wireguard-openbsd/lib/librthread/Makefile, branch master WireGuard implementation for the OpenBSD kernel https://git.zx2c4.com/wireguard-openbsd/atom/lib/librthread/Makefile?h=master 2020-02-06T03:13:45Z Instead of opting in to futexes on archs with atomics opt out on archs 2020-02-06T03:13:45Z jsg jsg@openbsd.org 2020-02-06T03:13:45Z urn:sha1:2ee00db36bd4c31e23829424e9f44f4dbb4646f4 without atomics, a smaller list. ok mpi@ visa@ New futex(2) based rwlock implementation based on the mutex code. 2019-02-13T13:22:14Z mpi mpi@openbsd.org 2019-02-13T13:22:14Z urn:sha1:5ecdd0566b441ae0b99e73f410875e05dc0fa5b7 This implementation reduces contention because threads no longer need to spin calling sched_yield(2) before going to sleep. Tested by many, thanks! ok visa@, pirofti@ Move sigwait(3) from libpthread to libc 2019-01-12T00:16:03Z jca jca@openbsd.org 2019-01-12T00:16:03Z urn:sha1:13e54a3ce65615faaf13e4717a510eb52bfb2efe POSIX wants it in libc, that's where the function can be found on other systems. Reported by naddy@, input from naddy@ and guenther@. "looks ok" guenther@, ok deraadt@ Note: riding the libc/libpthread major cranks earlier today. Switch alpha to futex(2) based condvars, mutexes and semaphores. 2018-10-21T17:07:24Z visa visa@openbsd.org 2018-10-21T17:07:24Z urn:sha1:2b819b9469dd1b5852b324ae10fcffed47a792b5 From Brad, tested by Miod, OK kettenis@ Switch powerpc to futex(2) based condvars, mutexes and semaphores. 2018-10-15T13:03:11Z visa visa@openbsd.org 2018-10-15T13:03:11Z urn:sha1:94fcb5388a8e944153fb2d66d69e156cf67adf78 From Brad, OK mpi@ kettenis@ enable futex(2) based mutexes on armv7 and use futex based semaphores in 2018-09-24T11:25:09Z jsg jsg@openbsd.org 2018-09-24T11:25:09Z urn:sha1:e9c926da912f1985b3a00df6995af59a26881ef3 librthread on armv7 as well from brad ok visa@ kettenis@ mpi@ New semaphore implementation making sem_post async-safe. 2018-06-08T13:53:01Z pirofti pirofti@openbsd.org 2018-06-08T13:53:01Z urn:sha1:4b11781bee459297183dc7fc1d9191404fa83c4a POSIX dictates that sem_post() needs to be async-safe here[0] and is thus included in the list of safe functions to call from within a signal handler here[1]. The old semaphore implementation is using spinlocks and __thrsleep to synchronize between threads. Let's say there are two threads: T0 and T1 and the semaphore has V=0. T1 calls sem_wait() and it will now sleep (spinlock) until someone else sem_post()'s. Let's say T0 sends a signal to T1 and exits. The signal handler calls sem_post() which is meant to unblock T1 by incrementing V. With the old semaphore implementation we we are now in a deadlock as sem_post spinlocks on the same lock. The new implementation does not suffer from this defect as it uses futexes to resolve locking and thus sem_post does not need to spin. Besides fixing this defect and making us POSIX compliant, this should also improve performance as there should be less context switching and thus less time spent in the kernel. For architectures that do not provied futexes and atomic operations, the old implementation will be used and it is now being renamed to rthread_sem_compat as discussed with mpi@. [0] -- http://pubs.opengroup.org/onlinepubs/9699919799/functions/sem_post.html [1] -- http://pubs.opengroup.org/onlinepubs/9699919799/functions/V2_chap02.html OK visa@, mpi@, guenther@ Move the thread-related .h files to /usr/src/include/, since the 2017-10-15T23:40:33Z guenther guenther@openbsd.org 2017-10-15T23:40:33Z urn:sha1:249f38f2da514405bb27d05caf81ae636ba2a4f5 implementation is now spread between libc and librthread. No changes to the content ok mpi@ Move mutex, condvar, and thread-specific data routes, pthread_once, and 2017-09-05T02:40:54Z guenther guenther@openbsd.org 2017-09-05T02:40:54Z urn:sha1:a5511fa9f431600dbd6dc2b46fc4e6b73e7d239c pthread_exit from libpthread to libc, along with low-level bits to support them. Major bump to both libc and libpthread. Requested by libressl team. Ports testing by naddy@ ok kettenis@ Enable the use of futex(2) in librthread on mips64. 2017-07-04T14:33:43Z visa visa@openbsd.org 2017-07-04T14:33:43Z urn:sha1:03ef7681b631b84ad7903a6fc274e25097ec2ea8 OK mpi@, deraadt@