[v3,16/37] x86/mm: Update maybe_mkwrite() for shadow stack

Commit Message

Edgecombe, Rick P Nov. 4, 2022, 10:35 p.m. UTC

From: Yu-cheng Yu <[e-mail]>

When serving a page fault, maybe_mkwrite() makes a PTE writable if there is
a write access to it, and its vma has VM_WRITE. Shadow stack accesses to
shadow stack vma's are also treated as write accesses by the fault handler.
This is because setting shadow stack memory makes it writable via some
instructions, so COW has to happen even for shadow stack reads.

So maybe_mkwrite() should continue to set VM_WRITE vma's as normally
writable, but also set VM_WRITE|VM_SHADOW_STACK vma's as shadow stack.

Do this by adding a pte_mkwrite_shstk() and a cross-arch stub. Check for
VM_SHADOW_STACK in maybe_mkwrite() and call pte_mkwrite_shstk()
accordingly.

Apply the same changes to maybe_pmd_mkwrite().

Tested-by: Pengfei Xu <[e-mail]>
Tested-by: John Allen <[e-mail]>
Signed-off-by: Yu-cheng Yu <[e-mail]>
Co-developed-by: Rick Edgecombe <[e-mail]>
Signed-off-by: Rick Edgecombe <[e-mail]>
Cc: Kees Cook <[e-mail]>

---

v3:
 - Remove unneeded define for maybe_mkwrite (Peterz)
 - Switch to cleaner version of maybe_mkwrite() (Peterz)

v2:
 - Change to handle shadow stacks that are VM_WRITE|VM_SHADOW_STACK
 - Ditch arch specific maybe_mkwrite(), and make the code generic
 - Move do_anonymous_page() to next patch (Kirill)

Yu-cheng v29:
 - Remove likely()'s.

 arch/x86/include/asm/pgtable.h |  2 ++
 include/linux/mm.h             | 13 ++++++++++---
 include/linux/pgtable.h        | 14 ++++++++++++++
 mm/huge_memory.c               | 10 +++++++---
 4 files changed, 33 insertions(+), 6 deletions(-)

Patch

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index f252c42f3ca1..df67bcf9f69e 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -420,6 +420,7 @@  static inline pte_t pte_mkdirty(pte_t pte)
 	return pte_set_flags(pte, dirty | _PAGE_SOFT_DIRTY);
 }
 
+#define pte_mkwrite_shstk pte_mkwrite_shstk
 static inline pte_t pte_mkwrite_shstk(pte_t pte)
 {
 	/* pte_clear_cow() also sets Dirty=1 */
@@ -556,6 +557,7 @@  static inline pmd_t pmd_mkdirty(pmd_t pmd)
 	return pmd_set_flags(pmd, dirty | _PAGE_SOFT_DIRTY);
 }
 
+#define pmd_mkwrite_shstk pmd_mkwrite_shstk
 static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd)
 {
 	return pmd_clear_cow(pmd);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 42c4e4bc972d..5d9536fa860a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1015,12 +1015,19 @@  void free_compound_page(struct page *page);
  * servicing faults for write access.  In the normal case, do always want
  * pte_mkwrite.  But get_user_pages can cause write faults for mappings
  * that do not have writing enabled, when used by access_process_vm.
+ *
+ * If a vma is shadow stack (a type of writable memory), mark the pte shadow
+ * stack.
  */
 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);
-	return pte;
+	if (!(vma->vm_flags & VM_WRITE))
+		return pte;
+
+	if (vma->vm_flags & VM_SHADOW_STACK)
+		return pte_mkwrite_shstk(pte);
+
+	return pte_mkwrite(pte);
 }
 
 vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page);
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index a108b60a6962..5ce6732a6b65 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -493,6 +493,13 @@  static inline pte_t pte_sw_mkyoung(pte_t pte)
 #define pte_mk_savedwrite pte_mkwrite
 #endif
 
+#ifndef pte_mkwrite_shstk
+static inline pte_t pte_mkwrite_shstk(pte_t pte)
+{
+	return pte;
+}
+#endif
+
 #ifndef pte_clear_savedwrite
 #define pte_clear_savedwrite pte_wrprotect
 #endif
@@ -501,6 +508,13 @@  static inline pte_t pte_sw_mkyoung(pte_t pte)
 #define pmd_savedwrite pmd_write
 #endif
 
+#ifndef pmd_mkwrite_shstk
+static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd)
+{
+	return pmd;
+}
+#endif
+
 #ifndef pmd_mk_savedwrite
 #define pmd_mk_savedwrite pmd_mkwrite
 #endif
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 561a42567477..73b9b78f8cf4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -553,9 +553,13 @@  __setup("transparent_hugepage=", setup_transparent_hugepage);
 
 pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
 {
-	if (likely(vma->vm_flags & VM_WRITE))
-		pmd = pmd_mkwrite(pmd);
-	return pmd;
+	if (!(vma->vm_flags & VM_WRITE))
+		return pmd;
+
+	if (vma->vm_flags & VM_SHADOW_STACK)
+		return pmd_mkwrite_shstk(pmd);
+
+	return pmd_mkwrite(pmd);
 }
 
 #ifdef CONFIG_MEMCG