Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Minor optimizations and cleanups of x86 cond_broadcast. | Ulrich Drepper | 2009-11-18 | 2 | -11/+10 |
| | |||||
* | Update cfi offsets for pthread_cond_broadcast and signal fir x86. | Dinakar Guniguntala | 2009-11-18 | 2 | -38/+16 |
| | |||||
* | Minimal unwind section size reduction. | Ulrich Drepper | 2009-11-17 | 1 | -17/+14 |
| | |||||
* | Use cfi directives in x86 pthread_cond_{,timed}wait. | Ulrich Drepper | 2009-11-17 | 2 | -344/+133 |
| | |||||
* | Make name of libgcc_s library configurable | Andreas Schwab | 2009-11-03 | 2 | -4/+6 |
| | |||||
* | configure tweaks, support $libc_add_on_config_subdirs | Roland McGrath | 2009-09-15 | 2 | -62/+38 |
| | |||||
* | Fix malformed #pragma. | Andreas Schwab | 2009-09-07 | 1 | -1/+1 |
| | |||||
* | Fix timer_create to initialize timer_t properly. | Suzuki Poulose | 2009-09-02 | 1 | -1/+2 |
| | |||||
* | SH lowlevellock broken for FUTEX_CLOCK_REALTIME. | Andrew Stubbs | 2009-08-28 | 1 | -9/+9 |
| | |||||
* | Handle AVX saving on x86-64 in interrupted smbol lookups. | Ulrich Drepper | 2009-08-25 | 1 | -2/+8 |
| | | | | | | | | | 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. | ||||
* | More namespace cleanups. | Ulrich Drepper | 2009-08-23 | 1 | -4/+6 |
| | |||||
* | Rvert accidental checkins. | Ulrich Drepper | 2009-08-22 | 5 | -545/+0 |
| | |||||
* | Add sigstack handling to Linux ____longjmp_chk on powerpc. | Andreas Schwab | 2009-08-22 | 5 | -0/+545 |
| | |||||
* | Add CFI directives to x86-64 pthread_rwlock_unlock. | Ulrich Drepper | 2009-08-11 | 1 | -2/+3 |
| | |||||
* | Add CFI directives to x86-64 pthread_rwlock_{rd,wr)lock. | Ulrich Drepper | 2009-08-10 | 2 | -2/+6 |
| | |||||
* | Fix check for PI mutex in x86-64 pthread_cond_signal | Andreas Schwab | 2009-08-10 | 1 | -3/+3 |
| | | | | Register eax contains the syscall number, use a different one instead. | ||||
* | Optimize x86-64 version of sem_timedwait. | Ulrich Drepper | 2009-08-08 | 1 | -65/+145 |
| | |||||
* | Another minor optimization of x86-64 pthread_cond_wait. | Ulrich Drepper | 2009-08-08 | 1 | -15/+7 |
| | |||||
* | Small optimizations to cancellable x86-64 code. | Ulrich Drepper | 2009-08-07 | 4 | -61/+40 |
| | |||||
* | Optimize x86-64 syscall cancellation handling. | Ulrich Drepper | 2009-08-04 | 5 | -44/+179 |
| | | | | | | | 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. | ||||
* | Regenerated. | Ulrich Drepper | 2009-07-31 | 1 | -8/+40 |
| | |||||
* | Fix x86-64 TCB alignment for future processor versions. | Ulrich Drepper | 2009-07-29 | 1 | -1/+6 |
| | |||||
* | Preserve SSE registers in runtime relocations on x86-64. | Ulrich Drepper | 2009-07-29 | 2 | -18/+56 |
| | | | | | | | | | | 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. | ||||
* | Fix bookkeeping in mutex when using requeue_pi. | Ulrich Drepper | 2009-07-28 | 5 | -20/+40 |
| | |||||
* | Check for .cfi_{personality,lsda} on x86-64. | Ulrich Drepper | 2009-07-23 | 2 | -0/+59 |
| | | | | We need this support in NPTL now to avoid the hand-coded tables. | ||||
* | Fix pthread_cond_timedwait error handling on old kernels. | Ulrich Drepper | 2009-07-23 | 1 | -2/+2 |
| | |||||
* | Minor optimizations of last x86-64 condvar changes. | Ulrich Drepper | 2009-07-20 | 2 | -23/+16 |
| | |||||
* | Support requeueing for condvars using PI mutex. x86-64 only. | Ulrich Drepper | 2009-07-19 | 5 | -36/+168 |
| | | | | | Add support for the new FUTEX_WAIT_REQUEUE_PI and FUTEX_CMP_REQUEUE_PI options of futex. | ||||
* | Make x86-64 pthread_cond_timedwait more robust. | Ulrich Drepper | 2009-07-19 | 1 | -0/+2 |
| | | | | | | 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. | ||||
* | Extend x86-64 __lll_robust_timedlock_wait to use futex syscall with absolute ↵ | Ulrich Drepper | 2009-07-19 | 1 | -2/+76 |
| | | | | timeout. | ||||
* | Extend x86-64 pthread_rwlock_timedrdlock to use futex syscall with absolute ↵ | Ulrich Drepper | 2009-07-18 | 1 | -18/+55 |
| | | | | timeout. | ||||
* | Pretty printing last change. | Ulrich Drepper | 2009-07-18 | 1 | -6/+6 |
| | |||||
* | Extend x86-64 pthread_rwlock_timedwrlock to use futex syscall with absolute ↵ | Ulrich Drepper | 2009-07-18 | 1 | -12/+49 |
| | | | | timeout. | ||||
* | Remove leftover cfi. | Ulrich Drepper | 2009-07-18 | 1 | -4/+1 |
| | |||||
* | Extend x86-64 pthread_cond_timedwait to use futex syscall with absolute timeout. | Ulrich Drepper | 2009-07-18 | 1 | -126/+292 |
| | |||||
* | Optimize x86-64 pthread_cond_timedwait. | Ulrich Drepper | 2009-07-18 | 1 | -144/+188 |
| | | | | | Instead of actively registering an unwind buffer we now use the exception handling functionality of the gcc runtime. | ||||
* | Optimize x86-64 pthread_cond_wait. | Ulrich Drepper | 2009-07-18 | 2 | -144/+309 |
| | | | | | Instead of actively registering an unwind buffer we now use the exception handling functionality of the gcc runtime. | ||||
* | Extend x86-64 sem_timedwait to use futex syscall with absolute timeout. | Ulrich Drepper | 2009-07-17 | 1 | -46/+116 |
| | |||||
* | Consistently use symbolic constants. | Ulrich Drepper | 2009-07-17 | 1 | -4/+3 |
| | |||||
* | Replace hand-coded unwind tables from x86-64 sem_timedwait. | Ulrich Drepper | 2009-07-17 | 1 | -122/+29 |
| | |||||
* | Optimize x86-64 sem_wait for uncontested semaphore. | Ulrich Drepper | 2009-07-17 | 1 | -24/+27 |
| | |||||
* | Replace hand-coded unwind tables from x86-64 sem_wait. | Ulrich Drepper | 2009-07-17 | 1 | -101/+25 |
| | |||||
* | Replace hand-coded unwind tables from x86-64 pthread_once. | Ulrich Drepper | 2009-07-17 | 1 | -106/+22 |
| | |||||
* | Replace hand-coded unwind tables from x86-64 pthread_cond_wait. | Ulrich Drepper | 2009-07-17 | 1 | -76/+18 |
| | |||||
* | Implement pthread_sigqueue. | Ulrich Drepper | 2009-06-12 | 2 | -1/+90 |
| | | | | | | 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. | ||||
* | Fix futex syscall parameter for x86 absolute timeout waits. | Bryan Kadzban | 2009-06-11 | 1 | -1/+1 |
| | | | | This affects only installations compiled for kernels older than 2.6.18. | ||||
* | Unify source for async cancel handling. | Ulrich Drepper | 2009-05-16 | 1 | -87/+4 |
| | | | | | Unify all three places where we enable async cancellation for syscalls. Optimize a bit. | ||||
* | * cancellation.c (__pthread_disable_asynccancel): Use THREAD_ATOMIC_AND | Ulrich Drepper | 2009-04-27 | 2 | -2/+28 |
| | | | | | | | | is available. * libc-cancellation.c (__libc_disable_asynccancel): Likewise. * sysdeps/x86_64/tls.h: Define THREAD_ATOMIC_AND. * sysdeps/i386/tls.h: Likewise. (tcbhead_t): Add __private_tm member. | ||||
* | * sysdeps/unix/sysv/linux/libc_pthread_init.c (__libc_pthread_init): | Ulrich Drepper | 2009-04-26 | 1 | -4/+4 |
| | | | | Avoid warning by using may_alias attribute on ptrhack. | ||||
* | [BZ #5807] | Ulrich Drepper | 2009-03-15 | 1 | -102/+21 |
| | | | | | | | 2009-03-15 Ulrich Drepper <drepper@redhat.com> [BZ #5807] * string/strlen.c (strlen): Fix omission in the expression to test for NUL bytes. |