[PATCH v4 13/39] x86/mm: Start actually marking _PAGE_COW

[Rick Edgecombe <rick.p.edgecombe@xxxxxxxxx>]

The recently introduced _PAGE_COW should be used instead of the HW Dirty
bit whenever a PTE is Write=0, in order to not inadvertently create
shadow stack PTEs. Update pte_mk*() helpers to do this, and apply the same
changes to pmd and pud.

Tested-by: Pengfei Xu <pengfei.xu@xxxxxxxxx>
Tested-by: John Allen <john.allen@xxxxxxx>
Co-developed-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@xxxxxxxxx>
---

v4:
 - Break part patch for better bisectability

 arch/x86/include/asm/pgtable.h | 133 ++++++++++++++++++++++++++++-----
 1 file changed, 113 insertions(+), 20 deletions(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index b68428099932..4a149cec0c07 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -124,9 +124,17 @@ extern pmdval_t early_pmd_flags;
  * The following only work if pte_present() is true.
  * Undefined behaviour if not..
  */
-static inline int pte_dirty(pte_t pte)
+static inline bool pte_dirty(pte_t pte)
 {
-	return pte_flags(pte) & _PAGE_DIRTY;
+	return pte_flags(pte) & _PAGE_DIRTY_BITS;
+}
+
+static inline bool pte_shstk(pte_t pte)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK))
+		return false;
+
+	return (pte_flags(pte) & (_PAGE_RW | _PAGE_DIRTY)) == _PAGE_DIRTY;
 }
 
 static inline int pte_young(pte_t pte)
@@ -134,9 +142,18 @@ static inline int pte_young(pte_t pte)
 	return pte_flags(pte) & _PAGE_ACCESSED;
 }
 
-static inline int pmd_dirty(pmd_t pmd)
+static inline bool pmd_dirty(pmd_t pmd)
 {
-	return pmd_flags(pmd) & _PAGE_DIRTY;
+	return pmd_flags(pmd) & _PAGE_DIRTY_BITS;
+}
+
+static inline bool pmd_shstk(pmd_t pmd)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK))
+		return false;
+
+	return (pmd_flags(pmd) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) ==
+	       (_PAGE_DIRTY | _PAGE_PSE);
 }
 
 static inline int pmd_young(pmd_t pmd)
@@ -144,9 +161,9 @@ static inline int pmd_young(pmd_t pmd)
 	return pmd_flags(pmd) & _PAGE_ACCESSED;
 }
 
-static inline int pud_dirty(pud_t pud)
+static inline bool pud_dirty(pud_t pud)
 {
-	return pud_flags(pud) & _PAGE_DIRTY;
+	return pud_flags(pud) & _PAGE_DIRTY_BITS;
 }
 
 static inline int pud_young(pud_t pud)
@@ -156,13 +173,21 @@ static inline int pud_young(pud_t pud)
 
 static inline int pte_write(pte_t pte)
 {
-	return pte_flags(pte) & _PAGE_RW;
+	/*
+	 * Shadow stack pages are logically writable, but do not have
+	 * _PAGE_RW.  Check for them separately from _PAGE_RW itself.
+	 */
+	return (pte_flags(pte) & _PAGE_RW) || pte_shstk(pte);
 }
 
 #define pmd_write pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
-	return pmd_flags(pmd) & _PAGE_RW;
+	/*
+	 * Shadow stack pages are logically writable, but do not have
+	 * _PAGE_RW.  Check for them separately from _PAGE_RW itself.
+	 */
+	return (pmd_flags(pmd) & _PAGE_RW) || pmd_shstk(pmd);
 }
 
 #define pud_write pud_write
@@ -357,7 +382,7 @@ static inline pte_t pte_clear_uffd_wp(pte_t pte)
 
 static inline pte_t pte_mkclean(pte_t pte)
 {
-	return pte_clear_flags(pte, _PAGE_DIRTY);
+	return pte_clear_flags(pte, _PAGE_DIRTY_BITS);
 }
 
 static inline pte_t pte_mkold(pte_t pte)
@@ -367,7 +392,16 @@ static inline pte_t pte_mkold(pte_t pte)
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
-	return pte_clear_flags(pte, _PAGE_RW);
+	pte = pte_clear_flags(pte, _PAGE_RW);
+
+	/*
+	 * Blindly clearing _PAGE_RW might accidentally create
+	 * a shadow stack PTE (Write=0,Dirty=1). Move the hardware
+	 * dirty value to the software bit.
+	 */
+	if (pte_dirty(pte))
+		pte = pte_mkcow(pte);
+	return pte;
 }
 
 static inline pte_t pte_mkexec(pte_t pte)
@@ -377,7 +411,19 @@ static inline pte_t pte_mkexec(pte_t pte)
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-	return pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+	pteval_t dirty = _PAGE_DIRTY;
+
+	/* Avoid creating Dirty=1,Write=0 PTEs */
+	if (cpu_feature_enabled(X86_FEATURE_USER_SHSTK) && !pte_write(pte))
+		dirty = _PAGE_COW;
+
+	return pte_set_flags(pte, dirty | _PAGE_SOFT_DIRTY);
+}
+
+static inline pte_t pte_mkwrite_shstk(pte_t pte)
+{
+	/* pte_clear_cow() also sets Dirty=1 */
+	return pte_clear_cow(pte);
 }
 
 static inline pte_t pte_mkyoung(pte_t pte)
@@ -387,7 +433,12 @@ static inline pte_t pte_mkyoung(pte_t pte)
 
 static inline pte_t pte_mkwrite(pte_t pte)
 {
-	return pte_set_flags(pte, _PAGE_RW);
+	pte = pte_set_flags(pte, _PAGE_RW);
+
+	if (pte_dirty(pte))
+		pte = pte_clear_cow(pte);
+
+	return pte;
 }
 
 static inline pte_t pte_mkhuge(pte_t pte)
@@ -478,17 +529,36 @@ static inline pmd_t pmd_mkold(pmd_t pmd)
 
 static inline pmd_t pmd_mkclean(pmd_t pmd)
 {
-	return pmd_clear_flags(pmd, _PAGE_DIRTY);
+	return pmd_clear_flags(pmd, _PAGE_DIRTY_BITS);
 }
 
 static inline pmd_t pmd_wrprotect(pmd_t pmd)
 {
-	return pmd_clear_flags(pmd, _PAGE_RW);
+	pmd = pmd_clear_flags(pmd, _PAGE_RW);
+	/*
+	 * Blindly clearing _PAGE_RW might accidentally create
+	 * a shadow stack PMD (RW=0, Dirty=1). Move the hardware
+	 * dirty value to the software bit.
+	 */
+	if (pmd_dirty(pmd))
+		pmd = pmd_mkcow(pmd);
+	return pmd;
 }
 
 static inline pmd_t pmd_mkdirty(pmd_t pmd)
 {
-	return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+	pmdval_t dirty = _PAGE_DIRTY;
+
+	/* Avoid creating (HW)Dirty=1, Write=0 PMDs */
+	if (cpu_feature_enabled(X86_FEATURE_USER_SHSTK) && !pmd_write(pmd))
+		dirty = _PAGE_COW;
+
+	return pmd_set_flags(pmd, dirty | _PAGE_SOFT_DIRTY);
+}
+
+static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd)
+{
+	return pmd_clear_cow(pmd);
 }
 
 static inline pmd_t pmd_mkdevmap(pmd_t pmd)
@@ -508,7 +578,11 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd)
 
 static inline pmd_t pmd_mkwrite(pmd_t pmd)
 {
-	return pmd_set_flags(pmd, _PAGE_RW);
+	pmd = pmd_set_flags(pmd, _PAGE_RW);
+
+	if (pmd_dirty(pmd))
+		pmd = pmd_clear_cow(pmd);
+	return pmd;
 }
 
 static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
@@ -552,17 +626,32 @@ static inline pud_t pud_mkold(pud_t pud)
 
 static inline pud_t pud_mkclean(pud_t pud)
 {
-	return pud_clear_flags(pud, _PAGE_DIRTY);
+	return pud_clear_flags(pud, _PAGE_DIRTY_BITS);
 }
 
 static inline pud_t pud_wrprotect(pud_t pud)
 {
-	return pud_clear_flags(pud, _PAGE_RW);
+	pud = pud_clear_flags(pud, _PAGE_RW);
+
+	/*
+	 * Blindly clearing _PAGE_RW might accidentally create
+	 * a shadow stack PUD (RW=0, Dirty=1). Move the hardware
+	 * dirty value to the software bit.
+	 */
+	if (pud_dirty(pud))
+		pud = pud_mkcow(pud);
+	return pud;
 }
 
 static inline pud_t pud_mkdirty(pud_t pud)
 {
-	return pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+	pudval_t dirty = _PAGE_DIRTY;
+
+	/* Avoid creating (HW)Dirty=1, Write=0 PUDs */
+	if (cpu_feature_enabled(X86_FEATURE_USER_SHSTK) && !pud_write(pud))
+		dirty = _PAGE_COW;
+
+	return pud_set_flags(pud, dirty | _PAGE_SOFT_DIRTY);
 }
 
 static inline pud_t pud_mkdevmap(pud_t pud)
@@ -582,7 +671,11 @@ static inline pud_t pud_mkyoung(pud_t pud)
 
 static inline pud_t pud_mkwrite(pud_t pud)
 {
-	return pud_set_flags(pud, _PAGE_RW);
+	pud = pud_set_flags(pud, _PAGE_RW);
+
+	if (pud_dirty(pud))
+		pud = pud_clear_cow(pud);
+	return pud;
 }
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
-- 
2.17.1