Merge tag 'x86_shstk_for_6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 shadow stack support from Dave Hansen:
 "This is the long awaited x86 shadow stack support, part of Intel's
  Control-flow Enforcement Technology (CET).

  CET consists of two related security features: shadow stacks and
  indirect branch tracking. This series implements just the shadow stack
  part of this feature, and just for userspace.

  The main use case for shadow stack is providing protection against
  return oriented programming attacks. It works by maintaining a
  secondary (shadow) stack using a special memory type that has
  protections against modification. When executing a CALL instruction,
  the processor pushes the return address to both the normal stack and
  to the special permission shadow stack. Upon RET, the processor pops
  the shadow stack copy and compares it to the normal stack copy.

  For more information, refer to the links below for the earlier
  versions of this patch set"

Link: https://lore.kernel.org/lkml/20220130211838.8382-1-rick.p.edgecombe@intel.com/
Link: https://lore.kernel.org/lkml/20230613001108.3040476-1-rick.p.edgecombe@intel.com/

* tag 'x86_shstk_for_6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (47 commits)
  x86/shstk: Change order of __user in type
  x86/ibt: Convert IBT selftest to asm
  x86/shstk: Don't retry vm_munmap() on -EINTR
  x86/kbuild: Fix Documentation/ reference
  x86/shstk: Move arch detail comment out of core mm
  x86/shstk: Add ARCH_SHSTK_STATUS
  x86/shstk: Add ARCH_SHSTK_UNLOCK
  x86: Add PTRACE interface for shadow stack
  selftests/x86: Add shadow stack test
  x86/cpufeatures: Enable CET CR4 bit for shadow stack
  x86/shstk: Wire in shadow stack interface
  x86: Expose thread features in /proc/$PID/status
  x86/shstk: Support WRSS for userspace
  x86/shstk: Introduce map_shadow_stack syscall
  x86/shstk: Check that signal frame is shadow stack mem
  x86/shstk: Check that SSP is aligned on sigreturn
  x86/shstk: Handle signals for shadow stack
  x86/shstk: Introduce routines modifying shstk
  x86/shstk: Handle thread shadow stack
  x86/shstk: Add user-mode shadow stack support
  ...

1 files changed, 266 insertions, 36 deletions

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index dbf8af70b7c2..d6ad98ca1288 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -125,9 +125,15 @@ 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)
+{
+	return cpu_feature_enabled(X86_FEATURE_SHSTK) &&
+	       (pte_flags(pte) & (_PAGE_RW | _PAGE_DIRTY)) == _PAGE_DIRTY;
 }
 
 static inline int pte_young(pte_t pte)
@@ -135,9 +141,16 @@ 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_BITS;
+}
+
+static inline bool pmd_shstk(pmd_t pmd)
 {
-	return pmd_flags(pmd) & _PAGE_DIRTY;
+	return cpu_feature_enabled(X86_FEATURE_SHSTK) &&
+	       (pmd_flags(pmd) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) ==
+	       (_PAGE_DIRTY | _PAGE_PSE);
 }
 
 #define pmd_young pmd_young
@@ -146,9 +159,9 @@ 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)
@@ -158,7 +171,27 @@ 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)
+{
+	/*
+	 * 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
+static inline int pud_write(pud_t pud)
+{
+	return pud_flags(pud) & _PAGE_RW;
 }
 
 static inline int pte_huge(pte_t pte)
@@ -292,9 +325,63 @@ static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear)
 	return native_make_pte(v & ~clear);
 }
 
+/*
+ * Write protection operations can result in Dirty=1,Write=0 PTEs. But in the
+ * case of X86_FEATURE_USER_SHSTK, these PTEs denote shadow stack memory. So
+ * when creating dirty, write-protected memory, a software bit is used:
+ * _PAGE_BIT_SAVED_DIRTY. The following functions take a PTE and transition the
+ * Dirty bit to SavedDirty, and vice-vesra.
+ *
+ * This shifting is only done if needed. In the case of shifting
+ * Dirty->SavedDirty, the condition is if the PTE is Write=0. In the case of
+ * shifting SavedDirty->Dirty, the condition is Write=1.
+ */
+static inline pgprotval_t mksaveddirty_shift(pgprotval_t v)
+{
+	pgprotval_t cond = (~v >> _PAGE_BIT_RW) & 1;
+
+	v |= ((v >> _PAGE_BIT_DIRTY) & cond) << _PAGE_BIT_SAVED_DIRTY;
+	v &= ~(cond << _PAGE_BIT_DIRTY);
+
+	return v;
+}
+
+static inline pgprotval_t clear_saveddirty_shift(pgprotval_t v)
+{
+	pgprotval_t cond = (v >> _PAGE_BIT_RW) & 1;
+
+	v |= ((v >> _PAGE_BIT_SAVED_DIRTY) & cond) << _PAGE_BIT_DIRTY;
+	v &= ~(cond << _PAGE_BIT_SAVED_DIRTY);
+
+	return v;
+}
+
+static inline pte_t pte_mksaveddirty(pte_t pte)
+{
+	pteval_t v = native_pte_val(pte);
+
+	v = mksaveddirty_shift(v);
+	return native_make_pte(v);
+}
+
+static inline pte_t pte_clear_saveddirty(pte_t pte)
+{
+	pteval_t v = native_pte_val(pte);
+
+	v = clear_saveddirty_shift(v);
+	return native_make_pte(v);
+}
+
 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 present.
+	 */
+	return pte_mksaveddirty(pte);
 }
 
 #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
@@ -332,7 +419,7 @@ 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)
@@ -347,7 +434,16 @@ 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);
+	pte = pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+
+	return pte_mksaveddirty(pte);
+}
+
+static inline pte_t pte_mkwrite_shstk(pte_t pte)
+{
+	pte = pte_clear_flags(pte, _PAGE_RW);
+
+	return pte_set_flags(pte, _PAGE_DIRTY);
 }
 
 static inline pte_t pte_mkyoung(pte_t pte)
@@ -355,11 +451,15 @@ static inline pte_t pte_mkyoung(pte_t pte)
 	return pte_set_flags(pte, _PAGE_ACCESSED);
 }
 
-static inline pte_t pte_mkwrite(pte_t pte)
+static inline pte_t pte_mkwrite_novma(pte_t pte)
 {
 	return pte_set_flags(pte, _PAGE_RW);
 }
 
+struct vm_area_struct;
+pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma);
+#define pte_mkwrite pte_mkwrite
+
 static inline pte_t pte_mkhuge(pte_t pte)
 {
 	return pte_set_flags(pte, _PAGE_PSE);
@@ -404,9 +504,34 @@ static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
 	return native_make_pmd(v & ~clear);
 }
 
+/* See comments above mksaveddirty_shift() */
+static inline pmd_t pmd_mksaveddirty(pmd_t pmd)
+{
+	pmdval_t v = native_pmd_val(pmd);
+
+	v = mksaveddirty_shift(v);
+	return native_make_pmd(v);
+}
+
+/* See comments above mksaveddirty_shift() */
+static inline pmd_t pmd_clear_saveddirty(pmd_t pmd)
+{
+	pmdval_t v = native_pmd_val(pmd);
+
+	v = clear_saveddirty_shift(v);
+	return native_make_pmd(v);
+}
+
 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.
+	 */
+	return pmd_mksaveddirty(pmd);
 }
 
 #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
@@ -433,12 +558,21 @@ 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_mkdirty(pmd_t pmd)
 {
-	return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+	pmd = pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+
+	return pmd_mksaveddirty(pmd);
+}
+
+static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd)
+{
+	pmd = pmd_clear_flags(pmd, _PAGE_RW);
+
+	return pmd_set_flags(pmd, _PAGE_DIRTY);
 }
 
 static inline pmd_t pmd_mkdevmap(pmd_t pmd)
@@ -456,11 +590,14 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd)
 	return pmd_set_flags(pmd, _PAGE_ACCESSED);
 }
 
-static inline pmd_t pmd_mkwrite(pmd_t pmd)
+static inline pmd_t pmd_mkwrite_novma(pmd_t pmd)
 {
 	return pmd_set_flags(pmd, _PAGE_RW);
 }
 
+pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
+#define pmd_mkwrite pmd_mkwrite
+
 static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
 {
 	pudval_t v = native_pud_val(pud);
@@ -475,6 +612,24 @@ static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
 	return native_make_pud(v & ~clear);
 }
 
+/* See comments above mksaveddirty_shift() */
+static inline pud_t pud_mksaveddirty(pud_t pud)
+{
+	pudval_t v = native_pud_val(pud);
+
+	v = mksaveddirty_shift(v);
+	return native_make_pud(v);
+}
+
+/* See comments above mksaveddirty_shift() */
+static inline pud_t pud_clear_saveddirty(pud_t pud)
+{
+	pudval_t v = native_pud_val(pud);
+
+	v = clear_saveddirty_shift(v);
+	return native_make_pud(v);
+}
+
 static inline pud_t pud_mkold(pud_t pud)
 {
 	return pud_clear_flags(pud, _PAGE_ACCESSED);
@@ -482,17 +637,26 @@ 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.
+	 */
+	return pud_mksaveddirty(pud);
 }
 
 static inline pud_t pud_mkdirty(pud_t pud)
 {
-	return pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+	pud = pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+
+	return pud_mksaveddirty(pud);
 }
 
 static inline pud_t pud_mkdevmap(pud_t pud)
@@ -512,7 +676,9 @@ 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);
+
+	return pud_clear_saveddirty(pud);
 }
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
@@ -629,6 +795,7 @@ static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask);
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	pteval_t val = pte_val(pte), oldval = val;
+	pte_t pte_result;
 
 	/*
 	 * Chop off the NX bit (if present), and add the NX portion of
@@ -637,17 +804,54 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	val &= _PAGE_CHG_MASK;
 	val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK;
 	val = flip_protnone_guard(oldval, val, PTE_PFN_MASK);
-	return __pte(val);
+
+	pte_result = __pte(val);
+
+	/*
+	 * To avoid creating Write=0,Dirty=1 PTEs, pte_modify() needs to avoid:
+	 *  1. Marking Write=0 PTEs Dirty=1
+	 *  2. Marking Dirty=1 PTEs Write=0
+	 *
+	 * The first case cannot happen because the _PAGE_CHG_MASK will filter
+	 * out any Dirty bit passed in newprot. Handle the second case by
+	 * going through the mksaveddirty exercise. Only do this if the old
+	 * value was Write=1 to avoid doing this on Shadow Stack PTEs.
+	 */
+	if (oldval & _PAGE_RW)
+		pte_result = pte_mksaveddirty(pte_result);
+	else
+		pte_result = pte_clear_saveddirty(pte_result);
+
+	return pte_result;
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
 	pmdval_t val = pmd_val(pmd), oldval = val;
+	pmd_t pmd_result;
 
-	val &= _HPAGE_CHG_MASK;
+	val &= (_HPAGE_CHG_MASK & ~_PAGE_DIRTY);
 	val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK;
 	val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK);
-	return __pmd(val);
+
+	pmd_result = __pmd(val);
+
+	/*
+	 * To avoid creating Write=0,Dirty=1 PMDs, pte_modify() needs to avoid:
+	 *  1. Marking Write=0 PMDs Dirty=1
+	 *  2. Marking Dirty=1 PMDs Write=0
+	 *
+	 * The first case cannot happen because the _PAGE_CHG_MASK will filter
+	 * out any Dirty bit passed in newprot. Handle the second case by
+	 * going through the mksaveddirty exercise. Only do this if the old
+	 * value was Write=1 to avoid doing this on Shadow Stack PTEs.
+	 */
+	if (oldval & _PAGE_RW)
+		pmd_result = pmd_mksaveddirty(pmd_result);
+	else
+		pmd_result = pmd_clear_saveddirty(pmd_result);
+
+	return pmd_result;
 }
 
 /*
@@ -831,7 +1035,14 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
  * (Currently stuck as a macro because of indirect forward reference
  * to linux/mm.h:page_to_nid())
  */
-#define mk_pte(page, pgprot)   pfn_pte(page_to_pfn(page), (pgprot))
+#define mk_pte(page, pgprot)						  \
+({									  \
+	pgprot_t __pgprot = pgprot;					  \
+									  \
+	WARN_ON_ONCE((pgprot_val(__pgprot) & (_PAGE_DIRTY | _PAGE_RW)) == \
+		    _PAGE_DIRTY);					  \
+	pfn_pte(page_to_pfn(page), __pgprot);				  \
+})
 
 static inline int pmd_bad(pmd_t pmd)
 {
@@ -1090,7 +1301,17 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 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);
+	/*
+	 * Avoid accidentally creating shadow stack PTEs
+	 * (Write=0,Dirty=1).  Use cmpxchg() to prevent races with
+	 * the hardware setting Dirty=1.
+	 */
+	pte_t old_pte, new_pte;
+
+	old_pte = READ_ONCE(*ptep);
+	do {
+		new_pte = pte_wrprotect(old_pte);
+	} while (!try_cmpxchg((long *)&ptep->pte, (long *)&old_pte, *(long *)&new_pte));
 }
 
 #define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0)
@@ -1116,12 +1337,6 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
 				  unsigned long address, pmd_t *pmdp);
 
 
-#define pmd_write pmd_write
-static inline int pmd_write(pmd_t pmd)
-{
-	return pmd_flags(pmd) & _PAGE_RW;
-}
-
 #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr,
 				       pmd_t *pmdp)
@@ -1148,13 +1363,17 @@ static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
 static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 				      unsigned long addr, pmd_t *pmdp)
 {
-	clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
-}
+	/*
+	 * Avoid accidentally creating shadow stack PTEs
+	 * (Write=0,Dirty=1).  Use cmpxchg() to prevent races with
+	 * the hardware setting Dirty=1.
+	 */
+	pmd_t old_pmd, new_pmd;
 
-#define pud_write pud_write
-static inline int pud_write(pud_t pud)
-{
-	return pud_flags(pud) & _PAGE_RW;
+	old_pmd = READ_ONCE(*pmdp);
+	do {
+		new_pmd = pmd_wrprotect(old_pmd);
+	} while (!try_cmpxchg((long *)pmdp, (long *)&old_pmd, *(long *)&new_pmd));
 }
 
 #ifndef pmdp_establish
@@ -1412,6 +1631,11 @@ static inline bool __pte_access_permitted(unsigned long pteval, bool write)
 {
 	unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER;
 
+	/*
+	 * Write=0,Dirty=1 PTEs are shadow stack, which the kernel
+	 * shouldn't generally allow access to, but since they
+	 * are already Write=0, the below logic covers both cases.
+	 */
 	if (write)
 		need_pte_bits |= _PAGE_RW;
 
@@ -1453,6 +1677,12 @@ static inline bool arch_has_hw_pte_young(void)
 	return true;
 }
 
+#define arch_check_zapped_pte arch_check_zapped_pte
+void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte);
+
+#define arch_check_zapped_pmd arch_check_zapped_pmd
+void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd);
+
 #ifdef CONFIG_XEN_PV
 #define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young
 static inline bool arch_has_hw_nonleaf_pmd_young(void)