Re: [RFC PATCH v9 15/27] mm: Handle THP/HugeTLB Shadow Stack page fault

[Kees Cook]

On Wed, Feb 05, 2020 at 10:19:23AM -0800, Yu-cheng Yu wrote:
> This patch implements THP Shadow Stack (SHSTK) copying in the same way as
> in the previous patch for regular PTE.
> 
> In copy_huge_pmd(), clear the dirty bit from the PMD to cause a page fault
> upon the next SHSTK access to the PMD.  At that time, fix the PMD and
> copy/re-use the page.

Now is as good a time as any to ask: do you have selftests for all this?
It seems like it would be really nice to have a way to verify SHSTK is
working correctly.

-Kees

> 
> Signed-off-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
> ---
>  arch/x86/mm/pgtable.c         |  8 ++++++++
>  include/asm-generic/pgtable.h | 11 +++++++++++
>  mm/huge_memory.c              |  4 ++++
>  3 files changed, 23 insertions(+)
> 
> diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
> index 2eb33794c08d..3340b1d4e9da 100644
> --- a/arch/x86/mm/pgtable.c
> +++ b/arch/x86/mm/pgtable.c
> @@ -886,4 +886,12 @@ inline pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma)
>  	else
>  		return pte;
>  }
> +
> +inline pmd_t pmd_set_vma_features(pmd_t pmd, struct vm_area_struct *vma)
> +{
> +	if (vma->vm_flags & VM_SHSTK)
> +		return pmd_mkdirty_shstk(pmd);
> +	else
> +		return pmd;
> +}
>  #endif /* CONFIG_X86_INTEL_SHADOW_STACK_USER */
> diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
> index 9cb2f9ba5895..a9df093fdf45 100644
> --- a/include/asm-generic/pgtable.h
> +++ b/include/asm-generic/pgtable.h
> @@ -1201,9 +1201,20 @@ static inline pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma)
>  {
>  	return pte;
>  }
> +
> +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> +static inline pmd_t pmd_set_vma_features(pmd_t pmd, struct vm_area_struct *vma)
> +{
> +	return pmd;
> +}
> +#endif
>  #else
>  bool arch_copy_pte_mapping(vm_flags_t vm_flags);
>  pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma);
> +
> +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> +pmd_t pmd_set_vma_features(pmd_t pmd, struct vm_area_struct *vma);
> +#endif
>  #endif
>  #endif /* CONFIG_MMU */
>  
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index a88093213674..93ef368df2dd 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -636,6 +636,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
>  
>  		entry = mk_huge_pmd(page, vma->vm_page_prot);
>  		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
> +		entry = pmd_set_vma_features(entry, vma);
>  		page_add_new_anon_rmap(page, vma, haddr, true);
>  		mem_cgroup_commit_charge(page, memcg, false, true);
>  		lru_cache_add_active_or_unevictable(page, vma);
> @@ -1278,6 +1279,7 @@ static vm_fault_t do_huge_pmd_wp_page_fallback(struct vm_fault *vmf,
>  		pte_t entry;
>  		entry = mk_pte(pages[i], vma->vm_page_prot);
>  		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
> +		entry = pte_set_vma_features(entry, vma);
>  		memcg = (void *)page_private(pages[i]);
>  		set_page_private(pages[i], 0);
>  		page_add_new_anon_rmap(pages[i], vmf->vma, haddr, false);
> @@ -1360,6 +1362,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
>  		pmd_t entry;
>  		entry = pmd_mkyoung(orig_pmd);
>  		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
> +		entry = pmd_set_vma_features(entry, vma);
>  		if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry,  1))
>  			update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
>  		ret |= VM_FAULT_WRITE;
> @@ -1432,6 +1435,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
>  		pmd_t entry;
>  		entry = mk_huge_pmd(new_page, vma->vm_page_prot);
>  		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
> +		entry = pmd_set_vma_features(entry, vma);
>  		pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd);
>  		page_add_new_anon_rmap(new_page, vma, haddr, true);
>  		mem_cgroup_commit_charge(new_page, memcg, false, true);
> -- 
> 2.21.0
> 

-- 
Kees Cook