This performance optimization chooses probabilistically to avoid moving
threads from the main queue into the secondary one when the secondary queue
is empty.

It is helpful when the lock is only lightly contended. In particular, it
makes CNA less eager to create a secondary queue, but does not introduce
any extra delays for threads waiting in that queue once it is created.

Signed-off-by: Alex Kogan <redacted>
Reviewed-by: Steve Sistare <redacted>
Reviewed-by: Waiman Long <longman@redhat.com>
---
 kernel/locking/qspinlock_cna.h | 39 ++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/kernel/locking/qspinlock_cna.h b/kernel/locking/qspinlock_cna.h
index 29c3abbd3d94..983c6a47a221 100644
--- a/kernel/locking/qspinlock_cna.h
+++ b/kernel/locking/qspinlock_cna.h

@@ -5,6 +5,7 @@
 
 #include <linux/topology.h>
 #include <linux/sched/rt.h>
+#include <linux/random.h>
 
 /*
  * Implement a NUMA-aware version of MCS (aka CNA, or compact NUMA-aware lock).

@@ -86,6 +87,34 @@ static inline bool intra_node_threshold_reached(struct cna_node *cn)
 	return current_time - threshold > 0;
 }
 
+/*
+ * Controls the probability for enabling the ordering 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);

@@ -293,6 +322,16 @@ static __always_inline u32 cna_wait_head_or_lock(struct qspinlock *lock,
 {
 	struct cna_node *cn = (struct cna_node *)node;
 
+	if (node->locked <= 1 && probably(SHUFFLE_REDUCTION_PROB_ARG)) {