mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH 1/2] locking/lockdep: Fix debug_locks off performance problem
@ 2018-10-19  1:45 Waiman Long
  2018-10-19  1:45 ` [PATCH 2/2] locking/lockdep: Make global debug_locks* variables read-mostly Waiman Long
  2018-10-19  9:33 ` [tip:locking/core] locking/lockdep: Fix debug_locks off performance problem tip-bot for Waiman Long
  0 siblings, 2 replies; 4+ messages in thread
From: Waiman Long @ 2018-10-19  1:45 UTC (permalink / raw)
  To: Peter Zijlstra, Ingo Molnar, Will Deacon, Thomas Gleixner
  Cc: linux-kernel, Waiman Long

It was found that when debug_locks was turned off because of a problem
found by the lockdep code, the system performance could drop quite
significantly when the lock_stat code was also configured into the
kernel. For instance, parallel kernel build time on a 4-socket x86-64
server nearly doubled.

Further analysis into the cause of the slowdown traced back to the
frequent call to debug_locks_off() from the __lock_acquired() function
probably due to some inconsistent lockdep states with debug_locks
off. The debug_locks_off() function did an unconditional atomic xchg
to write a 0 value into debug_locks which had already been set to 0.
This led to severe cacheline contention in the cacheline that held
debug_locks.  As debug_locks is being referenced in quite a few different
places in the kernel, this greatly slow down the system performance.

To prevent that trashing of debug_locks cacheline, lock_acquired()
and lock_contended() now checks the state of debug_locks before
proceeding. The debug_locks_off() function is also modified to check
debug_locks before calling __debug_locks_off().

Signed-off-by: Waiman Long <longman@redhat.com>
---
 kernel/locking/lockdep.c | 4 ++--
 lib/debug_locks.c        | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index be76f47..1efada2 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4066,7 +4066,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
-	if (unlikely(!lock_stat))
+	if (unlikely(!lock_stat || !debug_locks))
 		return;
 
 	if (unlikely(current->lockdep_recursion))
@@ -4086,7 +4086,7 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
-	if (unlikely(!lock_stat))
+	if (unlikely(!lock_stat || !debug_locks))
 		return;
 
 	if (unlikely(current->lockdep_recursion))
diff --git a/lib/debug_locks.c b/lib/debug_locks.c
index 96c4c63..124fdf2 100644
--- a/lib/debug_locks.c
+++ b/lib/debug_locks.c
@@ -37,7 +37,7 @@
  */
 int debug_locks_off(void)
 {
-	if (__debug_locks_off()) {
+	if (debug_locks && __debug_locks_off()) {
 		if (!debug_locks_silent) {
 			console_verbose();
 			return 1;
-- 
1.8.3.1


^ permalink raw reply	[flat|nested] 4+ messages in thread
end of thread, other threads:[~2018-10-19  9:34 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-10-19  1:45 [PATCH 1/2] locking/lockdep: Fix debug_locks off performance problem Waiman Long
2018-10-19  1:45 ` [PATCH 2/2] locking/lockdep: Make global debug_locks* variables read-mostly Waiman Long
2018-10-19  9:34   ` [tip:locking/core] " tip-bot for Waiman Long
2018-10-19  9:33 ` [tip:locking/core] locking/lockdep: Fix debug_locks off performance problem tip-bot for Waiman Long

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome