Re: [PATCH v3 04/22] x86/doublefault: Make memmove() notrace/NOKPROBE

[Peter Zijlstra]

On Thu, Feb 20, 2020 at 01:17:27PM +0100, Borislav Petkov wrote:
> On Wed, Feb 19, 2020 at 04:57:15PM +0100, Peter Zijlstra wrote:
> > -		memmove(&gpregs->ip, (void *)regs->sp, 5*8);
> > +		for (i = 0; i < count; i++) {
> > +			int idx = (dst <= src) ? i : count - i;
> > +			dst[idx] = src[idx];
> > +		}
> 
> Or, you can actually unroll it. This way it even documents clearly what
> it does:
> 
> diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
> index fe38015ed50a..2b790a574ba5 100644
> --- a/arch/x86/kernel/traps.c
> +++ b/arch/x86/kernel/traps.c
> @@ -298,6 +298,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign
>  		regs->ip == (unsigned long)native_irq_return_iret)
>  	{
>  		struct pt_regs *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
> +		unsigned long *p = (unsigned long *)regs->sp;
>  
>  		/*
>  		 * regs->sp points to the failing IRET frame on the
> @@ -305,7 +306,11 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign
>  		 * in gpregs->ss through gpregs->ip.
>  		 *
>  		 */
> -		memmove(&gpregs->ip, (void *)regs->sp, 5*8);
> +		gpregs->ip	= *p;
> +		gpregs->cs	= *(p + 1);
> +		gpregs->flags	= *(p + 2);
> +		gpregs->sp	= *(p + 3);
> +		gpregs->ss	= *(p + 4);
>  		gpregs->orig_ax = 0;  /* Missing (lost) #GP error code */
>  
>  		/*

While I love that; is that actually correct? This is an unroll of
memcpy() not memmove(). IFF the ranges overlap, the above is buggered.

Was the original memmove() really needed?