summaryrefslogtreecommitdiff
path: root/src/thread
AgeCommit message (Expand)AuthorFilesLines
2011-04-22fix initial stack alignment in new threads on x86_64Rich Felker1-1/+1
2011-04-20fix minor bugs due to incorrect threaded-predicate semanticsRich Felker2-5/+3
2011-04-19move some more code out of pthread_create.cRich Felker2-7/+4
2011-04-19fix uninitialized waiters field in semaphoresRich Felker1-0/+1
2011-04-18recheck cancellation disabled flag after syscall returns EINTRRich Felker1-1/+1
2011-04-17fix typo in x86_64 cancellable syscall asmRich Felker1-1/+1
2011-04-17pthread_exit is not supposed to affect cancellabilityRich Felker1-2/+0
2011-04-17fix pthread_exit from cancellation handlerRich Felker1-5/+5
2011-04-17clean up handling of thread/nothread mode, lockingRich Felker3-16/+10
2011-04-17debloat: use __syscall instead of syscall where possibleRich Felker2-2/+2
2011-04-17fix bugs in cancellable syscall asmRich Felker3-11/+12
2011-04-17optimize cancellation enable/disable codeRich Felker3-4/+10
2011-04-17don't use pthread_once when there is no danger in raceRich Felker1-2/+5
2011-04-17fix some minor issues in cancellation handling patchRich Felker3-11/+19
2011-04-17overhaul pthread cancellationRich Felker13-59/+182
2011-04-14change sem_trywait algorithm so it never has to call __wakeRich Felker1-3/+2
2011-04-14cheap trick to further optimize locking normal mutexesRich Felker2-2/+2
2011-04-14use a separate signal from SIGCANCEL for SIGEV_THREAD timersRich Felker1-2/+0
2011-04-13simplify cancellation point handlingRich Felker2-16/+5
2011-04-06fixed crash in new rsyscall (failure to set sa_flags for signal handler)Rich Felker1-0/+2
2011-04-06consistency: change all remaining syscalls to use SYS_ rather than __NR_ prefixRich Felker7-8/+8
2011-04-06move rsyscall out of pthread_create moduleRich Felker2-96/+122
2011-04-06pthread exit stuff: don't bother setting errno when we won't check it.Rich Felker1-2/+2
2011-04-06fix rsyscall handler: must not clobber errno from signal contextRich Felker1-2/+4
2011-04-06major semaphore improvements (performance and correctness)Rich Felker5-21/+37
2011-04-05new framework to inhibit thread cancellation when neededRich Felker2-5/+15
2011-04-03pthread_create need not set errnoRich Felker1-1/+1
2011-04-03block all signals during rsyscallRich Felker1-4/+9
2011-04-03fix race condition in rsyscall handlerRich Felker1-1/+1
2011-04-03don't trust siginfo in rsyscall handlerRich Felker1-3/+2
2011-04-03simplify calling of timer signal handlerRich Felker1-7/+4
2011-04-03simplify pthread tsd key handlingRich Felker2-8/+6
2011-04-03omit pthread tsd dtor code if tsd is not usedRich Felker2-14/+24
2011-04-01simplify setting result on thread cancellationRich Felker1-1/+1
2011-04-01use bss instead of mmap for main thread's pthread thread-specific dataRich Felker2-9/+4
2011-04-01fix misspelled PTHREAD_CANCELED constantRich Felker1-1/+1
2011-04-01use a_store to set cancel flag in pthread_cancel, to ensure a barrierRich Felker1-1/+1
2011-03-31simplify pthread_key_deleteRich Felker1-1/+1
2011-03-31greatly simplify pthread_key_create (~20% size reduction)Rich Felker1-10/+9
2011-03-30avoid crash on stupid but allowable usage of pthread_mutex_unlockRich Felker1-1/+3
2011-03-30streamline mutex unlock to remove a useless branch, use a_store to unlockRich Felker1-2/+6
2011-03-30cheap special-case optimization for normal mutexesRich Felker1-0/+4
2011-03-29revert mutex "optimization" that turned out to be worseRich Felker1-1/+1
2011-03-29major improvements to cancellation handlingRich Felker2-6/+13
2011-03-28revert some more spin optimizations that turned out to be pessimizationsRich Felker2-3/+2
2011-03-28fix broken spinlock due to miscompilationRich Felker1-1/+1
2011-03-25match glibc/lsb cancellation abi on i386Rich Felker6-0/+36
2011-03-24prepare pthread_spin_unlock for archs that need memory barriersRich Felker1-1/+2
2011-03-24optimize contended case for pthread_spin_trylockRich Felker1-1/+2
2011-03-24optimize spinlock spinRich Felker1-1/+1
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-06 00:25:30 +0000