[PATCH] x86_64: x86_64 version of the smp alternative patch.

Changes are largely identical to the i386 version:

 * alternative #define are moved to the new alternative.h file.
 * one new elf section with pointers to the lock prefixes which can be
   nop'ed out for non-smp.
 * two new elf sections simliar to the "classic" alternatives to
   replace SMP code with simpler UP code.
 * fixup headers to use alternative.h instead of defining their own
   LOCK / LOCK_PREFIX macros.

The patch reuses the i386 version of the alternatives code to avoid code
duplication.  The code in alternatives.c was shuffled around a bit to
reduce the number of #ifdefs needed.  It also got some tweaks needed for
x86_64 (vsyscall page handling) and new features (noreplacement option
which was x86_64 only up to now).  Debug printk's are changed from
compile-time to runtime.

Loosely based on a early version from Bastian Blank <waldi@debian.org>

Signed-off-by: Gerd Hoffmann <kraxel@suse.de>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

10 files changed, 192 insertions, 123 deletions

diff --git a/include/asm-i386/alternative.h b/include/asm-i386/alternative.h
index d79e9ee10fd..c61bd1a17f3 100644
--- a/include/asm-i386/alternative.h
+++ b/include/asm-i386/alternative.h
@@ -5,6 +5,8 @@
 
 #include <asm/types.h>
 
+#include <linux/types.h>
+
 struct alt_instr {
 	u8 *instr; 		/* original instruction */
 	u8 *replacement;
diff --git a/include/asm-x86_64/alternative.h b/include/asm-x86_64/alternative.h
new file mode 100644
index 00000000000..387c8f66af7
--- /dev/null
+++ b/include/asm-x86_64/alternative.h
@@ -0,0 +1,146 @@
+#ifndef _X86_64_ALTERNATIVE_H
+#define _X86_64_ALTERNATIVE_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+
+struct alt_instr {
+	u8 *instr; 		/* original instruction */
+	u8 *replacement;
+	u8  cpuid;		/* cpuid bit set for replacement */
+	u8  instrlen;		/* length of original instruction */
+	u8  replacementlen; 	/* length of new instruction, <= instrlen */
+	u8  pad[5];
+};
+
+extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+
+struct module;
+extern void alternatives_smp_module_add(struct module *mod, char *name,
+					void *locks, void *locks_end,
+					void *text, void *text_end);
+extern void alternatives_smp_module_del(struct module *mod);
+extern void alternatives_smp_switch(int smp);
+
+#endif
+
+/*
+ * Alternative instructions for different CPU types or capabilities.
+ *
+ * This allows to use optimized instructions even on generic binary
+ * kernels.
+ *
+ * length of oldinstr must be longer or equal the length of newinstr
+ * It can be padded with nops as needed.
+ *
+ * For non barrier like inlines please define new variants
+ * without volatile and memory clobber.
+ */
+#define alternative(oldinstr, newinstr, feature) 	\
+	asm volatile ("661:\n\t" oldinstr "\n662:\n" 		     \
+		      ".section .altinstructions,\"a\"\n"     	     \
+		      "  .align 8\n"				       \
+		      "  .quad 661b\n"            /* label */          \
+		      "  .quad 663f\n"		  /* new instruction */ \
+		      "  .byte %c0\n"             /* feature bit */    \
+		      "  .byte 662b-661b\n"       /* sourcelen */      \
+		      "  .byte 664f-663f\n"       /* replacementlen */ \
+		      ".previous\n"					\
+		      ".section .altinstr_replacement,\"ax\"\n"		\
+		      "663:\n\t" newinstr "\n664:\n"   /* replacement */ \
+		      ".previous" :: "i" (feature) : "memory")
+
+/*
+ * Alternative inline assembly with input.
+ *
+ * Pecularities:
+ * No memory clobber here.
+ * Argument numbers start with 1.
+ * Best is to use constraints that are fixed size (like (%1) ... "r")
+ * If you use variable sized constraints like "m" or "g" in the
+ * replacement make sure to pad to the worst case length.
+ */
+#define alternative_input(oldinstr, newinstr, feature, input...)	\
+	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
+		      ".section .altinstructions,\"a\"\n"		\
+		      "  .align 8\n"					\
+		      "  .quad 661b\n"            /* label */		\
+		      "  .quad 663f\n"		  /* new instruction */	\
+		      "  .byte %c0\n"             /* feature bit */	\
+		      "  .byte 662b-661b\n"       /* sourcelen */	\
+		      "  .byte 664f-663f\n"       /* replacementlen */	\
+		      ".previous\n"					\
+		      ".section .altinstr_replacement,\"ax\"\n"		\
+		      "663:\n\t" newinstr "\n664:\n"   /* replacement */ \
+		      ".previous" :: "i" (feature), ##input)
+
+/* Like alternative_input, but with a single output argument */
+#define alternative_io(oldinstr, newinstr, feature, output, input...) \
+	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
+		      ".section .altinstructions,\"a\"\n"		\
+		      "  .align 8\n"					\
+		      "  .quad 661b\n"            /* label */		\
+		      "  .quad 663f\n"		  /* new instruction */	\
+		      "  .byte %c[feat]\n"        /* feature bit */	\
+		      "  .byte 662b-661b\n"       /* sourcelen */	\
+		      "  .byte 664f-663f\n"       /* replacementlen */	\
+		      ".previous\n"					\
+		      ".section .altinstr_replacement,\"ax\"\n"		\
+		      "663:\n\t" newinstr "\n664:\n"   /* replacement */ \
+		      ".previous" : output : [feat] "i" (feature), ##input)
+
+/*
+ * Alternative inline assembly for SMP.
+ *
+ * alternative_smp() takes two versions (SMP first, UP second) and is
+ * for more complex stuff such as spinlocks.
+ *
+ * The LOCK_PREFIX macro defined here replaces the LOCK and
+ * LOCK_PREFIX macros used everywhere in the source tree.
+ *
+ * SMP alternatives use the same data structures as the other
+ * alternatives and the X86_FEATURE_UP flag to indicate the case of a
+ * UP system running a SMP kernel.  The existing apply_alternatives()
+ * works fine for patching a SMP kernel for UP.
+ *
+ * The SMP alternative tables can be kept after boot and contain both
+ * UP and SMP versions of the instructions to allow switching back to
+ * SMP at runtime, when hotplugging in a new CPU, which is especially
+ * useful in virtualized environments.
+ *
+ * The very common lock prefix is handled as special case in a
+ * separate table which is a pure address list without replacement ptr
+ * and size information.  That keeps the table sizes small.
+ */
+
+#ifdef CONFIG_SMP
+#define alternative_smp(smpinstr, upinstr, args...)			\
+	asm volatile ("661:\n\t" smpinstr "\n662:\n"			\
+		      ".section .smp_altinstructions,\"a\"\n"		\
+		      "  .align 8\n"					\
+		      "  .quad 661b\n"            /* label */		\
+		      "  .quad 663f\n"		  /* new instruction */	\
+		      "  .byte 0x66\n"            /* X86_FEATURE_UP */	\
+		      "  .byte 662b-661b\n"       /* sourcelen */	\
+		      "  .byte 664f-663f\n"       /* replacementlen */	\
+		      ".previous\n"					\
+		      ".section .smp_altinstr_replacement,\"awx\"\n"	\
+		      "663:\n\t" upinstr "\n"     /* replacement */	\
+		      "664:\n\t.fill 662b-661b,1,0x42\n" /* space for original */ \
+		      ".previous" : args)
+
+#define LOCK_PREFIX \
+		".section .smp_locks,\"a\"\n"	\
+		"  .align 8\n"			\
+		"  .quad 661f\n" /* address */	\
+		".previous\n"			\
+	       	"661:\n\tlock; "
+
+#else /* ! CONFIG_SMP */
+#define alternative_smp(smpinstr, upinstr, args...) \
+	asm volatile (upinstr : args)
+#define LOCK_PREFIX ""
+#endif
+
+#endif /* _X86_64_ALTERNATIVE_H */
diff --git a/include/asm-x86_64/atomic.h b/include/asm-x86_64/atomic.h
index bd3fa67ed83..007e88d6d43 100644
--- a/include/asm-x86_64/atomic.h
+++ b/include/asm-x86_64/atomic.h
@@ -1,7 +1,7 @@
 #ifndef __ARCH_X86_64_ATOMIC__
 #define __ARCH_X86_64_ATOMIC__
 
-#include <asm/types.h>
+#include <asm/alternative.h>
 
 /* atomic_t should be 32 bit signed type */
 
@@ -52,7 +52,7 @@ typedef struct { volatile int counter; } atomic_t;
 static __inline__ void atomic_add(int i, atomic_t *v)
 {
 	__asm__ __volatile__(
-		LOCK "addl %1,%0"
+		LOCK_PREFIX "addl %1,%0"
 		:"=m" (v->counter)
 		:"ir" (i), "m" (v->counter));
 }
@@ -67,7 +67,7 @@ static __inline__ void atomic_add(int i, atomic_t *v)
 static __inline__ void atomic_sub(int i, atomic_t *v)
 {
 	__asm__ __volatile__(
-		LOCK "subl %1,%0"
+		LOCK_PREFIX "subl %1,%0"
 		:"=m" (v->counter)
 		:"ir" (i), "m" (v->counter));
 }
@@ -86,7 +86,7 @@ static __inline__ int atomic_sub_and_test(int i, atomic_t *v)
 	unsigned char c;
 
 	__asm__ __volatile__(
-		LOCK "subl %2,%0; sete %1"
+		LOCK_PREFIX "subl %2,%0; sete %1"
 		:"=m" (v->counter), "=qm" (c)
 		:"ir" (i), "m" (v->counter) : "memory");
 	return c;
@@ -101,7 +101,7 @@ static __inline__ int atomic_sub_and_test(int i, atomic_t *v)
 static __inline__ void atomic_inc(atomic_t *v)
 {
 	__asm__ __volatile__(
-		LOCK "incl %0"
+		LOCK_PREFIX "incl %0"
 		:"=m" (v->counter)
 		:"m" (v->counter));
 }
@@ -115,7 +115,7 @@ static __inline__ void atomic_inc(atomic_t *v)
 static __inline__ void atomic_dec(atomic_t *v)
 {
 	__asm__ __volatile__(
-		LOCK "decl %0"
+		LOCK_PREFIX "decl %0"
 		:"=m" (v->counter)
 		:"m" (v->counter));
 }
@@ -133,7 +133,7 @@ static __inline__ int atomic_dec_and_test(atomic_t *v)
 	unsigned char c;
 
 	__asm__ __volatile__(
-		LOCK "decl %0; sete %1"
+		LOCK_PREFIX "decl %0; sete %1"
 		:"=m" (v->counter), "=qm" (c)
 		:"m" (v->counter) : "memory");
 	return c != 0;
@@ -152,7 +152,7 @@ static __inline__ int atomic_inc_and_test(atomic_t *v)
 	unsigned char c;
 
 	__asm__ __volatile__(
-		LOCK "incl %0; sete %1"
+		LOCK_PREFIX "incl %0; sete %1"
 		:"=m" (v->counter), "=qm" (c)
 		:"m" (v->counter) : "memory");
 	return c != 0;
@@ -172,7 +172,7 @@ static __inline__ int atomic_add_negative(int i, atomic_t *v)
 	unsigned char c;
 
 	__asm__ __volatile__(
-		LOCK "addl %2,%0; sets %1"
+		LOCK_PREFIX "addl %2,%0; sets %1"
 		:"=m" (v->counter), "=qm" (c)
 		:"ir" (i), "m" (v->counter) : "memory");
 	return c;
@@ -189,7 +189,7 @@ static __inline__ int atomic_add_return(int i, atomic_t *v)
 {
 	int __i = i;
 	__asm__ __volatile__(
-		LOCK "xaddl %0, %1;"
+		LOCK_PREFIX "xaddl %0, %1;"
 		:"=r"(i)
 		:"m"(v->counter), "0"(i));
 	return i + __i;
@@ -237,7 +237,7 @@ typedef struct { volatile long counter; } atomic64_t;
 static __inline__ void atomic64_add(long i, atomic64_t *v)
 {
 	__asm__ __volatile__(
-		LOCK "addq %1,%0"
+		LOCK_PREFIX "addq %1,%0"
 		:"=m" (v->counter)
 		:"ir" (i), "m" (v->counter));
 }
@@ -252,7 +252,7 @@ static __inline__ void atomic64_add(long i, atomic64_t *v)
 static __inline__ void atomic64_sub(long i, atomic64_t *v)
 {
 	__asm__ __volatile__(
-		LOCK "subq %1,%0"
+		LOCK_PREFIX "subq %1,%0"
 		:"=m" (v->counter)
 		:"ir" (i), "m" (v->counter));
 }
@@ -271,7 +271,7 @@ static __inline__ int atomic64_sub_and_test(long i, atomic64_t *v)
 	unsigned char c;
 
 	__asm__ __volatile__(
-		LOCK "subq %2,%0; sete %1"
+		LOCK_PREFIX "subq %2,%0; sete %1"
 		:"=m" (v->counter), "=qm" (c)
 		:"ir" (i), "m" (v->counter) : "memory");
 	return c;
@@ -286,7 +286,7 @@ static __inline__ int atomic64_sub_and_test(long i, atomic64_t *v)
 static __inline__ void atomic64_inc(atomic64_t *v)
 {
 	__asm__ __volatile__(
-		LOCK "incq %0"
+		LOCK_PREFIX "incq %0"
 		:"=m" (v->counter)
 		:"m" (v->counter));
 }
@@ -300,7 +300,7 @@ static __inline__ void atomic64_inc(atomic64_t *v)
 static __inline__ void atomic64_dec(atomic64_t *v)
 {
 	__asm__ __volatile__(
-		LOCK "decq %0"
+		LOCK_PREFIX "decq %0"
 		:"=m" (v->counter)
 		:"m" (v->counter));
 }
@@ -318,7 +318,7 @@ static __inline__ int atomic64_dec_and_test(atomic64_t *v)
 	unsigned char c;
 
 	__asm__ __volatile__(
-		LOCK "decq %0; sete %1"
+		LOCK_PREFIX "decq %0; sete %1"
 		:"=m" (v->counter), "=qm" (c)
 		:"m" (v->counter) : "memory");
 	return c != 0;
@@ -337,7 +337,7 @@ static __inline__ int atomic64_inc_and_test(atomic64_t *v)
 	unsigned char c;
 
 	__asm__ __volatile__(
-		LOCK "incq %0; sete %1"
+		LOCK_PREFIX "incq %0; sete %1"
 		:"=m" (v->counter), "=qm" (c)
 		:"m" (v->counter) : "memory");
 	return c != 0;
@@ -357,7 +357,7 @@ static __inline__ int atomic64_add_negative(long i, atomic64_t *v)
 	unsigned char c;
 
 	__asm__ __volatile__(
-		LOCK "addq %2,%0; sets %1"
+		LOCK_PREFIX "addq %2,%0; sets %1"
 		:"=m" (v->counter), "=qm" (c)
 		:"ir" (i), "m" (v->counter) : "memory");
 	return c;
@@ -374,7 +374,7 @@ static __inline__ long atomic64_add_return(long i, atomic64_t *v)
 {
 	long __i = i;
 	__asm__ __volatile__(
-		LOCK "xaddq %0, %1;"
+		LOCK_PREFIX "xaddq %0, %1;"
 		:"=r"(i)
 		:"m"(v->counter), "0"(i));
 	return i + __i;
@@ -418,11 +418,11 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t *v)
 
 /* These are x86-specific, used by some header files */
 #define atomic_clear_mask(mask, addr) \
-__asm__ __volatile__(LOCK "andl %0,%1" \
+__asm__ __volatile__(LOCK_PREFIX "andl %0,%1" \
 : : "r" (~(mask)),"m" (*addr) : "memory")
 
 #define atomic_set_mask(mask, addr) \
-__asm__ __volatile__(LOCK "orl %0,%1" \
+__asm__ __volatile__(LOCK_PREFIX "orl %0,%1" \
 : : "r" ((unsigned)mask),"m" (*(addr)) : "memory")
 
 /* Atomic operations are already serializing on x86 */
diff --git a/include/asm-x86_64/bitops.h b/include/asm-x86_64/bitops.h
index e9bf933d25d..f7ba57b1cc0 100644
--- a/include/asm-x86_64/bitops.h
+++ b/include/asm-x86_64/bitops.h
@@ -5,12 +5,7 @@
  * Copyright 1992, Linus Torvalds.
  */
 
-
-#ifdef CONFIG_SMP
-#define LOCK_PREFIX "lock ; "
-#else
-#define LOCK_PREFIX ""
-#endif
+#include <asm/alternative.h>
 
 #define ADDR (*(volatile long *) addr)
 
diff --git a/include/asm-x86_64/cpufeature.h b/include/asm-x86_64/cpufeature.h
index 662964b74e3..afc44e55740 100644
--- a/include/asm-x86_64/cpufeature.h
+++ b/include/asm-x86_64/cpufeature.h
@@ -65,6 +65,8 @@
 #define X86_FEATURE_CONSTANT_TSC (3*32+5) /* TSC runs at constant rate */
 #define X86_FEATURE_SYNC_RDTSC  (3*32+6)  /* RDTSC syncs CPU core */
 #define X86_FEATURE_FXSAVE_LEAK (3*32+7)  /* FIP/FOP/FDP leaks through FXSAVE */
+#define X86_FEATURE_UP		(3*32+8) /* SMP kernel running on UP */
+
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* Streaming SIMD Extensions-3 */
diff --git a/include/asm-x86_64/mutex.h b/include/asm-x86_64/mutex.h
index 11fbee2bd6c..06fab6de2a8 100644
--- a/include/asm-x86_64/mutex.h
+++ b/include/asm-x86_64/mutex.h
@@ -24,7 +24,7 @@ do {									\
 	typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);		\
 									\
 	__asm__ __volatile__(						\
-		LOCK	"   decl (%%rdi)	\n"			\
+		LOCK_PREFIX "   decl (%%rdi)	\n"			\
 			"   js 2f		\n"			\
 			"1:			\n"			\
 									\
@@ -74,7 +74,7 @@ do {									\
 	typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);		\
 									\
 	__asm__ __volatile__(						\
-		LOCK	"   incl (%%rdi)	\n"			\
+		LOCK_PREFIX "   incl (%%rdi)	\n"			\
 			"   jle 2f		\n"			\
 			"1:			\n"			\
 									\
diff --git a/include/asm-x86_64/rwlock.h b/include/asm-x86_64/rwlock.h
index 9942cc39306..dea0e945926 100644
--- a/include/asm-x86_64/rwlock.h
+++ b/include/asm-x86_64/rwlock.h
@@ -24,7 +24,7 @@
 #define RW_LOCK_BIAS_STR	"0x01000000"
 
 #define __build_read_lock_ptr(rw, helper)   \
-	asm volatile(LOCK "subl $1,(%0)\n\t" \
+	asm volatile(LOCK_PREFIX "subl $1,(%0)\n\t" \
 		     "js 2f\n" \
 		     "1:\n" \
 		    LOCK_SECTION_START("") \
@@ -34,7 +34,7 @@
 		     ::"a" (rw) : "memory")
 
 #define __build_read_lock_const(rw, helper)   \
-	asm volatile(LOCK "subl $1,%0\n\t" \
+	asm volatile(LOCK_PREFIX "subl $1,%0\n\t" \
 		     "js 2f\n" \
 		     "1:\n" \
 		    LOCK_SECTION_START("") \
@@ -54,7 +54,7 @@
 					} while (0)
 
 #define __build_write_lock_ptr(rw, helper) \
-	asm volatile(LOCK "subl $" RW_LOCK_BIAS_STR ",(%0)\n\t" \
+	asm volatile(LOCK_PREFIX "subl $" RW_LOCK_BIAS_STR ",(%0)\n\t" \
 		     "jnz 2f\n" \
 		     "1:\n" \
 		     LOCK_SECTION_START("") \
@@ -64,7 +64,7 @@
 		     ::"a" (rw) : "memory")
 
 #define __build_write_lock_const(rw, helper) \
-	asm volatile(LOCK "subl $" RW_LOCK_BIAS_STR ",%0\n\t" \
+	asm volatile(LOCK_PREFIX "subl $" RW_LOCK_BIAS_STR ",%0\n\t" \
 		     "jnz 2f\n" \
 		     "1:\n" \
 		    LOCK_SECTION_START("") \
diff --git a/include/asm-x86_64/semaphore.h b/include/asm-x86_64/semaphore.h
index a389aa6fe80..064df08b9a0 100644
--- a/include/asm-x86_64/semaphore.h
+++ b/include/asm-x86_64/semaphore.h
@@ -106,7 +106,7 @@ static inline void down(struct semaphore * sem)
 
 	__asm__ __volatile__(
 		"# atomic down operation\n\t"
-		LOCK "decl %0\n\t"     /* --sem->count */
+		LOCK_PREFIX "decl %0\n\t"     /* --sem->count */
 		"js 2f\n"
 		"1:\n"
 		LOCK_SECTION_START("")
@@ -130,7 +130,7 @@ static inline int down_interruptible(struct semaphore * sem)
 
 	__asm__ __volatile__(
 		"# atomic interruptible down operation\n\t"
-		LOCK "decl %1\n\t"     /* --sem->count */
+		LOCK_PREFIX "decl %1\n\t"     /* --sem->count */
 		"js 2f\n\t"
 		"xorl %0,%0\n"
 		"1:\n"
@@ -154,7 +154,7 @@ static inline int down_trylock(struct semaphore * sem)
 
 	__asm__ __volatile__(
 		"# atomic interruptible down operation\n\t"
-		LOCK "decl %1\n\t"     /* --sem->count */
+		LOCK_PREFIX "decl %1\n\t"     /* --sem->count */
 		"js 2f\n\t"
 		"xorl %0,%0\n"
 		"1:\n"
@@ -178,7 +178,7 @@ static inline void up(struct semaphore * sem)
 {
 	__asm__ __volatile__(
 		"# atomic up operation\n\t"
-		LOCK "incl %0\n\t"     /* ++sem->count */
+		LOCK_PREFIX "incl %0\n\t"     /* ++sem->count */
 		"jle 2f\n"
 		"1:\n"
 		LOCK_SECTION_START("")
diff --git a/include/asm-x86_64/spinlock.h b/include/asm-x86_64/spinlock.h
index 5d8a5e3589f..8d3421996f9 100644
--- a/include/asm-x86_64/spinlock.h
+++ b/include/asm-x86_64/spinlock.h
@@ -31,15 +31,19 @@
 	"jmp 1b\n" \
 	LOCK_SECTION_END
 
+#define __raw_spin_lock_string_up \
+	"\n\tdecl %0"
+
 #define __raw_spin_unlock_string \
 	"movl $1,%0" \
 		:"=m" (lock->slock) : : "memory"
 
 static inline void __raw_spin_lock(raw_spinlock_t *lock)
 {
-	__asm__ __volatile__(
-		__raw_spin_lock_string
-		:"=m" (lock->slock) : : "memory");
+	alternative_smp(
+		__raw_spin_lock_string,
+		__raw_spin_lock_string_up,
+		"=m" (lock->slock) : : "memory");
 }
 
 #define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
diff --git a/include/asm-x86_64/system.h b/include/asm-x86_64/system.h
index f48e0dad8b3..68e559f3631 100644
--- a/include/asm-x86_64/system.h
+++ b/include/asm-x86_64/system.h
@@ -3,15 +3,10 @@
 
 #include <linux/kernel.h>
 #include <asm/segment.h>
+#include <asm/alternative.h>
 
 #ifdef __KERNEL__
 
-#ifdef CONFIG_SMP
-#define LOCK_PREFIX "lock ; "
-#else
-#define LOCK_PREFIX ""
-#endif
-
 #define __STR(x) #x
 #define STR(x) __STR(x)
 
@@ -34,7 +29,7 @@
 		     "thread_return:\n\t"					    \
 		     "movq %%gs:%P[pda_pcurrent],%%rsi\n\t"			  \
 		     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
-		     LOCK "btr  %[tif_fork],%P[ti_flags](%%r8)\n\t"		  \
+		     LOCK_PREFIX "btr  %[tif_fork],%P[ti_flags](%%r8)\n\t"	  \
 		     "movq %%rax,%%rdi\n\t" 					  \
 		     "jc   ret_from_fork\n\t"					  \
 		     RESTORE_CONTEXT						    \
@@ -69,82 +64,6 @@ extern void load_gs_index(unsigned);
 		".previous"			\
 		: :"r" (value), "r" (0))
 
-#ifdef __KERNEL__
-struct alt_instr { 
-	__u8 *instr; 		/* original instruction */
-	__u8 *replacement;
-	__u8  cpuid;		/* cpuid bit set for replacement */
-	__u8  instrlen;		/* length of original instruction */
-	__u8  replacementlen; 	/* length of new instruction, <= instrlen */ 
-	__u8  pad[5];
-}; 
-#endif
-
-/*
- * Alternative instructions for different CPU types or capabilities.
- * 
- * This allows to use optimized instructions even on generic binary
- * kernels.
- * 
- * length of oldinstr must be longer or equal the length of newinstr
- * It can be padded with nops as needed.
- * 
- * For non barrier like inlines please define new variants
- * without volatile and memory clobber.
- */
-#define alternative(oldinstr, newinstr, feature) 	\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n" 		     \
-		      ".section .altinstructions,\"a\"\n"     	     \
-		      "  .align 8\n"				       \
-		      "  .quad 661b\n"            /* label */          \
-		      "  .quad 663f\n"		  /* new instruction */ \
-		      "  .byte %c0\n"             /* feature bit */    \
-		      "  .byte 662b-661b\n"       /* sourcelen */      \
-		      "  .byte 664f-663f\n"       /* replacementlen */ \
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"   /* replacement */ \
-		      ".previous" :: "i" (feature) : "memory")  
-
-/*
- * Alternative inline assembly with input.
- * 
- * Peculiarities:
- * No memory clobber here. 
- * Argument numbers start with 1.
- * Best is to use constraints that are fixed size (like (%1) ... "r")
- * If you use variable sized constraints like "m" or "g" in the 
- * replacement make sure to pad to the worst case length.
- */
-#define alternative_input(oldinstr, newinstr, feature, input...)	\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      "  .align 8\n"					\
-		      "  .quad 661b\n"            /* label */		\
-		      "  .quad 663f\n"		  /* new instruction */	\
-		      "  .byte %c0\n"             /* feature bit */	\
-		      "  .byte 662b-661b\n"       /* sourcelen */	\
-		      "  .byte 664f-663f\n"       /* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"   /* replacement */ \
-		      ".previous" :: "i" (feature), ##input)
-
-/* Like alternative_input, but with a single output argument */
-#define alternative_io(oldinstr, newinstr, feature, output, input...) \
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      "  .align 8\n"					\
-		      "  .quad 661b\n"            /* label */		\
-		      "  .quad 663f\n"		  /* new instruction */	\
-		      "  .byte %c[feat]\n"        /* feature bit */	\
-		      "  .byte 662b-661b\n"       /* sourcelen */	\
-		      "  .byte 664f-663f\n"       /* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"   /* replacement */ \
-		      ".previous" : output : [feat] "i" (feature), ##input)
-
 /*
  * Clear and set 'TS' bit respectively
  */
@@ -366,5 +285,6 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 void cpu_idle_wait(void);
 
 extern unsigned long arch_align_stack(unsigned long sp);
+extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
 
 #endif