Merge tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Series of merge handling cleanups (Baolin, Christoph)

 - Series of blk-throttle fixes and cleanups (Baolin)

 - Series cleaning up BDI, seperating the block device from the
   backing_dev_info (Christoph)

 - Removal of bdget() as a generic API (Christoph)

 - Removal of blkdev_get() as a generic API (Christoph)

 - Cleanup of is-partition checks (Christoph)

 - Series reworking disk revalidation (Christoph)

 - Series cleaning up bio flags (Christoph)

 - bio crypt fixes (Eric)

 - IO stats inflight tweak (Gabriel)

 - blk-mq tags fixes (Hannes)

 - Buffer invalidation fixes (Jan)

 - Allow soft limits for zone append (Johannes)

 - Shared tag set improvements (John, Kashyap)

 - Allow IOPRIO_CLASS_RT for CAP_SYS_NICE (Khazhismel)

 - DM no-wait support (Mike, Konstantin)

 - Request allocation improvements (Ming)

 - Allow md/dm/bcache to use IO stat helpers (Song)

 - Series improving blk-iocost (Tejun)

 - Various cleanups (Geert, Damien, Danny, Julia, Tetsuo, Tian, Wang,
   Xianting, Yang, Yufen, yangerkun)

* tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-block: (191 commits)
  block: fix uapi blkzoned.h comments
  blk-mq: move cancel of hctx->run_work to the front of blk_exit_queue
  blk-mq: get rid of the dead flush handle code path
  block: get rid of unnecessary local variable
  block: fix comment and add lockdep assert
  blk-mq: use helper function to test hw stopped
  block: use helper function to test queue register
  block: remove redundant mq check
  block: invoke blk_mq_exit_sched no matter whether have .exit_sched
  percpu_ref: don't refer to ref->data if it isn't allocated
  block: ratelimit handle_bad_sector() message
  blk-throttle: Re-use the throtl_set_slice_end()
  blk-throttle: Open code __throtl_de/enqueue_tg()
  blk-throttle: Move service tree validation out of the throtl_rb_first()
  blk-throttle: Move the list operation after list validation
  blk-throttle: Fix IO hang for a corner case
  blk-throttle: Avoid tracking latency if low limit is invalid
  blk-throttle: Avoid getting the current time if tg->last_finish_time is 0
  blk-throttle: Remove a meaningless parameter for throtl_downgrade_state()
  block: Remove redundant 'return' statement
  ...

15 files changed, 123 insertions, 150 deletions

diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 3576123d8299..6ecf863bfa2f 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -625,7 +625,7 @@ static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
 
 	inode = file_inode(vma->vm_file);
 
-	if (!mapping_cap_writeback_dirty(inode->i_mapping))
+	if (!mapping_can_writeback(inode->i_mapping))
 		wbc.nr_to_write = 0;
 
 	might_sleep();
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 74df32be4c6a..e34fa20acf61 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -80,8 +80,10 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 	if (ret)
 		return ret;
 
-	if (v9ses->cache)
-		sb->s_bdi->ra_pages = VM_READAHEAD_PAGES;
+	if (!v9ses->cache) {
+		sb->s_bdi->ra_pages = 0;
+		sb->s_bdi->io_pages = 0;
+	}
 
 	sb->s_flags |= SB_ACTIVE | SB_DIRSYNC;
 	if (!v9ses->cache)
diff --git a/fs/afs/super.c b/fs/afs/super.c
index b552357b1d13..3a40ee752c1e 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -456,7 +456,6 @@ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx)
 	ret = super_setup_bdi(sb);
 	if (ret)
 		return ret;
-	sb->s_bdi->ra_pages	= VM_READAHEAD_PAGES;
 
 	/* allocate the root inode and dentry */
 	if (as->dyn_root) {
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 8ae833e00443..9e84b1928b94 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -103,6 +103,35 @@ void invalidate_bdev(struct block_device *bdev)
 }
 EXPORT_SYMBOL(invalidate_bdev);
 
+/*
+ * Drop all buffers & page cache for given bdev range. This function bails
+ * with error if bdev has other exclusive owner (such as filesystem).
+ */
+int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
+			loff_t lstart, loff_t lend)
+{
+	struct block_device *claimed_bdev = NULL;
+	int err;
+
+	/*
+	 * If we don't hold exclusive handle for the device, upgrade to it
+	 * while we discard the buffer cache to avoid discarding buffers
+	 * under live filesystem.
+	 */
+	if (!(mode & FMODE_EXCL)) {
+		claimed_bdev = bdev->bd_contains;
+		err = bd_prepare_to_claim(bdev, claimed_bdev,
+					  truncate_bdev_range);
+		if (err)
+			return err;
+	}
+	truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
+	if (claimed_bdev)
+		bd_abort_claiming(bdev, claimed_bdev, truncate_bdev_range);
+	return 0;
+}
+EXPORT_SYMBOL(truncate_bdev_range);
+
 static void set_init_blocksize(struct block_device *bdev)
 {
 	bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev));
@@ -862,7 +891,7 @@ static int bdev_set(struct inode *inode, void *data)
 	return 0;
 }
 
-struct block_device *bdget(dev_t dev)
+static struct block_device *bdget(dev_t dev)
 {
 	struct block_device *bdev;
 	struct inode *inode;
@@ -876,11 +905,11 @@ struct block_device *bdget(dev_t dev)
 	bdev = &BDEV_I(inode)->bdev;
 
 	if (inode->i_state & I_NEW) {
+		spin_lock_init(&bdev->bd_size_lock);
 		bdev->bd_contains = NULL;
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
 		bdev->bd_part_count = 0;
-		bdev->bd_invalidated = 0;
 		inode->i_mode = S_IFBLK;
 		inode->i_rdev = dev;
 		inode->i_bdev = bdev;
@@ -891,8 +920,6 @@ struct block_device *bdget(dev_t dev)
 	return bdev;
 }
 
-EXPORT_SYMBOL(bdget);
-
 /**
  * bdgrab -- Grab a reference to an already referenced block device
  * @bdev:	Block device to grab a reference to.
@@ -904,6 +931,11 @@ struct block_device *bdgrab(struct block_device *bdev)
 }
 EXPORT_SYMBOL(bdgrab);
 
+struct block_device *bdget_part(struct hd_struct *part)
+{
+	return bdget(part_devt(part));
+}
+
 long nr_blockdev_pages(void)
 {
 	struct inode *inode;
@@ -1290,6 +1322,7 @@ static void check_disk_size_change(struct gendisk *disk,
 {
 	loff_t disk_size, bdev_size;
 
+	spin_lock(&bdev->bd_size_lock);
 	disk_size = (loff_t)get_capacity(disk) << 9;
 	bdev_size = i_size_read(bdev->bd_inode);
 	if (disk_size != bdev_size) {
@@ -1299,85 +1332,51 @@ static void check_disk_size_change(struct gendisk *disk,
 			       disk->disk_name, bdev_size, disk_size);
 		}
 		i_size_write(bdev->bd_inode, disk_size);
-		if (bdev_size > disk_size && __invalidate_device(bdev, false))
+	}
+	spin_unlock(&bdev->bd_size_lock);
+
+	if (bdev_size > disk_size) {
+		if (__invalidate_device(bdev, false))
 			pr_warn("VFS: busy inodes on resized disk %s\n",
 				disk->disk_name);
 	}
-	bdev->bd_invalidated = 0;
 }
 
 /**
- * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
- * @disk: struct gendisk to be revalidated
+ * revalidate_disk_size - checks for disk size change and adjusts bdev size.
+ * @disk: struct gendisk to check
+ * @verbose: if %true log a message about a size change if there is any
  *
- * This routine is a wrapper for lower-level driver's revalidate_disk
- * call-backs.  It is used to do common pre and post operations needed
- * for all revalidate_disk operations.
+ * This routine checks to see if the bdev size does not match the disk size
+ * and adjusts it if it differs. When shrinking the bdev size, its all caches
+ * are freed.
  */
-int revalidate_disk(struct gendisk *disk)
+void revalidate_disk_size(struct gendisk *disk, bool verbose)
 {
-	int ret = 0;
-
-	if (disk->fops->revalidate_disk)
-		ret = disk->fops->revalidate_disk(disk);
+	struct block_device *bdev;
 
 	/*
 	 * Hidden disks don't have associated bdev so there's no point in
-	 * revalidating it.
+	 * revalidating them.
 	 */
-	if (!(disk->flags & GENHD_FL_HIDDEN)) {
-		struct block_device *bdev = bdget_disk(disk, 0);
-
-		if (!bdev)
-			return ret;
+	if (disk->flags & GENHD_FL_HIDDEN)
+		return;
 
-		mutex_lock(&bdev->bd_mutex);
-		check_disk_size_change(disk, bdev, ret == 0);
-		mutex_unlock(&bdev->bd_mutex);
+	bdev = bdget_disk(disk, 0);
+	if (bdev) {
+		check_disk_size_change(disk, bdev, verbose);
 		bdput(bdev);
 	}
-	return ret;
 }
-EXPORT_SYMBOL(revalidate_disk);
+EXPORT_SYMBOL(revalidate_disk_size);
 
-/*
- * This routine checks whether a removable media has been changed,
- * and invalidates all buffer-cache-entries in that case. This
- * is a relatively slow routine, so we have to try to minimize using
- * it. Thus it is called only upon a 'mount' or 'open'. This
- * is the best way of combining speed and utility, I think.
- * People changing diskettes in the middle of an operation deserve
- * to lose :-)
- */
-int check_disk_change(struct block_device *bdev)
+void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 {
-	struct gendisk *disk = bdev->bd_disk;
-	const struct block_device_operations *bdops = disk->fops;
-	unsigned int events;
-
-	events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE |
-				   DISK_EVENT_EJECT_REQUEST);
-	if (!(events & DISK_EVENT_MEDIA_CHANGE))
-		return 0;
-
-	if (__invalidate_device(bdev, true))
-		pr_warn("VFS: busy inodes on changed media %s\n",
-			disk->disk_name);
-	bdev->bd_invalidated = 1;
-	if (bdops->revalidate_disk)
-		bdops->revalidate_disk(bdev->bd_disk);
-	return 1;
-}
-
-EXPORT_SYMBOL(check_disk_change);
-
-void bd_set_size(struct block_device *bdev, loff_t size)
-{
-	inode_lock(bdev->bd_inode);
-	i_size_write(bdev->bd_inode, size);
-	inode_unlock(bdev->bd_inode);
+	spin_lock(&bdev->bd_size_lock);
+	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
+	spin_unlock(&bdev->bd_size_lock);
 }
-EXPORT_SYMBOL(bd_set_size);
+EXPORT_SYMBOL(bd_set_nr_sectors);
 
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
@@ -1388,6 +1387,8 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate)
 
 	lockdep_assert_held(&bdev->bd_mutex);
 
+	clear_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
+
 rescan:
 	ret = blk_drop_partitions(bdev);
 	if (ret)
@@ -1446,22 +1447,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 	struct gendisk *disk;
 	int ret;
 	int partno;
-	int perm = 0;
 	bool first_open = false, unblock_events = true, need_restart;
 
-	if (mode & FMODE_READ)
-		perm |= MAY_READ;
-	if (mode & FMODE_WRITE)
-		perm |= MAY_WRITE;
-	/*
-	 * hooks: /n/, see "layering violations".
-	 */
-	if (!for_part) {
-		ret = devcgroup_inode_permission(bdev->bd_inode, perm);
-		if (ret != 0)
-			return ret;
-	}
-
  restart:
 	need_restart = false;
 	ret = -ENXIO;
@@ -1514,7 +1501,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			}
 
 			if (!ret) {
-				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
+				bd_set_nr_sectors(bdev, get_capacity(disk));
 				set_init_blocksize(bdev);
 			}
 
@@ -1524,7 +1511,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			 * The latter is necessary to prevent ghost
 			 * partitions on a removed medium.
 			 */
-			if (bdev->bd_invalidated &&
+			if (test_bit(GD_NEED_PART_SCAN, &disk->state) &&
 			    (!ret || ret == -ENOMEDIUM))
 				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 
@@ -1542,7 +1529,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 				ret = -ENXIO;
 				goto out_clear;
 			}
-			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
+			bd_set_nr_sectors(bdev, bdev->bd_part->nr_sects);
 			set_init_blocksize(bdev);
 		}
 
@@ -1554,7 +1541,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
 			/* the same as first opener case, read comment there */
-			if (bdev->bd_invalidated &&
+			if (test_bit(GD_NEED_PART_SCAN, &disk->state) &&
 			    (!ret || ret == -ENOMEDIUM))
 				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 			if (ret)
@@ -1632,16 +1619,27 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
  * RETURNS:
  * 0 on success, -errno on failure.
  */
-int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
+static int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 {
-	int res;
+	int ret, perm = 0;
 
-	res =__blkdev_get(bdev, mode, holder, 0);
-	if (res)
-		bdput(bdev);
-	return res;
+	if (mode & FMODE_READ)
+		perm |= MAY_READ;
+	if (mode & FMODE_WRITE)
+		perm |= MAY_WRITE;
+	ret = devcgroup_inode_permission(bdev->bd_inode, perm);
+	if (ret)
+		goto bdput;
+
+	ret =__blkdev_get(bdev, mode, holder, 0);
+	if (ret)
+		goto bdput;
+	return 0;
+
+bdput:
+	bdput(bdev);
+	return ret;
 }
-EXPORT_SYMBOL(blkdev_get);
 
 /**
  * blkdev_get_by_path - open a block device by name
@@ -1889,7 +1887,7 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (bdev_read_only(I_BDEV(bd_inode)))
 		return -EPERM;
 
-	if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode))
+	if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev))
 		return -ETXTBSY;
 
 	if (!iov_iter_count(from))
@@ -1969,7 +1967,6 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 			     loff_t len)
 {
 	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
-	struct address_space *mapping;
 	loff_t end = start + len - 1;
 	loff_t isize;
 	int error;
@@ -1997,8 +1994,9 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 		return -EINVAL;
 
 	/* Invalidate the page cache, including dirty pages. */
-	mapping = bdev->bd_inode->i_mapping;
-	truncate_inode_pages_range(mapping, start, end);
+	error = truncate_bdev_range(bdev, file->f_mode, start, end);
+	if (error)
+		return error;
 
 	switch (mode) {
 	case FALLOC_FL_ZERO_RANGE:
@@ -2025,7 +2023,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 	 * the caller will be given -EBUSY.  The third argument is
 	 * inclusive, so the rounding here is safe.
 	 */
-	return invalidate_inode_pages2_range(mapping,
+	return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping,
 					     start >> PAGE_SHIFT,
 					     end >> PAGE_SHIFT);
 }
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 764001609a15..8e3438672a82 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3032,8 +3032,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_sb_buffer;
 	}
 
-	sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
-	sb->s_bdi->ra_pages = VM_READAHEAD_PAGES;
 	sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super);
 	sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE);
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 50bbc99e3d96..5a28a6aa7f16 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2771,16 +2771,6 @@ int nobh_writepage(struct page *page, get_block_t *get_block,
 	/* Is the page fully outside i_size? (truncate in progress) */
 	offset = i_size & (PAGE_SIZE-1);
 	if (page->index >= end_index+1 || !offset) {
-		/*
-		 * The page may have dirty, unmapped buffers.  For example,
-		 * they may have been added in ext3_writepage().  Make them
-		 * freeable here, so the page does not leak.
-		 */
-#if 0
-		/* Not really sure about this  - do we need this ? */
-		if (page->mapping->a_ops->invalidatepage)
-			page->mapping->a_ops->invalidatepage(page, offset);
-#endif
 		unlock_page(page);
 		return 0; /* don't care */
 	}
@@ -2975,12 +2965,6 @@ int block_write_full_page(struct page *page, get_block_t *get_block,
 	/* Is the page fully outside i_size? (truncate in progress) */
 	offset = i_size & (PAGE_SIZE-1);
 	if (page->index >= end_index+1 || !offset) {
-		/*
-		 * The page may have dirty, unmapped buffers.  For example,
-		 * they may have been added in ext3_writepage().  Make them
-		 * freeable here, so the page does not leak.
-		 */
-		do_invalidatepage(page, 0, PAGE_SIZE);
 		unlock_page(page);
 		return 0; /* don't care */
 	}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 58b27e4070a3..e6005c78bfa9 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2321,7 +2321,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 
 			wb = locked_inode_to_wb_and_lock_list(inode);
 
-			WARN(bdi_cap_writeback_dirty(wb->bdi) &&
+			WARN((wb->bdi->capabilities & BDI_CAP_WRITEBACK) &&
 			     !test_bit(WB_registered, &wb->state),
 			     "bdi-%s not registered\n", bdi_dev_name(wb->bdi));
 
@@ -2346,7 +2346,8 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			 * to make sure background write-back happens
 			 * later.
 			 */
-			if (bdi_cap_writeback_dirty(wb->bdi) && wakeup_bdi)
+			if (wakeup_bdi &&
+			    (wb->bdi->capabilities & BDI_CAP_WRITEBACK))
 				wb_wakeup_delayed(wb);
 			return;
 		}
@@ -2581,7 +2582,7 @@ int write_inode_now(struct inode *inode, int sync)
 		.range_end = LLONG_MAX,
 	};
 
-	if (!mapping_cap_writeback_dirty(inode->i_mapping))
+	if (!mapping_can_writeback(inode->i_mapping))
 		wbc.nr_to_write = 0;
 
 	might_sleep();
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index bba747520e9b..581329203d68 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1049,9 +1049,9 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
 	if (err)
 		return err;
 
-	sb->s_bdi->ra_pages = VM_READAHEAD_PAGES;
 	/* fuse does it's own writeback accounting */
-	sb->s_bdi->capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT;
+	sb->s_bdi->capabilities &= ~BDI_CAP_WRITEBACK_ACCT;
+	sb->s_bdi->capabilities |= BDI_CAP_STRICTLIMIT;
 
 	/*
 	 * For a single fuse filesystem use max 1% of dirty +
diff --git a/fs/namei.c b/fs/namei.c
index e99e2a9da0f7..f1eb8ccd2be9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -568,8 +568,8 @@ static bool path_connected(struct vfsmount *mnt, struct dentry *dentry)
 {
 	struct super_block *sb = mnt->mnt_sb;
 
-	/* Bind mounts and multi-root filesystems can have disconnected paths */
-	if (!(sb->s_iflags & SB_I_MULTIROOT) && (mnt->mnt_root == sb->s_root))
+	/* Bind mounts can have disconnected paths */
+	if (mnt->mnt_root == sb->s_root)
 		return true;
 
 	return is_subdir(dentry, mnt->mnt_root);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 7a70287f21a2..f943e37853fa 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1200,13 +1200,6 @@ static void nfs_get_cache_cookie(struct super_block *sb,
 }
 #endif
 
-static void nfs_set_readahead(struct backing_dev_info *bdi,
-			      unsigned long iomax_pages)
-{
-	bdi->ra_pages = VM_READAHEAD_PAGES;
-	bdi->io_pages = iomax_pages;
-}
-
 int nfs_get_tree_common(struct fs_context *fc)
 {
 	struct nfs_fs_context *ctx = nfs_fc2context(fc);
@@ -1251,7 +1244,7 @@ int nfs_get_tree_common(struct fs_context *fc)
 					     MINOR(server->s_dev));
 		if (error)
 			goto error_splat_super;
-		nfs_set_readahead(s->s_bdi, server->rpages);
+		s->s_bdi->io_pages = server->rpages;
 		server->super = s;
 	}
 
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 311e5ce80cfc..a07c39c94bbd 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -170,7 +170,7 @@ nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
 		struct nfs4_client *clp,
 		struct nfsd4_getdeviceinfo *gdp)
 {
-	if (sb->s_bdev != sb->s_bdev->bd_contains)
+	if (bdev_is_partition(sb->s_bdev))
 		return nfserr_inval;
 	return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp));
 }
@@ -382,7 +382,7 @@ nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb,
 		struct nfs4_client *clp,
 		struct nfsd4_getdeviceinfo *gdp)
 {
-	if (sb->s_bdev != sb->s_bdev->bd_contains)
+	if (bdev_is_partition(sb->s_bdev))
 		return nfserr_inval;
 	return nfserrno(nfsd4_block_get_device_info_scsi(sb, clp, gdp));
 }
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 89d13e0705fe..0179a73a3fa2 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1766,7 +1766,6 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
 	int sectsize;
 	char *p = (char *)page;
 	struct fd f;
-	struct inode *inode;
 	ssize_t ret = -EINVAL;
 	int live_threshold;
 
@@ -1793,20 +1792,16 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
 	    reg->hr_block_bytes == 0)
 		goto out2;
 
-	inode = igrab(f.file->f_mapping->host);
-	if (inode == NULL)
+	if (!S_ISBLK(f.file->f_mapping->host->i_mode))
 		goto out2;
 
-	if (!S_ISBLK(inode->i_mode))
-		goto out3;
-
-	reg->hr_bdev = I_BDEV(f.file->f_mapping->host);
-	ret = blkdev_get(reg->hr_bdev, FMODE_WRITE | FMODE_READ, NULL);
-	if (ret) {
+	reg->hr_bdev = blkdev_get_by_dev(f.file->f_mapping->host->i_rdev,
+					 FMODE_WRITE | FMODE_READ, NULL);
+	if (IS_ERR(reg->hr_bdev)) {
+		ret = PTR_ERR(reg->hr_bdev);
 		reg->hr_bdev = NULL;
-		goto out3;
+		goto out2;
 	}
-	inode = NULL;
 
 	bdevname(reg->hr_bdev, reg->hr_dev_name);
 
@@ -1909,16 +1904,13 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
 		       config_item_name(&reg->hr_item), reg->hr_dev_name);
 
 out3:
-	iput(inode);
+	if (ret < 0) {
+		blkdev_put(reg->hr_bdev, FMODE_READ | FMODE_WRITE);
+		reg->hr_bdev = NULL;
+	}
 out2:
 	fdput(f);
 out:
-	if (ret < 0) {
-		if (reg->hr_bdev) {
-			blkdev_put(reg->hr_bdev, FMODE_READ|FMODE_WRITE);
-			reg->hr_bdev = NULL;
-		}
-	}
 	return ret;
 }
 
diff --git a/fs/super.c b/fs/super.c
index 904459b35119..a51c2083cd6b 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1256,6 +1256,8 @@ static int set_bdev_super(struct super_block *s, void *data)
 	s->s_dev = s->s_bdev->bd_dev;
 	s->s_bdi = bdi_get(s->s_bdev->bd_bdi);
 
+	if (blk_queue_stable_writes(s->s_bdev->bd_disk->queue))
+		s->s_iflags |= SB_I_STABLE_WRITES;
 	return 0;
 }
 
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index a2420c900275..fbddb2a1c03f 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -2177,6 +2177,8 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 				   c->vi.vol_id);
 	if (err)
 		goto out_close;
+	sb->s_bdi->ra_pages = 0;
+	sb->s_bdi->io_pages = 0;
 
 	sb->s_fs_info = c;
 	sb->s_magic = UBIFS_SUPER_MAGIC;
diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c
index 25aade344192..d7816c01a4f6 100644
--- a/fs/vboxsf/super.c
+++ b/fs/vboxsf/super.c
@@ -167,6 +167,8 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc)
 	err = super_setup_bdi_name(sb, "vboxsf-%d", sbi->bdi_id);
 	if (err)
 		goto fail_free;
+	sb->s_bdi->ra_pages = 0;
+	sb->s_bdi->io_pages = 0;
 
 	/* Turn source into a shfl_string and map the folder */
 	size = strlen(fc->source) + 1;