[PATCH v5 5/5] locking/qspinlock: Introduce the shuffle reduction optimization into CNA

[Alex Kogan]

This optimization reduces the probability threads will be shuffled between
the main and secondary queues when the secondary queue is empty.
It is helpful when the lock is only lightly contended.

Signed-off-by: Alex Kogan <alex.kogan@xxxxxxxxxx>
Reviewed-by: Steve Sistare <steven.sistare@xxxxxxxxxx>
---
 kernel/locking/qspinlock_cna.h | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/kernel/locking/qspinlock_cna.h b/kernel/locking/qspinlock_cna.h
index b92a6f9a19db..6a66850be1e6 100644
--- a/kernel/locking/qspinlock_cna.h
+++ b/kernel/locking/qspinlock_cna.h
@@ -4,6 +4,7 @@
 #endif
 
 #include <linux/topology.h>
+#include <linux/random.h>
 
 /*
  * Implement a NUMA-aware version of MCS (aka CNA, or compact NUMA-aware lock).
@@ -63,6 +64,34 @@ struct cna_node {
  */
 #define INTRA_NODE_HANDOFF_THRESHOLD (1 << 16)
 
+/*
+ * Controls the probability for enabling the scan of the main queue when
+ * the secondary queue is empty. The chosen value reduces the amount of
+ * unnecessary shuffling of threads between the two waiting queues when
+ * the contention is low, while responding fast enough and enabling
+ * the shuffling when the contention is high.
+ */
+#define SHUFFLE_REDUCTION_PROB_ARG  (7)
+
+/* Per-CPU pseudo-random number seed */
+static DEFINE_PER_CPU(u32, seed);
+
+/*
+ * Return false with probability 1 / 2^@num_bits.
+ * Intuitively, the larger @num_bits the less likely false is to be returned.
+ * @num_bits must be a number between 0 and 31.
+ */
+static bool probably(unsigned int num_bits)
+{
+	u32 s;
+
+	s = this_cpu_read(seed);
+	s = next_pseudo_random32(s);
+	this_cpu_write(seed, s);
+
+	return s & ((1 << num_bits) - 1);
+}
+
 static void __init cna_init_nodes_per_cpu(unsigned int cpu)
 {
 	struct mcs_spinlock *base = per_cpu_ptr(&qnodes[0].mcs, cpu);
@@ -235,6 +264,7 @@ __always_inline u32 cna_pre_scan(struct qspinlock *lock,
 	 * should be made in cna_pass_lock()
 	 */
 	cn->pre_scan_result =
+		(node->locked <= 1 && probably(SHUFFLE_REDUCTION_PROB_ARG)) ||
 		cn->intra_count == INTRA_NODE_HANDOFF_THRESHOLD ?
 			1 : cna_scan_main_queue(node, node);
 
-- 
2.11.0 (Apple Git-81)