btrfs: avoid blocking nowait dio when locking file range

If we are doing a NOWAIT direct IO read/write, we can block when locking
the file range at btrfs_dio_iomap_begin(), as it's possible the range (or
a part of it) is already locked by another task (mmap writes, another
direct IO read/write racing with us, fiemap, etc). We are also waiting for
completion of any ordered extent we find in the range, which also can
block us for a significant amount of time.

There's also the incorrect fallback to buffered IO (returning -ENOTBLK)
when we are dealing with a NOWAIT request and we can't proceed. In this
case we should be returning -EAGAIN, as falling back to buffered IO can
result in blocking for many different reasons, so that the caller can
delegate a retry to a context where blocking is more acceptable.

Fix these cases by:

1) Doing a try lock on the file range and failing with -EAGAIN if we
   can not lock right away;

2) Fail with -EAGAIN if we find an ordered extent;

3) Return -EAGAIN instead of -ENOTBLK when we need to fallback to
   buffered IO and we have a NOWAIT request.

This will also allow us to avoid a duplicated check that verifies if we
are able to do a NOCOW write for NOWAIT direct IO writes, done in the
next patch.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 23 insertions, 11 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a240b7fff984..fa5dd209ca58 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7250,14 +7250,22 @@ out:
 }
 
 static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
-			      struct extent_state **cached_state, bool writing)
+			      struct extent_state **cached_state,
+			      unsigned int iomap_flags)
 {
+	const bool writing = (iomap_flags & IOMAP_WRITE);
+	const bool nowait = (iomap_flags & IOMAP_NOWAIT);
+	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_ordered_extent *ordered;
 	int ret = 0;
 
 	while (1) {
-		lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-				 cached_state);
+		if (nowait) {
+			if (!try_lock_extent(io_tree, lockstart, lockend))
+				return -EAGAIN;
+		} else {
+			lock_extent_bits(io_tree, lockstart, lockend, cached_state);
+		}
 		/*
 		 * We're concerned with the entire range that we're going to be
 		 * doing DIO to, so we need to make sure there's no ordered
@@ -7278,10 +7286,14 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 							 lockstart, lockend)))
 			break;
 
-		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-				     cached_state);
+		unlock_extent_cached(io_tree, lockstart, lockend, cached_state);
 
 		if (ordered) {
+			if (nowait) {
+				btrfs_put_ordered_extent(ordered);
+				ret = -EAGAIN;
+				break;
+			}
 			/*
 			 * If we are doing a DIO read and the ordered extent we
 			 * found is for a buffered write, we can not wait for it
@@ -7301,7 +7313,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 			    test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags))
 				btrfs_start_ordered_extent(ordered, 1);
 			else
-				ret = -ENOTBLK;
+				ret = nowait ? -EAGAIN : -ENOTBLK;
 			btrfs_put_ordered_extent(ordered);
 		} else {
 			/*
@@ -7317,7 +7329,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 			 * ordered extent to complete while holding a lock on
 			 * that page.
 			 */
-			ret = -ENOTBLK;
+			ret = nowait ? -EAGAIN : -ENOTBLK;
 		}
 
 		if (ret)
@@ -7572,12 +7584,12 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 
 	/*
 	 * If this errors out it's because we couldn't invalidate pagecache for
-	 * this range and we need to fallback to buffered.
+	 * this range and we need to fallback to buffered IO, or we are doing a
+	 * NOWAIT read/write and we need to block.
 	 */
-	if (lock_extent_direct(inode, lockstart, lockend, &cached_state, write)) {
-		ret = -ENOTBLK;
+	ret = lock_extent_direct(inode, lockstart, lockend, &cached_state, flags);
+	if (ret < 0)
 		goto err;
-	}
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len);
 	if (IS_ERR(em)) {