btrfs: do not hold the extent lock for entire read

Historically we've held the extent lock throughout the entire read.
There's been a few reasons for this, but it's mostly just caused us
problems.  For example, this prevents us from allowing page faults
during direct io reads, because we could deadlock.  This has forced us
to only allow 4k reads at a time for io_uring NOWAIT requests because we
have no idea if we'll be forced to page fault and thus have to do a
whole lot of work.

On the buffered side we are protected by the page lock, as long as we're
reading things like buffered writes, punch hole, and even direct IO to a
certain degree will get hung up on the page lock while the page is in
flight.

On the direct side we have the dio extent lock, which acts much like the
way the extent lock worked previously to this patch, however just for
direct reads.  This protects direct reads from concurrent direct writes,
while we're protected from buffered writes via the inode lock.

Now that we're protected in all cases, narrow the extent lock to the
part where we're getting the extent map to submit the reads, no longer
holding the extent lock for the entire read operation.  Push the extent
lock down into do_readpage() so that we're only grabbing it when looking
up the extent map.  This portion was contributed by Goldwyn.

Co-developed-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 4 insertions, 90 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index f7a388529c17..bd1a7b2fc71a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -480,75 +480,6 @@ static void end_bbio_data_write(struct btrfs_bio *bbio)
 	bio_put(bio);
 }
 
-/*
- * Record previously processed extent range
- *
- * For endio_readpage_release_extent() to handle a full extent range, reducing
- * the extent io operations.
- */
-struct processed_extent {
-	struct btrfs_inode *inode;
-	/* Start of the range in @inode */
-	u64 start;
-	/* End of the range in @inode */
-	u64 end;
-	bool uptodate;
-};
-
-/*
- * Try to release processed extent range
- *
- * May not release the extent range right now if the current range is
- * contiguous to processed extent.
- *
- * Will release processed extent when any of @inode, @uptodate, the range is
- * no longer contiguous to the processed range.
- *
- * Passing @inode == NULL will force processed extent to be released.
- */
-static void endio_readpage_release_extent(struct processed_extent *processed,
-			      struct btrfs_inode *inode, u64 start, u64 end,
-			      bool uptodate)
-{
-	struct extent_state *cached = NULL;
-	struct extent_io_tree *tree;
-
-	/* The first extent, initialize @processed */
-	if (!processed->inode)
-		goto update;
-
-	/*
-	 * Contiguous to processed extent, just uptodate the end.
-	 *
-	 * Several things to notice:
-	 *
-	 * - bio can be merged as long as on-disk bytenr is contiguous
-	 *   This means we can have page belonging to other inodes, thus need to
-	 *   check if the inode still matches.
-	 * - bvec can contain range beyond current page for multi-page bvec
-	 *   Thus we need to do processed->end + 1 >= start check
-	 */
-	if (processed->inode == inode && processed->uptodate == uptodate &&
-	    processed->end + 1 >= start && end >= processed->end) {
-		processed->end = end;
-		return;
-	}
-
-	tree = &processed->inode->io_tree;
-	/*
-	 * Now we don't have range contiguous to the processed range, release
-	 * the processed range now.
-	 */
-	unlock_extent(tree, processed->start, processed->end, &cached);
-
-update:
-	/* Update processed to current range */
-	processed->inode = inode;
-	processed->start = start;
-	processed->end = end;
-	processed->uptodate = uptodate;
-}
-
 static void begin_folio_read(struct btrfs_fs_info *fs_info, struct folio *folio)
 {
 	ASSERT(folio_test_locked(folio));
@@ -575,7 +506,6 @@ static void end_bbio_data_read(struct btrfs_bio *bbio)
 {
 	struct btrfs_fs_info *fs_info = bbio->fs_info;
 	struct bio *bio = &bbio->bio;
-	struct processed_extent processed = { 0 };
 	struct folio_iter fi;
 	const u32 sectorsize = fs_info->sectorsize;
 
@@ -640,11 +570,7 @@ static void end_bbio_data_read(struct btrfs_bio *bbio)
 
 		/* Update page status and unlock. */
 		end_folio_read(folio, uptodate, start, len);
-		endio_readpage_release_extent(&processed, BTRFS_I(inode),
-					      start, end, uptodate);
 	}
-	/* Release the last extent */
-	endio_readpage_release_extent(&processed, NULL, 0, 0, false);
 	bio_put(bio);
 }
 
@@ -973,6 +899,7 @@ static struct extent_map *__get_extent_map(struct inode *inode,
 					   u64 len, struct extent_map **em_cached)
 {
 	struct extent_map *em;
+	struct extent_state *cached_state = NULL;
 
 	ASSERT(em_cached);
 
@@ -988,12 +915,15 @@ static struct extent_map *__get_extent_map(struct inode *inode,
 		*em_cached = NULL;
 	}
 
+	btrfs_lock_and_flush_ordered_range(BTRFS_I(inode), start, start + len - 1, &cached_state);
 	em = btrfs_get_extent(BTRFS_I(inode), folio, start, len);
 	if (!IS_ERR(em)) {
 		BUG_ON(*em_cached);
 		refcount_inc(&em->refs);
 		*em_cached = em;
 	}
+	unlock_extent(&BTRFS_I(inode)->io_tree, start, start + len - 1, &cached_state);
+
 	return em;
 }
 /*
@@ -1019,11 +949,9 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
 	size_t pg_offset = 0;
 	size_t iosize;
 	size_t blocksize = fs_info->sectorsize;
-	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 
 	ret = set_folio_extent_mapped(folio);
 	if (ret < 0) {
-		unlock_extent(tree, start, end, NULL);
 		folio_unlock(folio);
 		return ret;
 	}
@@ -1047,14 +975,12 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
 		if (cur >= last_byte) {
 			iosize = folio_size(folio) - pg_offset;
 			folio_zero_range(folio, pg_offset, iosize);
-			unlock_extent(tree, cur, cur + iosize - 1, NULL);
 			end_folio_read(folio, true, cur, iosize);
 			break;
 		}
 		em = __get_extent_map(inode, folio, cur, end - cur + 1,
 				      em_cached);
 		if (IS_ERR(em)) {
-			unlock_extent(tree, cur, end, NULL);
 			end_folio_read(folio, false, cur, end + 1 - cur);
 			return PTR_ERR(em);
 		}
@@ -1123,7 +1049,6 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
 		if (block_start == EXTENT_MAP_HOLE) {
 			folio_zero_range(folio, pg_offset, iosize);
 
-			unlock_extent(tree, cur, cur + iosize - 1, NULL);
 			end_folio_read(folio, true, cur, iosize);
 			cur = cur + iosize;
 			pg_offset += iosize;
@@ -1131,7 +1056,6 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
 		}
 		/* the get_extent function already copied into the folio */
 		if (block_start == EXTENT_MAP_INLINE) {
-			unlock_extent(tree, cur, cur + iosize - 1, NULL);
 			end_folio_read(folio, true, cur, iosize);
 			cur = cur + iosize;
 			pg_offset += iosize;
@@ -1156,15 +1080,10 @@ 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);
-	u64 start = folio_pos(folio);
-	u64 end = start + folio_size(folio) - 1;
 	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, NULL);
-
 	ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl, NULL);
 	free_extent_map(em_cached);
 
@@ -2337,15 +2256,10 @@ int btrfs_writepages(struct address_space *mapping, struct writeback_control *wb
 void btrfs_readahead(struct readahead_control *rac)
 {
 	struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD };
-	struct btrfs_inode *inode = BTRFS_I(rac->mapping->host);
 	struct folio *folio;
-	u64 start = readahead_pos(rac);
-	u64 end = start + readahead_length(rac) - 1;
 	struct extent_map *em_cached = NULL;
 	u64 prev_em_start = (u64)-1;
 
-	btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);
-
 	while ((folio = readahead_folio(rac)) != NULL)
 		btrfs_do_readpage(folio, &em_cached, &bio_ctrl, &prev_em_start);