On Wed, Feb 05, 2020 at 10:19:22AM -0800, Yu-cheng Yu wrote:
> When a task does fork(), its Shadow Stack (SHSTK) must be duplicated for
> the child. This patch implements a flow similar to copy-on-write of an
> anonymous page, but for SHSTK.
>
> A SHSTK PTE must be RO and Dirty. This Dirty bit requirement is used to
> effect the copying. In copy_one_pte(), clear the Dirty bit from a SHSTK
> PTE to cause a page fault upon the next SHSTK access. At that time, fix
> the PTE and copy/re-use the page.
Just to confirm, during the fork, it's really not a SHSTK for a moment
(it's still RO, but not dirty). Can other racing threads muck this up,
or is this bit removed only on the copied side?
-Kees
>
> Signed-off-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
> ---
> arch/x86/mm/pgtable.c | 15 +++++++++++++++
> include/asm-generic/pgtable.h | 17 +++++++++++++++++
> mm/memory.c | 7 ++++++-
> 3 files changed, 38 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
> index 7bd2c3a52297..2eb33794c08d 100644
> --- a/arch/x86/mm/pgtable.c
> +++ b/arch/x86/mm/pgtable.c
> @@ -872,3 +872,18 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
>
> #endif /* CONFIG_X86_64 */
> #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
> +
> +#ifdef CONFIG_X86_INTEL_SHADOW_STACK_USER
> +inline bool arch_copy_pte_mapping(vm_flags_t vm_flags)
> +{
> + return (vm_flags & VM_SHSTK);
> +}
> +
> +inline pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma)
> +{
> + if (vma->vm_flags & VM_SHSTK)
> + return pte_mkdirty_shstk(pte);
> + else
> + return pte;
> +}
> +#endif /* CONFIG_X86_INTEL_SHADOW_STACK_USER */
> diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
> index 798ea36a0549..9cb2f9ba5895 100644
> --- a/include/asm-generic/pgtable.h
> +++ b/include/asm-generic/pgtable.h
> @@ -1190,6 +1190,23 @@ static inline bool arch_has_pfn_modify_check(void)
> }
> #endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */
>
> +#ifdef CONFIG_MMU
> +#ifndef CONFIG_ARCH_HAS_SHSTK
> +static inline bool arch_copy_pte_mapping(vm_flags_t vm_flags)
> +{
> + return false;
> +}
> +
> +static inline pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma)
> +{
> + return pte;
> +}
> +#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);
> +#endif
> +#endif /* CONFIG_MMU */
> +
> /*
> * Architecture PAGE_KERNEL_* fallbacks
> *
> diff --git a/mm/memory.c b/mm/memory.c
> index 45442d9a4f52..6daa28614327 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -772,7 +772,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
> * If it's a COW mapping, write protect it both
> * in the parent and the child
> */
> - if (is_cow_mapping(vm_flags) && pte_write(pte)) {
> + if ((is_cow_mapping(vm_flags) && pte_write(pte)) ||
> + arch_copy_pte_mapping(vm_flags)) {
> ptep_set_wrprotect(src_mm, addr, src_pte);
> pte = pte_wrprotect(pte);
> }
> @@ -2417,6 +2418,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
> flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
> entry = pte_mkyoung(vmf->orig_pte);
> entry = maybe_mkwrite(pte_mkdirty(entry), vma);
> + entry = pte_set_vma_features(entry, vma);
> if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1))
> update_mmu_cache(vma, vmf->address, vmf->pte);
> pte_unmap_unlock(vmf->pte, vmf->ptl);
> @@ -2504,6 +2506,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
> flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
> entry = mk_pte(new_page, vma->vm_page_prot);
> entry = maybe_mkwrite(pte_mkdirty(entry), vma);
> + entry = pte_set_vma_features(entry, vma);
> /*
> * Clear the pte entry and flush it first, before updating the
> * pte with the new entry. This will avoid a race condition
> @@ -3023,6 +3026,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> pte = mk_pte(page, vma->vm_page_prot);
> if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) {
> pte = maybe_mkwrite(pte_mkdirty(pte), vma);
> + pte = pte_set_vma_features(pte, vma);
> vmf->flags &= ~FAULT_FLAG_WRITE;
> ret |= VM_FAULT_WRITE;
> exclusive = RMAP_EXCLUSIVE;
> @@ -3165,6 +3169,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
> entry = mk_pte(page, vma->vm_page_prot);
> if (vma->vm_flags & VM_WRITE)
> entry = pte_mkwrite(pte_mkdirty(entry));
> + entry = pte_set_vma_features(entry, vma);
>
> vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
> &vmf->ptl);
> --
> 2.21.0
>
>
--
Kees Cook
