Merge branch 'perf'

Signed-off-by: Avi Kivity <avi@redhat.com>

11 files changed, 864 insertions, 446 deletions

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index b4ac2cdcb64..1fa03e04ae4 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -373,6 +373,7 @@ extern atomic_t init_deasserted;
 extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
 #endif
 
+#ifdef CONFIG_X86_LOCAL_APIC
 static inline u32 apic_read(u32 reg)
 {
 	return apic->read(reg);
@@ -403,10 +404,19 @@ static inline u32 safe_apic_wait_icr_idle(void)
 	return apic->safe_wait_icr_idle();
 }
 
+#else /* CONFIG_X86_LOCAL_APIC */
+
+static inline u32 apic_read(u32 reg) { return 0; }
+static inline void apic_write(u32 reg, u32 val) { }
+static inline u64 apic_icr_read(void) { return 0; }
+static inline void apic_icr_write(u32 low, u32 high) { }
+static inline void apic_wait_icr_idle(void) { }
+static inline u32 safe_apic_wait_icr_idle(void) { return 0; }
+
+#endif /* CONFIG_X86_LOCAL_APIC */
 
 static inline void ack_APIC_irq(void)
 {
-#ifdef CONFIG_X86_LOCAL_APIC
 	/*
 	 * ack_APIC_irq() actually gets compiled as a single instruction
 	 * ... yummie.
@@ -414,7 +424,6 @@ static inline void ack_APIC_irq(void)
 
 	/* Docs say use 0 for future compatibility */
 	apic_write(APIC_EOI, 0);
-#endif
 }
 
 static inline unsigned default_get_apic_id(unsigned long x)
diff --git a/arch/x86/include/asm/ds.h b/arch/x86/include/asm/ds.h
deleted file mode 100644
index 70dac199b09..00000000000
--- a/arch/x86/include/asm/ds.h
+++ /dev/null
@@ -1,302 +0,0 @@
-/*
- * Debug Store (DS) support
- *
- * This provides a low-level interface to the hardware's Debug Store
- * feature that is used for branch trace store (BTS) and
- * precise-event based sampling (PEBS).
- *
- * It manages:
- * - DS and BTS hardware configuration
- * - buffer overflow handling (to be done)
- * - buffer access
- *
- * It does not do:
- * - security checking (is the caller allowed to trace the task)
- * - buffer allocation (memory accounting)
- *
- *
- * Copyright (C) 2007-2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
- */
-
-#ifndef _ASM_X86_DS_H
-#define _ASM_X86_DS_H
-
-
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/err.h>
-
-
-#ifdef CONFIG_X86_DS
-
-struct task_struct;
-struct ds_context;
-struct ds_tracer;
-struct bts_tracer;
-struct pebs_tracer;
-
-typedef void (*bts_ovfl_callback_t)(struct bts_tracer *);
-typedef void (*pebs_ovfl_callback_t)(struct pebs_tracer *);
-
-
-/*
- * A list of features plus corresponding macros to talk about them in
- * the ds_request function's flags parameter.
- *
- * We use the enum to index an array of corresponding control bits;
- * we use the macro to index a flags bit-vector.
- */
-enum ds_feature {
-	dsf_bts = 0,
-	dsf_bts_kernel,
-#define BTS_KERNEL (1 << dsf_bts_kernel)
-	/* trace kernel-mode branches */
-
-	dsf_bts_user,
-#define BTS_USER (1 << dsf_bts_user)
-	/* trace user-mode branches */
-
-	dsf_bts_overflow,
-	dsf_bts_max,
-	dsf_pebs = dsf_bts_max,
-
-	dsf_pebs_max,
-	dsf_ctl_max = dsf_pebs_max,
-	dsf_bts_timestamps = dsf_ctl_max,
-#define BTS_TIMESTAMPS (1 << dsf_bts_timestamps)
-	/* add timestamps into BTS trace */
-
-#define BTS_USER_FLAGS (BTS_KERNEL | BTS_USER | BTS_TIMESTAMPS)
-};
-
-
-/*
- * Request BTS or PEBS
- *
- * Due to alignement constraints, the actual buffer may be slightly
- * smaller than the requested or provided buffer.
- *
- * Returns a pointer to a tracer structure on success, or
- * ERR_PTR(errcode) on failure.
- *
- * The interrupt threshold is independent from the overflow callback
- * to allow users to use their own overflow interrupt handling mechanism.
- *
- * 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;
- *       NULL if cyclic buffer requested
- * th: the interrupt threshold in records from the end of the buffer;
- *     -1 if no interrupt threshold is requested.
- * flags: a bit-mask of the above 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);
-extern void ds_suspend_bts(struct bts_tracer *tracer);
-extern void ds_resume_bts(struct bts_tracer *tracer);
-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.
- *
- * This is the low-level, arch-dependent interface for working
- * directly on the raw trace data.
- */
-struct ds_trace {
-	/* the number of bts/pebs records */
-	size_t n;
-	/* the size of a bts/pebs record in bytes */
-	size_t size;
-	/* pointers into the raw buffer:
-	   - to the first entry */
-	void *begin;
-	/* - one beyond the last entry */
-	void *end;
-	/* - one beyond the newest entry */
-	void *top;
-	/* - the interrupt threshold */
-	void *ith;
-	/* flags given on ds_request() */
-	unsigned int flags;
-};
-
-/*
- * An arch-independent view on branch trace data.
- */
-enum bts_qualifier {
-	bts_invalid,
-#define BTS_INVALID bts_invalid
-
-	bts_branch,
-#define BTS_BRANCH bts_branch
-
-	bts_task_arrives,
-#define BTS_TASK_ARRIVES bts_task_arrives
-
-	bts_task_departs,
-#define BTS_TASK_DEPARTS bts_task_departs
-
-	bts_qual_bit_size = 4,
-	bts_qual_max = (1 << bts_qual_bit_size),
-};
-
-struct bts_struct {
-	__u64 qualifier;
-	union {
-		/* BTS_BRANCH */
-		struct {
-			__u64 from;
-			__u64 to;
-		} lbr;
-		/* BTS_TASK_ARRIVES or BTS_TASK_DEPARTS */
-		struct {
-			__u64 clock;
-			pid_t pid;
-		} event;
-	} variant;
-};
-
-
-/*
- * The BTS state.
- *
- * This gives access to the raw DS state and adds functions to provide
- * an arch-independent view of the BTS data.
- */
-struct bts_trace {
-	struct ds_trace ds;
-
-	int (*read)(struct bts_tracer *tracer, const void *at,
-		    struct bts_struct *out);
-	int (*write)(struct bts_tracer *tracer, const struct bts_struct *in);
-};
-
-
-/*
- * The PEBS state.
- *
- * This gives access to the raw DS state and the PEBS-specific counter
- * reset value.
- */
-struct pebs_trace {
-	struct ds_trace ds;
-
-	/* 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];
-};
-
-
-/*
- * Read the BTS or PEBS trace.
- *
- * Returns a view on the trace collected for the parameter tracer.
- *
- * The view remains valid as long as the traced task is not running or
- * the tracer is suspended.
- * Writes into the trace buffer are not reflected.
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern const struct bts_trace *ds_read_bts(struct bts_tracer *tracer);
-extern const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer);
-
-
-/*
- * Reset the write pointer of the BTS/PEBS buffer.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern int ds_reset_bts(struct bts_tracer *tracer);
-extern int ds_reset_pebs(struct pebs_tracer *tracer);
-
-/*
- * Set the PEBS counter reset value.
- *
- * 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,
-			     unsigned int counter, u64 value);
-
-/*
- * Initialization
- */
-struct cpuinfo_x86;
-extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
-
-/*
- * Context switch work
- */
-extern void ds_switch_to(struct task_struct *prev, struct task_struct *next);
-
-#else /* CONFIG_X86_DS */
-
-struct cpuinfo_x86;
-static inline void __cpuinit ds_init_intel(struct cpuinfo_x86 *ignored) {}
-static inline void ds_switch_to(struct task_struct *prev,
-				struct task_struct *next) {}
-
-#endif /* CONFIG_X86_DS */
-#endif /* _ASM_X86_DS_H */
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 96c2e0ad04c..88c765e1641 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -68,6 +68,8 @@ struct insn {
 	const insn_byte_t *next_byte;
 };
 
+#define MAX_INSN_SIZE	16
+
 #define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6)
 #define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3)
 #define X86_MODRM_RM(modrm) ((modrm) & 0x07)
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 4ffa345a8cc..54788253915 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -24,6 +24,7 @@
 #include <linux/types.h>
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
+#include <asm/insn.h>
 
 #define  __ARCH_WANT_KPROBES_INSN_SLOT
 
@@ -36,7 +37,6 @@ typedef u8 kprobe_opcode_t;
 #define RELATIVEJUMP_SIZE 5
 #define RELATIVECALL_OPCODE 0xe8
 #define RELATIVE_ADDR_SIZE 4
-#define MAX_INSN_SIZE 16
 #define MAX_STACK_SIZE 64
 #define MIN_STACK_SIZE(ADDR)					       \
 	(((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4604e6a54d3..bc473acfa7f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -71,11 +71,14 @@
 #define MSR_IA32_LASTINTTOIP		0x000001de
 
 /* DEBUGCTLMSR bits (others vary by model): */
-#define _DEBUGCTLMSR_LBR	0 /* last branch recording */
-#define _DEBUGCTLMSR_BTF	1 /* single-step on branches */
-
-#define DEBUGCTLMSR_LBR		(1UL << _DEBUGCTLMSR_LBR)
-#define DEBUGCTLMSR_BTF		(1UL << _DEBUGCTLMSR_BTF)
+#define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
+#define DEBUGCTLMSR_TR			(1UL <<  6)
+#define DEBUGCTLMSR_BTS			(1UL <<  7)
+#define DEBUGCTLMSR_BTINT		(1UL <<  8)
+#define DEBUGCTLMSR_BTS_OFF_OS		(1UL <<  9)
+#define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
+#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
 
 #define MSR_IA32_MC0_CTL		0x00000400
 #define MSR_IA32_MC0_STATUS		0x00000401
@@ -359,6 +362,8 @@
 #define MSR_P4_U2L_ESCR0		0x000003b0
 #define MSR_P4_U2L_ESCR1		0x000003b1
 
+#define MSR_P4_PEBS_MATRIX_VERT		0x000003f2
+
 /* Intel Core-based CPU performance counters */
 #define MSR_CORE_PERF_FIXED_CTR0	0x00000309
 #define MSR_CORE_PERF_FIXED_CTR1	0x0000030a
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index db6109a885a..254883d0c7e 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -5,7 +5,7 @@
  * Performance event hw details:
  */
 
-#define X86_PMC_MAX_GENERIC					8
+#define X86_PMC_MAX_GENERIC				       32
 #define X86_PMC_MAX_FIXED					3
 
 #define X86_PMC_IDX_GENERIC				        0
@@ -18,39 +18,31 @@
 #define MSR_ARCH_PERFMON_EVENTSEL0			     0x186
 #define MSR_ARCH_PERFMON_EVENTSEL1			     0x187
 
-#define ARCH_PERFMON_EVENTSEL_ENABLE			  (1 << 22)
-#define ARCH_PERFMON_EVENTSEL_ANY			  (1 << 21)
-#define ARCH_PERFMON_EVENTSEL_INT			  (1 << 20)
-#define ARCH_PERFMON_EVENTSEL_OS			  (1 << 17)
-#define ARCH_PERFMON_EVENTSEL_USR			  (1 << 16)
-
-/*
- * Includes eventsel and unit mask as well:
- */
-
-
-#define INTEL_ARCH_EVTSEL_MASK		0x000000FFULL
-#define INTEL_ARCH_UNIT_MASK		0x0000FF00ULL
-#define INTEL_ARCH_EDGE_MASK		0x00040000ULL
-#define INTEL_ARCH_INV_MASK		0x00800000ULL
-#define INTEL_ARCH_CNT_MASK		0xFF000000ULL
-#define INTEL_ARCH_EVENT_MASK	(INTEL_ARCH_UNIT_MASK|INTEL_ARCH_EVTSEL_MASK)
-
-/*
- * filter mask to validate fixed counter events.
- * the following filters disqualify for fixed counters:
- *  - inv
- *  - edge
- *  - cnt-mask
- *  The other filters are supported by fixed counters.
- *  The any-thread option is supported starting with v3.
- */
-#define INTEL_ARCH_FIXED_MASK \
-	(INTEL_ARCH_CNT_MASK| \
-	 INTEL_ARCH_INV_MASK| \
-	 INTEL_ARCH_EDGE_MASK|\
-	 INTEL_ARCH_UNIT_MASK|\
-	 INTEL_ARCH_EVENT_MASK)
+#define ARCH_PERFMON_EVENTSEL_EVENT			0x000000FFULL
+#define ARCH_PERFMON_EVENTSEL_UMASK			0x0000FF00ULL
+#define ARCH_PERFMON_EVENTSEL_USR			(1ULL << 16)
+#define ARCH_PERFMON_EVENTSEL_OS			(1ULL << 17)
+#define ARCH_PERFMON_EVENTSEL_EDGE			(1ULL << 18)
+#define ARCH_PERFMON_EVENTSEL_INT			(1ULL << 20)
+#define ARCH_PERFMON_EVENTSEL_ANY			(1ULL << 21)
+#define ARCH_PERFMON_EVENTSEL_ENABLE			(1ULL << 22)
+#define ARCH_PERFMON_EVENTSEL_INV			(1ULL << 23)
+#define ARCH_PERFMON_EVENTSEL_CMASK			0xFF000000ULL
+
+#define AMD64_EVENTSEL_EVENT	\
+	(ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32))
+#define INTEL_ARCH_EVENT_MASK	\
+	(ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
+
+#define X86_RAW_EVENT_MASK		\
+	(ARCH_PERFMON_EVENTSEL_EVENT |	\
+	 ARCH_PERFMON_EVENTSEL_UMASK |	\
+	 ARCH_PERFMON_EVENTSEL_EDGE  |	\
+	 ARCH_PERFMON_EVENTSEL_INV   |	\
+	 ARCH_PERFMON_EVENTSEL_CMASK)
+#define AMD64_RAW_EVENT_MASK		\
+	(X86_RAW_EVENT_MASK          |  \
+	 AMD64_EVENTSEL_EVENT)
 
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		      0x3c
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)
@@ -67,7 +59,7 @@
 union cpuid10_eax {
 	struct {
 		unsigned int version_id:8;
-		unsigned int num_events:8;
+		unsigned int num_counters:8;
 		unsigned int bit_width:8;
 		unsigned int mask_length:8;
 	} split;
@@ -76,7 +68,7 @@ union cpuid10_eax {
 
 union cpuid10_edx {
 	struct {
-		unsigned int num_events_fixed:4;
+		unsigned int num_counters_fixed:4;
 		unsigned int reserved:28;
 	} split;
 	unsigned int full;
@@ -136,6 +128,18 @@ extern void perf_events_lapic_init(void);
 
 #define PERF_EVENT_INDEX_OFFSET			0
 
+/*
+ * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups.
+ * This flag is otherwise unused and ABI specified to be 0, so nobody should
+ * care what we do with it.
+ */
+#define PERF_EFLAGS_EXACT	(1UL << 3)
+
+struct pt_regs;
+extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_misc_flags(struct pt_regs *regs);
+#define perf_misc_flags(regs)	perf_misc_flags(regs)
+
 #else
 static inline void init_hw_perf_events(void)		{ }
 static inline void perf_events_lapic_init(void)	{ }
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
new file mode 100644
index 00000000000..b05400a542f
--- /dev/null
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -0,0 +1,794 @@
+/*
+ * Netburst Perfomance Events (P4, old Xeon)
+ */
+
+#ifndef PERF_EVENT_P4_H
+#define PERF_EVENT_P4_H
+
+#include <linux/cpu.h>
+#include <linux/bitops.h>
+
+/*
+ * NetBurst has perfomance MSRs shared between
+ * threads if HT is turned on, ie for both logical
+ * processors (mem: in turn in Atom with HT support
+ * perf-MSRs are not shared and every thread has its
+ * own perf-MSRs set)
+ */
+#define ARCH_P4_TOTAL_ESCR	(46)
+#define ARCH_P4_RESERVED_ESCR	(2) /* IQ_ESCR(0,1) not always present */
+#define ARCH_P4_MAX_ESCR	(ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR)
+#define ARCH_P4_MAX_CCCR	(18)
+#define ARCH_P4_MAX_COUNTER	(ARCH_P4_MAX_CCCR / 2)
+
+#define P4_ESCR_EVENT_MASK	0x7e000000U
+#define P4_ESCR_EVENT_SHIFT	25
+#define P4_ESCR_EVENTMASK_MASK	0x01fffe00U
+#define P4_ESCR_EVENTMASK_SHIFT	9
+#define P4_ESCR_TAG_MASK	0x000001e0U
+#define P4_ESCR_TAG_SHIFT	5
+#define P4_ESCR_TAG_ENABLE	0x00000010U
+#define P4_ESCR_T0_OS		0x00000008U
+#define P4_ESCR_T0_USR		0x00000004U
+#define P4_ESCR_T1_OS		0x00000002U
+#define P4_ESCR_T1_USR		0x00000001U
+
+#define P4_ESCR_EVENT(v)	((v) << P4_ESCR_EVENT_SHIFT)
+#define P4_ESCR_EMASK(v)	((v) << P4_ESCR_EVENTMASK_SHIFT)
+#define P4_ESCR_TAG(v)		((v) << P4_ESCR_TAG_SHIFT)
+
+/* Non HT mask */
+#define P4_ESCR_MASK			\
+	(P4_ESCR_EVENT_MASK	|	\
+	P4_ESCR_EVENTMASK_MASK	|	\
+	P4_ESCR_TAG_MASK	|	\
+	P4_ESCR_TAG_ENABLE	|	\
+	P4_ESCR_T0_OS		|	\
+	P4_ESCR_T0_USR)
+
+/* HT mask */
+#define P4_ESCR_MASK_HT			\
+	(P4_ESCR_MASK |	P4_ESCR_T1_OS | P4_ESCR_T1_USR)
+
+#define P4_CCCR_OVF			0x80000000U
+#define P4_CCCR_CASCADE			0x40000000U
+#define P4_CCCR_OVF_PMI_T0		0x04000000U
+#define P4_CCCR_OVF_PMI_T1		0x08000000U
+#define P4_CCCR_FORCE_OVF		0x02000000U
+#define P4_CCCR_EDGE			0x01000000U
+#define P4_CCCR_THRESHOLD_MASK		0x00f00000U
+#define P4_CCCR_THRESHOLD_SHIFT		20
+#define P4_CCCR_COMPLEMENT		0x00080000U
+#define P4_CCCR_COMPARE			0x00040000U
+#define P4_CCCR_ESCR_SELECT_MASK	0x0000e000U
+#define P4_CCCR_ESCR_SELECT_SHIFT	13
+#define P4_CCCR_ENABLE			0x00001000U
+#define P4_CCCR_THREAD_SINGLE		0x00010000U
+#define P4_CCCR_THREAD_BOTH		0x00020000U
+#define P4_CCCR_THREAD_ANY		0x00030000U
+#define P4_CCCR_RESERVED		0x00000fffU
+
+#define P4_CCCR_THRESHOLD(v)		((v) << P4_CCCR_THRESHOLD_SHIFT)
+#define P4_CCCR_ESEL(v)			((v) << P4_CCCR_ESCR_SELECT_SHIFT)
+
+/* Custom bits in reerved CCCR area */
+#define P4_CCCR_CACHE_OPS_MASK		0x0000003fU
+
+
+/* Non HT mask */
+#define P4_CCCR_MASK				\
+	(P4_CCCR_OVF			|	\
+	P4_CCCR_CASCADE			|	\
+	P4_CCCR_OVF_PMI_T0		|	\
+	P4_CCCR_FORCE_OVF		|	\
+	P4_CCCR_EDGE			|	\
+	P4_CCCR_THRESHOLD_MASK		|	\
+	P4_CCCR_COMPLEMENT		|	\
+	P4_CCCR_COMPARE			|	\
+	P4_CCCR_ESCR_SELECT_MASK	|	\
+	P4_CCCR_ENABLE)
+
+/* HT mask */
+#define P4_CCCR_MASK_HT	(P4_CCCR_MASK | P4_CCCR_THREAD_ANY)
+
+#define P4_GEN_ESCR_EMASK(class, name, bit)	\
+	class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT)
+#define P4_ESCR_EMASK_BIT(class, name)		class##__##name
+
+/*
+ * config field is 64bit width and consists of
+ * HT << 63 | ESCR << 32 | CCCR
+ * where HT is HyperThreading bit (since ESCR
+ * has it reserved we may use it for own purpose)
+ *
+ * note that this is NOT the addresses of respective
+ * ESCR and CCCR but rather an only packed value should
+ * be unpacked and written to a proper addresses
+ *
+ * the base idea is to pack as much info as
+ * possible
+ */
+#define p4_config_pack_escr(v)		(((u64)(v)) << 32)
+#define p4_config_pack_cccr(v)		(((u64)(v)) & 0xffffffffULL)
+#define p4_config_unpack_escr(v)	(((u64)(v)) >> 32)
+#define p4_config_unpack_cccr(v)	(((u64)(v)) & 0xffffffffULL)
+
+#define p4_config_unpack_emask(v)			\
+	({						\
+		u32 t = p4_config_unpack_escr((v));	\
+		t = t &  P4_ESCR_EVENTMASK_MASK;	\
+		t = t >> P4_ESCR_EVENTMASK_SHIFT;	\
+		t;					\
+	})
+
+#define p4_config_unpack_event(v)			\
+	({						\
+		u32 t = p4_config_unpack_escr((v));	\
+		t = t &  P4_ESCR_EVENT_MASK;		\
+		t = t >> P4_ESCR_EVENT_SHIFT;		\
+		t;					\
+	})
+
+#define p4_config_unpack_cache_event(v)	(((u64)(v)) & P4_CCCR_CACHE_OPS_MASK)
+
+#define P4_CONFIG_HT_SHIFT		63
+#define P4_CONFIG_HT			(1ULL << P4_CONFIG_HT_SHIFT)
+
+static inline bool p4_is_event_cascaded(u64 config)
+{
+	u32 cccr = p4_config_unpack_cccr(config);
+	return !!(cccr & P4_CCCR_CASCADE);
+}
+
+static inline int p4_ht_config_thread(u64 config)
+{
+	return !!(config & P4_CONFIG_HT);
+}
+
+static inline u64 p4_set_ht_bit(u64 config)
+{
+	return config | P4_CONFIG_HT;
+}
+
+static inline u64 p4_clear_ht_bit(u64 config)
+{
+	return config & ~P4_CONFIG_HT;
+}
+
+static inline int p4_ht_active(void)
+{
+#ifdef CONFIG_SMP
+	return smp_num_siblings > 1;
+#endif
+	return 0;
+}
+
+static inline int p4_ht_thread(int cpu)
+{
+#ifdef CONFIG_SMP
+	if (smp_num_siblings == 2)
+		return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+#endif
+	return 0;
+}
+
+static inline int p4_should_swap_ts(u64 config, int cpu)
+{
+	return p4_ht_config_thread(config) ^ p4_ht_thread(cpu);
+}
+
+static inline u32 p4_default_cccr_conf(int cpu)
+{
+	/*
+	 * Note that P4_CCCR_THREAD_ANY is "required" on
+	 * non-HT machines (on HT machines we count TS events
+	 * regardless the state of second logical processor
+	 */
+	u32 cccr = P4_CCCR_THREAD_ANY;
+
+	if (!p4_ht_thread(cpu))
+		cccr |= P4_CCCR_OVF_PMI_T0;
+	else
+		cccr |= P4_CCCR_OVF_PMI_T1;
+
+	return cccr;
+}
+
+static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_usr)
+{
+	u32 escr = 0;
+
+	if (!p4_ht_thread(cpu)) {
+		if (!exclude_os)
+			escr |= P4_ESCR_T0_OS;
+		if (!exclude_usr)
+			escr |= P4_ESCR_T0_USR;
+	} else {
+		if (!exclude_os)
+			escr |= P4_ESCR_T1_OS;
+		if (!exclude_usr)
+			escr |= P4_ESCR_T1_USR;
+	}
+
+	return escr;
+}
+
+enum P4_EVENTS {
+	P4_EVENT_TC_DELIVER_MODE,
+	P4_EVENT_BPU_FETCH_REQUEST,
+	P4_EVENT_ITLB_REFERENCE,
+	P4_EVENT_MEMORY_CANCEL,
+	P4_EVENT_MEMORY_COMPLETE,
+	P4_EVENT_LOAD_PORT_REPLAY,
+	P4_EVENT_STORE_PORT_REPLAY,
+	P4_EVENT_MOB_LOAD_REPLAY,
+	P4_EVENT_PAGE_WALK_TYPE,
+	P4_EVENT_BSQ_CACHE_REFERENCE,
+	P4_EVENT_IOQ_ALLOCATION,
+	P4_EVENT_IOQ_ACTIVE_ENTRIES,
+	P4_EVENT_FSB_DATA_ACTIVITY,
+	P4_EVENT_BSQ_ALLOCATION,
+	P4_EVENT_BSQ_ACTIVE_ENTRIES,
+	P4_EVENT_SSE_INPUT_ASSIST,
+	P4_EVENT_PACKED_SP_UOP,
+	P4_EVENT_PACKED_DP_UOP,
+	P4_EVENT_SCALAR_SP_UOP,
+	P4_EVENT_SCALAR_DP_UOP,
+	P4_EVENT_64BIT_MMX_UOP,
+	P4_EVENT_128BIT_MMX_UOP,
+	P4_EVENT_X87_FP_UOP,
+	P4_EVENT_TC_MISC,
+	P4_EVENT_GLOBAL_POWER_EVENTS,
+	P4_EVENT_TC_MS_XFER,
+	P4_EVENT_UOP_QUEUE_WRITES,
+	P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE,
+	P4_EVENT_RETIRED_BRANCH_TYPE,
+	P4_EVENT_RESOURCE_STALL,
+	P4_EVENT_WC_BUFFER,
+	P4_EVENT_B2B_CYCLES,
+	P4_EVENT_BNR,
+	P4_EVENT_SNOOP,
+	P4_EVENT_RESPONSE,
+	P4_EVENT_FRONT_END_EVENT,
+	P4_EVENT_EXECUTION_EVENT,
+	P4_EVENT_REPLAY_EVENT,
+	P4_EVENT_INSTR_RETIRED,
+	P4_EVENT_UOPS_RETIRED,
+	P4_EVENT_UOP_TYPE,
+	P4_EVENT_BRANCH_RETIRED,
+	P4_EVENT_MISPRED_BRANCH_RETIRED,
+	P4_EVENT_X87_ASSIST,
+	P4_EVENT_MACHINE_CLEAR,
+	P4_EVENT_INSTR_COMPLETED,
+};
+
+#define P4_OPCODE(event)		event##_OPCODE
+#define P4_OPCODE_ESEL(opcode)		((opcode & 0x00ff) >> 0)
+#define P4_OPCODE_EVNT(opcode)		((opcode & 0xff00) >> 8)
+#define P4_OPCODE_PACK(event, sel)	(((event) << 8) | sel)
+
+/*
+ * Comments below the event represent ESCR restriction
+ * for this event and counter index per ESCR
+ *
+ * MSR_P4_IQ_ESCR0 and MSR_P4_IQ_ESCR1 are available only on early
+ * processor builds (family 0FH, models 01H-02H). These MSRs
+ * are not available on later versions, so that we don't use
+ * them completely
+ *
+ * Also note that CCCR1 do not have P4_CCCR_ENABLE bit properly
+ * working so that we should not use this CCCR and respective
+ * counter as result
+ */
+enum P4_EVENT_OPCODES {
+	P4_OPCODE(P4_EVENT_TC_DELIVER_MODE)		= P4_OPCODE_PACK(0x01, 0x01),
+	/*
+	 * MSR_P4_TC_ESCR0:	4, 5
+	 * MSR_P4_TC_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST)		= P4_OPCODE_PACK(0x03, 0x00),
+	/*
+	 * MSR_P4_BPU_ESCR0:	0, 1
+	 * MSR_P4_BPU_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_ITLB_REFERENCE)		= P4_OPCODE_PACK(0x18, 0x03),
+	/*
+	 * MSR_P4_ITLB_ESCR0:	0, 1
+	 * MSR_P4_ITLB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_MEMORY_CANCEL)		= P4_OPCODE_PACK(0x02, 0x05),
+	/*
+	 * MSR_P4_DAC_ESCR0:	8, 9
+	 * MSR_P4_DAC_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_MEMORY_COMPLETE)		= P4_OPCODE_PACK(0x08, 0x02),
+	/*
+	 * MSR_P4_SAAT_ESCR0:	8, 9
+	 * MSR_P4_SAAT_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY)		= P4_OPCODE_PACK(0x04, 0x02),
+	/*
+	 * MSR_P4_SAAT_ESCR0:	8, 9
+	 * MSR_P4_SAAT_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY)		= P4_OPCODE_PACK(0x05, 0x02),
+	/*
+	 * MSR_P4_SAAT_ESCR0:	8, 9
+	 * MSR_P4_SAAT_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY)		= P4_OPCODE_PACK(0x03, 0x02),
+	/*
+	 * MSR_P4_MOB_ESCR0:	0, 1
+	 * MSR_P4_MOB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE)		= P4_OPCODE_PACK(0x01, 0x04),
+	/*
+	 * MSR_P4_PMH_ESCR0:	0, 1
+	 * MSR_P4_PMH_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE)		= P4_OPCODE_PACK(0x0c, 0x07),
+	/*
+	 * MSR_P4_BSU_ESCR0:	0, 1
+	 * MSR_P4_BSU_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_IOQ_ALLOCATION)		= P4_OPCODE_PACK(0x03, 0x06),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES)		= P4_OPCODE_PACK(0x1a, 0x06),
+	/*
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY)		= P4_OPCODE_PACK(0x17, 0x06),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_BSQ_ALLOCATION)		= P4_OPCODE_PACK(0x05, 0x07),
+	/*
+	 * MSR_P4_BSU_ESCR0:	0, 1
+	 */
+
+	P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES)		= P4_OPCODE_PACK(0x06, 0x07),
+	/*
+	 * NOTE: no ESCR name in docs, it's guessed
+	 * MSR_P4_BSU_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST)		= P4_OPCODE_PACK(0x34, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_PACKED_SP_UOP)		= P4_OPCODE_PACK(0x08, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_PACKED_DP_UOP)		= P4_OPCODE_PACK(0x0c, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_SCALAR_SP_UOP)		= P4_OPCODE_PACK(0x0a, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_SCALAR_DP_UOP)		= P4_OPCODE_PACK(0x0e, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_64BIT_MMX_UOP)		= P4_OPCODE_PACK(0x02, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_128BIT_MMX_UOP)		= P4_OPCODE_PACK(0x1a, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_X87_FP_UOP)			= P4_OPCODE_PACK(0x04, 0x01),
+	/*
+	 * MSR_P4_FIRM_ESCR0:	8, 9
+	 * MSR_P4_FIRM_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_TC_MISC)			= P4_OPCODE_PACK(0x06, 0x01),
+	/*
+	 * MSR_P4_TC_ESCR0:	4, 5
+	 * MSR_P4_TC_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS)		= P4_OPCODE_PACK(0x13, 0x06),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_TC_MS_XFER)			= P4_OPCODE_PACK(0x05, 0x00),
+	/*
+	 * MSR_P4_MS_ESCR0:	4, 5
+	 * MSR_P4_MS_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES)		= P4_OPCODE_PACK(0x09, 0x00),
+	/*
+	 * MSR_P4_MS_ESCR0:	4, 5
+	 * MSR_P4_MS_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE)	= P4_OPCODE_PACK(0x05, 0x02),
+	/*
+	 * MSR_P4_TBPU_ESCR0:	4, 5
+	 * MSR_P4_TBPU_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE)		= P4_OPCODE_PACK(0x04, 0x02),
+	/*
+	 * MSR_P4_TBPU_ESCR0:	4, 5
+	 * MSR_P4_TBPU_ESCR1:	6, 7
+	 */
+
+	P4_OPCODE(P4_EVENT_RESOURCE_STALL)		= P4_OPCODE_PACK(0x01, 0x01),
+	/*
+	 * MSR_P4_ALF_ESCR0:	12, 13, 16
+	 * MSR_P4_ALF_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_WC_BUFFER)			= P4_OPCODE_PACK(0x05, 0x05),
+	/*
+	 * MSR_P4_DAC_ESCR0:	8, 9
+	 * MSR_P4_DAC_ESCR1:	10, 11
+	 */
+
+	P4_OPCODE(P4_EVENT_B2B_CYCLES)			= P4_OPCODE_PACK(0x16, 0x03),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_BNR)				= P4_OPCODE_PACK(0x08, 0x03),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_SNOOP)			= P4_OPCODE_PACK(0x06, 0x03),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_RESPONSE)			= P4_OPCODE_PACK(0x04, 0x03),
+	/*
+	 * MSR_P4_FSB_ESCR0:	0, 1
+	 * MSR_P4_FSB_ESCR1:	2, 3
+	 */
+
+	P4_OPCODE(P4_EVENT_FRONT_END_EVENT)		= P4_OPCODE_PACK(0x08, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_EXECUTION_EVENT)		= P4_OPCODE_PACK(0x0c, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_REPLAY_EVENT)		= P4_OPCODE_PACK(0x09, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_INSTR_RETIRED)		= P4_OPCODE_PACK(0x02, 0x04),
+	/*
+	 * MSR_P4_CRU_ESCR0:	12, 13, 16
+	 * MSR_P4_CRU_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_UOPS_RETIRED)		= P4_OPCODE_PACK(0x01, 0x04),
+	/*
+	 * MSR_P4_CRU_ESCR0:	12, 13, 16
+	 * MSR_P4_CRU_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_UOP_TYPE)			= P4_OPCODE_PACK(0x02, 0x02),
+	/*
+	 * MSR_P4_RAT_ESCR0:	12, 13, 16
+	 * MSR_P4_RAT_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_BRANCH_RETIRED)		= P4_OPCODE_PACK(0x06, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED)	= P4_OPCODE_PACK(0x03, 0x04),
+	/*
+	 * MSR_P4_CRU_ESCR0:	12, 13, 16
+	 * MSR_P4_CRU_ESCR1:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_X87_ASSIST)			= P4_OPCODE_PACK(0x03, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_MACHINE_CLEAR)		= P4_OPCODE_PACK(0x02, 0x05),
+	/*
+	 * MSR_P4_CRU_ESCR2:	12, 13, 16
+	 * MSR_P4_CRU_ESCR3:	14, 15, 17
+	 */
+
+	P4_OPCODE(P4_EVENT_INSTR_COMPLETED)		= P4_OPCODE_PACK(0x07, 0x04),
+	/*
+	 * MSR_P4_CRU_ESCR0:	12, 13, 16
+	 * MSR_P4_CRU_ESCR1:	14, 15, 17
+	 */
+};
+
+/*
+ * a caller should use P4_ESCR_EMASK_NAME helper to
+ * pick the EventMask needed, for example
+ *
+ *	P4_ESCR_EMASK_NAME(P4_EVENT_TC_DELIVER_MODE, DD)
+ */
+enum P4_ESCR_EMASKS {
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DD, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DB, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DI, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BD, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BB, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BI, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, ID, 6),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BPU_FETCH_REQUEST, TCMISS, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, MISS, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT_UK, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, ST_RB_FULL, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, 64K_CONF, 3),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, LSC, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, SSC, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_LOAD_PORT_REPLAY, SPLIT_LD, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_STORE_PORT_REPLAY, SPLIT_ST, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STA, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STD, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, PARTIAL_DATA, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, UNALGN_ADDR, 5),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, DTMISS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, ITMISS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS, 10),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, DEFAULT, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_READ, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_WRITE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_UC, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WC, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WT, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WP, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WB, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OWN, 13),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OTHER, 14),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, PREFETCH, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, DEFAULT, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_READ, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_WRITE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_UC, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WC, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WT, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WP, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WB, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OWN, 13),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OTHER, 14),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, PREFETCH, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OTHER, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_DRV, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OWN, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OTHER, 5),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE0, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE1, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN0, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN1, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_IO_TYPE, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LOCK_TYPE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_CACHE_TYPE, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_SPLIT_TYPE, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_DEM_TYPE, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_ORD_TYPE, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE0, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE1, 12),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE2, 13),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE0, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE1, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN0, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN1, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_IO_TYPE, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LOCK_TYPE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_CACHE_TYPE, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_SPLIT_TYPE, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_DEM_TYPE, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_ORD_TYPE, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE0, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE1, 12),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE2, 13),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_SSE_INPUT_ASSIST, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_SP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_DP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_SP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_DP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_64BIT_MMX_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_128BIT_MMX_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_FP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_MISC, FLUSH, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_MS_XFER, CISC, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_BUILD, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_DELIVER, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_ROM, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CONDITIONAL, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CALL, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, RETURN, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, INDIRECT, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CALL, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_RESOURCE_STALL, SBFULL, 5),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_EVICTS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_FULL_EVICTS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, BOGUS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS0, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS1, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS2, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS3, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS0, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS1, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS2, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS3, 7),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, BOGUS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSTAG, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSNTAG, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSTAG, 3),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, BOGUS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGLOADS, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGSTORES, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNP, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNM, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTP, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTM, 3),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSU, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSO, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAO, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAU, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, PREA, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, CLEAR, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, MOCLEAR, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, SMCLEAR, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, BOGUS, 1),
+};
+
+/* P4 PEBS: stale for a while */
+#define P4_PEBS_METRIC_MASK	0x00001fffU
+#define P4_PEBS_UOB_TAG		0x01000000U
+#define P4_PEBS_ENABLE		0x02000000U
+
+/* Replay metrics for MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT */
+#define P4_PEBS__1stl_cache_load_miss_retired	0x3000001
+#define P4_PEBS__2ndl_cache_load_miss_retired	0x3000002
+#define P4_PEBS__dtlb_load_miss_retired		0x3000004
+#define P4_PEBS__dtlb_store_miss_retired	0x3000004
+#define P4_PEBS__dtlb_all_miss_retired		0x3000004
+#define P4_PEBS__tagged_mispred_branch		0x3018000
+#define P4_PEBS__mob_load_replay_retired	0x3000200
+#define P4_PEBS__split_load_retired		0x3000400
+#define P4_PEBS__split_store_retired		0x3000400
+
+#define P4_VERT__1stl_cache_load_miss_retired	0x0000001
+#define P4_VERT__2ndl_cache_load_miss_retired	0x0000001
+#define P4_VERT__dtlb_load_miss_retired		0x0000001
+#define P4_VERT__dtlb_store_miss_retired	0x0000002
+#define P4_VERT__dtlb_all_miss_retired		0x0000003
+#define P4_VERT__tagged_mispred_branch		0x0000010
+#define P4_VERT__mob_load_replay_retired	0x0000001
+#define P4_VERT__split_load_retired		0x0000001
+#define P4_VERT__split_store_retired		0x0000002
+
+enum P4_CACHE_EVENTS {
+	P4_CACHE__NONE,
+
+	P4_CACHE__1stl_cache_load_miss_retired,
+	P4_CACHE__2ndl_cache_load_miss_retired,
+	P4_CACHE__dtlb_load_miss_retired,
+	P4_CACHE__dtlb_store_miss_retired,
+	P4_CACHE__itlb_reference_hit,
+	P4_CACHE__itlb_reference_miss,
+
+	P4_CACHE__MAX
+};
+
+#endif /* PERF_EVENT_P4_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index b753ea59703..32428b410b5 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -21,7 +21,6 @@ struct mm_struct;
 #include <asm/msr.h>
 #include <asm/desc_defs.h>
 #include <asm/nops.h>
-#include <asm/ds.h>
 
 #include <linux/personality.h>
 #include <linux/cpumask.h>
@@ -29,6 +28,7 @@ struct mm_struct;
 #include <linux/threads.h>
 #include <linux/math64.h>
 #include <linux/init.h>
+#include <linux/err.h>
 
 #define HBP_NUM 4
 /*
@@ -473,10 +473,6 @@ struct thread_struct {
 	unsigned long		iopl;
 	/* Max allowed port in the bitmap, in bytes: */
 	unsigned		io_bitmap_max;
-/* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set.  */
-	unsigned long	debugctlmsr;
-	/* Debug Store context; see asm/ds.h */
-	struct ds_context	*ds_ctx;
 };
 
 static inline unsigned long native_get_debugreg(int regno)
@@ -803,7 +799,7 @@ extern void cpu_init(void);
 
 static inline unsigned long get_debugctlmsr(void)
 {
-    unsigned long debugctlmsr = 0;
+	unsigned long debugctlmsr = 0;
 
 #ifndef CONFIG_X86_DEBUGCTLMSR
 	if (boot_cpu_data.x86 < 6)
@@ -811,21 +807,6 @@ static inline unsigned long get_debugctlmsr(void)
 #endif
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 
-    return debugctlmsr;
-}
-
-static inline unsigned long get_debugctlmsr_on_cpu(int cpu)
-{
-	u64 debugctlmsr = 0;
-	u32 val1, val2;
-
-#ifndef CONFIG_X86_DEBUGCTLMSR
-	if (boot_cpu_data.x86 < 6)
-		return 0;
-#endif
-	rdmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, &val1, &val2);
-	debugctlmsr = val1 | ((u64)val2 << 32);
-
 	return debugctlmsr;
 }
 
@@ -838,18 +819,6 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr)
 	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 }
 
-static inline void update_debugctlmsr_on_cpu(int cpu,
-					     unsigned long debugctlmsr)
-{
-#ifndef CONFIG_X86_DEBUGCTLMSR
-	if (boot_cpu_data.x86 < 6)
-		return;
-#endif
-	wrmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR,
-		     (u32)((u64)debugctlmsr),
-		     (u32)((u64)debugctlmsr >> 32));
-}
-
 /*
  * from system description table in BIOS. Mostly for MCA use, but
  * others may find it useful:
diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h
index 86723035a51..52b098a6eeb 100644
--- a/arch/x86/include/asm/ptrace-abi.h
+++ b/arch/x86/include/asm/ptrace-abi.h
@@ -82,61 +82,6 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
-
-/* configuration/status structure used in PTRACE_BTS_CONFIG and
-   PTRACE_BTS_STATUS commands.
-*/
-struct ptrace_bts_config {
-	/* requested or actual size of BTS buffer in bytes */
-	__u32 size;
-	/* bitmask of below flags */
-	__u32 flags;
-	/* buffer overflow signal */
-	__u32 signal;
-	/* actual size of bts_struct in bytes */
-	__u32 bts_size;
-};
-#endif /* __ASSEMBLY__ */
-
-#define PTRACE_BTS_O_TRACE	0x1 /* branch trace */
-#define PTRACE_BTS_O_SCHED	0x2 /* scheduling events w/ jiffies */
-#define PTRACE_BTS_O_SIGNAL     0x4 /* send SIG<signal> on buffer overflow
-				       instead of wrapping around */
-#define PTRACE_BTS_O_ALLOC	0x8 /* (re)allocate buffer */
-
-#define PTRACE_BTS_CONFIG	40
-/* Configure branch trace recording.
-   ADDR points to a struct ptrace_bts_config.
-   DATA gives the size of that buffer.
-   A new buffer is allocated, if requested in the flags.
-   An overflow signal may only be requested for new buffers.
-   Returns the number of bytes read.
-*/
-#define PTRACE_BTS_STATUS	41
-/* Return the current configuration in a struct ptrace_bts_config
-   pointed to by ADDR; DATA gives the size of that buffer.
-   Returns the number of bytes written.
-*/
-#define PTRACE_BTS_SIZE		42
-/* Return the number of available BTS records for draining.
-   DATA and ADDR are ignored.
-*/
-#define PTRACE_BTS_GET		43
-/* Get a single BTS record.
-   DATA defines the index into the BTS array, where 0 is the newest
-   entry, and higher indices refer to older entries.
-   ADDR is pointing to struct bts_struct (see asm/ds.h).
-*/
-#define PTRACE_BTS_CLEAR	44
-/* Clear the BTS buffer.
-   DATA and ADDR are ignored.
-*/
-#define PTRACE_BTS_DRAIN	45
-/* Read all available BTS records and clear the buffer.
-   ADDR points to an array of struct bts_struct.
-   DATA gives the size of that buffer.
-   BTS records are read from oldest to newest.
-   Returns number of BTS records drained.
-*/
+#endif
 
 #endif /* _ASM_X86_PTRACE_ABI_H */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 69a686a7dff..78cd1ea9450 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -289,12 +289,6 @@ extern int do_get_thread_area(struct task_struct *p, int idx,
 extern int do_set_thread_area(struct task_struct *p, int idx,
 			      struct user_desc __user *info, int can_allocate);
 
-#ifdef CONFIG_X86_PTRACE_BTS
-extern void ptrace_bts_untrace(struct task_struct *tsk);
-
-#define arch_ptrace_untrace(tsk)	ptrace_bts_untrace(tsk)
-#endif /* CONFIG_X86_PTRACE_BTS */
-
 #endif /* __KERNEL__ */
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index e0d28901e96..d017ed5502e 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -92,8 +92,7 @@ struct thread_info {
 #define TIF_IO_BITMAP		22	/* uses I/O bitmap */
 #define TIF_FREEZE		23	/* is freezing for suspend */
 #define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
-#define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
-#define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
+#define TIF_BLOCKSTEP		25	/* set when we want DEBUGCTLMSR_BTF */
 #define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
 #define TIF_SYSCALL_TRACEPOINT	28	/* syscall tracepoint instrumentation */
 
@@ -115,8 +114,7 @@ struct thread_info {
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
 #define _TIF_FREEZE		(1 << TIF_FREEZE)
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
-#define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
-#define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
+#define _TIF_BLOCKSTEP		(1 << TIF_BLOCKSTEP)
 #define _TIF_LAZY_MMU_UPDATES	(1 << TIF_LAZY_MMU_UPDATES)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 
@@ -147,7 +145,7 @@ struct thread_info {
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
-	(_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC)
+	(_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP)
 
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)