summaryrefslogtreecommitdiff
path: root/include/linux
diff options
context:
space:
mode:
authorMikulas Patocka <mpatocka@redhat.com>2012-10-22 19:37:47 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2012-10-28 10:59:36 -0700
commit5c1eabe68501d1e1b1586c7f4c46cc531828c4ab (patch)
treed97aab24d8d0abbd8378e7c851f7a55d266bb851 /include/linux
parente657e078d3dfa9f96976db7a2b5fd7d7c9f1f1a6 (diff)
percpu-rw-semaphores: use light/heavy barriers
This patch introduces new barrier pair light_mb() and heavy_mb() for percpu rw semaphores. This patch fixes a bug in percpu-rw-semaphores where a barrier was missing in percpu_up_write. This patch improves performance on the read path of percpu-rw-semaphores: on non-x86 cpus, there was a smp_mb() in percpu_up_read. This patch changes it to a compiler barrier and removes the "#if defined(X86) ..." condition. From: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/linux')
-rw-r--r--include/linux/percpu-rwsem.h20
1 files changed, 7 insertions, 13 deletions
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index cf80f7e5277f..18f35b54286c 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -12,6 +12,9 @@ struct percpu_rw_semaphore {
struct mutex mtx;
};
+#define light_mb() barrier()
+#define heavy_mb() synchronize_sched()
+
static inline void percpu_down_read(struct percpu_rw_semaphore *p)
{
rcu_read_lock();
@@ -24,22 +27,12 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *p)
}
this_cpu_inc(*p->counters);
rcu_read_unlock();
+ light_mb(); /* A, between read of p->locked and read of data, paired with D */
}
static inline void percpu_up_read(struct percpu_rw_semaphore *p)
{
- /*
- * On X86, write operation in this_cpu_dec serves as a memory unlock
- * barrier (i.e. memory accesses may be moved before the write, but
- * no memory accesses are moved past the write).
- * On other architectures this may not be the case, so we need smp_mb()
- * there.
- */
-#if defined(CONFIG_X86) && (!defined(CONFIG_X86_PPRO_FENCE) && !defined(CONFIG_X86_OOSTORE))
- barrier();
-#else
- smp_mb();
-#endif
+ light_mb(); /* B, between read of the data and write to p->counter, paired with C */
this_cpu_dec(*p->counters);
}
@@ -61,11 +54,12 @@ static inline void percpu_down_write(struct percpu_rw_semaphore *p)
synchronize_rcu();
while (__percpu_count(p->counters))
msleep(1);
- smp_rmb(); /* paired with smp_mb() in percpu_sem_up_read() */
+ heavy_mb(); /* C, between read of p->counter and write to data, paired with B */
}
static inline void percpu_up_write(struct percpu_rw_semaphore *p)
{
+ heavy_mb(); /* D, between write to data and write to p->locked, paired with A */
p->locked = false;
mutex_unlock(&p->mtx);
}