| Age | Commit message (Collapse) | Author | Files | Lines | |
|---|---|---|---|---|---|
| 2011-03-16 | cut out a syscall on thread creation in the case where guard size is 0 | Rich Felker | 1 | -1/+1 | |
| 2011-03-16 | don't expose EAGAIN, etc. from timed futex wait to caller | Rich Felker | 1 | -1/+4 | |
| 2011-03-12 | implement flockfile api, rework stdio locking | Rich Felker | 1 | -0/+1 | |
| 2011-03-11 | implement dummy pthread_attr_[gs]etschedparam functions | Rich Felker | 2 | -0/+14 | |
| for some reason these functions are not shaded by the PS/TPS option in POSIX, so presumably they are mandatory, even though the functionality they offer is optional. for now, provide them in case any programs depend on their existence, but disallow any priority except the default. | |||||
| 2011-03-11 | fix pthread_attr_* implementations to match corrected prototypes | Rich Felker | 4 | -4/+4 | |
| 2011-03-10 | fix failure behavior of sem_open when sem does not exist | Rich Felker | 1 | -1/+5 | |
| 2011-03-10 | fix some semaphore wait semantics (race condition deadlock and error checking) | Rich Felker | 2 | -1/+7 | |
| 2011-03-10 | fix sem_open and sem_close to obey posix semantics | Rich Felker | 2 | -33/+80 | |
| multiple opens of the same named semaphore must return the same pointer, and only the last close can unmap it. thus the ugly global state keeping track of mappings. the maximum number of distinct named semaphores that can be opened is limited sufficiently small that the linear searches take trivial time, especially compared to the syscall overhead of these functions. | |||||
| 2011-03-10 | optimize pthread termination in the non-detached case | Rich Felker | 1 | -4/+15 | |
| we can avoid blocking signals by simply using a flag to mark that the thread has exited and prevent it from getting counted in the rsyscall signal-pingpong. this restores the original pthread create/join throughput from before the sigprocmask call was added. | |||||
| 2011-03-10 | security fix: check that cancel/rsyscall signal was sent by the process itself | Rich Felker | 1 | -0/+3 | |
| 2011-03-09 | fix error handling for pthread_sigmask | Rich Felker | 1 | -0/+10 | |
| it must return errno, not -1, and should reject invalud values for how. | |||||
| 2011-03-09 | optimize pthread initialization | Rich Felker | 1 | -2/+2 | |
| the set_tid_address returns the tid (which is also the pid when called from the initial thread) so there is no need to make a separate syscall to get pid/tid. | |||||
| 2011-03-08 | simplify and optimize pthread_mutex_trylock | Rich Felker | 1 | -17/+16 | |
| 2011-03-08 | rwlock trylock functions were wrongly returning EAGAIN instead of EBUSY | Rich Felker | 2 | -3/+3 | |
| 2011-03-08 | fix major breakage in pthread_once (it was always deadlocking) | Rich Felker | 1 | -8/+7 | |
| the issue was a break statement that was breaking only from the switch, not the enclosing for loop, and a failure to set the final success state. | |||||
| 2011-03-08 | fix and optimize non-default-type mutex behavior | Rich Felker | 3 | -25/+18 | |
| problem 1: mutex type from the attribute was being ignored by pthread_mutex_init, so recursive/errorchecking mutexes were never being used at all. problem 2: ownership of recursive mutexes was not being enforced at unlock time. | |||||
| 2011-03-08 | implement pthread_mutexattr_[gs]etpshared functions | Rich Felker | 2 | -0/+16 | |
| 2011-03-08 | disallow cpu time clocks as condattr clock values | Rich Felker | 1 | -1/+1 | |
| 2011-03-07 | fix off-by-one error in sem_(timed)wait (using old sem value instead of new) | Rich Felker | 1 | -1/+1 | |
| 2011-03-07 | use the selected clock from the condattr for pthread_cond_timedwait | Rich Felker | 2 | -1/+2 | |
| 2011-03-07 | implement pthread_rwlockattr_* (essentially no-ops) | Rich Felker | 4 | -0/+28 | |
| 2011-03-07 | implement pthread_condattr_* interfaces | Rich Felker | 6 | -0/+45 | |
| note that, while the attributes are stored, they are not used in pthread_cond_init yet. | |||||
| 2011-03-07 | reject invalid attribute settings | Rich Felker | 2 | -0/+2 | |
| note that this is a pedantic conformance issue and waste of code. it only affects broken code or code that is probing for conformance. | |||||
| 2011-03-07 | implement barrier attribute functions (essentially no-ops) | Rich Felker | 4 | -0/+27 | |
| 2011-03-04 | enforce stack size min in pthread_attr_setstacksize | Rich Felker | 1 | -1/+1 | |
| 2011-03-04 | implement POSIX semaphores | Rich Felker | 10 | -0/+201 | |
| 2011-03-03 | optimize POSIX TSD for fast pthread_getspecific | Rich Felker | 4 | -9/+14 | |
| 2011-02-19 | use rt_sigprocmask, not legacy sigprocmask, syscall in pthread exit code | Rich Felker | 1 | -1/+1 | |
| 2011-02-19 | race condition fix: block all signals before decrementing thread count | Rich Felker | 3 | -22/+2 | |
| the existence of a (kernelspace) thread must never have observable effects after the thread count is decremented. if signals are not blocked, it could end up handling the signal for rsyscall and contributing towards the count of threads which have changed ids, causing a thread to be missed. this could lead to one thread retaining unwanted privilege level. this change may also address other subtle race conditions in application code that uses signals. | |||||
| 2011-02-19 | make pthread_exit run dtors for last thread, wait to decrement thread count | Rich Felker | 1 | -3/+3 | |
| 2011-02-18 | add pthread_atfork interface | Rich Felker | 1 | -0/+48 | |
| note that this presently does not handle consistency of the libc's own global state during forking. as per POSIX 2008, if the parent process was threaded, the child process may only call async-signal-safe functions until one of the exec-family functions is called, so the current behavior is believed to be conformant even if non-ideal. it may be improved at some later time. | |||||
| 2011-02-17 | reorganize pthread data structures and move the definitions to alltypes.h | Rich Felker | 23 | -83/+83 | |
| this allows sys/types.h to provide the pthread types, as required by POSIX. this design also facilitates forcing ABI-compatible sizes in the arch-specific alltypes.h, while eliminating the need for developers changing the internals of the pthread types to poke around with arch-specific headers they may not be able to test. | |||||
| 2011-02-16 | patch by njk, simplifies thread register initialization for x86_64 | Rich Felker | 1 | -4/+0 | |
| It's not necessary to save any registers on the stack across syscall in x86_64 __set_thread_area. Don't waste cycles or bytes on it. | |||||
| 2011-02-16 | patch from njk: make x86_64 __uniclone branchless. | Rich Felker | 1 | -6/+6 | |
| 2011-02-15 | Port musl to x86-64. One giant commit! | Nicholas J. Kain | 3 | -0/+61 | |
| 2011-02-15 | finish unifying thread register handling in preparation for porting | Rich Felker | 4 | -44/+25 | |
| 2011-02-15 | begin unifying clone/thread management interface in preparation for porting | Rich Felker | 2 | -29/+19 | |
| 2011-02-15 | make pthread_create return EAGAIN on resource failure, as required by POSIX | Rich Felker | 1 | -1/+1 | |
| 2011-02-13 | reorganize thread exit code, make pthread_exit call cancellation handlers (pt2) | Rich Felker | 2 | -22/+51 | |
| 2011-02-13 | reorganize thread exit code, make pthread_exit call cancellation handlers | Rich Felker | 1 | -25/+0 | |
| 2011-02-12 | initial check-in, version 0.5.0v0.5.0 | Rich Felker | 70 | -0/+1030 | |
 |
index : musl | |
| The musl libc tree (WIP / dev branches) | root |
| summaryrefslogtreecommitdiff |