syscalls: implement execveat() system call

This patchset adds execveat(2) for x86, and is derived from Meredydd
Luff's patch from Sept 2012 (https://lkml.org/lkml/2012/9/11/528).

The primary aim of adding an execveat syscall is to allow an
implementation of fexecve(3) that does not rely on the /proc filesystem,
at least for executables (rather than scripts).  The current glibc version
of fexecve(3) is implemented via /proc, which causes problems in sandboxed
or otherwise restricted environments.

Given the desire for a /proc-free fexecve() implementation, HPA suggested
(https://lkml.org/lkml/2006/7/11/556) that an execveat(2) syscall would be
an appropriate generalization.

Also, having a new syscall means that it can take a flags argument without
back-compatibility concerns.  The current implementation just defines the
AT_EMPTY_PATH and AT_SYMLINK_NOFOLLOW flags, but other flags could be
added in future -- for example, flags for new namespaces (as suggested at
https://lkml.org/lkml/2006/7/11/474).

Related history:
 - https://lkml.org/lkml/2006/12/27/123 is an example of someone
   realizing that fexecve() is likely to fail in a chroot environment.
 - http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=514043 covered
   documenting the /proc requirement of fexecve(3) in its manpage, to
   "prevent other people from wasting their time".
 - https://bugzilla.redhat.com/show_bug.cgi?id=241609 described a
   problem where a process that did setuid() could not fexecve()
   because it no longer had access to /proc/self/fd; this has since
   been fixed.

This patch (of 4):

Add a new execveat(2) system call.  execveat() is to execve() as openat()
is to open(): it takes a file descriptor that refers to a directory, and
resolves the filename relative to that.

In addition, if the filename is empty and AT_EMPTY_PATH is specified,
execveat() executes the file to which the file descriptor refers.  This
replicates the functionality of fexecve(), which is a system call in other
UNIXen, but in Linux glibc it depends on opening "/proc/self/fd/<fd>" (and
so relies on /proc being mounted).

The filename fed to the executed program as argv[0] (or the name of the
script fed to a script interpreter) will be of the form "/dev/fd/<fd>"
(for an empty filename) or "/dev/fd/<fd>/<filename>", effectively
reflecting how the executable was found.  This does however mean that
execution of a script in a /proc-less environment won't work; also, script
execution via an O_CLOEXEC file descriptor fails (as the file will not be
accessible after exec).

Based on patches by Meredydd Luff.

Signed-off-by: David Drysdale <drysdale@google.com>
Cc: Meredydd Luff <meredydd@senatehouse.org>
Cc: Shuah Khan <shuah.kh@samsung.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Rich Felker <dalias@aerifal.cx>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 20 insertions, 1 deletions

diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 61f29e5ea840..576e4639ca60 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -53,6 +53,10 @@ struct linux_binprm {
 #define BINPRM_FLAGS_EXECFD_BIT 1
 #define BINPRM_FLAGS_EXECFD (1 << BINPRM_FLAGS_EXECFD_BIT)
 
+/* filename of the binary will be inaccessible after exec */
+#define BINPRM_FLAGS_PATH_INACCESSIBLE_BIT 2
+#define BINPRM_FLAGS_PATH_INACCESSIBLE (1 << BINPRM_FLAGS_PATH_INACCESSIBLE_BIT)
+
 /* Function parameter for binfmt->coredump */
 struct coredump_params {
 	const siginfo_t *siginfo;
diff --git a/include/linux/compat.h b/include/linux/compat.h
index e6494261eaff..7450ca2ac1fc 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -357,6 +357,9 @@ asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int);
 
 asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv,
 		     const compat_uptr_t __user *envp);
+asmlinkage long compat_sys_execveat(int dfd, const char __user *filename,
+		     const compat_uptr_t __user *argv,
+		     const compat_uptr_t __user *envp, int flags);
 
 asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
 		compat_ulong_t __user *outp, compat_ulong_t __user *exp,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1d1838de6882..4193a0bd99b0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2096,6 +2096,7 @@ extern int vfs_open(const struct path *, struct file *, const struct cred *);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
 
+extern struct filename *getname_flags(const char __user *, int, int *);
 extern struct filename *getname(const char __user *);
 extern struct filename *getname_kernel(const char *);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4cfdbcf8cf56..8db31ef98d2f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2485,6 +2485,10 @@ extern void do_group_exit(int);
 extern int do_execve(struct filename *,
 		     const char __user * const __user *,
 		     const char __user * const __user *);
+extern int do_execveat(int, struct filename *,
+		       const char __user * const __user *,
+		       const char __user * const __user *,
+		       int);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index c9afdc7a7f84..85893d744901 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -877,4 +877,9 @@ asmlinkage long sys_seccomp(unsigned int op, unsigned int flags,
 asmlinkage long sys_getrandom(char __user *buf, size_t count,
 			      unsigned int flags);
 asmlinkage long sys_bpf(int cmd, union bpf_attr *attr, unsigned int size);
+
+asmlinkage long sys_execveat(int dfd, const char __user *filename,
+			const char __user *const __user *argv,
+			const char __user *const __user *envp, int flags);
+
 #endif
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 22749c134117..e016bd9b1a04 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -707,9 +707,11 @@ __SYSCALL(__NR_getrandom, sys_getrandom)
 __SYSCALL(__NR_memfd_create, sys_memfd_create)
 #define __NR_bpf 280
 __SYSCALL(__NR_bpf, sys_bpf)
+#define __NR_execveat 281
+__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
 
 #undef __NR_syscalls
-#define __NR_syscalls 281
+#define __NR_syscalls 282
 
 /*
  * All syscalls below here should go away really,