summaryrefslogtreecommitdiff
path: root/src/internal
diff options
context:
space:
mode:
authorRich Felker <dalias@aerifal.cx>2014-08-15 23:54:52 -0400
committerRich Felker <dalias@aerifal.cx>2014-08-15 23:54:52 -0400
commitbc09d58c0432a4eca5f6a1e536679a527f971116 (patch)
treeb11245485fda79d368a3bd2d4bb26d9070328a74 /src/internal
parentd86af2a0803cace7b0f616f2a696fb3e25e9b628 (diff)
downloadmusl-bc09d58c0432a4eca5f6a1e536679a527f971116.tar.gz
musl-bc09d58c0432a4eca5f6a1e536679a527f971116.tar.bz2
musl-bc09d58c0432a4eca5f6a1e536679a527f971116.tar.xz
musl-bc09d58c0432a4eca5f6a1e536679a527f971116.zip
make futex operations use private-futex mode when possible
private-futex uses the virtual address of the futex int directly as the hash key rather than requiring the kernel to resolve the address to an underlying backing for the mapping in which it lies. for certain usage patterns it improves performance significantly. in many places, the code using futex __wake and __wait operations was already passing a correct fixed zero or nonzero flag for the priv argument, so no change was needed at the site of the call, only in the __wake and __wait functions themselves. in other places, especially where the process-shared attribute for a synchronization object was not previously tracked, additional new code is needed. for mutexes, the only place to store the flag is in the type field, so additional bit masking logic is needed for accessing the type. for non-process-shared condition variable broadcasts, the futex requeue operation is unable to requeue from a private futex to a process-shared one in the mutex structure, so requeue is simply disabled in this case by waking all waiters. for robust mutexes, the kernel always performs a non-private wake when the owner dies. in order not to introduce a behavioral regression in non-process-shared robust mutexes (when the owning thread dies), they are simply forced to be treated as process-shared for now, giving correct behavior at the expense of performance. this can be fixed by adding explicit code to pthread_exit to do the right thing for non-shared robust mutexes in userspace rather than relying on the kernel to do it, and will be fixed in this way later. since not all supported kernels have private futex support, the new code detects EINVAL from the futex syscall and falls back to making the call without the private flag. no attempt to cache the result is made; caching it and using the cached value efficiently is somewhat difficult, and not worth the complexity when the benefits would be seen only on ancient kernels which have numerous other limitations and bugs anyway.
Diffstat (limited to 'src/internal')
-rw-r--r--src/internal/pthread_impl.h10
1 files changed, 8 insertions, 2 deletions
diff --git a/src/internal/pthread_impl.h b/src/internal/pthread_impl.h
index 650e8115..826191c2 100644
--- a/src/internal/pthread_impl.h
+++ b/src/internal/pthread_impl.h
@@ -76,6 +76,7 @@ struct __timer {
#define _c_destroy __u.__i[8]
#define _rw_lock __u.__i[0]
#define _rw_waiters __u.__i[1]
+#define _rw_shared __u.__i[2]
#define _b_lock __u.__i[0]
#define _b_waiters __u.__i[1]
#define _b_limit __u.__i[2]
@@ -108,8 +109,13 @@ void __unmapself(void *, size_t);
int __timedwait(volatile int *, int, clockid_t, const struct timespec *, void (*)(void *), void *, int);
void __wait(volatile int *, volatile int *, int, int);
-#define __wake(addr, cnt, priv) \
- __syscall(SYS_futex, addr, FUTEX_WAKE, (cnt)<0?INT_MAX:(cnt))
+static inline void __wake(volatile void *addr, int cnt, int priv)
+{
+ if (priv) priv = 128;
+ if (cnt<0) cnt = INT_MAX;
+ __syscall(SYS_futex, addr, FUTEX_WAKE|priv, cnt) != -EINVAL ||
+ __syscall(SYS_futex, addr, FUTEX_WAKE, cnt);
+}
void __acquire_ptc();
void __release_ptc();