aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2009-07-19Make x86-64 pthread_cond_timedwait more robust.Ulrich Drepper2-0/+7
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.
2009-07-19Extend x86-64 __lll_robust_timedlock_wait to use futex syscall with absolute ↵Ulrich Drepper2-2/+80
timeout.
2009-07-18Add more sem_timedwait tests.Ulrich Drepper3-1/+20
2009-07-18Extend x86-64 pthread_rwlock_timedrdlock to use futex syscall with absolute ↵Ulrich Drepper2-18/+57
timeout.
2009-07-18Pretty printing last change.Ulrich Drepper1-6/+6
2009-07-18Extend x86-64 pthread_rwlock_timedwrlock to use futex syscall with absolute ↵Ulrich Drepper2-12/+53
timeout.
2009-07-18Remove leftover cfi.Ulrich Drepper1-4/+1
2009-07-18Extend pthread_cond_timedwait tests.Ulrich Drepper2-1/+18
2009-07-18Extend x86-64 pthread_cond_timedwait to use futex syscall with absolute timeout.Ulrich Drepper2-126/+296
2009-07-18Optimize x86-64 pthread_cond_timedwait.Ulrich Drepper2-144/+190
Instead of actively registering an unwind buffer we now use the exception handling functionality of the gcc runtime.
2009-07-18Optimize x86-64 pthread_cond_wait.Ulrich Drepper3-144/+315
Instead of actively registering an unwind buffer we now use the exception handling functionality of the gcc runtime.
2009-07-17Extend x86-64 sem_timedwait to use futex syscall with absolute timeout.Ulrich Drepper2-46/+120
2009-07-17Consistently use symbolic constants.Ulrich Drepper1-4/+3
2009-07-17Replace hand-coded unwind tables from x86-64 sem_timedwait.Ulrich Drepper2-122/+31
2009-07-17Optimize x86-64 sem_wait for uncontested semaphore.Ulrich Drepper2-24/+30
2009-07-17Replace hand-coded unwind tables from x86-64 sem_wait.Ulrich Drepper2-101/+26
2009-07-17Replace hand-coded unwind tables from x86-64 pthread_once.Ulrich Drepper4-113/+65
2009-07-17Replace hand-coded unwind tables from x86-64 pthread_cond_wait.Ulrich Drepper2-76/+24
2009-07-17Revert "Fix lock handling in memory hander of nscd."Ulrich Drepper8-16/+27
This reverts commit 137028b4d7e50f71906c1656c27079eac5a1d085. Conflicts: ChangeLog
2009-07-17Add missing BZ number in ChangeLog.Ulrich Drepper1-0/+1
2009-07-16Handle overly large answer buffers in resolver.Ulrich Drepper2-1/+7
In EDNS0 records the maximum result size is transmitted in a 16 bit value. Large buffer sizes were handled incorrectly by using only the low 16 bits. Fix this by limiting the size to 0xffff.
2009-07-16Fix lock handling in memory hander of nscd.Petr Baudis8-27/+16
The commit 20e498bd removes the pthread_mutex_rdlock() calls, but not the corresponding pthread_mutex_unlock() calls. Also, the database lock is never unlocked in one branch of the mempool_alloc() if. I think unreproducible random assert(dh->usable) crashes in prune_cache() were caused by this. But an easy way to make nscd threads hang with the broken locking was.
2009-07-16Use correct release semantic in list update.Andreas Schwab2-1/+7
nscd uses lockfree lists and we need to ensure the correct release semantics is used when adding to the list.
2009-07-16Fix race in corruption check.Ulrich Drepper2-2/+29
With atomic fastbins the checks performed can race with concurrent modifications of the arena. If we detect a problem re-do the test after getting the lock.
2009-07-16Use rel semantics of cas instead of acq semantics with full barrier before ↵Jakub Jelinek3-13/+35
it in _int_free The following patch fixes catomic_compare_and_exchange_*_rel definitions (which were never used and weren't correct) and uses catomic_compare_and_exchange_val_rel in _int_free. Comparing to the pre-2009-07-02 --enable-experimental-malloc state the generated code should be identical on all arches other than ppc/ppc64 and on ppc/ppc64 should use lwsync instead of isync barrier.
2009-07-16Remove warning and little optimization.Ulrich Drepper3-0/+9
The prototype for _dl_higher_prime_number was missing. While at it, the function is now marked with internal_function.
2009-07-16Optimize restoring of ymm registers on x86-64.Ulrich Drepper2-43/+39
The patch mainly reduces the code size but also avoids some jumps.
2009-07-16Fix up whitespaces in new memcmp for x86-64.Ulrich Drepper1-42/+42
2009-07-16memcmp implementation for x86-64 using SSE2.H.J. Lu2-0/+363
2009-07-15Fix thinko in AVX audit patch.Ulrich Drepper1-20/+4
Don't use AVX instructions too often.
2009-07-15Fix typo in last change.Ulrich Drepper1-1/+1
2009-07-15Secure AVX changes for auditing code.Ulrich Drepper3-326/+299
The original AVX patch used a function pointer to handle the difference between machines with and without AVX support. This is insecure. A well-placed memory exploit could lead to redirection of the execution. Using a variable and several tests is a bit slower but cannot be exploited in this way.
2009-07-15Fix build issue with modules for audit test on machines != x86-64.Ulrich Drepper2-3/+10
2009-07-10Add AVX support to ld.so auditing for x86-64.H.J. Lu19-126/+1018
2009-07-10Remove do-lookup.h.Ulrich Drepper4-388/+369
It is not necessary/useful anymore to have the content separate from dl-lookup.c.
2009-07-10Fix comment in Linux's <sys/epoll.h>.Ulrich Drepper2-2/+6
2009-07-09Implement STB_GNU_UNIQUE handling.Ulrich Drepper16-12/+375
Some symbols have to be identified process-wide by their name. This is particularly important for some C++ features (e.g., class local static data and static variables in inline functions). This cannot completely be implemented with ELF functionality so far. The STB_GNU_UNIQUE binding helps by ensuring the dynamic linker will always use the same definition for all symbols with the same name and this binding.
2009-07-07Define STB_GNU_UNIQUE.Ulrich Drepper2-0/+3
2009-07-07Clean up code for hash table handling in ld.so.Ulrich Drepper3-69/+74
2009-07-06Optimize test for valid ELF symbol types in lookup function.ibm/masterUlrich Drepper2-7/+11
2009-07-05Fix wrong PPC_FEATURE_* values.Andreas Schwab2-2/+7
Nothing uses these wrong values yet, but it fixes a warning due to conflicting definitions in <asm/cputable.h>.
2009-07-03Minor cleanups in recently added files.Ulrich Drepper3-79/+60
2009-07-03Align functions to 16-byte boundary.Ulrich Drepper5-0/+12
Some of the new multi-arch string functions for x86-64 were not aligned to 16 byte boundarie,s possibly creating unnecessary cache line misses and delays.
2009-07-03Add SSE4.2 support for strcspn, strpbrk, and strspn on x86-64.H.J. Lu14-7/+875
2009-07-02Fix whitespace in last patch.Ulrich Drepper2-2/+2
2009-07-02Fix handling of xmm6 in ld.so audit hooks on x86-64.H.J. Lu6-3/+227
2009-07-02Whitespace fixes in last patch.Ulrich Drepper1-31/+31
2009-07-02SSSE3 strcpy/stpcpy for x86-64H.J. Lu10-12/+1982
This patch adds SSSE3 strcpy/stpcpy. I got up to 4X speed up on Core 2 and Core i7. I disabled it on Atom since SSSE3 version is slower for shorter (<64byte) data.
2009-07-02Fix possible race when freeing object in fast bin list.Ulrich Drepper2-0/+6
2009-07-01Fix NIS and NIS+ getnetbyaddr backends.Ulrich Drepper3-2/+7
The addresses were interpreted as class-based network addresses.
generated by cgit v1.1 at 2024-12-29 01:28:43 +0000