summaryrefslogtreecommitdiffstats
path: root/fs/namei.c
diff options
context:
space:
mode:
authorAl Viro <viro@zeniv.linux.org.uk>2015-05-12 12:22:47 -0400
committerAl Viro <viro@zeniv.linux.org.uk>2015-05-15 01:10:38 -0400
commitaed434ada68573549d9f5106cde26b94c48e51c2 (patch)
tree9cf3fe783412ce33d95e96deed19f260be0bd16d /fs/namei.c
parent99ff6cf0e67ada025ba8054a055862383355ec0e (diff)
downloadlinux-aed434ada68573549d9f5106cde26b94c48e51c2.tar.bz2
namei: be careful with mountpoint crossings in follow_dotdot_rcu()
Otherwise we are risking a hard error where nonlazy restart would be the right thing to do; it's a very narrow race with mount --move and most of the time it ends up being completely harmless, but it's possible to construct a case when we'll get a bogus hard error instead of falling back to non-lazy walk... For one thing, when crossing _into_ overmount of parent we need to check for mount_lock bumps when we get NULL from __lookup_mnt() as well. For another, and less exotically, we need to make sure that the data fetched in follow_up_rcu() had been consistent. ->mnt_mountpoint is pinned for as long as it is a mountpoint, but we need to check mount_lock after fetching to verify that. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Diffstat (limited to 'fs/namei.c')
-rw-r--r--fs/namei.c51
1 files changed, 21 insertions, 30 deletions
diff --git a/fs/namei.c b/fs/namei.c
index 0cccb24ac0b7..d5f45681ea88 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1018,21 +1018,6 @@ const char *get_link(struct nameidata *nd)
return res;
}
-static int follow_up_rcu(struct path *path)
-{
- struct mount *mnt = real_mount(path->mnt);
- struct mount *parent;
- struct dentry *mountpoint;
-
- parent = mnt->mnt_parent;
- if (&parent->mnt == path->mnt)
- return 0;
- mountpoint = mnt->mnt_mountpoint;
- path->dentry = mountpoint;
- path->mnt = &parent->mnt;
- return 1;
-}
-
/*
* follow_up - Find the mountpoint of path's vfsmount
*
@@ -1289,10 +1274,8 @@ static int follow_dotdot_rcu(struct nameidata *nd)
set_root_rcu(nd);
while (1) {
- if (nd->path.dentry == nd->root.dentry &&
- nd->path.mnt == nd->root.mnt) {
+ if (path_equal(&nd->path, &nd->root))
break;
- }
if (nd->path.dentry != nd->path.mnt->mnt_root) {
struct dentry *old = nd->path.dentry;
struct dentry *parent = old->d_parent;
@@ -1300,34 +1283,42 @@ static int follow_dotdot_rcu(struct nameidata *nd)
inode = parent->d_inode;
seq = read_seqcount_begin(&parent->d_seq);
- if (read_seqcount_retry(&old->d_seq, nd->seq))
- goto failed;
+ if (unlikely(read_seqcount_retry(&old->d_seq, nd->seq)))
+ return -ECHILD;
nd->path.dentry = parent;
nd->seq = seq;
break;
+ } else {
+ struct mount *mnt = real_mount(nd->path.mnt);
+ struct mount *mparent = mnt->mnt_parent;
+ struct dentry *mountpoint = mnt->mnt_mountpoint;
+ struct inode *inode2 = mountpoint->d_inode;
+ unsigned seq = read_seqcount_begin(&mountpoint->d_seq);
+ if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
+ return -ECHILD;
+ if (&mparent->mnt == nd->path.mnt)
+ break;
+ /* we know that mountpoint was pinned */
+ nd->path.dentry = mountpoint;
+ nd->path.mnt = &mparent->mnt;
+ inode = inode2;
+ nd->seq = seq;
}
- if (!follow_up_rcu(&nd->path))
- break;
- inode = nd->path.dentry->d_inode;
- nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
}
- while (d_mountpoint(nd->path.dentry)) {
+ while (unlikely(d_mountpoint(nd->path.dentry))) {
struct mount *mounted;
mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
+ if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
+ return -ECHILD;
if (!mounted)
break;
nd->path.mnt = &mounted->mnt;
nd->path.dentry = mounted->mnt.mnt_root;
inode = nd->path.dentry->d_inode;
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
- if (read_seqretry(&mount_lock, nd->m_seq))
- goto failed;
}
nd->inode = inode;
return 0;
-
-failed:
- return -ECHILD;
}
/*