AS spin lock bugs
Hi,
Was looking at io tracking for cfq, and I think I found some spin lock bugs in current as (current BK). as_update_iohist() runs from add_request which is typically in process context. It could be run with interrupts disabled though, either driver private stuff or using the generic block layer tagging.
Anyways, as_update_iohist() grabs aic->lock without disabling interrupts, while as_completed_request() typically runs at interrupt time and grabs the same lock. Deadlock.
To be safe, both need to use the flags saving lock variants.
===== drivers/block/as-iosched.c 1.28 vs edited =====
drivers/block/as-iosched.c +6 -5
@@ -783,14 +783,14 @@ {struct as_rq *arq =RQ_DATA (rq);int data_dir = arq->is_sync; -unsigned long thinktime; +unsigned long thinktime, flags;sector_t seek_dist;if (aic ==NULL )return ;if (data_dir ==REQ_SYNC ) { -spin_lock (&aic->lock); +spin_lock_irqsave (&aic->lock, flags);if (test_bit (AS_TASK_IORUNNING , &aic->state) && !atomic_read(&aic->nr_queued)
@@ -844,7 +844,7 @@ aic->seek_total = (aic->seek_total>>1 ) + (aic->seek_total>>2 ); -spin_unlock (&aic->lock); +spin_unlock_irqrestore (&aic->lock, flags); } }
@@ -909,6 +909,7 @@struct as_data *ad = q->elevator.elevator_data;struct as_rq *arq =RQ_DATA (rq);struct as_io_context *aic; +unsigned long flags;WARN_ON (!list_empty (&rq->queuelist));
@@ -959,12 +960,12 @@if (!aic)return ; -spin_lock (&aic->lock); +spin_lock_irqsave (&aic->lock, flags);if (arq->is_sync ==REQ_SYNC ) {set_bit (AS_TASK_IORUNNING , &aic->state); aic->last_end_request = jiffies; } -spin_unlock (&aic->lock); +spin_unlock_irqrestore (&aic->lock, flags);put_io_context (arq->io_context); }
Signature · 1 line
Jens Axboe
Quoted 5 lines · Jens Axboe
drivers/block/as-iosched.c +0
-1@@ -959,12 +960,12 @@if (!aic)return ; -spin_lock (&aic->lock);
drivers/block/as-iosched.c line 971
Quoted 10 lines
drivers/block/as-iosched.c +2
-1+spin_lock_irqsave (&aic->lock, flags);if (arq->is_sync ==REQ_SYNC ) {set_bit (AS_TASK_IORUNNING , &aic->state); aic->last_end_request = jiffies; } -spin_unlock (&aic->lock); +spin_unlock_irqrestore (&aic->lock, flags);put_io_context (arq->io_context); }
BTW, this looks bogus. Why do you need any locking there?
Signature · 1 line
Jens Axboe
Quoted 8 lines · Jens Axboe
Hi,
Was looking at io tracking for cfq, and I think I found some spin lock bugs in current as (current BK).
as_update_iohist()runs fromadd_requestwhich is typically in process context. It could be run with interrupts disabled though, either driver private stuff or using the generic block layer tagging.
Quoted 6 lines
Anyways,
as_update_iohist()grabsaic->lockwithout disabling interrupts, whileas_completed_request()typically runs at interrupt time and grabs the same lock. Deadlock.To be safe, both need to use the flags saving lock variants.
Hi Jens,
I was hoping everything ran under the queue lock which should always have interrupts off on the local CPU. The lock in question is to prevent a as_completed_request on one queue from racing with as_update_iohist on another. Each would be on a different CPU.
Maybe I'm wrong, did you actually see misbehaviour?
Quoted 16 lines · Nick Piggin
Quoted 12 lines · Jens Axboe
Hi,
Was looking at io tracking for cfq, and I think I found some spin lock bugs in current as (current BK).
as_update_iohist()runs fromadd_requestwhich is typically in process context. It could be run with interrupts disabled though, either driver private stuff or using the generic block layer tagging.Anyways,
as_update_iohist()grabsaic->lockwithout disabling interrupts, whileas_completed_request()typically runs at interrupt time and grabs the same lock. Deadlock.
Quoted 8 lines
Quoted 2 lines
To be safe, both need to use the flags saving lock variants.
Hi Jens,
I was hoping everything ran under the queue lock which should always have interrupts off on the local CPU. The lock in question is to prevent aas_completed_requeston one queue from racing withas_update_iohiston another. Each would be on a different CPU.
Ah yes you are right. The queue lock will be held in both places.
Quoted 1 line
Maybe I'm wrong, did you actually see misbehaviour?
Nope, just looking over the code. What about the second lock, why is that needed? I don't see that protecting anything.
Signature · 1 line
Jens Axboe
Quoted 15 lines · Jens Axboe
Quoted 13 lines · Jens Axboe
drivers/block/as-iosched.c +2
-2@@ -959,12 +960,12 @@if (!aic)return ; -spin_lock (&aic->lock); +spin_lock_irqsave (&aic->lock, flags);if (arq->is_sync ==REQ_SYNC ) {set_bit (AS_TASK_IORUNNING , &aic->state); aic->last_end_request = jiffies; } -spin_unlock (&aic->lock); +spin_unlock_irqrestore (&aic->lock, flags);
Quoted 6 lines
drivers/block/as-iosched.c line 971
Quoted 3 lines
drivers/block/as-iosched.c +0
-0put_io_context (arq->io_context); }BTW, this looks bogus. Why do you need any locking there?
To prevent a request completion on another queue on another CPU from racing with request insertion: last_end_request is undefined if the flag is not set. I guess you could flip the statements and put a smp_mb between them. Probably not worth the trouble though.
Quoted 26 lines · Nick Piggin
Quoted 15 lines · Jens Axboe
Quoted 13 lines · Jens Axboe
drivers/block/as-iosched.c +2
-2@@ -959,12 +960,12 @@if (!aic)return ; -spin_lock (&aic->lock); +spin_lock_irqsave (&aic->lock, flags);if (arq->is_sync ==REQ_SYNC ) {set_bit (AS_TASK_IORUNNING , &aic->state); aic->last_end_request = jiffies; } -spin_unlock (&aic->lock); +spin_unlock_irqrestore (&aic->lock, flags);Quoted 6 lines
drivers/block/as-iosched.c line 971
Quoted 3 lines
drivers/block/as-iosched.c +0
-0put_io_context (arq->io_context); }BTW, this looks bogus. Why do you need any locking there?
Quoted 4 lines
To prevent a request completion on another queue on another CPU from racing with request insertion:
last_end_requestis undefined if the flag is not set. I guess you could flip the statements and put asmp_mbbetween them. Probably not worth the trouble though.
No better to make it explicit, probably doesn't matter much in real-life. Thanks for the clarifications.
Signature · 1 line
Jens Axboe
Quoted 27 lines · Jens Axboe
Quoted 26 lines · Nick Piggin
Quoted 21 lines · Jens Axboe
Quoted 6 lines · Jens Axboe
drivers/block/as-iosched.c +0
-1@@ -959,12 +960,12 @@if (!aic)return ; -spin_lock (&aic->lock);drivers/block/as-iosched.c line 971
Quoted 10 lines
drivers/block/as-iosched.c +2
-1+spin_lock_irqsave (&aic->lock, flags);if (arq->is_sync ==REQ_SYNC ) {set_bit (AS_TASK_IORUNNING , &aic->state); aic->last_end_request = jiffies; } -spin_unlock (&aic->lock); +spin_unlock_irqrestore (&aic->lock, flags);put_io_context (arq->io_context); }BTW, this looks bogus. Why do you need any locking there?
Quoted 7 lines
Quoted 4 lines
To prevent a request completion on another queue on another CPU from racing with request insertion:
last_end_requestis undefined if the flag is not set. I guess you could flip the statements and put asmp_mbbetween them. Probably not worth the trouble though.No better to make it explicit, probably doesn't matter much in real-life. Thanks for the clarifications.
Ah, it would be clearer as:
if (arq->is_sync == REQ_SYNC) {
spin_lock(&aic->lock);
set_bit(AS_TASK_IORUNNING, &aic->state);
aic->last_end_request = jiffies;
spin_unlock(&aic->lock);
}Then it doesn't need comments :)
Signature · 1 line
Jens Axboe
Quoted 42 lines · Jens Axboe
Quoted 29 lines · Jens Axboe
Quoted 27 lines · Nick Piggin
Quoted 23 lines · Jens Axboe
Quoted 7 lines · Jens Axboe
drivers/block/as-iosched.c +0
-1@@ -959,12 +960,12 @@if (!aic)return ; -spin_lock (&aic->lock);drivers/block/as-iosched.c line 971
Quoted 10 lines
drivers/block/as-iosched.c +2
-1+spin_lock_irqsave (&aic->lock, flags);if (arq->is_sync ==REQ_SYNC ) {set_bit (AS_TASK_IORUNNING , &aic->state); aic->last_end_request = jiffies; } -spin_unlock (&aic->lock); +spin_unlock_irqrestore (&aic->lock, flags);put_io_context (arq->io_context); }BTW, this looks bogus. Why do you need any locking there?
Quoted 8 lines
Quoted 5 lines
To prevent a request completion on another queue on another CPU from racing with request insertion:
last_end_requestis undefined if the flag is not set. I guess you could flip the statements and put asmp_mbbetween them. Probably not worth the trouble though.No better to make it explicit, probably doesn't matter much in real-life. Thanks for the clarifications.
Ah, it would be clearer as:
Quoted 9 lines
if (arq->is_sync == REQ_SYNC) { spin_lock(&aic->lock); set_bit(AS_TASK_IORUNNING, &aic->state); aic->last_end_request = jiffies; spin_unlock(&aic->lock); }Then it doesn't need comments :)
Yeah thats was a bit silly of me I see why you got confused. I have actually fixed this up in mm3. So it should get through to Linus sometime after 2.6.0.