[PATCH v3 next 2/5] Optimise vcpu_is_preempted() check

[david . laight . linux]

From: David Laight <david.laight.linux@xxxxxxxxx>

The vcpu_is_preempted() test stops osq_lock() spinning if a virtual
  CPU is no longer running.
Although patched out for bare-metal, the code still needs the CPU number.
Reading this from 'prev->cpu' is a pretty much guaranteed have a cache miss
when osq_unlock() is waking up the next cpu.

Instead save 'prev->cpu' in 'node->prev_cpu' and use that value instead.
Update in the osq_lock() 'unqueue' path when 'node->prev' is changed.

Signed-off-by: David Laight <david.laight.linux@xxxxxxxxx>
---
 kernel/locking/osq_lock.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index 96c6094157b5..0e1c7d11b6c0 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -16,6 +16,7 @@ struct optimistic_spin_node {
 	struct optimistic_spin_node *next, *prev;
 	int locked; /* 1 if lock acquired */
 	int cpu; /* encoded CPU # + 1 value */
+	int prev_cpu; /* encoded CPU # + 1 value */
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
@@ -29,9 +30,9 @@ static inline int encode_cpu(int cpu_nr)
 	return cpu_nr + 1;
 }
 
-static inline int node_cpu(struct optimistic_spin_node *node)
+static inline int prev_cpu_nr(struct optimistic_spin_node *node)
 {
-	return node->cpu - 1;
+	return READ_ONCE(node->prev_cpu) - 1;
 }
 
 static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
@@ -110,6 +111,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	if (old == OSQ_UNLOCKED_VAL)
 		return true;
 
+	WRITE_ONCE(node->prev_cpu, old);
 	prev = decode_cpu(old);
 	node->prev = prev;
 	node->locked = 0;
@@ -144,7 +146,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	 * polling, be careful.
 	 */
 	if (smp_cond_load_relaxed(&node->locked, VAL || need_resched() ||
-				  vcpu_is_preempted(node_cpu(node->prev))))
+				  vcpu_is_preempted(prev_cpu_nr(node))))
 		return true;
 
 	/* unqueue */
@@ -201,6 +203,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	 * it will wait in Step-A.
 	 */
 
+	WRITE_ONCE(next->prev_cpu, prev->cpu);
 	WRITE_ONCE(next->prev, prev);
 	WRITE_ONCE(prev->next, next);
 
-- 
2.39.5