@ void dev_pm_enable_wake_irq_complete(struct device *dev) return; if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED && - wirq->status & WAKE_IRQ_DEDICATED_REVERSE) + wirq->status & WAKE_IRQ_DEDICATED_REVERSE) { enable_irq(wirq->irq); + wirq->status |= WAKE_IRQ_DEDICATED_ENABLED; + } } /** diff --git a/drivers/base/regmap/regcache-maple.c b/drivers/base/regmap/regcache-maple.c index 41edd6a430eb45..0b6c2277128b42 100644 --- a/drivers/base/regmap/regcache-maple.c +++ b/drivers/base/regmap/regcache-maple.c @@ -110,9 +110,10 @@ static int regcache_maple_drop(struct regmap *map, unsigned int min, struct maple_tree *mt = map->cache; MA_STATE(mas, mt, min, max); unsigned long *entry, *lower, *upper; - unsigned long lower_index, lower_last; + /* initialized to work around false-positive -Wuninitialized warning */ + unsigned long lower_index = 0, lower_last = 0; unsigned long upper_index, upper_last; - int ret; + int ret = 0; lower = NULL; upper = NULL; @@ -145,7 +146,7 @@ static int regcache_maple_drop(struct regmap *map, unsigned int min, upper_index = max + 1; upper_last = mas.last; - upper = kmemdup(&entry[max + 1], + upper = kmemdup(&entry[max - mas.index + 1], ((mas.last - max) * sizeof(unsigned long)), map->alloc_flags); @@ -244,7 +245,7 @@ static int regcache_maple_sync(struct regmap *map, unsigned int min, unsigned long lmin = min; unsigned long lmax = max; unsigned int r, v, sync_start; - int ret; + int ret = 0; bool sync_needed = false; map->cache_bypass = true; diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index c5d151e9c48159..ac63a73ccdaaa2 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -334,6 +334,11 @@ static int regcache_default_sync(struct regmap *map, unsigned int min, return 0; } +static int rbtree_all(const void *key, const struct rb_node *node) +{ + return 0; +} + /** * regcache_sync - Sync the register cache with the hardware. * @@ -351,6 +356,7 @@ int regcache_sync(struct regmap *map) unsigned int i; const char *name; bool bypass; + struct rb_node *node; if (WARN_ON(map->cache_type == REGCACHE_NONE)) return -EINVAL; @@ -392,6 +398,29 @@ int regcache_sync(struct regmap *map) /* Restore the bypass state */ map->cache_bypass = bypass; map->no_sync_defaults = false; + + /* + * If we did any paging with cache bypassed and a cached + * paging register then the register and cache state might + * have gone out of sync, force writes of all the paging + * registers. + */ + rb_for_each(node, 0, &map->range_tree, rbtree_all) { + struct regmap_range_node *this = + rb_entry(node, struct regmap_range_node, node); + + /* If there's nothing in the cache there's nothing to sync */ + if (regcache_read(map, this->selector_reg, &i) != 0) + continue; + + ret = _regmap_write(map, this->selector_reg, i); + if (ret != 0) { + dev_err(map->dev, "Failed to write %x = %x: %d\n", + this->selector_reg, i, ret); + break; + } + } + map->unlock(map->lock_arg); regmap_async_complete(map); diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c index f36027591e1a8d..bdd80b73c3e6c1 100644 --- a/drivers/base/regmap/regmap-debugfs.c +++ b/drivers/base/regmap/regmap-debugfs.c @@ -48,7 +48,7 @@ static ssize_t regmap_name_read_file(struct file *file, name = map->dev->driver->name; ret = snprintf(buf, PAGE_SIZE, "%s\n", name); - if (ret < 0) { + if (ret >= PAGE_SIZE) { kfree(buf); return ret; } diff --git a/drivers/base/regmap/regmap-i2c.c b/drivers/base/regmap/regmap-i2c.c index 3ec611dc0c09fb..a905e955bbfc78 100644 --- a/drivers/base/regmap/regmap-i2c.c +++ b/drivers/base/regmap/regmap-i2c.c @@ -350,7 +350,8 @@ static const struct regmap_bus *regmap_get_i2c_bus(struct i2c_client *i2c, if (quirks->max_write_len && (bus->max_raw_write == 0 || bus->max_raw_write > quirks->max_write_len)) - max_write = quirks->max_write_len; + max_write = quirks->max_write_len - + (config->reg_bits + config->pad_bits) / BITS_PER_BYTE; if (max_read || max_write) { ret_bus = kmemdup(bus, sizeof(*bus), GFP_KERNEL); diff --git a/drivers/base/regmap/regmap-kunit.c b/drivers/base/regmap/regmap-kunit.c index 264d29b3fced0b..5f1e914646cd91 100644 --- a/drivers/base/regmap/regmap-kunit.c +++ b/drivers/base/regmap/regmap-kunit.c @@ -9,6 +9,23 @@ #define BLOCK_TEST_SIZE 12 +static void get_changed_bytes(void *orig, void *new, size_t size) +{ + char *o = orig; + char *n = new; + int i; + + get_random_bytes(new, size); + + /* + * This could be nicer and more efficient but we shouldn't + * super care. + */ + for (i = 0; i < size; i++) + while (n[i] == o[i]) + get_random_bytes(&n[i], 1); +} + static const struct regmap_config test_regmap_config = { .max_register = BLOCK_TEST_SIZE, .reg_stride = 1, @@ -1131,7 +1148,7 @@ static void raw_sync(struct kunit *test) struct regmap *map; struct regmap_config config; struct regmap_ram_data *data; - u16 val[2]; + u16 val[3]; u16 *hw_buf; unsigned int rval; int i; @@ -1145,17 +1162,13 @@ static void raw_sync(struct kunit *test) hw_buf = (u16 *)data->vals; - get_random_bytes(&val, sizeof(val)); + get_changed_bytes(&hw_buf[2], &val[0], sizeof(val)); /* Do a regular write and a raw write in cache only mode */ regcache_cache_only(map, true); - KUNIT_EXPECT_EQ(test, 0, regmap_raw_write(map, 2, val, sizeof(val))); - if (config.val_format_endian == REGMAP_ENDIAN_BIG) - KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 6, - be16_to_cpu(val[0]))); - else - KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 6, - le16_to_cpu(val[0]))); + KUNIT_EXPECT_EQ(test, 0, regmap_raw_write(map, 2, val, + sizeof(u16) * 2)); + KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 4, val[2])); /* We should read back the new values, and defaults for the rest */ for (i = 0; i < config.max_register + 1; i++) { @@ -1164,24 +1177,34 @@ static void raw_sync(struct kunit *test) switch (i) { case 2: case 3: - case 6: if (config.val_format_endian == REGMAP_ENDIAN_BIG) { KUNIT_EXPECT_EQ(test, rval, - be16_to_cpu(val[i % 2])); + be16_to_cpu(val[i - 2])); } else { KUNIT_EXPECT_EQ(test, rval, - le16_to_cpu(val[i % 2])); + le16_to_cpu(val[i - 2])); } break; + case 4: + KUNIT_EXPECT_EQ(test, rval, val[i - 2]); + break; default: KUNIT_EXPECT_EQ(test, config.reg_defaults[i].def, rval); break; } } + + /* + * The value written via _write() was translated by the core, + * translate the original copy for comparison purposes. + */ + if (config.val_format_endian == REGMAP_ENDIAN_BIG) + val[2] = cpu_to_be16(val[2]); + else + val[2] = cpu_to_le16(val[2]); /* The values should not appear in the "hardware" */ - KUNIT_EXPECT_MEMNEQ(test, &hw_buf[2], val, sizeof(val)); - KUNIT_EXPECT_MEMNEQ(test, &hw_buf[6], val, sizeof(u16)); + KUNIT_EXPECT_MEMNEQ(test, &hw_buf[2], &val[0], sizeof(val)); for (i = 0; i < config.max_register + 1; i++) data->written[i] = false; @@ -1192,8 +1215,7 @@ static void raw_sync(struct kunit *test) KUNIT_EXPECT_EQ(test, 0, regcache_sync(map)); /* The values should now appear in the "hardware" */ - KUNIT_EXPECT_MEMEQ(test, &hw_buf[2], val, sizeof(val)); - KUNIT_EXPECT_MEMEQ(test, &hw_buf[6], val, sizeof(u16)); + KUNIT_EXPECT_MEMEQ(test, &hw_buf[2], &val[0], sizeof(val)); regmap_exit(map); } diff --git a/drivers/base/regmap/regmap-spi.c b/drivers/base/regmap/regmap-spi.c index 37ab23a9d0345a..7f14c5ed1e2294 100644 --- a/drivers/base/regmap/regmap-spi.c +++ b/drivers/base/regmap/regmap-spi.c @@ -122,8 +122,7 @@ static const struct regmap_bus *regmap_get_spi_bus(struct spi_device *spi, return ERR_PTR(-ENOMEM); max_msg_size = spi_max_message_size(spi); - reg_reserve_size = config->reg_bits / BITS_PER_BYTE - + config->pad_bits / BITS_PER_BYTE; + reg_reserve_size = (config->reg_bits + config->pad_bits) / BITS_PER_BYTE; if (max_size + reg_reserve_size > max_msg_size) max_size -= reg_reserve_size; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 234a84ecde8b1b..c5b5241891a5a6 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1620,17 +1620,19 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, } if (!map->cache_bypass && map->format.parse_val) { - unsigned int ival; + unsigned int ival, offset; int val_bytes = map->format.val_bytes; - for (i = 0; i < val_len / val_bytes; i++) { - ival = map->format.parse_val(val + (i * val_bytes)); - ret = regcache_write(map, - reg + regmap_get_offset(map, i), - ival); + + /* Cache the last written value for noinc writes */ + i = noinc ? val_len - val_bytes : 0; + for (; i < val_len; i += val_bytes) { + ival = map->format.parse_val(val + i); + offset = noinc ? 0 : regmap_get_offset(map, i / val_bytes); + ret = regcache_write(map, reg + offset, ival); if (ret) { dev_err(map->dev, "Error in caching of register: %x ret: %d\n", - reg + regmap_get_offset(map, i), ret); + reg + offset, ret); return ret; } } @@ -2834,6 +2836,43 @@ int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val) } EXPORT_SYMBOL_GPL(regmap_read); +/** + * regmap_read_bypassed() - Read a value from a single register direct + * from the device, bypassing the cache + * + * @map: Register map to read from + * @reg: Register to be read from + * @val: Pointer to store read value + * + * A value of zero will be returned on success, a negative errno will + * be returned in error cases. + */ +int regmap_read_bypassed(struct regmap *map, unsigned int reg, unsigned int *val) +{ + int ret; + bool bypass, cache_only; + + if (!IS_ALIGNED(reg, map->reg_stride)) + return -EINVAL; + + map->lock(map->lock_arg); + + bypass = map->cache_bypass; + cache_only = map->cache_only; + map->cache_bypass = true; + map->cache_only = false; + + ret = _regmap_read(map, reg, val); + + map->cache_bypass = bypass; + map->cache_only = cache_only; + + map->unlock(map->lock_arg); + + return ret; +} +EXPORT_SYMBOL_GPL(regmap_read_bypassed); + /** * regmap_raw_read() - Read raw data from the device * diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c index 1886995a0b3a30..079bd14bdedc7c 100644 --- a/drivers/base/swnode.c +++ b/drivers/base/swnode.c @@ -541,6 +541,9 @@ software_node_get_reference_args(const struct fwnode_handle *fwnode, if (nargs > NR_FWNODE_REFERENCE_ARGS) return -EINVAL; + if (!args) + return 0; + args->fwnode = software_node_get(refnode); args->nargs = nargs; diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index cf6883756155a3..37eff1c9745155 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -333,6 +333,7 @@ aoeblk_gdalloc(void *vp) struct gendisk *gd; mempool_t *mp; struct blk_mq_tag_set *set; + sector_t ssize; ulong flags; int late = 0; int err; @@ -395,7 +396,7 @@ aoeblk_gdalloc(void *vp) gd->minors = AOE_PARTITIONS; gd->fops = &aoe_bdops; gd->private_data = d; - set_capacity(gd, d->ssize); + ssize = d->ssize; snprintf(gd->disk_name, sizeof gd->disk_name, "etherd/e%ld.%d", d->aoemajor, d->aoeminor); @@ -404,6 +405,8 @@ aoeblk_gdalloc(void *vp) spin_unlock_irqrestore(&d->lock, flags); + set_capacity(gd, ssize); + err = device_add_disk(NULL, gd, aoe_attr_groups); if (err) goto out_disk_cleanup; diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index d7317425be510d..d1f4ddc576451a 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -361,6 +361,7 @@ ata_rw_frameinit(struct frame *f) } ah->cmdstat = ATA_CMD_PIO_READ | writebit | extbit; + dev_hold(t->ifp->nd); skb->dev = t->ifp->nd; } @@ -401,6 +402,8 @@ aoecmd_ata_rw(struct aoedev *d) __skb_queue_head_init(&queue); __skb_queue_tail(&queue, skb); aoenet_xmit(&queue); + } else { + dev_put(f->t->ifp->nd); } return 1; } @@ -419,13 +422,16 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu rcu_read_lock(); for_each_netdev_rcu(&init_net, ifp) { dev_hold(ifp); - if (!is_aoe_netif(ifp)) - goto cont; + if (!is_aoe_netif(ifp)) { + dev_put(ifp); + continue; + } skb = new_skb(sizeof *h + sizeof *ch); if (skb == NULL) { printk(KERN_INFO "aoe: skb alloc failure\n"); - goto cont; + dev_put(ifp); + continue; } skb_put(skb, sizeof *h + sizeof *ch); skb->dev = ifp; @@ -440,9 +446,6 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu h->major = cpu_to_be16(aoemajor); h->minor = aoeminor; h->cmd = AOECMD_CFG; - -cont: - dev_put(ifp); } rcu_read_unlock(); } @@ -483,10 +486,13 @@ resend(struct aoedev *d, struct frame *f) memcpy(h->dst, t->addr, sizeof h->dst); memcpy(h->src, t->ifp->nd->dev_addr, sizeof h->src); + dev_hold(t->ifp->nd); skb->dev = t->ifp->nd; skb = skb_clone(skb, GFP_ATOMIC); - if (skb == NULL) + if (skb == NULL) { + dev_put(t->ifp->nd); return; + } f->sent = ktime_get(); __skb_queue_head_init(&queue); __skb_queue_tail(&queue, skb); @@ -617,6 +623,8 @@ probe(struct aoetgt *t) __skb_queue_head_init(&queue); __skb_queue_tail(&queue, skb); aoenet_xmit(&queue); + } else { + dev_put(f->t->ifp->nd); } } @@ -1395,6 +1403,7 @@ aoecmd_ata_id(struct aoedev *d) ah->cmdstat = ATA_CMD_ID_ATA; ah->lba3 = 0xa0; + dev_hold(t->ifp->nd); skb->dev = t->ifp->nd; d->rttavg = RTTAVG_INIT; @@ -1404,6 +1413,8 @@ aoecmd_ata_id(struct aoedev *d) skb = skb_clone(skb, GFP_ATOMIC); if (skb) f->sent = ktime_get(); + else + dev_put(t->ifp->nd); return skb; } diff --git a/drivers/block/aoe/aoenet.c b/drivers/block/aoe/aoenet.c index 63773a90581dd3..1e66c7a188a121 100644 --- a/drivers/block/aoe/aoenet.c +++ b/drivers/block/aoe/aoenet.c @@ -64,6 +64,7 @@ tx(int id) __must_hold(&txlock) pr_warn("aoe: packet could not be sent on %s. %s\n", ifp ? ifp->name : "netif", "consider increasing tx_queue_len"); + dev_put(ifp); spin_lock_irq(&txlock); } return 0; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 6bc86106c7b2ab..102cc3034412d9 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -3392,10 +3392,12 @@ void drbd_uuid_new_current(struct drbd_device *device) __must_hold(local) void drbd_uuid_set_bm(struct drbd_device *device, u64 val) __must_hold(local) { unsigned long flags; - if (device->ldev->md.uuid[UI_BITMAP] == 0 && val == 0) + spin_lock_irqsave(&device->ldev->md.uuid_lock, flags); + if (device->ldev->md.uuid[UI_BITMAP] == 0 && val == 0) { + spin_unlock_irqrestore(&device->ldev->md.uuid_lock, flags); return; + } - spin_lock_irqsave(&device->ldev->md.uuid_lock, flags); if (val == 0) { drbd_uuid_move_history(device); device->ldev->md.uuid[UI_HISTORY_START] = device->ldev->md.uuid[UI_BITMAP]; diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index 287a8d1d3f707f..87cf5883078f5b 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -876,7 +876,7 @@ is_valid_state(struct drbd_device *device, union drbd_state ns) ns.disk == D_OUTDATED) rv = SS_CONNECTED_OUTDATES; - else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && + else if (nc && (ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && (nc->verify_alg[0] == 0)) rv = SS_NO_VERIFY_ALG; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 9f2d412fc560e1..886c6359903779 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -165,39 +165,37 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file) return get_size(lo->lo_offset, lo->lo_sizelimit, file); } +/* + * We support direct I/O only if lo_offset is aligned with the logical I/O size + * of backing device, and the logical block size of loop is bigger than that of + * the backing device. + */ +static bool lo_bdev_can_use_dio(struct loop_device *lo, + struct block_device *backing_bdev) +{ + unsigned short sb_bsize = bdev_logical_block_size(backing_bdev); + + if (queue_logical_block_size(lo->lo_queue) < sb_bsize) + return false; + if (lo->lo_offset & (sb_bsize - 1)) + return false; + return true; +} + static void __loop_update_dio(struct loop_device *lo, bool dio) { struct file *file = lo->lo_backing_file; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - unsigned short sb_bsize = 0; - unsigned dio_align = 0; + struct inode *inode = file->f_mapping->host; + struct block_device *backing_bdev = NULL; bool use_dio; - if (inode->i_sb->s_bdev) { - sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev); - dio_align = sb_bsize - 1; - } + if (S_ISBLK(inode->i_mode)) + backing_bdev = I_BDEV(inode); + else if (inode->i_sb->s_bdev) + backing_bdev = inode->i_sb->s_bdev; - /* - * We support direct I/O only if lo_offset is aligned with the - * logical I/O size of backing device, and the logical block - * size of loop is bigger than the backing device's. - * - * TODO: the above condition may be loosed in the future, and - * direct I/O may be switched runtime at that time because most - * of requests in sane applications should be PAGE_SIZE aligned - */ - if (dio) { - if (queue_logical_block_size(lo->lo_queue) >= sb_bsize && - !(lo->lo_offset & dio_align) && - (file->f_mode & FMODE_CAN_ODIRECT)) - use_dio = true; - else - use_dio = false; - } else { - use_dio = false; - } + use_dio = dio && (file->f_mode & FMODE_CAN_ODIRECT) && + (!backing_bdev || lo_bdev_can_use_dio(lo, backing_bdev)); if (lo->use_dio == use_dio) return; @@ -213,13 +211,10 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) if (lo->lo_state == Lo_bound) blk_mq_freeze_queue(lo->lo_queue); lo->use_dio = use_dio; - if (use_dio) { - blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, lo->lo_queue); + if (use_dio) lo->lo_flags |= LO_FLAGS_DIRECT_IO; - } else { - blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue); + else lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; - } if (lo->lo_state == Lo_bound) blk_mq_unfreeze_queue(lo->lo_queue); } @@ -2040,14 +2035,6 @@ static int loop_add(int i) blk_queue_max_hw_sectors(lo->lo_queue, BLK_DEF_MAX_SECTORS); - /* - * By default, we do buffer IO, so it doesn't make sense to enable - * merge because the I/O submitted to backing file is handled page by - * page. For directio mode, merge does help to dispatch bigger request - * to underlayer disk. We will enable merge once directio is enabled. - */ - blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue); - /* * Disable partition scanning by default. The in-kernel partition * scanning can be requested individually per-device during its diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 800f131222fc8f..96b349148e5788 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -67,6 +67,7 @@ struct nbd_sock { struct recv_thread_args { struct work_struct work; struct nbd_device *nbd; + struct nbd_sock *nsock; int index; }; @@ -180,6 +181,17 @@ static void nbd_requeue_cmd(struct nbd_cmd *cmd) { struct request *req = blk_mq_rq_from_pdu(cmd); + lockdep_assert_held(&cmd->lock); + + /* + * Clear INFLIGHT flag so that this cmd won't be completed in + * normal completion path + * + * INFLIGHT flag will be set when the cmd is queued to nbd next + * time. + */ + __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); + if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags)) blk_mq_requeue_request(req, true); } @@ -250,7 +262,6 @@ static void nbd_dev_remove(struct nbd_device *nbd) struct gendisk *disk = nbd->disk; del_gendisk(disk); - put_disk(disk); blk_mq_free_tag_set(&nbd->tag_set); /* @@ -261,7 +272,7 @@ static void nbd_dev_remove(struct nbd_device *nbd) idr_remove(&nbd_index_idr, nbd->index); mutex_unlock(&nbd_index_mutex); destroy_workqueue(nbd->recv_workq); - kfree(nbd); + put_disk(disk); } static void nbd_dev_remove_work(struct work_struct *work) @@ -396,6 +407,22 @@ static u32 req_to_nbd_cmd_type(struct request *req) } } +static struct nbd_config *nbd_get_config_unlocked(struct nbd_device *nbd) +{ + if (refcount_inc_not_zero(&nbd->config_refs)) { + /* + * Add smp_mb__after_atomic to ensure that reading nbd->config_refs + * and reading nbd->config is ordered. The pair is the barrier in + * nbd_alloc_and_init_config(), avoid nbd->config_refs is set + * before nbd->config. + */ + smp_mb__after_atomic(); + return nbd->config; + } + + return NULL; +} + static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); @@ -410,13 +437,13 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req) return BLK_EH_DONE; } - if (!refcount_inc_not_zero(&nbd->config_refs)) { + config = nbd_get_config_unlocked(nbd); + if (!config) { cmd->status = BLK_STS_TIMEOUT; __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); mutex_unlock(&cmd->lock); goto done; } - config = nbd->config; if (config->num_connections > 1 || (config->num_connections == 1 && nbd->tag_set.timeout)) { @@ -445,8 +472,8 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req) nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); } - mutex_unlock(&cmd->lock); nbd_requeue_cmd(cmd); + mutex_unlock(&cmd->lock); nbd_config_put(nbd); return BLK_EH_DONE; } @@ -490,17 +517,11 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req) return BLK_EH_DONE; } -/* - * Send or receive packet. Return a positive value on success and - * negtive value on failue, and never return 0. - */ -static int sock_xmit(struct nbd_device *nbd, int index, int send, - struct iov_iter *iter, int msg_flags, int *sent) +static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, + struct iov_iter *iter, int msg_flags, int *sent) { - struct nbd_config *config = nbd->config; - struct socket *sock = config->socks[index]->sock; int result; - struct msghdr msg; + struct msghdr msg = {} ; unsigned int noreclaim_flag; if (unlikely(!sock)) { @@ -516,10 +537,6 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send, do { sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC; sock->sk->sk_use_task_frag = false; - msg.msg_name = NULL; - msg.msg_namelen = 0; - msg.msg_control = NULL; - msg.msg_controllen = 0; msg.msg_flags = msg_flags | MSG_NOSIGNAL; if (send) @@ -541,6 +558,19 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send, return result; } +/* + * Send or receive packet. Return a positive value on success and + * negtive value on failure, and never return 0. + */ +static int sock_xmit(struct nbd_device *nbd, int index, int send, + struct iov_iter *iter, int msg_flags, int *sent) +{ + struct nbd_config *config = nbd->config; + struct socket *sock = config->socks[index]->sock; + + return __sock_xmit(nbd, sock, send, iter, msg_flags, sent); +} + /* * Different settings for sk->sk_sndtimeo can result in different return values * if there is a signal pending when we enter sendmsg, because reasons? @@ -550,7 +580,10 @@ static inline int was_interrupted(int result) return result == -ERESTARTSYS || result == -EINTR; } -/* always call with the tx_lock held */ +/* + * Returns BLK_STS_RESOURCE if the caller should retry after a delay. Returns + * -EAGAIN if the caller should requeue @cmd. Returns -EIO if sending failed. + */ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) { struct request *req = blk_mq_rq_from_pdu(cmd); @@ -567,6 +600,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) u32 nbd_cmd_flags = 0; int sent = nsock->sent, skip = 0; + lockdep_assert_held(&cmd->lock); + lockdep_assert_held(&nsock->tx_lock); + iov_iter_kvec(&from, ITER_SOURCE, &iov, 1, sizeof(request)); type = req_to_nbd_cmd_type(req); @@ -631,7 +667,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) nsock->sent = sent; } set_bit(NBD_CMD_REQUEUED, &cmd->flags); - return BLK_STS_RESOURCE; + return (__force int)BLK_STS_RESOURCE; } dev_err_ratelimited(disk_to_dev(nbd->disk), "Send control failed (result %d)\n", result); @@ -672,7 +708,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) nsock->pending = req; nsock->sent = sent; set_bit(NBD_CMD_REQUEUED, &cmd->flags); - return BLK_STS_RESOURCE; + return (__force int)BLK_STS_RESOURCE; } dev_err(disk_to_dev(nbd->disk), "Send data failed (result %d)\n", @@ -697,7 +733,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) return 0; } -static int nbd_read_reply(struct nbd_device *nbd, int index, +static int nbd_read_reply(struct nbd_device *nbd, struct socket *sock, struct nbd_reply *reply) { struct kvec iov = {.iov_base = reply, .iov_len = sizeof(*reply)}; @@ -706,7 +742,7 @@ static int nbd_read_reply(struct nbd_device *nbd, int index, reply->magic = 0; iov_iter_kvec(&to, ITER_DEST, &iov, 1, sizeof(*reply)); - result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL); + result = __sock_xmit(nbd, sock, 0, &to, MSG_WAITALL, NULL); if (result < 0) { if (!nbd_disconnected(nbd->config)) dev_err(disk_to_dev(nbd->disk), @@ -830,14 +866,14 @@ static void recv_work(struct work_struct *work) struct nbd_device *nbd = args->nbd; struct nbd_config *config = nbd->config; struct request_queue *q = nbd->disk->queue; - struct nbd_sock *nsock; + struct nbd_sock *nsock = args->nsock; struct nbd_cmd *cmd; struct request *rq; while (1) { struct nbd_reply reply; - if (nbd_read_reply(nbd, args->index, &reply)) + if (nbd_read_reply(nbd, nsock->sock, &reply)) break; /* @@ -872,7 +908,6 @@ static void recv_work(struct work_struct *work) percpu_ref_put(&q->q_usage_counter); } - nsock = config->socks[args->index]; mutex_lock(&nsock->tx_lock); nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); @@ -970,7 +1005,7 @@ static int wait_for_reconnect(struct nbd_device *nbd) return !test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags); } -static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) +static blk_status_t nbd_handle_cmd(struct nbd_cmd *cmd, int index) { struct request *req = blk_mq_rq_from_pdu(cmd); struct nbd_device *nbd = cmd->nbd; @@ -978,18 +1013,20 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) struct nbd_sock *nsock; int ret; - if (!refcount_inc_not_zero(&nbd->config_refs)) { + lockdep_assert_held(&cmd->lock); + + config = nbd_get_config_unlocked(nbd); + if (!config) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Socks array is empty\n"); - return -EINVAL; + return BLK_STS_IOERR; } - config = nbd->config; if (index >= config->num_connections) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Attempted send on invalid socket\n"); nbd_config_put(nbd); - return -EINVAL; + return BLK_STS_IOERR; } cmd->status = BLK_STS_OK; again: @@ -1012,7 +1049,7 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) */ sock_shutdown(nbd); nbd_config_put(nbd); - return -EIO; + return BLK_STS_IOERR; } goto again; } @@ -1025,7 +1062,7 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) blk_mq_start_request(req); if (unlikely(nsock->pending && nsock->pending != req)) { nbd_requeue_cmd(cmd); - ret = 0; + ret = BLK_STS_OK; goto out; } /* @@ -1044,19 +1081,19 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) "Request send failed, requeueing\n"); nbd_mark_nsock_dead(nbd, nsock, 1); nbd_requeue_cmd(cmd); - ret = 0; + ret = BLK_STS_OK; } out: mutex_unlock(&nsock->tx_lock); nbd_config_put(nbd); - return ret; + return ret < 0 ? BLK_STS_IOERR : (__force blk_status_t)ret; } static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(bd->rq); - int ret; + blk_status_t ret; /* * Since we look at the bio's to send the request over the network we @@ -1076,10 +1113,6 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, * appropriate. */ ret = nbd_handle_cmd(cmd, hctx->queue_num); - if (ret < 0) - ret = BLK_STS_IOERR; - else if (!ret) - ret = BLK_STS_OK; mutex_unlock(&cmd->lock); return ret; @@ -1216,6 +1249,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg) INIT_WORK(&args->work, recv_work); args->index = i; args->nbd = nbd; + args->nsock = nsock; nsock->cookie++; mutex_unlock(&nsock->tx_lock); sockfd_put(old); @@ -1398,6 +1432,7 @@ static int nbd_start_device(struct nbd_device *nbd) refcount_inc(&nbd->config_refs); INIT_WORK(&args->work, recv_work); args->nbd = nbd; + args->nsock = config->socks[i]; args->index = i; queue_work(nbd->recv_workq, &args->work); } @@ -1531,17 +1566,20 @@ static int nbd_ioctl(struct block_device *bdev, blk_mode_t mode, return error; } -static struct nbd_config *nbd_alloc_config(void) +static int nbd_alloc_and_init_config(struct nbd_device *nbd) { struct nbd_config *config; + if (WARN_ON(nbd->config)) + return -EINVAL; + if (!try_module_get(THIS_MODULE)) - return ERR_PTR(-ENODEV); + return -ENODEV; config = kzalloc(sizeof(struct nbd_config), GFP_NOFS); if (!config) { module_put(THIS_MODULE); - return ERR_PTR(-ENOMEM); + return -ENOMEM; } atomic_set(&config->recv_threads, 0); @@ -1549,12 +1587,24 @@ static struct nbd_config *nbd_alloc_config(void) init_waitqueue_head(&config->conn_wait); config->blksize_bits = NBD_DEF_BLKSIZE_BITS; atomic_set(&config->live_connections, 0); - return config; + + nbd->config = config; + /* + * Order refcount_set(&nbd->config_refs, 1) and nbd->config assignment, + * its pair is the barrier in nbd_get_config_unlocked(). + * So nbd_get_config_unlocked() won't see nbd->config as null after + * refcount_inc_not_zero() succeed. + */ + smp_mb__before_atomic(); + refcount_set(&nbd->config_refs, 1); + + return 0; } static int nbd_open(struct gendisk *disk, blk_mode_t mode) { struct nbd_device *nbd; + struct nbd_config *config; int ret = 0; mutex_lock(&nbd_index_mutex); @@ -1567,27 +1617,25 @@ static int nbd_open(struct gendisk *disk, blk_mode_t mode) ret = -ENXIO; goto out; } - if (!refcount_inc_not_zero(&nbd->config_refs)) { - struct nbd_config *config; + config = nbd_get_config_unlocked(nbd); + if (!config) { mutex_lock(&nbd->config_lock); if (refcount_inc_not_zero(&nbd->config_refs)) { mutex_unlock(&nbd->config_lock); goto out; } - config = nbd_alloc_config(); - if (IS_ERR(config)) { - ret = PTR_ERR(config); + ret = nbd_alloc_and_init_config(nbd); + if (ret) { mutex_unlock(&nbd->config_lock); goto out; } - nbd->config = config; - refcount_set(&nbd->config_refs, 1); + refcount_inc(&nbd->refs); mutex_unlock(&nbd->config_lock); if (max_part) set_bit(GD_NEED_PART_SCAN, &disk->state); - } else if (nbd_disconnected(nbd->config)) { + } else if (nbd_disconnected(config)) { if (max_part) set_bit(GD_NEED_PART_SCAN, &disk->state); } @@ -1608,6 +1656,13 @@ static void nbd_release(struct gendisk *disk) nbd_put(nbd); } +static void nbd_free_disk(struct gendisk *disk) +{ + struct nbd_device *nbd = disk->private_data; + + kfree(nbd); +} + static const struct block_device_operations nbd_fops = { .owner = THIS_MODULE, @@ -1615,6 +1670,7 @@ static const struct block_device_operations nbd_fops = .release = nbd_release, .ioctl = nbd_ioctl, .compat_ioctl = nbd_ioctl, + .free_disk = nbd_free_disk, }; #if IS_ENABLED(CONFIG_DEBUG_FS) @@ -1983,22 +2039,17 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info) pr_err("nbd%d already in use\n", index); return -EBUSY; } - if (WARN_ON(nbd->config)) { - mutex_unlock(&nbd->config_lock); - nbd_put(nbd); - return -EINVAL; - } - config = nbd_alloc_config(); - if (IS_ERR(config)) { + + ret = nbd_alloc_and_init_config(nbd); + if (ret) { mutex_unlock(&nbd->config_lock); nbd_put(nbd); pr_err("couldn't allocate config\n"); - return PTR_ERR(config); + return ret; } - nbd->config = config; - refcount_set(&nbd->config_refs, 1); - set_bit(NBD_RT_BOUND, &config->runtime_flags); + config = nbd->config; + set_bit(NBD_RT_BOUND, &config->runtime_flags); ret = nbd_genl_size_set(info, nbd); if (ret) goto out; @@ -2201,7 +2252,8 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) } mutex_unlock(&nbd_index_mutex); - if (!refcount_inc_not_zero(&nbd->config_refs)) { + config = nbd_get_config_unlocked(nbd); + if (!config) { dev_err(nbd_to_dev(nbd), "not configured, cannot reconfigure\n"); nbd_put(nbd); @@ -2209,7 +2261,6 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) } mutex_lock(&nbd->config_lock); - config = nbd->config; if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) || !nbd->pid) { dev_err(nbd_to_dev(nbd), @@ -2401,6 +2452,12 @@ static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info) } dev_list = nla_nest_start_noflag(reply, NBD_ATTR_DEVICE_LIST); + if (!dev_list) { + nlmsg_free(reply); + ret = -EMSGSIZE; + goto out; + } + if (index == -1) { ret = idr_for_each(&nbd_index_idr, &status_cb, reply); if (ret) { diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 968090935eb23f..97ed3bd9707f41 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -392,13 +392,25 @@ static int nullb_update_nr_hw_queues(struct nullb_device *dev, static int nullb_apply_submit_queues(struct nullb_device *dev, unsigned int submit_queues) { - return nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues); + int ret; + + mutex_lock(&lock); + ret = nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues); + mutex_unlock(&lock); + + return ret; } static int nullb_apply_poll_queues(struct nullb_device *dev, unsigned int poll_queues) { - return nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues); + int ret; + + mutex_lock(&lock); + ret = nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues); + mutex_unlock(&lock); + + return ret; } NULLB_DEVICE_ATTR(size, ulong, NULL); @@ -444,28 +456,32 @@ static ssize_t nullb_device_power_store(struct config_item *item, if (ret < 0) return ret; + ret = count; + mutex_lock(&lock); if (!dev->power && newp) { if (test_and_set_bit(NULLB_DEV_FL_UP, &dev->flags)) - return count; + goto out; + ret = null_add_dev(dev); if (ret) { clear_bit(NULLB_DEV_FL_UP, &dev->flags); - return ret; + goto out; } set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags); dev->power = newp; + ret = count; } else if (dev->power && !newp) { if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) { - mutex_lock(&lock); dev->power = newp; null_del_dev(dev->nullb); - mutex_unlock(&lock); } clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags); } - return count; +out: + mutex_unlock(&lock); + return ret; } CONFIGFS_ATTR(nullb_device_, power); @@ -1819,7 +1835,7 @@ static void null_del_dev(struct nullb *nullb) dev = nullb->dev; - ida_simple_remove(&nullb_indexes, nullb->index); + ida_free(&nullb_indexes, nullb->index); list_del_init(&nullb->list); @@ -2013,8 +2029,8 @@ static int null_validate_conf(struct nullb_device *dev) return -EINVAL; } - dev->blocksize = round_down(dev->blocksize, 512); - dev->blocksize = clamp_t(unsigned int, dev->blocksize, 512, 4096); + if (blk_validate_block_size(dev->blocksize)) + return -EINVAL; if (dev->queue_mode == NULL_Q_MQ && dev->use_per_node_hctx) { if (dev->submit_queues != nr_online_nodes) @@ -2153,22 +2169,17 @@ static int null_add_dev(struct nullb_device *dev) nullb->q->queuedata = nullb; blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q); - mutex_lock(&lock); - rv = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL); - if (rv < 0) { - mutex_unlock(&lock); + rv = ida_alloc(&nullb_indexes, GFP_KERNEL); + if (rv < 0) goto out_cleanup_zone; - } + nullb->index = rv; dev->index = rv; - mutex_unlock(&lock); blk_queue_logical_block_size(nullb->q, dev->blocksize); blk_queue_physical_block_size(nullb->q, dev->blocksize); - if (!dev->max_sectors) - dev->max_sectors = queue_max_hw_sectors(nullb->q); - dev->max_sectors = min(dev->max_sectors, BLK_DEF_MAX_SECTORS); - blk_queue_max_hw_sectors(nullb->q, dev->max_sectors); + if (dev->max_sectors) + blk_queue_max_hw_sectors(nullb->q, dev->max_sectors); if (dev->virt_boundary) blk_queue_virt_boundary(nullb->q, PAGE_SIZE - 1); @@ -2187,9 +2198,7 @@ static int null_add_dev(struct nullb_device *dev) if (rv) goto out_ida_free; - mutex_lock(&lock); list_add_tail(&nullb->list, &nullb_list); - mutex_unlock(&lock); pr_info("disk %s created\n", nullb->disk_name); @@ -2238,7 +2247,9 @@ static int null_create_dev(void) if (!dev) return -ENOMEM; + mutex_lock(&lock); ret = null_add_dev(dev); + mutex_unlock(&lock); if (ret) { null_free_dev(dev); return ret; @@ -2268,12 +2279,6 @@ static int __init null_init(void) g_bs = PAGE_SIZE; } - if (g_max_sectors > BLK_DEF_MAX_SECTORS) { - pr_warn("invalid max sectors\n"); - pr_warn("defaults max sectors to %u\n", BLK_DEF_MAX_SECTORS); - g_max_sectors = BLK_DEF_MAX_SECTORS; - } - if (g_home_node != NUMA_NO_NODE && g_home_node >= nr_online_nodes) { pr_err("invalid home_node value\n"); g_home_node = NUMA_NO_NODE; @@ -2360,10 +2365,13 @@ static void __exit null_exit(void) if (g_queue_mode == NULL_Q_MQ && shared_tags) blk_mq_free_tag_set(&tag_set); + + mutex_destroy(&lock); } module_init(null_init); module_exit(null_exit); MODULE_AUTHOR("Jens Axboe "); +MODULE_DESCRIPTION("multi queue aware block test driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c index 55c5b48bc276fe..d057f7099e7f7e 100644 --- a/drivers/block/null_blk/zoned.c +++ b/drivers/block/null_blk/zoned.c @@ -83,6 +83,17 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q) return -EINVAL; } + /* + * If a smaller zone capacity was requested, do not allow a smaller last + * zone at the same time as such zone configuration does not correspond + * to any real zoned device. + */ + if (dev->zone_capacity != dev->zone_size && + dev->size & (dev->zone_size - 1)) { + pr_err("A smaller last zone is not allowed with zone capacity smaller than zone size.\n"); + return -EINVAL; + } + zone_capacity_sects = mb_to_sects(dev->zone_capacity); dev_capacity_sects = mb_to_sects(dev->size); dev->zone_size_sects = mb_to_sects(dev->zone_size); @@ -112,7 +123,7 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q) if (dev->zone_max_active && dev->zone_max_open > dev->zone_max_active) { dev->zone_max_open = dev->zone_max_active; pr_info("changed the maximum number of open zones to %u\n", - dev->nr_zones); + dev->zone_max_open); } else if (dev->zone_max_open >= dev->nr_zones - dev->zone_nr_conv) { dev->zone_max_open = 0; pr_info("zone_max_open limit disabled, limit >= zone count\n"); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index a999b698b131f7..6fcd7f0fe4f03e 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -362,7 +362,7 @@ enum rbd_watch_state { enum rbd_lock_state { RBD_LOCK_STATE_UNLOCKED, RBD_LOCK_STATE_LOCKED, - RBD_LOCK_STATE_RELEASING, + RBD_LOCK_STATE_QUIESCING, }; /* WatchNotify::ClientId */ @@ -422,7 +422,7 @@ struct rbd_device { struct list_head running_list; struct completion acquire_wait; int acquire_err; - struct completion releasing_wait; + struct completion quiescing_wait; spinlock_t object_map_lock; u8 *object_map; @@ -525,7 +525,7 @@ static bool __rbd_is_lock_owner(struct rbd_device *rbd_dev) lockdep_assert_held(&rbd_dev->lock_rwsem); return rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED || - rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING; + rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING; } static bool rbd_is_lock_owner(struct rbd_device *rbd_dev) @@ -3452,17 +3452,19 @@ static bool rbd_lock_add_request(struct rbd_img_request *img_req) static void rbd_lock_del_request(struct rbd_img_request *img_req) { struct rbd_device *rbd_dev = img_req->rbd_dev; - bool need_wakeup; + bool need_wakeup = false; lockdep_assert_held(&rbd_dev->lock_rwsem); spin_lock(&rbd_dev->lock_lists_lock); - rbd_assert(!list_empty(&img_req->lock_item)); - list_del_init(&img_req->lock_item); - need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING && - list_empty(&rbd_dev->running_list)); + if (!list_empty(&img_req->lock_item)) { + rbd_assert(!list_empty(&rbd_dev->running_list)); + list_del_init(&img_req->lock_item); + need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING && + list_empty(&rbd_dev->running_list)); + } spin_unlock(&rbd_dev->lock_lists_lock); if (need_wakeup) - complete(&rbd_dev->releasing_wait); + complete(&rbd_dev->quiescing_wait); } static int rbd_img_exclusive_lock(struct rbd_img_request *img_req) @@ -3475,11 +3477,6 @@ static int rbd_img_exclusive_lock(struct rbd_img_request *img_req) if (rbd_lock_add_request(img_req)) return 1; - if (rbd_dev->opts->exclusive) { - WARN_ON(1); /* lock got released? */ - return -EROFS; - } - /* * Note the use of mod_delayed_work() in rbd_acquire_lock() * and cancel_delayed_work() in wake_lock_waiters(). @@ -3842,14 +3839,19 @@ static void wake_lock_waiters(struct rbd_device *rbd_dev, int result) return; } - list_for_each_entry(img_req, &rbd_dev->acquiring_list, lock_item) { + while (!list_empty(&rbd_dev->acquiring_list)) { + img_req = list_first_entry(&rbd_dev->acquiring_list, + struct rbd_img_request, lock_item); mutex_lock(&img_req->state_mutex); rbd_assert(img_req->state == RBD_IMG_EXCLUSIVE_LOCK); + if (!result) + list_move_tail(&img_req->lock_item, + &rbd_dev->running_list); + else + list_del_init(&img_req->lock_item); rbd_img_schedule(img_req, result); mutex_unlock(&img_req->state_mutex); } - - list_splice_tail_init(&rbd_dev->acquiring_list, &rbd_dev->running_list); } static bool locker_equal(const struct ceph_locker *lhs, @@ -4175,16 +4177,16 @@ static bool rbd_quiesce_lock(struct rbd_device *rbd_dev) /* * Ensure that all in-flight IO is flushed. */ - rbd_dev->lock_state = RBD_LOCK_STATE_RELEASING; - rbd_assert(!completion_done(&rbd_dev->releasing_wait)); + rbd_dev->lock_state = RBD_LOCK_STATE_QUIESCING; + rbd_assert(!completion_done(&rbd_dev->quiescing_wait)); if (list_empty(&rbd_dev->running_list)) return true; up_write(&rbd_dev->lock_rwsem); - wait_for_completion(&rbd_dev->releasing_wait); + wait_for_completion(&rbd_dev->quiescing_wait); down_write(&rbd_dev->lock_rwsem); - if (rbd_dev->lock_state != RBD_LOCK_STATE_RELEASING) + if (rbd_dev->lock_state != RBD_LOCK_STATE_QUIESCING) return false; rbd_assert(list_empty(&rbd_dev->running_list)); @@ -4595,6 +4597,10 @@ static void rbd_reacquire_lock(struct rbd_device *rbd_dev) rbd_warn(rbd_dev, "failed to update lock cookie: %d", ret); + if (rbd_dev->opts->exclusive) + rbd_warn(rbd_dev, + "temporarily releasing lock on exclusive mapping"); + /* * Lock cookie cannot be updated on older OSDs, so do * a manual release and queue an acquire. @@ -5376,7 +5382,7 @@ static struct rbd_device *__rbd_dev_create(struct rbd_spec *spec) INIT_LIST_HEAD(&rbd_dev->acquiring_list); INIT_LIST_HEAD(&rbd_dev->running_list); init_completion(&rbd_dev->acquire_wait); - init_completion(&rbd_dev->releasing_wait); + init_completion(&rbd_dev->quiescing_wait); spin_lock_init(&rbd_dev->object_map_lock); @@ -6582,11 +6588,6 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev) if (ret) return ret; - /* - * The lock may have been released by now, unless automatic lock - * transitions are disabled. - */ - rbd_assert(!rbd_dev->opts->exclusive || rbd_is_lock_owner(rbd_dev)); return 0; } diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index c186df0ec641c8..b67e39a34010b1 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -585,6 +585,7 @@ static char *rnbd_srv_get_full_path(struct rnbd_srv_session *srv_sess, { char *full_path; char *a, *b; + int len; full_path = kmalloc(PATH_MAX, GFP_KERNEL); if (!full_path) @@ -596,19 +597,19 @@ static char *rnbd_srv_get_full_path(struct rnbd_srv_session *srv_sess, */ a = strnstr(dev_search_path, "%SESSNAME%", sizeof(dev_search_path)); if (a) { - int len = a - dev_search_path; + len = a - dev_search_path; len = snprintf(full_path, PATH_MAX, "%.*s/%s/%s", len, dev_search_path, srv_sess->sessname, dev_name); - if (len >= PATH_MAX) { - pr_err("Too long path: %s, %s, %s\n", - dev_search_path, srv_sess->sessname, dev_name); - kfree(full_path); - return ERR_PTR(-EINVAL); - } } else { - snprintf(full_path, PATH_MAX, "%s/%s", - dev_search_path, dev_name); + len = snprintf(full_path, PATH_MAX, "%s/%s", + dev_search_path, dev_name); + } + if (len >= PATH_MAX) { + pr_err("Too long path: %s, %s, %s\n", + dev_search_path, srv_sess->sessname, dev_name); + kfree(full_path); + return ERR_PTR(-EINVAL); } /* eliminitate duplicated slashes */ diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 630ddfe6657bc9..f31607a24f5735 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -68,9 +68,6 @@ struct ublk_rq_data { struct llist_node node; struct kref ref; - __u64 sector; - __u32 operation; - __u32 nr_zones; }; struct ublk_uring_cmd_pdu { @@ -115,6 +112,9 @@ struct ublk_uring_cmd_pdu { */ #define UBLK_IO_FLAG_NEED_GET_DATA 0x08 +/* atomic RW with ubq->cancel_lock */ +#define UBLK_IO_FLAG_CANCELED 0x80000000 + struct ublk_io { /* userspace buffer address from io cmd */ __u64 addr; @@ -139,6 +139,7 @@ struct ublk_queue { bool force_abort; bool timeout; unsigned short nr_io_ready; /* how many ios setup */ + spinlock_t cancel_lock; struct ublk_device *dev; struct ublk_io ios[]; }; @@ -211,6 +212,33 @@ static inline bool ublk_queue_is_zoned(struct ublk_queue *ubq) #ifdef CONFIG_BLK_DEV_ZONED +struct ublk_zoned_report_desc { + __u64 sector; + __u32 operation; + __u32 nr_zones; +}; + +static DEFINE_XARRAY(ublk_zoned_report_descs); + +static int ublk_zoned_insert_report_desc(const struct request *req, + struct ublk_zoned_report_desc *desc) +{ + return xa_insert(&ublk_zoned_report_descs, (unsigned long)req, + desc, GFP_KERNEL); +} + +static struct ublk_zoned_report_desc *ublk_zoned_erase_report_desc( + const struct request *req) +{ + return xa_erase(&ublk_zoned_report_descs, (unsigned long)req); +} + +static struct ublk_zoned_report_desc *ublk_zoned_get_report_desc( + const struct request *req) +{ + return xa_load(&ublk_zoned_report_descs, (unsigned long)req); +} + static int ublk_get_nr_zones(const struct ublk_device *ub) { const struct ublk_param_basic *p = &ub->params.basic; @@ -317,7 +345,7 @@ static int ublk_report_zones(struct gendisk *disk, sector_t sector, unsigned int zones_in_request = min_t(unsigned int, remaining_zones, max_zones_per_request); struct request *req; - struct ublk_rq_data *pdu; + struct ublk_zoned_report_desc desc; blk_status_t status; memset(buffer, 0, buffer_length); @@ -328,20 +356,23 @@ static int ublk_report_zones(struct gendisk *disk, sector_t sector, goto out; } - pdu = blk_mq_rq_to_pdu(req); - pdu->operation = UBLK_IO_OP_REPORT_ZONES; - pdu->sector = sector; - pdu->nr_zones = zones_in_request; + desc.operation = UBLK_IO_OP_REPORT_ZONES; + desc.sector = sector; + desc.nr_zones = zones_in_request; + ret = ublk_zoned_insert_report_desc(req, &desc); + if (ret) + goto free_req; ret = blk_rq_map_kern(disk->queue, req, buffer, buffer_length, GFP_KERNEL); - if (ret) { - blk_mq_free_request(req); - goto out; - } + if (ret) + goto erase_desc; status = blk_execute_rq(req, 0); ret = blk_status_to_errno(status); +erase_desc: + ublk_zoned_erase_report_desc(req); +free_req: blk_mq_free_request(req); if (ret) goto out; @@ -375,7 +406,7 @@ static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq, { struct ublksrv_io_desc *iod = ublk_get_iod(ubq, req->tag); struct ublk_io *io = &ubq->ios[req->tag]; - struct ublk_rq_data *pdu = blk_mq_rq_to_pdu(req); + struct ublk_zoned_report_desc *desc; u32 ublk_op; switch (req_op(req)) { @@ -398,12 +429,15 @@ static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq, ublk_op = UBLK_IO_OP_ZONE_RESET_ALL; break; case REQ_OP_DRV_IN: - ublk_op = pdu->operation; + desc = ublk_zoned_get_report_desc(req); + if (!desc) + return BLK_STS_IOERR; + ublk_op = desc->operation; switch (ublk_op) { case UBLK_IO_OP_REPORT_ZONES: iod->op_flags = ublk_op | ublk_req_build_flags(req); - iod->nr_zones = pdu->nr_zones; - iod->start_sector = pdu->sector; + iod->nr_zones = desc->nr_zones; + iod->start_sector = desc->sector; return BLK_STS_OK; default: return BLK_STS_IOERR; @@ -1477,28 +1511,28 @@ static inline bool ublk_queue_ready(struct ublk_queue *ubq) return ubq->nr_io_ready == ubq->q_depth; } -static void ublk_cmd_cancel_cb(struct io_uring_cmd *cmd, unsigned issue_flags) -{ - io_uring_cmd_done(cmd, UBLK_IO_RES_ABORT, 0, issue_flags); -} - static void ublk_cancel_queue(struct ublk_queue *ubq) { int i; - if (!ublk_queue_ready(ubq)) - return; - for (i = 0; i < ubq->q_depth; i++) { struct ublk_io *io = &ubq->ios[i]; - if (io->flags & UBLK_IO_FLAG_ACTIVE) - io_uring_cmd_complete_in_task(io->cmd, - ublk_cmd_cancel_cb); - } + if (io->flags & UBLK_IO_FLAG_ACTIVE) { + bool done; - /* all io commands are canceled */ - ubq->nr_io_ready = 0; + spin_lock(&ubq->cancel_lock); + done = !!(io->flags & UBLK_IO_FLAG_CANCELED); + if (!done) + io->flags |= UBLK_IO_FLAG_CANCELED; + spin_unlock(&ubq->cancel_lock); + + if (!done) + io_uring_cmd_done(io->cmd, + UBLK_IO_RES_ABORT, 0, + IO_URING_F_UNLOCKED); + } + } } /* Cancel all pending commands, must be called after del_gendisk() returns */ @@ -1545,7 +1579,6 @@ static void __ublk_quiesce_dev(struct ublk_device *ub) blk_mq_quiesce_queue(ub->ub_disk->queue); ublk_wait_tagset_rqs_idle(ub); ub->dev_info.state = UBLK_S_DEV_QUIESCED; - ublk_cancel_dev(ub); /* we are going to release task_struct of ubq_daemon and resets * ->ubq_daemon to NULL. So in monitor_work, check on ubq_daemon causes UAF. * Besides, monitor_work is not necessary in QUIESCED state since we have @@ -1568,6 +1601,7 @@ static void ublk_quiesce_work_fn(struct work_struct *work) __ublk_quiesce_dev(ub); unlock: mutex_unlock(&ub->mutex); + ublk_cancel_dev(ub); } static void ublk_unquiesce_dev(struct ublk_device *ub) @@ -1607,8 +1641,8 @@ static void ublk_stop_dev(struct ublk_device *ub) put_disk(ub->ub_disk); ub->ub_disk = NULL; unlock: - ublk_cancel_dev(ub); mutex_unlock(&ub->mutex); + ublk_cancel_dev(ub); cancel_delayed_work_sync(&ub->monitor_work); } @@ -1962,6 +1996,7 @@ static int ublk_init_queue(struct ublk_device *ub, int q_id) void *ptr; int size; + spin_lock_init(&ubq->cancel_lock); ubq->flags = ub->dev_info.flags; ubq->q_id = q_id; ubq->q_depth = ub->dev_info.queue_depth; @@ -2292,10 +2327,19 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) * TODO: provide forward progress for RECOVERY handler, so that * unprivileged device can benefit from it */ - if (info.flags & UBLK_F_UNPRIVILEGED_DEV) + if (info.flags & UBLK_F_UNPRIVILEGED_DEV) { info.flags &= ~(UBLK_F_USER_RECOVERY_REISSUE | UBLK_F_USER_RECOVERY); + /* + * For USER_COPY, we depends on userspace to fill request + * buffer by pwrite() to ublk char device, which can't be + * used for unprivileged device + */ + if (info.flags & UBLK_F_USER_COPY) + return -EINVAL; + } + /* the created device is always owned by current user */ ublk_store_owner_uid_gid(&info.owner_uid, &info.owner_gid); @@ -2569,8 +2613,9 @@ static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) int i; WARN_ON_ONCE(!(ubq->ubq_daemon && ubq_daemon_is_dying(ubq))); + /* All old ioucmds have to be completed */ - WARN_ON_ONCE(ubq->nr_io_ready); + ubq->nr_io_ready = 0; /* old daemon is PF_EXITING, put it now */ put_task_struct(ubq->ubq_daemon); /* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */ @@ -2597,6 +2642,8 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub, mutex_lock(&ub->mutex); if (!ublk_can_use_recovery(ub)) goto out_unlock; + if (!ub->nr_queues_ready) + goto out_unlock; /* * START_RECOVERY is only allowd after: * diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 1fe011676d070e..41b2fd7e1b9e50 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -1021,12 +1021,12 @@ static void virtblk_config_changed(struct virtio_device *vdev) static int init_vq(struct virtio_blk *vblk) { int err; - int i; + unsigned short i; vq_callback_t **callbacks; const char **names; struct virtqueue **vqs; unsigned short num_vqs; - unsigned int num_poll_vqs; + unsigned short num_poll_vqs; struct virtio_device *vdev = vblk->vdev; struct irq_affinity desc = { 0, }; @@ -1070,13 +1070,13 @@ static int init_vq(struct virtio_blk *vblk) for (i = 0; i < num_vqs - num_poll_vqs; i++) { callbacks[i] = virtblk_done; - snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%d", i); + snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%u", i); names[i] = vblk->vqs[i].name; } for (; i < num_vqs; i++) { callbacks[i] = NULL; - snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req_poll.%d", i); + snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req_poll.%u", i); names[i] = vblk->vqs[i].name; } @@ -1313,6 +1313,7 @@ static int virtblk_probe(struct virtio_device *vdev) u16 min_io_size; u8 physical_block_exp, alignment_offset; unsigned int queue_depth; + size_t max_dma_size; if (!vdev->config->get) { dev_err(&vdev->dev, "%s failure: config access disabled\n", @@ -1411,7 +1412,8 @@ static int virtblk_probe(struct virtio_device *vdev) /* No real sector limit. */ blk_queue_max_hw_sectors(q, UINT_MAX); - max_size = virtio_max_dma_size(vdev); + max_dma_size = virtio_max_dma_size(vdev); + max_size = max_dma_size > U32_MAX ? U32_MAX : max_dma_size; /* Host can optionally specify maximum segment size and number of * segments. */ @@ -1627,14 +1629,15 @@ static int virtblk_freeze(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; + /* Ensure no requests in virtqueues before deleting vqs. */ + blk_mq_freeze_queue(vblk->disk->queue); + /* Ensure we don't receive any more interrupts */ virtio_reset_device(vdev); /* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); - blk_mq_quiesce_queue(vblk->disk->queue); - vdev->config->del_vqs(vdev); kfree(vblk->vqs); @@ -1652,7 +1655,7 @@ static int virtblk_restore(struct virtio_device *vdev) virtio_device_ready(vdev); - blk_mq_unquiesce_queue(vblk->disk->queue); + blk_mq_unfreeze_queue(vblk->disk->queue); return 0; } #endif diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 06673c6ca25555..606f388c7a5716 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1983,6 +1983,13 @@ static void zram_destroy_comps(struct zram *zram) zcomp_destroy(comp); zram->num_active_comps--; } + + for (prio = ZRAM_PRIMARY_COMP; prio < ZRAM_MAX_COMPS; prio++) { + /* Do not free statically defined compression algorithms */ + if (zram->comp_algs[prio] != default_compressor) + kfree(zram->comp_algs[prio]); + zram->comp_algs[prio] = NULL; + } } static void zram_reset_device(struct zram *zram) diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index 88262d3a93923a..ce97b336fbfb8a 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -3,7 +3,6 @@ * Copyright (c) 2008-2009 Atheros Communications Inc. */ - #include #include #include @@ -128,7 +127,6 @@ MODULE_DEVICE_TABLE(usb, ath3k_table); * for AR3012 */ static const struct usb_device_id ath3k_blist_tbl[] = { - /* Atheros AR3012 with sflash firmware*/ { USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xe04d), .driver_info = BTUSB_ATH3012 }, @@ -202,7 +200,7 @@ static inline void ath3k_log_failed_loading(int err, int len, int size, #define TIMEGAP_USEC_MAX 100 static int ath3k_load_firmware(struct usb_device *udev, - const struct firmware *firmware) + const struct firmware *firmware) { u8 *send_buf; int len = 0; @@ -237,9 +235,9 @@ static int ath3k_load_firmware(struct usb_device *udev, memcpy(send_buf, firmware->data + sent, size); err = usb_bulk_msg(udev, pipe, send_buf, size, - &len, 3000); + &len, 3000); - if (err || (len != size)) { + if (err || len != size) { ath3k_log_failed_loading(err, len, size, count); goto error; } @@ -262,7 +260,7 @@ static int ath3k_get_state(struct usb_device *udev, unsigned char *state) } static int ath3k_get_version(struct usb_device *udev, - struct ath3k_version *version) + struct ath3k_version *version) { return usb_control_msg_recv(udev, 0, ATH3K_GETVERSION, USB_TYPE_VENDOR | USB_DIR_IN, 0, 0, @@ -271,7 +269,7 @@ static int ath3k_get_version(struct usb_device *udev, } static int ath3k_load_fwfile(struct usb_device *udev, - const struct firmware *firmware) + const struct firmware *firmware) { u8 *send_buf; int len = 0; @@ -310,8 +308,8 @@ static int ath3k_load_fwfile(struct usb_device *udev, memcpy(send_buf, firmware->data + sent, size); err = usb_bulk_msg(udev, pipe, send_buf, size, - &len, 3000); - if (err || (len != size)) { + &len, 3000); + if (err || len != size) { ath3k_log_failed_loading(err, len, size, count); kfree(send_buf); return err; @@ -425,7 +423,6 @@ static int ath3k_load_syscfg(struct usb_device *udev) } switch (fw_version.ref_clock) { - case ATH3K_XTAL_FREQ_26M: clk_value = 26; break; @@ -441,7 +438,7 @@ static int ath3k_load_syscfg(struct usb_device *udev) } snprintf(filename, ATH3K_NAME_LEN, "ar3k/ramps_0x%08x_%d%s", - le32_to_cpu(fw_version.rom_version), clk_value, ".dfu"); + le32_to_cpu(fw_version.rom_version), clk_value, ".dfu"); ret = request_firmware(&firmware, filename, &udev->dev); if (ret < 0) { @@ -456,7 +453,7 @@ static int ath3k_load_syscfg(struct usb_device *udev) } static int ath3k_probe(struct usb_interface *intf, - const struct usb_device_id *id) + const struct usb_device_id *id) { const struct firmware *firmware; struct usb_device *udev = interface_to_usbdev(intf); @@ -505,10 +502,10 @@ static int ath3k_probe(struct usb_interface *intf, if (ret < 0) { if (ret == -ENOENT) BT_ERR("Firmware file \"%s\" not found", - ATH3K_FIRMWARE); + ATH3K_FIRMWARE); else BT_ERR("Firmware file \"%s\" request failed (err=%d)", - ATH3K_FIRMWARE, ret); + ATH3K_FIRMWARE, ret); return ret; } diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 2462796a512a5f..a936219aebb81a 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -26,21 +26,11 @@ #define ECDSA_OFFSET 644 #define ECDSA_HEADER_LEN 320 -#define BTINTEL_PPAG_NAME "PPAG" - enum { DSM_SET_WDISABLE2_DELAY = 1, DSM_SET_RESET_METHOD = 3, }; -/* structure to store the PPAG data read from ACPI table */ -struct btintel_ppag { - u32 domain; - u32 mode; - acpi_status status; - struct hci_dev *hdev; -}; - #define CMD_WRITE_BOOT_PARAMS 0xfc0e struct cmd_write_boot_params { __le32 boot_addr; @@ -441,7 +431,7 @@ int btintel_read_version(struct hci_dev *hdev, struct intel_version *ver) return PTR_ERR(skb); } - if (skb->len != sizeof(*ver)) { + if (!skb || skb->len != sizeof(*ver)) { bt_dev_err(hdev, "Intel version event size mismatch"); kfree_skb(skb); return -EILSEQ; @@ -1312,65 +1302,6 @@ static int btintel_read_debug_features(struct hci_dev *hdev, return 0; } -static acpi_status btintel_ppag_callback(acpi_handle handle, u32 lvl, void *data, - void **ret) -{ - acpi_status status; - size_t len; - struct btintel_ppag *ppag = data; - union acpi_object *p, *elements; - struct acpi_buffer string = {ACPI_ALLOCATE_BUFFER, NULL}; - struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL}; - struct hci_dev *hdev = ppag->hdev; - - status = acpi_get_name(handle, ACPI_FULL_PATHNAME, &string); - if (ACPI_FAILURE(status)) { - bt_dev_warn(hdev, "PPAG-BT: ACPI Failure: %s", acpi_format_exception(status)); - return status; - } - - len = strlen(string.pointer); - if (len < strlen(BTINTEL_PPAG_NAME)) { - kfree(string.pointer); - return AE_OK; - } - - if (strncmp((char *)string.pointer + len - 4, BTINTEL_PPAG_NAME, 4)) { - kfree(string.pointer); - return AE_OK; - } - kfree(string.pointer); - - status = acpi_evaluate_object(handle, NULL, NULL, &buffer); - if (ACPI_FAILURE(status)) { - ppag->status = status; - bt_dev_warn(hdev, "PPAG-BT: ACPI Failure: %s", acpi_format_exception(status)); - return status; - } - - p = buffer.pointer; - ppag = (struct btintel_ppag *)data; - - if (p->type != ACPI_TYPE_PACKAGE || p->package.count != 2) { - kfree(buffer.pointer); - bt_dev_warn(hdev, "PPAG-BT: Invalid object type: %d or package count: %d", - p->type, p->package.count); - ppag->status = AE_ERROR; - return AE_ERROR; - } - - elements = p->package.elements; - - /* PPAG table is located at element[1] */ - p = &elements[1]; - - ppag->domain = (u32)p->package.elements[0].integer.value; - ppag->mode = (u32)p->package.elements[1].integer.value; - ppag->status = AE_OK; - kfree(buffer.pointer); - return AE_CTRL_TERMINATE; -} - static int btintel_set_debug_features(struct hci_dev *hdev, const struct intel_debug_features *features) { @@ -2399,10 +2330,13 @@ static int btintel_configure_offload(struct hci_dev *hdev) static void btintel_set_ppag(struct hci_dev *hdev, struct intel_version_tlv *ver) { - struct btintel_ppag ppag; struct sk_buff *skb; struct hci_ppag_enable_cmd ppag_cmd; acpi_handle handle; + struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL}; + union acpi_object *p, *elements; + u32 domain, mode; + acpi_status status; /* PPAG is not supported if CRF is HrP2, Jfp2, JfP1 */ switch (ver->cnvr_top & 0xFFF) { @@ -2420,22 +2354,34 @@ static void btintel_set_ppag(struct hci_dev *hdev, struct intel_version_tlv *ver return; } - memset(&ppag, 0, sizeof(ppag)); - - ppag.hdev = hdev; - ppag.status = AE_NOT_FOUND; - acpi_walk_namespace(ACPI_TYPE_PACKAGE, handle, 1, NULL, - btintel_ppag_callback, &ppag, NULL); - - if (ACPI_FAILURE(ppag.status)) { - if (ppag.status == AE_NOT_FOUND) { + status = acpi_evaluate_object(handle, "PPAG", NULL, &buffer); + if (ACPI_FAILURE(status)) { + if (status == AE_NOT_FOUND) { bt_dev_dbg(hdev, "PPAG-BT: ACPI entry not found"); return; } + bt_dev_warn(hdev, "PPAG-BT: ACPI Failure: %s", acpi_format_exception(status)); return; } - if (ppag.domain != 0x12) { + p = buffer.pointer; + if (p->type != ACPI_TYPE_PACKAGE || p->package.count != 2) { + bt_dev_warn(hdev, "PPAG-BT: Invalid object type: %d or package count: %d", + p->type, p->package.count); + kfree(buffer.pointer); + return; + } + + elements = p->package.elements; + + /* PPAG table is located at element[1] */ + p = &elements[1]; + + domain = (u32)p->package.elements[0].integer.value; + mode = (u32)p->package.elements[1].integer.value; + kfree(buffer.pointer); + + if (domain != 0x12) { bt_dev_dbg(hdev, "PPAG-BT: Bluetooth domain is disabled in ACPI firmware"); return; } @@ -2446,19 +2392,22 @@ static void btintel_set_ppag(struct hci_dev *hdev, struct intel_version_tlv *ver * BIT 1 : 0 Disabled in China * 1 Enabled in China */ - if ((ppag.mode & 0x01) != BIT(0) && (ppag.mode & 0x02) != BIT(1)) { - bt_dev_dbg(hdev, "PPAG-BT: EU, China mode are disabled in CB/BIOS"); + mode &= 0x03; + + if (!mode) { + bt_dev_dbg(hdev, "PPAG-BT: EU, China mode are disabled in BIOS"); return; } - ppag_cmd.ppag_enable_flags = cpu_to_le32(ppag.mode); + ppag_cmd.ppag_enable_flags = cpu_to_le32(mode); - skb = __hci_cmd_sync(hdev, INTEL_OP_PPAG_CMD, sizeof(ppag_cmd), &ppag_cmd, HCI_CMD_TIMEOUT); + skb = __hci_cmd_sync(hdev, INTEL_OP_PPAG_CMD, sizeof(ppag_cmd), + &ppag_cmd, HCI_CMD_TIMEOUT); if (IS_ERR(skb)) { bt_dev_warn(hdev, "Failed to send PPAG Enable (%ld)", PTR_ERR(skb)); return; } - bt_dev_info(hdev, "PPAG-BT: Enabled (Mode %d)", ppag.mode); + bt_dev_info(hdev, "PPAG-BT: Enabled (Mode %d)", mode); kfree_skb(skb); } @@ -2896,6 +2845,9 @@ static int btintel_setup_combined(struct hci_dev *hdev) btintel_set_dsm_reset_method(hdev, &ver_tlv); err = btintel_bootloader_setup_tlv(hdev, &ver_tlv); + if (err) + goto exit_error; + btintel_register_devcoredump_support(hdev); break; default: diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c index 9658b33c824a70..18f34998a1204a 100644 --- a/drivers/bluetooth/btmrvl_main.c +++ b/drivers/bluetooth/btmrvl_main.c @@ -121,13 +121,6 @@ int btmrvl_process_event(struct btmrvl_private *priv, struct sk_buff *skb) ((event->data[2] == MODULE_BROUGHT_UP) || (event->data[2] == MODULE_ALREADY_UP)) ? "Bring-up succeed" : "Bring-up failed"); - - if (event->length > 3 && event->data[3]) - priv->btmrvl_dev.dev_type = HCI_AMP; - else - priv->btmrvl_dev.dev_type = HCI_PRIMARY; - - BT_DBG("dev_type: %d", priv->btmrvl_dev.dev_type); } else if (priv->btmrvl_dev.sendcmdflag && event->data[1] == MODULE_SHUTDOWN_REQ) { BT_DBG("EVENT:%s", (event->data[2]) ? @@ -686,8 +679,6 @@ int btmrvl_register_hdev(struct btmrvl_private *priv) hdev->wakeup = btmrvl_wakeup; SET_HCIDEV_DEV(hdev, &card->func->dev); - hdev->dev_type = priv->btmrvl_dev.dev_type; - ret = hci_register_dev(hdev); if (ret < 0) { BT_ERR("Can not register HCI device"); diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index d76c799553aaa1..468e4165c7cc0e 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -92,7 +92,7 @@ static int btmrvl_sdio_probe_of(struct device *dev, } else { ret = devm_request_irq(dev, cfg->irq_bt, btmrvl_wake_irq_bt, - 0, "bt_wake", card); + IRQF_NO_AUTOEN, "bt_wake", card); if (ret) { dev_err(dev, "Failed to request irq_bt %d (%d)\n", @@ -101,7 +101,6 @@ static int btmrvl_sdio_probe_of(struct device *dev, /* Configure wakeup (enabled by default) */ device_init_wakeup(dev, true); - disable_irq(cfg->irq_bt); } } diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index aaabb732082cd8..812fd2a8f853e1 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -372,14 +372,18 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) struct btmediatek_data *data = hci_get_priv(hdev); int err; - if (!IS_ENABLED(CONFIG_DEV_COREDUMP)) + if (!IS_ENABLED(CONFIG_DEV_COREDUMP)) { + kfree_skb(skb); return 0; + } switch (data->cd_info.state) { case HCI_DEVCOREDUMP_IDLE: err = hci_devcd_init(hdev, MTK_COREDUMP_SIZE); - if (err < 0) + if (err < 0) { + kfree_skb(skb); break; + } data->cd_info.cnt = 0; /* It is supposed coredump can be done within 5 seconds */ @@ -405,9 +409,6 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) break; } - if (err < 0) - kfree_skb(skb); - return err; } EXPORT_SYMBOL_GPL(btmtk_process_coredump); @@ -420,5 +421,6 @@ MODULE_LICENSE("GPL"); MODULE_FIRMWARE(FIRMWARE_MT7622); MODULE_FIRMWARE(FIRMWARE_MT7663); MODULE_FIRMWARE(FIRMWARE_MT7668); +MODULE_FIRMWARE(FIRMWARE_MT7922); MODULE_FIRMWARE(FIRMWARE_MT7961); MODULE_FIRMWARE(FIRMWARE_MT7925); diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h index 56f5502baadf9f..cbcdb99a22e6dd 100644 --- a/drivers/bluetooth/btmtk.h +++ b/drivers/bluetooth/btmtk.h @@ -4,6 +4,7 @@ #define FIRMWARE_MT7622 "mediatek/mt7622pr2h.bin" #define FIRMWARE_MT7663 "mediatek/mt7663pr2h.bin" #define FIRMWARE_MT7668 "mediatek/mt7668pr2h.bin" +#define FIRMWARE_MT7922 "mediatek/BT_RAM_CODE_MT7922_1_1_hdr.bin" #define FIRMWARE_MT7961 "mediatek/BT_RAM_CODE_MT7961_1_2_hdr.bin" #define FIRMWARE_MT7925 "mediatek/mt7925/BT_RAM_CODE_MT7925_1_1_hdr.bin" diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c index 935feab815d973..203a000a84e341 100644 --- a/drivers/bluetooth/btmtkuart.c +++ b/drivers/bluetooth/btmtkuart.c @@ -336,7 +336,7 @@ mtk_stp_split(struct btmtkuart_dev *bdev, const unsigned char *data, int count, return data; } -static int btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count) +static void btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count) { struct btmtkuart_dev *bdev = hci_get_drvdata(hdev); const unsigned char *p_left = data, *p_h4; @@ -375,25 +375,20 @@ static int btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count) bt_dev_err(bdev->hdev, "Frame reassembly failed (%d)", err); bdev->rx_skb = NULL; - return err; + return; } sz_left -= sz_h4; p_left += sz_h4; } - - return 0; } static int btmtkuart_receive_buf(struct serdev_device *serdev, const u8 *data, size_t count) { struct btmtkuart_dev *bdev = serdev_device_get_drvdata(serdev); - int err; - err = btmtkuart_recv(bdev->hdev, data, count); - if (err < 0) - return err; + btmtkuart_recv(bdev->hdev, data, count); bdev->hdev->stat.byte_rx += count; diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index b7e66b7ac57022..5ee9a8b8dcfdb8 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -29,6 +29,7 @@ #define BTNXPUART_CHECK_BOOT_SIGNATURE 3 #define BTNXPUART_SERDEV_OPEN 4 #define BTNXPUART_IR_IN_PROGRESS 5 +#define BTNXPUART_FW_DOWNLOAD_ABORT 6 /* NXP HW err codes */ #define BTNXPUART_IR_HW_ERR 0xb0 @@ -126,6 +127,7 @@ struct ps_data { struct hci_dev *hdev; struct work_struct work; struct timer_list ps_timer; + struct mutex ps_lock; }; struct wakeup_cmd_payload { @@ -158,6 +160,7 @@ struct btnxpuart_dev { u8 fw_name[MAX_FW_FILE_NAME_LEN]; u32 fw_dnld_v1_offset; u32 fw_v1_sent_bytes; + u32 fw_dnld_v3_offset; u32 fw_v3_offset_correction; u32 fw_v1_expected_len; u32 boot_reg_offset; @@ -186,6 +189,11 @@ struct btnxpuart_dev { #define NXP_NAK_V3 0x7b #define NXP_CRC_ERROR_V3 0x7c +/* Bootloader signature error codes */ +#define NXP_ACK_RX_TIMEOUT 0x0002 /* ACK not received from host */ +#define NXP_HDR_RX_TIMEOUT 0x0003 /* FW Header chunk not received */ +#define NXP_DATA_RX_TIMEOUT 0x0004 /* FW Data chunk not received */ + #define HDR_LEN 16 #define NXP_RECV_CHIP_VER_V1 \ @@ -276,11 +284,22 @@ struct nxp_bootloader_cmd { __be32 crc; } __packed; +struct nxp_v3_rx_timeout_nak { + u8 nak; + __le32 offset; + u8 crc; +} __packed; + +union nxp_v3_rx_timeout_nak_u { + struct nxp_v3_rx_timeout_nak pkt; + u8 buf[6]; +}; + static u8 crc8_table[CRC8_TABLE_SIZE]; /* Default configurations */ #define DEFAULT_H2C_WAKEUP_MODE WAKEUP_METHOD_BREAK -#define DEFAULT_PS_MODE PS_MODE_DISABLE +#define DEFAULT_PS_MODE PS_MODE_ENABLE #define FW_INIT_BAUDRATE HCI_NXP_PRI_BAUDRATE static struct sk_buff *nxp_drv_send_cmd(struct hci_dev *hdev, u16 opcode, @@ -317,6 +336,9 @@ static void ps_start_timer(struct btnxpuart_dev *nxpdev) if (psdata->cur_psmode == PS_MODE_ENABLE) mod_timer(&psdata->ps_timer, jiffies + msecs_to_jiffies(psdata->h2c_ps_interval)); + + if (psdata->ps_state == PS_STATE_AWAKE && psdata->ps_cmd == PS_CMD_ENTER_PS) + cancel_work_sync(&psdata->work); } static void ps_cancel_timer(struct btnxpuart_dev *nxpdev) @@ -324,7 +346,7 @@ static void ps_cancel_timer(struct btnxpuart_dev *nxpdev) struct ps_data *psdata = &nxpdev->psdata; flush_work(&psdata->work); - del_timer_sync(&psdata->ps_timer); + timer_shutdown_sync(&psdata->ps_timer); } static void ps_control(struct hci_dev *hdev, u8 ps_state) @@ -337,6 +359,7 @@ static void ps_control(struct hci_dev *hdev, u8 ps_state) !test_bit(BTNXPUART_SERDEV_OPEN, &nxpdev->tx_state)) return; + mutex_lock(&psdata->ps_lock); switch (psdata->cur_h2c_wakeupmode) { case WAKEUP_METHOD_DTR: if (ps_state == PS_STATE_AWAKE) @@ -350,12 +373,15 @@ static void ps_control(struct hci_dev *hdev, u8 ps_state) status = serdev_device_break_ctl(nxpdev->serdev, 0); else status = serdev_device_break_ctl(nxpdev->serdev, -1); + msleep(20); /* Allow chip to detect UART-break and enter sleep */ bt_dev_dbg(hdev, "Set UART break: %s, status=%d", str_on_off(ps_state == PS_STATE_SLEEP), status); break; } if (!status) psdata->ps_state = ps_state; + mutex_unlock(&psdata->ps_lock); + if (ps_state == PS_STATE_AWAKE) btnxpuart_tx_wakeup(nxpdev); } @@ -391,17 +417,42 @@ static void ps_setup(struct hci_dev *hdev) psdata->hdev = hdev; INIT_WORK(&psdata->work, ps_work_func); + mutex_init(&psdata->ps_lock); timer_setup(&psdata->ps_timer, ps_timeout_func, 0); } -static void ps_wakeup(struct btnxpuart_dev *nxpdev) +static bool ps_wakeup(struct btnxpuart_dev *nxpdev) { struct ps_data *psdata = &nxpdev->psdata; + u8 ps_state; + + mutex_lock(&psdata->ps_lock); + ps_state = psdata->ps_state; + mutex_unlock(&psdata->ps_lock); - if (psdata->ps_state != PS_STATE_AWAKE) { + if (ps_state != PS_STATE_AWAKE) { psdata->ps_cmd = PS_CMD_EXIT_PS; schedule_work(&psdata->work); + return true; } + return false; +} + +static void ps_cleanup(struct btnxpuart_dev *nxpdev) +{ + struct ps_data *psdata = &nxpdev->psdata; + u8 ps_state; + + mutex_lock(&psdata->ps_lock); + ps_state = psdata->ps_state; + mutex_unlock(&psdata->ps_lock); + + if (ps_state != PS_STATE_AWAKE) + ps_control(psdata->hdev, PS_STATE_AWAKE); + + ps_cancel_timer(nxpdev); + cancel_work_sync(&psdata->work); + mutex_destroy(&psdata->ps_lock); } static int send_ps_cmd(struct hci_dev *hdev, void *data) @@ -534,6 +585,7 @@ static int nxp_download_firmware(struct hci_dev *hdev) nxpdev->fw_v1_sent_bytes = 0; nxpdev->fw_v1_expected_len = HDR_LEN; nxpdev->boot_reg_offset = 0; + nxpdev->fw_dnld_v3_offset = 0; nxpdev->fw_v3_offset_correction = 0; nxpdev->baudrate_changed = false; nxpdev->timeout_changed = false; @@ -548,14 +600,23 @@ static int nxp_download_firmware(struct hci_dev *hdev) !test_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state), msecs_to_jiffies(60000)); + + release_firmware(nxpdev->fw); + memset(nxpdev->fw_name, 0, sizeof(nxpdev->fw_name)); + if (err == 0) { - bt_dev_err(hdev, "FW Download Timeout."); + bt_dev_err(hdev, "FW Download Timeout. offset: %d", + nxpdev->fw_dnld_v1_offset ? + nxpdev->fw_dnld_v1_offset : + nxpdev->fw_dnld_v3_offset); return -ETIMEDOUT; } + if (test_bit(BTNXPUART_FW_DOWNLOAD_ABORT, &nxpdev->tx_state)) { + bt_dev_err(hdev, "FW Download Aborted"); + return -EINTR; + } serdev_device_set_flow_control(nxpdev->serdev, true); - release_firmware(nxpdev->fw); - memset(nxpdev->fw_name, 0, sizeof(nxpdev->fw_name)); /* Allow the downloaded FW to initialize */ msleep(1200); @@ -883,6 +944,32 @@ static int nxp_recv_chip_ver_v3(struct hci_dev *hdev, struct sk_buff *skb) return 0; } +static void nxp_handle_fw_download_error(struct hci_dev *hdev, struct v3_data_req *req) +{ + struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev); + __u32 offset = __le32_to_cpu(req->offset); + __u16 err = __le16_to_cpu(req->error); + union nxp_v3_rx_timeout_nak_u nak_tx_buf; + + switch (err) { + case NXP_ACK_RX_TIMEOUT: + case NXP_HDR_RX_TIMEOUT: + case NXP_DATA_RX_TIMEOUT: + nak_tx_buf.pkt.nak = NXP_NAK_V3; + nak_tx_buf.pkt.offset = __cpu_to_le32(offset); + nak_tx_buf.pkt.crc = crc8(crc8_table, nak_tx_buf.buf, + sizeof(nak_tx_buf) - 1, 0xff); + serdev_device_write_buf(nxpdev->serdev, nak_tx_buf.buf, + sizeof(nak_tx_buf)); + break; + default: + bt_dev_dbg(hdev, "Unknown bootloader error code: %d", err); + break; + + } + +} + static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb) { struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev); @@ -897,7 +984,12 @@ static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb) if (!req || !nxpdev->fw) goto free_skb; - nxp_send_ack(NXP_ACK_V3, hdev); + if (!req->error) { + nxp_send_ack(NXP_ACK_V3, hdev); + } else { + nxp_handle_fw_download_error(hdev, req); + goto free_skb; + } len = __le16_to_cpu(req->len); @@ -924,9 +1016,6 @@ static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb) wake_up_interruptible(&nxpdev->fw_dnld_done_wait_q); goto free_skb; } - if (req->error) - bt_dev_dbg(hdev, "FW Download received err 0x%02x from chip", - req->error); offset = __le32_to_cpu(req->offset); if (offset < nxpdev->fw_v3_offset_correction) { @@ -938,8 +1027,9 @@ static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb) goto free_skb; } - serdev_device_write_buf(nxpdev->serdev, nxpdev->fw->data + offset - - nxpdev->fw_v3_offset_correction, len); + nxpdev->fw_dnld_v3_offset = offset - nxpdev->fw_v3_offset_correction; + serdev_device_write_buf(nxpdev->serdev, nxpdev->fw->data + + nxpdev->fw_dnld_v3_offset, len); free_skb: kfree_skb(skb); @@ -1171,7 +1261,6 @@ static struct sk_buff *nxp_dequeue(void *data) { struct btnxpuart_dev *nxpdev = (struct btnxpuart_dev *)data; - ps_wakeup(nxpdev); ps_start_timer(nxpdev); return skb_dequeue(&nxpdev->txq); } @@ -1186,6 +1275,9 @@ static void btnxpuart_tx_work(struct work_struct *work) struct sk_buff *skb; int len; + if (ps_wakeup(nxpdev)) + return; + while ((skb = nxp_dequeue(nxpdev))) { len = serdev_device_write_buf(serdev, skb->data, skb->len); hdev->stat.byte_tx += len; @@ -1232,8 +1324,12 @@ static int btnxpuart_close(struct hci_dev *hdev) { struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev); - ps_wakeup(nxpdev); serdev_device_close(nxpdev->serdev); + skb_queue_purge(&nxpdev->txq); + if (!IS_ERR_OR_NULL(nxpdev->rx_skb)) { + kfree_skb(nxpdev->rx_skb); + nxpdev->rx_skb = NULL; + } clear_bit(BTNXPUART_SERDEV_OPEN, &nxpdev->tx_state); return 0; } @@ -1248,8 +1344,10 @@ static int btnxpuart_flush(struct hci_dev *hdev) cancel_work_sync(&nxpdev->tx_work); - kfree_skb(nxpdev->rx_skb); - nxpdev->rx_skb = NULL; + if (!IS_ERR_OR_NULL(nxpdev->rx_skb)) { + kfree_skb(nxpdev->rx_skb); + nxpdev->rx_skb = NULL; + } return 0; } @@ -1276,11 +1374,10 @@ static int btnxpuart_receive_buf(struct serdev_device *serdev, const u8 *data, if (IS_ERR(nxpdev->rx_skb)) { int err = PTR_ERR(nxpdev->rx_skb); /* Safe to ignore out-of-sync bootloader signatures */ - if (is_fw_downloading(nxpdev)) - return count; - bt_dev_err(nxpdev->hdev, "Frame reassembly failed (%d)", err); + if (!is_fw_downloading(nxpdev)) + bt_dev_err(nxpdev->hdev, "Frame reassembly failed (%d)", err); nxpdev->rx_skb = NULL; - return err; + return count; } if (!is_fw_downloading(nxpdev)) nxpdev->hdev->stat.byte_rx += count; @@ -1366,16 +1463,22 @@ static void nxp_serdev_remove(struct serdev_device *serdev) struct btnxpuart_dev *nxpdev = serdev_device_get_drvdata(serdev); struct hci_dev *hdev = nxpdev->hdev; - /* Restore FW baudrate to fw_init_baudrate if changed. - * This will ensure FW baudrate is in sync with - * driver baudrate in case this driver is re-inserted. - */ - if (nxpdev->current_baudrate != nxpdev->fw_init_baudrate) { - nxpdev->new_baudrate = nxpdev->fw_init_baudrate; - nxp_set_baudrate_cmd(hdev, NULL); + if (is_fw_downloading(nxpdev)) { + set_bit(BTNXPUART_FW_DOWNLOAD_ABORT, &nxpdev->tx_state); + clear_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state); + wake_up_interruptible(&nxpdev->check_boot_sign_wait_q); + wake_up_interruptible(&nxpdev->fw_dnld_done_wait_q); + } else { + /* Restore FW baudrate to fw_init_baudrate if changed. + * This will ensure FW baudrate is in sync with + * driver baudrate in case this driver is re-inserted. + */ + if (nxpdev->current_baudrate != nxpdev->fw_init_baudrate) { + nxpdev->new_baudrate = nxpdev->fw_init_baudrate; + nxp_set_baudrate_cmd(hdev, NULL); + } } - - ps_cancel_timer(nxpdev); + ps_cleanup(nxpdev); hci_unregister_dev(hdev); hci_free_dev(hdev); } diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index 5a35ac4138c6cf..35fb26cbf22941 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -99,7 +99,8 @@ static int qca_read_fw_build_info(struct hci_dev *hdev) { struct sk_buff *skb; struct edl_event_hdr *edl; - char cmd, build_label[QCA_FW_BUILD_VER_LEN]; + char *build_label; + char cmd; int build_lbl_len, err = 0; bt_dev_dbg(hdev, "QCA read fw build info"); @@ -114,6 +115,11 @@ static int qca_read_fw_build_info(struct hci_dev *hdev) return err; } + if (skb->len < sizeof(*edl)) { + err = -EILSEQ; + goto out; + } + edl = (struct edl_event_hdr *)(skb->data); if (!edl) { bt_dev_err(hdev, "QCA read fw build info with no header"); @@ -129,14 +135,27 @@ static int qca_read_fw_build_info(struct hci_dev *hdev) goto out; } + if (skb->len < sizeof(*edl) + 1) { + err = -EILSEQ; + goto out; + } + build_lbl_len = edl->data[0]; - if (build_lbl_len <= QCA_FW_BUILD_VER_LEN - 1) { - memcpy(build_label, edl->data + 1, build_lbl_len); - *(build_label + build_lbl_len) = '\0'; + + if (skb->len < sizeof(*edl) + 1 + build_lbl_len) { + err = -EILSEQ; + goto out; + } + + build_label = kstrndup(&edl->data[1], build_lbl_len, GFP_KERNEL); + if (!build_label) { + err = -ENOMEM; + goto out; } hci_set_fw_info(hdev, "%s", build_label); + kfree(build_label); out: kfree_skb(skb); return err; @@ -152,7 +171,7 @@ static int qca_send_patch_config_cmd(struct hci_dev *hdev) bt_dev_dbg(hdev, "QCA Patch config"); skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, sizeof(cmd), - cmd, HCI_EV_VENDOR, HCI_INIT_TIMEOUT); + cmd, 0, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); bt_dev_err(hdev, "Sending QCA Patch config failed (%d)", err); @@ -205,6 +224,49 @@ static int qca_send_reset(struct hci_dev *hdev) return 0; } +static int qca_read_fw_board_id(struct hci_dev *hdev, u16 *bid) +{ + u8 cmd; + struct sk_buff *skb; + struct edl_event_hdr *edl; + int err = 0; + + cmd = EDL_GET_BID_REQ_CMD; + skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, EDL_PATCH_CMD_LEN, + &cmd, 0, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + bt_dev_err(hdev, "Reading QCA board ID failed (%d)", err); + return err; + } + + edl = skb_pull_data(skb, sizeof(*edl)); + if (!edl) { + bt_dev_err(hdev, "QCA read board ID with no header"); + err = -EILSEQ; + goto out; + } + + if (edl->cresp != EDL_CMD_REQ_RES_EVT || + edl->rtype != EDL_GET_BID_REQ_CMD) { + bt_dev_err(hdev, "QCA Wrong packet: %d %d", edl->cresp, edl->rtype); + err = -EIO; + goto out; + } + + if (skb->len < 3) { + err = -EILSEQ; + goto out; + } + + *bid = (edl->data[1] << 8) + edl->data[2]; + bt_dev_dbg(hdev, "%s: bid = %x", __func__, *bid); + +out: + kfree_skb(skb); + return err; +} + int qca_send_pre_shutdown_cmd(struct hci_dev *hdev) { struct sk_buff *skb; @@ -227,9 +289,10 @@ int qca_send_pre_shutdown_cmd(struct hci_dev *hdev) } EXPORT_SYMBOL_GPL(qca_send_pre_shutdown_cmd); -static void qca_tlv_check_data(struct hci_dev *hdev, +static int qca_tlv_check_data(struct hci_dev *hdev, struct qca_fw_config *config, - u8 *fw_data, enum qca_btsoc_type soc_type) + u8 *fw_data, size_t fw_size, + enum qca_btsoc_type soc_type) { const u8 *data; u32 type_len; @@ -239,12 +302,16 @@ static void qca_tlv_check_data(struct hci_dev *hdev, struct tlv_type_patch *tlv_patch; struct tlv_type_nvm *tlv_nvm; uint8_t nvm_baud_rate = config->user_baud_rate; + u8 type; config->dnld_mode = QCA_SKIP_EVT_NONE; config->dnld_type = QCA_SKIP_EVT_NONE; switch (config->type) { case ELF_TYPE_PATCH: + if (fw_size < 7) + return -EINVAL; + config->dnld_mode = QCA_SKIP_EVT_VSE_CC; config->dnld_type = QCA_SKIP_EVT_VSE_CC; @@ -253,6 +320,9 @@ static void qca_tlv_check_data(struct hci_dev *hdev, bt_dev_dbg(hdev, "File version : 0x%x", fw_data[6]); break; case TLV_TYPE_PATCH: + if (fw_size < sizeof(struct tlv_type_hdr) + sizeof(struct tlv_type_patch)) + return -EINVAL; + tlv = (struct tlv_type_hdr *)fw_data; type_len = le32_to_cpu(tlv->type_len); tlv_patch = (struct tlv_type_patch *)tlv->data; @@ -292,25 +362,64 @@ static void qca_tlv_check_data(struct hci_dev *hdev, break; case TLV_TYPE_NVM: + if (fw_size < sizeof(struct tlv_type_hdr)) + return -EINVAL; + tlv = (struct tlv_type_hdr *)fw_data; type_len = le32_to_cpu(tlv->type_len); - length = (type_len >> 8) & 0x00ffffff; + length = type_len >> 8; + type = type_len & 0xff; - BT_DBG("TLV Type\t\t : 0x%x", type_len & 0x000000ff); + /* Some NVM files have more than one set of tags, only parse + * the first set when it has type 2 for now. When there is + * more than one set there is an enclosing header of type 4. + */ + if (type == 4) { + if (fw_size < 2 * sizeof(struct tlv_type_hdr)) + return -EINVAL; + + tlv++; + + type_len = le32_to_cpu(tlv->type_len); + length = type_len >> 8; + type = type_len & 0xff; + } + + BT_DBG("TLV Type\t\t : 0x%x", type); BT_DBG("Length\t\t : %d bytes", length); + if (type != 2) + break; + + if (fw_size < length + (tlv->data - fw_data)) + return -EINVAL; + idx = 0; data = tlv->data; - while (idx < length) { + while (idx < length - sizeof(struct tlv_type_nvm)) { tlv_nvm = (struct tlv_type_nvm *)(data + idx); tag_id = le16_to_cpu(tlv_nvm->tag_id); tag_len = le16_to_cpu(tlv_nvm->tag_len); + if (length < idx + sizeof(struct tlv_type_nvm) + tag_len) + return -EINVAL; + /* Update NVM tags as needed */ switch (tag_id) { + case EDL_TAG_ID_BD_ADDR: + if (tag_len != sizeof(bdaddr_t)) + return -EINVAL; + + memcpy(&config->bdaddr, tlv_nvm->data, sizeof(bdaddr_t)); + + break; + case EDL_TAG_ID_HCI: + if (tag_len < 3) + return -EINVAL; + /* HCI transport layer parameters * enabling software inband sleep * onto controller side. @@ -326,6 +435,9 @@ static void qca_tlv_check_data(struct hci_dev *hdev, break; case EDL_TAG_ID_DEEP_SLEEP: + if (tag_len < 1) + return -EINVAL; + /* Sleep enable mask * enabling deep sleep feature on controller. */ @@ -334,14 +446,16 @@ static void qca_tlv_check_data(struct hci_dev *hdev, break; } - idx += (sizeof(u16) + sizeof(u16) + 8 + tag_len); + idx += sizeof(struct tlv_type_nvm) + tag_len; } break; default: BT_ERR("Unknown TLV type %d", config->type); - break; + return -EINVAL; } + + return 0; } static int qca_tlv_send_segment(struct hci_dev *hdev, int seg_size, @@ -491,7 +605,9 @@ static int qca_download_firmware(struct hci_dev *hdev, memcpy(data, fw->data, size); release_firmware(fw); - qca_tlv_check_data(hdev, config, data, soc_type); + ret = qca_tlv_check_data(hdev, config, data, size, soc_type); + if (ret) + goto out; segment = data; remain = size; @@ -574,14 +690,64 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr) } EXPORT_SYMBOL_GPL(qca_set_bdaddr_rome); +static int qca_check_bdaddr(struct hci_dev *hdev, const struct qca_fw_config *config) +{ + struct hci_rp_read_bd_addr *bda; + struct sk_buff *skb; + int err; + + if (bacmp(&hdev->public_addr, BDADDR_ANY)) + return 0; + + skb = __hci_cmd_sync(hdev, HCI_OP_READ_BD_ADDR, 0, NULL, + HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + bt_dev_err(hdev, "Failed to read device address (%d)", err); + return err; + } + + if (skb->len != sizeof(*bda)) { + bt_dev_err(hdev, "Device address length mismatch"); + kfree_skb(skb); + return -EIO; + } + + bda = (struct hci_rp_read_bd_addr *)skb->data; + if (!bacmp(&bda->bdaddr, &config->bdaddr)) + set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); + + kfree_skb(skb); + + return 0; +} + +static void qca_generate_hsp_nvm_name(char *fwname, size_t max_size, + struct qca_btsoc_version ver, u8 rom_ver, u16 bid) +{ + const char *variant; + + /* hsp gf chip */ + if ((le32_to_cpu(ver.soc_id) & QCA_HSP_GF_SOC_MASK) == QCA_HSP_GF_SOC_ID) + variant = "g"; + else + variant = ""; + + if (bid == 0x0) + snprintf(fwname, max_size, "qca/hpnv%02x%s.bin", rom_ver, variant); + else + snprintf(fwname, max_size, "qca/hpnv%02x%s.%x", rom_ver, variant, bid); +} + int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, enum qca_btsoc_type soc_type, struct qca_btsoc_version ver, const char *firmware_name) { - struct qca_fw_config config; + struct qca_fw_config config = {}; int err; u8 rom_ver = 0; u32 soc_ver; + u16 boardid = 0; bt_dev_dbg(hdev, "QCA setup on UART"); @@ -615,6 +781,10 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, snprintf(config.fwname, sizeof(config.fwname), "qca/apbtfw%02x.tlv", rom_ver); break; + case QCA_QCA2066: + snprintf(config.fwname, sizeof(config.fwname), + "qca/hpbtfw%02x.tlv", rom_ver); + break; case QCA_QCA6390: snprintf(config.fwname, sizeof(config.fwname), "qca/htbtfw%02x.tlv", rom_ver); @@ -649,6 +819,9 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, /* Give the controller some time to get ready to receive the NVM */ msleep(10); + if (soc_type == QCA_QCA2066) + qca_read_fw_board_id(hdev, &boardid); + /* Download NVM configuration */ config.type = TLV_TYPE_NVM; if (firmware_name) { @@ -671,6 +844,10 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, snprintf(config.fwname, sizeof(config.fwname), "qca/apnv%02x.bin", rom_ver); break; + case QCA_QCA2066: + qca_generate_hsp_nvm_name(config.fwname, + sizeof(config.fwname), ver, rom_ver, boardid); + break; case QCA_QCA6390: snprintf(config.fwname, sizeof(config.fwname), "qca/htnv%02x.bin", rom_ver); @@ -702,6 +879,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, switch (soc_type) { case QCA_WCN3991: + case QCA_QCA2066: case QCA_QCA6390: case QCA_WCN6750: case QCA_WCN6855: @@ -750,6 +928,10 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, break; } + err = qca_check_bdaddr(hdev, &config); + if (err) + return err; + bt_dev_info(hdev, "QCA setup on UART is completed"); return 0; @@ -758,11 +940,15 @@ EXPORT_SYMBOL_GPL(qca_uart_setup); int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr) { + bdaddr_t bdaddr_swapped; struct sk_buff *skb; int err; - skb = __hci_cmd_sync_ev(hdev, EDL_WRITE_BD_ADDR_OPCODE, 6, bdaddr, - HCI_EV_VENDOR, HCI_INIT_TIMEOUT); + baswap(&bdaddr_swapped, bdaddr); + + skb = __hci_cmd_sync_ev(hdev, EDL_WRITE_BD_ADDR_OPCODE, 6, + &bdaddr_swapped, HCI_EV_VENDOR, + HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); bt_dev_err(hdev, "QCA Change address cmd failed (%d)", err); diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h index 03bff5c0059def..215433fd76a106 100644 --- a/drivers/bluetooth/btqca.h +++ b/drivers/bluetooth/btqca.h @@ -12,6 +12,7 @@ #define EDL_PATCH_VER_REQ_CMD (0x19) #define EDL_PATCH_TLV_REQ_CMD (0x1E) #define EDL_GET_BUILD_INFO_CMD (0x20) +#define EDL_GET_BID_REQ_CMD (0x23) #define EDL_NVM_ACCESS_SET_REQ_CMD (0x01) #define EDL_PATCH_CONFIG_CMD (0x28) #define MAX_SIZE_PER_TLV_SEGMENT (243) @@ -28,6 +29,7 @@ #define EDL_PATCH_CONFIG_RES_EVT (0x00) #define QCA_DISABLE_LOGGING_SUB_OP (0x14) +#define EDL_TAG_ID_BD_ADDR 2 #define EDL_TAG_ID_HCI (17) #define EDL_TAG_ID_DEEP_SLEEP (27) @@ -46,8 +48,8 @@ #define get_soc_ver(soc_id, rom_ver) \ ((le32_to_cpu(soc_id) << 16) | (le16_to_cpu(rom_ver))) -#define QCA_FW_BUILD_VER_LEN 255 - +#define QCA_HSP_GF_SOC_ID 0x1200 +#define QCA_HSP_GF_SOC_MASK 0x0000ff00 enum qca_baudrate { QCA_BAUDRATE_115200 = 0, @@ -92,6 +94,7 @@ struct qca_fw_config { uint8_t user_baud_rate; enum qca_tlv_dnld_mode dnld_mode; enum qca_tlv_dnld_mode dnld_type; + bdaddr_t bdaddr; }; struct edl_event_hdr { @@ -146,6 +149,7 @@ enum qca_btsoc_type { QCA_WCN3990, QCA_WCN3998, QCA_WCN3991, + QCA_QCA2066, QCA_QCA6390, QCA_WCN6750, QCA_WCN6855, diff --git a/drivers/bluetooth/btrsi.c b/drivers/bluetooth/btrsi.c index 634cf8f5ed2dbd..0c91d7635ac39e 100644 --- a/drivers/bluetooth/btrsi.c +++ b/drivers/bluetooth/btrsi.c @@ -134,7 +134,6 @@ static int rsi_hci_attach(void *priv, struct rsi_proto_ops *ops) hdev->bus = HCI_USB; hci_set_drvdata(hdev, h_adapter); - hdev->dev_type = HCI_PRIMARY; hdev->open = rsi_hci_open; hdev->close = rsi_hci_close; hdev->flush = rsi_hci_flush; diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 277d039ecbb429..1e7c1f9db9e4b9 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -1285,6 +1285,7 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) btrealtek_set_flag(hdev, REALTEK_ALT6_CONTINUOUS_TX_CHIP); if (btrtl_dev->project_id == CHIP_ID_8852A || + btrtl_dev->project_id == CHIP_ID_8852B || btrtl_dev->project_id == CHIP_ID_8852C) set_bit(HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER, &hdev->quirks); diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index f19d31ee37ea89..fdcfe9c50313ea 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -32,9 +32,6 @@ static const struct sdio_device_id btsdio_table[] = { /* Generic Bluetooth Type-B SDIO device */ { SDIO_DEVICE_CLASS(SDIO_CLASS_BT_B) }, - /* Generic Bluetooth AMP controller */ - { SDIO_DEVICE_CLASS(SDIO_CLASS_BT_AMP) }, - { } /* Terminating entry */ }; @@ -319,11 +316,6 @@ static int btsdio_probe(struct sdio_func *func, hdev->bus = HCI_SDIO; hci_set_drvdata(hdev, data); - if (id->class == SDIO_CLASS_BT_AMP) - hdev->dev_type = HCI_AMP; - else - hdev->dev_type = HCI_PRIMARY; - data->hdev = hdev; SET_HCIDEV_DEV(hdev, &func->dev); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 499f4809fcdf3d..b3a9b93f027a90 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -537,14 +537,26 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3592), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0489, 0xe122), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek 8852BE Bluetooth devices */ { USB_DEVICE(0x0cb8, 0xc559), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0bda, 0x4853), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0bda, 0x887b), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0bda, 0xb85b), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x13d3, 0x3570), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3571), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x13d3, 0x3591), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0489, 0xe125), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek Bluetooth devices */ { USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01), @@ -1342,7 +1354,15 @@ static int btusb_submit_intr_urb(struct hci_dev *hdev, gfp_t mem_flags) if (!urb) return -ENOMEM; - size = le16_to_cpu(data->intr_ep->wMaxPacketSize); + if (le16_to_cpu(data->udev->descriptor.idVendor) == 0x0a12 && + le16_to_cpu(data->udev->descriptor.idProduct) == 0x0001) + /* Fake CSR devices don't seem to support sort-transter */ + size = le16_to_cpu(data->intr_ep->wMaxPacketSize); + else + /* Use maximum HCI Event size so the USB stack handles + * ZPL/short-transfer automatically. + */ + size = HCI_MAX_EVENT_SIZE; buf = kmalloc(size, mem_flags); if (!buf) { @@ -2818,6 +2838,9 @@ static int btusb_mtk_hci_wmt_sync(struct hci_dev *hdev, goto err_free_wc; } + if (data->evt_skb == NULL) + goto err_free_wc; + /* Parse and handle the return WMT event */ wmt_evt = (struct btmtk_hci_wmt_evt *)data->evt_skb->data; if (wmt_evt->whdr.op != hdr->op) { @@ -3260,7 +3283,6 @@ static int btusb_recv_acl_mtk(struct hci_dev *hdev, struct sk_buff *skb) { struct btusb_data *data = hci_get_drvdata(hdev); u16 handle = le16_to_cpu(hci_acl_hdr(skb)->handle); - struct sk_buff *skb_cd; switch (handle) { case 0xfc6f: /* Firmware dump from device */ @@ -3273,9 +3295,12 @@ static int btusb_recv_acl_mtk(struct hci_dev *hdev, struct sk_buff *skb) * for backward compatibility, so we have to clone the packet * extraly for the in-kernel coredump support. */ - skb_cd = skb_clone(skb, GFP_ATOMIC); - if (skb_cd) - btmtk_process_coredump(hdev, skb_cd); + if (IS_ENABLED(CONFIG_DEV_COREDUMP)) { + struct sk_buff *skb_cd = skb_clone(skb, GFP_ATOMIC); + + if (skb_cd) + btmtk_process_coredump(hdev, skb_cd); + } fallthrough; case 0x05ff: /* Firmware debug logging 1 */ @@ -3448,13 +3473,12 @@ static void btusb_dump_hdr_qca(struct hci_dev *hdev, struct sk_buff *skb) static void btusb_coredump_qca(struct hci_dev *hdev) { + int err; static const u8 param[] = { 0x26 }; - struct sk_buff *skb; - skb = __hci_cmd_sync(hdev, 0xfc0c, 1, param, HCI_CMD_TIMEOUT); - if (IS_ERR(skb)) - bt_dev_err(hdev, "%s: triggle crash failed (%ld)", __func__, PTR_ERR(skb)); - kfree_skb(skb); + err = __hci_cmd_send(hdev, 0xfc0c, 1, param); + if (err < 0) + bt_dev_err(hdev, "%s: triggle crash failed (%d)", __func__, err); } /* @@ -4298,11 +4322,6 @@ static int btusb_probe(struct usb_interface *intf, hdev->bus = HCI_USB; hci_set_drvdata(hdev, data); - if (id->driver_info & BTUSB_AMP) - hdev->dev_type = HCI_AMP; - else - hdev->dev_type = HCI_PRIMARY; - data->hdev = hdev; SET_HCIDEV_DEV(hdev, &intf->dev); @@ -4468,6 +4487,7 @@ static int btusb_probe(struct usb_interface *intf, set_bit(HCI_QUIRK_BROKEN_READ_TRANSMIT_POWER, &hdev->quirks); set_bit(HCI_QUIRK_BROKEN_SET_RPA_TIMEOUT, &hdev->quirks); set_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &hdev->quirks); + set_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks); } if (!reset) diff --git a/drivers/bluetooth/hci_bcm4377.c b/drivers/bluetooth/hci_bcm4377.c index 19ad0e78864629..0dc3ca3d410736 100644 --- a/drivers/bluetooth/hci_bcm4377.c +++ b/drivers/bluetooth/hci_bcm4377.c @@ -32,7 +32,7 @@ enum bcm4377_chip { #define BCM4378_DEVICE_ID 0x5f69 #define BCM4387_DEVICE_ID 0x5f71 -#define BCM4377_TIMEOUT 1000 +#define BCM4377_TIMEOUT msecs_to_jiffies(1000) /* * These devices only support DMA transactions inside a 32bit window @@ -512,6 +512,7 @@ struct bcm4377_hw { unsigned long disable_aspm : 1; unsigned long broken_ext_scan : 1; unsigned long broken_mws_transport_config : 1; + unsigned long broken_le_coded : 1; int (*send_calibration)(struct bcm4377_data *bcm4377); int (*send_ptb)(struct bcm4377_data *bcm4377, @@ -715,7 +716,7 @@ static void bcm4377_handle_ack(struct bcm4377_data *bcm4377, ring->events[msgid] = NULL; } - bitmap_release_region(ring->msgids, msgid, ring->n_entries); + bitmap_release_region(ring->msgids, msgid, 0); unlock: spin_unlock_irqrestore(&ring->lock, flags); @@ -1416,7 +1417,7 @@ static int bcm4377_check_bdaddr(struct bcm4377_data *bcm4377) bda = (struct hci_rp_read_bd_addr *)skb->data; if (!bcm4377_is_valid_bdaddr(bcm4377, &bda->bdaddr)) - set_bit(HCI_QUIRK_INVALID_BDADDR, &bcm4377->hdev->quirks); + set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &bcm4377->hdev->quirks); kfree_skb(skb); return 0; @@ -2360,18 +2361,18 @@ static int bcm4377_probe(struct pci_dev *pdev, const struct pci_device_id *id) bcm4377->hdev = hdev; hdev->bus = HCI_PCI; - hdev->dev_type = HCI_PRIMARY; hdev->open = bcm4377_hci_open; hdev->close = bcm4377_hci_close; hdev->send = bcm4377_hci_send_frame; hdev->set_bdaddr = bcm4377_hci_set_bdaddr; hdev->setup = bcm4377_hci_setup; - set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); if (bcm4377->hw->broken_mws_transport_config) set_bit(HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG, &hdev->quirks); if (bcm4377->hw->broken_ext_scan) set_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &hdev->quirks); + if (bcm4377->hw->broken_le_coded) + set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks); pci_set_drvdata(pdev, bcm4377); hci_set_drvdata(hdev, bcm4377); @@ -2461,6 +2462,7 @@ static const struct bcm4377_hw bcm4377_hw_variants[] = { .bar0_core2_window2 = 0x18107000, .has_bar0_core2_window2 = true, .broken_mws_transport_config = true, + .broken_le_coded = true, .send_calibration = bcm4378_send_calibration, .send_ptb = bcm4378_send_ptb, }, @@ -2474,6 +2476,7 @@ static const struct bcm4377_hw bcm4377_hw_variants[] = { .has_bar0_core2_window2 = true, .clear_pciecfg_subsystem_ctrl_bit19 = true, .broken_mws_transport_config = true, + .broken_le_coded = true, .send_calibration = bcm4387_send_calibration, .send_ptb = bcm4378_send_ptb, }, diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index 71e748a9477e44..c0436881a533c5 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -113,6 +113,7 @@ struct h5_vnd { int (*suspend)(struct h5 *h5); int (*resume)(struct h5 *h5); const struct acpi_gpio_mapping *acpi_gpio_map; + int sizeof_priv; }; struct h5_device_data { @@ -863,7 +864,8 @@ static int h5_serdev_probe(struct serdev_device *serdev) if (IS_ERR(h5->device_wake_gpio)) return PTR_ERR(h5->device_wake_gpio); - return hci_uart_register_device(&h5->serdev_hu, &h5p); + return hci_uart_register_device_priv(&h5->serdev_hu, &h5p, + h5->vnd->sizeof_priv); } static void h5_serdev_remove(struct serdev_device *serdev) @@ -1070,6 +1072,7 @@ static struct h5_vnd rtl_vnd = { .suspend = h5_btrtl_suspend, .resume = h5_btrtl_resume, .acpi_gpio_map = acpi_btrtl_gpios, + .sizeof_priv = sizeof(struct btrealtek_data), }; static const struct h5_device_data h5_data_rtl8822cs = { diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index a26367e9fb197c..17a2f158a0dfab 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -667,11 +667,6 @@ static int hci_uart_register_dev(struct hci_uart *hu) if (!test_bit(HCI_UART_RESET_ON_INIT, &hu->hdev_flags)) set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); - if (test_bit(HCI_UART_CREATE_AMP, &hu->hdev_flags)) - hdev->dev_type = HCI_AMP; - else - hdev->dev_type = HCI_PRIMARY; - /* Only call open() for the protocol after hdev is fully initialized as * open() (or a timer/workqueue it starts) may attempt to reference it. */ @@ -722,7 +717,6 @@ static int hci_uart_set_flags(struct hci_uart *hu, unsigned long flags) { unsigned long valid_flags = BIT(HCI_UART_RAW_DEVICE) | BIT(HCI_UART_RESET_ON_INIT) | - BIT(HCI_UART_CREATE_AMP) | BIT(HCI_UART_INIT_PENDING) | BIT(HCI_UART_EXT_CONFIG) | BIT(HCI_UART_VND_DETECT); diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 4b57e15f9c7a7a..7a552387129ef0 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -225,6 +225,7 @@ struct qca_serdev { struct qca_power *bt_power; u32 init_speed; u32 oper_speed; + bool bdaddr_property_broken; const char *firmware_name; }; @@ -1089,6 +1090,7 @@ static void qca_controller_memdump(struct work_struct *work) qca->memdump_state = QCA_MEMDUMP_COLLECTED; cancel_delayed_work(&qca->ctrl_memdump_timeout); clear_bit(QCA_MEMDUMP_COLLECTION, &qca->flags); + clear_bit(QCA_IBS_DISABLED, &qca->flags); mutex_unlock(&qca->hci_memdump_lock); return; } @@ -1671,6 +1673,9 @@ static bool qca_wakeup(struct hci_dev *hdev) struct hci_uart *hu = hci_get_drvdata(hdev); bool wakeup; + if (!hu->serdev) + return true; + /* BT SoC attached through the serial bus is handled by the serdev driver. * So we need to use the device handle of the serdev driver to get the * status of device may wakeup. @@ -1806,13 +1811,12 @@ static int qca_power_on(struct hci_dev *hdev) static void hci_coredump_qca(struct hci_dev *hdev) { + int err; static const u8 param[] = { 0x26 }; - struct sk_buff *skb; - skb = __hci_cmd_sync(hdev, 0xfc0c, 1, param, HCI_CMD_TIMEOUT); - if (IS_ERR(skb)) - bt_dev_err(hdev, "%s: trigger crash failed (%ld)", __func__, PTR_ERR(skb)); - kfree_skb(skb); + err = __hci_cmd_send(hdev, 0xfc0c, 1, param); + if (err < 0) + bt_dev_err(hdev, "%s: trigger crash failed (%d)", __func__, err); } static int qca_setup(struct hci_uart *hu) @@ -1825,6 +1829,7 @@ static int qca_setup(struct hci_uart *hu) const char *firmware_name = qca_get_firmware_name(hu); int ret; struct qca_btsoc_version ver; + struct qca_serdev *qcadev; const char *soc_name; ret = qca_check_speeds(hu); @@ -1841,6 +1846,10 @@ static int qca_setup(struct hci_uart *hu) set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); switch (soc_type) { + case QCA_QCA2066: + soc_name = "qca2066"; + break; + case QCA_WCN3988: case QCA_WCN3990: case QCA_WCN3991: @@ -1882,7 +1891,10 @@ static int qca_setup(struct hci_uart *hu) case QCA_WCN6750: case QCA_WCN6855: case QCA_WCN7850: - set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); + qcadev = serdev_device_get_drvdata(hu->serdev); + if (qcadev->bdaddr_property_broken) + set_bit(HCI_QUIRK_BDADDR_PROPERTY_BROKEN, &hdev->quirks); + hci_set_aosp_capable(hdev); ret = qca_read_soc_version(hdev, &ver, soc_type); @@ -1929,8 +1941,10 @@ static int qca_setup(struct hci_uart *hu) qca_debugfs_init(hdev); hu->hdev->hw_error = qca_hw_error; hu->hdev->cmd_timeout = qca_cmd_timeout; - if (device_can_wakeup(hu->serdev->ctrl->dev.parent)) - hu->hdev->wakeup = qca_wakeup; + if (hu->serdev) { + if (device_can_wakeup(hu->serdev->ctrl->dev.parent)) + hu->hdev->wakeup = qca_wakeup; + } } else if (ret == -ENOENT) { /* No patch/nvm-config found, run with original fw/config */ set_bit(QCA_ROM_FW, &qca->flags); @@ -2032,9 +2046,15 @@ static const struct qca_device_data qca_soc_data_wcn3998 __maybe_unused = { .num_vregs = 4, }; +static const struct qca_device_data qca_soc_data_qca2066 __maybe_unused = { + .soc_type = QCA_QCA2066, + .num_vregs = 0, +}; + static const struct qca_device_data qca_soc_data_qca6390 __maybe_unused = { .soc_type = QCA_QCA6390, .num_vregs = 0, + .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, }; static const struct qca_device_data qca_soc_data_wcn6750 __maybe_unused = { @@ -2253,6 +2273,9 @@ static int qca_serdev_probe(struct serdev_device *serdev) if (!qcadev->oper_speed) BT_DBG("UART will pick default operating speed"); + qcadev->bdaddr_property_broken = device_property_read_bool(&serdev->dev, + "qcom,local-bd-address-broken"); + if (data) qcadev->btsoc_type = data->soc_type; else @@ -2284,20 +2307,25 @@ static int qca_serdev_probe(struct serdev_device *serdev) qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable", GPIOD_OUT_LOW); - if (IS_ERR_OR_NULL(qcadev->bt_en) && + if (IS_ERR(qcadev->bt_en) && (data->soc_type == QCA_WCN6750 || data->soc_type == QCA_WCN6855)) { dev_err(&serdev->dev, "failed to acquire BT_EN gpio\n"); - power_ctrl_enabled = false; + return PTR_ERR(qcadev->bt_en); } + if (!qcadev->bt_en) + power_ctrl_enabled = false; + qcadev->sw_ctrl = devm_gpiod_get_optional(&serdev->dev, "swctrl", GPIOD_IN); - if (IS_ERR_OR_NULL(qcadev->sw_ctrl) && + if (IS_ERR(qcadev->sw_ctrl) && (data->soc_type == QCA_WCN6750 || data->soc_type == QCA_WCN6855 || - data->soc_type == QCA_WCN7850)) - dev_warn(&serdev->dev, "failed to acquire SW_CTRL gpio\n"); + data->soc_type == QCA_WCN7850)) { + dev_err(&serdev->dev, "failed to acquire SW_CTRL gpio\n"); + return PTR_ERR(qcadev->sw_ctrl); + } qcadev->susclk = devm_clk_get_optional(&serdev->dev, NULL); if (IS_ERR(qcadev->susclk)) { @@ -2315,11 +2343,14 @@ static int qca_serdev_probe(struct serdev_device *serdev) default: qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable", GPIOD_OUT_LOW); - if (IS_ERR_OR_NULL(qcadev->bt_en)) { - dev_warn(&serdev->dev, "failed to acquire enable gpio\n"); - power_ctrl_enabled = false; + if (IS_ERR(qcadev->bt_en)) { + dev_err(&serdev->dev, "failed to acquire enable gpio\n"); + return PTR_ERR(qcadev->bt_en); } + if (!qcadev->bt_en) + power_ctrl_enabled = false; + qcadev->susclk = devm_clk_get_optional(&serdev->dev, NULL); if (IS_ERR(qcadev->susclk)) { dev_warn(&serdev->dev, "failed to acquire clk\n"); @@ -2398,15 +2429,27 @@ static void qca_serdev_shutdown(struct device *dev) struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev); struct hci_uart *hu = &qcadev->serdev_hu; struct hci_dev *hdev = hu->hdev; - struct qca_data *qca = hu->priv; const u8 ibs_wake_cmd[] = { 0xFD }; const u8 edl_reset_soc_cmd[] = { 0x01, 0x00, 0xFC, 0x01, 0x05 }; if (qcadev->btsoc_type == QCA_QCA6390) { - if (test_bit(QCA_BT_OFF, &qca->flags) || - !test_bit(HCI_RUNNING, &hdev->flags)) + /* The purpose of sending the VSC is to reset SOC into a initial + * state and the state will ensure next hdev->setup() success. + * if HCI_QUIRK_NON_PERSISTENT_SETUP is set, it means that + * hdev->setup() can do its job regardless of SoC state, so + * don't need to send the VSC. + * if HCI_SETUP is set, it means that hdev->setup() was never + * invoked and the SOC is already in the initial state, so + * don't also need to send the VSC. + */ + if (test_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks) || + hci_dev_test_flag(hdev, HCI_SETUP)) return; + /* The serdev must be in open state when conrol logic arrives + * here, so also fix the use-after-free issue caused by that + * the serdev is flushed or wrote after it is closed. + */ serdev_device_write_flush(serdev); ret = serdev_device_write_buf(serdev, ibs_wake_cmd, sizeof(ibs_wake_cmd)); @@ -2559,6 +2602,7 @@ static SIMPLE_DEV_PM_OPS(qca_pm_ops, qca_suspend, qca_resume); #ifdef CONFIG_OF static const struct of_device_id qca_bluetooth_of_match[] = { + { .compatible = "qcom,qca2066-bt", .data = &qca_soc_data_qca2066}, { .compatible = "qcom,qca6174-bt" }, { .compatible = "qcom,qca6390-bt", .data = &qca_soc_data_qca6390}, { .compatible = "qcom,qca9377-bt" }, @@ -2576,6 +2620,7 @@ MODULE_DEVICE_TABLE(of, qca_bluetooth_of_match); #ifdef CONFIG_ACPI static const struct acpi_device_id qca_bluetooth_acpi_match[] = { + { "QCOM2066", (kernel_ulong_t)&qca_soc_data_qca2066 }, { "QCOM6390", (kernel_ulong_t)&qca_soc_data_qca6390 }, { "DLA16390", (kernel_ulong_t)&qca_soc_data_qca6390 }, { "DLB16390", (kernel_ulong_t)&qca_soc_data_qca6390 }, diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c index f16fd79bc02b8a..1165831570e3c4 100644 --- a/drivers/bluetooth/hci_serdev.c +++ b/drivers/bluetooth/hci_serdev.c @@ -300,8 +300,9 @@ static const struct serdev_device_ops hci_serdev_client_ops = { .write_wakeup = hci_uart_write_wakeup, }; -int hci_uart_register_device(struct hci_uart *hu, - const struct hci_uart_proto *p) +int hci_uart_register_device_priv(struct hci_uart *hu, + const struct hci_uart_proto *p, + int sizeof_priv) { int err; struct hci_dev *hdev; @@ -325,7 +326,7 @@ int hci_uart_register_device(struct hci_uart *hu, set_bit(HCI_UART_PROTO_READY, &hu->flags); /* Initialize and register HCI device */ - hdev = hci_alloc_dev(); + hdev = hci_alloc_dev_priv(sizeof_priv); if (!hdev) { BT_ERR("Can't allocate HCI device"); err = -ENOMEM; @@ -365,11 +366,6 @@ int hci_uart_register_device(struct hci_uart *hu, if (test_bit(HCI_UART_EXT_CONFIG, &hu->hdev_flags)) set_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks); - if (test_bit(HCI_UART_CREATE_AMP, &hu->hdev_flags)) - hdev->dev_type = HCI_AMP; - else - hdev->dev_type = HCI_PRIMARY; - if (test_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags)) return 0; @@ -394,7 +390,7 @@ int hci_uart_register_device(struct hci_uart *hu, percpu_free_rwsem(&hu->proto_lock); return err; } -EXPORT_SYMBOL_GPL(hci_uart_register_device); +EXPORT_SYMBOL_GPL(hci_uart_register_device_priv); void hci_uart_unregister_device(struct hci_uart *hu) { diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h index fb4a2d0d8cc802..00bf7ae82c5b72 100644 --- a/drivers/bluetooth/hci_uart.h +++ b/drivers/bluetooth/hci_uart.h @@ -37,7 +37,6 @@ #define HCI_UART_RAW_DEVICE 0 #define HCI_UART_RESET_ON_INIT 1 -#define HCI_UART_CREATE_AMP 2 #define HCI_UART_INIT_PENDING 3 #define HCI_UART_EXT_CONFIG 4 #define HCI_UART_VND_DETECT 5 @@ -97,7 +96,17 @@ struct hci_uart { int hci_uart_register_proto(const struct hci_uart_proto *p); int hci_uart_unregister_proto(const struct hci_uart_proto *p); -int hci_uart_register_device(struct hci_uart *hu, const struct hci_uart_proto *p); + +int hci_uart_register_device_priv(struct hci_uart *hu, + const struct hci_uart_proto *p, + int sizeof_priv); + +static inline int hci_uart_register_device(struct hci_uart *hu, + const struct hci_uart_proto *p) +{ + return hci_uart_register_device_priv(hu, p, 0); +} + void hci_uart_unregister_device(struct hci_uart *hu); int hci_uart_tx_wakeup(struct hci_uart *hu); diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index f3892e9ce800ff..28750a40f0ed52 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -44,6 +45,7 @@ struct vhci_data { bool wakeup; __u16 msft_opcode; bool aosp_capable; + atomic_t initialized; }; static int vhci_open_dev(struct hci_dev *hdev) @@ -75,11 +77,10 @@ static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1); - mutex_lock(&data->open_mutex); skb_queue_tail(&data->readq, skb); - mutex_unlock(&data->open_mutex); - wake_up_interruptible(&data->read_wait); + if (atomic_read(&data->initialized)) + wake_up_interruptible(&data->read_wait); return 0; } @@ -383,17 +384,10 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) { struct hci_dev *hdev; struct sk_buff *skb; - __u8 dev_type; if (data->hdev) return -EBADFD; - /* bits 0-1 are dev_type (Primary or AMP) */ - dev_type = opcode & 0x03; - - if (dev_type != HCI_PRIMARY && dev_type != HCI_AMP) - return -EINVAL; - /* bits 2-5 are reserved (must be zero) */ if (opcode & 0x3c) return -EINVAL; @@ -411,7 +405,6 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) data->hdev = hdev; hdev->bus = HCI_VIRTUAL; - hdev->dev_type = dev_type; hci_set_drvdata(hdev, data); hdev->open = vhci_open_dev; @@ -464,7 +457,8 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) skb_put_u8(skb, 0xff); skb_put_u8(skb, opcode); put_unaligned_le16(hdev->id, skb_put(skb, 2)); - skb_queue_tail(&data->readq, skb); + skb_queue_head(&data->readq, skb); + atomic_inc(&data->initialized); wake_up_interruptible(&data->read_wait); return 0; @@ -632,7 +626,7 @@ static void vhci_open_timeout(struct work_struct *work) struct vhci_data *data = container_of(work, struct vhci_data, open_timeout.work); - vhci_create_device(data, amp ? HCI_AMP : HCI_PRIMARY); + vhci_create_device(data, 0x00); } static int vhci_open(struct inode *inode, struct file *file) diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c index 2ac70b560c46db..18208e152a3675 100644 --- a/drivers/bluetooth/virtio_bt.c +++ b/drivers/bluetooth/virtio_bt.c @@ -274,7 +274,6 @@ static int virtbt_probe(struct virtio_device *vdev) switch (type) { case VIRTIO_BT_CONFIG_TYPE_PRIMARY: - case VIRTIO_BT_CONFIG_TYPE_AMP: break; default: return -EINVAL; @@ -303,7 +302,6 @@ static int virtbt_probe(struct virtio_device *vdev) vbt->hdev = hdev; hdev->bus = HCI_VIRTIO; - hdev->dev_type = type; hci_set_drvdata(hdev, vbt); hdev->open = virtbt_open; diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig index c98dd6ca26297f..fab27506d945e9 100644 --- a/drivers/bus/Kconfig +++ b/drivers/bus/Kconfig @@ -186,11 +186,12 @@ config SUNXI_RSB config TEGRA_ACONNECT tristate "Tegra ACONNECT Bus Driver" - depends on ARCH_TEGRA_210_SOC + depends on ARCH_TEGRA depends on OF && PM help Driver for the Tegra ACONNECT bus which is used to interface with - the devices inside the Audio Processing Engine (APE) for Tegra210. + the devices inside the Audio Processing Engine (APE) for + Tegra210 and later. config TEGRA_GMI tristate "Tegra Generic Memory Interface bus driver" diff --git a/drivers/bus/arm-integrator-lm.c b/drivers/bus/arm-integrator-lm.c index b715c8ab36e8bd..a65c79b08804f4 100644 --- a/drivers/bus/arm-integrator-lm.c +++ b/drivers/bus/arm-integrator-lm.c @@ -85,6 +85,7 @@ static int integrator_ap_lm_probe(struct platform_device *pdev) return -ENODEV; } map = syscon_node_to_regmap(syscon); + of_node_put(syscon); if (IS_ERR(map)) { dev_err(dev, "could not find Integrator/AP system controller\n"); diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c index 42c9386a7b423f..f9fd1582f150de 100644 --- a/drivers/bus/imx-weim.c +++ b/drivers/bus/imx-weim.c @@ -117,7 +117,7 @@ static int imx_weim_gpr_setup(struct platform_device *pdev) i++; } - if (i == 0 || i % 4) + if (i == 0) goto err; for (i = 0; i < ARRAY_SIZE(gprvals); i++) { diff --git a/drivers/bus/mhi/ep/internal.h b/drivers/bus/mhi/ep/internal.h index a2125fa5fe2f97..accbf3a51d0cf5 100644 --- a/drivers/bus/mhi/ep/internal.h +++ b/drivers/bus/mhi/ep/internal.h @@ -159,6 +159,7 @@ struct mhi_ep_chan { void (*xfer_cb)(struct mhi_ep_device *mhi_dev, struct mhi_result *result); enum mhi_ch_state state; enum dma_data_direction dir; + size_t rd_offset; u64 tre_loc; u32 tre_size; u32 tre_bytes_left; diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c index 600881808982aa..c48f4d9f2c690b 100644 --- a/drivers/bus/mhi/ep/main.c +++ b/drivers/bus/mhi/ep/main.c @@ -71,45 +71,77 @@ static int mhi_ep_send_event(struct mhi_ep_cntrl *mhi_cntrl, u32 ring_idx, static int mhi_ep_send_completion_event(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring, struct mhi_ring_element *tre, u32 len, enum mhi_ev_ccs code) { - struct mhi_ring_element event = {}; + struct mhi_ring_element *event; + int ret; + + event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL); + if (!event) + return -ENOMEM; + + event->ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(*tre)); + event->dword[0] = MHI_TRE_EV_DWORD0(code, len); + event->dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT); - event.ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(*tre)); - event.dword[0] = MHI_TRE_EV_DWORD0(code, len); - event.dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT); + ret = mhi_ep_send_event(mhi_cntrl, ring->er_index, event, MHI_TRE_DATA_GET_BEI(tre)); + kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event); - return mhi_ep_send_event(mhi_cntrl, ring->er_index, &event, MHI_TRE_DATA_GET_BEI(tre)); + return ret; } int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state state) { - struct mhi_ring_element event = {}; + struct mhi_ring_element *event; + int ret; + + event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL); + if (!event) + return -ENOMEM; - event.dword[0] = MHI_SC_EV_DWORD0(state); - event.dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT); + event->dword[0] = MHI_SC_EV_DWORD0(state); + event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT); - return mhi_ep_send_event(mhi_cntrl, 0, &event, 0); + ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0); + kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event); + + return ret; } int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_env) { - struct mhi_ring_element event = {}; + struct mhi_ring_element *event; + int ret; + + event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL); + if (!event) + return -ENOMEM; + + event->dword[0] = MHI_EE_EV_DWORD0(exec_env); + event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT); - event.dword[0] = MHI_EE_EV_DWORD0(exec_env); - event.dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT); + ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0); + kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event); - return mhi_ep_send_event(mhi_cntrl, 0, &event, 0); + return ret; } static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ev_ccs code) { struct mhi_ep_ring *ring = &mhi_cntrl->mhi_cmd->ring; - struct mhi_ring_element event = {}; + struct mhi_ring_element *event; + int ret; - event.ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(struct mhi_ring_element)); - event.dword[0] = MHI_CC_EV_DWORD0(code); - event.dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT); + event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL); + if (!event) + return -ENOMEM; + + event->ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(struct mhi_ring_element)); + event->dword[0] = MHI_CC_EV_DWORD0(code); + event->dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT); - return mhi_ep_send_event(mhi_cntrl, 0, &event, 0); + ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0); + kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event); + + return ret; } static int mhi_ep_process_cmd_ring(struct mhi_ep_ring *ring, struct mhi_ring_element *el) @@ -151,6 +183,8 @@ static int mhi_ep_process_cmd_ring(struct mhi_ep_ring *ring, struct mhi_ring_ele goto err_unlock; } + + mhi_chan->rd_offset = ch_ring->rd_offset; } /* Set channel state to RUNNING */ @@ -280,22 +314,85 @@ bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_directio struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl; struct mhi_ep_ring *ring = &mhi_cntrl->mhi_chan[mhi_chan->chan].ring; - return !!(ring->rd_offset == ring->wr_offset); + return !!(mhi_chan->rd_offset == ring->wr_offset); } EXPORT_SYMBOL_GPL(mhi_ep_queue_is_empty); +static void mhi_ep_read_completion(struct mhi_ep_buf_info *buf_info) +{ + struct mhi_ep_device *mhi_dev = buf_info->mhi_dev; + struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl; + struct mhi_ep_chan *mhi_chan = mhi_dev->ul_chan; + struct mhi_ep_ring *ring = &mhi_cntrl->mhi_chan[mhi_chan->chan].ring; + struct mhi_ring_element *el = &ring->ring_cache[ring->rd_offset]; + struct mhi_result result = {}; + int ret; + + if (mhi_chan->xfer_cb) { + result.buf_addr = buf_info->cb_buf; + result.dir = mhi_chan->dir; + result.bytes_xferd = buf_info->size; + + mhi_chan->xfer_cb(mhi_dev, &result); + } + + /* + * The host will split the data packet into multiple TREs if it can't fit + * the packet in a single TRE. In that case, CHAIN flag will be set by the + * host for all TREs except the last one. + */ + if (buf_info->code != MHI_EV_CC_OVERFLOW) { + if (MHI_TRE_DATA_GET_CHAIN(el)) { + /* + * IEOB (Interrupt on End of Block) flag will be set by the host if + * it expects the completion event for all TREs of a TD. + */ + if (MHI_TRE_DATA_GET_IEOB(el)) { + ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el, + MHI_TRE_DATA_GET_LEN(el), + MHI_EV_CC_EOB); + if (ret < 0) { + dev_err(&mhi_chan->mhi_dev->dev, + "Error sending transfer compl. event\n"); + goto err_free_tre_buf; + } + } + } else { + /* + * IEOT (Interrupt on End of Transfer) flag will be set by the host + * for the last TRE of the TD and expects the completion event for + * the same. + */ + if (MHI_TRE_DATA_GET_IEOT(el)) { + ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el, + MHI_TRE_DATA_GET_LEN(el), + MHI_EV_CC_EOT); + if (ret < 0) { + dev_err(&mhi_chan->mhi_dev->dev, + "Error sending transfer compl. event\n"); + goto err_free_tre_buf; + } + } + } + } + + mhi_ep_ring_inc_index(ring); + +err_free_tre_buf: + kmem_cache_free(mhi_cntrl->tre_buf_cache, buf_info->cb_buf); +} + static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl, - struct mhi_ep_ring *ring, - struct mhi_result *result, - u32 len) + struct mhi_ep_ring *ring) { struct mhi_ep_chan *mhi_chan = &mhi_cntrl->mhi_chan[ring->ch_id]; struct device *dev = &mhi_cntrl->mhi_dev->dev; size_t tr_len, read_offset, write_offset; + struct mhi_ep_buf_info buf_info = {}; + u32 len = MHI_EP_DEFAULT_MTU; struct mhi_ring_element *el; bool tr_done = false; - void *write_addr; - u64 read_addr; + void *buf_addr; u32 buf_left; int ret; @@ -308,7 +405,7 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl, return -ENODEV; } - el = &ring->ring_cache[ring->rd_offset]; + el = &ring->ring_cache[mhi_chan->rd_offset]; /* Check if there is data pending to be read from previous read operation */ if (mhi_chan->tre_bytes_left) { @@ -324,81 +421,51 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl, read_offset = mhi_chan->tre_size - mhi_chan->tre_bytes_left; write_offset = len - buf_left; - read_addr = mhi_chan->tre_loc + read_offset; - write_addr = result->buf_addr + write_offset; + + buf_addr = kmem_cache_zalloc(mhi_cntrl->tre_buf_cache, GFP_KERNEL); + if (!buf_addr) + return -ENOMEM; + + buf_info.host_addr = mhi_chan->tre_loc + read_offset; + buf_info.dev_addr = buf_addr + write_offset; + buf_info.size = tr_len; + buf_info.cb = mhi_ep_read_completion; + buf_info.cb_buf = buf_addr; + buf_info.mhi_dev = mhi_chan->mhi_dev; + + if (mhi_chan->tre_bytes_left - tr_len) + buf_info.code = MHI_EV_CC_OVERFLOW; dev_dbg(dev, "Reading %zd bytes from channel (%u)\n", tr_len, ring->ch_id); - ret = mhi_cntrl->read_from_host(mhi_cntrl, read_addr, write_addr, tr_len); + ret = mhi_cntrl->read_async(mhi_cntrl, &buf_info); if (ret < 0) { dev_err(&mhi_chan->mhi_dev->dev, "Error reading from channel\n"); - return ret; + goto err_free_buf_addr; } buf_left -= tr_len; mhi_chan->tre_bytes_left -= tr_len; - /* - * Once the TRE (Transfer Ring Element) of a TD (Transfer Descriptor) has been - * read completely: - * - * 1. Send completion event to the host based on the flags set in TRE. - * 2. Increment the local read offset of the transfer ring. - */ if (!mhi_chan->tre_bytes_left) { - /* - * The host will split the data packet into multiple TREs if it can't fit - * the packet in a single TRE. In that case, CHAIN flag will be set by the - * host for all TREs except the last one. - */ - if (MHI_TRE_DATA_GET_CHAIN(el)) { - /* - * IEOB (Interrupt on End of Block) flag will be set by the host if - * it expects the completion event for all TREs of a TD. - */ - if (MHI_TRE_DATA_GET_IEOB(el)) { - ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el, - MHI_TRE_DATA_GET_LEN(el), - MHI_EV_CC_EOB); - if (ret < 0) { - dev_err(&mhi_chan->mhi_dev->dev, - "Error sending transfer compl. event\n"); - return ret; - } - } - } else { - /* - * IEOT (Interrupt on End of Transfer) flag will be set by the host - * for the last TRE of the TD and expects the completion event for - * the same. - */ - if (MHI_TRE_DATA_GET_IEOT(el)) { - ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el, - MHI_TRE_DATA_GET_LEN(el), - MHI_EV_CC_EOT); - if (ret < 0) { - dev_err(&mhi_chan->mhi_dev->dev, - "Error sending transfer compl. event\n"); - return ret; - } - } - + if (MHI_TRE_DATA_GET_IEOT(el)) tr_done = true; - } - mhi_ep_ring_inc_index(ring); + mhi_chan->rd_offset = (mhi_chan->rd_offset + 1) % ring->ring_size; } - - result->bytes_xferd += tr_len; } while (buf_left && !tr_done); return 0; + +err_free_buf_addr: + kmem_cache_free(mhi_cntrl->tre_buf_cache, buf_addr); + + return ret; } -static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_element *el) +static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring) { struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl; struct mhi_result result = {}; - u32 len = MHI_EP_DEFAULT_MTU; struct mhi_ep_chan *mhi_chan; int ret; @@ -419,44 +486,59 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result); } else { /* UL channel */ - result.buf_addr = kzalloc(len, GFP_KERNEL); - if (!result.buf_addr) - return -ENOMEM; - do { - ret = mhi_ep_read_channel(mhi_cntrl, ring, &result, len); + ret = mhi_ep_read_channel(mhi_cntrl, ring); if (ret < 0) { dev_err(&mhi_chan->mhi_dev->dev, "Failed to read channel\n"); - kfree(result.buf_addr); return ret; } - result.dir = mhi_chan->dir; - mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result); - result.bytes_xferd = 0; - memset(result.buf_addr, 0, len); - /* Read until the ring becomes empty */ } while (!mhi_ep_queue_is_empty(mhi_chan->mhi_dev, DMA_TO_DEVICE)); - - kfree(result.buf_addr); } return 0; } +static void mhi_ep_skb_completion(struct mhi_ep_buf_info *buf_info) +{ + struct mhi_ep_device *mhi_dev = buf_info->mhi_dev; + struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl; + struct mhi_ep_chan *mhi_chan = mhi_dev->dl_chan; + struct mhi_ep_ring *ring = &mhi_cntrl->mhi_chan[mhi_chan->chan].ring; + struct mhi_ring_element *el = &ring->ring_cache[ring->rd_offset]; + struct device *dev = &mhi_dev->dev; + struct mhi_result result = {}; + int ret; + + if (mhi_chan->xfer_cb) { + result.buf_addr = buf_info->cb_buf; + result.dir = mhi_chan->dir; + result.bytes_xferd = buf_info->size; + + mhi_chan->xfer_cb(mhi_dev, &result); + } + + ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el, buf_info->size, + buf_info->code); + if (ret) { + dev_err(dev, "Error sending transfer completion event\n"); + return; + } + + mhi_ep_ring_inc_index(ring); +} + /* TODO: Handle partially formed TDs */ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb) { struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl; struct mhi_ep_chan *mhi_chan = mhi_dev->dl_chan; struct device *dev = &mhi_chan->mhi_dev->dev; + struct mhi_ep_buf_info buf_info = {}; struct mhi_ring_element *el; u32 buf_left, read_offset; struct mhi_ep_ring *ring; - enum mhi_ev_ccs code; - void *read_addr; - u64 write_addr; size_t tr_len; u32 tre_len; int ret; @@ -480,40 +562,44 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb) goto err_exit; } - el = &ring->ring_cache[ring->rd_offset]; + el = &ring->ring_cache[mhi_chan->rd_offset]; tre_len = MHI_TRE_DATA_GET_LEN(el); tr_len = min(buf_left, tre_len); read_offset = skb->len - buf_left; - read_addr = skb->data + read_offset; - write_addr = MHI_TRE_DATA_GET_PTR(el); - dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id); - ret = mhi_cntrl->write_to_host(mhi_cntrl, read_addr, write_addr, tr_len); - if (ret < 0) { - dev_err(dev, "Error writing to the channel\n"); - goto err_exit; - } + buf_info.dev_addr = skb->data + read_offset; + buf_info.host_addr = MHI_TRE_DATA_GET_PTR(el); + buf_info.size = tr_len; + buf_info.cb = mhi_ep_skb_completion; + buf_info.cb_buf = skb; + buf_info.mhi_dev = mhi_dev; - buf_left -= tr_len; /* * For all TREs queued by the host for DL channel, only the EOT flag will be set. * If the packet doesn't fit into a single TRE, send the OVERFLOW event to * the host so that the host can adjust the packet boundary to next TREs. Else send * the EOT event to the host indicating the packet boundary. */ - if (buf_left) - code = MHI_EV_CC_OVERFLOW; + if (buf_left - tr_len) + buf_info.code = MHI_EV_CC_OVERFLOW; else - code = MHI_EV_CC_EOT; + buf_info.code = MHI_EV_CC_EOT; - ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el, tr_len, code); - if (ret) { - dev_err(dev, "Error sending transfer completion event\n"); + dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id); + ret = mhi_cntrl->write_async(mhi_cntrl, &buf_info); + if (ret < 0) { + dev_err(dev, "Error writing to the channel\n"); goto err_exit; } - mhi_ep_ring_inc_index(ring); + buf_left -= tr_len; + + /* + * Update the read offset cached in mhi_chan. Actual read offset + * will be updated by the completion handler. + */ + mhi_chan->rd_offset = (mhi_chan->rd_offset + 1) % ring->ring_size; } while (buf_left); mutex_unlock(&mhi_chan->lock); @@ -714,7 +800,6 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work) struct mhi_ep_cntrl *mhi_cntrl = container_of(work, struct mhi_ep_cntrl, ch_ring_work); struct device *dev = &mhi_cntrl->mhi_dev->dev; struct mhi_ep_ring_item *itr, *tmp; - struct mhi_ring_element *el; struct mhi_ep_ring *ring; struct mhi_ep_chan *chan; unsigned long flags; @@ -748,31 +833,29 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work) if (ret) { dev_err(dev, "Error updating write offset for ring\n"); mutex_unlock(&chan->lock); - kfree(itr); + kmem_cache_free(mhi_cntrl->ring_item_cache, itr); continue; } /* Sanity check to make sure there are elements in the ring */ - if (ring->rd_offset == ring->wr_offset) { + if (chan->rd_offset == ring->wr_offset) { mutex_unlock(&chan->lock); - kfree(itr); + kmem_cache_free(mhi_cntrl->ring_item_cache, itr); continue; } - el = &ring->ring_cache[ring->rd_offset]; - dev_dbg(dev, "Processing the ring for channel (%u)\n", ring->ch_id); - ret = mhi_ep_process_ch_ring(ring, el); + ret = mhi_ep_process_ch_ring(ring); if (ret) { dev_err(dev, "Error processing ring for channel (%u): %d\n", ring->ch_id, ret); mutex_unlock(&chan->lock); - kfree(itr); + kmem_cache_free(mhi_cntrl->ring_item_cache, itr); continue; } mutex_unlock(&chan->lock); - kfree(itr); + kmem_cache_free(mhi_cntrl->ring_item_cache, itr); } } @@ -828,7 +911,7 @@ static void mhi_ep_queue_channel_db(struct mhi_ep_cntrl *mhi_cntrl, unsigned lon u32 ch_id = ch_idx + i; ring = &mhi_cntrl->mhi_chan[ch_id].ring; - item = kzalloc(sizeof(*item), GFP_ATOMIC); + item = kmem_cache_zalloc(mhi_cntrl->ring_item_cache, GFP_ATOMIC); if (!item) return; @@ -1375,6 +1458,29 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl, goto err_free_ch; } + mhi_cntrl->ev_ring_el_cache = kmem_cache_create("mhi_ep_event_ring_el", + sizeof(struct mhi_ring_element), 0, + 0, NULL); + if (!mhi_cntrl->ev_ring_el_cache) { + ret = -ENOMEM; + goto err_free_cmd; + } + + mhi_cntrl->tre_buf_cache = kmem_cache_create("mhi_ep_tre_buf", MHI_EP_DEFAULT_MTU, 0, + 0, NULL); + if (!mhi_cntrl->tre_buf_cache) { + ret = -ENOMEM; + goto err_destroy_ev_ring_el_cache; + } + + mhi_cntrl->ring_item_cache = kmem_cache_create("mhi_ep_ring_item", + sizeof(struct mhi_ep_ring_item), 0, + 0, NULL); + if (!mhi_cntrl->ring_item_cache) { + ret = -ENOMEM; + goto err_destroy_tre_buf_cache; + } + INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker); INIT_WORK(&mhi_cntrl->reset_work, mhi_ep_reset_worker); INIT_WORK(&mhi_cntrl->cmd_ring_work, mhi_ep_cmd_ring_worker); @@ -1383,7 +1489,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl, mhi_cntrl->wq = alloc_workqueue("mhi_ep_wq", 0, 0); if (!mhi_cntrl->wq) { ret = -ENOMEM; - goto err_free_cmd; + goto err_destroy_ring_item_cache; } INIT_LIST_HEAD(&mhi_cntrl->st_transition_list); @@ -1442,6 +1548,12 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl, ida_free(&mhi_ep_cntrl_ida, mhi_cntrl->index); err_destroy_wq: destroy_workqueue(mhi_cntrl->wq); +err_destroy_ring_item_cache: + kmem_cache_destroy(mhi_cntrl->ring_item_cache); +err_destroy_ev_ring_el_cache: + kmem_cache_destroy(mhi_cntrl->ev_ring_el_cache); +err_destroy_tre_buf_cache: + kmem_cache_destroy(mhi_cntrl->tre_buf_cache); err_free_cmd: kfree(mhi_cntrl->mhi_cmd); err_free_ch: @@ -1463,6 +1575,9 @@ void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl) free_irq(mhi_cntrl->irq, mhi_cntrl); + kmem_cache_destroy(mhi_cntrl->tre_buf_cache); + kmem_cache_destroy(mhi_cntrl->ev_ring_el_cache); + kmem_cache_destroy(mhi_cntrl->ring_item_cache); kfree(mhi_cntrl->mhi_cmd); kfree(mhi_cntrl->mhi_chan); diff --git a/drivers/bus/mhi/ep/ring.c b/drivers/bus/mhi/ep/ring.c index 115518ec76a43a..ba9f696d1aa80e 100644 --- a/drivers/bus/mhi/ep/ring.c +++ b/drivers/bus/mhi/ep/ring.c @@ -30,7 +30,8 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end) { struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl; struct device *dev = &mhi_cntrl->mhi_dev->dev; - size_t start, copy_size; + struct mhi_ep_buf_info buf_info = {}; + size_t start; int ret; /* Don't proceed in the case of event ring. This happens during mhi_ep_ring_start(). */ @@ -43,30 +44,34 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end) start = ring->wr_offset; if (start < end) { - copy_size = (end - start) * sizeof(struct mhi_ring_element); - ret = mhi_cntrl->read_from_host(mhi_cntrl, ring->rbase + - (start * sizeof(struct mhi_ring_element)), - &ring->ring_cache[start], copy_size); + buf_info.size = (end - start) * sizeof(struct mhi_ring_element); + buf_info.host_addr = ring->rbase + (start * sizeof(struct mhi_ring_element)); + buf_info.dev_addr = &ring->ring_cache[start]; + + ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info); if (ret < 0) return ret; } else { - copy_size = (ring->ring_size - start) * sizeof(struct mhi_ring_element); - ret = mhi_cntrl->read_from_host(mhi_cntrl, ring->rbase + - (start * sizeof(struct mhi_ring_element)), - &ring->ring_cache[start], copy_size); + buf_info.size = (ring->ring_size - start) * sizeof(struct mhi_ring_element); + buf_info.host_addr = ring->rbase + (start * sizeof(struct mhi_ring_element)); + buf_info.dev_addr = &ring->ring_cache[start]; + + ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info); if (ret < 0) return ret; if (end) { - ret = mhi_cntrl->read_from_host(mhi_cntrl, ring->rbase, - &ring->ring_cache[0], - end * sizeof(struct mhi_ring_element)); + buf_info.host_addr = ring->rbase; + buf_info.dev_addr = &ring->ring_cache[0]; + buf_info.size = end * sizeof(struct mhi_ring_element); + + ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info); if (ret < 0) return ret; } } - dev_dbg(dev, "Cached ring: start %zu end %zu size %zu\n", start, end, copy_size); + dev_dbg(dev, "Cached ring: start %zu end %zu size %zu\n", start, end, buf_info.size); return 0; } @@ -102,6 +107,7 @@ int mhi_ep_ring_add_element(struct mhi_ep_ring *ring, struct mhi_ring_element *e { struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl; struct device *dev = &mhi_cntrl->mhi_dev->dev; + struct mhi_ep_buf_info buf_info = {}; size_t old_offset = 0; u32 num_free_elem; __le64 rp; @@ -133,12 +139,11 @@ int mhi_ep_ring_add_element(struct mhi_ep_ring *ring, struct mhi_ring_element *e rp = cpu_to_le64(ring->rd_offset * sizeof(*el) + ring->rbase); memcpy_toio((void __iomem *) &ring->ring_ctx->generic.rp, &rp, sizeof(u64)); - ret = mhi_cntrl->write_to_host(mhi_cntrl, el, ring->rbase + (old_offset * sizeof(*el)), - sizeof(*el)); - if (ret < 0) - return ret; + buf_info.host_addr = ring->rbase + (old_offset * sizeof(*el)); + buf_info.dev_addr = el; + buf_info.size = sizeof(*el); - return 0; + return mhi_cntrl->write_sync(mhi_cntrl, &buf_info); } void mhi_ep_ring_init(struct mhi_ep_ring *ring, enum mhi_ep_ring_type type, u32 id) diff --git a/drivers/bus/mhi/host/init.c b/drivers/bus/mhi/host/init.c index f78aefd2d7a362..cfd17c02fe20ef 100644 --- a/drivers/bus/mhi/host/init.c +++ b/drivers/bus/mhi/host/init.c @@ -62,6 +62,7 @@ static const char * const mhi_pm_state_str[] = { [MHI_PM_STATE_FW_DL_ERR] = "Firmware Download Error", [MHI_PM_STATE_SYS_ERR_DETECT] = "SYS ERROR Detect", [MHI_PM_STATE_SYS_ERR_PROCESS] = "SYS ERROR Process", + [MHI_PM_STATE_SYS_ERR_FAIL] = "SYS ERROR Failure", [MHI_PM_STATE_SHUTDOWN_PROCESS] = "SHUTDOWN Process", [MHI_PM_STATE_LD_ERR_FATAL_DETECT] = "Linkdown or Error Fatal Detect", }; diff --git a/drivers/bus/mhi/host/internal.h b/drivers/bus/mhi/host/internal.h index 2e139e76de4c03..d2858236af52b1 100644 --- a/drivers/bus/mhi/host/internal.h +++ b/drivers/bus/mhi/host/internal.h @@ -88,6 +88,7 @@ enum mhi_pm_state { MHI_PM_STATE_FW_DL_ERR, MHI_PM_STATE_SYS_ERR_DETECT, MHI_PM_STATE_SYS_ERR_PROCESS, + MHI_PM_STATE_SYS_ERR_FAIL, MHI_PM_STATE_SHUTDOWN_PROCESS, MHI_PM_STATE_LD_ERR_FATAL_DETECT, MHI_PM_STATE_MAX @@ -104,14 +105,16 @@ enum mhi_pm_state { #define MHI_PM_FW_DL_ERR BIT(7) #define MHI_PM_SYS_ERR_DETECT BIT(8) #define MHI_PM_SYS_ERR_PROCESS BIT(9) -#define MHI_PM_SHUTDOWN_PROCESS BIT(10) +#define MHI_PM_SYS_ERR_FAIL BIT(10) +#define MHI_PM_SHUTDOWN_PROCESS BIT(11) /* link not accessible */ -#define MHI_PM_LD_ERR_FATAL_DETECT BIT(11) +#define MHI_PM_LD_ERR_FATAL_DETECT BIT(12) #define MHI_REG_ACCESS_VALID(pm_state) ((pm_state & (MHI_PM_POR | MHI_PM_M0 | \ MHI_PM_M2 | MHI_PM_M3_ENTER | MHI_PM_M3_EXIT | \ MHI_PM_SYS_ERR_DETECT | MHI_PM_SYS_ERR_PROCESS | \ - MHI_PM_SHUTDOWN_PROCESS | MHI_PM_FW_DL_ERR))) + MHI_PM_SYS_ERR_FAIL | MHI_PM_SHUTDOWN_PROCESS | \ + MHI_PM_FW_DL_ERR))) #define MHI_PM_IN_ERROR_STATE(pm_state) (pm_state >= MHI_PM_FW_DL_ERR) #define MHI_PM_IN_FATAL_STATE(pm_state) (pm_state == MHI_PM_LD_ERR_FATAL_DETECT) #define MHI_DB_ACCESS_VALID(mhi_cntrl) (mhi_cntrl->pm_state & mhi_cntrl->db_access) diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c index dcf627b36e829e..d6653cbcf94a2e 100644 --- a/drivers/bus/mhi/host/main.c +++ b/drivers/bus/mhi/host/main.c @@ -268,7 +268,8 @@ static void mhi_del_ring_element(struct mhi_controller *mhi_cntrl, static bool is_valid_ring_ptr(struct mhi_ring *ring, dma_addr_t addr) { - return addr >= ring->iommu_base && addr < ring->iommu_base + ring->len; + return addr >= ring->iommu_base && addr < ring->iommu_base + ring->len && + !(addr & (sizeof(struct mhi_ring_element) - 1)); } int mhi_destroy_device(struct device *dev, void *data) @@ -642,6 +643,8 @@ static int parse_xfer_event(struct mhi_controller *mhi_cntrl, mhi_del_ring_element(mhi_cntrl, tre_ring); local_rp = tre_ring->rp; + read_unlock_bh(&mhi_chan->lock); + /* notify client */ mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result); @@ -667,6 +670,8 @@ static int parse_xfer_event(struct mhi_controller *mhi_cntrl, kfree(buf_info->cb_buf); } } + + read_lock_bh(&mhi_chan->lock); } break; } /* CC_EOT */ @@ -1122,17 +1127,15 @@ static int mhi_queue(struct mhi_device *mhi_dev, struct mhi_buf_info *buf_info, if (unlikely(MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state))) return -EIO; - read_lock_irqsave(&mhi_cntrl->pm_lock, flags); - ret = mhi_is_ring_full(mhi_cntrl, tre_ring); - if (unlikely(ret)) { - ret = -EAGAIN; - goto exit_unlock; - } + if (unlikely(ret)) + return -EAGAIN; ret = mhi_gen_tre(mhi_cntrl, mhi_chan, buf_info, mflags); if (unlikely(ret)) - goto exit_unlock; + return ret; + + read_lock_irqsave(&mhi_cntrl->pm_lock, flags); /* Packet is queued, take a usage ref to exit M3 if necessary * for host->device buffer, balanced put is done on buffer completion @@ -1152,7 +1155,6 @@ static int mhi_queue(struct mhi_device *mhi_dev, struct mhi_buf_info *buf_info, if (dir == DMA_FROM_DEVICE) mhi_cntrl->runtime_put(mhi_cntrl); -exit_unlock: read_unlock_irqrestore(&mhi_cntrl->pm_lock, flags); return ret; @@ -1204,6 +1206,9 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan, int eot, eob, chain, bei; int ret; + /* Protect accesses for reading and incrementing WP */ + write_lock_bh(&mhi_chan->lock); + buf_ring = &mhi_chan->buf_ring; tre_ring = &mhi_chan->tre_ring; @@ -1221,8 +1226,10 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan, if (!info->pre_mapped) { ret = mhi_cntrl->map_single(mhi_cntrl, buf_info); - if (ret) + if (ret) { + write_unlock_bh(&mhi_chan->lock); return ret; + } } eob = !!(flags & MHI_EOB); @@ -1239,6 +1246,8 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan, mhi_add_ring_element(mhi_cntrl, tre_ring); mhi_add_ring_element(mhi_cntrl, buf_ring); + write_unlock_bh(&mhi_chan->lock); + return 0; } diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c index 08f3f039dbddcf..154841916f5652 100644 --- a/drivers/bus/mhi/host/pci_generic.c +++ b/drivers/bus/mhi/host/pci_generic.c @@ -578,6 +578,15 @@ static const struct mhi_pci_dev_info mhi_telit_fn990_info = { .mru_default = 32768, }; +static const struct mhi_pci_dev_info mhi_telit_fe990a_info = { + .name = "telit-fe990a", + .config = &modem_telit_fn990_config, + .bar_num = MHI_PCI_DEFAULT_BAR_NUM, + .dma_data_width = 32, + .sideband_wake = false, + .mru_default = 32768, +}; + /* Keep the list sorted based on the PID. New VID should be added as the last entry */ static const struct pci_device_id mhi_pci_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0304), @@ -595,9 +604,9 @@ static const struct pci_device_id mhi_pci_id_table[] = { /* Telit FN990 */ { PCI_DEVICE_SUB(PCI_VENDOR_ID_QCOM, 0x0308, 0x1c5d, 0x2010), .driver_data = (kernel_ulong_t) &mhi_telit_fn990_info }, - /* Telit FE990 */ + /* Telit FE990A */ { PCI_DEVICE_SUB(PCI_VENDOR_ID_QCOM, 0x0308, 0x1c5d, 0x2015), - .driver_data = (kernel_ulong_t) &mhi_telit_fn990_info }, + .driver_data = (kernel_ulong_t) &mhi_telit_fe990a_info }, { PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0308), .driver_data = (kernel_ulong_t) &mhi_qcom_sdx65_info }, { PCI_DEVICE(PCI_VENDOR_ID_QUECTEL, 0x1001), /* EM120R-GL (sdx24) */ diff --git a/drivers/bus/mhi/host/pm.c b/drivers/bus/mhi/host/pm.c index 8a4362d75fc437..27f8a40f288cfd 100644 --- a/drivers/bus/mhi/host/pm.c +++ b/drivers/bus/mhi/host/pm.c @@ -36,7 +36,10 @@ * M0 <--> M0 * M0 -> FW_DL_ERR * M0 -> M3_ENTER -> M3 -> M3_EXIT --> M0 - * L1: SYS_ERR_DETECT -> SYS_ERR_PROCESS --> POR + * L1: SYS_ERR_DETECT -> SYS_ERR_PROCESS + * SYS_ERR_PROCESS -> SYS_ERR_FAIL + * SYS_ERR_FAIL -> SYS_ERR_DETECT + * SYS_ERR_PROCESS --> POR * L2: SHUTDOWN_PROCESS -> LD_ERR_FATAL_DETECT * SHUTDOWN_PROCESS -> DISABLE * L3: LD_ERR_FATAL_DETECT <--> LD_ERR_FATAL_DETECT @@ -93,7 +96,12 @@ static const struct mhi_pm_transitions dev_state_transitions[] = { }, { MHI_PM_SYS_ERR_PROCESS, - MHI_PM_POR | MHI_PM_SHUTDOWN_PROCESS | + MHI_PM_POR | MHI_PM_SYS_ERR_FAIL | MHI_PM_SHUTDOWN_PROCESS | + MHI_PM_LD_ERR_FATAL_DETECT + }, + { + MHI_PM_SYS_ERR_FAIL, + MHI_PM_SYS_ERR_DETECT | MHI_PM_SHUTDOWN_PROCESS | MHI_PM_LD_ERR_FATAL_DETECT }, /* L2 States */ @@ -624,7 +632,13 @@ static void mhi_pm_sys_error_transition(struct mhi_controller *mhi_cntrl) !in_reset, timeout); if (!ret || in_reset) { dev_err(dev, "Device failed to exit MHI Reset state\n"); - goto exit_sys_error_transition; + write_lock_irq(&mhi_cntrl->pm_lock); + cur_state = mhi_tryset_pm_state(mhi_cntrl, + MHI_PM_SYS_ERR_FAIL); + write_unlock_irq(&mhi_cntrl->pm_lock); + /* Shutdown may have occurred, otherwise cleanup now */ + if (cur_state != MHI_PM_SYS_ERR_FAIL) + goto exit_sys_error_transition; } /* diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c index 5eb0fe73ddc45b..e384fbc6c1d931 100644 --- a/drivers/bus/moxtet.c +++ b/drivers/bus/moxtet.c @@ -755,7 +755,7 @@ static int moxtet_irq_setup(struct moxtet *moxtet) moxtet->irq.masked = ~0; ret = request_threaded_irq(moxtet->dev_irq, NULL, moxtet_irq_thread_fn, - IRQF_ONESHOT, "moxtet", moxtet); + IRQF_SHARED | IRQF_ONESHOT, "moxtet", moxtet); if (ret < 0) goto err_free; @@ -830,6 +830,12 @@ static void moxtet_remove(struct spi_device *spi) mutex_destroy(&moxtet->lock); } +static const struct spi_device_id moxtet_spi_ids[] = { + { "moxtet" }, + { }, +}; +MODULE_DEVICE_TABLE(spi, moxtet_spi_ids); + static const struct of_device_id moxtet_dt_ids[] = { { .compatible = "cznic,moxtet" }, {}, @@ -841,6 +847,7 @@ static struct spi_driver moxtet_spi_driver = { .name = "moxtet", .of_match_table = moxtet_dt_ids, }, + .id_table = moxtet_spi_ids, .probe = moxtet_probe, .remove = moxtet_remove, }; diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index d57bc066dce6b4..9ed9239b1228f6 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -2158,13 +2158,23 @@ static int sysc_reset(struct sysc *ddata) sysc_val = sysc_read_sysconfig(ddata); sysc_val |= sysc_mask; sysc_write(ddata, sysc_offset, sysc_val); - /* Flush posted write */ + + /* + * Some devices need a delay before reading registers + * after reset. Presumably a srst_udelay is not needed + * for devices that use a rstctrl register reset. + */ + if (ddata->cfg.srst_udelay) + fsleep(ddata->cfg.srst_udelay); + + /* + * Flush posted write. For devices needing srst_udelay + * this should trigger an interconnect error if the + * srst_udelay value is needed but not configured. + */ sysc_val = sysc_read_sysconfig(ddata); } - if (ddata->cfg.srst_udelay) - fsleep(ddata->cfg.srst_udelay); - if (ddata->post_reset_quirk) ddata->post_reset_quirk(ddata); diff --git a/drivers/cache/ax45mp_cache.c b/drivers/cache/ax45mp_cache.c index 57186c58dc849c..1d7dd3d2c101cd 100644 --- a/drivers/cache/ax45mp_cache.c +++ b/drivers/cache/ax45mp_cache.c @@ -129,8 +129,12 @@ static void ax45mp_dma_cache_wback(phys_addr_t paddr, size_t size) unsigned long line_size; unsigned long flags; + if (unlikely(start == end)) + return; + line_size = ax45mp_priv.ax45mp_cache_line_size; start = start & (~(line_size - 1)); + end = ((end + line_size - 1) & (~(line_size - 1))); local_irq_save(flags); ax45mp_cpu_dcache_wb_range(start, end); local_irq_restore(flags); diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index cc283980598333..01f46caf1f88b7 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -2358,7 +2358,7 @@ static int cdrom_ioctl_timed_media_change(struct cdrom_device_info *cdi, return -EFAULT; tmp_info.media_flags = 0; - if (tmp_info.last_media_change - cdi->last_media_change_ms < 0) + if (cdi->last_media_change_ms > tmp_info.last_media_change) tmp_info.media_flags |= MEDIA_CHANGED_FLAG; tmp_info.last_media_change = cdi->last_media_change_ms; diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c index c6f181702b9a7b..edbc4d33811776 100644 --- a/drivers/char/agp/parisc-agp.c +++ b/drivers/char/agp/parisc-agp.c @@ -38,7 +38,7 @@ static struct _parisc_agp_info { int lba_cap_offset; - u64 *gatt; + __le64 *gatt; u64 gatt_entries; u64 gart_base; @@ -104,7 +104,7 @@ parisc_agp_create_gatt_table(struct agp_bridge_data *bridge) int i; for (i = 0; i < info->gatt_entries; i++) { - info->gatt[i] = (unsigned long)agp_bridge->scratch_page; + info->gatt[i] = cpu_to_le64(agp_bridge->scratch_page); } return 0; @@ -158,9 +158,9 @@ parisc_agp_insert_memory(struct agp_memory *mem, off_t pg_start, int type) for (k = 0; k < info->io_pages_per_kpage; k++, j++, paddr += info->io_page_size) { - info->gatt[j] = + info->gatt[j] = cpu_to_le64( parisc_agp_mask_memory(agp_bridge, - paddr, type); + paddr, type)); asm_io_fdc(&info->gatt[j]); } } @@ -184,7 +184,7 @@ parisc_agp_remove_memory(struct agp_memory *mem, off_t pg_start, int type) io_pg_start = info->io_pages_per_kpage * pg_start; io_pg_count = info->io_pages_per_kpage * mem->page_count; for (i = io_pg_start; i < io_pg_count + io_pg_start; i++) { - info->gatt[i] = agp_bridge->scratch_page; + info->gatt[i] = cpu_to_le64(agp_bridge->scratch_page); } agp_bridge->driver->tlb_flush(mem); @@ -204,7 +204,8 @@ parisc_agp_mask_memory(struct agp_bridge_data *bridge, dma_addr_t addr, pa |= (ci >> PAGE_SHIFT) & 0xff;/* move CI (8 bits) into lowest byte */ pa |= SBA_PDIR_VALID_BIT; /* set "valid" bit */ - return cpu_to_le64(pa); + /* return native (big-endian) PDIR entry */ + return pa; } static void @@ -251,7 +252,8 @@ static int __init agp_ioc_init(void __iomem *ioc_regs) { struct _parisc_agp_info *info = &parisc_agp_info; - u64 iova_base, *io_pdir, io_tlb_ps; + u64 iova_base, io_tlb_ps; + __le64 *io_pdir; int io_tlb_shift; printk(KERN_INFO DRVPFX "IO PDIR shared with sba_iommu\n"); diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index ee71376f174b70..3bc1d9243dbd05 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -289,8 +289,13 @@ hpet_read(struct file *file, char __user *buf, size_t count, loff_t * ppos) if (!devp->hd_ireqfreq) return -EIO; - if (count < sizeof(unsigned long)) - return -EINVAL; + if (in_compat_syscall()) { + if (count < sizeof(compat_ulong_t)) + return -EINVAL; + } else { + if (count < sizeof(unsigned long)) + return -EINVAL; + } add_wait_queue(&devp->hd_waitqueue, &wait); @@ -314,9 +319,16 @@ hpet_read(struct file *file, char __user *buf, size_t count, loff_t * ppos) schedule(); } - retval = put_user(data, (unsigned long __user *)buf); - if (!retval) - retval = sizeof(unsigned long); + if (in_compat_syscall()) { + retval = put_user(data, (compat_ulong_t __user *)buf); + if (!retval) + retval = sizeof(compat_ulong_t); + } else { + retval = put_user(data, (unsigned long __user *)buf); + if (!retval) + retval = sizeof(unsigned long); + } + out: __set_current_state(TASK_RUNNING); remove_wait_queue(&devp->hd_waitqueue, &wait); @@ -671,12 +683,24 @@ struct compat_hpet_info { unsigned short hi_timer; }; +/* 32-bit types would lead to different command codes which should be + * translated into 64-bit ones before passed to hpet_ioctl_common + */ +#define COMPAT_HPET_INFO _IOR('h', 0x03, struct compat_hpet_info) +#define COMPAT_HPET_IRQFREQ _IOW('h', 0x6, compat_ulong_t) + static long hpet_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct hpet_info info; int err; + if (cmd == COMPAT_HPET_INFO) + cmd = HPET_INFO; + + if (cmd == COMPAT_HPET_IRQFREQ) + cmd = HPET_IRQFREQ; + mutex_lock(&hpet_mutex); err = hpet_ioctl_common(file->private_data, cmd, arg, &info); mutex_unlock(&hpet_mutex); diff --git a/drivers/char/hw_random/amd-rng.c b/drivers/char/hw_random/amd-rng.c index 86162a13681e67..9a24d19236dc70 100644 --- a/drivers/char/hw_random/amd-rng.c +++ b/drivers/char/hw_random/amd-rng.c @@ -143,8 +143,10 @@ static int __init amd_rng_mod_init(void) found: err = pci_read_config_dword(pdev, 0x58, &pmbase); - if (err) + if (err) { + err = pcibios_err_to_errno(err); goto put_dev; + } pmbase &= 0x0000FF00; if (pmbase == 0) { diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c index e19b0f9f48b97f..57a80ec93badac 100644 --- a/drivers/char/hw_random/bcm2835-rng.c +++ b/drivers/char/hw_random/bcm2835-rng.c @@ -70,7 +70,7 @@ static int bcm2835_rng_read(struct hwrng *rng, void *buf, size_t max, while ((rng_readl(priv, RNG_STATUS) >> 24) == 0) { if (!wait) return 0; - hwrng_msleep(rng, 1000); + hwrng_yield(rng); } num_words = rng_readl(priv, RNG_STATUS) >> 24; @@ -94,8 +94,10 @@ static int bcm2835_rng_init(struct hwrng *rng) return ret; ret = reset_control_reset(priv->reset); - if (ret) + if (ret) { + clk_disable_unprepare(priv->clk); return ret; + } if (priv->mask_interrupts) { /* mask the interrupt */ diff --git a/drivers/char/hw_random/cctrng.c b/drivers/char/hw_random/cctrng.c index 1abbff04a015a5..a55f5f2d35dff7 100644 --- a/drivers/char/hw_random/cctrng.c +++ b/drivers/char/hw_random/cctrng.c @@ -624,6 +624,7 @@ static int __maybe_unused cctrng_resume(struct device *dev) /* wait for Cryptocell reset completion */ if (!cctrng_wait_for_reset_completion(drvdata)) { dev_err(dev, "Cryptocell reset not completed"); + clk_disable_unprepare(drvdata->clk); return -EBUSY; } diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index e3598ec9cfca8b..a182fe794f9855 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -23,10 +23,13 @@ #include #include #include +#include #include #define RNG_MODULE_NAME "hw_random" +#define RNG_BUFFER_SIZE (SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES) + static struct hwrng *current_rng; /* the current rng has been explicitly chosen by user via sysfs */ static int cur_rng_set_by_user; @@ -58,7 +61,7 @@ static inline int rng_get_data(struct hwrng *rng, u8 *buffer, size_t size, static size_t rng_buffer_size(void) { - return SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES; + return RNG_BUFFER_SIZE; } static void add_early_randomness(struct hwrng *rng) @@ -171,7 +174,6 @@ static int hwrng_init(struct hwrng *rng) reinit_completion(&rng->cleanup_done); skip_init: - rng->quality = min_t(u16, min_t(u16, default_quality, 1024), rng->quality ?: 1024); current_quality = rng->quality; /* obsolete */ return 0; @@ -209,6 +211,7 @@ static inline int rng_get_data(struct hwrng *rng, u8 *buffer, size_t size, static ssize_t rng_dev_read(struct file *filp, char __user *buf, size_t size, loff_t *offp) { + u8 buffer[RNG_BUFFER_SIZE]; ssize_t ret = 0; int err = 0; int bytes_read, len; @@ -236,34 +239,37 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, if (bytes_read < 0) { err = bytes_read; goto out_unlock_reading; + } else if (bytes_read == 0 && + (filp->f_flags & O_NONBLOCK)) { + err = -EAGAIN; + goto out_unlock_reading; } + data_avail = bytes_read; } - if (!data_avail) { - if (filp->f_flags & O_NONBLOCK) { - err = -EAGAIN; - goto out_unlock_reading; - } - } else { - len = data_avail; + len = data_avail; + if (len) { if (len > size) len = size; data_avail -= len; - if (copy_to_user(buf + ret, rng_buffer + data_avail, - len)) { + memcpy(buffer, rng_buffer + data_avail, len); + } + mutex_unlock(&reading_mutex); + put_rng(rng); + + if (len) { + if (copy_to_user(buf + ret, buffer, len)) { err = -EFAULT; - goto out_unlock_reading; + goto out; } size -= len; ret += len; } - mutex_unlock(&reading_mutex); - put_rng(rng); if (need_resched()) schedule_timeout_interruptible(1); @@ -274,6 +280,7 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, } } out: + memzero_explicit(buffer, sizeof(buffer)); return ret ? : err; out_unlock_reading: @@ -555,6 +562,9 @@ int hwrng_register(struct hwrng *rng) complete(&rng->cleanup_done); init_completion(&rng->dying); + /* Adjust quality field to always have a proper value */ + rng->quality = min_t(u16, min_t(u16, default_quality, 1024), rng->quality ?: 1024); + if (!current_rng || (!cur_rng_set_by_user && rng->quality > current_rng->quality)) { /* @@ -678,6 +688,12 @@ long hwrng_msleep(struct hwrng *rng, unsigned int msecs) } EXPORT_SYMBOL_GPL(hwrng_msleep); +long hwrng_yield(struct hwrng *rng) +{ + return wait_for_completion_interruptible_timeout(&rng->dying, 1); +} +EXPORT_SYMBOL_GPL(hwrng_yield); + static int __init hwrng_modinit(void) { int ret; diff --git a/drivers/char/hw_random/geode-rng.c b/drivers/char/hw_random/geode-rng.c index 12fbe809183190..159baf00a86755 100644 --- a/drivers/char/hw_random/geode-rng.c +++ b/drivers/char/hw_random/geode-rng.c @@ -58,7 +58,8 @@ struct amd_geode_priv { static int geode_rng_data_read(struct hwrng *rng, u32 *data) { - void __iomem *mem = (void __iomem *)rng->priv; + struct amd_geode_priv *priv = (struct amd_geode_priv *)rng->priv; + void __iomem *mem = priv->membase; *data = readl(mem + GEODE_RNG_DATA_REG); @@ -67,7 +68,8 @@ static int geode_rng_data_read(struct hwrng *rng, u32 *data) static int geode_rng_data_present(struct hwrng *rng, int wait) { - void __iomem *mem = (void __iomem *)rng->priv; + struct amd_geode_priv *priv = (struct amd_geode_priv *)rng->priv; + void __iomem *mem = priv->membase; int data, i; for (i = 0; i < 20; i++) { diff --git a/drivers/char/hw_random/jh7110-trng.c b/drivers/char/hw_random/jh7110-trng.c index 38474d48a25e16..b1f94e3c0c6a4a 100644 --- a/drivers/char/hw_random/jh7110-trng.c +++ b/drivers/char/hw_random/jh7110-trng.c @@ -300,7 +300,7 @@ static int starfive_trng_probe(struct platform_device *pdev) ret = devm_request_irq(&pdev->dev, irq, starfive_trng_irq, 0, pdev->name, (void *)trng); if (ret) - return dev_err_probe(&pdev->dev, irq, + return dev_err_probe(&pdev->dev, ret, "Failed to register interrupt handler\n"); trng->hclk = devm_clk_get(&pdev->dev, "hclk"); diff --git a/drivers/char/hw_random/mtk-rng.c b/drivers/char/hw_random/mtk-rng.c index aa993753ab120b..1e3048f2bb38f0 100644 --- a/drivers/char/hw_random/mtk-rng.c +++ b/drivers/char/hw_random/mtk-rng.c @@ -142,7 +142,7 @@ static int mtk_rng_probe(struct platform_device *pdev) dev_set_drvdata(&pdev->dev, priv); pm_runtime_set_autosuspend_delay(&pdev->dev, RNG_AUTOSUSPEND_TIMEOUT); pm_runtime_use_autosuspend(&pdev->dev); - pm_runtime_enable(&pdev->dev); + devm_pm_runtime_enable(&pdev->dev); dev_info(&pdev->dev, "registered RNG driver\n"); diff --git a/drivers/char/ipmi/ssif_bmc.c b/drivers/char/ipmi/ssif_bmc.c index 56346fb328727e..ab4e87a99f0874 100644 --- a/drivers/char/ipmi/ssif_bmc.c +++ b/drivers/char/ipmi/ssif_bmc.c @@ -177,13 +177,15 @@ static ssize_t ssif_bmc_write(struct file *file, const char __user *buf, size_t unsigned long flags; ssize_t ret; - if (count > sizeof(struct ipmi_ssif_msg)) + if (count < sizeof(msg.len) || + count > sizeof(struct ipmi_ssif_msg)) return -EINVAL; if (copy_from_user(&msg, buf, count)) return -EFAULT; - if (!msg.len || count < sizeof_field(struct ipmi_ssif_msg, len) + msg.len) + if (!msg.len || msg.len > IPMI_SSIF_PAYLOAD_MAX || + count < sizeof_field(struct ipmi_ssif_msg, len) + msg.len) return -EINVAL; spin_lock_irqsave(&ssif_bmc->lock, flags); diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c index 4c188e9e477cdf..58e9dcc2a30874 100644 --- a/drivers/char/ppdev.c +++ b/drivers/char/ppdev.c @@ -296,28 +296,35 @@ static int register_device(int minor, struct pp_struct *pp) if (!port) { pr_warn("%s: no associated port!\n", name); rc = -ENXIO; - goto err; + goto err_free_name; + } + + index = ida_alloc(&ida_index, GFP_KERNEL); + if (index < 0) { + pr_warn("%s: failed to get index!\n", name); + rc = index; + goto err_put_port; } - index = ida_simple_get(&ida_index, 0, 0, GFP_KERNEL); memset(&ppdev_cb, 0, sizeof(ppdev_cb)); ppdev_cb.irq_func = pp_irq; ppdev_cb.flags = (pp->flags & PP_EXCL) ? PARPORT_FLAG_EXCL : 0; ppdev_cb.private = pp; pdev = parport_register_dev_model(port, name, &ppdev_cb, index); - parport_put_port(port); if (!pdev) { pr_warn("%s: failed to register device!\n", name); rc = -ENXIO; - ida_simple_remove(&ida_index, index); - goto err; + ida_free(&ida_index, index); + goto err_put_port; } pp->pdev = pdev; pp->index = index; dev_dbg(&pdev->dev, "registered pardevice\n"); -err: +err_put_port: + parport_put_port(port); +err_free_name: kfree(name); return rc; } @@ -750,7 +757,7 @@ static int pp_release(struct inode *inode, struct file *file) if (pp->pdev) { parport_unregister_device(pp->pdev); - ida_simple_remove(&ida_index, pp->index); + ida_free(&ida_index, pp->index); pp->pdev = NULL; pr_debug(CHRDEV "%x: unregistered pardevice\n", minor); } diff --git a/drivers/char/random.c b/drivers/char/random.c index 3cb37760dfec23..7b5d4822fa3ae1 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -702,7 +702,7 @@ static void extract_entropy(void *buf, size_t len) static void __cold _credit_init_bits(size_t bits) { - static struct execute_work set_ready; + static DECLARE_WORK(set_ready, crng_set_ready); unsigned int new, orig, add; unsigned long flags; @@ -718,8 +718,8 @@ static void __cold _credit_init_bits(size_t bits) if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */ - if (static_key_initialized) - execute_in_process_context(crng_set_ready, &set_ready); + if (static_key_initialized && system_unbound_wq) + queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); @@ -890,8 +890,8 @@ void __init random_init(void) /* * If we were initialized by the cpu or bootloader before jump labels - * are initialized, then we should enable the static branch here, where - * it's guaranteed that jump labels have been initialized. + * or workqueues are initialized, then we should enable the static + * branch here, where it's guaranteed that these have been initialized. */ if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) crng_set_ready(NULL); diff --git a/drivers/char/tpm/eventlog/common.c b/drivers/char/tpm/eventlog/common.c index 639c3f395a5afc..4c0bbba64ee500 100644 --- a/drivers/char/tpm/eventlog/common.c +++ b/drivers/char/tpm/eventlog/common.c @@ -47,6 +47,8 @@ static int tpm_bios_measurements_open(struct inode *inode, if (!err) { seq = file->private_data; seq->private = chip; + } else { + put_device(&chip->dev); } return err; diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c index 30b4c288c1bbc3..c3fbbf4d3db79a 100644 --- a/drivers/char/tpm/tpm-dev-common.c +++ b/drivers/char/tpm/tpm-dev-common.c @@ -47,6 +47,8 @@ static ssize_t tpm_dev_transmit(struct tpm_chip *chip, struct tpm_space *space, if (!ret) ret = tpm2_commit_space(chip, space, buf, &len); + else + tpm2_flush_space(chip); out_rc: return ret ? ret : len; diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c index 363afdd4d1d306..d4d1007fe8117e 100644 --- a/drivers/char/tpm/tpm2-space.c +++ b/drivers/char/tpm/tpm2-space.c @@ -166,6 +166,9 @@ void tpm2_flush_space(struct tpm_chip *chip) struct tpm_space *space = &chip->work_space; int i; + if (!space) + return; + for (i = 0; i < ARRAY_SIZE(space->context_tbl); i++) if (space->context_tbl[i] && ~space->context_tbl[i]) tpm2_flush_context(chip, space->context_tbl[i]); diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 1b350412d8a6be..f6aa0dfadb93ee 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -919,8 +919,6 @@ static int tpm_tis_probe_irq_single(struct tpm_chip *chip, u32 intmask, int rc; u32 int_status; - INIT_WORK(&priv->free_irq_work, tpm_tis_free_irq_func); - rc = devm_request_threaded_irq(chip->dev.parent, irq, NULL, tis_int_handler, IRQF_ONESHOT | flags, dev_name(&chip->dev), chip); @@ -1022,7 +1020,8 @@ void tpm_tis_remove(struct tpm_chip *chip) interrupt = 0; tpm_tis_write32(priv, reg, ~TPM_GLOBAL_INT_ENABLE & interrupt); - flush_work(&priv->free_irq_work); + if (priv->free_irq_work.func) + flush_work(&priv->free_irq_work); tpm_tis_clkrun_enable(chip, false); @@ -1132,6 +1131,7 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, priv->phy_ops = phy_ops; priv->locality_count = 0; mutex_init(&priv->locality_count_mutex); + INIT_WORK(&priv->free_irq_work, tpm_tis_free_irq_func); dev_set_drvdata(&chip->dev, priv); diff --git a/drivers/char/tpm/tpm_tis_spi_main.c b/drivers/char/tpm/tpm_tis_spi_main.c index c5c3197ee29f04..4bdad9e3667fa5 100644 --- a/drivers/char/tpm/tpm_tis_spi_main.c +++ b/drivers/char/tpm/tpm_tis_spi_main.c @@ -37,6 +37,7 @@ #include "tpm_tis_spi.h" #define MAX_SPI_FRAMESIZE 64 +#define SPI_HDRSIZE 4 /* * TCG SPI flow control is documented in section 6.4 of the spec[1]. In short, @@ -247,7 +248,7 @@ static int tpm_tis_spi_write_bytes(struct tpm_tis_data *data, u32 addr, int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy, int irq, const struct tpm_tis_phy_ops *phy_ops) { - phy->iobuf = devm_kmalloc(&spi->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL); + phy->iobuf = devm_kmalloc(&spi->dev, SPI_HDRSIZE + MAX_SPI_FRAMESIZE, GFP_KERNEL); if (!phy->iobuf) return -ENOMEM; diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 680d1ef2a21794..796ab9a4e48fa1 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -2052,25 +2052,27 @@ static int virtcons_probe(struct virtio_device *vdev) multiport = true; } - err = init_vqs(portdev); - if (err < 0) { - dev_err(&vdev->dev, "Error %d initializing vqs\n", err); - goto free_chrdev; - } - spin_lock_init(&portdev->ports_lock); INIT_LIST_HEAD(&portdev->ports); INIT_LIST_HEAD(&portdev->list); - virtio_device_ready(portdev->vdev); - INIT_WORK(&portdev->config_work, &config_work_handler); INIT_WORK(&portdev->control_work, &control_work_handler); if (multiport) { spin_lock_init(&portdev->c_ivq_lock); spin_lock_init(&portdev->c_ovq_lock); + } + err = init_vqs(portdev); + if (err < 0) { + dev_err(&vdev->dev, "Error %d initializing vqs\n", err); + goto free_chrdev; + } + + virtio_device_ready(portdev->vdev); + + if (multiport) { err = fill_queue(portdev->c_ivq, &portdev->c_ivq_lock); if (err < 0) { dev_err(&vdev->dev, diff --git a/drivers/char/xillybus/xillyusb.c b/drivers/char/xillybus/xillyusb.c index 5a5afa14ca8cb8..45771b1a3716a2 100644 --- a/drivers/char/xillybus/xillyusb.c +++ b/drivers/char/xillybus/xillyusb.c @@ -50,6 +50,7 @@ MODULE_LICENSE("GPL v2"); static const char xillyname[] = "xillyusb"; static unsigned int fifo_buf_order; +static struct workqueue_struct *wakeup_wq; #define USB_VENDOR_ID_XILINX 0x03fd #define USB_VENDOR_ID_ALTERA 0x09fb @@ -569,10 +570,6 @@ static void cleanup_dev(struct kref *kref) * errors if executed. The mechanism relies on that xdev->error is assigned * a non-zero value by report_io_error() prior to queueing wakeup_all(), * which prevents bulk_in_work() from calling process_bulk_in(). - * - * The fact that wakeup_all() and bulk_in_work() are queued on the same - * workqueue makes their concurrent execution very unlikely, however the - * kernel's API doesn't seem to ensure this strictly. */ static void wakeup_all(struct work_struct *work) @@ -627,7 +624,7 @@ static void report_io_error(struct xillyusb_dev *xdev, if (do_once) { kref_get(&xdev->kref); /* xdev is used by work item */ - queue_work(xdev->workq, &xdev->wakeup_workitem); + queue_work(wakeup_wq, &xdev->wakeup_workitem); } } @@ -1906,6 +1903,13 @@ static const struct file_operations xillyusb_fops = { static int xillyusb_setup_base_eps(struct xillyusb_dev *xdev) { + struct usb_device *udev = xdev->udev; + + /* Verify that device has the two fundamental bulk in/out endpoints */ + if (usb_pipe_type_check(udev, usb_sndbulkpipe(udev, MSG_EP_NUM)) || + usb_pipe_type_check(udev, usb_rcvbulkpipe(udev, IN_EP_NUM))) + return -ENODEV; + xdev->msg_ep = endpoint_alloc(xdev, MSG_EP_NUM | USB_DIR_OUT, bulk_out_work, 1, 2); if (!xdev->msg_ep) @@ -1935,14 +1939,15 @@ static int setup_channels(struct xillyusb_dev *xdev, __le16 *chandesc, int num_channels) { - struct xillyusb_channel *chan; + struct usb_device *udev = xdev->udev; + struct xillyusb_channel *chan, *new_channels; int i; chan = kcalloc(num_channels, sizeof(*chan), GFP_KERNEL); if (!chan) return -ENOMEM; - xdev->channels = chan; + new_channels = chan; for (i = 0; i < num_channels; i++, chan++) { unsigned int in_desc = le16_to_cpu(*chandesc++); @@ -1971,6 +1976,15 @@ static int setup_channels(struct xillyusb_dev *xdev, */ if ((out_desc & 0x80) && i < 14) { /* Entry is valid */ + if (usb_pipe_type_check(udev, + usb_sndbulkpipe(udev, i + 2))) { + dev_err(xdev->dev, + "Missing BULK OUT endpoint %d\n", + i + 2); + kfree(new_channels); + return -ENODEV; + } + chan->writable = 1; chan->out_synchronous = !!(out_desc & 0x40); chan->out_seekable = !!(out_desc & 0x20); @@ -1980,6 +1994,7 @@ static int setup_channels(struct xillyusb_dev *xdev, } } + xdev->channels = new_channels; return 0; } @@ -2096,9 +2111,11 @@ static int xillyusb_discovery(struct usb_interface *interface) * just after responding with the IDT, there is no reason for any * work item to be running now. To be sure that xdev->channels * is updated on anything that might run in parallel, flush the - * workqueue, which rarely does anything. + * device's workqueue and the wakeup work item. This rarely + * does anything. */ flush_workqueue(xdev->workq); + flush_work(&xdev->wakeup_workitem); xdev->num_channels = num_channels; @@ -2258,6 +2275,10 @@ static int __init xillyusb_init(void) { int rc = 0; + wakeup_wq = alloc_workqueue(xillyname, 0, 0); + if (!wakeup_wq) + return -ENOMEM; + if (LOG2_INITIAL_FIFO_BUF_SIZE > PAGE_SHIFT) fifo_buf_order = LOG2_INITIAL_FIFO_BUF_SIZE - PAGE_SHIFT; else @@ -2265,12 +2286,17 @@ static int __init xillyusb_init(void) rc = usb_register(&xillyusb_driver); + if (rc) + destroy_workqueue(wakeup_wq); + return rc; } static void __exit xillyusb_exit(void) { usb_deregister(&xillyusb_driver); + + destroy_workqueue(wakeup_wq); } module_init(xillyusb_init); diff --git a/drivers/clk/at91/sama7g5.c b/drivers/clk/at91/sama7g5.c index 91b5c6f1481964..4e9594714b1428 100644 --- a/drivers/clk/at91/sama7g5.c +++ b/drivers/clk/at91/sama7g5.c @@ -66,6 +66,7 @@ enum pll_component_id { PLL_COMPID_FRAC, PLL_COMPID_DIV0, PLL_COMPID_DIV1, + PLL_COMPID_MAX, }; /* @@ -165,7 +166,7 @@ static struct sama7g5_pll { u8 t; u8 eid; u8 safe_div; -} sama7g5_plls[][PLL_ID_MAX] = { +} sama7g5_plls[][PLL_COMPID_MAX] = { [PLL_ID_CPU] = { [PLL_COMPID_FRAC] = { .n = "cpupll_fracck", @@ -1038,7 +1039,7 @@ static void __init sama7g5_pmc_setup(struct device_node *np) sama7g5_pmc->chws[PMC_MAIN] = hw; for (i = 0; i < PLL_ID_MAX; i++) { - for (j = 0; j < 3; j++) { + for (j = 0; j < PLL_COMPID_MAX; j++) { struct clk_hw *parent_hw; if (!sama7g5_plls[i][j].n) diff --git a/drivers/clk/bcm/clk-bcm2711-dvp.c b/drivers/clk/bcm/clk-bcm2711-dvp.c index e4fbbf3c40fe2b..3cb235df9d379f 100644 --- a/drivers/clk/bcm/clk-bcm2711-dvp.c +++ b/drivers/clk/bcm/clk-bcm2711-dvp.c @@ -56,6 +56,8 @@ static int clk_dvp_probe(struct platform_device *pdev) if (ret) return ret; + data->num = NR_CLOCKS; + data->hws[0] = clk_hw_register_gate_parent_data(&pdev->dev, "hdmi0-108MHz", &clk_dvp_parent, 0, @@ -76,7 +78,6 @@ static int clk_dvp_probe(struct platform_device *pdev) goto unregister_clk0; } - data->num = NR_CLOCKS; ret = of_clk_add_hw_provider(pdev->dev.of_node, of_clk_hw_onecell_get, data); if (ret) diff --git a/drivers/clk/bcm/clk-bcm53573-ilp.c b/drivers/clk/bcm/clk-bcm53573-ilp.c index 84f2af736ee8a6..83ef41d618be37 100644 --- a/drivers/clk/bcm/clk-bcm53573-ilp.c +++ b/drivers/clk/bcm/clk-bcm53573-ilp.c @@ -112,7 +112,7 @@ static void bcm53573_ilp_init(struct device_node *np) goto err_free_ilp; } - ilp->regmap = syscon_node_to_regmap(of_get_parent(np)); + ilp->regmap = syscon_node_to_regmap(np->parent); if (IS_ERR(ilp->regmap)) { err = PTR_ERR(ilp->regmap); goto err_free_ilp; diff --git a/drivers/clk/bcm/clk-raspberrypi.c b/drivers/clk/bcm/clk-raspberrypi.c index 829406dc44a202..4d411408e4afef 100644 --- a/drivers/clk/bcm/clk-raspberrypi.c +++ b/drivers/clk/bcm/clk-raspberrypi.c @@ -371,8 +371,8 @@ static int raspberrypi_discover_clocks(struct raspberrypi_clk *rpi, if (IS_ERR(hw)) return PTR_ERR(hw); - data->hws[clks->id] = hw; data->num = clks->id + 1; + data->hws[clks->id] = hw; } clks++; diff --git a/drivers/clk/clk-en7523.c b/drivers/clk/clk-en7523.c index 7cde328495e2b6..7914e60f3d6c56 100644 --- a/drivers/clk/clk-en7523.c +++ b/drivers/clk/clk-en7523.c @@ -40,6 +40,7 @@ struct en_clk_desc { u8 div_shift; u16 div_val0; u8 div_step; + u8 div_offset; }; struct en_clk_gate { @@ -67,6 +68,7 @@ static const struct en_clk_desc en7523_base_clks[] = { .div_bits = 3, .div_shift = 0, .div_step = 1, + .div_offset = 1, }, { .id = EN7523_CLK_EMI, .name = "emi", @@ -80,6 +82,7 @@ static const struct en_clk_desc en7523_base_clks[] = { .div_bits = 3, .div_shift = 0, .div_step = 1, + .div_offset = 1, }, { .id = EN7523_CLK_BUS, .name = "bus", @@ -93,6 +96,7 @@ static const struct en_clk_desc en7523_base_clks[] = { .div_bits = 3, .div_shift = 0, .div_step = 1, + .div_offset = 1, }, { .id = EN7523_CLK_SLIC, .name = "slic", @@ -133,13 +137,14 @@ static const struct en_clk_desc en7523_base_clks[] = { .div_bits = 3, .div_shift = 0, .div_step = 1, + .div_offset = 1, }, { .id = EN7523_CLK_CRYPTO, .name = "crypto", .base_reg = REG_CRYPTO_CLKSRC, .base_bits = 1, - .base_shift = 8, + .base_shift = 0, .base_values = emi_base, .n_base_values = ARRAY_SIZE(emi_base), } @@ -184,7 +189,7 @@ static u32 en7523_get_div(void __iomem *base, int i) if (!val && desc->div_val0) return desc->div_val0; - return (val + 1) * desc->div_step; + return (val + desc->div_offset) * desc->div_step; } static int en7523_pci_is_enabled(struct clk_hw *hw) diff --git a/drivers/clk/clk-npcm7xx.c b/drivers/clk/clk-npcm7xx.c index e319cfa51a8a3f..030186def9c69a 100644 --- a/drivers/clk/clk-npcm7xx.c +++ b/drivers/clk/clk-npcm7xx.c @@ -510,7 +510,7 @@ static void __init npcm7xx_clk_init(struct device_node *clk_np) return; npcm7xx_init_fail: - kfree(npcm7xx_clk_data->hws); + kfree(npcm7xx_clk_data); npcm7xx_init_np_err: iounmap(clk_base); npcm7xx_init_error: diff --git a/drivers/clk/clk-renesas-pcie.c b/drivers/clk/clk-renesas-pcie.c index 7d7b2cb7531804..b00c38469cfadb 100644 --- a/drivers/clk/clk-renesas-pcie.c +++ b/drivers/clk/clk-renesas-pcie.c @@ -24,10 +24,12 @@ #define RS9_REG_SS_AMP_0V7 0x1 #define RS9_REG_SS_AMP_0V8 0x2 #define RS9_REG_SS_AMP_0V9 0x3 +#define RS9_REG_SS_AMP_DEFAULT RS9_REG_SS_AMP_0V8 #define RS9_REG_SS_AMP_MASK 0x3 #define RS9_REG_SS_SSC_100 0 #define RS9_REG_SS_SSC_M025 (1 << 3) #define RS9_REG_SS_SSC_M050 (3 << 3) +#define RS9_REG_SS_SSC_DEFAULT RS9_REG_SS_SSC_100 #define RS9_REG_SS_SSC_MASK (3 << 3) #define RS9_REG_SS_SSC_LOCK BIT(5) #define RS9_REG_SR 0x2 @@ -163,7 +165,7 @@ static u8 rs9_calc_dif(const struct rs9_driver_data *rs9, int idx) enum rs9_model model = rs9->chip_info->model; if (model == RENESAS_9FGV0241) - return BIT(idx) + 1; + return BIT(idx + 1); else if (model == RENESAS_9FGV0441) return BIT(idx); @@ -211,8 +213,8 @@ static int rs9_get_common_config(struct rs9_driver_data *rs9) int ret; /* Set defaults */ - rs9->pll_amplitude = RS9_REG_SS_AMP_0V7; - rs9->pll_ssc = RS9_REG_SS_SSC_100; + rs9->pll_amplitude = RS9_REG_SS_AMP_DEFAULT; + rs9->pll_ssc = RS9_REG_SS_SSC_DEFAULT; /* Output clock amplitude */ ret = of_property_read_u32(np, "renesas,out-amplitude-microvolt", @@ -253,13 +255,13 @@ static void rs9_update_config(struct rs9_driver_data *rs9) int i; /* If amplitude is non-default, update it. */ - if (rs9->pll_amplitude != RS9_REG_SS_AMP_0V7) { + if (rs9->pll_amplitude != RS9_REG_SS_AMP_DEFAULT) { regmap_update_bits(rs9->regmap, RS9_REG_SS, RS9_REG_SS_AMP_MASK, rs9->pll_amplitude); } /* If SSC is non-default, update it. */ - if (rs9->pll_ssc != RS9_REG_SS_SSC_100) { + if (rs9->pll_ssc != RS9_REG_SS_SSC_DEFAULT) { regmap_update_bits(rs9->regmap, RS9_REG_SS, RS9_REG_SS_SSC_MASK, rs9->pll_ssc); } diff --git a/drivers/clk/clk-scmi.c b/drivers/clk/clk-scmi.c index 2c7a830ce3080f..fdec715c9ba9b3 100644 --- a/drivers/clk/clk-scmi.c +++ b/drivers/clk/clk-scmi.c @@ -213,6 +213,7 @@ static int scmi_clocks_probe(struct scmi_device *sdev) sclk->info = scmi_proto_clk_ops->info_get(ph, idx); if (!sclk->info) { dev_dbg(dev, "invalid clock info for idx %d\n", idx); + devm_kfree(dev, sclk); continue; } diff --git a/drivers/clk/clk-si521xx.c b/drivers/clk/clk-si521xx.c index ef4ba467e747bc..5886bc54aa0e78 100644 --- a/drivers/clk/clk-si521xx.c +++ b/drivers/clk/clk-si521xx.c @@ -282,7 +282,7 @@ static int si521xx_probe(struct i2c_client *client) const u16 chip_info = (u16)(uintptr_t)device_get_match_data(&client->dev); const struct clk_parent_data clk_parent_data = { .index = 0 }; const u8 data[3] = { SI521XX_REG_BC, 1, 1 }; - unsigned char name[6] = "DIFF0"; + unsigned char name[16] = "DIFF0"; struct clk_init_data init = {}; struct si521xx *si; int i, ret; @@ -316,7 +316,7 @@ static int si521xx_probe(struct i2c_client *client) /* Register clock */ for (i = 0; i < hweight16(chip_info); i++) { memset(&init, 0, sizeof(init)); - snprintf(name, 6, "DIFF%d", i); + snprintf(name, sizeof(name), "DIFF%d", i); init.name = name; init.ops = &si521xx_diff_clk_ops; init.parent_data = &clk_parent_data; diff --git a/drivers/clk/clk-si5341.c b/drivers/clk/clk-si5341.c index 9599857842c72c..2920fe2e5e8bef 100644 --- a/drivers/clk/clk-si5341.c +++ b/drivers/clk/clk-si5341.c @@ -895,10 +895,8 @@ static int si5341_output_clk_set_rate(struct clk_hw *hw, unsigned long rate, r[0] = r_div ? (r_div & 0xff) : 1; r[1] = (r_div >> 8) & 0xff; r[2] = (r_div >> 16) & 0xff; - err = regmap_bulk_write(output->data->regmap, + return regmap_bulk_write(output->data->regmap, SI5341_OUT_R_REG(output), r, 3); - - return 0; } static int si5341_output_reparent(struct clk_si5341_output *output, u8 index) diff --git a/drivers/clk/clk-sp7021.c b/drivers/clk/clk-sp7021.c index 01d3c4c7b0b23f..7cb7d501d7a6eb 100644 --- a/drivers/clk/clk-sp7021.c +++ b/drivers/clk/clk-sp7021.c @@ -604,14 +604,14 @@ static int sp7021_clk_probe(struct platform_device *pdev) int i; clk_base = devm_platform_ioremap_resource(pdev, 0); - if (!clk_base) - return -ENXIO; + if (IS_ERR(clk_base)) + return PTR_ERR(clk_base); pll_base = devm_platform_ioremap_resource(pdev, 1); - if (!pll_base) - return -ENXIO; + if (IS_ERR(pll_base)) + return PTR_ERR(pll_base); sys_base = devm_platform_ioremap_resource(pdev, 2); - if (!sys_base) - return -ENXIO; + if (IS_ERR(sys_base)) + return PTR_ERR(sys_base); /* enable default clks */ for (i = 0; i < ARRAY_SIZE(sp_clken); i++) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 473563bc74960f..f8776065ad1f19 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -37,6 +37,10 @@ static HLIST_HEAD(clk_root_list); static HLIST_HEAD(clk_orphan_list); static LIST_HEAD(clk_notifier_list); +/* List of registered clks that use runtime PM */ +static HLIST_HEAD(clk_rpm_list); +static DEFINE_MUTEX(clk_rpm_list_lock); + static const struct hlist_head *all_lists[] = { &clk_root_list, &clk_orphan_list, @@ -59,6 +63,7 @@ struct clk_core { struct clk_hw *hw; struct module *owner; struct device *dev; + struct hlist_node rpm_node; struct device_node *of_node; struct clk_core *parent; struct clk_parent_map *parents; @@ -122,6 +127,89 @@ static void clk_pm_runtime_put(struct clk_core *core) pm_runtime_put_sync(core->dev); } +/** + * clk_pm_runtime_get_all() - Runtime "get" all clk provider devices + * + * Call clk_pm_runtime_get() on all runtime PM enabled clks in the clk tree so + * that disabling unused clks avoids a deadlock where a device is runtime PM + * resuming/suspending and the runtime PM callback is trying to grab the + * prepare_lock for something like clk_prepare_enable() while + * clk_disable_unused_subtree() holds the prepare_lock and is trying to runtime + * PM resume/suspend the device as well. + * + * Context: Acquires the 'clk_rpm_list_lock' and returns with the lock held on + * success. Otherwise the lock is released on failure. + * + * Return: 0 on success, negative errno otherwise. + */ +static int clk_pm_runtime_get_all(void) +{ + int ret; + struct clk_core *core, *failed; + + /* + * Grab the list lock to prevent any new clks from being registered + * or unregistered until clk_pm_runtime_put_all(). + */ + mutex_lock(&clk_rpm_list_lock); + + /* + * Runtime PM "get" all the devices that are needed for the clks + * currently registered. Do this without holding the prepare_lock, to + * avoid the deadlock. + */ + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) { + ret = clk_pm_runtime_get(core); + if (ret) { + failed = core; + pr_err("clk: Failed to runtime PM get '%s' for clk '%s'\n", + dev_name(failed->dev), failed->name); + goto err; + } + } + + return 0; + +err: + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) { + if (core == failed) + break; + + clk_pm_runtime_put(core); + } + mutex_unlock(&clk_rpm_list_lock); + + return ret; +} + +/** + * clk_pm_runtime_put_all() - Runtime "put" all clk provider devices + * + * Put the runtime PM references taken in clk_pm_runtime_get_all() and release + * the 'clk_rpm_list_lock'. + */ +static void clk_pm_runtime_put_all(void) +{ + struct clk_core *core; + + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) + clk_pm_runtime_put(core); + mutex_unlock(&clk_rpm_list_lock); +} + +static void clk_pm_runtime_init(struct clk_core *core) +{ + struct device *dev = core->dev; + + if (dev && pm_runtime_enabled(dev)) { + core->rpm_enabled = true; + + mutex_lock(&clk_rpm_list_lock); + hlist_add_head(&core->rpm_node, &clk_rpm_list); + mutex_unlock(&clk_rpm_list_lock); + } +} + /*** locking ***/ static void clk_prepare_lock(void) { @@ -418,6 +506,9 @@ static struct clk_core *clk_core_get(struct clk_core *core, u8 p_index) if (IS_ERR(hw)) return ERR_CAST(hw); + if (!hw) + return NULL; + return hw->core; } @@ -1359,9 +1450,6 @@ static void __init clk_unprepare_unused_subtree(struct clk_core *core) if (core->flags & CLK_IGNORE_UNUSED) return; - if (clk_pm_runtime_get(core)) - return; - if (clk_core_is_prepared(core)) { trace_clk_unprepare(core); if (core->ops->unprepare_unused) @@ -1370,8 +1458,6 @@ static void __init clk_unprepare_unused_subtree(struct clk_core *core) core->ops->unprepare(core->hw); trace_clk_unprepare_complete(core); } - - clk_pm_runtime_put(core); } static void __init clk_disable_unused_subtree(struct clk_core *core) @@ -1387,9 +1473,6 @@ static void __init clk_disable_unused_subtree(struct clk_core *core) if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_prepare_enable(core->parent); - if (clk_pm_runtime_get(core)) - goto unprepare_out; - flags = clk_enable_lock(); if (core->enable_count) @@ -1414,8 +1497,6 @@ static void __init clk_disable_unused_subtree(struct clk_core *core) unlock_out: clk_enable_unlock(flags); - clk_pm_runtime_put(core); -unprepare_out: if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_disable_unprepare(core->parent); } @@ -1431,6 +1512,7 @@ __setup("clk_ignore_unused", clk_ignore_unused_setup); static int __init clk_disable_unused(void) { struct clk_core *core; + int ret; if (clk_ignore_unused) { pr_warn("clk: Not disabling unused clocks\n"); @@ -1439,6 +1521,13 @@ static int __init clk_disable_unused(void) pr_info("clk: Disabling unused clocks\n"); + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; + /* + * Grab the prepare lock to keep the clk topology stable while iterating + * over clks. + */ clk_prepare_lock(); hlist_for_each_entry(core, &clk_root_list, child_node) @@ -1455,6 +1544,8 @@ static int __init clk_disable_unused(void) clk_prepare_unlock(); + clk_pm_runtime_put_all(); + return 0; } late_initcall_sync(clk_disable_unused); @@ -3188,28 +3279,41 @@ static void clk_summary_show_one(struct seq_file *s, struct clk_core *c, int level) { int phase; + struct clk *clk_user; + int multi_node = 0; - seq_printf(s, "%*s%-*s %7d %8d %8d %11lu %10lu ", + seq_printf(s, "%*s%-*s %-7d %-8d %-8d %-11lu %-10lu ", level * 3 + 1, "", - 30 - level * 3, c->name, + 35 - level * 3, c->name, c->enable_count, c->prepare_count, c->protect_count, clk_core_get_rate_recalc(c), clk_core_get_accuracy_recalc(c)); phase = clk_core_get_phase(c); if (phase >= 0) - seq_printf(s, "%5d", phase); + seq_printf(s, "%-5d", phase); else seq_puts(s, "-----"); - seq_printf(s, " %6d", clk_core_get_scaled_duty_cycle(c, 100000)); + seq_printf(s, " %-6d", clk_core_get_scaled_duty_cycle(c, 100000)); if (c->ops->is_enabled) - seq_printf(s, " %9c\n", clk_core_is_enabled(c) ? 'Y' : 'N'); + seq_printf(s, " %5c ", clk_core_is_enabled(c) ? 'Y' : 'N'); else if (!c->ops->enable) - seq_printf(s, " %9c\n", 'Y'); + seq_printf(s, " %5c ", 'Y'); else - seq_printf(s, " %9c\n", '?'); + seq_printf(s, " %5c ", '?'); + + hlist_for_each_entry(clk_user, &c->clks, clks_node) { + seq_printf(s, "%*s%-*s %-25s\n", + level * 3 + 2 + 105 * multi_node, "", + 30, + clk_user->dev_id ? clk_user->dev_id : "deviceless", + clk_user->con_id ? clk_user->con_id : "no_connection_id"); + + multi_node = 1; + } + } static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c, @@ -3217,9 +3321,7 @@ static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c, { struct clk_core *child; - clk_pm_runtime_get(c); clk_summary_show_one(s, c, level); - clk_pm_runtime_put(c); hlist_for_each_entry(child, &c->children, child_node) clk_summary_show_subtree(s, child, level + 1); @@ -3229,10 +3331,15 @@ static int clk_summary_show(struct seq_file *s, void *data) { struct clk_core *c; struct hlist_head **lists = s->private; + int ret; - seq_puts(s, " enable prepare protect duty hardware\n"); - seq_puts(s, " clock count count count rate accuracy phase cycle enable\n"); - seq_puts(s, "-------------------------------------------------------------------------------------------------------\n"); + seq_puts(s, " enable prepare protect duty hardware connection\n"); + seq_puts(s, " clock count count count rate accuracy phase cycle enable consumer id\n"); + seq_puts(s, "---------------------------------------------------------------------------------------------------------------------------------------------\n"); + + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; clk_prepare_lock(); @@ -3241,6 +3348,7 @@ static int clk_summary_show(struct seq_file *s, void *data) clk_summary_show_subtree(s, c, 0); clk_prepare_unlock(); + clk_pm_runtime_put_all(); return 0; } @@ -3288,8 +3396,14 @@ static int clk_dump_show(struct seq_file *s, void *data) struct clk_core *c; bool first_node = true; struct hlist_head **lists = s->private; + int ret; + + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; seq_putc(s, '{'); + clk_prepare_lock(); for (; *lists; lists++) { @@ -3302,6 +3416,7 @@ static int clk_dump_show(struct seq_file *s, void *data) } clk_prepare_unlock(); + clk_pm_runtime_put_all(); seq_puts(s, "}\n"); return 0; @@ -3916,8 +4031,6 @@ static int __clk_core_init(struct clk_core *core) } clk_core_reparent_orphans_nolock(); - - kref_init(&core->ref); out: clk_pm_runtime_put(core); unlock: @@ -4146,6 +4259,22 @@ static void clk_core_free_parent_map(struct clk_core *core) kfree(core->parents); } +/* Free memory allocated for a struct clk_core */ +static void __clk_release(struct kref *ref) +{ + struct clk_core *core = container_of(ref, struct clk_core, ref); + + if (core->rpm_enabled) { + mutex_lock(&clk_rpm_list_lock); + hlist_del(&core->rpm_node); + mutex_unlock(&clk_rpm_list_lock); + } + + clk_core_free_parent_map(core); + kfree_const(core->name); + kfree(core); +} + static struct clk * __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) { @@ -4166,6 +4295,8 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) goto fail_out; } + kref_init(&core->ref); + core->name = kstrdup_const(init->name, GFP_KERNEL); if (!core->name) { ret = -ENOMEM; @@ -4178,9 +4309,8 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) } core->ops = init->ops; - if (dev && pm_runtime_enabled(dev)) - core->rpm_enabled = true; core->dev = dev; + clk_pm_runtime_init(core); core->of_node = np; if (dev && dev->driver) core->owner = dev->driver->owner; @@ -4220,12 +4350,10 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) hw->clk = NULL; fail_create_clk: - clk_core_free_parent_map(core); fail_parents: fail_ops: - kfree_const(core->name); fail_name: - kfree(core); + kref_put(&core->ref, __clk_release); fail_out: return ERR_PTR(ret); } @@ -4305,18 +4433,6 @@ int of_clk_hw_register(struct device_node *node, struct clk_hw *hw) } EXPORT_SYMBOL_GPL(of_clk_hw_register); -/* Free memory allocated for a clock. */ -static void __clk_release(struct kref *ref) -{ - struct clk_core *core = container_of(ref, struct clk_core, ref); - - lockdep_assert_held(&prepare_lock); - - clk_core_free_parent_map(core); - kfree_const(core->name); - kfree(core); -} - /* * Empty clk_ops for unregistered clocks. These are used temporarily * after clk_unregister() was called on a clock and until last clock @@ -4407,7 +4523,8 @@ void clk_unregister(struct clk *clk) if (ops == &clk_nodrv_ops) { pr_err("%s: unregistered clock: %s\n", __func__, clk->core->name); - goto unlock; + clk_prepare_unlock(); + return; } /* * Assign empty clock ops for consumers that might still hold @@ -4441,11 +4558,10 @@ void clk_unregister(struct clk *clk) if (clk->core->protect_count) pr_warn("%s: unregistering protected clock: %s\n", __func__, clk->core->name); + clk_prepare_unlock(); kref_put(&clk->core->ref, __clk_release); free_clk(clk); -unlock: - clk_prepare_unlock(); } EXPORT_SYMBOL_GPL(clk_unregister); @@ -4604,13 +4720,11 @@ void __clk_put(struct clk *clk) if (clk->min_rate > 0 || clk->max_rate < ULONG_MAX) clk_set_rate_range_nolock(clk, 0, ULONG_MAX); - owner = clk->core->owner; - kref_put(&clk->core->ref, __clk_release); - clk_prepare_unlock(); + owner = clk->core->owner; + kref_put(&clk->core->ref, __clk_release); module_put(owner); - free_clk(clk); } diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c index ee37d0be6877db..9cd80522ca2d77 100644 --- a/drivers/clk/clkdev.c +++ b/drivers/clk/clkdev.c @@ -144,7 +144,7 @@ void clkdev_add_table(struct clk_lookup *cl, size_t num) mutex_unlock(&clocks_mutex); } -#define MAX_DEV_ID 20 +#define MAX_DEV_ID 24 #define MAX_CON_ID 16 struct clk_lookup_alloc { diff --git a/drivers/clk/davinci/da8xx-cfgchip.c b/drivers/clk/davinci/da8xx-cfgchip.c index e5b2cdfe88ce18..dff7ca35536cc1 100644 --- a/drivers/clk/davinci/da8xx-cfgchip.c +++ b/drivers/clk/davinci/da8xx-cfgchip.c @@ -508,7 +508,7 @@ da8xx_cfgchip_register_usb0_clk48(struct device *dev, const char * const parent_names[] = { "usb_refclkin", "pll0_auxclk" }; struct clk *fck_clk; struct da8xx_usb0_clk48 *usb0; - struct clk_init_data init; + struct clk_init_data init = {}; int ret; fck_clk = devm_clk_get(dev, "fck"); @@ -583,7 +583,7 @@ da8xx_cfgchip_register_usb1_clk48(struct device *dev, { const char * const parent_names[] = { "usb0_clk48", "usb_refclkin" }; struct da8xx_usb1_clk48 *usb1; - struct clk_init_data init; + struct clk_init_data init = {}; int ret; usb1 = devm_kzalloc(dev, sizeof(*usb1), GFP_KERNEL); diff --git a/drivers/clk/hisilicon/clk-hi3519.c b/drivers/clk/hisilicon/clk-hi3519.c index b871872d9960db..141b727ff60d64 100644 --- a/drivers/clk/hisilicon/clk-hi3519.c +++ b/drivers/clk/hisilicon/clk-hi3519.c @@ -130,7 +130,7 @@ static void hi3519_clk_unregister(struct platform_device *pdev) of_clk_del_provider(pdev->dev.of_node); hisi_clk_unregister_gate(hi3519_gate_clks, - ARRAY_SIZE(hi3519_mux_clks), + ARRAY_SIZE(hi3519_gate_clks), crg->clk_data); hisi_clk_unregister_mux(hi3519_mux_clks, ARRAY_SIZE(hi3519_mux_clks), diff --git a/drivers/clk/hisilicon/clk-hi3559a.c b/drivers/clk/hisilicon/clk-hi3559a.c index ff4ca0edce06a3..4623befafaec4d 100644 --- a/drivers/clk/hisilicon/clk-hi3559a.c +++ b/drivers/clk/hisilicon/clk-hi3559a.c @@ -491,7 +491,6 @@ static void hisi_clk_register_pll(struct hi3559av100_pll_clock *clks, clk = clk_register(NULL, &p_clk->hw); if (IS_ERR(clk)) { - devm_kfree(dev, p_clk); dev_err(dev, "%s: failed to register clock %s\n", __func__, clks[i].name); continue; diff --git a/drivers/clk/hisilicon/clk-hi3620.c b/drivers/clk/hisilicon/clk-hi3620.c index 2d7186905abdc0..5d0226530fdb2f 100644 --- a/drivers/clk/hisilicon/clk-hi3620.c +++ b/drivers/clk/hisilicon/clk-hi3620.c @@ -466,8 +466,10 @@ static void __init hi3620_mmc_clk_init(struct device_node *node) return; clk_data->clks = kcalloc(num, sizeof(*clk_data->clks), GFP_KERNEL); - if (!clk_data->clks) + if (!clk_data->clks) { + kfree(clk_data); return; + } for (i = 0; i < num; i++) { struct hisi_mmc_clock *mmc_clk = &hi3620_mmc_clks[i]; diff --git a/drivers/clk/imx/Kconfig b/drivers/clk/imx/Kconfig index f6b82e0b9703a7..db3bca5f4ec9c4 100644 --- a/drivers/clk/imx/Kconfig +++ b/drivers/clk/imx/Kconfig @@ -96,6 +96,7 @@ config CLK_IMX8QXP depends on (ARCH_MXC && ARM64) || COMPILE_TEST depends on IMX_SCU && HAVE_ARM_SMCCC select MXC_CLK_SCU + select MXC_CLK help Build the driver for IMX8QXP SCU based clocks. diff --git a/drivers/clk/imx/clk-composite-7ulp.c b/drivers/clk/imx/clk-composite-7ulp.c index e208ddc511339e..db7f40b07d1abf 100644 --- a/drivers/clk/imx/clk-composite-7ulp.c +++ b/drivers/clk/imx/clk-composite-7ulp.c @@ -14,6 +14,7 @@ #include "../clk-fractional-divider.h" #include "clk.h" +#define PCG_PR_MASK BIT(31) #define PCG_PCS_SHIFT 24 #define PCG_PCS_MASK 0x7 #define PCG_CGC_SHIFT 30 @@ -78,6 +79,12 @@ static struct clk_hw *imx_ulp_clk_hw_composite(const char *name, struct clk_hw *hw; u32 val; + val = readl(reg); + if (!(val & PCG_PR_MASK)) { + pr_info("PCC PR is 0 for clk:%s, bypass\n", name); + return 0; + } + if (mux_present) { mux = kzalloc(sizeof(*mux), GFP_KERNEL); if (!mux) diff --git a/drivers/clk/imx/clk-composite-8m.c b/drivers/clk/imx/clk-composite-8m.c index 27a08c50ac1d84..ac5e9d60acb833 100644 --- a/drivers/clk/imx/clk-composite-8m.c +++ b/drivers/clk/imx/clk-composite-8m.c @@ -204,6 +204,34 @@ static const struct clk_ops imx8m_clk_composite_mux_ops = { .determine_rate = imx8m_clk_composite_mux_determine_rate, }; +static int imx8m_clk_composite_gate_enable(struct clk_hw *hw) +{ + struct clk_gate *gate = to_clk_gate(hw); + unsigned long flags; + u32 val; + + spin_lock_irqsave(gate->lock, flags); + + val = readl(gate->reg); + val |= BIT(gate->bit_idx); + writel(val, gate->reg); + + spin_unlock_irqrestore(gate->lock, flags); + + return 0; +} + +static void imx8m_clk_composite_gate_disable(struct clk_hw *hw) +{ + /* composite clk requires the disable hook */ +} + +static const struct clk_ops imx8m_clk_composite_gate_ops = { + .enable = imx8m_clk_composite_gate_enable, + .disable = imx8m_clk_composite_gate_disable, + .is_enabled = clk_gate_is_enabled, +}; + struct clk_hw *__imx8m_clk_hw_composite(const char *name, const char * const *parent_names, int num_parents, void __iomem *reg, @@ -217,10 +245,11 @@ struct clk_hw *__imx8m_clk_hw_composite(const char *name, struct clk_mux *mux = NULL; const struct clk_ops *divider_ops; const struct clk_ops *mux_ops; + const struct clk_ops *gate_ops; mux = kzalloc(sizeof(*mux), GFP_KERNEL); if (!mux) - goto fail; + return ERR_CAST(hw); mux_hw = &mux->hw; mux->reg = reg; @@ -230,7 +259,7 @@ struct clk_hw *__imx8m_clk_hw_composite(const char *name, div = kzalloc(sizeof(*div), GFP_KERNEL); if (!div) - goto fail; + goto free_mux; div_hw = &div->hw; div->reg = reg; @@ -257,28 +286,32 @@ struct clk_hw *__imx8m_clk_hw_composite(const char *name, div->flags = CLK_DIVIDER_ROUND_CLOSEST; /* skip registering the gate ops if M4 is enabled */ - if (!mcore_booted) { - gate = kzalloc(sizeof(*gate), GFP_KERNEL); - if (!gate) - goto fail; - - gate_hw = &gate->hw; - gate->reg = reg; - gate->bit_idx = PCG_CGC_SHIFT; - gate->lock = &imx_ccm_lock; - } + gate = kzalloc(sizeof(*gate), GFP_KERNEL); + if (!gate) + goto free_div; + + gate_hw = &gate->hw; + gate->reg = reg; + gate->bit_idx = PCG_CGC_SHIFT; + gate->lock = &imx_ccm_lock; + if (!mcore_booted) + gate_ops = &clk_gate_ops; + else + gate_ops = &imx8m_clk_composite_gate_ops; hw = clk_hw_register_composite(NULL, name, parent_names, num_parents, mux_hw, mux_ops, div_hw, - divider_ops, gate_hw, &clk_gate_ops, flags); + divider_ops, gate_hw, gate_ops, flags); if (IS_ERR(hw)) - goto fail; + goto free_gate; return hw; -fail: +free_gate: kfree(gate); +free_div: kfree(div); +free_mux: kfree(mux); return ERR_CAST(hw); } diff --git a/drivers/clk/imx/clk-composite-93.c b/drivers/clk/imx/clk-composite-93.c index 81164bdcd6cc9a..6c6c5a30f3282d 100644 --- a/drivers/clk/imx/clk-composite-93.c +++ b/drivers/clk/imx/clk-composite-93.c @@ -76,6 +76,13 @@ static int imx93_clk_composite_gate_enable(struct clk_hw *hw) static void imx93_clk_composite_gate_disable(struct clk_hw *hw) { + /* + * Skip disable the root clock gate if mcore enabled. + * The root clock may be used by the mcore. + */ + if (mcore_booted) + return; + imx93_clk_composite_gate_endisable(hw, 0); } @@ -222,7 +229,7 @@ struct clk_hw *imx93_clk_composite_flags(const char *name, const char * const *p hw = clk_hw_register_composite(NULL, name, parent_names, num_parents, mux_hw, &clk_mux_ro_ops, div_hw, &clk_divider_ro_ops, NULL, NULL, flags); - } else if (!mcore_booted) { + } else { gate = kzalloc(sizeof(*gate), GFP_KERNEL); if (!gate) goto fail; @@ -238,12 +245,6 @@ struct clk_hw *imx93_clk_composite_flags(const char *name, const char * const *p &imx93_clk_composite_divider_ops, gate_hw, &imx93_clk_composite_gate_ops, flags | CLK_SET_RATE_NO_REPARENT); - } else { - hw = clk_hw_register_composite(NULL, name, parent_names, num_parents, - mux_hw, &imx93_clk_composite_mux_ops, div_hw, - &imx93_clk_composite_divider_ops, NULL, - &imx93_clk_composite_gate_ops, - flags | CLK_SET_RATE_NO_REPARENT); } if (IS_ERR(hw)) diff --git a/drivers/clk/imx/clk-fracn-gppll.c b/drivers/clk/imx/clk-fracn-gppll.c index 44462ab50e513c..1becba2b62d0be 100644 --- a/drivers/clk/imx/clk-fracn-gppll.c +++ b/drivers/clk/imx/clk-fracn-gppll.c @@ -291,6 +291,10 @@ static int clk_fracn_gppll_prepare(struct clk_hw *hw) if (val & POWERUP_MASK) return 0; + if (pll->flags & CLK_FRACN_GPPLL_FRACN) + writel_relaxed(readl_relaxed(pll->base + PLL_NUMERATOR), + pll->base + PLL_NUMERATOR); + val |= CLKMUX_BYPASS; writel_relaxed(val, pll->base + PLL_CTRL); diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c index f9394e94f69d73..05c7a82b751f3c 100644 --- a/drivers/clk/imx/clk-imx6ul.c +++ b/drivers/clk/imx/clk-imx6ul.c @@ -542,8 +542,8 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node) clk_set_parent(hws[IMX6UL_CLK_ENFC_SEL]->clk, hws[IMX6UL_CLK_PLL2_PFD2]->clk); - clk_set_parent(hws[IMX6UL_CLK_ENET1_REF_SEL]->clk, hws[IMX6UL_CLK_ENET_REF]->clk); - clk_set_parent(hws[IMX6UL_CLK_ENET2_REF_SEL]->clk, hws[IMX6UL_CLK_ENET2_REF]->clk); + clk_set_parent(hws[IMX6UL_CLK_ENET1_REF_SEL]->clk, hws[IMX6UL_CLK_ENET1_REF_125M]->clk); + clk_set_parent(hws[IMX6UL_CLK_ENET2_REF_SEL]->clk, hws[IMX6UL_CLK_ENET2_REF_125M]->clk); imx_register_uart_clocks(); } diff --git a/drivers/clk/imx/clk-imx7d.c b/drivers/clk/imx/clk-imx7d.c index 2b77d1fc7bb946..1e1296e748357b 100644 --- a/drivers/clk/imx/clk-imx7d.c +++ b/drivers/clk/imx/clk-imx7d.c @@ -498,9 +498,9 @@ static void __init imx7d_clocks_init(struct device_node *ccm_node) hws[IMX7D_ENET_AXI_ROOT_SRC] = imx_clk_hw_mux2_flags("enet_axi_src", base + 0x8900, 24, 3, enet_axi_sel, ARRAY_SIZE(enet_axi_sel), CLK_SET_PARENT_GATE); hws[IMX7D_NAND_USDHC_BUS_ROOT_SRC] = imx_clk_hw_mux2_flags("nand_usdhc_src", base + 0x8980, 24, 3, nand_usdhc_bus_sel, ARRAY_SIZE(nand_usdhc_bus_sel), CLK_SET_PARENT_GATE); hws[IMX7D_DRAM_PHYM_ROOT_SRC] = imx_clk_hw_mux2_flags("dram_phym_src", base + 0x9800, 24, 1, dram_phym_sel, ARRAY_SIZE(dram_phym_sel), CLK_SET_PARENT_GATE); - hws[IMX7D_DRAM_ROOT_SRC] = imx_clk_hw_mux2_flags("dram_src", base + 0x9880, 24, 1, dram_sel, ARRAY_SIZE(dram_sel), CLK_SET_PARENT_GATE); + hws[IMX7D_DRAM_ROOT_SRC] = imx_clk_hw_mux2("dram_src", base + 0x9880, 24, 1, dram_sel, ARRAY_SIZE(dram_sel)); hws[IMX7D_DRAM_PHYM_ALT_ROOT_SRC] = imx_clk_hw_mux2_flags("dram_phym_alt_src", base + 0xa000, 24, 3, dram_phym_alt_sel, ARRAY_SIZE(dram_phym_alt_sel), CLK_SET_PARENT_GATE); - hws[IMX7D_DRAM_ALT_ROOT_SRC] = imx_clk_hw_mux2_flags("dram_alt_src", base + 0xa080, 24, 3, dram_alt_sel, ARRAY_SIZE(dram_alt_sel), CLK_SET_PARENT_GATE); + hws[IMX7D_DRAM_ALT_ROOT_SRC] = imx_clk_hw_mux2("dram_alt_src", base + 0xa080, 24, 3, dram_alt_sel, ARRAY_SIZE(dram_alt_sel)); hws[IMX7D_USB_HSIC_ROOT_SRC] = imx_clk_hw_mux2_flags("usb_hsic_src", base + 0xa100, 24, 3, usb_hsic_sel, ARRAY_SIZE(usb_hsic_sel), CLK_SET_PARENT_GATE); hws[IMX7D_PCIE_CTRL_ROOT_SRC] = imx_clk_hw_mux2_flags("pcie_ctrl_src", base + 0xa180, 24, 3, pcie_ctrl_sel, ARRAY_SIZE(pcie_ctrl_sel), CLK_SET_PARENT_GATE); hws[IMX7D_PCIE_PHY_ROOT_SRC] = imx_clk_hw_mux2_flags("pcie_phy_src", base + 0xa200, 24, 3, pcie_phy_sel, ARRAY_SIZE(pcie_phy_sel), CLK_SET_PARENT_GATE); diff --git a/drivers/clk/imx/clk-imx8-acm.c b/drivers/clk/imx/clk-imx8-acm.c index 1e82f72b75c674..1c95ae905eec82 100644 --- a/drivers/clk/imx/clk-imx8-acm.c +++ b/drivers/clk/imx/clk-imx8-acm.c @@ -279,8 +279,10 @@ static int clk_imx_acm_attach_pm_domains(struct device *dev, for (i = 0; i < dev_pm->num_domains; i++) { dev_pm->pd_dev[i] = dev_pm_domain_attach_by_id(dev, i); - if (IS_ERR(dev_pm->pd_dev[i])) - return PTR_ERR(dev_pm->pd_dev[i]); + if (IS_ERR(dev_pm->pd_dev[i])) { + ret = PTR_ERR(dev_pm->pd_dev[i]); + goto detach_pm; + } dev_pm->pd_dev_link[i] = device_link_add(dev, dev_pm->pd_dev[i], @@ -371,7 +373,7 @@ static int imx8_acm_clk_probe(struct platform_device *pdev) sels[i].shift, sels[i].width, 0, NULL, NULL); if (IS_ERR(hws[sels[i].clkid])) { - pm_runtime_disable(&pdev->dev); + ret = PTR_ERR(hws[sels[i].clkid]); goto err_clk_register; } } @@ -381,12 +383,16 @@ static int imx8_acm_clk_probe(struct platform_device *pdev) ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, clk_hw_data); if (ret < 0) { dev_err(dev, "failed to register hws for ACM\n"); - pm_runtime_disable(&pdev->dev); + goto err_clk_register; } -err_clk_register: + pm_runtime_put_sync(&pdev->dev); + return 0; +err_clk_register: pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + clk_imx_acm_detach_pm_domains(&pdev->dev, &priv->dev_pm); return ret; } diff --git a/drivers/clk/imx/clk-imx8mp-audiomix.c b/drivers/clk/imx/clk-imx8mp-audiomix.c index e4300df88f1acc..ab2a028b3027d3 100644 --- a/drivers/clk/imx/clk-imx8mp-audiomix.c +++ b/drivers/clk/imx/clk-imx8mp-audiomix.c @@ -18,7 +18,12 @@ #define CLKEN0 0x000 #define CLKEN1 0x004 -#define SAI_MCLK_SEL(n) (0x300 + 4 * (n)) /* n in 0..5 */ +#define SAI1_MCLK_SEL 0x300 +#define SAI2_MCLK_SEL 0x304 +#define SAI3_MCLK_SEL 0x308 +#define SAI5_MCLK_SEL 0x30C +#define SAI6_MCLK_SEL 0x310 +#define SAI7_MCLK_SEL 0x314 #define PDM_SEL 0x318 #define SAI_PLL_GNRL_CTL 0x400 @@ -95,13 +100,13 @@ static const struct clk_parent_data clk_imx8mp_audiomix_pll_bypass_sels[] = { IMX8MP_CLK_AUDIOMIX_SAI##n##_MCLK1_SEL, {}, \ clk_imx8mp_audiomix_sai##n##_mclk1_parents, \ ARRAY_SIZE(clk_imx8mp_audiomix_sai##n##_mclk1_parents), \ - SAI_MCLK_SEL(n), 1, 0 \ + SAI##n##_MCLK_SEL, 1, 0 \ }, { \ "sai"__stringify(n)"_mclk2_sel", \ IMX8MP_CLK_AUDIOMIX_SAI##n##_MCLK2_SEL, {}, \ clk_imx8mp_audiomix_sai_mclk2_parents, \ ARRAY_SIZE(clk_imx8mp_audiomix_sai_mclk2_parents), \ - SAI_MCLK_SEL(n), 4, 1 \ + SAI##n##_MCLK_SEL, 4, 1 \ }, { \ "sai"__stringify(n)"_ipg_cg", \ IMX8MP_CLK_AUDIOMIX_SAI##n##_IPG, \ @@ -141,6 +146,15 @@ static const struct clk_parent_data clk_imx8mp_audiomix_pll_bypass_sels[] = { PDM_SEL, 2, 0 \ } +#define CLK_GATE_PARENT(gname, cname, pname) \ + { \ + gname"_cg", \ + IMX8MP_CLK_AUDIOMIX_##cname, \ + { .fw_name = pname, .name = pname }, NULL, 1, \ + CLKEN0 + 4 * !!(IMX8MP_CLK_AUDIOMIX_##cname / 32), \ + 1, IMX8MP_CLK_AUDIOMIX_##cname % 32 \ + } + struct clk_imx8mp_audiomix_sel { const char *name; int clkid; @@ -158,14 +172,14 @@ static struct clk_imx8mp_audiomix_sel sels[] = { CLK_GATE("earc", EARC_IPG), CLK_GATE("ocrama", OCRAMA_IPG), CLK_GATE("aud2htx", AUD2HTX_IPG), - CLK_GATE("earc_phy", EARC_PHY), + CLK_GATE_PARENT("earc_phy", EARC_PHY, "sai_pll_out_div2"), CLK_GATE("sdma2", SDMA2_ROOT), CLK_GATE("sdma3", SDMA3_ROOT), CLK_GATE("spba2", SPBA2_ROOT), CLK_GATE("dsp", DSP_ROOT), CLK_GATE("dspdbg", DSPDBG_ROOT), CLK_GATE("edma", EDMA_ROOT), - CLK_GATE("audpll", AUDPLL_ROOT), + CLK_GATE_PARENT("audpll", AUDPLL_ROOT, "osc_24m"), CLK_GATE("mu2", MU2_ROOT), CLK_GATE("mu3", MU3_ROOT), CLK_PDM, diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 670aa2bab3017e..e561ff7b135fb5 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -551,8 +551,8 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) hws[IMX8MP_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb_root", ccm_base + 0x9080, 0, 1); - hws[IMX8MP_CLK_DRAM_ALT] = imx8m_clk_hw_composite("dram_alt", imx8mp_dram_alt_sels, ccm_base + 0xa000); - hws[IMX8MP_CLK_DRAM_APB] = imx8m_clk_hw_composite_critical("dram_apb", imx8mp_dram_apb_sels, ccm_base + 0xa080); + hws[IMX8MP_CLK_DRAM_ALT] = imx8m_clk_hw_fw_managed_composite("dram_alt", imx8mp_dram_alt_sels, ccm_base + 0xa000); + hws[IMX8MP_CLK_DRAM_APB] = imx8m_clk_hw_fw_managed_composite_critical("dram_apb", imx8mp_dram_apb_sels, ccm_base + 0xa080); hws[IMX8MP_CLK_VPU_G1] = imx8m_clk_hw_composite("vpu_g1", imx8mp_vpu_g1_sels, ccm_base + 0xa100); hws[IMX8MP_CLK_VPU_G2] = imx8m_clk_hw_composite("vpu_g2", imx8mp_vpu_g2_sels, ccm_base + 0xa180); hws[IMX8MP_CLK_CAN1] = imx8m_clk_hw_composite("can1", imx8mp_can1_sels, ccm_base + 0xa200); diff --git a/drivers/clk/imx/clk-imx8mq.c b/drivers/clk/imx/clk-imx8mq.c index 4bd65879fcd347..f70ed231b92d63 100644 --- a/drivers/clk/imx/clk-imx8mq.c +++ b/drivers/clk/imx/clk-imx8mq.c @@ -288,8 +288,7 @@ static int imx8mq_clocks_probe(struct platform_device *pdev) void __iomem *base; int err; - clk_hw_data = kzalloc(struct_size(clk_hw_data, hws, - IMX8MQ_CLK_END), GFP_KERNEL); + clk_hw_data = devm_kzalloc(dev, struct_size(clk_hw_data, hws, IMX8MQ_CLK_END), GFP_KERNEL); if (WARN_ON(!clk_hw_data)) return -ENOMEM; @@ -306,10 +305,12 @@ static int imx8mq_clocks_probe(struct platform_device *pdev) hws[IMX8MQ_CLK_EXT4] = imx_get_clk_hw_by_name(np, "clk_ext4"); np = of_find_compatible_node(NULL, NULL, "fsl,imx8mq-anatop"); - base = of_iomap(np, 0); + base = devm_of_iomap(dev, np, 0, NULL); of_node_put(np); - if (WARN_ON(!base)) - return -ENOMEM; + if (WARN_ON(IS_ERR(base))) { + err = PTR_ERR(base); + goto unregister_hws; + } hws[IMX8MQ_ARM_PLL_REF_SEL] = imx_clk_hw_mux("arm_pll_ref_sel", base + 0x28, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels)); hws[IMX8MQ_GPU_PLL_REF_SEL] = imx_clk_hw_mux("gpu_pll_ref_sel", base + 0x18, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels)); @@ -395,8 +396,10 @@ static int imx8mq_clocks_probe(struct platform_device *pdev) np = dev->of_node; base = devm_platform_ioremap_resource(pdev, 0); - if (WARN_ON(IS_ERR(base))) - return PTR_ERR(base); + if (WARN_ON(IS_ERR(base))) { + err = PTR_ERR(base); + goto unregister_hws; + } /* CORE */ hws[IMX8MQ_CLK_A53_DIV] = imx8m_clk_hw_composite_core("arm_a53_div", imx8mq_a53_sels, base + 0x8000); diff --git a/drivers/clk/imx/clk-imx8qxp.c b/drivers/clk/imx/clk-imx8qxp.c index cadcbb318f5cf5..6d458995f3887d 100644 --- a/drivers/clk/imx/clk-imx8qxp.c +++ b/drivers/clk/imx/clk-imx8qxp.c @@ -66,6 +66,22 @@ static const char * const lcd_pxl_sels[] = { "lcd_pxl_bypass_div_clk", }; +static const char *const lvds0_sels[] = { + "clk_dummy", + "clk_dummy", + "clk_dummy", + "clk_dummy", + "mipi0_lvds_bypass_clk", +}; + +static const char *const lvds1_sels[] = { + "clk_dummy", + "clk_dummy", + "clk_dummy", + "clk_dummy", + "mipi1_lvds_bypass_clk", +}; + static const char * const mipi_sels[] = { "clk_dummy", "clk_dummy", @@ -147,10 +163,10 @@ static int imx8qxp_clk_probe(struct platform_device *pdev) imx_clk_scu("adc0_clk", IMX_SC_R_ADC_0, IMX_SC_PM_CLK_PER); imx_clk_scu("adc1_clk", IMX_SC_R_ADC_1, IMX_SC_PM_CLK_PER); imx_clk_scu("pwm_clk", IMX_SC_R_LCD_0_PWM_0, IMX_SC_PM_CLK_PER); + imx_clk_scu("elcdif_pll", IMX_SC_R_ELCDIF_PLL, IMX_SC_PM_CLK_PLL); imx_clk_scu2("lcd_clk", lcd_sels, ARRAY_SIZE(lcd_sels), IMX_SC_R_LCD_0, IMX_SC_PM_CLK_PER); - imx_clk_scu2("lcd_pxl_clk", lcd_pxl_sels, ARRAY_SIZE(lcd_pxl_sels), IMX_SC_R_LCD_0, IMX_SC_PM_CLK_MISC0); imx_clk_scu("lcd_pxl_bypass_div_clk", IMX_SC_R_LCD_0, IMX_SC_PM_CLK_BYPASS); - imx_clk_scu("elcdif_pll", IMX_SC_R_ELCDIF_PLL, IMX_SC_PM_CLK_PLL); + imx_clk_scu2("lcd_pxl_clk", lcd_pxl_sels, ARRAY_SIZE(lcd_pxl_sels), IMX_SC_R_LCD_0, IMX_SC_PM_CLK_MISC0); /* Audio SS */ imx_clk_scu("audio_pll0_clk", IMX_SC_R_AUDIO_PLL_0, IMX_SC_PM_CLK_PLL); @@ -183,26 +199,26 @@ static int imx8qxp_clk_probe(struct platform_device *pdev) imx_clk_scu("usb3_lpm_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_MISC); /* Display controller SS */ - imx_clk_scu2("dc0_disp0_clk", dc0_sels, ARRAY_SIZE(dc0_sels), IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC0); - imx_clk_scu2("dc0_disp1_clk", dc0_sels, ARRAY_SIZE(dc0_sels), IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC1); imx_clk_scu("dc0_pll0_clk", IMX_SC_R_DC_0_PLL_0, IMX_SC_PM_CLK_PLL); imx_clk_scu("dc0_pll1_clk", IMX_SC_R_DC_0_PLL_1, IMX_SC_PM_CLK_PLL); imx_clk_scu("dc0_bypass0_clk", IMX_SC_R_DC_0_VIDEO0, IMX_SC_PM_CLK_BYPASS); + imx_clk_scu2("dc0_disp0_clk", dc0_sels, ARRAY_SIZE(dc0_sels), IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC0); + imx_clk_scu2("dc0_disp1_clk", dc0_sels, ARRAY_SIZE(dc0_sels), IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC1); imx_clk_scu("dc0_bypass1_clk", IMX_SC_R_DC_0_VIDEO1, IMX_SC_PM_CLK_BYPASS); - imx_clk_scu2("dc1_disp0_clk", dc1_sels, ARRAY_SIZE(dc1_sels), IMX_SC_R_DC_1, IMX_SC_PM_CLK_MISC0); - imx_clk_scu2("dc1_disp1_clk", dc1_sels, ARRAY_SIZE(dc1_sels), IMX_SC_R_DC_1, IMX_SC_PM_CLK_MISC1); imx_clk_scu("dc1_pll0_clk", IMX_SC_R_DC_1_PLL_0, IMX_SC_PM_CLK_PLL); imx_clk_scu("dc1_pll1_clk", IMX_SC_R_DC_1_PLL_1, IMX_SC_PM_CLK_PLL); imx_clk_scu("dc1_bypass0_clk", IMX_SC_R_DC_1_VIDEO0, IMX_SC_PM_CLK_BYPASS); + imx_clk_scu2("dc1_disp0_clk", dc1_sels, ARRAY_SIZE(dc1_sels), IMX_SC_R_DC_1, IMX_SC_PM_CLK_MISC0); + imx_clk_scu2("dc1_disp1_clk", dc1_sels, ARRAY_SIZE(dc1_sels), IMX_SC_R_DC_1, IMX_SC_PM_CLK_MISC1); imx_clk_scu("dc1_bypass1_clk", IMX_SC_R_DC_1_VIDEO1, IMX_SC_PM_CLK_BYPASS); /* MIPI-LVDS SS */ imx_clk_scu("mipi0_bypass_clk", IMX_SC_R_MIPI_0, IMX_SC_PM_CLK_BYPASS); imx_clk_scu("mipi0_pixel_clk", IMX_SC_R_MIPI_0, IMX_SC_PM_CLK_PER); - imx_clk_scu("mipi0_lvds_pixel_clk", IMX_SC_R_LVDS_0, IMX_SC_PM_CLK_MISC2); imx_clk_scu("mipi0_lvds_bypass_clk", IMX_SC_R_LVDS_0, IMX_SC_PM_CLK_BYPASS); - imx_clk_scu("mipi0_lvds_phy_clk", IMX_SC_R_LVDS_0, IMX_SC_PM_CLK_MISC3); + imx_clk_scu2("mipi0_lvds_pixel_clk", lvds0_sels, ARRAY_SIZE(lvds0_sels), IMX_SC_R_LVDS_0, IMX_SC_PM_CLK_MISC2); + imx_clk_scu2("mipi0_lvds_phy_clk", lvds0_sels, ARRAY_SIZE(lvds0_sels), IMX_SC_R_LVDS_0, IMX_SC_PM_CLK_MISC3); imx_clk_scu2("mipi0_dsi_tx_esc_clk", mipi_sels, ARRAY_SIZE(mipi_sels), IMX_SC_R_MIPI_0, IMX_SC_PM_CLK_MST_BUS); imx_clk_scu2("mipi0_dsi_rx_esc_clk", mipi_sels, ARRAY_SIZE(mipi_sels), IMX_SC_R_MIPI_0, IMX_SC_PM_CLK_SLV_BUS); imx_clk_scu2("mipi0_dsi_phy_clk", mipi_sels, ARRAY_SIZE(mipi_sels), IMX_SC_R_MIPI_0, IMX_SC_PM_CLK_PHY); @@ -212,9 +228,9 @@ static int imx8qxp_clk_probe(struct platform_device *pdev) imx_clk_scu("mipi1_bypass_clk", IMX_SC_R_MIPI_1, IMX_SC_PM_CLK_BYPASS); imx_clk_scu("mipi1_pixel_clk", IMX_SC_R_MIPI_1, IMX_SC_PM_CLK_PER); - imx_clk_scu("mipi1_lvds_pixel_clk", IMX_SC_R_LVDS_1, IMX_SC_PM_CLK_MISC2); imx_clk_scu("mipi1_lvds_bypass_clk", IMX_SC_R_LVDS_1, IMX_SC_PM_CLK_BYPASS); - imx_clk_scu("mipi1_lvds_phy_clk", IMX_SC_R_LVDS_1, IMX_SC_PM_CLK_MISC3); + imx_clk_scu2("mipi1_lvds_pixel_clk", lvds1_sels, ARRAY_SIZE(lvds1_sels), IMX_SC_R_LVDS_1, IMX_SC_PM_CLK_MISC2); + imx_clk_scu2("mipi1_lvds_phy_clk", lvds1_sels, ARRAY_SIZE(lvds1_sels), IMX_SC_R_LVDS_1, IMX_SC_PM_CLK_MISC3); imx_clk_scu2("mipi1_dsi_tx_esc_clk", mipi_sels, ARRAY_SIZE(mipi_sels), IMX_SC_R_MIPI_1, IMX_SC_PM_CLK_MST_BUS); imx_clk_scu2("mipi1_dsi_rx_esc_clk", mipi_sels, ARRAY_SIZE(mipi_sels), IMX_SC_R_MIPI_1, IMX_SC_PM_CLK_SLV_BUS); diff --git a/drivers/clk/keystone/pll.c b/drivers/clk/keystone/pll.c index ee5c72369334ff..6bbdd4705d71fd 100644 --- a/drivers/clk/keystone/pll.c +++ b/drivers/clk/keystone/pll.c @@ -281,12 +281,13 @@ static void __init of_pll_div_clk_init(struct device_node *node) clk = clk_register_divider(NULL, clk_name, parent_name, 0, reg, shift, mask, 0, NULL); - if (clk) { - of_clk_add_provider(node, of_clk_src_simple_get, clk); - } else { + if (IS_ERR(clk)) { pr_err("%s: error registering divider %s\n", __func__, clk_name); iounmap(reg); + return; } + + of_clk_add_provider(node, of_clk_src_simple_get, clk); } CLK_OF_DECLARE(pll_divider_clock, "ti,keystone,pll-divider-clock", of_pll_div_clk_init); @@ -328,10 +329,12 @@ static void __init of_pll_mux_clk_init(struct device_node *node) clk = clk_register_mux(NULL, clk_name, (const char **)&parents, ARRAY_SIZE(parents) , 0, reg, shift, mask, 0, NULL); - if (clk) - of_clk_add_provider(node, of_clk_src_simple_get, clk); - else + if (IS_ERR(clk)) { pr_err("%s: error registering mux %s\n", __func__, clk_name); + return; + } + + of_clk_add_provider(node, of_clk_src_simple_get, clk); } CLK_OF_DECLARE(pll_mux_clock, "ti,keystone,pll-mux-clock", of_pll_mux_clk_init); diff --git a/drivers/clk/mediatek/clk-mt2701.c b/drivers/clk/mediatek/clk-mt2701.c index c81f3e33ce568f..12d9560eb4ba22 100644 --- a/drivers/clk/mediatek/clk-mt2701.c +++ b/drivers/clk/mediatek/clk-mt2701.c @@ -667,6 +667,8 @@ static int mtk_topckgen_init(struct platform_device *pdev) return PTR_ERR(base); clk_data = mtk_alloc_clk_data(CLK_TOP_NR); + if (!clk_data) + return -ENOMEM; mtk_clk_register_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), clk_data); @@ -747,6 +749,8 @@ static void __init mtk_infrasys_init_early(struct device_node *node) if (!infra_clk_data) { infra_clk_data = mtk_alloc_clk_data(CLK_INFRA_NR); + if (!infra_clk_data) + return; for (i = 0; i < CLK_INFRA_NR; i++) infra_clk_data->hws[i] = ERR_PTR(-EPROBE_DEFER); @@ -774,6 +778,8 @@ static int mtk_infrasys_init(struct platform_device *pdev) if (!infra_clk_data) { infra_clk_data = mtk_alloc_clk_data(CLK_INFRA_NR); + if (!infra_clk_data) + return -ENOMEM; } else { for (i = 0; i < CLK_INFRA_NR; i++) { if (infra_clk_data->hws[i] == ERR_PTR(-EPROBE_DEFER)) @@ -890,6 +896,8 @@ static int mtk_pericfg_init(struct platform_device *pdev) return PTR_ERR(base); clk_data = mtk_alloc_clk_data(CLK_PERI_NR); + if (!clk_data) + return -ENOMEM; mtk_clk_register_gates(&pdev->dev, node, peri_clks, ARRAY_SIZE(peri_clks), clk_data); diff --git a/drivers/clk/mediatek/clk-mt6765.c b/drivers/clk/mediatek/clk-mt6765.c index 1f4c8d0c041abe..9c7f7407d7980b 100644 --- a/drivers/clk/mediatek/clk-mt6765.c +++ b/drivers/clk/mediatek/clk-mt6765.c @@ -737,6 +737,8 @@ static int clk_mt6765_apmixed_probe(struct platform_device *pdev) return PTR_ERR(base); clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); + if (!clk_data) + return -ENOMEM; mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); @@ -769,6 +771,8 @@ static int clk_mt6765_top_probe(struct platform_device *pdev) return PTR_ERR(base); clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); + if (!clk_data) + return -ENOMEM; mtk_clk_register_fixed_clks(fixed_clks, ARRAY_SIZE(fixed_clks), clk_data); @@ -807,6 +811,8 @@ static int clk_mt6765_ifr_probe(struct platform_device *pdev) return PTR_ERR(base); clk_data = mtk_alloc_clk_data(CLK_IFR_NR_CLK); + if (!clk_data) + return -ENOMEM; mtk_clk_register_gates(&pdev->dev, node, ifr_clks, ARRAY_SIZE(ifr_clks), clk_data); diff --git a/drivers/clk/mediatek/clk-mt6779.c b/drivers/clk/mediatek/clk-mt6779.c index 3ee2f5a2319a0e..ffedb1fe3c672d 100644 --- a/drivers/clk/mediatek/clk-mt6779.c +++ b/drivers/clk/mediatek/clk-mt6779.c @@ -1217,6 +1217,8 @@ static int clk_mt6779_apmixed_probe(struct platform_device *pdev) struct device_node *node = pdev->dev.of_node; clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); + if (!clk_data) + return -ENOMEM; mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); @@ -1237,6 +1239,8 @@ static int clk_mt6779_top_probe(struct platform_device *pdev) return PTR_ERR(base); clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); + if (!clk_data) + return -ENOMEM; mtk_clk_register_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), clk_data); diff --git a/drivers/clk/mediatek/clk-mt6797.c b/drivers/clk/mediatek/clk-mt6797.c index 2ebd25f0ce71df..f12d4e9ff0bbaf 100644 --- a/drivers/clk/mediatek/clk-mt6797.c +++ b/drivers/clk/mediatek/clk-mt6797.c @@ -390,6 +390,8 @@ static int mtk_topckgen_init(struct platform_device *pdev) return PTR_ERR(base); clk_data = mtk_alloc_clk_data(CLK_TOP_NR); + if (!clk_data) + return -ENOMEM; mtk_clk_register_factors(top_fixed_divs, ARRAY_SIZE(top_fixed_divs), clk_data); @@ -545,6 +547,8 @@ static void mtk_infrasys_init_early(struct device_node *node) if (!infra_clk_data) { infra_clk_data = mtk_alloc_clk_data(CLK_INFRA_NR); + if (!infra_clk_data) + return; for (i = 0; i < CLK_INFRA_NR; i++) infra_clk_data->hws[i] = ERR_PTR(-EPROBE_DEFER); @@ -570,6 +574,8 @@ static int mtk_infrasys_init(struct platform_device *pdev) if (!infra_clk_data) { infra_clk_data = mtk_alloc_clk_data(CLK_INFRA_NR); + if (!infra_clk_data) + return -ENOMEM; } else { for (i = 0; i < CLK_INFRA_NR; i++) { if (infra_clk_data->hws[i] == ERR_PTR(-EPROBE_DEFER)) diff --git a/drivers/clk/mediatek/clk-mt7622-apmixedsys.c b/drivers/clk/mediatek/clk-mt7622-apmixedsys.c index 9cffd278e9a43e..1b8f859b6b6ccd 100644 --- a/drivers/clk/mediatek/clk-mt7622-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt7622-apmixedsys.c @@ -127,7 +127,6 @@ static void clk_mt7622_apmixed_remove(struct platform_device *pdev) of_clk_del_provider(node); mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); - mtk_free_clk_data(clk_data); } static const struct of_device_id of_match_clk_mt7622_apmixed[] = { diff --git a/drivers/clk/mediatek/clk-mt7629-eth.c b/drivers/clk/mediatek/clk-mt7629-eth.c index fe714debdc9ece..1bfedc988cfe89 100644 --- a/drivers/clk/mediatek/clk-mt7629-eth.c +++ b/drivers/clk/mediatek/clk-mt7629-eth.c @@ -77,6 +77,8 @@ static int clk_mt7629_ethsys_init(struct platform_device *pdev) int r; clk_data = mtk_alloc_clk_data(CLK_ETH_NR_CLK); + if (!clk_data) + return -ENOMEM; mtk_clk_register_gates(&pdev->dev, node, eth_clks, CLK_ETH_NR_CLK, clk_data); @@ -100,6 +102,8 @@ static int clk_mt7629_sgmiisys_init(struct platform_device *pdev) int r; clk_data = mtk_alloc_clk_data(CLK_SGMII_NR_CLK); + if (!clk_data) + return -ENOMEM; mtk_clk_register_gates(&pdev->dev, node, sgmii_clks[id++], CLK_SGMII_NR_CLK, clk_data); diff --git a/drivers/clk/mediatek/clk-mt7629.c b/drivers/clk/mediatek/clk-mt7629.c index 2882107d0f2403..b8a1f01bc974d2 100644 --- a/drivers/clk/mediatek/clk-mt7629.c +++ b/drivers/clk/mediatek/clk-mt7629.c @@ -555,6 +555,8 @@ static int mtk_topckgen_init(struct platform_device *pdev) return PTR_ERR(base); clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); + if (!clk_data) + return -ENOMEM; mtk_clk_register_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), clk_data); @@ -579,6 +581,8 @@ static int mtk_infrasys_init(struct platform_device *pdev) struct clk_hw_onecell_data *clk_data; clk_data = mtk_alloc_clk_data(CLK_INFRA_NR_CLK); + if (!clk_data) + return -ENOMEM; mtk_clk_register_gates(&pdev->dev, node, infra_clks, ARRAY_SIZE(infra_clks), clk_data); @@ -602,6 +606,8 @@ static int mtk_pericfg_init(struct platform_device *pdev) return PTR_ERR(base); clk_data = mtk_alloc_clk_data(CLK_PERI_NR_CLK); + if (!clk_data) + return -ENOMEM; mtk_clk_register_gates(&pdev->dev, node, peri_clks, ARRAY_SIZE(peri_clks), clk_data); diff --git a/drivers/clk/mediatek/clk-mt7981-topckgen.c b/drivers/clk/mediatek/clk-mt7981-topckgen.c index 682f4ca9e89ada..493aa11d3a175f 100644 --- a/drivers/clk/mediatek/clk-mt7981-topckgen.c +++ b/drivers/clk/mediatek/clk-mt7981-topckgen.c @@ -357,8 +357,9 @@ static const struct mtk_mux top_muxes[] = { MUX_GATE_CLR_SET_UPD(CLK_TOP_SGM_325M_SEL, "sgm_325m_sel", sgm_325m_parents, 0x050, 0x054, 0x058, 8, 1, 15, 0x1C0, 21), - MUX_GATE_CLR_SET_UPD(CLK_TOP_SGM_REG_SEL, "sgm_reg_sel", sgm_reg_parents, - 0x050, 0x054, 0x058, 16, 1, 23, 0x1C0, 22), + MUX_GATE_CLR_SET_UPD_FLAGS(CLK_TOP_SGM_REG_SEL, "sgm_reg_sel", sgm_reg_parents, + 0x050, 0x054, 0x058, 16, 1, 23, 0x1C0, 22, + CLK_IS_CRITICAL | CLK_SET_RATE_PARENT), MUX_GATE_CLR_SET_UPD(CLK_TOP_EIP97B_SEL, "eip97b_sel", eip97b_parents, 0x050, 0x054, 0x058, 24, 3, 31, 0x1C0, 23), /* CLK_CFG_6 */ diff --git a/drivers/clk/mediatek/clk-mt8135-apmixedsys.c b/drivers/clk/mediatek/clk-mt8135-apmixedsys.c index d1239b4b3db74b..41bb2d2e2ea740 100644 --- a/drivers/clk/mediatek/clk-mt8135-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8135-apmixedsys.c @@ -59,7 +59,7 @@ static int clk_mt8135_apmixed_probe(struct platform_device *pdev) ret = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); if (ret) - return ret; + goto free_clk_data; ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (ret) @@ -69,6 +69,8 @@ static int clk_mt8135_apmixed_probe(struct platform_device *pdev) unregister_plls: mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); +free_clk_data: + mtk_free_clk_data(clk_data); return ret; } diff --git a/drivers/clk/mediatek/clk-mt8183-mfgcfg.c b/drivers/clk/mediatek/clk-mt8183-mfgcfg.c index ba504e19d42031..62d876e150e117 100644 --- a/drivers/clk/mediatek/clk-mt8183-mfgcfg.c +++ b/drivers/clk/mediatek/clk-mt8183-mfgcfg.c @@ -29,6 +29,7 @@ static const struct mtk_gate mfg_clks[] = { static const struct mtk_clk_desc mfg_desc = { .clks = mfg_clks, .num_clks = ARRAY_SIZE(mfg_clks), + .need_runtime_pm = true, }; static const struct of_device_id of_match_clk_mt8183_mfg[] = { diff --git a/drivers/clk/mediatek/clk-mt8183.c b/drivers/clk/mediatek/clk-mt8183.c index 6e23461a04559c..934d5a15acfc58 100644 --- a/drivers/clk/mediatek/clk-mt8183.c +++ b/drivers/clk/mediatek/clk-mt8183.c @@ -790,7 +790,7 @@ static const struct mtk_gate infra_clks[] = { /* infra_sspm_26m_self is main clock in co-processor, should not be closed in Linux. */ GATE_INFRA3_FLAGS(CLK_INFRA_SSPM_26M_SELF, "infra_sspm_26m_self", "f_f26m_ck", 3, CLK_IS_CRITICAL), /* infra_sspm_32k_self is main clock in co-processor, should not be closed in Linux. */ - GATE_INFRA3_FLAGS(CLK_INFRA_SSPM_32K_SELF, "infra_sspm_32k_self", "f_f26m_ck", 4, CLK_IS_CRITICAL), + GATE_INFRA3_FLAGS(CLK_INFRA_SSPM_32K_SELF, "infra_sspm_32k_self", "clk32k", 4, CLK_IS_CRITICAL), GATE_INFRA3(CLK_INFRA_UFS_AXI, "infra_ufs_axi", "axi_sel", 5), GATE_INFRA3(CLK_INFRA_I2C6, "infra_i2c6", "i2c_sel", 6), GATE_INFRA3(CLK_INFRA_AP_MSDC0, "infra_ap_msdc0", "msdc50_hclk_sel", 7), diff --git a/drivers/clk/mediatek/clk-mt8365-mm.c b/drivers/clk/mediatek/clk-mt8365-mm.c index 01a2ef8f594ef5..3f62ec75073367 100644 --- a/drivers/clk/mediatek/clk-mt8365-mm.c +++ b/drivers/clk/mediatek/clk-mt8365-mm.c @@ -53,7 +53,7 @@ static const struct mtk_gate mm_clks[] = { GATE_MM0(CLK_MM_MM_DSI0, "mm_dsi0", "mm_sel", 17), GATE_MM0(CLK_MM_MM_DISP_RDMA1, "mm_disp_rdma1", "mm_sel", 18), GATE_MM0(CLK_MM_MM_MDP_RDMA1, "mm_mdp_rdma1", "mm_sel", 19), - GATE_MM0(CLK_MM_DPI0_DPI0, "mm_dpi0_dpi0", "vpll_dpix", 20), + GATE_MM0(CLK_MM_DPI0_DPI0, "mm_dpi0_dpi0", "dpi0_sel", 20), GATE_MM0(CLK_MM_MM_FAKE, "mm_fake", "mm_sel", 21), GATE_MM0(CLK_MM_MM_SMI_COMMON, "mm_smi_common", "mm_sel", 22), GATE_MM0(CLK_MM_MM_SMI_LARB0, "mm_smi_larb0", "mm_sel", 23), diff --git a/drivers/clk/mediatek/clk-mtk.c b/drivers/clk/mediatek/clk-mtk.c index 2e55368dc4d820..ba1d1c495bc2bf 100644 --- a/drivers/clk/mediatek/clk-mtk.c +++ b/drivers/clk/mediatek/clk-mtk.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "clk-mtk.h" @@ -494,6 +495,18 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, return IS_ERR(base) ? PTR_ERR(base) : -ENOMEM; } + + if (mcd->need_runtime_pm) { + devm_pm_runtime_enable(&pdev->dev); + /* + * Do a pm_runtime_resume_and_get() to workaround a possible + * deadlock between clk_register() and the genpd framework. + */ + r = pm_runtime_resume_and_get(&pdev->dev); + if (r) + return r; + } + /* Calculate how many clk_hw_onecell_data entries to allocate */ num_clks = mcd->num_clks + mcd->num_composite_clks; num_clks += mcd->num_fixed_clks + mcd->num_factor_clks; @@ -574,6 +587,9 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, goto unregister_clks; } + if (mcd->need_runtime_pm) + pm_runtime_put(&pdev->dev); + return r; unregister_clks: @@ -604,6 +620,9 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, free_base: if (mcd->shared_io && base) iounmap(base); + + if (mcd->need_runtime_pm) + pm_runtime_put(&pdev->dev); return r; } diff --git a/drivers/clk/mediatek/clk-mtk.h b/drivers/clk/mediatek/clk-mtk.h index 22096501a60a7b..c17fe1c2d732da 100644 --- a/drivers/clk/mediatek/clk-mtk.h +++ b/drivers/clk/mediatek/clk-mtk.h @@ -237,6 +237,8 @@ struct mtk_clk_desc { int (*clk_notifier_func)(struct device *dev, struct clk *clk); unsigned int mfg_clk_idx; + + bool need_runtime_pm; }; int mtk_clk_pdev_probe(struct platform_device *pdev); diff --git a/drivers/clk/mediatek/clk-pll.c b/drivers/clk/mediatek/clk-pll.c index a4eca5fd539c83..513ab6b1b32292 100644 --- a/drivers/clk/mediatek/clk-pll.c +++ b/drivers/clk/mediatek/clk-pll.c @@ -321,10 +321,8 @@ struct clk_hw *mtk_clk_register_pll_ops(struct mtk_clk_pll *pll, ret = clk_hw_register(NULL, &pll->hw); - if (ret) { - kfree(pll); + if (ret) return ERR_PTR(ret); - } return &pll->hw; } @@ -340,6 +338,8 @@ struct clk_hw *mtk_clk_register_pll(const struct mtk_pll_data *data, return ERR_PTR(-ENOMEM); hw = mtk_clk_register_pll_ops(pll, data, base, &mtk_pll_ops); + if (IS_ERR(hw)) + kfree(pll); return hw; } diff --git a/drivers/clk/mediatek/clk-pllfh.c b/drivers/clk/mediatek/clk-pllfh.c index 3a2b3f90be25d5..094ec8a26d6683 100644 --- a/drivers/clk/mediatek/clk-pllfh.c +++ b/drivers/clk/mediatek/clk-pllfh.c @@ -68,7 +68,7 @@ void fhctl_parse_dt(const u8 *compatible_node, struct mtk_pllfh_data *pllfhs, node = of_find_compatible_node(NULL, NULL, compatible_node); if (!node) { - pr_err("cannot find \"%s\"\n", compatible_node); + pr_warn("cannot find \"%s\"\n", compatible_node); return; } diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c index c12f81dfa67453..5f60f2bcca592a 100644 --- a/drivers/clk/meson/axg.c +++ b/drivers/clk/meson/axg.c @@ -2142,7 +2142,9 @@ static struct clk_regmap *const axg_clk_regmaps[] = { &axg_vclk_input, &axg_vclk2_input, &axg_vclk_div, + &axg_vclk_div1, &axg_vclk2_div, + &axg_vclk2_div1, &axg_vclk_div2_en, &axg_vclk_div4_en, &axg_vclk_div6_en, diff --git a/drivers/clk/mmp/clk-of-pxa168.c b/drivers/clk/mmp/clk-of-pxa168.c index fb0df64cf053c4..c5a7ba1deaa3a1 100644 --- a/drivers/clk/mmp/clk-of-pxa168.c +++ b/drivers/clk/mmp/clk-of-pxa168.c @@ -308,18 +308,21 @@ static void __init pxa168_clk_init(struct device_node *np) pxa_unit->mpmu_base = of_iomap(np, 0); if (!pxa_unit->mpmu_base) { pr_err("failed to map mpmu registers\n"); + kfree(pxa_unit); return; } pxa_unit->apmu_base = of_iomap(np, 1); if (!pxa_unit->apmu_base) { pr_err("failed to map apmu registers\n"); + kfree(pxa_unit); return; } pxa_unit->apbc_base = of_iomap(np, 2); if (!pxa_unit->apbc_base) { pr_err("failed to map apbc registers\n"); + kfree(pxa_unit); return; } diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index 865db5202e4cfe..a79b837583894f 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -131,6 +131,7 @@ config IPQ_APSS_6018 tristate "IPQ APSS Clock Controller" select IPQ_APSS_PLL depends on QCOM_APCS_IPC || COMPILE_TEST + depends on QCOM_SMEM help Support for APSS clock controller on IPQ platforms. The APSS clock controller manages the Mux and enable block that feeds the diff --git a/drivers/clk/qcom/apss-ipq-pll.c b/drivers/clk/qcom/apss-ipq-pll.c index e170331858cc14..41279e5437a620 100644 --- a/drivers/clk/qcom/apss-ipq-pll.c +++ b/drivers/clk/qcom/apss-ipq-pll.c @@ -68,13 +68,13 @@ static struct clk_alpha_pll ipq_pll_stromer_plus = { .fw_name = "xo", }, .num_parents = 1, - .ops = &clk_alpha_pll_stromer_ops, + .ops = &clk_alpha_pll_stromer_plus_ops, }, }, }; static const struct alpha_pll_config ipq5332_pll_config = { - .l = 0x3e, + .l = 0x2d, .config_ctl_val = 0x4001075b, .config_ctl_hi_val = 0x304, .main_output_mask = BIT(0), diff --git a/drivers/clk/qcom/camcc-sc7280.c b/drivers/clk/qcom/camcc-sc7280.c index 49f046ea857cbe..c1551de51d4013 100644 --- a/drivers/clk/qcom/camcc-sc7280.c +++ b/drivers/clk/qcom/camcc-sc7280.c @@ -2260,6 +2260,7 @@ static struct gdsc cam_cc_bps_gdsc = { .name = "cam_cc_bps_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = HW_CTRL | RETAIN_FF_ENABLE, }; @@ -2269,6 +2270,7 @@ static struct gdsc cam_cc_ife_0_gdsc = { .name = "cam_cc_ife_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = RETAIN_FF_ENABLE, }; @@ -2278,6 +2280,7 @@ static struct gdsc cam_cc_ife_1_gdsc = { .name = "cam_cc_ife_1_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = RETAIN_FF_ENABLE, }; @@ -2287,6 +2290,7 @@ static struct gdsc cam_cc_ife_2_gdsc = { .name = "cam_cc_ife_2_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = RETAIN_FF_ENABLE, }; @@ -2296,6 +2300,7 @@ static struct gdsc cam_cc_ipe_0_gdsc = { .name = "cam_cc_ipe_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = HW_CTRL | RETAIN_FF_ENABLE, }; diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c index e4ef645f65d1fd..8b3e5f84e89a77 100644 --- a/drivers/clk/qcom/clk-alpha-pll.c +++ b/drivers/clk/qcom/clk-alpha-pll.c @@ -40,7 +40,7 @@ #define PLL_USER_CTL(p) ((p)->offset + (p)->regs[PLL_OFF_USER_CTL]) # define PLL_POST_DIV_SHIFT 8 -# define PLL_POST_DIV_MASK(p) GENMASK((p)->width, 0) +# define PLL_POST_DIV_MASK(p) GENMASK((p)->width - 1, 0) # define PLL_ALPHA_EN BIT(24) # define PLL_ALPHA_MODE BIT(25) # define PLL_VCO_SHIFT 20 @@ -212,7 +212,6 @@ const u8 clk_alpha_pll_regs[][PLL_OFF_MAX_REGS] = { [PLL_OFF_USER_CTL] = 0x18, [PLL_OFF_USER_CTL_U] = 0x1c, [PLL_OFF_CONFIG_CTL] = 0x20, - [PLL_OFF_CONFIG_CTL_U] = 0xff, [PLL_OFF_TEST_CTL] = 0x30, [PLL_OFF_TEST_CTL_U] = 0x34, [PLL_OFF_STATUS] = 0x28, @@ -1479,8 +1478,8 @@ clk_trion_pll_postdiv_set_rate(struct clk_hw *hw, unsigned long rate, } return regmap_update_bits(regmap, PLL_USER_CTL(pll), - PLL_POST_DIV_MASK(pll) << PLL_POST_DIV_SHIFT, - val << PLL_POST_DIV_SHIFT); + PLL_POST_DIV_MASK(pll) << pll->post_div_shift, + val << pll->post_div_shift); } const struct clk_ops clk_alpha_pll_postdiv_trion_ops = { @@ -1639,7 +1638,7 @@ static int __alpha_pll_trion_set_rate(struct clk_hw *hw, unsigned long rate, if (ret < 0) return ret; - regmap_write(pll->clkr.regmap, PLL_L_VAL(pll), l); + regmap_update_bits(pll->clkr.regmap, PLL_L_VAL(pll), LUCID_EVO_PLL_L_VAL_MASK, l); regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL(pll), a); /* Latch the PLL input */ @@ -1758,6 +1757,58 @@ const struct clk_ops clk_alpha_pll_agera_ops = { }; EXPORT_SYMBOL_GPL(clk_alpha_pll_agera_ops); +/** + * clk_lucid_5lpe_pll_configure - configure the lucid 5lpe pll + * + * @pll: clk alpha pll + * @regmap: register map + * @config: configuration to apply for pll + */ +void clk_lucid_5lpe_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, + const struct alpha_pll_config *config) +{ + /* + * If the bootloader left the PLL enabled it's likely that there are + * RCGs that will lock up if we disable the PLL below. + */ + if (trion_pll_is_enabled(pll, regmap)) { + pr_debug("Lucid 5LPE PLL is already enabled, skipping configuration\n"); + return; + } + + clk_alpha_pll_write_config(regmap, PLL_L_VAL(pll), config->l); + regmap_write(regmap, PLL_CAL_L_VAL(pll), TRION_PLL_CAL_VAL); + clk_alpha_pll_write_config(regmap, PLL_ALPHA_VAL(pll), config->alpha); + clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL(pll), + config->config_ctl_val); + clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL_U(pll), + config->config_ctl_hi_val); + clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL_U1(pll), + config->config_ctl_hi1_val); + clk_alpha_pll_write_config(regmap, PLL_USER_CTL(pll), + config->user_ctl_val); + clk_alpha_pll_write_config(regmap, PLL_USER_CTL_U(pll), + config->user_ctl_hi_val); + clk_alpha_pll_write_config(regmap, PLL_USER_CTL_U1(pll), + config->user_ctl_hi1_val); + clk_alpha_pll_write_config(regmap, PLL_TEST_CTL(pll), + config->test_ctl_val); + clk_alpha_pll_write_config(regmap, PLL_TEST_CTL_U(pll), + config->test_ctl_hi_val); + clk_alpha_pll_write_config(regmap, PLL_TEST_CTL_U1(pll), + config->test_ctl_hi1_val); + + /* Disable PLL output */ + regmap_update_bits(regmap, PLL_MODE(pll), PLL_OUTCTRL, 0); + + /* Set operation mode to OFF */ + regmap_write(regmap, PLL_OPMODE(pll), PLL_STANDBY); + + /* Place the PLL in STANDBY mode */ + regmap_update_bits(regmap, PLL_MODE(pll), PLL_RESET_N, PLL_RESET_N); +} +EXPORT_SYMBOL_GPL(clk_lucid_5lpe_pll_configure); + static int alpha_pll_lucid_5lpe_enable(struct clk_hw *hw) { struct clk_alpha_pll *pll = to_clk_alpha_pll(hw); @@ -2445,6 +2496,8 @@ static int clk_alpha_pll_stromer_set_rate(struct clk_hw *hw, unsigned long rate, rate = alpha_pll_round_rate(rate, prate, &l, &a, ALPHA_REG_BITWIDTH); regmap_write(pll->clkr.regmap, PLL_L_VAL(pll), l); + + a <<= ALPHA_REG_BITWIDTH - ALPHA_BITWIDTH; regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL(pll), a); regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL_U(pll), a >> ALPHA_BITWIDTH); @@ -2479,3 +2532,69 @@ const struct clk_ops clk_alpha_pll_stromer_ops = { .set_rate = clk_alpha_pll_stromer_set_rate, }; EXPORT_SYMBOL_GPL(clk_alpha_pll_stromer_ops); + +static int clk_alpha_pll_stromer_plus_set_rate(struct clk_hw *hw, + unsigned long rate, + unsigned long prate) +{ + struct clk_alpha_pll *pll = to_clk_alpha_pll(hw); + u32 l, alpha_width = pll_alpha_width(pll); + int ret, pll_mode; + u64 a; + + rate = alpha_pll_round_rate(rate, prate, &l, &a, alpha_width); + + ret = regmap_read(pll->clkr.regmap, PLL_MODE(pll), &pll_mode); + if (ret) + return ret; + + regmap_write(pll->clkr.regmap, PLL_MODE(pll), 0); + + /* Delay of 2 output clock ticks required until output is disabled */ + udelay(1); + + regmap_write(pll->clkr.regmap, PLL_L_VAL(pll), l); + + if (alpha_width > ALPHA_BITWIDTH) + a <<= alpha_width - ALPHA_BITWIDTH; + + regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL(pll), a); + regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL_U(pll), + a >> ALPHA_BITWIDTH); + + regmap_update_bits(pll->clkr.regmap, PLL_USER_CTL(pll), + PLL_ALPHA_EN, PLL_ALPHA_EN); + + regmap_write(pll->clkr.regmap, PLL_MODE(pll), PLL_BYPASSNL); + + /* Wait five micro seconds or more */ + udelay(5); + regmap_update_bits(pll->clkr.regmap, PLL_MODE(pll), PLL_RESET_N, + PLL_RESET_N); + + /* The lock time should be less than 50 micro seconds worst case */ + usleep_range(50, 60); + + ret = wait_for_pll_enable_lock(pll); + if (ret) { + pr_err("Wait for PLL enable lock failed [%s] %d\n", + clk_hw_get_name(hw), ret); + return ret; + } + + if (pll_mode & PLL_OUTCTRL) + regmap_update_bits(pll->clkr.regmap, PLL_MODE(pll), PLL_OUTCTRL, + PLL_OUTCTRL); + + return 0; +} + +const struct clk_ops clk_alpha_pll_stromer_plus_ops = { + .prepare = clk_alpha_pll_enable, + .unprepare = clk_alpha_pll_disable, + .is_enabled = clk_alpha_pll_is_enabled, + .recalc_rate = clk_alpha_pll_recalc_rate, + .determine_rate = clk_alpha_pll_stromer_determine_rate, + .set_rate = clk_alpha_pll_stromer_plus_set_rate, +}; +EXPORT_SYMBOL_GPL(clk_alpha_pll_stromer_plus_ops); diff --git a/drivers/clk/qcom/clk-alpha-pll.h b/drivers/clk/qcom/clk-alpha-pll.h index e4bd863027ab63..3fd0ef41c72c89 100644 --- a/drivers/clk/qcom/clk-alpha-pll.h +++ b/drivers/clk/qcom/clk-alpha-pll.h @@ -152,6 +152,7 @@ extern const struct clk_ops clk_alpha_pll_postdiv_ops; extern const struct clk_ops clk_alpha_pll_huayra_ops; extern const struct clk_ops clk_alpha_pll_postdiv_ro_ops; extern const struct clk_ops clk_alpha_pll_stromer_ops; +extern const struct clk_ops clk_alpha_pll_stromer_plus_ops; extern const struct clk_ops clk_alpha_pll_fabia_ops; extern const struct clk_ops clk_alpha_pll_fixed_fabia_ops; @@ -197,6 +198,8 @@ void clk_agera_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, void clk_zonda_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, const struct alpha_pll_config *config); +void clk_lucid_5lpe_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, + const struct alpha_pll_config *config); void clk_lucid_evo_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, const struct alpha_pll_config *config); void clk_rivian_evo_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, diff --git a/drivers/clk/qcom/clk-rcg.h b/drivers/clk/qcom/clk-rcg.h index e6d84c8c7989c8..84c497f361bc6b 100644 --- a/drivers/clk/qcom/clk-rcg.h +++ b/drivers/clk/qcom/clk-rcg.h @@ -176,6 +176,7 @@ extern const struct clk_ops clk_byte2_ops; extern const struct clk_ops clk_pixel_ops; extern const struct clk_ops clk_gfx3d_ops; extern const struct clk_ops clk_rcg2_shared_ops; +extern const struct clk_ops clk_rcg2_shared_no_init_park_ops; extern const struct clk_ops clk_dp_ops; struct clk_rcg_dfs_data { diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index e22baf3a7112aa..461f54fe5e4f1f 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -158,17 +158,11 @@ static int clk_rcg2_set_parent(struct clk_hw *hw, u8 index) static unsigned long calc_rate(unsigned long rate, u32 m, u32 n, u32 mode, u32 hid_div) { - if (hid_div) { - rate *= 2; - rate /= hid_div + 1; - } + if (hid_div) + rate = mult_frac(rate, 2, hid_div + 1); - if (mode) { - u64 tmp = rate; - tmp *= m; - do_div(tmp, n); - rate = tmp; - } + if (mode) + rate = mult_frac(rate, m, n); return rate; } @@ -1144,7 +1138,39 @@ clk_rcg2_shared_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) return clk_rcg2_recalc_rate(hw, parent_rate); } +static int clk_rcg2_shared_init(struct clk_hw *hw) +{ + /* + * This does a few things: + * + * 1. Sets rcg->parked_cfg to reflect the value at probe so that the + * proper parent is reported from clk_rcg2_shared_get_parent(). + * + * 2. Clears the force enable bit of the RCG because we rely on child + * clks (branches) to turn the RCG on/off with a hardware feedback + * mechanism and only set the force enable bit in the RCG when we + * want to make sure the clk stays on for parent switches or + * parking. + * + * 3. Parks shared RCGs on the safe source at registration because we + * can't be certain that the parent clk will stay on during boot, + * especially if the parent is shared. If this RCG is enabled at + * boot, and the parent is turned off, the RCG will get stuck on. A + * GDSC can wedge if is turned on and the RCG is stuck on because + * the GDSC's controller will hang waiting for the clk status to + * toggle on when it never does. + * + * The safest option here is to "park" the RCG at init so that the clk + * can never get stuck on or off. This ensures the GDSC can't get + * wedged. + */ + clk_rcg2_shared_disable(hw); + + return 0; +} + const struct clk_ops clk_rcg2_shared_ops = { + .init = clk_rcg2_shared_init, .enable = clk_rcg2_shared_enable, .disable = clk_rcg2_shared_disable, .get_parent = clk_rcg2_shared_get_parent, @@ -1156,6 +1182,36 @@ const struct clk_ops clk_rcg2_shared_ops = { }; EXPORT_SYMBOL_GPL(clk_rcg2_shared_ops); +static int clk_rcg2_shared_no_init_park(struct clk_hw *hw) +{ + struct clk_rcg2 *rcg = to_clk_rcg2(hw); + + /* + * Read the config register so that the parent is properly mapped at + * registration time. + */ + regmap_read(rcg->clkr.regmap, rcg->cmd_rcgr + CFG_REG, &rcg->parked_cfg); + + return 0; +} + +/* + * Like clk_rcg2_shared_ops but skip the init so that the clk frequency is left + * unchanged at registration time. + */ +const struct clk_ops clk_rcg2_shared_no_init_park_ops = { + .init = clk_rcg2_shared_no_init_park, + .enable = clk_rcg2_shared_enable, + .disable = clk_rcg2_shared_disable, + .get_parent = clk_rcg2_shared_get_parent, + .set_parent = clk_rcg2_shared_set_parent, + .recalc_rate = clk_rcg2_shared_recalc_rate, + .determine_rate = clk_rcg2_determine_rate, + .set_rate = clk_rcg2_shared_set_rate, + .set_rate_and_parent = clk_rcg2_shared_set_rate_and_parent, +}; +EXPORT_SYMBOL_GPL(clk_rcg2_shared_no_init_park_ops); + /* Common APIs to be used for DFS based RCGR */ static void clk_rcg2_dfs_populate_freq(struct clk_hw *hw, unsigned int l, struct freq_tbl *f) diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c index 4c5b552b47b6a1..a556c9e77d192d 100644 --- a/drivers/clk/qcom/clk-rpmh.c +++ b/drivers/clk/qcom/clk-rpmh.c @@ -263,6 +263,8 @@ static int clk_rpmh_bcm_send_cmd(struct clk_rpmh *c, bool enable) cmd_state = 0; } + cmd_state = min(cmd_state, BCM_TCS_CMD_VOTE_MASK); + if (c->last_sent_aggr_state != cmd_state) { cmd.addr = c->res_addr; cmd.data = BCM_TCS_CMD(1, enable, 0, cmd_state); diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c index 0191fc0dd7dac1..789903a1b3f2b3 100644 --- a/drivers/clk/qcom/clk-smd-rpm.c +++ b/drivers/clk/qcom/clk-smd-rpm.c @@ -758,6 +758,7 @@ static struct clk_smd_rpm *msm8976_clks[] = { static const struct rpm_smd_clk_desc rpm_clk_msm8976 = { .clks = msm8976_clks, + .num_clks = ARRAY_SIZE(msm8976_clks), .icc_clks = bimc_pcnoc_snoc_smmnoc_icc_clks, .num_icc_clks = ARRAY_SIZE(bimc_pcnoc_snoc_smmnoc_icc_clks), }; diff --git a/drivers/clk/qcom/dispcc-sdm845.c b/drivers/clk/qcom/dispcc-sdm845.c index 735adfefc37983..e792e0b130d333 100644 --- a/drivers/clk/qcom/dispcc-sdm845.c +++ b/drivers/clk/qcom/dispcc-sdm845.c @@ -759,6 +759,8 @@ static struct clk_branch disp_cc_mdss_vsync_clk = { static struct gdsc mdss_gdsc = { .gdscr = 0x3000, + .en_few_wait_val = 0x6, + .en_rest_wait_val = 0x5, .pd = { .name = "mdss_gdsc", }, diff --git a/drivers/clk/qcom/dispcc-sm6350.c b/drivers/clk/qcom/dispcc-sm6350.c index ea6f54ed846ece..441f042f5ea459 100644 --- a/drivers/clk/qcom/dispcc-sm6350.c +++ b/drivers/clk/qcom/dispcc-sm6350.c @@ -221,26 +221,17 @@ static struct clk_rcg2 disp_cc_mdss_dp_crypto_clk_src = { }, }; -static const struct freq_tbl ftbl_disp_cc_mdss_dp_link_clk_src[] = { - F(162000, P_DP_PHY_PLL_LINK_CLK, 1, 0, 0), - F(270000, P_DP_PHY_PLL_LINK_CLK, 1, 0, 0), - F(540000, P_DP_PHY_PLL_LINK_CLK, 1, 0, 0), - F(810000, P_DP_PHY_PLL_LINK_CLK, 1, 0, 0), - { } -}; - static struct clk_rcg2 disp_cc_mdss_dp_link_clk_src = { .cmd_rcgr = 0x10f8, .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_0, - .freq_tbl = ftbl_disp_cc_mdss_dp_link_clk_src, .clkr.hw.init = &(struct clk_init_data){ .name = "disp_cc_mdss_dp_link_clk_src", .parent_data = disp_cc_parent_data_0, .num_parents = ARRAY_SIZE(disp_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; diff --git a/drivers/clk/qcom/dispcc-sm8250.c b/drivers/clk/qcom/dispcc-sm8250.c index e17bb8b543b51b..317a7e2b50bfbc 100644 --- a/drivers/clk/qcom/dispcc-sm8250.c +++ b/drivers/clk/qcom/dispcc-sm8250.c @@ -851,6 +851,7 @@ static struct clk_branch disp_cc_mdss_dp_link1_intf_clk = { &disp_cc_mdss_dp_link1_div_clk_src.clkr.hw, }, .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -886,6 +887,7 @@ static struct clk_branch disp_cc_mdss_dp_link_intf_clk = { &disp_cc_mdss_dp_link_div_clk_src.clkr.hw, }, .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1011,6 +1013,7 @@ static struct clk_branch disp_cc_mdss_mdp_lut_clk = { &disp_cc_mdss_mdp_clk_src.clkr.hw, }, .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1359,8 +1362,13 @@ static int disp_cc_sm8250_probe(struct platform_device *pdev) disp_cc_sm8250_clocks[DISP_CC_MDSS_EDP_GTC_CLK_SRC] = NULL; } - clk_lucid_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config); - clk_lucid_pll_configure(&disp_cc_pll1, regmap, &disp_cc_pll1_config); + if (of_device_is_compatible(pdev->dev.of_node, "qcom,sm8350-dispcc")) { + clk_lucid_5lpe_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config); + clk_lucid_5lpe_pll_configure(&disp_cc_pll1, regmap, &disp_cc_pll1_config); + } else { + clk_lucid_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config); + clk_lucid_pll_configure(&disp_cc_pll1, regmap, &disp_cc_pll1_config); + } /* Enable clock gating for MDP clocks */ regmap_update_bits(regmap, 0x8000, 0x10, 0x10); diff --git a/drivers/clk/qcom/dispcc-sm8450.c b/drivers/clk/qcom/dispcc-sm8450.c index 2c4aecd75186b0..239cc726c7e296 100644 --- a/drivers/clk/qcom/dispcc-sm8450.c +++ b/drivers/clk/qcom/dispcc-sm8450.c @@ -309,26 +309,17 @@ static struct clk_rcg2 disp_cc_mdss_dptx0_aux_clk_src = { }, }; -static const struct freq_tbl ftbl_disp_cc_mdss_dptx0_link_clk_src[] = { - F(162000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(270000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(540000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(810000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - { } -}; - static struct clk_rcg2 disp_cc_mdss_dptx0_link_clk_src = { .cmd_rcgr = 0x819c, .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx0_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -382,13 +373,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx1_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx1_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -442,13 +432,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx2_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx2_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -502,13 +491,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx3_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx3_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; diff --git a/drivers/clk/qcom/dispcc-sm8550.c b/drivers/clk/qcom/dispcc-sm8550.c index aefa19f3c2c514..95b4c0548f50d6 100644 --- a/drivers/clk/qcom/dispcc-sm8550.c +++ b/drivers/clk/qcom/dispcc-sm8550.c @@ -81,6 +81,10 @@ static const struct alpha_pll_config disp_cc_pll0_config = { .config_ctl_val = 0x20485699, .config_ctl_hi_val = 0x00182261, .config_ctl_hi1_val = 0x82aa299c, + .test_ctl_val = 0x00000000, + .test_ctl_hi_val = 0x00000003, + .test_ctl_hi1_val = 0x00009000, + .test_ctl_hi2_val = 0x00000034, .user_ctl_val = 0x00000000, .user_ctl_hi_val = 0x00000005, }; @@ -108,6 +112,10 @@ static const struct alpha_pll_config disp_cc_pll1_config = { .config_ctl_val = 0x20485699, .config_ctl_hi_val = 0x00182261, .config_ctl_hi1_val = 0x82aa299c, + .test_ctl_val = 0x00000000, + .test_ctl_hi_val = 0x00000003, + .test_ctl_hi1_val = 0x00009000, + .test_ctl_hi2_val = 0x00000034, .user_ctl_val = 0x00000000, .user_ctl_hi_val = 0x00000005, }; @@ -188,7 +196,7 @@ static const struct clk_parent_data disp_cc_parent_data_3[] = { static const struct parent_map disp_cc_parent_map_4[] = { { P_BI_TCXO, 0 }, { P_DP0_PHY_PLL_LINK_CLK, 1 }, - { P_DP1_PHY_PLL_VCO_DIV_CLK, 2 }, + { P_DP0_PHY_PLL_VCO_DIV_CLK, 2 }, { P_DP3_PHY_PLL_VCO_DIV_CLK, 3 }, { P_DP1_PHY_PLL_VCO_DIV_CLK, 4 }, { P_DP2_PHY_PLL_VCO_DIV_CLK, 6 }, @@ -205,7 +213,7 @@ static const struct clk_parent_data disp_cc_parent_data_4[] = { static const struct parent_map disp_cc_parent_map_5[] = { { P_BI_TCXO, 0 }, - { P_DSI0_PHY_PLL_OUT_BYTECLK, 4 }, + { P_DSI0_PHY_PLL_OUT_BYTECLK, 2 }, { P_DSI1_PHY_PLL_OUT_BYTECLK, 4 }, }; @@ -337,26 +345,17 @@ static struct clk_rcg2 disp_cc_mdss_dptx0_aux_clk_src = { }, }; -static const struct freq_tbl ftbl_disp_cc_mdss_dptx0_link_clk_src[] = { - F(162000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(270000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(540000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(810000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - { } -}; - static struct clk_rcg2 disp_cc_mdss_dptx0_link_clk_src = { .cmd_rcgr = 0x8170, .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_7, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx0_link_clk_src", .parent_data = disp_cc_parent_data_7, .num_parents = ARRAY_SIZE(disp_cc_parent_data_7), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -401,7 +400,7 @@ static struct clk_rcg2 disp_cc_mdss_dptx1_aux_clk_src = { .parent_data = disp_cc_parent_data_0, .num_parents = ARRAY_SIZE(disp_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_dp_ops, + .ops = &clk_rcg2_ops, }, }; @@ -410,13 +409,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx1_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx1_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -470,13 +468,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx2_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx2_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -530,13 +527,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx3_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx3_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -566,7 +562,7 @@ static struct clk_rcg2 disp_cc_mdss_esc0_clk_src = { .parent_data = disp_cc_parent_data_5, .num_parents = ARRAY_SIZE(disp_cc_parent_data_5), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -581,7 +577,7 @@ static struct clk_rcg2 disp_cc_mdss_esc1_clk_src = { .parent_data = disp_cc_parent_data_5, .num_parents = ARRAY_SIZE(disp_cc_parent_data_5), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1615,7 +1611,7 @@ static struct gdsc mdss_gdsc = { .name = "mdss_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = HW_CTRL | RETAIN_FF_ENABLE, + .flags = POLL_CFG_GDSCR | HW_CTRL | RETAIN_FF_ENABLE, }; static struct gdsc mdss_int2_gdsc = { @@ -1624,7 +1620,7 @@ static struct gdsc mdss_int2_gdsc = { .name = "mdss_int2_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = HW_CTRL | RETAIN_FF_ENABLE, + .flags = POLL_CFG_GDSCR | HW_CTRL | RETAIN_FF_ENABLE, }; static struct clk_regmap *disp_cc_sm8550_clocks[] = { diff --git a/drivers/clk/qcom/gcc-ipq5018.c b/drivers/clk/qcom/gcc-ipq5018.c index 19dc2b71cacf00..3136ba1c2a59cc 100644 --- a/drivers/clk/qcom/gcc-ipq5018.c +++ b/drivers/clk/qcom/gcc-ipq5018.c @@ -128,7 +128,6 @@ static struct clk_alpha_pll_postdiv gpll0 = { }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -143,7 +142,6 @@ static struct clk_alpha_pll_postdiv gpll2 = { }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -158,7 +156,6 @@ static struct clk_alpha_pll_postdiv gpll4 = { }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -859,6 +856,7 @@ static struct clk_rcg2 lpass_sway_clk_src = { static const struct freq_tbl ftbl_pcie0_aux_clk_src[] = { F(2000000, P_XO, 12, 0, 0), + { } }; static struct clk_rcg2 pcie0_aux_clk_src = { @@ -1101,6 +1099,7 @@ static const struct freq_tbl ftbl_qpic_io_macro_clk_src[] = { F(100000000, P_GPLL0, 8, 0, 0), F(200000000, P_GPLL0, 4, 0, 0), F(320000000, P_GPLL0, 2.5, 0, 0), + { } }; static struct clk_rcg2 qpic_io_macro_clk_src = { @@ -1196,6 +1195,7 @@ static struct clk_rcg2 ubi0_axi_clk_src = { static const struct freq_tbl ftbl_ubi0_core_clk_src[] = { F(850000000, P_UBI32_PLL, 1, 0, 0), F(1000000000, P_UBI32_PLL, 1, 0, 0), + { } }; static struct clk_rcg2 ubi0_core_clk_src = { @@ -1756,7 +1756,7 @@ static struct clk_branch gcc_gmac0_sys_clk = { .halt_check = BRANCH_HALT_DELAY, .halt_bit = 31, .clkr = { - .enable_reg = 0x683190, + .enable_reg = 0x68190, .enable_mask = BIT(0), .hw.init = &(struct clk_init_data) { .name = "gcc_gmac0_sys_clk", @@ -2182,7 +2182,7 @@ static struct clk_branch gcc_pcie1_axi_s_clk = { }; static struct clk_branch gcc_pcie1_pipe_clk = { - .halt_reg = 8, + .halt_reg = 0x76018, .halt_check = BRANCH_HALT_DELAY, .halt_bit = 31, .clkr = { @@ -3634,7 +3634,7 @@ static const struct qcom_reset_map gcc_ipq5018_resets[] = { [GCC_SYSTEM_NOC_BCR] = { 0x26000, 0 }, [GCC_TCSR_BCR] = { 0x28000, 0 }, [GCC_TLMM_BCR] = { 0x34000, 0 }, - [GCC_UBI0_AXI_ARES] = { 0x680}, + [GCC_UBI0_AXI_ARES] = { 0x68010, 0 }, [GCC_UBI0_AHB_ARES] = { 0x68010, 1 }, [GCC_UBI0_NC_AXI_ARES] = { 0x68010, 2 }, [GCC_UBI0_DBG_ARES] = { 0x68010, 3 }, diff --git a/drivers/clk/qcom/gcc-ipq5332.c b/drivers/clk/qcom/gcc-ipq5332.c index b02026f8549b2f..6a4877d8882946 100644 --- a/drivers/clk/qcom/gcc-ipq5332.c +++ b/drivers/clk/qcom/gcc-ipq5332.c @@ -71,7 +71,6 @@ static struct clk_fixed_factor gpll0_div2 = { &gpll0_main.clkr.hw }, .num_parents = 1, .ops = &clk_fixed_factor_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -85,7 +84,6 @@ static struct clk_alpha_pll_postdiv gpll0 = { &gpll0_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -114,7 +112,6 @@ static struct clk_alpha_pll_postdiv gpll2 = { &gpll2_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -154,7 +151,6 @@ static struct clk_alpha_pll_postdiv gpll4 = { &gpll4_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -3392,6 +3388,7 @@ static struct clk_regmap *gcc_ipq5332_clocks[] = { [GCC_QDSS_DAP_DIV_CLK_SRC] = &gcc_qdss_dap_div_clk_src.clkr, [GCC_QDSS_ETR_USB_CLK] = &gcc_qdss_etr_usb_clk.clkr, [GCC_QDSS_EUD_AT_CLK] = &gcc_qdss_eud_at_clk.clkr, + [GCC_QDSS_TSCTR_CLK_SRC] = &gcc_qdss_tsctr_clk_src.clkr, [GCC_QPIC_AHB_CLK] = &gcc_qpic_ahb_clk.clkr, [GCC_QPIC_CLK] = &gcc_qpic_clk.clkr, [GCC_QPIC_IO_MACRO_CLK] = &gcc_qpic_io_macro_clk.clkr, diff --git a/drivers/clk/qcom/gcc-ipq6018.c b/drivers/clk/qcom/gcc-ipq6018.c index 6120fbbc5de053..2e4189e770d3ff 100644 --- a/drivers/clk/qcom/gcc-ipq6018.c +++ b/drivers/clk/qcom/gcc-ipq6018.c @@ -72,7 +72,6 @@ static struct clk_fixed_factor gpll0_out_main_div2 = { &gpll0_main.clkr.hw }, .num_parents = 1, .ops = &clk_fixed_factor_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -86,7 +85,6 @@ static struct clk_alpha_pll_postdiv gpll0 = { &gpll0_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -161,7 +159,6 @@ static struct clk_alpha_pll_postdiv gpll6 = { &gpll6_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -192,7 +189,6 @@ static struct clk_alpha_pll_postdiv gpll4 = { &gpll4_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -243,7 +239,6 @@ static struct clk_alpha_pll_postdiv gpll2 = { &gpll2_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -274,7 +269,6 @@ static struct clk_alpha_pll_postdiv nss_crypto_pll = { &nss_crypto_pll_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -1560,6 +1554,7 @@ static struct clk_regmap_div nss_ubi0_div_clk_src = { static const struct freq_tbl ftbl_pcie_aux_clk_src[] = { F(24000000, P_XO, 1, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_core_pi_sleep_clk[] = { @@ -1740,6 +1735,7 @@ static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = { F(160000000, P_GPLL0, 5, 0, 0), F(216000000, P_GPLL6, 5, 0, 0), F(308570000, P_GPLL6, 3.5, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_gpll6_gpll0_div2[] = { diff --git a/drivers/clk/qcom/gcc-ipq8074.c b/drivers/clk/qcom/gcc-ipq8074.c index 63ac2ced76bb95..7bc679871f324f 100644 --- a/drivers/clk/qcom/gcc-ipq8074.c +++ b/drivers/clk/qcom/gcc-ipq8074.c @@ -75,7 +75,6 @@ static struct clk_fixed_factor gpll0_out_main_div2 = { &gpll0_main.clkr.hw }, .num_parents = 1, .ops = &clk_fixed_factor_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -121,7 +120,6 @@ static struct clk_alpha_pll_postdiv gpll2 = { &gpll2_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -154,7 +152,6 @@ static struct clk_alpha_pll_postdiv gpll4 = { &gpll4_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -188,7 +185,6 @@ static struct clk_alpha_pll_postdiv gpll6 = { &gpll6_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -201,7 +197,6 @@ static struct clk_fixed_factor gpll6_out_main_div2 = { &gpll6_main.clkr.hw }, .num_parents = 1, .ops = &clk_fixed_factor_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -266,7 +261,6 @@ static struct clk_alpha_pll_postdiv nss_crypto_pll = { &nss_crypto_pll_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -650,6 +644,7 @@ static struct clk_rcg2 pcie0_axi_clk_src = { static const struct freq_tbl ftbl_pcie_aux_clk_src[] = { F(19200000, P_XO, 1, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_sleep_clk[] = { @@ -801,6 +796,7 @@ static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = { F(19200000, P_XO, 1, 0, 0), F(160000000, P_GPLL0, 5, 0, 0), F(308570000, P_GPLL6, 3.5, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_gpll6_gpll0_div2[] = { diff --git a/drivers/clk/qcom/gcc-ipq9574.c b/drivers/clk/qcom/gcc-ipq9574.c index 8f430367299e66..cdbbf2cc9c5d19 100644 --- a/drivers/clk/qcom/gcc-ipq9574.c +++ b/drivers/clk/qcom/gcc-ipq9574.c @@ -65,7 +65,7 @@ static const struct clk_parent_data gcc_sleep_clk_data[] = { static struct clk_alpha_pll gpll0_main = { .offset = 0x20000, - .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT_EVO], .clkr = { .enable_reg = 0x0b000, .enable_mask = BIT(0), @@ -87,14 +87,13 @@ static struct clk_fixed_factor gpll0_out_main_div2 = { &gpll0_main.clkr.hw }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_fixed_factor_ops, }, }; static struct clk_alpha_pll_postdiv gpll0 = { .offset = 0x20000, - .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT_EVO], .width = 4, .clkr.hw.init = &(const struct clk_init_data) { .name = "gpll0", @@ -102,14 +101,13 @@ static struct clk_alpha_pll_postdiv gpll0 = { &gpll0_main.clkr.hw }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_alpha_pll_postdiv_ro_ops, }, }; static struct clk_alpha_pll gpll4_main = { .offset = 0x22000, - .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT_EVO], .clkr = { .enable_reg = 0x0b000, .enable_mask = BIT(2), @@ -124,7 +122,7 @@ static struct clk_alpha_pll gpll4_main = { static struct clk_alpha_pll_postdiv gpll4 = { .offset = 0x22000, - .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT_EVO], .width = 4, .clkr.hw.init = &(const struct clk_init_data) { .name = "gpll4", @@ -132,14 +130,13 @@ static struct clk_alpha_pll_postdiv gpll4 = { &gpll4_main.clkr.hw }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_alpha_pll_postdiv_ro_ops, }, }; static struct clk_alpha_pll gpll2_main = { .offset = 0x21000, - .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT_EVO], .clkr = { .enable_reg = 0x0b000, .enable_mask = BIT(1), @@ -154,7 +151,7 @@ static struct clk_alpha_pll gpll2_main = { static struct clk_alpha_pll_postdiv gpll2 = { .offset = 0x21000, - .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT_EVO], .width = 4, .clkr.hw.init = &(const struct clk_init_data) { .name = "gpll2", @@ -162,7 +159,6 @@ static struct clk_alpha_pll_postdiv gpll2 = { &gpll2_main.clkr.hw }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_alpha_pll_postdiv_ro_ops, }, }; @@ -2086,6 +2082,7 @@ static struct clk_branch gcc_sdcc1_apps_clk = { static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = { F(150000000, P_GPLL4, 8, 0, 0), F(300000000, P_GPLL4, 4, 0, 0), + { } }; static struct clk_rcg2 sdcc1_ice_core_clk_src = { @@ -2143,9 +2140,10 @@ static struct clk_rcg2 pcnoc_bfdcd_clk_src = { static struct clk_branch gcc_crypto_axi_clk = { .halt_reg = 0x16010, + .halt_check = BRANCH_HALT_VOTED, .clkr = { - .enable_reg = 0x16010, - .enable_mask = BIT(0), + .enable_reg = 0xb004, + .enable_mask = BIT(15), .hw.init = &(const struct clk_init_data) { .name = "gcc_crypto_axi_clk", .parent_hws = (const struct clk_hw *[]) { @@ -2159,9 +2157,10 @@ static struct clk_branch gcc_crypto_axi_clk = { static struct clk_branch gcc_crypto_ahb_clk = { .halt_reg = 0x16014, + .halt_check = BRANCH_HALT_VOTED, .clkr = { - .enable_reg = 0x16014, - .enable_mask = BIT(0), + .enable_reg = 0xb004, + .enable_mask = BIT(16), .hw.init = &(const struct clk_init_data) { .name = "gcc_crypto_ahb_clk", .parent_hws = (const struct clk_hw *[]) { diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c index 14dcc3f036683c..e7b03a17514a5d 100644 --- a/drivers/clk/qcom/gcc-msm8996.c +++ b/drivers/clk/qcom/gcc-msm8996.c @@ -244,71 +244,6 @@ static const struct clk_parent_data gcc_xo_gpll0_gpll4_gpll0_early_div[] = { { .hw = &gpll0_early_div.hw } }; -static const struct freq_tbl ftbl_system_noc_clk_src[] = { - F(19200000, P_XO, 1, 0, 0), - F(50000000, P_GPLL0_EARLY_DIV, 6, 0, 0), - F(100000000, P_GPLL0, 6, 0, 0), - F(150000000, P_GPLL0, 4, 0, 0), - F(200000000, P_GPLL0, 3, 0, 0), - F(240000000, P_GPLL0, 2.5, 0, 0), - { } -}; - -static struct clk_rcg2 system_noc_clk_src = { - .cmd_rcgr = 0x0401c, - .hid_width = 5, - .parent_map = gcc_xo_gpll0_gpll0_early_div_map, - .freq_tbl = ftbl_system_noc_clk_src, - .clkr.hw.init = &(struct clk_init_data){ - .name = "system_noc_clk_src", - .parent_data = gcc_xo_gpll0_gpll0_early_div, - .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_early_div), - .ops = &clk_rcg2_ops, - }, -}; - -static const struct freq_tbl ftbl_config_noc_clk_src[] = { - F(19200000, P_XO, 1, 0, 0), - F(37500000, P_GPLL0, 16, 0, 0), - F(75000000, P_GPLL0, 8, 0, 0), - { } -}; - -static struct clk_rcg2 config_noc_clk_src = { - .cmd_rcgr = 0x0500c, - .hid_width = 5, - .parent_map = gcc_xo_gpll0_map, - .freq_tbl = ftbl_config_noc_clk_src, - .clkr.hw.init = &(struct clk_init_data){ - .name = "config_noc_clk_src", - .parent_data = gcc_xo_gpll0, - .num_parents = ARRAY_SIZE(gcc_xo_gpll0), - .ops = &clk_rcg2_ops, - }, -}; - -static const struct freq_tbl ftbl_periph_noc_clk_src[] = { - F(19200000, P_XO, 1, 0, 0), - F(37500000, P_GPLL0, 16, 0, 0), - F(50000000, P_GPLL0, 12, 0, 0), - F(75000000, P_GPLL0, 8, 0, 0), - F(100000000, P_GPLL0, 6, 0, 0), - { } -}; - -static struct clk_rcg2 periph_noc_clk_src = { - .cmd_rcgr = 0x06014, - .hid_width = 5, - .parent_map = gcc_xo_gpll0_map, - .freq_tbl = ftbl_periph_noc_clk_src, - .clkr.hw.init = &(struct clk_init_data){ - .name = "periph_noc_clk_src", - .parent_data = gcc_xo_gpll0, - .num_parents = ARRAY_SIZE(gcc_xo_gpll0), - .ops = &clk_rcg2_ops, - }, -}; - static const struct freq_tbl ftbl_usb30_master_clk_src[] = { F(19200000, P_XO, 1, 0, 0), F(120000000, P_GPLL0, 5, 0, 0), @@ -1297,11 +1232,7 @@ static struct clk_branch gcc_mmss_noc_cfg_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_mmss_noc_cfg_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &config_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED, + .flags = CLK_IGNORE_UNUSED, .ops = &clk_branch2_ops, }, }, @@ -1464,11 +1395,6 @@ static struct clk_branch gcc_usb_phy_cfg_ahb2phy_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_usb_phy_cfg_ahb2phy_clk", - .parent_hws = (const struct clk_hw*[]){ - &periph_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1498,11 +1424,6 @@ static struct clk_branch gcc_sdcc1_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_sdcc1_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &periph_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1549,11 +1470,6 @@ static struct clk_branch gcc_sdcc2_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_sdcc2_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &periph_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1583,11 +1499,6 @@ static struct clk_branch gcc_sdcc3_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_sdcc3_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &periph_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1617,11 +1528,6 @@ static struct clk_branch gcc_sdcc4_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_sdcc4_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &periph_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1635,11 +1541,6 @@ static struct clk_branch gcc_blsp1_ahb_clk = { .enable_mask = BIT(17), .hw.init = &(struct clk_init_data){ .name = "gcc_blsp1_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &periph_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1977,11 +1878,6 @@ static struct clk_branch gcc_blsp2_ahb_clk = { .enable_mask = BIT(15), .hw.init = &(struct clk_init_data){ .name = "gcc_blsp2_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &periph_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2318,11 +2214,6 @@ static struct clk_branch gcc_pdm_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pdm_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &periph_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2353,11 +2244,6 @@ static struct clk_branch gcc_prng_ahb_clk = { .enable_mask = BIT(13), .hw.init = &(struct clk_init_data){ .name = "gcc_prng_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &config_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2370,11 +2256,6 @@ static struct clk_branch gcc_tsif_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_tsif_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &periph_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2422,11 +2303,6 @@ static struct clk_branch gcc_boot_rom_ahb_clk = { .enable_mask = BIT(10), .hw.init = &(struct clk_init_data){ .name = "gcc_boot_rom_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &config_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2520,11 +2396,6 @@ static struct clk_branch gcc_pcie_0_slv_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_0_slv_axi_clk", - .parent_hws = (const struct clk_hw*[]){ - &system_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2537,11 +2408,6 @@ static struct clk_branch gcc_pcie_0_mstr_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_0_mstr_axi_clk", - .parent_hws = (const struct clk_hw*[]){ - &system_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2554,11 +2420,6 @@ static struct clk_branch gcc_pcie_0_cfg_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_0_cfg_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &config_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2606,11 +2467,6 @@ static struct clk_branch gcc_pcie_1_slv_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_1_slv_axi_clk", - .parent_hws = (const struct clk_hw*[]){ - &system_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2623,11 +2479,6 @@ static struct clk_branch gcc_pcie_1_mstr_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_1_mstr_axi_clk", - .parent_hws = (const struct clk_hw*[]){ - &system_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2640,11 +2491,6 @@ static struct clk_branch gcc_pcie_1_cfg_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_1_cfg_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &config_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2692,11 +2538,6 @@ static struct clk_branch gcc_pcie_2_slv_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_2_slv_axi_clk", - .parent_hws = (const struct clk_hw*[]){ - &system_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2709,11 +2550,6 @@ static struct clk_branch gcc_pcie_2_mstr_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_2_mstr_axi_clk", - .parent_hws = (const struct clk_hw*[]){ - &system_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2726,11 +2562,6 @@ static struct clk_branch gcc_pcie_2_cfg_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_2_cfg_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &config_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2778,11 +2609,6 @@ static struct clk_branch gcc_pcie_phy_cfg_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_phy_cfg_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &config_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2829,11 +2655,6 @@ static struct clk_branch gcc_ufs_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_ufs_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &config_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -3060,11 +2881,7 @@ static struct clk_branch gcc_aggre0_snoc_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_aggre0_snoc_axi_clk", - .parent_hws = (const struct clk_hw*[]){ - &system_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -3077,11 +2894,7 @@ static struct clk_branch gcc_aggre0_cnoc_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_aggre0_cnoc_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &config_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -3094,11 +2907,7 @@ static struct clk_branch gcc_smmu_aggre0_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_smmu_aggre0_axi_clk", - .parent_hws = (const struct clk_hw*[]){ - &system_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -3111,11 +2920,7 @@ static struct clk_branch gcc_smmu_aggre0_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_smmu_aggre0_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &config_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -3162,10 +2967,6 @@ static struct clk_branch gcc_dcc_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_dcc_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &config_noc_clk_src.clkr.hw, - }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -3178,10 +2979,6 @@ static struct clk_branch gcc_aggre0_noc_mpu_cfg_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_aggre0_noc_mpu_cfg_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &config_noc_clk_src.clkr.hw, - }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -3194,11 +2991,6 @@ static struct clk_branch gcc_qspi_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_qspi_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &periph_noc_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -3347,10 +3139,6 @@ static struct clk_branch gcc_mss_cfg_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_mss_cfg_ahb_clk", - .parent_hws = (const struct clk_hw*[]){ - &config_noc_clk_src.clkr.hw, - }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -3363,10 +3151,6 @@ static struct clk_branch gcc_mss_mnoc_bimc_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_mss_mnoc_bimc_axi_clk", - .parent_hws = (const struct clk_hw*[]){ - &system_noc_clk_src.clkr.hw, - }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -3379,10 +3163,6 @@ static struct clk_branch gcc_mss_snoc_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_mss_snoc_axi_clk", - .parent_hws = (const struct clk_hw*[]){ - &system_noc_clk_src.clkr.hw, - }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -3395,10 +3175,6 @@ static struct clk_branch gcc_mss_q6_bimc_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_mss_q6_bimc_axi_clk", - .parent_hws = (const struct clk_hw*[]){ - &system_noc_clk_src.clkr.hw, - }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -3495,9 +3271,6 @@ static struct clk_regmap *gcc_msm8996_clocks[] = { [GPLL0] = &gpll0.clkr, [GPLL4_EARLY] = &gpll4_early.clkr, [GPLL4] = &gpll4.clkr, - [SYSTEM_NOC_CLK_SRC] = &system_noc_clk_src.clkr, - [CONFIG_NOC_CLK_SRC] = &config_noc_clk_src.clkr, - [PERIPH_NOC_CLK_SRC] = &periph_noc_clk_src.clkr, [USB30_MASTER_CLK_SRC] = &usb30_master_clk_src.clkr, [USB30_MOCK_UTMI_CLK_SRC] = &usb30_mock_utmi_clk_src.clkr, [USB3_PHY_AUX_CLK_SRC] = &usb3_phy_aux_clk_src.clkr, diff --git a/drivers/clk/qcom/gcc-sa8775p.c b/drivers/clk/qcom/gcc-sa8775p.c index 8171d23c96e64d..a54438205698cd 100644 --- a/drivers/clk/qcom/gcc-sa8775p.c +++ b/drivers/clk/qcom/gcc-sa8775p.c @@ -4305,74 +4305,114 @@ static struct clk_branch gcc_video_axi1_clk = { static struct gdsc pcie_0_gdsc = { .gdscr = 0xa9004, + .collapse_ctrl = 0x4b104, + .collapse_mask = BIT(0), + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .pd = { .name = "pcie_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE | RETAIN_FF_ENABLE | POLL_CFG_GDSCR, }; static struct gdsc pcie_1_gdsc = { .gdscr = 0x77004, + .collapse_ctrl = 0x4b104, + .collapse_mask = BIT(1), + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .pd = { .name = "pcie_1_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE | RETAIN_FF_ENABLE | POLL_CFG_GDSCR, }; static struct gdsc ufs_card_gdsc = { .gdscr = 0x81004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .pd = { .name = "ufs_card_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR, }; static struct gdsc ufs_phy_gdsc = { .gdscr = 0x83004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .pd = { .name = "ufs_phy_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR, }; static struct gdsc usb20_prim_gdsc = { .gdscr = 0x1c004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .pd = { .name = "usb20_prim_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR, }; static struct gdsc usb30_prim_gdsc = { .gdscr = 0x1b004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .pd = { .name = "usb30_prim_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR, }; static struct gdsc usb30_sec_gdsc = { .gdscr = 0x2f004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .pd = { .name = "usb30_sec_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR, }; static struct gdsc emac0_gdsc = { .gdscr = 0xb6004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .pd = { .name = "emac0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR, }; static struct gdsc emac1_gdsc = { .gdscr = 0xb4004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .pd = { .name = "emac1_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR, }; static struct clk_regmap *gcc_sa8775p_clocks[] = { diff --git a/drivers/clk/qcom/gcc-sc7280.c b/drivers/clk/qcom/gcc-sc7280.c index 2b661df5de2660..bc81026292fc9b 100644 --- a/drivers/clk/qcom/gcc-sc7280.c +++ b/drivers/clk/qcom/gcc-sc7280.c @@ -3467,6 +3467,9 @@ static int gcc_sc7280_probe(struct platform_device *pdev) regmap_update_bits(regmap, 0x71004, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x7100C, BIT(13), BIT(13)); + /* FORCE_MEM_CORE_ON for ufs phy ice core clocks */ + qcom_branch_set_force_mem_core(regmap, gcc_ufs_phy_ice_core_clk, true); + ret = qcom_cc_register_rcg_dfs(regmap, gcc_dfs_clocks, ARRAY_SIZE(gcc_dfs_clocks)); if (ret) diff --git a/drivers/clk/qcom/gcc-sc8180x.c b/drivers/clk/qcom/gcc-sc8180x.c index ae21473815596d..ec0c45881c67a7 100644 --- a/drivers/clk/qcom/gcc-sc8180x.c +++ b/drivers/clk/qcom/gcc-sc8180x.c @@ -142,6 +142,23 @@ static struct clk_alpha_pll gpll7 = { }, }; +static struct clk_alpha_pll gpll9 = { + .offset = 0x1c000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TRION], + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(9), + .hw.init = &(const struct clk_init_data) { + .name = "gpll9", + .parent_data = &(const struct clk_parent_data) { + .fw_name = "bi_tcxo", + }, + .num_parents = 1, + .ops = &clk_alpha_pll_fixed_trion_ops, + }, + }, +}; + static const struct parent_map gcc_parent_map_0[] = { { P_BI_TCXO, 0 }, { P_GPLL0_OUT_MAIN, 1 }, @@ -241,7 +258,7 @@ static const struct parent_map gcc_parent_map_7[] = { static const struct clk_parent_data gcc_parents_7[] = { { .fw_name = "bi_tcxo", }, { .hw = &gpll0.clkr.hw }, - { .name = "gppl9" }, + { .hw = &gpll9.clkr.hw }, { .hw = &gpll4.clkr.hw }, { .hw = &gpll0_out_even.clkr.hw }, }; @@ -260,28 +277,6 @@ static const struct clk_parent_data gcc_parents_8[] = { { .hw = &gpll0_out_even.clkr.hw }, }; -static const struct freq_tbl ftbl_gcc_cpuss_ahb_clk_src[] = { - F(19200000, P_BI_TCXO, 1, 0, 0), - F(50000000, P_GPLL0_OUT_MAIN, 12, 0, 0), - F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), - { } -}; - -static struct clk_rcg2 gcc_cpuss_ahb_clk_src = { - .cmd_rcgr = 0x48014, - .mnd_width = 0, - .hid_width = 5, - .parent_map = gcc_parent_map_0, - .freq_tbl = ftbl_gcc_cpuss_ahb_clk_src, - .clkr.hw.init = &(struct clk_init_data){ - .name = "gcc_cpuss_ahb_clk_src", - .parent_data = gcc_parents_0, - .num_parents = ARRAY_SIZE(gcc_parents_0), - .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, - }, -}; - static const struct freq_tbl ftbl_gcc_emac_ptp_clk_src[] = { F(19200000, P_BI_TCXO, 1, 0, 0), F(50000000, P_GPLL0_OUT_EVEN, 6, 0, 0), @@ -916,7 +911,7 @@ static const struct freq_tbl ftbl_gcc_sdcc2_apps_clk_src[] = { F(25000000, P_GPLL0_OUT_MAIN, 12, 1, 2), F(50000000, P_GPLL0_OUT_MAIN, 12, 0, 0), F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), - F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + F(202000000, P_GPLL9_OUT_MAIN, 4, 0, 0), { } }; @@ -939,9 +934,8 @@ static const struct freq_tbl ftbl_gcc_sdcc4_apps_clk_src[] = { F(400000, P_BI_TCXO, 12, 1, 4), F(9600000, P_BI_TCXO, 2, 0, 0), F(19200000, P_BI_TCXO, 1, 0, 0), - F(37500000, P_GPLL0_OUT_MAIN, 16, 0, 0), F(50000000, P_GPLL0_OUT_MAIN, 12, 0, 0), - F(75000000, P_GPLL0_OUT_MAIN, 8, 0, 0), + F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), { } }; @@ -1599,25 +1593,6 @@ static struct clk_branch gcc_cfg_noc_usb3_sec_axi_clk = { }, }; -/* For CPUSS functionality the AHB clock needs to be left enabled */ -static struct clk_branch gcc_cpuss_ahb_clk = { - .halt_reg = 0x48000, - .halt_check = BRANCH_HALT_VOTED, - .clkr = { - .enable_reg = 0x52004, - .enable_mask = BIT(21), - .hw.init = &(struct clk_init_data){ - .name = "gcc_cpuss_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ - &gcc_cpuss_ahb_clk_src.clkr.hw - }, - .num_parents = 1, - .flags = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT, - .ops = &clk_branch2_ops, - }, - }, -}; - static struct clk_branch gcc_cpuss_rbcpr_clk = { .halt_reg = 0x48008, .halt_check = BRANCH_HALT, @@ -3150,25 +3125,6 @@ static struct clk_branch gcc_sdcc4_apps_clk = { }, }; -/* For CPUSS functionality the SYS NOC clock needs to be left enabled */ -static struct clk_branch gcc_sys_noc_cpuss_ahb_clk = { - .halt_reg = 0x4819c, - .halt_check = BRANCH_HALT_VOTED, - .clkr = { - .enable_reg = 0x52004, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "gcc_sys_noc_cpuss_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ - &gcc_cpuss_ahb_clk_src.clkr.hw - }, - .num_parents = 1, - .flags = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT, - .ops = &clk_branch2_ops, - }, - }, -}; - static struct clk_branch gcc_tsif_ahb_clk = { .halt_reg = 0x36004, .halt_check = BRANCH_HALT, @@ -4258,8 +4214,6 @@ static struct clk_regmap *gcc_sc8180x_clocks[] = { [GCC_CFG_NOC_USB3_MP_AXI_CLK] = &gcc_cfg_noc_usb3_mp_axi_clk.clkr, [GCC_CFG_NOC_USB3_PRIM_AXI_CLK] = &gcc_cfg_noc_usb3_prim_axi_clk.clkr, [GCC_CFG_NOC_USB3_SEC_AXI_CLK] = &gcc_cfg_noc_usb3_sec_axi_clk.clkr, - [GCC_CPUSS_AHB_CLK] = &gcc_cpuss_ahb_clk.clkr, - [GCC_CPUSS_AHB_CLK_SRC] = &gcc_cpuss_ahb_clk_src.clkr, [GCC_CPUSS_RBCPR_CLK] = &gcc_cpuss_rbcpr_clk.clkr, [GCC_DDRSS_GPU_AXI_CLK] = &gcc_ddrss_gpu_axi_clk.clkr, [GCC_DISP_HF_AXI_CLK] = &gcc_disp_hf_axi_clk.clkr, @@ -4396,7 +4350,6 @@ static struct clk_regmap *gcc_sc8180x_clocks[] = { [GCC_SDCC4_AHB_CLK] = &gcc_sdcc4_ahb_clk.clkr, [GCC_SDCC4_APPS_CLK] = &gcc_sdcc4_apps_clk.clkr, [GCC_SDCC4_APPS_CLK_SRC] = &gcc_sdcc4_apps_clk_src.clkr, - [GCC_SYS_NOC_CPUSS_AHB_CLK] = &gcc_sys_noc_cpuss_ahb_clk.clkr, [GCC_TSIF_AHB_CLK] = &gcc_tsif_ahb_clk.clkr, [GCC_TSIF_INACTIVITY_TIMERS_CLK] = &gcc_tsif_inactivity_timers_clk.clkr, [GCC_TSIF_REF_CLK] = &gcc_tsif_ref_clk.clkr, @@ -4483,6 +4436,7 @@ static struct clk_regmap *gcc_sc8180x_clocks[] = { [GPLL1] = &gpll1.clkr, [GPLL4] = &gpll4.clkr, [GPLL7] = &gpll7.clkr, + [GPLL9] = &gpll9.clkr, }; static const struct qcom_reset_map gcc_sc8180x_resets[] = { diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c index 725cd52d2398ed..ea4c3bf4fb9bf7 100644 --- a/drivers/clk/qcom/gcc-sdm845.c +++ b/drivers/clk/qcom/gcc-sdm845.c @@ -4037,3 +4037,4 @@ module_exit(gcc_sdm845_exit); MODULE_DESCRIPTION("QTI GCC SDM845 Driver"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("platform:gcc-sdm845"); +MODULE_SOFTDEP("pre: rpmhpd"); diff --git a/drivers/clk/qcom/gcc-sm6350.c b/drivers/clk/qcom/gcc-sm6350.c index cf4a7b6e0b23ad..0559a33faf00e6 100644 --- a/drivers/clk/qcom/gcc-sm6350.c +++ b/drivers/clk/qcom/gcc-sm6350.c @@ -100,8 +100,8 @@ static struct clk_alpha_pll gpll6 = { .enable_mask = BIT(6), .hw.init = &(struct clk_init_data){ .name = "gpll6", - .parent_hws = (const struct clk_hw*[]){ - &gpll0.clkr.hw, + .parent_data = &(const struct clk_parent_data){ + .fw_name = "bi_tcxo", }, .num_parents = 1, .ops = &clk_alpha_pll_fixed_fabia_ops, @@ -124,7 +124,7 @@ static struct clk_alpha_pll_postdiv gpll6_out_even = { .clkr.hw.init = &(struct clk_init_data){ .name = "gpll6_out_even", .parent_hws = (const struct clk_hw*[]){ - &gpll0.clkr.hw, + &gpll6.clkr.hw, }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_fabia_ops, @@ -139,8 +139,8 @@ static struct clk_alpha_pll gpll7 = { .enable_mask = BIT(7), .hw.init = &(struct clk_init_data){ .name = "gpll7", - .parent_hws = (const struct clk_hw*[]){ - &gpll0.clkr.hw, + .parent_data = &(const struct clk_parent_data){ + .fw_name = "bi_tcxo", }, .num_parents = 1, .ops = &clk_alpha_pll_fixed_fabia_ops, diff --git a/drivers/clk/qcom/gcc-sm8150.c b/drivers/clk/qcom/gcc-sm8150.c index 41ab210875fb24..05d115c52dfebb 100644 --- a/drivers/clk/qcom/gcc-sm8150.c +++ b/drivers/clk/qcom/gcc-sm8150.c @@ -774,7 +774,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .name = "gcc_sdcc2_apps_clk_src", .parent_data = gcc_parents_6, .num_parents = ARRAY_SIZE(gcc_parents_6), - .flags = CLK_SET_RATE_PARENT, + .flags = CLK_OPS_PARENT_ENABLE, .ops = &clk_rcg2_floor_ops, }, }; diff --git a/drivers/clk/qcom/gcc-sm8250.c b/drivers/clk/qcom/gcc-sm8250.c index c6c5261264f118..272da807c6945d 100644 --- a/drivers/clk/qcom/gcc-sm8250.c +++ b/drivers/clk/qcom/gcc-sm8250.c @@ -3226,7 +3226,7 @@ static struct gdsc pcie_0_gdsc = { .pd = { .name = "pcie_0_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc pcie_1_gdsc = { @@ -3234,7 +3234,7 @@ static struct gdsc pcie_1_gdsc = { .pd = { .name = "pcie_1_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc pcie_2_gdsc = { @@ -3242,7 +3242,7 @@ static struct gdsc pcie_2_gdsc = { .pd = { .name = "pcie_2_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc ufs_card_gdsc = { diff --git a/drivers/clk/qcom/gcc-sm8450.c b/drivers/clk/qcom/gcc-sm8450.c index 56354298255160..4c55df89ddca7d 100644 --- a/drivers/clk/qcom/gcc-sm8450.c +++ b/drivers/clk/qcom/gcc-sm8450.c @@ -2974,7 +2974,7 @@ static struct gdsc pcie_0_gdsc = { .pd = { .name = "pcie_0_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc pcie_1_gdsc = { @@ -2982,7 +2982,7 @@ static struct gdsc pcie_1_gdsc = { .pd = { .name = "pcie_1_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc ufs_phy_gdsc = { diff --git a/drivers/clk/qcom/gcc-sm8550.c b/drivers/clk/qcom/gcc-sm8550.c index 586126c4dd907c..eb3765c57b6502 100644 --- a/drivers/clk/qcom/gcc-sm8550.c +++ b/drivers/clk/qcom/gcc-sm8550.c @@ -401,7 +401,7 @@ static struct clk_rcg2 gcc_gp1_clk_src = { .parent_data = gcc_parent_data_1, .num_parents = ARRAY_SIZE(gcc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -416,7 +416,7 @@ static struct clk_rcg2 gcc_gp2_clk_src = { .parent_data = gcc_parent_data_1, .num_parents = ARRAY_SIZE(gcc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -431,7 +431,7 @@ static struct clk_rcg2 gcc_gp3_clk_src = { .parent_data = gcc_parent_data_1, .num_parents = ARRAY_SIZE(gcc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -451,7 +451,7 @@ static struct clk_rcg2 gcc_pcie_0_aux_clk_src = { .parent_data = gcc_parent_data_2, .num_parents = ARRAY_SIZE(gcc_parent_data_2), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -471,7 +471,7 @@ static struct clk_rcg2 gcc_pcie_0_phy_rchng_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -486,7 +486,7 @@ static struct clk_rcg2 gcc_pcie_1_aux_clk_src = { .parent_data = gcc_parent_data_2, .num_parents = ARRAY_SIZE(gcc_parent_data_2), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -501,7 +501,7 @@ static struct clk_rcg2 gcc_pcie_1_phy_rchng_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -521,7 +521,7 @@ static struct clk_rcg2 gcc_pdm2_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1025,7 +1025,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .parent_data = gcc_parent_data_9, .num_parents = ARRAY_SIZE(gcc_parent_data_9), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1048,7 +1048,7 @@ static struct clk_rcg2 gcc_sdcc4_apps_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1071,7 +1071,7 @@ static struct clk_rcg2 gcc_ufs_phy_axi_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1093,7 +1093,7 @@ static struct clk_rcg2 gcc_ufs_phy_ice_core_clk_src = { .parent_data = gcc_parent_data_3, .num_parents = ARRAY_SIZE(gcc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1114,7 +1114,7 @@ static struct clk_rcg2 gcc_ufs_phy_phy_aux_clk_src = { .parent_data = gcc_parent_data_4, .num_parents = ARRAY_SIZE(gcc_parent_data_4), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1136,7 +1136,7 @@ static struct clk_rcg2 gcc_ufs_phy_unipro_core_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1159,7 +1159,7 @@ static struct clk_rcg2 gcc_usb30_prim_master_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_no_init_park_ops, }, }; @@ -1174,7 +1174,7 @@ static struct clk_rcg2 gcc_usb30_prim_mock_utmi_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1189,7 +1189,7 @@ static struct clk_rcg2 gcc_usb3_prim_phy_aux_clk_src = { .parent_data = gcc_parent_data_2, .num_parents = ARRAY_SIZE(gcc_parent_data_2), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -2998,38 +2998,46 @@ static struct clk_branch gcc_video_axi1_clk = { static struct gdsc pcie_0_gdsc = { .gdscr = 0x6b004, + .collapse_ctrl = 0x52020, + .collapse_mask = BIT(0), .pd = { .name = "pcie_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = POLL_CFG_GDSCR, + .flags = VOTABLE | POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; static struct gdsc pcie_0_phy_gdsc = { .gdscr = 0x6c000, + .collapse_ctrl = 0x52020, + .collapse_mask = BIT(3), .pd = { .name = "pcie_0_phy_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = POLL_CFG_GDSCR, + .flags = VOTABLE | POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; static struct gdsc pcie_1_gdsc = { .gdscr = 0x8d004, + .collapse_ctrl = 0x52020, + .collapse_mask = BIT(1), .pd = { .name = "pcie_1_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = POLL_CFG_GDSCR, + .flags = VOTABLE | POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; static struct gdsc pcie_1_phy_gdsc = { .gdscr = 0x8e000, + .collapse_ctrl = 0x52020, + .collapse_mask = BIT(4), .pd = { .name = "pcie_1_phy_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = POLL_CFG_GDSCR, + .flags = VOTABLE | POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; static struct gdsc ufs_phy_gdsc = { @@ -3038,7 +3046,7 @@ static struct gdsc ufs_phy_gdsc = { .name = "ufs_phy_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = POLL_CFG_GDSCR, + .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; static struct gdsc ufs_mem_phy_gdsc = { @@ -3047,7 +3055,7 @@ static struct gdsc ufs_mem_phy_gdsc = { .name = "ufs_mem_phy_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = POLL_CFG_GDSCR, + .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; static struct gdsc usb30_prim_gdsc = { @@ -3056,7 +3064,7 @@ static struct gdsc usb30_prim_gdsc = { .name = "usb30_prim_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = POLL_CFG_GDSCR, + .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; static struct gdsc usb3_phy_gdsc = { @@ -3065,7 +3073,7 @@ static struct gdsc usb3_phy_gdsc = { .name = "usb3_phy_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = POLL_CFG_GDSCR, + .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; static struct clk_regmap *gcc_sm8550_clocks[] = { diff --git a/drivers/clk/qcom/gpucc-sa8775p.c b/drivers/clk/qcom/gpucc-sa8775p.c index 26ecfa63be1939..0d9a8379efaa83 100644 --- a/drivers/clk/qcom/gpucc-sa8775p.c +++ b/drivers/clk/qcom/gpucc-sa8775p.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2021-2022, Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2021-2022, 2024, Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2023, Linaro Limited */ @@ -161,7 +161,7 @@ static struct clk_rcg2 gpu_cc_ff_clk_src = { .name = "gpu_cc_ff_clk_src", .parent_data = gpu_cc_parent_data_0, .num_parents = ARRAY_SIZE(gpu_cc_parent_data_0), - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -181,7 +181,7 @@ static struct clk_rcg2 gpu_cc_gmu_clk_src = { .parent_data = gpu_cc_parent_data_1, .num_parents = ARRAY_SIZE(gpu_cc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -200,7 +200,7 @@ static struct clk_rcg2 gpu_cc_hub_clk_src = { .name = "gpu_cc_hub_clk_src", .parent_data = gpu_cc_parent_data_2, .num_parents = ARRAY_SIZE(gpu_cc_parent_data_2), - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -280,7 +280,7 @@ static struct clk_branch gpu_cc_ahb_clk = { &gpu_cc_hub_ahb_div_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -294,8 +294,7 @@ static struct clk_branch gpu_cc_cb_clk = { .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data){ .name = "gpu_cc_cb_clk", - .flags = CLK_IS_CRITICAL, - .ops = &clk_branch2_ops, + .ops = &clk_branch2_aon_ops, }, }, }; @@ -312,7 +311,7 @@ static struct clk_branch gpu_cc_crc_ahb_clk = { &gpu_cc_hub_ahb_div_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -330,7 +329,7 @@ static struct clk_branch gpu_cc_cx_ff_clk = { &gpu_cc_ff_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -348,7 +347,7 @@ static struct clk_branch gpu_cc_cx_gmu_clk = { &gpu_cc_gmu_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_aon_ops, }, }, @@ -362,7 +361,6 @@ static struct clk_branch gpu_cc_cx_snoc_dvm_clk = { .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data){ .name = "gpu_cc_cx_snoc_dvm_clk", - .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -380,7 +378,7 @@ static struct clk_branch gpu_cc_cxo_aon_clk = { &gpu_cc_xo_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -398,7 +396,7 @@ static struct clk_branch gpu_cc_cxo_clk = { &gpu_cc_xo_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -416,7 +414,7 @@ static struct clk_branch gpu_cc_demet_clk = { &gpu_cc_demet_div_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_aon_ops, }, }, @@ -430,7 +428,6 @@ static struct clk_branch gpu_cc_hlos1_vote_gpu_smmu_clk = { .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data){ .name = "gpu_cc_hlos1_vote_gpu_smmu_clk", - .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -448,7 +445,7 @@ static struct clk_branch gpu_cc_hub_aon_clk = { &gpu_cc_hub_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_aon_ops, }, }, @@ -466,7 +463,7 @@ static struct clk_branch gpu_cc_hub_cx_int_clk = { &gpu_cc_hub_cx_int_div_clk_src.clkr.hw, }, .num_parents = 1, - .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_aon_ops, }, }, @@ -480,7 +477,6 @@ static struct clk_branch gpu_cc_memnoc_gfx_clk = { .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data){ .name = "gpu_cc_memnoc_gfx_clk", - .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -494,7 +490,6 @@ static struct clk_branch gpu_cc_sleep_clk = { .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data){ .name = "gpu_cc_sleep_clk", - .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -528,16 +523,22 @@ static struct clk_regmap *gpu_cc_sa8775p_clocks[] = { static struct gdsc cx_gdsc = { .gdscr = 0x9108, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .gds_hw_ctrl = 0x953c, .pd = { .name = "cx_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = VOTABLE | RETAIN_FF_ENABLE | ALWAYS_ON, + .flags = VOTABLE | RETAIN_FF_ENABLE, }; static struct gdsc gx_gdsc = { .gdscr = 0x905c, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .pd = { .name = "gx_gdsc", .power_on = gdsc_gx_do_nothing_enable, diff --git a/drivers/clk/qcom/gpucc-sm8150.c b/drivers/clk/qcom/gpucc-sm8150.c index 8422fd0474932d..c89a5b59ddb7c2 100644 --- a/drivers/clk/qcom/gpucc-sm8150.c +++ b/drivers/clk/qcom/gpucc-sm8150.c @@ -37,8 +37,8 @@ static struct alpha_pll_config gpu_cc_pll1_config = { .config_ctl_hi_val = 0x00002267, .config_ctl_hi1_val = 0x00000024, .test_ctl_val = 0x00000000, - .test_ctl_hi_val = 0x00000002, - .test_ctl_hi1_val = 0x00000000, + .test_ctl_hi_val = 0x00000000, + .test_ctl_hi1_val = 0x00000020, .user_ctl_val = 0x00000000, .user_ctl_hi_val = 0x00000805, .user_ctl_hi1_val = 0x000000d0, diff --git a/drivers/clk/qcom/gpucc-sm8350.c b/drivers/clk/qcom/gpucc-sm8350.c index 8dc54dff983f3a..33c4fb8891caa3 100644 --- a/drivers/clk/qcom/gpucc-sm8350.c +++ b/drivers/clk/qcom/gpucc-sm8350.c @@ -2,6 +2,7 @@ /* * Copyright (c) 2019-2020, The Linux Foundation. All rights reserved. * Copyright (c) 2022, Linaro Limited + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. */ #include @@ -147,7 +148,7 @@ static struct clk_rcg2 gpu_cc_gmu_clk_src = { .parent_data = gpu_cc_parent_data_0, .num_parents = ARRAY_SIZE(gpu_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -169,7 +170,7 @@ static struct clk_rcg2 gpu_cc_hub_clk_src = { .parent_data = gpu_cc_parent_data_1, .num_parents = ARRAY_SIZE(gpu_cc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; diff --git a/drivers/clk/qcom/kpss-xcc.c b/drivers/clk/qcom/kpss-xcc.c index 97358c98c6c98e..d8c1f2b41eeb39 100644 --- a/drivers/clk/qcom/kpss-xcc.c +++ b/drivers/clk/qcom/kpss-xcc.c @@ -63,9 +63,7 @@ static int kpss_xcc_driver_probe(struct platform_device *pdev) if (IS_ERR(hw)) return PTR_ERR(hw); - of_clk_add_hw_provider(dev->of_node, of_clk_hw_simple_get, hw); - - return 0; + return of_clk_add_hw_provider(dev->of_node, of_clk_hw_simple_get, hw); } static struct platform_driver kpss_xcc_driver = { diff --git a/drivers/clk/qcom/mmcc-apq8084.c b/drivers/clk/qcom/mmcc-apq8084.c index 02fc21208dd14b..c89700ab93f9c6 100644 --- a/drivers/clk/qcom/mmcc-apq8084.c +++ b/drivers/clk/qcom/mmcc-apq8084.c @@ -348,6 +348,7 @@ static struct freq_tbl ftbl_mmss_axi_clk[] = { F(333430000, P_MMPLL1, 3.5, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), F(466800000, P_MMPLL1, 2.5, 0, 0), + { } }; static struct clk_rcg2 mmss_axi_clk_src = { @@ -372,6 +373,7 @@ static struct freq_tbl ftbl_ocmemnoc_clk[] = { F(150000000, P_GPLL0, 4, 0, 0), F(228570000, P_MMPLL0, 3.5, 0, 0), F(320000000, P_MMPLL0, 2.5, 0, 0), + { } }; static struct clk_rcg2 ocmemnoc_clk_src = { diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c index 1f3bd302fe6ed4..6df22a67f02d3e 100644 --- a/drivers/clk/qcom/mmcc-msm8974.c +++ b/drivers/clk/qcom/mmcc-msm8974.c @@ -290,6 +290,7 @@ static struct freq_tbl ftbl_mmss_axi_clk[] = { F(291750000, P_MMPLL1, 4, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), F(466800000, P_MMPLL1, 2.5, 0, 0), + { } }; static struct clk_rcg2 mmss_axi_clk_src = { @@ -314,6 +315,7 @@ static struct freq_tbl ftbl_ocmemnoc_clk[] = { F(150000000, P_GPLL0, 4, 0, 0), F(291750000, P_MMPLL1, 4, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), + { } }; static struct clk_rcg2 ocmemnoc_clk_src = { diff --git a/drivers/clk/qcom/mmcc-msm8998.c b/drivers/clk/qcom/mmcc-msm8998.c index a023c4374be96a..275fb3b71ede4c 100644 --- a/drivers/clk/qcom/mmcc-msm8998.c +++ b/drivers/clk/qcom/mmcc-msm8998.c @@ -2439,6 +2439,7 @@ static struct clk_branch fd_ahb_clk = { static struct clk_branch mnoc_ahb_clk = { .halt_reg = 0x5024, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x5024, .enable_mask = BIT(0), @@ -2454,6 +2455,7 @@ static struct clk_branch mnoc_ahb_clk = { static struct clk_branch bimc_smmu_ahb_clk = { .halt_reg = 0xe004, + .halt_check = BRANCH_HALT_SKIP, .hwcg_reg = 0xe004, .hwcg_bit = 1, .clkr = { @@ -2471,6 +2473,7 @@ static struct clk_branch bimc_smmu_ahb_clk = { static struct clk_branch bimc_smmu_axi_clk = { .halt_reg = 0xe008, + .halt_check = BRANCH_HALT_SKIP, .hwcg_reg = 0xe008, .hwcg_bit = 1, .clkr = { @@ -2532,6 +2535,8 @@ static struct clk_branch vmem_ahb_clk = { static struct gdsc video_top_gdsc = { .gdscr = 0x1024, + .cxcs = (unsigned int []){ 0x1028, 0x1034, 0x1038 }, + .cxc_count = 3, .pd = { .name = "video_top", }, @@ -2540,20 +2545,26 @@ static struct gdsc video_top_gdsc = { static struct gdsc video_subcore0_gdsc = { .gdscr = 0x1040, + .cxcs = (unsigned int []){ 0x1048 }, + .cxc_count = 1, .pd = { .name = "video_subcore0", }, .parent = &video_top_gdsc.pd, .pwrsts = PWRSTS_OFF_ON, + .flags = HW_CTRL, }; static struct gdsc video_subcore1_gdsc = { .gdscr = 0x1044, + .cxcs = (unsigned int []){ 0x104c }, + .cxc_count = 1, .pd = { .name = "video_subcore1", }, .parent = &video_top_gdsc.pd, .pwrsts = PWRSTS_OFF_ON, + .flags = HW_CTRL, }; static struct gdsc mdss_gdsc = { @@ -2607,11 +2618,13 @@ static struct gdsc camss_cpp_gdsc = { static struct gdsc bimc_smmu_gdsc = { .gdscr = 0xe020, .gds_hw_ctrl = 0xe024, + .cxcs = (unsigned int []){ 0xe008 }, + .cxc_count = 1, .pd = { .name = "bimc_smmu", }, .pwrsts = PWRSTS_OFF_ON, - .flags = HW_CTRL | ALWAYS_ON, + .flags = VOTABLE, }; static struct clk_regmap *mmcc_msm8998_clocks[] = { diff --git a/drivers/clk/qcom/reset.c b/drivers/clk/qcom/reset.c index e45e32804d2c75..d96c96a9089f40 100644 --- a/drivers/clk/qcom/reset.c +++ b/drivers/clk/qcom/reset.c @@ -22,8 +22,8 @@ static int qcom_reset(struct reset_controller_dev *rcdev, unsigned long id) return 0; } -static int -qcom_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) +static int qcom_reset_set_assert(struct reset_controller_dev *rcdev, + unsigned long id, bool assert) { struct qcom_reset_controller *rst; const struct qcom_reset_map *map; @@ -33,21 +33,22 @@ qcom_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) map = &rst->reset_map[id]; mask = map->bitmask ? map->bitmask : BIT(map->bit); - return regmap_update_bits(rst->regmap, map->reg, mask, mask); + regmap_update_bits(rst->regmap, map->reg, mask, assert ? mask : 0); + + /* Read back the register to ensure write completion, ignore the value */ + regmap_read(rst->regmap, map->reg, &mask); + + return 0; } -static int -qcom_reset_deassert(struct reset_controller_dev *rcdev, unsigned long id) +static int qcom_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) { - struct qcom_reset_controller *rst; - const struct qcom_reset_map *map; - u32 mask; - - rst = to_qcom_reset_controller(rcdev); - map = &rst->reset_map[id]; - mask = map->bitmask ? map->bitmask : BIT(map->bit); + return qcom_reset_set_assert(rcdev, id, true); +} - return regmap_update_bits(rst->regmap, map->reg, mask, 0); +static int qcom_reset_deassert(struct reset_controller_dev *rcdev, unsigned long id) +{ + return qcom_reset_set_assert(rcdev, id, false); } const struct reset_control_ops qcom_reset_ops = { diff --git a/drivers/clk/qcom/videocc-sm8150.c b/drivers/clk/qcom/videocc-sm8150.c index 1afdbe4a249d62..52a9a453a14326 100644 --- a/drivers/clk/qcom/videocc-sm8150.c +++ b/drivers/clk/qcom/videocc-sm8150.c @@ -33,6 +33,7 @@ static struct alpha_pll_config video_pll0_config = { .config_ctl_val = 0x20485699, .config_ctl_hi_val = 0x00002267, .config_ctl_hi1_val = 0x00000024, + .test_ctl_hi1_val = 0x00000020, .user_ctl_val = 0x00000000, .user_ctl_hi_val = 0x00000805, .user_ctl_hi1_val = 0x000000D0, @@ -214,6 +215,10 @@ static const struct regmap_config video_cc_sm8150_regmap_config = { static const struct qcom_reset_map video_cc_sm8150_resets[] = { [VIDEO_CC_MVSC_CORE_CLK_BCR] = { 0x850, 2 }, + [VIDEO_CC_INTERFACE_BCR] = { 0x8f0 }, + [VIDEO_CC_MVS0_BCR] = { 0x870 }, + [VIDEO_CC_MVS1_BCR] = { 0x8b0 }, + [VIDEO_CC_MVSC_BCR] = { 0x810 }, }; static const struct qcom_cc_desc video_cc_sm8150_desc = { diff --git a/drivers/clk/ralink/clk-mtmips.c b/drivers/clk/ralink/clk-mtmips.c index 1e7991439527a8..50a443bf79ecd3 100644 --- a/drivers/clk/ralink/clk-mtmips.c +++ b/drivers/clk/ralink/clk-mtmips.c @@ -821,6 +821,10 @@ static const struct mtmips_clk_data mt76x8_clk_data = { }; static const struct of_device_id mtmips_of_match[] = { + { + .compatible = "ralink,rt2880-reset", + .data = NULL, + }, { .compatible = "ralink,rt2880-sysc", .data = &rt2880_clk_data, @@ -1088,25 +1092,11 @@ static int mtmips_clk_probe(struct platform_device *pdev) return 0; } -static const struct of_device_id mtmips_clk_of_match[] = { - { .compatible = "ralink,rt2880-reset" }, - { .compatible = "ralink,rt2880-sysc" }, - { .compatible = "ralink,rt3050-sysc" }, - { .compatible = "ralink,rt3052-sysc" }, - { .compatible = "ralink,rt3352-sysc" }, - { .compatible = "ralink,rt3883-sysc" }, - { .compatible = "ralink,rt5350-sysc" }, - { .compatible = "ralink,mt7620-sysc" }, - { .compatible = "ralink,mt7628-sysc" }, - { .compatible = "ralink,mt7688-sysc" }, - {} -}; - static struct platform_driver mtmips_clk_driver = { .probe = mtmips_clk_probe, .driver = { .name = "mtmips-clk", - .of_match_table = mtmips_clk_of_match, + .of_match_table = mtmips_of_match, }, }; diff --git a/drivers/clk/renesas/r8a779a0-cpg-mssr.c b/drivers/clk/renesas/r8a779a0-cpg-mssr.c index 4c2872f45387ff..ff3f85e906fe17 100644 --- a/drivers/clk/renesas/r8a779a0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779a0-cpg-mssr.c @@ -139,7 +139,7 @@ static const struct mssr_mod_clk r8a779a0_mod_clks[] __initconst = { DEF_MOD("avb3", 214, R8A779A0_CLK_S3D2), DEF_MOD("avb4", 215, R8A779A0_CLK_S3D2), DEF_MOD("avb5", 216, R8A779A0_CLK_S3D2), - DEF_MOD("canfd0", 328, R8A779A0_CLK_CANFD), + DEF_MOD("canfd0", 328, R8A779A0_CLK_S3D2), DEF_MOD("csi40", 331, R8A779A0_CLK_CSI0), DEF_MOD("csi41", 400, R8A779A0_CLK_CSI0), DEF_MOD("csi42", 401, R8A779A0_CLK_CSI0), diff --git a/drivers/clk/renesas/r8a779f0-cpg-mssr.c b/drivers/clk/renesas/r8a779f0-cpg-mssr.c index f721835c7e2124..cc06127406ab57 100644 --- a/drivers/clk/renesas/r8a779f0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779f0-cpg-mssr.c @@ -161,7 +161,7 @@ static const struct mssr_mod_clk r8a779f0_mod_clks[] __initconst = { DEF_MOD("cmt1", 911, R8A779F0_CLK_R), DEF_MOD("cmt2", 912, R8A779F0_CLK_R), DEF_MOD("cmt3", 913, R8A779F0_CLK_R), - DEF_MOD("pfc0", 915, R8A779F0_CLK_CL16M), + DEF_MOD("pfc0", 915, R8A779F0_CLK_CPEX), DEF_MOD("tsc", 919, R8A779F0_CLK_CL16M), DEF_MOD("rswitch2", 1505, R8A779F0_CLK_RSW2), DEF_MOD("ether-serdes", 1506, R8A779F0_CLK_S0D2_HSC), diff --git a/drivers/clk/renesas/r8a779g0-cpg-mssr.c b/drivers/clk/renesas/r8a779g0-cpg-mssr.c index 7cc580d6736261..7999faa9a921be 100644 --- a/drivers/clk/renesas/r8a779g0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779g0-cpg-mssr.c @@ -22,7 +22,7 @@ enum clk_ids { /* Core Clock Outputs exported to DT */ - LAST_DT_CORE_CLK = R8A779G0_CLK_R, + LAST_DT_CORE_CLK = R8A779G0_CLK_CP, /* External Input Clocks */ CLK_EXTAL, @@ -141,6 +141,7 @@ static const struct cpg_core_clk r8a779g0_core_clks[] __initconst = { DEF_FIXED("svd2_vip", R8A779G0_CLK_SVD2_VIP, CLK_SV_VIP, 2, 1), DEF_FIXED("cbfusa", R8A779G0_CLK_CBFUSA, CLK_EXTAL, 2, 1), DEF_FIXED("cpex", R8A779G0_CLK_CPEX, CLK_EXTAL, 2, 1), + DEF_FIXED("cp", R8A779G0_CLK_CP, CLK_EXTAL, 2, 1), DEF_FIXED("viobus", R8A779G0_CLK_VIOBUS, CLK_VIO, 1, 1), DEF_FIXED("viobusd2", R8A779G0_CLK_VIOBUSD2, CLK_VIO, 2, 1), DEF_FIXED("vcbus", R8A779G0_CLK_VCBUS, CLK_VC, 1, 1), @@ -230,10 +231,10 @@ static const struct mssr_mod_clk r8a779g0_mod_clks[] __initconst = { DEF_MOD("cmt1", 911, R8A779G0_CLK_R), DEF_MOD("cmt2", 912, R8A779G0_CLK_R), DEF_MOD("cmt3", 913, R8A779G0_CLK_R), - DEF_MOD("pfc0", 915, R8A779G0_CLK_CL16M), - DEF_MOD("pfc1", 916, R8A779G0_CLK_CL16M), - DEF_MOD("pfc2", 917, R8A779G0_CLK_CL16M), - DEF_MOD("pfc3", 918, R8A779G0_CLK_CL16M), + DEF_MOD("pfc0", 915, R8A779G0_CLK_CP), + DEF_MOD("pfc1", 916, R8A779G0_CLK_CP), + DEF_MOD("pfc2", 917, R8A779G0_CLK_CP), + DEF_MOD("pfc3", 918, R8A779G0_CLK_CP), DEF_MOD("tsc", 919, R8A779G0_CLK_CL16M), DEF_MOD("ssiu", 2926, R8A779G0_CLK_S0D6_PER), DEF_MOD("ssi", 2927, R8A779G0_CLK_S0D6_PER), diff --git a/drivers/clk/renesas/r9a07g043-cpg.c b/drivers/clk/renesas/r9a07g043-cpg.c index 1a7a6d60aca44b..6c6bc79b2e9cec 100644 --- a/drivers/clk/renesas/r9a07g043-cpg.c +++ b/drivers/clk/renesas/r9a07g043-cpg.c @@ -250,6 +250,10 @@ static struct rzg2l_mod_clk r9a07g043_mod_clks[] = { 0x5a8, 1), DEF_MOD("tsu_pclk", R9A07G043_TSU_PCLK, R9A07G043_CLK_TSU, 0x5ac, 0), +#ifdef CONFIG_RISCV + DEF_MOD("nceplic_aclk", R9A07G043_NCEPLIC_ACLK, R9A07G043_CLK_P1, + 0x608, 0), +#endif }; static struct rzg2l_reset r9a07g043_resets[] = { @@ -303,6 +307,10 @@ static struct rzg2l_reset r9a07g043_resets[] = { DEF_RST(R9A07G043_ADC_PRESETN, 0x8a8, 0), DEF_RST(R9A07G043_ADC_ADRST_N, 0x8a8, 1), DEF_RST(R9A07G043_TSU_PRESETN, 0x8ac, 0), +#ifdef CONFIG_RISCV + DEF_RST(R9A07G043_NCEPLIC_ARESETN, 0x908, 0), +#endif + }; static const unsigned int r9a07g043_crit_mod_clks[] __initconst = { @@ -312,6 +320,7 @@ static const unsigned int r9a07g043_crit_mod_clks[] __initconst = { #endif #ifdef CONFIG_RISCV MOD_CLK_BASE + R9A07G043_IAX45_CLK, + MOD_CLK_BASE + R9A07G043_NCEPLIC_ACLK, #endif MOD_CLK_BASE + R9A07G043_DMAC_ACLK, }; diff --git a/drivers/clk/renesas/rcar-cpg-lib.c b/drivers/clk/renesas/rcar-cpg-lib.c index e2e0447de1901d..5a15f8788b9227 100644 --- a/drivers/clk/renesas/rcar-cpg-lib.c +++ b/drivers/clk/renesas/rcar-cpg-lib.c @@ -70,8 +70,21 @@ void cpg_simple_notifier_register(struct raw_notifier_head *notifiers, #define STPnHCK BIT(9 - SDnSRCFC_SHIFT) static const struct clk_div_table cpg_sdh_div_table[] = { + /* + * These values are recommended by the datasheet. Because they come + * first, Linux will only use these. + */ { 0, 1 }, { 1, 2 }, { STPnHCK | 2, 4 }, { STPnHCK | 3, 8 }, - { STPnHCK | 4, 16 }, { 0, 0 }, + { STPnHCK | 4, 16 }, + /* + * These values are not recommended because STPnHCK is wrong. But they + * have been seen because of broken firmware. So, we support reading + * them but Linux will sanitize them when initializing through + * recalc_rate. + */ + { STPnHCK | 0, 1 }, { STPnHCK | 1, 2 }, { 2, 4 }, { 3, 8 }, { 4, 16 }, + /* Sentinel */ + { 0, 0 } }; struct clk * __init cpg_sdh_clk_register(const char *name, diff --git a/drivers/clk/renesas/rzg2l-cpg.c b/drivers/clk/renesas/rzg2l-cpg.c index 47f488387f33a1..75f9eca020ce57 100644 --- a/drivers/clk/renesas/rzg2l-cpg.c +++ b/drivers/clk/renesas/rzg2l-cpg.c @@ -11,6 +11,7 @@ * Copyright (C) 2015 Renesas Electronics Corp. */ +#include #include #include #include @@ -38,14 +39,13 @@ #define WARN_DEBUG(x) do { } while (0) #endif -#define DIV_RSMASK(v, s, m) ((v >> s) & m) #define GET_SHIFT(val) ((val >> 12) & 0xff) #define GET_WIDTH(val) ((val >> 8) & 0xf) -#define KDIV(val) DIV_RSMASK(val, 16, 0xffff) -#define MDIV(val) DIV_RSMASK(val, 6, 0x3ff) -#define PDIV(val) DIV_RSMASK(val, 0, 0x3f) -#define SDIV(val) DIV_RSMASK(val, 0, 0x7) +#define KDIV(val) ((s16)FIELD_GET(GENMASK(31, 16), val)) +#define MDIV(val) FIELD_GET(GENMASK(15, 6), val) +#define PDIV(val) FIELD_GET(GENMASK(5, 0), val) +#define SDIV(val) FIELD_GET(GENMASK(2, 0), val) #define CLK_ON_R(reg) (reg) #define CLK_MON_R(reg) (0x180 + (reg)) @@ -188,7 +188,9 @@ static int rzg2l_cpg_sd_clk_mux_set_parent(struct clk_hw *hw, u8 index) u32 off = GET_REG_OFFSET(hwdata->conf); u32 shift = GET_SHIFT(hwdata->conf); const u32 clk_src_266 = 2; - u32 bitmask; + u32 msk, val, bitmask; + unsigned long flags; + int ret; /* * As per the HW manual, we should not directly switch from 533 MHz to @@ -202,26 +204,30 @@ static int rzg2l_cpg_sd_clk_mux_set_parent(struct clk_hw *hw, u8 index) * the index to value mapping is done by adding 1 to the index. */ bitmask = (GENMASK(GET_WIDTH(hwdata->conf) - 1, 0) << shift) << 16; + msk = off ? CPG_CLKSTATUS_SELSDHI1_STS : CPG_CLKSTATUS_SELSDHI0_STS; + spin_lock_irqsave(&priv->rmw_lock, flags); if (index != clk_src_266) { - u32 msk, val; - int ret; - writel(bitmask | ((clk_src_266 + 1) << shift), priv->base + off); - msk = off ? CPG_CLKSTATUS_SELSDHI1_STS : CPG_CLKSTATUS_SELSDHI0_STS; - - ret = readl_poll_timeout(priv->base + CPG_CLKSTATUS, val, - !(val & msk), 100, - CPG_SDHI_CLK_SWITCH_STATUS_TIMEOUT_US); - if (ret) { - dev_err(priv->dev, "failed to switch clk source\n"); - return ret; - } + ret = readl_poll_timeout_atomic(priv->base + CPG_CLKSTATUS, val, + !(val & msk), 10, + CPG_SDHI_CLK_SWITCH_STATUS_TIMEOUT_US); + if (ret) + goto unlock; } writel(bitmask | ((index + 1) << shift), priv->base + off); - return 0; + ret = readl_poll_timeout_atomic(priv->base + CPG_CLKSTATUS, val, + !(val & msk), 10, + CPG_SDHI_CLK_SWITCH_STATUS_TIMEOUT_US); +unlock: + spin_unlock_irqrestore(&priv->rmw_lock, flags); + + if (ret) + dev_err(priv->dev, "failed to switch clk source\n"); + + return ret; } static u8 rzg2l_cpg_sd_clk_mux_get_parent(struct clk_hw *hw) @@ -232,14 +238,8 @@ static u8 rzg2l_cpg_sd_clk_mux_get_parent(struct clk_hw *hw) val >>= GET_SHIFT(hwdata->conf); val &= GENMASK(GET_WIDTH(hwdata->conf) - 1, 0); - if (val) { - val--; - } else { - /* Prohibited clk source, change it to 533 MHz(reset value) */ - rzg2l_cpg_sd_clk_mux_set_parent(hw, 0); - } - return val; + return val ? val - 1 : 0; } static const struct clk_ops rzg2l_cpg_sd_clk_mux_ops = { @@ -695,18 +695,18 @@ static unsigned long rzg2l_cpg_pll_clk_recalc_rate(struct clk_hw *hw, struct pll_clk *pll_clk = to_pll(hw); struct rzg2l_cpg_priv *priv = pll_clk->priv; unsigned int val1, val2; - unsigned int mult = 1; - unsigned int div = 1; + u64 rate; if (pll_clk->type != CLK_TYPE_SAM_PLL) return parent_rate; val1 = readl(priv->base + GET_REG_SAMPLL_CLK1(pll_clk->conf)); val2 = readl(priv->base + GET_REG_SAMPLL_CLK2(pll_clk->conf)); - mult = MDIV(val1) + KDIV(val1) / 65536; - div = PDIV(val1) << SDIV(val2); - return DIV_ROUND_CLOSEST_ULL((u64)parent_rate * mult, div); + rate = mul_u64_u32_shr(parent_rate, (MDIV(val1) << 16) + KDIV(val1), + 16 + SDIV(val2)); + + return DIV_ROUND_CLOSEST_ULL(rate, PDIV(val1)); } static const struct clk_ops rzg2l_cpg_pll_ops = { @@ -1105,41 +1105,33 @@ rzg2l_cpg_register_mod_clk(const struct rzg2l_mod_clk *mod, #define rcdev_to_priv(x) container_of(x, struct rzg2l_cpg_priv, rcdev) -static int rzg2l_cpg_reset(struct reset_controller_dev *rcdev, - unsigned long id) -{ - struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); - const struct rzg2l_cpg_info *info = priv->info; - unsigned int reg = info->resets[id].off; - u32 dis = BIT(info->resets[id].bit); - u32 we = dis << 16; - - dev_dbg(rcdev->dev, "reset id:%ld offset:0x%x\n", id, CLK_RST_R(reg)); - - /* Reset module */ - writel(we, priv->base + CLK_RST_R(reg)); - - /* Wait for at least one cycle of the RCLK clock (@ ca. 32 kHz) */ - udelay(35); - - /* Release module from reset state */ - writel(we | dis, priv->base + CLK_RST_R(reg)); - - return 0; -} - static int rzg2l_cpg_assert(struct reset_controller_dev *rcdev, unsigned long id) { struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; unsigned int reg = info->resets[id].off; - u32 value = BIT(info->resets[id].bit) << 16; + u32 mask = BIT(info->resets[id].bit); + s8 monbit = info->resets[id].monbit; + u32 value = mask << 16; dev_dbg(rcdev->dev, "assert id:%ld offset:0x%x\n", id, CLK_RST_R(reg)); writel(value, priv->base + CLK_RST_R(reg)); - return 0; + + if (info->has_clk_mon_regs) { + reg = CLK_MRST_R(reg); + } else if (monbit >= 0) { + reg = CPG_RST_MON; + mask = BIT(monbit); + } else { + /* Wait for at least one cycle of the RCLK clock (@ ca. 32 kHz) */ + udelay(35); + return 0; + } + + return readl_poll_timeout_atomic(priv->base + reg, value, + value & mask, 10, 200); } static int rzg2l_cpg_deassert(struct reset_controller_dev *rcdev, @@ -1148,14 +1140,40 @@ static int rzg2l_cpg_deassert(struct reset_controller_dev *rcdev, struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; unsigned int reg = info->resets[id].off; - u32 dis = BIT(info->resets[id].bit); - u32 value = (dis << 16) | dis; + u32 mask = BIT(info->resets[id].bit); + s8 monbit = info->resets[id].monbit; + u32 value = (mask << 16) | mask; dev_dbg(rcdev->dev, "deassert id:%ld offset:0x%x\n", id, CLK_RST_R(reg)); writel(value, priv->base + CLK_RST_R(reg)); - return 0; + + if (info->has_clk_mon_regs) { + reg = CLK_MRST_R(reg); + } else if (monbit >= 0) { + reg = CPG_RST_MON; + mask = BIT(monbit); + } else { + /* Wait for at least one cycle of the RCLK clock (@ ca. 32 kHz) */ + udelay(35); + return 0; + } + + return readl_poll_timeout_atomic(priv->base + reg, value, + !(value & mask), 10, 200); +} + +static int rzg2l_cpg_reset(struct reset_controller_dev *rcdev, + unsigned long id) +{ + int ret; + + ret = rzg2l_cpg_assert(rcdev, id); + if (ret) + return ret; + + return rzg2l_cpg_deassert(rcdev, id); } static int rzg2l_cpg_status(struct reset_controller_dev *rcdev, @@ -1163,18 +1181,21 @@ static int rzg2l_cpg_status(struct reset_controller_dev *rcdev, { struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; - unsigned int reg = info->resets[id].off; - u32 bitmask = BIT(info->resets[id].bit); s8 monbit = info->resets[id].monbit; + unsigned int reg; + u32 bitmask; if (info->has_clk_mon_regs) { - return !!(readl(priv->base + CLK_MRST_R(reg)) & bitmask); + reg = CLK_MRST_R(info->resets[id].off); + bitmask = BIT(info->resets[id].bit); } else if (monbit >= 0) { - u32 monbitmask = BIT(monbit); - - return !!(readl(priv->base + CPG_RST_MON) & monbitmask); + reg = CPG_RST_MON; + bitmask = BIT(monbit); + } else { + return -ENOTSUPP; } - return -ENOTSUPP; + + return !!(readl(priv->base + reg) & bitmask); } static const struct reset_control_ops rzg2l_cpg_reset_ops = { diff --git a/drivers/clk/renesas/rzg2l-cpg.h b/drivers/clk/renesas/rzg2l-cpg.h index 6cee9e56acc722..91e9c2569f801b 100644 --- a/drivers/clk/renesas/rzg2l-cpg.h +++ b/drivers/clk/renesas/rzg2l-cpg.h @@ -43,7 +43,7 @@ #define CPG_CLKSTATUS_SELSDHI0_STS BIT(28) #define CPG_CLKSTATUS_SELSDHI1_STS BIT(29) -#define CPG_SDHI_CLK_SWITCH_STATUS_TIMEOUT_US 20000 +#define CPG_SDHI_CLK_SWITCH_STATUS_TIMEOUT_US 200 /* n = 0/1/2 for PLL1/4/6 */ #define CPG_SAMPLL_CLK1(n) (0x04 + (16 * n)) diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c index aa53797dbfc145..75071e0cd3216e 100644 --- a/drivers/clk/rockchip/clk-rk3128.c +++ b/drivers/clk/rockchip/clk-rk3128.c @@ -138,7 +138,7 @@ PNAME(mux_pll_src_5plls_p) = { "cpll", "gpll", "gpll_div2", "gpll_div3", "usb480 PNAME(mux_pll_src_4plls_p) = { "cpll", "gpll", "gpll_div2", "usb480m" }; PNAME(mux_pll_src_3plls_p) = { "cpll", "gpll", "gpll_div2" }; -PNAME(mux_aclk_peri_src_p) = { "gpll_peri", "cpll_peri", "gpll_div2_peri", "gpll_div3_peri" }; +PNAME(mux_clk_peri_src_p) = { "gpll", "cpll", "gpll_div2", "gpll_div3" }; PNAME(mux_mmc_src_p) = { "cpll", "gpll", "gpll_div2", "xin24m" }; PNAME(mux_clk_cif_out_src_p) = { "clk_cif_src", "xin24m" }; PNAME(mux_sclk_vop_src_p) = { "cpll", "gpll", "gpll_div2", "gpll_div3" }; @@ -275,23 +275,17 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { RK2928_CLKGATE_CON(0), 11, GFLAGS), /* PD_PERI */ - GATE(0, "gpll_peri", "gpll", CLK_IGNORE_UNUSED, + COMPOSITE(0, "clk_peri_src", mux_clk_peri_src_p, 0, + RK2928_CLKSEL_CON(10), 14, 2, MFLAGS, 0, 5, DFLAGS, RK2928_CLKGATE_CON(2), 0, GFLAGS), - GATE(0, "cpll_peri", "cpll", CLK_IGNORE_UNUSED, - RK2928_CLKGATE_CON(2), 0, GFLAGS), - GATE(0, "gpll_div2_peri", "gpll_div2", CLK_IGNORE_UNUSED, - RK2928_CLKGATE_CON(2), 0, GFLAGS), - GATE(0, "gpll_div3_peri", "gpll_div3", CLK_IGNORE_UNUSED, - RK2928_CLKGATE_CON(2), 0, GFLAGS), - COMPOSITE_NOGATE(0, "aclk_peri_src", mux_aclk_peri_src_p, 0, - RK2928_CLKSEL_CON(10), 14, 2, MFLAGS, 0, 5, DFLAGS), - COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "aclk_peri_src", 0, + + COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "clk_peri_src", 0, RK2928_CLKSEL_CON(10), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO, RK2928_CLKGATE_CON(2), 3, GFLAGS), - COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "aclk_peri_src", 0, + COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "clk_peri_src", 0, RK2928_CLKSEL_CON(10), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO, RK2928_CLKGATE_CON(2), 2, GFLAGS), - GATE(ACLK_PERI, "aclk_peri", "aclk_peri_src", 0, + GATE(ACLK_PERI, "aclk_peri", "clk_peri_src", 0, RK2928_CLKGATE_CON(2), 1, GFLAGS), GATE(SCLK_TIMER0, "sclk_timer0", "xin24m", 0, @@ -316,7 +310,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { GATE(SCLK_MIPI_24M, "clk_mipi_24m", "xin24m", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(2), 15, GFLAGS), - COMPOSITE(SCLK_SDMMC, "sclk_sdmmc0", mux_mmc_src_p, 0, + COMPOSITE(SCLK_SDMMC, "sclk_sdmmc", mux_mmc_src_p, 0, RK2928_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 6, DFLAGS, RK2928_CLKGATE_CON(2), 11, GFLAGS), @@ -490,7 +484,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { GATE(HCLK_I2S_2CH, "hclk_i2s_2ch", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 2, GFLAGS), GATE(0, "hclk_usb_peri", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 13, GFLAGS), GATE(HCLK_HOST2, "hclk_host2", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 3, GFLAGS), - GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(3), 13, GFLAGS), + GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(5), 13, GFLAGS), GATE(0, "hclk_peri_ahb", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 14, GFLAGS), GATE(HCLK_SPDIF, "hclk_spdif", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 9, GFLAGS), GATE(HCLK_TSP, "hclk_tsp", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 12, GFLAGS), diff --git a/drivers/clk/rockchip/clk-rk3228.c b/drivers/clk/rockchip/clk-rk3228.c index a24a35553e1349..7343d2d7676bca 100644 --- a/drivers/clk/rockchip/clk-rk3228.c +++ b/drivers/clk/rockchip/clk-rk3228.c @@ -409,7 +409,7 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = { RK2928_CLKSEL_CON(29), 0, 3, DFLAGS), DIV(0, "sclk_vop_pre", "sclk_vop_src", 0, RK2928_CLKSEL_CON(27), 8, 8, DFLAGS), - MUX(DCLK_VOP, "dclk_vop", mux_dclk_vop_p, 0, + MUX(DCLK_VOP, "dclk_vop", mux_dclk_vop_p, CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT, RK2928_CLKSEL_CON(27), 1, 1, MFLAGS), FACTOR(0, "xin12m", "xin24m", 0, 1, 2), diff --git a/drivers/clk/rockchip/clk-rk3568.c b/drivers/clk/rockchip/clk-rk3568.c index 16dabe2b9c47f4..db713e1526cdc3 100644 --- a/drivers/clk/rockchip/clk-rk3568.c +++ b/drivers/clk/rockchip/clk-rk3568.c @@ -72,6 +72,7 @@ static struct rockchip_pll_rate_table rk3568_pll_rates[] = { RK3036_PLL_RATE(408000000, 1, 68, 2, 2, 1, 0), RK3036_PLL_RATE(312000000, 1, 78, 6, 1, 1, 0), RK3036_PLL_RATE(297000000, 2, 99, 4, 1, 1, 0), + RK3036_PLL_RATE(292500000, 1, 195, 4, 4, 1, 0), RK3036_PLL_RATE(241500000, 2, 161, 4, 2, 1, 0), RK3036_PLL_RATE(216000000, 1, 72, 4, 2, 1, 0), RK3036_PLL_RATE(200000000, 1, 100, 3, 4, 1, 0), diff --git a/drivers/clk/rockchip/clk-rk3588.c b/drivers/clk/rockchip/clk-rk3588.c index 6994165e03957c..d8ffcaefa480b3 100644 --- a/drivers/clk/rockchip/clk-rk3588.c +++ b/drivers/clk/rockchip/clk-rk3588.c @@ -526,7 +526,7 @@ PNAME(pmu_200m_100m_p) = { "clk_pmu1_200m_src", "clk_pmu1_100m_src" }; PNAME(pmu_300m_24m_p) = { "clk_300m_src", "xin24m" }; PNAME(pmu_400m_24m_p) = { "clk_400m_src", "xin24m" }; PNAME(pmu_100m_50m_24m_src_p) = { "clk_pmu1_100m_src", "clk_pmu1_50m_src", "xin24m" }; -PNAME(pmu_24m_32k_100m_src_p) = { "xin24m", "32k", "clk_pmu1_100m_src" }; +PNAME(pmu_24m_32k_100m_src_p) = { "xin24m", "xin32k", "clk_pmu1_100m_src" }; PNAME(hclk_pmu1_root_p) = { "clk_pmu1_200m_src", "clk_pmu1_100m_src", "clk_pmu1_50m_src", "xin24m" }; PNAME(hclk_pmu_cm0_root_p) = { "clk_pmu1_400m_src", "clk_pmu1_200m_src", "clk_pmu1_100m_src", "xin24m" }; PNAME(mclk_pdm0_p) = { "clk_pmu1_300m_src", "clk_pmu1_200m_src" }; diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c index 4059d9365ae642..b9d6ffcb340912 100644 --- a/drivers/clk/rockchip/clk.c +++ b/drivers/clk/rockchip/clk.c @@ -433,12 +433,13 @@ void rockchip_clk_register_branches(struct rockchip_clk_provider *ctx, struct rockchip_clk_branch *list, unsigned int nr_clk) { - struct clk *clk = NULL; + struct clk *clk; unsigned int idx; unsigned long flags; for (idx = 0; idx < nr_clk; idx++, list++) { flags = list->flags; + clk = NULL; /* catch simple muxes */ switch (list->branch_type) { diff --git a/drivers/clk/samsung/clk-exynos7885.c b/drivers/clk/samsung/clk-exynos7885.c index f7d7427a558ba0..87387d4cbf48a2 100644 --- a/drivers/clk/samsung/clk-exynos7885.c +++ b/drivers/clk/samsung/clk-exynos7885.c @@ -20,7 +20,7 @@ #define CLKS_NR_TOP (CLK_GOUT_FSYS_USB30DRD + 1) #define CLKS_NR_CORE (CLK_GOUT_TREX_P_CORE_PCLK_P_CORE + 1) #define CLKS_NR_PERI (CLK_GOUT_WDT1_PCLK + 1) -#define CLKS_NR_FSYS (CLK_GOUT_MMC_SDIO_SDCLKIN + 1) +#define CLKS_NR_FSYS (CLK_MOUT_FSYS_USB30DRD_USER + 1) /* ---- CMU_TOP ------------------------------------------------------------- */ diff --git a/drivers/clk/samsung/clk-exynos850.c b/drivers/clk/samsung/clk-exynos850.c index bdc1eef7d6e548..c7b0b9751307b9 100644 --- a/drivers/clk/samsung/clk-exynos850.c +++ b/drivers/clk/samsung/clk-exynos850.c @@ -605,7 +605,7 @@ static const struct samsung_div_clock apm_div_clks[] __initconst = { static const struct samsung_gate_clock apm_gate_clks[] __initconst = { GATE(CLK_GOUT_CLKCMU_CMGP_BUS, "gout_clkcmu_cmgp_bus", "dout_apm_bus", - CLK_CON_GAT_CLKCMU_CMGP_BUS, 21, 0, 0), + CLK_CON_GAT_CLKCMU_CMGP_BUS, 21, CLK_SET_RATE_PARENT, 0), GATE(CLK_GOUT_CLKCMU_CHUB_BUS, "gout_clkcmu_chub_bus", "mout_clkcmu_chub_bus", CLK_CON_GAT_GATE_CLKCMU_CHUB_BUS, 21, 0, 0), @@ -974,19 +974,19 @@ static const struct samsung_fixed_rate_clock cmgp_fixed_clks[] __initconst = { static const struct samsung_mux_clock cmgp_mux_clks[] __initconst = { MUX(CLK_MOUT_CMGP_ADC, "mout_cmgp_adc", mout_cmgp_adc_p, CLK_CON_MUX_CLK_CMGP_ADC, 0, 1), - MUX(CLK_MOUT_CMGP_USI0, "mout_cmgp_usi0", mout_cmgp_usi0_p, - CLK_CON_MUX_MUX_CLK_CMGP_USI_CMGP0, 0, 1), - MUX(CLK_MOUT_CMGP_USI1, "mout_cmgp_usi1", mout_cmgp_usi1_p, - CLK_CON_MUX_MUX_CLK_CMGP_USI_CMGP1, 0, 1), + MUX_F(CLK_MOUT_CMGP_USI0, "mout_cmgp_usi0", mout_cmgp_usi0_p, + CLK_CON_MUX_MUX_CLK_CMGP_USI_CMGP0, 0, 1, CLK_SET_RATE_PARENT, 0), + MUX_F(CLK_MOUT_CMGP_USI1, "mout_cmgp_usi1", mout_cmgp_usi1_p, + CLK_CON_MUX_MUX_CLK_CMGP_USI_CMGP1, 0, 1, CLK_SET_RATE_PARENT, 0), }; static const struct samsung_div_clock cmgp_div_clks[] __initconst = { DIV(CLK_DOUT_CMGP_ADC, "dout_cmgp_adc", "gout_clkcmu_cmgp_bus", CLK_CON_DIV_DIV_CLK_CMGP_ADC, 0, 4), - DIV(CLK_DOUT_CMGP_USI0, "dout_cmgp_usi0", "mout_cmgp_usi0", - CLK_CON_DIV_DIV_CLK_CMGP_USI_CMGP0, 0, 5), - DIV(CLK_DOUT_CMGP_USI1, "dout_cmgp_usi1", "mout_cmgp_usi1", - CLK_CON_DIV_DIV_CLK_CMGP_USI_CMGP1, 0, 5), + DIV_F(CLK_DOUT_CMGP_USI0, "dout_cmgp_usi0", "mout_cmgp_usi0", + CLK_CON_DIV_DIV_CLK_CMGP_USI_CMGP0, 0, 5, CLK_SET_RATE_PARENT, 0), + DIV_F(CLK_DOUT_CMGP_USI1, "dout_cmgp_usi1", "mout_cmgp_usi1", + CLK_CON_DIV_DIV_CLK_CMGP_USI_CMGP1, 0, 5, CLK_SET_RATE_PARENT, 0), }; static const struct samsung_gate_clock cmgp_gate_clks[] __initconst = { @@ -1001,12 +1001,12 @@ static const struct samsung_gate_clock cmgp_gate_clks[] __initconst = { "gout_clkcmu_cmgp_bus", CLK_CON_GAT_GOUT_CMGP_GPIO_PCLK, 21, CLK_IGNORE_UNUSED, 0), GATE(CLK_GOUT_CMGP_USI0_IPCLK, "gout_cmgp_usi0_ipclk", "dout_cmgp_usi0", - CLK_CON_GAT_GOUT_CMGP_USI_CMGP0_IPCLK, 21, 0, 0), + CLK_CON_GAT_GOUT_CMGP_USI_CMGP0_IPCLK, 21, CLK_SET_RATE_PARENT, 0), GATE(CLK_GOUT_CMGP_USI0_PCLK, "gout_cmgp_usi0_pclk", "gout_clkcmu_cmgp_bus", CLK_CON_GAT_GOUT_CMGP_USI_CMGP0_PCLK, 21, 0, 0), GATE(CLK_GOUT_CMGP_USI1_IPCLK, "gout_cmgp_usi1_ipclk", "dout_cmgp_usi1", - CLK_CON_GAT_GOUT_CMGP_USI_CMGP1_IPCLK, 21, 0, 0), + CLK_CON_GAT_GOUT_CMGP_USI_CMGP1_IPCLK, 21, CLK_SET_RATE_PARENT, 0), GATE(CLK_GOUT_CMGP_USI1_PCLK, "gout_cmgp_usi1_pclk", "gout_clkcmu_cmgp_bus", CLK_CON_GAT_GOUT_CMGP_USI_CMGP1_PCLK, 21, 0, 0), @@ -1557,8 +1557,9 @@ static const struct samsung_mux_clock peri_mux_clks[] __initconst = { mout_peri_uart_user_p, PLL_CON0_MUX_CLKCMU_PERI_UART_USER, 4, 1), MUX(CLK_MOUT_PERI_HSI2C_USER, "mout_peri_hsi2c_user", mout_peri_hsi2c_user_p, PLL_CON0_MUX_CLKCMU_PERI_HSI2C_USER, 4, 1), - MUX(CLK_MOUT_PERI_SPI_USER, "mout_peri_spi_user", mout_peri_spi_user_p, - PLL_CON0_MUX_CLKCMU_PERI_SPI_USER, 4, 1), + MUX_F(CLK_MOUT_PERI_SPI_USER, "mout_peri_spi_user", + mout_peri_spi_user_p, PLL_CON0_MUX_CLKCMU_PERI_SPI_USER, 4, 1, + CLK_SET_RATE_PARENT, 0), }; static const struct samsung_div_clock peri_div_clks[] __initconst = { @@ -1568,8 +1569,8 @@ static const struct samsung_div_clock peri_div_clks[] __initconst = { CLK_CON_DIV_DIV_CLK_PERI_HSI2C_1, 0, 5), DIV(CLK_DOUT_PERI_HSI2C2, "dout_peri_hsi2c2", "gout_peri_hsi2c2", CLK_CON_DIV_DIV_CLK_PERI_HSI2C_2, 0, 5), - DIV(CLK_DOUT_PERI_SPI0, "dout_peri_spi0", "mout_peri_spi_user", - CLK_CON_DIV_DIV_CLK_PERI_SPI_0, 0, 5), + DIV_F(CLK_DOUT_PERI_SPI0, "dout_peri_spi0", "mout_peri_spi_user", + CLK_CON_DIV_DIV_CLK_PERI_SPI_0, 0, 5, CLK_SET_RATE_PARENT, 0), }; static const struct samsung_gate_clock peri_gate_clks[] __initconst = { @@ -1611,7 +1612,7 @@ static const struct samsung_gate_clock peri_gate_clks[] __initconst = { "mout_peri_bus_user", CLK_CON_GAT_GOUT_PERI_PWM_MOTOR_PCLK, 21, 0, 0), GATE(CLK_GOUT_SPI0_IPCLK, "gout_spi0_ipclk", "dout_peri_spi0", - CLK_CON_GAT_GOUT_PERI_SPI_0_IPCLK, 21, 0, 0), + CLK_CON_GAT_GOUT_PERI_SPI_0_IPCLK, 21, CLK_SET_RATE_PARENT, 0), GATE(CLK_GOUT_SPI0_PCLK, "gout_spi0_pclk", "mout_peri_bus_user", CLK_CON_GAT_GOUT_PERI_SPI_0_PCLK, 21, 0, 0), GATE(CLK_GOUT_SYSREG_PERI_PCLK, "gout_sysreg_peri_pclk", diff --git a/drivers/clk/samsung/clk-exynosautov9.c b/drivers/clk/samsung/clk-exynosautov9.c index e9c06eb93e6665..f04bacacab2cb8 100644 --- a/drivers/clk/samsung/clk-exynosautov9.c +++ b/drivers/clk/samsung/clk-exynosautov9.c @@ -352,13 +352,13 @@ static const struct samsung_pll_clock top_pll_clks[] __initconst = { /* CMU_TOP_PURECLKCOMP */ PLL(pll_0822x, FOUT_SHARED0_PLL, "fout_shared0_pll", "oscclk", PLL_LOCKTIME_PLL_SHARED0, PLL_CON3_PLL_SHARED0, NULL), - PLL(pll_0822x, FOUT_SHARED0_PLL, "fout_shared1_pll", "oscclk", + PLL(pll_0822x, FOUT_SHARED1_PLL, "fout_shared1_pll", "oscclk", PLL_LOCKTIME_PLL_SHARED1, PLL_CON3_PLL_SHARED1, NULL), - PLL(pll_0822x, FOUT_SHARED0_PLL, "fout_shared2_pll", "oscclk", + PLL(pll_0822x, FOUT_SHARED2_PLL, "fout_shared2_pll", "oscclk", PLL_LOCKTIME_PLL_SHARED2, PLL_CON3_PLL_SHARED2, NULL), - PLL(pll_0822x, FOUT_SHARED0_PLL, "fout_shared3_pll", "oscclk", + PLL(pll_0822x, FOUT_SHARED3_PLL, "fout_shared3_pll", "oscclk", PLL_LOCKTIME_PLL_SHARED3, PLL_CON3_PLL_SHARED3, NULL), - PLL(pll_0822x, FOUT_SHARED0_PLL, "fout_shared4_pll", "oscclk", + PLL(pll_0822x, FOUT_SHARED4_PLL, "fout_shared4_pll", "oscclk", PLL_LOCKTIME_PLL_SHARED4, PLL_CON3_PLL_SHARED4, NULL), }; diff --git a/drivers/clk/sifive/sifive-prci.c b/drivers/clk/sifive/sifive-prci.c index af81eb835bc235..b1be6a2d24aa9c 100644 --- a/drivers/clk/sifive/sifive-prci.c +++ b/drivers/clk/sifive/sifive-prci.c @@ -4,7 +4,6 @@ * Copyright (C) 2020 Zong Li */ -#include #include #include #include @@ -536,13 +535,6 @@ static int __prci_register_clocks(struct device *dev, struct __prci_data *pd, return r; } - r = clk_hw_register_clkdev(&pic->hw, pic->name, dev_name(dev)); - if (r) { - dev_warn(dev, "Failed to register clkdev for %s: %d\n", - init.name, r); - return r; - } - pd->hw_clks.hws[i] = &pic->hw; } diff --git a/drivers/clk/socfpga/stratix10-clk.h b/drivers/clk/socfpga/stratix10-clk.h index 75234e0783e1cc..83fe4eb3133cbe 100644 --- a/drivers/clk/socfpga/stratix10-clk.h +++ b/drivers/clk/socfpga/stratix10-clk.h @@ -7,8 +7,10 @@ #define __STRATIX10_CLK_H struct stratix10_clock_data { - struct clk_hw_onecell_data clk_data; void __iomem *base; + + /* Must be last */ + struct clk_hw_onecell_data clk_data; }; struct stratix10_pll_clock { diff --git a/drivers/clk/starfive/clk-starfive-jh7110-sys.c b/drivers/clk/starfive/clk-starfive-jh7110-sys.c index 3884eff9fe9315..58ef7c6d69cce9 100644 --- a/drivers/clk/starfive/clk-starfive-jh7110-sys.c +++ b/drivers/clk/starfive/clk-starfive-jh7110-sys.c @@ -385,6 +385,32 @@ int jh7110_reset_controller_register(struct jh71x0_clk_priv *priv, } EXPORT_SYMBOL_GPL(jh7110_reset_controller_register); +/* + * This clock notifier is called when the rate of PLL0 clock is to be changed. + * The cpu_root clock should save the curent parent clock and switch its parent + * clock to osc before PLL0 rate will be changed. Then switch its parent clock + * back after the PLL0 rate is completed. + */ +static int jh7110_pll0_clk_notifier_cb(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct jh71x0_clk_priv *priv = container_of(nb, struct jh71x0_clk_priv, pll_clk_nb); + struct clk *cpu_root = priv->reg[JH7110_SYSCLK_CPU_ROOT].hw.clk; + int ret = 0; + + if (action == PRE_RATE_CHANGE) { + struct clk *osc = clk_get(priv->dev, "osc"); + + priv->original_clk = clk_get_parent(cpu_root); + ret = clk_set_parent(cpu_root, osc); + clk_put(osc); + } else if (action == POST_RATE_CHANGE) { + ret = clk_set_parent(cpu_root, priv->original_clk); + } + + return notifier_from_errno(ret); +} + static int __init jh7110_syscrg_probe(struct platform_device *pdev) { struct jh71x0_clk_priv *priv; @@ -413,7 +439,10 @@ static int __init jh7110_syscrg_probe(struct platform_device *pdev) if (IS_ERR(priv->pll[0])) return PTR_ERR(priv->pll[0]); } else { - clk_put(pllclk); + priv->pll_clk_nb.notifier_call = jh7110_pll0_clk_notifier_cb; + ret = clk_notifier_register(pllclk, &priv->pll_clk_nb); + if (ret) + return ret; priv->pll[0] = NULL; } diff --git a/drivers/clk/starfive/clk-starfive-jh7110-vout.c b/drivers/clk/starfive/clk-starfive-jh7110-vout.c index 10cc1ec4392517..36340ca42cc7ed 100644 --- a/drivers/clk/starfive/clk-starfive-jh7110-vout.c +++ b/drivers/clk/starfive/clk-starfive-jh7110-vout.c @@ -145,7 +145,7 @@ static int jh7110_voutcrg_probe(struct platform_device *pdev) /* enable power domain and clocks */ pm_runtime_enable(priv->dev); - ret = pm_runtime_get_sync(priv->dev); + ret = pm_runtime_resume_and_get(priv->dev); if (ret < 0) return dev_err_probe(priv->dev, ret, "failed to turn on power\n"); diff --git a/drivers/clk/starfive/clk-starfive-jh71x0.h b/drivers/clk/starfive/clk-starfive-jh71x0.h index 34bb11c72eb73b..ebc55b9ef83705 100644 --- a/drivers/clk/starfive/clk-starfive-jh71x0.h +++ b/drivers/clk/starfive/clk-starfive-jh71x0.h @@ -114,6 +114,8 @@ struct jh71x0_clk_priv { spinlock_t rmw_lock; struct device *dev; void __iomem *base; + struct clk *original_clk; + struct notifier_block pll_clk_nb; struct clk_hw *pll[3]; struct jh71x0_clk reg[]; }; diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c index 8951ffc14ff52c..6a4b2b9ef30a82 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c @@ -182,6 +182,8 @@ static struct ccu_nkm pll_mipi_clk = { &ccu_nkm_ops, CLK_SET_RATE_UNGATE | CLK_SET_RATE_PARENT), .features = CCU_FEATURE_CLOSEST_RATE, + .min_rate = 500000000, + .max_rate = 1400000000, }, }; diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c index 42568c6161814d..892df807275c8e 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c @@ -1181,11 +1181,18 @@ static const u32 usb2_clk_regs[] = { SUN50I_H6_USB3_CLK_REG, }; +static struct ccu_mux_nb sun50i_h6_cpu_nb = { + .common = &cpux_clk.common, + .cm = &cpux_clk.mux, + .delay_us = 1, + .bypass_index = 0, /* index of 24 MHz oscillator */ +}; + static int sun50i_h6_ccu_probe(struct platform_device *pdev) { void __iomem *reg; + int i, ret; u32 val; - int i; reg = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(reg)) @@ -1252,7 +1259,15 @@ static int sun50i_h6_ccu_probe(struct platform_device *pdev) val |= BIT(24); writel(val, reg + SUN50I_H6_HDMI_CEC_CLK_REG); - return devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_h6_ccu_desc); + ret = devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_h6_ccu_desc); + if (ret) + return ret; + + /* Reparent CPU during PLL CPUX rate changes */ + ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk, + &sun50i_h6_cpu_nb); + + return 0; } static const struct of_device_id sun50i_h6_ccu_ids[] = { diff --git a/drivers/clk/sunxi-ng/ccu_common.c b/drivers/clk/sunxi-ng/ccu_common.c index 8babce55302f5f..be375ce0149c8b 100644 --- a/drivers/clk/sunxi-ng/ccu_common.c +++ b/drivers/clk/sunxi-ng/ccu_common.c @@ -44,6 +44,16 @@ bool ccu_is_better_rate(struct ccu_common *common, unsigned long current_rate, unsigned long best_rate) { + unsigned long min_rate, max_rate; + + clk_hw_get_rate_range(&common->hw, &min_rate, &max_rate); + + if (current_rate > max_rate) + return false; + + if (current_rate < min_rate) + return false; + if (common->features & CCU_FEATURE_CLOSEST_RATE) return abs(current_rate - target_rate) < abs(best_rate - target_rate); @@ -138,6 +148,21 @@ static int sunxi_ccu_probe(struct sunxi_ccu *ccu, struct device *dev, } } + for (i = 0; i < desc->num_ccu_clks; i++) { + struct ccu_common *cclk = desc->ccu_clks[i]; + + if (!cclk) + continue; + + if (cclk->max_rate) + clk_hw_set_rate_range(&cclk->hw, cclk->min_rate, + cclk->max_rate); + else + WARN(cclk->min_rate, + "No max_rate, ignoring min_rate of clock %d - %s\n", + i, clk_hw_get_name(&cclk->hw)); + } + ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, desc->hw_clks); if (ret) diff --git a/drivers/clk/sunxi-ng/ccu_common.h b/drivers/clk/sunxi-ng/ccu_common.h index 942a72c0943744..329734f8cf42b4 100644 --- a/drivers/clk/sunxi-ng/ccu_common.h +++ b/drivers/clk/sunxi-ng/ccu_common.h @@ -31,6 +31,9 @@ struct ccu_common { u16 lock_reg; u32 prediv; + unsigned long min_rate; + unsigned long max_rate; + unsigned long features; spinlock_t *lock; struct clk_hw hw; diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c index d964e3affd42ce..0eab7f3e2eab9e 100644 --- a/drivers/clk/ti/clk-dra7-atl.c +++ b/drivers/clk/ti/clk-dra7-atl.c @@ -240,6 +240,7 @@ static int of_dra7_atl_clk_probe(struct platform_device *pdev) } clk = of_clk_get_from_provider(&clkspec); + of_node_put(clkspec.np); if (IS_ERR(clk)) { pr_err("%s: failed to get atl clock %d from provider\n", __func__, i); diff --git a/drivers/clk/ti/divider.c b/drivers/clk/ti/divider.c index 768a1f3398b47d..5d5bb123ba9494 100644 --- a/drivers/clk/ti/divider.c +++ b/drivers/clk/ti/divider.c @@ -309,7 +309,6 @@ static struct clk *_register_divider(struct device_node *node, u32 flags, struct clk_omap_divider *div) { - struct clk *clk; struct clk_init_data init; const char *parent_name; const char *name; @@ -326,12 +325,7 @@ static struct clk *_register_divider(struct device_node *node, div->hw.init = &init; /* register the clock */ - clk = of_ti_clk_register(node, &div->hw, name); - - if (IS_ERR(clk)) - kfree(div); - - return clk; + return of_ti_clk_register(node, &div->hw, name); } int ti_clk_parse_divider_data(int *div_table, int num_dividers, int max_div, diff --git a/drivers/clk/visconti/pll.c b/drivers/clk/visconti/pll.c index 1f3234f2266744..e9cd80e085dc3b 100644 --- a/drivers/clk/visconti/pll.c +++ b/drivers/clk/visconti/pll.c @@ -329,12 +329,12 @@ struct visconti_pll_provider * __init visconti_init_pll(struct device_node *np, if (!ctx) return ERR_PTR(-ENOMEM); - for (i = 0; i < nr_plls; ++i) - ctx->clk_data.hws[i] = ERR_PTR(-ENOENT); - ctx->node = np; ctx->reg_base = base; ctx->clk_data.num = nr_plls; + for (i = 0; i < nr_plls; ++i) + ctx->clk_data.hws[i] = ERR_PTR(-ENOENT); + return ctx; } diff --git a/drivers/clk/visconti/pll.h b/drivers/clk/visconti/pll.h index 01d07f1bf01b10..c4bd40676da4bf 100644 --- a/drivers/clk/visconti/pll.h +++ b/drivers/clk/visconti/pll.h @@ -15,8 +15,10 @@ struct visconti_pll_provider { void __iomem *reg_base; - struct clk_hw_onecell_data clk_data; struct device_node *node; + + /* Must be last */ + struct clk_hw_onecell_data clk_data; }; #define VISCONTI_PLL_RATE(_rate, _dacen, _dsmen, \ diff --git a/drivers/clk/zynq/clkc.c b/drivers/clk/zynq/clkc.c index 7bdeaff2bfd68b..c28d3dacf0fb22 100644 --- a/drivers/clk/zynq/clkc.c +++ b/drivers/clk/zynq/clkc.c @@ -42,6 +42,7 @@ static void __iomem *zynq_clkc_base; #define SLCR_SWDT_CLK_SEL (zynq_clkc_base + 0x204) #define NUM_MIO_PINS 54 +#define CLK_NAME_LEN 16 #define DBG_CLK_CTRL_CLKACT_TRC BIT(0) #define DBG_CLK_CTRL_CPU_1XCLKACT BIT(1) @@ -215,7 +216,7 @@ static void __init zynq_clk_setup(struct device_node *np) int i; u32 tmp; int ret; - char *clk_name; + char clk_name[CLK_NAME_LEN]; unsigned int fclk_enable = 0; const char *clk_output_name[clk_max]; const char *cpu_parents[4]; @@ -426,12 +427,10 @@ static void __init zynq_clk_setup(struct device_node *np) "gem1_emio_mux", CLK_SET_RATE_PARENT, SLCR_GEM1_CLK_CTRL, 0, 0, &gem1clk_lock); - tmp = strlen("mio_clk_00x"); - clk_name = kmalloc(tmp, GFP_KERNEL); for (i = 0; i < NUM_MIO_PINS; i++) { int idx; - snprintf(clk_name, tmp, "mio_clk_%2.2d", i); + snprintf(clk_name, CLK_NAME_LEN, "mio_clk_%2.2d", i); idx = of_property_match_string(np, "clock-names", clk_name); if (idx >= 0) can_mio_mux_parents[i] = of_clk_get_parent_name(np, @@ -439,7 +438,6 @@ static void __init zynq_clk_setup(struct device_node *np) else can_mio_mux_parents[i] = dummy_nm; } - kfree(clk_name); clk_register_mux(NULL, "can_mux", periph_parents, 4, CLK_SET_RATE_NO_REPARENT, SLCR_CAN_CLK_CTRL, 4, 2, 0, &canclk_lock); diff --git a/drivers/clk/zynqmp/clk-mux-zynqmp.c b/drivers/clk/zynqmp/clk-mux-zynqmp.c index 60359333f26dbe..9b5d3050b74229 100644 --- a/drivers/clk/zynqmp/clk-mux-zynqmp.c +++ b/drivers/clk/zynqmp/clk-mux-zynqmp.c @@ -89,7 +89,7 @@ static int zynqmp_clk_mux_set_parent(struct clk_hw *hw, u8 index) static const struct clk_ops zynqmp_clk_mux_ops = { .get_parent = zynqmp_clk_mux_get_parent, .set_parent = zynqmp_clk_mux_set_parent, - .determine_rate = __clk_mux_determine_rate, + .determine_rate = __clk_mux_determine_rate_closest, }; static const struct clk_ops zynqmp_clk_mux_ro_ops = { diff --git a/drivers/clk/zynqmp/divider.c b/drivers/clk/zynqmp/divider.c index 33a3b2a226595d..5a00487ae408be 100644 --- a/drivers/clk/zynqmp/divider.c +++ b/drivers/clk/zynqmp/divider.c @@ -110,52 +110,6 @@ static unsigned long zynqmp_clk_divider_recalc_rate(struct clk_hw *hw, return DIV_ROUND_UP_ULL(parent_rate, value); } -static void zynqmp_get_divider2_val(struct clk_hw *hw, - unsigned long rate, - struct zynqmp_clk_divider *divider, - u32 *bestdiv) -{ - int div1; - int div2; - long error = LONG_MAX; - unsigned long div1_prate; - struct clk_hw *div1_parent_hw; - struct zynqmp_clk_divider *pdivider; - struct clk_hw *div2_parent_hw = clk_hw_get_parent(hw); - - if (!div2_parent_hw) - return; - - pdivider = to_zynqmp_clk_divider(div2_parent_hw); - if (!pdivider) - return; - - div1_parent_hw = clk_hw_get_parent(div2_parent_hw); - if (!div1_parent_hw) - return; - - div1_prate = clk_hw_get_rate(div1_parent_hw); - *bestdiv = 1; - for (div1 = 1; div1 <= pdivider->max_div;) { - for (div2 = 1; div2 <= divider->max_div;) { - long new_error = ((div1_prate / div1) / div2) - rate; - - if (abs(new_error) < abs(error)) { - *bestdiv = div2; - error = new_error; - } - if (divider->flags & CLK_DIVIDER_POWER_OF_TWO) - div2 = div2 << 1; - else - div2++; - } - if (pdivider->flags & CLK_DIVIDER_POWER_OF_TWO) - div1 = div1 << 1; - else - div1++; - } -} - /** * zynqmp_clk_divider_round_rate() - Round rate of divider clock * @hw: handle between common and hardware-specific interfaces @@ -174,6 +128,7 @@ static long zynqmp_clk_divider_round_rate(struct clk_hw *hw, u32 div_type = divider->div_type; u32 bestdiv; int ret; + u8 width; /* if read only, just return current value */ if (divider->flags & CLK_DIVIDER_READ_ONLY) { @@ -193,23 +148,12 @@ static long zynqmp_clk_divider_round_rate(struct clk_hw *hw, return DIV_ROUND_UP_ULL((u64)*prate, bestdiv); } - bestdiv = zynqmp_divider_get_val(*prate, rate, divider->flags); - - /* - * In case of two divisors, compute best divider values and return - * divider2 value based on compute value. div1 will be automatically - * set to optimum based on required total divider value. - */ - if (div_type == TYPE_DIV2 && - (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)) { - zynqmp_get_divider2_val(hw, rate, divider, &bestdiv); - } + width = fls(divider->max_div); - if ((clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) && divider->is_frac) - bestdiv = rate % *prate ? 1 : bestdiv; + rate = divider_round_rate(hw, rate, prate, NULL, width, divider->flags); - bestdiv = min_t(u32, bestdiv, divider->max_div); - *prate = rate * bestdiv; + if (divider->is_frac && (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) && (rate % *prate)) + *prate = rate; return rate; } diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 7dd2c615bce231..071b04f1ee7309 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -836,8 +836,9 @@ static u64 __arch_timer_check_delta(void) * Note that TVAL is signed, thus has only 31 of its * 32 bits to express magnitude. */ - MIDR_ALL_VERSIONS(MIDR_CPU_MODEL(ARM_CPU_IMP_APM, - APM_CPU_PART_POTENZA)), + MIDR_REV_RANGE(MIDR_CPU_MODEL(ARM_CPU_IMP_APM, + APM_CPU_PART_XGENE), + APM_CPU_VAR_POTENZA, 0x0, 0xf), {}, }; diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c index 44a61dc6f93208..22a58d35a41fa5 100644 --- a/drivers/clocksource/arm_global_timer.c +++ b/drivers/clocksource/arm_global_timer.c @@ -32,7 +32,7 @@ #define GT_CONTROL_IRQ_ENABLE BIT(2) /* banked */ #define GT_CONTROL_AUTO_INC BIT(3) /* banked */ #define GT_CONTROL_PRESCALER_SHIFT 8 -#define GT_CONTROL_PRESCALER_MAX 0xF +#define GT_CONTROL_PRESCALER_MAX 0xFF #define GT_CONTROL_PRESCALER_MASK (GT_CONTROL_PRESCALER_MAX << \ GT_CONTROL_PRESCALER_SHIFT) @@ -290,18 +290,17 @@ static int gt_clk_rate_change_cb(struct notifier_block *nb, switch (event) { case PRE_RATE_CHANGE: { - int psv; + unsigned long psv; - psv = DIV_ROUND_CLOSEST(ndata->new_rate, - gt_target_rate); - - if (abs(gt_target_rate - (ndata->new_rate / psv)) > MAX_F_ERR) + psv = DIV_ROUND_CLOSEST(ndata->new_rate, gt_target_rate); + if (!psv || + abs(gt_target_rate - (ndata->new_rate / psv)) > MAX_F_ERR) return NOTIFY_BAD; psv--; /* prescaler within legal range? */ - if (psv < 0 || psv > GT_CONTROL_PRESCALER_MAX) + if (psv > GT_CONTROL_PRESCALER_MAX) return NOTIFY_BAD; /* diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c index 26919556ef5f0b..b72b36e0abed86 100644 --- a/drivers/clocksource/sh_cmt.c +++ b/drivers/clocksource/sh_cmt.c @@ -528,6 +528,7 @@ static void sh_cmt_set_next(struct sh_cmt_channel *ch, unsigned long delta) static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id) { struct sh_cmt_channel *ch = dev_id; + unsigned long flags; /* clear flags */ sh_cmt_write_cmcsr(ch, sh_cmt_read_cmcsr(ch) & @@ -558,6 +559,8 @@ static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id) ch->flags &= ~FLAG_SKIPEVENT; + raw_spin_lock_irqsave(&ch->lock, flags); + if (ch->flags & FLAG_REPROGRAM) { ch->flags &= ~FLAG_REPROGRAM; sh_cmt_clock_event_program_verify(ch, 1); @@ -570,6 +573,8 @@ static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id) ch->flags &= ~FLAG_IRQCONTEXT; + raw_spin_unlock_irqrestore(&ch->lock, flags); + return IRQ_HANDLED; } @@ -780,12 +785,18 @@ static int sh_cmt_clock_event_next(unsigned long delta, struct clock_event_device *ced) { struct sh_cmt_channel *ch = ced_to_sh_cmt(ced); + unsigned long flags; BUG_ON(!clockevent_state_oneshot(ced)); + + raw_spin_lock_irqsave(&ch->lock, flags); + if (likely(ch->flags & FLAG_IRQCONTEXT)) ch->next_match_value = delta - 1; else - sh_cmt_set_next(ch, delta - 1); + __sh_cmt_set_next(ch, delta - 1); + + raw_spin_unlock_irqrestore(&ch->lock, flags); return 0; } diff --git a/drivers/clocksource/timer-atmel-tcb.c b/drivers/clocksource/timer-atmel-tcb.c index 27af17c9959004..2a90c92a9182ab 100644 --- a/drivers/clocksource/timer-atmel-tcb.c +++ b/drivers/clocksource/timer-atmel-tcb.c @@ -315,6 +315,7 @@ static void __init tcb_setup_dual_chan(struct atmel_tc *tc, int mck_divisor_idx) writel(mck_divisor_idx /* likely divide-by-8 */ | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP /* free-run */ + | ATMEL_TC_ASWTRG_SET /* TIOA0 rises at software trigger */ | ATMEL_TC_ACPA_SET /* TIOA0 rises at 0 */ | ATMEL_TC_ACPC_CLEAR, /* (duty cycle 50%) */ tcaddr + ATMEL_TC_REG(0, CMR)); diff --git a/drivers/clocksource/timer-imx-gpt.c b/drivers/clocksource/timer-imx-gpt.c index 28ab4f1a7c713b..6a878d227a13b5 100644 --- a/drivers/clocksource/timer-imx-gpt.c +++ b/drivers/clocksource/timer-imx-gpt.c @@ -434,12 +434,16 @@ static int __init mxc_timer_init_dt(struct device_node *np, enum imx_gpt_type t return -ENOMEM; imxtm->base = of_iomap(np, 0); - if (!imxtm->base) - return -ENXIO; + if (!imxtm->base) { + ret = -ENXIO; + goto err_kfree; + } imxtm->irq = irq_of_parse_and_map(np, 0); - if (imxtm->irq <= 0) - return -EINVAL; + if (imxtm->irq <= 0) { + ret = -EINVAL; + goto err_kfree; + } imxtm->clk_ipg = of_clk_get_by_name(np, "ipg"); @@ -452,11 +456,15 @@ static int __init mxc_timer_init_dt(struct device_node *np, enum imx_gpt_type t ret = _mxc_timer_init(imxtm); if (ret) - return ret; + goto err_kfree; initialized = 1; return 0; + +err_kfree: + kfree(imxtm); + return ret; } static int __init imx1_timer_init_dt(struct device_node *np) diff --git a/drivers/clocksource/timer-imx-tpm.c b/drivers/clocksource/timer-imx-tpm.c index bd64a8a8427f3c..92c025b70eb62f 100644 --- a/drivers/clocksource/timer-imx-tpm.c +++ b/drivers/clocksource/timer-imx-tpm.c @@ -83,20 +83,28 @@ static u64 notrace tpm_read_sched_clock(void) static int tpm_set_next_event(unsigned long delta, struct clock_event_device *evt) { - unsigned long next, now; + unsigned long next, prev, now; - next = tpm_read_counter(); - next += delta; + prev = tpm_read_counter(); + next = prev + delta; writel(next, timer_base + TPM_C0V); now = tpm_read_counter(); + /* + * Need to wait CNT increase at least 1 cycle to make sure + * the C0V has been updated into HW. + */ + if ((next & 0xffffffff) != readl(timer_base + TPM_C0V)) + while (now == tpm_read_counter()) + ; + /* * NOTE: We observed in a very small probability, the bus fabric * contention between GPU and A7 may results a few cycles delay * of writing CNT registers which may cause the min_delta event got * missed, so we need add a ETIME check here in case it happened. */ - return (int)(next - now) <= 0 ? -ETIME : 0; + return (now - prev) >= delta ? -ETIME : 0; } static int tpm_set_state_oneshot(struct clock_event_device *evt) diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c index c3f54d9912be79..420202bf76e42c 100644 --- a/drivers/clocksource/timer-of.c +++ b/drivers/clocksource/timer-of.c @@ -25,10 +25,7 @@ static __init void timer_of_irq_exit(struct of_timer_irq *of_irq) struct clock_event_device *clkevt = &to->clkevt; - if (of_irq->percpu) - free_percpu_irq(of_irq->irq, clkevt); - else - free_irq(of_irq->irq, clkevt); + free_irq(of_irq->irq, clkevt); } /** @@ -42,9 +39,6 @@ static __init void timer_of_irq_exit(struct of_timer_irq *of_irq) * - Get interrupt number by name * - Get interrupt number by index * - * When the interrupt is per CPU, 'request_percpu_irq()' is called, - * otherwise 'request_irq()' is used. - * * Returns 0 on success, < 0 otherwise */ static __init int timer_of_irq_init(struct device_node *np, @@ -69,12 +63,9 @@ static __init int timer_of_irq_init(struct device_node *np, return -EINVAL; } - ret = of_irq->percpu ? - request_percpu_irq(of_irq->irq, of_irq->handler, - np->full_name, clkevt) : - request_irq(of_irq->irq, of_irq->handler, - of_irq->flags ? of_irq->flags : IRQF_TIMER, - np->full_name, clkevt); + ret = request_irq(of_irq->irq, of_irq->handler, + of_irq->flags ? of_irq->flags : IRQF_TIMER, + np->full_name, clkevt); if (ret) { pr_err("Failed to request irq %d for %pOF\n", of_irq->irq, np); return ret; diff --git a/drivers/clocksource/timer-of.h b/drivers/clocksource/timer-of.h index a5478f3e8589df..01a2c6b7db0659 100644 --- a/drivers/clocksource/timer-of.h +++ b/drivers/clocksource/timer-of.h @@ -11,7 +11,6 @@ struct of_timer_irq { int irq; int index; - int percpu; const char *name; unsigned long flags; irq_handler_t handler; diff --git a/drivers/clocksource/timer-qcom.c b/drivers/clocksource/timer-qcom.c index b4afe3a6758351..eac4c95c6127f2 100644 --- a/drivers/clocksource/timer-qcom.c +++ b/drivers/clocksource/timer-qcom.c @@ -233,6 +233,7 @@ static int __init msm_dt_timer_init(struct device_node *np) } if (of_property_read_u32(np, "clock-frequency", &freq)) { + iounmap(cpu0_base); pr_err("Unknown frequency\n"); return -EINVAL; } @@ -243,7 +244,11 @@ static int __init msm_dt_timer_init(struct device_node *np) freq /= 4; writel_relaxed(DGT_CLK_CTL_DIV_4, source_base + DGT_CLK_CTL); - return msm_timer_init(freq, 32, irq, !!percpu_offset); + ret = msm_timer_init(freq, 32, irq, !!percpu_offset); + if (ret) + iounmap(cpu0_base); + + return ret; } TIMER_OF_DECLARE(kpss_timer, "qcom,kpss-timer", msm_dt_timer_init); TIMER_OF_DECLARE(scss_timer, "qcom,scss-timer", msm_dt_timer_init); diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index 09ab29cb7f6416..56acf26172621f 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -140,6 +140,8 @@ struct dmtimer { struct platform_device *pdev; struct list_head node; struct notifier_block nb; + struct notifier_block fclk_nb; + unsigned long fclk_rate; }; static u32 omap_reserved_systimers; @@ -181,7 +183,7 @@ static inline u32 dmtimer_read(struct dmtimer *timer, u32 reg) * dmtimer_write - write timer registers in posted and non-posted mode * @timer: timer pointer over which write operation is to perform * @reg: lowest byte holds the register offset - * @value: data to write into the register + * @val: data to write into the register * * The posted mode bit is encoded in reg. Note that in posted mode, the write * pending bit must be checked. Otherwise a write on a register which has a @@ -253,8 +255,7 @@ static inline void __omap_dm_timer_enable_posted(struct dmtimer *timer) timer->posted = OMAP_TIMER_POSTED; } -static inline void __omap_dm_timer_stop(struct dmtimer *timer, - unsigned long rate) +static inline void __omap_dm_timer_stop(struct dmtimer *timer) { u32 l; @@ -269,7 +270,7 @@ static inline void __omap_dm_timer_stop(struct dmtimer *timer, * Wait for functional clock period x 3.5 to make sure that * timer is stopped */ - udelay(3500000 / rate + 1); + udelay(3500000 / timer->fclk_rate + 1); #endif } @@ -348,6 +349,21 @@ static int omap_timer_context_notifier(struct notifier_block *nb, return NOTIFY_OK; } +static int omap_timer_fclk_notifier(struct notifier_block *nb, + unsigned long event, void *data) +{ + struct clk_notifier_data *clk_data = data; + struct dmtimer *timer = container_of(nb, struct dmtimer, fclk_nb); + + switch (event) { + case POST_RATE_CHANGE: + timer->fclk_rate = clk_data->new_rate; + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + static int omap_dm_timer_reset(struct dmtimer *timer) { u32 l, timeout = 100000; @@ -754,7 +770,6 @@ static int omap_dm_timer_stop(struct omap_dm_timer *cookie) { struct dmtimer *timer; struct device *dev; - unsigned long rate = 0; timer = to_dmtimer(cookie); if (unlikely(!timer)) @@ -762,10 +777,7 @@ static int omap_dm_timer_stop(struct omap_dm_timer *cookie) dev = &timer->pdev->dev; - if (!timer->omap1) - rate = clk_get_rate(timer->fclk); - - __omap_dm_timer_stop(timer, rate); + __omap_dm_timer_stop(timer); pm_runtime_put_sync(dev); @@ -937,7 +949,7 @@ static int omap_dm_timer_set_int_enable(struct omap_dm_timer *cookie, /** * omap_dm_timer_set_int_disable - disable timer interrupts - * @timer: pointer to timer handle + * @cookie: pointer to timer cookie * @mask: bit mask of interrupts to be disabled * * Disables the specified timer interrupts for a timer. @@ -1124,6 +1136,14 @@ static int omap_dm_timer_probe(struct platform_device *pdev) timer->fclk = devm_clk_get(dev, "fck"); if (IS_ERR(timer->fclk)) return PTR_ERR(timer->fclk); + + timer->fclk_nb.notifier_call = omap_timer_fclk_notifier; + ret = devm_clk_notifier_register(dev, timer->fclk, + &timer->fclk_nb); + if (ret) + return ret; + + timer->fclk_rate = clk_get_rate(timer->fclk); } else { timer->fclk = ERR_PTR(-ENODEV); } diff --git a/drivers/comedi/drivers/comedi_test.c b/drivers/comedi/drivers/comedi_test.c index 30ea8b53ebf819..05ae9122823f80 100644 --- a/drivers/comedi/drivers/comedi_test.c +++ b/drivers/comedi/drivers/comedi_test.c @@ -87,6 +87,8 @@ struct waveform_private { struct comedi_device *dev; /* parent comedi device */ u64 ao_last_scan_time; /* time of previous AO scan in usec */ unsigned int ao_scan_period; /* AO scan period in usec */ + bool ai_timer_enable:1; /* should AI timer be running? */ + bool ao_timer_enable:1; /* should AO timer be running? */ unsigned short ao_loopbacks[N_CHANS]; }; @@ -236,8 +238,12 @@ static void waveform_ai_timer(struct timer_list *t) time_increment = devpriv->ai_convert_time - now; else time_increment = 1; - mod_timer(&devpriv->ai_timer, - jiffies + usecs_to_jiffies(time_increment)); + spin_lock(&dev->spinlock); + if (devpriv->ai_timer_enable) { + mod_timer(&devpriv->ai_timer, + jiffies + usecs_to_jiffies(time_increment)); + } + spin_unlock(&dev->spinlock); } overrun: @@ -393,9 +399,12 @@ static int waveform_ai_cmd(struct comedi_device *dev, * Seem to need an extra jiffy here, otherwise timer expires slightly * early! */ + spin_lock_bh(&dev->spinlock); + devpriv->ai_timer_enable = true; devpriv->ai_timer.expires = jiffies + usecs_to_jiffies(devpriv->ai_convert_period) + 1; add_timer(&devpriv->ai_timer); + spin_unlock_bh(&dev->spinlock); return 0; } @@ -404,6 +413,9 @@ static int waveform_ai_cancel(struct comedi_device *dev, { struct waveform_private *devpriv = dev->private; + spin_lock_bh(&dev->spinlock); + devpriv->ai_timer_enable = false; + spin_unlock_bh(&dev->spinlock); if (in_softirq()) { /* Assume we were called from the timer routine itself. */ del_timer(&devpriv->ai_timer); @@ -495,8 +507,12 @@ static void waveform_ao_timer(struct timer_list *t) unsigned int time_inc = devpriv->ao_last_scan_time + devpriv->ao_scan_period - now; - mod_timer(&devpriv->ao_timer, - jiffies + usecs_to_jiffies(time_inc)); + spin_lock(&dev->spinlock); + if (devpriv->ao_timer_enable) { + mod_timer(&devpriv->ao_timer, + jiffies + usecs_to_jiffies(time_inc)); + } + spin_unlock(&dev->spinlock); } underrun: @@ -517,9 +533,12 @@ static int waveform_ao_inttrig_start(struct comedi_device *dev, async->inttrig = NULL; devpriv->ao_last_scan_time = ktime_to_us(ktime_get()); + spin_lock_bh(&dev->spinlock); + devpriv->ao_timer_enable = true; devpriv->ao_timer.expires = jiffies + usecs_to_jiffies(devpriv->ao_scan_period); add_timer(&devpriv->ao_timer); + spin_unlock_bh(&dev->spinlock); return 1; } @@ -604,6 +623,9 @@ static int waveform_ao_cancel(struct comedi_device *dev, struct waveform_private *devpriv = dev->private; s->async->inttrig = NULL; + spin_lock_bh(&dev->spinlock); + devpriv->ao_timer_enable = false; + spin_unlock_bh(&dev->spinlock); if (in_softirq()) { /* Assume we were called from the timer routine itself. */ del_timer(&devpriv->ao_timer); diff --git a/drivers/comedi/drivers/ni_routing/tools/convert_c_to_py.c b/drivers/comedi/drivers/ni_routing/tools/convert_c_to_py.c index d55521b5bdcb2d..892a66b2cea665 100644 --- a/drivers/comedi/drivers/ni_routing/tools/convert_c_to_py.c +++ b/drivers/comedi/drivers/ni_routing/tools/convert_c_to_py.c @@ -140,6 +140,11 @@ int main(void) { FILE *fp = fopen("ni_values.py", "w"); + if (fp == NULL) { + fprintf(stderr, "Could not open file!"); + return -1; + } + /* write route register values */ fprintf(fp, "ni_route_values = {\n"); for (int i = 0; ni_all_route_values[i]; ++i) diff --git a/drivers/comedi/drivers/vmk80xx.c b/drivers/comedi/drivers/vmk80xx.c index 4536ed43f65b27..84dce5184a77ae 100644 --- a/drivers/comedi/drivers/vmk80xx.c +++ b/drivers/comedi/drivers/vmk80xx.c @@ -641,33 +641,22 @@ static int vmk80xx_find_usb_endpoints(struct comedi_device *dev) struct vmk80xx_private *devpriv = dev->private; struct usb_interface *intf = comedi_to_usb_interface(dev); struct usb_host_interface *iface_desc = intf->cur_altsetting; - struct usb_endpoint_descriptor *ep_desc; - int i; - - if (iface_desc->desc.bNumEndpoints != 2) - return -ENODEV; - - for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) { - ep_desc = &iface_desc->endpoint[i].desc; - - if (usb_endpoint_is_int_in(ep_desc) || - usb_endpoint_is_bulk_in(ep_desc)) { - if (!devpriv->ep_rx) - devpriv->ep_rx = ep_desc; - continue; - } + struct usb_endpoint_descriptor *ep_rx_desc, *ep_tx_desc; + int ret; - if (usb_endpoint_is_int_out(ep_desc) || - usb_endpoint_is_bulk_out(ep_desc)) { - if (!devpriv->ep_tx) - devpriv->ep_tx = ep_desc; - continue; - } - } + if (devpriv->model == VMK8061_MODEL) + ret = usb_find_common_endpoints(iface_desc, &ep_rx_desc, + &ep_tx_desc, NULL, NULL); + else + ret = usb_find_common_endpoints(iface_desc, NULL, NULL, + &ep_rx_desc, &ep_tx_desc); - if (!devpriv->ep_rx || !devpriv->ep_tx) + if (ret) return -ENODEV; + devpriv->ep_rx = ep_rx_desc; + devpriv->ep_tx = ep_tx_desc; + if (!usb_endpoint_maxp(devpriv->ep_rx) || !usb_endpoint_maxp(devpriv->ep_tx)) return -EINVAL; diff --git a/drivers/counter/ti-eqep.c b/drivers/counter/ti-eqep.c index b0f24cf3e891de..4d3de4a35801fc 100644 --- a/drivers/counter/ti-eqep.c +++ b/drivers/counter/ti-eqep.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include @@ -376,6 +377,7 @@ static int ti_eqep_probe(struct platform_device *pdev) struct counter_device *counter; struct ti_eqep_cnt *priv; void __iomem *base; + struct clk *clk; int err; counter = devm_counter_alloc(dev, sizeof(*priv)); @@ -415,6 +417,10 @@ static int ti_eqep_probe(struct platform_device *pdev) pm_runtime_enable(dev); pm_runtime_get_sync(dev); + clk = devm_clk_get_enabled(dev, NULL); + if (IS_ERR(clk)) + return dev_err_probe(dev, PTR_ERR(clk), "failed to enable clock\n"); + err = counter_add(counter); if (err < 0) { pm_runtime_put_sync(dev); diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 123b4bbfcfee19..c5cecbd89ba9ce 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -173,6 +173,7 @@ config ARM_QCOM_CPUFREQ_NVMEM config ARM_QCOM_CPUFREQ_HW tristate "QCOM CPUFreq HW driver" depends on ARCH_QCOM || COMPILE_TEST + depends on COMMON_CLK help Support for the CPUFreq HW driver. Some QCOM chipsets have a HW engine to offload the steps diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 37f1cdf46d2918..4ac3a35dcd983c 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -890,8 +890,10 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) if (perf->states[0].core_frequency * 1000 != freq_table[0].frequency) pr_warn(FW_WARN "P-state 0 is not max freq\n"); - if (acpi_cpufreq_driver.set_boost) + if (acpi_cpufreq_driver.set_boost) { set_boost(policy, acpi_cpufreq_driver.boost_enabled); + policy->boost_enabled = acpi_cpufreq_driver.boost_enabled; + } return result; diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 9a1e194d5cf882..f461f99eb040c6 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include @@ -49,6 +50,8 @@ #define AMD_PSTATE_TRANSITION_LATENCY 20000 #define AMD_PSTATE_TRANSITION_DELAY 1000 +#define CPPC_HIGHEST_PERF_PERFORMANCE 196 +#define CPPC_HIGHEST_PERF_DEFAULT 166 /* * TODO: We need more time to fine tune processors with shared memory solution @@ -64,6 +67,7 @@ static struct cpufreq_driver amd_pstate_driver; static struct cpufreq_driver amd_pstate_epp_driver; static int cppc_state = AMD_PSTATE_UNDEFINED; static bool cppc_enabled; +static bool amd_pstate_prefcore = true; /* * AMD Energy Preference Performance (EPP) @@ -175,6 +179,26 @@ static int amd_pstate_get_energy_pref_index(struct amd_cpudata *cpudata) return index; } +static void pstate_update_perf(struct amd_cpudata *cpudata, u32 min_perf, + u32 des_perf, u32 max_perf, bool fast_switch) +{ + if (fast_switch) + wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached)); + else + wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, + READ_ONCE(cpudata->cppc_req_cached)); +} + +DEFINE_STATIC_CALL(amd_pstate_update_perf, pstate_update_perf); + +static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata, + u32 min_perf, u32 des_perf, + u32 max_perf, bool fast_switch) +{ + static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf, + max_perf, fast_switch); +} + static int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp) { int ret; @@ -191,6 +215,9 @@ static int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp) if (!ret) cpudata->epp_cached = epp; } else { + amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U, + cpudata->max_limit_perf, false); + perf_ctrls.energy_perf = epp; ret = cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1); if (ret) { @@ -287,6 +314,21 @@ static inline int amd_pstate_enable(bool enable) return static_call(amd_pstate_enable)(enable); } +static u32 amd_pstate_highest_perf_set(struct amd_cpudata *cpudata) +{ + struct cpuinfo_x86 *c = &cpu_data(0); + + /* + * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f, + * the highest performance level is set to 196. + * https://bugzilla.kernel.org/show_bug.cgi?id=218759 + */ + if (c->x86 == 0x19 && (c->x86_model >= 0x70 && c->x86_model <= 0x7f)) + return CPPC_HIGHEST_PERF_PERFORMANCE; + + return CPPC_HIGHEST_PERF_DEFAULT; +} + static int pstate_init_perf(struct amd_cpudata *cpudata) { u64 cap1; @@ -297,21 +339,22 @@ static int pstate_init_perf(struct amd_cpudata *cpudata) if (ret) return ret; - /* - * TODO: Introduce AMD specific power feature. - * - * CPPC entry doesn't indicate the highest performance in some ASICs. + /* For platforms that do not support the preferred core feature, the + * highest_pef may be configured with 166 or 255, to avoid max frequency + * calculated wrongly. we take the AMD_CPPC_HIGHEST_PERF(cap1) value as + * the default max perf. */ - highest_perf = amd_get_highest_perf(); - if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1)) + if (cpudata->hw_prefcore) + highest_perf = amd_pstate_highest_perf_set(cpudata); + else highest_perf = AMD_CPPC_HIGHEST_PERF(cap1); WRITE_ONCE(cpudata->highest_perf, highest_perf); - + WRITE_ONCE(cpudata->max_limit_perf, highest_perf); WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1)); - + WRITE_ONCE(cpudata->min_limit_perf, AMD_CPPC_LOWEST_PERF(cap1)); return 0; } @@ -324,16 +367,18 @@ static int cppc_init_perf(struct amd_cpudata *cpudata) if (ret) return ret; - highest_perf = amd_get_highest_perf(); - if (highest_perf > cppc_perf.highest_perf) + if (cpudata->hw_prefcore) + highest_perf = amd_pstate_highest_perf_set(cpudata); + else highest_perf = cppc_perf.highest_perf; WRITE_ONCE(cpudata->highest_perf, highest_perf); - + WRITE_ONCE(cpudata->max_limit_perf, highest_perf); WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf); WRITE_ONCE(cpudata->lowest_nonlinear_perf, cppc_perf.lowest_nonlinear_perf); WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf); + WRITE_ONCE(cpudata->min_limit_perf, cppc_perf.lowest_perf); if (cppc_state == AMD_PSTATE_ACTIVE) return 0; @@ -360,16 +405,6 @@ static inline int amd_pstate_init_perf(struct amd_cpudata *cpudata) return static_call(amd_pstate_init_perf)(cpudata); } -static void pstate_update_perf(struct amd_cpudata *cpudata, u32 min_perf, - u32 des_perf, u32 max_perf, bool fast_switch) -{ - if (fast_switch) - wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached)); - else - wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, - READ_ONCE(cpudata->cppc_req_cached)); -} - static void cppc_update_perf(struct amd_cpudata *cpudata, u32 min_perf, u32 des_perf, u32 max_perf, bool fast_switch) @@ -383,16 +418,6 @@ static void cppc_update_perf(struct amd_cpudata *cpudata, cppc_set_perf(cpudata->cpu, &perf_ctrls); } -DEFINE_STATIC_CALL(amd_pstate_update_perf, pstate_update_perf); - -static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata, - u32 min_perf, u32 des_perf, - u32 max_perf, bool fast_switch) -{ - static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf, - max_perf, fast_switch); -} - static inline bool amd_pstate_sample(struct amd_cpudata *cpudata) { u64 aperf, mperf, tsc; @@ -432,6 +457,10 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf, u64 prev = READ_ONCE(cpudata->cppc_req_cached); u64 value = prev; + min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf, + cpudata->max_limit_perf); + max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf, + cpudata->max_limit_perf); des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf); if ((cppc_state == AMD_PSTATE_GUIDED) && (gov_flags & CPUFREQ_GOV_DYNAMIC_SWITCHING)) { @@ -470,6 +499,22 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy) return 0; } +static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy) +{ + u32 max_limit_perf, min_limit_perf; + struct amd_cpudata *cpudata = policy->driver_data; + + max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq); + min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq); + + WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf); + WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf); + WRITE_ONCE(cpudata->max_limit_freq, policy->max); + WRITE_ONCE(cpudata->min_limit_freq, policy->min); + + return 0; +} + static int amd_pstate_update_freq(struct cpufreq_policy *policy, unsigned int target_freq, bool fast_switch) { @@ -480,6 +525,9 @@ static int amd_pstate_update_freq(struct cpufreq_policy *policy, if (!cpudata->max_freq) return -ENODEV; + if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq) + amd_pstate_update_min_max_limit(policy); + cap_perf = READ_ONCE(cpudata->highest_perf); min_perf = READ_ONCE(cpudata->lowest_perf); max_perf = cap_perf; @@ -518,7 +566,9 @@ static int amd_pstate_target(struct cpufreq_policy *policy, static unsigned int amd_pstate_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq) { - return amd_pstate_update_freq(policy, target_freq, true); + if (!amd_pstate_update_freq(policy, target_freq, true)) + return target_freq; + return policy->cur; } static void amd_pstate_adjust_perf(unsigned int cpu, @@ -532,6 +582,10 @@ static void amd_pstate_adjust_perf(unsigned int cpu, struct amd_cpudata *cpudata = policy->driver_data; unsigned int target_freq; + if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq) + amd_pstate_update_min_max_limit(policy); + + cap_perf = READ_ONCE(cpudata->highest_perf); lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); max_freq = READ_ONCE(cpudata->max_freq); @@ -540,7 +594,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu, if (target_perf < capacity) des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity); - min_perf = READ_ONCE(cpudata->highest_perf); + min_perf = READ_ONCE(cpudata->lowest_perf); if (_min_perf < capacity) min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity); @@ -676,6 +730,80 @@ static void amd_perf_ctl_reset(unsigned int cpu) wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0); } +/* + * Set amd-pstate preferred core enable can't be done directly from cpufreq callbacks + * due to locking, so queue the work for later. + */ +static void amd_pstste_sched_prefcore_workfn(struct work_struct *work) +{ + sched_set_itmt_support(); +} +static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn); + +/* + * Get the highest performance register value. + * @cpu: CPU from which to get highest performance. + * @highest_perf: Return address. + * + * Return: 0 for success, -EIO otherwise. + */ +static int amd_pstate_get_highest_perf(int cpu, u32 *highest_perf) +{ + int ret; + + if (boot_cpu_has(X86_FEATURE_CPPC)) { + u64 cap1; + + ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &cap1); + if (ret) + return ret; + WRITE_ONCE(*highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); + } else { + u64 cppc_highest_perf; + + ret = cppc_get_highest_perf(cpu, &cppc_highest_perf); + if (ret) + return ret; + WRITE_ONCE(*highest_perf, cppc_highest_perf); + } + + return (ret); +} + +#define CPPC_MAX_PERF U8_MAX + +static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata) +{ + int ret, prio; + u32 highest_perf; + + ret = amd_pstate_get_highest_perf(cpudata->cpu, &highest_perf); + if (ret) + return; + + cpudata->hw_prefcore = true; + /* check if CPPC preferred core feature is enabled*/ + if (highest_perf < CPPC_MAX_PERF) + prio = (int)highest_perf; + else { + pr_debug("AMD CPPC preferred core is unsupported!\n"); + cpudata->hw_prefcore = false; + return; + } + + if (!amd_pstate_prefcore) + return; + + /* + * The priorities can be set regardless of whether or not + * sched_set_itmt_support(true) has been called and it is valid to + * update them at any time after it has been called. + */ + sched_set_itmt_core_prio(prio, cpudata->cpu); + + schedule_work(&sched_prefcore_work); +} + static int amd_pstate_cpu_init(struct cpufreq_policy *policy) { int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; @@ -697,6 +825,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) cpudata->cpu = policy->cpu; + amd_pstate_init_prefcore(cpudata); + ret = amd_pstate_init_perf(cpudata); if (ret) goto free_cpudata1; @@ -745,6 +875,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) /* Initial processor data capability frequencies */ cpudata->max_freq = max_freq; cpudata->min_freq = min_freq; + cpudata->max_limit_freq = max_freq; + cpudata->min_limit_freq = min_freq; cpudata->nominal_freq = nominal_freq; cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq; @@ -845,16 +977,32 @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy, return sysfs_emit(buf, "%u\n", perf); } +static ssize_t show_amd_pstate_hw_prefcore(struct cpufreq_policy *policy, + char *buf) +{ + bool hw_prefcore; + struct amd_cpudata *cpudata = policy->driver_data; + + hw_prefcore = READ_ONCE(cpudata->hw_prefcore); + + return sysfs_emit(buf, "%s\n", str_enabled_disabled(hw_prefcore)); +} + static ssize_t show_energy_performance_available_preferences( struct cpufreq_policy *policy, char *buf) { int i = 0; int offset = 0; + struct amd_cpudata *cpudata = policy->driver_data; + + if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) + return sysfs_emit_at(buf, offset, "%s\n", + energy_perf_strings[EPP_INDEX_PERFORMANCE]); while (energy_perf_strings[i] != NULL) offset += sysfs_emit_at(buf, offset, "%s ", energy_perf_strings[i++]); - sysfs_emit_at(buf, offset, "\n"); + offset += sysfs_emit_at(buf, offset, "\n"); return offset; } @@ -1037,18 +1185,27 @@ static ssize_t status_store(struct device *a, struct device_attribute *b, return ret < 0 ? ret : count; } +static ssize_t prefcore_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%s\n", str_enabled_disabled(amd_pstate_prefcore)); +} + cpufreq_freq_attr_ro(amd_pstate_max_freq); cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq); cpufreq_freq_attr_ro(amd_pstate_highest_perf); +cpufreq_freq_attr_ro(amd_pstate_hw_prefcore); cpufreq_freq_attr_rw(energy_performance_preference); cpufreq_freq_attr_ro(energy_performance_available_preferences); static DEVICE_ATTR_RW(status); +static DEVICE_ATTR_RO(prefcore); static struct freq_attr *amd_pstate_attr[] = { &amd_pstate_max_freq, &amd_pstate_lowest_nonlinear_freq, &amd_pstate_highest_perf, + &amd_pstate_hw_prefcore, NULL, }; @@ -1056,6 +1213,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = { &amd_pstate_max_freq, &amd_pstate_lowest_nonlinear_freq, &amd_pstate_highest_perf, + &amd_pstate_hw_prefcore, &energy_performance_preference, &energy_performance_available_preferences, NULL, @@ -1063,6 +1221,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = { static struct attribute *pstate_global_attributes[] = { &dev_attr_status.attr, + &dev_attr_prefcore.attr, NULL }; @@ -1114,6 +1273,8 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) cpudata->cpu = policy->cpu; cpudata->epp_policy = 0; + amd_pstate_init_prefcore(cpudata); + ret = amd_pstate_init_perf(cpudata); if (ret) goto free_cpudata1; @@ -1179,21 +1340,36 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) { + struct amd_cpudata *cpudata = policy->driver_data; + + if (cpudata) { + kfree(cpudata); + policy->driver_data = NULL; + } + pr_debug("CPU %d exiting\n", policy->cpu); return 0; } -static void amd_pstate_epp_init(unsigned int cpu) +static void amd_pstate_epp_update_limit(struct cpufreq_policy *policy) { - struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); struct amd_cpudata *cpudata = policy->driver_data; - u32 max_perf, min_perf; + u32 max_perf, min_perf, min_limit_perf, max_limit_perf; u64 value; s16 epp; max_perf = READ_ONCE(cpudata->highest_perf); min_perf = READ_ONCE(cpudata->lowest_perf); + max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq); + min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq); + WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf); + WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf); + + max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf, + cpudata->max_limit_perf); + min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf, + cpudata->max_limit_perf); value = READ_ONCE(cpudata->cppc_req_cached); if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) @@ -1210,9 +1386,6 @@ static void amd_pstate_epp_init(unsigned int cpu) value &= ~AMD_CPPC_DES_PERF(~0L); value |= AMD_CPPC_DES_PERF(0); - if (cpudata->epp_policy == cpudata->policy) - goto skip_epp; - cpudata->epp_policy = cpudata->policy; /* Get BIOS pre-defined epp value */ @@ -1222,7 +1395,7 @@ static void amd_pstate_epp_init(unsigned int cpu) * This return value can only be negative for shared_memory * systems where EPP register read/write not supported. */ - goto skip_epp; + return; } if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) @@ -1236,8 +1409,6 @@ static void amd_pstate_epp_init(unsigned int cpu) WRITE_ONCE(cpudata->cppc_req_cached, value); amd_pstate_set_epp(cpudata, epp); -skip_epp: - cpufreq_cpu_put(policy); } static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) @@ -1252,7 +1423,7 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) cpudata->policy = policy->policy; - amd_pstate_epp_init(policy->cpu); + amd_pstate_epp_update_limit(policy); return 0; } @@ -1527,7 +1698,17 @@ static int __init amd_pstate_param(char *str) return amd_pstate_set_driver(mode_idx); } + +static int __init amd_prefcore_param(char *str) +{ + if (!strcmp(str, "disable")) + amd_pstate_prefcore = false; + + return 0; +} + early_param("amd_pstate", amd_pstate_param); +early_param("amd_prefcore", amd_prefcore_param); MODULE_AUTHOR("Huang Rui "); MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver"); diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index 35fb3a559ea97b..ea8438550b4901 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -481,7 +481,12 @@ static bool brcm_avs_is_firmware_loaded(struct private_data *priv) static unsigned int brcm_avs_cpufreq_get(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct private_data *priv = policy->driver_data; + struct private_data *priv; + + if (!policy) + return 0; + + priv = policy->driver_data; cpufreq_cpu_put(policy); diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index fe08ca419b3dc3..1ba3943be8a3dd 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -844,10 +844,15 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu) { struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0}; struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct cppc_cpudata *cpu_data = policy->driver_data; + struct cppc_cpudata *cpu_data; u64 delivered_perf; int ret; + if (!policy) + return -ENODEV; + + cpu_data = policy->driver_data; + cpufreq_cpu_put(policy); ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t0); @@ -927,10 +932,15 @@ static struct cpufreq_driver cppc_cpufreq_driver = { static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct cppc_cpudata *cpu_data = policy->driver_data; + struct cppc_cpudata *cpu_data; u64 desired_perf; int ret; + if (!policy) + return -ENODEV; + + cpu_data = policy->driver_data; + cpufreq_cpu_put(policy); ret = cppc_get_desired_perf(cpu, &desired_perf); diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 8bd6e5e8f121ce..2d83bbc65dd0bd 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -208,7 +208,7 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu) if (!priv) return -ENOMEM; - if (!alloc_cpumask_var(&priv->cpus, GFP_KERNEL)) + if (!zalloc_cpumask_var(&priv->cpus, GFP_KERNEL)) return -ENOMEM; cpumask_set_cpu(cpu, priv->cpus); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 60ed89000e82dc..df445b44e9ec0b 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -644,14 +644,16 @@ static ssize_t store_local_boost(struct cpufreq_policy *policy, if (policy->boost_enabled == enable) return count; + policy->boost_enabled = enable; + cpus_read_lock(); ret = cpufreq_driver->set_boost(policy, enable); cpus_read_unlock(); - if (ret) + if (ret) { + policy->boost_enabled = !policy->boost_enabled; return ret; - - policy->boost_enabled = enable; + } return count; } @@ -1419,6 +1421,10 @@ static int cpufreq_online(unsigned int cpu) goto out_free_policy; } + /* Let the per-policy boost flag mirror the cpufreq_driver boost during init */ + if (cpufreq_boost_enabled() && policy_has_boost_freq(policy)) + policy->boost_enabled = true; + /* * The initialization has succeeded and the policy is online. * If there is a problem with its frequency table, take it @@ -1571,7 +1577,8 @@ static int cpufreq_online(unsigned int cpu) if (cpufreq_driver->ready) cpufreq_driver->ready(policy); - if (cpufreq_thermal_control_enabled(cpufreq_driver)) + /* Register cpufreq cooling only for a new policy */ + if (new_policy && cpufreq_thermal_control_enabled(cpufreq_driver)) policy->cdev = of_cpufreq_cooling_register(policy); pr_debug("initialization complete\n"); @@ -1655,11 +1662,6 @@ static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy) else policy->last_policy = policy->policy; - if (cpufreq_thermal_control_enabled(cpufreq_driver)) { - cpufreq_cooling_unregister(policy->cdev); - policy->cdev = NULL; - } - if (has_target()) cpufreq_exit_governor(policy); @@ -1669,10 +1671,13 @@ static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy) */ if (cpufreq_driver->offline) { cpufreq_driver->offline(policy); - } else if (cpufreq_driver->exit) { - cpufreq_driver->exit(policy); - policy->freq_table = NULL; + return; } + + if (cpufreq_driver->exit) + cpufreq_driver->exit(policy); + + policy->freq_table = NULL; } static int cpufreq_offline(unsigned int cpu) @@ -1720,8 +1725,17 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) return; } + /* + * Unregister cpufreq cooling once all the CPUs of the policy are + * removed. + */ + if (cpufreq_thermal_control_enabled(cpufreq_driver)) { + cpufreq_cooling_unregister(policy->cdev); + policy->cdev = NULL; + } + /* We did light-weight exit earlier, do full tear down now */ - if (cpufreq_driver->offline) + if (cpufreq_driver->offline && cpufreq_driver->exit) cpufreq_driver->exit(policy); up_write(&policy->rwsem); @@ -2756,11 +2770,12 @@ int cpufreq_boost_trigger_state(int state) cpus_read_lock(); for_each_active_policy(policy) { + policy->boost_enabled = state; ret = cpufreq_driver->set_boost(policy, state); - if (ret) + if (ret) { + policy->boost_enabled = !policy->boost_enabled; goto err_reset_state; - - policy->boost_enabled = state; + } } cpus_read_unlock(); diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index a33df3c66c88c2..40a9ff18da068c 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -131,23 +131,23 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) len += sysfs_emit_at(buf, len, " From : To\n"); len += sysfs_emit_at(buf, len, " : "); for (i = 0; i < stats->state_num; i++) { - if (len >= PAGE_SIZE) + if (len >= PAGE_SIZE - 1) break; len += sysfs_emit_at(buf, len, "%9u ", stats->freq_table[i]); } - if (len >= PAGE_SIZE) - return PAGE_SIZE; + if (len >= PAGE_SIZE - 1) + return PAGE_SIZE - 1; len += sysfs_emit_at(buf, len, "\n"); for (i = 0; i < stats->state_num; i++) { - if (len >= PAGE_SIZE) + if (len >= PAGE_SIZE - 1) break; len += sysfs_emit_at(buf, len, "%9u: ", stats->freq_table[i]); for (j = 0; j < stats->state_num; j++) { - if (len >= PAGE_SIZE) + if (len >= PAGE_SIZE - 1) break; if (pending) @@ -157,12 +157,12 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) len += sysfs_emit_at(buf, len, "%9u ", count); } - if (len >= PAGE_SIZE) + if (len >= PAGE_SIZE - 1) break; len += sysfs_emit_at(buf, len, "\n"); } - if (len >= PAGE_SIZE) { + if (len >= PAGE_SIZE - 1) { pr_warn_once("cpufreq transition table exceeds PAGE_SIZE. Disabling\n"); return -EFBIG; } diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index c4d4643b6ca650..c17dc51a5a022d 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -40,7 +40,7 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy, cpufreq_for_each_valid_entry(pos, table) { freq = pos->frequency; - if (!cpufreq_boost_enabled() + if ((!cpufreq_boost_enabled() || !policy->boost_enabled) && (pos->flags & CPUFREQ_BOOST_FREQ)) continue; diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 494d044b9e7207..33728c242f66ca 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -327,7 +327,7 @@ static int imx6ul_opp_check_speed_grading(struct device *dev) imx6x_disable_freq_in_opp(dev, 696000000); if (of_machine_is_compatible("fsl,imx6ull")) { - if (val != OCOTP_CFG3_6ULL_SPEED_792MHZ) + if (val < OCOTP_CFG3_6ULL_SPEED_792MHZ) imx6x_disable_freq_in_opp(dev, 792000000); if (val != OCOTP_CFG3_6ULL_SPEED_900MHZ) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index dc50c9fb488dfc..8a4fdf212ce0de 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -356,15 +356,14 @@ static void intel_pstate_set_itmt_prio(int cpu) int ret; ret = cppc_get_perf_caps(cpu, &cppc_perf); - if (ret) - return; - /* - * On some systems with overclocking enabled, CPPC.highest_perf is hardcoded to 0xff. - * In this case we can't use CPPC.highest_perf to enable ITMT. - * In this case we can look at MSR_HWP_CAPABILITIES bits [8:0] to decide. + * If CPPC is not available, fall back to MSR_HWP_CAPABILITIES bits [8:0]. + * + * Also, on some systems with overclocking enabled, CPPC.highest_perf is + * hardcoded to 0xff, so CPPC.highest_perf cannot be used to enable ITMT. + * Fall back to MSR_HWP_CAPABILITIES then too. */ - if (cppc_perf.highest_perf == CPPC_MAX_PERF) + if (ret || cppc_perf.highest_perf == CPPC_MAX_PERF) cppc_perf.highest_perf = HWP_HIGHEST_PERF(READ_ONCE(all_cpu_data[cpu]->hwp_cap_cached)); /* @@ -526,6 +525,30 @@ static int intel_pstate_cppc_get_scaling(int cpu) } #endif /* CONFIG_ACPI_CPPC_LIB */ +static int intel_pstate_freq_to_hwp_rel(struct cpudata *cpu, int freq, + unsigned int relation) +{ + if (freq == cpu->pstate.turbo_freq) + return cpu->pstate.turbo_pstate; + + if (freq == cpu->pstate.max_freq) + return cpu->pstate.max_pstate; + + switch (relation) { + case CPUFREQ_RELATION_H: + return freq / cpu->pstate.scaling; + case CPUFREQ_RELATION_C: + return DIV_ROUND_CLOSEST(freq, cpu->pstate.scaling); + } + + return DIV_ROUND_UP(freq, cpu->pstate.scaling); +} + +static int intel_pstate_freq_to_hwp(struct cpudata *cpu, int freq) +{ + return intel_pstate_freq_to_hwp_rel(cpu, freq, CPUFREQ_RELATION_L); +} + /** * intel_pstate_hybrid_hwp_adjust - Calibrate HWP performance levels. * @cpu: Target CPU. @@ -543,6 +566,7 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu) int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling; int perf_ctl_turbo = pstate_funcs.get_turbo(cpu->cpu); int scaling = cpu->pstate.scaling; + int freq; pr_debug("CPU%d: perf_ctl_max_phys = %d\n", cpu->cpu, perf_ctl_max_phys); pr_debug("CPU%d: perf_ctl_turbo = %d\n", cpu->cpu, perf_ctl_turbo); @@ -556,16 +580,16 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu) cpu->pstate.max_freq = rounddown(cpu->pstate.max_pstate * scaling, perf_ctl_scaling); - cpu->pstate.max_pstate_physical = - DIV_ROUND_UP(perf_ctl_max_phys * perf_ctl_scaling, - scaling); + freq = perf_ctl_max_phys * perf_ctl_scaling; + cpu->pstate.max_pstate_physical = intel_pstate_freq_to_hwp(cpu, freq); - cpu->pstate.min_freq = cpu->pstate.min_pstate * perf_ctl_scaling; + freq = cpu->pstate.min_pstate * perf_ctl_scaling; + cpu->pstate.min_freq = freq; /* * Cast the min P-state value retrieved via pstate_funcs.get_min() to * the effective range of HWP performance levels. */ - cpu->pstate.min_pstate = DIV_ROUND_UP(cpu->pstate.min_freq, scaling); + cpu->pstate.min_pstate = intel_pstate_freq_to_hwp(cpu, freq); } static inline void update_turbo_state(void) @@ -1608,7 +1632,7 @@ static void intel_pstate_notify_work(struct work_struct *work) wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_STATUS, 0); } -static DEFINE_SPINLOCK(hwp_notify_lock); +static DEFINE_RAW_SPINLOCK(hwp_notify_lock); static cpumask_t hwp_intr_enable_mask; void notify_hwp_interrupt(void) @@ -1625,7 +1649,7 @@ void notify_hwp_interrupt(void) if (!(value & 0x01)) return; - spin_lock_irqsave(&hwp_notify_lock, flags); + raw_spin_lock_irqsave(&hwp_notify_lock, flags); if (!cpumask_test_cpu(this_cpu, &hwp_intr_enable_mask)) goto ack_intr; @@ -1649,13 +1673,13 @@ void notify_hwp_interrupt(void) schedule_delayed_work(&cpudata->hwp_notify_work, msecs_to_jiffies(10)); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_unlock_irqrestore(&hwp_notify_lock, flags); return; ack_intr: wrmsrl_safe(MSR_HWP_STATUS, 0); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_unlock_irqrestore(&hwp_notify_lock, flags); } static void intel_pstate_disable_hwp_interrupt(struct cpudata *cpudata) @@ -1668,10 +1692,10 @@ static void intel_pstate_disable_hwp_interrupt(struct cpudata *cpudata) /* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */ wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00); - spin_lock_irqsave(&hwp_notify_lock, flags); + raw_spin_lock_irqsave(&hwp_notify_lock, flags); if (cpumask_test_and_clear_cpu(cpudata->cpu, &hwp_intr_enable_mask)) cancel_delayed_work(&cpudata->hwp_notify_work); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_unlock_irqrestore(&hwp_notify_lock, flags); } static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata) @@ -1680,10 +1704,10 @@ static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata) if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) { unsigned long flags; - spin_lock_irqsave(&hwp_notify_lock, flags); + raw_spin_lock_irqsave(&hwp_notify_lock, flags); INIT_DELAYED_WORK(&cpudata->hwp_notify_work, intel_pstate_notify_work); cpumask_set_cpu(cpudata->cpu, &hwp_intr_enable_mask); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_unlock_irqrestore(&hwp_notify_lock, flags); /* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */ wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x01); @@ -2528,13 +2552,12 @@ static void intel_pstate_update_perf_limits(struct cpudata *cpu, * abstract values to represent performance rather than pure ratios. */ if (hwp_active && cpu->pstate.scaling != perf_ctl_scaling) { - int scaling = cpu->pstate.scaling; int freq; freq = max_policy_perf * perf_ctl_scaling; - max_policy_perf = DIV_ROUND_UP(freq, scaling); + max_policy_perf = intel_pstate_freq_to_hwp(cpu, freq); freq = min_policy_perf * perf_ctl_scaling; - min_policy_perf = DIV_ROUND_UP(freq, scaling); + min_policy_perf = intel_pstate_freq_to_hwp(cpu, freq); } pr_debug("cpu:%d min_policy_perf:%d max_policy_perf:%d\n", @@ -2908,18 +2931,7 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy, cpufreq_freq_transition_begin(policy, &freqs); - switch (relation) { - case CPUFREQ_RELATION_L: - target_pstate = DIV_ROUND_UP(freqs.new, cpu->pstate.scaling); - break; - case CPUFREQ_RELATION_H: - target_pstate = freqs.new / cpu->pstate.scaling; - break; - default: - target_pstate = DIV_ROUND_CLOSEST(freqs.new, cpu->pstate.scaling); - break; - } - + target_pstate = intel_pstate_freq_to_hwp_rel(cpu, freqs.new, relation); target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, false); freqs.new = target_pstate * cpu->pstate.scaling; @@ -2937,7 +2949,7 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy, update_turbo_state(); - target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling); + target_pstate = intel_pstate_freq_to_hwp(cpu, target_freq); target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true); @@ -2974,6 +2986,9 @@ static void intel_cpufreq_adjust_perf(unsigned int cpunum, if (min_pstate < cpu->min_perf_ratio) min_pstate = cpu->min_perf_ratio; + if (min_pstate > cpu->max_perf_ratio) + min_pstate = cpu->max_perf_ratio; + max_pstate = min(cap_pstate, cpu->max_perf_ratio); if (max_pstate < min_pstate) max_pstate = min_pstate; @@ -3121,10 +3136,10 @@ static void intel_pstate_driver_cleanup(void) if (intel_pstate_driver == &intel_pstate) intel_pstate_clear_update_util_hook(cpu); - spin_lock(&hwp_notify_lock); + raw_spin_lock(&hwp_notify_lock); kfree(all_cpu_data[cpu]); WRITE_ONCE(all_cpu_data[cpu], NULL); - spin_unlock(&hwp_notify_lock); + raw_spin_unlock(&hwp_notify_lock); } } cpus_read_unlock(); diff --git a/drivers/cpufreq/mediatek-cpufreq-hw.c b/drivers/cpufreq/mediatek-cpufreq-hw.c index d46afb3c009230..8d097dcddda47d 100644 --- a/drivers/cpufreq/mediatek-cpufreq-hw.c +++ b/drivers/cpufreq/mediatek-cpufreq-hw.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #define LUT_MAX_ENTRIES 32U @@ -300,7 +301,23 @@ static struct cpufreq_driver cpufreq_mtk_hw_driver = { static int mtk_cpufreq_hw_driver_probe(struct platform_device *pdev) { const void *data; - int ret; + int ret, cpu; + struct device *cpu_dev; + struct regulator *cpu_reg; + + /* Make sure that all CPU supplies are available before proceeding. */ + for_each_possible_cpu(cpu) { + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) + return dev_err_probe(&pdev->dev, -EPROBE_DEFER, + "Failed to get cpu%d device\n", cpu); + + cpu_reg = devm_regulator_get(cpu_dev, "cpu"); + if (IS_ERR(cpu_reg)) + return dev_err_probe(&pdev->dev, PTR_ERR(cpu_reg), + "CPU%d regulator get failed\n", cpu); + } + data = of_device_get_match_data(&pdev->dev); if (!data) diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c index 84d7033e5efe83..ef51dfb39baa92 100644 --- a/drivers/cpufreq/qcom-cpufreq-nvmem.c +++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c @@ -40,10 +40,14 @@ struct qcom_cpufreq_match_data { const char **genpd_names; }; +struct qcom_cpufreq_drv_cpu { + int opp_token; +}; + struct qcom_cpufreq_drv { - int *opp_tokens; u32 versions; const struct qcom_cpufreq_match_data *data; + struct qcom_cpufreq_drv_cpu cpus[]; }; static struct platform_device *cpufreq_dt_pdev, *cpufreq_pdev; @@ -243,42 +247,39 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) return -ENOENT; } - drv = kzalloc(sizeof(*drv), GFP_KERNEL); - if (!drv) + drv = devm_kzalloc(&pdev->dev, struct_size(drv, cpus, num_possible_cpus()), + GFP_KERNEL); + if (!drv) { + of_node_put(np); return -ENOMEM; + } match = pdev->dev.platform_data; drv->data = match->data; if (!drv->data) { - ret = -ENODEV; - goto free_drv; + of_node_put(np); + return -ENODEV; } if (drv->data->get_version) { speedbin_nvmem = of_nvmem_cell_get(np, NULL); if (IS_ERR(speedbin_nvmem)) { - ret = dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem), - "Could not get nvmem cell\n"); - goto free_drv; + of_node_put(np); + return dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem), + "Could not get nvmem cell\n"); } ret = drv->data->get_version(cpu_dev, speedbin_nvmem, &pvs_name, drv); if (ret) { + of_node_put(np); nvmem_cell_put(speedbin_nvmem); - goto free_drv; + return ret; } nvmem_cell_put(speedbin_nvmem); } of_node_put(np); - drv->opp_tokens = kcalloc(num_possible_cpus(), sizeof(*drv->opp_tokens), - GFP_KERNEL); - if (!drv->opp_tokens) { - ret = -ENOMEM; - goto free_drv; - } - for_each_possible_cpu(cpu) { struct dev_pm_opp_config config = { .supported_hw = NULL, @@ -304,9 +305,9 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) } if (config.supported_hw || config.genpd_names) { - drv->opp_tokens[cpu] = dev_pm_opp_set_config(cpu_dev, &config); - if (drv->opp_tokens[cpu] < 0) { - ret = drv->opp_tokens[cpu]; + drv->cpus[cpu].opp_token = dev_pm_opp_set_config(cpu_dev, &config); + if (drv->cpus[cpu].opp_token < 0) { + ret = drv->cpus[cpu].opp_token; dev_err(cpu_dev, "Failed to set OPP config\n"); goto free_opp; } @@ -325,11 +326,7 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) free_opp: for_each_possible_cpu(cpu) - dev_pm_opp_clear_config(drv->opp_tokens[cpu]); - kfree(drv->opp_tokens); -free_drv: - kfree(drv); - + dev_pm_opp_clear_config(drv->cpus[cpu].opp_token); return ret; } @@ -341,10 +338,7 @@ static void qcom_cpufreq_remove(struct platform_device *pdev) platform_device_unregister(cpufreq_dt_pdev); for_each_possible_cpu(cpu) - dev_pm_opp_clear_config(drv->opp_tokens[cpu]); - - kfree(drv->opp_tokens); - kfree(drv); + dev_pm_opp_clear_config(drv->cpus[cpu].opp_token); } static struct platform_driver qcom_cpufreq_driver = { diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index f34e6382a4c500..079940c69ee0ba 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -62,9 +62,9 @@ static unsigned int scmi_cpufreq_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq) { struct scmi_data *priv = policy->driver_data; + unsigned long freq = target_freq; - if (!perf_ops->freq_set(ph, priv->domain_id, - target_freq * 1000, true)) + if (!perf_ops->freq_set(ph, priv->domain_id, freq * 1000, true)) return target_freq; return 0; @@ -310,8 +310,11 @@ static int scmi_cpufreq_probe(struct scmi_device *sdev) #ifdef CONFIG_COMMON_CLK /* dummy clock provider as needed by OPP if clocks property is used */ - if (of_property_present(dev->of_node, "#clock-cells")) - devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL); + if (of_property_present(dev->of_node, "#clock-cells")) { + ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL); + if (ret) + return dev_err_probe(dev, ret, "%s: registering clock provider failed\n", __func__); + } #endif ret = cpufreq_register_driver(&scmi_cpufreq_driver); diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c index 88ef5e57ccd05c..386aed3637b4ef 100644 --- a/drivers/cpufreq/tegra194-cpufreq.c +++ b/drivers/cpufreq/tegra194-cpufreq.c @@ -450,6 +450,8 @@ static int tegra_cpufreq_init_cpufreq_table(struct cpufreq_policy *policy, if (IS_ERR(opp)) continue; + dev_pm_opp_put(opp); + ret = dev_pm_opp_enable(cpu_dev, pos->frequency * KHZ); if (ret < 0) return ret; diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c index 3c37d78996607f..cb5d1c8fefeb44 100644 --- a/drivers/cpufreq/ti-cpufreq.c +++ b/drivers/cpufreq/ti-cpufreq.c @@ -61,6 +61,9 @@ struct ti_cpufreq_soc_data { unsigned long efuse_shift; unsigned long rev_offset; bool multi_regulator; +/* Backward compatibility hack: Might have missing syscon */ +#define TI_QUIRK_SYSCON_MAY_BE_MISSING 0x1 + u8 quirks; }; struct ti_cpufreq_data { @@ -182,6 +185,7 @@ static struct ti_cpufreq_soc_data omap34xx_soc_data = { .efuse_mask = BIT(3), .rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE, .multi_regulator = false, + .quirks = TI_QUIRK_SYSCON_MAY_BE_MISSING, }; /* @@ -209,6 +213,7 @@ static struct ti_cpufreq_soc_data omap36xx_soc_data = { .efuse_mask = BIT(9), .rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE, .multi_regulator = true, + .quirks = TI_QUIRK_SYSCON_MAY_BE_MISSING, }; /* @@ -223,6 +228,7 @@ static struct ti_cpufreq_soc_data am3517_soc_data = { .efuse_mask = 0, .rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE, .multi_regulator = false, + .quirks = TI_QUIRK_SYSCON_MAY_BE_MISSING, }; static struct ti_cpufreq_soc_data am625_soc_data = { @@ -250,7 +256,7 @@ static int ti_cpufreq_get_efuse(struct ti_cpufreq_data *opp_data, ret = regmap_read(opp_data->syscon, opp_data->soc_data->efuse_offset, &efuse); - if (ret == -EIO) { + if (opp_data->soc_data->quirks & TI_QUIRK_SYSCON_MAY_BE_MISSING && ret == -EIO) { /* not a syscon register! */ void __iomem *regs = ioremap(OMAP3_SYSCON_BASE + opp_data->soc_data->efuse_offset, 4); @@ -291,7 +297,7 @@ static int ti_cpufreq_get_rev(struct ti_cpufreq_data *opp_data, ret = regmap_read(opp_data->syscon, opp_data->soc_data->rev_offset, &revision); - if (ret == -EIO) { + if (opp_data->soc_data->quirks & TI_QUIRK_SYSCON_MAY_BE_MISSING && ret == -EIO) { /* not a syscon register! */ void __iomem *regs = ioremap(OMAP3_SYSCON_BASE + opp_data->soc_data->rev_offset, 4); @@ -418,7 +424,7 @@ static int ti_cpufreq_probe(struct platform_device *pdev) ret = dev_pm_opp_set_config(opp_data->cpu_dev, &config); if (ret < 0) { - dev_err(opp_data->cpu_dev, "Failed to set OPP config\n"); + dev_err_probe(opp_data->cpu_dev, ret, "Failed to set OPP config\n"); goto fail_put_node; } diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c index e66df22f96955f..d8515d5c0853dc 100644 --- a/drivers/cpuidle/cpuidle-haltpoll.c +++ b/drivers/cpuidle/cpuidle-haltpoll.c @@ -25,13 +25,12 @@ MODULE_PARM_DESC(force, "Load unconditionally"); static struct cpuidle_device __percpu *haltpoll_cpuidle_devices; static enum cpuhp_state haltpoll_hp_state; -static int default_enter_idle(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) +static __cpuidle int default_enter_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) { - if (current_clr_polling_and_test()) { - local_irq_enable(); + if (current_clr_polling_and_test()) return index; - } + arch_cpu_idle(); return index; } diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c index e8094fc92491eb..c0fe92409175a4 100644 --- a/drivers/cpuidle/cpuidle-riscv-sbi.c +++ b/drivers/cpuidle/cpuidle-riscv-sbi.c @@ -8,6 +8,7 @@ #define pr_fmt(fmt) "cpuidle-riscv-sbi: " fmt +#include #include #include #include @@ -267,19 +268,16 @@ static int sbi_cpuidle_dt_init_states(struct device *dev, { struct sbi_cpuidle_data *data = per_cpu_ptr(&sbi_cpuidle_data, cpu); struct device_node *state_node; - struct device_node *cpu_node; u32 *states; int i, ret; - cpu_node = of_cpu_device_node_get(cpu); + struct device_node *cpu_node __free(device_node) = of_cpu_device_node_get(cpu); if (!cpu_node) return -ENODEV; states = devm_kcalloc(dev, state_count, sizeof(*states), GFP_KERNEL); - if (!states) { - ret = -ENOMEM; - goto fail; - } + if (!states) + return -ENOMEM; /* Parse SBI specific details from state DT nodes */ for (i = 1; i < state_count; i++) { @@ -295,10 +293,8 @@ static int sbi_cpuidle_dt_init_states(struct device *dev, pr_debug("sbi-state %#x index %d\n", states[i], i); } - if (i != state_count) { - ret = -ENODEV; - goto fail; - } + if (i != state_count) + return -ENODEV; /* Initialize optional data, used for the hierarchical topology. */ ret = sbi_dt_cpu_init_topology(drv, data, state_count, cpu); @@ -308,10 +304,7 @@ static int sbi_cpuidle_dt_init_states(struct device *dev, /* Store states in the per-cpu struct. */ data->states = states; -fail: - of_node_put(cpu_node); - - return ret; + return 0; } static void sbi_cpuidle_deinit_cpu(int cpu) diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index d9cda7f6ccb98d..cf5873cc45dc8c 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "cpuidle.h" @@ -187,7 +188,7 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv) s->target_residency = div_u64(s->target_residency_ns, NSEC_PER_USEC); if (s->exit_latency > 0) - s->exit_latency_ns = s->exit_latency * NSEC_PER_USEC; + s->exit_latency_ns = mul_u32_u32(s->exit_latency, NSEC_PER_USEC); else if (s->exit_latency_ns < 0) s->exit_latency_ns = 0; else diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c index 8d4c42863a621e..d2cf9619018b1a 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c @@ -299,22 +299,6 @@ static int sun8i_ce_cipher_prepare(struct crypto_engine *engine, void *async_req return err; } -static void sun8i_ce_cipher_run(struct crypto_engine *engine, void *areq) -{ - struct skcipher_request *breq = container_of(areq, struct skcipher_request, base); - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(breq); - struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm); - struct sun8i_ce_dev *ce = op->ce; - struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(breq); - int flow, err; - - flow = rctx->flow; - err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(breq->base.tfm)); - local_bh_disable(); - crypto_finalize_skcipher_request(engine, breq, err); - local_bh_enable(); -} - static void sun8i_ce_cipher_unprepare(struct crypto_engine *engine, void *async_req) { @@ -360,6 +344,23 @@ static void sun8i_ce_cipher_unprepare(struct crypto_engine *engine, dma_unmap_single(ce->dev, rctx->addr_key, op->keylen, DMA_TO_DEVICE); } +static void sun8i_ce_cipher_run(struct crypto_engine *engine, void *areq) +{ + struct skcipher_request *breq = container_of(areq, struct skcipher_request, base); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(breq); + struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm); + struct sun8i_ce_dev *ce = op->ce; + struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(breq); + int flow, err; + + flow = rctx->flow; + err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(breq->base.tfm)); + sun8i_ce_cipher_unprepare(engine, areq); + local_bh_disable(); + crypto_finalize_skcipher_request(engine, breq, err); + local_bh_enable(); +} + int sun8i_ce_cipher_do_one(struct crypto_engine *engine, void *areq) { int err = sun8i_ce_cipher_prepare(engine, areq); @@ -368,7 +369,6 @@ int sun8i_ce_cipher_do_one(struct crypto_engine *engine, void *areq) return err; sun8i_ce_cipher_run(engine, areq); - sun8i_ce_cipher_unprepare(engine, areq); return 0; } diff --git a/drivers/crypto/bcm/spu2.c b/drivers/crypto/bcm/spu2.c index 07989bb8c220a4..3fdc64b5a65e7e 100644 --- a/drivers/crypto/bcm/spu2.c +++ b/drivers/crypto/bcm/spu2.c @@ -495,7 +495,7 @@ static void spu2_dump_omd(u8 *omd, u16 hash_key_len, u16 ciph_key_len, if (hash_iv_len) { packet_log(" Hash IV Length %u bytes\n", hash_iv_len); packet_dump(" hash IV: ", ptr, hash_iv_len); - ptr += ciph_key_len; + ptr += hash_iv_len; } if (ciph_iv_len) { diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c index eba2d750c3b074..066f08a3a040d8 100644 --- a/drivers/crypto/caam/caamalg.c +++ b/drivers/crypto/caam/caamalg.c @@ -575,7 +575,8 @@ static int chachapoly_setkey(struct crypto_aead *aead, const u8 *key, if (keylen != CHACHA_KEY_SIZE + saltlen) return -EINVAL; - ctx->cdata.key_virt = key; + memcpy(ctx->key, key, keylen); + ctx->cdata.key_virt = ctx->key; ctx->cdata.keylen = keylen - saltlen; return chachapoly_set_sh_desc(aead); diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c index 9156bbe038b7b0..a148ff1f0872c4 100644 --- a/drivers/crypto/caam/caamalg_qi2.c +++ b/drivers/crypto/caam/caamalg_qi2.c @@ -641,7 +641,8 @@ static int chachapoly_setkey(struct crypto_aead *aead, const u8 *key, if (keylen != CHACHA_KEY_SIZE + saltlen) return -EINVAL; - ctx->cdata.key_virt = key; + memcpy(ctx->key, key, keylen); + ctx->cdata.key_virt = ctx->key; ctx->cdata.keylen = keylen - saltlen; return chachapoly_set_sh_desc(aead); diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index 290c8500c247f9..65785dc5b73b2b 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -708,6 +708,7 @@ static struct ahash_edesc *ahash_edesc_alloc(struct ahash_request *req, GFP_KERNEL : GFP_ATOMIC; struct ahash_edesc *edesc; + sg_num = pad_sg_nents(sg_num); edesc = kzalloc(struct_size(edesc, sec4_sg, sg_num), flags); if (!edesc) return NULL; diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c index aa4e1a5006919d..cb8e99936abb72 100644 --- a/drivers/crypto/ccp/ccp-ops.c +++ b/drivers/crypto/ccp/ccp-ops.c @@ -179,8 +179,11 @@ static int ccp_init_dm_workarea(struct ccp_dm_workarea *wa, wa->dma.address = dma_map_single(wa->dev, wa->address, len, dir); - if (dma_mapping_error(wa->dev, wa->dma.address)) + if (dma_mapping_error(wa->dev, wa->dma.address)) { + kfree(wa->address); + wa->address = NULL; return -ENOMEM; + } wa->dma.length = len; } diff --git a/drivers/crypto/ccp/dbc.c b/drivers/crypto/ccp/dbc.c index 839ea14b9a853f..6f33149ef80df0 100644 --- a/drivers/crypto/ccp/dbc.c +++ b/drivers/crypto/ccp/dbc.c @@ -205,7 +205,7 @@ int dbc_dev_init(struct psp_device *psp) return -ENOMEM; BUILD_BUG_ON(sizeof(union dbc_buffer) > PAGE_SIZE); - dbc_dev->mbox = (void *)devm_get_free_pages(dev, GFP_KERNEL, 0); + dbc_dev->mbox = (void *)devm_get_free_pages(dev, GFP_KERNEL | __GFP_ZERO, 0); if (!dbc_dev->mbox) { ret = -ENOMEM; goto cleanup_dev; diff --git a/drivers/crypto/ccp/platform-access.c b/drivers/crypto/ccp/platform-access.c index 94367bc49e35b8..1b8ed33897332e 100644 --- a/drivers/crypto/ccp/platform-access.c +++ b/drivers/crypto/ccp/platform-access.c @@ -118,9 +118,16 @@ int psp_send_platform_access_msg(enum psp_platform_access_msg msg, goto unlock; } - /* Store the status in request header for caller to investigate */ + /* + * Read status from PSP. If status is non-zero, it indicates an error + * occurred during "processing" of the command. + * If status is zero, it indicates the command was "processed" + * successfully, but the result of the command is in the payload. + * Return both cases to the caller as -EIO to investigate. + */ cmd_reg = ioread32(cmd); - req->header.status = FIELD_GET(PSP_CMDRESP_STS, cmd_reg); + if (FIELD_GET(PSP_CMDRESP_STS, cmd_reg)) + req->header.status = FIELD_GET(PSP_CMDRESP_STS, cmd_reg); if (req->header.status) { ret = -EIO; goto unlock; diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index f97166fba9d930..07e6f782b62252 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -520,10 +520,16 @@ EXPORT_SYMBOL_GPL(sev_platform_init); static int __sev_platform_shutdown_locked(int *error) { - struct sev_device *sev = psp_master->sev_data; + struct psp_device *psp = psp_master; + struct sev_device *sev; int ret; - if (!sev || sev->state == SEV_STATE_UNINIT) + if (!psp || !psp->sev_data) + return 0; + + sev = psp->sev_data; + + if (sev->state == SEV_STATE_UNINIT) return 0; ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error); @@ -1361,6 +1367,8 @@ void sev_pci_init(void) return; err: + sev_dev_destroy(psp_master); + psp_master->sev_data = NULL; } diff --git a/drivers/crypto/ccp/sp-platform.c b/drivers/crypto/ccp/sp-platform.c index 7d79a8744f9a6a..c43ad7e1acf7ea 100644 --- a/drivers/crypto/ccp/sp-platform.c +++ b/drivers/crypto/ccp/sp-platform.c @@ -39,44 +39,38 @@ static const struct sp_dev_vdata dev_vdata[] = { }, }; -#ifdef CONFIG_ACPI static const struct acpi_device_id sp_acpi_match[] = { { "AMDI0C00", (kernel_ulong_t)&dev_vdata[0] }, { }, }; MODULE_DEVICE_TABLE(acpi, sp_acpi_match); -#endif -#ifdef CONFIG_OF static const struct of_device_id sp_of_match[] = { { .compatible = "amd,ccp-seattle-v1a", .data = (const void *)&dev_vdata[0] }, { }, }; MODULE_DEVICE_TABLE(of, sp_of_match); -#endif static struct sp_dev_vdata *sp_get_of_version(struct platform_device *pdev) { -#ifdef CONFIG_OF const struct of_device_id *match; match = of_match_node(sp_of_match, pdev->dev.of_node); if (match && match->data) return (struct sp_dev_vdata *)match->data; -#endif + return NULL; } static struct sp_dev_vdata *sp_get_acpi_version(struct platform_device *pdev) { -#ifdef CONFIG_ACPI const struct acpi_device_id *match; match = acpi_match_device(sp_acpi_match, &pdev->dev); if (match && match->driver_data) return (struct sp_dev_vdata *)match->driver_data; -#endif + return NULL; } @@ -214,12 +208,8 @@ static int sp_platform_resume(struct platform_device *pdev) static struct platform_driver sp_platform_driver = { .driver = { .name = "ccp", -#ifdef CONFIG_ACPI .acpi_match_table = sp_acpi_match, -#endif -#ifdef CONFIG_OF .of_match_table = sp_of_match, -#endif }, .probe = sp_platform_probe, .remove = sp_platform_remove, diff --git a/drivers/crypto/hisilicon/debugfs.c b/drivers/crypto/hisilicon/debugfs.c index 2cc1591949db7e..bd205f1f2279e4 100644 --- a/drivers/crypto/hisilicon/debugfs.c +++ b/drivers/crypto/hisilicon/debugfs.c @@ -794,8 +794,14 @@ static void dfx_regs_uninit(struct hisi_qm *qm, { int i; + if (!dregs) + return; + /* Setting the pointer is NULL to prevent double free */ for (i = 0; i < reg_len; i++) { + if (!dregs[i].regs) + continue; + kfree(dregs[i].regs); dregs[i].regs = NULL; } @@ -845,14 +851,21 @@ static struct dfx_diff_registers *dfx_regs_init(struct hisi_qm *qm, static int qm_diff_regs_init(struct hisi_qm *qm, struct dfx_diff_registers *dregs, u32 reg_len) { + int ret; + qm->debug.qm_diff_regs = dfx_regs_init(qm, qm_diff_regs, ARRAY_SIZE(qm_diff_regs)); - if (IS_ERR(qm->debug.qm_diff_regs)) - return PTR_ERR(qm->debug.qm_diff_regs); + if (IS_ERR(qm->debug.qm_diff_regs)) { + ret = PTR_ERR(qm->debug.qm_diff_regs); + qm->debug.qm_diff_regs = NULL; + return ret; + } qm->debug.acc_diff_regs = dfx_regs_init(qm, dregs, reg_len); if (IS_ERR(qm->debug.acc_diff_regs)) { dfx_regs_uninit(qm, qm->debug.qm_diff_regs, ARRAY_SIZE(qm_diff_regs)); - return PTR_ERR(qm->debug.acc_diff_regs); + ret = PTR_ERR(qm->debug.acc_diff_regs); + qm->debug.acc_diff_regs = NULL; + return ret; } return 0; @@ -893,7 +906,9 @@ static int qm_last_regs_init(struct hisi_qm *qm) static void qm_diff_regs_uninit(struct hisi_qm *qm, u32 reg_len) { dfx_regs_uninit(qm, qm->debug.acc_diff_regs, reg_len); + qm->debug.acc_diff_regs = NULL; dfx_regs_uninit(qm, qm->debug.qm_diff_regs, ARRAY_SIZE(qm_diff_regs)); + qm->debug.qm_diff_regs = NULL; } /** diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c index 39297ce70f441e..3463f5ee83c0df 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_main.c +++ b/drivers/crypto/hisilicon/hpre/hpre_main.c @@ -13,9 +13,7 @@ #include #include "hpre.h" -#define HPRE_QM_ABNML_INT_MASK 0x100004 #define HPRE_CTRL_CNT_CLR_CE_BIT BIT(0) -#define HPRE_COMM_CNT_CLR_CE 0x0 #define HPRE_CTRL_CNT_CLR_CE 0x301000 #define HPRE_FSM_MAX_CNT 0x301008 #define HPRE_VFG_AXQOS 0x30100c @@ -42,7 +40,6 @@ #define HPRE_HAC_INT_SET 0x301500 #define HPRE_RNG_TIMEOUT_NUM 0x301A34 #define HPRE_CORE_INT_ENABLE 0 -#define HPRE_CORE_INT_DISABLE GENMASK(21, 0) #define HPRE_RDCHN_INI_ST 0x301a00 #define HPRE_CLSTR_BASE 0x302000 #define HPRE_CORE_EN_OFFSET 0x04 @@ -66,7 +63,6 @@ #define HPRE_CLSTR_ADDR_INTRVL 0x1000 #define HPRE_CLUSTER_INQURY 0x100 #define HPRE_CLSTR_ADDR_INQRY_RSLT 0x104 -#define HPRE_TIMEOUT_ABNML_BIT 6 #define HPRE_PASID_EN_BIT 9 #define HPRE_REG_RD_INTVRL_US 10 #define HPRE_REG_RD_TMOUT_US 1000 @@ -117,8 +113,6 @@ #define HPRE_DFX_COMMON2_LEN 0xE #define HPRE_DFX_CORE_LEN 0x43 -#define HPRE_DEV_ALG_MAX_LEN 256 - static const char hpre_name[] = "hisi_hpre"; static struct dentry *hpre_debugfs_root; static const struct pci_device_id hpre_dev_ids[] = { @@ -134,12 +128,7 @@ struct hpre_hw_error { const char *msg; }; -struct hpre_dev_alg { - u32 alg_msk; - const char *alg; -}; - -static const struct hpre_dev_alg hpre_dev_algs[] = { +static const struct qm_dev_alg hpre_dev_algs[] = { { .alg_msk = BIT(0), .alg = "rsa\n" @@ -209,9 +198,9 @@ static const struct hisi_qm_cap_info hpre_basic_info[] = { {HPRE_QM_RESET_MASK_CAP, 0x3128, 0, GENMASK(31, 0), 0x0, 0xC37, 0x6C37}, {HPRE_QM_OOO_SHUTDOWN_MASK_CAP, 0x3128, 0, GENMASK(31, 0), 0x0, 0x4, 0x6C37}, {HPRE_QM_CE_MASK_CAP, 0x312C, 0, GENMASK(31, 0), 0x0, 0x8, 0x8}, - {HPRE_NFE_MASK_CAP, 0x3130, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0x1FFFFFE}, - {HPRE_RESET_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0xBFFFFE}, - {HPRE_OOO_SHUTDOWN_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x22, 0xBFFFFE}, + {HPRE_NFE_MASK_CAP, 0x3130, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0x1FFFC3E}, + {HPRE_RESET_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0xBFFC3E}, + {HPRE_OOO_SHUTDOWN_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x22, 0xBFFC3E}, {HPRE_CE_MASK_CAP, 0x3138, 0, GENMASK(31, 0), 0x0, 0x1, 0x1}, {HPRE_CLUSTER_NUM_CAP, 0x313c, 20, GENMASK(3, 0), 0x0, 0x4, 0x1}, {HPRE_CORE_TYPE_NUM_CAP, 0x313c, 16, GENMASK(3, 0), 0x0, 0x2, 0x2}, @@ -232,6 +221,20 @@ static const struct hisi_qm_cap_info hpre_basic_info[] = { {HPRE_CORE10_ALG_BITMAP_CAP, 0x3170, 0, GENMASK(31, 0), 0x0, 0x10, 0x10} }; +enum hpre_pre_store_cap_idx { + HPRE_CLUSTER_NUM_CAP_IDX = 0x0, + HPRE_CORE_ENABLE_BITMAP_CAP_IDX, + HPRE_DRV_ALG_BITMAP_CAP_IDX, + HPRE_DEV_ALG_BITMAP_CAP_IDX, +}; + +static const u32 hpre_pre_store_caps[] = { + HPRE_CLUSTER_NUM_CAP, + HPRE_CORE_ENABLE_BITMAP_CAP, + HPRE_DRV_ALG_BITMAP_CAP, + HPRE_DEV_ALG_BITMAP_CAP, +}; + static const struct hpre_hw_error hpre_hw_errors[] = { { .int_msk = BIT(0), @@ -350,46 +353,19 @@ static struct dfx_diff_registers hpre_diff_regs[] = { }, }; +static const struct hisi_qm_err_ini hpre_err_ini; + bool hpre_check_alg_support(struct hisi_qm *qm, u32 alg) { u32 cap_val; - cap_val = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_DRV_ALG_BITMAP_CAP, qm->cap_ver); + cap_val = qm->cap_tables.dev_cap_table[HPRE_DRV_ALG_BITMAP_CAP_IDX].cap_val; if (alg & cap_val) return true; return false; } -static int hpre_set_qm_algs(struct hisi_qm *qm) -{ - struct device *dev = &qm->pdev->dev; - char *algs, *ptr; - u32 alg_msk; - int i; - - if (!qm->use_sva) - return 0; - - algs = devm_kzalloc(dev, HPRE_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL); - if (!algs) - return -ENOMEM; - - alg_msk = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_DEV_ALG_BITMAP_CAP, qm->cap_ver); - - for (i = 0; i < ARRAY_SIZE(hpre_dev_algs); i++) - if (alg_msk & hpre_dev_algs[i].alg_msk) - strcat(algs, hpre_dev_algs[i].alg); - - ptr = strrchr(algs, '\n'); - if (ptr) - *ptr = '\0'; - - qm->uacce->algs = algs; - - return 0; -} - static int hpre_diff_regs_show(struct seq_file *s, void *unused) { struct hisi_qm *qm = s->private; @@ -433,8 +409,11 @@ static u32 uacce_mode = UACCE_MODE_NOUACCE; module_param_cb(uacce_mode, &hpre_uacce_mode_ops, &uacce_mode, 0444); MODULE_PARM_DESC(uacce_mode, UACCE_MODE_DESC); +static bool pf_q_num_flag; static int pf_q_num_set(const char *val, const struct kernel_param *kp) { + pf_q_num_flag = true; + return q_num_set(val, kp, PCI_DEVICE_ID_HUAWEI_HPRE_PF); } @@ -456,16 +435,6 @@ static u32 vfs_num; module_param_cb(vfs_num, &vfs_num_ops, &vfs_num, 0444); MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63), 0(default)"); -static inline int hpre_cluster_num(struct hisi_qm *qm) -{ - return hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_CLUSTER_NUM_CAP, qm->cap_ver); -} - -static inline int hpre_cluster_core_mask(struct hisi_qm *qm) -{ - return hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_CORE_ENABLE_BITMAP_CAP, qm->cap_ver); -} - struct hisi_qp *hpre_create_qp(u8 type) { int node = cpu_to_node(smp_processor_id()); @@ -532,13 +501,15 @@ static int hpre_cfg_by_dsm(struct hisi_qm *qm) static int hpre_set_cluster(struct hisi_qm *qm) { - u32 cluster_core_mask = hpre_cluster_core_mask(qm); - u8 clusters_num = hpre_cluster_num(qm); struct device *dev = &qm->pdev->dev; unsigned long offset; + u32 cluster_core_mask; + u8 clusters_num; u32 val = 0; int ret, i; + cluster_core_mask = qm->cap_tables.dev_cap_table[HPRE_CORE_ENABLE_BITMAP_CAP_IDX].cap_val; + clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val; for (i = 0; i < clusters_num; i++) { offset = i * HPRE_CLSTR_ADDR_INTRVL; @@ -680,11 +651,6 @@ static int hpre_set_user_domain_and_cache(struct hisi_qm *qm) writel(HPRE_QM_USR_CFG_MASK, qm->io_base + QM_AWUSER_M_CFG_ENABLE); writel_relaxed(HPRE_QM_AXI_CFG_MASK, qm->io_base + QM_AXI_M_CFG); - /* HPRE need more time, we close this interrupt */ - val = readl_relaxed(qm->io_base + HPRE_QM_ABNML_INT_MASK); - val |= BIT(HPRE_TIMEOUT_ABNML_BIT); - writel_relaxed(val, qm->io_base + HPRE_QM_ABNML_INT_MASK); - if (qm->ver >= QM_HW_V3) writel(HPRE_RSA_ENB | HPRE_ECC_ENB, qm->io_base + HPRE_TYPES_ENB); @@ -693,9 +659,7 @@ static int hpre_set_user_domain_and_cache(struct hisi_qm *qm) writel(HPRE_QM_VFG_AX_MASK, qm->io_base + HPRE_VFG_AXCACHE); writel(0x0, qm->io_base + HPRE_BD_ENDIAN); - writel(0x0, qm->io_base + HPRE_INT_MASK); writel(0x0, qm->io_base + HPRE_POISON_BYPASS); - writel(0x0, qm->io_base + HPRE_COMM_CNT_CLR_CE); writel(0x0, qm->io_base + HPRE_ECC_BYPASS); writel(HPRE_BD_USR_MASK, qm->io_base + HPRE_BD_ARUSR_CFG); @@ -733,11 +697,12 @@ static int hpre_set_user_domain_and_cache(struct hisi_qm *qm) static void hpre_cnt_regs_clear(struct hisi_qm *qm) { - u8 clusters_num = hpre_cluster_num(qm); unsigned long offset; + u8 clusters_num; int i; /* clear clusterX/cluster_ctrl */ + clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val; for (i = 0; i < clusters_num; i++) { offset = HPRE_CLSTR_BASE + i * HPRE_CLSTR_ADDR_INTRVL; writel(0x0, qm->io_base + offset + HPRE_CLUSTER_INQURY); @@ -784,7 +749,7 @@ static void hpre_hw_error_disable(struct hisi_qm *qm) static void hpre_hw_error_enable(struct hisi_qm *qm) { - u32 ce, nfe; + u32 ce, nfe, err_en; ce = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_CE_MASK_CAP, qm->cap_ver); nfe = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_NFE_MASK_CAP, qm->cap_ver); @@ -801,7 +766,8 @@ static void hpre_hw_error_enable(struct hisi_qm *qm) hpre_master_ooo_ctrl(qm, true); /* enable hpre hw error interrupts */ - writel(HPRE_CORE_INT_ENABLE, qm->io_base + HPRE_INT_MASK); + err_en = ce | nfe | HPRE_HAC_RAS_FE_ENABLE; + writel(~err_en, qm->io_base + HPRE_INT_MASK); } static inline struct hisi_qm *hpre_file_to_qm(struct hpre_debugfs_file *file) @@ -1024,16 +990,17 @@ static int hpre_pf_comm_regs_debugfs_init(struct hisi_qm *qm) static int hpre_cluster_debugfs_init(struct hisi_qm *qm) { - u8 clusters_num = hpre_cluster_num(qm); struct device *dev = &qm->pdev->dev; char buf[HPRE_DBGFS_VAL_MAX_LEN]; struct debugfs_regset32 *regset; struct dentry *tmp_d; + u8 clusters_num; int i, ret; + clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val; for (i = 0; i < clusters_num; i++) { ret = snprintf(buf, HPRE_DBGFS_VAL_MAX_LEN, "cluster%d", i); - if (ret < 0) + if (ret >= HPRE_DBGFS_VAL_MAX_LEN) return -EINVAL; tmp_d = debugfs_create_dir(buf, qm->debug.debug_root); @@ -1135,8 +1102,37 @@ static void hpre_debugfs_exit(struct hisi_qm *qm) debugfs_remove_recursive(qm->debug.debug_root); } +static int hpre_pre_store_cap_reg(struct hisi_qm *qm) +{ + struct hisi_qm_cap_record *hpre_cap; + struct device *dev = &qm->pdev->dev; + size_t i, size; + + size = ARRAY_SIZE(hpre_pre_store_caps); + hpre_cap = devm_kzalloc(dev, sizeof(*hpre_cap) * size, GFP_KERNEL); + if (!hpre_cap) + return -ENOMEM; + + for (i = 0; i < size; i++) { + hpre_cap[i].type = hpre_pre_store_caps[i]; + hpre_cap[i].cap_val = hisi_qm_get_hw_info(qm, hpre_basic_info, + hpre_pre_store_caps[i], qm->cap_ver); + } + + if (hpre_cap[HPRE_CLUSTER_NUM_CAP_IDX].cap_val > HPRE_CLUSTERS_NUM_MAX) { + dev_err(dev, "Device cluster num %u is out of range for driver supports %d!\n", + hpre_cap[HPRE_CLUSTER_NUM_CAP_IDX].cap_val, HPRE_CLUSTERS_NUM_MAX); + return -EINVAL; + } + + qm->cap_tables.dev_cap_table = hpre_cap; + + return 0; +} + static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) { + u64 alg_msk; int ret; if (pdev->revision == QM_HW_V1) { @@ -1157,6 +1153,9 @@ static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->qp_num = pf_q_num; qm->debug.curr_qm_qp_num = pf_q_num; qm->qm_list = &hpre_devices; + qm->err_ini = &hpre_err_ini; + if (pf_q_num_flag) + set_bit(QM_MODULE_PARAM, &qm->misc_ctl); } ret = hisi_qm_init(qm); @@ -1165,7 +1164,16 @@ static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) return ret; } - ret = hpre_set_qm_algs(qm); + /* Fetch and save the value of capability registers */ + ret = hpre_pre_store_cap_reg(qm); + if (ret) { + pci_err(pdev, "Failed to pre-store capability registers!\n"); + hisi_qm_uninit(qm); + return ret; + } + + alg_msk = qm->cap_tables.dev_cap_table[HPRE_DEV_ALG_BITMAP_CAP_IDX].cap_val; + ret = hisi_qm_set_algs(qm, alg_msk, hpre_dev_algs, ARRAY_SIZE(hpre_dev_algs)); if (ret) { pci_err(pdev, "Failed to set hpre algs!\n"); hisi_qm_uninit(qm); @@ -1178,11 +1186,12 @@ static int hpre_show_last_regs_init(struct hisi_qm *qm) { int cluster_dfx_regs_num = ARRAY_SIZE(hpre_cluster_dfx_regs); int com_dfx_regs_num = ARRAY_SIZE(hpre_com_dfx_regs); - u8 clusters_num = hpre_cluster_num(qm); struct qm_debug *debug = &qm->debug; void __iomem *io_base; + u8 clusters_num; int i, j, idx; + clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val; debug->last_words = kcalloc(cluster_dfx_regs_num * clusters_num + com_dfx_regs_num, sizeof(unsigned int), GFP_KERNEL); if (!debug->last_words) @@ -1219,10 +1228,10 @@ static void hpre_show_last_dfx_regs(struct hisi_qm *qm) { int cluster_dfx_regs_num = ARRAY_SIZE(hpre_cluster_dfx_regs); int com_dfx_regs_num = ARRAY_SIZE(hpre_com_dfx_regs); - u8 clusters_num = hpre_cluster_num(qm); struct qm_debug *debug = &qm->debug; struct pci_dev *pdev = qm->pdev; void __iomem *io_base; + u8 clusters_num; int i, j, idx; u32 val; @@ -1237,6 +1246,7 @@ static void hpre_show_last_dfx_regs(struct hisi_qm *qm) hpre_com_dfx_regs[i].name, debug->last_words[i], val); } + clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val; for (i = 0; i < clusters_num; i++) { io_base = qm->io_base + hpre_cluster_offsets[i]; for (j = 0; j < cluster_dfx_regs_num; j++) { @@ -1333,8 +1343,6 @@ static int hpre_pf_probe_init(struct hpre *hpre) hpre_open_sva_prefetch(qm); - qm->err_ini = &hpre_err_ini; - qm->err_ini->err_info_init(qm); hisi_qm_dev_err_init(qm); ret = hpre_show_last_regs_init(qm); if (ret) @@ -1363,6 +1371,18 @@ static int hpre_probe_init(struct hpre *hpre) return 0; } +static void hpre_probe_uninit(struct hisi_qm *qm) +{ + if (qm->fun_type == QM_HW_VF) + return; + + hpre_cnt_regs_clear(qm); + qm->debug.curr_qm_qp_num = 0; + hpre_show_last_regs_uninit(qm); + hpre_close_sva_prefetch(qm); + hisi_qm_dev_err_uninit(qm); +} + static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct hisi_qm *qm; @@ -1388,7 +1408,7 @@ static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = hisi_qm_start(qm); if (ret) - goto err_with_err_init; + goto err_with_probe_init; ret = hpre_debugfs_init(qm); if (ret) @@ -1425,9 +1445,8 @@ static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id) hpre_debugfs_exit(qm); hisi_qm_stop(qm, QM_NORMAL); -err_with_err_init: - hpre_show_last_regs_uninit(qm); - hisi_qm_dev_err_uninit(qm); +err_with_probe_init: + hpre_probe_uninit(qm); err_with_qm_init: hisi_qm_uninit(qm); @@ -1448,13 +1467,7 @@ static void hpre_remove(struct pci_dev *pdev) hpre_debugfs_exit(qm); hisi_qm_stop(qm, QM_NORMAL); - if (qm->fun_type == QM_HW_PF) { - hpre_cnt_regs_clear(qm); - qm->debug.curr_qm_qp_num = 0; - hpre_show_last_regs_uninit(qm); - hisi_qm_dev_err_uninit(qm); - } - + hpre_probe_uninit(qm); hisi_qm_uninit(qm); } diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index a99fd589445cef..1b00edbbfe26a9 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -206,8 +206,6 @@ #define WAIT_PERIOD 20 #define REMOVE_WAIT_DELAY 10 -#define QM_DRIVER_REMOVING 0 -#define QM_RST_SCHED 1 #define QM_QOS_PARAM_NUM 2 #define QM_QOS_MAX_VAL 1000 #define QM_QOS_RATE 100 @@ -230,6 +228,8 @@ #define QM_QOS_MAX_CIR_U 6 #define QM_AUTOSUSPEND_DELAY 3000 +#define QM_DEV_ALG_MAX_LEN 256 + #define QM_MK_CQC_DW3_V1(hop_num, pg_sz, buf_sz, cqe_sz) \ (((hop_num) << QM_CQ_HOP_NUM_SHIFT) | \ ((pg_sz) << QM_CQ_PAGE_SIZE_SHIFT) | \ @@ -308,6 +308,13 @@ enum qm_basic_type { QM_VF_IRQ_NUM_CAP, }; +enum qm_pre_store_cap_idx { + QM_EQ_IRQ_TYPE_CAP_IDX = 0x0, + QM_AEQ_IRQ_TYPE_CAP_IDX, + QM_ABN_IRQ_TYPE_CAP_IDX, + QM_PF2VF_IRQ_TYPE_CAP_IDX, +}; + static const struct hisi_qm_cap_info qm_cap_info_comm[] = { {QM_SUPPORT_DB_ISOLATION, 0x30, 0, BIT(0), 0x0, 0x0, 0x0}, {QM_SUPPORT_FUNC_QOS, 0x3100, 0, BIT(8), 0x0, 0x0, 0x1}, @@ -337,6 +344,13 @@ static const struct hisi_qm_cap_info qm_basic_info[] = { {QM_VF_IRQ_NUM_CAP, 0x311c, 0, GENMASK(15, 0), 0x1, 0x2, 0x3}, }; +static const u32 qm_pre_store_caps[] = { + QM_EQ_IRQ_TYPE_CAP, + QM_AEQ_IRQ_TYPE_CAP, + QM_ABN_IRQ_TYPE_CAP, + QM_PF2VF_IRQ_TYPE_CAP, +}; + struct qm_mailbox { __le16 w0; __le16 queue_num; @@ -441,6 +455,7 @@ static struct qm_typical_qos_table shaper_cbs_s[] = { }; static void qm_irqs_unregister(struct hisi_qm *qm); +static int qm_reset_device(struct hisi_qm *qm); static bool qm_avail_state(struct hisi_qm *qm, enum qm_state new) { @@ -789,6 +804,40 @@ static void qm_get_xqc_depth(struct hisi_qm *qm, u16 *low_bits, *high_bits = (depth >> QM_XQ_DEPTH_SHIFT) & QM_XQ_DEPTH_MASK; } +int hisi_qm_set_algs(struct hisi_qm *qm, u64 alg_msk, const struct qm_dev_alg *dev_algs, + u32 dev_algs_size) +{ + struct device *dev = &qm->pdev->dev; + char *algs, *ptr; + int i; + + if (!qm->uacce) + return 0; + + if (dev_algs_size >= QM_DEV_ALG_MAX_LEN) { + dev_err(dev, "algs size %u is equal or larger than %d.\n", + dev_algs_size, QM_DEV_ALG_MAX_LEN); + return -EINVAL; + } + + algs = devm_kzalloc(dev, QM_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL); + if (!algs) + return -ENOMEM; + + for (i = 0; i < dev_algs_size; i++) + if (alg_msk & dev_algs[i].alg_msk) + strcat(algs, dev_algs[i].alg); + + ptr = strrchr(algs, '\n'); + if (ptr) { + *ptr = '\0'; + qm->uacce->algs = algs; + } + + return 0; +} +EXPORT_SYMBOL_GPL(hisi_qm_set_algs); + static u32 qm_get_irq_num(struct hisi_qm *qm) { if (qm->fun_type == QM_HW_PF) @@ -849,53 +898,23 @@ static void qm_poll_req_cb(struct hisi_qp *qp) qm_db(qm, qp->qp_id, QM_DOORBELL_CMD_CQ, qp->qp_status.cq_head, 0); atomic_dec(&qp->qp_status.used); + + cond_resched(); } /* set c_flag */ qm_db(qm, qp->qp_id, QM_DOORBELL_CMD_CQ, qp->qp_status.cq_head, 1); } -static int qm_get_complete_eqe_num(struct hisi_qm_poll_data *poll_data) -{ - struct hisi_qm *qm = poll_data->qm; - struct qm_eqe *eqe = qm->eqe + qm->status.eq_head; - u16 eq_depth = qm->eq_depth; - int eqe_num = 0; - u16 cqn; - - while (QM_EQE_PHASE(eqe) == qm->status.eqc_phase) { - cqn = le32_to_cpu(eqe->dw0) & QM_EQE_CQN_MASK; - poll_data->qp_finish_id[eqe_num] = cqn; - eqe_num++; - - if (qm->status.eq_head == eq_depth - 1) { - qm->status.eqc_phase = !qm->status.eqc_phase; - eqe = qm->eqe; - qm->status.eq_head = 0; - } else { - eqe++; - qm->status.eq_head++; - } - - if (eqe_num == (eq_depth >> 1) - 1) - break; - } - - qm_db(qm, 0, QM_DOORBELL_CMD_EQ, qm->status.eq_head, 0); - - return eqe_num; -} - static void qm_work_process(struct work_struct *work) { struct hisi_qm_poll_data *poll_data = container_of(work, struct hisi_qm_poll_data, work); struct hisi_qm *qm = poll_data->qm; + u16 eqe_num = poll_data->eqe_num; struct hisi_qp *qp; - int eqe_num, i; + int i; - /* Get qp id of completed tasks and re-enable the interrupt. */ - eqe_num = qm_get_complete_eqe_num(poll_data); for (i = eqe_num - 1; i >= 0; i--) { qp = &qm->qp_array[poll_data->qp_finish_id[i]]; if (unlikely(atomic_read(&qp->qp_status.flags) == QP_STOP)) @@ -911,39 +930,55 @@ static void qm_work_process(struct work_struct *work) } } -static bool do_qm_eq_irq(struct hisi_qm *qm) +static void qm_get_complete_eqe_num(struct hisi_qm *qm) { struct qm_eqe *eqe = qm->eqe + qm->status.eq_head; - struct hisi_qm_poll_data *poll_data; - u16 cqn; + struct hisi_qm_poll_data *poll_data = NULL; + u16 eq_depth = qm->eq_depth; + u16 cqn, eqe_num = 0; - if (!readl(qm->io_base + QM_VF_EQ_INT_SOURCE)) - return false; + if (QM_EQE_PHASE(eqe) != qm->status.eqc_phase) { + atomic64_inc(&qm->debug.dfx.err_irq_cnt); + qm_db(qm, 0, QM_DOORBELL_CMD_EQ, qm->status.eq_head, 0); + return; + } - if (QM_EQE_PHASE(eqe) == qm->status.eqc_phase) { + cqn = le32_to_cpu(eqe->dw0) & QM_EQE_CQN_MASK; + if (unlikely(cqn >= qm->qp_num)) + return; + poll_data = &qm->poll_data[cqn]; + + while (QM_EQE_PHASE(eqe) == qm->status.eqc_phase) { cqn = le32_to_cpu(eqe->dw0) & QM_EQE_CQN_MASK; - poll_data = &qm->poll_data[cqn]; - queue_work(qm->wq, &poll_data->work); + poll_data->qp_finish_id[eqe_num] = cqn; + eqe_num++; + + if (qm->status.eq_head == eq_depth - 1) { + qm->status.eqc_phase = !qm->status.eqc_phase; + eqe = qm->eqe; + qm->status.eq_head = 0; + } else { + eqe++; + qm->status.eq_head++; + } - return true; + if (eqe_num == (eq_depth >> 1) - 1) + break; } - return false; + poll_data->eqe_num = eqe_num; + queue_work(qm->wq, &poll_data->work); + qm_db(qm, 0, QM_DOORBELL_CMD_EQ, qm->status.eq_head, 0); } static irqreturn_t qm_eq_irq(int irq, void *data) { struct hisi_qm *qm = data; - bool ret; - - ret = do_qm_eq_irq(qm); - if (ret) - return IRQ_HANDLED; - atomic64_inc(&qm->debug.dfx.err_irq_cnt); - qm_db(qm, 0, QM_DOORBELL_CMD_EQ, qm->status.eq_head, 0); + /* Get qp id of completed tasks and re-enable the interrupt */ + qm_get_complete_eqe_num(qm); - return IRQ_NONE; + return IRQ_HANDLED; } static irqreturn_t qm_mb_cmd_irq(int irq, void *data) @@ -1025,6 +1060,8 @@ static irqreturn_t qm_aeq_thread(int irq, void *data) u16 aeq_depth = qm->aeq_depth; u32 type, qp_id; + atomic64_inc(&qm->debug.dfx.aeq_irq_cnt); + while (QM_AEQE_PHASE(aeqe) == qm->status.aeqc_phase) { type = le32_to_cpu(aeqe->dw0) >> QM_AEQE_TYPE_SHIFT; qp_id = le32_to_cpu(aeqe->dw0) & QM_AEQE_CQN_MASK; @@ -1062,17 +1099,6 @@ static irqreturn_t qm_aeq_thread(int irq, void *data) return IRQ_HANDLED; } -static irqreturn_t qm_aeq_irq(int irq, void *data) -{ - struct hisi_qm *qm = data; - - atomic64_inc(&qm->debug.dfx.aeq_irq_cnt); - if (!readl(qm->io_base + QM_VF_AEQ_INT_SOURCE)) - return IRQ_NONE; - - return IRQ_WAKE_THREAD; -} - static void qm_init_qp_status(struct hisi_qp *qp) { struct hisi_qp_status *qp_status = &qp->qp_status; @@ -2824,7 +2850,6 @@ static void hisi_qm_pre_init(struct hisi_qm *qm) mutex_init(&qm->mailbox_lock); init_rwsem(&qm->qps_lock); qm->qp_in_used = 0; - qm->misc_ctl = false; if (test_bit(QM_SUPPORT_RPM, &qm->caps)) { if (!acpi_device_power_manageable(ACPI_COMPANION(&pdev->dev))) dev_info(&pdev->dev, "_PS0 and _PR0 are not defined"); @@ -2928,12 +2953,9 @@ void hisi_qm_uninit(struct hisi_qm *qm) hisi_qm_set_state(qm, QM_NOT_READY); up_write(&qm->qps_lock); + qm_remove_uacce(qm); qm_irqs_unregister(qm); hisi_qm_pci_uninit(qm); - if (qm->use_sva) { - uacce_remove(qm->uacce); - qm->uacce = NULL; - } } EXPORT_SYMBOL_GPL(hisi_qm_uninit); @@ -4084,6 +4106,28 @@ static int qm_set_vf_mse(struct hisi_qm *qm, bool set) return -ETIMEDOUT; } +static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) +{ + u32 nfe_enb = 0; + + /* Kunpeng930 hardware automatically close master ooo when NFE occurs */ + if (qm->ver >= QM_HW_V3) + return; + + if (!qm->err_status.is_dev_ecc_mbit && + qm->err_status.is_qm_ecc_mbit && + qm->err_ini->close_axi_master_ooo) { + qm->err_ini->close_axi_master_ooo(qm); + } else if (qm->err_status.is_dev_ecc_mbit && + !qm->err_status.is_qm_ecc_mbit && + !qm->err_ini->close_axi_master_ooo) { + nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE); + writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE, + qm->io_base + QM_RAS_NFE_ENABLE); + writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET); + } +} + static int qm_vf_reset_prepare(struct hisi_qm *qm, enum qm_stop_reason stop_reason) { @@ -4148,6 +4192,8 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) return ret; } + qm_dev_ecc_mbit_handle(qm); + /* PF obtains the information of VF by querying the register. */ qm_cmd_uninit(qm); @@ -4178,33 +4224,26 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) return 0; } -static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) +static int qm_master_ooo_check(struct hisi_qm *qm) { - u32 nfe_enb = 0; + u32 val; + int ret; - /* Kunpeng930 hardware automatically close master ooo when NFE occurs */ - if (qm->ver >= QM_HW_V3) - return; + /* Check the ooo register of the device before resetting the device. */ + writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN, qm->io_base + ACC_MASTER_GLOBAL_CTRL); + ret = readl_relaxed_poll_timeout(qm->io_base + ACC_MASTER_TRANS_RETURN, + val, (val == ACC_MASTER_TRANS_RETURN_RW), + POLL_PERIOD, POLL_TIMEOUT); + if (ret) + pci_warn(qm->pdev, "Bus lock! Please reset system.\n"); - if (!qm->err_status.is_dev_ecc_mbit && - qm->err_status.is_qm_ecc_mbit && - qm->err_ini->close_axi_master_ooo) { - qm->err_ini->close_axi_master_ooo(qm); - } else if (qm->err_status.is_dev_ecc_mbit && - !qm->err_status.is_qm_ecc_mbit && - !qm->err_ini->close_axi_master_ooo) { - nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE); - writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE, - qm->io_base + QM_RAS_NFE_ENABLE); - writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET); - } + return ret; } -static int qm_soft_reset(struct hisi_qm *qm) +static int qm_soft_reset_prepare(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; int ret; - u32 val; /* Ensure all doorbells and mailboxes received by QM */ ret = qm_check_req_recv(qm); @@ -4225,30 +4264,23 @@ static int qm_soft_reset(struct hisi_qm *qm) return ret; } - qm_dev_ecc_mbit_handle(qm); - - /* OOO register set and check */ - writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN, - qm->io_base + ACC_MASTER_GLOBAL_CTRL); - - /* If bus lock, reset chip */ - ret = readl_relaxed_poll_timeout(qm->io_base + ACC_MASTER_TRANS_RETURN, - val, - (val == ACC_MASTER_TRANS_RETURN_RW), - POLL_PERIOD, POLL_TIMEOUT); - if (ret) { - pci_emerg(pdev, "Bus lock! Please reset system.\n"); + ret = qm_master_ooo_check(qm); + if (ret) return ret; - } if (qm->err_ini->close_sva_prefetch) qm->err_ini->close_sva_prefetch(qm); ret = qm_set_pf_mse(qm, false); - if (ret) { + if (ret) pci_err(pdev, "Fails to disable pf MSE bit.\n"); - return ret; - } + + return ret; +} + +static int qm_reset_device(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; /* The reset related sub-control registers are not in PCI BAR */ if (ACPI_HANDLE(&pdev->dev)) { @@ -4267,12 +4299,23 @@ static int qm_soft_reset(struct hisi_qm *qm) pci_err(pdev, "Reset step %llu failed!\n", value); return -EIO; } - } else { - pci_err(pdev, "No reset method!\n"); - return -EINVAL; + + return 0; } - return 0; + pci_err(pdev, "No reset method!\n"); + return -EINVAL; +} + +static int qm_soft_reset(struct hisi_qm *qm) +{ + int ret; + + ret = qm_soft_reset_prepare(qm); + if (ret) + return ret; + + return qm_reset_device(qm); } static int qm_vf_reset_done(struct hisi_qm *qm) @@ -4929,7 +4972,7 @@ static void qm_unregister_abnormal_irq(struct hisi_qm *qm) if (qm->fun_type == QM_HW_VF) return; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_ABN_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_ABN_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_ABN_IRQ_TYPE_MASK)) return; @@ -4946,7 +4989,7 @@ static int qm_register_abnormal_irq(struct hisi_qm *qm) if (qm->fun_type == QM_HW_VF) return 0; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_ABN_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_ABN_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_ABN_IRQ_TYPE_MASK)) return 0; @@ -4963,7 +5006,7 @@ static void qm_unregister_mb_cmd_irq(struct hisi_qm *qm) struct pci_dev *pdev = qm->pdev; u32 irq_vector, val; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_PF2VF_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_PF2VF_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) return; @@ -4977,7 +5020,7 @@ static int qm_register_mb_cmd_irq(struct hisi_qm *qm) u32 irq_vector, val; int ret; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_PF2VF_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_PF2VF_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) return 0; @@ -4994,7 +5037,7 @@ static void qm_unregister_aeq_irq(struct hisi_qm *qm) struct pci_dev *pdev = qm->pdev; u32 irq_vector, val; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_AEQ_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_AEQ_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) return; @@ -5008,13 +5051,13 @@ static int qm_register_aeq_irq(struct hisi_qm *qm) u32 irq_vector, val; int ret; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_AEQ_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_AEQ_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) return 0; irq_vector = val & QM_IRQ_VECTOR_MASK; - ret = request_threaded_irq(pci_irq_vector(pdev, irq_vector), qm_aeq_irq, - qm_aeq_thread, 0, qm->dev_name, qm); + ret = request_threaded_irq(pci_irq_vector(pdev, irq_vector), NULL, + qm_aeq_thread, IRQF_ONESHOT, qm->dev_name, qm); if (ret) dev_err(&pdev->dev, "failed to request eq irq, ret = %d", ret); @@ -5026,7 +5069,7 @@ static void qm_unregister_eq_irq(struct hisi_qm *qm) struct pci_dev *pdev = qm->pdev; u32 irq_vector, val; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_EQ_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_EQ_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) return; @@ -5040,7 +5083,7 @@ static int qm_register_eq_irq(struct hisi_qm *qm) u32 irq_vector, val; int ret; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_EQ_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_EQ_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) return 0; @@ -5093,6 +5136,7 @@ static int qm_irqs_register(struct hisi_qm *qm) static int qm_get_qp_num(struct hisi_qm *qm) { + struct device *dev = &qm->pdev->dev; bool is_db_isolation; /* VF's qp_num assigned by PF in v2, and VF can get qp_num by vft. */ @@ -5109,17 +5153,47 @@ static int qm_get_qp_num(struct hisi_qm *qm) qm->max_qp_num = hisi_qm_get_hw_info(qm, qm_basic_info, QM_FUNC_MAX_QP_CAP, is_db_isolation); - /* check if qp number is valid */ - if (qm->qp_num > qm->max_qp_num) { - dev_err(&qm->pdev->dev, "qp num(%u) is more than max qp num(%u)!\n", + if (qm->qp_num <= qm->max_qp_num) + return 0; + + if (test_bit(QM_MODULE_PARAM, &qm->misc_ctl)) { + /* Check whether the set qp number is valid */ + dev_err(dev, "qp num(%u) is more than max qp num(%u)!\n", qm->qp_num, qm->max_qp_num); return -EINVAL; } + dev_info(dev, "Default qp num(%u) is too big, reset it to Function's max qp num(%u)!\n", + qm->qp_num, qm->max_qp_num); + qm->qp_num = qm->max_qp_num; + qm->debug.curr_qm_qp_num = qm->qp_num; + + return 0; +} + +static int qm_pre_store_irq_type_caps(struct hisi_qm *qm) +{ + struct hisi_qm_cap_record *qm_cap; + struct pci_dev *pdev = qm->pdev; + size_t i, size; + + size = ARRAY_SIZE(qm_pre_store_caps); + qm_cap = devm_kzalloc(&pdev->dev, sizeof(*qm_cap) * size, GFP_KERNEL); + if (!qm_cap) + return -ENOMEM; + + for (i = 0; i < size; i++) { + qm_cap[i].type = qm_pre_store_caps[i]; + qm_cap[i].cap_val = hisi_qm_get_hw_info(qm, qm_basic_info, + qm_pre_store_caps[i], qm->cap_ver); + } + + qm->cap_tables.qm_cap_table = qm_cap; + return 0; } -static void qm_get_hw_caps(struct hisi_qm *qm) +static int qm_get_hw_caps(struct hisi_qm *qm) { const struct hisi_qm_cap_info *cap_info = qm->fun_type == QM_HW_PF ? qm_cap_info_pf : qm_cap_info_vf; @@ -5150,6 +5224,9 @@ static void qm_get_hw_caps(struct hisi_qm *qm) if (val) set_bit(cap_info[i].type, &qm->caps); } + + /* Fetch and save the value of irq type related capability registers */ + return qm_pre_store_irq_type_caps(qm); } static int qm_get_pci_res(struct hisi_qm *qm) @@ -5171,7 +5248,10 @@ static int qm_get_pci_res(struct hisi_qm *qm) goto err_request_mem_regions; } - qm_get_hw_caps(qm); + ret = qm_get_hw_caps(qm); + if (ret) + goto err_ioremap; + if (test_bit(QM_SUPPORT_DB_ISOLATION, &qm->caps)) { qm->db_interval = QM_QP_DB_INTERVAL; qm->db_phys_base = pci_resource_start(pdev, PCI_BAR_4); @@ -5203,6 +5283,35 @@ static int qm_get_pci_res(struct hisi_qm *qm) return ret; } +static int qm_clear_device(struct hisi_qm *qm) +{ + acpi_handle handle = ACPI_HANDLE(&qm->pdev->dev); + int ret; + + if (qm->fun_type == QM_HW_VF) + return 0; + + /* Device does not support reset, return */ + if (!qm->err_ini->err_info_init) + return 0; + qm->err_ini->err_info_init(qm); + + if (!handle) + return 0; + + /* No reset method, return */ + if (!acpi_has_method(handle, qm->err_info.acpi_rst)) + return 0; + + ret = qm_master_ooo_check(qm); + if (ret) { + writel(0x0, qm->io_base + ACC_MASTER_GLOBAL_CTRL); + return ret; + } + + return qm_reset_device(qm); +} + static int hisi_qm_pci_init(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -5232,8 +5341,14 @@ static int hisi_qm_pci_init(struct hisi_qm *qm) goto err_get_pci_res; } + ret = qm_clear_device(qm); + if (ret) + goto err_free_vectors; + return 0; +err_free_vectors: + pci_free_irq_vectors(pdev); err_get_pci_res: qm_put_pci_res(qm); err_disable_pcidev: @@ -5499,7 +5614,6 @@ static int qm_prepare_for_suspend(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; int ret; - u32 val; ret = qm->ops->set_msi(qm, false); if (ret) { @@ -5507,18 +5621,9 @@ static int qm_prepare_for_suspend(struct hisi_qm *qm) return ret; } - /* shutdown OOO register */ - writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN, - qm->io_base + ACC_MASTER_GLOBAL_CTRL); - - ret = readl_relaxed_poll_timeout(qm->io_base + ACC_MASTER_TRANS_RETURN, - val, - (val == ACC_MASTER_TRANS_RETURN_RW), - POLL_PERIOD, POLL_TIMEOUT); - if (ret) { - pci_emerg(pdev, "Bus lock! Please reset system.\n"); + ret = qm_master_ooo_check(qm); + if (ret) return ret; - } ret = qm_set_pf_mse(qm, false); if (ret) diff --git a/drivers/crypto/hisilicon/qm_common.h b/drivers/crypto/hisilicon/qm_common.h index 1406a422d45517..8e36aa9c681be4 100644 --- a/drivers/crypto/hisilicon/qm_common.h +++ b/drivers/crypto/hisilicon/qm_common.h @@ -4,7 +4,6 @@ #define QM_COMMON_H #define QM_DBG_READ_LEN 256 -#define QM_RESETTING 2 struct qm_cqe { __le32 rsvd0; diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h index 3e57fc04b37703..410c83712e2851 100644 --- a/drivers/crypto/hisilicon/sec2/sec.h +++ b/drivers/crypto/hisilicon/sec2/sec.h @@ -220,6 +220,13 @@ enum sec_cap_type { SEC_CORE4_ALG_BITMAP_HIGH, }; +enum sec_cap_reg_record_idx { + SEC_DRV_ALG_BITMAP_LOW_IDX = 0x0, + SEC_DRV_ALG_BITMAP_HIGH_IDX, + SEC_DEV_ALG_BITMAP_LOW_IDX, + SEC_DEV_ALG_BITMAP_HIGH_IDX, +}; + void sec_destroy_qps(struct hisi_qp **qps, int qp_num); struct hisi_qp **sec_create_qps(void); int sec_register_to_crypto(struct hisi_qm *qm); diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c index 074e50ef512c11..932cc277eb3a5e 100644 --- a/drivers/crypto/hisilicon/sec2/sec_crypto.c +++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c @@ -478,8 +478,10 @@ static void sec_alg_resource_free(struct sec_ctx *ctx, if (ctx->pbuf_supported) sec_free_pbuf_resource(dev, qp_ctx->res); - if (ctx->alg_type == SEC_AEAD) + if (ctx->alg_type == SEC_AEAD) { sec_free_mac_resource(dev, qp_ctx->res); + sec_free_aiv_resource(dev, qp_ctx->res); + } } static int sec_alloc_qp_ctx_resource(struct hisi_qm *qm, struct sec_ctx *ctx, @@ -2543,8 +2545,12 @@ static int sec_register_aead(u64 alg_mask) int sec_register_to_crypto(struct hisi_qm *qm) { - u64 alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH, SEC_DRV_ALG_BITMAP_LOW); - int ret; + u64 alg_mask; + int ret = 0; + + alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH_IDX, + SEC_DRV_ALG_BITMAP_LOW_IDX); + ret = sec_register_skcipher(alg_mask); if (ret) @@ -2559,7 +2565,10 @@ int sec_register_to_crypto(struct hisi_qm *qm) void sec_unregister_from_crypto(struct hisi_qm *qm) { - u64 alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH, SEC_DRV_ALG_BITMAP_LOW); + u64 alg_mask; + + alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH_IDX, + SEC_DRV_ALG_BITMAP_LOW_IDX); sec_unregister_aead(alg_mask, ARRAY_SIZE(sec_aeads)); sec_unregister_skcipher(alg_mask, ARRAY_SIZE(sec_skciphers)); diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index 77f9f131b85035..cf7b6a37e7df7a 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -120,7 +120,6 @@ GENMASK_ULL(42, 25)) #define SEC_AEAD_BITMAP (GENMASK_ULL(7, 6) | GENMASK_ULL(18, 17) | \ GENMASK_ULL(45, 43)) -#define SEC_DEV_ALG_MAX_LEN 256 struct sec_hw_error { u32 int_msk; @@ -132,11 +131,6 @@ struct sec_dfx_item { u32 offset; }; -struct sec_dev_alg { - u64 alg_msk; - const char *algs; -}; - static const char sec_name[] = "hisi_sec2"; static struct dentry *sec_debugfs_root; @@ -173,15 +167,22 @@ static const struct hisi_qm_cap_info sec_basic_info[] = { {SEC_CORE4_ALG_BITMAP_HIGH, 0x3170, 0, GENMASK(31, 0), 0x3FFF, 0x3FFF, 0x3FFF}, }; -static const struct sec_dev_alg sec_dev_algs[] = { { +static const u32 sec_pre_store_caps[] = { + SEC_DRV_ALG_BITMAP_LOW, + SEC_DRV_ALG_BITMAP_HIGH, + SEC_DEV_ALG_BITMAP_LOW, + SEC_DEV_ALG_BITMAP_HIGH, +}; + +static const struct qm_dev_alg sec_dev_algs[] = { { .alg_msk = SEC_CIPHER_BITMAP, - .algs = "cipher\n", + .alg = "cipher\n", }, { .alg_msk = SEC_DIGEST_BITMAP, - .algs = "digest\n", + .alg = "digest\n", }, { .alg_msk = SEC_AEAD_BITMAP, - .algs = "aead\n", + .alg = "aead\n", }, }; @@ -311,8 +312,11 @@ static int sec_diff_regs_show(struct seq_file *s, void *unused) } DEFINE_SHOW_ATTRIBUTE(sec_diff_regs); +static bool pf_q_num_flag; static int sec_pf_q_num_set(const char *val, const struct kernel_param *kp) { + pf_q_num_flag = true; + return q_num_set(val, kp, PCI_DEVICE_ID_HUAWEI_SEC_PF); } @@ -391,8 +395,8 @@ u64 sec_get_alg_bitmap(struct hisi_qm *qm, u32 high, u32 low) { u32 cap_val_h, cap_val_l; - cap_val_h = hisi_qm_get_hw_info(qm, sec_basic_info, high, qm->cap_ver); - cap_val_l = hisi_qm_get_hw_info(qm, sec_basic_info, low, qm->cap_ver); + cap_val_h = qm->cap_tables.dev_cap_table[high].cap_val; + cap_val_l = qm->cap_tables.dev_cap_table[low].cap_val; return ((u64)cap_val_h << SEC_ALG_BITMAP_SHIFT) | (u64)cap_val_l; } @@ -1057,9 +1061,6 @@ static int sec_pf_probe_init(struct sec_dev *sec) struct hisi_qm *qm = &sec->qm; int ret; - qm->err_ini = &sec_err_ini; - qm->err_ini->err_info_init(qm); - ret = sec_set_user_domain_and_cache(qm); if (ret) return ret; @@ -1074,37 +1075,31 @@ static int sec_pf_probe_init(struct sec_dev *sec) return ret; } -static int sec_set_qm_algs(struct hisi_qm *qm) +static int sec_pre_store_cap_reg(struct hisi_qm *qm) { - struct device *dev = &qm->pdev->dev; - char *algs, *ptr; - u64 alg_mask; - int i; - - if (!qm->use_sva) - return 0; + struct hisi_qm_cap_record *sec_cap; + struct pci_dev *pdev = qm->pdev; + size_t i, size; - algs = devm_kzalloc(dev, SEC_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL); - if (!algs) + size = ARRAY_SIZE(sec_pre_store_caps); + sec_cap = devm_kzalloc(&pdev->dev, sizeof(*sec_cap) * size, GFP_KERNEL); + if (!sec_cap) return -ENOMEM; - alg_mask = sec_get_alg_bitmap(qm, SEC_DEV_ALG_BITMAP_HIGH, SEC_DEV_ALG_BITMAP_LOW); - - for (i = 0; i < ARRAY_SIZE(sec_dev_algs); i++) - if (alg_mask & sec_dev_algs[i].alg_msk) - strcat(algs, sec_dev_algs[i].algs); - - ptr = strrchr(algs, '\n'); - if (ptr) - *ptr = '\0'; + for (i = 0; i < size; i++) { + sec_cap[i].type = sec_pre_store_caps[i]; + sec_cap[i].cap_val = hisi_qm_get_hw_info(qm, sec_basic_info, + sec_pre_store_caps[i], qm->cap_ver); + } - qm->uacce->algs = algs; + qm->cap_tables.dev_cap_table = sec_cap; return 0; } static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) { + u64 alg_msk; int ret; qm->pdev = pdev; @@ -1120,6 +1115,9 @@ static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->qp_num = pf_q_num; qm->debug.curr_qm_qp_num = pf_q_num; qm->qm_list = &sec_devices; + qm->err_ini = &sec_err_ini; + if (pf_q_num_flag) + set_bit(QM_MODULE_PARAM, &qm->misc_ctl); } else if (qm->fun_type == QM_HW_VF && qm->ver == QM_HW_V1) { /* * have no way to get qm configure in VM in v1 hardware, @@ -1137,7 +1135,16 @@ static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) return ret; } - ret = sec_set_qm_algs(qm); + /* Fetch and save the value of capability registers */ + ret = sec_pre_store_cap_reg(qm); + if (ret) { + pci_err(qm->pdev, "Failed to pre-store capability registers!\n"); + hisi_qm_uninit(qm); + return ret; + } + + alg_msk = sec_get_alg_bitmap(qm, SEC_DEV_ALG_BITMAP_HIGH_IDX, SEC_DEV_ALG_BITMAP_LOW_IDX); + ret = hisi_qm_set_algs(qm, alg_msk, sec_dev_algs, ARRAY_SIZE(sec_dev_algs)); if (ret) { pci_err(qm->pdev, "Failed to set sec algs!\n"); hisi_qm_uninit(qm); @@ -1173,6 +1180,12 @@ static int sec_probe_init(struct sec_dev *sec) static void sec_probe_uninit(struct hisi_qm *qm) { + if (qm->fun_type == QM_HW_VF) + return; + + sec_debug_regs_clear(qm); + sec_show_last_regs_uninit(qm); + sec_close_sva_prefetch(qm); hisi_qm_dev_err_uninit(qm); } @@ -1265,7 +1278,6 @@ static int sec_probe(struct pci_dev *pdev, const struct pci_device_id *id) sec_debugfs_exit(qm); hisi_qm_stop(qm, QM_NORMAL); err_probe_uninit: - sec_show_last_regs_uninit(qm); sec_probe_uninit(qm); err_qm_uninit: sec_qm_uninit(qm); @@ -1287,11 +1299,6 @@ static void sec_remove(struct pci_dev *pdev) sec_debugfs_exit(qm); (void)hisi_qm_stop(qm, QM_NORMAL); - - if (qm->fun_type == QM_HW_PF) - sec_debug_regs_clear(qm); - sec_show_last_regs_uninit(qm); - sec_probe_uninit(qm); sec_qm_uninit(qm); diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index f3ce34198775d8..9d47b3675da7d4 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -73,7 +73,6 @@ #define HZIP_AXI_SHUTDOWN_ENABLE BIT(14) #define HZIP_WR_PORT BIT(11) -#define HZIP_DEV_ALG_MAX_LEN 256 #define HZIP_ALG_ZLIB_BIT GENMASK(1, 0) #define HZIP_ALG_GZIP_BIT GENMASK(3, 2) #define HZIP_ALG_DEFLATE_BIT GENMASK(5, 4) @@ -106,6 +105,14 @@ #define HZIP_CLOCK_GATED_EN (HZIP_CORE_GATED_EN | \ HZIP_CORE_GATED_OOO_EN) +/* zip comp high performance */ +#define HZIP_HIGH_PERF_OFFSET 0x301208 + +enum { + HZIP_HIGH_COMP_RATE, + HZIP_HIGH_COMP_PERF, +}; + static const char hisi_zip_name[] = "hisi_zip"; static struct dentry *hzip_debugfs_root; @@ -119,23 +126,18 @@ struct zip_dfx_item { u32 offset; }; -struct zip_dev_alg { - u32 alg_msk; - const char *algs; -}; - -static const struct zip_dev_alg zip_dev_algs[] = { { +static const struct qm_dev_alg zip_dev_algs[] = { { .alg_msk = HZIP_ALG_ZLIB_BIT, - .algs = "zlib\n", + .alg = "zlib\n", }, { .alg_msk = HZIP_ALG_GZIP_BIT, - .algs = "gzip\n", + .alg = "gzip\n", }, { .alg_msk = HZIP_ALG_DEFLATE_BIT, - .algs = "deflate\n", + .alg = "deflate\n", }, { .alg_msk = HZIP_ALG_LZ77_BIT, - .algs = "lz77_zstd\n", + .alg = "lz77_zstd\n", }, }; @@ -246,6 +248,26 @@ static struct hisi_qm_cap_info zip_basic_cap_info[] = { {ZIP_CAP_MAX, 0x317c, 0, GENMASK(0, 0), 0x0, 0x0, 0x0} }; +enum zip_pre_store_cap_idx { + ZIP_CORE_NUM_CAP_IDX = 0x0, + ZIP_CLUSTER_COMP_NUM_CAP_IDX, + ZIP_CLUSTER_DECOMP_NUM_CAP_IDX, + ZIP_DECOMP_ENABLE_BITMAP_IDX, + ZIP_COMP_ENABLE_BITMAP_IDX, + ZIP_DRV_ALG_BITMAP_IDX, + ZIP_DEV_ALG_BITMAP_IDX, +}; + +static const u32 zip_pre_store_caps[] = { + ZIP_CORE_NUM_CAP, + ZIP_CLUSTER_COMP_NUM_CAP, + ZIP_CLUSTER_DECOMP_NUM_CAP, + ZIP_DECOMP_ENABLE_BITMAP, + ZIP_COMP_ENABLE_BITMAP, + ZIP_DRV_ALG_BITMAP, + ZIP_DEV_ALG_BITMAP, +}; + enum { HZIP_COMP_CORE0, HZIP_COMP_CORE1, @@ -351,6 +373,37 @@ static int hzip_diff_regs_show(struct seq_file *s, void *unused) return 0; } DEFINE_SHOW_ATTRIBUTE(hzip_diff_regs); + +static int perf_mode_set(const char *val, const struct kernel_param *kp) +{ + int ret; + u32 n; + + if (!val) + return -EINVAL; + + ret = kstrtou32(val, 10, &n); + if (ret != 0 || (n != HZIP_HIGH_COMP_PERF && + n != HZIP_HIGH_COMP_RATE)) + return -EINVAL; + + return param_set_int(val, kp); +} + +static const struct kernel_param_ops zip_com_perf_ops = { + .set = perf_mode_set, + .get = param_get_int, +}; + +/* + * perf_mode = 0 means enable high compression rate mode, + * perf_mode = 1 means enable high compression performance mode. + * These two modes only apply to the compression direction. + */ +static u32 perf_mode = HZIP_HIGH_COMP_RATE; +module_param_cb(perf_mode, &zip_com_perf_ops, &perf_mode, 0444); +MODULE_PARM_DESC(perf_mode, "ZIP high perf mode 0(default), 1(enable)"); + static const struct kernel_param_ops zip_uacce_mode_ops = { .set = uacce_mode_set, .get = param_get_int, @@ -364,8 +417,11 @@ static u32 uacce_mode = UACCE_MODE_NOUACCE; module_param_cb(uacce_mode, &zip_uacce_mode_ops, &uacce_mode, 0444); MODULE_PARM_DESC(uacce_mode, UACCE_MODE_DESC); +static bool pf_q_num_flag; static int pf_q_num_set(const char *val, const struct kernel_param *kp) { + pf_q_num_flag = true; + return q_num_set(val, kp, PCI_DEVICE_ID_HUAWEI_ZIP_PF); } @@ -406,40 +462,33 @@ bool hisi_zip_alg_support(struct hisi_qm *qm, u32 alg) { u32 cap_val; - cap_val = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_DRV_ALG_BITMAP, qm->cap_ver); + cap_val = qm->cap_tables.dev_cap_table[ZIP_DRV_ALG_BITMAP_IDX].cap_val; if ((alg & cap_val) == alg) return true; return false; } -static int hisi_zip_set_qm_algs(struct hisi_qm *qm) +static int hisi_zip_set_high_perf(struct hisi_qm *qm) { - struct device *dev = &qm->pdev->dev; - char *algs, *ptr; - u32 alg_mask; - int i; - - if (!qm->use_sva) - return 0; - - algs = devm_kzalloc(dev, HZIP_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL); - if (!algs) - return -ENOMEM; - - alg_mask = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_DEV_ALG_BITMAP, qm->cap_ver); - - for (i = 0; i < ARRAY_SIZE(zip_dev_algs); i++) - if (alg_mask & zip_dev_algs[i].alg_msk) - strcat(algs, zip_dev_algs[i].algs); - - ptr = strrchr(algs, '\n'); - if (ptr) - *ptr = '\0'; + u32 val; + int ret; - qm->uacce->algs = algs; + val = readl_relaxed(qm->io_base + HZIP_HIGH_PERF_OFFSET); + if (perf_mode == HZIP_HIGH_COMP_PERF) + val |= HZIP_HIGH_COMP_PERF; + else + val &= ~HZIP_HIGH_COMP_PERF; + + /* Set perf mode */ + writel(val, qm->io_base + HZIP_HIGH_PERF_OFFSET); + ret = readl_relaxed_poll_timeout(qm->io_base + HZIP_HIGH_PERF_OFFSET, + val, val == perf_mode, HZIP_DELAY_1_US, + HZIP_POLL_TIMEOUT_US); + if (ret) + pci_err(qm->pdev, "failed to set perf mode\n"); - return 0; + return ret; } static void hisi_zip_open_sva_prefetch(struct hisi_qm *qm) @@ -538,10 +587,8 @@ static int hisi_zip_set_user_domain_and_cache(struct hisi_qm *qm) } /* let's open all compression/decompression cores */ - dcomp_bm = hisi_qm_get_hw_info(qm, zip_basic_cap_info, - ZIP_DECOMP_ENABLE_BITMAP, qm->cap_ver); - comp_bm = hisi_qm_get_hw_info(qm, zip_basic_cap_info, - ZIP_COMP_ENABLE_BITMAP, qm->cap_ver); + dcomp_bm = qm->cap_tables.dev_cap_table[ZIP_DECOMP_ENABLE_BITMAP_IDX].cap_val; + comp_bm = qm->cap_tables.dev_cap_table[ZIP_COMP_ENABLE_BITMAP_IDX].cap_val; writel(HZIP_DECOMP_CHECK_ENABLE | dcomp_bm | comp_bm, base + HZIP_CLOCK_GATE_CTRL); /* enable sqc,cqc writeback */ @@ -768,9 +815,8 @@ static int hisi_zip_core_debug_init(struct hisi_qm *qm) char buf[HZIP_BUF_SIZE]; int i; - zip_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CORE_NUM_CAP, qm->cap_ver); - zip_comp_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CLUSTER_COMP_NUM_CAP, - qm->cap_ver); + zip_core_num = qm->cap_tables.dev_cap_table[ZIP_CORE_NUM_CAP_IDX].cap_val; + zip_comp_core_num = qm->cap_tables.dev_cap_table[ZIP_CLUSTER_COMP_NUM_CAP_IDX].cap_val; for (i = 0; i < zip_core_num; i++) { if (i < zip_comp_core_num) @@ -912,7 +958,7 @@ static int hisi_zip_show_last_regs_init(struct hisi_qm *qm) u32 zip_core_num; int i, j, idx; - zip_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CORE_NUM_CAP, qm->cap_ver); + zip_core_num = qm->cap_tables.dev_cap_table[ZIP_CORE_NUM_CAP_IDX].cap_val; debug->last_words = kcalloc(core_dfx_regs_num * zip_core_num + com_dfx_regs_num, sizeof(unsigned int), GFP_KERNEL); @@ -968,9 +1014,9 @@ static void hisi_zip_show_last_dfx_regs(struct hisi_qm *qm) hzip_com_dfx_regs[i].name, debug->last_words[i], val); } - zip_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CORE_NUM_CAP, qm->cap_ver); - zip_comp_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CLUSTER_COMP_NUM_CAP, - qm->cap_ver); + zip_core_num = qm->cap_tables.dev_cap_table[ZIP_CORE_NUM_CAP_IDX].cap_val; + zip_comp_core_num = qm->cap_tables.dev_cap_table[ZIP_CLUSTER_COMP_NUM_CAP_IDX].cap_val; + for (i = 0; i < zip_core_num; i++) { if (i < zip_comp_core_num) scnprintf(buf, sizeof(buf), "Comp_core-%d", i); @@ -1104,13 +1150,15 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip) hisi_zip->ctrl = ctrl; ctrl->hisi_zip = hisi_zip; - qm->err_ini = &hisi_zip_err_ini; - qm->err_ini->err_info_init(qm); ret = hisi_zip_set_user_domain_and_cache(qm); if (ret) return ret; + ret = hisi_zip_set_high_perf(qm); + if (ret) + return ret; + hisi_zip_open_sva_prefetch(qm); hisi_qm_dev_err_init(qm); hisi_zip_debug_regs_clear(qm); @@ -1122,8 +1170,31 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip) return ret; } +static int zip_pre_store_cap_reg(struct hisi_qm *qm) +{ + struct hisi_qm_cap_record *zip_cap; + struct pci_dev *pdev = qm->pdev; + size_t i, size; + + size = ARRAY_SIZE(zip_pre_store_caps); + zip_cap = devm_kzalloc(&pdev->dev, sizeof(*zip_cap) * size, GFP_KERNEL); + if (!zip_cap) + return -ENOMEM; + + for (i = 0; i < size; i++) { + zip_cap[i].type = zip_pre_store_caps[i]; + zip_cap[i].cap_val = hisi_qm_get_hw_info(qm, zip_basic_cap_info, + zip_pre_store_caps[i], qm->cap_ver); + } + + qm->cap_tables.dev_cap_table = zip_cap; + + return 0; +} + static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) { + u64 alg_msk; int ret; qm->pdev = pdev; @@ -1139,6 +1210,9 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->qp_num = pf_q_num; qm->debug.curr_qm_qp_num = pf_q_num; qm->qm_list = &zip_devices; + qm->err_ini = &hisi_zip_err_ini; + if (pf_q_num_flag) + set_bit(QM_MODULE_PARAM, &qm->misc_ctl); } else if (qm->fun_type == QM_HW_VF && qm->ver == QM_HW_V1) { /* * have no way to get qm configure in VM in v1 hardware, @@ -1157,7 +1231,16 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) return ret; } - ret = hisi_zip_set_qm_algs(qm); + /* Fetch and save the value of capability registers */ + ret = zip_pre_store_cap_reg(qm); + if (ret) { + pci_err(qm->pdev, "Failed to pre-store capability registers!\n"); + hisi_qm_uninit(qm); + return ret; + } + + alg_msk = qm->cap_tables.dev_cap_table[ZIP_DEV_ALG_BITMAP_IDX].cap_val; + ret = hisi_qm_set_algs(qm, alg_msk, zip_dev_algs, ARRAY_SIZE(zip_dev_algs)); if (ret) { pci_err(qm->pdev, "Failed to set zip algs!\n"); hisi_qm_uninit(qm); @@ -1194,6 +1277,16 @@ static int hisi_zip_probe_init(struct hisi_zip *hisi_zip) return 0; } +static void hisi_zip_probe_uninit(struct hisi_qm *qm) +{ + if (qm->fun_type == QM_HW_VF) + return; + + hisi_zip_show_last_regs_uninit(qm); + hisi_zip_close_sva_prefetch(qm); + hisi_qm_dev_err_uninit(qm); +} + static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct hisi_zip *hisi_zip; @@ -1220,7 +1313,7 @@ static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = hisi_qm_start(qm); if (ret) - goto err_dev_err_uninit; + goto err_probe_uninit; ret = hisi_zip_debugfs_init(qm); if (ret) @@ -1257,9 +1350,8 @@ static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id) hisi_zip_debugfs_exit(qm); hisi_qm_stop(qm, QM_NORMAL); -err_dev_err_uninit: - hisi_zip_show_last_regs_uninit(qm); - hisi_qm_dev_err_uninit(qm); +err_probe_uninit: + hisi_zip_probe_uninit(qm); err_qm_uninit: hisi_zip_qm_uninit(qm); @@ -1280,8 +1372,7 @@ static void hisi_zip_remove(struct pci_dev *pdev) hisi_zip_debugfs_exit(qm); hisi_qm_stop(qm, QM_NORMAL); - hisi_zip_show_last_regs_uninit(qm); - hisi_qm_dev_err_uninit(qm); + hisi_zip_probe_uninit(qm); hisi_zip_qm_uninit(qm); } diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c index 272c28b5a0883e..b83818634ae477 100644 --- a/drivers/crypto/inside-secure/safexcel_cipher.c +++ b/drivers/crypto/inside-secure/safexcel_cipher.c @@ -742,9 +742,9 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring, max(totlen_src, totlen_dst)); return -EINVAL; } - if (sreq->nr_src > 0) - dma_map_sg(priv->dev, src, sreq->nr_src, - DMA_BIDIRECTIONAL); + if (sreq->nr_src > 0 && + !dma_map_sg(priv->dev, src, sreq->nr_src, DMA_BIDIRECTIONAL)) + return -EIO; } else { if (unlikely(totlen_src && (sreq->nr_src <= 0))) { dev_err(priv->dev, "Source buffer not large enough (need %d bytes)!", @@ -752,8 +752,9 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring, return -EINVAL; } - if (sreq->nr_src > 0) - dma_map_sg(priv->dev, src, sreq->nr_src, DMA_TO_DEVICE); + if (sreq->nr_src > 0 && + !dma_map_sg(priv->dev, src, sreq->nr_src, DMA_TO_DEVICE)) + return -EIO; if (unlikely(totlen_dst && (sreq->nr_dst <= 0))) { dev_err(priv->dev, "Dest buffer not large enough (need %d bytes)!", @@ -762,9 +763,11 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring, goto unmap; } - if (sreq->nr_dst > 0) - dma_map_sg(priv->dev, dst, sreq->nr_dst, - DMA_FROM_DEVICE); + if (sreq->nr_dst > 0 && + !dma_map_sg(priv->dev, dst, sreq->nr_dst, DMA_FROM_DEVICE)) { + ret = -EIO; + goto unmap; + } } memcpy(ctx->base.ctxr->data, ctx->key, ctx->key_len); diff --git a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c index dd4464b7e00b18..615af08832076a 100644 --- a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c +++ b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include #include @@ -13,6 +14,10 @@ #include "adf_4xxx_hw_data.h" #include "icp_qat_hw.h" +#define ADF_AE_GROUP_0 GENMASK(3, 0) +#define ADF_AE_GROUP_1 GENMASK(7, 4) +#define ADF_AE_GROUP_2 BIT(8) + enum adf_fw_objs { ADF_FW_SYM_OBJ, ADF_FW_ASYM_OBJ, @@ -40,39 +45,45 @@ struct adf_fw_config { }; static const struct adf_fw_config adf_fw_cy_config[] = { - {0xF0, ADF_FW_SYM_OBJ}, - {0xF, ADF_FW_ASYM_OBJ}, - {0x100, ADF_FW_ADMIN_OBJ}, + {ADF_AE_GROUP_1, ADF_FW_SYM_OBJ}, + {ADF_AE_GROUP_0, ADF_FW_ASYM_OBJ}, + {ADF_AE_GROUP_2, ADF_FW_ADMIN_OBJ}, }; static const struct adf_fw_config adf_fw_dc_config[] = { - {0xF0, ADF_FW_DC_OBJ}, - {0xF, ADF_FW_DC_OBJ}, - {0x100, ADF_FW_ADMIN_OBJ}, + {ADF_AE_GROUP_1, ADF_FW_DC_OBJ}, + {ADF_AE_GROUP_0, ADF_FW_DC_OBJ}, + {ADF_AE_GROUP_2, ADF_FW_ADMIN_OBJ}, }; static const struct adf_fw_config adf_fw_sym_config[] = { - {0xF0, ADF_FW_SYM_OBJ}, - {0xF, ADF_FW_SYM_OBJ}, - {0x100, ADF_FW_ADMIN_OBJ}, + {ADF_AE_GROUP_1, ADF_FW_SYM_OBJ}, + {ADF_AE_GROUP_0, ADF_FW_SYM_OBJ}, + {ADF_AE_GROUP_2, ADF_FW_ADMIN_OBJ}, }; static const struct adf_fw_config adf_fw_asym_config[] = { - {0xF0, ADF_FW_ASYM_OBJ}, - {0xF, ADF_FW_ASYM_OBJ}, - {0x100, ADF_FW_ADMIN_OBJ}, + {ADF_AE_GROUP_1, ADF_FW_ASYM_OBJ}, + {ADF_AE_GROUP_0, ADF_FW_ASYM_OBJ}, + {ADF_AE_GROUP_2, ADF_FW_ADMIN_OBJ}, }; static const struct adf_fw_config adf_fw_asym_dc_config[] = { - {0xF0, ADF_FW_ASYM_OBJ}, - {0xF, ADF_FW_DC_OBJ}, - {0x100, ADF_FW_ADMIN_OBJ}, + {ADF_AE_GROUP_1, ADF_FW_ASYM_OBJ}, + {ADF_AE_GROUP_0, ADF_FW_DC_OBJ}, + {ADF_AE_GROUP_2, ADF_FW_ADMIN_OBJ}, }; static const struct adf_fw_config adf_fw_sym_dc_config[] = { - {0xF0, ADF_FW_SYM_OBJ}, - {0xF, ADF_FW_DC_OBJ}, - {0x100, ADF_FW_ADMIN_OBJ}, + {ADF_AE_GROUP_1, ADF_FW_SYM_OBJ}, + {ADF_AE_GROUP_0, ADF_FW_DC_OBJ}, + {ADF_AE_GROUP_2, ADF_FW_ADMIN_OBJ}, +}; + +static const struct adf_fw_config adf_fw_dcc_config[] = { + {ADF_AE_GROUP_1, ADF_FW_DC_OBJ}, + {ADF_AE_GROUP_0, ADF_FW_SYM_OBJ}, + {ADF_AE_GROUP_2, ADF_FW_ADMIN_OBJ}, }; static_assert(ARRAY_SIZE(adf_fw_cy_config) == ARRAY_SIZE(adf_fw_dc_config)); @@ -80,6 +91,7 @@ static_assert(ARRAY_SIZE(adf_fw_cy_config) == ARRAY_SIZE(adf_fw_sym_config)); static_assert(ARRAY_SIZE(adf_fw_cy_config) == ARRAY_SIZE(adf_fw_asym_config)); static_assert(ARRAY_SIZE(adf_fw_cy_config) == ARRAY_SIZE(adf_fw_asym_dc_config)); static_assert(ARRAY_SIZE(adf_fw_cy_config) == ARRAY_SIZE(adf_fw_sym_dc_config)); +static_assert(ARRAY_SIZE(adf_fw_cy_config) == ARRAY_SIZE(adf_fw_dcc_config)); /* Worker thread to service arbiter mappings */ static const u32 default_thrd_to_arb_map[ADF_4XXX_MAX_ACCELENGINES] = { @@ -94,59 +106,18 @@ static const u32 thrd_to_arb_map_dc[ADF_4XXX_MAX_ACCELENGINES] = { 0x0 }; +static const u32 thrd_to_arb_map_dcc[ADF_4XXX_MAX_ACCELENGINES] = { + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x0000FFFF, 0x0000FFFF, 0x0000FFFF, 0x0000FFFF, + 0x0 +}; + static struct adf_hw_device_class adf_4xxx_class = { .name = ADF_4XXX_DEVICE_NAME, .type = DEV_4XXX, .instances = 0, }; -enum dev_services { - SVC_CY = 0, - SVC_CY2, - SVC_DC, - SVC_SYM, - SVC_ASYM, - SVC_DC_ASYM, - SVC_ASYM_DC, - SVC_DC_SYM, - SVC_SYM_DC, -}; - -static const char *const dev_cfg_services[] = { - [SVC_CY] = ADF_CFG_CY, - [SVC_CY2] = ADF_CFG_ASYM_SYM, - [SVC_DC] = ADF_CFG_DC, - [SVC_SYM] = ADF_CFG_SYM, - [SVC_ASYM] = ADF_CFG_ASYM, - [SVC_DC_ASYM] = ADF_CFG_DC_ASYM, - [SVC_ASYM_DC] = ADF_CFG_ASYM_DC, - [SVC_DC_SYM] = ADF_CFG_DC_SYM, - [SVC_SYM_DC] = ADF_CFG_SYM_DC, -}; - -static int get_service_enabled(struct adf_accel_dev *accel_dev) -{ - char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0}; - int ret; - - ret = adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC, - ADF_SERVICES_ENABLED, services); - if (ret) { - dev_err(&GET_DEV(accel_dev), - ADF_SERVICES_ENABLED " param not found\n"); - return ret; - } - - ret = match_string(dev_cfg_services, ARRAY_SIZE(dev_cfg_services), - services); - if (ret < 0) - dev_err(&GET_DEV(accel_dev), - "Invalid value of " ADF_SERVICES_ENABLED " param: %s\n", - services); - - return ret; -} - static u32 get_accel_mask(struct adf_hw_device_data *self) { return ADF_4XXX_ACCELERATORS_MASK; @@ -212,6 +183,7 @@ static u32 get_accel_cap(struct adf_accel_dev *accel_dev) { struct pci_dev *pdev = accel_dev->accel_pci_dev.pci_dev; u32 capabilities_sym, capabilities_asym, capabilities_dc; + u32 capabilities_dcc; u32 fusectl1; /* Read accelerator capabilities mask */ @@ -278,12 +250,20 @@ static u32 get_accel_cap(struct adf_accel_dev *accel_dev) capabilities_dc &= ~ICP_ACCEL_CAPABILITIES_CNV_INTEGRITY64; } - switch (get_service_enabled(accel_dev)) { + switch (adf_get_service_enabled(accel_dev)) { case SVC_CY: case SVC_CY2: return capabilities_sym | capabilities_asym; case SVC_DC: return capabilities_dc; + case SVC_DCC: + /* + * Sym capabilities are available for chaining operations, + * but sym crypto instances cannot be supported + */ + capabilities_dcc = capabilities_dc | capabilities_sym; + capabilities_dcc &= ~ICP_ACCEL_CAPABILITIES_CRYPTO_SYMMETRIC; + return capabilities_dcc; case SVC_SYM: return capabilities_sym; case SVC_ASYM: @@ -306,9 +286,11 @@ static enum dev_sku_info get_sku(struct adf_hw_device_data *self) static const u32 *adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev) { - switch (get_service_enabled(accel_dev)) { + switch (adf_get_service_enabled(accel_dev)) { case SVC_DC: return thrd_to_arb_map_dc; + case SVC_DCC: + return thrd_to_arb_map_dcc; default: return default_thrd_to_arb_map; } @@ -393,38 +375,104 @@ static u32 uof_get_num_objs(void) return ARRAY_SIZE(adf_fw_cy_config); } -static const char *uof_get_name(struct adf_accel_dev *accel_dev, u32 obj_num, - const char * const fw_objs[], int num_objs) +static const struct adf_fw_config *get_fw_config(struct adf_accel_dev *accel_dev) { - int id; - - switch (get_service_enabled(accel_dev)) { + switch (adf_get_service_enabled(accel_dev)) { case SVC_CY: case SVC_CY2: - id = adf_fw_cy_config[obj_num].obj; - break; + return adf_fw_cy_config; case SVC_DC: - id = adf_fw_dc_config[obj_num].obj; - break; + return adf_fw_dc_config; + case SVC_DCC: + return adf_fw_dcc_config; case SVC_SYM: - id = adf_fw_sym_config[obj_num].obj; - break; + return adf_fw_sym_config; case SVC_ASYM: - id = adf_fw_asym_config[obj_num].obj; - break; + return adf_fw_asym_config; case SVC_ASYM_DC: case SVC_DC_ASYM: - id = adf_fw_asym_dc_config[obj_num].obj; - break; + return adf_fw_asym_dc_config; case SVC_SYM_DC: case SVC_DC_SYM: - id = adf_fw_sym_dc_config[obj_num].obj; - break; + return adf_fw_sym_dc_config; default: - id = -EINVAL; - break; + return NULL; + } +} + +enum adf_rp_groups { + RP_GROUP_0 = 0, + RP_GROUP_1, + RP_GROUP_COUNT +}; + +static u16 get_ring_to_svc_map(struct adf_accel_dev *accel_dev) +{ + enum adf_cfg_service_type rps[RP_GROUP_COUNT]; + const struct adf_fw_config *fw_config; + u16 ring_to_svc_map; + int i, j; + + fw_config = get_fw_config(accel_dev); + if (!fw_config) + return 0; + + /* If dcc, all rings handle compression requests */ + if (adf_get_service_enabled(accel_dev) == SVC_DCC) { + for (i = 0; i < RP_GROUP_COUNT; i++) + rps[i] = COMP; + goto set_mask; } + for (i = 0; i < RP_GROUP_COUNT; i++) { + switch (fw_config[i].ae_mask) { + case ADF_AE_GROUP_0: + j = RP_GROUP_0; + break; + case ADF_AE_GROUP_1: + j = RP_GROUP_1; + break; + default: + return 0; + } + + switch (fw_config[i].obj) { + case ADF_FW_SYM_OBJ: + rps[j] = SYM; + break; + case ADF_FW_ASYM_OBJ: + rps[j] = ASYM; + break; + case ADF_FW_DC_OBJ: + rps[j] = COMP; + break; + default: + rps[j] = 0; + break; + } + } + +set_mask: + ring_to_svc_map = rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_0_SHIFT | + rps[RP_GROUP_1] << ADF_CFG_SERV_RING_PAIR_1_SHIFT | + rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_2_SHIFT | + rps[RP_GROUP_1] << ADF_CFG_SERV_RING_PAIR_3_SHIFT; + + return ring_to_svc_map; +} + +static const char *uof_get_name(struct adf_accel_dev *accel_dev, u32 obj_num, + const char * const fw_objs[], int num_objs) +{ + const struct adf_fw_config *fw_config; + int id; + + fw_config = get_fw_config(accel_dev); + if (fw_config) + id = fw_config[obj_num].obj; + else + id = -EINVAL; + if (id < 0 || id > num_objs) return NULL; @@ -447,26 +495,13 @@ static const char *uof_get_name_402xx(struct adf_accel_dev *accel_dev, u32 obj_n static u32 uof_get_ae_mask(struct adf_accel_dev *accel_dev, u32 obj_num) { - switch (get_service_enabled(accel_dev)) { - case SVC_CY: - return adf_fw_cy_config[obj_num].ae_mask; - case SVC_DC: - return adf_fw_dc_config[obj_num].ae_mask; - case SVC_CY2: - return adf_fw_cy_config[obj_num].ae_mask; - case SVC_SYM: - return adf_fw_sym_config[obj_num].ae_mask; - case SVC_ASYM: - return adf_fw_asym_config[obj_num].ae_mask; - case SVC_ASYM_DC: - case SVC_DC_ASYM: - return adf_fw_asym_dc_config[obj_num].ae_mask; - case SVC_SYM_DC: - case SVC_DC_SYM: - return adf_fw_sym_dc_config[obj_num].ae_mask; - default: + const struct adf_fw_config *fw_config; + + fw_config = get_fw_config(accel_dev); + if (!fw_config) return 0; - } + + return fw_config[obj_num].ae_mask; } void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data, u32 dev_id) @@ -522,6 +557,7 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data, u32 dev_id) hw_data->uof_get_ae_mask = uof_get_ae_mask; hw_data->set_msix_rttable = set_msix_default_rttable; hw_data->set_ssm_wdtimer = adf_gen4_set_ssm_wdtimer; + hw_data->get_ring_to_svc_map = get_ring_to_svc_map; hw_data->disable_iov = adf_disable_sriov; hw_data->ring_pair_reset = adf_gen4_ring_pair_reset; hw_data->enable_pm = adf_gen4_enable_pm; diff --git a/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c b/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c index 6d4e2e139ffa24..f6f9e20f74b543 100644 --- a/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c +++ b/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c @@ -11,6 +11,7 @@ #include #include "adf_4xxx_hw_data.h" +#include "adf_cfg_services.h" #include "qat_compression.h" #include "qat_crypto.h" #include "adf_transport_access_macros.h" @@ -23,30 +24,6 @@ static const struct pci_device_id adf_pci_tbl[] = { }; MODULE_DEVICE_TABLE(pci, adf_pci_tbl); -enum configs { - DEV_CFG_CY = 0, - DEV_CFG_DC, - DEV_CFG_SYM, - DEV_CFG_ASYM, - DEV_CFG_ASYM_SYM, - DEV_CFG_ASYM_DC, - DEV_CFG_DC_ASYM, - DEV_CFG_SYM_DC, - DEV_CFG_DC_SYM, -}; - -static const char * const services_operations[] = { - ADF_CFG_CY, - ADF_CFG_DC, - ADF_CFG_SYM, - ADF_CFG_ASYM, - ADF_CFG_ASYM_SYM, - ADF_CFG_ASYM_DC, - ADF_CFG_DC_ASYM, - ADF_CFG_SYM_DC, - ADF_CFG_DC_SYM, -}; - static void adf_cleanup_accel(struct adf_accel_dev *accel_dev) { if (accel_dev->hw_device) { @@ -292,16 +269,17 @@ int adf_gen4_dev_config(struct adf_accel_dev *accel_dev) if (ret) goto err; - ret = sysfs_match_string(services_operations, services); + ret = sysfs_match_string(adf_cfg_services, services); if (ret < 0) goto err; switch (ret) { - case DEV_CFG_CY: - case DEV_CFG_ASYM_SYM: + case SVC_CY: + case SVC_CY2: ret = adf_crypto_dev_config(accel_dev); break; - case DEV_CFG_DC: + case SVC_DC: + case SVC_DCC: ret = adf_comp_dev_config(accel_dev); break; default: @@ -485,7 +463,9 @@ module_pci_driver(adf_driver); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Intel"); MODULE_FIRMWARE(ADF_4XXX_FW); +MODULE_FIRMWARE(ADF_402XX_FW); MODULE_FIRMWARE(ADF_4XXX_MMP); +MODULE_FIRMWARE(ADF_402XX_MMP); MODULE_DESCRIPTION("Intel(R) QuickAssist Technology"); MODULE_VERSION(ADF_DRV_VERSION); MODULE_SOFTDEP("pre: crypto-intel_qat"); diff --git a/drivers/crypto/intel/qat/qat_common/Makefile b/drivers/crypto/intel/qat/qat_common/Makefile index 43622c7fca712c..8dbf146de3fa59 100644 --- a/drivers/crypto/intel/qat/qat_common/Makefile +++ b/drivers/crypto/intel/qat/qat_common/Makefile @@ -3,6 +3,7 @@ obj-$(CONFIG_CRYPTO_DEV_QAT) += intel_qat.o intel_qat-objs := adf_cfg.o \ adf_isr.o \ adf_ctl_drv.o \ + adf_cfg_services.o \ adf_dev_mgr.o \ adf_init.o \ adf_accel_engine.o \ diff --git a/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h b/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h index e57abde66f4fb3..79d5a1535eda34 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h +++ b/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h @@ -29,7 +29,7 @@ #define ADF_PCI_MAX_BARS 3 #define ADF_DEVICE_NAME_LENGTH 32 #define ADF_ETR_MAX_RINGS_PER_BANK 16 -#define ADF_MAX_MSIX_VECTOR_NAME 16 +#define ADF_MAX_MSIX_VECTOR_NAME 48 #define ADF_DEVICE_NAME_PREFIX "qat_" enum adf_accel_capabilities { @@ -182,6 +182,7 @@ struct adf_hw_device_data { void (*get_arb_info)(struct arb_info *arb_csrs_info); void (*get_admin_info)(struct admin_info *admin_csrs_info); enum dev_sku_info (*get_sku)(struct adf_hw_device_data *self); + u16 (*get_ring_to_svc_map)(struct adf_accel_dev *accel_dev); int (*alloc_irq)(struct adf_accel_dev *accel_dev); void (*free_irq)(struct adf_accel_dev *accel_dev); void (*enable_error_correction)(struct adf_accel_dev *accel_dev); diff --git a/drivers/crypto/intel/qat/qat_common/adf_admin.c b/drivers/crypto/intel/qat/qat_common/adf_admin.c index ff790823b86861..194d64d4b99a1b 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_admin.c +++ b/drivers/crypto/intel/qat/qat_common/adf_admin.c @@ -8,6 +8,7 @@ #include #include "adf_accel_devices.h" #include "adf_common_drv.h" +#include "adf_cfg.h" #include "adf_heartbeat.h" #include "icp_qat_fw_init_admin.h" @@ -212,6 +213,17 @@ int adf_get_fw_timestamp(struct adf_accel_dev *accel_dev, u64 *timestamp) return 0; } +static int adf_set_chaining(struct adf_accel_dev *accel_dev) +{ + u32 ae_mask = GET_HW_DATA(accel_dev)->ae_mask; + struct icp_qat_fw_init_admin_resp resp = { }; + struct icp_qat_fw_init_admin_req req = { }; + + req.cmd_id = ICP_QAT_FW_DC_CHAIN_INIT; + + return adf_send_admin(accel_dev, &req, &resp, ae_mask); +} + static int adf_get_dc_capabilities(struct adf_accel_dev *accel_dev, u32 *capabilities) { @@ -284,6 +296,19 @@ int adf_send_admin_hb_timer(struct adf_accel_dev *accel_dev, uint32_t ticks) return adf_send_admin(accel_dev, &req, &resp, ae_mask); } +static bool is_dcc_enabled(struct adf_accel_dev *accel_dev) +{ + char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0}; + int ret; + + ret = adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC, + ADF_SERVICES_ENABLED, services); + if (ret) + return false; + + return !strcmp(services, "dcc"); +} + /** * adf_send_admin_init() - Function sends init message to FW * @accel_dev: Pointer to acceleration device. @@ -297,6 +322,16 @@ int adf_send_admin_init(struct adf_accel_dev *accel_dev) u32 dc_capabilities = 0; int ret; + ret = adf_set_fw_constants(accel_dev); + if (ret) + return ret; + + if (is_dcc_enabled(accel_dev)) { + ret = adf_set_chaining(accel_dev); + if (ret) + return ret; + } + ret = adf_get_dc_capabilities(accel_dev, &dc_capabilities); if (ret) { dev_err(&GET_DEV(accel_dev), "Cannot get dc capabilities\n"); @@ -304,10 +339,6 @@ int adf_send_admin_init(struct adf_accel_dev *accel_dev) } accel_dev->hw_device->extended_dc_capabilities = dc_capabilities; - ret = adf_set_fw_constants(accel_dev); - if (ret) - return ret; - return adf_init_ae(accel_dev); } EXPORT_SYMBOL_GPL(adf_send_admin_init); diff --git a/drivers/crypto/intel/qat/qat_common/adf_aer.c b/drivers/crypto/intel/qat/qat_common/adf_aer.c index 04af32a2811c8f..af495a6f039f6b 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_aer.c +++ b/drivers/crypto/intel/qat/qat_common/adf_aer.c @@ -92,7 +92,8 @@ static void adf_device_reset_worker(struct work_struct *work) if (adf_dev_restart(accel_dev)) { /* The device hanged and we can't restart it so stop here */ dev_err(&GET_DEV(accel_dev), "Restart device failed\n"); - kfree(reset_data); + if (reset_data->mode == ADF_DEV_RESET_ASYNC) + kfree(reset_data); WARN(1, "QAT: device restart failed. Device is unusable\n"); return; } @@ -100,10 +101,10 @@ static void adf_device_reset_worker(struct work_struct *work) clear_bit(ADF_STATUS_RESTARTING, &accel_dev->status); /* The dev is back alive. Notify the caller if in sync mode */ - if (reset_data->mode == ADF_DEV_RESET_SYNC) - complete(&reset_data->compl); - else + if (reset_data->mode == ADF_DEV_RESET_ASYNC) kfree(reset_data); + else + complete(&reset_data->compl); } static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev, @@ -135,6 +136,7 @@ static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev, if (!timeout) { dev_err(&GET_DEV(accel_dev), "Reset device timeout expired\n"); + cancel_work_sync(&reset_data->reset_work); ret = -EFAULT; } kfree(reset_data); diff --git a/drivers/crypto/intel/qat/qat_common/adf_cfg.c b/drivers/crypto/intel/qat/qat_common/adf_cfg.c index 8836f015c39c41..2cf102ad4ca82d 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_cfg.c +++ b/drivers/crypto/intel/qat/qat_common/adf_cfg.c @@ -290,17 +290,19 @@ int adf_cfg_add_key_value_param(struct adf_accel_dev *accel_dev, * 3. if the key exists with the same value, then return without doing * anything (the newly created key_val is freed). */ + down_write(&cfg->lock); if (!adf_cfg_key_val_get(accel_dev, section_name, key, temp_val)) { if (strncmp(temp_val, key_val->val, sizeof(temp_val))) { adf_cfg_keyval_remove(key, section); } else { kfree(key_val); - return 0; + goto out; } } - down_write(&cfg->lock); adf_cfg_keyval_add(key_val, section); + +out: up_write(&cfg->lock); return 0; } diff --git a/drivers/crypto/intel/qat/qat_common/adf_cfg_services.c b/drivers/crypto/intel/qat/qat_common/adf_cfg_services.c new file mode 100644 index 00000000000000..26805229446843 --- /dev/null +++ b/drivers/crypto/intel/qat/qat_common/adf_cfg_services.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2023 Intel Corporation */ + +#include +#include +#include +#include "adf_cfg.h" +#include "adf_cfg_services.h" +#include "adf_cfg_strings.h" + +const char *const adf_cfg_services[] = { + [SVC_CY] = ADF_CFG_CY, + [SVC_CY2] = ADF_CFG_ASYM_SYM, + [SVC_DC] = ADF_CFG_DC, + [SVC_DCC] = ADF_CFG_DCC, + [SVC_SYM] = ADF_CFG_SYM, + [SVC_ASYM] = ADF_CFG_ASYM, + [SVC_DC_ASYM] = ADF_CFG_DC_ASYM, + [SVC_ASYM_DC] = ADF_CFG_ASYM_DC, + [SVC_DC_SYM] = ADF_CFG_DC_SYM, + [SVC_SYM_DC] = ADF_CFG_SYM_DC, +}; +EXPORT_SYMBOL_GPL(adf_cfg_services); + +int adf_get_service_enabled(struct adf_accel_dev *accel_dev) +{ + char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0}; + int ret; + + ret = adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC, + ADF_SERVICES_ENABLED, services); + if (ret) { + dev_err(&GET_DEV(accel_dev), + ADF_SERVICES_ENABLED " param not found\n"); + return ret; + } + + ret = match_string(adf_cfg_services, ARRAY_SIZE(adf_cfg_services), + services); + if (ret < 0) + dev_err(&GET_DEV(accel_dev), + "Invalid value of " ADF_SERVICES_ENABLED " param: %s\n", + services); + + return ret; +} +EXPORT_SYMBOL_GPL(adf_get_service_enabled); diff --git a/drivers/crypto/intel/qat/qat_common/adf_cfg_services.h b/drivers/crypto/intel/qat/qat_common/adf_cfg_services.h new file mode 100644 index 00000000000000..c6b0328b0f5b03 --- /dev/null +++ b/drivers/crypto/intel/qat/qat_common/adf_cfg_services.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2023 Intel Corporation */ +#ifndef _ADF_CFG_SERVICES_H_ +#define _ADF_CFG_SERVICES_H_ + +#include "adf_cfg_strings.h" + +struct adf_accel_dev; + +enum adf_services { + SVC_CY = 0, + SVC_CY2, + SVC_DC, + SVC_DCC, + SVC_SYM, + SVC_ASYM, + SVC_DC_ASYM, + SVC_ASYM_DC, + SVC_DC_SYM, + SVC_SYM_DC, + SVC_COUNT +}; + +extern const char *const adf_cfg_services[SVC_COUNT]; + +int adf_get_service_enabled(struct adf_accel_dev *accel_dev); + +#endif diff --git a/drivers/crypto/intel/qat/qat_common/adf_cfg_strings.h b/drivers/crypto/intel/qat/qat_common/adf_cfg_strings.h index 6066dc637352ca..322b76903a737d 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_cfg_strings.h +++ b/drivers/crypto/intel/qat/qat_common/adf_cfg_strings.h @@ -32,6 +32,7 @@ #define ADF_CFG_DC_ASYM "dc;asym" #define ADF_CFG_SYM_DC "sym;dc" #define ADF_CFG_DC_SYM "dc;sym" +#define ADF_CFG_DCC "dcc" #define ADF_SERVICES_ENABLED "ServicesEnabled" #define ADF_PM_IDLE_SUPPORT "PmIdleSupport" #define ADF_ETRMGR_COALESCING_ENABLED "InterruptCoalescingEnabled" diff --git a/drivers/crypto/intel/qat/qat_common/adf_clock.c b/drivers/crypto/intel/qat/qat_common/adf_clock.c index dc0778691eb0ba..eae44969dc84fa 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_clock.c +++ b/drivers/crypto/intel/qat/qat_common/adf_clock.c @@ -82,6 +82,9 @@ static int measure_clock(struct adf_accel_dev *accel_dev, u32 *frequency) } delta_us = timespec_to_us(&ts3) - timespec_to_us(&ts1); + if (!delta_us) + return -EINVAL; + temp = (timestamp2 - timestamp1) * ME_CLK_DIVIDER * 10; temp = DIV_ROUND_CLOSEST_ULL(temp, delta_us); /* diff --git a/drivers/crypto/intel/qat/qat_common/adf_common_drv.h b/drivers/crypto/intel/qat/qat_common/adf_common_drv.h index 673b5044c62a50..79ff7982378d9f 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_common_drv.h +++ b/drivers/crypto/intel/qat/qat_common/adf_common_drv.h @@ -25,6 +25,8 @@ #define ADF_STATUS_AE_STARTED 6 #define ADF_STATUS_PF_RUNNING 7 #define ADF_STATUS_IRQ_ALLOCATED 8 +#define ADF_STATUS_CRYPTO_ALGS_REGISTERED 9 +#define ADF_STATUS_COMP_ALGS_REGISTERED 10 enum adf_dev_reset_mode { ADF_DEV_RESET_ASYNC = 0, diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen2_pfvf.c b/drivers/crypto/intel/qat/qat_common/adf_gen2_pfvf.c index 70ef1196393814..43af81fcab8686 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_gen2_pfvf.c +++ b/drivers/crypto/intel/qat/qat_common/adf_gen2_pfvf.c @@ -100,7 +100,9 @@ static u32 adf_gen2_disable_pending_vf2pf_interrupts(void __iomem *pmisc_addr) errmsk3 |= ADF_GEN2_ERR_MSK_VF2PF(ADF_GEN2_VF_MSK); ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); - errmsk3 &= ADF_GEN2_ERR_MSK_VF2PF(sources | disabled); + /* Update only section of errmsk3 related to VF2PF */ + errmsk3 &= ~ADF_GEN2_ERR_MSK_VF2PF(ADF_GEN2_VF_MSK); + errmsk3 |= ADF_GEN2_ERR_MSK_VF2PF(sources | disabled); ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); /* Return the sources of the (new) interrupt(s) */ diff --git a/drivers/crypto/intel/qat/qat_common/adf_init.c b/drivers/crypto/intel/qat/qat_common/adf_init.c index 89001fe92e7629..0f9e2d59ce3857 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_init.c +++ b/drivers/crypto/intel/qat/qat_common/adf_init.c @@ -97,6 +97,9 @@ static int adf_dev_init(struct adf_accel_dev *accel_dev) return -EFAULT; } + if (hw_data->get_ring_to_svc_map) + hw_data->ring_to_svc_map = hw_data->get_ring_to_svc_map(accel_dev); + if (adf_ae_init(accel_dev)) { dev_err(&GET_DEV(accel_dev), "Failed to initialise Acceleration Engine\n"); @@ -231,6 +234,7 @@ static int adf_dev_start(struct adf_accel_dev *accel_dev) clear_bit(ADF_STATUS_STARTED, &accel_dev->status); return -EFAULT; } + set_bit(ADF_STATUS_CRYPTO_ALGS_REGISTERED, &accel_dev->status); if (!list_empty(&accel_dev->compression_list) && qat_comp_algs_register()) { dev_err(&GET_DEV(accel_dev), @@ -239,6 +243,7 @@ static int adf_dev_start(struct adf_accel_dev *accel_dev) clear_bit(ADF_STATUS_STARTED, &accel_dev->status); return -EFAULT; } + set_bit(ADF_STATUS_COMP_ALGS_REGISTERED, &accel_dev->status); adf_dbgfs_add(accel_dev); @@ -272,13 +277,17 @@ static void adf_dev_stop(struct adf_accel_dev *accel_dev) clear_bit(ADF_STATUS_STARTING, &accel_dev->status); clear_bit(ADF_STATUS_STARTED, &accel_dev->status); - if (!list_empty(&accel_dev->crypto_list)) { + if (!list_empty(&accel_dev->crypto_list) && + test_bit(ADF_STATUS_CRYPTO_ALGS_REGISTERED, &accel_dev->status)) { qat_algs_unregister(); qat_asym_algs_unregister(); } + clear_bit(ADF_STATUS_CRYPTO_ALGS_REGISTERED, &accel_dev->status); - if (!list_empty(&accel_dev->compression_list)) + if (!list_empty(&accel_dev->compression_list) && + test_bit(ADF_STATUS_COMP_ALGS_REGISTERED, &accel_dev->status)) qat_comp_algs_unregister(); + clear_bit(ADF_STATUS_COMP_ALGS_REGISTERED, &accel_dev->status); list_for_each(list_itr, &service_table) { service = list_entry(list_itr, struct service_hndl, list); @@ -440,13 +449,6 @@ int adf_dev_down(struct adf_accel_dev *accel_dev, bool reconfig) mutex_lock(&accel_dev->state_lock); - if (!adf_dev_started(accel_dev)) { - dev_info(&GET_DEV(accel_dev), "Device qat_dev%d already down\n", - accel_dev->accel_id); - ret = -EINVAL; - goto out; - } - if (reconfig) { ret = adf_dev_shutdown_cache_cfg(accel_dev); goto out; diff --git a/drivers/crypto/intel/qat/qat_common/adf_sysfs.c b/drivers/crypto/intel/qat/qat_common/adf_sysfs.c index a74d2f93036709..8f04b0d3c5ac89 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_sysfs.c +++ b/drivers/crypto/intel/qat/qat_common/adf_sysfs.c @@ -5,6 +5,7 @@ #include #include "adf_accel_devices.h" #include "adf_cfg.h" +#include "adf_cfg_services.h" #include "adf_common_drv.h" static const char * const state_operations[] = { @@ -52,6 +53,13 @@ static ssize_t state_store(struct device *dev, struct device_attribute *attr, case DEV_DOWN: dev_info(dev, "Stopping device qat_dev%d\n", accel_id); + if (!adf_dev_started(accel_dev)) { + dev_info(&GET_DEV(accel_dev), "Device qat_dev%d already down\n", + accel_id); + + break; + } + ret = adf_dev_down(accel_dev, true); if (ret < 0) return -EINVAL; @@ -61,7 +69,9 @@ static ssize_t state_store(struct device *dev, struct device_attribute *attr, dev_info(dev, "Starting device qat_dev%d\n", accel_id); ret = adf_dev_up(accel_dev, true); - if (ret < 0) { + if (ret == -EALREADY) { + break; + } else if (ret) { dev_err(dev, "Failed to start device qat_dev%d\n", accel_id); adf_dev_down(accel_dev, true); @@ -75,18 +85,6 @@ static ssize_t state_store(struct device *dev, struct device_attribute *attr, return count; } -static const char * const services_operations[] = { - ADF_CFG_CY, - ADF_CFG_DC, - ADF_CFG_SYM, - ADF_CFG_ASYM, - ADF_CFG_ASYM_SYM, - ADF_CFG_ASYM_DC, - ADF_CFG_DC_ASYM, - ADF_CFG_SYM_DC, - ADF_CFG_DC_SYM, -}; - static ssize_t cfg_services_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -121,7 +119,7 @@ static ssize_t cfg_services_store(struct device *dev, struct device_attribute *a struct adf_accel_dev *accel_dev; int ret; - ret = sysfs_match_string(services_operations, buf); + ret = sysfs_match_string(adf_cfg_services, buf); if (ret < 0) return ret; @@ -135,7 +133,7 @@ static ssize_t cfg_services_store(struct device *dev, struct device_attribute *a return -EINVAL; } - ret = adf_sysfs_update_dev_config(accel_dev, services_operations[ret]); + ret = adf_sysfs_update_dev_config(accel_dev, adf_cfg_services[ret]); if (ret < 0) return ret; diff --git a/drivers/crypto/intel/qat/qat_common/adf_transport_debug.c b/drivers/crypto/intel/qat/qat_common/adf_transport_debug.c index 08bca1c506c0ef..e2dd568b87b519 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_transport_debug.c +++ b/drivers/crypto/intel/qat/qat_common/adf_transport_debug.c @@ -90,7 +90,7 @@ DEFINE_SEQ_ATTRIBUTE(adf_ring_debug); int adf_ring_debugfs_add(struct adf_etr_ring_data *ring, const char *name) { struct adf_etr_ring_debug_entry *ring_debug; - char entry_name[8]; + char entry_name[16]; ring_debug = kzalloc(sizeof(*ring_debug), GFP_KERNEL); if (!ring_debug) @@ -192,7 +192,7 @@ int adf_bank_debugfs_add(struct adf_etr_bank_data *bank) { struct adf_accel_dev *accel_dev = bank->accel_dev; struct dentry *parent = accel_dev->transport->debug; - char name[8]; + char name[16]; snprintf(name, sizeof(name), "bank_%02d", bank->bank_number); bank->bank_debug_dir = debugfs_create_dir(name, parent); diff --git a/drivers/crypto/intel/qat/qat_common/icp_qat_fw_init_admin.h b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_init_admin.h index 3e968a4bcc9cd5..019a6443834e0b 100644 --- a/drivers/crypto/intel/qat/qat_common/icp_qat_fw_init_admin.h +++ b/drivers/crypto/intel/qat/qat_common/icp_qat_fw_init_admin.h @@ -16,6 +16,7 @@ enum icp_qat_fw_init_admin_cmd_id { ICP_QAT_FW_HEARTBEAT_SYNC = 7, ICP_QAT_FW_HEARTBEAT_GET = 8, ICP_QAT_FW_COMP_CAPABILITY_GET = 9, + ICP_QAT_FW_DC_CHAIN_INIT = 11, ICP_QAT_FW_HEARTBEAT_TIMER_SET = 13, ICP_QAT_FW_TIMER_GET = 19, ICP_QAT_FW_PM_STATE_CONFIG = 128, diff --git a/drivers/crypto/intel/qat/qat_common/qat_algs_send.c b/drivers/crypto/intel/qat/qat_common/qat_algs_send.c index bb80455b3e81e2..b97b678823a975 100644 --- a/drivers/crypto/intel/qat/qat_common/qat_algs_send.c +++ b/drivers/crypto/intel/qat/qat_common/qat_algs_send.c @@ -40,40 +40,44 @@ void qat_alg_send_backlog(struct qat_instance_backlog *backlog) spin_unlock_bh(&backlog->lock); } -static void qat_alg_backlog_req(struct qat_alg_req *req, - struct qat_instance_backlog *backlog) -{ - INIT_LIST_HEAD(&req->list); - - spin_lock_bh(&backlog->lock); - list_add_tail(&req->list, &backlog->list); - spin_unlock_bh(&backlog->lock); -} - -static int qat_alg_send_message_maybacklog(struct qat_alg_req *req) +static bool qat_alg_try_enqueue(struct qat_alg_req *req) { struct qat_instance_backlog *backlog = req->backlog; struct adf_etr_ring_data *tx_ring = req->tx_ring; u32 *fw_req = req->fw_req; - /* If any request is already backlogged, then add to backlog list */ + /* Check if any request is already backlogged */ if (!list_empty(&backlog->list)) - goto enqueue; + return false; - /* If ring is nearly full, then add to backlog list */ + /* Check if ring is nearly full */ if (adf_ring_nearly_full(tx_ring)) - goto enqueue; + return false; - /* If adding request to HW ring fails, then add to backlog list */ + /* Try to enqueue to HW ring */ if (adf_send_message(tx_ring, fw_req)) - goto enqueue; + return false; - return -EINPROGRESS; + return true; +} -enqueue: - qat_alg_backlog_req(req, backlog); - return -EBUSY; +static int qat_alg_send_message_maybacklog(struct qat_alg_req *req) +{ + struct qat_instance_backlog *backlog = req->backlog; + int ret = -EINPROGRESS; + + if (qat_alg_try_enqueue(req)) + return ret; + + spin_lock_bh(&backlog->lock); + if (!qat_alg_try_enqueue(req)) { + list_add_tail(&req->list, &backlog->list); + ret = -EBUSY; + } + spin_unlock_bh(&backlog->lock); + + return ret; } int qat_alg_send_message(struct qat_alg_req *req) diff --git a/drivers/crypto/intel/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c b/drivers/crypto/intel/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c index 09551f94912653..0e40897cc983a8 100644 --- a/drivers/crypto/intel/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c +++ b/drivers/crypto/intel/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c @@ -191,8 +191,12 @@ static u32 disable_pending_vf2pf_interrupts(void __iomem *pmisc_addr) ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, errmsk5); - errmsk3 &= ADF_DH895XCC_ERR_MSK_VF2PF_L(sources | disabled); - errmsk5 &= ADF_DH895XCC_ERR_MSK_VF2PF_U(sources | disabled); + /* Update only section of errmsk3 and errmsk5 related to VF2PF */ + errmsk3 &= ~ADF_DH895XCC_ERR_MSK_VF2PF_L(ADF_DH895XCC_VF_MSK); + errmsk5 &= ~ADF_DH895XCC_ERR_MSK_VF2PF_U(ADF_DH895XCC_VF_MSK); + + errmsk3 |= ADF_DH895XCC_ERR_MSK_VF2PF_L(sources | disabled); + errmsk5 |= ADF_DH895XCC_ERR_MSK_VF2PF_U(sources | disabled); ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, errmsk5); diff --git a/drivers/crypto/marvell/Kconfig b/drivers/crypto/marvell/Kconfig index a48591af12d025..78217577aa5403 100644 --- a/drivers/crypto/marvell/Kconfig +++ b/drivers/crypto/marvell/Kconfig @@ -28,6 +28,7 @@ config CRYPTO_DEV_OCTEONTX_CPT select CRYPTO_SKCIPHER select CRYPTO_HASH select CRYPTO_AEAD + select CRYPTO_AUTHENC select CRYPTO_DEV_MARVELL help This driver allows you to utilize the Marvell Cryptographic @@ -47,6 +48,7 @@ config CRYPTO_DEV_OCTEONTX2_CPT select CRYPTO_SKCIPHER select CRYPTO_HASH select CRYPTO_AEAD + select CRYPTO_AUTHENC select NET_DEVLINK help This driver allows you to utilize the Marvell Cryptographic diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c index 1c2c870e887aab..f64b72398eced9 100644 --- a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c +++ b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include "otx_cptvf.h" @@ -66,6 +65,8 @@ static struct cpt_device_table ae_devices = { .count = ATOMIC_INIT(0) }; +static struct otx_cpt_sdesc *alloc_sdesc(struct crypto_shash *alg); + static inline int get_se_device(struct pci_dev **pdev, int *cpu_num) { int count, ret = 0; @@ -515,44 +516,61 @@ static int cpt_aead_init(struct crypto_aead *tfm, u8 cipher_type, u8 mac_type) ctx->cipher_type = cipher_type; ctx->mac_type = mac_type; + switch (ctx->mac_type) { + case OTX_CPT_SHA1: + ctx->hashalg = crypto_alloc_shash("sha1", 0, 0); + break; + + case OTX_CPT_SHA256: + ctx->hashalg = crypto_alloc_shash("sha256", 0, 0); + break; + + case OTX_CPT_SHA384: + ctx->hashalg = crypto_alloc_shash("sha384", 0, 0); + break; + + case OTX_CPT_SHA512: + ctx->hashalg = crypto_alloc_shash("sha512", 0, 0); + break; + } + + if (IS_ERR(ctx->hashalg)) + return PTR_ERR(ctx->hashalg); + + crypto_aead_set_reqsize_dma(tfm, sizeof(struct otx_cpt_req_ctx)); + + if (!ctx->hashalg) + return 0; + /* * When selected cipher is NULL we use HMAC opcode instead of * FLEXICRYPTO opcode therefore we don't need to use HASH algorithms * for calculating ipad and opad */ if (ctx->cipher_type != OTX_CPT_CIPHER_NULL) { - switch (ctx->mac_type) { - case OTX_CPT_SHA1: - ctx->hashalg = crypto_alloc_shash("sha1", 0, - CRYPTO_ALG_ASYNC); - if (IS_ERR(ctx->hashalg)) - return PTR_ERR(ctx->hashalg); - break; - - case OTX_CPT_SHA256: - ctx->hashalg = crypto_alloc_shash("sha256", 0, - CRYPTO_ALG_ASYNC); - if (IS_ERR(ctx->hashalg)) - return PTR_ERR(ctx->hashalg); - break; + int ss = crypto_shash_statesize(ctx->hashalg); - case OTX_CPT_SHA384: - ctx->hashalg = crypto_alloc_shash("sha384", 0, - CRYPTO_ALG_ASYNC); - if (IS_ERR(ctx->hashalg)) - return PTR_ERR(ctx->hashalg); - break; + ctx->ipad = kzalloc(ss, GFP_KERNEL); + if (!ctx->ipad) { + crypto_free_shash(ctx->hashalg); + return -ENOMEM; + } - case OTX_CPT_SHA512: - ctx->hashalg = crypto_alloc_shash("sha512", 0, - CRYPTO_ALG_ASYNC); - if (IS_ERR(ctx->hashalg)) - return PTR_ERR(ctx->hashalg); - break; + ctx->opad = kzalloc(ss, GFP_KERNEL); + if (!ctx->opad) { + kfree(ctx->ipad); + crypto_free_shash(ctx->hashalg); + return -ENOMEM; } } - crypto_aead_set_reqsize_dma(tfm, sizeof(struct otx_cpt_req_ctx)); + ctx->sdesc = alloc_sdesc(ctx->hashalg); + if (!ctx->sdesc) { + kfree(ctx->opad); + kfree(ctx->ipad); + crypto_free_shash(ctx->hashalg); + return -ENOMEM; + } return 0; } @@ -608,8 +626,7 @@ static void otx_cpt_aead_exit(struct crypto_aead *tfm) kfree(ctx->ipad); kfree(ctx->opad); - if (ctx->hashalg) - crypto_free_shash(ctx->hashalg); + crypto_free_shash(ctx->hashalg); kfree(ctx->sdesc); } @@ -705,7 +722,7 @@ static inline void swap_data64(void *buf, u32 len) *dst = cpu_to_be64p(src); } -static int copy_pad(u8 mac_type, u8 *out_pad, u8 *in_pad) +static int swap_pad(u8 mac_type, u8 *pad) { struct sha512_state *sha512; struct sha256_state *sha256; @@ -713,22 +730,19 @@ static int copy_pad(u8 mac_type, u8 *out_pad, u8 *in_pad) switch (mac_type) { case OTX_CPT_SHA1: - sha1 = (struct sha1_state *) in_pad; + sha1 = (struct sha1_state *)pad; swap_data32(sha1->state, SHA1_DIGEST_SIZE); - memcpy(out_pad, &sha1->state, SHA1_DIGEST_SIZE); break; case OTX_CPT_SHA256: - sha256 = (struct sha256_state *) in_pad; + sha256 = (struct sha256_state *)pad; swap_data32(sha256->state, SHA256_DIGEST_SIZE); - memcpy(out_pad, &sha256->state, SHA256_DIGEST_SIZE); break; case OTX_CPT_SHA384: case OTX_CPT_SHA512: - sha512 = (struct sha512_state *) in_pad; + sha512 = (struct sha512_state *)pad; swap_data64(sha512->state, SHA512_DIGEST_SIZE); - memcpy(out_pad, &sha512->state, SHA512_DIGEST_SIZE); break; default: @@ -738,55 +752,53 @@ static int copy_pad(u8 mac_type, u8 *out_pad, u8 *in_pad) return 0; } -static int aead_hmac_init(struct crypto_aead *cipher) +static int aead_hmac_init(struct crypto_aead *cipher, + struct crypto_authenc_keys *keys) { struct otx_cpt_aead_ctx *ctx = crypto_aead_ctx_dma(cipher); - int state_size = crypto_shash_statesize(ctx->hashalg); int ds = crypto_shash_digestsize(ctx->hashalg); int bs = crypto_shash_blocksize(ctx->hashalg); - int authkeylen = ctx->auth_key_len; + int authkeylen = keys->authkeylen; u8 *ipad = NULL, *opad = NULL; - int ret = 0, icount = 0; + int icount = 0; + int ret; - ctx->sdesc = alloc_sdesc(ctx->hashalg); - if (!ctx->sdesc) - return -ENOMEM; + if (authkeylen > bs) { + ret = crypto_shash_digest(&ctx->sdesc->shash, keys->authkey, + authkeylen, ctx->key); + if (ret) + return ret; + authkeylen = ds; + } else + memcpy(ctx->key, keys->authkey, authkeylen); - ctx->ipad = kzalloc(bs, GFP_KERNEL); - if (!ctx->ipad) { - ret = -ENOMEM; - goto calc_fail; - } + ctx->enc_key_len = keys->enckeylen; + ctx->auth_key_len = authkeylen; - ctx->opad = kzalloc(bs, GFP_KERNEL); - if (!ctx->opad) { - ret = -ENOMEM; - goto calc_fail; - } + if (ctx->cipher_type == OTX_CPT_CIPHER_NULL) + return keys->enckeylen ? -EINVAL : 0; - ipad = kzalloc(state_size, GFP_KERNEL); - if (!ipad) { - ret = -ENOMEM; - goto calc_fail; + switch (keys->enckeylen) { + case AES_KEYSIZE_128: + ctx->key_type = OTX_CPT_AES_128_BIT; + break; + case AES_KEYSIZE_192: + ctx->key_type = OTX_CPT_AES_192_BIT; + break; + case AES_KEYSIZE_256: + ctx->key_type = OTX_CPT_AES_256_BIT; + break; + default: + /* Invalid key length */ + return -EINVAL; } - opad = kzalloc(state_size, GFP_KERNEL); - if (!opad) { - ret = -ENOMEM; - goto calc_fail; - } + memcpy(ctx->key + authkeylen, keys->enckey, keys->enckeylen); - if (authkeylen > bs) { - ret = crypto_shash_digest(&ctx->sdesc->shash, ctx->key, - authkeylen, ipad); - if (ret) - goto calc_fail; - - authkeylen = ds; - } else { - memcpy(ipad, ctx->key, authkeylen); - } + ipad = ctx->ipad; + opad = ctx->opad; + memcpy(ipad, ctx->key, authkeylen); memset(ipad + authkeylen, 0, bs - authkeylen); memcpy(opad, ipad, bs); @@ -804,7 +816,7 @@ static int aead_hmac_init(struct crypto_aead *cipher) crypto_shash_init(&ctx->sdesc->shash); crypto_shash_update(&ctx->sdesc->shash, ipad, bs); crypto_shash_export(&ctx->sdesc->shash, ipad); - ret = copy_pad(ctx->mac_type, ctx->ipad, ipad); + ret = swap_pad(ctx->mac_type, ipad); if (ret) goto calc_fail; @@ -812,25 +824,9 @@ static int aead_hmac_init(struct crypto_aead *cipher) crypto_shash_init(&ctx->sdesc->shash); crypto_shash_update(&ctx->sdesc->shash, opad, bs); crypto_shash_export(&ctx->sdesc->shash, opad); - ret = copy_pad(ctx->mac_type, ctx->opad, opad); - if (ret) - goto calc_fail; - - kfree(ipad); - kfree(opad); - - return 0; + ret = swap_pad(ctx->mac_type, opad); calc_fail: - kfree(ctx->ipad); - ctx->ipad = NULL; - kfree(ctx->opad); - ctx->opad = NULL; - kfree(ipad); - kfree(opad); - kfree(ctx->sdesc); - ctx->sdesc = NULL; - return ret; } @@ -838,57 +834,15 @@ static int otx_cpt_aead_cbc_aes_sha_setkey(struct crypto_aead *cipher, const unsigned char *key, unsigned int keylen) { - struct otx_cpt_aead_ctx *ctx = crypto_aead_ctx_dma(cipher); - struct crypto_authenc_key_param *param; - int enckeylen = 0, authkeylen = 0; - struct rtattr *rta = (void *)key; - int status = -EINVAL; - - if (!RTA_OK(rta, keylen)) - goto badkey; - - if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM) - goto badkey; - - if (RTA_PAYLOAD(rta) < sizeof(*param)) - goto badkey; - - param = RTA_DATA(rta); - enckeylen = be32_to_cpu(param->enckeylen); - key += RTA_ALIGN(rta->rta_len); - keylen -= RTA_ALIGN(rta->rta_len); - if (keylen < enckeylen) - goto badkey; + struct crypto_authenc_keys authenc_keys; + int status; - if (keylen > OTX_CPT_MAX_KEY_SIZE) - goto badkey; - - authkeylen = keylen - enckeylen; - memcpy(ctx->key, key, keylen); - - switch (enckeylen) { - case AES_KEYSIZE_128: - ctx->key_type = OTX_CPT_AES_128_BIT; - break; - case AES_KEYSIZE_192: - ctx->key_type = OTX_CPT_AES_192_BIT; - break; - case AES_KEYSIZE_256: - ctx->key_type = OTX_CPT_AES_256_BIT; - break; - default: - /* Invalid key length */ - goto badkey; - } - - ctx->enc_key_len = enckeylen; - ctx->auth_key_len = authkeylen; - - status = aead_hmac_init(cipher); + status = crypto_authenc_extractkeys(&authenc_keys, key, keylen); if (status) goto badkey; - return 0; + status = aead_hmac_init(cipher, &authenc_keys); + badkey: return status; } @@ -897,36 +851,7 @@ static int otx_cpt_aead_ecb_null_sha_setkey(struct crypto_aead *cipher, const unsigned char *key, unsigned int keylen) { - struct otx_cpt_aead_ctx *ctx = crypto_aead_ctx_dma(cipher); - struct crypto_authenc_key_param *param; - struct rtattr *rta = (void *)key; - int enckeylen = 0; - - if (!RTA_OK(rta, keylen)) - goto badkey; - - if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM) - goto badkey; - - if (RTA_PAYLOAD(rta) < sizeof(*param)) - goto badkey; - - param = RTA_DATA(rta); - enckeylen = be32_to_cpu(param->enckeylen); - key += RTA_ALIGN(rta->rta_len); - keylen -= RTA_ALIGN(rta->rta_len); - if (enckeylen != 0) - goto badkey; - - if (keylen > OTX_CPT_MAX_KEY_SIZE) - goto badkey; - - memcpy(ctx->key, key, keylen); - ctx->enc_key_len = enckeylen; - ctx->auth_key_len = keylen; - return 0; -badkey: - return -EINVAL; + return otx_cpt_aead_cbc_aes_sha_setkey(cipher, key, keylen); } static int otx_cpt_aead_gcm_aes_setkey(struct crypto_aead *cipher, diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptlf.c b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c index 6edd27ff8c4e3c..e4bd3f030ceca7 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptlf.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c @@ -419,8 +419,8 @@ int otx2_cptlf_init(struct otx2_cptlfs_info *lfs, u8 eng_grp_mask, int pri, return 0; free_iq: - otx2_cpt_free_instruction_queues(lfs); cptlf_hw_cleanup(lfs); + otx2_cpt_free_instruction_queues(lfs); detach_rsrcs: otx2_cpt_detach_rsrcs_msg(lfs); clear_lfs_num: @@ -431,11 +431,13 @@ EXPORT_SYMBOL_NS_GPL(otx2_cptlf_init, CRYPTO_DEV_OCTEONTX2_CPT); void otx2_cptlf_shutdown(struct otx2_cptlfs_info *lfs) { - lfs->lfs_num = 0; /* Cleanup LFs hardware side */ cptlf_hw_cleanup(lfs); + /* Free instruction queues */ + otx2_cpt_free_instruction_queues(lfs); /* Send request to detach LFs */ otx2_cpt_detach_rsrcs_msg(lfs); + lfs->lfs_num = 0; } EXPORT_SYMBOL_NS_GPL(otx2_cptlf_shutdown, CRYPTO_DEV_OCTEONTX2_CPT); diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c index e27ddd3c4e5581..4385d3df52b4d4 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include "otx2_cptvf.h" @@ -54,6 +53,8 @@ static struct cpt_device_table se_devices = { .count = ATOMIC_INIT(0) }; +static struct otx2_cpt_sdesc *alloc_sdesc(struct crypto_shash *alg); + static inline int get_se_device(struct pci_dev **pdev, int *cpu_num) { int count; @@ -580,40 +581,56 @@ static int cpt_aead_init(struct crypto_aead *atfm, u8 cipher_type, u8 mac_type) ctx->cipher_type = cipher_type; ctx->mac_type = mac_type; + switch (ctx->mac_type) { + case OTX2_CPT_SHA1: + ctx->hashalg = crypto_alloc_shash("sha1", 0, 0); + break; + + case OTX2_CPT_SHA256: + ctx->hashalg = crypto_alloc_shash("sha256", 0, 0); + break; + + case OTX2_CPT_SHA384: + ctx->hashalg = crypto_alloc_shash("sha384", 0, 0); + break; + + case OTX2_CPT_SHA512: + ctx->hashalg = crypto_alloc_shash("sha512", 0, 0); + break; + } + + if (IS_ERR(ctx->hashalg)) + return PTR_ERR(ctx->hashalg); + + if (ctx->hashalg) { + ctx->sdesc = alloc_sdesc(ctx->hashalg); + if (!ctx->sdesc) { + crypto_free_shash(ctx->hashalg); + return -ENOMEM; + } + } + /* * When selected cipher is NULL we use HMAC opcode instead of * FLEXICRYPTO opcode therefore we don't need to use HASH algorithms * for calculating ipad and opad */ - if (ctx->cipher_type != OTX2_CPT_CIPHER_NULL) { - switch (ctx->mac_type) { - case OTX2_CPT_SHA1: - ctx->hashalg = crypto_alloc_shash("sha1", 0, - CRYPTO_ALG_ASYNC); - if (IS_ERR(ctx->hashalg)) - return PTR_ERR(ctx->hashalg); - break; - - case OTX2_CPT_SHA256: - ctx->hashalg = crypto_alloc_shash("sha256", 0, - CRYPTO_ALG_ASYNC); - if (IS_ERR(ctx->hashalg)) - return PTR_ERR(ctx->hashalg); - break; + if (ctx->cipher_type != OTX2_CPT_CIPHER_NULL && ctx->hashalg) { + int ss = crypto_shash_statesize(ctx->hashalg); - case OTX2_CPT_SHA384: - ctx->hashalg = crypto_alloc_shash("sha384", 0, - CRYPTO_ALG_ASYNC); - if (IS_ERR(ctx->hashalg)) - return PTR_ERR(ctx->hashalg); - break; + ctx->ipad = kzalloc(ss, GFP_KERNEL); + if (!ctx->ipad) { + kfree(ctx->sdesc); + crypto_free_shash(ctx->hashalg); + return -ENOMEM; + } - case OTX2_CPT_SHA512: - ctx->hashalg = crypto_alloc_shash("sha512", 0, - CRYPTO_ALG_ASYNC); - if (IS_ERR(ctx->hashalg)) - return PTR_ERR(ctx->hashalg); - break; + ctx->opad = kzalloc(ss, GFP_KERNEL); + if (!ctx->opad) { + kfree(ctx->ipad); + kfree(ctx->sdesc); + crypto_free_shash(ctx->hashalg); + return -ENOMEM; } } switch (ctx->cipher_type) { @@ -686,8 +703,7 @@ static void otx2_cpt_aead_exit(struct crypto_aead *tfm) kfree(ctx->ipad); kfree(ctx->opad); - if (ctx->hashalg) - crypto_free_shash(ctx->hashalg); + crypto_free_shash(ctx->hashalg); kfree(ctx->sdesc); if (ctx->fbk_cipher) { @@ -760,7 +776,7 @@ static inline void swap_data64(void *buf, u32 len) cpu_to_be64s(src); } -static int copy_pad(u8 mac_type, u8 *out_pad, u8 *in_pad) +static int swap_pad(u8 mac_type, u8 *pad) { struct sha512_state *sha512; struct sha256_state *sha256; @@ -768,22 +784,19 @@ static int copy_pad(u8 mac_type, u8 *out_pad, u8 *in_pad) switch (mac_type) { case OTX2_CPT_SHA1: - sha1 = (struct sha1_state *) in_pad; + sha1 = (struct sha1_state *)pad; swap_data32(sha1->state, SHA1_DIGEST_SIZE); - memcpy(out_pad, &sha1->state, SHA1_DIGEST_SIZE); break; case OTX2_CPT_SHA256: - sha256 = (struct sha256_state *) in_pad; + sha256 = (struct sha256_state *)pad; swap_data32(sha256->state, SHA256_DIGEST_SIZE); - memcpy(out_pad, &sha256->state, SHA256_DIGEST_SIZE); break; case OTX2_CPT_SHA384: case OTX2_CPT_SHA512: - sha512 = (struct sha512_state *) in_pad; + sha512 = (struct sha512_state *)pad; swap_data64(sha512->state, SHA512_DIGEST_SIZE); - memcpy(out_pad, &sha512->state, SHA512_DIGEST_SIZE); break; default: @@ -793,55 +806,54 @@ static int copy_pad(u8 mac_type, u8 *out_pad, u8 *in_pad) return 0; } -static int aead_hmac_init(struct crypto_aead *cipher) +static int aead_hmac_init(struct crypto_aead *cipher, + struct crypto_authenc_keys *keys) { struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx_dma(cipher); - int state_size = crypto_shash_statesize(ctx->hashalg); int ds = crypto_shash_digestsize(ctx->hashalg); int bs = crypto_shash_blocksize(ctx->hashalg); - int authkeylen = ctx->auth_key_len; + int authkeylen = keys->authkeylen; u8 *ipad = NULL, *opad = NULL; - int ret = 0, icount = 0; + int icount = 0; + int ret; - ctx->sdesc = alloc_sdesc(ctx->hashalg); - if (!ctx->sdesc) - return -ENOMEM; + if (authkeylen > bs) { + ret = crypto_shash_digest(&ctx->sdesc->shash, keys->authkey, + authkeylen, ctx->key); + if (ret) + goto calc_fail; - ctx->ipad = kzalloc(bs, GFP_KERNEL); - if (!ctx->ipad) { - ret = -ENOMEM; - goto calc_fail; - } + authkeylen = ds; + } else + memcpy(ctx->key, keys->authkey, authkeylen); - ctx->opad = kzalloc(bs, GFP_KERNEL); - if (!ctx->opad) { - ret = -ENOMEM; - goto calc_fail; - } + ctx->enc_key_len = keys->enckeylen; + ctx->auth_key_len = authkeylen; - ipad = kzalloc(state_size, GFP_KERNEL); - if (!ipad) { - ret = -ENOMEM; - goto calc_fail; - } + if (ctx->cipher_type == OTX2_CPT_CIPHER_NULL) + return keys->enckeylen ? -EINVAL : 0; - opad = kzalloc(state_size, GFP_KERNEL); - if (!opad) { - ret = -ENOMEM; - goto calc_fail; + switch (keys->enckeylen) { + case AES_KEYSIZE_128: + ctx->key_type = OTX2_CPT_AES_128_BIT; + break; + case AES_KEYSIZE_192: + ctx->key_type = OTX2_CPT_AES_192_BIT; + break; + case AES_KEYSIZE_256: + ctx->key_type = OTX2_CPT_AES_256_BIT; + break; + default: + /* Invalid key length */ + return -EINVAL; } - if (authkeylen > bs) { - ret = crypto_shash_digest(&ctx->sdesc->shash, ctx->key, - authkeylen, ipad); - if (ret) - goto calc_fail; + memcpy(ctx->key + authkeylen, keys->enckey, keys->enckeylen); - authkeylen = ds; - } else { - memcpy(ipad, ctx->key, authkeylen); - } + ipad = ctx->ipad; + opad = ctx->opad; + memcpy(ipad, ctx->key, authkeylen); memset(ipad + authkeylen, 0, bs - authkeylen); memcpy(opad, ipad, bs); @@ -859,7 +871,7 @@ static int aead_hmac_init(struct crypto_aead *cipher) crypto_shash_init(&ctx->sdesc->shash); crypto_shash_update(&ctx->sdesc->shash, ipad, bs); crypto_shash_export(&ctx->sdesc->shash, ipad); - ret = copy_pad(ctx->mac_type, ctx->ipad, ipad); + ret = swap_pad(ctx->mac_type, ipad); if (ret) goto calc_fail; @@ -867,25 +879,9 @@ static int aead_hmac_init(struct crypto_aead *cipher) crypto_shash_init(&ctx->sdesc->shash); crypto_shash_update(&ctx->sdesc->shash, opad, bs); crypto_shash_export(&ctx->sdesc->shash, opad); - ret = copy_pad(ctx->mac_type, ctx->opad, opad); - if (ret) - goto calc_fail; - - kfree(ipad); - kfree(opad); - - return 0; + ret = swap_pad(ctx->mac_type, opad); calc_fail: - kfree(ctx->ipad); - ctx->ipad = NULL; - kfree(ctx->opad); - ctx->opad = NULL; - kfree(ipad); - kfree(opad); - kfree(ctx->sdesc); - ctx->sdesc = NULL; - return ret; } @@ -893,87 +889,17 @@ static int otx2_cpt_aead_cbc_aes_sha_setkey(struct crypto_aead *cipher, const unsigned char *key, unsigned int keylen) { - struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx_dma(cipher); - struct crypto_authenc_key_param *param; - int enckeylen = 0, authkeylen = 0; - struct rtattr *rta = (void *)key; - - if (!RTA_OK(rta, keylen)) - return -EINVAL; + struct crypto_authenc_keys authenc_keys; - if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM) - return -EINVAL; - - if (RTA_PAYLOAD(rta) < sizeof(*param)) - return -EINVAL; - - param = RTA_DATA(rta); - enckeylen = be32_to_cpu(param->enckeylen); - key += RTA_ALIGN(rta->rta_len); - keylen -= RTA_ALIGN(rta->rta_len); - if (keylen < enckeylen) - return -EINVAL; - - if (keylen > OTX2_CPT_MAX_KEY_SIZE) - return -EINVAL; - - authkeylen = keylen - enckeylen; - memcpy(ctx->key, key, keylen); - - switch (enckeylen) { - case AES_KEYSIZE_128: - ctx->key_type = OTX2_CPT_AES_128_BIT; - break; - case AES_KEYSIZE_192: - ctx->key_type = OTX2_CPT_AES_192_BIT; - break; - case AES_KEYSIZE_256: - ctx->key_type = OTX2_CPT_AES_256_BIT; - break; - default: - /* Invalid key length */ - return -EINVAL; - } - - ctx->enc_key_len = enckeylen; - ctx->auth_key_len = authkeylen; - - return aead_hmac_init(cipher); + return crypto_authenc_extractkeys(&authenc_keys, key, keylen) ?: + aead_hmac_init(cipher, &authenc_keys); } static int otx2_cpt_aead_ecb_null_sha_setkey(struct crypto_aead *cipher, const unsigned char *key, unsigned int keylen) { - struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx_dma(cipher); - struct crypto_authenc_key_param *param; - struct rtattr *rta = (void *)key; - int enckeylen = 0; - - if (!RTA_OK(rta, keylen)) - return -EINVAL; - - if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM) - return -EINVAL; - - if (RTA_PAYLOAD(rta) < sizeof(*param)) - return -EINVAL; - - param = RTA_DATA(rta); - enckeylen = be32_to_cpu(param->enckeylen); - key += RTA_ALIGN(rta->rta_len); - keylen -= RTA_ALIGN(rta->rta_len); - if (enckeylen != 0) - return -EINVAL; - - if (keylen > OTX2_CPT_MAX_KEY_SIZE) - return -EINVAL; - - memcpy(ctx->key, key, keylen); - ctx->enc_key_len = enckeylen; - ctx->auth_key_len = keylen; - - return 0; + return otx2_cpt_aead_cbc_aes_sha_setkey(cipher, key, keylen); } static int otx2_cpt_aead_gcm_aes_setkey(struct crypto_aead *cipher, diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c index bac729c885f960..215a1b17b6ce0a 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c @@ -249,8 +249,11 @@ static void cptvf_lf_shutdown(struct otx2_cptlfs_info *lfs) otx2_cptlf_unregister_interrupts(lfs); /* Cleanup LFs software side */ lf_sw_cleanup(lfs); + /* Free instruction queues */ + otx2_cpt_free_instruction_queues(lfs); /* Send request to detach LFs */ otx2_cpt_detach_rsrcs_msg(lfs); + lfs->lfs_num = 0; } static int cptvf_lf_init(struct otx2_cptvf_dev *cptvf) diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c index 8c143180645e5b..29c9537216fa6d 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c +++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c @@ -332,12 +332,12 @@ static int rk_hash_run(struct crypto_engine *engine, void *breq) theend: pm_runtime_put_autosuspend(rkc->dev); + rk_hash_unprepare(engine, breq); + local_bh_disable(); crypto_finalize_hash_request(engine, breq, err); local_bh_enable(); - rk_hash_unprepare(engine, breq); - return 0; } diff --git a/drivers/crypto/sa2ul.c b/drivers/crypto/sa2ul.c index 6238d34f8db2f6..94eb6f6afa2572 100644 --- a/drivers/crypto/sa2ul.c +++ b/drivers/crypto/sa2ul.c @@ -1869,9 +1869,8 @@ static int sa_aead_setkey(struct crypto_aead *authenc, crypto_aead_set_flags(ctx->fallback.aead, crypto_aead_get_flags(authenc) & CRYPTO_TFM_REQ_MASK); - crypto_aead_setkey(ctx->fallback.aead, key, keylen); - return 0; + return crypto_aead_setkey(ctx->fallback.aead, key, keylen); } static int sa_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize) diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c index 62d93526920f80..8e84dd98a273da 100644 --- a/drivers/crypto/sahara.c +++ b/drivers/crypto/sahara.c @@ -43,7 +43,6 @@ #define FLAGS_MODE_MASK 0x000f #define FLAGS_ENCRYPT BIT(0) #define FLAGS_CBC BIT(1) -#define FLAGS_NEW_KEY BIT(3) #define SAHARA_HDR_BASE 0x00800000 #define SAHARA_HDR_SKHA_ALG_AES 0 @@ -141,8 +140,6 @@ struct sahara_hw_link { }; struct sahara_ctx { - unsigned long flags; - /* AES-specific context */ int keylen; u8 key[AES_KEYSIZE_128]; @@ -151,6 +148,7 @@ struct sahara_ctx { struct sahara_aes_reqctx { unsigned long mode; + u8 iv_out[AES_BLOCK_SIZE]; struct skcipher_request fallback_req; // keep at the end }; @@ -446,27 +444,24 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev) int ret; int i, j; int idx = 0; + u32 len; - /* Copy new key if necessary */ - if (ctx->flags & FLAGS_NEW_KEY) { - memcpy(dev->key_base, ctx->key, ctx->keylen); - ctx->flags &= ~FLAGS_NEW_KEY; + memcpy(dev->key_base, ctx->key, ctx->keylen); - if (dev->flags & FLAGS_CBC) { - dev->hw_desc[idx]->len1 = AES_BLOCK_SIZE; - dev->hw_desc[idx]->p1 = dev->iv_phys_base; - } else { - dev->hw_desc[idx]->len1 = 0; - dev->hw_desc[idx]->p1 = 0; - } - dev->hw_desc[idx]->len2 = ctx->keylen; - dev->hw_desc[idx]->p2 = dev->key_phys_base; - dev->hw_desc[idx]->next = dev->hw_phys_desc[1]; + if (dev->flags & FLAGS_CBC) { + dev->hw_desc[idx]->len1 = AES_BLOCK_SIZE; + dev->hw_desc[idx]->p1 = dev->iv_phys_base; + } else { + dev->hw_desc[idx]->len1 = 0; + dev->hw_desc[idx]->p1 = 0; + } + dev->hw_desc[idx]->len2 = ctx->keylen; + dev->hw_desc[idx]->p2 = dev->key_phys_base; + dev->hw_desc[idx]->next = dev->hw_phys_desc[1]; + dev->hw_desc[idx]->hdr = sahara_aes_key_hdr(dev); - dev->hw_desc[idx]->hdr = sahara_aes_key_hdr(dev); + idx++; - idx++; - } dev->nb_in_sg = sg_nents_for_len(dev->in_sg, dev->total); if (dev->nb_in_sg < 0) { @@ -488,24 +483,27 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev) DMA_TO_DEVICE); if (!ret) { dev_err(dev->device, "couldn't map in sg\n"); - goto unmap_in; + return -EINVAL; } + ret = dma_map_sg(dev->device, dev->out_sg, dev->nb_out_sg, DMA_FROM_DEVICE); if (!ret) { dev_err(dev->device, "couldn't map out sg\n"); - goto unmap_out; + goto unmap_in; } /* Create input links */ dev->hw_desc[idx]->p1 = dev->hw_phys_link[0]; sg = dev->in_sg; + len = dev->total; for (i = 0; i < dev->nb_in_sg; i++) { - dev->hw_link[i]->len = sg->length; + dev->hw_link[i]->len = min(len, sg->length); dev->hw_link[i]->p = sg->dma_address; if (i == (dev->nb_in_sg - 1)) { dev->hw_link[i]->next = 0; } else { + len -= min(len, sg->length); dev->hw_link[i]->next = dev->hw_phys_link[i + 1]; sg = sg_next(sg); } @@ -514,12 +512,14 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev) /* Create output links */ dev->hw_desc[idx]->p2 = dev->hw_phys_link[i]; sg = dev->out_sg; + len = dev->total; for (j = i; j < dev->nb_out_sg + i; j++) { - dev->hw_link[j]->len = sg->length; + dev->hw_link[j]->len = min(len, sg->length); dev->hw_link[j]->p = sg->dma_address; if (j == (dev->nb_out_sg + i - 1)) { dev->hw_link[j]->next = 0; } else { + len -= min(len, sg->length); dev->hw_link[j]->next = dev->hw_phys_link[j + 1]; sg = sg_next(sg); } @@ -538,9 +538,6 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev) return 0; -unmap_out: - dma_unmap_sg(dev->device, dev->out_sg, dev->nb_out_sg, - DMA_FROM_DEVICE); unmap_in: dma_unmap_sg(dev->device, dev->in_sg, dev->nb_in_sg, DMA_TO_DEVICE); @@ -548,8 +545,24 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev) return -EINVAL; } +static void sahara_aes_cbc_update_iv(struct skcipher_request *req) +{ + struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); + struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); + unsigned int ivsize = crypto_skcipher_ivsize(skcipher); + + /* Update IV buffer to contain the last ciphertext block */ + if (rctx->mode & FLAGS_ENCRYPT) { + sg_pcopy_to_buffer(req->dst, sg_nents(req->dst), req->iv, + ivsize, req->cryptlen - ivsize); + } else { + memcpy(req->iv, rctx->iv_out, ivsize); + } +} + static int sahara_aes_process(struct skcipher_request *req) { + struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); struct sahara_dev *dev = dev_ptr; struct sahara_ctx *ctx; struct sahara_aes_reqctx *rctx; @@ -571,8 +584,17 @@ static int sahara_aes_process(struct skcipher_request *req) rctx->mode &= FLAGS_MODE_MASK; dev->flags = (dev->flags & ~FLAGS_MODE_MASK) | rctx->mode; - if ((dev->flags & FLAGS_CBC) && req->iv) - memcpy(dev->iv_base, req->iv, AES_KEYSIZE_128); + if ((dev->flags & FLAGS_CBC) && req->iv) { + unsigned int ivsize = crypto_skcipher_ivsize(skcipher); + + memcpy(dev->iv_base, req->iv, ivsize); + + if (!(dev->flags & FLAGS_ENCRYPT)) { + sg_pcopy_to_buffer(req->src, sg_nents(req->src), + rctx->iv_out, ivsize, + req->cryptlen - ivsize); + } + } /* assign new context to device */ dev->ctx = ctx; @@ -585,16 +607,20 @@ static int sahara_aes_process(struct skcipher_request *req) timeout = wait_for_completion_timeout(&dev->dma_completion, msecs_to_jiffies(SAHARA_TIMEOUT_MS)); - if (!timeout) { - dev_err(dev->device, "AES timeout\n"); - return -ETIMEDOUT; - } dma_unmap_sg(dev->device, dev->out_sg, dev->nb_out_sg, DMA_FROM_DEVICE); dma_unmap_sg(dev->device, dev->in_sg, dev->nb_in_sg, DMA_TO_DEVICE); + if (!timeout) { + dev_err(dev->device, "AES timeout\n"); + return -ETIMEDOUT; + } + + if ((dev->flags & FLAGS_CBC) && req->iv) + sahara_aes_cbc_update_iv(req); + return 0; } @@ -608,7 +634,6 @@ static int sahara_aes_setkey(struct crypto_skcipher *tfm, const u8 *key, /* SAHARA only supports 128bit keys */ if (keylen == AES_KEYSIZE_128) { memcpy(ctx->key, key, keylen); - ctx->flags |= FLAGS_NEW_KEY; return 0; } @@ -624,12 +649,40 @@ static int sahara_aes_setkey(struct crypto_skcipher *tfm, const u8 *key, return crypto_skcipher_setkey(ctx->fallback, key, keylen); } +static int sahara_aes_fallback(struct skcipher_request *req, unsigned long mode) +{ + struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); + struct sahara_ctx *ctx = crypto_skcipher_ctx( + crypto_skcipher_reqtfm(req)); + + skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback); + skcipher_request_set_callback(&rctx->fallback_req, + req->base.flags, + req->base.complete, + req->base.data); + skcipher_request_set_crypt(&rctx->fallback_req, req->src, + req->dst, req->cryptlen, req->iv); + + if (mode & FLAGS_ENCRYPT) + return crypto_skcipher_encrypt(&rctx->fallback_req); + + return crypto_skcipher_decrypt(&rctx->fallback_req); +} + static int sahara_aes_crypt(struct skcipher_request *req, unsigned long mode) { struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); + struct sahara_ctx *ctx = crypto_skcipher_ctx( + crypto_skcipher_reqtfm(req)); struct sahara_dev *dev = dev_ptr; int err = 0; + if (!req->cryptlen) + return 0; + + if (unlikely(ctx->keylen != AES_KEYSIZE_128)) + return sahara_aes_fallback(req, mode); + dev_dbg(dev->device, "nbytes: %d, enc: %d, cbc: %d\n", req->cryptlen, !!(mode & FLAGS_ENCRYPT), !!(mode & FLAGS_CBC)); @@ -652,81 +705,21 @@ static int sahara_aes_crypt(struct skcipher_request *req, unsigned long mode) static int sahara_aes_ecb_encrypt(struct skcipher_request *req) { - struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); - struct sahara_ctx *ctx = crypto_skcipher_ctx( - crypto_skcipher_reqtfm(req)); - - if (unlikely(ctx->keylen != AES_KEYSIZE_128)) { - skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback); - skcipher_request_set_callback(&rctx->fallback_req, - req->base.flags, - req->base.complete, - req->base.data); - skcipher_request_set_crypt(&rctx->fallback_req, req->src, - req->dst, req->cryptlen, req->iv); - return crypto_skcipher_encrypt(&rctx->fallback_req); - } - return sahara_aes_crypt(req, FLAGS_ENCRYPT); } static int sahara_aes_ecb_decrypt(struct skcipher_request *req) { - struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); - struct sahara_ctx *ctx = crypto_skcipher_ctx( - crypto_skcipher_reqtfm(req)); - - if (unlikely(ctx->keylen != AES_KEYSIZE_128)) { - skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback); - skcipher_request_set_callback(&rctx->fallback_req, - req->base.flags, - req->base.complete, - req->base.data); - skcipher_request_set_crypt(&rctx->fallback_req, req->src, - req->dst, req->cryptlen, req->iv); - return crypto_skcipher_decrypt(&rctx->fallback_req); - } - return sahara_aes_crypt(req, 0); } static int sahara_aes_cbc_encrypt(struct skcipher_request *req) { - struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); - struct sahara_ctx *ctx = crypto_skcipher_ctx( - crypto_skcipher_reqtfm(req)); - - if (unlikely(ctx->keylen != AES_KEYSIZE_128)) { - skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback); - skcipher_request_set_callback(&rctx->fallback_req, - req->base.flags, - req->base.complete, - req->base.data); - skcipher_request_set_crypt(&rctx->fallback_req, req->src, - req->dst, req->cryptlen, req->iv); - return crypto_skcipher_encrypt(&rctx->fallback_req); - } - return sahara_aes_crypt(req, FLAGS_ENCRYPT | FLAGS_CBC); } static int sahara_aes_cbc_decrypt(struct skcipher_request *req) { - struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); - struct sahara_ctx *ctx = crypto_skcipher_ctx( - crypto_skcipher_reqtfm(req)); - - if (unlikely(ctx->keylen != AES_KEYSIZE_128)) { - skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback); - skcipher_request_set_callback(&rctx->fallback_req, - req->base.flags, - req->base.complete, - req->base.data); - skcipher_request_set_crypt(&rctx->fallback_req, req->src, - req->dst, req->cryptlen, req->iv); - return crypto_skcipher_decrypt(&rctx->fallback_req); - } - return sahara_aes_crypt(req, FLAGS_CBC); } @@ -783,6 +776,7 @@ static int sahara_sha_hw_links_create(struct sahara_dev *dev, int start) { struct scatterlist *sg; + unsigned int len; unsigned int i; int ret; @@ -804,12 +798,14 @@ static int sahara_sha_hw_links_create(struct sahara_dev *dev, if (!ret) return -EFAULT; + len = rctx->total; for (i = start; i < dev->nb_in_sg + start; i++) { - dev->hw_link[i]->len = sg->length; + dev->hw_link[i]->len = min(len, sg->length); dev->hw_link[i]->p = sg->dma_address; if (i == (dev->nb_in_sg + start - 1)) { dev->hw_link[i]->next = 0; } else { + len -= min(len, sg->length); dev->hw_link[i]->next = dev->hw_phys_link[i + 1]; sg = sg_next(sg); } @@ -890,24 +886,6 @@ static int sahara_sha_hw_context_descriptor_create(struct sahara_dev *dev, return 0; } -static int sahara_walk_and_recalc(struct scatterlist *sg, unsigned int nbytes) -{ - if (!sg || !sg->length) - return nbytes; - - while (nbytes && sg) { - if (nbytes <= sg->length) { - sg->length = nbytes; - sg_mark_end(sg); - break; - } - nbytes -= sg->length; - sg = sg_next(sg); - } - - return nbytes; -} - static int sahara_sha_prepare_request(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); @@ -944,36 +922,20 @@ static int sahara_sha_prepare_request(struct ahash_request *req) hash_later, 0); } - /* nbytes should now be multiple of blocksize */ - req->nbytes = req->nbytes - hash_later; - - sahara_walk_and_recalc(req->src, req->nbytes); - + rctx->total = len - hash_later; /* have data from previous operation and current */ if (rctx->buf_cnt && req->nbytes) { sg_init_table(rctx->in_sg_chain, 2); sg_set_buf(rctx->in_sg_chain, rctx->rembuf, rctx->buf_cnt); - sg_chain(rctx->in_sg_chain, 2, req->src); - - rctx->total = req->nbytes + rctx->buf_cnt; rctx->in_sg = rctx->in_sg_chain; - - req->src = rctx->in_sg_chain; /* only data from previous operation */ } else if (rctx->buf_cnt) { - if (req->src) - rctx->in_sg = req->src; - else - rctx->in_sg = rctx->in_sg_chain; - /* buf was copied into rembuf above */ + rctx->in_sg = rctx->in_sg_chain; sg_init_one(rctx->in_sg, rctx->rembuf, rctx->buf_cnt); - rctx->total = rctx->buf_cnt; /* no data from previous operation */ } else { rctx->in_sg = req->src; - rctx->total = req->nbytes; - req->src = rctx->in_sg; } /* on next call, we only have the remaining data in the buffer */ @@ -994,7 +956,10 @@ static int sahara_sha_process(struct ahash_request *req) return ret; if (rctx->first) { - sahara_sha_hw_data_descriptor_create(dev, rctx, req, 0); + ret = sahara_sha_hw_data_descriptor_create(dev, rctx, req, 0); + if (ret) + return ret; + dev->hw_desc[0]->next = 0; rctx->first = 0; } else { @@ -1002,7 +967,10 @@ static int sahara_sha_process(struct ahash_request *req) sahara_sha_hw_context_descriptor_create(dev, rctx, req, 0); dev->hw_desc[0]->next = dev->hw_phys_desc[1]; - sahara_sha_hw_data_descriptor_create(dev, rctx, req, 1); + ret = sahara_sha_hw_data_descriptor_create(dev, rctx, req, 1); + if (ret) + return ret; + dev->hw_desc[1]->next = 0; } @@ -1015,18 +983,19 @@ static int sahara_sha_process(struct ahash_request *req) timeout = wait_for_completion_timeout(&dev->dma_completion, msecs_to_jiffies(SAHARA_TIMEOUT_MS)); - if (!timeout) { - dev_err(dev->device, "SHA timeout\n"); - return -ETIMEDOUT; - } if (rctx->sg_in_idx) dma_unmap_sg(dev->device, dev->in_sg, dev->nb_in_sg, DMA_TO_DEVICE); + if (!timeout) { + dev_err(dev->device, "SHA timeout\n"); + return -ETIMEDOUT; + } + memcpy(rctx->context, dev->context_base, rctx->context_size); - if (req->result) + if (req->result && rctx->last) memcpy(req->result, rctx->context, rctx->digest_size); return 0; @@ -1170,8 +1139,7 @@ static int sahara_sha_import(struct ahash_request *req, const void *in) static int sahara_sha_cra_init(struct crypto_tfm *tfm) { crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm), - sizeof(struct sahara_sha_reqctx) + - SHA_BUFFER_LEN + SHA256_BLOCK_SIZE); + sizeof(struct sahara_sha_reqctx)); return 0; } diff --git a/drivers/crypto/starfive/jh7110-cryp.c b/drivers/crypto/starfive/jh7110-cryp.c index 08e974e0dd1247..4f5b6818208dc2 100644 --- a/drivers/crypto/starfive/jh7110-cryp.c +++ b/drivers/crypto/starfive/jh7110-cryp.c @@ -168,7 +168,7 @@ static int starfive_cryp_probe(struct platform_device *pdev) ret = devm_request_irq(&pdev->dev, irq, starfive_cryp_irq, 0, pdev->name, (void *)cryp); if (ret) - return dev_err_probe(&pdev->dev, irq, + return dev_err_probe(&pdev->dev, ret, "Failed to register interrupt handler\n"); clk_prepare_enable(cryp->hclk); @@ -180,12 +180,8 @@ static int starfive_cryp_probe(struct platform_device *pdev) spin_unlock(&dev_list.lock); ret = starfive_dma_init(cryp); - if (ret) { - if (ret == -EPROBE_DEFER) - goto err_probe_defer; - else - goto err_dma_init; - } + if (ret) + goto err_dma_init; /* Initialize crypto engine */ cryp->engine = crypto_engine_alloc_init(&pdev->dev, 1); @@ -233,7 +229,7 @@ static int starfive_cryp_probe(struct platform_device *pdev) tasklet_kill(&cryp->aes_done); tasklet_kill(&cryp->hash_done); -err_probe_defer: + return ret; } diff --git a/drivers/crypto/starfive/jh7110-cryp.h b/drivers/crypto/starfive/jh7110-cryp.h index fe011d50473d76..607f70292b215d 100644 --- a/drivers/crypto/starfive/jh7110-cryp.h +++ b/drivers/crypto/starfive/jh7110-cryp.h @@ -30,6 +30,7 @@ #define MAX_KEY_SIZE SHA512_BLOCK_SIZE #define STARFIVE_AES_IV_LEN AES_BLOCK_SIZE #define STARFIVE_AES_CTR_LEN AES_BLOCK_SIZE +#define STARFIVE_RSA_MAX_KEYSZ 256 union starfive_aes_csr { u32 v; @@ -212,12 +213,11 @@ struct starfive_cryp_request_ctx { struct scatterlist *out_sg; struct ahash_request ahash_fbk_req; size_t total; - size_t nents; unsigned int blksize; unsigned int digsize; unsigned long in_sg_len; unsigned char *adata; - u8 rsa_data[] __aligned(sizeof(u32)); + u8 rsa_data[STARFIVE_RSA_MAX_KEYSZ] __aligned(sizeof(u32)); }; struct starfive_cryp_dev *starfive_cryp_find_dev(struct starfive_cryp_ctx *ctx); diff --git a/drivers/crypto/starfive/jh7110-rsa.c b/drivers/crypto/starfive/jh7110-rsa.c index f31bbd825f883f..1db9a3d02848b5 100644 --- a/drivers/crypto/starfive/jh7110-rsa.c +++ b/drivers/crypto/starfive/jh7110-rsa.c @@ -37,7 +37,6 @@ // A * A * R mod N ==> A #define CRYPTO_CMD_AARN 0x7 -#define STARFIVE_RSA_MAX_KEYSZ 256 #define STARFIVE_RSA_RESET 0x2 static inline int starfive_pka_wait_done(struct starfive_cryp_ctx *ctx) @@ -91,7 +90,7 @@ static int starfive_rsa_montgomery_form(struct starfive_cryp_ctx *ctx, { struct starfive_cryp_dev *cryp = ctx->cryp; struct starfive_cryp_request_ctx *rctx = ctx->rctx; - int count = rctx->total / sizeof(u32) - 1; + int count = (ALIGN(rctx->total, 4) / 4) - 1; int loop; u32 temp; u8 opsize; @@ -274,12 +273,17 @@ static int starfive_rsa_enc_core(struct starfive_cryp_ctx *ctx, int enc) struct starfive_cryp_dev *cryp = ctx->cryp; struct starfive_cryp_request_ctx *rctx = ctx->rctx; struct starfive_rsa_key *key = &ctx->rsa_key; - int ret = 0; + int ret = 0, shift = 0; writel(STARFIVE_RSA_RESET, cryp->base + STARFIVE_PKA_CACR_OFFSET); - rctx->total = sg_copy_to_buffer(rctx->in_sg, rctx->nents, - rctx->rsa_data, rctx->total); + if (!IS_ALIGNED(rctx->total, sizeof(u32))) { + shift = sizeof(u32) - (rctx->total & 0x3); + memset(rctx->rsa_data, 0, shift); + } + + rctx->total = sg_copy_to_buffer(rctx->in_sg, sg_nents(rctx->in_sg), + rctx->rsa_data + shift, rctx->total); if (enc) { key->bitlen = key->e_bitlen; @@ -329,7 +333,6 @@ static int starfive_rsa_enc(struct akcipher_request *req) rctx->in_sg = req->src; rctx->out_sg = req->dst; rctx->total = req->src_len; - rctx->nents = sg_nents(rctx->in_sg); ctx->rctx = rctx; return starfive_rsa_enc_core(ctx, 1); diff --git a/drivers/crypto/stm32/stm32-crc32.c b/drivers/crypto/stm32/stm32-crc32.c index 90a920e7f6642f..c439be1650c84d 100644 --- a/drivers/crypto/stm32/stm32-crc32.c +++ b/drivers/crypto/stm32/stm32-crc32.c @@ -104,7 +104,7 @@ static struct stm32_crc *stm32_crc_get_next_crc(void) struct stm32_crc *crc; spin_lock_bh(&crc_list.lock); - crc = list_first_entry(&crc_list.dev_list, struct stm32_crc, list); + crc = list_first_entry_or_null(&crc_list.dev_list, struct stm32_crc, list); if (crc) list_move_tail(&crc->list, &crc_list.dev_list); spin_unlock_bh(&crc_list.lock); diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c index f095f0065428a9..2f1b82cf10b1c4 100644 --- a/drivers/crypto/stm32/stm32-cryp.c +++ b/drivers/crypto/stm32/stm32-cryp.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -1665,8 +1666,11 @@ static irqreturn_t stm32_cryp_irq_thread(int irq, void *arg) it_mask &= ~IMSCR_OUT; stm32_cryp_write(cryp, cryp->caps->imsc, it_mask); - if (!cryp->payload_in && !cryp->header_in && !cryp->payload_out) + if (!cryp->payload_in && !cryp->header_in && !cryp->payload_out) { + local_bh_disable(); stm32_cryp_finish_req(cryp, 0); + local_bh_enable(); + } return IRQ_HANDLED; } diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c index 2621ff8a93764d..de53eddf6796b6 100644 --- a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c @@ -104,7 +104,8 @@ static void virtio_crypto_dataq_akcipher_callback(struct virtio_crypto_request * } static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher_ctx *ctx, - struct virtio_crypto_ctrl_header *header, void *para, + struct virtio_crypto_ctrl_header *header, + struct virtio_crypto_akcipher_session_para *para, const uint8_t *key, unsigned int keylen) { struct scatterlist outhdr_sg, key_sg, inhdr_sg, *sgs[3]; @@ -128,7 +129,7 @@ static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher ctrl = &vc_ctrl_req->ctrl; memcpy(&ctrl->header, header, sizeof(ctrl->header)); - memcpy(&ctrl->u, para, sizeof(ctrl->u)); + memcpy(&ctrl->u.akcipher_create_session.para, para, sizeof(*para)); input = &vc_ctrl_req->input; input->status = cpu_to_le32(VIRTIO_CRYPTO_ERR); diff --git a/drivers/crypto/virtio/virtio_crypto_common.h b/drivers/crypto/virtio/virtio_crypto_common.h index 154590e1f7643d..7059bbe5a2ebaa 100644 --- a/drivers/crypto/virtio/virtio_crypto_common.h +++ b/drivers/crypto/virtio/virtio_crypto_common.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -28,6 +29,7 @@ struct data_queue { char name[32]; struct crypto_engine *engine; + struct tasklet_struct done_task; }; struct virtio_crypto { diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c index 43a0838d31ff01..b909c6a2bf1c34 100644 --- a/drivers/crypto/virtio/virtio_crypto_core.c +++ b/drivers/crypto/virtio/virtio_crypto_core.c @@ -72,27 +72,28 @@ int virtio_crypto_ctrl_vq_request(struct virtio_crypto *vcrypto, struct scatterl return 0; } -static void virtcrypto_dataq_callback(struct virtqueue *vq) +static void virtcrypto_done_task(unsigned long data) { - struct virtio_crypto *vcrypto = vq->vdev->priv; + struct data_queue *data_vq = (struct data_queue *)data; + struct virtqueue *vq = data_vq->vq; struct virtio_crypto_request *vc_req; - unsigned long flags; unsigned int len; - unsigned int qid = vq->index; - spin_lock_irqsave(&vcrypto->data_vq[qid].lock, flags); do { virtqueue_disable_cb(vq); while ((vc_req = virtqueue_get_buf(vq, &len)) != NULL) { - spin_unlock_irqrestore( - &vcrypto->data_vq[qid].lock, flags); if (vc_req->alg_cb) vc_req->alg_cb(vc_req, len); - spin_lock_irqsave( - &vcrypto->data_vq[qid].lock, flags); } } while (!virtqueue_enable_cb(vq)); - spin_unlock_irqrestore(&vcrypto->data_vq[qid].lock, flags); +} + +static void virtcrypto_dataq_callback(struct virtqueue *vq) +{ + struct virtio_crypto *vcrypto = vq->vdev->priv; + struct data_queue *dq = &vcrypto->data_vq[vq->index]; + + tasklet_schedule(&dq->done_task); } static int virtcrypto_find_vqs(struct virtio_crypto *vi) @@ -150,6 +151,8 @@ static int virtcrypto_find_vqs(struct virtio_crypto *vi) ret = -ENOMEM; goto err_engine; } + tasklet_init(&vi->data_vq[i].done_task, virtcrypto_done_task, + (unsigned long)&vi->data_vq[i]); } kfree(names); @@ -497,12 +500,15 @@ static void virtcrypto_free_unused_reqs(struct virtio_crypto *vcrypto) static void virtcrypto_remove(struct virtio_device *vdev) { struct virtio_crypto *vcrypto = vdev->priv; + int i; dev_info(&vdev->dev, "Start virtcrypto_remove.\n"); flush_work(&vcrypto->config_work); if (virtcrypto_dev_started(vcrypto)) virtcrypto_dev_stop(vcrypto); + for (i = 0; i < vcrypto->max_data_queues; i++) + tasklet_kill(&vcrypto->data_vq[i].done_task); virtio_reset_device(vdev); virtcrypto_free_unused_reqs(vcrypto); virtcrypto_clear_crypto_engines(vcrypto); diff --git a/drivers/crypto/xilinx/zynqmp-aes-gcm.c b/drivers/crypto/xilinx/zynqmp-aes-gcm.c index ce335578b759ed..84103fc3f66f18 100644 --- a/drivers/crypto/xilinx/zynqmp-aes-gcm.c +++ b/drivers/crypto/xilinx/zynqmp-aes-gcm.c @@ -231,7 +231,10 @@ static int zynqmp_handle_aes_req(struct crypto_engine *engine, err = zynqmp_aes_aead_cipher(areq); } + local_bh_disable(); crypto_finalize_aead_request(engine, areq, err); + local_bh_enable(); + return 0; } diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index 40d055560e52fd..43195345583098 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -194,31 +194,27 @@ struct cxl_cfmws_context { int id; }; -static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, - const unsigned long end) +static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws, + struct cxl_cfmws_context *ctx) { int target_map[CXL_DECODER_MAX_INTERLEAVE]; - struct cxl_cfmws_context *ctx = arg; struct cxl_port *root_port = ctx->root_port; struct resource *cxl_res = ctx->cxl_res; struct cxl_cxims_context cxims_ctx; struct cxl_root_decoder *cxlrd; struct device *dev = ctx->dev; - struct acpi_cedt_cfmws *cfmws; cxl_calc_hb_fn cxl_calc_hb; struct cxl_decoder *cxld; unsigned int ways, i, ig; struct resource *res; int rc; - cfmws = (struct acpi_cedt_cfmws *) header; - rc = cxl_acpi_cfmws_verify(dev, cfmws); if (rc) { dev_err(dev, "CFMWS range %#llx-%#llx not registered\n", cfmws->base_hpa, cfmws->base_hpa + cfmws->window_size - 1); - return 0; + return rc; } rc = eiw_to_ways(cfmws->interleave_ways, &ways); @@ -254,7 +250,7 @@ static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, cxlrd = cxl_root_decoder_alloc(root_port, ways, cxl_calc_hb); if (IS_ERR(cxlrd)) - return 0; + return PTR_ERR(cxlrd); cxld = &cxlrd->cxlsd.cxld; cxld->flags = cfmws_to_decoder_flags(cfmws->restrictions); @@ -295,16 +291,7 @@ static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, put_device(&cxld->dev); else rc = cxl_decoder_autoremove(dev, cxld); - if (rc) { - dev_err(dev, "Failed to add decode range: %pr", res); - return rc; - } - dev_dbg(dev, "add: %s node: %d range [%#llx - %#llx]\n", - dev_name(&cxld->dev), - phys_to_target_node(cxld->hpa_range.start), - cxld->hpa_range.start, cxld->hpa_range.end); - - return 0; + return rc; err_insert: kfree(res->name); @@ -313,6 +300,29 @@ static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, return -ENOMEM; } +static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, + const unsigned long end) +{ + struct acpi_cedt_cfmws *cfmws = (struct acpi_cedt_cfmws *)header; + struct cxl_cfmws_context *ctx = arg; + struct device *dev = ctx->dev; + int rc; + + rc = __cxl_parse_cfmws(cfmws, ctx); + if (rc) + dev_err(dev, + "Failed to add decode range: [%#llx - %#llx] (%d)\n", + cfmws->base_hpa, + cfmws->base_hpa + cfmws->window_size - 1, rc); + else + dev_dbg(dev, "decode range: node: %d range [%#llx - %#llx]\n", + phys_to_target_node(cfmws->base_hpa), cfmws->base_hpa, + cfmws->base_hpa + cfmws->window_size - 1); + + /* never fail cxl_acpi load for a single window failure */ + return 0; +} + __mock struct acpi_device *to_cxl_host_bridge(struct device *host, struct device *dev) { diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index 45e7e044cf4a04..6444cc827c9ceb 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -27,7 +27,14 @@ void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled); int cxl_region_init(void); void cxl_region_exit(void); int cxl_get_poison_by_endpoint(struct cxl_port *port); +struct cxl_region *cxl_dpa_to_region(const struct cxl_memdev *cxlmd, u64 dpa); + #else +static inline +struct cxl_region *cxl_dpa_to_region(const struct cxl_memdev *cxlmd, u64 dpa) +{ + return NULL; +} static inline int cxl_get_poison_by_endpoint(struct cxl_port *port) { return 0; @@ -75,6 +82,7 @@ resource_size_t __rcrb_to_component(struct device *dev, enum cxl_rcrb which); extern struct rw_semaphore cxl_dpa_rwsem; +extern struct rw_semaphore cxl_region_rwsem; int cxl_memdev_init(void); void cxl_memdev_exit(void); diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 4449b34a80cc9b..3600b7cbfb5893 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -52,6 +52,14 @@ int devm_cxl_add_passthrough_decoder(struct cxl_port *port) struct cxl_dport *dport = NULL; int single_port_map[1]; unsigned long index; + struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev); + + /* + * Capability checks are moot for passthrough decoders, support + * any and all possibilities. + */ + cxlhdm->interleave_mask = ~0U; + cxlhdm->iw_cap_mask = ~0UL; cxlsd = cxl_switch_decoder_alloc(port, 1); if (IS_ERR(cxlsd)) @@ -79,13 +87,18 @@ static void parse_hdm_decoder_caps(struct cxl_hdm *cxlhdm) cxlhdm->interleave_mask |= GENMASK(11, 8); if (FIELD_GET(CXL_HDM_DECODER_INTERLEAVE_14_12, hdm_cap)) cxlhdm->interleave_mask |= GENMASK(14, 12); + cxlhdm->iw_cap_mask = BIT(1) | BIT(2) | BIT(4) | BIT(8); + if (FIELD_GET(CXL_HDM_DECODER_INTERLEAVE_3_6_12_WAY, hdm_cap)) + cxlhdm->iw_cap_mask |= BIT(3) | BIT(6) | BIT(12); + if (FIELD_GET(CXL_HDM_DECODER_INTERLEAVE_16_WAY, hdm_cap)) + cxlhdm->iw_cap_mask |= BIT(16); } static int map_hdm_decoder_regs(struct cxl_port *port, void __iomem *crb, struct cxl_component_regs *regs) { struct cxl_register_map map = { - .dev = &port->dev, + .host = &port->dev, .resource = port->component_reg_phys, .base = crb, .max_size = CXL_COMPONENT_REG_BLOCK_SIZE, @@ -373,10 +386,9 @@ resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled) { resource_size_t base = -1; - down_read(&cxl_dpa_rwsem); + lockdep_assert_held(&cxl_dpa_rwsem); if (cxled->dpa_res) base = cxled->dpa_res->start; - up_read(&cxl_dpa_rwsem); return base; } @@ -575,17 +587,11 @@ static void cxld_set_type(struct cxl_decoder *cxld, u32 *ctrl) CXL_HDM_DECODER0_CTRL_HOSTONLY); } -static int cxlsd_set_targets(struct cxl_switch_decoder *cxlsd, u64 *tgt) +static void cxlsd_set_targets(struct cxl_switch_decoder *cxlsd, u64 *tgt) { struct cxl_dport **t = &cxlsd->target[0]; int ways = cxlsd->cxld.interleave_ways; - if (dev_WARN_ONCE(&cxlsd->cxld.dev, - ways > 8 || ways > cxlsd->nr_targets, - "ways: %d overflows targets: %d\n", ways, - cxlsd->nr_targets)) - return -ENXIO; - *tgt = FIELD_PREP(GENMASK(7, 0), t[0]->port_id); if (ways > 1) *tgt |= FIELD_PREP(GENMASK(15, 8), t[1]->port_id); @@ -601,8 +607,6 @@ static int cxlsd_set_targets(struct cxl_switch_decoder *cxlsd, u64 *tgt) *tgt |= FIELD_PREP(GENMASK_ULL(55, 48), t[6]->port_id); if (ways > 7) *tgt |= FIELD_PREP(GENMASK_ULL(63, 56), t[7]->port_id); - - return 0; } /* @@ -643,13 +647,33 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld) if (cxld->flags & CXL_DECODER_F_ENABLE) return 0; - if (port->commit_end + 1 != id) { + if (cxl_num_decoders_committed(port) != id) { dev_dbg(&port->dev, "%s: out of order commit, expected decoder%d.%d\n", - dev_name(&cxld->dev), port->id, port->commit_end + 1); + dev_name(&cxld->dev), port->id, + cxl_num_decoders_committed(port)); return -EBUSY; } + /* + * For endpoint decoders hosted on CXL memory devices that + * support the sanitize operation, make sure sanitize is not in-flight. + */ + if (is_endpoint_decoder(&cxld->dev)) { + struct cxl_endpoint_decoder *cxled = + to_cxl_endpoint_decoder(&cxld->dev); + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct cxl_memdev_state *mds = + to_cxl_memdev_state(cxlmd->cxlds); + + if (mds && mds->security.sanitize_active) { + dev_dbg(&cxlmd->dev, + "attempted to commit %s during sanitize\n", + dev_name(&cxld->dev)); + return -EBUSY; + } + } + down_read(&cxl_dpa_rwsem); /* common decoder settings */ ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(cxld->id)); @@ -670,13 +694,7 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld) void __iomem *tl_lo = hdm + CXL_HDM_DECODER0_TL_LOW(id); u64 targets; - rc = cxlsd_set_targets(cxlsd, &targets); - if (rc) { - dev_dbg(&port->dev, "%s: target configuration error\n", - dev_name(&cxld->dev)); - goto err; - } - + cxlsd_set_targets(cxlsd, &targets); writel(upper_32_bits(targets), tl_hi); writel(lower_32_bits(targets), tl_lo); } else { @@ -694,7 +712,6 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld) port->commit_end++; rc = cxld_await_commit(hdm, cxld->id); -err: if (rc) { dev_dbg(&port->dev, "%s: error %d committing decoder\n", dev_name(&cxld->dev), rc); @@ -844,7 +861,9 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, cxld->target_type = CXL_DECODER_HOSTONLYMEM; else cxld->target_type = CXL_DECODER_DEVMEM; - if (cxld->id != port->commit_end + 1) { + + guard(rwsem_write)(&cxl_region_rwsem); + if (cxld->id != cxl_num_decoders_committed(port)) { dev_warn(&port->dev, "decoder%d.%d: Committed out of order\n", port->id, cxld->id); diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 4df4f614f490ef..fecaa18f4dd203 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -928,7 +928,7 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, for (cnt = 0; cnt < total; cnt++) { payload->handles[i++] = get_pl->records[cnt].hdr.handle; dev_dbg(mds->cxlds.dev, "Event log '%d': Clearing %u\n", log, - le16_to_cpu(payload->handles[i])); + le16_to_cpu(payload->handles[i - 1])); if (i == max_handles) { payload->nr_recs = i; @@ -959,24 +959,22 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, struct cxl_memdev *cxlmd = mds->cxlds.cxlmd; struct device *dev = mds->cxlds.dev; struct cxl_get_event_payload *payload; - struct cxl_mbox_cmd mbox_cmd; u8 log_type = type; u16 nr_rec; mutex_lock(&mds->event.log_lock); payload = mds->event.buf; - mbox_cmd = (struct cxl_mbox_cmd) { - .opcode = CXL_MBOX_OP_GET_EVENT_RECORD, - .payload_in = &log_type, - .size_in = sizeof(log_type), - .payload_out = payload, - .size_out = mds->payload_size, - .min_out = struct_size(payload, records, 0), - }; - do { int rc, i; + struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd) { + .opcode = CXL_MBOX_OP_GET_EVENT_RECORD, + .payload_in = &log_type, + .size_in = sizeof(log_type), + .payload_out = payload, + .size_out = mds->payload_size, + .min_out = struct_size(payload, records, 0), + }; rc = cxl_internal_send_cmd(mds, &mbox_cmd); if (rc) { @@ -1125,20 +1123,7 @@ int cxl_dev_state_identify(struct cxl_memdev_state *mds) } EXPORT_SYMBOL_NS_GPL(cxl_dev_state_identify, CXL); -/** - * cxl_mem_sanitize() - Send a sanitization command to the device. - * @mds: The device data for the operation - * @cmd: The specific sanitization command opcode - * - * Return: 0 if the command was executed successfully, regardless of - * whether or not the actual security operation is done in the background, - * such as for the Sanitize case. - * Error return values can be the result of the mailbox command, -EINVAL - * when security requirements are not met or invalid contexts. - * - * See CXL 3.0 @8.2.9.8.5.1 Sanitize and @8.2.9.8.5.2 Secure Erase. - */ -int cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd) +static int __cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd) { int rc; u32 sec_out = 0; @@ -1183,7 +1168,45 @@ int cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd) return 0; } -EXPORT_SYMBOL_NS_GPL(cxl_mem_sanitize, CXL); + + +/** + * cxl_mem_sanitize() - Send a sanitization command to the device. + * @cxlmd: The device for the operation + * @cmd: The specific sanitization command opcode + * + * Return: 0 if the command was executed successfully, regardless of + * whether or not the actual security operation is done in the background, + * such as for the Sanitize case. + * Error return values can be the result of the mailbox command, -EINVAL + * when security requirements are not met or invalid contexts, or -EBUSY + * if the sanitize operation is already in flight. + * + * See CXL 3.0 @8.2.9.8.5.1 Sanitize and @8.2.9.8.5.2 Secure Erase. + */ +int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd) +{ + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_port *endpoint; + int rc; + + /* synchronize with cxl_mem_probe() and decoder write operations */ + device_lock(&cxlmd->dev); + endpoint = cxlmd->endpoint; + down_read(&cxl_region_rwsem); + /* + * Require an endpoint to be safe otherwise the driver can not + * be sure that the device is unmapped. + */ + if (endpoint && cxl_num_decoders_committed(endpoint) == 0) + rc = __cxl_mem_sanitize(mds, cmd); + else + rc = -EBUSY; + up_read(&cxl_region_rwsem); + device_unlock(&cxlmd->dev); + + return rc; +} static int add_dpa_res(struct device *dev, struct resource *parent, struct resource *res, resource_size_t start, @@ -1285,7 +1308,6 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); struct cxl_mbox_poison_out *po; struct cxl_mbox_poison_in pi; - struct cxl_mbox_cmd mbox_cmd; int nr_records = 0; int rc; @@ -1297,16 +1319,16 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, pi.offset = cpu_to_le64(offset); pi.length = cpu_to_le64(len / CXL_POISON_LEN_MULT); - mbox_cmd = (struct cxl_mbox_cmd) { - .opcode = CXL_MBOX_OP_GET_POISON, - .size_in = sizeof(pi), - .payload_in = &pi, - .size_out = mds->payload_size, - .payload_out = po, - .min_out = struct_size(po, record, 0), - }; - do { + struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd){ + .opcode = CXL_MBOX_OP_GET_POISON, + .size_in = sizeof(pi), + .payload_in = &pi, + .size_out = mds->payload_size, + .payload_out = po, + .min_out = struct_size(po, record, 0), + }; + rc = cxl_internal_send_cmd(mds, &mbox_cmd); if (rc) break; diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 14b547c07f5476..eb895c70043fdf 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -125,13 +125,16 @@ static ssize_t security_state_show(struct device *dev, struct cxl_memdev *cxlmd = to_cxl_memdev(dev); struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); - u64 reg = readq(cxlds->regs.mbox + CXLDEV_MBOX_BG_CMD_STATUS_OFFSET); - u32 pct = FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_PCT_MASK, reg); - u16 cmd = FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_OPCODE_MASK, reg); unsigned long state = mds->security.state; + int rc = 0; - if (cmd == CXL_MBOX_OP_SANITIZE && pct != 100) - return sysfs_emit(buf, "sanitize\n"); + /* sync with latest submission state */ + mutex_lock(&mds->mbox_mutex); + if (mds->security.sanitize_active) + rc = sysfs_emit(buf, "sanitize\n"); + mutex_unlock(&mds->mbox_mutex); + if (rc) + return rc; if (!(state & CXL_PMEM_SEC_STATE_USER_PASS_SET)) return sysfs_emit(buf, "disabled\n"); @@ -152,24 +155,17 @@ static ssize_t security_sanitize_store(struct device *dev, const char *buf, size_t len) { struct cxl_memdev *cxlmd = to_cxl_memdev(dev); - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); - struct cxl_port *port = cxlmd->endpoint; bool sanitize; ssize_t rc; if (kstrtobool(buf, &sanitize) || !sanitize) return -EINVAL; - if (!port || !is_cxl_endpoint(port)) - return -EINVAL; - - /* ensure no regions are mapped to this memdev */ - if (port->commit_end != -1) - return -EBUSY; - - rc = cxl_mem_sanitize(mds, CXL_MBOX_OP_SANITIZE); + rc = cxl_mem_sanitize(cxlmd, CXL_MBOX_OP_SANITIZE); + if (rc) + return rc; - return rc ? rc : len; + return len; } static struct device_attribute dev_attr_security_sanitize = __ATTR(sanitize, 0200, NULL, security_sanitize_store); @@ -179,24 +175,17 @@ static ssize_t security_erase_store(struct device *dev, const char *buf, size_t len) { struct cxl_memdev *cxlmd = to_cxl_memdev(dev); - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); - struct cxl_port *port = cxlmd->endpoint; ssize_t rc; bool erase; if (kstrtobool(buf, &erase) || !erase) return -EINVAL; - if (!port || !is_cxl_endpoint(port)) - return -EINVAL; - - /* ensure no regions are mapped to this memdev */ - if (port->commit_end != -1) - return -EBUSY; - - rc = cxl_mem_sanitize(mds, CXL_MBOX_OP_SECURE_ERASE); + rc = cxl_mem_sanitize(cxlmd, CXL_MBOX_OP_SECURE_ERASE); + if (rc) + return rc; - return rc ? rc : len; + return len; } static struct device_attribute dev_attr_security_erase = __ATTR(erase, 0200, NULL, security_erase_store); @@ -238,11 +227,17 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) if (!port || !is_cxl_endpoint(port)) return -EINVAL; - rc = down_read_interruptible(&cxl_dpa_rwsem); + rc = down_read_interruptible(&cxl_region_rwsem); if (rc) return rc; - if (port->commit_end == -1) { + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) { + up_read(&cxl_region_rwsem); + return rc; + } + + if (cxl_num_decoders_committed(port) == 0) { /* No regions mapped to this memdev */ rc = cxl_get_poison_by_memdev(cxlmd); } else { @@ -250,55 +245,12 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) rc = cxl_get_poison_by_endpoint(port); } up_read(&cxl_dpa_rwsem); + up_read(&cxl_region_rwsem); return rc; } EXPORT_SYMBOL_NS_GPL(cxl_trigger_poison_list, CXL); -struct cxl_dpa_to_region_context { - struct cxl_region *cxlr; - u64 dpa; -}; - -static int __cxl_dpa_to_region(struct device *dev, void *arg) -{ - struct cxl_dpa_to_region_context *ctx = arg; - struct cxl_endpoint_decoder *cxled; - u64 dpa = ctx->dpa; - - if (!is_endpoint_decoder(dev)) - return 0; - - cxled = to_cxl_endpoint_decoder(dev); - if (!cxled->dpa_res || !resource_size(cxled->dpa_res)) - return 0; - - if (dpa > cxled->dpa_res->end || dpa < cxled->dpa_res->start) - return 0; - - dev_dbg(dev, "dpa:0x%llx mapped in region:%s\n", dpa, - dev_name(&cxled->cxld.region->dev)); - - ctx->cxlr = cxled->cxld.region; - - return 1; -} - -static struct cxl_region *cxl_dpa_to_region(struct cxl_memdev *cxlmd, u64 dpa) -{ - struct cxl_dpa_to_region_context ctx; - struct cxl_port *port; - - ctx = (struct cxl_dpa_to_region_context) { - .dpa = dpa, - }; - port = cxlmd->endpoint; - if (port && is_cxl_endpoint(port) && port->commit_end != -1) - device_for_each_child(&port->dev, &ctx, __cxl_dpa_to_region); - - return ctx.cxlr; -} - static int cxl_validate_poison_dpa(struct cxl_memdev *cxlmd, u64 dpa) { struct cxl_dev_state *cxlds = cxlmd->cxlds; @@ -335,10 +287,16 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; - rc = down_read_interruptible(&cxl_dpa_rwsem); + rc = down_read_interruptible(&cxl_region_rwsem); if (rc) return rc; + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) { + up_read(&cxl_region_rwsem); + return rc; + } + rc = cxl_validate_poison_dpa(cxlmd, dpa); if (rc) goto out; @@ -366,6 +324,7 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_INJECT); out: up_read(&cxl_dpa_rwsem); + up_read(&cxl_region_rwsem); return rc; } @@ -383,10 +342,16 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; - rc = down_read_interruptible(&cxl_dpa_rwsem); + rc = down_read_interruptible(&cxl_region_rwsem); if (rc) return rc; + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) { + up_read(&cxl_region_rwsem); + return rc; + } + rc = cxl_validate_poison_dpa(cxlmd, dpa); if (rc) goto out; @@ -423,6 +388,7 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_CLEAR); out: up_read(&cxl_dpa_rwsem); + up_read(&cxl_region_rwsem); return rc; } @@ -556,21 +522,11 @@ void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds, } EXPORT_SYMBOL_NS_GPL(clear_exclusive_cxl_commands, CXL); -static void cxl_memdev_security_shutdown(struct device *dev) -{ - struct cxl_memdev *cxlmd = to_cxl_memdev(dev); - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); - - if (mds->security.poll) - cancel_delayed_work_sync(&mds->security.poll_dwork); -} - static void cxl_memdev_shutdown(struct device *dev) { struct cxl_memdev *cxlmd = to_cxl_memdev(dev); down_write(&cxl_memdev_rwsem); - cxl_memdev_security_shutdown(dev); cxlmd->cxlds = NULL; up_write(&cxl_memdev_rwsem); } @@ -580,8 +536,8 @@ static void cxl_memdev_unregister(void *_cxlmd) struct cxl_memdev *cxlmd = _cxlmd; struct device *dev = &cxlmd->dev; - cxl_memdev_shutdown(dev); cdev_device_del(&cxlmd->cdev, dev); + cxl_memdev_shutdown(dev); put_device(dev); } @@ -961,17 +917,16 @@ static const struct fw_upload_ops cxl_memdev_fw_ops = { .cleanup = cxl_fw_cleanup, }; -static void devm_cxl_remove_fw_upload(void *fwl) +static void cxl_remove_fw_upload(void *fwl) { firmware_upload_unregister(fwl); } -int cxl_memdev_setup_fw_upload(struct cxl_memdev_state *mds) +int devm_cxl_setup_fw_upload(struct device *host, struct cxl_memdev_state *mds) { struct cxl_dev_state *cxlds = &mds->cxlds; struct device *dev = &cxlds->cxlmd->dev; struct fw_upload *fwl; - int rc; if (!test_bit(CXL_MEM_COMMAND_ID_GET_FW_INFO, mds->enabled_cmds)) return 0; @@ -979,19 +934,10 @@ int cxl_memdev_setup_fw_upload(struct cxl_memdev_state *mds) fwl = firmware_upload_register(THIS_MODULE, dev, dev_name(dev), &cxl_memdev_fw_ops, mds); if (IS_ERR(fwl)) - return dev_err_probe(dev, PTR_ERR(fwl), - "Failed to register firmware loader\n"); - - rc = devm_add_action_or_reset(cxlds->dev, devm_cxl_remove_fw_upload, - fwl); - if (rc) - dev_err(dev, - "Failed to add firmware loader remove action: %d\n", - rc); - - return rc; + return PTR_ERR(fwl); + return devm_add_action_or_reset(host, cxl_remove_fw_upload, fwl); } -EXPORT_SYMBOL_NS_GPL(cxl_memdev_setup_fw_upload, CXL); +EXPORT_SYMBOL_NS_GPL(devm_cxl_setup_fw_upload, CXL); static const struct file_operations cxl_memdev_fops = { .owner = THIS_MODULE, @@ -1002,36 +948,8 @@ static const struct file_operations cxl_memdev_fops = { .llseek = noop_llseek, }; -static void put_sanitize(void *data) -{ - struct cxl_memdev_state *mds = data; - - sysfs_put(mds->security.sanitize_node); -} - -static int cxl_memdev_security_init(struct cxl_memdev *cxlmd) -{ - struct cxl_dev_state *cxlds = cxlmd->cxlds; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); - struct device *dev = &cxlmd->dev; - struct kernfs_node *sec; - - sec = sysfs_get_dirent(dev->kobj.sd, "security"); - if (!sec) { - dev_err(dev, "sysfs_get_dirent 'security' failed\n"); - return -ENODEV; - } - mds->security.sanitize_node = sysfs_get_dirent(sec, "state"); - sysfs_put(sec); - if (!mds->security.sanitize_node) { - dev_err(dev, "sysfs_get_dirent 'state' failed\n"); - return -ENODEV; - } - - return devm_add_action_or_reset(cxlds->dev, put_sanitize, mds); - } - -struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds) +struct cxl_memdev *devm_cxl_add_memdev(struct device *host, + struct cxl_dev_state *cxlds) { struct cxl_memdev *cxlmd; struct device *dev; @@ -1059,11 +977,7 @@ struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds) if (rc) goto err; - rc = cxl_memdev_security_init(cxlmd); - if (rc) - goto err; - - rc = devm_add_action_or_reset(cxlds->dev, cxl_memdev_unregister, cxlmd); + rc = devm_add_action_or_reset(host, cxl_memdev_unregister, cxlmd); if (rc) return ERR_PTR(rc); return cxlmd; @@ -1079,6 +993,50 @@ struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds) } EXPORT_SYMBOL_NS_GPL(devm_cxl_add_memdev, CXL); +static void sanitize_teardown_notifier(void *data) +{ + struct cxl_memdev_state *mds = data; + struct kernfs_node *state; + + /* + * Prevent new irq triggered invocations of the workqueue and + * flush inflight invocations. + */ + mutex_lock(&mds->mbox_mutex); + state = mds->security.sanitize_node; + mds->security.sanitize_node = NULL; + mutex_unlock(&mds->mbox_mutex); + + cancel_delayed_work_sync(&mds->security.poll_dwork); + sysfs_put(state); +} + +int devm_cxl_sanitize_setup_notifier(struct device *host, + struct cxl_memdev *cxlmd) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); + struct kernfs_node *sec; + + if (!test_bit(CXL_SEC_ENABLED_SANITIZE, mds->security.enabled_cmds)) + return 0; + + /* + * Note, the expectation is that @cxlmd would have failed to be + * created if these sysfs_get_dirent calls fail. + */ + sec = sysfs_get_dirent(cxlmd->dev.kobj.sd, "security"); + if (!sec) + return -ENOENT; + mds->security.sanitize_node = sysfs_get_dirent(sec, "state"); + sysfs_put(sec); + if (!mds->security.sanitize_node) + return -ENOENT; + + return devm_add_action_or_reset(host, sanitize_teardown_notifier, mds); +} +EXPORT_SYMBOL_NS_GPL(devm_cxl_sanitize_setup_notifier, CXL); + __init int cxl_memdev_init(void) { dev_t devt; diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index c7a7887ebdcff8..6edfd054667373 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -388,10 +388,6 @@ int cxl_dvsec_rr_decode(struct device *dev, int d, size |= temp & CXL_DVSEC_MEM_SIZE_LOW_MASK; if (!size) { - info->dvsec_range[i] = (struct range) { - .start = 0, - .end = CXL_RESOURCE_NONE, - }; continue; } @@ -409,12 +405,10 @@ int cxl_dvsec_rr_decode(struct device *dev, int d, base |= temp & CXL_DVSEC_MEM_BASE_LOW_MASK; - info->dvsec_range[i] = (struct range) { + info->dvsec_range[ranges++] = (struct range) { .start = base, .end = base + size - 1 }; - - ranges++; } info->ranges = ranges; @@ -475,9 +469,9 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, allowed++; } - if (!allowed) { - cxl_set_mem_enable(cxlds, 0); - info->mem_enabled = 0; + if (!allowed && info->mem_enabled) { + dev_err(dev, "Range register decodes outside platform defined CXL ranges.\n"); + return -ENXIO; } /* diff --git a/drivers/cxl/core/pmu.c b/drivers/cxl/core/pmu.c index 7684c843e5a59c..5d8e06b0ba6e88 100644 --- a/drivers/cxl/core/pmu.c +++ b/drivers/cxl/core/pmu.c @@ -23,7 +23,7 @@ const struct device_type cxl_pmu_type = { static void remove_dev(void *dev) { - device_del(dev); + device_unregister(dev); } int devm_cxl_pmu_add(struct device *parent, struct cxl_pmu_regs *regs, diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 7ca01a834e188c..c67cc8c9d5cc61 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -28,9 +28,22 @@ * instantiated by the core. */ +/* + * All changes to the interleave configuration occur with this lock held + * for write. + */ +DECLARE_RWSEM(cxl_region_rwsem); + static DEFINE_IDA(cxl_port_ida); static DEFINE_XARRAY(cxl_root_buses); +int cxl_num_decoders_committed(struct cxl_port *port) +{ + lockdep_assert_held(&cxl_region_rwsem); + + return port->commit_end + 1; +} + static ssize_t devtype_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -159,14 +172,10 @@ static ssize_t target_list_show(struct device *dev, { struct cxl_switch_decoder *cxlsd = to_cxl_switch_decoder(dev); ssize_t offset; - unsigned int seq; int rc; - do { - seq = read_seqbegin(&cxlsd->target_lock); - rc = emit_target_list(cxlsd, buf); - } while (read_seqretry(&cxlsd->target_lock, seq)); - + guard(rwsem_read)(&cxl_region_rwsem); + rc = emit_target_list(cxlsd, buf); if (rc < 0) return rc; offset = rc; @@ -213,9 +222,9 @@ static ssize_t dpa_resource_show(struct device *dev, struct device_attribute *at char *buf) { struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev); - u64 base = cxl_dpa_resource_start(cxled); - return sysfs_emit(buf, "%#llx\n", base); + guard(rwsem_read)(&cxl_dpa_rwsem); + return sysfs_emit(buf, "%#llx\n", (u64)cxl_dpa_resource_start(cxled)); } static DEVICE_ATTR_RO(dpa_resource); @@ -691,14 +700,14 @@ static struct cxl_port *cxl_port_alloc(struct device *uport_dev, return ERR_PTR(rc); } -static int cxl_setup_comp_regs(struct device *dev, struct cxl_register_map *map, +static int cxl_setup_comp_regs(struct device *host, struct cxl_register_map *map, resource_size_t component_reg_phys) { if (component_reg_phys == CXL_RESOURCE_NONE) return 0; *map = (struct cxl_register_map) { - .dev = dev, + .host = host, .reg_type = CXL_REGLOC_RBI_COMPONENT, .resource = component_reg_phys, .max_size = CXL_COMPONENT_REG_BLOCK_SIZE, @@ -716,13 +725,23 @@ static int cxl_port_setup_regs(struct cxl_port *port, component_reg_phys); } -static int cxl_dport_setup_regs(struct cxl_dport *dport, +static int cxl_dport_setup_regs(struct device *host, struct cxl_dport *dport, resource_size_t component_reg_phys) { + int rc; + if (dev_is_platform(dport->dport_dev)) return 0; - return cxl_setup_comp_regs(dport->dport_dev, &dport->comp_map, - component_reg_phys); + + /* + * use @dport->dport_dev for the context for error messages during + * register probing, and fixup @host after the fact, since @host may be + * NULL. + */ + rc = cxl_setup_comp_regs(dport->dport_dev, &dport->comp_map, + component_reg_phys); + dport->comp_map.host = host; + return rc; } static struct cxl_port *__devm_cxl_add_port(struct device *host, @@ -983,7 +1002,16 @@ __devm_cxl_add_dport(struct cxl_port *port, struct device *dport_dev, if (!dport) return ERR_PTR(-ENOMEM); - if (rcrb != CXL_RESOURCE_NONE) { + dport->dport_dev = dport_dev; + dport->port_id = port_id; + dport->port = port; + + if (rcrb == CXL_RESOURCE_NONE) { + rc = cxl_dport_setup_regs(&port->dev, dport, + component_reg_phys); + if (rc) + return ERR_PTR(rc); + } else { dport->rcrb.base = rcrb; component_reg_phys = __rcrb_to_component(dport_dev, &dport->rcrb, CXL_RCRB_DOWNSTREAM); @@ -992,6 +1020,14 @@ __devm_cxl_add_dport(struct cxl_port *port, struct device *dport_dev, return ERR_PTR(-ENXIO); } + /* + * RCH @dport is not ready to map until associated with its + * memdev + */ + rc = cxl_dport_setup_regs(NULL, dport, component_reg_phys); + if (rc) + return ERR_PTR(rc); + dport->rch = true; } @@ -999,14 +1035,6 @@ __devm_cxl_add_dport(struct cxl_port *port, struct device *dport_dev, dev_dbg(dport_dev, "Component Registers found for dport: %pa\n", &component_reg_phys); - dport->dport_dev = dport_dev; - dport->port_id = port_id; - dport->port = port; - - rc = cxl_dport_setup_regs(dport, component_reg_phys); - if (rc) - return ERR_PTR(rc); - cond_cxl_root_lock(port); rc = add_dport(port, dport); cond_cxl_root_unlock(port); @@ -1217,35 +1245,39 @@ static struct device *grandparent(struct device *dev) return NULL; } +static struct device *endpoint_host(struct cxl_port *endpoint) +{ + struct cxl_port *port = to_cxl_port(endpoint->dev.parent); + + if (is_cxl_root(port)) + return port->uport_dev; + return &port->dev; +} + static void delete_endpoint(void *data) { struct cxl_memdev *cxlmd = data; struct cxl_port *endpoint = cxlmd->endpoint; - struct cxl_port *parent_port; - struct device *parent; - - parent_port = cxl_mem_find_port(cxlmd, NULL); - if (!parent_port) - goto out; - parent = &parent_port->dev; + struct device *host = endpoint_host(endpoint); - device_lock(parent); - if (parent->driver && !endpoint->dead) { - devm_release_action(parent, cxl_unlink_parent_dport, endpoint); - devm_release_action(parent, cxl_unlink_uport, endpoint); - devm_release_action(parent, unregister_port, endpoint); + device_lock(host); + if (host->driver && !endpoint->dead) { + devm_release_action(host, cxl_unlink_parent_dport, endpoint); + devm_release_action(host, cxl_unlink_uport, endpoint); + devm_release_action(host, unregister_port, endpoint); } cxlmd->endpoint = NULL; - device_unlock(parent); - put_device(parent); -out: + device_unlock(host); put_device(&endpoint->dev); + put_device(host); } int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint) { + struct device *host = endpoint_host(endpoint); struct device *dev = &cxlmd->dev; + get_device(host); get_device(&endpoint->dev); cxlmd->endpoint = endpoint; cxlmd->depth = endpoint->depth; @@ -1543,7 +1575,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_mem_find_port, CXL); static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd, struct cxl_port *port, int *target_map) { - int i, rc = 0; + int i; if (!target_map) return 0; @@ -1553,19 +1585,16 @@ static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd, if (xa_empty(&port->dports)) return -EINVAL; - write_seqlock(&cxlsd->target_lock); - for (i = 0; i < cxlsd->nr_targets; i++) { + guard(rwsem_write)(&cxl_region_rwsem); + for (i = 0; i < cxlsd->cxld.interleave_ways; i++) { struct cxl_dport *dport = find_dport(port, target_map[i]); - if (!dport) { - rc = -ENXIO; - break; - } + if (!dport) + return -ENXIO; cxlsd->target[i] = dport; } - write_sequnlock(&cxlsd->target_lock); - return rc; + return 0; } struct cxl_dport *cxl_hb_modulo(struct cxl_root_decoder *cxlrd, int pos) @@ -1635,7 +1664,6 @@ static int cxl_switch_decoder_init(struct cxl_port *port, return -EINVAL; cxlsd->nr_targets = nr_targets; - seqlock_init(&cxlsd->target_lock); return cxl_decoder_init(port, &cxlsd->cxld); } diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 6d63b8798c2992..5060d9802795ee 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -28,12 +28,6 @@ * 3. Decoder targets */ -/* - * All changes to the interleave configuration occur with this lock held - * for write. - */ -static DECLARE_RWSEM(cxl_region_rwsem); - static struct cxl_region *to_cxl_region(struct device *dev); static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, @@ -294,7 +288,7 @@ static ssize_t commit_store(struct device *dev, struct device_attribute *attr, */ rc = cxl_region_invalidate_memregion(cxlr); if (rc) - return rc; + goto out; if (commit) { rc = cxl_region_decode_commit(cxlr); @@ -403,7 +397,7 @@ static ssize_t interleave_ways_store(struct device *dev, return rc; /* - * Even for x3, x9, and x12 interleaves the region interleave must be a + * Even for x3, x6, and x12 interleaves the region interleave must be a * power of 2 multiple of the host bridge interleave. */ if (!is_power_of_2(val / cxld->interleave_ways) || @@ -531,7 +525,7 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size) struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent); struct cxl_region_params *p = &cxlr->params; struct resource *res; - u32 remainder = 0; + u64 remainder = 0; lockdep_assert_held_write(&cxl_region_rwsem); @@ -551,7 +545,7 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size) (cxlr->mode == CXL_DECODER_PMEM && uuid_is_null(&p->uuid))) return -ENXIO; - div_u64_rem(size, SZ_256M * p->interleave_ways, &remainder); + div64_u64_rem(size, (u64)SZ_256M * p->interleave_ways, &remainder); if (remainder) return -EINVAL; @@ -735,12 +729,17 @@ static int match_auto_decoder(struct device *dev, void *data) return 0; } -static struct cxl_decoder *cxl_region_find_decoder(struct cxl_port *port, - struct cxl_region *cxlr) +static struct cxl_decoder * +cxl_region_find_decoder(struct cxl_port *port, + struct cxl_endpoint_decoder *cxled, + struct cxl_region *cxlr) { struct device *dev; int id = 0; + if (port == cxled_to_port(cxled)) + return &cxled->cxld; + if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) dev = device_find_child(&port->dev, &cxlr->params, match_auto_decoder); @@ -758,8 +757,31 @@ static struct cxl_decoder *cxl_region_find_decoder(struct cxl_port *port, return to_cxl_decoder(dev); } -static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port, - struct cxl_region *cxlr) +static bool auto_order_ok(struct cxl_port *port, struct cxl_region *cxlr_iter, + struct cxl_decoder *cxld) +{ + struct cxl_region_ref *rr = cxl_rr_load(port, cxlr_iter); + struct cxl_decoder *cxld_iter = rr->decoder; + + /* + * Allow the out of order assembly of auto-discovered regions. + * Per CXL Spec 3.1 8.2.4.20.12 software must commit decoders + * in HPA order. Confirm that the decoder with the lesser HPA + * starting address has the lesser id. + */ + dev_dbg(&cxld->dev, "check for HPA violation %s:%d < %s:%d\n", + dev_name(&cxld->dev), cxld->id, + dev_name(&cxld_iter->dev), cxld_iter->id); + + if (cxld_iter->id > cxld->id) + return true; + + return false; +} + +static struct cxl_region_ref * +alloc_region_ref(struct cxl_port *port, struct cxl_region *cxlr, + struct cxl_endpoint_decoder *cxled) { struct cxl_region_params *p = &cxlr->params; struct cxl_region_ref *cxl_rr, *iter; @@ -769,16 +791,21 @@ static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port, xa_for_each(&port->regions, index, iter) { struct cxl_region_params *ip = &iter->region->params; - if (!ip->res) + if (!ip->res || ip->res->start < p->res->start) continue; - if (ip->res->start > p->res->start) { - dev_dbg(&cxlr->dev, - "%s: HPA order violation %s:%pr vs %pr\n", - dev_name(&port->dev), - dev_name(&iter->region->dev), ip->res, p->res); - return ERR_PTR(-EBUSY); + if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) { + struct cxl_decoder *cxld; + + cxld = cxl_region_find_decoder(port, cxled, cxlr); + if (auto_order_ok(port, iter->region, cxld)) + continue; } + dev_dbg(&cxlr->dev, "%s: HPA order violation %s:%pr vs %pr\n", + dev_name(&port->dev), + dev_name(&iter->region->dev), ip->res, p->res); + + return ERR_PTR(-EBUSY); } cxl_rr = kzalloc(sizeof(*cxl_rr), GFP_KERNEL); @@ -858,10 +885,7 @@ static int cxl_rr_alloc_decoder(struct cxl_port *port, struct cxl_region *cxlr, { struct cxl_decoder *cxld; - if (port == cxled_to_port(cxled)) - cxld = &cxled->cxld; - else - cxld = cxl_region_find_decoder(port, cxlr); + cxld = cxl_region_find_decoder(port, cxled, cxlr); if (!cxld) { dev_dbg(&cxlr->dev, "%s: no decoder available\n", dev_name(&port->dev)); @@ -958,7 +982,7 @@ static int cxl_port_attach_region(struct cxl_port *port, nr_targets_inc = true; } } else { - cxl_rr = alloc_region_ref(port, cxlr); + cxl_rr = alloc_region_ref(port, cxlr, cxled); if (IS_ERR(cxl_rr)) { dev_dbg(&cxlr->dev, "%s: failed to allocate region reference\n", @@ -973,6 +997,26 @@ static int cxl_port_attach_region(struct cxl_port *port, } cxld = cxl_rr->decoder; + /* + * the number of targets should not exceed the target_count + * of the decoder + */ + if (is_switch_decoder(&cxld->dev)) { + struct cxl_switch_decoder *cxlsd; + + cxlsd = to_cxl_switch_decoder(&cxld->dev); + if (cxl_rr->nr_targets > cxlsd->nr_targets) { + dev_dbg(&cxlr->dev, + "%s:%s %s add: %s:%s @ %d overflows targets: %d\n", + dev_name(port->uport_dev), dev_name(&port->dev), + dev_name(&cxld->dev), dev_name(&cxlmd->dev), + dev_name(&cxled->cxld.dev), pos, + cxlsd->nr_targets); + rc = -ENXIO; + goto out_erase; + } + } + rc = cxl_rr_ep_add(cxl_rr, cxled); if (rc) { dev_dbg(&cxlr->dev, @@ -1082,6 +1126,50 @@ static int check_last_peer(struct cxl_endpoint_decoder *cxled, return 0; } +static int check_interleave_cap(struct cxl_decoder *cxld, int iw, int ig) +{ + struct cxl_port *port = to_cxl_port(cxld->dev.parent); + struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev); + unsigned int interleave_mask; + u8 eiw; + u16 eig; + int high_pos, low_pos; + + if (!test_bit(iw, &cxlhdm->iw_cap_mask)) + return -ENXIO; + /* + * Per CXL specification r3.1(8.2.4.20.13 Decoder Protection), + * if eiw < 8: + * DPAOFFSET[51: eig + 8] = HPAOFFSET[51: eig + 8 + eiw] + * DPAOFFSET[eig + 7: 0] = HPAOFFSET[eig + 7: 0] + * + * when the eiw is 0, all the bits of HPAOFFSET[51: 0] are used, the + * interleave bits are none. + * + * if eiw >= 8: + * DPAOFFSET[51: eig + 8] = HPAOFFSET[51: eig + eiw] / 3 + * DPAOFFSET[eig + 7: 0] = HPAOFFSET[eig + 7: 0] + * + * when the eiw is 8, all the bits of HPAOFFSET[51: 0] are used, the + * interleave bits are none. + */ + ways_to_eiw(iw, &eiw); + if (eiw == 0 || eiw == 8) + return 0; + + granularity_to_eig(ig, &eig); + if (eiw > 8) + high_pos = eiw + eig - 1; + else + high_pos = eiw + eig + 7; + low_pos = eig + 8; + interleave_mask = GENMASK(high_pos, low_pos); + if (interleave_mask & ~cxlhdm->interleave_mask) + return -ENXIO; + + return 0; +} + static int cxl_port_setup_targets(struct cxl_port *port, struct cxl_region *cxlr, struct cxl_endpoint_decoder *cxled) @@ -1133,7 +1221,14 @@ static int cxl_port_setup_targets(struct cxl_port *port, } if (is_cxl_root(parent_port)) { - parent_ig = cxlrd->cxlsd.cxld.interleave_granularity; + /* + * Root decoder IG is always set to value in CFMWS which + * may be different than this region's IG. We can use the + * region's IG here since interleave_granularity_store() + * does not allow interleaved host-bridges with + * root IG != region IG. + */ + parent_ig = p->interleave_granularity; parent_iw = cxlrd->cxlsd.cxld.interleave_ways; /* * For purposes of address bit routing, use power-of-2 math for @@ -1195,6 +1290,14 @@ static int cxl_port_setup_targets(struct cxl_port *port, return rc; } + if (iw > 8 || iw > cxlsd->nr_targets) { + dev_dbg(&cxlr->dev, + "%s:%s:%s: ways: %d overflows targets: %d\n", + dev_name(port->uport_dev), dev_name(&port->dev), + dev_name(&cxld->dev), iw, cxlsd->nr_targets); + return -ENXIO; + } + if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) { if (cxld->interleave_ways != iw || cxld->interleave_granularity != ig || @@ -1217,6 +1320,15 @@ static int cxl_port_setup_targets(struct cxl_port *port, return -ENXIO; } } else { + rc = check_interleave_cap(cxld, iw, ig); + if (rc) { + dev_dbg(&cxlr->dev, + "%s:%s iw: %d ig: %d is not supported\n", + dev_name(port->uport_dev), + dev_name(&port->dev), iw, ig); + return rc; + } + cxld->interleave_ways = iw; cxld->interleave_granularity = ig; cxld->hpa_range = (struct range) { @@ -1416,10 +1528,13 @@ static int cxl_region_attach_position(struct cxl_region *cxlr, const struct cxl_dport *dport, int pos) { struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct cxl_switch_decoder *cxlsd = &cxlrd->cxlsd; + struct cxl_decoder *cxld = &cxlsd->cxld; + int iw = cxld->interleave_ways; struct cxl_port *iter; int rc; - if (cxlrd->calc_hb(cxlrd, pos) != dport) { + if (dport != cxlrd->cxlsd.target[pos % iw]) { dev_dbg(&cxlr->dev, "%s:%s invalid target position for %s\n", dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev), dev_name(&cxlrd->cxlsd.cxld.dev)); @@ -1480,6 +1595,14 @@ static int cxl_region_attach_auto(struct cxl_region *cxlr, return 0; } +static int cmp_interleave_pos(const void *a, const void *b) +{ + struct cxl_endpoint_decoder *cxled_a = *(typeof(cxled_a) *)a; + struct cxl_endpoint_decoder *cxled_b = *(typeof(cxled_b) *)b; + + return cxled_a->pos - cxled_b->pos; +} + static struct cxl_port *next_port(struct cxl_port *port) { if (!port->parent_dport) @@ -1487,119 +1610,127 @@ static struct cxl_port *next_port(struct cxl_port *port) return port->parent_dport->port; } -static int decoder_match_range(struct device *dev, void *data) +static int match_switch_decoder_by_range(struct device *dev, void *data) { - struct cxl_endpoint_decoder *cxled = data; struct cxl_switch_decoder *cxlsd; + struct range *r1, *r2 = data; if (!is_switch_decoder(dev)) return 0; cxlsd = to_cxl_switch_decoder(dev); - return range_contains(&cxlsd->cxld.hpa_range, &cxled->cxld.hpa_range); -} + r1 = &cxlsd->cxld.hpa_range; -static void find_positions(const struct cxl_switch_decoder *cxlsd, - const struct cxl_port *iter_a, - const struct cxl_port *iter_b, int *a_pos, - int *b_pos) -{ - int i; - - for (i = 0, *a_pos = -1, *b_pos = -1; i < cxlsd->nr_targets; i++) { - if (cxlsd->target[i] == iter_a->parent_dport) - *a_pos = i; - else if (cxlsd->target[i] == iter_b->parent_dport) - *b_pos = i; - if (*a_pos >= 0 && *b_pos >= 0) - break; - } + if (is_root_decoder(dev)) + return range_contains(r1, r2); + return (r1->start == r2->start && r1->end == r2->end); } -static int cmp_decode_pos(const void *a, const void *b) +static int find_pos_and_ways(struct cxl_port *port, struct range *range, + int *pos, int *ways) { - struct cxl_endpoint_decoder *cxled_a = *(typeof(cxled_a) *)a; - struct cxl_endpoint_decoder *cxled_b = *(typeof(cxled_b) *)b; - struct cxl_memdev *cxlmd_a = cxled_to_memdev(cxled_a); - struct cxl_memdev *cxlmd_b = cxled_to_memdev(cxled_b); - struct cxl_port *port_a = cxled_to_port(cxled_a); - struct cxl_port *port_b = cxled_to_port(cxled_b); - struct cxl_port *iter_a, *iter_b, *port = NULL; struct cxl_switch_decoder *cxlsd; + struct cxl_port *parent; struct device *dev; - int a_pos, b_pos; - unsigned int seq; - - /* Exit early if any prior sorting failed */ - if (cxled_a->pos < 0 || cxled_b->pos < 0) - return 0; + int rc = -ENXIO; - /* - * Walk up the hierarchy to find a shared port, find the decoder that - * maps the range, compare the relative position of those dport - * mappings. - */ - for (iter_a = port_a; iter_a; iter_a = next_port(iter_a)) { - struct cxl_port *next_a, *next_b; + parent = next_port(port); + if (!parent) + return rc; - next_a = next_port(iter_a); - if (!next_a) - break; + dev = device_find_child(&parent->dev, range, + match_switch_decoder_by_range); + if (!dev) { + dev_err(port->uport_dev, + "failed to find decoder mapping %#llx-%#llx\n", + range->start, range->end); + return rc; + } + cxlsd = to_cxl_switch_decoder(dev); + *ways = cxlsd->cxld.interleave_ways; - for (iter_b = port_b; iter_b; iter_b = next_port(iter_b)) { - next_b = next_port(iter_b); - if (next_a != next_b) - continue; - port = next_a; + for (int i = 0; i < *ways; i++) { + if (cxlsd->target[i] == port->parent_dport) { + *pos = i; + rc = 0; break; } - - if (port) - break; } + put_device(dev); - if (!port) { - dev_err(cxlmd_a->dev.parent, - "failed to find shared port with %s\n", - dev_name(cxlmd_b->dev.parent)); - goto err; - } + return rc; +} - dev = device_find_child(&port->dev, cxled_a, decoder_match_range); - if (!dev) { - struct range *range = &cxled_a->cxld.hpa_range; +/** + * cxl_calc_interleave_pos() - calculate an endpoint position in a region + * @cxled: endpoint decoder member of given region + * + * The endpoint position is calculated by traversing the topology from + * the endpoint to the root decoder and iteratively applying this + * calculation: + * + * position = position * parent_ways + parent_pos; + * + * ...where @position is inferred from switch and root decoder target lists. + * + * Return: position >= 0 on success + * -ENXIO on failure + */ +static int cxl_calc_interleave_pos(struct cxl_endpoint_decoder *cxled) +{ + struct cxl_port *iter, *port = cxled_to_port(cxled); + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct range *range = &cxled->cxld.hpa_range; + int parent_ways = 0, parent_pos = 0, pos = 0; + int rc; - dev_err(port->uport_dev, - "failed to find decoder that maps %#llx-%#llx\n", - range->start, range->end); - goto err; - } + /* + * Example: the expected interleave order of the 4-way region shown + * below is: mem0, mem2, mem1, mem3 + * + * root_port + * / \ + * host_bridge_0 host_bridge_1 + * | | | | + * mem0 mem1 mem2 mem3 + * + * In the example the calculator will iterate twice. The first iteration + * uses the mem position in the host-bridge and the ways of the host- + * bridge to generate the first, or local, position. The second + * iteration uses the host-bridge position in the root_port and the ways + * of the root_port to refine the position. + * + * A trace of the calculation per endpoint looks like this: + * mem0: pos = 0 * 2 + 0 mem2: pos = 0 * 2 + 0 + * pos = 0 * 2 + 0 pos = 0 * 2 + 1 + * pos: 0 pos: 1 + * + * mem1: pos = 0 * 2 + 1 mem3: pos = 0 * 2 + 1 + * pos = 1 * 2 + 0 pos = 1 * 2 + 1 + * pos: 2 pos = 3 + * + * Note that while this example is simple, the method applies to more + * complex topologies, including those with switches. + */ - cxlsd = to_cxl_switch_decoder(dev); - do { - seq = read_seqbegin(&cxlsd->target_lock); - find_positions(cxlsd, iter_a, iter_b, &a_pos, &b_pos); - } while (read_seqretry(&cxlsd->target_lock, seq)); + /* Iterate from endpoint to root_port refining the position */ + for (iter = port; iter; iter = next_port(iter)) { + if (is_cxl_root(iter)) + break; - put_device(dev); + rc = find_pos_and_ways(iter, range, &parent_pos, &parent_ways); + if (rc) + return rc; - if (a_pos < 0 || b_pos < 0) { - dev_err(port->uport_dev, - "failed to find shared decoder for %s and %s\n", - dev_name(cxlmd_a->dev.parent), - dev_name(cxlmd_b->dev.parent)); - goto err; + pos = pos * parent_ways + parent_pos; } - dev_dbg(port->uport_dev, "%s comes %s %s\n", - dev_name(cxlmd_a->dev.parent), - a_pos - b_pos < 0 ? "before" : "after", - dev_name(cxlmd_b->dev.parent)); + dev_dbg(&cxlmd->dev, + "decoder:%s parent:%s port:%s range:%#llx-%#llx pos:%d\n", + dev_name(&cxled->cxld.dev), dev_name(cxlmd->dev.parent), + dev_name(&port->dev), range->start, range->end, pos); - return a_pos - b_pos; -err: - cxled_a->pos = -1; - return 0; + return pos; } static int cxl_region_sort_targets(struct cxl_region *cxlr) @@ -1607,22 +1738,21 @@ static int cxl_region_sort_targets(struct cxl_region *cxlr) struct cxl_region_params *p = &cxlr->params; int i, rc = 0; - sort(p->targets, p->nr_targets, sizeof(p->targets[0]), cmp_decode_pos, - NULL); - for (i = 0; i < p->nr_targets; i++) { struct cxl_endpoint_decoder *cxled = p->targets[i]; + cxled->pos = cxl_calc_interleave_pos(cxled); /* - * Record that sorting failed, but still continue to restore - * cxled->pos with its ->targets[] position so that follow-on - * code paths can reliably do p->targets[cxled->pos] to - * self-reference their entry. + * Record that sorting failed, but still continue to calc + * cxled->pos so that follow-on code paths can reliably + * do p->targets[cxled->pos] to self-reference their entry. */ if (cxled->pos < 0) rc = -ENXIO; - cxled->pos = i; } + /* Keep the cxlr target list in interleave position order */ + sort(p->targets, p->nr_targets, sizeof(p->targets[0]), + cmp_interleave_pos, NULL); dev_dbg(&cxlr->dev, "region sort %s\n", rc ? "failed" : "successful"); return rc; @@ -1638,6 +1768,15 @@ static int cxl_region_attach(struct cxl_region *cxlr, struct cxl_dport *dport; int rc = -ENXIO; + rc = check_interleave_cap(&cxled->cxld, p->interleave_ways, + p->interleave_granularity); + if (rc) { + dev_dbg(&cxlr->dev, "%s iw: %d ig: %d is not supported\n", + dev_name(&cxled->cxld.dev), p->interleave_ways, + p->interleave_granularity); + return rc; + } + if (cxled->mode != cxlr->mode) { dev_dbg(&cxlr->dev, "%s region mode: %d mismatch: %d\n", dev_name(&cxled->cxld.dev), cxlr->mode, cxled->mode); @@ -1658,6 +1797,12 @@ static int cxl_region_attach(struct cxl_region *cxlr, return -ENXIO; } + if (p->nr_targets >= p->interleave_ways) { + dev_dbg(&cxlr->dev, "region already has %d endpoints\n", + p->nr_targets); + return -EINVAL; + } + ep_port = cxled_to_port(cxled); root_port = cxlrd_to_port(cxlrd); dport = cxl_find_dport_by_dev(root_port, ep_port->host_bridge); @@ -1750,7 +1895,7 @@ static int cxl_region_attach(struct cxl_region *cxlr, if (p->nr_targets == p->interleave_ways) { rc = cxl_region_setup_targets(cxlr); if (rc) - goto err_decrement; + return rc; p->state = CXL_CONFIG_ACTIVE; } @@ -1761,13 +1906,27 @@ static int cxl_region_attach(struct cxl_region *cxlr, .end = p->res->end, }; - return 0; + if (p->nr_targets != p->interleave_ways) + return 0; -err_decrement: - p->nr_targets--; - cxled->pos = -1; - p->targets[pos] = NULL; - return rc; + /* + * Test the auto-discovery position calculator function + * against this successfully created user-defined region. + * A fail message here means that this interleave config + * will fail when presented as CXL_REGION_F_AUTO. + */ + for (int i = 0; i < p->nr_targets; i++) { + struct cxl_endpoint_decoder *cxled = p->targets[i]; + int test_pos; + + test_pos = cxl_calc_interleave_pos(cxled); + dev_dbg(&cxled->cxld.dev, + "Test cxl_calc_interleave_pos(): %s test_pos:%d cxled->pos:%d\n", + (test_pos == cxled->pos) ? "success" : "fail", + test_pos, cxled->pos); + } + + return 0; } static int cxl_region_detach(struct cxl_endpoint_decoder *cxled) @@ -2112,15 +2271,6 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd, struct device *dev; int rc; - switch (mode) { - case CXL_DECODER_RAM: - case CXL_DECODER_PMEM: - break; - default: - dev_err(&cxlrd->cxlsd.cxld.dev, "unsupported mode %d\n", mode); - return ERR_PTR(-EINVAL); - } - cxlr = cxl_region_alloc(cxlrd, id); if (IS_ERR(cxlr)) return cxlr; @@ -2171,6 +2321,15 @@ static struct cxl_region *__create_region(struct cxl_root_decoder *cxlrd, { int rc; + switch (mode) { + case CXL_DECODER_RAM: + case CXL_DECODER_PMEM: + break; + default: + dev_err(&cxlrd->cxlsd.cxld.dev, "unsupported mode %d\n", mode); + return ERR_PTR(-EINVAL); + } + rc = memregion_alloc(GFP_KERNEL); if (rc < 0) return ERR_PTR(rc); @@ -2423,10 +2582,6 @@ int cxl_get_poison_by_endpoint(struct cxl_port *port) struct cxl_poison_context ctx; int rc = 0; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) - return rc; - ctx = (struct cxl_poison_context) { .port = port }; @@ -2436,10 +2591,64 @@ int cxl_get_poison_by_endpoint(struct cxl_port *port) rc = cxl_get_poison_unmapped(to_cxl_memdev(port->uport_dev), &ctx); - up_read(&cxl_region_rwsem); return rc; } +struct cxl_dpa_to_region_context { + struct cxl_region *cxlr; + u64 dpa; +}; + +static int __cxl_dpa_to_region(struct device *dev, void *arg) +{ + struct cxl_dpa_to_region_context *ctx = arg; + struct cxl_endpoint_decoder *cxled; + struct cxl_region *cxlr; + u64 dpa = ctx->dpa; + + if (!is_endpoint_decoder(dev)) + return 0; + + cxled = to_cxl_endpoint_decoder(dev); + if (!cxled || !cxled->dpa_res || !resource_size(cxled->dpa_res)) + return 0; + + if (dpa > cxled->dpa_res->end || dpa < cxled->dpa_res->start) + return 0; + + /* + * Stop the region search (return 1) when an endpoint mapping is + * found. The region may not be fully constructed so offering + * the cxlr in the context structure is not guaranteed. + */ + cxlr = cxled->cxld.region; + if (cxlr) + dev_dbg(dev, "dpa:0x%llx mapped in region:%s\n", dpa, + dev_name(&cxlr->dev)); + else + dev_dbg(dev, "dpa:0x%llx mapped in endpoint:%s\n", dpa, + dev_name(dev)); + + ctx->cxlr = cxlr; + + return 1; +} + +struct cxl_region *cxl_dpa_to_region(const struct cxl_memdev *cxlmd, u64 dpa) +{ + struct cxl_dpa_to_region_context ctx; + struct cxl_port *port; + + ctx = (struct cxl_dpa_to_region_context) { + .dpa = dpa, + }; + port = cxlmd->endpoint; + if (port && is_cxl_endpoint(port) && cxl_num_decoders_committed(port)) + device_for_each_child(&port->dev, &ctx, __cxl_dpa_to_region); + + return ctx.cxlr; +} + static struct lock_class_key cxl_pmem_region_key; static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr) @@ -2480,6 +2689,7 @@ static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr) if (i == 0) { cxl_nvb = cxl_find_nvdimm_bridge(cxlmd); if (!cxl_nvb) { + kfree(cxlr_pmem); cxlr_pmem = ERR_PTR(-ENODEV); goto out; } @@ -2696,7 +2906,7 @@ static int devm_cxl_add_dax_region(struct cxl_region *cxlr) return rc; } -static int match_decoder_by_range(struct device *dev, void *data) +static int match_root_decoder_by_range(struct device *dev, void *data) { struct range *r1, *r2 = data; struct cxl_root_decoder *cxlrd; @@ -2827,7 +3037,7 @@ int cxl_add_to_region(struct cxl_port *root, struct cxl_endpoint_decoder *cxled) int rc; cxlrd_dev = device_find_child(&root->dev, &cxld->hpa_range, - match_decoder_by_range); + match_root_decoder_by_range); if (!cxlrd_dev) { dev_err(cxlmd->dev.parent, "%s:%s no CXL window for range %#llx:%#llx\n", diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c index 6281127b3e9d97..bab4592db647f7 100644 --- a/drivers/cxl/core/regs.c +++ b/drivers/cxl/core/regs.c @@ -204,7 +204,7 @@ int cxl_map_component_regs(const struct cxl_register_map *map, struct cxl_component_regs *regs, unsigned long map_mask) { - struct device *dev = map->dev; + struct device *host = map->host; struct mapinfo { const struct cxl_reg_map *rmap; void __iomem **addr; @@ -225,7 +225,7 @@ int cxl_map_component_regs(const struct cxl_register_map *map, continue; phys_addr = map->resource + mi->rmap->offset; length = mi->rmap->size; - *(mi->addr) = devm_cxl_iomap_block(dev, phys_addr, length); + *(mi->addr) = devm_cxl_iomap_block(host, phys_addr, length); if (!*(mi->addr)) return -ENOMEM; } @@ -237,7 +237,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_map_component_regs, CXL); int cxl_map_device_regs(const struct cxl_register_map *map, struct cxl_device_regs *regs) { - struct device *dev = map->dev; + struct device *host = map->host; resource_size_t phys_addr = map->resource; struct mapinfo { const struct cxl_reg_map *rmap; @@ -259,7 +259,7 @@ int cxl_map_device_regs(const struct cxl_register_map *map, addr = phys_addr + mi->rmap->offset; length = mi->rmap->size; - *(mi->addr) = devm_cxl_iomap_block(dev, addr, length); + *(mi->addr) = devm_cxl_iomap_block(host, addr, length); if (!*(mi->addr)) return -ENOMEM; } @@ -271,6 +271,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_map_device_regs, CXL); static bool cxl_decode_regblock(struct pci_dev *pdev, u32 reg_lo, u32 reg_hi, struct cxl_register_map *map) { + u8 reg_type = FIELD_GET(CXL_DVSEC_REG_LOCATOR_BLOCK_ID_MASK, reg_lo); int bar = FIELD_GET(CXL_DVSEC_REG_LOCATOR_BIR_MASK, reg_lo); u64 offset = ((u64)reg_hi << 32) | (reg_lo & CXL_DVSEC_REG_LOCATOR_BLOCK_OFF_LOW_MASK); @@ -278,11 +279,11 @@ static bool cxl_decode_regblock(struct pci_dev *pdev, u32 reg_lo, u32 reg_hi, if (offset > pci_resource_len(pdev, bar)) { dev_warn(&pdev->dev, "BAR%d: %pr: too small (offset: %pa, type: %d)\n", bar, - &pdev->resource[bar], &offset, map->reg_type); + &pdev->resource[bar], &offset, reg_type); return false; } - map->reg_type = FIELD_GET(CXL_DVSEC_REG_LOCATOR_BLOCK_ID_MASK, reg_lo); + map->reg_type = reg_type; map->resource = pci_resource_start(pdev, bar) + offset; map->max_size = pci_resource_len(pdev, bar) - offset; return true; @@ -309,7 +310,7 @@ int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type, int regloc, i; *map = (struct cxl_register_map) { - .dev = &pdev->dev, + .host = &pdev->dev, .resource = CXL_RESOURCE_NONE, }; @@ -403,15 +404,15 @@ EXPORT_SYMBOL_NS_GPL(cxl_map_pmu_regs, CXL); static int cxl_map_regblock(struct cxl_register_map *map) { - struct device *dev = map->dev; + struct device *host = map->host; map->base = ioremap(map->resource, map->max_size); if (!map->base) { - dev_err(dev, "failed to map registers\n"); + dev_err(host, "failed to map registers\n"); return -ENOMEM; } - dev_dbg(dev, "Mapped CXL Memory Device resource %pa\n", &map->resource); + dev_dbg(host, "Mapped CXL Memory Device resource %pa\n", &map->resource); return 0; } @@ -425,28 +426,28 @@ static int cxl_probe_regs(struct cxl_register_map *map) { struct cxl_component_reg_map *comp_map; struct cxl_device_reg_map *dev_map; - struct device *dev = map->dev; + struct device *host = map->host; void __iomem *base = map->base; switch (map->reg_type) { case CXL_REGLOC_RBI_COMPONENT: comp_map = &map->component_map; - cxl_probe_component_regs(dev, base, comp_map); - dev_dbg(dev, "Set up component registers\n"); + cxl_probe_component_regs(host, base, comp_map); + dev_dbg(host, "Set up component registers\n"); break; case CXL_REGLOC_RBI_MEMDEV: dev_map = &map->device_map; - cxl_probe_device_regs(dev, base, dev_map); + cxl_probe_device_regs(host, base, dev_map); if (!dev_map->status.valid || !dev_map->mbox.valid || !dev_map->memdev.valid) { - dev_err(dev, "registers not found: %s%s%s\n", + dev_err(host, "registers not found: %s%s%s\n", !dev_map->status.valid ? "status " : "", !dev_map->mbox.valid ? "mbox " : "", !dev_map->memdev.valid ? "memdev " : ""); return -ENXIO; } - dev_dbg(dev, "Probing device registers...\n"); + dev_dbg(host, "Probing device registers...\n"); break; default: break; diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index a0b5819bc70b30..bdf24867d5174c 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -252,8 +252,8 @@ TRACE_EVENT(cxl_generic_event, * DRAM Event Record * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44 */ -#define CXL_DPA_FLAGS_MASK 0x3F -#define CXL_DPA_MASK (~CXL_DPA_FLAGS_MASK) +#define CXL_DPA_FLAGS_MASK GENMASK(1, 0) +#define CXL_DPA_MASK GENMASK_ULL(63, 6) #define CXL_DPA_VOLATILE BIT(0) #define CXL_DPA_NOT_REPAIRABLE BIT(1) @@ -642,18 +642,18 @@ u64 cxl_trace_hpa(struct cxl_region *cxlr, struct cxl_memdev *memdev, u64 dpa); TRACE_EVENT(cxl_poison, - TP_PROTO(struct cxl_memdev *cxlmd, struct cxl_region *region, + TP_PROTO(struct cxl_memdev *cxlmd, struct cxl_region *cxlr, const struct cxl_poison_record *record, u8 flags, __le64 overflow_ts, enum cxl_poison_trace_type trace_type), - TP_ARGS(cxlmd, region, record, flags, overflow_ts, trace_type), + TP_ARGS(cxlmd, cxlr, record, flags, overflow_ts, trace_type), TP_STRUCT__entry( __string(memdev, dev_name(&cxlmd->dev)) __string(host, dev_name(cxlmd->dev.parent)) __field(u64, serial) __field(u8, trace_type) - __string(region, region) + __string(region, cxlr ? dev_name(&cxlr->dev) : "") __field(u64, overflow_ts) __field(u64, hpa) __field(u64, dpa) @@ -673,10 +673,10 @@ TRACE_EVENT(cxl_poison, __entry->source = cxl_poison_record_source(record); __entry->trace_type = trace_type; __entry->flags = flags; - if (region) { - __assign_str(region, dev_name(®ion->dev)); - memcpy(__entry->uuid, ®ion->params.uuid, 16); - __entry->hpa = cxl_trace_hpa(region, cxlmd, + if (cxlr) { + __assign_str(region, dev_name(&cxlr->dev)); + memcpy(__entry->uuid, &cxlr->params.uuid, 16); + __entry->hpa = cxl_trace_hpa(cxlr, cxlmd, __entry->dpa); } else { __assign_str(region, ""); diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 76d92561af2949..bb3ad219b6b316 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -43,6 +43,8 @@ #define CXL_HDM_DECODER_TARGET_COUNT_MASK GENMASK(7, 4) #define CXL_HDM_DECODER_INTERLEAVE_11_8 BIT(8) #define CXL_HDM_DECODER_INTERLEAVE_14_12 BIT(9) +#define CXL_HDM_DECODER_INTERLEAVE_3_6_12_WAY BIT(11) +#define CXL_HDM_DECODER_INTERLEAVE_16_WAY BIT(12) #define CXL_HDM_DECODER_CTRL_OFFSET 0x4 #define CXL_HDM_DECODER_ENABLE BIT(1) #define CXL_HDM_DECODER0_BASE_LOW_OFFSET(i) (0x20 * (i) + 0x10) @@ -247,7 +249,7 @@ struct cxl_pmu_reg_map { /** * struct cxl_register_map - DVSEC harvested register block mapping parameters - * @dev: device for devm operations and logging + * @host: device for devm operations and logging * @base: virtual base of the register-block-BAR + @block_offset * @resource: physical resource base of the register block * @max_size: maximum mapping size to perform register search @@ -257,7 +259,7 @@ struct cxl_pmu_reg_map { * @pmu_map: cxl_reg_maps for CXL Performance Monitoring Units */ struct cxl_register_map { - struct device *dev; + struct device *host; void __iomem *base; resource_size_t resource; resource_size_t max_size; @@ -404,7 +406,6 @@ struct cxl_endpoint_decoder { /** * struct cxl_switch_decoder - Switch specific CXL HDM Decoder * @cxld: base cxl_decoder object - * @target_lock: coordinate coherent reads of the target list * @nr_targets: number of elements in @target * @target: active ordered target list in current decoder configuration * @@ -416,7 +417,6 @@ struct cxl_endpoint_decoder { */ struct cxl_switch_decoder { struct cxl_decoder cxld; - seqlock_t target_lock; int nr_targets; struct cxl_dport *target[]; }; @@ -679,6 +679,7 @@ static inline bool is_cxl_root(struct cxl_port *port) return port->uport_dev == port->dev.parent; } +int cxl_num_decoders_committed(struct cxl_port *port); bool is_cxl_port(const struct device *dev); struct cxl_port *to_cxl_port(const struct device *dev); struct pci_bus; diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 706f8a6d1ef43c..edb46123e3eb0f 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -84,9 +84,12 @@ static inline bool is_cxl_endpoint(struct cxl_port *port) return is_cxl_memdev(port->uport_dev); } -struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds); +struct cxl_memdev *devm_cxl_add_memdev(struct device *host, + struct cxl_dev_state *cxlds); +int devm_cxl_sanitize_setup_notifier(struct device *host, + struct cxl_memdev *cxlmd); struct cxl_memdev_state; -int cxl_memdev_setup_fw_upload(struct cxl_memdev_state *mds); +int devm_cxl_setup_fw_upload(struct device *host, struct cxl_memdev_state *mds); int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, resource_size_t base, resource_size_t len, resource_size_t skipped); @@ -360,16 +363,16 @@ struct cxl_fw_state { * * @state: state of last security operation * @enabled_cmds: All security commands enabled in the CEL - * @poll: polling for sanitization is enabled, device has no mbox irq support * @poll_tmo_secs: polling timeout + * @sanitize_active: sanitize completion pending * @poll_dwork: polling work item * @sanitize_node: sanitation sysfs file to notify */ struct cxl_security_state { unsigned long state; DECLARE_BITMAP(enabled_cmds, CXL_SEC_ENABLED_MAX); - bool poll; int poll_tmo_secs; + bool sanitize_active; struct delayed_work poll_dwork; struct kernfs_node *sanitize_node; }; @@ -535,7 +538,7 @@ enum cxl_opcode { 0x3b, 0x3f, 0x17) #define DEFINE_CXL_VENDOR_DEBUG_UUID \ - UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f, 0xd6, 0x07, 0x19, \ + UUID_INIT(0x5e1819d9, 0x11a9, 0x400c, 0x81, 0x1f, 0xd6, 0x07, 0x19, \ 0x40, 0x3d, 0x86) struct cxl_mbox_get_supported_logs { @@ -883,13 +886,23 @@ static inline void cxl_mem_active_dec(void) } #endif -int cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd); +int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd); +/** + * struct cxl_hdm - HDM Decoder registers and cached / decoded capabilities + * @regs: mapped registers, see devm_cxl_setup_hdm() + * @decoder_count: number of decoders for this port + * @target_count: for switch decoders, max downstream port targets + * @interleave_mask: interleave granularity capability, see check_interleave_cap() + * @iw_cap_mask: bitmask of supported interleave ways, see check_interleave_cap() + * @port: mapped cxl_port, see devm_cxl_setup_hdm() + */ struct cxl_hdm { struct cxl_component_regs regs; unsigned int decoder_count; unsigned int target_count; unsigned int interleave_mask; + unsigned long iw_cap_mask; struct cxl_port *port; }; diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 44a21ab7add51b..8bece1e2e2491d 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -128,10 +128,10 @@ static irqreturn_t cxl_pci_mbox_irq(int irq, void *id) reg = readq(cxlds->regs.mbox + CXLDEV_MBOX_BG_CMD_STATUS_OFFSET); opcode = FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_OPCODE_MASK, reg); if (opcode == CXL_MBOX_OP_SANITIZE) { + mutex_lock(&mds->mbox_mutex); if (mds->security.sanitize_node) - sysfs_notify_dirent(mds->security.sanitize_node); - - dev_dbg(cxlds->dev, "Sanitization operation ended\n"); + mod_delayed_work(system_wq, &mds->security.poll_dwork, 0); + mutex_unlock(&mds->mbox_mutex); } else { /* short-circuit the wait in __cxl_pci_mbox_send_cmd() */ rcuwait_wake_up(&mds->mbox_wait); @@ -152,18 +152,16 @@ static void cxl_mbox_sanitize_work(struct work_struct *work) mutex_lock(&mds->mbox_mutex); if (cxl_mbox_background_complete(cxlds)) { mds->security.poll_tmo_secs = 0; - put_device(cxlds->dev); - if (mds->security.sanitize_node) sysfs_notify_dirent(mds->security.sanitize_node); + mds->security.sanitize_active = false; dev_dbg(cxlds->dev, "Sanitization operation ended\n"); } else { int timeout = mds->security.poll_tmo_secs + 10; mds->security.poll_tmo_secs = min(15 * 60, timeout); - queue_delayed_work(system_wq, &mds->security.poll_dwork, - timeout * HZ); + schedule_delayed_work(&mds->security.poll_dwork, timeout * HZ); } mutex_unlock(&mds->mbox_mutex); } @@ -295,18 +293,15 @@ static int __cxl_pci_mbox_send_cmd(struct cxl_memdev_state *mds, * and allow userspace to poll(2) for completion. */ if (mbox_cmd->opcode == CXL_MBOX_OP_SANITIZE) { - if (mds->security.poll) { - /* hold the device throughout */ - get_device(cxlds->dev); - - /* give first timeout a second */ - timeout = 1; - mds->security.poll_tmo_secs = timeout; - queue_delayed_work(system_wq, - &mds->security.poll_dwork, - timeout * HZ); - } - + if (mds->security.sanitize_active) + return -EBUSY; + + /* give first timeout a second */ + timeout = 1; + mds->security.poll_tmo_secs = timeout; + mds->security.sanitize_active = true; + schedule_delayed_work(&mds->security.poll_dwork, + timeout * HZ); dev_dbg(dev, "Sanitization operation started\n"); goto success; } @@ -389,7 +384,9 @@ static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds) const int cap = readl(cxlds->regs.mbox + CXLDEV_MBOX_CAPS_OFFSET); struct device *dev = cxlds->dev; unsigned long timeout; + int irq, msgnum; u64 md_status; + u32 ctrl; timeout = jiffies + mbox_ready_timeout * HZ; do { @@ -437,33 +434,26 @@ static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds) dev_dbg(dev, "Mailbox payload sized %zu", mds->payload_size); rcuwait_init(&mds->mbox_wait); + INIT_DELAYED_WORK(&mds->security.poll_dwork, cxl_mbox_sanitize_work); - if (cap & CXLDEV_MBOX_CAP_BG_CMD_IRQ) { - u32 ctrl; - int irq, msgnum; - struct pci_dev *pdev = to_pci_dev(cxlds->dev); - - msgnum = FIELD_GET(CXLDEV_MBOX_CAP_IRQ_MSGNUM_MASK, cap); - irq = pci_irq_vector(pdev, msgnum); - if (irq < 0) - goto mbox_poll; - - if (cxl_request_irq(cxlds, irq, cxl_pci_mbox_irq, NULL)) - goto mbox_poll; + /* background command interrupts are optional */ + if (!(cap & CXLDEV_MBOX_CAP_BG_CMD_IRQ)) + return 0; - /* enable background command mbox irq support */ - ctrl = readl(cxlds->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET); - ctrl |= CXLDEV_MBOX_CTRL_BG_CMD_IRQ; - writel(ctrl, cxlds->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET); + msgnum = FIELD_GET(CXLDEV_MBOX_CAP_IRQ_MSGNUM_MASK, cap); + irq = pci_irq_vector(to_pci_dev(cxlds->dev), msgnum); + if (irq < 0) + return 0; + if (cxl_request_irq(cxlds, irq, NULL, cxl_pci_mbox_irq)) return 0; - } -mbox_poll: - mds->security.poll = true; - INIT_DELAYED_WORK(&mds->security.poll_dwork, cxl_mbox_sanitize_work); + dev_dbg(cxlds->dev, "Mailbox interrupts enabled\n"); + /* enable background command mbox irq support */ + ctrl = readl(cxlds->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET); + ctrl |= CXLDEV_MBOX_CTRL_BG_CMD_IRQ; + writel(ctrl, cxlds->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET); - dev_dbg(cxlds->dev, "Mailbox interrupts are unsupported"); return 0; } @@ -484,7 +474,7 @@ static int cxl_rcrb_get_comp_regs(struct pci_dev *pdev, resource_size_t component_reg_phys; *map = (struct cxl_register_map) { - .dev = &pdev->dev, + .host = &pdev->dev, .resource = CXL_RESOURCE_NONE, }; @@ -882,11 +872,15 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) return rc; - cxlmd = devm_cxl_add_memdev(cxlds); + cxlmd = devm_cxl_add_memdev(&pdev->dev, cxlds); if (IS_ERR(cxlmd)) return PTR_ERR(cxlmd); - rc = cxl_memdev_setup_fw_upload(mds); + rc = devm_cxl_setup_fw_upload(&pdev->dev, mds); + if (rc) + return rc; + + rc = devm_cxl_sanitize_setup_notifier(&pdev->dev, cxlmd); if (rc) return rc; diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 93ebedc5ec8ca3..01e89b7ac637f2 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -86,7 +86,7 @@ static void dax_set_mapping(struct vm_fault *vmf, pfn_t pfn, nr_pages = 1; pgoff = linear_page_index(vmf->vma, - ALIGN(vmf->address, fault_size)); + ALIGN_DOWN(vmf->address, fault_size)); for (i = 0; i < nr_pages; i++) { struct page *page = pfn_to_page(pfn_t_to_pfn(pfn) + i); diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 474d81831ad36b..49c542ecccde3b 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -461,10 +461,14 @@ static void devfreq_monitor(struct work_struct *work) if (err) dev_err(&devfreq->dev, "dvfs failed with (%d) error\n", err); + if (devfreq->stop_polling) + goto out; + queue_delayed_work(devfreq_wq, &devfreq->work, msecs_to_jiffies(devfreq->profile->polling_ms)); - mutex_unlock(&devfreq->lock); +out: + mutex_unlock(&devfreq->lock); trace_devfreq_monitor(devfreq); } @@ -483,6 +487,10 @@ void devfreq_monitor_start(struct devfreq *devfreq) if (IS_SUPPORTED_FLAG(devfreq->governor->flags, IRQ_DRIVEN)) return; + mutex_lock(&devfreq->lock); + if (delayed_work_pending(&devfreq->work)) + goto out; + switch (devfreq->profile->timer) { case DEVFREQ_TIMER_DEFERRABLE: INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor); @@ -491,12 +499,16 @@ void devfreq_monitor_start(struct devfreq *devfreq) INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor); break; default: - return; + goto out; } if (devfreq->profile->polling_ms) queue_delayed_work(devfreq_wq, &devfreq->work, msecs_to_jiffies(devfreq->profile->polling_ms)); + +out: + devfreq->stop_polling = false; + mutex_unlock(&devfreq->lock); } EXPORT_SYMBOL(devfreq_monitor_start); @@ -513,6 +525,14 @@ void devfreq_monitor_stop(struct devfreq *devfreq) if (IS_SUPPORTED_FLAG(devfreq->governor->flags, IRQ_DRIVEN)) return; + mutex_lock(&devfreq->lock); + if (devfreq->stop_polling) { + mutex_unlock(&devfreq->lock); + return; + } + + devfreq->stop_polling = true; + mutex_unlock(&devfreq->lock); cancel_delayed_work_sync(&devfreq->work); } EXPORT_SYMBOL(devfreq_monitor_stop); @@ -1688,7 +1708,7 @@ static ssize_t trans_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { struct devfreq *df = to_devfreq(dev); - ssize_t len; + ssize_t len = 0; int i, j; unsigned int max_state; @@ -1697,7 +1717,7 @@ static ssize_t trans_stat_show(struct device *dev, max_state = df->max_state; if (max_state == 0) - return sprintf(buf, "Not Supported.\n"); + return scnprintf(buf, PAGE_SIZE, "Not Supported.\n"); mutex_lock(&df->lock); if (!df->stop_polling && @@ -1707,31 +1727,52 @@ static ssize_t trans_stat_show(struct device *dev, } mutex_unlock(&df->lock); - len = sprintf(buf, " From : To\n"); - len += sprintf(buf + len, " :"); - for (i = 0; i < max_state; i++) - len += sprintf(buf + len, "%10lu", - df->freq_table[i]); + len += scnprintf(buf + len, PAGE_SIZE - len, " From : To\n"); + len += scnprintf(buf + len, PAGE_SIZE - len, " :"); + for (i = 0; i < max_state; i++) { + if (len >= PAGE_SIZE - 1) + break; + len += scnprintf(buf + len, PAGE_SIZE - len, "%10lu", + df->freq_table[i]); + } + if (len >= PAGE_SIZE - 1) + return PAGE_SIZE - 1; - len += sprintf(buf + len, " time(ms)\n"); + len += scnprintf(buf + len, PAGE_SIZE - len, " time(ms)\n"); for (i = 0; i < max_state; i++) { + if (len >= PAGE_SIZE - 1) + break; if (df->freq_table[i] == df->previous_freq) - len += sprintf(buf + len, "*"); + len += scnprintf(buf + len, PAGE_SIZE - len, "*"); else - len += sprintf(buf + len, " "); + len += scnprintf(buf + len, PAGE_SIZE - len, " "); + if (len >= PAGE_SIZE - 1) + break; + + len += scnprintf(buf + len, PAGE_SIZE - len, "%10lu:", + df->freq_table[i]); + for (j = 0; j < max_state; j++) { + if (len >= PAGE_SIZE - 1) + break; + len += scnprintf(buf + len, PAGE_SIZE - len, "%10u", + df->stats.trans_table[(i * max_state) + j]); + } + if (len >= PAGE_SIZE - 1) + break; + len += scnprintf(buf + len, PAGE_SIZE - len, "%10llu\n", (u64) + jiffies64_to_msecs(df->stats.time_in_state[i])); + } - len += sprintf(buf + len, "%10lu:", df->freq_table[i]); - for (j = 0; j < max_state; j++) - len += sprintf(buf + len, "%10u", - df->stats.trans_table[(i * max_state) + j]); + if (len < PAGE_SIZE - 1) + len += scnprintf(buf + len, PAGE_SIZE - len, "Total transition : %u\n", + df->stats.total_trans); - len += sprintf(buf + len, "%10llu\n", (u64) - jiffies64_to_msecs(df->stats.time_in_state[i])); + if (len >= PAGE_SIZE - 1) { + pr_warn_once("devfreq transition table exceeds PAGE_SIZE. Disabling\n"); + return -EFBIG; } - len += sprintf(buf + len, "Total transition : %u\n", - df->stats.total_trans); return len; } diff --git a/drivers/devfreq/event/rockchip-dfi.c b/drivers/devfreq/event/rockchip-dfi.c index 39ac069cabc756..74893c06aa087f 100644 --- a/drivers/devfreq/event/rockchip-dfi.c +++ b/drivers/devfreq/event/rockchip-dfi.c @@ -193,14 +193,15 @@ static int rockchip_dfi_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(data->clk), "Cannot get the clk pclk_ddr_mon\n"); - /* try to find the optional reference to the pmu syscon */ node = of_parse_phandle(np, "rockchip,pmu", 0); - if (node) { - data->regmap_pmu = syscon_node_to_regmap(node); - of_node_put(node); - if (IS_ERR(data->regmap_pmu)) - return PTR_ERR(data->regmap_pmu); - } + if (!node) + return dev_err_probe(&pdev->dev, -ENODEV, "Can't find pmu_grf registers\n"); + + data->regmap_pmu = syscon_node_to_regmap(node); + of_node_put(node); + if (IS_ERR(data->regmap_pmu)) + return PTR_ERR(data->regmap_pmu); + data->dev = dev; desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL); diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 38b4110378de05..eb8b733065b24d 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -301,7 +301,7 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence, dma_resv_list_entry(fobj, i, obj, &old, &old_usage); if ((old->context == fence->context && old_usage >= usage && - dma_fence_is_later(fence, old)) || + dma_fence_is_later_or_same(fence, old)) || dma_fence_is_signaled(old)) { dma_resv_list_set(fobj, i, fence, usage); dma_fence_put(old); diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c index ee899f8e67215f..bea7e574f916e1 100644 --- a/drivers/dma-buf/heaps/cma_heap.c +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -165,7 +165,7 @@ static vm_fault_t cma_heap_vm_fault(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct cma_heap_buffer *buffer = vma->vm_private_data; - if (vmf->pgoff > buffer->pagecount) + if (vmf->pgoff >= buffer->pagecount) return VM_FAULT_SIGBUS; vmf->page = buffer->pages[vmf->pgoff]; diff --git a/drivers/dma-buf/st-dma-fence-chain.c b/drivers/dma-buf/st-dma-fence-chain.c index c0979c8049b5a3..ed4b323886e430 100644 --- a/drivers/dma-buf/st-dma-fence-chain.c +++ b/drivers/dma-buf/st-dma-fence-chain.c @@ -84,11 +84,11 @@ static int sanitycheck(void *arg) return -ENOMEM; chain = mock_chain(NULL, f, 1); - if (!chain) + if (chain) + dma_fence_enable_sw_signaling(chain); + else err = -ENOMEM; - dma_fence_enable_sw_signaling(chain); - dma_fence_signal(f); dma_fence_put(f); @@ -476,10 +476,9 @@ static int find_race(void *arg) for (i = 0; i < ncpus; i++) { int ret; - ret = kthread_stop(threads[i]); + ret = kthread_stop_put(threads[i]); if (ret && !err) err = ret; - put_task_struct(threads[i]); } kfree(threads); @@ -591,8 +590,7 @@ static int wait_forward(void *arg) for (i = 0; i < fc.chain_length; i++) dma_fence_signal(fc.fences[i]); - err = kthread_stop(tsk); - put_task_struct(tsk); + err = kthread_stop_put(tsk); err: fence_chains_fini(&fc); @@ -621,8 +619,7 @@ static int wait_backward(void *arg) for (i = fc.chain_length; i--; ) dma_fence_signal(fc.fences[i]); - err = kthread_stop(tsk); - put_task_struct(tsk); + err = kthread_stop_put(tsk); err: fence_chains_fini(&fc); @@ -669,8 +666,7 @@ static int wait_random(void *arg) for (i = 0; i < fc.chain_length; i++) dma_fence_signal(fc.fences[i]); - err = kthread_stop(tsk); - put_task_struct(tsk); + err = kthread_stop_put(tsk); err: fence_chains_fini(&fc); diff --git a/drivers/dma-buf/st-dma-fence.c b/drivers/dma-buf/st-dma-fence.c index fb6e0a6ae2c96e..6a1bfcd0cc2108 100644 --- a/drivers/dma-buf/st-dma-fence.c +++ b/drivers/dma-buf/st-dma-fence.c @@ -540,6 +540,12 @@ static int race_signal_callback(void *arg) t[i].before = pass; t[i].task = kthread_run(thread_signal_callback, &t[i], "dma-fence:%d", i); + if (IS_ERR(t[i].task)) { + ret = PTR_ERR(t[i].task); + while (--i >= 0) + kthread_stop_put(t[i].task); + return ret; + } get_task_struct(t[i].task); } @@ -548,11 +554,9 @@ static int race_signal_callback(void *arg) for (i = 0; i < ARRAY_SIZE(t); i++) { int err; - err = kthread_stop(t[i].task); + err = kthread_stop_put(t[i].task); if (err && !ret) ret = err; - - put_task_struct(t[i].task); } } diff --git a/drivers/dma-buf/sync_debug.c b/drivers/dma-buf/sync_debug.c index 101394f16930f8..237bce21d1e724 100644 --- a/drivers/dma-buf/sync_debug.c +++ b/drivers/dma-buf/sync_debug.c @@ -110,12 +110,12 @@ static void sync_print_obj(struct seq_file *s, struct sync_timeline *obj) seq_printf(s, "%s: %d\n", obj->name, obj->value); - spin_lock_irq(&obj->lock); + spin_lock(&obj->lock); /* Caller already disabled IRQ. */ list_for_each(pos, &obj->pt_list) { struct sync_pt *pt = container_of(pos, struct sync_pt, link); sync_print_fence(s, &pt->base, false); } - spin_unlock_irq(&obj->lock); + spin_unlock(&obj->lock); } static void sync_print_sync_file(struct seq_file *s, diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 4ccae1a3b88427..e36506471a4f67 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -380,7 +380,7 @@ config LPC18XX_DMAMUX config MCF_EDMA tristate "Freescale eDMA engine support, ColdFire mcf5441x SoCs" - depends on M5441x || COMPILE_TEST + depends on M5441x || (COMPILE_TEST && FSL_EDMA=n) select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help @@ -629,16 +629,16 @@ config TEGRA20_APB_DMA config TEGRA210_ADMA tristate "NVIDIA Tegra210 ADMA support" - depends on (ARCH_TEGRA_210_SOC || COMPILE_TEST) + depends on (ARCH_TEGRA || COMPILE_TEST) select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help - Support for the NVIDIA Tegra210 ADMA controller driver. The - DMA controller has multiple DMA channels and is used to service - various audio clients in the Tegra210 audio processing engine - (APE). This DMA controller transfers data from memory to - peripheral and vice versa. It does not support memory to - memory data transfer. + Support for the NVIDIA Tegra210/Tegra186/Tegra194/Tegra234 ADMA + controller driver. The DMA controller has multiple DMA channels + and is used to service various audio clients in the Tegra210 + audio processing engine (APE). This DMA controller transfers + data from memory to peripheral and vice versa. It does not + support memory to memory data transfer. config TIMB_DMA tristate "Timberdale FPGA DMA support" diff --git a/drivers/dma/altera-msgdma.c b/drivers/dma/altera-msgdma.c index 4153c2edb04901..711e3756a39a52 100644 --- a/drivers/dma/altera-msgdma.c +++ b/drivers/dma/altera-msgdma.c @@ -233,7 +233,7 @@ static void msgdma_free_descriptor(struct msgdma_device *mdev, struct msgdma_sw_desc *child, *next; mdev->desc_free_cnt++; - list_add_tail(&desc->node, &mdev->free_list); + list_move_tail(&desc->node, &mdev->free_list); list_for_each_entry_safe(child, next, &desc->tx_list, node) { mdev->desc_free_cnt++; list_move_tail(&child->node, &mdev->free_list); @@ -583,17 +583,16 @@ static void msgdma_issue_pending(struct dma_chan *chan) static void msgdma_chan_desc_cleanup(struct msgdma_device *mdev) { struct msgdma_sw_desc *desc, *next; + unsigned long irqflags; list_for_each_entry_safe(desc, next, &mdev->done_list, node) { struct dmaengine_desc_callback cb; - list_del(&desc->node); - dmaengine_desc_get_callback(&desc->async_tx, &cb); if (dmaengine_desc_callback_valid(&cb)) { - spin_unlock(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, irqflags); dmaengine_desc_callback_invoke(&cb, NULL); - spin_lock(&mdev->lock); + spin_lock_irqsave(&mdev->lock, irqflags); } /* Run any dependencies, then free the descriptor */ diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c index 3af795635c5ce6..356298e4dd22b3 100644 --- a/drivers/dma/apple-admac.c +++ b/drivers/dma/apple-admac.c @@ -57,6 +57,8 @@ #define REG_BUS_WIDTH(ch) (0x8040 + (ch) * 0x200) +#define BUS_WIDTH_WORD_SIZE GENMASK(3, 0) +#define BUS_WIDTH_FRAME_SIZE GENMASK(7, 4) #define BUS_WIDTH_8BIT 0x00 #define BUS_WIDTH_16BIT 0x01 #define BUS_WIDTH_32BIT 0x02 @@ -740,7 +742,8 @@ static int admac_device_config(struct dma_chan *chan, struct admac_data *ad = adchan->host; bool is_tx = admac_chan_direction(adchan->no) == DMA_MEM_TO_DEV; int wordsize = 0; - u32 bus_width = 0; + u32 bus_width = readl_relaxed(ad->base + REG_BUS_WIDTH(adchan->no)) & + ~(BUS_WIDTH_WORD_SIZE | BUS_WIDTH_FRAME_SIZE); switch (is_tx ? config->dst_addr_width : config->src_addr_width) { case DMA_SLAVE_BUSWIDTH_1_BYTE: diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c index fc7cdad371616a..4f426be2868843 100644 --- a/drivers/dma/dma-axi-dmac.c +++ b/drivers/dma/dma-axi-dmac.c @@ -1033,8 +1033,8 @@ static int axi_dmac_remove(struct platform_device *pdev) { struct axi_dmac *dmac = platform_get_drvdata(pdev); - of_dma_controller_free(pdev->dev.of_node); free_irq(dmac->irq, dmac); + of_dma_controller_free(pdev->dev.of_node); tasklet_kill(&dmac->chan.vchan.task); dma_async_device_unregister(&dmac->dma_dev); clk_disable_unprepare(dmac->clk); diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index b7388ae62d7f1f..491b222402216a 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -1103,6 +1103,9 @@ EXPORT_SYMBOL_GPL(dma_async_device_channel_register); static void __dma_async_device_channel_unregister(struct dma_device *device, struct dma_chan *chan) { + if (chan->local == NULL) + return; + WARN_ONCE(!device->device_release && chan->client_count, "%s called while %d clients hold a reference\n", __func__, chan->client_count); diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c index dd02f84e404d08..72fb40de58b3f4 100644 --- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c +++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c @@ -256,6 +256,7 @@ static struct axi_dma_desc *axi_desc_alloc(u32 num) kfree(desc); return NULL; } + desc->nr_hw_descs = num; return desc; } @@ -282,7 +283,7 @@ static struct axi_dma_lli *axi_desc_get(struct axi_dma_chan *chan, static void axi_desc_put(struct axi_dma_desc *desc) { struct axi_dma_chan *chan = desc->chan; - int count = atomic_read(&chan->descs_allocated); + int count = desc->nr_hw_descs; struct axi_dma_hw_desc *hw_desc; int descs_put; @@ -1093,9 +1094,6 @@ static void axi_chan_block_xfer_complete(struct axi_dma_chan *chan) /* Remove the completed descriptor from issued list before completing */ list_del(&vd->node); vchan_cookie_complete(vd); - - /* Submit queued descriptors after processing the completed ones */ - axi_chan_start_first_queued(chan); } out: diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac.h b/drivers/dma/dw-axi-dmac/dw-axi-dmac.h index eb267cb24f6702..8521530a34ec46 100644 --- a/drivers/dma/dw-axi-dmac/dw-axi-dmac.h +++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac.h @@ -104,6 +104,7 @@ struct axi_dma_desc { u32 completed_blocks; u32 length; u32 period_len; + u32 nr_hw_descs; }; struct axi_dma_chan_config { diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c index b38786f0ad7995..b75fdaffad9a4e 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-core.c +++ b/drivers/dma/dw-edma/dw-edma-v0-core.c @@ -346,6 +346,20 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk) dw_edma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr); } +static void dw_edma_v0_sync_ll_data(struct dw_edma_chunk *chunk) +{ + /* + * In case of remote eDMA engine setup, the DW PCIe RP/EP internal + * configuration registers and application memory are normally accessed + * over different buses. Ensure LL-data reaches the memory before the + * doorbell register is toggled by issuing the dummy-read from the remote + * LL memory in a hope that the MRd TLP will return only after the + * last MWr TLP is completed + */ + if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL)) + readl(chunk->ll_region.vaddr.io); +} + static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) { struct dw_edma_chan *chan = chunk->chan; @@ -412,6 +426,9 @@ static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) SET_CH_32(dw, chan->dir, chan->id, llp.msb, upper_32_bits(chunk->ll_region.paddr)); } + + dw_edma_v0_sync_ll_data(chunk); + /* Doorbell */ SET_RW_32(dw, chan->dir, doorbell, FIELD_PREP(EDMA_V0_DOORBELL_CH_MASK, chan->id)); diff --git a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c index 0745d9e7d259b1..406f169b09a75a 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c +++ b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c @@ -176,7 +176,7 @@ dw_edma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent) }; struct dentry *regs_dent, *ch_dent; int nr_entries, i; - char name[16]; + char name[32]; regs_dent = debugfs_create_dir(WRITE_STR, dent); @@ -239,7 +239,7 @@ static noinline_for_stack void dw_edma_debugfs_regs_rd(struct dw_edma *dw, }; struct dentry *regs_dent, *ch_dent; int nr_entries, i; - char name[16]; + char name[32]; regs_dent = debugfs_create_dir(READ_STR, dent); diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c index 00b735a0202ab2..e3f8db4fe909a1 100644 --- a/drivers/dma/dw-edma/dw-hdma-v0-core.c +++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c @@ -17,8 +17,8 @@ enum dw_hdma_control { DW_HDMA_V0_CB = BIT(0), DW_HDMA_V0_TCB = BIT(1), DW_HDMA_V0_LLP = BIT(2), - DW_HDMA_V0_LIE = BIT(3), - DW_HDMA_V0_RIE = BIT(4), + DW_HDMA_V0_LWIE = BIT(3), + DW_HDMA_V0_RWIE = BIT(4), DW_HDMA_V0_CCS = BIT(8), DW_HDMA_V0_LLE = BIT(9), }; @@ -65,18 +65,12 @@ static void dw_hdma_v0_core_off(struct dw_edma *dw) static u16 dw_hdma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir) { - u32 num_ch = 0; - int id; - - for (id = 0; id < HDMA_V0_MAX_NR_CH; id++) { - if (GET_CH_32(dw, id, dir, ch_en) & BIT(0)) - num_ch++; - } - - if (num_ch > HDMA_V0_MAX_NR_CH) - num_ch = HDMA_V0_MAX_NR_CH; - - return (u16)num_ch; + /* + * The HDMA IP have no way to know the number of hardware channels + * available, we set it to maximum channels and let the platform + * set the right number of channels. + */ + return HDMA_V0_MAX_NR_CH; } static enum dma_status dw_hdma_v0_core_ch_status(struct dw_edma_chan *chan) @@ -201,25 +195,14 @@ static void dw_hdma_v0_write_ll_link(struct dw_edma_chunk *chunk, static void dw_hdma_v0_core_write_chunk(struct dw_edma_chunk *chunk) { struct dw_edma_burst *child; - struct dw_edma_chan *chan = chunk->chan; u32 control = 0, i = 0; - int j; if (chunk->cb) control = DW_HDMA_V0_CB; - j = chunk->bursts_alloc; - list_for_each_entry(child, &chunk->burst->list, list) { - j--; - if (!j) { - control |= DW_HDMA_V0_LIE; - if (!(chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL)) - control |= DW_HDMA_V0_RIE; - } - + list_for_each_entry(child, &chunk->burst->list, list) dw_hdma_v0_write_ll_data(chunk, i++, control, child->sz, child->sar, child->dar); - } control = DW_HDMA_V0_LLP | DW_HDMA_V0_TCB; if (!chunk->cb) @@ -228,6 +211,20 @@ static void dw_hdma_v0_core_write_chunk(struct dw_edma_chunk *chunk) dw_hdma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr); } +static void dw_hdma_v0_sync_ll_data(struct dw_edma_chunk *chunk) +{ + /* + * In case of remote HDMA engine setup, the DW PCIe RP/EP internal + * configuration registers and application memory are normally accessed + * over different buses. Ensure LL-data reaches the memory before the + * doorbell register is toggled by issuing the dummy-read from the remote + * LL memory in a hope that the MRd TLP will return only after the + * last MWr TLP is completed + */ + if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL)) + readl(chunk->ll_region.vaddr.io); +} + static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first) { struct dw_edma_chan *chan = chunk->chan; @@ -239,10 +236,13 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first) if (first) { /* Enable engine */ SET_CH_32(dw, chan->dir, chan->id, ch_en, BIT(0)); - /* Interrupt enable&unmask - done, abort */ - tmp = GET_CH_32(dw, chan->dir, chan->id, int_setup) | - HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK | - HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_STOP_INT_EN; + /* Interrupt unmask - stop, abort */ + tmp = GET_CH_32(dw, chan->dir, chan->id, int_setup); + tmp &= ~(HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK); + /* Interrupt enable - stop, abort */ + tmp |= HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_ABORT_INT_EN; + if (!(dw->chip->flags & DW_EDMA_CHIP_LOCAL)) + tmp |= HDMA_V0_REMOTE_STOP_INT_EN | HDMA_V0_REMOTE_ABORT_INT_EN; SET_CH_32(dw, chan->dir, chan->id, int_setup, tmp); /* Channel control */ SET_CH_32(dw, chan->dir, chan->id, control1, HDMA_V0_LINKLIST_EN); @@ -256,6 +256,9 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first) /* Set consumer cycle */ SET_CH_32(dw, chan->dir, chan->id, cycle_sync, HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT); + + dw_hdma_v0_sync_ll_data(chunk); + /* Doorbell */ SET_CH_32(dw, chan->dir, chan->id, doorbell, HDMA_V0_DOORBELL_START); } diff --git a/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c index 520c81978b085f..dcdc57fe976c13 100644 --- a/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c +++ b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c @@ -116,7 +116,7 @@ static void dw_hdma_debugfs_regs_ch(struct dw_edma *dw, enum dw_edma_dir dir, static void dw_hdma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent) { struct dentry *regs_dent, *ch_dent; - char name[16]; + char name[32]; int i; regs_dent = debugfs_create_dir(WRITE_STR, dent); @@ -133,7 +133,7 @@ static void dw_hdma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent) static void dw_hdma_debugfs_regs_rd(struct dw_edma *dw, struct dentry *dent) { struct dentry *regs_dent, *ch_dent; - char name[16]; + char name[32]; int i; regs_dent = debugfs_create_dir(READ_STR, dent); diff --git a/drivers/dma/dw-edma/dw-hdma-v0-regs.h b/drivers/dma/dw-edma/dw-hdma-v0-regs.h index a974abdf8aaf5e..eab5fd7177e545 100644 --- a/drivers/dma/dw-edma/dw-hdma-v0-regs.h +++ b/drivers/dma/dw-edma/dw-hdma-v0-regs.h @@ -15,7 +15,7 @@ #define HDMA_V0_LOCAL_ABORT_INT_EN BIT(6) #define HDMA_V0_REMOTE_ABORT_INT_EN BIT(5) #define HDMA_V0_LOCAL_STOP_INT_EN BIT(4) -#define HDMA_V0_REMOTEL_STOP_INT_EN BIT(3) +#define HDMA_V0_REMOTE_STOP_INT_EN BIT(3) #define HDMA_V0_ABORT_INT_MASK BIT(2) #define HDMA_V0_STOP_INT_MASK BIT(0) #define HDMA_V0_LINKLIST_EN BIT(0) diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index 5f7d690e3dbae8..b341a6f1b04383 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -621,12 +622,10 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, struct dw_desc *prev; struct dw_desc *first; u32 ctllo, ctlhi; - u8 m_master = dwc->dws.m_master; - u8 lms = DWC_LLP_LMS(m_master); + u8 lms = DWC_LLP_LMS(dwc->dws.m_master); dma_addr_t reg; unsigned int reg_width; unsigned int mem_width; - unsigned int data_width = dw->pdata->data_width[m_master]; unsigned int i; struct scatterlist *sg; size_t total_len = 0; @@ -660,7 +659,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, mem = sg_dma_address(sg); len = sg_dma_len(sg); - mem_width = __ffs(data_width | mem | len); + mem_width = __ffs(sconfig->src_addr_width | mem | len); slave_sg_todev_fill_desc: desc = dwc_desc_get(dwc); @@ -720,7 +719,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, lli_write(desc, sar, reg); lli_write(desc, dar, mem); lli_write(desc, ctlhi, ctlhi); - mem_width = __ffs(data_width | mem); + mem_width = __ffs(sconfig->dst_addr_width | mem); lli_write(desc, ctllo, ctllo | DWC_CTLL_DST_WIDTH(mem_width)); desc->len = dlen; @@ -780,17 +779,93 @@ bool dw_dma_filter(struct dma_chan *chan, void *param) } EXPORT_SYMBOL_GPL(dw_dma_filter); +static int dwc_verify_p_buswidth(struct dma_chan *chan) +{ + struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + struct dw_dma *dw = to_dw_dma(chan->device); + u32 reg_width, max_width; + + if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV) + reg_width = dwc->dma_sconfig.dst_addr_width; + else if (dwc->dma_sconfig.direction == DMA_DEV_TO_MEM) + reg_width = dwc->dma_sconfig.src_addr_width; + else /* DMA_MEM_TO_MEM */ + return 0; + + max_width = dw->pdata->data_width[dwc->dws.p_master]; + + /* Fall-back to 1-byte transfer width if undefined */ + if (reg_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) + reg_width = DMA_SLAVE_BUSWIDTH_1_BYTE; + else if (!is_power_of_2(reg_width) || reg_width > max_width) + return -EINVAL; + else /* bus width is valid */ + return 0; + + /* Update undefined addr width value */ + if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV) + dwc->dma_sconfig.dst_addr_width = reg_width; + else /* DMA_DEV_TO_MEM */ + dwc->dma_sconfig.src_addr_width = reg_width; + + return 0; +} + +static int dwc_verify_m_buswidth(struct dma_chan *chan) +{ + struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + struct dw_dma *dw = to_dw_dma(chan->device); + u32 reg_width, reg_burst, mem_width; + + mem_width = dw->pdata->data_width[dwc->dws.m_master]; + + /* + * It's possible to have a data portion locked in the DMA FIFO in case + * of the channel suspension. Subsequent channel disabling will cause + * that data silent loss. In order to prevent that maintain the src and + * dst transfer widths coherency by means of the relation: + * (CTLx.SRC_TR_WIDTH * CTLx.SRC_MSIZE >= CTLx.DST_TR_WIDTH) + * Look for the details in the commit message that brings this change. + * + * Note the DMA configs utilized in the calculations below must have + * been verified to have correct values by this method call. + */ + if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV) { + reg_width = dwc->dma_sconfig.dst_addr_width; + if (mem_width < reg_width) + return -EINVAL; + + dwc->dma_sconfig.src_addr_width = mem_width; + } else if (dwc->dma_sconfig.direction == DMA_DEV_TO_MEM) { + reg_width = dwc->dma_sconfig.src_addr_width; + reg_burst = rounddown_pow_of_two(dwc->dma_sconfig.src_maxburst); + + dwc->dma_sconfig.dst_addr_width = min(mem_width, reg_width * reg_burst); + } + + return 0; +} + static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig) { struct dw_dma_chan *dwc = to_dw_dma_chan(chan); struct dw_dma *dw = to_dw_dma(chan->device); + int ret; memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig)); dwc->dma_sconfig.src_maxburst = - clamp(dwc->dma_sconfig.src_maxburst, 0U, dwc->max_burst); + clamp(dwc->dma_sconfig.src_maxburst, 1U, dwc->max_burst); dwc->dma_sconfig.dst_maxburst = - clamp(dwc->dma_sconfig.dst_maxburst, 0U, dwc->max_burst); + clamp(dwc->dma_sconfig.dst_maxburst, 1U, dwc->max_burst); + + ret = dwc_verify_p_buswidth(chan); + if (ret) + return ret; + + ret = dwc_verify_m_buswidth(chan); + if (ret) + return ret; dw->encode_maxburst(dwc, &dwc->dma_sconfig.src_maxburst); dw->encode_maxburst(dwc, &dwc->dma_sconfig.dst_maxburst); diff --git a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c index a42a37634881b2..da91bc9a8e6f0e 100644 --- a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c +++ b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c @@ -38,15 +38,17 @@ static int dpaa2_qdma_alloc_chan_resources(struct dma_chan *chan) if (!dpaa2_chan->fd_pool) goto err; - dpaa2_chan->fl_pool = dma_pool_create("fl_pool", dev, - sizeof(struct dpaa2_fl_entry), - sizeof(struct dpaa2_fl_entry), 0); + dpaa2_chan->fl_pool = + dma_pool_create("fl_pool", dev, + sizeof(struct dpaa2_fl_entry) * 3, + sizeof(struct dpaa2_fl_entry), 0); + if (!dpaa2_chan->fl_pool) goto err_fd; dpaa2_chan->sdd_pool = dma_pool_create("sdd_pool", dev, - sizeof(struct dpaa2_qdma_sd_d), + sizeof(struct dpaa2_qdma_sd_d) * 2, sizeof(struct dpaa2_qdma_sd_d), 0); if (!dpaa2_chan->sdd_pool) goto err_fl; diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index 6a3abe5b17908d..53fdfd32a7e772 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -3,6 +3,7 @@ // Copyright (c) 2013-2014 Freescale Semiconductor, Inc // Copyright (c) 2017 Sysam, Angelo Dureghello +#include #include #include #include @@ -74,18 +75,10 @@ static void fsl_edma3_enable_request(struct fsl_edma_chan *fsl_chan) flags = fsl_edma_drvflags(fsl_chan); val = edma_readl_chreg(fsl_chan, ch_sbr); - /* Remote/local swapped wrongly on iMX8 QM Audio edma */ - if (flags & FSL_EDMA_DRV_QUIRK_SWAPPED) { - if (!fsl_chan->is_rxchan) - val |= EDMA_V3_CH_SBR_RD; - else - val |= EDMA_V3_CH_SBR_WR; - } else { - if (fsl_chan->is_rxchan) - val |= EDMA_V3_CH_SBR_RD; - else - val |= EDMA_V3_CH_SBR_WR; - } + if (fsl_chan->is_rxchan) + val |= EDMA_V3_CH_SBR_RD; + else + val |= EDMA_V3_CH_SBR_WR; if (fsl_chan->is_remote) val &= ~(EDMA_V3_CH_SBR_RD | EDMA_V3_CH_SBR_WR); @@ -97,8 +90,8 @@ static void fsl_edma3_enable_request(struct fsl_edma_chan *fsl_chan) * ch_mux: With the exception of 0, attempts to write a value * already in use will be forced to 0. */ - if (!edma_readl_chreg(fsl_chan, ch_mux)) - edma_writel_chreg(fsl_chan, fsl_chan->srcid, ch_mux); + if (!edma_readl(fsl_chan->edma, fsl_chan->mux_addr)) + edma_writel(fsl_chan->edma, fsl_chan->srcid, fsl_chan->mux_addr); } val = edma_readl_chreg(fsl_chan, ch_csr); @@ -134,7 +127,7 @@ static void fsl_edma3_disable_request(struct fsl_edma_chan *fsl_chan) flags = fsl_edma_drvflags(fsl_chan); if (flags & FSL_EDMA_DRV_HAS_CHMUX) - edma_writel_chreg(fsl_chan, 0, ch_mux); + edma_writel(fsl_chan->edma, 0, fsl_chan->mux_addr); val &= ~EDMA_V3_CH_CSR_ERQ; edma_writel_chreg(fsl_chan, val, ch_csr); @@ -503,7 +496,7 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan, if (fsl_chan->is_multi_fifo) { /* set mloff to support multiple fifo */ burst = cfg->direction == DMA_DEV_TO_MEM ? - cfg->src_addr_width : cfg->dst_addr_width; + cfg->src_maxburst : cfg->dst_maxburst; nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-(burst * 4)); /* enable DMLOE/SMLOE */ if (cfg->direction == DMA_MEM_TO_DEV) { @@ -754,6 +747,8 @@ struct dma_async_tx_descriptor *fsl_edma_prep_memcpy(struct dma_chan *chan, fsl_desc->iscyclic = false; fsl_chan->is_sw = true; + if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_MEM_REMOTE) + fsl_chan->is_remote = true; /* To match with copy_align and max_seg_size so 1 tcd is enough */ fsl_edma_fill_tcd(fsl_chan, fsl_desc->tcd[0].vtcd, dma_src, dma_dst, @@ -802,6 +797,9 @@ int fsl_edma_alloc_chan_resources(struct dma_chan *chan) { struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan); + if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_HAS_CHCLK) + clk_prepare_enable(fsl_chan->clk); + fsl_chan->tcd_pool = dma_pool_create("tcd_pool", chan->device->dev, sizeof(struct fsl_edma_hw_tcd), 32, 0); @@ -828,6 +826,10 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan) dma_pool_destroy(fsl_chan->tcd_pool); fsl_chan->tcd_pool = NULL; fsl_chan->is_sw = false; + fsl_chan->srcid = 0; + fsl_chan->is_remote = false; + if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_HAS_CHCLK) + clk_disable_unprepare(fsl_chan->clk); } void fsl_edma_cleanup_vchan(struct dma_device *dmadev) diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h index 40d50cc3d75a34..6028389de408b0 100644 --- a/drivers/dma/fsl-edma-common.h +++ b/drivers/dma/fsl-edma-common.h @@ -30,8 +30,9 @@ #define EDMA_TCD_ATTR_SSIZE(x) (((x) & GENMASK(2, 0)) << 8) #define EDMA_TCD_ATTR_SMOD(x) (((x) & GENMASK(4, 0)) << 11) -#define EDMA_TCD_CITER_CITER(x) ((x) & GENMASK(14, 0)) -#define EDMA_TCD_BITER_BITER(x) ((x) & GENMASK(14, 0)) +#define EDMA_TCD_ITER_MASK GENMASK(14, 0) +#define EDMA_TCD_CITER_CITER(x) ((x) & EDMA_TCD_ITER_MASK) +#define EDMA_TCD_BITER_BITER(x) ((x) & EDMA_TCD_ITER_MASK) #define EDMA_TCD_CSR_START BIT(0) #define EDMA_TCD_CSR_INT_MAJOR BIT(1) @@ -145,6 +146,7 @@ struct fsl_edma_chan { enum dma_data_direction dma_dir; char chan_name[32]; struct fsl_edma_hw_tcd __iomem *tcd; + void __iomem *mux_addr; u32 real_count; struct work_struct issue_worker; struct platform_device *pdev; @@ -176,8 +178,7 @@ struct fsl_edma_desc { #define FSL_EDMA_DRV_HAS_PD BIT(5) #define FSL_EDMA_DRV_HAS_CHCLK BIT(6) #define FSL_EDMA_DRV_HAS_CHMUX BIT(7) -/* imx8 QM audio edma remote local swapped */ -#define FSL_EDMA_DRV_QUIRK_SWAPPED BIT(8) +#define FSL_EDMA_DRV_MEM_REMOTE BIT(8) /* control and status register is in tcd address space, edma3 reg layout */ #define FSL_EDMA_DRV_SPLIT_REG BIT(9) #define FSL_EDMA_DRV_BUS_8BYTE BIT(10) @@ -206,6 +207,8 @@ struct fsl_edma_drvdata { u32 chreg_off; u32 chreg_space_sz; u32 flags; + u32 mux_off; /* channel mux register offset */ + u32 mux_skip; /* how much skip for each channel */ int (*setup_irq)(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma); }; diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index 8c4ed7012e232e..8a0ae90548997c 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -9,6 +9,8 @@ * Vybrid and Layerscape SoCs. */ +#include +#include #include #include #include @@ -23,10 +25,6 @@ #include "fsl-edma-common.h" -#define ARGS_RX BIT(0) -#define ARGS_REMOTE BIT(1) -#define ARGS_MULTI_FIFO BIT(2) - static void fsl_edma_synchronize(struct dma_chan *chan) { struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan); @@ -155,9 +153,15 @@ static struct dma_chan *fsl_edma3_xlate(struct of_phandle_args *dma_spec, i = fsl_chan - fsl_edma->chans; fsl_chan->priority = dma_spec->args[1]; - fsl_chan->is_rxchan = dma_spec->args[2] & ARGS_RX; - fsl_chan->is_remote = dma_spec->args[2] & ARGS_REMOTE; - fsl_chan->is_multi_fifo = dma_spec->args[2] & ARGS_MULTI_FIFO; + fsl_chan->is_rxchan = dma_spec->args[2] & FSL_EDMA_RX; + fsl_chan->is_remote = dma_spec->args[2] & FSL_EDMA_REMOTE; + fsl_chan->is_multi_fifo = dma_spec->args[2] & FSL_EDMA_MULTI_FIFO; + + if ((dma_spec->args[2] & FSL_EDMA_EVEN_CH) && (i & 0x1)) + continue; + + if ((dma_spec->args[2] & FSL_EDMA_ODD_CH) && !(i & 0x1)) + continue; if (!b_chmux && i == dma_spec->args[0]) { chan = dma_get_slave_channel(chan); @@ -336,16 +340,19 @@ static struct fsl_edma_drvdata imx7ulp_data = { }; static struct fsl_edma_drvdata imx8qm_data = { - .flags = FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3, + .flags = FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3 | FSL_EDMA_DRV_MEM_REMOTE, .chreg_space_sz = 0x10000, .chreg_off = 0x10000, .setup_irq = fsl_edma3_irq_init, }; -static struct fsl_edma_drvdata imx8qm_audio_data = { - .flags = FSL_EDMA_DRV_QUIRK_SWAPPED | FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3, +static struct fsl_edma_drvdata imx8ulp_data = { + .flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_CHCLK | FSL_EDMA_DRV_HAS_DMACLK | + FSL_EDMA_DRV_EDMA3, .chreg_space_sz = 0x10000, .chreg_off = 0x10000, + .mux_off = 0x10000 + offsetof(struct fsl_edma3_ch_reg, ch_mux), + .mux_skip = 0x10000, .setup_irq = fsl_edma3_irq_init, }; @@ -360,6 +367,8 @@ static struct fsl_edma_drvdata imx93_data4 = { .flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4, .chreg_space_sz = 0x8000, .chreg_off = 0x10000, + .mux_off = 0x10000 + offsetof(struct fsl_edma3_ch_reg, ch_mux), + .mux_skip = 0x8000, .setup_irq = fsl_edma3_irq_init, }; @@ -368,7 +377,7 @@ static const struct of_device_id fsl_edma_dt_ids[] = { { .compatible = "fsl,ls1028a-edma", .data = &ls1028a_data}, { .compatible = "fsl,imx7ulp-edma", .data = &imx7ulp_data}, { .compatible = "fsl,imx8qm-edma", .data = &imx8qm_data}, - { .compatible = "fsl,imx8qm-adma", .data = &imx8qm_audio_data}, + { .compatible = "fsl,imx8ulp-edma", .data = &imx8ulp_data}, { .compatible = "fsl,imx93-edma3", .data = &imx93_data3}, { .compatible = "fsl,imx93-edma4", .data = &imx93_data4}, { /* sentinel */ } @@ -400,9 +409,8 @@ static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_eng link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); - if (IS_ERR(link)) { - dev_err(dev, "Failed to add device_link to %d: %ld\n", i, - PTR_ERR(link)); + if (!link) { + dev_err(dev, "Failed to add device_link to %d\n", i); return -EINVAL; } @@ -424,6 +432,7 @@ static int fsl_edma_probe(struct platform_device *pdev) struct fsl_edma_engine *fsl_edma; const struct fsl_edma_drvdata *drvdata = NULL; u32 chan_mask[2] = {0, 0}; + char clk_name[36]; struct edma_regs *regs; int chans; int ret, i; @@ -537,12 +546,23 @@ static int fsl_edma_probe(struct platform_device *pdev) offsetof(struct fsl_edma3_ch_reg, tcd) : 0; fsl_chan->tcd = fsl_edma->membase + i * drvdata->chreg_space_sz + drvdata->chreg_off + len; + fsl_chan->mux_addr = fsl_edma->membase + drvdata->mux_off + i * drvdata->mux_skip; + + if (drvdata->flags & FSL_EDMA_DRV_HAS_CHCLK) { + snprintf(clk_name, sizeof(clk_name), "ch%02d", i); + fsl_chan->clk = devm_clk_get_enabled(&pdev->dev, + (const char *)clk_name); + if (IS_ERR(fsl_chan->clk)) + return PTR_ERR(fsl_chan->clk); + } fsl_chan->pdev = pdev; vchan_init(&fsl_chan->vchan, &fsl_edma->dma_dev); edma_write_tcdreg(fsl_chan, 0, csr); fsl_edma_chan_mux(fsl_chan, 0, false); + if (fsl_chan->edma->drvdata->flags & FSL_EDMA_DRV_HAS_CHCLK) + clk_disable_unprepare(fsl_chan->clk); } ret = fsl_edma->drvdata->setup_irq(pdev, fsl_edma); @@ -587,7 +607,8 @@ static int fsl_edma_probe(struct platform_device *pdev) DMAENGINE_ALIGN_32_BYTES; /* Per worst case 'nbytes = 1' take CITER as the max_seg_size */ - dma_set_max_seg_size(fsl_edma->dma_dev.dev, 0x3fff); + dma_set_max_seg_size(fsl_edma->dma_dev.dev, + FIELD_GET(EDMA_TCD_ITER_MASK, EDMA_TCD_ITER_MASK)); fsl_edma->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT; @@ -640,6 +661,8 @@ static int fsl_edma_suspend_late(struct device *dev) for (i = 0; i < fsl_edma->n_chans; i++) { fsl_chan = &fsl_edma->chans[i]; + if (fsl_edma->chan_masked & BIT(i)) + continue; spin_lock_irqsave(&fsl_chan->vchan.lock, flags); /* Make sure chan is idle or will force disable. */ if (unlikely(!fsl_chan->idle)) { @@ -664,13 +687,16 @@ static int fsl_edma_resume_early(struct device *dev) for (i = 0; i < fsl_edma->n_chans; i++) { fsl_chan = &fsl_edma->chans[i]; + if (fsl_edma->chan_masked & BIT(i)) + continue; fsl_chan->pm_state = RUNNING; edma_write_tcdreg(fsl_chan, 0, csr); if (fsl_chan->slave_id != 0) fsl_edma_chan_mux(fsl_chan, fsl_chan->slave_id, true); } - edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr); + if (!(fsl_edma->drvdata->flags & FSL_EDMA_DRV_SPLIT_REG)) + edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr); return 0; } diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c index a8cc8a4bc6102c..b7a2254b0de475 100644 --- a/drivers/dma/fsl-qdma.c +++ b/drivers/dma/fsl-qdma.c @@ -109,6 +109,7 @@ #define FSL_QDMA_CMD_WTHROTL_OFFSET 20 #define FSL_QDMA_CMD_DSEN_OFFSET 19 #define FSL_QDMA_CMD_LWC_OFFSET 16 +#define FSL_QDMA_CMD_PF BIT(17) /* Field definition for Descriptor status */ #define QDMA_CCDF_STATUS_RTE BIT(5) @@ -384,7 +385,8 @@ static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp, qdma_csgf_set_f(csgf_dest, len); /* Descriptor Buffer */ cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE << - FSL_QDMA_CMD_RWTTYPE_OFFSET); + FSL_QDMA_CMD_RWTTYPE_OFFSET) | + FSL_QDMA_CMD_PF; sdf->data = QDMA_SDDF_CMD(cmd); cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE << @@ -514,11 +516,11 @@ static struct fsl_qdma_queue queue_temp = queue_head + i + (j * queue_num); queue_temp->cq = - dma_alloc_coherent(&pdev->dev, - sizeof(struct fsl_qdma_format) * - queue_size[i], - &queue_temp->bus_addr, - GFP_KERNEL); + dmam_alloc_coherent(&pdev->dev, + sizeof(struct fsl_qdma_format) * + queue_size[i], + &queue_temp->bus_addr, + GFP_KERNEL); if (!queue_temp->cq) return NULL; queue_temp->block_base = fsl_qdma->block_base + @@ -563,11 +565,11 @@ static struct fsl_qdma_queue /* * Buffer for queue command */ - status_head->cq = dma_alloc_coherent(&pdev->dev, - sizeof(struct fsl_qdma_format) * - status_size, - &status_head->bus_addr, - GFP_KERNEL); + status_head->cq = dmam_alloc_coherent(&pdev->dev, + sizeof(struct fsl_qdma_format) * + status_size, + &status_head->bus_addr, + GFP_KERNEL); if (!status_head->cq) { devm_kfree(&pdev->dev, status_head); return NULL; @@ -805,7 +807,7 @@ fsl_qdma_irq_init(struct platform_device *pdev, int i; int cpu; int ret; - char irq_name[20]; + char irq_name[32]; fsl_qdma->error_irq = platform_get_irq_byname(pdev, "qdma-error"); @@ -1197,10 +1199,6 @@ static int fsl_qdma_probe(struct platform_device *pdev) if (!fsl_qdma->queue) return -ENOMEM; - ret = fsl_qdma_irq_init(pdev, fsl_qdma); - if (ret) - return ret; - fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0"); if (fsl_qdma->irq_base < 0) return fsl_qdma->irq_base; @@ -1239,16 +1237,19 @@ static int fsl_qdma_probe(struct platform_device *pdev) platform_set_drvdata(pdev, fsl_qdma); - ret = dma_async_device_register(&fsl_qdma->dma_dev); + ret = fsl_qdma_reg_init(fsl_qdma); if (ret) { - dev_err(&pdev->dev, - "Can't register NXP Layerscape qDMA engine.\n"); + dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n"); return ret; } - ret = fsl_qdma_reg_init(fsl_qdma); + ret = fsl_qdma_irq_init(pdev, fsl_qdma); + if (ret) + return ret; + + ret = dma_async_device_register(&fsl_qdma->dma_dev); if (ret) { - dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n"); + dev_err(&pdev->dev, "Can't register NXP Layerscape qDMA engine.\n"); return ret; } @@ -1268,8 +1269,6 @@ static void fsl_qdma_cleanup_vchan(struct dma_device *dmadev) static int fsl_qdma_remove(struct platform_device *pdev) { - int i; - struct fsl_qdma_queue *status; struct device_node *np = pdev->dev.of_node; struct fsl_qdma_engine *fsl_qdma = platform_get_drvdata(pdev); @@ -1278,11 +1277,6 @@ static int fsl_qdma_remove(struct platform_device *pdev) of_dma_controller_free(np); dma_async_device_unregister(&fsl_qdma->dma_dev); - for (i = 0; i < fsl_qdma->block_number; i++) { - status = fsl_qdma->status[i]; - dma_free_coherent(&pdev->dev, sizeof(struct fsl_qdma_format) * - status->n_cq, status->cq, status->bus_addr); - } return 0; } diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c index 0ac634a51c5e35..6fa797fd85017d 100644 --- a/drivers/dma/idma64.c +++ b/drivers/dma/idma64.c @@ -171,6 +171,10 @@ static irqreturn_t idma64_irq(int irq, void *dev) u32 status_err; unsigned short i; + /* Since IRQ may be shared, check if DMA controller is powered on */ + if (status == GENMASK(31, 0)) + return IRQ_NONE; + dev_vdbg(idma64->dma.dev, "%s: status=%#x\n", __func__, status); /* Check if we have any interrupt from the DMA controller */ @@ -594,7 +598,9 @@ static int idma64_probe(struct idma64_chip *chip) idma64->dma.dev = chip->sysdev; - dma_set_max_seg_size(idma64->dma.dev, IDMA64C_CTLH_BLOCK_TS_MASK); + ret = dma_set_max_seg_size(idma64->dma.dev, IDMA64C_CTLH_BLOCK_TS_MASK); + if (ret) + return ret; ret = dma_async_device_register(&idma64->dma); if (ret) diff --git a/drivers/dma/idxd/Makefile b/drivers/dma/idxd/Makefile index dc096839ac6374..c5e679070e4633 100644 --- a/drivers/dma/idxd/Makefile +++ b/drivers/dma/idxd/Makefile @@ -1,12 +1,12 @@ ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE=IDXD +obj-$(CONFIG_INTEL_IDXD_BUS) += idxd_bus.o +idxd_bus-y := bus.o + obj-$(CONFIG_INTEL_IDXD) += idxd.o idxd-y := init.o irq.o device.o sysfs.o submit.o dma.o cdev.o debugfs.o idxd-$(CONFIG_INTEL_IDXD_PERFMON) += perfmon.o -obj-$(CONFIG_INTEL_IDXD_BUS) += idxd_bus.o -idxd_bus-y := bus.o - obj-$(CONFIG_INTEL_IDXD_COMPAT) += idxd_compat.o idxd_compat-y := compat.o diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index d32deb9b4e3dee..c18633ad8455fa 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -342,10 +342,10 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid) if (!evl) return; - spin_lock(&evl->lock); + mutex_lock(&evl->lock); status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); t = status.tail; - h = evl->head; + h = status.head; size = evl->size; while (h != t) { @@ -354,9 +354,8 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid) set_bit(h, evl->bmap); h = (h + 1) % size; } - spin_unlock(&evl->lock); - drain_workqueue(wq->wq); + mutex_unlock(&evl->lock); } static int idxd_cdev_release(struct inode *node, struct file *filep) @@ -401,6 +400,18 @@ static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma) int rc; dev_dbg(&pdev->dev, "%s called\n", __func__); + + /* + * Due to an erratum in some of the devices supported by the driver, + * direct user submission to the device can be unsafe. + * (See the INTEL-SA-01084 security advisory) + * + * For the devices that exhibit this behavior, require that the user + * has CAP_SYS_RAWIO capabilities. + */ + if (!idxd->user_submission_safe && !capable(CAP_SYS_RAWIO)) + return -EPERM; + rc = check_vma(wq, vma, __func__); if (rc < 0) return rc; @@ -415,6 +426,70 @@ static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_page_prot); } +static int idxd_submit_user_descriptor(struct idxd_user_context *ctx, + struct dsa_hw_desc __user *udesc) +{ + struct idxd_wq *wq = ctx->wq; + struct idxd_dev *idxd_dev = &wq->idxd->idxd_dev; + const uint64_t comp_addr_align = is_dsa_dev(idxd_dev) ? 0x20 : 0x40; + void __iomem *portal = idxd_wq_portal_addr(wq); + struct dsa_hw_desc descriptor __aligned(64); + int rc; + + rc = copy_from_user(&descriptor, udesc, sizeof(descriptor)); + if (rc) + return -EFAULT; + + /* + * DSA devices are capable of indirect ("batch") command submission. + * On devices where direct user submissions are not safe, we cannot + * allow this since there is no good way for us to verify these + * indirect commands. + */ + if (is_dsa_dev(idxd_dev) && descriptor.opcode == DSA_OPCODE_BATCH && + !wq->idxd->user_submission_safe) + return -EINVAL; + /* + * As per the programming specification, the completion address must be + * aligned to 32 or 64 bytes. If this is violated the hardware + * engine can get very confused (security issue). + */ + if (!IS_ALIGNED(descriptor.completion_addr, comp_addr_align)) + return -EINVAL; + + if (wq_dedicated(wq)) + iosubmit_cmds512(portal, &descriptor, 1); + else { + descriptor.priv = 0; + descriptor.pasid = ctx->pasid; + rc = idxd_enqcmds(wq, portal, &descriptor); + if (rc < 0) + return rc; + } + + return 0; +} + +static ssize_t idxd_cdev_write(struct file *filp, const char __user *buf, size_t len, + loff_t *unused) +{ + struct dsa_hw_desc __user *udesc = (struct dsa_hw_desc __user *)buf; + struct idxd_user_context *ctx = filp->private_data; + ssize_t written = 0; + int i; + + for (i = 0; i < len/sizeof(struct dsa_hw_desc); i++) { + int rc = idxd_submit_user_descriptor(ctx, udesc + i); + + if (rc) + return written ? written : rc; + + written += sizeof(struct dsa_hw_desc); + } + + return written; +} + static __poll_t idxd_cdev_poll(struct file *filp, struct poll_table_struct *wait) { @@ -437,6 +512,7 @@ static const struct file_operations idxd_cdev_fops = { .open = idxd_cdev_open, .release = idxd_cdev_release, .mmap = idxd_cdev_mmap, + .write = idxd_cdev_write, .poll = idxd_cdev_poll, }; @@ -501,7 +577,6 @@ void idxd_wq_del_cdev(struct idxd_wq *wq) struct idxd_cdev *idxd_cdev; idxd_cdev = wq->idxd_cdev; - ida_destroy(&file_ida); wq->idxd_cdev = NULL; cdev_device_del(&idxd_cdev->cdev, cdev_dev(idxd_cdev)); put_device(cdev_dev(idxd_cdev)); diff --git a/drivers/dma/idxd/debugfs.c b/drivers/dma/idxd/debugfs.c index 9cfbd9b14c4c43..ad4245cb301d50 100644 --- a/drivers/dma/idxd/debugfs.c +++ b/drivers/dma/idxd/debugfs.c @@ -66,11 +66,11 @@ static int debugfs_evl_show(struct seq_file *s, void *d) if (!evl || !evl->log) return 0; - spin_lock(&evl->lock); + mutex_lock(&evl->lock); - h = evl->head; evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); t = evl_status.tail; + h = evl_status.head; evl_size = evl->size; seq_printf(s, "Event Log head %u tail %u interrupt pending %u\n\n", @@ -87,7 +87,7 @@ static int debugfs_evl_show(struct seq_file *s, void *d) dump_event_entry(idxd, s, i, &count, processed); } - spin_unlock(&evl->lock); + mutex_unlock(&evl->lock); return 0; } diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 8f754f922217de..542d340552dd71 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -770,7 +770,7 @@ static int idxd_device_evl_setup(struct idxd_device *idxd) goto err_alloc; } - spin_lock(&evl->lock); + mutex_lock(&evl->lock); evl->log = addr; evl->dma = dma_addr; evl->log_size = size; @@ -791,7 +791,7 @@ static int idxd_device_evl_setup(struct idxd_device *idxd) gencfg.evl_en = 1; iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET); - spin_unlock(&evl->lock); + mutex_unlock(&evl->lock); return 0; err_alloc: @@ -802,6 +802,9 @@ static int idxd_device_evl_setup(struct idxd_device *idxd) static void idxd_device_evl_free(struct idxd_device *idxd) { + void *evl_log; + unsigned int evl_log_size; + dma_addr_t evl_dma; union gencfg_reg gencfg; union genctrl_reg genctrl; struct device *dev = &idxd->pdev->dev; @@ -811,7 +814,7 @@ static void idxd_device_evl_free(struct idxd_device *idxd) if (!gencfg.evl_en) return; - spin_lock(&evl->lock); + mutex_lock(&evl->lock); gencfg.evl_en = 0; iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET); @@ -822,11 +825,15 @@ static void idxd_device_evl_free(struct idxd_device *idxd) iowrite64(0, idxd->reg_base + IDXD_EVLCFG_OFFSET); iowrite64(0, idxd->reg_base + IDXD_EVLCFG_OFFSET + 8); - dma_free_coherent(dev, evl->log_size, evl->log, evl->dma); bitmap_free(evl->bmap); + evl_log = evl->log; + evl_log_size = evl->log_size; + evl_dma = evl->dma; evl->log = NULL; evl->size = IDXD_EVL_SIZE_MIN; - spin_unlock(&evl->lock); + mutex_unlock(&evl->lock); + + dma_free_coherent(dev, evl_log_size, evl_log, evl_dma); } static void idxd_group_config_write(struct idxd_group *group) diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index e269ca1f486255..bea10c5cdb76bb 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -275,18 +275,18 @@ struct idxd_driver_data { int evl_cr_off; int cr_status_off; int cr_result_off; + bool user_submission_safe; }; struct idxd_evl { /* Lock to protect event log access. */ - spinlock_t lock; + struct mutex lock; void *log; dma_addr_t dma; /* Total size of event log = number of entries * entry size. */ unsigned int log_size; /* The number of entries in the event log. */ u16 size; - u16 head; unsigned long *bmap; bool batch_fail[IDXD_MAX_BATCH_IDENT]; }; @@ -361,6 +361,8 @@ struct idxd_device { struct dentry *dbgfs_dir; struct dentry *dbgfs_evl_file; + + bool user_submission_safe; }; static inline unsigned int evl_ent_size(struct idxd_device *idxd) diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 0eb1c827a215f9..786afb256b6e0d 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -47,6 +47,7 @@ static struct idxd_driver_data idxd_driver_data[] = { .align = 32, .dev_type = &dsa_device_type, .evl_cr_off = offsetof(struct dsa_evl_entry, cr), + .user_submission_safe = false, /* See INTEL-SA-01084 security advisory */ .cr_status_off = offsetof(struct dsa_completion_record, status), .cr_result_off = offsetof(struct dsa_completion_record, result), }, @@ -57,6 +58,7 @@ static struct idxd_driver_data idxd_driver_data[] = { .align = 64, .dev_type = &iax_device_type, .evl_cr_off = offsetof(struct iax_evl_entry, cr), + .user_submission_safe = false, /* See INTEL-SA-01084 security advisory */ .cr_status_off = offsetof(struct iax_completion_record, status), .cr_result_off = offsetof(struct iax_completion_record, error_code), }, @@ -342,7 +344,9 @@ static void idxd_cleanup_internals(struct idxd_device *idxd) static int idxd_init_evl(struct idxd_device *idxd) { struct device *dev = &idxd->pdev->dev; + unsigned int evl_cache_size; struct idxd_evl *evl; + const char *idxd_name; if (idxd->hw.gen_cap.evl_support == 0) return 0; @@ -351,12 +355,19 @@ static int idxd_init_evl(struct idxd_device *idxd) if (!evl) return -ENOMEM; - spin_lock_init(&evl->lock); + mutex_init(&evl->lock); evl->size = IDXD_EVL_SIZE_MIN; - idxd->evl_cache = kmem_cache_create(dev_name(idxd_confdev(idxd)), - sizeof(struct idxd_evl_fault) + evl_ent_size(idxd), - 0, 0, NULL); + idxd_name = dev_name(idxd_confdev(idxd)); + evl_cache_size = sizeof(struct idxd_evl_fault) + evl_ent_size(idxd); + /* + * Since completion record in evl_cache will be copied to user + * when handling completion record page fault, need to create + * the cache suitable for user copy. + */ + idxd->evl_cache = kmem_cache_create_usercopy(idxd_name, evl_cache_size, + 0, 0, 0, evl_cache_size, + NULL); if (!idxd->evl_cache) { kfree(evl); return -ENOMEM; @@ -758,6 +769,8 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev_info(&pdev->dev, "Intel(R) Accelerator Device (v%x)\n", idxd->hw.version); + idxd->user_submission_safe = data->user_submission_safe; + return 0; err_dev_register: diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index b501320a9c7ad0..7efc85b5bad9e9 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -363,13 +363,13 @@ static void process_evl_entries(struct idxd_device *idxd) evl_status.bits = 0; evl_status.int_pending = 1; - spin_lock(&evl->lock); + mutex_lock(&evl->lock); /* Clear interrupt pending bit */ iowrite32(evl_status.bits_upper32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET + sizeof(u32)); - h = evl->head; evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); t = evl_status.tail; + h = evl_status.head; size = idxd->evl->size; while (h != t) { @@ -378,10 +378,9 @@ static void process_evl_entries(struct idxd_device *idxd) h = (h + 1) % size; } - evl->head = h; evl_status.head = h; iowrite32(evl_status.bits_lower32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET); - spin_unlock(&evl->lock); + mutex_unlock(&evl->lock); } irqreturn_t idxd_misc_thread(int vec, void *data) @@ -612,11 +611,13 @@ static void irq_process_work_list(struct idxd_irq_entry *irq_entry) spin_unlock(&irq_entry->list_lock); - list_for_each_entry(desc, &flist, list) { + list_for_each_entry_safe(desc, n, &flist, list) { /* * Check against the original status as ABORT is software defined * and 0xff, which DSA_COMP_STATUS_MASK can mask out. */ + list_del(&desc->list); + if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) { idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, true); continue; diff --git a/drivers/dma/idxd/perfmon.c b/drivers/dma/idxd/perfmon.c index fdda6d60426295..5e94247e1ea703 100644 --- a/drivers/dma/idxd/perfmon.c +++ b/drivers/dma/idxd/perfmon.c @@ -528,14 +528,11 @@ static int perf_event_cpu_offline(unsigned int cpu, struct hlist_node *node) return 0; target = cpumask_any_but(cpu_online_mask, cpu); - /* migrate events if there is a valid target */ - if (target < nr_cpu_ids) + if (target < nr_cpu_ids) { cpumask_set_cpu(target, &perfmon_dsa_cpu_mask); - else - target = -1; - - perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target); + perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target); + } return 0; } diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index 7b54a3939ea135..cfbcd1adb1d1c2 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -6,9 +6,6 @@ #include /* PCI Config */ -#define PCI_DEVICE_ID_INTEL_DSA_SPR0 0x0b25 -#define PCI_DEVICE_ID_INTEL_IAX_SPR0 0x0cfe - #define DEVICE_VERSION_1 0x100 #define DEVICE_VERSION_2 0x200 diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index c01db23e3333f7..3f922518e3a525 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -182,13 +182,6 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) portal = idxd_wq_portal_addr(wq); - /* - * The wmb() flushes writes to coherent DMA data before - * possibly triggering a DMA read. The wmb() is necessary - * even on UP because the recipient is a device. - */ - wmb(); - /* * Pending the descriptor to the lockless list for the irq_entry * that we designated the descriptor to. @@ -199,6 +192,13 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) llist_add(&desc->llnode, &ie->pending_llist); } + /* + * The wmb() flushes writes to coherent DMA data before + * possibly triggering a DMA read. The wmb() is necessary + * even on UP because the recipient is a device. + */ + wmb(); + if (wq_dedicated(wq)) { iosubmit_cmds512(portal, desc->hw, 1); } else { diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 7caba90d85b31e..1fd5a93045f79e 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1197,12 +1197,35 @@ static ssize_t wq_enqcmds_retries_store(struct device *dev, struct device_attrib static struct device_attribute dev_attr_wq_enqcmds_retries = __ATTR(enqcmds_retries, 0644, wq_enqcmds_retries_show, wq_enqcmds_retries_store); +static ssize_t op_cap_show_common(struct device *dev, char *buf, unsigned long *opcap_bmap) +{ + ssize_t pos; + int i; + + pos = 0; + for (i = IDXD_MAX_OPCAP_BITS/64 - 1; i >= 0; i--) { + unsigned long val = opcap_bmap[i]; + + /* On systems where direct user submissions are not safe, we need to clear out + * the BATCH capability from the capability mask in sysfs since we cannot support + * that command on such systems. + */ + if (i == DSA_OPCODE_BATCH/64 && !confdev_to_idxd(dev)->user_submission_safe) + clear_bit(DSA_OPCODE_BATCH % 64, &val); + + pos += sysfs_emit_at(buf, pos, "%*pb", 64, &val); + pos += sysfs_emit_at(buf, pos, "%c", i == 0 ? '\n' : ','); + } + + return pos; +} + static ssize_t wq_op_config_show(struct device *dev, struct device_attribute *attr, char *buf) { struct idxd_wq *wq = confdev_to_wq(dev); - return sysfs_emit(buf, "%*pb\n", IDXD_MAX_OPCAP_BITS, wq->opcap_bmap); + return op_cap_show_common(dev, buf, wq->opcap_bmap); } static int idxd_verify_supported_opcap(struct idxd_device *idxd, unsigned long *opmask) @@ -1421,7 +1444,7 @@ static ssize_t op_cap_show(struct device *dev, { struct idxd_device *idxd = confdev_to_idxd(dev); - return sysfs_emit(buf, "%*pb\n", IDXD_MAX_OPCAP_BITS, idxd->opcap_bmap); + return op_cap_show_common(dev, buf, idxd->opcap_bmap); } static DEVICE_ATTR_RO(op_cap); diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c index 9c364e92cb828d..e8f45a7fded435 100644 --- a/drivers/dma/ioat/init.c +++ b/drivers/dma/ioat/init.c @@ -534,18 +534,6 @@ static int ioat_probe(struct ioatdma_device *ioat_dma) return err; } -static int ioat_register(struct ioatdma_device *ioat_dma) -{ - int err = dma_async_device_register(&ioat_dma->dma_dev); - - if (err) { - ioat_disable_interrupts(ioat_dma); - dma_pool_destroy(ioat_dma->completion_pool); - } - - return err; -} - static void ioat_dma_remove(struct ioatdma_device *ioat_dma) { struct dma_device *dma = &ioat_dma->dma_dev; @@ -1181,9 +1169,9 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca) ioat_chan->reg_base + IOAT_DCACTRL_OFFSET); } - err = ioat_register(ioat_dma); + err = dma_async_device_register(&ioat_dma->dma_dev); if (err) - return err; + goto err_disable_interrupts; ioat_kobject_add(ioat_dma, &ioat_ktype); @@ -1192,20 +1180,29 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca) /* disable relaxed ordering */ err = pcie_capability_read_word(pdev, PCI_EXP_DEVCTL, &val16); - if (err) - return pcibios_err_to_errno(err); + if (err) { + err = pcibios_err_to_errno(err); + goto err_disable_interrupts; + } /* clear relaxed ordering enable */ val16 &= ~PCI_EXP_DEVCTL_RELAX_EN; err = pcie_capability_write_word(pdev, PCI_EXP_DEVCTL, val16); - if (err) - return pcibios_err_to_errno(err); + if (err) { + err = pcibios_err_to_errno(err); + goto err_disable_interrupts; + } if (ioat_dma->cap & IOAT_CAP_DPS) writeb(ioat_pending_level + 1, ioat_dma->reg_base + IOAT_PREFETCH_LIMIT_OFFSET); return 0; + +err_disable_interrupts: + ioat_disable_interrupts(ioat_dma); + dma_pool_destroy(ioat_dma->completion_pool); + return err; } static void ioat_shutdown(struct pci_dev *pdev) @@ -1350,6 +1347,8 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) void __iomem * const *iomap; struct device *dev = &pdev->dev; struct ioatdma_device *device; + unsigned int i; + u8 version; int err; err = pcim_enable_device(pdev); @@ -1363,6 +1362,10 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (!iomap) return -ENOMEM; + version = readb(iomap[IOAT_MMIO_BAR] + IOAT_VER_OFFSET); + if (version < IOAT_VER_3_0) + return -ENODEV; + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) return err; @@ -1373,17 +1376,18 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_master(pdev); pci_set_drvdata(pdev, device); - device->version = readb(device->reg_base + IOAT_VER_OFFSET); + device->version = version; if (device->version >= IOAT_VER_3_4) ioat_dca_enabled = 0; - if (device->version >= IOAT_VER_3_0) { - if (is_skx_ioat(pdev)) - device->version = IOAT_VER_3_2; - err = ioat3_dma_probe(device, ioat_dca_enabled); - } else - return -ENODEV; + if (is_skx_ioat(pdev)) + device->version = IOAT_VER_3_2; + + err = ioat3_dma_probe(device, ioat_dca_enabled); if (err) { + for (i = 0; i < IOAT_MAX_CHANS; i++) + kfree(device->idx[i]); + kfree(device); dev_err(dev, "Intel(R) I/OAT DMA Engine init failed\n"); return -ENODEV; } @@ -1445,6 +1449,7 @@ module_init(ioat_init_module); static void __exit ioat_exit_module(void) { pci_unregister_driver(&ioat_pci_driver); + kmem_cache_destroy(ioat_sed_cache); kmem_cache_destroy(ioat_cache); } module_exit(ioat_exit_module); diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c index 384476757c5e3a..3bcf73ef69dc7f 100644 --- a/drivers/dma/owl-dma.c +++ b/drivers/dma/owl-dma.c @@ -250,7 +250,7 @@ static void pchan_update(struct owl_dma_pchan *pchan, u32 reg, else regval &= ~val; - writel(val, pchan->base + reg); + writel(regval, pchan->base + reg); } static void pchan_writel(struct owl_dma_pchan *pchan, u32 reg, u32 data) @@ -274,7 +274,7 @@ static void dma_update(struct owl_dma *od, u32 reg, u32 val, bool state) else regval &= ~val; - writel(val, od->base + reg); + writel(regval, od->base + reg); } static void dma_writel(struct owl_dma *od, u32 reg, u32 data) diff --git a/drivers/dma/ptdma/ptdma-dmaengine.c b/drivers/dma/ptdma/ptdma-dmaengine.c index 1aa65e5de0f3ad..f792407348077d 100644 --- a/drivers/dma/ptdma/ptdma-dmaengine.c +++ b/drivers/dma/ptdma/ptdma-dmaengine.c @@ -385,8 +385,6 @@ int pt_dmaengine_register(struct pt_device *pt) chan->vc.desc_free = pt_do_cleanup; vchan_init(&chan->vc, dma_dev); - dma_set_mask_and_coherent(pt->dev, DMA_BIT_MASK(64)); - ret = dma_async_device_register(dma_dev); if (ret) goto err_reg; diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c index 1b046d9a3a269a..16d342654da2bf 100644 --- a/drivers/dma/pxa_dma.c +++ b/drivers/dma/pxa_dma.c @@ -722,7 +722,6 @@ static void pxad_free_desc(struct virt_dma_desc *vd) dma_addr_t dma; struct pxad_desc_sw *sw_desc = to_pxad_sw_desc(vd); - BUG_ON(sw_desc->nb_desc == 0); for (i = sw_desc->nb_desc - 1; i >= 0; i--) { if (i > 0) dma = sw_desc->hw_desc[i - 1]->ddadr; diff --git a/drivers/dma/sh/shdma.h b/drivers/dma/sh/shdma.h index 9c121a4b33ad82..f97d80343aea42 100644 --- a/drivers/dma/sh/shdma.h +++ b/drivers/dma/sh/shdma.h @@ -25,7 +25,7 @@ struct sh_dmae_chan { const struct sh_dmae_slave_config *config; /* Slave DMA configuration */ int xmit_shift; /* log_2(bytes_per_xfer) */ void __iomem *base; - char dev_id[16]; /* unique name per DMAC of channel */ + char dev_id[32]; /* unique name per DMAC of channel */ int pm_error; dma_addr_t slave_addr; }; diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c index 0b30151fb45c4c..9840594a6aaa1f 100644 --- a/drivers/dma/stm32-dma.c +++ b/drivers/dma/stm32-dma.c @@ -1249,8 +1249,8 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy( enum dma_slave_buswidth max_width; struct stm32_dma_desc *desc; size_t xfer_count, offset; - u32 num_sgs, best_burst, dma_burst, threshold; - int i; + u32 num_sgs, best_burst, threshold; + int dma_burst, i; num_sgs = DIV_ROUND_UP(len, STM32_DMA_ALIGNED_MAX_DATA_ITEMS); desc = kzalloc(struct_size(desc, sg_req, num_sgs), GFP_NOWAIT); @@ -1268,6 +1268,10 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy( best_burst = stm32_dma_get_best_burst(len, STM32_DMA_MAX_BURST, threshold, max_width); dma_burst = stm32_dma_get_burst(chan, best_burst); + if (dma_burst < 0) { + kfree(desc); + return NULL; + } stm32_dma_clear_reg(&desc->sg_req[i].chan_reg); desc->sg_req[i].chan_reg.dma_scr = diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c index bae08b3f55c73f..f414efdbd809e1 100644 --- a/drivers/dma/stm32-mdma.c +++ b/drivers/dma/stm32-mdma.c @@ -489,7 +489,7 @@ static int stm32_mdma_set_xfer_param(struct stm32_mdma_chan *chan, src_maxburst = chan->dma_config.src_maxburst; dst_maxburst = chan->dma_config.dst_maxburst; - ccr = stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id)); + ccr = stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id)) & ~STM32_MDMA_CCR_EN; ctcr = stm32_mdma_read(dmadev, STM32_MDMA_CTCR(chan->id)); ctbr = stm32_mdma_read(dmadev, STM32_MDMA_CTBR(chan->id)); @@ -965,7 +965,7 @@ stm32_mdma_prep_dma_memcpy(struct dma_chan *c, dma_addr_t dest, dma_addr_t src, if (!desc) return NULL; - ccr = stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id)); + ccr = stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id)) & ~STM32_MDMA_CCR_EN; ctcr = stm32_mdma_read(dmadev, STM32_MDMA_CTCR(chan->id)); ctbr = stm32_mdma_read(dmadev, STM32_MDMA_CTBR(chan->id)); cbndtr = stm32_mdma_read(dmadev, STM32_MDMA_CBNDTR(chan->id)); diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c index 33b10100110096..674cf630528383 100644 --- a/drivers/dma/tegra186-gpc-dma.c +++ b/drivers/dma/tegra186-gpc-dma.c @@ -746,6 +746,9 @@ static int tegra_dma_get_residual(struct tegra_dma_channel *tdc) bytes_xfer = dma_desc->bytes_xfer + sg_req[dma_desc->sg_idx].len - (wcount * 4); + if (dma_desc->bytes_req == bytes_xfer) + return 0; + residual = dma_desc->bytes_req - (bytes_xfer % dma_desc->bytes_req); return residual; diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index aa8e2e8ac26098..155c409d2b434d 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -2401,9 +2401,14 @@ static int edma_probe(struct platform_device *pdev) if (irq < 0 && node) irq = irq_of_parse_and_map(node, 0); - if (irq >= 0) { + if (irq > 0) { irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccint", dev_name(dev)); + if (!irq_name) { + ret = -ENOMEM; + goto err_disable_pm; + } + ret = devm_request_irq(dev, irq, dma_irq_handler, 0, irq_name, ecc); if (ret) { @@ -2417,9 +2422,14 @@ static int edma_probe(struct platform_device *pdev) if (irq < 0 && node) irq = irq_of_parse_and_map(node, 2); - if (irq >= 0) { + if (irq > 0) { irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccerrint", dev_name(dev)); + if (!irq_name) { + ret = -ENOMEM; + goto err_disable_pm; + } + ret = devm_request_irq(dev, irq, dma_ccerr_handler, 0, irq_name, ecc); if (ret) { diff --git a/drivers/dma/ti/k3-psil-am62.c b/drivers/dma/ti/k3-psil-am62.c index 2b6fd6e37c6107..1272b1541f61e2 100644 --- a/drivers/dma/ti/k3-psil-am62.c +++ b/drivers/dma/ti/k3-psil-am62.c @@ -74,7 +74,9 @@ static struct psil_ep am62_src_ep_map[] = { PSIL_SAUL(0x7505, 21, 35, 8, 36, 0), PSIL_SAUL(0x7506, 22, 43, 8, 43, 0), PSIL_SAUL(0x7507, 23, 43, 8, 44, 0), - /* PDMA_MAIN0 - SPI0-3 */ + /* PDMA_MAIN0 - SPI0-2 */ + PSIL_PDMA_XY_PKT(0x4300), + PSIL_PDMA_XY_PKT(0x4301), PSIL_PDMA_XY_PKT(0x4302), PSIL_PDMA_XY_PKT(0x4303), PSIL_PDMA_XY_PKT(0x4304), @@ -85,8 +87,6 @@ static struct psil_ep am62_src_ep_map[] = { PSIL_PDMA_XY_PKT(0x4309), PSIL_PDMA_XY_PKT(0x430a), PSIL_PDMA_XY_PKT(0x430b), - PSIL_PDMA_XY_PKT(0x430c), - PSIL_PDMA_XY_PKT(0x430d), /* PDMA_MAIN1 - UART0-6 */ PSIL_PDMA_XY_PKT(0x4400), PSIL_PDMA_XY_PKT(0x4401), @@ -141,7 +141,9 @@ static struct psil_ep am62_dst_ep_map[] = { /* SAUL */ PSIL_SAUL(0xf500, 27, 83, 8, 83, 1), PSIL_SAUL(0xf501, 28, 91, 8, 91, 1), - /* PDMA_MAIN0 - SPI0-3 */ + /* PDMA_MAIN0 - SPI0-2 */ + PSIL_PDMA_XY_PKT(0xc300), + PSIL_PDMA_XY_PKT(0xc301), PSIL_PDMA_XY_PKT(0xc302), PSIL_PDMA_XY_PKT(0xc303), PSIL_PDMA_XY_PKT(0xc304), @@ -152,8 +154,6 @@ static struct psil_ep am62_dst_ep_map[] = { PSIL_PDMA_XY_PKT(0xc309), PSIL_PDMA_XY_PKT(0xc30a), PSIL_PDMA_XY_PKT(0xc30b), - PSIL_PDMA_XY_PKT(0xc30c), - PSIL_PDMA_XY_PKT(0xc30d), /* PDMA_MAIN1 - UART0-6 */ PSIL_PDMA_XY_PKT(0xc400), PSIL_PDMA_XY_PKT(0xc401), diff --git a/drivers/dma/ti/k3-psil-am62a.c b/drivers/dma/ti/k3-psil-am62a.c index ca9d71f914220a..4cf9123b0e9326 100644 --- a/drivers/dma/ti/k3-psil-am62a.c +++ b/drivers/dma/ti/k3-psil-am62a.c @@ -84,7 +84,9 @@ static struct psil_ep am62a_src_ep_map[] = { PSIL_SAUL(0x7505, 21, 35, 8, 36, 0), PSIL_SAUL(0x7506, 22, 43, 8, 43, 0), PSIL_SAUL(0x7507, 23, 43, 8, 44, 0), - /* PDMA_MAIN0 - SPI0-3 */ + /* PDMA_MAIN0 - SPI0-2 */ + PSIL_PDMA_XY_PKT(0x4300), + PSIL_PDMA_XY_PKT(0x4301), PSIL_PDMA_XY_PKT(0x4302), PSIL_PDMA_XY_PKT(0x4303), PSIL_PDMA_XY_PKT(0x4304), @@ -95,8 +97,6 @@ static struct psil_ep am62a_src_ep_map[] = { PSIL_PDMA_XY_PKT(0x4309), PSIL_PDMA_XY_PKT(0x430a), PSIL_PDMA_XY_PKT(0x430b), - PSIL_PDMA_XY_PKT(0x430c), - PSIL_PDMA_XY_PKT(0x430d), /* PDMA_MAIN1 - UART0-6 */ PSIL_PDMA_XY_PKT(0x4400), PSIL_PDMA_XY_PKT(0x4401), @@ -151,7 +151,9 @@ static struct psil_ep am62a_dst_ep_map[] = { /* SAUL */ PSIL_SAUL(0xf500, 27, 83, 8, 83, 1), PSIL_SAUL(0xf501, 28, 91, 8, 91, 1), - /* PDMA_MAIN0 - SPI0-3 */ + /* PDMA_MAIN0 - SPI0-2 */ + PSIL_PDMA_XY_PKT(0xc300), + PSIL_PDMA_XY_PKT(0xc301), PSIL_PDMA_XY_PKT(0xc302), PSIL_PDMA_XY_PKT(0xc303), PSIL_PDMA_XY_PKT(0xc304), @@ -162,8 +164,6 @@ static struct psil_ep am62a_dst_ep_map[] = { PSIL_PDMA_XY_PKT(0xc309), PSIL_PDMA_XY_PKT(0xc30a), PSIL_PDMA_XY_PKT(0xc30b), - PSIL_PDMA_XY_PKT(0xc30c), - PSIL_PDMA_XY_PKT(0xc30d), /* PDMA_MAIN1 - UART0-6 */ PSIL_PDMA_XY_PKT(0xc400), PSIL_PDMA_XY_PKT(0xc401), diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index 30fd2f386f36a1..02a1ab04f498e5 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -3968,6 +3968,7 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc, { struct udma_chan *uc = to_udma_chan(&vc->chan); struct udma_desc *d; + u8 status; if (!vd) return; @@ -3977,12 +3978,12 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc, if (d->metadata_size) udma_fetch_epib(uc, d); - /* Provide residue information for the client */ if (result) { void *desc_vaddr = udma_curr_cppi5_desc_vaddr(d, d->desc_idx); if (cppi5_desc_get_type(desc_vaddr) == CPPI5_INFO0_DESC_TYPE_VAL_HOST) { + /* Provide residue information for the client */ result->residue = d->residue - cppi5_hdesc_get_pktlen(desc_vaddr); if (result->residue) @@ -3991,7 +3992,12 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc, result->result = DMA_TRANS_NOERROR; } else { result->residue = 0; - result->result = DMA_TRANS_NOERROR; + /* Propagate TR Response errors to the client */ + status = d->hwdesc[0].tr_resp_base->status; + if (status) + result->result = DMA_TRANS_ABORTED; + else + result->result = DMA_TRANS_NOERROR; } } } @@ -4464,7 +4470,9 @@ static int udma_get_mmrs(struct platform_device *pdev, struct udma_dev *ud) ud->rchan_cnt = UDMA_CAP2_RCHAN_CNT(cap2); break; case DMA_TYPE_BCDMA: - ud->bchan_cnt = BCDMA_CAP2_BCHAN_CNT(cap2); + ud->bchan_cnt = BCDMA_CAP2_BCHAN_CNT(cap2) + + BCDMA_CAP3_HBCHAN_CNT(cap3) + + BCDMA_CAP3_UBCHAN_CNT(cap3); ud->tchan_cnt = BCDMA_CAP2_TCHAN_CNT(cap2); ud->rchan_cnt = BCDMA_CAP2_RCHAN_CNT(cap2); ud->rflow_cnt = ud->rchan_cnt; diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c index 84dc5240a8074a..93938ed80fc837 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -214,7 +214,8 @@ struct xilinx_dpdma_tx_desc { * @running: true if the channel is running * @first_frame: flag for the first frame of stream * @video_group: flag if multi-channel operation is needed for video channels - * @lock: lock to access struct xilinx_dpdma_chan + * @lock: lock to access struct xilinx_dpdma_chan. Must be taken before + * @vchan.lock, if both are to be held. * @desc_pool: descriptor allocation pool * @err_task: error IRQ bottom half handler * @desc: References to descriptors being processed @@ -1097,12 +1098,14 @@ static void xilinx_dpdma_chan_vsync_irq(struct xilinx_dpdma_chan *chan) * Complete the active descriptor, if any, promote the pending * descriptor to active, and queue the next transfer, if any. */ + spin_lock(&chan->vchan.lock); if (chan->desc.active) vchan_cookie_complete(&chan->desc.active->vdesc); chan->desc.active = pending; chan->desc.pending = NULL; xilinx_dpdma_chan_queue_transfer(chan); + spin_unlock(&chan->vchan.lock); out: spin_unlock_irqrestore(&chan->lock, flags); @@ -1264,10 +1267,12 @@ static void xilinx_dpdma_issue_pending(struct dma_chan *dchan) struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan); unsigned long flags; - spin_lock_irqsave(&chan->vchan.lock, flags); + spin_lock_irqsave(&chan->lock, flags); + spin_lock(&chan->vchan.lock); if (vchan_issue_pending(&chan->vchan)) xilinx_dpdma_chan_queue_transfer(chan); - spin_unlock_irqrestore(&chan->vchan.lock, flags); + spin_unlock(&chan->vchan.lock); + spin_unlock_irqrestore(&chan->lock, flags); } static int xilinx_dpdma_config(struct dma_chan *dchan, @@ -1495,7 +1500,9 @@ static void xilinx_dpdma_chan_err_task(struct tasklet_struct *t) XILINX_DPDMA_EINTR_CHAN_ERR_MASK << chan->id); spin_lock_irqsave(&chan->lock, flags); + spin_lock(&chan->vchan.lock); xilinx_dpdma_chan_queue_transfer(chan); + spin_unlock(&chan->vchan.lock); spin_unlock_irqrestore(&chan->lock, flags); } diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index 61945d3113cc32..446364264e2b18 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -54,11 +54,13 @@ obj-$(CONFIG_EDAC_MPC85XX) += mpc85xx_edac_mod.o layerscape_edac_mod-y := fsl_ddr_edac.o layerscape_edac.o obj-$(CONFIG_EDAC_LAYERSCAPE) += layerscape_edac_mod.o -skx_edac-y := skx_common.o skx_base.o -obj-$(CONFIG_EDAC_SKX) += skx_edac.o +skx_edac_common-y := skx_common.o -i10nm_edac-y := skx_common.o i10nm_base.o -obj-$(CONFIG_EDAC_I10NM) += i10nm_edac.o +skx_edac-y := skx_base.o +obj-$(CONFIG_EDAC_SKX) += skx_edac.o skx_edac_common.o + +i10nm_edac-y := i10nm_base.o +obj-$(CONFIG_EDAC_I10NM) += i10nm_edac.o skx_edac_common.o obj-$(CONFIG_EDAC_CELL) += cell_edac.o obj-$(CONFIG_EDAC_PPC4XX) += ppc4xx_edac.o diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 9b6642d0087130..b61c7f02a8c17c 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -80,7 +80,7 @@ int __amd64_read_pci_cfg_dword(struct pci_dev *pdev, int offset, amd64_warn("%s: error reading F%dx%03x.\n", func, PCI_FUNC(pdev->devfn), offset); - return err; + return pcibios_err_to_errno(err); } int __amd64_write_pci_cfg_dword(struct pci_dev *pdev, int offset, @@ -93,7 +93,7 @@ int __amd64_write_pci_cfg_dword(struct pci_dev *pdev, int offset, amd64_warn("%s: error writing to F%dx%03x.\n", func, PCI_FUNC(pdev->devfn), offset); - return err; + return pcibios_err_to_errno(err); } /* @@ -1016,8 +1016,10 @@ static int gpu_get_node_map(void) } ret = pci_read_config_dword(pdev, REG_LOCAL_NODE_TYPE_MAP, &tmp); - if (ret) + if (ret) { + ret = pcibios_err_to_errno(ret); goto out; + } gpu_node_map.node_count = FIELD_GET(LNTM_NODE_COUNT, tmp); gpu_node_map.base_node_id = FIELD_GET(LNTM_BASE_NODE_ID, tmp); diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index 1a18693294db48..a0edb61a5a01ac 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -245,7 +245,7 @@ static u64 ehl_err_addr_to_imc_addr(u64 eaddr, int mc) if (igen6_tom <= _4GB) return eaddr + igen6_tolud - _4GB; - if (eaddr < _4GB) + if (eaddr >= igen6_tom) return eaddr + igen6_tolud - igen6_tom; return eaddr; @@ -627,7 +627,7 @@ static int errcmd_enable_error_reporting(bool enable) rc = pci_read_config_word(imc->pdev, ERRCMD_OFFSET, &errcmd); if (rc) - return rc; + return pcibios_err_to_errno(rc); if (enable) errcmd |= ERRCMD_CE | ERRSTS_UE; @@ -636,7 +636,7 @@ static int errcmd_enable_error_reporting(bool enable) rc = pci_write_config_word(imc->pdev, ERRCMD_OFFSET, errcmd); if (rc) - return rc; + return pcibios_err_to_errno(rc); return 0; } diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index ce3e0069e028d0..8d18099fd528cf 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -48,7 +48,7 @@ static u64 skx_tolm, skx_tohm; static LIST_HEAD(dev_edac_list); static bool skx_mem_cfg_2lm; -int __init skx_adxl_get(void) +int skx_adxl_get(void) { const char * const *names; int i, j; @@ -110,12 +110,14 @@ int __init skx_adxl_get(void) return -ENODEV; } +EXPORT_SYMBOL_GPL(skx_adxl_get); -void __exit skx_adxl_put(void) +void skx_adxl_put(void) { kfree(adxl_values); kfree(adxl_msg); } +EXPORT_SYMBOL_GPL(skx_adxl_put); static bool skx_adxl_decode(struct decoded_addr *res, bool error_in_1st_level_mem) { @@ -187,12 +189,14 @@ void skx_set_mem_cfg(bool mem_cfg_2lm) { skx_mem_cfg_2lm = mem_cfg_2lm; } +EXPORT_SYMBOL_GPL(skx_set_mem_cfg); void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log) { driver_decode = decode; skx_show_retry_rd_err_log = show_retry_log; } +EXPORT_SYMBOL_GPL(skx_set_decode); int skx_get_src_id(struct skx_dev *d, int off, u8 *id) { @@ -206,6 +210,7 @@ int skx_get_src_id(struct skx_dev *d, int off, u8 *id) *id = GET_BITFIELD(reg, 12, 14); return 0; } +EXPORT_SYMBOL_GPL(skx_get_src_id); int skx_get_node_id(struct skx_dev *d, u8 *id) { @@ -219,6 +224,7 @@ int skx_get_node_id(struct skx_dev *d, u8 *id) *id = GET_BITFIELD(reg, 0, 2); return 0; } +EXPORT_SYMBOL_GPL(skx_get_node_id); static int get_width(u32 mtr) { @@ -284,6 +290,7 @@ int skx_get_all_bus_mappings(struct res_config *cfg, struct list_head **list) *list = &dev_edac_list; return ndev; } +EXPORT_SYMBOL_GPL(skx_get_all_bus_mappings); int skx_get_hi_lo(unsigned int did, int off[], u64 *tolm, u64 *tohm) { @@ -323,6 +330,7 @@ int skx_get_hi_lo(unsigned int did, int off[], u64 *tolm, u64 *tohm) pci_dev_put(pdev); return -ENODEV; } +EXPORT_SYMBOL_GPL(skx_get_hi_lo); static int skx_get_dimm_attr(u32 reg, int lobit, int hibit, int add, int minval, int maxval, const char *name) @@ -394,6 +402,7 @@ int skx_get_dimm_info(u32 mtr, u32 mcmtr, u32 amap, struct dimm_info *dimm, return 1; } +EXPORT_SYMBOL_GPL(skx_get_dimm_info); int skx_get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc, int chan, int dimmno, const char *mod_str) @@ -442,6 +451,7 @@ int skx_get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc, return (size == 0 || size == ~0ull) ? 0 : 1; } +EXPORT_SYMBOL_GPL(skx_get_nvdimm_info); int skx_register_mci(struct skx_imc *imc, struct pci_dev *pdev, const char *ctl_name, const char *mod_str, @@ -512,6 +522,7 @@ int skx_register_mci(struct skx_imc *imc, struct pci_dev *pdev, imc->mci = NULL; return rc; } +EXPORT_SYMBOL_GPL(skx_register_mci); static void skx_unregister_mci(struct skx_imc *imc) { @@ -648,6 +659,10 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val, memset(&res, 0, sizeof(res)); res.mce = mce; res.addr = mce->addr & MCI_ADDR_PHYSADDR; + if (!pfn_to_online_page(res.addr >> PAGE_SHIFT) && !arch_is_platform_page(res.addr)) { + pr_err("Invalid address 0x%llx in IA32_MC%d_ADDR\n", mce->addr, mce->bank); + return NOTIFY_DONE; + } /* Try driver decoder first */ if (!(driver_decode && driver_decode(&res))) { @@ -684,6 +699,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val, mce->kflags |= MCE_HANDLED_EDAC; return NOTIFY_DONE; } +EXPORT_SYMBOL_GPL(skx_mce_check_error); void skx_remove(void) { @@ -721,3 +737,8 @@ void skx_remove(void) kfree(d); } } +EXPORT_SYMBOL_GPL(skx_remove); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Tony Luck"); +MODULE_DESCRIPTION("MC Driver for Intel server processors"); diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h index b6d3607dffe27b..11faf1db4fa482 100644 --- a/drivers/edac/skx_common.h +++ b/drivers/edac/skx_common.h @@ -231,8 +231,8 @@ typedef int (*get_dimm_config_f)(struct mem_ctl_info *mci, typedef bool (*skx_decode_f)(struct decoded_addr *res); typedef void (*skx_show_retry_log_f)(struct decoded_addr *res, char *msg, int len, bool scrub_err); -int __init skx_adxl_get(void); -void __exit skx_adxl_put(void); +int skx_adxl_get(void); +void skx_adxl_put(void); void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log); void skx_set_mem_cfg(bool mem_cfg_2lm); diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index c4fc64cbecd0e6..6ddc90d7ba7c2a 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -9,6 +9,8 @@ #include #include #include +#include +#include #include #include @@ -299,6 +301,7 @@ struct synps_ecc_status { /** * struct synps_edac_priv - DDR memory controller private instance data. * @baseaddr: Base address of the DDR controller. + * @reglock: Concurrent CSRs access lock. * @message: Buffer for framing the event specific info. * @stat: ECC status information. * @p_data: Platform data. @@ -313,6 +316,7 @@ struct synps_ecc_status { */ struct synps_edac_priv { void __iomem *baseaddr; + spinlock_t reglock; char message[SYNPS_EDAC_MSG_SIZE]; struct synps_ecc_status stat; const struct synps_platform_data *p_data; @@ -334,6 +338,7 @@ struct synps_edac_priv { * @get_mtype: Get mtype. * @get_dtype: Get dtype. * @get_ecc_state: Get ECC state. + * @get_mem_info: Get EDAC memory info * @quirks: To differentiate IPs. */ struct synps_platform_data { @@ -341,6 +346,9 @@ struct synps_platform_data { enum mem_type (*get_mtype)(const void __iomem *base); enum dev_type (*get_dtype)(const void __iomem *base); bool (*get_ecc_state)(void __iomem *base); +#ifdef CONFIG_EDAC_DEBUG + u64 (*get_mem_info)(struct synps_edac_priv *priv); +#endif int quirks; }; @@ -399,6 +407,25 @@ static int zynq_get_error_info(struct synps_edac_priv *priv) return 0; } +#ifdef CONFIG_EDAC_DEBUG +/** + * zynqmp_get_mem_info - Get the current memory info. + * @priv: DDR memory controller private instance data. + * + * Return: host interface address. + */ +static u64 zynqmp_get_mem_info(struct synps_edac_priv *priv) +{ + u64 hif_addr = 0, linear_addr; + + linear_addr = priv->poison_addr; + if (linear_addr >= SZ_32G) + linear_addr = linear_addr - SZ_32G + SZ_2G; + hif_addr = linear_addr >> 3; + return hif_addr; +} +#endif + /** * zynqmp_get_error_info - Get the current ECC error info. * @priv: DDR memory controller private instance data. @@ -408,7 +435,8 @@ static int zynq_get_error_info(struct synps_edac_priv *priv) static int zynqmp_get_error_info(struct synps_edac_priv *priv) { struct synps_ecc_status *p; - u32 regval, clearval = 0; + u32 regval, clearval; + unsigned long flags; void __iomem *base; base = priv->baseaddr; @@ -452,10 +480,14 @@ static int zynqmp_get_error_info(struct synps_edac_priv *priv) p->ueinfo.blknr = (regval & ECC_CEADDR1_BLKNR_MASK); p->ueinfo.data = readl(base + ECC_UESYND0_OFST); out: - clearval = ECC_CTRL_CLR_CE_ERR | ECC_CTRL_CLR_CE_ERRCNT; - clearval |= ECC_CTRL_CLR_UE_ERR | ECC_CTRL_CLR_UE_ERRCNT; + spin_lock_irqsave(&priv->reglock, flags); + + clearval = readl(base + ECC_CLR_OFST) | + ECC_CTRL_CLR_CE_ERR | ECC_CTRL_CLR_CE_ERRCNT | + ECC_CTRL_CLR_UE_ERR | ECC_CTRL_CLR_UE_ERRCNT; writel(clearval, base + ECC_CLR_OFST); - writel(0x0, base + ECC_CLR_OFST); + + spin_unlock_irqrestore(&priv->reglock, flags); return 0; } @@ -515,24 +547,41 @@ static void handle_error(struct mem_ctl_info *mci, struct synps_ecc_status *p) static void enable_intr(struct synps_edac_priv *priv) { + unsigned long flags; + /* Enable UE/CE Interrupts */ - if (priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR) - writel(DDR_UE_MASK | DDR_CE_MASK, - priv->baseaddr + ECC_CLR_OFST); - else + if (!(priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)) { writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK, priv->baseaddr + DDR_QOS_IRQ_EN_OFST); + return; + } + + spin_lock_irqsave(&priv->reglock, flags); + + writel(DDR_UE_MASK | DDR_CE_MASK, + priv->baseaddr + ECC_CLR_OFST); + + spin_unlock_irqrestore(&priv->reglock, flags); } static void disable_intr(struct synps_edac_priv *priv) { + unsigned long flags; + /* Disable UE/CE Interrupts */ - if (priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR) - writel(0x0, priv->baseaddr + ECC_CLR_OFST); - else + if (!(priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)) { writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK, priv->baseaddr + DDR_QOS_IRQ_DB_OFST); + + return; + } + + spin_lock_irqsave(&priv->reglock, flags); + + writel(0, priv->baseaddr + ECC_CLR_OFST); + + spin_unlock_irqrestore(&priv->reglock, flags); } /** @@ -576,8 +625,6 @@ static irqreturn_t intr_handler(int irq, void *dev_id) /* v3.0 of the controller does not have this register */ if (!(priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)) writel(regval, priv->baseaddr + DDR_QOS_IRQ_STAT_OFST); - else - enable_intr(priv); return IRQ_HANDLED; } @@ -899,6 +946,9 @@ static const struct synps_platform_data zynqmp_edac_def = { .get_mtype = zynqmp_get_mtype, .get_dtype = zynqmp_get_dtype, .get_ecc_state = zynqmp_get_ecc_state, +#ifdef CONFIG_EDAC_DEBUG + .get_mem_info = zynqmp_get_mem_info, +#endif .quirks = (DDR_ECC_INTR_SUPPORT #ifdef CONFIG_EDAC_DEBUG | DDR_ECC_DATA_POISON_SUPPORT @@ -952,10 +1002,16 @@ MODULE_DEVICE_TABLE(of, synps_edac_match); static void ddr_poison_setup(struct synps_edac_priv *priv) { int col = 0, row = 0, bank = 0, bankgrp = 0, rank = 0, regval; + const struct synps_platform_data *p_data; int index; ulong hif_addr = 0; - hif_addr = priv->poison_addr >> 3; + p_data = priv->p_data; + + if (p_data->get_mem_info) + hif_addr = p_data->get_mem_info(priv); + else + hif_addr = priv->poison_addr >> 3; for (index = 0; index < DDR_MAX_ROW_SHIFT; index++) { if (priv->row_shift[index]) @@ -1359,6 +1415,7 @@ static int mc_probe(struct platform_device *pdev) priv = mci->pvt_info; priv->baseaddr = baseaddr; priv->p_data = p_data; + spin_lock_init(&priv->reglock); mc_init(mci, pdev); diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c index b9c5772da959cc..90d46e5c4ff069 100644 --- a/drivers/edac/thunderx_edac.c +++ b/drivers/edac/thunderx_edac.c @@ -1133,7 +1133,7 @@ static irqreturn_t thunderx_ocx_com_threaded_isr(int irq, void *irq_id) decode_register(other, OCX_OTHER_SIZE, ocx_com_errors, ctx->reg_com_int); - strncat(msg, other, OCX_MESSAGE_SIZE); + strlcat(msg, other, OCX_MESSAGE_SIZE); for (lane = 0; lane < OCX_RX_LANES; lane++) if (ctx->reg_com_int & BIT(lane)) { @@ -1142,12 +1142,12 @@ static irqreturn_t thunderx_ocx_com_threaded_isr(int irq, void *irq_id) lane, ctx->reg_lane_int[lane], lane, ctx->reg_lane_stat11[lane]); - strncat(msg, other, OCX_MESSAGE_SIZE); + strlcat(msg, other, OCX_MESSAGE_SIZE); decode_register(other, OCX_OTHER_SIZE, ocx_lane_errors, ctx->reg_lane_int[lane]); - strncat(msg, other, OCX_MESSAGE_SIZE); + strlcat(msg, other, OCX_MESSAGE_SIZE); } if (ctx->reg_com_int & OCX_COM_INT_CE) @@ -1217,7 +1217,7 @@ static irqreturn_t thunderx_ocx_lnk_threaded_isr(int irq, void *irq_id) decode_register(other, OCX_OTHER_SIZE, ocx_com_link_errors, ctx->reg_com_link_int); - strncat(msg, other, OCX_MESSAGE_SIZE); + strlcat(msg, other, OCX_MESSAGE_SIZE); if (ctx->reg_com_link_int & OCX_COM_LINK_INT_UE) edac_device_handle_ue(ocx->edac_dev, 0, 0, msg); @@ -1896,7 +1896,7 @@ static irqreturn_t thunderx_l2c_threaded_isr(int irq, void *irq_id) decode_register(other, L2C_OTHER_SIZE, l2_errors, ctx->reg_int); - strncat(msg, other, L2C_MESSAGE_SIZE); + strlcat(msg, other, L2C_MESSAGE_SIZE); if (ctx->reg_int & mask_ue) edac_device_handle_ue(l2c->edac_dev, 0, 0, msg); diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig index 8de9023c2a3878..cf472e44c5ff90 100644 --- a/drivers/extcon/Kconfig +++ b/drivers/extcon/Kconfig @@ -116,7 +116,8 @@ config EXTCON_MAX77843 config EXTCON_MAX8997 tristate "Maxim MAX8997 EXTCON Support" - depends on MFD_MAX8997 && IRQ_DOMAIN + depends on MFD_MAX8997 + select IRQ_DOMAIN help If you say yes here you get support for the MUIC device of Maxim MAX8997 PMIC. The MAX8997 MUIC is a USB port accessory diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c index 6f7a60d2ed9161..e7f55c021e562f 100644 --- a/drivers/extcon/extcon.c +++ b/drivers/extcon/extcon.c @@ -1280,8 +1280,6 @@ int extcon_dev_register(struct extcon_dev *edev) edev->id = ret; - dev_set_name(&edev->dev, "extcon%d", edev->id); - ret = extcon_alloc_cables(edev); if (ret < 0) goto err_alloc_cables; @@ -1310,6 +1308,7 @@ int extcon_dev_register(struct extcon_dev *edev) RAW_INIT_NOTIFIER_HEAD(&edev->nh_all); dev_set_drvdata(&edev->dev, edev); + dev_set_name(&edev->dev, "extcon%d", edev->id); edev->state = 0; ret = device_register(&edev->dev); diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index 6ac5ff20a2fe22..401a77e3b5fa8e 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -429,7 +429,23 @@ static void bm_work(struct work_struct *work) */ card->bm_generation = generation; - if (root_device == NULL) { + if (card->gap_count == 0) { + /* + * If self IDs have inconsistent gap counts, do a + * bus reset ASAP. The config rom read might never + * complete, so don't wait for it. However, still + * send a PHY configuration packet prior to the + * bus reset. The PHY configuration packet might + * fail, but 1394-2008 8.4.5.2 explicitly permits + * it in this case, so it should be safe to try. + */ + new_root_id = local_id; + /* + * We must always send a bus reset if the gap count + * is inconsistent, so bypass the 5-reset limit. + */ + card->bm_retries = 0; + } else if (root_device == NULL) { /* * Either link_on is false, or we failed to read the * config rom. In either case, pick another root. @@ -484,7 +500,19 @@ static void bm_work(struct work_struct *work) fw_notice(card, "phy config: new root=%x, gap_count=%d\n", new_root_id, gap_count); fw_send_phy_config(card, new_root_id, generation, gap_count); - reset_bus(card, true); + /* + * Where possible, use a short bus reset to minimize + * disruption to isochronous transfers. But in the event + * of a gap count inconsistency, use a long bus reset. + * + * As noted in 1394a 8.4.6.2, nodes on a mixed 1394/1394a bus + * may set different gap counts after a bus reset. On a mixed + * 1394/1394a bus, a short bus reset can get doubled. Some + * nodes may treat the double reset as one bus reset and others + * may treat it as two, causing a gap count inconsistency + * again. Using a long bus reset prevents this. + */ + reset_bus(card, card->gap_count != 0); /* Will allocate broadcast channel after the reset. */ goto out; } diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 6274b86eb94377..73cc2f2dcbf923 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -598,11 +598,11 @@ static void complete_transaction(struct fw_card *card, int rcode, u32 request_ts queue_event(client, &e->event, rsp, sizeof(*rsp) + rsp->length, NULL, 0); break; + } default: WARN_ON(1); break; } - } /* Drop the idr's reference */ client_put(client); diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index aa597cda0d8874..da8a4c8f287687 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -100,10 +100,9 @@ static int textual_leaf_to_string(const u32 *block, char *buf, size_t size) * @buf: where to put the string * @size: size of @buf, in bytes * - * The string is taken from a minimal ASCII text descriptor leaf after - * the immediate entry with @key. The string is zero-terminated. - * An overlong string is silently truncated such that it and the - * zero byte fit into @size. + * The string is taken from a minimal ASCII text descriptor leaf just after the entry with the + * @key. The string is zero-terminated. An overlong string is silently truncated such that it + * and the zero byte fit into @size. * * Returns strlen(buf) or a negative error code. */ @@ -717,14 +716,11 @@ static void create_units(struct fw_device *device) fw_unit_attributes, &unit->attribute_group); - if (device_register(&unit->device) < 0) - goto skip_unit; - fw_device_get(device); - continue; - - skip_unit: - kfree(unit); + if (device_register(&unit->device) < 0) { + put_device(&unit->device); + continue; + } } } diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c index b0d671db178a85..ea31ac7ac1ca93 100644 --- a/drivers/firewire/nosy.c +++ b/drivers/firewire/nosy.c @@ -148,10 +148,12 @@ packet_buffer_get(struct client *client, char __user *data, size_t user_length) if (atomic_read(&buffer->size) == 0) return -ENODEV; - /* FIXME: Check length <= user_length. */ + length = buffer->head->length; + + if (length > user_length) + return 0; end = buffer->data + buffer->capacity; - length = buffer->head->length; if (&buffer->head->data[length] < end) { if (copy_to_user(data, buffer->head->data, length)) diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 7e88fd4897414b..b9ae0340b8a703 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -279,6 +279,51 @@ static char ohci_driver_name[] = KBUILD_MODNAME; #define QUIRK_TI_SLLZ059 0x20 #define QUIRK_IR_WAKE 0x40 +// On PCI Express Root Complex in any type of AMD Ryzen machine, VIA VT6306/6307/6308 with Asmedia +// ASM1083/1085 brings an inconvenience that the read accesses to 'Isochronous Cycle Timer' register +// (at offset 0xf0 in PCI I/O space) often causes unexpected system reboot. The mechanism is not +// clear, since the read access to the other registers is enough safe; e.g. 'Node ID' register, +// while it is probable due to detection of any type of PCIe error. +#define QUIRK_REBOOT_BY_CYCLE_TIMER_READ 0x80000000 + +#if IS_ENABLED(CONFIG_X86) + +static bool has_reboot_by_cycle_timer_read_quirk(const struct fw_ohci *ohci) +{ + return !!(ohci->quirks & QUIRK_REBOOT_BY_CYCLE_TIMER_READ); +} + +#define PCI_DEVICE_ID_ASMEDIA_ASM108X 0x1080 + +static bool detect_vt630x_with_asm1083_on_amd_ryzen_machine(const struct pci_dev *pdev) +{ + const struct pci_dev *pcie_to_pci_bridge; + + // Detect any type of AMD Ryzen machine. + if (!static_cpu_has(X86_FEATURE_ZEN)) + return false; + + // Detect VIA VT6306/6307/6308. + if (pdev->vendor != PCI_VENDOR_ID_VIA) + return false; + if (pdev->device != PCI_DEVICE_ID_VIA_VT630X) + return false; + + // Detect Asmedia ASM1083/1085. + pcie_to_pci_bridge = pdev->bus->self; + if (pcie_to_pci_bridge->vendor != PCI_VENDOR_ID_ASMEDIA) + return false; + if (pcie_to_pci_bridge->device != PCI_DEVICE_ID_ASMEDIA_ASM108X) + return false; + + return true; +} + +#else +#define has_reboot_by_cycle_timer_read_quirk(ohci) false +#define detect_vt630x_with_asm1083_on_amd_ryzen_machine(pdev) false +#endif + /* In case of multiple matches in ohci_quirks[], only the first one is used. */ static const struct { unsigned short vendor, device, revision, flags; @@ -1511,6 +1556,8 @@ static int handle_at_packet(struct context *context, #define HEADER_GET_DATA_LENGTH(q) (((q) >> 16) & 0xffff) #define HEADER_GET_EXTENDED_TCODE(q) (((q) >> 0) & 0xffff) +static u32 get_cycle_time(struct fw_ohci *ohci); + static void handle_local_rom(struct fw_ohci *ohci, struct fw_packet *packet, u32 csr) { @@ -1535,6 +1582,8 @@ static void handle_local_rom(struct fw_ohci *ohci, (void *) ohci->config_rom + i, length); } + // Timestamping on behalf of the hardware. + response.timestamp = cycle_time_to_ohci_tstamp(get_cycle_time(ohci)); fw_core_handle_response(&ohci->card, &response); } @@ -1583,6 +1632,8 @@ static void handle_local_lock(struct fw_ohci *ohci, fw_fill_response(&response, packet->header, RCODE_BUSY, NULL, 0); out: + // Timestamping on behalf of the hardware. + response.timestamp = cycle_time_to_ohci_tstamp(get_cycle_time(ohci)); fw_core_handle_response(&ohci->card, &response); } @@ -1625,8 +1676,6 @@ static void handle_local_request(struct context *ctx, struct fw_packet *packet) } } -static u32 get_cycle_time(struct fw_ohci *ohci); - static void at_context_transmit(struct context *ctx, struct fw_packet *packet) { unsigned long flags; @@ -1724,6 +1773,9 @@ static u32 get_cycle_time(struct fw_ohci *ohci) s32 diff01, diff12; int i; + if (has_reboot_by_cycle_timer_read_quirk(ohci)) + return 0; + c2 = reg_read(ohci, OHCI1394_IsochronousCycleTimer); if (ohci->quirks & QUIRK_CYCLE_TIMER) { @@ -2012,6 +2064,8 @@ static void bus_reset_work(struct work_struct *work) ohci->generation = generation; reg_write(ohci, OHCI1394_IntEventClear, OHCI1394_busReset); + if (param_debug & OHCI_PARAM_DEBUG_BUSRESETS) + reg_write(ohci, OHCI1394_IntMaskSet, OHCI1394_busReset); if (ohci->quirks & QUIRK_RESET_PACKET) ohci->request_generation = generation; @@ -2077,12 +2131,14 @@ static irqreturn_t irq_handler(int irq, void *data) return IRQ_NONE; /* - * busReset and postedWriteErr must not be cleared yet + * busReset and postedWriteErr events must not be cleared yet * (OHCI 1.1 clauses 7.2.3.2 and 13.2.8.1) */ reg_write(ohci, OHCI1394_IntEventClear, event & ~(OHCI1394_busReset | OHCI1394_postedWriteErr)); log_irqs(ohci, event); + if (event & OHCI1394_busReset) + reg_write(ohci, OHCI1394_IntMaskClear, OHCI1394_busReset); if (event & OHCI1394_selfIDComplete) queue_work(selfid_workqueue, &ohci->bus_reset_work); @@ -3630,6 +3686,9 @@ static int pci_probe(struct pci_dev *dev, if (param_quirks) ohci->quirks = param_quirks; + if (detect_vt630x_with_asm1083_on_amd_ryzen_machine(dev)) + ohci->quirks |= QUIRK_REBOOT_BY_CYCLE_TIMER_READ; + /* * Because dma_alloc_coherent() allocates at least one page, * we save space by using a common buffer for the AR request/ @@ -3722,6 +3781,7 @@ static int pci_probe(struct pci_dev *dev, return 0; fail_msi: + devm_free_irq(&dev->dev, dev->irq, ohci); pci_disable_msi(dev); return err; @@ -3749,6 +3809,7 @@ static void pci_remove(struct pci_dev *dev) software_reset(ohci); + devm_free_irq(&dev->dev, dev->irq, ohci); pci_disable_msi(dev); dev_notice(&dev->dev, "removing fw-ohci device\n"); diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index 7edf2c95282fa2..e779d866022b9f 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -1519,9 +1519,9 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev) sdev->use_10_for_rw = 1; if (sbp2_param_exclusive_login) { - sdev->manage_system_start_stop = true; - sdev->manage_runtime_start_stop = true; - sdev->manage_shutdown = true; + sdev->manage_system_start_stop = 1; + sdev->manage_runtime_start_stop = 1; + sdev->manage_shutdown = 1; } if (sdev->type == TYPE_ROM) diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index b59e3041fd6275..f0e9f250669e2f 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -229,6 +229,7 @@ config QCOM_SCM_DOWNLOAD_MODE_DEFAULT config SYSFB bool select BOOT_VESA_SUPPORT + select SCREEN_INFO config SYSFB_SIMPLEFB bool "Mark VGA/VBE/EFI FB as generic system framebuffer" diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index 2b8bfcd010f5fd..7865438b36960d 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -193,6 +193,7 @@ struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, dev->release = ffa_release_device; dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id); + ffa_dev->id = id; ffa_dev->vm_id = vm_id; ffa_dev->ops = ops; uuid_copy(&ffa_dev->uuid, uuid); diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 121f4fc903cd57..7cd6b1564e8018 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -587,17 +587,9 @@ static int ffa_partition_info_get(const char *uuid_str, return 0; } -static void _ffa_mode_32bit_set(struct ffa_device *dev) -{ - dev->mode_32bit = true; -} - static void ffa_mode_32bit_set(struct ffa_device *dev) { - if (drv_info->version > FFA_VERSION_1_0) - return; - - _ffa_mode_32bit_set(dev); + dev->mode_32bit = true; } static int ffa_sync_send_receive(struct ffa_device *dev, @@ -706,7 +698,7 @@ static void ffa_setup_partitions(void) if (drv_info->version > FFA_VERSION_1_0 && !(tpbuf->properties & FFA_PARTITION_AARCH64_EXEC)) - _ffa_mode_32bit_set(ffa_dev); + ffa_mode_32bit_set(ffa_dev); } kfree(pbuf); } diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h index c46dc5215af7a7..00b165d1f502df 100644 --- a/drivers/firmware/arm_scmi/common.h +++ b/drivers/firmware/arm_scmi/common.h @@ -314,6 +314,7 @@ void shmem_fetch_notification(struct scmi_shared_mem __iomem *shmem, void shmem_clear_channel(struct scmi_shared_mem __iomem *shmem); bool shmem_poll_done(struct scmi_shared_mem __iomem *shmem, struct scmi_xfer *xfer); +bool shmem_channel_free(struct scmi_shared_mem __iomem *shmem); /* declarations for message passing transports */ struct scmi_msg_payld; diff --git a/drivers/firmware/arm_scmi/mailbox.c b/drivers/firmware/arm_scmi/mailbox.c index 19246ed1f01ff7..b8d470417e8f99 100644 --- a/drivers/firmware/arm_scmi/mailbox.c +++ b/drivers/firmware/arm_scmi/mailbox.c @@ -45,6 +45,20 @@ static void rx_callback(struct mbox_client *cl, void *m) { struct scmi_mailbox *smbox = client_to_scmi_mailbox(cl); + /* + * An A2P IRQ is NOT valid when received while the platform still has + * the ownership of the channel, because the platform at first releases + * the SMT channel and then sends the completion interrupt. + * + * This addresses a possible race condition in which a spurious IRQ from + * a previous timed-out reply which arrived late could be wrongly + * associated with the next pending transaction. + */ + if (cl->knows_txdone && !shmem_channel_free(smbox->shmem)) { + dev_warn(smbox->cinfo->dev, "Ignoring spurious A2P IRQ !\n"); + return; + } + scmi_rx_callback(smbox->cinfo, shmem_read_header(smbox->shmem), NULL); } diff --git a/drivers/firmware/arm_scmi/optee.c b/drivers/firmware/arm_scmi/optee.c index e123de6e8c67a9..aa02392265d326 100644 --- a/drivers/firmware/arm_scmi/optee.c +++ b/drivers/firmware/arm_scmi/optee.c @@ -467,6 +467,13 @@ static int scmi_optee_chan_free(int id, void *p, void *data) struct scmi_chan_info *cinfo = p; struct scmi_optee_channel *channel = cinfo->transport_info; + /* + * Different protocols might share the same chan info, so a previous + * call might have already freed the structure. + */ + if (!channel) + return 0; + mutex_lock(&scmi_optee_private->mu); list_del(&channel->link); mutex_unlock(&scmi_optee_private->mu); diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index 30dedd6ebfde61..dd344506b0a37d 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -145,7 +145,6 @@ struct scmi_msg_resp_perf_describe_levels_v4 { struct perf_dom_info { u32 id; bool set_limits; - bool set_perf; bool perf_limit_notify; bool perf_level_notify; bool perf_fastchannels; @@ -153,8 +152,8 @@ struct perf_dom_info { u32 opp_count; u32 sustained_freq_khz; u32 sustained_perf_level; - u32 mult_factor; - char name[SCMI_MAX_STR_SIZE]; + unsigned long mult_factor; + struct scmi_perf_domain_info info; struct scmi_opp opp[MAX_OPPS]; struct scmi_fc_info *fc_info; struct xarray opps_by_idx; @@ -257,7 +256,7 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph, flags = le32_to_cpu(attr->flags); dom_info->set_limits = SUPPORTS_SET_LIMITS(flags); - dom_info->set_perf = SUPPORTS_SET_PERF_LVL(flags); + dom_info->info.set_perf = SUPPORTS_SET_PERF_LVL(flags); dom_info->perf_limit_notify = SUPPORTS_PERF_LIMIT_NOTIFY(flags); dom_info->perf_level_notify = SUPPORTS_PERF_LEVEL_NOTIFY(flags); dom_info->perf_fastchannels = SUPPORTS_PERF_FASTCHANNELS(flags); @@ -269,14 +268,16 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph, dom_info->sustained_perf_level = le32_to_cpu(attr->sustained_perf_level); if (!dom_info->sustained_freq_khz || - !dom_info->sustained_perf_level) + !dom_info->sustained_perf_level || + dom_info->level_indexing_mode) /* CPUFreq converts to kHz, hence default 1000 */ dom_info->mult_factor = 1000; else dom_info->mult_factor = - (dom_info->sustained_freq_khz * 1000) / - dom_info->sustained_perf_level; - strscpy(dom_info->name, attr->name, SCMI_SHORT_NAME_MAX_SIZE); + (dom_info->sustained_freq_khz * 1000UL) + / dom_info->sustained_perf_level; + strscpy(dom_info->info.name, attr->name, + SCMI_SHORT_NAME_MAX_SIZE); } ph->xops->xfer_put(ph, t); @@ -288,7 +289,7 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph, if (!ret && PROTOCOL_REV_MAJOR(version) >= 0x3 && SUPPORTS_EXTENDED_NAMES(flags)) ph->hops->extended_name_get(ph, PERF_DOMAIN_NAME_GET, - dom_info->id, dom_info->name, + dom_info->id, dom_info->info.name, SCMI_MAX_STR_SIZE); if (dom_info->level_indexing_mode) { @@ -346,8 +347,8 @@ process_response_opp(struct scmi_opp *opp, unsigned int loop_idx, } static inline void -process_response_opp_v4(struct perf_dom_info *dom, struct scmi_opp *opp, - unsigned int loop_idx, +process_response_opp_v4(struct device *dev, struct perf_dom_info *dom, + struct scmi_opp *opp, unsigned int loop_idx, const struct scmi_msg_resp_perf_describe_levels_v4 *r) { opp->perf = le32_to_cpu(r->opp[loop_idx].perf_val); @@ -358,10 +359,23 @@ process_response_opp_v4(struct perf_dom_info *dom, struct scmi_opp *opp, /* Note that PERF v4 reports always five 32-bit words */ opp->indicative_freq = le32_to_cpu(r->opp[loop_idx].indicative_freq); if (dom->level_indexing_mode) { + int ret; + opp->level_index = le32_to_cpu(r->opp[loop_idx].level_index); - xa_store(&dom->opps_by_idx, opp->level_index, opp, GFP_KERNEL); - xa_store(&dom->opps_by_lvl, opp->perf, opp, GFP_KERNEL); + ret = xa_insert(&dom->opps_by_idx, opp->level_index, opp, + GFP_KERNEL); + if (ret) + dev_warn(dev, + "Failed to add opps_by_idx at %d - ret:%d\n", + opp->level_index, ret); + + ret = xa_insert(&dom->opps_by_lvl, opp->perf, opp, GFP_KERNEL); + if (ret) + dev_warn(dev, + "Failed to add opps_by_lvl at %d - ret:%d\n", + opp->perf, ret); + hash_add(dom->opps_by_freq, &opp->hash, opp->indicative_freq); } } @@ -378,7 +392,7 @@ iter_perf_levels_process_response(const struct scmi_protocol_handle *ph, if (PROTOCOL_REV_MAJOR(p->version) <= 0x3) process_response_opp(opp, st->loop_idx, response); else - process_response_opp_v4(p->perf_dom, opp, st->loop_idx, + process_response_opp_v4(ph->dev, p->perf_dom, opp, st->loop_idx, response); p->perf_dom->opp_count++; @@ -423,6 +437,36 @@ scmi_perf_describe_levels_get(const struct scmi_protocol_handle *ph, return ret; } +static int scmi_perf_num_domains_get(const struct scmi_protocol_handle *ph) +{ + struct scmi_perf_info *pi = ph->get_priv(ph); + + return pi->num_domains; +} + +static inline struct perf_dom_info * +scmi_perf_domain_lookup(const struct scmi_protocol_handle *ph, u32 domain) +{ + struct scmi_perf_info *pi = ph->get_priv(ph); + + if (domain >= pi->num_domains) + return ERR_PTR(-EINVAL); + + return pi->dom_info + domain; +} + +static const struct scmi_perf_domain_info * +scmi_perf_info_get(const struct scmi_protocol_handle *ph, u32 domain) +{ + struct perf_dom_info *dom; + + dom = scmi_perf_domain_lookup(ph, domain); + if (IS_ERR(dom)) + return ERR_PTR(-EINVAL); + + return &dom->info; +} + static int scmi_perf_msg_limits_set(const struct scmi_protocol_handle *ph, u32 domain, u32 max_perf, u32 min_perf) { @@ -446,17 +490,6 @@ static int scmi_perf_msg_limits_set(const struct scmi_protocol_handle *ph, return ret; } -static inline struct perf_dom_info * -scmi_perf_domain_lookup(const struct scmi_protocol_handle *ph, u32 domain) -{ - struct scmi_perf_info *pi = ph->get_priv(ph); - - if (domain >= pi->num_domains) - return ERR_PTR(-EINVAL); - - return pi->dom_info + domain; -} - static int __scmi_perf_limits_set(const struct scmi_protocol_handle *ph, struct perf_dom_info *dom, u32 max_perf, u32 min_perf) @@ -780,7 +813,6 @@ static int scmi_dvfs_device_opps_add(const struct scmi_protocol_handle *ph, { int idx, ret, domain; unsigned long freq; - struct scmi_opp *opp; struct perf_dom_info *dom; domain = scmi_dev_domain_id(dev); @@ -791,28 +823,21 @@ static int scmi_dvfs_device_opps_add(const struct scmi_protocol_handle *ph, if (IS_ERR(dom)) return PTR_ERR(dom); - for (opp = dom->opp, idx = 0; idx < dom->opp_count; idx++, opp++) { + for (idx = 0; idx < dom->opp_count; idx++) { if (!dom->level_indexing_mode) - freq = opp->perf * dom->mult_factor; + freq = dom->opp[idx].perf * dom->mult_factor; else - freq = opp->indicative_freq * 1000; + freq = dom->opp[idx].indicative_freq * dom->mult_factor; ret = dev_pm_opp_add(dev, freq, 0); if (ret) { dev_warn(dev, "failed to add opp %luHz\n", freq); - - while (idx-- > 0) { - if (!dom->level_indexing_mode) - freq = (--opp)->perf * dom->mult_factor; - else - freq = (--opp)->indicative_freq * 1000; - dev_pm_opp_remove(dev, freq); - } + dev_pm_opp_remove_all_dynamic(dev); return ret; } dev_dbg(dev, "[%d][%s]:: Registered OPP[%d] %lu\n", - domain, dom->name, idx, freq); + domain, dom->info.name, idx, freq); } return 0; } @@ -851,7 +876,8 @@ static int scmi_dvfs_freq_set(const struct scmi_protocol_handle *ph, u32 domain, } else { struct scmi_opp *opp; - opp = LOOKUP_BY_FREQ(dom->opps_by_freq, freq / 1000); + opp = LOOKUP_BY_FREQ(dom->opps_by_freq, + freq / dom->mult_factor); if (!opp) return -EIO; @@ -885,7 +911,7 @@ static int scmi_dvfs_freq_get(const struct scmi_protocol_handle *ph, u32 domain, if (!opp) return -EIO; - *freq = opp->indicative_freq * 1000; + *freq = opp->indicative_freq * dom->mult_factor; } return ret; @@ -908,7 +934,7 @@ static int scmi_dvfs_est_power_get(const struct scmi_protocol_handle *ph, if (!dom->level_indexing_mode) opp_freq = opp->perf * dom->mult_factor; else - opp_freq = opp->indicative_freq * 1000; + opp_freq = opp->indicative_freq * dom->mult_factor; if (opp_freq < *freq) continue; @@ -948,6 +974,8 @@ scmi_power_scale_get(const struct scmi_protocol_handle *ph) } static const struct scmi_perf_proto_ops perf_proto_ops = { + .num_domains_get = scmi_perf_num_domains_get, + .info_get = scmi_perf_info_get, .limits_set = scmi_perf_limits_set, .limits_get = scmi_perf_limits_get, .level_set = scmi_perf_level_set, diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c index 0493aa3c12bf53..130d13e9cd6beb 100644 --- a/drivers/firmware/arm_scmi/raw_mode.c +++ b/drivers/firmware/arm_scmi/raw_mode.c @@ -921,7 +921,7 @@ static int scmi_dbg_raw_mode_open(struct inode *inode, struct file *filp) rd->raw = raw; filp->private_data = rd; - return 0; + return nonseekable_open(inode, filp); } static int scmi_dbg_raw_mode_release(struct inode *inode, struct file *filp) @@ -950,6 +950,7 @@ static const struct file_operations scmi_dbg_raw_mode_reset_fops = { .open = scmi_dbg_raw_mode_open, .release = scmi_dbg_raw_mode_release, .write = scmi_dbg_raw_mode_reset_write, + .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -959,6 +960,7 @@ static const struct file_operations scmi_dbg_raw_mode_message_fops = { .read = scmi_dbg_raw_mode_message_read, .write = scmi_dbg_raw_mode_message_write, .poll = scmi_dbg_raw_mode_message_poll, + .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -975,6 +977,7 @@ static const struct file_operations scmi_dbg_raw_mode_message_async_fops = { .read = scmi_dbg_raw_mode_message_read, .write = scmi_dbg_raw_mode_message_async_write, .poll = scmi_dbg_raw_mode_message_poll, + .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -998,6 +1001,7 @@ static const struct file_operations scmi_dbg_raw_mode_notification_fops = { .release = scmi_dbg_raw_mode_release, .read = scmi_test_dbg_raw_mode_notif_read, .poll = scmi_test_dbg_raw_mode_notif_poll, + .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -1021,6 +1025,7 @@ static const struct file_operations scmi_dbg_raw_mode_errors_fops = { .release = scmi_dbg_raw_mode_release, .read = scmi_test_dbg_raw_mode_errors_read, .poll = scmi_test_dbg_raw_mode_errors_poll, + .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -1111,7 +1116,6 @@ static int scmi_raw_mode_setup(struct scmi_raw_mode_info *raw, int i; for (i = 0; i < num_chans; i++) { - void *xret; struct scmi_raw_queue *q; q = scmi_raw_queue_init(raw); @@ -1120,13 +1124,12 @@ static int scmi_raw_mode_setup(struct scmi_raw_mode_info *raw, goto err_xa; } - xret = xa_store(&raw->chans_q, channels[i], q, + ret = xa_insert(&raw->chans_q, channels[i], q, GFP_KERNEL); - if (xa_err(xret)) { + if (ret) { dev_err(dev, "Fail to allocate Raw queue 0x%02X\n", channels[i]); - ret = xa_err(xret); goto err_xa; } } @@ -1322,6 +1325,12 @@ void scmi_raw_message_report(void *r, struct scmi_xfer *xfer, dev = raw->handle->dev; q = scmi_raw_queue_select(raw, idx, SCMI_XFER_IS_CHAN_SET(xfer) ? chan_id : 0); + if (!q) { + dev_warn(dev, + "RAW[%d] - NO queue for chan 0x%X. Dropping report.\n", + idx, chan_id); + return; + } /* * Grab the msg_q_lock upfront to avoid a possible race between diff --git a/drivers/firmware/arm_scmi/shmem.c b/drivers/firmware/arm_scmi/shmem.c index 87b4f4d35f0623..517d52fb3bcbbb 100644 --- a/drivers/firmware/arm_scmi/shmem.c +++ b/drivers/firmware/arm_scmi/shmem.c @@ -122,3 +122,9 @@ bool shmem_poll_done(struct scmi_shared_mem __iomem *shmem, (SCMI_SHMEM_CHAN_STAT_CHANNEL_ERROR | SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE); } + +bool shmem_channel_free(struct scmi_shared_mem __iomem *shmem) +{ + return (ioread32(&shmem->channel_status) & + SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE); +} diff --git a/drivers/firmware/arm_scmi/smc.c b/drivers/firmware/arm_scmi/smc.c index c193516a254d9e..771797b6e26806 100644 --- a/drivers/firmware/arm_scmi/smc.c +++ b/drivers/firmware/arm_scmi/smc.c @@ -196,6 +196,13 @@ static int smc_chan_free(int id, void *p, void *data) struct scmi_chan_info *cinfo = p; struct scmi_smc *scmi_info = cinfo->transport_info; + /* + * Different protocols might share the same chan info, so a previous + * smc_chan_free call might have already freed the structure. + */ + if (!scmi_info) + return 0; + /* Ignore any possible further reception on the IRQ path */ if (scmi_info->irq > 0) free_irq(scmi_info->irq, scmi_info); diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index 79d4254d1f9bc5..e62ffffe5fb8d4 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -522,7 +522,7 @@ void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp) { cs_dsp_debugfs_clear(dsp); debugfs_remove_recursive(dsp->debugfs_root); - dsp->debugfs_root = NULL; + dsp->debugfs_root = ERR_PTR(-ENODEV); } EXPORT_SYMBOL_NS_GPL(cs_dsp_cleanup_debugfs, FW_CS_DSP); #else @@ -796,6 +796,9 @@ int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, lockdep_assert_held(&ctl->dsp->pwr_lock); + if (ctl->flags && !(ctl->flags & WMFW_CTL_FLAG_WRITEABLE)) + return -EPERM; + if (len + off * sizeof(u32) > ctl->len) return -EINVAL; @@ -1053,9 +1056,16 @@ struct cs_dsp_coeff_parsed_coeff { int len; }; -static int cs_dsp_coeff_parse_string(int bytes, const u8 **pos, const u8 **str) +static int cs_dsp_coeff_parse_string(int bytes, const u8 **pos, unsigned int avail, + const u8 **str) { - int length; + int length, total_field_len; + + /* String fields are at least one __le32 */ + if (sizeof(__le32) > avail) { + *pos = NULL; + return 0; + } switch (bytes) { case 1: @@ -1068,10 +1078,16 @@ static int cs_dsp_coeff_parse_string(int bytes, const u8 **pos, const u8 **str) return 0; } + total_field_len = ((length + bytes) + 3) & ~0x03; + if ((unsigned int)total_field_len > avail) { + *pos = NULL; + return 0; + } + if (str) *str = *pos + bytes; - *pos += ((length + bytes) + 3) & ~0x03; + *pos += total_field_len; return length; } @@ -1096,71 +1112,134 @@ static int cs_dsp_coeff_parse_int(int bytes, const u8 **pos) return val; } -static inline void cs_dsp_coeff_parse_alg(struct cs_dsp *dsp, const u8 **data, - struct cs_dsp_coeff_parsed_alg *blk) +static int cs_dsp_coeff_parse_alg(struct cs_dsp *dsp, + const struct wmfw_region *region, + struct cs_dsp_coeff_parsed_alg *blk) { const struct wmfw_adsp_alg_data *raw; + unsigned int data_len = le32_to_cpu(region->len); + unsigned int pos; + const u8 *tmp; + + raw = (const struct wmfw_adsp_alg_data *)region->data; switch (dsp->fw_ver) { case 0: case 1: - raw = (const struct wmfw_adsp_alg_data *)*data; - *data = raw->data; + if (sizeof(*raw) > data_len) + return -EOVERFLOW; blk->id = le32_to_cpu(raw->id); blk->name = raw->name; - blk->name_len = strlen(raw->name); + blk->name_len = strnlen(raw->name, ARRAY_SIZE(raw->name)); blk->ncoeff = le32_to_cpu(raw->ncoeff); + + pos = sizeof(*raw); break; default: - blk->id = cs_dsp_coeff_parse_int(sizeof(raw->id), data); - blk->name_len = cs_dsp_coeff_parse_string(sizeof(u8), data, + if (sizeof(raw->id) > data_len) + return -EOVERFLOW; + + tmp = region->data; + blk->id = cs_dsp_coeff_parse_int(sizeof(raw->id), &tmp); + pos = tmp - region->data; + + tmp = ®ion->data[pos]; + blk->name_len = cs_dsp_coeff_parse_string(sizeof(u8), &tmp, data_len - pos, &blk->name); - cs_dsp_coeff_parse_string(sizeof(u16), data, NULL); - blk->ncoeff = cs_dsp_coeff_parse_int(sizeof(raw->ncoeff), data); + if (!tmp) + return -EOVERFLOW; + + pos = tmp - region->data; + cs_dsp_coeff_parse_string(sizeof(u16), &tmp, data_len - pos, NULL); + if (!tmp) + return -EOVERFLOW; + + pos = tmp - region->data; + if (sizeof(raw->ncoeff) > (data_len - pos)) + return -EOVERFLOW; + + blk->ncoeff = cs_dsp_coeff_parse_int(sizeof(raw->ncoeff), &tmp); + pos += sizeof(raw->ncoeff); break; } + if ((int)blk->ncoeff < 0) + return -EOVERFLOW; + cs_dsp_dbg(dsp, "Algorithm ID: %#x\n", blk->id); cs_dsp_dbg(dsp, "Algorithm name: %.*s\n", blk->name_len, blk->name); cs_dsp_dbg(dsp, "# of coefficient descriptors: %#x\n", blk->ncoeff); + + return pos; } -static inline void cs_dsp_coeff_parse_coeff(struct cs_dsp *dsp, const u8 **data, - struct cs_dsp_coeff_parsed_coeff *blk) +static int cs_dsp_coeff_parse_coeff(struct cs_dsp *dsp, + const struct wmfw_region *region, + unsigned int pos, + struct cs_dsp_coeff_parsed_coeff *blk) { const struct wmfw_adsp_coeff_data *raw; + unsigned int data_len = le32_to_cpu(region->len); + unsigned int blk_len, blk_end_pos; const u8 *tmp; - int length; + + raw = (const struct wmfw_adsp_coeff_data *)®ion->data[pos]; + if (sizeof(raw->hdr) > (data_len - pos)) + return -EOVERFLOW; + + blk_len = le32_to_cpu(raw->hdr.size); + if (blk_len > S32_MAX) + return -EOVERFLOW; + + if (blk_len > (data_len - pos - sizeof(raw->hdr))) + return -EOVERFLOW; + + blk_end_pos = pos + sizeof(raw->hdr) + blk_len; + + blk->offset = le16_to_cpu(raw->hdr.offset); + blk->mem_type = le16_to_cpu(raw->hdr.type); switch (dsp->fw_ver) { case 0: case 1: - raw = (const struct wmfw_adsp_coeff_data *)*data; - *data = *data + sizeof(raw->hdr) + le32_to_cpu(raw->hdr.size); + if (sizeof(*raw) > (data_len - pos)) + return -EOVERFLOW; - blk->offset = le16_to_cpu(raw->hdr.offset); - blk->mem_type = le16_to_cpu(raw->hdr.type); blk->name = raw->name; - blk->name_len = strlen(raw->name); + blk->name_len = strnlen(raw->name, ARRAY_SIZE(raw->name)); blk->ctl_type = le16_to_cpu(raw->ctl_type); blk->flags = le16_to_cpu(raw->flags); blk->len = le32_to_cpu(raw->len); break; default: - tmp = *data; - blk->offset = cs_dsp_coeff_parse_int(sizeof(raw->hdr.offset), &tmp); - blk->mem_type = cs_dsp_coeff_parse_int(sizeof(raw->hdr.type), &tmp); - length = cs_dsp_coeff_parse_int(sizeof(raw->hdr.size), &tmp); - blk->name_len = cs_dsp_coeff_parse_string(sizeof(u8), &tmp, + pos += sizeof(raw->hdr); + tmp = ®ion->data[pos]; + blk->name_len = cs_dsp_coeff_parse_string(sizeof(u8), &tmp, data_len - pos, &blk->name); - cs_dsp_coeff_parse_string(sizeof(u8), &tmp, NULL); - cs_dsp_coeff_parse_string(sizeof(u16), &tmp, NULL); + if (!tmp) + return -EOVERFLOW; + + pos = tmp - region->data; + cs_dsp_coeff_parse_string(sizeof(u8), &tmp, data_len - pos, NULL); + if (!tmp) + return -EOVERFLOW; + + pos = tmp - region->data; + cs_dsp_coeff_parse_string(sizeof(u16), &tmp, data_len - pos, NULL); + if (!tmp) + return -EOVERFLOW; + + pos = tmp - region->data; + if (sizeof(raw->ctl_type) + sizeof(raw->flags) + sizeof(raw->len) > + (data_len - pos)) + return -EOVERFLOW; + blk->ctl_type = cs_dsp_coeff_parse_int(sizeof(raw->ctl_type), &tmp); + pos += sizeof(raw->ctl_type); blk->flags = cs_dsp_coeff_parse_int(sizeof(raw->flags), &tmp); + pos += sizeof(raw->flags); blk->len = cs_dsp_coeff_parse_int(sizeof(raw->len), &tmp); - - *data = *data + sizeof(raw->hdr) + length; break; } @@ -1170,6 +1249,8 @@ static inline void cs_dsp_coeff_parse_coeff(struct cs_dsp *dsp, const u8 **data, cs_dsp_dbg(dsp, "\tCoefficient flags: %#x\n", blk->flags); cs_dsp_dbg(dsp, "\tALSA control type: %#x\n", blk->ctl_type); cs_dsp_dbg(dsp, "\tALSA control len: %#x\n", blk->len); + + return blk_end_pos; } static int cs_dsp_check_coeff_flags(struct cs_dsp *dsp, @@ -1193,12 +1274,16 @@ static int cs_dsp_parse_coeff(struct cs_dsp *dsp, struct cs_dsp_alg_region alg_region = {}; struct cs_dsp_coeff_parsed_alg alg_blk; struct cs_dsp_coeff_parsed_coeff coeff_blk; - const u8 *data = region->data; - int i, ret; + int i, pos, ret; + + pos = cs_dsp_coeff_parse_alg(dsp, region, &alg_blk); + if (pos < 0) + return pos; - cs_dsp_coeff_parse_alg(dsp, &data, &alg_blk); for (i = 0; i < alg_blk.ncoeff; i++) { - cs_dsp_coeff_parse_coeff(dsp, &data, &coeff_blk); + pos = cs_dsp_coeff_parse_coeff(dsp, region, pos, &coeff_blk); + if (pos < 0) + return pos; switch (coeff_blk.ctl_type) { case WMFW_CTL_TYPE_BYTES: @@ -1267,6 +1352,10 @@ static unsigned int cs_dsp_adsp1_parse_sizes(struct cs_dsp *dsp, const struct wmfw_adsp1_sizes *adsp1_sizes; adsp1_sizes = (void *)&firmware->data[pos]; + if (sizeof(*adsp1_sizes) > firmware->size - pos) { + cs_dsp_err(dsp, "%s: file truncated\n", file); + return 0; + } cs_dsp_dbg(dsp, "%s: %d DM, %d PM, %d ZM\n", file, le32_to_cpu(adsp1_sizes->dm), le32_to_cpu(adsp1_sizes->pm), @@ -1283,6 +1372,10 @@ static unsigned int cs_dsp_adsp2_parse_sizes(struct cs_dsp *dsp, const struct wmfw_adsp2_sizes *adsp2_sizes; adsp2_sizes = (void *)&firmware->data[pos]; + if (sizeof(*adsp2_sizes) > firmware->size - pos) { + cs_dsp_err(dsp, "%s: file truncated\n", file); + return 0; + } cs_dsp_dbg(dsp, "%s: %d XM, %d YM %d PM, %d ZM\n", file, le32_to_cpu(adsp2_sizes->xm), le32_to_cpu(adsp2_sizes->ym), @@ -1322,7 +1415,6 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, struct regmap *regmap = dsp->regmap; unsigned int pos = 0; const struct wmfw_header *header; - const struct wmfw_adsp1_sizes *adsp1_sizes; const struct wmfw_footer *footer; const struct wmfw_region *region; const struct cs_dsp_region *mem; @@ -1338,10 +1430,8 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, ret = -EINVAL; - pos = sizeof(*header) + sizeof(*adsp1_sizes) + sizeof(*footer); - if (pos >= firmware->size) { - cs_dsp_err(dsp, "%s: file too short, %zu bytes\n", - file, firmware->size); + if (sizeof(*header) >= firmware->size) { + ret = -EOVERFLOW; goto out_fw; } @@ -1369,22 +1459,36 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, pos = sizeof(*header); pos = dsp->ops->parse_sizes(dsp, file, pos, firmware); + if ((pos == 0) || (sizeof(*footer) > firmware->size - pos)) { + ret = -EOVERFLOW; + goto out_fw; + } footer = (void *)&firmware->data[pos]; pos += sizeof(*footer); if (le32_to_cpu(header->len) != pos) { - cs_dsp_err(dsp, "%s: unexpected header length %d\n", - file, le32_to_cpu(header->len)); + ret = -EOVERFLOW; goto out_fw; } cs_dsp_dbg(dsp, "%s: timestamp %llu\n", file, le64_to_cpu(footer->timestamp)); - while (pos < firmware->size && - sizeof(*region) < firmware->size - pos) { + while (pos < firmware->size) { + /* Is there enough data for a complete block header? */ + if (sizeof(*region) > firmware->size - pos) { + ret = -EOVERFLOW; + goto out_fw; + } + region = (void *)&(firmware->data[pos]); + + if (le32_to_cpu(region->len) > firmware->size - pos - sizeof(*region)) { + ret = -EOVERFLOW; + goto out_fw; + } + region_name = "Unknown"; reg = 0; text = NULL; @@ -1441,16 +1545,6 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, regions, le32_to_cpu(region->len), offset, region_name); - if (le32_to_cpu(region->len) > - firmware->size - pos - sizeof(*region)) { - cs_dsp_err(dsp, - "%s.%d: %s region len %d bytes exceeds file length %zu\n", - file, regions, region_name, - le32_to_cpu(region->len), firmware->size); - ret = -EINVAL; - goto out_fw; - } - if (text) { memcpy(text, region->data, le32_to_cpu(region->len)); cs_dsp_info(dsp, "%s: %s\n", file, text); @@ -1501,6 +1595,9 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, cs_dsp_buf_free(&buf_list); kfree(text); + if (ret == -EOVERFLOW) + cs_dsp_err(dsp, "%s: file content overflows file data\n", file); + return ret; } @@ -2068,10 +2165,20 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware pos = le32_to_cpu(hdr->len); blocks = 0; - while (pos < firmware->size && - sizeof(*blk) < firmware->size - pos) { + while (pos < firmware->size) { + /* Is there enough data for a complete block header? */ + if (sizeof(*blk) > firmware->size - pos) { + ret = -EOVERFLOW; + goto out_fw; + } + blk = (void *)(&firmware->data[pos]); + if (le32_to_cpu(blk->len) > firmware->size - pos - sizeof(*blk)) { + ret = -EOVERFLOW; + goto out_fw; + } + type = le16_to_cpu(blk->type); offset = le16_to_cpu(blk->offset); version = le32_to_cpu(blk->ver) >> 8; @@ -2168,17 +2275,6 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware } if (reg) { - if (le32_to_cpu(blk->len) > - firmware->size - pos - sizeof(*blk)) { - cs_dsp_err(dsp, - "%s.%d: %s region len %d bytes exceeds file length %zu\n", - file, blocks, region_name, - le32_to_cpu(blk->len), - firmware->size); - ret = -EINVAL; - goto out_fw; - } - buf = cs_dsp_buf_alloc(blk->data, le32_to_cpu(blk->len), &buf_list); @@ -2218,6 +2314,10 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware regmap_async_complete(regmap); cs_dsp_buf_free(&buf_list); kfree(text); + + if (ret == -EOVERFLOW) + cs_dsp_err(dsp, "%s: file content overflows file data\n", file); + return ret; } @@ -2246,6 +2346,11 @@ static int cs_dsp_common_init(struct cs_dsp *dsp) mutex_init(&dsp->pwr_lock); +#ifdef CONFIG_DEBUG_FS + /* Ensure this is invalid if client never provides a debugfs root */ + dsp->debugfs_root = ERR_PTR(-ENODEV); +#endif + return 0; } diff --git a/drivers/firmware/dmi-id.c b/drivers/firmware/dmi-id.c index 5f3a3e913d28fb..d19c78a78ae3ac 100644 --- a/drivers/firmware/dmi-id.c +++ b/drivers/firmware/dmi-id.c @@ -169,9 +169,14 @@ static int dmi_dev_uevent(const struct device *dev, struct kobj_uevent_env *env) return 0; } +static void dmi_dev_release(struct device *dev) +{ + kfree(dev); +} + static struct class dmi_class = { .name = "dmi", - .dev_release = (void(*)(struct device *)) kfree, + .dev_release = dmi_dev_release, .dev_uevent = dmi_dev_uevent, }; diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 015c95a825d315..ac2a5d2d47463f 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -101,6 +101,17 @@ static void dmi_decode_table(u8 *buf, (data - buf + sizeof(struct dmi_header)) <= dmi_len) { const struct dmi_header *dm = (const struct dmi_header *)data; + /* + * If a short entry is found (less than 4 bytes), not only it + * is invalid, but we cannot reliably locate the next entry. + */ + if (dm->length < sizeof(struct dmi_header)) { + pr_warn(FW_BUG + "Corrupted DMI table, offset %zd (only %d entries processed)\n", + data - buf, i); + break; + } + /* * We want to know the total length (formatted area and * strings) before decoding to make sure we won't run off the diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c index 83f5bb57fa4c46..83092d93f36a63 100644 --- a/drivers/firmware/efi/arm-runtime.c +++ b/drivers/firmware/efi/arm-runtime.c @@ -107,7 +107,7 @@ static int __init arm_enable_runtime_services(void) efi_memory_desc_t *md; for_each_efi_memory_desc(md) { - int md_size = md->num_pages << EFI_PAGE_SHIFT; + u64 md_size = md->num_pages << EFI_PAGE_SHIFT; struct resource *res; if (!(md->attribute & EFI_MEMORY_SP)) diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index 3e8d4b51a8140c..97bafb5f703892 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -292,7 +292,7 @@ static int efi_capsule_open(struct inode *inode, struct file *file) return -ENOMEM; } - cap_info->phys = kzalloc(sizeof(void *), GFP_KERNEL); + cap_info->phys = kzalloc(sizeof(phys_addr_t), GFP_KERNEL); if (!cap_info->phys) { kfree(cap_info->pages); kfree(cap_info); diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c index ef0820f1a9246e..59b0d7197b6852 100644 --- a/drivers/firmware/efi/efi-init.c +++ b/drivers/firmware/efi/efi-init.c @@ -134,15 +134,6 @@ static __init int is_usable_memory(efi_memory_desc_t *md) case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: case EFI_PERSISTENT_MEMORY: - /* - * Special purpose memory is 'soft reserved', which means it - * is set aside initially, but can be hotplugged back in or - * be assigned to the dax driver after boot. - */ - if (efi_soft_reserve_enabled() && - (md->attribute & EFI_MEMORY_SP)) - return false; - /* * According to the spec, these regions are no longer reserved * after calling ExitBootServices(). However, we can only use @@ -187,6 +178,16 @@ static __init void reserve_regions(void) size = npages << PAGE_SHIFT; if (is_memory(md)) { + /* + * Special purpose memory is 'soft reserved', which + * means it is set aside initially. Don't add a memblock + * for it now so that it can be hotplugged back in or + * be assigned to the dax driver after boot. + */ + if (efi_soft_reserve_enabled() && + (md->attribute & EFI_MEMORY_SP)) + continue; + early_init_dt_add_memory_arch(paddr, size); if (!is_usable_memory(md)) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 1974f0ad32badb..2c1095dcc2f2f8 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -199,6 +199,8 @@ static bool generic_ops_supported(void) name_size = sizeof(name); + if (!efi.get_next_variable) + return false; status = efi.get_next_variable(&name_size, &name, &guid); if (status == EFI_UNSUPPORTED) return false; diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index a1157c2a717040..a0f1569b790da5 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -28,7 +28,7 @@ cflags-$(CONFIG_ARM) += -DEFI_HAVE_STRLEN -DEFI_HAVE_STRNLEN \ -DEFI_HAVE_MEMCHR -DEFI_HAVE_STRRCHR \ -DEFI_HAVE_STRCMP -fno-builtin -fpic \ $(call cc-option,-mno-single-pic-base) -cflags-$(CONFIG_RISCV) += -fpic +cflags-$(CONFIG_RISCV) += -fpic -mno-relax cflags-$(CONFIG_LOONGARCH) += -fpie cflags-$(CONFIG_EFI_PARAMS_FROM_FDT) += -I$(srctree)/scripts/dtc/libfdt @@ -108,13 +108,6 @@ lib-y := $(patsubst %.o,%.stub.o,$(lib-y)) # https://bugs.llvm.org/show_bug.cgi?id=46480 STUBCOPY_FLAGS-y += --remove-section=.note.gnu.property -# -# For x86, bootloaders like systemd-boot or grub-efi do not zero-initialize the -# .bss section, so the .bss section of the EFI stub needs to be included in the -# .data section of the compressed kernel to ensure initialization. Rename the -# .bss section here so it's easy to pick out in the linker script. -# -STUBCOPY_FLAGS-$(CONFIG_X86) += --rename-section .bss=.bss.efistub,load,alloc STUBCOPY_RELOC-$(CONFIG_X86_32) := R_386_32 STUBCOPY_RELOC-$(CONFIG_X86_64) := R_X86_64_64 diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index bfa30625f5d031..3dc2f9aaf08db0 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -24,6 +24,8 @@ static bool efi_noinitrd; static bool efi_nosoftreserve; static bool efi_disable_pci_dma = IS_ENABLED(CONFIG_EFI_DISABLE_PCI_DMA); +int efi_mem_encrypt; + bool __pure __efi_soft_reserve_enabled(void) { return !efi_nosoftreserve; @@ -75,6 +77,12 @@ efi_status_t efi_parse_options(char const *cmdline) efi_noinitrd = true; } else if (IS_ENABLED(CONFIG_X86_64) && !strcmp(param, "no5lvl")) { efi_no5lvl = true; + } else if (IS_ENABLED(CONFIG_ARCH_HAS_MEM_ENCRYPT) && + !strcmp(param, "mem_encrypt") && val) { + if (parse_option_str(val, "on")) + efi_mem_encrypt = 1; + else if (parse_option_str(val, "off")) + efi_mem_encrypt = -1; } else if (!strcmp(param, "efi") && val) { efi_nochunk = parse_option_str(val, "nochunk"); efi_novamap |= parse_option_str(val, "novamap"); diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 212687c30d79c4..fc18fd649ed771 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -37,8 +37,8 @@ extern bool efi_no5lvl; extern bool efi_nochunk; extern bool efi_nokaslr; extern int efi_loglevel; +extern int efi_mem_encrypt; extern bool efi_novamap; - extern const efi_system_table_t *efi_system_table; typedef union efi_dxe_services_table efi_dxe_services_table_t; @@ -956,7 +956,8 @@ efi_status_t efi_get_random_bytes(unsigned long size, u8 *out); efi_status_t efi_random_alloc(unsigned long size, unsigned long align, unsigned long *addr, unsigned long random_seed, - int memory_type, unsigned long alloc_limit); + int memory_type, unsigned long alloc_min, + unsigned long alloc_max); efi_status_t efi_random_get_seed(void); diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index 70e9789ff9de0a..6a337f1f8787b3 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -335,8 +335,8 @@ efi_status_t allocate_new_fdt_and_exit_boot(void *handle, fail: efi_free(fdt_size, fdt_addr); - - efi_bs_call(free_pool, priv.runtime_map); + if (!efi_novamap) + efi_bs_call(free_pool, priv.runtime_map); return EFI_LOAD_ERROR; } diff --git a/drivers/firmware/efi/libstub/kaslr.c b/drivers/firmware/efi/libstub/kaslr.c index 62d63f7a2645bf..1a9808012abd36 100644 --- a/drivers/firmware/efi/libstub/kaslr.c +++ b/drivers/firmware/efi/libstub/kaslr.c @@ -119,7 +119,7 @@ efi_status_t efi_kaslr_relocate_kernel(unsigned long *image_addr, */ status = efi_random_alloc(*reserve_size, min_kimg_align, reserve_addr, phys_seed, - EFI_LOADER_CODE, EFI_ALLOC_LIMIT); + EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT); if (status != EFI_SUCCESS) efi_warn("efi_random_alloc() failed: 0x%lx\n", status); } else { diff --git a/drivers/firmware/efi/libstub/loongarch-stub.c b/drivers/firmware/efi/libstub/loongarch-stub.c index 72c71ae201f0da..736b6aae323d35 100644 --- a/drivers/firmware/efi/libstub/loongarch-stub.c +++ b/drivers/firmware/efi/libstub/loongarch-stub.c @@ -8,10 +8,10 @@ #include #include #include "efistub.h" +#include "loongarch-stub.h" extern int kernel_asize; extern int kernel_fsize; -extern int kernel_offset; extern int kernel_entry; efi_status_t handle_kernel_image(unsigned long *image_addr, @@ -24,7 +24,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, efi_status_t status; unsigned long kernel_addr = 0; - kernel_addr = (unsigned long)&kernel_offset - kernel_offset; + kernel_addr = (unsigned long)image->image_base; status = efi_relocate_kernel(&kernel_addr, kernel_fsize, kernel_asize, EFI_KIMG_PREFERRED_ADDRESS, efi_get_kimg_min_align(), 0x0); @@ -35,9 +35,10 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, return status; } -unsigned long kernel_entry_address(void) +unsigned long kernel_entry_address(unsigned long kernel_addr, + efi_loaded_image_t *image) { - unsigned long base = (unsigned long)&kernel_offset - kernel_offset; + unsigned long base = (unsigned long)image->image_base; - return (unsigned long)&kernel_entry - base + VMLINUX_LOAD_ADDRESS; + return (unsigned long)&kernel_entry - base + kernel_addr; } diff --git a/drivers/firmware/efi/libstub/loongarch-stub.h b/drivers/firmware/efi/libstub/loongarch-stub.h new file mode 100644 index 00000000000000..cd015955a0152b --- /dev/null +++ b/drivers/firmware/efi/libstub/loongarch-stub.h @@ -0,0 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +unsigned long kernel_entry_address(unsigned long kernel_addr, + efi_loaded_image_t *image); diff --git a/drivers/firmware/efi/libstub/loongarch.c b/drivers/firmware/efi/libstub/loongarch.c index 807cba2693fc17..d0ef93551c44f6 100644 --- a/drivers/firmware/efi/libstub/loongarch.c +++ b/drivers/firmware/efi/libstub/loongarch.c @@ -8,6 +8,7 @@ #include #include #include "efistub.h" +#include "loongarch-stub.h" typedef void __noreturn (*kernel_entry_t)(bool efi, unsigned long cmdline, unsigned long systab); @@ -37,9 +38,10 @@ static efi_status_t exit_boot_func(struct efi_boot_memmap *map, void *priv) return EFI_SUCCESS; } -unsigned long __weak kernel_entry_address(void) +unsigned long __weak kernel_entry_address(unsigned long kernel_addr, + efi_loaded_image_t *image) { - return *(unsigned long *)(PHYSADDR(VMLINUX_LOAD_ADDRESS) + 8); + return *(unsigned long *)(kernel_addr + 8) - PHYSADDR(VMLINUX_LOAD_ADDRESS) + kernel_addr; } efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image, @@ -73,7 +75,7 @@ efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image, csr_write64(CSR_DMW0_INIT, LOONGARCH_CSR_DMWIN0); csr_write64(CSR_DMW1_INIT, LOONGARCH_CSR_DMWIN1); - real_kernel_entry = (void *)kernel_entry_address(); + real_kernel_entry = (void *)kernel_entry_address(kernel_addr, image); real_kernel_entry(true, (unsigned long)cmdline_ptr, (unsigned long)efi_system_table); diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c index 674a064b8f7adc..c41e7b2091cdd1 100644 --- a/drivers/firmware/efi/libstub/randomalloc.c +++ b/drivers/firmware/efi/libstub/randomalloc.c @@ -17,7 +17,7 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, unsigned long size, unsigned long align_shift, - u64 alloc_limit) + u64 alloc_min, u64 alloc_max) { unsigned long align = 1UL << align_shift; u64 first_slot, last_slot, region_end; @@ -30,11 +30,11 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, return 0; region_end = min(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - 1, - alloc_limit); + alloc_max); if (region_end < size) return 0; - first_slot = round_up(md->phys_addr, align); + first_slot = round_up(max(md->phys_addr, alloc_min), align); last_slot = round_down(region_end - size + 1, align); if (first_slot > last_slot) @@ -56,7 +56,8 @@ efi_status_t efi_random_alloc(unsigned long size, unsigned long *addr, unsigned long random_seed, int memory_type, - unsigned long alloc_limit) + unsigned long alloc_min, + unsigned long alloc_max) { unsigned long total_slots = 0, target_slot; unsigned long total_mirrored_slots = 0; @@ -78,7 +79,8 @@ efi_status_t efi_random_alloc(unsigned long size, efi_memory_desc_t *md = (void *)map->map + map_offset; unsigned long slots; - slots = get_entry_num_slots(md, size, ilog2(align), alloc_limit); + slots = get_entry_num_slots(md, size, ilog2(align), alloc_min, + alloc_max); MD_NUM_SLOTS(md) = slots; total_slots += slots; if (md->attribute & EFI_MEMORY_MORE_RELIABLE) @@ -118,7 +120,7 @@ efi_status_t efi_random_alloc(unsigned long size, continue; } - target = round_up(md->phys_addr, align) + target_slot * align; + target = round_up(max_t(u64, md->phys_addr, alloc_min), align) + target_slot * align; pages = size / EFI_PAGE_SIZE; status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS, diff --git a/drivers/firmware/efi/libstub/screen_info.c b/drivers/firmware/efi/libstub/screen_info.c index a51ec201ca3cbe..5d3a1e32d1776b 100644 --- a/drivers/firmware/efi/libstub/screen_info.c +++ b/drivers/firmware/efi/libstub/screen_info.c @@ -32,6 +32,8 @@ struct screen_info *__alloc_screen_info(void) if (status != EFI_SUCCESS) return NULL; + memset(si, 0, sizeof(*si)); + status = efi_bs_call(install_configuration_table, &screen_info_guid, si); if (status == EFI_SUCCESS) diff --git a/drivers/firmware/efi/libstub/tpm.c b/drivers/firmware/efi/libstub/tpm.c index 7acbac16eae0b2..95da291c3083ef 100644 --- a/drivers/firmware/efi/libstub/tpm.c +++ b/drivers/firmware/efi/libstub/tpm.c @@ -115,7 +115,7 @@ void efi_retrieve_tpm2_eventlog(void) } /* Allocate space for the logs and copy them. */ - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, + status = efi_bs_call(allocate_pool, EFI_ACPI_RECLAIM_MEMORY, sizeof(*log_tbl) + log_size, (void **)&log_tbl); if (status != EFI_SUCCESS) { diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 9d5df683f8821c..b2b06d18b7b4a7 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -21,6 +21,8 @@ #include "efistub.h" #include "x86-stub.h" +extern char _bss[], _ebss[]; + const efi_system_table_t *efi_system_table; const efi_dxe_services_table_t *efi_dxe_table; static efi_loaded_image_t *image = NULL; @@ -223,8 +225,8 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) } } -void efi_adjust_memory_range_protection(unsigned long start, - unsigned long size) +efi_status_t efi_adjust_memory_range_protection(unsigned long start, + unsigned long size) { efi_status_t status; efi_gcd_memory_space_desc_t desc; @@ -236,13 +238,26 @@ void efi_adjust_memory_range_protection(unsigned long start, rounded_end = roundup(start + size, EFI_PAGE_SIZE); if (memattr != NULL) { - efi_call_proto(memattr, clear_memory_attributes, rounded_start, - rounded_end - rounded_start, EFI_MEMORY_XP); - return; + status = efi_call_proto(memattr, set_memory_attributes, + rounded_start, + rounded_end - rounded_start, + EFI_MEMORY_RO); + if (status != EFI_SUCCESS) { + efi_warn("Failed to set EFI_MEMORY_RO attribute\n"); + return status; + } + + status = efi_call_proto(memattr, clear_memory_attributes, + rounded_start, + rounded_end - rounded_start, + EFI_MEMORY_XP); + if (status != EFI_SUCCESS) + efi_warn("Failed to clear EFI_MEMORY_XP attribute\n"); + return status; } if (efi_dxe_table == NULL) - return; + return EFI_SUCCESS; /* * Don't modify memory region attributes, they are @@ -255,7 +270,7 @@ void efi_adjust_memory_range_protection(unsigned long start, status = efi_dxe_call(get_memory_space_descriptor, start, &desc); if (status != EFI_SUCCESS) - return; + break; next = desc.base_address + desc.length; @@ -280,8 +295,10 @@ void efi_adjust_memory_range_protection(unsigned long start, unprotect_start, unprotect_start + unprotect_size, status); + break; } } + return EFI_SUCCESS; } static void setup_unaccepted_memory(void) @@ -307,17 +324,20 @@ static void setup_unaccepted_memory(void) efi_err("Memory acceptance protocol failed\n"); } +static efi_char16_t *efistub_fw_vendor(void) +{ + unsigned long vendor = efi_table_attr(efi_system_table, fw_vendor); + + return (efi_char16_t *)vendor; +} + static const efi_char16_t apple[] = L"Apple"; static void setup_quirks(struct boot_params *boot_params) { - efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long) - efi_table_attr(efi_system_table, fw_vendor); - - if (!memcmp(fw_vendor, apple, sizeof(apple))) { - if (IS_ENABLED(CONFIG_APPLE_PROPERTIES)) - retrieve_apple_device_properties(boot_params); - } + if (IS_ENABLED(CONFIG_APPLE_PROPERTIES) && + !memcmp(efistub_fw_vendor(), apple, sizeof(apple))) + retrieve_apple_device_properties(boot_params); } /* @@ -449,14 +469,17 @@ void __noreturn efi_stub_entry(efi_handle_t handle, efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg) { + efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID; struct boot_params *boot_params; struct setup_header *hdr; - void *image_base; - efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID; int options_size = 0; efi_status_t status; + unsigned long alloc; char *cmdline_ptr; + if (efi_is_native()) + memset(_bss, 0, _ebss - _bss); + efi_system_table = sys_table_arg; /* Check if we were booted by the EFI firmware */ @@ -469,58 +492,32 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, efi_exit(handle, status); } - image_base = efi_table_attr(image, image_base); - - status = efi_allocate_pages(sizeof(struct boot_params), - (unsigned long *)&boot_params, ULONG_MAX); - if (status != EFI_SUCCESS) { - efi_err("Failed to allocate lowmem for boot params\n"); + status = efi_allocate_pages(PARAM_SIZE, &alloc, ULONG_MAX); + if (status != EFI_SUCCESS) efi_exit(handle, status); - } - - memset(boot_params, 0x0, sizeof(struct boot_params)); - hdr = &boot_params->hdr; + boot_params = memset((void *)alloc, 0x0, PARAM_SIZE); + hdr = &boot_params->hdr; - /* Copy the setup header from the second sector to boot_params */ - memcpy(&hdr->jump, image_base + 512, - sizeof(struct setup_header) - offsetof(struct setup_header, jump)); - - /* - * Fill out some of the header fields ourselves because the - * EFI firmware loader doesn't load the first sector. - */ + /* Assign the setup_header fields that the kernel actually cares about */ hdr->root_flags = 1; hdr->vid_mode = 0xffff; - hdr->boot_flag = 0xAA55; hdr->type_of_loader = 0x21; + hdr->initrd_addr_max = INT_MAX; /* Convert unicode cmdline to ascii */ cmdline_ptr = efi_convert_cmdline(image, &options_size); - if (!cmdline_ptr) - goto fail; - - efi_set_u64_split((unsigned long)cmdline_ptr, - &hdr->cmd_line_ptr, &boot_params->ext_cmd_line_ptr); - - hdr->ramdisk_image = 0; - hdr->ramdisk_size = 0; + if (!cmdline_ptr) { + efi_free(PARAM_SIZE, alloc); + efi_exit(handle, EFI_OUT_OF_RESOURCES); + } - /* - * Disregard any setup data that was provided by the bootloader: - * setup_data could be pointing anywhere, and we have no way of - * authenticating or validating the payload. - */ - hdr->setup_data = 0; + efi_set_u64_split((unsigned long)cmdline_ptr, &hdr->cmd_line_ptr, + &boot_params->ext_cmd_line_ptr); efi_stub_entry(handle, sys_table_arg, boot_params); /* not reached */ - -fail: - efi_free(sizeof(struct boot_params), (unsigned long)boot_params); - - efi_exit(handle, status); } static void add_e820ext(struct boot_params *params, @@ -786,6 +783,26 @@ static void error(char *str) efi_warn("Decompression failed: %s\n", str); } +static const char *cmdline_memmap_override; + +static efi_status_t parse_options(const char *cmdline) +{ + static const char opts[][14] = { + "mem=", "memmap=", "efi_fake_mem=", "hugepages=" + }; + + for (int i = 0; i < ARRAY_SIZE(opts); i++) { + const char *p = strstr(cmdline, opts[i]); + + if (p == cmdline || (p > cmdline && isspace(p[-1]))) { + cmdline_memmap_override = opts[i]; + break; + } + } + + return efi_parse_options(cmdline); +} + static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) { unsigned long virt_addr = LOAD_PHYSICAL_ADDR; @@ -799,15 +816,34 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && !efi_nokaslr) { u64 range = KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR - kernel_total_size; + static const efi_char16_t ami[] = L"American Megatrends"; efi_get_seed(seed, sizeof(seed)); virt_addr += (range * seed[1]) >> 32; virt_addr &= ~(CONFIG_PHYSICAL_ALIGN - 1); + + /* + * Older Dell systems with AMI UEFI firmware v2.0 may hang + * while decompressing the kernel if physical address + * randomization is enabled. + * + * https://bugzilla.kernel.org/show_bug.cgi?id=218173 + */ + if (efi_system_table->hdr.revision <= EFI_2_00_SYSTEM_TABLE_REVISION && + !memcmp(efistub_fw_vendor(), ami, sizeof(ami))) { + efi_debug("AMI firmware v2.0 or older detected - disabling physical KASLR\n"); + seed[0] = 0; + } else if (cmdline_memmap_override) { + efi_info("%s detected on the kernel command line - disabling physical KASLR\n", + cmdline_memmap_override); + seed[0] = 0; + } } status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr, seed[0], EFI_LOADER_CODE, + LOAD_PHYSICAL_ADDR, EFI_X86_KERNEL_ALLOC_LIMIT); if (status != EFI_SUCCESS) return status; @@ -820,9 +856,7 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) *kernel_entry = addr + entry; - efi_adjust_memory_range_protection(addr, kernel_total_size); - - return EFI_SUCCESS; + return efi_adjust_memory_range_protection(addr, kernel_text_size); } static void __noreturn enter_kernel(unsigned long kernel_addr, @@ -878,7 +912,7 @@ void __noreturn efi_stub_entry(efi_handle_t handle, } #ifdef CONFIG_CMDLINE_BOOL - status = efi_parse_options(CONFIG_CMDLINE); + status = parse_options(CONFIG_CMDLINE); if (status != EFI_SUCCESS) { efi_err("Failed to parse options\n"); goto fail; @@ -887,13 +921,16 @@ void __noreturn efi_stub_entry(efi_handle_t handle, if (!IS_ENABLED(CONFIG_CMDLINE_OVERRIDE)) { unsigned long cmdline_paddr = ((u64)hdr->cmd_line_ptr | ((u64)boot_params->ext_cmd_line_ptr << 32)); - status = efi_parse_options((char *)cmdline_paddr); + status = parse_options((char *)cmdline_paddr); if (status != EFI_SUCCESS) { efi_err("Failed to parse options\n"); goto fail; } } + if (efi_mem_encrypt > 0) + hdr->xloadflags |= XLF_MEM_ENCRYPTION; + status = efi_decompress_kernel(&kernel_entry); if (status != EFI_SUCCESS) { efi_err("Failed to decompress kernel\n"); @@ -968,8 +1005,6 @@ void __noreturn efi_stub_entry(efi_handle_t handle, void efi_handover_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg, struct boot_params *boot_params) { - extern char _bss[], _ebss[]; - memset(_bss, 0, _ebss - _bss); efi_stub_entry(handle, sys_table_arg, boot_params); } diff --git a/drivers/firmware/efi/libstub/x86-stub.h b/drivers/firmware/efi/libstub/x86-stub.h index 2748bca192dfb2..4433d0f97441ca 100644 --- a/drivers/firmware/efi/libstub/x86-stub.h +++ b/drivers/firmware/efi/libstub/x86-stub.h @@ -7,8 +7,8 @@ extern struct boot_params *boot_params_pointer asm("boot_params"); extern void trampoline_32bit_src(void *, bool); extern const u16 trampoline_ljmp_imm_offset; -void efi_adjust_memory_range_protection(unsigned long start, - unsigned long size); +efi_status_t efi_adjust_memory_range_protection(unsigned long start, + unsigned long size); #ifdef CONFIG_X86_64 efi_status_t efi_setup_5level_paging(void); diff --git a/drivers/firmware/efi/libstub/zboot.c b/drivers/firmware/efi/libstub/zboot.c index bdb17eac0cb401..1ceace95675868 100644 --- a/drivers/firmware/efi/libstub/zboot.c +++ b/drivers/firmware/efi/libstub/zboot.c @@ -119,7 +119,7 @@ efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab) } status = efi_random_alloc(alloc_size, min_kimg_align, &image_base, - seed, EFI_LOADER_CODE, EFI_ALLOC_LIMIT); + seed, EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT); if (status != EFI_SUCCESS) { efi_err("Failed to allocate memory\n"); goto free_cmdline; diff --git a/drivers/firmware/efi/libstub/zboot.lds b/drivers/firmware/efi/libstub/zboot.lds index ac8c0ef851581f..af2c82f7bd9024 100644 --- a/drivers/firmware/efi/libstub/zboot.lds +++ b/drivers/firmware/efi/libstub/zboot.lds @@ -41,6 +41,7 @@ SECTIONS } /DISCARD/ : { + *(.discard .discard.*) *(.modinfo .init.modinfo) } } diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c index a1180461a445cf..77dd20f9df312c 100644 --- a/drivers/firmware/efi/memmap.c +++ b/drivers/firmware/efi/memmap.c @@ -15,10 +15,6 @@ #include #include -#ifndef __efi_memmap_free -#define __efi_memmap_free(phys, size, flags) do { } while (0) -#endif - /** * __efi_memmap_init - Common code for mapping the EFI memory map * @data: EFI memory map data @@ -51,11 +47,6 @@ int __init __efi_memmap_init(struct efi_memory_map_data *data) return -ENOMEM; } - if (efi.memmap.flags & (EFI_MEMMAP_MEMBLOCK | EFI_MEMMAP_SLAB)) - __efi_memmap_free(efi.memmap.phys_map, - efi.memmap.desc_size * efi.memmap.nr_map, - efi.memmap.flags); - map.phys_map = data->phys_map; map.nr_map = data->size / data->desc_size; map.map_end = map.map + data->size; diff --git a/drivers/firmware/efi/riscv-runtime.c b/drivers/firmware/efi/riscv-runtime.c index 09525fb5c240e6..01f0f90ea41831 100644 --- a/drivers/firmware/efi/riscv-runtime.c +++ b/drivers/firmware/efi/riscv-runtime.c @@ -85,7 +85,7 @@ static int __init riscv_enable_runtime_services(void) efi_memory_desc_t *md; for_each_efi_memory_desc(md) { - int md_size = md->num_pages << EFI_PAGE_SHIFT; + u64 md_size = md->num_pages << EFI_PAGE_SHIFT; struct resource *res; if (!(md->attribute & EFI_MEMORY_SP)) diff --git a/drivers/firmware/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c index 135278ddaf627b..6c3d84d9bcc16f 100644 --- a/drivers/firmware/efi/unaccepted_memory.c +++ b/drivers/firmware/efi/unaccepted_memory.c @@ -3,6 +3,7 @@ #include #include #include +#include #include /* Protects unaccepted memory bitmap and accepting_list */ @@ -100,7 +101,7 @@ void accept_memory(phys_addr_t start, phys_addr_t end) * overlap on physical address level. */ list_for_each_entry(entry, &accepting_list, list) { - if (entry->end < range.start) + if (entry->end <= range.start) continue; if (entry->start >= range.end) continue; @@ -148,6 +149,9 @@ void accept_memory(phys_addr_t start, phys_addr_t end) } list_del(&range.list); + + touch_softlockup_watchdog(); + spin_unlock_irqrestore(&unaccepted_memory_lock, flags); } diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c index d9629ff8786199..2328ca58bba61f 100644 --- a/drivers/firmware/psci/psci.c +++ b/drivers/firmware/psci/psci.c @@ -497,10 +497,12 @@ int psci_cpu_suspend_enter(u32 state) static int psci_system_suspend(unsigned long unused) { + int err; phys_addr_t pa_cpu_resume = __pa_symbol(cpu_resume); - return invoke_psci_fn(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND), + err = invoke_psci_fn(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND), pa_cpu_resume, 0, 0); + return psci_to_linux_errno(err); } static int psci_system_suspend_enter(suspend_state_t state) diff --git a/drivers/firmware/qcom_scm-smc.c b/drivers/firmware/qcom_scm-smc.c index 16cf88acfa8ee0..0a2a2c794d0eda 100644 --- a/drivers/firmware/qcom_scm-smc.c +++ b/drivers/firmware/qcom_scm-smc.c @@ -71,7 +71,7 @@ int scm_get_wq_ctx(u32 *wq_ctx, u32 *flags, u32 *more_pending) struct arm_smccc_res get_wq_res; struct arm_smccc_args get_wq_ctx = {0}; - get_wq_ctx.args[0] = ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL, + get_wq_ctx.args[0] = ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_64, ARM_SMCCC_OWNER_SIP, SCM_SMC_FNID(QCOM_SCM_SVC_WAITQ, QCOM_SCM_WAITQ_GET_WQ_CTX)); diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c index 06fe8aca870d7b..7af59985f1c1f9 100644 --- a/drivers/firmware/qcom_scm.c +++ b/drivers/firmware/qcom_scm.c @@ -167,6 +167,12 @@ static enum qcom_scm_convention __get_convention(void) if (likely(qcom_scm_convention != SMC_CONVENTION_UNKNOWN)) return qcom_scm_convention; + /* + * Per the "SMC calling convention specification", the 64-bit calling + * convention can only be used when the client is 64-bit, otherwise + * system will encounter the undefined behaviour. + */ +#if IS_ENABLED(CONFIG_ARM64) /* * Device isn't required as there is only one argument - no device * needed to dma_map_single to secure world @@ -187,6 +193,7 @@ static enum qcom_scm_convention __get_convention(void) forced = true; goto found; } +#endif probed_convention = SMC_CONVENTION_ARM_32; ret = __scm_smc_call(NULL, &desc, probed_convention, &res, true); @@ -491,13 +498,14 @@ int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, size_t size, ret = qcom_scm_bw_enable(); if (ret) - return ret; + goto disable_clk; desc.args[1] = mdata_phys; ret = qcom_scm_call(__scm->dev, &desc, &res); - qcom_scm_bw_disable(); + +disable_clk: qcom_scm_clk_disable(); out: @@ -559,10 +567,12 @@ int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, phys_addr_t size) ret = qcom_scm_bw_enable(); if (ret) - return ret; + goto disable_clk; ret = qcom_scm_call(__scm->dev, &desc, &res); qcom_scm_bw_disable(); + +disable_clk: qcom_scm_clk_disable(); return ret ? : res.result[0]; @@ -594,10 +604,12 @@ int qcom_scm_pas_auth_and_reset(u32 peripheral) ret = qcom_scm_bw_enable(); if (ret) - return ret; + goto disable_clk; ret = qcom_scm_call(__scm->dev, &desc, &res); qcom_scm_bw_disable(); + +disable_clk: qcom_scm_clk_disable(); return ret ? : res.result[0]; @@ -628,11 +640,12 @@ int qcom_scm_pas_shutdown(u32 peripheral) ret = qcom_scm_bw_enable(); if (ret) - return ret; + goto disable_clk; ret = qcom_scm_call(__scm->dev, &desc, &res); - qcom_scm_bw_disable(); + +disable_clk: qcom_scm_clk_disable(); return ret ? : res.result[0]; @@ -1326,7 +1339,7 @@ static int qcom_scm_find_dload_address(struct device *dev, u64 *addr) */ bool qcom_scm_is_available(void) { - return !!__scm; + return !!READ_ONCE(__scm); } EXPORT_SYMBOL_GPL(qcom_scm_is_available); @@ -1407,10 +1420,12 @@ static int qcom_scm_probe(struct platform_device *pdev) if (!scm) return -ENOMEM; + scm->dev = &pdev->dev; ret = qcom_scm_find_dload_address(&pdev->dev, &scm->dload_mode_addr); if (ret < 0) return ret; + init_completion(&scm->waitq_comp); mutex_init(&scm->scm_bw_lock); scm->path = devm_of_icc_get(&pdev->dev, NULL); @@ -1442,10 +1457,8 @@ static int qcom_scm_probe(struct platform_device *pdev) if (ret) return ret; - __scm = scm; - __scm->dev = &pdev->dev; - - init_completion(&__scm->waitq_comp); + /* Let all above stores be available after this */ + smp_store_release(&__scm, scm); irq = platform_get_irq_optional(pdev, 0); if (irq < 0) { diff --git a/drivers/firmware/raspberrypi.c b/drivers/firmware/raspberrypi.c index f66efaa5196d9d..428ae54d3196c2 100644 --- a/drivers/firmware/raspberrypi.c +++ b/drivers/firmware/raspberrypi.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -97,8 +98,8 @@ int rpi_firmware_property_list(struct rpi_firmware *fw, if (size & 3) return -EINVAL; - buf = dma_alloc_coherent(fw->cl.dev, PAGE_ALIGN(size), &bus_addr, - GFP_ATOMIC); + buf = dma_alloc_coherent(fw->chan->mbox->dev, PAGE_ALIGN(size), + &bus_addr, GFP_ATOMIC); if (!buf) return -ENOMEM; @@ -126,7 +127,7 @@ int rpi_firmware_property_list(struct rpi_firmware *fw, ret = -EINVAL; } - dma_free_coherent(fw->cl.dev, PAGE_ALIGN(size), buf, bus_addr); + dma_free_coherent(fw->chan->mbox->dev, PAGE_ALIGN(size), buf, bus_addr); return ret; } diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c index 82fcfd29bc4d29..defd7a36cb08a4 100644 --- a/drivers/firmware/sysfb.c +++ b/drivers/firmware/sysfb.c @@ -77,6 +77,8 @@ static __init int sysfb_init(void) bool compatible; int ret = 0; + screen_info_apply_fixups(); + mutex_lock(&disable_lock); if (disabled) goto unlock_mutex; @@ -128,4 +130,4 @@ static __init int sysfb_init(void) } /* must execute after PCI subsystem for EFI quirks */ -subsys_initcall_sync(sysfb_init); +device_initcall(sysfb_init); diff --git a/drivers/firmware/tegra/bpmp-debugfs.c b/drivers/firmware/tegra/bpmp-debugfs.c index 6dfe3d34109ee9..b20d04950d99b3 100644 --- a/drivers/firmware/tegra/bpmp-debugfs.c +++ b/drivers/firmware/tegra/bpmp-debugfs.c @@ -77,7 +77,7 @@ static const char *get_filename(struct tegra_bpmp *bpmp, root_path_buf = kzalloc(root_path_buf_len, GFP_KERNEL); if (!root_path_buf) - goto out; + return NULL; root_path = dentry_path(bpmp->debugfs_mirror, root_path_buf, root_path_buf_len); diff --git a/drivers/firmware/tegra/bpmp.c b/drivers/firmware/tegra/bpmp.c index 51d062e0c3f129..c3a1dc3449617f 100644 --- a/drivers/firmware/tegra/bpmp.c +++ b/drivers/firmware/tegra/bpmp.c @@ -24,12 +24,6 @@ #define MSG_RING BIT(1) #define TAG_SZ 32 -static inline struct tegra_bpmp * -mbox_client_to_bpmp(struct mbox_client *client) -{ - return container_of(client, struct tegra_bpmp, mbox.client); -} - static inline const struct tegra_bpmp_ops * channel_to_ops(struct tegra_bpmp_channel *channel) { @@ -313,6 +307,8 @@ static ssize_t tegra_bpmp_channel_write(struct tegra_bpmp_channel *channel, return __tegra_bpmp_channel_write(channel, mrq, flags, data, size); } +static int __maybe_unused tegra_bpmp_resume(struct device *dev); + int tegra_bpmp_transfer_atomic(struct tegra_bpmp *bpmp, struct tegra_bpmp_message *msg) { @@ -325,6 +321,14 @@ int tegra_bpmp_transfer_atomic(struct tegra_bpmp *bpmp, if (!tegra_bpmp_message_valid(msg)) return -EINVAL; + if (bpmp->suspended) { + /* Reset BPMP IPC channels during resume based on flags passed */ + if (msg->flags & TEGRA_BPMP_MESSAGE_RESET) + tegra_bpmp_resume(bpmp->dev); + else + return -EAGAIN; + } + channel = bpmp->tx_channel; spin_lock(&bpmp->atomic_tx_lock); @@ -364,6 +368,14 @@ int tegra_bpmp_transfer(struct tegra_bpmp *bpmp, if (!tegra_bpmp_message_valid(msg)) return -EINVAL; + if (bpmp->suspended) { + /* Reset BPMP IPC channels during resume based on flags passed */ + if (msg->flags & TEGRA_BPMP_MESSAGE_RESET) + tegra_bpmp_resume(bpmp->dev); + else + return -EAGAIN; + } + channel = tegra_bpmp_write_threaded(bpmp, msg->mrq, msg->tx.data, msg->tx.size); if (IS_ERR(channel)) @@ -796,10 +808,21 @@ static int tegra_bpmp_probe(struct platform_device *pdev) return err; } +static int __maybe_unused tegra_bpmp_suspend(struct device *dev) +{ + struct tegra_bpmp *bpmp = dev_get_drvdata(dev); + + bpmp->suspended = true; + + return 0; +} + static int __maybe_unused tegra_bpmp_resume(struct device *dev) { struct tegra_bpmp *bpmp = dev_get_drvdata(dev); + bpmp->suspended = false; + if (bpmp->soc->ops->resume) return bpmp->soc->ops->resume(bpmp); else @@ -807,6 +830,7 @@ static int __maybe_unused tegra_bpmp_resume(struct device *dev) } static const struct dev_pm_ops tegra_bpmp_pm_ops = { + .suspend_noirq = tegra_bpmp_suspend, .resume_noirq = tegra_bpmp_resume, }; diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c index 26a37f47f4ca54..3b4c9355cb60f6 100644 --- a/drivers/firmware/ti_sci.c +++ b/drivers/firmware/ti_sci.c @@ -161,7 +161,7 @@ static int ti_sci_debugfs_create(struct platform_device *pdev, { struct device *dev = &pdev->dev; struct resource *res; - char debug_name[50] = "ti_sci_debug@"; + char debug_name[50]; /* Debug region is optional */ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, @@ -178,10 +178,10 @@ static int ti_sci_debugfs_create(struct platform_device *pdev, /* Setup NULL termination */ info->debug_buffer[info->debug_region_size] = 0; - info->d = debugfs_create_file(strncat(debug_name, dev_name(dev), - sizeof(debug_name) - - sizeof("ti_sci_debug@")), - 0444, NULL, info, &ti_sci_debug_fops); + snprintf(debug_name, sizeof(debug_name), "ti_sci_debug@%s", + dev_name(dev)); + info->d = debugfs_create_file(debug_name, 0444, NULL, info, + &ti_sci_debug_fops); if (IS_ERR(info->d)) return PTR_ERR(info->d); @@ -190,19 +190,6 @@ static int ti_sci_debugfs_create(struct platform_device *pdev, return 0; } -/** - * ti_sci_debugfs_destroy() - clean up log debug file - * @pdev: platform device pointer - * @info: Pointer to SCI entity information - */ -static void ti_sci_debugfs_destroy(struct platform_device *pdev, - struct ti_sci_info *info) -{ - if (IS_ERR(info->debug_region)) - return; - - debugfs_remove(info->d); -} #else /* CONFIG_DEBUG_FS */ static inline int ti_sci_debugfs_create(struct platform_device *dev, struct ti_sci_info *info) @@ -3449,43 +3436,12 @@ static int ti_sci_probe(struct platform_device *pdev) return ret; } -static int ti_sci_remove(struct platform_device *pdev) -{ - struct ti_sci_info *info; - struct device *dev = &pdev->dev; - int ret = 0; - - of_platform_depopulate(dev); - - info = platform_get_drvdata(pdev); - - if (info->nb.notifier_call) - unregister_restart_handler(&info->nb); - - mutex_lock(&ti_sci_list_mutex); - if (info->users) - ret = -EBUSY; - else - list_del(&info->node); - mutex_unlock(&ti_sci_list_mutex); - - if (!ret) { - ti_sci_debugfs_destroy(pdev, info); - - /* Safe to free channels since no more users */ - mbox_free_channel(info->chan_tx); - mbox_free_channel(info->chan_rx); - } - - return ret; -} - static struct platform_driver ti_sci_driver = { .probe = ti_sci_probe, - .remove = ti_sci_remove, .driver = { .name = "ti-sci", .of_match_table = of_match_ptr(ti_sci_of_match), + .suppress_bind_attrs = true, }, }; module_platform_driver(ti_sci_driver); diff --git a/drivers/firmware/turris-mox-rwtm.c b/drivers/firmware/turris-mox-rwtm.c index 2de0fb139ce176..3d354ebd38c285 100644 --- a/drivers/firmware/turris-mox-rwtm.c +++ b/drivers/firmware/turris-mox-rwtm.c @@ -2,7 +2,7 @@ /* * Turris Mox rWTM firmware driver * - * Copyright (C) 2019 Marek Behún + * Copyright (C) 2019, 2024 Marek Behún */ #include @@ -174,6 +174,9 @@ static void mox_rwtm_rx_callback(struct mbox_client *cl, void *data) struct mox_rwtm *rwtm = dev_get_drvdata(cl->dev); struct armada_37xx_rwtm_rx_msg *msg = data; + if (completion_done(&rwtm->cmd_done)) + return; + rwtm->reply = *msg; complete(&rwtm->cmd_done); } @@ -199,9 +202,8 @@ static int mox_get_board_info(struct mox_rwtm *rwtm) if (ret < 0) return ret; - ret = wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2); - if (ret < 0) - return ret; + if (!wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2)) + return -ETIMEDOUT; ret = mox_get_status(MBOX_CMD_BOARD_INFO, reply->retval); if (ret == -ENODATA) { @@ -235,9 +237,8 @@ static int mox_get_board_info(struct mox_rwtm *rwtm) if (ret < 0) return ret; - ret = wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2); - if (ret < 0) - return ret; + if (!wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2)) + return -ETIMEDOUT; ret = mox_get_status(MBOX_CMD_ECDSA_PUB_KEY, reply->retval); if (ret == -ENODATA) { @@ -274,9 +275,8 @@ static int check_get_random_support(struct mox_rwtm *rwtm) if (ret < 0) return ret; - ret = wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2); - if (ret < 0) - return ret; + if (!wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2)) + return -ETIMEDOUT; return mox_get_status(MBOX_CMD_GET_RANDOM, rwtm->reply.retval); } @@ -499,6 +499,7 @@ static int turris_mox_rwtm_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rwtm); mutex_init(&rwtm->busy); + init_completion(&rwtm->cmd_done); rwtm->mbox_client.dev = dev; rwtm->mbox_client.rx_callback = mox_rwtm_rx_callback; @@ -512,8 +513,6 @@ static int turris_mox_rwtm_probe(struct platform_device *pdev) goto remove_files; } - init_completion(&rwtm->cmd_done); - ret = mox_get_board_info(rwtm); if (ret < 0) dev_warn(dev, "Cannot read board information: %i\n", ret); diff --git a/drivers/fpga/dfl-pci.c b/drivers/fpga/dfl-pci.c index 98b8fd16183e41..80cac3a5f97678 100644 --- a/drivers/fpga/dfl-pci.c +++ b/drivers/fpga/dfl-pci.c @@ -78,6 +78,7 @@ static void cci_pci_free_irq(struct pci_dev *pcidev) #define PCIE_DEVICE_ID_SILICOM_PAC_N5011 0x1001 #define PCIE_DEVICE_ID_INTEL_DFL 0xbcce /* PCI Subdevice ID for PCIE_DEVICE_ID_INTEL_DFL */ +#define PCIE_SUBDEVICE_ID_INTEL_D5005 0x138d #define PCIE_SUBDEVICE_ID_INTEL_N6000 0x1770 #define PCIE_SUBDEVICE_ID_INTEL_N6001 0x1771 #define PCIE_SUBDEVICE_ID_INTEL_C6100 0x17d4 @@ -101,6 +102,8 @@ static struct pci_device_id cci_pcie_id_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_PAC_D5005_VF),}, {PCI_DEVICE(PCI_VENDOR_ID_SILICOM_DENMARK, PCIE_DEVICE_ID_SILICOM_PAC_N5010),}, {PCI_DEVICE(PCI_VENDOR_ID_SILICOM_DENMARK, PCIE_DEVICE_ID_SILICOM_PAC_N5011),}, + {PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_DFL, + PCI_VENDOR_ID_INTEL, PCIE_SUBDEVICE_ID_INTEL_D5005),}, {PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_DFL, PCI_VENDOR_ID_INTEL, PCIE_SUBDEVICE_ID_INTEL_N6000),}, {PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_DFL_VF, diff --git a/drivers/fpga/fpga-bridge.c b/drivers/fpga/fpga-bridge.c index a024be2b84e291..83d35fbb824505 100644 --- a/drivers/fpga/fpga-bridge.c +++ b/drivers/fpga/fpga-bridge.c @@ -55,33 +55,26 @@ int fpga_bridge_disable(struct fpga_bridge *bridge) } EXPORT_SYMBOL_GPL(fpga_bridge_disable); -static struct fpga_bridge *__fpga_bridge_get(struct device *dev, +static struct fpga_bridge *__fpga_bridge_get(struct device *bridge_dev, struct fpga_image_info *info) { struct fpga_bridge *bridge; - int ret = -ENODEV; - bridge = to_fpga_bridge(dev); + bridge = to_fpga_bridge(bridge_dev); bridge->info = info; - if (!mutex_trylock(&bridge->mutex)) { - ret = -EBUSY; - goto err_dev; - } + if (!mutex_trylock(&bridge->mutex)) + return ERR_PTR(-EBUSY); - if (!try_module_get(dev->parent->driver->owner)) - goto err_ll_mod; + if (!try_module_get(bridge->br_ops_owner)) { + mutex_unlock(&bridge->mutex); + return ERR_PTR(-ENODEV); + } dev_dbg(&bridge->dev, "get\n"); return bridge; - -err_ll_mod: - mutex_unlock(&bridge->mutex); -err_dev: - put_device(dev); - return ERR_PTR(ret); } /** @@ -98,13 +91,18 @@ static struct fpga_bridge *__fpga_bridge_get(struct device *dev, struct fpga_bridge *of_fpga_bridge_get(struct device_node *np, struct fpga_image_info *info) { - struct device *dev; + struct fpga_bridge *bridge; + struct device *bridge_dev; - dev = class_find_device_by_of_node(&fpga_bridge_class, np); - if (!dev) + bridge_dev = class_find_device_by_of_node(&fpga_bridge_class, np); + if (!bridge_dev) return ERR_PTR(-ENODEV); - return __fpga_bridge_get(dev, info); + bridge = __fpga_bridge_get(bridge_dev, info); + if (IS_ERR(bridge)) + put_device(bridge_dev); + + return bridge; } EXPORT_SYMBOL_GPL(of_fpga_bridge_get); @@ -125,6 +123,7 @@ static int fpga_bridge_dev_match(struct device *dev, const void *data) struct fpga_bridge *fpga_bridge_get(struct device *dev, struct fpga_image_info *info) { + struct fpga_bridge *bridge; struct device *bridge_dev; bridge_dev = class_find_device(&fpga_bridge_class, NULL, dev, @@ -132,7 +131,11 @@ struct fpga_bridge *fpga_bridge_get(struct device *dev, if (!bridge_dev) return ERR_PTR(-ENODEV); - return __fpga_bridge_get(bridge_dev, info); + bridge = __fpga_bridge_get(bridge_dev, info); + if (IS_ERR(bridge)) + put_device(bridge_dev); + + return bridge; } EXPORT_SYMBOL_GPL(fpga_bridge_get); @@ -146,7 +149,7 @@ void fpga_bridge_put(struct fpga_bridge *bridge) dev_dbg(&bridge->dev, "put\n"); bridge->info = NULL; - module_put(bridge->dev.parent->driver->owner); + module_put(bridge->br_ops_owner); mutex_unlock(&bridge->mutex); put_device(&bridge->dev); } @@ -316,18 +319,19 @@ static struct attribute *fpga_bridge_attrs[] = { ATTRIBUTE_GROUPS(fpga_bridge); /** - * fpga_bridge_register - create and register an FPGA Bridge device + * __fpga_bridge_register - create and register an FPGA Bridge device * @parent: FPGA bridge device from pdev * @name: FPGA bridge name * @br_ops: pointer to structure of fpga bridge ops * @priv: FPGA bridge private data + * @owner: owner module containing the br_ops * * Return: struct fpga_bridge pointer or ERR_PTR() */ struct fpga_bridge * -fpga_bridge_register(struct device *parent, const char *name, - const struct fpga_bridge_ops *br_ops, - void *priv) +__fpga_bridge_register(struct device *parent, const char *name, + const struct fpga_bridge_ops *br_ops, + void *priv, struct module *owner) { struct fpga_bridge *bridge; int id, ret; @@ -357,6 +361,7 @@ fpga_bridge_register(struct device *parent, const char *name, bridge->name = name; bridge->br_ops = br_ops; + bridge->br_ops_owner = owner; bridge->priv = priv; bridge->dev.groups = br_ops->groups; @@ -386,7 +391,7 @@ fpga_bridge_register(struct device *parent, const char *name, return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(fpga_bridge_register); +EXPORT_SYMBOL_GPL(__fpga_bridge_register); /** * fpga_bridge_unregister - unregister an FPGA bridge diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c index 06651389c59262..0f4035b089a2ea 100644 --- a/drivers/fpga/fpga-mgr.c +++ b/drivers/fpga/fpga-mgr.c @@ -664,20 +664,16 @@ static struct attribute *fpga_mgr_attrs[] = { }; ATTRIBUTE_GROUPS(fpga_mgr); -static struct fpga_manager *__fpga_mgr_get(struct device *dev) +static struct fpga_manager *__fpga_mgr_get(struct device *mgr_dev) { struct fpga_manager *mgr; - mgr = to_fpga_manager(dev); + mgr = to_fpga_manager(mgr_dev); - if (!try_module_get(dev->parent->driver->owner)) - goto err_dev; + if (!try_module_get(mgr->mops_owner)) + mgr = ERR_PTR(-ENODEV); return mgr; - -err_dev: - put_device(dev); - return ERR_PTR(-ENODEV); } static int fpga_mgr_dev_match(struct device *dev, const void *data) @@ -693,12 +689,18 @@ static int fpga_mgr_dev_match(struct device *dev, const void *data) */ struct fpga_manager *fpga_mgr_get(struct device *dev) { - struct device *mgr_dev = class_find_device(&fpga_mgr_class, NULL, dev, - fpga_mgr_dev_match); + struct fpga_manager *mgr; + struct device *mgr_dev; + + mgr_dev = class_find_device(&fpga_mgr_class, NULL, dev, fpga_mgr_dev_match); if (!mgr_dev) return ERR_PTR(-ENODEV); - return __fpga_mgr_get(mgr_dev); + mgr = __fpga_mgr_get(mgr_dev); + if (IS_ERR(mgr)) + put_device(mgr_dev); + + return mgr; } EXPORT_SYMBOL_GPL(fpga_mgr_get); @@ -711,13 +713,18 @@ EXPORT_SYMBOL_GPL(fpga_mgr_get); */ struct fpga_manager *of_fpga_mgr_get(struct device_node *node) { - struct device *dev; + struct fpga_manager *mgr; + struct device *mgr_dev; - dev = class_find_device_by_of_node(&fpga_mgr_class, node); - if (!dev) + mgr_dev = class_find_device_by_of_node(&fpga_mgr_class, node); + if (!mgr_dev) return ERR_PTR(-ENODEV); - return __fpga_mgr_get(dev); + mgr = __fpga_mgr_get(mgr_dev); + if (IS_ERR(mgr)) + put_device(mgr_dev); + + return mgr; } EXPORT_SYMBOL_GPL(of_fpga_mgr_get); @@ -727,7 +734,7 @@ EXPORT_SYMBOL_GPL(of_fpga_mgr_get); */ void fpga_mgr_put(struct fpga_manager *mgr) { - module_put(mgr->dev.parent->driver->owner); + module_put(mgr->mops_owner); put_device(&mgr->dev); } EXPORT_SYMBOL_GPL(fpga_mgr_put); @@ -766,9 +773,10 @@ void fpga_mgr_unlock(struct fpga_manager *mgr) EXPORT_SYMBOL_GPL(fpga_mgr_unlock); /** - * fpga_mgr_register_full - create and register an FPGA Manager device + * __fpga_mgr_register_full - create and register an FPGA Manager device * @parent: fpga manager device from pdev * @info: parameters for fpga manager + * @owner: owner module containing the ops * * The caller of this function is responsible for calling fpga_mgr_unregister(). * Using devm_fpga_mgr_register_full() instead is recommended. @@ -776,7 +784,8 @@ EXPORT_SYMBOL_GPL(fpga_mgr_unlock); * Return: pointer to struct fpga_manager pointer or ERR_PTR() */ struct fpga_manager * -fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info) +__fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info, + struct module *owner) { const struct fpga_manager_ops *mops = info->mops; struct fpga_manager *mgr; @@ -804,6 +813,8 @@ fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *in mutex_init(&mgr->ref_mutex); + mgr->mops_owner = owner; + mgr->name = info->name; mgr->mops = info->mops; mgr->priv = info->priv; @@ -841,14 +852,15 @@ fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *in return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(fpga_mgr_register_full); +EXPORT_SYMBOL_GPL(__fpga_mgr_register_full); /** - * fpga_mgr_register - create and register an FPGA Manager device + * __fpga_mgr_register - create and register an FPGA Manager device * @parent: fpga manager device from pdev * @name: fpga manager name * @mops: pointer to structure of fpga manager ops * @priv: fpga manager private data + * @owner: owner module containing the ops * * The caller of this function is responsible for calling fpga_mgr_unregister(). * Using devm_fpga_mgr_register() instead is recommended. This simple @@ -859,8 +871,8 @@ EXPORT_SYMBOL_GPL(fpga_mgr_register_full); * Return: pointer to struct fpga_manager pointer or ERR_PTR() */ struct fpga_manager * -fpga_mgr_register(struct device *parent, const char *name, - const struct fpga_manager_ops *mops, void *priv) +__fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv, struct module *owner) { struct fpga_manager_info info = { 0 }; @@ -868,9 +880,9 @@ fpga_mgr_register(struct device *parent, const char *name, info.mops = mops; info.priv = priv; - return fpga_mgr_register_full(parent, &info); + return __fpga_mgr_register_full(parent, &info, owner); } -EXPORT_SYMBOL_GPL(fpga_mgr_register); +EXPORT_SYMBOL_GPL(__fpga_mgr_register); /** * fpga_mgr_unregister - unregister an FPGA manager @@ -900,9 +912,10 @@ static void devm_fpga_mgr_unregister(struct device *dev, void *res) } /** - * devm_fpga_mgr_register_full - resource managed variant of fpga_mgr_register() + * __devm_fpga_mgr_register_full - resource managed variant of fpga_mgr_register() * @parent: fpga manager device from pdev * @info: parameters for fpga manager + * @owner: owner module containing the ops * * Return: fpga manager pointer on success, negative error code otherwise. * @@ -910,7 +923,8 @@ static void devm_fpga_mgr_unregister(struct device *dev, void *res) * function will be called automatically when the managing device is detached. */ struct fpga_manager * -devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info) +__devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info, + struct module *owner) { struct fpga_mgr_devres *dr; struct fpga_manager *mgr; @@ -919,7 +933,7 @@ devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_inf if (!dr) return ERR_PTR(-ENOMEM); - mgr = fpga_mgr_register_full(parent, info); + mgr = __fpga_mgr_register_full(parent, info, owner); if (IS_ERR(mgr)) { devres_free(dr); return mgr; @@ -930,14 +944,15 @@ devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_inf return mgr; } -EXPORT_SYMBOL_GPL(devm_fpga_mgr_register_full); +EXPORT_SYMBOL_GPL(__devm_fpga_mgr_register_full); /** - * devm_fpga_mgr_register - resource managed variant of fpga_mgr_register() + * __devm_fpga_mgr_register - resource managed variant of fpga_mgr_register() * @parent: fpga manager device from pdev * @name: fpga manager name * @mops: pointer to structure of fpga manager ops * @priv: fpga manager private data + * @owner: owner module containing the ops * * Return: fpga manager pointer on success, negative error code otherwise. * @@ -946,8 +961,9 @@ EXPORT_SYMBOL_GPL(devm_fpga_mgr_register_full); * device is detached. */ struct fpga_manager * -devm_fpga_mgr_register(struct device *parent, const char *name, - const struct fpga_manager_ops *mops, void *priv) +__devm_fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv, + struct module *owner) { struct fpga_manager_info info = { 0 }; @@ -955,9 +971,9 @@ devm_fpga_mgr_register(struct device *parent, const char *name, info.mops = mops; info.priv = priv; - return devm_fpga_mgr_register_full(parent, &info); + return __devm_fpga_mgr_register_full(parent, &info, owner); } -EXPORT_SYMBOL_GPL(devm_fpga_mgr_register); +EXPORT_SYMBOL_GPL(__devm_fpga_mgr_register); static void fpga_mgr_dev_release(struct device *dev) { diff --git a/drivers/fpga/fpga-region.c b/drivers/fpga/fpga-region.c index b364a929425ce9..753cd142503e0e 100644 --- a/drivers/fpga/fpga-region.c +++ b/drivers/fpga/fpga-region.c @@ -53,7 +53,7 @@ static struct fpga_region *fpga_region_get(struct fpga_region *region) } get_device(dev); - if (!try_module_get(dev->parent->driver->owner)) { + if (!try_module_get(region->ops_owner)) { put_device(dev); mutex_unlock(®ion->mutex); return ERR_PTR(-ENODEV); @@ -75,7 +75,7 @@ static void fpga_region_put(struct fpga_region *region) dev_dbg(dev, "put\n"); - module_put(dev->parent->driver->owner); + module_put(region->ops_owner); put_device(dev); mutex_unlock(®ion->mutex); } @@ -181,14 +181,16 @@ static struct attribute *fpga_region_attrs[] = { ATTRIBUTE_GROUPS(fpga_region); /** - * fpga_region_register_full - create and register an FPGA Region device + * __fpga_region_register_full - create and register an FPGA Region device * @parent: device parent * @info: parameters for FPGA Region + * @owner: module containing the get_bridges function * * Return: struct fpga_region or ERR_PTR() */ struct fpga_region * -fpga_region_register_full(struct device *parent, const struct fpga_region_info *info) +__fpga_region_register_full(struct device *parent, const struct fpga_region_info *info, + struct module *owner) { struct fpga_region *region; int id, ret = 0; @@ -213,6 +215,7 @@ fpga_region_register_full(struct device *parent, const struct fpga_region_info * region->compat_id = info->compat_id; region->priv = info->priv; region->get_bridges = info->get_bridges; + region->ops_owner = owner; mutex_init(®ion->mutex); INIT_LIST_HEAD(®ion->bridge_list); @@ -241,13 +244,14 @@ fpga_region_register_full(struct device *parent, const struct fpga_region_info * return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(fpga_region_register_full); +EXPORT_SYMBOL_GPL(__fpga_region_register_full); /** - * fpga_region_register - create and register an FPGA Region device + * __fpga_region_register - create and register an FPGA Region device * @parent: device parent * @mgr: manager that programs this region * @get_bridges: optional function to get bridges to a list + * @owner: module containing the get_bridges function * * This simple version of the register function should be sufficient for most users. * The fpga_region_register_full() function is available for users that need to @@ -256,17 +260,17 @@ EXPORT_SYMBOL_GPL(fpga_region_register_full); * Return: struct fpga_region or ERR_PTR() */ struct fpga_region * -fpga_region_register(struct device *parent, struct fpga_manager *mgr, - int (*get_bridges)(struct fpga_region *)) +__fpga_region_register(struct device *parent, struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *), struct module *owner) { struct fpga_region_info info = { 0 }; info.mgr = mgr; info.get_bridges = get_bridges; - return fpga_region_register_full(parent, &info); + return __fpga_region_register_full(parent, &info, owner); } -EXPORT_SYMBOL_GPL(fpga_region_register); +EXPORT_SYMBOL_GPL(__fpga_region_register); /** * fpga_region_unregister - unregister an FPGA region diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 673bafb8be5887..ebd4e113dc2654 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -691,7 +691,8 @@ config GPIO_UNIPHIER Say yes here to support UniPhier GPIOs. config GPIO_VF610 - def_bool y + bool "VF610 GPIO support" + default y if SOC_VF610 depends on ARCH_MXC select GPIOLIB_IRQCHIP help @@ -1506,7 +1507,7 @@ config GPIO_TPS68470 are "output only" GPIOs. config GPIO_TQMX86 - tristate "TQ-Systems QTMX86 GPIO" + tristate "TQ-Systems TQMx86 GPIO" depends on MFD_TQMX86 || COMPILE_TEST depends on HAS_IOPORT_MAP select GPIOLIB_IRQCHIP diff --git a/drivers/gpio/gpio-74x164.c b/drivers/gpio/gpio-74x164.c index e00c333105170f..753e7be039e4d9 100644 --- a/drivers/gpio/gpio-74x164.c +++ b/drivers/gpio/gpio-74x164.c @@ -127,8 +127,6 @@ static int gen_74x164_probe(struct spi_device *spi) if (IS_ERR(chip->gpiod_oe)) return PTR_ERR(chip->gpiod_oe); - gpiod_set_value_cansleep(chip->gpiod_oe, 1); - spi_set_drvdata(spi, chip); chip->gpio_chip.label = spi->modalias; @@ -153,6 +151,8 @@ static int gen_74x164_probe(struct spi_device *spi) goto exit_destroy; } + gpiod_set_value_cansleep(chip->gpiod_oe, 1); + ret = gpiochip_add_data(&chip->gpio_chip, chip); if (!ret) return 0; diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index 58f107194fdafd..76468e6a2899a8 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -406,6 +406,8 @@ static void __aspeed_gpio_set(struct gpio_chip *gc, unsigned int offset, gpio->dcache[GPIO_BANK(offset)] = reg; iowrite32(reg, addr); + /* Flush write */ + ioread32(addr); } static void aspeed_gpio_set(struct gpio_chip *gc, unsigned int offset, @@ -1191,7 +1193,7 @@ static int __init aspeed_gpio_probe(struct platform_device *pdev) if (!gpio_id) return -EINVAL; - gpio->clk = of_clk_get(pdev->dev.of_node, 0); + gpio->clk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(gpio->clk)) { dev_warn(&pdev->dev, "Failed to get clock from devicetree, debouncing disabled\n"); diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c index 1ee62cd58582b6..25db014494a4de 100644 --- a/drivers/gpio/gpio-crystalcove.c +++ b/drivers/gpio/gpio-crystalcove.c @@ -92,7 +92,7 @@ static inline int to_reg(int gpio, enum ctrl_register reg_type) case 0x5e: return GPIOPANELCTL; default: - return -EOPNOTSUPP; + return -ENOTSUPP; } } diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 8db5717bdabe56..75107ede3bf8f4 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -225,6 +225,11 @@ static int davinci_gpio_probe(struct platform_device *pdev) else nirq = DIV_ROUND_UP(ngpio, 16); + if (nirq > MAX_INT_PER_BANK) { + dev_err(dev, "Too many IRQs!\n"); + return -EINVAL; + } + chips = devm_kzalloc(dev, sizeof(*chips), GFP_KERNEL); if (!chips) return -ENOMEM; @@ -284,7 +289,7 @@ static int davinci_gpio_probe(struct platform_device *pdev) * serve as EDMA event triggers. */ -static void gpio_irq_disable(struct irq_data *d) +static void gpio_irq_mask(struct irq_data *d) { struct davinci_gpio_regs __iomem *g = irq2regs(d); uintptr_t mask = (uintptr_t)irq_data_get_irq_handler_data(d); @@ -293,7 +298,7 @@ static void gpio_irq_disable(struct irq_data *d) writel_relaxed(mask, &g->clr_rising); } -static void gpio_irq_enable(struct irq_data *d) +static void gpio_irq_unmask(struct irq_data *d) { struct davinci_gpio_regs __iomem *g = irq2regs(d); uintptr_t mask = (uintptr_t)irq_data_get_irq_handler_data(d); @@ -319,8 +324,8 @@ static int gpio_irq_type(struct irq_data *d, unsigned trigger) static struct irq_chip gpio_irqchip = { .name = "GPIO", - .irq_enable = gpio_irq_enable, - .irq_disable = gpio_irq_disable, + .irq_unmask = gpio_irq_unmask, + .irq_mask = gpio_irq_mask, .irq_set_type = gpio_irq_type, .flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_SKIP_SET_WAKE, }; diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index c22fcaa44a614c..6b7d47a52b10a1 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -283,13 +283,15 @@ static void dwapb_irq_enable(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct dwapb_gpio *gpio = to_dwapb_gpio(gc); + irq_hw_number_t hwirq = irqd_to_hwirq(d); unsigned long flags; u32 val; raw_spin_lock_irqsave(&gc->bgpio_lock, flags); - val = dwapb_read(gpio, GPIO_INTEN); - val |= BIT(irqd_to_hwirq(d)); + val = dwapb_read(gpio, GPIO_INTEN) | BIT(hwirq); dwapb_write(gpio, GPIO_INTEN, val); + val = dwapb_read(gpio, GPIO_INTMASK) & ~BIT(hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags); } @@ -297,12 +299,14 @@ static void dwapb_irq_disable(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct dwapb_gpio *gpio = to_dwapb_gpio(gc); + irq_hw_number_t hwirq = irqd_to_hwirq(d); unsigned long flags; u32 val; raw_spin_lock_irqsave(&gc->bgpio_lock, flags); - val = dwapb_read(gpio, GPIO_INTEN); - val &= ~BIT(irqd_to_hwirq(d)); + val = dwapb_read(gpio, GPIO_INTMASK) | BIT(hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); + val = dwapb_read(gpio, GPIO_INTEN) & ~BIT(hwirq); dwapb_write(gpio, GPIO_INTEN, val); raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags); } diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c index 5320cf1de89c46..b24e349deed5eb 100644 --- a/drivers/gpio/gpio-eic-sprd.c +++ b/drivers/gpio/gpio-eic-sprd.c @@ -321,20 +321,27 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) switch (flow_type) { case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 1); + sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IC, 1); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 0); + sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IC, 1); break; case IRQ_TYPE_EDGE_RISING: case IRQ_TYPE_EDGE_FALLING: case IRQ_TYPE_EDGE_BOTH: state = sprd_eic_get(chip, offset); - if (state) + if (state) { sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 0); - else + sprd_eic_update(chip, offset, + SPRD_EIC_DBNC_IC, 1); + } else { sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 1); + sprd_eic_update(chip, offset, + SPRD_EIC_DBNC_IC, 1); + } break; default: return -ENOTSUPP; @@ -346,20 +353,27 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) switch (flow_type) { case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTCLR, 1); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTCLR, 1); break; case IRQ_TYPE_EDGE_RISING: case IRQ_TYPE_EDGE_FALLING: case IRQ_TYPE_EDGE_BOTH: state = sprd_eic_get(chip, offset); - if (state) + if (state) { sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 0); - else + sprd_eic_update(chip, offset, + SPRD_EIC_LATCH_INTCLR, 1); + } else { sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 1); + sprd_eic_update(chip, offset, + SPRD_EIC_LATCH_INTCLR, 1); + } break; default: return -ENOTSUPP; @@ -373,29 +387,34 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_FALLING: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_BOTH: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 1); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; default: @@ -408,29 +427,34 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_FALLING: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_BOTH: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 1); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; default: diff --git a/drivers/gpio/gpio-lpc32xx.c b/drivers/gpio/gpio-lpc32xx.c index 5ef8af8249806a..c097e310c9e841 100644 --- a/drivers/gpio/gpio-lpc32xx.c +++ b/drivers/gpio/gpio-lpc32xx.c @@ -529,6 +529,7 @@ static const struct of_device_id lpc32xx_gpio_of_match[] = { { .compatible = "nxp,lpc3220-gpio", }, { }, }; +MODULE_DEVICE_TABLE(of, lpc32xx_gpio_of_match); static struct platform_driver lpc32xx_gpio_driver = { .driver = { diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c index 7a3e1760fc5b7d..10ea71273c8915 100644 --- a/drivers/gpio/gpio-mlxbf3.c +++ b/drivers/gpio/gpio-mlxbf3.c @@ -39,6 +39,8 @@ #define MLXBF_GPIO_CAUSE_OR_EVTEN0 0x14 #define MLXBF_GPIO_CAUSE_OR_CLRCAUSE 0x18 +#define MLXBF_GPIO_CLR_ALL_INTS GENMASK(31, 0) + struct mlxbf3_gpio_context { struct gpio_chip gc; @@ -82,6 +84,8 @@ static void mlxbf3_gpio_irq_disable(struct irq_data *irqd) val = readl(gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0); val &= ~BIT(offset); writel(val, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0); + + writel(BIT(offset), gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_CLRCAUSE); raw_spin_unlock_irqrestore(&gs->gc.bgpio_lock, flags); gpiochip_disable_irq(gc, offset); @@ -215,6 +219,8 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev) gs->gpio_clr_io + MLXBF_GPIO_FW_DATA_OUT_CLEAR, gs->gpio_set_io + MLXBF_GPIO_FW_OUTPUT_ENABLE_SET, gs->gpio_clr_io + MLXBF_GPIO_FW_OUTPUT_ENABLE_CLEAR, 0); + if (ret) + return dev_err_probe(dev, ret, "%s: bgpio_init() failed", __func__); gc->request = gpiochip_generic_request; gc->free = gpiochip_generic_free; @@ -251,6 +257,15 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev) return 0; } +static void mlxbf3_gpio_shutdown(struct platform_device *pdev) +{ + struct mlxbf3_gpio_context *gs = platform_get_drvdata(pdev); + + /* Disable and clear all interrupts */ + writel(0, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0); + writel(MLXBF_GPIO_CLR_ALL_INTS, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_CLRCAUSE); +} + static const struct acpi_device_id mlxbf3_gpio_acpi_match[] = { { "MLNXBF33", 0 }, {} @@ -263,6 +278,7 @@ static struct platform_driver mlxbf3_gpio_driver = { .acpi_match_table = mlxbf3_gpio_acpi_match, }, .probe = mlxbf3_gpio_probe, + .shutdown = mlxbf3_gpio_shutdown, }; module_platform_driver(mlxbf3_gpio_driver); diff --git a/drivers/gpio/gpio-mmio.c b/drivers/gpio/gpio-mmio.c index 74fdf0d87b2c8e..c9f9f4e36c89b5 100644 --- a/drivers/gpio/gpio-mmio.c +++ b/drivers/gpio/gpio-mmio.c @@ -622,8 +622,6 @@ int bgpio_init(struct gpio_chip *gc, struct device *dev, ret = gpiochip_get_ngpios(gc, dev); if (ret) gc->ngpio = gc->bgpio_bits; - else - gc->bgpio_bits = roundup_pow_of_two(round_up(gc->ngpio, 8)); ret = bgpio_setup_io(gc, dat, set, clr, flags); if (ret) diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index bdd50a78e4142d..ce9a94e332801f 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -766,6 +766,8 @@ static void pca953x_irq_bus_sync_unlock(struct irq_data *d) int level; if (chip->driver_data & PCA_PCAL) { + guard(mutex)(&chip->i2c_lock); + /* Enable latch on interrupt-enabled inputs */ pca953x_write_regs(chip, PCAL953X_IN_LATCH, chip->irq_mask); diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index b35b9604413f08..caeb3bdc78f8db 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -713,6 +713,7 @@ static int rockchip_gpio_probe(struct platform_device *pdev) return -ENODEV; pctldev = of_pinctrl_get(pctlnp); + of_node_put(pctlnp); if (!pctldev) return -EPROBE_DEFER; diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 44bf1709a6488c..a8e5ac95cf1702 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -1438,10 +1438,10 @@ static const struct config_item_type gpio_sim_device_config_group_type = { static struct config_group * gpio_sim_config_make_device_group(struct config_group *group, const char *name) { - struct gpio_sim_device *dev __free(kfree) = NULL; int id; - dev = kzalloc(sizeof(*dev), GFP_KERNEL); + struct gpio_sim_device *dev __free(kfree) = kzalloc(sizeof(*dev), + GFP_KERNEL); if (!dev) return ERR_PTR(-ENOMEM); diff --git a/drivers/gpio/gpio-tangier.c b/drivers/gpio/gpio-tangier.c index 7ce3eddaed2572..1ce40b7673b114 100644 --- a/drivers/gpio/gpio-tangier.c +++ b/drivers/gpio/gpio-tangier.c @@ -205,7 +205,8 @@ static int tng_gpio_set_config(struct gpio_chip *chip, unsigned int offset, static void tng_irq_ack(struct irq_data *d) { - struct tng_gpio *priv = irq_data_get_irq_chip_data(d); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct tng_gpio *priv = gpiochip_get_data(gc); irq_hw_number_t gpio = irqd_to_hwirq(d); unsigned long flags; void __iomem *gisr; @@ -241,7 +242,8 @@ static void tng_irq_unmask_mask(struct tng_gpio *priv, u32 gpio, bool unmask) static void tng_irq_mask(struct irq_data *d) { - struct tng_gpio *priv = irq_data_get_irq_chip_data(d); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct tng_gpio *priv = gpiochip_get_data(gc); irq_hw_number_t gpio = irqd_to_hwirq(d); tng_irq_unmask_mask(priv, gpio, false); @@ -250,7 +252,8 @@ static void tng_irq_mask(struct irq_data *d) static void tng_irq_unmask(struct irq_data *d) { - struct tng_gpio *priv = irq_data_get_irq_chip_data(d); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct tng_gpio *priv = gpiochip_get_data(gc); irq_hw_number_t gpio = irqd_to_hwirq(d); gpiochip_enable_irq(&priv->chip, gpio); diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c index d87dd06db40d07..9130c691a2dd32 100644 --- a/drivers/gpio/gpio-tegra186.c +++ b/drivers/gpio/gpio-tegra186.c @@ -36,12 +36,6 @@ #define TEGRA186_GPIO_SCR_SEC_REN BIT(27) #define TEGRA186_GPIO_SCR_SEC_G1W BIT(9) #define TEGRA186_GPIO_SCR_SEC_G1R BIT(1) -#define TEGRA186_GPIO_FULL_ACCESS (TEGRA186_GPIO_SCR_SEC_WEN | \ - TEGRA186_GPIO_SCR_SEC_REN | \ - TEGRA186_GPIO_SCR_SEC_G1R | \ - TEGRA186_GPIO_SCR_SEC_G1W) -#define TEGRA186_GPIO_SCR_SEC_ENABLE (TEGRA186_GPIO_SCR_SEC_WEN | \ - TEGRA186_GPIO_SCR_SEC_REN) /* control registers */ #define TEGRA186_GPIO_ENABLE_CONFIG 0x00 @@ -177,10 +171,18 @@ static inline bool tegra186_gpio_is_accessible(struct tegra_gpio *gpio, unsigned value = __raw_readl(secure + TEGRA186_GPIO_SCR); - if ((value & TEGRA186_GPIO_SCR_SEC_ENABLE) == 0) - return true; + /* + * When SCR_SEC_[R|W]EN is unset, then we have full read/write access to all the + * registers for given GPIO pin. + * When SCR_SEC[R|W]EN is set, then there is need to further check the accompanying + * SCR_SEC_G1[R|W] bit to determine read/write access to all the registers for given + * GPIO pin. + */ - if ((value & TEGRA186_GPIO_FULL_ACCESS) == TEGRA186_GPIO_FULL_ACCESS) + if (((value & TEGRA186_GPIO_SCR_SEC_REN) == 0 || + ((value & TEGRA186_GPIO_SCR_SEC_REN) && (value & TEGRA186_GPIO_SCR_SEC_G1R))) && + ((value & TEGRA186_GPIO_SCR_SEC_WEN) == 0 || + ((value & TEGRA186_GPIO_SCR_SEC_WEN) && (value & TEGRA186_GPIO_SCR_SEC_G1W)))) return true; return false; diff --git a/drivers/gpio/gpio-tqmx86.c b/drivers/gpio/gpio-tqmx86.c index 3a28c1f273c396..f2e7e8754d95d6 100644 --- a/drivers/gpio/gpio-tqmx86.c +++ b/drivers/gpio/gpio-tqmx86.c @@ -6,6 +6,7 @@ * Vadim V.Vlasov */ +#include #include #include #include @@ -28,16 +29,25 @@ #define TQMX86_GPIIC 3 /* GPI Interrupt Configuration Register */ #define TQMX86_GPIIS 4 /* GPI Interrupt Status Register */ +#define TQMX86_GPII_NONE 0 #define TQMX86_GPII_FALLING BIT(0) #define TQMX86_GPII_RISING BIT(1) +/* Stored in irq_type as a trigger type, but not actually valid as a register + * value, so the name doesn't use "GPII" + */ +#define TQMX86_INT_BOTH (BIT(0) | BIT(1)) #define TQMX86_GPII_MASK (BIT(0) | BIT(1)) #define TQMX86_GPII_BITS 2 +/* Stored in irq_type with GPII bits */ +#define TQMX86_INT_UNMASKED BIT(2) struct tqmx86_gpio_data { struct gpio_chip chip; void __iomem *io_base; int irq; + /* Lock must be held for accessing output and irq_type fields */ raw_spinlock_t spinlock; + DECLARE_BITMAP(output, TQMX86_NGPIO); u8 irq_type[TQMX86_NGPI]; }; @@ -64,15 +74,10 @@ static void tqmx86_gpio_set(struct gpio_chip *chip, unsigned int offset, { struct tqmx86_gpio_data *gpio = gpiochip_get_data(chip); unsigned long flags; - u8 val; raw_spin_lock_irqsave(&gpio->spinlock, flags); - val = tqmx86_gpio_read(gpio, TQMX86_GPIOD); - if (value) - val |= BIT(offset); - else - val &= ~BIT(offset); - tqmx86_gpio_write(gpio, val, TQMX86_GPIOD); + __assign_bit(offset, gpio->output, value); + tqmx86_gpio_write(gpio, bitmap_get_value8(gpio->output, 0), TQMX86_GPIOD); raw_spin_unlock_irqrestore(&gpio->spinlock, flags); } @@ -107,21 +112,38 @@ static int tqmx86_gpio_get_direction(struct gpio_chip *chip, return GPIO_LINE_DIRECTION_OUT; } +static void tqmx86_gpio_irq_config(struct tqmx86_gpio_data *gpio, int offset) + __must_hold(&gpio->spinlock) +{ + u8 type = TQMX86_GPII_NONE, gpiic; + + if (gpio->irq_type[offset] & TQMX86_INT_UNMASKED) { + type = gpio->irq_type[offset] & TQMX86_GPII_MASK; + + if (type == TQMX86_INT_BOTH) + type = tqmx86_gpio_get(&gpio->chip, offset + TQMX86_NGPO) + ? TQMX86_GPII_FALLING + : TQMX86_GPII_RISING; + } + + gpiic = tqmx86_gpio_read(gpio, TQMX86_GPIIC); + gpiic &= ~(TQMX86_GPII_MASK << (offset * TQMX86_GPII_BITS)); + gpiic |= type << (offset * TQMX86_GPII_BITS); + tqmx86_gpio_write(gpio, gpiic, TQMX86_GPIIC); +} + static void tqmx86_gpio_irq_mask(struct irq_data *data) { unsigned int offset = (data->hwirq - TQMX86_NGPO); struct tqmx86_gpio_data *gpio = gpiochip_get_data( irq_data_get_irq_chip_data(data)); unsigned long flags; - u8 gpiic, mask; - - mask = TQMX86_GPII_MASK << (offset * TQMX86_GPII_BITS); raw_spin_lock_irqsave(&gpio->spinlock, flags); - gpiic = tqmx86_gpio_read(gpio, TQMX86_GPIIC); - gpiic &= ~mask; - tqmx86_gpio_write(gpio, gpiic, TQMX86_GPIIC); + gpio->irq_type[offset] &= ~TQMX86_INT_UNMASKED; + tqmx86_gpio_irq_config(gpio, offset); raw_spin_unlock_irqrestore(&gpio->spinlock, flags); + gpiochip_disable_irq(&gpio->chip, irqd_to_hwirq(data)); } @@ -131,16 +153,12 @@ static void tqmx86_gpio_irq_unmask(struct irq_data *data) struct tqmx86_gpio_data *gpio = gpiochip_get_data( irq_data_get_irq_chip_data(data)); unsigned long flags; - u8 gpiic, mask; - - mask = TQMX86_GPII_MASK << (offset * TQMX86_GPII_BITS); gpiochip_enable_irq(&gpio->chip, irqd_to_hwirq(data)); + raw_spin_lock_irqsave(&gpio->spinlock, flags); - gpiic = tqmx86_gpio_read(gpio, TQMX86_GPIIC); - gpiic &= ~mask; - gpiic |= gpio->irq_type[offset] << (offset * TQMX86_GPII_BITS); - tqmx86_gpio_write(gpio, gpiic, TQMX86_GPIIC); + gpio->irq_type[offset] |= TQMX86_INT_UNMASKED; + tqmx86_gpio_irq_config(gpio, offset); raw_spin_unlock_irqrestore(&gpio->spinlock, flags); } @@ -151,7 +169,7 @@ static int tqmx86_gpio_irq_set_type(struct irq_data *data, unsigned int type) unsigned int offset = (data->hwirq - TQMX86_NGPO); unsigned int edge_type = type & IRQF_TRIGGER_MASK; unsigned long flags; - u8 new_type, gpiic; + u8 new_type; switch (edge_type) { case IRQ_TYPE_EDGE_RISING: @@ -161,19 +179,16 @@ static int tqmx86_gpio_irq_set_type(struct irq_data *data, unsigned int type) new_type = TQMX86_GPII_FALLING; break; case IRQ_TYPE_EDGE_BOTH: - new_type = TQMX86_GPII_FALLING | TQMX86_GPII_RISING; + new_type = TQMX86_INT_BOTH; break; default: return -EINVAL; /* not supported */ } - gpio->irq_type[offset] = new_type; - raw_spin_lock_irqsave(&gpio->spinlock, flags); - gpiic = tqmx86_gpio_read(gpio, TQMX86_GPIIC); - gpiic &= ~((TQMX86_GPII_MASK) << (offset * TQMX86_GPII_BITS)); - gpiic |= new_type << (offset * TQMX86_GPII_BITS); - tqmx86_gpio_write(gpio, gpiic, TQMX86_GPIIC); + gpio->irq_type[offset] &= ~TQMX86_GPII_MASK; + gpio->irq_type[offset] |= new_type; + tqmx86_gpio_irq_config(gpio, offset); raw_spin_unlock_irqrestore(&gpio->spinlock, flags); return 0; @@ -184,8 +199,8 @@ static void tqmx86_gpio_irq_handler(struct irq_desc *desc) struct gpio_chip *chip = irq_desc_get_handler_data(desc); struct tqmx86_gpio_data *gpio = gpiochip_get_data(chip); struct irq_chip *irq_chip = irq_desc_get_chip(desc); - unsigned long irq_bits; - int i = 0; + unsigned long irq_bits, flags; + int i; u8 irq_status; chained_irq_enter(irq_chip, desc); @@ -194,6 +209,34 @@ static void tqmx86_gpio_irq_handler(struct irq_desc *desc) tqmx86_gpio_write(gpio, irq_status, TQMX86_GPIIS); irq_bits = irq_status; + + raw_spin_lock_irqsave(&gpio->spinlock, flags); + for_each_set_bit(i, &irq_bits, TQMX86_NGPI) { + /* + * Edge-both triggers are implemented by flipping the edge + * trigger after each interrupt, as the controller only supports + * either rising or falling edge triggers, but not both. + * + * Internally, the TQMx86 GPIO controller has separate status + * registers for rising and falling edge interrupts. GPIIC + * configures which bits from which register are visible in the + * interrupt status register GPIIS and defines what triggers the + * parent IRQ line. Writing to GPIIS always clears both rising + * and falling interrupt flags internally, regardless of the + * currently configured trigger. + * + * In consequence, we can cleanly implement the edge-both + * trigger in software by first clearing the interrupt and then + * setting the new trigger based on the current GPIO input in + * tqmx86_gpio_irq_config() - even if an edge arrives between + * reading the input and setting the trigger, we will have a new + * interrupt pending. + */ + if ((gpio->irq_type[i] & TQMX86_GPII_MASK) == TQMX86_INT_BOTH) + tqmx86_gpio_irq_config(gpio, i); + } + raw_spin_unlock_irqrestore(&gpio->spinlock, flags); + for_each_set_bit(i, &irq_bits, TQMX86_NGPI) generic_handle_domain_irq(gpio->chip.irq.domain, i + TQMX86_NGPO); @@ -277,6 +320,13 @@ static int tqmx86_gpio_probe(struct platform_device *pdev) tqmx86_gpio_write(gpio, (u8)~TQMX86_DIR_INPUT_MASK, TQMX86_GPIODD); + /* + * Reading the previous output state is not possible with TQMx86 hardware. + * Initialize all outputs to 0 to have a defined state that matches the + * shadow register. + */ + tqmx86_gpio_write(gpio, 0, TQMX86_GPIOD); + chip = &gpio->chip; chip->label = "gpio-tqmx86"; chip->owner = THIS_MODULE; diff --git a/drivers/gpio/gpio-wcove.c b/drivers/gpio/gpio-wcove.c index c18b6b47384f1b..94ca9d03c09494 100644 --- a/drivers/gpio/gpio-wcove.c +++ b/drivers/gpio/gpio-wcove.c @@ -104,7 +104,7 @@ static inline int to_reg(int gpio, enum ctrl_register type) unsigned int reg = type == CTRL_IN ? GPIO_IN_CTRL_BASE : GPIO_OUT_CTRL_BASE; if (gpio >= WCOVE_GPIO_NUM) - return -EOPNOTSUPP; + return -ENOTSUPP; return reg + gpio; } diff --git a/drivers/gpio/gpio-zynqmp-modepin.c b/drivers/gpio/gpio-zynqmp-modepin.c index a0d69387c1532d..2f3c9ebfa78d1d 100644 --- a/drivers/gpio/gpio-zynqmp-modepin.c +++ b/drivers/gpio/gpio-zynqmp-modepin.c @@ -146,6 +146,7 @@ static const struct of_device_id modepin_platform_id[] = { { .compatible = "xlnx,zynqmp-gpio-modepin", }, { } }; +MODULE_DEVICE_TABLE(of, modepin_platform_id); static struct platform_driver modepin_platform_driver = { .driver = { diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 51e41676de0b8d..b366b4ca4c40e9 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -128,7 +128,24 @@ static bool acpi_gpio_deferred_req_irqs_done; static int acpi_gpiochip_find(struct gpio_chip *gc, void *data) { - return device_match_acpi_handle(&gc->gpiodev->dev, data); + /* First check the actual GPIO device */ + if (device_match_acpi_handle(&gc->gpiodev->dev, data)) + return true; + + /* + * When the ACPI device is artificially split to the banks of GPIOs, + * where each of them is represented by a separate GPIO device, + * the firmware node of the physical device may not be shared among + * the banks as they may require different values for the same property, + * e.g., number of GPIOs in a certain bank. In such case the ACPI handle + * of a GPIO device is NULL and can not be used. Hence we have to check + * the parent device to be sure that there is no match before bailing + * out. + */ + if (gc->parent) + return device_match_acpi_handle(gc->parent, data); + + return false; } /** @@ -1655,6 +1672,40 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = { .ignore_wake = "SYNA1202:00@16", }, }, + { + /* + * On the Peaq C1010 2-in-1 INT33FC:00 pin 3 is connected to + * a "dolby" button. At the ACPI level an _AEI event-handler + * is connected which sets an ACPI variable to 1 on both + * edges. This variable can be polled + cleared to 0 using + * WMI. But since the variable is set on both edges the WMI + * interface is pretty useless even when polling. + * So instead the x86-android-tablets code instantiates + * a gpio-keys platform device for it. + * Ignore the _AEI handler for the pin, so that it is not busy. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "PEAQ"), + DMI_MATCH(DMI_PRODUCT_NAME, "PEAQ PMM C1010 MD99187"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_interrupt = "INT33FC:00@3", + }, + }, + { + /* + * Spurious wakeups from TP_ATTN# pin + * Found in BIOS 0.35 + * https://gitlab.freedesktop.org/drm/amd/-/issues/3073 + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GPD"), + DMI_MATCH(DMI_PRODUCT_NAME, "G1619-04"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_wake = "PNP0C50:00@8", + }, + }, {} /* Terminating entry */ }; diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index e39d344feb2899..545998e9f6ad21 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -21,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -130,6 +132,10 @@ struct linehandle_state { GPIOHANDLE_REQUEST_OPEN_DRAIN | \ GPIOHANDLE_REQUEST_OPEN_SOURCE) +#define GPIOHANDLE_REQUEST_DIRECTION_FLAGS \ + (GPIOHANDLE_REQUEST_INPUT | \ + GPIOHANDLE_REQUEST_OUTPUT) + static int linehandle_validate_flags(u32 flags) { /* Return an error if an unknown flag is set */ @@ -210,21 +216,21 @@ static long linehandle_set_config(struct linehandle_state *lh, if (ret) return ret; + /* Lines must be reconfigured explicitly as input or output. */ + if (!(lflags & GPIOHANDLE_REQUEST_DIRECTION_FLAGS)) + return -EINVAL; + for (i = 0; i < lh->num_descs; i++) { desc = lh->descs[i]; - linehandle_flags_to_desc_flags(gcnf.flags, &desc->flags); + linehandle_flags_to_desc_flags(lflags, &desc->flags); - /* - * Lines have to be requested explicitly for input - * or output, else the line will be treated "as is". - */ if (lflags & GPIOHANDLE_REQUEST_OUTPUT) { int val = !!gcnf.default_values[i]; ret = gpiod_direction_output(desc, val); if (ret) return ret; - } else if (lflags & GPIOHANDLE_REQUEST_INPUT) { + } else { ret = gpiod_direction_input(desc); if (ret) return ret; @@ -461,6 +467,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip) /** * struct line - contains the state of a requested line + * @node: to store the object in supinfo_tree if supplemental * @desc: the GPIO descriptor for this line. * @req: the corresponding line request * @irq: the interrupt triggered in response to events on this GPIO @@ -473,6 +480,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip) * @line_seqno: the seqno for the current edge event in the sequence of * events for this line. * @work: the worker that implements software debouncing + * @debounce_period_us: the debounce period in microseconds * @sw_debounced: flag indicating if the software debouncer is active * @level: the current debounced physical level of the line * @hdesc: the Hardware Timestamp Engine (HTE) descriptor @@ -481,6 +489,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip) * @last_seqno: the last sequence number before debounce period expires */ struct line { + struct rb_node node; struct gpio_desc *desc; /* * -- edge detector specific fields -- @@ -514,6 +523,15 @@ struct line { * -- debouncer specific fields -- */ struct delayed_work work; + /* + * debounce_period_us is accessed by debounce_irq_handler() and + * process_hw_ts() which are disabled when modified by + * debounce_setup(), edge_detector_setup() or edge_detector_stop() + * or can live with a stale version when updated by + * edge_detector_update(). + * The modifying functions are themselves mutually exclusive. + */ + unsigned int debounce_period_us; /* * sw_debounce is accessed by linereq_set_config(), which is the * only setter, and linereq_get_values(), which can live with a @@ -546,6 +564,17 @@ struct line { #endif /* CONFIG_HTE */ }; +/* + * a rbtree of the struct lines containing supplemental info. + * Used to populate gpio_v2_line_info with cdev specific fields not contained + * in the struct gpio_desc. + * A line is determined to contain supplemental information by + * line_has_supinfo(). + */ +static struct rb_root supinfo_tree = RB_ROOT; +/* covers supinfo_tree */ +static DEFINE_SPINLOCK(supinfo_lock); + /** * struct linereq - contains the state of a userspace line request * @gdev: the GPIO device the line request pertains to @@ -559,7 +588,8 @@ struct line { * this line request. Note that this is not used when @num_lines is 1, as * the line_seqno is then the same and is cheaper to calculate. * @config_mutex: mutex for serializing ioctl() calls to ensure consistency - * of configuration, particularly multi-step accesses to desc flags. + * of configuration, particularly multi-step accesses to desc flags and + * changes to supinfo status. * @lines: the lines held by this line request, with @num_lines elements. */ struct linereq { @@ -575,6 +605,103 @@ struct linereq { struct line lines[]; }; +static void supinfo_insert(struct line *line) +{ + struct rb_node **new = &(supinfo_tree.rb_node), *parent = NULL; + struct line *entry; + + guard(spinlock)(&supinfo_lock); + + while (*new) { + entry = container_of(*new, struct line, node); + + parent = *new; + if (line->desc < entry->desc) { + new = &((*new)->rb_left); + } else if (line->desc > entry->desc) { + new = &((*new)->rb_right); + } else { + /* this should never happen */ + WARN(1, "duplicate line inserted"); + return; + } + } + + rb_link_node(&line->node, parent, new); + rb_insert_color(&line->node, &supinfo_tree); +} + +static void supinfo_erase(struct line *line) +{ + guard(spinlock)(&supinfo_lock); + + rb_erase(&line->node, &supinfo_tree); +} + +static struct line *supinfo_find(struct gpio_desc *desc) +{ + struct rb_node *node = supinfo_tree.rb_node; + struct line *line; + + while (node) { + line = container_of(node, struct line, node); + if (desc < line->desc) + node = node->rb_left; + else if (desc > line->desc) + node = node->rb_right; + else + return line; + } + return NULL; +} + +static void supinfo_to_lineinfo(struct gpio_desc *desc, + struct gpio_v2_line_info *info) +{ + struct gpio_v2_line_attribute *attr; + struct line *line; + + guard(spinlock)(&supinfo_lock); + + line = supinfo_find(desc); + if (!line) + return; + + attr = &info->attrs[info->num_attrs]; + attr->id = GPIO_V2_LINE_ATTR_ID_DEBOUNCE; + attr->debounce_period_us = READ_ONCE(line->debounce_period_us); + info->num_attrs++; +} + +static inline bool line_has_supinfo(struct line *line) +{ + return READ_ONCE(line->debounce_period_us); +} + +/* + * Checks line_has_supinfo() before and after the change to avoid unnecessary + * supinfo_tree access. + * Called indirectly by linereq_create() or linereq_set_config() so line + * is already protected from concurrent changes. + */ +static void line_set_debounce_period(struct line *line, + unsigned int debounce_period_us) +{ + bool was_suppl = line_has_supinfo(line); + + WRITE_ONCE(line->debounce_period_us, debounce_period_us); + + /* if supinfo status is unchanged then we're done */ + if (line_has_supinfo(line) == was_suppl) + return; + + /* supinfo status has changed, so update the tree */ + if (was_suppl) + supinfo_erase(line); + else + supinfo_insert(line); +} + #define GPIO_V2_LINE_BIAS_FLAGS \ (GPIO_V2_LINE_FLAG_BIAS_PULL_UP | \ GPIO_V2_LINE_FLAG_BIAS_PULL_DOWN | \ @@ -655,6 +782,25 @@ static u32 line_event_id(int level) GPIO_V2_LINE_EVENT_FALLING_EDGE; } +static inline char *make_irq_label(const char *orig) +{ + char *new; + + if (!orig) + return NULL; + + new = kstrdup_and_replace(orig, '/', ':', GFP_KERNEL); + if (!new) + return ERR_PTR(-ENOMEM); + + return new; +} + +static inline void free_irq_label(const char *label) +{ + kfree(label); +} + #ifdef CONFIG_HTE static enum hte_return process_hw_ts_thread(void *p) @@ -723,7 +869,7 @@ static enum hte_return process_hw_ts(struct hte_ts_data *ts, void *p) line->total_discard_seq++; line->last_seqno = ts->seq; mod_delayed_work(system_wq, &line->work, - usecs_to_jiffies(READ_ONCE(line->desc->debounce_period_us))); + usecs_to_jiffies(READ_ONCE(line->debounce_period_us))); } else { if (unlikely(ts->seq < line->line_seqno)) return HTE_CB_HANDLED; @@ -864,7 +1010,7 @@ static irqreturn_t debounce_irq_handler(int irq, void *p) struct line *line = p; mod_delayed_work(system_wq, &line->work, - usecs_to_jiffies(READ_ONCE(line->desc->debounce_period_us))); + usecs_to_jiffies(READ_ONCE(line->debounce_period_us))); return IRQ_HANDLED; } @@ -942,11 +1088,12 @@ static int debounce_setup(struct line *line, unsigned int debounce_period_us) { unsigned long irqflags; int ret, level, irq; + char *label; /* try hardware */ ret = gpiod_set_debounce(line->desc, debounce_period_us); if (!ret) { - WRITE_ONCE(line->desc->debounce_period_us, debounce_period_us); + line_set_debounce_period(line, debounce_period_us); return ret; } if (ret != -ENOTSUPP) @@ -964,11 +1111,17 @@ static int debounce_setup(struct line *line, unsigned int debounce_period_us) if (irq < 0) return -ENXIO; + label = make_irq_label(line->req->label); + if (IS_ERR(label)) + return -ENOMEM; + irqflags = IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING; ret = request_irq(irq, debounce_irq_handler, irqflags, - line->req->label, line); - if (ret) + label, line); + if (ret) { + free_irq_label(label); return ret; + } line->irq = irq; } else { ret = hte_edge_setup(line, GPIO_V2_LINE_FLAG_EDGE_BOTH); @@ -1013,7 +1166,7 @@ static u32 gpio_v2_line_config_debounce_period(struct gpio_v2_line_config *lc, static void edge_detector_stop(struct line *line) { if (line->irq) { - free_irq(line->irq, line); + free_irq_label(free_irq(line->irq, line)); line->irq = 0; } @@ -1025,8 +1178,7 @@ static void edge_detector_stop(struct line *line) cancel_delayed_work_sync(&line->work); WRITE_ONCE(line->sw_debounced, 0); WRITE_ONCE(line->edflags, 0); - if (line->desc) - WRITE_ONCE(line->desc->debounce_period_us, 0); + line_set_debounce_period(line, 0); /* do not change line->level - see comment in debounced_value() */ } @@ -1038,6 +1190,7 @@ static int edge_detector_setup(struct line *line, unsigned long irqflags = 0; u64 eflags; int irq, ret; + char *label; eflags = edflags & GPIO_V2_LINE_EDGE_FLAGS; if (eflags && !kfifo_initialized(&line->req->events)) { @@ -1051,7 +1204,7 @@ static int edge_detector_setup(struct line *line, ret = debounce_setup(line, debounce_period_us); if (ret) return ret; - WRITE_ONCE(line->desc->debounce_period_us, debounce_period_us); + line_set_debounce_period(line, debounce_period_us); } /* detection disabled or sw debouncer will provide edge detection */ @@ -1074,11 +1227,17 @@ static int edge_detector_setup(struct line *line, IRQF_TRIGGER_RISING : IRQF_TRIGGER_FALLING; irqflags |= IRQF_ONESHOT; + label = make_irq_label(line->req->label); + if (IS_ERR(label)) + return PTR_ERR(label); + /* Request a thread to read the events */ ret = request_threaded_irq(irq, edge_irq_handler, edge_irq_thread, - irqflags, line->req->label, line); - if (ret) + irqflags, label, line); + if (ret) { + free_irq_label(label); return ret; + } line->irq = irq; return 0; @@ -1088,17 +1247,31 @@ static int edge_detector_update(struct line *line, struct gpio_v2_line_config *lc, unsigned int line_idx, u64 edflags) { + u64 eflags; + int ret; u64 active_edflags = READ_ONCE(line->edflags); unsigned int debounce_period_us = gpio_v2_line_config_debounce_period(lc, line_idx); if ((active_edflags == edflags) && - (READ_ONCE(line->desc->debounce_period_us) == debounce_period_us)) + (READ_ONCE(line->debounce_period_us) == debounce_period_us)) return 0; /* sw debounced and still will be...*/ if (debounce_period_us && READ_ONCE(line->sw_debounced)) { - WRITE_ONCE(line->desc->debounce_period_us, debounce_period_us); + line_set_debounce_period(line, debounce_period_us); + /* + * ensure event fifo is initialised if edge detection + * is now enabled. + */ + eflags = edflags & GPIO_V2_LINE_EDGE_FLAGS; + if (eflags && !kfifo_initialized(&line->req->events)) { + ret = kfifo_alloc(&line->req->events, + line->req->event_buffer_size, + GFP_KERNEL); + if (ret) + return ret; + } return 0; } @@ -1392,12 +1565,14 @@ static long linereq_set_config_unlocked(struct linereq *lr, line = &lr->lines[i]; desc = lr->lines[i].desc; flags = gpio_v2_line_config_flags(lc, i); - gpio_v2_line_config_flags_to_desc_flags(flags, &desc->flags); - edflags = flags & GPIO_V2_LINE_EDGE_DETECTOR_FLAGS; /* - * Lines have to be requested explicitly for input - * or output, else the line will be treated "as is". + * Lines not explicitly reconfigured as input or output + * are left unchanged. */ + if (!(flags & GPIO_V2_LINE_DIRECTION_FLAGS)) + continue; + gpio_v2_line_config_flags_to_desc_flags(flags, &desc->flags); + edflags = flags & GPIO_V2_LINE_EDGE_DETECTOR_FLAGS; if (flags & GPIO_V2_LINE_FLAG_OUTPUT) { int val = gpio_v2_line_config_output_value(lc, i); @@ -1405,7 +1580,7 @@ static long linereq_set_config_unlocked(struct linereq *lr, ret = gpiod_direction_output(desc, val); if (ret) return ret; - } else if (flags & GPIO_V2_LINE_FLAG_INPUT) { + } else { ret = gpiod_direction_input(desc); if (ret) return ret; @@ -1573,6 +1748,7 @@ static ssize_t linereq_read(struct file *file, char __user *buf, static void linereq_free(struct linereq *lr) { + struct line *line; unsigned int i; if (lr->device_unregistered_nb.notifier_call) @@ -1580,10 +1756,14 @@ static void linereq_free(struct linereq *lr) &lr->device_unregistered_nb); for (i = 0; i < lr->num_lines; i++) { - if (lr->lines[i].desc) { - edge_detector_stop(&lr->lines[i]); - gpiod_free(lr->lines[i].desc); - } + line = &lr->lines[i]; + if (!line->desc) + continue; + + edge_detector_stop(line); + if (line_has_supinfo(line)) + supinfo_erase(line); + gpiod_free(line->desc); } kfifo_free(&lr->events); kfree(lr->label); @@ -1943,7 +2123,7 @@ static void lineevent_free(struct lineevent_state *le) blocking_notifier_chain_unregister(&le->gdev->device_notifier, &le->device_unregistered_nb); if (le->irq) - free_irq(le->irq, le); + free_irq_label(free_irq(le->irq, le)); if (le->desc) gpiod_free(le->desc); kfree(le->label); @@ -2091,6 +2271,7 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) int fd; int ret; int irq, irqflags = 0; + char *label; if (copy_from_user(&eventreq, ip, sizeof(eventreq))) return -EFAULT; @@ -2175,15 +2356,23 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) if (ret) goto out_free_le; + label = make_irq_label(le->label); + if (IS_ERR(label)) { + ret = PTR_ERR(label); + goto out_free_le; + } + /* Request a thread to read the events */ ret = request_threaded_irq(irq, lineevent_irq_handler, lineevent_irq_thread, irqflags, - le->label, + label, le); - if (ret) + if (ret) { + free_irq_label(label); goto out_free_le; + } le->irq = irq; @@ -2274,8 +2463,6 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc, struct gpio_chip *gc = desc->gdev->chip; bool ok_for_pinctrl; unsigned long flags; - u32 debounce_period_us; - unsigned int num_attrs = 0; memset(info, 0, sizeof(*info)); info->offset = gpio_chip_hwgpio(desc); @@ -2342,14 +2529,6 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc, else if (test_bit(FLAG_EVENT_CLOCK_HTE, &desc->flags)) info->flags |= GPIO_V2_LINE_FLAG_EVENT_CLOCK_HTE; - debounce_period_us = READ_ONCE(desc->debounce_period_us); - if (debounce_period_us) { - info->attrs[num_attrs].id = GPIO_V2_LINE_ATTR_ID_DEBOUNCE; - info->attrs[num_attrs].debounce_period_us = debounce_period_us; - num_attrs++; - } - info->num_attrs = num_attrs; - spin_unlock_irqrestore(&gpio_lock, flags); } @@ -2456,6 +2635,7 @@ static int lineinfo_get(struct gpio_chardev_data *cdev, void __user *ip, return -EBUSY; } gpio_desc_to_lineinfo(desc, &lineinfo); + supinfo_to_lineinfo(desc, &lineinfo); if (copy_to_user(ip, &lineinfo, sizeof(lineinfo))) { if (watch) @@ -2482,10 +2662,7 @@ static int lineinfo_unwatch(struct gpio_chardev_data *cdev, void __user *ip) return 0; } -/* - * gpio_ioctl() - ioctl handler for the GPIO chardev - */ -static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +static long gpio_ioctl_unlocked(struct file *file, unsigned int cmd, unsigned long arg) { struct gpio_chardev_data *cdev = file->private_data; struct gpio_device *gdev = cdev->gdev; @@ -2522,6 +2699,17 @@ static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } } +/* + * gpio_ioctl() - ioctl handler for the GPIO chardev + */ +static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct gpio_chardev_data *cdev = file->private_data; + + return call_ioctl_locked(file, cmd, arg, cdev->gdev, + gpio_ioctl_unlocked); +} + #ifdef CONFIG_COMPAT static long gpio_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -2546,6 +2734,7 @@ static int lineinfo_changed_notify(struct notifier_block *nb, chg.event_type = action; chg.timestamp_ns = ktime_get_ns(); gpio_desc_to_lineinfo(desc, &chg.info); + supinfo_to_lineinfo(desc, &chg.info); ret = kfifo_in_spinlocked(&cdev->events, &chg, 1, &cdev->wait.lock); if (ret) @@ -2766,11 +2955,11 @@ static int gpio_chrdev_release(struct inode *inode, struct file *file) struct gpio_chardev_data *cdev = file->private_data; struct gpio_device *gdev = cdev->gdev; - bitmap_free(cdev->watched_lines); blocking_notifier_chain_unregister(&gdev->device_notifier, &cdev->device_unregistered_nb); blocking_notifier_chain_unregister(&gdev->line_state_notifier, &cdev->lineinfo_changed_nb); + bitmap_free(cdev->watched_lines); gpio_device_put(gdev); kfree(cdev); diff --git a/drivers/gpio/gpiolib-devres.c b/drivers/gpio/gpiolib-devres.c index fe9ce6b19f15c5..4987e62dcb3d15 100644 --- a/drivers/gpio/gpiolib-devres.c +++ b/drivers/gpio/gpiolib-devres.c @@ -158,7 +158,7 @@ struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, if (!dr) return ERR_PTR(-ENOMEM); - desc = fwnode_gpiod_get_index(fwnode, con_id, index, flags, label); + desc = gpiod_find_and_request(dev, fwnode, con_id, index, flags, label, false); if (IS_ERR(desc)) { devres_free(dr); return desc; diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 531faabead0f40..cec9e8f29bbdfe 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -192,6 +192,24 @@ static void of_gpio_try_fixup_polarity(const struct device_node *np, */ { "himax,hx8357", "gpios-reset", false }, { "himax,hx8369", "gpios-reset", false }, +#endif +#if IS_ENABLED(CONFIG_PCI_LANTIQ) + /* + * According to the PCI specification, the RST# pin is an + * active-low signal. However, most of the device trees that + * have been widely used for a long time incorrectly describe + * reset GPIO as active-high, and were also using wrong name + * for the property. + */ + { "lantiq,pci-xway", "gpio-reset", false }, +#endif +#if IS_ENABLED(CONFIG_TOUCHSCREEN_TSC2005) + /* + * DTS for Nokia N900 incorrectly specified "active high" + * polarity for the reset line, while the chip actually + * treats it as "active low". + */ + { "ti,tsc2005", "reset-gpios", false }, #endif }; unsigned int i; @@ -491,9 +509,9 @@ static struct gpio_desc *of_find_gpio_rename(struct device_node *np, { "reset", "reset-n-io", "marvell,nfc-uart" }, { "reset", "reset-n-io", "mrvl,nfc-uart" }, #endif -#if !IS_ENABLED(CONFIG_PCI_LANTIQ) +#if IS_ENABLED(CONFIG_PCI_LANTIQ) /* MIPS Lantiq PCI */ - { "reset", "gpios-reset", "lantiq,pci-xway" }, + { "reset", "gpio-reset", "lantiq,pci-xway" }, #endif /* @@ -512,6 +530,10 @@ static struct gpio_desc *of_find_gpio_rename(struct device_node *np, #if IS_ENABLED(CONFIG_SND_SOC_CS42L56) { "reset", "cirrus,gpio-nreset", "cirrus,cs42l56" }, #endif +#if IS_ENABLED(CONFIG_SND_SOC_MT2701_CS42448) + { "i2s1-in-sel-gpio1", NULL, "mediatek,mt2701-cs42448-machine" }, + { "i2s1-in-sel-gpio2", NULL, "mediatek,mt2701-cs42448-machine" }, +#endif #if IS_ENABLED(CONFIG_SND_SOC_TLV320AIC3X) { "reset", "gpio-reset", "ti,tlv320aic3x" }, { "reset", "gpio-reset", "ti,tlv320aic33" }, diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c index 50503a4525eb03..6c27312c627883 100644 --- a/drivers/gpio/gpiolib-sysfs.c +++ b/drivers/gpio/gpiolib-sysfs.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include #include @@ -474,14 +475,17 @@ static ssize_t export_store(const struct class *class, goto done; status = gpiod_set_transitory(desc, false); - if (!status) { - status = gpiod_export(desc, true); - if (status < 0) - gpiod_free(desc); - else - set_bit(FLAG_SYSFS, &desc->flags); + if (status) { + gpiod_free(desc); + goto done; } + status = gpiod_export(desc, true); + if (status < 0) + gpiod_free(desc); + else + set_bit(FLAG_SYSFS, &desc->flags); + done: if (status) pr_debug("%s: status %d\n", __func__, status); @@ -771,15 +775,15 @@ void gpiochip_sysfs_unregister(struct gpio_device *gdev) struct gpio_desc *desc; struct gpio_chip *chip = gdev->chip; - if (!gdev->mockdev) - return; + scoped_guard(mutex, &sysfs_lock) { + if (!gdev->mockdev) + return; - device_unregister(gdev->mockdev); + device_unregister(gdev->mockdev); - /* prevent further gpiod exports */ - mutex_lock(&sysfs_lock); - gdev->mockdev = NULL; - mutex_unlock(&sysfs_lock); + /* prevent further gpiod exports */ + gdev->mockdev = NULL; + } /* unregister gpiod class devices owned by sysfs */ for_each_gpio_desc_with_flag(chip, desc, FLAG_SYSFS) { @@ -814,7 +818,7 @@ static int __init gpiolib_sysfs_init(void) * gpiochip_sysfs_register() acquires a mutex. This is unsafe * and needs to be fixed. * - * Also it would be nice to use gpiochip_find() here so we + * Also it would be nice to use gpio_device_find() here so we * can keep gpio_chips local to gpiolib.c, but the yield of * gpio_lock prevents us from doing this. */ diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 40a0022ea71909..5c0016c77d2abe 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -164,7 +165,7 @@ struct gpio_desc *gpiochip_get_desc(struct gpio_chip *gc, if (hwnum >= gdev->ngpio) return ERR_PTR(-EINVAL); - return &gdev->descs[hwnum]; + return &gdev->descs[array_index_nospec(hwnum, gdev->ngpio)]; } EXPORT_SYMBOL_GPL(gpiochip_get_desc); @@ -894,11 +895,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, ret = gpiochip_irqchip_init_valid_mask(gc); if (ret) - goto err_remove_acpi_chip; + goto err_free_hogs; ret = gpiochip_irqchip_init_hw(gc); if (ret) - goto err_remove_acpi_chip; + goto err_remove_irqchip_mask; ret = gpiochip_add_irqchip(gc, lock_key, request_key); if (ret) @@ -923,13 +924,13 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, gpiochip_irqchip_remove(gc); err_remove_irqchip_mask: gpiochip_irqchip_free_valid_mask(gc); -err_remove_acpi_chip: +err_free_hogs: + gpiochip_free_hogs(gc); acpi_gpiochip_remove(gc); + gpiochip_remove_pin_ranges(gc); err_remove_of_chip: - gpiochip_free_hogs(gc); of_gpiochip_remove(gc); err_free_gpiochip_mask: - gpiochip_remove_pin_ranges(gc); gpiochip_free_valid_mask(gc); if (gdev->dev.release) { /* release() has been registered by gpiochip_setup_dev() */ @@ -1014,16 +1015,10 @@ void gpiochip_remove(struct gpio_chip *gc) } EXPORT_SYMBOL_GPL(gpiochip_remove); -/** - * gpiochip_find() - iterator for locating a specific gpio_chip - * @data: data to pass to match function - * @match: Callback function to check gpio_chip +/* + * FIXME: This will be removed soon. * - * Similar to bus_find_device. It returns a reference to a gpio_chip as - * determined by a user supplied @match callback. The callback should return - * 0 if the device doesn't match and non-zero if it does. If the callback is - * non-zero, this function will return to the caller and not iterate over any - * more gpio_chips. + * This function is depracated, don't use. */ struct gpio_chip *gpiochip_find(void *data, int (*match)(struct gpio_chip *gc, @@ -1031,21 +1026,62 @@ struct gpio_chip *gpiochip_find(void *data, { struct gpio_device *gdev; struct gpio_chip *gc = NULL; - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - list_for_each_entry(gdev, &gpio_devices, list) - if (gdev->chip && match(gdev->chip, data)) { - gc = gdev->chip; - break; - } - spin_unlock_irqrestore(&gpio_lock, flags); + gdev = gpio_device_find(data, match); + if (gdev) { + gc = gdev->chip; + gpio_device_put(gdev); + } return gc; } EXPORT_SYMBOL_GPL(gpiochip_find); +/** + * gpio_device_find() - find a specific GPIO device + * @data: data to pass to match function + * @match: Callback function to check gpio_chip + * + * Returns: + * New reference to struct gpio_device. + * + * Similar to bus_find_device(). It returns a reference to a gpio_device as + * determined by a user supplied @match callback. The callback should return + * 0 if the device doesn't match and non-zero if it does. If the callback + * returns non-zero, this function will return to the caller and not iterate + * over any more gpio_devices. + * + * The callback takes the GPIO chip structure as argument. During the execution + * of the callback function the chip is protected from being freed. TODO: This + * actually has yet to be implemented. + * + * If the function returns non-NULL, the returned reference must be freed by + * the caller using gpio_device_put(). + */ +struct gpio_device *gpio_device_find(void *data, + int (*match)(struct gpio_chip *gc, + void *data)) +{ + struct gpio_device *gdev; + + /* + * Not yet but in the future the spinlock below will become a mutex. + * Annotate this function before anyone tries to use it in interrupt + * context like it happened with gpiochip_find(). + */ + might_sleep(); + + guard(spinlock_irqsave)(&gpio_lock); + + list_for_each_entry(gdev, &gpio_devices, list) { + if (gdev->chip && match(gdev->chip, data)) + return gpio_device_get(gdev); + } + + return NULL; +} +EXPORT_SYMBOL_GPL(gpio_device_find); + static int gpiochip_match_name(struct gpio_chip *gc, void *data) { const char *name = data; @@ -1058,6 +1094,30 @@ static struct gpio_chip *find_chip_by_name(const char *name) return gpiochip_find((void *)name, gpiochip_match_name); } +/** + * gpio_device_get() - Increase the reference count of this GPIO device + * @gdev: GPIO device to increase the refcount for + * + * Returns: + * Pointer to @gdev. + */ +struct gpio_device *gpio_device_get(struct gpio_device *gdev) +{ + return to_gpio_device(get_device(&gdev->dev)); +} +EXPORT_SYMBOL_GPL(gpio_device_get); + +/** + * gpio_device_put() - Decrease the reference count of this GPIO device and + * possibly free all resources associated with it. + * @gdev: GPIO device to decrease the reference count for + */ +void gpio_device_put(struct gpio_device *gdev) +{ + put_device(&gdev->dev); +} +EXPORT_SYMBOL_GPL(gpio_device_put); + #ifdef CONFIG_GPIOLIB_IRQCHIP /* @@ -3962,13 +4022,13 @@ static struct gpio_desc *gpiod_find_by_fwnode(struct fwnode_handle *fwnode, return desc; } -static struct gpio_desc *gpiod_find_and_request(struct device *consumer, - struct fwnode_handle *fwnode, - const char *con_id, - unsigned int idx, - enum gpiod_flags flags, - const char *label, - bool platform_lookup_allowed) +struct gpio_desc *gpiod_find_and_request(struct device *consumer, + struct fwnode_handle *fwnode, + const char *con_id, + unsigned int idx, + enum gpiod_flags flags, + const char *label, + bool platform_lookup_allowed) { unsigned long lookupflags = GPIO_LOOKUP_FLAGS_DEFAULT; struct gpio_desc *desc; diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h index a0a67569300b98..9bbde38238d33a 100644 --- a/drivers/gpio/gpiolib.h +++ b/drivers/gpio/gpiolib.h @@ -86,16 +86,6 @@ static inline struct gpio_device *to_gpio_device(struct device *dev) return container_of(dev, struct gpio_device, dev); } -static inline struct gpio_device *gpio_device_get(struct gpio_device *gdev) -{ - return to_gpio_device(get_device(&gdev->dev)); -} - -static inline void gpio_device_put(struct gpio_device *gdev) -{ - put_device(&gdev->dev); -} - /* gpio suffixes used for ACPI and device tree lookup */ static __maybe_unused const char * const gpio_suffixes[] = { "gpios", "gpio" }; @@ -217,6 +207,14 @@ static inline int gpiod_request_user(struct gpio_desc *desc, const char *label) return ret; } +struct gpio_desc *gpiod_find_and_request(struct device *consumer, + struct fwnode_handle *fwnode, + const char *con_id, + unsigned int idx, + enum gpiod_flags flags, + const char *label, + bool platform_lookup_allowed); + int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id, unsigned long lflags, enum gpiod_flags dflags); int gpio_set_debounce_timeout(struct gpio_desc *desc, unsigned int debounce); diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 3caa020391c752..ec4abf9ff47b5f 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -198,7 +198,7 @@ config DRM_TTM config DRM_TTM_KUNIT_TEST tristate "KUnit tests for TTM" if !KUNIT_ALL_TESTS default n - depends on DRM && KUNIT && MMU + depends on DRM && KUNIT && MMU && (UML || COMPILE_TEST) select DRM_TTM select DRM_EXPORT_FOR_TESTS if m select DRM_KUNIT_TEST_HELPERS @@ -206,7 +206,8 @@ config DRM_TTM_KUNIT_TEST help Enables unit tests for TTM, a GPU memory manager subsystem used to manage memory buffers. This option is mostly useful for kernel - developers. + developers. It depends on (UML || COMPILE_TEST) since no other driver + which uses TTM can be loaded while running the tests. If in doubt, say "N". diff --git a/drivers/gpu/drm/amd/amdgpu/aldebaran.c b/drivers/gpu/drm/amd/amdgpu/aldebaran.c index 2b97b8a96fb494..7fea4f0f495a39 100644 --- a/drivers/gpu/drm/amd/amdgpu/aldebaran.c +++ b/drivers/gpu/drm/amd/amdgpu/aldebaran.c @@ -100,7 +100,7 @@ static int aldebaran_mode2_suspend_ip(struct amdgpu_device *adev) adev->ip_blocks[i].status.hw = false; } - return r; + return 0; } static int @@ -333,6 +333,7 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl, { struct list_head *reset_device_list = reset_context->reset_device_list; struct amdgpu_device *tmp_adev = NULL; + struct amdgpu_ras *con; int r; if (reset_device_list == NULL) @@ -358,7 +359,30 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl, */ amdgpu_register_gpu_instance(tmp_adev); - /* Resume RAS */ + /* Resume RAS, ecc_irq */ + con = amdgpu_ras_get_context(tmp_adev); + if (!amdgpu_sriov_vf(tmp_adev) && con) { + if (tmp_adev->sdma.ras && + tmp_adev->sdma.ras->ras_block.ras_late_init) { + r = tmp_adev->sdma.ras->ras_block.ras_late_init(tmp_adev, + &tmp_adev->sdma.ras->ras_block.ras_comm); + if (r) { + dev_err(tmp_adev->dev, "SDMA failed to execute ras_late_init! ret:%d\n", r); + goto end; + } + } + + if (tmp_adev->gfx.ras && + tmp_adev->gfx.ras->ras_block.ras_late_init) { + r = tmp_adev->gfx.ras->ras_block.ras_late_init(tmp_adev, + &tmp_adev->gfx.ras->ras_block.ras_comm); + if (r) { + dev_err(tmp_adev->dev, "GFX failed to execute ras_late_init! ret:%d\n", r); + goto end; + } + } + } + amdgpu_ras_resume(tmp_adev); /* Update PSP FW topology after reset */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index a79d53bdbe136a..d59e8536192ca9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1009,6 +1009,8 @@ struct amdgpu_device { bool in_s3; bool in_s4; bool in_s0ix; + /* indicate amdgpu suspension status */ + bool suspend_complete; enum pp_mp1_state mp1_state; struct amdgpu_doorbell_index doorbell_index; @@ -1367,6 +1369,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev, void amdgpu_driver_release_kms(struct drm_device *dev); int amdgpu_device_ip_suspend(struct amdgpu_device *adev); +int amdgpu_device_prepare(struct drm_device *dev); int amdgpu_device_suspend(struct drm_device *dev, bool fbcon); int amdgpu_device_resume(struct drm_device *dev, bool fbcon); u32 amdgpu_get_vblank_counter_kms(struct drm_crtc *crtc); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_afmt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_afmt.c index a4d65973bf7cf4..80771b1480fff5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_afmt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_afmt.c @@ -100,6 +100,7 @@ struct amdgpu_afmt_acr amdgpu_afmt_acr(uint32_t clock) amdgpu_afmt_calc_cts(clock, &res.cts_32khz, &res.n_32khz, 32000); amdgpu_afmt_calc_cts(clock, &res.cts_44_1khz, &res.n_44_1khz, 44100); amdgpu_afmt_calc_cts(clock, &res.cts_48khz, &res.n_48khz, 48000); + res.clock = clock; return res; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 25d5fda5b243e3..af6c6d89e63afb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -335,15 +335,15 @@ int amdgpu_amdkfd_alloc_gtt_mem(struct amdgpu_device *adev, size_t size, return r; } -void amdgpu_amdkfd_free_gtt_mem(struct amdgpu_device *adev, void *mem_obj) +void amdgpu_amdkfd_free_gtt_mem(struct amdgpu_device *adev, void **mem_obj) { - struct amdgpu_bo *bo = (struct amdgpu_bo *) mem_obj; + struct amdgpu_bo **bo = (struct amdgpu_bo **) mem_obj; - amdgpu_bo_reserve(bo, true); - amdgpu_bo_kunmap(bo); - amdgpu_bo_unpin(bo); - amdgpu_bo_unreserve(bo); - amdgpu_bo_unref(&(bo)); + amdgpu_bo_reserve(*bo, true); + amdgpu_bo_kunmap(*bo); + amdgpu_bo_unpin(*bo); + amdgpu_bo_unreserve(*bo); + amdgpu_bo_unref(bo); } int amdgpu_amdkfd_alloc_gws(struct amdgpu_device *adev, size_t size, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 2fe9860725bd94..3134e6ad81d1d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -221,7 +221,7 @@ int amdgpu_amdkfd_evict_userptr(struct mmu_interval_notifier *mni, int amdgpu_amdkfd_alloc_gtt_mem(struct amdgpu_device *adev, size_t size, void **mem_obj, uint64_t *gpu_addr, void **cpu_ptr, bool mqd_gfx9); -void amdgpu_amdkfd_free_gtt_mem(struct amdgpu_device *adev, void *mem_obj); +void amdgpu_amdkfd_free_gtt_mem(struct amdgpu_device *adev, void **mem_obj); int amdgpu_amdkfd_alloc_gws(struct amdgpu_device *adev, size_t size, void **mem_obj); void amdgpu_amdkfd_free_gws(struct amdgpu_device *adev, void *mem_obj); @@ -303,6 +303,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv); +int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_sync_memory( struct amdgpu_device *adev, struct kgd_mem *mem, bool intr); int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_mem *mem, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c index 469785d337911a..1ef758ac5076ef 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c @@ -90,7 +90,7 @@ struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f) return NULL; fence = container_of(f, struct amdgpu_amdkfd_fence, base); - if (fence && f->ops == &amdkfd_fence_ops) + if (f->ops == &amdkfd_fence_ops) return fence; return NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index e036011137aa22..a1f35510d53955 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -213,7 +213,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, (kfd_mem_limit.ttm_mem_used + ttm_mem_needed > kfd_mem_limit.max_ttm_mem_limit) || (adev && xcp_id >= 0 && adev->kfd.vram_used[xcp_id] + vram_needed > - vram_size - reserved_for_pt)) { + vram_size - reserved_for_pt - atomic64_read(&adev->vram_pin_size))) { ret = -ENOMEM; goto release; } @@ -407,6 +407,10 @@ static int amdgpu_amdkfd_bo_validate(struct amdgpu_bo *bo, uint32_t domain, "Called with userptr BO")) return -EINVAL; + /* bo has been pinned, not need validate it */ + if (bo->tbo.pin_count) + return 0; + amdgpu_bo_placement_from_domain(bo, domain); ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); @@ -733,7 +737,7 @@ kfd_mem_dmaunmap_sg_bo(struct kgd_mem *mem, enum dma_data_direction dir; if (unlikely(!ttm->sg)) { - pr_err("SG Table of BO is UNEXPECTEDLY NULL"); + pr_debug("SG Table of BO is NULL"); return; } @@ -1135,7 +1139,8 @@ static int reserve_bo_and_cond_vms(struct kgd_mem *mem, int ret; ctx->sync = &mem->sync; - drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT | + DRM_EXEC_IGNORE_DUPLICATES); drm_exec_until_all_locked(&ctx->exec) { ctx->n_vms = 0; list_for_each_entry(entry, &mem->attachments, list) { @@ -1201,8 +1206,6 @@ static void unmap_bo_from_gpuvm(struct kgd_mem *mem, amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update); amdgpu_sync_fence(sync, bo_va->last_pt_update); - - kfd_mem_dmaunmap_attachment(mem, entry); } static int update_gpuvm_pte(struct kgd_mem *mem, @@ -1257,6 +1260,7 @@ static int map_bo_to_gpuvm(struct kgd_mem *mem, update_gpuvm_pte_failed: unmap_bo_from_gpuvm(mem, entry, sync); + kfd_mem_dmaunmap_attachment(mem, entry); return ret; } @@ -1785,6 +1789,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( err_bo_create: amdgpu_amdkfd_unreserve_mem_limit(adev, aligned_size, flags, xcp_id); err_reserve_limit: + amdgpu_sync_free(&(*mem)->sync); mutex_destroy(&(*mem)->lock); if (gobj) drm_gem_object_put(gobj); @@ -1860,8 +1865,10 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( mem->va + bo_size * (1 + mem->aql_queue)); /* Remove from VM internal data structures */ - list_for_each_entry_safe(entry, tmp, &mem->attachments, list) + list_for_each_entry_safe(entry, tmp, &mem->attachments, list) { + kfd_mem_dmaunmap_attachment(mem, entry); kfd_mem_detach(entry); + } ret = unreserve_bo_and_vms(&ctx, false, false); @@ -2035,6 +2042,37 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( return ret; } +int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv) +{ + struct kfd_mem_attachment *entry; + struct amdgpu_vm *vm; + int ret; + + vm = drm_priv_to_vm(drm_priv); + + mutex_lock(&mem->lock); + + ret = amdgpu_bo_reserve(mem->bo, true); + if (ret) + goto out; + + list_for_each_entry(entry, &mem->attachments, list) { + if (entry->bo_va->base.vm != vm) + continue; + if (entry->bo_va->base.bo->tbo.ttm && + !entry->bo_va->base.bo->tbo.ttm->sg) + continue; + + kfd_mem_dmaunmap_attachment(mem, entry); + } + + amdgpu_bo_unreserve(mem->bo); +out: + mutex_unlock(&mem->lock); + + return ret; +} + int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv) { @@ -2597,7 +2635,7 @@ static int confirm_valid_user_pages_locked(struct amdkfd_process_info *process_i /* keep mem without hmm range at userptr_inval_list */ if (!mem->range) - continue; + continue; /* Only check mem with hmm range associated */ valid = amdgpu_ttm_tt_get_user_pages_done( @@ -2814,9 +2852,6 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) if (!attachment->is_mapped) continue; - if (attachment->bo_va->base.bo->tbo.pin_count) - continue; - kfd_mem_dmaunmap_attachment(mem, attachment); ret = update_gpuvm_pte(mem, attachment, &sync_obj); if (ret) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index dce9e7d5e4ec67..a14a54a734c128 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -1476,6 +1476,8 @@ int amdgpu_atombios_init_mc_reg_table(struct amdgpu_device *adev, (u32)le32_to_cpu(*((u32 *)reg_data + j)); j++; } else if ((reg_table->mc_reg_address[i].pre_reg_data & LOW_NIBBLE_MASK) == DATA_EQU_PREV) { + if (i == 0) + continue; reg_table->mc_reg_table_entry[num_ranges].mc_data[i] = reg_table->mc_reg_table_entry[num_ranges].mc_data[i - 1]; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index fb2681dd6b338c..6521d06c7e4e72 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -211,6 +211,7 @@ union igp_info { struct atom_integrated_system_info_v1_11 v11; struct atom_integrated_system_info_v1_12 v12; struct atom_integrated_system_info_v2_1 v21; + struct atom_integrated_system_info_v2_3 v23; }; union umc_info { @@ -359,6 +360,20 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev, if (vram_type) *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type); break; + case 3: + mem_channel_number = igp_info->v23.umachannelnumber; + if (!mem_channel_number) + mem_channel_number = 1; + mem_type = igp_info->v23.memorytype; + if (mem_type == LpDdr5MemType) + mem_channel_width = 32; + else + mem_channel_width = 64; + if (vram_width) + *vram_width = mem_channel_number * mem_channel_width; + if (vram_type) + *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type); + break; default: return -EINVAL; } @@ -384,7 +399,7 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev, mem_channel_number = vram_info->v30.channel_num; mem_channel_width = vram_info->v30.channel_width; if (vram_width) - *vram_width = mem_channel_number * (1 << mem_channel_width); + *vram_width = mem_channel_number * 16; break; default: return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index 38ccec913f0097..f3a09ecb76992b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -29,6 +29,7 @@ #include "amdgpu.h" #include "atom.h" +#include #include #include #include @@ -287,6 +288,10 @@ static bool amdgpu_atrm_get_bios(struct amdgpu_device *adev) if (adev->flags & AMD_IS_APU) return false; + /* ATRM is for on-platform devices only */ + if (dev_is_removable(&adev->pdev->dev)) + return false; + while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) { dhandle = ACPI_HANDLE(&pdev->dev); if (!dhandle) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index b6298e901cbd4f..9a53ca555e7088 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -183,6 +183,7 @@ int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id, } rcu_read_unlock(); + *result = NULL; return -ENOENT; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index b8280be6225d9f..c3d89088123dbd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -213,6 +213,9 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, struct amdgpu_firmware_info *ucode; id = fw_type_convert(cgs_device, type); + if (id >= AMDGPU_UCODE_ID_MAXIMUM) + return -EINVAL; + ucode = &adev->firmware.ucode[id]; if (ucode->fw == NULL) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index d93a8961274c6a..13c97ba7a820b4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -207,7 +207,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, } for (i = 0; i < p->nchunks; i++) { - struct drm_amdgpu_cs_chunk __user **chunk_ptr = NULL; + struct drm_amdgpu_cs_chunk __user *chunk_ptr = NULL; struct drm_amdgpu_cs_chunk user_chunk; uint32_t __user *cdata; @@ -263,6 +263,10 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, if (size < sizeof(struct drm_amdgpu_bo_list_in)) goto free_partial_kdata; + /* Only a single BO list is allowed to simplify handling. */ + if (p->bo_list) + goto free_partial_kdata; + ret = amdgpu_cs_p1_bo_handles(p, p->chunks[i].kdata); if (ret) goto free_partial_kdata; @@ -819,7 +823,7 @@ static int amdgpu_cs_bo_validate(void *param, struct amdgpu_bo *bo) p->bytes_moved += ctx.bytes_moved; if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && - amdgpu_bo_in_cpu_visible_vram(bo)) + amdgpu_res_cpu_visible(adev, bo->tbo.resource)) p->bytes_moved_vis += ctx.bytes_moved; if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) { @@ -1057,6 +1061,9 @@ static int amdgpu_cs_patch_ibs(struct amdgpu_cs_parser *p, r = amdgpu_ring_parse_cs(ring, p, job, ib); if (r) return r; + + if (ib->sa_bo) + ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo); } else { ib->ptr = (uint32_t *)kptr; r = amdgpu_ring_patch_cs_in_place(ring, p, job, ib); @@ -1093,6 +1100,21 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) unsigned int i; int r; + /* + * We can't use gang submit on with reserved VMIDs when the VM changes + * can't be invalidated by more than one engine at the same time. + */ + if (p->gang_size > 1 && !p->adev->vm_manager.concurrent_flush) { + for (i = 0; i < p->gang_size; ++i) { + struct drm_sched_entity *entity = p->entities[i]; + struct drm_gpu_scheduler *sched = entity->rq->sched; + struct amdgpu_ring *ring = to_amdgpu_ring(sched); + + if (amdgpu_vmid_uses_reserved(vm, ring->vm_hub)) + return -EINVAL; + } + } + r = amdgpu_vm_clear_freed(adev, vm, NULL); if (r) return r; @@ -1411,7 +1433,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) if (r == -ENOMEM) DRM_ERROR("Not enough memory for command submission!\n"); else if (r != -ERESTARTSYS && r != -EAGAIN) - DRM_ERROR("Failed to process the buffer list %d!\n", r); + DRM_DEBUG("Failed to process the buffer list %d!\n", r); goto error_fini; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 76549c2cffebe1..cf8804fa7e9716 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -684,16 +684,24 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data, switch (args->in.op) { case AMDGPU_CTX_OP_ALLOC_CTX: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_alloc(adev, fpriv, filp, priority, &id); args->out.alloc.ctx_id = id; break; case AMDGPU_CTX_OP_FREE_CTX: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_free(fpriv, id); break; case AMDGPU_CTX_OP_QUERY_STATE: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_query(adev, fpriv, id, &args->out); break; case AMDGPU_CTX_OP_QUERY_STATE2: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_query2(adev, fpriv, id, &args->out); break; case AMDGPU_CTX_OP_GET_STABLE_PSTATE: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index a4faea4fa0b592..1c2c9ff9d39df0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -638,6 +638,9 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf, if (size & 0x3 || *pos & 0x3) return -EINVAL; + if (!adev->didt_rreg) + return -EOPNOTSUPP; + r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); @@ -694,6 +697,9 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user if (size & 0x3 || *pos & 0x3) return -EINVAL; + if (!adev->didt_wreg) + return -EOPNOTSUPP; + r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); @@ -748,6 +754,9 @@ static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf, ssize_t result = 0; int r; + if (!adev->smc_rreg) + return -EOPNOTSUPP; + if (size & 0x3 || *pos & 0x3) return -EINVAL; @@ -804,6 +813,9 @@ static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user * ssize_t result = 0; int r; + if (!adev->smc_wreg) + return -EOPNOTSUPP; + if (size & 0x3 || *pos & 0x3) return -EINVAL; @@ -2040,12 +2052,13 @@ static ssize_t amdgpu_reset_dump_register_list_write(struct file *f, struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private; char reg_offset[11]; uint32_t *new = NULL, *tmp = NULL; - int ret, i = 0, len = 0; + unsigned int len = 0; + int ret, i = 0; do { memset(reg_offset, 0, 11); if (copy_from_user(reg_offset, buf + len, - min(10, ((int)size-len)))) { + min(10, (size-len)))) { ret = -EFAULT; goto error_free; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 2b8356699f235d..9c99d69b4b083e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include @@ -1217,6 +1218,7 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev) return true; fw_ver = *((uint32_t *)adev->pm.fw->data + 69); + release_firmware(adev->pm.fw); if (fw_ver < 0x00160e00) return true; } @@ -1547,6 +1549,7 @@ static void amdgpu_switcheroo_set_state(struct pci_dev *pdev, } else { pr_info("switched off\n"); dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; + amdgpu_device_prepare(dev); amdgpu_device_suspend(dev, true); amdgpu_device_cache_pci_state(pdev); /* Shut down the device */ @@ -1895,15 +1898,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) adev->firmware.gpu_info_fw = NULL; - if (adev->mman.discovery_bin) { - /* - * FIXME: The bounding box is still needed by Navi12, so - * temporarily read it from gpu_info firmware. Should be dropped - * when DAL no longer needs it. - */ - if (adev->asic_type != CHIP_NAVI12) - return 0; - } + if (adev->mman.discovery_bin) + return 0; switch (adev->asic_type) { default: @@ -2018,7 +2014,6 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) */ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) { - struct drm_device *dev = adev_to_drm(adev); struct pci_dev *parent; int i, r; bool total; @@ -2089,7 +2084,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) (amdgpu_is_atpx_hybrid() || amdgpu_has_atpx_dgpu_power_cntl()) && ((adev->flags & AMD_IS_APU) == 0) && - !pci_is_thunderbolt_attached(to_pci_dev(dev->dev))) + !dev_is_removable(&adev->pdev->dev)) adev->flags |= AMD_IS_PX; if (!(adev->flags & AMD_IS_APU)) { @@ -2103,6 +2098,8 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) adev->pm.pp_feature &= ~PP_GFXOFF_MASK; if (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID) adev->pm.pp_feature &= ~PP_OVERDRIVE_MASK; + if (!amdgpu_device_pcie_dynamic_switching_supported()) + adev->pm.pp_feature &= ~PP_PCIE_DPM_MASK; total = true; for (i = 0; i < adev->num_ip_blocks; i++) { @@ -3476,10 +3473,6 @@ static void amdgpu_device_set_mcbp(struct amdgpu_device *adev) adev->gfx.mcbp = true; else if (amdgpu_mcbp == 0) adev->gfx.mcbp = false; - else if ((adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 0, 0)) && - (adev->ip_versions[GC_HWIP][0] < IP_VERSION(10, 0, 0)) && - adev->gfx.num_gfx_rings) - adev->gfx.mcbp = true; if (amdgpu_sriov_vf(adev)) adev->gfx.mcbp = true; @@ -3568,6 +3561,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, mutex_init(&adev->grbm_idx_mutex); mutex_init(&adev->mn_lock); mutex_init(&adev->virt.vf_errors.lock); + mutex_init(&adev->virt.rlcg_reg_lock); hash_init(adev->mn_hash); mutex_init(&adev->psp.mutex); mutex_init(&adev->notifier_lock); @@ -3901,7 +3895,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, px = amdgpu_device_supports_px(ddev); - if (px || (!pci_is_thunderbolt_attached(adev->pdev) && + if (px || (!dev_is_removable(&adev->pdev->dev) && apple_gmux_detect(NULL, NULL))) vga_switcheroo_register_client(adev->pdev, &amdgpu_switcheroo_ops, px); @@ -4046,7 +4040,7 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev) px = amdgpu_device_supports_px(adev_to_drm(adev)); - if (px || (!pci_is_thunderbolt_attached(adev->pdev) && + if (px || (!dev_is_removable(&adev->pdev->dev) && apple_gmux_detect(NULL, NULL))) vga_switcheroo_unregister_client(adev->pdev); @@ -4102,6 +4096,43 @@ static int amdgpu_device_evict_resources(struct amdgpu_device *adev) /* * Suspend & resume. */ +/** + * amdgpu_device_prepare - prepare for device suspend + * + * @dev: drm dev pointer + * + * Prepare to put the hw in the suspend state (all asics). + * Returns 0 for success or an error on failure. + * Called at driver suspend. + */ +int amdgpu_device_prepare(struct drm_device *dev) +{ + struct amdgpu_device *adev = drm_to_adev(dev); + int i, r; + + if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) + return 0; + + /* Evict the majority of BOs before starting suspend sequence */ + r = amdgpu_device_evict_resources(adev); + if (r) + return r; + + flush_delayed_work(&adev->gfx.gfx_off_delay_work); + + for (i = 0; i < adev->num_ip_blocks; i++) { + if (!adev->ip_blocks[i].status.valid) + continue; + if (!adev->ip_blocks[i].version->funcs->prepare_suspend) + continue; + r = adev->ip_blocks[i].version->funcs->prepare_suspend((void *)adev); + if (r) + return r; + } + + return 0; +} + /** * amdgpu_device_suspend - initiate device suspend * @@ -4122,11 +4153,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) adev->in_suspend = true; - /* Evict the majority of BOs before grabbing the full access */ - r = amdgpu_device_evict_resources(adev); - if (r) - return r; - if (amdgpu_sriov_vf(adev)) { amdgpu_virt_fini_data_exchange(adev); r = amdgpu_virt_request_full_gpu(adev, false); @@ -4141,7 +4167,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true); cancel_delayed_work_sync(&adev->delayed_init_work); - flush_delayed_work(&adev->gfx.gfx_off_delay_work); amdgpu_ras_suspend(adev); @@ -4455,7 +4480,8 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) shadow = vmbo->shadow; /* No need to recover an evicted BO */ - if (shadow->tbo.resource->mem_type != TTM_PL_TT || + if (!shadow->tbo.resource || + shadow->tbo.resource->mem_type != TTM_PL_TT || shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET || shadow->parent->tbo.resource->mem_type != TTM_PL_VRAM) continue; @@ -4661,11 +4687,14 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev) dev_info(adev->dev, "GPU mode1 reset\n"); + /* Cache the state before bus master disable. The saved config space + * values are used in other cases like restore after mode-2 reset. + */ + amdgpu_device_cache_pci_state(adev->pdev); + /* disable BM */ pci_clear_master(adev->pdev); - amdgpu_device_cache_pci_state(adev->pdev); - if (amdgpu_dpm_is_mode1_reset_supported(adev)) { dev_info(adev->dev, "GPU smu mode1 reset\n"); ret = amdgpu_dpm_mode1_reset(adev); @@ -5183,7 +5212,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, * Flush RAM to disk so that after reboot * the user can read log and see why the system rebooted. */ - if (need_emergency_restart && amdgpu_ras_get_context(adev)->reboot) { + if (need_emergency_restart && amdgpu_ras_get_context(adev) && + amdgpu_ras_get_context(adev)->reboot) { DRM_WARN("Emergency reboot."); ksys_sync_helper(); @@ -5206,7 +5236,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, * to put adev in the 1st position. */ INIT_LIST_HEAD(&device_list); - if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1)) { + if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1) && hive) { list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) { list_add_tail(&tmp_adev->reset_list, &device_list); if (gpu_reset_for_dev_remove && adev->shutdown) @@ -5617,7 +5647,7 @@ int amdgpu_device_baco_exit(struct drm_device *dev) adev->nbio.funcs->enable_doorbell_interrupt) adev->nbio.funcs->enable_doorbell_interrupt(adev, true); - if (amdgpu_passthrough(adev) && + if (amdgpu_passthrough(adev) && adev->nbio.funcs && adev->nbio.funcs->clear_doorbell_interrupt) adev->nbio.funcs->clear_doorbell_interrupt(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 7d5e7ad28ba82a..b04d789bfd1005 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -93,6 +93,7 @@ MODULE_FIRMWARE(FIRMWARE_IP_DISCOVERY); #define mmRCC_CONFIG_MEMSIZE 0xde3 +#define mmMP0_SMN_C2PMSG_33 0x16061 #define mmMM_INDEX 0x0 #define mmMM_INDEX_HI 0x6 #define mmMM_DATA 0x1 @@ -231,8 +232,26 @@ static int amdgpu_discovery_read_binary_from_sysmem(struct amdgpu_device *adev, static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev, uint8_t *binary) { - uint64_t vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20; - int ret = 0; + uint64_t vram_size; + u32 msg; + int i, ret = 0; + + /* It can take up to a second for IFWI init to complete on some dGPUs, + * but generally it should be in the 60-100ms range. Normally this starts + * as soon as the device gets power so by the time the OS loads this has long + * completed. However, when a card is hotplugged via e.g., USB4, we need to + * wait for this to complete. Once the C2PMSG is updated, we can + * continue. + */ + if (dev_is_removable(&adev->pdev->dev)) { + for (i = 0; i < 1000; i++) { + msg = RREG32(mmMP0_SMN_C2PMSG_33); + if (msg & 0x80000000) + break; + msleep(1); + } + } + vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20; if (vram_size) { uint64_t pos = vram_size - DISCOVERY_TMR_OFFSET; @@ -1251,11 +1270,10 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev) * 0b10 : encode is disabled * 0b01 : decode is disabled */ - adev->vcn.vcn_config[adev->vcn.num_vcn_inst] = - ip->revision & 0xc0; - ip->revision &= ~0xc0; if (adev->vcn.num_vcn_inst < AMDGPU_MAX_VCN_INSTANCES) { + adev->vcn.vcn_config[adev->vcn.num_vcn_inst] = + ip->revision & 0xc0; adev->vcn.num_vcn_inst++; adev->vcn.inst_mask |= (1U << ip->instance_number); @@ -1266,6 +1284,7 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev) adev->vcn.num_vcn_inst + 1, AMDGPU_MAX_VCN_INSTANCES); } + ip->revision &= ~0xc0; } if (le16_to_cpu(ip->hw_id) == SDMA0_HWID || le16_to_cpu(ip->hw_id) == SDMA1_HWID || @@ -1531,7 +1550,7 @@ static int amdgpu_discovery_get_mall_info(struct amdgpu_device *adev) break; case 2: mall_size_per_umc = le32_to_cpu(mall_info->v2.mall_size_per_umc); - adev->gmc.mall_size = mall_size_per_umc * adev->gmc.num_umc; + adev->gmc.mall_size = (uint64_t)mall_size_per_umc * adev->gmc.num_umc; break; default: dev_err(adev->dev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 363e6a2cad8c20..5fbb9caa7415fd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -340,14 +340,11 @@ int amdgpu_display_crtc_set_config(struct drm_mode_set *set, adev->have_disp_power_ref = true; return ret; } - /* if we have no active crtcs, then drop the power ref - * we got before + /* if we have no active crtcs, then go to + * drop the power ref we got before */ - if (!active && adev->have_disp_power_ref) { - pm_runtime_put_autosuspend(dev->dev); + if (!active && adev->have_disp_power_ref) adev->have_disp_power_ref = false; - } - out: /* drop the power reference we got coming in here */ pm_runtime_put_autosuspend(dev->dev); @@ -912,8 +909,7 @@ static int check_tiling_flags_gfx6(struct amdgpu_framebuffer *afb) { u64 micro_tile_mode; - /* Zero swizzle mode means linear */ - if (AMDGPU_TILING_GET(afb->tiling_flags, SWIZZLE_MODE) == 0) + if (AMDGPU_TILING_GET(afb->tiling_flags, ARRAY_MODE) == 1) /* LINEAR_ALIGNED */ return 0; micro_tile_mode = AMDGPU_TILING_GET(afb->tiling_flags, MICRO_TILE_MODE); @@ -1037,6 +1033,30 @@ static int amdgpu_display_verify_sizes(struct amdgpu_framebuffer *rfb) block_width = 256 / format_info->cpp[i]; block_height = 1; block_size_log2 = 8; + } else if (AMD_FMT_MOD_GET(TILE_VERSION, modifier) >= AMD_FMT_MOD_TILE_VER_GFX12) { + int swizzle = AMD_FMT_MOD_GET(TILE, modifier); + + switch (swizzle) { + case AMD_FMT_MOD_TILE_GFX12_256B_2D: + block_size_log2 = 8; + break; + case AMD_FMT_MOD_TILE_GFX12_4K_2D: + block_size_log2 = 12; + break; + case AMD_FMT_MOD_TILE_GFX12_64K_2D: + block_size_log2 = 16; + break; + case AMD_FMT_MOD_TILE_GFX12_256K_2D: + block_size_log2 = 18; + break; + default: + drm_dbg_kms(rfb->base.dev, + "Gfx12 swizzle mode with unknown block size: %d\n", swizzle); + return -EINVAL; + } + + get_block_dimensions(block_size_log2, format_info->cpp[i], + &block_width, &block_height); } else { int swizzle = AMD_FMT_MOD_GET(TILE, modifier); @@ -1072,7 +1092,8 @@ static int amdgpu_display_verify_sizes(struct amdgpu_framebuffer *rfb) return ret; } - if (AMD_FMT_MOD_GET(DCC, modifier)) { + if (AMD_FMT_MOD_GET(TILE_VERSION, modifier) <= AMD_FMT_MOD_TILE_VER_GFX11 && + AMD_FMT_MOD_GET(DCC, modifier)) { if (AMD_FMT_MOD_GET(DCC_RETILE, modifier)) { block_size_log2 = get_dcc_block_size(modifier, false, false); get_block_dimensions(block_size_log2 + 8, format_info->cpp[0], diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h index 09f6727e7c73ae..4a8b33f55f6bc3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h @@ -357,8 +357,9 @@ int amdgpu_doorbell_init(struct amdgpu_device *adev); void amdgpu_doorbell_fini(struct amdgpu_device *adev); int amdgpu_doorbell_create_kernel_doorbells(struct amdgpu_device *adev); uint32_t amdgpu_doorbell_index_on_bar(struct amdgpu_device *adev, - struct amdgpu_bo *db_bo, - uint32_t doorbell_index); + struct amdgpu_bo *db_bo, + uint32_t doorbell_index, + uint32_t db_size); #define RDOORBELL32(index) amdgpu_mm_rdoorbell(adev, (index)) #define WDOORBELL32(index, v) amdgpu_mm_wdoorbell(adev, (index), (v)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c index 8eee5d783a92bd..3f3662e8b87103 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c @@ -113,20 +113,25 @@ void amdgpu_mm_wdoorbell64(struct amdgpu_device *adev, u32 index, u64 v) * * @adev: amdgpu_device pointer * @db_bo: doorbell object's bo - * @db_index: doorbell relative index in this doorbell object + * @doorbell_index: doorbell relative index in this doorbell object + * @db_size: doorbell size is in byte * * returns doorbell's absolute index in BAR */ uint32_t amdgpu_doorbell_index_on_bar(struct amdgpu_device *adev, - struct amdgpu_bo *db_bo, - uint32_t doorbell_index) + struct amdgpu_bo *db_bo, + uint32_t doorbell_index, + uint32_t db_size) { int db_bo_offset; db_bo_offset = amdgpu_bo_gpu_offset_no_check(db_bo); - /* doorbell index is 32 bit but doorbell's size is 64-bit, so *2 */ - return db_bo_offset / sizeof(u32) + doorbell_index * 2; + /* doorbell index is 32 bit but doorbell's size can be 32 bit + * or 64 bit, so *db_size(in byte)/4 for alignment. + */ + return db_bo_offset / sizeof(u32) + doorbell_index * + DIV_ROUND_UP(db_size, 4); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 81edf66dbea8bd..f9bc38d20ce3ee 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2195,6 +2195,8 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, pm_runtime_mark_last_busy(ddev->dev); pm_runtime_put_autosuspend(ddev->dev); + pci_wake_from_d3(pdev, TRUE); + /* * For runpm implemented via BACO, PMFW will handle the * timing for BACO in and out: @@ -2384,8 +2386,9 @@ static int amdgpu_pmops_prepare(struct device *dev) /* Return a positive number here so * DPM_FLAG_SMART_SUSPEND works properly */ - if (amdgpu_device_supports_boco(drm_dev)) - return pm_runtime_suspended(dev); + if (amdgpu_device_supports_boco(drm_dev) && + pm_runtime_suspended(dev)) + return 1; /* if we will not support s3 or s2i for the device * then skip suspend @@ -2394,7 +2397,7 @@ static int amdgpu_pmops_prepare(struct device *dev) !amdgpu_acpi_is_s3_active(adev)) return 1; - return 0; + return amdgpu_device_prepare(drm_dev); } static void amdgpu_pmops_complete(struct device *dev) @@ -2407,6 +2410,7 @@ static int amdgpu_pmops_suspend(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); + adev->suspend_complete = false; if (amdgpu_acpi_is_s0ix_active(adev)) adev->in_s0ix = true; else if (amdgpu_acpi_is_s3_active(adev)) @@ -2421,6 +2425,7 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); + adev->suspend_complete = true; if (amdgpu_acpi_should_gpu_reset(adev)) return amdgpu_asic_reset(adev); @@ -2594,6 +2599,9 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) if (amdgpu_device_supports_boco(drm_dev)) adev->mp1_state = PP_MP1_STATE_UNLOAD; + ret = amdgpu_device_prepare(drm_dev); + if (ret) + return ret; ret = amdgpu_device_suspend(drm_dev, false); if (ret) { adev->in_runpm = false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c index e71768661ca8d2..09a34c7258e226 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c @@ -179,7 +179,7 @@ static int __amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr, * Returns the number of bytes read/written; -errno on error. */ static int amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr, - u8 *eeprom_buf, u16 buf_size, bool read) + u8 *eeprom_buf, u32 buf_size, bool read) { const struct i2c_adapter_quirks *quirks = i2c_adap->quirks; u16 limit; @@ -225,7 +225,7 @@ static int amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr, int amdgpu_eeprom_read(struct i2c_adapter *i2c_adap, u32 eeprom_addr, u8 *eeprom_buf, - u16 bytes) + u32 bytes) { return amdgpu_eeprom_xfer(i2c_adap, eeprom_addr, eeprom_buf, bytes, true); @@ -233,7 +233,7 @@ int amdgpu_eeprom_read(struct i2c_adapter *i2c_adap, int amdgpu_eeprom_write(struct i2c_adapter *i2c_adap, u32 eeprom_addr, u8 *eeprom_buf, - u16 bytes) + u32 bytes) { return amdgpu_eeprom_xfer(i2c_adap, eeprom_addr, eeprom_buf, bytes, false); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h index 6935adb2be1f1c..8083b8253ef433 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h @@ -28,10 +28,10 @@ int amdgpu_eeprom_read(struct i2c_adapter *i2c_adap, u32 eeprom_addr, u8 *eeprom_buf, - u16 bytes); + u32 bytes); int amdgpu_eeprom_write(struct i2c_adapter *i2c_adap, u32 eeprom_addr, u8 *eeprom_buf, - u16 bytes); + u32 bytes); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c index 6038b5021b27be..792c059ff7b352 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c @@ -105,6 +105,10 @@ void amdgpu_show_fdinfo(struct drm_printer *p, struct drm_file *file) stats.requested_visible_vram/1024UL); drm_printf(p, "amd-requested-gtt:\t%llu KiB\n", stats.requested_gtt/1024UL); + drm_printf(p, "drm-shared-vram:\t%llu KiB\n", stats.vram_shared/1024UL); + drm_printf(p, "drm-shared-gtt:\t%llu KiB\n", stats.gtt_shared/1024UL); + drm_printf(p, "drm-shared-cpu:\t%llu KiB\n", stats.cpu_shared/1024UL); + for (hw_ip = 0; hw_ip < AMDGPU_HW_IP_NUM; ++hw_ip) { if (!usage[hw_ip]) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index 73b8cca35bab87..eace2c9d0c3624 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -34,6 +34,7 @@ #include #endif #include "amdgpu.h" +#include "amdgpu_reset.h" #include #include @@ -400,7 +401,10 @@ void amdgpu_gart_invalidate_tlb(struct amdgpu_device *adev) return; mb(); - amdgpu_device_flush_hdp(adev, NULL); + if (down_read_trylock(&adev->reset_domain->sem)) { + amdgpu_device_flush_hdp(adev, NULL); + up_read(&adev->reset_domain->sem); + } for_each_set_bit(i, adev->vmhubs_mask, AMDGPU_MAX_VMHUBS) amdgpu_gmc_flush_gpu_tlb(adev, 0, i, 0); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index ca4d2d430e28c8..a1b15d0d6c4893 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -962,6 +962,7 @@ static int amdgpu_debugfs_gem_info_show(struct seq_file *m, void *unused) list_for_each_entry(file, &dev->filelist, lhead) { struct task_struct *task; struct drm_gem_object *gobj; + struct pid *pid; int id; /* @@ -971,8 +972,9 @@ static int amdgpu_debugfs_gem_info_show(struct seq_file *m, void *unused) * Therefore, we need to protect this ->comm access using RCU. */ rcu_read_lock(); - task = pid_task(file->pid, PIDTYPE_TGID); - seq_printf(m, "pid %8d command %s:\n", pid_nr(file->pid), + pid = rcu_dereference(file->pid); + task = pid_task(pid, PIDTYPE_TGID); + seq_printf(m, "pid %8d command %s:\n", pid_nr(pid), task ? task->comm : ""); rcu_read_unlock(); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 2382921710ece7..e7b053898f9e90 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -384,9 +384,11 @@ int amdgpu_gfx_mqd_sw_init(struct amdgpu_device *adev, struct amdgpu_ring *ring = &kiq->ring; u32 domain = AMDGPU_GEM_DOMAIN_GTT; +#if !defined(CONFIG_ARM) && !defined(CONFIG_ARM64) /* Only enable on gfx10 and 11 for now to avoid changing behavior on older chips */ if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(10, 0, 0)) domain |= AMDGPU_GEM_DOMAIN_VRAM; +#endif /* create MQD for KIQ */ if (!adev->enable_mes_kiq && !ring->mqd_obj) { @@ -700,8 +702,15 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable) if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state) { - schedule_delayed_work(&adev->gfx.gfx_off_delay_work, + /* If going to s2idle, no need to wait */ + if (adev->in_s0ix) { + if (!amdgpu_dpm_set_powergating_by_smu(adev, + AMD_IP_BLOCK_TYPE_GFX, true)) + adev->gfx.gfx_off_state = true; + } else { + schedule_delayed_work(&adev->gfx.gfx_off_delay_work, delay); + } } } else { if (adev->gfx.gfx_off_req_count == 0) { @@ -784,8 +793,11 @@ int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *r int r; if (amdgpu_ras_is_supported(adev, ras_block->block)) { - if (!amdgpu_persistent_edc_harvesting_supported(adev)) - amdgpu_ras_reset_error_status(adev, AMDGPU_RAS_BLOCK__GFX); + if (!amdgpu_persistent_edc_harvesting_supported(adev)) { + r = amdgpu_ras_reset_error_status(adev, AMDGPU_RAS_BLOCK__GFX); + if (r) + return r; + } r = amdgpu_ras_block_late_init(adev, ras_block); if (r) @@ -929,7 +941,10 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg) pr_err("critical bug! too many kiq readers\n"); goto failed_unlock; } - amdgpu_ring_alloc(ring, 32); + r = amdgpu_ring_alloc(ring, 32); + if (r) + goto failed_unlock; + amdgpu_ring_emit_rreg(ring, reg, reg_val_offs); r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT); if (r) @@ -995,7 +1010,10 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v) } spin_lock_irqsave(&kiq->ring_lock, flags); - amdgpu_ring_alloc(ring, 32); + r = amdgpu_ring_alloc(ring, 32); + if (r) + goto failed_unlock; + amdgpu_ring_emit_wreg(ring, reg, v); r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT); if (r) @@ -1031,6 +1049,7 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v) failed_undo: amdgpu_ring_undo(ring); +failed_unlock: spin_unlock_irqrestore(&kiq->ring_lock, flags); failed_kiq_write: dev_err(adev->dev, "failed to write reg:%x\n", reg); @@ -1175,7 +1194,8 @@ void amdgpu_gfx_cp_init_microcode(struct amdgpu_device *adev, fw_size = le32_to_cpu(cp_hdr_v2_0->data_size_bytes); break; default: - break; + dev_err(adev->dev, "Invalid ucode id %u\n", ucode_id); + return; } if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index d78bd97325434f..0b6a0e149f1c4c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -650,7 +650,6 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) struct amdgpu_gmc *gmc = &adev->gmc; uint32_t gc_ver = adev->ip_versions[GC_HWIP][0]; bool noretry_default = (gc_ver == IP_VERSION(9, 0, 1) || - gc_ver == IP_VERSION(9, 3, 0) || gc_ver == IP_VERSION(9, 4, 0) || gc_ver == IP_VERSION(9, 4, 1) || gc_ver == IP_VERSION(9, 4, 2) || @@ -876,21 +875,28 @@ int amdgpu_gmc_vram_checking(struct amdgpu_device *adev) * seconds, so here, we just pick up three parts for emulation. */ ret = memcmp(vram_ptr, cptr, 10); - if (ret) - return ret; + if (ret) { + ret = -EIO; + goto release_buffer; + } ret = memcmp(vram_ptr + (size / 2), cptr, 10); - if (ret) - return ret; + if (ret) { + ret = -EIO; + goto release_buffer; + } ret = memcmp(vram_ptr + size - 10, cptr, 10); - if (ret) - return ret; + if (ret) { + ret = -EIO; + goto release_buffer; + } +release_buffer: amdgpu_bo_free_kernel(&vram_bo, &vram_gpu, &vram_ptr); - return 0; + return ret; } static ssize_t current_memory_partition_show( diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c index 081267161d4018..57516a8c5db347 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c @@ -129,13 +129,25 @@ static const struct mmu_interval_notifier_ops amdgpu_hmm_hsa_ops = { */ int amdgpu_hmm_register(struct amdgpu_bo *bo, unsigned long addr) { + int r; + if (bo->kfd_bo) - return mmu_interval_notifier_insert(&bo->notifier, current->mm, + r = mmu_interval_notifier_insert(&bo->notifier, current->mm, addr, amdgpu_bo_size(bo), &amdgpu_hmm_hsa_ops); - return mmu_interval_notifier_insert(&bo->notifier, current->mm, addr, - amdgpu_bo_size(bo), - &amdgpu_hmm_gfx_ops); + else + r = mmu_interval_notifier_insert(&bo->notifier, current->mm, addr, + amdgpu_bo_size(bo), + &amdgpu_hmm_gfx_ops); + if (r) + /* + * Make sure amdgpu_hmm_unregister() doesn't call + * mmu_interval_notifier_remove() when the notifier isn't properly + * initialized. + */ + bo->notifier.mm = NULL; + + return r; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index ff1ea99292fbf0..69dfc699d78b07 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -409,7 +409,7 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring, if (r || !idle) goto error; - if (vm->reserved_vmid[vmhub] || (enforce_isolation && (vmhub == AMDGPU_GFXHUB(0)))) { + if (amdgpu_vmid_uses_reserved(vm, vmhub)) { r = amdgpu_vmid_grab_reserved(vm, ring, job, &id, fence); if (r || !id) goto error; @@ -459,6 +459,19 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring, return r; } +/* + * amdgpu_vmid_uses_reserved - check if a VM will use a reserved VMID + * @vm: the VM to check + * @vmhub: the VMHUB which will be used + * + * Returns: True if the VM will use a reserved VMID. + */ +bool amdgpu_vmid_uses_reserved(struct amdgpu_vm *vm, unsigned int vmhub) +{ + return vm->reserved_vmid[vmhub] || + (enforce_isolation && (vmhub == AMDGPU_GFXHUB(0))); +} + int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev, unsigned vmhub) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h index fa8c42c83d5d26..240fa675126029 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h @@ -78,6 +78,7 @@ void amdgpu_pasid_free_delayed(struct dma_resv *resv, bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev, struct amdgpu_vmid *id); +bool amdgpu_vmid_uses_reserved(struct amdgpu_vm *vm, unsigned int vmhub); int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev, unsigned vmhub); void amdgpu_vmid_free_reserved(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h index 6c6184f0dbc17e..508f02eb0cf8f9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h @@ -28,7 +28,7 @@ #define AMDGPU_IH_MAX_NUM_IVS 32 #define IH_RING_SIZE (256 * 1024) -#define IH_SW_RING_SIZE (8 * 1024) /* enough for 256 CAM entries */ +#define IH_SW_RING_SIZE (16 * 1024) /* enough for 512 CAM entries */ struct amdgpu_device; struct amdgpu_iv_entry; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index fa6d0adcec206c..5978edf7ea71e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -438,6 +438,14 @@ void amdgpu_irq_dispatch(struct amdgpu_device *adev, entry.ih = ih; entry.iv_entry = (const uint32_t *)&ih->ring[ring_index]; + + /* + * timestamp is not supported on some legacy SOCs (cik, cz, iceland, + * si and tonga), so initialize timestamp and timestamp_src to 0 + */ + entry.timestamp = 0; + entry.timestamp_src = 0; + amdgpu_ih_decode_iv(adev, &entry); trace_amdgpu_iv(ih - &adev->irq.ih, &entry); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 78476bc75b4e1d..99dd86337e8412 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -258,9 +258,8 @@ amdgpu_job_prepare_job(struct drm_sched_job *sched_job, struct dma_fence *fence = NULL; int r; - /* Ignore soft recovered fences here */ r = drm_sched_entity_error(s_entity); - if (r && r != -ENODATA) + if (r) goto error; if (!fence && job->gang_submit) @@ -300,12 +299,15 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job) dma_fence_set_error(finished, -ECANCELED); if (finished->error < 0) { - DRM_INFO("Skip scheduling IBs!\n"); + dev_dbg(adev->dev, "Skip scheduling IBs in ring(%s)", + ring->name); } else { r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, job, &fence); if (r) - DRM_ERROR("Error scheduling IBs (%d)\n", r); + dev_err(adev->dev, + "Error scheduling IBs (%d) in ring(%s)", r, + ring->name); } job->job_run_counter++; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index d30dc0b718c73e..5797055b1148f7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -43,6 +43,7 @@ #include "amdgpu_gem.h" #include "amdgpu_display.h" #include "amdgpu_ras.h" +#include "amdgpu_reset.h" #include "amd_pcie.h" void amdgpu_unregister_gpu_instance(struct amdgpu_device *adev) @@ -722,6 +723,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) ? -EFAULT : 0; } case AMDGPU_INFO_READ_MMR_REG: { + int ret = 0; unsigned int n, alloc_size; uint32_t *regs; unsigned int se_num = (info->read_mmr_reg.instance >> @@ -731,24 +733,37 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) AMDGPU_INFO_MMR_SH_INDEX_SHIFT) & AMDGPU_INFO_MMR_SH_INDEX_MASK; + if (!down_read_trylock(&adev->reset_domain->sem)) + return -ENOENT; + /* set full masks if the userspace set all bits * in the bitfields */ - if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) + if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) { se_num = 0xffffffff; - else if (se_num >= AMDGPU_GFX_MAX_SE) - return -EINVAL; - if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) + } else if (se_num >= AMDGPU_GFX_MAX_SE) { + ret = -EINVAL; + goto out; + } + + if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) { sh_num = 0xffffffff; - else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE) - return -EINVAL; + } else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE) { + ret = -EINVAL; + goto out; + } - if (info->read_mmr_reg.count > 128) - return -EINVAL; + if (info->read_mmr_reg.count > 128) { + ret = -EINVAL; + goto out; + } regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), GFP_KERNEL); - if (!regs) - return -ENOMEM; + if (!regs) { + ret = -ENOMEM; + goto out; + } + alloc_size = info->read_mmr_reg.count * sizeof(*regs); amdgpu_gfx_off_ctrl(adev, false); @@ -760,13 +775,17 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) info->read_mmr_reg.dword_offset + i); kfree(regs); amdgpu_gfx_off_ctrl(adev, true); - return -EFAULT; + ret = -EFAULT; + goto out; } } amdgpu_gfx_off_ctrl(adev, true); n = copy_to_user(out, regs, min(size, alloc_size)); kfree(regs); - return n ? -EFAULT : 0; + ret = (n ? -EFAULT : 0); +out: + up_read(&adev->reset_domain->sem); + return ret; } case AMDGPU_INFO_DEV_INFO: { struct drm_amdgpu_info_device *dev_info; @@ -1026,7 +1045,12 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) if (amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&ui32, &ui32_size)) { - return -EINVAL; + /* fall back to input power for backwards compat */ + if (amdgpu_dpm_read_sensor(adev, + AMDGPU_PP_SENSOR_GPU_INPUT_POWER, + (void *)&ui32, &ui32_size)) { + return -EINVAL; + } } ui32 >>= 8; break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index b6015157763af8..c5c55e132af21d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -556,8 +556,20 @@ static void amdgpu_mes_queue_init_mqd(struct amdgpu_device *adev, mqd_prop.hqd_queue_priority = p->hqd_queue_priority; mqd_prop.hqd_active = false; + if (p->queue_type == AMDGPU_RING_TYPE_GFX || + p->queue_type == AMDGPU_RING_TYPE_COMPUTE) { + mutex_lock(&adev->srbm_mutex); + amdgpu_gfx_select_me_pipe_q(adev, p->ring->me, p->ring->pipe, 0, 0, 0); + } + mqd_mgr->init_mqd(adev, q->mqd_cpu_ptr, &mqd_prop); + if (p->queue_type == AMDGPU_RING_TYPE_GFX || + p->queue_type == AMDGPU_RING_TYPE_COMPUTE) { + amdgpu_gfx_select_me_pipe_q(adev, 0, 0, 0, 0, 0); + mutex_unlock(&adev->srbm_mutex); + } + amdgpu_bo_unreserve(q->mqd_obj); } @@ -873,6 +885,11 @@ int amdgpu_mes_set_shader_debugger(struct amdgpu_device *adev, op_input.op = MES_MISC_OP_SET_SHADER_DEBUGGER; op_input.set_shader_debugger.process_context_addr = process_context_addr; op_input.set_shader_debugger.flags.u32all = flags; + + /* use amdgpu mes_flush_shader_debugger instead */ + if (op_input.set_shader_debugger.flags.process_ctx_flush) + return -EINVAL; + op_input.set_shader_debugger.spi_gdbg_per_vmid_cntl = spi_gdbg_per_vmid_cntl; memcpy(op_input.set_shader_debugger.tcp_watch_cntl, tcp_watch_cntl, sizeof(op_input.set_shader_debugger.tcp_watch_cntl)); @@ -892,6 +909,32 @@ int amdgpu_mes_set_shader_debugger(struct amdgpu_device *adev, return r; } +int amdgpu_mes_flush_shader_debugger(struct amdgpu_device *adev, + uint64_t process_context_addr) +{ + struct mes_misc_op_input op_input = {0}; + int r; + + if (!adev->mes.funcs->misc_op) { + DRM_ERROR("mes flush shader debugger is not supported!\n"); + return -EINVAL; + } + + op_input.op = MES_MISC_OP_SET_SHADER_DEBUGGER; + op_input.set_shader_debugger.process_context_addr = process_context_addr; + op_input.set_shader_debugger.flags.process_ctx_flush = true; + + amdgpu_mes_lock(&adev->mes); + + r = adev->mes.funcs->misc_op(&adev->mes, &op_input); + if (r) + DRM_ERROR("failed to set_shader_debugger\n"); + + amdgpu_mes_unlock(&adev->mes); + + return r; +} + static void amdgpu_mes_ring_to_queue_props(struct amdgpu_device *adev, struct amdgpu_ring *ring, @@ -993,9 +1036,13 @@ int amdgpu_mes_add_ring(struct amdgpu_device *adev, int gang_id, switch (queue_type) { case AMDGPU_RING_TYPE_GFX: ring->funcs = adev->gfx.gfx_ring[0].funcs; + ring->me = adev->gfx.gfx_ring[0].me; + ring->pipe = adev->gfx.gfx_ring[0].pipe; break; case AMDGPU_RING_TYPE_COMPUTE: ring->funcs = adev->gfx.compute_ring[0].funcs; + ring->me = adev->gfx.compute_ring[0].me; + ring->pipe = adev->gfx.compute_ring[0].pipe; break; case AMDGPU_RING_TYPE_SDMA: ring->funcs = adev->sdma.instance[0].ring.funcs; @@ -1051,6 +1098,7 @@ void amdgpu_mes_remove_ring(struct amdgpu_device *adev, return; amdgpu_mes_remove_hw_queue(adev, ring->hw_queue_id); + del_timer_sync(&ring->fence_drv.fallback_timer); amdgpu_ring_fini(ring); kfree(ring); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index a27b424ffe0056..c2c88b772361d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -291,9 +291,10 @@ struct mes_misc_op_input { uint64_t process_context_addr; union { struct { - uint64_t single_memop : 1; - uint64_t single_alu_op : 1; - uint64_t reserved: 30; + uint32_t single_memop : 1; + uint32_t single_alu_op : 1; + uint32_t reserved: 29; + uint32_t process_ctx_flush: 1; }; uint32_t u32all; } flags; @@ -369,7 +370,8 @@ int amdgpu_mes_set_shader_debugger(struct amdgpu_device *adev, const uint32_t *tcp_watch_cntl, uint32_t flags, bool trap_en); - +int amdgpu_mes_flush_shader_debugger(struct amdgpu_device *adev, + uint64_t process_context_addr); int amdgpu_mes_add_ring(struct amdgpu_device *adev, int gang_id, int queue_type, int idx, struct amdgpu_mes_ctx_data *ctx_data, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index ace837cfa0a6bc..4e9ae52ef9fdbf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -613,6 +613,8 @@ int amdgpu_bo_create(struct amdgpu_device *adev, else amdgpu_bo_placement_from_domain(bo, bp->domain); if (bp->type == ttm_bo_type_kernel) + bo->tbo.priority = 2; + else if (!(bp->flags & AMDGPU_GEM_CREATE_DISCARDABLE)) bo->tbo.priority = 1; if (!bp->destroy) @@ -625,8 +627,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev, return r; if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && - bo->tbo.resource->mem_type == TTM_PL_VRAM && - amdgpu_bo_in_cpu_visible_vram(bo)) + amdgpu_res_cpu_visible(adev, bo->tbo.resource)) amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, ctx.bytes_moved); else @@ -1250,7 +1251,7 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, * amdgpu_bo_move_notify - notification about a memory move * @bo: pointer to a buffer object * @evict: if this move is evicting the buffer from the graphics address space - * @new_mem: new information of the bufer object + * @new_mem: new resource for backing the BO * * Marks the corresponding &amdgpu_bo buffer object as invalid, also performs * bookkeeping. @@ -1261,8 +1262,8 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, struct ttm_resource *new_mem) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); - struct amdgpu_bo *abo; struct ttm_resource *old_mem = bo->resource; + struct amdgpu_bo *abo; if (!amdgpu_bo_is_amdgpu_bo(bo)) return; @@ -1273,44 +1274,50 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, amdgpu_bo_kunmap(abo); if (abo->tbo.base.dma_buf && !abo->tbo.base.import_attach && - bo->resource->mem_type != TTM_PL_SYSTEM) + old_mem && old_mem->mem_type != TTM_PL_SYSTEM) dma_buf_move_notify(abo->tbo.base.dma_buf); - /* remember the eviction */ - if (evict) - atomic64_inc(&adev->num_evictions); - - /* update statistics */ - if (!new_mem) - return; - /* move_notify is called before move happens */ - trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type); + trace_amdgpu_bo_move(abo, new_mem ? new_mem->mem_type : -1, + old_mem ? old_mem->mem_type : -1); } void amdgpu_bo_get_memory(struct amdgpu_bo *bo, struct amdgpu_mem_stats *stats) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + struct ttm_resource *res = bo->tbo.resource; uint64_t size = amdgpu_bo_size(bo); + struct drm_gem_object *obj; unsigned int domain; + bool shared; /* Abort if the BO doesn't currently have a backing store */ - if (!bo->tbo.resource) + if (!res) return; - domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); + obj = &bo->tbo.base; + shared = drm_gem_object_is_shared_for_memory_stats(obj); + + domain = amdgpu_mem_type_to_domain(res->mem_type); switch (domain) { case AMDGPU_GEM_DOMAIN_VRAM: stats->vram += size; - if (amdgpu_bo_in_cpu_visible_vram(bo)) + if (amdgpu_res_cpu_visible(adev, bo->tbo.resource)) stats->visible_vram += size; + if (shared) + stats->vram_shared += size; break; case AMDGPU_GEM_DOMAIN_GTT: stats->gtt += size; + if (shared) + stats->gtt_shared += size; break; case AMDGPU_GEM_DOMAIN_CPU: default: stats->cpu += size; + if (shared) + stats->cpu_shared += size; break; } @@ -1395,10 +1402,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) /* Remember that this BO was accessed by the CPU */ abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - if (bo->resource->mem_type != TTM_PL_VRAM) - return 0; - - if (amdgpu_bo_in_cpu_visible_vram(abo)) + if (amdgpu_res_cpu_visible(adev, bo->resource)) return 0; /* Can't move a pinned BO to visible VRAM */ @@ -1422,7 +1426,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) /* this should never happen */ if (bo->resource->mem_type == TTM_PL_VRAM && - !amdgpu_bo_in_cpu_visible_vram(abo)) + !amdgpu_res_cpu_visible(adev, bo->resource)) return VM_FAULT_SIGBUS; ttm_bo_move_to_lru_tail_unlocked(bo); @@ -1582,6 +1586,7 @@ uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev, */ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct dma_buf_attachment *attachment; struct dma_buf *dma_buf; const char *placement; @@ -1590,10 +1595,11 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) if (dma_resv_trylock(bo->tbo.base.resv)) { unsigned int domain; + domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); switch (domain) { case AMDGPU_GEM_DOMAIN_VRAM: - if (amdgpu_bo_in_cpu_visible_vram(bo)) + if (amdgpu_res_cpu_visible(adev, bo->tbo.resource)) placement = "VRAM VISIBLE"; else placement = "VRAM"; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index d28e21baef16ee..bc42ccbde659ac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -138,12 +138,18 @@ struct amdgpu_bo_vm { struct amdgpu_mem_stats { /* current VRAM usage, includes visible VRAM */ uint64_t vram; + /* current shared VRAM usage, includes visible VRAM */ + uint64_t vram_shared; /* current visible VRAM usage */ uint64_t visible_vram; /* current GTT usage */ uint64_t gtt; + /* current shared GTT usage */ + uint64_t gtt_shared; /* current system memory usage */ uint64_t cpu; + /* current shared system memory usage */ + uint64_t cpu_shared; /* sum of evicted buffers, includes visible VRAM */ uint64_t evicted_vram; /* sum of evicted buffers due to CPU access */ @@ -244,28 +250,6 @@ static inline u64 amdgpu_bo_mmap_offset(struct amdgpu_bo *bo) return drm_vma_node_offset_addr(&bo->tbo.base.vma_node); } -/** - * amdgpu_bo_in_cpu_visible_vram - check if BO is (partly) in visible VRAM - */ -static inline bool amdgpu_bo_in_cpu_visible_vram(struct amdgpu_bo *bo) -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - struct amdgpu_res_cursor cursor; - - if (!bo->tbo.resource || bo->tbo.resource->mem_type != TTM_PL_VRAM) - return false; - - amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor); - while (cursor.remaining) { - if (cursor.start < adev->gmc.visible_vram_size) - return true; - - amdgpu_res_next(&cursor, cursor.size); - } - - return false; -} - /** * amdgpu_bo_explicit_sync - return whether the bo is explicitly synced */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 429ef212c1f25b..a4f9015345ccb5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -1336,6 +1336,9 @@ static void psp_xgmi_reflect_topology_info(struct psp_context *psp, uint8_t dst_num_links = node_info.num_links; hive = amdgpu_get_xgmi_hive(psp->adev); + if (WARN_ON(!hive)) + return; + list_for_each_entry(mirror_adev, &hive->device_list, gmc.xgmi.head) { struct psp_xgmi_topology_info *mirror_top_info; int j; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c index 468a67b302d4c1..9aff579c6abf54 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c @@ -166,6 +166,9 @@ static ssize_t ta_if_load_debugfs_write(struct file *fp, const char *buf, size_t if (ret) return -EFAULT; + if (ta_bin_len > PSP_1_MEG) + return -EINVAL; + copy_pos += sizeof(uint32_t); ta_bin = kzalloc(ta_bin_len, GFP_KERNEL); @@ -334,7 +337,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size set_ta_context_funcs(psp, ta_type, &context); - if (!context->initialized) { + if (!context || !context->initialized) { dev_err(adev->dev, "TA is not initialized\n"); ret = -EINVAL; goto err_free_shared_buf; @@ -362,7 +365,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size } } - if (copy_to_user((char *)buf, context->mem_context.shared_buf, shared_buf_len)) + if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len)) ret = -EFAULT; err_free_shared_buf: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 163445baa4fc80..7cba98f8bbdca8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1025,6 +1025,9 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev, if (!obj) return -EINVAL; + if (!info || info->head.block == AMDGPU_RAS_BLOCK_COUNT) + return -EINVAL; + if (info->head.block == AMDGPU_RAS_BLOCK__UMC) { amdgpu_ras_get_ecc_info(adev, &err_data); } else { @@ -1373,7 +1376,8 @@ static void amdgpu_ras_sysfs_remove_bad_page_node(struct amdgpu_device *adev) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); - sysfs_remove_file_from_group(&adev->dev->kobj, + if (adev->dev->kobj.sd) + sysfs_remove_file_from_group(&adev->dev->kobj, &con->badpages_attr.attr, RAS_FS_NAME); } @@ -1390,7 +1394,8 @@ static int amdgpu_ras_sysfs_remove_feature_node(struct amdgpu_device *adev) .attrs = attrs, }; - sysfs_remove_group(&adev->dev->kobj, &group); + if (adev->dev->kobj.sd) + sysfs_remove_group(&adev->dev->kobj, &group); return 0; } @@ -1437,7 +1442,8 @@ int amdgpu_ras_sysfs_remove(struct amdgpu_device *adev, if (!obj || !obj->attr_inuse) return -EINVAL; - sysfs_remove_file_from_group(&adev->dev->kobj, + if (adev->dev->kobj.sd) + sysfs_remove_file_from_group(&adev->dev->kobj, &obj->sysfs_attr.attr, RAS_FS_NAME); obj->attr_inuse = 0; @@ -1774,12 +1780,15 @@ static void amdgpu_ras_interrupt_process_handler(struct work_struct *work) int amdgpu_ras_interrupt_dispatch(struct amdgpu_device *adev, struct ras_dispatch_if *info) { - struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head); - struct ras_ih_data *data = &obj->ih_data; + struct ras_manager *obj; + struct ras_ih_data *data; + obj = amdgpu_ras_find_obj(adev, &info->head); if (!obj) return -EINVAL; + data = &obj->ih_data; + if (data->inuse == 0) return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index 595d5e535aca63..9d82701d365bbe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -214,6 +214,12 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev, control->i2c_address = EEPROM_I2C_MADDR_0; return true; case IP_VERSION(13, 0, 0): + if (strnstr(atom_ctx->vbios_pn, "D707", + sizeof(atom_ctx->vbios_pn))) + control->i2c_address = EEPROM_I2C_MADDR_0; + else + control->i2c_address = EEPROM_I2C_MADDR_4; + return true; case IP_VERSION(13, 0, 6): case IP_VERSION(13, 0, 10): control->i2c_address = EEPROM_I2C_MADDR_4; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 80d6e132e4095d..f44b303ae287a7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -352,7 +352,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, ring->max_dw = max_dw; ring->hw_prio = hw_prio; - if (!ring->no_scheduler) { + if (!ring->no_scheduler && ring->funcs->type < AMDGPU_HW_IP_NUM) { hw_ip = ring->funcs->type; num_sched = &adev->gpu_sched[hw_ip][hw_prio].num_scheds; adev->gpu_sched[hw_ip][hw_prio].sched[(*num_sched)++] = @@ -469,8 +469,9 @@ static ssize_t amdgpu_debugfs_ring_read(struct file *f, char __user *buf, size_t size, loff_t *pos) { struct amdgpu_ring *ring = file_inode(f)->i_private; - int r, i; uint32_t value, result, early[3]; + loff_t i; + int r; if (*pos & 3 || size & 3) return -EINVAL; @@ -520,46 +521,58 @@ static ssize_t amdgpu_debugfs_mqd_read(struct file *f, char __user *buf, { struct amdgpu_ring *ring = file_inode(f)->i_private; volatile u32 *mqd; - int r; + u32 *kbuf; + int r, i; uint32_t value, result; if (*pos & 3 || size & 3) return -EINVAL; - result = 0; + kbuf = kmalloc(ring->mqd_size, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; r = amdgpu_bo_reserve(ring->mqd_obj, false); if (unlikely(r != 0)) - return r; + goto err_free; r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&mqd); - if (r) { - amdgpu_bo_unreserve(ring->mqd_obj); - return r; - } + if (r) + goto err_unreserve; + + /* + * Copy to local buffer to avoid put_user(), which might fault + * and acquire mmap_sem, under reservation_ww_class_mutex. + */ + for (i = 0; i < ring->mqd_size/sizeof(u32); i++) + kbuf[i] = mqd[i]; + amdgpu_bo_kunmap(ring->mqd_obj); + amdgpu_bo_unreserve(ring->mqd_obj); + + result = 0; while (size) { if (*pos >= ring->mqd_size) - goto done; + break; - value = mqd[*pos/4]; + value = kbuf[*pos/4]; r = put_user(value, (uint32_t *)buf); if (r) - goto done; + goto err_free; buf += 4; result += 4; size -= 4; *pos += 4; } -done: - amdgpu_bo_kunmap(ring->mqd_obj); - mqd = NULL; - amdgpu_bo_unreserve(ring->mqd_obj); - if (r) - return r; - + kfree(kbuf); return result; + +err_unreserve: + amdgpu_bo_unreserve(ring->mqd_obj); +err_free: + kfree(kbuf); + return r; } static const struct file_operations amdgpu_debugfs_mqd_fops = { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c index 8ed0e073656f88..41ebe690eeffa7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c @@ -135,6 +135,10 @@ static ssize_t amdgpu_securedisplay_debugfs_write(struct file *f, const char __u mutex_unlock(&psp->securedisplay_context.mutex); break; case 2: + if (size < 3 || phy_id >= TA_SECUREDISPLAY_MAX_PHY) { + dev_err(adev->dev, "Invalid input: %s\n", str); + return -EINVAL; + } mutex_lock(&psp->securedisplay_context.mutex); psp_prep_securedisplay_cmd_buf(psp, &securedisplay_cmd, TA_SECUREDISPLAY_COMMAND__SEND_ROI_CRC); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index dcd8c066bc1f50..1b013a44ca99af 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -191,7 +191,8 @@ static bool amdgpu_sync_test_fence(struct amdgpu_device *adev, /* Never sync to VM updates either. */ if (fence_owner == AMDGPU_FENCE_OWNER_VM && - owner != AMDGPU_FENCE_OWNER_UNDEFINED) + owner != AMDGPU_FENCE_OWNER_UNDEFINED && + owner != AMDGPU_FENCE_OWNER_KFD) return false; /* Ignore fences depending on the sync mode */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 4e51dce3aab5d6..8c3fb1562ffef9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -137,7 +137,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo, amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU); } else if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && !(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) && - amdgpu_bo_in_cpu_visible_vram(abo)) { + amdgpu_res_cpu_visible(adev, bo->resource)) { /* Try evicting to the CPU inaccessible part of VRAM * first, but only set GTT as busy placement, so this @@ -408,40 +408,55 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo, return r; } -/* - * amdgpu_mem_visible - Check that memory can be accessed by ttm_bo_move_memcpy +/** + * amdgpu_res_cpu_visible - Check that resource can be accessed by CPU + * @adev: amdgpu device + * @res: the resource to check * - * Called by amdgpu_bo_move() + * Returns: true if the full resource is CPU visible, false otherwise. */ -static bool amdgpu_mem_visible(struct amdgpu_device *adev, - struct ttm_resource *mem) +bool amdgpu_res_cpu_visible(struct amdgpu_device *adev, + struct ttm_resource *res) { - u64 mem_size = (u64)mem->size; struct amdgpu_res_cursor cursor; - u64 end; - if (mem->mem_type == TTM_PL_SYSTEM || - mem->mem_type == TTM_PL_TT) + if (!res) + return false; + + if (res->mem_type == TTM_PL_SYSTEM || res->mem_type == TTM_PL_TT || + res->mem_type == AMDGPU_PL_PREEMPT || res->mem_type == AMDGPU_PL_DOORBELL) return true; - if (mem->mem_type != TTM_PL_VRAM) + + if (res->mem_type != TTM_PL_VRAM) return false; - amdgpu_res_first(mem, 0, mem_size, &cursor); - end = cursor.start + cursor.size; + amdgpu_res_first(res, 0, res->size, &cursor); while (cursor.remaining) { + if ((cursor.start + cursor.size) > adev->gmc.visible_vram_size) + return false; amdgpu_res_next(&cursor, cursor.size); + } - if (!cursor.remaining) - break; + return true; +} - /* ttm_resource_ioremap only supports contiguous memory */ - if (end != cursor.start) - return false; +/* + * amdgpu_res_copyable - Check that memory can be accessed by ttm_bo_move_memcpy + * + * Called by amdgpu_bo_move() + */ +static bool amdgpu_res_copyable(struct amdgpu_device *adev, + struct ttm_resource *mem) +{ + if (!amdgpu_res_cpu_visible(adev, mem)) + return false; - end = cursor.start + cursor.size; - } + /* ttm_resource_ioremap only supports contiguous memory */ + if (mem->mem_type == TTM_PL_VRAM && + !(mem->placement & TTM_PL_FLAG_CONTIGUOUS)) + return false; - return end <= adev->gmc.visible_vram_size; + return true; } /* @@ -471,14 +486,16 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, if (!old_mem || (old_mem->mem_type == TTM_PL_SYSTEM && bo->ttm == NULL)) { + amdgpu_bo_move_notify(bo, evict, new_mem); ttm_bo_move_null(bo, new_mem); - goto out; + return 0; } if (old_mem->mem_type == TTM_PL_SYSTEM && (new_mem->mem_type == TTM_PL_TT || new_mem->mem_type == AMDGPU_PL_PREEMPT)) { + amdgpu_bo_move_notify(bo, evict, new_mem); ttm_bo_move_null(bo, new_mem); - goto out; + return 0; } if ((old_mem->mem_type == TTM_PL_TT || old_mem->mem_type == AMDGPU_PL_PREEMPT) && @@ -488,9 +505,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, return r; amdgpu_ttm_backend_unbind(bo->bdev, bo->ttm); + amdgpu_bo_move_notify(bo, evict, new_mem); ttm_resource_free(bo, &bo->resource); ttm_bo_assign_mem(bo, new_mem); - goto out; + return 0; } if (old_mem->mem_type == AMDGPU_PL_GDS || @@ -502,8 +520,9 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, new_mem->mem_type == AMDGPU_PL_OA || new_mem->mem_type == AMDGPU_PL_DOORBELL) { /* Nothing to save here */ + amdgpu_bo_move_notify(bo, evict, new_mem); ttm_bo_move_null(bo, new_mem); - goto out; + return 0; } if (bo->type == ttm_bo_type_device && @@ -515,27 +534,28 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; } - if (adev->mman.buffer_funcs_enabled) { - if (((old_mem->mem_type == TTM_PL_SYSTEM && - new_mem->mem_type == TTM_PL_VRAM) || - (old_mem->mem_type == TTM_PL_VRAM && - new_mem->mem_type == TTM_PL_SYSTEM))) { - hop->fpfn = 0; - hop->lpfn = 0; - hop->mem_type = TTM_PL_TT; - hop->flags = TTM_PL_FLAG_TEMPORARY; - return -EMULTIHOP; - } + if (adev->mman.buffer_funcs_enabled && + ((old_mem->mem_type == TTM_PL_SYSTEM && + new_mem->mem_type == TTM_PL_VRAM) || + (old_mem->mem_type == TTM_PL_VRAM && + new_mem->mem_type == TTM_PL_SYSTEM))) { + hop->fpfn = 0; + hop->lpfn = 0; + hop->mem_type = TTM_PL_TT; + hop->flags = TTM_PL_FLAG_TEMPORARY; + return -EMULTIHOP; + } + amdgpu_bo_move_notify(bo, evict, new_mem); + if (adev->mman.buffer_funcs_enabled) r = amdgpu_move_blit(bo, evict, new_mem, old_mem); - } else { + else r = -ENODEV; - } if (r) { /* Check that all memory is CPU accessible */ - if (!amdgpu_mem_visible(adev, old_mem) || - !amdgpu_mem_visible(adev, new_mem)) { + if (!amdgpu_res_copyable(adev, old_mem) || + !amdgpu_res_copyable(adev, new_mem)) { pr_err("Move buffer fallback to memcpy unavailable\n"); return r; } @@ -545,10 +565,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, return r; } -out: - /* update statistics */ + /* update statistics after the move */ + if (evict) + atomic64_inc(&adev->num_evictions); atomic64_add(bo->base.size, &adev->num_bytes_moved); - amdgpu_bo_move_notify(bo, evict, new_mem); return 0; } @@ -561,7 +581,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *mem) { struct amdgpu_device *adev = amdgpu_ttm_adev(bdev); - size_t bus_size = (size_t)mem->size; switch (mem->mem_type) { case TTM_PL_SYSTEM: @@ -572,9 +591,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev, break; case TTM_PL_VRAM: mem->bus.offset = mem->start << PAGE_SHIFT; - /* check if it's visible */ - if ((mem->bus.offset + bus_size) > adev->gmc.visible_vram_size) - return -EINVAL; if (adev->mman.aper_base_kaddr && mem->placement & TTM_PL_FLAG_CONTIGUOUS) @@ -868,6 +884,7 @@ static void amdgpu_ttm_gart_bind(struct amdgpu_device *adev, amdgpu_gart_bind(adev, gtt->offset, ttm->num_pages, gtt->ttm.dma_address, flags); } + gtt->bound = true; } /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 65ec82141a8e01..32cf6b6f6efd96 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -139,6 +139,9 @@ int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr, int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr, uint64_t start); +bool amdgpu_res_cpu_visible(struct amdgpu_device *adev, + struct ttm_resource *res); + int amdgpu_ttm_init(struct amdgpu_device *adev); void amdgpu_ttm_fini(struct amdgpu_device *adev); void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c index 8beefc045e1451..bef7541770641c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c @@ -1326,9 +1326,13 @@ int amdgpu_ucode_request(struct amdgpu_device *adev, const struct firmware **fw, if (err) return -ENODEV; + err = amdgpu_ucode_validate(*fw); - if (err) + if (err) { dev_dbg(adev->dev, "\"%s\" failed to validate\n", fw_name); + release_firmware(*fw); + *fw = NULL; + } return err; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 1904edf6840716..88a3aa36b41d77 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -742,7 +742,8 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t created = 0; uint32_t allocated = 0; uint32_t tmp, handle = 0; - uint32_t *size = &tmp; + uint32_t dummy = 0xffffffff; + uint32_t *size = &dummy; unsigned int idx; int i, r = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 36b55d2bd51a91..111350ef1b742a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -135,6 +135,10 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) } } + /* from vcn4 and above, only unified queue is used */ + adev->vcn.using_unified_queue = + adev->ip_versions[UVD_HWIP][0] >= IP_VERSION(4, 0, 0); + hdr = (const struct common_firmware_header *)adev->vcn.fw->data; adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version); @@ -259,18 +263,6 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev) return 0; } -/* from vcn4 and above, only unified queue is used */ -static bool amdgpu_vcn_using_unified_queue(struct amdgpu_ring *ring) -{ - struct amdgpu_device *adev = ring->adev; - bool ret = false; - - if (adev->ip_versions[UVD_HWIP][0] >= IP_VERSION(4, 0, 0)) - ret = true; - - return ret; -} - bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type type, uint32_t vcn_instance) { bool ret = false; @@ -292,8 +284,15 @@ int amdgpu_vcn_suspend(struct amdgpu_device *adev) void *ptr; int i, idx; + bool in_ras_intr = amdgpu_ras_intr_triggered(); + cancel_delayed_work_sync(&adev->vcn.idle_work); + /* err_event_athub will corrupt VCPU buffer, so we need to + * restore fw data and clear buffer in amdgpu_vcn_resume() */ + if (in_ras_intr) + return 0; + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { if (adev->vcn.harvest_config & (1 << i)) continue; @@ -373,7 +372,9 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work) for (i = 0; i < adev->vcn.num_enc_rings; ++i) fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_enc[i]); - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && + !adev->vcn.using_unified_queue) { struct dpg_pause_state new_state; if (fence[j] || @@ -419,7 +420,9 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring) amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN, AMD_PG_STATE_UNGATE); - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && + !adev->vcn.using_unified_queue) { struct dpg_pause_state new_state; if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) { @@ -445,8 +448,12 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring) void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring) { + struct amdgpu_device *adev = ring->adev; + + /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ if (ring->adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && - ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) + ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC && + !adev->vcn.using_unified_queue) atomic_dec(&ring->adev->vcn.inst[ring->me].dpg_enc_submission_cnt); atomic_dec(&ring->adev->vcn.total_submission_cnt); @@ -700,12 +707,11 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, struct amdgpu_job *job; struct amdgpu_ib *ib; uint64_t addr = AMDGPU_GPU_PAGE_ALIGN(ib_msg->gpu_addr); - bool sq = amdgpu_vcn_using_unified_queue(ring); uint32_t *ib_checksum; uint32_t ib_pack_in_dw; int i, r; - if (sq) + if (adev->vcn.using_unified_queue) ib_size_dw += 8; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, @@ -718,7 +724,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, ib->length_dw = 0; /* single queue headers */ - if (sq) { + if (adev->vcn.using_unified_queue) { ib_pack_in_dw = sizeof(struct amdgpu_vcn_decode_buffer) / sizeof(uint32_t) + 4 + 2; /* engine info + decoding ib in dw */ ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, ib_pack_in_dw, false); @@ -737,7 +743,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0; - if (sq) + if (adev->vcn.using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, ib_pack_in_dw); r = amdgpu_job_submit_direct(job, ring, &f); @@ -827,15 +833,15 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand struct dma_fence **fence) { unsigned int ib_size_dw = 16; + struct amdgpu_device *adev = ring->adev; struct amdgpu_job *job; struct amdgpu_ib *ib; struct dma_fence *f = NULL; uint32_t *ib_checksum = NULL; uint64_t addr; - bool sq = amdgpu_vcn_using_unified_queue(ring); int i, r; - if (sq) + if (adev->vcn.using_unified_queue) ib_size_dw += 8; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, @@ -849,7 +855,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand ib->length_dw = 0; - if (sq) + if (adev->vcn.using_unified_queue) ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true); ib->ptr[ib->length_dw++] = 0x00000018; @@ -871,7 +877,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0; - if (sq) + if (adev->vcn.using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11); r = amdgpu_job_submit_direct(job, ring, &f); @@ -894,15 +900,15 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han struct dma_fence **fence) { unsigned int ib_size_dw = 16; + struct amdgpu_device *adev = ring->adev; struct amdgpu_job *job; struct amdgpu_ib *ib; struct dma_fence *f = NULL; uint32_t *ib_checksum = NULL; uint64_t addr; - bool sq = amdgpu_vcn_using_unified_queue(ring); int i, r; - if (sq) + if (adev->vcn.using_unified_queue) ib_size_dw += 8; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, @@ -916,7 +922,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han ib->length_dw = 0; - if (sq) + if (adev->vcn.using_unified_queue) ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true); ib->ptr[ib->length_dw++] = 0x00000018; @@ -938,7 +944,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0; - if (sq) + if (adev->vcn.using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11); r = amdgpu_job_submit_direct(job, ring, &f); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index a3eed90b6af090..3dc2cffdae4fca 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -284,6 +284,7 @@ struct amdgpu_vcn { uint16_t inst_mask; uint8_t num_inst_per_aid; + bool using_unified_queue; }; struct amdgpu_fw_shared_rb_ptrs_struct { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 96857ae7fb5bc6..22575422ca7ec1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -137,8 +137,10 @@ int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init) if (virt->ops && virt->ops->req_full_gpu) { r = virt->ops->req_full_gpu(adev, init); - if (r) + if (r) { + adev->no_hw_access = true; return r; + } adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME; } @@ -615,7 +617,7 @@ static int amdgpu_virt_write_vf2pf_data(struct amdgpu_device *adev) vf2pf_info->dummy_page_addr = (uint64_t)adev->dummy_page_addr; vf2pf_info->checksum = amd_sriov_msg_checksum( - vf2pf_info, vf2pf_info->header.size, 0, 0); + vf2pf_info, sizeof(*vf2pf_info), 0, 0); return 0; } @@ -998,11 +1000,17 @@ static u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v return 0; } + if (amdgpu_device_skip_hw_access(adev)) + return 0; + reg_access_ctrl = &adev->gfx.rlc.reg_access_ctrl[xcc_id]; scratch_reg0 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg0; scratch_reg1 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg1; scratch_reg2 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg2; scratch_reg3 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg3; + + mutex_lock(&adev->virt.rlcg_reg_lock); + if (reg_access_ctrl->spare_int) spare_int = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->spare_int; @@ -1058,6 +1066,9 @@ static u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v } ret = readl(scratch_reg0); + + mutex_unlock(&adev->virt.rlcg_reg_lock); + return ret; } @@ -1067,6 +1078,9 @@ void amdgpu_sriov_wreg(struct amdgpu_device *adev, { u32 rlcg_flag; + if (amdgpu_device_skip_hw_access(adev)) + return; + if (!amdgpu_sriov_runtime(adev) && amdgpu_virt_get_rlcg_reg_access_flag(adev, acc_flags, hwip, true, &rlcg_flag)) { amdgpu_virt_rlcg_reg_rw(adev, offset, value, rlcg_flag, xcc_id); @@ -1084,6 +1098,9 @@ u32 amdgpu_sriov_rreg(struct amdgpu_device *adev, { u32 rlcg_flag; + if (amdgpu_device_skip_hw_access(adev)) + return 0; + if (!amdgpu_sriov_runtime(adev) && amdgpu_virt_get_rlcg_reg_access_flag(adev, acc_flags, hwip, false, &rlcg_flag)) return amdgpu_virt_rlcg_reg_rw(adev, offset, 0, rlcg_flag, xcc_id); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index fabb83e9d9aec7..23b6efa9d25df8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -263,6 +263,8 @@ struct amdgpu_virt { /* the ucode id to signal the autoload */ uint32_t autoload_ucode_id; + + struct mutex rlcg_reg_lock; }; struct amdgpu_video_codec_info; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index 7148a216ae2fe4..f417c3393a0904 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -2,6 +2,7 @@ #include #include +#include #include #include "amdgpu.h" @@ -239,6 +240,8 @@ static int amdgpu_vkms_conn_get_modes(struct drm_connector *connector) for (i = 0; i < ARRAY_SIZE(common_modes); i++) { mode = drm_cvt_mode(dev, common_modes[i].w, common_modes[i].h, 60, false, false, false); + if (!mode) + continue; drm_mode_probed_add(connector, mode); } @@ -311,7 +314,13 @@ static int amdgpu_vkms_prepare_fb(struct drm_plane *plane, return 0; } afb = to_amdgpu_framebuffer(new_state->fb); - obj = new_state->fb->obj[0]; + + obj = drm_gem_fb_get_obj(new_state->fb, 0); + if (!obj) { + DRM_ERROR("Failed to get obj from framebuffer\n"); + return -EINVAL; + } + rbo = gem_to_amdgpu_bo(obj); adev = amdgpu_ttm_adev(rbo->tbo.bdev); @@ -365,12 +374,19 @@ static void amdgpu_vkms_cleanup_fb(struct drm_plane *plane, struct drm_plane_state *old_state) { struct amdgpu_bo *rbo; + struct drm_gem_object *obj; int r; if (!old_state->fb) return; - rbo = gem_to_amdgpu_bo(old_state->fb->obj[0]); + obj = drm_gem_fb_get_obj(old_state->fb, 0); + if (!obj) { + DRM_ERROR("Failed to get obj from framebuffer\n"); + return; + } + + rbo = gem_to_amdgpu_bo(obj); r = amdgpu_bo_reserve(rbo, false); if (unlikely(r)) { DRM_ERROR("failed to reserve rbo before unpin\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 82f25996ff5ef6..f02b6232680f33 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -285,6 +285,7 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm) list_for_each_entry_safe(vm_bo, tmp, &vm->idle, vm_status) { struct amdgpu_bo *bo = vm_bo->bo; + vm_bo->moved = true; if (!bo || bo->tbo.type != ttm_bo_type_kernel) list_move(&vm_bo->vm_status, &vm_bo->vm->moved); else if (bo->parent) @@ -417,7 +418,7 @@ uint64_t amdgpu_vm_generation(struct amdgpu_device *adev, struct amdgpu_vm *vm) if (!vm) return result; - result += vm->generation; + result += lower_32_bits(vm->generation); /* Add one if the page tables will be re-generated on next CS */ if (drm_sched_entity_error(&vm->delayed)) ++result; @@ -442,13 +443,14 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm, int (*validate)(void *p, struct amdgpu_bo *bo), void *param) { + uint64_t new_vm_generation = amdgpu_vm_generation(adev, vm); struct amdgpu_vm_bo_base *bo_base; struct amdgpu_bo *shadow; struct amdgpu_bo *bo; int r; - if (drm_sched_entity_error(&vm->delayed)) { - ++vm->generation; + if (vm->generation != new_vm_generation) { + vm->generation = new_vm_generation; amdgpu_vm_bo_reset_state_machine(vm); amdgpu_vm_fini_entities(vm); r = amdgpu_vm_init_entities(adev, vm); @@ -1095,8 +1097,8 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, bo = gem_to_amdgpu_bo(gobj); } mem = bo->tbo.resource; - if (mem->mem_type == TTM_PL_TT || - mem->mem_type == AMDGPU_PL_PREEMPT) + if (mem && (mem->mem_type == TTM_PL_TT || + mem->mem_type == AMDGPU_PL_PREEMPT)) pages_addr = bo->tbo.ttm->dma_address; } @@ -1499,6 +1501,37 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev, trace_amdgpu_vm_bo_map(bo_va, mapping); } +/* Validate operation parameters to prevent potential abuse */ +static int amdgpu_vm_verify_parameters(struct amdgpu_device *adev, + struct amdgpu_bo *bo, + uint64_t saddr, + uint64_t offset, + uint64_t size) +{ + uint64_t tmp, lpfn; + + if (saddr & AMDGPU_GPU_PAGE_MASK + || offset & AMDGPU_GPU_PAGE_MASK + || size & AMDGPU_GPU_PAGE_MASK) + return -EINVAL; + + if (check_add_overflow(saddr, size, &tmp) + || check_add_overflow(offset, size, &tmp) + || size == 0 /* which also leads to end < begin */) + return -EINVAL; + + /* make sure object fit at this offset */ + if (bo && offset + size > amdgpu_bo_size(bo)) + return -EINVAL; + + /* Ensure last pfn not exceed max_pfn */ + lpfn = (saddr + size - 1) >> AMDGPU_GPU_PAGE_SHIFT; + if (lpfn >= adev->vm_manager.max_pfn) + return -EINVAL; + + return 0; +} + /** * amdgpu_vm_bo_map - map bo inside a vm * @@ -1525,21 +1558,14 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, struct amdgpu_bo *bo = bo_va->base.bo; struct amdgpu_vm *vm = bo_va->base.vm; uint64_t eaddr; + int r; - /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) - return -EINVAL; - if (saddr + size <= saddr || offset + size <= offset) - return -EINVAL; - - /* make sure object fit at this offset */ - eaddr = saddr + size - 1; - if ((bo && offset + size > amdgpu_bo_size(bo)) || - (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) - return -EINVAL; + r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size); + if (r) + return r; saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; tmp = amdgpu_vm_it_iter_first(&vm->va, saddr, eaddr); if (tmp) { @@ -1592,17 +1618,9 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, uint64_t eaddr; int r; - /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) - return -EINVAL; - if (saddr + size <= saddr || offset + size <= offset) - return -EINVAL; - - /* make sure object fit at this offset */ - eaddr = saddr + size - 1; - if ((bo && offset + size > amdgpu_bo_size(bo)) || - (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) - return -EINVAL; + r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size); + if (r) + return r; /* Allocate all the needed memory */ mapping = kmalloc(sizeof(*mapping), GFP_KERNEL); @@ -1616,7 +1634,7 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, } saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; mapping->start = saddr; mapping->last = eaddr; @@ -1703,10 +1721,14 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, struct amdgpu_bo_va_mapping *before, *after, *tmp, *next; LIST_HEAD(removed); uint64_t eaddr; + int r; + + r = amdgpu_vm_verify_parameters(adev, NULL, saddr, 0, size); + if (r) + return r; - eaddr = saddr + size - 1; saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; /* Allocate all the needed memory */ before = kzalloc(sizeof(*before), GFP_KERNEL); @@ -2125,7 +2147,8 @@ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout) * Returns: * 0 for success, error for failure. */ -int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id) +int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, + int32_t xcp_id) { struct amdgpu_bo *root_bo; struct amdgpu_bo_vm *root; @@ -2144,6 +2167,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp INIT_LIST_HEAD(&vm->done); INIT_LIST_HEAD(&vm->pt_freed); INIT_WORK(&vm->pt_free_work, amdgpu_vm_pt_free_work); + INIT_KFIFO(vm->faults); r = amdgpu_vm_init_entities(adev, vm); if (r) @@ -2169,7 +2193,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp vm->last_update = dma_fence_get_stub(); vm->last_unlocked = dma_fence_get_stub(); vm->last_tlb_flush = dma_fence_get_stub(); - vm->generation = 0; + vm->generation = amdgpu_vm_generation(adev, NULL); mutex_init(&vm->eviction_lock); vm->evicting = false; @@ -2178,34 +2202,33 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp false, &root, xcp_id); if (r) goto error_free_delayed; - root_bo = &root->bo; + + root_bo = amdgpu_bo_ref(&root->bo); r = amdgpu_bo_reserve(root_bo, true); - if (r) - goto error_free_root; + if (r) { + amdgpu_bo_unref(&root->shadow); + amdgpu_bo_unref(&root_bo); + goto error_free_delayed; + } + amdgpu_vm_bo_base_init(&vm->root, vm, root_bo); r = dma_resv_reserve_fences(root_bo->tbo.base.resv, 1); if (r) - goto error_unreserve; - - amdgpu_vm_bo_base_init(&vm->root, vm, root_bo); + goto error_free_root; r = amdgpu_vm_pt_clear(adev, vm, root, false); if (r) - goto error_unreserve; + goto error_free_root; amdgpu_bo_unreserve(vm->root.bo); - - INIT_KFIFO(vm->faults); + amdgpu_bo_unref(&root_bo); return 0; -error_unreserve: - amdgpu_bo_unreserve(vm->root.bo); - error_free_root: - amdgpu_bo_unref(&root->shadow); + amdgpu_vm_pt_free_root(adev, vm); + amdgpu_bo_unreserve(vm->root.bo); amdgpu_bo_unref(&root_bo); - vm->root.bo = NULL; error_free_delayed: dma_fence_put(vm->last_tlb_flush); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index 96d601e209b8bd..026a3db9472983 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -642,13 +642,14 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) if (!entry->bo) return; + + entry->bo->vm_bo = NULL; shadow = amdgpu_bo_shadowed(entry->bo); if (shadow) { ttm_bo_set_bulk_move(&shadow->tbo, NULL); amdgpu_bo_unref(&shadow); } ttm_bo_set_bulk_move(&entry->bo->tbo, NULL); - entry->bo->vm_bo = NULL; spin_lock(&entry->vm->status_lock); list_del(&entry->vm_status); @@ -765,11 +766,15 @@ int amdgpu_vm_pde_update(struct amdgpu_vm_update_params *params, struct amdgpu_vm_bo_base *entry) { struct amdgpu_vm_bo_base *parent = amdgpu_vm_pt_parent(entry); - struct amdgpu_bo *bo = parent->bo, *pbo; + struct amdgpu_bo *bo, *pbo; struct amdgpu_vm *vm = params->vm; uint64_t pde, pt, flags; unsigned int level; + if (WARN_ON(!parent)) + return -EINVAL; + + bo = parent->bo; for (level = 0, pbo = bo->parent; pbo; ++level) pbo = pbo->parent; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index 349416e176a127..1cf1498204678b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -102,6 +102,11 @@ static int amdgpu_vm_sdma_prepare(struct amdgpu_vm_update_params *p, if (!r) r = amdgpu_sync_push_to_job(&sync, p->job); amdgpu_sync_free(&sync); + + if (r) { + p->num_dw_left = 0; + amdgpu_job_free(p->job); + } return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h index 9a1036aeec2a0b..9142238e7791a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h @@ -179,6 +179,6 @@ amdgpu_get_next_xcp(struct amdgpu_xcp_mgr *xcp_mgr, int *from) #define for_each_xcp(xcp_mgr, xcp, i) \ for (i = 0, xcp = amdgpu_get_next_xcp(xcp_mgr, &i); xcp; \ - xcp = amdgpu_get_next_xcp(xcp_mgr, &i)) + ++i, xcp = amdgpu_get_next_xcp(xcp_mgr, &i)) #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h index 104a5ad8397da7..198687545407e9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h @@ -209,7 +209,7 @@ struct amd_sriov_msg_pf2vf_info { uint32_t pcie_atomic_ops_support_flags; /* reserved */ uint32_t reserved[256 - AMD_SRIOV_MSG_PF2VF_INFO_FILLED_SIZE]; -}; +} __packed; struct amd_sriov_msg_vf2pf_info_header { /* the total structure size in byte */ @@ -267,7 +267,7 @@ struct amd_sriov_msg_vf2pf_info { /* reserved */ uint32_t reserved[256 - AMD_SRIOV_MSG_VF2PF_INFO_FILLED_SIZE]; -}; +} __packed; /* mailbox message send from guest to host */ enum amd_sriov_mailbox_request_message { diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c index d0fc62784e8217..6c6f9d9b5d8978 100644 --- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c +++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c @@ -61,6 +61,11 @@ void aqua_vanjaram_doorbell_index_init(struct amdgpu_device *adev) adev->doorbell_index.max_assignment = AMDGPU_DOORBELL_LAYOUT1_MAX_ASSIGNMENT << 1; } +static bool aqua_vanjaram_xcp_vcn_shared(struct amdgpu_device *adev) +{ + return (adev->xcp_mgr->num_xcps > adev->vcn.num_vcn_inst); +} + static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev, uint32_t inst_idx, struct amdgpu_ring *ring) { @@ -86,7 +91,7 @@ static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev, case AMDGPU_RING_TYPE_VCN_ENC: case AMDGPU_RING_TYPE_VCN_JPEG: ip_blk = AMDGPU_XCP_VCN; - if (adev->xcp_mgr->mode == AMDGPU_CPX_PARTITION_MODE) + if (aqua_vanjaram_xcp_vcn_shared(adev)) inst_mask = 1 << (inst_idx * 2); break; default: @@ -139,10 +144,12 @@ static int aqua_vanjaram_xcp_sched_list_update( aqua_vanjaram_xcp_gpu_sched_update(adev, ring, ring->xcp_id); - /* VCN is shared by two partitions under CPX MODE */ + /* VCN may be shared by two partitions under CPX MODE in certain + * configs. + */ if ((ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC || - ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) && - adev->xcp_mgr->mode == AMDGPU_CPX_PARTITION_MODE) + ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) && + aqua_vanjaram_xcp_vcn_shared(adev)) aqua_vanjaram_xcp_gpu_sched_update(adev, ring, ring->xcp_id + 1); } @@ -493,6 +500,12 @@ static int aqua_vanjaram_switch_partition_mode(struct amdgpu_xcp_mgr *xcp_mgr, if (mode == AMDGPU_AUTO_COMPUTE_PARTITION_MODE) { mode = __aqua_vanjaram_get_auto_mode(xcp_mgr); + if (mode == AMDGPU_UNKNOWN_COMPUTE_PARTITION_MODE) { + dev_err(adev->dev, + "Invalid config, no compatible compute partition mode found, available memory partitions: %d", + adev->gmc.num_mem_partitions); + return -EINVAL; + } } else if (!__aqua_vanjaram_is_valid_mode(xcp_mgr, mode)) { dev_err(adev->dev, "Invalid compute partition mode requested, requested: %s, available memory partitions: %d", diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c index 9f63ddb89b75c1..1195d37f19fc5c 100644 --- a/drivers/gpu/drm/amd/amdgpu/atom.c +++ b/drivers/gpu/drm/amd/amdgpu/atom.c @@ -313,7 +313,7 @@ static uint32_t atom_get_src_int(atom_exec_context *ctx, uint8_t attr, DEBUG("IMM 0x%02X\n", val); return val; } - return 0; + break; case ATOM_ARG_PLL: idx = U8(*ptr); (*ptr)++; diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c index d95b2dc7806341..157e898dc3820d 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c @@ -2065,26 +2065,29 @@ amdgpu_atombios_encoder_get_lcd_info(struct amdgpu_encoder *encoder) fake_edid_record = (ATOM_FAKE_EDID_PATCH_RECORD *)record; if (fake_edid_record->ucFakeEDIDLength) { struct edid *edid; - int edid_size = - max((int)EDID_LENGTH, (int)fake_edid_record->ucFakeEDIDLength); - edid = kmalloc(edid_size, GFP_KERNEL); + int edid_size; + + if (fake_edid_record->ucFakeEDIDLength == 128) + edid_size = fake_edid_record->ucFakeEDIDLength; + else + edid_size = fake_edid_record->ucFakeEDIDLength * 128; + edid = kmemdup(&fake_edid_record->ucFakeEDIDString[0], + edid_size, GFP_KERNEL); if (edid) { - memcpy((u8 *)edid, (u8 *)&fake_edid_record->ucFakeEDIDString[0], - fake_edid_record->ucFakeEDIDLength); - if (drm_edid_is_valid(edid)) { adev->mode_info.bios_hardcoded_edid = edid; adev->mode_info.bios_hardcoded_edid_size = edid_size; - } else + } else { kfree(edid); + } } + record += struct_size(fake_edid_record, + ucFakeEDIDString, + edid_size); + } else { + /* empty fake edid record must be 3 bytes long */ + record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD) + 1; } - record += fake_edid_record->ucFakeEDIDLength ? - struct_size(fake_edid_record, - ucFakeEDIDString, - fake_edid_record->ucFakeEDIDLength) : - /* empty fake edid record must be 3 bytes long */ - sizeof(ATOM_FAKE_EDID_PATCH_RECORD) + 1; break; case LCD_PANEL_RESOLUTION_RECORD_TYPE: panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record; diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c index 6f7c031dd197a2..f24e34dc33d1de 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c @@ -204,6 +204,12 @@ static u32 cik_ih_get_wptr(struct amdgpu_device *adev, tmp = RREG32(mmIH_RB_CNTL); tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; WREG32(mmIH_RB_CNTL, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; + WREG32(mmIH_RB_CNTL, tmp); } return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c index b8c47e0cf37ad5..c19681492efa74 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c @@ -216,6 +216,11 @@ static u32 cz_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32(mmIH_RB_CNTL, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32(mmIH_RB_CNTL, tmp); out: return (wptr & ih->ptr_mask); diff --git a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c index 5dfab80ffff213..cd298556f7a608 100644 --- a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c +++ b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c @@ -70,6 +70,8 @@ static u32 df_v1_7_get_hbm_channel_number(struct amdgpu_device *adev) int fb_channel_number; fb_channel_number = adev->df.funcs->get_fb_channel_number(adev); + if (fb_channel_number >= ARRAY_SIZE(df_v1_7_channel_number)) + fb_channel_number = 0; return df_v1_7_channel_number[fb_channel_number]; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 9032d7a24d7cd7..53c99bc6abb333 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3989,16 +3989,13 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) if (!amdgpu_sriov_vf(adev)) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", ucode_prefix); - err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, fw_name); - /* don't check this. There are apparently firmwares in the wild with - * incorrect size in the header - */ - if (err == -ENODEV) - goto out; + err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev); if (err) - dev_dbg(adev->dev, - "gfx10: amdgpu_ucode_request() failed \"%s\"\n", - fw_name); + goto out; + + /* don't validate this firmware. There are apparently firmwares + * in the wild with incorrect size in the header + */ rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; version_major = le16_to_cpu(rlc_hdr->header.header_version_major); version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor); @@ -4023,8 +4020,6 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) err = 0; adev->gfx.mec2_fw = NULL; } - amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2); - amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT); gfx_v10_0_check_fw_write_wait(adev); out: @@ -6457,11 +6452,11 @@ static int gfx_v10_0_gfx_init_queue(struct amdgpu_ring *ring) nv_grbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); if (adev->gfx.me.mqd_backup[mqd_idx]) - memcpy(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); + memcpy_fromio(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); } else { /* restore mqd with the backup copy */ if (adev->gfx.me.mqd_backup[mqd_idx]) - memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); + memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset the ring */ ring->wptr = 0; *ring->wptr_cpu_addr = 0; @@ -6575,7 +6570,7 @@ static int gfx_v10_0_compute_mqd_init(struct amdgpu_device *adev, void *m, #ifdef __BIG_ENDIAN tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, ENDIAN_SWAP, 1); #endif - tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 0); + tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH, 0); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1); @@ -6735,7 +6730,7 @@ static int gfx_v10_0_kiq_init_queue(struct amdgpu_ring *ring) if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */ /* reset MQD to a clean status */ if (adev->gfx.kiq[0].mqd_backup) - memcpy(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd)); + memcpy_toio(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd)); /* reset ring buffer */ ring->wptr = 0; @@ -6758,7 +6753,7 @@ static int gfx_v10_0_kiq_init_queue(struct amdgpu_ring *ring) mutex_unlock(&adev->srbm_mutex); if (adev->gfx.kiq[0].mqd_backup) - memcpy(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd)); + memcpy_fromio(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd)); } return 0; @@ -6779,11 +6774,11 @@ static int gfx_v10_0_kcq_init_queue(struct amdgpu_ring *ring) mutex_unlock(&adev->srbm_mutex); if (adev->gfx.mec.mqd_backup[mqd_idx]) - memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); + memcpy_fromio(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); } else { /* restore MQD to a clean status */ if (adev->gfx.mec.mqd_backup[mqd_idx]) - memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd)); + memcpy_toio(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset ring buffer */ ring->wptr = 0; atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0); @@ -7897,22 +7892,15 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev, static void gfx_v10_0_update_spm_vmid_internal(struct amdgpu_device *adev, unsigned int vmid) { - u32 reg, data; + u32 data; /* not for *_SOC15 */ - reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL); - if (amdgpu_sriov_is_pp_one_vf(adev)) - data = RREG32_NO_KIQ(reg); - else - data = RREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL); + data = RREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL); data &= ~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK; data |= (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT; - if (amdgpu_sriov_is_pp_one_vf(adev)) - WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data); - else - WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data); + WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data); } static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned int vmid) @@ -8760,7 +8748,9 @@ static void gfx_v10_0_ring_soft_recovery(struct amdgpu_ring *ring, value = REG_SET_FIELD(value, SQ_CMD, MODE, 0x01); value = REG_SET_FIELD(value, SQ_CMD, CHECK_VMID, 1); value = REG_SET_FIELD(value, SQ_CMD, VM_ID, vmid); + amdgpu_gfx_rlc_enter_safe_mode(adev, 0); WREG32_SOC15(GC, 0, mmSQ_CMD, value); + amdgpu_gfx_rlc_exit_safe_mode(adev, 0); } static void @@ -9162,7 +9152,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = { 7 + /* PIPELINE_SYNC */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* VM_FLUSH */ + 4 + /* VM_FLUSH */ 8 + /* FENCE for VM_FLUSH */ 20 + /* GDS switch */ 4 + /* double SWITCH_BUFFER, @@ -9253,7 +9243,6 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = { 7 + /* gfx_v10_0_ring_emit_pipeline_sync */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* gfx_v10_0_ring_emit_vm_flush */ 8 + 8 + 8, /* gfx_v10_0_ring_emit_fence_kiq x3 for user fence, vm fence */ .emit_ib_size = 7, /* gfx_v10_0_ring_emit_ib_compute */ .emit_ib = gfx_v10_0_ring_emit_ib_compute, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 762d7a19f1be16..54ec9b32562c28 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -83,6 +83,10 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_4_me.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_4_mec.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_4_rlc.bin"); +static const struct soc15_reg_golden golden_settings_gc_11_0[] = { + SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL, 0x20000000, 0x20000000) +}; + static const struct soc15_reg_golden golden_settings_gc_11_0_1[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, regCGTT_GS_NGG_CLK_CTRL, 0x9fff8fff, 0x00000010), @@ -275,6 +279,10 @@ static void gfx_v11_0_init_golden_registers(struct amdgpu_device *adev) default: break; } + soc15_program_register_sequence(adev, + golden_settings_gc_11_0, + (const u32)ARRAY_SIZE(golden_settings_gc_11_0)); + } static void gfx_v11_0_write_data_to_reg(struct amdgpu_ring *ring, int eng_sel, @@ -390,7 +398,7 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD); cpu_ptr = &adev->wb.wb[index]; - r = amdgpu_ib_get(adev, NULL, 16, AMDGPU_IB_POOL_DIRECT, &ib); + r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib); if (r) { DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r); goto err1; @@ -1608,7 +1616,7 @@ static void gfx_v11_0_setup_rb(struct amdgpu_device *adev) active_rb_bitmap |= (0x3 << (i * rb_bitmap_width_per_sa)); } - active_rb_bitmap |= global_active_rb_bitmap; + active_rb_bitmap &= global_active_rb_bitmap; adev->gfx.config.backend_enable_mask = active_rb_bitmap; adev->gfx.config.num_rbs = hweight32(active_rb_bitmap); } @@ -3684,11 +3692,11 @@ static int gfx_v11_0_gfx_init_queue(struct amdgpu_ring *ring) soc21_grbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); if (adev->gfx.me.mqd_backup[mqd_idx]) - memcpy(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); + memcpy_fromio(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); } else { /* restore mqd with the backup copy */ if (adev->gfx.me.mqd_backup[mqd_idx]) - memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); + memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset the ring */ ring->wptr = 0; *ring->wptr_cpu_addr = 0; @@ -3799,7 +3807,7 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m, (order_base_2(prop->queue_size / 4) - 1)); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE, (order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1)); - tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 0); + tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH, 0); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1); @@ -3977,7 +3985,7 @@ static int gfx_v11_0_kiq_init_queue(struct amdgpu_ring *ring) if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */ /* reset MQD to a clean status */ if (adev->gfx.kiq[0].mqd_backup) - memcpy(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd)); + memcpy_toio(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd)); /* reset ring buffer */ ring->wptr = 0; @@ -4000,7 +4008,7 @@ static int gfx_v11_0_kiq_init_queue(struct amdgpu_ring *ring) mutex_unlock(&adev->srbm_mutex); if (adev->gfx.kiq[0].mqd_backup) - memcpy(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd)); + memcpy_fromio(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd)); } return 0; @@ -4021,11 +4029,11 @@ static int gfx_v11_0_kcq_init_queue(struct amdgpu_ring *ring) mutex_unlock(&adev->srbm_mutex); if (adev->gfx.mec.mqd_backup[mqd_idx]) - memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); + memcpy_fromio(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); } else { /* restore MQD to a clean status */ if (adev->gfx.mec.mqd_backup[mqd_idx]) - memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd)); + memcpy_toio(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset ring buffer */ ring->wptr = 0; atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0); @@ -4261,11 +4269,11 @@ static int gfx_v11_0_hw_init(void *handle) /* RLC autoload sequence 1: Program rlc ram */ if (adev->gfx.imu.funcs->program_rlc_ram) adev->gfx.imu.funcs->program_rlc_ram(adev); + /* rlc autoload firmware */ + r = gfx_v11_0_rlc_backdoor_autoload_enable(adev); + if (r) + return r; } - /* rlc autoload firmware */ - r = gfx_v11_0_rlc_backdoor_autoload_enable(adev); - if (r) - return r; } else { if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) { if (adev->gfx.imu.funcs && (amdgpu_dpm > 0)) { @@ -4953,23 +4961,16 @@ static int gfx_v11_0_update_gfx_clock_gating(struct amdgpu_device *adev, static void gfx_v11_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid) { - u32 reg, data; + u32 data; amdgpu_gfx_off_ctrl(adev, false); - reg = SOC15_REG_OFFSET(GC, 0, regRLC_SPM_MC_CNTL); - if (amdgpu_sriov_is_pp_one_vf(adev)) - data = RREG32_NO_KIQ(reg); - else - data = RREG32(reg); + data = RREG32_SOC15_NO_KIQ(GC, 0, regRLC_SPM_MC_CNTL); data &= ~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK; data |= (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT; - if (amdgpu_sriov_is_pp_one_vf(adev)) - WREG32_SOC15_NO_KIQ(GC, 0, regRLC_SPM_MC_CNTL, data); - else - WREG32_SOC15(GC, 0, regRLC_SPM_MC_CNTL, data); + WREG32_SOC15_NO_KIQ(GC, 0, regRLC_SPM_MC_CNTL, data); amdgpu_gfx_off_ctrl(adev, true); } @@ -5700,7 +5701,9 @@ static void gfx_v11_0_ring_soft_recovery(struct amdgpu_ring *ring, value = REG_SET_FIELD(value, SQ_CMD, MODE, 0x01); value = REG_SET_FIELD(value, SQ_CMD, CHECK_VMID, 1); value = REG_SET_FIELD(value, SQ_CMD, VM_ID, vmid); + amdgpu_gfx_rlc_enter_safe_mode(adev, 0); WREG32_SOC15(GC, 0, regSQ_CMD, value); + amdgpu_gfx_rlc_exit_safe_mode(adev, 0); } static void @@ -6094,7 +6097,7 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_gfx = { 7 + /* PIPELINE_SYNC */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* VM_FLUSH */ + 4 + /* VM_FLUSH */ 8 + /* FENCE for VM_FLUSH */ 20 + /* GDS switch */ 5 + /* COND_EXEC */ @@ -6179,7 +6182,6 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_kiq = { 7 + /* gfx_v11_0_ring_emit_pipeline_sync */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* gfx_v11_0_ring_emit_vm_flush */ 8 + 8 + 8, /* gfx_v11_0_ring_emit_fence_kiq x3 for user fence, vm fence */ .emit_ib_size = 7, /* gfx_v11_0_ring_emit_ib_compute */ .emit_ib = gfx_v11_0_ring_emit_ib_compute, @@ -6345,6 +6347,9 @@ static int gfx_v11_0_get_cu_info(struct amdgpu_device *adev, mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { + bitmap = i * adev->gfx.config.max_sh_per_se + j; + if (!((gfx_v11_0_get_sa_active_bitmap(adev) >> bitmap) & 1)) + continue; mask = 1; counter = 0; gfx_v11_0_select_se_sh(adev, i, j, 0xffffffff, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 885ebd703260f0..1943beb135c4c2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -883,8 +883,8 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index * 4); adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD); memset(&ib, 0, sizeof(ib)); - r = amdgpu_ib_get(adev, NULL, 16, - AMDGPU_IB_POOL_DIRECT, &ib); + + r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib); if (r) goto err1; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index fd61574a737cb1..895060f6948f30 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1039,8 +1039,8 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index * 4); adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD); memset(&ib, 0, sizeof(ib)); - r = amdgpu_ib_get(adev, NULL, 16, - AMDGPU_IB_POOL_DIRECT, &ib); + + r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib); if (r) goto err1; @@ -1172,6 +1172,10 @@ static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = { { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc6 }, /* Apple MacBook Pro (15-inch, 2019) Radeon Pro Vega 20 4 GB */ { 0x1002, 0x69af, 0x106b, 0x019a, 0xc0 }, + /* https://bbs.openkylin.top/t/topic/171497 */ + { 0x1002, 0x15d8, 0x19e5, 0x3e14, 0xc2 }, + /* HP 705G4 DM with R5 2400G */ + { 0x1002, 0x15dd, 0x103c, 0x8464, 0xd6 }, { 0, 0, 0, 0, 0 }, }; @@ -3033,6 +3037,14 @@ static int gfx_v9_0_cp_gfx_start(struct amdgpu_device *adev) gfx_v9_0_cp_gfx_enable(adev, true); + /* Now only limit the quirk on the APU gfx9 series and already + * confirmed that the APU gfx10/gfx11 needn't such update. + */ + if (adev->flags & AMD_IS_APU && + adev->in_s3 && !adev->suspend_complete) { + DRM_INFO(" Will skip the CSB packet resubmit\n"); + return 0; + } r = amdgpu_ring_alloc(ring, gfx_v9_0_get_csb_size(adev) + 4 + 3); if (r) { DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r); @@ -5697,7 +5709,9 @@ static void gfx_v9_0_ring_soft_recovery(struct amdgpu_ring *ring, unsigned vmid) value = REG_SET_FIELD(value, SQ_CMD, MODE, 0x01); value = REG_SET_FIELD(value, SQ_CMD, CHECK_VMID, 1); value = REG_SET_FIELD(value, SQ_CMD, VM_ID, vmid); + amdgpu_gfx_rlc_enter_safe_mode(adev, 0); WREG32_SOC15(GC, 0, mmSQ_CMD, value); + amdgpu_gfx_rlc_exit_safe_mode(adev, 0); } static void gfx_v9_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev, @@ -6980,7 +6994,6 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = { 7 + /* gfx_v9_0_ring_emit_pipeline_sync */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* gfx_v9_0_ring_emit_vm_flush */ 8 + 8 + 8 + /* gfx_v9_0_ring_emit_fence x3 for user fence, vm fence */ 7 + /* gfx_v9_0_emit_mem_sync */ 5 + /* gfx_v9_0_emit_wave_limit for updating mmSPI_WCL_PIPE_PERCENT_GFX register */ @@ -7018,7 +7031,6 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_kiq = { 7 + /* gfx_v9_0_ring_emit_pipeline_sync */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* gfx_v9_0_ring_emit_vm_flush */ 8 + 8 + 8, /* gfx_v9_0_ring_emit_fence_kiq x3 for user fence, vm fence */ .emit_ib_size = 7, /* gfx_v9_0_ring_emit_ib_compute */ .emit_fence = gfx_v9_0_ring_emit_fence_kiq, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index 18ce5fe45f6f86..caa04d897c2ded 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -296,8 +296,8 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index * 4); adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD); memset(&ib, 0, sizeof(ib)); - r = amdgpu_ib_get(adev, NULL, 16, - AMDGPU_IB_POOL_DIRECT, &ib); + + r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib); if (r) goto err1; @@ -425,16 +425,16 @@ static int gfx_v9_4_3_init_cp_compute_microcode(struct amdgpu_device *adev, static int gfx_v9_4_3_init_microcode(struct amdgpu_device *adev) { - const char *chip_name; + char ucode_prefix[15]; int r; - chip_name = "gc_9_4_3"; + amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix)); - r = gfx_v9_4_3_init_rlc_microcode(adev, chip_name); + r = gfx_v9_4_3_init_rlc_microcode(adev, ucode_prefix); if (r) return r; - r = gfx_v9_4_3_init_cp_compute_microcode(adev, chip_name); + r = gfx_v9_4_3_init_cp_compute_microcode(adev, ucode_prefix); if (r) return r; @@ -4290,9 +4290,10 @@ static u32 gfx_v9_4_3_get_cu_active_bitmap(struct amdgpu_device *adev, int xcc_i static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev, struct amdgpu_cu_info *cu_info) { - int i, j, k, counter, xcc_id, active_cu_number = 0; - u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0; + int i, j, k, prev_counter, counter, xcc_id, active_cu_number = 0; + u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0, tmp; unsigned disable_masks[4 * 4]; + bool is_symmetric_cus; if (!adev || !cu_info) return -EINVAL; @@ -4310,6 +4311,7 @@ static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev, mutex_lock(&adev->grbm_idx_mutex); for (xcc_id = 0; xcc_id < NUM_XCC(adev->gfx.xcc_mask); xcc_id++) { + is_symmetric_cus = true; for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { mask = 1; @@ -4337,6 +4339,15 @@ static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev, ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8)); cu_info->ao_cu_bitmap[i][j] = ao_bitmap; } + if (i && is_symmetric_cus && prev_counter != counter) + is_symmetric_cus = false; + prev_counter = counter; + } + if (is_symmetric_cus) { + tmp = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_CPC_DEBUG); + tmp = REG_SET_FIELD(tmp, CP_CPC_DEBUG, CPC_HARVESTING_RELAUNCH_DISABLE, 1); + tmp = REG_SET_FIELD(tmp, CP_CPC_DEBUG, CPC_HARVESTING_DISPATCH_DISABLE, 1); + WREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_CPC_DEBUG, tmp); } gfx_v9_4_3_xcc_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, xcc_id); diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c index cdc290a474a927..66c6bab75f8a58 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c @@ -102,7 +102,9 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR, min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); - if (adev->apu_flags & AMD_APU_IS_RAVEN2) + if (adev->apu_flags & (AMD_APU_IS_RAVEN2 | + AMD_APU_IS_RENOIR | + AMD_APU_IS_GREEN_SARDINE)) /* * Raven2 has a HW issue that it is unable to use the * vram which is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c index 0834af7715497d..b50f24f7ea5c99 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c @@ -139,7 +139,9 @@ gfxhub_v1_2_xcc_init_system_aperture_regs(struct amdgpu_device *adev, WREG32_SOC15_RLC(GC, GET_INST(GC, i), regMC_VM_SYSTEM_APERTURE_LOW_ADDR, min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); - if (adev->apu_flags & AMD_APU_IS_RAVEN2) + if (adev->apu_flags & (AMD_APU_IS_RAVEN2 | + AMD_APU_IS_RENOIR | + AMD_APU_IS_GREEN_SARDINE)) /* * Raven2 has a HW issue that it is unable to use the * vram which is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index fa87a85e1017e7..62ecf4d89cb9cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -1141,6 +1141,10 @@ static int gmc_v10_0_hw_fini(void *handle) amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); + if (adev->gmc.ecc_irq.funcs && + amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC)) + amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index e3b76fd28d158c..3d797a1adef3e5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -974,6 +974,11 @@ static int gmc_v11_0_hw_fini(void *handle) } amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); + + if (adev->gmc.ecc_irq.funcs && + amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC)) + amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); + gmc_v11_0_gart_disable(adev); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index 5b837a65fad20c..dfee4aae80393a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -914,8 +914,8 @@ static int gmc_v6_0_hw_init(void *handle) if (amdgpu_emu_mode == 1) return amdgpu_gmc_vram_checking(adev); - else - return r; + + return 0; } static int gmc_v6_0_hw_fini(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 6a6929ac27482d..fd905889a4c63b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -1103,8 +1103,8 @@ static int gmc_v7_0_hw_init(void *handle) if (amdgpu_emu_mode == 1) return amdgpu_gmc_vram_checking(adev); - else - return r; + + return 0; } static int gmc_v7_0_hw_fini(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 5af23520251322..0bebcdbb265807 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -1224,8 +1224,8 @@ static int gmc_v8_0_hw_init(void *handle) if (amdgpu_emu_mode == 1) return amdgpu_gmc_vram_checking(adev); - else - return r; + + return 0; } static int gmc_v8_0_hw_fini(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index f9a5a2c0573e41..6d2b9d260d92c5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1949,7 +1949,7 @@ gmc_v9_0_init_sw_mem_ranges(struct amdgpu_device *adev, break; } - size = adev->gmc.real_vram_size >> AMDGPU_GPU_PAGE_SHIFT; + size = (adev->gmc.real_vram_size + SZ_16M) >> AMDGPU_GPU_PAGE_SHIFT; size /= adev->gmc.num_mem_partitions; for (i = 0; i < adev->gmc.num_mem_partitions; ++i) { @@ -2220,8 +2220,6 @@ static int gmc_v9_0_sw_fini(void *handle) if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 3)) amdgpu_gmc_sysfs_fini(adev); - adev->gmc.num_mem_partitions = 0; - kfree(adev->gmc.mem_partitions); amdgpu_gmc_ras_fini(adev); amdgpu_gem_force_release(adev); @@ -2235,6 +2233,9 @@ static int gmc_v9_0_sw_fini(void *handle) amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0); amdgpu_bo_fini(adev); + adev->gmc.num_mem_partitions = 0; + kfree(adev->gmc.mem_partitions); + return 0; } @@ -2372,8 +2373,8 @@ static int gmc_v9_0_hw_init(void *handle) if (amdgpu_emu_mode == 1) return amdgpu_gmc_vram_checking(adev); - else - return r; + + return 0; } /** @@ -2412,6 +2413,10 @@ static int gmc_v9_0_hw_fini(void *handle) amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); + if (adev->gmc.ecc_irq.funcs && + amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC)) + amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c index aecad530b10a61..2c02ae69883d2b 100644 --- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c @@ -215,6 +215,11 @@ static u32 iceland_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32(mmIH_RB_CNTL, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32(mmIH_RB_CNTL, tmp); out: return (wptr & ih->ptr_mask); diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c index ec0c8f8b465ab2..725b1a585088db 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c @@ -135,6 +135,34 @@ static int ih_v6_0_toggle_ring_interrupts(struct amdgpu_device *adev, tmp = RREG32(ih_regs->ih_rb_cntl); tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_ENABLE, (enable ? 1 : 0)); + + if (enable) { + /* Unset the CLEAR_OVERFLOW bit to make sure the next step + * is switching the bit from 0 to 1 + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + if (amdgpu_sriov_vf(adev) && amdgpu_sriov_reg_indirect_ih(adev)) { + if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp)) + return -ETIMEDOUT; + } else { + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + } + + /* Clear RB_OVERFLOW bit */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); + if (amdgpu_sriov_vf(adev) && amdgpu_sriov_reg_indirect_ih(adev)) { + if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp)) + return -ETIMEDOUT; + } else { + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + } + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + } + /* enable_intr field is only valid in ring0 */ if (ih == &adev->irq.ih) tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, ENABLE_INTR, (enable ? 1 : 0)); @@ -418,6 +446,12 @@ static u32 ih_v6_0_get_wptr(struct amdgpu_device *adev, tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl); tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c index 8fb05eae340ad2..b8da0fc29378c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c @@ -418,6 +418,13 @@ static u32 ih_v6_1_get_wptr(struct amdgpu_device *adev, tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl); tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c index 4ab90c7852c3ed..ca123ff553477e 100644 --- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c @@ -39,7 +39,7 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_4_imu.bin"); static int imu_v11_0_init_microcode(struct amdgpu_device *adev) { - char fw_name[40]; + char fw_name[45]; char ucode_prefix[30]; int err; const struct imu_firmware_header_v1_0 *imu_hdr; diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c index 77595e9622da34..7ac0228fe532ee 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c @@ -23,6 +23,7 @@ #include "amdgpu.h" #include "amdgpu_jpeg.h" +#include "amdgpu_cs.h" #include "soc15.h" #include "soc15d.h" #include "vcn_v1_0.h" @@ -34,6 +35,9 @@ static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev); static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring); +static int jpeg_v1_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib); static void jpeg_v1_0_decode_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val) { @@ -300,7 +304,10 @@ static void jpeg_v1_0_decode_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_VMID), 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + if (ring->funcs->parse_cs) + amdgpu_ring_write(ring, 0); + else + amdgpu_ring_write(ring, (vmid | (vmid << 4))); amdgpu_ring_write(ring, PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JPEG_VMID), 0, 0, PACKETJ_TYPE0)); @@ -554,6 +561,7 @@ static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = { .get_rptr = jpeg_v1_0_decode_ring_get_rptr, .get_wptr = jpeg_v1_0_decode_ring_get_wptr, .set_wptr = jpeg_v1_0_decode_ring_set_wptr, + .parse_cs = jpeg_v1_dec_ring_parse_cs, .emit_frame_size = 6 + 6 + /* hdp invalidate / flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + @@ -612,3 +620,69 @@ static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring) vcn_v1_0_set_pg_for_begin_use(ring, set_clocks); } + +/** + * jpeg_v1_dec_ring_parse_cs - command submission parser + * + * @parser: Command submission parser context + * @job: the job to parse + * @ib: the IB to parse + * + * Parse the command stream, return -EINVAL for invalid packet, + * 0 otherwise + */ +static int jpeg_v1_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + u32 i, reg, res, cond, type; + int ret = 0; + struct amdgpu_device *adev = parser->adev; + + for (i = 0; i < ib->length_dw ; i += 2) { + reg = CP_PACKETJ_GET_REG(ib->ptr[i]); + res = CP_PACKETJ_GET_RES(ib->ptr[i]); + cond = CP_PACKETJ_GET_COND(ib->ptr[i]); + type = CP_PACKETJ_GET_TYPE(ib->ptr[i]); + + if (res || cond != PACKETJ_CONDITION_CHECK0) /* only allow 0 for now */ + return -EINVAL; + + if (reg >= JPEG_V1_REG_RANGE_START && reg <= JPEG_V1_REG_RANGE_END) + continue; + + switch (type) { + case PACKETJ_TYPE0: + if (reg != JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_HIGH && + reg != JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_LOW && + reg != JPEG_V1_LMI_JPEG_READ_64BIT_BAR_HIGH && + reg != JPEG_V1_LMI_JPEG_READ_64BIT_BAR_LOW && + reg != JPEG_V1_REG_CTX_INDEX && + reg != JPEG_V1_REG_CTX_DATA) { + ret = -EINVAL; + } + break; + case PACKETJ_TYPE1: + if (reg != JPEG_V1_REG_CTX_DATA) + ret = -EINVAL; + break; + case PACKETJ_TYPE3: + if (reg != JPEG_V1_REG_SOFT_RESET) + ret = -EINVAL; + break; + case PACKETJ_TYPE6: + if (ib->ptr[i] != CP_PACKETJ_NOP) + ret = -EINVAL; + break; + default: + ret = -EINVAL; + } + + if (ret) { + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + break; + } + } + + return ret; +} diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h index bbf33a6a397298..9654d22e03763c 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h @@ -29,4 +29,15 @@ int jpeg_v1_0_sw_init(void *handle); void jpeg_v1_0_sw_fini(void *handle); void jpeg_v1_0_start(struct amdgpu_device *adev, int mode); +#define JPEG_V1_REG_RANGE_START 0x8000 +#define JPEG_V1_REG_RANGE_END 0x803f + +#define JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_HIGH 0x8238 +#define JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_LOW 0x8239 +#define JPEG_V1_LMI_JPEG_READ_64BIT_BAR_HIGH 0x825a +#define JPEG_V1_LMI_JPEG_READ_64BIT_BAR_LOW 0x825b +#define JPEG_V1_REG_CTX_INDEX 0x8328 +#define JPEG_V1_REG_CTX_DATA 0x8329 +#define JPEG_V1_REG_SOFT_RESET 0x83a0 + #endif /*__JPEG_V1_0_H__*/ diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c index 1c8116d75f63c4..fbe57499495ec5 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -543,11 +543,11 @@ void jpeg_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8))); amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8))); amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c index 1de79d660285d7..78aaaee492e111 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c @@ -23,6 +23,7 @@ #include "amdgpu.h" #include "amdgpu_jpeg.h" +#include "amdgpu_cs.h" #include "soc15.h" #include "soc15d.h" #include "jpeg_v4_0_3.h" @@ -769,11 +770,15 @@ static void jpeg_v4_0_3_dec_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + + if (ring->funcs->parse_cs) + amdgpu_ring_write(ring, 0); + else + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8))); amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JPEG_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8))); amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); @@ -1052,6 +1057,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_3_dec_ring_vm_funcs = { .get_rptr = jpeg_v4_0_3_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_3_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_3_dec_ring_set_wptr, + .parse_cs = jpeg_v4_0_3_dec_ring_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + @@ -1216,3 +1222,56 @@ static void jpeg_v4_0_3_set_ras_funcs(struct amdgpu_device *adev) { adev->jpeg.ras = &jpeg_v4_0_3_ras; } + +/** + * jpeg_v4_0_3_dec_ring_parse_cs - command submission parser + * + * @parser: Command submission parser context + * @job: the job to parse + * @ib: the IB to parse + * + * Parse the command stream, return -EINVAL for invalid packet, + * 0 otherwise + */ +int jpeg_v4_0_3_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + uint32_t i, reg, res, cond, type; + struct amdgpu_device *adev = parser->adev; + + for (i = 0; i < ib->length_dw ; i += 2) { + reg = CP_PACKETJ_GET_REG(ib->ptr[i]); + res = CP_PACKETJ_GET_RES(ib->ptr[i]); + cond = CP_PACKETJ_GET_COND(ib->ptr[i]); + type = CP_PACKETJ_GET_TYPE(ib->ptr[i]); + + if (res) /* only support 0 at the moment */ + return -EINVAL; + + switch (type) { + case PACKETJ_TYPE0: + if (cond != PACKETJ_CONDITION_CHECK0 || reg < JPEG_REG_RANGE_START || reg > JPEG_REG_RANGE_END) { + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + return -EINVAL; + } + break; + case PACKETJ_TYPE3: + if (cond != PACKETJ_CONDITION_CHECK3 || reg < JPEG_REG_RANGE_START || reg > JPEG_REG_RANGE_END) { + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + return -EINVAL; + } + break; + case PACKETJ_TYPE6: + if (ib->ptr[i] == CP_PACKETJ_NOP) + continue; + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + return -EINVAL; + default: + dev_err(adev->dev, "Unknown packet type %d !\n", type); + return -EINVAL; + } + } + + return 0; +} diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h index 22483dc663518f..9598eda9d71564 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h @@ -46,6 +46,12 @@ #define JRBC_DEC_EXTERNAL_REG_WRITE_ADDR 0x18000 +#define JPEG_REG_RANGE_START 0x4000 +#define JPEG_REG_RANGE_END 0x41c2 + extern const struct amdgpu_ip_block_version jpeg_v4_0_3_ip_block; +int jpeg_v4_0_3_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib); #endif /* __JPEG_V4_0_3_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index fb91b31056cae7..d25f87fb197148 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -96,7 +96,9 @@ static void mmhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR, min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); - if (adev->apu_flags & AMD_APU_IS_RAVEN2) + if (adev->apu_flags & (AMD_APU_IS_RAVEN2 | + AMD_APU_IS_RENOIR | + AMD_APU_IS_GREEN_SARDINE)) /* * Raven2 has a HW issue that it is unable to use the vram which * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c index 784c4e07747077..3d8e579d5c4e8a 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c @@ -130,6 +130,9 @@ static void mmhub_v1_8_init_system_aperture_regs(struct amdgpu_device *adev) uint64_t value; int i; + if (amdgpu_sriov_vf(adev)) + return; + inst_mask = adev->aid_mask; for_each_inst(i, inst_mask) { /* Program the AGP BAR */ @@ -139,9 +142,6 @@ static void mmhub_v1_8_init_system_aperture_regs(struct amdgpu_device *adev) WREG32_SOC15(MMHUB, i, regMC_VM_AGP_TOP, adev->gmc.agp_end >> 24); - if (amdgpu_sriov_vf(adev)) - return; - /* Program the system aperture low logical page number. */ WREG32_SOC15(MMHUB, i, regMC_VM_SYSTEM_APERTURE_LOW_ADDR, min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c index b6a8478dabf43c..737eff53f54f04 100644 --- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c @@ -442,6 +442,12 @@ static u32 navi10_ih_get_wptr(struct amdgpu_device *adev, tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl); tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c index 4038455d799845..ef368ca79a6686 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c @@ -28,6 +28,7 @@ #include "nbio/nbio_2_3_offset.h" #include "nbio/nbio_2_3_sh_mask.h" #include +#include #include #define smnPCIE_CONFIG_CNTL 0x11180044 @@ -361,7 +362,7 @@ static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev, data |= NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L0S_INACTIVITY__SHIFT; - if (pci_is_thunderbolt_attached(adev->pdev)) + if (dev_is_removable(&adev->pdev->dev)) data |= NAVI10_PCIE__LC_L1_INACTIVITY_TBT_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; else data |= NAVI10_PCIE__LC_L1_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; @@ -480,7 +481,7 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev) def = data = RREG32_PCIE(smnPCIE_LC_CNTL); data |= NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L0S_INACTIVITY__SHIFT; - if (pci_is_thunderbolt_attached(adev->pdev)) + if (dev_is_removable(&adev->pdev->dev)) data |= NAVI10_PCIE__LC_L1_INACTIVITY_TBT_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; else data |= NAVI10_PCIE__LC_L1_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index 685abf57ffddc1..977b956bf930a7 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -384,7 +384,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device else WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl); - if (!ras->disable_ras_err_cnt_harvest) { + if (ras && !ras->disable_ras_err_cnt_harvest && obj) { /* * clear error status after ras_controller_intr * according to hw team and count ue number diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c index f85eec05d21815..0a601336cf697f 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c @@ -426,6 +426,12 @@ static void nbio_v7_9_init_registers(struct amdgpu_device *adev) u32 inst_mask; int i; + if (amdgpu_sriov_vf(adev)) + adev->rmmio_remap.reg_offset = + SOC15_REG_OFFSET( + NBIO, 0, + regBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) + << 2; WREG32_SOC15(NBIO, 0, regXCC_DOORBELL_FENCE, 0xff & ~(adev->gfx.xcc_mask)); @@ -604,11 +610,6 @@ static void nbio_v7_9_handle_ras_controller_intr_no_bifring(struct amdgpu_device dev_info(adev->dev, "RAS controller interrupt triggered " "by NBIF error\n"); - - /* ras_controller_int is dedicated for nbif ras error, - * not the global interrupt for sync flood - */ - amdgpu_ras_reset_gpu(adev); } } diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index 469eed084976c7..fe1995ed13be7b 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -59,6 +59,9 @@ MODULE_FIRMWARE("amdgpu/psp_14_0_0_ta.bin"); /* Read USB-PD from LFB */ #define GFX_CMD_USB_PD_USE_LFB 0x480 +/* Retry times for vmbx ready wait */ +#define PSP_VMBX_POLLING_LIMIT 3000 + /* VBIOS gfl defines */ #define MBOX_READY_MASK 0x80000000 #define MBOX_STATUS_MASK 0x0000FFFF @@ -138,7 +141,7 @@ static int psp_v13_0_wait_for_vmbx_ready(struct psp_context *psp) struct amdgpu_device *adev = psp->adev; int retry_loop, ret; - for (retry_loop = 0; retry_loop < 70; retry_loop++) { + for (retry_loop = 0; retry_loop < PSP_VMBX_POLLING_LIMIT; retry_loop++) { /* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_33 set to 1 */ ret = psp_wait_for( @@ -158,14 +161,18 @@ static int psp_v13_0_wait_for_vmbx_ready(struct psp_context *psp) static int psp_v13_0_wait_for_bootloader(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; - int retry_loop, ret; + int retry_loop, retry_cnt, ret; + retry_cnt = + (adev->ip_versions[MP0_HWIP][0] == IP_VERSION(13, 0, 6)) ? + PSP_VMBX_POLLING_LIMIT : + 10; /* Wait for bootloader to signify that it is ready having bit 31 of * C2PMSG_35 set to 1. All other bits are expected to be cleared. * If there is an error in processing command, bits[7:0] will be set. * This is applicable for PSP v13.0.6 and newer. */ - for (retry_loop = 0; retry_loop < 10; retry_loop++) { + for (retry_loop = 0; retry_loop < retry_cnt; retry_loop++) { ret = psp_wait_for( psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35), 0x80000000, 0xffffffff, false); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index cd37f45e01a119..0ba9a3d3312f5a 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -2027,10 +2027,13 @@ static int sdma_v4_0_process_trap_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) { - uint32_t instance; + int instance; DRM_DEBUG("IH: SDMA trap\n"); instance = sdma_v4_0_irq_id_to_seq(entry->client_id); + if (instance < 0) + return instance; + switch (entry->ring_id) { case 0: amdgpu_fence_process(&adev->sdma.instance[instance].ring); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c index f413898dda37db..4e8d5e6a65e410 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c @@ -365,7 +365,8 @@ static void sdma_v4_4_2_ring_emit_hdp_flush(struct amdgpu_ring *ring) u32 ref_and_mask = 0; const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg; - ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me; + ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 + << (ring->me % adev->sdma.num_inst_per_aid); sdma_v4_4_2_wait_reg_mem(ring, 0, 1, adev->nbio.funcs->get_hdp_flush_done_offset(adev), @@ -1612,19 +1613,9 @@ static int sdma_v4_4_2_set_ecc_irq_state(struct amdgpu_device *adev, u32 sdma_cntl; sdma_cntl = RREG32_SDMA(type, regSDMA_CNTL); - switch (state) { - case AMDGPU_IRQ_STATE_DISABLE: - sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, - DRAM_ECC_INT_ENABLE, 0); - WREG32_SDMA(type, regSDMA_CNTL, sdma_cntl); - break; - /* sdma ecc interrupt is enabled by default - * driver doesn't need to do anything to - * enable the interrupt */ - case AMDGPU_IRQ_STATE_ENABLE: - default: - break; - } + sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, DRAM_ECC_INT_ENABLE, + state == AMDGPU_IRQ_STATE_ENABLE ? 1 : 0); + WREG32_SDMA(type, regSDMA_CNTL, sdma_cntl); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 2b3ebebc4299c0..47d4840c6275c7 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -188,6 +188,14 @@ static void sdma_v5_2_ring_set_wptr(struct amdgpu_ring *ring) DRM_DEBUG("calling WDOORBELL64(0x%08x, 0x%016llx)\n", ring->doorbell_index, ring->wptr << 2); WDOORBELL64(ring->doorbell_index, ring->wptr << 2); + /* SDMA seems to miss doorbells sometimes when powergating kicks in. + * Updating the wptr directly will wake it. This is only safe because + * we disallow gfxoff in begin_use() and then allow it again in end_use(). + */ + WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR), + lower_32_bits(ring->wptr << 2)); + WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI), + upper_32_bits(ring->wptr << 2)); } else { DRM_DEBUG("Not using doorbell -- " "mmSDMA%i_GFX_RB_WPTR == 0x%08x " @@ -292,17 +300,21 @@ static void sdma_v5_2_ring_emit_hdp_flush(struct amdgpu_ring *ring) u32 ref_and_mask = 0; const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg; - ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me; - - amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) | - SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) | - SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */ - amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2); - amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2); - amdgpu_ring_write(ring, ref_and_mask); /* reference */ - amdgpu_ring_write(ring, ref_and_mask); /* mask */ - amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | - SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */ + if (ring->me > 1) { + amdgpu_asic_flush_hdp(adev, ring); + } else { + ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me; + + amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) | + SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) | + SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */ + amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2); + amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2); + amdgpu_ring_write(ring, ref_and_mask); /* reference */ + amdgpu_ring_write(ring, ref_and_mask); /* mask */ + amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | + SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */ + } } /** @@ -1651,6 +1663,36 @@ static void sdma_v5_2_get_clockgating_state(void *handle, u64 *flags) *flags |= AMD_CG_SUPPORT_SDMA_LS; } +static void sdma_v5_2_ring_begin_use(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + + /* SDMA 5.2.3 (RMB) FW doesn't seem to properly + * disallow GFXOFF in some cases leading to + * hangs in SDMA. Disallow GFXOFF while SDMA is active. + * We can probably just limit this to 5.2.3, + * but it shouldn't hurt for other parts since + * this GFXOFF will be disallowed anyway when SDMA is + * active, this just makes it explicit. + * sdma_v5_2_ring_set_wptr() takes advantage of this + * to update the wptr because sometimes SDMA seems to miss + * doorbells when entering PG. If you remove this, update + * sdma_v5_2_ring_set_wptr() as well! + */ + amdgpu_gfx_off_ctrl(adev, false); +} + +static void sdma_v5_2_ring_end_use(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + + /* SDMA 5.2.3 (RMB) FW doesn't seem to properly + * disallow GFXOFF in some cases leading to + * hangs in SDMA. Allow GFXOFF when SDMA is complete. + */ + amdgpu_gfx_off_ctrl(adev, true); +} + const struct amd_ip_funcs sdma_v5_2_ip_funcs = { .name = "sdma_v5_2", .early_init = sdma_v5_2_early_init, @@ -1698,6 +1740,8 @@ static const struct amdgpu_ring_funcs sdma_v5_2_ring_funcs = { .test_ib = sdma_v5_2_ring_test_ib, .insert_nop = sdma_v5_2_ring_insert_nop, .pad_ib = sdma_v5_2_ring_pad_ib, + .begin_use = sdma_v5_2_ring_begin_use, + .end_use = sdma_v5_2_ring_end_use, .emit_wreg = sdma_v5_2_ring_emit_wreg, .emit_reg_wait = sdma_v5_2_ring_emit_reg_wait, .emit_reg_write_reg_wait = sdma_v5_2_ring_emit_reg_write_reg_wait, diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c index 9a24f17a57502e..cada9f300a7f51 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c @@ -119,6 +119,12 @@ static u32 si_ih_get_wptr(struct amdgpu_device *adev, tmp = RREG32(IH_RB_CNTL); tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; WREG32(IH_RB_CNTL, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; + WREG32(IH_RB_CNTL, tmp); } return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c b/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c index 8b8086d5c864bc..896c7e434d3bc8 100644 --- a/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c +++ b/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c @@ -93,7 +93,7 @@ static int sienna_cichlid_mode2_suspend_ip(struct amdgpu_device *adev) adev->ip_blocks[i].status.hw = false; } - return r; + return 0; } static int diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c b/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c index ae29620b1ea405..a7cef33a2a3da6 100644 --- a/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c +++ b/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c @@ -92,7 +92,7 @@ static int smu_v13_0_10_mode2_suspend_ip(struct amdgpu_device *adev) adev->ip_blocks[i].status.hw = false; } - return r; + return 0; } static int diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index f5be40d7ba3679..a41ed67ea9feaf 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -325,7 +325,8 @@ static u32 soc15_get_xclk(struct amdgpu_device *adev) u32 reference_clock = adev->clock.spll.reference_freq; if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 0) || - adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 1)) + adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 1) || + adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 6)) return 10000; if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(10, 0, 0) || adev->ip_versions[MP1_HWIP][0] == IP_VERSION(10, 0, 1)) @@ -573,11 +574,34 @@ soc15_asic_reset_method(struct amdgpu_device *adev) return AMD_RESET_METHOD_MODE1; } +static bool soc15_need_reset_on_resume(struct amdgpu_device *adev) +{ + u32 sol_reg; + + sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81); + + /* Will reset for the following suspend abort cases. + * 1) Only reset limit on APU side, dGPU hasn't checked yet. + * 2) S3 suspend abort and TOS already launched. + */ + if (adev->flags & AMD_IS_APU && adev->in_s3 && + !adev->suspend_complete && + sol_reg) + return true; + + return false; +} + static int soc15_asic_reset(struct amdgpu_device *adev) { /* original raven doesn't have full asic reset */ - if ((adev->apu_flags & AMD_APU_IS_RAVEN) || - (adev->apu_flags & AMD_APU_IS_RAVEN2)) + /* On the latest Raven, the GPU reset can be performed + * successfully. So now, temporarily enable it for the + * S3 suspend abort case. + */ + if (((adev->apu_flags & AMD_APU_IS_RAVEN) || + (adev->apu_flags & AMD_APU_IS_RAVEN2)) && + !soc15_need_reset_on_resume(adev)) return 0; switch (soc15_asic_reset_method(adev)) { @@ -1159,6 +1183,11 @@ static int soc15_common_early_init(void *handle) AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_JPEG; adev->external_rev_id = adev->rev_id + 0x46; + /* GC 9.4.3 uses MMIO register region hole at a different offset */ + if (!amdgpu_sriov_vf(adev)) { + adev->rmmio_remap.reg_offset = 0x1A000; + adev->rmmio_remap.bus_addr = adev->rmmio_base + 0x1A000; + } break; default: /* FIXME: not supported yet */ @@ -1294,6 +1323,10 @@ static int soc15_common_resume(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (soc15_need_reset_on_resume(adev)) { + dev_info(adev->dev, "S3 suspend abort case, let's reset ASIC.\n"); + soc15_asic_reset(adev); + } return soc15_common_hw_init(adev); } @@ -1416,9 +1449,11 @@ static void soc15_common_get_clockgating_state(void *handle, u64 *flags) if (amdgpu_sriov_vf(adev)) *flags = 0; - adev->nbio.funcs->get_clockgating_state(adev, flags); + if (adev->nbio.funcs && adev->nbio.funcs->get_clockgating_state) + adev->nbio.funcs->get_clockgating_state(adev, flags); - adev->hdp.funcs->get_clock_gating_state(adev, flags); + if (adev->hdp.funcs && adev->hdp.funcs->get_clock_gating_state) + adev->hdp.funcs->get_clock_gating_state(adev, flags); if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(13, 0, 2)) { @@ -1434,9 +1469,11 @@ static void soc15_common_get_clockgating_state(void *handle, u64 *flags) } /* AMD_CG_SUPPORT_ROM_MGCG */ - adev->smuio.funcs->get_clock_gating_state(adev, flags); + if (adev->smuio.funcs && adev->smuio.funcs->get_clock_gating_state) + adev->smuio.funcs->get_clock_gating_state(adev, flags); - adev->df.funcs->get_clockgating_state(adev, flags); + if (adev->df.funcs && adev->df.funcs->get_clockgating_state) + adev->df.funcs->get_clockgating_state(adev, flags); } static int soc15_common_set_powergating_state(void *handle, diff --git a/drivers/gpu/drm/amd/amdgpu/soc15d.h b/drivers/gpu/drm/amd/amdgpu/soc15d.h index 2357ff39323f05..e74e1983da53aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15d.h +++ b/drivers/gpu/drm/amd/amdgpu/soc15d.h @@ -76,6 +76,12 @@ ((cond & 0xF) << 24) | \ ((type & 0xF) << 28)) +#define CP_PACKETJ_NOP 0x60000000 +#define CP_PACKETJ_GET_REG(x) ((x) & 0x3FFFF) +#define CP_PACKETJ_GET_RES(x) (((x) >> 18) & 0x3F) +#define CP_PACKETJ_GET_COND(x) (((x) >> 24) & 0xF) +#define CP_PACKETJ_GET_TYPE(x) (((x) >> 28) & 0xF) + /* Packet 3 types */ #define PACKET3_NOP 0x10 #define PACKET3_SET_BASE 0x11 diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 8b2ff2b281b0ad..4712ffc0a482c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -50,13 +50,13 @@ static const struct amd_ip_funcs soc21_common_ip_funcs; /* SOC21 */ static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] = { {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, }; static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] = { {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)}, }; static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode_vcn0 = { @@ -449,10 +449,8 @@ static bool soc21_need_full_reset(struct amdgpu_device *adev) { switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(11, 0, 0): - return amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC); case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): - return false; default: return true; } @@ -804,10 +802,35 @@ static int soc21_common_suspend(void *handle) return soc21_common_hw_fini(adev); } +static bool soc21_need_reset_on_resume(struct amdgpu_device *adev) +{ + u32 sol_reg1, sol_reg2; + + /* Will reset for the following suspend abort cases. + * 1) Only reset dGPU side. + * 2) S3 suspend got aborted and TOS is active. + */ + if (!(adev->flags & AMD_IS_APU) && adev->in_s3 && + !adev->suspend_complete) { + sol_reg1 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81); + msleep(100); + sol_reg2 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81); + + return (sol_reg1 != sol_reg2); + } + + return false; +} + static int soc21_common_resume(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (soc21_need_reset_on_resume(adev)) { + dev_info(adev->dev, "S3 suspend aborted, resetting..."); + soc21_asic_reset(adev); + } + return soc21_common_hw_init(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c index 917707bba7f362..450b6e83150914 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c @@ -219,6 +219,12 @@ static u32 tonga_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32(mmIH_RB_CNTL, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32(mmIH_RB_CNTL, tmp); + out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c index d364c6dd152c33..bf68e18e3824b8 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c @@ -373,6 +373,12 @@ static u32 vega10_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c index dbc99536440f2f..131e7b769519c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c @@ -421,6 +421,12 @@ static u32 vega20_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index c37f1fcd2165b5..19d46be6394295 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -417,7 +417,7 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p, err_create_queue: if (wptr_bo) - amdgpu_amdkfd_free_gtt_mem(dev->adev, wptr_bo); + amdgpu_amdkfd_free_gtt_mem(dev->adev, (void **)&wptr_bo); err_wptr_map_gart: err_bind_process: err_pdd: @@ -778,8 +778,8 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, * nodes, but not more than args->num_of_nodes as that is * the amount of memory allocated by user */ - pa = kzalloc((sizeof(struct kfd_process_device_apertures) * - args->num_of_nodes), GFP_KERNEL); + pa = kcalloc(args->num_of_nodes, sizeof(struct kfd_process_device_apertures), + GFP_KERNEL); if (!pa) return -ENOMEM; @@ -1138,7 +1138,7 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep, goto err_unlock; } offset = dev->adev->rmmio_remap.bus_addr; - if (!offset) { + if (!offset || (PAGE_SIZE > 4096)) { err = -ENOMEM; goto err_unlock; } @@ -1432,17 +1432,23 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, goto sync_memory_failed; } } - mutex_unlock(&p->mutex); - if (flush_tlb) { - /* Flush TLBs after waiting for the page table updates to complete */ - for (i = 0; i < args->n_devices; i++) { - peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); - if (WARN_ON_ONCE(!peer_pdd)) - continue; + /* Flush TLBs after waiting for the page table updates to complete */ + for (i = 0; i < args->n_devices; i++) { + peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); + if (WARN_ON_ONCE(!peer_pdd)) + continue; + if (flush_tlb) kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); - } + + /* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */ + err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv); + if (err) + goto sync_memory_failed; } + + mutex_unlock(&p->mutex); + kfree(devices_arr); return 0; @@ -1516,7 +1522,7 @@ static int kfd_ioctl_get_dmabuf_info(struct file *filep, /* Find a KFD GPU device that supports the get_dmabuf_info query */ for (i = 0; kfd_topology_enum_kfd_devices(i, &dev) == 0; i++) - if (dev) + if (dev && !kfd_devcgroup_check_permission(dev)) break; if (!dev) return -EINVAL; @@ -1538,7 +1544,7 @@ static int kfd_ioctl_get_dmabuf_info(struct file *filep, if (xcp_id >= 0) args->gpu_id = dmabuf_adev->kfd.dev->nodes[xcp_id]->id; else - args->gpu_id = dmabuf_adev->kfd.dev->nodes[0]->id; + args->gpu_id = dev->id; args->flags = flags; /* Copy metadata buffer to user mode */ @@ -2307,7 +2313,7 @@ static int criu_restore_memory_of_gpu(struct kfd_process_device *pdd, return -EINVAL; } offset = pdd->dev->adev->rmmio_remap.bus_addr; - if (!offset) { + if (!offset || (PAGE_SIZE > 4096)) { pr_err("amdgpu_amdkfd_get_mmio_remap_phys_addr failed\n"); return -ENOMEM; } @@ -3348,6 +3354,9 @@ static int kfd_mmio_mmap(struct kfd_node *dev, struct kfd_process *process, if (vma->vm_end - vma->vm_start != PAGE_SIZE) return -EINVAL; + if (PAGE_SIZE > 4096) + return -EINVAL; + address = dev->adev->rmmio_remap.bus_addr; vm_flags_set(vma, VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE | diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.h b/drivers/gpu/drm/amd/amdkfd/kfd_crat.h index 74c2d7a0d62857..2f54ee08f26961 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.h @@ -42,8 +42,6 @@ #define CRAT_OEMTABLEID_LENGTH 8 #define CRAT_RESERVED_LENGTH 6 -#define CRAT_OEMID_64BIT_MASK ((1ULL << (CRAT_OEMID_LENGTH * 8)) - 1) - /* Compute Unit flags */ #define COMPUTE_UNIT_CPU (1 << 0) /* Create Virtual CRAT for CPU */ #define COMPUTE_UNIT_GPU (1 << 1) /* Create Virtual CRAT for GPU */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c index 9ec750666382fe..94aaf2fc556ca1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c @@ -103,7 +103,8 @@ void debug_event_write_work_handler(struct work_struct *work) struct kfd_process, debug_event_workarea); - kernel_write(process->dbg_ev_file, &write_data, 1, &pos); + if (process->debug_trap_enabled && process->dbg_ev_file) + kernel_write(process->dbg_ev_file, &write_data, 1, &pos); } /* update process/device/queue exception status, write to descriptor @@ -645,6 +646,7 @@ int kfd_dbg_trap_disable(struct kfd_process *target) else if (target->runtime_info.runtime_state != DEBUG_RUNTIME_STATE_DISABLED) target->runtime_info.runtime_state = DEBUG_RUNTIME_STATE_ENABLED; + cancel_work_sync(&target->debug_event_workarea); fput(target->dbg_ev_file); target->dbg_ev_file = NULL; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 93ce181eb3baa0..9d0b0bf70ad1ea 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -402,15 +402,8 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf) f2g = &gfx_v11_kfd2kgd; break; case IP_VERSION(11, 0, 3): - if ((adev->pdev->device == 0x7460 && - adev->pdev->revision == 0x00) || - (adev->pdev->device == 0x7461 && - adev->pdev->revision == 0x00)) - /* Note: Compiler version is 11.0.5 while HW version is 11.0.3 */ - gfx_target_version = 110005; - else - /* Note: Compiler version is 11.0.1 while HW version is 11.0.3 */ - gfx_target_version = 110001; + /* Note: Compiler version is 11.0.1 while HW version is 11.0.3 */ + gfx_target_version = 110001; f2g = &gfx_v11_kfd2kgd; break; default: @@ -845,7 +838,7 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, kfd_doorbell_error: kfd_gtt_sa_fini(kfd); kfd_gtt_sa_init_error: - amdgpu_amdkfd_free_gtt_mem(kfd->adev, kfd->gtt_mem); + amdgpu_amdkfd_free_gtt_mem(kfd->adev, &kfd->gtt_mem); alloc_gtt_mem_failure: dev_err(kfd_device, "device %x:%x NOT added due to errors\n", @@ -863,7 +856,7 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd) kfd_doorbell_fini(kfd); ida_destroy(&kfd->doorbell_ida); kfd_gtt_sa_fini(kfd); - amdgpu_amdkfd_free_gtt_mem(kfd->adev, kfd->gtt_mem); + amdgpu_amdkfd_free_gtt_mem(kfd->adev, &kfd->gtt_mem); } kfree(kfd); @@ -935,7 +928,6 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm) { struct kfd_node *node; int i; - int count; if (!kfd->init_complete) return; @@ -943,12 +935,10 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm) /* for runtime suspend, skip locking kfd */ if (!run_pm) { mutex_lock(&kfd_processes_mutex); - count = ++kfd_locked; - mutex_unlock(&kfd_processes_mutex); - /* For first KFD device suspend all the KFD processes */ - if (count == 1) + if (++kfd_locked == 1) kfd_suspend_all_processes(); + mutex_unlock(&kfd_processes_mutex); } for (i = 0; i < kfd->num_nodes; i++) { @@ -959,7 +949,7 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm) int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm) { - int ret, count, i; + int ret, i; if (!kfd->init_complete) return 0; @@ -973,12 +963,10 @@ int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm) /* for runtime resume, skip unlocking kfd */ if (!run_pm) { mutex_lock(&kfd_processes_mutex); - count = --kfd_locked; - mutex_unlock(&kfd_processes_mutex); - - WARN_ONCE(count < 0, "KFD suspend / resume ref. error"); - if (count == 0) + if (--kfd_locked == 0) ret = kfd_resume_all_processes(); + WARN_ONCE(kfd_locked < 0, "KFD suspend / resume ref. error"); + mutex_unlock(&kfd_processes_mutex); } return ret; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 0d3d538b64ebc3..4d9a406925e189 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -407,7 +407,8 @@ static int allocate_doorbell(struct qcm_process_device *qpd, q->properties.doorbell_off = amdgpu_doorbell_index_on_bar(dev->adev, qpd->proc_doorbells, - q->doorbell_id); + q->doorbell_id, + dev->kfd->device_info.doorbell_size); return 0; } @@ -1979,6 +1980,7 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, pr_err("HIQ MQD's queue_doorbell_id0 is not 0, Queue preemption time out\n"); while (halt_if_hws_hang) schedule(); + kfd_hws_hang(dqm); return -ETIME; } @@ -2608,7 +2610,7 @@ static void deallocate_hiq_sdma_mqd(struct kfd_node *dev, { WARN(!mqd, "No hiq sdma mqd trunk to free"); - amdgpu_amdkfd_free_gtt_mem(dev->adev, mqd->gtt_mem); + amdgpu_amdkfd_free_gtt_mem(dev->adev, &mqd->gtt_mem); } void device_queue_manager_uninit(struct device_queue_manager *dqm) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c index 7b38537c7c99bd..05c74887fd6fda 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c @@ -161,7 +161,10 @@ void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd, if (inx >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) return NULL; - *doorbell_off = amdgpu_doorbell_index_on_bar(kfd->adev, kfd->doorbells, inx); + *doorbell_off = amdgpu_doorbell_index_on_bar(kfd->adev, + kfd->doorbells, + inx, + kfd->device_info.doorbell_size); inx *= 2; pr_debug("Get kernel queue doorbell\n" @@ -240,7 +243,10 @@ phys_addr_t kfd_get_process_doorbells(struct kfd_process_device *pdd) return 0; } - first_db_index = amdgpu_doorbell_index_on_bar(adev, pdd->qpd.proc_doorbells, 0); + first_db_index = amdgpu_doorbell_index_on_bar(adev, + pdd->qpd.proc_doorbells, + 0, + pdd->dev->kfd->device_info.doorbell_size); return adev->doorbell.base + first_db_index * sizeof(uint32_t); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c index 62b205dac63a05..6604a3f99c5ecf 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c @@ -330,12 +330,6 @@ static void kfd_init_apertures_vi(struct kfd_process_device *pdd, uint8_t id) pdd->gpuvm_limit = pdd->dev->kfd->shared_resources.gpuvm_size - 1; - /* dGPUs: the reserved space for kernel - * before SVM - */ - pdd->qpd.cwsr_base = SVM_CWSR_BASE; - pdd->qpd.ib_base = SVM_IB_BASE; - pdd->scratch_base = MAKE_SCRATCH_APP_BASE_VI(); pdd->scratch_limit = MAKE_SCRATCH_APP_LIMIT(pdd->scratch_base); } @@ -345,18 +339,18 @@ static void kfd_init_apertures_v9(struct kfd_process_device *pdd, uint8_t id) pdd->lds_base = MAKE_LDS_APP_BASE_V9(); pdd->lds_limit = MAKE_LDS_APP_LIMIT(pdd->lds_base); - pdd->gpuvm_base = PAGE_SIZE; + /* Raven needs SVM to support graphic handle, etc. Leave the small + * reserved space before SVM on Raven as well, even though we don't + * have to. + * Set gpuvm_base and gpuvm_limit to CANONICAL addresses so that they + * are used in Thunk to reserve SVM. + */ + pdd->gpuvm_base = SVM_USER_BASE; pdd->gpuvm_limit = pdd->dev->kfd->shared_resources.gpuvm_size - 1; pdd->scratch_base = MAKE_SCRATCH_APP_BASE_V9(); pdd->scratch_limit = MAKE_SCRATCH_APP_LIMIT(pdd->scratch_base); - - /* - * Place TBA/TMA on opposite side of VM hole to prevent - * stray faults from triggering SVM on these pages. - */ - pdd->qpd.cwsr_base = pdd->dev->kfd->shared_resources.gpuvm_size; } int kfd_init_apertures(struct kfd_process *process) @@ -413,6 +407,12 @@ int kfd_init_apertures(struct kfd_process *process) return -EINVAL; } } + + /* dGPUs: the reserved space for kernel + * before SVM + */ + pdd->qpd.cwsr_base = SVM_CWSR_BASE; + pdd->qpd.ib_base = SVM_IB_BASE; } dev_dbg(kfd_device, "node id %u\n", id); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c index c7991e07b6be56..f85ca6cb90f56c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c @@ -268,7 +268,7 @@ static void event_interrupt_wq_v10(struct kfd_node *dev, SQ_INTERRUPT_WORD_WAVE_CTXID1, ENCODING); switch (encoding) { case SQ_INTERRUPT_WORD_ENCODING_AUTO: - pr_debug( + pr_debug_ratelimited( "sq_intr: auto, se %d, ttrace %d, wlt %d, ttrac_buf0_full %d, ttrac_buf1_full %d, ttrace_utc_err %d\n", REG_GET_FIELD(context_id1, SQ_INTERRUPT_WORD_AUTO_CTXID1, SE_ID), @@ -284,7 +284,7 @@ static void event_interrupt_wq_v10(struct kfd_node *dev, THREAD_TRACE_UTC_ERROR)); break; case SQ_INTERRUPT_WORD_ENCODING_INST: - pr_debug("sq_intr: inst, se %d, data 0x%x, sa %d, priv %d, wave_id %d, simd_id %d, wgp_id %d\n", + pr_debug_ratelimited("sq_intr: inst, se %d, data 0x%x, sa %d, priv %d, wave_id %d, simd_id %d, wgp_id %d\n", REG_GET_FIELD(context_id1, SQ_INTERRUPT_WORD_WAVE_CTXID1, SE_ID), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID0, @@ -310,7 +310,7 @@ static void event_interrupt_wq_v10(struct kfd_node *dev, case SQ_INTERRUPT_WORD_ENCODING_ERROR: sq_intr_err_type = REG_GET_FIELD(context_id0, KFD_CTXID0, ERR_TYPE); - pr_warn("sq_intr: error, se %d, data 0x%x, sa %d, priv %d, wave_id %d, simd_id %d, wgp_id %d, err_type %d\n", + pr_warn_ratelimited("sq_intr: error, se %d, data 0x%x, sa %d, priv %d, wave_id %d, simd_id %d, wgp_id %d, err_type %d\n", REG_GET_FIELD(context_id1, SQ_INTERRUPT_WORD_WAVE_CTXID1, SE_ID), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID0, @@ -336,7 +336,8 @@ static void event_interrupt_wq_v10(struct kfd_node *dev, break; } kfd_signal_event_interrupt(pasid, context_id0 & 0x7fffff, 23); - } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) { + } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE && + KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) { kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_DEBUG_DOORBELL_ID(context_id0), KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c index f933bd231fb9ce..3ca9c160da7c23 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c @@ -150,7 +150,7 @@ enum SQ_INTERRUPT_ERROR_TYPE { static void print_sq_intr_info_auto(uint32_t context_id0, uint32_t context_id1) { - pr_debug( + pr_debug_ratelimited( "sq_intr: auto, ttrace %d, wlt %d, ttrace_buf_full %d, reg_tms %d, cmd_tms %d, host_cmd_ovf %d, host_reg_ovf %d, immed_ovf %d, ttrace_utc_err %d\n", REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID0, THREAD_TRACE), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID0, WLT), @@ -165,7 +165,7 @@ static void print_sq_intr_info_auto(uint32_t context_id0, uint32_t context_id1) static void print_sq_intr_info_inst(uint32_t context_id0, uint32_t context_id1) { - pr_debug( + pr_debug_ratelimited( "sq_intr: inst, data 0x%08x, sh %d, priv %d, wave_id %d, simd_id %d, wgp_id %d\n", REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID0, DATA), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID0, SH_ID), @@ -177,7 +177,7 @@ static void print_sq_intr_info_inst(uint32_t context_id0, uint32_t context_id1) static void print_sq_intr_info_error(uint32_t context_id0, uint32_t context_id1) { - pr_warn( + pr_warn_ratelimited( "sq_intr: error, detail 0x%08x, type %d, sh %d, priv %d, wave_id %d, simd_id %d, wgp_id %d\n", REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_ERROR_CTXID0, DETAIL), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_ERROR_CTXID0, TYPE), @@ -325,7 +325,8 @@ static void event_interrupt_wq_v11(struct kfd_node *dev, /* CP */ if (source_id == SOC15_INTSRC_CP_END_OF_PIPE) kfd_signal_event_interrupt(pasid, context_id0, 32); - else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) + else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE && + KFD_DBG_EC_TYPE_IS_PACKET(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0))) kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_CTXID0_DOORBELL_ID(context_id0), KFD_EC_MASK(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c index 830396b1c3b145..8a6729939ae55f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c @@ -333,7 +333,7 @@ static void event_interrupt_wq_v9(struct kfd_node *dev, encoding = REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, ENCODING); switch (encoding) { case SQ_INTERRUPT_WORD_ENCODING_AUTO: - pr_debug( + pr_debug_ratelimited( "sq_intr: auto, se %d, ttrace %d, wlt %d, ttrac_buf_full %d, reg_tms %d, cmd_tms %d, host_cmd_ovf %d, host_reg_ovf %d, immed_ovf %d, ttrace_utc_err %d\n", REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, SE_ID), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, THREAD_TRACE), @@ -347,7 +347,7 @@ static void event_interrupt_wq_v9(struct kfd_node *dev, REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, THREAD_TRACE_UTC_ERROR)); break; case SQ_INTERRUPT_WORD_ENCODING_INST: - pr_debug("sq_intr: inst, se %d, data 0x%x, sh %d, priv %d, wave_id %d, simd_id %d, cu_id %d, intr_data 0x%x\n", + pr_debug_ratelimited("sq_intr: inst, se %d, data 0x%x, sh %d, priv %d, wave_id %d, simd_id %d, cu_id %d, intr_data 0x%x\n", REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SE_ID), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, DATA), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SH_ID), @@ -366,7 +366,7 @@ static void event_interrupt_wq_v9(struct kfd_node *dev, break; case SQ_INTERRUPT_WORD_ENCODING_ERROR: sq_intr_err = REG_GET_FIELD(sq_int_data, KFD_SQ_INT_DATA, ERR_TYPE); - pr_warn("sq_intr: error, se %d, data 0x%x, sh %d, priv %d, wave_id %d, simd_id %d, cu_id %d, err_type %d\n", + pr_warn_ratelimited("sq_intr: error, se %d, data 0x%x, sh %d, priv %d, wave_id %d, simd_id %d, cu_id %d, err_type %d\n", REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SE_ID), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, DATA), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SH_ID), @@ -385,7 +385,8 @@ static void event_interrupt_wq_v9(struct kfd_node *dev, break; } kfd_signal_event_interrupt(pasid, sq_int_data, 24); - } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) { + } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE && + KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) { kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_DEBUG_DOORBELL_ID(context_id0), KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 7d82c7da223ab8..3263b5fa182d20 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -516,10 +516,19 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, start = prange->start << PAGE_SHIFT; end = (prange->last + 1) << PAGE_SHIFT; + r = amdgpu_amdkfd_reserve_mem_limit(node->adev, + prange->npages * PAGE_SIZE, + KFD_IOC_ALLOC_MEM_FLAGS_VRAM, + node->xcp ? node->xcp->id : 0); + if (r) { + dev_dbg(node->adev->dev, "failed to reserve VRAM, r: %ld\n", r); + return -ENOSPC; + } + r = svm_range_vram_node_new(node, prange, true); if (r) { dev_dbg(node->adev->dev, "fail %ld to alloc vram\n", r); - return r; + goto out; } ttm_res_offset = prange->offset << PAGE_SHIFT; @@ -549,6 +558,11 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, svm_range_vram_node_free(prange); } +out: + amdgpu_amdkfd_unreserve_mem_limit(node->adev, + prange->npages * PAGE_SIZE, + KFD_IOC_ALLOC_MEM_FLAGS_VRAM, + node->xcp ? node->xcp->id : 0); return r < 0 ? r : 0; } @@ -1021,7 +1035,7 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev) } else { res = devm_request_free_mem_region(adev->dev, &iomem_resource, size); if (IS_ERR(res)) - return -ENOMEM; + return PTR_ERR(res); pgmap->range.start = res->start; pgmap->range.end = res->end; pgmap->type = MEMORY_DEVICE_PRIVATE; @@ -1037,10 +1051,10 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev) r = devm_memremap_pages(adev->dev, pgmap); if (IS_ERR(r)) { pr_err("failed to register HMM device memory\n"); - /* Disable SVM support capability */ - pgmap->type = 0; if (pgmap->type == MEMORY_DEVICE_PRIVATE) devm_release_mem_region(adev->dev, res->start, resource_size(res)); + /* Disable SVM support capability */ + pgmap->type = 0; return PTR_ERR(r); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c index 447829c22295c6..4c3f379803117e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c @@ -223,7 +223,7 @@ void kfd_free_mqd_cp(struct mqd_manager *mm, void *mqd, struct kfd_mem_obj *mqd_mem_obj) { if (mqd_mem_obj->gtt_mem) { - amdgpu_amdkfd_free_gtt_mem(mm->dev->adev, mqd_mem_obj->gtt_mem); + amdgpu_amdkfd_free_gtt_mem(mm->dev->adev, &mqd_mem_obj->gtt_mem); kfree(mqd_mem_obj); } else { kfd_gtt_sa_free(mm->dev, mqd_mem_obj); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c index 8b7fed91352696..22cbfa1bdaddb9 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c @@ -170,6 +170,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; m->cp_hqd_pq_control |= ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1; + m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control); m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c index 15277f1d5cf0a9..d722cbd317834a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c @@ -224,6 +224,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; m->cp_hqd_pq_control |= ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1; + m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control); m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c index 42d881809dc70e..1ac66c5337df47 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c @@ -686,7 +686,7 @@ static void update_mqd_v9_4_3(struct mqd_manager *mm, void *mqd, m = get_mqd(mqd + size * xcc); update_mqd(mm, m, q, minfo); - update_cu_mask(mm, mqd, minfo, xcc); + update_cu_mask(mm, m, minfo, xcc); if (q->format == KFD_QUEUE_FORMAT_AQL) { switch (xcc) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index fa24e1852493dc..67204c3dfbb8f6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -971,7 +971,7 @@ struct kfd_process { struct work_struct debug_event_workarea; /* Tracks debug per-vmid request for debug flags */ - bool dbg_flags; + u32 dbg_flags; atomic_t poison; /* Queues are in paused stated because we are in the process of doing a CRIU checkpoint */ @@ -1128,7 +1128,7 @@ static inline struct kfd_node *kfd_node_by_irq_ids(struct amdgpu_device *adev, struct kfd_dev *dev = adev->kfd.dev; uint32_t i; - if (adev->ip_versions[GC_HWIP][0] != IP_VERSION(9, 4, 3)) + if (KFD_GC_VERSION(dev) != IP_VERSION(9, 4, 3)) return dev->nodes[0]; for (i = 0; i < dev->num_nodes; i++) @@ -1466,7 +1466,7 @@ void kfd_flush_tlb(struct kfd_process_device *pdd, enum TLB_FLUSH_TYPE type); static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev) { - return KFD_GC_VERSION(dev) > IP_VERSION(9, 4, 2) || + return KFD_GC_VERSION(dev) >= IP_VERSION(9, 4, 2) || (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && dev->sdma_fw_version >= 18) || KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0); } @@ -1482,10 +1482,15 @@ void kfd_dec_compute_active(struct kfd_node *dev); /* Cgroup Support */ /* Check with device cgroup if @kfd device is accessible */ -static inline int kfd_devcgroup_check_permission(struct kfd_node *kfd) +static inline int kfd_devcgroup_check_permission(struct kfd_node *node) { #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) - struct drm_device *ddev = adev_to_drm(kfd->adev); + struct drm_device *ddev; + + if (node->xcp) + ddev = node->xcp->ddev; + else + ddev = adev_to_drm(node->adev); return devcgroup_check_permission(DEVCG_DEV_CHAR, DRM_MAJOR, ddev->render->index, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index fbf053001af978..43f520b3796700 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -818,9 +818,9 @@ struct kfd_process *kfd_create_process(struct task_struct *thread) mutex_lock(&kfd_processes_mutex); if (kfd_is_locked()) { - mutex_unlock(&kfd_processes_mutex); pr_debug("KFD is locked! Cannot create process"); - return ERR_PTR(-EINVAL); + process = ERR_PTR(-EINVAL); + goto out; } /* A prior open of /dev/kfd could have already created the process. */ @@ -828,6 +828,14 @@ struct kfd_process *kfd_create_process(struct task_struct *thread) if (process) { pr_debug("Process already found\n"); } else { + /* If the process just called exec(3), it is possible that the + * cleanup of the kfd_process (following the release of the mm + * of the old process image) is still in the cleanup work queue. + * Make sure to drain any job before trying to recreate any + * resource for this process. + */ + flush_workqueue(kfd_process_wq); + process = create_process(thread); if (IS_ERR(process)) goto out; @@ -1039,7 +1047,7 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) if (pdd->dev->kfd->shared_resources.enable_mes) amdgpu_amdkfd_free_gtt_mem(pdd->dev->adev, - pdd->proc_ctx_bo); + &pdd->proc_ctx_bo); /* * before destroying pdd, make sure to report availability * for auto suspend diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index adb5e4bdc0b204..0583af4e84fa3f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -28,6 +28,7 @@ #include "kfd_priv.h" #include "kfd_kernel_queue.h" #include "amdgpu_amdkfd.h" +#include "amdgpu_reset.h" static inline struct process_queue_node *get_queue_by_qid( struct process_queue_manager *pqm, unsigned int qid) @@ -87,6 +88,12 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd) return; dev->dqm->ops.process_termination(dev->dqm, &pdd->qpd); + if (dev->kfd->shared_resources.enable_mes && + down_read_trylock(&dev->adev->reset_domain->sem)) { + amdgpu_mes_flush_shader_debugger(dev->adev, + pdd->proc_ctx_gpu_addr); + up_read(&dev->adev->reset_domain->sem); + } pdd->already_dequeued = true; } @@ -169,16 +176,43 @@ int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p) return 0; } +static void pqm_clean_queue_resource(struct process_queue_manager *pqm, + struct process_queue_node *pqn) +{ + struct kfd_node *dev; + struct kfd_process_device *pdd; + + dev = pqn->q->device; + + pdd = kfd_get_process_device_data(dev, pqm->process); + if (!pdd) { + pr_err("Process device data doesn't exist\n"); + return; + } + + if (pqn->q->gws) { + if (KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) && + !dev->kfd->shared_resources.enable_mes) + amdgpu_amdkfd_remove_gws_from_process( + pqm->process->kgd_process_info, pqn->q->gws); + pdd->qpd.num_gws = 0; + } + + if (dev->kfd->shared_resources.enable_mes) { + amdgpu_amdkfd_free_gtt_mem(dev->adev, &pqn->q->gang_ctx_bo); + if (pqn->q->wptr_bo) + amdgpu_amdkfd_free_gtt_mem(dev->adev, (void **)&pqn->q->wptr_bo); + } +} + void pqm_uninit(struct process_queue_manager *pqm) { struct process_queue_node *pqn, *next; list_for_each_entry_safe(pqn, next, &pqm->queues, process_queue_list) { - if (pqn->q && pqn->q->gws && - KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) && - !pqn->q->device->kfd->shared_resources.enable_mes) - amdgpu_amdkfd_remove_gws_from_process(pqm->process->kgd_process_info, - pqn->q->gws); + if (pqn->q) + pqm_clean_queue_resource(pqm, pqn); + kfd_procfs_del_queue(pqn->q); uninit_queue(pqn->q); list_del(&pqn->process_queue_list); @@ -377,7 +411,8 @@ int pqm_create_queue(struct process_queue_manager *pqm, */ uint32_t first_db_index = amdgpu_doorbell_index_on_bar(pdd->dev->adev, pdd->qpd.proc_doorbells, - 0); + 0, + pdd->dev->kfd->device_info.doorbell_size); *p_doorbell_offset_in_process = (q->properties.doorbell_off - first_db_index) * sizeof(uint32_t); @@ -460,22 +495,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) goto err_destroy_queue; } - if (pqn->q->gws) { - if (KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) && - !dev->kfd->shared_resources.enable_mes) - amdgpu_amdkfd_remove_gws_from_process( - pqm->process->kgd_process_info, - pqn->q->gws); - pdd->qpd.num_gws = 0; - } - - if (dev->kfd->shared_resources.enable_mes) { - amdgpu_amdkfd_free_gtt_mem(dev->adev, - pqn->q->gang_ctx_bo); - if (pqn->q->wptr_bo) - amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->wptr_bo); - - } + pqm_clean_queue_resource(pqm, pqn); uninit_queue(pqn->q); } @@ -962,6 +982,7 @@ int kfd_criu_restore_queue(struct kfd_process *p, pr_debug("Queue id %d was restored successfully\n", queue_id); kfree(q_data); + kfree(q_extra_data); return ret; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index bb16b795d1bc2a..ce76d455499841 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -391,14 +391,9 @@ static void svm_range_bo_release(struct kref *kref) spin_lock(&svm_bo->list_lock); } spin_unlock(&svm_bo->list_lock); - if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base)) { - /* We're not in the eviction worker. - * Signal the fence and synchronize with any - * pending eviction work. - */ + if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base)) + /* We're not in the eviction worker. Signal the fence. */ dma_fence_signal(&svm_bo->eviction_fence->base); - cancel_work_sync(&svm_bo->eviction_work); - } dma_fence_put(&svm_bo->eviction_fence->base); amdgpu_bo_unref(&svm_bo->bo); kfree(svm_bo); @@ -495,11 +490,11 @@ svm_range_validate_svm_bo(struct kfd_node *node, struct svm_range *prange) /* We need a new svm_bo. Spin-loop to wait for concurrent * svm_range_bo_release to finish removing this range from - * its range list. After this, it is safe to reuse the - * svm_bo pointer and svm_bo_list head. + * its range list and set prange->svm_bo to null. After this, + * it is safe to reuse the svm_bo pointer and svm_bo_list head. */ - while (!list_empty_careful(&prange->svm_bo_list)) - ; + while (!list_empty_careful(&prange->svm_bo_list) || prange->svm_bo) + cond_resched(); return false; } @@ -628,8 +623,15 @@ svm_range_vram_node_new(struct kfd_node *node, struct svm_range *prange, void svm_range_vram_node_free(struct svm_range *prange) { - svm_range_bo_unref(prange->svm_bo); - prange->ttm_res = NULL; + /* serialize prange->svm_bo unref */ + mutex_lock(&prange->lock); + /* prange->svm_bo has not been unref */ + if (prange->ttm_res) { + prange->ttm_res = NULL; + mutex_unlock(&prange->lock); + svm_range_bo_unref(prange->svm_bo); + } else + mutex_unlock(&prange->lock); } struct kfd_node * @@ -760,7 +762,7 @@ svm_range_apply_attrs(struct kfd_process *p, struct svm_range *prange, prange->flags &= ~attrs[i].value; break; case KFD_IOCTL_SVM_ATTR_GRANULARITY: - prange->granularity = attrs[i].value; + prange->granularity = min_t(uint32_t, attrs[i].value, 0x3F); break; default: WARN_ONCE(1, "svm_range_check_attrs wasn't called?"); @@ -820,7 +822,7 @@ svm_range_is_same_attrs(struct kfd_process *p, struct svm_range *prange, } } - return !prange->is_error_flag; + return true; } /** @@ -1625,18 +1627,24 @@ static int svm_range_validate_and_map(struct mm_struct *mm, if (test_bit(gpuidx, prange->bitmap_access)) bitmap_set(ctx->bitmap, gpuidx, 1); } + + /* + * If prange is already mapped or with always mapped flag, + * update mapping on GPUs with ACCESS attribute + */ + if (bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) { + if (prange->mapped_to_gpu || + prange->flags & KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED) + bitmap_copy(ctx->bitmap, prange->bitmap_access, MAX_GPU_INSTANCE); + } } else { bitmap_or(ctx->bitmap, prange->bitmap_access, prange->bitmap_aip, MAX_GPU_INSTANCE); } if (bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) { - bitmap_copy(ctx->bitmap, prange->bitmap_access, MAX_GPU_INSTANCE); - if (!prange->mapped_to_gpu || - bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) { - r = 0; - goto free_ctx; - } + r = 0; + goto free_ctx; } if (prange->actual_loc && !prange->ttm_res) { @@ -1662,73 +1670,66 @@ static int svm_range_validate_and_map(struct mm_struct *mm, start = prange->start << PAGE_SHIFT; end = (prange->last + 1) << PAGE_SHIFT; - for (addr = start; addr < end && !r; ) { + for (addr = start; !r && addr < end; ) { struct hmm_range *hmm_range; struct vm_area_struct *vma; - unsigned long next; + unsigned long next = 0; unsigned long offset; unsigned long npages; bool readonly; vma = vma_lookup(mm, addr); - if (!vma) { + if (vma) { + readonly = !(vma->vm_flags & VM_WRITE); + + next = min(vma->vm_end, end); + npages = (next - addr) >> PAGE_SHIFT; + WRITE_ONCE(p->svms.faulting_task, current); + r = amdgpu_hmm_range_get_pages(&prange->notifier, addr, npages, + readonly, owner, NULL, + &hmm_range); + WRITE_ONCE(p->svms.faulting_task, NULL); + if (r) { + pr_debug("failed %d to get svm range pages\n", r); + if (r == -EBUSY) + r = -EAGAIN; + } + } else { r = -EFAULT; - goto unreserve_out; - } - readonly = !(vma->vm_flags & VM_WRITE); - - next = min(vma->vm_end, end); - npages = (next - addr) >> PAGE_SHIFT; - WRITE_ONCE(p->svms.faulting_task, current); - r = amdgpu_hmm_range_get_pages(&prange->notifier, addr, npages, - readonly, owner, NULL, - &hmm_range); - WRITE_ONCE(p->svms.faulting_task, NULL); - if (r) { - pr_debug("failed %d to get svm range pages\n", r); - if (r == -EBUSY) - r = -EAGAIN; - goto unreserve_out; } - offset = (addr - start) >> PAGE_SHIFT; - r = svm_range_dma_map(prange, ctx->bitmap, offset, npages, - hmm_range->hmm_pfns); - if (r) { - pr_debug("failed %d to dma map range\n", r); - goto unreserve_out; + if (!r) { + offset = (addr - start) >> PAGE_SHIFT; + r = svm_range_dma_map(prange, ctx->bitmap, offset, npages, + hmm_range->hmm_pfns); + if (r) + pr_debug("failed %d to dma map range\n", r); } svm_range_lock(prange); - if (amdgpu_hmm_range_get_pages_done(hmm_range)) { + if (!r && amdgpu_hmm_range_get_pages_done(hmm_range)) { pr_debug("hmm update the range, need validate again\n"); r = -EAGAIN; - goto unlock_out; } - if (!list_empty(&prange->child_list)) { + + if (!r && !list_empty(&prange->child_list)) { pr_debug("range split by unmap in parallel, validate again\n"); r = -EAGAIN; - goto unlock_out; } - r = svm_range_map_to_gpus(prange, offset, npages, readonly, - ctx->bitmap, wait, flush_tlb); + if (!r) + r = svm_range_map_to_gpus(prange, offset, npages, readonly, + ctx->bitmap, wait, flush_tlb); + + if (!r && next == end) + prange->mapped_to_gpu = true; -unlock_out: svm_range_unlock(prange); addr = next; } - if (addr == end) { - prange->validated_once = true; - prange->mapped_to_gpu = true; - } - -unreserve_out: svm_range_unreserve_bos(ctx); - - prange->is_error_flag = !!r; if (!r) prange->validate_timestamp = ktime_get_boottime(); @@ -2097,7 +2098,8 @@ svm_range_add(struct kfd_process *p, uint64_t start, uint64_t size, next = interval_tree_iter_next(node, start, last); next_start = min(node->last, last) + 1; - if (svm_range_is_same_attrs(p, prange, nattr, attrs)) { + if (svm_range_is_same_attrs(p, prange, nattr, attrs) && + prange->mapped_to_gpu) { /* nothing to do */ } else if (node->start < start || node->last > last) { /* node intersects the update range and its attributes @@ -2341,8 +2343,10 @@ static void svm_range_deferred_list_work(struct work_struct *work) mutex_unlock(&svms->lock); mmap_write_unlock(mm); - /* Pairs with mmget in svm_range_add_list_work */ - mmput(mm); + /* Pairs with mmget in svm_range_add_list_work. If dropping the + * last mm refcount, schedule release work to avoid circular locking + */ + mmput_async(mm); spin_lock(&svms->deferred_list_lock); } @@ -2653,6 +2657,7 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr, { struct vm_area_struct *vma; struct interval_tree_node *node; + struct rb_node *rb_node; unsigned long start_limit, end_limit; vma = vma_lookup(p->mm, addr << PAGE_SHIFT); @@ -2672,16 +2677,15 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr, if (node) { end_limit = min(end_limit, node->start); /* Last range that ends before the fault address */ - node = container_of(rb_prev(&node->rb), - struct interval_tree_node, rb); + rb_node = rb_prev(&node->rb); } else { /* Last range must end before addr because * there was no range after addr */ - node = container_of(rb_last(&p->svms.objects.rb_root), - struct interval_tree_node, rb); + rb_node = rb_last(&p->svms.objects.rb_root); } - if (node) { + if (rb_node) { + node = container_of(rb_node, struct interval_tree_node, rb); if (node->last >= addr) { WARN(1, "Overlap with prev node and page fault addr\n"); return -EFAULT; @@ -3412,18 +3416,19 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange, r = svm_migrate_to_vram(prange, best_loc, mm, KFD_MIGRATE_TRIGGER_PREFETCH); *migrated = !r; - return r; + return 0; } int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence) { - if (!fence) - return -EINVAL; - - if (dma_fence_is_signaled(&fence->base)) - return 0; - - if (fence->svm_bo) { + /* Dereferencing fence->svm_bo is safe here because the fence hasn't + * signaled yet and we're under the protection of the fence->lock. + * After the fence is signaled in svm_range_bo_release, we cannot get + * here any more. + * + * Reference is dropped in svm_range_evict_svm_bo_worker. + */ + if (svm_bo_ref_unless_zero(fence->svm_bo)) { WRITE_ONCE(fence->svm_bo->evicting, 1); schedule_work(&fence->svm_bo->eviction_work); } @@ -3438,8 +3443,6 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work) int r = 0; svm_bo = container_of(work, struct svm_range_bo, eviction_work); - if (!svm_bo_ref_unless_zero(svm_bo)) - return; /* svm_bo was freed while eviction was pending */ if (mmget_not_zero(svm_bo->eviction_fence->mm)) { mm = svm_bo->eviction_fence->mm; @@ -3507,7 +3510,7 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm, struct svm_range *next; bool update_mapping = false; bool flush_tlb; - int r = 0; + int r, ret = 0; pr_debug("pasid 0x%x svms 0x%p [0x%llx 0x%llx] pages 0x%llx\n", p->pasid, &p->svms, start, start + size - 1, size); @@ -3595,7 +3598,7 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm, out_unlock_range: mutex_unlock(&prange->migrate_mutex); if (r) - break; + ret = r; } dynamic_svm_range_dump(svms); @@ -3608,7 +3611,7 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm, pr_debug("pasid 0x%x svms 0x%p [0x%llx 0x%llx] done, r=%d\n", p->pasid, &p->svms, start, start + size - 1, r); - return r; + return ret ? ret : r; } static int diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h index 9e668eeefb32df..25f71190573865 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h @@ -132,9 +132,7 @@ struct svm_range { struct list_head child_list; DECLARE_BITMAP(bitmap_access, MAX_GPU_INSTANCE); DECLARE_BITMAP(bitmap_aip, MAX_GPU_INSTANCE); - bool validated_once; bool mapped_to_gpu; - bool is_error_flag; }; static inline void svm_range_lock(struct svm_range *prange) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index c8c75ff7cea80d..8362a71ab70752 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -958,8 +958,7 @@ static void kfd_update_system_properties(void) dev = list_last_entry(&topology_device_list, struct kfd_topology_device, list); if (dev) { - sys_props.platform_id = - (*((uint64_t *)dev->oem_id)) & CRAT_OEMID_64BIT_MASK; + sys_props.platform_id = dev->oem_id64; sys_props.platform_oem = *((uint64_t *)dev->oem_table_id); sys_props.platform_rev = dev->oem_revision; } @@ -1342,10 +1341,11 @@ static int kfd_create_indirect_link_prop(struct kfd_topology_device *kdev, int g num_cpu++; } + if (list_empty(&kdev->io_link_props)) + return -ENODATA; + gpu_link = list_first_entry(&kdev->io_link_props, - struct kfd_iolink_properties, list); - if (!gpu_link) - return -ENOMEM; + struct kfd_iolink_properties, list); for (i = 0; i < num_cpu; i++) { /* CPU <--> GPU */ @@ -1423,15 +1423,17 @@ static int kfd_add_peer_prop(struct kfd_topology_device *kdev, peer->gpu->adev)) return ret; + if (list_empty(&kdev->io_link_props)) + return -ENODATA; + iolink1 = list_first_entry(&kdev->io_link_props, - struct kfd_iolink_properties, list); - if (!iolink1) - return -ENOMEM; + struct kfd_iolink_properties, list); + + if (list_empty(&peer->io_link_props)) + return -ENODATA; iolink2 = list_first_entry(&peer->io_link_props, - struct kfd_iolink_properties, list); - if (!iolink2) - return -ENOMEM; + struct kfd_iolink_properties, list); props = kfd_alloc_struct(props); if (!props) @@ -1449,17 +1451,19 @@ static int kfd_add_peer_prop(struct kfd_topology_device *kdev, /* CPU->CPU link*/ cpu_dev = kfd_topology_device_by_proximity_domain(iolink1->node_to); if (cpu_dev) { - list_for_each_entry(iolink3, &cpu_dev->io_link_props, list) - if (iolink3->node_to == iolink2->node_to) - break; - - props->weight += iolink3->weight; - props->min_latency += iolink3->min_latency; - props->max_latency += iolink3->max_latency; - props->min_bandwidth = min(props->min_bandwidth, - iolink3->min_bandwidth); - props->max_bandwidth = min(props->max_bandwidth, - iolink3->max_bandwidth); + list_for_each_entry(iolink3, &cpu_dev->io_link_props, list) { + if (iolink3->node_to != iolink2->node_to) + continue; + + props->weight += iolink3->weight; + props->min_latency += iolink3->min_latency; + props->max_latency += iolink3->max_latency; + props->min_bandwidth = min(props->min_bandwidth, + iolink3->min_bandwidth); + props->max_bandwidth = min(props->max_bandwidth, + iolink3->max_bandwidth); + break; + } } else { WARN(1, "CPU node not found"); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h index 27386ce9a021da..2d1c9d771bef2d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h @@ -154,7 +154,10 @@ struct kfd_topology_device { struct attribute attr_gpuid; struct attribute attr_name; struct attribute attr_props; - uint8_t oem_id[CRAT_OEMID_LENGTH]; + union { + uint8_t oem_id[CRAT_OEMID_LENGTH]; + uint64_t oem_id64; + }; uint8_t oem_table_id[CRAT_OEMTABLEID_LENGTH]; uint32_t oem_revision; }; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 868946dd7ef126..a3f17c572bf06e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -65,7 +65,6 @@ #include "amdgpu_dm_debugfs.h" #endif #include "amdgpu_dm_psr.h" -#include "amdgpu_dm_replay.h" #include "ivsrcid/ivsrcid_vislands30.h" @@ -265,7 +264,7 @@ static u32 dm_vblank_get_counter(struct amdgpu_device *adev, int crtc) static int dm_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc, u32 *vbl, u32 *position) { - u32 v_blank_start, v_blank_end, h_position, v_position; + u32 v_blank_start = 0, v_blank_end = 0, h_position = 0, v_position = 0; struct amdgpu_crtc *acrtc = NULL; if ((crtc < 0) || (crtc >= adev->mode_info.num_crtc)) @@ -715,6 +714,12 @@ static void dmub_hpd_callback(struct amdgpu_device *adev, return; } + /* Skip DMUB HPD IRQ in suspend/resume. We will probe them later. */ + if (notify->type == DMUB_NOTIFICATION_HPD && adev->in_suspend) { + DRM_INFO("Skip DMUB HPD IRQ callback in suspend/resume\n"); + return; + } + link_index = notify->link_index; link = adev->dm.dc->links[link_index]; dev = adev->dm.ddev; @@ -802,7 +807,7 @@ static void dm_handle_hpd_work(struct work_struct *work) */ static void dm_dmub_outbox1_low_irq(void *interrupt_params) { - struct dmub_notification notify; + struct dmub_notification notify = {0}; struct common_irq_params *irq_params = interrupt_params; struct amdgpu_device *adev = irq_params->adev; struct amdgpu_display_manager *dm = &adev->dm; @@ -1248,7 +1253,9 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_ /* AGP aperture is disabled */ if (agp_bot == agp_top) { logical_addr_low = adev->gmc.fb_start >> 18; - if (adev->apu_flags & AMD_APU_IS_RAVEN2) + if (adev->apu_flags & (AMD_APU_IS_RAVEN2 | + AMD_APU_IS_RENOIR | + AMD_APU_IS_GREEN_SARDINE)) /* * Raven2 has a HW issue that it is unable to use the vram which * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the @@ -1260,7 +1267,9 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_ logical_addr_high = adev->gmc.fb_end >> 18; } else { logical_addr_low = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18; - if (adev->apu_flags & AMD_APU_IS_RAVEN2) + if (adev->apu_flags & (AMD_APU_IS_RAVEN2 | + AMD_APU_IS_RENOIR | + AMD_APU_IS_GREEN_SARDINE)) /* * Raven2 has a HW issue that it is unable to use the vram which * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the @@ -1692,8 +1701,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) DRM_INFO("Display Core v%s initialized on %s\n", DC_VER, dce_version_to_string(adev->dm.dc->ctx->dce_version)); } else { - DRM_INFO("Display Core v%s failed to initialize on %s\n", DC_VER, - dce_version_to_string(adev->dm.dc->ctx->dce_version)); + DRM_INFO("Display Core failed to initialize with v%s!\n", DC_VER); goto error; } @@ -1814,21 +1822,12 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) DRM_ERROR("amdgpu: fail to register dmub aux callback"); goto error; } - if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD, dmub_hpd_callback, true)) { - DRM_ERROR("amdgpu: fail to register dmub hpd callback"); - goto error; - } - if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_IRQ, dmub_hpd_callback, true)) { - DRM_ERROR("amdgpu: fail to register dmub hpd callback"); - goto error; - } - } - - /* Enable outbox notification only after IRQ handlers are registered and DMUB is alive. - * It is expected that DMUB will resend any pending notifications at this point, for - * example HPD from DPIA. - */ - if (dc_is_dmub_outbox_supported(adev->dm.dc)) { + /* Enable outbox notification only after IRQ handlers are registered and DMUB is alive. + * It is expected that DMUB will resend any pending notifications at this point. Note + * that hpd and hpd_irq handler registration are deferred to register_hpd_handlers() to + * align legacy interface initialization sequence. Connection status will be proactivly + * detected once in the amdgpu_dm_initialize_drm_device. + */ dc_enable_dmub_outbox(adev->dm.dc); /* DPIA trace goes to dmesg logs only if outbox is enabled */ @@ -1909,17 +1908,15 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev) adev->dm.hdcp_workqueue = NULL; } - if (adev->dm.dc) + if (adev->dm.dc) { dc_deinit_callbacks(adev->dm.dc); - - if (adev->dm.dc) dc_dmub_srv_destroy(&adev->dm.dc->ctx->dmub_srv); - - if (dc_enable_dmub_notifications(adev->dm.dc)) { - kfree(adev->dm.dmub_notify); - adev->dm.dmub_notify = NULL; - destroy_workqueue(adev->dm.delayed_hpd_wq); - adev->dm.delayed_hpd_wq = NULL; + if (dc_enable_dmub_notifications(adev->dm.dc)) { + kfree(adev->dm.dmub_notify); + adev->dm.dmub_notify = NULL; + destroy_workqueue(adev->dm.delayed_hpd_wq); + adev->dm.delayed_hpd_wq = NULL; + } } if (adev->dm.dmub_bo) @@ -2085,7 +2082,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) struct dmub_srv_create_params create_params; struct dmub_srv_region_params region_params; struct dmub_srv_region_info region_info; - struct dmub_srv_fb_params fb_params; + struct dmub_srv_memory_params memory_params; struct dmub_srv_fb_info *fb_info; struct dmub_srv *dmub_srv; const struct dmcub_firmware_header_v1_0 *hdr; @@ -2185,6 +2182,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) adev->dm.dmub_fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes) + PSP_HEADER_BYTES; + region_params.is_mailbox_in_inbox = false; status = dmub_srv_calc_region_info(dmub_srv, ®ion_params, ®ion_info); @@ -2208,10 +2206,10 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) return r; /* Rebase the regions on the framebuffer address. */ - memset(&fb_params, 0, sizeof(fb_params)); - fb_params.cpu_addr = adev->dm.dmub_bo_cpu_addr; - fb_params.gpu_addr = adev->dm.dmub_bo_gpu_addr; - fb_params.region_info = ®ion_info; + memset(&memory_params, 0, sizeof(memory_params)); + memory_params.cpu_fb_addr = adev->dm.dmub_bo_cpu_addr; + memory_params.gpu_fb_addr = adev->dm.dmub_bo_gpu_addr; + memory_params.region_info = ®ion_info; adev->dm.dmub_fb_info = kzalloc(sizeof(*adev->dm.dmub_fb_info), GFP_KERNEL); @@ -2223,7 +2221,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) return -ENOMEM; } - status = dmub_srv_calc_fb_info(dmub_srv, &fb_params, fb_info); + status = dmub_srv_calc_mem_info(dmub_srv, &memory_params, fb_info); if (status != DMUB_STATUS_OK) { DRM_ERROR("Error calculating DMUB FB info: %d\n", status); return -EINVAL; @@ -2253,6 +2251,7 @@ static int dm_sw_fini(void *handle) if (adev->dm.dmub_srv) { dmub_srv_destroy(adev->dm.dmub_srv); + kfree(adev->dm.dmub_srv); adev->dm.dmub_srv = NULL; } @@ -2635,7 +2634,8 @@ static int dm_suspend(void *handle) dm->cached_dc_state = dc_copy_state(dm->dc->current_state); - dm_gpureset_toggle_interrupts(adev, dm->cached_dc_state, false); + if (dm->cached_dc_state) + dm_gpureset_toggle_interrupts(adev, dm->cached_dc_state, false); amdgpu_dm_commit_zero_streams(dm->dc); @@ -2963,6 +2963,7 @@ static int dm_resume(void *handle) dc_stream_release(dm_new_crtc_state->stream); dm_new_crtc_state->stream = NULL; } + dm_new_crtc_state->base.color_mgmt_changed = true; } for_each_new_plane_in_state(dm->cached_state, plane, new_plane_state, i) { @@ -2981,6 +2982,10 @@ static int dm_resume(void *handle) /* Do mst topology probing after resuming cached state*/ drm_connector_list_iter_begin(ddev, &iter); drm_for_each_connector_iter(connector, &iter) { + + if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) + continue; + aconnector = to_amdgpu_dm_connector(connector); if (aconnector->dc_link->type != dc_connection_mst_branch || aconnector->mst_root) @@ -3481,6 +3486,14 @@ static void register_hpd_handlers(struct amdgpu_device *adev) int_params.requested_polarity = INTERRUPT_POLARITY_DEFAULT; int_params.current_polarity = INTERRUPT_POLARITY_DEFAULT; + if (dc_is_dmub_outbox_supported(adev->dm.dc)) { + if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD, dmub_hpd_callback, true)) + DRM_ERROR("amdgpu: fail to register dmub hpd callback"); + + if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_IRQ, dmub_hpd_callback, true)) + DRM_ERROR("amdgpu: fail to register dmub hpd callback"); + } + list_for_each_entry(connector, &dev->mode_config.connector_list, head) { @@ -3506,10 +3519,6 @@ static void register_hpd_handlers(struct amdgpu_device *adev) handle_hpd_rx_irq, (void *) aconnector); } - - if (adev->dm.hpd_rx_offload_wq) - adev->dm.hpd_rx_offload_wq[connector->index].aconnector = - aconnector; } } @@ -4034,6 +4043,7 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev) #define AMDGPU_DM_DEFAULT_MIN_BACKLIGHT 12 #define AMDGPU_DM_DEFAULT_MAX_BACKLIGHT 255 +#define AMDGPU_DM_MIN_SPREAD ((AMDGPU_DM_DEFAULT_MAX_BACKLIGHT - AMDGPU_DM_DEFAULT_MIN_BACKLIGHT) / 2) #define AUX_BL_DEFAULT_TRANSITION_TIME_MS 50 static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm, @@ -4048,6 +4058,21 @@ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm, return; amdgpu_acpi_get_backlight_caps(&caps); + + /* validate the firmware value is sane */ + if (caps.caps_valid) { + int spread = caps.max_input_signal - caps.min_input_signal; + + if (caps.max_input_signal > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || + caps.min_input_signal < 0 || + spread > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || + spread < AMDGPU_DM_MIN_SPREAD) { + DRM_DEBUG_KMS("DM: Invalid backlight caps: min=%d, max=%d\n", + caps.min_input_signal, caps.max_input_signal); + caps.caps_valid = false; + } + } + if (caps.caps_valid) { dm->backlight_caps[bl_idx].caps_valid = true; if (caps.aux_support) @@ -4338,7 +4363,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) enum dc_connection_type new_connection_type = dc_connection_none; const struct dc_plane_cap *plane; bool psr_feature_enabled = false; - bool replay_feature_enabled = false; int max_overlay = dm->dc->caps.max_slave_planes; dm->display_indexes_num = dm->dc->caps.max_streams; @@ -4355,7 +4379,10 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) /* There is one primary plane per CRTC */ primary_planes = dm->dc->caps.max_streams; - ASSERT(primary_planes <= AMDGPU_MAX_PLANES); + if (primary_planes > AMDGPU_MAX_PLANES) { + DRM_ERROR("DM: Plane nums out of 6 planes\n"); + return -EINVAL; + } /* * Initialize primary planes, implicit planes for legacy IOCTLS. @@ -4448,20 +4475,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) } } - if (!(amdgpu_dc_debug_mask & DC_DISABLE_REPLAY)) { - switch (adev->ip_versions[DCE_HWIP][0]) { - case IP_VERSION(3, 1, 4): - case IP_VERSION(3, 1, 5): - case IP_VERSION(3, 1, 6): - case IP_VERSION(3, 2, 0): - case IP_VERSION(3, 2, 1): - replay_feature_enabled = true; - break; - default: - replay_feature_enabled = amdgpu_dc_feature_mask & DC_REPLAY_MASK; - break; - } - } /* loops over all connectors on the board */ for (i = 0; i < link_cnt; i++) { struct dc_link *link = NULL; @@ -4493,6 +4506,10 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) link = dc_get_link_at_index(dm->dc, i); + if (dm->hpd_rx_offload_wq) + dm->hpd_rx_offload_wq[aconnector->base.index].aconnector = + aconnector; + if (!dc_link_detect_connection_type(link, &new_connection_type)) DRM_ERROR("KMS: Failed to detect connector\n"); @@ -4510,12 +4527,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) amdgpu_dm_update_connector_after_detect(aconnector); setup_backlight_device(dm, aconnector); - /* - * Disable psr if replay can be enabled - */ - if (replay_feature_enabled && amdgpu_dm_setup_replay(link, aconnector)) - psr_feature_enabled = false; - if (psr_feature_enabled) amdgpu_dm_set_psr_caps(link); @@ -5170,6 +5181,9 @@ static void fill_dc_dirty_rects(struct drm_plane *plane, if (plane->type == DRM_PLANE_TYPE_CURSOR) return; + if (new_plane_state->rotation != DRM_MODE_ROTATE_0) + goto ffu; + num_clips = drm_plane_get_damage_clips_count(new_plane_state); clips = drm_plane_get_damage_clips(new_plane_state); @@ -5773,6 +5787,9 @@ get_highest_refresh_rate_mode(struct amdgpu_dm_connector *aconnector, &aconnector->base.probed_modes : &aconnector->base.modes; + if (aconnector->base.connector_type == DRM_MODE_CONNECTOR_WRITEBACK) + return NULL; + if (aconnector->freesync_vid_base.clock != 0) return &aconnector->freesync_vid_base; @@ -6087,7 +6104,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (recalculate_timing) { freesync_mode = get_highest_refresh_rate_mode(aconnector, false); drm_mode_copy(&saved_mode, &mode); + saved_mode.picture_aspect_ratio = mode.picture_aspect_ratio; drm_mode_copy(&mode, freesync_mode); + mode.picture_aspect_ratio = saved_mode.picture_aspect_ratio; } else { decide_crtc_timing_for_drm_display_mode( &mode, preferred_mode, scale); @@ -6137,19 +6156,25 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket); - if (stream->link->psr_settings.psr_feature_enabled || stream->link->replay_settings.replay_feature_enabled) { + if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT || + stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST || + stream->signal == SIGNAL_TYPE_EDP) { + const struct dc_edid_caps *edid_caps; + unsigned int disable_colorimetry = 0; + + if (aconnector->dc_sink) { + edid_caps = &aconnector->dc_sink->edid_caps; + disable_colorimetry = edid_caps->panel_patch.disable_colorimetry; + } + // // should decide stream support vsc sdp colorimetry capability // before building vsc info packet // - stream->use_vsc_sdp_for_colorimetry = false; - if (aconnector->dc_sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { - stream->use_vsc_sdp_for_colorimetry = - aconnector->dc_sink->is_vsc_sdp_colorimetry_supported; - } else { - if (stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED) - stream->use_vsc_sdp_for_colorimetry = true; - } + stream->use_vsc_sdp_for_colorimetry = stream->link->dpcd_caps.dpcd_rev.raw >= 0x14 && + stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED && + !disable_colorimetry; + if (stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22) tf = TRANSFER_FUNC_GAMMA_22; mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf); @@ -6236,7 +6261,7 @@ int amdgpu_dm_connector_atomic_set_property(struct drm_connector *connector, dm_new_state->underscan_enable = val; ret = 0; } else if (property == adev->mode_info.abm_level_property) { - dm_new_state->abm_level = val; + dm_new_state->abm_level = val ?: ABM_LEVEL_IMMEDIATE_DISABLE; ret = 0; } @@ -6281,7 +6306,8 @@ int amdgpu_dm_connector_atomic_get_property(struct drm_connector *connector, *val = dm_state->underscan_enable; ret = 0; } else if (property == adev->mode_info.abm_level_property) { - *val = dm_state->abm_level; + *val = (dm_state->abm_level != ABM_LEVEL_IMMEDIATE_DISABLE) ? + dm_state->abm_level : 0; ret = 0; } @@ -6354,7 +6380,8 @@ void amdgpu_dm_connector_funcs_reset(struct drm_connector *connector) state->pbn = 0; if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) - state->abm_level = amdgpu_dm_abm_level; + state->abm_level = amdgpu_dm_abm_level ?: + ABM_LEVEL_IMMEDIATE_DISABLE; __drm_atomic_helper_connector_reset(connector, &state->base); } @@ -6491,7 +6518,8 @@ static void create_eml_sink(struct amdgpu_dm_connector *aconnector) aconnector->dc_sink = aconnector->dc_link->local_sink ? aconnector->dc_link->local_sink : aconnector->dc_em_sink; - dc_sink_retain(aconnector->dc_sink); + if (aconnector->dc_sink) + dc_sink_retain(aconnector->dc_sink); } } @@ -6863,8 +6891,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder, if (IS_ERR(mst_state)) return PTR_ERR(mst_state); - if (!mst_state->pbn_div) - mst_state->pbn_div = dm_mst_get_pbn_divider(aconnector->mst_root->dc_link); + mst_state->pbn_div = dm_mst_get_pbn_divider(aconnector->mst_root->dc_link); if (!state->duplicated) { int max_bpc = conn_state->max_requested_bpc; @@ -6876,7 +6903,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder, max_bpc); bpp = convert_dc_color_depth_into_bpc(color_depth) * 3; clock = adjusted_mode->clock; - dm_new_connector_state->pbn = drm_dp_calc_pbn_mode(clock, bpp, false); + dm_new_connector_state->pbn = drm_dp_calc_pbn_mode(clock, bpp << 4); } dm_new_connector_state->vcpi_slots = @@ -6904,7 +6931,7 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state, struct amdgpu_dm_connector *aconnector; struct dm_connector_state *dm_conn_state; int i, j, ret; - int vcpi, pbn_div, pbn, slot_num = 0; + int vcpi, pbn_div, pbn = 0, slot_num = 0; for_each_new_connector_in_state(state, connector, new_con_state, i) { @@ -6941,7 +6968,7 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state, } } - if (j == dc_state->stream_count) + if (j == dc_state->stream_count || pbn_div == 0) continue; slot_num = DIV_ROUND_UP(pbn, pbn_div); @@ -7305,7 +7332,8 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector) drm_add_modes_noedid(connector, 1920, 1080); } else { amdgpu_dm_connector_ddc_get_modes(connector, edid); - amdgpu_dm_connector_add_common_modes(encoder, connector); + if (encoder) + amdgpu_dm_connector_add_common_modes(encoder, connector); amdgpu_dm_connector_add_freesync_modes(connector, edid); } amdgpu_dm_fbc_init(connector); @@ -7431,6 +7459,9 @@ static int amdgpu_dm_i2c_xfer(struct i2c_adapter *i2c_adap, int i; int result = -EIO; + if (!ddc_service->ddc_pin || !ddc_service->ddc_pin->hw_info.hw_supported) + return result; + cmd.payloads = kcalloc(num, sizeof(struct i2c_payload), GFP_KERNEL); if (!cmd.payloads) @@ -8286,15 +8317,13 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, bundle->stream_update.vrr_infopacket = &acrtc_state->stream->vrr_infopacket; } - } else if (cursor_update && acrtc_state->active_planes > 0 && - acrtc_attach->base.state->event) { - drm_crtc_vblank_get(pcrtc); - + } else if (cursor_update && acrtc_state->active_planes > 0) { spin_lock_irqsave(&pcrtc->dev->event_lock, flags); - - acrtc_attach->event = acrtc_attach->base.state->event; - acrtc_attach->base.state->event = NULL; - + if (acrtc_attach->base.state->event) { + drm_crtc_vblank_get(pcrtc); + acrtc_attach->event = acrtc_attach->base.state->event; + acrtc_attach->base.state->event = NULL; + } spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags); } @@ -8459,6 +8488,9 @@ static void amdgpu_dm_commit_audio(struct drm_device *dev, continue; notify: + if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) + continue; + aconnector = to_amdgpu_dm_connector(connector); mutex_lock(&adev->dm.audio_lock); @@ -9539,14 +9571,14 @@ static bool should_reset_plane(struct drm_atomic_state *state, struct drm_plane *other; struct drm_plane_state *old_other_state, *new_other_state; struct drm_crtc_state *new_crtc_state; + struct amdgpu_device *adev = drm_to_adev(plane->dev); int i; /* - * TODO: Remove this hack once the checks below are sufficient - * enough to determine when we need to reset all the planes on - * the stream. + * TODO: Remove this hack for all asics once it proves that the + * fast updates works fine on DCN3.2+. */ - if (state->allow_modeset) + if (adev->ip_versions[DCE_HWIP][0] < IP_VERSION(3, 2, 0) && state->allow_modeset) return true; /* Exit early if we know that we're adding or removing the plane. */ @@ -9892,16 +9924,27 @@ static void dm_get_oriented_plane_size(struct drm_plane_state *plane_state, } } +static void +dm_get_plane_scale(struct drm_plane_state *plane_state, + int *out_plane_scale_w, int *out_plane_scale_h) +{ + int plane_src_w, plane_src_h; + + dm_get_oriented_plane_size(plane_state, &plane_src_w, &plane_src_h); + *out_plane_scale_w = plane_state->crtc_w * 1000 / plane_src_w; + *out_plane_scale_h = plane_state->crtc_h * 1000 / plane_src_h; +} + static int dm_check_crtc_cursor(struct drm_atomic_state *state, struct drm_crtc *crtc, struct drm_crtc_state *new_crtc_state) { - struct drm_plane *cursor = crtc->cursor, *underlying; + struct drm_plane *cursor = crtc->cursor, *plane, *underlying; + struct drm_plane_state *old_plane_state, *new_plane_state; struct drm_plane_state *new_cursor_state, *new_underlying_state; int i; int cursor_scale_w, cursor_scale_h, underlying_scale_w, underlying_scale_h; - int cursor_src_w, cursor_src_h; - int underlying_src_w, underlying_src_h; + bool any_relevant_change = false; /* On DCE and DCN there is no dedicated hardware cursor plane. We get a * cursor per pipe but it's going to inherit the scaling and @@ -9909,13 +9952,50 @@ static int dm_check_crtc_cursor(struct drm_atomic_state *state, * blending properties match the underlying planes'. */ - new_cursor_state = drm_atomic_get_new_plane_state(state, cursor); - if (!new_cursor_state || !new_cursor_state->fb) + /* If no plane was enabled or changed scaling, no need to check again */ + for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { + int new_scale_w, new_scale_h, old_scale_w, old_scale_h; + + if (!new_plane_state || !new_plane_state->fb || new_plane_state->crtc != crtc) + continue; + + if (!old_plane_state || !old_plane_state->fb || old_plane_state->crtc != crtc) { + any_relevant_change = true; + break; + } + + if (new_plane_state->fb == old_plane_state->fb && + new_plane_state->crtc_w == old_plane_state->crtc_w && + new_plane_state->crtc_h == old_plane_state->crtc_h) + continue; + + dm_get_plane_scale(new_plane_state, &new_scale_w, &new_scale_h); + dm_get_plane_scale(old_plane_state, &old_scale_w, &old_scale_h); + + if (new_scale_w != old_scale_w || new_scale_h != old_scale_h) { + any_relevant_change = true; + break; + } + } + + if (!any_relevant_change) return 0; - dm_get_oriented_plane_size(new_cursor_state, &cursor_src_w, &cursor_src_h); - cursor_scale_w = new_cursor_state->crtc_w * 1000 / cursor_src_w; - cursor_scale_h = new_cursor_state->crtc_h * 1000 / cursor_src_h; + new_cursor_state = drm_atomic_get_plane_state(state, cursor); + if (IS_ERR(new_cursor_state)) + return PTR_ERR(new_cursor_state); + + if (!new_cursor_state->fb) + return 0; + + dm_get_plane_scale(new_cursor_state, &cursor_scale_w, &cursor_scale_h); + + /* Need to check all enabled planes, even if this commit doesn't change + * their state + */ + i = drm_atomic_add_affected_planes(state, crtc); + if (i) + return i; for_each_new_plane_in_state_reverse(state, underlying, new_underlying_state, i) { /* Narrow down to non-cursor planes on the same CRTC as the cursor */ @@ -9926,10 +10006,8 @@ static int dm_check_crtc_cursor(struct drm_atomic_state *state, if (!new_underlying_state->fb) continue; - dm_get_oriented_plane_size(new_underlying_state, - &underlying_src_w, &underlying_src_h); - underlying_scale_w = new_underlying_state->crtc_w * 1000 / underlying_src_w; - underlying_scale_h = new_underlying_state->crtc_h * 1000 / underlying_src_h; + dm_get_plane_scale(new_underlying_state, + &underlying_scale_w, &underlying_scale_h); if (cursor_scale_w != underlying_scale_w || cursor_scale_h != underlying_scale_h) { @@ -10021,7 +10099,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state; struct drm_dp_mst_topology_mgr *mgr; struct drm_dp_mst_topology_state *mst_state; - struct dsc_mst_fairness_vars vars[MAX_PIPES]; + struct dsc_mst_fairness_vars vars[MAX_PIPES] = {0}; trace_amdgpu_dm_atomic_check_begin(state); @@ -10321,11 +10399,13 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, goto fail; } - ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars); - if (ret) { - DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n"); - ret = -EINVAL; - goto fail; + if (dc_resource_is_dsc_encoding_supported(dc)) { + ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars); + if (ret) { + DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n"); + ret = -EINVAL; + goto fail; + } } ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars); @@ -10585,6 +10665,49 @@ static bool parse_edid_cea(struct amdgpu_dm_connector *aconnector, return ret; } +static void parse_edid_displayid_vrr(struct drm_connector *connector, + struct edid *edid) +{ + u8 *edid_ext = NULL; + int i; + int j = 0; + u16 min_vfreq; + u16 max_vfreq; + + if (edid == NULL || edid->extensions == 0) + return; + + /* Find DisplayID extension */ + for (i = 0; i < edid->extensions; i++) { + edid_ext = (void *)(edid + (i + 1)); + if (edid_ext[0] == DISPLAYID_EXT) + break; + } + + if (edid_ext == NULL) + return; + + while (j < EDID_LENGTH) { + /* Get dynamic video timing range from DisplayID if available */ + if (EDID_LENGTH - j > 13 && edid_ext[j] == 0x25 && + (edid_ext[j+1] & 0xFE) == 0 && (edid_ext[j+2] == 9)) { + min_vfreq = edid_ext[j+9]; + if (edid_ext[j+1] & 7) + max_vfreq = edid_ext[j+10] + ((edid_ext[j+11] & 3) << 8); + else + max_vfreq = edid_ext[j+10]; + + if (max_vfreq && min_vfreq) { + connector->display_info.monitor_range.max_vfreq = max_vfreq; + connector->display_info.monitor_range.min_vfreq = min_vfreq; + + return; + } + } + j++; + } +} + static int parse_amd_vsdb(struct amdgpu_dm_connector *aconnector, struct edid *edid, struct amdgpu_hdmi_vsdb_info *vsdb_info) { @@ -10707,18 +10830,31 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector, if (!adev->dm.freesync_module) goto update; - if (sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT - || sink->sink_signal == SIGNAL_TYPE_EDP) { + /* Some eDP panels only have the refresh rate range info in DisplayID */ + if ((connector->display_info.monitor_range.min_vfreq == 0 || + connector->display_info.monitor_range.max_vfreq == 0)) + parse_edid_displayid_vrr(connector, edid); + + if (edid && (sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT || + sink->sink_signal == SIGNAL_TYPE_EDP)) { bool edid_check_required = false; - if (edid) { - edid_check_required = is_dp_capable_without_timing_msa( - adev->dm.dc, - amdgpu_dm_connector); + if (is_dp_capable_without_timing_msa(adev->dm.dc, + amdgpu_dm_connector)) { + if (edid->features & DRM_EDID_FEATURE_CONTINUOUS_FREQ) { + amdgpu_dm_connector->min_vfreq = connector->display_info.monitor_range.min_vfreq; + amdgpu_dm_connector->max_vfreq = connector->display_info.monitor_range.max_vfreq; + if (amdgpu_dm_connector->max_vfreq - + amdgpu_dm_connector->min_vfreq > 10) + freesync_capable = true; + } else { + edid_check_required = edid->version > 1 || + (edid->version == 1 && + edid->revision > 1); + } } - if (edid_check_required == true && (edid->version > 1 || - (edid->version == 1 && edid->revision > 1))) { + if (edid_check_required) { for (i = 0; i < 4; i++) { timing = &edid->detailed_timings[i]; @@ -10738,14 +10874,23 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector, if (range->flags != 1) continue; - amdgpu_dm_connector->min_vfreq = range->min_vfreq; - amdgpu_dm_connector->max_vfreq = range->max_vfreq; - amdgpu_dm_connector->pixel_clock_mhz = - range->pixel_clock_mhz * 10; - connector->display_info.monitor_range.min_vfreq = range->min_vfreq; connector->display_info.monitor_range.max_vfreq = range->max_vfreq; + if (edid->revision >= 4) { + if (data->pad2 & DRM_EDID_RANGE_OFFSET_MIN_VFREQ) + connector->display_info.monitor_range.min_vfreq += 255; + if (data->pad2 & DRM_EDID_RANGE_OFFSET_MAX_VFREQ) + connector->display_info.monitor_range.max_vfreq += 255; + } + + amdgpu_dm_connector->min_vfreq = + connector->display_info.monitor_range.min_vfreq; + amdgpu_dm_connector->max_vfreq = + connector->display_info.monitor_range.max_vfreq; + amdgpu_dm_connector->pixel_clock_mhz = + range->pixel_clock_mhz * 10; + break; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 9e4cc5eeda767e..88606b805330d7 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -49,7 +49,7 @@ #define AMDGPU_DM_MAX_NUM_EDP 2 -#define AMDGPU_DMUB_NOTIFICATION_MAX 5 +#define AMDGPU_DMUB_NOTIFICATION_MAX 6 #define HDMI_AMD_VENDOR_SPECIFIC_DATA_BLOCK_IEEE_REGISTRATION_ID 0x00001A #define AMD_VSDB_VERSION_3_FEATURECAP_REPLAYMODE 0x40 diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index 97b7a0b8a1c26c..30d4c6fd95f531 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -29,7 +29,6 @@ #include "dc.h" #include "amdgpu.h" #include "amdgpu_dm_psr.h" -#include "amdgpu_dm_replay.h" #include "amdgpu_dm_crtc.h" #include "amdgpu_dm_plane.h" #include "amdgpu_dm_trace.h" @@ -124,12 +123,7 @@ static void vblank_control_worker(struct work_struct *work) * fill_dc_dirty_rects(). */ if (vblank_work->stream && vblank_work->stream->link) { - /* - * Prioritize replay, instead of psr - */ - if (vblank_work->stream->link->replay_settings.replay_feature_enabled) - amdgpu_dm_replay_enable(vblank_work->stream, false); - else if (vblank_work->enable) { + if (vblank_work->enable) { if (vblank_work->stream->link->psr_settings.psr_version < DC_PSR_VERSION_SU_1 && vblank_work->stream->link->psr_settings.psr_allow_active) amdgpu_dm_psr_disable(vblank_work->stream); @@ -138,7 +132,6 @@ static void vblank_control_worker(struct work_struct *work) #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY !amdgpu_dm_crc_window_is_activated(&vblank_work->acrtc->base) && #endif - vblank_work->stream->link->panel_config.psr.disallow_replay && vblank_work->acrtc->dm_irq_params.allow_psr_entry) { amdgpu_dm_psr_enable(vblank_work->stream); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 7c21e21bcc51a0..c8609595f324b4 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -1219,7 +1219,7 @@ static ssize_t dp_sdp_message_debugfs_write(struct file *f, const char __user *b size_t size, loff_t *pos) { int r; - uint8_t data[36]; + uint8_t data[36] = {0}; struct amdgpu_dm_connector *connector = file_inode(f)->i_private; struct dm_crtc_state *acrtc_state; uint32_t write_size = 36; @@ -1453,7 +1453,7 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf, const uint32_t rd_buf_size = 10; struct pipe_ctx *pipe_ctx; ssize_t result = 0; - int i, r, str_len = 30; + int i, r, str_len = 10; rd_buf = kcalloc(rd_buf_size, sizeof(char), GFP_KERNEL); @@ -1465,7 +1465,9 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -1566,7 +1568,9 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -1651,7 +1655,9 @@ static ssize_t dp_dsc_slice_width_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -1750,7 +1756,9 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -1835,7 +1843,9 @@ static ssize_t dp_dsc_slice_height_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -1934,7 +1944,9 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -2015,7 +2027,9 @@ static ssize_t dp_dsc_bits_per_pixel_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -2111,7 +2125,9 @@ static ssize_t dp_dsc_bits_per_pixel_write(struct file *f, const char __user *bu for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -2190,7 +2206,9 @@ static ssize_t dp_dsc_pic_width_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -2246,7 +2264,9 @@ static ssize_t dp_dsc_pic_height_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -2317,7 +2337,9 @@ static ssize_t dp_dsc_chunk_size_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -2388,7 +2410,9 @@ static ssize_t dp_dsc_slice_bpg_offset_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -2905,7 +2929,7 @@ static int psr_read_residency(void *data, u64 *val) { struct amdgpu_dm_connector *connector = data; struct dc_link *link = connector->dc_link; - u32 residency; + u32 residency = 0; link->dc->link_srv->edp_get_psr_residency(link, &residency); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 4b230933b28ebf..227a148b0f82a5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -63,6 +63,18 @@ static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps) DRM_DEBUG_DRIVER("Disabling FAMS on monitor with panel id %X\n", panel_id); edid_caps->panel_patch.disable_fams = true; break; + /* Workaround for some monitors that do not clear DPCD 0x317 if FreeSync is unsupported */ + case drm_edid_encode_panel_id('A', 'U', 'O', 0xA7AB): + case drm_edid_encode_panel_id('A', 'U', 'O', 0xE69B): + case drm_edid_encode_panel_id('B', 'O', 'E', 0x092A): + case drm_edid_encode_panel_id('L', 'G', 'D', 0x06D1): + DRM_DEBUG_DRIVER("Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id); + edid_caps->panel_patch.remove_sink_ext_caps = true; + break; + case drm_edid_encode_panel_id('S', 'D', 'C', 0x4154): + DRM_DEBUG_DRIVER("Disabling VSC on monitor with panel id %X\n", panel_id); + edid_caps->panel_patch.disable_colorimetry = true; + break; default: return; } @@ -113,6 +125,8 @@ enum dc_edid_status dm_helpers_parse_edid_caps( edid_caps->edid_hdmi = connector->display_info.is_hdmi; + apply_edid_quirks(edid_buf, edid_caps); + sad_count = drm_edid_to_sad((struct edid *) edid->raw_edid, &sads); if (sad_count <= 0) return result; @@ -139,8 +153,6 @@ enum dc_edid_status dm_helpers_parse_edid_caps( else edid_caps->speaker_flags = DEFAULT_SPEAKER_LOCATION; - apply_edid_quirks(edid_buf, edid_caps); - kfree(sads); kfree(sadb); @@ -950,6 +962,11 @@ int dm_helper_dmub_aux_transfer_sync( struct aux_payload *payload, enum aux_return_code_type *operation_result) { + if (!link->hpd_status) { + *operation_result = AUX_RET_ERROR_HPD_DISCON; + return -1; + } + return amdgpu_dm_process_dmub_aux_transfer_sync(ctx, link->link_index, payload, operation_result); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 57230661132bd9..d390e3d62e56e3 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -246,7 +246,7 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto aconnector->dsc_aux = &aconnector->mst_root->dm_dp_aux.aux; /* synaptics cascaded MST hub case */ - if (!aconnector->dsc_aux && is_synaptics_cascaded_panamera(aconnector->dc_link, port)) + if (is_synaptics_cascaded_panamera(aconnector->dc_link, port)) aconnector->dsc_aux = port->mgr->aux; if (!aconnector->dsc_aux) @@ -606,6 +606,9 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, &connector->base, dev->mode_config.tile_property, 0); + connector->colorspace_property = master->base.colorspace_property; + if (connector->colorspace_property) + drm_connector_attach_colorspace_property(connector); drm_connector_set_path_property(connector, pathprop); @@ -1112,7 +1115,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, params[count].num_slices_v = aconnector->dsc_settings.dsc_num_slices_v; params[count].bpp_overwrite = aconnector->dsc_settings.dsc_bits_per_pixel; params[count].compression_possible = stream->sink->dsc_caps.dsc_dec_caps.is_dsc_supported; - dc_dsc_get_policy_for_timing(params[count].timing, 0, &dsc_policy); + dc_dsc_get_policy_for_timing(params[count].timing, 0, &dsc_policy, dc_link_get_highest_encoding_format(stream->link)); if (!dc_dsc_compute_bandwidth_range( stream->sink->ctx->dc->res_pool->dscs[0], stream->sink->ctx->dc->debug.dsc_min_slice_height_override, @@ -1263,6 +1266,9 @@ static bool is_dsc_need_re_compute( } } + if (new_stream_on_link_num == 0) + return false; + /* check current_state if there stream on link but it is not in * new request state */ @@ -1577,7 +1583,7 @@ static bool is_dsc_common_config_possible(struct dc_stream_state *stream, { struct dc_dsc_policy dsc_policy = {0}; - dc_dsc_get_policy_for_timing(&stream->timing, 0, &dsc_policy); + dc_dsc_get_policy_for_timing(&stream->timing, 0, &dsc_policy, dc_link_get_highest_encoding_format(stream->link)); dc_dsc_compute_bandwidth_range(stream->sink->ctx->dc->res_pool->dscs[0], stream->sink->ctx->dc->debug.dsc_min_slice_height_override, dsc_policy.min_target_bpp * 16, @@ -1598,31 +1604,31 @@ enum dc_status dm_dp_mst_is_port_support_mode( unsigned int upper_link_bw_in_kbps = 0, down_link_bw_in_kbps = 0; unsigned int max_compressed_bw_in_kbps = 0; struct dc_dsc_bw_range bw_range = {0}; - struct drm_dp_mst_topology_mgr *mst_mgr; + uint16_t full_pbn = aconnector->mst_output_port->full_pbn; /* - * check if the mode could be supported if DSC pass-through is supported - * AND check if there enough bandwidth available to support the mode - * with DSC enabled. + * Consider the case with the depth of the mst topology tree is equal or less than 2 + * A. When dsc bitstream can be transmitted along the entire path + * 1. dsc is possible between source and branch/leaf device (common dsc params is possible), AND + * 2. dsc passthrough supported at MST branch, or + * 3. dsc decoding supported at leaf MST device + * Use maximum dsc compression as bw constraint + * B. When dsc bitstream cannot be transmitted along the entire path + * Use native bw as bw constraint */ if (is_dsc_common_config_possible(stream, &bw_range) && - aconnector->mst_output_port->passthrough_aux) { - mst_mgr = aconnector->mst_output_port->mgr; - mutex_lock(&mst_mgr->lock); - + (aconnector->mst_output_port->passthrough_aux || + aconnector->dsc_aux == &aconnector->mst_output_port->aux)) { cur_link_settings = stream->link->verified_link_cap; upper_link_bw_in_kbps = dc_link_bandwidth_kbps(aconnector->dc_link, - &cur_link_settings - ); - down_link_bw_in_kbps = kbps_from_pbn(aconnector->mst_output_port->full_pbn); + &cur_link_settings); + down_link_bw_in_kbps = kbps_from_pbn(full_pbn); /* pick the bottleneck */ end_to_end_bw_in_kbps = min(upper_link_bw_in_kbps, down_link_bw_in_kbps); - mutex_unlock(&mst_mgr->lock); - /* * use the maximum dsc compression bandwidth as the required * bandwidth for the mode @@ -1636,9 +1642,8 @@ enum dc_status dm_dp_mst_is_port_support_mode( } else { /* check if mode could be supported within full_pbn */ bpp = convert_dc_color_depth_into_bpc(stream->timing.display_color_depth) * 3; - pbn = drm_dp_calc_pbn_mode(stream->timing.pix_clk_100hz / 10, bpp, false); - - if (pbn > aconnector->mst_output_port->full_pbn) + pbn = drm_dp_calc_pbn_mode(stream->timing.pix_clk_100hz / 10, bpp << 4); + if (pbn > full_pbn) return DC_FAIL_BANDWIDTH_VALIDATE; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index cc74dd69acf2ba..d1329f20b7bd4b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include "amdgpu.h" @@ -848,10 +849,14 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane, } afb = to_amdgpu_framebuffer(new_state->fb); - obj = new_state->fb->obj[0]; + obj = drm_gem_fb_get_obj(new_state->fb, 0); + if (!obj) { + DRM_ERROR("Failed to get obj from framebuffer\n"); + return -EINVAL; + } + rbo = gem_to_amdgpu_bo(obj); adev = amdgpu_ttm_adev(rbo->tbo.bdev); - r = amdgpu_bo_reserve(rbo, true); if (r) { dev_err(adev->dev, "fail to reserve bo (%d)\n", r); @@ -1276,7 +1281,8 @@ void amdgpu_dm_plane_handle_cursor_update(struct drm_plane *plane, adev->dm.dc->caps.color.dpp.gamma_corr) attributes.attribute_flags.bits.ENABLE_CURSOR_DEGAMMA = 1; - attributes.pitch = afb->base.pitches[0] / afb->base.format->cpp[0]; + if (afb) + attributes.pitch = afb->base.pitches[0] / afb->base.format->cpp[0]; if (crtc_state->stream) { mutex_lock(&adev->dm.dc_lock); diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c index 6b319044758151..684b005f564c47 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c @@ -667,6 +667,9 @@ static enum bp_result get_ss_info_v3_1( ss_table_header_include = ((ATOM_ASIC_INTERNAL_SS_INFO_V3 *) bios_get_image(&bp->base, DATA_TABLES(ASIC_InternalSS_Info), struct_size(ss_table_header_include, asSpreadSpectrum, 1))); + if (!ss_table_header_include) + return BP_RESULT_UNSUPPORTED; + table_size = (le16_to_cpu(ss_table_header_include->sHeader.usStructureSize) - sizeof(ATOM_COMMON_TABLE_HEADER)) @@ -1036,6 +1039,8 @@ static enum bp_result get_ss_info_from_internal_ss_info_tbl_V2_1( &bp->base, DATA_TABLES(ASIC_InternalSS_Info), struct_size(header, asSpreadSpectrum, 1))); + if (!header) + return result; memset(info, 0, sizeof(struct spread_spectrum_info)); @@ -1109,6 +1114,8 @@ static enum bp_result get_ss_info_from_ss_info_table( get_atom_data_table_revision(header, &revision); tbl = GET_IMAGE(ATOM_SPREAD_SPECTRUM_INFO, DATA_TABLES(SS_Info)); + if (!tbl) + return result; if (1 != revision.major || 2 > revision.minor) return result; @@ -1636,6 +1643,8 @@ static uint32_t get_ss_entry_number_from_ss_info_tbl( tbl = GET_IMAGE(ATOM_SPREAD_SPECTRUM_INFO, DATA_TABLES(SS_Info)); + if (!tbl) + return number; if (1 != revision.major || 2 > revision.minor) return number; @@ -1718,6 +1727,8 @@ static uint32_t get_ss_entry_number_from_internal_ss_info_tbl_v2_1( &bp->base, DATA_TABLES(ASIC_InternalSS_Info), struct_size(header_include, asSpreadSpectrum, 1))); + if (!header_include) + return 0; size = (le16_to_cpu(header_include->sHeader.usStructureSize) - sizeof(ATOM_COMMON_TABLE_HEADER)) @@ -1756,6 +1767,9 @@ static uint32_t get_ss_entry_number_from_internal_ss_info_tbl_V3_1( header_include = ((ATOM_ASIC_INTERNAL_SS_INFO_V3 *) bios_get_image(&bp->base, DATA_TABLES(ASIC_InternalSS_Info), struct_size(header_include, asSpreadSpectrum, 1))); + if (!header_include) + return number; + size = (le16_to_cpu(header_include->sHeader.usStructureSize) - sizeof(ATOM_COMMON_TABLE_HEADER)) / sizeof(ATOM_ASIC_SS_ASSIGNMENT_V3); @@ -2552,8 +2566,8 @@ static enum bp_result construct_integrated_info( /* Sort voltage table from low to high*/ if (result == BP_RESULT_OK) { - uint32_t i; - uint32_t j; + int32_t i; + int32_t j; for (i = 1; i < NUMBER_OF_DISP_CLK_VOLTAGE; ++i) { for (j = i; j > 0; --j) { diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 484d62bcf2c2e2..384ddb28e6f6d6 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -1015,13 +1015,20 @@ static enum bp_result get_ss_info_v4_5( DC_LOG_BIOS("AS_SIGNAL_TYPE_HDMI ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; case AS_SIGNAL_TYPE_DISPLAY_PORT: - ss_info->spread_spectrum_percentage = + if (bp->base.integrated_info) { + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", bp->base.integrated_info->gpuclk_ss_percentage); + ss_info->spread_spectrum_percentage = + bp->base.integrated_info->gpuclk_ss_percentage; + ss_info->type.CENTER_MODE = + bp->base.integrated_info->gpuclk_ss_type; + } else { + ss_info->spread_spectrum_percentage = disp_cntl_tbl->dp_ss_percentage; - ss_info->spread_spectrum_range = + ss_info->spread_spectrum_range = disp_cntl_tbl->dp_ss_rate_10hz * 10; - if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) - ss_info->type.CENTER_MODE = true; - + if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) + ss_info->type.CENTER_MODE = true; + } DC_LOG_BIOS("AS_SIGNAL_TYPE_DISPLAY_PORT ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; case AS_SIGNAL_TYPE_GPU_PLL: @@ -1692,7 +1699,7 @@ static enum bp_result bios_parser_enable_disp_power_gating( static enum bp_result bios_parser_enable_lvtma_control( struct dc_bios *dcb, uint8_t uc_pwr_on, - uint8_t panel_instance, + uint8_t pwrseq_instance, uint8_t bypass_panel_control_wait) { struct bios_parser *bp = BP_FROM_DCB(dcb); @@ -1700,7 +1707,7 @@ static enum bp_result bios_parser_enable_lvtma_control( if (!bp->cmd_tbl.enable_lvtma_control) return BP_RESULT_FAILURE; - return bp->cmd_tbl.enable_lvtma_control(bp, uc_pwr_on, panel_instance, bypass_panel_control_wait); + return bp->cmd_tbl.enable_lvtma_control(bp, uc_pwr_on, pwrseq_instance, bypass_panel_control_wait); } static bool bios_parser_is_accelerated_mode( @@ -1853,19 +1860,21 @@ static enum bp_result get_firmware_info_v3_2( /* Vega12 */ smu_info_v3_2 = GET_IMAGE(struct atom_smu_info_v3_2, DATA_TABLES(smu_info)); - DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage); if (!smu_info_v3_2) return BP_RESULT_BADBIOSTABLE; + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage); + info->default_engine_clk = smu_info_v3_2->bootup_dcefclk_10khz * 10; } else if (revision.minor == 3) { /* Vega20 */ smu_info_v3_3 = GET_IMAGE(struct atom_smu_info_v3_3, DATA_TABLES(smu_info)); - DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage); if (!smu_info_v3_3) return BP_RESULT_BADBIOSTABLE; + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage); + info->default_engine_clk = smu_info_v3_3->bootup_dcefclk_10khz * 10; } @@ -2428,10 +2437,11 @@ static enum bp_result get_integrated_info_v11( info_v11 = GET_IMAGE(struct atom_integrated_system_info_v1_11, DATA_TABLES(integratedsysteminfo)); - DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage); if (info_v11 == NULL) return BP_RESULT_BADBIOSTABLE; + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage); + info->gpu_cap_info = le32_to_cpu(info_v11->gpucapinfo); /* @@ -2643,11 +2653,12 @@ static enum bp_result get_integrated_info_v2_1( info_v2_1 = GET_IMAGE(struct atom_integrated_system_info_v2_1, DATA_TABLES(integratedsysteminfo)); - DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage); if (info_v2_1 == NULL) return BP_RESULT_BADBIOSTABLE; + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage); + info->gpu_cap_info = le32_to_cpu(info_v2_1->gpucapinfo); /* @@ -2805,11 +2816,11 @@ static enum bp_result get_integrated_info_v2_2( info_v2_2 = GET_IMAGE(struct atom_integrated_system_info_v2_2, DATA_TABLES(integratedsysteminfo)); - DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage); - if (info_v2_2 == NULL) return BP_RESULT_BADBIOSTABLE; + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage); + info->gpu_cap_info = le32_to_cpu(info_v2_2->gpucapinfo); /* @@ -2826,6 +2837,8 @@ static enum bp_result get_integrated_info_v2_2( info->ma_channel_number = info_v2_2->umachannelnumber; info->dp_ss_control = le16_to_cpu(info_v2_2->reserved1); + info->gpuclk_ss_percentage = info_v2_2->gpuclk_ss_percentage; + info->gpuclk_ss_type = info_v2_2->gpuclk_ss_type; for (i = 0; i < NUMBER_OF_UCHAR_FOR_GUID; ++i) { info->ext_disp_conn_info.gu_id[i] = @@ -2922,8 +2935,11 @@ static enum bp_result construct_integrated_info( struct atom_common_table_header *header; struct atom_data_revision revision; - uint32_t i; - uint32_t j; + int32_t i; + int32_t j; + + if (!info) + return result; if (info && DATA_TABLES(integratedsysteminfo)) { header = GET_IMAGE(struct atom_common_table_header, @@ -2948,6 +2964,7 @@ static enum bp_result construct_integrated_info( result = get_integrated_info_v2_1(bp, info); break; case 2: + case 3: result = get_integrated_info_v2_2(bp, info); break; default: diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c index 90a02d7bd3da3f..ab0adabf9dd4c6 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c @@ -976,7 +976,7 @@ static unsigned int get_smu_clock_info_v3_1(struct bios_parser *bp, uint8_t id) static enum bp_result enable_lvtma_control( struct bios_parser *bp, uint8_t uc_pwr_on, - uint8_t panel_instance, + uint8_t pwrseq_instance, uint8_t bypass_panel_control_wait); static void init_enable_lvtma_control(struct bios_parser *bp) @@ -989,7 +989,7 @@ static void init_enable_lvtma_control(struct bios_parser *bp) static void enable_lvtma_control_dmcub( struct dc_dmub_srv *dmcub, uint8_t uc_pwr_on, - uint8_t panel_instance, + uint8_t pwrseq_instance, uint8_t bypass_panel_control_wait) { @@ -1002,8 +1002,8 @@ static void enable_lvtma_control_dmcub( DMUB_CMD__VBIOS_LVTMA_CONTROL; cmd.lvtma_control.data.uc_pwr_action = uc_pwr_on; - cmd.lvtma_control.data.panel_inst = - panel_instance; + cmd.lvtma_control.data.pwrseq_inst = + pwrseq_instance; cmd.lvtma_control.data.bypass_panel_control_wait = bypass_panel_control_wait; dm_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); @@ -1012,7 +1012,7 @@ static void enable_lvtma_control_dmcub( static enum bp_result enable_lvtma_control( struct bios_parser *bp, uint8_t uc_pwr_on, - uint8_t panel_instance, + uint8_t pwrseq_instance, uint8_t bypass_panel_control_wait) { enum bp_result result = BP_RESULT_FAILURE; @@ -1021,7 +1021,7 @@ static enum bp_result enable_lvtma_control( bp->base.ctx->dc->debug.dmub_command_table) { enable_lvtma_control_dmcub(bp->base.ctx->dmub_srv, uc_pwr_on, - panel_instance, + pwrseq_instance, bypass_panel_control_wait); return BP_RESULT_OK; } diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.h b/drivers/gpu/drm/amd/display/dc/bios/command_table2.h index b6d09bf6cf72b6..41c8c014397f29 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.h +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.h @@ -96,7 +96,7 @@ struct cmd_tbl { struct bios_parser *bp, uint8_t id); enum bp_result (*enable_lvtma_control)(struct bios_parser *bp, uint8_t uc_pwr_on, - uint8_t panel_instance, + uint8_t pwrseq_instance, uint8_t bypass_panel_control_wait); }; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index 0c6a4ab72b1d29..97cdc24cef9a5c 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -484,7 +484,8 @@ static void build_watermark_ranges(struct clk_bw_params *bw_params, struct pp_sm ranges->reader_wm_sets[num_valid_sets].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX; /* Modify previous watermark range to cover up to max */ - ranges->reader_wm_sets[num_valid_sets - 1].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX; + if (num_valid_sets > 0) + ranges->reader_wm_sets[num_valid_sets - 1].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX; } num_valid_sets++; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c index 7326b756584610..2618504e260e47 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c @@ -131,30 +131,27 @@ static int dcn314_get_active_display_cnt_wa( return display_count; } -static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) +static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, + bool safe_to_lower, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; for (i = 0; i < dc->res_pool->pipe_count; ++i) { - struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + struct pipe_ctx *pipe = safe_to_lower + ? &context->res_ctx.pipe_ctx[i] + : &dc->current_state->res_ctx.pipe_ctx[i]; if (pipe->top_pipe || pipe->prev_odm_pipe) continue; if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) { - struct stream_encoder *stream_enc = pipe->stream_res.stream_enc; - if (disable) { - if (stream_enc && stream_enc->funcs->disable_fifo) - pipe->stream_res.stream_enc->funcs->disable_fifo(stream_enc); + if (pipe->stream_res.tg && pipe->stream_res.tg->funcs->immediate_disable_crtc) + pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); - pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); reset_sync_context_for_pipe(dc, context, i); } else { pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); - - if (stream_enc && stream_enc->funcs->enable_fifo) - pipe->stream_res.stream_enc->funcs->enable_fifo(stream_enc); } } } @@ -252,11 +249,11 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base, } if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - dcn314_disable_otg_wa(clk_mgr_base, context, true); + dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn314_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - dcn314_disable_otg_wa(clk_mgr_base, context, false); + dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false); update_dispclk = true; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index b2c4f97afc8b4c..d4d3f58a613f7a 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -145,6 +145,10 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, */ clk_mgr_base->clks.zstate_support = new_clocks->zstate_support; if (safe_to_lower) { + if (clk_mgr_base->clks.dtbclk_en && !new_clocks->dtbclk_en) { + dcn315_smu_set_dtbclk(clk_mgr, false); + clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en; + } /* check that we're not already in lower */ if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_LOW_POWER) { display_count = dcn315_get_active_display_cnt_wa(dc, context); @@ -160,6 +164,10 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, } } } else { + if (!clk_mgr_base->clks.dtbclk_en && new_clocks->dtbclk_en) { + dcn315_smu_set_dtbclk(clk_mgr, true); + clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en; + } /* check that we're not already in D0 */ if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_MISSION_MODE) { union display_idle_optimization_u idle_info = { 0 }; @@ -334,7 +342,7 @@ static struct wm_table lpddr5_wm_table = { { .wm_inst = WM_A, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -342,7 +350,7 @@ static struct wm_table lpddr5_wm_table = { { .wm_inst = WM_B, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -350,7 +358,7 @@ static struct wm_table lpddr5_wm_table = { { .wm_inst = WM_C, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -358,7 +366,7 @@ static struct wm_table lpddr5_wm_table = { { .wm_inst = WM_D, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 09151cc56ce4f2..a13ead3d21e310 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -99,20 +99,25 @@ static int dcn316_get_active_display_cnt_wa( return display_count; } -static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) +static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, + bool safe_to_lower, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; for (i = 0; i < dc->res_pool->pipe_count; ++i) { - struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + struct pipe_ctx *pipe = safe_to_lower + ? &context->res_ctx.pipe_ctx[i] + : &dc->current_state->res_ctx.pipe_ctx[i]; if (pipe->top_pipe || pipe->prev_odm_pipe) continue; - if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL || - dc_is_virtual_signal(pipe->stream->signal))) { + if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal) || + !pipe->stream->link_enc)) { if (disable) { - pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); + if (pipe->stream_res.tg && pipe->stream_res.tg->funcs->immediate_disable_crtc) + pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); + reset_sync_context_for_pipe(dc, context, i); } else pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); @@ -207,11 +212,11 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base, } if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - dcn316_disable_otg_wa(clk_mgr_base, context, true); + dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn316_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - dcn316_disable_otg_wa(clk_mgr_base, context, false); + dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false); update_dispclk = true; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c index e9345f6554dbcb..2428a4763b85f6 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c @@ -547,8 +547,12 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, * since we calculate mode support based on softmax being the max UCLK * frequency. */ - dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, - dc->clk_mgr->bw_params->dc_mode_softmax_memclk); + if (dc->debug.disable_dc_mode_overwrite) { + dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz); + dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz); + } else + dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, + dc->clk_mgr->bw_params->dc_mode_softmax_memclk); } else { dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz); } @@ -581,8 +585,13 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, /* set UCLK to requested value if P-State switching is supported, or to re-enable P-State switching */ if (clk_mgr_base->clks.p_state_change_support && (update_uclk || !clk_mgr_base->clks.prev_p_state_change_support) && - !dc->work_arounds.clock_update_disable_mask.uclk) + !dc->work_arounds.clock_update_disable_mask.uclk) { + if (dc->clk_mgr->dc_mode_softmax_enabled && dc->debug.disable_dc_mode_overwrite) + dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK, + max((int)dc->clk_mgr->bw_params->dc_mode_softmax_memclk, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz))); + dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz)); + } if (clk_mgr_base->clks.num_ways != new_clocks->num_ways && clk_mgr_base->clks.num_ways > new_clocks->num_ways) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index d08e60dff46deb..c2efe18ceacd07 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -990,7 +990,8 @@ static bool dc_construct(struct dc *dc, /* set i2c speed if not done by the respective dcnxxx__resource.c */ if (dc->caps.i2c_speed_in_khz_hdcp == 0) dc->caps.i2c_speed_in_khz_hdcp = dc->caps.i2c_speed_in_khz; - + if (dc->caps.max_optimizable_video_width == 0) + dc->caps.max_optimizable_video_width = 5120; dc->clk_mgr = dc_clk_mgr_create(dc->ctx, dc->res_pool->pp_smu, dc->res_pool->dccg); if (!dc->clk_mgr) goto fail; @@ -1069,53 +1070,6 @@ static void apply_ctx_interdependent_lock(struct dc *dc, } } -static void phantom_pipe_blank( - struct dc *dc, - struct timing_generator *tg, - int width, - int height) -{ - struct dce_hwseq *hws = dc->hwseq; - enum dc_color_space color_space; - struct tg_color black_color = {0}; - struct output_pixel_processor *opp = NULL; - uint32_t num_opps, opp_id_src0, opp_id_src1; - uint32_t otg_active_width, otg_active_height; - uint32_t i; - - /* program opp dpg blank color */ - color_space = COLOR_SPACE_SRGB; - color_space_to_black_color(dc, color_space, &black_color); - - otg_active_width = width; - otg_active_height = height; - - /* get the OPTC source */ - tg->funcs->get_optc_source(tg, &num_opps, &opp_id_src0, &opp_id_src1); - ASSERT(opp_id_src0 < dc->res_pool->res_cap->num_opp); - - for (i = 0; i < dc->res_pool->res_cap->num_opp; i++) { - if (dc->res_pool->opps[i] != NULL && dc->res_pool->opps[i]->inst == opp_id_src0) { - opp = dc->res_pool->opps[i]; - break; - } - } - - if (opp && opp->funcs->opp_set_disp_pattern_generator) - opp->funcs->opp_set_disp_pattern_generator( - opp, - CONTROLLER_DP_TEST_PATTERN_SOLID_COLOR, - CONTROLLER_DP_COLOR_SPACE_UDEFINED, - COLOR_DEPTH_UNDEFINED, - &black_color, - otg_active_width, - otg_active_height, - 0); - - if (tg->funcs->is_tg_enabled(tg)) - hws->funcs.wait_for_blank_complete(opp); -} - static void dc_update_viusal_confirm_color(struct dc *dc, struct dc_state *context, struct pipe_ctx *pipe_ctx) { if (dc->ctx->dce_version >= DCN_VERSION_1_0) { @@ -1206,7 +1160,8 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) main_pipe_width = old_stream->mall_stream_config.paired_stream->dst.width; main_pipe_height = old_stream->mall_stream_config.paired_stream->dst.height; - phantom_pipe_blank(dc, tg, main_pipe_width, main_pipe_height); + if (dc->hwss.blank_phantom) + dc->hwss.blank_phantom(dc, tg, main_pipe_width, main_pipe_height); tg->funcs->enable_crtc(tg); } } @@ -1343,6 +1298,7 @@ struct dc *dc_create(const struct dc_init_data *init_params) return NULL; if (init_params->dce_environment == DCE_ENV_VIRTUAL_HW) { + dc->caps.linear_pitch_alignment = 64; if (!dc_construct_ctx(dc, init_params)) goto destruct_dc; } else { @@ -1735,7 +1691,7 @@ bool dc_validate_boot_timing(const struct dc *dc, if (crtc_timing->pix_clk_100hz != pix_clk_100hz) return false; - if (!se->funcs->dp_get_pixel_format) + if (!se || !se->funcs->dp_get_pixel_format) return false; if (!se->funcs->dp_get_pixel_format( @@ -1755,6 +1711,9 @@ bool dc_validate_boot_timing(const struct dc *dc, return false; } + if (link->dpcd_caps.channel_coding_cap.bits.DP_128b_132b_SUPPORTED) + return false; + if (dc->link_srv->edp_is_ilr_optimization_required(link, crtc_timing)) { DC_LOG_EVENT_LINK_TRAINING("Seamless boot disabled to optimize eDP link rate\n"); return false; @@ -1888,7 +1847,7 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c if (dc->hwss.subvp_pipe_control_lock) dc->hwss.subvp_pipe_control_lock(dc, context, true, true, NULL, subvp_prev_use); - if (dc->debug.enable_double_buffered_dsc_pg_support) + if (dc->hwss.update_dsc_pg) dc->hwss.update_dsc_pg(dc, context, false); disable_dangling_plane(dc, context); @@ -1993,9 +1952,13 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c wait_for_no_pipes_pending(dc, context); /* pplib is notified if disp_num changed */ dc->hwss.optimize_bandwidth(dc, context); + /* Need to do otg sync again as otg could be out of sync due to otg + * workaround applied during clock update + */ + dc_trigger_sync(dc, context); } - if (dc->debug.enable_double_buffered_dsc_pg_support) + if (dc->hwss.update_dsc_pg) dc->hwss.update_dsc_pg(dc, context, true); if (dc->ctx->dce_version >= DCE_VERSION_MAX) @@ -2242,7 +2205,7 @@ void dc_post_update_surfaces_to_stream(struct dc *dc) dc->hwss.optimize_bandwidth(dc, context); - if (dc->debug.enable_double_buffered_dsc_pg_support) + if (dc->hwss.update_dsc_pg) dc->hwss.update_dsc_pg(dc, context, true); } @@ -2488,6 +2451,7 @@ static enum surface_update_type get_plane_info_update_type(const struct dc_surfa } static enum surface_update_type get_scaling_info_update_type( + const struct dc *dc, const struct dc_surface_update *u) { union surface_update_flags *update_flags = &u->surface->update_flags; @@ -2520,6 +2484,12 @@ static enum surface_update_type get_scaling_info_update_type( update_flags->bits.clock_change = 1; } + if (u->scaling_info->src_rect.width > dc->caps.max_optimizable_video_width && + (u->scaling_info->clip_rect.width > u->surface->clip_rect.width || + u->scaling_info->clip_rect.height > u->surface->clip_rect.height)) + /* Changing clip size of a large surface may result in MPC slice count change */ + update_flags->bits.bandwidth_change = 1; + if (u->scaling_info->src_rect.x != u->surface->src_rect.x || u->scaling_info->src_rect.y != u->surface->src_rect.y || u->scaling_info->clip_rect.x != u->surface->clip_rect.x @@ -2557,7 +2527,7 @@ static enum surface_update_type det_surface_update(const struct dc *dc, type = get_plane_info_update_type(u); elevate_update_type(&overall_type, type); - type = get_scaling_info_update_type(u); + type = get_scaling_info_update_type(dc, u); elevate_update_type(&overall_type, type); if (u->flip_addr) { @@ -3571,7 +3541,7 @@ static void commit_planes_for_stream(struct dc *dc, if (get_seamless_boot_stream_count(context) == 0) dc->hwss.prepare_bandwidth(dc, context); - if (dc->debug.enable_double_buffered_dsc_pg_support) + if (dc->hwss.update_dsc_pg) dc->hwss.update_dsc_pg(dc, context, false); context_clock_trace(dc, context); @@ -3827,7 +3797,8 @@ static void commit_planes_for_stream(struct dc *dc, } if ((update_type != UPDATE_TYPE_FAST) && stream->update_flags.bits.dsc_changed) - if (top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_enable) { + if (top_pipe_to_program && + top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_enable) { top_pipe_to_program->stream_res.tg->funcs->wait_for_state( top_pipe_to_program->stream_res.tg, CRTC_STATE_VACTIVE); @@ -4374,6 +4345,14 @@ bool dc_update_planes_and_stream(struct dc *dc, update_type, context); } else { + if (!stream_update && + dc->hwss.is_pipe_topology_transition_seamless && + !dc->hwss.is_pipe_topology_transition_seamless( + dc, dc->current_state, context)) { + + DC_LOG_ERROR("performing non-seamless pipe topology transition with surface only update!\n"); + BREAK_TO_DEBUGGER(); + } commit_planes_for_stream( dc, srf_updates, @@ -4737,7 +4716,8 @@ void dc_allow_idle_optimizations(struct dc *dc, bool allow) if (allow == dc->idle_optimizations_allowed) return; - if (dc->hwss.apply_idle_power_optimizations && dc->hwss.apply_idle_power_optimizations(dc, allow)) + if (dc->hwss.apply_idle_power_optimizations && dc->clk_mgr != NULL && + dc->hwss.apply_idle_power_optimizations(dc, allow)) dc->idle_optimizations_allowed = allow; } @@ -4895,18 +4875,28 @@ void dc_mclk_switch_using_fw_based_vblank_stretch_shut_down(struct dc *dc) */ bool dc_is_dmub_outbox_supported(struct dc *dc) { - /* DCN31 B0 USB4 DPIA needs dmub notifications for interrupts */ - if (dc->ctx->asic_id.chip_family == FAMILY_YELLOW_CARP && - dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0 && - !dc->debug.dpia_debug.bits.disable_dpia) - return true; + switch (dc->ctx->asic_id.chip_family) { - if (dc->ctx->asic_id.chip_family == AMDGPU_FAMILY_GC_11_0_1 && - !dc->debug.dpia_debug.bits.disable_dpia) - return true; + case FAMILY_YELLOW_CARP: + /* DCN31 B0 USB4 DPIA needs dmub notifications for interrupts */ + if (dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0 && + !dc->debug.dpia_debug.bits.disable_dpia) + return true; + break; + + case AMDGPU_FAMILY_GC_11_0_1: + case AMDGPU_FAMILY_GC_11_5_0: + if (!dc->debug.dpia_debug.bits.disable_dpia) + return true; + break; + + default: + break; + } /* dmub aux needs dmub notifications to be enabled */ return dc->debug.enable_dmub_aux_for_legacy_ddc; + } /** @@ -5284,3 +5274,24 @@ void dc_query_current_properties(struct dc *dc, struct dc_current_properties *pr properties->cursor_size_limit = subvp_in_use ? 64 : dc->caps.max_cursor_size; } +/** + ***************************************************************************** + * dc_set_edp_power() - DM controls eDP power to be ON/OFF + * + * Called when DM wants to power on/off eDP. + * Only work on links with flag skip_implict_edp_power_control is set. + * + ***************************************************************************** + */ +void dc_set_edp_power(const struct dc *dc, struct dc_link *edp_link, + bool powerOn) +{ + if (edp_link->connector_signal != SIGNAL_TYPE_EDP) + return; + + if (edp_link->skip_implict_edp_power_control == false) + return; + + edp_link->dc->link_srv->edp_set_panel_power(edp_link, powerOn); +} + diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c index ed94187c2afa2d..f365773d571485 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c @@ -497,7 +497,7 @@ void dc_link_enable_hpd_filter(struct dc_link *link, bool enable) link->dc->link_srv->enable_hpd_filter(link, enable); } -bool dc_link_validate(struct dc *dc, const struct dc_stream_state *streams, const unsigned int count) +bool dc_link_dp_dpia_validate(struct dc *dc, const struct dc_stream_state *streams, const unsigned int count) { return dc->link_srv->validate_dpia_bandwidth(streams, count); } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index f7b51aca602006..99fcd39bb15e0d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -996,7 +996,7 @@ static void adjust_recout_for_visual_confirm(struct rect *recout, struct dc *dc = pipe_ctx->stream->ctx->dc; int dpp_offset, base_offset; - if (dc->debug.visual_confirm == VISUAL_CONFIRM_DISABLE) + if (dc->debug.visual_confirm == VISUAL_CONFIRM_DISABLE || !pipe_ctx->plane_res.dpp) return; dpp_offset = pipe_ctx->stream->timing.v_addressable / VISUAL_CONFIRM_DPP_OFFSET_DENO; @@ -2154,6 +2154,8 @@ static bool are_stream_backends_same( bool dc_is_stream_unchanged( struct dc_stream_state *old_stream, struct dc_stream_state *stream) { + if (!old_stream || !stream) + return false; if (!are_stream_backends_same(old_stream, stream)) return false; @@ -2385,6 +2387,9 @@ static struct audio *find_first_free_audio( { int i, available_audio_count; + if (id == ENGINE_ID_UNKNOWN) + return NULL; + available_audio_count = pool->audio_count; for (i = 0; i < available_audio_count; i++) { @@ -2874,8 +2879,10 @@ static bool planes_changed_for_existing_stream(struct dc_state *context, } } - if (!stream_status) + if (!stream_status) { ASSERT(0); + return false; + } for (i = 0; i < set_count; i++) if (set[i].stream == stream) @@ -3924,6 +3931,9 @@ void resource_build_bit_depth_reduction_params(struct dc_stream_state *stream, enum dc_status dc_validate_stream(struct dc *dc, struct dc_stream_state *stream) { + if (dc == NULL || stream == NULL) + return DC_ERROR_UNEXPECTED; + struct dc_link *link = stream->link; struct timing_generator *tg = dc->res_pool->timing_generators[0]; enum dc_status res = DC_OK; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index 01fe2d2fd24172..ebe571fcefe32e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -582,7 +582,7 @@ uint32_t dc_stream_get_vblank_counter(const struct dc_stream_state *stream) for (i = 0; i < MAX_PIPES; i++) { struct timing_generator *tg = res_ctx->pipe_ctx[i].stream_res.tg; - if (res_ctx->pipe_ctx[i].stream != stream) + if (res_ctx->pipe_ctx[i].stream != stream || !tg) continue; return tg->funcs->get_frame_count(tg); @@ -641,7 +641,7 @@ bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream, for (i = 0; i < MAX_PIPES; i++) { struct timing_generator *tg = res_ctx->pipe_ctx[i].stream_res.tg; - if (res_ctx->pipe_ctx[i].stream != stream) + if (res_ctx->pipe_ctx[i].stream != stream || !tg) continue; tg->funcs->get_scanoutpos(tg, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c index a80e45300783c0..f4f3ca7aad60e2 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c @@ -154,7 +154,8 @@ const struct dc_plane_status *dc_plane_get_status( if (pipe_ctx->plane_state != plane_state) continue; - pipe_ctx->plane_state->status.is_flip_pending = false; + if (pipe_ctx->plane_state) + pipe_ctx->plane_state->status.is_flip_pending = false; break; } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 31e3183497a7f5..5f2eac868b7472 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -231,6 +231,11 @@ struct dc_caps { uint32_t dmdata_alloc_size; unsigned int max_cursor_size; unsigned int max_video_width; + /* + * max video plane width that can be safely assumed to be always + * supported by single DPP pipe. + */ + unsigned int max_optimizable_video_width; unsigned int min_horizontal_blanking_period; int linear_pitch_alignment; bool dcc_const_color; @@ -1533,7 +1538,6 @@ struct dc_link { enum edp_revision edp_revision; union dpcd_sink_ext_caps dpcd_sink_ext_caps; - struct backlight_settings backlight_settings; struct psr_settings psr_settings; struct replay_settings replay_settings; @@ -1573,6 +1577,7 @@ struct dc_link { struct phy_state phy_state; // BW ALLOCATON USB4 ONLY struct dc_dpia_bw_alloc dpia_bw_alloc_config; + bool skip_implict_edp_power_control; }; /* Return an enumerated dc_link. @@ -1592,6 +1597,9 @@ void dc_get_edp_links(const struct dc *dc, struct dc_link **edp_links, int *edp_num); +void dc_set_edp_power(const struct dc *dc, struct dc_link *edp_link, + bool powerOn); + /* The function initiates detection handshake over the given link. It first * determines if there are display connections over the link. If so it initiates * detection protocols supported by the connected receiver device. The function @@ -2108,11 +2116,11 @@ int dc_link_dp_dpia_handle_usb4_bandwidth_allocation_for_link( * * @dc: pointer to dc struct * @stream: pointer to all possible streams - * @num_streams: number of valid DPIA streams + * @count: number of valid DPIA streams * * return: TRUE if bw used by DPIAs doesn't exceed available BW else return FALSE */ -bool dc_link_validate(struct dc *dc, const struct dc_stream_state *streams, +bool dc_link_dp_dpia_validate(struct dc *dc, const struct dc_stream_state *streams, const unsigned int count); /* Sink Interfaces - A sink corresponds to a display output device */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h index be9aa1a71847d7..26940d94d8fb40 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h @@ -140,7 +140,7 @@ struct dc_vbios_funcs { enum bp_result (*enable_lvtma_control)( struct dc_bios *bios, uint8_t uc_pwr_on, - uint8_t panel_instance, + uint8_t pwrseq_instance, uint8_t bypass_panel_control_wait); enum bp_result (*get_soc_bb_info)( diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h index cfaa39c5dd16bd..83719f5bea4956 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h @@ -1433,6 +1433,12 @@ struct dp_trace { #ifndef DP_TUNNELING_STATUS #define DP_TUNNELING_STATUS 0xE0025 /* 1.4a */ #endif +#ifndef DP_TUNNELING_MAX_LINK_RATE +#define DP_TUNNELING_MAX_LINK_RATE 0xE0028 /* 1.4a */ +#endif +#ifndef DP_TUNNELING_MAX_LANE_COUNT +#define DP_TUNNELING_MAX_LANE_COUNT 0xE0029 /* 1.4a */ +#endif #ifndef DPTX_BW_ALLOCATION_MODE_CONTROL #define DPTX_BW_ALLOCATION_MODE_CONTROL 0xE0030 /* 1.4a */ #endif diff --git a/drivers/gpu/drm/amd/display/dc/dc_dsc.h b/drivers/gpu/drm/amd/display/dc/dc_dsc.h index fe3078b8789ef1..01c07545ef6b47 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dsc.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dsc.h @@ -100,7 +100,8 @@ uint32_t dc_dsc_stream_bandwidth_overhead_in_kbps( */ void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, uint32_t max_target_bpp_limit_override_x16, - struct dc_dsc_policy *policy); + struct dc_dsc_policy *policy, + const enum dc_link_encoding_format link_encoding); void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit); diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h index 100d62162b717e..00de342e5290b7 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h @@ -244,7 +244,7 @@ enum pixel_format { #define DC_MAX_DIRTY_RECTS 3 struct dc_flip_addrs { struct dc_plane_address address; - unsigned int flip_timestamp_in_us; + unsigned long long flip_timestamp_in_us; bool flip_immediate; /* TODO: add flip duration for FreeSync */ bool triplebuffer_flips; @@ -465,6 +465,7 @@ struct dc_cursor_mi_param { struct fixed31_32 v_scale_ratio; enum dc_rotation_angle rotation; bool mirror; + struct dc_stream_state *stream; }; /* IPP related types */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 3697ea1d14c1bf..d5b3e3a32cc6d4 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -302,7 +302,6 @@ struct dc_stream_state { bool vblank_synchronized; bool fpo_in_use; struct mall_stream_config mall_stream_config; - bool skip_edp_power_down; }; #define ABM_LEVEL_IMMEDIATE_DISABLE 255 diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index 445ad79001ce2d..6eaa02a80344bc 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -189,6 +189,8 @@ struct dc_panel_patch { unsigned int disable_fams; unsigned int skip_avmute; unsigned int mst_start_top_delay; + unsigned int remove_sink_ext_caps; + unsigned int disable_colorimetry; }; struct dc_edid_caps { @@ -1002,10 +1004,6 @@ struct link_mst_stream_allocation_table { struct link_mst_stream_allocation stream_allocations[MAX_CONTROLLER_NUM]; }; -struct backlight_settings { - uint32_t backlight_millinits; -}; - /* PSR feature flags */ struct psr_settings { bool psr_feature_enabled; // PSR is supported by sink @@ -1113,21 +1111,25 @@ struct dc_panel_config { } ilr; }; +#define MAX_SINKS_PER_LINK 4 + /* * USB4 DPIA BW ALLOCATION STRUCTS */ struct dc_dpia_bw_alloc { - int sink_verified_bw; // The Verified BW that sink can allocated and use that has been verified already - int sink_allocated_bw; // The Actual Allocated BW that sink currently allocated - int sink_max_bw; // The Max BW that sink can require/support + int remote_sink_req_bw[MAX_SINKS_PER_LINK]; // BW requested by remote sinks + int link_verified_bw; // The Verified BW that link can allocated and use that has been verified already + int link_max_bw; // The Max BW that link can require/support + int allocated_bw; // The Actual Allocated BW for this DPIA int estimated_bw; // The estimated available BW for this DPIA int bw_granularity; // BW Granularity + int dp_overhead; // DP overhead in dp tunneling bool bw_alloc_enabled; // The BW Alloc Mode Support is turned ON for all 3: DP-Tx & Dpia & CM bool response_ready; // Response ready from the CM side + uint8_t nrd_max_lane_count; // Non-reduced max lane count + uint8_t nrd_max_link_rate; // Non-reduced max link rate }; -#define MAX_SINKS_PER_LINK 4 - enum dc_hpd_enable_select { HPD_EN_FOR_ALL_EDP = 0, HPD_EN_FOR_PRIMARY_EDP_ONLY, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c index b87bfecb7755ae..a8e79104b684ea 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c @@ -586,7 +586,8 @@ static void dcn10_dmcu_set_psr_enable(struct dmcu *dmcu, bool enable, bool wait) if (state == PSR_STATE0) break; } - fsleep(500); + /* must *not* be fsleep - this can be called from high irq levels */ + udelay(500); } /* assert if max retry hit */ diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_abm.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_abm.c index d3e6544022b787..930fd929e93a4f 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_abm.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_abm.c @@ -145,7 +145,11 @@ static bool dmub_abm_save_restore_ex( return ret; } -static bool dmub_abm_set_pipe_ex(struct abm *abm, uint32_t otg_inst, uint32_t option, uint32_t panel_inst) +static bool dmub_abm_set_pipe_ex(struct abm *abm, + uint32_t otg_inst, + uint32_t option, + uint32_t panel_inst, + uint32_t pwrseq_inst) { bool ret = false; unsigned int feature_support; @@ -153,7 +157,7 @@ static bool dmub_abm_set_pipe_ex(struct abm *abm, uint32_t otg_inst, uint32_t op feature_support = abm_feature_support(abm, panel_inst); if (feature_support == ABM_LCD_SUPPORT) - ret = dmub_abm_set_pipe(abm, otg_inst, option, panel_inst); + ret = dmub_abm_set_pipe(abm, otg_inst, option, panel_inst, pwrseq_inst); return ret; } diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.c index 592a8f7a1c6d00..42c802afc4681b 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.c @@ -254,7 +254,11 @@ bool dmub_abm_save_restore( return true; } -bool dmub_abm_set_pipe(struct abm *abm, uint32_t otg_inst, uint32_t option, uint32_t panel_inst) +bool dmub_abm_set_pipe(struct abm *abm, + uint32_t otg_inst, + uint32_t option, + uint32_t panel_inst, + uint32_t pwrseq_inst) { union dmub_rb_cmd cmd; struct dc_context *dc = abm->ctx; @@ -264,6 +268,7 @@ bool dmub_abm_set_pipe(struct abm *abm, uint32_t otg_inst, uint32_t option, uint cmd.abm_set_pipe.header.type = DMUB_CMD__ABM; cmd.abm_set_pipe.header.sub_type = DMUB_CMD__ABM_SET_PIPE; cmd.abm_set_pipe.abm_set_pipe_data.otg_inst = otg_inst; + cmd.abm_set_pipe.abm_set_pipe_data.pwrseq_inst = pwrseq_inst; cmd.abm_set_pipe.abm_set_pipe_data.set_pipe_option = option; cmd.abm_set_pipe.abm_set_pipe_data.panel_inst = panel_inst; cmd.abm_set_pipe.abm_set_pipe_data.ramping_boundary = ramping_boundary; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.h b/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.h index 853564d7f4714c..07ea6c8d414f3b 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.h @@ -44,7 +44,7 @@ bool dmub_abm_save_restore( struct dc_context *dc, unsigned int panel_inst, struct abm_save_restore *pData); -bool dmub_abm_set_pipe(struct abm *abm, uint32_t otg_inst, uint32_t option, uint32_t panel_inst); +bool dmub_abm_set_pipe(struct abm *abm, uint32_t otg_inst, uint32_t option, uint32_t panel_inst, uint32_t pwrseq_inst); bool dmub_abm_set_backlight_level(struct abm *abm, unsigned int backlight_pwm_u16_16, unsigned int frame_ramp, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c index 0f24b6fbd22013..4704c9c85ee6f5 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c @@ -216,7 +216,8 @@ static void dmub_psr_enable(struct dmub_psr *dmub, bool enable, bool wait, uint8 break; } - fsleep(500); + /* must *not* be fsleep - this can be called from high irq levels */ + udelay(500); } /* assert if max retry hit */ diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c index 28149e53c2a68f..eeb5b8247c9652 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c @@ -102,7 +102,8 @@ static void dmub_replay_enable(struct dmub_replay *dmub, bool enable, bool wait, break; } - fsleep(500); + /* must *not* be fsleep - this can be called from high irq levels */ + udelay(500); } /* assert if max retry hit */ diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 2a6157555fd1e4..7b5c1498941dd6 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -788,7 +788,7 @@ void dce110_edp_power_control( struct dc_context *ctx = link->ctx; struct bp_transmitter_control cntl = { 0 }; enum bp_result bp_result; - uint8_t panel_instance; + uint8_t pwrseq_instance; if (dal_graphics_object_id_get_connector_id(link->link_enc->connector) @@ -871,7 +871,7 @@ void dce110_edp_power_control( cntl.coherent = false; cntl.lanes_number = LANE_COUNT_FOUR; cntl.hpd_sel = link->link_enc->hpd_source; - panel_instance = link->panel_cntl->inst; + pwrseq_instance = link->panel_cntl->pwrseq_inst; if (ctx->dc->ctx->dmub_srv && ctx->dc->debug.dmub_command_table) { @@ -879,11 +879,11 @@ void dce110_edp_power_control( if (cntl.action == TRANSMITTER_CONTROL_POWER_ON) { bp_result = ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, LVTMA_CONTROL_POWER_ON, - panel_instance, link->link_powered_externally); + pwrseq_instance, link->link_powered_externally); } else { bp_result = ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, LVTMA_CONTROL_POWER_OFF, - panel_instance, link->link_powered_externally); + pwrseq_instance, link->link_powered_externally); } } @@ -954,7 +954,7 @@ void dce110_edp_backlight_control( { struct dc_context *ctx = link->ctx; struct bp_transmitter_control cntl = { 0 }; - uint8_t panel_instance; + uint8_t pwrseq_instance; unsigned int pre_T11_delay = OLED_PRE_T11_DELAY; unsigned int post_T7_delay = OLED_POST_T7_DELAY; @@ -1007,7 +1007,7 @@ void dce110_edp_backlight_control( */ /* dc_service_sleep_in_milliseconds(50); */ /*edp 1.2*/ - panel_instance = link->panel_cntl->inst; + pwrseq_instance = link->panel_cntl->pwrseq_inst; if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON) { if (!link->dc->config.edp_no_power_sequencing) @@ -1032,11 +1032,11 @@ void dce110_edp_backlight_control( if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON) ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, LVTMA_CONTROL_LCD_BLON, - panel_instance, link->link_powered_externally); + pwrseq_instance, link->link_powered_externally); else ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, LVTMA_CONTROL_LCD_BLOFF, - panel_instance, link->link_powered_externally); + pwrseq_instance, link->link_powered_externally); } link_transmitter_control(ctx->dc_bios, &cntl); @@ -1179,9 +1179,10 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx) dto_params.timing = &pipe_ctx->stream->timing; dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst; if (dccg) { - dccg->funcs->set_dtbclk_dto(dccg, &dto_params); dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst); dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, dp_hpo_inst); + if (dccg && dccg->funcs->set_dtbclk_dto) + dccg->funcs->set_dtbclk_dto(dccg, &dto_params); } } else if (dccg && dccg->funcs->disable_symclk_se) { dccg->funcs->disable_symclk_se(dccg, stream_enc->stream_enc_inst, @@ -1226,7 +1227,7 @@ void dce110_blank_stream(struct pipe_ctx *pipe_ctx) struct dce_hwseq *hws = link->dc->hwseq; if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) { - if (!stream->skip_edp_power_down) + if (!link->skip_implict_edp_power_control) hws->funcs.edp_backlight_control(link, false); link->dc->hwss.set_abm_immediate_disable(pipe_ctx); } @@ -2124,7 +2125,8 @@ static void dce110_reset_hw_ctx_wrap( BREAK_TO_DEBUGGER(); } pipe_ctx_old->stream_res.tg->funcs->disable_crtc(pipe_ctx_old->stream_res.tg); - pipe_ctx_old->stream->link->phy_state.symclk_ref_cnts.otg = 0; + if (dc_is_hdmi_tmds_signal(pipe_ctx_old->stream->signal)) + pipe_ctx_old->stream->link->phy_state.symclk_ref_cnts.otg = 0; pipe_ctx_old->plane_res.mi->funcs->free_mem_input( pipe_ctx_old->plane_res.mi, dc->current_state->stream_count); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c index 3538973bd0c6cb..684e30f9cf8985 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c @@ -382,6 +382,11 @@ bool cm_helper_translate_curve_to_hw_format(struct dc_context *ctx, i += increment) { if (j == hw_points - 1) break; + if (i >= TRANSFER_FUNC_POINTS) { + DC_LOG_ERROR("Index out of bounds: i=%d, TRANSFER_FUNC_POINTS=%d\n", + i, TRANSFER_FUNC_POINTS); + return false; + } rgb_resulted[j].red = output_tf->tf_pts.red[i]; rgb_resulted[j].green = output_tf->tf_pts.green[i]; rgb_resulted[j].blue = output_tf->tf_pts.blue[i]; @@ -566,6 +571,8 @@ bool cm_helper_translate_curve_to_degamma_hw_format( i += increment) { if (j == hw_points - 1) break; + if (i >= TRANSFER_FUNC_POINTS) + return false; rgb_resulted[j].red = output_tf->tf_pts.red[i]; rgb_resulted[j].green = output_tf->tf_pts.green[i]; rgb_resulted[j].blue = output_tf->tf_pts.blue[i]; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 9834b75f1837ba..ff38a85c4fa22d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -111,7 +111,8 @@ void dcn10_lock_all_pipes(struct dc *dc, if (pipe_ctx->top_pipe || !pipe_ctx->stream || (!pipe_ctx->plane_state && !old_pipe_ctx->plane_state) || - !tg->funcs->is_tg_enabled(tg)) + !tg->funcs->is_tg_enabled(tg) || + pipe_ctx->stream->mall_stream_config.type == SUBVP_PHANTOM) continue; if (lock) @@ -1053,7 +1054,8 @@ static void dcn10_reset_back_end_for_pipe( if (pipe_ctx->stream_res.tg->funcs->set_drr) pipe_ctx->stream_res.tg->funcs->set_drr( pipe_ctx->stream_res.tg, NULL); - pipe_ctx->stream->link->phy_state.symclk_ref_cnts.otg = 0; + if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal)) + pipe_ctx->stream->link->phy_state.symclk_ref_cnts.otg = 0; } for (i = 0; i < dc->res_pool->pipe_count; i++) @@ -1830,6 +1832,9 @@ bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx, { struct dpp *dpp = pipe_ctx->plane_res.dpp; + if (!stream) + return false; + if (dpp == NULL) return false; @@ -1852,8 +1857,8 @@ bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx, } else dpp->funcs->dpp_program_regamma_pwl(dpp, NULL, OPP_REGAMMA_BYPASS); - if (stream != NULL && stream->ctx != NULL && - stream->out_transfer_func != NULL) { + if (stream->ctx && + stream->out_transfer_func) { log_tf(stream->ctx, stream->out_transfer_func, dpp->regamma_params.hw_points_num); @@ -3406,7 +3411,8 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) .h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz, .v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert, .rotation = pipe_ctx->plane_state->rotation, - .mirror = pipe_ctx->plane_state->horizontal_mirror + .mirror = pipe_ctx->plane_state->horizontal_mirror, + .stream = pipe_ctx->stream, }; bool pipe_split_on = false; bool odm_combine_on = (pipe_ctx->next_odm_pipe != NULL) || @@ -3515,7 +3521,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) (int)hubp->curs_attr.width || pos_cpy.x <= (int)hubp->curs_attr.width + pipe_ctx->plane_state->src_rect.x) { - pos_cpy.x = temp_x + viewport_width; + pos_cpy.x = 2 * viewport_width - temp_x; } } } else { @@ -3608,7 +3614,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) (int)hubp->curs_attr.width || pos_cpy.x <= (int)hubp->curs_attr.width + pipe_ctx->plane_state->src_rect.x) { - pos_cpy.x = 2 * viewport_width - temp_x; + pos_cpy.x = temp_x + viewport_width; } } } else { diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c index 994fb732a7cb76..a0d437f0ce2baf 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c @@ -690,6 +690,9 @@ static void wbscl_set_scaler_filter( int pair; uint16_t odd_coef, even_coef; + if (!filter) + return; + for (phase = 0; phase < (NUM_PHASES / 2 + 1); phase++) { for (pair = 0; pair < tap_pairs; pair++) { even_coef = filter[phase * taps + 2 * pair]; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index 4566bc7abf17e6..aa252dc2632671 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -1075,8 +1075,16 @@ void hubp2_cursor_set_position( if (src_y_offset < 0) src_y_offset = 0; /* Save necessary cursor info x, y position. w, h is saved in attribute func. */ - hubp->cur_rect.x = src_x_offset + param->viewport.x; - hubp->cur_rect.y = src_y_offset + param->viewport.y; + if (param->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 && + param->rotation != ROTATION_ANGLE_0) { + hubp->cur_rect.x = 0; + hubp->cur_rect.y = 0; + hubp->cur_rect.w = param->stream->timing.h_addressable; + hubp->cur_rect.h = param->stream->timing.v_addressable; + } else { + hubp->cur_rect.x = src_x_offset + param->viewport.x; + hubp->cur_rect.y = src_y_offset + param->viewport.y; + } } void hubp2_clk_cntl(struct hubp *hubp, bool enable) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index aeadc587433fd5..12af2859002f72 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1792,6 +1792,8 @@ void dcn20_program_front_end_for_ctx( int i; struct dce_hwseq *hws = dc->hwseq; DC_LOGGER_INIT(dc->ctx->logger); + unsigned int prev_hubp_count = 0; + unsigned int hubp_count = 0; /* Carry over GSL groups in case the context is changing. */ for (i = 0; i < dc->res_pool->pipe_count; i++) { @@ -1815,6 +1817,20 @@ void dcn20_program_front_end_for_ctx( } } + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (dc->current_state->res_ctx.pipe_ctx[i].plane_state) + prev_hubp_count++; + if (context->res_ctx.pipe_ctx[i].plane_state) + hubp_count++; + } + + if (prev_hubp_count == 0 && hubp_count > 0) { + if (dc->res_pool->hubbub->funcs->force_pstate_change_control) + dc->res_pool->hubbub->funcs->force_pstate_change_control( + dc->res_pool->hubbub, true, false); + udelay(500); + } + /* Set pipe update flags and lock pipes */ for (i = 0; i < dc->res_pool->pipe_count; i++) dcn20_detect_pipe_changes(&dc->current_state->res_ctx.pipe_ctx[i], @@ -1830,8 +1846,16 @@ void dcn20_program_front_end_for_ctx( dc->current_state->res_ctx.pipe_ctx[i].stream->mall_stream_config.type == SUBVP_PHANTOM) { struct timing_generator *tg = dc->current_state->res_ctx.pipe_ctx[i].stream_res.tg; - if (tg->funcs->enable_crtc) + if (tg->funcs->enable_crtc) { + if (dc->hwss.blank_phantom) { + int main_pipe_width, main_pipe_height; + + main_pipe_width = dc->current_state->res_ctx.pipe_ctx[i].stream->mall_stream_config.paired_stream->dst.width; + main_pipe_height = dc->current_state->res_ctx.pipe_ctx[i].stream->mall_stream_config.paired_stream->dst.height; + dc->hwss.blank_phantom(dc, tg, main_pipe_width, main_pipe_height); + } tg->funcs->enable_crtc(tg); + } } } /* OTG blank before disabling all front ends */ @@ -1954,6 +1978,10 @@ void dcn20_post_unlock_program_front_end( } } + if (dc->res_pool->hubbub->funcs->force_pstate_change_control) + dc->res_pool->hubbub->funcs->force_pstate_change_control( + dc->res_pool->hubbub, false, false); + for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; @@ -2505,7 +2533,8 @@ static void dcn20_reset_back_end_for_pipe( * the case where the same symclk is shared across multiple otg * instances */ - link->phy_state.symclk_ref_cnts.otg = 0; + if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal)) + link->phy_state.symclk_ref_cnts.otg = 0; if (link->phy_state.symclk_state == SYMCLK_ON_TX_OFF) { link_hwss->disable_link_output(link, &pipe_ctx->link_res, pipe_ctx->stream->signal); @@ -2699,18 +2728,17 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx) } if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) { - dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst; - dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, dp_hpo_inst); - - phyd32clk = get_phyd32clk_src(link); - dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk); - dto_params.otg_inst = tg->inst; dto_params.pixclk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10; dto_params.num_odm_segments = get_odm_segment_count(pipe_ctx); dto_params.timing = &pipe_ctx->stream->timing; dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr); dccg->funcs->set_dtbclk_dto(dccg, &dto_params); + dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst; + dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, dp_hpo_inst); + + phyd32clk = get_phyd32clk_src(link); + dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk); } else { } if (hws->funcs.calculate_dccg_k1_k2_values && dc->res_pool->dccg->funcs->set_pixel_rate_div) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c index 43463d08f21ba9..1b08749b084b1d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c @@ -137,7 +137,8 @@ void dcn21_PLAT_58856_wa(struct dc_state *context, struct pipe_ctx *pipe_ctx) pipe_ctx->stream->dpms_off = true; } -static bool dmub_abm_set_pipe(struct abm *abm, uint32_t otg_inst, uint32_t option, uint32_t panel_inst) +static bool dmub_abm_set_pipe(struct abm *abm, uint32_t otg_inst, + uint32_t option, uint32_t panel_inst, uint32_t pwrseq_inst) { union dmub_rb_cmd cmd; struct dc_context *dc = abm->ctx; @@ -147,6 +148,7 @@ static bool dmub_abm_set_pipe(struct abm *abm, uint32_t otg_inst, uint32_t optio cmd.abm_set_pipe.header.type = DMUB_CMD__ABM; cmd.abm_set_pipe.header.sub_type = DMUB_CMD__ABM_SET_PIPE; cmd.abm_set_pipe.abm_set_pipe_data.otg_inst = otg_inst; + cmd.abm_set_pipe.abm_set_pipe_data.pwrseq_inst = pwrseq_inst; cmd.abm_set_pipe.abm_set_pipe_data.set_pipe_option = option; cmd.abm_set_pipe.abm_set_pipe_data.panel_inst = panel_inst; cmd.abm_set_pipe.abm_set_pipe_data.ramping_boundary = ramping_boundary; @@ -179,7 +181,6 @@ void dcn21_set_abm_immediate_disable(struct pipe_ctx *pipe_ctx) struct abm *abm = pipe_ctx->stream_res.abm; uint32_t otg_inst = pipe_ctx->stream_res.tg->inst; struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl; - struct dmcu *dmcu = pipe_ctx->stream->ctx->dc->res_pool->dmcu; if (dmcu) { @@ -190,9 +191,13 @@ void dcn21_set_abm_immediate_disable(struct pipe_ctx *pipe_ctx) if (abm && panel_cntl) { if (abm->funcs && abm->funcs->set_pipe_ex) { abm->funcs->set_pipe_ex(abm, otg_inst, SET_ABM_PIPE_IMMEDIATELY_DISABLE, - panel_cntl->inst); + panel_cntl->inst, panel_cntl->pwrseq_inst); } else { - dmub_abm_set_pipe(abm, otg_inst, SET_ABM_PIPE_IMMEDIATELY_DISABLE, panel_cntl->inst); + dmub_abm_set_pipe(abm, + otg_inst, + SET_ABM_PIPE_IMMEDIATELY_DISABLE, + panel_cntl->inst, + panel_cntl->pwrseq_inst); } panel_cntl->funcs->store_backlight_level(panel_cntl); } @@ -201,21 +206,32 @@ void dcn21_set_abm_immediate_disable(struct pipe_ctx *pipe_ctx) void dcn21_set_pipe(struct pipe_ctx *pipe_ctx) { struct abm *abm = pipe_ctx->stream_res.abm; - uint32_t otg_inst = pipe_ctx->stream_res.tg->inst; + struct timing_generator *tg = pipe_ctx->stream_res.tg; struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl; struct dmcu *dmcu = pipe_ctx->stream->ctx->dc->res_pool->dmcu; + uint32_t otg_inst; + + if (!abm && !tg && !panel_cntl) + return; + + otg_inst = tg->inst; if (dmcu) { dce110_set_pipe(pipe_ctx); return; } - if (abm && panel_cntl) { - if (abm->funcs && abm->funcs->set_pipe_ex) { - abm->funcs->set_pipe_ex(abm, otg_inst, SET_ABM_PIPE_NORMAL, panel_cntl->inst); - } else { - dmub_abm_set_pipe(abm, otg_inst, SET_ABM_PIPE_NORMAL, panel_cntl->inst); - } + if (abm->funcs && abm->funcs->set_pipe_ex) { + abm->funcs->set_pipe_ex(abm, + otg_inst, + SET_ABM_PIPE_NORMAL, + panel_cntl->inst, + panel_cntl->pwrseq_inst); + } else { + dmub_abm_set_pipe(abm, otg_inst, + SET_ABM_PIPE_NORMAL, + panel_cntl->inst, + panel_cntl->pwrseq_inst); } } @@ -225,26 +241,35 @@ bool dcn21_set_backlight_level(struct pipe_ctx *pipe_ctx, { struct dc_context *dc = pipe_ctx->stream->ctx; struct abm *abm = pipe_ctx->stream_res.abm; + struct timing_generator *tg = pipe_ctx->stream_res.tg; struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl; + uint32_t otg_inst; + + if (!abm && !tg && !panel_cntl) + return false; + + otg_inst = tg->inst; if (dc->dc->res_pool->dmcu) { dce110_set_backlight_level(pipe_ctx, backlight_pwm_u16_16, frame_ramp); return true; } - if (abm != NULL) { - uint32_t otg_inst = pipe_ctx->stream_res.tg->inst; - - if (abm && panel_cntl) { - if (abm->funcs && abm->funcs->set_pipe_ex) { - abm->funcs->set_pipe_ex(abm, otg_inst, SET_ABM_PIPE_NORMAL, panel_cntl->inst); - } else { - dmub_abm_set_pipe(abm, otg_inst, SET_ABM_PIPE_NORMAL, panel_cntl->inst); - } - } + if (abm->funcs && abm->funcs->set_pipe_ex) { + abm->funcs->set_pipe_ex(abm, + otg_inst, + SET_ABM_PIPE_NORMAL, + panel_cntl->inst, + panel_cntl->pwrseq_inst); + } else { + dmub_abm_set_pipe(abm, + otg_inst, + SET_ABM_PIPE_NORMAL, + panel_cntl->inst, + panel_cntl->pwrseq_inst); } - if (abm && abm->funcs && abm->funcs->set_backlight_level_pwm) + if (abm->funcs && abm->funcs->set_backlight_level_pwm) abm->funcs->set_backlight_level_pwm(abm, backlight_pwm_u16_16, frame_ramp, 0, panel_cntl->inst); else diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c index e0df9b0065f9c0..62c02adae7e76e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c @@ -178,6 +178,8 @@ bool cm3_helper_translate_curve_to_hw_format( i += increment) { if (j == hw_points - 1) break; + if (i >= TRANSFER_FUNC_POINTS) + return false; rgb_resulted[j].red = output_tf->tf_pts.red[i]; rgb_resulted[j].green = output_tf->tf_pts.green[i]; rgb_resulted[j].blue = output_tf->tf_pts.blue[i]; @@ -355,6 +357,8 @@ bool cm3_helper_translate_curve_to_degamma_hw_format( i += increment) { if (j == hw_points - 1) break; + if (i >= TRANSFER_FUNC_POINTS) + return false; rgb_resulted[j].red = output_tf->tf_pts.red[i]; rgb_resulted[j].green = output_tf->tf_pts.green[i]; rgb_resulted[j].blue = output_tf->tf_pts.blue[i]; diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index 255713ec29bb0f..d59af329d0009e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -214,7 +214,11 @@ bool dcn30_set_output_transfer_func(struct dc *dc, } } - mpc->funcs->set_output_gamma(mpc, mpcc_id, params); + if (mpc->funcs->set_output_gamma) + mpc->funcs->set_output_gamma(mpc, mpcc_id, params); + else + DC_LOG_ERROR("%s: set_output_gamma function pointer is NULL.\n", __func__); + return ret; } @@ -619,10 +623,20 @@ void dcn30_set_avmute(struct pipe_ctx *pipe_ctx, bool enable) if (pipe_ctx == NULL) return; - if (dc_is_hdmi_signal(pipe_ctx->stream->signal) && pipe_ctx->stream_res.stream_enc != NULL) + if (dc_is_hdmi_signal(pipe_ctx->stream->signal) && pipe_ctx->stream_res.stream_enc != NULL) { pipe_ctx->stream_res.stream_enc->funcs->set_avmute( pipe_ctx->stream_res.stream_enc, enable); + + /* Wait for two frame to make sure AV mute is sent out */ + if (enable) { + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + } + } } void dcn30_update_info_frame(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index 79d6697d13b678..9485fda890cd71 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -996,7 +996,7 @@ static struct stream_encoder *dcn301_stream_encoder_create(enum engine_id eng_id vpg = dcn301_vpg_create(ctx, vpg_inst); afmt = dcn301_afmt_create(ctx, afmt_inst); - if (!enc1 || !vpg || !afmt) { + if (!enc1 || !vpg || !afmt || eng_id >= ARRAY_SIZE(stream_enc_regs)) { kfree(enc1); kfree(vpg); kfree(afmt); diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c index 5b7ad38f85e08f..65e45a0b4ff343 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c @@ -395,6 +395,12 @@ void dcn31_hpo_dp_link_enc_set_throttled_vcp_size( x), 25)); + // If y rounds up to integer, carry it over to x. + if (y >> 25) { + x += 1; + y = 0; + } + switch (stream_encoder_inst) { case 0: REG_SET_2(DP_DPHY_SYM32_VC_RATE_CNTL0, 0, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 2a7f47642a4479..22da2007601ee9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -523,7 +523,8 @@ static void dcn31_reset_back_end_for_pipe( if (pipe_ctx->stream_res.tg->funcs->set_odm_bypass) pipe_ctx->stream_res.tg->funcs->set_odm_bypass( pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing); - pipe_ctx->stream->link->phy_state.symclk_ref_cnts.otg = 0; + if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal)) + pipe_ctx->stream->link->phy_state.symclk_ref_cnts.otg = 0; if (pipe_ctx->stream_res.tg->funcs->set_drr) pipe_ctx->stream_res.tg->funcs->set_drr( diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c index 217acd4e292a30..d849b1eaa4a5c3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c @@ -50,7 +50,7 @@ static bool dcn31_query_backlight_info(struct panel_cntl *panel_cntl, union dmub cmd->panel_cntl.header.type = DMUB_CMD__PANEL_CNTL; cmd->panel_cntl.header.sub_type = DMUB_CMD__PANEL_CNTL_QUERY_BACKLIGHT_INFO; cmd->panel_cntl.header.payload_bytes = sizeof(cmd->panel_cntl.data); - cmd->panel_cntl.data.inst = dcn31_panel_cntl->base.inst; + cmd->panel_cntl.data.pwrseq_inst = dcn31_panel_cntl->base.pwrseq_inst; return dm_execute_dmub_cmd(dc_dmub_srv->ctx, cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY); } @@ -78,7 +78,7 @@ static uint32_t dcn31_panel_cntl_hw_init(struct panel_cntl *panel_cntl) cmd.panel_cntl.header.type = DMUB_CMD__PANEL_CNTL; cmd.panel_cntl.header.sub_type = DMUB_CMD__PANEL_CNTL_HW_INIT; cmd.panel_cntl.header.payload_bytes = sizeof(cmd.panel_cntl.data); - cmd.panel_cntl.data.inst = dcn31_panel_cntl->base.inst; + cmd.panel_cntl.data.pwrseq_inst = dcn31_panel_cntl->base.pwrseq_inst; cmd.panel_cntl.data.bl_pwm_cntl = panel_cntl->stored_backlight_registers.BL_PWM_CNTL; cmd.panel_cntl.data.bl_pwm_period_cntl = panel_cntl->stored_backlight_registers.BL_PWM_PERIOD_CNTL; cmd.panel_cntl.data.bl_pwm_ref_div1 = @@ -157,4 +157,5 @@ void dcn31_panel_cntl_construct( dcn31_panel_cntl->base.funcs = &dcn31_link_panel_cntl_funcs; dcn31_panel_cntl->base.ctx = init_data->ctx; dcn31_panel_cntl->base.inst = init_data->inst; + dcn31_panel_cntl->base.pwrseq_inst = init_data->pwrseq_inst; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c index 4d2820ffe4682f..33a8626bda7359 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c @@ -476,7 +476,8 @@ void dcn314_disable_link_output(struct dc_link *link, struct dmcu *dmcu = dc->res_pool->dmcu; if (signal == SIGNAL_TYPE_EDP && - link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_backlight_control && + !link->skip_implict_edp_power_control) link->dc->hwss.edp_backlight_control(link, false); else if (dmcu != NULL && dmcu->funcs->lock_phy) dmcu->funcs->lock_phy(dmcu); diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index 004beed9bd444c..3e65e683db0acf 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -869,7 +869,7 @@ static const struct dc_plane_cap plane_cap = { static const struct dc_debug_options debug_defaults_drv = { .disable_z10 = false, .enable_z9_disable_interface = true, - .minimum_z8_residency_time = 2000, + .minimum_z8_residency_time = 2100, .psr_skip_crtc_disable = true, .replay_skip_crtc_disabled = true, .disable_dmcu = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index 680e7fa8d18abc..650e1598bddcb1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -77,6 +77,9 @@ void dcn32_dsc_pg_control( if (hws->ctx->dc->debug.disable_dsc_power_gate) return; + if (!hws->ctx->dc->debug.enable_double_buffered_dsc_pg_support) + return; + REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); if (org_ip_request_cntl == 0) REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); @@ -214,7 +217,7 @@ static bool dcn32_check_no_memory_request_for_cab(struct dc *dc) static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *ctx) { int i; - uint8_t num_ways = 0; + uint32_t num_ways = 0; uint32_t mall_ss_size_bytes = 0; mall_ss_size_bytes = ctx->bw_ctx.bw.dcn.mall_ss_size_bytes; @@ -244,7 +247,8 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable) { union dmub_rb_cmd cmd; - uint8_t ways, i; + uint8_t i; + uint32_t ways; int j; bool mall_ss_unsupported = false; struct dc_plane_state *plane = NULL; @@ -304,7 +308,7 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable) cmd.cab.header.type = DMUB_CMD__CAB_FOR_SS; cmd.cab.header.sub_type = DMUB_CMD__CAB_DCN_SS_FIT_IN_CAB; cmd.cab.header.payload_bytes = sizeof(cmd.cab) - sizeof(cmd.cab.header); - cmd.cab.cab_alloc_ways = ways; + cmd.cab.cab_alloc_ways = (uint8_t)ways; dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); @@ -482,8 +486,7 @@ bool dcn32_set_mcm_luts( if (plane_state->blend_tf->type == TF_TYPE_HWPWL) lut_params = &plane_state->blend_tf->pwl; else if (plane_state->blend_tf->type == TF_TYPE_DISTRIBUTED_POINTS) { - cm_helper_translate_curve_to_hw_format(plane_state->ctx, - plane_state->blend_tf, + cm3_helper_translate_curve_to_hw_format(plane_state->blend_tf, &dpp_base->regamma_params, false); lut_params = &dpp_base->regamma_params; } @@ -497,8 +500,7 @@ bool dcn32_set_mcm_luts( else if (plane_state->in_shaper_func->type == TF_TYPE_DISTRIBUTED_POINTS) { // TODO: dpp_base replace ASSERT(false); - cm_helper_translate_curve_to_hw_format(plane_state->ctx, - plane_state->in_shaper_func, + cm3_helper_translate_curve_to_hw_format(plane_state->in_shaper_func, &dpp_base->shaper_params, true); lut_params = &dpp_base->shaper_params; } @@ -1573,3 +1575,101 @@ void dcn32_init_blank( if (opp) hws->funcs.wait_for_blank_complete(opp); } + +void dcn32_blank_phantom(struct dc *dc, + struct timing_generator *tg, + int width, + int height) +{ + struct dce_hwseq *hws = dc->hwseq; + enum dc_color_space color_space; + struct tg_color black_color = {0}; + struct output_pixel_processor *opp = NULL; + uint32_t num_opps, opp_id_src0, opp_id_src1; + uint32_t otg_active_width, otg_active_height; + uint32_t i; + + /* program opp dpg blank color */ + color_space = COLOR_SPACE_SRGB; + color_space_to_black_color(dc, color_space, &black_color); + + otg_active_width = width; + otg_active_height = height; + + /* get the OPTC source */ + tg->funcs->get_optc_source(tg, &num_opps, &opp_id_src0, &opp_id_src1); + ASSERT(opp_id_src0 < dc->res_pool->res_cap->num_opp); + + for (i = 0; i < dc->res_pool->res_cap->num_opp; i++) { + if (dc->res_pool->opps[i] != NULL && dc->res_pool->opps[i]->inst == opp_id_src0) { + opp = dc->res_pool->opps[i]; + break; + } + } + + if (opp && opp->funcs->opp_set_disp_pattern_generator) + opp->funcs->opp_set_disp_pattern_generator( + opp, + CONTROLLER_DP_TEST_PATTERN_SOLID_COLOR, + CONTROLLER_DP_COLOR_SPACE_UDEFINED, + COLOR_DEPTH_UNDEFINED, + &black_color, + otg_active_width, + otg_active_height, + 0); + + if (tg->funcs->is_tg_enabled(tg)) + hws->funcs.wait_for_blank_complete(opp); +} + +bool dcn32_is_pipe_topology_transition_seamless(struct dc *dc, + const struct dc_state *cur_ctx, + const struct dc_state *new_ctx) +{ + int i; + const struct pipe_ctx *cur_pipe, *new_pipe; + bool is_seamless = true; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + cur_pipe = &cur_ctx->res_ctx.pipe_ctx[i]; + new_pipe = &new_ctx->res_ctx.pipe_ctx[i]; + + if (resource_is_pipe_type(cur_pipe, FREE_PIPE) || + resource_is_pipe_type(new_pipe, FREE_PIPE)) + /* adding or removing free pipes is always seamless */ + continue; + else if (resource_is_pipe_type(cur_pipe, OTG_MASTER)) { + if (resource_is_pipe_type(new_pipe, OTG_MASTER)) + if (cur_pipe->stream->stream_id == new_pipe->stream->stream_id) + /* OTG master with the same stream is seamless */ + continue; + } else if (resource_is_pipe_type(cur_pipe, OPP_HEAD)) { + if (resource_is_pipe_type(new_pipe, OPP_HEAD)) { + if (cur_pipe->stream_res.tg == new_pipe->stream_res.tg) + /* + * OPP heads sharing the same timing + * generator is seamless + */ + continue; + } + } else if (resource_is_pipe_type(cur_pipe, DPP_PIPE)) { + if (resource_is_pipe_type(new_pipe, DPP_PIPE)) { + if (cur_pipe->stream_res.opp == new_pipe->stream_res.opp) + /* + * DPP pipes sharing the same OPP head is + * seamless + */ + continue; + } + } + + /* + * This pipe's transition doesn't fall under any seamless + * conditions + */ + is_seamless = false; + break; + } + + return is_seamless; +} diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h index 2d2628f31bed7d..9992e40acd217b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h @@ -115,4 +115,13 @@ void dcn32_init_blank( struct dc *dc, struct timing_generator *tg); +void dcn32_blank_phantom(struct dc *dc, + struct timing_generator *tg, + int width, + int height); + +bool dcn32_is_pipe_topology_transition_seamless(struct dc *dc, + const struct dc_state *cur_ctx, + const struct dc_state *new_ctx); + #endif /* __DC_HWSS_DCN32_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c index c7417147dff19b..1edadff39a5eff 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c @@ -115,6 +115,8 @@ static const struct hw_sequencer_funcs dcn32_funcs = { .update_phantom_vp_position = dcn32_update_phantom_vp_position, .update_dsc_pg = dcn32_update_dsc_pg, .apply_update_flags_for_phantom = dcn32_apply_update_flags_for_phantom, + .blank_phantom = dcn32_blank_phantom, + .is_pipe_topology_transition_seamless = dcn32_is_pipe_topology_transition_seamless, }; static const struct hwseq_private_funcs dcn32_private_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c index 8abb94f60078fc..058dee76054ea7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c @@ -142,6 +142,16 @@ static bool optc32_disable_crtc(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); + REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT, + OPTC_SEG0_SRC_SEL, 0xf, + OPTC_SEG1_SRC_SEL, 0xf, + OPTC_SEG2_SRC_SEL, 0xf, + OPTC_SEG3_SRC_SEL, 0xf, + OPTC_NUM_OF_INPUT_SEGMENT, 0); + + REG_UPDATE(OPTC_MEMORY_CONFIG, + OPTC_MEM_SEL, 0); + /* disable otg request until end of the first line * in the vertical blank region */ @@ -174,6 +184,13 @@ static void optc32_disable_phantom_otg(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); + REG_UPDATE_5(OPTC_DATA_SOURCE_SELECT, + OPTC_SEG0_SRC_SEL, 0xf, + OPTC_SEG1_SRC_SEL, 0xf, + OPTC_SEG2_SRC_SEL, 0xf, + OPTC_SEG3_SRC_SEL, 0xf, + OPTC_NUM_OF_INPUT_SEGMENT, 0); + REG_UPDATE(OTG_CONTROL, OTG_MASTER_EN, 0); } @@ -219,9 +236,6 @@ static void optc32_setup_manual_trigger(struct timing_generator *optc) OTG_V_TOTAL_MAX_SEL, 1, OTG_FORCE_LOCK_ON_EVENT, 0, OTG_SET_V_TOTAL_MIN_MASK, (1 << 1)); /* TRIGA */ - - // Setup manual flow control for EOF via TRIG_A - optc->funcs->setup_manual_trigger(optc); } } diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c index 8d73cceb485bf4..aa4c64eec7b3d6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c @@ -1756,6 +1756,9 @@ static bool dcn321_resource_construct( dc->caps.color.mpc.ogam_rom_caps.hlg = 0; dc->caps.color.mpc.ocsc = 1; + /* Use pipe context based otg sync logic */ + dc->config.use_pipe_ctx_sync_logic = true; + dc->config.dc_mode_clk_limit_support = true; /* read VBIOS LTTPR caps */ { diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index 77cf5545c94cc8..0ba9a7997d561c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -61,18 +61,22 @@ endif endif ifneq ($(CONFIG_FRAME_WARN),0) +ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) +frame_warn_flag := -Wframe-larger-than=3072 +else frame_warn_flag := -Wframe-larger-than=2048 endif +endif CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags) diff --git a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c index 50b0434354f8f5..c08169de3660c5 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c @@ -1453,10 +1453,9 @@ void dcn_bw_update_from_pplib_fclks( ASSERT(fclks->num_levels); vmin0p65_idx = 0; - vmid0p72_idx = fclks->num_levels - - (fclks->num_levels > 2 ? 3 : (fclks->num_levels > 1 ? 2 : 1)); - vnom0p8_idx = fclks->num_levels - (fclks->num_levels > 1 ? 2 : 1); - vmax0p9_idx = fclks->num_levels - 1; + vmid0p72_idx = fclks->num_levels > 2 ? fclks->num_levels - 3 : 0; + vnom0p8_idx = fclks->num_levels > 1 ? fclks->num_levels - 2 : 0; + vmax0p9_idx = fclks->num_levels > 0 ? fclks->num_levels - 1 : 0; dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = 32 * (fclks->data[vmin0p65_idx].clocks_in_khz / 1000.0) / 1000.0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dc_features.h b/drivers/gpu/drm/amd/display/dc/dml/dc_features.h index 2cbdd75429ffd6..6e669a2c5b2d44 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dc_features.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dc_features.h @@ -36,7 +36,7 @@ * Define the maximum amount of states supported by the ASIC. Every ASIC has a * specific number of states; this macro defines the maximum number of states. */ -#define DC__VOLTAGE_STATES 20 +#define DC__VOLTAGE_STATES 40 #define DC__NUM_DPP__4 1 #define DC__NUM_DPP__0_PRESENT 1 #define DC__NUM_DPP__1_PRESENT 1 diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 5805fb02af14e3..8a5a038fd85578 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -438,7 +438,115 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { .use_urgent_burst_bw = 0 }; -struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { 0 }; +struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { + .clock_limits = { + { + .state = 0, + .dcfclk_mhz = 560.0, + .fabricclk_mhz = 560.0, + .dispclk_mhz = 513.0, + .dppclk_mhz = 513.0, + .phyclk_mhz = 540.0, + .socclk_mhz = 560.0, + .dscclk_mhz = 171.0, + .dram_speed_mts = 1069.0, + }, + { + .state = 1, + .dcfclk_mhz = 694.0, + .fabricclk_mhz = 694.0, + .dispclk_mhz = 642.0, + .dppclk_mhz = 642.0, + .phyclk_mhz = 600.0, + .socclk_mhz = 694.0, + .dscclk_mhz = 214.0, + .dram_speed_mts = 1324.0, + }, + { + .state = 2, + .dcfclk_mhz = 875.0, + .fabricclk_mhz = 875.0, + .dispclk_mhz = 734.0, + .dppclk_mhz = 734.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 875.0, + .dscclk_mhz = 245.0, + .dram_speed_mts = 1670.0, + }, + { + .state = 3, + .dcfclk_mhz = 1000.0, + .fabricclk_mhz = 1000.0, + .dispclk_mhz = 1100.0, + .dppclk_mhz = 1100.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1000.0, + .dscclk_mhz = 367.0, + .dram_speed_mts = 2000.0, + }, + { + .state = 4, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 2000.0, + }, + { + .state = 5, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 2000.0, + }, + }, + + .num_states = 5, + .sr_exit_time_us = 1.9, + .sr_enter_plus_exit_time_us = 4.4, + .urgent_latency_us = 3.0, + .urgent_latency_pixel_data_only_us = 4.0, + .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, + .urgent_latency_vm_data_only_us = 4.0, + .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, + .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, + .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, + .max_avg_sdp_bw_use_normal_percent = 40.0, + .max_avg_dram_bw_use_normal_percent = 40.0, + .writeback_latency_us = 12.0, + .ideal_dram_bw_after_urgent_percent = 40.0, + .max_request_size_bytes = 256, + .dram_channel_width_bytes = 16, + .fabric_datapath_to_dcn_data_return_bytes = 64, + .dcn_downspread_percent = 0.5, + .downspread_percent = 0.5, + .dram_page_open_time_ns = 50.0, + .dram_rw_turnaround_time_ns = 17.5, + .dram_return_buffer_per_channel_bytes = 8192, + .round_trip_ping_latency_dcfclk_cycles = 131, + .urgent_out_of_order_return_per_channel_bytes = 4096, + .channel_interleave_bytes = 256, + .num_banks = 8, + .num_chans = 16, + .vmm_page_size_bytes = 4096, + .dram_clock_change_latency_us = 45.0, + .writeback_dram_clock_change_latency_us = 23.0, + .return_bus_width_bytes = 64, + .dispclk_dppclk_vco_speed_mhz = 3850, + .xfc_bus_transport_time_us = 20, + .xfc_xbuf_latency_tolerance_us = 50, + .use_urgent_burst_bw = 0, +}; struct _vcs_dpi_ip_params_st dcn2_1_ip = { .odm_capable = 1, @@ -948,10 +1056,8 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc { int plane_count; int i; - unsigned int min_dst_y_next_start_us; plane_count = 0; - min_dst_y_next_start_us = 0; for (i = 0; i < dc->res_pool->pipe_count; i++) { if (context->res_ctx.pipe_ctx[i].plane_state) plane_count++; @@ -973,26 +1079,15 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc else if (context->stream_count == 1 && context->streams[0]->signal == SIGNAL_TYPE_EDP) { struct dc_link *link = context->streams[0]->sink->link; struct dc_stream_status *stream_status = &context->stream_status[0]; - struct dc_stream_state *current_stream = context->streams[0]; int minmum_z8_residency = dc->debug.minimum_z8_residency_time > 0 ? dc->debug.minimum_z8_residency_time : 1000; bool allow_z8 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z8_residency; bool is_pwrseq0 = link->link_index == 0; - bool isFreesyncVideo; - - isFreesyncVideo = current_stream->adjust.v_total_min == current_stream->adjust.v_total_max; - isFreesyncVideo = isFreesyncVideo && current_stream->timing.v_total < current_stream->adjust.v_total_min; - for (i = 0; i < dc->res_pool->pipe_count; i++) { - if (context->res_ctx.pipe_ctx[i].stream == current_stream && isFreesyncVideo) { - min_dst_y_next_start_us = context->res_ctx.pipe_ctx[i].dlg_regs.min_dst_y_next_start_us; - break; - } - } /* Don't support multi-plane configurations */ if (stream_status->plane_count > 1) return DCN_ZSTATE_SUPPORT_DISALLOW; - if (is_pwrseq0 && (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || min_dst_y_next_start_us > 5000)) + if (is_pwrseq0 && context->bw_ctx.dml.vba.StutterPeriod > 5000.0) return DCN_ZSTATE_SUPPORT_ALLOW; else if (is_pwrseq0 && link->psr_settings.psr_version == DC_PSR_VERSION_1 && !link->panel_config.psr.disable_psr) return allow_z8 ? DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY : DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c index 0fc9f3e3ffaefd..f603486af6e306 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c @@ -78,7 +78,7 @@ static void calculate_ttu_cursor(struct display_mode_lib *mode_lib, static unsigned int get_bytes_per_element(enum source_format_class source_format, bool is_chroma) { - unsigned int ret_val = 0; + unsigned int ret_val = 1; if (source_format == dm_444_16) { if (!is_chroma) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c index 618f4b682ab1b1..9f28e4d3c664c7 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c @@ -53,7 +53,7 @@ static void calculate_ttu_cursor( static unsigned int get_bytes_per_element(enum source_format_class source_format, bool is_chroma) { - unsigned int ret_val = 0; + unsigned int ret_val = 1; if (source_format == dm_444_16) { if (!is_chroma) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c index e2bcd205aa936f..8da97a96b1ceb9 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c @@ -304,6 +304,16 @@ void dcn302_fpu_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_p dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16; } + /* bw_params->clk_table.entries[MAX_NUM_DPM_LVL]. + * MAX_NUM_DPM_LVL is 8. + * dcn3_02_soc.clock_limits[DC__VOLTAGE_STATES]. + * DC__VOLTAGE_STATES is 40. + */ + if (num_states > MAX_NUM_DPM_LVL) { + ASSERT(0); + return; + } + dcn3_02_soc.num_states = num_states; for (i = 0; i < dcn3_02_soc.num_states; i++) { dcn3_02_soc.clock_limits[i].state = i; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c index 3eb3a021ab7d72..c283780ad0621a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c @@ -299,6 +299,16 @@ void dcn303_fpu_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_p dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16; } + /* bw_params->clk_table.entries[MAX_NUM_DPM_LVL]. + * MAX_NUM_DPM_LVL is 8. + * dcn3_02_soc.clock_limits[DC__VOLTAGE_STATES]. + * DC__VOLTAGE_STATES is 40. + */ + if (num_states > MAX_NUM_DPM_LVL) { + ASSERT(0); + return; + } + dcn3_03_soc.num_states = num_states; for (i = 0; i < dcn3_03_soc.num_states; i++) { dcn3_03_soc.clock_limits[i].state = i; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c index deb6d162a2d5c0..7307b7b8d8ad75 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c @@ -291,6 +291,7 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_15_soc = { .do_urgent_latency_adjustment = false, .urgent_latency_adjustment_fabric_clock_component_us = 0, .urgent_latency_adjustment_fabric_clock_reference_mhz = 0, + .dispclk_dppclk_vco_speed_mhz = 2400.0, .num_chans = 4, .dummy_pstate_latency_us = 10.0 }; @@ -438,6 +439,7 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_16_soc = { .do_urgent_latency_adjustment = false, .urgent_latency_adjustment_fabric_clock_component_us = 0, .urgent_latency_adjustment_fabric_clock_reference_mhz = 0, + .dispclk_dppclk_vco_speed_mhz = 2500.0, }; void dcn31_zero_pipe_dcc_fraction(display_e2e_pipe_params_st *pipes, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 711d4085b33b8f..3d82cbef12740c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -1964,6 +1964,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, int i, pipe_idx, vlevel_temp = 0; double dcfclk = dcn3_2_soc.clock_limits[0].dcfclk_mhz; double dcfclk_from_validation = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; + double dram_speed_from_validation = context->bw_ctx.dml.vba.DRAMSpeed; double dcfclk_from_fw_based_mclk_switching = dcfclk_from_validation; bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] != dm_dram_clock_change_unsupported; @@ -2151,7 +2152,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, } if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].valid) { - min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed; + min_dram_speed_mts = dram_speed_from_validation; min_dram_speed_mts_margin = 160; context->bw_ctx.dml.soc.dram_clock_change_latency_us = @@ -2884,6 +2885,16 @@ void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_pa dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16; } + /* bw_params->clk_table.entries[MAX_NUM_DPM_LVL]. + * MAX_NUM_DPM_LVL is 8. + * dcn3_02_soc.clock_limits[DC__VOLTAGE_STATES]. + * DC__VOLTAGE_STATES is 40. + */ + if (num_states > MAX_NUM_DPM_LVL) { + ASSERT(0); + return; + } + dcn3_2_soc.num_states = num_states; for (i = 0; i < dcn3_2_soc.num_states; i++) { dcn3_2_soc.clock_limits[i].state = i; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index cbdfb762c10c58..0782a34689a00f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -813,6 +813,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman (v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ || v->DCFCLKPerState[mode_lib->vba.VoltageLevel] <= DCFCLK_FREQ_EXTRA_PREFETCH_REQ_MHZ) ? mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, + mode_lib->vba.PrefetchModePerState[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] > 0 || mode_lib->vba.DRAMClockChangeRequirementFinal == false, + /* Output */ &v->DSTXAfterScaler[k], &v->DSTYAfterScaler[k], @@ -3317,6 +3319,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->SwathHeightCThisState[k], v->TWait, (v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ || v->DCFCLKState[i][j] <= DCFCLK_FREQ_EXTRA_PREFETCH_REQ_MHZ) ? mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, + mode_lib->vba.PrefetchModePerState[i][j] > 0 || mode_lib->vba.DRAMClockChangeRequirementFinal == false, /* Output */ &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler[k], @@ -3361,6 +3364,9 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l &mode_lib->vba.UrgentBurstFactorLumaPre[k], &mode_lib->vba.UrgentBurstFactorChromaPre[k], &mode_lib->vba.NotUrgentLatencyHidingPre[k]); + + v->cursor_bw_pre[k] = mode_lib->vba.NumberOfCursors[k] * mode_lib->vba.CursorWidth[k][0] * mode_lib->vba.CursorBPP[k][0] / + 8.0 / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]) * v->VRatioPreY[i][j][k]; } { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index ecea008f19d3aa..208b89d13d3f6d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -3423,6 +3423,7 @@ bool dml32_CalculatePrefetchSchedule( unsigned int SwathHeightC, double TWait, double TPreReq, + bool ExtendPrefetchIfPossible, /* Output */ double *DSTXAfterScaler, double *DSTYAfterScaler, @@ -3892,12 +3893,32 @@ bool dml32_CalculatePrefetchSchedule( /* Clamp to oto for bandwidth calculation */ LinesForPrefetchBandwidth = dst_y_prefetch_oto; } else { - *DestinationLinesForPrefetch = dst_y_prefetch_equ; - TimeForFetchingMetaPTE = Tvm_equ; - TimeForFetchingRowInVBlank = Tr0_equ; - *PrefetchBandwidth = prefetch_bw_equ; - /* Clamp to equ for bandwidth calculation */ - LinesForPrefetchBandwidth = dst_y_prefetch_equ; + /* For mode programming we want to extend the prefetch as much as possible + * (up to oto, or as long as we can for equ) if we're not already applying + * the 60us prefetch requirement. This is to avoid intermittent underflow + * issues during prefetch. + * + * The prefetch extension is applied under the following scenarios: + * 1. We're in prefetch mode > 0 (i.e. we don't support MCLK switch in blank) + * 2. We're using subvp or drr methods of p-state switch, in which case we + * we don't care if prefetch takes up more of the blanking time + * + * Mode programming typically chooses the smallest prefetch time possible + * (i.e. highest bandwidth during prefetch) presumably to create margin between + * p-states / c-states that happen in vblank and prefetch. Therefore we only + * apply this prefetch extension when p-state in vblank is not required (UCLK + * p-states take up the most vblank time). + */ + if (ExtendPrefetchIfPossible && TPreReq == 0 && VStartup < MaxVStartup) { + MyError = true; + } else { + *DestinationLinesForPrefetch = dst_y_prefetch_equ; + TimeForFetchingMetaPTE = Tvm_equ; + TimeForFetchingRowInVBlank = Tr0_equ; + *PrefetchBandwidth = prefetch_bw_equ; + /* Clamp to equ for bandwidth calculation */ + LinesForPrefetchBandwidth = dst_y_prefetch_equ; + } } *DestinationLinesToRequestVMInVBlank = dml_ceil(4.0 * TimeForFetchingMetaPTE / LineTime, 1.0) / 4.0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h index 592d174df6c629..5d34735df83db1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h @@ -747,6 +747,7 @@ bool dml32_CalculatePrefetchSchedule( unsigned int SwathHeightC, double TWait, double TPreReq, + bool ExtendPrefetchIfPossible, /* Output */ double *DSTXAfterScaler, double *DSTYAfterScaler, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c index b26fcf86014c70..ae2196c36f218b 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c @@ -789,6 +789,16 @@ void dcn321_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16; } + /* bw_params->clk_table.entries[MAX_NUM_DPM_LVL]. + * MAX_NUM_DPM_LVL is 8. + * dcn3_02_soc.clock_limits[DC__VOLTAGE_STATES]. + * DC__VOLTAGE_STATES is 40. + */ + if (num_states > MAX_NUM_DPM_LVL) { + ASSERT(0); + return; + } + dcn3_21_soc.num_states = num_states; for (i = 0; i < dcn3_21_soc.num_states; i++) { dcn3_21_soc.clock_limits[i].state = i; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c index 9a3ded31119529..85453bbb4f9b13 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c @@ -1099,8 +1099,13 @@ void ModeSupportAndSystemConfiguration(struct display_mode_lib *mode_lib) // Total Available Pipes Support Check for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k) { - total_pipes += mode_lib->vba.DPPPerPlane[k]; pipe_idx = get_pipe_idx(mode_lib, k); + if (pipe_idx == -1) { + ASSERT(0); + continue; // skip inactive planes + } + total_pipes += mode_lib->vba.DPPPerPlane[k]; + if (mode_lib->vba.cache_pipes[pipe_idx].clks_cfg.dppclk_mhz > 0.0) mode_lib->vba.DPPCLK[k] = mode_lib->vba.cache_pipes[pipe_idx].clks_cfg.dppclk_mhz; else diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c index 3966845c769453..9edc9b0e3f082d 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c @@ -861,7 +861,7 @@ static bool setup_dsc_config( memset(dsc_cfg, 0, sizeof(struct dc_dsc_config)); - dc_dsc_get_policy_for_timing(timing, options->max_target_bpp_limit_override_x16, &policy); + dc_dsc_get_policy_for_timing(timing, options->max_target_bpp_limit_override_x16, &policy, link_encoding); pic_width = timing->h_addressable + timing->h_border_left + timing->h_border_right; pic_height = timing->v_addressable + timing->v_border_top + timing->v_border_bottom; @@ -1033,7 +1033,12 @@ static bool setup_dsc_config( if (!is_dsc_possible) goto done; - dsc_cfg->num_slices_v = pic_height/slice_height; + if (slice_height > 0) { + dsc_cfg->num_slices_v = pic_height / slice_height; + } else { + is_dsc_possible = false; + goto done; + } if (target_bandwidth_kbps > 0) { is_dsc_possible = decide_dsc_target_bpp_x16( @@ -1129,7 +1134,8 @@ uint32_t dc_dsc_stream_bandwidth_overhead_in_kbps( void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, uint32_t max_target_bpp_limit_override_x16, - struct dc_dsc_policy *policy) + struct dc_dsc_policy *policy, + const enum dc_link_encoding_format link_encoding) { uint32_t bpc = 0; diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c index 3ede6e02c3a786..f2037d78f71abd 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c @@ -56,7 +56,7 @@ struct gpio_service *dal_gpio_service_create( struct dc_context *ctx) { struct gpio_service *service; - uint32_t index_of_id; + int32_t index_of_id; service = kzalloc(sizeof(struct gpio_service), GFP_KERNEL); @@ -112,7 +112,7 @@ struct gpio_service *dal_gpio_service_create( return service; failure_2: - while (index_of_id) { + while (index_of_id > 0) { --index_of_id; kfree(service->busyness[index_of_id]); } @@ -239,6 +239,9 @@ static bool is_pin_busy( enum gpio_id id, uint32_t en) { + if (id == GPIO_ID_UNKNOWN) + return false; + return service->busyness[id][en]; } @@ -247,6 +250,9 @@ static void set_pin_busy( enum gpio_id id, uint32_t en) { + if (id == GPIO_ID_UNKNOWN) + return; + service->busyness[id][en] = true; } @@ -255,6 +261,9 @@ static void set_pin_free( enum gpio_id id, uint32_t en) { + if (id == GPIO_ID_UNKNOWN) + return; + service->busyness[id][en] = false; } @@ -263,7 +272,7 @@ enum gpio_result dal_gpio_service_lock( enum gpio_id id, uint32_t en) { - if (!service->busyness[id]) { + if (id != GPIO_ID_UNKNOWN && !service->busyness[id]) { ASSERT_CRITICAL(false); return GPIO_RESULT_OPEN_FAILED; } @@ -277,7 +286,7 @@ enum gpio_result dal_gpio_service_unlock( enum gpio_id id, uint32_t en) { - if (!service->busyness[id]) { + if (id != GPIO_ID_UNKNOWN && !service->busyness[id]) { ASSERT_CRITICAL(false); return GPIO_RESULT_OPEN_FAILED; } diff --git a/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c b/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c index 25ffc052d53be9..df2cb5279ce51d 100644 --- a/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c +++ b/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c @@ -130,13 +130,21 @@ static bool hdmi_14_process_transaction( const uint8_t hdcp_i2c_addr_link_primary = 0x3a; /* 0x74 >> 1*/ const uint8_t hdcp_i2c_addr_link_secondary = 0x3b; /* 0x76 >> 1*/ struct i2c_command i2c_command; - uint8_t offset = hdcp_i2c_offsets[message_info->msg_id]; + uint8_t offset; struct i2c_payload i2c_payloads[] = { - { true, 0, 1, &offset }, + { true, 0, 1, 0 }, /* actual hdcp payload, will be filled later, zeroed for now*/ { 0 } }; + if (message_info->msg_id == HDCP_MESSAGE_ID_INVALID) { + DC_LOG_ERROR("%s: Invalid message_info msg_id - %d\n", __func__, message_info->msg_id); + return false; + } + + offset = hdcp_i2c_offsets[message_info->msg_id]; + i2c_payloads[0].data = &offset; + switch (message_info->link) { case HDCP_LINK_SECONDARY: i2c_payloads[0].address = hdcp_i2c_addr_link_secondary; @@ -310,6 +318,11 @@ static bool dp_11_process_transaction( struct dc_link *link, struct hdcp_protection_message *message_info) { + if (message_info->msg_id == HDCP_MESSAGE_ID_INVALID) { + DC_LOG_ERROR("%s: Invalid message_info msg_id - %d\n", __func__, message_info->msg_id); + return false; + } + return dpcd_access_helper( link, message_info->length, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/abm.h b/drivers/gpu/drm/amd/display/dc/inc/hw/abm.h index 33db15d69f2337..9f521cf0fc5a2b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/abm.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/abm.h @@ -64,7 +64,8 @@ struct abm_funcs { bool (*set_pipe_ex)(struct abm *abm, unsigned int otg_inst, unsigned int option, - unsigned int panel_inst); + unsigned int panel_inst, + unsigned int pwrseq_inst); }; #endif diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h index 24af9d80b9373a..248adc1705e357 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h @@ -56,12 +56,14 @@ struct panel_cntl_funcs { struct panel_cntl_init_data { struct dc_context *ctx; uint32_t inst; + uint32_t pwrseq_inst; }; struct panel_cntl { const struct panel_cntl_funcs *funcs; struct dc_context *ctx; uint32_t inst; + uint32_t pwrseq_inst; /* registers setting needs to be saved and restored at InitBacklight */ struct panel_cntl_backlight_registers stored_backlight_registers; }; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h index 02ff99f7bec2ba..66e680902c95c7 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h @@ -388,6 +388,11 @@ struct hw_sequencer_funcs { void (*z10_restore)(const struct dc *dc); void (*z10_save_init)(struct dc *dc); + void (*blank_phantom)(struct dc *dc, + struct timing_generator *tg, + int width, + int height); + void (*update_visual_confirm_color)(struct dc *dc, struct pipe_ctx *pipe_ctx, int mpcc_id); @@ -396,6 +401,9 @@ struct hw_sequencer_funcs { struct dc_state *context, struct pipe_ctx *phantom_pipe); void (*apply_update_flags_for_phantom)(struct pipe_ctx *phantom_pipe); + bool (*is_pipe_topology_transition_seamless)(struct dc *dc, + const struct dc_state *cur_ctx, + const struct dc_state *new_ctx); void (*commit_subvp_config)(struct dc *dc, struct dc_state *context); void (*enable_phantom_streams)(struct dc *dc, struct dc_state *context); diff --git a/drivers/gpu/drm/amd/display/dc/inc/link.h b/drivers/gpu/drm/amd/display/dc/inc/link.h index e3e8c76c17cfac..d7685368140ab5 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/link.h +++ b/drivers/gpu/drm/amd/display/dc/inc/link.h @@ -295,6 +295,7 @@ struct link_service { bool (*edp_receiver_ready_T9)(struct dc_link *link); bool (*edp_receiver_ready_T7)(struct dc_link *link); bool (*edp_power_alpm_dpcd_enable)(struct dc_link *link, bool enable); + void (*edp_set_panel_power)(struct dc_link *link, bool powerOn); /*************************** DP CTS ************************************/ diff --git a/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c b/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c index 44649db5f3e32f..5646b7788f02e4 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c @@ -211,8 +211,12 @@ bool dce110_vblank_set(struct irq_service *irq_service, info->ext_id); uint8_t pipe_offset = dal_irq_src - IRQ_TYPE_VBLANK; - struct timing_generator *tg = - dc->current_state->res_ctx.pipe_ctx[pipe_offset].stream_res.tg; + struct timing_generator *tg; + + if (pipe_offset >= MAX_PIPES) + return false; + + tg = dc->current_state->res_ctx.pipe_ctx[pipe_offset].stream_res.tg; if (enable) { if (!tg || !tg->funcs->arm_vert_intr(tg, 2)) { diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_dp.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_dp.c index e1257404357b11..cec68c5dba1322 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_dp.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_dp.c @@ -28,6 +28,8 @@ #include "dccg.h" #include "clk_mgr.h" +#define DC_LOGGER link->ctx->logger + void set_hpo_dp_throttled_vcp_size(struct pipe_ctx *pipe_ctx, struct fixed31_32 throttled_vcp_size) { @@ -108,6 +110,11 @@ void enable_hpo_dp_link_output(struct dc_link *link, enum clock_source_id clock_source, const struct dc_link_settings *link_settings) { + if (!link_res->hpo_dp_link_enc) { + DC_LOG_ERROR("%s: invalid hpo_dp_link_enc\n", __func__); + return; + } + if (link->dc->res_pool->dccg->funcs->set_symclk32_le_root_clock_gating) link->dc->res_pool->dccg->funcs->set_symclk32_le_root_clock_gating( link->dc->res_pool->dccg, @@ -124,6 +131,11 @@ void disable_hpo_dp_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal) { + if (!link_res->hpo_dp_link_enc) { + DC_LOG_ERROR("%s: invalid hpo_dp_link_enc\n", __func__); + return; + } + link_res->hpo_dp_link_enc->funcs->link_disable(link_res->hpo_dp_link_enc); link_res->hpo_dp_link_enc->funcs->disable_link_phy( link_res->hpo_dp_link_enc, signal); diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.c index b621b97711b617..a7f5b0f6272ce0 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.c @@ -162,7 +162,12 @@ static void set_hpo_fixed_vs_pe_retimer_dp_link_test_pattern(struct dc_link *lin link_res->hpo_dp_link_enc->funcs->set_link_test_pattern( link_res->hpo_dp_link_enc, tp_params); } + link->dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_SET_SOURCE_PATTERN); + + // Give retimer extra time to lock before updating DP_TRAINING_PATTERN_SET to TPS1 + if (tp_params->dp_phy_pattern == DP_TEST_PATTERN_128b_132b_TPS1_TRAINING_MODE) + msleep(30); } static void set_hpo_fixed_vs_pe_retimer_dp_lane_settings(struct dc_link *link, diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index c9b6676eaf53b9..c7a9e286a5d4d3 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -876,7 +876,7 @@ static bool detect_link_and_local_sink(struct dc_link *link, (link->dpcd_sink_ext_caps.bits.oled == 1)) { dpcd_set_source_specific_data(link); msleep(post_oui_delay); - set_cached_brightness_aux(link); + set_default_brightness_aux(link); } return true; @@ -1085,6 +1085,9 @@ static bool detect_link_and_local_sink(struct dc_link *link, if (sink->edid_caps.panel_patch.skip_scdc_overwrite) link->ctx->dc->debug.hdmi20_disable = true; + if (sink->edid_caps.panel_patch.remove_sink_ext_caps) + link->dpcd_sink_ext_caps.raw = 0; + if (dc_is_hdmi_signal(link->connector_signal)) read_scdc_caps(link->ddc, link->local_sink); @@ -1163,6 +1166,12 @@ static bool detect_link_and_local_sink(struct dc_link *link, dm_helpers_init_panel_settings(dc_ctx, &link->panel_config, sink); // Override dc_panel_config if system has specific settings dm_helpers_override_panel_settings(dc_ctx, &link->panel_config); + + //sink only can use supported link rate table, we are foreced to enable it + if (link->reported_link_cap.link_rate == LINK_RATE_UNKNOWN) + link->panel_config.ilr.optimize_edp_link_rate = true; + if (edp_is_ilr_optimization_enabled(link)) + link->reported_link_cap.link_rate = get_max_link_rate_from_ilr_table(link); } } else { diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c index 79aef205598b7f..4901e27f678bcf 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c @@ -873,11 +873,15 @@ bool link_set_dsc_pps_packet(struct pipe_ctx *pipe_ctx, bool enable, bool immedi { struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc; struct dc_stream_state *stream = pipe_ctx->stream; - DC_LOGGER_INIT(dsc->ctx->logger); - if (!pipe_ctx->stream->timing.flags.DSC || !dsc) + if (!pipe_ctx->stream->timing.flags.DSC) + return false; + + if (!dsc) return false; + DC_LOGGER_INIT(dsc->ctx->logger); + if (enable) { struct dsc_config dsc_cfg; uint8_t dsc_packed_pps[128]; @@ -1055,18 +1059,21 @@ static struct fixed31_32 get_pbn_from_bw_in_kbps(uint64_t kbps) uint32_t denominator = 1; /* - * margin 5300ppm + 300ppm ~ 0.6% as per spec, factor is 1.006 + * The 1.006 factor (margin 5300ppm + 300ppm ~ 0.6% as per spec) is not + * required when determining PBN/time slot utilization on the link between + * us and the branch, since that overhead is already accounted for in + * the get_pbn_per_slot function. + * * The unit of 54/64Mbytes/sec is an arbitrary unit chosen based on * common multiplier to render an integer PBN for all link rate/lane * counts combinations * calculate - * peak_kbps *= (1006/1000) * peak_kbps *= (64/54) - * peak_kbps *= 8 convert to bytes + * peak_kbps /= (8 * 1000) convert to bytes */ - numerator = 64 * PEAK_FACTOR_X1000; - denominator = 54 * 8 * 1000 * 1000; + numerator = 64; + denominator = 54 * 8 * 1000; kbps *= numerator; peak_kbps = dc_fixpt_from_fraction(kbps, denominator); @@ -1930,7 +1937,7 @@ static void disable_link_dp(struct dc_link *link, dp_disable_link_phy(link, link_res, signal); if (link->connector_signal == SIGNAL_TYPE_EDP) { - if (!link->dc->config.edp_no_power_sequencing) + if (!link->skip_implict_edp_power_control) link->dc->hwss.edp_power_control(link, false); } @@ -2064,17 +2071,11 @@ static enum dc_status enable_link_dp(struct dc_state *state, } } - /* - * If the link is DP-over-USB4 do the following: - * - Train with fallback when enabling DPIA link. Conventional links are + /* Train with fallback when enabling DPIA link. Conventional links are * trained with fallback during sink detection. - * - Allocate only what the stream needs for bw in Gbps. Inform the CM - * in case stream needs more or less bw from what has been allocated - * earlier at plug time. */ - if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) do_fallback = true; - } /* * Temporary w/a to get DP2.0 link rates to work with SST. @@ -2140,8 +2141,7 @@ static enum dc_status enable_link_dp(struct dc_state *state, if (link->dpcd_sink_ext_caps.bits.oled == 1 || link->dpcd_sink_ext_caps.bits.sdr_aux_backlight_control == 1 || link->dpcd_sink_ext_caps.bits.hdr_aux_backlight_control == 1) { - set_cached_brightness_aux(link); - + set_default_brightness_aux(link); if (link->dpcd_sink_ext_caps.bits.oled == 1) msleep(bl_oled_enable_delay); edp_backlight_enable_aux(link, true); @@ -2219,7 +2219,7 @@ static enum dc_status enable_link( * link settings. Need to call disable first before enabling at * new link settings. */ - if (link->link_status.link_active && !stream->skip_edp_power_down) + if (link->link_status.link_active) disable_link(link, &pipe_ctx->link_res, pipe_ctx->stream->signal); switch (pipe_ctx->stream->signal) { @@ -2257,6 +2257,32 @@ static enum dc_status enable_link( return status; } +static bool allocate_usb4_bandwidth_for_stream(struct dc_stream_state *stream, int bw) +{ + return true; +} + +static bool allocate_usb4_bandwidth(struct dc_stream_state *stream) +{ + bool ret; + + int bw = dc_bandwidth_in_kbps_from_timing(&stream->timing, + dc_link_get_highest_encoding_format(stream->sink->link)); + + ret = allocate_usb4_bandwidth_for_stream(stream, bw); + + return ret; +} + +static bool deallocate_usb4_bandwidth(struct dc_stream_state *stream) +{ + bool ret; + + ret = allocate_usb4_bandwidth_for_stream(stream, 0); + + return ret; +} + void link_set_dpms_off(struct pipe_ctx *pipe_ctx) { struct dc *dc = pipe_ctx->stream->ctx->dc; @@ -2293,6 +2319,9 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx) update_psp_stream_config(pipe_ctx, true); dc->hwss.blank_stream(pipe_ctx); + if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + deallocate_usb4_bandwidth(pipe_ctx->stream); + if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) deallocate_mst_payload(pipe_ctx); else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT && @@ -2338,9 +2367,7 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx) dc->hwss.disable_stream(pipe_ctx); } else { dc->hwss.disable_stream(pipe_ctx); - if (!pipe_ctx->stream->skip_edp_power_down) { - disable_link(pipe_ctx->stream->link, &pipe_ctx->link_res, pipe_ctx->stream->signal); - } + disable_link(pipe_ctx->stream->link, &pipe_ctx->link_res, pipe_ctx->stream->signal); } if (pipe_ctx->stream->timing.flags.DSC) { @@ -2516,6 +2543,9 @@ void link_set_dpms_on( } } + if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + allocate_usb4_bandwidth(pipe_ctx->stream); + if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) allocate_mst_payload(pipe_ctx); else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT && diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c index 0895742a310241..eb7c9f226af5cb 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c @@ -223,6 +223,7 @@ static void construct_link_service_edp_panel_control(struct link_service *link_s link_srv->edp_receiver_ready_T9 = edp_receiver_ready_T9; link_srv->edp_receiver_ready_T7 = edp_receiver_ready_T7; link_srv->edp_power_alpm_dpcd_enable = edp_power_alpm_dpcd_enable; + link_srv->edp_set_panel_power = edp_set_panel_power; } /* link dp cts implements dp compliance test automation protocols and manual @@ -366,6 +367,27 @@ static enum transmitter translate_encoder_to_transmitter( } } +static uint8_t translate_dig_inst_to_pwrseq_inst(struct dc_link *link) +{ + uint8_t pwrseq_inst = 0xF; + + switch (link->eng_id) { + case ENGINE_ID_DIGA: + pwrseq_inst = 0; + break; + case ENGINE_ID_DIGB: + pwrseq_inst = 1; + break; + default: + DC_LOG_WARNING("Unsupported pwrseq engine id: %d!\n", link->eng_id); + ASSERT(false); + break; + } + + return pwrseq_inst; +} + + static void link_destruct(struct dc_link *link) { int i; @@ -381,7 +403,7 @@ static void link_destruct(struct dc_link *link) if (link->panel_cntl) link->panel_cntl->funcs->destroy(&link->panel_cntl); - if (link->link_enc) { + if (link->link_enc && !link->is_dig_mapping_flexible) { /* Update link encoder resource tracking variables. These are used for * the dynamic assignment of link encoders to streams. Virtual links * are not assigned encoder resources on creation. @@ -593,24 +615,6 @@ static bool construct_phy(struct dc_link *link, link->ddc_hw_inst = dal_ddc_get_line(get_ddc_pin(link->ddc)); - - if (link->dc->res_pool->funcs->panel_cntl_create && - (link->link_id.id == CONNECTOR_ID_EDP || - link->link_id.id == CONNECTOR_ID_LVDS)) { - panel_cntl_init_data.ctx = dc_ctx; - panel_cntl_init_data.inst = - panel_cntl_init_data.ctx->dc_edp_id_count; - link->panel_cntl = - link->dc->res_pool->funcs->panel_cntl_create( - &panel_cntl_init_data); - panel_cntl_init_data.ctx->dc_edp_id_count++; - - if (link->panel_cntl == NULL) { - DC_ERROR("Failed to create link panel_cntl!\n"); - goto panel_cntl_create_fail; - } - } - enc_init_data.ctx = dc_ctx; bp_funcs->get_src_obj(dc_ctx->dc_bios, link->link_id, 0, &enc_init_data.encoder); @@ -625,14 +629,14 @@ static bool construct_phy(struct dc_link *link, link->link_enc = link->dc->res_pool->funcs->link_enc_create(dc_ctx, &enc_init_data); - DC_LOG_DC("BIOS object table - DP_IS_USB_C: %d", link->link_enc->features.flags.bits.DP_IS_USB_C); - DC_LOG_DC("BIOS object table - IS_DP2_CAPABLE: %d", link->link_enc->features.flags.bits.IS_DP2_CAPABLE); - if (!link->link_enc) { DC_ERROR("Failed to create link encoder!\n"); goto link_enc_create_fail; } + DC_LOG_DC("BIOS object table - DP_IS_USB_C: %d", link->link_enc->features.flags.bits.DP_IS_USB_C); + DC_LOG_DC("BIOS object table - IS_DP2_CAPABLE: %d", link->link_enc->features.flags.bits.IS_DP2_CAPABLE); + /* Update link encoder tracking variables. These are used for the dynamic * assignment of link encoders to streams. */ @@ -641,6 +645,23 @@ static bool construct_phy(struct dc_link *link, link->dc->res_pool->dig_link_enc_count++; link->link_enc_hw_inst = link->link_enc->transmitter; + + if (link->dc->res_pool->funcs->panel_cntl_create && + (link->link_id.id == CONNECTOR_ID_EDP || + link->link_id.id == CONNECTOR_ID_LVDS)) { + panel_cntl_init_data.ctx = dc_ctx; + panel_cntl_init_data.inst = panel_cntl_init_data.ctx->dc_edp_id_count; + panel_cntl_init_data.pwrseq_inst = translate_dig_inst_to_pwrseq_inst(link); + link->panel_cntl = + link->dc->res_pool->funcs->panel_cntl_create( + &panel_cntl_init_data); + panel_cntl_init_data.ctx->dc_edp_id_count++; + + if (link->panel_cntl == NULL) { + DC_ERROR("Failed to create link panel_cntl!\n"); + goto panel_cntl_create_fail; + } + } for (i = 0; i < 4; i++) { if (bp_funcs->get_device_tag(dc_ctx->dc_bios, link->link_id, i, diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c index b45fda96eaf649..5b0bc7f6a188cc 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c @@ -346,23 +346,61 @@ enum dc_status link_validate_mode_timing( return DC_OK; } +/* + * This function calculates the bandwidth required for the stream timing + * and aggregates the stream bandwidth for the respective dpia link + * + * @stream: pointer to the dc_stream_state struct instance + * @num_streams: number of streams to be validated + * + * return: true if validation is succeeded + */ bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const unsigned int num_streams) { - bool ret = true; - int bw_needed[MAX_DPIA_NUM]; - struct dc_link *link[MAX_DPIA_NUM]; + int bw_needed[MAX_DPIA_NUM] = {0}; + struct dc_link *dpia_link[MAX_DPIA_NUM] = {0}; + int num_dpias = 0; + + for (unsigned int i = 0; i < num_streams; ++i) { + if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT) { + /* new dpia sst stream, check whether it exceeds max dpia */ + if (num_dpias >= MAX_DPIA_NUM) + return false; - if (!num_streams || num_streams > MAX_DPIA_NUM) - return ret; + dpia_link[num_dpias] = stream[i].link; + bw_needed[num_dpias] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing, + dc_link_get_highest_encoding_format(dpia_link[num_dpias])); + num_dpias++; + } else if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { + uint8_t j = 0; + /* check whether its a known dpia link */ + for (; j < num_dpias; ++j) { + if (dpia_link[j] == stream[i].link) + break; + } + + if (j == num_dpias) { + /* new dpia mst stream, check whether it exceeds max dpia */ + if (num_dpias >= MAX_DPIA_NUM) + return false; + else { + dpia_link[j] = stream[i].link; + num_dpias++; + } + } + + bw_needed[j] += dc_bandwidth_in_kbps_from_timing(&stream[i].timing, + dc_link_get_highest_encoding_format(dpia_link[j])); + } + } - for (uint8_t i = 0; i < num_streams; ++i) { + /* Include dp overheads */ + for (uint8_t i = 0; i < num_dpias; ++i) { + int dp_overhead = 0; - link[i] = stream[i].link; - bw_needed[i] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing, - dc_link_get_highest_encoding_format(link[i])); + dp_overhead = link_dp_dpia_get_dp_overhead_in_dp_tunneling(dpia_link[i]); + bw_needed[i] += dp_overhead; } - ret = dpia_validate_usb4_bw(link, bw_needed, num_streams); - - return ret; + return dpia_validate_usb4_bw(dpia_link, bw_needed, num_dpias); } diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c index 237e0ff955f3cc..3d589072fe307e 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c @@ -528,7 +528,7 @@ static bool decide_fallback_link_setting_max_bw_policy( struct dc_link_settings *cur, enum link_training_result training_result) { - uint8_t cur_idx = 0, next_idx; + uint32_t cur_idx = 0, next_idx; bool found = false; if (training_result == LINK_TRAINING_ABORT) @@ -707,8 +707,7 @@ bool edp_decide_link_settings(struct dc_link *link, * edp_supported_link_rates_count is only valid for eDP v1.4 or higher. * Per VESA eDP spec, "The DPCD revision for eDP v1.4 is 13h" */ - if (link->dpcd_caps.dpcd_rev.raw < DPCD_REV_13 || - link->dpcd_caps.edp_supported_link_rates_count == 0) { + if (!edp_is_ilr_optimization_enabled(link)) { *link_setting = link->verified_link_cap; return true; } @@ -772,8 +771,7 @@ bool decide_edp_link_settings_with_dsc(struct dc_link *link, * edp_supported_link_rates_count is only valid for eDP v1.4 or higher. * Per VESA eDP spec, "The DPCD revision for eDP v1.4 is 13h" */ - if ((link->dpcd_caps.dpcd_rev.raw < DPCD_REV_13 || - link->dpcd_caps.edp_supported_link_rates_count == 0)) { + if (!edp_is_ilr_optimization_enabled(link)) { /* for DSC enabled case, we search for minimum lane count */ memset(&initial_link_setting, 0, sizeof(initial_link_setting)); initial_link_setting.lane_count = LANE_COUNT_ONE; @@ -910,21 +908,17 @@ bool link_decide_link_settings(struct dc_stream_state *stream, memset(link_setting, 0, sizeof(*link_setting)); - /* if preferred is specified through AMDDP, use it, if it's enough - * to drive the mode - */ - if (link->preferred_link_setting.lane_count != - LANE_COUNT_UNKNOWN && - link->preferred_link_setting.link_rate != - LINK_RATE_UNKNOWN) { + if (dc_is_dp_signal(stream->signal) && + link->preferred_link_setting.lane_count != LANE_COUNT_UNKNOWN && + link->preferred_link_setting.link_rate != LINK_RATE_UNKNOWN) { + /* if preferred is specified through AMDDP, use it, if it's enough + * to drive the mode + */ *link_setting = link->preferred_link_setting; - return true; - } - - /* MST doesn't perform link training for now - * TODO: add MST specific link training routine - */ - if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { + } else if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { + /* MST doesn't perform link training for now + * TODO: add MST specific link training routine + */ decide_mst_link_settings(link, link_setting); } else if (link->connector_signal == SIGNAL_TYPE_EDP) { /* enable edp link optimization for DSC eDP case */ @@ -1586,9 +1580,17 @@ static bool retrieve_link_cap(struct dc_link *link) return false; } - if (dp_is_lttpr_present(link)) + if (dp_is_lttpr_present(link)) { configure_lttpr_mode_transparent(link); + // Echo TOTAL_LTTPR_CNT back downstream + core_link_write_dpcd( + link, + DP_TOTAL_LTTPR_CNT, + &link->dpcd_caps.lttpr_caps.phy_repeater_cnt, + sizeof(link->dpcd_caps.lttpr_caps.phy_repeater_cnt)); + } + /* Read DP tunneling information. */ status = dpcd_get_tunneling_device_data(link); @@ -1938,9 +1940,7 @@ void detect_edp_sink_caps(struct dc_link *link) * edp_supported_link_rates_count is only valid for eDP v1.4 or higher. * Per VESA eDP spec, "The DPCD revision for eDP v1.4 is 13h" */ - if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_13 && - (link->panel_config.ilr.optimize_edp_link_rate || - link->reported_link_cap.link_rate == LINK_RATE_UNKNOWN)) { + if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_13) { // Read DPCD 00010h - 0001Fh 16 bytes at one shot core_link_read_dpcd(link, DP_SUPPORTED_LINK_RATES, supported_link_rates, sizeof(supported_link_rates)); @@ -1958,12 +1958,10 @@ void detect_edp_sink_caps(struct dc_link *link) link_rate = linkRateInKHzToLinkRateMultiplier(link_rate_in_khz); link->dpcd_caps.edp_supported_link_rates[link->dpcd_caps.edp_supported_link_rates_count] = link_rate; link->dpcd_caps.edp_supported_link_rates_count++; - - if (link->reported_link_cap.link_rate < link_rate) - link->reported_link_cap.link_rate = link_rate; } } } + core_link_read_dpcd(link, DP_EDP_BACKLIGHT_ADJUSTMENT_CAP, &backlight_adj_cap, sizeof(backlight_adj_cap)); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c index 7581023daa4789..5a965c26bf2095 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c @@ -50,15 +50,28 @@ static bool get_bw_alloc_proceed_flag(struct dc_link *tmp) && tmp->hpd_status && tmp->dpia_bw_alloc_config.bw_alloc_enabled); } + static void reset_bw_alloc_struct(struct dc_link *link) { link->dpia_bw_alloc_config.bw_alloc_enabled = false; - link->dpia_bw_alloc_config.sink_verified_bw = 0; - link->dpia_bw_alloc_config.sink_max_bw = 0; + link->dpia_bw_alloc_config.link_verified_bw = 0; + link->dpia_bw_alloc_config.link_max_bw = 0; + link->dpia_bw_alloc_config.allocated_bw = 0; link->dpia_bw_alloc_config.estimated_bw = 0; link->dpia_bw_alloc_config.bw_granularity = 0; + link->dpia_bw_alloc_config.dp_overhead = 0; link->dpia_bw_alloc_config.response_ready = false; + link->dpia_bw_alloc_config.nrd_max_lane_count = 0; + link->dpia_bw_alloc_config.nrd_max_link_rate = 0; + for (int i = 0; i < MAX_SINKS_PER_LINK; i++) + link->dpia_bw_alloc_config.remote_sink_req_bw[i] = 0; + DC_LOG_DEBUG("reset usb4 bw alloc of link(%d)\n", link->link_index); } + +#define BW_GRANULARITY_0 4 // 0.25 Gbps +#define BW_GRANULARITY_1 2 // 0.5 Gbps +#define BW_GRANULARITY_2 1 // 1 Gbps + static uint8_t get_bw_granularity(struct dc_link *link) { uint8_t bw_granularity = 0; @@ -71,16 +84,20 @@ static uint8_t get_bw_granularity(struct dc_link *link) switch (bw_granularity & 0x3) { case 0: - bw_granularity = 4; + bw_granularity = BW_GRANULARITY_0; break; case 1: + bw_granularity = BW_GRANULARITY_1; + break; + case 2: default: - bw_granularity = 2; + bw_granularity = BW_GRANULARITY_2; break; } return bw_granularity; } + static int get_estimated_bw(struct dc_link *link) { uint8_t bw_estimated_bw = 0; @@ -93,31 +110,33 @@ static int get_estimated_bw(struct dc_link *link) return bw_estimated_bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity); } -static bool allocate_usb4_bw(int *stream_allocated_bw, int bw_needed, struct dc_link *link) + +static int get_non_reduced_max_link_rate(struct dc_link *link) { - if (bw_needed > 0) - *stream_allocated_bw += bw_needed; + uint8_t nrd_max_link_rate = 0; - return true; + core_link_read_dpcd( + link, + DP_TUNNELING_MAX_LINK_RATE, + &nrd_max_link_rate, + sizeof(uint8_t)); + + return nrd_max_link_rate; } -static bool deallocate_usb4_bw(int *stream_allocated_bw, int bw_to_dealloc, struct dc_link *link) -{ - bool ret = false; - if (*stream_allocated_bw > 0) { - *stream_allocated_bw -= bw_to_dealloc; - ret = true; - } else { - //Do nothing for now - ret = true; - } +static int get_non_reduced_max_lane_count(struct dc_link *link) +{ + uint8_t nrd_max_lane_count = 0; - // Unplug so reset values - if (!link->hpd_status) - reset_bw_alloc_struct(link); + core_link_read_dpcd( + link, + DP_TUNNELING_MAX_LANE_COUNT, + &nrd_max_lane_count, + sizeof(uint8_t)); - return ret; + return nrd_max_lane_count; } + /* * Read all New BW alloc configuration ex: estimated_bw, allocated_bw, * granuality, Driver_ID, CM_Group, & populate the BW allocation structs @@ -125,10 +144,22 @@ static bool deallocate_usb4_bw(int *stream_allocated_bw, int bw_to_dealloc, stru */ static void init_usb4_bw_struct(struct dc_link *link) { - // Init the known values + reset_bw_alloc_struct(link); + + /* init the known values */ link->dpia_bw_alloc_config.bw_granularity = get_bw_granularity(link); link->dpia_bw_alloc_config.estimated_bw = get_estimated_bw(link); + link->dpia_bw_alloc_config.nrd_max_link_rate = get_non_reduced_max_link_rate(link); + link->dpia_bw_alloc_config.nrd_max_lane_count = get_non_reduced_max_lane_count(link); + + DC_LOG_DEBUG("%s: bw_granularity(%d), estimated_bw(%d)\n", + __func__, link->dpia_bw_alloc_config.bw_granularity, + link->dpia_bw_alloc_config.estimated_bw); + DC_LOG_DEBUG("%s: nrd_max_link_rate(%d), nrd_max_lane_count(%d)\n", + __func__, link->dpia_bw_alloc_config.nrd_max_link_rate, + link->dpia_bw_alloc_config.nrd_max_lane_count); } + static uint8_t get_lowest_dpia_index(struct dc_link *link) { const struct dc *dc_struct = link->dc; @@ -141,51 +172,66 @@ static uint8_t get_lowest_dpia_index(struct dc_link *link) dc_struct->links[i]->ep_type != DISPLAY_ENDPOINT_USB4_DPIA) continue; - if (idx > dc_struct->links[i]->link_index) + if (idx > dc_struct->links[i]->link_index) { idx = dc_struct->links[i]->link_index; + break; + } } return idx; } + /* - * Get the Max Available BW or Max Estimated BW for each Host Router + * Get the maximum dp tunnel banwidth of host router * - * @link: pointer to the dc_link struct instance - * @type: ESTIMATD BW or MAX AVAILABLE BW + * @dc: pointer to the dc struct instance + * @hr_index: host router index * - * return: response_ready flag from dc_link struct + * return: host router maximum dp tunnel bandwidth */ -static int get_host_router_total_bw(struct dc_link *link, uint8_t type) +static int get_host_router_total_dp_tunnel_bw(const struct dc *dc, uint8_t hr_index) { - const struct dc *dc_struct = link->dc; - uint8_t lowest_dpia_index = get_lowest_dpia_index(link); - uint8_t idx = (link->link_index - lowest_dpia_index) / 2, idx_temp = 0; - struct dc_link *link_temp; + uint8_t lowest_dpia_index = get_lowest_dpia_index(dc->links[0]); + uint8_t hr_index_temp = 0; + struct dc_link *link_dpia_primary, *link_dpia_secondary; int total_bw = 0; - int i; - for (i = 0; i < MAX_PIPES * 2; ++i) { - - if (!dc_struct->links[i] || dc_struct->links[i]->ep_type != DISPLAY_ENDPOINT_USB4_DPIA) - continue; + for (uint8_t i = 0; i < (MAX_PIPES * 2) - 1; ++i) { - link_temp = dc_struct->links[i]; - if (!link_temp || !link_temp->hpd_status) + if (!dc->links[i] || dc->links[i]->ep_type != DISPLAY_ENDPOINT_USB4_DPIA) continue; - idx_temp = (link_temp->link_index - lowest_dpia_index) / 2; - - if (idx_temp == idx) { - - if (type == HOST_ROUTER_BW_ESTIMATED) - total_bw += link_temp->dpia_bw_alloc_config.estimated_bw; - else if (type == HOST_ROUTER_BW_ALLOCATED) - total_bw += link_temp->dpia_bw_alloc_config.sink_allocated_bw; + hr_index_temp = (dc->links[i]->link_index - lowest_dpia_index) / 2; + + if (hr_index_temp == hr_index) { + link_dpia_primary = dc->links[i]; + link_dpia_secondary = dc->links[i + 1]; + + /** + * If BW allocation enabled on both DPIAs, then + * HR BW = Estimated(dpia_primary) + Allocated(dpia_secondary) + * otherwise HR BW = Estimated(bw alloc enabled dpia) + */ + if ((link_dpia_primary->hpd_status && + link_dpia_primary->dpia_bw_alloc_config.bw_alloc_enabled) && + (link_dpia_secondary->hpd_status && + link_dpia_secondary->dpia_bw_alloc_config.bw_alloc_enabled)) { + total_bw += link_dpia_primary->dpia_bw_alloc_config.estimated_bw + + link_dpia_secondary->dpia_bw_alloc_config.allocated_bw; + } else if (link_dpia_primary->hpd_status && + link_dpia_primary->dpia_bw_alloc_config.bw_alloc_enabled) { + total_bw = link_dpia_primary->dpia_bw_alloc_config.estimated_bw; + } else if (link_dpia_secondary->hpd_status && + link_dpia_secondary->dpia_bw_alloc_config.bw_alloc_enabled) { + total_bw += link_dpia_secondary->dpia_bw_alloc_config.estimated_bw; + } + break; } } return total_bw; } + /* * Cleanup function for when the dpia is unplugged to reset struct * and perform any required clean up @@ -194,42 +240,49 @@ static int get_host_router_total_bw(struct dc_link *link, uint8_t type) * * return: none */ -static bool dpia_bw_alloc_unplug(struct dc_link *link) +static void dpia_bw_alloc_unplug(struct dc_link *link) { - if (!link) - return true; - - return deallocate_usb4_bw(&link->dpia_bw_alloc_config.sink_allocated_bw, - link->dpia_bw_alloc_config.sink_allocated_bw, link); + if (link) { + DC_LOG_DEBUG("%s: resetting bw alloc config for link(%d)\n", + __func__, link->link_index); + reset_bw_alloc_struct(link); + } } + static void set_usb4_req_bw_req(struct dc_link *link, int req_bw) { uint8_t requested_bw; uint32_t temp; - // 1. Add check for this corner case #1 - if (req_bw > link->dpia_bw_alloc_config.estimated_bw) + /* Error check whether request bw greater than allocated */ + if (req_bw > link->dpia_bw_alloc_config.estimated_bw) { + DC_LOG_ERROR("%s: Request bw greater than estimated bw for link(%d)\n", + __func__, link->link_index); req_bw = link->dpia_bw_alloc_config.estimated_bw; + } temp = req_bw * link->dpia_bw_alloc_config.bw_granularity; requested_bw = temp / Kbps_TO_Gbps; - // Always make sure to add more to account for floating points + /* Always make sure to add more to account for floating points */ if (temp % Kbps_TO_Gbps) ++requested_bw; - // 2. Add check for this corner case #2 + /* Error check whether requested and allocated are equal */ req_bw = requested_bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity); - if (req_bw == link->dpia_bw_alloc_config.sink_allocated_bw) - return; + if (req_bw && (req_bw == link->dpia_bw_alloc_config.allocated_bw)) { + DC_LOG_ERROR("%s: Request bw equals to allocated bw for link(%d)\n", + __func__, link->link_index); + } - if (core_link_write_dpcd( + link->dpia_bw_alloc_config.response_ready = false; // Reset flag + core_link_write_dpcd( link, REQUESTED_BW, &requested_bw, - sizeof(uint8_t)) == DC_OK) - link->dpia_bw_alloc_config.response_ready = false; // Reset flag + sizeof(uint8_t)); } + /* * Return the response_ready flag from dc_link struct * @@ -241,6 +294,7 @@ static bool get_cm_response_ready_flag(struct dc_link *link) { return link->dpia_bw_alloc_config.response_ready; } + // ------------------------------------------------------------------ // PUBLIC FUNCTIONS // ------------------------------------------------------------------ @@ -277,27 +331,35 @@ bool link_dp_dpia_set_dptx_usb4_bw_alloc_support(struct dc_link *link) DPTX_BW_ALLOCATION_MODE_CONTROL, &response, sizeof(uint8_t)) != DC_OK) { - DC_LOG_DEBUG("%s: **** FAILURE Enabling DPtx BW Allocation Mode Support ***\n", - __func__); + DC_LOG_DEBUG("%s: FAILURE Enabling DPtx BW Allocation Mode Support for link(%d)\n", + __func__, link->link_index); } else { // SUCCESS Enabled DPtx BW Allocation Mode Support - link->dpia_bw_alloc_config.bw_alloc_enabled = true; - DC_LOG_DEBUG("%s: **** SUCCESS Enabling DPtx BW Allocation Mode Support ***\n", - __func__); + DC_LOG_DEBUG("%s: SUCCESS Enabling DPtx BW Allocation Mode Support for link(%d)\n", + __func__, link->link_index); ret = true; init_usb4_bw_struct(link); + link->dpia_bw_alloc_config.bw_alloc_enabled = true; + + /* + * During DP tunnel creation, CM preallocates BW and reduces estimated BW of other + * DPIA. CM release preallocation only when allocation is complete. Do zero alloc + * to make the CM to release preallocation and update estimated BW correctly for + * all DPIAs per host router + */ + link_dp_dpia_allocate_usb4_bandwidth_for_stream(link, 0); } } out: return ret; } + void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t result) { int bw_needed = 0; int estimated = 0; - int host_router_total_estimated_bw = 0; if (!get_bw_alloc_proceed_flag((link))) return; @@ -306,14 +368,22 @@ void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t res case DPIA_BW_REQ_FAILED: - DC_LOG_DEBUG("%s: *** *** BW REQ FAILURE for DP-TX Request *** ***\n", __func__); + /* + * Ideally, we shouldn't run into this case as we always validate available + * bandwidth and request within that limit + */ + estimated = bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity); + + DC_LOG_ERROR("%s: BW REQ FAILURE for DP-TX Request for link(%d)\n", + __func__, link->link_index); + DC_LOG_ERROR("%s: current estimated_bw(%d), new estimated_bw(%d)\n", + __func__, link->dpia_bw_alloc_config.estimated_bw, estimated); - // Update the new Estimated BW value updated by CM - link->dpia_bw_alloc_config.estimated_bw = - bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity); + /* Update the new Estimated BW value updated by CM */ + link->dpia_bw_alloc_config.estimated_bw = estimated; + /* Allocate the previously requested bandwidth */ set_usb4_req_bw_req(link, link->dpia_bw_alloc_config.estimated_bw); - link->dpia_bw_alloc_config.response_ready = false; /* * If FAIL then it is either: @@ -326,68 +396,34 @@ void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t res case DPIA_BW_REQ_SUCCESS: - DC_LOG_DEBUG("%s: *** BW REQ SUCCESS for DP-TX Request ***\n", __func__); - - // 1. SUCCESS 1st time before any Pruning is done - // 2. SUCCESS after prev. FAIL before any Pruning is done - // 3. SUCCESS after Pruning is done but before enabling link - bw_needed = bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity); - // 1. - if (!link->dpia_bw_alloc_config.sink_allocated_bw) { - - allocate_usb4_bw(&link->dpia_bw_alloc_config.sink_allocated_bw, bw_needed, link); - link->dpia_bw_alloc_config.sink_verified_bw = - link->dpia_bw_alloc_config.sink_allocated_bw; - - // SUCCESS from first attempt - if (link->dpia_bw_alloc_config.sink_allocated_bw > - link->dpia_bw_alloc_config.sink_max_bw) - link->dpia_bw_alloc_config.sink_verified_bw = - link->dpia_bw_alloc_config.sink_max_bw; - } - // 3. - else if (link->dpia_bw_alloc_config.sink_allocated_bw) { - - // Find out how much do we need to de-alloc - if (link->dpia_bw_alloc_config.sink_allocated_bw > bw_needed) - deallocate_usb4_bw(&link->dpia_bw_alloc_config.sink_allocated_bw, - link->dpia_bw_alloc_config.sink_allocated_bw - bw_needed, link); - else - allocate_usb4_bw(&link->dpia_bw_alloc_config.sink_allocated_bw, - bw_needed - link->dpia_bw_alloc_config.sink_allocated_bw, link); - } + DC_LOG_DEBUG("%s: BW REQ SUCCESS for DP-TX Request for link(%d)\n", + __func__, link->link_index); + DC_LOG_DEBUG("%s: current allocated_bw(%d), new allocated_bw(%d)\n", + __func__, link->dpia_bw_alloc_config.allocated_bw, bw_needed); - // 4. If this is the 2nd sink then any unused bw will be reallocated to master DPIA - // => check if estimated_bw changed + link->dpia_bw_alloc_config.allocated_bw = bw_needed; link->dpia_bw_alloc_config.response_ready = true; break; case DPIA_EST_BW_CHANGED: - DC_LOG_DEBUG("%s: *** ESTIMATED BW CHANGED for DP-TX Request ***\n", __func__); - estimated = bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity); - host_router_total_estimated_bw = get_host_router_total_bw(link, HOST_ROUTER_BW_ESTIMATED); - // 1. If due to unplug of other sink - if (estimated == host_router_total_estimated_bw) { - // First update the estimated & max_bw fields - if (link->dpia_bw_alloc_config.estimated_bw < estimated) - link->dpia_bw_alloc_config.estimated_bw = estimated; - } - // 2. If due to realloc bw btw 2 dpia due to plug OR realloc unused Bw - else { - // We lost estimated bw usually due to plug event of other dpia - link->dpia_bw_alloc_config.estimated_bw = estimated; - } + DC_LOG_DEBUG("%s: ESTIMATED BW CHANGED for link(%d)\n", + __func__, link->link_index); + DC_LOG_DEBUG("%s: current estimated_bw(%d), new estimated_bw(%d)\n", + __func__, link->dpia_bw_alloc_config.estimated_bw, estimated); + + link->dpia_bw_alloc_config.estimated_bw = estimated; break; case DPIA_BW_ALLOC_CAPS_CHANGED: - DC_LOG_DEBUG("%s: *** BW ALLOC CAPABILITY CHANGED for DP-TX Request ***\n", __func__); + DC_LOG_ERROR("%s: BW ALLOC CAPABILITY CHANGED to Disabled for link(%d)\n", + __func__, link->link_index); link->dpia_bw_alloc_config.bw_alloc_enabled = false; break; } @@ -405,21 +441,21 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea if (link->hpd_status && peak_bw > 0) { // If DP over USB4 then we need to check BW allocation - link->dpia_bw_alloc_config.sink_max_bw = peak_bw; - set_usb4_req_bw_req(link, link->dpia_bw_alloc_config.sink_max_bw); + link->dpia_bw_alloc_config.link_max_bw = peak_bw; + set_usb4_req_bw_req(link, link->dpia_bw_alloc_config.link_max_bw); do { - if (!(timeout > 0)) + if (timeout > 0) timeout--; else break; - fsleep(10 * 1000); + msleep(10); } while (!get_cm_response_ready_flag(link)); if (!timeout) ret = 0;// ERROR TIMEOUT waiting for response for allocating bw - else if (link->dpia_bw_alloc_config.sink_allocated_bw > 0) - ret = get_host_router_total_bw(link, HOST_ROUTER_BW_ALLOCATED); + else if (link->dpia_bw_alloc_config.allocated_bw > 0) + ret = link->dpia_bw_alloc_config.allocated_bw; } //2. Cold Unplug else if (!link->hpd_status) @@ -428,65 +464,102 @@ int dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pea out: return ret; } -int link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int req_bw) +bool link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int req_bw) { - int ret = 0; + bool ret = false; uint8_t timeout = 10; + DC_LOG_DEBUG("%s: ENTER: link(%d), hpd_status(%d), current allocated_bw(%d), req_bw(%d)\n", + __func__, link->link_index, link->hpd_status, + link->dpia_bw_alloc_config.allocated_bw, req_bw); + if (!get_bw_alloc_proceed_flag(link)) goto out; - /* - * Sometimes stream uses same timing parameters as the already - * allocated max sink bw so no need to re-alloc - */ - if (req_bw != link->dpia_bw_alloc_config.sink_allocated_bw) { - set_usb4_req_bw_req(link, req_bw); - do { - if (!(timeout > 0)) - timeout--; - else - break; - udelay(10 * 1000); - } while (!get_cm_response_ready_flag(link)); + set_usb4_req_bw_req(link, req_bw); + do { + if (timeout > 0) + timeout--; + else + break; + msleep(10); + } while (!get_cm_response_ready_flag(link)); - if (!timeout) - ret = 0;// ERROR TIMEOUT waiting for response for allocating bw - else if (link->dpia_bw_alloc_config.sink_allocated_bw > 0) - ret = get_host_router_total_bw(link, HOST_ROUTER_BW_ALLOCATED); - } + if (timeout) + ret = true; out: + DC_LOG_DEBUG("%s: EXIT: timeout(%d), ret(%d)\n", __func__, timeout, ret); return ret; } + bool dpia_validate_usb4_bw(struct dc_link **link, int *bw_needed_per_dpia, const unsigned int num_dpias) { bool ret = true; - int bw_needed_per_hr[MAX_HR_NUM] = { 0, 0 }; - uint8_t lowest_dpia_index = 0, dpia_index = 0; - uint8_t i; + int bw_needed_per_hr[MAX_HR_NUM] = { 0, 0 }, host_router_total_dp_bw = 0; + uint8_t lowest_dpia_index, i, hr_index; if (!num_dpias || num_dpias > MAX_DPIA_NUM) return ret; - //Get total Host Router BW & Validate against each Host Router max BW + lowest_dpia_index = get_lowest_dpia_index(link[0]); + + /* get total Host Router BW with granularity for the given modes */ for (i = 0; i < num_dpias; ++i) { + int granularity_Gbps = 0; + int bw_granularity = 0; if (!link[i]->dpia_bw_alloc_config.bw_alloc_enabled) continue; - lowest_dpia_index = get_lowest_dpia_index(link[i]); if (link[i]->link_index < lowest_dpia_index) continue; - dpia_index = (link[i]->link_index - lowest_dpia_index) / 2; - bw_needed_per_hr[dpia_index] += bw_needed_per_dpia[i]; - if (bw_needed_per_hr[dpia_index] > get_host_router_total_bw(link[i], HOST_ROUTER_BW_ALLOCATED)) { + granularity_Gbps = (Kbps_TO_Gbps / link[i]->dpia_bw_alloc_config.bw_granularity); + bw_granularity = (bw_needed_per_dpia[i] / granularity_Gbps) * granularity_Gbps + + ((bw_needed_per_dpia[i] % granularity_Gbps) ? granularity_Gbps : 0); - ret = false; - break; + hr_index = (link[i]->link_index - lowest_dpia_index) / 2; + bw_needed_per_hr[hr_index] += bw_granularity; + } + + /* validate against each Host Router max BW */ + for (hr_index = 0; hr_index < MAX_HR_NUM; ++hr_index) { + if (bw_needed_per_hr[hr_index]) { + host_router_total_dp_bw = get_host_router_total_dp_tunnel_bw(link[0]->dc, hr_index); + if (bw_needed_per_hr[hr_index] > host_router_total_dp_bw) { + ret = false; + break; + } } } return ret; } + +int link_dp_dpia_get_dp_overhead_in_dp_tunneling(struct dc_link *link) +{ + int dp_overhead = 0, link_mst_overhead = 0; + + if (!get_bw_alloc_proceed_flag((link))) + return dp_overhead; + + /* if its mst link, add MTPH overhead */ + if ((link->type == dc_connection_mst_branch) && + !link->dpcd_caps.channel_coding_cap.bits.DP_128b_132b_SUPPORTED) { + /* For 8b/10b encoding: MTP is 64 time slots long, slot 0 is used for MTPH + * MST overhead is 1/64 of link bandwidth (excluding any overhead) + */ + const struct dc_link_settings *link_cap = + dc_link_get_link_cap(link); + uint32_t link_bw_in_kbps = (uint32_t)link_cap->link_rate * + (uint32_t)link_cap->lane_count * + LINK_RATE_REF_FREQ_IN_KHZ * 8; + link_mst_overhead = (link_bw_in_kbps / 64) + ((link_bw_in_kbps % 64) ? 1 : 0); + } + + /* add all the overheads */ + dp_overhead = link_mst_overhead; + + return dp_overhead; +} diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h index 7292690383ae1f..3b6d8494f9d5da 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h @@ -59,9 +59,9 @@ bool link_dp_dpia_set_dptx_usb4_bw_alloc_support(struct dc_link *link); * @link: pointer to the dc_link struct instance * @req_bw: Bw requested by the stream * - * return: allocated bw else return 0 + * return: true if allocated successfully */ -int link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int req_bw); +bool link_dp_dpia_allocate_usb4_bandwidth_for_stream(struct dc_link *link, int req_bw); /* * Handle the USB4 BW Allocation related functionality here: @@ -99,4 +99,13 @@ void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t res */ bool dpia_validate_usb4_bw(struct dc_link **link, int *bw_needed, const unsigned int num_dpias); +/* + * Obtain all the DP overheads in dp tunneling for the dpia link + * + * @link: pointer to the dc_link struct instance + * + * return: DP overheads in DP tunneling + */ +int link_dp_dpia_get_dp_overhead_in_dp_tunneling(struct dc_link *link); + #endif /* DC_INC_LINK_DP_DPIA_BW_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c index b7abba55bc2fdf..9bde0c8bf914a6 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c @@ -73,7 +73,8 @@ void dp_disable_link_phy(struct dc_link *link, { struct dc *dc = link->ctx->dc; - if (!link->wa_flags.dp_keep_receiver_powered) + if (!link->wa_flags.dp_keep_receiver_powered && + !link->skip_implict_edp_power_control) dpcd_write_rx_power_ctrl(link, false); dc->hwss.disable_link_output(link, link_res, signal); @@ -142,32 +143,25 @@ enum dc_status dp_set_fec_ready(struct dc_link *link, const struct link_resource link_enc = link_enc_cfg_get_link_enc(link); ASSERT(link_enc); + if (link_enc->funcs->fec_set_ready == NULL) + return DC_NOT_SUPPORTED; - if (!dp_should_enable_fec(link)) - return status; - - if (link_enc->funcs->fec_set_ready && - link->dpcd_caps.fec_cap.bits.FEC_CAPABLE) { - if (ready) { - fec_config = 1; - status = core_link_write_dpcd(link, - DP_FEC_CONFIGURATION, - &fec_config, - sizeof(fec_config)); - if (status == DC_OK) { - link_enc->funcs->fec_set_ready(link_enc, true); - link->fec_state = dc_link_fec_ready; - } else { - link_enc->funcs->fec_set_ready(link_enc, false); - link->fec_state = dc_link_fec_not_ready; - dm_error("dpcd write failed to set fec_ready"); - } - } else if (link->fec_state == dc_link_fec_ready) { + if (ready && dp_should_enable_fec(link)) { + fec_config = 1; + + status = core_link_write_dpcd(link, DP_FEC_CONFIGURATION, + &fec_config, sizeof(fec_config)); + + if (status == DC_OK) { + link_enc->funcs->fec_set_ready(link_enc, true); + link->fec_state = dc_link_fec_ready; + } + } else { + if (link->fec_state == dc_link_fec_ready) { fec_config = 0; - status = core_link_write_dpcd(link, - DP_FEC_CONFIGURATION, - &fec_config, - sizeof(fec_config)); + core_link_write_dpcd(link, DP_FEC_CONFIGURATION, + &fec_config, sizeof(fec_config)); + link_enc->funcs->fec_set_ready(link_enc, false); link->fec_state = dc_link_fec_not_ready; } @@ -182,14 +176,12 @@ void dp_set_fec_enable(struct dc_link *link, bool enable) link_enc = link_enc_cfg_get_link_enc(link); ASSERT(link_enc); - - if (!dp_should_enable_fec(link)) + if (link_enc->funcs->fec_set_enable == NULL) return; - if (link_enc->funcs->fec_set_enable && - link->dpcd_caps.fec_cap.bits.FEC_CAPABLE) { - if (link->fec_state == dc_link_fec_ready && enable) { - /* Accord to DP spec, FEC enable sequence can first + if (enable && dp_should_enable_fec(link)) { + if (link->fec_state == dc_link_fec_ready) { + /* According to DP spec, FEC enable sequence can first * be transmitted anytime after 1000 LL codes have * been transmitted on the link after link training * completion. Using 1 lane RBR should have the maximum @@ -199,7 +191,9 @@ void dp_set_fec_enable(struct dc_link *link, bool enable) udelay(7); link_enc->funcs->fec_set_enable(link_enc, true); link->fec_state = dc_link_fec_enabled; - } else if (link->fec_state == dc_link_fec_enabled && !enable) { + } + } else { + if (link->fec_state == dc_link_fec_enabled) { link_enc->funcs->fec_set_enable(link_enc, false); link->fec_state = dc_link_fec_ready; } diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c index 90339c2dfd8487..9d1adfc09fb2aa 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c @@ -517,6 +517,7 @@ enum link_training_result dp_check_link_loss_status( { enum link_training_result status = LINK_TRAINING_SUCCESS; union lane_status lane_status; + union lane_align_status_updated dpcd_lane_status_updated; uint8_t dpcd_buf[6] = {0}; uint32_t lane; @@ -532,10 +533,12 @@ enum link_training_result dp_check_link_loss_status( * check lanes status */ lane_status.raw = dp_get_nibble_at_index(&dpcd_buf[2], lane); + dpcd_lane_status_updated.raw = dpcd_buf[4]; if (!lane_status.bits.CHANNEL_EQ_DONE_0 || !lane_status.bits.CR_DONE_0 || - !lane_status.bits.SYMBOL_LOCKED_0) { + !lane_status.bits.SYMBOL_LOCKED_0 || + !dp_is_interlane_aligned(dpcd_lane_status_updated)) { /* if one of the channel equalization, clock * recovery or symbol lock is dropped * consider it as (link has been @@ -807,7 +810,7 @@ void dp_decide_lane_settings( const struct link_training_settings *lt_settings, const union lane_adjust ln_adjust[LANE_COUNT_DP_MAX], struct dc_lane_settings hw_lane_settings[LANE_COUNT_DP_MAX], - union dpcd_training_lane dpcd_lane_settings[LANE_COUNT_DP_MAX]) + union dpcd_training_lane *dpcd_lane_settings) { uint32_t lane; @@ -911,10 +914,10 @@ static enum dc_status configure_lttpr_mode_non_transparent( /* Driver does not need to train the first hop. Skip DPCD read and clear * AUX_RD_INTERVAL for DPTX-to-DPIA hop. */ - if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && repeater_cnt > 0 && repeater_cnt < MAX_REPEATER_CNT) link->dpcd_caps.lttpr_caps.aux_rd_interval[--repeater_cnt] = 0; - for (repeater_id = repeater_cnt; repeater_id > 0; repeater_id--) { + for (repeater_id = repeater_cnt; repeater_id > 0 && repeater_id < MAX_REPEATER_CNT; repeater_id--) { aux_interval_address = DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 + ((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (repeater_id - 1)); core_link_read_dpcd( diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h index 7d027bac82551d..851bd17317a0c4 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h @@ -111,7 +111,7 @@ void dp_decide_lane_settings( const struct link_training_settings *lt_settings, const union lane_adjust ln_adjust[LANE_COUNT_DP_MAX], struct dc_lane_settings hw_lane_settings[LANE_COUNT_DP_MAX], - union dpcd_training_lane dpcd_lane_settings[LANE_COUNT_DP_MAX]); + union dpcd_training_lane *dpcd_lane_settings); enum dc_dp_training_pattern decide_cr_training_pattern( const struct dc_link_settings *link_settings); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c index fd8f6f19814617..68096d12f52fd6 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c @@ -115,7 +115,7 @@ static enum link_training_result perform_fixed_vs_pe_nontransparent_training_seq lt_settings->cr_pattern_time = 16000; /* Fixed VS/PE specific: Toggle link rate */ - apply_toggle_rate_wa = (link->vendor_specific_lttpr_link_rate_wa == target_rate); + apply_toggle_rate_wa = ((link->vendor_specific_lttpr_link_rate_wa == target_rate) || (link->vendor_specific_lttpr_link_rate_wa == 0)); target_rate = get_dpcd_link_rate(<_settings->link_settings); toggle_rate = (target_rate == 0x6) ? 0xA : 0x6; @@ -271,7 +271,7 @@ enum link_training_result dp_perform_fixed_vs_pe_training_sequence_legacy( /* Vendor specific: Toggle link rate */ toggle_rate = (rate == 0x6) ? 0xA : 0x6; - if (link->vendor_specific_lttpr_link_rate_wa == rate) { + if (link->vendor_specific_lttpr_link_rate_wa == rate || link->vendor_specific_lttpr_link_rate_wa == 0) { core_link_write_dpcd( link, DP_LINK_BW_SET, @@ -617,7 +617,7 @@ enum link_training_result dp_perform_fixed_vs_pe_training_sequence( /* Vendor specific: Toggle link rate */ toggle_rate = (rate == 0x6) ? 0xA : 0x6; - if (link->vendor_specific_lttpr_link_rate_wa == rate) { + if (link->vendor_specific_lttpr_link_rate_wa == rate || link->vendor_specific_lttpr_link_rate_wa == 0) { core_link_write_dpcd( link, DP_LINK_BW_SET, diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c index 5c9a30211c109f..fc50931c2aecbb 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c @@ -205,7 +205,7 @@ enum dc_status core_link_read_dpcd( uint32_t extended_size; /* size of the remaining partitioned address space */ uint32_t size_left_to_read; - enum dc_status status; + enum dc_status status = DC_ERROR_UNEXPECTED; /* size of the next partition to be read from */ uint32_t partition_size; uint32_t data_index = 0; @@ -234,7 +234,7 @@ enum dc_status core_link_write_dpcd( { uint32_t partition_size; uint32_t data_index = 0; - enum dc_status status; + enum dc_status status = DC_ERROR_UNEXPECTED; while (size) { partition_size = dpcd_get_next_partition_size(address, size); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c index 98e715aa6d8e34..13104d000b9e09 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c @@ -33,6 +33,7 @@ #include "link_dp_capability.h" #include "dm_helpers.h" #include "dal_asic_id.h" +#include "link_dp_phy.h" #include "dce/dmub_psr.h" #include "dc/dc_dmub_srv.h" #include "dce/dmub_replay.h" @@ -167,7 +168,6 @@ bool edp_set_backlight_level_nits(struct dc_link *link, *(uint32_t *)&dpcd_backlight_set.backlight_level_millinits = backlight_millinits; *(uint16_t *)&dpcd_backlight_set.backlight_transition_time_ms = (uint16_t)transition_time_in_ms; - link->backlight_settings.backlight_millinits = backlight_millinits; if (!link->dpcd_caps.panel_luminance_control) { if (core_link_write_dpcd(link, DP_SOURCE_BACKLIGHT_LEVEL, @@ -280,9 +280,9 @@ bool set_default_brightness_aux(struct dc_link *link) if (link && link->dpcd_sink_ext_caps.bits.oled == 1) { if (!read_default_bl_aux(link, &default_backlight)) default_backlight = 150000; - // if < 5 nits or > 5000, it might be wrong readback - if (default_backlight < 5000 || default_backlight > 5000000) - default_backlight = 150000; // + // if < 1 nits or > 5000, it might be wrong readback + if (default_backlight < 1000 || default_backlight > 5000000) + default_backlight = 150000; return edp_set_backlight_level_nits(link, true, default_backlight, 0); @@ -290,14 +290,23 @@ bool set_default_brightness_aux(struct dc_link *link) return false; } -bool set_cached_brightness_aux(struct dc_link *link) +bool edp_is_ilr_optimization_enabled(struct dc_link *link) { - if (link->backlight_settings.backlight_millinits) - return edp_set_backlight_level_nits(link, true, - link->backlight_settings.backlight_millinits, 0); - else - return set_default_brightness_aux(link); - return false; + if (link->dpcd_caps.edp_supported_link_rates_count == 0 || !link->panel_config.ilr.optimize_edp_link_rate) + return false; + return true; +} + +enum dc_link_rate get_max_link_rate_from_ilr_table(struct dc_link *link) +{ + enum dc_link_rate link_rate = link->reported_link_cap.link_rate; + + for (int i = 0; i < link->dpcd_caps.edp_supported_link_rates_count; i++) { + if (link_rate < link->dpcd_caps.edp_supported_link_rates[i]) + link_rate = link->dpcd_caps.edp_supported_link_rates[i]; + } + + return link_rate; } bool edp_is_ilr_optimization_required(struct dc_link *link, @@ -311,8 +320,7 @@ bool edp_is_ilr_optimization_required(struct dc_link *link, ASSERT(link || crtc_timing); // invalid input - if (link->dpcd_caps.edp_supported_link_rates_count == 0 || - !link->panel_config.ilr.optimize_edp_link_rate) + if (!edp_is_ilr_optimization_enabled(link)) return false; @@ -362,6 +370,34 @@ void edp_panel_backlight_power_on(struct dc_link *link, bool wait_for_hpd) link->dc->hwss.edp_backlight_control(link, true); } +void edp_set_panel_power(struct dc_link *link, bool powerOn) +{ + if (powerOn) { + // 1. panel VDD on + if (!link->dc->config.edp_no_power_sequencing) + link->dc->hwss.edp_power_control(link, true); + link->dc->hwss.edp_wait_for_hpd_ready(link, true); + + // 2. panel BL on + if (link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_backlight_control(link, true); + + // 3. Rx power on + dpcd_write_rx_power_ctrl(link, true); + } else { + // 3. Rx power off + dpcd_write_rx_power_ctrl(link, false); + + // 2. panel BL off + if (link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_backlight_control(link, false); + + // 1. panel VDD off + if (!link->dc->config.edp_no_power_sequencing) + link->dc->hwss.edp_power_control(link, false); + } +} + bool edp_wait_for_t12(struct dc_link *link) { if (link->connector_signal == SIGNAL_TYPE_EDP && link->dc->hwss.edp_wait_for_T12) { @@ -846,7 +882,8 @@ bool edp_set_replay_allow_active(struct dc_link *link, const bool *allow_active, /* Set power optimization flag */ if (power_opts && link->replay_settings.replay_power_opt_active != *power_opts) { - if (link->replay_settings.replay_feature_enabled && replay->funcs->replay_set_power_opt) { + if (replay != NULL && link->replay_settings.replay_feature_enabled && + replay->funcs->replay_set_power_opt) { replay->funcs->replay_set_power_opt(replay, *power_opts, panel_inst); link->replay_settings.replay_power_opt_active = *power_opts; } @@ -884,8 +921,8 @@ bool edp_get_replay_state(const struct dc_link *link, uint64_t *state) bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream) { /* To-do: Setup Replay */ - struct dc *dc = link->ctx->dc; - struct dmub_replay *replay = dc->res_pool->replay; + struct dc *dc; + struct dmub_replay *replay; int i; unsigned int panel_inst; struct replay_context replay_context = { 0 }; @@ -901,6 +938,10 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream if (!link) return false; + dc = link->ctx->dc; + + replay = dc->res_pool->replay; + if (!replay) return false; @@ -929,8 +970,7 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream replay_context.line_time_in_ns = lineTimeInNs; - if (replay) - link->replay_settings.replay_feature_enabled = + link->replay_settings.replay_feature_enabled = replay->funcs->replay_copy_settings(replay, link, &replay_context, panel_inst); if (link->replay_settings.replay_feature_enabled) { diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h index 0a5bbda8c739c4..a034288ad75d4a 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h @@ -30,7 +30,6 @@ enum dp_panel_mode dp_get_panel_mode(struct dc_link *link); void dp_set_panel_mode(struct dc_link *link, enum dp_panel_mode panel_mode); bool set_default_brightness_aux(struct dc_link *link); -bool set_cached_brightness_aux(struct dc_link *link); void edp_panel_backlight_power_on(struct dc_link *link, bool wait_for_hpd); int edp_get_backlight_level(const struct dc_link *link); bool edp_get_backlight_level_nits(struct dc_link *link, @@ -64,9 +63,12 @@ bool edp_get_replay_state(const struct dc_link *link, uint64_t *state); bool edp_wait_for_t12(struct dc_link *link); bool edp_is_ilr_optimization_required(struct dc_link *link, struct dc_crtc_timing *crtc_timing); +bool edp_is_ilr_optimization_enabled(struct dc_link *link); +enum dc_link_rate get_max_link_rate_from_ilr_table(struct dc_link *link); bool edp_backlight_enable_aux(struct dc_link *link, bool enable); void edp_add_delay_for_T9(struct dc_link *link); bool edp_receiver_ready_T9(struct dc_link *link); bool edp_receiver_ready_T7(struct dc_link *link); bool edp_power_alpm_dpcd_enable(struct dc_link *link, bool enable); +void edp_set_panel_power(struct dc_link *link, bool powerOn); #endif /* __DC_LINK_EDP_POWER_CONTROL_H__ */ diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h index 2d995c87fbb986..d3c4a9a577eeab 100644 --- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h @@ -186,6 +186,7 @@ struct dmub_srv_region_params { uint32_t vbios_size; const uint8_t *fw_inst_const; const uint8_t *fw_bss_data; + bool is_mailbox_in_inbox; }; /** @@ -205,20 +206,25 @@ struct dmub_srv_region_params { */ struct dmub_srv_region_info { uint32_t fb_size; + uint32_t inbox_size; uint8_t num_regions; struct dmub_region regions[DMUB_WINDOW_TOTAL]; }; /** - * struct dmub_srv_fb_params - parameters used for driver fb setup + * struct dmub_srv_memory_params - parameters used for driver fb setup * @region_info: region info calculated by dmub service - * @cpu_addr: base cpu address for the framebuffer - * @gpu_addr: base gpu virtual address for the framebuffer + * @cpu_fb_addr: base cpu address for the framebuffer + * @cpu_inbox_addr: base cpu address for the gart + * @gpu_fb_addr: base gpu virtual address for the framebuffer + * @gpu_inbox_addr: base gpu virtual address for the gart */ -struct dmub_srv_fb_params { +struct dmub_srv_memory_params { const struct dmub_srv_region_info *region_info; - void *cpu_addr; - uint64_t gpu_addr; + void *cpu_fb_addr; + void *cpu_inbox_addr; + uint64_t gpu_fb_addr; + uint64_t gpu_inbox_addr; }; /** @@ -546,8 +552,8 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, * DMUB_STATUS_OK - success * DMUB_STATUS_INVALID - unspecified error */ -enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub, - const struct dmub_srv_fb_params *params, +enum dmub_status dmub_srv_calc_mem_info(struct dmub_srv *dmub, + const struct dmub_srv_memory_params *params, struct dmub_srv_fb_info *out); /** diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index 7afa78b918b58f..d58cb7f63a4b12 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -3301,6 +3301,16 @@ struct dmub_cmd_abm_set_pipe_data { * TODO: Remove. */ uint8_t ramping_boundary; + + /** + * PwrSeq HW Instance. + */ + uint8_t pwrseq_inst; + + /** + * Explicit padding to 4 byte boundary. + */ + uint8_t pad[3]; }; /** @@ -3715,7 +3725,7 @@ enum dmub_cmd_panel_cntl_type { * struct dmub_cmd_panel_cntl_data - Panel control data. */ struct dmub_cmd_panel_cntl_data { - uint32_t inst; /**< panel instance */ + uint32_t pwrseq_inst; /**< pwrseq instance */ uint32_t current_backlight; /* in/out */ uint32_t bl_pwm_cntl; /* in/out */ uint32_t bl_pwm_period_cntl; /* in/out */ @@ -3742,7 +3752,7 @@ struct dmub_cmd_lvtma_control_data { uint8_t uc_pwr_action; /**< LVTMA_ACTION */ uint8_t bypass_panel_control_wait; uint8_t reserved_0[2]; /**< For future use */ - uint8_t panel_inst; /**< LVTMA control instance */ + uint8_t pwrseq_inst; /**< LVTMA control instance */ uint8_t reserved_1[3]; /**< For future use */ }; diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c index 93624ffe4eb824..6c45e216c709c2 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c @@ -386,7 +386,7 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, uint32_t fw_state_size = DMUB_FW_STATE_SIZE; uint32_t trace_buffer_size = DMUB_TRACE_BUFFER_SIZE; uint32_t scratch_mem_size = DMUB_SCRATCH_MEM_SIZE; - + uint32_t previous_top = 0; if (!dmub->sw_init) return DMUB_STATUS_INVALID; @@ -411,8 +411,15 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, bios->base = dmub_align(stack->top, 256); bios->top = bios->base + params->vbios_size; - mail->base = dmub_align(bios->top, 256); - mail->top = mail->base + DMUB_MAILBOX_SIZE; + if (params->is_mailbox_in_inbox) { + mail->base = 0; + mail->top = mail->base + DMUB_MAILBOX_SIZE; + previous_top = bios->top; + } else { + mail->base = dmub_align(bios->top, 256); + mail->top = mail->base + DMUB_MAILBOX_SIZE; + previous_top = mail->top; + } fw_info = dmub_get_fw_meta_info(params); @@ -431,7 +438,7 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, dmub->fw_version = fw_info->fw_version; } - trace_buff->base = dmub_align(mail->top, 256); + trace_buff->base = dmub_align(previous_top, 256); trace_buff->top = trace_buff->base + dmub_align(trace_buffer_size, 64); fw_state->base = dmub_align(trace_buff->top, 256); @@ -442,11 +449,14 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, out->fb_size = dmub_align(scratch_mem->top, 4096); + if (params->is_mailbox_in_inbox) + out->inbox_size = dmub_align(mail->top, 4096); + return DMUB_STATUS_OK; } -enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub, - const struct dmub_srv_fb_params *params, +enum dmub_status dmub_srv_calc_mem_info(struct dmub_srv *dmub, + const struct dmub_srv_memory_params *params, struct dmub_srv_fb_info *out) { uint8_t *cpu_base; @@ -461,8 +471,8 @@ enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub, if (params->region_info->num_regions != DMUB_NUM_WINDOWS) return DMUB_STATUS_INVALID; - cpu_base = (uint8_t *)params->cpu_addr; - gpu_base = params->gpu_addr; + cpu_base = (uint8_t *)params->cpu_fb_addr; + gpu_base = params->gpu_fb_addr; for (i = 0; i < DMUB_NUM_WINDOWS; ++i) { const struct dmub_region *reg = @@ -470,6 +480,12 @@ enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub, out->fb[i].cpu_addr = cpu_base + reg->base; out->fb[i].gpu_addr = gpu_base + reg->base; + + if (i == DMUB_WINDOW_4_MAILBOX && params->cpu_inbox_addr != 0) { + out->fb[i].cpu_addr = (uint8_t *)params->cpu_inbox_addr + reg->base; + out->fb[i].gpu_addr = params->gpu_inbox_addr + reg->base; + } + out->fb[i].size = reg->top - reg->base; } @@ -658,9 +674,16 @@ enum dmub_status dmub_srv_sync_inbox1(struct dmub_srv *dmub) return DMUB_STATUS_INVALID; if (dmub->hw_funcs.get_inbox1_rptr && dmub->hw_funcs.get_inbox1_wptr) { - dmub->inbox1_rb.rptr = dmub->hw_funcs.get_inbox1_rptr(dmub); - dmub->inbox1_rb.wrpt = dmub->hw_funcs.get_inbox1_wptr(dmub); - dmub->inbox1_last_wptr = dmub->inbox1_rb.wrpt; + uint32_t rptr = dmub->hw_funcs.get_inbox1_rptr(dmub); + uint32_t wptr = dmub->hw_funcs.get_inbox1_wptr(dmub); + + if (rptr > dmub->inbox1_rb.capacity || wptr > dmub->inbox1_rb.capacity) { + return DMUB_STATUS_HW_FAILURE; + } else { + dmub->inbox1_rb.rptr = rptr; + dmub->inbox1_rb.wrpt = wptr; + dmub->inbox1_last_wptr = dmub->inbox1_rb.wrpt; + } } return DMUB_STATUS_OK; @@ -694,6 +717,11 @@ enum dmub_status dmub_srv_cmd_queue(struct dmub_srv *dmub, if (!dmub->hw_init) return DMUB_STATUS_INVALID; + if (dmub->inbox1_rb.rptr > dmub->inbox1_rb.capacity || + dmub->inbox1_rb.wrpt > dmub->inbox1_rb.capacity) { + return DMUB_STATUS_HW_FAILURE; + } + if (dmub_rb_push_front(&dmub->inbox1_rb, cmd)) return DMUB_STATUS_OK; @@ -969,6 +997,7 @@ enum dmub_status dmub_srv_wait_for_inbox0_ack(struct dmub_srv *dmub, uint32_t ti ack = dmub->hw_funcs.read_inbox0_ack_register(dmub); if (ack) return DMUB_STATUS_OK; + udelay(1); } return DMUB_STATUS_TIMEOUT; } diff --git a/drivers/gpu/drm/amd/display/include/dpcd_defs.h b/drivers/gpu/drm/amd/display/include/dpcd_defs.h index 914f28e9f22426..aee5170f5fb231 100644 --- a/drivers/gpu/drm/amd/display/include/dpcd_defs.h +++ b/drivers/gpu/drm/amd/display/include/dpcd_defs.h @@ -177,4 +177,9 @@ enum dpcd_psr_sink_states { #define DP_SINK_PR_PIXEL_DEVIATION_PER_LINE 0x379 #define DP_SINK_PR_MAX_NUMBER_OF_DEVIATION_LINE 0x37A +/* Remove once drm_dp_helper.h is updated upstream */ +#ifndef DP_TOTAL_LTTPR_CNT +#define DP_TOTAL_LTTPR_CNT 0xF000A /* 2.1 */ +#endif + #endif /* __DAL_DPCD_DEFS_H__ */ diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h index bc96d021136080..813463ffe15c52 100644 --- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h +++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h @@ -417,6 +417,8 @@ struct integrated_info { /* V2.1 */ struct edp_info edp1_info; struct edp_info edp2_info; + uint32_t gpuclk_ss_percentage; + uint32_t gpuclk_ss_type; }; /* diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index ef3a674090211c..803586f4267af8 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -133,7 +133,7 @@ unsigned int mod_freesync_calc_v_total_from_refresh( v_total = div64_u64(div64_u64(((unsigned long long)( frame_duration_in_ns) * (stream->timing.pix_clk_100hz / 10)), - stream->timing.h_total), 1000000); + stream->timing.h_total) + 500000, 1000000); /* v_total cannot be less than nominal */ if (v_total < stream->timing.v_total) { diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c index 1ddb4f5eac8e53..cee5e9e64ae711 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c @@ -432,18 +432,18 @@ static enum mod_hdcp_status authenticated_dp(struct mod_hdcp *hdcp, goto out; } - if (status == MOD_HDCP_STATUS_SUCCESS) - mod_hdcp_execute_and_set(mod_hdcp_read_bstatus, - &input->bstatus_read, &status, - hdcp, "bstatus_read"); - if (status == MOD_HDCP_STATUS_SUCCESS) - mod_hdcp_execute_and_set(check_link_integrity_dp, - &input->link_integrity_check, &status, - hdcp, "link_integrity_check"); - if (status == MOD_HDCP_STATUS_SUCCESS) - mod_hdcp_execute_and_set(check_no_reauthentication_request_dp, - &input->reauth_request_check, &status, - hdcp, "reauth_request_check"); + mod_hdcp_execute_and_set(mod_hdcp_read_bstatus, + &input->bstatus_read, &status, + hdcp, "bstatus_read"); + + mod_hdcp_execute_and_set(check_link_integrity_dp, + &input->link_integrity_check, &status, + hdcp, "link_integrity_check"); + + mod_hdcp_execute_and_set(check_no_reauthentication_request_dp, + &input->reauth_request_check, &status, + hdcp, "reauth_request_check"); + out: return status; } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c index f7b5583ee609a5..1b2df97226a3f2 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c @@ -156,7 +156,16 @@ static enum mod_hdcp_status read(struct mod_hdcp *hdcp, uint32_t cur_size = 0; uint32_t data_offset = 0; + if (msg_id == MOD_HDCP_MESSAGE_ID_INVALID || + msg_id >= MOD_HDCP_MESSAGE_ID_MAX) + return MOD_HDCP_STATUS_DDC_FAILURE; + if (is_dp_hdcp(hdcp)) { + int num_dpcd_addrs = sizeof(hdcp_dpcd_addrs) / + sizeof(hdcp_dpcd_addrs[0]); + if (msg_id >= num_dpcd_addrs) + return MOD_HDCP_STATUS_DDC_FAILURE; + while (buf_len > 0) { cur_size = MIN(buf_len, HDCP_MAX_AUX_TRANSACTION_SIZE); success = hdcp->config.ddc.funcs.read_dpcd(hdcp->config.ddc.handle, @@ -171,6 +180,11 @@ static enum mod_hdcp_status read(struct mod_hdcp *hdcp, data_offset += cur_size; } } else { + int num_i2c_offsets = sizeof(hdcp_i2c_offsets) / + sizeof(hdcp_i2c_offsets[0]); + if (msg_id >= num_i2c_offsets) + return MOD_HDCP_STATUS_DDC_FAILURE; + success = hdcp->config.ddc.funcs.read_i2c( hdcp->config.ddc.handle, HDCP_I2C_ADDR, @@ -215,7 +229,16 @@ static enum mod_hdcp_status write(struct mod_hdcp *hdcp, uint32_t cur_size = 0; uint32_t data_offset = 0; + if (msg_id == MOD_HDCP_MESSAGE_ID_INVALID || + msg_id >= MOD_HDCP_MESSAGE_ID_MAX) + return MOD_HDCP_STATUS_DDC_FAILURE; + if (is_dp_hdcp(hdcp)) { + int num_dpcd_addrs = sizeof(hdcp_dpcd_addrs) / + sizeof(hdcp_dpcd_addrs[0]); + if (msg_id >= num_dpcd_addrs) + return MOD_HDCP_STATUS_DDC_FAILURE; + while (buf_len > 0) { cur_size = MIN(buf_len, HDCP_MAX_AUX_TRANSACTION_SIZE); success = hdcp->config.ddc.funcs.write_dpcd( @@ -231,6 +254,11 @@ static enum mod_hdcp_status write(struct mod_hdcp *hdcp, data_offset += cur_size; } } else { + int num_i2c_offsets = sizeof(hdcp_i2c_offsets) / + sizeof(hdcp_i2c_offsets[0]); + if (msg_id >= num_i2c_offsets) + return MOD_HDCP_STATUS_DDC_FAILURE; + hdcp->buf[0] = hdcp_i2c_offsets[msg_id]; memmove(&hdcp->buf[1], buf, buf_len); success = hdcp->config.ddc.funcs.write_i2c( diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index ee67a35c2a8edd..ff930a71e496a9 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -513,6 +513,9 @@ enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp) hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf; memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory)); + if (!display) + return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND; + hdcp_cmd->in_msg.hdcp2_create_session_v2.display_handle = display->index; if (hdcp->connection.link.adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_0) diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h b/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h index 4220fd8fdd60ca..54cd86060f4d67 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h @@ -57,10 +57,10 @@ void mod_stats_update_event(struct mod_stats *mod_stats, unsigned int length); void mod_stats_update_flip(struct mod_stats *mod_stats, - unsigned long timestamp_in_ns); + unsigned long long timestamp_in_ns); void mod_stats_update_vupdate(struct mod_stats *mod_stats, - unsigned long timestamp_in_ns); + unsigned long long timestamp_in_ns); void mod_stats_update_freesync(struct mod_stats *mod_stats, unsigned int v_total_min, diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 73a2b37fbbd759..2b3d5183818aca 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -839,6 +839,8 @@ bool is_psr_su_specific_panel(struct dc_link *link) ((dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x08) || (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x07))) isPSRSUSupported = false; + else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03) + isPSRSUSupported = false; else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1) isPSRSUSupported = true; } diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 67d7b7ee8a2a02..a9880fc5319550 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -240,7 +240,6 @@ enum DC_FEATURE_MASK { DC_DISABLE_LTTPR_DP2_0 = (1 << 6), //0x40, disabled by default DC_PSR_ALLOW_SMU_OPT = (1 << 7), //0x80, disabled by default DC_PSR_ALLOW_MULTI_DISP_OPT = (1 << 8), //0x100, disabled by default - DC_REPLAY_MASK = (1 << 9), //0x200, disabled by default for dcn < 3.1.4 }; enum DC_DEBUG_MASK { @@ -251,7 +250,6 @@ enum DC_DEBUG_MASK { DC_DISABLE_PSR = 0x10, DC_FORCE_SUBVP_MCLK_SWITCH = 0x20, DC_DISABLE_MPO = 0x40, - DC_DISABLE_REPLAY = 0x50, DC_ENABLE_DPIA_TRACE = 0x80, }; @@ -297,6 +295,7 @@ struct amd_ip_funcs { int (*hw_init)(void *handle); int (*hw_fini)(void *handle); void (*late_fini)(void *handle); + int (*prepare_suspend)(void *handle); int (*suspend)(void *handle); int (*resume)(void *handle); bool (*is_idle)(void *handle); diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h index c92c4b83253f81..4bff1ef8a9a640 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h @@ -6369,6 +6369,8 @@ #define regTCP_INVALIDATE_BASE_IDX 1 #define regTCP_STATUS 0x19a1 #define regTCP_STATUS_BASE_IDX 1 +#define regTCP_CNTL 0x19a2 +#define regTCP_CNTL_BASE_IDX 1 #define regTCP_CNTL2 0x19a3 #define regTCP_CNTL2_BASE_IDX 1 #define regTCP_DEBUG_INDEX 0x19a5 diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index fa7d6ced786f19..ccc79bdd4f5adf 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -702,7 +702,7 @@ struct atom_gpio_pin_lut_v2_1 { struct atom_common_table_header table_header; /*the real number of this included in the structure is calcualted by using the (whole structure size - the header size)/size of atom_gpio_pin_lut */ - struct atom_gpio_pin_assignment gpio_pin[8]; + struct atom_gpio_pin_assignment gpio_pin[]; }; @@ -1006,7 +1006,7 @@ struct display_object_info_table_v1_4 uint16_t supporteddevices; uint8_t number_of_path; uint8_t reserved; - struct atom_display_object_path_v2 display_path[8]; //the real number of this included in the structure is calculated by using the (whole structure size - the header size- number_of_path)/size of atom_display_object_path + struct atom_display_object_path_v2 display_path[]; //the real number of this included in the structure is calculated by using the (whole structure size - the header size- number_of_path)/size of atom_display_object_path }; struct display_object_info_table_v1_5 { @@ -1016,7 +1016,7 @@ struct display_object_info_table_v1_5 { uint8_t reserved; // the real number of this included in the structure is calculated by using the // (whole structure size - the header size- number_of_path)/size of atom_display_object_path - struct atom_display_object_path_v3 display_path[8]; + struct atom_display_object_path_v3 display_path[]; }; /* @@ -1625,6 +1625,49 @@ struct atom_integrated_system_info_v2_2 uint32_t reserved4[189]; }; +struct uma_carveout_option { + char optionName[29]; //max length of string is 28chars + '\0'. Current design is for "minimum", "Medium", "High". This makes entire struct size 64bits + uint8_t memoryCarvedGb; //memory carved out with setting + uint8_t memoryRemainingGb; //memory remaining on system + union { + struct _flags { + uint8_t Auto : 1; + uint8_t Custom : 1; + uint8_t Reserved : 6; + } flags; + uint8_t all8; + } uma_carveout_option_flags; +}; + +struct atom_integrated_system_info_v2_3 { + struct atom_common_table_header table_header; + uint32_t vbios_misc; // enum of atom_system_vbiosmisc_def + uint32_t gpucapinfo; // enum of atom_system_gpucapinf_def + uint32_t system_config; + uint32_t cpucapinfo; + uint16_t gpuclk_ss_percentage; // unit of 0.001%, 1000 mean 1% + uint16_t gpuclk_ss_type; + uint16_t dpphy_override; // bit vector, enum of atom_sysinfo_dpphy_override_def + uint8_t memorytype; // enum of atom_dmi_t17_mem_type_def, APU memory type indication. + uint8_t umachannelnumber; // number of memory channels + uint8_t htc_hyst_limit; + uint8_t htc_tmp_limit; + uint8_t reserved1; // dp_ss_control + uint8_t gpu_package_id; + struct edp_info_table edp1_info; + struct edp_info_table edp2_info; + uint32_t reserved2[8]; + struct atom_external_display_connection_info extdispconninfo; + uint8_t UMACarveoutVersion; + uint8_t UMACarveoutIndexMax; + uint8_t UMACarveoutTypeDefault; + uint8_t UMACarveoutIndexDefault; + uint8_t UMACarveoutType; //Auto or Custom + uint8_t UMACarveoutIndex; + struct uma_carveout_option UMASizeControlOption[20]; + uint8_t reserved3[110]; +}; + // system_config enum atom_system_vbiosmisc_def{ INTEGRATED_SYSTEM_INFO__GET_EDID_CALLBACK_FUNC_SUPPORT = 0x01, @@ -3508,7 +3551,7 @@ struct atom_gpio_voltage_object_v4 uint8_t phase_delay_us; // phase delay in unit of micro second uint8_t reserved; uint32_t gpio_mask_val; // GPIO Mask value - struct atom_voltage_gpio_map_lut voltage_gpio_lut[1]; + struct atom_voltage_gpio_map_lut voltage_gpio_lut[] __counted_by(gpio_entry_num); }; struct atom_svid2_voltage_object_v4 diff --git a/drivers/gpu/drm/amd/include/mes_v11_api_def.h b/drivers/gpu/drm/amd/include/mes_v11_api_def.h index b1db2b19018742..e07e93167a82c2 100644 --- a/drivers/gpu/drm/amd/include/mes_v11_api_def.h +++ b/drivers/gpu/drm/amd/include/mes_v11_api_def.h @@ -571,7 +571,8 @@ struct SET_SHADER_DEBUGGER { struct { uint32_t single_memop : 1; /* SQ_DEBUG.single_memop */ uint32_t single_alu_op : 1; /* SQ_DEBUG.single_alu_op */ - uint32_t reserved : 30; + uint32_t reserved : 29; + uint32_t process_ctx_flush : 1; }; uint32_t u32all; } flags; diff --git a/drivers/gpu/drm/amd/include/pptable.h b/drivers/gpu/drm/amd/include/pptable.h index 0b6a057e0a4c48..5aac8d545bdc6d 100644 --- a/drivers/gpu/drm/amd/include/pptable.h +++ b/drivers/gpu/drm/amd/include/pptable.h @@ -78,7 +78,7 @@ typedef struct _ATOM_PPLIB_THERMALCONTROLLER typedef struct _ATOM_PPLIB_STATE { UCHAR ucNonClockStateIndex; - UCHAR ucClockStateIndices[1]; // variable-sized + UCHAR ucClockStateIndices[]; // variable-sized } ATOM_PPLIB_STATE; @@ -473,7 +473,7 @@ typedef struct _ATOM_PPLIB_STATE_V2 /** * Driver will read the first ucNumDPMLevels in this array */ - UCHAR clockInfoIndex[1]; + UCHAR clockInfoIndex[]; } ATOM_PPLIB_STATE_V2; typedef struct _StateArray{ diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 8bb2da13826f16..babb73147adfb3 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -734,7 +734,7 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev, if (adev->in_suspend && !adev->in_runpm) return -EPERM; - if (count > 127) + if (count > 127 || count == 0) return -EINVAL; if (*buf == 's') @@ -754,7 +754,8 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev, else return -EINVAL; - memcpy(buf_cpy, buf, count+1); + memcpy(buf_cpy, buf, count); + buf_cpy[count] = 0; tmp_str = buf_cpy; @@ -771,6 +772,9 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev, return -EINVAL; parameter_size++; + if (!tmp_str) + break; + while (isspace(*tmp_str)) tmp_str++; } @@ -1467,9 +1471,9 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev, return -EINVAL; } -static unsigned int amdgpu_hwmon_get_sensor_generic(struct amdgpu_device *adev, - enum amd_pp_sensors sensor, - void *query) +static int amdgpu_hwmon_get_sensor_generic(struct amdgpu_device *adev, + enum amd_pp_sensors sensor, + void *query) { int r, size = sizeof(uint32_t); @@ -2391,6 +2395,7 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev, { struct amdgpu_device *adev = dev_get_drvdata(dev); int err, ret; + u32 pwm_mode; int value; if (amdgpu_in_reset(adev)) @@ -2402,13 +2407,22 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev, if (err) return err; + if (value == 0) + pwm_mode = AMD_FAN_CTRL_NONE; + else if (value == 1) + pwm_mode = AMD_FAN_CTRL_MANUAL; + else if (value == 2) + pwm_mode = AMD_FAN_CTRL_AUTO; + else + return -EINVAL; + ret = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (ret < 0) { pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); return ret; } - ret = amdgpu_dpm_set_fan_control_mode(adev, value); + ret = amdgpu_dpm_set_fan_control_mode(adev, pwm_mode); pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); @@ -2773,8 +2787,8 @@ static ssize_t amdgpu_hwmon_show_vddnb_label(struct device *dev, return sysfs_emit(buf, "vddnb\n"); } -static unsigned int amdgpu_hwmon_get_power(struct device *dev, - enum amd_pp_sensors sensor) +static int amdgpu_hwmon_get_power(struct device *dev, + enum amd_pp_sensors sensor) { struct amdgpu_device *adev = dev_get_drvdata(dev); unsigned int uw; @@ -2795,7 +2809,7 @@ static ssize_t amdgpu_hwmon_show_power_avg(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned int val; + int val; val = amdgpu_hwmon_get_power(dev, AMDGPU_PP_SENSOR_GPU_AVG_POWER); if (val < 0) @@ -2808,7 +2822,7 @@ static ssize_t amdgpu_hwmon_show_power_input(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned int val; + int val; val = amdgpu_hwmon_get_power(dev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER); if (val < 0) diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c index 5d28c951a31972..c8586cb7d0fec5 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c @@ -164,6 +164,8 @@ static void sumo_construct_vid_mapping_table(struct amdgpu_device *adev, for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++) { if (table[i].ulSupportedSCLK != 0) { + if (table[i].usVoltageIndex >= SUMO_MAX_NUMBER_VOLTAGES) + continue; vid_mapping_table->entries[table[i].usVoltageIndex].vid_7bit = table[i].usVoltageID; vid_mapping_table->entries[table[i].usVoltageIndex].vid_2bit = @@ -2735,10 +2737,8 @@ static int kv_parse_power_table(struct amdgpu_device *adev) non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *) &non_clock_info_array->nonClockInfo[non_clock_array_index]; ps = kzalloc(sizeof(struct kv_ps), GFP_KERNEL); - if (ps == NULL) { - kfree(adev->pm.dpm.ps); + if (ps == NULL) return -ENOMEM; - } adev->pm.dpm.ps[i].ps_priv = ps; k = 0; idx = (u8 *)&power_state->v2.clockInfoIndex[0]; diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c index 81fb4e5dd804bd..60377747bab4fc 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c @@ -272,10 +272,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) le16_to_cpu(power_info->pplib4.usVddcDependencyOnSCLKOffset)); ret = amdgpu_parse_clk_voltage_dep_table(&adev->pm.dpm.dyn_state.vddc_dependency_on_sclk, dep_table); - if (ret) { - amdgpu_free_extended_power_table(adev); + if (ret) return ret; - } } if (power_info->pplib4.usVddciDependencyOnMCLKOffset) { dep_table = (ATOM_PPLIB_Clock_Voltage_Dependency_Table *) @@ -283,10 +281,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) le16_to_cpu(power_info->pplib4.usVddciDependencyOnMCLKOffset)); ret = amdgpu_parse_clk_voltage_dep_table(&adev->pm.dpm.dyn_state.vddci_dependency_on_mclk, dep_table); - if (ret) { - amdgpu_free_extended_power_table(adev); + if (ret) return ret; - } } if (power_info->pplib4.usVddcDependencyOnMCLKOffset) { dep_table = (ATOM_PPLIB_Clock_Voltage_Dependency_Table *) @@ -294,10 +290,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) le16_to_cpu(power_info->pplib4.usVddcDependencyOnMCLKOffset)); ret = amdgpu_parse_clk_voltage_dep_table(&adev->pm.dpm.dyn_state.vddc_dependency_on_mclk, dep_table); - if (ret) { - amdgpu_free_extended_power_table(adev); + if (ret) return ret; - } } if (power_info->pplib4.usMvddDependencyOnMCLKOffset) { dep_table = (ATOM_PPLIB_Clock_Voltage_Dependency_Table *) @@ -305,10 +299,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) le16_to_cpu(power_info->pplib4.usMvddDependencyOnMCLKOffset)); ret = amdgpu_parse_clk_voltage_dep_table(&adev->pm.dpm.dyn_state.mvdd_dependency_on_mclk, dep_table); - if (ret) { - amdgpu_free_extended_power_table(adev); + if (ret) return ret; - } } if (power_info->pplib4.usMaxClockVoltageOnDCOffset) { ATOM_PPLIB_Clock_Voltage_Limit_Table *clk_v = @@ -339,10 +331,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) kcalloc(psl->ucNumEntries, sizeof(struct amdgpu_phase_shedding_limits_entry), GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.phase_shedding_limits_table.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.phase_shedding_limits_table.entries) return -ENOMEM; - } entry = &psl->entries[0]; for (i = 0; i < psl->ucNumEntries; i++) { @@ -383,10 +373,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) ATOM_PPLIB_CAC_Leakage_Record *entry; u32 size = cac_table->ucNumEntries * sizeof(struct amdgpu_cac_leakage_table); adev->pm.dpm.dyn_state.cac_leakage_table.entries = kzalloc(size, GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.cac_leakage_table.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.cac_leakage_table.entries) return -ENOMEM; - } entry = &cac_table->entries[0]; for (i = 0; i < cac_table->ucNumEntries; i++) { if (adev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_EVV) { @@ -438,10 +426,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) sizeof(struct amdgpu_vce_clock_voltage_dependency_entry); adev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries = kzalloc(size, GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries) return -ENOMEM; - } adev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.count = limits->numEntries; entry = &limits->entries[0]; @@ -493,10 +479,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) sizeof(struct amdgpu_uvd_clock_voltage_dependency_entry); adev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries = kzalloc(size, GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries) return -ENOMEM; - } adev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.count = limits->numEntries; entry = &limits->entries[0]; @@ -525,10 +509,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) sizeof(struct amdgpu_clock_voltage_dependency_entry); adev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.entries = kzalloc(size, GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.entries) return -ENOMEM; - } adev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.count = limits->numEntries; entry = &limits->entries[0]; @@ -548,10 +530,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) le16_to_cpu(ext_hdr->usPPMTableOffset)); adev->pm.dpm.dyn_state.ppm_table = kzalloc(sizeof(struct amdgpu_ppm_table), GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.ppm_table) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.ppm_table) return -ENOMEM; - } adev->pm.dpm.dyn_state.ppm_table->ppm_design = ppm->ucPpmDesign; adev->pm.dpm.dyn_state.ppm_table->cpu_core_number = le16_to_cpu(ppm->usCpuCoreNumber); @@ -583,10 +563,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) sizeof(struct amdgpu_clock_voltage_dependency_entry); adev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.entries = kzalloc(size, GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.entries) return -ENOMEM; - } adev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.count = limits->numEntries; entry = &limits->entries[0]; @@ -606,10 +584,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) ATOM_PowerTune_Table *pt; adev->pm.dpm.dyn_state.cac_tdp_table = kzalloc(sizeof(struct amdgpu_cac_tdp_table), GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.cac_tdp_table) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.cac_tdp_table) return -ENOMEM; - } if (rev > 0) { ATOM_PPLIB_POWERTUNE_Table_V1 *ppt = (ATOM_PPLIB_POWERTUNE_Table_V1 *) (mode_info->atom_context->bios + data_offset + @@ -645,10 +621,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) ret = amdgpu_parse_clk_voltage_dep_table( &adev->pm.dpm.dyn_state.vddgfx_dependency_on_sclk, dep_table); - if (ret) { - kfree(adev->pm.dpm.dyn_state.vddgfx_dependency_on_sclk.entries); + if (ret) return ret; - } } } diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index 02e69ccff3bac4..99dde52a429013 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -6925,6 +6925,23 @@ static int si_dpm_enable(struct amdgpu_device *adev) return 0; } +static int si_set_temperature_range(struct amdgpu_device *adev) +{ + int ret; + + ret = si_thermal_enable_alert(adev, false); + if (ret) + return ret; + ret = si_thermal_set_temperature_range(adev, R600_TEMP_RANGE_MIN, R600_TEMP_RANGE_MAX); + if (ret) + return ret; + ret = si_thermal_enable_alert(adev, true); + if (ret) + return ret; + + return ret; +} + static void si_dpm_disable(struct amdgpu_device *adev) { struct rv7xx_power_info *pi = rv770_get_pi(adev); @@ -7379,10 +7396,9 @@ static int si_dpm_init(struct amdgpu_device *adev) kcalloc(4, sizeof(struct amdgpu_clock_voltage_dependency_entry), GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries) return -ENOMEM; - } + adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.count = 4; adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[0].clk = 0; adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[0].v = 0; @@ -7609,6 +7625,18 @@ static int si_dpm_process_interrupt(struct amdgpu_device *adev, static int si_dpm_late_init(void *handle) { + int ret; + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + if (!adev->pm.dpm_enabled) + return 0; + + ret = si_set_temperature_range(adev); + if (ret) + return ret; +#if 0 //TODO ? + si_dpm_powergate_uvd(adev, true); +#endif return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 9e4f8a4104a346..86f95a291d65f6 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -99,7 +99,7 @@ static void pp_swctf_delayed_work_handler(struct work_struct *work) struct amdgpu_device *adev = hwmgr->adev; struct amdgpu_dpm_thermal *range = &adev->pm.dpm.thermal; - uint32_t gpu_temperature, size; + uint32_t gpu_temperature, size = sizeof(gpu_temperature); int ret; /* @@ -927,7 +927,7 @@ static int pp_dpm_switch_power_profile(void *handle, enum PP_SMC_POWER_PROFILE type, bool en) { struct pp_hwmgr *hwmgr = handle; - long workload; + long workload[1]; uint32_t index; if (!hwmgr || !hwmgr->pm_en) @@ -945,12 +945,12 @@ static int pp_dpm_switch_power_profile(void *handle, hwmgr->workload_mask &= ~(1 << hwmgr->workload_prority[type]); index = fls(hwmgr->workload_mask); index = index > 0 && index <= Workload_Policy_Max ? index - 1 : 0; - workload = hwmgr->workload_setting[index]; + workload[0] = hwmgr->workload_setting[index]; } else { hwmgr->workload_mask |= (1 << hwmgr->workload_prority[type]); index = fls(hwmgr->workload_mask); index = index <= Workload_Policy_Max ? index - 1 : 0; - workload = hwmgr->workload_setting[index]; + workload[0] = hwmgr->workload_setting[index]; } if (type == PP_SMC_POWER_PROFILE_COMPUTE && @@ -960,7 +960,7 @@ static int pp_dpm_switch_power_profile(void *handle, } if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) - hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, &workload, 0); + hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, workload, 0); return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c index 1d829402cd2e23..18f00038d8441c 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c @@ -30,9 +30,8 @@ int psm_init_power_state_table(struct pp_hwmgr *hwmgr) { int result; unsigned int i; - unsigned int table_entries; struct pp_power_state *state; - int size; + int size, table_entries; if (hwmgr->hwmgr_func->get_num_of_pp_table_entries == NULL) return 0; @@ -40,15 +39,19 @@ int psm_init_power_state_table(struct pp_hwmgr *hwmgr) if (hwmgr->hwmgr_func->get_power_state_size == NULL) return 0; - hwmgr->num_ps = table_entries = hwmgr->hwmgr_func->get_num_of_pp_table_entries(hwmgr); + table_entries = hwmgr->hwmgr_func->get_num_of_pp_table_entries(hwmgr); - hwmgr->ps_size = size = hwmgr->hwmgr_func->get_power_state_size(hwmgr) + + size = hwmgr->hwmgr_func->get_power_state_size(hwmgr) + sizeof(struct pp_power_state); - if (table_entries == 0 || size == 0) { + if (table_entries <= 0 || size == 0) { pr_warn("Please check whether power state management is supported on this asic\n"); + hwmgr->num_ps = 0; + hwmgr->ps_size = 0; return 0; } + hwmgr->num_ps = table_entries; + hwmgr->ps_size = size; hwmgr->ps = kcalloc(table_entries, size, GFP_KERNEL); if (hwmgr->ps == NULL) @@ -269,7 +272,7 @@ int psm_adjust_power_state_dynamic(struct pp_hwmgr *hwmgr, bool skip_display_set struct pp_power_state *new_ps) { uint32_t index; - long workload; + long workload[1]; if (hwmgr->not_vf) { if (!skip_display_settings) @@ -294,10 +297,10 @@ int psm_adjust_power_state_dynamic(struct pp_hwmgr *hwmgr, bool skip_display_set if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) { index = fls(hwmgr->workload_mask); index = index > 0 && index <= Workload_Policy_Max ? index - 1 : 0; - workload = hwmgr->workload_setting[index]; + workload[0] = hwmgr->workload_setting[index]; - if (hwmgr->power_profile_mode != workload && hwmgr->hwmgr_func->set_power_profile_mode) - hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, &workload, 0); + if (hwmgr->power_profile_mode != workload[0] && hwmgr->hwmgr_func->set_power_profile_mode) + hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, workload, 0); } return 0; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c index f503e61faa6008..cc3b62f7339417 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c @@ -73,8 +73,9 @@ static int atomctrl_retrieve_ac_timing( j++; } else if ((table->mc_reg_address[i].uc_pre_reg_data & LOW_NIBBLE_MASK) == DATA_EQU_PREV) { - table->mc_reg_table_entry[num_ranges].mc_data[i] = - table->mc_reg_table_entry[num_ranges].mc_data[i-1]; + if (i) + table->mc_reg_table_entry[num_ranges].mc_data[i] = + table->mc_reg_table_entry[num_ranges].mc_data[i-1]; } } num_ranges++; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h index 7a31cfa5e7fb4d..9fcad69a9f3446 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h @@ -164,7 +164,7 @@ typedef struct _ATOM_Tonga_State { typedef struct _ATOM_Tonga_State_Array { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Tonga_State entries[1]; /* Dynamically allocate entries. */ + ATOM_Tonga_State entries[]; /* Dynamically allocate entries. */ } ATOM_Tonga_State_Array; typedef struct _ATOM_Tonga_MCLK_Dependency_Record { @@ -179,7 +179,7 @@ typedef struct _ATOM_Tonga_MCLK_Dependency_Record { typedef struct _ATOM_Tonga_MCLK_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Tonga_MCLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Tonga_MCLK_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Tonga_MCLK_Dependency_Table; typedef struct _ATOM_Tonga_SCLK_Dependency_Record { @@ -194,7 +194,7 @@ typedef struct _ATOM_Tonga_SCLK_Dependency_Record { typedef struct _ATOM_Tonga_SCLK_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Tonga_SCLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Tonga_SCLK_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Tonga_SCLK_Dependency_Table; typedef struct _ATOM_Polaris_SCLK_Dependency_Record { @@ -210,7 +210,7 @@ typedef struct _ATOM_Polaris_SCLK_Dependency_Record { typedef struct _ATOM_Polaris_SCLK_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Polaris_SCLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Polaris_SCLK_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Polaris_SCLK_Dependency_Table; typedef struct _ATOM_Tonga_PCIE_Record { @@ -222,7 +222,7 @@ typedef struct _ATOM_Tonga_PCIE_Record { typedef struct _ATOM_Tonga_PCIE_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Tonga_PCIE_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Tonga_PCIE_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Tonga_PCIE_Table; typedef struct _ATOM_Polaris10_PCIE_Record { @@ -235,7 +235,7 @@ typedef struct _ATOM_Polaris10_PCIE_Record { typedef struct _ATOM_Polaris10_PCIE_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Polaris10_PCIE_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Polaris10_PCIE_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Polaris10_PCIE_Table; @@ -252,7 +252,7 @@ typedef struct _ATOM_Tonga_MM_Dependency_Record { typedef struct _ATOM_Tonga_MM_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Tonga_MM_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Tonga_MM_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Tonga_MM_Dependency_Table; typedef struct _ATOM_Tonga_Voltage_Lookup_Record { @@ -265,7 +265,7 @@ typedef struct _ATOM_Tonga_Voltage_Lookup_Record { typedef struct _ATOM_Tonga_Voltage_Lookup_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Tonga_Voltage_Lookup_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Tonga_Voltage_Lookup_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Tonga_Voltage_Lookup_Table; typedef struct _ATOM_Tonga_Fan_Table { diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c index f2a55c1413f597..17882f8dfdd34f 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c @@ -200,7 +200,7 @@ static int get_platform_power_management_table( struct pp_hwmgr *hwmgr, ATOM_Tonga_PPM_Table *atom_ppm_table) { - struct phm_ppm_table *ptr = kzalloc(sizeof(ATOM_Tonga_PPM_Table), GFP_KERNEL); + struct phm_ppm_table *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL); struct phm_ppt_v1_information *pp_table_information = (struct phm_ppt_v1_information *)(hwmgr->pptable); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c index 5794b64507bf94..56a22575258064 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c @@ -1185,6 +1185,8 @@ static int init_overdrive_limits(struct pp_hwmgr *hwmgr, fw_info = smu_atom_get_data_table(hwmgr->adev, GetIndexIntoMasterTable(DATA, FirmwareInfo), &size, &frev, &crev); + PP_ASSERT_WITH_CODE(fw_info != NULL, + "Missing firmware info!", return -EINVAL); if ((fw_info->ucTableFormatRevision == 1) && (le16_to_cpu(fw_info->usStructureSize) >= sizeof(ATOM_FIRMWARE_INFO_V1_4))) diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index 02ba68d7c6546b..f62381b189ade9 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -1036,7 +1036,9 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, switch (type) { case PP_SCLK: - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetGfxclkFrequency, &now); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetGfxclkFrequency, &now); + if (ret) + return ret; /* driver only know min/max gfx_clk, Add level 1 for all other gfx clks */ if (now == data->gfx_max_freq_limit/100) @@ -1057,7 +1059,9 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, i == 2 ? "*" : ""); break; case PP_MCLK: - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetFclkFrequency, &now); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetFclkFrequency, &now); + if (ret) + return ret; for (i = 0; i < mclk_table->count; i++) size += sprintf(buf + size, "%d: %uMhz %s\n", @@ -1550,7 +1554,10 @@ static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr, } if (input[0] == 0) { - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq); + if (ret) + return ret; + if (input[1] < min_freq) { pr_err("Fine grain setting minimum sclk (%ld) MHz is less than the minimum allowed (%d) MHz\n", input[1], min_freq); @@ -1558,7 +1565,10 @@ static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr, } smu10_data->gfx_actual_soft_min_freq = input[1]; } else if (input[0] == 1) { - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq); + if (ret) + return ret; + if (input[1] > max_freq) { pr_err("Fine grain setting maximum sclk (%ld) MHz is greater than the maximum allowed (%d) MHz\n", input[1], max_freq); @@ -1573,10 +1583,15 @@ static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr, pr_err("Input parameter number not correct\n"); return -EINVAL; } - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq); - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq); - + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq); + if (ret) + return ret; smu10_data->gfx_actual_soft_min_freq = min_freq; + + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq); + if (ret) + return ret; + smu10_data->gfx_actual_soft_max_freq = max_freq; } else if (type == PP_OD_COMMIT_DPM_TABLE) { if (size != 0) { diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 5a2371484a58c5..53849fd3615f68 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -1823,9 +1823,7 @@ static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr) data->mclk_dpm_key_disabled = hwmgr->feature_mask & PP_MCLK_DPM_MASK ? false : true; data->sclk_dpm_key_disabled = hwmgr->feature_mask & PP_SCLK_DPM_MASK ? false : true; - data->pcie_dpm_key_disabled = - !amdgpu_device_pcie_dynamic_switching_supported() || - !(hwmgr->feature_mask & PP_PCIE_DPM_MASK); + data->pcie_dpm_key_disabled = !(hwmgr->feature_mask & PP_PCIE_DPM_MASK); /* need to set voltage control types before EVV patching */ data->voltage_control = SMU7_VOLTAGE_CONTROL_NONE; data->vddci_control = SMU7_VOLTAGE_CONTROL_NONE; @@ -2959,6 +2957,7 @@ static int smu7_update_edc_leakage_table(struct pp_hwmgr *hwmgr) static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) { + struct amdgpu_device *adev = hwmgr->adev; struct smu7_hwmgr *data; int result = 0; @@ -2976,6 +2975,8 @@ static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) result = smu7_get_evv_voltages(hwmgr); if (result) { pr_info("Get EVV Voltage Failed. Abort Driver loading!\n"); + kfree(hwmgr->backend); + hwmgr->backend = NULL; return -EINVAL; } } else { @@ -2993,38 +2994,37 @@ static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) /* Initalize Dynamic State Adjustment Rule Settings */ result = phm_initializa_dynamic_state_adjustment_rule_settings(hwmgr); - if (0 == result) { - struct amdgpu_device *adev = hwmgr->adev; + if (result) + goto fail; - data->is_tlu_enabled = false; + data->is_tlu_enabled = false; - hwmgr->platform_descriptor.hardwareActivityPerformanceLevels = + hwmgr->platform_descriptor.hardwareActivityPerformanceLevels = SMU7_MAX_HARDWARE_POWERLEVELS; - hwmgr->platform_descriptor.hardwarePerformanceLevels = 2; - hwmgr->platform_descriptor.minimumClocksReductionPercentage = 50; + hwmgr->platform_descriptor.hardwarePerformanceLevels = 2; + hwmgr->platform_descriptor.minimumClocksReductionPercentage = 50; - data->pcie_gen_cap = adev->pm.pcie_gen_mask; - if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) - data->pcie_spc_cap = 20; - else - data->pcie_spc_cap = 16; - data->pcie_lane_cap = adev->pm.pcie_mlw_mask; - - hwmgr->platform_descriptor.vbiosInterruptId = 0x20000400; /* IRQ_SOURCE1_SW_INT */ -/* The true clock step depends on the frequency, typically 4.5 or 9 MHz. Here we use 5. */ - hwmgr->platform_descriptor.clockStep.engineClock = 500; - hwmgr->platform_descriptor.clockStep.memoryClock = 500; - smu7_thermal_parameter_init(hwmgr); - } else { - /* Ignore return value in here, we are cleaning up a mess. */ - smu7_hwmgr_backend_fini(hwmgr); - } + data->pcie_gen_cap = adev->pm.pcie_gen_mask; + if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) + data->pcie_spc_cap = 20; + else + data->pcie_spc_cap = 16; + data->pcie_lane_cap = adev->pm.pcie_mlw_mask; + + hwmgr->platform_descriptor.vbiosInterruptId = 0x20000400; /* IRQ_SOURCE1_SW_INT */ + /* The true clock step depends on the frequency, typically 4.5 or 9 MHz. Here we use 5. */ + hwmgr->platform_descriptor.clockStep.engineClock = 500; + hwmgr->platform_descriptor.clockStep.memoryClock = 500; + smu7_thermal_parameter_init(hwmgr); result = smu7_update_edc_leakage_table(hwmgr); if (result) - return result; + goto fail; return 0; +fail: + smu7_hwmgr_backend_fini(hwmgr); + return result; } static int smu7_force_dpm_highest(struct pp_hwmgr *hwmgr) @@ -3314,8 +3314,7 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, const struct pp_power_state *current_ps) { struct amdgpu_device *adev = hwmgr->adev; - struct smu7_power_state *smu7_ps = - cast_phw_smu7_power_state(&request_ps->hardware); + struct smu7_power_state *smu7_ps; uint32_t sclk; uint32_t mclk; struct PP_Clocks minimum_clocks = {0}; @@ -3332,6 +3331,10 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, uint32_t latency; bool latency_allowed = false; + smu7_ps = cast_phw_smu7_power_state(&request_ps->hardware); + if (!smu7_ps) + return -EINVAL; + data->battery_state = (PP_StateUILabel_Battery == request_ps->classification.ui_label); data->mclk_ignore_signal = false; @@ -3997,6 +4000,7 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx, uint32_t sclk, mclk, activity_percent; uint32_t offset, val_vid; struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); + struct amdgpu_device *adev = hwmgr->adev; /* size must be at least 4 bytes for all sensors */ if (*size < 4) @@ -4040,7 +4044,21 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx, *size = 4; return 0; case AMDGPU_PP_SENSOR_GPU_INPUT_POWER: - return smu7_get_gpu_power(hwmgr, (uint32_t *)value); + if ((adev->asic_type != CHIP_HAWAII) && + (adev->asic_type != CHIP_BONAIRE) && + (adev->asic_type != CHIP_FIJI) && + (adev->asic_type != CHIP_TONGA)) + return smu7_get_gpu_power(hwmgr, (uint32_t *)value); + else + return -EOPNOTSUPP; + case AMDGPU_PP_SENSOR_GPU_AVG_POWER: + if ((adev->asic_type != CHIP_HAWAII) && + (adev->asic_type != CHIP_BONAIRE) && + (adev->asic_type != CHIP_FIJI) && + (adev->asic_type != CHIP_TONGA)) + return -EOPNOTSUPP; + else + return smu7_get_gpu_power(hwmgr, (uint32_t *)value); case AMDGPU_PP_SENSOR_VDDGFX: if ((data->vr_config & VRCONF_VDDGFX_MASK) == (VR_SVI2_PLANE_2 << VRCONF_VDDGFX_SHIFT)) @@ -5623,7 +5641,7 @@ static int smu7_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, uint mode = input[size]; switch (mode) { case PP_SMC_POWER_PROFILE_CUSTOM: - if (size < 8 && size != 0) + if (size != 8 && size != 0) return -EINVAL; /* If only CUSTOM is passed in, use the saved values. Check * that we actually have a CUSTOM profile by ensuring that diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c index b015a601b385ae..7e119742087325 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c @@ -584,6 +584,7 @@ static int smu8_init_uvd_limit(struct pp_hwmgr *hwmgr) hwmgr->dyn_state.uvd_clock_voltage_dependency_table; unsigned long clock = 0; uint32_t level; + int ret; if (NULL == table || table->count <= 0) return -EINVAL; @@ -591,7 +592,9 @@ static int smu8_init_uvd_limit(struct pp_hwmgr *hwmgr) data->uvd_dpm.soft_min_clk = 0; data->uvd_dpm.hard_min_clk = 0; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxUvdLevel, &level); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxUvdLevel, &level); + if (ret) + return ret; if (level < table->count) clock = table->entries[level].vclk; @@ -611,6 +614,7 @@ static int smu8_init_vce_limit(struct pp_hwmgr *hwmgr) hwmgr->dyn_state.vce_clock_voltage_dependency_table; unsigned long clock = 0; uint32_t level; + int ret; if (NULL == table || table->count <= 0) return -EINVAL; @@ -618,7 +622,9 @@ static int smu8_init_vce_limit(struct pp_hwmgr *hwmgr) data->vce_dpm.soft_min_clk = 0; data->vce_dpm.hard_min_clk = 0; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxEclkLevel, &level); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxEclkLevel, &level); + if (ret) + return ret; if (level < table->count) clock = table->entries[level].ecclk; @@ -638,6 +644,7 @@ static int smu8_init_acp_limit(struct pp_hwmgr *hwmgr) hwmgr->dyn_state.acp_clock_voltage_dependency_table; unsigned long clock = 0; uint32_t level; + int ret; if (NULL == table || table->count <= 0) return -EINVAL; @@ -645,7 +652,9 @@ static int smu8_init_acp_limit(struct pp_hwmgr *hwmgr) data->acp_dpm.soft_min_clk = 0; data->acp_dpm.hard_min_clk = 0; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxAclkLevel, &level); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxAclkLevel, &level); + if (ret) + return ret; if (level < table->count) clock = table->entries[level].acpclk; @@ -1065,16 +1074,18 @@ static int smu8_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, struct pp_power_state *prequest_ps, const struct pp_power_state *pcurrent_ps) { - struct smu8_power_state *smu8_ps = - cast_smu8_power_state(&prequest_ps->hardware); - - const struct smu8_power_state *smu8_current_ps = - cast_const_smu8_power_state(&pcurrent_ps->hardware); - + struct smu8_power_state *smu8_ps; + const struct smu8_power_state *smu8_current_ps; struct smu8_hwmgr *data = hwmgr->backend; struct PP_Clocks clocks = {0, 0, 0, 0}; bool force_high; + smu8_ps = cast_smu8_power_state(&prequest_ps->hardware); + smu8_current_ps = cast_const_smu8_power_state(&pcurrent_ps->hardware); + + if (!smu8_ps || !smu8_current_ps) + return -EINVAL; + smu8_ps->need_dfs_bypass = true; data->battery_state = (PP_StateUILabel_Battery == prequest_ps->classification.ui_label); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index 6d6bc6a380b365..6c87b3d4ab362f 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -354,13 +354,13 @@ static int vega10_odn_initial_default_setting(struct pp_hwmgr *hwmgr) return 0; } -static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr) +static int vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr) { struct vega10_hwmgr *data = hwmgr->backend; - int i; uint32_t sub_vendor_id, hw_revision; uint32_t top32, bottom32; struct amdgpu_device *adev = hwmgr->adev; + int ret, i; vega10_initialize_power_tune_defaults(hwmgr); @@ -485,9 +485,12 @@ static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr) if (data->registry_data.vr0hot_enabled) data->smu_features[GNLD_VR0HOT].supported = true; - smum_send_msg_to_smc(hwmgr, + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetSmuVersion, &hwmgr->smu_version); + if (ret) + return ret; + /* ACG firmware has major version 5 */ if ((hwmgr->smu_version & 0xff000000) == 0x5000000) data->smu_features[GNLD_ACG].supported = true; @@ -505,10 +508,16 @@ static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr) data->smu_features[GNLD_PCC_LIMIT].supported = true; /* Get the SN to turn into a Unique ID */ - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32); - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32); + if (ret) + return ret; + + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32); + if (ret) + return ret; adev->unique_id = ((uint64_t)bottom32 << 32) | top32; + return 0; } #ifdef PPLIB_VEGA10_EVV_SUPPORT @@ -882,7 +891,9 @@ static int vega10_hwmgr_backend_init(struct pp_hwmgr *hwmgr) vega10_set_features_platform_caps(hwmgr); - vega10_init_dpm_defaults(hwmgr); + result = vega10_init_dpm_defaults(hwmgr); + if (result) + return result; #ifdef PPLIB_VEGA10_EVV_SUPPORT /* Get leakage voltage based on leakage ID. */ @@ -2350,15 +2361,20 @@ static int vega10_acg_enable(struct pp_hwmgr *hwmgr) { struct vega10_hwmgr *data = hwmgr->backend; uint32_t agc_btc_response; + int ret; if (data->smu_features[GNLD_ACG].supported) { if (0 == vega10_enable_smc_features(hwmgr, true, data->smu_features[GNLD_DPM_PREFETCHER].smu_feature_bitmap)) data->smu_features[GNLD_DPM_PREFETCHER].enabled = true; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_InitializeAcg, NULL); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_InitializeAcg, NULL); + if (ret) + return ret; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_RunAcgBtc, &agc_btc_response); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_RunAcgBtc, &agc_btc_response); + if (ret) + agc_btc_response = 0; if (1 == agc_btc_response) { if (1 == data->acg_loop_state) @@ -2571,8 +2587,11 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr) } } - pp_atomfwctrl_get_voltage_table_v4(hwmgr, VOLTAGE_TYPE_VDDC, + result = pp_atomfwctrl_get_voltage_table_v4(hwmgr, VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2, &voltage_table); + PP_ASSERT_WITH_CODE(!result, + "Failed to get voltage table!", + return result); pp_table->MaxVidStep = voltage_table.max_vid_step; pp_table->GfxDpmVoltageMode = @@ -3259,8 +3278,7 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, const struct pp_power_state *current_ps) { struct amdgpu_device *adev = hwmgr->adev; - struct vega10_power_state *vega10_ps = - cast_phw_vega10_power_state(&request_ps->hardware); + struct vega10_power_state *vega10_ps; uint32_t sclk; uint32_t mclk; struct PP_Clocks minimum_clocks = {0}; @@ -3278,6 +3296,10 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, uint32_t stable_pstate_sclk = 0, stable_pstate_mclk = 0; uint32_t latency; + vega10_ps = cast_phw_vega10_power_state(&request_ps->hardware); + if (!vega10_ps) + return -EINVAL; + data->battery_state = (PP_StateUILabel_Battery == request_ps->classification.ui_label); @@ -3415,13 +3437,17 @@ static int vega10_find_dpm_states_clocks_in_dpm_table(struct pp_hwmgr *hwmgr, co const struct vega10_power_state *vega10_ps = cast_const_phw_vega10_power_state(states->pnew_state); struct vega10_single_dpm_table *sclk_table = &(data->dpm_table.gfx_table); - uint32_t sclk = vega10_ps->performance_levels - [vega10_ps->performance_level_count - 1].gfx_clock; struct vega10_single_dpm_table *mclk_table = &(data->dpm_table.mem_table); - uint32_t mclk = vega10_ps->performance_levels - [vega10_ps->performance_level_count - 1].mem_clock; + uint32_t sclk, mclk; uint32_t i; + if (vega10_ps == NULL) + return -EINVAL; + sclk = vega10_ps->performance_levels + [vega10_ps->performance_level_count - 1].gfx_clock; + mclk = vega10_ps->performance_levels + [vega10_ps->performance_level_count - 1].mem_clock; + for (i = 0; i < sclk_table->count; i++) { if (sclk == sclk_table->dpm_levels[i].value) break; @@ -3728,6 +3754,9 @@ static int vega10_generate_dpm_level_enable_mask( cast_const_phw_vega10_power_state(states->pnew_state); int i; + if (vega10_ps == NULL) + return -EINVAL; + PP_ASSERT_WITH_CODE(!vega10_trim_dpm_states(hwmgr, vega10_ps), "Attempt to Trim DPM States Failed!", return -1); @@ -3900,11 +3929,14 @@ static int vega10_get_gpu_power(struct pp_hwmgr *hwmgr, uint32_t *query) { uint32_t value; + int ret; if (!query) return -EINVAL; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrPkgPwr, &value); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrPkgPwr, &value); + if (ret) + return ret; /* SMC returning actual watts, keep consistent with legacy asics, low 8 bit as 8 fractional bits */ *query = value << 8; @@ -4800,14 +4832,16 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, uint32_t gen_speed, lane_width, current_gen_speed, current_lane_width; PPTable_t *pptable = &(data->smc_state_table.pp_table); - int i, now, size = 0, count = 0; + int i, ret, now, size = 0, count = 0; switch (type) { case PP_SCLK: if (data->registry_data.sclk_dpm_key_disabled) break; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentGfxclkIndex, &now); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentGfxclkIndex, &now); + if (ret) + break; if (hwmgr->pp_one_vf && (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)) @@ -4823,7 +4857,9 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, if (data->registry_data.mclk_dpm_key_disabled) break; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentUclkIndex, &now); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentUclkIndex, &now); + if (ret) + break; for (i = 0; i < mclk_table->count; i++) size += sprintf(buf + size, "%d: %uMhz %s\n", @@ -4834,7 +4870,9 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, if (data->registry_data.socclk_dpm_key_disabled) break; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentSocclkIndex, &now); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentSocclkIndex, &now); + if (ret) + break; for (i = 0; i < soc_table->count; i++) size += sprintf(buf + size, "%d: %uMhz %s\n", @@ -4845,8 +4883,10 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, if (data->registry_data.dcefclk_dpm_key_disabled) break; - smum_send_msg_to_smc_with_parameter(hwmgr, + ret = smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetClockFreqMHz, CLK_DCEFCLK, &now); + if (ret) + break; for (i = 0; i < dcef_table->count; i++) size += sprintf(buf + size, "%d: %uMhz %s\n", @@ -4995,6 +5035,8 @@ static int vega10_check_states_equal(struct pp_hwmgr *hwmgr, vega10_psa = cast_const_phw_vega10_power_state(pstate1); vega10_psb = cast_const_phw_vega10_power_state(pstate2); + if (vega10_psa == NULL || vega10_psb == NULL) + return -EINVAL; /* If the two states don't even have the same number of performance levels * they cannot be the same state. @@ -5128,6 +5170,8 @@ static int vega10_set_sclk_od(struct pp_hwmgr *hwmgr, uint32_t value) return -EINVAL; vega10_ps = cast_phw_vega10_power_state(&ps->hardware); + if (vega10_ps == NULL) + return -EINVAL; vega10_ps->performance_levels [vega10_ps->performance_level_count - 1].gfx_clock = @@ -5179,6 +5223,8 @@ static int vega10_set_mclk_od(struct pp_hwmgr *hwmgr, uint32_t value) return -EINVAL; vega10_ps = cast_phw_vega10_power_state(&ps->hardware); + if (vega10_ps == NULL) + return -EINVAL; vega10_ps->performance_levels [vega10_ps->performance_level_count - 1].mem_clock = @@ -5420,6 +5466,9 @@ static void vega10_odn_update_power_state(struct pp_hwmgr *hwmgr) return; vega10_ps = cast_phw_vega10_power_state(&ps->hardware); + if (vega10_ps == NULL) + return; + max_level = vega10_ps->performance_level_count - 1; if (vega10_ps->performance_levels[max_level].gfx_clock != @@ -5442,6 +5491,9 @@ static void vega10_odn_update_power_state(struct pp_hwmgr *hwmgr) ps = (struct pp_power_state *)((unsigned long)(hwmgr->ps) + hwmgr->ps_size * (hwmgr->num_ps - 1)); vega10_ps = cast_phw_vega10_power_state(&ps->hardware); + if (vega10_ps == NULL) + return; + max_level = vega10_ps->performance_level_count - 1; if (vega10_ps->performance_levels[max_level].gfx_clock != @@ -5632,6 +5684,8 @@ static int vega10_get_performance_level(struct pp_hwmgr *hwmgr, const struct pp_ return -EINVAL; vega10_ps = cast_const_phw_vega10_power_state(state); + if (vega10_ps == NULL) + return -EINVAL; i = index > vega10_ps->performance_level_count - 1 ? vega10_ps->performance_level_count - 1 : index; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c index 460067933de2ef..069c0f5205e004 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c @@ -293,12 +293,12 @@ static int vega12_set_features_platform_caps(struct pp_hwmgr *hwmgr) return 0; } -static void vega12_init_dpm_defaults(struct pp_hwmgr *hwmgr) +static int vega12_init_dpm_defaults(struct pp_hwmgr *hwmgr) { struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend); struct amdgpu_device *adev = hwmgr->adev; uint32_t top32, bottom32; - int i; + int i, ret; data->smu_features[GNLD_DPM_PREFETCHER].smu_feature_id = FEATURE_DPM_PREFETCHER_BIT; @@ -364,10 +364,16 @@ static void vega12_init_dpm_defaults(struct pp_hwmgr *hwmgr) } /* Get the SN to turn into a Unique ID */ - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32); - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32); + if (ret) + return ret; + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32); + if (ret) + return ret; adev->unique_id = ((uint64_t)bottom32 << 32) | top32; + + return 0; } static int vega12_set_private_data_based_on_pptable(struct pp_hwmgr *hwmgr) @@ -410,7 +416,11 @@ static int vega12_hwmgr_backend_init(struct pp_hwmgr *hwmgr) vega12_set_features_platform_caps(hwmgr); - vega12_init_dpm_defaults(hwmgr); + result = vega12_init_dpm_defaults(hwmgr); + if (result) { + pr_err("%s failed\n", __func__); + return result; + } /* Parse pptable data read from VBIOS */ vega12_set_private_data_based_on_pptable(hwmgr); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index 3b33af30eb0fbc..9fdb9990d18829 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -328,12 +328,12 @@ static int vega20_set_features_platform_caps(struct pp_hwmgr *hwmgr) return 0; } -static void vega20_init_dpm_defaults(struct pp_hwmgr *hwmgr) +static int vega20_init_dpm_defaults(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); struct amdgpu_device *adev = hwmgr->adev; uint32_t top32, bottom32; - int i; + int i, ret; data->smu_features[GNLD_DPM_PREFETCHER].smu_feature_id = FEATURE_DPM_PREFETCHER_BIT; @@ -404,10 +404,17 @@ static void vega20_init_dpm_defaults(struct pp_hwmgr *hwmgr) } /* Get the SN to turn into a Unique ID */ - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32); - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32); + if (ret) + return ret; + + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32); + if (ret) + return ret; adev->unique_id = ((uint64_t)bottom32 << 32) | top32; + + return 0; } static int vega20_set_private_data_based_on_pptable(struct pp_hwmgr *hwmgr) @@ -427,6 +434,7 @@ static int vega20_hwmgr_backend_init(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data; struct amdgpu_device *adev = hwmgr->adev; + int result; data = kzalloc(sizeof(struct vega20_hwmgr), GFP_KERNEL); if (data == NULL) @@ -452,8 +460,11 @@ static int vega20_hwmgr_backend_init(struct pp_hwmgr *hwmgr) vega20_set_features_platform_caps(hwmgr); - vega20_init_dpm_defaults(hwmgr); - + result = vega20_init_dpm_defaults(hwmgr); + if (result) { + pr_err("%s failed\n", __func__); + return result; + } /* Parse pptable data read from VBIOS */ vega20_set_private_data_based_on_pptable(hwmgr); @@ -4091,9 +4102,11 @@ static int vega20_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, ui if (power_profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) { struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); - if (size == 0 && !data->is_custom_profile_set) + + if (size != 10 && size != 0) return -EINVAL; - if (size < 10 && size != 0) + + if (size == 0 && !data->is_custom_profile_set) return -EINVAL; result = vega20_get_activity_monitor_coeff(hwmgr, @@ -4155,6 +4168,8 @@ static int vega20_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, ui activity_monitor.Fclk_PD_Data_error_coeff = input[8]; activity_monitor.Fclk_PD_Data_error_rate_coeff = input[9]; break; + default: + return -EINVAL; } result = vega20_set_activity_monitor_coeff(hwmgr, diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c index a70d7389664904..f9c0f117725dd1 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c @@ -130,13 +130,17 @@ int vega10_get_enabled_smc_features(struct pp_hwmgr *hwmgr, uint64_t *features_enabled) { uint32_t enabled_features; + int ret; if (features_enabled == NULL) return -EINVAL; - smum_send_msg_to_smc(hwmgr, + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetEnabledSmuFeatures, &enabled_features); + if (ret) + return ret; + *features_enabled = enabled_features; return 0; diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index f005a90c35af43..4d17b6958397ed 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -24,6 +24,7 @@ #include #include +#include #include #include "amdgpu.h" @@ -741,16 +742,8 @@ static int smu_late_init(void *handle) * handle the switch automatically. Driver involvement * is unnecessary. */ - if (!smu->dc_controlled_by_gpio) { - ret = smu_set_power_source(smu, - adev->pm.ac_power ? SMU_POWER_SOURCE_AC : - SMU_POWER_SOURCE_DC); - if (ret) { - dev_err(adev->dev, "Failed to switch to %s mode!\n", - adev->pm.ac_power ? "AC" : "DC"); - return ret; - } - } + adev->pm.ac_power = power_supply_is_system_supplied() > 0; + smu_set_ac_dc(smu); if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 1)) || (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 3))) @@ -1232,7 +1225,7 @@ static int smu_smc_hw_setup(struct smu_context *smu) { struct smu_feature *feature = &smu->smu_feature; struct amdgpu_device *adev = smu->adev; - uint32_t pcie_gen = 0, pcie_width = 0; + uint8_t pcie_gen = 0, pcie_width = 0; uint64_t features_supported; int ret = 0; @@ -1848,12 +1841,13 @@ static int smu_bump_power_profile_mode(struct smu_context *smu, } static int smu_adjust_power_state_dynamic(struct smu_context *smu, - enum amd_dpm_forced_level level, - bool skip_display_settings) + enum amd_dpm_forced_level level, + bool skip_display_settings, + bool init) { int ret = 0; int index = 0; - long workload; + long workload[1]; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); if (!skip_display_settings) { @@ -1893,10 +1887,10 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu, smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) { index = fls(smu->workload_mask); index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0; - workload = smu->workload_setting[index]; + workload[0] = smu->workload_setting[index]; - if (smu->power_profile_mode != workload) - smu_bump_power_profile_mode(smu, &workload, 0); + if (init || smu->power_profile_mode != workload[0]) + smu_bump_power_profile_mode(smu, workload, 0); } return ret; @@ -1916,11 +1910,13 @@ static int smu_handle_task(struct smu_context *smu, ret = smu_pre_display_config_changed(smu); if (ret) return ret; - ret = smu_adjust_power_state_dynamic(smu, level, false); + ret = smu_adjust_power_state_dynamic(smu, level, false, false); break; case AMD_PP_TASK_COMPLETE_INIT: + ret = smu_adjust_power_state_dynamic(smu, level, true, true); + break; case AMD_PP_TASK_READJUST_POWER_STATE: - ret = smu_adjust_power_state_dynamic(smu, level, true); + ret = smu_adjust_power_state_dynamic(smu, level, true, false); break; default: break; @@ -1946,7 +1942,7 @@ static int smu_switch_power_profile(void *handle, { struct smu_context *smu = handle; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); - long workload; + long workload[1]; uint32_t index; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) @@ -1959,17 +1955,17 @@ static int smu_switch_power_profile(void *handle, smu->workload_mask &= ~(1 << smu->workload_prority[type]); index = fls(smu->workload_mask); index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0; - workload = smu->workload_setting[index]; + workload[0] = smu->workload_setting[index]; } else { smu->workload_mask |= (1 << smu->workload_prority[type]); index = fls(smu->workload_mask); index = index <= WORKLOAD_POLICY_MAX ? index - 1 : 0; - workload = smu->workload_setting[index]; + workload[0] = smu->workload_setting[index]; } if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL && smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) - smu_bump_power_profile_mode(smu, &workload, 0); + smu_bump_power_profile_mode(smu, workload, 0); return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index 5a52098bcf1664..72ed836328966c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -844,7 +844,7 @@ struct pptable_funcs { * &pcie_gen_cap: Maximum allowed PCIe generation. * &pcie_width_cap: Maximum allowed PCIe width. */ - int (*update_pcie_parameters)(struct smu_context *smu, uint32_t pcie_gen_cap, uint32_t pcie_width_cap); + int (*update_pcie_parameters)(struct smu_context *smu, uint8_t pcie_gen_cap, uint8_t pcie_width_cap); /** * @i2c_init: Initialize i2c. diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index 355c156d871aff..cc02f979e9e984 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -296,8 +296,8 @@ int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu, uint32_t pptable_id); int smu_v13_0_update_pcie_parameters(struct smu_context *smu, - uint32_t pcie_gen_cap, - uint32_t pcie_width_cap); + uint8_t pcie_gen_cap, + uint8_t pcie_width_cap); #endif #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index 704a2b577a0e2f..4c58c2cd26d886 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -2356,8 +2356,8 @@ static uint16_t arcturus_get_current_pcie_link_speed(struct smu_context *smu) /* TODO: confirm this on real target */ esm_ctrl = RREG32_PCIE(smnPCIE_ESM_CTRL); - if ((esm_ctrl >> 15) & 0x1FFFF) - return (uint16_t)(((esm_ctrl >> 8) & 0x3F) + 128); + if ((esm_ctrl >> 15) & 0x1) + return (uint16_t)(((esm_ctrl >> 8) & 0x7F) + 128); return smu_v11_0_get_current_pcie_link_speed(smu); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 18487ae10bcff4..b1b23233635a64 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -1222,19 +1222,22 @@ static int navi10_get_current_clk_freq_by_table(struct smu_context *smu, value); } -static bool navi10_is_support_fine_grained_dpm(struct smu_context *smu, enum smu_clk_type clk_type) +static int navi10_is_support_fine_grained_dpm(struct smu_context *smu, enum smu_clk_type clk_type) { PPTable_t *pptable = smu->smu_table.driver_pptable; DpmDescriptor_t *dpm_desc = NULL; - uint32_t clk_index = 0; + int clk_index = 0; clk_index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_CLK, clk_type); + if (clk_index < 0) + return clk_index; + dpm_desc = &pptable->DpmDescriptor[clk_index]; /* 0 - Fine grained DPM, 1 - Discrete DPM */ - return dpm_desc->SnapToDiscrete == 0; + return dpm_desc->SnapToDiscrete == 0 ? 1 : 0; } static inline bool navi10_od_feature_is_supported(struct smu_11_0_overdrive_table *od_table, enum SMU_11_0_ODFEATURE_CAP cap) @@ -1290,7 +1293,11 @@ static int navi10_emit_clk_levels(struct smu_context *smu, if (ret) return ret; - if (!navi10_is_support_fine_grained_dpm(smu, clk_type)) { + ret = navi10_is_support_fine_grained_dpm(smu, clk_type); + if (ret < 0) + return ret; + + if (!ret) { for (i = 0; i < count; i++) { ret = smu_v11_0_get_dpm_freq_by_index(smu, clk_type, i, &value); @@ -1499,7 +1506,11 @@ static int navi10_print_clk_levels(struct smu_context *smu, if (ret) return size; - if (!navi10_is_support_fine_grained_dpm(smu, clk_type)) { + ret = navi10_is_support_fine_grained_dpm(smu, clk_type); + if (ret < 0) + return ret; + + if (!ret) { for (i = 0; i < count; i++) { ret = smu_v11_0_get_dpm_freq_by_index(smu, clk_type, i, &value); if (ret) @@ -1668,7 +1679,11 @@ static int navi10_force_clk_levels(struct smu_context *smu, case SMU_UCLK: case SMU_FCLK: /* There is only 2 levels for fine grained DPM */ - if (navi10_is_support_fine_grained_dpm(smu, clk_type)) { + ret = navi10_is_support_fine_grained_dpm(smu, clk_type); + if (ret < 0) + return ret; + + if (ret) { soft_max_level = (soft_max_level >= 1 ? 1 : 0); soft_min_level = (soft_min_level >= 1 ? 1 : 0); } @@ -2376,8 +2391,8 @@ static int navi10_get_power_limit(struct smu_context *smu, } static int navi10_update_pcie_parameters(struct smu_context *smu, - uint32_t pcie_gen_cap, - uint32_t pcie_width_cap) + uint8_t pcie_gen_cap, + uint8_t pcie_width_cap) { struct smu_11_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; PPTable_t *pptable = smu->smu_table.driver_pptable; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index da2860da60188e..a7f4f82d23b4b9 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -2085,14 +2085,14 @@ static int sienna_cichlid_display_disable_memory_clock_switch(struct smu_context #define MAX(a, b) ((a) > (b) ? (a) : (b)) static int sienna_cichlid_update_pcie_parameters(struct smu_context *smu, - uint32_t pcie_gen_cap, - uint32_t pcie_width_cap) + uint8_t pcie_gen_cap, + uint8_t pcie_width_cap) { struct smu_11_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; struct smu_11_0_pcie_table *pcie_table = &dpm_context->dpm_tables.pcie_table; uint8_t *table_member1, *table_member2; - uint32_t min_gen_speed, max_gen_speed; - uint32_t min_lane_width, max_lane_width; + uint8_t min_gen_speed, max_gen_speed; + uint8_t min_lane_width, max_lane_width; uint32_t smu_pcie_arg; int ret, i; @@ -2108,7 +2108,7 @@ static int sienna_cichlid_update_pcie_parameters(struct smu_context *smu, min_lane_width = min_lane_width > max_lane_width ? max_lane_width : min_lane_width; - if (!amdgpu_device_pcie_dynamic_switching_supported()) { + if (!(smu->adev->pm.pp_feature & PP_PCIE_DPM_MASK)) { pcie_table->pcie_gen[0] = max_gen_speed; pcie_table->pcie_lane[0] = max_lane_width; } else { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index aa4a5498a12f73..123c19bb622808 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -1441,10 +1441,12 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev, case 0x3: dev_dbg(adev->dev, "Switched to AC mode!\n"); schedule_work(&smu->interrupt_work); + adev->pm.ac_power = true; break; case 0x4: dev_dbg(adev->dev, "Switched to DC mode!\n"); schedule_work(&smu->interrupt_work); + adev->pm.ac_power = false; break; case 0x7: /* diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 201cec59984281..f46cda88948312 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -1009,6 +1009,18 @@ static int vangogh_get_dpm_ultimate_freq(struct smu_context *smu, } } if (min) { + ret = vangogh_get_profiling_clk_mask(smu, + AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK, + NULL, + NULL, + &mclk_mask, + &fclk_mask, + &soc_mask); + if (ret) + goto failed; + + vclk_mask = dclk_mask = 0; + switch (clk_type) { case SMU_UCLK: case SMU_MCLK: @@ -2481,6 +2493,8 @@ static u32 vangogh_set_gfxoff_residency(struct smu_context *smu, bool start) ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_LogGfxOffResidency, start, &residency); + if (ret) + return ret; if (!start) adev->gfx.gfx_off_residency = residency; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index cc3169400c9b08..ded8952d984907 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -257,8 +257,11 @@ static int aldebaran_tables_init(struct smu_context *smu) } smu_table->ecc_table = kzalloc(tables[SMU_TABLE_ECCINFO].size, GFP_KERNEL); - if (!smu_table->ecc_table) + if (!smu_table->ecc_table) { + kfree(smu_table->metrics_table); + kfree(smu_table->gpu_metrics_table); return -ENOMEM; + } return 0; } @@ -1717,8 +1720,8 @@ static int aldebaran_get_current_pcie_link_speed(struct smu_context *smu) /* TODO: confirm this on real target */ esm_ctrl = RREG32_PCIE(smnPCIE_ESM_CTRL); - if ((esm_ctrl >> 15) & 0x1FFFF) - return (((esm_ctrl >> 8) & 0x3F) + 128); + if ((esm_ctrl >> 15) & 0x1) + return (((esm_ctrl >> 8) & 0x7F) + 128); return smu_v13_0_get_current_pcie_link_speed(smu); } @@ -1928,7 +1931,8 @@ static int aldebaran_mode2_reset(struct smu_context *smu) index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_MSG, SMU_MSG_GfxDeviceDriverReset); - + if (index < 0 ) + return -EINVAL; mutex_lock(&smu->message_lock); if (smu_version >= 0x00441400) { ret = smu_cmn_send_msg_without_waiting(smu, (uint16_t)index, SMU_RESET_MODE_2); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 0232adb95df3a8..c0adfa46ac7896 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -79,8 +79,8 @@ MODULE_FIRMWARE("amdgpu/smu_13_0_10.bin"); #define PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK 0x00000070L #define PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT 0x4 #define smnPCIE_LC_SPEED_CNTL 0x11140290 -#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK 0xC000 -#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT 0xE +#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK 0xE0 +#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT 0x5 static const int link_width[] = {0, 1, 2, 4, 8, 12, 16}; @@ -1377,10 +1377,12 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev, case 0x3: dev_dbg(adev->dev, "Switched to AC mode!\n"); smu_v13_0_ack_ac_dc_interrupt(smu); + adev->pm.ac_power = true; break; case 0x4: dev_dbg(adev->dev, "Switched to DC mode!\n"); smu_v13_0_ack_ac_dc_interrupt(smu); + adev->pm.ac_power = false; break; case 0x7: /* @@ -2420,8 +2422,8 @@ int smu_v13_0_mode1_reset(struct smu_context *smu) } int smu_v13_0_update_pcie_parameters(struct smu_context *smu, - uint32_t pcie_gen_cap, - uint32_t pcie_width_cap) + uint8_t pcie_gen_cap, + uint8_t pcie_width_cap) { struct smu_13_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; struct smu_13_0_pcie_table *pcie_table = @@ -2430,7 +2432,10 @@ int smu_v13_0_update_pcie_parameters(struct smu_context *smu, uint32_t smu_pcie_arg; int ret, i; - if (!amdgpu_device_pcie_dynamic_switching_supported()) { + if (!num_of_levels) + return 0; + + if (!(smu->adev->pm.pp_feature & PP_PCIE_DPM_MASK)) { if (pcie_table->pcie_gen[num_of_levels - 1] < pcie_gen_cap) pcie_gen_cap = pcie_table->pcie_gen[num_of_levels - 1]; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 3903a47669e437..4022dd44ebb2b3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -352,12 +352,12 @@ static int smu_v13_0_0_check_powerplay_table(struct smu_context *smu) if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_HARDWAREDC) smu->dc_controlled_by_gpio = true; - if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_BACO || - powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_MACO) + if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_BACO) { smu_baco->platform_support = true; - if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_MACO) - smu_baco->maco_support = true; + if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_MACO) + smu_baco->maco_support = true; + } /* * We are in the transition to a new OD mechanism. @@ -2163,38 +2163,10 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu, } } - if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE && - (((smu->adev->pdev->device == 0x744C) && (smu->adev->pdev->revision == 0xC8)) || - ((smu->adev->pdev->device == 0x744C) && (smu->adev->pdev->revision == 0xCC)))) { - ret = smu_cmn_update_table(smu, - SMU_TABLE_ACTIVITY_MONITOR_COEFF, - WORKLOAD_PPLIB_COMPUTE_BIT, - (void *)(&activity_monitor_external), - false); - if (ret) { - dev_err(smu->adev->dev, "[%s] Failed to get activity monitor!", __func__); - return ret; - } - - ret = smu_cmn_update_table(smu, - SMU_TABLE_ACTIVITY_MONITOR_COEFF, - WORKLOAD_PPLIB_CUSTOM_BIT, - (void *)(&activity_monitor_external), - true); - if (ret) { - dev_err(smu->adev->dev, "[%s] Failed to set activity monitor!", __func__); - return ret; - } - - workload_type = smu_cmn_to_asic_specific_index(smu, - CMN2ASIC_MAPPING_WORKLOAD, - PP_SMC_POWER_PROFILE_CUSTOM); - } else { - /* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */ - workload_type = smu_cmn_to_asic_specific_index(smu, + /* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */ + workload_type = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_WORKLOAD, smu->power_profile_mode); - } if (workload_type < 0) return -EINVAL; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c index 626591f54bc497..1fd4702dc63936 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c @@ -226,8 +226,20 @@ static int smu_v13_0_4_system_features_control(struct smu_context *smu, bool en) struct amdgpu_device *adev = smu->adev; int ret = 0; - if (!en && !adev->in_s0ix) + if (!en && !adev->in_s0ix) { + if (adev->in_s4) { + /* Adds a GFX reset as workaround just before sending the + * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering + * an invalid state. + */ + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset, + SMU_RESET_MODE_2, NULL); + if (ret) + return ret; + } + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL); + } return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index de80e191a92c49..44c5f8585f1ee7 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -1941,8 +1941,8 @@ static int smu_v13_0_6_get_current_pcie_link_speed(struct smu_context *smu) /* TODO: confirm this on real target */ esm_ctrl = RREG32_PCIE(smnPCIE_ESM_CTRL); - if ((esm_ctrl >> 15) & 0x1FFFF) - return (((esm_ctrl >> 8) & 0x3F) + 128); + if ((esm_ctrl >> 15) & 0x1) + return (((esm_ctrl >> 8) & 0x7F) + 128); speed_level = (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) & PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK) @@ -1968,8 +1968,10 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table metrics = kzalloc(sizeof(MetricsTable_t), GFP_KERNEL); ret = smu_v13_0_6_get_metrics_table(smu, metrics, true); - if (ret) + if (ret) { + kfree(metrics); return ret; + } smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 3); @@ -2037,6 +2039,17 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table return sizeof(struct gpu_metrics_v1_3); } +static void smu_v13_0_6_restore_pci_config(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + int i; + + for (i = 0; i < 16; i++) + pci_write_config_dword(adev->pdev, i * 4, + adev->pdev->saved_config_space[i]); + pci_restore_msi_state(adev->pdev); +} + static int smu_v13_0_6_mode2_reset(struct smu_context *smu) { int ret = 0, index; @@ -2045,6 +2058,8 @@ static int smu_v13_0_6_mode2_reset(struct smu_context *smu) index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_MSG, SMU_MSG_GfxDeviceDriverReset); + if (index < 0) + return index; mutex_lock(&smu->message_lock); @@ -2058,6 +2073,20 @@ static int smu_v13_0_6_mode2_reset(struct smu_context *smu) /* Restore the config space saved during init */ amdgpu_device_load_pci_state(adev->pdev); + /* Certain platforms have switches which assign virtual BAR values to + * devices. OS uses the virtual BAR values and device behind the switch + * is assgined another BAR value. When device's config space registers + * are queried, switch returns the virtual BAR values. When mode-2 reset + * is performed, switch is unaware of it, and will continue to return + * the same virtual values to the OS.This affects + * pci_restore_config_space() API as it doesn't write the value saved if + * the current value read from config space is the same as what is + * saved. As a workaround, make sure the config space is restored + * always. + */ + if (!(adev->flags & AMD_IS_APU)) + smu_v13_0_6_restore_pci_config(smu); + dev_dbg(smu->adev->dev, "wait for reset ack\n"); do { ret = smu_cmn_wait_for_response(smu); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 94ef5b4d116d7c..51ae41cb43ea0e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -341,12 +341,13 @@ static int smu_v13_0_7_check_powerplay_table(struct smu_context *smu) if (powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_HARDWAREDC) smu->dc_controlled_by_gpio = true; - if (powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_BACO || - powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_MACO) + if (powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_BACO) { smu_baco->platform_support = true; - if (smu_baco->platform_support && (BoardTable->HsrEnabled || BoardTable->VddqOffEnabled)) - smu_baco->maco_support = true; + if ((powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_MACO) + && (BoardTable->HsrEnabled || BoardTable->VddqOffEnabled)) + smu_baco->maco_support = true; + } #if 0 if (!overdrive_lowerlimits->FeatureCtrlMask || diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c index 2c661f28410eda..b645c5998230b0 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c @@ -5,6 +5,7 @@ * */ #include +#include #include #include @@ -610,12 +611,34 @@ get_crtc_primary(struct komeda_kms_dev *kms, struct komeda_crtc *crtc) return NULL; } +static int komeda_attach_bridge(struct device *dev, + struct komeda_pipeline *pipe, + struct drm_encoder *encoder) +{ + struct drm_bridge *bridge; + int err; + + bridge = devm_drm_of_get_bridge(dev, pipe->of_node, + KOMEDA_OF_PORT_OUTPUT, 0); + if (IS_ERR(bridge)) + return dev_err_probe(dev, PTR_ERR(bridge), "remote bridge not found for pipe: %s\n", + of_node_full_name(pipe->of_node)); + + err = drm_bridge_attach(encoder, bridge, NULL, 0); + if (err) + dev_err(dev, "bridge_attach() failed for pipe: %s\n", + of_node_full_name(pipe->of_node)); + + return err; +} + static int komeda_crtc_add(struct komeda_kms_dev *kms, struct komeda_crtc *kcrtc) { struct drm_crtc *crtc = &kcrtc->base; struct drm_device *base = &kms->base; - struct drm_bridge *bridge; + struct komeda_pipeline *pipe = kcrtc->master; + struct drm_encoder *encoder = &kcrtc->encoder; int err; err = drm_crtc_init_with_planes(base, crtc, @@ -626,27 +649,25 @@ static int komeda_crtc_add(struct komeda_kms_dev *kms, drm_crtc_helper_add(crtc, &komeda_crtc_helper_funcs); - crtc->port = kcrtc->master->of_output_port; + crtc->port = pipe->of_output_port; /* Construct an encoder for each pipeline and attach it to the remote * bridge */ kcrtc->encoder.possible_crtcs = drm_crtc_mask(crtc); - err = drm_simple_encoder_init(base, &kcrtc->encoder, - DRM_MODE_ENCODER_TMDS); + err = drm_simple_encoder_init(base, encoder, DRM_MODE_ENCODER_TMDS); if (err) return err; - bridge = devm_drm_of_get_bridge(base->dev, kcrtc->master->of_node, - KOMEDA_OF_PORT_OUTPUT, 0); - if (IS_ERR(bridge)) - return PTR_ERR(bridge); - - err = drm_bridge_attach(&kcrtc->encoder, bridge, NULL, 0); + if (pipe->of_output_links[0]) { + err = komeda_attach_bridge(base->dev, pipe, encoder); + if (err) + return err; + } drm_crtc_enable_color_mgmt(crtc, 0, true, KOMEDA_COLOR_LUT_SIZE); - return err; + return 0; } int komeda_kms_add_crtcs(struct komeda_kms_dev *kms, struct komeda_dev *mdev) diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c index 9299026701f348..1a5fa7df284dec 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c @@ -160,6 +160,7 @@ static int komeda_crtc_normalize_zpos(struct drm_crtc *crtc, struct drm_plane *plane; struct list_head zorder_list; int order = 0, err; + u32 slave_zpos = 0; DRM_DEBUG_ATOMIC("[CRTC:%d:%s] calculating normalized zpos values\n", crtc->base.id, crtc->name); @@ -199,10 +200,13 @@ static int komeda_crtc_normalize_zpos(struct drm_crtc *crtc, plane_st->zpos, plane_st->normalized_zpos); /* calculate max slave zorder */ - if (has_bit(drm_plane_index(plane), kcrtc->slave_planes)) + if (has_bit(drm_plane_index(plane), kcrtc->slave_planes)) { + slave_zpos = plane_st->normalized_zpos; + if (to_kplane_st(plane_st)->layer_split) + slave_zpos++; kcrtc_st->max_slave_zorder = - max(plane_st->normalized_zpos, - kcrtc_st->max_slave_zorder); + max(slave_zpos, kcrtc_st->max_slave_zorder); + } } crtc_st->zpos_changed = true; diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c index 4618687a8f4d64..f4e76b46ca327a 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c @@ -259,7 +259,7 @@ komeda_component_get_avail_scaler(struct komeda_component *c, u32 avail_scalers; pipe_st = komeda_pipeline_get_state(c->pipeline, state); - if (!pipe_st) + if (IS_ERR_OR_NULL(pipe_st)) return NULL; avail_scalers = (pipe_st->active_comps & KOMEDA_PIPELINE_SCALERS) ^ @@ -1223,7 +1223,7 @@ int komeda_build_display_data_flow(struct komeda_crtc *kcrtc, return 0; } -static void +static int komeda_pipeline_unbound_components(struct komeda_pipeline *pipe, struct komeda_pipeline_state *new) { @@ -1243,8 +1243,12 @@ komeda_pipeline_unbound_components(struct komeda_pipeline *pipe, c = komeda_pipeline_get_component(pipe, id); c_st = komeda_component_get_state_and_set_user(c, drm_st, NULL, new->crtc); + if (PTR_ERR(c_st) == -EDEADLK) + return -EDEADLK; WARN_ON(IS_ERR(c_st)); } + + return 0; } /* release unclaimed pipeline resource */ @@ -1266,9 +1270,8 @@ int komeda_release_unclaimed_resources(struct komeda_pipeline *pipe, if (WARN_ON(IS_ERR_OR_NULL(st))) return -EINVAL; - komeda_pipeline_unbound_components(pipe, st); + return komeda_pipeline_unbound_components(pipe, st); - return 0; } /* Since standalone disabled components must be disabled separately and in the diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c index 626709bec6f5ff..2577f0cef8fcda 100644 --- a/drivers/gpu/drm/arm/malidp_mw.c +++ b/drivers/gpu/drm/arm/malidp_mw.c @@ -72,7 +72,10 @@ static void malidp_mw_connector_reset(struct drm_connector *connector) __drm_atomic_helper_connector_destroy_state(connector->state); kfree(connector->state); - __drm_atomic_helper_connector_reset(connector, &mw_state->base); + connector->state = NULL; + + if (mw_state) + __drm_atomic_helper_connector_reset(connector, &mw_state->base); } static enum drm_connector_status diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c index d207b03f8357c7..78122b35a0cbb3 100644 --- a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c +++ b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c @@ -358,11 +358,18 @@ static void aspeed_gfx_remove(struct platform_device *pdev) sysfs_remove_group(&pdev->dev.kobj, &aspeed_sysfs_attr_group); drm_dev_unregister(drm); aspeed_gfx_unload(drm); + drm_atomic_helper_shutdown(drm); +} + +static void aspeed_gfx_shutdown(struct platform_device *pdev) +{ + drm_atomic_helper_shutdown(platform_get_drvdata(pdev)); } static struct platform_driver aspeed_gfx_platform_driver = { .probe = aspeed_gfx_probe, .remove_new = aspeed_gfx_remove, + .shutdown = aspeed_gfx_shutdown, .driver = { .name = "aspeed_gfx", .of_match_table = aspeed_gfx_match, diff --git a/drivers/gpu/drm/ast/ast_dp.c b/drivers/gpu/drm/ast/ast_dp.c index fdd9a493aa9c08..c6f226b6f08136 100644 --- a/drivers/gpu/drm/ast/ast_dp.c +++ b/drivers/gpu/drm/ast/ast_dp.c @@ -180,6 +180,7 @@ void ast_dp_set_on_off(struct drm_device *dev, bool on) { struct ast_device *ast = to_ast_device(dev); u8 video_on_off = on; + u32 i = 0; // Video On/Off ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xE3, (u8) ~AST_DP_VIDEO_ENABLE, on); @@ -192,6 +193,8 @@ void ast_dp_set_on_off(struct drm_device *dev, bool on) ASTDP_MIRROR_VIDEO_ENABLE) != video_on_off) { // wait 1 ms mdelay(1); + if (++i > 200) + break; } } } diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h index 848a9f1403e896..f7053f2972bb92 100644 --- a/drivers/gpu/drm/ast/ast_drv.h +++ b/drivers/gpu/drm/ast/ast_drv.h @@ -172,6 +172,17 @@ to_ast_sil164_connector(struct drm_connector *connector) return container_of(connector, struct ast_sil164_connector, base); } +struct ast_bmc_connector { + struct drm_connector base; + struct drm_connector *physical_connector; +}; + +static inline struct ast_bmc_connector * +to_ast_bmc_connector(struct drm_connector *connector) +{ + return container_of(connector, struct ast_bmc_connector, base); +} + /* * Device */ @@ -216,7 +227,7 @@ struct ast_device { } astdp; struct { struct drm_encoder encoder; - struct drm_connector connector; + struct ast_bmc_connector bmc_connector; } bmc; } output; diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 32f04ec6c386fa..3de0f457fff6ab 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -1767,6 +1767,30 @@ static const struct drm_encoder_funcs ast_bmc_encoder_funcs = { .destroy = drm_encoder_cleanup, }; +static int ast_bmc_connector_helper_detect_ctx(struct drm_connector *connector, + struct drm_modeset_acquire_ctx *ctx, + bool force) +{ + struct ast_bmc_connector *bmc_connector = to_ast_bmc_connector(connector); + struct drm_connector *physical_connector = bmc_connector->physical_connector; + + /* + * Most user-space compositors cannot handle more than one connected + * connector per CRTC. Hence, we only mark the BMC as connected if the + * physical connector is disconnected. If the physical connector's status + * is connected or unknown, the BMC remains disconnected. This has no + * effect on the output of the BMC. + * + * FIXME: Remove this logic once user-space compositors can handle more + * than one connector per CRTC. The BMC should always be connected. + */ + + if (physical_connector && physical_connector->status == connector_status_disconnected) + return connector_status_connected; + + return connector_status_disconnected; +} + static int ast_bmc_connector_helper_get_modes(struct drm_connector *connector) { return drm_add_modes_noedid(connector, 4096, 4096); @@ -1774,6 +1798,7 @@ static int ast_bmc_connector_helper_get_modes(struct drm_connector *connector) static const struct drm_connector_helper_funcs ast_bmc_connector_helper_funcs = { .get_modes = ast_bmc_connector_helper_get_modes, + .detect_ctx = ast_bmc_connector_helper_detect_ctx, }; static const struct drm_connector_funcs ast_bmc_connector_funcs = { @@ -1784,12 +1809,33 @@ static const struct drm_connector_funcs ast_bmc_connector_funcs = { .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; -static int ast_bmc_output_init(struct ast_device *ast) +static int ast_bmc_connector_init(struct drm_device *dev, + struct ast_bmc_connector *bmc_connector, + struct drm_connector *physical_connector) +{ + struct drm_connector *connector = &bmc_connector->base; + int ret; + + ret = drm_connector_init(dev, connector, &ast_bmc_connector_funcs, + DRM_MODE_CONNECTOR_VIRTUAL); + if (ret) + return ret; + + drm_connector_helper_add(connector, &ast_bmc_connector_helper_funcs); + + bmc_connector->physical_connector = physical_connector; + + return 0; +} + +static int ast_bmc_output_init(struct ast_device *ast, + struct drm_connector *physical_connector) { struct drm_device *dev = &ast->base; struct drm_crtc *crtc = &ast->crtc; struct drm_encoder *encoder = &ast->output.bmc.encoder; - struct drm_connector *connector = &ast->output.bmc.connector; + struct ast_bmc_connector *bmc_connector = &ast->output.bmc.bmc_connector; + struct drm_connector *connector = &bmc_connector->base; int ret; ret = drm_encoder_init(dev, encoder, @@ -1799,13 +1845,10 @@ static int ast_bmc_output_init(struct ast_device *ast) return ret; encoder->possible_crtcs = drm_crtc_mask(crtc); - ret = drm_connector_init(dev, connector, &ast_bmc_connector_funcs, - DRM_MODE_CONNECTOR_VIRTUAL); + ret = ast_bmc_connector_init(dev, bmc_connector, physical_connector); if (ret) return ret; - drm_connector_helper_add(connector, &ast_bmc_connector_helper_funcs); - ret = drm_connector_attach_encoder(connector, encoder); if (ret) return ret; @@ -1864,6 +1907,7 @@ static const struct drm_mode_config_funcs ast_mode_config_funcs = { int ast_mode_config_init(struct ast_device *ast) { struct drm_device *dev = &ast->base; + struct drm_connector *physical_connector = NULL; int ret; ret = drmm_mode_config_init(dev); @@ -1904,23 +1948,27 @@ int ast_mode_config_init(struct ast_device *ast) ret = ast_vga_output_init(ast); if (ret) return ret; + physical_connector = &ast->output.vga.vga_connector.base; } if (ast->tx_chip_types & AST_TX_SIL164_BIT) { ret = ast_sil164_output_init(ast); if (ret) return ret; + physical_connector = &ast->output.sil164.sil164_connector.base; } if (ast->tx_chip_types & AST_TX_DP501_BIT) { ret = ast_dp501_output_init(ast); if (ret) return ret; + physical_connector = &ast->output.dp501.connector; } if (ast->tx_chip_types & AST_TX_ASTDP_BIT) { ret = ast_astdp_output_init(ast); if (ret) return ret; + physical_connector = &ast->output.astdp.connector; } - ret = ast_bmc_output_init(ast); + ret = ast_bmc_output_init(ast, physical_connector); if (ret) return ret; diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index 44a660a4bdbfc4..3e6a4e2044c0eb 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -181,6 +181,7 @@ config DRM_NWL_MIPI_DSI select DRM_KMS_HELPER select DRM_MIPI_DSI select DRM_PANEL_BRIDGE + select GENERIC_PHY select GENERIC_PHY_MIPI_DPHY select MFD_SYSCON select MULTIPLEXER @@ -227,6 +228,7 @@ config DRM_SAMSUNG_DSIM select DRM_KMS_HELPER select DRM_MIPI_DSI select DRM_PANEL_BRIDGE + select GENERIC_PHY select GENERIC_PHY_MIPI_DPHY help The Samsung MIPI DSIM bridge controller driver. @@ -311,6 +313,7 @@ config DRM_TOSHIBA_TC358768 select REGMAP_I2C select DRM_PANEL select DRM_MIPI_DSI + select VIDEOMODE_HELPERS help Toshiba TC358768AXBG/TC358778XBG DSI bridge chip driver. diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 2611afd2c1c136..ef2b6ce544d0a8 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -1291,17 +1291,6 @@ static int adv7511_probe(struct i2c_client *i2c) INIT_WORK(&adv7511->hpd_work, adv7511_hpd_work); - if (i2c->irq) { - init_waitqueue_head(&adv7511->wq); - - ret = devm_request_threaded_irq(dev, i2c->irq, NULL, - adv7511_irq_handler, - IRQF_ONESHOT, dev_name(dev), - adv7511); - if (ret) - goto err_unregister_cec; - } - adv7511_power_off(adv7511); i2c_set_clientdata(i2c, adv7511); @@ -1325,6 +1314,17 @@ static int adv7511_probe(struct i2c_client *i2c) adv7511_audio_init(dev, adv7511); + if (i2c->irq) { + init_waitqueue_head(&adv7511->wq); + + ret = devm_request_threaded_irq(dev, i2c->irq, NULL, + adv7511_irq_handler, + IRQF_ONESHOT, dev_name(dev), + adv7511); + if (ret) + goto err_unregister_audio; + } + if (adv7511->type == ADV7533 || adv7511->type == ADV7535) { ret = adv7533_attach_dsi(adv7511); if (ret) diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c index 6a4f20fccf8417..7b0bc9704eacb1 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c @@ -1027,7 +1027,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, u32 status_reg; u8 *buffer = msg->buffer; unsigned int i; - int num_transferred = 0; int ret; /* Buffer size of AUX CH is 16 bytes */ @@ -1079,7 +1078,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, reg = buffer[i]; writel(reg, dp->reg_base + ANALOGIX_DP_BUF_DATA_0 + 4 * i); - num_transferred++; } } @@ -1127,7 +1125,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, reg = readl(dp->reg_base + ANALOGIX_DP_BUF_DATA_0 + 4 * i); buffer[i] = (unsigned char)reg; - num_transferred++; } } @@ -1144,7 +1141,7 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, (msg->request & ~DP_AUX_I2C_MOT) == DP_AUX_NATIVE_READ) msg->reply = DP_AUX_NATIVE_REPLY_ACK; - return num_transferred > 0 ? num_transferred : -EBUSY; + return msg->size; aux_error: /* if aux err happen, reset aux */ diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c index 51abe42c639e54..c1191ef5e8e679 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.c +++ b/drivers/gpu/drm/bridge/analogix/anx7625.c @@ -1298,10 +1298,32 @@ static void anx7625_config(struct anx7625_data *ctx) XTAL_FRQ_SEL, XTAL_FRQ_27M); } +static int anx7625_hpd_timer_config(struct anx7625_data *ctx) +{ + int ret; + + /* Set irq detect window to 2ms */ + ret = anx7625_reg_write(ctx, ctx->i2c.tx_p2_client, + HPD_DET_TIMER_BIT0_7, HPD_TIME & 0xFF); + ret |= anx7625_reg_write(ctx, ctx->i2c.tx_p2_client, + HPD_DET_TIMER_BIT8_15, + (HPD_TIME >> 8) & 0xFF); + ret |= anx7625_reg_write(ctx, ctx->i2c.tx_p2_client, + HPD_DET_TIMER_BIT16_23, + (HPD_TIME >> 16) & 0xFF); + + return ret; +} + +static int anx7625_read_hpd_gpio_config_status(struct anx7625_data *ctx) +{ + return anx7625_reg_read(ctx, ctx->i2c.rx_p0_client, GPIO_CTRL_2); +} + static void anx7625_disable_pd_protocol(struct anx7625_data *ctx) { struct device *dev = ctx->dev; - int ret; + int ret, val; /* Reset main ocm */ ret = anx7625_reg_write(ctx, ctx->i2c.rx_p0_client, 0x88, 0x40); @@ -1315,6 +1337,19 @@ static void anx7625_disable_pd_protocol(struct anx7625_data *ctx) DRM_DEV_DEBUG_DRIVER(dev, "disable PD feature fail.\n"); else DRM_DEV_DEBUG_DRIVER(dev, "disable PD feature succeeded.\n"); + + /* + * Make sure the HPD GPIO already be configured after OCM release before + * setting HPD detect window register. Here we poll the status register + * at maximum 40ms, then config HPD irq detect window register + */ + readx_poll_timeout(anx7625_read_hpd_gpio_config_status, + ctx, val, + ((val & HPD_SOURCE) || (val < 0)), + 2000, 2000 * 20); + + /* Set HPD irq detect window to 2ms */ + anx7625_hpd_timer_config(ctx); } static int anx7625_ocm_loading_check(struct anx7625_data *ctx) @@ -1437,20 +1472,6 @@ static void anx7625_start_dp_work(struct anx7625_data *ctx) static int anx7625_read_hpd_status_p0(struct anx7625_data *ctx) { - int ret; - - /* Set irq detect window to 2ms */ - ret = anx7625_reg_write(ctx, ctx->i2c.tx_p2_client, - HPD_DET_TIMER_BIT0_7, HPD_TIME & 0xFF); - ret |= anx7625_reg_write(ctx, ctx->i2c.tx_p2_client, - HPD_DET_TIMER_BIT8_15, - (HPD_TIME >> 8) & 0xFF); - ret |= anx7625_reg_write(ctx, ctx->i2c.tx_p2_client, - HPD_DET_TIMER_BIT16_23, - (HPD_TIME >> 16) & 0xFF); - if (ret < 0) - return ret; - return anx7625_reg_read(ctx, ctx->i2c.rx_p0_client, SYSTEM_STSTUS); } @@ -1741,6 +1762,7 @@ static ssize_t anx7625_aux_transfer(struct drm_dp_aux *aux, u8 request = msg->request & ~DP_AUX_I2C_MOT; int ret = 0; + mutex_lock(&ctx->aux_lock); pm_runtime_get_sync(dev); msg->reply = 0; switch (request) { @@ -1757,6 +1779,7 @@ static ssize_t anx7625_aux_transfer(struct drm_dp_aux *aux, msg->size, msg->buffer); pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); + mutex_unlock(&ctx->aux_lock); return ret; } @@ -2053,10 +2076,8 @@ static int anx7625_setup_dsi_device(struct anx7625_data *ctx) }; host = of_find_mipi_dsi_host_by_node(ctx->pdata.mipi_host_node); - if (!host) { - DRM_DEV_ERROR(dev, "fail to find dsi host.\n"); - return -EPROBE_DEFER; - } + if (!host) + return dev_err_probe(dev, -EPROBE_DEFER, "fail to find dsi host.\n"); dsi = devm_mipi_dsi_device_register_full(dev, host, &info); if (IS_ERR(dsi)) { @@ -2453,18 +2474,27 @@ static void anx7625_bridge_atomic_disable(struct drm_bridge *bridge, ctx->connector = NULL; anx7625_dp_stop(ctx); - pm_runtime_put_sync(dev); + mutex_lock(&ctx->aux_lock); + pm_runtime_put_sync_suspend(dev); + mutex_unlock(&ctx->aux_lock); } +static void +anx7625_audio_update_connector_status(struct anx7625_data *ctx, + enum drm_connector_status status); + static enum drm_connector_status anx7625_bridge_detect(struct drm_bridge *bridge) { struct anx7625_data *ctx = bridge_to_anx7625(bridge); struct device *dev = ctx->dev; + enum drm_connector_status status; DRM_DEV_DEBUG_DRIVER(dev, "drm bridge detect\n"); - return anx7625_sink_detect(ctx); + status = anx7625_sink_detect(ctx); + anx7625_audio_update_connector_status(ctx, status); + return status; } static struct edid *anx7625_bridge_get_edid(struct drm_bridge *bridge, @@ -2647,6 +2677,7 @@ static int anx7625_i2c_probe(struct i2c_client *client) mutex_init(&platform->lock); mutex_init(&platform->hdcp_wq_lock); + mutex_init(&platform->aux_lock); INIT_DELAYED_WORK(&platform->hdcp_work, hdcp_check_work_func); platform->hdcp_workqueue = create_workqueue("hdcp workqueue"); diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.h b/drivers/gpu/drm/bridge/analogix/anx7625.h index 5af819611ebce8..39ed35d3383633 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.h +++ b/drivers/gpu/drm/bridge/analogix/anx7625.h @@ -259,6 +259,10 @@ #define AP_MIPI_RX_EN BIT(5) /* 1: MIPI RX input in 0: no RX in */ #define AP_DISABLE_PD BIT(6) #define AP_DISABLE_DISPLAY BIT(7) + +#define GPIO_CTRL_2 0x49 +#define HPD_SOURCE BIT(6) + /***************************************************************/ /* Register definition of device address 0x84 */ #define MIPI_PHY_CONTROL_3 0x03 @@ -471,6 +475,8 @@ struct anx7625_data { struct workqueue_struct *hdcp_workqueue; /* Lock for hdcp work queue */ struct mutex hdcp_wq_lock; + /* Lock for aux transfer and disable */ + struct mutex aux_lock; char edid_block; struct display_timing dt; u8 display_timing_valid; diff --git a/drivers/gpu/drm/bridge/cadence/Kconfig b/drivers/gpu/drm/bridge/cadence/Kconfig index ec35215a20034c..cced81633ddcda 100644 --- a/drivers/gpu/drm/bridge/cadence/Kconfig +++ b/drivers/gpu/drm/bridge/cadence/Kconfig @@ -4,6 +4,7 @@ config DRM_CDNS_DSI select DRM_KMS_HELPER select DRM_MIPI_DSI select DRM_PANEL_BRIDGE + select GENERIC_PHY select GENERIC_PHY_MIPI_DPHY depends on OF help diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c index 6af565ac307ae3..858f5b6508491f 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c @@ -2057,6 +2057,9 @@ static void cdns_mhdp_atomic_enable(struct drm_bridge *bridge, mhdp_state = to_cdns_mhdp_bridge_state(new_state); mhdp_state->current_mode = drm_mode_duplicate(bridge->dev, mode); + if (!mhdp_state->current_mode) + return; + drm_mode_set_name(mhdp_state->current_mode); dev_dbg(mhdp->dev, "%s: Enabling mode %s\n", __func__, mode->name); diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c index 946212a9559814..5e3b8edcf79487 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c @@ -403,7 +403,8 @@ static int _cdns_mhdp_hdcp_disable(struct cdns_mhdp_device *mhdp) static int _cdns_mhdp_hdcp_enable(struct cdns_mhdp_device *mhdp, u8 content_type) { - int ret, tries = 3; + int ret = -EINVAL; + int tries = 3; u32 i; for (i = 0; i < tries; i++) { diff --git a/drivers/gpu/drm/bridge/chipone-icn6211.c b/drivers/gpu/drm/bridge/chipone-icn6211.c index d205e755e524ae..5e295f86f2a73f 100644 --- a/drivers/gpu/drm/bridge/chipone-icn6211.c +++ b/drivers/gpu/drm/bridge/chipone-icn6211.c @@ -563,10 +563,8 @@ static int chipone_dsi_host_attach(struct chipone *icn) host = of_find_mipi_dsi_host_by_node(host_node); of_node_put(host_node); - if (!host) { - dev_err(dev, "failed to find dsi host\n"); - return -EPROBE_DEFER; - } + if (!host) + return dev_err_probe(dev, -EPROBE_DEFER, "failed to find dsi host\n"); dsi = mipi_dsi_device_register_full(host, &info); if (IS_ERR(dsi)) { diff --git a/drivers/gpu/drm/bridge/ite-it6505.c b/drivers/gpu/drm/bridge/ite-it6505.c index 2f300f5ca051cc..4ad527fe04f27e 100644 --- a/drivers/gpu/drm/bridge/ite-it6505.c +++ b/drivers/gpu/drm/bridge/ite-it6505.c @@ -1306,9 +1306,15 @@ static void it6505_video_reset(struct it6505 *it6505) it6505_link_reset_step_train(it6505); it6505_set_bits(it6505, REG_DATA_MUTE_CTRL, EN_VID_MUTE, EN_VID_MUTE); it6505_set_bits(it6505, REG_INFOFRAME_CTRL, EN_VID_CTRL_PKT, 0x00); - it6505_set_bits(it6505, REG_RESET_CTRL, VIDEO_RESET, VIDEO_RESET); + + it6505_set_bits(it6505, REG_VID_BUS_CTRL1, TX_FIFO_RESET, TX_FIFO_RESET); + it6505_set_bits(it6505, REG_VID_BUS_CTRL1, TX_FIFO_RESET, 0x00); + it6505_set_bits(it6505, REG_501_FIFO_CTRL, RST_501_FIFO, RST_501_FIFO); it6505_set_bits(it6505, REG_501_FIFO_CTRL, RST_501_FIFO, 0x00); + + it6505_set_bits(it6505, REG_RESET_CTRL, VIDEO_RESET, VIDEO_RESET); + usleep_range(1000, 2000); it6505_set_bits(it6505, REG_RESET_CTRL, VIDEO_RESET, 0x00); } @@ -2240,14 +2246,15 @@ static void it6505_link_training_work(struct work_struct *work) ret = it6505_link_start_auto_train(it6505); DRM_DEV_DEBUG_DRIVER(dev, "auto train %s, auto_train_retry: %d", ret ? "pass" : "failed", it6505->auto_train_retry); - it6505->auto_train_retry--; if (ret) { + it6505->auto_train_retry = AUTO_TRAIN_RETRY; it6505_link_train_ok(it6505); - return; + } else { + it6505->auto_train_retry--; + it6505_dump(it6505); } - it6505_dump(it6505); } static void it6505_plugged_status_to_codec(struct it6505 *it6505) @@ -2468,31 +2475,53 @@ static void it6505_irq_link_train_fail(struct it6505 *it6505) schedule_work(&it6505->link_works); } -static void it6505_irq_video_fifo_error(struct it6505 *it6505) +static bool it6505_test_bit(unsigned int bit, const unsigned int *addr) { - struct device *dev = it6505->dev; - - DRM_DEV_DEBUG_DRIVER(dev, "video fifo overflow interrupt"); - it6505->auto_train_retry = AUTO_TRAIN_RETRY; - flush_work(&it6505->link_works); - it6505_stop_hdcp(it6505); - it6505_video_reset(it6505); + return 1 & (addr[bit / BITS_PER_BYTE] >> (bit % BITS_PER_BYTE)); } -static void it6505_irq_io_latch_fifo_overflow(struct it6505 *it6505) +static void it6505_irq_video_handler(struct it6505 *it6505, const int *int_status) { struct device *dev = it6505->dev; + int reg_0d, reg_int03; - DRM_DEV_DEBUG_DRIVER(dev, "IO latch fifo overflow interrupt"); - it6505->auto_train_retry = AUTO_TRAIN_RETRY; - flush_work(&it6505->link_works); - it6505_stop_hdcp(it6505); - it6505_video_reset(it6505); -} + /* + * When video SCDT change with video not stable, + * Or video FIFO error, need video reset + */ -static bool it6505_test_bit(unsigned int bit, const unsigned int *addr) -{ - return 1 & (addr[bit / BITS_PER_BYTE] >> (bit % BITS_PER_BYTE)); + if ((!it6505_get_video_status(it6505) && + (it6505_test_bit(INT_SCDT_CHANGE, (unsigned int *)int_status))) || + (it6505_test_bit(BIT_INT_IO_FIFO_OVERFLOW, + (unsigned int *)int_status)) || + (it6505_test_bit(BIT_INT_VID_FIFO_ERROR, + (unsigned int *)int_status))) { + it6505->auto_train_retry = AUTO_TRAIN_RETRY; + flush_work(&it6505->link_works); + it6505_stop_hdcp(it6505); + it6505_video_reset(it6505); + + usleep_range(10000, 11000); + + /* + * Clear FIFO error IRQ to prevent fifo error -> reset loop + * HW will trigger SCDT change IRQ again when video stable + */ + + reg_int03 = it6505_read(it6505, INT_STATUS_03); + reg_0d = it6505_read(it6505, REG_SYSTEM_STS); + + reg_int03 &= (BIT(INT_VID_FIFO_ERROR) | BIT(INT_IO_LATCH_FIFO_OVERFLOW)); + it6505_write(it6505, INT_STATUS_03, reg_int03); + + DRM_DEV_DEBUG_DRIVER(dev, "reg08 = 0x%02x", reg_int03); + DRM_DEV_DEBUG_DRIVER(dev, "reg0D = 0x%02x", reg_0d); + + return; + } + + if (it6505_test_bit(INT_SCDT_CHANGE, (unsigned int *)int_status)) + it6505_irq_scdt(it6505); } static irqreturn_t it6505_int_threaded_handler(int unused, void *data) @@ -2505,15 +2534,12 @@ static irqreturn_t it6505_int_threaded_handler(int unused, void *data) } irq_vec[] = { { BIT_INT_HPD, it6505_irq_hpd }, { BIT_INT_HPD_IRQ, it6505_irq_hpd_irq }, - { BIT_INT_SCDT, it6505_irq_scdt }, { BIT_INT_HDCP_FAIL, it6505_irq_hdcp_fail }, { BIT_INT_HDCP_DONE, it6505_irq_hdcp_done }, { BIT_INT_AUX_CMD_FAIL, it6505_irq_aux_cmd_fail }, { BIT_INT_HDCP_KSV_CHECK, it6505_irq_hdcp_ksv_check }, { BIT_INT_AUDIO_FIFO_ERROR, it6505_irq_audio_fifo_error }, { BIT_INT_LINK_TRAIN_FAIL, it6505_irq_link_train_fail }, - { BIT_INT_VID_FIFO_ERROR, it6505_irq_video_fifo_error }, - { BIT_INT_IO_FIFO_OVERFLOW, it6505_irq_io_latch_fifo_overflow }, }; int int_status[3], i; @@ -2543,6 +2569,7 @@ static irqreturn_t it6505_int_threaded_handler(int unused, void *data) if (it6505_test_bit(irq_vec[i].bit, (unsigned int *)int_status)) irq_vec[i].handler(it6505); } + it6505_irq_video_handler(it6505, (unsigned int *)int_status); } pm_runtime_put_sync(dev); diff --git a/drivers/gpu/drm/bridge/ite-it66121.c b/drivers/gpu/drm/bridge/ite-it66121.c index 466641c77fe911..8f5846b76d5943 100644 --- a/drivers/gpu/drm/bridge/ite-it66121.c +++ b/drivers/gpu/drm/bridge/ite-it66121.c @@ -884,14 +884,14 @@ static struct edid *it66121_bridge_get_edid(struct drm_bridge *bridge, mutex_lock(&ctx->lock); ret = it66121_preamble_ddc(ctx); if (ret) { - edid = ERR_PTR(ret); + edid = NULL; goto out_unlock; } ret = regmap_write(ctx->regmap, IT66121_DDC_HEADER_REG, IT66121_DDC_HEADER_EDID); if (ret) { - edid = ERR_PTR(ret); + edid = NULL; goto out_unlock; } @@ -1447,10 +1447,14 @@ static int it66121_audio_get_eld(struct device *dev, void *data, struct it66121_ctx *ctx = dev_get_drvdata(dev); mutex_lock(&ctx->lock); - - memcpy(buf, ctx->connector->eld, - min(sizeof(ctx->connector->eld), len)); - + if (!ctx->connector) { + /* Pass en empty ELD if connector not available */ + dev_dbg(dev, "No connector present, passing empty EDID data"); + memset(buf, 0, len); + } else { + memcpy(buf, ctx->connector->eld, + min(sizeof(ctx->connector->eld), len)); + } mutex_unlock(&ctx->lock); return 0; diff --git a/drivers/gpu/drm/bridge/lontium-lt8912b.c b/drivers/gpu/drm/bridge/lontium-lt8912b.c index 4eaea67fb71c20..5e43a40a5d5221 100644 --- a/drivers/gpu/drm/bridge/lontium-lt8912b.c +++ b/drivers/gpu/drm/bridge/lontium-lt8912b.c @@ -45,7 +45,6 @@ struct lt8912 { u8 data_lanes; bool is_power_on; - bool is_attached; }; static int lt8912_write_init_config(struct lt8912 *lt) @@ -412,50 +411,31 @@ static const struct drm_connector_funcs lt8912_connector_funcs = { .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; -static enum drm_mode_status -lt8912_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) -{ - if (mode->clock > 150000) - return MODE_CLOCK_HIGH; - - if (mode->hdisplay > 1920) - return MODE_BAD_HVALUE; - - if (mode->vdisplay > 1080) - return MODE_BAD_VVALUE; - - return MODE_OK; -} - static int lt8912_connector_get_modes(struct drm_connector *connector) { - struct edid *edid; - int ret = -1; - int num = 0; + const struct drm_edid *drm_edid; struct lt8912 *lt = connector_to_lt8912(connector); u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24; + int ret, num; - edid = drm_bridge_get_edid(lt->hdmi_port, connector); - if (edid) { - drm_connector_update_edid_property(connector, edid); - num = drm_add_edid_modes(connector, edid); - } else { - return ret; - } + drm_edid = drm_bridge_edid_read(lt->hdmi_port, connector); + drm_edid_connector_update(connector, drm_edid); + if (!drm_edid) + return 0; + + num = drm_edid_connector_add_modes(connector); ret = drm_display_info_set_bus_formats(&connector->display_info, &bus_format, 1); - if (ret) - num = ret; + if (ret < 0) + num = 0; - kfree(edid); + drm_edid_free(drm_edid); return num; } static const struct drm_connector_helper_funcs lt8912_connector_helper_funcs = { .get_modes = lt8912_connector_get_modes, - .mode_valid = lt8912_connector_mode_valid, }; static void lt8912_bridge_mode_set(struct drm_bridge *bridge, @@ -486,10 +466,8 @@ static int lt8912_attach_dsi(struct lt8912 *lt) }; host = of_find_mipi_dsi_host_by_node(lt->host_node); - if (!host) { - dev_err(dev, "failed to find dsi host\n"); - return -EPROBE_DEFER; - } + if (!host) + return dev_err_probe(dev, -EPROBE_DEFER, "failed to find dsi host\n"); dsi = devm_mipi_dsi_device_register_full(dev, host, &info); if (IS_ERR(dsi)) { @@ -559,6 +537,13 @@ static int lt8912_bridge_attach(struct drm_bridge *bridge, struct lt8912 *lt = bridge_to_lt8912(bridge); int ret; + ret = drm_bridge_attach(bridge->encoder, lt->hdmi_port, bridge, + DRM_BRIDGE_ATTACH_NO_CONNECTOR); + if (ret < 0) { + dev_err(lt->dev, "Failed to attach next bridge (%d)\n", ret); + return ret; + } + if (!(flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR)) { ret = lt8912_bridge_connector_init(bridge); if (ret) { @@ -575,8 +560,6 @@ static int lt8912_bridge_attach(struct drm_bridge *bridge, if (ret) goto error; - lt->is_attached = true; - return 0; error: @@ -588,15 +571,27 @@ static void lt8912_bridge_detach(struct drm_bridge *bridge) { struct lt8912 *lt = bridge_to_lt8912(bridge); - if (lt->is_attached) { - lt8912_hard_power_off(lt); + lt8912_hard_power_off(lt); - if (lt->hdmi_port->ops & DRM_BRIDGE_OP_HPD) - drm_bridge_hpd_disable(lt->hdmi_port); + if (lt->connector.dev && lt->hdmi_port->ops & DRM_BRIDGE_OP_HPD) + drm_bridge_hpd_disable(lt->hdmi_port); +} - drm_connector_unregister(<->connector); - drm_connector_cleanup(<->connector); - } +static enum drm_mode_status +lt8912_bridge_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + if (mode->clock > 150000) + return MODE_CLOCK_HIGH; + + if (mode->hdisplay > 1920) + return MODE_BAD_HVALUE; + + if (mode->vdisplay > 1080) + return MODE_BAD_VVALUE; + + return MODE_OK; } static enum drm_connector_status @@ -629,6 +624,7 @@ static struct edid *lt8912_bridge_get_edid(struct drm_bridge *bridge, static const struct drm_bridge_funcs lt8912_bridge_funcs = { .attach = lt8912_bridge_attach, .detach = lt8912_bridge_detach, + .mode_valid = lt8912_bridge_mode_valid, .mode_set = lt8912_bridge_mode_set, .enable = lt8912_bridge_enable, .detect = lt8912_bridge_detect, @@ -750,7 +746,6 @@ static void lt8912_remove(struct i2c_client *client) { struct lt8912 *lt = i2c_get_clientdata(client); - lt8912_bridge_detach(<->bridge); drm_bridge_remove(<->bridge); lt8912_free_i2c(lt); lt8912_put_dt(lt); diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index 9663601ce09818..89bdd938757e11 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -760,10 +760,8 @@ static struct mipi_dsi_device *lt9611_attach_dsi(struct lt9611 *lt9611, int ret; host = of_find_mipi_dsi_host_by_node(dsi_node); - if (!host) { - dev_err(lt9611->dev, "failed to find dsi host\n"); - return ERR_PTR(-EPROBE_DEFER); - } + if (!host) + return ERR_PTR(dev_err_probe(lt9611->dev, -EPROBE_DEFER, "failed to find dsi host\n")); dsi = devm_mipi_dsi_device_register_full(dev, host, &info); if (IS_ERR(dsi)) { diff --git a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c index 22c84d29c2bc58..c41ffd0bc04941 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c @@ -265,10 +265,8 @@ static struct mipi_dsi_device *lt9611uxc_attach_dsi(struct lt9611uxc *lt9611uxc, int ret; host = of_find_mipi_dsi_host_by_node(dsi_node); - if (!host) { - dev_err(dev, "failed to find dsi host\n"); - return ERR_PTR(-EPROBE_DEFER); - } + if (!host) + return ERR_PTR(dev_err_probe(dev, -EPROBE_DEFER, "failed to find dsi host\n")); dsi = devm_mipi_dsi_device_register_full(dev, host, &info); if (IS_ERR(dsi)) { @@ -929,9 +927,9 @@ static int lt9611uxc_probe(struct i2c_client *client) init_waitqueue_head(<9611uxc->wq); INIT_WORK(<9611uxc->work, lt9611uxc_hpd_work); - ret = devm_request_threaded_irq(dev, client->irq, NULL, - lt9611uxc_irq_thread_handler, - IRQF_ONESHOT, "lt9611uxc", lt9611uxc); + ret = request_threaded_irq(client->irq, NULL, + lt9611uxc_irq_thread_handler, + IRQF_ONESHOT, "lt9611uxc", lt9611uxc); if (ret) { dev_err(dev, "failed to request irq\n"); goto err_disable_regulators; @@ -967,6 +965,8 @@ static int lt9611uxc_probe(struct i2c_client *client) return lt9611uxc_audio_init(dev, lt9611uxc); err_remove_bridge: + free_irq(client->irq, lt9611uxc); + cancel_work_sync(<9611uxc->work); drm_bridge_remove(<9611uxc->bridge); err_disable_regulators: @@ -983,7 +983,7 @@ static void lt9611uxc_remove(struct i2c_client *client) { struct lt9611uxc *lt9611uxc = i2c_get_clientdata(client); - disable_irq(client->irq); + free_irq(client->irq, lt9611uxc); cancel_work_sync(<9611uxc->work); lt9611uxc_audio_exit(lt9611uxc); drm_bridge_remove(<9611uxc->bridge); diff --git a/drivers/gpu/drm/bridge/nxp-ptn3460.c b/drivers/gpu/drm/bridge/nxp-ptn3460.c index d81920227a8aeb..7c0076e499533a 100644 --- a/drivers/gpu/drm/bridge/nxp-ptn3460.c +++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c @@ -54,13 +54,13 @@ static int ptn3460_read_bytes(struct ptn3460_bridge *ptn_bridge, char addr, int ret; ret = i2c_master_send(ptn_bridge->client, &addr, 1); - if (ret <= 0) { + if (ret < 0) { DRM_ERROR("Failed to send i2c command, ret=%d\n", ret); return ret; } ret = i2c_master_recv(ptn_bridge->client, buf, len); - if (ret <= 0) { + if (ret < 0) { DRM_ERROR("Failed to recv i2c data, ret=%d\n", ret); return ret; } @@ -78,7 +78,7 @@ static int ptn3460_write_byte(struct ptn3460_bridge *ptn_bridge, char addr, buf[1] = val; ret = i2c_master_send(ptn_bridge->client, buf, ARRAY_SIZE(buf)); - if (ret <= 0) { + if (ret < 0) { DRM_ERROR("Failed to send i2c command, ret=%d\n", ret); return ret; } diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c index 9316384b44745b..a1dd2ead8dcc4d 100644 --- a/drivers/gpu/drm/bridge/panel.c +++ b/drivers/gpu/drm/bridge/panel.c @@ -360,9 +360,12 @@ EXPORT_SYMBOL(drm_panel_bridge_set_orientation); static void devm_drm_panel_bridge_release(struct device *dev, void *res) { - struct drm_bridge **bridge = res; + struct drm_bridge *bridge = *(struct drm_bridge **)res; - drm_panel_bridge_remove(*bridge); + if (!bridge) + return; + + drm_bridge_remove(bridge); } /** diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c index 8161b1a1a4b12f..14d4dcf239da83 100644 --- a/drivers/gpu/drm/bridge/parade-ps8640.c +++ b/drivers/gpu/drm/bridge/parade-ps8640.c @@ -107,6 +107,7 @@ struct ps8640 { struct device_link *link; bool pre_enabled; bool need_post_hpd_delay; + struct mutex aux_lock; }; static const struct regmap_config ps8640_regmap_config[] = { @@ -210,7 +211,7 @@ static ssize_t ps8640_aux_transfer_msg(struct drm_dp_aux *aux, struct ps8640 *ps_bridge = aux_to_ps8640(aux); struct regmap *map = ps_bridge->regmap[PAGE0_DP_CNTL]; struct device *dev = &ps_bridge->page[PAGE0_DP_CNTL]->dev; - unsigned int len = msg->size; + size_t len = msg->size; unsigned int data; unsigned int base; int ret; @@ -330,11 +331,12 @@ static ssize_t ps8640_aux_transfer_msg(struct drm_dp_aux *aux, return ret; } - buf[i] = data; + if (i < msg->size) + buf[i] = data; } } - return len; + return min(len, msg->size); } static ssize_t ps8640_aux_transfer(struct drm_dp_aux *aux, @@ -344,11 +346,20 @@ static ssize_t ps8640_aux_transfer(struct drm_dp_aux *aux, struct device *dev = &ps_bridge->page[PAGE0_DP_CNTL]->dev; int ret; + mutex_lock(&ps_bridge->aux_lock); pm_runtime_get_sync(dev); + ret = _ps8640_wait_hpd_asserted(ps_bridge, 200 * 1000); + if (ret) { + pm_runtime_put_sync_suspend(dev); + goto exit; + } ret = ps8640_aux_transfer_msg(aux, msg); pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); +exit: + mutex_unlock(&ps_bridge->aux_lock); + return ret; } @@ -469,7 +480,18 @@ static void ps8640_atomic_post_disable(struct drm_bridge *bridge, ps_bridge->pre_enabled = false; ps8640_bridge_vdo_control(ps_bridge, DISABLE); + + /* + * The bridge seems to expect everything to be power cycled at the + * disable process, so grab a lock here to make sure + * ps8640_aux_transfer() is not holding a runtime PM reference and + * preventing the bridge from suspend. + */ + mutex_lock(&ps_bridge->aux_lock); + pm_runtime_put_sync_suspend(&ps_bridge->page[PAGE0_DP_CNTL]->dev); + + mutex_unlock(&ps_bridge->aux_lock); } static int ps8640_bridge_attach(struct drm_bridge *bridge, @@ -618,6 +640,8 @@ static int ps8640_probe(struct i2c_client *client) if (!ps_bridge) return -ENOMEM; + mutex_init(&ps_bridge->aux_lock); + ps_bridge->supplies[0].supply = "vdd12"; ps_bridge->supplies[1].supply = "vdd33"; ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(ps_bridge->supplies), diff --git a/drivers/gpu/drm/bridge/samsung-dsim.c b/drivers/gpu/drm/bridge/samsung-dsim.c index cf777bdb25d2a4..f24666b4819384 100644 --- a/drivers/gpu/drm/bridge/samsung-dsim.c +++ b/drivers/gpu/drm/bridge/samsung-dsim.c @@ -385,7 +385,7 @@ static const unsigned int imx8mm_dsim_reg_values[] = { [RESET_TYPE] = DSIM_SWRST, [PLL_TIMER] = 500, [STOP_STATE_CNT] = 0xf, - [PHYCTRL_ULPS_EXIT] = 0, + [PHYCTRL_ULPS_EXIT] = DSIM_PHYCTRL_ULPS_EXIT(0xaf), [PHYCTRL_VREG_LP] = 0, [PHYCTRL_SLEW_UP] = 0, [PHYTIMING_LPX] = DSIM_PHYTIMING_LPX(0x06), @@ -413,6 +413,7 @@ static const struct samsung_dsim_driver_data exynos3_dsi_driver_data = { .m_min = 41, .m_max = 125, .min_freq = 500, + .has_broken_fifoctrl_emptyhdr = 1, }; static const struct samsung_dsim_driver_data exynos4_dsi_driver_data = { @@ -429,6 +430,7 @@ static const struct samsung_dsim_driver_data exynos4_dsi_driver_data = { .m_min = 41, .m_max = 125, .min_freq = 500, + .has_broken_fifoctrl_emptyhdr = 1, }; static const struct samsung_dsim_driver_data exynos5_dsi_driver_data = { @@ -939,10 +941,6 @@ static int samsung_dsim_init_link(struct samsung_dsim *dsi) reg = samsung_dsim_read(dsi, DSIM_ESCMODE_REG); reg &= ~DSIM_STOP_STATE_CNT_MASK; reg |= DSIM_STOP_STATE_CNT(driver_data->reg_values[STOP_STATE_CNT]); - - if (!samsung_dsim_hw_is_exynos(dsi->plat_data->hw_type)) - reg |= DSIM_FORCE_STOP_STATE; - samsung_dsim_write(dsi, DSIM_ESCMODE_REG, reg); reg = DSIM_BTA_TIMEOUT(0xff) | DSIM_LPDR_TIMEOUT(0xffff); @@ -1010,8 +1008,20 @@ static int samsung_dsim_wait_for_hdr_fifo(struct samsung_dsim *dsi) do { u32 reg = samsung_dsim_read(dsi, DSIM_FIFOCTRL_REG); - if (reg & DSIM_SFR_HEADER_EMPTY) - return 0; + if (!dsi->driver_data->has_broken_fifoctrl_emptyhdr) { + if (reg & DSIM_SFR_HEADER_EMPTY) + return 0; + } else { + if (!(reg & DSIM_SFR_HEADER_FULL)) { + /* + * Wait a little bit, so the pending data can + * actually leave the FIFO to avoid overflow. + */ + if (!cond_resched()) + usleep_range(950, 1050); + return 0; + } + } if (!cond_resched()) usleep_range(950, 1050); @@ -1387,18 +1397,6 @@ static void samsung_dsim_disable_irq(struct samsung_dsim *dsi) disable_irq(dsi->irq); } -static void samsung_dsim_set_stop_state(struct samsung_dsim *dsi, bool enable) -{ - u32 reg = samsung_dsim_read(dsi, DSIM_ESCMODE_REG); - - if (enable) - reg |= DSIM_FORCE_STOP_STATE; - else - reg &= ~DSIM_FORCE_STOP_STATE; - - samsung_dsim_write(dsi, DSIM_ESCMODE_REG, reg); -} - static int samsung_dsim_init(struct samsung_dsim *dsi) { const struct samsung_dsim_driver_data *driver_data = dsi->driver_data; @@ -1448,9 +1446,6 @@ static void samsung_dsim_atomic_pre_enable(struct drm_bridge *bridge, ret = samsung_dsim_init(dsi); if (ret) return; - - samsung_dsim_set_display_mode(dsi); - samsung_dsim_set_display_enable(dsi, true); } } @@ -1459,12 +1454,8 @@ static void samsung_dsim_atomic_enable(struct drm_bridge *bridge, { struct samsung_dsim *dsi = bridge_to_dsi(bridge); - if (samsung_dsim_hw_is_exynos(dsi->plat_data->hw_type)) { - samsung_dsim_set_display_mode(dsi); - samsung_dsim_set_display_enable(dsi, true); - } else { - samsung_dsim_set_stop_state(dsi, false); - } + samsung_dsim_set_display_mode(dsi); + samsung_dsim_set_display_enable(dsi, true); dsi->state |= DSIM_STATE_VIDOUT_AVAILABLE; } @@ -1477,9 +1468,6 @@ static void samsung_dsim_atomic_disable(struct drm_bridge *bridge, if (!(dsi->state & DSIM_STATE_ENABLED)) return; - if (!samsung_dsim_hw_is_exynos(dsi->plat_data->hw_type)) - samsung_dsim_set_stop_state(dsi, true); - dsi->state &= ~DSIM_STATE_VIDOUT_AVAILABLE; } @@ -1781,8 +1769,6 @@ static ssize_t samsung_dsim_host_transfer(struct mipi_dsi_host *host, if (ret) return ret; - samsung_dsim_set_stop_state(dsi, false); - ret = mipi_dsi_create_packet(&xfer.packet, msg); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c index 2bdc5b439bebd5..4560ae9cbce150 100644 --- a/drivers/gpu/drm/bridge/sii902x.c +++ b/drivers/gpu/drm/bridge/sii902x.c @@ -1080,6 +1080,26 @@ static int sii902x_init(struct sii902x *sii902x) return ret; } + ret = sii902x_audio_codec_init(sii902x, dev); + if (ret) + return ret; + + i2c_set_clientdata(sii902x->i2c, sii902x); + + sii902x->i2cmux = i2c_mux_alloc(sii902x->i2c->adapter, dev, + 1, 0, I2C_MUX_GATE, + sii902x_i2c_bypass_select, + sii902x_i2c_bypass_deselect); + if (!sii902x->i2cmux) { + ret = -ENOMEM; + goto err_unreg_audio; + } + + sii902x->i2cmux->priv = sii902x; + ret = i2c_mux_add_adapter(sii902x->i2cmux, 0, 0, 0); + if (ret) + goto err_unreg_audio; + sii902x->bridge.funcs = &sii902x_bridge_funcs; sii902x->bridge.of_node = dev->of_node; sii902x->bridge.timings = &default_sii902x_timings; @@ -1090,19 +1110,13 @@ static int sii902x_init(struct sii902x *sii902x) drm_bridge_add(&sii902x->bridge); - sii902x_audio_codec_init(sii902x, dev); - - i2c_set_clientdata(sii902x->i2c, sii902x); + return 0; - sii902x->i2cmux = i2c_mux_alloc(sii902x->i2c->adapter, dev, - 1, 0, I2C_MUX_GATE, - sii902x_i2c_bypass_select, - sii902x_i2c_bypass_deselect); - if (!sii902x->i2cmux) - return -ENOMEM; +err_unreg_audio: + if (!PTR_ERR_OR_ZERO(sii902x->audio.pdev)) + platform_device_unregister(sii902x->audio.pdev); - sii902x->i2cmux->priv = sii902x; - return i2c_mux_add_adapter(sii902x->i2cmux, 0, 0, 0); + return ret; } static int sii902x_probe(struct i2c_client *client) @@ -1170,12 +1184,14 @@ static int sii902x_probe(struct i2c_client *client) } static void sii902x_remove(struct i2c_client *client) - { struct sii902x *sii902x = i2c_get_clientdata(client); - i2c_mux_del_adapters(sii902x->i2cmux); drm_bridge_remove(&sii902x->bridge); + i2c_mux_del_adapters(sii902x->i2cmux); + + if (!PTR_ERR_OR_ZERO(sii902x->audio.pdev)) + platform_device_unregister(sii902x->audio.pdev); } static const struct of_device_id sii902x_dt_ids[] = { diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c index b45bffab7c8174..7fd4a5fe03edf6 100644 --- a/drivers/gpu/drm/bridge/tc358767.c +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -2034,7 +2034,7 @@ static irqreturn_t tc_irq_handler(int irq, void *arg) dev_err(tc->dev, "syserr %x\n", stat); } - if (tc->hpd_pin >= 0 && tc->bridge.dev) { + if (tc->hpd_pin >= 0 && tc->bridge.dev && tc->aux.drm_dev) { /* * H is triggered when the GPIO goes high. * @@ -2273,7 +2273,7 @@ static int tc_probe(struct i2c_client *client) } else { if (tc->hpd_pin < 0 || tc->hpd_pin > 1) { dev_err(dev, "failed to parse HPD number\n"); - return ret; + return -EINVAL; } } diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index 819a4b6ec2a07f..c72d5fbbb0ec40 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -9,12 +9,14 @@ #include #include #include +#include #include #include #include #include #include #include +#include #include #include @@ -156,6 +158,7 @@ struct tc358768_priv { u32 frs; /* PLL Freqency range for HSCK (post divider) */ u32 dsiclk; /* pll_clk / 2 */ + u32 pclk; /* incoming pclk rate */ }; static inline struct tc358768_priv *dsi_host_to_tc358768(struct mipi_dsi_host @@ -216,6 +219,10 @@ static void tc358768_update_bits(struct tc358768_priv *priv, u32 reg, u32 mask, u32 tmp, orig; tc358768_read(priv, reg, &orig); + + if (priv->error) + return; + tmp = orig & ~mask; tmp |= val & mask; if (tmp != orig) @@ -375,6 +382,7 @@ static int tc358768_calc_pll(struct tc358768_priv *priv, priv->prd = best_prd; priv->frs = frs; priv->dsiclk = best_pll / 2; + priv->pclk = mode->clock * 1000; return 0; } @@ -600,7 +608,7 @@ static int tc358768_setup_pll(struct tc358768_priv *priv, dev_dbg(priv->dev, "PLL: refclk %lu, fbd %u, prd %u, frs %u\n", clk_get_rate(priv->refclk), fbd, prd, frs); - dev_dbg(priv->dev, "PLL: pll_clk: %u, DSIClk %u, DSIByteClk %u\n", + dev_dbg(priv->dev, "PLL: pll_clk: %u, DSIClk %u, HSByteClk %u\n", priv->dsiclk * 2, priv->dsiclk, priv->dsiclk / 4); dev_dbg(priv->dev, "PLL: pclk %u (panel: %u)\n", tc358768_pll_to_pclk(priv, priv->dsiclk * 2), @@ -623,15 +631,36 @@ static int tc358768_setup_pll(struct tc358768_priv *priv, return tc358768_clear_error(priv); } -#define TC358768_PRECISION 1000 -static u32 tc358768_ns_to_cnt(u32 ns, u32 period_nsk) +static u32 tc358768_ns_to_cnt(u32 ns, u32 period_ps) +{ + return DIV_ROUND_UP(ns * 1000, period_ps); +} + +static u32 tc358768_ps_to_ns(u32 ps) { - return (ns * TC358768_PRECISION + period_nsk) / period_nsk; + return ps / 1000; } -static u32 tc358768_to_ns(u32 nsk) +static u32 tc358768_dpi_to_ns(u32 val, u32 pclk) { - return (nsk / TC358768_PRECISION); + return (u32)div_u64((u64)val * NANO, pclk); +} + +/* Convert value in DPI pixel clock units to DSI byte count */ +static u32 tc358768_dpi_to_dsi_bytes(struct tc358768_priv *priv, u32 val) +{ + u64 m = (u64)val * priv->dsiclk / 4 * priv->dsi_lanes; + u64 n = priv->pclk; + + return (u32)div_u64(m + n - 1, n); +} + +static u32 tc358768_dsi_bytes_to_ns(struct tc358768_priv *priv, u32 val) +{ + u64 m = (u64)val * NANO; + u64 n = priv->dsiclk / 4 * priv->dsi_lanes; + + return (u32)div_u64(m, n); } static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) @@ -642,13 +671,23 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) u32 val, val2, lptxcnt, hact, data_type; s32 raw_val; const struct drm_display_mode *mode; - u32 dsibclk_nsk, dsiclk_nsk, ui_nsk; - u32 dsiclk, dsibclk, video_start; - const u32 internal_delay = 40; + u32 hsbyteclk_ps, dsiclk_ps, ui_ps; + u32 dsiclk, hsbyteclk; int ret, i; + struct videomode vm; + struct device *dev = priv->dev; + /* In pixelclock units */ + u32 dpi_htot, dpi_data_start; + /* In byte units */ + u32 dsi_dpi_htot, dsi_dpi_data_start; + u32 dsi_hsw, dsi_hbp, dsi_hact, dsi_hfp; + const u32 dsi_hss = 4; /* HSS is a short packet (4 bytes) */ + /* In hsbyteclk units */ + u32 dsi_vsdly; + const u32 internal_dly = 40; if (mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS) { - dev_warn_once(priv->dev, "Non-continuous mode unimplemented, falling back to continuous\n"); + dev_warn_once(dev, "Non-continuous mode unimplemented, falling back to continuous\n"); mode_flags &= ~MIPI_DSI_CLOCK_NON_CONTINUOUS; } @@ -656,7 +695,7 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) ret = tc358768_sw_reset(priv); if (ret) { - dev_err(priv->dev, "Software reset failed: %d\n", ret); + dev_err(dev, "Software reset failed: %d\n", ret); tc358768_hw_disable(priv); return; } @@ -664,53 +703,194 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) mode = &bridge->encoder->crtc->state->adjusted_mode; ret = tc358768_setup_pll(priv, mode); if (ret) { - dev_err(priv->dev, "PLL setup failed: %d\n", ret); + dev_err(dev, "PLL setup failed: %d\n", ret); tc358768_hw_disable(priv); return; } + drm_display_mode_to_videomode(mode, &vm); + dsiclk = priv->dsiclk; - dsibclk = dsiclk / 4; + hsbyteclk = dsiclk / 4; /* Data Format Control Register */ val = BIT(2) | BIT(1) | BIT(0); /* rdswap_en | dsitx_en | txdt_en */ switch (dsi_dev->format) { case MIPI_DSI_FMT_RGB888: val |= (0x3 << 4); - hact = mode->hdisplay * 3; - video_start = (mode->htotal - mode->hsync_start) * 3; + hact = vm.hactive * 3; data_type = MIPI_DSI_PACKED_PIXEL_STREAM_24; break; case MIPI_DSI_FMT_RGB666: val |= (0x4 << 4); - hact = mode->hdisplay * 3; - video_start = (mode->htotal - mode->hsync_start) * 3; + hact = vm.hactive * 3; data_type = MIPI_DSI_PACKED_PIXEL_STREAM_18; break; case MIPI_DSI_FMT_RGB666_PACKED: val |= (0x4 << 4) | BIT(3); - hact = mode->hdisplay * 18 / 8; - video_start = (mode->htotal - mode->hsync_start) * 18 / 8; + hact = vm.hactive * 18 / 8; data_type = MIPI_DSI_PIXEL_STREAM_3BYTE_18; break; case MIPI_DSI_FMT_RGB565: val |= (0x5 << 4); - hact = mode->hdisplay * 2; - video_start = (mode->htotal - mode->hsync_start) * 2; + hact = vm.hactive * 2; data_type = MIPI_DSI_PACKED_PIXEL_STREAM_16; break; default: - dev_err(priv->dev, "Invalid data format (%u)\n", + dev_err(dev, "Invalid data format (%u)\n", dsi_dev->format); tc358768_hw_disable(priv); return; } + /* + * There are three important things to make TC358768 work correctly, + * which are not trivial to manage: + * + * 1. Keep the DPI line-time and the DSI line-time as close to each + * other as possible. + * 2. TC358768 goes to LP mode after each line's active area. The DSI + * HFP period has to be long enough for entering and exiting LP mode. + * But it is not clear how to calculate this. + * 3. VSDly (video start delay) has to be long enough to ensure that the + * DSI TX does not start transmitting until we have started receiving + * pixel data from the DPI input. It is not clear how to calculate + * this either. + */ + + dpi_htot = vm.hactive + vm.hfront_porch + vm.hsync_len + vm.hback_porch; + dpi_data_start = vm.hsync_len + vm.hback_porch; + + dev_dbg(dev, "dpi horiz timing (pclk): %u + %u + %u + %u = %u\n", + vm.hsync_len, vm.hback_porch, vm.hactive, vm.hfront_porch, + dpi_htot); + + dev_dbg(dev, "dpi horiz timing (ns): %u + %u + %u + %u = %u\n", + tc358768_dpi_to_ns(vm.hsync_len, vm.pixelclock), + tc358768_dpi_to_ns(vm.hback_porch, vm.pixelclock), + tc358768_dpi_to_ns(vm.hactive, vm.pixelclock), + tc358768_dpi_to_ns(vm.hfront_porch, vm.pixelclock), + tc358768_dpi_to_ns(dpi_htot, vm.pixelclock)); + + dev_dbg(dev, "dpi data start (ns): %u + %u = %u\n", + tc358768_dpi_to_ns(vm.hsync_len, vm.pixelclock), + tc358768_dpi_to_ns(vm.hback_porch, vm.pixelclock), + tc358768_dpi_to_ns(dpi_data_start, vm.pixelclock)); + + dsi_dpi_htot = tc358768_dpi_to_dsi_bytes(priv, dpi_htot); + dsi_dpi_data_start = tc358768_dpi_to_dsi_bytes(priv, dpi_data_start); + + if (dsi_dev->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) { + dsi_hsw = tc358768_dpi_to_dsi_bytes(priv, vm.hsync_len); + dsi_hbp = tc358768_dpi_to_dsi_bytes(priv, vm.hback_porch); + } else { + /* HBP is included in HSW in event mode */ + dsi_hbp = 0; + dsi_hsw = tc358768_dpi_to_dsi_bytes(priv, + vm.hsync_len + + vm.hback_porch); + + /* + * The pixel packet includes the actual pixel data, and: + * DSI packet header = 4 bytes + * DCS code = 1 byte + * DSI packet footer = 2 bytes + */ + dsi_hact = hact + 4 + 1 + 2; + + dsi_hfp = dsi_dpi_htot - dsi_hact - dsi_hsw - dsi_hss; + + /* + * Here we should check if HFP is long enough for entering LP + * and exiting LP, but it's not clear how to calculate that. + * Instead, this is a naive algorithm that just adjusts the HFP + * and HSW so that HFP is (at least) roughly 2/3 of the total + * blanking time. + */ + if (dsi_hfp < (dsi_hfp + dsi_hsw + dsi_hss) * 2 / 3) { + u32 old_hfp = dsi_hfp; + u32 old_hsw = dsi_hsw; + u32 tot = dsi_hfp + dsi_hsw + dsi_hss; + + dsi_hsw = tot / 3; + + /* + * Seems like sometimes HSW has to be divisible by num-lanes, but + * not always... + */ + dsi_hsw = roundup(dsi_hsw, priv->dsi_lanes); + + dsi_hfp = dsi_dpi_htot - dsi_hact - dsi_hsw - dsi_hss; + + dev_dbg(dev, + "hfp too short, adjusting dsi hfp and dsi hsw from %u, %u to %u, %u\n", + old_hfp, old_hsw, dsi_hfp, dsi_hsw); + } + + dev_dbg(dev, + "dsi horiz timing (bytes): %u, %u + %u + %u + %u = %u\n", + dsi_hss, dsi_hsw, dsi_hbp, dsi_hact, dsi_hfp, + dsi_hss + dsi_hsw + dsi_hbp + dsi_hact + dsi_hfp); + + dev_dbg(dev, "dsi horiz timing (ns): %u + %u + %u + %u + %u = %u\n", + tc358768_dsi_bytes_to_ns(priv, dsi_hss), + tc358768_dsi_bytes_to_ns(priv, dsi_hsw), + tc358768_dsi_bytes_to_ns(priv, dsi_hbp), + tc358768_dsi_bytes_to_ns(priv, dsi_hact), + tc358768_dsi_bytes_to_ns(priv, dsi_hfp), + tc358768_dsi_bytes_to_ns(priv, dsi_hss + dsi_hsw + + dsi_hbp + dsi_hact + dsi_hfp)); + } + + /* VSDly calculation */ + + /* Start with the HW internal delay */ + dsi_vsdly = internal_dly; + + /* Convert to byte units as the other variables are in byte units */ + dsi_vsdly *= priv->dsi_lanes; + + /* Do we need more delay, in addition to the internal? */ + if (dsi_dpi_data_start > dsi_vsdly + dsi_hss + dsi_hsw + dsi_hbp) { + dsi_vsdly = dsi_dpi_data_start - dsi_hss - dsi_hsw - dsi_hbp; + dsi_vsdly = roundup(dsi_vsdly, priv->dsi_lanes); + } + + dev_dbg(dev, "dsi data start (bytes) %u + %u + %u + %u = %u\n", + dsi_vsdly, dsi_hss, dsi_hsw, dsi_hbp, + dsi_vsdly + dsi_hss + dsi_hsw + dsi_hbp); + + dev_dbg(dev, "dsi data start (ns) %u + %u + %u + %u = %u\n", + tc358768_dsi_bytes_to_ns(priv, dsi_vsdly), + tc358768_dsi_bytes_to_ns(priv, dsi_hss), + tc358768_dsi_bytes_to_ns(priv, dsi_hsw), + tc358768_dsi_bytes_to_ns(priv, dsi_hbp), + tc358768_dsi_bytes_to_ns(priv, dsi_vsdly + dsi_hss + dsi_hsw + dsi_hbp)); + + /* Convert back to hsbyteclk */ + dsi_vsdly /= priv->dsi_lanes; + + /* + * The docs say that there is an internal delay of 40 cycles. + * However, we get underflows if we follow that rule. If we + * instead ignore the internal delay, things work. So either + * the docs are wrong or the calculations are wrong. + * + * As a temporary fix, add the internal delay here, to counter + * the subtraction when writing the register. + */ + dsi_vsdly += internal_dly; + + /* Clamp to the register max */ + if (dsi_vsdly - internal_dly > 0x3ff) { + dev_warn(dev, "VSDly too high, underflows likely\n"); + dsi_vsdly = 0x3ff + internal_dly; + } + /* VSDly[9:0] */ - video_start = max(video_start, internal_delay + 1) - internal_delay; - tc358768_write(priv, TC358768_VSDLY, video_start); + tc358768_write(priv, TC358768_VSDLY, dsi_vsdly - internal_dly); tc358768_write(priv, TC358768_DATAFMT, val); tc358768_write(priv, TC358768_DSITX_DT, data_type); @@ -722,67 +902,67 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) tc358768_write(priv, TC358768_D0W_CNTRL + i * 4, 0x0000); /* DSI Timings */ - dsibclk_nsk = (u32)div_u64((u64)1000000000 * TC358768_PRECISION, - dsibclk); - dsiclk_nsk = (u32)div_u64((u64)1000000000 * TC358768_PRECISION, dsiclk); - ui_nsk = dsiclk_nsk / 2; - dev_dbg(priv->dev, "dsiclk_nsk: %u\n", dsiclk_nsk); - dev_dbg(priv->dev, "ui_nsk: %u\n", ui_nsk); - dev_dbg(priv->dev, "dsibclk_nsk: %u\n", dsibclk_nsk); + hsbyteclk_ps = (u32)div_u64(PICO, hsbyteclk); + dsiclk_ps = (u32)div_u64(PICO, dsiclk); + ui_ps = dsiclk_ps / 2; + dev_dbg(dev, "dsiclk: %u ps, ui %u ps, hsbyteclk %u ps\n", dsiclk_ps, + ui_ps, hsbyteclk_ps); /* LP11 > 100us for D-PHY Rx Init */ - val = tc358768_ns_to_cnt(100 * 1000, dsibclk_nsk) - 1; - dev_dbg(priv->dev, "LINEINITCNT: 0x%x\n", val); + val = tc358768_ns_to_cnt(100 * 1000, hsbyteclk_ps) - 1; + dev_dbg(dev, "LINEINITCNT: %u\n", val); tc358768_write(priv, TC358768_LINEINITCNT, val); /* LPTimeCnt > 50ns */ - val = tc358768_ns_to_cnt(50, dsibclk_nsk) - 1; + val = tc358768_ns_to_cnt(50, hsbyteclk_ps) - 1; lptxcnt = val; - dev_dbg(priv->dev, "LPTXTIMECNT: 0x%x\n", val); + dev_dbg(dev, "LPTXTIMECNT: %u\n", val); tc358768_write(priv, TC358768_LPTXTIMECNT, val); /* 38ns < TCLK_PREPARE < 95ns */ - val = tc358768_ns_to_cnt(65, dsibclk_nsk) - 1; + val = tc358768_ns_to_cnt(65, hsbyteclk_ps) - 1; + dev_dbg(dev, "TCLK_PREPARECNT %u\n", val); /* TCLK_PREPARE + TCLK_ZERO > 300ns */ - val2 = tc358768_ns_to_cnt(300 - tc358768_to_ns(2 * ui_nsk), - dsibclk_nsk) - 2; + val2 = tc358768_ns_to_cnt(300 - tc358768_ps_to_ns(2 * ui_ps), + hsbyteclk_ps) - 2; + dev_dbg(dev, "TCLK_ZEROCNT %u\n", val2); val |= val2 << 8; - dev_dbg(priv->dev, "TCLK_HEADERCNT: 0x%x\n", val); tc358768_write(priv, TC358768_TCLK_HEADERCNT, val); /* TCLK_TRAIL > 60ns AND TEOT <= 105 ns + 12*UI */ - raw_val = tc358768_ns_to_cnt(60 + tc358768_to_ns(2 * ui_nsk), dsibclk_nsk) - 5; + raw_val = tc358768_ns_to_cnt(60 + tc358768_ps_to_ns(2 * ui_ps), hsbyteclk_ps) - 5; val = clamp(raw_val, 0, 127); - dev_dbg(priv->dev, "TCLK_TRAILCNT: 0x%x\n", val); + dev_dbg(dev, "TCLK_TRAILCNT: %u\n", val); tc358768_write(priv, TC358768_TCLK_TRAILCNT, val); /* 40ns + 4*UI < THS_PREPARE < 85ns + 6*UI */ - val = 50 + tc358768_to_ns(4 * ui_nsk); - val = tc358768_ns_to_cnt(val, dsibclk_nsk) - 1; + val = 50 + tc358768_ps_to_ns(4 * ui_ps); + val = tc358768_ns_to_cnt(val, hsbyteclk_ps) - 1; + dev_dbg(dev, "THS_PREPARECNT %u\n", val); /* THS_PREPARE + THS_ZERO > 145ns + 10*UI */ - raw_val = tc358768_ns_to_cnt(145 - tc358768_to_ns(3 * ui_nsk), dsibclk_nsk) - 10; + raw_val = tc358768_ns_to_cnt(145 - tc358768_ps_to_ns(3 * ui_ps), hsbyteclk_ps) - 10; val2 = clamp(raw_val, 0, 127); + dev_dbg(dev, "THS_ZEROCNT %u\n", val2); val |= val2 << 8; - dev_dbg(priv->dev, "THS_HEADERCNT: 0x%x\n", val); tc358768_write(priv, TC358768_THS_HEADERCNT, val); /* TWAKEUP > 1ms in lptxcnt steps */ - val = tc358768_ns_to_cnt(1020000, dsibclk_nsk); + val = tc358768_ns_to_cnt(1020000, hsbyteclk_ps); val = val / (lptxcnt + 1) - 1; - dev_dbg(priv->dev, "TWAKEUP: 0x%x\n", val); + dev_dbg(dev, "TWAKEUP: %u\n", val); tc358768_write(priv, TC358768_TWAKEUP, val); /* TCLK_POSTCNT > 60ns + 52*UI */ - val = tc358768_ns_to_cnt(60 + tc358768_to_ns(52 * ui_nsk), - dsibclk_nsk) - 3; - dev_dbg(priv->dev, "TCLK_POSTCNT: 0x%x\n", val); + val = tc358768_ns_to_cnt(60 + tc358768_ps_to_ns(52 * ui_ps), + hsbyteclk_ps) - 3; + dev_dbg(dev, "TCLK_POSTCNT: %u\n", val); tc358768_write(priv, TC358768_TCLK_POSTCNT, val); /* max(60ns + 4*UI, 8*UI) < THS_TRAILCNT < 105ns + 12*UI */ - raw_val = tc358768_ns_to_cnt(60 + tc358768_to_ns(18 * ui_nsk), - dsibclk_nsk) - 4; + raw_val = tc358768_ns_to_cnt(60 + tc358768_ps_to_ns(18 * ui_ps), + hsbyteclk_ps) - 4; val = clamp(raw_val, 0, 15); - dev_dbg(priv->dev, "THS_TRAILCNT: 0x%x\n", val); + dev_dbg(dev, "THS_TRAILCNT: %u\n", val); tc358768_write(priv, TC358768_THS_TRAILCNT, val); val = BIT(0); @@ -790,16 +970,17 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) val |= BIT(i + 1); tc358768_write(priv, TC358768_HSTXVREGEN, val); - if (!(mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS)) - tc358768_write(priv, TC358768_TXOPTIONCNTRL, 0x1); + tc358768_write(priv, TC358768_TXOPTIONCNTRL, + (mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS) ? 0 : BIT(0)); /* TXTAGOCNT[26:16] RXTASURECNT[10:0] */ - val = tc358768_to_ns((lptxcnt + 1) * dsibclk_nsk * 4); - val = tc358768_ns_to_cnt(val, dsibclk_nsk) / 4 - 1; - val2 = tc358768_ns_to_cnt(tc358768_to_ns((lptxcnt + 1) * dsibclk_nsk), - dsibclk_nsk) - 2; + val = tc358768_ps_to_ns((lptxcnt + 1) * hsbyteclk_ps * 4); + val = tc358768_ns_to_cnt(val, hsbyteclk_ps) / 4 - 1; + dev_dbg(dev, "TXTAGOCNT: %u\n", val); + val2 = tc358768_ns_to_cnt(tc358768_ps_to_ns((lptxcnt + 1) * hsbyteclk_ps), + hsbyteclk_ps) - 2; + dev_dbg(dev, "RXTASURECNT: %u\n", val2); val = val << 16 | val2; - dev_dbg(priv->dev, "BTACNTRL1: 0x%x\n", val); tc358768_write(priv, TC358768_BTACNTRL1, val); /* START[0] */ @@ -810,58 +991,44 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) tc358768_write(priv, TC358768_DSI_EVENT, 0); /* vact */ - tc358768_write(priv, TC358768_DSI_VACT, mode->vdisplay); + tc358768_write(priv, TC358768_DSI_VACT, vm.vactive); /* vsw */ - tc358768_write(priv, TC358768_DSI_VSW, - mode->vsync_end - mode->vsync_start); + tc358768_write(priv, TC358768_DSI_VSW, vm.vsync_len); + /* vbp */ - tc358768_write(priv, TC358768_DSI_VBPR, - mode->vtotal - mode->vsync_end); - - /* hsw * byteclk * ndl / pclk */ - val = (u32)div_u64((mode->hsync_end - mode->hsync_start) * - ((u64)priv->dsiclk / 4) * priv->dsi_lanes, - mode->clock * 1000); - tc358768_write(priv, TC358768_DSI_HSW, val); - - /* hbp * byteclk * ndl / pclk */ - val = (u32)div_u64((mode->htotal - mode->hsync_end) * - ((u64)priv->dsiclk / 4) * priv->dsi_lanes, - mode->clock * 1000); - tc358768_write(priv, TC358768_DSI_HBPR, val); + tc358768_write(priv, TC358768_DSI_VBPR, vm.vback_porch); } else { /* Set event mode */ tc358768_write(priv, TC358768_DSI_EVENT, 1); /* vact */ - tc358768_write(priv, TC358768_DSI_VACT, mode->vdisplay); + tc358768_write(priv, TC358768_DSI_VACT, vm.vactive); /* vsw (+ vbp) */ tc358768_write(priv, TC358768_DSI_VSW, - mode->vtotal - mode->vsync_start); + vm.vsync_len + vm.vback_porch); + /* vbp (not used in event mode) */ tc358768_write(priv, TC358768_DSI_VBPR, 0); + } - /* (hsw + hbp) * byteclk * ndl / pclk */ - val = (u32)div_u64((mode->htotal - mode->hsync_start) * - ((u64)priv->dsiclk / 4) * priv->dsi_lanes, - mode->clock * 1000); - tc358768_write(priv, TC358768_DSI_HSW, val); + /* hsw (bytes) */ + tc358768_write(priv, TC358768_DSI_HSW, dsi_hsw); - /* hbp (not used in event mode) */ - tc358768_write(priv, TC358768_DSI_HBPR, 0); - } + /* hbp (bytes) */ + tc358768_write(priv, TC358768_DSI_HBPR, dsi_hbp); /* hact (bytes) */ tc358768_write(priv, TC358768_DSI_HACT, hact); /* VSYNC polarity */ - if (!(mode->flags & DRM_MODE_FLAG_NVSYNC)) - tc358768_update_bits(priv, TC358768_CONFCTL, BIT(5), BIT(5)); + tc358768_update_bits(priv, TC358768_CONFCTL, BIT(5), + (mode->flags & DRM_MODE_FLAG_PVSYNC) ? BIT(5) : 0); + /* HSYNC polarity */ - if (mode->flags & DRM_MODE_FLAG_PHSYNC) - tc358768_update_bits(priv, TC358768_PP_MISC, BIT(0), BIT(0)); + tc358768_update_bits(priv, TC358768_PP_MISC, BIT(0), + (mode->flags & DRM_MODE_FLAG_PHSYNC) ? BIT(0) : 0); /* Start DSI Tx */ tc358768_write(priv, TC358768_DSI_START, 0x1); @@ -891,7 +1058,7 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) ret = tc358768_clear_error(priv); if (ret) { - dev_err(priv->dev, "Bridge pre_enable failed: %d\n", ret); + dev_err(dev, "Bridge pre_enable failed: %d\n", ret); tc358768_bridge_disable(bridge); tc358768_bridge_post_disable(bridge); } diff --git a/drivers/gpu/drm/bridge/tc358775.c b/drivers/gpu/drm/bridge/tc358775.c index 90a89d70d83287..c737670631929a 100644 --- a/drivers/gpu/drm/bridge/tc358775.c +++ b/drivers/gpu/drm/bridge/tc358775.c @@ -454,10 +454,6 @@ static void tc_bridge_enable(struct drm_bridge *bridge) dev_dbg(tc->dev, "bus_formats %04x bpc %d\n", connector->display_info.bus_formats[0], tc->bpc); - /* - * Default hardware register settings of tc358775 configured - * with MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA jeida-24 format - */ if (connector->display_info.bus_formats[0] == MEDIA_BUS_FMT_RGB888_1X7X4_SPWG) { /* VESA-24 */ @@ -468,14 +464,15 @@ static void tc_bridge_enable(struct drm_bridge *bridge) d2l_write(tc->i2c, LV_MX1619, LV_MX(LVI_B6, LVI_B7, LVI_B1, LVI_B2)); d2l_write(tc->i2c, LV_MX2023, LV_MX(LVI_B3, LVI_B4, LVI_B5, LVI_L0)); d2l_write(tc->i2c, LV_MX2427, LV_MX(LVI_HS, LVI_VS, LVI_DE, LVI_R6)); - } else { /* MEDIA_BUS_FMT_RGB666_1X7X3_SPWG - JEIDA-18 */ - d2l_write(tc->i2c, LV_MX0003, LV_MX(LVI_R0, LVI_R1, LVI_R2, LVI_R3)); - d2l_write(tc->i2c, LV_MX0407, LV_MX(LVI_R4, LVI_L0, LVI_R5, LVI_G0)); - d2l_write(tc->i2c, LV_MX0811, LV_MX(LVI_G1, LVI_G2, LVI_L0, LVI_L0)); - d2l_write(tc->i2c, LV_MX1215, LV_MX(LVI_G3, LVI_G4, LVI_G5, LVI_B0)); - d2l_write(tc->i2c, LV_MX1619, LV_MX(LVI_L0, LVI_L0, LVI_B1, LVI_B2)); - d2l_write(tc->i2c, LV_MX2023, LV_MX(LVI_B3, LVI_B4, LVI_B5, LVI_L0)); - d2l_write(tc->i2c, LV_MX2427, LV_MX(LVI_HS, LVI_VS, LVI_DE, LVI_L0)); + } else { + /* JEIDA-18 and JEIDA-24 */ + d2l_write(tc->i2c, LV_MX0003, LV_MX(LVI_R2, LVI_R3, LVI_R4, LVI_R5)); + d2l_write(tc->i2c, LV_MX0407, LV_MX(LVI_R6, LVI_R1, LVI_R7, LVI_G2)); + d2l_write(tc->i2c, LV_MX0811, LV_MX(LVI_G3, LVI_G4, LVI_G0, LVI_G1)); + d2l_write(tc->i2c, LV_MX1215, LV_MX(LVI_G5, LVI_G6, LVI_G7, LVI_B2)); + d2l_write(tc->i2c, LV_MX1619, LV_MX(LVI_B0, LVI_B1, LVI_B3, LVI_B4)); + d2l_write(tc->i2c, LV_MX2023, LV_MX(LVI_B5, LVI_B6, LVI_B7, LVI_L0)); + d2l_write(tc->i2c, LV_MX2427, LV_MX(LVI_HS, LVI_VS, LVI_DE, LVI_R0)); } d2l_write(tc->i2c, VFUEN, VFUEN_EN); @@ -610,10 +607,8 @@ static int tc_attach_host(struct tc_data *tc) }; host = of_find_mipi_dsi_host_by_node(tc->host_node); - if (!host) { - dev_err(dev, "failed to find dsi host\n"); - return -EPROBE_DEFER; - } + if (!host) + return dev_err_probe(dev, -EPROBE_DEFER, "failed to find dsi host\n"); dsi = devm_mipi_dsi_device_register_full(dev, host, &info); if (IS_ERR(dsi)) { diff --git a/drivers/gpu/drm/bridge/ti-dlpc3433.c b/drivers/gpu/drm/bridge/ti-dlpc3433.c index b65632ec7e7daa..3f933ba2946820 100644 --- a/drivers/gpu/drm/bridge/ti-dlpc3433.c +++ b/drivers/gpu/drm/bridge/ti-dlpc3433.c @@ -319,12 +319,11 @@ static int dlpc_host_attach(struct dlpc *dlpc) .channel = 0, .node = NULL, }; + int ret; host = of_find_mipi_dsi_host_by_node(dlpc->host_node); - if (!host) { - DRM_DEV_ERROR(dev, "failed to find dsi host\n"); - return -EPROBE_DEFER; - } + if (!host) + return dev_err_probe(dev, -EPROBE_DEFER, "failed to find dsi host\n"); dlpc->dsi = mipi_dsi_device_register_full(host, &info); if (IS_ERR(dlpc->dsi)) { @@ -336,7 +335,11 @@ static int dlpc_host_attach(struct dlpc *dlpc) dlpc->dsi->format = MIPI_DSI_FMT_RGB565; dlpc->dsi->lanes = dlpc->dsi_lanes; - return devm_mipi_dsi_attach(dev, dlpc->dsi); + ret = devm_mipi_dsi_attach(dev, dlpc->dsi); + if (ret) + DRM_DEV_ERROR(dev, "failed to attach dsi host\n"); + + return ret; } static int dlpc3433_probe(struct i2c_client *client) @@ -367,10 +370,8 @@ static int dlpc3433_probe(struct i2c_client *client) drm_bridge_add(&dlpc->bridge); ret = dlpc_host_attach(dlpc); - if (ret) { - DRM_DEV_ERROR(dev, "failed to attach dsi host\n"); + if (ret) goto err_remove_bridge; - } return 0; diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index 061e8bd5915de8..8a23116346a8a5 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -478,7 +478,6 @@ static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge, dev_err(ctx->dev, "failed to lock PLL, ret=%i\n", ret); /* On failure, disable PLL again and exit. */ regmap_write(ctx->regmap, REG_RC_PLL_EN, 0x00); - regulator_disable(ctx->vcc); return; } diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 84148a79414b7f..3309c01fa7153c 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -527,6 +527,7 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux, u32 request_val = AUX_CMD_REQ(msg->request); u8 *buf = msg->buffer; unsigned int len = msg->size; + unsigned int short_len; unsigned int val; int ret; u8 addr_len[SN_AUX_LENGTH_REG + 1 - SN_AUX_ADDR_19_16_REG]; @@ -600,7 +601,8 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux, } if (val & AUX_IRQ_STATUS_AUX_SHORT) { - ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &len); + ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &short_len); + len = min(len, short_len); if (ret) goto exit; } else if (val & AUX_IRQ_STATUS_NAT_I2C_FAIL) { diff --git a/drivers/gpu/drm/bridge/ti-tpd12s015.c b/drivers/gpu/drm/bridge/ti-tpd12s015.c index e0e015243a602d..b588fea12502d6 100644 --- a/drivers/gpu/drm/bridge/ti-tpd12s015.c +++ b/drivers/gpu/drm/bridge/ti-tpd12s015.c @@ -179,7 +179,7 @@ static int tpd12s015_probe(struct platform_device *pdev) return 0; } -static int __exit tpd12s015_remove(struct platform_device *pdev) +static int tpd12s015_remove(struct platform_device *pdev) { struct tpd12s015_device *tpd = platform_get_drvdata(pdev); @@ -197,7 +197,7 @@ MODULE_DEVICE_TABLE(of, tpd12s015_of_match); static struct platform_driver tpd12s015_driver = { .probe = tpd12s015_probe, - .remove = __exit_p(tpd12s015_remove), + .remove = tpd12s015_remove, .driver = { .name = "tpd12s015", .of_match_table = tpd12s015_of_match, diff --git a/drivers/gpu/drm/ci/build.yml b/drivers/gpu/drm/ci/build.yml index e6503f1c5927bb..17ab38304885cd 100644 --- a/drivers/gpu/drm/ci/build.yml +++ b/drivers/gpu/drm/ci/build.yml @@ -1,6 +1,7 @@ .build: extends: - .build-rules + - .container+build-rules stage: build artifacts: paths: diff --git a/drivers/gpu/drm/ci/gitlab-ci.yml b/drivers/gpu/drm/ci/gitlab-ci.yml index 2c4df53f5dfe3a..36949243674800 100644 --- a/drivers/gpu/drm/ci/gitlab-ci.yml +++ b/drivers/gpu/drm/ci/gitlab-ci.yml @@ -1,6 +1,6 @@ variables: DRM_CI_PROJECT_PATH: &drm-ci-project-path mesa/mesa - DRM_CI_COMMIT_SHA: &drm-ci-commit-sha 0dc961645c4f0241f8512cb0ec3ad59635842072 + DRM_CI_COMMIT_SHA: &drm-ci-commit-sha edfbf74df1d4d6ce54ffe24566108be0e1a98c3d UPSTREAM_REPO: git://anongit.freedesktop.org/drm/drm TARGET_BRANCH: drm-next @@ -24,7 +24,9 @@ variables: PIPELINE_ARTIFACTS_BASE: ${S3_HOST}/artifacts/${CI_PROJECT_PATH}/${CI_PIPELINE_ID} # per-job artifact storage on MinIO JOB_ARTIFACTS_BASE: ${PIPELINE_ARTIFACTS_BASE}/${CI_JOB_ID} - + # default kernel for rootfs before injecting the current kernel tree + KERNEL_IMAGE_BASE: https://${S3_HOST}/mesa-lava/gfx-ci/linux/v6.4.12-for-mesa-ci-f6b4ad45f48d + LAVA_TAGS: subset-1-gfx LAVA_JOB_PRIORITY: 30 default: @@ -86,6 +88,17 @@ include: - '/.gitlab-ci/container/gitlab-ci.yml' - '/.gitlab-ci/test/gitlab-ci.yml' - '/.gitlab-ci/lava/lava-gitlab-ci.yml' + - '/src/microsoft/ci/gitlab-ci-inc.yml' + - '/src/gallium/drivers/zink/ci/gitlab-ci-inc.yml' + - '/src/gallium/drivers/crocus/ci/gitlab-ci-inc.yml' + - '/src/gallium/drivers/softpipe/ci/gitlab-ci-inc.yml' + - '/src/gallium/drivers/llvmpipe/ci/gitlab-ci-inc.yml' + - '/src/gallium/drivers/virgl/ci/gitlab-ci-inc.yml' + - '/src/gallium/drivers/nouveau/ci/gitlab-ci-inc.yml' + - '/src/gallium/frontends/lavapipe/ci/gitlab-ci-inc.yml' + - '/src/intel/ci/gitlab-ci-inc.yml' + - '/src/freedreno/ci/gitlab-ci-inc.yml' + - '/src/amd/ci/gitlab-ci-inc.yml' - drivers/gpu/drm/ci/image-tags.yml - drivers/gpu/drm/ci/container.yml - drivers/gpu/drm/ci/static-checks.yml @@ -154,6 +167,11 @@ stages: # Run automatically once all dependency jobs have passed - when: on_success +# When to automatically run the CI for container jobs +.container+build-rules: + rules: + - !reference [.no_scheduled_pipelines-rules, rules] + - when: manual .ci-deqp-artifacts: artifacts: diff --git a/drivers/gpu/drm/ci/image-tags.yml b/drivers/gpu/drm/ci/image-tags.yml index f051b6c547c531..157d987149f072 100644 --- a/drivers/gpu/drm/ci/image-tags.yml +++ b/drivers/gpu/drm/ci/image-tags.yml @@ -1,5 +1,5 @@ variables: - CONTAINER_TAG: "2023-08-10-mesa-uprev" + CONTAINER_TAG: "2023-10-11-mesa-uprev" DEBIAN_X86_64_BUILD_BASE_IMAGE: "debian/x86_64_build-base" DEBIAN_BASE_TAG: "${CONTAINER_TAG}" diff --git a/drivers/gpu/drm/ci/lava-submit.sh b/drivers/gpu/drm/ci/lava-submit.sh index 0c4456b21b0fc6..379f26ea87cc00 100755 --- a/drivers/gpu/drm/ci/lava-submit.sh +++ b/drivers/gpu/drm/ci/lava-submit.sh @@ -22,7 +22,7 @@ cp "$SCRIPTS_DIR"/setup-test-env.sh results/job-rootfs-overlay/ # Prepare env vars for upload. section_start variables "Variables passed through:" -KERNEL_IMAGE_BASE_URL="https://${BASE_SYSTEM_HOST_PATH}" \ +KERNEL_IMAGE_BASE="https://${BASE_SYSTEM_HOST_PATH}" \ artifacts/ci-common/generate-env.sh | tee results/job-rootfs-overlay/set-job-env-vars.sh section_end variables diff --git a/drivers/gpu/drm/ci/test.yml b/drivers/gpu/drm/ci/test.yml index 6473cddaa7a962..6f81dc10865b5e 100644 --- a/drivers/gpu/drm/ci/test.yml +++ b/drivers/gpu/drm/ci/test.yml @@ -86,7 +86,7 @@ msm:sc7180: extends: - .lava-igt:arm64 stage: msm - parallel: 2 + parallel: 4 variables: DRIVER_NAME: msm DEVICE_TYPE: sc7180-trogdor-lazor-limozeen @@ -104,7 +104,10 @@ msm:apq8016: DRIVER_NAME: msm BM_DTB: https://${PIPELINE_ARTIFACTS_BASE}/arm64/apq8016-sbc.dtb GPU_VERSION: apq8016 - BM_CMDLINE: "ip=dhcp console=ttyMSM0,115200n8 $BM_KERNEL_EXTRA_ARGS root=/dev/nfs rw nfsrootdebug nfsroot=,tcp,nfsvers=4.2 init=/init $BM_KERNELARGS" + # disabling unused clocks congests with the MDSS runtime PM trying to + # disable those clocks and causes boot to fail. + # Reproducer: DRM_MSM=y, DRM_I2C_ADV7511=m + BM_KERNEL_EXTRA_ARGS: clk_ignore_unused RUNNER_TAG: google-freedreno-db410c script: - ./install/bare-metal/fastboot.sh @@ -155,7 +158,7 @@ rockchip:rk3399: extends: - .lava-igt:arm64 stage: rockchip - parallel: 3 + parallel: 2 variables: DRIVER_NAME: rockchip DEVICE_TYPE: rk3399-gru-kevin @@ -178,7 +181,7 @@ rockchip:rk3399: i915:apl: extends: - .i915 - parallel: 12 + parallel: 3 variables: DEVICE_TYPE: asus-C523NA-A20057-coral GPU_VERSION: apl @@ -187,7 +190,7 @@ i915:apl: i915:glk: extends: - .i915 - parallel: 5 + parallel: 2 variables: DEVICE_TYPE: hp-x360-12b-ca0010nr-n4020-octopus GPU_VERSION: glk @@ -196,7 +199,7 @@ i915:glk: i915:amly: extends: - .i915 - parallel: 8 + parallel: 2 variables: DEVICE_TYPE: asus-C433TA-AJ0005-rammus GPU_VERSION: amly @@ -205,7 +208,7 @@ i915:amly: i915:kbl: extends: - .i915 - parallel: 5 + parallel: 3 variables: DEVICE_TYPE: hp-x360-14-G1-sona GPU_VERSION: kbl @@ -214,7 +217,7 @@ i915:kbl: i915:whl: extends: - .i915 - parallel: 8 + parallel: 2 variables: DEVICE_TYPE: dell-latitude-5400-8665U-sarien GPU_VERSION: whl @@ -223,7 +226,7 @@ i915:whl: i915:cml: extends: - .i915 - parallel: 6 + parallel: 2 variables: DEVICE_TYPE: asus-C436FA-Flip-hatch GPU_VERSION: cml @@ -232,11 +235,11 @@ i915:cml: i915:tgl: extends: - .i915 - parallel: 6 + parallel: 5 variables: - DEVICE_TYPE: asus-cx9400-volteer + DEVICE_TYPE: acer-cp514-2h-1130g7-volteer GPU_VERSION: tgl - RUNNER_TAG: mesa-ci-x86-64-lava-asus-cx9400-volteer + RUNNER_TAG: mesa-ci-x86-64-lava-acer-cp514-2h-1130g7-volteer .amdgpu: extends: @@ -251,6 +254,7 @@ i915:tgl: amdgpu:stoney: extends: - .amdgpu + parallel: 2 variables: DEVICE_TYPE: hp-11A-G6-EE-grunt GPU_VERSION: stoney @@ -269,6 +273,7 @@ amdgpu:stoney: mediatek:mt8173: extends: - .mediatek + parallel: 4 variables: DEVICE_TYPE: mt8173-elm-hana GPU_VERSION: mt8173 @@ -280,6 +285,7 @@ mediatek:mt8173: mediatek:mt8183: extends: - .mediatek + parallel: 3 variables: DEVICE_TYPE: mt8183-kukui-jacuzzi-juniper-sku16 GPU_VERSION: mt8183 @@ -289,6 +295,7 @@ mediatek:mt8183: .mediatek:mt8192: extends: - .mediatek + parallel: 3 variables: DEVICE_TYPE: mt8192-asurada-spherion-r0 GPU_VERSION: mt8192 @@ -307,6 +314,7 @@ mediatek:mt8183: meson:g12b: extends: - .meson + parallel: 3 variables: DEVICE_TYPE: meson-g12b-a311d-khadas-vim3 GPU_VERSION: g12b diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index e6a78fd32380a1..851f0baf94600c 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -532,6 +532,15 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, mutex_lock(&aux->hw_mutex); + /* + * If the device attached to the aux bus is powered down then there's + * no reason to attempt a transfer. Error out immediately. + */ + if (aux->powered_down) { + ret = -EBUSY; + goto unlock; + } + /* * The specification doesn't give any recommendation on how often to * retry native transactions. We used to retry 7 times like for @@ -599,6 +608,29 @@ int drm_dp_dpcd_probe(struct drm_dp_aux *aux, unsigned int offset) } EXPORT_SYMBOL(drm_dp_dpcd_probe); +/** + * drm_dp_dpcd_set_powered() - Set whether the DP device is powered + * @aux: DisplayPort AUX channel; for convenience it's OK to pass NULL here + * and the function will be a no-op. + * @powered: true if powered; false if not + * + * If the endpoint device on the DP AUX bus is known to be powered down + * then this function can be called to make future transfers fail immediately + * instead of needing to time out. + * + * If this function is never called then a device defaults to being powered. + */ +void drm_dp_dpcd_set_powered(struct drm_dp_aux *aux, bool powered) +{ + if (!aux) + return; + + mutex_lock(&aux->hw_mutex); + aux->powered_down = !powered; + mutex_unlock(&aux->hw_mutex); +} +EXPORT_SYMBOL(drm_dp_dpcd_set_powered); + /** * drm_dp_dpcd_read() - read a series of bytes from the DPCD * @aux: DisplayPort AUX channel (SST or MST) @@ -1855,6 +1887,9 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, struct drm_dp_aux_msg msg; int err = 0; + if (aux->powered_down) + return -EBUSY; + dp_aux_i2c_transfer_size = clamp(dp_aux_i2c_transfer_size, 1, DP_AUX_MAX_PAYLOAD_BYTES); memset(&msg, 0, sizeof(msg)); diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index 8c929ef72c72c7..6ead31701e79ea 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -2923,7 +2923,7 @@ static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, /* FIXME: Actually do some real error handling here */ ret = drm_dp_mst_wait_tx_reply(mstb, txmsg); - if (ret <= 0) { + if (ret < 0) { drm_err(mgr->dev, "Sending link address failed with %d\n", ret); goto out; } @@ -2975,7 +2975,7 @@ static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, mutex_unlock(&mgr->lock); out: - if (ret <= 0) + if (ret < 0) mstb->link_address_sent = false; kfree(txmsg); return ret < 0 ? ret : changed; @@ -4024,6 +4024,7 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) if (up_req->msg.req_type == DP_CONNECTION_STATUS_NOTIFY) { const struct drm_dp_connection_status_notify *conn_stat = &up_req->msg.u.conn_stat; + bool handle_csn; drm_dbg_kms(mgr->dev, "Got CSN: pn: %d ldps:%d ddps: %d mcs: %d ip: %d pdt: %d\n", conn_stat->port_number, @@ -4032,6 +4033,16 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) conn_stat->message_capability_status, conn_stat->input_port, conn_stat->peer_device_type); + + mutex_lock(&mgr->probe_lock); + handle_csn = mgr->mst_primary->link_address_sent; + mutex_unlock(&mgr->probe_lock); + + if (!handle_csn) { + drm_dbg_kms(mgr->dev, "Got CSN before finish topology probing. Skip it."); + kfree(up_req); + goto out; + } } else if (up_req->msg.req_type == DP_RESOURCE_STATUS_NOTIFY) { const struct drm_dp_resource_status_notify *res_stat = &up_req->msg.u.resource_stat; @@ -4690,13 +4701,12 @@ EXPORT_SYMBOL(drm_dp_check_act_status); /** * drm_dp_calc_pbn_mode() - Calculate the PBN for a mode. - * @clock: dot clock for the mode - * @bpp: bpp for the mode. - * @dsc: DSC mode. If true, bpp has units of 1/16 of a bit per pixel + * @clock: dot clock + * @bpp: bpp as .4 binary fixed point * * This uses the formula in the spec to calculate the PBN value for a mode. */ -int drm_dp_calc_pbn_mode(int clock, int bpp, bool dsc) +int drm_dp_calc_pbn_mode(int clock, int bpp) { /* * margin 5300ppm + 300ppm ~ 0.6% as per spec, factor is 1.006 @@ -4707,18 +4717,9 @@ int drm_dp_calc_pbn_mode(int clock, int bpp, bool dsc) * peak_kbps *= (1006/1000) * peak_kbps *= (64/54) * peak_kbps *= 8 convert to bytes - * - * If the bpp is in units of 1/16, further divide by 16. Put this - * factor in the numerator rather than the denominator to avoid - * integer overflow */ - - if (dsc) - return DIV_ROUND_UP_ULL(mul_u32_u32(clock * (bpp / 16), 64 * 1006), - 8 * 54 * 1000 * 1000); - - return DIV_ROUND_UP_ULL(mul_u32_u32(clock * bpp, 64 * 1006), - 8 * 54 * 1000 * 1000); + return DIV_ROUND_UP_ULL(mul_u32_u32(clock * bpp, 64 * 1006 >> 4), + 1000 * 8 * 54 * 1000); } EXPORT_SYMBOL(drm_dp_calc_pbn_mode); diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 60794fcde1d50f..554d4468aa7c08 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -2012,7 +2012,7 @@ int drm_atomic_helper_commit(struct drm_device *dev, return ret; drm_atomic_helper_async_commit(dev, state); - drm_atomic_helper_cleanup_planes(dev, state); + drm_atomic_helper_unprepare_planes(dev, state); return 0; } @@ -2072,7 +2072,7 @@ int drm_atomic_helper_commit(struct drm_device *dev, return 0; err: - drm_atomic_helper_cleanup_planes(dev, state); + drm_atomic_helper_unprepare_planes(dev, state); return ret; } EXPORT_SYMBOL(drm_atomic_helper_commit); @@ -2650,6 +2650,39 @@ int drm_atomic_helper_prepare_planes(struct drm_device *dev, } EXPORT_SYMBOL(drm_atomic_helper_prepare_planes); +/** + * drm_atomic_helper_unprepare_planes - release plane resources on aborts + * @dev: DRM device + * @state: atomic state object with old state structures + * + * This function cleans up plane state, specifically framebuffers, from the + * atomic state. It undoes the effects of drm_atomic_helper_prepare_planes() + * when aborting an atomic commit. For cleaning up after a successful commit + * use drm_atomic_helper_cleanup_planes(). + */ +void drm_atomic_helper_unprepare_planes(struct drm_device *dev, + struct drm_atomic_state *state) +{ + struct drm_plane *plane; + struct drm_plane_state *new_plane_state; + int i; + + for_each_new_plane_in_state(state, plane, new_plane_state, i) { + const struct drm_plane_helper_funcs *funcs = plane->helper_private; + + if (funcs->end_fb_access) + funcs->end_fb_access(plane, new_plane_state); + } + + for_each_new_plane_in_state(state, plane, new_plane_state, i) { + const struct drm_plane_helper_funcs *funcs = plane->helper_private; + + if (funcs->cleanup_fb) + funcs->cleanup_fb(plane, new_plane_state); + } +} +EXPORT_SYMBOL(drm_atomic_helper_unprepare_planes); + static bool plane_crtc_active(const struct drm_plane_state *state) { return state->crtc && state->crtc->state->active; @@ -2784,6 +2817,17 @@ void drm_atomic_helper_commit_planes(struct drm_device *dev, funcs->atomic_flush(crtc, old_state); } + + /* + * Signal end of framebuffer access here before hw_done. After hw_done, + * a later commit might have already released the plane state. + */ + for_each_old_plane_in_state(old_state, plane, old_plane_state, i) { + const struct drm_plane_helper_funcs *funcs = plane->helper_private; + + if (funcs->end_fb_access) + funcs->end_fb_access(plane, old_plane_state); + } } EXPORT_SYMBOL(drm_atomic_helper_commit_planes); @@ -2911,40 +2955,22 @@ EXPORT_SYMBOL(drm_atomic_helper_disable_planes_on_crtc); * configuration. Hence the old configuration must be perserved in @old_state to * be able to call this function. * - * This function must also be called on the new state when the atomic update - * fails at any point after calling drm_atomic_helper_prepare_planes(). + * This function may not be called on the new state when the atomic update + * fails at any point after calling drm_atomic_helper_prepare_planes(). Use + * drm_atomic_helper_unprepare_planes() in this case. */ void drm_atomic_helper_cleanup_planes(struct drm_device *dev, struct drm_atomic_state *old_state) { struct drm_plane *plane; - struct drm_plane_state *old_plane_state, *new_plane_state; + struct drm_plane_state *old_plane_state; int i; - for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) { + for_each_old_plane_in_state(old_state, plane, old_plane_state, i) { const struct drm_plane_helper_funcs *funcs = plane->helper_private; - if (funcs->end_fb_access) - funcs->end_fb_access(plane, new_plane_state); - } - - for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) { - const struct drm_plane_helper_funcs *funcs; - struct drm_plane_state *plane_state; - - /* - * This might be called before swapping when commit is aborted, - * in which case we have to cleanup the new state. - */ - if (old_plane_state == plane->state) - plane_state = new_plane_state; - else - plane_state = old_plane_state; - - funcs = plane->helper_private; - if (funcs->cleanup_fb) - funcs->cleanup_fb(plane, plane_state); + funcs->cleanup_fb(plane, old_plane_state); } } EXPORT_SYMBOL(drm_atomic_helper_cleanup_planes); diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c index 98d3b10c08ae19..ab03b08433f8f3 100644 --- a/drivers/gpu/drm/drm_atomic_uapi.c +++ b/drivers/gpu/drm/drm_atomic_uapi.c @@ -585,7 +585,7 @@ static int drm_atomic_plane_set_property(struct drm_plane *plane, &state->fb_damage_clips, val, -1, - sizeof(struct drm_rect), + sizeof(struct drm_mode_rect), &replaced); return ret; } else if (property == plane->scaling_filter_property) { diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c index cf92a9ae8034c9..6899b3dc1f12a5 100644 --- a/drivers/gpu/drm/drm_auth.c +++ b/drivers/gpu/drm/drm_auth.c @@ -235,7 +235,8 @@ static int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv) static int drm_master_check_perm(struct drm_device *dev, struct drm_file *file_priv) { - if (file_priv->pid == task_pid(current) && file_priv->was_master) + if (file_priv->was_master && + rcu_access_pointer(file_priv->pid) == task_tgid(current)) return 0; if (!capable(CAP_SYS_ADMIN)) diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c index 39e68e45bb124b..62d8a291c49c7a 100644 --- a/drivers/gpu/drm/drm_bridge.c +++ b/drivers/gpu/drm/drm_bridge.c @@ -27,8 +27,9 @@ #include #include -#include #include +#include +#include #include #include #include @@ -686,11 +687,17 @@ void drm_atomic_bridge_chain_post_disable(struct drm_bridge *bridge, */ list_for_each_entry_from(next, &encoder->bridge_chain, chain_node) { - if (next->pre_enable_prev_first) { + if (!next->pre_enable_prev_first) { next = list_prev_entry(next, chain_node); limit = next; break; } + + if (list_is_last(&next->chain_node, + &encoder->bridge_chain)) { + limit = next; + break; + } } /* Call these bridges in reverse order */ @@ -773,7 +780,7 @@ void drm_atomic_bridge_chain_pre_enable(struct drm_bridge *bridge, /* Found first bridge that does NOT * request prev to be enabled first */ - limit = list_prev_entry(next, chain_node); + limit = next; break; } } @@ -1206,6 +1213,47 @@ int drm_bridge_get_modes(struct drm_bridge *bridge, } EXPORT_SYMBOL_GPL(drm_bridge_get_modes); +/** + * drm_bridge_edid_read - read the EDID data of the connected display + * @bridge: bridge control structure + * @connector: the connector to read EDID for + * + * If the bridge supports output EDID retrieval, as reported by the + * DRM_BRIDGE_OP_EDID bridge ops flag, call &drm_bridge_funcs.edid_read to get + * the EDID and return it. Otherwise return NULL. + * + * If &drm_bridge_funcs.edid_read is not set, fall back to using + * drm_bridge_get_edid() and wrapping it in struct drm_edid. + * + * RETURNS: + * The retrieved EDID on success, or NULL otherwise. + */ +const struct drm_edid *drm_bridge_edid_read(struct drm_bridge *bridge, + struct drm_connector *connector) +{ + if (!(bridge->ops & DRM_BRIDGE_OP_EDID)) + return NULL; + + /* Transitional: Fall back to ->get_edid. */ + if (!bridge->funcs->edid_read) { + const struct drm_edid *drm_edid; + struct edid *edid; + + edid = drm_bridge_get_edid(bridge, connector); + if (!edid) + return NULL; + + drm_edid = drm_edid_alloc(edid, (edid->extensions + 1) * EDID_LENGTH); + + kfree(edid); + + return drm_edid; + } + + return bridge->funcs->edid_read(bridge, connector); +} +EXPORT_SYMBOL_GPL(drm_bridge_edid_read); + /** * drm_bridge_get_edid - get the EDID data of the connected display * @bridge: bridge control structure @@ -1215,6 +1263,8 @@ EXPORT_SYMBOL_GPL(drm_bridge_get_modes); * DRM_BRIDGE_OP_EDID bridge ops flag, call &drm_bridge_funcs.get_edid to * get the EDID and return it. Otherwise return NULL. * + * Deprecated. Prefer using drm_bridge_edid_read(). + * * RETURNS: * The retrieved EDID on success, or NULL otherwise. */ diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index e6f5ba5f4bafd0..d9cbf4e3327cdb 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -332,6 +332,7 @@ alloc_range_bias(struct drm_buddy *mm, u64 start, u64 end, unsigned int order) { + u64 req_size = mm->chunk_size << order; struct drm_buddy_block *block; struct drm_buddy_block *buddy; LIST_HEAD(dfs); @@ -367,6 +368,15 @@ alloc_range_bias(struct drm_buddy *mm, if (drm_buddy_block_is_allocated(block)) continue; + if (block_start < start || block_end > end) { + u64 adjusted_start = max(block_start, start); + u64 adjusted_end = min(block_end, end); + + if (round_down(adjusted_end + 1, req_size) <= + round_up(adjusted_start, req_size)) + continue; + } + if (contains(start, end, block_start, block_end) && order == drm_buddy_block_order(block)) { /* diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 871e4e2129d6da..51df7244de7185 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -777,6 +777,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, unsigned int total_modes_count = 0; struct drm_client_offset *offsets; unsigned int connector_count = 0; + /* points to modes protected by mode_config.mutex */ struct drm_display_mode **modes; struct drm_crtc **crtcs; int i, ret = 0; @@ -845,7 +846,6 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, drm_client_pick_crtcs(client, connectors, connector_count, crtcs, modes, 0, width, height); } - mutex_unlock(&dev->mode_config.mutex); drm_client_modeset_release(client); @@ -869,12 +869,18 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, kfree(modeset->mode); modeset->mode = drm_mode_duplicate(dev, mode); + if (!modeset->mode) { + ret = -ENOMEM; + break; + } + drm_connector_get(connector); modeset->connectors[modeset->num_connectors++] = connector; modeset->x = offset->x; modeset->y = offset->y; } } + mutex_unlock(&dev->mode_config.mutex); mutex_unlock(&client->modeset_mutex); out: diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index c44d5bcf12847b..309aad5f0c808d 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -2925,7 +2925,7 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, dev->mode_config.max_width, dev->mode_config.max_height); else - drm_dbg_kms(dev, "User-space requested a forced probe on [CONNECTOR:%d:%s] but is not the DRM master, demoting to read-only probe", + drm_dbg_kms(dev, "User-space requested a forced probe on [CONNECTOR:%d:%s] but is not the DRM master, demoting to read-only probe\n", connector->base.id, connector->name); } diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index df9bf3c9206e71..65f9f66933bba2 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -715,8 +715,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, struct drm_mode_set set; uint32_t __user *set_connectors_ptr; struct drm_modeset_acquire_ctx ctx; - int ret; - int i; + int ret, i, num_connectors = 0; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EOPNOTSUPP; @@ -871,6 +870,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, connector->name); connector_set[i] = connector; + num_connectors++; } } @@ -879,7 +879,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, set.y = crtc_req->y; set.mode = mode; set.connectors = connector_set; - set.num_connectors = crtc_req->count_connectors; + set.num_connectors = num_connectors; set.fb = fb; if (drm_drv_uses_atomic_modeset(dev)) @@ -892,7 +892,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, drm_framebuffer_put(fb); if (connector_set) { - for (i = 0; i < crtc_req->count_connectors; i++) { + for (i = 0; i < num_connectors; i++) { if (connector_set[i]) drm_connector_put(connector_set[i]); } @@ -904,6 +904,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, connector_set = NULL; fb = NULL; mode = NULL; + num_connectors = 0; DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); diff --git a/drivers/gpu/drm/drm_damage_helper.c b/drivers/gpu/drm/drm_damage_helper.c index d8b2955e88fd0a..afb02aae707b4f 100644 --- a/drivers/gpu/drm/drm_damage_helper.c +++ b/drivers/gpu/drm/drm_damage_helper.c @@ -241,7 +241,8 @@ drm_atomic_helper_damage_iter_init(struct drm_atomic_helper_damage_iter *iter, iter->plane_src.x2 = (src.x2 >> 16) + !!(src.x2 & 0xFFFF); iter->plane_src.y2 = (src.y2 >> 16) + !!(src.y2 & 0xFFFF); - if (!iter->clips || !drm_rect_equals(&state->src, &old_state->src)) { + if (!iter->clips || state->ignore_damage_clips || + !drm_rect_equals(&state->src, &old_state->src)) { iter->clips = NULL; iter->num_clips = 0; iter->full_update = true; diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c index 2de43ff3ce0a43..41b0682c638ef0 100644 --- a/drivers/gpu/drm/drm_debugfs.c +++ b/drivers/gpu/drm/drm_debugfs.c @@ -92,15 +92,17 @@ static int drm_clients_info(struct seq_file *m, void *data) */ mutex_lock(&dev->filelist_mutex); list_for_each_entry_reverse(priv, &dev->filelist, lhead) { - struct task_struct *task; bool is_current_master = drm_is_current_master(priv); + struct task_struct *task; + struct pid *pid; - rcu_read_lock(); /* locks pid_task()->comm */ - task = pid_task(priv->pid, PIDTYPE_TGID); + rcu_read_lock(); /* Locks priv->pid and pid_task()->comm! */ + pid = rcu_dereference(priv->pid); + task = pid_task(pid, PIDTYPE_TGID); uid = task ? __task_cred(task)->euid : GLOBAL_ROOT_UID; seq_printf(m, "%20s %5d %3d %c %c %5d %10u\n", task ? task->comm : "", - pid_vnr(priv->pid), + pid_vnr(pid), priv->minor->index, is_current_master ? 'y' : 'n', priv->authenticated ? 'y' : 'n', diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 3eda026ffac6a9..d453d710ef0c10 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include @@ -54,8 +55,7 @@ MODULE_AUTHOR("Gareth Hughes, Leif Delgass, José Fonseca, Jon Smirl"); MODULE_DESCRIPTION("DRM shared core routines"); MODULE_LICENSE("GPL and additional rights"); -static DEFINE_SPINLOCK(drm_minor_lock); -static struct idr drm_minors_idr; +DEFINE_XARRAY_ALLOC(drm_minors_xa); /* * If the drm core fails to init for whatever reason, @@ -83,6 +83,18 @@ DEFINE_STATIC_SRCU(drm_unplug_srcu); * registered and unregistered dynamically according to device-state. */ +static struct xarray *drm_minor_get_xa(enum drm_minor_type type) +{ + if (type == DRM_MINOR_PRIMARY || type == DRM_MINOR_RENDER) + return &drm_minors_xa; +#if IS_ENABLED(CONFIG_DRM_ACCEL) + else if (type == DRM_MINOR_ACCEL) + return &accel_minors_xa; +#endif + else + return ERR_PTR(-EOPNOTSUPP); +} + static struct drm_minor **drm_minor_get_slot(struct drm_device *dev, enum drm_minor_type type) { @@ -101,25 +113,31 @@ static struct drm_minor **drm_minor_get_slot(struct drm_device *dev, static void drm_minor_alloc_release(struct drm_device *dev, void *data) { struct drm_minor *minor = data; - unsigned long flags; WARN_ON(dev != minor->dev); put_device(minor->kdev); - if (minor->type == DRM_MINOR_ACCEL) { - accel_minor_remove(minor->index); - } else { - spin_lock_irqsave(&drm_minor_lock, flags); - idr_remove(&drm_minors_idr, minor->index); - spin_unlock_irqrestore(&drm_minor_lock, flags); - } + xa_erase(drm_minor_get_xa(minor->type), minor->index); } +/* + * DRM used to support 64 devices, for backwards compatibility we need to maintain the + * minor allocation scheme where minors 0-63 are primary nodes, 64-127 are control nodes, + * and 128-191 are render nodes. + * After reaching the limit, we're allocating minors dynamically - first-come, first-serve. + * Accel nodes are using a distinct major, so the minors are allocated in continuous 0-MAX + * range. + */ +#define DRM_MINOR_LIMIT(t) ({ \ + typeof(t) _t = (t); \ + _t == DRM_MINOR_ACCEL ? XA_LIMIT(0, ACCEL_MAX_MINORS) : XA_LIMIT(64 * _t, 64 * _t + 63); \ +}) +#define DRM_EXTENDED_MINOR_LIMIT XA_LIMIT(192, (1 << MINORBITS) - 1) + static int drm_minor_alloc(struct drm_device *dev, enum drm_minor_type type) { struct drm_minor *minor; - unsigned long flags; int r; minor = drmm_kzalloc(dev, sizeof(*minor), GFP_KERNEL); @@ -129,25 +147,14 @@ static int drm_minor_alloc(struct drm_device *dev, enum drm_minor_type type) minor->type = type; minor->dev = dev; - idr_preload(GFP_KERNEL); - if (type == DRM_MINOR_ACCEL) { - r = accel_minor_alloc(); - } else { - spin_lock_irqsave(&drm_minor_lock, flags); - r = idr_alloc(&drm_minors_idr, - NULL, - 64 * type, - 64 * (type + 1), - GFP_NOWAIT); - spin_unlock_irqrestore(&drm_minor_lock, flags); - } - idr_preload_end(); - + r = xa_alloc(drm_minor_get_xa(type), &minor->index, + NULL, DRM_MINOR_LIMIT(type), GFP_KERNEL); + if (r == -EBUSY && (type == DRM_MINOR_PRIMARY || type == DRM_MINOR_RENDER)) + r = xa_alloc(&drm_minors_xa, &minor->index, + NULL, DRM_EXTENDED_MINOR_LIMIT, GFP_KERNEL); if (r < 0) return r; - minor->index = r; - r = drmm_add_action_or_reset(dev, drm_minor_alloc_release, minor); if (r) return r; @@ -163,7 +170,7 @@ static int drm_minor_alloc(struct drm_device *dev, enum drm_minor_type type) static int drm_minor_register(struct drm_device *dev, enum drm_minor_type type) { struct drm_minor *minor; - unsigned long flags; + void *entry; int ret; DRM_DEBUG("\n"); @@ -187,13 +194,12 @@ static int drm_minor_register(struct drm_device *dev, enum drm_minor_type type) goto err_debugfs; /* replace NULL with @minor so lookups will succeed from now on */ - if (minor->type == DRM_MINOR_ACCEL) { - accel_minor_replace(minor, minor->index); - } else { - spin_lock_irqsave(&drm_minor_lock, flags); - idr_replace(&drm_minors_idr, minor, minor->index); - spin_unlock_irqrestore(&drm_minor_lock, flags); + entry = xa_store(drm_minor_get_xa(type), minor->index, minor, GFP_KERNEL); + if (xa_is_err(entry)) { + ret = xa_err(entry); + goto err_debugfs; } + WARN_ON(entry); DRM_DEBUG("new minor registered %d\n", minor->index); return 0; @@ -206,20 +212,13 @@ static int drm_minor_register(struct drm_device *dev, enum drm_minor_type type) static void drm_minor_unregister(struct drm_device *dev, enum drm_minor_type type) { struct drm_minor *minor; - unsigned long flags; minor = *drm_minor_get_slot(dev, type); if (!minor || !device_is_registered(minor->kdev)) return; /* replace @minor with NULL so lookups will fail from now on */ - if (minor->type == DRM_MINOR_ACCEL) { - accel_minor_replace(NULL, minor->index); - } else { - spin_lock_irqsave(&drm_minor_lock, flags); - idr_replace(&drm_minors_idr, NULL, minor->index); - spin_unlock_irqrestore(&drm_minor_lock, flags); - } + xa_store(drm_minor_get_xa(type), minor->index, NULL, GFP_KERNEL); device_del(minor->kdev); dev_set_drvdata(minor->kdev, NULL); /* safety belt */ @@ -235,16 +234,15 @@ static void drm_minor_unregister(struct drm_device *dev, enum drm_minor_type typ * minor->dev pointer will stay valid! However, the device may get unplugged and * unregistered while you hold the minor. */ -struct drm_minor *drm_minor_acquire(unsigned int minor_id) +struct drm_minor *drm_minor_acquire(struct xarray *minor_xa, unsigned int minor_id) { struct drm_minor *minor; - unsigned long flags; - spin_lock_irqsave(&drm_minor_lock, flags); - minor = idr_find(&drm_minors_idr, minor_id); + xa_lock(minor_xa); + minor = xa_load(minor_xa, minor_id); if (minor) drm_dev_get(minor->dev); - spin_unlock_irqrestore(&drm_minor_lock, flags); + xa_unlock(minor_xa); if (!minor) { return ERR_PTR(-ENODEV); @@ -940,8 +938,11 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags) goto err_minors; } - if (drm_core_check_feature(dev, DRIVER_MODESET)) - drm_modeset_register_all(dev); + if (drm_core_check_feature(dev, DRIVER_MODESET)) { + ret = drm_modeset_register_all(dev); + if (ret) + goto err_unload; + } DRM_INFO("Initialized %s %d.%d.%d %s for %s on minor %d\n", driver->name, driver->major, driver->minor, @@ -951,6 +952,9 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags) goto out_unlock; +err_unload: + if (dev->driver->unload) + dev->driver->unload(dev); err_minors: remove_compat_control_link(dev); drm_minor_unregister(dev, DRM_MINOR_ACCEL); @@ -1032,7 +1036,7 @@ static int drm_stub_open(struct inode *inode, struct file *filp) DRM_DEBUG("\n"); - minor = drm_minor_acquire(iminor(inode)); + minor = drm_minor_acquire(&drm_minors_xa, iminor(inode)); if (IS_ERR(minor)) return PTR_ERR(minor); @@ -1067,7 +1071,7 @@ static void drm_core_exit(void) unregister_chrdev(DRM_MAJOR, "drm"); debugfs_remove(drm_debugfs_root); drm_sysfs_destroy(); - idr_destroy(&drm_minors_idr); + WARN_ON(!xa_empty(&drm_minors_xa)); drm_connector_ida_destroy(); } @@ -1076,7 +1080,6 @@ static int __init drm_core_init(void) int ret; drm_connector_ida_init(); - idr_init(&drm_minors_idr); drm_memcpy_init_early(); ret = drm_sysfs_init(); diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 4b71040ae5be5c..ee3fab115c4b5b 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -2308,7 +2308,8 @@ int drm_edid_override_connector_update(struct drm_connector *connector) override = drm_edid_override_get(connector); if (override) { - num_modes = drm_edid_connector_update(connector, override); + if (drm_edid_connector_update(connector, override) == 0) + num_modes = drm_edid_connector_add_modes(connector); drm_edid_free(override); @@ -3499,11 +3500,19 @@ static struct drm_display_mode *drm_mode_detailed(struct drm_connector *connecto mode->vsync_end = mode->vsync_start + vsync_pulse_width; mode->vtotal = mode->vdisplay + vblank; - /* Some EDIDs have bogus h/vtotal values */ - if (mode->hsync_end > mode->htotal) - mode->htotal = mode->hsync_end + 1; - if (mode->vsync_end > mode->vtotal) - mode->vtotal = mode->vsync_end + 1; + /* Some EDIDs have bogus h/vsync_end values */ + if (mode->hsync_end > mode->htotal) { + drm_dbg_kms(dev, "[CONNECTOR:%d:%s] reducing hsync_end %d->%d\n", + connector->base.id, connector->name, + mode->hsync_end, mode->htotal); + mode->hsync_end = mode->htotal; + } + if (mode->vsync_end > mode->vtotal) { + drm_dbg_kms(dev, "[CONNECTOR:%d:%s] reducing vsync_end %d->%d\n", + connector->base.id, connector->name, + mode->vsync_end, mode->vtotal); + mode->vsync_end = mode->vtotal; + } drm_mode_do_interlace_quirk(mode, pt); @@ -7312,7 +7321,7 @@ static void drm_parse_tiled_block(struct drm_connector *connector, static bool displayid_is_tiled_block(const struct displayid_iter *iter, const struct displayid_block *block) { - return (displayid_version(iter) == DISPLAY_ID_STRUCTURE_VER_12 && + return (displayid_version(iter) < DISPLAY_ID_STRUCTURE_VER_20 && block->tag == DATA_BLOCK_TILED_DISPLAY) || (displayid_version(iter) == DISPLAY_ID_STRUCTURE_VER_20 && block->tag == DATA_BLOCK_2_TILED_DISPLAY_TOPOLOGY); diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index d612133e2cf7ec..618b045230336e 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -524,6 +524,9 @@ struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper) if (!info) return ERR_PTR(-ENOMEM); + if (!drm_leak_fbdev_smem) + info->flags |= FBINFO_HIDE_SMEM_START; + ret = fb_alloc_cmap(&info->cmap, 256, 0); if (ret) goto err_release; @@ -628,6 +631,17 @@ static void drm_fb_helper_add_damage_clip(struct drm_fb_helper *helper, u32 x, u static void drm_fb_helper_damage(struct drm_fb_helper *helper, u32 x, u32 y, u32 width, u32 height) { + /* + * This function may be invoked by panic() to flush the frame + * buffer, where all CPUs except the panic CPU are stopped. + * During the following schedule_work(), the panic CPU needs + * the worker_pool lock, which might be held by a stopped CPU, + * causing schedule_work() and panic() to block. Return early on + * oops_in_progress to prevent this blocking. + */ + if (oops_in_progress) + return; + drm_fb_helper_add_damage_clip(helper, x, y, width, height); schedule_work(&helper->damage_work); @@ -1860,9 +1874,6 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper) info = fb_helper->info; info->var.pixclock = 0; - if (!drm_leak_fbdev_smem) - info->flags |= FBINFO_HIDE_SMEM_START; - /* Need to drop locks to avoid recursive deadlock in * register_framebuffer. This is ok because the only thing left to do is * register the fbdev emulation instance in kernel_fb_helper_list. */ diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c index 6c9427bb4053ba..13cd754af311d1 100644 --- a/drivers/gpu/drm/drm_fbdev_dma.c +++ b/drivers/gpu/drm/drm_fbdev_dma.c @@ -130,7 +130,10 @@ static int drm_fbdev_dma_helper_fb_probe(struct drm_fb_helper *fb_helper, info->flags |= FBINFO_READS_FAST; /* signal caching */ info->screen_size = sizes->surface_height * fb->pitches[0]; info->screen_buffer = map.vaddr; - info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer)); + if (!(info->flags & FBINFO_HIDE_SMEM_START)) { + if (!drm_WARN_ON(dev, is_vmalloc_addr(info->screen_buffer))) + info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer)); + } info->fix.smem_len = info->screen_size; return 0; diff --git a/drivers/gpu/drm/drm_fbdev_generic.c b/drivers/gpu/drm/drm_fbdev_generic.c index d647d89764cb98..b4659cd6285ab6 100644 --- a/drivers/gpu/drm/drm_fbdev_generic.c +++ b/drivers/gpu/drm/drm_fbdev_generic.c @@ -113,7 +113,6 @@ static int drm_fbdev_generic_helper_fb_probe(struct drm_fb_helper *fb_helper, /* screen */ info->flags |= FBINFO_VIRTFB | FBINFO_READS_FAST; info->screen_buffer = screen_buffer; - info->fix.smem_start = page_to_phys(vmalloc_to_page(info->screen_buffer)); info->fix.smem_len = screen_size; /* deferred I/O */ diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 883d83bc0e3d5f..48af0e2960a226 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -160,7 +160,7 @@ struct drm_file *drm_file_alloc(struct drm_minor *minor) /* Get a unique identifier for fdinfo: */ file->client_id = atomic64_inc_return(&ident); - file->pid = get_pid(task_tgid(current)); + rcu_assign_pointer(file->pid, get_pid(task_tgid(current))); file->minor = minor; /* for compatibility root is always authenticated */ @@ -200,7 +200,7 @@ struct drm_file *drm_file_alloc(struct drm_minor *minor) drm_syncobj_release(file); if (drm_core_check_feature(dev, DRIVER_GEM)) drm_gem_release(dev, file); - put_pid(file->pid); + put_pid(rcu_access_pointer(file->pid)); kfree(file); return ERR_PTR(ret); @@ -291,7 +291,7 @@ void drm_file_free(struct drm_file *file) WARN_ON(!list_empty(&file->event_list)); - put_pid(file->pid); + put_pid(rcu_access_pointer(file->pid)); kfree(file); } @@ -413,7 +413,7 @@ int drm_open(struct inode *inode, struct file *filp) int retcode; int need_setup = 0; - minor = drm_minor_acquire(iminor(inode)); + minor = drm_minor_acquire(&drm_minors_xa, iminor(inode)); if (IS_ERR(minor)) return PTR_ERR(minor); @@ -505,6 +505,38 @@ int drm_release(struct inode *inode, struct file *filp) } EXPORT_SYMBOL(drm_release); +void drm_file_update_pid(struct drm_file *filp) +{ + struct drm_device *dev; + struct pid *pid, *old; + + /* + * Master nodes need to keep the original ownership in order for + * drm_master_check_perm to keep working correctly. (See comment in + * drm_auth.c.) + */ + if (filp->was_master) + return; + + pid = task_tgid(current); + + /* + * Quick unlocked check since the model is a single handover followed by + * exclusive repeated use. + */ + if (pid == rcu_access_pointer(filp->pid)) + return; + + dev = filp->minor->dev; + mutex_lock(&dev->filelist_mutex); + get_pid(pid); + old = rcu_replace_pointer(filp->pid, pid, 1); + mutex_unlock(&dev->filelist_mutex); + + synchronize_rcu(); + put_pid(old); +} + /** * drm_release_noglobal - release method for DRM file * @inode: device inode @@ -924,7 +956,7 @@ void drm_show_memory_stats(struct drm_printer *p, struct drm_file *file) { struct drm_gem_object *obj; struct drm_memory_stats status = {}; - enum drm_gem_object_status supported_status; + enum drm_gem_object_status supported_status = 0; int id; spin_lock(&file->table_lock); diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c index aff3746dedfb48..1955eaeba0ab7c 100644 --- a/drivers/gpu/drm/drm_framebuffer.c +++ b/drivers/gpu/drm/drm_framebuffer.c @@ -570,7 +570,7 @@ int drm_mode_getfb2_ioctl(struct drm_device *dev, struct drm_mode_fb_cmd2 *r = data; struct drm_framebuffer *fb; unsigned int i; - int ret; + int ret = 0; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EINVAL; diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index e435f986cd135b..1ff0678be7c75b 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -610,6 +610,9 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct return ret; } + if (is_cow_mapping(vma->vm_flags)) + return -EINVAL; + dma_resv_lock(shmem->base.resv, NULL); ret = drm_gem_shmem_get_pages(shmem); dma_resv_unlock(shmem->base.resv); diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index ba12acd551390b..0ef5fc2a61f194 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -77,10 +77,6 @@ void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv); void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv, uint32_t handle); -/* drm_drv.c */ -struct drm_minor *drm_minor_acquire(unsigned int minor_id); -void drm_minor_release(struct drm_minor *minor); - /* drm_managed.c */ void drm_managed_release(struct drm_device *dev); void drmm_add_final_kfree(struct drm_device *dev, void *container); diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index f03ffbacfe9b48..77590b0f38fa38 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -776,6 +776,9 @@ long drm_ioctl_kernel(struct file *file, drm_ioctl_t *func, void *kdata, struct drm_device *dev = file_priv->minor->dev; int retcode; + /* Update drm_file owner if fd was passed along. */ + drm_file_update_pid(file_priv); + if (drm_dev_is_unplugged(dev)) return -ENODEV; diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index 150fe155506809..94375c6a542564 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -510,8 +510,8 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, /* Handle leased objects, if any */ idr_init(&leases); if (object_count != 0) { - object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), - array_size(object_count, sizeof(__u32))); + object_ids = memdup_array_user(u64_to_user_ptr(cl->object_ids), + object_count, sizeof(__u32)); if (IS_ERR(object_ids)) { ret = PTR_ERR(object_ids); idr_destroy(&leases); diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 14201f73aab134..52a93149363b46 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -347,7 +347,8 @@ static int mipi_dsi_remove_device_fn(struct device *dev, void *priv) { struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev); - mipi_dsi_detach(dsi); + if (dsi->attached) + mipi_dsi_detach(dsi); mipi_dsi_device_unregister(dsi); return 0; @@ -370,11 +371,18 @@ EXPORT_SYMBOL(mipi_dsi_host_unregister); int mipi_dsi_attach(struct mipi_dsi_device *dsi) { const struct mipi_dsi_host_ops *ops = dsi->host->ops; + int ret; if (!ops || !ops->attach) return -ENOSYS; - return ops->attach(dsi->host, dsi); + ret = ops->attach(dsi->host, dsi); + if (ret) + return ret; + + dsi->attached = true; + + return 0; } EXPORT_SYMBOL(mipi_dsi_attach); @@ -386,9 +394,14 @@ int mipi_dsi_detach(struct mipi_dsi_device *dsi) { const struct mipi_dsi_host_ops *ops = dsi->host->ops; + if (WARN_ON(!dsi->attached)) + return -EINVAL; + if (!ops || !ops->detach) return -ENOSYS; + dsi->attached = false; + return ops->detach(dsi->host, dsi); } EXPORT_SYMBOL(mipi_dsi_detach); @@ -641,7 +654,7 @@ EXPORT_SYMBOL(mipi_dsi_set_maximum_return_packet_size); * * Return: 0 on success or a negative error code on failure. */ -ssize_t mipi_dsi_compression_mode(struct mipi_dsi_device *dsi, bool enable) +int mipi_dsi_compression_mode(struct mipi_dsi_device *dsi, bool enable) { /* Note: Needs updating for non-default PPS or algorithm */ u8 tx[2] = { enable << 0, 0 }; @@ -666,8 +679,8 @@ EXPORT_SYMBOL(mipi_dsi_compression_mode); * * Return: 0 on success or a negative error code on failure. */ -ssize_t mipi_dsi_picture_parameter_set(struct mipi_dsi_device *dsi, - const struct drm_dsc_picture_parameter_set *pps) +int mipi_dsi_picture_parameter_set(struct mipi_dsi_device *dsi, + const struct drm_dsc_picture_parameter_set *pps) { struct mipi_dsi_msg msg = { .channel = dsi->channel, diff --git a/drivers/gpu/drm/drm_modeset_helper.c b/drivers/gpu/drm/drm_modeset_helper.c index f858dfedf2cfcf..2c582020cb4237 100644 --- a/drivers/gpu/drm/drm_modeset_helper.c +++ b/drivers/gpu/drm/drm_modeset_helper.c @@ -193,13 +193,22 @@ int drm_mode_config_helper_suspend(struct drm_device *dev) if (!dev) return 0; + /* + * Don't disable polling if it was never initialized + */ + if (dev->mode_config.poll_enabled) + drm_kms_helper_poll_disable(dev); - drm_kms_helper_poll_disable(dev); drm_fb_helper_set_suspend_unlocked(dev->fb_helper, 1); state = drm_atomic_helper_suspend(dev); if (IS_ERR(state)) { drm_fb_helper_set_suspend_unlocked(dev->fb_helper, 0); - drm_kms_helper_poll_enable(dev); + /* + * Don't enable polling if it was never initialized + */ + if (dev->mode_config.poll_enabled) + drm_kms_helper_poll_enable(dev); + return PTR_ERR(state); } @@ -239,7 +248,11 @@ int drm_mode_config_helper_resume(struct drm_device *dev) dev->mode_config.suspend_state = NULL; drm_fb_helper_set_suspend_unlocked(dev->fb_helper, 0); - drm_kms_helper_poll_enable(dev); + /* + * Don't enable polling if it is not initialized + */ + if (dev->mode_config.poll_enabled) + drm_kms_helper_poll_enable(dev); return ret; } diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c index e814020bbcd3b3..cfbe020de54e01 100644 --- a/drivers/gpu/drm/drm_panel.c +++ b/drivers/gpu/drm/drm_panel.c @@ -274,19 +274,24 @@ EXPORT_SYMBOL(drm_panel_disable); * The modes probed from the panel are automatically added to the connector * that the panel is attached to. * - * Return: The number of modes available from the panel on success or a - * negative error code on failure. + * Return: The number of modes available from the panel on success, or 0 on + * failure (no modes). */ int drm_panel_get_modes(struct drm_panel *panel, struct drm_connector *connector) { if (!panel) - return -EINVAL; + return 0; - if (panel->funcs && panel->funcs->get_modes) - return panel->funcs->get_modes(panel, connector); + if (panel->funcs && panel->funcs->get_modes) { + int num; - return -EOPNOTSUPP; + num = panel->funcs->get_modes(panel, connector); + if (num > 0) + return num; + } + + return 0; } EXPORT_SYMBOL(drm_panel_get_modes); diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index d5c15292ae9378..5b2506c65e9520 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -117,6 +117,12 @@ static const struct drm_dmi_panel_orientation_data lcd1080x1920_leftside_up = { .orientation = DRM_MODE_PANEL_ORIENTATION_LEFT_UP, }; +static const struct drm_dmi_panel_orientation_data lcd1080x1920_rightside_up = { + .width = 1080, + .height = 1920, + .orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP, +}; + static const struct drm_dmi_panel_orientation_data lcd1200x1920_rightside_up = { .width = 1200, .height = 1920, @@ -196,6 +202,24 @@ static const struct dmi_system_id orientation_data[] = { DMI_MATCH(DMI_BOARD_NAME, "NEXT"), }, .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* AYA NEO KUN */ + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AYANEO"), + DMI_MATCH(DMI_BOARD_NAME, "KUN"), + }, + .driver_data = (void *)&lcd1600x2560_rightside_up, + }, { /* AYN Loki Max */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ayn"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Loki Max"), + }, + .driver_data = (void *)&lcd1080x1920_leftside_up, + }, { /* AYN Loki Zero */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ayn"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Loki Zero"), + }, + .driver_data = (void *)&lcd1080x1920_leftside_up, }, { /* Chuwi HiBook (CWI514) */ .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Hampoo"), @@ -279,6 +303,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "G1618-03") }, .driver_data = (void *)&lcd720x1280_rightside_up, + }, { /* GPD Win Mini */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "GPD"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "G1617-01") + }, + .driver_data = (void *)&lcd1080x1920_rightside_up, }, { /* I.T.Works TW891 */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."), @@ -336,6 +366,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "IdeaPad Duet 3 10IGL5"), }, .driver_data = (void *)&lcd1200x1920_rightside_up, + }, { /* Lenovo Legion Go 8APU1 */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Legion Go 8APU1"), + }, + .driver_data = (void *)&lcd1600x2560_leftside_up, }, { /* Lenovo Yoga Book X90F / X90L */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), @@ -390,6 +426,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "ONE XPLAYER"), }, .driver_data = (void *)&lcd1600x2560_leftside_up, + }, { /* OrangePi Neo */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "OrangePi"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "NEO-01"), + }, + .driver_data = (void *)&lcd1200x1920_rightside_up, }, { /* Samsung GalaxyBook 10.6 */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), @@ -403,6 +445,13 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "1"), }, .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* Valve Steam Deck */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Valve"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Galileo"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "1"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* VIOS LTH17 */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "VIOS"), diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index 24e7998d17313e..311e179904a2ab 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -678,6 +678,19 @@ int drm_mode_getplane_res(struct drm_device *dev, void *data, !file_priv->universal_planes) continue; + /* + * If we're running on a virtualized driver then, + * unless userspace advertizes support for the + * virtualized cursor plane, disable cursor planes + * because they'll be broken due to missing cursor + * hotspot info. + */ + if (plane->type == DRM_PLANE_TYPE_CURSOR && + drm_core_check_feature(dev, DRIVER_CURSOR_HOTSPOT) && + file_priv->atomic && + !file_priv->supports_virtualized_cursor_plane) + continue; + if (drm_lease_held(file_priv, plane->base.id)) { if (count < plane_resp->count_planes && put_user(plane->base.id, plane_ptr + count)) @@ -1387,6 +1400,7 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev, out: if (fb) drm_framebuffer_put(fb); + fb = NULL; if (plane->old_fb) drm_framebuffer_put(plane->old_fb); plane->old_fb = NULL; diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 63b709a67471b9..03bd3c7bd0dc2c 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -278,7 +278,7 @@ void drm_gem_dmabuf_release(struct dma_buf *dma_buf) } EXPORT_SYMBOL(drm_gem_dmabuf_release); -/* +/** * drm_gem_prime_fd_to_handle - PRIME import function for GEM drivers * @dev: drm_device to import into * @file_priv: drm file-private structure @@ -292,9 +292,9 @@ EXPORT_SYMBOL(drm_gem_dmabuf_release); * * Returns 0 on success or a negative error code on failure. */ -static int drm_gem_prime_fd_to_handle(struct drm_device *dev, - struct drm_file *file_priv, int prime_fd, - uint32_t *handle) +int drm_gem_prime_fd_to_handle(struct drm_device *dev, + struct drm_file *file_priv, int prime_fd, + uint32_t *handle) { struct dma_buf *dma_buf; struct drm_gem_object *obj; @@ -360,6 +360,7 @@ static int drm_gem_prime_fd_to_handle(struct drm_device *dev, dma_buf_put(dma_buf); return ret; } +EXPORT_SYMBOL(drm_gem_prime_fd_to_handle); int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) @@ -408,7 +409,7 @@ static struct dma_buf *export_and_register_object(struct drm_device *dev, return dmabuf; } -/* +/** * drm_gem_prime_handle_to_fd - PRIME export function for GEM drivers * @dev: dev to export the buffer from * @file_priv: drm file-private structure @@ -421,10 +422,10 @@ static struct dma_buf *export_and_register_object(struct drm_device *dev, * The actual exporting from GEM object to a dma-buf is done through the * &drm_gem_object_funcs.export callback. */ -static int drm_gem_prime_handle_to_fd(struct drm_device *dev, - struct drm_file *file_priv, uint32_t handle, - uint32_t flags, - int *prime_fd) +int drm_gem_prime_handle_to_fd(struct drm_device *dev, + struct drm_file *file_priv, uint32_t handle, + uint32_t flags, + int *prime_fd) { struct drm_gem_object *obj; int ret = 0; @@ -506,6 +507,7 @@ static int drm_gem_prime_handle_to_fd(struct drm_device *dev, return ret; } +EXPORT_SYMBOL(drm_gem_prime_handle_to_fd); int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) @@ -580,7 +582,12 @@ int drm_gem_map_attach(struct dma_buf *dma_buf, { struct drm_gem_object *obj = dma_buf->priv; - if (!obj->funcs->get_sg_table) + /* + * drm_gem_map_dma_buf() requires obj->get_sg_table(), but drivers + * that implement their own ->map_dma_buf() do not. + */ + if (dma_buf->ops->map_dma_buf == drm_gem_map_dma_buf && + !obj->funcs->get_sg_table) return -ENOSYS; return drm_gem_pin(obj); @@ -818,7 +825,7 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev, if (max_segment == 0) max_segment = UINT_MAX; err = sg_alloc_table_from_pages_segment(sg, pages, nr_pages, 0, - nr_pages << PAGE_SHIFT, + (unsigned long)nr_pages << PAGE_SHIFT, max_segment, GFP_KERNEL); if (err) { kfree(sg); @@ -864,9 +871,9 @@ EXPORT_SYMBOL(drm_prime_get_contiguous_size); * @obj: GEM object to export * @flags: flags like DRM_CLOEXEC and DRM_RDWR * - * This is the implementation of the &drm_gem_object_funcs.export functions - * for GEM drivers using the PRIME helpers. It is used as the default for - * drivers that do not set their own. + * This is the implementation of the &drm_gem_object_funcs.export functions for GEM drivers + * using the PRIME helpers. It is used as the default in + * drm_gem_prime_handle_to_fd(). */ struct dma_buf *drm_gem_prime_export(struct drm_gem_object *obj, int flags) @@ -962,9 +969,10 @@ EXPORT_SYMBOL(drm_gem_prime_import_dev); * @dev: drm_device to import into * @dma_buf: dma-buf object to import * - * This is the implementation of the gem_prime_import functions for GEM - * drivers using the PRIME helpers. It is the default for drivers that do - * not set their own &drm_driver.gem_prime_import. + * This is the implementation of the gem_prime_import functions for GEM drivers + * using the PRIME helpers. Drivers can use this as their + * &drm_driver.gem_prime_import implementation. It is used as the default + * implementation in drm_gem_prime_fd_to_handle(). * * Drivers must arrange to call drm_prime_gem_destroy() from their * &drm_gem_object_funcs.free hook when using this function. diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index 5b93c11895bb1e..aab76334083e8a 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -100,8 +100,9 @@ void __drm_puts_coredump(struct drm_printer *p, const char *str) copy = iterator->remain; /* Copy out the bit of the string that we need */ - memcpy(iterator->data, - str + (iterator->start - iterator->offset), copy); + if (iterator->data) + memcpy(iterator->data, + str + (iterator->start - iterator->offset), copy); iterator->offset = iterator->start + copy; iterator->remain -= copy; @@ -110,7 +111,8 @@ void __drm_puts_coredump(struct drm_printer *p, const char *str) len = min_t(ssize_t, strlen(str), iterator->remain); - memcpy(iterator->data + pos, str, len); + if (iterator->data) + memcpy(iterator->data + pos, str, len); iterator->offset += len; iterator->remain -= len; @@ -140,8 +142,9 @@ void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf) if ((iterator->offset >= iterator->start) && (len < iterator->remain)) { ssize_t pos = iterator->offset - iterator->start; - snprintf(((char *) iterator->data) + pos, - iterator->remain, "%pV", vaf); + if (iterator->data) + snprintf(((char *) iterator->data) + pos, + iterator->remain, "%pV", vaf); iterator->offset += len; iterator->remain -= len; diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index 3f479483d7d80f..c90afb5d089871 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -293,14 +293,17 @@ static void reschedule_output_poll_work(struct drm_device *dev) * Drivers can call this helper from their device resume implementation. It is * not an error to call this even when output polling isn't enabled. * + * If device polling was never initialized before, this call will trigger a + * warning and return. + * * Note that calls to enable and disable polling must be strictly ordered, which * is automatically the case when they're only call from suspend/resume * callbacks. */ void drm_kms_helper_poll_enable(struct drm_device *dev) { - if (!dev->mode_config.poll_enabled || !drm_kms_helper_poll || - dev->mode_config.poll_running) + if (drm_WARN_ON_ONCE(dev, !dev->mode_config.poll_enabled) || + !drm_kms_helper_poll || dev->mode_config.poll_running) return; if (drm_kms_helper_enable_hpd(dev) || @@ -419,6 +422,13 @@ static int drm_helper_probe_get_modes(struct drm_connector *connector) count = connector_funcs->get_modes(connector); + /* The .get_modes() callback should not return negative values. */ + if (count < 0) { + drm_err(connector->dev, ".get_modes() returned %pe\n", + ERR_PTR(count)); + count = 0; + } + /* * Fallback for when DDC probe failed in drm_get_edid() and thus skipped * override/firmware EDID. @@ -619,8 +629,12 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector, 0); } - /* Re-enable polling in case the global poll config changed. */ - drm_kms_helper_poll_enable(dev); + /* + * Re-enable polling in case the global poll config changed but polling + * is still initialized. + */ + if (dev->mode_config.poll_enabled) + drm_kms_helper_poll_enable(dev); if (connector->status == connector_status_disconnected) { DRM_DEBUG_KMS("[CONNECTOR:%d:%s] disconnected\n", @@ -871,12 +885,18 @@ EXPORT_SYMBOL(drm_kms_helper_is_poll_worker); * not an error to call this even when output polling isn't enabled or already * disabled. Polling is re-enabled by calling drm_kms_helper_poll_enable(). * + * If however, the polling was never initialized, this call will trigger a + * warning and return + * * Note that calls to enable and disable polling must be strictly ordered, which * is automatically the case when they're only call from suspend/resume * callbacks. */ void drm_kms_helper_poll_disable(struct drm_device *dev) { + if (drm_WARN_ON(dev, !dev->mode_config.poll_enabled)) + return; + if (dev->mode_config.poll_running) drm_kms_helper_disable_hpd(dev); diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index f7003d1ec5ef1e..7b4ed5ca0a9bd2 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -1034,7 +1034,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, uint64_t *points; uint32_t signaled_count, i; - if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) + if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) lockdep_assert_none_held_once(); points = kmalloc_array(count, sizeof(*points), GFP_KERNEL); @@ -1069,7 +1070,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, fence = drm_syncobj_fence_get(syncobjs[i]); if (!fence || dma_fence_chain_find_seqno(&fence, points[i])) { dma_fence_put(fence); - if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { + if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) { continue; } else { timeout = -EINVAL; @@ -1102,7 +1104,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, * fallthough and try a 0 timeout wait! */ - if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { + if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) { for (i = 0; i < count; ++i) drm_syncobj_fence_add_wait(syncobjs[i], &entries[i]); } @@ -1377,10 +1380,21 @@ syncobj_eventfd_entry_func(struct drm_syncobj *syncobj, /* This happens inside the syncobj lock */ fence = dma_fence_get(rcu_dereference_protected(syncobj->fence, 1)); + if (!fence) + return; + ret = dma_fence_chain_find_seqno(&fence, entry->point); - if (ret != 0 || !fence) { + if (ret != 0) { + /* The given seqno has not been submitted yet. */ dma_fence_put(fence); return; + } else if (!fence) { + /* If dma_fence_chain_find_seqno returns 0 but sets the fence + * to NULL, it implies that the given seqno is signaled and a + * later seqno has already been submitted. Assign a stub fence + * so that the eventfd still gets signaled below. + */ + fence = dma_fence_get_stub(); } list_del_init(&entry->node); @@ -1407,6 +1421,7 @@ drm_syncobj_eventfd_ioctl(struct drm_device *dev, void *data, struct drm_syncobj *syncobj; struct eventfd_ctx *ev_fd_ctx; struct syncobj_eventfd_entry *entry; + int ret; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) return -EOPNOTSUPP; @@ -1422,13 +1437,15 @@ drm_syncobj_eventfd_ioctl(struct drm_device *dev, void *data, return -ENOENT; ev_fd_ctx = eventfd_ctx_fdget(args->fd); - if (IS_ERR(ev_fd_ctx)) - return PTR_ERR(ev_fd_ctx); + if (IS_ERR(ev_fd_ctx)) { + ret = PTR_ERR(ev_fd_ctx); + goto err_fdget; + } entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) { - eventfd_ctx_put(ev_fd_ctx); - return -ENOMEM; + ret = -ENOMEM; + goto err_kzalloc; } entry->syncobj = syncobj; entry->ev_fd_ctx = ev_fd_ctx; @@ -1439,6 +1456,12 @@ drm_syncobj_eventfd_ioctl(struct drm_device *dev, void *data, drm_syncobj_put(syncobj); return 0; + +err_kzalloc: + eventfd_ctx_put(ev_fd_ctx); +err_fdget: + drm_syncobj_put(syncobj); + return ret; } int diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index a8d3fa81e4ec5d..f9bc837e22bddc 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -494,7 +494,7 @@ static const struct drm_driver etnaviv_drm_driver = { .desc = "etnaviv DRM", .date = "20151214", .major = 1, - .minor = 3, + .minor = 4, }; /* diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index b5f73502e3dd42..69fccbcd92c622 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -356,9 +356,11 @@ static void *etnaviv_gem_vmap_impl(struct etnaviv_gem_object *obj) static inline enum dma_data_direction etnaviv_op_to_dma_dir(u32 op) { - if (op & ETNA_PREP_READ) + op &= ETNA_PREP_READ | ETNA_PREP_WRITE; + + if (op == ETNA_PREP_READ) return DMA_FROM_DEVICE; - else if (op & ETNA_PREP_WRITE) + else if (op == ETNA_PREP_WRITE) return DMA_TO_DEVICE; else return DMA_BIDIRECTIONAL; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 9276756e1397d3..371e1f2733f6fb 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -632,8 +632,8 @@ static void etnaviv_gpu_enable_mlcg(struct etnaviv_gpu *gpu) /* Disable TX clock gating on affected core revisions. */ if (etnaviv_is_model_rev(gpu, GC4000, 0x5222) || etnaviv_is_model_rev(gpu, GC2000, 0x5108) || - etnaviv_is_model_rev(gpu, GC2000, 0x6202) || - etnaviv_is_model_rev(gpu, GC2000, 0x6203)) + etnaviv_is_model_rev(gpu, GC7000, 0x6202) || + etnaviv_is_model_rev(gpu, GC7000, 0x6203)) pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_TX; /* Disable SE and RA clock gating on affected core revisions. */ diff --git a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c index 67201242438bed..8665f2658d51b3 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c @@ -265,6 +265,9 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { bool etnaviv_fill_identity_from_hwdb(struct etnaviv_gpu *gpu) { struct etnaviv_chip_identity *ident = &gpu->identity; + const u32 product_id = ident->product_id; + const u32 customer_id = ident->customer_id; + const u32 eco_id = ident->eco_id; int i; for (i = 0; i < ARRAY_SIZE(etnaviv_chip_identities); i++) { @@ -278,6 +281,12 @@ bool etnaviv_fill_identity_from_hwdb(struct etnaviv_gpu *gpu) etnaviv_chip_identities[i].eco_id == ~0U)) { memcpy(ident, &etnaviv_chip_identities[i], sizeof(*ident)); + + /* Restore some id values as ~0U aka 'don't care' might been used. */ + ident->product_id = product_id; + ident->customer_id = customer_id; + ident->eco_id = eco_id; + return true; } } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 345fec6cb1a4c1..97e406d9ac06f4 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -38,9 +38,6 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job u32 dma_addr; int change; - /* block scheduler */ - drm_sched_stop(&gpu->sched, sched_job); - /* * If the GPU managed to complete this jobs fence, the timout is * spurious. Bail out. @@ -63,6 +60,9 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job goto out_no_timeout; } + /* block scheduler */ + drm_sched_stop(&gpu->sched, sched_job); + if(sched_job) drm_sched_increase_karma(sched_job); @@ -76,8 +76,7 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job return DRM_GPU_SCHED_STAT_NOMINAL; out_no_timeout: - /* restart scheduler after GPU is usable again */ - drm_sched_start(&gpu->sched, true); + list_add(&sched_job->list, &sched_job->sched->pending_list); return DRM_GPU_SCHED_STAT_NOMINAL; } diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 4d986077738b9b..bce027552474a6 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -319,9 +319,9 @@ static void decon_win_set_bldmod(struct decon_context *ctx, unsigned int win, static void decon_win_set_pixfmt(struct decon_context *ctx, unsigned int win, struct drm_framebuffer *fb) { - struct exynos_drm_plane plane = ctx->planes[win]; + struct exynos_drm_plane *plane = &ctx->planes[win]; struct exynos_drm_plane_state *state = - to_exynos_plane_state(plane.base.state); + to_exynos_plane_state(plane->base.state); unsigned int alpha = state->base.alpha; unsigned int pixel_alpha; unsigned long val; diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c index 3404ec1367fb92..71ee824c4140bd 100644 --- a/drivers/gpu/drm/exynos/exynos_dp.c +++ b/drivers/gpu/drm/exynos/exynos_dp.c @@ -288,7 +288,6 @@ struct platform_driver dp_driver = { .remove = exynos_dp_remove, .driver = { .name = "exynos-dp", - .owner = THIS_MODULE, .pm = pm_ptr(&exynos_dp_pm_ops), .of_match_table = exynos_dp_match, }, diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c index a971590b813230..e2c7373f20c6b7 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dma.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c @@ -107,18 +107,16 @@ int exynos_drm_register_dma(struct drm_device *drm, struct device *dev, return 0; if (!priv->mapping) { - void *mapping; + void *mapping = NULL; if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) mapping = arm_iommu_create_mapping(&platform_bus_type, EXYNOS_DEV_ADDR_START, EXYNOS_DEV_ADDR_SIZE); else if (IS_ENABLED(CONFIG_IOMMU_DMA)) mapping = iommu_get_domain_for_dev(priv->dma_dev); - else - mapping = ERR_PTR(-ENODEV); - if (IS_ERR(mapping)) - return PTR_ERR(mapping); + if (!mapping) + return -ENODEV; priv->mapping = mapping; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index 8399256cb5c9d7..5380fb6c55ae1e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -300,6 +300,7 @@ static int exynos_drm_bind(struct device *dev) drm_mode_config_cleanup(drm); exynos_drm_cleanup_dma(drm); kfree(private); + dev_set_drvdata(dev, NULL); err_free_drm: drm_dev_put(drm); @@ -313,6 +314,7 @@ static void exynos_drm_unbind(struct device *dev) drm_dev_unregister(drm); drm_kms_helper_poll_fini(drm); + drm_atomic_helper_shutdown(drm); component_unbind_all(drm->dev, drm); drm_mode_config_cleanup(drm); @@ -350,9 +352,18 @@ static int exynos_drm_platform_remove(struct platform_device *pdev) return 0; } +static void exynos_drm_platform_shutdown(struct platform_device *pdev) +{ + struct drm_device *drm = platform_get_drvdata(pdev); + + if (drm) + drm_atomic_helper_shutdown(drm); +} + static struct platform_driver exynos_drm_platform_driver = { .probe = exynos_drm_platform_probe, .remove = exynos_drm_platform_remove, + .shutdown = exynos_drm_platform_shutdown, .driver = { .name = "exynos-drm", .pm = &exynos_drm_pm_ops, diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 8dde7b1e9b35d9..5bdc246f5fad09 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -661,9 +661,9 @@ static void fimd_win_set_bldmod(struct fimd_context *ctx, unsigned int win, static void fimd_win_set_pixfmt(struct fimd_context *ctx, unsigned int win, struct drm_framebuffer *fb, int width) { - struct exynos_drm_plane plane = ctx->planes[win]; + struct exynos_drm_plane *plane = &ctx->planes[win]; struct exynos_drm_plane_state *state = - to_exynos_plane_state(plane.base.state); + to_exynos_plane_state(plane->base.state); uint32_t pixel_format = fb->format->format; unsigned int alpha = state->base.alpha; u32 val = WINCONx_ENWIN; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 34cdabc30b4f5e..1456abd5b9dde1 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -1173,7 +1173,7 @@ static int gsc_bind(struct device *dev, struct device *master, void *data) struct exynos_drm_ipp *ipp = &ctx->ipp; ctx->drm_dev = drm_dev; - ctx->drm_dev = drm_dev; + ipp->drm_dev = drm_dev; exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, @@ -1342,7 +1342,7 @@ static int __maybe_unused gsc_runtime_resume(struct device *dev) for (i = 0; i < ctx->num_clocks; i++) { ret = clk_prepare_enable(ctx->clocks[i]); if (ret) { - while (--i > 0) + while (--i >= 0) clk_disable_unprepare(ctx->clocks[i]); return ret; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index f5e1adfcaa514e..e17f9c5c9c90e6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -309,6 +309,7 @@ static int vidi_get_modes(struct drm_connector *connector) struct vidi_context *ctx = ctx_from_connector(connector); struct edid *edid; int edid_len; + int count; /* * the edid data comes from user side and it would be set @@ -316,19 +317,23 @@ static int vidi_get_modes(struct drm_connector *connector) */ if (!ctx->raw_edid) { DRM_DEV_DEBUG_KMS(ctx->dev, "raw_edid is null.\n"); - return -EFAULT; + return 0; } edid_len = (1 + ctx->raw_edid->extensions) * EDID_LENGTH; edid = kmemdup(ctx->raw_edid, edid_len, GFP_KERNEL); if (!edid) { DRM_DEV_DEBUG_KMS(ctx->dev, "failed to allocate edid\n"); - return -ENOMEM; + return 0; } drm_connector_update_edid_property(connector, edid); - return drm_add_edid_modes(connector, edid); + count = drm_add_edid_modes(connector, edid); + + kfree(edid); + + return count; } static const struct drm_connector_helper_funcs vidi_connector_helper_funcs = { diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index f3aaa4ea3e6820..906133331a4424 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -887,11 +887,11 @@ static int hdmi_get_modes(struct drm_connector *connector) int ret; if (!hdata->ddc_adpt) - return -ENODEV; + goto no_edid; edid = drm_get_edid(connector, hdata->ddc_adpt); if (!edid) - return -ENODEV; + goto no_edid; hdata->dvi_mode = !connector->display_info.is_hdmi; DRM_DEV_DEBUG_KMS(hdata->dev, "%s : width[%d] x height[%d]\n", @@ -906,6 +906,9 @@ static int hdmi_get_modes(struct drm_connector *connector) kfree(edid); return ret; + +no_edid: + return drm_add_modes_noedid(connector, 640, 480); } static int hdmi_find_phy_conf(struct hdmi_context *hdata, u32 pixel_clock) @@ -1861,6 +1864,8 @@ static int hdmi_bind(struct device *dev, struct device *master, void *data) return ret; crtc = exynos_drm_crtc_get_by_type(drm_dev, EXYNOS_DISPLAY_TYPE_HDMI); + if (IS_ERR(crtc)) + return PTR_ERR(crtc); crtc->pipe_clk = &hdata->phy_clk; ret = hdmi_create_connector(encoder); diff --git a/drivers/gpu/drm/gma500/Makefile b/drivers/gpu/drm/gma500/Makefile index 4f302cd5e1a6ca..58fed80c7392a0 100644 --- a/drivers/gpu/drm/gma500/Makefile +++ b/drivers/gpu/drm/gma500/Makefile @@ -34,7 +34,6 @@ gma500_gfx-y += \ psb_intel_lvds.o \ psb_intel_modes.o \ psb_intel_sdvo.o \ - psb_lid.o \ psb_irq.o gma500_gfx-$(CONFIG_ACPI) += opregion.o diff --git a/drivers/gpu/drm/gma500/cdv_intel_lvds.c b/drivers/gpu/drm/gma500/cdv_intel_lvds.c index f08a6803dc1849..3adc2c9ab72da0 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c +++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c @@ -311,6 +311,9 @@ static int cdv_intel_lvds_get_modes(struct drm_connector *connector) if (mode_dev->panel_fixed_mode != NULL) { struct drm_display_mode *mode = drm_mode_duplicate(dev, mode_dev->panel_fixed_mode); + if (!mode) + return 0; + drm_mode_probed_add(connector, mode); return 1; } diff --git a/drivers/gpu/drm/gma500/psb_device.c b/drivers/gpu/drm/gma500/psb_device.c index dcfcd7b89d4a1d..6dece8f0e380f7 100644 --- a/drivers/gpu/drm/gma500/psb_device.c +++ b/drivers/gpu/drm/gma500/psb_device.c @@ -73,8 +73,7 @@ static int psb_backlight_setup(struct drm_device *dev) } psb_intel_lvds_set_brightness(dev, PSB_MAX_BRIGHTNESS); - /* This must occur after the backlight is properly initialised */ - psb_lid_timer_init(dev_priv); + return 0; } @@ -259,8 +258,6 @@ static int psb_chip_setup(struct drm_device *dev) static void psb_chip_teardown(struct drm_device *dev) { - struct drm_psb_private *dev_priv = to_drm_psb_private(dev); - psb_lid_timer_takedown(dev_priv); gma_intel_teardown_gmbus(dev); } diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h index f7f709df99b498..bb1cd45c085cd6 100644 --- a/drivers/gpu/drm/gma500/psb_drv.h +++ b/drivers/gpu/drm/gma500/psb_drv.h @@ -170,7 +170,6 @@ #define PSB_NUM_VBLANKS 2 #define PSB_WATCHDOG_DELAY (HZ * 2) -#define PSB_LID_DELAY (HZ / 10) #define PSB_MAX_BRIGHTNESS 100 @@ -424,6 +423,7 @@ struct drm_psb_private { uint32_t pipestat[PSB_NUM_PIPE]; spinlock_t irqmask_lock; + bool irq_enabled; /* Power */ bool pm_initialized; @@ -498,11 +498,7 @@ struct drm_psb_private { /* Hotplug handling */ struct work_struct hotplug_work; - /* LID-Switch */ - spinlock_t lid_lock; - struct timer_list lid_timer; struct psb_intel_opregion opregion; - u32 lid_last_state; /* Watchdog */ uint32_t apm_reg; @@ -598,10 +594,6 @@ struct psb_ops { int i2c_bus; /* I2C bus identifier for Moorestown */ }; -/* psb_lid.c */ -extern void psb_lid_timer_init(struct drm_psb_private *dev_priv); -extern void psb_lid_timer_takedown(struct drm_psb_private *dev_priv); - /* modesetting */ extern void psb_modeset_init(struct drm_device *dev); extern void psb_modeset_cleanup(struct drm_device *dev); diff --git a/drivers/gpu/drm/gma500/psb_intel_lvds.c b/drivers/gpu/drm/gma500/psb_intel_lvds.c index 8486de230ec91b..8d1be94a443b24 100644 --- a/drivers/gpu/drm/gma500/psb_intel_lvds.c +++ b/drivers/gpu/drm/gma500/psb_intel_lvds.c @@ -504,6 +504,9 @@ static int psb_intel_lvds_get_modes(struct drm_connector *connector) if (mode_dev->panel_fixed_mode != NULL) { struct drm_display_mode *mode = drm_mode_duplicate(dev, mode_dev->panel_fixed_mode); + if (!mode) + return 0; + drm_mode_probed_add(connector, mode); return 1; } diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c index 343c51250207d8..7bbb79b0497d8d 100644 --- a/drivers/gpu/drm/gma500/psb_irq.c +++ b/drivers/gpu/drm/gma500/psb_irq.c @@ -327,6 +327,8 @@ int gma_irq_install(struct drm_device *dev) gma_irq_postinstall(dev); + dev_priv->irq_enabled = true; + return 0; } @@ -337,6 +339,9 @@ void gma_irq_uninstall(struct drm_device *dev) unsigned long irqflags; unsigned int i; + if (!dev_priv->irq_enabled) + return; + spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags); if (dev_priv->ops->hotplug_enable) diff --git a/drivers/gpu/drm/gma500/psb_lid.c b/drivers/gpu/drm/gma500/psb_lid.c deleted file mode 100644 index 58a7fe39263601..00000000000000 --- a/drivers/gpu/drm/gma500/psb_lid.c +++ /dev/null @@ -1,80 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/************************************************************************** - * Copyright (c) 2007, Intel Corporation. - * - * Authors: Thomas Hellstrom - **************************************************************************/ - -#include - -#include "psb_drv.h" -#include "psb_intel_reg.h" -#include "psb_reg.h" - -static void psb_lid_timer_func(struct timer_list *t) -{ - struct drm_psb_private *dev_priv = from_timer(dev_priv, t, lid_timer); - struct drm_device *dev = (struct drm_device *)&dev_priv->dev; - struct timer_list *lid_timer = &dev_priv->lid_timer; - unsigned long irq_flags; - u32 __iomem *lid_state = dev_priv->opregion.lid_state; - u32 pp_status; - - if (readl(lid_state) == dev_priv->lid_last_state) - goto lid_timer_schedule; - - if ((readl(lid_state)) & 0x01) { - /*lid state is open*/ - REG_WRITE(PP_CONTROL, REG_READ(PP_CONTROL) | POWER_TARGET_ON); - do { - pp_status = REG_READ(PP_STATUS); - } while ((pp_status & PP_ON) == 0 && - (pp_status & PP_SEQUENCE_MASK) != 0); - - if (REG_READ(PP_STATUS) & PP_ON) { - /*FIXME: should be backlight level before*/ - psb_intel_lvds_set_brightness(dev, 100); - } else { - DRM_DEBUG("LVDS panel never powered up"); - return; - } - } else { - psb_intel_lvds_set_brightness(dev, 0); - - REG_WRITE(PP_CONTROL, REG_READ(PP_CONTROL) & ~POWER_TARGET_ON); - do { - pp_status = REG_READ(PP_STATUS); - } while ((pp_status & PP_ON) == 0); - } - dev_priv->lid_last_state = readl(lid_state); - -lid_timer_schedule: - spin_lock_irqsave(&dev_priv->lid_lock, irq_flags); - if (!timer_pending(lid_timer)) { - lid_timer->expires = jiffies + PSB_LID_DELAY; - add_timer(lid_timer); - } - spin_unlock_irqrestore(&dev_priv->lid_lock, irq_flags); -} - -void psb_lid_timer_init(struct drm_psb_private *dev_priv) -{ - struct timer_list *lid_timer = &dev_priv->lid_timer; - unsigned long irq_flags; - - spin_lock_init(&dev_priv->lid_lock); - spin_lock_irqsave(&dev_priv->lid_lock, irq_flags); - - timer_setup(lid_timer, psb_lid_timer_func, 0); - - lid_timer->expires = jiffies + PSB_LID_DELAY; - - add_timer(lid_timer); - spin_unlock_irqrestore(&dev_priv->lid_lock, irq_flags); -} - -void psb_lid_timer_takedown(struct drm_psb_private *dev_priv) -{ - del_timer_sync(&dev_priv->lid_timer); -} - diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 79f65eff6bb2a3..23400313d8a64c 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -104,6 +104,7 @@ gt-y += \ gt/intel_ggtt_fencing.o \ gt/intel_gt.o \ gt/intel_gt_buffer_pool.o \ + gt/intel_gt_ccs_mode.o \ gt/intel_gt_clock_utils.o \ gt/intel_gt_debugfs.o \ gt/intel_gt_engines_debugfs.o \ diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c index 4c7187f7913ea5..e8ee0a08947e8f 100644 --- a/drivers/gpu/drm/i915/display/g4x_dp.c +++ b/drivers/gpu/drm/i915/display/g4x_dp.c @@ -141,7 +141,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder, intel_de_rmw(dev_priv, TRANS_DP_CTL(crtc->pipe), TRANS_DP_ENH_FRAMING, - drm_dp_enhanced_frame_cap(intel_dp->dpcd) ? + pipe_config->enhanced_framing ? TRANS_DP_ENH_FRAMING : 0); } else { if (IS_G4X(dev_priv) && pipe_config->limited_color_range) @@ -153,7 +153,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder, intel_dp->DP |= DP_SYNC_VS_HIGH; intel_dp->DP |= DP_LINK_TRAIN_OFF; - if (drm_dp_enhanced_frame_cap(intel_dp->dpcd)) + if (pipe_config->enhanced_framing) intel_dp->DP |= DP_ENHANCED_FRAMING; if (IS_CHERRYVIEW(dev_priv)) @@ -351,6 +351,9 @@ static void intel_dp_get_config(struct intel_encoder *encoder, u32 trans_dp = intel_de_read(dev_priv, TRANS_DP_CTL(crtc->pipe)); + if (trans_dp & TRANS_DP_ENH_FRAMING) + pipe_config->enhanced_framing = true; + if (trans_dp & TRANS_DP_HSYNC_ACTIVE_HIGH) flags |= DRM_MODE_FLAG_PHSYNC; else @@ -361,6 +364,9 @@ static void intel_dp_get_config(struct intel_encoder *encoder, else flags |= DRM_MODE_FLAG_NVSYNC; } else { + if (tmp & DP_ENHANCED_FRAMING) + pipe_config->enhanced_framing = true; + if (tmp & DP_SYNC_HS_HIGH) flags |= DRM_MODE_FLAG_PHSYNC; else diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index ad6488e9c2b2b8..5b8efe8e735a9b 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -1440,6 +1440,13 @@ static void gen11_dsi_post_disable(struct intel_atomic_state *state, static enum drm_mode_status gen11_dsi_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + struct drm_i915_private *i915 = to_i915(connector->dev); + enum drm_mode_status status; + + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; + /* FIXME: DSC? */ return intel_dsi_mode_valid(connector, mode); } diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c index 7cf51dd8c05670..aaddd8c0cfa0ee 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.c +++ b/drivers/gpu/drm/i915/display/intel_atomic.c @@ -259,6 +259,7 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc) drm_property_blob_get(crtc_state->post_csc_lut); crtc_state->update_pipe = false; + crtc_state->update_m_n = false; crtc_state->disable_lp_wm = false; crtc_state->disable_cxsr = false; crtc_state->update_wm_pre = false; diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c index 3d9c9b4f27f802..1cf1674897e9f2 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.c +++ b/drivers/gpu/drm/i915/display/intel_audio.c @@ -75,19 +75,6 @@ struct intel_audio_funcs { struct intel_crtc_state *crtc_state); }; -/* DP N/M table */ -#define LC_810M 810000 -#define LC_540M 540000 -#define LC_270M 270000 -#define LC_162M 162000 - -struct dp_aud_n_m { - int sample_rate; - int clock; - u16 m; - u16 n; -}; - struct hdmi_aud_ncts { int sample_rate; int clock; @@ -95,60 +82,6 @@ struct hdmi_aud_ncts { int cts; }; -/* Values according to DP 1.4 Table 2-104 */ -static const struct dp_aud_n_m dp_aud_n_m[] = { - { 32000, LC_162M, 1024, 10125 }, - { 44100, LC_162M, 784, 5625 }, - { 48000, LC_162M, 512, 3375 }, - { 64000, LC_162M, 2048, 10125 }, - { 88200, LC_162M, 1568, 5625 }, - { 96000, LC_162M, 1024, 3375 }, - { 128000, LC_162M, 4096, 10125 }, - { 176400, LC_162M, 3136, 5625 }, - { 192000, LC_162M, 2048, 3375 }, - { 32000, LC_270M, 1024, 16875 }, - { 44100, LC_270M, 784, 9375 }, - { 48000, LC_270M, 512, 5625 }, - { 64000, LC_270M, 2048, 16875 }, - { 88200, LC_270M, 1568, 9375 }, - { 96000, LC_270M, 1024, 5625 }, - { 128000, LC_270M, 4096, 16875 }, - { 176400, LC_270M, 3136, 9375 }, - { 192000, LC_270M, 2048, 5625 }, - { 32000, LC_540M, 1024, 33750 }, - { 44100, LC_540M, 784, 18750 }, - { 48000, LC_540M, 512, 11250 }, - { 64000, LC_540M, 2048, 33750 }, - { 88200, LC_540M, 1568, 18750 }, - { 96000, LC_540M, 1024, 11250 }, - { 128000, LC_540M, 4096, 33750 }, - { 176400, LC_540M, 3136, 18750 }, - { 192000, LC_540M, 2048, 11250 }, - { 32000, LC_810M, 1024, 50625 }, - { 44100, LC_810M, 784, 28125 }, - { 48000, LC_810M, 512, 16875 }, - { 64000, LC_810M, 2048, 50625 }, - { 88200, LC_810M, 1568, 28125 }, - { 96000, LC_810M, 1024, 16875 }, - { 128000, LC_810M, 4096, 50625 }, - { 176400, LC_810M, 3136, 28125 }, - { 192000, LC_810M, 2048, 16875 }, -}; - -static const struct dp_aud_n_m * -audio_config_dp_get_n_m(const struct intel_crtc_state *crtc_state, int rate) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(dp_aud_n_m); i++) { - if (rate == dp_aud_n_m[i].sample_rate && - crtc_state->port_clock == dp_aud_n_m[i].clock) - return &dp_aud_n_m[i]; - } - - return NULL; -} - static const struct { int clock; u32 config; @@ -386,47 +319,17 @@ hsw_dp_audio_config_update(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { struct drm_i915_private *i915 = to_i915(encoder->base.dev); - struct i915_audio_component *acomp = i915->display.audio.component; enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; - enum port port = encoder->port; - const struct dp_aud_n_m *nm; - int rate; - u32 tmp; - - rate = acomp ? acomp->aud_sample_rate[port] : 0; - nm = audio_config_dp_get_n_m(crtc_state, rate); - if (nm) - drm_dbg_kms(&i915->drm, "using Maud %u, Naud %u\n", nm->m, - nm->n); - else - drm_dbg_kms(&i915->drm, "using automatic Maud, Naud\n"); - - tmp = intel_de_read(i915, HSW_AUD_CFG(cpu_transcoder)); - tmp &= ~AUD_CONFIG_N_VALUE_INDEX; - tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK; - tmp &= ~AUD_CONFIG_N_PROG_ENABLE; - tmp |= AUD_CONFIG_N_VALUE_INDEX; - - if (nm) { - tmp &= ~AUD_CONFIG_N_MASK; - tmp |= AUD_CONFIG_N(nm->n); - tmp |= AUD_CONFIG_N_PROG_ENABLE; - } - - intel_de_write(i915, HSW_AUD_CFG(cpu_transcoder), tmp); - - tmp = intel_de_read(i915, HSW_AUD_M_CTS_ENABLE(cpu_transcoder)); - tmp &= ~AUD_CONFIG_M_MASK; - tmp &= ~AUD_M_CTS_M_VALUE_INDEX; - tmp &= ~AUD_M_CTS_M_PROG_ENABLE; - if (nm) { - tmp |= nm->m; - tmp |= AUD_M_CTS_M_VALUE_INDEX; - tmp |= AUD_M_CTS_M_PROG_ENABLE; - } + /* Enable time stamps. Let HW calculate Maud/Naud values */ + intel_de_rmw(i915, HSW_AUD_CFG(cpu_transcoder), + AUD_CONFIG_N_VALUE_INDEX | + AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK | + AUD_CONFIG_UPPER_N_MASK | + AUD_CONFIG_LOWER_N_MASK | + AUD_CONFIG_N_PROG_ENABLE, + AUD_CONFIG_N_VALUE_INDEX); - intel_de_write(i915, HSW_AUD_M_CTS_ENABLE(cpu_transcoder), tmp); } static void @@ -1348,17 +1251,6 @@ static const struct component_ops i915_audio_component_bind_ops = { static void i915_audio_component_init(struct drm_i915_private *i915) { u32 aud_freq, aud_freq_init; - int ret; - - ret = component_add_typed(i915->drm.dev, - &i915_audio_component_bind_ops, - I915_COMPONENT_AUDIO); - if (ret < 0) { - drm_err(&i915->drm, - "failed to add audio component (%d)\n", ret); - /* continue with reduced functionality */ - return; - } if (DISPLAY_VER(i915) >= 9) { aud_freq_init = intel_de_read(i915, AUD_FREQ_CNTRL); @@ -1381,6 +1273,21 @@ static void i915_audio_component_init(struct drm_i915_private *i915) /* init with current cdclk */ intel_audio_cdclk_change_post(i915); +} + +static void i915_audio_component_register(struct drm_i915_private *i915) +{ + int ret; + + ret = component_add_typed(i915->drm.dev, + &i915_audio_component_bind_ops, + I915_COMPONENT_AUDIO); + if (ret < 0) { + drm_err(&i915->drm, + "failed to add audio component (%d)\n", ret); + /* continue with reduced functionality */ + return; + } i915->display.audio.component_registered = true; } @@ -1413,6 +1320,12 @@ void intel_audio_init(struct drm_i915_private *i915) i915_audio_component_init(i915); } +void intel_audio_register(struct drm_i915_private *i915) +{ + if (!i915->display.audio.lpe.platdev) + i915_audio_component_register(i915); +} + /** * intel_audio_deinit() - deinitialize the audio driver * @i915: the i915 drm device private data diff --git a/drivers/gpu/drm/i915/display/intel_audio.h b/drivers/gpu/drm/i915/display/intel_audio.h index 07d034a981e90e..9779343a371068 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.h +++ b/drivers/gpu/drm/i915/display/intel_audio.h @@ -28,6 +28,7 @@ void intel_audio_codec_get_config(struct intel_encoder *encoder, void intel_audio_cdclk_change_pre(struct drm_i915_private *dev_priv); void intel_audio_cdclk_change_post(struct drm_i915_private *dev_priv); void intel_audio_init(struct drm_i915_private *dev_priv); +void intel_audio_register(struct drm_i915_private *i915); void intel_audio_deinit(struct drm_i915_private *dev_priv); void intel_audio_sdp_split_update(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_backlight.c b/drivers/gpu/drm/i915/display/intel_backlight.c index 2e8f17c0452223..ff9b9918b0a134 100644 --- a/drivers/gpu/drm/i915/display/intel_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_backlight.c @@ -274,7 +274,7 @@ static void ext_pwm_set_backlight(const struct drm_connector_state *conn_state, struct intel_panel *panel = &to_intel_connector(conn_state->connector)->panel; pwm_set_relative_duty_cycle(&panel->backlight.pwm_state, level, 100); - pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state); + pwm_apply_might_sleep(panel->backlight.pwm, &panel->backlight.pwm_state); } static void @@ -427,7 +427,7 @@ static void ext_pwm_disable_backlight(const struct drm_connector_state *old_conn intel_backlight_set_pwm_level(old_conn_state, level); panel->backlight.pwm_state.enabled = false; - pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state); + pwm_apply_might_sleep(panel->backlight.pwm, &panel->backlight.pwm_state); } void intel_backlight_disable(const struct drm_connector_state *old_conn_state) @@ -749,7 +749,7 @@ static void ext_pwm_enable_backlight(const struct intel_crtc_state *crtc_state, pwm_set_relative_duty_cycle(&panel->backlight.pwm_state, level, 100); panel->backlight.pwm_state.enabled = true; - pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state); + pwm_apply_might_sleep(panel->backlight.pwm, &panel->backlight.pwm_state); } static void __intel_backlight_enable(const struct intel_crtc_state *crtc_state, diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index f735b035436c02..27d1c49b46ec48 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -1035,22 +1035,11 @@ parse_lfp_backlight(struct drm_i915_private *i915, panel->vbt.backlight.type = INTEL_BACKLIGHT_DISPLAY_DDI; panel->vbt.backlight.controller = 0; if (i915->display.vbt.version >= 191) { - size_t exp_size; + const struct lfp_backlight_control_method *method; - if (i915->display.vbt.version >= 236) - exp_size = sizeof(struct bdb_lfp_backlight_data); - else if (i915->display.vbt.version >= 234) - exp_size = EXP_BDB_LFP_BL_DATA_SIZE_REV_234; - else - exp_size = EXP_BDB_LFP_BL_DATA_SIZE_REV_191; - - if (get_blocksize(backlight_data) >= exp_size) { - const struct lfp_backlight_control_method *method; - - method = &backlight_data->backlight_control[panel_type]; - panel->vbt.backlight.type = method->type; - panel->vbt.backlight.controller = method->controller; - } + method = &backlight_data->backlight_control[panel_type]; + panel->vbt.backlight.type = method->type; + panel->vbt.backlight.controller = method->controller; } panel->vbt.backlight.pwm_freq_hz = entry->pwm_freq_hz; @@ -1945,16 +1934,12 @@ static int get_init_otp_deassert_fragment_len(struct drm_i915_private *i915, * these devices we split the init OTP sequence into a deassert sequence and * the actual init OTP part. */ -static void fixup_mipi_sequences(struct drm_i915_private *i915, - struct intel_panel *panel) +static void vlv_fixup_mipi_sequences(struct drm_i915_private *i915, + struct intel_panel *panel) { u8 *init_otp; int len; - /* Limit this to VLV for now. */ - if (!IS_VALLEYVIEW(i915)) - return; - /* Limit this to v1 vid-mode sequences */ if (panel->vbt.dsi.config->is_cmd_mode || panel->vbt.dsi.seq_version != 1) @@ -1990,6 +1975,41 @@ static void fixup_mipi_sequences(struct drm_i915_private *i915, panel->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] = init_otp + len - 1; } +/* + * Some machines (eg. Lenovo 82TQ) appear to have broken + * VBT sequences: + * - INIT_OTP is not present at all + * - what should be in INIT_OTP is in DISPLAY_ON + * - what should be in DISPLAY_ON is in BACKLIGHT_ON + * (along with the actual backlight stuff) + * + * To make those work we simply swap DISPLAY_ON and INIT_OTP. + * + * TODO: Do we need to limit this to specific machines, + * or examine the contents of the sequences to + * avoid false positives? + */ +static void icl_fixup_mipi_sequences(struct drm_i915_private *i915, + struct intel_panel *panel) +{ + if (!panel->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] && + panel->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_ON]) { + drm_dbg_kms(&i915->drm, "Broken VBT: Swapping INIT_OTP and DISPLAY_ON sequences\n"); + + swap(panel->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP], + panel->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_ON]); + } +} + +static void fixup_mipi_sequences(struct drm_i915_private *i915, + struct intel_panel *panel) +{ + if (DISPLAY_VER(i915) >= 11) + icl_fixup_mipi_sequences(i915, panel); + else if (IS_VALLEYVIEW(i915)) + vlv_fixup_mipi_sequences(i915, panel); +} + static void parse_mipi_sequence(struct drm_i915_private *i915, struct intel_panel *panel) @@ -3313,6 +3333,9 @@ bool intel_bios_encoder_supports_dp_dual_mode(const struct intel_bios_encoder_da { const struct child_device_config *child = &devdata->child; + if (!devdata) + return false; + if (!intel_bios_encoder_supports_dp(devdata) || !intel_bios_encoder_supports_hdmi(devdata)) return false; diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 2fb030b1ff1de3..fc3a6eb1de7414 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2453,7 +2453,8 @@ intel_set_cdclk_pre_plane_update(struct intel_atomic_state *state) intel_atomic_get_old_cdclk_state(state); const struct intel_cdclk_state *new_cdclk_state = intel_atomic_get_new_cdclk_state(state); - enum pipe pipe = new_cdclk_state->pipe; + struct intel_cdclk_config cdclk_config; + enum pipe pipe; if (!intel_cdclk_changed(&old_cdclk_state->actual, &new_cdclk_state->actual)) @@ -2462,12 +2463,25 @@ intel_set_cdclk_pre_plane_update(struct intel_atomic_state *state) if (IS_DG2(i915)) intel_cdclk_pcode_pre_notify(state); - if (pipe == INVALID_PIPE || - old_cdclk_state->actual.cdclk <= new_cdclk_state->actual.cdclk) { - drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed); + if (new_cdclk_state->disable_pipes) { + cdclk_config = new_cdclk_state->actual; + pipe = INVALID_PIPE; + } else { + if (new_cdclk_state->actual.cdclk >= old_cdclk_state->actual.cdclk) { + cdclk_config = new_cdclk_state->actual; + pipe = new_cdclk_state->pipe; + } else { + cdclk_config = old_cdclk_state->actual; + pipe = INVALID_PIPE; + } - intel_set_cdclk(i915, &new_cdclk_state->actual, pipe); + cdclk_config.voltage_level = max(new_cdclk_state->actual.voltage_level, + old_cdclk_state->actual.voltage_level); } + + drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed); + + intel_set_cdclk(i915, &cdclk_config, pipe); } /** @@ -2485,7 +2499,7 @@ intel_set_cdclk_post_plane_update(struct intel_atomic_state *state) intel_atomic_get_old_cdclk_state(state); const struct intel_cdclk_state *new_cdclk_state = intel_atomic_get_new_cdclk_state(state); - enum pipe pipe = new_cdclk_state->pipe; + enum pipe pipe; if (!intel_cdclk_changed(&old_cdclk_state->actual, &new_cdclk_state->actual)) @@ -2494,12 +2508,15 @@ intel_set_cdclk_post_plane_update(struct intel_atomic_state *state) if (IS_DG2(i915)) intel_cdclk_pcode_post_notify(state); - if (pipe != INVALID_PIPE && - old_cdclk_state->actual.cdclk > new_cdclk_state->actual.cdclk) { - drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed); + if (!new_cdclk_state->disable_pipes && + new_cdclk_state->actual.cdclk < old_cdclk_state->actual.cdclk) + pipe = new_cdclk_state->pipe; + else + pipe = INVALID_PIPE; - intel_set_cdclk(i915, &new_cdclk_state->actual, pipe); - } + drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed); + + intel_set_cdclk(i915, &new_cdclk_state->actual, pipe); } static int intel_pixel_rate_to_cdclk(const struct intel_crtc_state *crtc_state) @@ -2688,6 +2705,18 @@ static int intel_compute_min_cdclk(struct intel_cdclk_state *cdclk_state) for_each_pipe(dev_priv, pipe) min_cdclk = max(cdclk_state->min_cdclk[pipe], min_cdclk); + /* + * Avoid glk_force_audio_cdclk() causing excessive screen + * blinking when multiple pipes are active by making sure + * CDCLK frequency is always high enough for audio. With a + * single active pipe we can always change CDCLK frequency + * by changing the cd2x divider (see glk_cdclk_table[]) and + * thus a full modeset won't be needed then. + */ + if (IS_GEMINILAKE(dev_priv) && cdclk_state->active_pipes && + !is_power_of_2(cdclk_state->active_pipes)) + min_cdclk = max(2 * 96000, min_cdclk); + if (min_cdclk > dev_priv->display.cdclk.max_cdclk_freq) { drm_dbg_kms(&dev_priv->drm, "required cdclk (%d kHz) exceeds max (%d kHz)\n", @@ -2934,6 +2963,7 @@ static struct intel_global_state *intel_cdclk_duplicate_state(struct intel_globa return NULL; cdclk_state->pipe = INVALID_PIPE; + cdclk_state->disable_pipes = false; return &cdclk_state->base; } @@ -3112,6 +3142,8 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) if (ret) return ret; + new_cdclk_state->disable_pipes = true; + drm_dbg_kms(&dev_priv->drm, "Modeset required for cdclk change\n"); } diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h index 48fd7d39e0cd9c..71bc032bfef16e 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.h +++ b/drivers/gpu/drm/i915/display/intel_cdclk.h @@ -51,6 +51,9 @@ struct intel_cdclk_state { /* bitmask of active pipes */ u8 active_pipes; + + /* update cdclk with pipes disabled */ + bool disable_pipes; }; int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c index 8090747586877e..4352f901776152 100644 --- a/drivers/gpu/drm/i915/display/intel_crt.c +++ b/drivers/gpu/drm/i915/display/intel_crt.c @@ -348,8 +348,13 @@ intel_crt_mode_valid(struct drm_connector *connector, struct drm_device *dev = connector->dev; struct drm_i915_private *dev_priv = to_i915(dev); int max_dotclk = dev_priv->max_dotclk_freq; + enum drm_mode_status status; int max_clock; + status = intel_cpu_transcoder_mode_valid(dev_priv, mode); + if (status != MODE_OK) + return status; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; @@ -451,6 +456,8 @@ static int hsw_crt_compute_config(struct intel_encoder *encoder, /* FDI must always be 2.7 GHz */ pipe_config->port_clock = 135000 * 2; + pipe_config->enhanced_framing = true; + adjusted_mode->crtc_clock = lpt_iclkip(pipe_config); return 0; diff --git a/drivers/gpu/drm/i915/display/intel_crtc.c b/drivers/gpu/drm/i915/display/intel_crtc.c index 182c6dd64f47cf..cfbfbfed3f5e66 100644 --- a/drivers/gpu/drm/i915/display/intel_crtc.c +++ b/drivers/gpu/drm/i915/display/intel_crtc.c @@ -468,9 +468,56 @@ static int intel_mode_vblank_start(const struct drm_display_mode *mode) return vblank_start; } +static void intel_crtc_vblank_evade_scanlines(struct intel_atomic_state *state, + struct intel_crtc *crtc, + int *min, int *max, int *vblank_start) +{ + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + const struct intel_crtc_state *new_crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + const struct intel_crtc_state *crtc_state; + const struct drm_display_mode *adjusted_mode; + + /* + * During fastsets/etc. the transcoder is still + * running with the old timings at this point. + * + * TODO: maybe just use the active timings here? + */ + if (intel_crtc_needs_modeset(new_crtc_state)) + crtc_state = new_crtc_state; + else + crtc_state = old_crtc_state; + + adjusted_mode = &crtc_state->hw.adjusted_mode; + + if (crtc->mode_flags & I915_MODE_FLAG_VRR) { + if (intel_vrr_is_push_sent(crtc_state)) + *vblank_start = intel_vrr_vmin_vblank_start(crtc_state); + else + *vblank_start = intel_vrr_vmax_vblank_start(crtc_state); + } else { + *vblank_start = intel_mode_vblank_start(adjusted_mode); + } + + /* FIXME needs to be calibrated sensibly */ + *min = *vblank_start - intel_usecs_to_scanlines(adjusted_mode, + VBLANK_EVASION_TIME_US); + *max = *vblank_start - 1; + + /* + * M/N is double buffered on the transcoder's undelayed vblank, + * so with seamless M/N we must evade both vblanks. + */ + if (new_crtc_state->update_m_n) + *min -= adjusted_mode->crtc_vblank_start - adjusted_mode->crtc_vdisplay; +} + /** * intel_pipe_update_start() - start update of a set of display registers - * @new_crtc_state: the new crtc state + * @state: the atomic state + * @crtc: the crtc * * Mark the start of an update to pipe registers that should be updated * atomically regarding vblank. If the next vblank will happens within @@ -480,11 +527,12 @@ static int intel_mode_vblank_start(const struct drm_display_mode *mode) * until a subsequent call to intel_pipe_update_end(). That is done to * avoid random delays. */ -void intel_pipe_update_start(struct intel_crtc_state *new_crtc_state) +void intel_pipe_update_start(struct intel_atomic_state *state, + struct intel_crtc *crtc) { - struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - const struct drm_display_mode *adjusted_mode = &new_crtc_state->hw.adjusted_mode; + struct intel_crtc_state *new_crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); long timeout = msecs_to_jiffies_timeout(1); int scanline, min, max, vblank_start; wait_queue_head_t *wq = drm_crtc_vblank_waitqueue(&crtc->base); @@ -500,27 +548,7 @@ void intel_pipe_update_start(struct intel_crtc_state *new_crtc_state) if (intel_crtc_needs_vblank_work(new_crtc_state)) intel_crtc_vblank_work_init(new_crtc_state); - if (new_crtc_state->vrr.enable) { - if (intel_vrr_is_push_sent(new_crtc_state)) - vblank_start = intel_vrr_vmin_vblank_start(new_crtc_state); - else - vblank_start = intel_vrr_vmax_vblank_start(new_crtc_state); - } else { - vblank_start = intel_mode_vblank_start(adjusted_mode); - } - - /* FIXME needs to be calibrated sensibly */ - min = vblank_start - intel_usecs_to_scanlines(adjusted_mode, - VBLANK_EVASION_TIME_US); - max = vblank_start - 1; - - /* - * M/N is double buffered on the transcoder's undelayed vblank, - * so with seamless M/N we must evade both vblanks. - */ - if (new_crtc_state->seamless_m_n && intel_crtc_needs_fastset(new_crtc_state)) - min -= adjusted_mode->crtc_vblank_start - adjusted_mode->crtc_vdisplay; - + intel_crtc_vblank_evade_scanlines(state, crtc, &min, &max, &vblank_start); if (min <= 0 || max <= 0) goto irq_disable; @@ -631,15 +659,18 @@ static void dbg_vblank_evade(struct intel_crtc *crtc, ktime_t end) {} /** * intel_pipe_update_end() - end update of a set of display registers - * @new_crtc_state: the new crtc state + * @state: the atomic state + * @crtc: the crtc * * Mark the end of an update started with intel_pipe_update_start(). This * re-enables interrupts and verifies the update was actually completed * before a vblank. */ -void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state) +void intel_pipe_update_end(struct intel_atomic_state *state, + struct intel_crtc *crtc) { - struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc); + struct intel_crtc_state *new_crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); enum pipe pipe = crtc->pipe; int scanline_end = intel_get_crtc_scanline(crtc); u32 end_vbl_count = intel_crtc_get_vblank_counter(crtc); @@ -697,15 +728,6 @@ void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state) */ intel_vrr_send_push(new_crtc_state); - /* - * Seamless M/N update may need to update frame timings. - * - * FIXME Should be synchronized with the start of vblank somehow... - */ - if (new_crtc_state->seamless_m_n && intel_crtc_needs_fastset(new_crtc_state)) - intel_crtc_update_active_timings(new_crtc_state, - new_crtc_state->vrr.enable); - local_irq_enable(); if (intel_vgpu_active(dev_priv)) diff --git a/drivers/gpu/drm/i915/display/intel_crtc.h b/drivers/gpu/drm/i915/display/intel_crtc.h index 51a4c8df9e6574..22d7993d1f0ba9 100644 --- a/drivers/gpu/drm/i915/display/intel_crtc.h +++ b/drivers/gpu/drm/i915/display/intel_crtc.h @@ -36,8 +36,10 @@ void intel_crtc_state_reset(struct intel_crtc_state *crtc_state, u32 intel_crtc_get_vblank_counter(struct intel_crtc *crtc); void intel_crtc_vblank_on(const struct intel_crtc_state *crtc_state); void intel_crtc_vblank_off(const struct intel_crtc_state *crtc_state); -void intel_pipe_update_start(struct intel_crtc_state *new_crtc_state); -void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state); +void intel_pipe_update_start(struct intel_atomic_state *state, + struct intel_crtc *crtc); +void intel_pipe_update_end(struct intel_atomic_state *state, + struct intel_crtc *crtc); void intel_wait_for_vblank_workers(struct intel_atomic_state *state); struct intel_crtc *intel_first_crtc(struct drm_i915_private *i915); struct intel_crtc *intel_crtc_for_pipe(struct drm_i915_private *i915, diff --git a/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c b/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c index 8d4640d0fd346b..66fe880af8f3f0 100644 --- a/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c +++ b/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c @@ -258,6 +258,9 @@ void intel_crtc_state_dump(const struct intel_crtc_state *pipe_config, intel_dump_m_n_config(pipe_config, "dp m2_n2", pipe_config->lane_count, &pipe_config->dp_m2_n2); + drm_dbg_kms(&i915->drm, "fec: %s, enhanced framing: %s\n", + str_enabled_disabled(pipe_config->fec_enable), + str_enabled_disabled(pipe_config->enhanced_framing)); } drm_dbg_kms(&i915->drm, "framestart delay: %d, MSA timing delay: %d\n", diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c index b342fad180ca5b..61df6cd3f37788 100644 --- a/drivers/gpu/drm/i915/display/intel_cursor.c +++ b/drivers/gpu/drm/i915/display/intel_cursor.c @@ -23,6 +23,8 @@ #include "intel_psr.h" #include "skl_watermark.h" +#include "gem/i915_gem_object.h" + /* Cursor formats */ static const u32 intel_cursor_formats[] = { DRM_FORMAT_ARGB8888, @@ -32,12 +34,10 @@ static u32 intel_cursor_base(const struct intel_plane_state *plane_state) { struct drm_i915_private *dev_priv = to_i915(plane_state->uapi.plane->dev); - const struct drm_framebuffer *fb = plane_state->hw.fb; - const struct drm_i915_gem_object *obj = intel_fb_obj(fb); u32 base; if (DISPLAY_INFO(dev_priv)->cursor_needs_physical) - base = sg_dma_address(obj->mm.pages->sgl); + base = plane_state->phys_dma_addr; else base = intel_plane_ggtt_offset(plane_state); diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c index 80e4ec6ee4031b..048e581fda16cb 100644 --- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c +++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c @@ -2420,7 +2420,8 @@ static void intel_program_port_clock_ctl(struct intel_encoder *encoder, val |= XELPDP_FORWARD_CLOCK_UNGATE; - if (is_hdmi_frl(crtc_state->port_clock)) + if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI) && + is_hdmi_frl(crtc_state->port_clock)) val |= XELPDP_DDI_CLOCK_SELECT(XELPDP_DDI_CLOCK_SELECT_DIV18CLK); else val |= XELPDP_DDI_CLOCK_SELECT(XELPDP_DDI_CLOCK_SELECT_MAXPCLK); diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 84bbf854337aa7..b347f906234945 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -3432,7 +3432,7 @@ static void mtl_ddi_prepare_link_retrain(struct intel_dp *intel_dp, dp_tp_ctl |= DP_TP_CTL_MODE_MST; } else { dp_tp_ctl |= DP_TP_CTL_MODE_SST; - if (drm_dp_enhanced_frame_cap(intel_dp->dpcd)) + if (crtc_state->enhanced_framing) dp_tp_ctl |= DP_TP_CTL_ENHANCED_FRAME_ENABLE; } intel_de_write(dev_priv, dp_tp_ctl_reg(encoder, crtc_state), dp_tp_ctl); @@ -3489,7 +3489,7 @@ static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp, dp_tp_ctl |= DP_TP_CTL_MODE_MST; } else { dp_tp_ctl |= DP_TP_CTL_MODE_SST; - if (drm_dp_enhanced_frame_cap(intel_dp->dpcd)) + if (crtc_state->enhanced_framing) dp_tp_ctl |= DP_TP_CTL_ENHANCED_FRAME_ENABLE; } intel_de_write(dev_priv, dp_tp_ctl_reg(encoder, crtc_state), dp_tp_ctl); @@ -3724,17 +3724,14 @@ static void intel_ddi_read_func_ctl(struct intel_encoder *encoder, intel_cpu_transcoder_get_m2_n2(crtc, cpu_transcoder, &pipe_config->dp_m2_n2); - if (DISPLAY_VER(dev_priv) >= 11) { - i915_reg_t dp_tp_ctl = dp_tp_ctl_reg(encoder, pipe_config); + pipe_config->enhanced_framing = + intel_de_read(dev_priv, dp_tp_ctl_reg(encoder, pipe_config)) & + DP_TP_CTL_ENHANCED_FRAME_ENABLE; + if (DISPLAY_VER(dev_priv) >= 11) pipe_config->fec_enable = - intel_de_read(dev_priv, dp_tp_ctl) & DP_TP_CTL_FEC_ENABLE; - - drm_dbg_kms(&dev_priv->drm, - "[ENCODER:%d:%s] Fec status: %u\n", - encoder->base.base.id, encoder->base.name, - pipe_config->fec_enable); - } + intel_de_read(dev_priv, + dp_tp_ctl_reg(encoder, pipe_config)) & DP_TP_CTL_FEC_ENABLE; if (dig_port->lspcon.active && intel_dp_has_hdmi_sink(&dig_port->dp)) pipe_config->infoframes.enable |= @@ -3747,6 +3744,9 @@ static void intel_ddi_read_func_ctl(struct intel_encoder *encoder, if (!HAS_DP20(dev_priv)) { /* FDI */ pipe_config->output_types |= BIT(INTEL_OUTPUT_ANALOG); + pipe_config->enhanced_framing = + intel_de_read(dev_priv, dp_tp_ctl_reg(encoder, pipe_config)) & + DP_TP_CTL_ENHANCED_FRAME_ENABLE; break; } fallthrough; /* 128b/132b */ @@ -4111,7 +4111,12 @@ static bool m_n_equal(const struct intel_link_m_n *m_n_1, static bool crtcs_port_sync_compatible(const struct intel_crtc_state *crtc_state1, const struct intel_crtc_state *crtc_state2) { + /* + * FIXME the modeset sequence is currently wrong and + * can't deal with bigjoiner + port sync at the same time. + */ return crtc_state1->hw.active && crtc_state2->hw.active && + !crtc_state1->bigjoiner_pipes && !crtc_state2->bigjoiner_pipes && crtc_state1->output_types == crtc_state2->output_types && crtc_state1->output_format == crtc_state2->output_format && crtc_state1->lane_count == crtc_state2->lane_count && diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 763ab569d8f324..1a59fca40252cd 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -5215,7 +5215,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_X(lane_lat_optim_mask); if (HAS_DOUBLE_BUFFERED_M_N(dev_priv)) { - if (!fastset || !pipe_config->seamless_m_n) + if (!fastset || !pipe_config->update_m_n) PIPE_CONF_CHECK_M_N(dp_m_n); } else { PIPE_CONF_CHECK_M_N(dp_m_n); @@ -5255,6 +5255,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_BOOL(hdmi_scrambling); PIPE_CONF_CHECK_BOOL(hdmi_high_tmds_clock_ratio); PIPE_CONF_CHECK_BOOL(has_infoframe); + PIPE_CONF_CHECK_BOOL(enhanced_framing); PIPE_CONF_CHECK_BOOL(fec_enable); PIPE_CONF_CHECK_BOOL_INCOMPLETE(has_audio); @@ -5352,7 +5353,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, if (IS_G4X(dev_priv) || DISPLAY_VER(dev_priv) >= 5) PIPE_CONF_CHECK_I(pipe_bpp); - if (!fastset || !pipe_config->seamless_m_n) { + if (!fastset || !pipe_config->update_m_n) { PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_clock); PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_clock); } @@ -5447,6 +5448,7 @@ int intel_modeset_all_pipes(struct intel_atomic_state *state, crtc_state->uapi.mode_changed = true; crtc_state->update_pipe = false; + crtc_state->update_m_n = false; ret = drm_atomic_add_affected_connectors(&state->base, &crtc->base); @@ -5564,13 +5566,14 @@ static void intel_crtc_check_fastset(const struct intel_crtc_state *old_crtc_sta { struct drm_i915_private *i915 = to_i915(old_crtc_state->uapi.crtc->dev); - if (!intel_pipe_config_compare(old_crtc_state, new_crtc_state, true)) { + if (!intel_pipe_config_compare(old_crtc_state, new_crtc_state, true)) drm_dbg_kms(&i915->drm, "fastset requirement not met, forcing full modeset\n"); + else + new_crtc_state->uapi.mode_changed = false; - return; - } + if (intel_crtc_needs_modeset(new_crtc_state)) + new_crtc_state->update_m_n = false; - new_crtc_state->uapi.mode_changed = false; if (!intel_crtc_needs_modeset(new_crtc_state)) new_crtc_state->update_pipe = true; } @@ -5976,6 +5979,17 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in return -EINVAL; } + /* + * FIXME: Bigjoiner+async flip is busted currently. + * Remove this check once the issues are fixed. + */ + if (new_crtc_state->bigjoiner_pipes) { + drm_dbg_kms(&i915->drm, + "[CRTC:%d:%s] async flip disallowed with bigjoiner\n", + crtc->base.base.id, crtc->base.name); + return -EINVAL; + } + for_each_oldnew_intel_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { if (plane->pipe != crtc->pipe) @@ -6285,6 +6299,7 @@ int intel_atomic_check(struct drm_device *dev, if (intel_cpu_transcoders_need_modeset(state, BIT(master))) { new_crtc_state->uapi.mode_changed = true; new_crtc_state->update_pipe = false; + new_crtc_state->update_m_n = false; } } @@ -6297,6 +6312,7 @@ int intel_atomic_check(struct drm_device *dev, if (intel_cpu_transcoders_need_modeset(state, trans)) { new_crtc_state->uapi.mode_changed = true; new_crtc_state->update_pipe = false; + new_crtc_state->update_m_n = false; } } @@ -6304,6 +6320,7 @@ int intel_atomic_check(struct drm_device *dev, if (intel_pipes_need_modeset(state, new_crtc_state->bigjoiner_pipes)) { new_crtc_state->uapi.mode_changed = true; new_crtc_state->update_pipe = false; + new_crtc_state->update_m_n = false; } } } @@ -6482,7 +6499,7 @@ static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state, IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) hsw_set_linetime_wm(new_crtc_state); - if (new_crtc_state->seamless_m_n) + if (new_crtc_state->update_m_n) intel_cpu_transcoder_set_m1_n1(crtc, new_crtc_state->cpu_transcoder, &new_crtc_state->dp_m_n); } @@ -6521,6 +6538,8 @@ static void commit_pipe_post_planes(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); const struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, crtc); @@ -6532,6 +6551,9 @@ static void commit_pipe_post_planes(struct intel_atomic_state *state, if (DISPLAY_VER(dev_priv) >= 9 && !intel_crtc_needs_modeset(new_crtc_state)) skl_detach_scalers(new_crtc_state); + + if (vrr_enabling(old_crtc_state, new_crtc_state)) + intel_vrr_enable(new_crtc_state); } static void intel_enable_crtc(struct intel_atomic_state *state, @@ -6572,12 +6594,6 @@ static void intel_update_crtc(struct intel_atomic_state *state, intel_dpt_configure(crtc); } - if (vrr_enabling(old_crtc_state, new_crtc_state)) { - intel_vrr_enable(new_crtc_state); - intel_crtc_update_active_timings(new_crtc_state, - new_crtc_state->vrr.enable); - } - if (!modeset) { if (new_crtc_state->preload_luts && intel_crtc_needs_color_update(new_crtc_state)) @@ -6604,7 +6620,7 @@ static void intel_update_crtc(struct intel_atomic_state *state, intel_crtc_planes_update_noarm(state, crtc); /* Perform vblank evasion around commit operation */ - intel_pipe_update_start(new_crtc_state); + intel_pipe_update_start(state, crtc); commit_pipe_pre_planes(state, crtc); @@ -6612,7 +6628,16 @@ static void intel_update_crtc(struct intel_atomic_state *state, commit_pipe_post_planes(state, crtc); - intel_pipe_update_end(new_crtc_state); + intel_pipe_update_end(state, crtc); + + /* + * VRR/Seamless M/N update may need to update frame timings. + * + * FIXME Should be synchronized with the start of vblank somehow... + */ + if (vrr_enabling(old_crtc_state, new_crtc_state) || new_crtc_state->update_m_n) + intel_crtc_update_active_timings(new_crtc_state, + new_crtc_state->vrr.enable); /* * We usually enable FIFO underrun interrupts as part of the @@ -6658,10 +6683,11 @@ static void intel_commit_modeset_disables(struct intel_atomic_state *state) if (!intel_crtc_needs_modeset(new_crtc_state)) continue; + intel_pre_plane_update(state, crtc); + if (!old_crtc_state->hw.active) continue; - intel_pre_plane_update(state, crtc); intel_crtc_disable_planes(state, crtc); } @@ -7279,7 +7305,7 @@ int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *_state, for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) intel_color_cleanup_commit(new_crtc_state); - drm_atomic_helper_cleanup_planes(dev, &state->base); + drm_atomic_helper_unprepare_planes(dev, &state->base); intel_runtime_pm_put(&dev_priv->runtime_pm, state->wakeref); return ret; } @@ -7660,6 +7686,16 @@ enum drm_mode_status intel_mode_valid(struct drm_device *dev, mode->vtotal > vtotal_max) return MODE_V_ILLEGAL; + return MODE_OK; +} + +enum drm_mode_status intel_cpu_transcoder_mode_valid(struct drm_i915_private *dev_priv, + const struct drm_display_mode *mode) +{ + /* + * Additional transcoder timing limits, + * excluding BXT/GLK DSI transcoders. + */ if (DISPLAY_VER(dev_priv) >= 5) { if (mode->hdisplay < 64 || mode->htotal - mode->hdisplay < 32) diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h index 49ac8473b988b3..13b0904d42e3df 100644 --- a/drivers/gpu/drm/i915/display/intel_display.h +++ b/drivers/gpu/drm/i915/display/intel_display.h @@ -405,6 +405,9 @@ enum drm_mode_status intel_mode_valid_max_plane_size(struct drm_i915_private *dev_priv, const struct drm_display_mode *mode, bool bigjoiner); +enum drm_mode_status +intel_cpu_transcoder_mode_valid(struct drm_i915_private *i915, + const struct drm_display_mode *mode); enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port); bool is_trans_port_sync_mode(const struct intel_crtc_state *state); bool is_trans_port_sync_master(const struct intel_crtc_state *state); diff --git a/drivers/gpu/drm/i915/display/intel_display_device.h b/drivers/gpu/drm/i915/display/intel_display_device.h index 215e682bd8b7a4..5fd07c18177661 100644 --- a/drivers/gpu/drm/i915/display/intel_display_device.h +++ b/drivers/gpu/drm/i915/display/intel_display_device.h @@ -46,6 +46,7 @@ struct drm_printer; #define HAS_DPT(i915) (DISPLAY_VER(i915) >= 13) #define HAS_DSB(i915) (DISPLAY_INFO(i915)->has_dsb) #define HAS_DSC(__i915) (DISPLAY_RUNTIME_INFO(__i915)->has_dsc) +#define HAS_DSC_MST(__i915) (DISPLAY_VER(__i915) >= 12 && HAS_DSC(__i915)) #define HAS_FBC(i915) (DISPLAY_RUNTIME_INFO(i915)->fbc_mask != 0) #define HAS_FPGA_DBG_UNCLAIMED(i915) (DISPLAY_INFO(i915)->has_fpga_dbg) #define HAS_FW_BLC(i915) (DISPLAY_VER(i915) > 2) diff --git a/drivers/gpu/drm/i915/display/intel_display_driver.c b/drivers/gpu/drm/i915/display/intel_display_driver.c index 8f144d4d3c3983..26514f931af7a6 100644 --- a/drivers/gpu/drm/i915/display/intel_display_driver.c +++ b/drivers/gpu/drm/i915/display/intel_display_driver.c @@ -386,6 +386,8 @@ void intel_display_driver_register(struct drm_i915_private *i915) intel_audio_init(i915); + intel_audio_register(i915); + intel_display_debugfs_register(i915); /* diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c index 916009894d89c7..1e099908772191 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power_well.c +++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c @@ -246,7 +246,14 @@ static enum phy icl_aux_pw_to_phy(struct drm_i915_private *i915, enum aux_ch aux_ch = icl_aux_pw_to_ch(power_well); struct intel_digital_port *dig_port = aux_ch_to_digital_port(i915, aux_ch); - return intel_port_to_phy(i915, dig_port->base.port); + /* + * FIXME should we care about the (VBT defined) dig_port->aux_ch + * relationship or should this be purely defined by the hardware layout? + * Currently if the port doesn't appear in the VBT, or if it's declared + * as HDMI-only and routed to a combo PHY, the encoder either won't be + * present at all or it will not have an aux_ch assigned. + */ + return dig_port ? intel_port_to_phy(i915, dig_port->base.port) : PHY_NONE; } static void hsw_wait_for_power_well_enable(struct drm_i915_private *dev_priv, @@ -414,7 +421,8 @@ icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv, intel_de_rmw(dev_priv, regs->driver, 0, HSW_PWR_WELL_CTL_REQ(pw_idx)); - if (DISPLAY_VER(dev_priv) < 12) + /* FIXME this is a mess */ + if (phy != PHY_NONE) intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy), 0, ICL_LANE_ENABLE_AUX); @@ -437,7 +445,10 @@ icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv, drm_WARN_ON(&dev_priv->drm, !IS_ICELAKE(dev_priv)); - intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy), ICL_LANE_ENABLE_AUX, 0); + /* FIXME this is a mess */ + if (phy != PHY_NONE) + intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy), + ICL_LANE_ENABLE_AUX, 0); intel_de_rmw(dev_priv, regs->driver, HSW_PWR_WELL_CTL_REQ(pw_idx), 0); diff --git a/drivers/gpu/drm/i915/display/intel_display_trace.h b/drivers/gpu/drm/i915/display/intel_display_trace.h index 99bdb833591ce1..7862e7cefe0278 100644 --- a/drivers/gpu/drm/i915/display/intel_display_trace.h +++ b/drivers/gpu/drm/i915/display/intel_display_trace.h @@ -411,7 +411,7 @@ TRACE_EVENT(intel_fbc_activate, struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev), plane->pipe); __assign_str(dev, __dev_name_kms(plane)); - __assign_str(name, plane->base.name) + __assign_str(name, plane->base.name); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); @@ -438,7 +438,7 @@ TRACE_EVENT(intel_fbc_deactivate, struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev), plane->pipe); __assign_str(dev, __dev_name_kms(plane)); - __assign_str(name, plane->base.name) + __assign_str(name, plane->base.name); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); @@ -465,7 +465,7 @@ TRACE_EVENT(intel_fbc_nuke, struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev), plane->pipe); __assign_str(dev, __dev_name_kms(plane)); - __assign_str(name, plane->base.name) + __assign_str(name, plane->base.name); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 731f2ec04d5cda..1c23b186aff20c 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -701,6 +701,7 @@ struct intel_plane_state { #define PLANE_HAS_FENCE BIT(0) struct intel_fb_view view; + u32 phys_dma_addr; /* for cursor_needs_physical */ /* Plane pxp decryption state */ bool decrypt; @@ -1083,6 +1084,7 @@ struct intel_crtc_state { unsigned fb_bits; /* framebuffers to flip */ bool update_pipe; /* can a fast modeset be performed? */ + bool update_m_n; /* update M/N seamlessly during fastset? */ bool disable_cxsr; bool update_wm_pre, update_wm_post; /* watermarks are updated */ bool fifo_changed; /* FIFO split is changed */ @@ -1195,7 +1197,6 @@ struct intel_crtc_state { /* m2_n2 for eDP downclock */ struct intel_link_m_n dp_m2_n2; bool has_drrs; - bool seamless_m_n; /* PSR is supported but might not be enabled due the lack of enabled planes */ bool has_psr; @@ -1362,6 +1363,8 @@ struct intel_crtc_state { u16 linetime; u16 ips_linetime; + bool enhanced_framing; + /* Forward Error correction State */ bool fec_enable; diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c index 5f479f3828bbee..8751973b5730fe 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -389,7 +389,7 @@ disable_all_flip_queue_events(struct drm_i915_private *i915) enum intel_dmc_id dmc_id; /* TODO: check if the following applies to all D13+ platforms. */ - if (!IS_DG2(i915) && !IS_TIGERLAKE(i915)) + if (!IS_TIGERLAKE(i915)) return; for_each_dmc_id(dmc_id) { @@ -493,6 +493,45 @@ void intel_dmc_disable_pipe(struct drm_i915_private *i915, enum pipe pipe) intel_de_rmw(i915, PIPEDMC_CONTROL(pipe), PIPEDMC_ENABLE, 0); } +static bool is_dmc_evt_ctl_reg(struct drm_i915_private *i915, + enum intel_dmc_id dmc_id, i915_reg_t reg) +{ + u32 offset = i915_mmio_reg_offset(reg); + u32 start = i915_mmio_reg_offset(DMC_EVT_CTL(i915, dmc_id, 0)); + u32 end = i915_mmio_reg_offset(DMC_EVT_CTL(i915, dmc_id, DMC_EVENT_HANDLER_COUNT_GEN12)); + + return offset >= start && offset < end; +} + +static bool disable_dmc_evt(struct drm_i915_private *i915, + enum intel_dmc_id dmc_id, + i915_reg_t reg, u32 data) +{ + if (!is_dmc_evt_ctl_reg(i915, dmc_id, reg)) + return false; + + /* keep all pipe DMC events disabled by default */ + if (dmc_id != DMC_FW_MAIN) + return true; + + return false; +} + +static u32 dmc_mmiodata(struct drm_i915_private *i915, + struct intel_dmc *dmc, + enum intel_dmc_id dmc_id, int i) +{ + if (disable_dmc_evt(i915, dmc_id, + dmc->dmc_info[dmc_id].mmioaddr[i], + dmc->dmc_info[dmc_id].mmiodata[i])) + return REG_FIELD_PREP(DMC_EVT_CTL_TYPE_MASK, + DMC_EVT_CTL_TYPE_EDGE_0_1) | + REG_FIELD_PREP(DMC_EVT_CTL_EVENT_ID_MASK, + DMC_EVT_CTL_EVENT_ID_FALSE); + else + return dmc->dmc_info[dmc_id].mmiodata[i]; +} + /** * intel_dmc_load_program() - write the firmware from memory to register. * @i915: i915 drm device. @@ -532,7 +571,7 @@ void intel_dmc_load_program(struct drm_i915_private *i915) for_each_dmc_id(dmc_id) { for (i = 0; i < dmc->dmc_info[dmc_id].mmio_count; i++) { intel_de_write(i915, dmc->dmc_info[dmc_id].mmioaddr[i], - dmc->dmc_info[dmc_id].mmiodata[i]); + dmc_mmiodata(i915, dmc, dmc_id, i)); } } diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index e0e4cb52928461..c8b6d0f79c9b41 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -393,6 +393,10 @@ bool intel_dp_can_bigjoiner(struct intel_dp *intel_dp) struct intel_encoder *encoder = &intel_dig_port->base; struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + /* eDP MSO is not compatible with joiner */ + if (intel_dp->mso_link_count) + return false; + return DISPLAY_VER(dev_priv) >= 12 || (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A); @@ -430,7 +434,7 @@ static int mtl_max_source_rate(struct intel_dp *intel_dp) enum phy phy = intel_port_to_phy(i915, dig_port->base.port); if (intel_is_c10phy(i915, phy)) - return intel_dp_is_edp(intel_dp) ? 675000 : 810000; + return 810000; return 2000000; } @@ -1127,6 +1131,10 @@ intel_dp_mode_valid(struct drm_connector *_connector, enum drm_mode_status status; bool dsc = false, bigjoiner = false; + status = intel_cpu_transcoder_mode_valid(dev_priv, mode); + if (status != MODE_OK) + return status; + if (mode->flags & DRM_MODE_FLAG_DBLCLK) return MODE_H_ILLEGAL; @@ -1306,13 +1314,14 @@ bool intel_dp_has_hdmi_sink(struct intel_dp *intel_dp) static bool intel_dp_source_supports_fec(struct intel_dp *intel_dp, const struct intel_crtc_state *pipe_config) { + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - /* On TGL, FEC is supported on all Pipes */ if (DISPLAY_VER(dev_priv) >= 12) return true; - if (DISPLAY_VER(dev_priv) == 11 && pipe_config->cpu_transcoder != TRANSCODER_A) + if (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A && + !intel_crtc_has_type(pipe_config, INTEL_OUTPUT_DP_MST)) return true; return false; @@ -2143,8 +2152,12 @@ intel_dp_drrs_compute_config(struct intel_connector *connector, intel_panel_downclock_mode(connector, &pipe_config->hw.adjusted_mode); int pixel_clock; - if (has_seamless_m_n(connector)) - pipe_config->seamless_m_n = true; + /* + * FIXME all joined pipes share the same transcoder. + * Need to account for that when updating M/N live. + */ + if (has_seamless_m_n(connector) && !pipe_config->bigjoiner_pipes) + pipe_config->update_m_n = true; if (!can_enable_drrs(connector, pipe_config, downclock_mode)) { if (intel_cpu_transcoder_has_m2_n2(i915, pipe_config->cpu_transcoder)) @@ -2308,6 +2321,9 @@ intel_dp_compute_config(struct intel_encoder *encoder, pipe_config->limited_color_range = intel_dp_limited_color_range(pipe_config, conn_state); + pipe_config->enhanced_framing = + drm_dp_enhanced_frame_cap(intel_dp->dpcd); + if (pipe_config->dsc.compression_enable) output_bpp = pipe_config->dsc.compressed_bpp; else @@ -3980,7 +3996,7 @@ static void intel_dp_process_phy_request(struct intel_dp *intel_dp, intel_dp->train_set, crtc_state->lane_count); drm_dp_set_phy_test_pattern(&intel_dp->aux, data, - link_status[DP_DPCD_REV]); + intel_dp->dpcd[DP_DPCD_REV]); } static u8 intel_dp_autotest_phy_pattern(struct intel_dp *intel_dp) @@ -4358,6 +4374,8 @@ int intel_dp_retrain_link(struct intel_encoder *encoder, !intel_dp_mst_is_master_trans(crtc_state)) continue; + intel_dp->link_trained = false; + intel_dp_check_frl_training(intel_dp); intel_dp_pcon_dsc_configure(intel_dp, crtc_state); intel_dp_start_link_train(intel_dp, crtc_state); @@ -5517,8 +5535,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, * (eg. Acer Chromebook C710), so we'll check it only if multiple * ports are attempting to use the same AUX CH, according to VBT. */ - if (intel_bios_dp_has_shared_aux_ch(encoder->devdata) && - !intel_digital_port_connected(encoder)) { + if (intel_bios_dp_has_shared_aux_ch(encoder->devdata)) { /* * If this fails, presume the DPCD answer came * from some other port using the same AUX CH. @@ -5526,10 +5543,27 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, * FIXME maybe cleaner to check this before the * DPCD read? Would need sort out the VDD handling... */ - drm_info(&dev_priv->drm, - "[ENCODER:%d:%s] HPD is down, disabling eDP\n", - encoder->base.base.id, encoder->base.name); - goto out_vdd_off; + if (!intel_digital_port_connected(encoder)) { + drm_info(&dev_priv->drm, + "[ENCODER:%d:%s] HPD is down, disabling eDP\n", + encoder->base.base.id, encoder->base.name); + goto out_vdd_off; + } + + /* + * Unfortunately even the HPD based detection fails on + * eg. Asus B360M-A (CFL+CNP), so as a last resort fall + * back to checking for a VGA branch device. Only do this + * on known affected platforms to minimize false positives. + */ + if (DISPLAY_VER(dev_priv) == 9 && drm_dp_is_branch(intel_dp->dpcd) && + (intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK) == + DP_DWN_STRM_PORT_TYPE_ANALOG) { + drm_info(&dev_priv->drm, + "[ENCODER:%d:%s] VGA converter detected, disabling eDP\n", + encoder->base.base.id, encoder->base.name); + goto out_vdd_off; + } } mutex_lock(&dev_priv->drm.mode_config.mutex); diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index a263773f4d68a4..eb5559e1a20024 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -114,10 +114,24 @@ intel_dp_set_lttpr_transparent_mode(struct intel_dp *intel_dp, bool enable) return drm_dp_dpcd_write(&intel_dp->aux, DP_PHY_REPEATER_MODE, &val, 1) == 1; } -static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +static bool intel_dp_lttpr_transparent_mode_enabled(struct intel_dp *intel_dp) +{ + return intel_dp->lttpr_common_caps[DP_PHY_REPEATER_MODE - + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV] == + DP_PHY_REPEATER_MODE_TRANSPARENT; +} + +/* + * Read the LTTPR common capabilities and switch the LTTPR PHYs to + * non-transparent mode if this is supported. Preserve the + * transparent/non-transparent mode on an active link. + * + * Return the number of detected LTTPRs in non-transparent mode or 0 if the + * LTTPRs are in transparent mode or the detection failed. + */ +static int intel_dp_init_lttpr_phys(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEIVER_CAP_SIZE]) { int lttpr_count; - int i; if (!intel_dp_read_lttpr_common_caps(intel_dp, dpcd)) return 0; @@ -131,6 +145,19 @@ static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEI if (lttpr_count == 0) return 0; + /* + * Don't change the mode on an active link, to prevent a loss of link + * synchronization. See DP Standard v2.0 3.6.7. about the LTTPR + * resetting its internal state when the mode is changed from + * non-transparent to transparent. + */ + if (intel_dp->link_trained) { + if (lttpr_count < 0 || intel_dp_lttpr_transparent_mode_enabled(intel_dp)) + goto out_reset_lttpr_count; + + return lttpr_count; + } + /* * See DP Standard v2.0 3.6.6.1. about the explicit disabling of * non-transparent mode and the disable->enable non-transparent mode @@ -151,11 +178,25 @@ static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEI "Switching to LTTPR non-transparent LT mode failed, fall-back to transparent mode\n"); intel_dp_set_lttpr_transparent_mode(intel_dp, true); - intel_dp_reset_lttpr_count(intel_dp); - return 0; + goto out_reset_lttpr_count; } + return lttpr_count; + +out_reset_lttpr_count: + intel_dp_reset_lttpr_count(intel_dp); + + return 0; +} + +static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + int lttpr_count; + int i; + + lttpr_count = intel_dp_init_lttpr_phys(intel_dp, dpcd); + for (i = 0; i < lttpr_count; i++) intel_dp_read_lttpr_phy_caps(intel_dp, dpcd, DP_PHY_LTTPR(i)); @@ -650,19 +691,30 @@ intel_dp_update_link_bw_set(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, u8 link_bw, u8 rate_select) { - u8 link_config[2]; + u8 lane_count = crtc_state->lane_count; + + if (crtc_state->enhanced_framing) + lane_count |= DP_LANE_COUNT_ENHANCED_FRAME_EN; - /* Write the link configuration data */ - link_config[0] = link_bw; - link_config[1] = crtc_state->lane_count; - if (drm_dp_enhanced_frame_cap(intel_dp->dpcd)) - link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; - drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, 2); - - /* eDP 1.4 rate select method. */ - if (!link_bw) - drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_RATE_SET, - &rate_select, 1); + if (link_bw) { + /* DP and eDP v1.3 and earlier link bw set method. */ + u8 link_config[] = { link_bw, lane_count }; + + drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, + ARRAY_SIZE(link_config)); + } else { + /* + * eDP v1.4 and later link rate set method. + * + * eDP v1.4x sinks shall ignore DP_LINK_RATE_SET if + * DP_LINK_BW_SET is set. Avoid writing DP_LINK_BW_SET. + * + * eDP v1.5 sinks allow choosing either, and the last choice + * shall be active. + */ + drm_dp_dpcd_writeb(&intel_dp->aux, DP_LANE_COUNT_SET, lane_count); + drm_dp_dpcd_writeb(&intel_dp->aux, DP_LINK_RATE_SET, rate_select); + } } /* @@ -1342,10 +1394,10 @@ void intel_dp_start_link_train(struct intel_dp *intel_dp, { struct drm_i915_private *i915 = dp_to_i915(intel_dp); bool passed; - /* - * TODO: Reiniting LTTPRs here won't be needed once proper connector - * HW state readout is added. + * Reinit the LTTPRs here to ensure that they are switched to + * non-transparent mode. During an earlier LTTPR detection this + * could've been prevented by an active link. */ int lttpr_count = intel_dp_init_lttpr_and_dprx_caps(intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index e3f176a093d2f3..d2f8f20722d92c 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -109,8 +109,7 @@ static int intel_dp_mst_find_vcpi_slots_for_bpp(struct intel_encoder *encoder, continue; crtc_state->pbn = drm_dp_calc_pbn_mode(adjusted_mode->crtc_clock, - dsc ? bpp << 4 : bpp, - dsc); + bpp << 4); slots = drm_dp_atomic_find_time_slots(state, &intel_dp->mst_mgr, connector->port, @@ -921,6 +920,10 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector, return 0; } + *status = intel_cpu_transcoder_mode_valid(dev_priv, mode); + if (*status != MODE_OK) + return 0; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) { *status = MODE_NO_DBLESCAN; return 0; @@ -937,7 +940,7 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector, return ret; if (mode_rate > max_rate || mode->clock > max_dotclk || - drm_dp_calc_pbn_mode(mode->clock, min_bpp, false) > port->full_pbn) { + drm_dp_calc_pbn_mode(mode->clock, min_bpp << 4) > port->full_pbn) { *status = MODE_CLOCK_HIGH; return 0; } @@ -955,9 +958,13 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector, if (intel_dp_need_bigjoiner(intel_dp, mode->hdisplay, target_clock)) { bigjoiner = true; max_dotclk *= 2; + + /* TODO: add support for bigjoiner */ + *status = MODE_CLOCK_HIGH; + return 0; } - if (DISPLAY_VER(dev_priv) >= 10 && + if (HAS_DSC_MST(dev_priv) && drm_dp_sink_supports_dsc(intel_dp->dsc_dpcd)) { /* * TBD pass the connector BPC, @@ -988,11 +995,15 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector, * Big joiner configuration needs DSC for TGL which is not true for * XE_LPD where uncompressed joiner is supported. */ - if (DISPLAY_VER(dev_priv) < 13 && bigjoiner && !dsc) - return MODE_CLOCK_HIGH; + if (DISPLAY_VER(dev_priv) < 13 && bigjoiner && !dsc) { + *status = MODE_CLOCK_HIGH; + return 0; + } - if (mode_rate > max_rate && !dsc) - return MODE_CLOCK_HIGH; + if (mode_rate > max_rate && !dsc) { + *status = MODE_CLOCK_HIGH; + return 0; + } *status = intel_mode_valid_max_plane_size(dev_priv, mode, false); return 0; diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index 6d68b36292d361..247e7d675e2b93 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -1556,7 +1556,7 @@ static void skl_wrpll_params_populate(struct skl_wrpll_params *params, } static int -skl_ddi_calculate_wrpll(int clock /* in Hz */, +skl_ddi_calculate_wrpll(int clock, int ref_clock, struct skl_wrpll_params *wrpll_params) { @@ -1581,7 +1581,7 @@ skl_ddi_calculate_wrpll(int clock /* in Hz */, }; unsigned int dco, d, i; unsigned int p0, p1, p2; - u64 afe_clock = clock * 5; /* AFE Clock is 5x Pixel clock */ + u64 afe_clock = (u64)clock * 1000 * 5; /* AFE Clock is 5x Pixel clock, in Hz */ for (d = 0; d < ARRAY_SIZE(dividers); d++) { for (dco = 0; dco < ARRAY_SIZE(dco_central_freq); dco++) { @@ -1713,7 +1713,7 @@ static int skl_ddi_hdmi_pll_dividers(struct intel_crtc_state *crtc_state) ctrl1 |= DPLL_CTRL1_HDMI_MODE(0); - ret = skl_ddi_calculate_wrpll(crtc_state->port_clock * 1000, + ret = skl_ddi_calculate_wrpll(crtc_state->port_clock, i915->display.dpll.ref_clks.nssc, &wrpll_params); if (ret) return ret; @@ -2462,7 +2462,7 @@ static void icl_wrpll_params_populate(struct skl_wrpll_params *params, static bool ehl_combo_pll_div_frac_wa_needed(struct drm_i915_private *i915) { - return (((IS_ELKHARTLAKE(i915) || IS_JASPERLAKE(i915)) && + return ((IS_ELKHARTLAKE(i915) && IS_DISPLAY_STEP(i915, STEP_B0, STEP_FOREVER)) || IS_TIGERLAKE(i915) || IS_ALDERLAKE_S(i915) || IS_ALDERLAKE_P(i915)) && i915->display.dpll.ref_clks.nssc == 38400; diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c index b386894c3a6db2..d1cfa966d48dac 100644 --- a/drivers/gpu/drm/i915/display/intel_dvo.c +++ b/drivers/gpu/drm/i915/display/intel_dvo.c @@ -217,11 +217,17 @@ intel_dvo_mode_valid(struct drm_connector *_connector, struct drm_display_mode *mode) { struct intel_connector *connector = to_intel_connector(_connector); + struct drm_i915_private *i915 = to_i915(connector->base.dev); struct intel_dvo *intel_dvo = intel_attached_dvo(connector); const struct drm_display_mode *fixed_mode = intel_panel_fixed_mode(connector, mode); int max_dotclk = to_i915(connector->base.dev)->max_dotclk_freq; int target_clock = mode->clock; + enum drm_mode_status status; + + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c index 446bbf7986b6f7..689b7c16d30072 100644 --- a/drivers/gpu/drm/i915/display/intel_fb.c +++ b/drivers/gpu/drm/i915/display/intel_fb.c @@ -1370,7 +1370,8 @@ plane_view_scanout_stride(const struct intel_framebuffer *fb, int color_plane, struct drm_i915_private *i915 = to_i915(fb->base.dev); unsigned int stride_tiles; - if (IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) + if ((IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) && + src_stride_tiles < dst_stride_tiles) stride_tiles = src_stride_tiles; else stride_tiles = dst_stride_tiles; @@ -1497,8 +1498,20 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p size += remap_info->size; } else { - unsigned int dst_stride = plane_view_dst_stride_tiles(fb, color_plane, - remap_info->width); + unsigned int dst_stride; + + /* + * The hardware automagically calculates the CCS AUX surface + * stride from the main surface stride so can't really remap a + * smaller subset (unless we'd remap in whole AUX page units). + */ + if (intel_fb_needs_pot_stride_remap(fb) && + intel_fb_is_ccs_modifier(fb->base.modifier)) + dst_stride = remap_info->src_stride; + else + dst_stride = remap_info->width; + + dst_stride = plane_view_dst_stride_tiles(fb, color_plane, dst_stride); assign_chk_ovf(i915, remap_info->dst_stride, dst_stride); color_plane_info->mapping_stride = dst_stride * diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c index fffd568070d414..a131656757f2b6 100644 --- a/drivers/gpu/drm/i915/display/intel_fb_pin.c +++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c @@ -254,6 +254,16 @@ int intel_plane_pin_fb(struct intel_plane_state *plane_state) return PTR_ERR(vma); plane_state->ggtt_vma = vma; + + /* + * Pre-populate the dma address before we enter the vblank + * evade critical section as i915_gem_object_get_dma_address() + * will trigger might_sleep() even if it won't actually sleep, + * which is the case when the fb has already been pinned. + */ + if (phys_cursor) + plane_state->phys_dma_addr = + i915_gem_object_get_dma_address(intel_fb_obj(fb), 0); } else { struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index a42549fa96918e..cb99839afcd03a 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -1005,7 +1005,8 @@ static void intel_hdcp_update_value(struct intel_connector *connector, hdcp->value = value; if (update_property) { drm_connector_get(&connector->base); - queue_work(i915->unordered_wq, &hdcp->prop_work); + if (!queue_work(i915->unordered_wq, &hdcp->prop_work)) + drm_connector_put(&connector->base); } } @@ -2480,7 +2481,8 @@ void intel_hdcp_update_pipe(struct intel_atomic_state *state, mutex_lock(&hdcp->mutex); hdcp->value = DRM_MODE_CONTENT_PROTECTION_DESIRED; drm_connector_get(&connector->base); - queue_work(i915->unordered_wq, &hdcp->prop_work); + if (!queue_work(i915->unordered_wq, &hdcp->prop_work)) + drm_connector_put(&connector->base); mutex_unlock(&hdcp->mutex); } @@ -2497,7 +2499,9 @@ void intel_hdcp_update_pipe(struct intel_atomic_state *state, */ if (!desired_and_not_enabled && !content_protection_type_changed) { drm_connector_get(&connector->base); - queue_work(i915->unordered_wq, &hdcp->prop_work); + if (!queue_work(i915->unordered_wq, &hdcp->prop_work)) + drm_connector_put(&connector->base); + } } diff --git a/drivers/gpu/drm/i915/display/intel_hdcp_regs.h b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h index 8023c85c7fa0ea..74059384892af8 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp_regs.h +++ b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h @@ -249,7 +249,7 @@ #define HDCP2_STREAM_STATUS(dev_priv, trans, port) \ (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP2_STREAM_STATUS(trans) : \ - PIPE_HDCP2_STREAM_STATUS(pipe)) + PIPE_HDCP2_STREAM_STATUS(port)) #define _PORTA_HDCP2_AUTH_STREAM 0x66F00 #define _PORTB_HDCP2_AUTH_STREAM 0x66F04 diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index 94a7e1537f4278..bc975918e0eb45 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -1986,6 +1986,10 @@ intel_hdmi_mode_valid(struct drm_connector *connector, bool ycbcr_420_only; enum intel_output_format sink_format; + status = intel_cpu_transcoder_mode_valid(dev_priv, mode); + if (status != MODE_OK) + return status; + if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING) clock *= 2; diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c index 3ace56979b70e0..dcb07d9a739d95 100644 --- a/drivers/gpu/drm/i915/display/intel_lvds.c +++ b/drivers/gpu/drm/i915/display/intel_lvds.c @@ -389,11 +389,16 @@ intel_lvds_mode_valid(struct drm_connector *_connector, struct drm_display_mode *mode) { struct intel_connector *connector = to_intel_connector(_connector); + struct drm_i915_private *i915 = to_i915(connector->base.dev); const struct drm_display_mode *fixed_mode = intel_panel_fixed_mode(connector, mode); int max_pixclk = to_i915(connector->base.dev)->max_dotclk_freq; enum drm_mode_status status; + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 97d5eef10130df..5cf3db7058b98c 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -674,7 +674,9 @@ static void hsw_activate_psr1(struct intel_dp *intel_dp) val |= EDP_PSR_IDLE_FRAMES(psr_compute_idle_frames(intel_dp)); - val |= EDP_PSR_MAX_SLEEP_TIME(max_sleep_time); + if (DISPLAY_VER(dev_priv) < 20) + val |= EDP_PSR_MAX_SLEEP_TIME(max_sleep_time); + if (IS_HASWELL(dev_priv)) val |= EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES; @@ -1398,9 +1400,21 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp, * can rely on frontbuffer tracking. */ mask = EDP_PSR_DEBUG_MASK_MEMUP | - EDP_PSR_DEBUG_MASK_HPD | - EDP_PSR_DEBUG_MASK_LPSP | - EDP_PSR_DEBUG_MASK_MAX_SLEEP; + EDP_PSR_DEBUG_MASK_HPD; + + /* + * For some unknown reason on HSW non-ULT (or at least on + * Dell Latitude E6540) external displays start to flicker + * when PSR is enabled on the eDP. SR/PC6 residency is much + * higher than should be possible with an external display. + * As a workaround leave LPSP unmasked to prevent PSR entry + * when external displays are active. + */ + if (DISPLAY_VER(dev_priv) >= 8 || IS_HASWELL_ULT(dev_priv)) + mask |= EDP_PSR_DEBUG_MASK_LPSP; + + if (DISPLAY_VER(dev_priv) < 20) + mask |= EDP_PSR_DEBUG_MASK_MAX_SLEEP; /* * No separate pipe reg write mask on hsw/bdw, so have to unmask all diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 7d25a64698e2f5..18ae41d5f4f988 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -1212,7 +1212,7 @@ static bool intel_sdvo_set_tv_format(struct intel_sdvo *intel_sdvo, struct intel_sdvo_tv_format format; u32 format_map; - format_map = 1 << conn_state->tv.mode; + format_map = 1 << conn_state->tv.legacy_mode; memset(&format, 0, sizeof(format)); memcpy(&format, &format_map, min(sizeof(format), sizeof(format_map))); @@ -1906,13 +1906,19 @@ static enum drm_mode_status intel_sdvo_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + struct drm_i915_private *i915 = to_i915(connector->dev); struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector)); struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector); - int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; bool has_hdmi_sink = intel_has_hdmi_sink(intel_sdvo_connector, connector->state); + int max_dotclk = i915->max_dotclk_freq; + enum drm_mode_status status; int clock = mode->clock; + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; @@ -2289,7 +2295,7 @@ static int intel_sdvo_get_tv_modes(struct drm_connector *connector) * Read the list of supported input resolutions for the selected TV * format. */ - format_map = 1 << conn_state->tv.mode; + format_map = 1 << conn_state->tv.legacy_mode; memcpy(&tv_res, &format_map, min(sizeof(format_map), sizeof(struct intel_sdvo_sdtv_resolution_request))); @@ -2354,7 +2360,7 @@ intel_sdvo_connector_atomic_get_property(struct drm_connector *connector, int i; for (i = 0; i < intel_sdvo_connector->format_supported_num; i++) - if (state->tv.mode == intel_sdvo_connector->tv_format_supported[i]) { + if (state->tv.legacy_mode == intel_sdvo_connector->tv_format_supported[i]) { *val = i; return 0; @@ -2410,7 +2416,7 @@ intel_sdvo_connector_atomic_set_property(struct drm_connector *connector, struct intel_sdvo_connector_state *sdvo_state = to_intel_sdvo_connector_state(state); if (property == intel_sdvo_connector->tv_format) { - state->tv.mode = intel_sdvo_connector->tv_format_supported[val]; + state->tv.legacy_mode = intel_sdvo_connector->tv_format_supported[val]; if (state->crtc) { struct drm_crtc_state *crtc_state = @@ -3065,7 +3071,7 @@ static bool intel_sdvo_tv_create_property(struct intel_sdvo *intel_sdvo, drm_property_add_enum(intel_sdvo_connector->tv_format, i, tv_format_names[intel_sdvo_connector->tv_format_supported[i]]); - intel_sdvo_connector->base.base.state->tv.mode = intel_sdvo_connector->tv_format_supported[0]; + intel_sdvo_connector->base.base.state->tv.legacy_mode = intel_sdvo_connector->tv_format_supported[0]; drm_object_attach_property(&intel_sdvo_connector->base.base.base, intel_sdvo_connector->tv_format, 0); return true; diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index 3ebf41859043e9..cdf2455440beaf 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -58,7 +58,7 @@ struct intel_tc_port { struct delayed_work link_reset_work; int link_refcount; bool legacy_port:1; - char port_name[8]; + const char *port_name; enum tc_port_mode mode; enum tc_port_mode init_mode; enum phy_fia phy_fia; @@ -1841,8 +1841,12 @@ int intel_tc_port_init(struct intel_digital_port *dig_port, bool is_legacy) else tc->phy_ops = &icl_tc_phy_ops; - snprintf(tc->port_name, sizeof(tc->port_name), - "%c/TC#%d", port_name(port), tc_port + 1); + tc->port_name = kasprintf(GFP_KERNEL, "%c/TC#%d", port_name(port), + tc_port + 1); + if (!tc->port_name) { + kfree(tc); + return -ENOMEM; + } mutex_init(&tc->lock); /* TODO: Combine the two works */ @@ -1863,6 +1867,7 @@ void intel_tc_port_cleanup(struct intel_digital_port *dig_port) { intel_tc_port_suspend(dig_port); + kfree(dig_port->tc->port_name); kfree(dig_port->tc); dig_port->tc = NULL; } diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c index 36b479b46b6004..042ed966807edb 100644 --- a/drivers/gpu/drm/i915/display/intel_tv.c +++ b/drivers/gpu/drm/i915/display/intel_tv.c @@ -949,7 +949,7 @@ intel_disable_tv(struct intel_atomic_state *state, static const struct tv_mode *intel_tv_mode_find(const struct drm_connector_state *conn_state) { - int format = conn_state->tv.mode; + int format = conn_state->tv.legacy_mode; return &tv_modes[format]; } @@ -958,8 +958,14 @@ static enum drm_mode_status intel_tv_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + struct drm_i915_private *i915 = to_i915(connector->dev); const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state); - int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; + int max_dotclk = i915->max_dotclk_freq; + enum drm_mode_status status; + + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; @@ -1704,7 +1710,7 @@ static void intel_tv_find_better_format(struct drm_connector *connector) break; } - connector->state->tv.mode = i; + connector->state->tv.legacy_mode = i; } static int @@ -1859,7 +1865,7 @@ static int intel_tv_atomic_check(struct drm_connector *connector, old_state = drm_atomic_get_old_connector_state(state, connector); new_crtc_state = drm_atomic_get_new_crtc_state(state, new_state->crtc); - if (old_state->tv.mode != new_state->tv.mode || + if (old_state->tv.legacy_mode != new_state->tv.legacy_mode || old_state->tv.margins.left != new_state->tv.margins.left || old_state->tv.margins.right != new_state->tv.margins.right || old_state->tv.margins.top != new_state->tv.margins.top || @@ -1896,7 +1902,7 @@ static void intel_tv_add_properties(struct drm_connector *connector) conn_state->tv.margins.right = 46; conn_state->tv.margins.bottom = 37; - conn_state->tv.mode = 0; + conn_state->tv.legacy_mode = 0; /* Create TV properties then attach current values */ for (i = 0; i < ARRAY_SIZE(tv_modes); i++) { @@ -1910,7 +1916,7 @@ static void intel_tv_add_properties(struct drm_connector *connector) drm_object_attach_property(&connector->base, i915->drm.mode_config.legacy_tv_mode_property, - conn_state->tv.mode); + conn_state->tv.legacy_mode); drm_object_attach_property(&connector->base, i915->drm.mode_config.tv_left_margin_property, conn_state->tv.margins.left); diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h index a9f44abfc9fc28..b50cd0dcabda90 100644 --- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h +++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h @@ -897,11 +897,6 @@ struct lfp_brightness_level { u16 reserved; } __packed; -#define EXP_BDB_LFP_BL_DATA_SIZE_REV_191 \ - offsetof(struct bdb_lfp_backlight_data, brightness_level) -#define EXP_BDB_LFP_BL_DATA_SIZE_REV_234 \ - offsetof(struct bdb_lfp_backlight_data, brightness_precision_bits) - struct bdb_lfp_backlight_data { u8 entry_size; struct lfp_backlight_data_entry data[16]; diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c index 88e4759b538b64..b844bdd16de99a 100644 --- a/drivers/gpu/drm/i915/display/intel_vrr.c +++ b/drivers/gpu/drm/i915/display/intel_vrr.c @@ -111,6 +111,13 @@ intel_vrr_compute_config(struct intel_crtc_state *crtc_state, if (!intel_vrr_is_capable(connector)) return; + /* + * FIXME all joined pipes share the same transcoder. + * Need to account for that during VRR toggle/push/etc. + */ + if (crtc_state->bigjoiner_pipes) + return; + if (adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) return; diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c index 1e7c97243fcf55..8a934bada6245d 100644 --- a/drivers/gpu/drm/i915/display/skl_scaler.c +++ b/drivers/gpu/drm/i915/display/skl_scaler.c @@ -504,7 +504,6 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv, { struct drm_plane *plane = NULL; struct intel_plane *intel_plane; - struct intel_plane_state *plane_state = NULL; struct intel_crtc_scaler_state *scaler_state = &crtc_state->scaler_state; struct drm_atomic_state *drm_state = crtc_state->uapi.state; @@ -536,6 +535,7 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv, /* walkthrough scaler_users bits and start assigning scalers */ for (i = 0; i < sizeof(scaler_state->scaler_users) * 8; i++) { + struct intel_plane_state *plane_state = NULL; int *scaler_id; const char *name; int idx, ret; diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index ffc15d278a39d3..d557ecd4e1ebe1 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -20,6 +20,7 @@ #include "skl_scaler.h" #include "skl_universal_plane.h" #include "skl_watermark.h" +#include "gt/intel_gt.h" #include "pxp/intel_pxp.h" static const u32 skl_plane_formats[] = { @@ -2169,8 +2170,8 @@ static bool skl_plane_has_rc_ccs(struct drm_i915_private *i915, enum pipe pipe, enum plane_id plane_id) { /* Wa_14017240301 */ - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0)) + if (IS_GFX_GT_IP_STEP(to_gt(i915), IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(to_gt(i915), IP_VER(12, 71), STEP_A0, STEP_B0)) return false; /* Wa_22011186057 */ diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index a96e7d028c5c61..d778b88413b777 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -1540,9 +1540,25 @@ static const struct drm_encoder_funcs intel_dsi_funcs = { .destroy = intel_dsi_encoder_destroy, }; +static enum drm_mode_status vlv_dsi_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) +{ + struct drm_i915_private *i915 = to_i915(connector->dev); + + if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { + enum drm_mode_status status; + + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; + } + + return intel_dsi_mode_valid(connector, mode); +} + static const struct drm_connector_helper_funcs intel_dsi_connector_helper_funcs = { .get_modes = intel_dsi_get_modes, - .mode_valid = intel_dsi_mode_valid, + .mode_valid = vlv_dsi_mode_valid, .atomic_check = intel_digital_connector_atomic_check, }; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 9a9ff84c90d7e6..e38f06a6e56ebc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -844,6 +844,7 @@ static int set_proto_ctx_sseu(struct drm_i915_file_private *fpriv, if (idx >= pc->num_user_engines) return -EINVAL; + idx = array_index_nospec(idx, pc->num_user_engines); pe = &pc->user_engines[idx]; /* Only render engine supports RPCS configuration. */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index d24c0ce8805c70..19156ba4b9ef40 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -405,8 +405,8 @@ static int ext_set_pat(struct i915_user_extension __user *base, void *data) BUILD_BUG_ON(sizeof(struct drm_i915_gem_create_ext_set_pat) != offsetofend(struct drm_i915_gem_create_ext_set_pat, rsvd)); - /* Limiting the extension only to Meteor Lake */ - if (!IS_METEORLAKE(i915)) + /* Limiting the extension only to Xe_LPG and beyond */ + if (GRAPHICS_VER_FULL(i915) < IP_VER(12, 70)) return -ENODEV; if (copy_from_user(&ext, base, sizeof(ext))) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 310654542b42c1..a59c17ec7fa366 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -290,6 +290,41 @@ static vm_fault_t vm_fault_cpu(struct vm_fault *vmf) return i915_error_to_vmf_fault(err); } +static void set_address_limits(struct vm_area_struct *area, + struct i915_vma *vma, + unsigned long obj_offset, + unsigned long *start_vaddr, + unsigned long *end_vaddr) +{ + unsigned long vm_start, vm_end, vma_size; /* user's memory parameters */ + long start, end; /* memory boundaries */ + + /* + * Let's move into the ">> PAGE_SHIFT" + * domain to be sure not to lose bits + */ + vm_start = area->vm_start >> PAGE_SHIFT; + vm_end = area->vm_end >> PAGE_SHIFT; + vma_size = vma->size >> PAGE_SHIFT; + + /* + * Calculate the memory boundaries by considering the offset + * provided by the user during memory mapping and the offset + * provided for the partial mapping. + */ + start = vm_start; + start -= obj_offset; + start += vma->gtt_view.partial.offset; + end = start + vma_size; + + start = max_t(long, start, vm_start); + end = min_t(long, end, vm_end); + + /* Let's move back into the "<< PAGE_SHIFT" domain */ + *start_vaddr = (unsigned long)start << PAGE_SHIFT; + *end_vaddr = (unsigned long)end << PAGE_SHIFT; +} + static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) { #define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT) @@ -302,14 +337,18 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) struct i915_ggtt *ggtt = to_gt(i915)->ggtt; bool write = area->vm_flags & VM_WRITE; struct i915_gem_ww_ctx ww; + unsigned long obj_offset; + unsigned long start, end; /* memory boundaries */ intel_wakeref_t wakeref; struct i915_vma *vma; pgoff_t page_offset; + unsigned long pfn; int srcu; int ret; - /* We don't use vmf->pgoff since that has the fake offset */ + obj_offset = area->vm_pgoff - drm_vma_node_start(&mmo->vma_node); page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT; + page_offset += obj_offset; trace_i915_gem_object_fault(obj, page_offset, true, write); @@ -402,12 +441,14 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) if (ret) goto err_unpin; + set_address_limits(area, vma, obj_offset, &start, &end); + + pfn = (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT; + pfn += (start - area->vm_start) >> PAGE_SHIFT; + pfn += obj_offset - vma->gtt_view.partial.offset; + /* Finally, remap it using the new GTT offset */ - ret = remap_io_mapping(area, - area->vm_start + (vma->gtt_view.partial.offset << PAGE_SHIFT), - (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT, - min_t(u64, vma->size, area->vm_end - area->vm_start), - &ggtt->iomap); + ret = remap_io_mapping(area, start, pfn, end - start, &ggtt->iomap); if (ret) goto err_fence; @@ -1088,6 +1129,8 @@ int i915_gem_fb_mmap(struct drm_i915_gem_object *obj, struct vm_area_struct *vma mmo = mmap_offset_attach(obj, mmap_type, NULL); if (IS_ERR(mmo)) return PTR_ERR(mmo); + + vma->vm_pgoff += drm_vma_node_start(&mmo->vma_node); } /* diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index f607b87890ddd6..c096fcdb2f1ed4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -285,7 +285,9 @@ bool i915_gem_object_has_iomem(const struct drm_i915_gem_object *obj); static inline bool i915_gem_object_is_shrinkable(const struct drm_i915_gem_object *obj) { - return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE); + /* TODO: make DPT shrinkable when it has no bound vmas */ + return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE) && + !obj->is_dpt; } static inline bool diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 9227f8146a583f..6dc097a2ac07b3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -1136,7 +1136,7 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) GEM_WARN_ON(!i915_ttm_cpu_maps_iomem(bo->resource)); } - if (wakeref & CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND) + if (wakeref && CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND != 0) intel_wakeref_auto(&to_i915(obj->base.dev)->runtime_pm.userfault_wakeref, msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 1d3ebdf4069b5d..c08b67593565c5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -379,6 +379,9 @@ i915_gem_userptr_release(struct drm_i915_gem_object *obj) { GEM_WARN_ON(obj->userptr.page_ref); + if (!obj->userptr.notifier.mm) + return; + mmu_interval_notifier_remove(&obj->userptr.notifier); obj->userptr.notifier.mm = NULL; } diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 7ad36198aab2a4..cddf8c16e9a726 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -4,9 +4,9 @@ */ #include "gen8_engine_cs.h" -#include "i915_drv.h" #include "intel_engine_regs.h" #include "intel_gpu_commands.h" +#include "intel_gt.h" #include "intel_lrc.h" #include "intel_ring.h" @@ -226,8 +226,8 @@ u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs) static int mtl_dummy_pipe_control(struct i915_request *rq) { /* Wa_14016712196 */ - if (IS_MTL_GRAPHICS_STEP(rq->i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(rq->i915, P, STEP_A0, STEP_B0)) { + if (IS_GFX_GT_IP_RANGE(rq->engine->gt, IP_VER(12, 70), IP_VER(12, 74)) || + IS_DG2(rq->i915)) { u32 *cs; /* dummy PIPE_CONTROL + depth flush */ @@ -808,6 +808,7 @@ u32 *gen12_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs) u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs) { struct drm_i915_private *i915 = rq->i915; + struct intel_gt *gt = rq->engine->gt; u32 flags = (PIPE_CONTROL_CS_STALL | PIPE_CONTROL_TLB_INVALIDATE | PIPE_CONTROL_TILE_CACHE_FLUSH | @@ -818,8 +819,7 @@ u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs) PIPE_CONTROL_FLUSH_ENABLE); /* Wa_14016712196 */ - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0)) + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74)) || IS_DG2(i915)) /* dummy PIPE_CONTROL + depth flush */ cs = gen12_emit_pipe_control(cs, 0, PIPE_CONTROL_DEPTH_CACHE_FLUSH, 0); diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index ecc990ec1b9526..f2973cd1a8aaef 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -258,8 +258,13 @@ static void signal_irq_work(struct irq_work *work) i915_request_put(rq); } + /* Lazy irq enabling after HW submission */ if (!READ_ONCE(b->irq_armed) && !list_empty(&b->signalers)) intel_breadcrumbs_arm_irq(b); + + /* And confirm that we still want irqs enabled before we yield */ + if (READ_ONCE(b->irq_armed) && !atomic_read(&b->active)) + intel_breadcrumbs_disarm_irq(b); } struct intel_breadcrumbs * @@ -310,13 +315,7 @@ void __intel_breadcrumbs_park(struct intel_breadcrumbs *b) return; /* Kick the work once more to drain the signalers, and disarm the irq */ - irq_work_sync(&b->irq_work); - while (READ_ONCE(b->irq_armed) && !atomic_read(&b->active)) { - local_irq_disable(); - signal_irq_work(&b->irq_work); - local_irq_enable(); - cond_resched(); - } + irq_work_queue(&b->irq_work); } void intel_breadcrumbs_free(struct kref *kref) @@ -399,7 +398,7 @@ static void insert_breadcrumb(struct i915_request *rq) * the request as it may have completed and raised the interrupt as * we were attaching it into the lists. */ - if (!b->irq_armed || __i915_request_is_complete(rq)) + if (!READ_ONCE(b->irq_armed) || __i915_request_is_complete(rq)) irq_work_queue(&b->irq_work); } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index e85d70a62123f9..d9bb352b8baab7 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -912,6 +912,29 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt) info->engine_mask &= ~BIT(GSC0); } + /* + * Do not create the command streamer for CCS slices beyond the first. + * All the workload submitted to the first engine will be shared among + * all the slices. + * + * Once the user will be allowed to customize the CCS mode, then this + * check needs to be removed. + */ + if (IS_DG2(gt->i915)) { + u8 first_ccs = __ffs(CCS_MASK(gt)); + + /* + * Store the number of active cslices before + * changing the CCS engine configuration + */ + gt->ccs.cslices = CCS_MASK(gt); + + /* Mask off all the CCS engine */ + info->engine_mask &= ~GENMASK(CCS3, CCS0); + /* Put back in the first CCS engine */ + info->engine_mask |= BIT(_CCS(first_ccs)); + } + return info->engine_mask; } @@ -1616,9 +1639,7 @@ static int __intel_engine_stop_cs(struct intel_engine_cs *engine, * Wa_22011802037: Prior to doing a reset, ensure CS is * stopped, set ring stop bit and prefetch disable bit to halt CS */ - if (IS_MTL_GRAPHICS_STEP(engine->i915, M, STEP_A0, STEP_B0) || - (GRAPHICS_VER(engine->i915) >= 11 && - GRAPHICS_VER_FULL(engine->i915) < IP_VER(12, 70))) + if (intel_engine_reset_needs_wa_22011802037(engine->gt)) intel_uncore_write_fw(uncore, RING_MODE_GEN7(engine->mmio_base), _MASKED_BIT_ENABLE(GEN12_GFX_PREFETCH_DISABLE)); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index b538b5c04948f6..5a3a5b29d15077 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -21,7 +21,7 @@ static void intel_gsc_idle_msg_enable(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; - if (IS_METEORLAKE(i915) && engine->id == GSC0) { + if (MEDIA_VER(i915) >= 13 && engine->id == GSC0) { intel_uncore_write(engine->gt->uncore, RC_PSMI_CTRL_GSCCS, _MASKED_BIT_DISABLE(IDLE_MSG_DISABLE)); @@ -278,9 +278,6 @@ static int __engine_park(struct intel_wakeref *wf) intel_engine_park_heartbeat(engine); intel_breadcrumbs_park(engine->breadcrumbs); - /* Must be reset upon idling, or we may miss the busy wakeup. */ - GEM_BUG_ON(engine->sched_engine->queue_priority_hint != INT_MIN); - if (engine->park) engine->park(engine); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c index dcedff41a825fc..d304e0a948f0d1 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_user.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c @@ -42,12 +42,15 @@ void intel_engine_add_user(struct intel_engine_cs *engine) (struct llist_head *)&engine->i915->uabi_engines); } -static const u8 uabi_classes[] = { +#define I915_NO_UABI_CLASS ((u16)(-1)) + +static const u16 uabi_classes[] = { [RENDER_CLASS] = I915_ENGINE_CLASS_RENDER, [COPY_ENGINE_CLASS] = I915_ENGINE_CLASS_COPY, [VIDEO_DECODE_CLASS] = I915_ENGINE_CLASS_VIDEO, [VIDEO_ENHANCEMENT_CLASS] = I915_ENGINE_CLASS_VIDEO_ENHANCE, [COMPUTE_CLASS] = I915_ENGINE_CLASS_COMPUTE, + [OTHER_CLASS] = I915_NO_UABI_CLASS, /* Not exposed to users, no uabi class. */ }; static int engine_cmp(void *priv, const struct list_head *A, @@ -202,6 +205,7 @@ static void engine_rename(struct intel_engine_cs *engine, const char *name, u16 void intel_engines_driver_register(struct drm_i915_private *i915) { + u16 name_instance, other_instance = 0; struct legacy_ring ring = {}; struct list_head *it, *next; struct rb_node **p, *prev; @@ -219,27 +223,28 @@ void intel_engines_driver_register(struct drm_i915_private *i915) if (intel_gt_has_unrecoverable_error(engine->gt)) continue; /* ignore incomplete engines */ - /* - * We don't want to expose the GSC engine to the users, but we - * still rename it so it is easier to identify in the debug logs - */ - if (engine->id == GSC0) { - engine_rename(engine, "gsc", 0); - continue; - } - GEM_BUG_ON(engine->class >= ARRAY_SIZE(uabi_classes)); engine->uabi_class = uabi_classes[engine->class]; + if (engine->uabi_class == I915_NO_UABI_CLASS) { + name_instance = other_instance++; + } else { + GEM_BUG_ON(engine->uabi_class >= + ARRAY_SIZE(i915->engine_uabi_class_count)); + name_instance = + i915->engine_uabi_class_count[engine->uabi_class]++; + } + engine->uabi_instance = name_instance; - GEM_BUG_ON(engine->uabi_class >= - ARRAY_SIZE(i915->engine_uabi_class_count)); - engine->uabi_instance = - i915->engine_uabi_class_count[engine->uabi_class]++; - - /* Replace the internal name with the final user facing name */ + /* + * Replace the internal name with the final user and log facing + * name. + */ engine_rename(engine, intel_engine_class_repr(engine->class), - engine->uabi_instance); + name_instance); + + if (engine->uabi_class == I915_NO_UABI_CLASS) + continue; rb_link_node(&engine->uabi_node, prev, p); rb_insert_color(&engine->uabi_node, &i915->uabi_engines); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 3292524469d509..2065be5a196bf6 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -3001,9 +3001,7 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine) * Wa_22011802037: In addition to stopping the cs, we need * to wait for any pending mi force wakeups */ - if (IS_MTL_GRAPHICS_STEP(engine->i915, M, STEP_A0, STEP_B0) || - (GRAPHICS_VER(engine->i915) >= 11 && - GRAPHICS_VER_FULL(engine->i915) < IP_VER(12, 70))) + if (intel_engine_reset_needs_wa_22011802037(engine->gt)) intel_engine_wait_for_pending_mi_fw(engine); engine->execlists.reset_ccid = active_ccid(engine); @@ -3274,6 +3272,9 @@ static void execlists_park(struct intel_engine_cs *engine) { cancel_timer(&engine->execlists.timer); cancel_timer(&engine->execlists.preempt); + + /* Reset upon idling, or we may delay the busy wakeup. */ + WRITE_ONCE(engine->sched_engine->queue_priority_hint, INT_MIN); } static void add_to_engine(struct i915_request *rq) @@ -3314,11 +3315,7 @@ static void remove_from_engine(struct i915_request *rq) static bool can_preempt(struct intel_engine_cs *engine) { - if (GRAPHICS_VER(engine->i915) > 8) - return true; - - /* GPGPU on bdw requires extra w/a; not implemented */ - return engine->class != RENDER_CLASS; + return GRAPHICS_VER(engine->i915) > 8; } static void kick_execlists(const struct i915_request *rq, int prio) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index da21f2786b5d7d..b20d8fe8aa95d5 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -190,6 +190,21 @@ void gen6_ggtt_invalidate(struct i915_ggtt *ggtt) spin_unlock_irq(&uncore->lock); } +static bool needs_wc_ggtt_mapping(struct drm_i915_private *i915) +{ + /* + * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range + * will be dropped. For WC mappings in general we have 64 byte burst + * writes when the WC buffer is flushed, so we can't use it, but have to + * resort to an uncached mapping. The WC issue is easily caught by the + * readback check when writing GTT PTE entries. + */ + if (!IS_GEN9_LP(i915) && GRAPHICS_VER(i915) < 11) + return true; + + return false; +} + static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt) { struct intel_uncore *uncore = ggtt->vm.gt->uncore; @@ -197,8 +212,12 @@ static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt) /* * Note that as an uncached mmio write, this will flush the * WCB of the writes into the GGTT before it triggers the invalidate. + * + * Only perform this when GGTT is mapped as WC, see ggtt_probe_common(). */ - intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN); + if (needs_wc_ggtt_mapping(ggtt->vm.i915)) + intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, + GFX_FLSH_CNTL_EN); } static void guc_ggtt_invalidate(struct i915_ggtt *ggtt) @@ -902,17 +921,11 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) GEM_WARN_ON(pci_resource_len(pdev, GEN4_GTTMMADR_BAR) != gen6_gttmmadr_size(i915)); phys_addr = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) + gen6_gttadr_offset(i915); - /* - * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range - * will be dropped. For WC mappings in general we have 64 byte burst - * writes when the WC buffer is flushed, so we can't use it, but have to - * resort to an uncached mapping. The WC issue is easily caught by the - * readback check when writing GTT PTE entries. - */ - if (IS_GEN9_LP(i915) || GRAPHICS_VER(i915) >= 11) - ggtt->gsm = ioremap(phys_addr, size); - else + if (needs_wc_ggtt_mapping(i915)) ggtt->gsm = ioremap_wc(phys_addr, size); + else + ggtt->gsm = ioremap(phys_addr, size); + if (!ggtt->gsm) { drm_err(&i915->drm, "Failed to map the ggtt page table\n"); return -ENOMEM; diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index 40371b8a9bbbd7..93bc1cc1ee7e64 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -298,6 +298,7 @@ void i915_vma_revoke_fence(struct i915_vma *vma) return; GEM_BUG_ON(fence->vma != vma); + i915_active_wait(&fence->active); GEM_BUG_ON(!i915_active_is_idle(&fence->active)); GEM_BUG_ON(atomic_read(&fence->pin_count)); diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index 449f0b7fc84343..95631e8f39e7b6 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -967,8 +967,6 @@ int intel_gt_probe_all(struct drm_i915_private *i915) err: i915_probe_error(i915, "Failed to initialize %s! (%d)\n", gtdef->name, ret); - intel_gt_release_all(i915); - return ret; } @@ -987,15 +985,6 @@ int intel_gt_tiles_init(struct drm_i915_private *i915) return 0; } -void intel_gt_release_all(struct drm_i915_private *i915) -{ - struct intel_gt *gt; - unsigned int id; - - for_each_gt(gt, i915, id) - i915->gt[id] = NULL; -} - void intel_gt_info_print(const struct intel_gt_info *info, struct drm_printer *p) { diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 6c34547b58b59f..6e63b46682f76b 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -14,6 +14,37 @@ struct drm_i915_private; struct drm_printer; +/* + * Check that the GT is a graphics GT and has an IP version within the + * specified range (inclusive). + */ +#define IS_GFX_GT_IP_RANGE(gt, from, until) ( \ + BUILD_BUG_ON_ZERO((from) < IP_VER(2, 0)) + \ + BUILD_BUG_ON_ZERO((until) < (from)) + \ + ((gt)->type != GT_MEDIA && \ + GRAPHICS_VER_FULL((gt)->i915) >= (from) && \ + GRAPHICS_VER_FULL((gt)->i915) <= (until))) + +/* + * Check that the GT is a graphics GT with a specific IP version and has + * a stepping in the range [from, until). The lower stepping bound is + * inclusive, the upper bound is exclusive. The most common use-case of this + * macro is for checking bounds for workarounds, which usually have a stepping + * ("from") at which the hardware issue is first present and another stepping + * ("until") at which a hardware fix is present and the software workaround is + * no longer necessary. E.g., + * + * IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) + * IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_B1, STEP_FOREVER) + * + * "STEP_FOREVER" can be passed as "until" for workarounds that have no upper + * stepping bound for the specified IP version. + */ +#define IS_GFX_GT_IP_STEP(gt, ipver, from, until) ( \ + BUILD_BUG_ON_ZERO((until) <= (from)) + \ + (IS_GFX_GT_IP_RANGE((gt), (ipver), (ipver)) && \ + IS_GRAPHICS_STEP((gt)->i915, (from), (until)))) + #define GT_TRACE(gt, fmt, ...) do { \ const struct intel_gt *gt__ __maybe_unused = (gt); \ GEM_TRACE("%s " fmt, dev_name(gt__->i915->drm.dev), \ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c new file mode 100644 index 00000000000000..3c62a44e9106ce --- /dev/null +++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2024 Intel Corporation + */ + +#include "i915_drv.h" +#include "intel_gt.h" +#include "intel_gt_ccs_mode.h" +#include "intel_gt_regs.h" + +unsigned int intel_gt_apply_ccs_mode(struct intel_gt *gt) +{ + int cslice; + u32 mode = 0; + int first_ccs = __ffs(CCS_MASK(gt)); + + if (!IS_DG2(gt->i915)) + return 0; + + /* Build the value for the fixed CCS load balancing */ + for (cslice = 0; cslice < I915_MAX_CCS; cslice++) { + if (gt->ccs.cslices & BIT(cslice)) + /* + * If available, assign the cslice + * to the first available engine... + */ + mode |= XEHP_CCS_MODE_CSLICE(cslice, first_ccs); + + else + /* + * ... otherwise, mark the cslice as + * unavailable if no CCS dispatches here + */ + mode |= XEHP_CCS_MODE_CSLICE(cslice, + XEHP_CCS_MODE_CSLICE_MASK); + } + + return mode; +} diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h new file mode 100644 index 00000000000000..55547f2ff426a4 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2024 Intel Corporation + */ + +#ifndef __INTEL_GT_CCS_MODE_H__ +#define __INTEL_GT_CCS_MODE_H__ + +struct intel_gt; + +unsigned int intel_gt_apply_ccs_mode(struct intel_gt *gt); + +#endif /* __INTEL_GT_CCS_MODE_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c index 2c0f1f3e28ff89..c6dec485aefbec 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c @@ -3,8 +3,7 @@ * Copyright © 2022 Intel Corporation */ -#include "i915_drv.h" - +#include "intel_gt.h" #include "intel_gt_mcr.h" #include "intel_gt_print.h" #include "intel_gt_regs.h" @@ -166,8 +165,8 @@ void intel_gt_mcr_init(struct intel_gt *gt) gt->steering_table[OADDRM] = xelpmp_oaddrm_steering_table; } else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) { /* Wa_14016747170 */ - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0)) + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0)) fuse = REG_FIELD_GET(MTL_GT_L3_EXC_MASK, intel_uncore_read(gt->uncore, MTL_GT_ACTIVITY_FACTOR)); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index 2cdfb2f713d026..64acab146b52f8 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -1468,8 +1468,14 @@ #define ECOBITS_PPGTT_CACHE4B (0 << 8) #define GEN12_RCU_MODE _MMIO(0x14800) +#define XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE REG_BIT(1) #define GEN12_RCU_MODE_CCS_ENABLE REG_BIT(0) +#define XEHP_CCS_MODE _MMIO(0x14804) +#define XEHP_CCS_MODE_CSLICE_MASK REG_GENMASK(2, 0) /* CCS0-3 + rsvd */ +#define XEHP_CCS_MODE_CSLICE_WIDTH ilog2(XEHP_CCS_MODE_CSLICE_MASK + 1) +#define XEHP_CCS_MODE_CSLICE(cslice, ccs) (ccs << (cslice * XEHP_CCS_MODE_CSLICE_WIDTH)) + #define CHV_FUSE_GT _MMIO(VLV_GUNIT_BASE + 0x2168) #define CHV_FGT_DISABLE_SS0 (1 << 10) #define CHV_FGT_DISABLE_SS1 (1 << 11) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index def7dd0eb6f196..cfdd2ad5e9549c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -207,6 +207,14 @@ struct intel_gt { [MAX_ENGINE_INSTANCE + 1]; enum intel_submission_method submission_method; + struct { + /* + * Mask of the non fused CCS slices + * to be used for the load balancing + */ + intel_engine_mask_t cslices; + } ccs; + /* * Default address space (either GGTT or ppGTT depending on arch). * diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index c378cc7c953c47..b99efa348ad1ec 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1316,29 +1316,6 @@ gen12_emit_cmd_buf_wa(const struct intel_context *ce, u32 *cs) return cs; } -/* - * On DG2 during context restore of a preempted context in GPGPU mode, - * RCS restore hang is detected. This is extremely timing dependent. - * To address this below sw wabb is implemented for DG2 A steppings. - */ -static u32 * -dg2_emit_rcs_hang_wabb(const struct intel_context *ce, u32 *cs) -{ - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = i915_mmio_reg_offset(GEN12_STATE_ACK_DEBUG(ce->engine->mmio_base)); - *cs++ = 0x21; - - *cs++ = MI_LOAD_REGISTER_REG; - *cs++ = i915_mmio_reg_offset(RING_NOPID(ce->engine->mmio_base)); - *cs++ = i915_mmio_reg_offset(XEHP_CULLBIT1); - - *cs++ = MI_LOAD_REGISTER_REG; - *cs++ = i915_mmio_reg_offset(RING_NOPID(ce->engine->mmio_base)); - *cs++ = i915_mmio_reg_offset(XEHP_CULLBIT2); - - return cs; -} - /* * The bspec's tuning guide asks us to program a vertical watermark value of * 0x3FF. However this register is not saved/restored properly by the @@ -1363,21 +1340,15 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs) cs = gen12_emit_cmd_buf_wa(ce, cs); cs = gen12_emit_restore_scratch(ce, cs); - /* Wa_22011450934:dg2 */ - if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_A0, STEP_B0) || - IS_DG2_GRAPHICS_STEP(ce->engine->i915, G11, STEP_A0, STEP_B0)) - cs = dg2_emit_rcs_hang_wabb(ce, cs); - /* Wa_16013000631:dg2 */ - if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_B0, STEP_C0) || - IS_DG2_G11(ce->engine->i915)) + if (IS_DG2_G11(ce->engine->i915)) cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0); cs = gen12_emit_aux_table_inv(ce->engine, cs); /* Wa_16014892111 */ - if (IS_MTL_GRAPHICS_STEP(ce->engine->i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(ce->engine->i915, P, STEP_A0, STEP_B0) || + if (IS_GFX_GT_IP_STEP(ce->engine->gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(ce->engine->gt, IP_VER(12, 71), STEP_A0, STEP_B0) || IS_DG2(ce->engine->i915)) cs = dg2_emit_draw_watermark_setting(cs); @@ -1391,8 +1362,7 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs) cs = gen12_emit_restore_scratch(ce, cs); /* Wa_16013000631:dg2 */ - if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_B0, STEP_C0) || - IS_DG2_G11(ce->engine->i915)) + if (IS_DG2_G11(ce->engine->i915)) if (ce->engine->class == COMPUTE_CLASS) cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index 2c014407225ccb..07269ff3be136d 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -404,18 +404,6 @@ static const struct drm_i915_mocs_entry dg2_mocs_table[] = { MOCS_ENTRY(3, 0, L3_3_WB | L3_LKUP(1)), }; -static const struct drm_i915_mocs_entry dg2_mocs_table_g10_ax[] = { - /* Wa_14011441408: Set Go to Memory for MOCS#0 */ - MOCS_ENTRY(0, 0, L3_1_UC | L3_GLBGO(1) | L3_LKUP(1)), - /* UC - Coherent; GO:Memory */ - MOCS_ENTRY(1, 0, L3_1_UC | L3_GLBGO(1) | L3_LKUP(1)), - /* UC - Non-Coherent; GO:Memory */ - MOCS_ENTRY(2, 0, L3_1_UC | L3_GLBGO(1)), - - /* WB - LC */ - MOCS_ENTRY(3, 0, L3_3_WB | L3_LKUP(1)), -}; - static const struct drm_i915_mocs_entry pvc_mocs_table[] = { /* Error */ MOCS_ENTRY(0, 0, L3_3_WB), @@ -507,7 +495,7 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915, memset(table, 0, sizeof(struct drm_i915_mocs_table)); table->unused_entries_index = I915_MOCS_PTE; - if (IS_METEORLAKE(i915)) { + if (IS_GFX_GT_IP_RANGE(&i915->gt0, IP_VER(12, 70), IP_VER(12, 71))) { table->size = ARRAY_SIZE(mtl_mocs_table); table->table = mtl_mocs_table; table->n_entries = MTL_NUM_MOCS_ENTRIES; @@ -521,13 +509,8 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915, table->wb_index = 2; table->unused_entries_index = 2; } else if (IS_DG2(i915)) { - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) { - table->size = ARRAY_SIZE(dg2_mocs_table_g10_ax); - table->table = dg2_mocs_table_g10_ax; - } else { - table->size = ARRAY_SIZE(dg2_mocs_table); - table->table = dg2_mocs_table; - } + table->size = ARRAY_SIZE(dg2_mocs_table); + table->table = dg2_mocs_table; table->uc_index = 1; table->n_entries = GEN9_NUM_MOCS_ENTRIES; table->unused_entries_index = 3; diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index 58bb1c55294c93..9e113e9473260a 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -118,14 +118,12 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6) GEN6_RC_CTL_EI_MODE(1); /* - * Wa_16011777198 and BSpec 52698 - Render powergating must be off. + * BSpec 52698 - Render powergating must be off. * FIXME BSpec is outdated, disabling powergating for MTL is just * temporary wa and should be removed after fixing real cause * of forcewake timeouts. */ - if (IS_METEORLAKE(gt->i915) || - IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) || - IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0)) + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) pg_enable = GEN9_MEDIA_PG_ENABLE | GEN11_MEDIA_SAMPLER_PG_ENABLE; @@ -584,19 +582,23 @@ static void __intel_rc6_disable(struct intel_rc6 *rc6) static void rc6_res_reg_init(struct intel_rc6 *rc6) { - memset(rc6->res_reg, INVALID_MMIO_REG.reg, sizeof(rc6->res_reg)); + i915_reg_t res_reg[INTEL_RC6_RES_MAX] = { + [0 ... INTEL_RC6_RES_MAX - 1] = INVALID_MMIO_REG, + }; switch (rc6_to_gt(rc6)->type) { case GT_MEDIA: - rc6->res_reg[INTEL_RC6_RES_RC6] = MTL_MEDIA_MC6; + res_reg[INTEL_RC6_RES_RC6] = MTL_MEDIA_MC6; break; default: - rc6->res_reg[INTEL_RC6_RES_RC6_LOCKED] = GEN6_GT_GFX_RC6_LOCKED; - rc6->res_reg[INTEL_RC6_RES_RC6] = GEN6_GT_GFX_RC6; - rc6->res_reg[INTEL_RC6_RES_RC6p] = GEN6_GT_GFX_RC6p; - rc6->res_reg[INTEL_RC6_RES_RC6pp] = GEN6_GT_GFX_RC6pp; + res_reg[INTEL_RC6_RES_RC6_LOCKED] = GEN6_GT_GFX_RC6_LOCKED; + res_reg[INTEL_RC6_RES_RC6] = GEN6_GT_GFX_RC6; + res_reg[INTEL_RC6_RES_RC6p] = GEN6_GT_GFX_RC6p; + res_reg[INTEL_RC6_RES_RC6pp] = GEN6_GT_GFX_RC6pp; break; } + + memcpy(rc6->res_reg, res_reg, sizeof(res_reg)); } void intel_rc6_init(struct intel_rc6 *rc6) diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index cc6bd21a3e51f1..13fb8e5042c584 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -705,7 +705,7 @@ static int __reset_guc(struct intel_gt *gt) static bool needs_wa_14015076503(struct intel_gt *gt, intel_engine_mask_t engine_mask) { - if (!IS_METEORLAKE(gt->i915) || !HAS_ENGINE(gt, GSC0)) + if (MEDIA_VER_FULL(gt->i915) != IP_VER(13, 0) || !HAS_ENGINE(gt, GSC0)) return false; if (!__HAS_ENGINE(engine_mask, GSC0)) @@ -1297,7 +1297,7 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg) if (msg) drm_notice(&engine->i915->drm, "Resetting %s for %s\n", engine->name, msg); - atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]); + i915_increase_reset_engine_count(&engine->i915->gpu_error, engine); ret = intel_gt_reset_engine(engine); if (ret) { @@ -1632,6 +1632,24 @@ void __intel_fini_wedge(struct intel_wedge_me *w) w->gt = NULL; } +/* + * Wa_22011802037 requires that we (or the GuC) ensure that no command + * streamers are executing MI_FORCE_WAKE while an engine reset is initiated. + */ +bool intel_engine_reset_needs_wa_22011802037(struct intel_gt *gt) +{ + if (GRAPHICS_VER(gt->i915) < 11) + return false; + + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0)) + return true; + + if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70)) + return false; + + return true; +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftest_reset.c" #include "selftest_hangcheck.c" diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h index 25c975b6e8fc01..f615b30b81c594 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.h +++ b/drivers/gpu/drm/i915/gt/intel_reset.h @@ -78,4 +78,6 @@ void __intel_fini_wedge(struct intel_wedge_me *w); bool intel_has_gpu_reset(const struct intel_gt *gt); bool intel_has_reset_engine(const struct intel_gt *gt); +bool intel_engine_reset_needs_wa_22011802037(struct intel_gt *gt); + #endif /* I915_RESET_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 092542f53aad9c..4feef874e6d695 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -1161,7 +1161,7 @@ void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *c { struct drm_i915_private *i915 = rps_to_i915(rps); - if (IS_METEORLAKE(i915)) + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) return mtl_get_freq_caps(rps, caps); else return __gen6_rps_get_freq_caps(rps, caps); diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 3ae0dbd39eaa3c..8fbb0686c5348d 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -10,6 +10,7 @@ #include "intel_engine_regs.h" #include "intel_gpu_commands.h" #include "intel_gt.h" +#include "intel_gt_ccs_mode.h" #include "intel_gt_mcr.h" #include "intel_gt_regs.h" #include "intel_ring.h" @@ -50,7 +51,8 @@ * registers belonging to BCS, VCS or VECS should be implemented in * xcs_engine_wa_init(). Workarounds for registers not belonging to a specific * engine's MMIO range but that are part of of the common RCS/CCS reset domain - * should be implemented in general_render_compute_wa_init(). + * should be implemented in general_render_compute_wa_init(). The settings + * about the CCS load balancing should be added in ccs_engine_wa_mode(). * * - GT workarounds: the list of these WAs is applied whenever these registers * revert to their default values: on GPU reset, suspend/resume [1]_, etc. @@ -764,39 +766,15 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine, { dg2_ctx_gt_tuning_init(engine, wal); - /* Wa_16011186671:dg2_g11 */ - if (IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) { - wa_mcr_masked_dis(wal, VFLSKPD, DIS_MULT_MISS_RD_SQUASH); - wa_mcr_masked_en(wal, VFLSKPD, DIS_OVER_FETCH_CACHE); - } - - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) { - /* Wa_14010469329:dg2_g10 */ - wa_mcr_masked_en(wal, XEHP_COMMON_SLICE_CHICKEN3, - XEHP_DUAL_SIMD8_SEQ_MERGE_DISABLE); - - /* - * Wa_22010465075:dg2_g10 - * Wa_22010613112:dg2_g10 - * Wa_14010698770:dg2_g10 - */ - wa_mcr_masked_en(wal, XEHP_COMMON_SLICE_CHICKEN3, - GEN12_DISABLE_CPS_AWARE_COLOR_PIPE); - } - /* Wa_16013271637:dg2 */ wa_mcr_masked_en(wal, XEHP_SLICE_COMMON_ECO_CHICKEN1, MSC_MSAA_REODER_BUF_BYPASS_DISABLE); /* Wa_14014947963:dg2 */ - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_FOREVER) || - IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915)) - wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000); + wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000); /* Wa_18018764978:dg2 */ - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_C0, STEP_FOREVER) || - IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915)) - wa_mcr_masked_en(wal, XEHP_PSS_MODE2, SCOREBOARD_STALL_FLUSH_CONTROL); + wa_mcr_masked_en(wal, XEHP_PSS_MODE2, SCOREBOARD_STALL_FLUSH_CONTROL); /* Wa_15010599737:dg2 */ wa_mcr_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN); @@ -805,27 +783,32 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine, wa_masked_en(wal, CACHE_MODE_1, MSAA_OPTIMIZATION_REDUC_DISABLE); } -static void mtl_ctx_gt_tuning_init(struct intel_engine_cs *engine, - struct i915_wa_list *wal) +static void xelpg_ctx_gt_tuning_init(struct intel_engine_cs *engine, + struct i915_wa_list *wal) { - struct drm_i915_private *i915 = engine->i915; + struct intel_gt *gt = engine->gt; dg2_ctx_gt_tuning_init(engine, wal); - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_B0, STEP_FOREVER) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_B0, STEP_FOREVER)) + /* + * Due to Wa_16014892111, the DRAW_WATERMARK tuning must be done in + * gen12_emit_indirect_ctx_rcs() rather than here on some early + * steppings. + */ + if (!(IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0))) wa_add(wal, DRAW_WATERMARK, VERT_WM_VAL, 0x3FF, 0, false); } -static void mtl_ctx_workarounds_init(struct intel_engine_cs *engine, - struct i915_wa_list *wal) +static void xelpg_ctx_workarounds_init(struct intel_engine_cs *engine, + struct i915_wa_list *wal) { - struct drm_i915_private *i915 = engine->i915; + struct intel_gt *gt = engine->gt; - mtl_ctx_gt_tuning_init(engine, wal); + xelpg_ctx_gt_tuning_init(engine, wal); - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0)) { + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0)) { /* Wa_14014947963 */ wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000); @@ -931,8 +914,8 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine, if (engine->class != RENDER_CLASS) goto done; - if (IS_METEORLAKE(i915)) - mtl_ctx_workarounds_init(engine, wal); + if (IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 74))) + xelpg_ctx_workarounds_init(engine, wal); else if (IS_PONTEVECCHIO(i915)) ; /* noop; none at this time */ else if (IS_DG2(i915)) @@ -1606,31 +1589,11 @@ xehpsdv_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) static void dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - struct intel_engine_cs *engine; - int id; - xehp_init_mcr(gt, wal); /* Wa_14011060649:dg2 */ wa_14011060649(gt, wal); - /* - * Although there are per-engine instances of these registers, - * they technically exist outside the engine itself and are not - * impacted by engine resets. Furthermore, they're part of the - * GuC blacklist so trying to treat them as engine workarounds - * will result in GuC initialization failure and a wedged GPU. - */ - for_each_engine(engine, gt, id) { - if (engine->class != VIDEO_DECODE_CLASS) - continue; - - /* Wa_16010515920:dg2_g10 */ - if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0)) - wa_write_or(wal, VDBOX_CGCTL3F18(engine->mmio_base), - ALNUNIT_CLKGATE_DIS); - } - if (IS_DG2_G10(gt->i915)) { /* Wa_22010523718:dg2 */ wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, @@ -1641,65 +1604,6 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) DSS_ROUTER_CLKGATE_DIS); } - if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0) || - IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0)) { - /* Wa_14012362059:dg2 */ - wa_mcr_write_or(wal, XEHP_MERT_MOD_CTRL, FORCE_MISS_FTLB); - } - - if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0)) { - /* Wa_14010948348:dg2_g10 */ - wa_write_or(wal, UNSLCGCTL9430, MSQDUNIT_CLKGATE_DIS); - - /* Wa_14011037102:dg2_g10 */ - wa_write_or(wal, UNSLCGCTL9444, LTCDD_CLKGATE_DIS); - - /* Wa_14011371254:dg2_g10 */ - wa_mcr_write_or(wal, XEHP_SLICE_UNIT_LEVEL_CLKGATE, NODEDSS_CLKGATE_DIS); - - /* Wa_14011431319:dg2_g10 */ - wa_write_or(wal, UNSLCGCTL9440, GAMTLBOACS_CLKGATE_DIS | - GAMTLBVDBOX7_CLKGATE_DIS | - GAMTLBVDBOX6_CLKGATE_DIS | - GAMTLBVDBOX5_CLKGATE_DIS | - GAMTLBVDBOX4_CLKGATE_DIS | - GAMTLBVDBOX3_CLKGATE_DIS | - GAMTLBVDBOX2_CLKGATE_DIS | - GAMTLBVDBOX1_CLKGATE_DIS | - GAMTLBVDBOX0_CLKGATE_DIS | - GAMTLBKCR_CLKGATE_DIS | - GAMTLBGUC_CLKGATE_DIS | - GAMTLBBLT_CLKGATE_DIS); - wa_write_or(wal, UNSLCGCTL9444, GAMTLBGFXA0_CLKGATE_DIS | - GAMTLBGFXA1_CLKGATE_DIS | - GAMTLBCOMPA0_CLKGATE_DIS | - GAMTLBCOMPA1_CLKGATE_DIS | - GAMTLBCOMPB0_CLKGATE_DIS | - GAMTLBCOMPB1_CLKGATE_DIS | - GAMTLBCOMPC0_CLKGATE_DIS | - GAMTLBCOMPC1_CLKGATE_DIS | - GAMTLBCOMPD0_CLKGATE_DIS | - GAMTLBCOMPD1_CLKGATE_DIS | - GAMTLBMERT_CLKGATE_DIS | - GAMTLBVEBOX3_CLKGATE_DIS | - GAMTLBVEBOX2_CLKGATE_DIS | - GAMTLBVEBOX1_CLKGATE_DIS | - GAMTLBVEBOX0_CLKGATE_DIS); - - /* Wa_14010569222:dg2_g10 */ - wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, - GAMEDIA_CLKGATE_DIS); - - /* Wa_14011028019:dg2_g10 */ - wa_mcr_write_or(wal, SSMCGCTL9530, RTFUNIT_CLKGATE_DIS); - - /* Wa_14010680813:dg2_g10 */ - wa_mcr_write_or(wal, XEHP_GAMSTLB_CTRL, - CONTROL_BLOCK_CLKGATE_DIS | - EGRESS_BLOCK_CLKGATE_DIS | - TAG_BLOCK_CLKGATE_DIS); - } - /* Wa_14014830051:dg2 */ wa_mcr_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN); @@ -1741,14 +1645,15 @@ pvc_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) static void xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - /* Wa_14018778641 / Wa_18018781329 */ + /* Wa_14018575942 / Wa_18018781329 */ + wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB); wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB); /* Wa_22016670082 */ wa_write_or(wal, GEN12_SQCNT1, GEN12_STRICT_RAR_ENABLE); - if (IS_MTL_GRAPHICS_STEP(gt->i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0)) { + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0)) { /* Wa_14014830051 */ wa_mcr_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN); @@ -1791,10 +1696,8 @@ xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) */ static void gt_tuning_settings(struct intel_gt *gt, struct i915_wa_list *wal) { - if (IS_METEORLAKE(gt->i915)) { - if (gt->type != GT_MEDIA) - wa_mcr_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); - + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74))) { + wa_mcr_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); wa_mcr_write_or(wal, XEHP_SQCM, EN_32B_ACCESS); } @@ -1826,7 +1729,7 @@ gt_init_workarounds(struct intel_gt *gt, struct i915_wa_list *wal) return; } - if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74))) xelpg_gt_workarounds_init(gt, wal); else if (IS_PONTEVECCHIO(i915)) pvc_gt_workarounds_init(gt, wal); @@ -2242,29 +2145,10 @@ static void dg2_whitelist_build(struct intel_engine_cs *engine) switch (engine->class) { case RENDER_CLASS: - /* - * Wa_1507100340:dg2_g10 - * - * This covers 4 registers which are next to one another : - * - PS_INVOCATION_COUNT - * - PS_INVOCATION_COUNT_UDW - * - PS_DEPTH_COUNT - * - PS_DEPTH_COUNT_UDW - */ - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) - whitelist_reg_ext(w, PS_INVOCATION_COUNT, - RING_FORCE_TO_NONPRIV_ACCESS_RD | - RING_FORCE_TO_NONPRIV_RANGE_4); - /* Required by recommended tuning setting (not a workaround) */ whitelist_mcr_reg(w, XEHP_COMMON_SLICE_CHICKEN3); break; - case COMPUTE_CLASS: - /* Wa_16011157294:dg2_g10 */ - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) - whitelist_reg(w, GEN9_CTX_PREEMPT_REG); - break; default: break; } @@ -2294,7 +2178,7 @@ static void pvc_whitelist_build(struct intel_engine_cs *engine) blacklist_trtt(engine); } -static void mtl_whitelist_build(struct intel_engine_cs *engine) +static void xelpg_whitelist_build(struct intel_engine_cs *engine) { struct i915_wa_list *w = &engine->whitelist; @@ -2316,8 +2200,10 @@ void intel_engine_init_whitelist(struct intel_engine_cs *engine) wa_init_start(w, engine->gt, "whitelist", engine->name); - if (IS_METEORLAKE(i915)) - mtl_whitelist_build(engine); + if (engine->gt->type == GT_MEDIA) + ; /* none yet */ + else if (IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 74))) + xelpg_whitelist_build(engine); else if (IS_PONTEVECCHIO(i915)) pvc_whitelist_build(engine); else if (IS_DG2(i915)) @@ -2415,62 +2301,35 @@ engine_fake_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) } } -static bool needs_wa_1308578152(struct intel_engine_cs *engine) -{ - return intel_sseu_find_first_xehp_dss(&engine->gt->info.sseu, 0, 0) >= - GEN_DSS_PER_GSLICE; -} - static void rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { struct drm_i915_private *i915 = engine->i915; + struct intel_gt *gt = engine->gt; - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0)) { + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0)) { /* Wa_22014600077 */ wa_mcr_masked_en(wal, GEN10_CACHE_MODE_SS, ENABLE_EU_COUNT_FOR_TDL_FLUSH); } - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0) || - IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || - IS_DG2_G11(i915) || IS_DG2_G12(i915)) { + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0) || + IS_DG2(i915)) { /* Wa_1509727124 */ wa_mcr_masked_en(wal, GEN10_SAMPLER_MODE, SC_DISABLE_POWER_OPTIMIZATION_EBB); } - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || - IS_DG2_G11(i915) || IS_DG2_G12(i915) || - IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0)) { + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_DG2(i915)) { /* Wa_22012856258 */ wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, GEN12_DISABLE_READ_SUPPRESSION); } - if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) { - /* Wa_14013392000:dg2_g11 */ - wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, GEN12_ENABLE_LARGE_GRF_MODE); - } - - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0) || - IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) { - /* Wa_14012419201:dg2 */ - wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, - GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX); - } - - /* Wa_1308578152:dg2_g10 when first gslice is fused off */ - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) && - needs_wa_1308578152(engine)) { - wa_masked_dis(wal, GEN12_CS_DEBUG_MODE1_CCCSUNIT_BE_COMMON, - GEN12_REPLAY_MODE_GRANULARITY); - } - - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || - IS_DG2_G11(i915) || IS_DG2_G12(i915)) { + if (IS_DG2(i915)) { /* * Wa_22010960976:dg2 * Wa_14013347512:dg2 @@ -2479,34 +2338,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK); } - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) { - /* - * Wa_1608949956:dg2_g10 - * Wa_14010198302:dg2_g10 - */ - wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, - MDQ_ARBITRATION_MODE | UGM_BACKUP_MODE); - } - - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) - /* Wa_22010430635:dg2 */ - wa_mcr_masked_en(wal, - GEN9_ROW_CHICKEN4, - GEN12_DISABLE_GRF_CLEAR); - - /* Wa_14013202645:dg2 */ - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) || - IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) - wa_mcr_write_or(wal, RT_CTRL, DIS_NULL_QUERY); - - /* Wa_22012532006:dg2 */ - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_C0) || - IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) - wa_mcr_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, - DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA); - - if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_B0, STEP_FOREVER) || - IS_DG2_G10(i915)) { + if (IS_DG2_G11(i915) || IS_DG2_G10(i915)) { /* Wa_22014600077:dg2 */ wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0, _MASKED_BIT_ENABLE(ENABLE_EU_COUNT_FOR_TDL_FLUSH), @@ -2514,6 +2346,19 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) true); } + if (IS_DG2(i915) || IS_ALDERLAKE_P(i915) || IS_ALDERLAKE_S(i915) || + IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { + /* + * Wa_1606700617:tgl,dg1,adl-p + * Wa_22010271021:tgl,rkl,dg1,adl-s,adl-p + * Wa_14010826681:tgl,dg1,rkl,adl-p + * Wa_18019627453:dg2 + */ + wa_masked_en(wal, + GEN9_CS_DEBUG_MODE1, + FF_DOP_CLOCK_GATE_DISABLE); + } + if (IS_ALDERLAKE_P(i915) || IS_ALDERLAKE_S(i915) || IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { /* Wa_1606931601:tgl,rkl,dg1,adl-s,adl-p */ @@ -2527,19 +2372,11 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) */ wa_write_or(wal, GEN7_FF_THREAD_MODE, GEN12_FF_TESSELATION_DOP_GATE_DISABLE); - } - if (IS_ALDERLAKE_P(i915) || IS_DG2(i915) || IS_ALDERLAKE_S(i915) || - IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { - /* - * Wa_1606700617:tgl,dg1,adl-p - * Wa_22010271021:tgl,rkl,dg1,adl-s,adl-p - * Wa_14010826681:tgl,dg1,rkl,adl-p - * Wa_18019627453:dg2 - */ - wa_masked_en(wal, - GEN9_CS_DEBUG_MODE1, - FF_DOP_CLOCK_GATE_DISABLE); + /* Wa_1406941453:tgl,rkl,dg1,adl-s,adl-p */ + wa_mcr_masked_en(wal, + GEN10_SAMPLER_MODE, + ENABLE_SMALLPL); } if (IS_ALDERLAKE_P(i915) || IS_ALDERLAKE_S(i915) || @@ -2566,14 +2403,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN8_RC_SEMA_IDLE_MSG_DISABLE); } - if (IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915) || - IS_ALDERLAKE_S(i915) || IS_ALDERLAKE_P(i915)) { - /* Wa_1406941453:tgl,rkl,dg1,adl-s,adl-p */ - wa_mcr_masked_en(wal, - GEN10_SAMPLER_MODE, - ENABLE_SMALLPL); - } - if (GRAPHICS_VER(i915) == 11) { /* This is not an Wa. Enable for better image quality */ wa_masked_en(wal, @@ -2975,10 +2804,12 @@ ccs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) * function invoked by __intel_engine_init_ctx_wa(). */ static void -add_render_compute_tuning_settings(struct drm_i915_private *i915, +add_render_compute_tuning_settings(struct intel_gt *gt, struct i915_wa_list *wal) { - if (IS_METEORLAKE(i915) || IS_DG2(i915)) + struct drm_i915_private *i915 = gt->i915; + + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74)) || IS_DG2(i915)) wa_mcr_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512); /* @@ -2994,6 +2825,30 @@ add_render_compute_tuning_settings(struct drm_i915_private *i915, wa_write_clr(wal, GEN8_GARBCNTL, GEN12_BUS_HASH_CTL_BIT_EXC); } +static void ccs_engine_wa_mode(struct intel_engine_cs *engine, struct i915_wa_list *wal) +{ + struct intel_gt *gt = engine->gt; + u32 mode; + + if (!IS_DG2(gt->i915)) + return; + + /* + * Wa_14019159160: This workaround, along with others, leads to + * significant challenges in utilizing load balancing among the + * CCS slices. Consequently, an architectural decision has been + * made to completely disable automatic CCS load balancing. + */ + wa_masked_en(wal, GEN12_RCU_MODE, XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE); + + /* + * After having disabled automatic load balancing we need to + * assign all slices to a single CCS. We will call it CCS mode 1 + */ + mode = intel_gt_apply_ccs_mode(gt); + wa_masked_en(wal, XEHP_CCS_MODE, mode); +} + /* * The workarounds in this function apply to shared registers in * the general render reset domain that aren't tied to a @@ -3007,8 +2862,9 @@ static void general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { struct drm_i915_private *i915 = engine->i915; + struct intel_gt *gt = engine->gt; - add_render_compute_tuning_settings(i915, wal); + add_render_compute_tuning_settings(gt, wal); if (GRAPHICS_VER(i915) >= 11) { /* This is not a Wa (although referred to as @@ -3029,13 +2885,14 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li GEN11_INDIRECT_STATE_BASE_ADDR_OVERRIDE); } - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_B0, STEP_FOREVER) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_B0, STEP_FOREVER)) + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_B0, STEP_FOREVER) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_B0, STEP_FOREVER) || + IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 74), IP_VER(12, 74))) /* Wa_14017856879 */ wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN3, MTL_DISABLE_FIX_FOR_EOT_FLUSH); - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0)) + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0)) /* * Wa_14017066071 * Wa_14017654203 @@ -3043,37 +2900,47 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li wa_mcr_masked_en(wal, GEN10_SAMPLER_MODE, MTL_DISABLE_SAMPLER_SC_OOO); - if (IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0)) + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0)) /* Wa_22015279794 */ wa_mcr_masked_en(wal, GEN10_CACHE_MODE_SS, DISABLE_PREFETCH_INTO_IC); - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0) || - IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || - IS_DG2_G11(i915) || IS_DG2_G12(i915)) { + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0) || + IS_DG2(i915)) { /* Wa_22013037850 */ wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DISABLE_128B_EVICTION_COMMAND_UDW); + + /* Wa_18017747507 */ + wa_masked_en(wal, VFG_PREEMPTION_CHICKEN, POLYGON_TRIFAN_LINELOOP_DISABLE); } - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0) || + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0) || IS_PONTEVECCHIO(i915) || IS_DG2(i915)) { /* Wa_22014226127 */ wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0, DISABLE_D8_D16_COASLESCE); } - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0) || - IS_DG2(i915)) { - /* Wa_18017747507 */ - wa_masked_en(wal, VFG_PREEMPTION_CHICKEN, POLYGON_TRIFAN_LINELOOP_DISABLE); + if (IS_PONTEVECCHIO(i915) || IS_DG2(i915)) { + /* Wa_14015227452:dg2,pvc */ + wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE); + + /* Wa_16015675438:dg2,pvc */ + wa_masked_en(wal, FF_SLICE_CS_CHICKEN2, GEN12_PERF_FIX_BALANCING_CFE_DISABLE); + } + + if (IS_DG2(i915)) { + /* + * Wa_16011620976:dg2_g11 + * Wa_22015475538:dg2 + */ + wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DIS_CHAIN_2XSIMD8); } - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) || - IS_DG2_G11(i915)) { + if (IS_DG2_G11(i915)) { /* * Wa_22012826095:dg2 * Wa_22013059131:dg2 @@ -3085,18 +2952,18 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li /* Wa_22013059131:dg2 */ wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0, FORCE_1_SUB_MESSAGE_PER_FRAGMENT); - } - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) { /* - * Wa_14010918519:dg2_g10 + * Wa_22012654132 * - * LSC_CHICKEN_BIT_0 always reads back as 0 is this stepping, - * so ignoring verification. + * Note that register 0xE420 is write-only and cannot be read + * back for verification on DG2 (due to Wa_14012342262), so + * we need to explicitly skip the readback. */ - wa_mcr_add(wal, LSC_CHICKEN_BIT_0_UDW, 0, - FORCE_SLM_FENCE_SCOPE_TO_TILE | FORCE_UGM_FENCE_SCOPE_TO_TILE, - 0, false); + wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0, + _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC), + 0 /* write-only, so skip validation */, + true); } if (IS_XEHPSDV(i915)) { @@ -3114,35 +2981,6 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN1, GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE); } - - if (IS_DG2(i915) || IS_PONTEVECCHIO(i915)) { - /* Wa_14015227452:dg2,pvc */ - wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE); - - /* Wa_16015675438:dg2,pvc */ - wa_masked_en(wal, FF_SLICE_CS_CHICKEN2, GEN12_PERF_FIX_BALANCING_CFE_DISABLE); - } - - if (IS_DG2(i915)) { - /* - * Wa_16011620976:dg2_g11 - * Wa_22015475538:dg2 - */ - wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DIS_CHAIN_2XSIMD8); - } - - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_C0) || IS_DG2_G11(i915)) - /* - * Wa_22012654132 - * - * Note that register 0xE420 is write-only and cannot be read - * back for verification on DG2 (due to Wa_14012342262), so - * we need to explicitly skip the readback. - */ - wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0, - _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC), - 0 /* write-only, so skip validation */, - true); } static void @@ -3158,8 +2996,10 @@ engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal * to a single RCS/CCS engine's workaround list since * they're reset as part of the general render domain reset. */ - if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE) + if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE) { general_render_compute_wa_init(engine, wal); + ccs_engine_wa_mode(engine, wal); + } if (engine->class == COMPUTE_CLASS) ccs_engine_wa_init(engine, wal); diff --git a/drivers/gpu/drm/i915/gt/selftest_migrate.c b/drivers/gpu/drm/i915/gt/selftest_migrate.c index 3def5ca72decfd..0fb07f073baa61 100644 --- a/drivers/gpu/drm/i915/gt/selftest_migrate.c +++ b/drivers/gpu/drm/i915/gt/selftest_migrate.c @@ -719,11 +719,9 @@ static int threaded_migrate(struct intel_migrate *migrate, if (IS_ERR_OR_NULL(tsk)) continue; - status = kthread_stop(tsk); + status = kthread_stop_put(tsk); if (status && !err) err = status; - - put_task_struct(tsk); } kfree(thread); diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h index 58012edd4eb0ec..4f4f53c42a9c56 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h @@ -29,9 +29,9 @@ */ #define GUC_KLV_LEN_MIN 1u -#define GUC_KLV_0_KEY (0xffff << 16) -#define GUC_KLV_0_LEN (0xffff << 0) -#define GUC_KLV_n_VALUE (0xffffffff << 0) +#define GUC_KLV_0_KEY (0xffffu << 16) +#define GUC_KLV_0_LEN (0xffffu << 0) +#define GUC_KLV_n_VALUE (0xffffffffu << 0) /** * DOC: GuC Self Config KLVs diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c index 0d3b22a7436595..e251e061d1adb7 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c @@ -304,7 +304,7 @@ void intel_gsc_uc_load_start(struct intel_gsc_uc *gsc) { struct intel_gt *gt = gsc_uc_to_gt(gsc); - if (!intel_uc_fw_is_loadable(&gsc->fw)) + if (!intel_uc_fw_is_loadable(&gsc->fw) || intel_uc_fw_is_in_error(&gsc->fw)) return; if (intel_gsc_uc_fw_init_done(gsc)) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index 569b5fe94c416f..861d0c58388cfc 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -272,18 +272,14 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc) GRAPHICS_VER_FULL(gt->i915) < IP_VER(12, 50)) flags |= GUC_WA_POLLCS; - /* Wa_16011759253:dg2_g10:a0 */ - if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0)) - flags |= GUC_WA_GAM_CREDITS; - /* Wa_14014475959 */ - if (IS_MTL_GRAPHICS_STEP(gt->i915, M, STEP_A0, STEP_B0) || + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || IS_DG2(gt->i915)) flags |= GUC_WA_HOLD_CCS_SWITCHOUT; /* - * Wa_14012197797:dg2_g10:a0,dg2_g11:a0 - * Wa_22011391025:dg2_g10,dg2_g11,dg2_g12 + * Wa_14012197797 + * Wa_22011391025 * * The same WA bit is used for both and 22011391025 is applicable to * all DG2. @@ -292,22 +288,14 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc) flags |= GUC_WA_DUAL_QUEUE; /* Wa_22011802037: graphics version 11/12 */ - if (IS_MTL_GRAPHICS_STEP(gt->i915, M, STEP_A0, STEP_B0) || - (GRAPHICS_VER(gt->i915) >= 11 && - GRAPHICS_VER_FULL(gt->i915) < IP_VER(12, 70))) + if (intel_engine_reset_needs_wa_22011802037(gt)) flags |= GUC_WA_PRE_PARSER; - /* Wa_16011777198:dg2 */ - if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) || - IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0)) - flags |= GUC_WA_RCS_RESET_BEFORE_RC6; - /* - * Wa_22012727170:dg2_g10[a0-c0), dg2_g11[a0..) - * Wa_22012727685:dg2_g11[a0..) + * Wa_22012727170 + * Wa_22012727685 */ - if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) || - IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_FOREVER)) + if (IS_DG2_G11(gt->i915)) flags |= GUC_WA_CONTEXT_ISOLATION; /* Wa_16015675438 */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index dc7b40e06e38af..236dfff81fea43 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1690,9 +1690,7 @@ static void guc_engine_reset_prepare(struct intel_engine_cs *engine) * Wa_22011802037: In addition to stopping the cs, we need * to wait for any pending mi force wakeups */ - if (IS_MTL_GRAPHICS_STEP(engine->i915, M, STEP_A0, STEP_B0) || - (GRAPHICS_VER(engine->i915) >= 11 && - GRAPHICS_VER_FULL(engine->i915) < IP_VER(12, 70))) { + if (intel_engine_reset_needs_wa_22011802037(engine->gt)) { intel_engine_stop_cs(engine); intel_engine_wait_for_pending_mi_fw(engine); } @@ -2697,9 +2695,9 @@ static void prepare_context_registration_info_v70(struct intel_context *ce, ce->parallel.guc.wqi_tail = 0; ce->parallel.guc.wqi_head = 0; - wq_desc_offset = i915_ggtt_offset(ce->state) + + wq_desc_offset = (u64)i915_ggtt_offset(ce->state) + __get_parent_scratch_offset(ce); - wq_base_offset = i915_ggtt_offset(ce->state) + + wq_base_offset = (u64)i915_ggtt_offset(ce->state) + __get_wq_offset(ce); info->wq_desc_lo = lower_32_bits(wq_desc_offset); info->wq_desc_hi = upper_32_bits(wq_desc_offset); @@ -4299,7 +4297,7 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine) /* Wa_14014475959:dg2 */ if (engine->class == COMPUTE_CLASS) - if (IS_MTL_GRAPHICS_STEP(engine->i915, M, STEP_A0, STEP_B0) || + if (IS_GFX_GT_IP_STEP(engine->gt, IP_VER(12, 70), STEP_A0, STEP_B0) || IS_DG2(engine->i915)) engine->flags |= I915_ENGINE_USES_WA_HOLD_CCS_SWITCHOUT; @@ -4774,7 +4772,8 @@ static void capture_error_state(struct intel_guc *guc, if (match) { intel_engine_set_hung_context(e, ce); engine_mask |= e->mask; - atomic_inc(&i915->gpu_error.reset_engine_count[e->uabi_class]); + i915_increase_reset_engine_count(&i915->gpu_error, + e); } } @@ -4786,7 +4785,7 @@ static void capture_error_state(struct intel_guc *guc, } else { intel_engine_set_hung_context(ce->engine, ce); engine_mask = ce->engine->mask; - atomic_inc(&i915->gpu_error.reset_engine_count[ce->engine->uabi_class]); + i915_increase_reset_engine_count(&i915->gpu_error, ce->engine); } with_intel_runtime_pm(&i915->runtime_pm, wakeref) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h index 9a431726c8d5b1..ac7b3aad2222e8 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h @@ -258,6 +258,11 @@ static inline bool intel_uc_fw_is_running(struct intel_uc_fw *uc_fw) return __intel_uc_fw_status(uc_fw) == INTEL_UC_FIRMWARE_RUNNING; } +static inline bool intel_uc_fw_is_in_error(struct intel_uc_fw *uc_fw) +{ + return intel_uc_fw_status_to_error(__intel_uc_fw_status(uc_fw)) != 0; +} + static inline bool intel_uc_fw_is_overridden(const struct intel_uc_fw *uc_fw) { return uc_fw->user_overridden; diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index a9f7fa9b90bdad..d30f8814d9b106 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -2850,8 +2850,7 @@ static int handle_mmio(struct intel_gvt_mmio_table_iter *iter, u32 offset, for (i = start; i < end; i += 4) { p = intel_gvt_find_mmio_info(gvt, i); if (p) { - WARN(1, "dup mmio definition offset %x\n", - info->offset); + WARN(1, "dup mmio definition offset %x\n", i); /* We return -EEXIST here to make GVT-g load fail. * So duplicated MMIO can be found as soon as diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c index 68eca023bbc68b..80301472ac9881 100644 --- a/drivers/gpu/drm/i915/gvt/interrupt.c +++ b/drivers/gpu/drm/i915/gvt/interrupt.c @@ -405,7 +405,7 @@ static void init_irq_map(struct intel_gvt_irq *irq) #define MSI_CAP_DATA(offset) (offset + 8) #define MSI_CAP_EN 0x1 -static int inject_virtual_interrupt(struct intel_vgpu *vgpu) +static void inject_virtual_interrupt(struct intel_vgpu *vgpu) { unsigned long offset = vgpu->gvt->device_info.msi_cap_offset; u16 control, data; @@ -417,10 +417,10 @@ static int inject_virtual_interrupt(struct intel_vgpu *vgpu) /* Do not generate MSI if MSIEN is disabled */ if (!(control & MSI_CAP_EN)) - return 0; + return; if (WARN(control & GENMASK(15, 1), "only support one MSI format\n")) - return -EINVAL; + return; trace_inject_msi(vgpu->id, addr, data); @@ -434,10 +434,9 @@ static int inject_virtual_interrupt(struct intel_vgpu *vgpu) * returned and don't inject interrupt into guest. */ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status)) - return -ESRCH; - if (vgpu->msi_trigger && eventfd_signal(vgpu->msi_trigger, 1) != 1) - return -EFAULT; - return 0; + return; + if (vgpu->msi_trigger) + eventfd_signal(vgpu->msi_trigger, 1); } static void propagate_event(struct intel_gvt_irq *irq, diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 4de44cf1026dce..7a90a2e32c9f1b 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -144,7 +144,7 @@ static const char *i915_cache_level_str(struct drm_i915_gem_object *obj) { struct drm_i915_private *i915 = obj_to_i915(obj); - if (IS_METEORLAKE(i915)) { + if (IS_GFX_GT_IP_RANGE(to_gt(i915), IP_VER(12, 70), IP_VER(12, 71))) { switch (obj->pat_index) { case 0: return " WB"; case 1: return " WT"; diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index ec4d26b3c17cc1..8dc5f85b7747b4 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -777,7 +777,7 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ret = i915_driver_mmio_probe(i915); if (ret < 0) - goto out_tiles_cleanup; + goto out_runtime_pm_put; ret = i915_driver_hw_probe(i915); if (ret < 0) @@ -837,8 +837,6 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) i915_ggtt_driver_late_release(i915); out_cleanup_mmio: i915_driver_mmio_release(i915); -out_tiles_cleanup: - intel_gt_release_all(i915); out_runtime_pm_put: enable_rpm_wakeref_asserts(&i915->runtime_pm); i915_driver_late_release(i915); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 7a8ce7239bc9e3..e0e0493d6c1f0d 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -658,10 +658,6 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define IS_XEHPSDV_GRAPHICS_STEP(__i915, since, until) \ (IS_XEHPSDV(__i915) && IS_GRAPHICS_STEP(__i915, since, until)) -#define IS_MTL_GRAPHICS_STEP(__i915, variant, since, until) \ - (IS_SUBPLATFORM(__i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_##variant) && \ - IS_GRAPHICS_STEP(__i915, since, until)) - #define IS_MTL_DISPLAY_STEP(__i915, since, until) \ (IS_METEORLAKE(__i915) && \ IS_DISPLAY_STEP(__i915, since, until)) diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index 9f5971f5e98014..48f6c00402c47a 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -16,6 +16,7 @@ #include "display/intel_display_device.h" #include "gt/intel_engine.h" +#include "gt/intel_engine_types.h" #include "gt/intel_gt_types.h" #include "gt/uc/intel_uc_fw.h" @@ -232,7 +233,7 @@ struct i915_gpu_error { atomic_t reset_count; /** Number of times an engine has been reset */ - atomic_t reset_engine_count[I915_NUM_ENGINES]; + atomic_t reset_engine_count[MAX_ENGINE_CLASS]; }; struct drm_i915_error_state_buf { @@ -255,7 +256,14 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error) static inline u32 i915_reset_engine_count(struct i915_gpu_error *error, const struct intel_engine_cs *engine) { - return atomic_read(&error->reset_engine_count[engine->uabi_class]); + return atomic_read(&error->reset_engine_count[engine->class]); +} + +static inline void +i915_increase_reset_engine_count(struct i915_gpu_error *error, + const struct intel_engine_cs *engine) +{ + atomic_inc(&error->reset_engine_count[engine->class]); } #define CORE_DUMP_FLAG_NONE 0x0 diff --git a/drivers/gpu/drm/i915/i915_hwmon.c b/drivers/gpu/drm/i915/i915_hwmon.c index 975da8e7f2a9f8..c0662a022f59c1 100644 --- a/drivers/gpu/drm/i915/i915_hwmon.c +++ b/drivers/gpu/drm/i915/i915_hwmon.c @@ -72,12 +72,13 @@ hwm_locked_with_pm_intel_uncore_rmw(struct hwm_drvdata *ddat, struct intel_uncore *uncore = ddat->uncore; intel_wakeref_t wakeref; - mutex_lock(&hwmon->hwmon_lock); + with_intel_runtime_pm(uncore->rpm, wakeref) { + mutex_lock(&hwmon->hwmon_lock); - with_intel_runtime_pm(uncore->rpm, wakeref) intel_uncore_rmw(uncore, reg, clear, set); - mutex_unlock(&hwmon->hwmon_lock); + mutex_unlock(&hwmon->hwmon_lock); + } } /* @@ -136,20 +137,21 @@ hwm_energy(struct hwm_drvdata *ddat, long *energy) else rgaddr = hwmon->rg.energy_status_all; - mutex_lock(&hwmon->hwmon_lock); + with_intel_runtime_pm(uncore->rpm, wakeref) { + mutex_lock(&hwmon->hwmon_lock); - with_intel_runtime_pm(uncore->rpm, wakeref) reg_val = intel_uncore_read(uncore, rgaddr); - if (reg_val >= ei->reg_val_prev) - ei->accum_energy += reg_val - ei->reg_val_prev; - else - ei->accum_energy += UINT_MAX - ei->reg_val_prev + reg_val; - ei->reg_val_prev = reg_val; + if (reg_val >= ei->reg_val_prev) + ei->accum_energy += reg_val - ei->reg_val_prev; + else + ei->accum_energy += UINT_MAX - ei->reg_val_prev + reg_val; + ei->reg_val_prev = reg_val; - *energy = mul_u64_u32_shr(ei->accum_energy, SF_ENERGY, - hwmon->scl_shift_energy); - mutex_unlock(&hwmon->hwmon_lock); + *energy = mul_u64_u32_shr(ei->accum_energy, SF_ENERGY, + hwmon->scl_shift_energy); + mutex_unlock(&hwmon->hwmon_lock); + } } static ssize_t @@ -175,7 +177,7 @@ hwm_power1_max_interval_show(struct device *dev, struct device_attribute *attr, * tau4 = (4 | x) << y * but add 2 when doing the final right shift to account for units */ - tau4 = ((1 << x_w) | x) << y; + tau4 = (u64)((1 << x_w) | x) << y; /* val in hwmon interface units (millisec) */ out = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w); @@ -211,7 +213,7 @@ hwm_power1_max_interval_store(struct device *dev, r = FIELD_PREP(PKG_MAX_WIN, PKG_MAX_WIN_DEFAULT); x = REG_FIELD_GET(PKG_MAX_WIN_X, r); y = REG_FIELD_GET(PKG_MAX_WIN_Y, r); - tau4 = ((1 << x_w) | x) << y; + tau4 = (u64)((1 << x_w) | x) << y; max_win = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w); if (val > max_win) @@ -404,6 +406,7 @@ hwm_power_max_write(struct hwm_drvdata *ddat, long val) /* Block waiting for GuC reset to complete when needed */ for (;;) { + wakeref = intel_runtime_pm_get(ddat->uncore->rpm); mutex_lock(&hwmon->hwmon_lock); prepare_to_wait(&ddat->waitq, &wait, TASK_INTERRUPTIBLE); @@ -417,14 +420,13 @@ hwm_power_max_write(struct hwm_drvdata *ddat, long val) } mutex_unlock(&hwmon->hwmon_lock); + intel_runtime_pm_put(ddat->uncore->rpm, wakeref); schedule(); } finish_wait(&ddat->waitq, &wait); if (ret) - goto unlock; - - wakeref = intel_runtime_pm_get(ddat->uncore->rpm); + goto exit; /* Disable PL1 limit and verify, because the limit cannot be disabled on all platforms */ if (val == PL1_DISABLE) { @@ -444,9 +446,8 @@ hwm_power_max_write(struct hwm_drvdata *ddat, long val) intel_uncore_rmw(ddat->uncore, hwmon->rg.pkg_rapl_limit, PKG_PWR_LIM_1_EN | PKG_PWR_LIM_1, nval); exit: - intel_runtime_pm_put(ddat->uncore->rpm, wakeref); -unlock: mutex_unlock(&hwmon->hwmon_lock); + intel_runtime_pm_put(ddat->uncore->rpm, wakeref); return ret; } @@ -792,7 +793,7 @@ void i915_hwmon_register(struct drm_i915_private *i915) if (!IS_DGFX(i915)) return; - hwmon = devm_kzalloc(dev, sizeof(*hwmon), GFP_KERNEL); + hwmon = kzalloc(sizeof(*hwmon), GFP_KERNEL); if (!hwmon) return; @@ -818,14 +819,12 @@ void i915_hwmon_register(struct drm_i915_private *i915) hwm_get_preregistration_info(i915); /* hwmon_dev points to device hwmon */ - hwmon_dev = devm_hwmon_device_register_with_info(dev, ddat->name, - ddat, - &hwm_chip_info, - hwm_groups); - if (IS_ERR(hwmon_dev)) { - i915->hwmon = NULL; - return; - } + hwmon_dev = hwmon_device_register_with_info(dev, ddat->name, + ddat, + &hwm_chip_info, + hwm_groups); + if (IS_ERR(hwmon_dev)) + goto err; ddat->hwmon_dev = hwmon_dev; @@ -838,16 +837,36 @@ void i915_hwmon_register(struct drm_i915_private *i915) if (!hwm_gt_is_visible(ddat_gt, hwmon_energy, hwmon_energy_input, 0)) continue; - hwmon_dev = devm_hwmon_device_register_with_info(dev, ddat_gt->name, - ddat_gt, - &hwm_gt_chip_info, - NULL); + hwmon_dev = hwmon_device_register_with_info(dev, ddat_gt->name, + ddat_gt, + &hwm_gt_chip_info, + NULL); if (!IS_ERR(hwmon_dev)) ddat_gt->hwmon_dev = hwmon_dev; } + return; +err: + i915_hwmon_unregister(i915); } void i915_hwmon_unregister(struct drm_i915_private *i915) { - fetch_and_zero(&i915->hwmon); + struct i915_hwmon *hwmon = i915->hwmon; + struct intel_gt *gt; + int i; + + if (!hwmon) + return; + + for_each_gt(gt, i915, i) + if (hwmon->ddat_gt[i].hwmon_dev) + hwmon_device_unregister(hwmon->ddat_gt[i].hwmon_dev); + + if (hwmon->ddat.hwmon_dev) + hwmon_device_unregister(hwmon->ddat.hwmon_dev); + + mutex_destroy(&hwmon->hwmon_lock); + + kfree(i915->hwmon); + i915->hwmon = NULL; } diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 59e1e21df27104..0808b54d3c5185 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -785,10 +785,6 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, * The reason field includes flags identifying what * triggered this specific report (mostly timer * triggered or e.g. due to a context switch). - * - * In MMIO triggered reports, some platforms do not set the - * reason bit in this field and it is valid to have a reason - * field of zero. */ reason = oa_report_reason(stream, report); ctx_id = oa_context_id(stream, report32); @@ -800,8 +796,41 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, * * Note: that we don't clear the valid_ctx_bit so userspace can * understand that the ID has been squashed by the kernel. + * + * Update: + * + * On XEHP platforms the behavior of context id valid bit has + * changed compared to prior platforms. To describe this, we + * define a few terms: + * + * context-switch-report: This is a report with the reason type + * being context-switch. It is generated when a context switches + * out. + * + * context-valid-bit: A bit that is set in the report ID field + * to indicate that a valid context has been loaded. + * + * gpu-idle: A condition characterized by a + * context-switch-report with context-valid-bit set to 0. + * + * On prior platforms, context-id-valid bit is set to 0 only + * when GPU goes idle. In all other reports, it is set to 1. + * + * On XEHP platforms, context-valid-bit is set to 1 in a context + * switch report if a new context switched in. For all other + * reports it is set to 0. + * + * This change in behavior causes an issue with MMIO triggered + * reports. MMIO triggered reports have the markers in the + * context ID field and the context-valid-bit is 0. The logic + * below to squash the context ID would render the report + * useless since the user will not be able to find it in the OA + * buffer. Since MMIO triggered reports exist only on XEHP, + * we should avoid squashing these for XEHP platforms. */ - if (oa_report_ctx_invalid(stream, report)) { + + if (oa_report_ctx_invalid(stream, report) && + GRAPHICS_VER_FULL(stream->engine->i915) < IP_VER(12, 50)) { ctx_id = INVALID_CTX_ID; oa_context_id_squash(stream, report32); } @@ -2752,26 +2781,6 @@ oa_configure_all_contexts(struct i915_perf_stream *stream, return 0; } -static int -gen12_configure_all_contexts(struct i915_perf_stream *stream, - const struct i915_oa_config *oa_config, - struct i915_active *active) -{ - struct flex regs[] = { - { - GEN8_R_PWR_CLK_STATE(RENDER_RING_BASE), - CTX_R_PWR_CLK_STATE, - }, - }; - - if (stream->engine->class != RENDER_CLASS) - return 0; - - return oa_configure_all_contexts(stream, - regs, ARRAY_SIZE(regs), - active); -} - static int lrc_configure_all_contexts(struct i915_perf_stream *stream, const struct i915_oa_config *oa_config, @@ -2878,7 +2887,6 @@ gen12_enable_metric_set(struct i915_perf_stream *stream, { struct drm_i915_private *i915 = stream->perf->i915; struct intel_uncore *uncore = stream->uncore; - struct i915_oa_config *oa_config = stream->oa_config; bool periodic = stream->periodic; u32 period_exponent = stream->period_exponent; u32 sqcnt1; @@ -2922,15 +2930,6 @@ gen12_enable_metric_set(struct i915_perf_stream *stream, intel_uncore_rmw(uncore, GEN12_SQCNT1, 0, sqcnt1); - /* - * Update all contexts prior writing the mux configurations as we need - * to make sure all slices/subslices are ON before writing to NOA - * registers. - */ - ret = gen12_configure_all_contexts(stream, oa_config, active); - if (ret) - return ret; - /* * For Gen12, performance counters are context * saved/restored. Only enable it for the context that @@ -2985,9 +2984,6 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream) _MASKED_BIT_DISABLE(GEN12_DISABLE_DOP_GATING)); } - /* Reset all contexts' slices/subslices configurations. */ - gen12_configure_all_contexts(stream, NULL, NULL); - /* disable the context save/restore or OAR counters */ if (stream->ctx) gen12_configure_oar_context(stream, NULL); @@ -3226,11 +3222,10 @@ get_sseu_config(struct intel_sseu *out_sseu, */ u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915) { - /* - * Wa_18013179988:dg2 - * Wa_14015846243:mtl - */ - if (IS_DG2(i915) || IS_METEORLAKE(i915)) { + struct intel_gt *gt = to_gt(i915); + + /* Wa_18013179988 */ + if (IS_DG2(i915) || IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74))) { intel_wakeref_t wakeref; u32 reg, shift; @@ -4286,11 +4281,8 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data, u32 known_open_flags; int ret; - if (!perf->i915) { - drm_dbg(&perf->i915->drm, - "i915 perf interface not available for this system\n"); + if (!perf->i915) return -ENOTSUPP; - } known_open_flags = I915_PERF_FLAG_FD_CLOEXEC | I915_PERF_FLAG_FD_NONBLOCK | @@ -4538,7 +4530,7 @@ static bool xehp_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr) static bool gen12_is_valid_mux_addr(struct i915_perf *perf, u32 addr) { - if (IS_METEORLAKE(perf->i915)) + if (GRAPHICS_VER_FULL(perf->i915) >= IP_VER(12, 70)) return reg_in_range_table(addr, mtl_oa_mux_regs); else return reg_in_range_table(addr, gen12_oa_mux_regs); @@ -4666,11 +4658,8 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data, struct i915_oa_reg *regs; int err, id; - if (!perf->i915) { - drm_dbg(&perf->i915->drm, - "i915 perf interface not available for this system\n"); + if (!perf->i915) return -ENOTSUPP; - } if (!perf->metrics_kobj) { drm_dbg(&perf->i915->drm, @@ -4832,11 +4821,8 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data, struct i915_oa_config *oa_config; int ret; - if (!perf->i915) { - drm_dbg(&perf->i915->drm, - "i915 perf interface not available for this system\n"); + if (!perf->i915) return -ENOTSUPP; - } if (i915_perf_stream_paranoid && !perfmon_capable()) { drm_dbg(&perf->i915->drm, diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index 8a9aad523eec2c..1d4cc91c0e40d5 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -51,7 +51,7 @@ static inline void debug_fence_init(struct i915_sw_fence *fence) debug_object_init(fence, &i915_sw_fence_debug_descr); } -static inline void debug_fence_init_onstack(struct i915_sw_fence *fence) +static inline __maybe_unused void debug_fence_init_onstack(struct i915_sw_fence *fence) { debug_object_init_on_stack(fence, &i915_sw_fence_debug_descr); } @@ -77,7 +77,7 @@ static inline void debug_fence_destroy(struct i915_sw_fence *fence) debug_object_destroy(fence, &i915_sw_fence_debug_descr); } -static inline void debug_fence_free(struct i915_sw_fence *fence) +static inline __maybe_unused void debug_fence_free(struct i915_sw_fence *fence) { debug_object_free(fence, &i915_sw_fence_debug_descr); smp_wmb(); /* flush the change in state before reallocation */ @@ -94,7 +94,7 @@ static inline void debug_fence_init(struct i915_sw_fence *fence) { } -static inline void debug_fence_init_onstack(struct i915_sw_fence *fence) +static inline __maybe_unused void debug_fence_init_onstack(struct i915_sw_fence *fence) { } @@ -115,7 +115,7 @@ static inline void debug_fence_destroy(struct i915_sw_fence *fence) { } -static inline void debug_fence_free(struct i915_sw_fence *fence) +static inline __maybe_unused void debug_fence_free(struct i915_sw_fence *fence) { } diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 6f180ee138531d..46e4a45e3c72ae 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -33,6 +33,7 @@ #include "gt/intel_engine.h" #include "gt/intel_engine_heartbeat.h" #include "gt/intel_gt.h" +#include "gt/intel_gt_pm.h" #include "gt/intel_gt_requests.h" #include "gt/intel_tlb.h" @@ -102,12 +103,34 @@ static inline struct i915_vma *active_to_vma(struct i915_active *ref) static int __i915_vma_active(struct i915_active *ref) { - return i915_vma_tryget(active_to_vma(ref)) ? 0 : -ENOENT; + struct i915_vma *vma = active_to_vma(ref); + + if (!i915_vma_tryget(vma)) + return -ENOENT; + + /* + * Exclude global GTT VMA from holding a GT wakeref + * while active, otherwise GPU never goes idle. + */ + if (!i915_vma_is_ggtt(vma)) + intel_gt_pm_get(vma->vm->gt); + + return 0; } static void __i915_vma_retire(struct i915_active *ref) { - i915_vma_put(active_to_vma(ref)); + struct i915_vma *vma = active_to_vma(ref); + + if (!i915_vma_is_ggtt(vma)) { + /* + * Since we can be called from atomic contexts, + * use an async variant of intel_gt_pm_put(). + */ + intel_gt_pm_put_async(vma->vm->gt); + } + + i915_vma_put(vma); } static struct i915_vma * @@ -1403,7 +1426,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, struct i915_vma_work *work = NULL; struct dma_fence *moving = NULL; struct i915_vma_resource *vma_res = NULL; - intel_wakeref_t wakeref = 0; + intel_wakeref_t wakeref; unsigned int bound; int err; @@ -1423,8 +1446,14 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, if (err) return err; - if (flags & PIN_GLOBAL) - wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm); + /* + * In case of a global GTT, we must hold a runtime-pm wakeref + * while global PTEs are updated. In other cases, we hold + * the rpm reference while the VMA is active. Since runtime + * resume may require allocations, which are forbidden inside + * vm->mutex, get the first rpm wakeref outside of the mutex. + */ + wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm); if (flags & vma->vm->bind_async_flags) { /* lock VM */ @@ -1560,8 +1589,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, if (work) dma_fence_work_commit_imm(&work->base); err_rpm: - if (wakeref) - intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref); + intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref); if (moving) dma_fence_put(moving); diff --git a/drivers/gpu/drm/i915/intel_clock_gating.c b/drivers/gpu/drm/i915/intel_clock_gating.c index 81a4d32734e946..c66eb6abd4a2ee 100644 --- a/drivers/gpu/drm/i915/intel_clock_gating.c +++ b/drivers/gpu/drm/i915/intel_clock_gating.c @@ -396,14 +396,6 @@ static void dg2_init_clock_gating(struct drm_i915_private *i915) /* Wa_22010954014:dg2 */ intel_uncore_rmw(&i915->uncore, XEHP_CLOCK_GATE_DIS, 0, SGSI_SIDECLK_DIS); - - /* - * Wa_14010733611:dg2_g10 - * Wa_22010146351:dg2_g10 - */ - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) - intel_uncore_rmw(&i915->uncore, XEHP_CLOCK_GATE_DIS, 0, - SGR_DIS | SGGI_DIS); } static void pvc_init_clock_gating(struct drm_i915_private *i915) diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.c b/drivers/gpu/drm/i915/selftests/igt_live_test.c index 4ddc6d902752af..7d41874a49c589 100644 --- a/drivers/gpu/drm/i915/selftests/igt_live_test.c +++ b/drivers/gpu/drm/i915/selftests/igt_live_test.c @@ -37,8 +37,9 @@ int igt_live_test_begin(struct igt_live_test *t, } for_each_engine(engine, gt, id) - t->reset_engine[id] = - i915_reset_engine_count(&i915->gpu_error, engine); + t->reset_engine[i][id] = + i915_reset_engine_count(&i915->gpu_error, + engine); } t->reset_global = i915_reset_count(&i915->gpu_error); @@ -66,14 +67,14 @@ int igt_live_test_end(struct igt_live_test *t) for_each_gt(gt, i915, i) { for_each_engine(engine, gt, id) { - if (t->reset_engine[id] == + if (t->reset_engine[i][id] == i915_reset_engine_count(&i915->gpu_error, engine)) continue; gt_err(gt, "%s(%s): engine '%s' was reset %d times!\n", t->func, t->name, engine->name, i915_reset_engine_count(&i915->gpu_error, engine) - - t->reset_engine[id]); + t->reset_engine[i][id]); return -EIO; } } diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.h b/drivers/gpu/drm/i915/selftests/igt_live_test.h index 36ed42736c5216..83e3ad430922fe 100644 --- a/drivers/gpu/drm/i915/selftests/igt_live_test.h +++ b/drivers/gpu/drm/i915/selftests/igt_live_test.h @@ -7,6 +7,7 @@ #ifndef IGT_LIVE_TEST_H #define IGT_LIVE_TEST_H +#include "gt/intel_gt_defines.h" /* for I915_MAX_GT */ #include "gt/intel_engine.h" /* for I915_NUM_ENGINES */ struct drm_i915_private; @@ -17,7 +18,7 @@ struct igt_live_test { const char *name; unsigned int reset_global; - unsigned int reset_engine[I915_NUM_ENGINES]; + unsigned int reset_engine[I915_MAX_GT][I915_NUM_ENGINES]; }; /* diff --git a/drivers/gpu/drm/imx/ipuv3/parallel-display.c b/drivers/gpu/drm/imx/ipuv3/parallel-display.c index 0fa0b590830b66..c62df2557dc65e 100644 --- a/drivers/gpu/drm/imx/ipuv3/parallel-display.c +++ b/drivers/gpu/drm/imx/ipuv3/parallel-display.c @@ -72,14 +72,14 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector) int ret; if (!mode) - return -EINVAL; + return 0; ret = of_get_drm_display_mode(np, &imxpd->mode, &imxpd->bus_flags, OF_USE_NATIVE_MODE); if (ret) { drm_mode_destroy(connector->dev, mode); - return ret; + return 0; } drm_mode_copy(mode, &imxpd->mode); diff --git a/drivers/gpu/drm/imx/lcdc/imx-lcdc.c b/drivers/gpu/drm/imx/lcdc/imx-lcdc.c index 22b65f4a0e3034..4beb3b4bd6942c 100644 --- a/drivers/gpu/drm/imx/lcdc/imx-lcdc.c +++ b/drivers/gpu/drm/imx/lcdc/imx-lcdc.c @@ -342,21 +342,12 @@ static const struct drm_mode_config_helper_funcs imx_lcdc_mode_config_helpers = .atomic_commit_tail = drm_atomic_helper_commit_tail_rpm, }; -static void imx_lcdc_release(struct drm_device *drm) -{ - struct imx_lcdc *lcdc = imx_lcdc_from_drmdev(drm); - - drm_kms_helper_poll_fini(drm); - kfree(lcdc); -} - DEFINE_DRM_GEM_DMA_FOPS(imx_lcdc_drm_fops); static struct drm_driver imx_lcdc_drm_driver = { .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, .fops = &imx_lcdc_drm_fops, DRM_GEM_DMA_DRIVER_OPS_VMAP, - .release = imx_lcdc_release, .name = "imx-lcdc", .desc = "i.MX LCDC driver", .date = "20200716", diff --git a/drivers/gpu/drm/lima/lima_bcast.c b/drivers/gpu/drm/lima/lima_bcast.c index fbc43f243c54d2..6d000504e1a4ee 100644 --- a/drivers/gpu/drm/lima/lima_bcast.c +++ b/drivers/gpu/drm/lima/lima_bcast.c @@ -43,6 +43,18 @@ void lima_bcast_suspend(struct lima_ip *ip) } +int lima_bcast_mask_irq(struct lima_ip *ip) +{ + bcast_write(LIMA_BCAST_BROADCAST_MASK, 0); + bcast_write(LIMA_BCAST_INTERRUPT_MASK, 0); + return 0; +} + +int lima_bcast_reset(struct lima_ip *ip) +{ + return lima_bcast_hw_init(ip); +} + int lima_bcast_init(struct lima_ip *ip) { int i; diff --git a/drivers/gpu/drm/lima/lima_bcast.h b/drivers/gpu/drm/lima/lima_bcast.h index 465ee587bceb2f..cd08841e47879c 100644 --- a/drivers/gpu/drm/lima/lima_bcast.h +++ b/drivers/gpu/drm/lima/lima_bcast.h @@ -13,4 +13,7 @@ void lima_bcast_fini(struct lima_ip *ip); void lima_bcast_enable(struct lima_device *dev, int num_pp); +int lima_bcast_mask_irq(struct lima_ip *ip); +int lima_bcast_reset(struct lima_ip *ip); + #endif diff --git a/drivers/gpu/drm/lima/lima_drv.c b/drivers/gpu/drm/lima/lima_drv.c index 10fd9154cc4653..8c9b656eeb59d2 100644 --- a/drivers/gpu/drm/lima/lima_drv.c +++ b/drivers/gpu/drm/lima/lima_drv.c @@ -486,3 +486,4 @@ module_platform_driver(lima_platform_driver); MODULE_AUTHOR("Lima Project Developers"); MODULE_DESCRIPTION("Lima DRM Driver"); MODULE_LICENSE("GPL v2"); +MODULE_SOFTDEP("pre: governor_simpleondemand"); diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c index 4f9736e5f929be..7ea244d876ca63 100644 --- a/drivers/gpu/drm/lima/lima_gem.c +++ b/drivers/gpu/drm/lima/lima_gem.c @@ -75,29 +75,34 @@ int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm) } else { bo->base.sgt = kmalloc(sizeof(*bo->base.sgt), GFP_KERNEL); if (!bo->base.sgt) { - sg_free_table(&sgt); - return -ENOMEM; + ret = -ENOMEM; + goto err_out0; } } ret = dma_map_sgtable(dev, &sgt, DMA_BIDIRECTIONAL, 0); - if (ret) { - sg_free_table(&sgt); - kfree(bo->base.sgt); - bo->base.sgt = NULL; - return ret; - } + if (ret) + goto err_out1; *bo->base.sgt = sgt; if (vm) { ret = lima_vm_map_bo(vm, bo, old_size >> PAGE_SHIFT); if (ret) - return ret; + goto err_out2; } bo->heap_size = new_size; return 0; + +err_out2: + dma_unmap_sgtable(dev, &sgt, DMA_BIDIRECTIONAL, 0); +err_out1: + kfree(bo->base.sgt); + bo->base.sgt = NULL; +err_out0: + sg_free_table(&sgt); + return ret; } int lima_gem_create_handle(struct drm_device *dev, struct drm_file *file, diff --git a/drivers/gpu/drm/lima/lima_gp.c b/drivers/gpu/drm/lima/lima_gp.c index 8dd501b7a3d0d8..82071835ec9ed2 100644 --- a/drivers/gpu/drm/lima/lima_gp.c +++ b/drivers/gpu/drm/lima/lima_gp.c @@ -166,6 +166,11 @@ static void lima_gp_task_run(struct lima_sched_pipe *pipe, gp_write(LIMA_GP_CMD, cmd); } +static int lima_gp_bus_stop_poll(struct lima_ip *ip) +{ + return !!(gp_read(LIMA_GP_STATUS) & LIMA_GP_STATUS_BUS_STOPPED); +} + static int lima_gp_hard_reset_poll(struct lima_ip *ip) { gp_write(LIMA_GP_PERF_CNT_0_LIMIT, 0xC01A0000); @@ -179,6 +184,13 @@ static int lima_gp_hard_reset(struct lima_ip *ip) gp_write(LIMA_GP_PERF_CNT_0_LIMIT, 0xC0FFE000); gp_write(LIMA_GP_INT_MASK, 0); + + gp_write(LIMA_GP_CMD, LIMA_GP_CMD_STOP_BUS); + ret = lima_poll_timeout(ip, lima_gp_bus_stop_poll, 10, 100); + if (ret) { + dev_err(dev->dev, "%s bus stop timeout\n", lima_ip_name(ip)); + return ret; + } gp_write(LIMA_GP_CMD, LIMA_GP_CMD_RESET); ret = lima_poll_timeout(ip, lima_gp_hard_reset_poll, 10, 100); if (ret) { @@ -212,6 +224,13 @@ static void lima_gp_task_mmu_error(struct lima_sched_pipe *pipe) lima_sched_pipe_task_done(pipe); } +static void lima_gp_task_mask_irq(struct lima_sched_pipe *pipe) +{ + struct lima_ip *ip = pipe->processor[0]; + + gp_write(LIMA_GP_INT_MASK, 0); +} + static int lima_gp_task_recover(struct lima_sched_pipe *pipe) { struct lima_ip *ip = pipe->processor[0]; @@ -317,7 +336,9 @@ int lima_gp_init(struct lima_ip *ip) void lima_gp_fini(struct lima_ip *ip) { + struct lima_device *dev = ip->dev; + devm_free_irq(dev->dev, ip->irq, ip); } int lima_gp_pipe_init(struct lima_device *dev) @@ -344,6 +365,7 @@ int lima_gp_pipe_init(struct lima_device *dev) pipe->task_error = lima_gp_task_error; pipe->task_mmu_error = lima_gp_task_mmu_error; pipe->task_recover = lima_gp_task_recover; + pipe->task_mask_irq = lima_gp_task_mask_irq; return 0; } diff --git a/drivers/gpu/drm/lima/lima_mmu.c b/drivers/gpu/drm/lima/lima_mmu.c index a1ae6c252dc2b5..8ca7047adbaca9 100644 --- a/drivers/gpu/drm/lima/lima_mmu.c +++ b/drivers/gpu/drm/lima/lima_mmu.c @@ -118,7 +118,12 @@ int lima_mmu_init(struct lima_ip *ip) void lima_mmu_fini(struct lima_ip *ip) { + struct lima_device *dev = ip->dev; + + if (ip->id == lima_ip_ppmmu_bcast) + return; + devm_free_irq(dev->dev, ip->irq, ip); } void lima_mmu_flush_tlb(struct lima_ip *ip) diff --git a/drivers/gpu/drm/lima/lima_pp.c b/drivers/gpu/drm/lima/lima_pp.c index a5c95bed08c09c..d34c9e8840f454 100644 --- a/drivers/gpu/drm/lima/lima_pp.c +++ b/drivers/gpu/drm/lima/lima_pp.c @@ -266,7 +266,9 @@ int lima_pp_init(struct lima_ip *ip) void lima_pp_fini(struct lima_ip *ip) { + struct lima_device *dev = ip->dev; + devm_free_irq(dev->dev, ip->irq, ip); } int lima_pp_bcast_resume(struct lima_ip *ip) @@ -299,7 +301,9 @@ int lima_pp_bcast_init(struct lima_ip *ip) void lima_pp_bcast_fini(struct lima_ip *ip) { + struct lima_device *dev = ip->dev; + devm_free_irq(dev->dev, ip->irq, ip); } static int lima_pp_task_validate(struct lima_sched_pipe *pipe, @@ -408,6 +412,9 @@ static void lima_pp_task_error(struct lima_sched_pipe *pipe) lima_pp_hard_reset(ip); } + + if (pipe->bcast_processor) + lima_bcast_reset(pipe->bcast_processor); } static void lima_pp_task_mmu_error(struct lima_sched_pipe *pipe) @@ -416,6 +423,20 @@ static void lima_pp_task_mmu_error(struct lima_sched_pipe *pipe) lima_sched_pipe_task_done(pipe); } +static void lima_pp_task_mask_irq(struct lima_sched_pipe *pipe) +{ + int i; + + for (i = 0; i < pipe->num_processor; i++) { + struct lima_ip *ip = pipe->processor[i]; + + pp_write(LIMA_PP_INT_MASK, 0); + } + + if (pipe->bcast_processor) + lima_bcast_mask_irq(pipe->bcast_processor); +} + static struct kmem_cache *lima_pp_task_slab; static int lima_pp_task_slab_refcnt; @@ -447,6 +468,7 @@ int lima_pp_pipe_init(struct lima_device *dev) pipe->task_fini = lima_pp_task_fini; pipe->task_error = lima_pp_task_error; pipe->task_mmu_error = lima_pp_task_mmu_error; + pipe->task_mask_irq = lima_pp_task_mask_irq; return 0; } diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c index ffd91a5ee29901..1114bffe38c837 100644 --- a/drivers/gpu/drm/lima/lima_sched.c +++ b/drivers/gpu/drm/lima/lima_sched.c @@ -402,6 +402,13 @@ static enum drm_gpu_sched_stat lima_sched_timedout_job(struct drm_sched_job *job struct lima_sched_task *task = to_lima_task(job); struct lima_device *ldev = pipe->ldev; + /* + * The task might still finish while this timeout handler runs. + * To prevent a race condition on its completion, mask all irqs + * on the running core until the next hard reset completes. + */ + pipe->task_mask_irq(pipe); + if (!pipe->error) DRM_ERROR("lima job timeout\n"); diff --git a/drivers/gpu/drm/lima/lima_sched.h b/drivers/gpu/drm/lima/lima_sched.h index 6a11764d87b389..edf205be436998 100644 --- a/drivers/gpu/drm/lima/lima_sched.h +++ b/drivers/gpu/drm/lima/lima_sched.h @@ -80,6 +80,7 @@ struct lima_sched_pipe { void (*task_error)(struct lima_sched_pipe *pipe); void (*task_mmu_error)(struct lima_sched_pipe *pipe); int (*task_recover)(struct lima_sched_pipe *pipe); + void (*task_mask_irq)(struct lima_sched_pipe *pipe); struct work_struct recover_work; }; diff --git a/drivers/gpu/drm/loongson/lsdc_pixpll.c b/drivers/gpu/drm/loongson/lsdc_pixpll.c index 04c15b4697e218..2609a2256da4bf 100644 --- a/drivers/gpu/drm/loongson/lsdc_pixpll.c +++ b/drivers/gpu/drm/loongson/lsdc_pixpll.c @@ -120,12 +120,14 @@ static int lsdc_pixel_pll_setup(struct lsdc_pixpll * const this) struct lsdc_pixpll_parms *pparms; this->mmio = ioremap(this->reg_base, this->reg_size); - if (IS_ERR_OR_NULL(this->mmio)) + if (!this->mmio) return -ENOMEM; pparms = kzalloc(sizeof(*pparms), GFP_KERNEL); - if (IS_ERR_OR_NULL(pparms)) + if (!pparms) { + iounmap(this->mmio); return -ENOMEM; + } pparms->ref_clock = LSDC_PLL_REF_CLK_KHZ; diff --git a/drivers/gpu/drm/mediatek/mtk_disp_merge.c b/drivers/gpu/drm/mediatek/mtk_disp_merge.c index e525a6b9e5b0bc..22f768d923d5ab 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_merge.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_merge.c @@ -103,7 +103,7 @@ void mtk_merge_stop_cmdq(struct device *dev, struct cmdq_pkt *cmdq_pkt) mtk_ddp_write(cmdq_pkt, 0, &priv->cmdq_reg, priv->regs, DISP_REG_MERGE_CTRL); - if (priv->async_clk) + if (!cmdq_pkt && priv->async_clk) reset_control_reset(priv->reset_ctl); } diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index 2bffe424546667..6f15069da8b020 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -38,6 +38,7 @@ #define DISP_REG_OVL_PITCH_MSB(n) (0x0040 + 0x20 * (n)) #define OVL_PITCH_MSB_2ND_SUBBUF BIT(16) #define DISP_REG_OVL_PITCH(n) (0x0044 + 0x20 * (n)) +#define OVL_CONST_BLEND BIT(28) #define DISP_REG_OVL_RDMA_CTRL(n) (0x00c0 + 0x20 * (n)) #define DISP_REG_OVL_RDMA_GMC(n) (0x00c8 + 0x20 * (n)) #define DISP_REG_OVL_ADDR_MT2701 0x0040 @@ -71,6 +72,8 @@ #define OVL_CON_VIRT_FLIP BIT(9) #define OVL_CON_HORZ_FLIP BIT(10) +#define OVL_COLOR_ALPHA GENMASK(31, 24) + static const u32 mt8173_formats[] = { DRM_FORMAT_XRGB8888, DRM_FORMAT_ARGB8888, @@ -273,7 +276,13 @@ void mtk_ovl_config(struct device *dev, unsigned int w, if (w != 0 && h != 0) mtk_ddp_write_relaxed(cmdq_pkt, h << 16 | w, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_ROI_SIZE); - mtk_ddp_write_relaxed(cmdq_pkt, 0x0, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_ROI_BGCLR); + + /* + * The background color must be opaque black (ARGB), + * otherwise the alpha blending will have no effect + */ + mtk_ddp_write_relaxed(cmdq_pkt, OVL_COLOR_ALPHA, &ovl->cmdq_reg, + ovl->regs, DISP_REG_OVL_ROI_BGCLR); mtk_ddp_write(cmdq_pkt, 0x1, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_RST); mtk_ddp_write(cmdq_pkt, 0x0, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_RST); @@ -407,6 +416,7 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, unsigned int fmt = pending->format; unsigned int offset = (pending->y << 16) | pending->x; unsigned int src_size = (pending->height << 16) | pending->width; + unsigned int ignore_pixel_alpha = 0; unsigned int con; bool is_afbc = pending->modifier != DRM_FORMAT_MOD_LINEAR; union overlay_pitch { @@ -428,6 +438,14 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, if (state->base.fb && state->base.fb->format->has_alpha) con |= OVL_CON_AEN | OVL_CON_ALPHA; + /* CONST_BLD must be enabled for XRGB formats although the alpha channel + * can be ignored, or OVL will still read the value from memory. + * For RGB888 related formats, whether CONST_BLD is enabled or not won't + * affect the result. Therefore we use !has_alpha as the condition. + */ + if (state->base.fb && !state->base.fb->format->has_alpha) + ignore_pixel_alpha = OVL_CONST_BLEND; + if (pending->rotation & DRM_MODE_REFLECT_Y) { con |= OVL_CON_VIRT_FLIP; addr += (pending->height - 1) * pending->pitch; @@ -443,8 +461,8 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, mtk_ddp_write_relaxed(cmdq_pkt, con, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_CON(idx)); - mtk_ddp_write_relaxed(cmdq_pkt, overlay_pitch.split_pitch.lsb, &ovl->cmdq_reg, ovl->regs, - DISP_REG_OVL_PITCH(idx)); + mtk_ddp_write_relaxed(cmdq_pkt, overlay_pitch.split_pitch.lsb | ignore_pixel_alpha, + &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH(idx)); mtk_ddp_write_relaxed(cmdq_pkt, src_size, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_SRC_SIZE(idx)); mtk_ddp_write_relaxed(cmdq_pkt, offset, &ovl->cmdq_reg, ovl->regs, diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c index 6bf6367853fbae..036028b8f5248d 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c @@ -111,7 +111,7 @@ void mtk_ovl_adaptor_layer_config(struct device *dev, unsigned int idx, merge = ovl_adaptor->ovl_adaptor_comp[OVL_ADAPTOR_MERGE0 + idx]; ethdr = ovl_adaptor->ovl_adaptor_comp[OVL_ADAPTOR_ETHDR0]; - if (!pending->enable) { + if (!pending->enable || !pending->width || !pending->height) { mtk_merge_stop_cmdq(merge, cmdq_pkt); mtk_mdp_rdma_stop(rdma_l, cmdq_pkt); mtk_mdp_rdma_stop(rdma_r, cmdq_pkt); @@ -436,8 +436,10 @@ static int ovl_adaptor_comp_init(struct device *dev, struct component_match **ma } comp_pdev = of_find_device_by_node(node); - if (!comp_pdev) + if (!comp_pdev) { + of_node_put(node); return -EPROBE_DEFER; + } priv->ovl_adaptor_comp[id] = &comp_pdev->dev; diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c index 2cb47f6637568b..48a4defbc66cc8 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp.c +++ b/drivers/gpu/drm/mediatek/mtk_dp.c @@ -2027,21 +2027,20 @@ static enum drm_connector_status mtk_dp_bdg_detect(struct drm_bridge *bridge) return ret; } -static struct edid *mtk_dp_get_edid(struct drm_bridge *bridge, - struct drm_connector *connector) +static const struct drm_edid *mtk_dp_edid_read(struct drm_bridge *bridge, + struct drm_connector *connector) { struct mtk_dp *mtk_dp = mtk_dp_from_bridge(bridge); bool enabled = mtk_dp->enabled; - struct edid *new_edid = NULL; + const struct drm_edid *drm_edid; struct mtk_dp_audio_cfg *audio_caps = &mtk_dp->info.audio_cur_cfg; - struct cea_sad *sads; if (!enabled) { drm_atomic_bridge_chain_pre_enable(bridge, connector->state->state); mtk_dp_aux_panel_poweron(mtk_dp, true); } - new_edid = drm_get_edid(connector, &mtk_dp->aux.ddc); + drm_edid = drm_edid_read_ddc(connector, &mtk_dp->aux.ddc); /* * Parse capability here to let atomic_get_input_bus_fmts and @@ -2049,12 +2048,32 @@ static struct edid *mtk_dp_get_edid(struct drm_bridge *bridge, */ if (mtk_dp_parse_capabilities(mtk_dp)) { drm_err(mtk_dp->drm_dev, "Can't parse capabilities\n"); - new_edid = NULL; + drm_edid_free(drm_edid); + drm_edid = NULL; } - if (new_edid) { - audio_caps->sad_count = drm_edid_to_sad(new_edid, &sads); - audio_caps->detect_monitor = drm_detect_monitor_audio(new_edid); + if (drm_edid) { + /* + * FIXME: get rid of drm_edid_raw() + */ + const struct edid *edid = drm_edid_raw(drm_edid); + struct cea_sad *sads; + int ret; + + ret = drm_edid_to_sad(edid, &sads); + /* Ignore any errors */ + if (ret < 0) + ret = 0; + if (ret) + kfree(sads); + audio_caps->sad_count = ret; + + /* + * FIXME: This should use connector->display_info.has_audio from + * a path that has read the EDID and called + * drm_edid_connector_update(). + */ + audio_caps->detect_monitor = drm_detect_monitor_audio(edid); } if (!enabled) { @@ -2062,7 +2081,7 @@ static struct edid *mtk_dp_get_edid(struct drm_bridge *bridge, drm_atomic_bridge_chain_post_disable(bridge, connector->state->state); } - return new_edid; + return drm_edid; } static ssize_t mtk_dp_aux_transfer(struct drm_dp_aux *mtk_aux, @@ -2076,7 +2095,7 @@ static ssize_t mtk_dp_aux_transfer(struct drm_dp_aux *mtk_aux, if (mtk_dp->bridge.type != DRM_MODE_CONNECTOR_eDP && !mtk_dp->train_info.cable_plugged_in) { - ret = -EAGAIN; + ret = -EIO; goto err; } @@ -2414,7 +2433,7 @@ static const struct drm_bridge_funcs mtk_dp_bridge_funcs = { .atomic_enable = mtk_dp_bridge_atomic_enable, .atomic_disable = mtk_dp_bridge_atomic_disable, .mode_valid = mtk_dp_bridge_mode_valid, - .get_edid = mtk_dp_get_edid, + .edid_read = mtk_dp_edid_read, .detect = mtk_dp_bdg_detect, }; @@ -2780,3 +2799,4 @@ MODULE_AUTHOR("Markus Schneider-Pargmann "); MODULE_AUTHOR("Bo-Chen Chen "); MODULE_DESCRIPTION("MediaTek DisplayPort Driver"); MODULE_LICENSE("GPL"); +MODULE_SOFTDEP("pre: phy_mtk_dp"); diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index 2f931e4e2b6009..bc073a6b367e5b 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -957,20 +957,6 @@ static const struct mtk_dpi_conf mt8186_conf = { .csc_enable_bit = CSC_ENABLE, }; -static const struct mtk_dpi_conf mt8188_dpintf_conf = { - .cal_factor = mt8195_dpintf_calculate_factor, - .max_clock_khz = 600000, - .output_fmts = mt8195_output_fmts, - .num_output_fmts = ARRAY_SIZE(mt8195_output_fmts), - .pixels_per_iter = 4, - .input_2pixel = false, - .dimension_mask = DPINTF_HPW_MASK, - .hvsize_mask = DPINTF_HSIZE_MASK, - .channel_swap_shift = DPINTF_CH_SWAP, - .yuv422_en_bit = DPINTF_YUV422_EN, - .csc_enable_bit = DPINTF_CSC_ENABLE, -}; - static const struct mtk_dpi_conf mt8192_conf = { .cal_factor = mt8183_calculate_factor, .reg_h_fre_con = 0xe0, @@ -1094,7 +1080,7 @@ static const struct of_device_id mtk_dpi_of_ids[] = { { .compatible = "mediatek,mt8173-dpi", .data = &mt8173_conf }, { .compatible = "mediatek,mt8183-dpi", .data = &mt8183_conf }, { .compatible = "mediatek,mt8186-dpi", .data = &mt8186_conf }, - { .compatible = "mediatek,mt8188-dp-intf", .data = &mt8188_dpintf_conf }, + { .compatible = "mediatek,mt8188-dp-intf", .data = &mt8195_dpintf_conf }, { .compatible = "mediatek,mt8192-dpi", .data = &mt8192_conf }, { .compatible = "mediatek,mt8195-dp-intf", .data = &mt8195_dpintf_conf }, { /* sentinel */ }, diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index b6fa4ad2f94dc0..659112da47b692 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -67,6 +67,8 @@ struct mtk_drm_crtc { /* lock for display hardware access */ struct mutex hw_lock; bool config_updating; + /* lock for config_updating to cmd buffer */ + spinlock_t config_lock; }; struct mtk_crtc_state { @@ -93,20 +95,27 @@ static void mtk_drm_crtc_finish_page_flip(struct mtk_drm_crtc *mtk_crtc) struct drm_crtc *crtc = &mtk_crtc->base; unsigned long flags; - spin_lock_irqsave(&crtc->dev->event_lock, flags); - drm_crtc_send_vblank_event(crtc, mtk_crtc->event); - drm_crtc_vblank_put(crtc); - mtk_crtc->event = NULL; - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + if (mtk_crtc->event) { + spin_lock_irqsave(&crtc->dev->event_lock, flags); + drm_crtc_send_vblank_event(crtc, mtk_crtc->event); + drm_crtc_vblank_put(crtc); + mtk_crtc->event = NULL; + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + } } static void mtk_drm_finish_page_flip(struct mtk_drm_crtc *mtk_crtc) { + unsigned long flags; + drm_crtc_handle_vblank(&mtk_crtc->base); + + spin_lock_irqsave(&mtk_crtc->config_lock, flags); if (!mtk_crtc->config_updating && mtk_crtc->pending_needs_vblank) { mtk_drm_crtc_finish_page_flip(mtk_crtc); mtk_crtc->pending_needs_vblank = false; } + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); } #if IS_REACHABLE(CONFIG_MTK_CMDQ) @@ -289,12 +298,19 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg) struct mtk_drm_crtc *mtk_crtc = container_of(cmdq_cl, struct mtk_drm_crtc, cmdq_client); struct mtk_crtc_state *state; unsigned int i; + unsigned long flags; if (data->sta < 0) return; state = to_mtk_crtc_state(mtk_crtc->base.state); + spin_lock_irqsave(&mtk_crtc->config_lock, flags); + if (mtk_crtc->config_updating) { + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + goto ddp_cmdq_cb_out; + } + state->pending_config = false; if (mtk_crtc->pending_planes) { @@ -321,6 +337,10 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg) mtk_crtc->pending_async_planes = false; } + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + +ddp_cmdq_cb_out: + mtk_crtc->cmdq_vblank_cnt = 0; wake_up(&mtk_crtc->cb_blocking_queue); } @@ -408,6 +428,9 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc) unsigned int local_layer; plane_state = to_mtk_plane_state(plane->state); + + /* should not enable layer before crtc enabled */ + plane_state->pending.enable = false; comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer); if (comp) mtk_ddp_comp_layer_config(comp, local_layer, @@ -427,6 +450,7 @@ static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc) { struct drm_device *drm = mtk_crtc->base.dev; struct drm_crtc *crtc = &mtk_crtc->base; + unsigned long flags; int i; for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) { @@ -458,10 +482,10 @@ static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc) pm_runtime_put(drm->dev); if (crtc->state->event && !crtc->state->active) { - spin_lock_irq(&crtc->dev->event_lock); + spin_lock_irqsave(&crtc->dev->event_lock, flags); drm_crtc_send_vblank_event(crtc, crtc->state->event); crtc->state->event = NULL; - spin_unlock_irq(&crtc->dev->event_lock); + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); } } @@ -550,9 +574,14 @@ static void mtk_drm_crtc_update_config(struct mtk_drm_crtc *mtk_crtc, struct mtk_drm_private *priv = crtc->dev->dev_private; unsigned int pending_planes = 0, pending_async_planes = 0; int i; + unsigned long flags; mutex_lock(&mtk_crtc->hw_lock); + + spin_lock_irqsave(&mtk_crtc->config_lock, flags); mtk_crtc->config_updating = true; + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + if (needs_vblank) mtk_crtc->pending_needs_vblank = true; @@ -606,7 +635,10 @@ static void mtk_drm_crtc_update_config(struct mtk_drm_crtc *mtk_crtc, mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0); } #endif + spin_lock_irqsave(&mtk_crtc->config_lock, flags); mtk_crtc->config_updating = false; + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + mutex_unlock(&mtk_crtc->hw_lock); } @@ -744,6 +776,7 @@ static void mtk_drm_crtc_atomic_begin(struct drm_crtc *crtc, crtc); struct mtk_crtc_state *mtk_crtc_state = to_mtk_crtc_state(crtc_state); struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); + unsigned long flags; if (mtk_crtc->event && mtk_crtc_state->base.event) DRM_ERROR("new event while there is still a pending event\n"); @@ -751,7 +784,11 @@ static void mtk_drm_crtc_atomic_begin(struct drm_crtc *crtc, if (mtk_crtc_state->base.event) { mtk_crtc_state->base.event->pipe = drm_crtc_index(crtc); WARN_ON(drm_crtc_vblank_get(crtc) != 0); + + spin_lock_irqsave(&crtc->dev->event_lock, flags); mtk_crtc->event = mtk_crtc_state->base.event; + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + mtk_crtc_state->base.event = NULL; } } @@ -877,7 +914,14 @@ static int mtk_drm_crtc_init_comp_planes(struct drm_device *drm_dev, struct device *mtk_drm_crtc_dma_dev_get(struct drm_crtc *crtc) { - struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); + struct mtk_drm_crtc *mtk_crtc = NULL; + + if (!crtc) + return NULL; + + mtk_crtc = to_mtk_crtc(crtc); + if (!mtk_crtc) + return NULL; return mtk_crtc->dma_dev; } @@ -997,6 +1041,7 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, drm_mode_crtc_set_gamma_size(&mtk_crtc->base, gamma_lut_size); drm_crtc_enable_color_mgmt(&mtk_crtc->base, 0, has_ctm, gamma_lut_size); mutex_init(&mtk_crtc->hw_lock); + spin_lock_init(&mtk_crtc->config_lock); #if IS_REACHABLE(CONFIG_MTK_CMDQ) i = priv->mbox_index++; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c index 771f4e1733539c..66ccde966e3c10 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c @@ -553,7 +553,7 @@ int mtk_ddp_comp_init(struct device_node *node, struct mtk_ddp_comp *comp, int ret; #endif - if (comp_id < 0 || comp_id >= DDP_COMPONENT_DRM_ID_MAX) + if (comp_id >= DDP_COMPONENT_DRM_ID_MAX) return -EINVAL; type = mtk_ddp_matches[comp_id].type; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 93552d76b6e778..ffe016d6cbcfe0 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -288,6 +288,7 @@ static const struct mtk_mmsys_driver_data mt8186_mmsys_driver_data = { static const struct mtk_mmsys_driver_data mt8188_vdosys0_driver_data = { .main_path = mt8188_mtk_ddp_main, .main_len = ARRAY_SIZE(mt8188_mtk_ddp_main), + .mmsys_dev_num = 1, }; static const struct mtk_mmsys_driver_data mt8192_mmsys_driver_data = { @@ -420,6 +421,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) struct mtk_drm_private *private = drm->dev_private; struct mtk_drm_private *priv_n; struct device *dma_dev = NULL; + struct drm_crtc *crtc; int ret, i, j; if (drm_firmware_drivers_only()) @@ -494,7 +496,9 @@ static int mtk_drm_kms_init(struct drm_device *drm) } /* Use OVL device for all DMA memory allocations */ - dma_dev = mtk_drm_crtc_dma_dev_get(drm_crtc_from_index(drm, 0)); + crtc = drm_crtc_from_index(drm, 0); + if (crtc) + dma_dev = mtk_drm_crtc_dma_dev_get(crtc); if (!dma_dev) { ret = -ENODEV; dev_err(drm->dev, "Need at least one OVL device\n"); @@ -715,6 +719,8 @@ static const struct of_device_id mtk_ddp_comp_dt_ids[] = { .data = (void *)MTK_DISP_OVL }, { .compatible = "mediatek,mt8192-disp-ovl", .data = (void *)MTK_DISP_OVL }, + { .compatible = "mediatek,mt8195-disp-ovl", + .data = (void *)MTK_DISP_OVL }, { .compatible = "mediatek,mt8183-disp-ovl-2l", .data = (void *)MTK_DISP_OVL_2L }, { .compatible = "mediatek,mt8192-disp-ovl-2l", @@ -922,6 +928,13 @@ static void mtk_drm_remove(struct platform_device *pdev) of_node_put(private->comp_node[i]); } +static void mtk_drm_shutdown(struct platform_device *pdev) +{ + struct mtk_drm_private *private = platform_get_drvdata(pdev); + + drm_atomic_helper_shutdown(private->drm); +} + static int mtk_drm_sys_prepare(struct device *dev) { struct mtk_drm_private *private = dev_get_drvdata(dev); @@ -953,6 +966,7 @@ static const struct dev_pm_ops mtk_drm_pm_ops = { static struct platform_driver mtk_drm_platform_driver = { .probe = mtk_drm_probe, .remove_new = mtk_drm_remove, + .shutdown = mtk_drm_shutdown, .driver = { .name = "mediatek-drm", .pm = &mtk_drm_pm_ops, diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c index 0e0a41b2f57f05..1bf229615b0188 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c @@ -38,6 +38,9 @@ static struct mtk_drm_gem_obj *mtk_drm_gem_init(struct drm_device *dev, size = round_up(size, PAGE_SIZE); + if (size == 0) + return ERR_PTR(-EINVAL); + mtk_gem_obj = kzalloc(sizeof(*mtk_gem_obj), GFP_KERNEL); if (!mtk_gem_obj) return ERR_PTR(-ENOMEM); @@ -121,7 +124,14 @@ int mtk_drm_gem_dumb_create(struct drm_file *file_priv, struct drm_device *dev, int ret; args->pitch = DIV_ROUND_UP(args->width * args->bpp, 8); - args->size = args->pitch * args->height; + + /* + * Multiply 2 variables of different types, + * for example: args->size = args->spacing * args->height; + * may cause coverity issue with unintentional overflow. + */ + args->size = args->pitch; + args->size *= args->height; mtk_gem = mtk_drm_gem_create(dev, args->size, false); if (IS_ERR(mtk_gem)) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c index db2f70ae060d6f..f10d4cc6c2234f 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c @@ -141,6 +141,7 @@ static void mtk_plane_update_new_state(struct drm_plane_state *new_state, dma_addr_t addr; dma_addr_t hdr_addr = 0; unsigned int hdr_pitch = 0; + int offset; gem = fb->obj[0]; mtk_gem = to_mtk_gem_obj(gem); @@ -150,8 +151,15 @@ static void mtk_plane_update_new_state(struct drm_plane_state *new_state, modifier = fb->modifier; if (modifier == DRM_FORMAT_MOD_LINEAR) { - addr += (new_state->src.x1 >> 16) * fb->format->cpp[0]; - addr += (new_state->src.y1 >> 16) * pitch; + /* + * Using dma_addr_t variable to calculate with multiplier of different types, + * for example: addr += (new_state->src.x1 >> 16) * fb->format->cpp[0]; + * may cause coverity issue with unintentional overflow. + */ + offset = (new_state->src.x1 >> 16) * fb->format->cpp[0]; + addr += offset; + offset = (new_state->src.y1 >> 16) * pitch; + addr += offset; } else { int width_in_blocks = ALIGN(fb->width, AFBC_DATA_BLOCK_WIDTH) / AFBC_DATA_BLOCK_WIDTH; @@ -159,21 +167,34 @@ static void mtk_plane_update_new_state(struct drm_plane_state *new_state, / AFBC_DATA_BLOCK_HEIGHT; int x_offset_in_blocks = (new_state->src.x1 >> 16) / AFBC_DATA_BLOCK_WIDTH; int y_offset_in_blocks = (new_state->src.y1 >> 16) / AFBC_DATA_BLOCK_HEIGHT; - int hdr_size; + int hdr_size, hdr_offset; hdr_pitch = width_in_blocks * AFBC_HEADER_BLOCK_SIZE; pitch = width_in_blocks * AFBC_DATA_BLOCK_WIDTH * AFBC_DATA_BLOCK_HEIGHT * fb->format->cpp[0]; hdr_size = ALIGN(hdr_pitch * height_in_blocks, AFBC_HEADER_ALIGNMENT); + hdr_offset = hdr_pitch * y_offset_in_blocks + + AFBC_HEADER_BLOCK_SIZE * x_offset_in_blocks; + + /* + * Using dma_addr_t variable to calculate with multiplier of different types, + * for example: addr += hdr_pitch * y_offset_in_blocks; + * may cause coverity issue with unintentional overflow. + */ + hdr_addr = addr + hdr_offset; - hdr_addr = addr + hdr_pitch * y_offset_in_blocks + - AFBC_HEADER_BLOCK_SIZE * x_offset_in_blocks; /* The data plane is offset by 1 additional block. */ - addr = addr + hdr_size + - pitch * y_offset_in_blocks + - AFBC_DATA_BLOCK_WIDTH * AFBC_DATA_BLOCK_HEIGHT * - fb->format->cpp[0] * (x_offset_in_blocks + 1); + offset = pitch * y_offset_in_blocks + + AFBC_DATA_BLOCK_WIDTH * AFBC_DATA_BLOCK_HEIGHT * + fb->format->cpp[0] * (x_offset_in_blocks + 1); + + /* + * Using dma_addr_t variable to calculate with multiplier of different types, + * for example: addr += pitch * y_offset_in_blocks; + * may cause coverity issue with unintentional overflow. + */ + addr = addr + hdr_size + offset; } mtk_plane_state->pending.enable = true; @@ -206,9 +227,11 @@ static void mtk_plane_atomic_async_update(struct drm_plane *plane, plane->state->src_y = new_state->src_y; plane->state->src_h = new_state->src_h; plane->state->src_w = new_state->src_w; - swap(plane->state->fb, new_state->fb); + plane->state->dst.x1 = new_state->dst.x1; + plane->state->dst.y1 = new_state->dst.y1; mtk_plane_update_new_state(new_state, new_plane_state); + swap(plane->state->fb, new_state->fb); wmb(); /* Make sure the above parameters are set before update */ new_plane_state->pending.async_dirty = true; mtk_drm_crtc_async_update(new_state->crtc, plane, state); diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index d8bfc2cce54dc6..0d96264ec5c6da 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -71,8 +71,8 @@ #define DSI_PS_WC 0x3fff #define DSI_PS_SEL (3 << 16) #define PACKED_PS_16BIT_RGB565 (0 << 16) -#define LOOSELY_PS_18BIT_RGB666 (1 << 16) -#define PACKED_PS_18BIT_RGB666 (2 << 16) +#define PACKED_PS_18BIT_RGB666 (1 << 16) +#define LOOSELY_PS_24BIT_RGB666 (2 << 16) #define PACKED_PS_24BIT_RGB888 (3 << 16) #define DSI_VSA_NL 0x20 @@ -367,10 +367,10 @@ static void mtk_dsi_ps_control_vact(struct mtk_dsi *dsi) ps_bpp_mode |= PACKED_PS_24BIT_RGB888; break; case MIPI_DSI_FMT_RGB666: - ps_bpp_mode |= PACKED_PS_18BIT_RGB666; + ps_bpp_mode |= LOOSELY_PS_24BIT_RGB666; break; case MIPI_DSI_FMT_RGB666_PACKED: - ps_bpp_mode |= LOOSELY_PS_18BIT_RGB666; + ps_bpp_mode |= PACKED_PS_18BIT_RGB666; break; case MIPI_DSI_FMT_RGB565: ps_bpp_mode |= PACKED_PS_16BIT_RGB565; @@ -407,7 +407,7 @@ static void mtk_dsi_rxtx_control(struct mtk_dsi *dsi) if (dsi->mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS) tmp_reg |= HSTX_CKLP_EN; - if (!(dsi->mode_flags & MIPI_DSI_MODE_NO_EOT_PACKET)) + if (dsi->mode_flags & MIPI_DSI_MODE_NO_EOT_PACKET) tmp_reg |= DIS_EOT; writel(tmp_reg, dsi->regs + DSI_TXRX_CTRL); @@ -424,7 +424,7 @@ static void mtk_dsi_ps_control(struct mtk_dsi *dsi) dsi_tmp_buf_bpp = 3; break; case MIPI_DSI_FMT_RGB666: - tmp_reg = LOOSELY_PS_18BIT_RGB666; + tmp_reg = LOOSELY_PS_24BIT_RGB666; dsi_tmp_buf_bpp = 3; break; case MIPI_DSI_FMT_RGB666_PACKED: @@ -484,7 +484,7 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi) timing->da_hs_zero + timing->da_hs_exit + 3; delta = dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST ? 18 : 12; - delta += dsi->mode_flags & MIPI_DSI_MODE_NO_EOT_PACKET ? 2 : 0; + delta += dsi->mode_flags & MIPI_DSI_MODE_NO_EOT_PACKET ? 0 : 2; horizontal_frontporch_byte = vm->hfront_porch * dsi_tmp_buf_bpp; horizontal_front_back_byte = horizontal_frontporch_byte + horizontal_backporch_byte; diff --git a/drivers/gpu/drm/mediatek/mtk_ethdr.c b/drivers/gpu/drm/mediatek/mtk_ethdr.c index db7ac666ec5e11..0cf8c889941565 100644 --- a/drivers/gpu/drm/mediatek/mtk_ethdr.c +++ b/drivers/gpu/drm/mediatek/mtk_ethdr.c @@ -50,7 +50,6 @@ #define MIXER_INX_MODE_BYPASS 0 #define MIXER_INX_MODE_EVEN_EXTEND 1 -#define DEFAULT_9BIT_ALPHA 0x100 #define MIXER_ALPHA_AEN BIT(8) #define MIXER_ALPHA 0xff #define ETHDR_CLK_NUM 13 @@ -154,13 +153,19 @@ void mtk_ethdr_layer_config(struct device *dev, unsigned int idx, unsigned int offset = (pending->x & 1) << 31 | pending->y << 16 | pending->x; unsigned int align_width = ALIGN_DOWN(pending->width, 2); unsigned int alpha_con = 0; + bool replace_src_a = false; dev_dbg(dev, "%s+ idx:%d", __func__, idx); if (idx >= 4) return; - if (!pending->enable) { + if (!pending->enable || !pending->width || !pending->height) { + /* + * instead of disabling layer with MIX_SRC_CON directly + * set the size to 0 to avoid screen shift due to mixer + * mode switch (hardware behavior) + */ mtk_ddp_write(cmdq_pkt, 0, &mixer->cmdq_base, mixer->regs, MIX_L_SRC_SIZE(idx)); return; } @@ -168,8 +173,16 @@ void mtk_ethdr_layer_config(struct device *dev, unsigned int idx, if (state->base.fb && state->base.fb->format->has_alpha) alpha_con = MIXER_ALPHA_AEN | MIXER_ALPHA; - mtk_mmsys_mixer_in_config(priv->mmsys_dev, idx + 1, alpha_con ? false : true, - DEFAULT_9BIT_ALPHA, + if (state->base.fb && !state->base.fb->format->has_alpha) { + /* + * Mixer doesn't support CONST_BLD mode, + * use a trick to make the output equivalent + */ + replace_src_a = true; + } + + mtk_mmsys_mixer_in_config(priv->mmsys_dev, idx + 1, replace_src_a, + MIXER_ALPHA, pending->x & 1 ? MIXER_INX_MODE_EVEN_EXTEND : MIXER_INX_MODE_BYPASS, align_width / 2 - 1, cmdq_pkt); diff --git a/drivers/gpu/drm/mediatek/mtk_mdp_rdma.c b/drivers/gpu/drm/mediatek/mtk_mdp_rdma.c index c3adaeefd551a2..c7233d0ac210f1 100644 --- a/drivers/gpu/drm/mediatek/mtk_mdp_rdma.c +++ b/drivers/gpu/drm/mediatek/mtk_mdp_rdma.c @@ -246,8 +246,7 @@ int mtk_mdp_rdma_clk_enable(struct device *dev) { struct mtk_mdp_rdma *rdma = dev_get_drvdata(dev); - clk_prepare_enable(rdma->clk); - return 0; + return clk_prepare_enable(rdma->clk); } void mtk_mdp_rdma_clk_disable(struct device *dev) diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index cb674966e9aca7..095f634ff7c799 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -250,29 +250,20 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) if (ret) goto free_drm; ret = meson_canvas_alloc(priv->canvas, &priv->canvas_id_vd1_0); - if (ret) { - meson_canvas_free(priv->canvas, priv->canvas_id_osd1); - goto free_drm; - } + if (ret) + goto free_canvas_osd1; ret = meson_canvas_alloc(priv->canvas, &priv->canvas_id_vd1_1); - if (ret) { - meson_canvas_free(priv->canvas, priv->canvas_id_osd1); - meson_canvas_free(priv->canvas, priv->canvas_id_vd1_0); - goto free_drm; - } + if (ret) + goto free_canvas_vd1_0; ret = meson_canvas_alloc(priv->canvas, &priv->canvas_id_vd1_2); - if (ret) { - meson_canvas_free(priv->canvas, priv->canvas_id_osd1); - meson_canvas_free(priv->canvas, priv->canvas_id_vd1_0); - meson_canvas_free(priv->canvas, priv->canvas_id_vd1_1); - goto free_drm; - } + if (ret) + goto free_canvas_vd1_1; priv->vsync_irq = platform_get_irq(pdev, 0); ret = drm_vblank_init(drm, 1); if (ret) - goto free_drm; + goto free_canvas_vd1_2; /* Assign limits per soc revision/package */ for (i = 0 ; i < ARRAY_SIZE(meson_drm_soc_attrs) ; ++i) { @@ -288,11 +279,11 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) */ ret = drm_aperture_remove_framebuffers(&meson_driver); if (ret) - goto free_drm; + goto free_canvas_vd1_2; ret = drmm_mode_config_init(drm); if (ret) - goto free_drm; + goto free_canvas_vd1_2; drm->mode_config.max_width = 3840; drm->mode_config.max_height = 2160; drm->mode_config.funcs = &meson_mode_config_funcs; @@ -307,7 +298,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) if (priv->afbcd.ops) { ret = priv->afbcd.ops->init(priv); if (ret) - goto free_drm; + goto free_canvas_vd1_2; } /* Encoder Initialization */ @@ -371,6 +362,14 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) exit_afbcd: if (priv->afbcd.ops) priv->afbcd.ops->exit(priv); +free_canvas_vd1_2: + meson_canvas_free(priv->canvas, priv->canvas_id_vd1_2); +free_canvas_vd1_1: + meson_canvas_free(priv->canvas, priv->canvas_id_vd1_1); +free_canvas_vd1_0: + meson_canvas_free(priv->canvas, priv->canvas_id_vd1_0); +free_canvas_osd1: + meson_canvas_free(priv->canvas, priv->canvas_id_osd1); free_drm: drm_dev_put(drm); diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c index 5a9538bc0e26f8..5565f7777529f8 100644 --- a/drivers/gpu/drm/meson/meson_dw_hdmi.c +++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c @@ -106,6 +106,8 @@ #define HHI_HDMI_CLK_CNTL 0x1cc /* 0x73 */ #define HHI_HDMI_PHY_CNTL0 0x3a0 /* 0xe8 */ #define HHI_HDMI_PHY_CNTL1 0x3a4 /* 0xe9 */ +#define PHY_CNTL1_INIT 0x03900000 +#define PHY_INVERT BIT(17) #define HHI_HDMI_PHY_CNTL2 0x3a8 /* 0xea */ #define HHI_HDMI_PHY_CNTL3 0x3ac /* 0xeb */ #define HHI_HDMI_PHY_CNTL4 0x3b0 /* 0xec */ @@ -130,6 +132,8 @@ struct meson_dw_hdmi_data { unsigned int addr); void (*dwc_write)(struct meson_dw_hdmi *dw_hdmi, unsigned int addr, unsigned int data); + u32 cntl0_init; + u32 cntl1_init; }; struct meson_dw_hdmi { @@ -384,26 +388,6 @@ static int dw_hdmi_phy_init(struct dw_hdmi *hdmi, void *data, dw_hdmi_bus_fmt_is_420(hdmi)) mode_is_420 = true; - /* Enable clocks */ - regmap_update_bits(priv->hhi, HHI_HDMI_CLK_CNTL, 0xffff, 0x100); - - /* Bring HDMITX MEM output of power down */ - regmap_update_bits(priv->hhi, HHI_MEM_PD_REG0, 0xff << 8, 0); - - /* Bring out of reset */ - dw_hdmi->data->top_write(dw_hdmi, HDMITX_TOP_SW_RESET, 0); - - /* Enable internal pixclk, tmds_clk, spdif_clk, i2s_clk, cecclk */ - dw_hdmi_top_write_bits(dw_hdmi, HDMITX_TOP_CLK_CNTL, - 0x3, 0x3); - - /* Enable cec_clk and hdcp22_tmdsclk_en */ - dw_hdmi_top_write_bits(dw_hdmi, HDMITX_TOP_CLK_CNTL, - 0x3 << 4, 0x3 << 4); - - /* Enable normal output to PHY */ - dw_hdmi->data->top_write(dw_hdmi, HDMITX_TOP_BIST_CNTL, BIT(12)); - /* TMDS pattern setup */ if (mode->clock > 340000 && !mode_is_420) { dw_hdmi->data->top_write(dw_hdmi, HDMITX_TOP_TMDS_CLK_PTTN_01, @@ -425,20 +409,6 @@ static int dw_hdmi_phy_init(struct dw_hdmi *hdmi, void *data, /* Setup PHY parameters */ meson_hdmi_phy_setup_mode(dw_hdmi, mode, mode_is_420); - /* Setup PHY */ - regmap_update_bits(priv->hhi, HHI_HDMI_PHY_CNTL1, - 0xffff << 16, 0x0390 << 16); - - /* BIT_INVERT */ - if (dw_hdmi_is_compatible(dw_hdmi, "amlogic,meson-gxl-dw-hdmi") || - dw_hdmi_is_compatible(dw_hdmi, "amlogic,meson-gxm-dw-hdmi") || - dw_hdmi_is_compatible(dw_hdmi, "amlogic,meson-g12a-dw-hdmi")) - regmap_update_bits(priv->hhi, HHI_HDMI_PHY_CNTL1, - BIT(17), 0); - else - regmap_update_bits(priv->hhi, HHI_HDMI_PHY_CNTL1, - BIT(17), BIT(17)); - /* Disable clock, fifo, fifo_wr */ regmap_update_bits(priv->hhi, HHI_HDMI_PHY_CNTL1, 0xf, 0); @@ -492,7 +462,9 @@ static void dw_hdmi_phy_disable(struct dw_hdmi *hdmi, DRM_DEBUG_DRIVER("\n"); - regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL0, 0); + /* Fallback to init mode */ + regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL1, dw_hdmi->data->cntl1_init); + regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL0, dw_hdmi->data->cntl0_init); } static enum drm_connector_status dw_hdmi_read_hpd(struct dw_hdmi *hdmi, @@ -610,11 +582,22 @@ static const struct regmap_config meson_dw_hdmi_regmap_config = { .fast_io = true, }; -static const struct meson_dw_hdmi_data meson_dw_hdmi_gx_data = { +static const struct meson_dw_hdmi_data meson_dw_hdmi_gxbb_data = { .top_read = dw_hdmi_top_read, .top_write = dw_hdmi_top_write, .dwc_read = dw_hdmi_dwc_read, .dwc_write = dw_hdmi_dwc_write, + .cntl0_init = 0x0, + .cntl1_init = PHY_CNTL1_INIT | PHY_INVERT, +}; + +static const struct meson_dw_hdmi_data meson_dw_hdmi_gxl_data = { + .top_read = dw_hdmi_top_read, + .top_write = dw_hdmi_top_write, + .dwc_read = dw_hdmi_dwc_read, + .dwc_write = dw_hdmi_dwc_write, + .cntl0_init = 0x0, + .cntl1_init = PHY_CNTL1_INIT, }; static const struct meson_dw_hdmi_data meson_dw_hdmi_g12a_data = { @@ -622,6 +605,8 @@ static const struct meson_dw_hdmi_data meson_dw_hdmi_g12a_data = { .top_write = dw_hdmi_g12a_top_write, .dwc_read = dw_hdmi_g12a_dwc_read, .dwc_write = dw_hdmi_g12a_dwc_write, + .cntl0_init = 0x000b4242, /* Bandgap */ + .cntl1_init = PHY_CNTL1_INIT, }; static void meson_dw_hdmi_init(struct meson_dw_hdmi *meson_dw_hdmi) @@ -656,6 +641,13 @@ static void meson_dw_hdmi_init(struct meson_dw_hdmi *meson_dw_hdmi) meson_dw_hdmi->data->top_write(meson_dw_hdmi, HDMITX_TOP_CLK_CNTL, 0xff); + /* Enable normal output to PHY */ + meson_dw_hdmi->data->top_write(meson_dw_hdmi, HDMITX_TOP_BIST_CNTL, BIT(12)); + + /* Setup PHY */ + regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL1, meson_dw_hdmi->data->cntl1_init); + regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL0, meson_dw_hdmi->data->cntl0_init); + /* Enable HDMI-TX Interrupt */ meson_dw_hdmi->data->top_write(meson_dw_hdmi, HDMITX_TOP_INTR_STAT_CLR, HDMITX_TOP_INTR_CORE); @@ -865,11 +857,11 @@ static const struct dev_pm_ops meson_dw_hdmi_pm_ops = { static const struct of_device_id meson_dw_hdmi_of_table[] = { { .compatible = "amlogic,meson-gxbb-dw-hdmi", - .data = &meson_dw_hdmi_gx_data }, + .data = &meson_dw_hdmi_gxbb_data }, { .compatible = "amlogic,meson-gxl-dw-hdmi", - .data = &meson_dw_hdmi_gx_data }, + .data = &meson_dw_hdmi_gxl_data }, { .compatible = "amlogic,meson-gxm-dw-hdmi", - .data = &meson_dw_hdmi_gx_data }, + .data = &meson_dw_hdmi_gxl_data }, { .compatible = "amlogic,meson-g12a-dw-hdmi", .data = &meson_dw_hdmi_g12a_data }, { } diff --git a/drivers/gpu/drm/meson/meson_dw_mipi_dsi.c b/drivers/gpu/drm/meson/meson_dw_mipi_dsi.c index e5fe4e994f43b1..72abe2057ec31e 100644 --- a/drivers/gpu/drm/meson/meson_dw_mipi_dsi.c +++ b/drivers/gpu/drm/meson/meson_dw_mipi_dsi.c @@ -95,6 +95,7 @@ static int dw_mipi_dsi_phy_init(void *priv_data) return ret; } + clk_disable_unprepare(mipi_dsi->px_clk); ret = clk_set_rate(mipi_dsi->px_clk, mipi_dsi->mode->clock * 1000); if (ret) { @@ -103,6 +104,12 @@ static int dw_mipi_dsi_phy_init(void *priv_data) return ret; } + ret = clk_prepare_enable(mipi_dsi->px_clk); + if (ret) { + dev_err(mipi_dsi->dev, "Failed to enable DSI Pixel clock (ret %d)\n", ret); + return ret; + } + switch (mipi_dsi->dsi_device->format) { case MIPI_DSI_FMT_RGB888: dpi_data_format = DPI_COLOR_24BIT; diff --git a/drivers/gpu/drm/meson/meson_encoder_cvbs.c b/drivers/gpu/drm/meson/meson_encoder_cvbs.c index 3f73b211fa8e3e..3407450435e205 100644 --- a/drivers/gpu/drm/meson/meson_encoder_cvbs.c +++ b/drivers/gpu/drm/meson/meson_encoder_cvbs.c @@ -294,6 +294,5 @@ void meson_encoder_cvbs_remove(struct meson_drm *priv) if (priv->encoders[MESON_ENC_CVBS]) { meson_encoder_cvbs = priv->encoders[MESON_ENC_CVBS]; drm_bridge_remove(&meson_encoder_cvbs->bridge); - drm_bridge_remove(meson_encoder_cvbs->next_bridge); } } diff --git a/drivers/gpu/drm/meson/meson_encoder_dsi.c b/drivers/gpu/drm/meson/meson_encoder_dsi.c index 3f93c70488cad1..311b91630fbe53 100644 --- a/drivers/gpu/drm/meson/meson_encoder_dsi.c +++ b/drivers/gpu/drm/meson/meson_encoder_dsi.c @@ -168,6 +168,5 @@ void meson_encoder_dsi_remove(struct meson_drm *priv) if (priv->encoders[MESON_ENC_DSI]) { meson_encoder_dsi = priv->encoders[MESON_ENC_DSI]; drm_bridge_remove(&meson_encoder_dsi->bridge); - drm_bridge_remove(meson_encoder_dsi->next_bridge); } } diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c index 25ea765586908f..c4686568c9ca5d 100644 --- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c +++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c @@ -474,6 +474,5 @@ void meson_encoder_hdmi_remove(struct meson_drm *priv) if (priv->encoders[MESON_ENC_HDMI]) { meson_encoder_hdmi = priv->encoders[MESON_ENC_HDMI]; drm_bridge_remove(&meson_encoder_hdmi->bridge); - drm_bridge_remove(meson_encoder_hdmi->next_bridge); } } diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c index 815dfe30492b6c..b43ac61201f312 100644 --- a/drivers/gpu/drm/meson/meson_plane.c +++ b/drivers/gpu/drm/meson/meson_plane.c @@ -534,6 +534,7 @@ int meson_plane_create(struct meson_drm *priv) struct meson_plane *meson_plane; struct drm_plane *plane; const uint64_t *format_modifiers = format_modifiers_default; + int ret; meson_plane = devm_kzalloc(priv->drm->dev, sizeof(*meson_plane), GFP_KERNEL); @@ -548,12 +549,16 @@ int meson_plane_create(struct meson_drm *priv) else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) format_modifiers = format_modifiers_afbc_g12a; - drm_universal_plane_init(priv->drm, plane, 0xFF, - &meson_plane_funcs, - supported_drm_formats, - ARRAY_SIZE(supported_drm_formats), - format_modifiers, - DRM_PLANE_TYPE_PRIMARY, "meson_primary_plane"); + ret = drm_universal_plane_init(priv->drm, plane, 0xFF, + &meson_plane_funcs, + supported_drm_formats, + ARRAY_SIZE(supported_drm_formats), + format_modifiers, + DRM_PLANE_TYPE_PRIMARY, "meson_primary_plane"); + if (ret) { + devm_kfree(priv->drm->dev, meson_plane); + return ret; + } drm_plane_helper_add(plane, &meson_plane_helper_funcs); diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c index 2a82119eb58ed8..2a942dc6a6dc23 100644 --- a/drivers/gpu/drm/meson/meson_vclk.c +++ b/drivers/gpu/drm/meson/meson_vclk.c @@ -790,13 +790,13 @@ meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq, FREQ_1000_1001(params[i].pixel_freq)); DRM_DEBUG_DRIVER("i = %d phy_freq = %d alt = %d\n", i, params[i].phy_freq, - FREQ_1000_1001(params[i].phy_freq/10)*10); + FREQ_1000_1001(params[i].phy_freq/1000)*1000); /* Match strict frequency */ if (phy_freq == params[i].phy_freq && vclk_freq == params[i].vclk_freq) return MODE_OK; /* Match 1000/1001 variant */ - if (phy_freq == (FREQ_1000_1001(params[i].phy_freq/10)*10) && + if (phy_freq == (FREQ_1000_1001(params[i].phy_freq/1000)*1000) && vclk_freq == FREQ_1000_1001(params[i].vclk_freq)) return MODE_OK; } @@ -1070,7 +1070,7 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target, for (freq = 0 ; params[freq].pixel_freq ; ++freq) { if ((phy_freq == params[freq].phy_freq || - phy_freq == FREQ_1000_1001(params[freq].phy_freq/10)*10) && + phy_freq == FREQ_1000_1001(params[freq].phy_freq/1000)*1000) && (vclk_freq == params[freq].vclk_freq || vclk_freq == FREQ_1000_1001(params[freq].vclk_freq))) { if (vclk_freq != params[freq].vclk_freq) diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c index abddf37f0ea119..2fb18b782b0536 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.c +++ b/drivers/gpu/drm/mgag200/mgag200_drv.c @@ -10,6 +10,7 @@ #include #include +#include #include #include #include @@ -278,6 +279,12 @@ static void mgag200_pci_remove(struct pci_dev *pdev) struct drm_device *dev = pci_get_drvdata(pdev); drm_dev_unregister(dev); + drm_atomic_helper_shutdown(dev); +} + +static void mgag200_pci_shutdown(struct pci_dev *pdev) +{ + drm_atomic_helper_shutdown(pci_get_drvdata(pdev)); } static struct pci_driver mgag200_pci_driver = { @@ -285,6 +292,7 @@ static struct pci_driver mgag200_pci_driver = { .id_table = mgag200_pciidlist, .probe = mgag200_pci_probe, .remove = mgag200_pci_remove, + .shutdown = mgag200_pci_shutdown, }; drm_module_pci_driver_if_modeset(mgag200_pci_driver, mgag200_modeset); diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h index 57c7edcab6029a..765e49fd891112 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.h +++ b/drivers/gpu/drm/mgag200/mgag200_drv.h @@ -392,6 +392,11 @@ void mgag200_primary_plane_helper_atomic_disable(struct drm_plane *plane, .destroy = drm_plane_cleanup, \ DRM_GEM_SHADOW_PLANE_FUNCS +void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, const struct drm_format_info *format); +void mgag200_crtc_set_gamma(struct mga_device *mdev, + const struct drm_format_info *format, + struct drm_color_lut *lut); + enum drm_mode_status mgag200_crtc_helper_mode_valid(struct drm_crtc *crtc, const struct drm_display_mode *mode); int mgag200_crtc_helper_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *new_state); diff --git a/drivers/gpu/drm/mgag200/mgag200_g200er.c b/drivers/gpu/drm/mgag200/mgag200_g200er.c index bce267e0f7de3c..8d4538b7104776 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200er.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200er.c @@ -202,6 +202,11 @@ static void mgag200_g200er_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200er_reset_tagfifo(mdev); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_g200ev.c b/drivers/gpu/drm/mgag200/mgag200_g200ev.c index ac957f42abe182..56e6f986bff311 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200ev.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200ev.c @@ -203,6 +203,11 @@ static void mgag200_g200ev_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200ev_set_hiprilvl(mdev); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_g200se.c b/drivers/gpu/drm/mgag200/mgag200_g200se.c index bd6e573c9a1a31..ff2b3c6622e7aa 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200se.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200se.c @@ -334,6 +334,11 @@ static void mgag200_g200se_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200se_set_hiprilvl(mdev, adjusted_mode, format); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_i2c.c b/drivers/gpu/drm/mgag200/mgag200_i2c.c index 0c48bdf3e7f800..f5c5d06d0d4bb7 100644 --- a/drivers/gpu/drm/mgag200/mgag200_i2c.c +++ b/drivers/gpu/drm/mgag200/mgag200_i2c.c @@ -31,6 +31,8 @@ #include #include +#include + #include "mgag200_drv.h" static int mga_i2c_read_gpio(struct mga_device *mdev) @@ -86,7 +88,7 @@ static int mga_gpio_getscl(void *data) return (mga_i2c_read_gpio(mdev) & i2c->clock) ? 1 : 0; } -static void mgag200_i2c_release(void *res) +static void mgag200_i2c_release(struct drm_device *dev, void *res) { struct mga_i2c_chan *i2c = res; @@ -115,7 +117,7 @@ int mgag200_i2c_init(struct mga_device *mdev, struct mga_i2c_chan *i2c) i2c->adapter.algo_data = &i2c->bit; i2c->bit.udelay = 10; - i2c->bit.timeout = 2; + i2c->bit.timeout = usecs_to_jiffies(2200); i2c->bit.data = i2c; i2c->bit.setsda = mga_gpio_setsda; i2c->bit.setscl = mga_gpio_setscl; @@ -126,5 +128,5 @@ int mgag200_i2c_init(struct mga_device *mdev, struct mga_i2c_chan *i2c) if (ret) return ret; - return devm_add_action_or_reset(dev->dev, mgag200_i2c_release, i2c); + return drmm_add_action_or_reset(dev, mgag200_i2c_release, i2c); } diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index af3ce5a6a636ac..0f0d59938c3a07 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -28,8 +28,8 @@ * This file contains setup code for the CRTC. */ -static void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, - const struct drm_format_info *format) +void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, + const struct drm_format_info *format) { int i; @@ -65,9 +65,9 @@ static void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, } } -static void mgag200_crtc_set_gamma(struct mga_device *mdev, - const struct drm_format_info *format, - struct drm_color_lut *lut) +void mgag200_crtc_set_gamma(struct mga_device *mdev, + const struct drm_format_info *format, + struct drm_color_lut *lut) { int i; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index e5916c10679679..8c2758a18a19cf 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -65,6 +65,8 @@ void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring, static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit) { + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); struct msm_ringbuffer *ring = submit->ring; struct drm_gem_object *obj; uint32_t *ptr, dwords; @@ -109,6 +111,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit } } + a5xx_gpu->last_seqno[ring->id] = submit->seqno; a5xx_flush(gpu, ring, true); a5xx_preempt_trigger(gpu); @@ -150,9 +153,13 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); OUT_RING(ring, 1); - /* Enable local preemption for finegrain preemption */ + /* + * Disable local preemption by default because it requires + * user-space to be aware of it and provide additional handling + * to restore rendering state or do various flushes on switch. + */ OUT_PKT7(ring, CP_PREEMPT_ENABLE_LOCAL, 1); - OUT_RING(ring, 0x1); + OUT_RING(ring, 0x0); /* Allow CP_CONTEXT_SWITCH_YIELD packets in the IB2 */ OUT_PKT7(ring, CP_YIELD_ENABLE, 1); @@ -206,6 +213,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) /* Write the fence to the scratch register */ OUT_PKT4(ring, REG_A5XX_CP_SCRATCH_REG(2), 1); OUT_RING(ring, submit->seqno); + a5xx_gpu->last_seqno[ring->id] = submit->seqno; /* * Execute a CACHE_FLUSH_TS event. This will ensure that the diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h index c7187bcc5e9082..9c0d701fe4b85b 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h @@ -34,8 +34,10 @@ struct a5xx_gpu { struct drm_gem_object *preempt_counters_bo[MSM_GPU_MAX_RINGS]; struct a5xx_preempt_record *preempt[MSM_GPU_MAX_RINGS]; uint64_t preempt_iova[MSM_GPU_MAX_RINGS]; + uint32_t last_seqno[MSM_GPU_MAX_RINGS]; atomic_t preempt_state; + spinlock_t preempt_start_lock; struct timer_list preempt_timer; struct drm_gem_object *shadow_bo; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index f58dd564d122ba..0469fea5501083 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -55,6 +55,8 @@ static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) /* Return the highest priority ringbuffer with something in it */ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu) { + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); unsigned long flags; int i; @@ -64,6 +66,8 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu) spin_lock_irqsave(&ring->preempt_lock, flags); empty = (get_wptr(ring) == gpu->funcs->get_rptr(gpu, ring)); + if (!empty && ring == a5xx_gpu->cur_ring) + empty = ring->memptrs->fence == a5xx_gpu->last_seqno[i]; spin_unlock_irqrestore(&ring->preempt_lock, flags); if (!empty) @@ -97,12 +101,19 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu) if (gpu->nr_rings == 1) return; + /* + * Serialize preemption start to ensure that we always make + * decision on latest state. Otherwise we can get stuck in + * lower priority or empty ring. + */ + spin_lock_irqsave(&a5xx_gpu->preempt_start_lock, flags); + /* * Try to start preemption by moving from NONE to START. If * unsuccessful, a preemption is already in flight */ if (!try_preempt_state(a5xx_gpu, PREEMPT_NONE, PREEMPT_START)) - return; + goto out; /* Get the next ring to preempt to */ ring = get_next_ring(gpu); @@ -127,9 +138,11 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu) set_preempt_state(a5xx_gpu, PREEMPT_ABORT); update_wptr(gpu, a5xx_gpu->cur_ring); set_preempt_state(a5xx_gpu, PREEMPT_NONE); - return; + goto out; } + spin_unlock_irqrestore(&a5xx_gpu->preempt_start_lock, flags); + /* Make sure the wptr doesn't update while we're in motion */ spin_lock_irqsave(&ring->preempt_lock, flags); a5xx_gpu->preempt[ring->id]->wptr = get_wptr(ring); @@ -152,6 +165,10 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu) /* And actually start the preemption */ gpu_write(gpu, REG_A5XX_CP_CONTEXT_SWITCH_CNTL, 1); + return; + +out: + spin_unlock_irqrestore(&a5xx_gpu->preempt_start_lock, flags); } void a5xx_preempt_irq(struct msm_gpu *gpu) @@ -188,6 +205,12 @@ void a5xx_preempt_irq(struct msm_gpu *gpu) update_wptr(gpu, a5xx_gpu->cur_ring); set_preempt_state(a5xx_gpu, PREEMPT_NONE); + + /* + * Try to trigger preemption again in case there was a submit or + * retire during ring switch + */ + a5xx_preempt_trigger(gpu); } void a5xx_preempt_hw_init(struct msm_gpu *gpu) @@ -204,6 +227,8 @@ void a5xx_preempt_hw_init(struct msm_gpu *gpu) return; for (i = 0; i < gpu->nr_rings; i++) { + a5xx_gpu->preempt[i]->data = 0; + a5xx_gpu->preempt[i]->info = 0; a5xx_gpu->preempt[i]->wptr = 0; a5xx_gpu->preempt[i]->rptr = 0; a5xx_gpu->preempt[i]->rbase = gpu->rb[i]->iova; @@ -298,5 +323,6 @@ void a5xx_preempt_init(struct msm_gpu *gpu) } } + spin_lock_init(&a5xx_gpu->preempt_start_lock); timer_setup(&a5xx_gpu->preempt_timer, a5xx_preempt_timer, 0); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index d4e85e24002fb7..3664c1476a83ad 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -2237,7 +2237,7 @@ static int a6xx_set_supported_hw(struct device *dev, const struct adreno_info *i DRM_DEV_ERROR(dev, "missing support for speed-bin: %u. Some OPPs may not be supported by hardware\n", speedbin); - return UINT_MAX; + supp_hw = BIT(0); /* Default */ } ret = devm_pm_opp_set_supported_hw(dev, &supp_hw, 1); @@ -2343,7 +2343,8 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) ret = a6xx_set_supported_hw(&pdev->dev, config->info); if (ret) { - a6xx_destroy(&(a6xx_gpu->base.base)); + a6xx_llc_slices_destroy(a6xx_gpu); + kfree(a6xx_gpu); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 575e7c56219ff1..b7b527e21dac8a 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -331,7 +331,7 @@ static const struct adreno_info gpulist[] = { ), }, { .machine = "qcom,sm6375", - .chip_ids = ADRENO_CHIP_IDS(0x06010900), + .chip_ids = ADRENO_CHIP_IDS(0x06010901), .family = ADRENO_6XX_GEN1, .revn = 619, .fw = { @@ -462,7 +462,7 @@ static const struct adreno_info gpulist[] = { { 190, 1 }, ), }, { - .chip_ids = ADRENO_CHIP_IDS(0x06080000), + .chip_ids = ADRENO_CHIP_IDS(0x06080001), .family = ADRENO_6XX_GEN2, .revn = 680, .fw = { diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 8090dde0328082..a2df8bd7aa940f 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -99,7 +99,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname, * was a bad idea, and is only provided for backwards * compatibility for older targets. */ - return -ENODEV; + return -ENOENT; } if (IS_ERR(fw)) { @@ -468,7 +468,7 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname) ret = request_firmware_direct(&fw, fwname, drm->dev); if (!ret) { DRM_DEV_INFO(drm->dev, "loaded %s from legacy location\n", - newname); + fwname); adreno_gpu->fwloc = FW_LOCATION_LEGACY; goto out; } else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) { @@ -1071,6 +1071,7 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, adreno_gpu->chip_id = config->chip_id; gpu->allow_relocs = config->info->family < ADRENO_6XX_GEN1; + gpu->pdev = pdev; /* Only handle the core clock when GMU is not in use (or is absent). */ if (adreno_has_gmu_wrapper(adreno_gpu) || diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h index 99acaf917e4304..f0c3804f425879 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h @@ -77,7 +77,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = { .name = "sspp_0", .id = SSPP_VIG0, .base = 0x4000, .len = 0x1f0, .features = VIG_SDM845_MASK, - .sblk = &sdm845_vig_sblk_0, + .sblk = &sm8150_vig_sblk_0, .xin_id = 0, .type = SSPP_TYPE_VIG, .clk_ctrl = DPU_CLK_CTRL_VIG0, @@ -85,7 +85,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = { .name = "sspp_1", .id = SSPP_VIG1, .base = 0x6000, .len = 0x1f0, .features = VIG_SDM845_MASK, - .sblk = &sdm845_vig_sblk_1, + .sblk = &sm8150_vig_sblk_1, .xin_id = 4, .type = SSPP_TYPE_VIG, .clk_ctrl = DPU_CLK_CTRL_VIG1, @@ -93,7 +93,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = { .name = "sspp_2", .id = SSPP_VIG2, .base = 0x8000, .len = 0x1f0, .features = VIG_SDM845_MASK, - .sblk = &sdm845_vig_sblk_2, + .sblk = &sm8150_vig_sblk_2, .xin_id = 8, .type = SSPP_TYPE_VIG, .clk_ctrl = DPU_CLK_CTRL_VIG2, @@ -101,7 +101,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = { .name = "sspp_3", .id = SSPP_VIG3, .base = 0xa000, .len = 0x1f0, .features = VIG_SDM845_MASK, - .sblk = &sdm845_vig_sblk_3, + .sblk = &sm8150_vig_sblk_3, .xin_id = 12, .type = SSPP_TYPE_VIG, .clk_ctrl = DPU_CLK_CTRL_VIG3, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h index f3de21025ca734..47de71e71e3108 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h @@ -76,7 +76,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = { .name = "sspp_0", .id = SSPP_VIG0, .base = 0x4000, .len = 0x1f0, .features = VIG_SDM845_MASK, - .sblk = &sdm845_vig_sblk_0, + .sblk = &sm8150_vig_sblk_0, .xin_id = 0, .type = SSPP_TYPE_VIG, .clk_ctrl = DPU_CLK_CTRL_VIG0, @@ -84,7 +84,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = { .name = "sspp_1", .id = SSPP_VIG1, .base = 0x6000, .len = 0x1f0, .features = VIG_SDM845_MASK, - .sblk = &sdm845_vig_sblk_1, + .sblk = &sm8150_vig_sblk_1, .xin_id = 4, .type = SSPP_TYPE_VIG, .clk_ctrl = DPU_CLK_CTRL_VIG1, @@ -92,7 +92,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = { .name = "sspp_2", .id = SSPP_VIG2, .base = 0x8000, .len = 0x1f0, .features = VIG_SDM845_MASK, - .sblk = &sdm845_vig_sblk_2, + .sblk = &sm8150_vig_sblk_2, .xin_id = 8, .type = SSPP_TYPE_VIG, .clk_ctrl = DPU_CLK_CTRL_VIG2, @@ -100,7 +100,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = { .name = "sspp_3", .id = SSPP_VIG3, .base = 0xa000, .len = 0x1f0, .features = VIG_SDM845_MASK, - .sblk = &sdm845_vig_sblk_3, + .sblk = &sm8150_vig_sblk_3, .xin_id = 12, .type = SSPP_TYPE_VIG, .clk_ctrl = DPU_CLK_CTRL_VIG3, @@ -377,6 +377,7 @@ static const struct dpu_perf_cfg sc8180x_perf_data = { .min_llcc_ib = 800000, .min_dram_ib = 800000, .danger_lut_tbl = {0xf, 0xffff, 0x0}, + .safe_lut_tbl = {0xfff0, 0xf000, 0xffff}, .qos_lut_tbl = { {.nentry = ARRAY_SIZE(sc7180_qos_linear), .entries = sc7180_qos_linear diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h index 5f9b437b82a689..ee781037ada93e 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h @@ -32,7 +32,7 @@ static const struct dpu_mdp_cfg sm8250_mdp = { [DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2bc, .bit_off = 8 }, [DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2c4, .bit_off = 8 }, [DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2bc, .bit_off = 20 }, - [DPU_CLK_CTRL_WB2] = { .reg_off = 0x3b8, .bit_off = 24 }, + [DPU_CLK_CTRL_WB2] = { .reg_off = 0x2bc, .bit_off = 16 }, }, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h index d030c08636b4c3..69d3f7e5e095b0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h @@ -25,7 +25,7 @@ static const struct dpu_mdp_cfg sc7180_mdp = { [DPU_CLK_CTRL_DMA0] = { .reg_off = 0x2ac, .bit_off = 8 }, [DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2b4, .bit_off = 8 }, [DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2c4, .bit_off = 8 }, - [DPU_CLK_CTRL_WB2] = { .reg_off = 0x3b8, .bit_off = 24 }, + [DPU_CLK_CTRL_WB2] = { .reg_off = 0x2bc, .bit_off = 16 }, }, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h index f8d16f9bf528d8..428bcbcfbf1925 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h @@ -31,6 +31,7 @@ static const struct dpu_mdp_cfg sm8350_mdp = { [DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2b4, .bit_off = 8 }, [DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2bc, .bit_off = 8 }, [DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2c4, .bit_off = 8 }, + [DPU_CLK_CTRL_WB2] = { .reg_off = 0x2bc, .bit_off = 16 }, [DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2bc, .bit_off = 20 }, }, }; @@ -304,6 +305,21 @@ static const struct dpu_dsc_cfg sm8350_dsc[] = { }, }; +static const struct dpu_wb_cfg sm8350_wb[] = { + { + .name = "wb_2", .id = WB_2, + .base = 0x65000, .len = 0x2c8, + .features = WB_SM8250_MASK, + .format_list = wb2_formats, + .num_formats = ARRAY_SIZE(wb2_formats), + .clk_ctrl = DPU_CLK_CTRL_WB2, + .xin_id = 6, + .vbif_idx = VBIF_RT, + .maxlinewidth = 4096, + .intr_wb_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 4), + }, +}; + static const struct dpu_intf_cfg sm8350_intf[] = { { .name = "intf_0", .id = INTF_0, @@ -401,6 +417,8 @@ const struct dpu_mdss_cfg dpu_sm8350_cfg = { .dsc = sm8350_dsc, .merge_3d_count = ARRAY_SIZE(sm8350_merge_3d), .merge_3d = sm8350_merge_3d, + .wb_count = ARRAY_SIZE(sm8350_wb), + .wb = sm8350_wb, .intf_count = ARRAY_SIZE(sm8350_intf), .intf = sm8350_intf, .vbif_count = ARRAY_SIZE(sdm845_vbif), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h index 3b5061c4402a67..9195cb996f444b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h @@ -25,7 +25,7 @@ static const struct dpu_mdp_cfg sc7280_mdp = { [DPU_CLK_CTRL_DMA0] = { .reg_off = 0x2ac, .bit_off = 8 }, [DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2b4, .bit_off = 8 }, [DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2c4, .bit_off = 8 }, - [DPU_CLK_CTRL_WB2] = { .reg_off = 0x3b8, .bit_off = 24 }, + [DPU_CLK_CTRL_WB2] = { .reg_off = 0x2bc, .bit_off = 16 }, }, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index 58f5e25679b153..ff9adb8000acdb 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -419,6 +419,7 @@ static const struct dpu_perf_cfg sc8280xp_perf_data = { .min_llcc_ib = 0, .min_dram_ib = 800000, .danger_lut_tbl = {0xf, 0xffff, 0x0}, + .safe_lut_tbl = {0xfe00, 0xfe00, 0xffff}, .qos_lut_tbl = { {.nentry = ARRAY_SIZE(sc8180x_qos_linear), .entries = sc8180x_qos_linear diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index 1b12178dfbcab7..72a1726371cae2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -32,6 +32,7 @@ static const struct dpu_mdp_cfg sm8450_mdp = { [DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2b4, .bit_off = 8 }, [DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2bc, .bit_off = 8 }, [DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2c4, .bit_off = 8 }, + [DPU_CLK_CTRL_WB2] = { .reg_off = 0x2bc, .bit_off = 16 }, [DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2bc, .bit_off = 20 }, }, }; @@ -76,7 +77,7 @@ static const struct dpu_sspp_cfg sm8450_sspp[] = { .name = "sspp_0", .id = SSPP_VIG0, .base = 0x4000, .len = 0x32c, .features = VIG_SC7180_MASK, - .sblk = &sm8250_vig_sblk_0, + .sblk = &sm8450_vig_sblk_0, .xin_id = 0, .type = SSPP_TYPE_VIG, .clk_ctrl = DPU_CLK_CTRL_VIG0, @@ -84,7 +85,7 @@ static const struct dpu_sspp_cfg sm8450_sspp[] = { .name = "sspp_1", .id = SSPP_VIG1, .base = 0x6000, .len = 0x32c, .features = VIG_SC7180_MASK, - .sblk = &sm8250_vig_sblk_1, + .sblk = &sm8450_vig_sblk_1, .xin_id = 4, .type = SSPP_TYPE_VIG, .clk_ctrl = DPU_CLK_CTRL_VIG1, @@ -92,7 +93,7 @@ static const struct dpu_sspp_cfg sm8450_sspp[] = { .name = "sspp_2", .id = SSPP_VIG2, .base = 0x8000, .len = 0x32c, .features = VIG_SC7180_MASK, - .sblk = &sm8250_vig_sblk_2, + .sblk = &sm8450_vig_sblk_2, .xin_id = 8, .type = SSPP_TYPE_VIG, .clk_ctrl = DPU_CLK_CTRL_VIG2, @@ -100,7 +101,7 @@ static const struct dpu_sspp_cfg sm8450_sspp[] = { .name = "sspp_3", .id = SSPP_VIG3, .base = 0xa000, .len = 0x32c, .features = VIG_SC7180_MASK, - .sblk = &sm8250_vig_sblk_3, + .sblk = &sm8450_vig_sblk_3, .xin_id = 12, .type = SSPP_TYPE_VIG, .clk_ctrl = DPU_CLK_CTRL_VIG3, @@ -326,6 +327,21 @@ static const struct dpu_dsc_cfg sm8450_dsc[] = { }, }; +static const struct dpu_wb_cfg sm8450_wb[] = { + { + .name = "wb_2", .id = WB_2, + .base = 0x65000, .len = 0x2c8, + .features = WB_SM8250_MASK, + .format_list = wb2_formats, + .num_formats = ARRAY_SIZE(wb2_formats), + .clk_ctrl = DPU_CLK_CTRL_WB2, + .xin_id = 6, + .vbif_idx = VBIF_RT, + .maxlinewidth = 4096, + .intr_wb_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 4), + }, +}; + static const struct dpu_intf_cfg sm8450_intf[] = { { .name = "intf_0", .id = INTF_0, @@ -423,6 +439,8 @@ const struct dpu_mdss_cfg dpu_sm8450_cfg = { .dsc = sm8450_dsc, .merge_3d_count = ARRAY_SIZE(sm8450_merge_3d), .merge_3d = sm8450_merge_3d, + .wb_count = ARRAY_SIZE(sm8450_wb), + .wb = sm8450_wb, .intf_count = ARRAY_SIZE(sm8450_intf), .intf = sm8450_intf, .vbif_count = ARRAY_SIZE(sdm845_vbif), diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h index b5b6e7031fb9e9..ba06312cbb163e 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h @@ -53,7 +53,7 @@ u32 dpu_core_irq_read( int dpu_core_irq_register_callback( struct dpu_kms *dpu_kms, int irq_idx, - void (*irq_cb)(void *arg, int irq_idx), + void (*irq_cb)(void *arg), void *irq_arg); /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c index ef871239adb2a3..68fae048a9a837 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c @@ -459,15 +459,15 @@ int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent) &perf->core_clk_rate); debugfs_create_u32("enable_bw_release", 0600, entry, (u32 *)&perf->enable_bw_release); - debugfs_create_u32("threshold_low", 0600, entry, + debugfs_create_u32("threshold_low", 0400, entry, (u32 *)&perf->perf_cfg->max_bw_low); - debugfs_create_u32("threshold_high", 0600, entry, + debugfs_create_u32("threshold_high", 0400, entry, (u32 *)&perf->perf_cfg->max_bw_high); - debugfs_create_u32("min_core_ib", 0600, entry, + debugfs_create_u32("min_core_ib", 0400, entry, (u32 *)&perf->perf_cfg->min_core_ib); - debugfs_create_u32("min_llcc_ib", 0600, entry, + debugfs_create_u32("min_llcc_ib", 0400, entry, (u32 *)&perf->perf_cfg->min_llcc_ib); - debugfs_create_u32("min_dram_ib", 0600, entry, + debugfs_create_u32("min_dram_ib", 0400, entry, (u32 *)&perf->perf_cfg->min_dram_ib); debugfs_create_file("perf_mode", 0600, entry, (u32 *)perf, &dpu_core_perf_mode_fops); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index 8ce7586e2ddf74..e238e4e8116caf 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2014-2021 The Linux Foundation. All rights reserved. * Copyright (C) 2013 Red Hat * Author: Rob Clark @@ -125,7 +125,7 @@ static void dpu_crtc_setup_lm_misr(struct dpu_crtc_state *crtc_state) continue; /* Calculate MISR over 1 frame */ - m->hw_lm->ops.setup_misr(m->hw_lm, true, 1); + m->hw_lm->ops.setup_misr(m->hw_lm); } } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index d34e684a417890..6262ec5e40204c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2013 Red Hat * Copyright (c) 2014-2018, 2020-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * * Author: Rob Clark */ @@ -39,6 +39,9 @@ #define DPU_ERROR_ENC(e, fmt, ...) DPU_ERROR("enc%d " fmt,\ (e) ? (e)->base.base.id : -1, ##__VA_ARGS__) +#define DPU_ERROR_ENC_RATELIMITED(e, fmt, ...) DPU_ERROR_RATELIMITED("enc%d " fmt,\ + (e) ? (e)->base.base.id : -1, ##__VA_ARGS__) + /* * Two to anticipate panels that can do cmd/vid dynamic switching * plan is to create all possible physical encoder types, and switch between @@ -121,6 +124,8 @@ enum dpu_enc_rc_states { * @base: drm_encoder base class for registration with DRM * @enc_spinlock: Virtual-Encoder-Wide Spin Lock for IRQ purposes * @enabled: True if the encoder is active, protected by enc_lock + * @commit_done_timedout: True if there has been a timeout on commit after + * enabling the encoder. * @num_phys_encs: Actual number of physical encoders contained. * @phys_encs: Container of physical encoders managed. * @cur_master: Pointer to the current master in this mode. Optimization @@ -169,6 +174,7 @@ struct dpu_encoder_virt { spinlock_t enc_spinlock; bool enabled; + bool commit_done_timedout; unsigned int num_phys_encs; struct dpu_encoder_phys *phys_encs[MAX_PHYS_ENCODERS_PER_VIRTUAL]; @@ -223,6 +229,13 @@ bool dpu_encoder_is_widebus_enabled(const struct drm_encoder *drm_enc) return dpu_enc->wide_bus_en; } +bool dpu_encoder_is_dsc_enabled(const struct drm_encoder *drm_enc) +{ + const struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); + + return dpu_enc->dsc ? true : false; +} + int dpu_encoder_get_crc_values_cnt(const struct drm_encoder *drm_enc) { struct dpu_encoder_virt *dpu_enc; @@ -255,7 +268,7 @@ void dpu_encoder_setup_misr(const struct drm_encoder *drm_enc) if (!phys->hw_intf || !phys->hw_intf->ops.setup_misr) continue; - phys->hw_intf->ops.setup_misr(phys->hw_intf, true, 1); + phys->hw_intf->ops.setup_misr(phys->hw_intf); } } @@ -347,8 +360,8 @@ static int dpu_encoder_helper_wait_event_timeout(int32_t drm_id, u32 irq_idx, struct dpu_encoder_wait_info *info); int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc, - int irq, - void (*func)(void *arg, int irq_idx), + int irq_idx, + void (*func)(void *arg), struct dpu_encoder_wait_info *wait_info) { u32 irq_status; @@ -362,54 +375,54 @@ int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc, /* return EWOULDBLOCK since we know the wait isn't necessary */ if (phys_enc->enable_state == DPU_ENC_DISABLED) { - DRM_ERROR("encoder is disabled id=%u, callback=%ps, irq=%d\n", + DRM_ERROR("encoder is disabled id=%u, callback=%ps, IRQ=[%d, %d]\n", DRMID(phys_enc->parent), func, - irq); + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); return -EWOULDBLOCK; } - if (irq < 0) { + if (irq_idx < 0) { DRM_DEBUG_KMS("skip irq wait id=%u, callback=%ps\n", DRMID(phys_enc->parent), func); return 0; } - DRM_DEBUG_KMS("id=%u, callback=%ps, irq=%d, pp=%d, pending_cnt=%d\n", + DRM_DEBUG_KMS("id=%u, callback=%ps, IRQ=[%d, %d], pp=%d, pending_cnt=%d\n", DRMID(phys_enc->parent), func, - irq, phys_enc->hw_pp->idx - PINGPONG_0, + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), phys_enc->hw_pp->idx - PINGPONG_0, atomic_read(wait_info->atomic_cnt)); ret = dpu_encoder_helper_wait_event_timeout( DRMID(phys_enc->parent), - irq, + irq_idx, wait_info); if (ret <= 0) { - irq_status = dpu_core_irq_read(phys_enc->dpu_kms, irq); + irq_status = dpu_core_irq_read(phys_enc->dpu_kms, irq_idx); if (irq_status) { unsigned long flags; - DRM_DEBUG_KMS("irq not triggered id=%u, callback=%ps, irq=%d, pp=%d, atomic_cnt=%d\n", + DRM_DEBUG_KMS("IRQ=[%d, %d] not triggered id=%u, callback=%ps, pp=%d, atomic_cnt=%d\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), DRMID(phys_enc->parent), func, - irq, phys_enc->hw_pp->idx - PINGPONG_0, atomic_read(wait_info->atomic_cnt)); local_irq_save(flags); - func(phys_enc, irq); + func(phys_enc); local_irq_restore(flags); ret = 0; } else { ret = -ETIMEDOUT; - DRM_DEBUG_KMS("irq timeout id=%u, callback=%ps, irq=%d, pp=%d, atomic_cnt=%d\n", + DRM_DEBUG_KMS("IRQ=[%d, %d] timeout id=%u, callback=%ps, pp=%d, atomic_cnt=%d\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), DRMID(phys_enc->parent), func, - irq, phys_enc->hw_pp->idx - PINGPONG_0, atomic_read(wait_info->atomic_cnt)); } } else { ret = 0; trace_dpu_enc_irq_wait_success(DRMID(phys_enc->parent), - func, irq, + func, irq_idx, phys_enc->hw_pp->idx - PINGPONG_0, atomic_read(wait_info->atomic_cnt)); } @@ -1106,8 +1119,6 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, cstate->num_mixers = num_lm; - dpu_enc->connector = conn_state->connector; - for (i = 0; i < dpu_enc->num_phys_encs; i++) { struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; @@ -1200,6 +1211,11 @@ static void dpu_encoder_virt_atomic_enable(struct drm_encoder *drm_enc, dpu_enc->dsc = dpu_encoder_get_dsc_config(drm_enc); mutex_lock(&dpu_enc->enc_lock); + + dpu_enc->commit_done_timedout = false; + + dpu_enc->connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc); + cur_mode = &dpu_enc->base.crtc->state->adjusted_mode; trace_dpu_enc_enable(DRMID(drm_enc), cur_mode->hdisplay, @@ -1255,7 +1271,7 @@ static void dpu_encoder_virt_atomic_disable(struct drm_encoder *drm_enc, trace_dpu_enc_disable(DRMID(drm_enc)); /* wait for idle */ - dpu_encoder_wait_for_event(drm_enc, MSM_ENC_TX_COMPLETE); + dpu_encoder_wait_for_tx_complete(drm_enc); dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_PRE_STOP); @@ -1662,8 +1678,7 @@ void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *drm_enc) phys = dpu_enc->phys_encs[i]; ctl = phys->hw_ctl; - if (ctl->ops.clear_pending_flush) - ctl->ops.clear_pending_flush(ctl); + ctl->ops.clear_pending_flush(ctl); /* update only for command mode primary ctl */ if ((phys == dpu_enc->cur_master) && @@ -1845,7 +1860,9 @@ static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, dsc_common_mode = 0; pic_width = dsc->pic_width; - dsc_common_mode = DSC_MODE_MULTIPLEX | DSC_MODE_SPLIT_PANEL; + dsc_common_mode = DSC_MODE_SPLIT_PANEL; + if (dpu_encoder_use_dsc_merge(enc_master->parent)) + dsc_common_mode |= DSC_MODE_MULTIPLEX; if (enc_master->intf_mode == INTF_MODE_VIDEO) dsc_common_mode |= DSC_MODE_VIDEO; @@ -2060,7 +2077,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) } /* reset the merge 3D HW block */ - if (phys_enc->hw_pp->merge_3d) { + if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) { phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d, BLEND_3D_NONE); if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d) @@ -2082,7 +2099,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) if (phys_enc->hw_wb) intf_cfg.wb = phys_enc->hw_wb->idx; - if (phys_enc->hw_pp->merge_3d) + if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx; if (ctl->ops.reset_intf_cfg) @@ -2161,6 +2178,7 @@ static void dpu_encoder_early_unregister(struct drm_encoder *encoder) } static int dpu_encoder_virt_add_phys_encs( + struct drm_device *dev, struct msm_display_info *disp_info, struct dpu_encoder_virt *dpu_enc, struct dpu_enc_phys_init_params *params) @@ -2182,7 +2200,7 @@ static int dpu_encoder_virt_add_phys_encs( if (disp_info->intf_type == INTF_WB) { - enc = dpu_encoder_phys_wb_init(params); + enc = dpu_encoder_phys_wb_init(dev, params); if (IS_ERR(enc)) { DPU_ERROR_ENC(dpu_enc, "failed to init wb enc: %ld\n", @@ -2193,7 +2211,7 @@ static int dpu_encoder_virt_add_phys_encs( dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc; ++dpu_enc->num_phys_encs; } else if (disp_info->is_cmd_mode) { - enc = dpu_encoder_phys_cmd_init(params); + enc = dpu_encoder_phys_cmd_init(dev, params); if (IS_ERR(enc)) { DPU_ERROR_ENC(dpu_enc, "failed to init cmd enc: %ld\n", @@ -2204,7 +2222,7 @@ static int dpu_encoder_virt_add_phys_encs( dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc; ++dpu_enc->num_phys_encs; } else { - enc = dpu_encoder_phys_vid_init(params); + enc = dpu_encoder_phys_vid_init(dev, params); if (IS_ERR(enc)) { DPU_ERROR_ENC(dpu_enc, "failed to init vid enc: %ld\n", @@ -2293,7 +2311,7 @@ static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc, break; } - ret = dpu_encoder_virt_add_phys_encs(disp_info, + ret = dpu_encoder_virt_add_phys_encs(dpu_kms->dev, disp_info, dpu_enc, &phys_params); if (ret) { DPU_ERROR_ENC(dpu_enc, "failed to add phys encs\n"); @@ -2327,7 +2345,7 @@ static void dpu_encoder_frame_done_timeout(struct timer_list *t) return; } - DPU_ERROR_ENC(dpu_enc, "frame done timeout\n"); + DPU_ERROR_ENC_RATELIMITED(dpu_enc, "frame done timeout\n"); event = DPU_ENCODER_FRAME_EVENT_ERROR; trace_dpu_enc_frame_done_timeout(DRMID(drm_enc), event); @@ -2405,10 +2423,18 @@ struct drm_encoder *dpu_encoder_init(struct drm_device *dev, return ERR_PTR(ret); } -int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc, - enum msm_event_wait event) +/** + * dpu_encoder_wait_for_commit_done() - Wait for encoder to flush pending state + * @drm_enc: encoder pointer + * + * Wait for hardware to have flushed the current pending changes to hardware at + * a vblank or CTL_START. Physical encoders will map this differently depending + * on the type: vid mode -> vsync_irq, cmd mode -> CTL_START. + * + * Return: 0 on success, -EWOULDBLOCK if already signaled, error otherwise + */ +int dpu_encoder_wait_for_commit_done(struct drm_encoder *drm_enc) { - int (*fn_wait)(struct dpu_encoder_phys *phys_enc) = NULL; struct dpu_encoder_virt *dpu_enc = NULL; int i, ret = 0; @@ -2422,26 +2448,51 @@ int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc, for (i = 0; i < dpu_enc->num_phys_encs; i++) { struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; - switch (event) { - case MSM_ENC_COMMIT_DONE: - fn_wait = phys->ops.wait_for_commit_done; - break; - case MSM_ENC_TX_COMPLETE: - fn_wait = phys->ops.wait_for_tx_complete; - break; - case MSM_ENC_VBLANK: - fn_wait = phys->ops.wait_for_vblank; - break; - default: - DPU_ERROR_ENC(dpu_enc, "unknown wait event %d\n", - event); - return -EINVAL; + if (phys->ops.wait_for_commit_done) { + DPU_ATRACE_BEGIN("wait_for_commit_done"); + ret = phys->ops.wait_for_commit_done(phys); + DPU_ATRACE_END("wait_for_commit_done"); + if (ret == -ETIMEDOUT && !dpu_enc->commit_done_timedout) { + dpu_enc->commit_done_timedout = true; + msm_disp_snapshot_state(drm_enc->dev); + } + if (ret) + return ret; } + } + + return ret; +} + +/** + * dpu_encoder_wait_for_tx_complete() - Wait for encoder to transfer pixels to panel + * @drm_enc: encoder pointer + * + * Wait for the hardware to transfer all the pixels to the panel. Physical + * encoders will map this differently depending on the type: vid mode -> vsync_irq, + * cmd mode -> pp_done. + * + * Return: 0 on success, -EWOULDBLOCK if already signaled, error otherwise + */ +int dpu_encoder_wait_for_tx_complete(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc = NULL; + int i, ret = 0; + + if (!drm_enc) { + DPU_ERROR("invalid encoder\n"); + return -EINVAL; + } + dpu_enc = to_dpu_encoder_virt(drm_enc); + DPU_DEBUG_ENC(dpu_enc, "\n"); + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; - if (fn_wait) { - DPU_ATRACE_BEGIN("wait_for_completion_event"); - ret = fn_wait(phys); - DPU_ATRACE_END("wait_for_completion_event"); + if (phys->ops.wait_for_tx_complete) { + DPU_ATRACE_BEGIN("wait_for_tx_complete"); + ret = phys->ops.wait_for_tx_complete(phys); + DPU_ATRACE_END("wait_for_tx_complete"); if (ret) return ret; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h index 4c05fd5e9ed18d..0c928d1876e4ae 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h @@ -93,25 +93,9 @@ void dpu_encoder_kickoff(struct drm_encoder *encoder); */ int dpu_encoder_vsync_time(struct drm_encoder *drm_enc, ktime_t *wakeup_time); -/** - * dpu_encoder_wait_for_event - Waits for encoder events - * @encoder: encoder pointer - * @event: event to wait for - * MSM_ENC_COMMIT_DONE - Wait for hardware to have flushed the current pending - * frames to hardware at a vblank or ctl_start - * Encoders will map this differently depending on the - * panel type. - * vid mode -> vsync_irq - * cmd mode -> ctl_start - * MSM_ENC_TX_COMPLETE - Wait for the hardware to transfer all the pixels to - * the panel. Encoders will map this differently - * depending on the panel type. - * vid mode -> vsync_irq - * cmd mode -> pp_done - * Returns: 0 on success, -EWOULDBLOCK if already signaled, error otherwise - */ -int dpu_encoder_wait_for_event(struct drm_encoder *drm_encoder, - enum msm_event_wait event); +int dpu_encoder_wait_for_commit_done(struct drm_encoder *drm_encoder); + +int dpu_encoder_wait_for_tx_complete(struct drm_encoder *drm_encoder); /* * dpu_encoder_get_intf_mode - get interface mode of the given encoder @@ -158,6 +142,13 @@ int dpu_encoder_get_vsync_count(struct drm_encoder *drm_enc); bool dpu_encoder_is_widebus_enabled(const struct drm_encoder *drm_enc); +/** + * dpu_encoder_is_dsc_enabled - indicate whether dsc is enabled + * for the encoder. + * @drm_enc: Pointer to previously created drm encoder structure + */ +bool dpu_encoder_is_dsc_enabled(const struct drm_encoder *drm_enc); + /** * dpu_encoder_get_crc_values_cnt - get number of physical encoders contained * in virtual encoder that can collect CRC values diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h index d48558ede488d5..57a3598f2a303c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h @@ -106,7 +106,6 @@ struct dpu_encoder_phys_ops { int (*control_vblank_irq)(struct dpu_encoder_phys *enc, bool enable); int (*wait_for_commit_done)(struct dpu_encoder_phys *phys_enc); int (*wait_for_tx_complete)(struct dpu_encoder_phys *phys_enc); - int (*wait_for_vblank)(struct dpu_encoder_phys *phys_enc); void (*prepare_for_kickoff)(struct dpu_encoder_phys *phys_enc); void (*handle_post_kickoff)(struct dpu_encoder_phys *phys_enc); void (*trigger_start)(struct dpu_encoder_phys *phys_enc); @@ -281,22 +280,24 @@ struct dpu_encoder_wait_info { * @p: Pointer to init params structure * Return: Error code or newly allocated encoder */ -struct dpu_encoder_phys *dpu_encoder_phys_vid_init( +struct dpu_encoder_phys *dpu_encoder_phys_vid_init(struct drm_device *dev, struct dpu_enc_phys_init_params *p); /** * dpu_encoder_phys_cmd_init - Construct a new command mode physical encoder + * @dev: Corresponding device for devres management * @p: Pointer to init params structure * Return: Error code or newly allocated encoder */ -struct dpu_encoder_phys *dpu_encoder_phys_cmd_init( +struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(struct drm_device *dev, struct dpu_enc_phys_init_params *p); /** * dpu_encoder_phys_wb_init - initialize writeback encoder + * @dev: Corresponding device for devres management * @init: Pointer to init info structure with initialization params */ -struct dpu_encoder_phys *dpu_encoder_phys_wb_init( +struct dpu_encoder_phys *dpu_encoder_phys_wb_init(struct drm_device *dev, struct dpu_enc_phys_init_params *p); /** @@ -365,7 +366,7 @@ void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc, */ int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc, int irq, - void (*func)(void *arg, int irq_idx), + void (*func)(void *arg), struct dpu_encoder_wait_info *wait_info); /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c index df88358e7037bf..83a804ebf8d7ef 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c @@ -13,6 +13,8 @@ #include "dpu_trace.h" #include "disp/msm_disp_snapshot.h" +#include + #define DPU_DEBUG_CMDENC(e, fmt, ...) DPU_DEBUG("enc%d intf%d " fmt, \ (e) && (e)->base.parent ? \ (e)->base.parent->base.id : -1, \ @@ -76,7 +78,7 @@ static void _dpu_encoder_phys_cmd_update_intf_cfg( phys_enc->hw_intf->ops.program_intf_cmd_cfg(phys_enc->hw_intf, &cmd_mode_cfg); } -static void dpu_encoder_phys_cmd_pp_tx_done_irq(void *arg, int irq_idx) +static void dpu_encoder_phys_cmd_pp_tx_done_irq(void *arg) { struct dpu_encoder_phys *phys_enc = arg; unsigned long lock_flags; @@ -103,7 +105,7 @@ static void dpu_encoder_phys_cmd_pp_tx_done_irq(void *arg, int irq_idx) DPU_ATRACE_END("pp_done_irq"); } -static void dpu_encoder_phys_cmd_te_rd_ptr_irq(void *arg, int irq_idx) +static void dpu_encoder_phys_cmd_te_rd_ptr_irq(void *arg) { struct dpu_encoder_phys *phys_enc = arg; struct dpu_encoder_phys_cmd *cmd_enc; @@ -126,7 +128,7 @@ static void dpu_encoder_phys_cmd_te_rd_ptr_irq(void *arg, int irq_idx) DPU_ATRACE_END("rd_ptr_irq"); } -static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg, int irq_idx) +static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg) { struct dpu_encoder_phys *phys_enc = arg; @@ -139,7 +141,7 @@ static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg, int irq_idx) DPU_ATRACE_END("ctl_start_irq"); } -static void dpu_encoder_phys_cmd_underrun_irq(void *arg, int irq_idx) +static void dpu_encoder_phys_cmd_underrun_irq(void *arg) { struct dpu_encoder_phys *phys_enc = arg; @@ -449,9 +451,6 @@ static void dpu_encoder_phys_cmd_enable_helper( _dpu_encoder_phys_cmd_pingpong_config(phys_enc); - if (!dpu_encoder_phys_cmd_is_master(phys_enc)) - return; - ctl = phys_enc->hw_ctl; ctl->ops.update_pending_flush_intf(ctl, phys_enc->hw_intf->idx); } @@ -567,14 +566,6 @@ static void dpu_encoder_phys_cmd_disable(struct dpu_encoder_phys *phys_enc) phys_enc->enable_state = DPU_ENC_DISABLED; } -static void dpu_encoder_phys_cmd_destroy(struct dpu_encoder_phys *phys_enc) -{ - struct dpu_encoder_phys_cmd *cmd_enc = - to_dpu_encoder_phys_cmd(phys_enc); - - kfree(cmd_enc); -} - static void dpu_encoder_phys_cmd_prepare_for_kickoff( struct dpu_encoder_phys *phys_enc) { @@ -690,33 +681,6 @@ static int dpu_encoder_phys_cmd_wait_for_commit_done( return _dpu_encoder_phys_cmd_wait_for_ctl_start(phys_enc); } -static int dpu_encoder_phys_cmd_wait_for_vblank( - struct dpu_encoder_phys *phys_enc) -{ - int rc = 0; - struct dpu_encoder_phys_cmd *cmd_enc; - struct dpu_encoder_wait_info wait_info; - - cmd_enc = to_dpu_encoder_phys_cmd(phys_enc); - - /* only required for master controller */ - if (!dpu_encoder_phys_cmd_is_master(phys_enc)) - return rc; - - wait_info.wq = &cmd_enc->pending_vblank_wq; - wait_info.atomic_cnt = &cmd_enc->pending_vblank_cnt; - wait_info.timeout_ms = KICKOFF_TIMEOUT_MS; - - atomic_inc(&cmd_enc->pending_vblank_cnt); - - rc = dpu_encoder_helper_wait_for_irq(phys_enc, - phys_enc->irq[INTR_IDX_RDPTR], - dpu_encoder_phys_cmd_te_rd_ptr_irq, - &wait_info); - - return rc; -} - static void dpu_encoder_phys_cmd_handle_post_kickoff( struct dpu_encoder_phys *phys_enc) { @@ -740,12 +704,10 @@ static void dpu_encoder_phys_cmd_init_ops( ops->atomic_mode_set = dpu_encoder_phys_cmd_atomic_mode_set; ops->enable = dpu_encoder_phys_cmd_enable; ops->disable = dpu_encoder_phys_cmd_disable; - ops->destroy = dpu_encoder_phys_cmd_destroy; ops->control_vblank_irq = dpu_encoder_phys_cmd_control_vblank_irq; ops->wait_for_commit_done = dpu_encoder_phys_cmd_wait_for_commit_done; ops->prepare_for_kickoff = dpu_encoder_phys_cmd_prepare_for_kickoff; ops->wait_for_tx_complete = dpu_encoder_phys_cmd_wait_for_tx_complete; - ops->wait_for_vblank = dpu_encoder_phys_cmd_wait_for_vblank; ops->trigger_start = dpu_encoder_phys_cmd_trigger_start; ops->needs_single_flush = dpu_encoder_phys_cmd_needs_single_flush; ops->irq_control = dpu_encoder_phys_cmd_irq_control; @@ -755,7 +717,7 @@ static void dpu_encoder_phys_cmd_init_ops( ops->get_line_count = dpu_encoder_phys_cmd_get_line_count; } -struct dpu_encoder_phys *dpu_encoder_phys_cmd_init( +struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(struct drm_device *dev, struct dpu_enc_phys_init_params *p) { struct dpu_encoder_phys *phys_enc = NULL; @@ -763,7 +725,7 @@ struct dpu_encoder_phys *dpu_encoder_phys_cmd_init( DPU_DEBUG("intf\n"); - cmd_enc = kzalloc(sizeof(*cmd_enc), GFP_KERNEL); + cmd_enc = drmm_kzalloc(dev, sizeof(*cmd_enc), GFP_KERNEL); if (!cmd_enc) { DPU_ERROR("failed to allocate\n"); return ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c index c2189e58de6af2..daaf0e60475380 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -11,6 +11,8 @@ #include "dpu_trace.h" #include "disp/msm_disp_snapshot.h" +#include + #define DPU_DEBUG_VIDENC(e, fmt, ...) DPU_DEBUG("enc%d intf%d " fmt, \ (e) && (e)->parent ? \ (e)->parent->base.id : -1, \ @@ -100,6 +102,7 @@ static void drm_mode_to_intf_timing_params( } timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent); + timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent); /* * for DP, divide the horizonal parameters by 2 when @@ -257,12 +260,14 @@ static void dpu_encoder_phys_vid_setup_timing_engine( mode.htotal >>= 1; mode.hsync_start >>= 1; mode.hsync_end >>= 1; + mode.hskew >>= 1; DPU_DEBUG_VIDENC(phys_enc, - "split_role %d, halve horizontal %d %d %d %d\n", + "split_role %d, halve horizontal %d %d %d %d %d\n", phys_enc->split_role, mode.hdisplay, mode.htotal, - mode.hsync_start, mode.hsync_end); + mode.hsync_start, mode.hsync_end, + mode.hskew); } drm_mode_to_intf_timing_params(phys_enc, &mode, &timing_params); @@ -297,7 +302,7 @@ static void dpu_encoder_phys_vid_setup_timing_engine( programmable_fetch_config(phys_enc, &timing_params); } -static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx) +static void dpu_encoder_phys_vid_vblank_irq(void *arg) { struct dpu_encoder_phys *phys_enc = arg; struct dpu_hw_ctl *hw_ctl; @@ -334,7 +339,7 @@ static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx) DPU_ATRACE_END("vblank_irq"); } -static void dpu_encoder_phys_vid_underrun_irq(void *arg, int irq_idx) +static void dpu_encoder_phys_vid_underrun_irq(void *arg) { struct dpu_encoder_phys *phys_enc = arg; @@ -438,13 +443,7 @@ static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc) phys_enc->enable_state = DPU_ENC_ENABLING; } -static void dpu_encoder_phys_vid_destroy(struct dpu_encoder_phys *phys_enc) -{ - DPU_DEBUG_VIDENC(phys_enc, "\n"); - kfree(phys_enc); -} - -static int dpu_encoder_phys_vid_wait_for_vblank( +static int dpu_encoder_phys_vid_wait_for_tx_complete( struct dpu_encoder_phys *phys_enc) { struct dpu_encoder_wait_info wait_info; @@ -558,7 +557,7 @@ static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc) * scanout buffer) don't latch properly.. */ if (dpu_encoder_phys_vid_is_master(phys_enc)) { - ret = dpu_encoder_phys_vid_wait_for_vblank(phys_enc); + ret = dpu_encoder_phys_vid_wait_for_tx_complete(phys_enc); if (ret) { atomic_set(&phys_enc->pending_kickoff_cnt, 0); DRM_ERROR("wait disable failed: id:%u intf:%d ret:%d\n", @@ -578,7 +577,7 @@ static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc) spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags); dpu_encoder_phys_inc_pending(phys_enc); spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags); - ret = dpu_encoder_phys_vid_wait_for_vblank(phys_enc); + ret = dpu_encoder_phys_vid_wait_for_tx_complete(phys_enc); if (ret) { atomic_set(&phys_enc->pending_kickoff_cnt, 0); DRM_ERROR("wait disable failed: id:%u intf:%d ret:%d\n", @@ -681,11 +680,9 @@ static void dpu_encoder_phys_vid_init_ops(struct dpu_encoder_phys_ops *ops) ops->atomic_mode_set = dpu_encoder_phys_vid_atomic_mode_set; ops->enable = dpu_encoder_phys_vid_enable; ops->disable = dpu_encoder_phys_vid_disable; - ops->destroy = dpu_encoder_phys_vid_destroy; ops->control_vblank_irq = dpu_encoder_phys_vid_control_vblank_irq; ops->wait_for_commit_done = dpu_encoder_phys_vid_wait_for_commit_done; - ops->wait_for_vblank = dpu_encoder_phys_vid_wait_for_vblank; - ops->wait_for_tx_complete = dpu_encoder_phys_vid_wait_for_vblank; + ops->wait_for_tx_complete = dpu_encoder_phys_vid_wait_for_tx_complete; ops->irq_control = dpu_encoder_phys_vid_irq_control; ops->prepare_for_kickoff = dpu_encoder_phys_vid_prepare_for_kickoff; ops->handle_post_kickoff = dpu_encoder_phys_vid_handle_post_kickoff; @@ -694,7 +691,7 @@ static void dpu_encoder_phys_vid_init_ops(struct dpu_encoder_phys_ops *ops) ops->get_frame_count = dpu_encoder_phys_vid_get_frame_count; } -struct dpu_encoder_phys *dpu_encoder_phys_vid_init( +struct dpu_encoder_phys *dpu_encoder_phys_vid_init(struct drm_device *dev, struct dpu_enc_phys_init_params *p) { struct dpu_encoder_phys *phys_enc = NULL; @@ -704,7 +701,7 @@ struct dpu_encoder_phys *dpu_encoder_phys_vid_init( return ERR_PTR(-EINVAL); } - phys_enc = kzalloc(sizeof(*phys_enc), GFP_KERNEL); + phys_enc = drmm_kzalloc(dev, sizeof(*phys_enc), GFP_KERNEL); if (!phys_enc) { DPU_ERROR("failed to create encoder due to memory allocation error\n"); return ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c index 78037a697633b6..0a45c546b03f2b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c @@ -8,6 +8,7 @@ #include #include +#include #include "dpu_encoder_phys.h" #include "dpu_formats.h" @@ -345,7 +346,11 @@ static void dpu_encoder_phys_wb_setup( } -static void _dpu_encoder_phys_wb_frame_done_helper(void *arg) +/** + * dpu_encoder_phys_wb_done_irq - writeback interrupt handler + * @arg: Pointer to writeback encoder + */ +static void dpu_encoder_phys_wb_done_irq(void *arg) { struct dpu_encoder_phys *phys_enc = arg; struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc); @@ -371,16 +376,6 @@ static void _dpu_encoder_phys_wb_frame_done_helper(void *arg) wake_up_all(&phys_enc->pending_kickoff_wq); } -/** - * dpu_encoder_phys_wb_done_irq - writeback interrupt handler - * @arg: Pointer to writeback encoder - * @irq_idx: interrupt index - */ -static void dpu_encoder_phys_wb_done_irq(void *arg, int irq_idx) -{ - _dpu_encoder_phys_wb_frame_done_helper(arg); -} - /** * dpu_encoder_phys_wb_irq_ctrl - irq control of WB * @phys: Pointer to physical encoder @@ -534,8 +529,7 @@ static void dpu_encoder_phys_wb_disable(struct dpu_encoder_phys *phys_enc) } /* reset h/w before final flush */ - if (phys_enc->hw_ctl->ops.clear_pending_flush) - phys_enc->hw_ctl->ops.clear_pending_flush(phys_enc->hw_ctl); + phys_enc->hw_ctl->ops.clear_pending_flush(phys_enc->hw_ctl); /* * New CTL reset sequence from 5.0 MDP onwards. @@ -553,20 +547,6 @@ static void dpu_encoder_phys_wb_disable(struct dpu_encoder_phys *phys_enc) phys_enc->enable_state = DPU_ENC_DISABLED; } -/** - * dpu_encoder_phys_wb_destroy - destroy writeback encoder - * @phys_enc: Pointer to physical encoder - */ -static void dpu_encoder_phys_wb_destroy(struct dpu_encoder_phys *phys_enc) -{ - if (!phys_enc) - return; - - DPU_DEBUG("[wb:%d]\n", phys_enc->hw_wb->idx - WB_0); - - kfree(phys_enc); -} - static void dpu_encoder_phys_wb_prepare_wb_job(struct dpu_encoder_phys *phys_enc, struct drm_writeback_job *job) { @@ -662,7 +642,6 @@ static void dpu_encoder_phys_wb_init_ops(struct dpu_encoder_phys_ops *ops) ops->atomic_mode_set = dpu_encoder_phys_wb_atomic_mode_set; ops->enable = dpu_encoder_phys_wb_enable; ops->disable = dpu_encoder_phys_wb_disable; - ops->destroy = dpu_encoder_phys_wb_destroy; ops->atomic_check = dpu_encoder_phys_wb_atomic_check; ops->wait_for_commit_done = dpu_encoder_phys_wb_wait_for_commit_done; ops->prepare_for_kickoff = dpu_encoder_phys_wb_prepare_for_kickoff; @@ -678,9 +657,10 @@ static void dpu_encoder_phys_wb_init_ops(struct dpu_encoder_phys_ops *ops) /** * dpu_encoder_phys_wb_init - initialize writeback encoder + * @dev: Corresponding device for devres management * @p: Pointer to init info structure with initialization params */ -struct dpu_encoder_phys *dpu_encoder_phys_wb_init( +struct dpu_encoder_phys *dpu_encoder_phys_wb_init(struct drm_device *dev, struct dpu_enc_phys_init_params *p) { struct dpu_encoder_phys *phys_enc = NULL; @@ -693,7 +673,7 @@ struct dpu_encoder_phys *dpu_encoder_phys_wb_init( return ERR_PTR(-EINVAL); } - wb_enc = kzalloc(sizeof(*wb_enc), GFP_KERNEL); + wb_enc = drmm_kzalloc(dev, sizeof(*wb_enc), GFP_KERNEL); if (!wb_enc) { DPU_ERROR("failed to allocate wb phys_enc enc\n"); return ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 713dfc0797181d..77d09f961d8669 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -250,14 +250,17 @@ static const uint32_t wb2_formats[] = { * SSPP sub blocks config *************************************************************/ +#define SSPP_SCALER_VER(maj, min) (((maj) << 16) | (min)) + /* SSPP common configuration */ -#define _VIG_SBLK(sdma_pri, qseed_ver) \ +#define _VIG_SBLK(sdma_pri, qseed_ver, scaler_ver) \ { \ .maxdwnscale = MAX_DOWNSCALE_RATIO, \ .maxupscale = MAX_UPSCALE_RATIO, \ .smart_dma_priority = sdma_pri, \ .scaler_blk = {.name = "scaler", \ .id = qseed_ver, \ + .version = scaler_ver, \ .base = 0xa00, .len = 0xa0,}, \ .csc_blk = {.name = "csc", \ .id = DPU_SSPP_CSC_10BIT, \ @@ -269,13 +272,14 @@ static const uint32_t wb2_formats[] = { .rotation_cfg = NULL, \ } -#define _VIG_SBLK_ROT(sdma_pri, qseed_ver, rot_cfg) \ +#define _VIG_SBLK_ROT(sdma_pri, qseed_ver, scaler_ver, rot_cfg) \ { \ .maxdwnscale = MAX_DOWNSCALE_RATIO, \ .maxupscale = MAX_UPSCALE_RATIO, \ .smart_dma_priority = sdma_pri, \ .scaler_blk = {.name = "scaler", \ .id = qseed_ver, \ + .version = scaler_ver, \ .base = 0xa00, .len = 0xa0,}, \ .csc_blk = {.name = "csc", \ .id = DPU_SSPP_CSC_10BIT, \ @@ -299,13 +303,17 @@ static const uint32_t wb2_formats[] = { } static const struct dpu_sspp_sub_blks msm8998_vig_sblk_0 = - _VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3); + _VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3, + SSPP_SCALER_VER(1, 2)); static const struct dpu_sspp_sub_blks msm8998_vig_sblk_1 = - _VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3); + _VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3, + SSPP_SCALER_VER(1, 2)); static const struct dpu_sspp_sub_blks msm8998_vig_sblk_2 = - _VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3); + _VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3, + SSPP_SCALER_VER(1, 2)); static const struct dpu_sspp_sub_blks msm8998_vig_sblk_3 = - _VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3); + _VIG_SBLK(0, DPU_SSPP_SCALER_QSEED3, + SSPP_SCALER_VER(1, 2)); static const struct dpu_rotation_cfg dpu_rot_sc7280_cfg_v2 = { .rot_maxheight = 1088, @@ -314,13 +322,30 @@ static const struct dpu_rotation_cfg dpu_rot_sc7280_cfg_v2 = { }; static const struct dpu_sspp_sub_blks sdm845_vig_sblk_0 = - _VIG_SBLK(5, DPU_SSPP_SCALER_QSEED3); + _VIG_SBLK(5, DPU_SSPP_SCALER_QSEED3, + SSPP_SCALER_VER(1, 3)); static const struct dpu_sspp_sub_blks sdm845_vig_sblk_1 = - _VIG_SBLK(6, DPU_SSPP_SCALER_QSEED3); + _VIG_SBLK(6, DPU_SSPP_SCALER_QSEED3, + SSPP_SCALER_VER(1, 3)); static const struct dpu_sspp_sub_blks sdm845_vig_sblk_2 = - _VIG_SBLK(7, DPU_SSPP_SCALER_QSEED3); + _VIG_SBLK(7, DPU_SSPP_SCALER_QSEED3, + SSPP_SCALER_VER(1, 3)); static const struct dpu_sspp_sub_blks sdm845_vig_sblk_3 = - _VIG_SBLK(8, DPU_SSPP_SCALER_QSEED3); + _VIG_SBLK(8, DPU_SSPP_SCALER_QSEED3, + SSPP_SCALER_VER(1, 3)); + +static const struct dpu_sspp_sub_blks sm8150_vig_sblk_0 = + _VIG_SBLK(5, DPU_SSPP_SCALER_QSEED3, + SSPP_SCALER_VER(1, 4)); +static const struct dpu_sspp_sub_blks sm8150_vig_sblk_1 = + _VIG_SBLK(6, DPU_SSPP_SCALER_QSEED3, + SSPP_SCALER_VER(1, 4)); +static const struct dpu_sspp_sub_blks sm8150_vig_sblk_2 = + _VIG_SBLK(7, DPU_SSPP_SCALER_QSEED3, + SSPP_SCALER_VER(1, 4)); +static const struct dpu_sspp_sub_blks sm8150_vig_sblk_3 = + _VIG_SBLK(8, DPU_SSPP_SCALER_QSEED3, + SSPP_SCALER_VER(1, 4)); static const struct dpu_sspp_sub_blks sdm845_dma_sblk_0 = _DMA_SBLK(1); static const struct dpu_sspp_sub_blks sdm845_dma_sblk_1 = _DMA_SBLK(2); @@ -328,34 +353,60 @@ static const struct dpu_sspp_sub_blks sdm845_dma_sblk_2 = _DMA_SBLK(3); static const struct dpu_sspp_sub_blks sdm845_dma_sblk_3 = _DMA_SBLK(4); static const struct dpu_sspp_sub_blks sc7180_vig_sblk_0 = - _VIG_SBLK(4, DPU_SSPP_SCALER_QSEED4); + _VIG_SBLK(4, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 0)); static const struct dpu_sspp_sub_blks sc7280_vig_sblk_0 = - _VIG_SBLK_ROT(4, DPU_SSPP_SCALER_QSEED4, &dpu_rot_sc7280_cfg_v2); + _VIG_SBLK_ROT(4, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 0), + &dpu_rot_sc7280_cfg_v2); static const struct dpu_sspp_sub_blks sm6115_vig_sblk_0 = - _VIG_SBLK(2, DPU_SSPP_SCALER_QSEED4); + _VIG_SBLK(2, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 0)); static const struct dpu_sspp_sub_blks sm6125_vig_sblk_0 = - _VIG_SBLK(3, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK(3, DPU_SSPP_SCALER_QSEED3LITE, + SSPP_SCALER_VER(2, 4)); static const struct dpu_sspp_sub_blks sm8250_vig_sblk_0 = - _VIG_SBLK(5, DPU_SSPP_SCALER_QSEED4); + _VIG_SBLK(5, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 0)); static const struct dpu_sspp_sub_blks sm8250_vig_sblk_1 = - _VIG_SBLK(6, DPU_SSPP_SCALER_QSEED4); + _VIG_SBLK(6, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 0)); static const struct dpu_sspp_sub_blks sm8250_vig_sblk_2 = - _VIG_SBLK(7, DPU_SSPP_SCALER_QSEED4); + _VIG_SBLK(7, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 0)); static const struct dpu_sspp_sub_blks sm8250_vig_sblk_3 = - _VIG_SBLK(8, DPU_SSPP_SCALER_QSEED4); + _VIG_SBLK(8, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 0)); + +static const struct dpu_sspp_sub_blks sm8450_vig_sblk_0 = + _VIG_SBLK(5, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 1)); +static const struct dpu_sspp_sub_blks sm8450_vig_sblk_1 = + _VIG_SBLK(6, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 1)); +static const struct dpu_sspp_sub_blks sm8450_vig_sblk_2 = + _VIG_SBLK(7, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 1)); +static const struct dpu_sspp_sub_blks sm8450_vig_sblk_3 = + _VIG_SBLK(8, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 1)); static const struct dpu_sspp_sub_blks sm8550_vig_sblk_0 = - _VIG_SBLK(7, DPU_SSPP_SCALER_QSEED4); + _VIG_SBLK(7, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 2)); static const struct dpu_sspp_sub_blks sm8550_vig_sblk_1 = - _VIG_SBLK(8, DPU_SSPP_SCALER_QSEED4); + _VIG_SBLK(8, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 2)); static const struct dpu_sspp_sub_blks sm8550_vig_sblk_2 = - _VIG_SBLK(9, DPU_SSPP_SCALER_QSEED4); + _VIG_SBLK(9, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 2)); static const struct dpu_sspp_sub_blks sm8550_vig_sblk_3 = - _VIG_SBLK(10, DPU_SSPP_SCALER_QSEED4); + _VIG_SBLK(10, DPU_SSPP_SCALER_QSEED4, + SSPP_SCALER_VER(3, 2)); static const struct dpu_sspp_sub_blks sm8550_dma_sblk_4 = _DMA_SBLK(5); static const struct dpu_sspp_sub_blks sm8550_dma_sblk_5 = _DMA_SBLK(6); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h index 6c9634209e9fc7..3f82d84bd1c907 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -269,7 +269,8 @@ enum { /** * struct dpu_scaler_blk: Scaler information * @info: HW register and features supported by this sub-blk - * @version: qseed block revision + * @version: qseed block revision, on QSEED3+ platforms this is the value of + * scaler_blk.base + QSEED3_HW_VERSION registers. */ struct dpu_scaler_blk { DPU_HW_SUBBLK_INFO; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h index 1c242298ff2ee0..dca87ea78e251c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h @@ -81,7 +81,8 @@ struct dpu_hw_ctl_ops { /** * Clear the value of the cached pending_flush_mask - * No effect on hardware + * No effect on hardware. + * Required to be implemented. * @ctx : ctl path ctx pointer */ void (*clear_pending_flush)(struct dpu_hw_ctl *ctx); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index e3c50439f80a13..c8d7929ce52323 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -197,8 +197,18 @@ static const struct dpu_intr_reg dpu_intr_set_7xxx[] = { }, }; -#define DPU_IRQ_REG(irq_idx) (irq_idx / 32) -#define DPU_IRQ_MASK(irq_idx) (BIT(irq_idx % 32)) +#define DPU_IRQ_MASK(irq_idx) (BIT(DPU_IRQ_BIT(irq_idx))) + +static inline bool dpu_core_irq_is_valid(int irq_idx) +{ + return irq_idx >= 0 && irq_idx < DPU_NUM_IRQS; +} + +static inline struct dpu_hw_intr_entry *dpu_core_irq_get_entry(struct dpu_hw_intr *intr, + int irq_idx) +{ + return &intr->irq_tbl[irq_idx]; +} /** * dpu_core_irq_callback_handler - dispatch core interrupts @@ -207,17 +217,22 @@ static const struct dpu_intr_reg dpu_intr_set_7xxx[] = { */ static void dpu_core_irq_callback_handler(struct dpu_kms *dpu_kms, int irq_idx) { - VERB("irq_idx=%d\n", irq_idx); + struct dpu_hw_intr_entry *irq_entry = dpu_core_irq_get_entry(dpu_kms->hw_intr, irq_idx); - if (!dpu_kms->hw_intr->irq_tbl[irq_idx].cb) - DRM_ERROR("no registered cb, idx:%d\n", irq_idx); + VERB("IRQ=[%d, %d]\n", DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); - atomic_inc(&dpu_kms->hw_intr->irq_tbl[irq_idx].count); + if (!irq_entry->cb) { + DRM_ERROR("no registered cb, IRQ=[%d, %d]\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); + return; + } + + atomic_inc(&irq_entry->count); /* * Perform registered function callback */ - dpu_kms->hw_intr->irq_tbl[irq_idx].cb(dpu_kms->hw_intr->irq_tbl[irq_idx].arg, irq_idx); + irq_entry->cb(irq_entry->arg); } irqreturn_t dpu_core_irq(struct msm_kms *kms) @@ -291,8 +306,9 @@ static int dpu_hw_intr_enable_irq_locked(struct dpu_hw_intr *intr, int irq_idx) if (!intr) return -EINVAL; - if (irq_idx < 0 || irq_idx >= intr->total_irqs) { - pr_err("invalid IRQ index: [%d]\n", irq_idx); + if (!dpu_core_irq_is_valid(irq_idx)) { + pr_err("invalid IRQ=[%d, %d]\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); return -EINVAL; } @@ -328,7 +344,8 @@ static int dpu_hw_intr_enable_irq_locked(struct dpu_hw_intr *intr, int irq_idx) intr->cache_irq_mask[reg_idx] = cache_irq_mask; } - pr_debug("DPU IRQ %d %senabled: MASK:0x%.8lx, CACHE-MASK:0x%.8x\n", irq_idx, dbgstr, + pr_debug("DPU IRQ=[%d, %d] %senabled: MASK:0x%.8lx, CACHE-MASK:0x%.8x\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), dbgstr, DPU_IRQ_MASK(irq_idx), cache_irq_mask); return 0; @@ -344,8 +361,9 @@ static int dpu_hw_intr_disable_irq_locked(struct dpu_hw_intr *intr, int irq_idx) if (!intr) return -EINVAL; - if (irq_idx < 0 || irq_idx >= intr->total_irqs) { - pr_err("invalid IRQ index: [%d]\n", irq_idx); + if (!dpu_core_irq_is_valid(irq_idx)) { + pr_err("invalid IRQ=[%d, %d]\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); return -EINVAL; } @@ -377,7 +395,8 @@ static int dpu_hw_intr_disable_irq_locked(struct dpu_hw_intr *intr, int irq_idx) intr->cache_irq_mask[reg_idx] = cache_irq_mask; } - pr_debug("DPU IRQ %d %sdisabled: MASK:0x%.8lx, CACHE-MASK:0x%.8x\n", irq_idx, dbgstr, + pr_debug("DPU IRQ=[%d, %d] %sdisabled: MASK:0x%.8lx, CACHE-MASK:0x%.8x\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), dbgstr, DPU_IRQ_MASK(irq_idx), cache_irq_mask); return 0; @@ -429,14 +448,8 @@ u32 dpu_core_irq_read(struct dpu_kms *dpu_kms, int irq_idx) if (!intr) return 0; - if (irq_idx < 0) { - DPU_ERROR("[%pS] invalid irq_idx=%d\n", - __builtin_return_address(0), irq_idx); - return 0; - } - - if (irq_idx < 0 || irq_idx >= intr->total_irqs) { - pr_err("invalid IRQ index: [%d]\n", irq_idx); + if (!dpu_core_irq_is_valid(irq_idx)) { + pr_err("invalid IRQ=[%d, %d]\n", DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); return 0; } @@ -462,13 +475,12 @@ struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr, const struct dpu_mdss_cfg *m) { struct dpu_hw_intr *intr; - int nirq = MDP_INTR_MAX * 32; unsigned int i; if (!addr || !m) return ERR_PTR(-EINVAL); - intr = kzalloc(struct_size(intr, irq_tbl, nirq), GFP_KERNEL); + intr = kzalloc(sizeof(*intr), GFP_KERNEL); if (!intr) return ERR_PTR(-ENOMEM); @@ -479,8 +491,6 @@ struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr, intr->hw.blk_addr = addr + m->mdp[0].base; - intr->total_irqs = nirq; - intr->irq_mask = BIT(MDP_SSPP_TOP0_INTR) | BIT(MDP_SSPP_TOP0_INTR2) | BIT(MDP_SSPP_TOP0_HIST_INTR); @@ -507,42 +517,47 @@ void dpu_hw_intr_destroy(struct dpu_hw_intr *intr) } int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int irq_idx, - void (*irq_cb)(void *arg, int irq_idx), + void (*irq_cb)(void *arg), void *irq_arg) { + struct dpu_hw_intr_entry *irq_entry; unsigned long irq_flags; int ret; if (!irq_cb) { - DPU_ERROR("invalid ird_idx:%d irq_cb:%ps\n", irq_idx, irq_cb); + DPU_ERROR("IRQ=[%d, %d] NULL callback\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); return -EINVAL; } - if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->total_irqs) { - DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx); + if (!dpu_core_irq_is_valid(irq_idx)) { + DPU_ERROR("invalid IRQ=[%d, %d] irq_cb:%ps\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), irq_cb); return -EINVAL; } - VERB("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx); + VERB("[%pS] IRQ=[%d, %d]\n", __builtin_return_address(0), + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); spin_lock_irqsave(&dpu_kms->hw_intr->irq_lock, irq_flags); - if (unlikely(WARN_ON(dpu_kms->hw_intr->irq_tbl[irq_idx].cb))) { + irq_entry = dpu_core_irq_get_entry(dpu_kms->hw_intr, irq_idx); + if (unlikely(WARN_ON(irq_entry->cb))) { spin_unlock_irqrestore(&dpu_kms->hw_intr->irq_lock, irq_flags); return -EBUSY; } trace_dpu_core_irq_register_callback(irq_idx, irq_cb); - dpu_kms->hw_intr->irq_tbl[irq_idx].arg = irq_arg; - dpu_kms->hw_intr->irq_tbl[irq_idx].cb = irq_cb; + irq_entry->arg = irq_arg; + irq_entry->cb = irq_cb; ret = dpu_hw_intr_enable_irq_locked( dpu_kms->hw_intr, irq_idx); if (ret) - DPU_ERROR("Fail to enable IRQ for irq_idx:%d\n", - irq_idx); + DPU_ERROR("Failed/ to enable IRQ=[%d, %d]\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); spin_unlock_irqrestore(&dpu_kms->hw_intr->irq_lock, irq_flags); trace_dpu_irq_register_success(irq_idx); @@ -552,26 +567,30 @@ int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int irq_idx, int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx) { + struct dpu_hw_intr_entry *irq_entry; unsigned long irq_flags; int ret; - if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->total_irqs) { - DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx); + if (!dpu_core_irq_is_valid(irq_idx)) { + DPU_ERROR("invalid IRQ=[%d, %d]\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); return -EINVAL; } - VERB("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx); + VERB("[%pS] IRQ=[%d, %d]\n", __builtin_return_address(0), + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); spin_lock_irqsave(&dpu_kms->hw_intr->irq_lock, irq_flags); trace_dpu_core_irq_unregister_callback(irq_idx); ret = dpu_hw_intr_disable_irq_locked(dpu_kms->hw_intr, irq_idx); if (ret) - DPU_ERROR("Fail to disable IRQ for irq_idx:%d: %d\n", - irq_idx, ret); + DPU_ERROR("Failed to disable IRQ=[%d, %d]: %d\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), ret); - dpu_kms->hw_intr->irq_tbl[irq_idx].cb = NULL; - dpu_kms->hw_intr->irq_tbl[irq_idx].arg = NULL; + irq_entry = dpu_core_irq_get_entry(dpu_kms->hw_intr, irq_idx); + irq_entry->cb = NULL; + irq_entry->arg = NULL; spin_unlock_irqrestore(&dpu_kms->hw_intr->irq_lock, irq_flags); @@ -584,18 +603,21 @@ int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx) static int dpu_debugfs_core_irq_show(struct seq_file *s, void *v) { struct dpu_kms *dpu_kms = s->private; + struct dpu_hw_intr_entry *irq_entry; unsigned long irq_flags; int i, irq_count; void *cb; - for (i = 0; i < dpu_kms->hw_intr->total_irqs; i++) { + for (i = 0; i < DPU_NUM_IRQS; i++) { spin_lock_irqsave(&dpu_kms->hw_intr->irq_lock, irq_flags); - irq_count = atomic_read(&dpu_kms->hw_intr->irq_tbl[i].count); - cb = dpu_kms->hw_intr->irq_tbl[i].cb; + irq_entry = dpu_core_irq_get_entry(dpu_kms->hw_intr, i); + irq_count = atomic_read(&irq_entry->count); + cb = irq_entry->cb; spin_unlock_irqrestore(&dpu_kms->hw_intr->irq_lock, irq_flags); if (irq_count || cb) - seq_printf(s, "idx:%d irq:%d cb:%ps\n", i, irq_count, cb); + seq_printf(s, "IRQ=[%d, %d] count:%d cb:%ps\n", + DPU_IRQ_REG(i), DPU_IRQ_BIT(i), irq_count, cb); } return 0; @@ -614,6 +636,7 @@ void dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms, void dpu_core_irq_preinstall(struct msm_kms *kms) { struct dpu_kms *dpu_kms = to_dpu_kms(kms); + struct dpu_hw_intr_entry *irq_entry; int i; pm_runtime_get_sync(&dpu_kms->pdev->dev); @@ -621,22 +644,28 @@ void dpu_core_irq_preinstall(struct msm_kms *kms) dpu_disable_all_irqs(dpu_kms); pm_runtime_put_sync(&dpu_kms->pdev->dev); - for (i = 0; i < dpu_kms->hw_intr->total_irqs; i++) - atomic_set(&dpu_kms->hw_intr->irq_tbl[i].count, 0); + for (i = 0; i < DPU_NUM_IRQS; i++) { + irq_entry = dpu_core_irq_get_entry(dpu_kms->hw_intr, i); + atomic_set(&irq_entry->count, 0); + } } void dpu_core_irq_uninstall(struct msm_kms *kms) { struct dpu_kms *dpu_kms = to_dpu_kms(kms); + struct dpu_hw_intr_entry *irq_entry; int i; if (!dpu_kms->hw_intr) return; pm_runtime_get_sync(&dpu_kms->pdev->dev); - for (i = 0; i < dpu_kms->hw_intr->total_irqs; i++) - if (dpu_kms->hw_intr->irq_tbl[i].cb) - DPU_ERROR("irq_idx=%d still enabled/registered\n", i); + for (i = 0; i < DPU_NUM_IRQS; i++) { + irq_entry = dpu_core_irq_get_entry(dpu_kms->hw_intr, i); + if (irq_entry->cb) + DPU_ERROR("IRQ=[%d, %d] still enabled/registered\n", + DPU_IRQ_REG(i), DPU_IRQ_BIT(i)); + } dpu_clear_irqs(dpu_kms); dpu_disable_all_irqs(dpu_kms); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h index dab761e548636f..9df5d6e737a116 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h @@ -37,6 +37,16 @@ enum dpu_hw_intr_reg { #define MDP_INTFn_INTR(intf) (MDP_INTF0_INTR + (intf - INTF_0)) #define DPU_IRQ_IDX(reg_idx, offset) (reg_idx * 32 + offset) +#define DPU_IRQ_REG(irq_idx) (irq_idx / 32) +#define DPU_IRQ_BIT(irq_idx) (irq_idx % 32) + +#define DPU_NUM_IRQS (MDP_INTR_MAX * 32) + +struct dpu_hw_intr_entry { + void (*cb)(void *arg); + void *arg; + atomic_t count; +}; /** * struct dpu_hw_intr: hw interrupts handling data structure @@ -44,7 +54,6 @@ enum dpu_hw_intr_reg { * @ops: function pointer mapping for IRQ handling * @cache_irq_mask: array of IRQ enable masks reg storage created during init * @save_irq_status: array of IRQ status reg storage created during init - * @total_irqs: total number of irq_idx mapped in the hw_interrupts * @irq_lock: spinlock for accessing IRQ resources * @irq_cb_tbl: array of IRQ callbacks */ @@ -52,16 +61,11 @@ struct dpu_hw_intr { struct dpu_hw_blk_reg_map hw; u32 cache_irq_mask[MDP_INTR_MAX]; u32 *save_irq_status; - u32 total_irqs; spinlock_t irq_lock; unsigned long irq_mask; const struct dpu_intr_reg *intr_set; - struct { - void (*cb)(void *arg, int irq_idx); - void *arg; - atomic_t count; - } irq_tbl[]; + struct dpu_hw_intr_entry irq_tbl[DPU_NUM_IRQS]; }; /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c index 8ec6505d9e7860..9cdd2d8bf79ba1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. */ @@ -161,13 +161,8 @@ static void dpu_hw_intf_setup_timing_engine(struct dpu_hw_intf *ctx, hsync_ctl = (hsync_period << 16) | p->hsync_pulse_width; display_hctl = (hsync_end_x << 16) | hsync_start_x; - /* - * DATA_HCTL_EN controls data timing which can be different from - * video timing. It is recommended to enable it for all cases, except - * if compression is enabled in 1 pixel per clock mode - */ if (p->wide_bus_en) - intf_cfg2 |= INTF_CFG2_DATABUS_WIDEN | INTF_CFG2_DATA_HCTL_EN; + intf_cfg2 |= INTF_CFG2_DATABUS_WIDEN; data_width = p->width; @@ -227,6 +222,14 @@ static void dpu_hw_intf_setup_timing_engine(struct dpu_hw_intf *ctx, DPU_REG_WRITE(c, INTF_CONFIG, intf_cfg); DPU_REG_WRITE(c, INTF_PANEL_FORMAT, panel_format); if (ctx->cap->features & BIT(DPU_DATA_HCTL_EN)) { + /* + * DATA_HCTL_EN controls data timing which can be different from + * video timing. It is recommended to enable it for all cases, except + * if compression is enabled in 1 pixel per clock mode + */ + if (!(p->compression_en && !p->wide_bus_en)) + intf_cfg2 |= INTF_CFG2_DATA_HCTL_EN; + DPU_REG_WRITE(c, INTF_CONFIG2, intf_cfg2); DPU_REG_WRITE(c, INTF_DISPLAY_DATA_HCTL, display_data_hctl); DPU_REG_WRITE(c, INTF_ACTIVE_DATA_HCTL, active_data_hctl); @@ -318,9 +321,9 @@ static u32 dpu_hw_intf_get_line_count(struct dpu_hw_intf *intf) return DPU_REG_READ(c, INTF_LINE_COUNT); } -static void dpu_hw_intf_setup_misr(struct dpu_hw_intf *intf, bool enable, u32 frame_count) +static void dpu_hw_intf_setup_misr(struct dpu_hw_intf *intf) { - dpu_hw_setup_misr(&intf->hw, INTF_MISR_CTRL, enable, frame_count); + dpu_hw_setup_misr(&intf->hw, INTF_MISR_CTRL, 0x1); } static int dpu_hw_intf_collect_misr(struct dpu_hw_intf *intf, u32 *misr_value) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h index 77f80531782b59..192f4e67b1732f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. */ @@ -33,6 +33,7 @@ struct dpu_hw_intf_timing_params { u32 hsync_skew; bool wide_bus_en; + bool compression_en; }; struct dpu_hw_intf_prog_fetch { @@ -94,7 +95,7 @@ struct dpu_hw_intf_ops { void (*bind_pingpong_blk)(struct dpu_hw_intf *intf, const enum dpu_pingpong pp); - void (*setup_misr)(struct dpu_hw_intf *intf, bool enable, u32 frame_count); + void (*setup_misr)(struct dpu_hw_intf *intf); int (*collect_misr)(struct dpu_hw_intf *intf, u32 *misr_value); // Tearcheck on INTF since DPU 5.0.0 diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c index d1c3bd8379ea94..a590c1f7465fbd 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2021, The Linux Foundation. All rights reserved. */ @@ -81,9 +81,9 @@ static void dpu_hw_lm_setup_border_color(struct dpu_hw_mixer *ctx, } } -static void dpu_hw_lm_setup_misr(struct dpu_hw_mixer *ctx, bool enable, u32 frame_count) +static void dpu_hw_lm_setup_misr(struct dpu_hw_mixer *ctx) { - dpu_hw_setup_misr(&ctx->hw, LM_MISR_CTRL, enable, frame_count); + dpu_hw_setup_misr(&ctx->hw, LM_MISR_CTRL, 0x0); } static int dpu_hw_lm_collect_misr(struct dpu_hw_mixer *ctx, u32 *misr_value) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h index 36992d046a533b..98b77cda65472d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2021, The Linux Foundation. All rights reserved. */ @@ -57,7 +58,7 @@ struct dpu_hw_lm_ops { /** * setup_misr: Enable/disable MISR */ - void (*setup_misr)(struct dpu_hw_mixer *ctx, bool enable, u32 frame_count); + void (*setup_misr)(struct dpu_hw_mixer *ctx); /** * collect_misr: Read MISR signature diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c index 9d2273fd2fed58..6eee9f68ab4c7d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. */ #define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ @@ -481,9 +481,11 @@ void _dpu_hw_setup_qos_lut(struct dpu_hw_blk_reg_map *c, u32 offset, cfg->danger_safe_en ? QOS_QOS_CTRL_DANGER_SAFE_EN : 0); } +/* + * note: Aside from encoders, input_sel should be set to 0x0 by default + */ void dpu_hw_setup_misr(struct dpu_hw_blk_reg_map *c, - u32 misr_ctrl_offset, - bool enable, u32 frame_count) + u32 misr_ctrl_offset, u8 input_sel) { u32 config = 0; @@ -492,15 +494,9 @@ void dpu_hw_setup_misr(struct dpu_hw_blk_reg_map *c, /* Clear old MISR value (in case it's read before a new value is calculated)*/ wmb(); - if (enable) { - config = (frame_count & MISR_FRAME_COUNT_MASK) | - MISR_CTRL_ENABLE | MISR_CTRL_FREE_RUN_MASK; - - DPU_REG_WRITE(c, misr_ctrl_offset, config); - } else { - DPU_REG_WRITE(c, misr_ctrl_offset, 0); - } - + config = MISR_FRAME_COUNT | MISR_CTRL_ENABLE | MISR_CTRL_FREE_RUN_MASK | + ((input_sel & 0xF) << 24); + DPU_REG_WRITE(c, misr_ctrl_offset, config); } int dpu_hw_collect_misr(struct dpu_hw_blk_reg_map *c, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h index 1f6079f4707109..0aed54d7f6c942 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2021, The Linux Foundation. All rights reserved. */ @@ -13,7 +13,7 @@ #include "dpu_hw_catalog.h" #define REG_MASK(n) ((BIT(n)) - 1) -#define MISR_FRAME_COUNT_MASK 0xFF +#define MISR_FRAME_COUNT 0x1 #define MISR_CTRL_ENABLE BIT(8) #define MISR_CTRL_STATUS BIT(9) #define MISR_CTRL_STATUS_CLEAR BIT(10) @@ -358,9 +358,7 @@ void _dpu_hw_setup_qos_lut(struct dpu_hw_blk_reg_map *c, u32 offset, const struct dpu_hw_qos_cfg *cfg); void dpu_hw_setup_misr(struct dpu_hw_blk_reg_map *c, - u32 misr_ctrl_offset, - bool enable, - u32 frame_count); + u32 misr_ctrl_offset, u8 input_sel); int dpu_hw_collect_misr(struct dpu_hw_blk_reg_map *c, u32 misr_ctrl_offset, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c index ebc41640038220..0aa598b355e9ec 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c @@ -86,6 +86,9 @@ static void dpu_hw_wb_setup_format(struct dpu_hw_wb *ctx, dst_format |= BIT(14); /* DST_ALPHA_X */ } + if (DPU_FORMAT_IS_YUV(fmt)) + dst_format |= BIT(15); + pattern = (fmt->element[3] << 24) | (fmt->element[2] << 16) | (fmt->element[1] << 8) | diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index aa6ba2cf4b8406..6ba289e04b3b22 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -490,7 +490,7 @@ static void dpu_kms_wait_for_commit_done(struct msm_kms *kms, * mode panels. This may be a no-op for command mode panels. */ trace_dpu_kms_wait_for_commit_done(DRMID(crtc)); - ret = dpu_encoder_wait_for_event(encoder, MSM_ENC_COMMIT_DONE); + ret = dpu_encoder_wait_for_commit_done(encoder); if (ret && ret != -EWOULDBLOCK) { DPU_ERROR("wait for commit done returned %d\n", ret); break; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index b6f53ca6e96285..8cb3cf842c52c0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -31,26 +31,17 @@ * @fmt: Pointer to format string */ #define DPU_DEBUG(fmt, ...) \ - do { \ - if (drm_debug_enabled(DRM_UT_KMS)) \ - DRM_DEBUG(fmt, ##__VA_ARGS__); \ - else \ - pr_debug(fmt, ##__VA_ARGS__); \ - } while (0) + DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__) /** * DPU_DEBUG_DRIVER - macro for hardware driver logging * @fmt: Pointer to format string */ #define DPU_DEBUG_DRIVER(fmt, ...) \ - do { \ - if (drm_debug_enabled(DRM_UT_DRIVER)) \ - DRM_ERROR(fmt, ##__VA_ARGS__); \ - else \ - pr_debug(fmt, ##__VA_ARGS__); \ - } while (0) + DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__) #define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__) +#define DPU_ERROR_RATELIMITED(fmt, ...) pr_err_ratelimited("[dpu error]" fmt, ##__VA_ARGS__) /** * ktime_compare_safe - compare two ktime structures diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 0be195f9149c56..637f50a8d42e62 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -679,6 +679,9 @@ static int dpu_plane_prepare_fb(struct drm_plane *plane, new_state->fb, &layout); if (ret) { DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret); + if (pstate->aspace) + msm_framebuffer_cleanup(new_state->fb, pstate->aspace, + pstate->needs_dirtyfb); return ret; } @@ -792,6 +795,8 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, plane); int ret = 0, min_scale; struct dpu_plane *pdpu = to_dpu_plane(plane); + struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base); + u64 max_mdp_clk_rate = kms->perf.max_core_clk_rate; struct dpu_plane_state *pstate = to_dpu_plane_state(new_plane_state); struct dpu_sw_pipe *pipe = &pstate->pipe; struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; @@ -860,14 +865,20 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, max_linewidth = pdpu->catalog->caps->max_linewidth; - if (drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) { + drm_rect_rotate(&pipe_cfg->src_rect, + new_plane_state->fb->width, new_plane_state->fb->height, + new_plane_state->rotation); + + if ((drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) || + _dpu_plane_calc_clk(&crtc_state->adjusted_mode, pipe_cfg) > max_mdp_clk_rate) { /* * In parallel multirect case only the half of the usual width * is supported for tiled formats. If we are here, we know that * full width is more than max_linewidth, thus each rect is * wider than allowed. */ - if (DPU_FORMAT_IS_UBWC(fmt)) { + if (DPU_FORMAT_IS_UBWC(fmt) && + drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) { DPU_DEBUG_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u, tiled format\n", DRM_RECT_ARG(&pipe_cfg->src_rect), max_linewidth); return -E2BIG; @@ -907,6 +918,14 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, r_pipe_cfg->dst_rect.x1 = pipe_cfg->dst_rect.x2; } + drm_rect_rotate_inv(&pipe_cfg->src_rect, + new_plane_state->fb->width, new_plane_state->fb->height, + new_plane_state->rotation); + if (r_pipe->sspp) + drm_rect_rotate_inv(&r_pipe_cfg->src_rect, + new_plane_state->fb->width, new_plane_state->fb->height, + new_plane_state->rotation); + ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, fmt, &crtc_state->adjusted_mode); if (ret) return ret; diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c index 169f9de4a12a73..3100957225a70f 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c @@ -269,6 +269,7 @@ static void mdp4_crtc_atomic_disable(struct drm_crtc *crtc, { struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc); struct mdp4_kms *mdp4_kms = get_kms(crtc); + unsigned long flags; DBG("%s", mdp4_crtc->name); @@ -281,6 +282,14 @@ static void mdp4_crtc_atomic_disable(struct drm_crtc *crtc, mdp_irq_unregister(&mdp4_kms->base, &mdp4_crtc->err); mdp4_disable(mdp4_kms); + if (crtc->state->event && !crtc->state->active) { + WARN_ON(mdp4_crtc->event); + spin_lock_irqsave(&mdp4_kms->dev->event_lock, flags); + drm_crtc_send_vblank_event(crtc, crtc->state->event); + crtc->state->event = NULL; + spin_unlock_irqrestore(&mdp4_kms->dev->event_lock, flags); + } + mdp4_crtc->enabled = false; } diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c index 56a3063545ec46..12d07e93a4c47e 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c @@ -356,7 +356,7 @@ void mdp5_smp_dump(struct mdp5_smp *smp, struct drm_printer *p) drm_printf(p, "%s:%d\t%d\t%s\n", pipe2name(pipe), j, inuse, - plane ? plane->name : NULL); + plane ? plane->name : "(null)"); total += inuse; } diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c index 8e3b677f35e64f..559809a5cbcfb1 100644 --- a/drivers/gpu/drm/msm/dp/dp_aux.c +++ b/drivers/gpu/drm/msm/dp/dp_aux.c @@ -35,6 +35,7 @@ struct dp_aux_private { bool no_send_stop; bool initted; bool is_edp; + bool enable_xfers; u32 offset; u32 segment; @@ -297,6 +298,17 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux, goto exit; } + /* + * If we're using DP and an external display isn't connected then the + * transfer won't succeed. Return right away. If we don't do this we + * can end up with long timeouts if someone tries to access the DP AUX + * character device when no DP device is connected. + */ + if (!aux->is_edp && !aux->enable_xfers) { + ret = -ENXIO; + goto exit; + } + /* * For eDP it's important to give a reasonably long wait here for HPD * to be asserted. This is because the panel driver may have _just_ @@ -428,6 +440,14 @@ irqreturn_t dp_aux_isr(struct drm_dp_aux *dp_aux) return IRQ_HANDLED; } +void dp_aux_enable_xfers(struct drm_dp_aux *dp_aux, bool enabled) +{ + struct dp_aux_private *aux; + + aux = container_of(dp_aux, struct dp_aux_private, dp_aux); + aux->enable_xfers = enabled; +} + void dp_aux_reconfig(struct drm_dp_aux *dp_aux) { struct dp_aux_private *aux; diff --git a/drivers/gpu/drm/msm/dp/dp_aux.h b/drivers/gpu/drm/msm/dp/dp_aux.h index 511305da4f66df..f3052cb43306bc 100644 --- a/drivers/gpu/drm/msm/dp/dp_aux.h +++ b/drivers/gpu/drm/msm/dp/dp_aux.h @@ -12,6 +12,7 @@ int dp_aux_register(struct drm_dp_aux *dp_aux); void dp_aux_unregister(struct drm_dp_aux *dp_aux); irqreturn_t dp_aux_isr(struct drm_dp_aux *dp_aux); +void dp_aux_enable_xfers(struct drm_dp_aux *dp_aux, bool enabled); void dp_aux_init(struct drm_dp_aux *dp_aux); void dp_aux_deinit(struct drm_dp_aux *dp_aux); void dp_aux_reconfig(struct drm_dp_aux *dp_aux); diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index 77a8d9366ed7b0..7472dfd631b837 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -135,11 +135,6 @@ static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl) tbd = dp_link_get_test_bits_depth(ctrl->link, ctrl->panel->dp_mode.bpp); - if (tbd == DP_TEST_BIT_DEPTH_UNKNOWN) { - pr_debug("BIT_DEPTH not set. Configure default\n"); - tbd = DP_TEST_BIT_DEPTH_8; - } - config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT; /* Num of Lanes */ @@ -1024,14 +1019,14 @@ static int dp_ctrl_update_vx_px(struct dp_ctrl_private *ctrl) if (ret) return ret; - if (voltage_swing_level >= DP_TRAIN_VOLTAGE_SWING_MAX) { + if (voltage_swing_level >= DP_TRAIN_LEVEL_MAX) { drm_dbg_dp(ctrl->drm_dev, "max. voltage swing level reached %d\n", voltage_swing_level); max_level_reached |= DP_TRAIN_MAX_SWING_REACHED; } - if (pre_emphasis_level >= DP_TRAIN_PRE_EMPHASIS_MAX) { + if (pre_emphasis_level >= DP_TRAIN_LEVEL_MAX) { drm_dbg_dp(ctrl->drm_dev, "max. pre-emphasis level reached %d\n", pre_emphasis_level); @@ -1122,7 +1117,7 @@ static int dp_ctrl_link_train_1(struct dp_ctrl_private *ctrl, } if (ctrl->link->phy_params.v_level >= - DP_TRAIN_VOLTAGE_SWING_MAX) { + DP_TRAIN_LEVEL_MAX) { DRM_ERROR_RATELIMITED("max v_level reached\n"); return -EAGAIN; } @@ -1258,6 +1253,8 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl, link_info.rate = ctrl->link->link_params.rate; link_info.capabilities = DP_LINK_CAP_ENHANCED_FRAMING; + dp_link_reset_phy_params_vx_px(ctrl->link); + dp_aux_link_configure(ctrl->aux, &link_info); if (drm_dp_max_downspread(dpcd)) diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 76f13954015b18..ed77c957eceba3 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -171,6 +171,11 @@ static const struct msm_dp_desc sm8350_dp_descs[] = { {} }; +static const struct msm_dp_desc sm8650_dp_descs[] = { + { .io_start = 0x0af54000, .id = MSM_DP_CONTROLLER_0, .connector_type = DRM_MODE_CONNECTOR_DisplayPort }, + {} +}; + static const struct of_device_id dp_dt_match[] = { { .compatible = "qcom,sc7180-dp", .data = &sc7180_dp_descs }, { .compatible = "qcom,sc7280-dp", .data = &sc7280_dp_descs }, @@ -181,6 +186,7 @@ static const struct of_device_id dp_dt_match[] = { { .compatible = "qcom,sc8280xp-edp", .data = &sc8280xp_edp_descs }, { .compatible = "qcom,sdm845-dp", .data = &sc7180_dp_descs }, { .compatible = "qcom,sm8350-dp", .data = &sm8350_dp_descs }, + { .compatible = "qcom,sm8650-dp", .data = &sm8650_dp_descs }, {} }; @@ -580,6 +586,8 @@ static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data) u32 state; int ret; + dp_aux_enable_xfers(dp->aux, true); + mutex_lock(&dp->event_mutex); state = dp->hpd_state; @@ -636,6 +644,8 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data) { u32 state; + dp_aux_enable_xfers(dp->aux, false); + mutex_lock(&dp->event_mutex); state = dp->hpd_state; diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c index 6375daaeb98e1c..a198af7b2d4499 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.c +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -7,6 +7,7 @@ #include +#include "dp_reg.h" #include "dp_link.h" #include "dp_panel.h" @@ -1114,7 +1115,7 @@ int dp_link_process_request(struct dp_link *dp_link) int dp_link_get_colorimetry_config(struct dp_link *dp_link) { - u32 cc; + u32 cc = DP_MISC0_COLORIMERY_CFG_LEGACY_RGB; struct dp_link_private *link; if (!dp_link) { @@ -1128,10 +1129,11 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link) * Unless a video pattern CTS test is ongoing, use RGB_VESA * Only RGB_VESA and RGB_CEA supported for now */ - if (dp_link_is_video_pattern_requested(link)) - cc = link->dp_link.test_video.test_dyn_range; - else - cc = DP_TEST_DYNAMIC_RANGE_VESA; + if (dp_link_is_video_pattern_requested(link)) { + if (link->dp_link.test_video.test_dyn_range & + DP_TEST_DYNAMIC_RANGE_CEA) + cc = DP_MISC0_COLORIMERY_CFG_CEA_RGB; + } return cc; } @@ -1139,6 +1141,7 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link) int dp_link_adjust_levels(struct dp_link *dp_link, u8 *link_status) { int i; + u8 max_p_level; int v_max = 0, p_max = 0; struct dp_link_private *link; @@ -1170,30 +1173,29 @@ int dp_link_adjust_levels(struct dp_link *dp_link, u8 *link_status) * Adjust the voltage swing and pre-emphasis level combination to within * the allowable range. */ - if (dp_link->phy_params.v_level > DP_TRAIN_VOLTAGE_SWING_MAX) { + if (dp_link->phy_params.v_level > DP_TRAIN_LEVEL_MAX) { drm_dbg_dp(link->drm_dev, "Requested vSwingLevel=%d, change to %d\n", dp_link->phy_params.v_level, - DP_TRAIN_VOLTAGE_SWING_MAX); - dp_link->phy_params.v_level = DP_TRAIN_VOLTAGE_SWING_MAX; + DP_TRAIN_LEVEL_MAX); + dp_link->phy_params.v_level = DP_TRAIN_LEVEL_MAX; } - if (dp_link->phy_params.p_level > DP_TRAIN_PRE_EMPHASIS_MAX) { + if (dp_link->phy_params.p_level > DP_TRAIN_LEVEL_MAX) { drm_dbg_dp(link->drm_dev, "Requested preEmphasisLevel=%d, change to %d\n", dp_link->phy_params.p_level, - DP_TRAIN_PRE_EMPHASIS_MAX); - dp_link->phy_params.p_level = DP_TRAIN_PRE_EMPHASIS_MAX; + DP_TRAIN_LEVEL_MAX); + dp_link->phy_params.p_level = DP_TRAIN_LEVEL_MAX; } - if ((dp_link->phy_params.p_level > DP_TRAIN_PRE_EMPHASIS_LVL_1) - && (dp_link->phy_params.v_level == - DP_TRAIN_VOLTAGE_SWING_LVL_2)) { + max_p_level = DP_TRAIN_LEVEL_MAX - dp_link->phy_params.v_level; + if (dp_link->phy_params.p_level > max_p_level) { drm_dbg_dp(link->drm_dev, "Requested preEmphasisLevel=%d, change to %d\n", dp_link->phy_params.p_level, - DP_TRAIN_PRE_EMPHASIS_LVL_1); - dp_link->phy_params.p_level = DP_TRAIN_PRE_EMPHASIS_LVL_1; + max_p_level); + dp_link->phy_params.p_level = max_p_level; } drm_dbg_dp(link->drm_dev, "adjusted: v_level=%d, p_level=%d\n", @@ -1211,6 +1213,9 @@ void dp_link_reset_phy_params_vx_px(struct dp_link *dp_link) u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp) { u32 tbd; + struct dp_link_private *link; + + link = container_of(dp_link, struct dp_link_private, dp_link); /* * Few simplistic rules and assumptions made here: @@ -1228,12 +1233,13 @@ u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp) tbd = DP_TEST_BIT_DEPTH_10; break; default: - tbd = DP_TEST_BIT_DEPTH_UNKNOWN; + drm_dbg_dp(link->drm_dev, "bpp=%d not supported, use bpc=8\n", + bpp); + tbd = DP_TEST_BIT_DEPTH_8; break; } - if (tbd != DP_TEST_BIT_DEPTH_UNKNOWN) - tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT); + tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT); return tbd; } diff --git a/drivers/gpu/drm/msm/dp/dp_link.h b/drivers/gpu/drm/msm/dp/dp_link.h index 9dd4dd92653046..79c3a02b8dacd7 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.h +++ b/drivers/gpu/drm/msm/dp/dp_link.h @@ -19,19 +19,7 @@ struct dp_link_info { unsigned long capabilities; }; -enum dp_link_voltage_level { - DP_TRAIN_VOLTAGE_SWING_LVL_0 = 0, - DP_TRAIN_VOLTAGE_SWING_LVL_1 = 1, - DP_TRAIN_VOLTAGE_SWING_LVL_2 = 2, - DP_TRAIN_VOLTAGE_SWING_MAX = DP_TRAIN_VOLTAGE_SWING_LVL_2, -}; - -enum dp_link_preemaphasis_level { - DP_TRAIN_PRE_EMPHASIS_LVL_0 = 0, - DP_TRAIN_PRE_EMPHASIS_LVL_1 = 1, - DP_TRAIN_PRE_EMPHASIS_LVL_2 = 2, - DP_TRAIN_PRE_EMPHASIS_MAX = DP_TRAIN_PRE_EMPHASIS_LVL_2, -}; +#define DP_TRAIN_LEVEL_MAX 3 struct dp_link_test_video { u32 test_video_pattern; diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index 42d52510ffd4ab..d26589eb8b218b 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -136,22 +136,22 @@ static int dp_panel_read_dpcd(struct dp_panel *dp_panel) static u32 dp_panel_get_supported_bpp(struct dp_panel *dp_panel, u32 mode_edid_bpp, u32 mode_pclk_khz) { - struct dp_link_info *link_info; + const struct dp_link_info *link_info; const u32 max_supported_bpp = 30, min_supported_bpp = 18; - u32 bpp = 0, data_rate_khz = 0; + u32 bpp, data_rate_khz; - bpp = min_t(u32, mode_edid_bpp, max_supported_bpp); + bpp = min(mode_edid_bpp, max_supported_bpp); link_info = &dp_panel->link_info; data_rate_khz = link_info->num_lanes * link_info->rate * 8; - while (bpp > min_supported_bpp) { + do { if (mode_pclk_khz * bpp <= data_rate_khz) - break; + return bpp; bpp -= 6; - } + } while (bpp > min_supported_bpp); - return bpp; + return min_supported_bpp; } static int dp_panel_update_modes(struct drm_connector *connector, @@ -289,26 +289,9 @@ int dp_panel_get_modes(struct dp_panel *dp_panel, static u8 dp_panel_get_edid_checksum(struct edid *edid) { - struct edid *last_block; - u8 *raw_edid; - bool is_edid_corrupt = false; - - if (!edid) { - DRM_ERROR("invalid edid input\n"); - return 0; - } - - raw_edid = (u8 *)edid; - raw_edid += (edid->extensions * EDID_LENGTH); - last_block = (struct edid *)raw_edid; - - /* block type extension */ - drm_edid_block_valid(raw_edid, 1, false, &is_edid_corrupt); - if (!is_edid_corrupt) - return last_block->checksum; + edid += edid->extensions; - DRM_ERROR("Invalid block, no checksum\n"); - return 0; + return edid->checksum; } void dp_panel_handle_sink_request(struct dp_panel *dp_panel) @@ -461,8 +444,9 @@ int dp_panel_init_panel_info(struct dp_panel *dp_panel) drm_mode->clock); drm_dbg_dp(panel->drm_dev, "bpp = %d\n", dp_panel->dp_mode.bpp); - dp_panel->dp_mode.bpp = max_t(u32, 18, - min_t(u32, dp_panel->dp_mode.bpp, 30)); + dp_panel->dp_mode.bpp = dp_panel_get_mode_bpp(dp_panel, dp_panel->dp_mode.bpp, + dp_panel->dp_mode.drm_mode.clock); + drm_dbg_dp(panel->drm_dev, "updated bpp = %d\n", dp_panel->dp_mode.bpp); diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h index ea85a691e72b5c..78785ed4b40c49 100644 --- a/drivers/gpu/drm/msm/dp/dp_reg.h +++ b/drivers/gpu/drm/msm/dp/dp_reg.h @@ -143,6 +143,9 @@ #define DP_MISC0_COLORIMETRY_CFG_SHIFT (0x00000001) #define DP_MISC0_TEST_BITS_DEPTH_SHIFT (0x00000005) +#define DP_MISC0_COLORIMERY_CFG_LEGACY_RGB (0) +#define DP_MISC0_COLORIMERY_CFG_CEA_RGB (0x04) + #define REG_DP_VALID_BOUNDARY (0x00000030) #define REG_DP_VALID_BOUNDARY_2 (0x00000034) diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c index baab79ab6e745e..32f965bacdc309 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.c +++ b/drivers/gpu/drm/msm/dsi/dsi.c @@ -126,6 +126,7 @@ static void dsi_unbind(struct device *dev, struct device *master, struct msm_drm_private *priv = dev_get_drvdata(master); struct msm_dsi *msm_dsi = dev_get_drvdata(dev); + msm_dsi_tx_buf_free(msm_dsi->host); priv->dsi[msm_dsi->id] = NULL; } diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h index bd3763a5d72340..3b46617a59f202 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.h +++ b/drivers/gpu/drm/msm/dsi/dsi.h @@ -125,6 +125,7 @@ int dsi_tx_buf_alloc_v2(struct msm_dsi_host *msm_host, int size); void *dsi_tx_buf_get_6g(struct msm_dsi_host *msm_host); void *dsi_tx_buf_get_v2(struct msm_dsi_host *msm_host); void dsi_tx_buf_put_6g(struct msm_dsi_host *msm_host); +void msm_dsi_tx_buf_free(struct mipi_dsi_host *mipi_host); int dsi_dma_base_get_6g(struct msm_dsi_host *msm_host, uint64_t *iova); int dsi_dma_base_get_v2(struct msm_dsi_host *msm_host, uint64_t *iova); int dsi_clk_init_v2(struct msm_dsi_host *msm_host); diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 3d6fb708dc223e..77b805eacb1b18 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -147,6 +147,7 @@ struct msm_dsi_host { /* DSI 6G TX buffer*/ struct drm_gem_object *tx_gem_obj; + struct msm_gem_address_space *aspace; /* DSI v2 TX buffer */ void *tx_buf; @@ -365,8 +366,8 @@ int dsi_link_clk_set_rate_6g(struct msm_dsi_host *msm_host) { int ret; - DBG("Set clk rates: pclk=%d, byteclk=%lu", - msm_host->mode->clock, msm_host->byte_clk_rate); + DBG("Set clk rates: pclk=%lu, byteclk=%lu", + msm_host->pixel_clk_rate, msm_host->byte_clk_rate); ret = dev_pm_opp_set_rate(&msm_host->pdev->dev, msm_host->byte_clk_rate); @@ -439,9 +440,9 @@ int dsi_link_clk_set_rate_v2(struct msm_dsi_host *msm_host) { int ret; - DBG("Set clk rates: pclk=%d, byteclk=%lu, esc_clk=%lu, dsi_src_clk=%lu", - msm_host->mode->clock, msm_host->byte_clk_rate, - msm_host->esc_clk_rate, msm_host->src_clk_rate); + DBG("Set clk rates: pclk=%lu, byteclk=%lu, esc_clk=%lu, dsi_src_clk=%lu", + msm_host->pixel_clk_rate, msm_host->byte_clk_rate, + msm_host->esc_clk_rate, msm_host->src_clk_rate); ret = clk_set_rate(msm_host->byte_clk, msm_host->byte_clk_rate); if (ret) { @@ -831,6 +832,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod u32 slice_per_intf, total_bytes_per_intf; u32 pkt_per_line; u32 eol_byte_num; + u32 bytes_per_pkt; /* first calculate dsc parameters and then program * compress mode registers @@ -838,6 +840,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod slice_per_intf = msm_dsc_get_slices_per_intf(dsc, hdisplay); total_bytes_per_intf = dsc->slice_chunk_size * slice_per_intf; + bytes_per_pkt = dsc->slice_chunk_size; /* * slice_per_pkt; */ eol_byte_num = total_bytes_per_intf % 3; @@ -875,6 +878,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod dsi_write(msm_host, REG_DSI_COMMAND_COMPRESSION_MODE_CTRL, reg_ctrl); dsi_write(msm_host, REG_DSI_COMMAND_COMPRESSION_MODE_CTRL2, reg_ctrl2); } else { + reg |= DSI_VIDEO_COMPRESSION_MODE_CTRL_WC(bytes_per_pkt); dsi_write(msm_host, REG_DSI_VIDEO_COMPRESSION_MODE_CTRL, reg); } } @@ -1111,8 +1115,10 @@ int dsi_tx_buf_alloc_6g(struct msm_dsi_host *msm_host, int size) uint64_t iova; u8 *data; + msm_host->aspace = msm_gem_address_space_get(priv->kms->aspace); + data = msm_gem_kernel_new(dev, size, MSM_BO_WC, - priv->kms->aspace, + msm_host->aspace, &msm_host->tx_gem_obj, &iova); if (IS_ERR(data)) { @@ -1141,10 +1147,10 @@ int dsi_tx_buf_alloc_v2(struct msm_dsi_host *msm_host, int size) return 0; } -static void dsi_tx_buf_free(struct msm_dsi_host *msm_host) +void msm_dsi_tx_buf_free(struct mipi_dsi_host *host) { + struct msm_dsi_host *msm_host = to_msm_dsi_host(host); struct drm_device *dev = msm_host->dev; - struct msm_drm_private *priv; /* * This is possible if we're tearing down before we've had a chance to @@ -1155,11 +1161,11 @@ static void dsi_tx_buf_free(struct msm_dsi_host *msm_host) if (!dev) return; - priv = dev->dev_private; if (msm_host->tx_gem_obj) { - msm_gem_unpin_iova(msm_host->tx_gem_obj, priv->kms->aspace); - drm_gem_object_put(msm_host->tx_gem_obj); + msm_gem_kernel_put(msm_host->tx_gem_obj, msm_host->aspace); + msm_gem_address_space_put(msm_host->aspace); msm_host->tx_gem_obj = NULL; + msm_host->aspace = NULL; } if (msm_host->tx_buf) @@ -1945,7 +1951,6 @@ void msm_dsi_host_destroy(struct mipi_dsi_host *host) struct msm_dsi_host *msm_host = to_msm_dsi_host(host); DBG(""); - dsi_tx_buf_free(msm_host); if (msm_host->workqueue) { destroy_workqueue(msm_host->workqueue); msm_host->workqueue = NULL; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index 05621e5e7d6343..e49ebd9f6326f3 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -516,7 +516,9 @@ static int dsi_phy_enable_resource(struct msm_dsi_phy *phy) struct device *dev = &phy->pdev->dev; int ret; - pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); + if (ret) + return ret; ret = clk_prepare_enable(phy->ahb_clk); if (ret) { @@ -689,6 +691,10 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(phy->ahb_clk), "Unable to get ahb clk\n"); + ret = devm_pm_runtime_enable(&pdev->dev); + if (ret) + return ret; + /* PLL init will call into clk_register which requires * register access, so we need to enable power and ahb clock. */ diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c index 3b1ed02f644d28..f72ce6a3c456d5 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -135,7 +135,7 @@ static void dsi_pll_calc_dec_frac(struct dsi_pll_7nm *pll, struct dsi_pll_config config->pll_clock_inverters = 0x00; else config->pll_clock_inverters = 0x40; - } else { + } else if (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_1) { if (pll_freq <= 1000000000ULL) config->pll_clock_inverters = 0xa0; else if (pll_freq <= 2500000000ULL) @@ -144,6 +144,16 @@ static void dsi_pll_calc_dec_frac(struct dsi_pll_7nm *pll, struct dsi_pll_config config->pll_clock_inverters = 0x00; else config->pll_clock_inverters = 0x40; + } else { + /* 4.2, 4.3 */ + if (pll_freq <= 1000000000ULL) + config->pll_clock_inverters = 0xa0; + else if (pll_freq <= 2500000000ULL) + config->pll_clock_inverters = 0x20; + else if (pll_freq <= 3500000000ULL) + config->pll_clock_inverters = 0x00; + else + config->pll_clock_inverters = 0x40; } config->decimal_div_start = dec; @@ -918,7 +928,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2)) { if (phy->cphy_mode) { vreg_ctrl_0 = 0x45; - vreg_ctrl_1 = 0x45; + vreg_ctrl_1 = 0x41; glbl_rescode_top_ctrl = 0x00; glbl_rescode_bot_ctrl = 0x00; } else { diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 02fd6c7d0bb7b9..48e1a8c6942c9f 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -74,18 +74,6 @@ enum msm_dsi_controller { #define MSM_GPU_MAX_RINGS 4 #define MAX_H_TILES_PER_DISPLAY 2 -/** - * enum msm_event_wait - type of HW events to wait for - * @MSM_ENC_COMMIT_DONE - wait for the driver to flush the registers to HW - * @MSM_ENC_TX_COMPLETE - wait for the HW to transfer the frame to panel - * @MSM_ENC_VBLANK - wait for the HW VBLANK event (for driver-internal waiters) - */ -enum msm_event_wait { - MSM_ENC_COMMIT_DONE = 0, - MSM_ENC_TX_COMPLETE, - MSM_ENC_VBLANK, -}; - /** * struct msm_display_topology - defines a display topology pipeline * @num_lm: number of layer mixers used diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c index 5f68e31a3e4e1c..0915f3b68752e3 100644 --- a/drivers/gpu/drm/msm/msm_gem_prime.c +++ b/drivers/gpu/drm/msm/msm_gem_prime.c @@ -26,7 +26,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map) { void *vaddr; - vaddr = msm_gem_get_vaddr(obj); + vaddr = msm_gem_get_vaddr_locked(obj); if (IS_ERR(vaddr)) return PTR_ERR(vaddr); iosys_map_set_vaddr(map, vaddr); @@ -36,7 +36,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map) void msm_gem_prime_vunmap(struct drm_gem_object *obj, struct iosys_map *map) { - msm_gem_put_vaddr(obj); + msm_gem_put_vaddr_locked(obj); } struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev, diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index f38296ad87434e..0641f5bb8649ac 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -76,7 +76,7 @@ static bool wait_for_idle(struct drm_gem_object *obj) { enum dma_resv_usage usage = dma_resv_usage_rw(true); - return dma_resv_wait_timeout(obj->resv, usage, false, 1000) > 0; + return dma_resv_wait_timeout(obj->resv, usage, false, 10) > 0; } static bool diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 7f64c66673002f..5a7541597d0ce8 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -749,12 +749,14 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) struct msm_ringbuffer *ring = submit->ring; unsigned long flags; - pm_runtime_get_sync(&gpu->pdev->dev); + WARN_ON(!mutex_is_locked(&gpu->lock)); - mutex_lock(&gpu->lock); + pm_runtime_get_sync(&gpu->pdev->dev); msm_gpu_hw_init(gpu); + submit->seqno = submit->hw_fence->seqno; + update_sw_cntrs(gpu); /* @@ -779,11 +781,8 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) gpu->funcs->submit(gpu, submit); gpu->cur_ctx_seqno = submit->queue->ctx->seqno; - hangcheck_timer_reset(gpu); - - mutex_unlock(&gpu->lock); - pm_runtime_put(&gpu->pdev->dev); + hangcheck_timer_reset(gpu); } /* @@ -928,7 +927,6 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, if (IS_ERR(gpu->gpu_cx)) gpu->gpu_cx = NULL; - gpu->pdev = pdev; platform_set_drvdata(pdev, &gpu->adreno_smmu); msm_devfreq_init(gpu); diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 5cc8d358cc9759..d5512037c38bcd 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -21,6 +21,8 @@ struct msm_iommu_pagetable { struct msm_mmu base; struct msm_mmu *parent; struct io_pgtable_ops *pgtbl_ops; + const struct iommu_flush_ops *tlb; + struct device *iommu_dev; unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ phys_addr_t ttbr; u32 asid; @@ -201,11 +203,33 @@ static const struct msm_mmu_funcs pagetable_funcs = { static void msm_iommu_tlb_flush_all(void *cookie) { + struct msm_iommu_pagetable *pagetable = cookie; + struct adreno_smmu_priv *adreno_smmu; + + if (!pm_runtime_get_if_in_use(pagetable->iommu_dev)) + return; + + adreno_smmu = dev_get_drvdata(pagetable->parent->dev); + + pagetable->tlb->tlb_flush_all((void *)adreno_smmu->cookie); + + pm_runtime_put_autosuspend(pagetable->iommu_dev); } static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size, size_t granule, void *cookie) { + struct msm_iommu_pagetable *pagetable = cookie; + struct adreno_smmu_priv *adreno_smmu; + + if (!pm_runtime_get_if_in_use(pagetable->iommu_dev)) + return; + + adreno_smmu = dev_get_drvdata(pagetable->parent->dev); + + pagetable->tlb->tlb_flush_walk(iova, size, granule, (void *)adreno_smmu->cookie); + + pm_runtime_put_autosuspend(pagetable->iommu_dev); } static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather, @@ -213,7 +237,7 @@ static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather, { } -static const struct iommu_flush_ops null_tlb_ops = { +static const struct iommu_flush_ops tlb_ops = { .tlb_flush_all = msm_iommu_tlb_flush_all, .tlb_flush_walk = msm_iommu_tlb_flush_walk, .tlb_add_page = msm_iommu_tlb_add_page, @@ -254,10 +278,10 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* The incoming cfg will have the TTBR1 quirk enabled */ ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1; - ttbr0_cfg.tlb = &null_tlb_ops; + ttbr0_cfg.tlb = &tlb_ops; pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1, - &ttbr0_cfg, iommu->domain); + &ttbr0_cfg, pagetable); if (!pagetable->pgtbl_ops) { kfree(pagetable); @@ -279,6 +303,8 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* Needed later for TLB flush */ pagetable->parent = parent; + pagetable->tlb = ttbr1_cfg->tlb; + pagetable->iommu_dev = ttbr1_cfg->iommu_dev; pagetable->pgsize_bitmap = ttbr0_cfg.pgsize_bitmap; pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr; diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index 348c66b1468341..83b49d489cb1c5 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -28,6 +28,8 @@ #define MIN_IB_BW 400000000UL /* Min ib vote 400MB */ +#define DEFAULT_REG_BW 153600 /* Used in mdss fbdev driver */ + struct msm_mdss { struct device *dev; @@ -40,8 +42,9 @@ struct msm_mdss { struct irq_domain *domain; } irq_controller; const struct msm_mdss_data *mdss_data; - struct icc_path *path[2]; - u32 num_paths; + struct icc_path *mdp_path[2]; + u32 num_mdp_paths; + struct icc_path *reg_bus_path; }; static int msm_mdss_parse_data_bus_icc_path(struct device *dev, @@ -49,38 +52,34 @@ static int msm_mdss_parse_data_bus_icc_path(struct device *dev, { struct icc_path *path0; struct icc_path *path1; + struct icc_path *reg_bus_path; - path0 = of_icc_get(dev, "mdp0-mem"); + path0 = devm_of_icc_get(dev, "mdp0-mem"); if (IS_ERR_OR_NULL(path0)) return PTR_ERR_OR_ZERO(path0); - msm_mdss->path[0] = path0; - msm_mdss->num_paths = 1; + msm_mdss->mdp_path[0] = path0; + msm_mdss->num_mdp_paths = 1; - path1 = of_icc_get(dev, "mdp1-mem"); + path1 = devm_of_icc_get(dev, "mdp1-mem"); if (!IS_ERR_OR_NULL(path1)) { - msm_mdss->path[1] = path1; - msm_mdss->num_paths++; + msm_mdss->mdp_path[1] = path1; + msm_mdss->num_mdp_paths++; } - return 0; -} - -static void msm_mdss_put_icc_path(void *data) -{ - struct msm_mdss *msm_mdss = data; - int i; + reg_bus_path = of_icc_get(dev, "cpu-cfg"); + if (!IS_ERR_OR_NULL(reg_bus_path)) + msm_mdss->reg_bus_path = reg_bus_path; - for (i = 0; i < msm_mdss->num_paths; i++) - icc_put(msm_mdss->path[i]); + return 0; } static void msm_mdss_icc_request_bw(struct msm_mdss *msm_mdss, unsigned long bw) { int i; - for (i = 0; i < msm_mdss->num_paths; i++) - icc_set_bw(msm_mdss->path[i], 0, Bps_to_icc(bw)); + for (i = 0; i < msm_mdss->num_mdp_paths; i++) + icc_set_bw(msm_mdss->mdp_path[i], 0, Bps_to_icc(bw)); } static void msm_mdss_irq(struct irq_desc *desc) @@ -245,6 +244,13 @@ static int msm_mdss_enable(struct msm_mdss *msm_mdss) */ msm_mdss_icc_request_bw(msm_mdss, MIN_IB_BW); + if (msm_mdss->mdss_data && msm_mdss->mdss_data->reg_bus_bw) + icc_set_bw(msm_mdss->reg_bus_path, 0, + msm_mdss->mdss_data->reg_bus_bw); + else + icc_set_bw(msm_mdss->reg_bus_path, 0, + DEFAULT_REG_BW); + ret = clk_bulk_prepare_enable(msm_mdss->num_clocks, msm_mdss->clocks); if (ret) { dev_err(msm_mdss->dev, "clock enable failed, ret:%d\n", ret); @@ -298,6 +304,9 @@ static int msm_mdss_disable(struct msm_mdss *msm_mdss) clk_bulk_disable_unprepare(msm_mdss->num_clocks, msm_mdss->clocks); msm_mdss_icc_request_bw(msm_mdss, 0); + if (msm_mdss->reg_bus_path) + icc_set_bw(msm_mdss->reg_bus_path, 0, 0); + return 0; } @@ -384,6 +393,8 @@ static struct msm_mdss *msm_mdss_init(struct platform_device *pdev, bool is_mdp5 if (!msm_mdss) return ERR_PTR(-ENOMEM); + msm_mdss->mdss_data = of_device_get_match_data(&pdev->dev); + msm_mdss->mmio = devm_platform_ioremap_resource_byname(pdev, is_mdp5 ? "mdss_phys" : "mdss"); if (IS_ERR(msm_mdss->mmio)) return ERR_CAST(msm_mdss->mmio); @@ -391,9 +402,6 @@ static struct msm_mdss *msm_mdss_init(struct platform_device *pdev, bool is_mdp5 dev_dbg(&pdev->dev, "mapped mdss address space @%pK\n", msm_mdss->mmio); ret = msm_mdss_parse_data_bus_icc_path(&pdev->dev, msm_mdss); - if (ret) - return ERR_PTR(ret); - ret = devm_add_action_or_reset(&pdev->dev, msm_mdss_put_icc_path, msm_mdss); if (ret) return ERR_PTR(ret); @@ -477,8 +485,6 @@ static int mdss_probe(struct platform_device *pdev) if (IS_ERR(mdss)) return PTR_ERR(mdss); - mdss->mdss_data = of_device_get_match_data(&pdev->dev); - platform_set_drvdata(pdev, mdss); /* @@ -512,18 +518,21 @@ static const struct msm_mdss_data msm8998_data = { .ubwc_enc_version = UBWC_1_0, .ubwc_dec_version = UBWC_1_0, .highest_bank_bit = 2, + .reg_bus_bw = 76800, }; static const struct msm_mdss_data qcm2290_data = { /* no UBWC */ .highest_bank_bit = 0x2, + .reg_bus_bw = 76800, }; static const struct msm_mdss_data sc7180_data = { .ubwc_enc_version = UBWC_2_0, .ubwc_dec_version = UBWC_2_0, .ubwc_static = 0x1e, - .highest_bank_bit = 0x3, + .highest_bank_bit = 0x1, + .reg_bus_bw = 76800, }; static const struct msm_mdss_data sc7280_data = { @@ -533,6 +542,7 @@ static const struct msm_mdss_data sc7280_data = { .ubwc_static = 1, .highest_bank_bit = 1, .macrotile_mode = 1, + .reg_bus_bw = 74000, }; static const struct msm_mdss_data sc8180x_data = { @@ -540,6 +550,7 @@ static const struct msm_mdss_data sc8180x_data = { .ubwc_dec_version = UBWC_3_0, .highest_bank_bit = 3, .macrotile_mode = 1, + .reg_bus_bw = 76800, }; static const struct msm_mdss_data sc8280xp_data = { @@ -549,12 +560,14 @@ static const struct msm_mdss_data sc8280xp_data = { .ubwc_static = 1, .highest_bank_bit = 2, .macrotile_mode = 1, + .reg_bus_bw = 76800, }; static const struct msm_mdss_data sdm845_data = { .ubwc_enc_version = UBWC_2_0, .ubwc_dec_version = UBWC_2_0, .highest_bank_bit = 2, + .reg_bus_bw = 76800, }; static const struct msm_mdss_data sm6350_data = { @@ -563,12 +576,14 @@ static const struct msm_mdss_data sm6350_data = { .ubwc_swizzle = 6, .ubwc_static = 0x1e, .highest_bank_bit = 1, + .reg_bus_bw = 76800, }; static const struct msm_mdss_data sm8150_data = { .ubwc_enc_version = UBWC_3_0, .ubwc_dec_version = UBWC_3_0, .highest_bank_bit = 2, + .reg_bus_bw = 76800, }; static const struct msm_mdss_data sm6115_data = { @@ -577,6 +592,7 @@ static const struct msm_mdss_data sm6115_data = { .ubwc_swizzle = 7, .ubwc_static = 0x11f, .highest_bank_bit = 0x1, + .reg_bus_bw = 76800, }; static const struct msm_mdss_data sm6125_data = { @@ -584,6 +600,7 @@ static const struct msm_mdss_data sm6125_data = { .ubwc_dec_version = UBWC_3_0, .ubwc_swizzle = 1, .highest_bank_bit = 1, + .reg_bus_bw = 76800, }; static const struct msm_mdss_data sm8250_data = { @@ -594,6 +611,18 @@ static const struct msm_mdss_data sm8250_data = { /* TODO: highest_bank_bit = 2 for LP_DDR4 */ .highest_bank_bit = 3, .macrotile_mode = 1, + .reg_bus_bw = 76800, +}; + +static const struct msm_mdss_data sm8350_data = { + .ubwc_enc_version = UBWC_4_0, + .ubwc_dec_version = UBWC_4_0, + .ubwc_swizzle = 6, + .ubwc_static = 1, + /* TODO: highest_bank_bit = 2 for LP_DDR4 */ + .highest_bank_bit = 3, + .macrotile_mode = 1, + .reg_bus_bw = 74000, }; static const struct msm_mdss_data sm8550_data = { @@ -604,6 +633,7 @@ static const struct msm_mdss_data sm8550_data = { /* TODO: highest_bank_bit = 2 for LP_DDR4 */ .highest_bank_bit = 3, .macrotile_mode = 1, + .reg_bus_bw = 57000, }; static const struct of_device_id mdss_dt_match[] = { { .compatible = "qcom,mdss" }, @@ -620,8 +650,8 @@ static const struct of_device_id mdss_dt_match[] = { { .compatible = "qcom,sm6375-mdss", .data = &sm6350_data }, { .compatible = "qcom,sm8150-mdss", .data = &sm8150_data }, { .compatible = "qcom,sm8250-mdss", .data = &sm8250_data }, - { .compatible = "qcom,sm8350-mdss", .data = &sm8250_data }, - { .compatible = "qcom,sm8450-mdss", .data = &sm8250_data }, + { .compatible = "qcom,sm8350-mdss", .data = &sm8350_data }, + { .compatible = "qcom,sm8450-mdss", .data = &sm8350_data }, { .compatible = "qcom,sm8550-mdss", .data = &sm8550_data }, {} }; diff --git a/drivers/gpu/drm/msm/msm_mdss.h b/drivers/gpu/drm/msm/msm_mdss.h index 02bbab42adbc0e..3afef4b1786d28 100644 --- a/drivers/gpu/drm/msm/msm_mdss.h +++ b/drivers/gpu/drm/msm/msm_mdss.h @@ -14,6 +14,7 @@ struct msm_mdss_data { u32 ubwc_static; u32 highest_bank_bit; u32 macrotile_mode; + u32 reg_bus_bw; }; #define UBWC_1_0 0x10000000 diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index 40c0bc35a44cee..7f5e0a961bba72 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -21,8 +21,6 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job) msm_fence_init(submit->hw_fence, fctx); - submit->seqno = submit->hw_fence->seqno; - mutex_lock(&priv->lru.lock); for (i = 0; i < submit->nr_bos; i++) { @@ -34,8 +32,13 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job) mutex_unlock(&priv->lru.lock); + /* TODO move submit path over to using a per-ring lock.. */ + mutex_lock(&gpu->lock); + msm_gpu_submit(gpu, submit); + mutex_unlock(&gpu->lock); + return dma_fence_get(submit->hw_fence); } diff --git a/drivers/gpu/drm/mxsfb/lcdif_drv.c b/drivers/gpu/drm/mxsfb/lcdif_drv.c index 18de2f17e2491c..6494e827075690 100644 --- a/drivers/gpu/drm/mxsfb/lcdif_drv.c +++ b/drivers/gpu/drm/mxsfb/lcdif_drv.c @@ -340,6 +340,9 @@ static int __maybe_unused lcdif_suspend(struct device *dev) if (ret) return ret; + if (pm_runtime_suspended(dev)) + return 0; + return lcdif_rpm_suspend(dev); } @@ -347,7 +350,8 @@ static int __maybe_unused lcdif_resume(struct device *dev) { struct drm_device *drm = dev_get_drvdata(dev); - lcdif_rpm_resume(dev); + if (!pm_runtime_suspended(dev)) + lcdif_rpm_resume(dev); return drm_mode_config_helper_resume(drm); } diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c index a34917b048f96f..8c7fff19c97bb0 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c +++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c @@ -1157,7 +1157,7 @@ nv04_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb, chan = drm->channel; if (!chan) return -ENODEV; - cli = (void *)chan->user.client; + cli = chan->cli; push = chan->chan.push; s = kzalloc(sizeof(*s), GFP_KERNEL); diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c index 670c9739e5e18c..2033214c4b7848 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c +++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c @@ -209,6 +209,8 @@ static int nv17_tv_get_ld_modes(struct drm_encoder *encoder, struct drm_display_mode *mode; mode = drm_mode_duplicate(encoder->dev, tv_mode); + if (!mode) + continue; mode->clock = tv_norm->tv_enc_mode.vrefresh * mode->htotal / 1000 * @@ -258,6 +260,8 @@ static int nv17_tv_get_hd_modes(struct drm_encoder *encoder, if (modes[i].hdisplay == output_mode->hdisplay && modes[i].vdisplay == output_mode->vdisplay) { mode = drm_mode_duplicate(encoder->dev, output_mode); + if (!mode) + continue; mode->type |= DRM_MODE_TYPE_PREFERRED; } else { @@ -265,6 +269,8 @@ static int nv17_tv_get_hd_modes(struct drm_encoder *encoder, modes[i].vdisplay, 60, false, (output_mode->flags & DRM_MODE_FLAG_INTERLACE), false); + if (!mode) + continue; } /* CVT modes are sometimes unsuitable... */ diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 4e7c9c353c5112..de8041c94de5d8 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -966,8 +966,7 @@ nv50_msto_atomic_check(struct drm_encoder *encoder, const int clock = crtc_state->adjusted_mode.clock; asyh->or.bpc = connector->display_info.bpc; - asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, asyh->or.bpc * 3, - false); + asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, asyh->or.bpc * 3 << 4); } mst_state = drm_atomic_get_mst_topology_state(state, &mstm->mgr); @@ -2310,7 +2309,7 @@ nv50_disp_atomic_commit(struct drm_device *dev, err_cleanup: if (ret) - drm_atomic_helper_cleanup_planes(dev, state); + drm_atomic_helper_unprepare_planes(dev, state); done: pm_runtime_put_autosuspend(dev->dev); return ret; diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/client.h b/drivers/gpu/drm/nouveau/include/nvkm/core/client.h index 0d9fc741a71932..932c9fd0b2d89c 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/core/client.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/core/client.h @@ -11,6 +11,7 @@ struct nvkm_client { u32 debug; struct rb_root objroot; + spinlock_t obj_lock; void *data; int (*event)(u64 token, void *argv, u32 argc); diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/event.h b/drivers/gpu/drm/nouveau/include/nvkm/core/event.h index 82b267c111470a..460459af272d6f 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/core/event.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/core/event.h @@ -14,7 +14,7 @@ struct nvkm_event { int index_nr; spinlock_t refs_lock; - spinlock_t list_lock; + rwlock_t list_lock; int *refs; struct list_head ntfy; @@ -38,7 +38,7 @@ nvkm_event_init(const struct nvkm_event_func *func, struct nvkm_subdev *subdev, int types_nr, int index_nr, struct nvkm_event *event) { spin_lock_init(&event->refs_lock); - spin_lock_init(&event->list_lock); + rwlock_init(&event->list_lock); return __nvkm_event_init(func, subdev, types_nr, index_nr, event); } diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index 2edd7bb13faea5..2e177ebab30398 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -204,6 +204,7 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS) struct nouveau_cli *cli = nouveau_cli(file_priv); struct nouveau_drm *drm = nouveau_drm(dev); struct nvif_device *device = &drm->client.device; + struct nvkm_device *nvkm_device = nvxx_device(&drm->client.device); struct nvkm_gr *gr = nvxx_gr(device); struct drm_nouveau_getparam *getparam = data; struct pci_dev *pdev = to_pci_dev(dev->dev); @@ -268,6 +269,17 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS) getparam->value = nouveau_exec_push_max_from_ib_max(ib_max); break; } + case NOUVEAU_GETPARAM_VRAM_BAR_SIZE: + getparam->value = nvkm_device->func->resource_size(nvkm_device, 1); + break; + case NOUVEAU_GETPARAM_VRAM_USED: { + struct ttm_resource_manager *vram_mgr = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM); + getparam->value = (u64)ttm_resource_manager_usage(vram_mgr); + break; + } + case NOUVEAU_GETPARAM_HAS_VMA_TILEMODE: + getparam->value = 1; + break; default: NV_PRINTK(dbg, cli, "unknown parameter %lld\n", getparam->param); return -EINVAL; @@ -339,7 +351,7 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS) list_add(&chan->head, &abi16->channels); /* create channel object and initialise dma and fence management */ - ret = nouveau_channel_new(drm, device, false, runm, init->fb_ctxdma_handle, + ret = nouveau_channel_new(cli, false, runm, init->fb_ctxdma_handle, init->tt_ctxdma_handle, &chan->chan); if (ret) goto done; diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c index 189903b65edc99..48cf593383b341 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bios.c +++ b/drivers/gpu/drm/nouveau/nouveau_bios.c @@ -23,6 +23,7 @@ */ #include "nouveau_drv.h" +#include "nouveau_bios.h" #include "nouveau_reg.h" #include "dispnv04/hw.h" #include "nouveau_encoder.h" @@ -1675,7 +1676,7 @@ apply_dcb_encoder_quirks(struct drm_device *dev, int idx, u32 *conn, u32 *conf) */ if (nv_match_device(dev, 0x0201, 0x1462, 0x8851)) { if (*conn == 0xf2005014 && *conf == 0xffffffff) { - fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, 1); + fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, DCB_OUTPUT_B); return false; } } @@ -1761,26 +1762,26 @@ fabricate_dcb_encoder_table(struct drm_device *dev, struct nvbios *bios) #ifdef __powerpc__ /* Apple iMac G4 NV17 */ if (of_machine_is_compatible("PowerMac4,5")) { - fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, 1); - fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, 2); + fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, DCB_OUTPUT_B); + fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, DCB_OUTPUT_C); return; } #endif /* Make up some sane defaults */ fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, - bios->legacy.i2c_indices.crt, 1, 1); + bios->legacy.i2c_indices.crt, 1, DCB_OUTPUT_B); if (nv04_tv_identify(dev, bios->legacy.i2c_indices.tv) >= 0) fabricate_dcb_output(dcb, DCB_OUTPUT_TV, bios->legacy.i2c_indices.tv, - all_heads, 0); + all_heads, DCB_OUTPUT_A); else if (bios->tmds.output0_script_ptr || bios->tmds.output1_script_ptr) fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, bios->legacy.i2c_indices.panel, - all_heads, 1); + all_heads, DCB_OUTPUT_B); } static int diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 0f3bd187ede67d..5d398a422459e1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -234,28 +234,28 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, } nvbo->contig = !(tile_flags & NOUVEAU_GEM_TILE_NONCONTIG); - if (!nouveau_cli_uvmm(cli) || internal) { - /* for BO noVM allocs, don't assign kinds */ - if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) { - nvbo->kind = (tile_flags & 0x0000ff00) >> 8; - if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { - kfree(nvbo); - return ERR_PTR(-EINVAL); - } - nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind; - } else if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) { - nvbo->kind = (tile_flags & 0x00007f00) >> 8; - nvbo->comp = (tile_flags & 0x00030000) >> 16; - if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { - kfree(nvbo); - return ERR_PTR(-EINVAL); - } - } else { - nvbo->zeta = (tile_flags & 0x00000007); + if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) { + nvbo->kind = (tile_flags & 0x0000ff00) >> 8; + if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { + kfree(nvbo); + return ERR_PTR(-EINVAL); + } + + nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind; + } else if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) { + nvbo->kind = (tile_flags & 0x00007f00) >> 8; + nvbo->comp = (tile_flags & 0x00030000) >> 16; + if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { + kfree(nvbo); + return ERR_PTR(-EINVAL); } - nvbo->mode = tile_mode; + } else { + nvbo->zeta = (tile_flags & 0x00000007); + } + nvbo->mode = tile_mode; + if (!nouveau_cli_uvmm(cli) || internal) { /* Determine the desirable target GPU page size for the buffer. */ for (i = 0; i < vmm->page_nr; i++) { /* Because we cannot currently allow VMM maps to fail @@ -297,12 +297,6 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, } nvbo->page = vmm->page[pi].shift; } else { - /* reject other tile flags when in VM mode. */ - if (tile_mode) - return ERR_PTR(-EINVAL); - if (tile_flags & ~NOUVEAU_GEM_TILE_NONCONTIG) - return ERR_PTR(-EINVAL); - /* Determine the desirable target GPU page size for the buffer. */ for (i = 0; i < vmm->page_nr; i++) { /* Because we cannot currently allow VMM maps to fail @@ -318,8 +312,9 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT)) continue; - if (pi < 0) - pi = i; + /* pick the last one as it will be smallest. */ + pi = i; + /* Stop once the buffer is larger than the current page size. */ if (*size >= 1ULL << vmm->page[i].shift) break; @@ -848,7 +843,7 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, { struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct nouveau_channel *chan = drm->ttm.chan; - struct nouveau_cli *cli = (void *)chan->user.client; + struct nouveau_cli *cli = chan->cli; struct nouveau_fence *fence; int ret; @@ -1254,6 +1249,8 @@ nouveau_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *reg) drm_vma_node_unmap(&nvbo->bo.base.vma_node, bdev->dev_mapping); nouveau_ttm_io_mem_free_locked(drm, nvbo->bo.resource); + nvbo->bo.resource->bus.offset = 0; + nvbo->bo.resource->bus.addr = NULL; goto retry; } diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index 7c97b288680760..cee36b1efd3917 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -52,7 +52,7 @@ static int nouveau_channel_killed(struct nvif_event *event, void *repv, u32 repc) { struct nouveau_channel *chan = container_of(event, typeof(*chan), kill); - struct nouveau_cli *cli = (void *)chan->user.client; + struct nouveau_cli *cli = chan->cli; NV_PRINTK(warn, cli, "channel %d killed!\n", chan->chid); @@ -66,7 +66,7 @@ int nouveau_channel_idle(struct nouveau_channel *chan) { if (likely(chan && chan->fence && !atomic_read(&chan->killed))) { - struct nouveau_cli *cli = (void *)chan->user.client; + struct nouveau_cli *cli = chan->cli; struct nouveau_fence *fence = NULL; int ret; @@ -142,10 +142,11 @@ nouveau_channel_wait(struct nvif_push *push, u32 size) } static int -nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device, +nouveau_channel_prep(struct nouveau_cli *cli, u32 size, struct nouveau_channel **pchan) { - struct nouveau_cli *cli = (void *)device->object.client; + struct nouveau_drm *drm = cli->drm; + struct nvif_device *device = &cli->device; struct nv_dma_v0 args = {}; struct nouveau_channel *chan; u32 target; @@ -155,6 +156,7 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device, if (!chan) return -ENOMEM; + chan->cli = cli; chan->device = device; chan->drm = drm; chan->vmm = nouveau_cli_vmm(cli); @@ -254,7 +256,7 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device, } static int -nouveau_channel_ctor(struct nouveau_drm *drm, struct nvif_device *device, bool priv, u64 runm, +nouveau_channel_ctor(struct nouveau_cli *cli, bool priv, u64 runm, struct nouveau_channel **pchan) { const struct nvif_mclass hosts[] = { @@ -279,7 +281,7 @@ nouveau_channel_ctor(struct nouveau_drm *drm, struct nvif_device *device, bool p struct nvif_chan_v0 chan; char name[TASK_COMM_LEN+16]; } args; - struct nouveau_cli *cli = (void *)device->object.client; + struct nvif_device *device = &cli->device; struct nouveau_channel *chan; const u64 plength = 0x10000; const u64 ioffset = plength; @@ -298,7 +300,7 @@ nouveau_channel_ctor(struct nouveau_drm *drm, struct nvif_device *device, bool p size = ioffset + ilength; /* allocate dma push buffer */ - ret = nouveau_channel_prep(drm, device, size, &chan); + ret = nouveau_channel_prep(cli, size, &chan); *pchan = chan; if (ret) return ret; @@ -493,13 +495,12 @@ nouveau_channel_init(struct nouveau_channel *chan, u32 vram, u32 gart) } int -nouveau_channel_new(struct nouveau_drm *drm, struct nvif_device *device, +nouveau_channel_new(struct nouveau_cli *cli, bool priv, u64 runm, u32 vram, u32 gart, struct nouveau_channel **pchan) { - struct nouveau_cli *cli = (void *)device->object.client; int ret; - ret = nouveau_channel_ctor(drm, device, priv, runm, pchan); + ret = nouveau_channel_ctor(cli, priv, runm, pchan); if (ret) { NV_PRINTK(dbg, cli, "channel create, %d\n", ret); return ret; diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.h b/drivers/gpu/drm/nouveau/nouveau_chan.h index 5de2ef4e98c2bb..260febd634ee21 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.h +++ b/drivers/gpu/drm/nouveau/nouveau_chan.h @@ -12,6 +12,7 @@ struct nouveau_channel { struct nvif_push *push; } chan; + struct nouveau_cli *cli; struct nvif_device *device; struct nouveau_drm *drm; struct nouveau_vmm *vmm; @@ -62,7 +63,7 @@ struct nouveau_channel { int nouveau_channels_init(struct nouveau_drm *); void nouveau_channels_fini(struct nouveau_drm *); -int nouveau_channel_new(struct nouveau_drm *, struct nvif_device *, bool priv, u64 runm, +int nouveau_channel_new(struct nouveau_cli *, bool priv, u64 runm, u32 vram, u32 gart, struct nouveau_channel **); void nouveau_channel_del(struct nouveau_channel **); int nouveau_channel_idle(struct nouveau_channel *); diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 79ea30aac31fb8..22a125243d81f7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -983,6 +983,9 @@ nouveau_connector_get_modes(struct drm_connector *connector) struct drm_display_mode *mode; mode = drm_mode_duplicate(dev, nv_connector->native_mode); + if (!mode) + return 0; + drm_mode_probed_add(connector, mode); ret = 1; } diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 12feecf71e752d..097bd3af0719e0 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -193,7 +193,7 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) if (!spage || !(src & MIGRATE_PFN_MIGRATE)) goto done; - dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address); + dpage = alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vmf->vma, vmf->address); if (!dpage) goto done; @@ -378,9 +378,9 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) dma_addr_t *dma_addrs; struct nouveau_fence *fence; - src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); - dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); - dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL); + src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL); + dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL); + dma_addrs = kvcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL | __GFP_NOFAIL); migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT, npages); @@ -406,11 +406,11 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) migrate_device_pages(src_pfns, dst_pfns, npages); nouveau_dmem_fence_done(&fence); migrate_device_finalize(src_pfns, dst_pfns, npages); - kfree(src_pfns); - kfree(dst_pfns); + kvfree(src_pfns); + kvfree(dst_pfns); for (i = 0; i < npages; i++) dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL); - kfree(dma_addrs); + kvfree(dma_addrs); } void diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c index 6a4980b2d4d4e1..bf2ae67b03d944 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dp.c +++ b/drivers/gpu/drm/nouveau/nouveau_dp.c @@ -108,12 +108,15 @@ nouveau_dp_detect(struct nouveau_connector *nv_connector, u8 *dpcd = nv_encoder->dp.dpcd; int ret = NOUVEAU_DP_NONE, hpd; - /* If we've already read the DPCD on an eDP device, we don't need to - * reread it as it won't change + /* eDP ports don't support hotplugging - so there's no point in probing eDP ports unless we + * haven't probed them once before. */ - if (connector->connector_type == DRM_MODE_CONNECTOR_eDP && - dpcd[DP_DPCD_REV] != 0) - return NOUVEAU_DP_SST; + if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) { + if (connector->status == connector_status_connected) + return NOUVEAU_DP_SST; + else if (connector->status == connector_status_disconnected) + return NOUVEAU_DP_NONE; + } mutex_lock(&nv_encoder->dp.hpd_irq_lock); if (mstm) { diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 4396f501b16a3f..ac15a662e06042 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -343,7 +343,7 @@ nouveau_accel_ce_init(struct nouveau_drm *drm) return; } - ret = nouveau_channel_new(drm, device, false, runm, NvDmaFB, NvDmaTT, &drm->cechan); + ret = nouveau_channel_new(&drm->client, true, runm, NvDmaFB, NvDmaTT, &drm->cechan); if (ret) NV_ERROR(drm, "failed to create ce channel, %d\n", ret); } @@ -371,7 +371,7 @@ nouveau_accel_gr_init(struct nouveau_drm *drm) return; } - ret = nouveau_channel_new(drm, device, false, runm, NvDmaFB, NvDmaTT, &drm->channel); + ret = nouveau_channel_new(&drm->client, false, runm, NvDmaFB, NvDmaTT, &drm->channel); if (ret) { NV_ERROR(drm, "failed to create kernel channel, %d\n", ret); nouveau_accel_gr_fini(drm); @@ -708,10 +708,11 @@ nouveau_drm_device_fini(struct drm_device *dev) } mutex_unlock(&drm->clients_lock); - nouveau_sched_fini(drm); - nouveau_cli_fini(&drm->client); nouveau_cli_fini(&drm->master); + + nouveau_sched_fini(drm); + nvif_parent_dtor(&drm->parent); mutex_destroy(&drm->clients_lock); kfree(drm); @@ -1133,7 +1134,10 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv) } get_task_comm(tmpname, current); - snprintf(name, sizeof(name), "%s[%d]", tmpname, pid_nr(fpriv->pid)); + rcu_read_lock(); + snprintf(name, sizeof(name), "%s[%d]", + tmpname, pid_nr(rcu_dereference(fpriv->pid))); + rcu_read_unlock(); if (!(cli = kzalloc(sizeof(*cli), GFP_KERNEL))) { ret = -ENOMEM; diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index ca762ea5541361..93f08f9479d89b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -103,6 +103,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error) void nouveau_fence_context_del(struct nouveau_fence_chan *fctx) { + cancel_work_sync(&fctx->uevent_work); nouveau_fence_context_kill(fctx, 0); nvif_event_dtor(&fctx->event); fctx->dead = 1; @@ -145,12 +146,13 @@ nouveau_fence_update(struct nouveau_channel *chan, struct nouveau_fence_chan *fc return drop; } -static int -nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc) +static void +nouveau_fence_uevent_work(struct work_struct *work) { - struct nouveau_fence_chan *fctx = container_of(event, typeof(*fctx), event); + struct nouveau_fence_chan *fctx = container_of(work, struct nouveau_fence_chan, + uevent_work); unsigned long flags; - int ret = NVIF_EVENT_KEEP; + int drop = 0; spin_lock_irqsave(&fctx->lock, flags); if (!list_empty(&fctx->pending)) { @@ -160,11 +162,20 @@ nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc fence = list_entry(fctx->pending.next, typeof(*fence), head); chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock)); if (nouveau_fence_update(chan, fctx)) - ret = NVIF_EVENT_DROP; + drop = 1; } + if (drop) + nvif_event_block(&fctx->event); + spin_unlock_irqrestore(&fctx->lock, flags); +} - return ret; +static int +nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc) +{ + struct nouveau_fence_chan *fctx = container_of(event, typeof(*fctx), event); + schedule_work(&fctx->uevent_work); + return NVIF_EVENT_KEEP; } void @@ -178,6 +189,7 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha } args; int ret; + INIT_WORK(&fctx->uevent_work, nouveau_fence_uevent_work); INIT_LIST_HEAD(&fctx->flip); INIT_LIST_HEAD(&fctx->pending); spin_lock_init(&fctx->lock); diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 64d33ae7f35610..8bc065acfe3587 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -44,6 +44,7 @@ struct nouveau_fence_chan { u32 context; char name[32]; + struct work_struct uevent_work; struct nvif_event event; int notify_ref, dead, killed; }; diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index a0d303e5ce3d8d..7b69e6df57486a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -758,7 +758,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data, return -ENOMEM; if (unlikely(nouveau_cli_uvmm(cli))) - return -ENOSYS; + return nouveau_abi16_put(abi16, -ENOSYS); list_for_each_entry(temp, &abi16->channels, head) { if (temp->chan->chid == req->channel) { diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index 1b2ff0c40fc1c9..6c599a9f49ee40 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -64,7 +64,8 @@ struct drm_gem_object *nouveau_gem_prime_import_sg_table(struct drm_device *dev, * to the caller, instead of a normal nouveau_bo ttm reference. */ ret = drm_gem_object_init(dev, &nvbo->bo.base, size); if (ret) { - nouveau_bo_ref(NULL, &nvbo); + drm_gem_object_release(&nvbo->bo.base); + kfree(nvbo); obj = ERR_PTR(-ENOMEM); goto unlock; } diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 186351ecf72fd7..ec9f307370fa8a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -1011,7 +1011,7 @@ nouveau_svm_fault_buffer_ctor(struct nouveau_svm *svm, s32 oclass, int id) if (ret) return ret; - buffer->fault = kvcalloc(sizeof(*buffer->fault), buffer->entries, GFP_KERNEL); + buffer->fault = kvcalloc(buffer->entries, sizeof(*buffer->fault), GFP_KERNEL); if (!buffer->fault) return -ENOMEM; diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index aae780e4a4aa37..3d41e590d4712d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -804,15 +804,15 @@ op_remap(struct drm_gpuva_op_remap *r, struct drm_gpuva_op_unmap *u = r->unmap; struct nouveau_uvma *uvma = uvma_from_va(u->va); u64 addr = uvma->va.va.addr; - u64 range = uvma->va.va.range; + u64 end = uvma->va.va.addr + uvma->va.va.range; if (r->prev) addr = r->prev->va.addr + r->prev->va.range; if (r->next) - range = r->next->va.addr - addr; + end = r->next->va.addr; - op_unmap_range(u, addr, range); + op_unmap_range(u, addr, end - addr); } static int @@ -1320,6 +1320,7 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job) drm_gpuva_for_each_op(va_op, op->ops) { struct drm_gem_object *obj = op_gem_obj(va_op); + struct nouveau_bo *nvbo; if (unlikely(!obj)) continue; @@ -1330,8 +1331,9 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job) if (unlikely(va_op->op == DRM_GPUVA_OP_UNMAP)) continue; - ret = nouveau_bo_validate(nouveau_gem_object(obj), - true, false); + nvbo = nouveau_gem_object(obj); + nouveau_bo_placement_set(nvbo, nvbo->valid_domains, 0); + ret = nouveau_bo_validate(nvbo, true, false); if (ret) { op = list_last_op(&bind_job->ops); goto unwind; diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c index a6602c01267156..3dda885df5b223 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c @@ -108,6 +108,9 @@ nouveau_vma_new(struct nouveau_bo *nvbo, struct nouveau_vmm *vmm, } else { ret = nvif_vmm_get(&vmm->vmm, PTES, false, mem->mem.page, 0, mem->mem.size, &tmp); + if (ret) + goto done; + vma->addr = tmp.addr; } diff --git a/drivers/gpu/drm/nouveau/nv04_fence.c b/drivers/gpu/drm/nouveau/nv04_fence.c index 5b71a5a5cd85ce..cdbc75e3d1f669 100644 --- a/drivers/gpu/drm/nouveau/nv04_fence.c +++ b/drivers/gpu/drm/nouveau/nv04_fence.c @@ -39,7 +39,7 @@ struct nv04_fence_priv { static int nv04_fence_emit(struct nouveau_fence *fence) { - struct nvif_push *push = fence->channel->chan.push; + struct nvif_push *push = unrcu_pointer(fence->channel)->chan.push; int ret = PUSH_WAIT(push, 2); if (ret == 0) { PUSH_NVSQ(push, NV_SW, 0x0150, fence->base.seqno); diff --git a/drivers/gpu/drm/nouveau/nvkm/core/client.c b/drivers/gpu/drm/nouveau/nvkm/core/client.c index ebdeb8eb9e7741..c55662937ab22c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/client.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/client.c @@ -180,6 +180,7 @@ nvkm_client_new(const char *name, u64 device, const char *cfg, const char *dbg, client->device = device; client->debug = nvkm_dbgopt(dbg, "CLIENT"); client->objroot = RB_ROOT; + spin_lock_init(&client->obj_lock); client->event = event; INIT_LIST_HEAD(&client->umem); spin_lock_init(&client->lock); diff --git a/drivers/gpu/drm/nouveau/nvkm/core/event.c b/drivers/gpu/drm/nouveau/nvkm/core/event.c index a6c877135598f7..61fed7792e415c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/event.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/event.c @@ -81,17 +81,17 @@ nvkm_event_ntfy_state(struct nvkm_event_ntfy *ntfy) static void nvkm_event_ntfy_remove(struct nvkm_event_ntfy *ntfy) { - spin_lock_irq(&ntfy->event->list_lock); + write_lock_irq(&ntfy->event->list_lock); list_del_init(&ntfy->head); - spin_unlock_irq(&ntfy->event->list_lock); + write_unlock_irq(&ntfy->event->list_lock); } static void nvkm_event_ntfy_insert(struct nvkm_event_ntfy *ntfy) { - spin_lock_irq(&ntfy->event->list_lock); + write_lock_irq(&ntfy->event->list_lock); list_add_tail(&ntfy->head, &ntfy->event->ntfy); - spin_unlock_irq(&ntfy->event->list_lock); + write_unlock_irq(&ntfy->event->list_lock); } static void @@ -176,7 +176,7 @@ nvkm_event_ntfy(struct nvkm_event *event, int id, u32 bits) return; nvkm_trace(event->subdev, "event: ntfy %08x on %d\n", bits, id); - spin_lock_irqsave(&event->list_lock, flags); + read_lock_irqsave(&event->list_lock, flags); list_for_each_entry_safe(ntfy, ntmp, &event->ntfy, head) { if (ntfy->id == id && ntfy->bits & bits) { @@ -185,7 +185,7 @@ nvkm_event_ntfy(struct nvkm_event *event, int id, u32 bits) } } - spin_unlock_irqrestore(&event->list_lock, flags); + read_unlock_irqrestore(&event->list_lock, flags); } void diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c index 91fb494d400935..afc8d4e3e16f47 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c @@ -187,7 +187,8 @@ nvkm_firmware_dtor(struct nvkm_firmware *fw) break; case NVKM_FIRMWARE_IMG_DMA: nvkm_memory_unref(&memory); - dma_free_coherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), fw->img, fw->phys); + dma_free_noncoherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), + fw->img, fw->phys, DMA_TO_DEVICE); break; default: WARN_ON(1); @@ -212,10 +213,12 @@ nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name, break; case NVKM_FIRMWARE_IMG_DMA: { dma_addr_t addr; - len = ALIGN(fw->len, PAGE_SIZE); - fw->img = dma_alloc_coherent(fw->device->dev, len, &addr, GFP_KERNEL); + fw->img = dma_alloc_noncoherent(fw->device->dev, + len, &addr, + DMA_TO_DEVICE, + GFP_KERNEL); if (fw->img) { memcpy(fw->img, src, fw->len); fw->phys = addr; diff --git a/drivers/gpu/drm/nouveau/nvkm/core/object.c b/drivers/gpu/drm/nouveau/nvkm/core/object.c index 7c554c14e8841d..aea3ba72027abf 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/object.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/object.c @@ -30,8 +30,10 @@ nvkm_object_search(struct nvkm_client *client, u64 handle, const struct nvkm_object_func *func) { struct nvkm_object *object; + unsigned long flags; if (handle) { + spin_lock_irqsave(&client->obj_lock, flags); struct rb_node *node = client->objroot.rb_node; while (node) { object = rb_entry(node, typeof(*object), node); @@ -40,9 +42,12 @@ nvkm_object_search(struct nvkm_client *client, u64 handle, else if (handle > object->object) node = node->rb_right; - else + else { + spin_unlock_irqrestore(&client->obj_lock, flags); goto done; + } } + spin_unlock_irqrestore(&client->obj_lock, flags); return ERR_PTR(-ENOENT); } else { object = &client->object; @@ -57,30 +62,39 @@ nvkm_object_search(struct nvkm_client *client, u64 handle, void nvkm_object_remove(struct nvkm_object *object) { + unsigned long flags; + + spin_lock_irqsave(&object->client->obj_lock, flags); if (!RB_EMPTY_NODE(&object->node)) rb_erase(&object->node, &object->client->objroot); + spin_unlock_irqrestore(&object->client->obj_lock, flags); } bool nvkm_object_insert(struct nvkm_object *object) { - struct rb_node **ptr = &object->client->objroot.rb_node; + struct rb_node **ptr; struct rb_node *parent = NULL; + unsigned long flags; + spin_lock_irqsave(&object->client->obj_lock, flags); + ptr = &object->client->objroot.rb_node; while (*ptr) { struct nvkm_object *this = rb_entry(*ptr, typeof(*this), node); parent = *ptr; - if (object->object < this->object) + if (object->object < this->object) { ptr = &parent->rb_left; - else - if (object->object > this->object) + } else if (object->object > this->object) { ptr = &parent->rb_right; - else + } else { + spin_unlock_irqrestore(&object->client->obj_lock, flags); return false; + } } rb_link_node(&object->node, parent, ptr); rb_insert_color(&object->node, &object->client->objroot); + spin_unlock_irqrestore(&object->client->obj_lock, flags); return true; } diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c index 80a480b1217468..a1c8545f1249a1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c @@ -89,6 +89,12 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user, nvkm_falcon_fw_dtor_sigs(fw); } + /* after last write to the img, sync dma mappings */ + dma_sync_single_for_device(fw->fw.device->dev, + fw->fw.phys, + sg_dma_len(&fw->fw.mem.sgl), + DMA_TO_DEVICE); + FLCNFW_DBG(fw, "resetting"); fw->func->reset(fw); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c index 19188683c8fca9..8c2bf1c16f2a95 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c @@ -154,11 +154,17 @@ shadow_fw_init(struct nvkm_bios *bios, const char *name) return (void *)fw; } +static void +shadow_fw_release(void *fw) +{ + release_firmware(fw); +} + static const struct nvbios_source shadow_fw = { .name = "firmware", .init = shadow_fw_init, - .fini = (void(*)(void *))release_firmware, + .fini = shadow_fw_release, .read = shadow_fw_read, .rw = false, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c index 4bf486b5710136..cb05f7f48a98bb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c @@ -66,11 +66,16 @@ of_init(struct nvkm_bios *bios, const char *name) return ERR_PTR(-EINVAL); } +static void of_fini(void *p) +{ + kfree(p); +} + const struct nvbios_source nvbios_of = { .name = "OpenFirmware", .init = of_init, - .fini = (void(*)(void *))kfree, + .fini = of_fini, .read = of_read, .size = of_size, .rw = false, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h index 50f0c1914f58e8..4c3f7439657987 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h @@ -46,6 +46,8 @@ u32 gm107_ram_probe_fbp(const struct nvkm_ram_func *, u32 gm200_ram_probe_fbp_amount(const struct nvkm_ram_func *, u32, struct nvkm_device *, int, int *); +int gp100_ram_init(struct nvkm_ram *); + /* RAM type-specific MR calculation routines */ int nvkm_sddr2_calc(struct nvkm_ram *); int nvkm_sddr3_calc(struct nvkm_ram *); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c index 378f6fb7099077..8987a21e81d174 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c @@ -27,7 +27,7 @@ #include #include -static int +int gp100_ram_init(struct nvkm_ram *ram) { struct nvkm_subdev *subdev = &ram->fb->subdev; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp102.c index 8550f5e473474b..b6b6ee59019d70 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp102.c @@ -5,6 +5,7 @@ static const struct nvkm_ram_func gp102_ram = { + .init = gp100_ram_init, }; int diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c index 4b2d7465d22f75..f4989f0526ecb8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c @@ -221,8 +221,11 @@ nv50_instobj_acquire(struct nvkm_memory *memory) void __iomem *map = NULL; /* Already mapped? */ - if (refcount_inc_not_zero(&iobj->maps)) + if (refcount_inc_not_zero(&iobj->maps)) { + /* read barrier match the wmb on refcount set */ + smp_rmb(); return iobj->map; + } /* Take the lock, and re-check that another thread hasn't * already mapped the object in the meantime. @@ -249,6 +252,8 @@ nv50_instobj_acquire(struct nvkm_memory *memory) iobj->base.memory.ptrs = &nv50_instobj_fast; else iobj->base.memory.ptrs = &nv50_instobj_slow; + /* barrier to ensure the ptrs are written before refcount is set */ + smp_wmb(); refcount_set(&iobj->maps, 1); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c index 6cb5eefa45e9aa..5a08458fe1b7f5 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c @@ -31,7 +31,7 @@ tu102_vmm_flush(struct nvkm_vmm *vmm, int depth) type |= 0x00000001; /* PAGE_ALL */ if (atomic_read(&vmm->engref[NVKM_SUBDEV_BAR])) - type |= 0x00000004; /* HUB_ONLY */ + type |= 0x00000006; /* HUB_ONLY | ALL PDB (hack) */ mutex_lock(&vmm->mmu->mutex); diff --git a/drivers/gpu/drm/omapdrm/Kconfig b/drivers/gpu/drm/omapdrm/Kconfig index b715301ec79f66..6c49270cb290a4 100644 --- a/drivers/gpu/drm/omapdrm/Kconfig +++ b/drivers/gpu/drm/omapdrm/Kconfig @@ -4,7 +4,7 @@ config DRM_OMAP depends on DRM && OF depends on ARCH_OMAP2PLUS select DRM_KMS_HELPER - select FB_DMAMEM_HELPERS if DRM_FBDEV_EMULATION + select FB_DMAMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION select VIDEOMODE_HELPERS select HDMI default n diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c index afeeb773755252..21996b713d1c3a 100644 --- a/drivers/gpu/drm/omapdrm/omap_drv.c +++ b/drivers/gpu/drm/omapdrm/omap_drv.c @@ -69,7 +69,6 @@ static void omap_atomic_commit_tail(struct drm_atomic_state *old_state) { struct drm_device *dev = old_state->dev; struct omap_drm_private *priv = dev->dev_private; - bool fence_cookie = dma_fence_begin_signalling(); dispc_runtime_get(priv->dispc); @@ -92,6 +91,8 @@ static void omap_atomic_commit_tail(struct drm_atomic_state *old_state) omap_atomic_wait_for_completion(dev, old_state); drm_atomic_helper_commit_planes(dev, old_state, 0); + + drm_atomic_helper_commit_hw_done(old_state); } else { /* * OMAP3 DSS seems to have issues with the work-around above, @@ -101,11 +102,9 @@ static void omap_atomic_commit_tail(struct drm_atomic_state *old_state) drm_atomic_helper_commit_planes(dev, old_state, 0); drm_atomic_helper_commit_modeset_enables(dev, old_state); - } - - drm_atomic_helper_commit_hw_done(old_state); - dma_fence_end_signalling(fence_cookie); + drm_atomic_helper_commit_hw_done(old_state); + } /* * Wait for completion of the page flips to ensure that old buffers @@ -696,6 +695,10 @@ static int omapdrm_init(struct omap_drm_private *priv, struct device *dev) soc = soc_device_match(omapdrm_soc_devices); priv->omaprev = soc ? (uintptr_t)soc->data : 0; priv->wq = alloc_ordered_workqueue("omapdrm", 0); + if (!priv->wq) { + ret = -ENOMEM; + goto err_alloc_workqueue; + } mutex_init(&priv->list_lock); INIT_LIST_HEAD(&priv->obj_list); @@ -754,6 +757,7 @@ static int omapdrm_init(struct omap_drm_private *priv, struct device *dev) drm_mode_config_cleanup(ddev); omap_gem_deinit(ddev); destroy_workqueue(priv->wq); +err_alloc_workqueue: omap_disconnect_pipelines(ddev); drm_dev_put(ddev); return ret; diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c index 6b08b137af1ad8..523be34682caf1 100644 --- a/drivers/gpu/drm/omapdrm/omap_fbdev.c +++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c @@ -51,6 +51,10 @@ static void pan_worker(struct work_struct *work) omap_gem_roll(bo, fbi->var.yoffset * npages); } +FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(omap_fbdev, + drm_fb_helper_damage_range, + drm_fb_helper_damage_area) + static int omap_fbdev_pan_display(struct fb_var_screeninfo *var, struct fb_info *fbi) { @@ -78,11 +82,9 @@ static int omap_fbdev_pan_display(struct fb_var_screeninfo *var, static int omap_fbdev_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) { - struct drm_fb_helper *helper = info->par; - struct drm_framebuffer *fb = helper->fb; - struct drm_gem_object *bo = drm_gem_fb_get_obj(fb, 0); + vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); - return drm_gem_mmap_obj(bo, omap_gem_mmap_size(bo), vma); + return fb_deferred_io_mmap(info, vma); } static void omap_fbdev_fb_destroy(struct fb_info *info) @@ -94,6 +96,7 @@ static void omap_fbdev_fb_destroy(struct fb_info *info) DBG(); + fb_deferred_io_cleanup(info); drm_fb_helper_fini(helper); omap_gem_unpin(bo); @@ -104,15 +107,19 @@ static void omap_fbdev_fb_destroy(struct fb_info *info) kfree(fbdev); } +/* + * For now, we cannot use FB_DEFAULT_DEFERRED_OPS and fb_deferred_io_mmap() + * because we use write-combine. + */ static const struct fb_ops omap_fb_ops = { .owner = THIS_MODULE, - __FB_DEFAULT_DMAMEM_OPS_RDWR, + __FB_DEFAULT_DEFERRED_OPS_RDWR(omap_fbdev), .fb_check_var = drm_fb_helper_check_var, .fb_set_par = drm_fb_helper_set_par, .fb_setcmap = drm_fb_helper_setcmap, .fb_blank = drm_fb_helper_blank, .fb_pan_display = omap_fbdev_pan_display, - __FB_DEFAULT_DMAMEM_OPS_DRAW, + __FB_DEFAULT_DEFERRED_OPS_DRAW(omap_fbdev), .fb_ioctl = drm_fb_helper_ioctl, .fb_mmap = omap_fbdev_fb_mmap, .fb_destroy = omap_fbdev_fb_destroy, @@ -213,6 +220,15 @@ static int omap_fbdev_create(struct drm_fb_helper *helper, fbi->fix.smem_start = dma_addr; fbi->fix.smem_len = bo->size; + /* deferred I/O */ + helper->fbdefio.delay = HZ / 20; + helper->fbdefio.deferred_io = drm_fb_helper_deferred_io; + + fbi->fbdefio = &helper->fbdefio; + ret = fb_deferred_io_init(fbi); + if (ret) + goto fail; + /* if we have DMM, then we can use it for scrolling by just * shuffling pages around in DMM rather than doing sw blit. */ @@ -238,8 +254,20 @@ static int omap_fbdev_create(struct drm_fb_helper *helper, return ret; } +static int omap_fbdev_dirty(struct drm_fb_helper *helper, struct drm_clip_rect *clip) +{ + if (!(clip->x1 < clip->x2 && clip->y1 < clip->y2)) + return 0; + + if (helper->fb->funcs->dirty) + return helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, clip, 1); + + return 0; +} + static const struct drm_fb_helper_funcs omap_fb_helper_funcs = { .fb_probe = omap_fbdev_create, + .fb_dirty = omap_fbdev_dirty, }; static struct drm_fb_helper *get_fb(struct fb_info *fbi) diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index 869e535faefa38..3a2f4a9f1d4665 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -184,7 +184,7 @@ config DRM_PANEL_ILITEK_IL9322 config DRM_PANEL_ILITEK_ILI9341 tristate "Ilitek ILI9341 240x320 QVGA panels" - depends on OF && SPI + depends on SPI select DRM_KMS_HELPER select DRM_GEM_DMA_HELPER depends on BACKLIGHT_CLASS_DEVICE diff --git a/drivers/gpu/drm/panel/panel-arm-versatile.c b/drivers/gpu/drm/panel/panel-arm-versatile.c index abb0788843c60c..503ecea72c5eac 100644 --- a/drivers/gpu/drm/panel/panel-arm-versatile.c +++ b/drivers/gpu/drm/panel/panel-arm-versatile.c @@ -267,6 +267,8 @@ static int versatile_panel_get_modes(struct drm_panel *panel, connector->display_info.bus_flags = vpanel->panel_type->bus_flags; mode = drm_mode_duplicate(connector->dev, &vpanel->panel_type->mode); + if (!mode) + return -ENOMEM; drm_mode_set_name(mode); mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index c9087f474cbc5a..e6328991c87e93 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -1847,7 +1847,11 @@ static int boe_panel_prepare(struct drm_panel *panel) usleep_range(10000, 11000); if (boe->desc->lp11_before_reset) { - mipi_dsi_dcs_nop(boe->dsi); + ret = mipi_dsi_dcs_nop(boe->dsi); + if (ret < 0) { + dev_err(&boe->dsi->dev, "Failed to send NOP: %d\n", ret); + goto poweroff; + } usleep_range(1000, 2000); } gpiod_set_value(boe->enable_gpio, 1); @@ -1868,13 +1872,13 @@ static int boe_panel_prepare(struct drm_panel *panel) return 0; poweroff: + gpiod_set_value(boe->enable_gpio, 0); regulator_disable(boe->avee); poweroffavdd: regulator_disable(boe->avdd); poweroff1v8: usleep_range(5000, 7000); regulator_disable(boe->pp1800); - gpiod_set_value(boe->enable_gpio, 0); return ret; } @@ -2049,6 +2053,7 @@ static const struct panel_desc auo_b101uan08_3_desc = { .mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE | MIPI_DSI_MODE_LPM, .init_cmds = auo_b101uan08_3_init_cmd, + .lp11_before_reset = true, }; static const struct drm_display_mode boe_tv105wum_nw0_default_mode = { @@ -2103,14 +2108,15 @@ static const struct panel_desc starry_qfh032011_53g_desc = { .mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE | MIPI_DSI_MODE_LPM, .init_cmds = starry_qfh032011_53g_init_cmd, + .lp11_before_reset = true, }; static const struct drm_display_mode starry_himax83102_j02_default_mode = { - .clock = 161600, + .clock = 162680, .hdisplay = 1200, - .hsync_start = 1200 + 40, - .hsync_end = 1200 + 40 + 20, - .htotal = 1200 + 40 + 20 + 40, + .hsync_start = 1200 + 60, + .hsync_end = 1200 + 60 + 20, + .htotal = 1200 + 60 + 20 + 40, .vdisplay = 1920, .vsync_start = 1920 + 116, .vsync_end = 1920 + 116 + 8, @@ -2237,6 +2243,8 @@ static int boe_panel_add(struct boe_panel *boe) gpiod_set_value(boe->enable_gpio, 0); + boe->base.prepare_prev_first = true; + drm_panel_init(&boe->base, dev, &boe_panel_funcs, DRM_MODE_CONNECTOR_DSI); err = of_drm_get_panel_orientation(dev->of_node, &boe->orientation); diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index 95c8472d878a99..94fe2f3836a9a3 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -203,6 +203,9 @@ struct edp_panel_entry { /** @name: Name of this panel (for printing to logs). */ const char *name; + + /** @override_edid_mode: Override the mode obtained by edid. */ + const struct drm_display_mode *override_edid_mode; }; struct panel_edp { @@ -301,6 +304,24 @@ static unsigned int panel_edp_get_display_modes(struct panel_edp *panel, return num; } +static int panel_edp_override_edid_mode(struct panel_edp *panel, + struct drm_connector *connector, + const struct drm_display_mode *override_mode) +{ + struct drm_display_mode *mode; + + mode = drm_mode_duplicate(connector->dev, override_mode); + if (!mode) { + dev_err(panel->base.dev, "failed to add additional mode\n"); + return 0; + } + + mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; + drm_mode_set_name(mode); + drm_mode_probed_add(connector, mode); + return 1; +} + static int panel_edp_get_non_edid_modes(struct panel_edp *panel, struct drm_connector *connector) { @@ -376,6 +397,7 @@ static int panel_edp_suspend(struct device *dev) { struct panel_edp *p = dev_get_drvdata(dev); + drm_dp_dpcd_set_powered(p->aux, false); gpiod_set_value_cansleep(p->enable_gpio, 0); regulator_disable(p->supply); p->unprepared_time = ktime_get_boottime(); @@ -392,8 +414,7 @@ static int panel_edp_unprepare(struct drm_panel *panel) if (!p->prepared) return 0; - pm_runtime_mark_last_busy(panel->dev); - ret = pm_runtime_put_autosuspend(panel->dev); + ret = pm_runtime_put_sync_suspend(panel->dev); if (ret < 0) return ret; p->prepared = false; @@ -433,6 +454,7 @@ static int panel_edp_prepare_once(struct panel_edp *p) } gpiod_set_value_cansleep(p->enable_gpio, 1); + drm_dp_dpcd_set_powered(p->aux, true); delay = p->desc->delay.hpd_reliable; if (p->no_hpd) @@ -469,6 +491,7 @@ static int panel_edp_prepare_once(struct panel_edp *p) return 0; error: + drm_dp_dpcd_set_powered(p->aux, false); gpiod_set_value_cansleep(p->enable_gpio, 0); regulator_disable(p->supply); p->unprepared_time = ktime_get_boottime(); @@ -568,6 +591,9 @@ static int panel_edp_get_modes(struct drm_panel *panel, { struct panel_edp *p = to_panel_edp(panel); int num = 0; + bool has_override_edid_mode = p->detected_panel && + p->detected_panel != ERR_PTR(-EINVAL) && + p->detected_panel->override_edid_mode; /* probe EDID if a DDC bus is available */ if (p->ddc) { @@ -575,9 +601,18 @@ static int panel_edp_get_modes(struct drm_panel *panel, if (!p->edid) p->edid = drm_get_edid(connector, p->ddc); - - if (p->edid) - num += drm_add_edid_modes(connector, p->edid); + if (p->edid) { + if (has_override_edid_mode) { + /* + * override_edid_mode is specified. Use + * override_edid_mode instead of from edid. + */ + num += panel_edp_override_edid_mode(p, connector, + p->detected_panel->override_edid_mode); + } else { + num += drm_add_edid_modes(connector, p->edid); + } + } pm_runtime_mark_last_busy(panel->dev); pm_runtime_put_autosuspend(panel->dev); @@ -973,6 +1008,8 @@ static const struct panel_desc auo_b116xak01 = { }, .delay = { .hpd_absent = 200, + .unprepare = 500, + .enable = 50, }, }; @@ -1828,6 +1865,15 @@ static const struct panel_delay delay_200_500_e200 = { .delay = _delay \ } +#define EDP_PANEL_ENTRY2(vend_chr_0, vend_chr_1, vend_chr_2, product_id, _delay, _name, _mode) \ +{ \ + .name = _name, \ + .panel_id = drm_edid_encode_panel_id(vend_chr_0, vend_chr_1, vend_chr_2, \ + product_id), \ + .delay = _delay, \ + .override_edid_mode = _mode \ +} + /* * This table is used to figure out power sequencing delays for panels that * are detected by EDID. Entries here may point to entries in the @@ -1840,7 +1886,8 @@ static const struct edp_panel_entry edp_panels[] = { EDP_PANEL_ENTRY('A', 'U', 'O', 0x145c, &delay_200_500_e50, "B116XAB01.4"), EDP_PANEL_ENTRY('A', 'U', 'O', 0x1e9b, &delay_200_500_e50, "B133UAN02.1"), EDP_PANEL_ENTRY('A', 'U', 'O', 0x1ea5, &delay_200_500_e50, "B116XAK01.6"), - EDP_PANEL_ENTRY('A', 'U', 'O', 0x405c, &auo_b116xak01.delay, "B116XAK01"), + EDP_PANEL_ENTRY('A', 'U', 'O', 0x235c, &delay_200_500_e50, "B116XTN02.3"), + EDP_PANEL_ENTRY('A', 'U', 'O', 0x405c, &auo_b116xak01.delay, "B116XAK01.0"), EDP_PANEL_ENTRY('A', 'U', 'O', 0x582d, &delay_200_500_e50, "B133UAN01.0"), EDP_PANEL_ENTRY('A', 'U', 'O', 0x615c, &delay_200_500_e50, "B116XAN06.1"), EDP_PANEL_ENTRY('A', 'U', 'O', 0x8594, &delay_200_500_e50, "B133UAN01.0"), @@ -1848,8 +1895,10 @@ static const struct edp_panel_entry edp_panels[] = { EDP_PANEL_ENTRY('B', 'O', 'E', 0x0786, &delay_200_500_p2e80, "NV116WHM-T01"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x07d1, &boe_nv133fhm_n61.delay, "NV133FHM-N61"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x082d, &boe_nv133fhm_n61.delay, "NV133FHM-N62"), + EDP_PANEL_ENTRY('B', 'O', 'E', 0x09c3, &delay_200_500_e50, "NT116WHM-N21,836X2"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x094b, &delay_200_500_e50, "NT116WHM-N21"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x095f, &delay_200_500_e50, "NE135FBM-N41 v8.1"), + EDP_PANEL_ENTRY('B', 'O', 'E', 0x0979, &delay_200_500_e50, "NV116WHM-N49 V8.0"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x098d, &boe_nv110wtm_n61.delay, "NV110WTM-N61"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x09dd, &delay_200_500_e50, "NT116WHM-N21"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x0a5d, &delay_200_500_e50, "NV116WHM-N45"), diff --git a/drivers/gpu/drm/panel/panel-elida-kd35t133.c b/drivers/gpu/drm/panel/panel-elida-kd35t133.c index e7be15b681021e..6de11723234644 100644 --- a/drivers/gpu/drm/panel/panel-elida-kd35t133.c +++ b/drivers/gpu/drm/panel/panel-elida-kd35t133.c @@ -104,6 +104,8 @@ static int kd35t133_unprepare(struct drm_panel *panel) return ret; } + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + regulator_disable(ctx->iovcc); regulator_disable(ctx->vdd); diff --git a/drivers/gpu/drm/panel/panel-himax-hx8394.c b/drivers/gpu/drm/panel/panel-himax-hx8394.c index c73243d85de718..631420d28be4c9 100644 --- a/drivers/gpu/drm/panel/panel-himax-hx8394.c +++ b/drivers/gpu/drm/panel/panel-himax-hx8394.c @@ -234,8 +234,7 @@ static int hx8394_enable(struct drm_panel *panel) sleep_in: /* This will probably fail, but let's try orderly power off anyway. */ - ret = mipi_dsi_dcs_enter_sleep_mode(dsi); - if (!ret) + if (!mipi_dsi_dcs_enter_sleep_mode(dsi)) msleep(50); return ret; diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c index 3574681891e816..b933380b7eb783 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c @@ -22,8 +22,9 @@ #include #include #include +#include #include -#include +#include #include #include @@ -421,7 +422,7 @@ static int ili9341_dpi_prepare(struct drm_panel *panel) ili9341_dpi_init(ili); - return ret; + return 0; } static int ili9341_dpi_enable(struct drm_panel *panel) @@ -691,7 +692,7 @@ static int ili9341_dpi_probe(struct spi_device *spi, struct gpio_desc *dc, * Every new incarnation of this display must have a unique * data entry for the system in this driver. */ - ili->conf = of_device_get_match_data(dev); + ili->conf = device_get_match_data(dev); if (!ili->conf) { dev_err(dev, "missing device configuration\n"); return -ENODEV; @@ -714,18 +715,18 @@ static int ili9341_probe(struct spi_device *spi) reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(reset)) - dev_err(dev, "Failed to get gpio 'reset'\n"); + return dev_err_probe(dev, PTR_ERR(reset), "Failed to get gpio 'reset'\n"); dc = devm_gpiod_get_optional(dev, "dc", GPIOD_OUT_LOW); if (IS_ERR(dc)) - dev_err(dev, "Failed to get gpio 'dc'\n"); + return dev_err_probe(dev, PTR_ERR(dc), "Failed to get gpio 'dc'\n"); if (!strcmp(id->name, "sf-tc240t-9370-t")) return ili9341_dpi_probe(spi, dc, reset); else if (!strcmp(id->name, "yx240qv29")) return ili9341_dbi_probe(spi, dc, reset); - return -1; + return -ENODEV; } static void ili9341_remove(struct spi_device *spi) diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c index 7838947a1bf3c9..bb201f848ae97a 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c @@ -883,10 +883,10 @@ static int ili9881c_prepare(struct drm_panel *panel) msleep(5); /* And reset it */ - gpiod_set_value(ctx->reset, 1); + gpiod_set_value_cansleep(ctx->reset, 1); msleep(20); - gpiod_set_value(ctx->reset, 0); + gpiod_set_value_cansleep(ctx->reset, 0); msleep(20); for (i = 0; i < ctx->desc->init_length; i++) { @@ -941,7 +941,7 @@ static int ili9881c_unprepare(struct drm_panel *panel) mipi_dsi_dcs_enter_sleep_mode(ctx->dsi); regulator_disable(ctx->power); - gpiod_set_value(ctx->reset, 1); + gpiod_set_value_cansleep(ctx->reset, 1); return 0; } diff --git a/drivers/gpu/drm/panel/panel-newvision-nv3051d.c b/drivers/gpu/drm/panel/panel-newvision-nv3051d.c index ad98dd9322b4a3..227937afe2572e 100644 --- a/drivers/gpu/drm/panel/panel-newvision-nv3051d.c +++ b/drivers/gpu/drm/panel/panel-newvision-nv3051d.c @@ -261,6 +261,8 @@ static int panel_nv3051d_unprepare(struct drm_panel *panel) usleep_range(10000, 15000); + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + regulator_disable(ctx->vdd); return 0; diff --git a/drivers/gpu/drm/panel/panel-novatek-nt35950.c b/drivers/gpu/drm/panel/panel-novatek-nt35950.c index 412ca84d058110..4be5013330ec27 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt35950.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt35950.c @@ -565,10 +565,8 @@ static int nt35950_probe(struct mipi_dsi_device *dsi) } dsi_r_host = of_find_mipi_dsi_host_by_node(dsi_r); of_node_put(dsi_r); - if (!dsi_r_host) { - dev_err(dev, "Cannot get secondary DSI host\n"); - return -EPROBE_DEFER; - } + if (!dsi_r_host) + return dev_err_probe(dev, -EPROBE_DEFER, "Cannot get secondary DSI host\n"); nt->dsi[1] = mipi_dsi_device_register_full(dsi_r_host, info); if (!nt->dsi[1]) { diff --git a/drivers/gpu/drm/panel/panel-novatek-nt36523.c b/drivers/gpu/drm/panel/panel-novatek-nt36523.c index 9632b9e95b7159..aab8937595a2a0 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt36523.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt36523.c @@ -935,8 +935,7 @@ static int j606f_boe_init_sequence(struct panel_info *pinfo) static const struct drm_display_mode elish_boe_modes[] = { { - /* There is only one 120 Hz timing, but it doesn't work perfectly, 104 Hz preferred */ - .clock = (1600 + 60 + 8 + 60) * (2560 + 26 + 4 + 168) * 104 / 1000, + .clock = (1600 + 60 + 8 + 60) * (2560 + 26 + 4 + 168) * 120 / 1000, .hdisplay = 1600, .hsync_start = 1600 + 60, .hsync_end = 1600 + 60 + 8, @@ -950,8 +949,7 @@ static const struct drm_display_mode elish_boe_modes[] = { static const struct drm_display_mode elish_csot_modes[] = { { - /* There is only one 120 Hz timing, but it doesn't work perfectly, 104 Hz preferred */ - .clock = (1600 + 200 + 40 + 52) * (2560 + 26 + 4 + 168) * 104 / 1000, + .clock = (1600 + 200 + 40 + 52) * (2560 + 26 + 4 + 168) * 120 / 1000, .hdisplay = 1600, .hsync_start = 1600 + 200, .hsync_end = 1600 + 200 + 40, @@ -1266,9 +1264,9 @@ static int nt36523_probe(struct mipi_dsi_device *dsi) return dev_err_probe(dev, -EPROBE_DEFER, "cannot get secondary DSI host\n"); pinfo->dsi[1] = mipi_dsi_device_register_full(dsi1_host, info); - if (!pinfo->dsi[1]) { + if (IS_ERR(pinfo->dsi[1])) { dev_err(dev, "cannot get secondary DSI device\n"); - return -ENODEV; + return PTR_ERR(pinfo->dsi[1]); } } diff --git a/drivers/gpu/drm/panel/panel-samsung-atna33xc20.c b/drivers/gpu/drm/panel/panel-samsung-atna33xc20.c index 5703f4712d96e5..9c336c71562b93 100644 --- a/drivers/gpu/drm/panel/panel-samsung-atna33xc20.c +++ b/drivers/gpu/drm/panel/panel-samsung-atna33xc20.c @@ -72,6 +72,7 @@ static int atana33xc20_suspend(struct device *dev) if (p->el3_was_on) atana33xc20_wait(p->el_on3_off_time, 150); + drm_dp_dpcd_set_powered(p->aux, false); ret = regulator_disable(p->supply); if (ret) return ret; @@ -93,6 +94,7 @@ static int atana33xc20_resume(struct device *dev) ret = regulator_enable(p->supply); if (ret) return ret; + drm_dp_dpcd_set_powered(p->aux, true); p->powered_on_time = ktime_get_boottime(); if (p->no_hpd) { @@ -107,19 +109,17 @@ static int atana33xc20_resume(struct device *dev) if (hpd_asserted < 0) ret = hpd_asserted; - if (ret) + if (ret) { dev_warn(dev, "Error waiting for HPD GPIO: %d\n", ret); - - return ret; - } - - if (p->aux->wait_hpd_asserted) { + goto error; + } + } else if (p->aux->wait_hpd_asserted) { ret = p->aux->wait_hpd_asserted(p->aux, HPD_MAX_US); - if (ret) + if (ret) { dev_warn(dev, "Controller error waiting for HPD: %d\n", ret); - - return ret; + goto error; + } } /* @@ -131,6 +131,12 @@ static int atana33xc20_resume(struct device *dev) * right times. */ return 0; + +error: + drm_dp_dpcd_set_powered(p->aux, false); + regulator_disable(p->supply); + + return ret; } static int atana33xc20_disable(struct drm_panel *panel) diff --git a/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c b/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c index ea5a857793827a..f23d8832a1ad05 100644 --- a/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c +++ b/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c @@ -309,7 +309,7 @@ static const struct s6d7aa0_panel_desc s6d7aa0_lsl080al02_desc = { .off_func = s6d7aa0_lsl080al02_off, .drm_mode = &s6d7aa0_lsl080al02_mode, .mode_flags = MIPI_DSI_MODE_VSYNC_FLUSH | MIPI_DSI_MODE_VIDEO_NO_HFP, - .bus_flags = DRM_BUS_FLAG_DE_HIGH, + .bus_flags = 0, .has_backlight = false, .use_passwd3 = false, diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index dd7928d9570f72..11ade6bac592f7 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2326,13 +2326,13 @@ static const struct panel_desc innolux_g070y2_t02 = { static const struct display_timing innolux_g101ice_l01_timing = { .pixelclock = { 60400000, 71100000, 74700000 }, .hactive = { 1280, 1280, 1280 }, - .hfront_porch = { 41, 80, 100 }, - .hback_porch = { 40, 79, 99 }, - .hsync_len = { 1, 1, 1 }, + .hfront_porch = { 30, 60, 70 }, + .hback_porch = { 30, 60, 70 }, + .hsync_len = { 22, 40, 60 }, .vactive = { 800, 800, 800 }, - .vfront_porch = { 5, 11, 14 }, - .vback_porch = { 4, 11, 14 }, - .vsync_len = { 1, 1, 1 }, + .vfront_porch = { 3, 8, 14 }, + .vback_porch = { 3, 8, 14 }, + .vsync_len = { 4, 7, 12 }, .flags = DISPLAY_FLAGS_DE_HIGH, }; @@ -2349,6 +2349,7 @@ static const struct panel_desc innolux_g101ice_l01 = { .disable = 200, }, .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, .connector_type = DRM_MODE_CONNECTOR_LVDS, }; @@ -2406,6 +2407,9 @@ static const struct panel_desc innolux_g121x1_l03 = { .unprepare = 200, .disable = 400, }, + .bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, + .connector_type = DRM_MODE_CONNECTOR_LVDS, }; static const struct display_timing innolux_g156hce_l01_timings = { @@ -2519,6 +2523,7 @@ static const struct display_timing koe_tx26d202vm0bwa_timing = { .vfront_porch = { 3, 5, 10 }, .vback_porch = { 2, 5, 10 }, .vsync_len = { 5, 5, 5 }, + .flags = DISPLAY_FLAGS_DE_HIGH, }; static const struct panel_desc koe_tx26d202vm0bwa = { @@ -3781,6 +3786,7 @@ static const struct panel_desc tianma_tm070jdhg30 = { }, .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, .connector_type = DRM_MODE_CONNECTOR_LVDS, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, }; static const struct panel_desc tianma_tm070jvhg33 = { @@ -3793,6 +3799,7 @@ static const struct panel_desc tianma_tm070jvhg33 = { }, .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, .connector_type = DRM_MODE_CONNECTOR_LVDS, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, }; static const struct display_timing tianma_tm070rvhg71_timing = { diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7701.c b/drivers/gpu/drm/panel/panel-sitronix-st7701.c index 0459965e1b4f7b..036ac403ed2138 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7701.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7701.c @@ -288,7 +288,7 @@ static void st7701_init_sequence(struct st7701 *st7701) FIELD_PREP(DSI_CMD2_BK1_PWRCTRL2_AVDD_MASK, DIV_ROUND_CLOSEST(desc->avdd_mv - 6200, 200)) | FIELD_PREP(DSI_CMD2_BK1_PWRCTRL2_AVCL_MASK, - DIV_ROUND_CLOSEST(-4400 + desc->avcl_mv, 200))); + DIV_ROUND_CLOSEST(-4400 - desc->avcl_mv, 200))); /* T2D = 0.2us * T2D[3:0] */ ST7701_DSI(st7701, DSI_CMD2_BK1_SPD1, diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7703.c b/drivers/gpu/drm/panel/panel-sitronix-st7703.c index 6a394563953501..7bb723d445ade4 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7703.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7703.c @@ -506,29 +506,30 @@ static int st7703_prepare(struct drm_panel *panel) return 0; dev_dbg(ctx->dev, "Resetting the panel\n"); - ret = regulator_enable(ctx->vcc); + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + + ret = regulator_enable(ctx->iovcc); if (ret < 0) { - dev_err(ctx->dev, "Failed to enable vcc supply: %d\n", ret); + dev_err(ctx->dev, "Failed to enable iovcc supply: %d\n", ret); return ret; } - ret = regulator_enable(ctx->iovcc); + + ret = regulator_enable(ctx->vcc); if (ret < 0) { - dev_err(ctx->dev, "Failed to enable iovcc supply: %d\n", ret); - goto disable_vcc; + dev_err(ctx->dev, "Failed to enable vcc supply: %d\n", ret); + regulator_disable(ctx->iovcc); + return ret; } - gpiod_set_value_cansleep(ctx->reset_gpio, 1); - usleep_range(20, 40); + /* Give power supplies time to stabilize before deasserting reset. */ + usleep_range(10000, 20000); + gpiod_set_value_cansleep(ctx->reset_gpio, 0); - msleep(20); + usleep_range(15000, 20000); ctx->prepared = true; return 0; - -disable_vcc: - regulator_disable(ctx->vcc); - return ret; } static const u32 mantix_bus_formats[] = { diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c index 88e80fe98112da..28bfc48a912729 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c @@ -282,15 +282,15 @@ static const struct drm_display_mode et028013dma_mode = { static const struct drm_display_mode jt240mhqs_hwt_ek_e3_mode = { .clock = 6000, .hdisplay = 240, - .hsync_start = 240 + 28, - .hsync_end = 240 + 28 + 10, - .htotal = 240 + 28 + 10 + 10, + .hsync_start = 240 + 38, + .hsync_end = 240 + 38 + 10, + .htotal = 240 + 38 + 10 + 10, .vdisplay = 280, - .vsync_start = 280 + 8, - .vsync_end = 280 + 8 + 4, - .vtotal = 280 + 8 + 4 + 4, - .width_mm = 43, - .height_mm = 37, + .vsync_start = 280 + 48, + .vsync_end = 280 + 48 + 4, + .vtotal = 280 + 48 + 4 + 4, + .width_mm = 37, + .height_mm = 43, .flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC, }; @@ -643,7 +643,9 @@ static int st7789v_probe(struct spi_device *spi) if (ret) return dev_err_probe(dev, ret, "Failed to get backlight\n"); - of_drm_get_panel_orientation(spi->dev.of_node, &ctx->orientation); + ret = of_drm_get_panel_orientation(spi->dev.of_node, &ctx->orientation); + if (ret) + return dev_err_probe(&spi->dev, ret, "Failed to get orientation\n"); drm_panel_add(&ctx->panel); diff --git a/drivers/gpu/drm/panel/panel-tpo-tpg110.c b/drivers/gpu/drm/panel/panel-tpo-tpg110.c index 845304435e2356..f6a212e542cb93 100644 --- a/drivers/gpu/drm/panel/panel-tpo-tpg110.c +++ b/drivers/gpu/drm/panel/panel-tpo-tpg110.c @@ -379,6 +379,8 @@ static int tpg110_get_modes(struct drm_panel *panel, connector->display_info.bus_flags = tpg->panel_mode->bus_flags; mode = drm_mode_duplicate(connector->dev, &tpg->panel_mode->mode); + if (!mode) + return -ENOMEM; drm_mode_set_name(mode); mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; diff --git a/drivers/gpu/drm/panel/panel-visionox-rm69299.c b/drivers/gpu/drm/panel/panel-visionox-rm69299.c index c2806e4fd553b1..6e946e5a036eeb 100644 --- a/drivers/gpu/drm/panel/panel-visionox-rm69299.c +++ b/drivers/gpu/drm/panel/panel-visionox-rm69299.c @@ -261,8 +261,6 @@ static void visionox_rm69299_remove(struct mipi_dsi_device *dsi) struct visionox_rm69299 *ctx = mipi_dsi_get_drvdata(dsi); mipi_dsi_detach(ctx->dsi); - mipi_dsi_device_unregister(ctx->dsi); - drm_panel_remove(&ctx->panel); } diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index a2ab99698ca80a..ddcc8259061bbd 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -731,3 +731,4 @@ module_platform_driver(panfrost_driver); MODULE_AUTHOR("Panfrost Project Developers"); MODULE_DESCRIPTION("Panfrost DRM Driver"); MODULE_LICENSE("GPL v2"); +MODULE_SOFTDEP("pre: governor_simpleondemand"); diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c index d28b99732ddeb6..c067ff550692ad 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gpu.c +++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c @@ -71,7 +71,12 @@ int panfrost_gpu_soft_reset(struct panfrost_device *pfdev) } gpu_write(pfdev, GPU_INT_CLEAR, GPU_IRQ_MASK_ALL); - gpu_write(pfdev, GPU_INT_MASK, GPU_IRQ_MASK_ALL); + + /* Only enable the interrupts we care about */ + gpu_write(pfdev, GPU_INT_MASK, + GPU_IRQ_MASK_ERROR | + GPU_IRQ_PERFCNT_SAMPLE_COMPLETED | + GPU_IRQ_CLEAN_CACHES_COMPLETED); return 0; } @@ -321,28 +326,38 @@ static void panfrost_gpu_init_features(struct panfrost_device *pfdev) pfdev->features.shader_present, pfdev->features.l2_present); } +static u64 panfrost_get_core_mask(struct panfrost_device *pfdev) +{ + u64 core_mask; + + if (pfdev->features.l2_present == 1) + return U64_MAX; + + /* + * Only support one core group now. + * ~(l2_present - 1) unsets all bits in l2_present except + * the bottom bit. (l2_present - 2) has all the bits in + * the first core group set. AND them together to generate + * a mask of cores in the first core group. + */ + core_mask = ~(pfdev->features.l2_present - 1) & + (pfdev->features.l2_present - 2); + dev_info_once(pfdev->dev, "using only 1st core group (%lu cores from %lu)\n", + hweight64(core_mask), + hweight64(pfdev->features.shader_present)); + + return core_mask; +} + void panfrost_gpu_power_on(struct panfrost_device *pfdev) { int ret; u32 val; - u64 core_mask = U64_MAX; + u64 core_mask; panfrost_gpu_init_quirks(pfdev); + core_mask = panfrost_get_core_mask(pfdev); - if (pfdev->features.l2_present != 1) { - /* - * Only support one core group now. - * ~(l2_present - 1) unsets all bits in l2_present except - * the bottom bit. (l2_present - 2) has all the bits in - * the first core group set. AND them together to generate - * a mask of cores in the first core group. - */ - core_mask = ~(pfdev->features.l2_present - 1) & - (pfdev->features.l2_present - 2); - dev_info_once(pfdev->dev, "using only 1st core group (%lu cores from %lu)\n", - hweight64(core_mask), - hweight64(pfdev->features.shader_present)); - } gpu_write(pfdev, L2_PWRON_LO, pfdev->features.l2_present & core_mask); ret = readl_relaxed_poll_timeout(pfdev->iomem + L2_READY_LO, val, val == (pfdev->features.l2_present & core_mask), @@ -367,9 +382,26 @@ void panfrost_gpu_power_on(struct panfrost_device *pfdev) void panfrost_gpu_power_off(struct panfrost_device *pfdev) { - gpu_write(pfdev, TILER_PWROFF_LO, 0); - gpu_write(pfdev, SHADER_PWROFF_LO, 0); - gpu_write(pfdev, L2_PWROFF_LO, 0); + int ret; + u32 val; + + gpu_write(pfdev, SHADER_PWROFF_LO, pfdev->features.shader_present); + ret = readl_relaxed_poll_timeout(pfdev->iomem + SHADER_PWRTRANS_LO, + val, !val, 1, 2000); + if (ret) + dev_err(pfdev->dev, "shader power transition timeout"); + + gpu_write(pfdev, TILER_PWROFF_LO, pfdev->features.tiler_present); + ret = readl_relaxed_poll_timeout(pfdev->iomem + TILER_PWRTRANS_LO, + val, !val, 1, 2000); + if (ret) + dev_err(pfdev->dev, "tiler power transition timeout"); + + gpu_write(pfdev, L2_PWROFF_LO, pfdev->features.l2_present); + ret = readl_poll_timeout(pfdev->iomem + L2_PWRTRANS_LO, + val, !val, 0, 2000); + if (ret) + dev_err(pfdev->dev, "l2 power transition timeout"); } int panfrost_gpu_init(struct panfrost_device *pfdev) diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index c0123d09f699c7..83fa384f6a24ce 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -500,11 +500,18 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, mapping_set_unevictable(mapping); for (i = page_offset; i < page_offset + NUM_FAULT_PAGES; i++) { + /* Can happen if the last fault only partially filled this + * section of the pages array before failing. In that case + * we skip already filled pages. + */ + if (pages[i]) + continue; + pages[i] = shmem_read_mapping_page(mapping, i); if (IS_ERR(pages[i])) { ret = PTR_ERR(pages[i]); pages[i] = NULL; - goto err_pages; + goto err_unlock; } } @@ -512,7 +519,7 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, ret = sg_alloc_table_from_pages(sgt, pages + page_offset, NUM_FAULT_PAGES, 0, SZ_2M, GFP_KERNEL); if (ret) - goto err_pages; + goto err_unlock; ret = dma_map_sgtable(pfdev->dev, sgt, DMA_BIDIRECTIONAL, 0); if (ret) @@ -534,8 +541,6 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, err_map: sg_free_table(sgt); -err_pages: - drm_gem_shmem_put_pages(&bo->base); err_unlock: dma_resv_unlock(obj->resv); err_bo: diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c index ba3b5b5f0cdfe4..02e6b74d501669 100644 --- a/drivers/gpu/drm/pl111/pl111_drv.c +++ b/drivers/gpu/drm/pl111/pl111_drv.c @@ -323,12 +323,18 @@ static void pl111_amba_remove(struct amba_device *amba_dev) struct pl111_drm_dev_private *priv = drm->dev_private; drm_dev_unregister(drm); + drm_atomic_helper_shutdown(drm); if (priv->panel) drm_panel_bridge_remove(priv->bridge); drm_dev_put(drm); of_reserved_mem_device_release(dev); } +static void pl111_amba_shutdown(struct amba_device *amba_dev) +{ + drm_atomic_helper_shutdown(amba_get_drvdata(amba_dev)); +} + /* * This early variant lacks the 565 and 444 pixel formats. */ @@ -431,6 +437,7 @@ static struct amba_driver pl111_amba_driver __maybe_unused = { }, .probe = pl111_amba_probe, .remove = pl111_amba_remove, + .shutdown = pl111_amba_shutdown, .id_table = pl111_id_table, }; diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 6492a70e3c396a..8ee614be9adf36 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -236,6 +236,9 @@ static int qxl_add_mode(struct drm_connector *connector, return 0; mode = drm_cvt_mode(dev, width, height, 60, false, false, false); + if (!mode) + return 0; + if (preferred) mode->type |= DRM_MODE_TYPE_PREFERRED; mode->hdisplay = width; @@ -1229,6 +1232,9 @@ int qxl_destroy_monitors_object(struct qxl_device *qdev) if (!qdev->monitors_config_bo) return 0; + kfree(qdev->dumb_heads); + qdev->dumb_heads = NULL; + qdev->monitors_config = NULL; qdev->ram_header->monitors_config = 0; diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c index b30ede1cf62d32..91930e84a9cd26 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.c +++ b/drivers/gpu/drm/qxl/qxl_drv.c @@ -283,7 +283,7 @@ static const struct drm_ioctl_desc qxl_ioctls[] = { }; static struct drm_driver qxl_driver = { - .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, + .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_CURSOR_HOTSPOT, .dumb_create = qxl_mode_dumb_create, .dumb_map_offset = drm_gem_ttm_dumb_map_offset, diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 4f06356d9ce2e1..f0ae087be914ee 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -4821,14 +4821,15 @@ int evergreen_irq_process(struct radeon_device *rdev) break; case 44: /* hdmi */ afmt_idx = src_data; - if (!(afmt_status[afmt_idx] & AFMT_AZ_FORMAT_WTRIG)) - DRM_DEBUG("IH: IH event w/o asserted irq bit?\n"); - if (afmt_idx > 5) { DRM_ERROR("Unhandled interrupt: %d %d\n", src_id, src_data); break; } + + if (!(afmt_status[afmt_idx] & AFMT_AZ_FORMAT_WTRIG)) + DRM_DEBUG("IH: IH event w/o asserted irq bit?\n"); + afmt_status[afmt_idx] &= ~AFMT_AZ_FORMAT_WTRIG; queue_hdmi = true; DRM_DEBUG("IH: HDMI%d\n", afmt_idx + 1); diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c index 0de79f3a7e3ffc..820c2c3641d388 100644 --- a/drivers/gpu/drm/radeon/evergreen_cs.c +++ b/drivers/gpu/drm/radeon/evergreen_cs.c @@ -395,7 +395,7 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i struct evergreen_cs_track *track = p->track; struct eg_surface surf; unsigned pitch, slice, mslice; - unsigned long offset; + u64 offset; int r; mslice = G_028C6C_SLICE_MAX(track->cb_color_view[id]) + 1; @@ -433,14 +433,14 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i return r; } - offset = track->cb_color_bo_offset[id] << 8; + offset = (u64)track->cb_color_bo_offset[id] << 8; if (offset & (surf.base_align - 1)) { - dev_warn(p->dev, "%s:%d cb[%d] bo base %ld not aligned with %ld\n", + dev_warn(p->dev, "%s:%d cb[%d] bo base %llu not aligned with %ld\n", __func__, __LINE__, id, offset, surf.base_align); return -EINVAL; } - offset += surf.layer_size * mslice; + offset += (u64)surf.layer_size * mslice; if (offset > radeon_bo_size(track->cb_color_bo[id])) { /* old ddx are broken they allocate bo with w*h*bpp but * program slice with ALIGN(h, 8), catch this and patch @@ -448,14 +448,14 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i */ if (!surf.mode) { uint32_t *ib = p->ib.ptr; - unsigned long tmp, nby, bsize, size, min = 0; + u64 tmp, nby, bsize, size, min = 0; /* find the height the ddx wants */ if (surf.nby > 8) { min = surf.nby - 8; } bsize = radeon_bo_size(track->cb_color_bo[id]); - tmp = track->cb_color_bo_offset[id] << 8; + tmp = (u64)track->cb_color_bo_offset[id] << 8; for (nby = surf.nby; nby > min; nby--) { size = nby * surf.nbx * surf.bpe * surf.nsamples; if ((tmp + size * mslice) <= bsize) { @@ -467,7 +467,7 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i slice = ((nby * surf.nbx) / 64) - 1; if (!evergreen_surface_check(p, &surf, "cb")) { /* check if this one works */ - tmp += surf.layer_size * mslice; + tmp += (u64)surf.layer_size * mslice; if (tmp <= bsize) { ib[track->cb_color_slice_idx[id]] = slice; goto old_ddx_ok; @@ -476,9 +476,9 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i } } dev_warn(p->dev, "%s:%d cb[%d] bo too small (layer size %d, " - "offset %d, max layer %d, bo size %ld, slice %d)\n", + "offset %llu, max layer %d, bo size %ld, slice %d)\n", __func__, __LINE__, id, surf.layer_size, - track->cb_color_bo_offset[id] << 8, mslice, + (u64)track->cb_color_bo_offset[id] << 8, mslice, radeon_bo_size(track->cb_color_bo[id]), slice); dev_warn(p->dev, "%s:%d problematic surf: (%d %d) (%d %d %d %d %d %d %d)\n", __func__, __LINE__, surf.nbx, surf.nby, @@ -562,7 +562,7 @@ static int evergreen_cs_track_validate_stencil(struct radeon_cs_parser *p) struct evergreen_cs_track *track = p->track; struct eg_surface surf; unsigned pitch, slice, mslice; - unsigned long offset; + u64 offset; int r; mslice = G_028008_SLICE_MAX(track->db_depth_view) + 1; @@ -608,18 +608,18 @@ static int evergreen_cs_track_validate_stencil(struct radeon_cs_parser *p) return r; } - offset = track->db_s_read_offset << 8; + offset = (u64)track->db_s_read_offset << 8; if (offset & (surf.base_align - 1)) { - dev_warn(p->dev, "%s:%d stencil read bo base %ld not aligned with %ld\n", + dev_warn(p->dev, "%s:%d stencil read bo base %llu not aligned with %ld\n", __func__, __LINE__, offset, surf.base_align); return -EINVAL; } - offset += surf.layer_size * mslice; + offset += (u64)surf.layer_size * mslice; if (offset > radeon_bo_size(track->db_s_read_bo)) { dev_warn(p->dev, "%s:%d stencil read bo too small (layer size %d, " - "offset %ld, max layer %d, bo size %ld)\n", + "offset %llu, max layer %d, bo size %ld)\n", __func__, __LINE__, surf.layer_size, - (unsigned long)track->db_s_read_offset << 8, mslice, + (u64)track->db_s_read_offset << 8, mslice, radeon_bo_size(track->db_s_read_bo)); dev_warn(p->dev, "%s:%d stencil invalid (0x%08x 0x%08x 0x%08x 0x%08x)\n", __func__, __LINE__, track->db_depth_size, @@ -627,18 +627,18 @@ static int evergreen_cs_track_validate_stencil(struct radeon_cs_parser *p) return -EINVAL; } - offset = track->db_s_write_offset << 8; + offset = (u64)track->db_s_write_offset << 8; if (offset & (surf.base_align - 1)) { - dev_warn(p->dev, "%s:%d stencil write bo base %ld not aligned with %ld\n", + dev_warn(p->dev, "%s:%d stencil write bo base %llu not aligned with %ld\n", __func__, __LINE__, offset, surf.base_align); return -EINVAL; } - offset += surf.layer_size * mslice; + offset += (u64)surf.layer_size * mslice; if (offset > radeon_bo_size(track->db_s_write_bo)) { dev_warn(p->dev, "%s:%d stencil write bo too small (layer size %d, " - "offset %ld, max layer %d, bo size %ld)\n", + "offset %llu, max layer %d, bo size %ld)\n", __func__, __LINE__, surf.layer_size, - (unsigned long)track->db_s_write_offset << 8, mslice, + (u64)track->db_s_write_offset << 8, mslice, radeon_bo_size(track->db_s_write_bo)); return -EINVAL; } @@ -659,7 +659,7 @@ static int evergreen_cs_track_validate_depth(struct radeon_cs_parser *p) struct evergreen_cs_track *track = p->track; struct eg_surface surf; unsigned pitch, slice, mslice; - unsigned long offset; + u64 offset; int r; mslice = G_028008_SLICE_MAX(track->db_depth_view) + 1; @@ -706,34 +706,34 @@ static int evergreen_cs_track_validate_depth(struct radeon_cs_parser *p) return r; } - offset = track->db_z_read_offset << 8; + offset = (u64)track->db_z_read_offset << 8; if (offset & (surf.base_align - 1)) { - dev_warn(p->dev, "%s:%d stencil read bo base %ld not aligned with %ld\n", + dev_warn(p->dev, "%s:%d stencil read bo base %llu not aligned with %ld\n", __func__, __LINE__, offset, surf.base_align); return -EINVAL; } - offset += surf.layer_size * mslice; + offset += (u64)surf.layer_size * mslice; if (offset > radeon_bo_size(track->db_z_read_bo)) { dev_warn(p->dev, "%s:%d depth read bo too small (layer size %d, " - "offset %ld, max layer %d, bo size %ld)\n", + "offset %llu, max layer %d, bo size %ld)\n", __func__, __LINE__, surf.layer_size, - (unsigned long)track->db_z_read_offset << 8, mslice, + (u64)track->db_z_read_offset << 8, mslice, radeon_bo_size(track->db_z_read_bo)); return -EINVAL; } - offset = track->db_z_write_offset << 8; + offset = (u64)track->db_z_write_offset << 8; if (offset & (surf.base_align - 1)) { - dev_warn(p->dev, "%s:%d stencil write bo base %ld not aligned with %ld\n", + dev_warn(p->dev, "%s:%d stencil write bo base %llu not aligned with %ld\n", __func__, __LINE__, offset, surf.base_align); return -EINVAL; } - offset += surf.layer_size * mslice; + offset += (u64)surf.layer_size * mslice; if (offset > radeon_bo_size(track->db_z_write_bo)) { dev_warn(p->dev, "%s:%d depth write bo too small (layer size %d, " - "offset %ld, max layer %d, bo size %ld)\n", + "offset %llu, max layer %d, bo size %ld)\n", __func__, __LINE__, surf.layer_size, - (unsigned long)track->db_z_write_offset << 8, mslice, + (u64)track->db_z_write_offset << 8, mslice, radeon_bo_size(track->db_z_write_bo)); return -EINVAL; } diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index 927e5f42e97d01..3e48cbb522a1ca 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -813,7 +813,7 @@ int ni_init_microcode(struct radeon_device *rdev) err = 0; } else if (rdev->smc_fw->size != smc_req_size) { pr_err("ni_mc: Bogus length %zu in firmware \"%s\"\n", - rdev->mc_fw->size, fw_name); + rdev->smc_fw->size, fw_name); err = -EINVAL; } } diff --git a/drivers/gpu/drm/radeon/pptable.h b/drivers/gpu/drm/radeon/pptable.h index 4c2eec49dadc93..ce8832916704f9 100644 --- a/drivers/gpu/drm/radeon/pptable.h +++ b/drivers/gpu/drm/radeon/pptable.h @@ -424,7 +424,7 @@ typedef struct _ATOM_PPLIB_SUMO_CLOCK_INFO{ typedef struct _ATOM_PPLIB_STATE_V2 { //number of valid dpm levels in this state; Driver uses it to calculate the whole - //size of the state: sizeof(ATOM_PPLIB_STATE_V2) + (ucNumDPMLevels - 1) * sizeof(UCHAR) + //size of the state: struct_size(ATOM_PPLIB_STATE_V2, clockInfoIndex, ucNumDPMLevels) UCHAR ucNumDPMLevels; //a index to the array of nonClockInfos @@ -432,14 +432,14 @@ typedef struct _ATOM_PPLIB_STATE_V2 /** * Driver will read the first ucNumDPMLevels in this array */ - UCHAR clockInfoIndex[1]; + UCHAR clockInfoIndex[] __counted_by(ucNumDPMLevels); } ATOM_PPLIB_STATE_V2; typedef struct _StateArray{ //how many states we have UCHAR ucNumEntries; - ATOM_PPLIB_STATE_V2 states[1]; + ATOM_PPLIB_STATE_V2 states[] /* __counted_by(ucNumEntries) */; }StateArray; @@ -450,7 +450,7 @@ typedef struct _ClockInfoArray{ //sizeof(ATOM_PPLIB_CLOCK_INFO) UCHAR ucEntrySize; - UCHAR clockInfo[1]; + UCHAR clockInfo[] __counted_by(ucNumEntries); }ClockInfoArray; typedef struct _NonClockInfoArray{ @@ -460,7 +460,7 @@ typedef struct _NonClockInfoArray{ //sizeof(ATOM_PPLIB_NONCLOCK_INFO) UCHAR ucEntrySize; - ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[1]; + ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[] __counted_by(ucNumEntries); }NonClockInfoArray; typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index affa9e0309b274..b63b6b4e9b2818 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -1015,45 +1015,65 @@ static int r100_cp_init_microcode(struct radeon_device *rdev) DRM_DEBUG_KMS("\n"); - if ((rdev->family == CHIP_R100) || (rdev->family == CHIP_RV100) || - (rdev->family == CHIP_RV200) || (rdev->family == CHIP_RS100) || - (rdev->family == CHIP_RS200)) { + switch (rdev->family) { + case CHIP_R100: + case CHIP_RV100: + case CHIP_RV200: + case CHIP_RS100: + case CHIP_RS200: DRM_INFO("Loading R100 Microcode\n"); fw_name = FIRMWARE_R100; - } else if ((rdev->family == CHIP_R200) || - (rdev->family == CHIP_RV250) || - (rdev->family == CHIP_RV280) || - (rdev->family == CHIP_RS300)) { + break; + + case CHIP_R200: + case CHIP_RV250: + case CHIP_RV280: + case CHIP_RS300: DRM_INFO("Loading R200 Microcode\n"); fw_name = FIRMWARE_R200; - } else if ((rdev->family == CHIP_R300) || - (rdev->family == CHIP_R350) || - (rdev->family == CHIP_RV350) || - (rdev->family == CHIP_RV380) || - (rdev->family == CHIP_RS400) || - (rdev->family == CHIP_RS480)) { + break; + + case CHIP_R300: + case CHIP_R350: + case CHIP_RV350: + case CHIP_RV380: + case CHIP_RS400: + case CHIP_RS480: DRM_INFO("Loading R300 Microcode\n"); fw_name = FIRMWARE_R300; - } else if ((rdev->family == CHIP_R420) || - (rdev->family == CHIP_R423) || - (rdev->family == CHIP_RV410)) { + break; + + case CHIP_R420: + case CHIP_R423: + case CHIP_RV410: DRM_INFO("Loading R400 Microcode\n"); fw_name = FIRMWARE_R420; - } else if ((rdev->family == CHIP_RS690) || - (rdev->family == CHIP_RS740)) { + break; + + case CHIP_RS690: + case CHIP_RS740: DRM_INFO("Loading RS690/RS740 Microcode\n"); fw_name = FIRMWARE_RS690; - } else if (rdev->family == CHIP_RS600) { + break; + + case CHIP_RS600: DRM_INFO("Loading RS600 Microcode\n"); fw_name = FIRMWARE_RS600; - } else if ((rdev->family == CHIP_RV515) || - (rdev->family == CHIP_R520) || - (rdev->family == CHIP_RV530) || - (rdev->family == CHIP_R580) || - (rdev->family == CHIP_RV560) || - (rdev->family == CHIP_RV570)) { + break; + + case CHIP_RV515: + case CHIP_R520: + case CHIP_RV530: + case CHIP_R580: + case CHIP_RV560: + case CHIP_RV570: DRM_INFO("Loading R500 Microcode\n"); fw_name = FIRMWARE_R520; + break; + + default: + DRM_ERROR("Unsupported Radeon family %u\n", rdev->family); + return -EINVAL; } err = request_firmware(&rdev->me_fw, fw_name, rdev->dev); @@ -2321,7 +2341,7 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) switch (prim_walk) { case 1: for (i = 0; i < track->num_arrays; i++) { - size = track->arrays[i].esize * track->max_indx * 4; + size = track->arrays[i].esize * track->max_indx * 4UL; if (track->arrays[i].robj == NULL) { DRM_ERROR("(PW %u) Vertex array %u no buffer " "bound\n", prim_walk, i); @@ -2340,7 +2360,7 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) break; case 2: for (i = 0; i < track->num_arrays; i++) { - size = track->arrays[i].esize * (nverts - 1) * 4; + size = track->arrays[i].esize * (nverts - 1) * 4UL; if (track->arrays[i].robj == NULL) { DRM_ERROR("(PW %u) Vertex array %u no buffer " "bound\n", prim_walk, i); diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index 638f861af80fa1..6cf54a747749d3 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -1275,7 +1275,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) return -EINVAL; } tmp = (reg - CB_COLOR0_BASE) / 4; - track->cb_color_bo_offset[tmp] = radeon_get_ib_value(p, idx) << 8; + track->cb_color_bo_offset[tmp] = (u64)radeon_get_ib_value(p, idx) << 8; ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); track->cb_color_base_last[tmp] = ib[idx]; track->cb_color_bo[tmp] = reloc->robj; @@ -1302,7 +1302,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) "0x%04X\n", reg); return -EINVAL; } - track->htile_offset = radeon_get_ib_value(p, idx) << 8; + track->htile_offset = (u64)radeon_get_ib_value(p, idx) << 8; ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); track->htile_bo = reloc->robj; track->db_dirty = true; diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 8afb03bbce2984..426a49851e3497 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -132,7 +132,6 @@ extern int radeon_cik_support; /* RADEON_IB_POOL_SIZE must be a power of 2 */ #define RADEON_IB_POOL_SIZE 16 #define RADEON_DEBUGFS_MAX_COMPONENTS 32 -#define RADEONFB_CONN_LIMIT 4 #define RADEON_BIOS_NUM_SCRATCH 8 /* internal ring indices */ @@ -2215,10 +2214,6 @@ int radeon_gem_pin_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); int radeon_gem_unpin_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); -int radeon_gem_pwrite_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv); -int radeon_gem_pread_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv); int radeon_gem_set_domain_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); int radeon_gem_mmap_ioctl(struct drm_device *dev, void *data, diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 85c4bb186203c3..53c7273eb6a5cf 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -922,8 +922,12 @@ bool radeon_get_atom_connector_info_from_supported_devices_table(struct max_device = ATOM_MAX_SUPPORTED_DEVICE_INFO; for (i = 0; i < max_device; i++) { - ATOM_CONNECTOR_INFO_I2C ci = - supported_devices->info.asConnInfo[i]; + ATOM_CONNECTOR_INFO_I2C ci; + + if (frev > 1) + ci = supported_devices->info_2d1.asConnInfo[i]; + else + ci = supported_devices->info.asConnInfo[i]; bios_connectors[i].valid = false; @@ -1712,26 +1716,29 @@ struct radeon_encoder_atom_dig *radeon_atombios_get_lvds_info(struct fake_edid_record = (ATOM_FAKE_EDID_PATCH_RECORD *)record; if (fake_edid_record->ucFakeEDIDLength) { struct edid *edid; - int edid_size = - max((int)EDID_LENGTH, (int)fake_edid_record->ucFakeEDIDLength); - edid = kmalloc(edid_size, GFP_KERNEL); + int edid_size; + + if (fake_edid_record->ucFakeEDIDLength == 128) + edid_size = fake_edid_record->ucFakeEDIDLength; + else + edid_size = fake_edid_record->ucFakeEDIDLength * 128; + edid = kmemdup(&fake_edid_record->ucFakeEDIDString[0], + edid_size, GFP_KERNEL); if (edid) { - memcpy((u8 *)edid, (u8 *)&fake_edid_record->ucFakeEDIDString[0], - fake_edid_record->ucFakeEDIDLength); - if (drm_edid_is_valid(edid)) { rdev->mode_info.bios_hardcoded_edid = edid; rdev->mode_info.bios_hardcoded_edid_size = edid_size; - } else + } else { kfree(edid); + } } + record += struct_size(fake_edid_record, + ucFakeEDIDString, + edid_size); + } else { + /* empty fake edid record must be 3 bytes long */ + record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD) + 1; } - record += fake_edid_record->ucFakeEDIDLength ? - struct_size(fake_edid_record, - ucFakeEDIDString, - fake_edid_record->ucFakeEDIDLength) : - /* empty fake edid record must be 3 bytes long */ - sizeof(ATOM_FAKE_EDID_PATCH_RECORD) + 1; break; case LCD_PANEL_RESOLUTION_RECORD_TYPE: panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record; diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index d2f02c3dfce297..b84b58926106a4 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -1119,6 +1119,8 @@ static int radeon_tv_get_modes(struct drm_connector *connector) else { /* only 800x600 is supported right now on pre-avivo chips */ tv_mode = drm_cvt_mode(dev, 800, 600, 60, false, false, false); + if (!tv_mode) + return 0; tv_mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; drm_mode_probed_add(connector, tv_mode); } diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 901e75ec70ff41..5f1d24d3120c4a 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -683,15 +683,20 @@ static void radeon_crtc_init(struct drm_device *dev, int index) struct radeon_device *rdev = dev->dev_private; struct radeon_crtc *radeon_crtc; - radeon_crtc = kzalloc(sizeof(struct radeon_crtc) + (RADEONFB_CONN_LIMIT * sizeof(struct drm_connector *)), GFP_KERNEL); + radeon_crtc = kzalloc(sizeof(*radeon_crtc), GFP_KERNEL); if (radeon_crtc == NULL) return; + radeon_crtc->flip_queue = alloc_workqueue("radeon-crtc", WQ_HIGHPRI, 0); + if (!radeon_crtc->flip_queue) { + kfree(radeon_crtc); + return; + } + drm_crtc_init(dev, &radeon_crtc->base, &radeon_crtc_funcs); drm_mode_crtc_set_gamma_size(&radeon_crtc->base, 256); radeon_crtc->crtc_id = index; - radeon_crtc->flip_queue = alloc_workqueue("radeon-crtc", WQ_HIGHPRI, 0); rdev->mode_info.crtcs[index] = radeon_crtc; if (rdev->family >= CHIP_BONAIRE) { @@ -704,12 +709,6 @@ static void radeon_crtc_init(struct drm_device *dev, int index) dev->mode_config.cursor_width = radeon_crtc->max_cursor_width; dev->mode_config.cursor_height = radeon_crtc->max_cursor_height; -#if 0 - radeon_crtc->mode_set.crtc = &radeon_crtc->base; - radeon_crtc->mode_set.connectors = (struct drm_connector **)(radeon_crtc + 1); - radeon_crtc->mode_set.num_connectors = 0; -#endif - if (rdev->is_atom_bios && (ASIC_IS_AVIVO(rdev) || radeon_r4xx_atom)) radeon_atombios_init_crtc(dev, radeon_crtc); else diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index fa531493b11134..7bf08164140ef7 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -555,8 +555,6 @@ static const struct drm_ioctl_desc radeon_ioctls_kms[] = { DRM_IOCTL_DEF_DRV(RADEON_GEM_CREATE, radeon_gem_create_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(RADEON_GEM_MMAP, radeon_gem_mmap_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(RADEON_GEM_SET_DOMAIN, radeon_gem_set_domain_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), - DRM_IOCTL_DEF_DRV(RADEON_GEM_PREAD, radeon_gem_pread_ioctl, DRM_AUTH), - DRM_IOCTL_DEF_DRV(RADEON_GEM_PWRITE, radeon_gem_pwrite_ioctl, DRM_AUTH), DRM_IOCTL_DEF_DRV(RADEON_GEM_WAIT_IDLE, radeon_gem_wait_idle_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(RADEON_CS, radeon_cs_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(RADEON_INFO, radeon_info_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c index 9cb6401fe97ed3..bb908f125269dc 100644 --- a/drivers/gpu/drm/radeon/radeon_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_encoders.c @@ -42,7 +42,7 @@ static uint32_t radeon_encoder_clones(struct drm_encoder *encoder) struct radeon_device *rdev = dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct drm_encoder *clone_encoder; - uint32_t index_mask = 0; + uint32_t index_mask = drm_encoder_mask(encoder); int count; /* DIG routing gets problematic */ diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 358d19242f4ba2..27225d1fe8d2e7 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -311,22 +311,6 @@ int radeon_gem_info_ioctl(struct drm_device *dev, void *data, return 0; } -int radeon_gem_pread_ioctl(struct drm_device *dev, void *data, - struct drm_file *filp) -{ - /* TODO: implement */ - DRM_ERROR("unimplemented %s\n", __func__); - return -EOPNOTSUPP; -} - -int radeon_gem_pwrite_ioctl(struct drm_device *dev, void *data, - struct drm_file *filp) -{ - /* TODO: implement */ - DRM_ERROR("unimplemented %s\n", __func__); - return -EOPNOTSUPP; -} - int radeon_gem_create_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { @@ -657,7 +641,7 @@ static void radeon_gem_va_update_vm(struct radeon_device *rdev, if (r) goto error_unlock; - if (bo_va->it.start) + if (bo_va->it.start && bo_va->bo) r = radeon_vm_bo_update(rdev, bo_va, bo_va->bo->tbo.resource); error_unlock: diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c index 987cabbf1318e9..c38b4d5d6a14f5 100644 --- a/drivers/gpu/drm/radeon/radeon_vm.c +++ b/drivers/gpu/drm/radeon/radeon_vm.c @@ -1204,13 +1204,17 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm) r = radeon_bo_create(rdev, pd_size, align, true, RADEON_GEM_DOMAIN_VRAM, 0, NULL, NULL, &vm->page_directory); - if (r) + if (r) { + kfree(vm->page_tables); + vm->page_tables = NULL; return r; - + } r = radeon_vm_clear_bo(rdev, vm->page_directory); if (r) { radeon_bo_unref(&vm->page_directory); vm->page_directory = NULL; + kfree(vm->page_tables); + vm->page_tables = NULL; return r; } diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index a91012447b56ed..85e9cba49cecb2 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -3611,6 +3611,10 @@ static int si_cp_start(struct radeon_device *rdev) for (i = RADEON_RING_TYPE_GFX_INDEX; i <= CAYMAN_RING_TYPE_CP2_INDEX; ++i) { ring = &rdev->ring[i]; r = radeon_ring_lock(rdev, ring, 2); + if (r) { + DRM_ERROR("radeon: cp failed to lock ring (%d).\n", r); + return r; + } /* clear the compute context state */ radeon_ring_write(ring, PACKET3_COMPUTE(PACKET3_CLEAR_STATE, 0)); diff --git a/drivers/gpu/drm/radeon/sumo_dpm.c b/drivers/gpu/drm/radeon/sumo_dpm.c index f74f381af05fdf..f7f1ddc6cdd810 100644 --- a/drivers/gpu/drm/radeon/sumo_dpm.c +++ b/drivers/gpu/drm/radeon/sumo_dpm.c @@ -1493,8 +1493,10 @@ static int sumo_parse_power_table(struct radeon_device *rdev) non_clock_array_index = power_state->v2.nonClockInfoIndex; non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *) &non_clock_info_array->nonClockInfo[non_clock_array_index]; - if (!rdev->pm.power_state[i].clock_info) + if (!rdev->pm.power_state[i].clock_info) { + kfree(rdev->pm.dpm.ps); return -EINVAL; + } ps = kzalloc(sizeof(struct sumo_ps), GFP_KERNEL); if (ps == NULL) { kfree(rdev->pm.dpm.ps); @@ -1619,6 +1621,8 @@ void sumo_construct_vid_mapping_table(struct radeon_device *rdev, for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++) { if (table[i].ulSupportedSCLK != 0) { + if (table[i].usVoltageIndex >= SUMO_MAX_NUMBER_VOLTAGES) + continue; vid_mapping_table->entries[table[i].usVoltageIndex].vid_7bit = table[i].usVoltageID; vid_mapping_table->entries[table[i].usVoltageIndex].vid_2bit = diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c index 08ea1c864cb238..ef1cc7bad20a76 100644 --- a/drivers/gpu/drm/radeon/trinity_dpm.c +++ b/drivers/gpu/drm/radeon/trinity_dpm.c @@ -1726,8 +1726,10 @@ static int trinity_parse_power_table(struct radeon_device *rdev) non_clock_array_index = power_state->v2.nonClockInfoIndex; non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *) &non_clock_info_array->nonClockInfo[non_clock_array_index]; - if (!rdev->pm.power_state[i].clock_info) + if (!rdev->pm.power_state[i].clock_info) { + kfree(rdev->pm.dpm.ps); return -EINVAL; + } ps = kzalloc(sizeof(struct sumo_ps), GFP_KERNEL); if (ps == NULL) { kfree(rdev->pm.dpm.ps); diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c index a29fbafce39366..3793863c210ebd 100644 --- a/drivers/gpu/drm/rockchip/cdn-dp-core.c +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c @@ -1177,6 +1177,7 @@ static int cdn_dp_probe(struct platform_device *pdev) struct cdn_dp_device *dp; struct extcon_dev *extcon; struct phy *phy; + int ret; int i; dp = devm_kzalloc(dev, sizeof(*dp), GFP_KERNEL); @@ -1217,9 +1218,19 @@ static int cdn_dp_probe(struct platform_device *pdev) mutex_init(&dp->lock); dev_set_drvdata(dev, dp); - cdn_dp_audio_codec_init(dp, dev); + ret = cdn_dp_audio_codec_init(dp, dev); + if (ret) + return ret; + + ret = component_add(dev, &cdn_dp_component_ops); + if (ret) + goto err_audio_deinit; - return component_add(dev, &cdn_dp_component_ops); + return 0; + +err_audio_deinit: + platform_device_unregister(dp->audio_pdev); + return ret; } static void cdn_dp_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c index 341550199111f9..89bc86d620146c 100644 --- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c @@ -435,6 +435,8 @@ static void dw_hdmi_rk3328_setup_hpd(struct dw_hdmi *dw_hdmi, void *data) HIWORD_UPDATE(RK3328_HDMI_SDAIN_MSK | RK3328_HDMI_SCLIN_MSK, RK3328_HDMI_SDAIN_MSK | RK3328_HDMI_SCLIN_MSK | RK3328_HDMI_HPD_IOE)); + + dw_hdmi_rk3328_read_hpd(dw_hdmi, data); } static const struct dw_hdmi_phy_ops rk3228_hdmi_phy_ops = { diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c index 6e5b922a121e24..345253e033c538 100644 --- a/drivers/gpu/drm/rockchip/inno_hdmi.c +++ b/drivers/gpu/drm/rockchip/inno_hdmi.c @@ -412,7 +412,7 @@ static int inno_hdmi_config_video_timing(struct inno_hdmi *hdmi, hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HBLANK_L, value & 0xFF); hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HBLANK_H, (value >> 8) & 0xFF); - value = mode->hsync_start - mode->hdisplay; + value = mode->htotal - mode->hsync_start; hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HDELAY_L, value & 0xFF); hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HDELAY_H, (value >> 8) & 0xFF); @@ -427,7 +427,7 @@ static int inno_hdmi_config_video_timing(struct inno_hdmi *hdmi, value = mode->vtotal - mode->vdisplay; hdmi_writeb(hdmi, HDMI_VIDEO_EXT_VBLANK, value & 0xFF); - value = mode->vsync_start - mode->vdisplay; + value = mode->vtotal - mode->vsync_start; hdmi_writeb(hdmi, HDMI_VIDEO_EXT_VDELAY, value & 0xFF); value = mode->vsync_end - mode->vsync_start; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c index b8f8b45ebf5940..93ed841f5dceae 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -40,7 +40,7 @@ static int rockchip_gem_iommu_map(struct rockchip_gem_object *rk_obj) ret = iommu_map_sgtable(private->domain, rk_obj->dma_addr, rk_obj->sgt, prot); - if (ret < rk_obj->base.size) { + if (ret < (ssize_t)rk_obj->base.size) { DRM_ERROR("failed to map buffer: size=%zd request_size=%zd\n", ret, rk_obj->base.size); ret = -ENOMEM; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 14320bc73e5bfc..ee72e8c6ad69bd 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -247,14 +247,22 @@ static inline void vop_cfg_done(struct vop *vop) VOP_REG_SET(vop, common, cfg_done, 1); } -static bool has_rb_swapped(uint32_t format) +static bool has_rb_swapped(uint32_t version, uint32_t format) { switch (format) { case DRM_FORMAT_XBGR8888: case DRM_FORMAT_ABGR8888: - case DRM_FORMAT_BGR888: case DRM_FORMAT_BGR565: return true; + /* + * full framework (IP version 3.x) only need rb swapped for RGB888 and + * little framework (IP version 2.x) only need rb swapped for BGR888, + * check for 3.x to also only rb swap BGR888 for unknown vop version + */ + case DRM_FORMAT_RGB888: + return VOP_MAJOR(version) == 3; + case DRM_FORMAT_BGR888: + return VOP_MAJOR(version) != 3; default: return false; } @@ -373,8 +381,8 @@ static void scl_vop_cal_scl_fac(struct vop *vop, const struct vop_win_data *win, if (info->is_yuv) is_yuv = true; - if (dst_w > 3840) { - DRM_DEV_ERROR(vop->dev, "Maximum dst width (3840) exceeded\n"); + if (dst_w > 4096) { + DRM_DEV_ERROR(vop->dev, "Maximum dst width (4096) exceeded\n"); return; } @@ -1013,7 +1021,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane, VOP_WIN_SET(vop, win, dsp_info, dsp_info); VOP_WIN_SET(vop, win, dsp_st, dsp_st); - rb_swap = has_rb_swapped(fb->format->format); + rb_swap = has_rb_swapped(vop->data->version, fb->format->format); VOP_WIN_SET(vop, win, rb_swap, rb_swap); /* @@ -1558,6 +1566,10 @@ static void vop_crtc_atomic_flush(struct drm_crtc *crtc, VOP_AFBC_SET(vop, enable, s->enable_afbc); vop_cfg_done(vop); + /* Ack the DMA transfer of the previous frame (RK3066). */ + if (VOP_HAS_REG(vop, common, dma_stop)) + VOP_REG_SET(vop, common, dma_stop, 0); + spin_unlock(&vop->reg_lock); /* @@ -1614,7 +1626,8 @@ static struct drm_crtc_state *vop_crtc_duplicate_state(struct drm_crtc *crtc) if (WARN_ON(!crtc->state)) return NULL; - rockchip_state = kzalloc(sizeof(*rockchip_state), GFP_KERNEL); + rockchip_state = kmemdup(to_rockchip_crtc_state(crtc->state), + sizeof(*rockchip_state), GFP_KERNEL); if (!rockchip_state) return NULL; @@ -1639,7 +1652,10 @@ static void vop_crtc_reset(struct drm_crtc *crtc) if (crtc->state) vop_crtc_destroy_state(crtc, crtc->state); - __drm_atomic_helper_crtc_reset(crtc, &crtc_state->base); + if (crtc_state) + __drm_atomic_helper_crtc_reset(crtc, &crtc_state->base); + else + __drm_atomic_helper_crtc_reset(crtc, NULL); } #ifdef CONFIG_DRM_ANALOGIX_DP diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h index 5f56e0597df84a..c5c716a69171a8 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h @@ -122,6 +122,7 @@ struct vop_common { struct vop_reg lut_buffer_index; struct vop_reg gate_en; struct vop_reg mmu_en; + struct vop_reg dma_stop; struct vop_reg out_mode; struct vop_reg standby; }; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c index 583df4d22f7e90..d1de12e850e746 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c @@ -609,6 +609,8 @@ static void vop2_setup_scale(struct vop2 *vop2, const struct vop2_win *win, const struct drm_format_info *info; u16 hor_scl_mode, ver_scl_mode; u16 hscl_filter_mode, vscl_filter_mode; + uint16_t cbcr_src_w = src_w; + uint16_t cbcr_src_h = src_h; u8 gt2 = 0; u8 gt4 = 0; u32 val; @@ -666,27 +668,27 @@ static void vop2_setup_scale(struct vop2 *vop2, const struct vop2_win *win, vop2_win_write(win, VOP2_WIN_YRGB_VSCL_FILTER_MODE, vscl_filter_mode); if (info->is_yuv) { - src_w /= info->hsub; - src_h /= info->vsub; + cbcr_src_w /= info->hsub; + cbcr_src_h /= info->vsub; gt4 = 0; gt2 = 0; - if (src_h >= (4 * dst_h)) { + if (cbcr_src_h >= (4 * dst_h)) { gt4 = 1; - src_h >>= 2; - } else if (src_h >= (2 * dst_h)) { + cbcr_src_h >>= 2; + } else if (cbcr_src_h >= (2 * dst_h)) { gt2 = 1; - src_h >>= 1; + cbcr_src_h >>= 1; } - hor_scl_mode = scl_get_scl_mode(src_w, dst_w); - ver_scl_mode = scl_get_scl_mode(src_h, dst_h); + hor_scl_mode = scl_get_scl_mode(cbcr_src_w, dst_w); + ver_scl_mode = scl_get_scl_mode(cbcr_src_h, dst_h); - val = vop2_scale_factor(src_w, dst_w); + val = vop2_scale_factor(cbcr_src_w, dst_w); vop2_win_write(win, VOP2_WIN_SCALE_CBCR_X, val); - val = vop2_scale_factor(src_h, dst_h); + val = vop2_scale_factor(cbcr_src_h, dst_h); vop2_win_write(win, VOP2_WIN_SCALE_CBCR_Y, val); vop2_win_write(win, VOP2_WIN_VSD_CBCR_GT4, gt4); @@ -1258,6 +1260,11 @@ static void vop2_plane_atomic_update(struct drm_plane *plane, vop2_win_write(win, VOP2_WIN_AFBC_ROTATE_270, rotate_270); vop2_win_write(win, VOP2_WIN_AFBC_ROTATE_90, rotate_90); } else { + if (vop2_cluster_window(win)) { + vop2_win_write(win, VOP2_WIN_AFBC_ENABLE, 0); + vop2_win_write(win, VOP2_WIN_AFBC_TRANSFORM_OFFSET, 0); + } + vop2_win_write(win, VOP2_WIN_YRGB_VIR, DIV_ROUND_UP(fb->pitches[0], 4)); } @@ -1925,7 +1932,7 @@ static void vop2_setup_layer_mixer(struct vop2_video_port *vp) port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT2_MUX, (vp2->nlayers + vp1->nlayers + vp0->nlayers - 1)); else - port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT1_MUX, 8); + port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT2_MUX, 8); layer_sel = vop2_readl(vop2, RK3568_OVL_LAYER_SEL); @@ -2079,30 +2086,15 @@ static const struct drm_crtc_helper_funcs vop2_crtc_helper_funcs = { .atomic_disable = vop2_crtc_atomic_disable, }; -static void vop2_crtc_reset(struct drm_crtc *crtc) -{ - struct rockchip_crtc_state *vcstate = to_rockchip_crtc_state(crtc->state); - - if (crtc->state) { - __drm_atomic_helper_crtc_destroy_state(crtc->state); - kfree(vcstate); - } - - vcstate = kzalloc(sizeof(*vcstate), GFP_KERNEL); - if (!vcstate) - return; - - crtc->state = &vcstate->base; - crtc->state->crtc = crtc; -} - static struct drm_crtc_state *vop2_crtc_duplicate_state(struct drm_crtc *crtc) { - struct rockchip_crtc_state *vcstate, *old_vcstate; + struct rockchip_crtc_state *vcstate; - old_vcstate = to_rockchip_crtc_state(crtc->state); + if (WARN_ON(!crtc->state)) + return NULL; - vcstate = kmemdup(old_vcstate, sizeof(*old_vcstate), GFP_KERNEL); + vcstate = kmemdup(to_rockchip_crtc_state(crtc->state), + sizeof(*vcstate), GFP_KERNEL); if (!vcstate) return NULL; @@ -2120,6 +2112,20 @@ static void vop2_crtc_destroy_state(struct drm_crtc *crtc, kfree(vcstate); } +static void vop2_crtc_reset(struct drm_crtc *crtc) +{ + struct rockchip_crtc_state *vcstate = + kzalloc(sizeof(*vcstate), GFP_KERNEL); + + if (crtc->state) + vop2_crtc_destroy_state(crtc, crtc->state); + + if (vcstate) + __drm_atomic_helper_crtc_reset(crtc, &vcstate->base); + else + __drm_atomic_helper_crtc_reset(crtc, NULL); +} + static const struct drm_crtc_funcs vop2_crtc_funcs = { .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c index 5828593877923f..1b6e0b210aa530 100644 --- a/drivers/gpu/drm/rockchip/rockchip_lvds.c +++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c @@ -577,8 +577,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, ret = -EINVAL; goto err_put_port; } else if (ret) { - DRM_DEV_ERROR(dev, "failed to find panel and bridge node\n"); - ret = -EPROBE_DEFER; + dev_err_probe(dev, ret, "failed to find panel and bridge node\n"); goto err_put_port; } if (lvds->panel) diff --git a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c index 7b28050067769d..f7d0edd762b36c 100644 --- a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c +++ b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c @@ -435,6 +435,7 @@ static const struct vop_output rk3066_output = { }; static const struct vop_common rk3066_common = { + .dma_stop = VOP_REG(RK3066_SYS_CTRL0, 0x1, 0), .standby = VOP_REG(RK3066_SYS_CTRL0, 0x1, 1), .out_mode = VOP_REG(RK3066_DSP_CTRL0, 0xf, 0), .cfg_done = VOP_REG(RK3066_REG_CFG_DONE, 0x1, 0), @@ -483,6 +484,7 @@ static const struct vop_data rk3066_vop = { .output = &rk3066_output, .win = rk3066_vop_win_data, .win_size = ARRAY_SIZE(rk3066_vop_win_data), + .feature = VOP_FEATURE_INTERNAL_RGB, .max_output = { 1920, 1080 }, }; diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index a42763e1429dc1..d3462be7493037 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -111,8 +111,10 @@ void drm_sched_entity_modify_sched(struct drm_sched_entity *entity, { WARN_ON(!num_sched_list || !sched_list); + spin_lock(&entity->rq_lock); entity->sched_list = sched_list; entity->num_sched_list = num_sched_list; + spin_unlock(&entity->rq_lock); } EXPORT_SYMBOL(drm_sched_entity_modify_sched); diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c index 5a80b228d18cae..deec6acdcf6462 100644 --- a/drivers/gpu/drm/solomon/ssd130x.c +++ b/drivers/gpu/drm/solomon/ssd130x.c @@ -267,7 +267,7 @@ static int ssd130x_pwm_enable(struct ssd130x_device *ssd130x) pwm_init_state(ssd130x->pwm, &pwmstate); pwm_set_relative_duty_cycle(&pwmstate, 50, 100); - pwm_apply_state(ssd130x->pwm, &pwmstate); + pwm_apply_might_sleep(ssd130x->pwm, &pwmstate); /* Enable the PWM */ pwm_enable(ssd130x->pwm); @@ -553,14 +553,45 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x, static void ssd130x_clear_screen(struct ssd130x_device *ssd130x, struct ssd130x_plane_state *ssd130x_state) { - struct drm_rect fullscreen = { - .x1 = 0, - .x2 = ssd130x->width, - .y1 = 0, - .y2 = ssd130x->height, - }; - - ssd130x_update_rect(ssd130x, ssd130x_state, &fullscreen); + unsigned int page_height = ssd130x->device_info->page_height; + unsigned int pages = DIV_ROUND_UP(ssd130x->height, page_height); + u8 *data_array = ssd130x_state->data_array; + unsigned int width = ssd130x->width; + int ret, i; + + if (!ssd130x->page_address_mode) { + memset(data_array, 0, width * pages); + + /* Set address range for horizontal addressing mode */ + ret = ssd130x_set_col_range(ssd130x, ssd130x->col_offset, width); + if (ret < 0) + return; + + ret = ssd130x_set_page_range(ssd130x, ssd130x->page_offset, pages); + if (ret < 0) + return; + + /* Write out update in one go if we aren't using page addressing mode */ + ssd130x_write_data(ssd130x, data_array, width * pages); + } else { + /* + * In page addressing mode, the start address needs to be reset, + * and each page then needs to be written out separately. + */ + memset(data_array, 0, width); + + for (i = 0; i < pages; i++) { + ret = ssd130x_set_page_pos(ssd130x, + ssd130x->page_offset + i, + ssd130x->col_offset); + if (ret < 0) + return; + + ret = ssd130x_write_data(ssd130x, data_array, width); + if (ret < 0) + return; + } + } } static int ssd130x_fb_blit_rect(struct drm_plane_state *state, diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c index c68c831136c9b0..e1232f74dfa537 100644 --- a/drivers/gpu/drm/stm/drv.c +++ b/drivers/gpu/drm/stm/drv.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "ltdc.h" @@ -75,7 +76,7 @@ static int drv_load(struct drm_device *ddev) DRM_DEBUG("%s\n", __func__); - ldev = devm_kzalloc(ddev->dev, sizeof(*ldev), GFP_KERNEL); + ldev = drmm_kzalloc(ddev, sizeof(*ldev), GFP_KERNEL); if (!ldev) return -ENOMEM; @@ -114,6 +115,7 @@ static void drv_unload(struct drm_device *ddev) DRM_DEBUG("%s\n", __func__); drm_kms_helper_poll_fini(ddev); + drm_atomic_helper_shutdown(ddev); ltdc_unload(ddev); } @@ -202,12 +204,14 @@ static int stm_drm_platform_probe(struct platform_device *pdev) ret = drm_dev_register(ddev, 0); if (ret) - goto err_put; + goto err_unload; drm_fbdev_dma_setup(ddev, 16); return 0; +err_unload: + drv_unload(ddev); err_put: drm_dev_put(ddev); @@ -225,6 +229,11 @@ static void stm_drm_platform_remove(struct platform_device *pdev) drm_dev_put(ddev); } +static void stm_drm_platform_shutdown(struct platform_device *pdev) +{ + drm_atomic_helper_shutdown(platform_get_drvdata(pdev)); +} + static const struct of_device_id drv_dt_ids[] = { { .compatible = "st,stm32-ltdc"}, { /* end node */ }, @@ -234,6 +243,7 @@ MODULE_DEVICE_TABLE(of, drv_dt_ids); static struct platform_driver stm_drm_platform_driver = { .probe = stm_drm_platform_probe, .remove_new = stm_drm_platform_remove, + .shutdown = stm_drm_platform_shutdown, .driver = { .name = "stm32-display", .of_match_table = drv_dt_ids, diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index 5576fdae496233..0832b749b66e7f 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -36,6 +36,7 @@ #include #include #include +#include #include