Merge patch series "enable bs > ps for block devices"

Luis Chamberlain <mcgrof@kernel.org> says:

This v3 series addresses the feedback from the v2 series [0]. The only
patch which was mofified was the patch titled "fs/mpage: use blocks_per_folio
instead of blocks_per_page". The motivation for this series is to mainly
start supporting block devices with logical block sizes larger than 4k,
we do this by addressing buffer-head support required for the block
device cache.

In the future these changes can be leveraged to also start experimenting
with LBS support for filesystems which support only buffer-heads. This
paves the way for that work.

Its perhaps is surprising to some but since this also lifts the block
device cache sector size support to 64k, devices which support up to
64k sector sizes can also leverage this to enable filesystems created with
larger sector sizes up to 64k sector sizes. The filesystem sector size
is used or documented in a bit of obscurity except for few filesystems,
but in short it ensures that the filesystem itself will not generate
writes iteslef smaller than the specified sector size. In practice this
means you can constrain metadata writes as well to a minimum size, and
so be completely deterministic with regards to the specified sector size
for min IO writes. For example since XFS can supports up to 32k sector size,
it means with these changes enable filesystems to also be created on x86_64
with both the filesystem block size and sector size to 32k, now that the block
device cache limitation is lifted.

Since this touches buffer-heads I've ran this through fstests on ext4
and found no new regressions. I've also used blktests against a kernel
built with these changes to test block devices with different larger logical
block sizes than 4k on x86_64. All changes to be able to test block
devices with a logical block size support > 4k are now merged on
upstream blktests.  I've tested the block layer with blktests with block
devices with logical block sizes up to 64k which is the max we are
currently supporting and found no new regressions.

Detailed changes in this series:

  - Modifies the commit log for "fs/buffer: remove batching from async
    read" as per Willy's request and collects his SOB.
  - Collects Reviewed-by tags
  - The patch titled "fs/mpage: use blocks_per_folio instead of blocks_per_page"
    received more love to account for Willy's point
    that we should keep accounting in order for nr_pages on mpage. This
    does this by using folio_nr_pages() on the args passed and adjusts
    the last_block accounting accordingly.
  - Through code inspection fixed folio_zero_segment() use to use
    folio_size() as we move to suppor large folios for unmapped
    folio segments on do_mpage_readpage(), this is dealt with on the
    patch titled "fs/mpage: use blocks_per_folio instead of blocks_per_page"
    as that's when we start accounting large folios into the picture.

[0] https://lkml.kernel.org/r/20250204231209.429356-1-mcgrof@kernel.org

* patches from https://lore.kernel.org/r/20250221223823.1680616-1-mcgrof@kernel.org:
  bdev: use bdev_io_min() for statx block size
  block/bdev: lift block size restrictions to 64k
  block/bdev: enable large folio support for large logical block sizes
  fs/buffer fs/mpage: remove large folio restriction
  fs/mpage: use blocks_per_folio instead of blocks_per_page
  fs/mpage: avoid negative shift for large blocksize
  fs/buffer: remove batching from async read
  fs/buffer: simplify block_read_full_folio() with bh_offset()

Link: https://lore.kernel.org/r/20250221223823.1680616-1-mcgrof@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

Author: brauner

block/bdev.c

@@ -148,6 +148,8 @@ static void set_init_blocksize(struct block_device *bdev)
 		bsize <<= 1;
 	}
 	BD_INODE(bdev)->i_blkbits = blksize_bits(bsize);
+	mapping_set_folio_min_order(BD_INODE(bdev)->i_mapping,
+				    get_order(bsize));
 }
 
 int set_blocksize(struct file *file, int size)
@@ -169,6 +171,7 @@ int set_blocksize(struct file *file, int size)
 	if (inode->i_blkbits != blksize_bits(size)) {
 		sync_blockdev(bdev);
 		inode->i_blkbits = blksize_bits(size);
+		mapping_set_folio_min_order(inode->i_mapping, get_order(size));
 		kill_bdev(bdev);
 	}
 	return 0;
@@ -180,8 +183,7 @@ int sb_set_blocksize(struct super_block *sb, int size)
 {
 	if (set_blocksize(sb->s_bdev_file, size))
 		return 0;
-	/* If we get here, we know size is power of two
-	 * and it's value is between 512 and PAGE_SIZE */
+	/* If we get here, we know size is validated */
 	sb->s_blocksize = size;
 	sb->s_blocksize_bits = blksize_bits(size);
 	return sb->s_blocksize;
@@ -1274,9 +1276,6 @@ void bdev_statx(struct path *path, struct kstat *stat,
 	struct inode *backing_inode;
 	struct block_device *bdev;
 
-	if (!(request_mask & (STATX_DIOALIGN | STATX_WRITE_ATOMIC)))
-		return;
-
 	backing_inode = d_backing_inode(path->dentry);
 
 	/*
@@ -1303,6 +1302,8 @@ void bdev_statx(struct path *path, struct kstat *stat,
 			queue_atomic_write_unit_max_bytes(bd_queue));
 	}
 
+	stat->blksize = bdev_io_min(bdev);
+
 	blkdev_put_no_open(bdev);
 }
 

fs/buffer.c

@@ -2361,9 +2361,8 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
 {
 	struct inode *inode = folio->mapping->host;
 	sector_t iblock, lblock;
-	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
+	struct buffer_head *bh, *head, *prev = NULL;
 	size_t blocksize;
-	int nr, i;
 	int fully_mapped = 1;
 	bool page_error = false;
 	loff_t limit = i_size_read(inode);
@@ -2372,16 +2371,12 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
 	if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode))
 		limit = inode->i_sb->s_maxbytes;
 
-	VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
-
 	head = folio_create_buffers(folio, inode, 0);
 	blocksize = head->b_size;
 
 	iblock = div_u64(folio_pos(folio), blocksize);
 	lblock = div_u64(limit + blocksize - 1, blocksize);
 	bh = head;
-	nr = 0;
-	i = 0;
 
 	do {
 		if (buffer_uptodate(bh))
@@ -2398,7 +2393,7 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
 					page_error = true;
 			}
 			if (!buffer_mapped(bh)) {
-				folio_zero_range(folio, i * blocksize,
+				folio_zero_range(folio, bh_offset(bh),
 						blocksize);
 				if (!err)
 					set_buffer_uptodate(bh);
@@ -2411,40 +2406,33 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
 			if (buffer_uptodate(bh))
 				continue;
 		}
-		arr[nr++] = bh;
-	} while (i++, iblock++, (bh = bh->b_this_page) != head);
-
-	if (fully_mapped)
-		folio_set_mappedtodisk(folio);
-
-	if (!nr) {
-		/*
-		 * All buffers are uptodate or get_block() returned an
-		 * error when trying to map them - we can finish the read.
-		 */
-		folio_end_read(folio, !page_error);
-		return 0;
-	}
 
-	/* Stage two: lock the buffers */
-	for (i = 0; i < nr; i++) {
-		bh = arr[i];
 		lock_buffer(bh);
+		if (buffer_uptodate(bh)) {
+			unlock_buffer(bh);
+			continue;
+		}
+
 		mark_buffer_async_read(bh);
-	}
+		if (prev)
+			submit_bh(REQ_OP_READ, prev);
+		prev = bh;
+	} while (iblock++, (bh = bh->b_this_page) != head);
+
+	if (fully_mapped)
+		folio_set_mappedtodisk(folio);
 
 	/*
-	 * Stage 3: start the IO.  Check for uptodateness
-	 * inside the buffer lock in case another process reading
-	 * the underlying blockdev brought it uptodate (the sct fix).
+	 * All buffers are uptodate or get_block() returned an error
+	 * when trying to map them - we must finish the read because
+	 * end_buffer_async_read() will never be called on any buffer
+	 * in this folio.
 	 */
-	for (i = 0; i < nr; i++) {
-		bh = arr[i];
-		if (buffer_uptodate(bh))
-			end_buffer_async_read(bh, 1);
-		else
-			submit_bh(REQ_OP_READ, bh);
-	}
+	if (prev)
+		submit_bh(REQ_OP_READ, prev);
+	else
+		folio_end_read(folio, !page_error);
+
 	return 0;
 }
 EXPORT_SYMBOL(block_read_full_folio);

fs/mpage.c

@@ -107,7 +107,7 @@ static void map_buffer_to_folio(struct folio *folio, struct buffer_head *bh,
 		 * don't make any buffers if there is only one buffer on
 		 * the folio and the folio just needs to be set up to date
 		 */
-		if (inode->i_blkbits == PAGE_SHIFT &&
+		if (inode->i_blkbits == folio_shift(folio) &&
 		    buffer_uptodate(bh)) {
 			folio_mark_uptodate(folio);
 			return;
@@ -153,15 +153,15 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 	struct folio *folio = args->folio;
 	struct inode *inode = folio->mapping->host;
 	const unsigned blkbits = inode->i_blkbits;
-	const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
+	const unsigned blocks_per_folio = folio_size(folio) >> blkbits;
 	const unsigned blocksize = 1 << blkbits;
 	struct buffer_head *map_bh = &args->map_bh;
 	sector_t block_in_file;
 	sector_t last_block;
 	sector_t last_block_in_file;
 	sector_t first_block;
 	unsigned page_block;
-	unsigned first_hole = blocks_per_page;
+	unsigned first_hole = blocks_per_folio;
 	struct block_device *bdev = NULL;
 	int length;
 	int fully_mapped = 1;
@@ -170,9 +170,6 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 	unsigned relative_block;
 	gfp_t gfp = mapping_gfp_constraint(folio->mapping, GFP_KERNEL);
 
-	/* MAX_BUF_PER_PAGE, for example */
-	VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
-
 	if (args->is_readahead) {
 		opf |= REQ_RAHEAD;
 		gfp |= __GFP_NORETRY | __GFP_NOWARN;
@@ -181,8 +178,8 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 	if (folio_buffers(folio))
 		goto confused;
 
-	block_in_file = (sector_t)folio->index << (PAGE_SHIFT - blkbits);
-	last_block = block_in_file + args->nr_pages * blocks_per_page;
+	block_in_file = folio_pos(folio) >> blkbits;
+	last_block = block_in_file + ((args->nr_pages * PAGE_SIZE) >> blkbits);
 	last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
 	if (last_block > last_block_in_file)
 		last_block = last_block_in_file;
@@ -204,7 +201,7 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 				clear_buffer_mapped(map_bh);
 				break;
 			}
-			if (page_block == blocks_per_page)
+			if (page_block == blocks_per_folio)
 				break;
 			page_block++;
 			block_in_file++;
@@ -216,7 +213,7 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 	 * Then do more get_blocks calls until we are done with this folio.
 	 */
 	map_bh->b_folio = folio;
-	while (page_block < blocks_per_page) {
+	while (page_block < blocks_per_folio) {
 		map_bh->b_state = 0;
 		map_bh->b_size = 0;
 
@@ -229,7 +226,7 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 
 		if (!buffer_mapped(map_bh)) {
 			fully_mapped = 0;
-			if (first_hole == blocks_per_page)
+			if (first_hole == blocks_per_folio)
 				first_hole = page_block;
 			page_block++;
 			block_in_file++;
@@ -247,7 +244,7 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 			goto confused;
 		}
 
-		if (first_hole != blocks_per_page)
+		if (first_hole != blocks_per_folio)
 			goto confused;		/* hole -> non-hole */
 
 		/* Contiguous blocks? */
@@ -260,16 +257,16 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 			if (relative_block == nblocks) {
 				clear_buffer_mapped(map_bh);
 				break;
-			} else if (page_block == blocks_per_page)
+			} else if (page_block == blocks_per_folio)
 				break;
 			page_block++;
 			block_in_file++;
 		}
 		bdev = map_bh->b_bdev;
 	}
 
-	if (first_hole != blocks_per_page) {
-		folio_zero_segment(folio, first_hole << blkbits, PAGE_SIZE);
+	if (first_hole != blocks_per_folio) {
+		folio_zero_segment(folio, first_hole << blkbits, folio_size(folio));
 		if (first_hole == 0) {
 			folio_mark_uptodate(folio);
 			folio_unlock(folio);
@@ -303,10 +300,10 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
 	relative_block = block_in_file - args->first_logical_block;
 	nblocks = map_bh->b_size >> blkbits;
 	if ((buffer_boundary(map_bh) && relative_block == nblocks) ||
-	    (first_hole != blocks_per_page))
+	    (first_hole != blocks_per_folio))
 		args->bio = mpage_bio_submit_read(args->bio);
 	else
-		args->last_block_in_bio = first_block + blocks_per_page - 1;
+		args->last_block_in_bio = first_block + blocks_per_folio - 1;
 out:
 	return args->bio;
 
@@ -385,7 +382,7 @@ int mpage_read_folio(struct folio *folio, get_block_t get_block)
 {
 	struct mpage_readpage_args args = {
 		.folio = folio,
-		.nr_pages = 1,
+		.nr_pages = folio_nr_pages(folio),
 		.get_block = get_block,
 	};
 
@@ -456,12 +453,12 @@ static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc,
 	struct address_space *mapping = folio->mapping;
 	struct inode *inode = mapping->host;
 	const unsigned blkbits = inode->i_blkbits;
-	const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
+	const unsigned blocks_per_folio = folio_size(folio) >> blkbits;
 	sector_t last_block;
 	sector_t block_in_file;
 	sector_t first_block;
 	unsigned page_block;
-	unsigned first_unmapped = blocks_per_page;
+	unsigned first_unmapped = blocks_per_folio;
 	struct block_device *bdev = NULL;
 	int boundary = 0;
 	sector_t boundary_block = 0;
@@ -486,12 +483,12 @@ static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc,
 				 */
 				if (buffer_dirty(bh))
 					goto confused;
-				if (first_unmapped == blocks_per_page)
+				if (first_unmapped == blocks_per_folio)
 					first_unmapped = page_block;
 				continue;
 			}
 
-			if (first_unmapped != blocks_per_page)
+			if (first_unmapped != blocks_per_folio)
 				goto confused;	/* hole -> non-hole */
 
 			if (!buffer_dirty(bh) || !buffer_uptodate(bh))
@@ -527,7 +524,7 @@ static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc,
 	 * The page has no buffers: map it to disk
 	 */
 	BUG_ON(!folio_test_uptodate(folio));
-	block_in_file = (sector_t)folio->index << (PAGE_SHIFT - blkbits);
+	block_in_file = folio_pos(folio) >> blkbits;
 	/*
 	 * Whole page beyond EOF? Skip allocating blocks to avoid leaking
 	 * space.
@@ -536,7 +533,7 @@ static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc,
 		goto page_is_mapped;
 	last_block = (i_size - 1) >> blkbits;
 	map_bh.b_folio = folio;
-	for (page_block = 0; page_block < blocks_per_page; ) {
+	for (page_block = 0; page_block < blocks_per_folio; ) {
 
 		map_bh.b_state = 0;
 		map_bh.b_size = 1 << blkbits;
@@ -618,14 +615,14 @@ static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc,
 	BUG_ON(folio_test_writeback(folio));
 	folio_start_writeback(folio);
 	folio_unlock(folio);
-	if (boundary || (first_unmapped != blocks_per_page)) {
+	if (boundary || (first_unmapped != blocks_per_folio)) {
 		bio = mpage_bio_submit_write(bio);
 		if (boundary_block) {
 			write_boundary_block(boundary_bdev,
 					boundary_block, 1 << blkbits);
 		}
 	} else {
-		mpd->last_block_in_bio = first_block + blocks_per_page - 1;
+		mpd->last_block_in_bio = first_block + blocks_per_folio - 1;
 	}
 	goto out;
 

include/linux/blkdev.h

@@ -267,10 +267,16 @@ static inline dev_t disk_devt(struct gendisk *disk)
 	return MKDEV(disk->major, disk->first_minor);
 }
 
+/*
+ * We should strive for 1 << (PAGE_SHIFT + MAX_PAGECACHE_ORDER)
+ * however we constrain this to what we can validate and test.
+ */
+#define BLK_MAX_BLOCK_SIZE      SZ_64K
+
 /* blk_validate_limits() validates bsize, so drivers don't usually need to */
 static inline int blk_validate_block_size(unsigned long bsize)
 {
-	if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
+	if (bsize < 512 || bsize > BLK_MAX_BLOCK_SIZE || !is_power_of_2(bsize))
 		return -EINVAL;
 
 	return 0;