@@ -3,6 +3,7 @@
/* Based on Christian Brauner's clone3() example */
#define _GNU_SOURCE
+#include <asm/mman.h>
#include <errno.h>
#include <inttypes.h>
#include <linux/types.h>
@@ -11,6 +12,7 @@
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
+#include <sys/mman.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include <sys/un.h>
@@ -19,8 +21,12 @@
#include <sched.h>
#include "../kselftest.h"
+#include "../ksft_shstk.h"
#include "clone3_selftests.h"
+static bool shadow_stack_supported;
+static size_t max_supported_args_size;
+
enum test_mode {
CLONE3_ARGS_NO_TEST,
CLONE3_ARGS_ALL_0,
@@ -28,6 +34,11 @@ enum test_mode {
CLONE3_ARGS_INVAL_EXIT_SIGNAL_NEG,
CLONE3_ARGS_INVAL_EXIT_SIGNAL_CSIG,
CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG,
+ CLONE3_ARGS_SHADOW_STACK,
+ CLONE3_ARGS_SHADOW_STACK_NO_SIZE,
+ CLONE3_ARGS_SHADOW_STACK_NO_POINTER,
+ CLONE3_ARGS_SHADOW_STACK_NO_TOKEN,
+ CLONE3_ARGS_SHADOW_STACK_NORMAL_MEMORY,
};
typedef bool (*filter_function)(void);
@@ -44,6 +55,44 @@ struct test {
filter_function filter;
};
+
+/*
+ * We check for shadow stack support by attempting to use
+ * map_shadow_stack() since features may have been locked by the
+ * dynamic linker resulting in spurious errors when we attempt to
+ * enable on startup. We warn if the enable failed.
+ */
+static void test_shadow_stack_supported(void)
+{
+ long ret;
+
+ ret = syscall(__NR_map_shadow_stack, 0, getpagesize(), 0);
+ if (ret == -1) {
+ ksft_print_msg("map_shadow_stack() not supported\n");
+ } else if ((void *)ret == MAP_FAILED) {
+ ksft_print_msg("Failed to map shadow stack\n");
+ } else {
+ ksft_print_msg("Shadow stack supportd\n");
+ shadow_stack_supported = true;
+
+ if (!shadow_stack_enabled)
+ ksft_print_msg("Mapped but did not enable shadow stack\n");
+ }
+}
+
+static unsigned long long get_shadow_stack_page(unsigned long flags)
+{
+ unsigned long long page;
+
+ page = syscall(__NR_map_shadow_stack, 0, getpagesize(), flags);
+ if ((void *)page == MAP_FAILED) {
+ ksft_print_msg("map_shadow_stack() failed: %d\n", errno);
+ return 0;
+ }
+
+ return page;
+}
+
static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode)
{
struct __clone_args args = {
@@ -89,6 +138,24 @@ static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode)
case CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG:
args.exit_signal = 0x00000000000000f0ULL;
break;
+ case CLONE3_ARGS_SHADOW_STACK:
+ args.shadow_stack = get_shadow_stack_page(SHADOW_STACK_SET_TOKEN);
+ args.shadow_stack_size = getpagesize();
+ break;
+ case CLONE3_ARGS_SHADOW_STACK_NO_POINTER:
+ args.shadow_stack_size = getpagesize();
+ break;
+ case CLONE3_ARGS_SHADOW_STACK_NO_SIZE:
+ args.shadow_stack = get_shadow_stack_page(SHADOW_STACK_SET_TOKEN);
+ break;
+ case CLONE3_ARGS_SHADOW_STACK_NORMAL_MEMORY:
+ args.shadow_stack = (unsigned long long)malloc(getpagesize());
+ args.shadow_stack_size = getpagesize();
+ break;
+ case CLONE3_ARGS_SHADOW_STACK_NO_TOKEN:
+ args.shadow_stack = get_shadow_stack_page(0);
+ args.shadow_stack_size = getpagesize();
+ break;
}
memcpy(&args_ext.args, &args, sizeof(struct __clone_args));
@@ -102,7 +169,12 @@ static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode)
if (pid == 0) {
ksft_print_msg("I am the child, my PID is %d\n", getpid());
- _exit(EXIT_SUCCESS);
+ /*
+ * Use a raw syscall to ensure we don't get issues
+ * with manually specified shadow stack and exit handlers.
+ */
+ syscall(__NR_exit, EXIT_SUCCESS);
+ ksft_print_msg("CHILD FAILED TO EXIT PID is %d\n", getpid());
}
ksft_print_msg("I am the parent (%d). My child's pid is %d\n",
@@ -184,6 +256,26 @@ static bool no_timenamespace(void)
return true;
}
+static bool have_shadow_stack(void)
+{
+ if (shadow_stack_supported) {
+ ksft_print_msg("Shadow stack supported\n");
+ return true;
+ }
+
+ return false;
+}
+
+static bool no_shadow_stack(void)
+{
+ if (!shadow_stack_supported) {
+ ksft_print_msg("Shadow stack not supported\n");
+ return true;
+ }
+
+ return false;
+}
+
static size_t page_size_plus_8(void)
{
return getpagesize() + 8;
@@ -327,6 +419,56 @@ static const struct test tests[] = {
.expected = -EINVAL,
.test_mode = CLONE3_ARGS_NO_TEST,
},
+ {
+ .name = "Shadow stack on system with shadow stack",
+ .size = 0,
+ .expected = 0,
+ .e2big_valid = true,
+ .test_mode = CLONE3_ARGS_SHADOW_STACK,
+ .filter = no_shadow_stack,
+ },
+ {
+ .name = "Shadow stack with no pointer",
+ .size = 0,
+ .expected = -EINVAL,
+ .e2big_valid = true,
+ .test_mode = CLONE3_ARGS_SHADOW_STACK_NO_POINTER,
+ },
+ {
+ .name = "Shadow stack with no size",
+ .size = 0,
+ .expected = -EINVAL,
+ .e2big_valid = true,
+ .test_mode = CLONE3_ARGS_SHADOW_STACK_NO_SIZE,
+ .filter = no_shadow_stack,
+ },
+ {
+ .name = "Shadow stack with no token",
+ .flags = CLONE_VM,
+ .size = 0,
+ .expected = -EINVAL,
+ .e2big_valid = true,
+ .test_mode = CLONE3_ARGS_SHADOW_STACK_NO_TOKEN,
+ .filter = no_shadow_stack,
+ },
+ {
+ .name = "Shadow stack with normal memory",
+ .flags = CLONE_VM,
+ .size = 0,
+ .expected = -EFAULT,
+ .e2big_valid = true,
+ .test_mode = CLONE3_ARGS_SHADOW_STACK_NORMAL_MEMORY,
+ .filter = no_shadow_stack,
+ },
+ {
+ .name = "Shadow stack on system without shadow stack",
+ .flags = CLONE_VM,
+ .size = 0,
+ .expected = -EINVAL,
+ .e2big_valid = true,
+ .test_mode = CLONE3_ARGS_SHADOW_STACK,
+ .filter = have_shadow_stack,
+ },
};
int main(int argc, char *argv[])
@@ -334,9 +476,12 @@ int main(int argc, char *argv[])
size_t size;
int i;
+ enable_shadow_stack();
+
ksft_print_header();
ksft_set_plan(ARRAY_SIZE(tests));
test_clone3_supported();
+ test_shadow_stack_supported();
for (i = 0; i < ARRAY_SIZE(tests); i++)
test_clone3(&tests[i]);
@@ -31,12 +31,50 @@ struct __clone_args {
__aligned_u64 set_tid;
__aligned_u64 set_tid_size;
__aligned_u64 cgroup;
+#ifndef CLONE_ARGS_SIZE_VER2
+#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */
+#endif
+ __aligned_u64 shadow_stack;
+ __aligned_u64 shadow_stack_size;
+#ifndef CLONE_ARGS_SIZE_VER3
+#define CLONE_ARGS_SIZE_VER3 104 /* sizeof fourth published struct */
+#endif
};
+/*
+ * For architectures with shadow stack support we need to be
+ * absolutely sure that the clone3() syscall will be inline and not a
+ * function call so we open code.
+ */
+#ifdef __x86_64__
+static pid_t __always_inline sys_clone3(struct __clone_args *args, size_t size)
+{
+ long ret;
+ register long _num __asm__ ("rax") = __NR_clone3;
+ register long _args __asm__ ("rdi") = (long)(args);
+ register long _size __asm__ ("rsi") = (long)(size);
+
+ __asm__ volatile (
+ "syscall\n"
+ : "=a"(ret)
+ : "r"(_args), "r"(_size),
+ "0"(_num)
+ : "rcx", "r11", "memory", "cc"
+ );
+
+ if (ret < 0) {
+ errno = -ret;
+ return -1;
+ }
+
+ return ret;
+}
+#else
static pid_t sys_clone3(struct __clone_args *args, size_t size)
{
return syscall(__NR_clone3, args, size);
}
+#endif
static inline void test_clone3_supported(void)
{