f2fs: fix multiple f2fs_add_link() calls having same name

commit 88c5c13a5027b36d914536fdba23f069d7067204 upstream.

It turns out a stakable filesystem like sdcardfs in AOSP can trigger multiple
vfs_create() to lower filesystem. In that case, f2fs will add multiple dentries
having same name which breaks filesystem consistency.

Until upper layer fixes, let's work around by f2fs, which shows actually not
much performance regression.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

2 files changed, 30 insertions, 5 deletions

diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 369f4513be37..ebdc90fc71b7 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -207,9 +207,13 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
                 f2fs_put_page(dentry_page, 0);
         }
 
-        if (!de && room && F2FS_I(dir)->chash != namehash) {
-                F2FS_I(dir)->chash = namehash;
-                F2FS_I(dir)->clevel = level;
+        /* This is to increase the speed of f2fs_create */
+        if (!de && room) {
+                F2FS_I(dir)->task = current;
+                if (F2FS_I(dir)->chash != namehash) {
+                        F2FS_I(dir)->chash = namehash;
+                        F2FS_I(dir)->clevel = level;
+                }
         }
 
         return de;
@@ -643,14 +647,34 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
                                 struct inode *inode, nid_t ino, umode_t mode)
 {
         struct fscrypt_name fname;
+        struct page *page = NULL;
+        struct f2fs_dir_entry *de = NULL;
         int err;
 
         err = fscrypt_setup_filename(dir, name, 0, &fname);
         if (err)
                 return err;
 
-        err = __f2fs_do_add_link(dir, &fname, inode, ino, mode);
-
+        /*
+         * An immature stakable filesystem shows a race condition between lookup
+         * and create. If we have same task when doing lookup and create, it's
+         * definitely fine as expected by VFS normally. Otherwise, let's just
+         * verify on-disk dentry one more time, which guarantees filesystem
+         * consistency more.
+         */
+        if (current != F2FS_I(dir)->task) {
+                de = __f2fs_find_entry(dir, &fname, &page);
+                F2FS_I(dir)->task = NULL;
+        }
+        if (de) {
+                f2fs_dentry_kunmap(dir, page);
+                f2fs_put_page(page, 0);
+                err = -EEXIST;
+        } else if (IS_ERR(page)) {
+                err = PTR_ERR(page);
+        } else {
+                err = __f2fs_do_add_link(dir, &fname, inode, ino, mode);
+        }
         fscrypt_free_filename(&fname);
         return err;
 }
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 506af456412f..ecc3fd0ca6bb 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -431,6 +431,7 @@ struct f2fs_inode_info {
         atomic_t dirty_pages;           /* # of dirty pages */
         f2fs_hash_t chash;              /* hash value of given file name */
         unsigned int clevel;            /* maximum level of given file name */
+        struct task_struct *task;       /* lookup and create consistency */
         nid_t i_xattr_nid;              /* node id that contains xattrs */
         unsigned long long xattr_ver;   /* cp version of xattr modification */
         loff_t  last_disk_size;         /* lastly written file size */