[prev in list] [next in list] [prev in thread] [next in thread] 

List:       linux-kernel
Subject:    [PATCH next v2 2/5] locking/osq_lock: Optimise the vcpu_is_preempted() check.
From:       David Laight <David.Laight () ACULAB ! COM>
Date:       2023-12-31 21:52:51
Message-ID: 3a9d1782cd50436c99ced8c10175bae6 () AcuMS ! aculab ! com
[Download RAW message or body]

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.

This is simpler than checking for 'node->prev' changing and caching
'prev->cpu'.

Signed-off-by: David Laight <david.laight@aculab.com>
---
 kernel/locking/osq_lock.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index e0bc74d85a76..eb8a6dfdb79d 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -14,8 +14,9 @@
 
 struct optimistic_spin_node {
 	struct optimistic_spin_node *next, *prev;
-	int locked; /* 1 if lock acquired */
-	int cpu; /* encoded CPU # + 1 value */
+	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);
@@ -29,11 +30,6 @@ static inline int encode_cpu(int cpu_nr)
 	return cpu_nr + 1;
 }
 
-static inline int node_cpu(struct optimistic_spin_node *node)
-{
-	return node->cpu - 1;
-}
-
 static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
 {
 	int cpu_nr = encoded_cpu_val - 1;
@@ -110,9 +106,10 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	if (old == OSQ_UNLOCKED_VAL)
 		return true;
 
-	node->locked = 0;
+	node->prev_cpu = old;
 	prev = decode_cpu(old);
 	node->prev = prev;
+	node->locked = 0;
 
 	/*
 	 * osq_lock()			unqueue
@@ -144,7 +141,7 @@ 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(READ_ONCE(node->prev_cpu) - 1)))
 		return true;
 
 	/* unqueue */
@@ -201,6 +198,7 @@ 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);
 
-- 
2.17.1

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)


[prev in list] [next in list] [prev in thread] [next in thread]