aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2009-08-20Improve backtrace_symbols{,_fd} output when missing symbols.roland/backtrace-symsRoland McGrath3-46/+92
2009-08-16Fix 64-bit platform handling in test cases for generated headers with constants.Ulrich Drepper2-3/+8
2009-08-14Improve test-skeleton.c to clean up after dead parent.Ulrich Drepper2-3/+19
2009-08-11Add CFI directives to x86-64 pthread_rwlock_unlock.Ulrich Drepper2-2/+8
2009-08-10Add CFI directives to x86-64 pthread_rwlock_{rd,wr)lock.Ulrich Drepper3-2/+12
2009-08-10SH: fix clobber list in stdlib/longlong.hSUGIOKA Toshinobu2-3/+9
2009-08-10Fix check for PI mutex in x86-64 pthread_cond_signalAndreas Schwab2-3/+9
Register eax contains the syscall number, use a different one instead.
2009-08-08Optimize x86-64 version of sem_timedwait.Ulrich Drepper2-65/+148
2009-08-08Remove duplicate NEWS entry.Ulrich Drepper1-3/+0
2009-08-08Yet more news items.Ulrich Drepper1-0/+4
2009-08-08Support mixed SSE/AVX audit and check AVX only once.H.J. Lu11-239/+1062
This patch fixes mixed SSE/AVX audit and checks AVX only once in _dl_runtime_profile. When an AVX or SSE register value in pltenter is modified, we have to make sure that the SSE part value is the same in both lr_xmm and lr_vector fields so that pltexit will get the correct value from either lr_xmm or lr_vector fields. AVX-enabled pltenter should update both lr_xmm and lr_vector fields to support stacked AVX/SSE pltenter functions.
2009-08-08Use PIC only if SHARED is defined.H.J. Lu3-0/+36
For ia32, we can avoid PIC in IFUNC functions in static library.
2009-08-08Simplify cpuid.h configure test.Jim Meyering3-14/+548
2009-08-08Another minor optimization of x86-64 pthread_cond_wait.Ulrich Drepper2-15/+13
2009-08-08Move SSE4.2 functions together.Ulrich Drepper3-0/+8
2009-08-08Add some news items.Ulrich Drepper1-3/+20
2009-08-07Add SSSE3-optimized implementation of str{,n}cmp for x86-64.Ulrich Drepper6-47/+194
2009-08-07Small optimizations to cancellable x86-64 code.Ulrich Drepper5-61/+49
2009-08-07Avoid warning through fake initialization.Ulrich Drepper2-0/+7
2009-08-07Fix whitespace in last patch.Ulrich Drepper1-1/+1
2009-08-07Add the missing "; \".H.J. Lu2-1/+5
2009-08-07Fix expanding STB_GNU_UNIQUE hash table.Andreas Schwab2-1/+6
An invalid symbol name pointer was entered into the hash table while enlarging it.
2009-08-07Fix whitespaces in last checkin.Ulrich Drepper1-1/+1
2009-08-07Properly count number of logical processors on Intel CPUs.H.J. Lu2-4/+43
The meaning of the 25-14 bits in EAX returned from cpuid with EAX = 4 has been changed from "the maximum number of threads sharing the cache" to "the maximum number of addressable IDs for logical processors sharing the cache" if cpuid takes EAX = 11. We need to use results from both EAX = 4 and EAX = 11 to get the number of threads sharing the cache. The 25-14 bits in EAX on Core i7 is 15 although the number of logical processors is 8. Here is a white paper on this: http://software.intel.com/en-us/articles/intel-64-architecture-processor-topology-enumeration/ This patch correctly counts number of logical processors on Intel CPUs with EAX = 11 support on cpuid. Tested on Dinnington, Core i7 and Nehalem EX/EP. It also fixed Pentium Ds workaround since EBX may not have the right value returned from cpuid with EAX = 1.
2009-08-07Fix sed expression in TAGS command.Andreas Schwab2-2/+7
The backslash-newline pair is interpreted as the beginning of an address regex.
2009-08-06Ignore TAGS.Andreas Schwab1-0/+1
2009-08-04Add x86 SSE strlen.Ulrich Drepper4-6/+166
2009-08-04Add x86 32-bit SSE4.2 string functions.H.J. Lu14-4/+243
This patch adds 32bit SSE4.2 string functions. It uses -16L instead of 0xfffffffffffffff0L, which works for both 32bit and 64bit long. Tested on 32bit Core i7 and Core 2.
2009-08-04Optimize x86-64 syscall cancellation handling.Ulrich Drepper6-44/+191
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.
2009-08-02Remove leftover code from Linux/x86 ____longjmp_chk.Ulrich Drepper1-6/+0
2009-08-02x86/x86-64 now needs <cpuid.h> from gcc.Ulrich Drepper3-44/+67
2009-08-01Remove last trace of bounded pointer handling from ____longjmp_chk on x86-64.Ulrich Drepper1-1/+1
2009-07-31Macro cleanup.Ulrich Drepper2-8/+12
Better definition of the *_NITSET macros.
2009-07-31Merge branch 'master' of file:///net/myware66/home/drepper/gnu/libcUlrich Drepper3-117/+59
2009-07-31Regenerated.Ulrich Drepper1-8/+40
2009-07-31Optimize x86 and x86-64 ____longjmp_chk for Linux.Ulrich Drepper3-117/+54
2009-07-31Fix ____longjmp_chk on x86-64.Ulrich Drepper2-2/+7
After a recent change to fix CFI in ____longjmp_chk the test of the ss_flags used the wrong memory location.
2009-07-31Support multiarch for i686.H.J. Lu13-49/+125
This patch adds multiarch support when configured for i686. I modified some x86-64 functions to support 32bit. I will contribute 32bit SSE string and memory functions later.
2009-07-31Fix obstack* on i?86Jakub Jelinek2-0/+5
obstack calls several callbacks, so on i?86 it'd better be compiled without -mpreferred-stack-boundary=2, otherwise the callbacks are called with misaligned stack.
2009-07-31Remove CHEC_ESP handling from i386 __longjmp.Ulrich Drepper1-9/+0
2009-07-30Whitespace cleanup.Ulrich Drepper1-2/+2
2009-07-30Add sigstack handling to Linux ____longjmp_chk on i386.Ulrich Drepper4-61/+156
All other i386 ports need to provide their own versions.
2009-07-30____longjmp_chk is now OS-specific.Ulrich Drepper3-145/+151
We use sigaltstack internally which on some systems is a syscall and should be used as such. Move the x86-64 version to the Linux specific directory and create in its place a file which always causes compile errors.
2009-07-30Change code a bit to correct CFI.Ulrich Drepper1-1/+3
2009-07-30Optimize ____longjmp_chk for x86-64 a bit.Ulrich Drepper1-5/+3
2009-07-30Add CFLAGS definition missing from last patch.Ulrich Drepper1-0/+2
2009-07-30Add test case for ____longjmp_chk vs signal stacks.Ulrich Drepper3-1/+119
2009-07-30Fix x86-64 ____longjmp_chk to handle signal stacks.Ulrich Drepper3-7/+111
The simple test previously used might trigger if the longjmp jumps from the signal stack to the normal stack. We now explicitly test for this case.
2009-07-30Stop backtrace when we make no more progress.Ulrich Drepper2-2/+13
2009-07-29Add support for x86-64 fma instruction.Ulrich Drepper6-2/+110
Use it to implement fma and fmaf, if possible.