[PATCH v3 2/3] nvme: check IO start time when deciding to defer KA

[Uday Shankar]

When a command completes, we set a flag which will skip sending a
keep alive at the next run of nvme_keep_alive_work when TBKAS is on.
However, if the command was submitted long ago, it's possible that
the controller may have also restarted its keep alive timer (as a
result of receiving the command) long ago. The following trace
demonstrates the issue, assuming TBKAS is on and KATO = 8 for
simplicity:

1. t = 0: submit I/O commands A, B, C, D, E
2. t = 0.5: commands A, B, C, D, E reach controller, restart its keep
            alive timer
3. t = 1: A completes
4. t = 2: run nvme_keep_alive_work, see recent completion, do nothing
5. t = 3: B completes
6. t = 4: run nvme_keep_alive_work, see recent completion, do nothing
7. t = 5: C completes
8. t = 6: run nvme_keep_alive_work, see recent completion, do nothing
9. t = 7: D completes
10. t = 8: run nvme_keep_alive_work, see recent completion, do nothing
11. t = 9: E completes

At this point, 8.5 seconds have passed without restarting the
controller's keep alive timer, so the controller will detect a keep
alive timeout.

Fix this by checking the IO start time when deciding to defer sending a
keep alive command. Only set comp_seen if the command started after the
most recent run of nvme_keep_alive_work. With this change, the
completions of B, C, and D will not set comp_seen and the run of
nvme_keep_alive_work at t = 4 will send a keep alive.

Reported-by: Costa Sapuntzakis <costa at purestorage.com>
Reported-by: Randy Jennings <randyj at purestorage.com>
Signed-off-by: Uday Shankar <ushankar at purestorage.com>
Reviewed-by: Hannes Reinecke <hare at suse.de>
Reviewed-by: Sagi Grimberg <sagi at grimberg.me>
---
 drivers/nvme/host/core.c | 14 +++++++++++++-
 drivers/nvme/host/nvme.h |  4 ++--
 2 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 7726277b951a..a31c04b5f849 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -397,7 +397,14 @@ void nvme_complete_rq(struct request *req)
 	trace_nvme_complete_rq(req);
 	nvme_cleanup_cmd(req);
 
-	if (ctrl->kas)
+	/*
+	 * Completions of long-running commands should not be able to
+	 * defer sending of periodic keep alives, since the controller
+	 * may have completed processing such commands a long time ago
+	 * (arbitrarily close to command submission time).
+	 */
+	if (ctrl->kas && !ctrl->comp_seen &&
+	    nvme_req(req)->start_time >= ctrl->ka_last_check_time)
 		ctrl->comp_seen = true;
 
 	switch (nvme_decide_disposition(req)) {
@@ -1188,6 +1195,8 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
 		return RQ_END_IO_NONE;
 	}
 
+	WRITE_ONCE(ctrl->ka_last_check_time, jiffies);
+	smp_wmb();
 	ctrl->comp_seen = false;
 	spin_lock_irqsave(&ctrl->lock, flags);
 	if (ctrl->state == NVME_CTRL_LIVE ||
@@ -1206,6 +1215,9 @@ static void nvme_keep_alive_work(struct work_struct *work)
 	bool comp_seen = ctrl->comp_seen;
 	struct request *rq;
 
+	WRITE_ONCE(ctrl->ka_last_check_time, jiffies);
+	smp_wmb();
+
 	if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) {
 		dev_dbg(ctrl->device,
 			"reschedule traffic based keep-alive timer\n");
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index f0a84e390a55..07ed39ea43e3 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -162,9 +162,7 @@ struct nvme_request {
 	u8			retries;
 	u8			flags;
 	u16			status;
-#ifdef CONFIG_NVME_MULTIPATH
 	unsigned long		start_time;
-#endif
 	struct nvme_ctrl	*ctrl;
 };
 
@@ -323,6 +321,7 @@ struct nvme_ctrl {
 	struct delayed_work ka_work;
 	struct delayed_work failfast_work;
 	struct nvme_command ka_cmd;
+	unsigned long ka_last_check_time;
 	struct work_struct fw_act_work;
 	unsigned long events;
 
@@ -1032,6 +1031,7 @@ static inline void nvme_start_request(struct request *rq)
 {
 	if (rq->cmd_flags & REQ_NVME_MPATH)
 		nvme_mpath_start_request(rq);
+	nvme_req(rq)->start_time = jiffies;
 	blk_mq_start_request(rq);
 }
 
-- 
2.25.1