summaryrefslogtreecommitdiff
path: root/arch/x86/events
diff options
context:
space:
mode:
authorKan Liang <kan.liang@linux.intel.com>2019-04-02 12:45:02 -0700
committerIngo Molnar <mingo@kernel.org>2019-04-16 12:25:47 +0200
commitc22497f5838c237e3094a4dfb99d1c5de6353239 (patch)
tree146038d425f37c7b0f32233aaf1e423f424a7e0b /arch/x86/events
parent477f00f9617009a9a3a9271885231573b728ca4f (diff)
perf/x86/intel: Support adaptive PEBS v4
Adaptive PEBS is a new way to report PEBS sampling information. Instead of a fixed size record for all PEBS events it allows to configure the PEBS record to only include the information needed. Events can then opt in to use such an extended record, or stay with a basic record which only contains the IP. The major new feature is to support LBRs in PEBS record. Besides normal LBR, this allows (much faster) large PEBS, while still supporting callstacks through callstack LBR. So essentially a lot of profiling can now be done without frequent interrupts, dropping the overhead significantly. The main requirement still is to use a period, and not use frequency mode, because frequency mode requires reevaluating the frequency on each overflow. The floating point state (XMM) is also supported, which allows efficient profiling of FP function arguments. Introduce specific drain function to handle variable length records. Use a new callback to parse the new record format, and also handle the STATUS field now being at a different offset. Add code to set up the configuration register. Since there is only a single register, all events either get the full super set of all events, or only the basic record. Originally-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: acme@kernel.org Cc: jolsa@kernel.org Link: https://lkml.kernel.org/r/20190402194509.2832-6-kan.liang@linux.intel.com [ Renamed GPRS => GP. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/events')
-rw-r--r--arch/x86/events/intel/core.c7
-rw-r--r--arch/x86/events/intel/ds.c380
-rw-r--r--arch/x86/events/intel/lbr.c22
-rw-r--r--arch/x86/events/perf_event.h11
4 files changed, 394 insertions, 26 deletions
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 8265b5026a19..bdc366d709aa 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2145,6 +2145,11 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
bits <<= (idx * 4);
mask = 0xfULL << (idx * 4);
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip) {
+ bits |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+ mask |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+ }
+
rdmsrl(hwc->config_base, ctrl_val);
ctrl_val &= ~mask;
ctrl_val |= bits;
@@ -3510,6 +3515,8 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
{
+ cpuc->pebs_record_size = x86_pmu.pebs_record_size;
+
if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
cpuc->shared_regs = allocate_shared_regs(cpu);
if (!cpuc->shared_regs)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 9ac73860645d..6436452d6342 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -906,17 +906,87 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
if (cpuc->n_pebs == cpuc->n_large_pebs) {
threshold = ds->pebs_absolute_maximum -
- reserved * x86_pmu.pebs_record_size;
+ reserved * cpuc->pebs_record_size;
} else {
- threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+ threshold = ds->pebs_buffer_base + cpuc->pebs_record_size;
}
ds->pebs_interrupt_threshold = threshold;
}
+static void adaptive_pebs_record_size_update(void)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ u64 pebs_data_cfg = cpuc->pebs_data_cfg;
+ int sz = sizeof(struct pebs_basic);
+
+ if (pebs_data_cfg & PEBS_DATACFG_MEMINFO)
+ sz += sizeof(struct pebs_meminfo);
+ if (pebs_data_cfg & PEBS_DATACFG_GP)
+ sz += sizeof(struct pebs_gprs);
+ if (pebs_data_cfg & PEBS_DATACFG_XMMS)
+ sz += sizeof(struct pebs_xmm);
+ if (pebs_data_cfg & PEBS_DATACFG_LBRS)
+ sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry);
+
+ cpuc->pebs_record_size = sz;
+}
+
+#define PERF_PEBS_MEMINFO_TYPE (PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC | \
+ PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \
+ PERF_SAMPLE_TRANSACTION)
+
+static u64 pebs_update_adaptive_cfg(struct perf_event *event)
+{
+ struct perf_event_attr *attr = &event->attr;
+ u64 sample_type = attr->sample_type;
+ u64 pebs_data_cfg = 0;
+ bool gprs, tsx_weight;
+
+ if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) &&
+ attr->precise_ip > 1)
+ return pebs_data_cfg;
+
+ if (sample_type & PERF_PEBS_MEMINFO_TYPE)
+ pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
+
+ /*
+ * We need GPRs when:
+ * + user requested them
+ * + precise_ip < 2 for the non event IP
+ * + For RTM TSX weight we need GPRs for the abort code.
+ */
+ gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PEBS_GP_REGS);
+
+ tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
+ ((attr->config & INTEL_ARCH_EVENT_MASK) ==
+ x86_pmu.rtm_abort_event);
+
+ if (gprs || (attr->precise_ip < 2) || tsx_weight)
+ pebs_data_cfg |= PEBS_DATACFG_GP;
+
+ if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PEBS_XMM_REGS))
+ pebs_data_cfg |= PEBS_DATACFG_XMMS;
+
+ if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+ /*
+ * For now always log all LBRs. Could configure this
+ * later.
+ */
+ pebs_data_cfg |= PEBS_DATACFG_LBRS |
+ ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
+ }
+
+ return pebs_data_cfg;
+}
+
static void
-pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
+pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
+ struct perf_event *event, bool add)
{
+ struct pmu *pmu = event->ctx->pmu;
/*
* Make sure we get updated with the first PEBS
* event. It will trigger also during removal, but
@@ -933,6 +1003,29 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
update = true;
}
+ /*
+ * The PEBS record doesn't shrink on pmu::del(). Doing so would require
+ * iterating all remaining PEBS events to reconstruct the config.
+ */
+ if (x86_pmu.intel_cap.pebs_baseline && add) {
+ u64 pebs_data_cfg;
+
+ /* Clear pebs_data_cfg and pebs_record_size for first PEBS. */
+ if (cpuc->n_pebs == 1) {
+ cpuc->pebs_data_cfg = 0;
+ cpuc->pebs_record_size = sizeof(struct pebs_basic);
+ }
+
+ pebs_data_cfg = pebs_update_adaptive_cfg(event);
+
+ /* Update pebs_record_size if new event requires more data. */
+ if (pebs_data_cfg & ~cpuc->pebs_data_cfg) {
+ cpuc->pebs_data_cfg |= pebs_data_cfg;
+ adaptive_pebs_record_size_update();
+ update = true;
+ }
+ }
+
if (update)
pebs_update_threshold(cpuc);
}
@@ -947,7 +1040,7 @@ void intel_pmu_pebs_add(struct perf_event *event)
if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs++;
- pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+ pebs_update_state(needed_cb, cpuc, event, true);
}
void intel_pmu_pebs_enable(struct perf_event *event)
@@ -965,6 +1058,14 @@ void intel_pmu_pebs_enable(struct perf_event *event)
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled |= 1ULL << 63;
+ if (x86_pmu.intel_cap.pebs_baseline) {
+ hwc->config |= ICL_EVENTSEL_ADAPTIVE;
+ if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) {
+ wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg);
+ cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg;
+ }
+ }
+
/*
* Use auto-reload if possible to save a MSR write in the PMI.
* This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
@@ -991,7 +1092,7 @@ void intel_pmu_pebs_del(struct perf_event *event)
if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs--;
- pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+ pebs_update_state(needed_cb, cpuc, event, false);
}
void intel_pmu_pebs_disable(struct perf_event *event)
@@ -1144,6 +1245,13 @@ static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax)
return txn;
}
+static inline u64 get_pebs_status(void *n)
+{
+ if (x86_pmu.intel_cap.pebs_format < 4)
+ return ((struct pebs_record_nhm *)n)->status;
+ return ((struct pebs_basic *)n)->applicable_counters;
+}
+
#define PERF_X86_EVENT_PEBS_HSW_PREC \
(PERF_X86_EVENT_PEBS_ST_HSW | \
PERF_X86_EVENT_PEBS_LD_HSW | \
@@ -1164,7 +1272,7 @@ static u64 get_data_src(struct perf_event *event, u64 aux)
return val;
}
-static void setup_pebs_sample_data(struct perf_event *event,
+static void setup_pebs_fixed_sample_data(struct perf_event *event,
struct pt_regs *iregs, void *__pebs,
struct perf_sample_data *data,
struct pt_regs *regs)
@@ -1306,6 +1414,140 @@ static void setup_pebs_sample_data(struct perf_event *event,
data->br_stack = &cpuc->lbr_stack;
}
+static void adaptive_pebs_save_regs(struct pt_regs *regs,
+ struct pebs_gprs *gprs)
+{
+ regs->ax = gprs->ax;
+ regs->bx = gprs->bx;
+ regs->cx = gprs->cx;
+ regs->dx = gprs->dx;
+ regs->si = gprs->si;
+ regs->di = gprs->di;
+ regs->bp = gprs->bp;
+ regs->sp = gprs->sp;
+#ifndef CONFIG_X86_32
+ regs->r8 = gprs->r8;
+ regs->r9 = gprs->r9;
+ regs->r10 = gprs->r10;
+ regs->r11 = gprs->r11;
+ regs->r12 = gprs->r12;
+ regs->r13 = gprs->r13;
+ regs->r14 = gprs->r14;
+ regs->r15 = gprs->r15;
+#endif
+}
+
+/*
+ * With adaptive PEBS the layout depends on what fields are configured.
+ */
+
+static void setup_pebs_adaptive_sample_data(struct perf_event *event,
+ struct pt_regs *iregs, void *__pebs,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct pebs_basic *basic = __pebs;
+ void *next_record = basic + 1;
+ u64 sample_type;
+ u64 format_size;
+ struct pebs_meminfo *meminfo = NULL;
+ struct pebs_gprs *gprs = NULL;
+ struct x86_perf_regs *perf_regs;
+
+ if (basic == NULL)
+ return;
+
+ perf_regs = container_of(regs, struct x86_perf_regs, regs);
+ perf_regs->xmm_regs = NULL;
+
+ sample_type = event->attr.sample_type;
+ format_size = basic->format_size;
+ perf_sample_data_init(data, 0, event->hw.last_period);
+ data->period = event->hw.last_period;
+
+ if (event->attr.use_clockid == 0)
+ data->time = native_sched_clock_from_tsc(basic->tsc);
+
+ /*
+ * We must however always use iregs for the unwinder to stay sane; the
+ * record BP,SP,IP can point into thin air when the record is from a
+ * previous PMI context or an (I)RET happened between the record and
+ * PMI.
+ */
+ if (sample_type & PERF_SAMPLE_CALLCHAIN)
+ data->callchain = perf_callchain(event, iregs);
+
+ *regs = *iregs;
+ /* The ip in basic is EventingIP */
+ set_linear_ip(regs, basic->ip);
+ regs->flags = PERF_EFLAGS_EXACT;
+
+ /*
+ * The record for MEMINFO is in front of GP
+ * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
+ * Save the pointer here but process later.
+ */
+ if (format_size & PEBS_DATACFG_MEMINFO) {
+ meminfo = next_record;
+ next_record = meminfo + 1;
+ }
+
+ if (format_size & PEBS_DATACFG_GP) {
+ gprs = next_record;
+ next_record = gprs + 1;
+
+ if (event->attr.precise_ip < 2) {
+ set_linear_ip(regs, gprs->ip);
+ regs->flags &= ~PERF_EFLAGS_EXACT;
+ }
+
+ if (sample_type & PERF_SAMPLE_REGS_INTR)
+ adaptive_pebs_save_regs(regs, gprs);
+ }
+
+ if (format_size & PEBS_DATACFG_MEMINFO) {
+ if (sample_type & PERF_SAMPLE_WEIGHT)
+ data->weight = meminfo->latency ?:
+ intel_get_tsx_weight(meminfo->tsx_tuning);
+
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ data->data_src.val = get_data_src(event, meminfo->aux);
+
+ if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
+ data->addr = meminfo->address;
+
+ if (sample_type & PERF_SAMPLE_TRANSACTION)
+ data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning,
+ gprs ? gprs->ax : 0);
+ }
+
+ if (format_size & PEBS_DATACFG_XMMS) {
+ struct pebs_xmm *xmm = next_record;
+
+ next_record = xmm + 1;
+ perf_regs->xmm_regs = xmm->xmm;
+ }
+
+ if (format_size & PEBS_DATACFG_LBRS) {
+ struct pebs_lbr *lbr = next_record;
+ int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
+ & 0xff) + 1;
+ next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry);
+
+ if (has_branch_stack(event)) {
+ intel_pmu_store_pebs_lbrs(lbr);
+ data->br_stack = &cpuc->lbr_stack;
+ }
+ }
+
+ WARN_ONCE(next_record != __pebs + (format_size >> 48),
+ "PEBS record size %llu, expected %llu, config %llx\n",
+ format_size >> 48,
+ (u64)(next_record - __pebs),
+ basic->format_size);
+}
+
static inline void *
get_next_pebs_record_by_bit(void *base, void *top, int bit)
{
@@ -1323,19 +1565,19 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
if (base == NULL)
return NULL;
- for (at = base; at < top; at += x86_pmu.pebs_record_size) {
- struct pebs_record_nhm *p = at;
+ for (at = base; at < top; at += cpuc->pebs_record_size) {
+ unsigned long status = get_pebs_status(at);
- if (test_bit(bit, (unsigned long *)&p->status)) {
+ if (test_bit(bit, (unsigned long *)&status)) {
/* PEBS v3 has accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3)
return at;
- if (p->status == (1 << bit))
+ if (status == (1 << bit))
return at;
/* clear non-PEBS bit and re-check */
- pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status = status & cpuc->pebs_enabled;
pebs_status &= PEBS_COUNTER_MASK;
if (pebs_status == (1 << bit))
return at;
@@ -1415,11 +1657,18 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
static void __intel_pmu_pebs_event(struct perf_event *event,
struct pt_regs *iregs,
void *base, void *top,
- int bit, int count)
+ int bit, int count,
+ void (*setup_sample)(struct perf_event *,
+ struct pt_regs *,
+ void *,
+ struct perf_sample_data *,
+ struct pt_regs *))
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
struct perf_sample_data data;
- struct pt_regs regs;
+ struct x86_perf_regs perf_regs;
+ struct pt_regs *regs = &perf_regs.regs;
void *at = get_next_pebs_record_by_bit(base, top, bit);
if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
@@ -1434,20 +1683,20 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
return;
while (count > 1) {
- setup_pebs_sample_data(event, iregs, at, &data, &regs);
- perf_event_output(event, &data, &regs);
- at += x86_pmu.pebs_record_size;
+ setup_sample(event, iregs, at, &data, regs);
+ perf_event_output(event, &data, regs);
+ at += cpuc->pebs_record_size;
at = get_next_pebs_record_by_bit(at, top, bit);
count--;
}
- setup_pebs_sample_data(event, iregs, at, &data, &regs);
+ setup_sample(event, iregs, at, &data, regs);
/*
* All but the last records are processed.
* The last one is left to be able to call the overflow handler.
*/
- if (perf_event_overflow(event, &data, &regs)) {
+ if (perf_event_overflow(event, &data, regs)) {
x86_pmu_stop(event, 0);
return;
}
@@ -1488,7 +1737,8 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
return;
}
- __intel_pmu_pebs_event(event, iregs, at, top, 0, n);
+ __intel_pmu_pebs_event(event, iregs, at, top, 0, n,
+ setup_pebs_fixed_sample_data);
}
static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
@@ -1550,8 +1800,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
/* PEBS v3 has more accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3) {
- for_each_set_bit(bit, (unsigned long *)&pebs_status,
- size)
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
counts[bit]++;
continue;
@@ -1590,8 +1839,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
* If collision happened, the record will be dropped.
*/
if (p->status != (1ULL << bit)) {
- for_each_set_bit(i, (unsigned long *)&pebs_status,
- x86_pmu.max_pebs_events)
+ for_each_set_bit(i, (unsigned long *)&pebs_status, size)
error[i]++;
continue;
}
@@ -1599,7 +1847,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
counts[bit]++;
}
- for (bit = 0; bit < size; bit++) {
+ for_each_set_bit(bit, (unsigned long *)&mask, size) {
if ((counts[bit] == 0) && (error[bit] == 0))
continue;
@@ -1620,11 +1868,66 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
if (counts[bit]) {
__intel_pmu_pebs_event(event, iregs, base,
- top, bit, counts[bit]);
+ top, bit, counts[bit],
+ setup_pebs_fixed_sample_data);
}
}
}
+static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs)
+{
+ short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct debug_store *ds = cpuc->ds;
+ struct perf_event *event;
+ void *base, *at, *top;
+ int bit, size;
+ u64 mask;
+
+ if (!x86_pmu.pebs_active)
+ return;
+
+ base = (struct pebs_basic *)(unsigned long)ds->pebs_buffer_base;
+ top = (struct pebs_basic *)(unsigned long)ds->pebs_index;
+
+ ds->pebs_index = ds->pebs_buffer_base;
+
+ mask = ((1ULL << x86_pmu.max_pebs_events) - 1) |
+ (((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
+ size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+
+ if (unlikely(base >= top)) {
+ intel_pmu_pebs_event_update_no_drain(cpuc, size);
+ return;
+ }
+
+ for (at = base; at < top; at += cpuc->pebs_record_size) {
+ u64 pebs_status;
+
+ pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
+ pebs_status &= mask;
+
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
+ counts[bit]++;
+ }
+
+ for_each_set_bit(bit, (unsigned long *)&mask, size) {
+ if (counts[bit] == 0)
+ continue;
+
+ event = cpuc->events[bit];
+ if (WARN_ON_ONCE(!event))
+ continue;
+
+ if (WARN_ON_ONCE(!event->attr.precise_ip))
+ continue;
+
+ __intel_pmu_pebs_event(event, iregs, base,
+ top, bit, counts[bit],
+ setup_pebs_adaptive_sample_data);
+ }
+}
+
/*
* BTS, PEBS probe and setup
*/
@@ -1646,8 +1949,12 @@ void __init intel_ds_init(void)
}
if (x86_pmu.pebs) {
char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-';
+ char *pebs_qual = "";
int format = x86_pmu.intel_cap.pebs_format;
+ if (format < 4)
+ x86_pmu.intel_cap.pebs_baseline = 0;
+
switch (format) {
case 0:
pr_cont("PEBS fmt0%c, ", pebs_type);
@@ -1683,6 +1990,29 @@ void __init intel_ds_init(void)
x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
break;
+ case 4:
+ x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl;
+ x86_pmu.pebs_record_size = sizeof(struct pebs_basic);
+ if (x86_pmu.intel_cap.pebs_baseline) {
+ x86_pmu.large_pebs_flags |=
+ PERF_SAMPLE_BRANCH_STACK |
+ PERF_SAMPLE_TIME;
+ x86_pmu.flags |= PMU_FL_PEBS_ALL;
+ pebs_qual = "-baseline";
+ } else {
+ /* Only basic record supported */
+ x86_pmu.pebs_no_xmm_regs = 1;
+ x86_pmu.large_pebs_flags &=
+ ~(PERF_SAMPLE_ADDR |
+ PERF_SAMPLE_TIME |
+ PERF_SAMPLE_DATA_SRC |
+ PERF_SAMPLE_TRANSACTION |
+ PERF_SAMPLE_REGS_USER |
+ PERF_SAMPLE_REGS_INTR);
+ }
+ pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
+ break;
+
default:
pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
x86_pmu.pebs = 0;
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 580c1b91c454..07b7175fc378 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1080,6 +1080,28 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
}
}
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int i;
+
+ cpuc->lbr_stack.nr = x86_pmu.lbr_nr;
+ for (i = 0; i < x86_pmu.lbr_nr; i++) {
+ u64 info = lbr->lbr[i].info;
+ struct perf_branch_entry *e = &cpuc->lbr_entries[i];
+
+ e->from = lbr->lbr[i].from;
+ e->to = lbr->lbr[i].to;
+ e->mispred = !!(info & LBR_INFO_MISPRED);
+ e->predicted = !(info & LBR_INFO_MISPRED);
+ e->in_tx = !!(info & LBR_INFO_IN_TX);
+ e->abort = !!(info & LBR_INFO_ABORT);
+ e->cycles = info & LBR_INFO_CYCLES;
+ e->reserved = 0;
+ }
+ intel_pmu_lbr_filter(cpuc);
+}
+
/*
* Map interface branch filters onto LBR filters
*/
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 7abfadb4f202..2059c143946f 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -224,6 +224,11 @@ struct cpu_hw_events {
int n_pebs;
int n_large_pebs;
+ /* Current super set of events hardware configuration */
+ u64 pebs_data_cfg;
+ u64 active_pebs_data_cfg;
+ int pebs_record_size;
+
/*
* Intel LBR bits
*/
@@ -490,6 +495,7 @@ union perf_capabilities {
* values > 32bit.
*/
u64 full_width_write:1;
+ u64 pebs_baseline:1;
};
u64 capabilities;
};
@@ -634,11 +640,12 @@ struct x86_pmu {
pebs_no_xmm_regs :1;
int pebs_record_size;
int pebs_buffer_size;
+ int max_pebs_events;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
- int max_pebs_events;
unsigned long large_pebs_flags;
+ u64 rtm_abort_event;
/*
* Intel LBR
@@ -978,6 +985,8 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
void intel_pmu_auto_reload_read(struct perf_event *event);
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr);
+
void intel_ds_init(void);
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);