summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDongli Zhang <dongli.zhang@oracle.com>2020-05-27 09:13:52 -0700
committerChristoph Hellwig <hch@lst.de>2020-05-27 20:32:56 +0200
commit9210c075cef29c1f764b4252f93105103bdfb292 (patch)
treec6d6b2a13976b6ac723df68bcc7c7312fc5bb397
parentb69e2ef24b7b4867f80f47e2781e95d0bacd15cb (diff)
downloadlinux-sh-9210c075cef29c1f764b4252f93105103bdfb292.tar.gz
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: fa46c6fb5d61 ("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>
-rw-r--r--drivers/nvme/host/pci.c11
1 files 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,