Merge tag 'xfs-4.18-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/x…

…fs-linux

Pull xfs updates from Darrick Wong:
 "New features this cycle include the ability to relabel mounted
  filesystems, support for fallocated swapfiles, and using FUA for pure
  data O_DSYNC directio writes. With this cycle we begin to integrate
  online filesystem repair and refactor the growfs code in preparation
  for eventual subvolume support, though the road ahead for both
  features is quite long.

  There are also numerous refactorings of the iomap code to remove
  unnecessary log overhead, to disentangle some of the quota code, and
  to prepare for buffer head removal in a future upstream kernel.

  Metadata validation continues to improve, both in the hot path
  veifiers and the online filesystem check code. I anticipate sending a
  second pull request in a few days with more metadata validation
  improvements.

  This series has been run through a full xfstests run over the weekend
  and through a quick xfstests run against this morning's master, with
  no major failures reported.

  Summary:

   - Strengthen inode number and structure validation when allocating
     inodes.

   - Reduce pointless buffer allocations during cache miss

   - Use FUA for pure data O_DSYNC directio writes

   - Various iomap refactorings

   - Strengthen quota metadata verification to avoid unfixable broken
     quota

   - Make AGFL block freeing a deferred operation to avoid blowing out
     transaction reservations when running complex operations

   - Get rid of the log item descriptors to reduce log overhead

   - Fix various reflink bugs where inodes were double-joined to
     transactions

   - Don't issue discards when trimming unwritten extents

   - Refactor incore dquot initialization and retrieval interfaces

   - Fix some locking problmes in the quota scrub code

   - Strengthen btree structure checks in scrub code

   - Rewrite swapfile activation to use iomap and support unwritten
     extents

   - Make scrub exit to userspace sooner when corruptions or
     cross-referencing problems are found

   - Make scrub invoke the data fork scrubber directly on metadata
     inodes

   - Don't do background reclamation of post-eof and cow blocks when the
     fs is suspended

   - Fix secondary superblock buffer lifespan hinting

   - Refactor growfs to use table-dispatched functions instead of long
     stringy functions

   - Move growfs code to libxfs

   - Implement online fs label getting and setting

   - Introduce online filesystem repair (in a very limited capacity)

   - Fix unit conversion problems in the realtime freemap iteration
     functions

   - Various refactorings and cleanups in preparation to remove buffer
     heads in a future release

   - Reimplement the old bmap call with iomap

   - Remove direct buffer head accesses from seek hole/data

   - Various bug fixes"

* tag 'xfs-4.18-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (121 commits)
  fs: use ->is_partially_uptodate in page_cache_seek_hole_data
  fs: remove the buffer_unwritten check in page_seek_hole_data
  fs: move page_cache_seek_hole_data to iomap.c
  xfs: use iomap_bmap
  iomap: add an iomap-based bmap implementation
  iomap: add a iomap_sector helper
  iomap: use __bio_add_page in iomap_dio_zero
  iomap: move IOMAP_F_BOUNDARY to gfs2
  iomap: fix the comment describing IOMAP_NOWAIT
  iomap: inline data should be an iomap type, not a flag
  mm: split ->readpages calls to avoid non-contiguous pages lists
  mm: return an unsigned int from __do_page_cache_readahead
  mm: give the 'ret' variable a better name __do_page_cache_readahead
  block: add a lower-level bio_add_page interface
  xfs: fix error handling in xfs_refcount_insert()
  xfs: fix xfs_rtalloc_rec units
  xfs: strengthen rtalloc query range checks
  xfs: xfs_rtbuf_get should check the bmapi_read results
  xfs: xfs_rtword_t should be unsigned, not signed
  dax: change bdev_dax_supported() to support boolean returns
  ...

Documentation/ioctl/ioctl-number.txt

@@ -296,7 +296,8 @@ Code  Seq#(hex)	Include File		Comments
 0x90	00	drivers/cdrom/sbpcd.h
 0x92	00-0F	drivers/usb/mon/mon_bin.c
 0x93	60-7F	linux/auto_fs.h
-0x94	all	fs/btrfs/ioctl.h
+0x94	all	fs/btrfs/ioctl.h	Btrfs filesystem
+		and linux/fs.h		some lifted to vfs/generic
 0x97	00-7F	fs/ceph/ioctl.h		Ceph file system
 0x99	00-0F				537-Addinboard driver
 					<mailto:buk@buks.ipn.de>

block/bio.c

@@ -774,7 +774,7 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
 			return 0;
 	}
 
-	if (bio->bi_vcnt >= bio->bi_max_vecs)
+	if (bio_full(bio))
 		return 0;
 
 	/*
@@ -822,52 +822,82 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
 EXPORT_SYMBOL(bio_add_pc_page);
 
 /**
- *	bio_add_page	-	attempt to add page to bio
- *	@bio: destination bio
- *	@page: page to add
- *	@len: vec entry length
- *	@offset: vec entry offset
+ * __bio_try_merge_page - try appending data to an existing bvec.
+ * @bio: destination bio
+ * @page: page to add
+ * @len: length of the data to add
+ * @off: offset of the data in @page
  *
- *	Attempt to add a page to the bio_vec maplist. This will only fail
- *	if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio.
+ * Try to add the data at @page + @off to the last bvec of @bio.  This is a
+ * a useful optimisation for file systems with a block size smaller than the
+ * page size.
+ *
+ * Return %true on success or %false on failure.
  */
-int bio_add_page(struct bio *bio, struct page *page,
-		 unsigned int len, unsigned int offset)
+bool __bio_try_merge_page(struct bio *bio, struct page *page,
+		unsigned int len, unsigned int off)
 {
-	struct bio_vec *bv;
-
-	/*
-	 * cloned bio must not modify vec list
-	 */
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
-		return 0;
+		return false;
 
-	/*
-	 * For filesystems with a blocksize smaller than the pagesize
-	 * we will often be called with the same page as last time and
-	 * a consecutive offset.  Optimize this special case.
-	 */
 	if (bio->bi_vcnt > 0) {
-		bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
-		if (page == bv->bv_page &&
-		    offset == bv->bv_offset + bv->bv_len) {
+		if (page == bv->bv_page && off == bv->bv_offset + bv->bv_len) {
 			bv->bv_len += len;
-			goto done;
+			bio->bi_iter.bi_size += len;
+			return true;
 		}
 	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(__bio_try_merge_page);
 
-	if (bio->bi_vcnt >= bio->bi_max_vecs)
-		return 0;
+/**
+ * __bio_add_page - add page to a bio in a new segment
+ * @bio: destination bio
+ * @page: page to add
+ * @len: length of the data to add
+ * @off: offset of the data in @page
+ *
+ * Add the data at @page + @off to @bio as a new bvec.  The caller must ensure
+ * that @bio has space for another bvec.
+ */
+void __bio_add_page(struct bio *bio, struct page *page,
+		unsigned int len, unsigned int off)
+{
+	struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt];
 
-	bv		= &bio->bi_io_vec[bio->bi_vcnt];
-	bv->bv_page	= page;
-	bv->bv_len	= len;
-	bv->bv_offset	= offset;
+	WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
+	WARN_ON_ONCE(bio_full(bio));
+
+	bv->bv_page = page;
+	bv->bv_offset = off;
+	bv->bv_len = len;
 
-	bio->bi_vcnt++;
-done:
 	bio->bi_iter.bi_size += len;
+	bio->bi_vcnt++;
+}
+EXPORT_SYMBOL_GPL(__bio_add_page);
+
+/**
+ *	bio_add_page	-	attempt to add page to bio
+ *	@bio: destination bio
+ *	@page: page to add
+ *	@len: vec entry length
+ *	@offset: vec entry offset
+ *
+ *	Attempt to add a page to the bio_vec maplist. This will only fail
+ *	if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio.
+ */
+int bio_add_page(struct bio *bio, struct page *page,
+		 unsigned int len, unsigned int offset)
+{
+	if (!__bio_try_merge_page(bio, page, len, offset)) {
+		if (bio_full(bio))
+			return 0;
+		__bio_add_page(bio, page, len, offset);
+	}
 	return len;
 }
 EXPORT_SYMBOL(bio_add_page);

drivers/dax/super.c

@@ -74,42 +74,42 @@ EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
 
 /**
  * __bdev_dax_supported() - Check if the device supports dax for filesystem
- * @sb: The superblock of the device
+ * @bdev: block device to check
  * @blocksize: The block size of the device
  *
  * This is a library function for filesystems to check if the block device
  * can be mounted with dax option.
  *
- * Return: negative errno if unsupported, 0 if supported.
+ * Return: true if supported, false if unsupported
  */
-int __bdev_dax_supported(struct super_block *sb, int blocksize)
+bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 {
-	struct block_device *bdev = sb->s_bdev;
 	struct dax_device *dax_dev;
 	pgoff_t pgoff;
 	int err, id;
 	void *kaddr;
 	pfn_t pfn;
 	long len;
+	char buf[BDEVNAME_SIZE];
 
 	if (blocksize != PAGE_SIZE) {
-		pr_debug("VFS (%s): error: unsupported blocksize for dax\n",
-				sb->s_id);
-		return -EINVAL;
+		pr_debug("%s: error: unsupported blocksize for dax\n",
+				bdevname(bdev, buf));
+		return false;
 	}
 
 	err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
 	if (err) {
-		pr_debug("VFS (%s): error: unaligned partition for dax\n",
-				sb->s_id);
-		return err;
+		pr_debug("%s: error: unaligned partition for dax\n",
+				bdevname(bdev, buf));
+		return false;
 	}
 
 	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
 	if (!dax_dev) {
-		pr_debug("VFS (%s): error: device does not support dax\n",
-				sb->s_id);
-		return -EOPNOTSUPP;
+		pr_debug("%s: error: device does not support dax\n",
+				bdevname(bdev, buf));
+		return false;
 	}
 
 	id = dax_read_lock();
@@ -119,9 +119,9 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
 	put_dax(dax_dev);
 
 	if (len < 1) {
-		pr_debug("VFS (%s): error: dax access failed (%ld)\n",
-				sb->s_id, len);
-		return len < 0 ? len : -EIO;
+		pr_debug("%s: error: dax access failed (%ld)\n",
+				bdevname(bdev, buf), len);
+		return false;
 	}
 
 	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED) && pfn_t_special(pfn)) {
@@ -137,12 +137,12 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
 	} else if (pfn_t_devmap(pfn)) {
 		/* pass */;
 	} else {
-		pr_debug("VFS (%s): error: dax support not enabled\n",
-				sb->s_id);
-		return -EOPNOTSUPP;
+		pr_debug("%s: error: dax support not enabled\n",
+				bdevname(bdev, buf));
+		return false;
 	}
 
-	return 0;
+	return true;
 }
 EXPORT_SYMBOL_GPL(__bdev_dax_supported);
 #endif

fs/buffer.c

@@ -3427,120 +3427,6 @@ int bh_submit_read(struct buffer_head *bh)
 }
 EXPORT_SYMBOL(bh_submit_read);
 
-/*
- * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff.
- *
- * Returns the offset within the file on success, and -ENOENT otherwise.
- */
-static loff_t
-page_seek_hole_data(struct page *page, loff_t lastoff, int whence)
-{
-	loff_t offset = page_offset(page);
-	struct buffer_head *bh, *head;
-	bool seek_data = whence == SEEK_DATA;
-
-	if (lastoff < offset)
-		lastoff = offset;
-
-	bh = head = page_buffers(page);
-	do {
-		offset += bh->b_size;
-		if (lastoff >= offset)
-			continue;
-
-		/*
-		 * Unwritten extents that have data in the page cache covering
-		 * them can be identified by the BH_Unwritten state flag.
-		 * Pages with multiple buffers might have a mix of holes, data
-		 * and unwritten extents - any buffer with valid data in it
-		 * should have BH_Uptodate flag set on it.
-		 */
-
-		if ((buffer_unwritten(bh) || buffer_uptodate(bh)) == seek_data)
-			return lastoff;
-
-		lastoff = offset;
-	} while ((bh = bh->b_this_page) != head);
-	return -ENOENT;
-}
-
-/*
- * Seek for SEEK_DATA / SEEK_HOLE in the page cache.
- *
- * Within unwritten extents, the page cache determines which parts are holes
- * and which are data: unwritten and uptodate buffer heads count as data;
- * everything else counts as a hole.
- *
- * Returns the resulting offset on successs, and -ENOENT otherwise.
- */
-loff_t
-page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
-			  int whence)
-{
-	pgoff_t index = offset >> PAGE_SHIFT;
-	pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE);
-	loff_t lastoff = offset;
-	struct pagevec pvec;
-
-	if (length <= 0)
-		return -ENOENT;
-
-	pagevec_init(&pvec);
-
-	do {
-		unsigned nr_pages, i;
-
-		nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, &index,
-						end - 1);
-		if (nr_pages == 0)
-			break;
-
-		for (i = 0; i < nr_pages; i++) {
-			struct page *page = pvec.pages[i];
-
-			/*
-			 * At this point, the page may be truncated or
-			 * invalidated (changing page->mapping to NULL), or
-			 * even swizzled back from swapper_space to tmpfs file
-			 * mapping.  However, page->index will not change
-			 * because we have a reference on the page.
-                         *
-			 * If current page offset is beyond where we've ended,
-			 * we've found a hole.
-                         */
-			if (whence == SEEK_HOLE &&
-			    lastoff < page_offset(page))
-				goto check_range;
-
-			lock_page(page);
-			if (likely(page->mapping == inode->i_mapping) &&
-			    page_has_buffers(page)) {
-				lastoff = page_seek_hole_data(page, lastoff, whence);
-				if (lastoff >= 0) {
-					unlock_page(page);
-					goto check_range;
-				}
-			}
-			unlock_page(page);
-			lastoff = page_offset(page) + PAGE_SIZE;
-		}
-		pagevec_release(&pvec);
-	} while (index < end);
-
-	/* When no page at lastoff and we are not done, we found a hole. */
-	if (whence != SEEK_HOLE)
-		goto not_found;
-
-check_range:
-	if (lastoff < offset + length)
-		goto out;
-not_found:
-	lastoff = -ENOENT;
-out:
-	pagevec_release(&pvec);
-	return lastoff;
-}
-
 void __init buffer_init(void)
 {
 	unsigned long nrpages;

fs/ext2/super.c

@@ -961,8 +961,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
 
 	if (sbi->s_mount_opt & EXT2_MOUNT_DAX) {
-		err = bdev_dax_supported(sb, blocksize);
-		if (err) {
+		if (!bdev_dax_supported(sb->s_bdev, blocksize)) {
 			ext2_msg(sb, KERN_ERR,
 				"DAX unsupported by block device. Turning off DAX.");
 			sbi->s_mount_opt &= ~EXT2_MOUNT_DAX;

fs/ext4/inline.c

@@ -1841,8 +1841,8 @@ int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap)
 	iomap->offset = 0;
 	iomap->length = min_t(loff_t, ext4_get_inline_size(inode),
 			      i_size_read(inode));
-	iomap->type = 0;
-	iomap->flags = IOMAP_F_DATA_INLINE;
+	iomap->type = IOMAP_INLINE;
+	iomap->flags = 0;
 
 out:
 	up_read(&EXT4_I(inode)->xattr_sem);

fs/ext4/super.c

@@ -3762,8 +3762,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 					" that may contain inline data");
 			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX;
 		}
-		err = bdev_dax_supported(sb, blocksize);
-		if (err) {
+		if (!bdev_dax_supported(sb->s_bdev, blocksize)) {
 			ext4_msg(sb, KERN_ERR,
 				"DAX unsupported by block device. Turning off DAX.");
 			sbi->s_mount_opt &= ~EXT4_MOUNT_DAX;