From mboxrd@z Thu Jan 1 00:00:00 1970 From: Yu-cheng Yu Subject: [PATCH v10 18/26] mm: Update can_follow_write_pte() for shadow stack Date: Wed, 29 Apr 2020 15:07:24 -0700 Message-ID: <20200429220732.31602-19-yu-cheng.yu@intel.com> References: <20200429220732.31602-1-yu-cheng.yu@intel.com> Mime-Version: 1.0 Content-Transfer-Encoding: 8bit Return-path: In-Reply-To: <20200429220732.31602-1-yu-cheng.yu-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org> Sender: linux-api-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: x86-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org, "H. Peter Anvin" , Thomas Gleixner , Ingo Molnar , linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-doc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org, linux-arch-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Arnd Bergmann , Andy Lutomirski , Balbir Singh , Borislav Petkov , Cyrill Gorcunov , Dave Hansen , Eugene Syromiatnikov , Florian Weimer , "H.J. Lu" , Jann Horn , Jonathan Corbet , Kees Cook , Mike Kravetz , Nadav Amit Cc: Yu-cheng Yu List-Id: linux-arch.vger.kernel.org Can_follow_write_pte() ensures a read-only page is COWed by checking the FOLL_COW flag, and uses pte_dirty() to validate the flag is still valid. Like a writable data page, a shadow stack page is writable, and becomes read-only during copy-on-write, but it is always dirty. Thus, in the can_follow_write_pte() check, it belongs to the writable page case and should be excluded from the read-only page pte_dirty() check. Apply the same changes to can_follow_write_pmd(). Signed-off-by: Yu-cheng Yu --- v10: - Reverse name changes to can_follow_write_*(). mm/gup.c | 8 +++++--- mm/huge_memory.c | 8 +++++--- 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/mm/gup.c b/mm/gup.c index 50681f0286de..c737782403ee 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -385,10 +385,12 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, * FOLL_FORCE can write to even unwritable pte's, but only * after we've gone through a COW cycle and they are dirty. */ -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, + struct vm_area_struct *vma) { return pte_write(pte) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && + !arch_shadow_stack_mapping(vma->vm_flags) && pte_dirty(pte)); } static struct page *follow_page_pte(struct vm_area_struct *vma, @@ -431,7 +433,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, } if ((flags & FOLL_NUMA) && pte_protnone(pte)) goto no_page; - if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) { + if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags, vma)) { pte_unmap_unlock(ptep, ptl); return NULL; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 608746bb9d19..cb1b0cb4b4eb 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1520,10 +1520,12 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) * FOLL_FORCE can write to even unwritable pmd's, but only * after we've gone through a COW cycle and they are dirty. */ -static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) +static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags, + struct vm_area_struct *vma) { return pmd_write(pmd) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && + !arch_shadow_stack_mapping(vma->vm_flags) && pmd_dirty(pmd)); } struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, @@ -1536,7 +1538,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, assert_spin_locked(pmd_lockptr(mm, pmd)); - if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags)) + if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags, vma)) goto out; /* Avoid dumping huge zero page */ -- 2.21.0 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: From: Yu-cheng Yu Subject: [PATCH v10 18/26] mm: Update can_follow_write_pte() for shadow stack Date: Wed, 29 Apr 2020 15:07:24 -0700 Message-ID: <20200429220732.31602-19-yu-cheng.yu@intel.com> In-Reply-To: <20200429220732.31602-1-yu-cheng.yu@intel.com> References: <20200429220732.31602-1-yu-cheng.yu@intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Sender: owner-linux-mm@kvack.org To: x86@kernel.org, "H. Peter Anvin" , Thomas Gleixner , Ingo Molnar , linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org, linux-mm@kvack.org, linux-arch@vger.kernel.org, linux-api@vger.kernel.org, Arnd Bergmann , Andy Lutomirski , Balbir Singh , Borislav Petkov , Cyrill Gorcunov , Dave Hansen , Eugene Syromiatnikov , Florian Weimer , "H.J. Lu" , Jann Horn , Jonathan Corbet , Kees Cook , Mike Kravetz , Nadav Amit , Oleg Nesterov , Pavel Machek , Peter Zijlstra , Randy Dunlap , "Ravi V. Shankar" , Vedvyas Shanbhogue , Dave Martin , Weijiang Yang Cc: Yu-cheng Yu List-ID: Message-ID: <20200429220724.CXl3txLNpBYXgpL81DM95FMQodHpodzopAnm_sysz3c@z> Can_follow_write_pte() ensures a read-only page is COWed by checking the FOLL_COW flag, and uses pte_dirty() to validate the flag is still valid. Like a writable data page, a shadow stack page is writable, and becomes read-only during copy-on-write, but it is always dirty. Thus, in the can_follow_write_pte() check, it belongs to the writable page case and should be excluded from the read-only page pte_dirty() check. Apply the same changes to can_follow_write_pmd(). Signed-off-by: Yu-cheng Yu --- v10: - Reverse name changes to can_follow_write_*(). mm/gup.c | 8 +++++--- mm/huge_memory.c | 8 +++++--- 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/mm/gup.c b/mm/gup.c index 50681f0286de..c737782403ee 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -385,10 +385,12 @@ static int follow_pfn_pte(struct vm_area_struct *vm= a, unsigned long address, * FOLL_FORCE can write to even unwritable pte's, but only * after we've gone through a COW cycle and they are dirty. */ -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, + struct vm_area_struct *vma) { return pte_write(pte) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && + !arch_shadow_stack_mapping(vma->vm_flags) && pte_dirty(pte)); } =20 static struct page *follow_page_pte(struct vm_area_struct *vma, @@ -431,7 +433,7 @@ static struct page *follow_page_pte(struct vm_area_st= ruct *vma, } if ((flags & FOLL_NUMA) && pte_protnone(pte)) goto no_page; - if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) { + if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags, vma)) { pte_unmap_unlock(ptep, ptl); return NULL; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 608746bb9d19..cb1b0cb4b4eb 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1520,10 +1520,12 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *v= mf, pmd_t orig_pmd) * FOLL_FORCE can write to even unwritable pmd's, but only * after we've gone through a COW cycle and they are dirty. */ -static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) +static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags, + struct vm_area_struct *vma) { return pmd_write(pmd) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && + !arch_shadow_stack_mapping(vma->vm_flags) && pmd_dirty(pmd)); } =20 struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, @@ -1536,7 +1538,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_s= truct *vma, =20 assert_spin_locked(pmd_lockptr(mm, pmd)); =20 - if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags)) + if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags, vma)) goto out; =20 /* Avoid dumping huge zero page */ --=20 2.21.0