From: Yu-cheng Yu <yu-cheng.yu@intel.com> To: x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>, Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>, 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 <arnd@arndb.de>, Andy Lutomirski <luto@amacapital.net>, Balbir Singh <bsingharora@gmail.com>, Cyrill Gorcunov <gorcunov@gmail.com>, Dave Hansen <dave.hansen@linux.intel.com>, Florian Weimer <fweimer@redhat.com>, "H.J. Lu" <hjl.tools@gmail.com>, Jann Horn <jannh@google.com>, Jonathan Corbet <corbet@lwn.net>, Kees Cook <keescook@chromiun.org>, Mike Kravetz <mike.kravetz@oracle.com>, Nadav Amit <nadav.amit@gmail.com>, Oleg Nesterov <oleg@redhat.com>, Pavel Machek <pavel@ucw.cz>Peter Cc: Yu-cheng Yu <yu-cheng.yu@intel.com> Subject: [RFC PATCH v3 15/24] mm: Handle THP/HugeTLB shadow stack page fault Date: Thu, 30 Aug 2018 07:38:55 -0700 [thread overview] Message-ID: <20180830143904.3168-16-yu-cheng.yu@intel.com> (raw) In-Reply-To: <20180830143904.3168-1-yu-cheng.yu@intel.com> This patch implements THP shadow stack memory copying in the same way as the previous patch for regular PTE. In copy_huge_pmd(), we clear the dirty bit from the PMD. On the next shadow stack access to the PMD, a page fault occurs. At that time, the page is copied/re-used and the PMD is fixed. Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com> --- arch/x86/mm/pgtable.c | 8 ++++++++ include/asm-generic/pgtable.h | 6 ++++++ mm/huge_memory.c | 4 ++++ 3 files changed, 18 insertions(+) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index c63261128ac3..0ab38bfbedfc 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -881,4 +881,12 @@ 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 558a485617cd..0f25186cd38d 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1151,8 +1151,14 @@ static inline pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma) { return pte; } + +static inline pmd_t pmd_set_vma_features(pmd_t pmd, struct vm_area_struct *vma) +{ + return 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); #endif #endif /* _ASM_GENERIC_PGTABLE_H */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c3bc7e9c9a2a..5b4c8f2fb85e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -597,6 +597,7 @@ 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); @@ -1194,6 +1195,7 @@ 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); @@ -1278,6 +1280,7 @@ 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; @@ -1349,6 +1352,7 @@ 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); -- 2.17.1
WARNING: multiple messages have this Message-ID (diff)
From: Yu-cheng Yu <yu-cheng.yu@intel.com> To: x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>, Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>, 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 <arnd@arndb.de>, Andy Lutomirski <luto@amacapital.net>, Balbir Singh <bsingharora@gmail.com>, Cyrill Gorcunov <gorcunov@gmail.com>, Dave Hansen <dave.hansen@linux.intel.com>, Florian Weimer <fweimer@redhat.com>, "H.J. Lu" <hjl.tools@gmail.com>, Jann Horn <jannh@google.com>, Jonathan Corbet <corbet@lwn.net>, Kees Cook <keescook@chromiun.org>, Mike Kravetz <mike.kravetz@oracle.com>, Nadav Amit <nadav.amit@gmail.com>, Oleg Nesterov <oleg@redhat.com>, Pavel Machek <pavel@ucw.cz>, Peter Zijlstra <peterz@infradead.org>, "Ravi V. Shankar" <ravi.v.shankar@intel.com>, Vedvyas Shanbhogue <vedvyas.shanbhogue@intel.com> Cc: Yu-cheng Yu <yu-cheng.yu@intel.com> Subject: [RFC PATCH v3 15/24] mm: Handle THP/HugeTLB shadow stack page fault Date: Thu, 30 Aug 2018 07:38:55 -0700 [thread overview] Message-ID: <20180830143904.3168-16-yu-cheng.yu@intel.com> (raw) Message-ID: <20180830143855.SR9sO-pMI33Qnc7GEi5n5P6MLWEXg1QEvO_NxLmWseo@z> (raw) In-Reply-To: <20180830143904.3168-1-yu-cheng.yu@intel.com> This patch implements THP shadow stack memory copying in the same way as the previous patch for regular PTE. In copy_huge_pmd(), we clear the dirty bit from the PMD. On the next shadow stack access to the PMD, a page fault occurs. At that time, the page is copied/re-used and the PMD is fixed. Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com> --- arch/x86/mm/pgtable.c | 8 ++++++++ include/asm-generic/pgtable.h | 6 ++++++ mm/huge_memory.c | 4 ++++ 3 files changed, 18 insertions(+) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index c63261128ac3..0ab38bfbedfc 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -881,4 +881,12 @@ 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 558a485617cd..0f25186cd38d 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1151,8 +1151,14 @@ static inline pte_t pte_set_vma_features(pte_t pte, struct vm_area_struct *vma) { return pte; } + +static inline pmd_t pmd_set_vma_features(pmd_t pmd, struct vm_area_struct *vma) +{ + return 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); #endif #endif /* _ASM_GENERIC_PGTABLE_H */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c3bc7e9c9a2a..5b4c8f2fb85e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -597,6 +597,7 @@ 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); @@ -1194,6 +1195,7 @@ 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); @@ -1278,6 +1280,7 @@ 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; @@ -1349,6 +1352,7 @@ 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); -- 2.17.1
next prev parent reply other threads:[~2018-08-30 14:38 UTC|newest] Thread overview: 146+ messages / expand[flat|nested] mbox.gz Atom feed top 2018-08-30 14:38 [RFC PATCH v3 00/24] Control Flow Enforcement: Shadow Stack Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 01/24] x86/cpufeatures: Add CPUIDs for Control-flow Enforcement Technology (CET) Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 02/24] x86/fpu/xstate: Change some names to separate XSAVES system and user states Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 03/24] x86/fpu/xstate: Enable XSAVES system states Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 04/24] x86/fpu/xstate: Add XSAVES system states for shadow stack Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 05/24] Documentation/x86: Add CET description Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 20:39 ` Pavel Machek 2018-08-30 20:39 ` Pavel Machek 2018-08-30 22:49 ` Yu-cheng Yu 2018-08-30 22:49 ` Yu-cheng Yu 2018-09-14 21:17 ` Yu-cheng Yu 2018-09-14 21:17 ` Yu-cheng Yu 2018-09-03 2:56 ` Randy Dunlap 2018-09-03 2:56 ` Randy Dunlap 2018-08-30 14:38 ` [RFC PATCH v3 06/24] x86/cet: Control protection exception handler Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-31 15:01 ` Jann Horn 2018-08-31 15:01 ` Jann Horn 2018-08-31 16:20 ` Yu-cheng Yu 2018-08-31 16:20 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 07/24] x86/cet/shstk: Add Kconfig option for user-mode shadow stack Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 08/24] mm: Introduce VM_SHSTK for shadow stack memory Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 09/24] x86/mm: Change _PAGE_DIRTY to _PAGE_DIRTY_HW Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 10/24] x86/mm: Introduce _PAGE_DIRTY_SW Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 11/24] drm/i915/gvt: Update _PAGE_DIRTY to _PAGE_DIRTY_BITS Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 12/24] x86/mm: Modify ptep_set_wrprotect and pmdp_set_wrprotect for _PAGE_DIRTY_SW Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 15:49 ` Jann Horn 2018-08-30 15:49 ` Jann Horn 2018-08-30 16:02 ` Yu-cheng Yu 2018-08-30 16:02 ` Yu-cheng Yu 2018-08-30 16:08 ` Dave Hansen 2018-08-30 16:08 ` Dave Hansen 2018-08-30 16:23 ` Jann Horn 2018-08-30 16:23 ` Jann Horn 2018-08-30 17:19 ` Dave Hansen 2018-08-30 17:19 ` Dave Hansen 2018-08-30 17:26 ` Yu-cheng Yu 2018-08-30 17:26 ` Yu-cheng Yu 2018-08-30 17:33 ` Dave Hansen 2018-08-30 17:33 ` Dave Hansen 2018-08-30 17:54 ` Yu-cheng Yu 2018-08-30 17:54 ` Yu-cheng Yu 2018-08-30 17:59 ` Jann Horn 2018-08-30 17:59 ` Jann Horn 2018-08-30 20:21 ` Yu-cheng Yu 2018-08-30 20:21 ` Yu-cheng Yu 2018-08-30 20:44 ` Jann Horn 2018-08-30 20:44 ` Jann Horn 2018-08-30 20:52 ` Yu-cheng Yu 2018-08-30 20:52 ` Yu-cheng Yu 2018-08-30 21:01 ` Jann Horn 2018-08-30 21:01 ` Jann Horn 2018-08-30 21:47 ` Jann Horn 2018-08-30 21:47 ` Jann Horn 2018-08-31 9:53 ` Peter Zijlstra 2018-08-31 9:53 ` Peter Zijlstra 2018-08-31 14:33 ` Yu-cheng Yu 2018-08-31 14:33 ` Yu-cheng Yu 2018-08-31 14:47 ` Dave Hansen 2018-08-31 14:47 ` Dave Hansen 2018-08-31 15:48 ` Yu-cheng Yu 2018-08-31 15:48 ` Yu-cheng Yu 2018-08-31 15:58 ` Dave Hansen 2018-08-31 15:58 ` Dave Hansen 2018-08-31 16:29 ` Peter Zijlstra 2018-08-31 16:29 ` Peter Zijlstra 2018-09-14 20:39 ` Yu-cheng Yu 2018-09-14 20:39 ` Yu-cheng Yu 2018-09-14 20:46 ` Dave Hansen 2018-09-14 20:46 ` Dave Hansen 2018-09-14 21:08 ` Yu-cheng Yu 2018-09-14 21:08 ` Yu-cheng Yu 2018-09-14 21:33 ` Dave Hansen 2018-09-14 21:33 ` Dave Hansen 2018-08-31 1:23 ` Andy Lutomirski 2018-08-31 1:23 ` Andy Lutomirski 2018-08-30 17:34 ` Andy Lutomirski 2018-08-30 17:34 ` Andy Lutomirski 2018-08-30 18:55 ` Dave Hansen 2018-08-30 18:55 ` Dave Hansen 2018-08-31 17:46 ` Andy Lutomirski 2018-08-31 17:46 ` Andy Lutomirski 2018-08-31 17:52 ` Dave Hansen 2018-08-31 17:52 ` Dave Hansen 2018-08-30 19:59 ` Randy Dunlap 2018-08-30 19:59 ` Randy Dunlap 2018-08-30 20:23 ` Yu-cheng Yu 2018-08-30 20:23 ` Yu-cheng Yu 2018-08-31 16:29 ` Dave Hansen 2018-08-31 16:29 ` Dave Hansen 2018-08-30 14:38 ` [RFC PATCH v3 13/24] x86/mm: Shadow stack page fault error checking Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 14/24] mm: Handle shadow stack page fault Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu [this message] 2018-08-30 14:38 ` [RFC PATCH v3 15/24] mm: Handle THP/HugeTLB " Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 16/24] mm: Update can_follow_write_pte/pmd for shadow stack Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 17/24] mm: Introduce do_mmap_locked() Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 18/24] x86/cet/shstk: User-mode shadow stack support Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 16:10 ` Jann Horn 2018-08-30 16:10 ` Jann Horn 2018-08-30 16:20 ` Yu-cheng Yu 2018-08-30 16:20 ` Yu-cheng Yu 2018-08-30 14:38 ` [RFC PATCH v3 19/24] x86/cet/shstk: Introduce WRUSS instruction Yu-cheng Yu 2018-08-30 14:38 ` Yu-cheng Yu 2018-08-30 15:39 ` Jann Horn 2018-08-30 15:39 ` Jann Horn 2018-08-30 15:55 ` Andy Lutomirski 2018-08-30 15:55 ` Andy Lutomirski 2018-08-30 16:22 ` Yu-cheng Yu 2018-08-30 16:22 ` Yu-cheng Yu 2018-08-31 21:49 ` Yu-cheng Yu 2018-08-31 21:49 ` Yu-cheng Yu 2018-08-31 22:16 ` Andy Lutomirski 2018-08-31 22:16 ` Andy Lutomirski 2018-09-14 20:46 ` Yu-cheng Yu 2018-09-14 20:46 ` Yu-cheng Yu 2018-08-30 14:39 ` [RFC PATCH v3 20/24] x86/cet/shstk: Signal handling for shadow stack Yu-cheng Yu 2018-08-30 14:39 ` Yu-cheng Yu 2018-08-30 14:39 ` [RFC PATCH v3 21/24] x86/cet/shstk: ELF header parsing of Shadow Stack Yu-cheng Yu 2018-08-30 14:39 ` Yu-cheng Yu 2018-08-30 14:39 ` [RFC PATCH v3 22/24] x86/cet/shstk: Handle thread shadow stack Yu-cheng Yu 2018-08-30 14:39 ` Yu-cheng Yu 2018-08-30 14:39 ` [RFC PATCH v3 23/24] x86/cet/shstk: Add arch_prctl functions for Shadow Stack Yu-cheng Yu 2018-08-30 14:39 ` Yu-cheng Yu 2018-08-30 14:39 ` [RFC PATCH v3 24/24] x86/cet/shstk: Add Shadow Stack instructions to opcode map Yu-cheng Yu 2018-08-30 14:39 ` Yu-cheng Yu 2018-09-02 8:13 ` [RFC PATCH v3 00/24] Control Flow Enforcement: Shadow Stack Balbir Singh 2018-09-02 8:13 ` Balbir Singh 2018-09-04 14:47 ` Yu-cheng Yu 2018-09-04 14:47 ` Yu-cheng Yu
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20180830143904.3168-16-yu-cheng.yu@intel.com \ --to=yu-cheng.yu@intel.com \ --cc=arnd@arndb.de \ --cc=bsingharora@gmail.com \ --cc=corbet@lwn.net \ --cc=dave.hansen@linux.intel.com \ --cc=fweimer@redhat.com \ --cc=gorcunov@gmail.com \ --cc=hjl.tools@gmail.com \ --cc=hpa@zytor.com \ --cc=jannh@google.com \ --cc=keescook@chromiun.org \ --cc=linux-api@vger.kernel.org \ --cc=linux-arch@vger.kernel.org \ --cc=linux-doc@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=luto@amacapital.net \ --cc=mike.kravetz@oracle.com \ --cc=mingo@redhat.com \ --cc=nadav.amit@gmail.com \ --cc=oleg@redhat.com \ --cc=pavel@ucw.cz \ --cc=tglx@linutronix.de \ --cc=x86@kernel.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).