From mboxrd@z Thu Jan 1 00:00:00 1970 From: Yu-cheng Yu Subject: [PATCH v5 18/27] mm: Update can_follow_write_pte/pmd for shadow stack Date: Thu, 11 Oct 2018 08:15:14 -0700 Message-ID: <20181011151523.27101-19-yu-cheng.yu@intel.com> References: <20181011151523.27101-1-yu-cheng.yu@intel.com> Return-path: In-Reply-To: <20181011151523.27101-1-yu-cheng.yu@intel.com> Sender: linux-kernel-owner@vger.kernel.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 , Cyrill Gorcunov , Dave Hansen , Eugene Syromiatnikov , Florian Weimer , "H.J. Lu" , Jann Horn , Jonathan Corbet , Kees Cook , Mike Kravetz , Nadav Amit , Oleg Nesterov , Pa Cc: Yu-cheng Yu List-Id: linux-arch.vger.kernel.org can_follow_write_pte/pmd look for the (RO & DIRTY) PTE/PMD to verify an exclusive RO page still exists after a broken COW. A shadow stack PTE is RO & PAGE_DIRTY_SW when it is shared, otherwise RO & PAGE_DIRTY_HW. Introduce pte_exclusive() and pmd_exclusive() to also verify a shadow stack PTE is exclusive. Also rename can_follow_write_pte/pmd() to can_follow_write() to make their meaning clear; i.e. "Can we write to the page?", not "Is the PTE writable?" Signed-off-by: Yu-cheng Yu --- arch/x86/mm/pgtable.c | 18 ++++++++++++++++++ include/asm-generic/pgtable.h | 4 ++++ mm/gup.c | 8 +++++--- mm/huge_memory.c | 8 +++++--- 4 files changed, 32 insertions(+), 6 deletions(-) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 864954bda7fe..80876b2d03b7 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -903,4 +903,22 @@ inline bool arch_copy_pte_mapping(vm_flags_t vm_flags) { return (vm_flags & VM_SHSTK); } + +inline bool pte_exclusive(pte_t pte, struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_SHSTK) + return pte_dirty_hw(pte); + else + return pte_dirty(pte); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +inline bool pmd_exclusive(pmd_t pmd, struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_SHSTK) + return pmd_dirty_hw(pmd); + else + return pmd_dirty(pmd); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* CONFIG_X86_INTEL_SHADOW_STACK_USER */ diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 7512e4dfd642..09881698a566 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1131,10 +1131,14 @@ static inline bool arch_has_pfn_modify_check(void) #define pte_set_vma_features(pte, vma) pte #define pmd_set_vma_features(pmd, vma) pmd #define arch_copy_pte_mapping(vma_flags) false +#define pte_exclusive(pte, vma) pte_dirty(pte) +#define pmd_exclusive(pmd, vma) pmd_dirty(pmd) #else pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma); pmd_t pmd_set_vma_features(pmd_t pmd, struct vm_area_struct *vma); bool arch_copy_pte_mapping(vm_flags_t vm_flags); +bool pte_exclusive(pte_t pte, struct vm_area_struct *vma); +bool pmd_exclusive(pmd_t pmd, struct vm_area_struct *vma); #endif #endif /* _ASM_GENERIC_PGTABLE_H */ diff --git a/mm/gup.c b/mm/gup.c index 1abc8b4afff6..03cb2e331f80 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -64,10 +64,12 @@ 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_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) && + pte_exclusive(pte, vma)); } static struct page *follow_page_pte(struct vm_area_struct *vma, @@ -105,7 +107,7 @@ 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, flags, vma)) { pte_unmap_unlock(ptep, ptl); return NULL; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 6e03e26c1cec..3b3e1026fb5b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1387,10 +1387,12 @@ 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_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) && + pmd_exclusive(pmd, vma)); } struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, @@ -1403,7 +1405,7 @@ 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, flags, vma)) goto out; /* Avoid dumping huge zero page */ -- 2.17.1 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga05.intel.com ([192.55.52.43]:3984 "EHLO mga05.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728528AbeJKWs0 (ORCPT ); Thu, 11 Oct 2018 18:48:26 -0400 From: Yu-cheng Yu Subject: [PATCH v5 18/27] mm: Update can_follow_write_pte/pmd for shadow stack Date: Thu, 11 Oct 2018 08:15:14 -0700 Message-ID: <20181011151523.27101-19-yu-cheng.yu@intel.com> In-Reply-To: <20181011151523.27101-1-yu-cheng.yu@intel.com> References: <20181011151523.27101-1-yu-cheng.yu@intel.com> Sender: linux-arch-owner@vger.kernel.org List-ID: 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 , 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 Cc: Yu-cheng Yu Message-ID: <20181011151514.dtaPyABzyl8VcJ30ZoF05g7CcAxEYbkjBmxsyuZklmk@z> can_follow_write_pte/pmd look for the (RO & DIRTY) PTE/PMD to verify an exclusive RO page still exists after a broken COW. A shadow stack PTE is RO & PAGE_DIRTY_SW when it is shared, otherwise RO & PAGE_DIRTY_HW. Introduce pte_exclusive() and pmd_exclusive() to also verify a shadow stack PTE is exclusive. Also rename can_follow_write_pte/pmd() to can_follow_write() to make their meaning clear; i.e. "Can we write to the page?", not "Is the PTE writable?" Signed-off-by: Yu-cheng Yu --- arch/x86/mm/pgtable.c | 18 ++++++++++++++++++ include/asm-generic/pgtable.h | 4 ++++ mm/gup.c | 8 +++++--- mm/huge_memory.c | 8 +++++--- 4 files changed, 32 insertions(+), 6 deletions(-) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 864954bda7fe..80876b2d03b7 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -903,4 +903,22 @@ inline bool arch_copy_pte_mapping(vm_flags_t vm_flags) { return (vm_flags & VM_SHSTK); } + +inline bool pte_exclusive(pte_t pte, struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_SHSTK) + return pte_dirty_hw(pte); + else + return pte_dirty(pte); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +inline bool pmd_exclusive(pmd_t pmd, struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_SHSTK) + return pmd_dirty_hw(pmd); + else + return pmd_dirty(pmd); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* CONFIG_X86_INTEL_SHADOW_STACK_USER */ diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 7512e4dfd642..09881698a566 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1131,10 +1131,14 @@ static inline bool arch_has_pfn_modify_check(void) #define pte_set_vma_features(pte, vma) pte #define pmd_set_vma_features(pmd, vma) pmd #define arch_copy_pte_mapping(vma_flags) false +#define pte_exclusive(pte, vma) pte_dirty(pte) +#define pmd_exclusive(pmd, vma) pmd_dirty(pmd) #else pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma); pmd_t pmd_set_vma_features(pmd_t pmd, struct vm_area_struct *vma); bool arch_copy_pte_mapping(vm_flags_t vm_flags); +bool pte_exclusive(pte_t pte, struct vm_area_struct *vma); +bool pmd_exclusive(pmd_t pmd, struct vm_area_struct *vma); #endif #endif /* _ASM_GENERIC_PGTABLE_H */ diff --git a/mm/gup.c b/mm/gup.c index 1abc8b4afff6..03cb2e331f80 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -64,10 +64,12 @@ 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_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) && + pte_exclusive(pte, vma)); } static struct page *follow_page_pte(struct vm_area_struct *vma, @@ -105,7 +107,7 @@ 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, flags, vma)) { pte_unmap_unlock(ptep, ptl); return NULL; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 6e03e26c1cec..3b3e1026fb5b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1387,10 +1387,12 @@ 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_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) && + pmd_exclusive(pmd, vma)); } struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, @@ -1403,7 +1405,7 @@ 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, flags, vma)) goto out; /* Avoid dumping huge zero page */ -- 2.17.1