Merge tag 'for-linus-20190125' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A collection of fixes for this release. This contains:

   - Silence sparse rightfully complaining about non-static wbt
     functions (Bart)

   - Fixes for the zoned comments/ioctl documentation (Damien)

   - direct-io fix that's been lingering for a while (Ernesto)

   - cgroup writeback fix (Tejun)

   - Set of NVMe patches for nvme-rdma/tcp (Sagi, Hannes, Raju)

   - Block recursion tracking fix (Ming)

   - Fix debugfs command flag naming for a few flags (Jianchao)"

* tag 'for-linus-20190125' of git://git.kernel.dk/linux-block:
  block: Fix comment typo
  uapi: fix ioctl documentation
  blk-wbt: Declare local functions static
  blk-mq: fix the cmd_flag_name array
  nvme-multipath: drop optimization for static ANA group IDs
  nvmet-rdma: fix null dereference under heavy load
  nvme-rdma: rework queue maps handling
  nvme-tcp: fix timeout handler
  nvme-rdma: fix timeout handler
  writeback: synchronize sync(2) against cgroup writeback membership switches
  block: cover another queue enter recursion via BIO_QUEUE_ENTERED
  direct-io: allow direct writes to empty inodes

4 files changed, 69 insertions, 32 deletions

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index df4b3a6db51b..b9fff3b8ed1b 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -545,8 +545,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0);
 	ctrl->ana_log_size = sizeof(struct nvme_ana_rsp_hdr) +
 		ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc);
-	if (!(ctrl->anacap & (1 << 6)))
-		ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32);
+	ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32);
 
 	if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) {
 		dev_err(ctrl->device,
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 0a2fd2949ad7..52abc3a6de12 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -119,6 +119,7 @@ struct nvme_rdma_ctrl {
 
 	struct nvme_ctrl	ctrl;
 	bool			use_inline_data;
+	u32			io_queues[HCTX_MAX_TYPES];
 };
 
 static inline struct nvme_rdma_ctrl *to_rdma_ctrl(struct nvme_ctrl *ctrl)
@@ -165,8 +166,8 @@ static inline int nvme_rdma_queue_idx(struct nvme_rdma_queue *queue)
 static bool nvme_rdma_poll_queue(struct nvme_rdma_queue *queue)
 {
 	return nvme_rdma_queue_idx(queue) >
-		queue->ctrl->ctrl.opts->nr_io_queues +
-		queue->ctrl->ctrl.opts->nr_write_queues;
+		queue->ctrl->io_queues[HCTX_TYPE_DEFAULT] +
+		queue->ctrl->io_queues[HCTX_TYPE_READ];
 }
 
 static inline size_t nvme_rdma_inline_data_size(struct nvme_rdma_queue *queue)
@@ -661,8 +662,21 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl)
 	nr_io_queues = min_t(unsigned int, nr_io_queues,
 				ibdev->num_comp_vectors);
 
-	nr_io_queues += min(opts->nr_write_queues, num_online_cpus());
-	nr_io_queues += min(opts->nr_poll_queues, num_online_cpus());
+	if (opts->nr_write_queues) {
+		ctrl->io_queues[HCTX_TYPE_DEFAULT] =
+				min(opts->nr_write_queues, nr_io_queues);
+		nr_io_queues += ctrl->io_queues[HCTX_TYPE_DEFAULT];
+	} else {
+		ctrl->io_queues[HCTX_TYPE_DEFAULT] = nr_io_queues;
+	}
+
+	ctrl->io_queues[HCTX_TYPE_READ] = nr_io_queues;
+
+	if (opts->nr_poll_queues) {
+		ctrl->io_queues[HCTX_TYPE_POLL] =
+			min(opts->nr_poll_queues, num_online_cpus());
+		nr_io_queues += ctrl->io_queues[HCTX_TYPE_POLL];
+	}
 
 	ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
 	if (ret)
@@ -1689,18 +1703,28 @@ static enum blk_eh_timer_return
 nvme_rdma_timeout(struct request *rq, bool reserved)
 {
 	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;
 
-	dev_warn(req->queue->ctrl->ctrl.device,
-		 "I/O %d QID %d timeout, reset controller\n",
-		 rq->tag, nvme_rdma_queue_idx(req->queue));
+	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
+		 rq->tag, nvme_rdma_queue_idx(queue));
 
-	/* queue error recovery */
-	nvme_rdma_error_recovery(req->queue->ctrl);
+	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
+		/*
+		 * Teardown immediately if controller times out while starting
+		 * or we are already started error recovery. all outstanding
+		 * requests are completed on shutdown, so we return BLK_EH_DONE.
+		 */
+		flush_work(&ctrl->err_work);
+		nvme_rdma_teardown_io_queues(ctrl, false);
+		nvme_rdma_teardown_admin_queue(ctrl, false);
+		return BLK_EH_DONE;
+	}
 
-	/* fail with DNR on cmd timeout */
-	nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
+	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
+	nvme_rdma_error_recovery(ctrl);
 
-	return BLK_EH_DONE;
+	return BLK_EH_RESET_TIMER;
 }
 
 static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
@@ -1779,17 +1803,15 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set)
 	struct nvme_rdma_ctrl *ctrl = set->driver_data;
 
 	set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
-	set->map[HCTX_TYPE_READ].nr_queues = ctrl->ctrl.opts->nr_io_queues;
+	set->map[HCTX_TYPE_DEFAULT].nr_queues =
+			ctrl->io_queues[HCTX_TYPE_DEFAULT];
+	set->map[HCTX_TYPE_READ].nr_queues = ctrl->io_queues[HCTX_TYPE_READ];
 	if (ctrl->ctrl.opts->nr_write_queues) {
 		/* separate read/write queues */
-		set->map[HCTX_TYPE_DEFAULT].nr_queues =
-				ctrl->ctrl.opts->nr_write_queues;
 		set->map[HCTX_TYPE_READ].queue_offset =
-				ctrl->ctrl.opts->nr_write_queues;
+				ctrl->io_queues[HCTX_TYPE_DEFAULT];
 	} else {
 		/* mixed read/write queues */
-		set->map[HCTX_TYPE_DEFAULT].nr_queues =
-				ctrl->ctrl.opts->nr_io_queues;
 		set->map[HCTX_TYPE_READ].queue_offset = 0;
 	}
 	blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_DEFAULT],
@@ -1799,12 +1821,12 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set)
 
 	if (ctrl->ctrl.opts->nr_poll_queues) {
 		set->map[HCTX_TYPE_POLL].nr_queues =
-				ctrl->ctrl.opts->nr_poll_queues;
+				ctrl->io_queues[HCTX_TYPE_POLL];
 		set->map[HCTX_TYPE_POLL].queue_offset =
-				ctrl->ctrl.opts->nr_io_queues;
+				ctrl->io_queues[HCTX_TYPE_DEFAULT];
 		if (ctrl->ctrl.opts->nr_write_queues)
 			set->map[HCTX_TYPE_POLL].queue_offset +=
-				ctrl->ctrl.opts->nr_write_queues;
+				ctrl->io_queues[HCTX_TYPE_READ];
 		blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]);
 	}
 	return 0;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 265a0543b381..5f0a00425242 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1948,20 +1948,23 @@ nvme_tcp_timeout(struct request *rq, bool reserved)
 	struct nvme_tcp_ctrl *ctrl = req->queue->ctrl;
 	struct nvme_tcp_cmd_pdu *pdu = req->pdu;
 
-	dev_dbg(ctrl->ctrl.device,
+	dev_warn(ctrl->ctrl.device,
 		"queue %d: timeout request %#x type %d\n",
-		nvme_tcp_queue_id(req->queue), rq->tag,
-		pdu->hdr.type);
+		nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type);
 
 	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
-		union nvme_result res = {};
-
-		nvme_req(rq)->flags |= NVME_REQ_CANCELLED;
-		nvme_end_request(rq, cpu_to_le16(NVME_SC_ABORT_REQ), res);
+		/*
+		 * Teardown immediately if controller times out while starting
+		 * or we are already started error recovery. all outstanding
+		 * requests are completed on shutdown, so we return BLK_EH_DONE.
+		 */
+		flush_work(&ctrl->err_work);
+		nvme_tcp_teardown_io_queues(&ctrl->ctrl, false);
+		nvme_tcp_teardown_admin_queue(&ctrl->ctrl, false);
 		return BLK_EH_DONE;
 	}
 
-	/* queue error recovery */
+	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
 	nvme_tcp_error_recovery(&ctrl->ctrl);
 
 	return BLK_EH_RESET_TIMER;
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index a8d23eb80192..a884e3a0e8af 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -139,6 +139,10 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc);
 static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc);
 static void nvmet_rdma_qp_event(struct ib_event *event, void *priv);
 static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue);
+static void nvmet_rdma_free_rsp(struct nvmet_rdma_device *ndev,
+				struct nvmet_rdma_rsp *r);
+static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev,
+				struct nvmet_rdma_rsp *r);
 
 static const struct nvmet_fabrics_ops nvmet_rdma_ops;
 
@@ -182,9 +186,17 @@ nvmet_rdma_get_rsp(struct nvmet_rdma_queue *queue)
 	spin_unlock_irqrestore(&queue->rsps_lock, flags);
 
 	if (unlikely(!rsp)) {
-		rsp = kmalloc(sizeof(*rsp), GFP_KERNEL);
+		int ret;
+
+		rsp = kzalloc(sizeof(*rsp), GFP_KERNEL);
 		if (unlikely(!rsp))
 			return NULL;
+		ret = nvmet_rdma_alloc_rsp(queue->dev, rsp);
+		if (unlikely(ret)) {
+			kfree(rsp);
+			return NULL;
+		}
+
 		rsp->allocated = true;
 	}
 
@@ -197,6 +209,7 @@ nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp)
 	unsigned long flags;
 
 	if (unlikely(rsp->allocated)) {
+		nvmet_rdma_free_rsp(rsp->queue->dev, rsp);
 		kfree(rsp);
 		return;
 	}