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
  ...

Documentation/fault-injection/nvme-fault-injection.rst

@@ -3,7 +3,7 @@ NVMe Fault Injection
 Linux's fault injection framework provides a systematic way to support
 error injection via debugfs in the /sys/kernel/debug directory. When
 enabled, the default NVME_SC_INVALID_OPCODE with no retry will be
-injected into the nvme_end_request. Users can change the default status
+injected into the nvme_try_complete_req. Users can change the default status
 code and no retry flag via the debugfs. The list of Generic Command
 Status can be found in include/linux/nvme.h
 

MAINTAINERS

@@ -3205,6 +3205,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 F:	block/
 F:	drivers/block/
+F:	include/linux/blk*
 F:	kernel/trace/blktrace.c
 F:	lib/sbitmap.c
 

block/bfq-cgroup.c

@@ -332,7 +332,7 @@ static void bfqg_put(struct bfq_group *bfqg)
 		kfree(bfqg);
 }
 
-void bfqg_and_blkg_get(struct bfq_group *bfqg)
+static void bfqg_and_blkg_get(struct bfq_group *bfqg)
 {
 	/* see comments in bfq_bic_update_cgroup for why refcounting bfqg */
 	bfqg_get(bfqg);

block/bfq-iosched.h

@@ -986,7 +986,6 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
 struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
-void bfqg_and_blkg_get(struct bfq_group *bfqg);
 void bfqg_and_blkg_put(struct bfq_group *bfqg);
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED

block/bfq-wf2q.c

@@ -533,9 +533,7 @@ static void bfq_get_entity(struct bfq_entity *entity)
 		bfqq->ref++;
 		bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
 			     bfqq, bfqq->ref);
-	} else
-		bfqg_and_blkg_get(container_of(entity, struct bfq_group,
-					       entity));
+	}
 }
 
 /**
@@ -649,14 +647,8 @@ static void bfq_forget_entity(struct bfq_service_tree *st,
 
 	entity->on_st_or_in_serv = false;
 	st->wsum -= entity->weight;
-	if (is_in_service)
-		return;
-
-	if (bfqq)
+	if (bfqq && !is_in_service)
 		bfq_put_queue(bfqq);
-	else
-		bfqg_and_blkg_put(container_of(entity, struct bfq_group,
-					       entity));
 }
 
 /**

block/bio.c

@@ -740,8 +740,8 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
 		struct page *page, unsigned int len, unsigned int off,
 		bool *same_page)
 {
-	phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) +
-		bv->bv_offset + bv->bv_len - 1;
+	size_t bv_end = bv->bv_offset + bv->bv_len;
+	phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1;
 	phys_addr_t page_addr = page_to_phys(page);
 
 	if (vec_end_addr + 1 != page_addr + off)
@@ -750,9 +750,9 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
 		return false;
 
 	*same_page = ((vec_end_addr & PAGE_MASK) == page_addr);
-	if (!*same_page && pfn_to_page(PFN_DOWN(vec_end_addr)) + 1 != page)
-		return false;
-	return true;
+	if (*same_page)
+		return true;
+	return (bv->bv_page + bv_end / PAGE_SIZE) == (page + off / PAGE_SIZE);
 }
 
 /*

block/blk-cgroup.c

@@ -1152,13 +1152,15 @@ int blkcg_init_queue(struct request_queue *q)
 	if (preloaded)
 		radix_tree_preload_end();
 
-	ret = blk_iolatency_init(q);
+	ret = blk_throtl_init(q);
 	if (ret)
 		goto err_destroy_all;
 
-	ret = blk_throtl_init(q);
-	if (ret)
+	ret = blk_iolatency_init(q);
+	if (ret) {
+		blk_throtl_exit(q);
 		goto err_destroy_all;
+	}
 	return 0;
 
 err_destroy_all:

block/blk-merge.c

@@ -154,7 +154,7 @@ static inline unsigned get_max_io_size(struct request_queue *q,
 	if (max_sectors > start_offset)
 		return max_sectors - start_offset;
 
-	return sectors & (lbs - 1);
+	return sectors & ~(lbs - 1);
 }
 
 static inline unsigned get_max_segment_size(const struct request_queue *q,
@@ -533,10 +533,17 @@ int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL(__blk_rq_map_sg);
 
+static inline unsigned int blk_rq_get_max_segments(struct request *rq)
+{
+	if (req_op(rq) == REQ_OP_DISCARD)
+		return queue_max_discard_segments(rq->q);
+	return queue_max_segments(rq->q);
+}
+
 static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
 		unsigned int nr_phys_segs)
 {
-	if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(req->q))
+	if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req))
 		goto no_merge;
 
 	if (blk_integrity_merge_bio(req->q, req, bio) == false)
@@ -624,7 +631,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 		return 0;
 
 	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
-	if (total_phys_segments > queue_max_segments(q))
+	if (total_phys_segments > blk_rq_get_max_segments(req))
 		return 0;
 
 	if (blk_integrity_merge_rq(q, req, next) == false)

block/blk-mq-sched.c

@@ -78,6 +78,15 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
 		return;
 	clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 
+	/*
+	 * Order clearing SCHED_RESTART and list_empty_careful(&hctx->dispatch)
+	 * in blk_mq_run_hw_queue(). Its pair is the barrier in
+	 * blk_mq_dispatch_rq_list(). So dispatch code won't see SCHED_RESTART,
+	 * meantime new request added to hctx->dispatch is missed to check in
+	 * blk_mq_run_hw_queue().
+	 */
+	smp_mb();
+
 	blk_mq_run_hw_queue(hctx, true);
 }
 

block/blk-mq.c

@@ -1437,6 +1437,15 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 		list_splice_tail_init(list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
 
+		/*
+		 * Order adding requests to hctx->dispatch and checking
+		 * SCHED_RESTART flag. The pair of this smp_mb() is the one
+		 * in blk_mq_sched_restart(). Avoid restart code path to
+		 * miss the new added requests to hctx->dispatch, meantime
+		 * SCHED_RESTART is observed here.
+		 */
+		smp_mb();
+
 		/*
 		 * If SCHED_RESTART was set by the caller of this function and
 		 * it is no longer set that means that it was cleared by another
@@ -1834,6 +1843,7 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 /**
  * blk_mq_request_bypass_insert - Insert a request at dispatch list.
  * @rq: Pointer to request to be inserted.
+ * @at_head: true if the request should be inserted at the head of the list.
  * @run_queue: If we should run the hardware queue after inserting the request.
  *
  * Should only be used carefully, when the caller knows we want to
@@ -2016,7 +2026,8 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	if (bypass_insert)
 		return BLK_STS_RESOURCE;
 
-	blk_mq_request_bypass_insert(rq, false, run_queue);
+	blk_mq_sched_insert_request(rq, false, run_queue, false);
+
 	return BLK_STS_OK;
 }
 

block/bsg-lib.c

@@ -378,7 +378,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
 	bset->timeout_fn = timeout;
 
 	set = &bset->tag_set;
-	set->ops = &bsg_mq_ops,
+	set->ops = &bsg_mq_ops;
 	set->nr_hw_queues = 1;
 	set->queue_depth = 128;
 	set->numa_node = NUMA_NO_NODE;

drivers/block/loop.c

@@ -878,6 +878,7 @@ static void loop_config_discard(struct loop_device *lo)
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
 	struct request_queue *q = lo->lo_queue;
+	u32 granularity, max_discard_sectors;
 
 	/*
 	 * If the backing device is a block device, mirror its zeroing
@@ -890,11 +891,10 @@ static void loop_config_discard(struct loop_device *lo)
 		struct request_queue *backingq;
 
 		backingq = bdev_get_queue(inode->i_bdev);
-		blk_queue_max_discard_sectors(q,
-			backingq->limits.max_write_zeroes_sectors);
 
-		blk_queue_max_write_zeroes_sectors(q,
-			backingq->limits.max_write_zeroes_sectors);
+		max_discard_sectors = backingq->limits.max_write_zeroes_sectors;
+		granularity = backingq->limits.discard_granularity ?:
+			queue_physical_block_size(backingq);
 
 	/*
 	 * We use punch hole to reclaim the free space used by the
@@ -903,23 +903,26 @@ static void loop_config_discard(struct loop_device *lo)
 	 * useful information.
 	 */
 	} else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) {
-		q->limits.discard_granularity = 0;
-		q->limits.discard_alignment = 0;
-		blk_queue_max_discard_sectors(q, 0);
-		blk_queue_max_write_zeroes_sectors(q, 0);
+		max_discard_sectors = 0;
+		granularity = 0;
 
 	} else {
-		q->limits.discard_granularity = inode->i_sb->s_blocksize;
-		q->limits.discard_alignment = 0;
-
-		blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
-		blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
+		max_discard_sectors = UINT_MAX >> 9;
+		granularity = inode->i_sb->s_blocksize;
 	}
 
-	if (q->limits.max_write_zeroes_sectors)
+	if (max_discard_sectors) {
+		q->limits.discard_granularity = granularity;
+		blk_queue_max_discard_sectors(q, max_discard_sectors);
+		blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
 		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
-	else
+	} else {
+		q->limits.discard_granularity = 0;
+		blk_queue_max_discard_sectors(q, 0);
+		blk_queue_max_write_zeroes_sectors(q, 0);
 		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
+	}
+	q->limits.discard_alignment = 0;
 }
 
 static void loop_unprepare_queue(struct loop_device *lo)

drivers/block/null_blk_main.c

@@ -1147,7 +1147,7 @@ static int null_handle_rq(struct nullb_cmd *cmd)
 		len = bvec.bv_len;
 		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
 				     op_is_write(req_op(rq)), sector,
-				     req_op(rq) & REQ_FUA);
+				     rq->cmd_flags & REQ_FUA);
 		if (err) {
 			spin_unlock_irq(&nullb->lock);
 			return err;

drivers/block/rnbd/rnbd-srv.c

@@ -148,7 +148,8 @@ static int process_rdma(struct rtrs_srv *sess,
 	/* Generate bio with pages pointing to the rdma buffer */
 	bio = rnbd_bio_map_kern(data, sess_dev->rnbd_dev->ibd_bio_set, datalen, GFP_KERNEL);
 	if (IS_ERR(bio)) {
-		rnbd_srv_err(sess_dev, "Failed to generate bio, err: %ld\n", PTR_ERR(bio));
+		err = PTR_ERR(bio);
+		rnbd_srv_err(sess_dev, "Failed to generate bio, err: %d\n", err);
 		goto sess_dev_put;
 	}
 

drivers/block/virtio_blk.c

@@ -126,16 +126,31 @@ static int virtblk_setup_discard_write_zeroes(struct request *req, bool unmap)
 	if (!range)
 		return -ENOMEM;
 
-	__rq_for_each_bio(bio, req) {
-		u64 sector = bio->bi_iter.bi_sector;
-		u32 num_sectors = bio->bi_iter.bi_size >> SECTOR_SHIFT;
-
-		range[n].flags = cpu_to_le32(flags);
-		range[n].num_sectors = cpu_to_le32(num_sectors);
-		range[n].sector = cpu_to_le64(sector);
-		n++;
+	/*
+	 * Single max discard segment means multi-range discard isn't
+	 * supported, and block layer only runs contiguity merge like
+	 * normal RW request. So we can't reply on bio for retrieving
+	 * each range info.
+	 */
+	if (queue_max_discard_segments(req->q) == 1) {
+		range[0].flags = cpu_to_le32(flags);
+		range[0].num_sectors = cpu_to_le32(blk_rq_sectors(req));
+		range[0].sector = cpu_to_le64(blk_rq_pos(req));
+		n = 1;
+	} else {
+		__rq_for_each_bio(bio, req) {
+			u64 sector = bio->bi_iter.bi_sector;
+			u32 num_sectors = bio->bi_iter.bi_size >> SECTOR_SHIFT;
+
+			range[n].flags = cpu_to_le32(flags);
+			range[n].num_sectors = cpu_to_le32(num_sectors);
+			range[n].sector = cpu_to_le64(sector);
+			n++;
+		}
 	}
 
+	WARN_ON_ONCE(n != segments);
+
 	req->special_vec.bv_page = virt_to_page(range);
 	req->special_vec.bv_offset = offset_in_page(range);
 	req->special_vec.bv_len = sizeof(*range) * segments;