Merge branch 'linus'

23 files changed, 267 insertions, 162 deletions

diff --git a/include/asm-i386/acpi.h b/include/asm-i386/acpi.h
index 55059abf9c9..20f52395421 100644
--- a/include/asm-i386/acpi.h
+++ b/include/asm-i386/acpi.h
@@ -103,6 +103,12 @@ __acpi_release_global_lock (unsigned int *lock)
         :"=r"(n_hi), "=r"(n_lo)     \
         :"0"(n_hi), "1"(n_lo))
 
+#ifdef CONFIG_X86_IO_APIC
+extern void check_acpi_pci(void);
+#else
+static inline void check_acpi_pci(void) { }
+#endif
+
 #ifdef CONFIG_ACPI 
 extern int acpi_lapic;
 extern int acpi_ioapic;
@@ -128,8 +134,6 @@ extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
 extern int skip_ioapic_setup;
 extern int acpi_skip_timer_override;
 
-extern void check_acpi_pci(void);
-
 static inline void disable_ioapic_setup(void)
 {
 	skip_ioapic_setup = 1;
@@ -142,8 +146,6 @@ static inline int ioapic_setup_disabled(void)
 
 #else
 static inline void disable_ioapic_setup(void) { }
-static inline void check_acpi_pci(void) { }
-
 #endif
 
 static inline void acpi_noirq_set(void) { acpi_noirq = 1; }
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/arch_hooks.h b/include/asm-i386/arch_hooks.h
index 28b96a6fb9f..238cf4275b9 100644
--- a/include/asm-i386/arch_hooks.h
+++ b/include/asm-i386/arch_hooks.h
@@ -24,4 +24,7 @@ extern void trap_init_hook(void);
 extern void time_init_hook(void);
 extern void mca_nmi_hook(void);
 
+extern int setup_early_printk(char *);
+extern void early_printk(const char *fmt, ...) __attribute__((format(printf,1,2)));
+
 #endif
diff --git a/include/asm-i386/atomic.h b/include/asm-i386/atomic.h
index de649d3aa2d..22d80ece95c 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;
@@ -231,8 +225,14 @@ static __inline__ int atomic_sub_return(int i, atomic_t *v)
 ({								\
 	int c, old;						\
 	c = atomic_read(v);					\
-	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c) \
+	for (;;) {						\
+		if (unlikely(c == (u)))				\
+			break;					\
+		old = atomic_cmpxchg((v), c, c + (a));		\
+		if (likely(old == c))				\
+			break;					\
 		c = old;					\
+	}							\
 	c != (u);						\
 })
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
@@ -242,11 +242,11 @@ 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/cache.h b/include/asm-i386/cache.h
index 615911e5bd2..ca15c9c665c 100644
--- a/include/asm-i386/cache.h
+++ b/include/asm-i386/cache.h
@@ -10,4 +10,6 @@
 #define L1_CACHE_SHIFT	(CONFIG_X86_L1_CACHE_SHIFT)
 #define L1_CACHE_BYTES	(1 << L1_CACHE_SHIFT)
 
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
 #endif
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/mach-default/do_timer.h b/include/asm-i386/mach-default/do_timer.h
index 56211414fc9..6312c3e7981 100644
--- a/include/asm-i386/mach-default/do_timer.h
+++ b/include/asm-i386/mach-default/do_timer.h
@@ -18,7 +18,7 @@ static inline void do_timer_interrupt_hook(struct pt_regs *regs)
 {
 	do_timer(regs);
 #ifndef CONFIG_SMP
-	update_process_times(user_mode(regs));
+	update_process_times(user_mode_vm(regs));
 #endif
 /*
  * In the SMP case we use the local APIC timer interrupt to do the
diff --git a/include/asm-i386/mach-es7000/mach_mpparse.h b/include/asm-i386/mach-es7000/mach_mpparse.h
index 4a0637a3e20..99f66be240b 100644
--- a/include/asm-i386/mach-es7000/mach_mpparse.h
+++ b/include/asm-i386/mach-es7000/mach_mpparse.h
@@ -30,7 +30,8 @@ static inline int mps_oem_check(struct mp_config_table *mpc, char *oem,
 	return 0;
 }
 
-static inline int es7000_check_dsdt()
+#ifdef CONFIG_ACPI
+static inline int es7000_check_dsdt(void)
 {
 	struct acpi_table_header *header = NULL;
 	if(!acpi_get_table_header_early(ACPI_DSDT, &header))
@@ -54,6 +55,11 @@ static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	}
 	return 0;
 }
-
+#else
+static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	return 0;
+}
+#endif
 
 #endif /* __ASM_MACH_MPPARSE_H */
diff --git a/include/asm-i386/mach-visws/do_timer.h b/include/asm-i386/mach-visws/do_timer.h
index 92d638fc8b1..95568e6ca91 100644
--- a/include/asm-i386/mach-visws/do_timer.h
+++ b/include/asm-i386/mach-visws/do_timer.h
@@ -11,7 +11,7 @@ static inline void do_timer_interrupt_hook(struct pt_regs *regs)
 
 	do_timer(regs);
 #ifndef CONFIG_SMP
-	update_process_times(user_mode(regs));
+	update_process_times(user_mode_vm(regs));
 #endif
 /*
  * In the SMP case we use the local APIC timer interrupt to do the
diff --git a/include/asm-i386/mach-voyager/do_timer.h b/include/asm-i386/mach-voyager/do_timer.h
index ae510e5d0d7..eaf51809898 100644
--- a/include/asm-i386/mach-voyager/do_timer.h
+++ b/include/asm-i386/mach-voyager/do_timer.h
@@ -5,7 +5,7 @@ static inline void do_timer_interrupt_hook(struct pt_regs *regs)
 {
 	do_timer(regs);
 #ifndef CONFIG_SMP
-	update_process_times(user_mode(regs));
+	update_process_times(user_mode_vm(regs));
 #endif
 
 	voyager_timer_interrupt(regs);
diff --git a/include/asm-i386/mpspec.h b/include/asm-i386/mpspec.h
index 64a0b8e6afe..62113d3bfdc 100644
--- a/include/asm-i386/mpspec.h
+++ b/include/asm-i386/mpspec.h
@@ -22,7 +22,6 @@ extern int mp_bus_id_to_type [MAX_MP_BUSSES];
 extern int mp_irq_entries;
 extern struct mpc_config_intsrc mp_irqs [MAX_IRQ_SOURCES];
 extern int mpc_default_type;
-extern int mp_bus_id_to_pci_bus [MAX_MP_BUSSES];
 extern unsigned long mp_lapic_addr;
 extern int pic_mode;
 extern int using_apic_timer;
diff --git a/include/asm-i386/mtrr.h b/include/asm-i386/mtrr.h
index 5b6ceda68c5..64cf937c7e3 100644
--- a/include/asm-i386/mtrr.h
+++ b/include/asm-i386/mtrr.h
@@ -25,6 +25,7 @@
 
 #include <linux/config.h>
 #include <linux/ioctl.h>
+#include <linux/errno.h>
 
 #define	MTRR_IOCTL_BASE	'M'
 
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/pgtable-2level.h b/include/asm-i386/pgtable-2level.h
index 74ef721b534..27bde973abc 100644
--- a/include/asm-i386/pgtable-2level.h
+++ b/include/asm-i386/pgtable-2level.h
@@ -61,4 +61,6 @@ static inline int pte_exec_kernel(pte_t pte)
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { (pte).pte_low })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val })
 
+void vmalloc_sync_all(void);
+
 #endif /* _I386_PGTABLE_2LEVEL_H */
diff --git a/include/asm-i386/pgtable-3level.h b/include/asm-i386/pgtable-3level.h
index f1a8b454920..36a5aa63cbb 100644
--- a/include/asm-i386/pgtable-3level.h
+++ b/include/asm-i386/pgtable-3level.h
@@ -152,4 +152,6 @@ static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 
 #define __pmd_free_tlb(tlb, x)		do { } while (0)
 
+#define vmalloc_sync_all() ((void)0)
+
 #endif /* _I386_PGTABLE_3LEVEL_H */
diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h
index 088a945bf26..ee056c41a9f 100644
--- a/include/asm-i386/pgtable.h
+++ b/include/asm-i386/pgtable.h
@@ -219,13 +219,12 @@ extern unsigned long pg0[];
  * The following only work if pte_present() is true.
  * Undefined behaviour if not..
  */
-#define __LARGE_PTE (_PAGE_PSE | _PAGE_PRESENT)
 static inline int pte_user(pte_t pte)		{ return (pte).pte_low & _PAGE_USER; }
 static inline int pte_read(pte_t pte)		{ return (pte).pte_low & _PAGE_USER; }
 static inline int pte_dirty(pte_t pte)		{ return (pte).pte_low & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return (pte).pte_low & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)		{ return (pte).pte_low & _PAGE_RW; }
-static inline int pte_huge(pte_t pte)		{ return ((pte).pte_low & __LARGE_PTE) == __LARGE_PTE; }
+static inline int pte_huge(pte_t pte)		{ return (pte).pte_low & _PAGE_PSE; }
 
 /*
  * The following only works if pte_present() is not true.
@@ -242,7 +241,7 @@ static inline pte_t pte_mkexec(pte_t pte)	{ (pte).pte_low |= _PAGE_USER; return
 static inline pte_t pte_mkdirty(pte_t pte)	{ (pte).pte_low |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)	{ (pte).pte_low |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)	{ (pte).pte_low |= _PAGE_RW; return pte; }
-static inline pte_t pte_mkhuge(pte_t pte)	{ (pte).pte_low |= __LARGE_PTE; return pte; }
+static inline pte_t pte_mkhuge(pte_t pte)	{ (pte).pte_low |= _PAGE_PSE; return pte; }
 
 #ifdef CONFIG_X86_PAE
 # include <asm/pgtable-3level.h>
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..d76b7693cf1 100644
--- a/include/asm-i386/spinlock.h
+++ b/include/asm-i386/spinlock.h
@@ -35,31 +35,41 @@
 #define __raw_spin_lock_string_flags \
 	"\n1:\t" \
 	"lock ; decb %0\n\t" \
-	"jns 4f\n\t" \
+	"jns 5f\n" \
 	"2:\t" \
 	"testl $0x200, %1\n\t" \
-	"jz 3f\n\t" \
-	"sti\n\t" \
+	"jz 4f\n\t" \
+	"sti\n" \
 	"3:\t" \
 	"rep;nop\n\t" \
 	"cmpb $0, %0\n\t" \
 	"jle 3b\n\t" \
 	"cli\n\t" \
 	"jmp 1b\n" \
-	"4:\n\t"
+	"4:\t" \
+	"rep;nop\n\t" \
+	"cmpb $0, %0\n\t" \
+	"jg 1b\n\t" \
+	"jmp 4b\n" \
+	"5:\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 +188,12 @@ 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
diff --git a/include/asm-i386/uaccess.h b/include/asm-i386/uaccess.h
index 3f1337c3420..371457b1ceb 100644
--- a/include/asm-i386/uaccess.h
+++ b/include/asm-i386/uaccess.h
@@ -197,13 +197,15 @@ extern void __put_user_8(void);
 
 #define put_user(x,ptr)						\
 ({	int __ret_pu;						\
+	__typeof__(*(ptr)) __pu_val;				\
 	__chk_user_ptr(ptr);					\
+	__pu_val = x;						\
 	switch(sizeof(*(ptr))) {				\
-	case 1: __put_user_1(x, ptr); break;			\
-	case 2: __put_user_2(x, ptr); break;			\
-	case 4: __put_user_4(x, ptr); break;			\
-	case 8: __put_user_8(x, ptr); break;			\
-	default:__put_user_X(x, ptr); break;			\
+	case 1: __put_user_1(__pu_val, ptr); break;		\
+	case 2: __put_user_2(__pu_val, ptr); break;		\
+	case 4: __put_user_4(__pu_val, ptr); break;		\
+	case 8: __put_user_8(__pu_val, ptr); break;		\
+	default:__put_user_X(__pu_val, ptr); break;		\
 	}							\
 	__ret_pu;						\
 })
diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h
index dc81a55dd94..d8afd0e3b81 100644
--- a/include/asm-i386/unistd.h
+++ b/include/asm-i386/unistd.h
@@ -347,9 +347,9 @@ __syscall_return(type,__res); \
 type name(type1 arg1) \
 { \
 long __res; \
-__asm__ volatile ("int $0x80" \
+__asm__ volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx" \
 	: "=a" (__res) \
-	: "0" (__NR_##name),"b" ((long)(arg1)) : "memory"); \
+	: "0" (__NR_##name),"ri" ((long)(arg1)) : "memory"); \
 __syscall_return(type,__res); \
 }
 
@@ -357,9 +357,10 @@ __syscall_return(type,__res); \
 type name(type1 arg1,type2 arg2) \
 { \
 long __res; \
-__asm__ volatile ("int $0x80" \
+__asm__ volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx" \
 	: "=a" (__res) \
-	: "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)) : "memory"); \
+	: "0" (__NR_##name),"ri" ((long)(arg1)),"c" ((long)(arg2)) \
+	: "memory"); \
 __syscall_return(type,__res); \
 }
 
@@ -367,9 +368,9 @@ __syscall_return(type,__res); \
 type name(type1 arg1,type2 arg2,type3 arg3) \
 { \
 long __res; \
-__asm__ volatile ("int $0x80" \
+__asm__ volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx" \
 	: "=a" (__res) \
-	: "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
+	: "0" (__NR_##name),"ri" ((long)(arg1)),"c" ((long)(arg2)), \
 		  "d" ((long)(arg3)) : "memory"); \
 __syscall_return(type,__res); \
 }
@@ -378,9 +379,9 @@ __syscall_return(type,__res); \
 type name (type1 arg1, type2 arg2, type3 arg3, type4 arg4) \
 { \
 long __res; \
-__asm__ volatile ("int $0x80" \
+__asm__ volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx" \
 	: "=a" (__res) \
-	: "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
+	: "0" (__NR_##name),"ri" ((long)(arg1)),"c" ((long)(arg2)), \
 	  "d" ((long)(arg3)),"S" ((long)(arg4)) : "memory"); \
 __syscall_return(type,__res); \
 } 
@@ -390,10 +391,12 @@ __syscall_return(type,__res); \
 type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5) \
 { \
 long __res; \
-__asm__ volatile ("int $0x80" \
+__asm__ volatile ("push %%ebx ; movl %2,%%ebx ; movl %1,%%eax ; " \
+                  "int $0x80 ; pop %%ebx" \
 	: "=a" (__res) \
-	: "0" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
-	  "d" ((long)(arg3)),"S" ((long)(arg4)),"D" ((long)(arg5)) : "memory"); \
+	: "i" (__NR_##name),"ri" ((long)(arg1)),"c" ((long)(arg2)), \
+	  "d" ((long)(arg3)),"S" ((long)(arg4)),"D" ((long)(arg5)) \
+	: "memory"); \
 __syscall_return(type,__res); \
 }
 
@@ -402,11 +405,14 @@ __syscall_return(type,__res); \
 type name (type1 arg1,type2 arg2,type3 arg3,type4 arg4,type5 arg5,type6 arg6) \
 { \
 long __res; \
-__asm__ volatile ("push %%ebp ; movl %%eax,%%ebp ; movl %1,%%eax ; int $0x80 ; pop %%ebp" \
+  struct { long __a1; long __a6; } __s = { (long)arg1, (long)arg6 }; \
+__asm__ volatile ("push %%ebp ; push %%ebx ; movl 4(%2),%%ebp ; " \
+                  "movl 0(%2),%%ebx ; movl %1,%%eax ; int $0x80 ; " \
+                  "pop %%ebx ;  pop %%ebp" \
 	: "=a" (__res) \
-	: "i" (__NR_##name),"b" ((long)(arg1)),"c" ((long)(arg2)), \
-	  "d" ((long)(arg3)),"S" ((long)(arg4)),"D" ((long)(arg5)), \
-	  "0" ((long)(arg6)) : "memory"); \
+	: "i" (__NR_##name),"0" ((long)(&__s)),"c" ((long)(arg2)), \
+	  "d" ((long)(arg3)),"S" ((long)(arg4)),"D" ((long)(arg5)) \
+	: "memory"); \
 __syscall_return(type,__res); \
 }