linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Yu-cheng Yu <yu-cheng.yu@intel.com>
To: linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
	linux-mm@kvack.org, linux-arch@vger.kernel.org, x86@kernel.org,
	"H. Peter Anvin" <hpa@zytor.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, "H.J. Lu" <hjl.tools@gmail.com>,
	Vedvyas Shanbhogue <vedvyas.shanbhogue@intel.com>,
	"Ravi V. Shankar" <ravi.v.shankar@intel.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Andy Lutomirski <luto@amacapital.net>,
	Jonathan Corbet <corbet@lwn.net>, Oleg Nesterov <oleg@redhat.com>,
	Arnd Bergmann <arnd@arndb.de>,
	Mike Kravetz <mike.kravetz@oracle.com>
Cc: Yu-cheng Yu <yu-cheng.yu@intel.com>
Subject: [PATCH 6/9] x86/mm: Introduce ptep_set_wrprotect_flush and related functions
Date: Thu,  7 Jun 2018 07:37:02 -0700	[thread overview]
Message-ID: <20180607143705.3531-7-yu-cheng.yu@intel.com> (raw)
In-Reply-To: <20180607143705.3531-1-yu-cheng.yu@intel.com>

The function ptep_set_wrprotect()/huge_ptep_set_wrprotect() is
used by copy_page_range()/copy_hugetlb_page_range() to copy
PTEs.

On x86, when the shadow stack is enabled, only a shadow stack
PTE has the read-only and _PAGE_DIRTY_HW combination.  Upon
making a dirty PTE read-only, we move its _PAGE_DIRTY_HW to
_PAGE_DIRTY_SW.

When ptep_set_wrprotect() moves _PAGE_DIRTY_HW to _PAGE_DIRTY_SW,
if the PTE is writable and the mm is shared, another task could
race to set _PAGE_DIRTY_HW again.

Introduce ptep_set_wrprotect_flush(), pmdp_set_wrprotect_flush(),
and huge_ptep_set_wrprotect_flush() to make sure this does not
happen.

Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
 arch/x86/include/asm/pgtable.h | 56 +++++++++++++++++++++++++++++++++++-------
 include/asm-generic/pgtable.h  | 26 ++++++++++++++++++++
 2 files changed, 73 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0996f8a6979a..1053b940b35c 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1148,11 +1148,27 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 	return pte;
 }
 
-#define __HAVE_ARCH_PTEP_SET_WRPROTECT
-static inline void ptep_set_wrprotect(struct mm_struct *mm,
-				      unsigned long addr, pte_t *ptep)
-{
-	clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT_FLUSH
+extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
+			      unsigned long address,
+			      pte_t *ptep);
+static inline void ptep_set_wrprotect_flush(struct vm_area_struct *vma,
+					    unsigned long addr, pte_t *ptep)
+{
+	bool rw;
+
+	rw = test_and_clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
+	if (IS_ENABLED(CONFIG_X86_INTEL_SHADOW_STACK_USER)) {
+		struct mm_struct *mm = vma->vm_mm;
+		pte_t pte;
+
+		if (rw && (atomic_read(&mm->mm_users) > 1))
+			pte = ptep_clear_flush(vma, addr, ptep);
+		else
+			pte = *ptep;
+		pte = pte_move_flags(pte, _PAGE_DIRTY_HW, _PAGE_DIRTY_SW);
+		set_pte_at(mm, addr, ptep, pte);
+	}
 }
 
 #define flush_tlb_fix_spurious_fault(vma, address) do { } while (0)
@@ -1198,11 +1214,33 @@ static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
 	return native_pudp_get_and_clear(pudp);
 }
 
-#define __HAVE_ARCH_PMDP_SET_WRPROTECT
-static inline void pmdp_set_wrprotect(struct mm_struct *mm,
-				      unsigned long addr, pmd_t *pmdp)
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT_FLUSH
+static inline void huge_ptep_set_wrprotect_flush(struct vm_area_struct *vma,
+						 unsigned long addr, pte_t *ptep)
 {
-	clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
+	ptep_set_wrprotect_flush(vma, addr, ptep);
+}
+
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT_FLUSH
+extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
+				   unsigned long address,
+				   pmd_t *pmdp);
+static inline void pmdp_set_wrprotect_flush(struct vm_area_struct *vma,
+					    unsigned long addr, pmd_t *pmdp)
+{	bool rw;
+
+	rw = test_and_clear_bit(_PAGE_BIT_RW, (unsigned long *)&pmdp);
+	if (IS_ENABLED(CONFIG_X86_INTEL_SHADOW_STACK_USER)) {
+		struct mm_struct *mm = vma->vm_mm;
+		pmd_t pmd;
+
+		if (rw && (atomic_read(&mm->mm_users) > 1))
+			pmd = pmdp_huge_clear_flush(vma, addr, pmdp);
+		else
+			pmd = *pmdp;
+		pmd = pmd_move_flags(pmd, _PAGE_DIRTY_HW, _PAGE_DIRTY_SW);
+		set_pmd_at(mm, addr, pmdp, pmd);
+	}
 }
 
 #define pud_write pud_write
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 3f6f998509f0..9bcfdfc045bb 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -121,6 +121,15 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
+#ifndef __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT_FLUSH
+static inline void huge_ptep_set_wrorptect_flush(struct vm_area_struct *vma,
+						 unsigned long addr,
+						 pte_t *ptep)
+{
+	huge_ptep_set_wrprotect(vma->vm_mm, addr, ptep);
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 				       unsigned long address,
@@ -226,6 +235,15 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres
 }
 #endif
 
+#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT_FLUSH
+static inline void ptep_set_wrprotect_flush(struct vm_area_struct *vma,
+					    unsigned long address,
+					    pte_t *ptep)
+{
+	ptep_set_wrprotect(vma->vm_mm, address, ptep);
+}
+#endif
+
 #ifndef pte_savedwrite
 #define pte_savedwrite pte_write
 #endif
@@ -266,6 +284,14 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
+#ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT_FLUSH
+static inline void pmdp_set_wrprotect_flush(struct vm_area_struct *vma,
+					    unsigned long address,
+					    pmd_t *pmdp)
+{
+	pmdp_set_wrprotect(vma->vm_mm, address, pmdp);
+}
+#endif
 #ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 static inline void pudp_set_wrprotect(struct mm_struct *mm,
-- 
2.15.1

  parent reply	other threads:[~2018-06-07 14:40 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-07 14:36 [PATCH 0/9] Control Flow Enforcement - Part (2) Yu-cheng Yu
2018-06-07 14:36 ` [PATCH 1/9] x86/cet: Control protection exception handler Yu-cheng Yu
2018-06-07 15:46   ` Andy Lutomirski
2018-06-07 16:23     ` Yu-cheng Yu
2018-06-08  4:17   ` kbuild test robot
2018-06-08  4:18   ` kbuild test robot
2018-06-07 14:36 ` [PATCH 2/9] x86/cet: Add Kconfig option for user-mode shadow stack Yu-cheng Yu
2018-06-07 15:47   ` Andy Lutomirski
2018-06-07 15:58     ` Yu-cheng Yu
2018-06-07 16:28       ` Andy Lutomirski
2018-06-07 14:36 ` [PATCH 3/9] mm: Introduce VM_SHSTK for shadow stack memory Yu-cheng Yu
2018-06-07 14:37 ` [PATCH 4/9] x86/mm: Change _PAGE_DIRTY to _PAGE_DIRTY_HW Yu-cheng Yu
2018-06-08  3:53   ` kbuild test robot
2018-06-07 14:37 ` [PATCH 5/9] x86/mm: Introduce _PAGE_DIRTY_SW Yu-cheng Yu
2018-06-08  5:15   ` kbuild test robot
2018-06-07 14:37 ` Yu-cheng Yu [this message]
2018-06-07 16:24   ` [PATCH 6/9] x86/mm: Introduce ptep_set_wrprotect_flush and related functions Andy Lutomirski
2018-06-07 18:21     ` Dave Hansen
2018-06-07 18:24       ` Andy Lutomirski
2018-06-07 20:29     ` Dave Hansen
2018-06-07 20:36       ` Yu-cheng Yu
2018-06-08  0:59       ` Andy Lutomirski
2018-06-08  1:20         ` Dave Hansen
2018-06-08  4:43   ` kbuild test robot
2018-06-08 14:13   ` kbuild test robot
2018-06-07 14:37 ` [PATCH 7/9] x86/mm: Shadow stack page fault error checking Yu-cheng Yu
2018-06-07 16:26   ` Andy Lutomirski
2018-06-07 16:46     ` Yu-cheng Yu
2018-06-07 16:56     ` Dave Hansen
2018-06-07 14:37 ` [PATCH 8/9] x86/cet: Handle shadow stack page fault Yu-cheng Yu
2018-06-07 14:37 ` [PATCH 9/9] x86/cet: Handle THP/HugeTLB shadow stack page copying 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=20180607143705.3531-7-yu-cheng.yu@intel.com \
    --to=yu-cheng.yu@intel.com \
    --cc=arnd@arndb.de \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=hjl.tools@gmail.com \
    --cc=hpa@zytor.com \
    --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=oleg@redhat.com \
    --cc=ravi.v.shankar@intel.com \
    --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
Be 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