[PATCH v11 5/5] locking/qspinlock: Avoid moving certain threads between waiting queues in CNA

[Alex Kogan]

Prohibit moving certain threads (e.g., in irq and nmi contexts)
to the secondary queue. Those prioritized threads will always stay
in the primary queue, and so will have a shorter wait time for the lock.

Signed-off-by: Alex Kogan <alex.kogan at oracle.com>
Reviewed-by: Steve Sistare <steven.sistare at oracle.com>
Reviewed-by: Waiman Long <longman at redhat.com>
---
 kernel/locking/qspinlock_cna.h | 26 ++++++++++++++++++++------
 1 file changed, 20 insertions(+), 6 deletions(-)

diff --git a/kernel/locking/qspinlock_cna.h b/kernel/locking/qspinlock_cna.h
index d3e27549c769..ac3109ab0a84 100644
--- a/kernel/locking/qspinlock_cna.h
+++ b/kernel/locking/qspinlock_cna.h
@@ -4,6 +4,7 @@
 #endif
 
 #include <linux/topology.h>
+#include <linux/sched/rt.h>
 
 /*
  * Implement a NUMA-aware version of MCS (aka CNA, or compact NUMA-aware lock).
@@ -35,7 +36,8 @@
  * running on the same NUMA node. If it is not, that waiter is detached from the
  * main queue and moved into the tail of the secondary queue. This way, we
  * gradually filter the primary queue, leaving only waiters running on the same
- * preferred NUMA node.
+ * preferred NUMA node. Note that certain priortized waiters (e.g., in
+ * irq and nmi contexts) are excluded from being moved to the secondary queue.
  *
  * We change the NUMA node preference after a waiter at the head of the
  * secondary queue spins for a certain amount of time (10ms, by default).
@@ -49,6 +51,8 @@
  *          Dave Dice <dave.dice at oracle.com>
  */
 
+#define CNA_PRIORITY_NODE      0xffff
+
 struct cna_node {
 	struct mcs_spinlock	mcs;
 	u16			numa_node;
@@ -121,9 +125,10 @@ static int __init cna_init_nodes(void)
 
 static __always_inline void cna_init_node(struct mcs_spinlock *node)
 {
+	bool priority = !in_task() || irqs_disabled() || rt_task(current);
 	struct cna_node *cn = (struct cna_node *)node;
 
-	cn->numa_node = cn->real_numa_node;
+	cn->numa_node = priority ? CNA_PRIORITY_NODE : cn->real_numa_node;
 	cn->start_time = 0;
 }
 
@@ -262,11 +267,13 @@ static u32 cna_order_queue(struct mcs_spinlock *node)
 	next_numa_node = ((struct cna_node *)next)->numa_node;
 
 	if (next_numa_node != numa_node) {
-		struct mcs_spinlock *nnext = READ_ONCE(next->next);
+		if (next_numa_node != CNA_PRIORITY_NODE) {
+			struct mcs_spinlock *nnext = READ_ONCE(next->next);
 
-		if (nnext) {
-			cna_splice_next(node, next, nnext);
-			next = nnext;
+			if (nnext) {
+				cna_splice_next(node, next, nnext);
+				next = nnext;
+			}
 		}
 		/*
 		 * Inherit NUMA node id of primary queue, to maintain the
@@ -284,6 +291,13 @@ static __always_inline u32 cna_wait_head_or_lock(struct qspinlock *lock,
 	struct cna_node *cn = (struct cna_node *)node;
 
 	if (!cn->start_time || !intra_node_threshold_reached(cn)) {
+		/*
+		 * We are at the head of the wait queue, no need to use
+		 * the fake NUMA node ID.
+		 */
+		if (cn->numa_node == CNA_PRIORITY_NODE)
+			cn->numa_node = cn->real_numa_node;
+
 		/*
 		 * Try and put the time otherwise spent spin waiting on
 		 * _Q_LOCKED_PENDING_MASK to use by sorting our lists.
-- 
2.21.1 (Apple Git-122.3)