x86, smap: Add STAC and CLAC instructions to control user space access

When Supervisor Mode Access Prevention (SMAP) is enabled, access to
userspace from the kernel is controlled by the AC flag.  To make the
performance of manipulating that flag acceptable, there are two new
instructions, STAC and CLAC, to set and clear it.

This patch adds those instructions, via alternative(), when the SMAP
feature is enabled.  It also adds X86_EFLAGS_AC unconditionally to the
SYSCALL entry mask; there is simply no reason to make that one
conditional.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/r/1348256595-29119-9-git-send-email-hpa@linux.intel.com

6 files changed, 42 insertions, 2 deletions

diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 5b2995f4557a..a30ca15be21c 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -17,6 +17,7 @@
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 #include <asm/asm.h>
+#include <asm/smap.h>
 
 /*
  * By placing feature2 after feature1 in altinstructions section, we logically
@@ -130,6 +131,7 @@ ENDPROC(bad_from_user)
  */
 ENTRY(copy_user_generic_unrolled)
         CFI_STARTPROC
+        ASM_STAC
         cmpl $8,%edx
         jb 20f          /* less then 8 bytes, go to byte copy loop */
         ALIGN_DESTINATION
@@ -177,6 +179,7 @@ ENTRY(copy_user_generic_unrolled)
         decl %ecx
         jnz 21b
 23:     xor %eax,%eax
+        ASM_CLAC
         ret
 
         .section .fixup,"ax"
@@ -232,6 +235,7 @@ ENDPROC(copy_user_generic_unrolled)
  */
 ENTRY(copy_user_generic_string)
         CFI_STARTPROC
+        ASM_STAC
         andl %edx,%edx
         jz 4f
         cmpl $8,%edx
@@ -246,6 +250,7 @@ ENTRY(copy_user_generic_string)
 3:      rep
         movsb
 4:      xorl %eax,%eax
+        ASM_CLAC
         ret
 
         .section .fixup,"ax"
@@ -273,12 +278,14 @@ ENDPROC(copy_user_generic_string)
  */
 ENTRY(copy_user_enhanced_fast_string)
         CFI_STARTPROC
+        ASM_STAC
         andl %edx,%edx
         jz 2f
         movl %edx,%ecx
 1:      rep
         movsb
 2:      xorl %eax,%eax
+        ASM_CLAC
         ret
 
         .section .fixup,"ax"
diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S
index cacddc7163eb..6a4f43c2d9e6 100644
--- a/arch/x86/lib/copy_user_nocache_64.S
+++ b/arch/x86/lib/copy_user_nocache_64.S
@@ -15,6 +15,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/asm.h>
+#include <asm/smap.h>
 
         .macro ALIGN_DESTINATION
 #ifdef FIX_ALIGNMENT
@@ -48,6 +49,7 @@
  */
 ENTRY(__copy_user_nocache)
         CFI_STARTPROC
+        ASM_STAC
         cmpl $8,%edx
         jb 20f          /* less then 8 bytes, go to byte copy loop */
         ALIGN_DESTINATION
@@ -95,6 +97,7 @@ ENTRY(__copy_user_nocache)
         decl %ecx
         jnz 21b
 23:     xorl %eax,%eax
+        ASM_CLAC
         sfence
         ret
 
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index b33b1fb1e6d4..156b9c804670 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -33,6 +33,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/asm.h>
+#include <asm/smap.h>
 
         .text
 ENTRY(__get_user_1)
@@ -40,8 +41,10 @@ ENTRY(__get_user_1)
         GET_THREAD_INFO(%_ASM_DX)
         cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
         jae bad_get_user
+        ASM_STAC
 1:      movzb (%_ASM_AX),%edx
         xor %eax,%eax
+        ASM_CLAC
         ret
         CFI_ENDPROC
 ENDPROC(__get_user_1)
@@ -53,8 +56,10 @@ ENTRY(__get_user_2)
         GET_THREAD_INFO(%_ASM_DX)
         cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
         jae bad_get_user
+        ASM_STAC
 2:      movzwl -1(%_ASM_AX),%edx
         xor %eax,%eax
+        ASM_CLAC
         ret
         CFI_ENDPROC
 ENDPROC(__get_user_2)
@@ -66,8 +71,10 @@ ENTRY(__get_user_4)
         GET_THREAD_INFO(%_ASM_DX)
         cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
         jae bad_get_user
+        ASM_STAC
 3:      mov -3(%_ASM_AX),%edx
         xor %eax,%eax
+        ASM_CLAC
         ret
         CFI_ENDPROC
 ENDPROC(__get_user_4)
@@ -80,8 +87,10 @@ ENTRY(__get_user_8)
         GET_THREAD_INFO(%_ASM_DX)
         cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
         jae     bad_get_user
+        ASM_STAC
 4:      movq -7(%_ASM_AX),%_ASM_DX
         xor %eax,%eax
+        ASM_CLAC
         ret
         CFI_ENDPROC
 ENDPROC(__get_user_8)
@@ -91,6 +100,7 @@ bad_get_user:
         CFI_STARTPROC
         xor %edx,%edx
         mov $(-EFAULT),%_ASM_AX
+        ASM_CLAC
         ret
         CFI_ENDPROC
 END(bad_get_user)
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 7f951c8f76c4..fc6ba17a7eec 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -15,6 +15,7 @@
 #include <asm/thread_info.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
+#include <asm/smap.h>
 
 
 /*
@@ -31,7 +32,8 @@
 
 #define ENTER   CFI_STARTPROC ; \
                 GET_THREAD_INFO(%_ASM_BX)
-#define EXIT    ret ; \
+#define EXIT    ASM_CLAC ;      \
+                ret ;           \
                 CFI_ENDPROC
 
 .text
@@ -39,6 +41,7 @@ ENTRY(__put_user_1)
         ENTER
         cmp TI_addr_limit(%_ASM_BX),%_ASM_CX
         jae bad_put_user
+        ASM_STAC
 1:      movb %al,(%_ASM_CX)
         xor %eax,%eax
         EXIT
@@ -50,6 +53,7 @@ ENTRY(__put_user_2)
         sub $1,%_ASM_BX
         cmp %_ASM_BX,%_ASM_CX
         jae bad_put_user
+        ASM_STAC
 2:      movw %ax,(%_ASM_CX)
         xor %eax,%eax
         EXIT
@@ -61,6 +65,7 @@ ENTRY(__put_user_4)
         sub $3,%_ASM_BX
         cmp %_ASM_BX,%_ASM_CX
         jae bad_put_user
+        ASM_STAC
 3:      movl %eax,(%_ASM_CX)
         xor %eax,%eax
         EXIT
@@ -72,6 +77,7 @@ ENTRY(__put_user_8)
         sub $7,%_ASM_BX
         cmp %_ASM_BX,%_ASM_CX
         jae bad_put_user
+        ASM_STAC
 4:      mov %_ASM_AX,(%_ASM_CX)
 #ifdef CONFIG_X86_32
 5:      movl %edx,4(%_ASM_CX)
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 1781b2f950e2..98f6d6b68f5a 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -42,10 +42,11 @@ do {									\
         int __d0;                                                       \
         might_fault();                                                  \
         __asm__ __volatile__(                                           \
+                ASM_STAC "\n"                                           \
                 "0:     rep; stosl\n"                                   \
                 "       movl %2,%0\n"                                   \
                 "1:     rep; stosb\n"                                   \
-                "2:\n"                                                  \
+                "2: " ASM_CLAC "\n"                                     \
                 ".section .fixup,\"ax\"\n"                              \
                 "3:     lea 0(%2,%0,4),%0\n"                            \
                 "       jmp 2b\n"                                       \
@@ -626,10 +627,12 @@ survive:
                 return n;
         }
 #endif
+        stac();
         if (movsl_is_ok(to, from, n))
                 __copy_user(to, from, n);
         else
                 n = __copy_user_intel(to, from, n);
+        clac();
         return n;
 }
 EXPORT_SYMBOL(__copy_to_user_ll);
@@ -637,10 +640,12 @@ EXPORT_SYMBOL(__copy_to_user_ll);
 unsigned long __copy_from_user_ll(void *to, const void __user *from,
                                         unsigned long n)
 {
+        stac();
         if (movsl_is_ok(to, from, n))
                 __copy_user_zeroing(to, from, n);
         else
                 n = __copy_user_zeroing_intel(to, from, n);
+        clac();
         return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll);
@@ -648,11 +653,13 @@ EXPORT_SYMBOL(__copy_from_user_ll);
 unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
                                          unsigned long n)
 {
+        stac();
         if (movsl_is_ok(to, from, n))
                 __copy_user(to, from, n);
         else
                 n = __copy_user_intel((void __user *)to,
                                       (const void *)from, n);
+        clac();
         return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nozero);
@@ -660,6 +667,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nozero);
 unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
                                         unsigned long n)
 {
+        stac();
 #ifdef CONFIG_X86_INTEL_USERCOPY
         if (n > 64 && cpu_has_xmm2)
                 n = __copy_user_zeroing_intel_nocache(to, from, n);
@@ -668,6 +676,7 @@ unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 #else
         __copy_user_zeroing(to, from, n);
 #endif
+        clac();
         return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nocache);
@@ -675,6 +684,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache);
 unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
                                         unsigned long n)
 {
+        stac();
 #ifdef CONFIG_X86_INTEL_USERCOPY
         if (n > 64 && cpu_has_xmm2)
                 n = __copy_user_intel_nocache(to, from, n);
@@ -683,6 +693,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr
 #else
         __copy_user(to, from, n);
 #endif
+        clac();
         return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index e5b130bc2d0e..05928aae911e 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -18,6 +18,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
         might_fault();
         /* no memory constraint because it doesn't change any memory gcc knows
            about */
+        stac();
         asm volatile(
                 "       testq  %[size8],%[size8]\n"
                 "       jz     4f\n"
@@ -40,6 +41,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
                 : [size8] "=&c"(size), [dst] "=&D" (__d0)
                 : [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr),
                   [zero] "r" (0UL), [eight] "r" (8UL));
+        clac();
         return size;
 }
 EXPORT_SYMBOL(__clear_user);
@@ -82,5 +84,6 @@ copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest)
         for (c = 0, zero_len = len; zerorest && zero_len; --zero_len)
                 if (__put_user_nocheck(c, to++, sizeof(char)))
                         break;
+        clac();
         return len;
 }