Andrew Stubbs
7812c65b90
SH lowlevellock broken for FUTEX_CLOCK_REALTIME.
2009-08-28 14:57:16 -07:00
Ulrich Drepper
84088310ce
Handle AVX saving on x86-64 in interrupted smbol lookups.
...
If a signal arrived during a symbol lookup and the signal handler also
required a symbol lookup, the end of the lookup in the signal handler reset
the flag whether restoring AVX/SSE registers is needed. Resetting means
in this case that the tail part of the outer lookup code will try to
restore the registers and this can fail miserably. We now restore to the
previous value which makes nesting calls possible.
2009-08-25 10:42:30 -07:00
Ulrich Drepper
b42a214c18
Hint to kernel that thread stack memory can be removed.
2009-08-24 16:23:47 -07:00
Ulrich Drepper
2d094b7395
More namespace cleanups.
2009-08-23 13:59:41 -07:00
Ulrich Drepper
cd16986ee3
Rvert accidental checkins.
2009-08-22 17:58:04 -07:00
Andreas Schwab
15efafdf07
Add sigstack handling to Linux ____longjmp_chk on powerpc.
2009-08-22 02:01:51 -07:00
Ulrich Drepper
ae0d545003
Add CFI directives to x86-64 pthread_rwlock_unlock.
2009-08-11 20:47:36 -07:00
Ulrich Drepper
1bc2b97ee4
Add CFI directives to x86-64 pthread_rwlock_{rd,wr)lock.
2009-08-10 11:26:16 -07:00
Andreas Schwab
ec4922395b
Fix check for PI mutex in x86-64 pthread_cond_signal
...
Register eax contains the syscall number, use a different one instead.
2009-08-10 08:10:11 -07:00
Ulrich Drepper
efa0569d2b
Optimize x86-64 version of sem_timedwait.
2009-08-08 17:48:09 -07:00
Ulrich Drepper
49eea97b00
Another minor optimization of x86-64 pthread_cond_wait.
2009-08-08 10:21:46 -07:00
Ulrich Drepper
9083bcc5dc
Small optimizations to cancellable x86-64 code.
2009-08-07 20:36:53 -07:00
Ulrich Drepper
421665c40a
Optimize x86-64 syscall cancellation handling.
...
The syscall wrappers had to save and restore the syscall parameter
values and return value when calling the functions to enable/disable
cancellation were called. Not anymore. The called functions are
special and don't modify any unexpected registers.
2009-08-04 11:03:46 -07:00
Ulrich Drepper
bd03a1afa2
Macro cleanup.
...
Better definition of the *_NITSET macros.
2009-07-31 22:30:30 -07:00
Ulrich Drepper
22d94a7bc9
Regenerated.
2009-07-31 21:48:59 -07:00
Ulrich Drepper
586fa886ad
Fix x86-64 TCB alignment for future processor versions.
2009-07-29 09:01:04 -07:00
Ulrich Drepper
b48a267b8f
Preserve SSE registers in runtime relocations on x86-64.
...
SSE registers are used for passing parameters and must be preserved
in runtime relocations. This is inside ld.so enforced through the
tests in tst-xmmymm.sh. But the malloc routines used after startup
come from libc.so and can be arbitrarily complex. It's overkill
to save the SSE registers all the time because of that. These calls
are rare. Instead we save them on demand. The new infrastructure
put in place in this patch makes this possible and efficient.
2009-07-29 08:33:03 -07:00
Ulrich Drepper
b0948ffdcb
Fix bookkeeping in mutex when using requeue_pi.
2009-07-28 09:40:39 -07:00
Ulrich Drepper
e73e694e38
pthread_mutex_unlock needs to use _rel semantics for atomic ops.
2009-07-27 13:46:56 -07:00
Ulrich Drepper
052757bfa6
Revert "Memory ordering in pthread_mutex_{,timed}lock."
...
This reverts commit 7b7f43bed1
2009-07-27 13:43:01 -07:00
Ulrich Drepper
7b7f43bed1
Memory ordering in pthread_mutex_{,timed}lock.
...
All commits should have happened before the mutex lock is taken.
Therefore use the _rel variant of the cmpxchg atomic op.
2009-07-26 13:00:04 -07:00
Ulrich Drepper
01b597da40
Check for .cfi_{personality,lsda} on x86-64.
...
We need this support in NPTL now to avoid the hand-coded tables.
2009-07-23 17:15:56 -07:00
Ulrich Drepper
f1adf1f490
Fix pthread_cond_timedwait error handling on old kernels.
2009-07-23 16:39:06 -07:00
Ulrich Drepper
c3db953c16
Minor optimizations of last x86-64 condvar changes.
2009-07-20 08:39:47 -07:00
Ulrich Drepper
42e69bcf11
Support requeueing for condvars using PI mutex. x86-64 only.
...
Add support for the new FUTEX_WAIT_REQUEUE_PI and FUTEX_CMP_REQUEUE_PI
options of futex.
2009-07-19 20:56:40 -07:00
Ulrich Drepper
515a8908ce
Make x86-64 pthread_cond_timedwait more robust.
...
It just happens that __pthread_enable_asynccancel doesn't modify the $rdi
register. But this isn't guaranteed. Hence we reload the register after
the calls.
2009-07-19 14:54:56 -07:00
Ulrich Drepper
e2dca2fea3
Extend x86-64 __lll_robust_timedlock_wait to use futex syscall with absolute timeout.
2009-07-19 00:00:17 -07:00
Ulrich Drepper
3d77b2687f
Add more sem_timedwait tests.
2009-07-18 22:07:25 -07:00
Ulrich Drepper
32c6c342b6
Extend x86-64 pthread_rwlock_timedrdlock to use futex syscall with absolute timeout.
2009-07-18 21:53:26 -07:00
Ulrich Drepper
4c74e6522a
Pretty printing last change.
2009-07-18 21:41:52 -07:00
Ulrich Drepper
d979611eb9
Extend x86-64 pthread_rwlock_timedwrlock to use futex syscall with absolute timeout.
2009-07-18 21:35:33 -07:00
Ulrich Drepper
d9201c1365
Remove leftover cfi.
2009-07-18 13:08:21 -07:00
Ulrich Drepper
f8b6cd2182
Extend pthread_cond_timedwait tests.
2009-07-18 12:45:27 -07:00
Ulrich Drepper
e88726b483
Extend x86-64 pthread_cond_timedwait to use futex syscall with absolute timeout.
2009-07-18 12:44:12 -07:00
Ulrich Drepper
92618c954f
Optimize x86-64 pthread_cond_timedwait.
...
Instead of actively registering an unwind buffer we now use the
exception handling functionality of the gcc runtime.
2009-07-18 08:53:18 -07:00
Ulrich Drepper
30b1954abb
Optimize x86-64 pthread_cond_wait.
...
Instead of actively registering an unwind buffer we now use the
exception handling functionality of the gcc runtime.
2009-07-18 08:09:39 -07:00
Ulrich Drepper
f351f2b756
Extend x86-64 sem_timedwait to use futex syscall with absolute timeout.
2009-07-17 19:08:54 -07:00
Ulrich Drepper
312d667b85
Consistently use symbolic constants.
2009-07-17 16:39:27 -07:00
Ulrich Drepper
aee2665a17
Replace hand-coded unwind tables from x86-64 sem_timedwait.
2009-07-17 16:26:06 -07:00
Ulrich Drepper
0adae46817
Optimize x86-64 sem_wait for uncontested semaphore.
2009-07-17 15:50:23 -07:00
Ulrich Drepper
c3c2f3cf56
Replace hand-coded unwind tables from x86-64 sem_wait.
2009-07-17 15:31:36 -07:00
Ulrich Drepper
63601ccd16
Replace hand-coded unwind tables from x86-64 pthread_once.
2009-07-17 14:45:08 -07:00
Ulrich Drepper
d52c96e73a
Replace hand-coded unwind tables from x86-64 pthread_cond_wait.
2009-07-17 12:14:09 -07:00
Ulrich Drepper
bfdb73e145
Implement pthread_sigqueue.
...
The kernel from 2.3.31 on supports the rt_tgsigqueueinfo syscall.
Use it to implement the non-standard extension which, like
sigqueue, can pass additional data to the receiving thread.
2009-06-12 08:34:02 -07:00
Bryan Kadzban
1828530f09
Fix futex syscall parameter for x86 absolute timeout waits.
...
This affects only installations compiled for kernels older than 2.6.18.
2009-06-11 11:32:51 -07:00
Ulrich Drepper
e20c4ef0ef
libc-cancellation.c cleanup.
...
The unrelated function __libc_cleanup_routine should not be in
this file. Move it into its own file.
2009-05-16 15:04:27 -07:00
Ulrich Drepper
cba0ca7925
Unify source for async cancel handling.
...
Unify all three places where we enable async cancellation for
syscalls. Optimize a bit.
2009-05-16 14:55:59 -07:00
Ulrich Drepper
a5b8b56df7
Rename nptl/init.c to nptl/nptl-init.c.
...
Needed to allow overwriting architectures init.c in csu and nptl
individually. Fixes BZ #9924 .
2009-05-16 08:57:49 -07:00
Ulrich Drepper
6dd78596d5
ChangeLog entries incorrectly applied.
2009-05-15 21:03:49 -07:00
Jakub Jelinek
1f3615a1c9
Add missing export of fallocate64 on 32-bit platforms.
...
Due to a pasto the fallocate64 interface, introduced in glibc 2.10,
isn't exported for 32-bit Linux platforms. It is too late for this
now so exported them for glibc 2.11.
2009-05-15 21:00:09 -07:00
