Merge tag 'block-5.9-2020-08-14' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A few fixes on the block side of things:

   - Discard granularity fix (Coly)

   - rnbd cleanups (Guoqing)

   - md error handling fix (Dan)

   - md sysfs fix (Junxiao)

   - Fix flush request accounting, which caused an IO slowdown for some
     configurations (Ming)

   - Properly propagate loop flag for partition scanning (Lennart)"

* tag 'block-5.9-2020-08-14' of git://git.kernel.dk/linux-block:
  block: fix double account of flush request's driver tag
  loop: unset GENHD_FL_NO_PART_SCAN on LOOP_CONFIGURE
  rnbd: no need to set bi_end_io in rnbd_bio_map_kern
  rnbd: remove rnbd_dev_submit_io
  md-cluster: Fix potential error pointer dereference in resize_bitmaps()
  block: check queue's limits.discard_granularity in __blkdev_issue_discard()
  md: get sysfs entry after redundancy attr group create

block/blk-flush.c

@@ -308,9 +308,16 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
 	flush_rq->mq_ctx = first_rq->mq_ctx;
 	flush_rq->mq_hctx = first_rq->mq_hctx;
 
-	if (!q->elevator)
+	if (!q->elevator) {
 		flush_rq->tag = first_rq->tag;
-	else
+
+		/*
+		 * We borrow data request's driver tag, so have to mark
+		 * this flush request as INFLIGHT for avoiding double
+		 * account of this driver tag
+		 */
+		flush_rq->rq_flags |= RQF_MQ_INFLIGHT;
+	} else
 		flush_rq->internal_tag = first_rq->internal_tag;
 
 	flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;

block/blk-lib.c

@@ -47,6 +47,15 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		op = REQ_OP_DISCARD;
 	}
 
+	/* In case the discard granularity isn't set by buggy device driver */
+	if (WARN_ON_ONCE(!q->limits.discard_granularity)) {
+		char dev_name[BDEVNAME_SIZE];
+
+		bdevname(bdev, dev_name);
+		pr_err_ratelimited("%s: Error: discard_granularity is 0.\n", dev_name);
+		return -EOPNOTSUPP;
+	}
+
 	bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
 	if ((sector | nr_sects) & bs_mask)
 		return -EINVAL;

drivers/block/loop.c

@@ -1171,6 +1171,8 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	if (part_shift)
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
 	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
+	if (partscan)
+		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
 
 	/* Grab the block_device to prevent its destruction after we
 	 * put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev).

drivers/block/rnbd/rnbd-srv-dev.c

@@ -45,7 +45,7 @@ void rnbd_dev_close(struct rnbd_dev *dev)
 	kfree(dev);
 }
 
-static void rnbd_dev_bi_end_io(struct bio *bio)
+void rnbd_dev_bi_end_io(struct bio *bio)
 {
 	struct rnbd_dev_blk_io *io = bio->bi_private;
 
@@ -63,8 +63,8 @@ static void rnbd_dev_bi_end_io(struct bio *bio)
  *	Map the kernel address into a bio suitable for io to a block
  *	device. Returns an error pointer in case of error.
  */
-static struct bio *rnbd_bio_map_kern(void *data, struct bio_set *bs,
-				     unsigned int len, gfp_t gfp_mask)
+struct bio *rnbd_bio_map_kern(void *data, struct bio_set *bs,
+			      unsigned int len, gfp_t gfp_mask)
 {
 	unsigned long kaddr = (unsigned long)data;
 	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -99,36 +99,5 @@ static struct bio *rnbd_bio_map_kern(void *data, struct bio_set *bs,
 		offset = 0;
 	}
 
-	bio->bi_end_io = bio_put;
 	return bio;
 }
-
-int rnbd_dev_submit_io(struct rnbd_dev *dev, sector_t sector, void *data,
-		       size_t len, u32 bi_size, enum rnbd_io_flags flags,
-		       short prio, void *priv)
-{
-	struct rnbd_dev_blk_io *io;
-	struct bio *bio;
-
-	/* Generate bio with pages pointing to the rdma buffer */
-	bio = rnbd_bio_map_kern(data, dev->ibd_bio_set, len, GFP_KERNEL);
-	if (IS_ERR(bio))
-		return PTR_ERR(bio);
-
-	io = container_of(bio, struct rnbd_dev_blk_io, bio);
-
-	io->dev	= dev;
-	io->priv = priv;
-
-	bio->bi_end_io = rnbd_dev_bi_end_io;
-	bio->bi_private	= io;
-	bio->bi_opf = rnbd_to_bio_flags(flags);
-	bio->bi_iter.bi_sector = sector;
-	bio->bi_iter.bi_size = bi_size;
-	bio_set_prio(bio, prio);
-	bio_set_dev(bio, dev->bdev);
-
-	submit_bio(bio);
-
-	return 0;
-}

drivers/block/rnbd/rnbd-srv-dev.h

@@ -41,6 +41,11 @@ void rnbd_dev_close(struct rnbd_dev *dev);
 
 void rnbd_endio(void *priv, int error);
 
+void rnbd_dev_bi_end_io(struct bio *bio);
+
+struct bio *rnbd_bio_map_kern(void *data, struct bio_set *bs,
+			      unsigned int len, gfp_t gfp_mask);
+
 static inline int rnbd_dev_get_max_segs(const struct rnbd_dev *dev)
 {
 	return queue_max_segments(bdev_get_queue(dev->bdev));
@@ -75,18 +80,4 @@ static inline int rnbd_dev_get_discard_alignment(const struct rnbd_dev *dev)
 	return bdev_get_queue(dev->bdev)->limits.discard_alignment;
 }
 
-/**
- * rnbd_dev_submit_io() - Submit an I/O to the disk
- * @dev:	device to that the I/O is submitted
- * @sector:	address to read/write data to
- * @data:	I/O data to write or buffer to read I/O date into
- * @len:	length of @data
- * @bi_size:	Amount of data that will be read/written
- * @prio:       IO priority
- * @priv:	private data passed to @io_fn
- */
-int rnbd_dev_submit_io(struct rnbd_dev *dev, sector_t sector, void *data,
-			size_t len, u32 bi_size, enum rnbd_io_flags flags,
-			short prio, void *priv);
-
 #endif /* RNBD_SRV_DEV_H */

drivers/block/rnbd/rnbd-srv.c

@@ -124,6 +124,9 @@ static int process_rdma(struct rtrs_srv *sess,
 	struct rnbd_srv_sess_dev *sess_dev;
 	u32 dev_id;
 	int err;
+	struct rnbd_dev_blk_io *io;
+	struct bio *bio;
+	short prio;
 
 	priv = kmalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -142,18 +145,29 @@ static int process_rdma(struct rtrs_srv *sess,
 	priv->sess_dev = sess_dev;
 	priv->id = id;
 
-	err = rnbd_dev_submit_io(sess_dev->rnbd_dev, le64_to_cpu(msg->sector),
-				  data, datalen, le32_to_cpu(msg->bi_size),
-				  le32_to_cpu(msg->rw),
-				  srv_sess->ver < RNBD_PROTO_VER_MAJOR ||
-				  usrlen < sizeof(*msg) ?
-				  0 : le16_to_cpu(msg->prio), priv);
-	if (unlikely(err)) {
-		rnbd_srv_err(sess_dev, "Submitting I/O to device failed, err: %d\n",
-			      err);
+	/* 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));
 		goto sess_dev_put;
 	}
 
+	io = container_of(bio, struct rnbd_dev_blk_io, bio);
+	io->dev = sess_dev->rnbd_dev;
+	io->priv = priv;
+
+	bio->bi_end_io = rnbd_dev_bi_end_io;
+	bio->bi_private = io;
+	bio->bi_opf = rnbd_to_bio_flags(le32_to_cpu(msg->rw));
+	bio->bi_iter.bi_sector = le64_to_cpu(msg->sector);
+	bio->bi_iter.bi_size = le32_to_cpu(msg->bi_size);
+	prio = srv_sess->ver < RNBD_PROTO_VER_MAJOR ||
+	       usrlen < sizeof(*msg) ? 0 : le16_to_cpu(msg->prio);
+	bio_set_prio(bio, prio);
+	bio_set_dev(bio, sess_dev->rnbd_dev->bdev);
+
+	submit_bio(bio);
+
 	return 0;
 
 sess_dev_put:

drivers/md/md-cluster.c

@@ -1139,6 +1139,7 @@ static int resize_bitmaps(struct mddev *mddev, sector_t newsize, sector_t oldsiz
 		bitmap = get_bitmap_from_slot(mddev, i);
 		if (IS_ERR(bitmap)) {
 			pr_err("can't get bitmap from slot %d\n", i);
+			bitmap = NULL;
 			goto out;
 		}
 		counts = &bitmap->counts;

drivers/md/md.c

@@ -850,7 +850,13 @@ void mddev_unlock(struct mddev *mddev)
 				sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
 				if (mddev->sysfs_action)
 					sysfs_put(mddev->sysfs_action);
+				if (mddev->sysfs_completed)
+					sysfs_put(mddev->sysfs_completed);
+				if (mddev->sysfs_degraded)
+					sysfs_put(mddev->sysfs_degraded);
 				mddev->sysfs_action = NULL;
+				mddev->sysfs_completed = NULL;
+				mddev->sysfs_degraded = NULL;
 			}
 		}
 		mddev->sysfs_active = 0;
@@ -4068,6 +4074,8 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 			pr_warn("md: cannot register extra attributes for %s\n",
 				mdname(mddev));
 		mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, "sync_action");
+		mddev->sysfs_completed = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_completed");
+		mddev->sysfs_degraded = sysfs_get_dirent_safe(mddev->kobj.sd, "degraded");
 	}
 	if (oldpers->sync_request != NULL &&
 	    pers->sync_request == NULL) {
@@ -5582,14 +5590,9 @@ static void md_free(struct kobject *ko)
 
 	if (mddev->sysfs_state)
 		sysfs_put(mddev->sysfs_state);
-	if (mddev->sysfs_completed)
-		sysfs_put(mddev->sysfs_completed);
-	if (mddev->sysfs_degraded)
-		sysfs_put(mddev->sysfs_degraded);
 	if (mddev->sysfs_level)
 		sysfs_put(mddev->sysfs_level);
 
-
 	if (mddev->gendisk)
 		del_gendisk(mddev->gendisk);
 	if (mddev->queue)
@@ -5757,8 +5760,6 @@ static int md_alloc(dev_t dev, char *name)
 	if (!error && mddev->kobj.sd) {
 		kobject_uevent(&mddev->kobj, KOBJ_ADD);
 		mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state");
-		mddev->sysfs_completed = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_completed");
-		mddev->sysfs_degraded = sysfs_get_dirent_safe(mddev->kobj.sd, "degraded");
 		mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level");
 	}
 	mddev_put(mddev);
@@ -6036,6 +6037,8 @@ int md_run(struct mddev *mddev)
 			pr_warn("md: cannot register extra attributes for %s\n",
 				mdname(mddev));
 		mddev->sysfs_action = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_action");
+		mddev->sysfs_completed = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_completed");
+		mddev->sysfs_degraded = sysfs_get_dirent_safe(mddev->kobj.sd, "degraded");
 	} else if (mddev->ro == 2) /* auto-readonly not meaningful */
 		mddev->ro = 0;