Merge tag 'for-6.14-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - fix stale page cache after race between readahead and direct IO write

 - fix hole expansion when writing at an offset beyond EOF, the range
   will not be zeroed

 - use proper way to calculate offsets in folio ranges

* tag 'for-6.14-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: fix hole expansion when writing at an offset beyond EOF
  btrfs: fix stale page cache after race between readahead and direct IO write
  btrfs: fix two misuses of folio_shift()

2 files changed, 21 insertions, 12 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index a2cac9d0a1a9..b2fae67f8fa3 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -523,8 +523,6 @@ static void end_bbio_data_read(struct btrfs_bio *bbio)
 		u64 end;
 		u32 len;
 
-		/* For now only order 0 folios are supported for data. */
-		ASSERT(folio_order(folio) == 0);
 		btrfs_debug(fs_info,
 			"%s: bi_sector=%llu, err=%d, mirror=%u",
 			__func__, bio->bi_iter.bi_sector, bio->bi_status,
@@ -552,7 +550,6 @@ static void end_bbio_data_read(struct btrfs_bio *bbio)
 
 		if (likely(uptodate)) {
 			loff_t i_size = i_size_read(inode);
-			pgoff_t end_index = i_size >> folio_shift(folio);
 
 			/*
 			 * Zero out the remaining part if this range straddles
@@ -561,9 +558,11 @@ static void end_bbio_data_read(struct btrfs_bio *bbio)
 			 * Here we should only zero the range inside the folio,
 			 * not touch anything else.
 			 *
-			 * NOTE: i_size is exclusive while end is inclusive.
+			 * NOTE: i_size is exclusive while end is inclusive and
+			 * folio_contains() takes PAGE_SIZE units.
 			 */
-			if (folio_index(folio) == end_index && i_size <= end) {
+			if (folio_contains(folio, i_size >> PAGE_SHIFT) &&
+			    i_size <= end) {
 				u32 zero_start = max(offset_in_folio(folio, i_size),
 						     offset_in_folio(folio, start));
 				u32 zero_len = offset_in_folio(folio, end) + 1 -
@@ -899,7 +898,6 @@ static struct extent_map *get_extent_map(struct btrfs_inode *inode,
 					 u64 len, struct extent_map **em_cached)
 {
 	struct extent_map *em;
-	struct extent_state *cached_state = NULL;
 
 	ASSERT(em_cached);
 
@@ -915,14 +913,12 @@ static struct extent_map *get_extent_map(struct btrfs_inode *inode,
 		*em_cached = NULL;
 	}
 
-	btrfs_lock_and_flush_ordered_range(inode, start, start + len - 1, &cached_state);
 	em = btrfs_get_extent(inode, folio, start, len);
 	if (!IS_ERR(em)) {
 		BUG_ON(*em_cached);
 		refcount_inc(&em->refs);
 		*em_cached = em;
 	}
-	unlock_extent(&inode->io_tree, start, start + len - 1, &cached_state);
 
 	return em;
 }
@@ -956,7 +952,7 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
 		return ret;
 	}
 
-	if (folio->index == last_byte >> folio_shift(folio)) {
+	if (folio_contains(folio, last_byte >> PAGE_SHIFT)) {
 		size_t zero_offset = offset_in_folio(folio, last_byte);
 
 		if (zero_offset) {
@@ -1079,11 +1075,18 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
 
 int btrfs_read_folio(struct file *file, struct folio *folio)
 {
+	struct btrfs_inode *inode = folio_to_inode(folio);
+	const u64 start = folio_pos(folio);
+	const u64 end = start + folio_size(folio) - 1;
+	struct extent_state *cached_state = NULL;
 	struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ };
 	struct extent_map *em_cached = NULL;
 	int ret;
 
+	btrfs_lock_and_flush_ordered_range(inode, start, end, &cached_state);
 	ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl, NULL);
+	unlock_extent(&inode->io_tree, start, end, &cached_state);
+
 	free_extent_map(em_cached);
 
 	/*
@@ -2380,12 +2383,20 @@ void btrfs_readahead(struct readahead_control *rac)
 {
 	struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD };
 	struct folio *folio;
+	struct btrfs_inode *inode = BTRFS_I(rac->mapping->host);
+	const u64 start = readahead_pos(rac);
+	const u64 end = start + readahead_length(rac) - 1;
+	struct extent_state *cached_state = NULL;
 	struct extent_map *em_cached = NULL;
 	u64 prev_em_start = (u64)-1;
 
+	btrfs_lock_and_flush_ordered_range(inode, start, end, &cached_state);
+
 	while ((folio = readahead_folio(rac)) != NULL)
 		btrfs_do_readpage(folio, &em_cached, &bio_ctrl, &prev_em_start);
 
+	unlock_extent(&inode->io_tree, start, end, &cached_state);
+
 	if (em_cached)
 		free_extent_map(em_cached);
 	submit_one_bio(&bio_ctrl);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 36f51c311bb1..ed3c0d6546c5 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1039,7 +1039,6 @@ int btrfs_write_check(struct kiocb *iocb, size_t count)
 	loff_t pos = iocb->ki_pos;
 	int ret;
 	loff_t oldsize;
-	loff_t start_pos;
 
 	/*
 	 * Quickly bail out on NOWAIT writes if we don't have the nodatacow or
@@ -1066,9 +1065,8 @@ int btrfs_write_check(struct kiocb *iocb, size_t count)
 		inode_inc_iversion(inode);
 	}
 
-	start_pos = round_down(pos, fs_info->sectorsize);
 	oldsize = i_size_read(inode);
-	if (start_pos > oldsize) {
+	if (pos > oldsize) {
 		/* Expand hole size to cover write data, preventing empty gap */
 		loff_t end_pos = round_up(pos + count, fs_info->sectorsize);