1 files changed, 82 insertions, 26 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c2730b116dc6..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)) {
@@ -450,8 +459,8 @@ bool nvme_cancel_request(struct request *req, void *data)
 	dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
 				"Cancelling I/O %d", req->tag);
 
-	/* don't abort one completed request */
-	if (blk_mq_request_completed(req))
+	/* don't abort one completed or idle request */
+	if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT)
 		return true;
 
 	nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD;
@@ -781,16 +790,26 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 		range = page_address(ns->ctrl->discard_page);
 	}
 
-	__rq_for_each_bio(bio, req) {
-		u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector);
-		u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;
+	if (queue_max_discard_segments(req->q) == 1) {
+		u64 slba = nvme_sect_to_lba(ns, blk_rq_pos(req));
+		u32 nlb = blk_rq_sectors(req) >> (ns->lba_shift - 9);
 
-		if (n < segments) {
-			range[n].cattr = cpu_to_le32(0);
-			range[n].nlb = cpu_to_le32(nlb);
-			range[n].slba = cpu_to_le64(slba);
+		range[0].cattr = cpu_to_le32(0);
+		range[0].nlb = cpu_to_le32(nlb);
+		range[0].slba = cpu_to_le64(slba);
+		n = 1;
+	} else {
+		__rq_for_each_bio(bio, req) {
+			u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector);
+			u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;
+
+			if (n < segments) {
+				range[n].cattr = cpu_to_le32(0);
+				range[n].nlb = cpu_to_le32(nlb);
+				range[n].slba = cpu_to_le64(slba);
+			}
+			n++;
 		}
-		n++;
 	}
 
 	if (WARN_ON_ONCE(n != segments)) {
@@ -1105,7 +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) {
@@ -1122,6 +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:
@@ -1151,9 +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,
@@ -1162,6 +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);
 
@@ -1172,6 +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 ||
@@ -1179,7 +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;
 }
 
@@ -1190,6 +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");
@@ -1664,6 +1718,9 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
 	struct request_queue *queue = disk->queue;
 	u32 size = queue_logical_block_size(queue);
 
+	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns, UINT_MAX))
+		ctrl->max_discard_sectors = nvme_lba_to_sect(ns, ctrl->dmrsl);
+
 	if (ctrl->max_discard_sectors == 0) {
 		blk_queue_max_discard_sectors(queue, 0);
 		return;
@@ -1678,9 +1735,6 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
 	if (queue->limits.max_discard_sectors)
 		return;
 
-	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns, UINT_MAX))
-		ctrl->max_discard_sectors = nvme_lba_to_sect(ns, ctrl->dmrsl);
-
 	blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors);
 	blk_queue_max_discard_segments(queue, ctrl->max_discard_segments);
 
@@ -3053,7 +3107,8 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
 	else
 		ctrl->max_zeroes_sectors = 0;
 
-	if (nvme_ctrl_limited_cns(ctrl))
+	if (ctrl->subsys->subtype != NVME_NQN_NVME ||
+	    nvme_ctrl_limited_cns(ctrl))
 		return 0;
 
 	id = kzalloc(sizeof(*id), GFP_KERNEL);
@@ -3574,6 +3629,9 @@ static ssize_t nvme_sysfs_delete(struct device *dev,
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
 
+	if (!test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags))
+		return -EBUSY;
+
 	if (device_remove_file_self(dev, attr))
 		nvme_delete_ctrl_sync(ctrl);
 	return count;
@@ -4808,8 +4866,6 @@ static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 	u32 aer_notice_type = nvme_aer_subtype(result);
 	bool requeue = true;
 
-	trace_nvme_async_event(ctrl, aer_notice_type);
-
 	switch (aer_notice_type) {
 	case NVME_AER_NOTICE_NS_CHANGED:
 		set_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events);
@@ -4845,7 +4901,6 @@ static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 
 static void nvme_handle_aer_persistent_error(struct nvme_ctrl *ctrl)
 {
-	trace_nvme_async_event(ctrl, NVME_AER_ERROR);
 	dev_warn(ctrl->device, "resetting controller due to AER\n");
 	nvme_reset_ctrl(ctrl);
 }
@@ -4861,6 +4916,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 	if (le16_to_cpu(status) >> 1 != NVME_SC_SUCCESS)
 		return;
 
+	trace_nvme_async_event(ctrl, result);
 	switch (aer_type) {
 	case NVME_AER_NOTICE:
 		requeue = nvme_handle_aen_notice(ctrl, result);
@@ -4878,7 +4934,6 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 	case NVME_AER_SMART:
 	case NVME_AER_CSS:
 	case NVME_AER_VS:
-		trace_nvme_async_event(ctrl, aer_type);
 		ctrl->aen_result = result;
 		break;
 	default:
@@ -5037,7 +5092,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 	 * that were missed. We identify persistent discovery controllers by
 	 * checking that they started once before, hence are reconnecting back.
 	 */
-	if (test_and_set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) &&
+	if (test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) &&
 	    nvme_discovery_ctrl(ctrl))
 		nvme_change_uevent(ctrl, "NVME_EVENT=rediscover");
 
@@ -5048,6 +5103,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 	}
 
 	nvme_change_uevent(ctrl, "NVME_EVENT=connected");
+	set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags);
 }
 EXPORT_SYMBOL_GPL(nvme_start_ctrl);
 
@@ -5381,14 +5437,14 @@ static int __init nvme_core_init(void)
 	if (result < 0)
 		goto destroy_delete_wq;
 
-	nvme_class = class_create(THIS_MODULE, "nvme");
+	nvme_class = class_create("nvme");
 	if (IS_ERR(nvme_class)) {
 		result = PTR_ERR(nvme_class);
 		goto unregister_chrdev;
 	}
 	nvme_class->dev_uevent = nvme_class_uevent;
 
-	nvme_subsys_class = class_create(THIS_MODULE, "nvme-subsystem");
+	nvme_subsys_class = class_create("nvme-subsystem");
 	if (IS_ERR(nvme_subsys_class)) {
 		result = PTR_ERR(nvme_subsys_class);
 		goto destroy_class;
@@ -5399,7 +5455,7 @@ static int __init nvme_core_init(void)
 	if (result < 0)
 		goto destroy_subsys_class;
 
-	nvme_ns_chr_class = class_create(THIS_MODULE, "nvme-generic");
+	nvme_ns_chr_class = class_create("nvme-generic");
 	if (IS_ERR(nvme_ns_chr_class)) {
 		result = PTR_ERR(nvme_ns_chr_class);
 		goto unregister_generic_ns;