Merge tag 'for-5.17/block-2022-01-11' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Unify where the struct request handling code is located in the blk-mq
   code (Christoph)

 - Header cleanups (Christoph)

 - Clean up the io_context handling code (Christoph, me)

 - Get rid of ->rq_disk in struct request (Christoph)

 - Error handling fix for add_disk() (Christoph)

 - request allocation cleanusp (Christoph)

 - Documentation updates (Eric, Matthew)

 - Remove trivial crypto unregister helper (Eric)

 - Reduce shared tag overhead (John)

 - Reduce poll_stats memory overhead (me)

 - Known indirect function call for dio (me)

 - Use atomic references for struct request (me)

 - Support request list issue for block and NVMe (me)

 - Improve queue dispatch pinning (Ming)

 - Improve the direct list issue code (Keith)

 - BFQ improvements (Jan)

 - Direct completion helper and use it in mmc block (Sebastian)

 - Use raw spinlock for the blktrace code (Wander)

 - fsync error handling fix (Ye)

 - Various fixes and cleanups (Lukas, Randy, Yang, Tetsuo, Ming, me)

* tag 'for-5.17/block-2022-01-11' of git://git.kernel.dk/linux-block: (132 commits)
  MAINTAINERS: add entries for block layer documentation
  docs: block: remove queue-sysfs.rst
  docs: sysfs-block: document virt_boundary_mask
  docs: sysfs-block: document stable_writes
  docs: sysfs-block: fill in missing documentation from queue-sysfs.rst
  docs: sysfs-block: add contact for nomerges
  docs: sysfs-block: sort alphabetically
  docs: sysfs-block: move to stable directory
  block: don't protect submit_bio_checks by q_usage_counter
  block: fix old-style declaration
  nvme-pci: fix queue_rqs list splitting
  block: introduce rq_list_move
  block: introduce rq_list_for_each_safe macro
  block: move rq_list macros to blk-mq.h
  block: drop needless assignment in set_task_ioprio()
  block: remove unnecessary trailing '\'
  bio.h: fix kernel-doc warnings
  block: check minor range in device_add_disk()
  block: use "unsigned long" for blk_validate_block_size().
  block: fix error unwinding in device_add_disk
  ...

5 files changed, 113 insertions, 49 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 1af8a4513708..290f26ed74c2 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1057,7 +1057,7 @@ static int nvme_execute_rq(struct gendisk *disk, struct request *rq,
 {
 	blk_status_t status;
 
-	status = blk_execute_rq(disk, rq, at_head);
+	status = blk_execute_rq(rq, at_head);
 	if (nvme_req(rq)->flags & NVME_REQ_CANCELLED)
 		return -EINTR;
 	if (nvme_req(rq)->status)
@@ -1284,7 +1284,7 @@ static void nvme_keep_alive_work(struct work_struct *work)
 
 	rq->timeout = ctrl->kato * HZ;
 	rq->end_io_data = ctrl;
-	blk_execute_rq_nowait(NULL, rq, 0, nvme_keep_alive_end_io);
+	blk_execute_rq_nowait(rq, false, nvme_keep_alive_end_io);
 }
 
 static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c
index 1352159733b0..83d2e6860d38 100644
--- a/drivers/nvme/host/fault_inject.c
+++ b/drivers/nvme/host/fault_inject.c
@@ -56,7 +56,7 @@ void nvme_fault_inject_fini(struct nvme_fault_inject *fault_inject)
 
 void nvme_should_fail(struct request *req)
 {
-	struct gendisk *disk = req->rq_disk;
+	struct gendisk *disk = req->q->disk;
 	struct nvme_fault_inject *fault_inject = NULL;
 	u16 status;
 
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index ca2ee806d74b..d8585df2c2fd 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -500,22 +500,13 @@ static inline void nvme_write_sq_db(struct nvme_queue *nvmeq, bool write_sq)
 	nvmeq->last_sq_tail = nvmeq->sq_tail;
 }
 
-/**
- * nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
- * @nvmeq: The queue to use
- * @cmd: The command to send
- * @write_sq: whether to write to the SQ doorbell
- */
-static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd,
-			    bool write_sq)
+static inline void nvme_sq_copy_cmd(struct nvme_queue *nvmeq,
+				    struct nvme_command *cmd)
 {
-	spin_lock(&nvmeq->sq_lock);
 	memcpy(nvmeq->sq_cmds + (nvmeq->sq_tail << nvmeq->sqes),
-	       cmd, sizeof(*cmd));
+		absolute_pointer(cmd), sizeof(*cmd));
 	if (++nvmeq->sq_tail == nvmeq->q_depth)
 		nvmeq->sq_tail = 0;
-	nvme_write_sq_db(nvmeq, write_sq);
-	spin_unlock(&nvmeq->sq_lock);
 }
 
 static void nvme_commit_rqs(struct blk_mq_hw_ctx *hctx)
@@ -912,52 +903,32 @@ static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req,
 	return BLK_STS_OK;
 }
 
-/*
- * NOTE: ns is NULL when called on the admin queue.
- */
-static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
-			 const struct blk_mq_queue_data *bd)
+static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
 {
-	struct nvme_ns *ns = hctx->queue->queuedata;
-	struct nvme_queue *nvmeq = hctx->driver_data;
-	struct nvme_dev *dev = nvmeq->dev;
-	struct request *req = bd->rq;
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	struct nvme_command *cmnd = &iod->cmd;
 	blk_status_t ret;
 
 	iod->aborted = 0;
 	iod->npages = -1;
 	iod->nents = 0;
 
-	/*
-	 * We should not need to do this, but we're still using this to
-	 * ensure we can drain requests on a dying queue.
-	 */
-	if (unlikely(!test_bit(NVMEQ_ENABLED, &nvmeq->flags)))
-		return BLK_STS_IOERR;
-
-	if (!nvme_check_ready(&dev->ctrl, req, true))
-		return nvme_fail_nonready_command(&dev->ctrl, req);
-
-	ret = nvme_setup_cmd(ns, req);
+	ret = nvme_setup_cmd(req->q->queuedata, req);
 	if (ret)
 		return ret;
 
 	if (blk_rq_nr_phys_segments(req)) {
-		ret = nvme_map_data(dev, req, cmnd);
+		ret = nvme_map_data(dev, req, &iod->cmd);
 		if (ret)
 			goto out_free_cmd;
 	}
 
 	if (blk_integrity_rq(req)) {
-		ret = nvme_map_metadata(dev, req, cmnd);
+		ret = nvme_map_metadata(dev, req, &iod->cmd);
 		if (ret)
 			goto out_unmap_data;
 	}
 
 	blk_mq_start_request(req);
-	nvme_submit_cmd(nvmeq, cmnd, bd->last);
 	return BLK_STS_OK;
 out_unmap_data:
 	nvme_unmap_data(dev, req);
@@ -966,6 +937,96 @@ out_free_cmd:
 	return ret;
 }
 
+/*
+ * NOTE: ns is NULL when called on the admin queue.
+ */
+static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
+			 const struct blk_mq_queue_data *bd)
+{
+	struct nvme_queue *nvmeq = hctx->driver_data;
+	struct nvme_dev *dev = nvmeq->dev;
+	struct request *req = bd->rq;
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+	blk_status_t ret;
+
+	/*
+	 * We should not need to do this, but we're still using this to
+	 * ensure we can drain requests on a dying queue.
+	 */
+	if (unlikely(!test_bit(NVMEQ_ENABLED, &nvmeq->flags)))
+		return BLK_STS_IOERR;
+
+	if (unlikely(!nvme_check_ready(&dev->ctrl, req, true)))
+		return nvme_fail_nonready_command(&dev->ctrl, req);
+
+	ret = nvme_prep_rq(dev, req);
+	if (unlikely(ret))
+		return ret;
+	spin_lock(&nvmeq->sq_lock);
+	nvme_sq_copy_cmd(nvmeq, &iod->cmd);
+	nvme_write_sq_db(nvmeq, bd->last);
+	spin_unlock(&nvmeq->sq_lock);
+	return BLK_STS_OK;
+}
+
+static void nvme_submit_cmds(struct nvme_queue *nvmeq, struct request **rqlist)
+{
+	spin_lock(&nvmeq->sq_lock);
+	while (!rq_list_empty(*rqlist)) {
+		struct request *req = rq_list_pop(rqlist);
+		struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+
+		nvme_sq_copy_cmd(nvmeq, &iod->cmd);
+	}
+	nvme_write_sq_db(nvmeq, true);
+	spin_unlock(&nvmeq->sq_lock);
+}
+
+static bool nvme_prep_rq_batch(struct nvme_queue *nvmeq, struct request *req)
+{
+	/*
+	 * We should not need to do this, but we're still using this to
+	 * ensure we can drain requests on a dying queue.
+	 */
+	if (unlikely(!test_bit(NVMEQ_ENABLED, &nvmeq->flags)))
+		return false;
+	if (unlikely(!nvme_check_ready(&nvmeq->dev->ctrl, req, true)))
+		return false;
+
+	req->mq_hctx->tags->rqs[req->tag] = req;
+	return nvme_prep_rq(nvmeq->dev, req) == BLK_STS_OK;
+}
+
+static void nvme_queue_rqs(struct request **rqlist)
+{
+	struct request *req, *next, *prev = NULL;
+	struct request *requeue_list = NULL;
+
+	rq_list_for_each_safe(rqlist, req, next) {
+		struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
+
+		if (!nvme_prep_rq_batch(nvmeq, req)) {
+			/* detach 'req' and add to remainder list */
+			rq_list_move(rqlist, &requeue_list, req, prev);
+
+			req = prev;
+			if (!req)
+				continue;
+		}
+
+		if (!next || req->mq_hctx != next->mq_hctx) {
+			/* detach rest of list, and submit */
+			req->rq_next = NULL;
+			nvme_submit_cmds(nvmeq, rqlist);
+			*rqlist = next;
+			prev = NULL;
+		} else
+			prev = req;
+	}
+
+	*rqlist = requeue_list;
+}
+
 static __always_inline void nvme_pci_unmap_rq(struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
@@ -1140,7 +1201,11 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl)
 
 	c.common.opcode = nvme_admin_async_event;
 	c.common.command_id = NVME_AQ_BLK_MQ_DEPTH;
-	nvme_submit_cmd(nvmeq, &c, true);
+
+	spin_lock(&nvmeq->sq_lock);
+	nvme_sq_copy_cmd(nvmeq, &c);
+	nvme_write_sq_db(nvmeq, true);
+	spin_unlock(&nvmeq->sq_lock);
 }
 
 static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
@@ -1371,7 +1436,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	}
 
 	abort_req->end_io_data = NULL;
-	blk_execute_rq_nowait(NULL, abort_req, 0, abort_endio);
+	blk_execute_rq_nowait(abort_req, false, abort_endio);
 
 	/*
 	 * The aborted req will be completed on receiving the abort req.
@@ -1663,6 +1728,7 @@ static const struct blk_mq_ops nvme_mq_admin_ops = {
 
 static const struct blk_mq_ops nvme_mq_ops = {
 	.queue_rq	= nvme_queue_rq,
+	.queue_rqs	= nvme_queue_rqs,
 	.complete	= nvme_pci_complete_rq,
 	.commit_rqs	= nvme_commit_rqs,
 	.init_hctx	= nvme_init_hctx,
@@ -2416,9 +2482,8 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
 	req->end_io_data = nvmeq;
 
 	init_completion(&nvmeq->delete_done);
-	blk_execute_rq_nowait(NULL, req, false,
-			opcode == nvme_admin_delete_cq ?
-				nvme_del_cq_end : nvme_del_queue_end);
+	blk_execute_rq_nowait(req, false, opcode == nvme_admin_delete_cq ?
+			nvme_del_cq_end : nvme_del_queue_end);
 	return 0;
 }
 
diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h
index 35bac7a25422..b5f85259461a 100644
--- a/drivers/nvme/host/trace.h
+++ b/drivers/nvme/host/trace.h
@@ -68,7 +68,7 @@ TRACE_EVENT(nvme_setup_cmd,
 		__entry->nsid = le32_to_cpu(cmd->common.nsid);
 		__entry->metadata = !!blk_integrity_rq(req);
 		__entry->fctype = cmd->fabrics.fctype;
-		__assign_disk_name(__entry->disk, req->rq_disk);
+		__assign_disk_name(__entry->disk, req->q->disk);
 		memcpy(__entry->cdw10, &cmd->common.cdw10,
 			sizeof(__entry->cdw10));
 	    ),
@@ -103,7 +103,7 @@ TRACE_EVENT(nvme_complete_rq,
 		__entry->retries = nvme_req(req)->retries;
 		__entry->flags = nvme_req(req)->flags;
 		__entry->status = nvme_req(req)->status;
-		__assign_disk_name(__entry->disk, req->rq_disk);
+		__assign_disk_name(__entry->disk, req->q->disk);
 	    ),
 	    TP_printk("nvme%d: %sqid=%d, cmdid=%u, res=%#llx, retries=%u, flags=0x%x, status=%#x",
 		      __entry->ctrl_id, __print_disk_name(__entry->disk),
@@ -153,7 +153,7 @@ TRACE_EVENT(nvme_sq,
 	),
 	TP_fast_assign(
 		__entry->ctrl_id = nvme_req(req)->ctrl->instance;
-		__assign_disk_name(__entry->disk, req->rq_disk);
+		__assign_disk_name(__entry->disk, req->q->disk);
 		__entry->qid = nvme_req_qid(req);
 		__entry->sq_head = le16_to_cpu(sq_head);
 		__entry->sq_tail = sq_tail;
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index f0efb3537989..9e5b89ae29df 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -284,8 +284,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
 		schedule_work(&req->p.work);
 	} else {
 		rq->end_io_data = req;
-		blk_execute_rq_nowait(ns ? ns->disk : NULL, rq, 0,
-				      nvmet_passthru_req_done);
+		blk_execute_rq_nowait(rq, false, nvmet_passthru_req_done);
 	}
 
 	if (ns)