Merge branch 'linus' into perfcounters/core

Conflicts:
	arch/x86/kernel/irqinit.c
	arch/x86/kernel/irqinit_64.c
	arch/x86/kernel/traps.c
	arch/x86/mm/fault.c
	include/linux/sched.h
	kernel/exit.c

44 files changed, 383 insertions, 352 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index f6aa18eadf7..1a37bcdc860 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/stddef.h>
+#include <linux/stringify.h>
 #include <asm/asm.h>
 
 /*
@@ -74,6 +75,22 @@ static inline void alternatives_smp_switch(int smp) {}
 
 const unsigned char *const *find_nop_table(void);
 
+/* alternative assembly primitive: */
+#define ALTERNATIVE(oldinstr, newinstr, feature)			\
+									\
+      "661:\n\t" oldinstr "\n662:\n"					\
+      ".section .altinstructions,\"a\"\n"				\
+      _ASM_ALIGN "\n"							\
+      _ASM_PTR "661b\n"				/* label           */	\
+      _ASM_PTR "663f\n"				/* new instruction */	\
+      "	 .byte " __stringify(feature) "\n"	/* feature bit     */	\
+      "	 .byte 662b-661b\n"			/* sourcelen       */	\
+      "	 .byte 664f-663f\n"			/* replacementlen  */	\
+      ".previous\n"							\
+      ".section .altinstr_replacement, \"ax\"\n"			\
+      "663:\n\t" newinstr "\n664:\n"		/* replacement     */	\
+      ".previous"
+
 /*
  * Alternative instructions for different CPU types or capabilities.
  *
@@ -87,18 +104,7 @@ const unsigned char *const *find_nop_table(void);
  * without volatile and memory clobber.
  */
 #define alternative(oldinstr, newinstr, feature)			\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      _ASM_ALIGN "\n"					\
-		      _ASM_PTR "661b\n"		/* label */		\
-		      _ASM_PTR "663f\n"		/* new instruction */	\
-		      "	 .byte %c0\n"		/* feature bit */	\
-		      "	 .byte 662b-661b\n"	/* sourcelen */		\
-		      "	 .byte 664f-663f\n"	/* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"  /* replacement */	\
-		      ".previous" :: "i" (feature) : "memory")
+	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) : : : "memory")
 
 /*
  * Alternative inline assembly with input.
@@ -109,35 +115,16 @@ const unsigned char *const *find_nop_table(void);
  * Best is to use constraints that are fixed size (like (%1) ... "r")
  * If you use variable sized constraints like "m" or "g" in the
  * replacement make sure to pad to the worst case length.
+ * Leaving an unused argument 0 to keep API compatibility.
  */
 #define alternative_input(oldinstr, newinstr, feature, input...)	\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      _ASM_ALIGN "\n"					\
-		      _ASM_PTR "661b\n"		/* label */		\
-		      _ASM_PTR "663f\n"		/* new instruction */	\
-		      "	 .byte %c0\n"		/* feature bit */	\
-		      "	 .byte 662b-661b\n"	/* sourcelen */		\
-		      "	 .byte 664f-663f\n"	/* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"  /* replacement */	\
-		      ".previous" :: "i" (feature), ##input)
+	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature)		\
+		: : "i" (0), ## input)
 
 /* Like alternative_input, but with a single output argument */
 #define alternative_io(oldinstr, newinstr, feature, output, input...)	\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      _ASM_ALIGN "\n"					\
-		      _ASM_PTR "661b\n"		/* label */		\
-		      _ASM_PTR "663f\n"		/* new instruction */	\
-		      "	 .byte %c[feat]\n"	/* feature bit */	\
-		      "	 .byte 662b-661b\n"	/* sourcelen */		\
-		      "	 .byte 664f-663f\n"	/* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"  /* replacement */ \
-		      ".previous" : output : [feat] "i" (feature), ##input)
+	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature)		\
+		: output : "i" (0), ## input)
 
 /*
  * use this macro(s) if you need more than one output parameter
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index f712344329b..262e0282004 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -27,6 +27,8 @@ extern int amd_iommu_init(void);
 extern int amd_iommu_init_dma_ops(void);
 extern void amd_iommu_detect(void);
 extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
+extern void amd_iommu_flush_all_domains(void);
+extern void amd_iommu_flush_all_devices(void);
 #else
 static inline int amd_iommu_init(void) { return -ENODEV; }
 static inline void amd_iommu_detect(void) { }
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 95c8cd9d22b..0c878caaa0a 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -194,6 +194,27 @@
 #define PD_DMA_OPS_MASK		(1UL << 0) /* domain used for dma_ops */
 #define PD_DEFAULT_MASK		(1UL << 1) /* domain is a default dma_ops
 					      domain for an IOMMU */
+extern bool amd_iommu_dump;
+#define DUMP_printk(format, arg...)					\
+	do {								\
+		if (amd_iommu_dump)						\
+			printk(KERN_INFO "AMD IOMMU: " format, ## arg);	\
+	} while(0);
+
+/*
+ * Make iterating over all IOMMUs easier
+ */
+#define for_each_iommu(iommu) \
+	list_for_each_entry((iommu), &amd_iommu_list, list)
+#define for_each_iommu_safe(iommu, next) \
+	list_for_each_entry_safe((iommu), (next), &amd_iommu_list, list)
+
+#define APERTURE_RANGE_SHIFT	27	/* 128 MB */
+#define APERTURE_RANGE_SIZE	(1ULL << APERTURE_RANGE_SHIFT)
+#define APERTURE_RANGE_PAGES	(APERTURE_RANGE_SIZE >> PAGE_SHIFT)
+#define APERTURE_MAX_RANGES	32	/* allows 4GB of DMA address space */
+#define APERTURE_RANGE_INDEX(a)	((a) >> APERTURE_RANGE_SHIFT)
+#define APERTURE_PAGE_INDEX(a)	(((a) >> 21) & 0x3fULL)
 
 /*
  * This structure contains generic data for  IOMMU protection domains
@@ -210,6 +231,26 @@ struct protection_domain {
 };
 
 /*
+ * For dynamic growth the aperture size is split into ranges of 128MB of
+ * DMA address space each. This struct represents one such range.
+ */
+struct aperture_range {
+
+	/* address allocation bitmap */
+	unsigned long *bitmap;
+
+	/*
+	 * Array of PTE pages for the aperture. In this array we save all the
+	 * leaf pages of the domain page table used for the aperture. This way
+	 * we don't need to walk the page table to find a specific PTE. We can
+	 * just calculate its address in constant time.
+	 */
+	u64 *pte_pages[64];
+
+	unsigned long offset;
+};
+
+/*
  * Data container for a dma_ops specific protection domain
  */
 struct dma_ops_domain {
@@ -222,18 +263,10 @@ struct dma_ops_domain {
 	unsigned long aperture_size;
 
 	/* address we start to search for free addresses */
-	unsigned long next_bit;
-
-	/* address allocation bitmap */
-	unsigned long *bitmap;
+	unsigned long next_address;
 
-	/*
-	 * Array of PTE pages for the aperture. In this array we save all the
-	 * leaf pages of the domain page table used for the aperture. This way
-	 * we don't need to walk the page table to find a specific PTE. We can
-	 * just calculate its address in constant time.
-	 */
-	u64 **pte_pages;
+	/* address space relevant data */
+	struct aperture_range *aperture[APERTURE_MAX_RANGES];
 
 	/* This will be set to true when TLB needs to be flushed */
 	bool need_flush;
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 42f2f837742..bb7d4792584 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -107,8 +107,7 @@ extern u32 native_safe_apic_wait_icr_idle(void);
 extern void native_apic_icr_write(u32 low, u32 id);
 extern u64 native_apic_icr_read(void);
 
-#define EIM_8BIT_APIC_ID	0
-#define EIM_32BIT_APIC_ID	1
+extern int x2apic_mode;
 
 #ifdef CONFIG_X86_X2APIC
 /*
@@ -166,10 +165,9 @@ static inline u64 native_x2apic_icr_read(void)
 	return val;
 }
 
-extern int x2apic, x2apic_phys;
+extern int x2apic_phys;
 extern void check_x2apic(void);
 extern void enable_x2apic(void);
-extern void enable_IR_x2apic(void);
 extern void x2apic_icr_write(u32 low, u32 id);
 static inline int x2apic_enabled(void)
 {
@@ -183,6 +181,8 @@ static inline int x2apic_enabled(void)
 		return 1;
 	return 0;
 }
+
+#define x2apic_supported()	(cpu_has_x2apic)
 #else
 static inline void check_x2apic(void)
 {
@@ -190,28 +190,20 @@ static inline void check_x2apic(void)
 static inline void enable_x2apic(void)
 {
 }
-static inline void enable_IR_x2apic(void)
-{
-}
 static inline int x2apic_enabled(void)
 {
 	return 0;
 }
 
-#define	x2apic	0
-
+#define	x2apic_preenabled 0
+#define	x2apic_supported()	0
 #endif
 
-extern int get_physical_broadcast(void);
+extern void enable_IR_x2apic(void);
 
-#ifdef CONFIG_X86_X2APIC
-static inline void ack_x2APIC_irq(void)
-{
-	/* Docs say use 0 for future compatibility */
-	native_apic_msr_write(APIC_EOI, 0);
-}
-#endif
+extern int get_physical_broadcast(void);
 
+extern void apic_disable(void);
 extern int lapic_get_maxlvt(void);
 extern void clear_local_APIC(void);
 extern void connect_bsp_APIC(void);
@@ -252,7 +244,7 @@ static inline void lapic_shutdown(void) { }
 #define local_apic_timer_c2_ok		1
 static inline void init_apic_mappings(void) { }
 static inline void disable_local_APIC(void) { }
-
+static inline void apic_disable(void) { }
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_64
@@ -410,7 +402,7 @@ static inline unsigned default_get_apic_id(unsigned long x)
 {
 	unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
 
-	if (APIC_XAPIC(ver))
+	if (APIC_XAPIC(ver) || boot_cpu_has(X86_FEATURE_EXTD_APICID))
 		return (x >> 24) & 0xFF;
 	else
 		return (x >> 24) & 0x0F;
@@ -478,6 +470,9 @@ static inline unsigned int read_apic_id(void)
 extern void default_setup_apic_routing(void);
 
 #ifdef CONFIG_X86_32
+
+extern struct apic apic_default;
+
 /*
  * Set up the logical destination ID.
  *
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index bc9514fb3b1..7ddb36ab933 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -22,6 +22,7 @@
 #  define	APIC_INTEGRATED(x)	(1)
 #endif
 #define		APIC_XAPIC(x)		((x) >= 0x14)
+#define		APIC_EXT_SPACE(x)	((x) & 0x80000000)
 #define	APIC_TASKPRI	0x80
 #define		APIC_TPRI_MASK		0xFFu
 #define	APIC_ARBPRI	0x90
@@ -116,7 +117,9 @@
 #define		APIC_TDR_DIV_32		0x8
 #define		APIC_TDR_DIV_64		0x9
 #define		APIC_TDR_DIV_128	0xA
-#define	APIC_EILVT0     0x500
+#define	APIC_EFEAT	0x400
+#define	APIC_ECTRL	0x410
+#define APIC_EILVTn(n)	(0x500 + 0x10 * n)
 #define		APIC_EILVT_NR_AMD_K8	1	/* # of extended interrupts */
 #define		APIC_EILVT_NR_AMD_10H	4
 #define		APIC_EILVT_LVTOFF(x)	(((x) >> 4) & 0xF)
@@ -125,9 +128,6 @@
 #define		APIC_EILVT_MSG_NMI	0x4
 #define		APIC_EILVT_MSG_EXT	0x7
 #define		APIC_EILVT_MASKED	(1 << 16)
-#define	APIC_EILVT1     0x510
-#define	APIC_EILVT2     0x520
-#define	APIC_EILVT3     0x530
 
 #define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
 #define APIC_BASE_MSR	0x800
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 6ba23dd9fc9..418e632d4a8 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -8,11 +8,26 @@
 
 #ifdef __KERNEL__
 
+#include <asm/page_types.h>
+
 /* Physical address where kernel should be loaded. */
 #define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
 				+ (CONFIG_PHYSICAL_ALIGN - 1)) \
 				& ~(CONFIG_PHYSICAL_ALIGN - 1))
 
+/* Minimum kernel alignment, as a power of two */
+#ifdef CONFIG_x86_64
+#define MIN_KERNEL_ALIGN_LG2	PMD_SHIFT
+#else
+#define MIN_KERNEL_ALIGN_LG2	(PAGE_SHIFT+1)
+#endif
+#define MIN_KERNEL_ALIGN	(_AC(1, UL) << MIN_KERNEL_ALIGN_LG2)
+
+#if (CONFIG_PHYSICAL_ALIGN & (CONFIG_PHYSICAL_ALIGN-1)) || \
+	(CONFIG_PHYSICAL_ALIGN < (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2))
+#error "Invalid value for CONFIG_PHYSICAL_ALIGN"
+#endif
+
 #ifdef CONFIG_KERNEL_BZIP2
 #define BOOT_HEAP_SIZE             0x400000
 #else /* !CONFIG_KERNEL_BZIP2 */
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index 433adaebf9b..1724e8de317 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -50,7 +50,8 @@ struct setup_header {
 	__u32	ramdisk_size;
 	__u32	bootsect_kludge;
 	__u16	heap_end_ptr;
-	__u16	_pad1;
+	__u8	ext_loader_ver;
+	__u8	ext_loader_type;
 	__u32	cmd_line_ptr;
 	__u32	initrd_addr_max;
 	__u32	kernel_alignment;
diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h
index 222802029fa..d96c1ee3a95 100644
--- a/arch/x86/include/asm/cpu_debug.h
+++ b/arch/x86/include/asm/cpu_debug.h
@@ -86,105 +86,7 @@ enum cpu_file_bit {
 	CPU_VALUE_BIT,				/* value		*/
 };
 
-#define	CPU_FILE_VALUE			(1 << CPU_VALUE_BIT)
-
-/*
- * DisplayFamily_DisplayModel	Processor Families/Processor Number Series
- * --------------------------	------------------------------------------
- * 05_01, 05_02, 05_04		Pentium, Pentium with MMX
- *
- * 06_01			Pentium Pro
- * 06_03, 06_05			Pentium II Xeon, Pentium II
- * 06_07, 06_08, 06_0A, 06_0B	Pentium III Xeon, Pentum III
- *
- * 06_09, 060D			Pentium M
- *
- * 06_0E			Core Duo, Core Solo
- *
- * 06_0F			Xeon 3000, 3200, 5100, 5300, 7300 series,
- *				Core 2 Quad, Core 2 Extreme, Core 2 Duo,
- *				Pentium dual-core
- * 06_17			Xeon 5200, 5400 series, Core 2 Quad Q9650
- *
- * 06_1C			Atom
- *
- * 0F_00, 0F_01, 0F_02		Xeon, Xeon MP, Pentium 4
- * 0F_03, 0F_04			Xeon, Xeon MP, Pentium 4, Pentium D
- *
- * 0F_06			Xeon 7100, 5000 Series, Xeon MP,
- *				Pentium 4, Pentium D
- */
-
-/* Register processors bits */
-enum cpu_processor_bit {
-	CPU_NONE,
-/* Intel */
-	CPU_INTEL_PENTIUM_BIT,
-	CPU_INTEL_P6_BIT,
-	CPU_INTEL_PENTIUM_M_BIT,
-	CPU_INTEL_CORE_BIT,
-	CPU_INTEL_CORE2_BIT,
-	CPU_INTEL_ATOM_BIT,
-	CPU_INTEL_XEON_P4_BIT,
-	CPU_INTEL_XEON_MP_BIT,
-/* AMD */
-	CPU_AMD_K6_BIT,
-	CPU_AMD_K7_BIT,
-	CPU_AMD_K8_BIT,
-	CPU_AMD_0F_BIT,
-	CPU_AMD_10_BIT,
-	CPU_AMD_11_BIT,
-};
-
-#define	CPU_INTEL_PENTIUM	(1 << CPU_INTEL_PENTIUM_BIT)
-#define	CPU_INTEL_P6		(1 << CPU_INTEL_P6_BIT)
-#define	CPU_INTEL_PENTIUM_M	(1 << CPU_INTEL_PENTIUM_M_BIT)
-#define	CPU_INTEL_CORE		(1 << CPU_INTEL_CORE_BIT)
-#define	CPU_INTEL_CORE2		(1 << CPU_INTEL_CORE2_BIT)
-#define	CPU_INTEL_ATOM		(1 << CPU_INTEL_ATOM_BIT)
-#define	CPU_INTEL_XEON_P4	(1 << CPU_INTEL_XEON_P4_BIT)
-#define	CPU_INTEL_XEON_MP	(1 << CPU_INTEL_XEON_MP_BIT)
-
-#define	CPU_INTEL_PX		(CPU_INTEL_P6 | CPU_INTEL_PENTIUM_M)
-#define	CPU_INTEL_COREX		(CPU_INTEL_CORE | CPU_INTEL_CORE2)
-#define	CPU_INTEL_XEON		(CPU_INTEL_XEON_P4 | CPU_INTEL_XEON_MP)
-#define	CPU_CO_AT		(CPU_INTEL_CORE | CPU_INTEL_ATOM)
-#define	CPU_C2_AT		(CPU_INTEL_CORE2 | CPU_INTEL_ATOM)
-#define	CPU_CX_AT		(CPU_INTEL_COREX | CPU_INTEL_ATOM)
-#define	CPU_CX_XE		(CPU_INTEL_COREX | CPU_INTEL_XEON)
-#define	CPU_P6_XE		(CPU_INTEL_P6 | CPU_INTEL_XEON)
-#define	CPU_PM_CO_AT		(CPU_INTEL_PENTIUM_M | CPU_CO_AT)
-#define	CPU_C2_AT_XE		(CPU_C2_AT | CPU_INTEL_XEON)
-#define	CPU_CX_AT_XE		(CPU_CX_AT | CPU_INTEL_XEON)
-#define	CPU_P6_CX_AT		(CPU_INTEL_P6 | CPU_CX_AT)
-#define	CPU_P6_CX_XE		(CPU_P6_XE | CPU_INTEL_COREX)
-#define	CPU_P6_CX_AT_XE		(CPU_INTEL_P6 | CPU_CX_AT_XE)
-#define	CPU_PM_CX_AT_XE		(CPU_INTEL_PENTIUM_M | CPU_CX_AT_XE)
-#define	CPU_PM_CX_AT		(CPU_INTEL_PENTIUM_M | CPU_CX_AT)
-#define	CPU_PM_CX_XE		(CPU_INTEL_PENTIUM_M | CPU_CX_XE)
-#define	CPU_PX_CX_AT		(CPU_INTEL_PX | CPU_CX_AT)
-#define	CPU_PX_CX_AT_XE		(CPU_INTEL_PX | CPU_CX_AT_XE)
-
-/* Select all supported Intel CPUs */
-#define	CPU_INTEL_ALL		(CPU_INTEL_PENTIUM | CPU_PX_CX_AT_XE)
-
-#define	CPU_AMD_K6		(1 << CPU_AMD_K6_BIT)
-#define	CPU_AMD_K7		(1 << CPU_AMD_K7_BIT)
-#define	CPU_AMD_K8		(1 << CPU_AMD_K8_BIT)
-#define	CPU_AMD_0F		(1 << CPU_AMD_0F_BIT)
-#define	CPU_AMD_10		(1 << CPU_AMD_10_BIT)
-#define	CPU_AMD_11		(1 << CPU_AMD_11_BIT)
-
-#define	CPU_K10_PLUS		(CPU_AMD_10 | CPU_AMD_11)
-#define	CPU_K0F_PLUS		(CPU_AMD_0F | CPU_K10_PLUS)
-#define	CPU_K8_PLUS		(CPU_AMD_K8 | CPU_K0F_PLUS)
-#define	CPU_K7_PLUS		(CPU_AMD_K7 | CPU_K8_PLUS)
-
-/* Select all supported AMD CPUs */
-#define	CPU_AMD_ALL		(CPU_AMD_K6 | CPU_K7_PLUS)
-
-/* Select all supported CPUs */
-#define	CPU_ALL			(CPU_INTEL_ALL | CPU_AMD_ALL)
+#define	CPU_FILE_VALUE		(1 << CPU_VALUE_BIT)
 
 #define MAX_CPU_FILES		512
 
@@ -220,7 +122,6 @@ struct cpu_debug_range {
 	unsigned		min;		/* Register range min	*/
 	unsigned		max;		/* Register range max	*/
 	unsigned		flag;		/* Supported flags	*/
-	unsigned		model;		/* Supported models	*/
 };
 
 #endif /* _ASM_X86_CPU_DEBUG_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index bb83b1c397a..19af42138f7 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -22,7 +22,7 @@
 #define X86_FEATURE_TSC		(0*32+ 4) /* Time Stamp Counter */
 #define X86_FEATURE_MSR		(0*32+ 5) /* Model-Specific Registers */
 #define X86_FEATURE_PAE		(0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE		(0*32+ 7) /* Machine Check Architecture */
+#define X86_FEATURE_MCE		(0*32+ 7) /* Machine Check Exception */
 #define X86_FEATURE_CX8		(0*32+ 8) /* CMPXCHG8 instruction */
 #define X86_FEATURE_APIC	(0*32+ 9) /* Onboard APIC */
 #define X86_FEATURE_SEP		(0*32+11) /* SYSENTER/SYSEXIT */
@@ -94,6 +94,7 @@
 #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
 #define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
 #define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
+#define X86_FEATURE_EXTD_APICID	(3*32+26) /* has extended APICID (8 bits) */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
@@ -192,11 +193,11 @@ extern const char * const x86_power_flags[32];
 #define clear_cpu_cap(c, bit)	clear_bit(bit, (unsigned long *)((c)->x86_capability))
 #define setup_clear_cpu_cap(bit) do { \
 	clear_cpu_cap(&boot_cpu_data, bit);	\
-	set_bit(bit, (unsigned long *)cleared_cpu_caps); \
+	set_bit(bit, (unsigned long *)cpu_caps_cleared); \
 } while (0)
 #define setup_force_cpu_cap(bit) do { \
 	set_cpu_cap(&boot_cpu_data, bit);	\
-	clear_bit(bit, (unsigned long *)cleared_cpu_caps);	\
+	set_bit(bit, (unsigned long *)cpu_caps_set);	\
 } while (0)
 
 #define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
diff --git a/arch/x86/include/asm/ds.h b/arch/x86/include/asm/ds.h
index a8f672ba100..70dac199b09 100644
--- a/arch/x86/include/asm/ds.h
+++ b/arch/x86/include/asm/ds.h
@@ -15,8 +15,8 @@
  * - buffer allocation (memory accounting)
  *
  *
- * Copyright (C) 2007-2008 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
+ * Copyright (C) 2007-2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
  */
 
 #ifndef _ASM_X86_DS_H
@@ -83,8 +83,10 @@ enum ds_feature {
  * The interrupt threshold is independent from the overflow callback
  * to allow users to use their own overflow interrupt handling mechanism.
  *
- * task: the task to request recording for;
- *       NULL for per-cpu recording on the current cpu
+ * The function might sleep.
+ *
+ * task: the task to request recording for
+ * cpu:  the cpu to request recording for
  * base: the base pointer for the (non-pageable) buffer;
  * size: the size of the provided buffer in bytes
  * ovfl: pointer to a function to be called on buffer overflow;
@@ -93,19 +95,28 @@ enum ds_feature {
  *     -1 if no interrupt threshold is requested.
  * flags: a bit-mask of the above flags
  */
-extern struct bts_tracer *ds_request_bts(struct task_struct *task,
-					 void *base, size_t size,
-					 bts_ovfl_callback_t ovfl,
-					 size_t th, unsigned int flags);
-extern struct pebs_tracer *ds_request_pebs(struct task_struct *task,
-					   void *base, size_t size,
-					   pebs_ovfl_callback_t ovfl,
-					   size_t th, unsigned int flags);
+extern struct bts_tracer *ds_request_bts_task(struct task_struct *task,
+					      void *base, size_t size,
+					      bts_ovfl_callback_t ovfl,
+					      size_t th, unsigned int flags);
+extern struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size,
+					     bts_ovfl_callback_t ovfl,
+					     size_t th, unsigned int flags);
+extern struct pebs_tracer *ds_request_pebs_task(struct task_struct *task,
+						void *base, size_t size,
+						pebs_ovfl_callback_t ovfl,
+						size_t th, unsigned int flags);
+extern struct pebs_tracer *ds_request_pebs_cpu(int cpu,
+					       void *base, size_t size,
+					       pebs_ovfl_callback_t ovfl,
+					       size_t th, unsigned int flags);
 
 /*
  * Release BTS or PEBS resources
  * Suspend and resume BTS or PEBS tracing
  *
+ * Must be called with irq's enabled.
+ *
  * tracer: the tracer handle returned from ds_request_~()
  */
 extern void ds_release_bts(struct bts_tracer *tracer);
@@ -115,6 +126,28 @@ extern void ds_release_pebs(struct pebs_tracer *tracer);
 extern void ds_suspend_pebs(struct pebs_tracer *tracer);
 extern void ds_resume_pebs(struct pebs_tracer *tracer);
 
+/*
+ * Release BTS or PEBS resources
+ * Suspend and resume BTS or PEBS tracing
+ *
+ * Cpu tracers must call this on the traced cpu.
+ * Task tracers must call ds_release_~_noirq() for themselves.
+ *
+ * May be called with irq's disabled.
+ *
+ * Returns 0 if successful;
+ * -EPERM if the cpu tracer does not trace the current cpu.
+ * -EPERM if the task tracer does not trace itself.
+ *
+ * tracer: the tracer handle returned from ds_request_~()
+ */
+extern int ds_release_bts_noirq(struct bts_tracer *tracer);
+extern int ds_suspend_bts_noirq(struct bts_tracer *tracer);
+extern int ds_resume_bts_noirq(struct bts_tracer *tracer);
+extern int ds_release_pebs_noirq(struct pebs_tracer *tracer);
+extern int ds_suspend_pebs_noirq(struct pebs_tracer *tracer);
+extern int ds_resume_pebs_noirq(struct pebs_tracer *tracer);
+
 
 /*
  * The raw DS buffer state as it is used for BTS and PEBS recording.
@@ -170,9 +203,9 @@ struct bts_struct {
 		} lbr;
 		/* BTS_TASK_ARRIVES or BTS_TASK_DEPARTS */
 		struct {
-			__u64 jiffies;
+			__u64 clock;
 			pid_t pid;
-		} timestamp;
+		} event;
 	} variant;
 };
 
@@ -201,8 +234,12 @@ struct bts_trace {
 struct pebs_trace {
 	struct ds_trace ds;
 
-	/* the PEBS reset value */
-	unsigned long long reset_value;
+	/* the number of valid counters in the below array */
+	unsigned int counters;
+
+#define MAX_PEBS_COUNTERS 4
+	/* the counter reset value */
+	unsigned long long counter_reset[MAX_PEBS_COUNTERS];
 };
 
 
@@ -237,9 +274,11 @@ extern int ds_reset_pebs(struct pebs_tracer *tracer);
  * Returns 0 on success; -Eerrno on error
  *
  * tracer: the tracer handle returned from ds_request_pebs()
+ * counter: the index of the counter
  * value: the new counter reset value
  */
-extern int ds_set_pebs_reset(struct pebs_tracer *tracer, u64 value);
+extern int ds_set_pebs_reset(struct pebs_tracer *tracer,
+			     unsigned int counter, u64 value);
 
 /*
  * Initialization
@@ -252,21 +291,12 @@ extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
  */
 extern void ds_switch_to(struc