Merge branch 'linus' into x86/cleanups

43 files changed, 555 insertions, 560 deletions

diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 4a8e80cdcfa..a9f8a814a1f 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -22,3 +22,4 @@ unifdef-y += unistd_32.h
 unifdef-y += unistd_64.h
 unifdef-y += vm86.h
 unifdef-y += vsyscall.h
+unifdef-y += swab.h
diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h
index ad5b9f6ecdd..85b46fba422 100644
--- a/arch/x86/include/asm/atomic_32.h
+++ b/arch/x86/include/asm/atomic_32.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_ATOMIC_32_H
 
 #include <linux/compiler.h>
+#include <linux/types.h>
 #include <asm/processor.h>
 #include <asm/cmpxchg.h>
 
@@ -10,15 +11,6 @@
  * resource counting etc..
  */
 
-/*
- * 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,
- * not some alias that contains the same information.
- */
-typedef struct {
-	int counter;
-} atomic_t;
-
 #define ATOMIC_INIT(i)	{ (i) }
 
 /**
diff --git a/arch/x86/include/asm/atomic_64.h b/arch/x86/include/asm/atomic_64.h
index 279d2a731f3..8c21731984d 100644
--- a/arch/x86/include/asm/atomic_64.h
+++ b/arch/x86/include/asm/atomic_64.h
@@ -1,25 +1,15 @@
 #ifndef _ASM_X86_ATOMIC_64_H
 #define _ASM_X86_ATOMIC_64_H
 
+#include <linux/types.h>
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
 
-/* atomic_t should be 32 bit signed type */
-
 /*
  * Atomic operations that C can't guarantee us.  Useful for
  * resource counting etc..
  */
 
-/*
- * 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,
- * not some alias that contains the same information.
- */
-typedef struct {
-	int counter;
-} atomic_t;
-
 #define ATOMIC_INIT(i)	{ (i) }
 
 /**
@@ -191,11 +181,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 #define atomic_inc_return(v)  (atomic_add_return(1, v))
 #define atomic_dec_return(v)  (atomic_sub_return(1, v))
 
-/* An 64bit atomic type */
-
-typedef struct {
-	long counter;
-} atomic64_t;
+/* The 64-bit atomic type */
 
 #define ATOMIC64_INIT(i)	{ (i) }
 
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 9fa9dcdf344..e02a359d2aa 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -300,7 +300,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 	return oldbit;
 }
 
-static inline int constant_test_bit(int nr, const volatile unsigned long *addr)
+static inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
 {
 	return ((1UL << (nr % BITS_PER_LONG)) &
 		(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
diff --git a/arch/x86/include/asm/byteorder.h b/arch/x86/include/asm/byteorder.h
index f110ad417df..7c49917e3d9 100644
--- a/arch/x86/include/asm/byteorder.h
+++ b/arch/x86/include/asm/byteorder.h
@@ -1,65 +1,7 @@
 #ifndef _ASM_X86_BYTEORDER_H
 #define _ASM_X86_BYTEORDER_H
 
-#include <asm/types.h>
-#include <linux/compiler.h>
-
-#define __LITTLE_ENDIAN
-
-static inline __attribute_const__ __u32 __arch_swab32(__u32 val)
-{
-#ifdef __i386__
-# ifdef CONFIG_X86_BSWAP
-	asm("bswap %0" : "=r" (val) : "0" (val));
-# else
-	asm("xchgb %b0,%h0\n\t"	/* swap lower bytes	*/
-	    "rorl $16,%0\n\t"	/* swap words		*/
-	    "xchgb %b0,%h0"	/* swap higher bytes	*/
-	    : "=q" (val)
-	    : "0" (val));
-# endif
-
-#else /* __i386__ */
-	asm("bswapl %0"
-	    : "=r" (val)
-	    : "0" (val));
-#endif
-	return val;
-}
-#define __arch_swab32 __arch_swab32
-
-static inline __attribute_const__ __u64 __arch_swab64(__u64 val)
-{
-#ifdef __i386__
-	union {
-		struct {
-			__u32 a;
-			__u32 b;
-		} s;
-		__u64 u;
-	} v;
-	v.u = val;
-# ifdef CONFIG_X86_BSWAP
-	asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1"
-	    : "=r" (v.s.a), "=r" (v.s.b)
-	    : "0" (v.s.a), "1" (v.s.b));
-# else
-	v.s.a = __arch_swab32(v.s.a);
-	v.s.b = __arch_swab32(v.s.b);
-	asm("xchgl %0,%1"
-	    : "=r" (v.s.a), "=r" (v.s.b)
-	    : "0" (v.s.a), "1" (v.s.b));
-# endif
-	return v.u;
-#else /* __i386__ */
-	asm("bswapq %0"
-	    : "=r" (val)
-	    : "0" (val));
-	return val;
-#endif
-}
-#define __arch_swab64 __arch_swab64
-
-#include <linux/byteorder.h>
+#include <asm/swab.h>
+#include <linux/byteorder/little_endian.h>
 
 #endif /* _ASM_X86_BYTEORDER_H */
diff --git a/arch/x86/include/asm/es7000/apic.h b/arch/x86/include/asm/es7000/apic.h
index bc53d5ef138..c58b9cc7446 100644
--- a/arch/x86/include/asm/es7000/apic.h
+++ b/arch/x86/include/asm/es7000/apic.h
@@ -1,6 +1,8 @@
 #ifndef __ASM_ES7000_APIC_H
 #define __ASM_ES7000_APIC_H
 
+#include <linux/gfp.h>
+
 #define xapic_phys_to_log_apicid(cpu) per_cpu(x86_bios_cpu_apicid, cpu)
 #define esr_disable (1)
 
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 74ad9ef6ae0..1963e27673c 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -18,15 +18,31 @@
 #include <asm/pda.h>
 #include <asm/thread_info.h>
 
+#ifdef CONFIG_X86_64
+
+extern cpumask_var_t cpu_callin_mask;
+extern cpumask_var_t cpu_callout_mask;
+extern cpumask_var_t cpu_initialized_mask;
+extern cpumask_var_t cpu_sibling_setup_mask;
+
+#else /* CONFIG_X86_32 */
+
+extern cpumask_t cpu_callin_map;
 extern cpumask_t cpu_callout_map;
 extern cpumask_t cpu_initialized;
-extern cpumask_t cpu_callin_map;
+extern cpumask_t cpu_sibling_setup_map;
+
+#define cpu_callin_mask		((struct cpumask *)&cpu_callin_map)
+#define cpu_callout_mask	((struct cpumask *)&cpu_callout_map)
+#define cpu_initialized_mask	((struct cpumask *)&cpu_initialized)
+#define cpu_sibling_setup_mask	((struct cpumask *)&cpu_sibling_setup_map)
+
+#endif /* CONFIG_X86_32 */
 
 extern int __cpuinit get_local_pda(int cpu);
 
 extern int smp_num_siblings;
 extern unsigned int num_processors;
-extern cpumask_t cpu_initialized;
 
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_t, cpu_core_map);
@@ -35,6 +51,16 @@ DECLARE_PER_CPU(u16, cpu_llc_id);
 DECLARE_PER_CPU(int, cpu_number);
 #endif
 
+static inline struct cpumask *cpu_sibling_mask(int cpu)
+{
+	return &per_cpu(cpu_sibling_map, cpu);
+}
+
+static inline struct cpumask *cpu_core_mask(int cpu)
+{
+	return &per_cpu(cpu_core_map, cpu);
+}
+
 DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
 DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
 
@@ -144,7 +170,7 @@ void smp_store_cpu_info(int id);
 /* We don't mark CPUs online until __cpu_up(), so we need another measure */
 static inline int num_booting_cpus(void)
 {
-	return cpus_weight(cpu_callout_map);
+	return cpumask_weight(cpu_callout_mask);
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/x86/include/asm/summit/apic.h b/arch/x86/include/asm/summit/apic.h
index 4bb5fb34f03..93d2c8667cf 100644
--- a/arch/x86/include/asm/summit/apic.h
+++ b/arch/x86/include/asm/summit/apic.h
@@ -2,6 +2,7 @@
 #define __ASM_SUMMIT_APIC_H
 
 #include <asm/smp.h>
+#include <linux/gfp.h>
 
 #define esr_disable (1)
 #define NO_BALANCE_IRQ (0)
diff --git a/arch/x86/include/asm/swab.h b/arch/x86/include/asm/swab.h
new file mode 100644
index 00000000000..306d4178ffc
--- /dev/null
+++ b/arch/x86/include/asm/swab.h
@@ -0,0 +1,61 @@
+#ifndef _ASM_X86_SWAB_H
+#define _ASM_X86_SWAB_H
+
+#include <asm/types.h>
+#include <linux/compiler.h>
+
+static inline __attribute_const__ __u32 __arch_swab32(__u32 val)
+{
+#ifdef __i386__
+# ifdef CONFIG_X86_BSWAP
+	asm("bswap %0" : "=r" (val) : "0" (val));
+# else
+	asm("xchgb %b0,%h0\n\t"	/* swap lower bytes	*/
+	    "rorl $16,%0\n\t"	/* swap words		*/
+	    "xchgb %b0,%h0"	/* swap higher bytes	*/
+	    : "=q" (val)
+	    : "0" (val));
+# endif
+
+#else /* __i386__ */
+	asm("bswapl %0"
+	    : "=r" (val)
+	    : "0" (val));
+#endif
+	return val;
+}
+#define __arch_swab32 __arch_swab32
+
+static inline __attribute_const__ __u64 __arch_swab64(__u64 val)
+{
+#ifdef __i386__
+	union {
+		struct {
+			__u32 a;
+			__u32 b;
+		} s;
+		__u64 u;
+	} v;
+	v.u = val;
+# ifdef CONFIG_X86_BSWAP
+	asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1"
+	    : "=r" (v.s.a), "=r" (v.s.b)
+	    : "0" (v.s.a), "1" (v.s.b));
+# else
+	v.s.a = __arch_swab32(v.s.a);
+	v.s.b = __arch_swab32(v.s.b);
+	asm("xchgl %0,%1"
+	    : "=r" (v.s.a), "=r" (v.s.b)
+	    : "0" (v.s.a), "1" (v.s.b));
+# endif
+	return v.u;
+#else /* __i386__ */
+	asm("bswapq %0"
+	    : "=r" (val)
+	    : "0" (val));
+	return val;
+#endif
+}
+#define __arch_swab64 __arch_swab64
+
+#endif /* _ASM_X86_SWAB_H */
diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h
index 51fb2c76ad7..b9e4e20174f 100644
--- a/arch/x86/include/asm/swiotlb.h
+++ b/arch/x86/include/asm/swiotlb.h
@@ -1,46 +1,10 @@
 #ifndef _ASM_X86_SWIOTLB_H
 #define _ASM_X86_SWIOTLB_H
 
-#include <asm/dma-mapping.h>
+#include <linux/swiotlb.h>
 
 /* SWIOTLB interface */
 
-extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr,
-				     size_t size, int dir);
-extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-				    dma_addr_t *dma_handle, gfp_t flags);
-extern void swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
-				 size_t size, int dir);
-extern void swiotlb_sync_single_for_cpu(struct device *hwdev,
-					dma_addr_t dev_addr,
-					size_t size, int dir);
-extern void swiotlb_sync_single_for_device(struct device *hwdev,
-					   dma_addr_t dev_addr,
-					   size_t size, int dir);
-extern void swiotlb_sync_single_range_for_cpu(struct device *hwdev,
-					      dma_addr_t dev_addr,
-					      unsigned long offset,
-					      size_t size, int dir);
-extern void swiotlb_sync_single_range_for_device(struct device *hwdev,
-						 dma_addr_t dev_addr,
-						 unsigned long offset,
-						 size_t size, int dir);
-extern void swiotlb_sync_sg_for_cpu(struct device *hwdev,
-				    struct scatterlist *sg, int nelems,
-				    int dir);
-extern void swiotlb_sync_sg_for_device(struct device *hwdev,
-				       struct scatterlist *sg, int nelems,
-				       int dir);
-extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg,
-			  int nents, int direction);
-extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg,
-			     int nents, int direction);
-extern int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr);
-extern void swiotlb_free_coherent(struct device *hwdev, size_t size,
-				  void *vaddr, dma_addr_t dma_handle);
-extern int swiotlb_dma_supported(struct device *hwdev, u64 mask);
-extern void swiotlb_init(void);
-
 extern int swiotlb_force;
 
 #ifdef CONFIG_SWIOTLB
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
deleted file mode 100644
index 8b064bd9c55..00000000000
--- a/arch/x86/include/asm/unwind.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef _ASM_X86_UNWIND_H
-#define _ASM_X86_UNWIND_H
-
-#define UNW_PC(frame) ((void)(frame), 0UL)
-#define UNW_SP(frame) ((void)(frame), 0UL)
-#define UNW_FP(frame) ((void)(frame), 0UL)
-
-static inline int arch_unw_user_mode(const void *info)
-{
-	return 0;
-}
-
-#endif /* _ASM_X86_UNWIND_H */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 29dc0c89d4a..d37593c2f43 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -47,7 +47,7 @@
 #endif
 
 static int __initdata acpi_force = 0;
-
+u32 acpi_rsdt_forced;
 #ifdef	CONFIG_ACPI
 int acpi_disabled = 0;
 #else
@@ -1374,6 +1374,17 @@ static void __init acpi_process_madt(void)
 			       "Invalid BIOS MADT, disabling ACPI\n");
 			disable_acpi();
 		}
+	} else {
+		/*
+ 		 * ACPI found no MADT, and so ACPI wants UP PIC mode.
+ 		 * In the event an MPS table was found, forget it.
+ 		 * Boot with "acpi=off" to use MPS on such a system.
+ 		 */
+		if (smp_found_config) {
+			printk(KERN_WARNING PREFIX
+				"No APIC-table, disabling MPS\n");
+			smp_found_config = 0;
+		}
 	}
 
 	/*
@@ -1809,6 +1820,10 @@ static int __init parse_acpi(char *arg)
 			disable_acpi();
 		acpi_ht = 1;
 	}
+	/* acpi=rsdt use RSDT instead of XSDT */
+	else if (strcmp(arg, "rsdt") == 0) {
+		acpi_rsdt_forced = 1;
+	}
 	/* "acpi=noirq" disables ACPI interrupt routing */
 	else if (strcmp(arg, "noirq") == 0) {
 		acpi_noirq_set();
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index c2502eb9aa8..bbbe4bbb6f3 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -56,6 +56,7 @@ static struct cstate_entry *cpu_cstate_entry;	/* per CPU ptr */
 static short mwait_supported[ACPI_PROCESSOR_MAX_POWER];
 
 #define MWAIT_SUBSTATE_MASK	(0xf)
+#define MWAIT_CSTATE_MASK	(0xf)
 #define MWAIT_SUBSTATE_SIZE	(4)
 
 #define CPUID_MWAIT_LEAF (5)
@@ -66,39 +67,20 @@ static short mwait_supported[ACPI_PROCESSOR_MAX_POWER];
 
 #define NATIVE_CSTATE_BEYOND_HALT	(2)
 
-int acpi_processor_ffh_cstate_probe(unsigned int cpu,
-		struct acpi_processor_cx *cx, struct acpi_power_register *reg)
+static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
 {
-	struct cstate_entry *percpu_entry;
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
-
-	cpumask_t saved_mask;
-	int retval;
+	struct acpi_processor_cx *cx = _cx;
+	long retval;
 	unsigned int eax, ebx, ecx, edx;
 	unsigned int edx_part;
 	unsigned int cstate_type; /* C-state type and not ACPI C-state type */
 	unsigned int num_cstate_subtype;
 
-	if (!cpu_cstate_entry || c->cpuid_level < CPUID_MWAIT_LEAF )
-		return -1;
-
-	if (reg->bit_offset != NATIVE_CSTATE_BEYOND_HALT)
-		return -1;
-
-	percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
-	percpu_entry->states[cx->index].eax = 0;
-	percpu_entry->states[cx->index].ecx = 0;
-
-	/* Make sure we are running on right CPU */
-	saved_mask = current->cpus_allowed;
-	retval = set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-	if (retval)
-		return -1;
-
 	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
 
 	/* Check whether this particular cx_type (in CST) is supported or not */
-	cstate_type = (cx->address >> MWAIT_SUBSTATE_SIZE) + 1;
+	cstate_type = ((cx->address >> MWAIT_SUBSTATE_SIZE) &
+			MWAIT_CSTATE_MASK) + 1;
 	edx_part = edx >> (cstate_type * MWAIT_SUBSTATE_SIZE);
 	num_cstate_subtype = edx_part & MWAIT_SUBSTATE_MASK;
 
@@ -114,21 +96,45 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 		retval = -1;
 		goto out;
 	}
-	percpu_entry->states[cx->index].ecx = MWAIT_ECX_INTERRUPT_BREAK;
-
-	/* Use the hint in CST */
-	percpu_entry->states[cx->index].eax = cx->address;
 
 	if (!mwait_supported[cstate_type]) {
 		mwait_supported[cstate_type] = 1;
-		printk(KERN_DEBUG "Monitor-Mwait will be used to enter C-%d "
-		       "state\n", cx->type);
+		printk(KERN_DEBUG
+			"Monitor-Mwait will be used to enter C-%d "
+			"state\n", cx->type);
 	}
-	snprintf(cx->desc, ACPI_CX_DESC_LEN, "ACPI FFH INTEL MWAIT 0x%x",
-		 cx->address);
-
+	snprintf(cx->desc,
+			ACPI_CX_DESC_LEN, "ACPI FFH INTEL MWAIT 0x%x",
+			cx->address);
 out:
-	set_cpus_allowed_ptr(current, &saved_mask);
+	return retval;
+}
+
+int acpi_processor_ffh_cstate_probe(unsigned int cpu,
+		struct acpi_processor_cx *cx, struct acpi_power_register *reg)
+{
+	struct cstate_entry *percpu_entry;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	long retval;
+
+	if (!cpu_cstate_entry || c->cpuid_level < CPUID_MWAIT_LEAF)
+		return -1;
+
+	if (reg->bit_offset != NATIVE_CSTATE_BEYOND_HALT)
+		return -1;
+
+	percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
+	percpu_entry->states[cx->index].eax = 0;
+	percpu_entry->states[cx->index].ecx = 0;
+
+	/* Make sure we are running on right CPU */
+
+	retval = work_on_cpu(cpu, acpi_processor_ffh_cstate_probe_cpu, cx);
+	if (retval == 0) {
+		/* Use the hint in CST */
+		percpu_entry->states[cx->index].eax = cx->address;
+		percpu_entry->states[cx->index].ecx = MWAIT_ECX_INTERRUPT_BREAK;
+	}
 	return retval;
 }
 EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 806b4e9051b..707c1f6f95f 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -159,6 +159,8 @@ static int __init acpi_sleep_setup(char *str)
 #endif
 		if (strncmp(str, "old_ordering", 12) == 0)
 			acpi_old_suspend_ordering();
+		if (strncmp(str, "s4_nonvs", 8) == 0)
+			acpi_s4_no_nvs();
 		str = strchr(str, ',');
 		if (str != NULL)
 			str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f7619a2eaff..14e543b6fd4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -41,6 +41,26 @@
 
 #include "cpu.h"
 
+#ifdef CONFIG_X86_64
+
+/* all of these masks are initialized in setup_cpu_local_masks() */
+cpumask_var_t cpu_callin_mask;
+cpumask_var_t cpu_callout_mask;
+cpumask_var_t cpu_initialized_mask;
+
+/* representing cpus for which sibling maps can be computed */
+cpumask_var_t cpu_sibling_setup_mask;
+
+#else /* CONFIG_X86_32 */
+
+cpumask_t cpu_callin_map;
+cpumask_t cpu_callout_map;
+cpumask_t cpu_initialized;
+cpumask_t cpu_sibling_setup_map;
+
+#endif /* CONFIG_X86_32 */
+
+
 static struct cpu_dev *this_cpu __cpuinitdata;
 
 #ifdef CONFIG_X86_64
@@ -857,8 +877,6 @@ static __init int setup_disablecpuid(char *arg)
 }
 __setup("clearcpuid=", setup_disablecpuid);
 
-cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
-
 #ifdef CONFIG_X86_64
 struct x8664_pda **_cpu_pda __read_mostly;
 EXPORT_SYMBOL(_cpu_pda);
@@ -977,7 +995,7 @@ void __cpuinit cpu_init(void)
 
 	me = current;
 
-	if (cpu_test_and_set(cpu, cpu_initialized))
+	if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask))
 		panic("CPU#%d already initialized!\n", cpu);
 
 	printk(KERN_INFO "Initializing CPU#%d\n", cpu);
@@ -1086,7 +1104,7 @@ void __cpuinit cpu_init(void)
 	struct tss_struct *t = &per_cpu(init_tss, cpu);
 	struct thread_struct *thread = &curr->thread;
 
-	if (cpu_test_and_set(cpu, cpu_initialized)) {
+	if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) {
 		printk(KERN_WARNING "CPU#%d already initialized!\n", cpu);
 		for (;;) local_irq_enable();
 	}
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 28102ad1a36..06fcd8f9323 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -145,13 +145,14 @@ typedef union {
 
 struct drv_cmd {
 	unsigned int type;
-	cpumask_t mask;
+	cpumask_var_t mask;
 	drv_addr_union addr;
 	u32 val;
 };
 
-static void do_drv_read(struct drv_cmd *cmd)
+static long do_drv_read(void *_cmd)
 {
+	struct drv_cmd *cmd = _cmd;
 	u32 h;
 
 	switch (cmd->type) {
@@ -166,10 +167,12 @@ static void do_drv_read(struct drv_cmd *cmd)
 	default:
 		break;
 	}
+	return 0;
 }
 
-static void do_drv_write(struct drv_cmd *cmd)
+static long do_drv_write(void *_cmd)
 {
+	struct drv_cmd *cmd = _cmd;
 	u32 lo, hi;
 
 	switch (cmd->type) {
@@ -186,48 +189,41 @@ static void do_drv_write(struct drv_cmd *cmd)
 	default:
 		break;
 	}
+	return 0;
 }
 
 static void drv_read(struct drv_cmd *cmd)
 {
-	cpumask_t saved_mask = current->cpus_allowed;
 	cmd->val = 0;
 
-	set_cpus_allowed_ptr(current, &cmd->mask);
-	do_drv_read(cmd);
-	set_cpus_allowed_ptr(current, &saved_mask);
+	work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd);
 }
 
 static void drv_write(struct drv_cmd *cmd)
 {
-	cpumask_t saved_mask = current->cpus_allowed;
 	unsigned int i;
 
-	for_each_cpu_mask_nr(i, cmd->mask) {
-		set_cpus_allowed_ptr(current, &cpumask_of_cpu(i));
-		do_drv_write(cmd);
+	for_each_cpu(i, cmd->mask) {
+		work_on_cpu(i, do_drv_write, cmd);
 	}
-
-	set_cpus_allowed_ptr(current, &saved_mask);
-	return;
 }
 
-static u32 get_cur_val(const cpumask_t *mask)
+static u32 get_cur_val(const struct cpumask *mask)
 {
 	struct acpi_processor_performance *perf;
 	struct drv_cmd cmd;
 
-	if (unlikely(cpus_empty(*mask)))
+	if (unlikely(cpumask_empty(mask)))
 		return 0;
 
-	switch (per_cpu(drv_data, first_cpu(*mask))->cpu_feature) {
+	switch (per_cpu(drv_data, cpumask_first(mask))->cpu_feature) {
 	case SYSTEM_INTEL_MSR_CAPABLE:
 		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
 		cmd.addr.msr.reg = MSR_IA32_PERF_STATUS;
 		break;
 	case SYSTEM_IO_CAPABLE:
 		cmd.type = SYSTEM_IO_CAPABLE;
-		perf = per_cpu(drv_data, first_cpu(*mask))->acpi_data;
+		perf = per_cpu(drv_data, cpumask_first(mask))->acpi_data;
 		cmd.addr.io.port = perf->control_register.address;
 		cmd.addr.io.bit_width = perf->control_register.bit_width;
 		break;
@@ -235,15 +231,44 @@ static u32 get_cur_val(const cpumask_t *mask)
 		return 0;
 	}
 
-	cmd.mask = *mask;
+	if (unlikely(!alloc_cpumask_var(&cmd.mask, GFP_KERNEL)))
+		return 0;
+
+	cpumask_copy(cmd.mask, mask);
 
 	drv_read(&cmd);
 
+	free_cpumask_var(cmd.mask);
+
 	dprintk("get_cur_val = %u\n", cmd.val);
 
 	return cmd.val;
 }
 
+struct perf_cur {
+	union {
+		struct {
+			u32 lo;
+			u32 hi;
+		} split;
+		u64 whole;
+	} aperf_cur, mperf_cur;
+};
+
+
+static long read_measured_perf_ctrs(void *_cur)
+{
+	struct perf_cur *cur = _cur;
+
+	rdmsr(MSR_IA32_APERF, cur->aperf_cur.split.lo, cur->aperf_cur.split.hi);
+	rdmsr(MSR_IA32_MPERF, cur->mperf_cur.split.lo, cur->mperf_cur.split.hi);
+
+	wrmsr(MSR_IA32_APERF, 0, 0);
+	wrmsr(MSR_IA32_MPERF, 0, 0);
+
+	return 0;
+}
+
 /*
  * Return the measured active (C0) frequency on this CPU since last call
  * to this function.
@@ -260,31 +285,12 @@ static u32 get_cur_val(const cpumask_t *mask)
 static unsigned int get_measured_perf(struct cpufreq_policy *policy,
 				      unsigned int cpu)
 {
-	union {
-		struct {
-			u32 lo;
-			u32 hi;
-		} split;
-		u64 whole;
-	} aperf_cur, mperf_cur;
-
-	cpumask_t saved_mask;
+	struct perf_cur cur;
 	unsigned int perf_percent;
 	unsigned int retval;
 
-	saved_mask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-	if (get_cpu() != cpu) {
-		/* We were not able to run on requested processor */
-		put_cpu();
+	if (!work_on_cpu(cpu, read_measured_perf_ctrs, &cur))
 		return 0;
-	}
-
-	rdmsr(MSR_IA32_APERF, aperf_cur.split.lo, aperf_cur.split.hi);
-	rdmsr(MSR_IA32_MPERF, mperf_cur.split.lo, mperf_cur.split.hi);
-
-	wrmsr(MSR_IA32_APERF, 0,0);
-	wrmsr(MSR_IA32_MPERF, 0,0);
 
 #ifdef __i386__
 	/*
@@ -292,37 +298,39 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy,
 	 * Get an approximate value. Return failure in case we cannot get
 	 * an approximate value.
 	 */
-	if (unlikely(aperf_cur.split.hi || mperf_cur.split.hi)) {
+	if (unlikely(cur.aperf_cur.split.hi || cur.mperf_cur.split.hi)) {
 		int shift_count;
 		u32 h;
 
-		h = max_t(u32, aperf_cur.split.hi, mperf_cur.split.hi);
+		h = max_t(u32, cur.aperf_cur.split.hi, cur.mperf_cur.split.hi);
 		shift_count = fls(h);
 
-		aperf_cur.whole >>= shift_count;
-		mperf_cur.whole >>= shift_count;
+		cur.aperf_cur.whole >>= shift_count;
+		cur.mperf_cur.whole >>= shift_count;
 	}
 
-	if (((unsigned long)(-1) / 100) < aperf_cur.split.lo) {
+	if (((unsigned long)(-1) / 100) < cur.aperf_cur.split.lo) {
 		int shift_count = 7;
-		aperf_cur.split.lo >>= shift_count;
-		mperf_cur.split.lo >>= shift_count;
+		cur.aperf_cur.split.lo >>= shift_count;
+		cur.mperf_cur.split.lo >>= shift_count;
 	}
 
-	if (aperf_cur.split.lo && mperf_cur.split.lo)
-		perf_percent = (aperf_cur.split.lo * 100) / mperf_cur.split.lo;
+	if (cur.aperf_cur.split.lo && cur.mperf_cur.split.lo)
+		perf_percent = (cur.aperf_cur.split.lo * 100) /
+				cur.mperf_cur.split.lo;
 	else
 		perf_percent = 0;
 
 #else
-	if (unlikely(((unsigned long)(-1) / 100) < aperf_cur.whole)) {
+	if (unlikely(((unsigned long)(-1) / 100) < cur.aperf_cur.whole)) {
 		int shift_count = 7;
-		aperf_cur.whole >>= shift_count;
-		mperf_cur.whole >>= shift_count;
+		cur.aperf_cur.whole >>= shift_count;
+		cur.mperf_cur.whole >>= shift_count;
 	}
 
-	if (aperf_cur.whole && mperf_cur.whole)
-		perf_percent = (aperf_cur.whole * 100) / mperf_cur.whole;
+	if (cur.aperf_cur.whole && cur.mperf_cur.whole)
+		perf_percent = (cur.aperf_cur.whole * 100) /
+				cur.mperf_cur.whole;
 	else
 		perf_percent = 0;
 
@@ -330,10 +338,6 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy,
 
 	retval = per_cpu(drv_data, policy->cpu)->max_freq * perf_percent / 100;
 
-	put_cpu();
-	set_cpus_allowed_ptr(current, &saved_mask);
-
-	dprintk("cpu %d: performance percent %d\n", cpu, perf_percent);
 	return retval;
 }
 
@@ -351,7 +355,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 	}
 
 	cached_freq = data->freq_table[data->acpi_data->state].frequency;
-	freq = extract_freq(get_cur_val(&cpumask_of_cpu(cpu)), data);
+	freq = extract_freq(get_cur_val(cpumask_of(cpu)), data);
 	if (freq != cached_freq) {
 		/*
 		 * The dreaded BIOS frequency change behind our back.
@@ -386,7 +390,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
 	struct acpi_processor_performance *perf;
 	struct cpufreq_freqs freqs;
-	cpumask_t online_policy_cpus;
 	struct drv_cmd cmd;
 	unsigned int next_state = 0; /* Index into freq_table */
 	unsigned int next_perf_state = 0; /* Index into perf table */
@@ -401,20 +404,18 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 		return -ENODEV;
 	}
 
+	if (unlikely(!alloc_cpumask_var(&cmd.mask, GFP_KERNEL)))
+		return -ENOMEM;
+
 	perf = data->acpi_data;
 	result = cpufreq_frequency_table_target(policy,
 						data->freq_table,
 						target_freq,
 						relation, &next_state);
-	if (unlikely(result))
-		return -ENODEV;
-
-#ifdef CONFIG_HOTPLUG_CPU
-	/* cpufreq holds the hotplug lock, so we are safe from here on */
-	cpus_and(online_policy_cpus, cpu_online_map, policy->cpus);
-#else
-	online_policy_cpus = policy->cpus;
-#endif
+	if (unlikely(result)) {
+		result = -ENODEV;
+		goto out;
+	}
 
 	next_perf_state = data->freq_table[next_state].index;
 	if (perf->state == next_perf_state) {
@@ -425,7 +426,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 		} else {
 			dprintk("Already at target state (P%d)\n",
 				next_perf_state);
-			return 0;
+			goto out;
 		}
 	}
 
@@ -444,19 +445,19 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 		cmd.val = (u32) perf->states[next_perf_state].control;
 		break;
 	default:
-		return -ENODEV;
+		result = -ENODEV;
+		goto out;
 	}
 
-	cpus_clear(cmd.mask);
-
+	/* cpufreq holds the hotplug lock, so we are safe from here on */
 	if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY)
-		cmd.mask = online_policy_cpus;
+		cpumask_and(cmd.mask, cpu_online_mask, policy->cpus);
 	else
-		cpu_set(policy->cpu, cmd.mask);
+		cpumask_copy(cmd.mask, cpumask_of(policy->cpu));
 
 	freqs.old = perf->states[perf->state].core_frequency * 1000;
 	freqs.new = data->freq_table[next_state].frequency;
-	for_each_cpu_mask_nr(i, cmd.mask) {
+	for_each_cpu(i, cmd.mask) {
 		freqs.cpu = i;
 		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 	}
@@ -464,19 +465,22 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	drv_write(&cmd);
 
 	if (acpi_pstate_strict) {
-		if (!check_freqs(&cmd.mask, freqs.new, data)) {
+		if (!check_freqs(cmd.mask, freqs.new, data)) {
 			dprintk("acpi_cpufreq_target failed (%d)\n",
 				policy->cpu);
-			return -EAGAIN;
+			result = -EAGAIN;
+			goto out;
 		}
 	}
 
-	for_each_cpu_mask_nr(i, cmd.mask) {
+	for_each_cpu(i, cmd.mask) {
 		freqs.cpu = i;
 		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 	}
 	perf->state = next_perf_state;
 
+out:
+	free_cpumask_var(cmd.mask);
 	return result;
 }
 
@@ -626,15 +630,15 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	 */
 	if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL ||
 	    policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
-		cpumask_copy(&policy->cpus, perf->shared_cpu_map);
+		cpumask_copy(policy->cpus, perf->shared_cpu_map);
 	}
-	cpumask_copy(&policy->related_cpus, perf->shared_cpu_map);
+	cpumask_copy(policy->related_cpus, perf->shared_cpu_map);
 
 #ifdef CONFIG_SMP
 	dmi_check_system(sw_any_bug_dmi_table);
-	if (bios_with_sw_any_bug && cpus_weight(policy->cpus) == 1) {
+	if (bios_with_sw_any_bug && cpumask_weight(policy->cpus) == 1) {
 		policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
-		policy->cpus = per_cpu(cpu_core_map, cpu);
+		cpumask_copy(policy->cpus, cpu_core_mask(cpu));
 	}
 #endif
 
diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c
index b0461856acf..a4cff5d6e38 100644
--- a/arch/x86/kernel/cpu/cpufreq/longhaul.c
+++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c
@@ -982,7 +982,7 @@ static int __init longhaul_init(void)
 	case 10:
 		printk(KERN_ERR PFX "Use acpi-cpufreq driver for VIA C7\n");
 	default:
-		;;
+		;
 	}
 
 	return -ENODEV;
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index beea4466b06..b585e04cbc9 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -122,7 +122,7 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy,
 		return 0;
 
 	/* notifiers */
-	for_each_cpu_mask_nr(i, policy->cpus) {
+	for_each_cpu(i, policy->cpus) {
 		freqs.cpu = i;
 		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 	}
@@ -130,11 +130,11 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy,
 	/* run on each logical CPU, see section 13.15.3 of IA32 Intel Architecture Software
 	 * Developer's Manual, Volume 3
 	 */
-	for_each_cpu_mask_nr(i, policy->cpus)
+	for_each_cpu(i, policy->cpus)
 		cpufreq_p4_setdc(i, p4clockmod_table[newstate].index);
 
 	/* notifiers */
-	for_each_cpu_mask_nr(i, policy->cpus) {
+	for_each_cpu(i, policy->cpus) {
 		freqs.cpu = i;
 		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 	}
@@ -203,7 +203,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
 	unsigned int i;
 
 #ifdef CONFIG_SMP
-	policy->cpus = per_cpu(cpu_sibling_map, policy->cpu);
+	cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu));
 #endif
 
 	/* Errata workaround */
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index c3c9adbaa26..5c28b37dea1 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1199,10 +1199,10 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	set_cpus_allowed_ptr(current, &oldmask);
 
 	if (cpu_family == CPU_HW_PSTATE)
-		pol->cpus = cpumask_of_cpu(pol->cpu);
+		cpumask_copy(pol->cpus, cpumask_of(pol->cpu));
 	else
-		pol->cpus = per_cpu(cpu_core_map, pol->cpu);
-	data->available_cores = &(pol->cpus);
+		cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu));
+	data->available_cores = pol->cpus;
 
 	/* Take a crude guess here.
 	 * That guess was in microseconds, so multiply with 1000 */
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
index 65cfb5d7f77..8ecc75b6c7c 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
@@ -53,7 +53,7 @@ struct powernow_k8_data {
 	/* we need to keep track of associated cores, but let cpufreq
 	 * handle hotplug events - so just point at cpufreq pol->cpus
 	 * structure */
-	cpumask_t *available_cores;
+	struct cpumask *available_cores;
 };
 
 
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index f0ea6fa2f53..f08998278a3 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -458,11 +458,6 @@ static int centrino_verify (struct cpufreq_policy *policy)
  *
  * Sets a new CPUFreq policy.
  */
-struct allmasks {
-	cpumask_t		saved_mask;
-	cpumask_t		covered_cpus;
-};
-
 static int centrino_target (struct cpufreq_policy *policy,
 			    unsigned int target_freq,
 			    unsigned int relation)
@@ -472,12 +467,15 @@ static int centrino_target (struct cpufreq_policy *policy,
 	struct cpufreq_freqs	freqs;
 	int			retval = 0;
 	unsigned int		j, k, first_cpu, tmp;
-	CPUMASK_ALLOC(allmasks);
-	CPUMASK_PTR(saved_mask, allmasks);
-	CPUMASK_PTR(covered_cpus, allmasks);
+	cpumask_var_t saved_mask, covered_cpus;
 
-	if (unlikely(allmasks == NULL))
+	if (unlikely(!alloc_cpumask_var(&saved_mask, GFP_KERNEL)))
 		return -ENOMEM;
+	if (unlikely(!alloc_cpumask_var(&covered_cpus, GFP_KERNEL))) {
+		free_cpumask_var(saved_mask);
+		return -ENOMEM;
+	}
+	cpumask_copy(saved_mask, &current->cpus_allowed);
 
 	if (unlikely(per_cpu(centrino_model, cpu) == NULL)) {
 		retval = -ENODEV;
@@ -493,11 +491,9 @@ static int centrino_target (struct cpufreq_policy *policy,
 		goto out;
 	}
 
-	*saved_mask = current->cpus_allowed;
 	first_cpu = 1;
-	cpus_clear(*covered_cpus);
-	for_each_cpu_mask_nr(j, policy->cpus) {
-		const cpumask_t *mask;
+	for_each_cpu(j, policy->cpus) {
+		const struct cpumask *mask;
 
 		/* cpufreq holds the hotplug lock, so we are safe here */
 		if (!cpu_online(j))
@@ -508,9 +504,9 @@ static int centrino_target (struct cpufreq_policy *policy,
 		 * Make sure we are running on CPU that wants to change freq
 		 */
 		if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY)
-			mask = &policy->cpus;
+			mask = policy->cpus;
 		else
-			mask = &cpumask_of_cpu(j);
+			mask = cpumask_of(j);
 
 		set_cpus_allowed_ptr(current, mask);
 		preempt_disable();
@@ -542,7 +538,7 @@ static int centrino_target (struct cpufreq_policy *policy,
 			dprintk("target=%dkHz old=%d new=%d msr=%04x\n",
 				target_freq, freqs.old, freqs.new, msr);
 
-			for_each_cpu_mask_nr(k, policy->cpus) {
+			for_each_cpu(k, policy->cpus) {
 				if (!cpu_online(k))
 					continue;
 				freqs.cpu = k;
@@ -567,7 +563,7 @@ static int centrino_target (struct cpufreq_policy *policy,
 		preempt_enable();
 	}
 
-	for_each_cpu_mask_nr(k, policy->cpus) {
+	for_each_cpu(k, policy->cpus) {
 		if (!cpu_online(k))
 			continue;
 		freqs.cpu = k;
@@ -590,7 +586,7 @@ static int centrino_target (struct cpufreq_policy *policy,
 		tmp = freqs.new;
 		freqs.new = freqs.old;
 		freqs.old = tmp;
-		for_each_cpu_mask_nr(j, policy->cpus) {
+		for_each_cpu(j, policy->cpus) {
 			if (!cpu_online(j))
 				continue;
 			cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
@@ -605,7 +601,8 @@ migrate_end:
 	preempt_enable();
 	set_cpus_allowed_ptr(current, saved_mask);
 out:
-	CPUMASK_FREE(allmasks);
+	free_cpumask_var(saved_mask);
+	free_cpumask_var(covered_cpus);
 	return retval;
 }
 
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
index 04d0376b64b..dedc1e98f16 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
@@ -229,7 +229,7 @@ static unsigned int speedstep_detect_chipset (void)
 	return 0;
 }
 
-static unsigned int _speedstep_get(const cpumask_t *cpus)
+static unsigned int _speedstep_get(const struct cpumask *cpus)
 {
 	unsigned int speed;
 	cpumask_t cpus_allowed;
@@ -244,7 +244,7 @@ static unsigned int _speedstep_get(const cpumask_t *cpus)
 
 static unsigned int speedstep_get(unsigned int cpu)
 {
-	return _speedstep_get(&cpumask_of_cpu(cpu));
+	return _speedstep_get(cpumask_of(cpu));
 }
 
 /**
@@ -267,7 +267,7 @@ static int speedstep_target (struct cpufreq_policy *policy,
 	if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0], target_freq, relation, &newstate))
 		return -EINVAL;
 
-	freqs.old = _speedstep_get(&policy->cpus);
+	freqs.old = _speedstep_get(policy->cpus);
 	freqs.new = speedstep_freqs[newstate].frequency;
 	freqs.cpu = policy->cpu;
 
@@ -279,20 +279,20 @@ static int speedstep_target (struct cpufreq_policy *policy,
 
 	cpus_allowed = current->cpus_allowed;
 
-	for_each_cpu_mask_nr(i, policy->cpus) {
+	for_each_cpu(i, policy->cpus) {
 		freqs.cpu = i;
 		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 	}
 
 	/* switch to physical CPU where state is to be changed */
-	set_cpus_allowed_ptr(current, &policy->cpus);
+	set_cpus_allowed_ptr(current, policy->cpus);
 
 	speedstep_set_state(newstate);
 
 	/* allow to be run on all CPUs */
 	set_cpus_allowed_ptr(current, &cpus_allowed);
 
-	for_each_cpu_mask_nr(i, policy->cpus) {
+	for_each_cpu(i, policy->cpus) {
 		freqs.cpu = i;
 		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 	}
@@ -322,11 +322,11 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 
 	/* only run on CPU to be set, or on its sibling */
 #ifdef CONFIG_SMP
-	policy->cpus = per_cpu(cpu_sibling_map, policy->cpu);
+	cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu));
 #endif
 
 	cpus_allowed = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, &policy->cpus);
+	set_cpus_allowed_ptr(current, policy->cpus);
 
 	/* detect low and high frequency and transition latency */
 	result = speedstep_get_freqs(speedstep_processor,
@@ -339,7 +339,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 		return result;
 
 	/* get current speed setting */
-	speed = _speedstep_get(&policy->cpus);
+	speed = _speedstep_get(policy->cpus);
 	if (!speed)
 		return -EIO;
 
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 65a13943e09..e85826829cf 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -665,6 +665,27 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn)
 }
 #endif
 
+#ifdef CONFIG_HIBERNATION
+/**
+ * Mark ACPI NVS memory region, so that we can save/restore it during
+ * hibernation and the subsequent resume.
+ */
+static int __init e820_mark_nvs_memory(void)
+{
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+
+		if (ei->type == E820_NVS)
+			hibernate_nvs_register(ei->addr, ei->size);
+	}
+
+	return 0;
+}
+core_initcall(e820_mark_nvs_memory);
+#endif
+
 /*
  * Early reserved memory areas.
  */
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 744aa7fc49d..76b8cd953de 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -201,6 +201,12 @@ struct chipset {
 	void (*f)(int num, int slot, int func);
 };
 
+/*
+ * Only works for devices on the root bus. If you add any devices
+ * not on bus 0 readd another loop level in early_quirks(). But
+ * be careful because at least the Nvidia quirk here relies on
+ * only matching on bus 0.
+ */
 static struct chipset early_qrk[] __initdata = {
 	{ PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
 	  PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs },
@@ -267,17 +273,17 @@ static int __init check_dev_quirk(int num, int slot, int func)
 
 void __init early_quirks(void)
 {
-	int num, slot, func;
+	int slot, func;
 
 	if (!early_pci_allowed())
 		return;
 
 	/* Poor man's PCI discovery */
-	for (num = 0; num < 32; num++)
-		for (slot = 0; slot < 32; slot++)
-			for (func = 0; func < 8; func++) {
-				/* Only probe function 0 on single fn devices */
-				if (check_dev_quirk(num, slot, func))
-					break;
-			}
+	/* Only scan the root bus */
+	for (slot = 0; slot < 32; slot++)
+		for (func = 0; func < 8; func++) {
+			/* Only probe function 0 on single fn devices */
+			if (check_dev_quirk(0, slot, func))
+				break;
+		}
 }
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 6c27679ec6a..884d985b8b8 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -376,9 +376,10 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p)
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
 {
-	mutex_lock(&kprobe_mutex);
-	free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1));
-	mutex_unlock(&kprobe_mutex);
+	if (p->ainsn.insn) {
+		free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1));
+		p->ainsn.insn = NULL;
+	}
 }
 
 static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
@@ -694,7 +695,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	/*
 	 * It is possible to have multiple instances associated with a given
 	 * task either because multiple functions in the call path have
-	 * return probes installed on them, and/or more then one
+	 * return probes installed on them, and/or more than one
 	 * return probe was registered for a target function.
 	 *
 	 * We can handle this because:
diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c
index c12314c9e86..8815f3c7fec 100644
--- a/arch/x86/kernel/mfgpt_32.c
+++ b/arch/x86/kernel/mfgpt_32.c
@@ -252,7 +252,7 @@ EXPORT_SYMBOL_GPL(geode_mfgpt_alloc_timer);
 /*
  * The MFPGT timers on the CS5536 provide us with suitable timers to use
  * as clock event sources - not as good as a HPET or APIC, but certainly
- * better then the PIT.  This isn't a general purpose MFGPT driver, but
+ * better than the PIT.  This isn't a general purpose MFGPT driver, but
  * a simplified one designed specifically to act as a clock event source.
  * For full details about the MFGPT, please consult the CS5536 data sheet.
  */
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 19a1044a0cd..b2542853314 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -38,7 +38,7 @@ EXPORT_SYMBOL(bad_dma_address);
    be probably a smaller DMA mask, but this is bug-to-bug compatible
    to older i386. */
 struct device x86_dma_fallback_dev = {
-	.bus_id = "fallback device",
+	.init_name = "fallback device",
 	.coherent_dma_mask = DMA_32BIT_MASK,
 	.dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
 };
diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c
index 8cba3749a51..d59c9174766 100644
--- a/arch/x86/kernel/pci-swiotlb_64.c
+++ b/arch/x86/kernel/pci-swiotlb_64.c
@@ -23,7 +23,7 @@ void *swiotlb_alloc(unsigned order, unsigned long nslabs)
 	return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
 }
 
-dma_addr_t swiotlb_phys_to_bus(phys_addr_t paddr)
+dma_addr_t swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
 {
 	return paddr;
 }
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index e4433bf4420..55c46074eba 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -130,7 +130,27 @@ static void __init setup_cpu_pda_map(void)
 	/* point to new pointer table */
 	_cpu_pda = new_cpu_pda;
 }
-#endif
+
+#endif /* CONFIG_SMP && CONFIG_X86_64 */
+
+#ifdef CONFIG_X86_64
+
+/* correctly size the local cpu masks */
+static void setup_cpu_local_masks(void)
+{
+	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
+	alloc_bootmem_cpumask_var(&cpu_callin_mask);
+	alloc_bootmem_cpumask_var(&cpu_callout_mask);
+	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
+}
+
+#else /* CONFIG_X86_32 */
+
+static inline void setup_cpu_local_masks(void)
+{
+}
+
+#endif /* CONFIG_X86_32 */
 
 /*
  * Great future plan:
@@ -186,6 +206,9 @@ void __init setup_per_cpu_areas(void)
 
 	/* Setup node to cpumask map */
 	setup_node_to_cpumask_map();
+
+	/* Setup cpu initialized, callin, callout masks */
+	setup_cpu_local_masks();
 }
 
 #endif
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index cf1f075886b..e6faa3316bd 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -128,16 +128,23 @@ void native_send_call_func_single_ipi(int cpu)
 
 void native_send_call_func_ipi(const struct cpumask *mask)
 {
-	cpumask_t allbutself;
+	cpumask_var_t allbutself;
 
-	allbutself = cpu_online_map;
-	cpu_clear(smp_processor_id(), allbutself);
+	if (!alloc_cpumask_var(&allbutself, GFP_ATOMIC)) {
+		send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
+		return;
+	}
 
-	if (cpus_equal(*mask, allbutself) &&
-	    cpus_equal(cpu_online_map, cpu_callout_map))
+	cpumask_copy(allbutself, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), allbutself);
+
+	if (cpumask_equal(mask, allbutself) &&
+	    cpumask_equal(cpu_online_mask, cpu_callout_mask))
 		send_IPI_allbutself(CALL_FUNCTION_VECTOR);
 	else
 		send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
+
+	free_cpumask_var(allbutself);
 }
 
 /*
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f8c885bed18..6c2b8444b83 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -101,9 +101,6 @@ EXPORT_SYMBOL(smp_num_siblings);
 /* Last level cache ID of each logical CPU */
 DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID;
 
-cpumask_t cpu_callin_map;
-cpumask_t cpu_callout_map;
-
 /* representing HT siblings of each logical CPU */
 DEFINE_PER_CPU(cpumask_t, cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
@@ -119,9 +116,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
 static atomic_t init_deasserted;
 
 
-/* representing cpus for which sibling maps can be computed */
-static cpumask_t cpu_sibling_setup_map;
-
 /* Set if we find a B stepping CPU */
 static int __cpuinitdata smp_b_stepping;
 
@@ -139,7 +133,7 @@ EXPORT_SYMBOL(cpu_to_node_map);
 static void map_cpu_to_node(int cpu, int node)
 {
 	printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node);
-	cpu_set(cpu, node_to_cpumask_map[node]);
+	cpumask_set_cpu(cpu, &node_to_cpumask_map[node]);
 	cpu_to_node_map[cpu] = node;
 }
 
@@ -150,7 +144,7 @@ static void unmap_cpu_to_node(int cpu)
 
 	printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu);
 	for (node = 0; node < MAX_NUMNODES; node++)
-		cpu_clear(cpu, node_to_cpumask_map[node]);
+		cpumask_clear_cpu(cpu, &node_to_cpumask_map[node]);
 	cpu_to_node_map[cpu] = 0;
 }
 #else /* !(CONFIG_NUMA && CONFIG_X86_32) */
@@ -208,7 +202,7 @@ static void __cpuinit smp_callin(void)
 	 */
 	phys_id = read_apic_id();
 	cpuid = smp_processor_id();
-	if (cpu_isset(cpuid, cpu_callin_map)) {
+	if (cpumask_test_cpu(cpuid, cpu_callin_mask)) {
 		panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
 					phys_id, cpuid);
 	}
@@ -230,7 +224,7 @@ static void __cpuinit smp_callin(void)
 		/*
 		 * Has the boot CPU finished it's STARTUP sequence?
 		 */
-		if (cpu_isset(cpuid, cpu_callout_map))
+		if (cpumask_test_cpu(cpuid, cpu_callout_mask))
 			break;
 		cpu_relax();
 	}
@@ -273,7 +267,7 @@ static void __cpuinit smp_callin(void)
 	/*
 	 * Allow the master to continue.
 	 */
-	cpu_set(cpuid, cpu_callin_map);
+	cpumask_set_cpu(cpuid, cpu_callin_mask);
 }
 
 static int __cpuinitdata unsafe_smp;
@@ -331,7 +325,7 @@ notrace static void __cpuinit start_secondary(void *unused)
 	ipi_call_lock();
 	lock_vector_lock();
 	__setup_vector_irq(smp_processor_id());
-	cpu_set(smp_processor_id(), cpu_online_map);
+	set_cpu_online(smp_processor_id(), true);
 	unlock_vector_lock();
 	ipi_call_unlock();
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
@@ -437,50 +431,52 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 	int i;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	cpu_set(cpu, cpu_sibling_setup_map);
+	cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
 
 	if (smp_num_siblings > 1) {
-		for_each_cpu_mask_nr(i, cpu_sibling_setup_map) {
-			if (c->phys_proc_id == cpu_data(i).phys_proc_id &&
-			    c->cpu_core_id == cpu_data(i).cpu_core_id) {
-				cpu_set(i, per_cpu(cpu_sibling_map, cpu));
-				cpu_set(cpu, per_cpu(cpu_sibling_map, i));
-				cpu_set(i, per_cpu(cpu_core_map, cpu));
-				cpu_set(cpu, per_cpu(cpu_core_map, i));
-				cpu_set(i, c->llc_shared_map);
-				cpu_set(cpu, cpu_data(i).llc_shared_map);
+		for_each_cpu(i, cpu_sibling_setup_mask) {
+			struct cpuinfo_x86 *o = &cpu_data(i);
+
+			if (c->phys_proc_id == o->phys_proc_id &&
+			    c->cpu_core_id == o->cpu_core_id) {
+				cpumask_set_cpu(i, cpu_sibling_mask(cpu));
+				cpumask_set_cpu(cpu, cpu_sibling_mask(i));
+				cpumask_set_cpu(i, cpu_core_mask(cpu));
+				cpumask_set_cpu(cpu, cpu_core_mask(i));
+				cpumask_set_cpu(i, &c->llc_shared_map);
+				cpumask_set_cpu(cpu, &o->llc_shared_map);
 			}
 		}
 	} else {
-		cpu_set(cpu, per_cpu(cpu_sibling_map, cpu));
+		cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
 	}
 
-	cpu_set(cpu, c->llc_shared_map);
+	cpumask_set_cpu(cpu, &c->llc_shared_map);
 
 	if (current_cpu_data.x86_max_cores == 1) {
-		per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu);
+		cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu));
 		c->booted_cores = 1;
 		return;
 	}
 
-	for_each_cpu_mask_nr(i, cpu_sibling_setup_map) {
+	for_each_cpu(i, cpu_sibling_setup_mask) {
 		if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
 		    per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
-			cpu_set(i, c->llc_shared_map);
-			cpu_set(cpu, cpu_data(i).llc_shared_map);
+			cpumask_set_cpu(i, &c->llc_shared_map);
+			cpumask_set_cpu(cpu, &cpu_data(i).llc_shared_map);
 		}
 		if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
-			cpu_set(i, per_cpu(cpu_core_map, cpu));
-			cpu_set(cpu, per_cpu(cpu_core_map, i));
+			cpumask_set_cpu(i, cpu_core_mask(cpu));
+			cpumask_set_cpu(cpu, cpu_core_mask(i));
 			/*
 			 *  Does this new cpu bringup a new core?
 			 */
-			if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) {
+			if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) {
 				/*
 				 * for each core in package, increment
 				 * the booted_cores for this new cpu
 				 */
-				if (first_cpu(per_cpu(cpu_sibling_map, i)) == i)
+				if (cpumask_first(cpu_sibling_mask(i)) == i)
 					c->booted_cores++;
 				/*
 				 * increment the core count for all
@@ -503,7 +499,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	 * And for power savings, we return cpu_core_map
 	 */
 	if (sched_mc_power_savings || sched_smt_power_savings)
-		return &per_cpu(cpu_core_map, cpu);
+		return cpu_core_mask(cpu);
 	else
 		return &c->llc_shared_map;
 }
@@ -522,7 +518,7 @@ static void impress_friends(void)
 	 */
 	pr_debug("Before bogomips.\n");
 	for_each_possible_cpu(cpu)
-		if (cpu_isset(cpu, cpu_callout_map))
+		if (cpumask_test_cpu(cpu, cpu_callout_mask))
 			bogosum += cpu_data(cpu).loops_per_jiffy;
 	printk(KERN_INFO
 		"Total of %d processors activated (%lu.%02lu BogoMIPS).\n",
@@ -903,19 +899,19 @@ do_rest:
 		 * allow APs to start initializing.
 		 */
 		pr_debug("Before Callout %d.\n", cpu);
-		cpu_set(cpu, cpu_callout_map);
+		cpumask_set_cpu(cpu, cpu_callout_mask);
 		pr_debug("After Callout %d.\n", cpu);
 
 		/*
 		 * Wait 5s total for a response
 		 */
 		for (timeout = 0; timeout < 50000; timeout++) {
-			if (cpu_isset(cpu, cpu_callin_map))
+			if (cpumask_test_cpu(cpu, cpu_callin_mask))
 				break;	/* It has booted */
 			udelay(100);
 		}
 
-		if (cpu_isset(cpu, cpu_callin_map)) {
+		if (cpumask_test_cpu(cpu, cpu_callin_mask)) {
 			/* number CPUs logically, starting from 1 (BSP is 0) */
 			pr_debug("OK.\n");
 			printk(KERN_INFO "CPU%d: ", cpu);
@@ -940,9 +936,14 @@ restore_state:
 	if (boot_error) {
 		/* Try to put things back the way they were before ... */
 		numa_remove_cpu(cpu); /* was set by numa_add_cpu */
-		cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */
-		cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */
-		cpu_clear(cpu, cpu_present_map);
+
+		/* was set by do_boot_cpu() */
+		cpumask_clear_cpu(cpu, cpu_callout_mask);
+
+		/* was set by cpu_init() */
+		cpumask_clear_cpu(cpu, cpu_initialized_mask);
+
+		set_cpu_present(cpu, false);
 		per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
 	}
 
@@ -976,7 +977,7 @@ int __cpuinit native_cpu_up(unsigned int cpu)
 	/*
 	 * Already booted CPU?
 	 */
-	if (cpu_isset(cpu, cpu_callin_map)) {
+	if (cpumask_test_cpu(cpu, cpu_callin_mask)) {
 		pr_debug("do_boot_cpu %d Already started\n", cpu);
 		return -ENOSYS;
 	}
@@ -1031,8 +1032,9 @@ int __cpuinit native_cpu_up(unsigned int cpu)
  */
 static __init void disable_smp(void)
 {
-	cpu_present_map = cpumask_of_cpu(0);
-	cpu_possible_map = cpumask_of_cpu(0);
+	/* use the read/write pointers to the present and possible maps */
+	cpumask_copy(&cpu_present_map, cpumask_of(0));
+	cpumask_copy(&cpu_possible_map, cpumask_of(0));
 	smpboot_clear_io_apic_irqs();
 
 	if (smp_found_config)
@@ -1040,8 +1042,8 @@ static __init void disable_smp(void)
 	else
 		physid_set_mask_of_physid(0, &phys_cpu_present_map);
 	map_cpu_to_logical_apicid();
-	cpu_set(0, per_cpu(cpu_sibling_map, 0));
-	cpu_set(0, per_cpu(cpu_core_map, 0));
+	cpumask_set_cpu(0, cpu_sibling_mask(0));
+	cpumask_set_cpu(0, cpu_core_mask(0));
 }
 
 /*
@@ -1063,14 +1065,14 @@ static int __init smp_sanity_check(unsigned max_cpus)
 		nr = 0;
 		for_each_present_cpu(cpu) {
 			if (nr >= 8)
-				cpu_clear(cpu, cpu_present_map);
+				set_cpu_present(cpu, false);
 			nr++;
 		}
 
 		nr = 0;
 		for_each_possible_cpu(cpu) {
 			if (nr >= 8)
-				cpu_clear(cpu, cpu_possible_map);
+				set_cpu_possible(cpu, false);
 			nr++;
 		}
 
@@ -1166,7 +1168,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	preempt_disable();
 	smp_cpu_index_default();
 	current_cpu_data = boot_cpu_data;
-	cpu_callin_map = cpumask_of_cpu(0);
+	cpumask_copy(cpu_callin_mask, cpumask_of(0));
 	mb();
 	/*
 	 * Setup boot CPU information
@@ -1241,8 +1243,8 @@ void __init native_smp_prepare_boot_cpu(void)
 	init_gdt(me);
 #endif
 	switch_to_new_gdt();
-	/* already set me in cpu_online_map in boot_cpu_init() */
-	cpu_set(me, cpu_callout_map);
+	/* already set me in cpu_online_mask in boot_cpu_init() */
+	cpumask_set_cpu(me, cpu_callout_mask);
 	per_cpu(cpu_state, me) = CPU_ONLINE;
 }
 
@@ -1310,7 +1312,7 @@ __init void prefill_possible_map(void)
 		possible, max_t(int, possible - num_processors, 0));
 
 	for (i = 0; i < possible; i++)
-		cpu_set(i, cpu_possible_map);
+		set_cpu_possible(i, true);
 
 	nr_cpu_ids = possible;
 }
@@ -1322,31 +1324,31 @@ static void remove_siblinginfo(int cpu)
 	int sibling;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	for_each_cpu_mask_nr(sibling, per_cpu(cpu_core_map, cpu)) {
-		cpu_clear(cpu, per_cpu(cpu_core_map, sibling));
+	for_each_cpu(sibling, cpu_core_mask(cpu)) {
+		cpumask_clear_cpu(cpu, cpu_core_mask(sibling));
 		/*/
 		 * last thread sibling in this cpu core going down
 		 */
-		if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1)
+		if (cpumask_weight(cpu_sibling_mask(cpu)) == 1)
 			cpu_data(sibling).booted_cores--;
 	}
 
-	for_each_cpu_mask_nr(sibling, per_cpu(cpu_sibling_map, cpu))
-		cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling));
-	cpus_clear(per_cpu(cpu_sibling_map, cpu));
-	cpus_clear(per_cpu(cpu_core_map, cpu));
+	for_each_cpu(sibling, cpu_sibling_mask(cpu))
+		cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
+	cpumask_clear(cpu_sibling_mask(cpu));
+	cpumask_clear(cpu_core_mask(cpu));
 	c->phys_proc_id = 0;
 	c->cpu_core_id = 0;
-	cpu_clear(cpu, cpu_sibling_setup_map);
+	cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
 }
 
 static void __ref remove_cpu_from_maps(int cpu)
 {
-	cpu_clear(cpu, cpu_online_map);
-	cpu_clear(cpu, cpu_callout_map);
-	cpu_clear(cpu, cpu_callin_map);
+	set_cpu_online(cpu, false);
+	cpumask_clear_cpu(cpu, cpu_callout_mask);
+	cpumask_clear_cpu(cpu, cpu_callin_mask);
 	/* was set by cpu_init() */
-	cpu_clear(cpu, cpu_initialized);
+	cpumask_clear_cpu(cpu, cpu_initialized_mask);
 	numa_remove_cpu(cpu);
 }
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 25d5c307358..98c2d055284 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -20,7 +20,6 @@
 #include <linux/module.h>
 #include <linux/ptrace.h>
 #include <linux/string.h>
-#include <linux/unwind.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/kexec.h>
@@ -51,7 +50,6 @@
 #include <asm/debugreg.h>
 #include <asm/atomic.h>
 #include <asm/system.h>
-#include <asm/unwind.h>
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/i387.h>
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 57ec8c86a87..9e268b6b204 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -667,7 +667,6 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (unlikely(in_atomic() || !mm))
 		goto bad_area_nosemaphore;
 
-again:
 	/*
 	 * When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
@@ -859,25 +858,14 @@ no_context:
 	oops_end(flags, regs, sig);
 #endif
 
-/*
- * We ran out of memory, or some other thing happened to us that made
- * us unable to handle the page fault gracefully.
- */
 out_of_memory:
+	/*
+	 * We ran out of memory, call the OOM killer, and return the userspace
+	 * (which will retry the fault, or kill us if we got oom-killed).
+	 */
 	up_read(&mm->mmap_sem);
-	if (is_global_init(tsk)) {
-		yield();
-		/*
-		 * Re-lookup the vma - in theory the vma tree might
-		 * have changed:
-		 */
-		goto again;
-	}
-
-	printk("VM: killing process %s\n", tsk->comm);
-	if (error_code & PF_USER)
-		do_group_exit(SIGKILL);
-	goto no_context;
+	pagefault_out_of_memory();
+	return;
 
 do_sigbus:
 	up_read(&mm->mmap_sem);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index a9dd0b7ad61..4a6989e47a5 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -327,6 +327,8 @@ int devmem_is_allowed(unsigned long pagenr)
 {
 	if (pagenr <= 256)
 		return 1;
+	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+		return 0;
 	if (!page_is_ram(pagenr))
 		return 1;
 	return 0;
@@ -1078,7 +1080,7 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	return __add_pages(zone, start_pfn, nr_pages);
+	return __add_pages(nid, zone, start_pfn, nr_pages);
 }
 #endif
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9f7a0d24d42..23f68e77ad1 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -857,7 +857,7 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	if (last_mapped_pfn > max_pfn_mapped)
 		max_pfn_mapped = last_mapped_pfn;
 
-	ret = __add_pages(zone, start_pfn, nr_pages);
+	ret = __add_pages(nid, zone, start_pfn, nr_pages);
 	WARN_ON_ONCE(ret);
 
 	return ret;
@@ -888,6 +888,8 @@ int devmem_is_allowed(unsigned long pagenr)
 {
 	if (pagenr <= 256)
 		return 1;
+	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+		return 0;
 	if (!page_is_ram(pagenr))
 		return 1;
 	return 0;
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 8518c678d83..d1f7439d173 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -239,7 +239,7 @@ void resume_map_numa_kva(pgd_t *pgd_base)
 		start_pfn = node_remap_start_pfn[node];
 		size = node_remap_size[node];
 
-		printk(KERN_DEBUG "%s: node %d\n", __FUNCTION__, node);
+		printk(KERN_DEBUG "%s: node %d\n", __func__, node);
 
 		for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) {
 			unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
@@ -251,7 +251,7 @@ void resume_map_numa_kva(pgd_t *pgd_base)
 						PAGE_KERNEL_LARGE_EXEC));
 
 			printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n",
-				__FUNCTION__, vaddr, start_pfn + pfn);
+				__func__, vaddr, start_pfn + pfn);
 		}
 	}
 }
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 98658f25f54..8fdf06e4edf 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -2,7 +2,7 @@
  * @file op_model_amd.c
  * athlon / K7 / K8 / Family 10h model-specific MSR operations
  *
- * @remark Copyright 2002-2008 OProfile authors
+ * @remark Copyright 2002-2009 OProfile authors
  * @remark Read the file COPYING
  *
  * @author John Levon
@@ -10,7 +10,7 @@
  * @author Graydon Hoare
  * @author Robert Richter <robert.richter@amd.com>
  * @author Barry Kasindorf
-*/
+ */
 
 #include <linux/oprofile.h>
 #include <linux/device.h>
@@ -60,53 +60,10 @@ static unsigned long reset_value[NUM_COUNTERS];
 #define IBS_OP_LOW_VALID_BIT		(1ULL<<18)	/* bit 18 */
 #define IBS_OP_LOW_ENABLE		(1ULL<<17)	/* bit 17 */
 
-/* Codes used in cpu_buffer.c */
-/* This produces duplicate code, need to be fixed */
-#define IBS_FETCH_BEGIN 3
-#define IBS_OP_BEGIN    4
-
-/*
- * The function interface needs to be fixed, something like add
- * data. Should then be added to linux/oprofile.h.
- */
-extern void
-oprofile_add_ibs_sample(struct pt_regs * const regs,
-			unsigned int * const ibs_sample, int ibs_code);
-
-struct ibs_fetch_sample {
-	/* MSRC001_1031 IBS Fetch Linear Address Register */
-	unsigned int ibs_fetch_lin_addr_low;
-	unsigned int ibs_fetch_lin_addr_high;
-	/* MSRC001_1030 IBS Fetch Control Register */
-	unsigned int ibs_fetch_ctl_low;
-	unsigned int ibs_fetch_ctl_high;
-	/* MSRC001_1032 IBS Fetch Physical Address Register */
-	unsigned int ibs_fetch_phys_addr_low;
-	unsigned int ibs_fetch_phys_addr_high;
-};
-
-struct ibs_op_sample {
-	/* MSRC001_1034 IBS Op Logical Address Register (IbsRIP) */
-	unsigned int ibs_op_rip_low;
-	unsigned int ibs_op_rip_high;
-	/* MSRC001_1035 IBS Op Data Register */
-	unsigned int ibs_op_data1_low;
-	unsigned int ibs_op_data1_high;
-	/* MSRC001_1036 IBS Op Data 2 Register */
-	unsigned int ibs_op_data2_low;
-	unsigned int ibs_op_data2_high;
-	/* MSRC001_1037 IBS Op Data 3 Register */
-	unsigned int ibs_op_data3_low;
-	unsigned int ibs_op_data3_high;
-	/* MSRC001_1038 IBS DC Linear Address Register (IbsDcLinAd) */
-	unsigned int ibs_dc_linear_low;
-	unsigned int ibs_dc_linear_high;
-	/* MSRC001_1039 IBS DC Physical Address Register (IbsDcPhysAd) */
-	unsigned int ibs_dc_phys_low;
-	unsigned int ibs_dc_phys_high;
-};
+#define IBS_FETCH_SIZE	6
+#define IBS_OP_SIZE	12
 
-static int ibs_allowed;	/* AMD Family10h and later */
+static int has_ibs;	/* AMD Family10h and later */
 
 struct op_ibs_config {
 	unsigned long op_enabled;
@@ -197,31 +154,29 @@ static inline int
 op_amd_handle_ibs(struct pt_regs * const regs,
 		  struct op_msrs const * const msrs)
 {
-	unsigned int low, high;
-	struct ibs_fetch_sample ibs_fetch;
-	struct ibs_op_sample ibs_op;
+	u32 low, high;
+	u64 msr;
+	struct op_entry entry;
 
-	if (!ibs_allowed)
+	if (!has_ibs)
 		return 1;
 
 	if (ibs_config.fetch_enabled) {
 		rdmsr(MSR_AMD64_IBSFETCHCTL, low, high);
 		if (high & IBS_FETCH_HIGH_VALID_BIT) {
-			ibs_fetch.ibs_fetch_ctl_high = high;
-			ibs_fetch.ibs_fetch_ctl_low = low;
-			rdmsr(MSR_AMD64_IBSFETCHLINAD, low, high);
-			ibs_fetch.ibs_fetch_lin_addr_high = high;
-			ibs_fetch.ibs_fetch_lin_addr_low = low;
-			rdmsr(MSR_AMD64_IBSFETCHPHYSAD, low, high);
-			ibs_fetch.ibs_fetch_phys_addr_high = high;
-			ibs_fetch.ibs_fetch_phys_addr_low = low;
-
-			oprofile_add_ibs_sample(regs,
-						(unsigned int *)&ibs_fetch,
-						IBS_FETCH_BEGIN);
+			rdmsrl(MSR_AMD64_IBSFETCHLINAD, msr);
+			oprofile_write_reserve(&entry, regs, msr,
+					       IBS_FETCH_CODE, IBS_FETCH_SIZE);
+			oprofile_add_data(&entry, (u32)msr);
+			oprofile_add_data(&entry, (u32)(msr >> 32));
+			oprofile_add_data(&entry, low);
+			oprofile_add_data(&entry, high);
+			rdmsrl(MSR_AMD64_IBSFETCHPHYSAD, msr);
+			oprofile_add_data(&entry, (u32)msr);
+			oprofile_add_data(&entry, (u32)(msr >> 32));
+			oprofile_write_commit(&entry);
 
 			/* reenable the IRQ */
-			rdmsr(MSR_AMD64_IBSFETCHCTL, low, high);
 			high &= ~IBS_FETCH_HIGH_VALID_BIT;
 			high |= IBS_FETCH_HIGH_ENABLE;
 			low &= IBS_FETCH_LOW_MAX_CNT_MASK;
@@ -232,30 +187,29 @@ op_amd_handle_ibs(struct pt_regs * const regs,
 	if (ibs_config.op_enabled) {
 		rdmsr(MSR_AMD64_IBSOPCTL, low, high);
 		if (low & IBS_OP_LOW_VALID_BIT) {
-			rdmsr(MSR_AMD64_IBSOPRIP, low, high);
-			ibs_op.ibs_op_rip_low = low;
-			ibs_op.ibs_op_rip_high = high;
-			rdmsr(MSR_AMD64_IBSOPDATA, low, high);
-			ibs_op.ibs_op_data1_low = low;
-			ibs_op.ibs_op_data1_high = high;
-			rdmsr(MSR_AMD64_IBSOPDATA2, low, high);
-			ibs_op.ibs_op_data2_low = low;
-			ibs_op.ibs_op_data2_high = high;
-			rdmsr(MSR_AMD64_IBSOPDATA3, low, high);
-			ibs_op.ibs_op_data3_low = low;
-			ibs_op.ibs_op_data3_high = high;
-			rdmsr(MSR_AMD64_IBSDCLINAD, low, high);
-			ibs_op.ibs_dc_linear_low = low;
-			ibs_op.ibs_dc_linear_high = high;
-			rdmsr(MSR_AMD64_IBSDCPHYSAD, low, high);
-			ibs_op.ibs_dc_phys_low = low;
-			ibs_op.ibs_dc_phys_high = high;
+			rdmsrl(MSR_AMD64_IBSOPRIP, msr);
+			oprofile_write_reserve(&entry, regs, msr,
+					       IBS_OP_CODE, IBS_OP_SIZE);
+			oprofile_add_data(&entry, (u32)msr);
+			oprofile_add_data(&entry, (u32)(msr >> 32));
+			rdmsrl(MSR_AMD64_IBSOPDATA, msr);
+			oprofile_add_data(&entry, (u32)msr);
+			oprofile_add_data(&entry, (u32)(msr >> 32));
+			rdmsrl(MSR_AMD64_IBSOPDATA2, msr);
+			oprofile_add_data(&entry, (u32)msr);
+			oprofile_add_data(&entry, (u32)(msr >> 32));
+			rdmsrl(MSR_AMD64_IBSOPDATA3, msr);
+			oprofile_add_data(&entry, (u32)msr);
+			oprofile_add_data(&entry, (u32)(msr >> 32));
+			rdmsrl(MSR_AMD64_IBSDCLINAD, msr);
+			oprofile_add_data(&entry, (u32)msr);
+			oprofile_add_data(&entry, (u32)(msr >> 32));
+			rdmsrl(MSR_AMD64_IBSDCPHYSAD, msr);
+			oprofile_add_data(&entry, (u32)msr);
+			oprofile_add_data(&entry, (u32)(msr >> 32));
+			oprofile_write_commit(&entry);
 
 			/* reenable the IRQ */
-			oprofile_add_ibs_sample(regs,
-						(unsigned int *)&ibs_op,
-						IBS_OP_BEGIN);
-			rdmsr(MSR_AMD64_IBSOPCTL, low, high);
 			high = 0;
 			low &= ~IBS_OP_LOW_VALID_BIT;
 			low |= IBS_OP_LOW_ENABLE;
@@ -305,14 +259,14 @@ static void op_amd_start(struct op_msrs const * const msrs)
 	}
 
 #ifdef CONFIG_OPROFILE_IBS
-	if (ibs_allowed && ibs_config.fetch_enabled) {
+	if (has_ibs && ibs_config.fetch_enabled) {
 		low = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF;
 		high = ((ibs_config.rand_en & 0x1) << 25) /* bit 57 */
 			+ IBS_FETCH_HIGH_ENABLE;
 		wrmsr(MSR_AMD64_IBSFETCHCTL, low, high);
 	}
 
-	if (ibs_allowed && ibs_config.op_enabled) {
+	if (has_ibs && ibs_config.op_enabled) {
 		low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF)
 			+ ((ibs_config.dispatched_ops & 0x1) << 19) /* bit 19 */
 			+ IBS_OP_LOW_ENABLE;
@@ -341,14 +295,14 @@ static void op_amd_stop(struct op_msrs const * const msrs)
 	}
 
 #ifdef CONFIG_OPROFILE_IBS
-	if (ibs_allowed && ibs_config.fetch_enabled) {
+	if (has_ibs && ibs_config.fetch_enabled) {
 		/* clear max count and enable */
 		low = 0;
 		high = 0;
 		wrmsr(MSR_AMD64_IBSFETCHCTL, low, high);
 	}
 
-	if (ibs_allowed && ibs_config.op_enabled) {
+	if (has_ibs && ibs_config.op_enabled) {
 		/* clear max count and enable */
 		low = 0;
 		high = 0;
@@ -409,6 +363,7 @@ static int init_ibs_nmi(void)
 				       | IBSCTL_LVTOFFSETVAL);
 		pci_read_config_dword(cpu_cfg, IBSCTL, &value);
 		if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) {
+			pci_dev_put(cpu_cfg);
 			printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
 				"IBSCTL = 0x%08x", value);
 			return 1;
@@ -436,20 +391,20 @@ static int init_ibs_nmi(void)
 /* uninitialize the APIC for the IBS interrupts if needed */
 static void clear_ibs_nmi(void)
 {
-	if (ibs_allowed)
+	if (has_ibs)
 		on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1);
 }
 
 /* initialize the APIC for the IBS interrupts if available */
 static void ibs_init(void)
 {
-	ibs_allowed = boot_cpu_has(X86_FEATURE_IBS);
+	has_ibs = boot_cpu_has(X86_FEATURE_IBS);
 
-	if (!ibs_allowed)
+	if (!has_ibs)
 		return;
 
 	if (init_ibs_nmi()) {
-		ibs_allowed = 0;
+		has_ibs = 0;
 		return;
 	}
 
@@ -458,7 +413,7 @@ static void ibs_init(void)
 
 static void ibs_exit(void)
 {
-	if (!ibs_allowed)
+	if (!has_ibs)
 		return;
 
 	clear_ibs_nmi();
@@ -478,7 +433,7 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
 	if (ret)
 		return ret;
 
-	if (!ibs_allowed)
+	if (!has_ibs)
 		return ret;
 
 	/* model specific files */
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 9e5752fe4d1..c0ecf250fe5 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -210,11 +210,10 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do
 	if (bus && node != -1) {
 #ifdef CONFIG_ACPI_NUMA
 		if (pxm >= 0)
-			printk(KERN_DEBUG "bus %02x -> pxm %d -> node %d\n",
-				busnum, pxm, node);
+			dev_printk(KERN_DEBUG, &bus->dev,
+				   "on NUMA node %d (pxm %d)\n", node, pxm);
 #else
-		printk(KERN_DEBUG "bus %02x -> node %d\n",
-			busnum, node);
+		dev_printk(KERN_DEBUG, &bus->dev, "on NUMA node %d\n", node);
 #endif
 	}
 
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 62ddb73e09e..82d22fc601a 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -551,17 +551,25 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 	if ((err = pci_enable_resources(dev, mask)) < 0)
 		return err;
 
-	if (!dev->msi_enabled)
+	if (!pci_dev_msi_enabled(dev))
 		return pcibios_enable_irq(dev);
 	return 0;
 }
 
 void pcibios_disable_device (struct pci_dev *dev)
 {
-	if (!dev->msi_enabled && pcibios_disable_irq)
+	if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq)
 		pcibios_disable_irq(dev);
 }
 
+int pci_ext_cfg_avail(struct pci_dev *dev)
+{
+	if (raw_pci_ext_ops)
+		return 1;
+	else
+		return 0;
+}
+
 struct pci_bus * __devinit pci_scan_bus_on_node(int busno, struct pci_ops *ops, int node)
 {
 	struct pci_bus *bus = NULL;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index e51bf2cda4b..f884740da31 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -129,7 +129,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 				pr = pci_find_parent_resource(dev, r);
 				if (!r->start || !pr ||
 				    request_resource(pr, r) < 0) {
-					dev_err(&dev->dev, "BAR %d: can't allocate resource\n", idx);
+					dev_info(&dev->dev, "BAR %d: can't allocate resource\n", idx);
 					/*
 					 * Something is wrong with the region.
 					 * Invalidate the resource to prevent
@@ -170,7 +170,7 @@ static void __init pcibios_allocate_resources(int pass)
 					r->flags, disabled, pass);
 				pr = pci_find_parent_resource(dev, r);
 				if (!pr || request_resource(pr, r) < 0) {
-					dev_err(&dev->dev, "BAR %d: can't allocate resource\n", idx);
+					dev_info(&dev->dev, "BAR %d: can't allocate resource\n", idx);
 					/* We'll assign a new address later */
 					r->end -= r->start;
 					r->start = 0;
diff --git a/arch/x86/pci/init.c b/arch/x86/pci/init.c
index bec3b048e72..25a1f8efed4 100644
--- a/arch/x86/pci/init.c
+++ b/arch/x86/pci/init.c
@@ -12,7 +12,8 @@ static __init int pci_arch_init(void)
 	type = pci_direct_probe();
 #endif
 
-	pci_mmcfg_early_init();
+	if (!(pci_probe & PCI_PROBE_NOEARLY))
+		pci_mmcfg_early_init();
 
 #ifdef CONFIG_PCI_OLPC
 	if (!pci_olpc_init())
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 373b9afe6d4..4064345cf14 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -533,7 +533,7 @@ static int pirq_bios_set(struct pci_dev *router, struct pci_dev *dev, int pirq,
 {
 	struct pci_dev *bridge;
 	int pin = pci_get_interrupt_pin(dev, &bridge);
-	return pcibios_set_irq_routing(bridge, pin, irq);
+	return pcibios_set_irq_routing(bridge, pin - 1, irq);
 }
 
 #endif
@@ -887,7 +887,6 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 		dev_dbg(&dev->dev, "no interrupt pin\n");
 		return 0;
 	}
-	pin = pin - 1;
 
 	/* Find IRQ routing entry */
 
@@ -897,17 +896,17 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 	info = pirq_get_info(dev);
 	if (!info) {
 		dev_dbg(&dev->dev, "PCI INT %c not found in routing table\n",
-			'A' + pin);
+			'A' + pin - 1);
 		return 0;
 	}
-	pirq = info->irq[pin].link;
-	mask = info->irq[pin].bitmap;
+	pirq = info->irq[pin - 1].link;
+	mask = info->irq[pin - 1].bitmap;
 	if (!pirq) {
-		dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + pin);
+		dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + pin - 1);
 		return 0;
 	}
 	dev_dbg(&dev->dev, "PCI INT %c -> PIRQ %02x, mask %04x, excl %04x",
-		'A' + pin, pirq, mask, pirq_table->exclusive_irqs);
+		'A' + pin - 1, pirq, mask, pirq_table->exclusive_irqs);
 	mask &= pcibios_irq_mask;
 
 	/* Work around broken HP Pavilion Notebooks which assign USB to
@@ -949,7 +948,7 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 				newirq = i;
 		}
 	}
-	dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + pin, newirq);
+	dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + pin - 1, newirq);
 
 	/* Check if it is hardcoded */
 	if ((pirq & 0xf0) == 0xf0) {
@@ -977,18 +976,18 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 			return 0;
 		}
 	}
-	dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", msg, 'A' + pin, irq);
+	dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", msg, 'A' + pin - 1, irq);
 
 	/* Update IRQ for all devices with the same pirq value */
 	while ((dev2 = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev2)) != NULL) {
 		pci_read_config_byte(dev2, PCI_INTERRUPT_PIN, &pin);
 		if (!pin)
 			continue;
-		pin--;
+
 		info = pirq_get_info(dev2);
 		if (!info)
 			continue;
-		if (info->irq[pin].link == pirq) {
+		if (info->irq[pin - 1].link == pirq) {
 			/*
 			 * We refuse to override the dev->irq
 			 * information. Give a warning!
@@ -1042,6 +1041,9 @@ static void __init pcibios_fixup_irqs(void)
 	dev = NULL;
 	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
 		pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+		if (!pin)
+			continue;
+
 #ifdef CONFIG_X86_IO_APIC
 		/*
 		 * Recalculate IRQ numbers if we use the I/O APIC.
@@ -1049,15 +1051,11 @@ static void __init pcibios_fixup_irqs(void)
 		if (io_apic_assign_pci_irqs) {
 			int irq;
 
-			if (!pin)
-				continue;
-
 			/*
 			 * interrupt pins are numbered starting from 1
 			 */
-			pin--;
 			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
-				PCI_SLOT(dev->devfn), pin);
+				PCI_SLOT(dev->devfn), pin - 1);
 			/*
 			 * Busses behind bridges are typically not listed in the
 			 * MP-table.  In this case we have to look up the IRQ
@@ -1070,22 +1068,22 @@ static void __init pcibios_fixup_irqs(void)
 				struct pci_dev *bridge = dev->bus->self;
 				int bus;
 
-				pin = (pin + PCI_SLOT(dev->devfn)) % 4;
+				pin = pci_swizzle_interrupt_pin(dev, pin);
 				bus = bridge->bus->number;
 				irq = IO_APIC_get_PCI_irq_vector(bus,
-						PCI_SLOT(bridge->devfn), pin);
+						PCI_SLOT(bridge->devfn), pin - 1);
 				if (irq >= 0)
 					dev_warn(&dev->dev,
 						"using bridge %s INT %c to "
 							"get IRQ %d\n",
 						 pci_name(bridge),
-						 'A' + pin, irq);
+						 'A' + pin - 1, irq);
 			}
 			if (irq >= 0) {
 				dev_info(&dev->dev,
 					"PCI->APIC IRQ transform: INT %c "
 						"-> IRQ %d\n",
-					'A' + pin, irq);
+					'A' + pin - 1, irq);
 				dev->irq = irq;
 			}
 		}
@@ -1093,7 +1091,7 @@ static void __init pcibios_fixup_irqs(void)
 		/*
 		 * Still no IRQ? Try to lookup one...
 		 */
-		if (pin && !dev->irq)
+		if (!dev->irq)
 			pcibios_lookup_irq(dev, 0);
 	}
 }
@@ -1220,12 +1218,10 @@ static int pirq_enable_irq(struct pci_dev *dev)
 	if (pin && !pcibios_lookup_irq(dev, 1) && !dev->irq) {
 		char *msg = "";
 
-		pin--; /* interrupt pins are numbered starting from 1 */
-
 		if (io_apic_assign_pci_irqs) {
 			int irq;
 
-			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin);
+			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin - 1);
 			/*
 			 * Busses behind bridges are typically not listed in the MP-table.
 			 * In this case we have to look up the IRQ based on the parent bus,
@@ -1236,20 +1232,20 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			while (irq < 0 && dev->bus->parent) { /* go back to the bridge */
 				struct pci_dev *bridge = dev->bus->self;
 
-				pin = (pin + PCI_SLOT(dev->devfn)) % 4;
+				pin = pci_swizzle_interrupt_pin(dev, pin);
 				irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
-						PCI_SLOT(bridge->devfn), pin);
+						PCI_SLOT(bridge->devfn), pin - 1);
 				if (irq >= 0)
 					dev_warn(&dev->dev, "using bridge %s "
 						 "INT %c to get IRQ %d\n",
-						 pci_name(bridge), 'A' + pin,
+						 pci_name(bridge), 'A' + pin - 1,
 						 irq);
 				dev = bridge;
 			}
 			dev = temp_dev;
 			if (irq >= 0) {
 				dev_info(&dev->dev, "PCI->APIC IRQ transform: "
-					 "INT %c -> IRQ %d\n", 'A' + pin, irq);
+					 "INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
 				dev->irq = irq;
 				return 0;
 			} else
@@ -1268,7 +1264,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			return 0;
 
 		dev_warn(&dev->dev, "can't find IRQ for PCI INT %c%s\n",
-			 'A' + pin, msg);
+			 'A' + pin - 1, msg);
 	}
 	return 0;
 }
diff --git a/arch/x86/pci/visws.c b/arch/x86/pci/visws.c
index 16d0c0eb0d1..bcead7a4687 100644
--- a/arch/x86/pci/visws.c
+++ b/arch/x86/pci/visws.c
@@ -24,24 +24,6 @@ static void pci_visws_disable_irq(struct pci_dev *dev) { }
 
 unsigned int pci_bus0, pci_bus1;
 
-static inline u8 bridge_swizzle(u8 pin, u8 slot) 
-{
-	return (((pin - 1) + slot) % 4) + 1;
-}
-
-static u8 __init visws_swizzle(struct pci_dev *dev, u8 *pinp)
-{
-	u8 pin = *pinp;
-
-	while (dev->bus->self) {	/* Move up the chain of bridges. */
-		pin = bridge_swizzle(pin, PCI_SLOT(dev->devfn));
-		dev = dev->bus->self;
-	}
-	*pinp = pin;
-
-	return PCI_SLOT(dev->devfn);
-}
-
 static int __init visws_map_irq(struct pci_dev *dev, u8 slot, u8 pin)
 {
 	int irq, bus = dev->bus->number;
@@ -106,7 +88,7 @@ int __init pci_visws_init(void)
 	raw_pci_ops = &pci_direct_conf1;
 	pci_scan_bus_with_sysdata(pci_bus0);
 	pci_scan_bus_with_sysdata(pci_bus1);
-	pci_fixup_irqs(visws_swizzle, visws_map_irq);
+	pci_fixup_irqs(pci_common_swizzle, visws_map_irq);
 	pcibios_resource_survey();
 	return 0;
 }