Merge tag 'io_uring-5.9-2020-08-23' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request from Sagi:
       - nvme completion rework from Christoph and Chao that mostly came
         from a bit of divergence of how we classify errors related to
         pathing/retry etc.
       - nvmet passthru fixes from Chaitanya
       - minor nvmet fixes from Amit and I
       - mpath round-robin path selection fix from Martin
       - ignore noiob for zoned devices from Keith
       - minor nvme-fc fix from Tianjia"

 - BFQ cgroup leak fix (Dmitry)

 - block layer MAINTAINERS addition (Geert)

 - fix null_blk FUA checking (Hou)

 - get_max_io_size() size fix (Keith)

 - fix block page_is_mergeable() for compound pages (Matthew)

 - discard granularity fixes (Ming)

 - IO scheduler ordering fix (Ming)

 - misc fixes

* tag 'io_uring-5.9-2020-08-23' of git://git.kernel.dk/linux-block: (31 commits)
  null_blk: fix passing of REQ_FUA flag in null_handle_rq
  nvmet: Disable keep-alive timer when kato is cleared to 0h
  nvme: redirect commands on dying queue
  nvme: just check the status code type in nvme_is_path_error
  nvme: refactor command completion
  nvme: rename and document nvme_end_request
  nvme: skip noiob for zoned devices
  nvme-pci: fix PRP pool size
  nvme-pci: Use u32 for nvme_dev.q_depth and nvme_queue.q_depth
  nvme: Use spin_lock_irq() when taking the ctrl->lock
  nvmet: call blk_mq_free_request() directly
  nvmet: fix oops in pt cmd execution
  nvmet: add ns tear down label for pt-cmd handling
  nvme: multipath: round-robin: eliminate "fallback" variable
  nvme: multipath: round-robin: fix single non-optimized path case
  nvme-fc: Fix wrong return value in __nvme_fc_init_request()
  nvmet-passthru: Reject commands with non-sgl flags set
  nvmet: fix a memory leak
  blkcg: fix memleak for iolatency
  MAINTAINERS: Add missing header files to BLOCK LAYER section
  ...

7 files changed, 122 insertions, 93 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 96ee5a476c4d..154942fc64eb 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -241,17 +241,6 @@ static blk_status_t nvme_error_status(u16 status)
 	}
 }
 
-static inline bool nvme_req_needs_retry(struct request *req)
-{
-	if (blk_noretry_request(req))
-		return false;
-	if (nvme_req(req)->status & NVME_SC_DNR)
-		return false;
-	if (nvme_req(req)->retries >= nvme_max_retries)
-		return false;
-	return true;
-}
-
 static void nvme_retry_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
@@ -268,34 +257,67 @@ static void nvme_retry_req(struct request *req)
 	blk_mq_delay_kick_requeue_list(req->q, delay);
 }
 
-void nvme_complete_rq(struct request *req)
+enum nvme_disposition {
+	COMPLETE,
+	RETRY,
+	FAILOVER,
+};
+
+static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
 {
-	blk_status_t status = nvme_error_status(nvme_req(req)->status);
+	if (likely(nvme_req(req)->status == 0))
+		return COMPLETE;
 
-	trace_nvme_complete_rq(req);
+	if (blk_noretry_request(req) ||
+	    (nvme_req(req)->status & NVME_SC_DNR) ||
+	    nvme_req(req)->retries >= nvme_max_retries)
+		return COMPLETE;
 
-	nvme_cleanup_cmd(req);
+	if (req->cmd_flags & REQ_NVME_MPATH) {
+		if (nvme_is_path_error(nvme_req(req)->status) ||
+		    blk_queue_dying(req->q))
+			return FAILOVER;
+	} else {
+		if (blk_queue_dying(req->q))
+			return COMPLETE;
+	}
 
-	if (nvme_req(req)->ctrl->kas)
-		nvme_req(req)->ctrl->comp_seen = true;
+	return RETRY;
+}
 
-	if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
-		if ((req->cmd_flags & REQ_NVME_MPATH) && nvme_failover_req(req))
-			return;
+static inline void nvme_end_req(struct request *req)
+{
+	blk_status_t status = nvme_error_status(nvme_req(req)->status);
 
-		if (!blk_queue_dying(req->q)) {
-			nvme_retry_req(req);
-			return;
-		}
-	} else if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
-		   req_op(req) == REQ_OP_ZONE_APPEND) {
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+	    req_op(req) == REQ_OP_ZONE_APPEND)
 		req->__sector = nvme_lba_to_sect(req->q->queuedata,
 			le64_to_cpu(nvme_req(req)->result.u64));
-	}
 
 	nvme_trace_bio_complete(req, status);
 	blk_mq_end_request(req, status);
 }
+
+void nvme_complete_rq(struct request *req)
+{
+	trace_nvme_complete_rq(req);
+	nvme_cleanup_cmd(req);
+
+	if (nvme_req(req)->ctrl->kas)
+		nvme_req(req)->ctrl->comp_seen = true;
+
+	switch (nvme_decide_disposition(req)) {
+	case COMPLETE:
+		nvme_end_req(req);
+		return;
+	case RETRY:
+		nvme_retry_req(req);
+		return;
+	case FAILOVER:
+		nvme_failover_req(req);
+		return;
+	}
+}
 EXPORT_SYMBOL_GPL(nvme_complete_rq);
 
 bool nvme_cancel_request(struct request *req, void *data, bool reserved)
@@ -2075,7 +2097,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		}
 	}
 
-	if (iob)
+	if (iob && !blk_queue_is_zoned(ns->queue))
 		blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(iob));
 	nvme_update_disk_info(disk, ns, id);
 #ifdef CONFIG_NVME_MULTIPATH
@@ -2965,14 +2987,14 @@ static struct nvme_cel *nvme_find_cel(struct nvme_ctrl *ctrl, u8 csi)
 {
 	struct nvme_cel *cel, *ret = NULL;
 
-	spin_lock(&ctrl->lock);
+	spin_lock_irq(&ctrl->lock);
 	list_for_each_entry(cel, &ctrl->cels, entry) {
 		if (cel->csi == csi) {
 			ret = cel;
 			break;
 		}
 	}
-	spin_unlock(&ctrl->lock);
+	spin_unlock_irq(&ctrl->lock);
 
 	return ret;
 }
@@ -2999,9 +3021,9 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
 
 	cel->csi = csi;
 
-	spin_lock(&ctrl->lock);
+	spin_lock_irq(&ctrl->lock);
 	list_add_tail(&cel->entry, &ctrl->cels);
-	spin_unlock(&ctrl->lock);
+	spin_unlock_irq(&ctrl->lock);
 out:
 	*log = &cel->log;
 	return 0;
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index eae43bb444e0..a7f474ddfff7 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2035,7 +2035,7 @@ done:
 	}
 
 	__nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
-	if (!nvme_end_request(rq, status, result))
+	if (!nvme_try_complete_req(rq, status, result))
 		nvme_fc_complete_rq(rq);
 
 check_error:
@@ -2078,7 +2078,7 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl,
 	if (fc_dma_mapping_error(ctrl->lport->dev, op->fcp_req.cmddma)) {
 		dev_err(ctrl->dev,
 			"FCP Op failed - cmdiu dma mapping failed.\n");
-		ret = EFAULT;
+		ret = -EFAULT;
 		goto out_on_error;
 	}
 
@@ -2088,7 +2088,7 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl,
 	if (fc_dma_mapping_error(ctrl->lport->dev, op->fcp_req.rspdma)) {
 		dev_err(ctrl->dev,
 			"FCP Op failed - rspiu dma mapping failed.\n");
-		ret = EFAULT;
+		ret = -EFAULT;
 	}
 
 	atomic_set(&op->state, FCPOP_STATE_IDLE);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 3ded54d2c9c6..d4ba736c6c89 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -65,51 +65,30 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 	}
 }
 
-bool nvme_failover_req(struct request *req)
+void nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
-	u16 status = nvme_req(req)->status;
+	u16 status = nvme_req(req)->status & 0x7ff;
 	unsigned long flags;
 
-	switch (status & 0x7ff) {
-	case NVME_SC_ANA_TRANSITION:
-	case NVME_SC_ANA_INACCESSIBLE:
-	case NVME_SC_ANA_PERSISTENT_LOSS:
-		/*
-		 * If we got back an ANA error we know the controller is alive,
-		 * but not ready to serve this namespaces.  The spec suggests
-		 * we should update our general state here, but due to the fact
-		 * that the admin and I/O queues are not serialized that is
-		 * fundamentally racy.  So instead just clear the current path,
-		 * mark the the path as pending and kick of a re-read of the ANA
-		 * log page ASAP.
-		 */
-		nvme_mpath_clear_current_path(ns);
-		if (ns->ctrl->ana_log_buf) {
-			set_bit(NVME_NS_ANA_PENDING, &ns->flags);
-			queue_work(nvme_wq, &ns->ctrl->ana_work);
-		}
-		break;
-	case NVME_SC_HOST_PATH_ERROR:
-	case NVME_SC_HOST_ABORTED_CMD:
-		/*
-		 * Temporary transport disruption in talking to the controller.
-		 * Try to send on a new path.
-		 */
-		nvme_mpath_clear_current_path(ns);
-		break;
-	default:
-		/* This was a non-ANA error so follow the normal error path. */
-		return false;
+	nvme_mpath_clear_current_path(ns);
+
+	/*
+	 * If we got back an ANA error, we know the controller is alive but not
+	 * ready to serve this namespace.  Kick of a re-read of the ANA
+	 * information page, and just try any other available path for now.
+	 */
+	if (nvme_is_ana_error(status) && ns->ctrl->ana_log_buf) {
+		set_bit(NVME_NS_ANA_PENDING, &ns->flags);
+		queue_work(nvme_wq, &ns->ctrl->ana_work);
 	}
 
 	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);
 
+	blk_mq_end_request(req, 0);
 	kblockd_schedule_work(&ns->head->requeue_work);
-	return true;
 }
 
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
@@ -233,7 +212,7 @@ static struct nvme_ns *nvme_next_ns(struct nvme_ns_head *head,
 static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 		int node, struct nvme_ns *old)
 {
-	struct nvme_ns *ns, *found, *fallback = NULL;
+	struct nvme_ns *ns, *found = NULL;
 
 	if (list_is_singular(&head->list)) {
 		if (nvme_path_is_disabled(old))
@@ -252,18 +231,22 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 			goto out;
 		}
 		if (ns->ana_state == NVME_ANA_NONOPTIMIZED)
-			fallback = ns;
+			found = ns;
 	}
 
-	/* No optimized path found, re-check the current path */
+	/*
+	 * 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) {
-		found = old;
-		goto out;
-	}
-	if (!fallback)
+	    (old->ana_state == NVME_ANA_OPTIMIZED ||
+	     (!found && old->ana_state == NVME_ANA_NONOPTIMIZED)))
+		return old;
+
+	if (!found)
 		return NULL;
-	found = fallback;
 out:
 	rcu_assign_pointer(head->current_path[node], found);
 	return found;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index ebb8c3ed3885..e9cf29449dd1 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -523,7 +523,31 @@ static inline u32 nvme_bytes_to_numd(size_t len)
 	return (len >> 2) - 1;
 }
 
-static inline bool nvme_end_request(struct request *req, __le16 status,
+static inline bool nvme_is_ana_error(u16 status)
+{
+	switch (status & 0x7ff) {
+	case NVME_SC_ANA_TRANSITION:
+	case NVME_SC_ANA_INACCESSIBLE:
+	case NVME_SC_ANA_PERSISTENT_LOSS:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline bool nvme_is_path_error(u16 status)
+{
+	/* check for a status code type of 'path related status' */
+	return (status & 0x700) == 0x300;
+}
+
+/*
+ * Fill in the status and result information from the CQE, and then figure out
+ * if blk-mq will need to use IPI magic to complete the request, and if yes do
+ * so.  If not let the caller complete the request without an indirect function
+ * call.
+ */
+static inline bool nvme_try_complete_req(struct request *req, __le16 status,
 		union nvme_result result)
 {
 	struct nvme_request *rq = nvme_req(req);
@@ -629,7 +653,7 @@ void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys);
 void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
 void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 			struct nvme_ctrl *ctrl, int *flags);
-bool nvme_failover_req(struct request *req);
+void nvme_failover_req(struct request *req);
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
 void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
@@ -688,9 +712,8 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 	sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
 }
 
-static inline bool nvme_failover_req(struct request *req)
+static inline void nvme_failover_req(struct request *req)
 {
-	return false;
 }
 static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 {
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 24d174a0623b..9aa948782704 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -120,7 +120,7 @@ struct nvme_dev {
 	unsigned max_qid;
 	unsigned io_queues[HCTX_MAX_TYPES];
 	unsigned int num_vecs;
-	u16 q_depth;
+	u32 q_depth;
 	int io_sqes;
 	u32 db_stride;
 	void __iomem *bar;
@@ -157,13 +157,13 @@ struct nvme_dev {
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp)
 {
 	int ret;
-	u16 n;
+	u32 n;
 
-	ret = kstrtou16(val, 10, &n);
+	ret = kstrtou32(val, 10, &n);
 	if (ret != 0 || n < 2)
 		return -EINVAL;
 
-	return param_set_ushort(val, kp);
+	return param_set_uint(val, kp);
 }
 
 static inline unsigned int sq_idx(unsigned int qid, u32 stride)
@@ -195,7 +195,7 @@ struct nvme_queue {
 	dma_addr_t sq_dma_addr;
 	dma_addr_t cq_dma_addr;
 	u32 __iomem *q_db;
-	u16 q_depth;
+	u32 q_depth;
 	u16 cq_vector;
 	u16 sq_tail;
 	u16 cq_head;
@@ -961,7 +961,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 
 	req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id);
 	trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
-	if (!nvme_end_request(req, cqe->status, cqe->result))
+	if (!nvme_try_complete_req(req, cqe->status, cqe->result))
 		nvme_pci_complete_rq(req);
 }
 
@@ -2320,7 +2320,7 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 
 	dev->ctrl.cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
 
-	dev->q_depth = min_t(u16, NVME_CAP_MQES(dev->ctrl.cap) + 1,
+	dev->q_depth = min_t(u32, NVME_CAP_MQES(dev->ctrl.cap) + 1,
 				io_queue_depth);
 	dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
 	dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap);
@@ -2460,7 +2460,8 @@ static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown)
 static int nvme_setup_prp_pools(struct nvme_dev *dev)
 {
 	dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
-						PAGE_SIZE, PAGE_SIZE, 0);
+						NVME_CTRL_PAGE_SIZE,
+						NVME_CTRL_PAGE_SIZE, 0);
 	if (!dev->prp_page_pool)
 		return -ENOMEM;
 
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 610e0b6bb6e4..eb1d54af7c77 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1189,7 +1189,7 @@ static void nvme_rdma_end_request(struct nvme_rdma_request *req)
 
 	if (!refcount_dec_and_test(&req->ref))
 		return;
-	if (!nvme_end_request(rq, req->status, req->result))
+	if (!nvme_try_complete_req(rq, req->status, req->result))
 		nvme_rdma_complete_rq(rq);
 }
 
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index f0c4bb47d22d..a44d8ace3a81 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -481,7 +481,7 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
 		return -EINVAL;
 	}
 
-	if (!nvme_end_request(rq, cqe->status, cqe->result))
+	if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
 		nvme_complete_rq(rq);
 	queue->nr_cqe++;
 
@@ -672,7 +672,7 @@ static inline void nvme_tcp_end_request(struct request *rq, u16 status)
 {
 	union nvme_result res = {};
 
-	if (!nvme_end_request(rq, cpu_to_le16(status << 1), res))
+	if (!nvme_try_complete_req(rq, cpu_to_le16(status << 1), res))
 		nvme_complete_rq(rq);
 }