[PATCH 3/3] nvme-pci: make nvme reset more reliable

[Ming Lei <ming.lei@xxxxxxxxxx>]

During waiting for in-flight IO completion in reset handler, timeout
or controller failure still may happen, then the controller is deleted
and all inflight IOs are failed. This way is too violent.

Improve the reset handling by replacing nvme_wait_freeze with query
& check controller. If all ns queues are frozen, the controller is reset
successfully, otherwise check and see if the controller has been disabled.
If yes, break from the current recovery and schedule a fresh new reset.

This way avoids to failing IO & removing controller unnecessarily.

Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Sagi Grimberg <sagi@xxxxxxxxxxx>
Cc: Keith Busch <kbusch@xxxxxxxxxx>
Cc: Max Gurtovoy <maxg@xxxxxxxxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
 drivers/nvme/host/pci.c | 37 ++++++++++++++++++++++++++++++-------
 1 file changed, 30 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index ce0d1e79467a..b5aeed33a634 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -24,6 +24,7 @@
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/sed-opal.h>
 #include <linux/pci-p2pdma.h>
+#include <linux/delay.h>
 
 #include "trace.h"
 #include "nvme.h"
@@ -1235,9 +1236,6 @@ 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_CONNECTING:
-		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
-		/* fall through */
 	case NVME_CTRL_DELETING:
 		dev_warn_ratelimited(dev->ctrl.device,
 			 "I/O %d QID %d timeout, disable controller\n",
@@ -2393,7 +2391,8 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 		u32 csts = readl(dev->bar + NVME_REG_CSTS);
 
 		if (dev->ctrl.state == NVME_CTRL_LIVE ||
-		    dev->ctrl.state == NVME_CTRL_RESETTING) {
+		    dev->ctrl.state == NVME_CTRL_RESETTING ||
+		    dev->ctrl.state == NVME_CTRL_CONNECTING) {
 			freeze = true;
 			nvme_start_freeze(&dev->ctrl);
 		}
@@ -2504,12 +2503,29 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev)
 		nvme_put_ctrl(&dev->ctrl);
 }
 
+static bool nvme_wait_freeze_and_check(struct nvme_dev *dev)
+{
+	bool frozen;
+
+	while (true) {
+		frozen = nvme_frozen(&dev->ctrl);
+		if (frozen)
+			break;
+		if (!dev->online_queues)
+			break;
+		msleep(5);
+	}
+
+	return frozen;
+}
+
 static void nvme_reset_work(struct work_struct *work)
 {
 	struct nvme_dev *dev =
 		container_of(work, struct nvme_dev, ctrl.reset_work);
 	bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
 	int result;
+	bool reset_done = true;
 
 	if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) {
 		result = -ENODEV;
@@ -2606,8 +2622,9 @@ static void nvme_reset_work(struct work_struct *work)
 		nvme_free_tagset(dev);
 	} else {
 		nvme_start_queues(&dev->ctrl);
-		nvme_wait_freeze(&dev->ctrl);
-		nvme_dev_add(dev);
+		reset_done = nvme_wait_freeze_and_check(dev);
+		if (reset_done)
+			nvme_dev_add(dev);
 		nvme_unfreeze(&dev->ctrl);
 	}
 
@@ -2622,7 +2639,13 @@ static void nvme_reset_work(struct work_struct *work)
 		goto out;
 	}
 
-	nvme_start_ctrl(&dev->ctrl);
+	/* New error happens during reset, so schedule a new reset */
+	if (!reset_done) {
+		dev_warn(dev->ctrl.device, "new error during reset\n");
+		nvme_reset_ctrl(&dev->ctrl);
+	} else {
+		nvme_start_ctrl(&dev->ctrl);
+	}
 	return;
 
  out_unlock:
-- 
2.25.2