[PATCH] x86: SMP alternatives

Implement SMP alternatives, i.e.  switching at runtime between different
code versions for UP and SMP.  The code can patch both SMP->UP and UP->SMP.
The UP->SMP case is useful for CPU hotplug.

With CONFIG_CPU_HOTPLUG enabled the code switches to UP at boot time and
when the number of CPUs goes down to 1, and switches to SMP when the number
of CPUs goes up to 2.

Without CONFIG_CPU_HOTPLUG or on non-SMP-capable systems the code is
patched once at boot time (if needed) and the tables are released
afterwards.

The changes in detail:

  * The current alternatives bits are moved to a separate file,
    the SMP alternatives code is added there.

  * The patch adds some new elf sections to the kernel:
    .smp_altinstructions
	like .altinstructions, also contains a list
	of alt_instr structs.
    .smp_altinstr_replacement
	like .altinstr_replacement, but also has some space to
	save original instruction before replaving it.
    .smp_locks
	list of pointers to lock prefixes which can be nop'ed
	out on UP.
    The first two are used to replace more complex instruction
    sequences such as spinlocks and semaphores.  It would be possible
    to deal with the lock prefixes with that as well, but by handling
    them as special case the table sizes become much smaller.

 * The sections are page-aligned and padded up to page size, so they
   can be free if they are not needed.

 * Splitted the code to release init pages to a separate function and
   use it to release the elf sections if they are unused.

Signed-off-by: Gerd Hoffmann <kraxel@suse.de>
Signed-off-by: Chuck Ebbert <76306.1226@compuserve.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

9 files changed, 194 insertions, 124 deletions

diff --git a/include/asm-i386/alternative.h b/include/asm-i386/alternative.h
new file mode 100644
index 00000000000..e201decea0c
--- /dev/null
+++ b/include/asm-i386/alternative.h
@@ -0,0 +1,129 @@
+#ifndef _I386_ALTERNATIVE_H
+#define _I386_ALTERNATIVE_H
+
+#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;
+};
+
+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 4\n"					\
+		      "  .long 661b\n"            /* label */		\
+		      "  .long 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 maake 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 4\n"					\
+		      "  .long 661b\n"            /* label */		\
+		      "  .long 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)
+
+/*
+ * 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 4\n"					\
+		      "  .long 661b\n"            /* label */		\
+		      "  .long 663f\n"		  /* new instruction */	\
+		      "  .byte 0x68\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 4\n"			\
+		"  .long 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 /* _I386_ALTERNATIVE_H */
diff --git a/include/asm-i386/atomic.h b/include/asm-i386/atomic.h
index de649d3aa2d..78b0032d1f2 100644
--- a/include/asm-i386/atomic.h
+++ b/include/asm-i386/atomic.h
@@ -10,12 +10,6 @@
  * resource counting etc..
  */
 
-#ifdef CONFIG_SMP
-#define LOCK "lock ; "
-#else
-#define LOCK ""
-#endif
-
 /*
  * Make sure gcc doesn't try to be clever and move things around
  * on us. We need to use _exactly_ the address the user gave us,
@@ -52,7 +46,7 @@ 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 +61,7 @@ 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 +80,7 @@ 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 +95,7 @@ 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 +109,7 @@ 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 +127,7 @@ 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 +146,7 @@ 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 +166,7 @@ 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;
@@ -195,7 +189,7 @@ static __inline__ int atomic_add_return(int i, atomic_t *v)
 	/* Modern 486+ processor */
 	__i = i;
 	__asm__ __volatile__(
-		LOCK "xaddl %0, %1;"
+		LOCK_PREFIX "xaddl %0, %1;"
 		:"=r"(i)
 		:"m"(v->counter), "0"(i));
 	return i + __i;
@@ -242,11 +236,11 @@ static __inline__ int atomic_sub_return(int i, atomic_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" (mask),"m" (*(addr)) : "memory")
 
 /* Atomic operations are already serializing on x86 */
diff --git a/include/asm-i386/bitops.h b/include/asm-i386/bitops.h
index 88e6ca248cd..7d20b95edb3 100644
--- a/include/asm-i386/bitops.h
+++ b/include/asm-i386/bitops.h
@@ -7,6 +7,7 @@
 
 #include <linux/config.h>
 #include <linux/compiler.h>
+#include <asm/alternative.h>
 
 /*
  * These have to be done with inline assembly: that way the bit-setting
@@ -16,12 +17,6 @@
  * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
  */
 
-#ifdef CONFIG_SMP
-#define LOCK_PREFIX "lock ; "
-#else
-#define LOCK_PREFIX ""
-#endif
-
 #define ADDR (*(volatile long *) addr)
 
 /**
diff --git a/include/asm-i386/cpufeature.h b/include/asm-i386/cpufeature.h
index c4ec2a4d8fd..5c0b5876b93 100644
--- a/include/asm-i386/cpufeature.h
+++ b/include/asm-i386/cpufeature.h
@@ -70,6 +70,7 @@
 #define X86_FEATURE_P3		(3*32+ 6) /* P3 */
 #define X86_FEATURE_P4		(3*32+ 7) /* P4 */
 #define X86_FEATURE_CONSTANT_TSC (3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP		(3*32+ 9) /* 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-i386/mutex.h b/include/asm-i386/mutex.h
index 9b2199e829f..05a53853122 100644
--- a/include/asm-i386/mutex.h
+++ b/include/asm-i386/mutex.h
@@ -9,6 +9,8 @@
 #ifndef _ASM_MUTEX_H
 #define _ASM_MUTEX_H
 
+#include "asm/alternative.h"
+
 /**
  *  __mutex_fastpath_lock - try to take the lock by moving the count
  *                          from 1 to a 0 value
@@ -27,7 +29,7 @@ do {									\
 	typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);		\
 									\
 	__asm__ __volatile__(						\
-		LOCK	"   decl (%%eax)	\n"			\
+		LOCK_PREFIX "   decl (%%eax)	\n"			\
 			"   js 2f		\n"			\
 			"1:			\n"			\
 									\
@@ -83,7 +85,7 @@ do {									\
 	typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);		\
 									\
 	__asm__ __volatile__(						\
-		LOCK	"   incl (%%eax)	\n"			\
+		LOCK_PREFIX "   incl (%%eax)	\n"			\
 			"   jle 2f		\n"			\
 			"1:			\n"			\
 									\
diff --git a/include/asm-i386/rwlock.h b/include/asm-i386/rwlock.h
index b57cc7afdf7..94f00195d54 100644
--- a/include/asm-i386/rwlock.h
+++ b/include/asm-i386/rwlock.h
@@ -21,21 +21,23 @@
 #define RW_LOCK_BIAS_STR	"0x01000000"
 
 #define __build_read_lock_ptr(rw, helper)   \
-	asm volatile(LOCK "subl $1,(%0)\n\t" \
-		     "jns 1f\n" \
-		     "call " helper "\n\t" \
-		     "1:\n" \
-		     ::"a" (rw) : "memory")
+	alternative_smp("lock; subl $1,(%0)\n\t" \
+			"jns 1f\n" \
+			"call " helper "\n\t" \
+			"1:\n", \
+			"subl $1,(%0)\n\t", \
+			:"a" (rw) : "memory")
 
 #define __build_read_lock_const(rw, helper)   \
-	asm volatile(LOCK "subl $1,%0\n\t" \
-		     "jns 1f\n" \
-		     "pushl %%eax\n\t" \
-		     "leal %0,%%eax\n\t" \
-		     "call " helper "\n\t" \
-		     "popl %%eax\n\t" \
-		     "1:\n" \
-		     :"=m" (*(volatile int *)rw) : : "memory")
+	alternative_smp("lock; subl $1,%0\n\t" \
+			"jns 1f\n" \
+			"pushl %%eax\n\t" \
+			"leal %0,%%eax\n\t" \
+			"call " helper "\n\t" \
+			"popl %%eax\n\t" \
+			"1:\n", \
+			"subl $1,%0\n\t", \
+			"=m" (*(volatile int *)rw) : : "memory")
 
 #define __build_read_lock(rw, helper)	do { \
 						if (__builtin_constant_p(rw)) \
@@ -45,21 +47,23 @@
 					} while (0)
 
 #define __build_write_lock_ptr(rw, helper) \
-	asm volatile(LOCK "subl $" RW_LOCK_BIAS_STR ",(%0)\n\t" \
-		     "jz 1f\n" \
-		     "call " helper "\n\t" \
-		     "1:\n" \
-		     ::"a" (rw) : "memory")
+	alternative_smp("lock; subl $" RW_LOCK_BIAS_STR ",(%0)\n\t" \
+			"jz 1f\n" \
+			"call " helper "\n\t" \
+			"1:\n", \
+			"subl $" RW_LOCK_BIAS_STR ",(%0)\n\t", \
+			:"a" (rw) : "memory")
 
 #define __build_write_lock_const(rw, helper) \
-	asm volatile(LOCK "subl $" RW_LOCK_BIAS_STR ",%0\n\t" \
-		     "jz 1f\n" \
-		     "pushl %%eax\n\t" \
-		     "leal %0,%%eax\n\t" \
-		     "call " helper "\n\t" \
-		     "popl %%eax\n\t" \
-		     "1:\n" \
-		     :"=m" (*(volatile int *)rw) : : "memory")
+	alternative_smp("lock; subl $" RW_LOCK_BIAS_STR ",%0\n\t" \
+			"jz 1f\n" \
+			"pushl %%eax\n\t" \
+			"leal %0,%%eax\n\t" \
+			"call " helper "\n\t" \
+			"popl %%eax\n\t" \
+			"1:\n", \
+			"subl $" RW_LOCK_BIAS_STR ",%0\n\t", \
+			"=m" (*(volatile int *)rw) : : "memory")
 
 #define __build_write_lock(rw, helper)	do { \
 						if (__builtin_constant_p(rw)) \
diff --git a/include/asm-i386/semaphore.h b/include/asm-i386/semaphore.h
index 6a42b2142fd..f7a0f310c52 100644
--- a/include/asm-i386/semaphore.h
+++ b/include/asm-i386/semaphore.h
@@ -99,7 +99,7 @@ static inline void down(struct semaphore * sem)
 	might_sleep();
 	__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("")
@@ -123,7 +123,7 @@ static inline int down_interruptible(struct semaphore * sem)
 	might_sleep();
 	__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"
@@ -148,7 +148,7 @@ 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"
@@ -173,7 +173,7 @@ 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-i386/spinlock.h b/include/asm-i386/spinlock.h
index 23604350cdf..a1b8a8a30e2 100644
--- a/include/asm-i386/spinlock.h
+++ b/include/asm-i386/spinlock.h
@@ -48,18 +48,23 @@
 	"jmp 1b\n" \
 	"4:\n\t"
 
+#define __raw_spin_lock_string_up \
+	"\n\tdecb %0"
+
 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");
 }
 
 static inline void __raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags)
 {
-	__asm__ __volatile__(
-		__raw_spin_lock_string_flags
-		:"=m" (lock->slock) : "r" (flags) : "memory");
+	alternative_smp(
+		__raw_spin_lock_string_flags,
+		__raw_spin_lock_string_up,
+		"=m" (lock->slock) : "r" (flags) : "memory");
 }
 
 static inline int __raw_spin_trylock(raw_spinlock_t *lock)
@@ -178,12 +183,12 @@ static inline int __raw_write_trylock(raw_rwlock_t *lock)
 
 static inline void __raw_read_unlock(raw_rwlock_t *rw)
 {
-	asm volatile("lock ; incl %0" :"=m" (rw->lock) : : "memory");
+	asm volatile(LOCK_PREFIX "incl %0" :"=m" (rw->lock) : : "memory");
 }
 
 static inline void __raw_write_unlock(raw_rwlock_t *rw)
 {
-	asm volatile("lock ; addl $" RW_LOCK_BIAS_STR ", %0"
+	asm volatile(LOCK_PREFIX "addl $" RW_LOCK_BIAS_STR ", %0"
 				 : "=m" (rw->lock) : : "memory");
 }
 
diff --git a/include/asm-i386/system.h b/include/asm-i386/system.h
index 399145a247f..d0d8d7448d8 100644
--- a/include/asm-i386/system.h
+++ b/include/asm-i386/system.h
@@ -352,67 +352,6 @@ static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long l
 
 #endif
     
-#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;
-}; 
-#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 4\n"				       \
-		      "  .long 661b\n"            /* label */          \
-		      "  .long 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 maake 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 4\n"						\
-		      "  .long 661b\n"            /* label */			\
-		      "  .long 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)
-
 /*
  * Force strict CPU ordering.
  * And yes, this is required on UP too when we're talking
@@ -558,5 +497,6 @@ static inline void sched_cacheflush(void)
 }
 
 extern unsigned long arch_align_stack(unsigned long sp);
+extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
 
 #endif