Re: [PATCH] emulated cmpxchg8b should be atomic on i386

[Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>]

Marcelo Tosatti wrote:
> Emulate cmpxchg8b atomically on i386. This is required to avoid a guest
> pte walker from seeing a splitted write.
>
> Signed-off-by: Marcelo Tosatti <mtosatti-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
>
> diff --git a/drivers/kvm/x86.c b/drivers/kvm/x86.c
> index 9db4e32..d58d795 100644
> --- a/drivers/kvm/x86.c
> +++ b/drivers/kvm/x86.c
> @@ -1674,6 +1674,33 @@ static int emulator_cmpxchg_emulated(uns
>  		reported = 1;
>  		printk(KERN_WARNING "kvm: emulating exchange as write\n");
>  	}
> +#ifndef CONFIG_X86_64
> +	/* guests cmpxchg8b have to be emulated atomically */
> +	if (bytes == 8) {
> +		gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
> +		struct page *page;
> +		char *addr;
> +		u64 *val;
> +
> +		if (gpa == UNMAPPED_GVA ||
> +	    	   (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
> +			goto emul_write;
> +
> +		val = (u64 *)new;
> +		page = gfn_to_page(page, gpa >> PAGE_SHIFT);
> +		addr = kmap_atomic(page, KM_USER0);
> +		addr += offset_in_page(gpa);
> +
> +		set_64bit((unsigned long long *)addr, val);
> +
> +		kunmap_atomic(page, KM_USER0);
> +		kvm_release_page_dirty(page);
> +
> +		return X86EMUL_CONTINUE;
> +	}
> +#endif
> +
> +emul_write:
>  	return emulator_write_emulated(addr, new, bytes, vcpu);
>  }
>   

Won't the compiler complain when it sees an unreferenced label?

Also, we should handle the page boundary crossing case (probably by just 
emulating as a write and crosssing fingers).

-- 
Any sufficiently difficult bug is indistinguishable from a feature.


-------------------------------------------------------------------------
SF.Net email is sponsored by:
Check out the new SourceForge.net Marketplace.
It's the best place to buy or sell services for
just about anything Open Source.
http://sourceforge.net/services/buy/index.php