workqueue: Document (some) memory-ordering properties of {queue,schedule}_work()
PATCH 1/1 workqueue: Document (some) memory-ordering properties of {queue,schedule}_work()
It's desirable to be able to rely on the following property: All stores preceding (in program order) a call to a successful queue_work() will be visible from the CPU which will execute the queued work by the time such work executes, e.g.,
{ x is initially 0 }
CPU0 CPU1
WRITE_ONCE(x, 1); [ "work" is being executed ]
r0 = queue_work(wq, work); r1 = READ_ONCE(x);
Forbids: r0 == true && r1 == 0
The current implementation of queue_work() provides such memory-ordering property:
- In __queue_work(), the ->lock spinlock is acquired.
- On the other side, in worker_thread(), this same ->lock is held when dequeueing work.
So the locking ordering makes things work out.
Add this property to the DocBook headers of {queue,schedule}_work().
--- include/linux/workqueue.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)
include/linux/workqueue.h +16 -0
@@ -487,6 +487,19 @@ extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task);* * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. +* +* Memory-ordering properties: If it returns %true, guarantees that all stores +* preceding the call to queue_work() in the program order will be visible from +* the CPU which will execute @work by the time such work executes, e.g., +* +* { x is initially 0 } +* +* CPU0 CPU1 +* +* WRITE_ONCE(x, 1); [ @work is being executed ] +* r0 = queue_work(wq, work); r1 = READ_ONCE(x); +* +* Forbids: r0 == true && r1 == 0 */ static inline bool queue_work (struct workqueue_struct *wq,struct work_struct *work)
@@ -546,6 +559,9 @@ static inline bool schedule_work_on(int cpu, struct work_struct *work)* This puts a job in the kernel-global workqueue if it was not already * queued and leaves it in the same position on the kernel-global * workqueue otherwise. +* +* Shares the same memory-ordering properties of queue_work(), c.f., the +* DocBook header of queue_work(). */ static inline bool schedule_work (struct work_struct *work) {
Signature · 1 line
2.24.0
Hi,
Quoted 57 lines · Andrea Parri
It's desirable to be able to rely on the following property: All stores preceding (in program order) a call to a successful
queue_work()will be visible from the CPU which will execute the queued work by the time such work executes, e.g.,{ x is initially 0 }
CPU0 CPU1
WRITE_ONCE(x, 1); [ "work" is being executed ]
r0 =queue_work(wq, work); r1 =READ_ONCE(x);Forbids: r0 == true && r1 == 0The current implementation of
queue_work()provides such memory-ordering property:- In
__queue_work(), the ->lock spinlock is acquired.- On the other side, in
worker_thread(), this same ->lock is held when dequeueing work.So the locking ordering makes things work out.
Add this property to the DocBook headers of {queue,schedule}_work().
Suggested-by Paul E. McKenney <[email protected]>Signed-off-by Andrea Parri <[email protected]>--- include/linux/workqueue.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)include/linux/workqueue.h +13
-0@@ -487,6 +487,19 @@ extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task);* * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. +* +* Memory-ordering properties: If it returns %true, guarantees that all stores +* preceding the call to queue_work() in the program order will be visible from +* the CPU which will execute @work by the time such work executes, e.g., +* +* { x is initially 0 } +* +* CPU0 CPU1 +* +* WRITE_ONCE(x, 1); [ @work is being executed ] +* r0 = queue_work(wq, work); r1 = READ_ONCE(x); +* +* Forbids: r0 == true && r1 == 0 */ static inline bool queue_work (struct workqueue_struct *wq,struct work_struct *work)
include/linux/workqueue.h static inline bool schedule_work_on(int cpu, struct work_struct *work) · line 563
Quoted 5 lines
include/linux/workqueue.h +2
-0@@ -546,6 +559,9 @@ static inline bool schedule_work_on(int cpu, struct work_struct *work)* This puts a job in the kernel-global workqueue if it was not already * queued and leaves it in the same position on the kernel-global * workqueue otherwise. +* +* Shares the same memory-ordering properties of queue_work(), c.f., the
nit: cf. the
Quoted 5 lines
include/linux/workqueue.h +1
-0+* DocBook header of queue_work(). */ static inline bool schedule_work (struct work_struct *work) {
Signature · 1 line
~Randy
Quoted 22 lines · Andrea Parri
It's desirable to be able to rely on the following property: All stores preceding (in program order) a call to a successful
queue_work()will be visible from the CPU which will execute the queued work by the time such work executes, e.g.,{ x is initially 0 }
CPU0 CPU1
WRITE_ONCE(x, 1); [ "work" is being executed ]
r0 =queue_work(wq, work); r1 =READ_ONCE(x);Forbids: r0 == true && r1 == 0The current implementation of
queue_work()provides such memory-ordering property:- In
__queue_work(), the ->lock spinlock is acquired.- On the other side, in
worker_thread(), this same ->lock is held when dequeueing work.
Quoted 6 lines
So the locking ordering makes things work out.
Add this property to the DocBook headers of {queue,schedule}_work().
Suggested-by Paul E. McKenney <[email protected]>Signed-off-by Andrea Parri <[email protected]>
An alternative to Randy's suggestion of dropping the comma following the "cf." is to just drop that whole phrase. I will let you and Randy work that one out, though. ;-)
Quoted 41 lines
--- include/linux/workqueue.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)include/linux/workqueue.h +16
-0@@ -487,6 +487,19 @@ extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task);* * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. +* +* Memory-ordering properties: If it returns %true, guarantees that all stores +* preceding the call to queue_work() in the program order will be visible from +* the CPU which will execute @work by the time such work executes, e.g., +* +* { x is initially 0 } +* +* CPU0 CPU1 +* +* WRITE_ONCE(x, 1); [ @work is being executed ] +* r0 = queue_work(wq, work); r1 = READ_ONCE(x); +* +* Forbids: r0 == true && r1 == 0 */ static inline bool queue_work (struct workqueue_struct *wq,struct work_struct *work)@@ -546,6 +559,9 @@ static inline bool schedule_work_on(int cpu, struct work_struct *work)* This puts a job in the kernel-global workqueue if it was not already * queued and leaves it in the same position on the kernel-global * workqueue otherwise. +* +* Shares the same memory-ordering properties of queue_work(), c.f., the +* DocBook header of queue_work(). */ static inline bool schedule_work (struct work_struct *work) {Signature · 1 line
2.24.0
Quoted 23 lines · Paul E. McKenney
Quoted 22 lines · Andrea Parri
It's desirable to be able to rely on the following property: All stores preceding (in program order) a call to a successful
queue_work()will be visible from the CPU which will execute the queued work by the time such work executes, e.g.,{ x is initially 0 }
CPU0 CPU1
WRITE_ONCE(x, 1); [ "work" is being executed ]
r0 =queue_work(wq, work); r1 =READ_ONCE(x);Forbids: r0 == true && r1 == 0The current implementation of
queue_work()provides such memory-ordering property:- In
__queue_work(), the ->lock spinlock is acquired.- On the other side, in
worker_thread(), this same ->lock is held when dequeueing work.
Quoted 8 lines
Quoted 6 lines
So the locking ordering makes things work out.
Add this property to the DocBook headers of {queue,schedule}_work().
Suggested-by Paul E. McKenney <[email protected]>Signed-off-by Andrea Parri <[email protected]>Acked-by Paul E. McKenney <[email protected]>
Thanks!
Quoted 4 lines
An alternative to Randy's suggestion of dropping the comma following the "cf." is to just drop that whole phrase. I will let you and Randy work that one out, though. ;-)
Either way works for me.
I'd give Tejun and Lai some more time to review this and send a non-RFC with your Ack and this nit fixed later this week (unless I hear some objections).
Thanks,
Andrea