Commit 9f9cafc1 authored by Jianchao Wang's avatar Jianchao Wang Committed by Christoph Hellwig

nvme-pci: move nvme_kill_queues to nvme_remove_dead_ctrl

There is race between nvme_remove and nvme_reset_work that can
lead to io hang.

nvme_remove                    nvme_reset_work
                               -> nvme_remove_dead_ctrl
                                 -> nvme_dev_disable
                                   -> quiesce request_queue
                                 -> queue remove_work
-> cancel_work_sync reset_work
-> nvme_remove_namespaces
  -> splice ctrl->namespaces
                               nvme_remove_dead_ctrl_work
                               -> nvme_kill_queues
  -> nvme_ns_remove               do nothing
    -> blk_cleanup_queue
      -> blk_freeze_queue

Finally, the request_queue is quiesced state when wait freeze,
we will get io hang here. To fix it, move the nvme_kill_queues
from nvme_remove_dead_ctrl_work to nvme_remove_dead_ctrl.
Suggested-by: default avatarKeith Busch <keith.busch@linux.intel.com>
Signed-off-by: default avatarJianchao Wang <jianchao.w.wang@oracle.com>
Reviewed-by: default avatarKeith Busch <keith.busch@intel.com>
Signed-off-by: default avatarChristoph Hellwig <hch@lst.de>
parent 02d62a8b
...@@ -2289,6 +2289,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status) ...@@ -2289,6 +2289,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status)
nvme_get_ctrl(&dev->ctrl); nvme_get_ctrl(&dev->ctrl);
nvme_dev_disable(dev, false); nvme_dev_disable(dev, false);
nvme_kill_queues(&dev->ctrl);
if (!queue_work(nvme_wq, &dev->remove_work)) if (!queue_work(nvme_wq, &dev->remove_work))
nvme_put_ctrl(&dev->ctrl); nvme_put_ctrl(&dev->ctrl);
} }
...@@ -2405,7 +2406,6 @@ static void nvme_remove_dead_ctrl_work(struct work_struct *work) ...@@ -2405,7 +2406,6 @@ static void nvme_remove_dead_ctrl_work(struct work_struct *work)
struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work); struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work);
struct pci_dev *pdev = to_pci_dev(dev->dev); struct pci_dev *pdev = to_pci_dev(dev->dev);
nvme_kill_queues(&dev->ctrl);
if (pci_get_drvdata(pdev)) if (pci_get_drvdata(pdev))
device_release_driver(&pdev->dev); device_release_driver(&pdev->dev);
nvme_put_ctrl(&dev->ctrl); nvme_put_ctrl(&dev->ctrl);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment