1 files changed, 65 insertions, 33 deletions

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 56caddeabb5e..3968f89f7855 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2017-2018 Christoph Hellwig.
  */
 
+#include <linux/backing-dev.h>
 #include <linux/moduleparam.h>
 #include <trace/events/block.h>
 #include "nvme.h"
@@ -64,17 +65,12 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 	}
 }
 
-void nvme_failover_req(struct request *req)
+bool nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
 	u16 status = nvme_req(req)->status;
 	unsigned long flags;
 
-	spin_lock_irqsave(&ns->head->requeue_lock, flags);
-	blk_steal_bios(&ns->head->requeue_list, req);
-	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
-	blk_mq_end_request(req, 0);
-
 	switch (status & 0x7ff) {
 	case NVME_SC_ANA_TRANSITION:
 	case NVME_SC_ANA_INACCESSIBLE:
@@ -103,15 +99,17 @@ void nvme_failover_req(struct request *req)
 		nvme_mpath_clear_current_path(ns);
 		break;
 	default:
-		/*
-		 * Reset the controller for any non-ANA error as we don't know
-		 * what caused the error.
-		 */
-		nvme_reset_ctrl(ns->ctrl);
-		break;
+		/* This was a non-ANA error so follow the normal error path. */
+		return false;
 	}
 
+	spin_lock_irqsave(&ns->head->requeue_lock, flags);
+	blk_steal_bios(&ns->head->requeue_list, req);
+	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
+	blk_mq_end_request(req, 0);
+
 	kblockd_schedule_work(&ns->head->requeue_work);
+	return true;
 }
 
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
@@ -248,6 +246,17 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 			fallback = ns;
 	}
 
+	/*
+	 * The loop above skips the current path for round-robin semantics.
+	 * Fall back to the current path if either:
+	 *  - no other optimized path found and current is optimized,
+	 *  - no other usable path found and current is usable.
+	 */
+	if (!nvme_path_is_disabled(old) &&
+	    (old->ana_state == NVME_ANA_OPTIMIZED ||
+	     (!fallback && old->ana_state == NVME_ANA_NONOPTIMIZED)))
+		return old;
+
 	if (!fallback)
 		return NULL;
 	found = fallback;
@@ -268,10 +277,13 @@ inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
 	struct nvme_ns *ns;
 
 	ns = srcu_dereference(head->current_path[node], &head->srcu);
-	if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR && ns)
-		ns = nvme_round_robin_path(head, node, ns);
-	if (unlikely(!ns || !nvme_path_is_optimized(ns)))
-		ns = __nvme_find_path(head, node);
+	if (unlikely(!ns))
+		return __nvme_find_path(head, node);
+
+	if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR)
+		return nvme_round_robin_path(head, node, ns);
+	if (unlikely(!nvme_path_is_optimized(ns)))
+		return __nvme_find_path(head, node);
 	return ns;
 }
 
@@ -413,15 +425,14 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 {
 	struct nvme_ns_head *head = ns->head;
 
-	lockdep_assert_held(&ns->head->lock);
-
 	if (!head->disk)
 		return;
 
-	if (!(head->disk->flags & GENHD_FL_UP))
+	if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
 		device_add_disk(&head->subsys->dev, head->disk,
 				nvme_ns_id_attr_groups);
 
+	mutex_lock(&head->lock);
 	if (nvme_path_is_optimized(ns)) {
 		int node, srcu_idx;
 
@@ -430,9 +441,10 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 			__nvme_find_path(head, node);
 		srcu_read_unlock(&head->srcu, srcu_idx);
 	}
+	mutex_unlock(&head->lock);
 
-	synchronize_srcu(&ns->head->srcu);
-	kblockd_schedule_work(&ns->head->requeue_work);
+	synchronize_srcu(&head->srcu);
+	kblockd_schedule_work(&head->requeue_work);
 }
 
 static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
@@ -483,14 +495,12 @@ static inline bool nvme_state_is_live(enum nvme_ana_state state)
 static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 		struct nvme_ns *ns)
 {
-	mutex_lock(&ns->head->lock);
 	ns->ana_grpid = le32_to_cpu(desc->grpid);
 	ns->ana_state = desc->state;
 	clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
 
 	if (nvme_state_is_live(ns->ana_state))
 		nvme_mpath_set_live(ns);
-	mutex_unlock(&ns->head->lock);
 }
 
 static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
@@ -640,31 +650,45 @@ static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr,
 }
 DEVICE_ATTR_RO(ana_state);
 
-static int nvme_set_ns_ana_state(struct nvme_ctrl *ctrl,
+static int nvme_lookup_ana_group_desc(struct nvme_ctrl *ctrl,
 		struct nvme_ana_group_desc *desc, void *data)
 {
-	struct nvme_ns *ns = data;
+	struct nvme_ana_group_desc *dst = data;
 
-	if (ns->ana_grpid == le32_to_cpu(desc->grpid)) {
-		nvme_update_ns_ana_state(desc, ns);
-		return -ENXIO; /* just break out of the loop */
-	}
+	if (desc->grpid != dst->grpid)
+		return 0;
 
-	return 0;
+	*dst = *desc;
+	return -ENXIO; /* just break out of the loop */
 }
 
 void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
 {
 	if (nvme_ctrl_use_ana(ns->ctrl)) {
+		struct nvme_ana_group_desc desc = {
+			.grpid = id->anagrpid,
+			.state = 0,
+		};
+
 		mutex_lock(&ns->ctrl->ana_lock);
 		ns->ana_grpid = le32_to_cpu(id->anagrpid);
-		nvme_parse_ana_log(ns->ctrl, ns, nvme_set_ns_ana_state);
+		nvme_parse_ana_log(ns->ctrl, &desc, nvme_lookup_ana_group_desc);
 		mutex_unlock(&ns->ctrl->ana_lock);
+		if (desc.state) {
+			/* found the group desc: update */
+			nvme_update_ns_ana_state(&desc, ns);
+		}
 	} else {
-		mutex_lock(&ns->head->lock);
 		ns->ana_state = NVME_ANA_OPTIMIZED; 
 		nvme_mpath_set_live(ns);
-		mutex_unlock(&ns->head->lock);
+	}
+
+	if (bdi_cap_stable_pages_required(ns->queue->backing_dev_info)) {
+		struct gendisk *disk = ns->head->disk;
+
+		if (disk)
+			disk->queue->backing_dev_info->capabilities |=
+					BDI_CAP_STABLE_WRITES;
 	}
 }
 
@@ -679,6 +703,14 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	kblockd_schedule_work(&head->requeue_work);
 	flush_work(&head->requeue_work);
 	blk_cleanup_queue(head->disk->queue);
+	if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
+		/*
+		 * if device_add_disk wasn't called, prevent
+		 * disk release to put a bogus reference on the
+		 * request queue
+		 */
+		head->disk->queue = NULL;
+	}
 	put_disk(head->disk);
 }