Re: [PATCH 5/6] KVM: MMU: prefetch ptes when intercepted guest #PF

[Avi Kivity]

On 06/15/2010 05:47 AM, Xiao Guangrong wrote:
> Support prefetch ptes when intercept guest #PF, avoid to #PF by later
> access
>
> If we meet any failure in the prefetch path, we will exit it and
> not try other ptes to avoid become heavy path
>
>
>
> +#define PTE_PREFETCH_NUM	16
> +
>   #define PT_FIRST_AVAIL_BITS_SHIFT 9
>   #define PT64_SECOND_AVAIL_BITS_SHIFT 52
>
> @@ -2041,6 +2043,39 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
>   {
>   }
>
> +static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
> +{
> +	struct kvm_mmu_page *sp;
> +	int index, i;
> +
> +	sp = page_header(__pa(sptep));
> +	WARN_ON(!sp->role.direct);
> +	index = sptep - sp->spt;
> +
> +	for (i = index + 1; i<  min(PT64_ENT_PER_PAGE,
> +				      index + PTE_PREFETCH_NUM); i++) {
> +		gfn_t gfn;
> +		pfn_t pfn;
> +		u64 *spte = sp->spt + i;
> +
> +		if (*spte != shadow_trap_nonpresent_pte)
> +			continue;
> +
> +		gfn = sp->gfn + (i<<  ((sp->role.level - 1) * PT64_LEVEL_BITS));
>    

Can calculate outside the loop and use +=.

Can this in fact work for level != PT_PAGE_TABLE_LEVEL?  We might start 
at PT_PAGE_DIRECTORY_LEVEL but get 4k pages while iterating.

> +
> +		pfn = gfn_to_pfn_atomic(vcpu->kvm, gfn);
> +		if (is_error_pfn(pfn)) {
> +			kvm_release_pfn_clean(pfn);
> +			break;
> +		}
> +		if (pte_prefetch_topup_memory_cache(vcpu))
> +			break;
> +
> +		mmu_set_spte(vcpu, spte, ACC_ALL, ACC_ALL, 0, 0, 1, NULL,
> +			     sp->role.level, gfn, pfn, true, false);
> +	}
> +}
>    

Nice.  Direct prefetch should usually succeed.

Can later augment to call get_users_pages_fast(..., PTE_PREFETCH_NUM, 
...) to reduce gup overhead.

> +static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, u64 *sptep)
> +{
> +	struct kvm_mmu_page *sp;
> +	pt_element_t *table = NULL;
> +	int offset = 0, shift, index, i;
> +
> +	sp = page_header(__pa(sptep));
> +	index = sptep - sp->spt;
> +
> +	if (PTTYPE == 32) {
> +		shift = PAGE_SHIFT - (PT_LEVEL_BITS -
> +					PT64_LEVEL_BITS) * sp->role.level;
> +		offset = sp->role.quadrant<<  shift;
> +	}
> +
> +	for (i = index + 1; i<  min(PT64_ENT_PER_PAGE,
> +				      index + PTE_PREFETCH_NUM); i++) {
> +		struct page *page;
> +		pt_element_t gpte;
> +		unsigned pte_access;
> +		u64 *spte = sp->spt + i;
> +		gfn_t gfn;
> +		pfn_t pfn;
> +		int dirty;
> +
> +		if (*spte != shadow_trap_nonpresent_pte)
> +			continue;
> +
> +		pte_access = sp->role.access;
> +		if (sp->role.direct) {
> +			dirty = 1;
> +			gfn = sp->gfn + (i<<  ((sp->role.level - 1) *
> +					      PT64_LEVEL_BITS));
> +			goto gfn_mapping;
> +		}
>    

Should just call direct_pte_prefetch.

> +
> +		if (!table) {
> +			page = gfn_to_page_atomic(vcpu->kvm, sp->gfn);
> +			if (is_error_page(page)) {
> +				kvm_release_page_clean(page);
> +				break;
> +			}
> +			table = kmap_atomic(page, KM_USER0);
> +			table = (pt_element_t *)((char *)table + offset);
> +		}
>    

Why not kvm_read_guest_atomic()?  Can do it outside the loop.

> +
> +		gpte = table[i];
> +		if (!(gpte&  PT_ACCESSED_MASK))
> +			continue;
> +
> +		if (!is_present_gpte(gpte)) {
> +			if (!sp->unsync)
> +				*spte = shadow_notrap_nonpresent_pte;
>    

Need __set_spte().

> +			continue;
> +		}
> +		dirty = is_dirty_gpte(gpte);
> +		gfn = (gpte&  PT64_BASE_ADDR_MASK)>>  PAGE_SHIFT;
> +		pte_access = pte_access&  FNAME(gpte_access)(vcpu, gpte);
> +gfn_mapping:
> +		pfn = gfn_to_pfn_atomic(vcpu->kvm, gfn);
> +		if (is_error_pfn(pfn)) {
> +			kvm_release_pfn_clean(pfn);
> +			break;
> +		}
> +
> +		if (pte_prefetch_topup_memory_cache(vcpu))
> +			break;
> +		mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
> +			     dirty, NULL, sp->role.level, gfn, pfn,
> +			     true, false);
> +	}
> +	if (table)
> +		kunmap_atomic((char *)table - offset, KM_USER0);
> +}
>    

I think lot of code can be shared with the pte prefetch in invlpg.

> +
>   /*
>    * Fetch a shadow pte for a specific level in the paging hierarchy.
>    */
> @@ -322,6 +397,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
>   				     is_dirty_gpte(gw->ptes[gw->level-1]),
>   				     ptwrite, level,
>   				     gw->gfn, pfn, false, true);
> +			FNAME(pte_prefetch)(vcpu, sptep);
>   			break;
>   		}
>
>    


--
error compiling committee.c: too many arguments to function

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/