Merge tag 'v5.0-rc5' into rdma.git for-next

Linux 5.0-rc5

Needed to merge the include/uapi changes so we have an up to date
single-tree for these files. Patches already posted are also expected to
need this for dependencies.

4 files changed, 68 insertions, 39 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/pci.c b/drivers/nvme/host/pci.c
index deb1a66bf117..9bc585415d9b 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2041,14 +2041,18 @@ static int nvme_setup_host_mem(struct nvme_dev *dev)
 	return ret;
 }
 
+/* irq_queues covers admin queue */
 static void nvme_calc_io_queues(struct nvme_dev *dev, unsigned int irq_queues)
 {
 	unsigned int this_w_queues = write_queues;
 
+	WARN_ON(!irq_queues);
+
 	/*
-	 * Setup read/write queue split
+	 * Setup read/write queue split, assign admin queue one independent
+	 * irq vector if irq_queues is > 1.
 	 */
-	if (irq_queues == 1) {
+	if (irq_queues <= 2) {
 		dev->io_queues[HCTX_TYPE_DEFAULT] = 1;
 		dev->io_queues[HCTX_TYPE_READ] = 0;
 		return;
@@ -2056,21 +2060,21 @@ static void nvme_calc_io_queues(struct nvme_dev *dev, unsigned int irq_queues)
 
 	/*
 	 * If 'write_queues' is set, ensure it leaves room for at least
-	 * one read queue
+	 * one read queue and one admin queue
 	 */
 	if (this_w_queues >= irq_queues)
-		this_w_queues = irq_queues - 1;
+		this_w_queues = irq_queues - 2;
 
 	/*
 	 * If 'write_queues' is set to zero, reads and writes will share
 	 * a queue set.
 	 */
 	if (!this_w_queues) {
-		dev->io_queues[HCTX_TYPE_DEFAULT] = irq_queues;
+		dev->io_queues[HCTX_TYPE_DEFAULT] = irq_queues - 1;
 		dev->io_queues[HCTX_TYPE_READ] = 0;
 	} else {
 		dev->io_queues[HCTX_TYPE_DEFAULT] = this_w_queues;
-		dev->io_queues[HCTX_TYPE_READ] = irq_queues - this_w_queues;
+		dev->io_queues[HCTX_TYPE_READ] = irq_queues - this_w_queues - 1;
 	}
 }
 
@@ -2095,7 +2099,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		this_p_queues = nr_io_queues - 1;
 		irq_queues = 1;
 	} else {
-		irq_queues = nr_io_queues - this_p_queues;
+		irq_queues = nr_io_queues - this_p_queues + 1;
 	}
 	dev->io_queues[HCTX_TYPE_POLL] = this_p_queues;
 
@@ -2115,8 +2119,9 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		 * If we got a failure and we're down to asking for just
 		 * 1 + 1 queues, just ask for a single vector. We'll share
 		 * that between the single IO queue and the admin queue.
+		 * Otherwise, we assign one independent vector to admin queue.
 		 */
-		if (result >= 0 && irq_queues > 1)
+		if (irq_queues > 1)
 			irq_queues = irq_sets[0] + irq_sets[1] + 1;
 
 		result = pci_alloc_irq_vectors_affinity(pdev, irq_queues,
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;