Re: [RFC] Question about TLB flush while set Stage-2 huge pages

[Zenghui Yu <yuzenghui@huawei.com>]

Hi Suzuki,

On 2019/3/19 1:34, Suzuki K Poulose wrote:
> Hi !
> On Sun, Mar 17, 2019 at 09:34:11PM +0800, Zenghui Yu wrote:
>> Hi Suzuki,
>>
>> ---8<---
>>
>> test: kvm: arm: Maybe two more fixes
>>
>> Applied based on Suzuki's patch.
>>
>> Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
>> ---
>>   virt/kvm/arm/mmu.c | 8 ++++++--
>>   1 file changed, 6 insertions(+), 2 deletions(-)
>>
>> diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
>> index 05765df..ccd5d5d 100644
>> --- a/virt/kvm/arm/mmu.c
>> +++ b/virt/kvm/arm/mmu.c
>> @@ -1089,7 +1089,9 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct
>> kvm_mmu_memory_cache
>>   		 * Normal THP split/merge follows mmu_notifier
>>   		 * callbacks and do get handled accordingly.
>>   		 */
>> -			unmap_stage2_range(kvm, (addr & S2_PMD_MASK), S2_PMD_SIZE);
>> +			addr &= S2_PMD_MASK;
>> +			unmap_stage2_ptes(kvm, pmd, addr, addr + S2_PMD_SIZE);
>> +			get_page(virt_to_page(pmd));
>>   		} else {
>>
>>   			/*
>> @@ -1138,7 +1140,9 @@ static int stage2_set_pud_huge(struct kvm *kvm, struct
>> kvm_mmu_memory_cache *cac
>>   	if (stage2_pud_present(kvm, old_pud)) {
>>   		/* If we have PTE level mapping, unmap the entire range */
>>   		if (WARN_ON_ONCE(!stage2_pud_huge(kvm, old_pud))) {
>> -			unmap_stage2_range(kvm, addr & S2_PUD_MASK, S2_PUD_SIZE);
>> +			addr &= S2_PUD_MASK;
>> +			unmap_stage2_pmds(kvm, pudp, addr, addr + S2_PUD_SIZE);
>> +			get_page(virt_to_page(pudp));
>>   		} else {
>>   			stage2_pud_clear(kvm, pudp);
>>   			kvm_tlb_flush_vmid_ipa(kvm, addr);
> 
> This makes it a bit tricky to follow the code. The other option is to
> do something like :

Yes.

> 
> 
> ---8>---
> 
> kvm: arm: Fix handling of stage2 huge mappings
> 
> We rely on the mmu_notifier call backs to handle the split/merging
> of huge pages and thus we are guaranteed that while creating a
> block mapping, the entire block is unmapped at stage2. However,
> we miss a case where the block mapping is split for dirty logging
> case and then could later be made block mapping, if we cancel the
> dirty logging. This not only creates inconsistent TLB entries for
> the pages in the the block, but also leakes the table pages for
> PMD level.
> 
> Handle these corner cases for the huge mappings at stage2 by
> unmapping the PTE level mapping. This could potentially release
> the upper level table. So we need to restart the table walk
> once we unmap the range.
> 
> Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
> ---
>   virt/kvm/arm/mmu.c | 57 +++++++++++++++++++++++++++++++++++++++---------------
>   1 file changed, 41 insertions(+), 16 deletions(-)
> 
> diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
> index fce0983..a38a3f1 100644
> --- a/virt/kvm/arm/mmu.c
> +++ b/virt/kvm/arm/mmu.c
> @@ -1060,25 +1060,41 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
>   {
>   	pmd_t *pmd, old_pmd;
>   
> +retry:
>   	pmd = stage2_get_pmd(kvm, cache, addr);
>   	VM_BUG_ON(!pmd);
>   
>   	old_pmd = *pmd;
> +	/*
> +	 * Multiple vcpus faulting on the same PMD entry, can
> +	 * lead to them sequentially updating the PMD with the
> +	 * same value. Following the break-before-make
> +	 * (pmd_clear() followed by tlb_flush()) process can
> +	 * hinder forward progress due to refaults generated
> +	 * on missing translations.
> +	 *
> +	 * Skip updating the page table if the entry is
> +	 * unchanged.
> +	 */
> +	if (pmd_val(old_pmd) == pmd_val(*new_pmd))
> +		return 0;
> +
>   	if (pmd_present(old_pmd)) {
>   		/*
> -		 * Multiple vcpus faulting on the same PMD entry, can
> -		 * lead to them sequentially updating the PMD with the
> -		 * same value. Following the break-before-make
> -		 * (pmd_clear() followed by tlb_flush()) process can
> -		 * hinder forward progress due to refaults generated
> -		 * on missing translations.
> -		 *
> -		 * Skip updating the page table if the entry is
> -		 * unchanged.
> +		 * If we already have PTE level mapping for this block,
> +		 * we must unmap it to avoid inconsistent TLB
> +		 * state. We could end up in this situation if
> +		 * the memory slot was marked for dirty logging
> +		 * and was reverted, leaving PTE level mappings
> +		 * for the pages accessed during the period.
> +		 * Normal THP split/merge follows mmu_notifier
> +		 * callbacks and do get handled accordingly.
> +		 * Unmap the PTE level mapping and retry.
>   		 */
> -		if (pmd_val(old_pmd) == pmd_val(*new_pmd))
> -			return 0;
> -
> +		if (!pmd_thp_or_huge(old_pmd)) {
> +			unmap_stage2_range(kvm, (addr & S2_PMD_MASK), S2_PMD_SIZE);
Nit: we can get rid of the parentheses around "addr & S2_PMD_MASK" to
make it looks the same as PUD level (but it is not necessary).
> +			goto retry;
> +		}
>   		/*
>   		 * Mapping in huge pages should only happen through a
>   		 * fault.  If a page is merged into a transparent huge
> @@ -1090,8 +1106,7 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
>   		 * should become splitting first, unmapped, merged,
>   		 * and mapped back in on-demand.
>   		 */
> -		VM_BUG_ON(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));
> -
> +		WARN_ON_ONCE(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));
>   		pmd_clear(pmd);
>   		kvm_tlb_flush_vmid_ipa(kvm, addr);
>   	} else {
> @@ -1107,6 +1122,7 @@ static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cac
>   {
>   	pud_t *pudp, old_pud;
>   
> +retry:
>   	pudp = stage2_get_pud(kvm, cache, addr);
>   	VM_BUG_ON(!pudp);
>   
> @@ -1122,8 +1138,17 @@ static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cac
>   		return 0;
>   
>   	if (stage2_pud_present(kvm, old_pud)) {
> -		stage2_pud_clear(kvm, pudp);
> -		kvm_tlb_flush_vmid_ipa(kvm, addr);
> +		/*
> +		 * If we already have PTE level mapping, unmap the entire
> +		 * range and retry.
> +		 */
> +		if (!stage2_pud_huge(kvm, old_pud)) {
> +			unmap_stage2_range(kvm, addr & S2_PUD_MASK, S2_PUD_SIZE);
> +			goto retry;
> +		} else {
> +			stage2_pud_clear(kvm, pudp);
> +			kvm_tlb_flush_vmid_ipa(kvm, addr);
> +		}
>   	} else {
>   		get_page(virt_to_page(pudp));
>   	}
> 

It look much better, and works fine now!


thanks,

zenghui