about summary refs log tree commit diff
path: root/src/thread/pthread_barrierattr_setpshared.c
diff options
context:
space:
mode:
authorRich Felker <dalias@aerifal.cx>2011-09-27 13:50:29 -0400
committerRich Felker <dalias@aerifal.cx>2011-09-27 13:50:29 -0400
commit60164570111873175111cf8a5b973375e492eee9 (patch)
tree1557931c4e0bacd2be217965be08031d5e3a4e51 /src/thread/pthread_barrierattr_setpshared.c
parent3f39c9b3130cd6c142d358159879b799370a6663 (diff)
downloadmusl-60164570111873175111cf8a5b973375e492eee9.tar.gz
musl-60164570111873175111cf8a5b973375e492eee9.tar.xz
musl-60164570111873175111cf8a5b973375e492eee9.zip
process-shared barrier support, based on discussion with bdonlan
this implementation is rather heavy-weight, but it's the first
solution i've found that's actually correct. all waiters actually wait
twice at the barrier so that they can synchronize exit, and they hold
a "vm lock" that prevents changes to virtual memory mappings (and
blocks pthread_barrier_destroy) until all waiters are finished
inspecting the barrier.

thus, it is safe for any thread to destroy and/or unmap the barrier's
memory as soon as pthread_barrier_wait returns, without further
synchronization.
Diffstat (limited to 'src/thread/pthread_barrierattr_setpshared.c')
-rw-r--r--src/thread/pthread_barrierattr_setpshared.c2
1 files changed, 1 insertions, 1 deletions
diff --git a/src/thread/pthread_barrierattr_setpshared.c b/src/thread/pthread_barrierattr_setpshared.c
index d6c7f9a3..1edc95dc 100644
--- a/src/thread/pthread_barrierattr_setpshared.c
+++ b/src/thread/pthread_barrierattr_setpshared.c
@@ -2,6 +2,6 @@
 
 int pthread_barrierattr_setpshared(pthread_barrierattr_t *a, int pshared)
 {
-	*a = !!pshared;
+	*a = pshared ? INT_MIN : 0;
 	return 0;
 }