Re: [PATCH v10 08/15] x86/vsyscall: Reorganize the page fault emulation code

["Edgecombe, Rick P" <rick.p.edgecombe@intel.com>]

On Mon, 2025-10-06 at 23:51 -0700, Sohil Mehta wrote:
> Separate out the actual vsyscall emulation from the #PF specific
> handling in preparation for the upcoming #GP emulation.
> 
> No functional change intended.
> 
> Signed-off-by: Sohil Mehta <sohil.mehta@intel.com>
> Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
> ---
> v10:
>  - Modify the code flow slightly to make it easier to follow.
> ---
>  arch/x86/entry/vsyscall/vsyscall_64.c | 63 ++++++++++++++-------------
>  arch/x86/include/asm/vsyscall.h       |  7 ++-
>  arch/x86/mm/fault.c                   |  2 +-
>  3 files changed, 36 insertions(+), 36 deletions(-)
> 
> diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
> index 6e6c0a740837..4c3f49bf39e6 100644
> --- a/arch/x86/entry/vsyscall/vsyscall_64.c
> +++ b/arch/x86/entry/vsyscall/vsyscall_64.c
> @@ -112,43 +112,13 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size)
>  	}
>  }
>  
> -bool emulate_vsyscall(unsigned long error_code,
> -		      struct pt_regs *regs, unsigned long address)
> +static bool __emulate_vsyscall(struct pt_regs *regs, unsigned long address)
>  {
>  	unsigned long caller;
>  	int vsyscall_nr, syscall_nr, tmp;
>  	long ret;
>  	unsigned long orig_dx;
>  
> -	/* Write faults or kernel-privilege faults never get fixed up. */
> -	if ((error_code & (X86_PF_WRITE | X86_PF_USER)) != X86_PF_USER)
> -		return false;
> -
> -	/*
> -	 * Assume that faults at regs->ip are because of an
> -	 * instruction fetch. Return early and avoid
> -	 * emulation for faults during data accesses:
> -	 */
> -	if (address != regs->ip) {
> -		/* Failed vsyscall read */
> -		if (vsyscall_mode == EMULATE)
> -			return false;
> -
> -		/*
> -		 * User code tried and failed to read the vsyscall page.
> -		 */
> -		warn_bad_vsyscall(KERN_INFO, regs, "vsyscall read attempt denied -- look up the vsyscall kernel parameter if you need a workaround");
> -		return false;
> -	}
> -
> -	/*
> -	 * X86_PF_INSTR is only set when NX is supported.  When
> -	 * available, use it to double-check that the emulation code
> -	 * is only being used for instruction fetches:
> -	 */
> -	if (cpu_feature_enabled(X86_FEATURE_NX))
> -		WARN_ON_ONCE(!(error_code & X86_PF_INSTR));
> -
>  	/*
>  	 * No point in checking CS -- the only way to get here is a user mode
>  	 * trap to a high address, which means that we're in 64-bit user code.

I don't know. Is this as true any more? We are now sometimes guessing based on
regs->ip of a #GP. What if the kernel accidentally tries to jump to the vsyscall
address? Then we are reading the kernel stack and strange things. Maybe it's
worth replacing the comment with a check? Feel free to call this paranoid.


> @@ -281,6 +251,37 @@ bool emulate_vsyscall(unsigned long error_code,
>  	return true;
>  }
>  
> +bool emulate_vsyscall_pf(unsigned long error_code, struct pt_regs *regs,
> +			 unsigned long address)
> +{
> +	/* Write faults or kernel-privilege faults never get fixed up. */
> +	if ((error_code & (X86_PF_WRITE | X86_PF_USER)) != X86_PF_USER)
> +		return false;
> +
> +	/*
> +	 * Assume that faults at regs->ip are because of an instruction
> +	 * fetch. Return early and avoid emulation for faults during
> +	 * data accesses:
> +	 */
> +	if (address != regs->ip) {
> +		 /* User code tried and failed to read the vsyscall page. */
> +		if (vsyscall_mode != EMULATE)
> +			warn_bad_vsyscall(KERN_INFO, regs, "vsyscall read attempt denied -- look up the vsyscall kernel parameter if you need a workaround");
> +
> +		return false;
> +	}
> +
> +	/*
> +	 * X86_PF_INSTR is only set when NX is supported.  When
> +	 * available, use it to double-check that the emulation code
> +	 * is only being used for instruction fetches:
> +	 */
> +	if (cpu_feature_enabled(X86_FEATURE_NX))
> +		WARN_ON_ONCE(!(error_code & X86_PF_INSTR));
> +
> +	return __emulate_vsyscall(regs, address);
> +}
> +
>  /*
>   * A pseudo VMA to allow ptrace access for the vsyscall page.  This only
>   * covers the 64bit vsyscall page now. 32bit has a real VMA now and does
> diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
> index 472f0263dbc6..f34902364972 100644
> --- a/arch/x86/include/asm/vsyscall.h
> +++ b/arch/x86/include/asm/vsyscall.h
> @@ -14,12 +14,11 @@ extern void set_vsyscall_pgtable_user_bits(pgd_t *root);
>   * Called on instruction fetch fault in vsyscall page.
>   * Returns true if handled.
>   */
> -extern bool emulate_vsyscall(unsigned long error_code,
> -			     struct pt_regs *regs, unsigned long address);
> +bool emulate_vsyscall_pf(unsigned long error_code, struct pt_regs *regs, unsigned long address);
>  #else
>  static inline void map_vsyscall(void) {}
> -static inline bool emulate_vsyscall(unsigned long error_code,
> -				    struct pt_regs *regs, unsigned long address)
> +static inline bool emulate_vsyscall_pf(unsigned long error_code,
> +				       struct pt_regs *regs, unsigned long address)
>  {
>  	return false;
>  }
> diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
> index 998bd807fc7b..fbcc2da75fd6 100644
> --- a/arch/x86/mm/fault.c
> +++ b/arch/x86/mm/fault.c
> @@ -1316,7 +1316,7 @@ void do_user_addr_fault(struct pt_regs *regs,
>  	 * to consider the PF_PK bit.
>  	 */
>  	if (is_vsyscall_vaddr(address)) {
> -		if (emulate_vsyscall(error_code, regs, address))
> +		if (emulate_vsyscall_pf(error_code, regs, address))
>  			return;
>  	}
>  #endif