Skip to contentSkip to conversation

nvme: Inform controller of doorbell config before unquiescing IO queues

PATCH In review William Butler 2 participants 2 messages Jan 10, 2024 NVMe

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 nvme: Inform controller of doorbell config before unquiescing IO queues

During resets, if queues are unquiesced first, then the host can submit IOs to the controller using shadow doorbell logic but the controller won't be aware. This can lead to necessary MMIO doorbells from being not issued, causing requests to be delayed and timed-out.

---
 drivers/nvme/host/pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/nvme/host/pci.c +1 -1
index 61af7ff1a9d6..f87c51a946b3 100644
@@ -2743,10 +2743,10 @@ static void nvme_reset_work(struct work_struct *work)
 	 * controller around but remove all namespaces.
 	 */
 	if (dev->online_queues > 1) {
+		nvme_dbbuf_set(dev);
 		nvme_unquiesce_io_queues(&dev->ctrl);
 		nvme_wait_freeze(&dev->ctrl);
 		nvme_pci_update_nr_queues(dev);
-		nvme_dbbuf_set(dev);
 		nvme_unfreeze(&dev->ctrl);
 	} else {
 		dev_warn(dev->ctrl.device, "IO queues lost\n");
Signature · 1 line
2.43.0.275.g3460e3d667-goog
maintainer
#1 lore raw
Quoted 4 lines · William Butler

During resets, if queues are unquiesced first, then the host can submit IOs to the controller using shadow doorbell logic but the controller won't be aware. This can lead to necessary MMIO doorbells from being not issued, causing requests to be delayed and timed-out.

Good catch. I guess we wouldn't normally expect any requests to be in queue at this point, but plenty of reasons it could happen.

Applied to nvme-6.8 with a slightly updated title to match the local conventions.