nvme-pci: shutdown on timeout during deletion

[ Upstream commit 9dc1a38ef1925d23c2933c5867df816386d92ff8 ]

We do not restart a controller in a deleting state for timeout errors.
When in this state, unblock potential request dispatchers with failed
completions by shutting down the controller on timeout detection.

Reported-by: Yufen Yu <yuyufen@huawei.com>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 377f6ff..c8eeecc 100644 (file)
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1132,6 +1132,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
        struct nvme_dev *dev = nvmeq->dev;
        struct request *abort_req;
        struct nvme_command cmd;
+       bool shutdown = false;
        u32 csts = readl(dev->bar + NVME_REG_CSTS);
 
        /* If PCI error recovery process is happening, we cannot reset or
@@ -1168,12 +1169,14 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
         * shutdown, so we return BLK_EH_DONE.
         */
        switch (dev->ctrl.state) {
+       case NVME_CTRL_DELETING:
+               shutdown = true;
        case NVME_CTRL_CONNECTING:
        case NVME_CTRL_RESETTING:
                dev_warn_ratelimited(dev->ctrl.device,
                         "I/O %d QID %d timeout, disable controller\n",
                         req->tag, nvmeq->qid);
-               nvme_dev_disable(dev, false);
+               nvme_dev_disable(dev, shutdown);
                nvme_req(req)->flags |= NVME_REQ_CANCELLED;
                return BLK_EH_DONE;
        default: