Merge tag 'nvme-5.10-2020-11-05' of git://git.infradead.org/nvme into block-5.10

Pull NVMe fixes from Christoph:

"nvme fixes for 5.10:

 - revert a nvme_queue size optimization (Keith Bush)
 - fabrics timeout races fixes (Chao Leng and Sagi Grimberg)"

* tag 'nvme-5.10-2020-11-05' of git://git.infradead.org/nvme:
  nvme-tcp: avoid repeated request completion
  nvme-rdma: avoid repeated request completion
  nvme-tcp: avoid race between time out and tear down
  nvme-rdma: avoid race between time out and tear down
  nvme: introduce nvme_sync_io_queues
  Revert "nvme-pci: remove last_sq_tail"

5 files changed, 33 insertions, 29 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 376096bfc54a..40ca71b29bb9 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4582,8 +4582,7 @@ void nvme_start_queues(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_start_queues);
 
-
-void nvme_sync_queues(struct nvme_ctrl *ctrl)
+void nvme_sync_io_queues(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
@@ -4591,7 +4590,12 @@ void nvme_sync_queues(struct nvme_ctrl *ctrl)
 	list_for_each_entry(ns, &ctrl->namespaces, list)
 		blk_sync_queue(ns->queue);
 	up_read(&ctrl->namespaces_rwsem);
+}
+EXPORT_SYMBOL_GPL(nvme_sync_io_queues);
 
+void nvme_sync_queues(struct nvme_ctrl *ctrl)
+{
+	nvme_sync_io_queues(ctrl);
 	if (ctrl->admin_q)
 		blk_sync_queue(ctrl->admin_q);
 }
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index cc111136a981..bc330bf0d3bd 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -602,6 +602,7 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl);
 void nvme_start_queues(struct nvme_ctrl *ctrl);
 void nvme_kill_queues(struct nvme_ctrl *ctrl);
 void nvme_sync_queues(struct nvme_ctrl *ctrl);
+void nvme_sync_io_queues(struct nvme_ctrl *ctrl);
 void nvme_unfreeze(struct nvme_ctrl *ctrl);
 void nvme_wait_freeze(struct nvme_ctrl *ctrl);
 int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index df8f3612107f..0578ff253c47 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -198,6 +198,7 @@ struct nvme_queue {
 	u32 q_depth;
 	u16 cq_vector;
 	u16 sq_tail;
+	u16 last_sq_tail;
 	u16 cq_head;
 	u16 qid;
 	u8 cq_phase;
@@ -455,11 +456,24 @@ static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
 	return 0;
 }
 
-static inline void nvme_write_sq_db(struct nvme_queue *nvmeq)
+/*
+ * Write sq tail if we are asked to, or if the next command would wrap.
+ */
+static inline void nvme_write_sq_db(struct nvme_queue *nvmeq, bool write_sq)
 {
+	if (!write_sq) {
+		u16 next_tail = nvmeq->sq_tail + 1;
+
+		if (next_tail == nvmeq->q_depth)
+			next_tail = 0;
+		if (next_tail != nvmeq->last_sq_tail)
+			return;
+	}
+
 	if (nvme_dbbuf_update_and_check_event(nvmeq->sq_tail,
 			nvmeq->dbbuf_sq_db, nvmeq->dbbuf_sq_ei))
 		writel(nvmeq->sq_tail, nvmeq->q_db);
+	nvmeq->last_sq_tail = nvmeq->sq_tail;
 }
 
 /**
@@ -476,8 +490,7 @@ static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd,
 	       cmd, sizeof(*cmd));
 	if (++nvmeq->sq_tail == nvmeq->q_depth)
 		nvmeq->sq_tail = 0;
-	if (write_sq)
-		nvme_write_sq_db(nvmeq);
+	nvme_write_sq_db(nvmeq, write_sq);
 	spin_unlock(&nvmeq->sq_lock);
 }
 
@@ -486,7 +499,8 @@ static void nvme_commit_rqs(struct blk_mq_hw_ctx *hctx)
 	struct nvme_queue *nvmeq = hctx->driver_data;
 
 	spin_lock(&nvmeq->sq_lock);
-	nvme_write_sq_db(nvmeq);
+	if (nvmeq->sq_tail != nvmeq->last_sq_tail)
+		nvme_write_sq_db(nvmeq, true);
 	spin_unlock(&nvmeq->sq_lock);
 }
 
@@ -1496,6 +1510,7 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
 	struct nvme_dev *dev = nvmeq->dev;
 
 	nvmeq->sq_tail = 0;
+	nvmeq->last_sq_tail = 0;
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 541b0cba6d80..65e3d0ef36e1 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -122,7 +122,6 @@ struct nvme_rdma_ctrl {
 	struct sockaddr_storage src_addr;
 
 	struct nvme_ctrl	ctrl;
-	struct mutex		teardown_lock;
 	bool			use_inline_data;
 	u32			io_queues[HCTX_MAX_TYPES];
 };
@@ -1010,8 +1009,8 @@ out_free_io_queues:
 static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&ctrl->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	blk_sync_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	if (ctrl->ctrl.admin_tagset) {
 		blk_mq_tagset_busy_iter(ctrl->ctrl.admin_tagset,
@@ -1021,16 +1020,15 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_destroy_admin_queue(ctrl, remove);
-	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&ctrl->teardown_lock);
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_start_freeze(&ctrl->ctrl);
 		nvme_stop_queues(&ctrl->ctrl);
+		nvme_sync_io_queues(&ctrl->ctrl);
 		nvme_rdma_stop_io_queues(ctrl);
 		if (ctrl->ctrl.tagset) {
 			blk_mq_tagset_busy_iter(ctrl->ctrl.tagset,
@@ -1041,7 +1039,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 			nvme_start_queues(&ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, remove);
 	}
-	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
@@ -1976,16 +1973,12 @@ static void nvme_rdma_complete_timed_out(struct request *rq)
 {
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_rdma_queue *queue = req->queue;
-	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
 
-	/* fence other contexts that may complete the command */
-	mutex_lock(&ctrl->teardown_lock);
 	nvme_rdma_stop_queue(queue);
-	if (!blk_mq_request_completed(rq)) {
+	if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) {
 		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
 		blk_mq_complete_request(rq);
 	}
-	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static enum blk_eh_timer_return
@@ -2320,7 +2313,6 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 		return ERR_PTR(-ENOMEM);
 	ctrl->ctrl.opts = opts;
 	INIT_LIST_HEAD(&ctrl->list);
-	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index d6a3e1487354..c0c33320fe65 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -124,7 +124,6 @@ struct nvme_tcp_ctrl {
 	struct sockaddr_storage src_addr;
 	struct nvme_ctrl	ctrl;
 
-	struct mutex		teardown_lock;
 	struct work_struct	err_work;
 	struct delayed_work	connect_work;
 	struct nvme_tcp_request async_req;
@@ -1886,8 +1885,8 @@ out_free_queue:
 static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->admin_q);
+	blk_sync_queue(ctrl->admin_q);
 	nvme_tcp_stop_queue(ctrl, 0);
 	if (ctrl->admin_tagset) {
 		blk_mq_tagset_busy_iter(ctrl->admin_tagset,
@@ -1897,18 +1896,17 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 	nvme_tcp_destroy_admin_queue(ctrl, remove);
-	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	if (ctrl->queue_count <= 1)
-		goto out;
+		return;
 	blk_mq_quiesce_queue(ctrl->admin_q);
 	nvme_start_freeze(ctrl);
 	nvme_stop_queues(ctrl);
+	nvme_sync_io_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);
 	if (ctrl->tagset) {
 		blk_mq_tagset_busy_iter(ctrl->tagset,
@@ -1918,8 +1916,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 	if (remove)
 		nvme_start_queues(ctrl);
 	nvme_tcp_destroy_io_queues(ctrl, remove);
-out:
-	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
@@ -2171,14 +2167,11 @@ static void nvme_tcp_complete_timed_out(struct request *rq)
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
 
-	/* fence other contexts that may complete the command */
-	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
-	if (!blk_mq_request_completed(rq)) {
+	if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) {
 		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
 		blk_mq_complete_request(rq);
 	}
-	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static enum blk_eh_timer_return
@@ -2455,7 +2448,6 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 			nvme_tcp_reconnect_ctrl_work);
 	INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work);
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work);
-	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =