Merge tag 'for-5.9/block-20200802' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
 "Good amount of cleanups and tech debt removals in here, and as a
  result, the diffstat shows a nice net reduction in code.

   - Softirq completion cleanups (Christoph)

   - Stop using ->queuedata (Christoph)

   - Cleanup bd claiming (Christoph)

   - Use check_events, moving away from the legacy media change
     (Christoph)

   - Use inode i_blkbits consistently (Christoph)

   - Remove old unused writeback congestion bits (Christoph)

   - Cleanup/unify submission path (Christoph)

   - Use bio_uninit consistently, instead of bio_disassociate_blkg
     (Christoph)

   - sbitmap cleared bits handling (John)

   - Request merging blktrace event addition (Jan)

   - sysfs add/remove race fixes (Luis)

   - blk-mq tag fixes/optimizations (Ming)

   - Duplicate words in comments (Randy)

   - Flush deferral cleanup (Yufen)

   - IO context locking/retry fixes (John)

   - struct_size() usage (Gustavo)

   - blk-iocost fixes (Chengming)

   - blk-cgroup IO stats fixes (Boris)

   - Various little fixes"

* tag 'for-5.9/block-20200802' of git://git.kernel.dk/linux-block: (135 commits)
  block: blk-timeout: delete duplicated word
  block: blk-mq-sched: delete duplicated word
  block: blk-mq: delete duplicated word
  block: genhd: delete duplicated words
  block: elevator: delete duplicated word and fix typos
  block: bio: delete duplicated words
  block: bfq-iosched: fix duplicated word
  iocost_monitor: start from the oldest usage index
  iocost: Fix check condition of iocg abs_vdebt
  block: Remove callback typedefs for blk_mq_ops
  block: Use non _rcu version of list functions for tag_set_list
  blk-cgroup: show global disk stats in root cgroup io.stat
  blk-cgroup: make iostat functions visible to stat printing
  block: improve discard bio alignment in __blkdev_issue_discard()
  block: change REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL to be odd numbers
  block: defer flush request no matter whether we have elevator
  block: make blk_timeout_init() static
  block: remove retry loop in ioc_release_fn()
  block: remove unnecessary ioc nested locking
  block: integrate bd_start_claiming into __blkdev_get
  ...

9 files changed, 45 insertions, 36 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4ee2330c603e..6bdcdd984394 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -304,7 +304,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved)
 		return true;
 
 	nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD;
-	blk_mq_force_complete_rq(req);
+	blk_mq_complete_request(req);
 	return true;
 }
 EXPORT_SYMBOL_GPL(nvme_cancel_request);
@@ -2175,6 +2175,7 @@ static void nvme_ns_head_release(struct gendisk *disk, fmode_t mode)
 
 const struct block_device_operations nvme_ns_head_ops = {
 	.owner		= THIS_MODULE,
+	.submit_bio	= nvme_ns_head_submit_bio,
 	.open		= nvme_ns_head_open,
 	.release	= nvme_ns_head_release,
 	.ioctl		= nvme_ioctl,
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index e999a8c4b7e8..6aa30bb5a762 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -227,6 +227,7 @@ static DECLARE_COMPLETION(nvme_fc_unload_proceed);
  */
 static struct device *fc_udev_device;
 
+static void nvme_fc_complete_rq(struct request *rq);
 
 /* *********************** FC-NVME Port Management ************************ */
 
@@ -2033,7 +2034,8 @@ done:
 	}
 
 	__nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
-	nvme_end_request(rq, status, result);
+	if (!nvme_end_request(rq, status, result))
+		nvme_fc_complete_rq(rq);
 
 check_error:
 	if (terminate_assoc)
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 66509472fe06..5a37a595411e 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -291,8 +291,7 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 	return false;
 }
 
-static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
-		struct bio *bio)
+blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
 {
 	struct nvme_ns_head *head = bio->bi_disk->private_data;
 	struct device *dev = disk_to_dev(head->disk);
@@ -301,12 +300,11 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
 	int srcu_idx;
 
 	/*
-	 * The namespace might be going away and the bio might
-	 * be moved to a different queue via blk_steal_bios(),
-	 * so we need to use the bio_split pool from the original
-	 * queue to allocate the bvecs from.
+	 * The namespace might be going away and the bio might be moved to a
+	 * different queue via blk_steal_bios(), so we need to use the bio_split
+	 * pool from the original queue to allocate the bvecs from.
 	 */
-	blk_queue_split(q, &bio);
+	blk_queue_split(&bio);
 
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = nvme_find_path(head);
@@ -316,7 +314,7 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
 		trace_block_bio_remap(bio->bi_disk->queue, bio,
 				      disk_devt(ns->head->disk),
 				      bio->bi_iter.bi_sector);
-		ret = direct_make_request(bio);
+		ret = submit_bio_noacct(bio);
 	} else if (nvme_available_path(head)) {
 		dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n");
 
@@ -353,7 +351,7 @@ static void nvme_requeue_work(struct work_struct *work)
 		 * path.
 		 */
 		bio->bi_disk = head->disk;
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 	}
 }
 
@@ -375,7 +373,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || !multipath)
 		return 0;
 
-	q = blk_alloc_queue(nvme_ns_head_make_request, ctrl->numa_node);
+	q = blk_alloc_queue(ctrl->numa_node);
 	if (!q)
 		goto out;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 09ffc3246f60..9c5b82af7978 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -481,7 +481,7 @@ static inline u32 nvme_bytes_to_numd(size_t len)
 	return (len >> 2) - 1;
 }
 
-static inline void nvme_end_request(struct request *req, __le16 status,
+static inline bool nvme_end_request(struct request *req, __le16 status,
 		union nvme_result result)
 {
 	struct nvme_request *rq = nvme_req(req);
@@ -490,7 +490,9 @@ static inline void nvme_end_request(struct request *req, __le16 status,
 	rq->result = result;
 	/* inject error when permitted by fault injection framework */
 	nvme_should_fail(req);
-	blk_mq_complete_request(req);
+	if (unlikely(blk_should_fake_timeout(req->q)))
+		return true;
+	return blk_mq_complete_request_remote(req);
 }
 
 static inline void nvme_get_ctrl(struct nvme_ctrl *ctrl)
@@ -593,6 +595,7 @@ void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
 void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
 struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
+blk_qc_t nvme_ns_head_submit_bio(struct bio *bio);
 
 static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 {
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index d4b1ff747123..0c85680984c1 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -963,7 +963,8 @@ 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);
-	nvme_end_request(req, cqe->status, cqe->result);
+	if (!nvme_end_request(req, cqe->status, cqe->result))
+		nvme_pci_complete_rq(req);
 }
 
 static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 13506a87a444..e881f879ac63 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -149,6 +149,7 @@ MODULE_PARM_DESC(register_always,
 static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
 		struct rdma_cm_event *event);
 static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc);
+static void nvme_rdma_complete_rq(struct request *rq);
 
 static const struct blk_mq_ops nvme_rdma_mq_ops;
 static const struct blk_mq_ops nvme_rdma_admin_mq_ops;
@@ -1149,6 +1150,16 @@ static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
 	queue_work(nvme_reset_wq, &ctrl->err_work);
 }
 
+static void nvme_rdma_end_request(struct nvme_rdma_request *req)
+{
+	struct request *rq = blk_mq_rq_from_pdu(req);
+
+	if (!refcount_dec_and_test(&req->ref))
+		return;
+	if (!nvme_end_request(rq, req->status, req->result))
+		nvme_rdma_complete_rq(rq);
+}
+
 static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc,
 		const char *op)
 {
@@ -1173,16 +1184,11 @@ static void nvme_rdma_inv_rkey_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct nvme_rdma_request *req =
 		container_of(wc->wr_cqe, struct nvme_rdma_request, reg_cqe);
-	struct request *rq = blk_mq_rq_from_pdu(req);
 
-	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+	if (unlikely(wc->status != IB_WC_SUCCESS))
 		nvme_rdma_wr_error(cq, wc, "LOCAL_INV");
-		return;
-	}
-
-	if (refcount_dec_and_test(&req->ref))
-		nvme_end_request(rq, req->status, req->result);
-
+	else
+		nvme_rdma_end_request(req);
 }
 
 static int nvme_rdma_inv_rkey(struct nvme_rdma_queue *queue,
@@ -1547,15 +1553,11 @@ static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
 		container_of(wc->wr_cqe, struct nvme_rdma_qe, cqe);
 	struct nvme_rdma_request *req =
 		container_of(qe, struct nvme_rdma_request, sqe);
-	struct request *rq = blk_mq_rq_from_pdu(req);
 
-	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+	if (unlikely(wc->status != IB_WC_SUCCESS))
 		nvme_rdma_wr_error(cq, wc, "SEND");
-		return;
-	}
-
-	if (refcount_dec_and_test(&req->ref))
-		nvme_end_request(rq, req->status, req->result);
+	else
+		nvme_rdma_end_request(req);
 }
 
 static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
@@ -1697,8 +1699,7 @@ static void nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue,
 		return;
 	}
 
-	if (refcount_dec_and_test(&req->ref))
-		nvme_end_request(rq, req->status, req->result);
+	nvme_rdma_end_request(req);
 }
 
 static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index f3a91818167b..472f9001521d 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -464,7 +464,8 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
 		return -EINVAL;
 	}
 
-	nvme_end_request(rq, cqe->status, cqe->result);
+	if (!nvme_end_request(rq, cqe->status, cqe->result))
+		nvme_complete_rq(rq);
 	queue->nr_cqe++;
 
 	return 0;
@@ -654,7 +655,8 @@ static inline void nvme_tcp_end_request(struct request *rq, u16 status)
 {
 	union nvme_result res = {};
 
-	nvme_end_request(rq, cpu_to_le16(status << 1), res);
+	if (!nvme_end_request(rq, cpu_to_le16(status << 1), res))
+		nvme_complete_rq(rq);
 }
 
 static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 6e2f623e472e..6816507fba58 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -467,7 +467,7 @@ static int nvmet_p2pmem_ns_enable(struct nvmet_ns *ns)
 		return -EINVAL;
 	}
 
-	if (!blk_queue_pci_p2pdma(ns->bdev->bd_queue)) {
+	if (!blk_queue_pci_p2pdma(ns->bdev->bd_disk->queue)) {
 		pr_err("peer-to-peer DMA is not supported by the driver of %s\n",
 		       ns->device_path);
 		return -EINVAL;
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 6344e73c9354..8a0d4fe7bc18 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -116,7 +116,8 @@ static void nvme_loop_queue_response(struct nvmet_req *req)
 			return;
 		}
 
-		nvme_end_request(rq, cqe->status, cqe->result);
+		if (!nvme_end_request(rq, cqe->status, cqe->result))
+			nvme_loop_complete_rq(rq);
 	}
 }