Merge tag 'vfs-6.19-rc1.folio' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull folio updates from Christian Brauner:
"Add a new folio_next_pos() helper function that returns the file
position of the first byte after the current folio. This is a common
operation in filesystems when needing to know the end of the current
folio.

The helper is lifted from btrfs which already had its own version, and
is now used across multiple filesystems and subsystems:
- btrfs
- buffer
- ext4
- f2fs
- gfs2
- iomap
- netfs
- xfs
- mm

This fixes a long-standing bug in ocfs2 on 32-bit systems with files
larger than 2GiB. Presumably this is not a common configuration, but
the fix is backported anyway. The other filesystems did not have bugs,
they were just mildly inefficient.

This also introduce uoff_t as the unsigned version of loff_t. A recent
commit inadvertently changed a comparison from being unsigned (on
64-bit systems) to being signed (which it had always been on 32-bit
systems), leading to sporadic fstests failures.

Generally file sizes are restricted to being a signed integer, but in
places where -1 is passed to indicate "up to the end of the file", it
is convenient to have an unsigned type to ensure comparisons are
always unsigned regardless of architecture"

* tag 'vfs-6.19-rc1.folio' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
fs: Add uoff_t
mm: Use folio_next_pos()
xfs: Use folio_next_pos()
netfs: Use folio_next_pos()
iomap: Use folio_next_pos()
gfs2: Use folio_next_pos()
f2fs: Use folio_next_pos()
ext4: Use folio_next_pos()
buffer: Use folio_next_pos()
btrfs: Use folio_next_pos()
filemap: Add folio_next_pos()

fs/btrfs/compression.h

···
 {
 	/* @cur must be inside the folio. */
 	ASSERT(folio_pos(folio) <= cur);
-	ASSERT(cur < folio_end(folio));
-	return min(range_end, folio_end(folio)) - cur;
+	ASSERT(cur < folio_next_pos(folio));
+	return umin(range_end, folio_next_pos(folio)) - cur;
 }
 
 int btrfs_alloc_compress_wsm(struct btrfs_fs_info *fs_info);

fs/btrfs/defrag.c

···
 	}
 
 	lock_start = folio_pos(folio);
-	lock_end = folio_end(folio) - 1;
+	lock_end = folio_next_pos(folio) - 1;
 	/* Wait for any existing ordered extent in the range */
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
···
 
 		if (!folio)
 			break;
-		if (start >= folio_end(folio) || start + len <= folio_pos(folio))
+		if (start >= folio_next_pos(folio) ||
+		    start + len <= folio_pos(folio))
 			continue;
 		btrfs_folio_clamp_clear_checked(fs_info, folio, start, len);
 		btrfs_folio_clamp_set_dirty(fs_info, folio, start, len);
···
 			folios[i] = NULL;
 			goto free_folios;
 		}
-		cur = folio_end(folios[i]);
+		cur = folio_next_pos(folios[i]);
 	}
 	for (int i = 0; i < nr_pages; i++) {
 		if (!folios[i])

fs/btrfs/extent_io.c

···
 				goto out;
 			}
 			range_start = max_t(u64, folio_pos(folio), start);
-			range_len = min_t(u64, folio_end(folio), end + 1) - range_start;
+			range_len = min_t(u64, folio_next_pos(folio), end + 1) - range_start;
 			btrfs_folio_set_lock(fs_info, folio, range_start, range_len);
 
 			processed_end = range_start + range_len - 1;
···
 	ASSERT(orig_end > orig_start);
 
 	/* The range should at least cover part of the folio */
-	ASSERT(!(orig_start >= folio_end(locked_folio) ||
+	ASSERT(!(orig_start >= folio_next_pos(locked_folio) ||
 		 orig_end <= folio_pos(locked_folio)));
 again:
 	/* step one, find a bunch of delalloc bytes starting at start */
···
 	struct btrfs_fs_info *fs_info = folio_to_fs_info(folio);
 
 	ASSERT(folio_pos(folio) <= start &&
-	       start + len <= folio_end(folio));
+	       start + len <= folio_next_pos(folio));
 
 	if (uptodate && btrfs_verify_folio(folio, start, len))
 		btrfs_folio_set_uptodate(fs_info, folio, start, len);
···
 	 * finished our folio read and unlocked the folio.
 	 */
 	if (btrfs_folio_test_dirty(fs_info, folio, cur, blocksize)) {
-		u64 range_len = min(folio_end(folio),
+		u64 range_len = umin(folio_next_pos(folio),
 				    ordered->file_offset + ordered->num_bytes) - cur;
 
 		ret = true;
···
 	 * So we return true and update @next_ret to the OE/folio boundary.
 	 */
 	if (btrfs_folio_test_uptodate(fs_info, folio, cur, blocksize)) {
-		u64 range_len = min(folio_end(folio),
+		u64 range_len = umin(folio_next_pos(folio),
 				    ordered->file_offset + ordered->num_bytes) - cur;
 
 		/*
···
 	for (int i = 0; i < num_extent_folios(eb); i++) {
 		struct folio *folio = eb->folios[i];
 		u64 range_start = max_t(u64, eb->start, folio_pos(folio));
-		u32 range_len = min_t(u64, folio_end(folio),
+		u32 range_len = min_t(u64, folio_next_pos(folio),
 				      eb->start + eb->len) - range_start;
 
 		folio_lock(folio);
···
 			continue;
 		}
 
-		cur_end = min_t(u64, folio_end(folio) - 1, end);
+		cur_end = min_t(u64, folio_next_pos(folio) - 1, end);
 		cur_len = cur_end + 1 - cur;
 
 		ASSERT(folio_test_locked(folio));
···
 	for (int i = 0; i < num_extent_folios(eb); i++) {
 		struct folio *folio = eb->folios[i];
 		u64 range_start = max_t(u64, eb->start, folio_pos(folio));
-		u32 range_len = min_t(u64, folio_end(folio),
+		u32 range_len = min_t(u64, folio_next_pos(folio),
 				      eb->start + eb->len) - range_start;
 
 		bio_add_folio_nofail(&bbio->bio, folio, range_len,

fs/btrfs/file.c

···
 	num_bytes = round_up(write_bytes + pos - start_pos,
 			     fs_info->sectorsize);
 	ASSERT(num_bytes <= U32_MAX);
-	ASSERT(folio_pos(folio) <= pos && folio_end(folio) >= pos + write_bytes);
+	ASSERT(folio_pos(folio) <= pos &&
+	       folio_next_pos(folio) >= pos + write_bytes);
 
 	end_of_last_block = start_pos + num_bytes - 1;
 
···
 				  u64 len)
 {
 	u64 clamp_start = max_t(u64, pos, folio_pos(folio));
-	u64 clamp_end = min_t(u64, pos + len, folio_end(folio));
+	u64 clamp_end = min_t(u64, pos + len, folio_next_pos(folio));
 	const u32 blocksize = inode_to_fs_info(inode)->sectorsize;
 	int ret = 0;
 
···
 	 * The reserved range goes beyond the current folio, shrink the reserved
 	 * space to the folio boundary.
 	 */
-	if (reserved_start + reserved_len > folio_end(folio)) {
-		const u64 last_block = folio_end(folio);
+	if (reserved_start + reserved_len > folio_next_pos(folio)) {
+		const u64 last_block = folio_next_pos(folio);
 
 		shrink_reserved_space(inode, *data_reserved, reserved_start,
 				      reserved_len, last_block - reserved_start,

fs/btrfs/inode.c

···
 			continue;
 		}
 
-		index = folio_end(folio) >> PAGE_SHIFT;
+		index = folio_next_index(folio);
 		/*
 		 * Here we just clear all Ordered bits for every page in the
 		 * range, then btrfs_mark_ordered_io_finished() will handle
···
 	 * The range must cover part of the @locked_folio, or a return of 1
 	 * can confuse the caller.
 	 */
-	ASSERT(!(end <= folio_pos(locked_folio) || start >= folio_end(locked_folio)));
+	ASSERT(!(end <= folio_pos(locked_folio) ||
+		 start >= folio_next_pos(locked_folio)));
 
 	if (should_nocow(inode, start, end)) {
 		ret = run_delalloc_nocow(inode, locked_folio, start, end);
···
 	struct btrfs_inode *inode = fixup->inode;
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	u64 page_start = folio_pos(folio);
-	u64 page_end = folio_end(folio) - 1;
+	u64 page_end = folio_next_pos(folio) - 1;
 	int ret = 0;
 	bool free_delalloc_space = true;
 
···
 	 */
 
 	zero_start = max_t(u64, folio_pos(folio), start);
-	zero_end = folio_end(folio);
+	zero_end = folio_next_pos(folio);
 	folio_zero_range(folio, zero_start - folio_pos(folio),
 			 zero_end - zero_start);
 
···
 		 * not reach disk, it still affects our page caches.
 		 */
 		zero_start = max_t(u64, folio_pos(folio), start);
-		zero_end = min_t(u64, folio_end(folio) - 1, end);
+		zero_end = min_t(u64, folio_next_pos(folio) - 1, end);
 	} else {
 		zero_start = max_t(u64, block_start, start);
 		zero_end = min_t(u64, block_end, end);

fs/btrfs/misc.h

···
 	return (found_set == start + nbits);
 }
 
-static inline u64 folio_end(struct folio *folio)
-{
-	return folio_pos(folio) + folio_size(folio);
-}
-
 #endif

fs/btrfs/ordered-data.c

···
 	if (folio) {
 		ASSERT(folio->mapping);
 		ASSERT(folio_pos(folio) <= file_offset);
-		ASSERT(file_offset + len <= folio_end(folio));
+		ASSERT(file_offset + len <= folio_next_pos(folio));
 
 		/*
 		 * Ordered flag indicates whether we still have

fs/btrfs/subpage.c

···
 	 * unmapped page like dummy extent buffer pages.
 	 */
 	if (folio->mapping)
-		ASSERT(folio_pos(folio) <= start && start + len <= folio_end(folio),
+		ASSERT(folio_pos(folio) <= start &&
+		       start + len <= folio_next_pos(folio),
 		       "start=%llu len=%u folio_pos=%llu folio_size=%zu",
 		       start, len, folio_pos(folio), folio_size(folio));
 }
···
 	if (folio_pos(folio) >= orig_start + orig_len)
 		*len = 0;
 	else
-		*len = min_t(u64, folio_end(folio), orig_start + orig_len) - *start;
+		*len = min_t(u64, folio_next_pos(folio), orig_start + orig_len) - *start;
 }
 
 static bool btrfs_subpage_end_and_test_lock(const struct btrfs_fs_info *fs_info,

fs/buffer.c

···
 	loff_t i_size = i_size_read(inode);
 
 	/* Is the folio fully inside i_size? */
-	if (folio_pos(folio) + folio_size(folio) <= i_size)
+	if (folio_next_pos(folio) <= i_size)
 		return __block_write_full_folio(inode, folio, get_block, wbc);
 
 	/* Is the folio fully outside i_size? (truncate in progress) */

fs/ext4/inode.c

···
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
 
-	if (pos + len > folio_pos(folio) + folio_size(folio))
-		len = folio_pos(folio) + folio_size(folio) - pos;
+	if (len > folio_next_pos(folio) - pos)
+		len = folio_next_pos(folio) - pos;
 
 	from = offset_in_folio(folio, pos);
 	to = from + len;
···
 
 			if (mpd->map.m_len == 0)
 				mpd->start_pos = folio_pos(folio);
-			mpd->next_pos = folio_pos(folio) + folio_size(folio);
+			mpd->next_pos = folio_next_pos(folio);
 			/*
 			 * Writeout when we cannot modify metadata is simple.
 			 * Just submit the page. For data=journal mode we
···
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
 
-	if (pos + len > folio_pos(folio) + folio_size(folio))
-		len = folio_pos(folio) + folio_size(folio) - pos;
+	if (len > folio_next_pos(folio) - pos)
+		len = folio_next_pos(folio) - pos;
 
 	ret = ext4_block_write_begin(NULL, folio, pos, len,
 				     ext4_da_get_block_prep);

fs/f2fs/compress.c

···
 	}
 
 	folio = page_folio(cc->rpages[last_index]);
-	psize = folio_pos(folio) + folio_size(folio);
+	psize = folio_next_pos(folio);
 
 	err = f2fs_get_node_info(fio.sbi, dn.nid, &ni, false);
 	if (err)

fs/gfs2/aops.c

···
 	 * the page size, the remaining memory is zeroed when mapped, and
 	 * writes to that region are not written out to the file."
 	 */
-	if (folio_pos(folio) < i_size &&
-	    i_size < folio_pos(folio) + folio_size(folio))
+	if (folio_pos(folio) < i_size && i_size < folio_next_pos(folio))
 		folio_zero_segment(folio, offset_in_folio(folio, i_size),
 				folio_size(folio));
 

fs/iomap/buffered-io.c

···
 	 * are not changing pagecache contents.
 	 */
 	if (!(iter->flags & IOMAP_UNSHARE) && pos <= folio_pos(folio) &&
-	    pos + len >= folio_pos(folio) + folio_size(folio))
+	    pos + len >= folio_next_pos(folio))
 		return 0;
 
 	ifs = ifs_alloc(iter->inode, folio, iter->flags);
···
 	if (!ifs)
 		return;
 
-	last_byte = min_t(loff_t, end_byte - 1,
-			folio_pos(folio) + folio_size(folio) - 1);
+	last_byte = min_t(loff_t, end_byte - 1, folio_next_pos(folio) - 1);
 	first_blk = offset_in_folio(folio, start_byte) >> blkbits;
 	last_blk = offset_in_folio(folio, last_byte) >> blkbits;
 	while ((first_blk = ifs_next_clean_block(folio, first_blk, last_blk))
···
 	 * Make sure the next punch start is correctly bound to
 	 * the end of this data range, not the end of the folio.
 	 */
-	*punch_start_byte = min_t(loff_t, end_byte,
-				folio_pos(folio) + folio_size(folio));
+	*punch_start_byte = min_t(loff_t, end_byte, folio_next_pos(folio));
 }
 
 /*
···
 				start_byte, end_byte, iomap, punch);
 
 		/* move offset to start of next folio in range */
-		start_byte = folio_pos(folio) + folio_size(folio);
+		start_byte = folio_next_pos(folio);
 		folio_unlock(folio);
 		folio_put(folio);
 	}

fs/netfs/buffered_write.c

···
 		folio_unlock(folio);
 		err = filemap_fdatawrite_range(mapping,
 					       folio_pos(folio),
-					       folio_pos(folio) + folio_size(folio));
+					       folio_next_pos(folio));
 		switch (err) {
 		case 0:
 			ret = VM_FAULT_RETRY;

fs/netfs/misc.c

···
 	if (folio_test_dirty(folio))
 		return false;
 
-	end = umin(folio_pos(folio) + folio_size(folio), i_size_read(&ctx->inode));
+	end = umin(folio_next_pos(folio), i_size_read(&ctx->inode));
 	if (end > ctx->zero_point)
 		ctx->zero_point = end;
 

fs/ocfs2/alloc.c

···
 		ocfs2_map_and_dirty_folio(inode, handle, from, to, folio, 1,
 				&phys);
 
-		start = folio_next_index(folio) << PAGE_SHIFT;
+		start = folio_next_pos(folio);
 	}
 out:
 	if (folios)

fs/xfs/scrub/xfarray.c

···
 		si->first_folio_idx = xfarray_idx(si->array,
 				folio_pos(si->folio) + si->array->obj_size - 1);
 
-		next_pos = folio_pos(si->folio) + folio_size(si->folio);
+		next_pos = folio_next_pos(si->folio);
 		si->last_folio_idx = xfarray_idx(si->array, next_pos - 1);
 		if (xfarray_pos(si->array, si->last_folio_idx + 1) > next_pos)
 			si->last_folio_idx--;

fs/xfs/xfs_aops.c

···
 	 * folio itself and not the start offset that is passed in.
 	 */
 	xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos,
-				folio_pos(folio) + folio_size(folio), NULL);
+				folio_next_pos(folio), NULL);
 }
 
 /*

include/linux/mm.h

···
 extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info);
 
 /* truncate.c */
-extern void truncate_inode_pages(struct address_space *, loff_t);
-extern void truncate_inode_pages_range(struct address_space *,
-				       loff_t lstart, loff_t lend);
-extern void truncate_inode_pages_final(struct address_space *);
+void truncate_inode_pages(struct address_space *mapping, loff_t lstart);
+void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart,
+		uoff_t lend);
+void truncate_inode_pages_final(struct address_space *mapping);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern vm_fault_t filemap_fault(struct vm_fault *vmf);

include/linux/pagemap.h

···
 }
 
 /**
+ * folio_next_pos - Get the file position of the next folio.
+ * @folio: The current folio.
+ *
+ * Return: The position of the folio which follows this folio in the file.
+ */
+static inline loff_t folio_next_pos(const struct folio *folio)
+{
+	return (loff_t)folio_next_index(folio) << PAGE_SHIFT;
+}
+
+/**
  * folio_file_page - The page for a particular index.
  * @folio: The folio which contains this index.
  * @index: The index we want to look up.

include/linux/shmem_fs.h

···
 					pgoff_t index, gfp_t gfp_mask);
 int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
 		struct list_head *folio_list);
-void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end);
+void shmem_truncate_range(struct inode *inode, loff_t start, uoff_t end);
 int shmem_unuse(unsigned int type);
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE

include/linux/types.h

···
 
 #if defined(__GNUC__)
 typedef __kernel_loff_t		loff_t;
+typedef __kernel_uoff_t		uoff_t;
 #endif
 
 /*

include/uapi/asm-generic/posix_types.h

···
  */
 typedef __kernel_long_t	__kernel_off_t;
 typedef long long	__kernel_loff_t;
+typedef unsigned long long	__kernel_uoff_t;
 typedef __kernel_long_t	__kernel_old_time_t;
 #ifndef __KERNEL__
 typedef __kernel_long_t	__kernel_time_t;

mm/shmem.c

···
  * Remove range of pages and swap entries from page cache, and free them.
  * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
  */
-static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
+static void shmem_undo_range(struct inode *inode, loff_t lstart, uoff_t lend,
 								 bool unfalloc)
 {
 	struct address_space *mapping = inode->i_mapping;
···
 	same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT);
 	folio = shmem_get_partial_folio(inode, lstart >> PAGE_SHIFT);
 	if (folio) {
-		same_folio = lend < folio_pos(folio) + folio_size(folio);
+		same_folio = lend < folio_next_pos(folio);
 		folio_mark_dirty(folio);
 		if (!truncate_inode_partial_folio(folio, lstart, lend)) {
 			start = folio_next_index(folio);
···
 	shmem_recalc_inode(inode, 0, -nr_swaps_freed);
 }
 
-void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
+void shmem_truncate_range(struct inode *inode, loff_t lstart, uoff_t lend)
 {
 	shmem_undo_range(inode, lstart, lend, false);
 	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
···
 }
 #endif
 
-void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
+void shmem_truncate_range(struct inode *inode, loff_t lstart, uoff_t lend)
 {
 	truncate_inode_pages_range(inode->i_mapping, lstart, lend);
 }

mm/truncate.c

···
  * page aligned properly.
  */
 void truncate_inode_pages_range(struct address_space *mapping,
-				loff_t lstart, loff_t lend)
+				loff_t lstart, uoff_t lend)
 {
 	pgoff_t		start;		/* inclusive */
 	pgoff_t		end;		/* exclusive */
···
 	same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT);
 	folio = __filemap_get_folio(mapping, lstart >> PAGE_SHIFT, FGP_LOCK, 0);
 	if (!IS_ERR(folio)) {
-		same_folio = lend < folio_pos(folio) + folio_size(folio);
+		same_folio = lend < folio_next_pos(folio);
 		if (!truncate_inode_partial_folio(folio, lstart, lend)) {
 			start = folio_next_index(folio);
 			if (same_folio)