summaryrefslogtreecommitdiffstats
path: root/tools/perf/util/evsel.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util/evsel.c')
-rw-r--r--tools/perf/util/evsel.c163
1 files changed, 142 insertions, 21 deletions
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dbfeceb2546c..ac0127be0459 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -241,7 +241,7 @@ void evsel__init(struct evsel *evsel,
{
perf_evsel__init(&evsel->core, attr, idx);
evsel->tracking = !idx;
- evsel->unit = "";
+ evsel->unit = strdup("");
evsel->scale = 1.0;
evsel->max_events = ULONG_MAX;
evsel->evlist = NULL;
@@ -276,13 +276,8 @@ struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx)
}
if (evsel__is_clock(evsel)) {
- /*
- * The evsel->unit points to static alias->unit
- * so it's ok to use static string in here.
- */
- static const char *unit = "msec";
-
- evsel->unit = unit;
+ free((char *)evsel->unit);
+ evsel->unit = strdup("msec");
evsel->scale = 1e-6;
}
@@ -294,7 +289,7 @@ static bool perf_event_can_profile_kernel(void)
return perf_event_paranoid_check(1);
}
-struct evsel *evsel__new_cycles(bool precise, __u32 type, __u64 config)
+struct evsel *evsel__new_cycles(bool precise __maybe_unused, __u32 type, __u64 config)
{
struct perf_event_attr attr = {
.type = type,
@@ -305,18 +300,16 @@ struct evsel *evsel__new_cycles(bool precise, __u32 type, __u64 config)
event_attr_init(&attr);
- if (!precise)
- goto new_event;
-
/*
* Now let the usual logic to set up the perf_event_attr defaults
* to kick in when we return and before perf_evsel__open() is called.
*/
-new_event:
evsel = evsel__new(&attr);
if (evsel == NULL)
goto out;
+ arch_evsel__fixup_new_cycles(&evsel->core.attr);
+
evsel->precise_max = true;
/* use asprintf() because free(evsel) assumes name is allocated */
@@ -410,6 +403,11 @@ struct evsel *evsel__clone(struct evsel *orig)
if (evsel->filter == NULL)
goto out_err;
}
+ if (orig->metric_id) {
+ evsel->metric_id = strdup(orig->metric_id);
+ if (evsel->metric_id == NULL)
+ goto out_err;
+ }
evsel->cgrp = cgroup__get(orig->cgrp);
evsel->tp_format = orig->tp_format;
evsel->handler = orig->handler;
@@ -417,7 +415,11 @@ struct evsel *evsel__clone(struct evsel *orig)
evsel->max_events = orig->max_events;
evsel->tool_event = orig->tool_event;
- evsel->unit = orig->unit;
+ free((char *)evsel->unit);
+ evsel->unit = strdup(orig->unit);
+ if (evsel->unit == NULL)
+ goto out_err;
+
evsel->scale = orig->scale;
evsel->snapshot = orig->snapshot;
evsel->per_pkg = orig->per_pkg;
@@ -779,6 +781,17 @@ out_unknown:
return "unknown";
}
+const char *evsel__metric_id(const struct evsel *evsel)
+{
+ if (evsel->metric_id)
+ return evsel->metric_id;
+
+ if (evsel->core.attr.type == PERF_TYPE_SOFTWARE && evsel->tool_event)
+ return "duration_time";
+
+ return "unknown";
+}
+
const char *evsel__group_name(struct evsel *evsel)
{
return evsel->group_name ?: "anon group";
@@ -1047,6 +1060,10 @@ void __weak arch_evsel__set_sample_weight(struct evsel *evsel)
evsel__set_sample_bit(evsel, WEIGHT);
}
+void __weak arch_evsel__fixup_new_cycles(struct perf_event_attr *attr __maybe_unused)
+{
+}
+
/*
* The enable_on_exec/disabled value strategy:
*
@@ -1423,6 +1440,8 @@ void evsel__exit(struct evsel *evsel)
zfree(&evsel->group_name);
zfree(&evsel->name);
zfree(&evsel->pmu_name);
+ zfree(&evsel->unit);
+ zfree(&evsel->metric_id);
evsel__zero_per_pkg(evsel);
hashmap__free(evsel->per_pkg_mask);
evsel->per_pkg_mask = NULL;
@@ -1807,7 +1826,7 @@ static void evsel__disable_missing_features(struct evsel *evsel)
evsel->open_flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC;
if (perf_missing_features.mmap2)
evsel->core.attr.mmap2 = 0;
- if (perf_missing_features.exclude_guest)
+ if (evsel->pmu && evsel->pmu->missing_features.exclude_guest)
evsel->core.attr.exclude_guest = evsel->core.attr.exclude_host = 0;
if (perf_missing_features.lbr_flags)
evsel->core.attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
@@ -1900,10 +1919,27 @@ bool evsel__detect_missing_features(struct evsel *evsel)
perf_missing_features.mmap2 = true;
pr_debug2_peo("switching off mmap2\n");
return true;
- } else if (!perf_missing_features.exclude_guest &&
- (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host)) {
- perf_missing_features.exclude_guest = true;
- pr_debug2_peo("switching off exclude_guest, exclude_host\n");
+ } else if ((evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) &&
+ (evsel->pmu == NULL || evsel->pmu->missing_features.exclude_guest)) {
+ if (evsel->pmu == NULL) {
+ evsel->pmu = evsel__find_pmu(evsel);
+ if (evsel->pmu)
+ evsel->pmu->missing_features.exclude_guest = true;
+ else {
+ /* we cannot find PMU, disable attrs now */
+ evsel->core.attr.exclude_host = false;
+ evsel->core.attr.exclude_guest = false;
+ }
+ }
+
+ if (evsel->exclude_GH) {
+ pr_debug2_peo("PMU has no exclude_host/guest support, bailing out\n");
+ return false;
+ }
+ if (!perf_missing_features.exclude_guest) {
+ perf_missing_features.exclude_guest = true;
+ pr_debug2_peo("switching off exclude_guest, exclude_host\n");
+ }
return true;
} else if (!perf_missing_features.sample_id_all) {
perf_missing_features.sample_id_all = true;
@@ -2221,6 +2257,54 @@ void __weak arch_perf_parse_sample_weight(struct perf_sample *data,
data->weight = *array;
}
+u64 evsel__bitfield_swap_branch_flags(u64 value)
+{
+ u64 new_val = 0;
+
+ /*
+ * branch_flags
+ * union {
+ * u64 values;
+ * struct {
+ * mispred:1 //target mispredicted
+ * predicted:1 //target predicted
+ * in_tx:1 //in transaction
+ * abort:1 //transaction abort
+ * cycles:16 //cycle count to last branch
+ * type:4 //branch type
+ * reserved:40
+ * }
+ * }
+ *
+ * Avoid bswap64() the entire branch_flag.value,
+ * as it has variable bit-field sizes. Instead the
+ * macro takes the bit-field position/size,
+ * swaps it based on the host endianness.
+ *
+ * tep_is_bigendian() is used here instead of
+ * bigendian() to avoid python test fails.
+ */
+ if (tep_is_bigendian()) {
+ new_val = bitfield_swap(value, 0, 1);
+ new_val |= bitfield_swap(value, 1, 1);
+ new_val |= bitfield_swap(value, 2, 1);
+ new_val |= bitfield_swap(value, 3, 1);
+ new_val |= bitfield_swap(value, 4, 16);
+ new_val |= bitfield_swap(value, 20, 4);
+ new_val |= bitfield_swap(value, 24, 40);
+ } else {
+ new_val = bitfield_swap(value, 63, 1);
+ new_val |= bitfield_swap(value, 62, 1);
+ new_val |= bitfield_swap(value, 61, 1);
+ new_val |= bitfield_swap(value, 60, 1);
+ new_val |= bitfield_swap(value, 44, 16);
+ new_val |= bitfield_swap(value, 40, 4);
+ new_val |= bitfield_swap(value, 0, 40);
+ }
+
+ return new_val;
+}
+
int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
struct perf_sample *data)
{
@@ -2408,6 +2492,8 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
if (type & PERF_SAMPLE_BRANCH_STACK) {
const u64 max_branch_nr = UINT64_MAX /
sizeof(struct branch_entry);
+ struct branch_entry *e;
+ unsigned int i;
OVERFLOW_CHECK_u64(array);
data->branch_stack = (struct branch_stack *)array++;
@@ -2416,10 +2502,33 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
return -EFAULT;
sz = data->branch_stack->nr * sizeof(struct branch_entry);
- if (evsel__has_branch_hw_idx(evsel))
+ if (evsel__has_branch_hw_idx(evsel)) {
sz += sizeof(u64);
- else
+ e = &data->branch_stack->entries[0];
+ } else {
data->no_hw_idx = true;
+ /*
+ * if the PERF_SAMPLE_BRANCH_HW_INDEX is not applied,
+ * only nr and entries[] will be output by kernel.
+ */
+ e = (struct branch_entry *)&data->branch_stack->hw_idx;
+ }
+
+ if (swapped) {
+ /*
+ * struct branch_flag does not have endian
+ * specific bit field definition. And bswap
+ * will not resolve the issue, since these
+ * are bit fields.
+ *
+ * evsel__bitfield_swap_branch_flags() uses a
+ * bitfield_swap macro to swap the bit position
+ * based on the host endians.
+ */
+ for (i = 0; i < data->branch_stack->nr; i++, e++)
+ e->flags.value = evsel__bitfield_swap_branch_flags(e->flags.value);
+ }
+
OVERFLOW_CHECK(array, sz, max_size);
array = (void *)array + sz;
}
@@ -2928,3 +3037,15 @@ void evsel__set_leader(struct evsel *evsel, struct evsel *leader)
{
evsel->core.leader = &leader->core;
}
+
+int evsel__source_count(const struct evsel *evsel)
+{
+ struct evsel *pos;
+ int count = 0;
+
+ evlist__for_each_entry(evsel->evlist, pos) {
+ if (pos->metric_leader == evsel)
+ count++;
+ }
+ return count;
+}
generated by cgit v1.2.3 (git 2.46.0) at 2025-04-25 22:45:30 +0000