[tip:locking/core] locking/mcs: Use smp_cond_load_acquire() in MCS spin loop

[tip-bot for Jason Low]

Commit-ID:  7f56b58a92aaf2cab049f32a19af7cc57a3972f2
Gitweb:     https://git.kernel.org/tip/7f56b58a92aaf2cab049f32a19af7cc57a3972f2
Author:     Jason Low <jason.low2@xxxxxx>
AuthorDate: Thu, 26 Apr 2018 11:34:22 +0100
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Fri, 27 Apr 2018 09:48:49 +0200

locking/mcs: Use smp_cond_load_acquire() in MCS spin loop

For qspinlocks on ARM64, we would like to use WFE instead
of purely spinning. Qspinlocks internally have lock
contenders spin on an MCS lock.

Update arch_mcs_spin_lock_contended() such that it uses
the new smp_cond_load_acquire() so that ARM64 can also
override this spin loop with its own implementation using WFE.

On x86, this can also be cheaper than spinning on
smp_load_acquire().

Signed-off-by: Jason Low <jason.low2@xxxxxx>
Signed-off-by: Will Deacon <will.deacon@xxxxxxx>
Acked-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Acked-by: Waiman Long <longman@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: boqun.feng@xxxxxxxxx
Cc: linux-arm-kernel@xxxxxxxxxxxxxxxxxxx
Cc: paulmck@xxxxxxxxxxxxxxxxxx
Link: http://lkml.kernel.org/r/1524738868-31318-9-git-send-email-will.deacon@xxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 kernel/locking/mcs_spinlock.h | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index f046b7ce9dd6..5e10153b4d3c 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -23,13 +23,15 @@ struct mcs_spinlock {
 
 #ifndef arch_mcs_spin_lock_contended
 /*
- * Using smp_load_acquire() provides a memory barrier that ensures
- * subsequent operations happen after the lock is acquired.
+ * Using smp_cond_load_acquire() provides the acquire semantics
+ * required so that subsequent operations happen after the
+ * lock is acquired. Additionally, some architectures such as
+ * ARM64 would like to do spin-waiting instead of purely
+ * spinning, and smp_cond_load_acquire() provides that behavior.
  */
 #define arch_mcs_spin_lock_contended(l)					\
 do {									\
-	while (!(smp_load_acquire(l)))					\
-		cpu_relax();						\
+	smp_cond_load_acquire(l, VAL);					\
 } while (0)
 #endif