Merge branch 'master' of /home/aia21/ntfs-2.6/

68 files changed, 454 insertions, 268 deletions

diff --git a/include/asm-alpha/mmu_context.h b/include/asm-alpha/mmu_context.h
index 6f92482..0c017fc 100644
--- a/include/asm-alpha/mmu_context.h
+++ b/include/asm-alpha/mmu_context.h
@@ -231,9 +231,8 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
 	int i;
 
-	for (i = 0; i < NR_CPUS; i++)
-		if (cpu_online(i))
-			mm->context[i] = 0;
+	for_each_online_cpu(i)
+		mm->context[i] = 0;
 	if (tsk != current)
 		task_thread_info(tsk)->pcb.ptbr
 		  = ((unsigned long)mm->pgd - IDENT_ADDR) >> PAGE_SHIFT;
diff --git a/include/asm-alpha/topology.h b/include/asm-alpha/topology.h
index eb740e2..420ccde 100644
--- a/include/asm-alpha/topology.h
+++ b/include/asm-alpha/topology.h
@@ -27,8 +27,8 @@ static inline cpumask_t node_to_cpumask(int node)
 	cpumask_t node_cpu_mask = CPU_MASK_NONE;
 	int cpu;
 
-	for(cpu = 0; cpu < NR_CPUS; cpu++) {
-		if (cpu_online(cpu) && (cpu_to_node(cpu) == node))
+	for_each_online_cpu(cpu) {
+		if (cpu_to_node(cpu) == node)
 			cpu_set(cpu, node_cpu_mask);
 	}
 
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 400c2b4..1a565a9 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -7,7 +7,7 @@
 #ifdef CONFIG_BUG
 #ifndef HAVE_ARCH_BUG
 #define BUG() do { \
-	printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \
+	printk("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __FUNCTION__); \
 	panic("BUG!"); \
 } while (0)
 #endif
@@ -19,7 +19,7 @@
 #ifndef HAVE_ARCH_WARN_ON
 #define WARN_ON(condition) do { \
 	if (unlikely((condition)!=0)) { \
-		printk("Badness in %s at %s:%d\n", __FUNCTION__, __FILE__, __LINE__); \
+		printk("BUG: warning at %s:%d/%s()\n", __FILE__, __LINE__, __FUNCTION__); \
 		dump_stack(); \
 	} \
 } while (0)
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 9044aeb..78cf455 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -19,10 +19,9 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 #define percpu_modcopy(pcpudst, src, size)			\
 do {								\
 	unsigned int __i;					\
-	for (__i = 0; __i < NR_CPUS; __i++)			\
-		if (cpu_possible(__i))				\
-			memcpy((pcpudst)+__per_cpu_offset[__i],	\
-			       (src), (size));			\
+	for_each_cpu(__i)					\
+		memcpy((pcpudst)+__per_cpu_offset[__i],		\
+		       (src), (size));				\
 } while (0)
 #else /* ! SMP */
 
diff --git a/include/asm-i386/alternative.h b/include/asm-i386/alternative.h
new file mode 100644
index 0000000..e201dec
--- /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 28b96a6..238cf42 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 de649d3..22d80ec 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 88e6ca2..7d20b95 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 615911e..ca15c9c 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 c4ec2a4..5c0b587 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 5621141..6312c3e 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 4a0637a..99f66be 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 92d638f..95568e6 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 ae510e5..eaf5180 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 64a0b8e..62113d3 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 5b6ceda..64cf937 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 9b2199e..05a5385 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 74ef721..27bde97 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 f1a8b45..36a5aa6 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/rwlock.h b/include/asm-i386/rwlock.h
index b57cc7a..94f0019 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 6a42b21..f7a0f31 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 2360435..d76b769 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 399145a..d0d8d74 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 3f1337c..371457b 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 dc81a55..d8afd0e 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); \
 }
 
diff --git a/include/asm-ia64/atomic.h b/include/asm-ia64/atomic.h
index d3e0dfa..569ec75 100644
--- a/include/asm-ia64/atomic.h
+++ b/include/asm-ia64/atomic.h
@@ -95,8 +95,14 @@ ia64_atomic64_sub (__s64 i, atomic64_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)
diff --git a/include/asm-ia64/cache.h b/include/asm-ia64/cache.h
index 40dd2519..f0a104d 100644
--- a/include/asm-ia64/cache.h
+++ b/include/asm-ia64/cache.h
@@ -25,4 +25,6 @@
 # define SMP_CACHE_BYTES	(1 << 3)
 #endif
 
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
 #endif /* _ASM_IA64_CACHE_H */
diff --git a/include/asm-m68k/atomic.h b/include/asm-m68k/atomic.h
index 862e497..732d696 100644
--- a/include/asm-m68k/atomic.h
+++ b/include/asm-m68k/atomic.h
@@ -175,8 +175,14 @@ static inline void atomic_set_mask(unsigned long mask, unsigned long *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)
diff --git a/include/asm-parisc/cache.h b/include/asm-parisc/cache.h
index 93f179f..ae50f8e 100644
--- a/include/asm-parisc/cache.h
+++ b/include/asm-parisc/cache.h
@@ -29,6 +29,8 @@
 
 #define SMP_CACHE_BYTES L1_CACHE_BYTES
 
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
 extern void flush_data_cache_local(void *);  /* flushes local data-cache only */
 extern void flush_instruction_cache_local(void *); /* flushes local code-cache only */
 #ifdef CONFIG_SMP
diff --git a/include/asm-powerpc/percpu.h b/include/asm-powerpc/percpu.h
index e31922c..464301c 100644
--- a/include/asm-powerpc/percpu.h
+++ b/include/asm-powerpc/percpu.h
@@ -27,10 +27,9 @@
 #define percpu_modcopy(pcpudst, src, size)			\
 do {								\
 	unsigned int __i;					\
-	for (__i = 0; __i < NR_CPUS; __i++)			\
-		if (cpu_possible(__i))				\
-			memcpy((pcpudst)+__per_cpu_offset(__i),	\
-			       (src), (size));			\
+	for_each_cpu(__i)					\
+		memcpy((pcpudst)+__per_cpu_offset(__i),		\
+		       (src), (size));				\
 } while (0)
 
 extern void setup_per_cpu_areas(void);
diff --git a/include/asm-s390/atomic.h b/include/asm-s390/atomic.h
index be6fefe..de1d992 100644
--- a/include/asm-s390/atomic.h
+++ b/include/asm-s390/atomic.h
@@ -89,10 +89,15 @@ static __inline__ int atomic_cmpxchg(atomic_t *v, int old, int new)
 static __inline__ int atomic_add_unless(atomic_t *v, int a, int u)
 {
 	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;
+	}
 	return c != u;
 }
 
@@ -167,10 +172,15 @@ static __inline__ int atomic64_add_unless(atomic64_t *v,
 					  long long a, long long u)
 {
 	long long c, old;
-
 	c = atomic64_read(v);
-	while (c != u && (old = atomic64_cmpxchg(v, c, c + a)) != c)
+	for (;;) {
+		if (unlikely(c == u))
+			break;
+		old = atomic64_cmpxchg(v, c, c + a);
+		if (likely(old == c))
+			break;
 		c = old;
+	}
 	return c != u;
 }
 
diff --git a/include/asm-s390/percpu.h b/include/asm-s390/percpu.h
index 123fcac..e10ed87 100644
--- a/include/asm-s390/percpu.h
+++ b/include/asm-s390/percpu.h
@@ -46,10 +46,9 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 #define percpu_modcopy(pcpudst, src, size)			\
 do {								\
 	unsigned int __i;					\
-	for (__i = 0; __i < NR_CPUS; __i++)			\
-		if (cpu_possible(__i))				\
-			memcpy((pcpudst)+__per_cpu_offset[__i],	\
-			       (src), (size));			\
+	for_each_cpu(__i)					\
+		memcpy((pcpudst)+__per_cpu_offset[__i],		\
+		       (src), (size));				\
 } while (0)
 
 #else /* ! SMP */
diff --git a/include/asm-sparc64/atomic.h b/include/asm-sparc64/atomic.h
index 25256bd..468eb48 100644
--- a/include/asm-sparc64/atomic.h
+++ b/include/asm-sparc64/atomic.h
@@ -78,9 +78,15 @@ extern int atomic64_sub_ret(int, atomic64_t *);
 ({								\
 	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);						\
+	}							\
+	likely(c != (u));					\
 })
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
 
diff --git a/include/asm-sparc64/cache.h b/include/asm-sparc64/cache.h
index f7d35a2..e9df17a 100644
--- a/include/asm-sparc64/cache.h
+++ b/include/asm-sparc64/cache.h
@@ -13,4 +13,6 @@
 #define        SMP_CACHE_BYTES_SHIFT	6
 #define        SMP_CACHE_BYTES		(1 << SMP_CACHE_BYTES_SHIFT) /* L2 cache line size. */
 
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
 #endif
diff --git a/include/asm-sparc64/percpu.h b/include/asm-sparc64/percpu.h
index aea4e51..82032e1 100644
--- a/include/asm-sparc64/percpu.h
+++ b/include/asm-sparc64/percpu.h
@@ -26,10 +26,9 @@ register unsigned long __local_per_cpu_offset asm("g5");
 #define percpu_modcopy(pcpudst, src, size)			\
 do {								\
 	unsigned int __i;					\
-	for (__i = 0; __i < NR_CPUS; __i++)			\
-		if (cpu_possible(__i))				\
-			memcpy((pcpudst)+__per_cpu_offset(__i),	\
-			       (src), (size));			\
+	for_each_cpu(__i)					\
+		memcpy((pcpudst)+__per_cpu_offset(__i),		\
+		       (src), (size));				\
 } while (0)
 #else /* ! SMP */
 
diff --git a/include/asm-um/alternative.h b/include/asm-um/alternative.h
new file mode 100644
index 0000000..b643439
--- /dev/null
+++ b/include/asm-um/alternative.h
@@ -0,0 +1,6 @@
+#ifndef __UM_ALTERNATIVE_H
+#define __UM_ALTERNATIVE_H
+
+#include "asm/arch/alternative.h"
+
+#endif
diff --git a/include/asm-x86_64/atomic.h b/include/asm-x86_64/atomic.h
index 4b5cd55..cecbf7b 100644
--- a/include/asm-x86_64/atomic.h
+++ b/include/asm-x86_64/atomic.h
@@ -405,8 +405,14 @@ static __inline__ long atomic64_sub_return(long i, atomic64_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)
diff --git a/include/asm-x86_64/cache.h b/include/asm-x86_64/cache.h
index 263f0a2..c8043a1 100644
--- a/include/asm-x86_64/cache.h
+++ b/include/asm-x86_64/cache.h
@@ -20,6 +20,8 @@
        __attribute__((__section__(".data.page_aligned")))
 #endif
 
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
 #endif
 
 #endif
diff --git a/include/asm-x86_64/percpu.h b/include/asm-x86_64/percpu.h
index 29a6b04..4405b4a 100644
--- a/include/asm-x86_64/percpu.h
+++ b/include/asm-x86_64/percpu.h
@@ -26,10 +26,9 @@
 #define percpu_modcopy(pcpudst, src, size)			\
 do {								\
 	unsigned int __i;					\
-	for (__i = 0; __i < NR_CPUS; __i++)			\
-		if (cpu_possible(__i))				\
-			memcpy((pcpudst)+__per_cpu_offset(__i),	\
-			       (src), (size));			\
+	for_each_cpu(__i)					\
+		memcpy((pcpudst)+__per_cpu_offset(__i),		\
+		       (src), (size));				\
 } while (0)
 
 extern void setup_per_cpu_areas(void);
diff --git a/include/linux/cache.h b/include/linux/cache.h
index d22e632..cc4b3aa 100644
--- a/include/linux/cache.h
+++ b/include/linux/cache.h
@@ -13,9 +13,7 @@
 #define SMP_CACHE_BYTES L1_CACHE_BYTES
 #endif
 
-#if defined(CONFIG_X86) || defined(CONFIG_SPARC64) || defined(CONFIG_IA64) || defined(CONFIG_PARISC)
-#define __read_mostly __attribute__((__section__(".data.read_mostly")))
-#else
+#ifndef __read_mostly
 #define __read_mostly
 #endif
 
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index b68fdf1..3c9b0bc 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -378,7 +378,6 @@ struct cdrom_generic_command
 #define CDC_MEDIA_CHANGED 	0x80    /* media changed */
 #define CDC_PLAY_AUDIO		0x100   /* audio functions */
 #define CDC_RESET               0x200   /* hard reset device */
-#define CDC_IOCTLS              0x400   /* driver has non-standard ioctls */
 #define CDC_DRIVE_STATUS        0x800   /* driver implements drive status */
 #define CDC_GENERIC_PACKET	0x1000	/* driver implements generic packets */
 #define CDC_CD_R		0x2000	/* drive is a CD-R */
@@ -974,9 +973,7 @@ struct cdrom_device_ops {
 	int (*reset) (struct cdrom_device_info *);
 	/* play stuff */
 	int (*audio_ioctl) (struct cdrom_device_info *,unsigned int, void *);
-	/* dev-specific */
- 	int (*dev_ioctl) (struct cdrom_device_info *,
-			  unsigned int, unsigned long);
+
 /* driver specifications */
 	const int capability;   /* capability flags */
 	int n_minors;           /* number of active minor devices */
diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
index 1289f0e..1e4bdfc 100644
--- a/include/linux/eventpoll.h
+++ b/include/linux/eventpoll.h
@@ -52,7 +52,12 @@ struct file;
 #ifdef CONFIG_EPOLL
 
 /* Used to initialize the epoll bits inside the "struct file" */
-void eventpoll_init_file(struct file *file);
+static inline void eventpoll_init_file(struct file *file)
+{
+	INIT_LIST_HEAD(&file->f_ep_links);
+	spin_lock_init(&file->f_ep_lock);
+}
+
 
 /* Used to release the epoll bits inside the "struct file" */
 void eventpoll_release_file(struct file *file);
@@ -85,7 +90,6 @@ static inline void eventpoll_release(struct file *file)
 	eventpoll_release_file(file);
 }
 
-
 #else
 
 static inline void eventpoll_init_file(struct file *file) {}
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index c0272d7..e7239f2 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -772,9 +772,12 @@ extern unsigned long ext3_count_free (struct buffer_head *, unsigned);
 
 
 /* inode.c */
-extern int ext3_forget(handle_t *, int, struct inode *, struct buffer_head *, int);
-extern struct buffer_head * ext3_getblk (handle_t *, struct inode *, long, int, int *);
-extern struct buffer_head * ext3_bread (handle_t *, struct inode *, int, int, int *);
+int ext3_forget(handle_t *, int, struct inode *, struct buffer_head *, int);
+struct buffer_head * ext3_getblk (handle_t *, struct inode *, long, int, int *);
+struct buffer_head * ext3_bread (handle_t *, struct inode *, int, int, int *);
+int ext3_get_block_handle(handle_t *handle, struct inode *inode,
+	sector_t iblock, struct buffer_head *bh_result, int create,
+	int extend_disksize);
 
 extern void ext3_read_inode (struct inode *);
 extern int  ext3_write_inode (struct inode *, int);
diff --git a/include/linux/ext3_fs_i.h b/include/linux/ext3_fs_i.h
index e71dd98..7abf901 100644
--- a/include/linux/ext3_fs_i.h
+++ b/include/linux/ext3_fs_i.h
@@ -19,6 +19,7 @@
 #include <linux/rwsem.h>
 #include <linux/rbtree.h>
 #include <linux/seqlock.h>
+#include <linux/mutex.h>
 
 struct ext3_reserve_window {
 	__u32			_rsv_start;	/* First byte reserved */
@@ -122,16 +123,16 @@ struct ext3_inode_info {
 	__u16 i_extra_isize;
 
 	/*
-	 * truncate_sem is for serialising ext3_truncate() against
+	 * truncate_mutex is for serialising ext3_truncate() against
 	 * ext3_getblock().  In the 2.4 ext2 design, great chunks of inode's
 	 * data tree are chopped off during truncate. We can't do that in
 	 * ext3 because whenever we perform intermediate commits during
 	 * truncate, the inode and all the metadata blocks *must* be in a
 	 * consistent state which allows truncation of the orphans to restart
 	 * during recovery.  Hence we must fix the get_block-vs-truncate race
-	 * by other means, so we have truncate_sem.
+	 * by other means, so we have truncate_mutex.
 	 */
-	struct semaphore truncate_sem;
+	struct mutex truncate_mutex;
 	struct inode vfs_inode;
 };
 
diff --git a/include/linux/file.h b/include/linux/file.h
index 9901b85..9f7c251 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -10,6 +10,7 @@
 #include <linux/compiler.h>
 #include <linux/spinlock.h>
 #include <linux/rcupdate.h>
+#include <linux/types.h>
 
 /*
  * The default fd array needs to be at least BITS_PER_LONG,
@@ -17,10 +18,22 @@
  */
 #define NR_OPEN_DEFAULT BITS_PER_LONG
 
+/*
+ * The embedded_fd_set is a small fd_set,
+ * suitable for most tasks (which open <= BITS_PER_LONG files)
+ */
+struct embedded_fd_set {
+	unsigned long fds_bits[1];
+};
+
+/*
+ * More than this number of fds: we use a separately allocated fd_set
+ */
+#define EMBEDDED_FD_SET_SIZE (BITS_PER_BYTE * sizeof(struct embedded_fd_set))
+
 struct fdtable {
 	unsigned int max_fds;
 	int max_fdset;
-	int next_fd;
 	struct file ** fd;      /* current fd array */
 	fd_set *close_on_exec;
 	fd_set *open_fds;
@@ -33,13 +46,20 @@ struct fdtable {
  * Open file table structure
  */
 struct files_struct {
+  /*
+   * read mostly part
+   */
 	atomic_t count;
 	struct fdtable *fdt;
 	struct fdtable fdtab;
-	fd_set close_on_exec_init;
-	fd_set open_fds_init;
+  /*
+   * written part on a separate cache line in SMP
+   */
+	spinlock_t file_lock ____cacheline_aligned_in_smp;
+	int next_fd;
+	struct embedded_fd_set close_on_exec_init;
+	struct embedded_fd_set open_fds_init;
 	struct file * fd_array[NR_OPEN_DEFAULT];
-	spinlock_t file_lock;     /* Protects concurrent writers.  Nests inside tsk->alloc_lock */
 };
 
 #define files_fdtable(files) (rcu_dereference((files)->fdt))
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 128d008..f9c9dea 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -397,8 +397,8 @@ struct block_device {
 	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
 	struct inode *		bd_inode;	/* will die */
 	int			bd_openers;
-	struct semaphore	bd_sem;	/* open/close mutex */
-	struct semaphore	bd_mount_sem;	/* mount mutex */
+	struct mutex		bd_mutex;	/* open/close mutex */
+	struct mutex		bd_mount_mutex;	/* mount mutex */
 	struct list_head	bd_inodes;
 	void *			bd_holder;
 	int			bd_holders;
@@ -509,7 +509,7 @@ struct inode {
 
 #ifdef CONFIG_INOTIFY
 	struct list_head	inotify_watches; /* watches on this inode */
-	struct semaphore	inotify_sem;	/* protects the watches list */
+	struct mutex		inotify_mutex;	/* protects the watches list */
 #endif
 
 	unsigned long		i_state;
@@ -847,7 +847,7 @@ struct super_block {
 	 * The next field is for VFS *only*. No filesystems have any business
 	 * even looking at it. You had been warned.
 	 */
-	struct semaphore s_vfs_rename_sem;	/* Kludge */
+	struct mutex s_vfs_rename_mutex;	/* Kludge */
 
 	/* Granuality of c/m/atime in ns.
 	   Cannot be worse than a second */
@@ -1115,6 +1115,18 @@ static inline void mark_inode_dirty_sync(struct inode *inode)
 	__mark_inode_dirty(inode, I_DIRTY_SYNC);
 }
 
+static inline void inode_inc_link_count(struct inode *inode)
+{
+	inode->i_nlink++;
+	mark_inode_dirty(inode);
+}
+
+static inline void inode_dec_link_count(struct inode *inode)
+{
+	inode->i_nlink--;
+	mark_inode_dirty(inode);
+}
+
 extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry);
 static inline void file_accessed(struct file *file)
 {
@@ -1534,7 +1546,7 @@ extern void destroy_inode(struct inode *);
 extern struct inode *new_inode(struct super_block *);
 extern int remove_suid(struct dentry *);
 extern void remove_dquot_ref(struct super_block *, int, struct list_head *);
-extern struct semaphore iprune_sem;
+extern struct mutex iprune_mutex;
 
 extern void __insert_inode_hash(struct inode *, unsigned long hashval);
 extern void remove_inode_hash(struct inode *);
diff --git a/include/linux/generic_serial.h b/include/linux/generic_serial.h
index 0abe9d9..652611a 100644
--- a/include/linux/generic_serial.h
+++ b/include/linux/generic_serial.h
@@ -12,6 +12,8 @@
 #ifndef GENERIC_SERIAL_H
 #define GENERIC_SERIAL_H
 
+#include <linux/mutex.h>
+
 struct real_driver {
   void                    (*disable_tx_interrupts) (void *);
   void                    (*enable_tx_interrupts) (void *);
@@ -34,7 +36,7 @@ struct gs_port {
   int                     xmit_head;
   int                     xmit_tail;
   int                     xmit_cnt;
-  struct semaphore        port_write_sem;
+  struct mutex            port_write_mutex;
   int                     flags;
   wait_queue_head_t       open_wait;
   wait_queue_head_t       close_wait;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index eef5ccd..fd647fd 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -149,22 +149,16 @@ struct disk_attribute {
 ({									\
 	typeof(gendiskp->dkstats->field) res = 0;			\
 	int i;								\
-	for (i=0; i < NR_CPUS; i++) {					\
-		if (!cpu_possible(i))					\
-			continue;					\
+	for_each_cpu(i)							\
 		res += per_cpu_ptr(gendiskp->dkstats, i)->field;	\
-	}								\
 	res;								\
 })
 
 static inline void disk_stat_set_all(struct gendisk *gendiskp, int value)	{
 	int i;
-	for (i=0; i < NR_CPUS; i++) {
-		if (cpu_possible(i)) {
-			memset(per_cpu_ptr(gendiskp->dkstats, i), value,	
-					sizeof (struct disk_stats));
-		}
-	}
+	for_each_cpu(i)
+		memset(per_cpu_ptr(gendiskp->dkstats, i), value,
+				sizeof (struct disk_stats));
 }		
 				
 #else
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index dcfd2ec..92146f3 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -7,11 +7,10 @@
 #define INIT_FDTABLE \
 {							\
 	.max_fds	= NR_OPEN_DEFAULT, 		\
-	.max_fdset	= __FD_SETSIZE, 		\
-	.next_fd	= 0, 				\
+	.max_fdset	= EMBEDDED_FD_SET_SIZE,		\
 	.fd		= &init_files.fd_array[0], 	\
-	.close_on_exec	= &init_files.close_on_exec_init, \
-	.open_fds	= &init_files.open_fds_init, 	\
+	.close_on_exec	= (fd_set *)&init_files.close_on_exec_init, \
+	.open_fds	= (fd_set *)&init_files.open_fds_init, 	\
 	.rcu		= RCU_HEAD_INIT, 		\
 	.free_files	= NULL,		 		\
 	.next		= NULL,		 		\
@@ -20,9 +19,10 @@
 #define INIT_FILES \
 { 							\
 	.count		= ATOMIC_INIT(1), 		\
-	.file_lock	= SPIN_LOCK_UNLOCKED, 		\
 	.fdt		= &init_files.fdtab, 		\
 	.fdtab		= INIT_FDTABLE,			\
+	.file_lock	= SPIN_LOCK_UNLOCKED, 		\
+	.next_fd	= 0, 				\
 	.close_on_exec_init = { { 0, } }, 		\
 	.open_fds_init	= { { 0, } }, 			\
 	.fd_array	= { NULL, } 			\
diff --git a/include/linux/jbd.h b/include/linux/jbd.h
index 41ee799..2ccbfb6 100644
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@@ -28,6 +28,7 @@
 #include <linux/journal-head.h>
 #include <linux/stddef.h>
 #include <linux/bit_spinlock.h>
+#include <linux/mutex.h>
 #include <asm/semaphore.h>
 #endif
 
@@ -575,7 +576,7 @@ struct transaction_s
  * @j_wait_checkpoint:  Wait queue to trigger checkpointing
  * @j_wait_commit: Wait queue to trigger commit
  * @j_wait_updates: Wait queue to wait for updates to complete
- * @j_checkpoint_sem: Semaphore for locking against concurrent checkpoints
+ * @j_checkpoint_mutex: Mutex for locking against concurrent checkpoints
  * @j_head: Journal head - identifies the first unused block in the journal
  * @j_tail: Journal tail - identifies the oldest still-used block in the
  *  journal.
@@ -645,7 +646,7 @@ struct journal_s
 	int			j_barrier_count;
 
 	/* The barrier lock itself */
-	struct semaphore	j_barrier;
+	struct mutex		j_barrier;
 
 	/*
 	 * Transactions: The current running transaction...
@@ -687,7 +688,7 @@ struct journal_s
 	wait_queue_head_t	j_wait_updates;
 
 	/* Semaphore for locking against concurrent checkpoints */
-	struct semaphore 	j_checkpoint_sem;
+	struct mutex	 	j_checkpoint_mutex;
 
 	/*
 	 * Journal head: identifies the first unused block in the journal.
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 3b507bf..bb6e7dd 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -91,6 +91,9 @@ extern struct notifier_block *panic_notifier_list;
 extern long (*panic_blink)(long time);
 NORET_TYPE void panic(const char * fmt, ...)
 	__attribute__ ((NORET_AND format (printf, 1, 2)));
+extern void oops_enter(void);
+extern void oops_exit(void);
+extern int oops_may_print(void);
 fastcall NORET_TYPE void do_exit(long error_code)
 	ATTRIB_NORET;
 NORET_TYPE void complete_and_exit(struct completion *, long)
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 669756b..778adc0 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -36,6 +36,7 @@
 #include <linux/percpu.h>
 #include <linux/spinlock.h>
 #include <linux/rcupdate.h>
+#include <linux/mutex.h>
 
 #ifdef CONFIG_KPROBES
 #include <asm/kprobes.h>
@@ -152,7 +153,7 @@ struct kretprobe_instance {
 };
 
 extern spinlock_t kretprobe_lock;
-extern struct semaphore kprobe_mutex;
+extern struct mutex kprobe_mutex;
 extern int arch_prepare_kprobe(struct kprobe *p);
 extern void arch_arm_kprobe(struct kprobe *p);
 extern void arch_disarm_kprobe(struct kprobe *p);
diff --git a/include/linux/loop.h b/include/linux/loop.h
index f965067..e76c761 100644
--- a/include/linux/loop.h
+++ b/include/linux/loop.h
@@ -17,6 +17,7 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 #include <linux/spinlock.h>
+#include <linux/mutex.h>
 
 /* Possible states of device */
 enum {
@@ -60,7 +61,7 @@ struct loop_device {
 	int			lo_state;
 	struct completion	lo_done;
 	struct completion	lo_bh_done;
-	struct semaphore	lo_ctl_mutex;
+	struct mutex		lo_ctl_mutex;
 	int			lo_pending;
 
 	request_queue_t		*lo_queue;
diff --git a/include/linux/msdos_fs.h b/include/linux/msdos_fs.h
index 8bcd945..779e6a5 100644
--- a/include/linux/msdos_fs.h
+++ b/include/linux/msdos_fs.h
@@ -184,6 +184,7 @@ struct fat_slot_info {
 #include <linux/string.h>
 #include <linux/nls.h>
 #include <linux/fs.h>
+#include <linux/mutex.h>
 
 struct fat_mount_options {
 	uid_t fs_uid;
@@ -226,7 +227,7 @@ struct msdos_sb_info {
 	unsigned long max_cluster;   /* maximum cluster number */
 	unsigned long root_cluster;  /* first cluster of the root directory */
 	unsigned long fsinfo_sector; /* sector number of FAT32 fsinfo */
-	struct semaphore fat_lock;
+	struct mutex fat_lock;
 	unsigned int prev_free;      /* previously allocated cluster number */
 	unsigned int free_clusters;  /* -1 if undefined */
 	struct fat_mount_options options;
diff --git a/include/linux/nbd.h b/include/linux/nbd.h
index f95d51f..a6ce409 100644
--- a/include/linux/nbd.h
+++ b/include/linux/nbd.h
@@ -38,6 +38,7 @@ enum {
 #ifdef __KERNEL__
 
 #include <linux/wait.h>
+#include <linux/mutex.h>
 
 /* values for flags field */
 #define NBD_READ_ONLY 0x0001
@@ -57,7 +58,7 @@ struct nbd_device {
 	struct request *active_req;
 	wait_queue_head_t active_wq;
 
-	struct semaphore tx_lock;
+	struct mutex tx_lock;
 	struct gendisk *disk;
 	int blksize;
 	u64 bytesize;
diff --git a/include/linux/ncp_fs_i.h b/include/linux/ncp_fs_i.h
index 415be1e..bdb4c8a 100644
--- a/include/linux/ncp_fs_i.h
+++ b/include/linux/ncp_fs_i.h
@@ -19,7 +19,7 @@ struct ncp_inode_info {
 	__le32	DosDirNum;
 	__u8	volNumber;
 	__le32	nwattr;
-	struct semaphore open_sem;
+	struct mutex open_mutex;
 	atomic_t	opened;
 	int	access;
 	int	flags;
diff --git a/include/linux/ncp_fs_sb.h b/include/linux/ncp_fs_sb.h
index cf858eb..b089d95 100644
--- a/include/linux/ncp_fs_sb.h
+++ b/include/linux/ncp_fs_sb.h
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include <linux/ncp_mount.h>
 #include <linux/net.h>
+#include <linux/mutex.h>
 
 #ifdef __KERNEL__
 
@@ -51,7 +52,7 @@ struct ncp_server {
 				   receive replies */
 
 	int lock;		/* To prevent mismatch in protocols. */
-	struct semaphore sem;
+	struct mutex mutex;
 
 	int current_size;	/* for packet preparation */
 	int has_subfunction;
@@ -96,7 +97,7 @@ struct ncp_server {
 	struct {
 		struct work_struct tq;		/* STREAM/DGRAM: data/error ready */
 		struct ncp_request_reply* creq;	/* STREAM/DGRAM: awaiting reply from this request */
-		struct semaphore creq_sem;	/* DGRAM only: lock accesses to rcv.creq */
+		struct mutex creq_mutex;	/* DGRAM only: lock accesses to rcv.creq */
 
 		unsigned int state;		/* STREAM only: receiver state */
 		struct {
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 5be87ba..6df2585 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -188,6 +188,8 @@ extern void device_power_up(void);
 extern void device_resume(void);
 
 #ifdef CONFIG_PM
+extern suspend_disk_method_t pm_disk_mode;
+
 extern int device_suspend(pm_message_t state);
 
 #define device_set_wakeup_enable(dev,val) \
@@ -215,7 +217,6 @@ static inline int dpm_runtime_suspend(struct device * dev, pm_message_t state)
 
 static inline void dpm_runtime_resume(struct device * dev)
 {
-
 }
 
 #endif
diff --git a/include/linux/profile.h b/include/linux/profile.h
index 026969a..1f2fea6 100644
--- a/include/linux/profile.h
+++ b/include/linux/profile.h
@@ -14,6 +14,7 @@
 
 struct proc_dir_entry;
 struct pt_regs;
+struct notifier_block;
 
 /* init basic kernel profiler */
 void __init profile_init(void);
@@ -32,7 +33,6 @@ enum profile_type {
 
 #ifdef CONFIG_PROFILING
 
-struct notifier_block;
 struct task_struct;
 struct mm_struct;
 
diff --git a/include/linux/quota.h b/include/linux/quota.h
index f33aeb2..8dc2d04 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -38,6 +38,7 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/spinlock.h>
+#include <linux/mutex.h>
 
 #define __DQUOT_VERSION__	"dquot_6.5.1"
 #define __DQUOT_NUM_VERSION__	6*10000+5*100+1
@@ -215,7 +216,7 @@ struct dquot {
 	struct list_head dq_inuse;	/* List of all quotas */
 	struct list_head dq_free;	/* Free list element */
 	struct list_head dq_dirty;	/* List of dirty dquots */
-	struct semaphore dq_lock;	/* dquot IO lock */
+	struct mutex dq_lock;		/* dquot IO lock */
 	atomic_t dq_count;		/* Use count */
 	wait_queue_head_t dq_wait_unused;	/* Wait queue for dquot to become unused */
 	struct super_block *dq_sb;	/* superblock this applies to */
@@ -285,8 +286,8 @@ struct quota_format_type {
 
 struct quota_info {
 	unsigned int flags;			/* Flags for diskquotas on this device */
-	struct semaphore dqio_sem;		/* lock device while I/O in progress */
-	struct semaphore dqonoff_sem;		/* Serialize quotaon & quotaoff */
+	struct mutex dqio_mutex;		/* lock device while I/O in progress */
+	struct mutex dqonoff_mutex;		/* Serialize quotaon & quotaoff */
 	struct rw_semaphore dqptr_sem;		/* serialize ops using quota_info struct, pointers from inode to dquots */
 	struct inode *files[MAXQUOTAS];		/* inodes of quotafiles */
 	struct mem_dqinfo info[MAXQUOTAS];	/* Information for each quota type */
diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h
index 9d5494a..3009c81 100644
--- a/include/linux/raid/raid1.h
+++ b/include/linux/raid/raid1.h
@@ -130,6 +130,6 @@ struct r1bio_s {
  * with failure when last write completes (and all failed).
  * Record that bi_end_io was called with this flag...
  */
-#define	R1BIO_Returned 4
+#define	R1BIO_Returned 6
 
 #endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index c2ec6c7..5673008 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -113,8 +113,6 @@ struct rcu_data {
 
 DECLARE_PER_CPU(struct rcu_data, rcu_data);
 DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
-extern struct rcu_ctrlblk rcu_ctrlblk;
-extern struct rcu_ctrlblk rcu_bh_ctrlblk;
 
 /*
  * Increment the quiescent state counter.
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 850a974..b95f6eb 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -4,7 +4,7 @@
 
 #include <linux/types.h>
 #include <linux/string.h>
-#include <asm/semaphore.h>
+#include <linux/mutex.h>
 
 struct seq_operations;
 struct file;
@@ -19,7 +19,7 @@ struct seq_file {
 	size_t count;
 	loff_t index;
 	loff_t version;
-	struct semaphore sem;
+	struct mutex lock;
 	struct seq_operations *op;
 	void *private;
 };
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 12415dd..54eac8a 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -234,14 +234,15 @@ extern struct page * read_swap_cache_async(swp_entry_t, struct vm_area_struct *v
 /* linux/mm/swapfile.c */
 extern long total_swap_pages;
 extern unsigned int nr_swapfiles;
-extern struct swap_info_struct swap_info[];
 extern void si_swapinfo(struct sysinfo *);
 extern swp_entry_t get_swap_page(void);
-extern swp_entry_t get_swap_page_of_type(int type);
+extern swp_entry_t get_swap_page_of_type(int);
 extern int swap_duplicate(swp_entry_t);
 extern int valid_swaphandles(swp_entry_t, unsigned long *);
 extern void swap_free(swp_entry_t);
 extern void free_swap_and_cache(swp_entry_t);
+extern int swap_type_of(dev_t);
+extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct swap_info_struct *, pgoff_t);
 extern struct swap_info_struct *get_swap_info_struct(unsigned);
 extern int can_share_swap_page(struct page *);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index f45cd74..f13f49a 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -24,6 +24,7 @@
 #include <linux/tty_driver.h>
 #include <linux/tty_ldisc.h>
 #include <linux/screen_info.h>
+#include <linux/mutex.h>
 
 #include <asm/system.h>
 
@@ -231,8 +232,8 @@ struct tty_struct {
 	int canon_data;
 	unsigned long canon_head;
 	unsigned int canon_column;
-	struct semaphore atomic_read;
-	struct semaphore atomic_write;
+	struct mutex atomic_read_lock;
+	struct mutex atomic_write_lock;
 	unsigned char *write_buf;
 	int write_cnt;
 	spinlock_t read_lock;
@@ -319,8 +320,7 @@ extern void tty_ldisc_put(int);
 extern void tty_wakeup(struct tty_struct *tty);
 extern void tty_ldisc_flush(struct tty_struct *tty);
 
-struct semaphore;
-extern struct semaphore tty_sem;
+extern struct mutex tty_mutex;
 
 /* n_tty.c */
 extern struct tty_ldisc tty_ldisc_N_TTY;
diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h
index 222faf9..0c6169f 100644
--- a/include/linux/tty_flip.h
+++ b/include/linux/tty_flip.h
@@ -7,14 +7,8 @@ extern int tty_insert_flip_string_flags(struct tty_struct *tty, unsigned char *c
 extern int tty_prepare_flip_string(struct tty_struct *tty, unsigned char **chars, size_t size);
 extern int tty_prepare_flip_string_flags(struct tty_struct *tty, unsigned char **chars, char **flags, size_t size);
 
-#ifdef INCLUDE_INLINE_FUNCS
-#define _INLINE_ extern
-#else
-#define _INLINE_ static __inline__
-#endif
-
-_INLINE_ int tty_insert_flip_char(struct tty_struct *tty,
-				   unsigned char ch, char flag)
+static inline int tty_insert_flip_char(struct tty_struct *tty,
+				       unsigned char ch, char flag)
 {
 	struct tty_buffer *tb = tty->buf.tail;
 	if (tb && tb->active && tb->used < tb->size) {
@@ -25,7 +19,7 @@ _INLINE_ int tty_insert_flip_char(struct tty_struct *tty,
 	return tty_insert_flip_string_flags(tty, &ch, &flag, 1);
 }
 
-_INLINE_ void tty_schedule_flip(struct tty_struct *tty)
+static inline void tty_schedule_flip(struct tty_struct *tty)
 {
 	unsigned long flags;
 	spin_lock_irqsave(&tty->buf.lock, flags);
diff --git a/include/linux/udf_fs_sb.h b/include/linux/udf_fs_sb.h
index b15ff2e..80ae9ef 100644
--- a/include/linux/udf_fs_sb.h
+++ b/include/linux/udf_fs_sb.h
@@ -13,7 +13,7 @@
 #ifndef _UDF_FS_SB_H
 #define _UDF_FS_SB_H 1
 
-#include <asm/semaphore.h>
+#include <linux/mutex.h>
 
 #pragma pack(1)
 
@@ -111,7 +111,7 @@ struct udf_sb_info
 	/* VAT inode */
 	struct inode		*s_vat;
 
-	struct semaphore	s_alloc_sem;
+	struct mutex		s_alloc_mutex;
 };
 
 #endif /* _UDF_FS_SB_H */
diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h
index fab5aed..530ae3f 100644
--- a/include/linux/vt_kern.h
+++ b/include/linux/vt_kern.h
@@ -73,6 +73,11 @@ int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc);
 int vt_waitactive(int vt);
 void change_console(struct vc_data *new_vc);
 void reset_vc(struct vc_data *vc);
+#ifdef CONFIG_VT
+int is_console_suspend_safe(void);
+#else
+static inline int is_console_suspend_safe(void) { return 1; }
+#endif
 
 /*
  * vc_screen.c shares this temporary buffer with the console write code so that