The generic syscall entry code has the form:

| syscall_trace_enter() | { | ptrace_report_syscall_entry() | } | | syscall_exit_work() | { | ptrace_report_syscall_exit() | }

In preparation for moving arm64 over to the generic entry code, split report_syscall() to two separate enter and exit functions to align the structure of the arm64 code with syscall_trace_enter() and syscall_exit_work() from the generic entry code.

No functional changes.

Suggested-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Jinjie Ruan ruanjinjie@huawei.com --- v8: - report_syscall_enter() -> report_syscall_entry(). - Add ptrace_save_reg() helper. --- arch/arm64/kernel/ptrace.c | 41 +++++++++++++++++++++++++++----------- 1 file changed, 29 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 4b001121c72d..abc5baa29cc9 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -2317,9 +2317,10 @@ enum ptrace_syscall_dir { PTRACE_SYSCALL_EXIT, };

-static void report_syscall(struct pt_regs *regs, enum ptrace_syscall_dir dir) +static inline unsigned long ptrace_save_reg(struct pt_regs *regs, + enum ptrace_syscall_dir dir, + int *regno) { - int regno; unsigned long saved_reg;

/* @@ -2338,15 +2339,31 @@ static void report_syscall(struct pt_regs *regs, enum ptrace_syscall_dir dir) * - Syscall stops behave differently to seccomp and pseudo-step traps * (the latter do not nobble any registers). */ - regno = (is_compat_task() ? 12 : 7); - saved_reg = regs->regs[regno]; - regs->regs[regno] = dir; + *regno = (is_compat_task() ? 12 : 7); + saved_reg = regs->regs[*regno]; + regs->regs[*regno] = dir;

- if (dir == PTRACE_SYSCALL_ENTER) { - if (ptrace_report_syscall_entry(regs)) - forget_syscall(regs); - regs->regs[regno] = saved_reg; - } else if (!test_thread_flag(TIF_SINGLESTEP)) { + return saved_reg; +} + +static void report_syscall_entry(struct pt_regs *regs) +{ + unsigned long saved_reg; + int regno; + + saved_reg = ptrace_save_reg(regs, PTRACE_SYSCALL_ENTER, &regno); + if (ptrace_report_syscall_entry(regs)) + forget_syscall(regs); + regs->regs[regno] = saved_reg; +} + +static void report_syscall_exit(struct pt_regs *regs) +{ + unsigned long saved_reg; + int regno; + + saved_reg = ptrace_save_reg(regs, PTRACE_SYSCALL_EXIT, &regno); + if (!test_thread_flag(TIF_SINGLESTEP)) { ptrace_report_syscall_exit(regs, 0); regs->regs[regno] = saved_reg; } else { @@ -2366,7 +2383,7 @@ int syscall_trace_enter(struct pt_regs *regs) unsigned long flags = read_thread_flags();

if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) { - report_syscall(regs, PTRACE_SYSCALL_ENTER); + report_syscall_entry(regs); if (flags & _TIF_SYSCALL_EMU) return NO_SYSCALL; } @@ -2394,7 +2411,7 @@ void syscall_trace_exit(struct pt_regs *regs) trace_sys_exit(regs, syscall_get_return_value(current, regs));

if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP)) - report_syscall(regs, PTRACE_SYSCALL_EXIT); + report_syscall_exit(regs);

rseq_syscall(regs); }

commit a9f3a74a29af ("entry: Provide generic syscall exit function") introduce generic syscall exit function and call rseq_syscall() before audit_syscall_exit() and arch_syscall_exit_tracehook().

And commit b74406f37737 ("arm: Add syscall detection for restartable sequences") add rseq support for arm32, which also call rseq_syscall() before audit_syscall_exit() and tracehook_report_syscall().

However, commit 409d5db49867c ("arm64: rseq: Implement backend rseq calls and select HAVE_RSEQ") implement arm64 rseq and call rseq_syscall() after audit_syscall_exit() and tracehook_report_syscall().

So compared to the generic entry and arm32 code, arm64 terminates the process a bit later if the syscall is issued within a restartable sequence.

But as commit b74406f37737 ("arm: Add syscall detection for restartable sequences") said, syscalls are not allowed inside restartable sequences, so should call rseq_syscall() at the very beginning of system call exiting path for CONFIG_DEBUG_RSEQ=y kernel. This could help us to detect whether there is a syscall issued inside restartable sequences.

It makes sense to raise SIGSEGV via rseq_syscall() before auditing and ptrace syscall exit, because this guarantees that the process is already in an error state with SIGSEGV pending when those later steps run. Although it makes no practical difference to signal delivery (signals are processed at the very end in arm64_exit_to_user_mode()), the ordering is more logical: detect and flag the error first, then proceed with the remaining work.

To make it more reasonable and in preparation for moving arm64 over to the generic entry code, move rseq_syscall() ahead before audit_syscall_exit().

Signed-off-by: Jinjie Ruan ruanjinjie@huawei.com --- arch/arm64/kernel/ptrace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 63ba6c961ecc..dfdd886dc0a9 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -2411,6 +2411,8 @@ int syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long flags)

void syscall_trace_exit(struct pt_regs *regs, unsigned long flags) { + rseq_syscall(regs); + audit_syscall_exit(regs);

if (flags & _TIF_SYSCALL_TRACEPOINT) @@ -2418,8 +2420,6 @@ void syscall_trace_exit(struct pt_regs *regs, unsigned long flags)

if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP)) report_syscall_exit(regs); - - rseq_syscall(regs); }

/*

From: kemal kmal@cock.li

Support aarch64 to test "Syscall User Dispatch" with sud_test selftest testcase.

Signed-off-by: kemal kmal@cock.li --- tools/testing/selftests/syscall_user_dispatch/sud_test.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c index 2eb2c06303f2..f53ebc89befc 100644 --- a/tools/testing/selftests/syscall_user_dispatch/sud_test.c +++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c @@ -192,6 +192,10 @@ static void handle_sigsys(int sig, siginfo_t *info, void *ucontext) ((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A0] = ((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A7]; #endif +#ifdef __aarch64__ + ((ucontext_t *)ucontext)->uc_mcontext.regs[0] = (unsigned int) + ((ucontext_t *)ucontext)->uc_mcontext.regs[8]; +#endif }

int setup_sigsys_handler(void)

The generic entry check audit context first and use syscall_get_arguments() helper.

In order to switch to the generic entry for arm64,

- Also use syscall_get_arguments() to get audit_syscall_entry()'s last four parameters.

- Extract the syscall_enter_audit() helper to make it clear.

- Check audit context first, which saves an unnecessary memcpy when current process's audit_context is NULL.

Overall these changes make syscall_enter_audit() exactly equivalent to the generic one.

No functional changes.

Signed-off-by: Jinjie Ruan ruanjinjie@huawei.com --- arch/arm64/kernel/ptrace.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 72d4d987ba3b..c2bd0130212d 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -2381,6 +2381,16 @@ static void report_syscall_exit(struct pt_regs *regs) } }

+static inline void syscall_enter_audit(struct pt_regs *regs, long syscall) +{ + if (unlikely(audit_context())) { + unsigned long args[6]; + + syscall_get_arguments(current, regs, args); + audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]); + } +} + int syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long flags) { int ret; @@ -2411,8 +2421,7 @@ int syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long flags) syscall = syscall_get_nr(current, regs); }

- audit_syscall_entry(syscall, regs->orig_x0, regs->regs[1], - regs->regs[2], regs->regs[3]); + syscall_enter_audit(regs, syscall);

return ret ? : syscall; }

Currently, x86, Riscv, Loongarch use the generic entry which makes maintainers' work easier and codes more elegant. arm64 has already switched to the generic IRQ entry, so completely convert arm64 to use the generic entry infrastructure from kernel/entry/*.

The changes are below: - Remove TIF_SYSCALL_* flag, _TIF_WORK_MASK, _TIF_SYSCALL_WORK, and remove has_syscall_work(), as _TIF_SYSCALL_WORK is equal with SYSCALL_WORK_ENTER.

- Implement arch_ptrace_report_syscall_entry/exit() with report_syscall_entry/exit() to do arm64-specific save/restore during syscall entry/exit.

- Add "ARCH_SYSCALL_WORK_EXIT" to be defined as "_TIF_SECCOMP | _TIF_SYSCALL_EMU" to keep the arm64 behaviour unchanged.

- Remove arm64 syscall_trace_enter(), syscall_exit_to_user_mode_prepare(), and related sub-functions including syscall_exit_work() and syscall_enter_audit(), by calling generic entry's functions with similar functionality.

- Implement arch_syscall_is_vdso_sigreturn() to support "Syscall User Dispatch".

Suggested-by: Kevin Brodsky kevin.brodsky@arm.com Suggested-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Jinjie Ruan ruanjinjie@huawei.com --- arch/arm64/Kconfig | 2 +- arch/arm64/include/asm/entry-common.h | 76 ++++++++++++++ arch/arm64/include/asm/syscall.h | 20 +++- arch/arm64/include/asm/thread_info.h | 16 +-- arch/arm64/kernel/debug-monitors.c | 7 ++ arch/arm64/kernel/ptrace.c | 138 -------------------------- arch/arm64/kernel/signal.c | 2 +- arch/arm64/kernel/syscall.c | 6 +- 8 files changed, 108 insertions(+), 159 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 6663ffd23f25..1463ff15d67a 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -152,9 +152,9 @@ config ARM64 select GENERIC_CPU_DEVICES select GENERIC_CPU_VULNERABILITIES select GENERIC_EARLY_IOREMAP + select GENERIC_ENTRY select GENERIC_IDLE_POLL_SETUP select GENERIC_IOREMAP - select GENERIC_IRQ_ENTRY select GENERIC_IRQ_IPI select GENERIC_IRQ_KEXEC_CLEAR_VM_FORWARD select GENERIC_IRQ_PROBE diff --git a/arch/arm64/include/asm/entry-common.h b/arch/arm64/include/asm/entry-common.h index cab8cd78f693..ab0544b44549 100644 --- a/arch/arm64/include/asm/entry-common.h +++ b/arch/arm64/include/asm/entry-common.h @@ -3,14 +3,21 @@ #ifndef _ASM_ARM64_ENTRY_COMMON_H #define _ASM_ARM64_ENTRY_COMMON_H

+#include <linux/ptrace.h> #include <linux/thread_info.h>

+#include <asm/compat.h> #include <asm/cpufeature.h> #include <asm/daifflags.h> #include <asm/fpsimd.h> #include <asm/mte.h> #include <asm/stacktrace.h>

+enum ptrace_syscall_dir { + PTRACE_SYSCALL_ENTER = 0, + PTRACE_SYSCALL_EXIT, +}; + #define ARCH_EXIT_TO_USER_MODE_WORK (_TIF_MTE_ASYNC_FAULT | _TIF_FOREIGN_FPSTATE)

static __always_inline void arch_exit_to_user_mode_work(struct pt_regs *regs, @@ -54,4 +61,73 @@ static inline bool arch_irqentry_exit_need_resched(void)

#define arch_irqentry_exit_need_resched arch_irqentry_exit_need_resched

+static inline unsigned long ptrace_save_reg(struct pt_regs *regs, + enum ptrace_syscall_dir dir, + int *regno) +{ + unsigned long saved_reg; + + /* + * We have some ABI weirdness here in the way that we handle syscall + * exit stops because we indicate whether or not the stop has been + * signalled from syscall entry or syscall exit by clobbering a general + * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee + * and restoring its old value after the stop. This means that: + * + * - Any writes by the tracer to this register during the stop are + * ignored/discarded. + * + * - The actual value of the register is not available during the stop, + * so the tracer cannot save it and restore it later. + * + * - Syscall stops behave differently to seccomp and pseudo-step traps + * (the latter do not nobble any registers). + */ + *regno = (is_compat_task() ? 12 : 7); + saved_reg = regs->regs[*regno]; + regs->regs[*regno] = dir; + + return saved_reg; +} + +static __always_inline int arch_ptrace_report_syscall_entry(struct pt_regs *regs) +{ + unsigned long saved_reg; + int regno, ret; + + saved_reg = ptrace_save_reg(regs, PTRACE_SYSCALL_ENTER, &regno); + ret = ptrace_report_syscall_entry(regs); + if (ret) + forget_syscall(regs); + regs->regs[regno] = saved_reg; + + return ret; +} + +#define arch_ptrace_report_syscall_entry arch_ptrace_report_syscall_entry + +static __always_inline void arch_ptrace_report_syscall_exit(struct pt_regs *regs, + int step) +{ + unsigned long saved_reg; + int regno; + + saved_reg = ptrace_save_reg(regs, PTRACE_SYSCALL_EXIT, &regno); + if (!step) { + ptrace_report_syscall_exit(regs, 0); + regs->regs[regno] = saved_reg; + } else { + regs->regs[regno] = saved_reg; + + /* + * Signal a pseudo-step exception since we are stepping but + * tracer modifications to the registers may have rewound the + * state machine. + */ + ptrace_report_syscall_exit(regs, 1); + } +} + +#define arch_ptrace_report_syscall_exit arch_ptrace_report_syscall_exit + #endif /* _ASM_ARM64_ENTRY_COMMON_H */ diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index 6225981fbbdb..f705ba2bb6fd 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -9,6 +9,9 @@ #include <linux/compat.h> #include <linux/err.h>

+#include <asm/compat.h> +#include <asm/vdso.h> + typedef long (*syscall_fn_t)(const struct pt_regs *regs);

extern const syscall_fn_t sys_call_table[]; @@ -114,12 +117,21 @@ static inline int syscall_get_arch(struct task_struct *task) return AUDIT_ARCH_AARCH64; }

-static inline bool has_syscall_work(unsigned long flags) +static inline bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs) { - return unlikely(flags & _TIF_SYSCALL_WORK); + unsigned long sigtramp; + +#ifdef CONFIG_COMPAT + if (is_compat_task()) { + unsigned long vdso = (unsigned long)current->mm->context.sigpage; + + return (regs->pc >= vdso && regs->pc < (vdso + PAGE_SIZE)); + } +#endif + sigtramp = (unsigned long)VDSO_SYMBOL(current->mm->context.vdso, sigtramp); + return regs->pc == (sigtramp + 8); }

-int syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long flags); -void syscall_exit_to_user_mode_prepare(struct pt_regs *regs); +#define ARCH_SYSCALL_WORK_EXIT (_TIF_SECCOMP | _TIF_SYSCALL_EMU)

#endif /* __ASM_SYSCALL_H */ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index ff4998fa1844..d3142b5d1b9c 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -43,6 +43,7 @@ struct thread_info { void *scs_sp; #endif u32 cpu; + unsigned long syscall_work; /* SYSCALL_WORK_ flags */ };

#define thread_saved_pc(tsk) \ @@ -65,11 +66,8 @@ void arch_setup_new_exec(void); #define TIF_UPROBE 5 /* uprobe breakpoint or singlestep */ #define TIF_MTE_ASYNC_FAULT 6 /* MTE Asynchronous Tag Check Fault */ #define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ -#define TIF_SYSCALL_TRACE 8 /* syscall trace active */ -#define TIF_SYSCALL_AUDIT 9 /* syscall auditing */ -#define TIF_SYSCALL_TRACEPOINT 10 /* syscall tracepoint for ftrace */ -#define TIF_SECCOMP 11 /* syscall secure computing */ -#define TIF_SYSCALL_EMU 12 /* syscall emulation active */ +#define TIF_SECCOMP 11 /* syscall secure computing */ +#define TIF_SYSCALL_EMU 12 /* syscall emulation active */ #define TIF_PATCH_PENDING 13 /* pending live patching update */ #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ #define TIF_FREEZE 19 @@ -92,24 +90,16 @@ void arch_setup_new_exec(void); #define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE) -#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) -#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) -#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) #define _TIF_PATCH_PENDING (1 << TIF_PATCH_PENDING) #define _TIF_UPROBE (1 << TIF_UPROBE) -#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_32BIT (1 << TIF_32BIT) #define _TIF_SVE (1 << TIF_SVE) #define _TIF_MTE_ASYNC_FAULT (1 << TIF_MTE_ASYNC_FAULT) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_TSC_SIGSEGV (1 << TIF_TSC_SIGSEGV)

-#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ - _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ - _TIF_SYSCALL_EMU) - #ifdef CONFIG_SHADOW_CALL_STACK #define INIT_SCS \ .scs_base = init_shadow_call_stack, \ diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 29307642f4c9..e67643a70405 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -385,11 +385,18 @@ void user_enable_single_step(struct task_struct *task)

if (!test_and_set_ti_thread_flag(ti, TIF_SINGLESTEP)) set_regs_spsr_ss(task_pt_regs(task)); + + /* + * Ensure that a trap is triggered once stepping out of a system + * call prior to executing any user instruction. + */ + set_task_syscall_work(task, SYSCALL_EXIT_TRAP); } NOKPROBE_SYMBOL(user_enable_single_step);

void user_disable_single_step(struct task_struct *task) { clear_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP); + clear_task_syscall_work(task, SYSCALL_EXIT_TRAP); } NOKPROBE_SYMBOL(user_disable_single_step); diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index c2bd0130212d..9e3b39e207d1 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -42,9 +42,6 @@ #include <asm/traps.h> #include <asm/system_misc.h>

-#define CREATE_TRACE_POINTS -#include <trace/events/syscalls.h> - struct pt_regs_offset { const char *name; int offset; @@ -2312,141 +2309,6 @@ long arch_ptrace(struct task_struct *child, long request, return ptrace_request(child, request, addr, data); }

-enum ptrace_syscall_dir { - PTRACE_SYSCALL_ENTER = 0, - PTRACE_SYSCALL_EXIT, -}; - -static inline unsigned long ptrace_save_reg(struct pt_regs *regs, - enum ptrace_syscall_dir dir, - int *regno) -{ - unsigned long saved_reg; - - /* - * We have some ABI weirdness here in the way that we handle syscall - * exit stops because we indicate whether or not the stop has been - * signalled from syscall entry or syscall exit by clobbering a general - * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee - * and restoring its old value after the stop. This means that: - * - * - Any writes by the tracer to this register during the stop are - * ignored/discarded. - * - * - The actual value of the register is not available during the stop, - * so the tracer cannot save it and restore it later. - * - * - Syscall stops behave differently to seccomp and pseudo-step traps - * (the latter do not nobble any registers). - */ - *regno = (is_compat_task() ? 12 : 7); - saved_reg = regs->regs[*regno]; - regs->regs[*regno] = dir; - - return saved_reg; -} - -static int report_syscall_entry(struct pt_regs *regs) -{ - unsigned long saved_reg; - int regno, ret; - - saved_reg = ptrace_save_reg(regs, PTRACE_SYSCALL_ENTER, &regno); - ret = ptrace_report_syscall_entry(regs); - if (ret) - forget_syscall(regs); - regs->regs[regno] = saved_reg; - - return ret; -} - -static void report_syscall_exit(struct pt_regs *regs) -{ - unsigned long saved_reg; - int regno; - - saved_reg = ptrace_save_reg(regs, PTRACE_SYSCALL_EXIT, &regno); - if (!test_thread_flag(TIF_SINGLESTEP)) { - ptrace_report_syscall_exit(regs, 0); - regs->regs[regno] = saved_reg; - } else { - regs->regs[regno] = saved_reg; - - /* - * Signal a pseudo-step exception since we are stepping but - * tracer modifications to the registers may have rewound the - * state machine. - */ - ptrace_report_syscall_exit(regs, 1); - } -} - -static inline void syscall_enter_audit(struct pt_regs *regs, long syscall) -{ - if (unlikely(audit_context())) { - unsigned long args[6]; - - syscall_get_arguments(current, regs, args); - audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]); - } -} - -int syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long flags) -{ - int ret; - - if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) { - ret = report_syscall_entry(regs); - if (ret || (flags & _TIF_SYSCALL_EMU)) - return NO_SYSCALL; - } - - /* Do the secure computing after ptrace; failures should be fast. */ - if (flags & _TIF_SECCOMP) { - ret = __secure_computing(); - if (ret == -1) - return NO_SYSCALL; - } - - /* Either of the above might have changed the syscall number */ - syscall = syscall_get_nr(current, regs); - - if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) { - trace_sys_enter(regs, syscall); - - /* - * Probes or BPF hooks in the tracepoint may have changed the - * system call number as well. - */ - syscall = syscall_get_nr(current, regs); - } - - syscall_enter_audit(regs, syscall); - - return ret ? : syscall; -} - -static void syscall_exit_work(struct pt_regs *regs, unsigned long flags) -{ - audit_syscall_exit(regs); - - if (flags & _TIF_SYSCALL_TRACEPOINT) - trace_sys_exit(regs, syscall_get_return_value(current, regs)); - - if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP)) - report_syscall_exit(regs); -} - -void syscall_exit_to_user_mode_prepare(struct pt_regs *regs) -{ - unsigned long flags = read_thread_flags(); - - rseq_syscall(regs); - - if (has_syscall_work(flags) || flags & _TIF_SINGLESTEP) - syscall_exit_work(regs, flags); -} - /* * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487D.a. * We permit userspace to set SSBS (AArch64 bit 12, AArch32 bit 23) which is diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 1110eeb21f57..d3ec1892b3c7 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -8,8 +8,8 @@

#include <linux/cache.h> #include <linux/compat.h> +#include <linux/entry-common.h> #include <linux/errno.h> -#include <linux/irq-entry-common.h> #include <linux/kernel.h> #include <linux/signal.h> #include <linux/freezer.h> diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 65021d0f49e1..9848772c63fd 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -2,6 +2,7 @@

#include <linux/compiler.h> #include <linux/context_tracking.h> +#include <linux/entry-common.h> #include <linux/errno.h> #include <linux/nospec.h> #include <linux/ptrace.h> @@ -68,6 +69,7 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno, static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, const syscall_fn_t syscall_table[]) { + unsigned long work = READ_ONCE(current_thread_info()->syscall_work); unsigned long flags = read_thread_flags();

regs->orig_x0 = regs->regs[0]; @@ -101,7 +103,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, return; }

- if (has_syscall_work(flags)) { + if (work & SYSCALL_WORK_ENTER) { /* * The de-facto standard way to skip a system call using ptrace * is to set the system call to -1 (NO_SYSCALL) and set x0 to a @@ -119,7 +121,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, */ if (scno == NO_SYSCALL) syscall_set_return_value(current, regs, -ENOSYS, 0); - scno = syscall_trace_enter(regs, scno, flags); + scno = syscall_trace_enter(regs, scno, work); if (scno == NO_SYSCALL) goto trace_exit; }