Age | Commit message (Expand) | Author | Files | Lines |
2011-04-17 | debloat: use __syscall instead of syscall where possible | Rich Felker | 2 | -2/+2 |
2011-04-17 | fix bugs in cancellable syscall asm | Rich Felker | 3 | -11/+12 |
2011-04-17 | optimize cancellation enable/disable code | Rich Felker | 3 | -4/+10 |
2011-04-17 | don't use pthread_once when there is no danger in race | Rich Felker | 1 | -2/+5 |
2011-04-17 | fix some minor issues in cancellation handling patch | Rich Felker | 3 | -11/+19 |
2011-04-17 | overhaul pthread cancellation | Rich Felker | 13 | -59/+182 |
2011-04-14 | change sem_trywait algorithm so it never has to call __wake | Rich Felker | 1 | -3/+2 |
2011-04-14 | cheap trick to further optimize locking normal mutexes | Rich Felker | 2 | -2/+2 |
2011-04-14 | use a separate signal from SIGCANCEL for SIGEV_THREAD timers | Rich Felker | 1 | -2/+0 |
2011-04-13 | simplify cancellation point handling | Rich Felker | 2 | -16/+5 |
2011-04-06 | fixed crash in new rsyscall (failure to set sa_flags for signal handler) | Rich Felker | 1 | -0/+2 |
2011-04-06 | consistency: change all remaining syscalls to use SYS_ rather than __NR_ prefix | Rich Felker | 7 | -8/+8 |
2011-04-06 | move rsyscall out of pthread_create module | Rich Felker | 2 | -96/+122 |
2011-04-06 | pthread exit stuff: don't bother setting errno when we won't check it. | Rich Felker | 1 | -2/+2 |
2011-04-06 | fix rsyscall handler: must not clobber errno from signal context | Rich Felker | 1 | -2/+4 |
2011-04-06 | major semaphore improvements (performance and correctness) | Rich Felker | 5 | -21/+37 |
2011-04-05 | new framework to inhibit thread cancellation when needed | Rich Felker | 2 | -5/+15 |
2011-04-03 | pthread_create need not set errno | Rich Felker | 1 | -1/+1 |
2011-04-03 | block all signals during rsyscall | Rich Felker | 1 | -4/+9 |
2011-04-03 | fix race condition in rsyscall handler | Rich Felker | 1 | -1/+1 |
2011-04-03 | don't trust siginfo in rsyscall handler | Rich Felker | 1 | -3/+2 |
2011-04-03 | simplify calling of timer signal handler | Rich Felker | 1 | -7/+4 |
2011-04-03 | simplify pthread tsd key handling | Rich Felker | 2 | -8/+6 |
2011-04-03 | omit pthread tsd dtor code if tsd is not used | Rich Felker | 2 | -14/+24 |
2011-04-01 | simplify setting result on thread cancellation | Rich Felker | 1 | -1/+1 |
2011-04-01 | use bss instead of mmap for main thread's pthread thread-specific data | Rich Felker | 2 | -9/+4 |
2011-04-01 | fix misspelled PTHREAD_CANCELED constant | Rich Felker | 1 | -1/+1 |
2011-04-01 | use a_store to set cancel flag in pthread_cancel, to ensure a barrier | Rich Felker | 1 | -1/+1 |
2011-03-31 | simplify pthread_key_delete | Rich Felker | 1 | -1/+1 |
2011-03-31 | greatly simplify pthread_key_create (~20% size reduction) | Rich Felker | 1 | -10/+9 |
2011-03-30 | avoid crash on stupid but allowable usage of pthread_mutex_unlock | Rich Felker | 1 | -1/+3 |
2011-03-30 | streamline mutex unlock to remove a useless branch, use a_store to unlock | Rich Felker | 1 | -2/+6 |
2011-03-30 | cheap special-case optimization for normal mutexes | Rich Felker | 1 | -0/+4 |
2011-03-29 | revert mutex "optimization" that turned out to be worse | Rich Felker | 1 | -1/+1 |
2011-03-29 | major improvements to cancellation handling | Rich Felker | 2 | -6/+13 |
2011-03-28 | revert some more spin optimizations that turned out to be pessimizations | Rich Felker | 2 | -3/+2 |
2011-03-28 | fix broken spinlock due to miscompilation | Rich Felker | 1 | -1/+1 |
2011-03-25 | match glibc/lsb cancellation abi on i386 | Rich Felker | 6 | -0/+36 |
2011-03-24 | prepare pthread_spin_unlock for archs that need memory barriers | Rich Felker | 1 | -1/+2 |
2011-03-24 | optimize contended case for pthread_spin_trylock | Rich Felker | 1 | -1/+2 |
2011-03-24 | optimize spinlock spin | Rich Felker | 1 | -1/+1 |
2011-03-24 | overhaul cancellation to fix resource leaks and dangerous behavior with signals | Rich Felker | 3 | -10/+21 |
2011-03-20 | global cleanup to use the new syscall interface | Rich Felker | 4 | -6/+5 |
2011-03-19 | if returning errno value directly from a syscall, we need to negate it. | Rich Felker | 2 | -2/+2 |
2011-03-19 | syscall overhaul part two - unify public and internal syscall interface | Rich Felker | 7 | -15/+9 |
2011-03-19 | overhaul syscall interface | Rich Felker | 1 | -2/+2 |
2011-03-17 | implement robust mutexes | Rich Felker | 8 | -10/+78 |
2011-03-17 | avoid function call to pthread_self in mutex unlock | Rich Felker | 1 | -1/+1 |
2011-03-17 | unify lock and owner fields of mutex structure | Rich Felker | 3 | -7/+6 |
2011-03-17 | optimize contended normal mutex case; add int compare-and-swap atomic | Rich Felker | 1 | -1/+1 |