mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-05 10:29:37 +00:00
nvme-pci: avoid race between nvme_reap_pending_cqes() and nvme_poll()
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().
Fixes: fa46c6fb5d
("nvme/pci: move cqe check after device shutdown")
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This commit is contained in:
parent
b69e2ef24b
commit
9210c075ce
1 changed files with 7 additions and 4 deletions
|
@ -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,
|
||||
|
|
Loading…
Reference in a new issue