@@ -491,7 +491,7 @@ struct nameidata {
struct path root;
struct inode *inode; /* path.dentry.d_inode */
unsigned int flags;
- unsigned seq, m_seq;
+ unsigned seq, m_seq, r_seq;
int last_type;
unsigned depth;
int total_link_count;
@@ -1828,19 +1828,35 @@ static inline int may_lookup(struct nameidata *nd)
static inline int handle_dots(struct nameidata *nd, int type)
{
if (type == LAST_DOTDOT) {
- /*
- * LOOKUP_BENEATH resolving ".." is not currently safe -- races can
- * cause our parent to have moved outside of the root and us to skip
- * over it.
- */
- if (unlikely(nd->flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT)))
- return -EXDEV;
+ int error = 0;
+
if (!nd->root.mnt)
set_root(nd);
- if (nd->flags & LOOKUP_RCU) {
- return follow_dotdot_rcu(nd);
- } else
- return follow_dotdot(nd);
+ if (nd->flags & LOOKUP_RCU)
+ error = follow_dotdot_rcu(nd);
+ else
+ error = follow_dotdot(nd);
+ if (error)
+ return error;
+
+ if (unlikely(nd->flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT))) {
+ bool m_retry = read_seqretry(&mount_lock, nd->m_seq);
+ bool r_retry = read_seqretry(&rename_lock, nd->r_seq);
+
+ /*
+ * Don't bother checking unless there's a racing
+ * rename(2) or MS_MOVE.
+ */
+ if (likely(!m_retry && !r_retry))
+ return 0;
+
+ if (m_retry && !(nd->flags & LOOKUP_RCU))
+ nd->m_seq = read_seqbegin(&mount_lock);
+ if (r_retry)
+ nd->r_seq = read_seqbegin(&rename_lock);
+ if (!path_is_under(&nd->path, &nd->root))
+ return -EXDEV;
+ }
}
return 0;
}
@@ -2361,6 +2377,11 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
nd->last_type = LAST_ROOT; /* if there are only slashes... */
nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
nd->depth = 0;
+
+ nd->m_seq = read_seqbegin(&mount_lock);
+ if (unlikely(flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT)))
+ nd->r_seq = read_seqbegin(&rename_lock);
+
if (flags & LOOKUP_ROOT) {
struct dentry *root = nd->root.dentry;
struct inode *inode = root->d_inode;
@@ -2371,7 +2392,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
if (flags & LOOKUP_RCU) {
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
nd->root_seq = nd->seq;
- nd->m_seq = read_seqbegin(&mount_lock);
} else {
path_get(&nd->path);
}
@@ -2382,8 +2402,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
nd->path.mnt = NULL;
nd->path.dentry = NULL;
- nd->m_seq = read_seqbegin(&mount_lock);
-
if (unlikely(nd->flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT))) {
error = dirfd_path_init(nd);
if (unlikely(error))
This patch allows for LOOKUP_BENEATH and LOOKUP_IN_ROOT to safely permit ".." resolution (in the case of LOOKUP_BENEATH the resolution will still fail if ".." resolution would resolve a path outside of the root -- while LOOKUP_IN_ROOT will chroot(2)-style scope it). magic-link jumps are still disallowed entirely because now they could result in inconsistent behaviour if resolution encounters a subsequent "..". The need for this patch is explained by observing there is a fairly easy-to-exploit race condition with chroot(2) (and thus by extension LOOKUP_IN_ROOT and LOOKUP_BENEATH if ".." is allowed) where a rename(2) of a path can be used to "skip over" nd->root and thus escape to the filesystem above nd->root. thread1 [attacker]: for (;;) renameat2(AT_FDCWD, "/a/b/c", AT_FDCWD, "/a/d", RENAME_EXCHANGE); thread2 [victim]: for (;;) resolveat(dirb, "b/c/../../etc/shadow", RESOLVE_IN_ROOT); With fairly significant regularity, thread2 will resolve to "/etc/shadow" rather than "/a/b/etc/shadow". There is also a similar (though somewhat more privileged) attack using MS_MOVE. With this patch, such cases will be detected *during* ".." resolution (which is the weak point of chroot(2) -- since walking *into* a subdirectory tautologically cannot result in you walking *outside* nd->root -- except through a bind-mount or magic-link). By detecting this at ".." resolution (rather than checking only at the end of the entire resolution) we can both correct escapes by jumping back to the root (in the case of LOOKUP_IN_ROOT), as well as avoid revealing to attackers the structure of the filesystem outside of the root (through timing attacks for instance). In order to avoid a quadratic lookup with each ".." entry, we only activate the slow path if a write through &rename_lock or &mount_lock has occurred during path resolution (&rename_lock and &mount_lock are re-taken to further optimise the lookup). Since the primary attack being protected against is MS_MOVE or rename(2), not doing additional checks unless a mount or rename have occurred avoids making the common case slow. The use of path_is_under() here might seem suspect, but on further inspection of the most important race (a path was *inside* the root but is now *outside*), there appears to be no attack potential: * If path_is_under() occurs before the rename, then the path will be resolved -- however the path was originally inside the root and thus there is no escape (and to userspace it'd look like the rename occurred after the path was resolved). If path_is_under() occurs afterwards, the resolution is blocked. * Subsequent ".." jumps are guaranteed to check path_is_under() -- by construction, &rename_lock or &mount_lock must have been taken by the attacker after path_is_under() returned in the victim. Thus ".." will not be able to escape from the previously-inside-root path. * Walking down in the moved path is still safe since the entire subtree was moved (either by rename(2) or MS_MOVE) and because (as discussed above) walking down is safe. I have run a variant of the above attack in a loop on several machines with this patch, and no instances of a breakout were detected. While this is not concrete proof that this is safe, when combined with the above argument it should lend some trustworthiness to this construction. Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Jann Horn <jannh@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Aleksa Sarai <cyphar@cyphar.com> --- fs/namei.c | 48 +++++++++++++++++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 15 deletions(-)