diff mbox series

MIPS: scall: Save thread_info.syscall unconditionally on entry

Message ID 20240328-mips_save_syscall-v1-1-9e1d62d6999d@flygoat.com (mailing list archive)
State Accepted
Commit 4370b673ccf240bf7587b0cb8e6726a5ccaf1f17
Headers show
Series MIPS: scall: Save thread_info.syscall unconditionally on entry | expand

Commit Message

Jiaxun Yang March 28, 2024, 2:27 p.m. UTC
thread_info.syscall is used by syscall_get_nr to supply syscall nr
over a thread stack frame.

Previously, thread_info.syscall is only saved at syscall_trace_enter
when syscall tracing is enabled. However rest of the kernel code do
expect syscall_get_nr to be available without syscall tracing. The
previous design breaks collect_syscall.

Move saving process to syscall entry to fix it.

Reported-by: Xi Ruoyao <xry111@xry111.site>
Link: https://github.com/util-linux/util-linux/issues/2867
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
---
 arch/mips/include/asm/ptrace.h |  2 +-
 arch/mips/kernel/asm-offsets.c |  1 +
 arch/mips/kernel/ptrace.c      | 15 ++++++---------
 arch/mips/kernel/scall32-o32.S | 23 +++++++++++++----------
 arch/mips/kernel/scall64-n32.S |  3 ++-
 arch/mips/kernel/scall64-n64.S |  3 ++-
 arch/mips/kernel/scall64-o32.S | 33 +++++++++++++++++----------------
 7 files changed, 42 insertions(+), 38 deletions(-)


---
base-commit: a6bd6c9333397f5a0e2667d4d82fef8c970108f2
change-id: 20240328-mips_save_syscall-be471311cc9b

Best regards,

Comments

Jiaxun Yang April 4, 2024, 3:07 p.m. UTC | #1
在2024年3月28日三月 下午2:27,Jiaxun Yang写道:
> thread_info.syscall is used by syscall_get_nr to supply syscall nr
> over a thread stack frame.
>
> Previously, thread_info.syscall is only saved at syscall_trace_enter
> when syscall tracing is enabled. However rest of the kernel code do
> expect syscall_get_nr to be available without syscall tracing. The
> previous design breaks collect_syscall.
>
> Move saving process to syscall entry to fix it.
>
> Reported-by: Xi Ruoyao <xry111@xry111.site>
> Link: https://github.com/util-linux/util-linux/issues/2867
> Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>

Ping, this needs to be in fixes tree.

Thanks

> ---
>  arch/mips/include/asm/ptrace.h |  2 +-
>  arch/mips/kernel/asm-offsets.c |  1 +
>  arch/mips/kernel/ptrace.c      | 15 ++++++---------
>  arch/mips/kernel/scall32-o32.S | 23 +++++++++++++----------
>  arch/mips/kernel/scall64-n32.S |  3 ++-
>  arch/mips/kernel/scall64-n64.S |  3 ++-
>  arch/mips/kernel/scall64-o32.S | 33 +++++++++++++++++----------------
>  7 files changed, 42 insertions(+), 38 deletions(-)
>
> diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
> index d14d0e37ad02..4a2b40ce39e0 100644
> --- a/arch/mips/include/asm/ptrace.h
> +++ b/arch/mips/include/asm/ptrace.h
> @@ -159,7 +159,7 @@ extern unsigned long exception_ip(struct pt_regs *regs);
>  #define exception_ip(regs) exception_ip(regs)
>  #define profile_pc(regs) instruction_pointer(regs)
> 
> -extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall);
> +extern asmlinkage long syscall_trace_enter(struct pt_regs *regs);
>  extern asmlinkage void syscall_trace_leave(struct pt_regs *regs);
> 
>  extern void die(const char *, struct pt_regs *) __noreturn;
> diff --git a/arch/mips/kernel/asm-offsets.c 
> b/arch/mips/kernel/asm-offsets.c
> index d1b11f66f748..cb1045ebab06 100644
> --- a/arch/mips/kernel/asm-offsets.c
> +++ b/arch/mips/kernel/asm-offsets.c
> @@ -101,6 +101,7 @@ void output_thread_info_defines(void)
>  	OFFSET(TI_CPU, thread_info, cpu);
>  	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
>  	OFFSET(TI_REGS, thread_info, regs);
> +	OFFSET(TI_SYSCALL, thread_info, syscall);
>  	DEFINE(_THREAD_SIZE, THREAD_SIZE);
>  	DEFINE(_THREAD_MASK, THREAD_MASK);
>  	DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
> diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
> index 59288c13b581..61503a36067e 100644
> --- a/arch/mips/kernel/ptrace.c
> +++ b/arch/mips/kernel/ptrace.c
> @@ -1317,16 +1317,13 @@ long arch_ptrace(struct task_struct *child, 
> long request,
>   * Notification of system call entry/exit
>   * - triggered by current->work.syscall_trace
>   */
> -asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
> +asmlinkage long syscall_trace_enter(struct pt_regs *regs)
>  {
>  	user_exit();
> 
> -	current_thread_info()->syscall = syscall;
> -
>  	if (test_thread_flag(TIF_SYSCALL_TRACE)) {
>  		if (ptrace_report_syscall_entry(regs))
>  			return -1;
> -		syscall = current_thread_info()->syscall;
>  	}
> 
>  #ifdef CONFIG_SECCOMP
> @@ -1335,7 +1332,7 @@ asmlinkage long syscall_trace_enter(struct 
> pt_regs *regs, long syscall)
>  		struct seccomp_data sd;
>  		unsigned long args[6];
> 
> -		sd.nr = syscall;
> +		sd.nr = current_thread_info()->syscall;
>  		sd.arch = syscall_get_arch(current);
>  		syscall_get_arguments(current, regs, args);
>  		for (i = 0; i < 6; i++)
> @@ -1345,23 +1342,23 @@ asmlinkage long syscall_trace_enter(struct 
> pt_regs *regs, long syscall)
>  		ret = __secure_computing(&sd);
>  		if (ret == -1)
>  			return ret;
> -		syscall = current_thread_info()->syscall;
>  	}
>  #endif
> 
>  	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
>  		trace_sys_enter(regs, regs->regs[2]);
> 
> -	audit_syscall_entry(syscall, regs->regs[4], regs->regs[5],
> +	audit_syscall_entry(current_thread_info()->syscall,
> +			    regs->regs[4], regs->regs[5],
>  			    regs->regs[6], regs->regs[7]);
> 
>  	/*
>  	 * Negative syscall numbers are mistaken for rejected syscalls, but
>  	 * won't have had the return value set appropriately, so we do so now.
>  	 */
> -	if (syscall < 0)
> +	if (current_thread_info()->syscall < 0)
>  		syscall_set_return_value(current, regs, -ENOSYS, 0);
> -	return syscall;
> +	return current_thread_info()->syscall;
>  }
> 
>  /*
> diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
> index 18dc9b345056..2c604717e630 100644
> --- a/arch/mips/kernel/scall32-o32.S
> +++ b/arch/mips/kernel/scall32-o32.S
> @@ -77,6 +77,18 @@ loads_done:
>  	PTR_WD	load_a7, bad_stack_a7
>  	.previous
> 
> +	/*
> +	 * syscall number is in v0 unless we called syscall(__NR_###)
> +	 * where the real syscall number is in a0
> +	 */
> +	subu	t2, v0,  __NR_O32_Linux
> +	bnez	t2, 1f /* __NR_syscall at offset 0 */
> +	LONG_S	a0, TI_SYSCALL($28)	# Save a0 as syscall number
> +	b	2f
> +1:
> +	LONG_S	v0, TI_SYSCALL($28)	# Save v0 as syscall number
> +2:
> +
>  	lw	t0, TI_FLAGS($28)	# syscall tracing enabled?
>  	li	t1, _TIF_WORK_SYSCALL_ENTRY
>  	and	t0, t1
> @@ -114,16 +126,7 @@ syscall_trace_entry:
>  	SAVE_STATIC
>  	move	a0, sp
> 
> -	/*
> -	 * syscall number is in v0 unless we called syscall(__NR_###)
> -	 * where the real syscall number is in a0
> -	 */
> -	move	a1, v0
> -	subu	t2, v0,  __NR_O32_Linux
> -	bnez	t2, 1f /* __NR_syscall at offset 0 */
> -	lw	a1, PT_R4(sp)
> -
> -1:	jal	syscall_trace_enter
> +	jal	syscall_trace_enter
> 
>  	bltz	v0, 1f			# seccomp failed? Skip syscall
> 
> diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
> index 97456b2ca7dc..97788859238c 100644
> --- a/arch/mips/kernel/scall64-n32.S
> +++ b/arch/mips/kernel/scall64-n32.S
> @@ -44,6 +44,8 @@ NESTED(handle_sysn32, PT_SIZE, sp)
> 
>  	sd	a3, PT_R26(sp)		# save a3 for syscall restarting
> 
> +	LONG_S	v0, TI_SYSCALL($28)     # Store syscall number
> +
>  	li	t1, _TIF_WORK_SYSCALL_ENTRY
>  	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
>  	and	t0, t1, t0
> @@ -72,7 +74,6 @@ syscall_common:
>  n32_syscall_trace_entry:
>  	SAVE_STATIC
>  	move	a0, sp
> -	move	a1, v0
>  	jal	syscall_trace_enter
> 
>  	bltz	v0, 1f			# seccomp failed? Skip syscall
> diff --git a/arch/mips/kernel/scall64-n64.S b/arch/mips/kernel/scall64-n64.S
> index e6264aa62e45..be11ea5cc67e 100644
> --- a/arch/mips/kernel/scall64-n64.S
> +++ b/arch/mips/kernel/scall64-n64.S
> @@ -46,6 +46,8 @@ NESTED(handle_sys64, PT_SIZE, sp)
> 
>  	sd	a3, PT_R26(sp)		# save a3 for syscall restarting
> 
> +	LONG_S	v0, TI_SYSCALL($28)     # Store syscall number
> +
>  	li	t1, _TIF_WORK_SYSCALL_ENTRY
>  	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
>  	and	t0, t1, t0
> @@ -82,7 +84,6 @@ n64_syscall_exit:
>  syscall_trace_entry:
>  	SAVE_STATIC
>  	move	a0, sp
> -	move	a1, v0
>  	jal	syscall_trace_enter
> 
>  	bltz	v0, 1f			# seccomp failed? Skip syscall
> diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
> index d3c2616cba22..7a5abb73e531 100644
> --- a/arch/mips/kernel/scall64-o32.S
> +++ b/arch/mips/kernel/scall64-o32.S
> @@ -79,6 +79,22 @@ loads_done:
>  	PTR_WD	load_a7, bad_stack_a7
>  	.previous
> 
> +	/*
> +	 * absolute syscall number is in v0 unless we called syscall(__NR_###)
> +	 * where the real syscall number is in a0
> +	 * note: NR_syscall is the first O32 syscall but the macro is
> +	 * only defined when compiling with -mabi=32 (CONFIG_32BIT)
> +	 * therefore __NR_O32_Linux is used (4000)
> +	 */
> +
> +	subu	t2, v0,  __NR_O32_Linux
> +	bnez	t2, 1f /* __NR_syscall at offset 0 */
> +	LONG_S	a0, TI_SYSCALL($28)	# Save a0 as syscall number
> +	b	2f
> +1:
> +	LONG_S	v0, TI_SYSCALL($28)	# Save v0 as syscall number
> +2:
> +
>  	li	t1, _TIF_WORK_SYSCALL_ENTRY
>  	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
>  	and	t0, t1, t0
> @@ -113,22 +129,7 @@ trace_a_syscall:
>  	sd	a7, PT_R11(sp)		# For indirect syscalls
> 
>  	move	a0, sp
> -	/*
> -	 * absolute syscall number is in v0 unless we called syscall(__NR_###)
> -	 * where the real syscall number is in a0
> -	 * note: NR_syscall is the first O32 syscall but the macro is
> -	 * only defined when compiling with -mabi=32 (CONFIG_32BIT)
> -	 * therefore __NR_O32_Linux is used (4000)
> -	 */
> -	.set	push
> -	.set	reorder
> -	subu	t1, v0,  __NR_O32_Linux
> -	move	a1, v0
> -	bnez	t1, 1f /* __NR_syscall at offset 0 */
> -	ld	a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
> -	.set	pop
> -
> -1:	jal	syscall_trace_enter
> +	jal	syscall_trace_enter
> 
>  	bltz	v0, 1f			# seccomp failed? Skip syscall
> 
>
> ---
> base-commit: a6bd6c9333397f5a0e2667d4d82fef8c970108f2
> change-id: 20240328-mips_save_syscall-be471311cc9b
>
> Best regards,
> -- 
> Jiaxun Yang <jiaxun.yang@flygoat.com>
Oleg Nesterov April 4, 2024, 3:31 p.m. UTC | #2
On 04/04, Jiaxun Yang wrote:
> 
> 
> 在2024年3月28日三月 下午2:27,Jiaxun Yang写道:
> > thread_info.syscall is used by syscall_get_nr to supply syscall nr
> > over a thread stack frame.
> >
> > Previously, thread_info.syscall is only saved at syscall_trace_enter
> > when syscall tracing is enabled. However rest of the kernel code do
> > expect syscall_get_nr to be available without syscall tracing. The
> > previous design breaks collect_syscall.
> >
> > Move saving process to syscall entry to fix it.
> >
> > Reported-by: Xi Ruoyao <xry111@xry111.site>
> > Link: https://github.com/util-linux/util-linux/issues/2867
> > Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
> 
> Ping, this needs to be in fixes tree.

Just in case... I see nothing wrong, but I can't review this patch.
I know nothing about arch/mips/ so I can't really understand these
low-level changes.

Oleg.

> 
> Thanks
> 
> > ---
> >  arch/mips/include/asm/ptrace.h |  2 +-
> >  arch/mips/kernel/asm-offsets.c |  1 +
> >  arch/mips/kernel/ptrace.c      | 15 ++++++---------
> >  arch/mips/kernel/scall32-o32.S | 23 +++++++++++++----------
> >  arch/mips/kernel/scall64-n32.S |  3 ++-
> >  arch/mips/kernel/scall64-n64.S |  3 ++-
> >  arch/mips/kernel/scall64-o32.S | 33 +++++++++++++++++----------------
> >  7 files changed, 42 insertions(+), 38 deletions(-)
> >
> > diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
> > index d14d0e37ad02..4a2b40ce39e0 100644
> > --- a/arch/mips/include/asm/ptrace.h
> > +++ b/arch/mips/include/asm/ptrace.h
> > @@ -159,7 +159,7 @@ extern unsigned long exception_ip(struct pt_regs *regs);
> >  #define exception_ip(regs) exception_ip(regs)
> >  #define profile_pc(regs) instruction_pointer(regs)
> > 
> > -extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall);
> > +extern asmlinkage long syscall_trace_enter(struct pt_regs *regs);
> >  extern asmlinkage void syscall_trace_leave(struct pt_regs *regs);
> > 
> >  extern void die(const char *, struct pt_regs *) __noreturn;
> > diff --git a/arch/mips/kernel/asm-offsets.c 
> > b/arch/mips/kernel/asm-offsets.c
> > index d1b11f66f748..cb1045ebab06 100644
> > --- a/arch/mips/kernel/asm-offsets.c
> > +++ b/arch/mips/kernel/asm-offsets.c
> > @@ -101,6 +101,7 @@ void output_thread_info_defines(void)
> >  	OFFSET(TI_CPU, thread_info, cpu);
> >  	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
> >  	OFFSET(TI_REGS, thread_info, regs);
> > +	OFFSET(TI_SYSCALL, thread_info, syscall);
> >  	DEFINE(_THREAD_SIZE, THREAD_SIZE);
> >  	DEFINE(_THREAD_MASK, THREAD_MASK);
> >  	DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
> > diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
> > index 59288c13b581..61503a36067e 100644
> > --- a/arch/mips/kernel/ptrace.c
> > +++ b/arch/mips/kernel/ptrace.c
> > @@ -1317,16 +1317,13 @@ long arch_ptrace(struct task_struct *child, 
> > long request,
> >   * Notification of system call entry/exit
> >   * - triggered by current->work.syscall_trace
> >   */
> > -asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
> > +asmlinkage long syscall_trace_enter(struct pt_regs *regs)
> >  {
> >  	user_exit();
> > 
> > -	current_thread_info()->syscall = syscall;
> > -
> >  	if (test_thread_flag(TIF_SYSCALL_TRACE)) {
> >  		if (ptrace_report_syscall_entry(regs))
> >  			return -1;
> > -		syscall = current_thread_info()->syscall;
> >  	}
> > 
> >  #ifdef CONFIG_SECCOMP
> > @@ -1335,7 +1332,7 @@ asmlinkage long syscall_trace_enter(struct 
> > pt_regs *regs, long syscall)
> >  		struct seccomp_data sd;
> >  		unsigned long args[6];
> > 
> > -		sd.nr = syscall;
> > +		sd.nr = current_thread_info()->syscall;
> >  		sd.arch = syscall_get_arch(current);
> >  		syscall_get_arguments(current, regs, args);
> >  		for (i = 0; i < 6; i++)
> > @@ -1345,23 +1342,23 @@ asmlinkage long syscall_trace_enter(struct 
> > pt_regs *regs, long syscall)
> >  		ret = __secure_computing(&sd);
> >  		if (ret == -1)
> >  			return ret;
> > -		syscall = current_thread_info()->syscall;
> >  	}
> >  #endif
> > 
> >  	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
> >  		trace_sys_enter(regs, regs->regs[2]);
> > 
> > -	audit_syscall_entry(syscall, regs->regs[4], regs->regs[5],
> > +	audit_syscall_entry(current_thread_info()->syscall,
> > +			    regs->regs[4], regs->regs[5],
> >  			    regs->regs[6], regs->regs[7]);
> > 
> >  	/*
> >  	 * Negative syscall numbers are mistaken for rejected syscalls, but
> >  	 * won't have had the return value set appropriately, so we do so now.
> >  	 */
> > -	if (syscall < 0)
> > +	if (current_thread_info()->syscall < 0)
> >  		syscall_set_return_value(current, regs, -ENOSYS, 0);
> > -	return syscall;
> > +	return current_thread_info()->syscall;
> >  }
> > 
> >  /*
> > diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
> > index 18dc9b345056..2c604717e630 100644
> > --- a/arch/mips/kernel/scall32-o32.S
> > +++ b/arch/mips/kernel/scall32-o32.S
> > @@ -77,6 +77,18 @@ loads_done:
> >  	PTR_WD	load_a7, bad_stack_a7
> >  	.previous
> > 
> > +	/*
> > +	 * syscall number is in v0 unless we called syscall(__NR_###)
> > +	 * where the real syscall number is in a0
> > +	 */
> > +	subu	t2, v0,  __NR_O32_Linux
> > +	bnez	t2, 1f /* __NR_syscall at offset 0 */
> > +	LONG_S	a0, TI_SYSCALL($28)	# Save a0 as syscall number
> > +	b	2f
> > +1:
> > +	LONG_S	v0, TI_SYSCALL($28)	# Save v0 as syscall number
> > +2:
> > +
> >  	lw	t0, TI_FLAGS($28)	# syscall tracing enabled?
> >  	li	t1, _TIF_WORK_SYSCALL_ENTRY
> >  	and	t0, t1
> > @@ -114,16 +126,7 @@ syscall_trace_entry:
> >  	SAVE_STATIC
> >  	move	a0, sp
> > 
> > -	/*
> > -	 * syscall number is in v0 unless we called syscall(__NR_###)
> > -	 * where the real syscall number is in a0
> > -	 */
> > -	move	a1, v0
> > -	subu	t2, v0,  __NR_O32_Linux
> > -	bnez	t2, 1f /* __NR_syscall at offset 0 */
> > -	lw	a1, PT_R4(sp)
> > -
> > -1:	jal	syscall_trace_enter
> > +	jal	syscall_trace_enter
> > 
> >  	bltz	v0, 1f			# seccomp failed? Skip syscall
> > 
> > diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
> > index 97456b2ca7dc..97788859238c 100644
> > --- a/arch/mips/kernel/scall64-n32.S
> > +++ b/arch/mips/kernel/scall64-n32.S
> > @@ -44,6 +44,8 @@ NESTED(handle_sysn32, PT_SIZE, sp)
> > 
> >  	sd	a3, PT_R26(sp)		# save a3 for syscall restarting
> > 
> > +	LONG_S	v0, TI_SYSCALL($28)     # Store syscall number
> > +
> >  	li	t1, _TIF_WORK_SYSCALL_ENTRY
> >  	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
> >  	and	t0, t1, t0
> > @@ -72,7 +74,6 @@ syscall_common:
> >  n32_syscall_trace_entry:
> >  	SAVE_STATIC
> >  	move	a0, sp
> > -	move	a1, v0
> >  	jal	syscall_trace_enter
> > 
> >  	bltz	v0, 1f			# seccomp failed? Skip syscall
> > diff --git a/arch/mips/kernel/scall64-n64.S b/arch/mips/kernel/scall64-n64.S
> > index e6264aa62e45..be11ea5cc67e 100644
> > --- a/arch/mips/kernel/scall64-n64.S
> > +++ b/arch/mips/kernel/scall64-n64.S
> > @@ -46,6 +46,8 @@ NESTED(handle_sys64, PT_SIZE, sp)
> > 
> >  	sd	a3, PT_R26(sp)		# save a3 for syscall restarting
> > 
> > +	LONG_S	v0, TI_SYSCALL($28)     # Store syscall number
> > +
> >  	li	t1, _TIF_WORK_SYSCALL_ENTRY
> >  	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
> >  	and	t0, t1, t0
> > @@ -82,7 +84,6 @@ n64_syscall_exit:
> >  syscall_trace_entry:
> >  	SAVE_STATIC
> >  	move	a0, sp
> > -	move	a1, v0
> >  	jal	syscall_trace_enter
> > 
> >  	bltz	v0, 1f			# seccomp failed? Skip syscall
> > diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
> > index d3c2616cba22..7a5abb73e531 100644
> > --- a/arch/mips/kernel/scall64-o32.S
> > +++ b/arch/mips/kernel/scall64-o32.S
> > @@ -79,6 +79,22 @@ loads_done:
> >  	PTR_WD	load_a7, bad_stack_a7
> >  	.previous
> > 
> > +	/*
> > +	 * absolute syscall number is in v0 unless we called syscall(__NR_###)
> > +	 * where the real syscall number is in a0
> > +	 * note: NR_syscall is the first O32 syscall but the macro is
> > +	 * only defined when compiling with -mabi=32 (CONFIG_32BIT)
> > +	 * therefore __NR_O32_Linux is used (4000)
> > +	 */
> > +
> > +	subu	t2, v0,  __NR_O32_Linux
> > +	bnez	t2, 1f /* __NR_syscall at offset 0 */
> > +	LONG_S	a0, TI_SYSCALL($28)	# Save a0 as syscall number
> > +	b	2f
> > +1:
> > +	LONG_S	v0, TI_SYSCALL($28)	# Save v0 as syscall number
> > +2:
> > +
> >  	li	t1, _TIF_WORK_SYSCALL_ENTRY
> >  	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
> >  	and	t0, t1, t0
> > @@ -113,22 +129,7 @@ trace_a_syscall:
> >  	sd	a7, PT_R11(sp)		# For indirect syscalls
> > 
> >  	move	a0, sp
> > -	/*
> > -	 * absolute syscall number is in v0 unless we called syscall(__NR_###)
> > -	 * where the real syscall number is in a0
> > -	 * note: NR_syscall is the first O32 syscall but the macro is
> > -	 * only defined when compiling with -mabi=32 (CONFIG_32BIT)
> > -	 * therefore __NR_O32_Linux is used (4000)
> > -	 */
> > -	.set	push
> > -	.set	reorder
> > -	subu	t1, v0,  __NR_O32_Linux
> > -	move	a1, v0
> > -	bnez	t1, 1f /* __NR_syscall at offset 0 */
> > -	ld	a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
> > -	.set	pop
> > -
> > -1:	jal	syscall_trace_enter
> > +	jal	syscall_trace_enter
> > 
> >  	bltz	v0, 1f			# seccomp failed? Skip syscall
> > 
> >
> > ---
> > base-commit: a6bd6c9333397f5a0e2667d4d82fef8c970108f2
> > change-id: 20240328-mips_save_syscall-be471311cc9b
> >
> > Best regards,
> > -- 
> > Jiaxun Yang <jiaxun.yang@flygoat.com>
> 
> -- 
> - Jiaxun
>
Thomas Bogendoerfer April 9, 2024, 2:59 p.m. UTC | #3
On Thu, Mar 28, 2024 at 02:27:56PM +0000, Jiaxun Yang wrote:
> thread_info.syscall is used by syscall_get_nr to supply syscall nr
> over a thread stack frame.
> 
> Previously, thread_info.syscall is only saved at syscall_trace_enter
> when syscall tracing is enabled. However rest of the kernel code do
> expect syscall_get_nr to be available without syscall tracing. The
> previous design breaks collect_syscall.
> 
> Move saving process to syscall entry to fix it.
> 
> Reported-by: Xi Ruoyao <xry111@xry111.site>
> Link: https://github.com/util-linux/util-linux/issues/2867
> Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
> ---
>  arch/mips/include/asm/ptrace.h |  2 +-
>  arch/mips/kernel/asm-offsets.c |  1 +
>  arch/mips/kernel/ptrace.c      | 15 ++++++---------
>  arch/mips/kernel/scall32-o32.S | 23 +++++++++++++----------
>  arch/mips/kernel/scall64-n32.S |  3 ++-
>  arch/mips/kernel/scall64-n64.S |  3 ++-
>  arch/mips/kernel/scall64-o32.S | 33 +++++++++++++++++----------------
>  7 files changed, 42 insertions(+), 38 deletions(-)

applied to mips-fixes.

Thomas.
diff mbox series

Patch

diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index d14d0e37ad02..4a2b40ce39e0 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -159,7 +159,7 @@  extern unsigned long exception_ip(struct pt_regs *regs);
 #define exception_ip(regs) exception_ip(regs)
 #define profile_pc(regs) instruction_pointer(regs)
 
-extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall);
+extern asmlinkage long syscall_trace_enter(struct pt_regs *regs);
 extern asmlinkage void syscall_trace_leave(struct pt_regs *regs);
 
 extern void die(const char *, struct pt_regs *) __noreturn;
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index d1b11f66f748..cb1045ebab06 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -101,6 +101,7 @@  void output_thread_info_defines(void)
 	OFFSET(TI_CPU, thread_info, cpu);
 	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
 	OFFSET(TI_REGS, thread_info, regs);
+	OFFSET(TI_SYSCALL, thread_info, syscall);
 	DEFINE(_THREAD_SIZE, THREAD_SIZE);
 	DEFINE(_THREAD_MASK, THREAD_MASK);
 	DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 59288c13b581..61503a36067e 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -1317,16 +1317,13 @@  long arch_ptrace(struct task_struct *child, long request,
  * Notification of system call entry/exit
  * - triggered by current->work.syscall_trace
  */
-asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
+asmlinkage long syscall_trace_enter(struct pt_regs *regs)
 {
 	user_exit();
 
-	current_thread_info()->syscall = syscall;
-
 	if (test_thread_flag(TIF_SYSCALL_TRACE)) {
 		if (ptrace_report_syscall_entry(regs))
 			return -1;
-		syscall = current_thread_info()->syscall;
 	}
 
 #ifdef CONFIG_SECCOMP
@@ -1335,7 +1332,7 @@  asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
 		struct seccomp_data sd;
 		unsigned long args[6];
 
-		sd.nr = syscall;
+		sd.nr = current_thread_info()->syscall;
 		sd.arch = syscall_get_arch(current);
 		syscall_get_arguments(current, regs, args);
 		for (i = 0; i < 6; i++)
@@ -1345,23 +1342,23 @@  asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
 		ret = __secure_computing(&sd);
 		if (ret == -1)
 			return ret;
-		syscall = current_thread_info()->syscall;
 	}
 #endif
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->regs[2]);
 
-	audit_syscall_entry(syscall, regs->regs[4], regs->regs[5],
+	audit_syscall_entry(current_thread_info()->syscall,
+			    regs->regs[4], regs->regs[5],
 			    regs->regs[6], regs->regs[7]);
 
 	/*
 	 * Negative syscall numbers are mistaken for rejected syscalls, but
 	 * won't have had the return value set appropriately, so we do so now.
 	 */
-	if (syscall < 0)
+	if (current_thread_info()->syscall < 0)
 		syscall_set_return_value(current, regs, -ENOSYS, 0);
-	return syscall;
+	return current_thread_info()->syscall;
 }
 
 /*
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 18dc9b345056..2c604717e630 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -77,6 +77,18 @@  loads_done:
 	PTR_WD	load_a7, bad_stack_a7
 	.previous
 
+	/*
+	 * syscall number is in v0 unless we called syscall(__NR_###)
+	 * where the real syscall number is in a0
+	 */
+	subu	t2, v0,  __NR_O32_Linux
+	bnez	t2, 1f /* __NR_syscall at offset 0 */
+	LONG_S	a0, TI_SYSCALL($28)	# Save a0 as syscall number
+	b	2f
+1:
+	LONG_S	v0, TI_SYSCALL($28)	# Save v0 as syscall number
+2:
+
 	lw	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	and	t0, t1
@@ -114,16 +126,7 @@  syscall_trace_entry:
 	SAVE_STATIC
 	move	a0, sp
 
-	/*
-	 * syscall number is in v0 unless we called syscall(__NR_###)
-	 * where the real syscall number is in a0
-	 */
-	move	a1, v0
-	subu	t2, v0,  __NR_O32_Linux
-	bnez	t2, 1f /* __NR_syscall at offset 0 */
-	lw	a1, PT_R4(sp)
-
-1:	jal	syscall_trace_enter
+	jal	syscall_trace_enter
 
 	bltz	v0, 1f			# seccomp failed? Skip syscall
 
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 97456b2ca7dc..97788859238c 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -44,6 +44,8 @@  NESTED(handle_sysn32, PT_SIZE, sp)
 
 	sd	a3, PT_R26(sp)		# save a3 for syscall restarting
 
+	LONG_S	v0, TI_SYSCALL($28)     # Store syscall number
+
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	and	t0, t1, t0
@@ -72,7 +74,6 @@  syscall_common:
 n32_syscall_trace_entry:
 	SAVE_STATIC
 	move	a0, sp
-	move	a1, v0
 	jal	syscall_trace_enter
 
 	bltz	v0, 1f			# seccomp failed? Skip syscall
diff --git a/arch/mips/kernel/scall64-n64.S b/arch/mips/kernel/scall64-n64.S
index e6264aa62e45..be11ea5cc67e 100644
--- a/arch/mips/kernel/scall64-n64.S
+++ b/arch/mips/kernel/scall64-n64.S
@@ -46,6 +46,8 @@  NESTED(handle_sys64, PT_SIZE, sp)
 
 	sd	a3, PT_R26(sp)		# save a3 for syscall restarting
 
+	LONG_S	v0, TI_SYSCALL($28)     # Store syscall number
+
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	and	t0, t1, t0
@@ -82,7 +84,6 @@  n64_syscall_exit:
 syscall_trace_entry:
 	SAVE_STATIC
 	move	a0, sp
-	move	a1, v0
 	jal	syscall_trace_enter
 
 	bltz	v0, 1f			# seccomp failed? Skip syscall
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index d3c2616cba22..7a5abb73e531 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -79,6 +79,22 @@  loads_done:
 	PTR_WD	load_a7, bad_stack_a7
 	.previous
 
+	/*
+	 * absolute syscall number is in v0 unless we called syscall(__NR_###)
+	 * where the real syscall number is in a0
+	 * note: NR_syscall is the first O32 syscall but the macro is
+	 * only defined when compiling with -mabi=32 (CONFIG_32BIT)
+	 * therefore __NR_O32_Linux is used (4000)
+	 */
+
+	subu	t2, v0,  __NR_O32_Linux
+	bnez	t2, 1f /* __NR_syscall at offset 0 */
+	LONG_S	a0, TI_SYSCALL($28)	# Save a0 as syscall number
+	b	2f
+1:
+	LONG_S	v0, TI_SYSCALL($28)	# Save v0 as syscall number
+2:
+
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	and	t0, t1, t0
@@ -113,22 +129,7 @@  trace_a_syscall:
 	sd	a7, PT_R11(sp)		# For indirect syscalls
 
 	move	a0, sp
-	/*
-	 * absolute syscall number is in v0 unless we called syscall(__NR_###)
-	 * where the real syscall number is in a0
-	 * note: NR_syscall is the first O32 syscall but the macro is
-	 * only defined when compiling with -mabi=32 (CONFIG_32BIT)
-	 * therefore __NR_O32_Linux is used (4000)
-	 */
-	.set	push
-	.set	reorder
-	subu	t1, v0,  __NR_O32_Linux
-	move	a1, v0
-	bnez	t1, 1f /* __NR_syscall at offset 0 */
-	ld	a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
-	.set	pop
-
-1:	jal	syscall_trace_enter
+	jal	syscall_trace_enter
 
 	bltz	v0, 1f			# seccomp failed? Skip syscall