diff mbox series

[v25,30/30] mm: Introduce PROT_SHSTK for shadow stack

Message ID 20210415221419.31835-31-yu-cheng.yu@intel.com (mailing list archive)
State New
Headers show
Series Control-flow Enforcement: Shadow Stack | expand

Commit Message

Yu, Yu-cheng April 15, 2021, 10:14 p.m. UTC
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_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@gmail.com/

Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
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      | 59 +++++++++++++++++++++++++++++++-
 arch/x86/include/uapi/asm/mman.h |  1 +
 include/linux/mm.h               |  1 +
 3 files changed, 60 insertions(+), 1 deletion(-)

Comments

Kirill A. Shutemov April 26, 2021, 6:52 a.m. UTC | #1
On Thu, Apr 15, 2021 at 03:14:19PM -0700, Yu-cheng Yu wrote:
> 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

Maybe PROT_SHADOW_STACK?

> existing APIs.  The x86-specific PROT_SHSTK 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@gmail.com/
> 
> Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
> Cc: Kees Cook <keescook@chromium.org>
> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> ---
> 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      | 59 +++++++++++++++++++++++++++++++-
>  arch/x86/include/uapi/asm/mman.h |  1 +
>  include/linux/mm.h               |  1 +
>  3 files changed, 60 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
> index 629f6c81263a..1821c179f35d 100644
> --- a/arch/x86/include/asm/mman.h
> +++ b/arch/x86/include/asm/mman.h
> @@ -20,11 +20,68 @@
>  		((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_SHSTK)
> +		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_SHSTK;
> +
> +	if (prot & ~valid)
> +		return false;
> +
> +	if (prot & PROT_SHSTK) {
> +		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;
> +	}
> +
> +	return true;
> +}
> +
> +#define arch_validate_prot arch_validate_prot
> +
> +static inline bool arch_validate_flags(unsigned long vm_flags, bool is_anon)
> +{
> +	if (vm_flags & VM_SHADOW_STACK) {
> +		if ((vm_flags & VM_SHARED) || !is_anon)

VM_SHARED check is redundant. vma_is_anonymous() should be enough.
Anonymous shared mappings would fail vma_is_anonymous().

> +			return false;
> +	}
> +
> +	return true;
> +}
> +
> +#define arch_validate_flags(vm_flags, is_anon) arch_validate_flags(vm_flags, is_anon)
> +
> +#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 3ce1923e6ed9..39bb7db344a6 100644
> --- a/arch/x86/include/uapi/asm/mman.h
> +++ b/arch/x86/include/uapi/asm/mman.h
> @@ -4,6 +4,7 @@
>  
>  #define MAP_32BIT	0x40		/* only give out 32bit addresses */
>  
> +#define PROT_SHSTK	0x10		/* shadow stack pages */
>  
>  #include <asm-generic/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
> 
>
Yu, Yu-cheng April 26, 2021, 6 p.m. UTC | #2
On 4/25/2021 11:52 PM, Kirill A. Shutemov wrote:
> On Thu, Apr 15, 2021 at 03:14:19PM -0700, Yu-cheng Yu wrote:
>> 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
> 
> Maybe PROT_SHADOW_STACK?
> 
>> existing APIs.  The x86-specific PROT_SHSTK 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@gmail.com/
>>
>> Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
>> Cc: Kees Cook <keescook@chromium.org>
>> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
>> ---
>> 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      | 59 +++++++++++++++++++++++++++++++-
>>   arch/x86/include/uapi/asm/mman.h |  1 +
>>   include/linux/mm.h               |  1 +
>>   3 files changed, 60 insertions(+), 1 deletion(-)
>>
>> diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
>> index 629f6c81263a..1821c179f35d 100644
>> --- a/arch/x86/include/asm/mman.h
>> +++ b/arch/x86/include/asm/mman.h

[...]

>> +
>> +#define arch_validate_prot arch_validate_prot
>> +
>> +static inline bool arch_validate_flags(unsigned long vm_flags, bool is_anon)
>> +{
>> +	if (vm_flags & VM_SHADOW_STACK) {
>> +		if ((vm_flags & VM_SHARED) || !is_anon)
> 
> VM_SHARED check is redundant. vma_is_anonymous() should be enough.
> Anonymous shared mappings would fail vma_is_anonymous().
>

Thanks for looking into this.  I will update and send another version.

Yu-cheng
diff mbox series

Patch

diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
index 629f6c81263a..1821c179f35d 100644
--- a/arch/x86/include/asm/mman.h
+++ b/arch/x86/include/asm/mman.h
@@ -20,11 +20,68 @@ 
 		((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_SHSTK)
+		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_SHSTK;
+
+	if (prot & ~valid)
+		return false;
+
+	if (prot & PROT_SHSTK) {
+		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;
+	}
+
+	return true;
+}
+
+#define arch_validate_prot arch_validate_prot
+
+static inline bool arch_validate_flags(unsigned long vm_flags, bool is_anon)
+{
+	if (vm_flags & VM_SHADOW_STACK) {
+		if ((vm_flags & VM_SHARED) || !is_anon)
+			return false;
+	}
+
+	return true;
+}
+
+#define arch_validate_flags(vm_flags, is_anon) arch_validate_flags(vm_flags, is_anon)
+
+#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 3ce1923e6ed9..39bb7db344a6 100644
--- a/arch/x86/include/uapi/asm/mman.h
+++ b/arch/x86/include/uapi/asm/mman.h
@@ -4,6 +4,7 @@ 
 
 #define MAP_32BIT	0x40		/* only give out 32bit addresses */
 
+#define PROT_SHSTK	0x10		/* shadow stack pages */
 
 #include <asm-generic/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)