[PATCH 1/3] fs: add O_BENEATH flag to openat(2)

From: David Drysdale
Date: Mon Nov 03 2014 - 06:56:11 EST

Add a new O_BENEATH flag for openat(2) which restricts the
provided path, rejecting (with -EACCES) paths that are not beneath
the provided dfd. In particular, reject:
- paths that contain .. components
- paths that begin with /
- symlinks that have paths as above.

Signed-off-by: David Drysdale <drysdale@xxxxxxxxxx>
---
arch/alpha/include/uapi/asm/fcntl.h | 1 +
arch/parisc/include/uapi/asm/fcntl.h | 1 +
arch/sparc/include/uapi/asm/fcntl.h | 1 +
fs/fcntl.c | 5 +++--
fs/namei.c | 43 ++++++++++++++++++++++++------------
fs/open.c | 4 +++-
include/linux/namei.h | 1 +
include/uapi/asm-generic/fcntl.h | 4 ++++
8 files changed, 43 insertions(+), 17 deletions(-)

diff --git a/arch/alpha/include/uapi/asm/fcntl.h b/arch/alpha/include/uapi/asm/fcntl.h
index 09f49a6b87d1..76a87038d2c1 100644
--- a/arch/alpha/include/uapi/asm/fcntl.h
+++ b/arch/alpha/include/uapi/asm/fcntl.h
@@ -33,6 +33,7 @@

#define O_PATH 040000000
#define __O_TMPFILE 0100000000
+#define O_BENEATH 0200000000 /* no / or .. in openat path */

#define F_GETLK 7
#define F_SETLK 8
diff --git a/arch/parisc/include/uapi/asm/fcntl.h b/arch/parisc/include/uapi/asm/fcntl.h
index 34a46cbc76ed..3adadf72f929 100644
--- a/arch/parisc/include/uapi/asm/fcntl.h
+++ b/arch/parisc/include/uapi/asm/fcntl.h
@@ -21,6 +21,7 @@

#define O_PATH 020000000
#define __O_TMPFILE 040000000
+#define O_BENEATH 080000000 /* no / or .. in openat path */

#define F_GETLK64 8
#define F_SETLK64 9
diff --git a/arch/sparc/include/uapi/asm/fcntl.h b/arch/sparc/include/uapi/asm/fcntl.h
index 7e8ace5bf760..ea38f0bd6cec 100644
--- a/arch/sparc/include/uapi/asm/fcntl.h
+++ b/arch/sparc/include/uapi/asm/fcntl.h
@@ -36,6 +36,7 @@

#define O_PATH 0x1000000
#define __O_TMPFILE 0x2000000
+#define O_BENEATH 0x4000000 /* no / or .. in openat path */

#define F_GETOWN 5 /* for sockets. */
#define F_SETOWN 6 /* for sockets. */
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 22d1c3df61ac..c07a32efc34b 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -747,14 +747,15 @@ static int __init fcntl_init(void)
* Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
* is defined as O_NONBLOCK on some platforms and not on others.
*/
- BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+ BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
O_RDONLY | O_WRONLY | O_RDWR |
O_CREAT | O_EXCL | O_NOCTTY |
O_TRUNC | O_APPEND | /* O_NONBLOCK | */
__O_SYNC | O_DSYNC | FASYNC |
O_DIRECT | O_LARGEFILE | O_DIRECTORY |
O_NOFOLLOW | O_NOATIME | O_CLOEXEC |
- __FMODE_EXEC | O_PATH | __O_TMPFILE
+ __FMODE_EXEC | O_PATH | __O_TMPFILE |
+ O_BENEATH
));

fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/namei.c b/fs/namei.c
index a7b05bf82d31..2fd547014b6b 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -647,7 +647,7 @@ static __always_inline void set_root(struct nameidata *nd)
get_fs_root(current->fs, &nd->root);
}

-static int link_path_walk(const char *, struct nameidata *);
+static int link_path_walk(const char *, struct nameidata *, unsigned int);

static __always_inline unsigned set_root_rcu(struct nameidata *nd)
{
@@ -819,7 +819,8 @@ static int may_linkat(struct path *link)
}

static __always_inline int
-follow_link(struct path *link, struct nameidata *nd, void **p)
+follow_link(struct path *link, struct nameidata *nd, unsigned int flags,
+ void **p)
{
struct dentry *dentry = link->dentry;
int error;
@@ -867,7 +868,7 @@ follow_link(struct path *link, struct nameidata *nd, void **p)
nd->flags |= LOOKUP_JUMPED;
}
nd->inode = nd->path.dentry->d_inode;
- error = link_path_walk(s, nd);
+ error = link_path_walk(s, nd, flags);
if (unlikely(error))
put_link(nd, link, *p);
}
@@ -1585,7 +1586,8 @@ out_err:
* Without that kind of total limit, nasty chains of consecutive
* symlinks can cause almost arbitrarily long lookups.
*/
-static inline int nested_symlink(struct path *path, struct nameidata *nd)
+static inline int nested_symlink(struct path *path, struct nameidata *nd,
+ unsigned int flags)
{
int res;

@@ -1603,7 +1605,7 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
struct path link = *path;
void *cookie;

- res = follow_link(&link, nd, &cookie);
+ res = follow_link(&link, nd, flags, &cookie);
if (res)
break;
res = walk_component(nd, path, LOOKUP_FOLLOW);
@@ -1739,13 +1741,19 @@ static inline u64 hash_name(const char *name)
* Returns 0 and nd will have valid dentry and mnt on success.
* Returns error and drops reference to input namei data on failure.
*/
-static int link_path_walk(const char *name, struct nameidata *nd)
+static int link_path_walk(const char *name, struct nameidata *nd,
+ unsigned int flags)
{
struct path next;
int err;

- while (*name=='/')
+ while (*name == '/') {
+ if (flags & LOOKUP_BENEATH) {
+ err = -EACCES;
+ goto exit;
+ }
name++;
+ }
if (!*name)
return 0;

@@ -1764,6 +1772,10 @@ static int link_path_walk(const char *name, struct nameidata *nd)
if (name[0] == '.') switch (hashlen_len(hash_len)) {
case 2:
if (name[1] == '.') {
+ if (flags & LOOKUP_BENEATH) {
+ err = -EACCES;
+ goto exit;
+ }
type = LAST_DOTDOT;
nd->flags |= LOOKUP_JUMPED;
}
@@ -1806,7 +1818,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
return err;

if (err) {
- err = nested_symlink(&next, nd);
+ err = nested_symlink(&next, nd, flags);
if (err)
return err;
}
@@ -1815,6 +1827,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
break;
}
}
+exit:
terminate_walk(nd);
return err;
}
@@ -1853,6 +1866,8 @@ static int path_init(int dfd, const char *name, unsigned int flags,

nd->m_seq = read_seqbegin(&mount_lock);
if (*name=='/') {
+ if (flags & LOOKUP_BENEATH)
+ return -EACCES;
if (flags & LOOKUP_RCU) {
rcu_read_lock();
nd->seq = set_root_rcu(nd);
@@ -1953,7 +1968,7 @@ static int path_lookupat(int dfd, const char *name,
return err;

current->total_link_count = 0;
- err = link_path_walk(name, nd);
+ err = link_path_walk(name, nd, flags);

if (!err && !(flags & LOOKUP_PARENT)) {
err = lookup_last(nd, &path);
@@ -1964,7 +1979,7 @@ static int path_lookupat(int dfd, const char *name,
if (unlikely(err))
break;
nd->flags |= LOOKUP_PARENT;
- err = follow_link(&link, nd, &cookie);
+ err = follow_link(&link, nd, flags, &cookie);
if (err)
break;
err = lookup_last(nd, &path);
@@ -2304,7 +2319,7 @@ path_mountpoint(int dfd, const char *name, struct path *path, unsigned int flags
return err;

current->total_link_count = 0;
- err = link_path_walk(name, &nd);
+ err = link_path_walk(name, &nd, flags);
if (err)
goto out;

@@ -2316,7 +2331,7 @@ path_mountpoint(int dfd, const char *name, struct path *path, unsigned int flags
if (unlikely(err))
break;
nd.flags |= LOOKUP_PARENT;
- err = follow_link(&link, &nd, &cookie);
+ err = follow_link(&link, &nd, flags, &cookie);
if (err)
break;
err = mountpoint_last(&nd, path);
@@ -3202,7 +3217,7 @@ static struct file *path_openat(int dfd, struct filename *pathname,
goto out;

current->total_link_count = 0;
- error = link_path_walk(pathname->name, nd);
+ error = link_path_walk(pathname->name, nd, flags);
if (unlikely(error))
goto out;

@@ -3221,7 +3236,7 @@ static struct file *path_openat(int dfd, struct filename *pathname,
break;
nd->flags |= LOOKUP_PARENT;
nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
- error = follow_link(&link, nd, &cookie);
+ error = follow_link(&link, nd, flags, &cookie);
if (unlikely(error))
break;
error = do_last(nd, &path, file, op, &opened, pathname);
diff --git a/fs/open.c b/fs/open.c
index d6fd3acde134..8afca5b87a0b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -874,7 +874,7 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
* If we have O_PATH in the open flag. Then we
* cannot have anything other than the below set of flags
*/
- flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
+ flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH | O_BENEATH;
acc_mode = 0;
} else {
acc_mode = MAY_OPEN | ACC_MODE(flags);
@@ -905,6 +905,8 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
lookup_flags |= LOOKUP_DIRECTORY;
if (!(flags & O_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
+ if (flags & O_BENEATH)
+ lookup_flags |= LOOKUP_BENEATH;
op->lookup_flags = lookup_flags;
return 0;
}
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 492de72560fa..bd0615d1143b 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -39,6 +39,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
#define LOOKUP_FOLLOW 0x0001
#define LOOKUP_DIRECTORY 0x0002
#define LOOKUP_AUTOMOUNT 0x0004
+#define LOOKUP_BENEATH 0x0008

#define LOOKUP_PARENT 0x0010
#define LOOKUP_REVAL 0x0020
diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
index 7543b3e51331..f63aa749a4fb 100644
--- a/include/uapi/asm-generic/fcntl.h
+++ b/include/uapi/asm-generic/fcntl.h
@@ -92,6 +92,10 @@
#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
#define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)

+#ifndef O_BENEATH
+#define O_BENEATH 040000000 /* no / or .. in openat path */
+#endif
+
#ifndef O_NDELAY
#define O_NDELAY O_NONBLOCK
#endif
--
2.1.0.rc2.206.gedb03e5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/