locking/pvqspinlock: Collect slowpath lock statistics

This patch enables the accumulation of kicking and waiting related
PV qspinlock statistics when the new QUEUED_LOCK_STAT configuration
option is selected. It also enables the collection of data which
enable us to calculate the kicking and wakeup latencies which have
a heavy dependency on the CPUs being used.

The statistical counters are per-cpu variables to minimize the
performance overhead in their updates. These counters are exported
via the debugfs filesystem under the qlockstat directory.  When the
corresponding debugfs files are read, summation and computing of the
required data are then performed.

The measured latencies for different CPUs are:

	CPU		Wakeup		Kicking
	---		------		-------
	Haswell-EX	63.6us		 7.4us
	Westmere-EX	67.6us		 9.3us

The measured latencies varied a bit from run-to-run. The wakeup
latency is much higher than the kicking latency.

A sample of statistical counters after system bootup (with vCPU
overcommit) was:

	pv_hash_hops=1.00
	pv_kick_unlock=1148
	pv_kick_wake=1146
	pv_latency_kick=11040
	pv_latency_wake=194840
	pv_spurious_wakeup=7
	pv_wait_again=4
	pv_wait_head=23
	pv_wait_node=1129

Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1447114167-47185-6-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 27 insertions, 5 deletions

diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 4bd323d38c60..aaeeefb791f8 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -41,6 +41,11 @@ struct pv_node {
 };
 
 /*
+ * Include queued spinlock statistics code
+ */
+#include "qspinlock_stat.h"
+
+/*
  * Lock and MCS node addresses hash table for fast lookup
  *
  * Hashing is done on a per-cacheline basis to minimize the need to access
@@ -100,10 +105,13 @@ static struct qspinlock **pv_hash(struct qspinlock *lock, struct pv_node *node)
 {
 	unsigned long offset, hash = hash_ptr(lock, pv_lock_hash_bits);
 	struct pv_hash_entry *he;
+	int hopcnt = 0;
 
 	for_each_hash_entry(he, offset, hash) {
+		hopcnt++;
 		if (!cmpxchg(&he->lock, NULL, lock)) {
 			WRITE_ONCE(he->node, node);
+			qstat_hop(hopcnt);
 			return &he->lock;
 		}
 	}
@@ -164,9 +172,11 @@ static void pv_init_node(struct mcs_spinlock *node)
 static void pv_wait_node(struct mcs_spinlock *node)
 {
 	struct pv_node *pn = (struct pv_node *)node;
+	int waitcnt = 0;
 	int loop;
 
-	for (;;) {
+	/* waitcnt processing will be compiled out if !QUEUED_LOCK_STAT */
+	for (;; waitcnt++) {
 		for (loop = SPIN_THRESHOLD; loop; loop--) {
 			if (READ_ONCE(node->locked))
 				return;
@@ -184,12 +194,16 @@ static void pv_wait_node(struct mcs_spinlock *node)
 		 */
 		smp_store_mb(pn->state, vcpu_halted);
 
-		if (!READ_ONCE(node->locked))
+		if (!READ_ONCE(node->locked)) {
+			qstat_inc(qstat_pv_wait_node, true);
+			qstat_inc(qstat_pv_wait_again, waitcnt);
 			pv_wait(&pn->state, vcpu_halted);
+		}
 
 		/*
-		 * If pv_kick_node() changed us to vcpu_hashed, retain that value
-		 * so that pv_wait_head() knows to not also try to hash this lock.
+		 * If pv_kick_node() changed us to vcpu_hashed, retain that
+		 * value so that pv_wait_head() knows to not also try to hash
+		 * this lock.
 		 */
 		cmpxchg(&pn->state, vcpu_halted, vcpu_running);
 
@@ -200,6 +214,7 @@ static void pv_wait_node(struct mcs_spinlock *node)
 		 * So it is better to spin for a while in the hope that the
 		 * MCS lock will be released soon.
 		 */
+		qstat_inc(qstat_pv_spurious_wakeup, !READ_ONCE(node->locked));
 	}
 
 	/*
@@ -250,6 +265,7 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node)
 	struct pv_node *pn = (struct pv_node *)node;
 	struct __qspinlock *l = (void *)lock;
 	struct qspinlock **lp = NULL;
+	int waitcnt = 0;
 	int loop;
 
 	/*
@@ -259,7 +275,7 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node)
 	if (READ_ONCE(pn->state) == vcpu_hashed)
 		lp = (struct qspinlock **)1;
 
-	for (;;) {
+	for (;; waitcnt++) {
 		for (loop = SPIN_THRESHOLD; loop; loop--) {
 			if (!READ_ONCE(l->locked))
 				return;
@@ -290,14 +306,19 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node)
 				return;
 			}
 		}
+		qstat_inc(qstat_pv_wait_head, true);
+		qstat_inc(qstat_pv_wait_again, waitcnt);
 		pv_wait(&l->locked, _Q_SLOW_VAL);
 
+		if (!READ_ONCE(l->locked))
+			return;
 		/*
 		 * The unlocker should have freed the lock before kicking the
 		 * CPU. So if the lock is still not free, it is a spurious
 		 * wakeup and so the vCPU should wait again after spinning for
 		 * a while.
 		 */
+		qstat_inc(qstat_pv_spurious_wakeup, true);
 	}
 
 	/*
@@ -352,6 +373,7 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 	 * vCPU is harmless other than the additional latency in completing
 	 * the unlock.
 	 */
+	qstat_inc(qstat_pv_kick_unlock, true);
 	pv_kick(node->cpu);
 }