#ifdef CONFIG_CPU_SUP_INTEL

/*
 * Intel PerfMon, used on Core and later.
 */
static const u64 intel_perfmon_event_map[] =
{
  [PERF_COUNT_HW_CPU_CYCLES]		= 0x003c,
  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x4f2e,
  [PERF_COUNT_HW_CACHE_MISSES]		= 0x412e,
  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
  [PERF_COUNT_HW_BUS_CYCLES]		= 0x013c,
};

static struct event_constraint intel_core_event_constraints[] =
{
	INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
	INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
	INTEL_EVENT_CONSTRAINT(0x13, 0x2), /* DIV */
	INTEL_EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */
	INTEL_EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */
	INTEL_EVENT_CONSTRAINT(0xc1, 0x1), /* FP_COMP_INSTR_RET */
	EVENT_CONSTRAINT_END
};

static struct event_constraint intel_core2_event_constraints[] =
{
	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
	/*
	 * Core2 has Fixed Counter 2 listed as CPU_CLK_UNHALTED.REF and event
	 * 0x013c as CPU_CLK_UNHALTED.BUS and specifies there is a fixed
	 * ratio between these counters.
	 */
	/* FIXED_EVENT_CONSTRAINT(0x013c, 2),  CPU_CLK_UNHALTED.REF */
	INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */
	INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
	INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
	INTEL_EVENT_CONSTRAINT(0x13, 0x2), /* DIV */
	INTEL_EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */
	INTEL_EVENT_CONSTRAINT(0x18, 0x1), /* IDLE_DURING_DIV */
	INTEL_EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */
	INTEL_EVENT_CONSTRAINT(0xa1, 0x1), /* RS_UOPS_DISPATCH_CYCLES */
	INTEL_EVENT_CONSTRAINT(0xc9, 0x1), /* ITLB_MISS_RETIRED (T30-9) */
	INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED */
	EVENT_CONSTRAINT_END
};

static struct event_constraint intel_nehalem_event_constraints[] =
{
	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
	/* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
	INTEL_EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */
	INTEL_EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */
	INTEL_EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */
	INTEL_EVENT_CONSTRAINT(0x43, 0x3), /* L1D_ALL_REF */
	INTEL_EVENT_CONSTRAINT(0x48, 0x3), /* L1D_PEND_MISS */
	INTEL_EVENT_CONSTRAINT(0x4e, 0x3), /* L1D_PREFETCH */
	INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
	INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */
	EVENT_CONSTRAINT_END
};

static struct event_constraint intel_westmere_event_constraints[] =
{
	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
	/* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
	INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
	INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */
	INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */
	EVENT_CONSTRAINT_END
};

static struct event_constraint intel_gen_event_constraints[] =
{
	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
	/* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
	EVENT_CONSTRAINT_END
};

static u64 intel_pmu_event_map(int hw_event)
{
	return intel_perfmon_event_map[hw_event];
}

static __initconst u64 westmere_hw_cache_event_ids
				[PERF_COUNT_HW_CACHE_MAX]
				[PERF_COUNT_HW_CACHE_OP_MAX]
				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
{
 [ C(L1D) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS       */
		[ C(RESULT_MISS)   ] = 0x0151, /* L1D.REPL                     */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES      */
		[ C(RESULT_MISS)   ] = 0x0251, /* L1D.M_REPL                   */
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS        */
		[ C(RESULT_MISS)   ] = 0x024e, /* L1D_PREFETCH.MISS            */
	},
 },
 [ C(L1I ) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS                    */
		[ C(RESULT_MISS)   ] = 0x0280, /* L1I.MISSES                   */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0x0,
		[ C(RESULT_MISS)   ] = 0x0,
	},
 },
 [ C(LL  ) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS               */
		[ C(RESULT_MISS)   ] = 0x0224, /* L2_RQSTS.LD_MISS             */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS                */
		[ C(RESULT_MISS)   ] = 0x0824, /* L2_RQSTS.RFO_MISS            */
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference                */
		[ C(RESULT_MISS)   ] = 0x412e, /* LLC Misses                   */
	},
 },
 [ C(DTLB) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS       */
		[ C(RESULT_MISS)   ] = 0x0108, /* DTLB_LOAD_MISSES.ANY         */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES      */
		[ C(RESULT_MISS)   ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS  */
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0x0,
		[ C(RESULT_MISS)   ] = 0x0,
	},
 },
 [ C(ITLB) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P           */
		[ C(RESULT_MISS)   ] = 0x0185, /* ITLB_MISSES.ANY              */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
 },
 [ C(BPU ) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
		[ C(RESULT_MISS)   ] = 0x03e8, /* BPU_CLEARS.ANY               */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
 },
};

static __initconst u64 nehalem_hw_cache_event_ids
				[PERF_COUNT_HW_CACHE_MAX]
				[PERF_COUNT_HW_CACHE_OP_MAX]
				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
{
 [ C(L1D) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI            */
		[ C(RESULT_MISS)   ] = 0x0140, /* L1D_CACHE_LD.I_STATE         */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI            */
		[ C(RESULT_MISS)   ] = 0x0141, /* L1D_CACHE_ST.I_STATE         */
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS        */
		[ C(RESULT_MISS)   ] = 0x024e, /* L1D_PREFETCH.MISS            */
	},
 },
 [ C(L1I ) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS                    */
		[ C(RESULT_MISS)   ] = 0x0280, /* L1I.MISSES                   */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0x0,
		[ C(RESULT_MISS)   ] = 0x0,
	},
 },
 [ C(LL  ) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS               */
		[ C(RESULT_MISS)   ] = 0x0224, /* L2_RQSTS.LD_MISS             */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS                */
		[ C(RESULT_MISS)   ] = 0x0824, /* L2_RQSTS.RFO_MISS            */
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference                */
		[ C(RESULT_MISS)   ] = 0x412e, /* LLC Misses                   */
	},
 },
 [ C(DTLB) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI   (alias)  */
		[ C(RESULT_MISS)   ] = 0x0108, /* DTLB_LOAD_MISSES.ANY         */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI   (alias)  */
		[ C(RESULT_MISS)   ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS  */
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0x0,
		[ C(RESULT_MISS)   ] = 0x0,
	},
 },
 [ C(ITLB) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P           */
		[ C(RESULT_MISS)   ] = 0x20c8, /* ITLB_MISS_RETIRED            */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
 },
 [ C(BPU ) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
		[ C(RESULT_MISS)   ] = 0x03e8, /* BPU_CLEARS.ANY               */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
 },
};

static __initconst u64 core2_hw_cache_event_ids
				[PERF_COUNT_HW_CACHE_MAX]
				[PERF_COUNT_HW_CACHE_OP_MAX]
				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
{
 [ C(L1D) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI          */
		[ C(RESULT_MISS)   ] = 0x0140, /* L1D_CACHE_LD.I_STATE       */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI          */
		[ C(RESULT_MISS)   ] = 0x0141, /* L1D_CACHE_ST.I_STATE       */
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0x104e, /* L1D_PREFETCH.REQUESTS      */
		[ C(RESULT_MISS)   ] = 0,
	},
 },
 [ C(L1I ) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x0080, /* L1I.READS                  */
		[ C(RESULT_MISS)   ] = 0x0081, /* L1I.MISSES                 */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0,
		[ C(RESULT_MISS)   ] = 0,
	},
 },
 [ C(LL  ) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI                 */
		[ C(RESULT_MISS)   ] = 0x4129, /* L2_LD.ISTATE               */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI                 */
		[ C(RESULT_MISS)   ] = 0x412A, /* L2_ST.ISTATE               */
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0,
		[ C(RESULT_MISS)   ] = 0,
	},
 },
 [ C(DTLB) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI  (alias) */
		[ C(RESULT_MISS)   ] = 0x0208, /* DTLB_MISSES.MISS_LD        */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI  (alias) */
		[ C(RESULT_MISS)   ] = 0x0808, /* DTLB_MISSES.MISS_ST        */
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0,
		[ C(RESULT_MISS)   ] = 0,
	},
 },
 [ C(ITLB) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P         */
		[ C(RESULT_MISS)   ] = 0x1282, /* ITLBMISSES                 */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
 },
 [ C(BPU ) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY        */
		[ C(RESULT_MISS)   ] = 0x00c5, /* BP_INST_RETIRED.MISPRED    */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
 },
};

static __initconst u64 atom_hw_cache_event_ids
				[PERF_COUNT_HW_CACHE_MAX]
				[PERF_COUNT_HW_CACHE_OP_MAX]
				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
{
 [ C(L1D) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE.LD               */
		[ C(RESULT_MISS)   ] = 0,
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE.ST               */
		[ C(RESULT_MISS)   ] = 0,
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0x0,
		[ C(RESULT_MISS)   ] = 0,
	},
 },
 [ C(L1I ) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS                  */
		[ C(RESULT_MISS)   ] = 0x0280, /* L1I.MISSES                 */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0,
		[ C(RESULT_MISS)   ] = 0,
	},
 },
 [ C(LL  ) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI                 */
		[ C(RESULT_MISS)   ] = 0x4129, /* L2_LD.ISTATE               */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI                 */
		[ C(RESULT_MISS)   ] = 0x412A, /* L2_ST.ISTATE               */
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0,
		[ C(RESULT_MISS)   ] = 0,
	},
 },
 [ C(DTLB) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE_LD.MESI  (alias) */
		[ C(RESULT_MISS)   ] = 0x0508, /* DTLB_MISSES.MISS_LD        */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE_ST.MESI  (alias) */
		[ C(RESULT_MISS)   ] = 0x0608, /* DTLB_MISSES.MISS_ST        */
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = 0,
		[ C(RESULT_MISS)   ] = 0,
	},
 },
 [ C(ITLB) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P         */
		[ C(RESULT_MISS)   ] = 0x0282, /* ITLB.MISSES                */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
 },
 [ C(BPU ) ] = {
	[ C(OP_READ) ] = {
		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY        */
		[ C(RESULT_MISS)   ] = 0x00c5, /* BP_INST_RETIRED.MISPRED    */
	},
	[ C(OP_WRITE) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
	[ C(OP_PREFETCH) ] = {
		[ C(RESULT_ACCESS) ] = -1,
		[ C(RESULT_MISS)   ] = -1,
	},
 },
};

static u64 intel_pmu_raw_event(u64 hw_event)
{
#define CORE_EVNTSEL_EVENT_MASK		0x000000FFULL
#define CORE_EVNTSEL_UNIT_MASK		0x0000FF00ULL
#define CORE_EVNTSEL_EDGE_MASK		0x00040000ULL
#define CORE_EVNTSEL_INV_MASK		0x00800000ULL
#define CORE_EVNTSEL_REG_MASK		0xFF000000ULL

#define CORE_EVNTSEL_MASK		\
	(INTEL_ARCH_EVTSEL_MASK |	\
	 INTEL_ARCH_UNIT_MASK   |	\
	 INTEL_ARCH_EDGE_MASK   |	\
	 INTEL_ARCH_INV_MASK    |	\
	 INTEL_ARCH_CNT_MASK)

	return hw_event & CORE_EVNTSEL_MASK;
}

static void intel_pmu_enable_bts(u64 config)
{
	unsigned long debugctlmsr;

	debugctlmsr = get_debugctlmsr();

	debugctlmsr |= X86_DEBUGCTL_TR;
	debugctlmsr |= X86_DEBUGCTL_BTS;
	debugctlmsr |= X86_DEBUGCTL_BTINT;

	if (!(config & ARCH_PERFMON_EVENTSEL_OS))
		debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS;

	if (!(config & ARCH_PERFMON_EVENTSEL_USR))
		debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR;

	update_debugctlmsr(debugctlmsr);
}

static void intel_pmu_disable_bts(void)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	unsigned long debugctlmsr;

	if (!cpuc->ds)
		return;

	debugctlmsr = get_debugctlmsr();

	debugctlmsr &=
		~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT |
		  X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR);

	update_debugctlmsr(debugctlmsr);
}

static void intel_pmu_disable_all(void)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);

	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);

	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask))
		intel_pmu_disable_bts();
}

static void intel_pmu_enable_all(void)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);

	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);

	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
		struct perf_event *event =
			cpuc->events[X86_PMC_IDX_FIXED_BTS];

		if (WARN_ON_ONCE(!event))
			return;

		intel_pmu_enable_bts(event->hw.config);
	}
}

static inline u64 intel_pmu_get_status(void)
{
	u64 status;

	rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);

	return status;
}

static inline void intel_pmu_ack_status(u64 ack)
{
	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
}

static inline void
intel_pmu_disable_fixed(struct hw_perf_event *hwc, int __idx)
{
	int idx = __idx - X86_PMC_IDX_FIXED;
	u64 ctrl_val, mask;

	mask = 0xfULL << (idx * 4);

	rdmsrl(hwc->config_base, ctrl_val);
	ctrl_val &= ~mask;
	(void)checking_wrmsrl(hwc->config_base, ctrl_val);
}

static void intel_pmu_drain_bts_buffer(void)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	struct debug_store *ds = cpuc->ds;
	struct bts_record {
		u64	from;
		u64	to;
		u64	flags;
	};
	struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
	struct bts_record *at, *top;
	struct perf_output_handle handle;
	struct perf_event_header header;
	struct perf_sample_data data;
	struct pt_regs regs;

	if (!event)
		return;

	if (!ds)
		return;

	at  = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
	top = (struct bts_record *)(unsigned long)ds->bts_index;

	if (top <= at)
		return;

	ds->bts_index = ds->bts_buffer_base;

	perf_sample_data_init(&data, 0);

	data.period	= event->hw.last_period;
	regs.ip		= 0;

	/*
	 * Prepare a generic sample, i.e. fill in the invariant fields.
	 * We will overwrite the from and to address before we output
	 * the sample.
	 */
	perf_prepare_sample(&header, &data, event, &regs);

	if (perf_output_begin(&handle, event,
			      header.size * (top - at), 1, 1))
		return;

	for (; at < top; at++) {
		data.ip		= at->from;
		data.addr	= at->to;

		perf_output_sample(&handle, &header, &data, event);
	}

	perf_output_end(&handle);

	/* There's new data available. */
	event->hw.interrupts++;
	event->pending_kill = POLL_IN;
}

static inline void
intel_pmu_disable_event(struct hw_perf_event *hwc, int idx)
{
	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
		intel_pmu_disable_bts();
		intel_pmu_drain_bts_buffer();
		return;
	}

	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
		intel_pmu_disable_fixed(hwc, idx);
		return;
	}

	x86_pmu_disable_event(hwc, idx);
}

static inline void
intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
{
	int idx = __idx - X86_PMC_IDX_FIXED;
	u64 ctrl_val, bits, mask;
	int err;

	/*
	 * Enable IRQ generation (0x8),
	 * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
	 * if requested:
	 */
	bits = 0x8ULL;
	if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
		bits |= 0x2;
	if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
		bits |= 0x1;

	/*
	 * ANY bit is supported in v3 and up
	 */
	if (x86_pmu.version > 2 && hwc->config & ARCH_PERFMON_EVENTSEL_ANY)
		bits |= 0x4;

	bits <<= (idx * 4);
	mask = 0xfULL << (idx * 4);

	rdmsrl(hwc->config_base, ctrl_val);
	ctrl_val &= ~mask;
	ctrl_val |= bits;
	err = checking_wrmsrl(hwc->config_base, ctrl_val);
}

static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
{
	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
		if (!__get_cpu_var(cpu_hw_events).enabled)
			return;

		intel_pmu_enable_bts(hwc->config);
		return;
	}

	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
		intel_pmu_enable_fixed(hwc, idx);
		return;
	}

	__x86_pmu_enable_event(hwc, idx);
}

/*
 * Save and restart an expired event. Called by NMI contexts,
 * so it has to be careful about preempting normal event ops:
 */
static int intel_pmu_save_and_restart(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	int idx = hwc->idx;
	int ret;

	x86_perf_event_update(event, hwc, idx);
	ret = x86_perf_event_set_period(event, hwc, idx);

	return ret;
}

static void intel_pmu_reset(void)
{
	struct debug_store *ds = __get_cpu_var(cpu_hw_events).ds;
	unsigned long flags;
	int idx;

	if (!x86_pmu.num_events)
		return;

	local_irq_save(flags);

	printk("clearing PMU state on CPU#%d\n", smp_processor_id());

	for (idx = 0; idx < x86_pmu.num_events; idx++) {
		checking_wrmsrl(x86_pmu.eventsel + idx, 0ull);
		checking_wrmsrl(x86_pmu.perfctr  + idx, 0ull);
	}
	for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) {
		checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
	}
	if (ds)
		ds->bts_index = ds->bts_buffer_base;

	local_irq_restore(flags);
}

/*
 * This handler is triggered by the local APIC, so the APIC IRQ handling
 * rules apply:
 */
static int intel_pmu_handle_irq(struct pt_regs *regs)
{
	struct perf_sample_data data;
	struct cpu_hw_events *cpuc;
	int bit, loops;
	u64 ack, status;

	perf_sample_data_init(&data, 0);

	cpuc = &__get_cpu_var(cpu_hw_events);

	perf_disable();
	intel_pmu_drain_bts_buffer();
	status = intel_pmu_get_status();
	if (!status) {
		perf_enable();
		return 0;
	}

	loops = 0;
again:
	if (++loops > 100) {
		WARN_ONCE(1, "perfevents: irq loop stuck!\n");
		perf_event_print_debug();
		intel_pmu_reset();
		perf_enable();
		return 1;
	}

	inc_irq_stat(apic_perf_irqs);
	ack = status;
	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
		struct perf_event *event = cpuc->events[bit];

		clear_bit(bit, (unsigned long *) &status);
		if (!test_bit(bit, cpuc->active_mask))
			continue;

		if (!intel_pmu_save_and_restart(event))
			continue;

		data.period = event->hw.last_period;

		if (perf_event_overflow(event, 1, &data, regs))
			intel_pmu_disable_event(&event->hw, bit);
	}

	intel_pmu_ack_status(ack);

	/*
	 * Repeat if there is more work to be done:
	 */
	status = intel_pmu_get_status();
	if (status)
		goto again;

	perf_enable();

	return 1;
}

static struct event_constraint bts_constraint =
	EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0);

static struct event_constraint *
intel_special_constraints(struct perf_event *event)
{
	unsigned int hw_event;

	hw_event = event->hw.config & INTEL_ARCH_EVENT_MASK;

	if (unlikely((hw_event ==
		      x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) &&
		     (event->hw.sample_period == 1))) {

		return &bts_constraint;
	}
	return NULL;
}

static struct event_constraint *
intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
{
	struct event_constraint *c;

	c = intel_special_constraints(event);
	if (c)
		return c;

	return x86_get_event_constraints(cpuc, event);
}

static __initconst struct x86_pmu core_pmu = {
	.name			= "core",
	.handle_irq		= x86_pmu_handle_irq,
	.disable_all		= x86_pmu_disable_all,
	.enable_all		= x86_pmu_enable_all,
	.enable			= x86_pmu_enable_event,
	.disable		= x86_pmu_disable_event,
	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
	.event_map		= intel_pmu_event_map,
	.raw_event		= intel_pmu_raw_event,
	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
	.apic			= 1,
	/*
	 * Intel PMCs cannot be accessed sanely above 32 bit width,
	 * so we install an artificial 1<<31 period regardless of
	 * the generic event period:
	 */
	.max_period		= (1ULL << 31) - 1,
	.get_event_constraints	= intel_get_event_constraints,
	.event_constraints	= intel_core_event_constraints,
};

static __initconst struct x86_pmu intel_pmu = {
	.name			= "Intel",
	.handle_irq		= intel_pmu_handle_irq,
	.disable_all		= intel_pmu_disable_all,
	.enable_all		= intel_pmu_enable_all,
	.enable			= intel_pmu_enable_event,
	.disable		= intel_pmu_disable_event,
	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
	.event_map		= intel_pmu_event_map,
	.raw_event		= intel_pmu_raw_event,
	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
	.apic			= 1,
	/*
	 * Intel PMCs cannot be accessed sanely above 32 bit width,
	 * so we install an artificial 1<<31 period regardless of
	 * the generic event period:
	 */
	.max_period		= (1ULL << 31) - 1,
	.enable_bts		= intel_pmu_enable_bts,
	.disable_bts		= intel_pmu_disable_bts,
	.get_event_constraints	= intel_get_event_constraints,

	.cpu_starting		= init_debug_store_on_cpu,
	.cpu_dying		= fini_debug_store_on_cpu,
};

static __init int intel_pmu_init(void)
{
	union cpuid10_edx edx;
	union cpuid10_eax eax;
	unsigned int unused;
	unsigned int ebx;
	int version;

	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
		/* check for P6 processor family */
	   if (boot_cpu_data.x86 == 6) {
		return p6_pmu_init();
	   } else {
		return -ENODEV;
	   }
	}

	/*
	 * Check whether the Architectural PerfMon supports
	 * Branch Misses Retired hw_event or not.
	 */
	cpuid(10, &eax.full, &ebx, &unused, &edx.full);
	if (eax.split.mask_length <= ARCH_PERFMON_BRANCH_MISSES_RETIRED)
		return -ENODEV;

	version = eax.split.version_id;
	if (version < 2)
		x86_pmu = core_pmu;
	else
		x86_pmu = intel_pmu;

	x86_pmu.version			= version;
	x86_pmu.num_events		= eax.split.num_events;
	x86_pmu.event_bits		= eax.split.bit_width;
	x86_pmu.event_mask		= (1ULL << eax.split.bit_width) - 1;

	/*
	 * Quirk: v2 perfmon does not report fixed-purpose events, so
	 * assume at least 3 events:
	 */
	if (version > 1)
		x86_pmu.num_events_fixed = max((int)edx.split.num_events_fixed, 3);

	/*
	 * Install the hw-cache-events table:
	 */
	switch (boot_cpu_data.x86_model) {
	case 14: /* 65 nm core solo/duo, "Yonah" */
		pr_cont("Core events, ");
		break;

	case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
	case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
	case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
	case 29: /* six-core 45 nm xeon "Dunnington" */
		memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
		       sizeof(hw_cache_event_ids));

		x86_pmu.event_constraints = intel_core2_event_constraints;
		pr_cont("Core2 events, ");
		break;

	case 26: /* 45 nm nehalem, "Bloomfield" */
	case 30: /* 45 nm nehalem, "Lynnfield" */
		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
		       sizeof(hw_cache_event_ids));

		x86_pmu.event_constraints = intel_nehalem_event_constraints;
		pr_cont("Nehalem/Corei7 events, ");
		break;
	case 28: /* Atom */
		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
		       sizeof(hw_cache_event_ids));

		x86_pmu.event_constraints = intel_gen_event_constraints;
		pr_cont("Atom events, ");
		break;

	case 37: /* 32 nm nehalem, "Clarkdale" */
	case 44: /* 32 nm nehalem, "Gulftown" */
		memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
		       sizeof(hw_cache_event_ids));

		x86_pmu.event_constraints = intel_westmere_event_constraints;
		pr_cont("Westmere events, ");
		break;

	default:
		/*
		 * default constraints for v2 and up
		 */
		x86_pmu.event_constraints = intel_gen_event_constraints;
		pr_cont("generic architected perfmon, ");
	}
	return 0;
}

#else /* CONFIG_CPU_SUP_INTEL */

static int intel_pmu_init(void)
{
	return 0;
}

#endif /* CONFIG_CPU_SUP_INTEL */