Currently as a result of templating from x86 code gcs_alloc_thread_stack() returns a pointer as an unsigned int however on arm64 we don't actually use this pointer value as anything other than a pass/fail flag. Simplify the interface to just return an int with 0 on success and a negative error code on failure.

Acked-by: Deepak Gupta debug@rivosinc.com Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/gcs.h | 8 ++++---- arch/arm64/kernel/process.c | 8 ++++---- arch/arm64/mm/gcs.c | 8 ++++---- 3 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/include/asm/gcs.h b/arch/arm64/include/asm/gcs.h index f50660603ecf5dc09a92740062df3a089b02b219..d8923b5f03b776252aca76ce316ef57399d71fa9 100644 --- a/arch/arm64/include/asm/gcs.h +++ b/arch/arm64/include/asm/gcs.h @@ -64,8 +64,8 @@ static inline bool task_gcs_el0_enabled(struct task_struct *task) void gcs_set_el0_mode(struct task_struct *task); void gcs_free(struct task_struct *task); void gcs_preserve_current_state(void); -unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, - const struct kernel_clone_args *args); +int gcs_alloc_thread_stack(struct task_struct *tsk, + const struct kernel_clone_args *args);

static inline int gcs_check_locked(struct task_struct *task, unsigned long new_val) @@ -91,8 +91,8 @@ static inline bool task_gcs_el0_enabled(struct task_struct *task) static inline void gcs_set_el0_mode(struct task_struct *task) { } static inline void gcs_free(struct task_struct *task) { } static inline void gcs_preserve_current_state(void) { } -static inline unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, - const struct kernel_clone_args *args) +static inline int gcs_alloc_thread_stack(struct task_struct *tsk, + const struct kernel_clone_args *args) { return -ENOTSUPP; } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index fdd095480c3ffb8c13fd4e7c9abc79e88143e08b..8ebd11c29792524dfeeade9cc7826b007329aa6a 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -297,7 +297,7 @@ static void flush_gcs(void) static int copy_thread_gcs(struct task_struct *p, const struct kernel_clone_args *args) { - unsigned long gcs; + int ret;

if (!system_supports_gcs()) return 0; @@ -305,9 +305,9 @@ static int copy_thread_gcs(struct task_struct *p, p->thread.gcs_base = 0; p->thread.gcs_size = 0;

- gcs = gcs_alloc_thread_stack(p, args); - if (IS_ERR_VALUE(gcs)) - return PTR_ERR((void *)gcs); + ret = gcs_alloc_thread_stack(p, args); + if (ret != 0) + return ret;

p->thread.gcs_el0_mode = current->thread.gcs_el0_mode; p->thread.gcs_el0_locked = current->thread.gcs_el0_locked; diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c index 5c46ec527b1cdaa8f52cff445d70ba0f8509d086..1f633a482558b59aac5427963d42b37fce08c8a6 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -38,8 +38,8 @@ static unsigned long gcs_size(unsigned long size) return max(PAGE_SIZE, size); }

-unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, - const struct kernel_clone_args *args) +int gcs_alloc_thread_stack(struct task_struct *tsk, + const struct kernel_clone_args *args) { unsigned long addr, size;

@@ -59,13 +59,13 @@ unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, size = gcs_size(size); addr = alloc_gcs(0, size); if (IS_ERR_VALUE(addr)) - return addr; + return PTR_ERR((void *)addr);

tsk->thread.gcs_base = addr; tsk->thread.gcs_size = size; tsk->thread.gcspr_el0 = addr + size - sizeof(u64);

- return addr; + return 0; }

SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsigned int, flags)

There are a number of architectures with shadow stack features which we are presenting to userspace with as consistent an API as we can (though there are some architecture specifics). Especially given that there are some important considerations for userspace code interacting directly with the feature let's provide some documentation covering the common aspects.

Reviewed-by: Catalin Marinas catalin.marinas@arm.com Reviewed-by: Kees Cook kees@kernel.org Tested-by: Kees Cook kees@kernel.org Acked-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Mark Brown broonie@kernel.org --- Documentation/userspace-api/index.rst | 1 + Documentation/userspace-api/shadow_stack.rst | 42 ++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+)

diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index 274cc7546efc2a042d2dc00aa67c71c52372179a..c39709bfba2c5682d0d1a22444db17c17bcf01ce 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -59,6 +59,7 @@ Everything else

ELF netlink/index + shadow_stack sysfs-platform_profile vduse futex2 diff --git a/Documentation/userspace-api/shadow_stack.rst b/Documentation/userspace-api/shadow_stack.rst new file mode 100644 index 0000000000000000000000000000000000000000..9d0d4e79cfa7c47d3208dd53071a3d0b86c18575 --- /dev/null +++ b/Documentation/userspace-api/shadow_stack.rst @@ -0,0 +1,42 @@ +============= +Shadow Stacks +============= + +Introduction +============ + +Several architectures have features which provide backward edge +control flow protection through a hardware maintained stack, only +writeable by userspace through very limited operations. This feature +is referred to as shadow stacks on Linux, on x86 it is part of Intel +Control Enforcement Technology (CET), on arm64 it is Guarded Control +Stacks feature (FEAT_GCS) and for RISC-V it is the Zicfiss extension. +It is expected that this feature will normally be managed by the +system dynamic linker and libc in ways broadly transparent to +application code, this document covers interfaces and considerations. + + +Enabling +======== + +Shadow stacks default to disabled when a userspace process is +executed, they can be enabled for the current thread with a syscall: + + - For x86 the ARCH_SHSTK_ENABLE arch_prctl() + - For other architectures the PR_SET_SHADOW_STACK_ENABLE prctl() + +It is expected that this will normally be done by the dynamic linker. +Any new threads created by a thread with shadow stacks enabled will +themselves have shadow stacks enabled. + + +Enablement considerations +========================= + +- Returning from the function that enables shadow stacks without first + disabling them will cause a shadow stack exception. This includes + any syscall wrapper or other library functions, the syscall will need + to be inlined. +- A lock feature allows userspace to prevent disabling of shadow stacks. +- Those that change the stack context like longjmp() or use of ucontext + changes on signal return will need support from libc.

While almost all users of shadow stacks should be relying on the dynamic linker and libc to enable the feature there are several low level test programs where it is useful to enable without any libc support, allowing testing without full system enablement. This low level testing is helpful during bringup of the support itself, and also in enabling coverage by automated testing without needing all system components in the target root filesystems to have enablement.

Provide a header with helpers for this purpose, intended for use only by test programs directly exercising shadow stack interfaces.

Reviewed-by: Rick Edgecombe rick.p.edgecombe@intel.com Reviewed-by: Kees Cook kees@kernel.org Tested-by: Kees Cook kees@kernel.org Acked-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/ksft_shstk.h | 98 ++++++++++++++++++++++++++++++++++++ 1 file changed, 98 insertions(+)

diff --git a/tools/testing/selftests/ksft_shstk.h b/tools/testing/selftests/ksft_shstk.h new file mode 100644 index 0000000000000000000000000000000000000000..869ecea2bf3ea3d30cead9819d2b3a75f5397754 --- /dev/null +++ b/tools/testing/selftests/ksft_shstk.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Helpers for shadow stack enablement, this is intended to only be + * used by low level test programs directly exercising interfaces for + * working with shadow stacks. + * + * Copyright (C) 2024 ARM Ltd. + */ + +#ifndef __KSFT_SHSTK_H +#define __KSFT_SHSTK_H + +#include <asm/mman.h> + +/* This is currently only defined for x86 */ +#ifndef SHADOW_STACK_SET_TOKEN +#define SHADOW_STACK_SET_TOKEN (1ULL << 0) +#endif + +static bool shadow_stack_enabled; + +#ifdef __x86_64__ +#define ARCH_SHSTK_ENABLE 0x5001 +#define ARCH_SHSTK_SHSTK (1ULL << 0) + +#define ARCH_PRCTL(arg1, arg2) \ +({ \ + long _ret; \ + register long _num asm("eax") = __NR_arch_prctl; \ + register long _arg1 asm("rdi") = (long)(arg1); \ + register long _arg2 asm("rsi") = (long)(arg2); \ + \ + asm volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define ENABLE_SHADOW_STACK +static inline __attribute__((always_inline)) void enable_shadow_stack(void) +{ + int ret = ARCH_PRCTL(ARCH_SHSTK_ENABLE, ARCH_SHSTK_SHSTK); + if (ret == 0) + shadow_stack_enabled = true; +} + +#endif + +#ifdef __aarch64__ +#define PR_SET_SHADOW_STACK_STATUS 75 +# define PR_SHADOW_STACK_ENABLE (1UL << 0) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = 0; \ + register long _arg4 __asm__ ("x3") = 0; \ + register long _arg5 __asm__ ("x4") = 0; \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), \ + "r"(_arg3), "r"(_arg4), \ + "r"(_arg5), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define ENABLE_SHADOW_STACK +static inline __attribute__((always_inline)) void enable_shadow_stack(void) +{ + int ret; + + ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, + PR_SHADOW_STACK_ENABLE); + if (ret == 0) + shadow_stack_enabled = true; +} + +#endif + +#ifndef __NR_map_shadow_stack +#define __NR_map_shadow_stack 453 +#endif + +#ifndef ENABLE_SHADOW_STACK +static inline void enable_shadow_stack(void) { } +#endif + +#endif

In order to make it easier to add more configuration for the tests and more support for runtime detection of when tests can be run pass the structure describing the tests into test_clone3() rather than picking the arguments out of it and have that function do all the per-test work.

No functional change.

Reviewed-by: Kees Cook kees@kernel.org Tested-by: Kees Cook kees@kernel.org Acked-by: Shuah Khan skhan@linuxfoundation.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/clone3/clone3.c | 77 ++++++++++++++++----------------- 1 file changed, 37 insertions(+), 40 deletions(-)

diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index e61f07973ce5e27aff30047b35e03b1b51875c15..e066b201fa64eb17c55939b7cec18ac5d109613b 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -30,6 +30,19 @@ enum test_mode { CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG, };

+typedef bool (*filter_function)(void); +typedef size_t (*size_function)(void); + +struct test { + const char *name; + uint64_t flags; + size_t size; + size_function size_function; + int expected; + enum test_mode test_mode; + filter_function filter; +}; + static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) { struct __clone_args args = { @@ -109,30 +122,40 @@ static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) return 0; }

-static bool test_clone3(uint64_t flags, size_t size, int expected, - enum test_mode test_mode) +static void test_clone3(const struct test *test) { + size_t size; int ret;

+ if (test->filter && test->filter()) { + ksft_test_result_skip("%s\n", test->name); + return; + } + + if (test->size_function) + size = test->size_function(); + else + size = test->size; + + ksft_print_msg("Running test '%s'\n", test->name); + ksft_print_msg( "[%d] Trying clone3() with flags %#" PRIx64 " (size %zu)\n", - getpid(), flags, size); - ret = call_clone3(flags, size, test_mode); + getpid(), test->flags, size); + ret = call_clone3(test->flags, size, test->test_mode); ksft_print_msg("[%d] clone3() with flags says: %d expected %d\n", - getpid(), ret, expected); - if (ret != expected) { + getpid(), ret, test->expected); + if (ret != test->expected) { ksft_print_msg( "[%d] Result (%d) is different than expected (%d)\n", - getpid(), ret, expected); - return false; + getpid(), ret, test->expected); + ksft_test_result_fail("%s\n", test->name); + return; }

- return true; + ksft_test_result_pass("%s\n", test->name); }

-typedef bool (*filter_function)(void); -typedef size_t (*size_function)(void); - static bool not_root(void) { if (getuid() != 0) { @@ -160,16 +183,6 @@ static size_t page_size_plus_8(void) return getpagesize() + 8; }

-struct test { - const char *name; - uint64_t flags; - size_t size; - size_function size_function; - int expected; - enum test_mode test_mode; - filter_function filter; -}; - static const struct test tests[] = { { .name = "simple clone3()", @@ -319,24 +332,8 @@ int main(int argc, char *argv[]) ksft_set_plan(ARRAY_SIZE(tests)); test_clone3_supported();

- for (i = 0; i < ARRAY_SIZE(tests); i++) { - if (tests[i].filter && tests[i].filter()) { - ksft_test_result_skip("%s\n", tests[i].name); - continue; - } - - if (tests[i].size_function) - size = tests[i].size_function(); - else - size = tests[i].size; - - ksft_print_msg("Running test '%s'\n", tests[i].name); - - ksft_test_result(test_clone3(tests[i].flags, size, - tests[i].expected, - tests[i].test_mode), - "%s\n", tests[i].name); - } + for (i = 0; i < ARRAY_SIZE(tests); i++) + test_clone3(&tests[i]);

ksft_finished(); }

Add basic test coverage for specifying the shadow stack for a newly created thread via clone3(), including coverage of the newly extended argument structure. We check that a user specified shadow stack can be provided, and that invalid combinations of parameters are rejected.

In order to facilitate testing on systems without userspace shadow stack support we manually enable shadow stacks on startup, this is architecture specific due to the use of an arch_prctl() on x86. Due to interactions with potential userspace locking of features we actually detect support for shadow stacks on the running system by attempting to allocate a shadow stack page during initialisation using map_shadow_stack(), warning if this succeeds when the enable failed.

In order to allow testing of user configured shadow stacks on architectures with that feature we need to ensure that we do not return from the function where the clone3() syscall is called in the child process, doing so would trigger a shadow stack underflow. To do this we use inline assembly rather than the standard syscall wrapper to call clone3(). In order to avoid surprises we also use a syscall rather than the libc exit() function., this should be overly cautious.

Acked-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/clone3/clone3.c | 143 +++++++++++++++++++++- tools/testing/selftests/clone3/clone3_selftests.h | 63 ++++++++++ 2 files changed, 205 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index 5b8b7d640e70132242fc6939450669acd0c534f9..b0378d7418cc8b00caebc6f92f58280bc04b0f80 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -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 +34,10 @@ 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_MISALIGNED, + CLONE3_ARGS_SHADOW_STACK_NO_TOKEN, + CLONE3_ARGS_SHADOW_STACK_NORMAL_MEMORY, };

typedef bool (*filter_function)(void); @@ -44,6 +54,44 @@ 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 void *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 (void *)page; +} + static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) { struct __clone_args args = { @@ -57,6 +105,7 @@ static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) } args_ext;

pid_t pid = -1; + void *p; int status;

memset(&args_ext, 0, sizeof(args_ext)); @@ -89,6 +138,26 @@ 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: + p = get_shadow_stack_page(SHADOW_STACK_SET_TOKEN); + p += getpagesize() - sizeof(void *); + args.shadow_stack_pointer = (unsigned long long)p; + break; + case CLONE3_ARGS_SHADOW_STACK_MISALIGNED: + p = get_shadow_stack_page(SHADOW_STACK_SET_TOKEN); + p += getpagesize() - sizeof(void *) - 1; + args.shadow_stack_pointer = (unsigned long long)p; + break; + case CLONE3_ARGS_SHADOW_STACK_NORMAL_MEMORY: + p = malloc(getpagesize()); + p += getpagesize() - sizeof(void *); + args.shadow_stack_pointer = (unsigned long long)p; + break; + case CLONE3_ARGS_SHADOW_STACK_NO_TOKEN: + p = get_shadow_stack_page(0); + p += getpagesize() - sizeof(void *); + args.shadow_stack_pointer = (unsigned long long)p; + break; }

memcpy(&args_ext.args, &args, sizeof(struct __clone_args)); @@ -102,7 +171,12 @@ 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 +258,26 @@ 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 +421,50 @@ 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 misaligned address", + .flags = CLONE_VM, + .size = 0, + .expected = -EINVAL, + .e2big_valid = true, + .test_mode = CLONE3_ARGS_SHADOW_STACK_MISALIGNED, + .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 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 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 +472,12 @@ 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]); diff --git a/tools/testing/selftests/clone3/clone3_selftests.h b/tools/testing/selftests/clone3/clone3_selftests.h index 39b5dcba663c30b9fc2542d9a0d2686105ce5761..26ff1554408a59af26bd708dc9c852210e370828 100644 --- a/tools/testing/selftests/clone3/clone3_selftests.h +++ b/tools/testing/selftests/clone3/clone3_selftests.h @@ -31,12 +31,75 @@ 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_pointer; +#ifndef CLONE_ARGS_SIZE_VER3 +#define CLONE_ARGS_SIZE_VER3 96 /* 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; +} +#elif defined(__aarch64__) +static pid_t __always_inline sys_clone3(struct __clone_args *args, size_t size) +{ + register long _num __asm__ ("x8") = __NR_clone3; + register long _args __asm__ ("x0") = (long)(args); + register long _size __asm__ ("x1") = (long)(size); + register long arg2 __asm__ ("x2") = 0; + register long arg3 __asm__ ("x3") = 0; + register long arg4 __asm__ ("x4") = 0; + + __asm__ volatile ( + "svc #0\n" + : "=r"(_args) + : "r"(_args), "r"(_size), + "r"(_num), "r"(arg2), + "r"(arg3), "r"(arg4) + : "memory", "cc" + ); + + if ((int)_args < 0) { + errno = -((int)_args); + return -1; + } + + return _args; +} +#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) {