[PATCHv2] nvme-pci: enhance timeout kernel log

[Keith Busch]

From: Keith Busch <kbusch at kernel.org>

Kernel configs don't necessarily have opcode decoding, and some opcodes
are not even decodable. It is still interesting for debugging SSD issues
to know what opcode is timing out, what request type it came from, and
the data size (if applicable).

Signed-off-by: Keith Busch <kbusch at kernel.org>
---
v1->v2:

  Even more verbose annotations in the messages (Jens and Chaitanya)

 drivers/nvme/host/pci.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 507bc149046dc..f71ec41489a73 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1284,6 +1284,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	struct request *abort_req;
 	struct nvme_command cmd = { };
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
+	u8 opcode;
 
 	/* If PCI error recovery process is happening, we cannot reset or
 	 * the recovery mechanism will surely fail.
@@ -1310,7 +1311,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 
 	if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) {
 		dev_warn(dev->ctrl.device,
-			 "I/O %d QID %d timeout, completion polled\n",
+			 "I/O tag %d QID %d timeout, completion polled\n",
 			 req->tag, nvmeq->qid);
 		return BLK_EH_DONE;
 	}
@@ -1327,7 +1328,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 		fallthrough;
 	case NVME_CTRL_DELETING:
 		dev_warn_ratelimited(dev->ctrl.device,
-			 "I/O %d QID %d timeout, disable controller\n",
+			 "I/O tag %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		nvme_dev_disable(dev, true);
@@ -1343,10 +1344,12 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 * command was already aborted once before and still hasn't been
 	 * returned to the driver, or if this is the admin queue.
 	 */
+	opcode = nvme_req(req)->cmd->common.opcode;
 	if (!nvmeq->qid || iod->aborted) {
 		dev_warn(dev->ctrl.device,
-			 "I/O %d QID %d timeout, reset controller\n",
-			 req->tag, nvmeq->qid);
+			 "I/O tag %d (opcode:%s %d) QID %d timeout, reset controller\n",
+			 req->tag, nvme_opcode_str(nvmeq->qid, opcode, 0),
+			 opcode, nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		goto disable;
 	}
@@ -1362,10 +1365,9 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
 
 	dev_warn(nvmeq->dev->ctrl.device,
-		"I/O %d (%s) QID %d timeout, aborting\n",
-		 req->tag,
-		 nvme_get_opcode_str(nvme_req(req)->cmd->common.opcode),
-		 nvmeq->qid);
+		 "I/O tag %d (opcode:%s %d) QID %d timeout, aborting req_op:%s(%u) size:%u\n",
+		 req->tag, nvme_get_opcode_str(opcode), opcode, nvmeq->qid,
+		 blk_op_str(req_op(req)), req_op(req), blk_rq_bytes(req));
 
 	abort_req = blk_mq_alloc_request(dev->ctrl.admin_q, nvme_req_op(&cmd),
 					 BLK_MQ_REQ_NOWAIT);
-- 
2.34.1