Merge tag 'for-6.14-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - extent map shrinker fixes:
     - fix potential use after free accessing an inode to reach fs_info,
       the shrinker could do iput() in the meantime
     - skip unnecessary scanning of inodes without extent maps
     - do direct iput(), no need for indirection via workqueue

 - in block < page mode, fix race when extending i_size in buffered mode

 - fix minor memory leak in selftests

 - print descriptive error message when seeding device is not found

* tag 'for-6.14-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: fix data overwriting bug during buffered write when block size < page size
  btrfs: output an error message if btrfs failed to find the seed fsid
  btrfs: do regular iput instead of delayed iput during extent map shrinking
  btrfs: skip inodes without loaded extent maps when shrinking extent maps
  btrfs: fix use-after-free on inode when scanning root during em shrinking
  btrfs: selftests: fix btrfs_test_delayed_refs() leak of transaction

4 files changed, 73 insertions, 26 deletions

diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 67ce85ff0ae2..7f46abbd6311 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -1128,6 +1128,8 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
 	long nr_dropped = 0;
 	struct rb_node *node;
 
+	lockdep_assert_held_write(&tree->lock);
+
 	/*
 	 * Take the mmap lock so that we serialize with the inode logging phase
 	 * of fsync because we may need to set the full sync flag on the inode,
@@ -1139,28 +1141,12 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
 	 * to find new extents, which may not be there yet because ordered
 	 * extents haven't completed yet.
 	 *
-	 * We also do a try lock because otherwise we could deadlock. This is
-	 * because the shrinker for this filesystem may be invoked while we are
-	 * in a path that is holding the mmap lock in write mode. For example in
-	 * a reflink operation while COWing an extent buffer, when allocating
-	 * pages for a new extent buffer and under memory pressure, the shrinker
-	 * may be invoked, and therefore we would deadlock by attempting to read
-	 * lock the mmap lock while we are holding already a write lock on it.
+	 * We also do a try lock because we don't want to block for too long and
+	 * we are holding the extent map tree's lock in write mode.
 	 */
 	if (!down_read_trylock(&inode->i_mmap_lock))
 		return 0;
 
-	/*
-	 * We want to be fast so if the lock is busy we don't want to spend time
-	 * waiting for it - either some task is about to do IO for the inode or
-	 * we may have another task shrinking extent maps, here in this code, so
-	 * skip this inode.
-	 */
-	if (!write_trylock(&tree->lock)) {
-		up_read(&inode->i_mmap_lock);
-		return 0;
-	}
-
 	node = rb_first(&tree->root);
 	while (node) {
 		struct rb_node *next = rb_next(node);
@@ -1201,12 +1187,61 @@ next:
 			break;
 		node = next;
 	}
-	write_unlock(&tree->lock);
 	up_read(&inode->i_mmap_lock);
 
 	return nr_dropped;
 }
 
+static struct btrfs_inode *find_first_inode_to_shrink(struct btrfs_root *root,
+						      u64 min_ino)
+{
+	struct btrfs_inode *inode;
+	unsigned long from = min_ino;
+
+	xa_lock(&root->inodes);
+	while (true) {
+		struct extent_map_tree *tree;
+
+		inode = xa_find(&root->inodes, &from, ULONG_MAX, XA_PRESENT);
+		if (!inode)
+			break;
+
+		tree = &inode->extent_tree;
+
+		/*
+		 * We want to be fast so if the lock is busy we don't want to
+		 * spend time waiting for it (some task is about to do IO for
+		 * the inode).
+		 */
+		if (!write_trylock(&tree->lock))
+			goto next;
+
+		/*
+		 * Skip inode if it doesn't have loaded extent maps, so we avoid
+		 * getting a reference and doing an iput later. This includes
+		 * cases like files that were opened for things like stat(2), or
+		 * files with all extent maps previously released through the
+		 * release folio callback (btrfs_release_folio()) or released in
+		 * a previous run, or directories which never have extent maps.
+		 */
+		if (RB_EMPTY_ROOT(&tree->root)) {
+			write_unlock(&tree->lock);
+			goto next;
+		}
+
+		if (igrab(&inode->vfs_inode))
+			break;
+
+		write_unlock(&tree->lock);
+next:
+		from = btrfs_ino(inode) + 1;
+		cond_resched_lock(&root->inodes.xa_lock);
+	}
+	xa_unlock(&root->inodes);
+
+	return inode;
+}
+
 static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx *ctx)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -1214,21 +1249,21 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
 	long nr_dropped = 0;
 	u64 min_ino = fs_info->em_shrinker_last_ino + 1;
 
-	inode = btrfs_find_first_inode(root, min_ino);
+	inode = find_first_inode_to_shrink(root, min_ino);
 	while (inode) {
 		nr_dropped += btrfs_scan_inode(inode, ctx);
+		write_unlock(&inode->extent_tree.lock);
 
 		min_ino = btrfs_ino(inode) + 1;
 		fs_info->em_shrinker_last_ino = btrfs_ino(inode);
-		btrfs_add_delayed_iput(inode);
+		iput(&inode->vfs_inode);
 
-		if (ctx->scanned >= ctx->nr_to_scan ||
-		    btrfs_fs_closing(inode->root->fs_info))
+		if (ctx->scanned >= ctx->nr_to_scan || btrfs_fs_closing(fs_info))
 			break;
 
 		cond_resched();
 
-		inode = btrfs_find_first_inode(root, min_ino);
+		inode = find_first_inode_to_shrink(root, min_ino);
 	}
 
 	if (inode) {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index ed3c0d6546c5..0b568c8d24cb 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1090,7 +1090,7 @@ ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i)
 	u64 lockend;
 	size_t num_written = 0;
 	ssize_t ret;
-	loff_t old_isize = i_size_read(inode);
+	loff_t old_isize;
 	unsigned int ilock_flags = 0;
 	const bool nowait = (iocb->ki_flags & IOCB_NOWAIT);
 	unsigned int bdp_flags = (nowait ? BDP_ASYNC : 0);
@@ -1103,6 +1103,13 @@ ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i)
 	if (ret < 0)
 		return ret;
 
+	/*
+	 * We can only trust the isize with inode lock held, or it can race with
+	 * other buffered writes and cause incorrect call of
+	 * pagecache_isize_extended() to overwrite existing data.
+	 */
+	old_isize = i_size_read(inode);
+
 	ret = generic_write_checks(iocb, i);
 	if (ret <= 0)
 		goto out;
diff --git a/fs/btrfs/tests/delayed-refs-tests.c b/fs/btrfs/tests/delayed-refs-tests.c
index 6558508c2ddf..265370e79a54 100644
--- a/fs/btrfs/tests/delayed-refs-tests.c
+++ b/fs/btrfs/tests/delayed-refs-tests.c
@@ -1009,6 +1009,7 @@ int btrfs_test_delayed_refs(u32 sectorsize, u32 nodesize)
 	if (!ret)
 		ret = select_delayed_refs_test(&trans);
 
+	kfree(transaction);
 out_free_fs_info:
 	btrfs_free_dummy_fs_info(fs_info);
 	return ret;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0a0776489055..fb22d4425cb0 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7200,8 +7200,12 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
 
 	fs_devices = find_fsid(fsid, NULL);
 	if (!fs_devices) {
-		if (!btrfs_test_opt(fs_info, DEGRADED))
+		if (!btrfs_test_opt(fs_info, DEGRADED)) {
+			btrfs_err(fs_info,
+		"failed to find fsid %pU when attempting to open seed devices",
+				  fsid);
 			return ERR_PTR(-ENOENT);
+		}
 
 		fs_devices = alloc_fs_devices(fsid);
 		if (IS_ERR(fs_devices))