Fix sget() race with failing mount

If sget() finds a matching superblock being set up, it'll
grab an active reference to it and grab s_umount.  That's
fine - we'll wait for completion of foofs_get_sb() that way.
However, if said foofs_get_sb() fails we'll end up holding
the halfway-created superblock.  deactivate_locked_super()
called by foofs_get_sb() will just unlock the sucker since
we are holding another active reference to it.

What we need is a way to tell if superblock has been successfully
set up.  Unfortunately, neither ->s_root nor the check for
MS_ACTIVE quite fit.  Cheap and easy way, suitable for backport:
new flag set by the (only) caller of ->get_sb().  If that flag
isn't present by the time sget() grabbed s_umount on preexisting
superblock it has found, it's seeing a stillborn and should
just bury it with deactivate_locked_super() (and repeat the search).

Longer term we want to set that flag in ->get_sb() instances (and
check for it to distinguish between "sget() found us a live sb"
and "sget() has allocated an sb, we need to set it up" in there,
instead of checking ->s_root as we do now).

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: stable@kernel.org

diff --git a/fs/namespace.c b/fs/namespace.c
index 88058de59c7c2ca9edf14453f1fbeeaa4017bfa8..32dcd24bbc9a3a9fef972f95451918961574b67b 100644 (file)
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1984,7 +1984,7 @@ long do_mount(char *dev_name, char *dir_name, char *type_page,
        if (flags & MS_RDONLY)
                mnt_flags |= MNT_READONLY;
 
-       flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE |
+       flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
                   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
                   MS_STRICTATIME);
 

diff --git a/fs/super.c b/fs/super.c
index 3479ca6f005ff7c87d22d52cd1381a89e06d0fbb..bd9eea4bb2bbe768beab53f07c61e98c8505f404 100644 (file)
--- a/fs/super.c
+++ b/fs/super.c
@@ -305,8 +305,13 @@ retry:
                        if (s) {
                                up_write(&s->s_umount);
                                destroy_super(s);
+                               s = NULL;
                        }
                        down_write(&old->s_umount);
+                       if (unlikely(!(old->s_flags & MS_BORN))) {
+                               deactivate_locked_super(old);
+                               goto retry;
+                       }
                        return old;
                }
        }
@@ -918,6 +923,7 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void
                goto out_free_secdata;
        BUG_ON(!mnt->mnt_sb);
        WARN_ON(!mnt->mnt_sb->s_bdi);
+       mnt->mnt_sb->s_flags |= MS_BORN;
 
        error = security_sb_kern_mount(mnt->mnt_sb, flags, secdata);
        if (error)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9bedf4219f8381b5b73a0c532c392155e1ca33b4..58e4b035e2825ee8b65e14cd1d797cf7a6d1037d 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -209,6 +209,7 @@ struct inodes_stat_t {
 #define MS_KERNMOUNT   (1<<22) /* this is a kern_mount call */
 #define MS_I_VERSION   (1<<23) /* Update inode I_version field */
 #define MS_STRICTATIME (1<<24) /* Always perform atime updates */
+#define MS_BORN                (1<<29)
 #define MS_ACTIVE      (1<<30)
 #define MS_NOUSER      (1<<31)