[PATCH v19 25/25] mm: Introduce PROT_SHSTK 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_SHSTK to mmap()/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_SHSTK to mmap()/mprotect() takes advantage of
existing APIs.  The x86-specific PROT_SHSTK is translated to VM_SHSTK 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.

Since arch_calc_vm_prot_bits() is modified, I have moved arch_vm_get_page
_prot() and arch_calc_vm_prot_bits() to x86/include/asm/mman.h.
This will be more consistent with other architectures.

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

Signed-off-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
---
 arch/x86/include/asm/mman.h      | 85 ++++++++++++++++++++++++++++++++
 arch/x86/include/uapi/asm/mman.h | 28 ++---------
 include/linux/mm.h               |  1 +
 mm/mmap.c                        |  8 ++-
 4 files changed, 97 insertions(+), 25 deletions(-)
 create mode 100644 arch/x86/include/asm/mman.h

diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
new file mode 100644
index 000000000000..db897d14fc37
--- /dev/null
+++ b/arch/x86/include/asm/mman.h
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_MMAN_H
+#define _ASM_X86_MMAN_H
+
+#include <linux/mm.h>
+#include <uapi/asm/mman.h>
+
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+/*
+ * Take the 4 protection key bits out of the vma->vm_flags
+ * value and turn them in to the bits that we can put in
+ * to a pte.
+ *
+ * Only override these if Protection Keys are available
+ * (which is only on 64-bit).
+ */
+#define arch_vm_get_page_prot(vm_flags)	__pgprot(	\
+		((vm_flags) & VM_PKEY_BIT0 ? _PAGE_PKEY_BIT0 : 0) |	\
+		((vm_flags) & VM_PKEY_BIT1 ? _PAGE_PKEY_BIT1 : 0) |	\
+		((vm_flags) & VM_PKEY_BIT2 ? _PAGE_PKEY_BIT2 : 0) |	\
+		((vm_flags) & VM_PKEY_BIT3 ? _PAGE_PKEY_BIT3 : 0))
+
+#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_WRITE) && (prot & PROT_SHSTK))
+		vm_prot_bits |= VM_SHSTK;
+
+	return vm_prot_bits;
+}
+
+#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
+
+#ifdef CONFIG_X86_CET
+static inline bool arch_validate_prot(unsigned long prot, unsigned long addr)
+{
+	unsigned long valid = PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM;
+
+	if (prot & ~(valid | PROT_SHSTK))
+		return false;
+
+	if (prot & PROT_SHSTK) {
+		struct vm_area_struct *vma;
+
+		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_SHSTK and PROT_WRITE are mutually
+		 * exclusive.
+		 */
+		if (prot & PROT_WRITE)
+			return false;
+
+		vma = find_vma(current->mm, addr);
+		if (!vma)
+			return false;
+
+		/*
+		 * Shadow stack cannot be backed by a file or shared.
+		 */
+		if (vma->vm_file || (vma->vm_flags & VM_SHARED))
+			return false;
+	}
+
+	return true;
+}
+
+#define arch_validate_prot arch_validate_prot
+#endif
+
+#endif /* _ASM_X86_MMAN_H */
diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h
index d4a8d0424bfb..39bb7db344a6 100644
--- a/arch/x86/include/uapi/asm/mman.h
+++ b/arch/x86/include/uapi/asm/mman.h
@@ -1,31 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_X86_MMAN_H
-#define _ASM_X86_MMAN_H
+#ifndef _UAPI_ASM_X86_MMAN_H
+#define _UAPI_ASM_X86_MMAN_H
 
 #define MAP_32BIT	0x40		/* only give out 32bit addresses */
 
-#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-/*
- * Take the 4 protection key bits out of the vma->vm_flags
- * value and turn them in to the bits that we can put in
- * to a pte.
- *
- * Only override these if Protection Keys are available
- * (which is only on 64-bit).
- */
-#define arch_vm_get_page_prot(vm_flags)	__pgprot(	\
-		((vm_flags) & VM_PKEY_BIT0 ? _PAGE_PKEY_BIT0 : 0) |	\
-		((vm_flags) & VM_PKEY_BIT1 ? _PAGE_PKEY_BIT1 : 0) |	\
-		((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) (		\
-		((key) & 0x1 ? VM_PKEY_BIT0 : 0) |      \
-		((key) & 0x2 ? VM_PKEY_BIT1 : 0) |      \
-		((key) & 0x4 ? VM_PKEY_BIT2 : 0) |      \
-		((key) & 0x8 ? VM_PKEY_BIT3 : 0))
-#endif
+#define PROT_SHSTK	0x10		/* shadow stack pages */
 
 #include <asm-generic/mman.h>
 
-#endif /* _ASM_X86_MMAN_H */
+#endif /* _UAPI_ASM_X86_MMAN_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 06e9899e13b8..f3a3b6be97e2 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_SHSTK
 #elif defined(CONFIG_PPC)
 # define VM_SAO		VM_ARCH_1	/* Strong Access Ordering (powerpc) */
 #elif defined(CONFIG_PARISC)
diff --git a/mm/mmap.c b/mm/mmap.c
index 95ce7cd68654..9434469db2ce 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1483,6 +1483,12 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 		struct inode *inode = file_inode(file);
 		unsigned long flags_mask;
 
+		/*
+		 * Call stack cannot be backed by a file.
+		 */
+		if (vm_flags & VM_SHSTK)
+			return -EINVAL;
+
 		if (!file_mmap_ok(file, inode, pgoff, len))
 			return -EOVERFLOW;
 
@@ -1547,7 +1553,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 	} else {
 		switch (flags & MAP_TYPE) {
 		case MAP_SHARED:
-			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
+			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP|VM_SHSTK))
 				return -EINVAL;
 			/*
 			 * Ignore pgoff.
-- 
2.21.0