static struct extra_reg intel_nehalem_extra_regs[] __read_mostly =
{
INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
+ INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
EVENT_EXTRA_END
};
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 */
EVENT_CONSTRAINT_END
};
{
INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1),
+ INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
EVENT_EXTRA_END
};
};
static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
- INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
- INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
+ INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
+ INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
+ INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
++ INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+ EVENT_EXTRA_END
+ };
+
+ static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
+ INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
+ INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
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");
+
+struct attribute *nhm_events_attrs[] = {
+ EVENT_PTR(mem_ld_nhm),
+ NULL,
+};
+
+struct attribute *snb_events_attrs[] = {
+ EVENT_PTR(mem_ld_snb),
+ EVENT_PTR(mem_st_snb),
+ NULL,
+};
+
static u64 intel_pmu_event_map(int hw_event)
{
return intel_perfmon_event_map[hw_event];
if (x86_pmu.event_constraints) {
for_each_event_constraint(c, x86_pmu.event_constraints) {
- if ((event->hw.config & c->cmask) == c->code)
+ if ((event->hw.config & c->cmask) == c->code) {
+ /* hw.flags zeroed at initialization */
+ event->hw.flags |= c->flags;
return c;
+ }
}
}
static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
struct perf_event *event)
{
+ event->hw.flags = 0;
intel_put_shared_regs_event_constraints(cpuc, event);
}
PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
+PMU_FORMAT_ATTR(ldlat, "config1:0-15");
+
static struct attribute *intel_arch3_formats_attr[] = {
&format_attr_event.attr,
&format_attr_umask.attr,
&format_attr_cmask.attr,
&format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */
+ &format_attr_ldlat.attr, /* PEBS load latency */
NULL,
};
x86_pmu.enable_all = intel_pmu_nhm_enable_all;
x86_pmu.extra_regs = intel_nehalem_extra_regs;
+ x86_pmu.cpu_events = nhm_events_attrs;
+
/* UOPS_ISSUED.STALLED_CYCLES */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
x86_pmu.extra_regs = intel_westmere_extra_regs;
x86_pmu.er_flags |= ERF_HAS_RSP_1;
+ x86_pmu.cpu_events = nhm_events_attrs;
+
/* UOPS_ISSUED.STALLED_CYCLES */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
x86_pmu.event_constraints = intel_snb_event_constraints;
x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
- x86_pmu.extra_regs = intel_snb_extra_regs;
+ if (boot_cpu_data.x86_model == 45)
+ x86_pmu.extra_regs = intel_snbep_extra_regs;
+ else
+ x86_pmu.extra_regs = intel_snb_extra_regs;
/* all extra regs are per-cpu when HT is on */
x86_pmu.er_flags |= ERF_HAS_RSP_1;
x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+ x86_pmu.cpu_events = snb_events_attrs;
+
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
x86_pmu.event_constraints = intel_ivb_event_constraints;
x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
- x86_pmu.extra_regs = intel_snb_extra_regs;
+ if (boot_cpu_data.x86_model == 62)
+ x86_pmu.extra_regs = intel_snbep_extra_regs;
+ else
+ x86_pmu.extra_regs = intel_snb_extra_regs;
/* all extra regs are per-cpu when HT is on */
x86_pmu.er_flags |= ERF_HAS_RSP_1;
x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+ x86_pmu.cpu_events = snb_events_attrs;
+
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
*/
+union intel_x86_pebs_dse {
+ u64 val;
+ struct {
+ unsigned int ld_dse:4;
+ unsigned int ld_stlb_miss:1;
+ unsigned int ld_locked:1;
+ unsigned int ld_reserved:26;
+ };
+ struct {
+ unsigned int st_l1d_hit:1;
+ unsigned int st_reserved1:3;
+ unsigned int st_stlb_miss:1;
+ unsigned int st_locked:1;
+ unsigned int st_reserved2:26;
+ };
+};
+
+
+/*
+ * Map PEBS Load Latency Data Source encodings to generic
+ * memory data source information
+ */
+#define P(a, b) PERF_MEM_S(a, b)
+#define OP_LH (P(OP, LOAD) | P(LVL, HIT))
+#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
+
+static const u64 pebs_data_source[] = {
+ P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
+ OP_LH | P(LVL, L1) | P(SNOOP, NONE), /* 0x01: L1 local */
+ OP_LH | P(LVL, LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */
+ OP_LH | P(LVL, L2) | P(SNOOP, NONE), /* 0x03: L2 hit */
+ OP_LH | P(LVL, L3) | P(SNOOP, NONE), /* 0x04: L3 hit */
+ OP_LH | P(LVL, L3) | P(SNOOP, MISS), /* 0x05: L3 hit, snoop miss */
+ OP_LH | P(LVL, L3) | P(SNOOP, HIT), /* 0x06: L3 hit, snoop hit */
+ OP_LH | P(LVL, L3) | P(SNOOP, HITM), /* 0x07: L3 hit, snoop hitm */
+ OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HIT), /* 0x08: L3 miss snoop hit */
+ OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/
+ OP_LH | P(LVL, LOC_RAM) | P(SNOOP, HIT), /* 0x0a: L3 miss, shared */
+ OP_LH | P(LVL, REM_RAM1) | P(SNOOP, HIT), /* 0x0b: L3 miss, shared */
+ OP_LH | P(LVL, LOC_RAM) | SNOOP_NONE_MISS,/* 0x0c: L3 miss, excl */
+ OP_LH | P(LVL, REM_RAM1) | SNOOP_NONE_MISS,/* 0x0d: L3 miss, excl */
+ OP_LH | P(LVL, IO) | P(SNOOP, NONE), /* 0x0e: I/O */
+ OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */
+};
+
+static u64 precise_store_data(u64 status)
+{
+ union intel_x86_pebs_dse dse;
+ u64 val = P(OP, STORE) | P(SNOOP, NA) | P(LVL, L1) | P(TLB, L2);
+
+ dse.val = status;
+
+ /*
+ * bit 4: TLB access
+ * 1 = stored missed 2nd level TLB
+ *
+ * so it either hit the walker or the OS
+ * otherwise hit 2nd level TLB
+ */
+ if (dse.st_stlb_miss)
+ val |= P(TLB, MISS);
+ else
+ val |= P(TLB, HIT);
+
+ /*
+ * bit 0: hit L1 data cache
+ * if not set, then all we know is that
+ * it missed L1D
+ */
+ if (dse.st_l1d_hit)
+ val |= P(LVL, HIT);
+ else
+ val |= P(LVL, MISS);
+
+ /*
+ * bit 5: Locked prefix
+ */
+ if (dse.st_locked)
+ val |= P(LOCK, LOCKED);
+
+ return val;
+}
+
+static u64 load_latency_data(u64 status)
+{
+ union intel_x86_pebs_dse dse;
+ u64 val;
+ int model = boot_cpu_data.x86_model;
+ int fam = boot_cpu_data.x86;
+
+ dse.val = status;
+
+ /*
+ * use the mapping table for bit 0-3
+ */
+ val = pebs_data_source[dse.ld_dse];
+
+ /*
+ * Nehalem models do not support TLB, Lock infos
+ */
+ if (fam == 0x6 && (model == 26 || model == 30
+ || model == 31 || model == 46)) {
+ val |= P(TLB, NA) | P(LOCK, NA);
+ return val;
+ }
+ /*
+ * bit 4: TLB access
+ * 0 = did not miss 2nd level TLB
+ * 1 = missed 2nd level TLB
+ */
+ if (dse.ld_stlb_miss)
+ val |= P(TLB, MISS) | P(TLB, L2);
+ else
+ val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+
+ /*
+ * bit 5: locked prefix
+ */
+ if (dse.ld_locked)
+ val |= P(LOCK, LOCKED);
+
+ return val;
+}
+
struct pebs_record_core {
u64 flags, ip;
u64 ax, bx, cx, dx;
if (top <= at)
return 0;
+ memset(®s, 0, sizeof(regs));
+
ds->bts_index = ds->bts_buffer_base;
perf_sample_data_init(&data, 0, event->hw.last_period);
- regs.ip = 0;
/*
* Prepare a generic sample, i.e. fill in the invariant fields.
};
struct event_constraint intel_nehalem_pebs_event_constraints[] = {
- INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */
+ INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */
};
struct event_constraint intel_westmere_pebs_event_constraints[] = {
- INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */
+ INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */
INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */
+ INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
+ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */
INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */
+ INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
+ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */
INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
if (x86_pmu.pebs_constraints) {
for_each_event_constraint(c, x86_pmu.pebs_constraints) {
- if ((event->hw.config & c->cmask) == c->code)
+ if ((event->hw.config & c->cmask) == c->code) {
+ event->hw.flags |= c->flags;
return c;
+ }
}
}
hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
cpuc->pebs_enabled |= 1ULL << hwc->idx;
+
+ if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+ cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
+ else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
+ cpuc->pebs_enabled |= 1ULL << 63;
}
void intel_pmu_pebs_disable(struct perf_event *event)
struct pt_regs *iregs, void *__pebs)
{
/*
- * We cast to pebs_record_core since that is a subset of
- * both formats and we don't use the other fields in this
- * routine.
+ * We cast to pebs_record_nhm to get the load latency data
+ * if extra_reg MSR_PEBS_LD_LAT_THRESHOLD used
*/
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct pebs_record_core *pebs = __pebs;
+ struct pebs_record_nhm *pebs = __pebs;
struct perf_sample_data data;
struct pt_regs regs;
+ u64 sample_type;
+ int fll, fst;
if (!intel_pmu_save_and_restart(event))
return;
+ fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
+ fst = event->hw.flags & PERF_X86_EVENT_PEBS_ST;
+
perf_sample_data_init(&data, 0, event->hw.last_period);
+ data.period = event->hw.last_period;
+ sample_type = event->attr.sample_type;
+
+ /*
+ * if PEBS-LL or PreciseStore
+ */
+ if (fll || fst) {
+ if (sample_type & PERF_SAMPLE_ADDR)
+ data.addr = pebs->dla;
+
+ /*
+ * Use latency for weight (only avail with PEBS-LL)
+ */
+ if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
+ data.weight = pebs->lat;
+
+ /*
+ * data.data_src encodes the data source
+ */
+ if (sample_type & PERF_SAMPLE_DATA_SRC) {
+ if (fll)
+ data.data_src.val = load_latency_data(pebs->dse);
+ else
+ data.data_src.val = precise_store_data(pebs->dse);
+ }
+ }
+
/*
* We use the interrupt regs as a base because the PEBS record
* does not contain a full regs set, specifically it seems to
#include <linux/ftrace_event.h>
#include <linux/hw_breakpoint.h>
#include <linux/mm_types.h>
+#include <linux/cgroup.h>
#include "internal.h"
#ifdef CONFIG_CGROUP_PERF
+/*
+ * perf_cgroup_info keeps track of time_enabled for a cgroup.
+ * This is a per-cpu dynamically allocated data structure.
+ */
+struct perf_cgroup_info {
+ u64 time;
+ u64 timestamp;
+};
+
+struct perf_cgroup {
+ struct cgroup_subsys_state css;
+ struct perf_cgroup_info __percpu *info;
+};
+
/*
* Must ensure cgroup is pinned (css_get) before calling
* this function. In other words, we cannot call this function
if (sample_type & PERF_SAMPLE_PERIOD)
size += sizeof(data->period);
+ if (sample_type & PERF_SAMPLE_WEIGHT)
+ size += sizeof(data->weight);
+
if (sample_type & PERF_SAMPLE_READ)
size += event->read_size;
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ size += sizeof(data->data_src.val);
+
event->header_size = size;
}
perf_output_sample_ustack(handle,
data->stack_user_size,
data->regs_user.regs);
+
+ if (sample_type & PERF_SAMPLE_WEIGHT)
+ perf_output_put(handle, data->weight);
+
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ perf_output_put(handle, data->data_src.val);
}
void perf_prepare_sample(struct perf_event_header *header,
} else {
if (arch_vma_name(mmap_event->vma)) {
name = strncpy(tmp, arch_vma_name(mmap_event->vma),
- sizeof(tmp));
+ sizeof(tmp) - 1);
+ tmp[sizeof(tmp) - 1] = '\0';
goto got_name;
}
mmap_event->file_name = name;
mmap_event->file_size = size;
+ if (!(vma->vm_flags & VM_EXEC))
+ mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_DATA;
+
mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
rcu_read_lock();
static int perf_swevent_init(struct perf_event *event)
{
- int event_id = event->attr.config;
+ u64 event_id = event->attr.config;
if (event->attr.type != PERF_TYPE_SOFTWARE)
return -ENOENT;
if (pmu->pmu_cpu_context)
goto got_cpu_context;
+ ret = -ENOMEM;
pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context);
if (!pmu->pmu_cpu_context)
goto free_dev;