Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
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>,
	Borislav Petkov <bp@alien8.de>,
	Cyrill Gorcunov <gorcunov@gmail.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Eugene Syromiatnikov <esyr@redhat.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@chromium.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>,
	Randy Dunlap <rdunlap@infradead.org>,
	"Ravi V. Shankar" <ravi.v.shankar@intel.com>,
	Vedvyas Shanbhogue <vedvyas.shanbhogue@intel.com>,
	Dave Martin <Dave.Martin@arm.com>
Cc: Yu-cheng Yu <yu-cheng.yu@intel.com>
Subject: [PATCH v8 17/27] mm: Update can_follow_write_pte/pmd for shadow stack
Date: Tue, 13 Aug 2019 13:52:15 -0700
Message-ID: <20190813205225.12032-18-yu-cheng.yu@intel.com> (raw)
In-Reply-To: <20190813205225.12032-1-yu-cheng.yu@intel.com>

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 <yu-cheng.yu@intel.com>
---
 arch/x86/mm/pgtable.c         | 18 ++++++++++++++++++
 include/asm-generic/pgtable.h | 12 ++++++++++++
 mm/gup.c                      |  8 +++++---
 mm/huge_memory.c              |  8 +++++---
 4 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 6f3959ca2a08..326715fd0c50 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -898,4 +898,22 @@ 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 438ce73b57ea..b58f40525ebc 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1203,10 +1203,22 @@ static inline bool arch_copy_pte_mapping(vm_flags_t vm_flags)
 {
 	return false;
 }
+
+static inline bool pte_exclusive(pte_t pte, struct vm_area_struct *vma)
+{
+	return pte_dirty(pte);
+}
+
+static inline bool pmd_exclusive(pmd_t pmd, struct vm_area_struct *vma)
+{
+	return 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 98f13ab37bac..d7b298c5f6cb 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -179,10 +179,12 @@ 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,
@@ -220,7 +222,7 @@ 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 39d66c628121..947eb0121671 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1444,10 +1444,12 @@ 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,
@@ -1460,7 +1462,7 @@ 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



  parent reply index

Thread overview: 53+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-13 20:51 [PATCH v8 00/27] Control-flow Enforcement: Shadow Stack Yu-cheng Yu
2019-08-13 20:51 ` [PATCH v8 01/27] Documentation/x86: Add CET description Yu-cheng Yu
2019-08-14  8:07   ` Florian Weimer
2019-08-14 15:57     ` Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 02/27] x86/cpufeatures: Add CET CPU feature flags for Control-flow Enforcement Technology (CET) Yu-cheng Yu
2019-08-21 10:20   ` Borislav Petkov
2019-08-21 14:46     ` Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 03/27] x86/fpu/xstate: Change names to separate XSAVES system and user states Yu-cheng Yu
2019-08-21 14:45   ` Borislav Petkov
2019-08-13 20:52 ` [PATCH v8 04/27] x86/fpu/xstate: Introduce XSAVES system states Yu-cheng Yu
2019-08-16 19:56   ` Thomas Gleixner
2019-08-16 19:59     ` Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 05/27] x86/fpu/xstate: Introduce CET MSR " Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 06/27] x86/cet: Add control protection exception handler Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 07/27] x86/cet/shstk: Add Kconfig option for user-mode shadow stack Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 08/27] mm: Introduce VM_SHSTK for shadow stack memory Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 09/27] mm/mmap: Prevent Shadow Stack VMA merges Yu-cheng Yu
2019-08-13 22:34   ` Dave Hansen
2019-08-14 16:20     ` Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 10/27] x86/mm: Change _PAGE_DIRTY to _PAGE_DIRTY_HW Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 11/27] x86/mm: Introduce _PAGE_DIRTY_SW Yu-cheng Yu
2019-08-13 23:02   ` Dave Hansen
2019-08-13 23:49     ` Andy Lutomirski
2019-08-14 16:42     ` Yu-cheng Yu
2019-08-14 16:58       ` Dave Hansen
2019-08-23 14:02   ` Peter Zijlstra
2019-08-27 22:37     ` Yu-cheng Yu
2019-08-28  7:03       ` Peter Zijlstra
2019-08-28 14:57         ` Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 12/27] drm/i915/gvt: Update _PAGE_DIRTY to _PAGE_DIRTY_BITS Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 13/27] x86/mm: Modify ptep_set_wrprotect and pmdp_set_wrprotect for _PAGE_DIRTY_SW Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 14/27] x86/mm: Shadow stack page fault error checking Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 15/27] mm: Handle shadow stack page fault Yu-cheng Yu
2019-08-13 22:55   ` Andy Lutomirski
2019-08-14 16:27     ` Yu-cheng Yu
2019-08-14 16:48       ` Dave Hansen
2019-08-14 17:00         ` Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 16/27] mm: Handle THP/HugeTLB " Yu-cheng Yu
2019-08-13 20:52 ` Yu-cheng Yu [this message]
2019-08-13 20:52 ` [PATCH v8 18/27] mm: Introduce do_mmap_locked() Yu-cheng Yu
2019-08-20  1:02   ` Sean Christopherson
2019-08-20 16:08     ` Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 19/27] x86/cet/shstk: User-mode shadow stack support Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 20/27] x86/cet/shstk: Introduce WRUSS instruction Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 21/27] x86/cet/shstk: Handle signals for shadow stack Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 22/27] binfmt_elf: Extract .note.gnu.property from an ELF file Yu-cheng Yu
2019-08-16 13:55   ` Dave Martin
2019-08-20 10:02   ` Dave Martin
2019-08-13 20:52 ` [PATCH v8 23/27] x86/cet/shstk: ELF header parsing of Shadow Stack Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 24/27] x86/cet/shstk: Handle thread shadow stack Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 25/27] mm/mmap: Add Shadow stack pages to memory accounting Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 26/27] x86/cet/shstk: Add arch_prctl functions for Shadow Stack Yu-cheng Yu
2019-08-13 20:52 ` [PATCH v8 27/27] x86/cet/shstk: Add Shadow Stack instructions to opcode map Yu-cheng Yu

Reply instructions:

You may reply publically 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=20190813205225.12032-18-yu-cheng.yu@intel.com \
    --to=yu-cheng.yu@intel.com \
    --cc=Dave.Martin@arm.com \
    --cc=arnd@arndb.de \
    --cc=bp@alien8.de \
    --cc=bsingharora@gmail.com \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=esyr@redhat.com \
    --cc=fweimer@redhat.com \
    --cc=gorcunov@gmail.com \
    --cc=hjl.tools@gmail.com \
    --cc=hpa@zytor.com \
    --cc=jannh@google.com \
    --cc=keescook@chromium.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=peterz@infradead.org \
    --cc=ravi.v.shankar@intel.com \
    --cc=rdunlap@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=vedvyas.shanbhogue@intel.com \
    --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: link

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org linux-mm@archiver.kernel.org
	public-inbox-index linux-mm


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/ public-inbox