[PATCH] nvme: ensure disabling pairs with unquiesce

[Keith Busch]

From: Keith Busch <kbusch at kernel.org>

If any error handling that disables the controller fails to queue the
reset work, like if the state changed to disconnected inbetween, then
the failed teardown needs to unquiesce the queues since it's no longer
paired with reset_work.

Reported-by: Ming Lei <ming.lei at redhat.com>
Signed-off-by: Keith Busch <kbusch at kernel.org>
---
 drivers/nvme/host/pci.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c9224d39195e5..bf21bd08ee7ed 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -108,6 +108,7 @@ MODULE_PARM_DESC(noacpi, "disable acpi bios quirks");
 struct nvme_dev;
 struct nvme_queue;
 
+static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown);
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown);
 static void nvme_delete_io_queues(struct nvme_dev *dev);
 static void nvme_update_attrs(struct nvme_dev *dev);
@@ -1298,9 +1299,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 */
 	if (nvme_should_reset(dev, csts)) {
 		nvme_warn_reset(dev, csts);
-		nvme_dev_disable(dev, false);
-		nvme_reset_ctrl(&dev->ctrl);
-		return BLK_EH_DONE;
+		goto disable;
 	}
 
 	/*
@@ -1351,10 +1350,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 			 "I/O %d QID %d timeout, reset controller\n",
 			 req->tag, nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
-		nvme_dev_disable(dev, false);
-		nvme_reset_ctrl(&dev->ctrl);
-
-		return BLK_EH_DONE;
+		goto disable;
 	}
 
 	if (atomic_dec_return(&dev->ctrl.abort_limit) < 0) {
@@ -1391,6 +1387,12 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 * as the device then is in a faulty state.
 	 */
 	return BLK_EH_RESET_TIMER;
+
+disable:
+	if (!nvme_disable_prepare_reset(dev, false) &&
+	    nvme_try_sched_reset(&dev->ctrl))
+		nvme_unquiesce_io_queues(&dev->ctrl);
+	return BLK_EH_DONE;
 }
 
 static void nvme_free_queue(struct nvme_queue *nvmeq)
@@ -3278,7 +3280,8 @@ static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev,
 	case pci_channel_io_frozen:
 		dev_warn(dev->ctrl.device,
 			"frozen state error detected, reset controller\n");
-		nvme_dev_disable(dev, false);
+		if (nvme_disable_prepare_reset(dev, false))
+			return PCI_ERS_RESULT_DISCONNECT;
 		return PCI_ERS_RESULT_NEED_RESET;
 	case pci_channel_io_perm_failure:
 		dev_warn(dev->ctrl.device,
@@ -3294,7 +3297,8 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
 
 	dev_info(dev->ctrl.device, "restart after slot reset\n");
 	pci_restore_state(pdev);
-	nvme_reset_ctrl(&dev->ctrl);
+	if (!nvme_try_sched_reset(&dev->ctrl))
+		nvme_unquiesce_io_queues(&dev->ctrl);
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
-- 
2.34.1