iomap: use find_next_bit() for dirty bitmap scanning

Use find_next_bit()/find_next_zero_bit() for iomap dirty bitmap
scanning. This uses __ffs() internally and is more efficient for
finding the next dirty or clean bit than iterating through the bitmap
range testing every bit.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Link: https://patch.msgid.link/20251111193658.3495942-9-joannelkoong@gmail.com
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>

Author: joannekoong

fs/iomap/buffered-io.c

@@ -76,13 +76,34 @@ static void iomap_set_range_uptodate(struct folio *folio, size_t off,
 		folio_mark_uptodate(folio);
 }
 
-static inline bool ifs_block_is_dirty(struct folio *folio,
-		struct iomap_folio_state *ifs, int block)
+/*
+ * Find the next dirty block in the folio. end_blk is inclusive.
+ * If no dirty block is found, this will return end_blk + 1.
+ */
+static unsigned ifs_next_dirty_block(struct folio *folio,
+		unsigned start_blk, unsigned end_blk)
 {
+	struct iomap_folio_state *ifs = folio->private;
 	struct inode *inode = folio->mapping->host;
-	unsigned int blks_per_folio = i_blocks_per_folio(inode, folio);
+	unsigned int blks = i_blocks_per_folio(inode, folio);
+
+	return find_next_bit(ifs->state, blks + end_blk + 1,
+			blks + start_blk) - blks;
+}
+
+/*
+ * Find the next clean block in the folio. end_blk is inclusive.
+ * If no clean block is found, this will return end_blk + 1.
+ */
+static unsigned ifs_next_clean_block(struct folio *folio,
+		unsigned start_blk, unsigned end_blk)
+{
+	struct iomap_folio_state *ifs = folio->private;
+	struct inode *inode = folio->mapping->host;
+	unsigned int blks = i_blocks_per_folio(inode, folio);
 
-	return test_bit(block + blks_per_folio, ifs->state);
+	return find_next_zero_bit(ifs->state, blks + end_blk + 1,
+			blks + start_blk) - blks;
 }
 
 static unsigned ifs_find_dirty_range(struct folio *folio,
@@ -93,18 +114,17 @@ static unsigned ifs_find_dirty_range(struct folio *folio,
 		offset_in_folio(folio, *range_start) >> inode->i_blkbits;
 	unsigned end_blk = min_not_zero(
 		offset_in_folio(folio, range_end) >> inode->i_blkbits,
-		i_blocks_per_folio(inode, folio));
-	unsigned nblks = 1;
-
-	while (!ifs_block_is_dirty(folio, ifs, start_blk))
-		if (++start_blk == end_blk)
-			return 0;
+		i_blocks_per_folio(inode, folio)) - 1;
+	unsigned nblks;
 
-	while (start_blk + nblks < end_blk) {
-		if (!ifs_block_is_dirty(folio, ifs, start_blk + nblks))
-			break;
-		nblks++;
-	}
+	start_blk = ifs_next_dirty_block(folio, start_blk, end_blk);
+	if (start_blk > end_blk)
+		return 0;
+	if (start_blk == end_blk)
+		nblks = 1;
+	else
+		nblks = ifs_next_clean_block(folio, start_blk + 1, end_blk) -
+				start_blk;
 
 	*range_start = folio_pos(folio) + (start_blk << inode->i_blkbits);
 	return nblks << inode->i_blkbits;
@@ -1166,7 +1186,7 @@ static void iomap_write_delalloc_ifs_punch(struct inode *inode,
 		struct folio *folio, loff_t start_byte, loff_t end_byte,
 		struct iomap *iomap, iomap_punch_t punch)
 {
-	unsigned int first_blk, last_blk, i;
+	unsigned int first_blk, last_blk;
 	loff_t last_byte;
 	u8 blkbits = inode->i_blkbits;
 	struct iomap_folio_state *ifs;
@@ -1185,10 +1205,11 @@ static void iomap_write_delalloc_ifs_punch(struct inode *inode,
 			folio_pos(folio) + folio_size(folio) - 1);
 	first_blk = offset_in_folio(folio, start_byte) >> blkbits;
 	last_blk = offset_in_folio(folio, last_byte) >> blkbits;
-	for (i = first_blk; i <= last_blk; i++) {
-		if (!ifs_block_is_dirty(folio, ifs, i))
-			punch(inode, folio_pos(folio) + (i << blkbits),
-				    1 << blkbits, iomap);
+	while ((first_blk = ifs_next_clean_block(folio, first_blk, last_blk))
+		       <= last_blk) {
+		punch(inode, folio_pos(folio) + (first_blk << blkbits),
+				1 << blkbits, iomap);
+		first_blk++;
 	}
 }