summaryrefslogtreecommitdiff
path: root/tools/perf/util
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util')
-rw-r--r--tools/perf/util/evlist.c13
-rw-r--r--tools/perf/util/evsel.c11
-rw-r--r--tools/perf/util/evsel.h2
-rw-r--r--tools/perf/util/intel-pt.c205
-rw-r--r--tools/perf/util/python.c17
-rw-r--r--tools/perf/util/units.c2
6 files changed, 234 insertions, 16 deletions
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index dca6843ea322..41bbe6f85b0d 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1342,19 +1342,18 @@ static int evlist__create_syswide_maps(struct evlist *evlist)
*/
cpus = perf_cpu_map__new(NULL);
if (!cpus)
- goto out;
+ return -ENOMEM;
threads = perf_thread_map__new_dummy();
- if (!threads)
- goto out_put;
+ if (!threads) {
+ perf_cpu_map__put(cpus);
+ return -ENOMEM;
+ }
perf_evlist__set_maps(&evlist->core, cpus, threads);
-
perf_thread_map__put(threads);
-out_put:
perf_cpu_map__put(cpus);
-out:
- return -ENOMEM;
+ return 0;
}
int evlist__open(struct evlist *evlist)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7db35dbdfcef..22969cc00a5f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1486,6 +1486,15 @@ static void evsel__free_config_terms(struct evsel *evsel)
free_config_terms(&evsel->config_terms);
}
+static void (*evsel__priv_destructor)(void *priv);
+
+void evsel__set_priv_destructor(void (*destructor)(void *priv))
+{
+ assert(evsel__priv_destructor == NULL);
+
+ evsel__priv_destructor = destructor;
+}
+
void evsel__exit(struct evsel *evsel)
{
assert(list_empty(&evsel->core.node));
@@ -1508,6 +1517,8 @@ void evsel__exit(struct evsel *evsel)
hashmap__free(evsel->per_pkg_mask);
evsel->per_pkg_mask = NULL;
zfree(&evsel->metric_events);
+ if (evsel__priv_destructor)
+ evsel__priv_destructor(evsel->priv);
perf_evsel__object.fini(evsel);
}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 8ce30329a077..fabf0697c36a 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -246,6 +246,8 @@ void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx);
void evsel__exit(struct evsel *evsel);
void evsel__delete(struct evsel *evsel);
+void evsel__set_priv_destructor(void (*destructor)(void *priv));
+
struct callchain_param;
void evsel__config(struct evsel *evsel, struct record_opts *opts,
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index bd09af447eb0..018eaddd4e6a 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -122,6 +122,7 @@ struct intel_pt {
bool single_pebs;
bool sample_pebs;
+ int pebs_data_src_fmt;
struct evsel *pebs_evsel;
u64 evt_sample_type;
@@ -170,6 +171,7 @@ enum switch_state {
struct intel_pt_pebs_event {
struct evsel *evsel;
u64 id;
+ int data_src_fmt;
};
struct intel_pt_queue {
@@ -2176,7 +2178,146 @@ static void intel_pt_add_lbrs(struct branch_stack *br_stack,
}
}
-static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel, u64 id)
+#define P(a, b) PERF_MEM_S(a, b)
+#define OP_LH (P(OP, LOAD) | P(LVL, HIT))
+#define LEVEL(x) P(LVLNUM, x)
+#define REM P(REMOTE, REMOTE)
+#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
+
+#define PERF_PEBS_DATA_SOURCE_GRT_MAX 0x10
+#define PERF_PEBS_DATA_SOURCE_GRT_MASK (PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
+
+/* Based on kernel __intel_pmu_pebs_data_source_grt() and pebs_data_source */
+static const u64 pebs_data_source_grt[PERF_PEBS_DATA_SOURCE_GRT_MAX] = {
+ P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA), /* L3 miss|SNP N/A */
+ OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* L1 hit|SNP None */
+ OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* LFB/MAB hit|SNP None */
+ OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* L2 hit|SNP None */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* L3 hit|SNP None */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT), /* L3 hit|SNP Hit */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* L3 hit|SNP HitM */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* L3 hit|SNP HitM */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD), /* L3 hit|SNP Fwd */
+ OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* Remote L3 hit|SNP HitM */
+ OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, HIT), /* RAM hit|SNP Hit */
+ OP_LH | P(LVL, REM_RAM1) | REM | LEVEL(L3) | P(SNOOP, HIT), /* Remote L3 hit|SNP Hit */
+ OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | SNOOP_NONE_MISS, /* RAM hit|SNP None or Miss */
+ OP_LH | P(LVL, REM_RAM1) | LEVEL(RAM) | REM | SNOOP_NONE_MISS, /* Remote RAM hit|SNP None or Miss */
+ OP_LH | P(LVL, IO) | LEVEL(NA) | P(SNOOP, NONE), /* I/O hit|SNP None */
+ OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE), /* Uncached hit|SNP None */
+};
+
+/* Based on kernel __intel_pmu_pebs_data_source_cmt() and pebs_data_source */
+static const u64 pebs_data_source_cmt[PERF_PEBS_DATA_SOURCE_GRT_MAX] = {
+ P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA), /* L3 miss|SNP N/A */
+ OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* L1 hit|SNP None */
+ OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* LFB/MAB hit|SNP None */
+ OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* L2 hit|SNP None */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* L3 hit|SNP None */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, MISS), /* L3 hit|SNP Hit */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT), /* L3 hit|SNP HitM */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD), /* L3 hit|SNP HitM */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* L3 hit|SNP Fwd */
+ OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* Remote L3 hit|SNP HitM */
+ OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, NONE), /* RAM hit|SNP Hit */
+ OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE), /* Remote L3 hit|SNP Hit */
+ OP_LH | LEVEL(RAM) | REM | P(SNOOPX, FWD), /* RAM hit|SNP None or Miss */
+ OP_LH | LEVEL(RAM) | REM | P(SNOOP, HITM), /* Remote RAM hit|SNP None or Miss */
+ OP_LH | P(LVL, IO) | LEVEL(NA) | P(SNOOP, NONE), /* I/O hit|SNP None */
+ OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE), /* Uncached hit|SNP None */
+};
+
+/* Based on kernel pebs_set_tlb_lock() */
+static inline void pebs_set_tlb_lock(u64 *val, bool tlb, bool lock)
+{
+ /*
+ * TLB access
+ * 0 = did not miss 2nd level TLB
+ * 1 = missed 2nd level TLB
+ */
+ if (tlb)
+ *val |= P(TLB, MISS) | P(TLB, L2);
+ else
+ *val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+
+ /* locked prefix */
+ if (lock)
+ *val |= P(LOCK, LOCKED);
+}
+
+/* Based on kernel __grt_latency_data() */
+static u64 intel_pt_grt_latency_data(u8 dse, bool tlb, bool lock, bool blk,
+ const u64 *pebs_data_source)
+{
+ u64 val;
+
+ dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK;
+ val = pebs_data_source[dse];
+
+ pebs_set_tlb_lock(&val, tlb, lock);
+
+ if (blk)
+ val |= P(BLK, DATA);
+ else
+ val |= P(BLK, NA);
+
+ return val;
+}
+
+/* Default value for data source */
+#define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\
+ PERF_MEM_S(LVL, NA) |\
+ PERF_MEM_S(SNOOP, NA) |\
+ PERF_MEM_S(LOCK, NA) |\
+ PERF_MEM_S(TLB, NA) |\
+ PERF_MEM_S(LVLNUM, NA))
+
+enum DATA_SRC_FORMAT {
+ DATA_SRC_FORMAT_ERR = -1,
+ DATA_SRC_FORMAT_NA = 0,
+ DATA_SRC_FORMAT_GRT = 1,
+ DATA_SRC_FORMAT_CMT = 2,
+};
+
+/* Based on kernel grt_latency_data() and cmt_latency_data */
+static u64 intel_pt_get_data_src(u64 mem_aux_info, int data_src_fmt)
+{
+ switch (data_src_fmt) {
+ case DATA_SRC_FORMAT_GRT: {
+ union {
+ u64 val;
+ struct {
+ unsigned int dse:4;
+ unsigned int locked:1;
+ unsigned int stlb_miss:1;
+ unsigned int fwd_blk:1;
+ unsigned int reserved:25;
+ };
+ } x = {.val = mem_aux_info};
+ return intel_pt_grt_latency_data(x.dse, x.stlb_miss, x.locked, x.fwd_blk,
+ pebs_data_source_grt);
+ }
+ case DATA_SRC_FORMAT_CMT: {
+ union {
+ u64 val;
+ struct {
+ unsigned int dse:5;
+ unsigned int locked:1;
+ unsigned int stlb_miss:1;
+ unsigned int fwd_blk:1;
+ unsigned int reserved:24;
+ };
+ } x = {.val = mem_aux_info};
+ return intel_pt_grt_latency_data(x.dse, x.stlb_miss, x.locked, x.fwd_blk,
+ pebs_data_source_cmt);
+ }
+ default:
+ return PERF_MEM_NA;
+ }
+}
+
+static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel,
+ u64 id, int data_src_fmt)
{
const struct intel_pt_blk_items *items = &ptq->state->items;
struct perf_sample sample = { .ip = 0, };
@@ -2294,6 +2435,18 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse
}
}
+ if (sample_type & PERF_SAMPLE_DATA_SRC) {
+ if (items->has_mem_aux_info && data_src_fmt) {
+ if (data_src_fmt < 0) {
+ pr_err("Intel PT missing data_src info\n");
+ return -1;
+ }
+ sample.data_src = intel_pt_get_data_src(items->mem_aux_info, data_src_fmt);
+ } else {
+ sample.data_src = PERF_MEM_NA;
+ }
+ }
+
if (sample_type & PERF_SAMPLE_TRANSACTION && items->has_tsx_aux_info) {
u64 ax = items->has_rax ? items->rax : 0;
/* Refer kernel's intel_hsw_transaction() */
@@ -2312,9 +2465,10 @@ static int intel_pt_synth_single_pebs_sample(struct intel_pt_queue *ptq)
{
struct intel_pt *pt = ptq->pt;
struct evsel *evsel = pt->pebs_evsel;
+ int data_src_fmt = pt->pebs_data_src_fmt;
u64 id = evsel->core.id[0];
- return intel_pt_do_synth_pebs_sample(ptq, evsel, id);
+ return intel_pt_do_synth_pebs_sample(ptq, evsel, id, data_src_fmt);
}
static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
@@ -2339,7 +2493,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
hw_id);
return intel_pt_synth_single_pebs_sample(ptq);
}
- err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id);
+ err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id, pe->data_src_fmt);
if (err)
return err;
}
@@ -3290,6 +3444,49 @@ static int intel_pt_process_itrace_start(struct intel_pt *pt,
event->itrace_start.tid);
}
+/*
+ * Events with data_src are identified by L1_Hit_Indication
+ * refer https://github.com/intel/perfmon
+ */
+static int intel_pt_data_src_fmt(struct intel_pt *pt, struct evsel *evsel)
+{
+ struct perf_env *env = pt->machine->env;
+ int fmt = DATA_SRC_FORMAT_NA;
+
+ if (!env->cpuid)
+ return DATA_SRC_FORMAT_ERR;
+
+ /*
+ * PEBS-via-PT is only supported on E-core non-hybrid. Of those only
+ * Gracemont and Crestmont have data_src. Check for:
+ * Alderlake N (Gracemont)
+ * Sierra Forest (Crestmont)
+ * Grand Ridge (Crestmont)
+ */
+
+ if (!strncmp(env->cpuid, "GenuineIntel,6,190,", 19))
+ fmt = DATA_SRC_FORMAT_GRT;
+
+ if (!strncmp(env->cpuid, "GenuineIntel,6,175,", 19) ||
+ !strncmp(env->cpuid, "GenuineIntel,6,182,", 19))
+ fmt = DATA_SRC_FORMAT_CMT;
+
+ if (fmt == DATA_SRC_FORMAT_NA)
+ return fmt;
+
+ /*
+ * Only data_src events are:
+ * mem-loads event=0xd0,umask=0x5
+ * mem-stores event=0xd0,umask=0x6
+ */
+ if (evsel->core.attr.type == PERF_TYPE_RAW &&
+ ((evsel->core.attr.config & 0xffff) == 0x5d0 ||
+ (evsel->core.attr.config & 0xffff) == 0x6d0))
+ return fmt;
+
+ return DATA_SRC_FORMAT_NA;
+}
+
static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt,
union perf_event *event,
struct perf_sample *sample)
@@ -3310,6 +3507,7 @@ static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt,
ptq->pebs[hw_id].evsel = evsel;
ptq->pebs[hw_id].id = sample->id;
+ ptq->pebs[hw_id].data_src_fmt = intel_pt_data_src_fmt(pt, evsel);
return 0;
}
@@ -3855,6 +4053,7 @@ static void intel_pt_setup_pebs_events(struct intel_pt *pt)
}
pt->single_pebs = true;
pt->sample_pebs = true;
+ pt->pebs_data_src_fmt = intel_pt_data_src_fmt(pt, evsel);
pt->pebs_evsel = evsel;
}
}
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 5be5fa2391de..e25c3fcaeccc 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -181,7 +181,7 @@ struct pyrf_event {
};
#define sample_members \
- sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"), \
+ sample_member_def(sample_ip, ip, T_ULONGLONG, "event ip"), \
sample_member_def(sample_pid, pid, T_INT, "event pid"), \
sample_member_def(sample_tid, tid, T_INT, "event tid"), \
sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"), \
@@ -610,6 +610,11 @@ static PyObject *pyrf_event__new(union perf_event *event)
event->header.type == PERF_RECORD_SWITCH_CPU_WIDE))
return NULL;
+ // FIXME this better be dynamic or we need to parse everything
+ // before calling perf_mmap__consume(), including tracepoint fields.
+ if (sizeof(pevent->event) < event->header.size)
+ return NULL;
+
ptype = pyrf_event__type[event->header.type];
pevent = PyObject_New(struct pyrf_event, ptype);
if (pevent != NULL)
@@ -1109,20 +1114,22 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
evsel = evlist__event2evsel(evlist, event);
if (!evsel) {
+ Py_DECREF(pyevent);
Py_INCREF(Py_None);
return Py_None;
}
pevent->evsel = evsel;
- err = evsel__parse_sample(evsel, event, &pevent->sample);
-
- /* Consume the even only after we parsed it out. */
perf_mmap__consume(&md->core);
- if (err)
+ err = evsel__parse_sample(evsel, &pevent->event, &pevent->sample);
+ if (err) {
+ Py_DECREF(pyevent);
return PyErr_Format(PyExc_OSError,
"perf: can't parse sample, err=%d", err);
+ }
+
return pyevent;
}
end:
diff --git a/tools/perf/util/units.c b/tools/perf/util/units.c
index 32c39cfe209b..4c6a86e1cb54 100644
--- a/tools/perf/util/units.c
+++ b/tools/perf/util/units.c
@@ -64,7 +64,7 @@ unsigned long convert_unit(unsigned long value, char *unit)
int unit_number__scnprintf(char *buf, size_t size, u64 n)
{
- char unit[4] = "BKMG";
+ char unit[] = "BKMG";
int i = 0;
while (((n / 1024) > 1) && (i < 3)) {
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-31 17:09:42 +0300