[PATCH v17 14/26] x86/mm: Update maybe_mkwrite() for shadow stack

[Yu-cheng Yu]

When serving a page fault, maybe_mkwrite() makes a PTE writable if its vma
has VM_WRITE.

A shadow stack vma has VM_SHSTK.  Its PTEs have _PAGE_DIRTY, but not
_PAGE_WRITE.  In fork(), _PAGE_DIRTY is cleared to effect copy-on-write,
and in page fault, _PAGE_DIRTY is restored and the shadow stack page is
writable again.

Update maybe_mkwrite() by introducing arch_maybe_mkwrite(), which sets
_PAGE_DIRTY for a shadow stack PTE.

Apply the same changes to maybe_pmd_mkwrite().

Signed-off-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
---
 arch/x86/Kconfig        |  4 ++++
 arch/x86/mm/pgtable.c   | 18 ++++++++++++++++++
 include/linux/mm.h      |  2 ++
 include/linux/pgtable.h | 24 ++++++++++++++++++++++++
 mm/huge_memory.c        |  2 ++
 5 files changed, 50 insertions(+)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 72cff400b9ae..fdaa437d9c53 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1953,6 +1953,9 @@ config X86_SGX
 config ARCH_HAS_SHADOW_STACK
 	def_bool n
 
+config ARCH_MAYBE_MKWRITE
+	def_bool n
+
 config X86_CET_USER
 	prompt "Intel Control-flow protection for user-mode"
 	def_bool n
@@ -1960,6 +1963,7 @@ config X86_CET_USER
 	depends on AS_WRUSS
 	select ARCH_USES_HIGH_VMA_FLAGS
 	select ARCH_HAS_SHADOW_STACK
+	select ARCH_MAYBE_MKWRITE
 	help
 	  Control-flow protection is a hardware security hardening feature
 	  that detects function-return address or jump target changes by
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index dfd82f51ba66..a9666b64bc05 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -610,6 +610,24 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
 }
 #endif
 
+#ifdef CONFIG_ARCH_MAYBE_MKWRITE
+pte_t arch_maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_flags & VM_SHSTK))
+		pte = pte_mkwrite_shstk(pte);
+	return pte;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+pmd_t arch_maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_flags & VM_SHSTK))
+		pmd = pmd_mkwrite_shstk(pmd);
+	return pmd;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif /* CONFIG_ARCH_MAYBE_MKWRITE */
+
 /**
  * reserve_top_address - reserves a hole in the top of kernel address space
  * @reserve - size of hole to reserve
diff --git a/include/linux/mm.h b/include/linux/mm.h
index d7e8b75505e6..7c789d439181 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -986,6 +986,8 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 {
 	if (likely(vma->vm_flags & VM_WRITE))
 		pte = pte_mkwrite(pte);
+	else
+		pte = arch_maybe_mkwrite(pte, vma);
 	return pte;
 }
 
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 8fcdfa52eb4b..d8452218d09b 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1439,6 +1439,30 @@ static inline bool arch_has_pfn_modify_check(void)
 }
 #endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */
 
+#ifdef CONFIG_MMU
+#ifdef CONFIG_ARCH_MAYBE_MKWRITE
+pte_t arch_maybe_mkwrite(pte_t pte, struct vm_area_struct *vma);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+pmd_t arch_maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+#else /* !CONFIG_ARCH_MAYBE_MKWRITE */
+static inline pte_t arch_maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
+{
+	return pte;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline pmd_t arch_maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
+{
+	return pmd;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+#endif /* CONFIG_ARCH_MAYBE_MKWRITE */
+#endif /* CONFIG_MMU */
+
 /*
  * Architecture PAGE_KERNEL_* fallbacks
  *
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9237976abe72..bfec65c9308b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -478,6 +478,8 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
 {
 	if (likely(vma->vm_flags & VM_WRITE))
 		pmd = pmd_mkwrite(pmd);
+	else
+		pmd = arch_maybe_pmd_mkwrite(pmd, vma);
 	return pmd;
 }
 
-- 
2.21.0