[f2fs-dev][PATCH v2] f2fs: reposition unlock_new_inode to prevent accessing invalid inode

[Chao Yu]

As the race condition on the inode cache, following scenario can appear:
[Thread a]				[Thread b]
					->f2fs_mkdir
					  ->f2fs_add_link
					    ->__f2fs_add_link
					      ->init_inode_metadata failed here
->gc_thread_func
  ->f2fs_gc
    ->do_garbage_collect
      ->gc_data_segment
        ->f2fs_iget
          ->iget_locked
            ->wait_on_inode
					  ->unlock_new_inode
        ->move_data_page
					  ->make_bad_inode
					  ->iput

When we fail in create/symlink/mkdir/mknod/tmpfile, the new allocated inode
should be set as bad to avoid being accessed by other thread. But in above
scenario, it allows f2fs to access the invalid inode before this inode was set
as bad.
This patch fix the potential problem, and this issue was found by code review.

change log from v1:
 o Add condition judgment in gc_data_segment() suggested by Changman Lee.
 o use iget_failed to simplify code.

Signed-off-by: Chao Yu <chao2.yu@xxxxxxxxxxx>
---
 fs/f2fs/gc.c    |  2 +-
 fs/f2fs/namei.c | 20 +++++---------------
 2 files changed, 6 insertions(+), 16 deletions(-)

diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index e8507b1..943a31d 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -593,7 +593,7 @@ next_step:
 
 		if (phase == 2) {
 			inode = f2fs_iget(sb, dni.ino);
-			if (IS_ERR(inode))
+			if (IS_ERR(inode) || is_bad_inode(inode))
 				continue;
 
 			start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 6b53ce9..ee103fd 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -134,9 +134,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	return 0;
 out:
 	clear_nlink(inode);
-	unlock_new_inode(inode);
-	make_bad_inode(inode);
-	iput(inode);
+	iget_failed(inode);
 	alloc_nid_failed(sbi, ino);
 	return err;
 }
@@ -267,9 +265,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	return err;
 out:
 	clear_nlink(inode);
-	unlock_new_inode(inode);
-	make_bad_inode(inode);
-	iput(inode);
+	iget_failed(inode);
 	alloc_nid_failed(sbi, inode->i_ino);
 	return err;
 }
@@ -308,9 +304,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 out_fail:
 	clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
 	clear_nlink(inode);
-	unlock_new_inode(inode);
-	make_bad_inode(inode);
-	iput(inode);
+	iget_failed(inode);
 	alloc_nid_failed(sbi, inode->i_ino);
 	return err;
 }
@@ -354,9 +348,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	return 0;
 out:
 	clear_nlink(inode);
-	unlock_new_inode(inode);
-	make_bad_inode(inode);
-	iput(inode);
+	iget_failed(inode);
 	alloc_nid_failed(sbi, inode->i_ino);
 	return err;
 }
@@ -688,9 +680,7 @@ release_out:
 out:
 	f2fs_unlock_op(sbi);
 	clear_nlink(inode);
-	unlock_new_inode(inode);
-	make_bad_inode(inode);
-	iput(inode);
+	iget_failed(inode);
 	alloc_nid_failed(sbi, inode->i_ino);
 	return err;
 }
-- 
2.0.1.474.g72c7794


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/