Merge tag 'v5.8.5' into dev-5.8dev-5.8

This is the 5.8.5 stable release

Signed-off-by: Joel Stanley <joel@jms.id.au>

8 files changed, 81 insertions, 25 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4ee2330c603e..f38548e6d55e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -362,6 +362,16 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 			break;
 		}
 		break;
+	case NVME_CTRL_DELETING_NOIO:
+		switch (old_state) {
+		case NVME_CTRL_DELETING:
+		case NVME_CTRL_DEAD:
+			changed = true;
+			/* FALLTHRU */
+		default:
+			break;
+		}
+		break;
 	case NVME_CTRL_DEAD:
 		switch (old_state) {
 		case NVME_CTRL_DELETING:
@@ -399,6 +409,7 @@ static bool nvme_state_terminal(struct nvme_ctrl *ctrl)
 	case NVME_CTRL_CONNECTING:
 		return false;
 	case NVME_CTRL_DELETING:
+	case NVME_CTRL_DELETING_NOIO:
 	case NVME_CTRL_DEAD:
 		return true;
 	default:
@@ -3344,6 +3355,7 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 		[NVME_CTRL_RESETTING]	= "resetting",
 		[NVME_CTRL_CONNECTING]	= "connecting",
 		[NVME_CTRL_DELETING]	= "deleting",
+		[NVME_CTRL_DELETING_NOIO]= "deleting (no IO)",
 		[NVME_CTRL_DEAD]	= "dead",
 	};
 
@@ -3911,6 +3923,9 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 	if (ctrl->state == NVME_CTRL_DEAD)
 		nvme_kill_queues(ctrl);
 
+	/* this is a no-op when called from the controller reset handler */
+	nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO);
+
 	down_write(&ctrl->namespaces_rwsem);
 	list_splice_init(&ctrl->namespaces, &ns_list);
 	up_write(&ctrl->namespaces_rwsem);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 2a6c8190eeb7..4ec4829d6233 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -547,7 +547,7 @@ static struct nvmf_transport_ops *nvmf_lookup_transport(
 blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
 		struct request *rq)
 {
-	if (ctrl->state != NVME_CTRL_DELETING &&
+	if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
 	    ctrl->state != NVME_CTRL_DEAD &&
 	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
 		return BLK_STS_RESOURCE;
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index a0ec40ab62ee..a9c1e3b4585e 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -182,7 +182,8 @@ bool nvmf_ip_options_match(struct nvme_ctrl *ctrl,
 static inline bool nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		bool queue_live)
 {
-	if (likely(ctrl->state == NVME_CTRL_LIVE))
+	if (likely(ctrl->state == NVME_CTRL_LIVE ||
+		   ctrl->state == NVME_CTRL_DELETING))
 		return true;
 	return __nvmf_check_ready(ctrl, rq, queue_live);
 }
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index e999a8c4b7e8..549f5b0fb0b4 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -825,6 +825,7 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
 		break;
 
 	case NVME_CTRL_DELETING:
+	case NVME_CTRL_DELETING_NOIO:
 	default:
 		/* no action to take - let it delete */
 		break;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 66509472fe06..267295323343 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -167,9 +167,18 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 
 static bool nvme_path_is_disabled(struct nvme_ns *ns)
 {
-	return ns->ctrl->state != NVME_CTRL_LIVE ||
-		test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
-		test_bit(NVME_NS_REMOVING, &ns->flags);
+	/*
+	 * We don't treat NVME_CTRL_DELETING as a disabled path as I/O should
+	 * still be able to complete assuming that the controller is connected.
+	 * Otherwise it will fail immediately and return to the requeue list.
+	 */
+	if (ns->ctrl->state != NVME_CTRL_LIVE &&
+	    ns->ctrl->state != NVME_CTRL_DELETING)
+		return true;
+	if (test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
+	    test_bit(NVME_NS_REMOVING, &ns->flags))
+		return true;
+	return false;
 }
 
 static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)
@@ -246,6 +255,12 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 			fallback = ns;
 	}
 
+	/* No optimized path found, re-check the current path */
+	if (!nvme_path_is_disabled(old) &&
+	    old->ana_state == NVME_ANA_OPTIMIZED) {
+		found = old;
+		goto out;
+	}
 	if (!fallback)
 		return NULL;
 	found = fallback;
@@ -266,10 +281,13 @@ 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;
 }
 
@@ -565,6 +583,9 @@ static void nvme_ana_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
 
+	if (ctrl->state != NVME_CTRL_LIVE)
+		return;
+
 	nvme_read_ana_log(ctrl);
 }
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 09ffc3246f60..e268f1d7e1a0 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -186,6 +186,7 @@ enum nvme_ctrl_state {
 	NVME_CTRL_RESETTING,
 	NVME_CTRL_CONNECTING,
 	NVME_CTRL_DELETING,
+	NVME_CTRL_DELETING_NOIO,
 	NVME_CTRL_DEAD,
 };
 
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 13506a87a444..876859cd14e8 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -941,15 +941,20 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 			ret = PTR_ERR(ctrl->ctrl.connect_q);
 			goto out_free_tag_set;
 		}
-	} else {
-		blk_mq_update_nr_hw_queues(&ctrl->tag_set,
-			ctrl->ctrl.queue_count - 1);
 	}
 
 	ret = nvme_rdma_start_io_queues(ctrl);
 	if (ret)
 		goto out_cleanup_connect_q;
 
+	if (!new) {
+		nvme_start_queues(&ctrl->ctrl);
+		nvme_wait_freeze(&ctrl->ctrl);
+		blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
+			ctrl->ctrl.queue_count - 1);
+		nvme_unfreeze(&ctrl->ctrl);
+	}
+
 	return 0;
 
 out_cleanup_connect_q:
@@ -982,6 +987,7 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
 	if (ctrl->ctrl.queue_count > 1) {
+		nvme_start_freeze(&ctrl->ctrl);
 		nvme_stop_queues(&ctrl->ctrl);
 		nvme_rdma_stop_io_queues(ctrl);
 		if (ctrl->ctrl.tagset) {
@@ -1076,11 +1082,12 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
 	if (!changed) {
 		/*
-		 * state change failure is ok if we're in DELETING state,
+		 * state change failure is ok if we started ctrl delete,
 		 * unless we're during creation of a new controller to
 		 * avoid races with teardown flow.
 		 */
-		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
+		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING &&
+			     ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO);
 		WARN_ON_ONCE(new);
 		ret = -EINVAL;
 		goto destroy_io;
@@ -1133,8 +1140,9 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
-		/* state change failure is ok if we're in DELETING state */
-		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
+		/* state change failure is ok if we started ctrl delete */
+		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING &&
+			     ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO);
 		return;
 	}
 
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index f3a91818167b..a6d2e3330a58 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1744,15 +1744,20 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 			ret = PTR_ERR(ctrl->connect_q);
 			goto out_free_tag_set;
 		}
-	} else {
-		blk_mq_update_nr_hw_queues(ctrl->tagset,
-			ctrl->queue_count - 1);
 	}
 
 	ret = nvme_tcp_start_io_queues(ctrl);
 	if (ret)
 		goto out_cleanup_connect_q;
 
+	if (!new) {
+		nvme_start_queues(ctrl);
+		nvme_wait_freeze(ctrl);
+		blk_mq_update_nr_hw_queues(ctrl->tagset,
+			ctrl->queue_count - 1);
+		nvme_unfreeze(ctrl);
+	}
+
 	return 0;
 
 out_cleanup_connect_q:
@@ -1857,6 +1862,7 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 {
 	if (ctrl->queue_count <= 1)
 		return;
+	nvme_start_freeze(ctrl);
 	nvme_stop_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);
 	if (ctrl->tagset) {
@@ -1923,11 +1929,12 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new)
 
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) {
 		/*
-		 * state change failure is ok if we're in DELETING state,
+		 * state change failure is ok if we started ctrl delete,
 		 * unless we're during creation of a new controller to
 		 * avoid races with teardown flow.
 		 */
-		WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING);
+		WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
+			     ctrl->state != NVME_CTRL_DELETING_NOIO);
 		WARN_ON_ONCE(new);
 		ret = -EINVAL;
 		goto destroy_io;
@@ -1983,8 +1990,9 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
 	blk_mq_unquiesce_queue(ctrl->admin_q);
 
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) {
-		/* state change failure is ok if we're in DELETING state */
-		WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING);
+		/* state change failure is ok if we started ctrl delete */
+		WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
+			     ctrl->state != NVME_CTRL_DELETING_NOIO);
 		return;
 	}
 
@@ -2019,8 +2027,9 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
 	nvme_tcp_teardown_ctrl(ctrl, false);
 
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) {
-		/* state change failure is ok if we're in DELETING state */
-		WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING);
+		/* state change failure is ok if we started ctrl delete */
+		WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
+			     ctrl->state != NVME_CTRL_DELETING_NOIO);
 		return;
 	}