1 files changed, 48 insertions, 4 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 1f0cbb77b249..3ec38e2b9173 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -397,7 +397,16 @@ 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).
+	 * req->deadline - req->timeout is the command submission time
+	 * in jiffies.
+	 */
+	if (ctrl->kas &&
+	    req->deadline - req->timeout >= ctrl->ka_last_check_time)
 		ctrl->comp_seen = true;
 
 	switch (nvme_decide_disposition(req)) {
@@ -1115,7 +1124,7 @@ u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
 }
 EXPORT_SYMBOL_NS_GPL(nvme_passthru_start, NVME_TARGET_PASSTHRU);
 
-void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects,
+void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects,
 		       struct nvme_command *cmd, int status)
 {
 	if (effects & NVME_CMD_EFFECTS_CSE_MASK) {
@@ -1132,6 +1141,8 @@ void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects,
 		nvme_queue_scan(ctrl);
 		flush_work(&ctrl->scan_work);
 	}
+	if (ns)
+		return;
 
 	switch (cmd->common.opcode) {
 	case nvme_admin_set_features:
@@ -1161,9 +1172,25 @@ EXPORT_SYMBOL_NS_GPL(nvme_passthru_end, NVME_TARGET_PASSTHRU);
  *   The host should send Keep Alive commands at half of the Keep Alive Timeout
  *   accounting for transport roundtrip times [..].
  */
+static unsigned long nvme_keep_alive_work_period(struct nvme_ctrl *ctrl)
+{
+	unsigned long delay = ctrl->kato * HZ / 2;
+
+	/*
+	 * When using Traffic Based Keep Alive, we need to run
+	 * nvme_keep_alive_work at twice the normal frequency, as one
+	 * command completion can postpone sending a keep alive command
+	 * by up to twice the delay between runs.
+	 */
+	if (ctrl->ctratt & NVME_CTRL_ATTR_TBKAS)
+		delay /= 2;
+	return delay;
+}
+
 static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
 {
-	queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ / 2);
+	queue_delayed_work(nvme_wq, &ctrl->ka_work,
+			   nvme_keep_alive_work_period(ctrl));
 }
 
 static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
@@ -1172,6 +1199,20 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
 	struct nvme_ctrl *ctrl = rq->end_io_data;
 	unsigned long flags;
 	bool startka = false;
+	unsigned long rtt = jiffies - (rq->deadline - rq->timeout);
+	unsigned long delay = nvme_keep_alive_work_period(ctrl);
+
+	/*
+	 * Subtract off the keepalive RTT so nvme_keep_alive_work runs
+	 * at the desired frequency.
+	 */
+	if (rtt <= delay) {
+		delay -= rtt;
+	} else {
+		dev_warn(ctrl->device, "long keepalive RTT (%u ms)\n",
+			 jiffies_to_msecs(rtt));
+		delay = 0;
+	}
 
 	blk_mq_free_request(rq);
 
@@ -1182,6 +1223,7 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
 		return RQ_END_IO_NONE;
 	}
 
+	ctrl->ka_last_check_time = jiffies;
 	ctrl->comp_seen = false;
 	spin_lock_irqsave(&ctrl->lock, flags);
 	if (ctrl->state == NVME_CTRL_LIVE ||
@@ -1189,7 +1231,7 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
 		startka = true;
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 	if (startka)
-		nvme_queue_keep_alive_work(ctrl);
+		queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
 	return RQ_END_IO_NONE;
 }
 
@@ -1200,6 +1242,8 @@ static void nvme_keep_alive_work(struct work_struct *work)
 	bool comp_seen = ctrl->comp_seen;
 	struct request *rq;
 
+	ctrl->ka_last_check_time = jiffies;
+
 	if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) {
 		dev_dbg(ctrl->device,
 			"reschedule traffic based keep-alive timer\n");