aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2009-07-29Prepare use if IFUNC functions outside libc.so.Ulrich Drepper3-3/+42
We use a callback function into libc.so to get access to the data structure with the information and have special versions of the test macros which automatically use this function.
2009-07-29Fix x86-64 TCB alignment for future processor versions.Ulrich Drepper3-6/+14
2009-07-29Improve CFI in x86-64 ld.so trampoline code.Ulrich Drepper2-1/+7
2009-07-29Properly restore AVX registers on x86-64.H.J. Lu2-10/+14
tst-audit4 and tst-audit5 fail under AVX emulator due to je instead of jne. This patch fixes them.
2009-07-29Preserve SSE registers in runtime relocations on x86-64.Ulrich Drepper10-21/+188
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.
2009-07-28Fix bookkeeping of static TLS block for TLS_TCB_AT_TP architectures.Ulrich Drepper3-5/+18
2009-07-28Fix bookkeeping in mutex when using requeue_pi.Ulrich Drepper9-24/+83
2009-07-27pthread_mutex_unlock needs to use _rel semantics for atomic ops.Ulrich Drepper2-3/+9
2009-07-27Revert "Memory ordering in pthread_mutex_{,timed}lock."Ulrich Drepper3-19/+12
This reverts commit 7b7f43bed134db6a0da34282fffcbf0af10d4613.
2009-07-27Refine testing for xmm/ymm register use in x86-64 ld.so.Ulrich Drepper6-12/+86
The test now takes the callgraph into account. Only code called during runtime relocation is affected by the limitation. We now determine the affected object files as closely as possible from the outside. This allowed to remove some the specializations for some of the string functions as they are only used in other code paths.
2009-07-27Break out _dl_scope_free into its own file.Ulrich Drepper3-36/+59
This reduces the coarse static callgraph that can be discovered by looking at the object files.
2009-07-27Define and implement RES_USE_DNSSEC option in resolver.Adam Tkac5-5/+26
2009-07-27Fix STB_GNU_UNIQUE handling for > 30 unique symbols.Jakub Jelinek2-2/+9
There were several issues when the initial 31 entries hashtab filled up. size * 3 <= tab->n_elements is always false, table can't have more elements than its size. I assume from libiberty/hashtab.c this meant to be check for 3/4 full. Even after fixing that, _dl_higher_prime_number (31) apparently returns 31, only _dl_higher_prime_number (32) returns 61. And, size variable wasn't updated during reallocation, which means during reallocation the insertion of the new entry was done into a wrong spot. All this lead to a hang in ld.so, because a search with n_elements 31 size 31 wouldn't ever terminate.
2009-07-27No need for special strcmp for rtld.Ulrich Drepper2-29/+0
2009-07-26Make sure no code in ld.so uses xmm/ymm registers on x86-64.Ulrich Drepper11-0/+498
This patch introduces a test to make sure no function modifies the xmm/ymm registers. With the exception of the auditing functions. The test is probably too pessimistic. All code linked into ld.so is checked. Perhaps at some point the callgraph starting from _dl_fixup and _dl_profile_fixup is checked and we can start using faster SSE-using functions in parts of ld.so.
2009-07-26Add missing ChangeLog entry for last checkin.Ulrich Drepper1-0/+20
2009-07-26Add SSE2 support to str{,n}cmp for x86-64.H.J. Lu5-267/+2055
2009-07-26Memory ordering in pthread_mutex_{,timed}lock.Ulrich Drepper3-12/+19
All commits should have happened before the mutex lock is taken. Therefore use the _rel variant of the cmpxchg atomic op.
2009-07-26Compatibility of signalfd/eventfd with older kernels.Ulrich Drepper4-6/+34
2009-07-26Handle SERVFAIL, NOTIMP, REFUSED replies from DNS server better.Ulrich Drepper2-5/+5
When doing IPv4+6 lookups we have to pass up the error record from send_dg.
2009-07-26Define NT_GNU_GOLD_VERSION.Ulrich Drepper2-0/+7
2009-07-25Some some optimizations for x86-64 strcmp.H.J. Lu2-9/+7
2009-07-25Handle missing NSS modules and those without callbacks.Ulrich Drepper2-0/+6
getaddrinfo didn't update the status variable in that round of the loop if no callback was used.
2009-07-25Optimize x86-64 SSE4.2 strcmp.Ulrich Drepper2-0/+10
The file contained some code which was never used. Don't compile it in.
2009-07-24Don't automatically use /lib/modules/* headers.Ulrich Drepper3-24/+6
Ever since the /usr/include/linux headers got cleaned up this isn't necessary. Meanwhile everybody should have these cleanups.
2009-07-24More white space fixes.Ulrich Drepper1-4/+4
2009-07-24White space fixes in last checkin.Ulrich Drepper2-7/+7
2009-07-24S/390: Hardware iconv modules.Andreas Krebbel8-8/+1628
2009-07-23Check for .cfi_{personality,lsda} on x86-64.Ulrich Drepper3-0/+61
We need this support in NPTL now to avoid the hand-coded tables.
2009-07-23Fix pthread_cond_timedwait error handling on old kernels.Ulrich Drepper2-2/+7
2009-07-23Avoid cpuid instructions in cache info discovery.Ulrich Drepper2-19/+35
When multiarch is enabled we have this information stored. Use it.
2009-07-23Add more cache descriptors for L3 caches on x86 and x86-64.Ulrich Drepper3-0/+10
The most recent AP 485 describes a few more cache descriptors for L3 caches with 24-way associativity.
2009-07-23Perform test for Arom x86-64 in central place and handle it.Ulrich Drepper3-11/+15
There will be more than one function which, in multiarch mode, wants to use SSSE3. We should not test in each of them for Atoms with slow SSSE3. Instead, disable the SSSE3 bit in the startup code for such machines.
2009-07-23Avoid warnings in test cases.Ulrich Drepper4-0/+11
The posix/tst-rfc3484* test cases caused warnings in newer gccs because the unused but copied sin_zero part of sockaddr_in wasn't explicitly initialized.
2009-07-23Make include/unistd.h suitable for C++ test cases.Duncan Simpson2-0/+8
2009-07-23Preserve stack alignment in i386 makecontext.Ulrich Drepper2-6/+7
2009-07-23Minor optimization of unloading prevention patch.Ulrich Drepper1-5/+5
References to unique symbols from copy relocations can only come from executables which cannot be unloaded anyway. Optimize the code to set the unload flag a bit.
2009-07-23Fix comment.Ulrich Drepper1-1/+1
2009-07-23Some more fixes for the unique symbol handling.Ulrich Drepper2-5/+7
The hash value can be zero, so we need a different test for empty slots. And unify the way we prevent a DSO from being unloaded.
2009-07-23Handle unloading of DSO with a unique symbol definition.Ulrich Drepper4-6/+60
2009-07-21Add 2.11 news items.Ulrich Drepper1-1/+22
2009-07-21Minor cleanups in x86-64 strstr.Ulrich Drepper2-78/+60
2009-07-20Better check for optimization in new x86-64 strstr/strcasestr.Ulrich Drepper2-11/+21
2009-07-20SSE4.2 strstr/strcasestr for x86-64.H.J. Lu8-5/+551
This patch implements SSE4.2 strstr/strcasestr, using Knuth-Morris-Pratt string searching algorithm.
2009-07-20Use correct index for _NL_CTYPE_NONASCII_CASE.Ulrich Drepper2-5/+5
2009-07-20Check generated locale for non-ASCII 8-bit characters with case conversion.Ulrich Drepper5-4/+47
If a locale does not have 8-bit characters with case conversion which are different from the ASCII conversion (±0x20) then we can perform some optimizations. These will follow later.
2009-07-20Minor optimizations of last x86-64 condvar changes.Ulrich Drepper3-23/+22
2009-07-19Support requeueing for condvars using PI mutex. x86-64 only.Ulrich Drepper6-36/+177
Add support for the new FUTEX_WAIT_REQUEUE_PI and FUTEX_CMP_REQUEUE_PI options of futex.
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.