TL;DR: reset POR_EL0 to "allow all" before writing the signal frame, preventing spurious uaccess failures.

When POE is supported, the POR_EL0 register constrains memory accesses based on the target page's POIndex (pkey). This raises the question: what constraints should apply to a signal handler? The current answer is that POR_EL0 is reset to POR_EL0_INIT when invoking the handler, giving it full access to POIndex 0. This is in line with x86's MPK support and remains unchanged.

This is only part of the story, though. POR_EL0 constrains all unprivileged memory accesses, meaning that uaccess routines such as put_user() are also impacted. As a result POR_EL0 may prevent the signal frame from being written to the signal stack (ultimately causing a SIGSEGV). This is especially concerning when an alternate signal stack is used, because userspace may want to prevent access to it outside of signal handlers. There is currently no provision for that: POR_EL0 is reset after writing to the stack, and POR_EL0_INIT only enables access to POIndex 0.

This patch ensures that POR_EL0 is reset to its most permissive state before the signal stack is accessed. Once the signal frame has been fully written, POR_EL0 is still set to POR_EL0_INIT - it is up to the signal handler to enable access to additional pkeys if needed. As to sigreturn(), it expects having access to the stack like any other syscall; we only need to ensure that POR_EL0 is restored from the signal frame after all uaccess calls. This approach is in line with the recent x86/pkeys series [1].

Resetting POR_EL0 early introduces some complications, in that we can no longer read the register directly in preserve_poe_context(). This is addressed by introducing a struct (user_access_state) and helpers to manage any such register impacting user accesses (uaccess and accesses in userspace). Things look like this on signal delivery:

1. Save original POR_EL0 into struct [save_reset_user_access_state()] 2. Set POR_EL0 to "allow all" [save_reset_user_access_state()] 3. Create signal frame 4. Write saved POR_EL0 value to the signal frame [preserve_poe_context()] 5. Finalise signal frame 6. If all operations succeeded: a. Set POR_EL0 to POR_EL0_INIT [set_handler_user_access_state()] b. Else reset POR_EL0 to its original value [restore_user_access_state()]

If any step fails when setting up the signal frame, the process will be sent a SIGSEGV, which it may be able to handle. Step 6.b ensures that the original POR_EL0 is saved in the signal frame when delivering that SIGSEGV (so that the original value is restored by sigreturn).

The return path (sys_rt_sigreturn) doesn't strictly require any change since restore_poe_context() is already called last. However, to avoid uaccess calls being accidentally added after that point, we use the same approach as in the delivery path, i.e. separating uaccess from writing to the register:

1. Read saved POR_EL0 value from the signal frame [restore_poe_context()] 2. Set POR_EL0 to the saved value [restore_user_access_state()]

[1] https://lore.kernel.org/lkml/20240802061318.2140081-1-aruna.ramakrishna@orac...

Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Kevin Brodsky kevin.brodsky@arm.com --- arch/arm64/kernel/signal.c | 92 ++++++++++++++++++++++++++++++++------ 1 file changed, 78 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 561986947530..c7d311d8b92a 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -19,6 +19,7 @@ #include <linux/ratelimit.h> #include <linux/rseq.h> #include <linux/syscalls.h> +#include <linux/pkeys.h>

#include <asm/daifflags.h> #include <asm/debug-monitors.h> @@ -66,10 +67,63 @@ struct rt_sigframe_user_layout { unsigned long end_offset; };

+/* + * Holds any EL0-controlled state that influences unprivileged memory accesses. + * This includes both accesses done in userspace and uaccess done in the kernel. + * + * This state needs to be carefully managed to ensure that it doesn't cause + * uaccess to fail when setting up the signal frame, and the signal handler + * itself also expects a well-defined state when entered. + */ +struct user_access_state { + u64 por_el0; +}; + #define BASE_SIGFRAME_SIZE round_up(sizeof(struct rt_sigframe), 16) #define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16) #define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16)

+/* + * Save the user access state into ua_state and reset it to disable any + * restrictions. + */ +static void save_reset_user_access_state(struct user_access_state *ua_state) +{ + if (system_supports_poe()) { + u64 por_enable_all = 0; + + for (int pkey = 0; pkey < arch_max_pkey(); pkey++) + por_enable_all |= POE_RXW << (pkey * POR_BITS_PER_PKEY); + + ua_state->por_el0 = read_sysreg_s(SYS_POR_EL0); + write_sysreg_s(por_enable_all, SYS_POR_EL0); + /* Ensure that any subsequent uaccess observes the updated value */ + isb(); + } +} + +/* + * Set the user access state for invoking the signal handler. + * + * No uaccess should be done after that function is called. + */ +static void set_handler_user_access_state(void) +{ + if (system_supports_poe()) + write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0); +} + +/* + * Restore the user access state to the values saved in ua_state. + * + * No uaccess should be done after that function is called. + */ +static void restore_user_access_state(const struct user_access_state *ua_state) +{ + if (system_supports_poe()) + write_sysreg_s(ua_state->por_el0, SYS_POR_EL0); +} + static void init_user_layout(struct rt_sigframe_user_layout *user) { const size_t reserved_size = @@ -261,18 +315,20 @@ static int restore_fpmr_context(struct user_ctxs *user) return err; }

-static int preserve_poe_context(struct poe_context __user *ctx) +static int preserve_poe_context(struct poe_context __user *ctx, + const struct user_access_state *ua_state) { int err = 0;

__put_user_error(POE_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(*ctx), &ctx->head.size, err); - __put_user_error(read_sysreg_s(SYS_POR_EL0), &ctx->por_el0, err); + __put_user_error(ua_state->por_el0, &ctx->por_el0, err);

return err; }

-static int restore_poe_context(struct user_ctxs *user) +static int restore_poe_context(struct user_ctxs *user, + struct user_access_state *ua_state) { u64 por_el0; int err = 0; @@ -282,7 +338,7 @@ static int restore_poe_context(struct user_ctxs *user)

__get_user_error(por_el0, &(user->poe->por_el0), err); if (!err) - write_sysreg_s(por_el0, SYS_POR_EL0); + ua_state->por_el0 = por_el0;

return err; } @@ -850,7 +906,8 @@ static int parse_user_sigframe(struct user_ctxs *user, }

static int restore_sigframe(struct pt_regs *regs, - struct rt_sigframe __user *sf) + struct rt_sigframe __user *sf, + struct user_access_state *ua_state) { sigset_t set; int i, err; @@ -899,7 +956,7 @@ static int restore_sigframe(struct pt_regs *regs, err = restore_zt_context(&user);

if (err == 0 && system_supports_poe() && user.poe) - err = restore_poe_context(&user); + err = restore_poe_context(&user, ua_state);

return err; } @@ -908,6 +965,7 @@ SYSCALL_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; + struct user_access_state ua_state;

/* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; @@ -924,12 +982,14 @@ SYSCALL_DEFINE0(rt_sigreturn) if (!access_ok(frame, sizeof (*frame))) goto badframe;

- if (restore_sigframe(regs, frame)) + if (restore_sigframe(regs, frame, &ua_state)) goto badframe;

if (restore_altstack(&frame->uc.uc_stack)) goto badframe;

+ restore_user_access_state(&ua_state); + return regs->regs[0];

badframe: @@ -1035,7 +1095,8 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, }

static int setup_sigframe(struct rt_sigframe_user_layout *user, - struct pt_regs *regs, sigset_t *set) + struct pt_regs *regs, sigset_t *set, + const struct user_access_state *ua_state) { int i, err = 0; struct rt_sigframe __user *sf = user->sigframe; @@ -1097,10 +1158,9 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, struct poe_context __user *poe_ctx = apply_user_offset(user, user->poe_offset);

- err |= preserve_poe_context(poe_ctx); + err |= preserve_poe_context(poe_ctx, ua_state); }

- /* ZA state if present */ if (system_supports_sme() && err == 0 && user->za_offset) { struct za_context __user *za_ctx = @@ -1237,9 +1297,6 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, sme_smstop(); }

- if (system_supports_poe()) - write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0); - if (ka->sa.sa_flags & SA_RESTORER) sigtramp = ka->sa.sa_restorer; else @@ -1253,6 +1310,7 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, { struct rt_sigframe_user_layout user; struct rt_sigframe __user *frame; + struct user_access_state ua_state; int err = 0;

fpsimd_signal_preserve_current_state(); @@ -1260,13 +1318,14 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, if (get_sigframe(&user, ksig, regs)) return 1;

+ save_reset_user_access_state(&ua_state); frame = user.sigframe;

__put_user_error(0, &frame->uc.uc_flags, err); __put_user_error(NULL, &frame->uc.uc_link, err);

err |= __save_altstack(&frame->uc.uc_stack, regs->sp); - err |= setup_sigframe(&user, regs, set); + err |= setup_sigframe(&user, regs, set, &ua_state); if (err == 0) { setup_return(regs, &ksig->ka, &user, usig); if (ksig->ka.sa.sa_flags & SA_SIGINFO) { @@ -1276,6 +1335,11 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, } }

+ if (err == 0) + set_handler_user_access_state(); + else + restore_user_access_state(&ua_state); + return err; }

The POE frame record is allocated unconditionally if POE is supported. If the allocation fails, a SIGSEGV is delivered before setup_sigframe() can be reached. As a result there is no need to consider poe_offset before saving POR_EL0; just remove that check. This is in line with other frame records (FPMR, TPIDR2).

Reviewed-by: Mark Brown broonie@kernel.org Reviewed-by: Dave Martin Dave.Martin@arm.com Acked-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Kevin Brodsky kevin.brodsky@arm.com --- arch/arm64/kernel/signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index c7d311d8b92a..d5eb517cc4df 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -1154,7 +1154,7 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, err |= preserve_fpmr_context(fpmr_ctx); }

- if (system_supports_poe() && err == 0 && user->poe_offset) { + if (system_supports_poe() && err == 0) { struct poe_context __user *poe_ctx = apply_user_offset(user, user->poe_offset);

pkey_sighandler_tests.c currently hardcodes x86 PKRU encodings. The first step towards running those tests on arm64 is to abstract away the pkey register values.

Since those tests want to deny access to all keys except a few, we have each arch define PKEY_REG_ALLOW_NONE, the pkey register value denying access to all keys. We then use the existing set_pkey_bits() helper to grant access to specific keys.

Because pkeys may also remove the execute permission on arm64, we need to be a little careful: all code is mapped with pkey 0, and we need it to remain executable. pkey_reg_restrictive_default() is introduced for that purpose: the value it returns prevents RW access to all pkeys, but retains X permission for pkey 0.

test_pkru_preserved_after_sigusr1() only checks that the pkey register value remains unchanged after a signal is delivered, so the particular value is irrelevant. We enable pkey 0 and a few more arbitrary keys in the smallest range available on all architectures (8 keys on arm64).

Signed-off-by: Kevin Brodsky kevin.brodsky@arm.com --- tools/testing/selftests/mm/pkey-arm64.h | 1 + tools/testing/selftests/mm/pkey-x86.h | 2 + .../selftests/mm/pkey_sighandler_tests.c | 53 +++++++++++++++---- 3 files changed, 47 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/mm/pkey-arm64.h b/tools/testing/selftests/mm/pkey-arm64.h index 580e1b0bb38e..d57fbeace38f 100644 --- a/tools/testing/selftests/mm/pkey-arm64.h +++ b/tools/testing/selftests/mm/pkey-arm64.h @@ -31,6 +31,7 @@ #define NR_RESERVED_PKEYS 1 /* pkey-0 */

#define PKEY_ALLOW_ALL 0x77777777 +#define PKEY_REG_ALLOW_NONE 0x0

#define PKEY_BITS_PER_PKEY 4 #define PAGE_SIZE sysconf(_SC_PAGESIZE) diff --git a/tools/testing/selftests/mm/pkey-x86.h b/tools/testing/selftests/mm/pkey-x86.h index 5f28e26a2511..ac91777c8917 100644 --- a/tools/testing/selftests/mm/pkey-x86.h +++ b/tools/testing/selftests/mm/pkey-x86.h @@ -34,6 +34,8 @@ #define PAGE_SIZE 4096 #define MB (1<<20)

+#define PKEY_REG_ALLOW_NONE 0x55555555 + static inline void __page_o_noops(void) { /* 8-bytes of instruction * 512 bytes = 1 page */ diff --git a/tools/testing/selftests/mm/pkey_sighandler_tests.c b/tools/testing/selftests/mm/pkey_sighandler_tests.c index a8088b645ad6..501880dbdc37 100644 --- a/tools/testing/selftests/mm/pkey_sighandler_tests.c +++ b/tools/testing/selftests/mm/pkey_sighandler_tests.c @@ -11,6 +11,7 @@ */ #define _GNU_SOURCE #define __SANE_USERSPACE_TYPES__ +#include <linux/mman.h> #include <errno.h> #include <sys/syscall.h> #include <string.h> @@ -65,6 +66,20 @@ long syscall_raw(long n, long a1, long a2, long a3, long a4, long a5, long a6) return ret; }

+/* + * Returns the most restrictive pkey register value that can be used by the + * tests. + */ +static inline u64 pkey_reg_restrictive_default(void) +{ + /* + * Disallow everything except execution on pkey 0, so that each caller + * doesn't need to enable it explicitly (the selftest code runs with + * its code mapped with pkey 0). + */ + return set_pkey_bits(PKEY_REG_ALLOW_NONE, 0, PKEY_DISABLE_ACCESS); +} + static void sigsegv_handler(int signo, siginfo_t *info, void *ucontext) { pthread_mutex_lock(&mutex); @@ -113,7 +128,7 @@ static void raise_sigusr2(void) static void *thread_segv_with_pkey0_disabled(void *ptr) { /* Disable MPK 0 (and all others too) */ - __write_pkey_reg(0x55555555); + __write_pkey_reg(pkey_reg_restrictive_default());

/* Segfault (with SEGV_MAPERR) */ *(int *) (0x1) = 1; @@ -123,7 +138,7 @@ static void *thread_segv_with_pkey0_disabled(void *ptr) static void *thread_segv_pkuerr_stack(void *ptr) { /* Disable MPK 0 (and all others too) */ - __write_pkey_reg(0x55555555); + __write_pkey_reg(pkey_reg_restrictive_default());

/* After we disable MPK 0, we can't access the stack to return */ return NULL; @@ -133,6 +148,7 @@ static void *thread_segv_maperr_ptr(void *ptr) { stack_t *stack = ptr; int *bad = (int *)1; + u64 pkey_reg;

/* * Setup alternate signal stack, which should be pkey_mprotect()ed by @@ -142,7 +158,9 @@ static void *thread_segv_maperr_ptr(void *ptr) syscall_raw(SYS_sigaltstack, (long)stack, 0, 0, 0, 0, 0);

/* Disable MPK 0. Only MPK 1 is enabled. */ - __write_pkey_reg(0x55555551); + pkey_reg = pkey_reg_restrictive_default(); + pkey_reg = set_pkey_bits(pkey_reg, 1, PKEY_UNRESTRICTED); + __write_pkey_reg(pkey_reg);

/* Segfault */ *bad = 1; @@ -240,6 +258,7 @@ static void test_sigsegv_handler_with_different_pkey_for_stack(void) int pkey; int parent_pid = 0; int child_pid = 0; + u64 pkey_reg;

sa.sa_flags = SA_SIGINFO | SA_ONSTACK;

@@ -257,7 +276,10 @@ static void test_sigsegv_handler_with_different_pkey_for_stack(void) assert(stack != MAP_FAILED);

/* Allow access to MPK 0 and MPK 1 */ - __write_pkey_reg(0x55555550); + pkey_reg = pkey_reg_restrictive_default(); + pkey_reg = set_pkey_bits(pkey_reg, 0, PKEY_UNRESTRICTED); + pkey_reg = set_pkey_bits(pkey_reg, 1, PKEY_UNRESTRICTED); + __write_pkey_reg(pkey_reg);

/* Protect the new stack with MPK 1 */ pkey = pkey_alloc(0, 0); @@ -307,7 +329,13 @@ static void test_sigsegv_handler_with_different_pkey_for_stack(void) static void test_pkru_preserved_after_sigusr1(void) { struct sigaction sa; - unsigned long pkru = 0x45454544; + u64 pkey_reg; + + /* Allow access to MPK 0 and an arbitrary set of keys */ + pkey_reg = pkey_reg_restrictive_default(); + pkey_reg = set_pkey_bits(pkey_reg, 0, PKEY_UNRESTRICTED); + pkey_reg = set_pkey_bits(pkey_reg, 3, PKEY_UNRESTRICTED); + pkey_reg = set_pkey_bits(pkey_reg, 7, PKEY_UNRESTRICTED);

sa.sa_flags = SA_SIGINFO;

@@ -320,7 +348,7 @@ static void test_pkru_preserved_after_sigusr1(void)

memset(&siginfo, 0, sizeof(siginfo));

- __write_pkey_reg(pkru); + __write_pkey_reg(pkey_reg);

raise(SIGUSR1);

@@ -330,7 +358,7 @@ static void test_pkru_preserved_after_sigusr1(void) pthread_mutex_unlock(&mutex);

/* Ensure the pkru value is the same after returning from signal. */ - ksft_test_result(pkru == __read_pkey_reg() && + ksft_test_result(pkey_reg == __read_pkey_reg() && siginfo.si_signo == SIGUSR1, "%s\n", __func__); } @@ -347,6 +375,7 @@ static noinline void *thread_sigusr2_self(void *ptr) 'S', 'I', 'G', 'U', 'S', 'R', '2', '.', '.', '.', '\n', '\0'}; stack_t *stack = ptr; + u64 pkey_reg;

/* * Setup alternate signal stack, which should be pkey_mprotect()ed by @@ -356,7 +385,9 @@ static noinline void *thread_sigusr2_self(void *ptr) syscall(SYS_sigaltstack, (long)stack, 0, 0, 0, 0, 0);

/* Disable MPK 0. Only MPK 2 is enabled. */ - __write_pkey_reg(0x55555545); + pkey_reg = pkey_reg_restrictive_default(); + pkey_reg = set_pkey_bits(pkey_reg, 2, PKEY_UNRESTRICTED); + __write_pkey_reg(pkey_reg);

raise_sigusr2();

@@ -384,6 +415,7 @@ static void test_pkru_sigreturn(void) int pkey; int parent_pid = 0; int child_pid = 0; + u64 pkey_reg;

sa.sa_handler = SIG_DFL; sa.sa_flags = 0; @@ -418,7 +450,10 @@ static void test_pkru_sigreturn(void) * the current thread's stack is protected by the default MPK 0. Hence * both need to be enabled. */ - __write_pkey_reg(0x55555544); + pkey_reg = pkey_reg_restrictive_default(); + pkey_reg = set_pkey_bits(pkey_reg, 0, PKEY_UNRESTRICTED); + pkey_reg = set_pkey_bits(pkey_reg, 2, PKEY_UNRESTRICTED); + __write_pkey_reg(pkey_reg);

/* Protect the stack with MPK 2 */ pkey = pkey_alloc(0, 0);

pkey_sighandler_tests.c makes raw syscalls using its own helper, syscall_raw(). One of those syscalls is clone, which is problematic as every architecture has a different opinion on the order of its arguments.

To complete arm64 support, we therefore add an appropriate implementation in syscall_raw(), and introduce a clone_raw() helper that shuffles arguments as needed for each arch.

Having done this, we enable building pkey_sighandler_tests for arm64 in the Makefile.

Signed-off-by: Kevin Brodsky kevin.brodsky@arm.com --- tools/testing/selftests/mm/Makefile | 8 +-- .../selftests/mm/pkey_sighandler_tests.c | 62 ++++++++++++++----- 2 files changed, 50 insertions(+), 20 deletions(-)

diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 02e1204971b0..0f8c110e0805 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -105,12 +105,12 @@ endif ifeq ($(CAN_BUILD_X86_64),1) TEST_GEN_FILES += $(BINARIES_64) endif -else

-ifneq (,$(filter $(ARCH),arm64 powerpc)) +else ifeq ($(ARCH),arm64) +TEST_GEN_FILES += protection_keys +TEST_GEN_FILES += pkey_sighandler_tests +else ifeq ($(ARCH),powerpc) TEST_GEN_FILES += protection_keys -endif - endif

ifneq (,$(filter $(ARCH),arm64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64 s390)) diff --git a/tools/testing/selftests/mm/pkey_sighandler_tests.c b/tools/testing/selftests/mm/pkey_sighandler_tests.c index 501880dbdc37..c593a426341c 100644 --- a/tools/testing/selftests/mm/pkey_sighandler_tests.c +++ b/tools/testing/selftests/mm/pkey_sighandler_tests.c @@ -60,12 +60,44 @@ long syscall_raw(long n, long a1, long a2, long a3, long a4, long a5, long a6) : "=a"(ret) : "a"(n), "b"(a1), "c"(a2), "d"(a3), "S"(a4), "D"(a5) : "memory"); +#elif defined __aarch64__ + register long x0 asm("x0") = a1; + register long x1 asm("x1") = a2; + register long x2 asm("x2") = a3; + register long x3 asm("x3") = a4; + register long x4 asm("x4") = a5; + register long x5 asm("x5") = a6; + register long x8 asm("x8") = n; + asm volatile ("svc #0" + : "=r"(x0) + : "r"(x0), "r"(x1), "r"(x2), "r"(x3), "r"(x4), "r"(x5), "r"(x8) + : "memory"); + ret = x0; #else # error syscall_raw() not implemented #endif return ret; }

+static inline long clone_raw(unsigned long flags, void *stack, + int *parent_tid, int *child_tid) +{ + long a1 = flags; + long a2 = (long)stack; + long a3 = (long)parent_tid; +#if defined(__x86_64__) || defined(__i386) + long a4 = (long)child_tid; + long a5 = 0; +#elif defined(__aarch64__) + long a4 = 0; + long a5 = (long)child_tid; +#else +# error clone_raw() not implemented +#endif + + return syscall_raw(SYS_clone, a1, a2, a3, a4, a5, 0); +} + /* * Returns the most restrictive pkey register value that can be used by the * tests. @@ -294,14 +326,13 @@ static void test_sigsegv_handler_with_different_pkey_for_stack(void) memset(&siginfo, 0, sizeof(siginfo));

/* Use clone to avoid newer glibcs using rseq on new threads */ - long ret = syscall_raw(SYS_clone, - CLONE_VM | CLONE_FS | CLONE_FILES | - CLONE_SIGHAND | CLONE_THREAD | CLONE_SYSVSEM | - CLONE_PARENT_SETTID | CLONE_CHILD_CLEARTID | - CLONE_DETACHED, - (long) ((char *)(stack) + STACK_SIZE), - (long) &parent_pid, - (long) &child_pid, 0, 0); + long ret = clone_raw(CLONE_VM | CLONE_FS | CLONE_FILES | + CLONE_SIGHAND | CLONE_THREAD | CLONE_SYSVSEM | + CLONE_PARENT_SETTID | CLONE_CHILD_CLEARTID | + CLONE_DETACHED, + stack + STACK_SIZE, + &parent_pid, + &child_pid);

if (ret < 0) { errno = -ret; @@ -466,14 +497,13 @@ static void test_pkru_sigreturn(void) sigstack.ss_size = STACK_SIZE;

/* Use clone to avoid newer glibcs using rseq on new threads */ - long ret = syscall_raw(SYS_clone, - CLONE_VM | CLONE_FS | CLONE_FILES | - CLONE_SIGHAND | CLONE_THREAD | CLONE_SYSVSEM | - CLONE_PARENT_SETTID | CLONE_CHILD_CLEARTID | - CLONE_DETACHED, - (long) ((char *)(stack) + STACK_SIZE), - (long) &parent_pid, - (long) &child_pid, 0, 0); + long ret = clone_raw(CLONE_VM | CLONE_FS | CLONE_FILES | + CLONE_SIGHAND | CLONE_THREAD | CLONE_SYSVSEM | + CLONE_PARENT_SETTID | CLONE_CHILD_CLEARTID | + CLONE_DETACHED, + stack + STACK_SIZE, + &parent_pid, + &child_pid);

if (ret < 0) { errno = -ret;