summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorTorvald Riegel <triegel@redhat.com>2015-06-23 15:22:25 +0200
committerTorvald Riegel <triegel@redhat.com>2015-06-30 15:57:15 +0200
commit4eb984d3ab5641ce7992204756ac15a61f5f7181 (patch)
tree12603bae9d2582033a3186174d1379121e1ea642 /sysdeps/nacl/lll_timedwait_tid.c
parentImprove tgamma accuracy (bug 18613). (diff)
downloadglibc-4eb984d3ab5641ce7992204756ac15a61f5f7181.tar.gz
glibc-4eb984d3ab5641ce7992204756ac15a61f5f7181.tar.bz2
glibc-4eb984d3ab5641ce7992204756ac15a61f5f7181.zip
Clean up BUSY_WAIT_NOP and atomic_delay.
This patch combines BUSY_WAIT_NOP and atomic_delay into a new atomic_spin_nop function and adjusts all clients. The new function is put into atomic.h because what is best done in a spin loop is architecture-specific, and atomics must be used for spinning. The function name is meant to tell users that this has no effect on synchronization semantics but is a performance aid for spinning.
Diffstat (limited to 'sysdeps/nacl/lll_timedwait_tid.c')
-rw-r--r--sysdeps/nacl/lll_timedwait_tid.c2
1 files changed, 1 insertions, 1 deletions
diff --git a/sysdeps/nacl/lll_timedwait_tid.c b/sysdeps/nacl/lll_timedwait_tid.c
index ecaf0b113a..ef544cf84f 100644
--- a/sysdeps/nacl/lll_timedwait_tid.c
+++ b/sysdeps/nacl/lll_timedwait_tid.c
@@ -40,7 +40,7 @@ __lll_timedwait_tid (int *tidp, const struct timespec *abstime)
finish quick enough that the timeout doesn't matter. If any
thread ever stays in this state for long, there is something
catastrophically wrong. */
- BUSY_WAIT_NOP;
+ atomic_spin_nop ();
else
{
assert (tid > 0);