Re: [PATCH 14/15] KVM: MTRR: do not map huage page for non-consistent range

[Paolo Bonzini <pbonzini@redhat.com>]

On 30/05/2015 12:59, Xiao Guangrong wrote:
> Currently guest MTRR is completely prohibited if cache snoop is supported on
> IOMMU (!noncoherent_dma) and host does the emulation based on the knowledge
> from host side, however, host side is not the good point to know
> what the purpose of guest is. A good example is that pass-throughed VGA
> frame buffer is not always UC as host expected

Can you explain how?  The original idea was that such a framebuffer
would be kvm_is_reserved_pfn and thus be unconditionally UC.

> +bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
> +					  int page_num)
> +{
> +	struct mtrr_looker looker;
> +	struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
> +	u64 start = gfn_to_gpa(gfn), end = gfn_to_gpa(gfn + page_num);
> +	int type = -1;
> +
> +	mtrr_for_each_mem_type(&looker, mtrr_state, start, end) {
> +		if (type == -1) {
> +			type = looker.mem_type;
> +			continue;
> +		}
> +
> +		if (type != looker.mem_type)
> +			return false;
> +	}
> +
> +	if ((type != -1) && looker.partial_map &&
> +	      (mtrr_state->def_type != type))
> +		return false;
> +

No Pascal-like parentheses.

Does this have a performance impact on shadow?  Perhaps we could cache
in struct kvm_arch_memory_slot whether the memslot is covered by MTRRs?

Paolo