summaryrefslogtreecommitdiff
path: root/lib/libthr/thread
Commit message (Expand)AuthorAgeFilesLines
* MFC r197477 - clean up keys deleted via pthread_key_delete()Brian Somers2010-06-091-1/+11
* MFC r198508, r198509:Konstantin Belousov2009-12-191-1/+3
* MFC rev 200498:Marcel Moolenaar2009-12-171-0/+3
* MFC r197445:Attilio Rao2009-09-241-2/+5
* In the current code, rdlock_count is not correctly handled for some cases.Attilio Rao2009-07-062-1/+4
* These are some cosmetic changes to improve the clarity of libthr's fork imple...Brian Feldman2009-05-111-9/+9
* Now that the kernel defines CACHE_LINE_SIZE in machine/param.h, useRobert Watson2009-04-191-2/+0
* Forcibly unlock the malloc() locks in the child process after fork(),Konstantin Belousov2009-03-191-1/+4
* Don't ignore other fcntl functions, directly call __sys_fcntl ifDavid Xu2009-03-091-1/+1
* Don't reference non-existent __fcntl_compat if WITHOUT_SYSCALL_COMPAT is defi...David Xu2009-03-091-0/+6
* When libthr and rtld start up, there are a number of magic spells castPeter Wemm2008-12-071-1/+1
* Provide custom simple allocator for rtld locks in libthr. The allocatorKonstantin Belousov2008-12-022-23/+23
* Invoke _rtld_atfork_post earlier, before we reinitialize rtld locksAlexander Kabaev2008-12-011-3/+4
* Unlock the malloc() locks in the child process after fork(). This givesKonstantin Belousov2008-11-291-0/+1
* Add two rtld exported symbols, _rtld_atfork_pre and _rtld_atfork_post.Konstantin Belousov2008-11-271-1/+10
* Allow psaddr_t to be widened by using thr_pread_{int,long,ptr},Marcel Moolenaar2008-09-141-2/+2
* Move call to _malloc_thread_cleanup() so that if this is the last thread,Jason Evans2008-09-091-3/+6
* Add thread-specific caching for small size classes, based on magazines.Jason Evans2008-08-271-0/+4
* In function pthread_condattr_getpshared, store result correctly.David Xu2008-08-011-1/+1
* Add two commands to _umtx_op system call to allow a simple mutex to beDavid Xu2008-06-243-54/+106
* Make pthread_cleanup_push() and pthread_cleanup_pop() as a pair of macros,David Xu2008-06-092-22/+48
* Call the fcntl compatiblity wrapper from the thread library fcntl wrappersDoug Rabson2008-05-301-1/+2
* Eliminate global mutex by using pthread_once's state field asDavid Xu2008-05-301-33/+29
* - Reduce function call overhead for uncontended case.David Xu2008-05-293-215/+102
* Remove libc_r's remnant code.David Xu2008-05-061-16/+0
* Use UMTX_OP_WAIT_UINT_PRIVATE and UMTX_OP_WAKE_PRIVATE to saveDavid Xu2008-04-299-19/+20
* Increase the default MUTEX_ADAPTIVE_SPINS to 2000, after furtherKris Kennaway2008-04-261-1/+1
* Avoid various shadowed variables. libthr is now almost WARNS=4 clean exceptXin LI2008-04-234-25/+25
* Use native rwlock.David Xu2008-04-221-54/+20
* _vfork is not in libthr, remove the reference.David Xu2008-04-161-1/+0
* don't include pthread_np.h, it is not used.David Xu2008-04-141-1/+0
* put THR_CRITICAL_LEAVE into do .. while statement.David Xu2008-04-031-2/+4
* add __hidden suffix to _umtx_op_err, this eliminates PLT.David Xu2008-04-031-1/+1
* Non-portable functions are in pthread_np.h, fix compiling problem.David Xu2008-04-021-1/+1
* Add pthread_setaffinity_np and pthread_getaffinity_np to libc namespace.David Xu2008-04-021-2/+0
* Remove unused functions.David Xu2008-04-022-55/+0
* Replace function _umtx_op with _umtx_op_err, the later function directlyDavid Xu2008-04-023-49/+31
* Replace userland rwlock with a pure kernel based rwlock, the newDavid Xu2008-04-024-220/+196
* Restore normal pthread_cond_signal path to avoid some obscure races.David Xu2008-04-011-2/+3
* return EAGAIN early rather than running bunch of code later, micro optimizeDavid Xu2008-04-011-1/+3
* Rewrite rwlock to user atomic operations to change rwlock state, thisDavid Xu2008-03-313-140/+280
* Compile libthr with warnings.Ruslan Ermilov2008-03-252-6/+8
* Fixed mis-implementation of pthread_mutex_get{spin,yield}loops_np().Ruslan Ermilov2008-03-251-4/+7
* Add POSIX pthread API pthread_getcpuclockid() to get a thread's cpuDavid Xu2008-03-222-0/+48
* Resolve __error()'s PLT early so that it needs not to be resolved again,David Xu2008-03-211-0/+3
* pthread_mutexattr_destroy() was accidentally broken in last revision,Ruslan Ermilov2008-03-201-0/+1
* Preserve application code's errno in rtld locking code, it attemps to keepDavid Xu2008-03-201-2/+31
* Make pthread_mutexattr_settype to return error number directly andDavid Xu2008-03-201-3/+1
* don't reduce new thread's refcount if current thread can not set cpusetDavid Xu2008-03-191-1/+1
* - Trim trailing spaces.David Xu2008-03-191-8/+8