Merge branch 'x86-smap-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86/smap support from Ingo Molnar:
 "This adds support for the SMAP (Supervisor Mode Access Prevention) CPU
  feature on Intel CPUs: a hardware feature that prevents unintended
  user-space data access from kernel privileged code.

  It's turned on automatically when possible.

  This, in combination with SMEP, makes it even harder to exploit kernel
  bugs such as NULL pointer dereferences."

Fix up trivial conflict in arch/x86/kernel/entry_64.S due to newly added
includes right next to each other.

* 'x86-smap-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, smep, smap: Make the switching functions one-way
  x86, suspend: On wakeup always initialize cr4 and EFER
  x86-32: Start out eflags and cr4 clean
  x86, smap: Do not abuse the [f][x]rstor_checking() functions for user space
  x86-32, smap: Add STAC/CLAC instructions to 32-bit kernel entry
  x86, smap: Reduce the SMAP overhead for signal handling
  x86, smap: A page fault due to SMAP is an oops
  x86, smap: Turn on Supervisor Mode Access Prevention
  x86, smap: Add STAC and CLAC instructions to control user space access
  x86, uaccess: Merge prototypes for clear_user/__clear_user
  x86, smap: Add a header file with macros for STAC/CLAC
  x86, alternative: Add header guards to <asm/alternative-asm.h>
  x86, alternative: Use .pushsection/.popsection
  x86, smap: Add CR4 bit for SMAP
  x86-32, mm: The WP test should be done on a kernel page

10 files changed, 190 insertions, 48 deletions

diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index 952bd0100c5c..372231c22a47 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -1,3 +1,6 @@
+#ifndef _ASM_X86_ALTERNATIVE_ASM_H
+#define _ASM_X86_ALTERNATIVE_ASM_H
+
 #ifdef __ASSEMBLY__
 
 #include <asm/asm.h>
@@ -5,10 +8,10 @@
 #ifdef CONFIG_SMP
 	.macro LOCK_PREFIX
 672:	lock
-	.section .smp_locks,"a"
+	.pushsection .smp_locks,"a"
 	.balign 4
 	.long 672b - .
-	.previous
+	.popsection
 	.endm
 #else
 	.macro LOCK_PREFIX
@@ -24,3 +27,5 @@
 .endm
 
 #endif  /*  __ASSEMBLY__  */
+
+#endif /* _ASM_X86_ALTERNATIVE_ASM_H */
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 444704c8e186..58ed6d96a6ac 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -29,10 +29,10 @@
 
 #ifdef CONFIG_SMP
 #define LOCK_PREFIX_HERE \
-		".section .smp_locks,\"a\"\n"	\
-		".balign 4\n"			\
-		".long 671f - .\n" /* offset */	\
-		".previous\n"			\
+		".pushsection .smp_locks,\"a\"\n"	\
+		".balign 4\n"				\
+		".long 671f - .\n" /* offset */		\
+		".popsection\n"				\
 		"671:"
 
 #define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; "
@@ -99,30 +99,30 @@ static inline int alternatives_text_reserved(void *start, void *end)
 /* alternative assembly primitive: */
 #define ALTERNATIVE(oldinstr, newinstr, feature)			\
 	OLDINSTR(oldinstr)						\
-	".section .altinstructions,\"a\"\n"				\
+	".pushsection .altinstructions,\"a\"\n"				\
 	ALTINSTR_ENTRY(feature, 1)					\
-	".previous\n"							\
-	".section .discard,\"aw\",@progbits\n"				\
+	".popsection\n"							\
+	".pushsection .discard,\"aw\",@progbits\n"			\
 	DISCARD_ENTRY(1)						\
-	".previous\n"							\
-	".section .altinstr_replacement, \"ax\"\n"			\
+	".popsection\n"							\
+	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(newinstr, feature, 1)			\
-	".previous"
+	".popsection"
 
 #define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
 	OLDINSTR(oldinstr)						\
-	".section .altinstructions,\"a\"\n"				\
+	".pushsection .altinstructions,\"a\"\n"				\
 	ALTINSTR_ENTRY(feature1, 1)					\
 	ALTINSTR_ENTRY(feature2, 2)					\
-	".previous\n"							\
-	".section .discard,\"aw\",@progbits\n"				\
+	".popsection\n"							\
+	".pushsection .discard,\"aw\",@progbits\n"			\
 	DISCARD_ENTRY(1)						\
 	DISCARD_ENTRY(2)						\
-	".previous\n"							\
-	".section .altinstr_replacement, \"ax\"\n"			\
+	".popsection\n"							\
+	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(newinstr1, feature1, 1)			\
 	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
-	".previous"
+	".popsection"
 
 /*
  * This must be included *after* the definition of ALTERNATIVE due to
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 92f3c6ed817f..831dbb9c6c02 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -21,6 +21,7 @@
 #include <asm/user.h>
 #include <asm/uaccess.h>
 #include <asm/xsave.h>
+#include <asm/smap.h>
 
 #ifdef CONFIG_X86_64
 # include <asm/sigcontext32.h>
@@ -121,6 +122,22 @@ static inline void sanitize_i387_state(struct task_struct *tsk)
 	__sanitize_i387_state(tsk);
 }
 
+#define user_insn(insn, output, input...)				\
+({									\
+	int err;							\
+	asm volatile(ASM_STAC "\n"					\
+		     "1:" #insn "\n\t"					\
+		     "2: " ASM_CLAC "\n"				\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:  movl $-1,%[err]\n"				\
+		     "    jmp  2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err), output				\
+		     : "0"(0), input);					\
+	err;								\
+})
+
 #define check_insn(insn, output, input...)				\
 ({									\
 	int err;							\
@@ -138,18 +155,18 @@ static inline void sanitize_i387_state(struct task_struct *tsk)
 
 static inline int fsave_user(struct i387_fsave_struct __user *fx)
 {
-	return check_insn(fnsave %[fx]; fwait,  [fx] "=m" (*fx), "m" (*fx));
+	return user_insn(fnsave %[fx]; fwait,  [fx] "=m" (*fx), "m" (*fx));
 }
 
 static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 {
 	if (config_enabled(CONFIG_X86_32))
-		return check_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+		return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
 	else if (config_enabled(CONFIG_AS_FXSAVEQ))
-		return check_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
+		return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
 
 	/* See comment in fpu_fxsave() below. */
-	return check_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
+	return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
 }
 
 static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
@@ -164,11 +181,28 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 			  "m" (*fx));
 }
 
+static inline int fxrstor_user(struct i387_fxsave_struct __user *fx)
+{
+	if (config_enabled(CONFIG_X86_32))
+		return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+
+	/* See comment in fpu_fxsave() below. */
+	return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
+			  "m" (*fx));
+}
+
 static inline int frstor_checking(struct i387_fsave_struct *fx)
 {
 	return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 }
 
+static inline int frstor_user(struct i387_fsave_struct __user *fx)
+{
+	return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
 static inline void fpu_fxsave(struct fpu *fpu)
 {
 	if (config_enabled(CONFIG_X86_32))
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index 71ecbcba1a4e..f373046e63ec 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -9,10 +9,13 @@
 #include <asm/asm.h>
 #include <asm/errno.h>
 #include <asm/processor.h>
+#include <asm/smap.h>
 
 #define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg)	\
-	asm volatile("1:\t" insn "\n"				\
-		     "2:\t.section .fixup,\"ax\"\n"		\
+	asm volatile("\t" ASM_STAC "\n"				\
+		     "1:\t" insn "\n"				\
+		     "2:\t" ASM_CLAC "\n"			\
+		     "\t.section .fixup,\"ax\"\n"		\
 		     "3:\tmov\t%3, %1\n"			\
 		     "\tjmp\t2b\n"				\
 		     "\t.previous\n"				\
@@ -21,12 +24,14 @@
 		     : "i" (-EFAULT), "0" (oparg), "1" (0))
 
 #define __futex_atomic_op2(insn, ret, oldval, uaddr, oparg)	\
-	asm volatile("1:\tmovl	%2, %0\n"			\
+	asm volatile("\t" ASM_STAC "\n"				\
+		     "1:\tmovl	%2, %0\n"			\
 		     "\tmovl\t%0, %3\n"				\
 		     "\t" insn "\n"				\
 		     "2:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"	\
 		     "\tjnz\t1b\n"				\
-		     "3:\t.section .fixup,\"ax\"\n"		\
+		     "3:\t" ASM_CLAC "\n"			\
+		     "\t.section .fixup,\"ax\"\n"		\
 		     "4:\tmov\t%5, %1\n"			\
 		     "\tjmp\t3b\n"				\
 		     "\t.previous\n"				\
@@ -122,8 +127,10 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
-		     "2:\t.section .fixup, \"ax\"\n"
+	asm volatile("\t" ASM_STAC "\n"
+		     "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
+		     "2:\t" ASM_CLAC "\n"
+		     "\t.section .fixup, \"ax\"\n"
 		     "3:\tmov     %3, %0\n"
 		     "\tjmp     2b\n"
 		     "\t.previous\n"
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index aea1d1d848c7..680cf09ed100 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -65,6 +65,7 @@
 #define X86_CR4_PCIDE	0x00020000 /* enable PCID support */
 #define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */
 #define X86_CR4_SMEP	0x00100000 /* enable SMEP support */
+#define X86_CR4_SMAP	0x00200000 /* enable SMAP support */
 
 /*
  * x86-64 Task Priority Register, CR8
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
new file mode 100644
index 000000000000..8d3120f4e270
--- /dev/null
+++ b/arch/x86/include/asm/smap.h
@@ -0,0 +1,91 @@
+/*
+ * Supervisor Mode Access Prevention support
+ *
+ * Copyright (C) 2012 Intel Corporation
+ * Author: H. Peter Anvin <hpa@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#ifndef _ASM_X86_SMAP_H
+#define _ASM_X86_SMAP_H
+
+#include <linux/stringify.h>
+#include <asm/nops.h>
+#include <asm/cpufeature.h>
+
+/* "Raw" instruction opcodes */
+#define __ASM_CLAC	.byte 0x0f,0x01,0xca
+#define __ASM_STAC	.byte 0x0f,0x01,0xcb
+
+#ifdef __ASSEMBLY__
+
+#include <asm/alternative-asm.h>
+
+#ifdef CONFIG_X86_SMAP
+
+#define ASM_CLAC							\
+	661: ASM_NOP3 ;							\
+	.pushsection .altinstr_replacement, "ax" ;			\
+	662: __ASM_CLAC ;						\
+	.popsection ;							\
+	.pushsection .altinstructions, "a" ;				\
+	altinstruction_entry 661b, 662b, X86_FEATURE_SMAP, 3, 3 ;	\
+	.popsection
+
+#define ASM_STAC							\
+	661: ASM_NOP3 ;							\
+	.pushsection .altinstr_replacement, "ax" ;			\
+	662: __ASM_STAC ;						\
+	.popsection ;							\
+	.pushsection .altinstructions, "a" ;				\
+	altinstruction_entry 661b, 662b, X86_FEATURE_SMAP, 3, 3 ;	\
+	.popsection
+
+#else /* CONFIG_X86_SMAP */
+
+#define ASM_CLAC
+#define ASM_STAC
+
+#endif /* CONFIG_X86_SMAP */
+
+#else /* __ASSEMBLY__ */
+
+#include <asm/alternative.h>
+
+#ifdef CONFIG_X86_SMAP
+
+static __always_inline void clac(void)
+{
+	/* Note: a barrier is implicit in alternative() */
+	alternative(ASM_NOP3, __stringify(__ASM_CLAC), X86_FEATURE_SMAP);
+}
+
+static __always_inline void stac(void)
+{
+	/* Note: a barrier is implicit in alternative() */
+	alternative(ASM_NOP3, __stringify(__ASM_STAC), X86_FEATURE_SMAP);
+}
+
+/* These macros can be used in asm() statements */
+#define ASM_CLAC \
+	ALTERNATIVE(ASM_NOP3, __stringify(__ASM_CLAC), X86_FEATURE_SMAP)
+#define ASM_STAC \
+	ALTERNATIVE(ASM_NOP3, __stringify(__ASM_STAC), X86_FEATURE_SMAP)
+
+#else /* CONFIG_X86_SMAP */
+
+static inline void clac(void) { }
+static inline void stac(void) { }
+
+#define ASM_CLAC
+#define ASM_STAC
+
+#endif /* CONFIG_X86_SMAP */
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_X86_SMAP_H */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index e1f3a17034fc..a91acfbb1a98 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -9,6 +9,7 @@
 #include <linux/string.h>
 #include <asm/asm.h>
 #include <asm/page.h>
+#include <asm/smap.h>
 
 #define VERIFY_READ 0
 #define VERIFY_WRITE 1
@@ -192,9 +193,10 @@ extern int __get_user_bad(void);
 
 #ifdef CONFIG_X86_32
 #define __put_user_asm_u64(x, addr, err, errret)			\
-	asm volatile("1:	movl %%eax,0(%2)\n"			\
+	asm volatile(ASM_STAC "\n"					\
+		     "1:	movl %%eax,0(%2)\n"			\
 		     "2:	movl %%edx,4(%2)\n"			\
-		     "3:\n"						\
+		     "3: " ASM_CLAC "\n"				\
 		     ".section .fixup,\"ax\"\n"				\
 		     "4:	movl %3,%0\n"				\
 		     "	jmp 3b\n"					\
@@ -205,9 +207,10 @@ extern int __get_user_bad(void);
 		     : "A" (x), "r" (addr), "i" (errret), "0" (err))
 
 #define __put_user_asm_ex_u64(x, addr)					\
-	asm volatile("1:	movl %%eax,0(%1)\n"			\
+	asm volatile(ASM_STAC "\n"					\
+		     "1:	movl %%eax,0(%1)\n"			\
 		     "2:	movl %%edx,4(%1)\n"			\
-		     "3:\n"						\
+		     "3: " ASM_CLAC "\n"				\
 		     _ASM_EXTABLE_EX(1b, 2b)				\
 		     _ASM_EXTABLE_EX(2b, 3b)				\
 		     : : "A" (x), "r" (addr))
@@ -379,8 +382,9 @@ do {									\
 } while (0)
 
 #define __get_user_asm(x, addr, err, itype, rtype, ltype, errret)	\
-	asm volatile("1:	mov"itype" %2,%"rtype"1\n"		\
-		     "2:\n"						\
+	asm volatile(ASM_STAC "\n"					\
+		     "1:	mov"itype" %2,%"rtype"1\n"		\
+		     "2: " ASM_CLAC "\n"				\
 		     ".section .fixup,\"ax\"\n"				\
 		     "3:	mov %3,%0\n"				\
 		     "	xor"itype" %"rtype"1,%"rtype"1\n"		\
@@ -443,8 +447,9 @@ struct __large_struct { unsigned long buf[100]; };
  * aliasing issues.
  */
 #define __put_user_asm(x, addr, err, itype, rtype, ltype, errret)	\
-	asm volatile("1:	mov"itype" %"rtype"1,%2\n"		\
-		     "2:\n"						\
+	asm volatile(ASM_STAC "\n"					\
+		     "1:	mov"itype" %"rtype"1,%2\n"		\
+		     "2: " ASM_CLAC "\n"				\
 		     ".section .fixup,\"ax\"\n"				\
 		     "3:	mov %3,%0\n"				\
 		     "	jmp 2b\n"					\
@@ -463,13 +468,13 @@ struct __large_struct { unsigned long buf[100]; };
  * uaccess_try and catch
  */
 #define uaccess_try	do {						\
-	int prev_err = current_thread_info()->uaccess_err;		\
 	current_thread_info()->uaccess_err = 0;				\
+	stac();								\
 	barrier();
 
 #define uaccess_catch(err)						\
+	clac();								\
 	(err) |= (current_thread_info()->uaccess_err ? -EFAULT : 0);	\
-	current_thread_info()->uaccess_err = prev_err;			\
 } while (0)
 
 /**
@@ -569,6 +574,9 @@ strncpy_from_user(char *dst, const char __user *src, long count);
 extern __must_check long strlen_user(const char __user *str);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
+unsigned long __must_check clear_user(void __user *mem, unsigned long len);
+unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
+
 /*
  * movsl can be slow when source and dest are not both 8-byte aligned
  */
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 576e39bca6ad..7f760a9f1f61 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -213,7 +213,4 @@ static inline unsigned long __must_check copy_from_user(void *to,
 	return n;
 }
 
-unsigned long __must_check clear_user(void __user *mem, unsigned long len);
-unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
-
 #endif /* _ASM_X86_UACCESS_32_H */
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index d8def8b3dba0..142810c457dc 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -217,9 +217,6 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 	}
 }
 
-__must_check unsigned long clear_user(void __user *mem, unsigned long len);
-__must_check unsigned long __clear_user(void __user *mem, unsigned long len);
-
 static __must_check __always_inline int
 __copy_from_user_inatomic(void *dst, const void __user *src, unsigned size)
 {
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 2ddee1b87793..0415cdabb5a6 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -70,8 +70,9 @@ static inline int xsave_user(struct xsave_struct __user *buf)
 	if (unlikely(err))
 		return -EFAULT;
 
-	__asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x27\n"
-			     "2:\n"
+	__asm__ __volatile__(ASM_STAC "\n"
+			     "1: .byte " REX_PREFIX "0x0f,0xae,0x27\n"
+			     "2: " ASM_CLAC "\n"
 			     ".section .fixup,\"ax\"\n"
 			     "3:  movl $-1,%[err]\n"
 			     "    jmp  2b\n"
@@ -90,8 +91,9 @@ static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask)
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
 
-	__asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n"
-			     "2:\n"
+	__asm__ __volatile__(ASM_STAC "\n"
+			     "1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n"
+			     "2: " ASM_CLAC "\n"
 			     ".section .fixup,\"ax\"\n"
 			     "3:  movl $-1,%[err]\n"
 			     "    jmp  2b\n"