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>
This commit is contained in:
parent
99ff6cf0e6
commit
aed434ada6
51
fs/namei.c
51
fs/namei.c
|
@ -1018,21 +1018,6 @@ const char *get_link(struct nameidata *nd)
|
||||||
return res;
|
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
|
* 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);
|
set_root_rcu(nd);
|
||||||
|
|
||||||
while (1) {
|
while (1) {
|
||||||
if (nd->path.dentry == nd->root.dentry &&
|
if (path_equal(&nd->path, &nd->root))
|
||||||
nd->path.mnt == nd->root.mnt) {
|
|
||||||
break;
|
break;
|
||||||
}
|
|
||||||
if (nd->path.dentry != nd->path.mnt->mnt_root) {
|
if (nd->path.dentry != nd->path.mnt->mnt_root) {
|
||||||
struct dentry *old = nd->path.dentry;
|
struct dentry *old = nd->path.dentry;
|
||||||
struct dentry *parent = old->d_parent;
|
struct dentry *parent = old->d_parent;
|
||||||
|
@ -1300,34 +1283,42 @@ static int follow_dotdot_rcu(struct nameidata *nd)
|
||||||
|
|
||||||
inode = parent->d_inode;
|
inode = parent->d_inode;
|
||||||
seq = read_seqcount_begin(&parent->d_seq);
|
seq = read_seqcount_begin(&parent->d_seq);
|
||||||
if (read_seqcount_retry(&old->d_seq, nd->seq))
|
if (unlikely(read_seqcount_retry(&old->d_seq, nd->seq)))
|
||||||
goto failed;
|
return -ECHILD;
|
||||||
nd->path.dentry = parent;
|
nd->path.dentry = parent;
|
||||||
nd->seq = seq;
|
nd->seq = seq;
|
||||||
break;
|
break;
|
||||||
}
|
} else {
|
||||||
if (!follow_up_rcu(&nd->path))
|
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;
|
break;
|
||||||
inode = nd->path.dentry->d_inode;
|
/* we know that mountpoint was pinned */
|
||||||
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
|
nd->path.dentry = mountpoint;
|
||||||
|
nd->path.mnt = &mparent->mnt;
|
||||||
|
inode = inode2;
|
||||||
|
nd->seq = seq;
|
||||||
}
|
}
|
||||||
while (d_mountpoint(nd->path.dentry)) {
|
}
|
||||||
|
while (unlikely(d_mountpoint(nd->path.dentry))) {
|
||||||
struct mount *mounted;
|
struct mount *mounted;
|
||||||
mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
|
mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
|
||||||
|
if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
|
||||||
|
return -ECHILD;
|
||||||
if (!mounted)
|
if (!mounted)
|
||||||
break;
|
break;
|
||||||
nd->path.mnt = &mounted->mnt;
|
nd->path.mnt = &mounted->mnt;
|
||||||
nd->path.dentry = mounted->mnt.mnt_root;
|
nd->path.dentry = mounted->mnt.mnt_root;
|
||||||
inode = nd->path.dentry->d_inode;
|
inode = nd->path.dentry->d_inode;
|
||||||
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
|
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
|
||||||
if (read_seqretry(&mount_lock, nd->m_seq))
|
|
||||||
goto failed;
|
|
||||||
}
|
}
|
||||||
nd->inode = inode;
|
nd->inode = inode;
|
||||||
return 0;
|
return 0;
|
||||||
|
|
||||||
failed:
|
|
||||||
return -ECHILD;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
|
|
Loading…
Reference in New Issue