* [PATCH 1/1] nvme-pci: avoid race between nvme_reap_pending_cqes() and nvme_poll()
@ 2020-05-27 0:49 Dongli Zhang
2020-05-27 2:37 ` Ming Lei
` (2 more replies)
0 siblings, 3 replies; 5+ messages in thread
From: Dongli Zhang @ 2020-05-27 0:49 UTC (permalink / raw)
To: linux-nvme; +Cc: kbusch, axboe, sagi, linux-kernel, hch
There may be a race between nvme_reap_pending_cqes() and nvme_poll(), e.g.,
when doing live reset while polling the nvme device.
CPU X CPU Y
nvme_poll()
nvme_dev_disable()
-> nvme_stop_queues()
-> nvme_suspend_io_queues()
-> nvme_suspend_queue()
-> spin_lock(&nvmeq->cq_poll_lock);
-> nvme_reap_pending_cqes()
-> nvme_process_cq() -> nvme_process_cq()
In the above scenario, the nvme_process_cq() for the same queue may be
running on both CPU X and CPU Y concurrently.
It is much more easier to reproduce the issue when CONFIG_PREEMPT is
enabled in kernel. When CONFIG_PREEMPT is disabled, it would take longer
time for nvme_stop_queues()-->blk_mq_quiesce_queue() to wait for grace
period.
This patch protects nvme_process_cq() with nvmeq->cq_poll_lock in
nvme_reap_pending_cqes().
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
---
drivers/nvme/host/pci.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 3726dc780d15..cc46e250fcac 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1382,16 +1382,19 @@ static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
/*
* Called only on a device that has been disabled and after all other threads
- * that can check this device's completion queues have synced. This is the
- * last chance for the driver to see a natural completion before
- * nvme_cancel_request() terminates all incomplete requests.
+ * that can check this device's completion queues have synced, except
+ * nvme_poll(). This is the last chance for the driver to see a natural
+ * completion before nvme_cancel_request() terminates all incomplete requests.
*/
static void nvme_reap_pending_cqes(struct nvme_dev *dev)
{
int i;
- for (i = dev->ctrl.queue_count - 1; i > 0; i--)
+ for (i = dev->ctrl.queue_count - 1; i > 0; i--) {
+ spin_lock(&dev->queues[i].cq_poll_lock);
nvme_process_cq(&dev->queues[i]);
+ spin_unlock(&dev->queues[i].cq_poll_lock);
+ }
}
static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
--
2.17.1
_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH 1/1] nvme-pci: avoid race between nvme_reap_pending_cqes() and nvme_poll()
2020-05-27 0:49 [PATCH 1/1] nvme-pci: avoid race between nvme_reap_pending_cqes() and nvme_poll() Dongli Zhang
@ 2020-05-27 2:37 ` Ming Lei
2020-05-27 3:27 ` Keith Busch
2020-05-27 5:05 ` Christoph Hellwig
2 siblings, 0 replies; 5+ messages in thread
From: Ming Lei @ 2020-05-27 2:37 UTC (permalink / raw)
To: Dongli Zhang
Cc: Sagi Grimberg, Linux Kernel Mailing List, linux-nvme, Jens Axboe,
Keith Busch, Christoph Hellwig
On Wed, May 27, 2020 at 8:57 AM Dongli Zhang <dongli.zhang@oracle.com> wrote:
>
> There may be a race between nvme_reap_pending_cqes() and nvme_poll(), e.g.,
> when doing live reset while polling the nvme device.
>
> CPU X CPU Y
> nvme_poll()
> nvme_dev_disable()
> -> nvme_stop_queues()
> -> nvme_suspend_io_queues()
> -> nvme_suspend_queue()
> -> spin_lock(&nvmeq->cq_poll_lock);
> -> nvme_reap_pending_cqes()
> -> nvme_process_cq() -> nvme_process_cq()
>
> In the above scenario, the nvme_process_cq() for the same queue may be
> running on both CPU X and CPU Y concurrently.
>
> It is much more easier to reproduce the issue when CONFIG_PREEMPT is
> enabled in kernel. When CONFIG_PREEMPT is disabled, it would take longer
> time for nvme_stop_queues()-->blk_mq_quiesce_queue() to wait for grace
> period.
>
> This patch protects nvme_process_cq() with nvmeq->cq_poll_lock in
> nvme_reap_pending_cqes().
>
> Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
> ---
> drivers/nvme/host/pci.c | 11 +++++++----
> 1 file changed, 7 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
> index 3726dc780d15..cc46e250fcac 100644
> --- a/drivers/nvme/host/pci.c
> +++ b/drivers/nvme/host/pci.c
> @@ -1382,16 +1382,19 @@ static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
>
> /*
> * Called only on a device that has been disabled and after all other threads
> - * that can check this device's completion queues have synced. This is the
> - * last chance for the driver to see a natural completion before
> - * nvme_cancel_request() terminates all incomplete requests.
> + * that can check this device's completion queues have synced, except
> + * nvme_poll(). This is the last chance for the driver to see a natural
> + * completion before nvme_cancel_request() terminates all incomplete requests.
> */
> static void nvme_reap_pending_cqes(struct nvme_dev *dev)
> {
> int i;
>
> - for (i = dev->ctrl.queue_count - 1; i > 0; i--)
> + for (i = dev->ctrl.queue_count - 1; i > 0; i--) {
> + spin_lock(&dev->queues[i].cq_poll_lock);
> nvme_process_cq(&dev->queues[i]);
> + spin_unlock(&dev->queues[i].cq_poll_lock);
> + }
> }
Looks a real race, and the fix is fine:
Reviewed-by: Ming Lei <ming.lei@redhat.com>
thanks,
Ming Lei
_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH 1/1] nvme-pci: avoid race between nvme_reap_pending_cqes() and nvme_poll()
2020-05-27 0:49 [PATCH 1/1] nvme-pci: avoid race between nvme_reap_pending_cqes() and nvme_poll() Dongli Zhang
2020-05-27 2:37 ` Ming Lei
@ 2020-05-27 3:27 ` Keith Busch
2020-05-27 5:05 ` Christoph Hellwig
2 siblings, 0 replies; 5+ messages in thread
From: Keith Busch @ 2020-05-27 3:27 UTC (permalink / raw)
To: Dongli Zhang; +Cc: axboe, sagi, linux-kernel, linux-nvme, hch
Looks good to me.
Reviewed-by: Keith Busch <kbusch@kernel.org>
_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH 1/1] nvme-pci: avoid race between nvme_reap_pending_cqes() and nvme_poll()
2020-05-27 0:49 [PATCH 1/1] nvme-pci: avoid race between nvme_reap_pending_cqes() and nvme_poll() Dongli Zhang
2020-05-27 2:37 ` Ming Lei
2020-05-27 3:27 ` Keith Busch
@ 2020-05-27 5:05 ` Christoph Hellwig
2020-05-27 5:18 ` Keith Busch
2 siblings, 1 reply; 5+ messages in thread
From: Christoph Hellwig @ 2020-05-27 5:05 UTC (permalink / raw)
To: Dongli Zhang; +Cc: sagi, linux-kernel, linux-nvme, axboe, kbusch, hch
Can you add a Fixes tag so that this gets queued up for -stable properly?
_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2020-05-27 5:19 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-05-27 0:49 [PATCH 1/1] nvme-pci: avoid race between nvme_reap_pending_cqes() and nvme_poll() Dongli Zhang
2020-05-27 2:37 ` Ming Lei
2020-05-27 3:27 ` Keith Busch
2020-05-27 5:05 ` Christoph Hellwig
2020-05-27 5:18 ` Keith Busch
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).