[PATCH v26 30/30] mm: Introduce PROT_SHADOW_STACK for shadow stack

[Yu-cheng Yu]

There are three possible options to create a shadow stack allocation API:
an arch_prctl, a new syscall, or adding PROT_SHADOW_STACK to mmap() and
mprotect().  Each has its advantages and compromises.

An arch_prctl() is the least intrusive.  However, the existing x86
arch_prctl() takes only two parameters.  Multiple parameters must be
passed in a memory buffer.  There is a proposal to pass more parameters in
registers [1], but no active discussion on that.

A new syscall minimizes compatibility issues and offers an extensible frame
work to other architectures, but this will likely result in some overlap of
mmap()/mprotect().

The introduction of PROT_SHADOW_STACK to mmap()/mprotect() takes advantage
of existing APIs.  The x86-specific PROT_SHADOW_STACK is translated to
VM_SHADOW_STACK and a shadow stack mapping is created without reinventing
the wheel.  There are potential pitfalls though.  The most obvious one
would be using this as a bypass to shadow stack protection.  However, the
attacker would have to get to the syscall first.

[1] https://lore.kernel.org/lkml/20200828121624.108243-1-hjl.tools@xxxxxxxxx/

Signed-off-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
---
v26:
- Change PROT_SHSTK to PROT_SHADOW_STACK.
- Remove (vm_flags & VM_SHARED) check, since it is covered by
  !vma_is_anonymous().

v24:
- Update arch_calc_vm_prot_bits(), leave PROT* checking to
  arch_validate_prot().
- Update arch_validate_prot(), leave vma flags checking to
  arch_validate_flags().
- Add arch_validate_flags().

 arch/x86/include/asm/mman.h      | 60 +++++++++++++++++++++++++++++++-
 arch/x86/include/uapi/asm/mman.h |  2 ++
 include/linux/mm.h               |  1 +
 3 files changed, 62 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
index 629f6c81263a..fbb90f1b02c0 100644
--- a/arch/x86/include/asm/mman.h
+++ b/arch/x86/include/asm/mman.h
@@ -20,11 +20,69 @@
 		((vm_flags) & VM_PKEY_BIT2 ? _PAGE_PKEY_BIT2 : 0) |	\
 		((vm_flags) & VM_PKEY_BIT3 ? _PAGE_PKEY_BIT3 : 0))
 
-#define arch_calc_vm_prot_bits(prot, key) (		\
+#define pkey_vm_prot_bits(prot, key) (			\
 		((key) & 0x1 ? VM_PKEY_BIT0 : 0) |      \
 		((key) & 0x2 ? VM_PKEY_BIT1 : 0) |      \
 		((key) & 0x4 ? VM_PKEY_BIT2 : 0) |      \
 		((key) & 0x8 ? VM_PKEY_BIT3 : 0))
+#else
+#define pkey_vm_prot_bits(prot, key) (0)
 #endif
 
+static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
+						   unsigned long pkey)
+{
+	unsigned long vm_prot_bits = pkey_vm_prot_bits(prot, pkey);
+
+	if (prot & PROT_SHADOW_STACK)
+		vm_prot_bits |= VM_SHADOW_STACK;
+
+	return vm_prot_bits;
+}
+
+#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
+
+#ifdef CONFIG_X86_SHADOW_STACK
+static inline bool arch_validate_prot(unsigned long prot, unsigned long addr)
+{
+	unsigned long valid = PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM |
+			      PROT_SHADOW_STACK;
+
+	if (prot & ~valid)
+		return false;
+
+	if (prot & PROT_SHADOW_STACK) {
+		if (!current->thread.cet.shstk_size)
+			return false;
+
+		/*
+		 * A shadow stack mapping is indirectly writable by only
+		 * the CALL and WRUSS instructions, but not other write
+		 * instructions).  PROT_SHADOW_STACK and PROT_WRITE are
+		 * mutually exclusive.
+		 */
+		if (prot & PROT_WRITE)
+			return false;
+	}
+
+	return true;
+}
+
+#define arch_validate_prot arch_validate_prot
+
+static inline bool arch_validate_flags(struct vm_area_struct *vma, unsigned long vm_flags)
+{
+	/*
+	 * Shadow stack must be anonymous and not shared.
+	 */
+	if ((vm_flags & VM_SHADOW_STACK) && !vma_is_anonymous(vma))
+		return false;
+
+	return true;
+}
+
+#define arch_validate_flags(vma, vm_flags) arch_validate_flags(vma, vm_flags)
+
+#endif /* CONFIG_X86_SHADOW_STACK */
+
 #endif /* _ASM_X86_MMAN_H */
diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h
index f28fa4acaeaf..4c36b263cf0a 100644
--- a/arch/x86/include/uapi/asm/mman.h
+++ b/arch/x86/include/uapi/asm/mman.h
@@ -4,6 +4,8 @@
 
 #define MAP_32BIT	0x40		/* only give out 32bit addresses */
 
+#define PROT_SHADOW_STACK	0x10	/* shadow stack pages */
+
 #include <asm-generic/mman.h>
 
 #endif /* _UAPI_ASM_X86_MMAN_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1ccec5cc399b..9a7652eea207 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -342,6 +342,7 @@ extern unsigned int kobjsize(const void *objp);
 
 #if defined(CONFIG_X86)
 # define VM_PAT		VM_ARCH_1	/* PAT reserves whole VMA at once (x86) */
+# define VM_ARCH_CLEAR	VM_SHADOW_STACK
 #elif defined(CONFIG_PPC)
 # define VM_SAO		VM_ARCH_1	/* Strong Access Ordering (powerpc) */
 #elif defined(CONFIG_PARISC)
-- 
2.21.0