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
  ...

5 files changed, 73 insertions, 8 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 20e6d1dde412..bf5d0b1b16f4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -319,11 +319,13 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_HIGH_ARCH_BIT_2	34	/* bit only usable on 64-bit architectures */
 #define VM_HIGH_ARCH_BIT_3	35	/* bit only usable on 64-bit architectures */
 #define VM_HIGH_ARCH_BIT_4	36	/* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_BIT_5	37	/* bit only usable on 64-bit architectures */
 #define VM_HIGH_ARCH_0	BIT(VM_HIGH_ARCH_BIT_0)
 #define VM_HIGH_ARCH_1	BIT(VM_HIGH_ARCH_BIT_1)
 #define VM_HIGH_ARCH_2	BIT(VM_HIGH_ARCH_BIT_2)
 #define VM_HIGH_ARCH_3	BIT(VM_HIGH_ARCH_BIT_3)
 #define VM_HIGH_ARCH_4	BIT(VM_HIGH_ARCH_BIT_4)
+#define VM_HIGH_ARCH_5	BIT(VM_HIGH_ARCH_BIT_5)
 #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */
 
 #ifdef CONFIG_ARCH_HAS_PKEYS
@@ -339,6 +341,21 @@ extern unsigned int kobjsize(const void *objp);
 #endif
 #endif /* CONFIG_ARCH_HAS_PKEYS */
 
+#ifdef CONFIG_X86_USER_SHADOW_STACK
+/*
+ * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of
+ * support core mm.
+ *
+ * These VMAs will get a single end guard page. This helps userspace protect
+ * itself from attacks. A single page is enough for current shadow stack archs
+ * (x86). See the comments near alloc_shstk() in arch/x86/kernel/shstk.c
+ * for more details on the guard size.
+ */
+# define VM_SHADOW_STACK	VM_HIGH_ARCH_5
+#else
+# define VM_SHADOW_STACK	VM_NONE
+#endif
+
 #if defined(CONFIG_X86)
 # define VM_PAT		VM_ARCH_1	/* PAT reserves whole VMA at once (x86) */
 #elif defined(CONFIG_PPC)
@@ -370,7 +387,7 @@ extern unsigned int kobjsize(const void *objp);
 #endif
 
 #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
-# define VM_UFFD_MINOR_BIT	37
+# define VM_UFFD_MINOR_BIT	38
 # define VM_UFFD_MINOR		BIT(VM_UFFD_MINOR_BIT)	/* UFFD minor faults */
 #else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
 # define VM_UFFD_MINOR		VM_NONE
@@ -397,6 +414,8 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
 #endif
 
+#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK)
+
 #ifdef CONFIG_STACK_GROWSUP
 #define VM_STACK	VM_GROWSUP
 #define VM_STACK_EARLY	VM_GROWSDOWN
@@ -1309,7 +1328,7 @@ static inline unsigned long thp_size(struct page *page)
 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);
+		pte = pte_mkwrite(pte, vma);
 	return pte;
 }
 
@@ -3265,7 +3284,8 @@ extern unsigned long mmap_region(struct file *file, unsigned long addr,
 	struct list_head *uf);
 extern unsigned long do_mmap(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long prot, unsigned long flags,
-	unsigned long pgoff, unsigned long *populate, struct list_head *uf);
+	vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate,
+	struct list_head *uf);
 extern int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm,
 			 unsigned long start, size_t len, struct list_head *uf,
 			 bool unlock);
@@ -3353,15 +3373,26 @@ struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr)
 	return mtree_load(&mm->mm_mt, addr);
 }
 
+static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_GROWSDOWN)
+		return stack_guard_gap;
+
+	/* See reasoning around the VM_SHADOW_STACK definition */
+	if (vma->vm_flags & VM_SHADOW_STACK)
+		return PAGE_SIZE;
+
+	return 0;
+}
+
 static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
 {
+	unsigned long gap = stack_guard_start_gap(vma);
 	unsigned long vm_start = vma->vm_start;
 
-	if (vma->vm_flags & VM_GROWSDOWN) {
-		vm_start -= stack_guard_gap;
-		if (vm_start > vma->vm_start)
-			vm_start = 0;
-	}
+	vm_start -= gap;
+	if (vm_start > vma->vm_start)
+		vm_start = 0;
 	return vm_start;
 }
 
diff --git a/include/linux/mman.h b/include/linux/mman.h
index cee1e4b566d8..40d94411d492 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -15,6 +15,9 @@
 #ifndef MAP_32BIT
 #define MAP_32BIT 0
 #endif
+#ifndef MAP_ABOVE4G
+#define MAP_ABOVE4G 0
+#endif
 #ifndef MAP_HUGE_2MB
 #define MAP_HUGE_2MB 0
 #endif
@@ -50,6 +53,7 @@
 		| MAP_STACK \
 		| MAP_HUGETLB \
 		| MAP_32BIT \
+		| MAP_ABOVE4G \
 		| MAP_HUGE_2MB \
 		| MAP_HUGE_1GB)
 
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index f49abcfe5eda..1fba072b3dac 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -371,6 +371,20 @@ static inline bool arch_has_hw_pte_young(void)
 }
 #endif
 
+#ifndef arch_check_zapped_pte
+static inline void arch_check_zapped_pte(struct vm_area_struct *vma,
+					 pte_t pte)
+{
+}
+#endif
+
+#ifndef arch_check_zapped_pmd
+static inline void arch_check_zapped_pmd(struct vm_area_struct *vma,
+					 pmd_t pmd)
+{
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 				       unsigned long address,
@@ -577,6 +591,20 @@ extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma,
 			      pud_t *pudp);
 #endif
 
+#ifndef pte_mkwrite
+static inline pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma)
+{
+	return pte_mkwrite_novma(pte);
+}
+#endif
+
+#if defined(CONFIG_ARCH_WANT_PMD_MKWRITE) && !defined(pmd_mkwrite)
+static inline pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
+{
+	return pmd_mkwrite_novma(pmd);
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT
 struct mm_struct;
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 253f2676d93a..de407e7c3b55 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -159,6 +159,7 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns,
 #endif /* CONFIG_PROC_PID_ARCH_STATUS */
 
 void arch_report_meminfo(struct seq_file *m);
+void arch_proc_pid_thread_features(struct seq_file *m, struct task_struct *task);
 
 #else /* CONFIG_PROC_FS */
 
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index c0cb22cd607d..22bc6bc147f8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -939,6 +939,7 @@ asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long l
 asmlinkage long sys_cachestat(unsigned int fd,
 		struct cachestat_range __user *cstat_range,
 		struct cachestat __user *cstat, unsigned int flags);
+asmlinkage long sys_map_shadow_stack(unsigned long addr, unsigned long size, unsigned int flags);
 
 /*
  * Architecture-specific system calls