blob: 829e89cfcee2deff8b937806b16dd573d736a895 [file] [log] [blame]
/*
* Per core/cpu state
*
* Used to coordinate shared registers between HT threads or
* among events on a single PMU.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/stddef.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/nmi.h>
#include <asm/cpufeature.h>
#include <asm/hardirq.h>
#include <asm/intel-family.h>
#include <asm/apic.h>
#include "../perf_event.h"
/*
* Intel PerfMon, used on Core and later.
*/
static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly =
{
[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,
[PERF_COUNT_HW_REF_CPU_CYCLES] = 0x0300, /* pseudo-encoding */
};
static struct event_constraint intel_core_event_constraints[] __read_mostly =
{
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[] __read_mostly =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 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[] __read_mostly =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 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 extra_reg intel_nehalem_extra_regs[] __read_mostly =
{
/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
EVENT_EXTRA_END
};
static struct event_constraint intel_westmere_event_constraints[] __read_mostly =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 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 */
INTEL_EVENT_CONSTRAINT(0xb3, 0x1), /* SNOOPQ_REQUEST_OUTSTANDING */
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_snb_event_constraints[] __read_mostly =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
INTEL_UEVENT_CONSTRAINT(0x06a3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */
INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
/*
* When HT is off these events can only run on the bottom 4 counters
* When HT is on, they are impacted by the HT bug and require EXCL access
*/
INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
INTEL_UEVENT_CONSTRAINT(0x0148, 0x4), /* L1D_PEND_MISS.PENDING */
INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMTPY */
INTEL_UEVENT_CONSTRAINT(0x019c, 0xf), /* IDQ_UOPS_NOT_DELIVERED.CORE */
INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_LDM_PENDING */
INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
INTEL_UEVENT_CONSTRAINT(0x06a3, 0xf), /* CYCLE_ACTIVITY.STALLS_LDM_PENDING */
INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
/*
* When HT is off these events can only run on the bottom 4 counters
* When HT is on, they are impacted by the HT bug and require EXCL access
*/
INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
EVENT_CONSTRAINT_END
};
static struct extra_reg intel_westmere_extra_regs[] __read_mostly =
{
/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
EVENT_EXTRA_END
};
static struct event_constraint intel_v1_event_constraints[] __read_mostly =
{
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_gen_event_constraints[] __read_mostly =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_slm_event_constraints[] __read_mostly =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_skl_event_constraints[] = {
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */
/*
* when HT is off, these can only run on the bottom 4 counters
*/
INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc6, 0xf), /* FRONTEND_RETIRED.* */
EVENT_CONSTRAINT_END
};
static struct extra_reg intel_knl_extra_regs[] __read_mostly = {
INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x799ffbb6e7ull, RSP_0),
INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x399ffbffe7ull, RSP_1),
EVENT_EXTRA_END
};
static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
EVENT_EXTRA_END
};
static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
EVENT_EXTRA_END
};
static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
/*
* Note the low 8 bits eventsel code is not a continuous field, containing
* some #GPing bits. These are masked out.
*/
INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
EVENT_EXTRA_END
};
EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
static struct attribute *nhm_events_attrs[] = {
EVENT_PTR(mem_ld_nhm),
NULL,
};
/*
* topdown events for Intel Core CPUs.
*
* The events are all in slots, which is a free slot in a 4 wide
* pipeline. Some events are already reported in slots, for cycle
* events we multiply by the pipeline width (4).
*
* With Hyper Threading on, topdown metrics are either summed or averaged
* between the threads of a core: (count_t0 + count_t1).
*
* For the average case the metric is always scaled to pipeline width,
* so we use factor 2 ((count_t0 + count_t1) / 2 * 4)
*/
EVENT_ATTR_STR_HT(topdown-total-slots, td_total_slots,
"event=0x3c,umask=0x0", /* cpu_clk_unhalted.thread */
"event=0x3c,umask=0x0,any=1"); /* cpu_clk_unhalted.thread_any */
EVENT_ATTR_STR_HT(topdown-total-slots.scale, td_total_slots_scale, "4", "2");
EVENT_ATTR_STR(topdown-slots-issued, td_slots_issued,
"event=0xe,umask=0x1"); /* uops_issued.any */
EVENT_ATTR_STR(topdown-slots-retired, td_slots_retired,
"event=0xc2,umask=0x2"); /* uops_retired.retire_slots */
EVENT_ATTR_STR(topdown-fetch-bubbles, td_fetch_bubbles,
"event=0x9c,umask=0x1"); /* idq_uops_not_delivered_core */
EVENT_ATTR_STR_HT(topdown-recovery-bubbles, td_recovery_bubbles,
"event=0xd,umask=0x3,cmask=1", /* int_misc.recovery_cycles */
"event=0xd,umask=0x3,cmask=1,any=1"); /* int_misc.recovery_cycles_any */
EVENT_ATTR_STR_HT(topdown-recovery-bubbles.scale, td_recovery_bubbles_scale,
"4", "2");
static struct attribute *snb_events_attrs[] = {
EVENT_PTR(mem_ld_snb),
EVENT_PTR(mem_st_snb),
EVENT_PTR(td_slots_issued),
EVENT_PTR(td_slots_retired),
EVENT_PTR(td_fetch_bubbles),
EVENT_PTR(td_total_slots),
EVENT_PTR(td_total_slots_scale),
EVENT_PTR(td_recovery_bubbles),
EVENT_PTR(td_recovery_bubbles_scale),
NULL,
};
static struct event_constraint intel_hsw_event_constraints[] = {
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */
INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
/* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
/* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
/* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf),
/*
* When HT is off these events can only run on the bottom 4 counters
* When HT is on, they are impacted by the HT bug and require EXCL access
*/
INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_bdw_event_constraints[] = {
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */
INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
/*
* when HT is off, these can only run on the bottom 4 counters
*/
INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */
EVENT_CONSTRAINT_END
};
static u64 intel_pmu_event_map(int hw_event)
{
return intel_perfmon_event_map[hw_event];
}
/*
* Notes on the events:
* - data reads do not include code reads (comparable to earlier tables)
* - data counts include speculative execution (except L1 write, dtlb, bpu)
* - remote node access includes remote memory, remote cache, remote mmio.
* - prefetches are not included in the counts.
* - icache miss does not include decoded icache
*/
#define SKL_DEMAND_DATA_RD BIT_ULL(0)
#define SKL_DEMAND_RFO BIT_ULL(1)
#define SKL_ANY_RESPONSE BIT_ULL(16)
#define SKL_SUPPLIER_NONE BIT_ULL(17)
#define SKL_L3_MISS_LOCAL_DRAM BIT_ULL(26)
#define SKL_L3_MISS_REMOTE_HOP0_DRAM BIT_ULL(27)
#define SKL_L3_MISS_REMOTE_HOP1_DRAM BIT_ULL(28)
#define SKL_L3_MISS_REMOTE_HOP2P_DRAM BIT_ULL(29)
#define SKL_L3_MISS (SKL_L3_MISS_LOCAL_DRAM| \
SKL_L3_MISS_REMOTE_HOP0_DRAM| \
SKL_L3_MISS_REMOTE_HOP1_DRAM| \
SKL_L3_MISS_REMOTE_HOP2P_DRAM)
#define SKL_SPL_HIT BIT_ULL(30)
#define SKL_SNOOP_NONE BIT_ULL(31)
#define SKL_SNOOP_NOT_NEEDED BIT_ULL(32)
#define SKL_SNOOP_MISS BIT_ULL(33)
#define SKL_SNOOP_HIT_NO_FWD BIT_ULL(34)
#define SKL_SNOOP_HIT_WITH_FWD BIT_ULL(35)
#define SKL_SNOOP_HITM BIT_ULL(36)
#define SKL_SNOOP_NON_DRAM BIT_ULL(37)
#define SKL_ANY_SNOOP (SKL_SPL_HIT|SKL_SNOOP_NONE| \
SKL_SNOOP_NOT_NEEDED|SKL_SNOOP_MISS| \
SKL_SNOOP_HIT_NO_FWD|SKL_SNOOP_HIT_WITH_FWD| \
SKL_SNOOP_HITM|SKL_SNOOP_NON_DRAM)
#define SKL_DEMAND_READ SKL_DEMAND_DATA_RD
#define SKL_SNOOP_DRAM (SKL_SNOOP_NONE| \
SKL_SNOOP_NOT_NEEDED|SKL_SNOOP_MISS| \
SKL_SNOOP_HIT_NO_FWD|SKL_SNOOP_HIT_WITH_FWD| \
SKL_SNOOP_HITM|SKL_SPL_HIT)
#define SKL_DEMAND_WRITE SKL_DEMAND_RFO
#define SKL_LLC_ACCESS SKL_ANY_RESPONSE
#define SKL_L3_MISS_REMOTE (SKL_L3_MISS_REMOTE_HOP0_DRAM| \
SKL_L3_MISS_REMOTE_HOP1_DRAM| \
SKL_L3_MISS_REMOTE_HOP2P_DRAM)
static __initconst const u64 skl_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) ] = 0x81d0, /* MEM_INST_RETIRED.ALL_LOADS */
[ C(RESULT_MISS) ] = 0x151, /* L1D.REPLACEMENT */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_INST_RETIRED.ALL_STORES */
[ C(RESULT_MISS) ] = 0x0,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
[ C(L1I ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x283, /* ICACHE_64B.MISS */
},
[ 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) ] = 0x1b7, /* OFFCORE_RESPONSE */
[ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */
[ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
[ C(DTLB) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_INST_RETIRED.ALL_LOADS */
[ C(RESULT_MISS) ] = 0xe08, /* DTLB_LOAD_MISSES.WALK_COMPLETED */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_INST_RETIRED.ALL_STORES */
[ C(RESULT_MISS) ] = 0xe49, /* DTLB_STORE_MISSES.WALK_COMPLETED */
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
[ C(ITLB) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x2085, /* ITLB_MISSES.STLB_HIT */
[ C(RESULT_MISS) ] = 0xe85, /* ITLB_MISSES.WALK_COMPLETED */
},
[ 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) ] = 0xc4, /* BR_INST_RETIRED.ALL_BRANCHES */
[ C(RESULT_MISS) ] = 0xc5, /* BR_MISP_RETIRED.ALL_BRANCHES */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = -1,
[ C(RESULT_MISS) ] = -1,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = -1,
[ C(RESULT_MISS) ] = -1,
},
},
[ C(NODE) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */
[ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */
[ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
};
static __initconst const u64 skl_hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] =
{
[ C(LL ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = SKL_DEMAND_READ|
SKL_LLC_ACCESS|SKL_ANY_SNOOP,
[ C(RESULT_MISS) ] = SKL_DEMAND_READ|
SKL_L3_MISS|SKL_ANY_SNOOP|
SKL_SUPPLIER_NONE,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = SKL_DEMAND_WRITE|
SKL_LLC_ACCESS|SKL_ANY_SNOOP,
[ C(RESULT_MISS) ] = SKL_DEMAND_WRITE|
SKL_L3_MISS|SKL_ANY_SNOOP|
SKL_SUPPLIER_NONE,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
[ C(NODE) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = SKL_DEMAND_READ|
SKL_L3_MISS_LOCAL_DRAM|SKL_SNOOP_DRAM,
[ C(RESULT_MISS) ] = SKL_DEMAND_READ|
SKL_L3_MISS_REMOTE|SKL_SNOOP_DRAM,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = SKL_DEMAND_WRITE|
SKL_L3_MISS_LOCAL_DRAM|SKL_SNOOP_DRAM,
[ C(RESULT_MISS) ] = SKL_DEMAND_WRITE|
SKL_L3_MISS_REMOTE|SKL_SNOOP_DRAM,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
};
#define SNB_DMND_DATA_RD (1ULL << 0)
#define SNB_DMND_RFO (1ULL << 1)
#define SNB_DMND_IFETCH (1ULL << 2)
#define SNB_DMND_WB (1ULL << 3)
#define SNB_PF_DATA_RD (1ULL << 4)
#define SNB_PF_RFO (1ULL << 5)
#define SNB_PF_IFETCH (1ULL << 6)
#define SNB_LLC_DATA_RD (1ULL << 7)
#define SNB_LLC_RFO (1ULL << 8)
#define SNB_LLC_IFETCH (1ULL << 9)
#define SNB_BUS_LOCKS (1ULL << 10)
#define SNB_STRM_ST (1ULL << 11)
#define SNB_OTHER (1ULL << 15)
#define SNB_RESP_ANY (1ULL << 16)
#define SNB_NO_SUPP (1ULL << 17)
#define SNB_LLC_HITM (1ULL << 18)
#define SNB_LLC_HITE (1ULL << 19)
#define SNB_LLC_HITS (1ULL << 20)
#define SNB_LLC_HITF (1ULL << 21)
#define SNB_LOCAL (1ULL << 22)
#define SNB_REMOTE (0xffULL << 23)
#define SNB_SNP_NONE (1ULL << 31)
#define SNB_SNP_NOT_NEEDED (1ULL << 32)
#define SNB_SNP_MISS (1ULL << 33)
#define SNB_NO_FWD (1ULL << 34)
#define SNB_SNP_FWD (1ULL << 35)
#define SNB_HITM (1ULL << 36)
#define SNB_NON_DRAM (1ULL << 37)
#define SNB_DMND_READ (SNB_DMND_DATA_RD|SNB_LLC_DATA_RD)
#define SNB_DMND_WRITE (SNB_DMND_RFO|SNB_LLC_RFO)
#define SNB_DMND_PREFETCH (SNB_PF_DATA_RD|SNB_PF_RFO)
#define SNB_SNP_ANY (SNB_SNP_NONE|SNB_SNP_NOT_NEEDED| \
SNB_SNP_MISS|SNB_NO_FWD|SNB_SNP_FWD| \
SNB_HITM)
#define SNB_DRAM_ANY (SNB_LOCAL|SNB_REMOTE|SNB_SNP_ANY)
#define SNB_DRAM_REMOTE (SNB_REMOTE|SNB_SNP_ANY)
#define SNB_L3_ACCESS SNB_RESP_ANY
#define SNB_L3_MISS (SNB_DRAM_ANY|SNB_NON_DRAM)
static __initconst const u64 snb_hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] =
{
[ C(LL ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = SNB_DMND_READ|SNB_L3_ACCESS,
[ C(RESULT_MISS) ] = SNB_DMND_READ|SNB_L3_MISS,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = SNB_DMND_WRITE|SNB_L3_ACCESS,
[ C(RESULT_MISS) ] = SNB_DMND_WRITE|SNB_L3_MISS,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = SNB_DMND_PREFETCH|SNB_L3_ACCESS,
[ C(RESULT_MISS) ] = SNB_DMND_PREFETCH|SNB_L3_MISS,
},
},
[ C(NODE) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = SNB_DMND_READ|SNB_DRAM_ANY,
[ C(RESULT_MISS) ] = SNB_DMND_READ|SNB_DRAM_REMOTE,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = SNB_DMND_WRITE|SNB_DRAM_ANY,
[ C(RESULT_MISS) ] = SNB_DMND_WRITE|SNB_DRAM_REMOTE,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = SNB_DMND_PREFETCH|SNB_DRAM_ANY,
[ C(RESULT_MISS) ] = SNB_DMND_PREFETCH|SNB_DRAM_REMOTE,
},
},
};
static __initconst const u64 snb_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) ] = 0xf1d0, /* MEM_UOP_RETIRED.LOADS */
[ C(RESULT_MISS) ] = 0x0151, /* L1D.REPLACEMENT */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0xf2d0, /* MEM_UOP_RETIRED.STORES */
[ C(RESULT_MISS) ] = 0x0851, /* L1D.ALL_M_REPLACEMENT */
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x024e, /* HW_PRE_REQ.DL1_MISS */
},
},
[ C(L1I ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0280, /* ICACHE.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) ] = {
/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_WRITE) ] = {
/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
},
[ C(DTLB) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOP_RETIRED.ALL_LOADS */
[ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.CAUSES_A_WALK */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOP_RETIRED.ALL_STORES */
[ C(RESULT_MISS) ] = 0x0149, /* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
[ C(ITLB) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x1085, /* ITLB_MISSES.STLB_HIT */
[ C(RESULT_MISS) ] = 0x0185, /* ITLB_MISSES.CAUSES_A_WALK */
},
[ 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) ] = 0x00c5, /* BR_MISP_RETIRED.ALL_BRANCHES */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = -1,
[ C(RESULT_MISS) ] = -1,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = -1,
[ C(RESULT_MISS) ] = -1,
},
},
[ C(NODE) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x01b7,
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x01b7,
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x01b7,
[ C(RESULT_MISS) ] = 0x01b7,
},
},
};
/*
* Notes on the events:
* - data reads do not include code reads (comparable to earlier tables)
* - data counts include speculative execution (except L1 write, dtlb, bpu)
* - remote node access includes remote memory, remote cache, remote mmio.
* - prefetches are not included in the counts because they are not
* reliably counted.
*/
#define HSW_DEMAND_DATA_RD BIT_ULL(0)
#define HSW_DEMAND_RFO BIT_ULL(1)
#define HSW_ANY_RESPONSE BIT_ULL(16)
#define HSW_SUPPLIER_NONE BIT_ULL(17)
#define HSW_L3_MISS_LOCAL_DRAM BIT_ULL(22)
#define HSW_L3_MISS_REMOTE_HOP0 BIT_ULL(27)
#define HSW_L3_MISS_REMOTE_HOP1 BIT_ULL(28)
#define HSW_L3_MISS_REMOTE_HOP2P BIT_ULL(29)
#define HSW_L3_MISS (HSW_L3_MISS_LOCAL_DRAM| \
HSW_L3_MISS_REMOTE_HOP0|HSW_L3_MISS_REMOTE_HOP1| \
HSW_L3_MISS_REMOTE_HOP2P)
#define HSW_SNOOP_NONE BIT_ULL(31)
#define HSW_SNOOP_NOT_NEEDED BIT_ULL(32)
#define HSW_SNOOP_MISS BIT_ULL(33)
#define HSW_SNOOP_HIT_NO_FWD BIT_ULL(34)
#define HSW_SNOOP_HIT_WITH_FWD BIT_ULL(35)
#define HSW_SNOOP_HITM BIT_ULL(36)
#define HSW_SNOOP_NON_DRAM BIT_ULL(37)
#define HSW_ANY_SNOOP (HSW_SNOOP_NONE| \
HSW_SNOOP_NOT_NEEDED|HSW_SNOOP_MISS| \
HSW_SNOOP_HIT_NO_FWD|HSW_SNOOP_HIT_WITH_FWD| \
HSW_SNOOP_HITM|HSW_SNOOP_NON_DRAM)
#define HSW_SNOOP_DRAM (HSW_ANY_SNOOP & ~HSW_SNOOP_NON_DRAM)
#define HSW_DEMAND_READ HSW_DEMAND_DATA_RD
#define HSW_DEMAND_WRITE HSW_DEMAND_RFO
#define HSW_L3_MISS_REMOTE (HSW_L3_MISS_REMOTE_HOP0|\
HSW_L3_MISS_REMOTE_HOP1|HSW_L3_MISS_REMOTE_HOP2P)
#define HSW_LLC_ACCESS HSW_ANY_RESPONSE
#define BDW_L3_MISS_LOCAL BIT(26)
#define BDW_L3_MISS (BDW_L3_MISS_LOCAL| \
HSW_L3_MISS_REMOTE_HOP0|HSW_L3_MISS_REMOTE_HOP1| \
HSW_L3_MISS_REMOTE_HOP2P)
static __initconst const u64 hsw_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) ] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */
[ C(RESULT_MISS) ] = 0x151, /* L1D.REPLACEMENT */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */
[ C(RESULT_MISS) ] = 0x0,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
[ C(L1I ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x280, /* ICACHE.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) ] = 0x1b7, /* OFFCORE_RESPONSE */
[ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */
[ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
[ C(DTLB) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */
[ C(RESULT_MISS) ] = 0x108, /* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */
[ C(RESULT_MISS) ] = 0x149, /* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
[ C(ITLB) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x6085, /* ITLB_MISSES.STLB_HIT */
[ C(RESULT_MISS) ] = 0x185, /* ITLB_MISSES.MISS_CAUSES_A_WALK */
},
[ 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) ] = 0xc4, /* BR_INST_RETIRED.ALL_BRANCHES */
[ C(RESULT_MISS) ] = 0xc5, /* BR_MISP_RETIRED.ALL_BRANCHES */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = -1,
[ C(RESULT_MISS) ] = -1,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = -1,
[ C(RESULT_MISS) ] = -1,
},
},
[ C(NODE) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */
[ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */
[ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
};
static __initconst const u64 hsw_hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] =
{
[ C(LL ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = HSW_DEMAND_READ|
HSW_LLC_ACCESS,
[ C(RESULT_MISS) ] = HSW_DEMAND_READ|
HSW_L3_MISS|HSW_ANY_SNOOP,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = HSW_DEMAND_WRITE|
HSW_LLC_ACCESS,
[ C(RESULT_MISS) ] = HSW_DEMAND_WRITE|
HSW_L3_MISS|HSW_ANY_SNOOP,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
[ C(NODE) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = HSW_DEMAND_READ|
HSW_L3_MISS_LOCAL_DRAM|
HSW_SNOOP_DRAM,
[ C(RESULT_MISS) ] = HSW_DEMAND_READ|
HSW_L3_MISS_REMOTE|
HSW_SNOOP_DRAM,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = HSW_DEMAND_WRITE|
HSW_L3_MISS_LOCAL_DRAM|
HSW_SNOOP_DRAM,
[ C(RESULT_MISS) ] = HSW_DEMAND_WRITE|
HSW_L3_MISS_REMOTE|
HSW_SNOOP_DRAM,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
};
static __initconst const 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) ] = {
/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
/*
* Use RFO, not WRITEBACK, because a write miss would typically occur
* on RFO.
*/
[ C(OP_WRITE) ] = {
/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
},
[ 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,
},
},
[ C(NODE) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x01b7,
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x01b7,
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x01b7,
[ C(RESULT_MISS) ] = 0x01b7,
},
},
};
/*
* Nehalem/Westmere MSR_OFFCORE_RESPONSE bits;
* See IA32 SDM Vol 3B 30.6.1.3
*/
#define NHM_DMND_DATA_RD (1 << 0)
#define NHM_DMND_RFO (1 << 1)
#define NHM_DMND_IFETCH (1 << 2)
#define NHM_DMND_WB (1 << 3)
#define NHM_PF_DATA_RD (1 << 4)
#define NHM_PF_DATA_RFO (1 << 5)
#define NHM_PF_IFETCH (1 << 6)
#define NHM_OFFCORE_OTHER (1 << 7)
#define NHM_UNCORE_HIT (1 << 8)
#define NHM_OTHER_CORE_HIT_SNP (1 << 9)
#define NHM_OTHER_CORE_HITM (1 << 10)
/* reserved */
#define NHM_REMOTE_CACHE_FWD (1 << 12)
#define NHM_REMOTE_DRAM (1 << 13)
#define NHM_LOCAL_DRAM (1 << 14)
#define NHM_NON_DRAM (1 << 15)
#define NHM_LOCAL (NHM_LOCAL_DRAM|NHM_REMOTE_CACHE_FWD)
#define NHM_REMOTE (NHM_REMOTE_DRAM)
#define NHM_DMND_READ (NHM_DMND_DATA_RD)
#define NHM_DMND_WRITE (NHM_DMND_RFO|NHM_DMND_WB)
#define NHM_DMND_PREFETCH (NHM_PF_DATA_RD|NHM_PF_DATA_RFO)
#define NHM_L3_HIT (NHM_UNCORE_HIT|NHM_OTHER_CORE_HIT_SNP|NHM_OTHER_CORE_HITM)
#define NHM_L3_MISS (NHM_NON_DRAM|NHM_LOCAL_DRAM|NHM_REMOTE_DRAM|NHM_REMOTE_CACHE_FWD)
#define NHM_L3_ACCESS (NHM_L3_HIT|NHM_L3_MISS)
static __initconst const u64 nehalem_hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] =
{
[ C(LL ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_L3_ACCESS,
[ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_L3_MISS,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_L3_ACCESS,
[ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_L3_MISS,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_L3_ACCESS,
[ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_L3_MISS,
},
},
[ C(NODE) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_LOCAL|NHM_REMOTE,
[ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_REMOTE,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_LOCAL|NHM_REMOTE,
[ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_REMOTE,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_LOCAL|NHM_REMOTE,
[ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_REMOTE,
},
},
};
static __initconst const 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) ] = 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) ] = {
/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
/*
* Use RFO, not WRITEBACK, because a write miss would typically occur
* on RFO.
*/
[ C(OP_WRITE) ] = {
/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
},
[ 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,
},
},
[ C(NODE) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x01b7,
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x01b7,
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x01b7,
[ C(RESULT_MISS) ] = 0x01b7,
},
},
};
static __initconst const 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 const 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,
},
},
};
EVENT_ATTR_STR(topdown-total-slots, td_total_slots_slm, "event=0x3c");
EVENT_ATTR_STR(topdown-total-slots.scale, td_total_slots_scale_slm, "2");
/* no_alloc_cycles.not_delivered */
EVENT_ATTR_STR(topdown-fetch-bubbles, td_fetch_bubbles_slm,
"event=0xca,umask=0x50");
EVENT_ATTR_STR(topdown-fetch-bubbles.scale, td_fetch_bubbles_scale_slm, "2");
/* uops_retired.all */
EVENT_ATTR_STR(topdown-slots-issued, td_slots_issued_slm,
"event=0xc2,umask=0x10");
/* uops_retired.all */
EVENT_ATTR_STR(topdown-slots-retired, td_slots_retired_slm,
"event=0xc2,umask=0x10");
static struct attribute *slm_events_attrs[] = {
EVENT_PTR(td_total_slots_slm),
EVENT_PTR(td_total_slots_scale_slm),
EVENT_PTR(td_fetch_bubbles_slm),
EVENT_PTR(td_fetch_bubbles_scale_slm),
EVENT_PTR(td_slots_issued_slm),
EVENT_PTR(td_slots_retired_slm),
NULL
};
static struct extra_reg intel_slm_extra_regs[] __read_mostly =
{
/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffffull, RSP_0),
INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x368005ffffull, RSP_1),
EVENT_EXTRA_END
};
#define SLM_DMND_READ SNB_DMND_DATA_RD
#define SLM_DMND_WRITE SNB_DMND_RFO
#define SLM_DMND_PREFETCH (SNB_PF_DATA_RD|SNB_PF_RFO)
#define SLM_SNP_ANY (SNB_SNP_NONE|SNB_SNP_MISS|SNB_NO_FWD|SNB_HITM)
#define SLM_LLC_ACCESS SNB_RESP_ANY
#define SLM_LLC_MISS (SLM_SNP_ANY|SNB_NON_DRAM)
static __initconst const u64 slm_hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] =
{
[ C(LL ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS,
[ C(RESULT_MISS) ] = 0,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS,
[ C(RESULT_MISS) ] = SLM_DMND_WRITE|SLM_LLC_MISS,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = SLM_DMND_PREFETCH|SLM_LLC_ACCESS,
[ C(RESULT_MISS) ] = SLM_DMND_PREFETCH|SLM_LLC_MISS,
},
},
};
static __initconst const u64 slm_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) ] = 0,
[ C(RESULT_MISS) ] = 0x0104, /* LD_DCU_MISS */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0,
[ C(RESULT_MISS) ] = 0,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0,
[ C(RESULT_MISS) ] = 0,
},
},
[ C(L1I ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x0380, /* ICACHE.ACCESSES */
[ C(RESULT_MISS) ] = 0x0280, /* ICACGE.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) ] = {
/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
[ C(RESULT_MISS) ] = 0,
},
[ C(OP_WRITE) ] = {
/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
},
[ C(DTLB) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0,
[ C(RESULT_MISS) ] = 0x0804, /* LD_DTLB_MISS */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0,
[ C(RESULT_MISS) ] = 0,
},
[ 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) ] = 0x40205, /* PAGE_WALKS.I_SIDE_WALKS */
},
[ 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,
},
},
};
EVENT_ATTR_STR(topdown-total-slots, td_total_slots_glm, "event=0x3c");
EVENT_ATTR_STR(topdown-total-slots.scale, td_total_slots_scale_glm, "3");
/* UOPS_NOT_DELIVERED.ANY */
EVENT_ATTR_STR(topdown-fetch-bubbles, td_fetch_bubbles_glm, "event=0x9c");
/* ISSUE_SLOTS_NOT_CONSUMED.RECOVERY */
EVENT_ATTR_STR(topdown-recovery-bubbles, td_recovery_bubbles_glm, "event=0xca,umask=0x02");
/* UOPS_RETIRED.ANY */
EVENT_ATTR_STR(topdown-slots-retired, td_slots_retired_glm, "event=0xc2");
/* UOPS_ISSUED.ANY */
EVENT_ATTR_STR(topdown-slots-issued, td_slots_issued_glm, "event=0x0e");
static struct attribute *glm_events_attrs[] = {
EVENT_PTR(td_total_slots_glm),
EVENT_PTR(td_total_slots_scale_glm),
EVENT_PTR(td_fetch_bubbles_glm),
EVENT_PTR(td_recovery_bubbles_glm),
EVENT_PTR(td_slots_issued_glm),
EVENT_PTR(td_slots_retired_glm),
NULL
};
static struct extra_reg intel_glm_extra_regs[] __read_mostly = {
/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x760005ffbfull, RSP_0),
INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x360005ffbfull, RSP_1),
EVENT_EXTRA_END
};
#define GLM_DEMAND_DATA_RD BIT_ULL(0)
#define GLM_DEMAND_RFO BIT_ULL(1)
#define GLM_ANY_RESPONSE BIT_ULL(16)
#define GLM_SNP_NONE_OR_MISS BIT_ULL(33)
#define GLM_DEMAND_READ GLM_DEMAND_DATA_RD
#define GLM_DEMAND_WRITE GLM_DEMAND_RFO
#define GLM_DEMAND_PREFETCH (SNB_PF_DATA_RD|SNB_PF_RFO)
#define GLM_LLC_ACCESS GLM_ANY_RESPONSE
#define GLM_SNP_ANY (GLM_SNP_NONE_OR_MISS|SNB_NO_FWD|SNB_HITM)
#define GLM_LLC_MISS (GLM_SNP_ANY|SNB_NON_DRAM)
static __initconst const u64 glm_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)] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */
[C(RESULT_MISS)] = 0x0,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */
[C(RESULT_MISS)] = 0x0,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = 0x0,
[C(RESULT_MISS)] = 0x0,
},
},
[C(L1I)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = 0x0380, /* ICACHE.ACCESSES */
[C(RESULT_MISS)] = 0x0280, /* ICACHE.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)] = 0x1b7, /* OFFCORE_RESPONSE */
[C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */
[C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */
[C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */
},
},
[C(DTLB)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */
[C(RESULT_MISS)] = 0x0,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */
[C(RESULT_MISS)] = 0x0,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = 0x0,
[C(RESULT_MISS)] = 0x0,
},
},
[C(ITLB)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = 0x00c0, /* INST_RETIRED.ANY_P */
[C(RESULT_MISS)] = 0x0481, /* ITLB.MISS */
},
[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)] = 0x00c5, /* BR_MISP_RETIRED.ALL_BRANCHES */
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = -1,
[C(RESULT_MISS)] = -1,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = -1,
[C(RESULT_MISS)] = -1,
},
},
};
static __initconst const u64 glm_hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
[C(LL)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = GLM_DEMAND_READ|
GLM_LLC_ACCESS,
[C(RESULT_MISS)] = GLM_DEMAND_READ|
GLM_LLC_MISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = GLM_DEMAND_WRITE|
GLM_LLC_ACCESS,
[C(RESULT_MISS)] = GLM_DEMAND_WRITE|
GLM_LLC_MISS,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = GLM_DEMAND_PREFETCH|
GLM_LLC_ACCESS,
[C(RESULT_MISS)] = GLM_DEMAND_PREFETCH|
GLM_LLC_MISS,
},
},
};
static __initconst const u64 glp_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)] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */
[C(RESULT_MISS)] = 0x0,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */
[C(RESULT_MISS)] = 0x0,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = 0x0,
[C(RESULT_MISS)] = 0x0,
},
},
[C(L1I)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = 0x0380, /* ICACHE.ACCESSES */
[C(RESULT_MISS)] = 0x0280, /* ICACHE.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)] = 0x1b7, /* OFFCORE_RESPONSE */
[C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */
[C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = 0x0,
[C(RESULT_MISS)] = 0x0,
},
},
[C(DTLB)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */
[C(RESULT_MISS)] = 0xe08, /* DTLB_LOAD_MISSES.WALK_COMPLETED */
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */
[C(RESULT_MISS)] = 0xe49, /* DTLB_STORE_MISSES.WALK_COMPLETED */
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = 0x0,
[C(RESULT_MISS)] = 0x0,
},
},
[C(ITLB)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = 0x00c0, /* INST_RETIRED.ANY_P */
[C(RESULT_MISS)] = 0x0481, /* ITLB.MISS */
},
[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)] = 0x00c5, /* BR_MISP_RETIRED.ALL_BRANCHES */
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = -1,
[C(RESULT_MISS)] = -1,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = -1,
[C(RESULT_MISS)] = -1,
},
},
};
static __initconst const u64 glp_hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
[C(LL)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = GLM_DEMAND_READ|
GLM_LLC_ACCESS,
[C(RESULT_MISS)] = GLM_DEMAND_READ|
GLM_LLC_MISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = GLM_DEMAND_WRITE|
GLM_LLC_ACCESS,
[C(RESULT_MISS)] = GLM_DEMAND_WRITE|
GLM_LLC_MISS,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = 0x0,
[C(RESULT_MISS)] = 0x0,
},
},
};
#define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */
#define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */
#define KNL_MCDRAM_LOCAL BIT_ULL(21)
#define KNL_MCDRAM_FAR BIT_ULL(22)
#define KNL_DDR_LOCAL BIT_ULL(23)
#define KNL_DDR_FAR BIT_ULL(24)
#define KNL_DRAM_ANY (KNL_MCDRAM_LOCAL | KNL_MCDRAM_FAR | \
KNL_DDR_LOCAL | KNL_DDR_FAR)
#define KNL_L2_READ SLM_DMND_READ
#define KNL_L2_WRITE SLM_DMND_WRITE
#define KNL_L2_PREFETCH SLM_DMND_PREFETCH
#define KNL_L2_ACCESS SLM_LLC_ACCESS
#define KNL_L2_MISS (KNL_OT_L2_HITE | KNL_OT_L2_HITF | \
KNL_DRAM_ANY | SNB_SNP_ANY | \
SNB_NON_DRAM)
static __initconst const u64 knl_hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
[C(LL)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = KNL_L2_READ | KNL_L2_ACCESS,
[C(RESULT_MISS)] = 0,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = KNL_L2_WRITE | KNL_L2_ACCESS,
[C(RESULT_MISS)] = KNL_L2_WRITE | KNL_L2_MISS,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = KNL_L2_PREFETCH | KNL_L2_ACCESS,
[C(RESULT_MISS)] = KNL_L2_PREFETCH | KNL_L2_MISS,
},
},
};
/*
* Used from PMIs where the LBRs are already disabled.
*
* This function could be called consecutively. It is required to remain in
* disabled state if called consecutively.
*
* During consecutive calls, the same disable value will be written to related
* registers, so the PMU state remains unchanged.
*
* intel_bts events don't coexist with intel PMU's BTS events because of
* x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them
* disabled around intel PMU's event batching etc, only inside the PMI handler.
*/
static void __intel_pmu_disable_all(void)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
intel_pmu_disable_bts();
intel_pmu_pebs_disable_all();
}
static void intel_pmu_disable_all(void)
{
__intel_pmu_disable_all();
intel_pmu_lbr_disable_all();
}
static void __intel_pmu_enable_all(int added, bool pmi)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
intel_pmu_pebs_enable_all();
intel_pmu_lbr_enable_all(pmi);
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL,
x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask);
if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
struct perf_event *event =
cpuc->events[INTEL_PMC_IDX_FIXED_BTS];
if (WARN_ON_ONCE(!event))
return;
intel_pmu_enable_bts(event->hw.config);
}
}
static void intel_pmu_enable_all(int added)
{
__intel_pmu_enable_all(added, false);
}
/*
* Workaround for:
* Intel Errata AAK100 (model 26)
* Intel Errata AAP53 (model 30)
* Intel Errata BD53 (model 44)
*
* The official story:
* These chips need to be 'reset' when adding counters by programming the
* magic three (non-counting) events 0x4300B5, 0x4300D2, and 0x4300B1 either
* in sequence on the same PMC or on different PMCs.
*
* In practise it appears some of these events do in fact count, and
* we need to programm all 4 events.
*/
static void intel_pmu_nhm_workaround(void)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
static const unsigned long nhm_magic[4] = {
0x4300B5,
0x4300D2,
0x4300B1,
0x4300B1
};
struct perf_event *event;
int i;
/*
* The Errata requires below steps:
* 1) Clear MSR_IA32_PEBS_ENABLE and MSR_CORE_PERF_GLOBAL_CTRL;
* 2) Configure 4 PERFEVTSELx with the magic events and clear
* the corresponding PMCx;
* 3) set bit0~bit3 of MSR_CORE_PERF_GLOBAL_CTRL;
* 4) Clear MSR_CORE_PERF_GLOBAL_CTRL;
* 5) Clear 4 pairs of ERFEVTSELx and PMCx;
*/
/*
* The real steps we choose are a little different from above.
* A) To reduce MSR operations, we don't run step 1) as they
* are already cleared before this function is called;
* B) Call x86_perf_event_update to save PMCx before configuring
* PERFEVTSELx with magic number;
* C) With step 5), we do clear only when the PERFEVTSELx is
* not used currently.
* D) Call x86_perf_event_set_period to restore PMCx;
*/
/* We always operate 4 pairs of PERF Counters */
for (i = 0; i < 4; i++) {
event = cpuc->events[i];
if (event)
x86_perf_event_update(event);
}
for (i = 0; i < 4; i++) {
wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + i, nhm_magic[i]);
wrmsrl(MSR_ARCH_PERFMON_PERFCTR0 + i, 0x0);
}
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0xf);
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
for (i = 0; i < 4; i++) {
event = cpuc->events[i];
if (event) {
x86_perf_event_set_period(event);
__x86_pmu_enable_event(&event->hw,
ARCH_PERFMON_EVENTSEL_ENABLE);
} else
wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + i, 0x0);
}
}
static void intel_pmu_nhm_enable_all(int added)
{
if (added)
intel_pmu_nhm_workaround();
intel_pmu_enable_all(added);
}
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 void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
{
int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
u64 ctrl_val, mask;
mask = 0xfULL << (idx * 4);
rdmsrl(hwc->config_base, ctrl_val);
ctrl_val &= ~mask;
wrmsrl(hwc->config_base, ctrl_val);
}
static inline bool event_is_checkpointed(struct perf_event *event)
{
return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
}
static void intel_pmu_disable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
intel_pmu_disable_bts();
intel_pmu_drain_bts_buffer();
return;
}
cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
cpuc->intel_cp_status &= ~(1ull << hwc->idx);
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_disable_fixed(hwc);
return;
}
x86_pmu_disable_event(event);
if (unlikely(event->attr.precise_ip))
intel_pmu_pebs_disable(event);
}
static void intel_pmu_del_event(struct perf_event *event)
{
if (needs_branch_stack(event))
intel_pmu_lbr_del(event);
if (event->attr.precise_ip)
intel_pmu_pebs_del(event);
}
static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
{
int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
u64 ctrl_val, bits, mask;
/*
* 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;
wrmsrl(hwc->config_base, ctrl_val);
}
static void intel_pmu_enable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
if (!__this_cpu_read(cpu_hw_events.enabled))
return;
intel_pmu_enable_bts(hwc->config);
return;
}
if (event->attr.exclude_host)
cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
if (event->attr.exclude_guest)
cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
if (unlikely(event_is_checkpointed(event)))
cpuc->intel_cp_status |= (1ull << hwc->idx);
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_enable_fixed(hwc);
return;
}
if (unlikely(event->attr.precise_ip))
intel_pmu_pebs_enable(event);
__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
}
static void intel_pmu_add_event(struct perf_event *event)
{
if (event->attr.precise_ip)
intel_pmu_pebs_add(event);
if (needs_branch_stack(event))
intel_pmu_lbr_add(event);
}
/*
* Save and restart an expired event. Called by NMI contexts,
* so it has to be careful about preempting normal event ops:
*/
int intel_pmu_save_and_restart(struct perf_event *event)
{
x86_perf_event_update(event);
/*
* For a checkpointed counter always reset back to 0. This
* avoids a situation where the counter overflows, aborts the
* transaction and is then set back to shortly before the
* overflow, and overflows and aborts again.
*/
if (unlikely(event_is_checkpointed(event))) {
/* No race with NMIs because the counter should not be armed */
wrmsrl(event->hw.event_base, 0);
local64_set(&event->hw.prev_count, 0);
}
return x86_perf_event_set_period(event);
}
static void intel_pmu_reset(void)
{
struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
unsigned long flags;
int idx;
if (!x86_pmu.num_counters)
return;
local_irq_save(flags);
pr_info("clearing PMU state on CPU#%d\n", smp_processor_id());
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
wrmsrl_safe(x86_pmu_config_addr(idx), 0ull);
wrmsrl_safe(x86_pmu_event_addr(idx), 0ull);
}
for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++)
wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
if (ds)
ds->bts_index = ds->bts_buffer_base;
/* Ack all overflows and disable fixed counters */
if (x86_pmu.version >= 2) {
intel_pmu_ack_status(intel_pmu_get_status());
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
}
/* Reset LBRs and LBR freezing */
if (x86_pmu.lbr_nr) {
update_debugctlmsr(get_debugctlmsr() &
~(DEBUGCTLMSR_FREEZE_LBRS_ON_PMI|DEBUGCTLMSR_LBR));
}
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 status;
int handled;
cpuc = this_cpu_ptr(&cpu_hw_events);
/*
* No known reason to not always do late ACK,
* but just in case do it opt-in.
*/
if (!x86_pmu.late_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
intel_bts_disable_local();
__intel_pmu_disable_all();
handled = intel_pmu_drain_bts_buffer();
handled += intel_bts_interrupt();
status = intel_pmu_get_status();
if (!status)
goto done;
loops = 0;
again:
intel_pmu_lbr_read();
intel_pmu_ack_status(status);
if (++loops > 100) {
static bool warned = false;
if (!warned) {
WARN(1, "perfevents: irq loop stuck!\n");
perf_event_print_debug();
warned = true;
}
intel_pmu_reset();
goto done;
}
inc_irq_stat(apic_perf_irqs);
/*
* Ignore a range of extra bits in status that do not indicate
* overflow by themselves.
*/
status &= ~(GLOBAL_STATUS_COND_CHG |
GLOBAL_STATUS_ASIF |
GLOBAL_STATUS_LBRS_FROZEN);
if (!status)
goto done;
/*
* In case multiple PEBS events are sampled at the same time,
* it is possible to have GLOBAL_STATUS bit 62 set indicating
* PEBS buffer overflow and also seeing at most 3 PEBS counters
* having their bits set in the status register. This is a sign
* that there was at least one PEBS record pending at the time
* of the PMU interrupt. PEBS counters must only be processed
* via the drain_pebs() calls and not via the regular sample
* processing loop coming after that the function, otherwise
* phony regular samples may be generated in the sampling buffer
* not marked with the EXACT tag. Another possibility is to have
* one PEBS event and at least one non-PEBS event whic hoverflows
* while PEBS has armed. In this case, bit 62 of GLOBAL_STATUS will
* not be set, yet the overflow status bit for the PEBS counter will
* be on Skylake.
*
* To avoid this problem, we systematically ignore the PEBS-enabled
* counters from the GLOBAL_STATUS mask and we always process PEBS
* events via drain_pebs().
*/
status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
/*
* PEBS overflow sets bit 62 in the global status register
*/
if (__test_and_clear_bit(62, (unsigned long *)&status)) {
handled++;
x86_pmu.drain_pebs(regs);
status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
}
/*
* Intel PT
*/
if (__test_and_clear_bit(55, (unsigned long *)&status)) {
handled++;
intel_pt_interrupt();
}
/*
* Checkpointed counters can lead to 'spurious' PMIs because the
* rollback caused by the PMI will have cleared the overflow status
* bit. Therefore always force probe these counters.
*/
status |= cpuc->intel_cp_status;
for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[bit];
handled++;
if (!test_bit(bit, cpuc->active_mask))
continue;
if (!intel_pmu_save_and_restart(event))
continue;
perf_sample_data_init(&data, 0, event->hw.last_period);
if (has_branch_stack(event))
data.br_stack = &cpuc->lbr_stack;
if (perf_event_overflow(event, &data, regs))
x86_pmu_stop(event, 0);
}
/*
* Repeat if there is more work to be done:
*/
status = intel_pmu_get_status();
if (status)
goto again;
done:
/* Only restore PMU state when it's active. See x86_pmu_disable(). */
if (cpuc->enabled)
__intel_pmu_enable_all(0, true);
intel_bts_enable_local();
/*
* Only unmask the NMI after the overflow counters
* have been reset. This avoids spurious NMIs on
* Haswell CPUs.
*/
if (x86_pmu.late_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
return handled;
}
static struct event_constraint *
intel_bts_constraints(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
unsigned int hw_event, bts_event;
if (event->attr.freq)
return NULL;
hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
if (unlikely(hw_event == bts_event && hwc->sample_period == 1))
return &bts_constraint;
return NULL;
}
static int intel_alt_er(int idx, u64 config)
{
int alt_idx = idx;
if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1))
return idx;
if (idx == EXTRA_REG_RSP_0)
alt_idx = EXTRA_REG_RSP_1;
if (idx == EXTRA_REG_RSP_1)
alt_idx = EXTRA_REG_RSP_0;
if (config & ~x86_pmu.extra_regs[alt_idx].valid_mask)
return idx;
return alt_idx;
}
static void intel_fixup_er(struct perf_event *event, int idx)
{
event->hw.extra_reg.idx = idx;
if (idx == EXTRA_REG_RSP_0) {
event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_0].event;
event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
} else if (idx == EXTRA_REG_RSP_1) {
event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_1].event;
event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
}
}
/*
* manage allocation of shared extra msr for certain events
*
* sharing can be:
* per-cpu: to be shared between the various events on a single PMU
* per-core: per-cpu + shared by HT threads
*/
static struct event_constraint *
__intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
struct perf_event *event,
struct hw_perf_event_extra *reg)
{
struct event_constraint *c = &emptyconstraint;
struct er_account *era;
unsigned long flags;
int idx = reg->idx;
/*
* reg->alloc can be set due to existing state, so for fake cpuc we
* need to ignore this, otherwise we might fail to allocate proper fake
* state for this extra reg constraint. Also see the comment below.
*/
if (reg->alloc && !cpuc->is_fake)
return NULL; /* call x86_get_event_constraint() */
again:
era = &cpuc->shared_regs->regs[idx];
/*
* we use spin_lock_irqsave() to avoid lockdep issues when
* passing a fake cpuc
*/
raw_spin_lock_irqsave(&era->lock, flags);
if (!atomic_read(&era->ref) || era->config == reg->config) {
/*
* If its a fake cpuc -- as per validate_{group,event}() we
* shouldn't touch event state and we can avoid doing so
* since both will only call get_event_constraints() once
* on each event, this avoids the need for reg->alloc.
*
* Not doing the ER fixup will only result in era->reg being
* wrong, but since we won't actually try and program hardware
* this isn't a problem either.
*/
if (!cpuc->is_fake) {
if (idx != reg->idx)
intel_fixup_er(event, idx);
/*
* x86_schedule_events() can call get_event_constraints()
* multiple times on events in the case of incremental
* scheduling(). reg->alloc ensures we only do the ER
* allocation once.
*/
reg->alloc = 1;
}
/* lock in msr value */
era->config = reg->config;
era->reg = reg->reg;
/* one more user */
atomic_inc(&era->ref);
/*
* need to call x86_get_event_constraint()
* to check if associated event has constraints
*/
c = NULL;
} else {
idx = intel_alt_er(idx, reg->config);
if (idx != reg->idx) {
raw_spin_unlock_irqrestore(&era->lock, flags);
goto again;
}
}
raw_spin_unlock_irqrestore(&era->lock, flags);
return c;
}
static void
__intel_shared_reg_put_constraints(struct cpu_hw_events *cpuc,
struct hw_perf_event_extra *reg)
{
struct er_account *era;
/*
* Only put constraint if extra reg was actually allocated. Also takes
* care of event which do not use an extra shared reg.
*
* Also, if this is a fake cpuc we shouldn't touch any event state
* (reg->alloc) and we don't care about leaving inconsistent cpuc state
* either since it'll be thrown out.
*/
if (!