Merge commit 'v2.6.29-rc1' into x86/urgent

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 830b9fcb642..19953df61c5 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -18,9 +18,26 @@
 #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 void (*mtrr_hook)(void);
 extern void zap_low_mappings(void);
@@ -29,7 +46,6 @@ 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);
@@ -38,6 +54,16 @@ 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);
 
@@ -149,7 +175,7 @@ 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);
 }
 #else
 static inline void prefill_possible_map(void)
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 3f95a40f718..83492b1f93b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -40,6 +40,26 @@
 
 #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
@@ -856,8 +876,6 @@ 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);
@@ -976,7 +994,7 @@ 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);
@@ -1085,7 +1103,7 @@ 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.spl