[PATCH v3 04/14] locking/qspinlock/x86: Increase _Q_PENDING_LOOPS upper bound
From: Will Deacon
Date: Thu Apr 26 2018 - 06:34:28 EST
On x86, atomic_cond_read_relaxed will busy-wait with a cpu_relax() loop,
so it is desirable to increase the number of times we spin on the qspinlock
lockword when it is found to be transitioning from pending to locked.
According to Waiman Long:
| Ideally, the spinning times should be at least a few times the typical
| cacheline load time from memory which I think can be down to 100ns or
| so for each cacheline load with the newest systems or up to several
| hundreds ns for older systems.
which in his benchmarking corresponded to 512 iterations.
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Suggested-by: Waiman Long <longman@xxxxxxxxxx>
Signed-off-by: Will Deacon <will.deacon@xxxxxxx>
arch/x86/include/asm/qspinlock.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 90b0b0ed8161..da1370ad206d 100644
@@ -7,6 +7,8 @@
+#define _Q_PENDING_LOOPS (1 << 9)
#define queued_spin_unlock queued_spin_unlock
* queued_spin_unlock - release a queued spinlock