fs/coredump: prevent fsuid=0 dumps into user-controlled directories

commit 378c6520e7d29280f400ef2ceaf155c86f05a71a upstream.

This commit fixes the following security hole affecting systems where
all of the following conditions are fulfilled:

 - The fs.suid_dumpable sysctl is set to 2.
 - The kernel.core_pattern sysctl's value starts with "/". (Systems
   where kernel.core_pattern starts with "|/" are not affected.)
 - Unprivileged user namespace creation is permitted. (This is
   true on Linux >=3.8, but some distributions disallow it by
   default using a distro patch.)

Under these conditions, if a program executes under secure exec rules,
causing it to run with the SUID_DUMP_ROOT flag, then unshares its user
namespace, changes its root directory and crashes, the coredump will be
written using fsuid=0 and a path derived from kernel.core_pattern - but
this path is interpreted relative to the root directory of the process,
allowing the attacker to control where a coredump will be written with
root privileges.

To fix the security issue, always interpret core_pattern for dumps that
are written under SUID_DUMP_ROOT relative to the root directory of init.

Signed-off-by: Jann Horn <jann@thejh.net>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.2: adjust filename, context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

3 files changed, 29 insertions, 9 deletions

diff --git a/fs/exec.c b/fs/exec.c
index aba5e13a6a68..a0006d85785c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -55,6 +55,9 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/oom.h>
 #include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/path.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -2246,6 +2249,8 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
  		}
 	} else {
 		struct inode *inode;
+		int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW |
+				 O_LARGEFILE | O_EXCL;
 
 		if (cprm.limit < binfmt->min_coredump)
 			goto fail_unlock;
@@ -2284,10 +2289,27 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 		 * what matters is that at least one of the two processes
 		 * writes its coredump successfully, not which one.
 		 */
-		cprm.file = filp_open(cn.corename,
-				 O_CREAT | 2 | O_NOFOLLOW |
-				 O_LARGEFILE | O_EXCL,
-				 0600);
+		if (need_suid_safe) {
+			/*
+			 * Using user namespaces, normal user tasks can change
+			 * their current->fs->root to point to arbitrary
+			 * directories. Since the intention of the "only dump
+			 * with a fully qualified path" rule is to control where
+			 * coredumps may be placed using root privileges,
+			 * current->fs->root must not be used. Instead, use the
+			 * root directory of init_task.
+			 */
+			struct path root;
+
+			task_lock(&init_task);
+			get_fs_root(init_task.fs, &root);
+			task_unlock(&init_task);
+			cprm.file = file_open_root(root.dentry, root.mnt,
+				cn.corename, open_flags, 0600);
+			path_put(&root);
+		} else {
+			cprm.file = filp_open(cn.corename, open_flags, 0600);
+		}
 		if (IS_ERR(cprm.file))
 			goto fail_unlock;
 
diff --git a/fs/fhandle.c b/fs/fhandle.c
index c9e18f3ecc41..710438a1e021 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -229,7 +229,7 @@ long do_handle_open(int mountdirfd,
 		path_put(&path);
 		return fd;
 	}
-	file = file_open_root(path.dentry, path.mnt, "", open_flag);
+	file = file_open_root(path.dentry, path.mnt, "", open_flag, 0);
 	if (IS_ERR(file)) {
 		put_unused_fd(fd);
 		retval =  PTR_ERR(file);
diff --git a/fs/open.c b/fs/open.c
index b8485d3cef97..ca155d4f23d3 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -958,12 +958,10 @@ struct file *filp_open(const char *filename, int flags, int mode)
 EXPORT_SYMBOL(filp_open);
 
 struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
-			    const char *filename, int flags)
+			    const char *filename, int flags, umode_t mode)
 {
 	struct open_flags op;
-	int lookup = build_open_flags(flags, 0, &op);
-	if (flags & O_CREAT)
-		return ERR_PTR(-EINVAL);
+	int lookup = build_open_flags(flags, mode, &op);
 	if (!filename && (flags & O_DIRECTORY))
 		if (!dentry->d_inode->i_op->lookup)
 			return ERR_PTR(-ENOTDIR);