Re: [RFC PATCH v2 16/27] mm: Modify can_follow_write_pte/pmd for shadow stack

[Dave Hansen]

On 07/17/2018 04:03 PM, Yu-cheng Yu wrote:
> On Fri, 2018-07-13 at 11:26 -0700, Dave Hansen wrote:
>> On 07/11/2018 10:05 AM, Yu-cheng Yu wrote:
>>>
>>> My understanding is that we don't want to follow write pte if the page
>>> is shared as read-only. ÂFor a SHSTK page, that is (R/O + DIRTY_SW),
>>> which means the SHSTK page has not been COW'ed. ÂIs that right?
>> Let's look at the code again:
>>
>>>
>>> -static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
>>> +static inline bool can_follow_write_pte(pte_t pte, unsigned int flags,
>>> +					bool shstk)
>>> Â{
>>> +	bool pte_cowed = shstk ? is_shstk_pte(pte):pte_dirty(pte);
>>> +
>>> Â	return pte_write(pte) ||
>>> -		((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
>>> +		((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_cowed);
>>> Â}
>> This is another case where the naming of pte_*() is biting us vs. the
>> perversion of the PTE bits.ÂÂThe lack of comments and explanation inthe
>> patch is compounding the confusion.
>>
>> We need to find a way to differentiate "someone can write to this PTE"
>> from "the write bit is set in this PTE".
>>
>> In this particular hunk, we need to make it clear that pte_write() is
>> *never* true for shadowstack PTEs.ÂÂIn other words, shadow stack VMAs
>> will (should?) never even *see* a pte_write() PTE.
>>
>> I think this is a case where you just need to bite the bullet and
>> bifurcate can_follow_write_pte().ÂÂJust separate the shadowstack and
>> non-shadowstack parts.
> 
> In case I don't understand the exact issue.
> What about the following.
> 
> diff --git a/mm/gup.c b/mm/gup.c
> index fc5f98069f4e..45a0837b27f9 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -70,6 +70,12 @@ static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
> Â		((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
> Â}
> Â
> +static inline bool can_follow_write_shstk_pte(pte_t pte, unsigned int flags)
> +{
> +	return ((flags & FOLL_FORCE) && (flags & FOLL_COW) &&
> +		is_shstk_pte(pte));
> +}
> +
> Âstatic struct page *follow_page_pte(struct vm_area_struct *vma,
> Â		unsigned long address, pmd_t *pmd, unsigned int flags)
> Â{
> @@ -105,9 +111,16 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
> Â	}
> Â	if ((flags & FOLL_NUMA) && pte_protnone(pte))
> Â		goto no_page;
> -	if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) {
> -		pte_unmap_unlock(ptep, ptl);
> -		return NULL;
> +	if (flags & FOLL_WRITE) {
> +		if (is_shstk_mapping(vma->vm_flags)) {
> +			if (!can_follow_write_shstk_pte(pte, flags)) {
> +				pte_unmap_unlock(ptep, ptl);
> +				return NULL;
> +			}
> +		} else if (!can_follow_write_pte(pte, flags) {
> +			pte_unmap_unlock(ptep, ptl);
> +			return NULL;
> +		}

That looks pretty horrible. :(

We need:

bool can_follow_write(vma, pte_t pte, unsigned int flags)
{
	if (!is_shstk_mapping(vma->vm_flags)) {
		// vanilla case here		
	} else {
		// shadowstack case here
	}
}