1. Patchew
  2. linux
  3. [PATCH v3 next 0/5] locking/osq_lock: Optimisations to osq_lock code
  4. View patch

[PATCH v3 next 3/5] Use node->prev_cpu instead of saving node->prev

david.laight.linux@gmail.com posted 5 patches 1 month ago
[PATCH v3 next 3/5] Use node->prev_cpu instead of saving node->prev
Posted by david.laight.linux@gmail.com 1 month ago 
From: David Laight <david.laight.linux@gmail.com>

node->prev is only used to update 'prev' in the unlikely case
of concurrent unqueues.
The new 'prev' pointer can be obtained from prev_cpu.

node->cpu (or more particularly) prev->cpu is only used for the
osq_wait_next() call in the unqueue path.
Normally this is exactly the value that the initial xchg() read
from lock->tail (used to obtain 'prev'), but can get updated
by concurrent unqueues.

Both the 'prev' and 'cpu' members of optimistic_spin_node are
now unused and can be deleted.

Signed-off-by: David Laight <david.laight.linux@gmail.com>
---
 kernel/locking/osq_lock.c | 31 ++++++++++++++-----------------
 1 file changed, 14 insertions(+), 17 deletions(-)

diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index 0e1c7d11b6c0..5dd7e08d4fda 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -13,9 +13,8 @@
  */
 
 struct optimistic_spin_node {
-	struct optimistic_spin_node *next, *prev;
+	struct optimistic_spin_node *next;
 	int locked; /* 1 if lock acquired */
-	int cpu; /* encoded CPU # + 1 value */
 	int prev_cpu; /* encoded CPU # + 1 value */
 };
 
@@ -96,10 +95,9 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
 	struct optimistic_spin_node *prev, *next;
 	int curr = encode_cpu(smp_processor_id());
-	int old;
+	int prev_cpu;
 
 	node->next = NULL;
-	node->cpu = curr;
 
 	/*
 	 * We need both ACQUIRE (pairs with corresponding RELEASE in
@@ -107,23 +105,22 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	 * the node fields we just initialised) semantics when updating
 	 * the lock tail.
 	 */
-	old = atomic_xchg(&lock->tail, curr);
-	if (old == OSQ_UNLOCKED_VAL)
+	prev_cpu = atomic_xchg(&lock->tail, curr);
+	if (prev_cpu == OSQ_UNLOCKED_VAL)
 		return true;
 
-	WRITE_ONCE(node->prev_cpu, old);
-	prev = decode_cpu(old);
-	node->prev = prev;
+	WRITE_ONCE(node->prev_cpu, prev_cpu);
+	prev = decode_cpu(prev_cpu);
 	node->locked = 0;
 
 	/*
 	 * osq_lock()			unqueue
 	 *
-	 * node->prev = prev		osq_wait_next()
+	 * node->prev_cpu = prev_cpu	osq_wait_next()
 	 * WMB				MB
-	 * prev->next = node		next->prev = prev // unqueue-C
+	 * prev->next = node		next->prev_cpu = prev_cpu // unqueue-C
 	 *
-	 * Here 'node->prev' and 'next->prev' are the same variable and we need
+	 * Here 'node->prev_cpu' and 'next->prev_cpu' are the same variable and we need
 	 * to ensure these stores happen in-order to avoid corrupting the list.
 	 */
 	smp_wmb();
@@ -179,9 +176,10 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 
 		/*
 		 * Or we race against a concurrent unqueue()'s step-B, in which
-		 * case its step-C will write us a new @node->prev pointer.
+		 * case its step-C will write us a new @node->prev_cpu value.
 		 */
-		prev = READ_ONCE(node->prev);
+		prev_cpu = READ_ONCE(node->prev_cpu);
+		prev = decode_cpu(prev_cpu);
 	}
 
 	/*
@@ -191,7 +189,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	 * back to @prev.
 	 */
 
-	next = osq_wait_next(lock, node, prev->cpu);
+	next = osq_wait_next(lock, node, prev_cpu);
 	if (!next)
 		return false;
 
@@ -203,8 +201,7 @@ 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(next->prev_cpu, prev_cpu);
 	WRITE_ONCE(prev->next, next);
 
 	return false;
-- 
2.39.5
Re: [PATCH v3 next 3/5] Use node->prev_cpu instead of saving node->prev
Posted by David Laight 1 month ago 
On Fri,  6 Mar 2026 22:51:48 +0000
david.laight.linux@gmail.com wrote:

Apologies to Yafang for mistyping his address...

> From: David Laight <david.laight.linux@gmail.com>
> 
> node->prev is only used to update 'prev' in the unlikely case
> of concurrent unqueues.
> The new 'prev' pointer can be obtained from prev_cpu.
> 
> node->cpu (or more particularly) prev->cpu is only used for the
> osq_wait_next() call in the unqueue path.
> Normally this is exactly the value that the initial xchg() read
> from lock->tail (used to obtain 'prev'), but can get updated
> by concurrent unqueues.
> 
> Both the 'prev' and 'cpu' members of optimistic_spin_node are
> now unused and can be deleted.
> 
> Signed-off-by: David Laight <david.laight.linux@gmail.com>
> ---
>  kernel/locking/osq_lock.c | 31 ++++++++++++++-----------------
>  1 file changed, 14 insertions(+), 17 deletions(-)
> 
> diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
> index 0e1c7d11b6c0..5dd7e08d4fda 100644
> --- a/kernel/locking/osq_lock.c
> +++ b/kernel/locking/osq_lock.c
> @@ -13,9 +13,8 @@
>   */
>  
>  struct optimistic_spin_node {
> -	struct optimistic_spin_node *next, *prev;
> +	struct optimistic_spin_node *next;
>  	int locked; /* 1 if lock acquired */
> -	int cpu; /* encoded CPU # + 1 value */
>  	int prev_cpu; /* encoded CPU # + 1 value */
>  };
>  
> @@ -96,10 +95,9 @@ bool osq_lock(struct optimistic_spin_queue *lock)
>  	struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
>  	struct optimistic_spin_node *prev, *next;
>  	int curr = encode_cpu(smp_processor_id());
> -	int old;
> +	int prev_cpu;
>  
>  	node->next = NULL;
> -	node->cpu = curr;
>  
>  	/*
>  	 * We need both ACQUIRE (pairs with corresponding RELEASE in
> @@ -107,23 +105,22 @@ bool osq_lock(struct optimistic_spin_queue *lock)
>  	 * the node fields we just initialised) semantics when updating
>  	 * the lock tail.
>  	 */
> -	old = atomic_xchg(&lock->tail, curr);
> -	if (old == OSQ_UNLOCKED_VAL)
> +	prev_cpu = atomic_xchg(&lock->tail, curr);
> +	if (prev_cpu == OSQ_UNLOCKED_VAL)
>  		return true;
>  
> -	WRITE_ONCE(node->prev_cpu, old);
> -	prev = decode_cpu(old);
> -	node->prev = prev;
> +	WRITE_ONCE(node->prev_cpu, prev_cpu);
> +	prev = decode_cpu(prev_cpu);
>  	node->locked = 0;
>  
>  	/*
>  	 * osq_lock()			unqueue
>  	 *
> -	 * node->prev = prev		osq_wait_next()
> +	 * node->prev_cpu = prev_cpu	osq_wait_next()
>  	 * WMB				MB
> -	 * prev->next = node		next->prev = prev // unqueue-C
> +	 * prev->next = node		next->prev_cpu = prev_cpu // unqueue-C
>  	 *
> -	 * Here 'node->prev' and 'next->prev' are the same variable and we need
> +	 * Here 'node->prev_cpu' and 'next->prev_cpu' are the same variable and we need
>  	 * to ensure these stores happen in-order to avoid corrupting the list.
>  	 */
>  	smp_wmb();
> @@ -179,9 +176,10 @@ bool osq_lock(struct optimistic_spin_queue *lock)
>  
>  		/*
>  		 * Or we race against a concurrent unqueue()'s step-B, in which
> -		 * case its step-C will write us a new @node->prev pointer.
> +		 * case its step-C will write us a new @node->prev_cpu value.
>  		 */
> -		prev = READ_ONCE(node->prev);
> +		prev_cpu = READ_ONCE(node->prev_cpu);
> +		prev = decode_cpu(prev_cpu);
>  	}
>  
>  	/*
> @@ -191,7 +189,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
>  	 * back to @prev.
>  	 */
>  
> -	next = osq_wait_next(lock, node, prev->cpu);
> +	next = osq_wait_next(lock, node, prev_cpu);
>  	if (!next)
>  		return false;
>  
> @@ -203,8 +201,7 @@ 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(next->prev_cpu, prev_cpu);
>  	WRITE_ONCE(prev->next, next);
>  
>  	return false;
Re: [PATCH v3 next 3/5] Use node->prev_cpu instead of saving node->prev
Posted by David Laight 1 month ago 
On Fri,  6 Mar 2026 22:51:48 +0000
david.laight.linux@gmail.com wrote:

Apologies to Yafang for mistyping his address....

> From: David Laight <david.laight.linux@gmail.com>
> 
> node->prev is only used to update 'prev' in the unlikely case
> of concurrent unqueues.
> The new 'prev' pointer can be obtained from prev_cpu.
> 
> node->cpu (or more particularly) prev->cpu is only used for the
> osq_wait_next() call in the unqueue path.
> Normally this is exactly the value that the initial xchg() read
> from lock->tail (used to obtain 'prev'), but can get updated
> by concurrent unqueues.
> 
> Both the 'prev' and 'cpu' members of optimistic_spin_node are
> now unused and can be deleted.
> 
> Signed-off-by: David Laight <david.laight.linux@gmail.com>
> ---
>  kernel/locking/osq_lock.c | 31 ++++++++++++++-----------------
>  1 file changed, 14 insertions(+), 17 deletions(-)
> 
> diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
> index 0e1c7d11b6c0..5dd7e08d4fda 100644
> --- a/kernel/locking/osq_lock.c
> +++ b/kernel/locking/osq_lock.c
> @@ -13,9 +13,8 @@
>   */
>  
>  struct optimistic_spin_node {
> -	struct optimistic_spin_node *next, *prev;
> +	struct optimistic_spin_node *next;
>  	int locked; /* 1 if lock acquired */
> -	int cpu; /* encoded CPU # + 1 value */
>  	int prev_cpu; /* encoded CPU # + 1 value */
>  };
>  
> @@ -96,10 +95,9 @@ bool osq_lock(struct optimistic_spin_queue *lock)
>  	struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
>  	struct optimistic_spin_node *prev, *next;
>  	int curr = encode_cpu(smp_processor_id());
> -	int old;
> +	int prev_cpu;
>  
>  	node->next = NULL;
> -	node->cpu = curr;
>  
>  	/*
>  	 * We need both ACQUIRE (pairs with corresponding RELEASE in
> @@ -107,23 +105,22 @@ bool osq_lock(struct optimistic_spin_queue *lock)
>  	 * the node fields we just initialised) semantics when updating
>  	 * the lock tail.
>  	 */
> -	old = atomic_xchg(&lock->tail, curr);
> -	if (old == OSQ_UNLOCKED_VAL)
> +	prev_cpu = atomic_xchg(&lock->tail, curr);
> +	if (prev_cpu == OSQ_UNLOCKED_VAL)
>  		return true;
>  
> -	WRITE_ONCE(node->prev_cpu, old);
> -	prev = decode_cpu(old);
> -	node->prev = prev;
> +	WRITE_ONCE(node->prev_cpu, prev_cpu);
> +	prev = decode_cpu(prev_cpu);
>  	node->locked = 0;
>  
>  	/*
>  	 * osq_lock()			unqueue
>  	 *
> -	 * node->prev = prev		osq_wait_next()
> +	 * node->prev_cpu = prev_cpu	osq_wait_next()
>  	 * WMB				MB
> -	 * prev->next = node		next->prev = prev // unqueue-C
> +	 * prev->next = node		next->prev_cpu = prev_cpu // unqueue-C
>  	 *
> -	 * Here 'node->prev' and 'next->prev' are the same variable and we need
> +	 * Here 'node->prev_cpu' and 'next->prev_cpu' are the same variable and we need
>  	 * to ensure these stores happen in-order to avoid corrupting the list.
>  	 */
>  	smp_wmb();
> @@ -179,9 +176,10 @@ bool osq_lock(struct optimistic_spin_queue *lock)
>  
>  		/*
>  		 * Or we race against a concurrent unqueue()'s step-B, in which
> -		 * case its step-C will write us a new @node->prev pointer.
> +		 * case its step-C will write us a new @node->prev_cpu value.
>  		 */
> -		prev = READ_ONCE(node->prev);
> +		prev_cpu = READ_ONCE(node->prev_cpu);
> +		prev = decode_cpu(prev_cpu);
>  	}
>  
>  	/*
> @@ -191,7 +189,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
>  	 * back to @prev.
>  	 */
>  
> -	next = osq_wait_next(lock, node, prev->cpu);
> +	next = osq_wait_next(lock, node, prev_cpu);
>  	if (!next)
>  		return false;
>  
> @@ -203,8 +201,7 @@ 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(next->prev_cpu, prev_cpu);
>  	WRITE_ONCE(prev->next, next);
>  
>  	return false;

Patchew 2.1-devel-ea86937

© 2016 - 2026 Red Hat, Inc.