Re: [PATCH v3 1/3] entry: Add some arch funcs to support arm64 to use generic entry

[Jinjie Ruan <ruanjinjie@huawei.com>]

On 2024/8/20 19:41, Kevin Brodsky wrote:
> On 29/06/2024 10:55, Jinjie Ruan wrote:
>> Add some arch functions to support arm64 to use generic entry, which do not
>> affect existing architectures that use generic entry:
>>
>>  - arch_prepare/post_report_syscall_entry/exit().
>>
>>  - arch_enter_from_kernel_mode(), arch_exit_to_kernel_mode_prepare().
>>
>>  - arch_irqentry_exit_need_resched() to support architecture-related
>>    need_resched() check logic.
>>
>> Also make syscall_exit_work() not static and move report_single_step() to
>> thread_info.h, which can be used by arm64 later.
>>
>> x86 and Riscv compilation test ok after this patch.
>>
>> Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
>> Suggested-by: Thomas Gleixner <tglx@linutronix.de>
>> ---
>> v3:
>> - Make the arch funcs not use __weak as Thomas suggested.
>> - Make arch_forget_syscall() folded in arch_post_report_syscall_entry().
>> - __always_inline -> inline.
>> - Move report_single_step() to thread_info.h for arm64
>> - Add Suggested-by.
>> - Update the commit message.
>>
>> v2:
>> - Fix a bug that not call arch_post_report_syscall_entry() in
>>   syscall_trace_enter() if ptrace_report_syscall_entry() return not zero.
>> - Update the commit message.
>> ---
>>  include/linux/entry-common.h | 90 ++++++++++++++++++++++++++++++++++++
>>  include/linux/thread_info.h  | 13 ++++++
>>  kernel/entry/common.c        | 37 +++++++--------
>>  3 files changed, 122 insertions(+), 18 deletions(-)
>>
>> diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
>> index b0fb775a600d..2aea23ca9d66 100644
>> --- a/include/linux/entry-common.h
>> +++ b/include/linux/entry-common.h
>> @@ -290,6 +290,94 @@ static __always_inline void arch_exit_to_user_mode(void);
>>  static __always_inline void arch_exit_to_user_mode(void) { }
>>  #endif
>>  
>> +/**
>> + * arch_enter_from_kernel_mode - Architecture specific check work.
> 
> Maybe those comments could be expanded to be closer to the existing
> ones, like arch_enter_from_user_mode()? It would help if they were more
> specific as to where they are called (especially the *report_syscall*
> ones) and how they are expected to be used.

You are right! It needed to be expanded.

> 
>> + */
>> +static inline void arch_enter_from_kernel_mode(struct pt_regs *regs);
>> +
>> +#ifndef arch_enter_from_kernel_mode
>> +static inline void arch_enter_from_kernel_mode(struct pt_regs *regs) { }
>> +#endif
>> +
>> +/**
>> + * arch_exit_to_kernel_mode_prepare - Architecture specific final work before
>> + *				      exit to kernel mode.
>> + */
>> +static inline void arch_exit_to_kernel_mode_prepare(struct pt_regs *regs);
> 
> Any reason to suffix this function with "prepare"? Just
> arch_exit_to_kernel_mode() seems appropriate (symmetric with
> arch_enter_from_kernel_mode()).

prepare means it is the first function before all other exit_to_kernel
operation in irqentry_exit(), but as the order problem, it can be
adjusted to the last to aligh with the older arm64 version.

> 
>> +
>> +#ifndef arch_exit_to_kernel_mode_prepare
>> +static inline void arch_exit_to_kernel_mode_prepare(struct pt_regs *regs) { }
>> +#endif
>> +
>> +/**
>> + * arch_prepare_report_syscall_entry - Architecture specific work before
>> + *			               report_syscall_entry().
>> + */
>> +static inline unsigned long arch_prepare_report_syscall_entry(struct pt_regs *regs);
> 
> The most common naming patterns for such arch helper pairs seems to be
> pre/post, so maybe arch_pre_report_syscall_entry()?

Right!

> 
>> +
>> +#ifndef arch_prepare_report_syscall_entry
>> +static inline unsigned long arch_prepare_report_syscall_entry(struct pt_regs *regs)
>> +{
>> +	return 0;
>> +}
>> +#endif
>> +
>> +/**
>> + * arch_post_report_syscall_entry - Architecture specific work after
>> + *			            report_syscall_entry().
>> + */
>> +static inline void arch_post_report_syscall_entry(struct pt_regs *regs,
>> +						  unsigned long saved_reg,
>> +						  long ret);
>> +
>> +#ifndef arch_post_report_syscall_entry
>> +static inline void arch_post_report_syscall_entry(struct pt_regs *regs,
>> +						  unsigned long saved_reg,
>> +						  long ret)
>> +{
>> +}
>> +#endif
>> +
>> +/**
>> + * arch_prepare_report_syscall_exit - Architecture specific work before
>> + *			              report_syscall_exit().
>> + */
>> +static inline unsigned long arch_prepare_report_syscall_exit(struct pt_regs *regs,
>> +							     unsigned long work);
>> +
>> +#ifndef arch_prepare_report_syscall_exit
>> +static inline unsigned long arch_prepare_report_syscall_exit(struct pt_regs *regs,
>> +							     unsigned long work)
>> +{
>> +	return 0;
>> +}
>> +#endif
>> +
>> +/**
>> + * arch_post_report_syscall_exit - Architecture specific work after
>> + *			           report_syscall_exit().
>> + */
>> +static inline void arch_post_report_syscall_exit(struct pt_regs *regs,
>> +						 unsigned long saved_reg,
>> +						 unsigned long work);
>> +
>> +#ifndef arch_post_report_syscall_exit
>> +static inline void arch_post_report_syscall_exit(struct pt_regs *regs,
>> +						 unsigned long saved_reg,
>> +						 unsigned long work)
>> +{
>> +}
>> +#endif
>> +
>> +/**
>> + * arch_irqentry_exit_need_resched - Architecture specific need resched function
>> + */
>> +static inline bool arch_irqentry_exit_need_resched(void);
>> +
>> +#ifndef arch_irqentry_exit_need_resched
>> +static inline bool arch_irqentry_exit_need_resched(void) { return true; }
>> +#endif
> 
> Nit: the existing arch_* hooks seem to be declared close to the function
> they are called from (e.g. arch_enter_from_user_mode() just before
> enter_from_user_mode()), maybe we could do the same with those new
> hooks, where possible.

Yes, do the same with those new hooks will be nice.

> 
>> +
>>  /**
>>   * arch_do_signal_or_restart -  Architecture specific signal delivery function
>>   * @regs:	Pointer to currents pt_regs
>> @@ -552,4 +640,6 @@ irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs);
>>   */
>>  void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state);
>>  
>> +void syscall_exit_work(struct pt_regs *regs, unsigned long work);
>> +
>>  #endif
>> diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
>> index 9ea0b28068f4..062de9666ef3 100644
>> --- a/include/linux/thread_info.h
>> +++ b/include/linux/thread_info.h
>> @@ -55,6 +55,19 @@ enum syscall_work_bit {
>>  #define SYSCALL_WORK_SYSCALL_AUDIT	BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT)
>>  #define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH)
>>  #define SYSCALL_WORK_SYSCALL_EXIT_TRAP	BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP)
>> +
>> +/*
>> + * If SYSCALL_EMU is set, then the only reason to report is when
>> + * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
>> + * instruction has been already reported in syscall_enter_from_user_mode().
>> + */
>> +static inline bool report_single_step(unsigned long work)
>> +{
>> +	if (work & SYSCALL_WORK_SYSCALL_EMU)
>> +		return false;
>> +
>> +	return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
>> +}
>>  #endif
>>  
>>  #include <asm/thread_info.h>
>> diff --git a/kernel/entry/common.c b/kernel/entry/common.c
>> index 90843cc38588..cd76391ffcb9 100644
>> --- a/kernel/entry/common.c
>> +++ b/kernel/entry/common.c
>> @@ -28,6 +28,7 @@ static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
>>  long syscall_trace_enter(struct pt_regs *regs, long syscall,
>>  				unsigned long work)
>>  {
>> +	unsigned long saved_reg;
> 
> Nit: could be declared inside the if block.

Right!

> 
> Kevin
> 
>>  	long ret = 0;
>>  
>>  	/*
>> @@ -42,8 +43,10 @@ long syscall_trace_enter(struct pt_regs *regs, long syscall,
>>  
>>  	/* Handle ptrace */
>>  	if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
>> +		saved_reg = arch_prepare_report_syscall_entry(regs);
>>  		ret = ptrace_report_syscall_entry(regs);
>> -		if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
>> +		arch_post_report_syscall_entry(regs, saved_reg, ret);
>> +		if (ret || work & SYSCALL_WORK_SYSCALL_EMU)
>>  			return -1L;
>>  	}
>>  
>> [...]
>