The generic entry abort the syscall_trace_enter() sequence if ptrace_report_syscall_entry() errors out, but arm64 not.

As the ptrace_report_syscall_entry() comment said, the calling arch code should abort the system call and must prevent normal entry so no system call is made if ptrace_report_syscall_entry() return nonzero.

In preparation for moving arm64 over to the generic entry code, return early if ptrace_report_syscall_entry() encounters an error.

Signed-off-by: Jinjie Ruan ruanjinjie@huawei.com --- arch/arm64/kernel/ptrace.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 4532e9831856..3926ce6aa268 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -2346,15 +2346,18 @@ static __always_inline unsigned long ptrace_save_reg(struct pt_regs *regs, return saved_reg; }

-static void report_syscall_entry(struct pt_regs *regs) +static int report_syscall_entry(struct pt_regs *regs) { unsigned long saved_reg; - int regno; + int regno, ret;

saved_reg = ptrace_save_reg(regs, PTRACE_SYSCALL_ENTER, &regno); - if (ptrace_report_syscall_entry(regs)) + 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) @@ -2381,10 +2384,11 @@ static void report_syscall_exit(struct pt_regs *regs) int syscall_trace_enter(struct pt_regs *regs) { unsigned long flags = read_thread_flags(); + int ret;

if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) { - report_syscall_entry(regs); - if (flags & _TIF_SYSCALL_EMU) + ret = report_syscall_entry(regs); + if (ret || (flags & _TIF_SYSCALL_EMU)) return NO_SYSCALL; }

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().

Reviewed-by: Kevin Brodsky kevin.brodsky@arm.com 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 b962cbcca11d..8b0a46aac51f 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -2416,6 +2416,8 @@ 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) @@ -2423,8 +2425,6 @@ 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); }

/*

Differ from generic entry, due to historical reasons, ARM64 need to save/restore during syscall entry/exit because ARM64 use a scratch register (ip(r12) on AArch32, x7 on AArch64) to denote syscall entry/exit.

In preparation for moving arm64 over to the generic entry code, add arch_ptrace_report_syscall_entry/exit() as the default ptrace_report_syscall_entry/exit() implementation. This allows arm64 to implement the architecture specific version.

This allows arm64 to implement the architecture specific version.

Reviewed-by: Kevin Brodsky kevin.brodsky@arm.com Suggested-by: Mark Rutland mark.rutland@arm.com Suggested-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Jinjie Ruan ruanjinjie@huawei.com --- kernel/entry/syscall-common.c | 43 +++++++++++++++++++++++++++++++++-- 1 file changed, 41 insertions(+), 2 deletions(-)

diff --git a/kernel/entry/syscall-common.c b/kernel/entry/syscall-common.c index 66e6ba7fa80c..27310e611567 100644 --- a/kernel/entry/syscall-common.c +++ b/kernel/entry/syscall-common.c @@ -17,6 +17,25 @@ static inline void syscall_enter_audit(struct pt_regs *regs, long syscall) } }

+/** + * arch_ptrace_report_syscall_entry - Architecture specific + * ptrace_report_syscall_entry(). + * + * Invoked from syscall_trace_enter() to wrap ptrace_report_syscall_entry(). + * Defaults to ptrace_report_syscall_entry. + * + * The main purpose is to support arch-specific ptrace_report_syscall_entry() + * implementation. + */ +static __always_inline int arch_ptrace_report_syscall_entry(struct pt_regs *regs); + +#ifndef arch_ptrace_report_syscall_entry +static __always_inline int arch_ptrace_report_syscall_entry(struct pt_regs *regs) +{ + return ptrace_report_syscall_entry(regs); +} +#endif + long syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long work) { @@ -34,7 +53,7 @@ long syscall_trace_enter(struct pt_regs *regs, long syscall,

/* Handle ptrace */ if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) { - ret = ptrace_report_syscall_entry(regs); + ret = arch_ptrace_report_syscall_entry(regs); if (ret || (work & SYSCALL_WORK_SYSCALL_EMU)) return -1L; } @@ -84,6 +103,26 @@ static inline bool report_single_step(unsigned long work) return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP; }

+/** + * arch_ptrace_report_syscall_exit - Architecture specific + * ptrace_report_syscall_exit. + * + * Invoked from syscall_exit_work() to wrap ptrace_report_syscall_exit(). + * + * The main purpose is to support arch-specific ptrace_report_syscall_exit + * implementation. + */ +static __always_inline void arch_ptrace_report_syscall_exit(struct pt_regs *regs, + int step); + +#ifndef arch_ptrace_report_syscall_exit +static __always_inline void arch_ptrace_report_syscall_exit(struct pt_regs *regs, + int step) +{ + ptrace_report_syscall_exit(regs, step); +} +#endif + void syscall_exit_work(struct pt_regs *regs, unsigned long work) { bool step; @@ -108,5 +147,5 @@ void syscall_exit_work(struct pt_regs *regs, unsigned long work)

step = report_single_step(work); if (step || work & SYSCALL_WORK_SYSCALL_TRACE) - ptrace_report_syscall_exit(regs, step); + arch_ptrace_report_syscall_exit(regs, step); }

The generic entry expand secure_computing() in place and call __secure_computing() directly.

In order to switch to the generic entry for arm64, refactor secure_computing() for syscall_trace_enter().

No functional changes.

Reviewed-by: Kevin Brodsky kevin.brodsky@arm.com Signed-off-by: Jinjie Ruan ruanjinjie@huawei.com --- arch/arm64/kernel/ptrace.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 25111c121b5e..c6dee8a355e5 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -2392,8 +2392,11 @@ int syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long flags) }

/* Do the secure computing after ptrace; failures should be fast. */ - if (secure_computing() == -1) - return NO_SYSCALL; + 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); @@ -2411,7 +2414,7 @@ int syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long flags) audit_syscall_entry(syscall, regs->orig_x0, regs->regs[1], regs->regs[2], regs->regs[3]);

- return syscall; + return ret ? : syscall; }

static inline bool report_single_step(unsigned long flags)

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.

Reviewed-by: Kevin Brodsky kevin.brodsky@arm.com 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 c6dee8a355e5..36e7ba3f38a5 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; }

As syscall_exit_work() do not handle seccomp, so not check _TIF_SECCOMP for syscall_exit_work().

And as the man manual of PTRACE_SYSEMU and PTRACE_SYSEMU_SINGLESTEP said, "For PTRACE_SYSEMU, continue and stop on entry to the next system call, which will not be executed. For PTRACE_SYSEMU_SINGLESTEP, do the same but also singlestep if not a system call.". So only the syscall entry need to be reported for SYSCALL_EMU, so not check _TIF_SYSCALL_EMU for syscall_exit_work().

After this, audit_syscall_exit() and report_syscall_exit() will no longer be called if only SECCOMP and/or SYSCALL_EMU is set.

And remove has_syscall_work() by the way as currently it is only used in el0_svc_common().

This is another preparation for moving arm64 over to the generic entry code.

Link：https://man7.org/linux/man-pages/man2/ptrace.2.html Signed-off-by: Jinjie Ruan ruanjinjie@huawei.com --- arch/arm64/include/asm/syscall.h | 5 ----- arch/arm64/include/asm/thread_info.h | 3 +++ arch/arm64/kernel/ptrace.c | 2 +- arch/arm64/kernel/syscall.c | 2 +- 4 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index ccdaa805aa52..9f2aa9c57560 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -120,11 +120,6 @@ static inline int syscall_get_arch(struct task_struct *task) return AUDIT_ARCH_AARCH64; }

-static inline bool has_syscall_work(unsigned long flags) -{ - return unlikely(flags & _TIF_SYSCALL_WORK); -} - int syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long flags); void syscall_exit_to_user_mode_prepare(struct pt_regs *regs);

diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index ff4998fa1844..8d308ef64612 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -110,6 +110,9 @@ void arch_setup_new_exec(void); _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ _TIF_SYSCALL_EMU)

+#define _TIF_SYSCALL_EXIT_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ + _TIF_SYSCALL_TRACEPOINT) + #ifdef CONFIG_SHADOW_CALL_STACK #define INIT_SCS \ .scs_base = init_shadow_call_stack, \ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 25fdf320d73a..3e233968efa2 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -2431,7 +2431,7 @@ void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)

rseq_syscall(regs);

- if (has_syscall_work(flags) || flags & _TIF_SINGLESTEP) + if (unlikely(flags & _TIF_SYSCALL_EXIT_WORK) || flags & _TIF_SINGLESTEP) syscall_exit_work(regs, flags); }

diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 65021d0f49e1..881fd261e8cb 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -101,7 +101,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, return; }

- if (has_syscall_work(flags)) { + if (unlikely(flags & _TIF_SYSCALL_WORK)) { /* * 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

The generic report_single_step() always returns false if SYSCALL_EMU is set, but arm64 only checks _TIF_SINGLESTEP and does not check _TIF_SYSCALL_EMU, which means that if both _TIF_SINGLESTEP and _TIF_SYSCALL_EMU are set, the generic entry will not report a single-step, whereas arm64 will do it.

As the man manual of PTRACE_SYSEMU and PTRACE_SYSEMU_SINGLESTEP said, "For PTRACE_SYSEMU, continue and stop on entry to the next system call, which will not be executed. For PTRACE_SYSEMU_SINGLESTEP, do the same but also singlestep if not a system call.". And as the generic entry report_single_step() comment said, If SYSCALL_EMU is set, then the only reason to report is when SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). Because this syscall instruction has been already reported in syscall_trace_enter(), there is no need to report the syscall again in syscall_exit_work().

In preparation for moving arm64 over to the generic entry code,

- Add report_single_step() helper for arm64 to make it clear.

- Do not report_syscall_exit() if both _TIF_SYSCALL_EMU and _TIF_SINGLESTEP set.

Signed-off-by: Jinjie Ruan ruanjinjie@huawei.com --- arch/arm64/kernel/ptrace.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 3e233968efa2..25111c121b5e 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -2414,14 +2414,25 @@ int syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long flags) return syscall; }

+static inline bool report_single_step(unsigned long flags) +{ + if (flags & _TIF_SYSCALL_EMU) + return false; + + return flags & _TIF_SINGLESTEP; +} + static void syscall_exit_work(struct pt_regs *regs, unsigned long flags) { + bool step; + 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)) + step = report_single_step(flags); + if (step || flags & _TIF_SYSCALL_TRACE) report_syscall_exit(regs); }

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.

- Remove _TIF_SYSCALL_WORK and 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 | 19 +++- arch/arm64/include/asm/thread_info.h | 19 +--- arch/arm64/kernel/debug-monitors.c | 7 ++ arch/arm64/kernel/ptrace.c | 153 -------------------------- arch/arm64/kernel/signal.c | 2 +- arch/arm64/kernel/syscall.c | 6 +- 8 files changed, 107 insertions(+), 177 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..d8bf4bf342e8 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 __always_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 9f2aa9c57560..240d45735cc5 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[]; @@ -120,7 +123,19 @@ static inline int syscall_get_arch(struct task_struct *task) return AUDIT_ARCH_AARCH64; }

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

#endif /* __ASM_SYSCALL_H */ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 8d308ef64612..0c083be23018 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 +66,6 @@ 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_PATCH_PENDING 13 /* pending live patching update */ #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ #define TIF_FREEZE 19 @@ -92,27 +88,14 @@ 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) - -#define _TIF_SYSCALL_EXIT_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ - _TIF_SYSCALL_TRACEPOINT) - #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 36e7ba3f38a5..cfbb6e409fcf 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -8,7 +8,6 @@ * Copyright (C) 2012 ARM Ltd. */

-#include <linux/audit.h> #include <linux/compat.h> #include <linux/kernel.h> #include <linux/sched/signal.h> @@ -18,7 +17,6 @@ #include <linux/smp.h> #include <linux/ptrace.h> #include <linux/user.h> -#include <linux/seccomp.h> #include <linux/security.h> #include <linux/init.h> #include <linux/signal.h> @@ -28,7 +26,6 @@ #include <linux/hw_breakpoint.h> #include <linux/regset.h> #include <linux/elf.h> -#include <linux/rseq.h>

#include <asm/compat.h> #include <asm/cpufeature.h> @@ -38,13 +35,9 @@ #include <asm/mte.h> #include <asm/pointer_auth.h> #include <asm/stacktrace.h> -#include <asm/syscall.h> #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; @@ -2312,152 +2305,6 @@ 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 __always_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 inline bool report_single_step(unsigned long flags) -{ - if (flags & _TIF_SYSCALL_EMU) - return false; - - return flags & _TIF_SINGLESTEP; -} - -static void syscall_exit_work(struct pt_regs *regs, unsigned long flags) -{ - bool step; - - audit_syscall_exit(regs); - - if (flags & _TIF_SYSCALL_TRACEPOINT) - trace_sys_exit(regs, syscall_get_return_value(current, regs)); - - step = report_single_step(flags); - if (step || flags & _TIF_SYSCALL_TRACE) - 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 (unlikely(flags & _TIF_SYSCALL_EXIT_WORK) || 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 881fd261e8cb..47e193a1cfff 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 (unlikely(flags & _TIF_SYSCALL_WORK)) { + if (unlikely(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; }