summaryrefslogtreecommitdiff
path: root/tools/perf/util
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util')
-rw-r--r--tools/perf/util/Build2
-rw-r--r--tools/perf/util/annotate.c40
-rw-r--r--tools/perf/util/arm-spe.c9
-rw-r--r--tools/perf/util/auxtrace.c125
-rw-r--r--tools/perf/util/auxtrace.h16
-rw-r--r--tools/perf/util/bpf-event.c96
-rw-r--r--tools/perf/util/bpf-event.h7
-rw-r--r--tools/perf/util/bpf-loader.c2
-rw-r--r--tools/perf/util/branch.h19
-rw-r--r--tools/perf/util/callchain.h8
-rw-r--r--tools/perf/util/cap.h4
-rw-r--r--tools/perf/util/cgroup.c3
-rw-r--r--tools/perf/util/cloexec.c2
-rw-r--r--tools/perf/util/cs-etm-decoder/cs-etm-decoder.c2
-rw-r--r--tools/perf/util/cs-etm.c14
-rw-r--r--tools/perf/util/cs-etm.h3
-rw-r--r--tools/perf/util/data-convert-bt.c6
-rw-r--r--tools/perf/util/dso.c1
-rw-r--r--tools/perf/util/dso.h1
-rw-r--r--tools/perf/util/env.h3
-rw-r--r--tools/perf/util/event.c2
-rw-r--r--tools/perf/util/evlist.c159
-rw-r--r--tools/perf/util/evlist.h9
-rw-r--r--tools/perf/util/evsel.c343
-rw-r--r--tools/perf/util/evsel.h194
-rw-r--r--tools/perf/util/evsel_config.h2
-rw-r--r--tools/perf/util/evsel_fprintf.c8
-rw-r--r--tools/perf/util/expr.c25
-rw-r--r--tools/perf/util/expr.h19
-rw-r--r--tools/perf/util/expr.l37
-rw-r--r--tools/perf/util/expr.y6
-rw-r--r--tools/perf/util/header.c121
-rw-r--r--tools/perf/util/header.h1
-rw-r--r--tools/perf/util/hist.c31
-rw-r--r--tools/perf/util/intel-bts.c16
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c2
-rw-r--r--tools/perf/util/intel-pt.c306
-rw-r--r--tools/perf/util/machine.c436
-rw-r--r--tools/perf/util/mem2node.c3
-rw-r--r--tools/perf/util/metricgroup.c78
-rw-r--r--tools/perf/util/metricgroup.h2
-rw-r--r--tools/perf/util/ordered-events.c2
-rw-r--r--tools/perf/util/parse-events.c39
-rw-r--r--tools/perf/util/parse-events.h1
-rw-r--r--tools/perf/util/parse-events.l1
-rw-r--r--tools/perf/util/parse-events.y12
-rw-r--r--tools/perf/util/perf_api_probe.c164
-rw-r--r--tools/perf/util/perf_api_probe.h14
-rw-r--r--tools/perf/util/pmu.c113
-rw-r--r--tools/perf/util/pmu.h10
-rw-r--r--tools/perf/util/python.c4
-rw-r--r--tools/perf/util/record.c185
-rw-r--r--tools/perf/util/record.h1
-rw-r--r--tools/perf/util/s390-cpumcf-kernel.h1
-rw-r--r--tools/perf/util/s390-cpumsf.c12
-rw-r--r--tools/perf/util/scripting-engines/trace-event-python.c6
-rw-r--r--tools/perf/util/session.c9
-rw-r--r--tools/perf/util/sideband_evlist.c148
-rw-r--r--tools/perf/util/smt.c10
-rw-r--r--tools/perf/util/sort.c12
-rw-r--r--tools/perf/util/sort.h2
-rw-r--r--tools/perf/util/stat-display.c23
-rw-r--r--tools/perf/util/stat-shadow.c55
-rw-r--r--tools/perf/util/stat.c24
-rw-r--r--tools/perf/util/symbol.c15
-rw-r--r--tools/perf/util/synthetic-events.c179
-rw-r--r--tools/perf/util/thread-stack.c274
-rw-r--r--tools/perf/util/thread-stack.h11
-rw-r--r--tools/perf/util/thread.c24
-rw-r--r--tools/perf/util/thread.h15
-rw-r--r--tools/perf/util/top.c2
-rw-r--r--tools/perf/util/top.h3
-rw-r--r--tools/perf/util/trace-event-read.c2
-rw-r--r--tools/perf/util/util.c1
74 files changed, 2475 insertions, 1062 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index c0cf8dff694e..ca07a162d602 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -10,6 +10,7 @@ perf-y += db-export.o
perf-y += env.o
perf-y += event.o
perf-y += evlist.o
+perf-y += sideband_evlist.o
perf-y += evsel.o
perf-y += evsel_fprintf.o
perf-y += perf_event_attr_fprintf.o
@@ -88,6 +89,7 @@ perf-y += counts.o
perf-y += stat.o
perf-y += stat-shadow.o
perf-y += stat-display.o
+perf-y += perf_api_probe.o
perf-y += record.o
perf-y += srcline.o
perf-y += srccode.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index f1ea0d61eb5b..d828c2d2edee 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1191,7 +1191,7 @@ static struct disasm_line *disasm_line__new(struct annotate_args *args)
struct disasm_line *dl = NULL;
int nr = 1;
- if (perf_evsel__is_group_event(args->evsel))
+ if (evsel__is_group_event(args->evsel))
nr = args->evsel->core.nr_members;
dl = zalloc(disasm_line_size(nr));
@@ -1437,7 +1437,7 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
if (queue)
return -1;
- if (perf_evsel__is_group_event(evsel))
+ if (evsel__is_group_event(evsel))
width *= evsel->core.nr_members;
if (!*al->line)
@@ -1821,6 +1821,24 @@ static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
}
#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+static int
+symbol__disassemble_bpf_image(struct symbol *sym,
+ struct annotate_args *args)
+{
+ struct annotation *notes = symbol__annotation(sym);
+ struct disasm_line *dl;
+
+ args->offset = -1;
+ args->line = strdup("to be implemented");
+ args->line_nr = 0;
+ dl = disasm_line__new(args);
+ if (dl)
+ annotation_line__add(&dl->al, &notes->src->source);
+
+ free(args->line);
+ return 0;
+}
+
/*
* Possibly create a new version of line with tabs expanded. Returns the
* existing or new line, storage is updated if a new line is allocated. If
@@ -1920,6 +1938,8 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) {
return symbol__disassemble_bpf(sym, args);
+ } else if (dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) {
+ return symbol__disassemble_bpf_image(sym, args);
} else if (dso__is_kcore(dso)) {
kce.kcore_filename = symfs_filename;
kce.addr = map__rip_2objdump(map, sym->start);
@@ -2136,7 +2156,7 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
.evsel = evsel,
.options = options,
};
- struct perf_env *env = perf_evsel__env(evsel);
+ struct perf_env *env = evsel__env(evsel);
const char *arch_name = perf_env__arch(env);
struct arch *arch;
int err;
@@ -2324,7 +2344,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel,
struct dso *dso = map->dso;
char *filename;
const char *d_filename;
- const char *evsel_name = perf_evsel__name(evsel);
+ const char *evsel_name = evsel__name(evsel);
struct annotation *notes = symbol__annotation(sym);
struct sym_hist *h = annotation__histogram(notes, evsel->idx);
struct annotation_line *pos, *queue = NULL;
@@ -2348,9 +2368,9 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel,
len = symbol__size(sym);
- if (perf_evsel__is_group_event(evsel)) {
+ if (evsel__is_group_event(evsel)) {
width *= evsel->core.nr_members;
- perf_evsel__group_desc(evsel, buf, sizeof(buf));
+ evsel__group_desc(evsel, buf, sizeof(buf));
evsel_name = buf;
}
@@ -2485,7 +2505,7 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
struct annotation_options *opts)
{
- const char *ev_name = perf_evsel__name(evsel);
+ const char *ev_name = evsel__name(evsel);
char buf[1024];
char *filename;
int err = -1;
@@ -2498,8 +2518,8 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
if (fp == NULL)
goto out_free_filename;
- if (perf_evsel__is_group_event(evsel)) {
- perf_evsel__group_desc(evsel, buf, sizeof(buf));
+ if (evsel__is_group_event(evsel)) {
+ evsel__group_desc(evsel, buf, sizeof(buf));
ev_name = buf;
}
@@ -3044,7 +3064,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
if (notes->offsets == NULL)
return ENOMEM;
- if (perf_evsel__is_group_event(evsel))
+ if (evsel__is_group_event(evsel))
nr_pcnt = evsel->core.nr_members;
err = symbol__annotate(ms, evsel, options, parch);
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 53be12b23ff4..875a0dd540e5 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -176,6 +176,14 @@ static void arm_spe_free(struct perf_session *session)
free(spe);
}
+static bool arm_spe_evsel_is_auxtrace(struct perf_session *session,
+ struct evsel *evsel)
+{
+ struct arm_spe *spe = container_of(session->auxtrace, struct arm_spe, auxtrace);
+
+ return evsel->core.attr.type == spe->pmu_type;
+}
+
static const char * const arm_spe_info_fmts[] = {
[ARM_SPE_PMU_TYPE] = " PMU Type %"PRId64"\n",
};
@@ -218,6 +226,7 @@ int arm_spe_process_auxtrace_info(union perf_event *event,
spe->auxtrace.flush_events = arm_spe_flush;
spe->auxtrace.free_events = arm_spe_free_events;
spe->auxtrace.free = arm_spe_free;
+ spe->auxtrace.evsel_is_auxtrace = arm_spe_evsel_is_auxtrace;
session->auxtrace = &spe->auxtrace;
arm_spe_print_info(&auxtrace_info->priv[0]);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 3571ce72ca28..749487a41cc7 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -33,6 +33,7 @@
#include "evsel.h"
#include "evsel_config.h"
#include "symbol.h"
+#include "util/perf_api_probe.h"
#include "util/synthetic-events.h"
#include "thread_map.h"
#include "asm/bug.h"
@@ -58,25 +59,6 @@
#include "symbol/kallsyms.h"
#include <internal/lib.h>
-static struct perf_pmu *perf_evsel__find_pmu(struct evsel *evsel)
-{
- struct perf_pmu *pmu = NULL;
-
- while ((pmu = perf_pmu__scan(pmu)) != NULL) {
- if (pmu->type == evsel->core.attr.type)
- break;
- }
-
- return pmu;
-}
-
-static bool perf_evsel__is_aux_event(struct evsel *evsel)
-{
- struct perf_pmu *pmu = perf_evsel__find_pmu(evsel);
-
- return pmu && pmu->auxtrace;
-}
-
/*
* Make a group from 'leader' to 'last', requiring that the events were not
* already grouped to a different leader.
@@ -88,7 +70,7 @@ static int perf_evlist__regroup(struct evlist *evlist,
struct evsel *evsel;
bool grp;
- if (!perf_evsel__is_group_leader(leader))
+ if (!evsel__is_group_leader(leader))
return -EINVAL;
grp = false;
@@ -703,8 +685,8 @@ static int auxtrace_validate_aux_sample_size(struct evlist *evlist,
evlist__for_each_entry(evlist, evsel) {
sz = evsel->core.attr.aux_sample_size;
- if (perf_evsel__is_group_leader(evsel)) {
- has_aux_leader = perf_evsel__is_aux_event(evsel);
+ if (evsel__is_group_leader(evsel)) {
+ has_aux_leader = evsel__is_aux_event(evsel);
if (sz) {
if (has_aux_leader)
pr_err("Cannot add AUX area sampling to an AUX area event\n");
@@ -723,10 +705,10 @@ static int auxtrace_validate_aux_sample_size(struct evlist *evlist,
pr_err("Cannot add AUX area sampling because group leader is not an AUX area event\n");
return -EINVAL;
}
- perf_evsel__set_sample_bit(evsel, AUX);
+ evsel__set_sample_bit(evsel, AUX);
opts->auxtrace_sample_mode = true;
} else {
- perf_evsel__reset_sample_bit(evsel, AUX);
+ evsel__reset_sample_bit(evsel, AUX);
}
}
@@ -777,8 +759,8 @@ int auxtrace_parse_sample_options(struct auxtrace_record *itr,
/* Set aux_sample_size based on --aux-sample option */
evlist__for_each_entry(evlist, evsel) {
- if (perf_evsel__is_group_leader(evsel)) {
- has_aux_leader = perf_evsel__is_aux_event(evsel);
+ if (evsel__is_group_leader(evsel)) {
+ has_aux_leader = evsel__is_aux_event(evsel);
} else if (has_aux_leader) {
evsel->core.attr.aux_sample_size = sz;
}
@@ -787,7 +769,7 @@ no_opt:
aux_evsel = NULL;
/* Override with aux_sample_size from config term */
evlist__for_each_entry(evlist, evsel) {
- if (perf_evsel__is_aux_event(evsel))
+ if (evsel__is_aux_event(evsel))
aux_evsel = evsel;
term = perf_evsel__get_config_term(evsel, AUX_SAMPLE_SIZE);
if (term) {
@@ -1234,29 +1216,79 @@ out_free:
return err;
}
+static void unleader_evsel(struct evlist *evlist, struct evsel *leader)
+{
+ struct evsel *new_leader = NULL;
+ struct evsel *evsel;
+
+ /* Find new leader for the group */
+ evlist__for_each_entry(evlist, evsel) {
+ if (evsel->leader != leader || evsel == leader)
+ continue;
+ if (!new_leader)
+ new_leader = evsel;
+ evsel->leader = new_leader;
+ }
+
+ /* Update group information */
+ if (new_leader) {
+ zfree(&new_leader->group_name);
+ new_leader->group_name = leader->group_name;
+ leader->group_name = NULL;
+
+ new_leader->core.nr_members = leader->core.nr_members - 1;
+ leader->core.nr_members = 1;
+ }
+}
+
+static void unleader_auxtrace(struct perf_session *session)
+{
+ struct evsel *evsel;
+
+ evlist__for_each_entry(session->evlist, evsel) {
+ if (auxtrace__evsel_is_auxtrace(session, evsel) &&
+ evsel__is_group_leader(evsel)) {
+ unleader_evsel(session->evlist, evsel);
+ }
+ }
+}
+
int perf_event__process_auxtrace_info(struct perf_session *session,
union perf_event *event)
{
enum auxtrace_type type = event->auxtrace_info.type;
+ int err;
if (dump_trace)
fprintf(stdout, " type: %u\n", type);
switch (type) {
case PERF_AUXTRACE_INTEL_PT:
- return intel_pt_process_auxtrace_info(event, session);
+ err = intel_pt_process_auxtrace_info(event, session);
+ break;
case PERF_AUXTRACE_INTEL_BTS:
- return intel_bts_process_auxtrace_info(event, session);
+ err = intel_bts_process_auxtrace_info(event, session);
+ break;
case PERF_AUXTRACE_ARM_SPE:
- return arm_spe_process_auxtrace_info(event, session);
+ err = arm_spe_process_auxtrace_info(event, session);
+ break;
case PERF_AUXTRACE_CS_ETM:
- return cs_etm__process_auxtrace_info(event, session);
+ err = cs_etm__process_auxtrace_info(event, session);
+ break;
case PERF_AUXTRACE_S390_CPUMSF:
- return s390_cpumsf_process_auxtrace_info(event, session);
+ err = s390_cpumsf_process_auxtrace_info(event, session);
+ break;
case PERF_AUXTRACE_UNKNOWN:
default:
return -EINVAL;
}
+
+ if (err)
+ return err;
+
+ unleader_auxtrace(session);
+
+ return 0;
}
s64 perf_event__process_auxtrace(struct perf_session *session,
@@ -1412,8 +1444,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
synth_opts->branches = true;
synth_opts->returns = true;
break;
+ case 'G':
case 'g':
- synth_opts->callchain = true;
+ if (p[-1] == 'G')
+ synth_opts->add_callchain = true;
+ else
+ synth_opts->callchain = true;
synth_opts->callchain_sz =
PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
while (*p == ' ' || *p == ',')
@@ -1428,8 +1464,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
synth_opts->callchain_sz = val;
}
break;
+ case 'L':
case 'l':
- synth_opts->last_branch = true;
+ if (p[-1] == 'L')
+ synth_opts->add_last_branch = true;
+ else
+ synth_opts->last_branch = true;
synth_opts->last_branch_sz =
PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
while (*p == ' ' || *p == ',')
@@ -2482,7 +2522,7 @@ static int parse_addr_filter(struct evsel *evsel, const char *filter,
goto out_exit;
}
- if (perf_evsel__append_addr_filter(evsel, new_filter)) {
+ if (evsel__append_addr_filter(evsel, new_filter)) {
err = -ENOMEM;
goto out_exit;
}
@@ -2500,9 +2540,9 @@ out_exit:
return err;
}
-static int perf_evsel__nr_addr_filter(struct evsel *evsel)
+static int evsel__nr_addr_filter(struct evsel *evsel)
{
- struct perf_pmu *pmu = perf_evsel__find_pmu(evsel);
+ struct perf_pmu *pmu = evsel__find_pmu(evsel);
int nr_addr_filters = 0;
if (!pmu)
@@ -2521,7 +2561,7 @@ int auxtrace_parse_filters(struct evlist *evlist)
evlist__for_each_entry(evlist, evsel) {
filter = evsel->filter;
- max_nr = perf_evsel__nr_addr_filter(evsel);
+ max_nr = evsel__nr_addr_filter(evsel);
if (!filter || !max_nr)
continue;
evsel->filter = NULL;
@@ -2577,3 +2617,12 @@ void auxtrace__free(struct perf_session *session)
return session->auxtrace->free(session);
}
+
+bool auxtrace__evsel_is_auxtrace(struct perf_session *session,
+ struct evsel *evsel)
+{
+ if (!session->auxtrace || !session->auxtrace->evsel_is_auxtrace)
+ return false;
+
+ return session->auxtrace->evsel_is_auxtrace(session, evsel);
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index e58ef160b599..0220a2e86c16 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -21,6 +21,7 @@
union perf_event;
struct perf_session;
struct evlist;
+struct evsel;
struct perf_tool;
struct mmap;
struct perf_sample;
@@ -73,8 +74,10 @@ enum itrace_period_type {
* @calls: limit branch samples to calls (can be combined with @returns)
* @returns: limit branch samples to returns (can be combined with @calls)
* @callchain: add callchain to 'instructions' events
+ * @add_callchain: add callchain to existing event records
* @thread_stack: feed branches to the thread_stack
* @last_branch: add branch context to 'instruction' events
+ * @add_last_branch: add branch context to existing event records
* @callchain_sz: maximum callchain size
* @last_branch_sz: branch context size
* @period: 'instructions' events period
@@ -100,8 +103,10 @@ struct itrace_synth_opts {
bool calls;
bool returns;
bool callchain;
+ bool add_callchain;
bool thread_stack;
bool last_branch;
+ bool add_last_branch;
unsigned int callchain_sz;
unsigned int last_branch_sz;
unsigned long long period;
@@ -166,6 +171,8 @@ struct auxtrace {
struct perf_tool *tool);
void (*free_events)(struct perf_session *session);
void (*free)(struct perf_session *session);
+ bool (*evsel_is_auxtrace)(struct perf_session *session,
+ struct evsel *evsel);
};
/**
@@ -584,6 +591,8 @@ void auxtrace__dump_auxtrace_sample(struct perf_session *session,
int auxtrace__flush_events(struct perf_session *session, struct perf_tool *tool);
void auxtrace__free_events(struct perf_session *session);
void auxtrace__free(struct perf_session *session);
+bool auxtrace__evsel_is_auxtrace(struct perf_session *session,
+ struct evsel *evsel);
#define ITRACE_HELP \
" i: synthesize instructions events\n" \
@@ -750,6 +759,13 @@ void auxtrace_index__free(struct list_head *head __maybe_unused)
}
static inline
+bool auxtrace__evsel_is_auxtrace(struct perf_session *session __maybe_unused,
+ struct evsel *evsel __maybe_unused)
+{
+ return false;
+}
+
+static inline
int auxtrace_parse_filters(struct evlist *evlist __maybe_unused)
{
return 0;
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index a3207d900339..3742511a08d1 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -6,6 +6,9 @@
#include <bpf/libbpf.h>
#include <linux/btf.h>
#include <linux/err.h>
+#include <linux/string.h>
+#include <internal/lib.h>
+#include <symbol/kallsyms.h>
#include "bpf-event.h"
#include "debug.h"
#include "dso.h"
@@ -290,11 +293,82 @@ out:
return err ? -1 : 0;
}
+struct kallsyms_parse {
+ union perf_event *event;
+ perf_event__handler_t process;
+ struct machine *machine;
+ struct perf_tool *tool;
+};
+
+static int
+process_bpf_image(char *name, u64 addr, struct kallsyms_parse *data)
+{
+ struct machine *machine = data->machine;
+ union perf_event *event = data->event;
+ struct perf_record_ksymbol *ksymbol;
+ int len;
+
+ ksymbol = &event->ksymbol;
+
+ *ksymbol = (struct perf_record_ksymbol) {
+ .header = {
+ .type = PERF_RECORD_KSYMBOL,
+ .size = offsetof(struct perf_record_ksymbol, name),
+ },
+ .addr = addr,
+ .len = page_size,
+ .ksym_type = PERF_RECORD_KSYMBOL_TYPE_BPF,
+ .flags = 0,
+ };
+
+ len = scnprintf(ksymbol->name, KSYM_NAME_LEN, "%s", name);
+ ksymbol->header.size += PERF_ALIGN(len + 1, sizeof(u64));
+ memset((void *) event + event->header.size, 0, machine->id_hdr_size);
+ event->header.size += machine->id_hdr_size;
+
+ return perf_tool__process_synth_event(data->tool, event, machine,
+ data->process);
+}
+
+static int
+kallsyms_process_symbol(void *data, const char *_name,
+ char type __maybe_unused, u64 start)
+{
+ char disp[KSYM_NAME_LEN];
+ char *module, *name;
+ unsigned long id;
+ int err = 0;
+
+ module = strchr(_name, '\t');
+ if (!module)
+ return 0;
+
+ /* We are going after [bpf] module ... */
+ if (strcmp(module + 1, "[bpf]"))
+ return 0;
+
+ name = memdup(_name, (module - _name) + 1);
+ if (!name)
+ return -ENOMEM;
+
+ name[module - _name] = 0;
+
+ /* .. and only for trampolines and dispatchers */
+ if ((sscanf(name, "bpf_trampoline_%lu", &id) == 1) ||
+ (sscanf(name, "bpf_dispatcher_%s", disp) == 1))
+ err = process_bpf_image(name, start, data);
+
+ free(name);
+ return err;
+}
+
int perf_event__synthesize_bpf_events(struct perf_session *session,
perf_event__handler_t process,
struct machine *machine,
struct record_opts *opts)
{
+ const char *kallsyms_filename = "/proc/kallsyms";
+ struct kallsyms_parse arg;
union perf_event *event;
__u32 id = 0;
int err;
@@ -303,6 +377,8 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
event = malloc(sizeof(event->bpf) + KSYM_NAME_LEN + machine->id_hdr_size);
if (!event)
return -1;
+
+ /* Synthesize all the bpf programs in system. */
while (true) {
err = bpf_prog_get_next_id(id, &id);
if (err) {
@@ -335,6 +411,23 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
break;
}
}
+
+ /* Synthesize all the bpf images - trampolines/dispatchers. */
+ if (symbol_conf.kallsyms_name != NULL)
+ kallsyms_filename = symbol_conf.kallsyms_name;
+
+ arg = (struct kallsyms_parse) {
+ .event = event,
+ .process = process,
+ .machine = machine,
+ .tool = session->tool,
+ };
+
+ if (kallsyms__parse(kallsyms_filename, &arg, kallsyms_process_symbol)) {
+ pr_err("%s: failed to synthesize bpf images: %s\n",
+ __func__, strerror(errno));
+ }
+
free(event);
return err;
}
@@ -416,8 +509,7 @@ static int bpf_event__sb_cb(union perf_event *event, void *data)
return 0;
}
-int bpf_event__add_sb_event(struct evlist **evlist,
- struct perf_env *env)
+int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)
{
struct perf_event_attr attr = {
.type = PERF_TYPE_SOFTWARE,
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index 81fdc88e6c1a..68f315c3df5b 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -33,8 +33,7 @@ struct btf_node {
#ifdef HAVE_LIBBPF_SUPPORT
int machine__process_bpf(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
-int bpf_event__add_sb_event(struct evlist **evlist,
- struct perf_env *env);
+int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env);
void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
struct perf_env *env,
FILE *fp);
@@ -46,8 +45,8 @@ static inline int machine__process_bpf(struct machine *machine __maybe_unused,
return 0;
}
-static inline int bpf_event__add_sb_event(struct evlist **evlist __maybe_unused,
- struct perf_env *env __maybe_unused)
+static inline int evlist__add_bpf_sb_event(struct evlist *evlist __maybe_unused,
+ struct perf_env *env __maybe_unused)
{
return 0;
}
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 10c187b8b8ea..83bfb8768235 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1430,7 +1430,7 @@ apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH;
}
- if (perf_evsel__is_bpf_output(evsel))
+ if (evsel__is_bpf_output(evsel))
check_pass = true;
if (attr->type == PERF_TYPE_RAW)
check_pass = true;
diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h
index 154a05cd03af..4d3f02fa223d 100644
--- a/tools/perf/util/branch.h
+++ b/tools/perf/util/branch.h
@@ -15,13 +15,18 @@
#include "event.h"
struct branch_flags {
- u64 mispred:1;
- u64 predicted:1;
- u64 in_tx:1;
- u64 abort:1;
- u64 cycles:16;
- u64 type:4;
- u64 reserved:40;
+ union {
+ u64 value;
+ struct {
+ u64 mispred:1;
+ u64 predicted:1;
+ u64 in_tx:1;
+ u64 abort:1;
+ u64 cycles:16;
+ u64 type:4;
+ u64 reserved:40;
+ };
+ };
};
struct branch_info {
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 706bb7bbe1e1..8f668ee29f25 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -143,6 +143,9 @@ struct callchain_cursor_node {
u64 ip;
struct map_symbol ms;
const char *srcline;
+ /* Indicate valid cursor node for LBR stitch */
+ bool valid;
+
bool branch;
struct branch_flags branch_flags;
u64 branch_from;
@@ -151,6 +154,11 @@ struct callchain_cursor_node {
struct callchain_cursor_node *next;
};
+struct stitch_list {
+ struct list_head node;
+ struct callchain_cursor_node cursor;
+};
+
struct callchain_cursor {
u64 nr;
struct callchain_cursor_node *first;
diff --git a/tools/perf/util/cap.h b/tools/perf/util/cap.h
index 051dc590ceee..ae52878c0b2e 100644
--- a/tools/perf/util/cap.h
+++ b/tools/perf/util/cap.h
@@ -29,4 +29,8 @@ static inline bool perf_cap__capable(int cap __maybe_unused)
#define CAP_SYSLOG 34
#endif
+#ifndef CAP_PERFMON
+#define CAP_PERFMON 38
+#endif
+
#endif /* __PERF_CAP_H */
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index b73fb7823048..050dea9f1e88 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -107,7 +107,8 @@ found:
static void cgroup__delete(struct cgroup *cgroup)
{
- close(cgroup->fd);
+ if (cgroup->fd >= 0)
+ close(cgroup->fd);
zfree(&cgroup->name);
free(cgroup);
}
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index a12872f2856a..6b3988a7aba8 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -28,7 +28,7 @@ int __weak sched_getcpu(void)
static int perf_flag_probe(void)
{
- /* use 'safest' configuration as used in perf_evsel__fallback() */
+ /* use 'safest' configuration as used in evsel__fallback() */
struct perf_event_attr attr = {
.type = PERF_TYPE_SOFTWARE,
.config = PERF_COUNT_SW_CPU_CLOCK,
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index cd92a99eb89d..cd007cc9c283 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -564,6 +564,8 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
resp = cs_etm_decoder__set_tid(etmq, packet_queue,
elem, trace_chan_id);
break;
+ /* Unused packet types */
+ case OCSD_GEN_TRC_ELEM_I_RANGE_NOPATH:
case OCSD_GEN_TRC_ELEM_ADDR_NACC:
case OCSD_GEN_TRC_ELEM_CYCLE_COUNT:
case OCSD_GEN_TRC_ELEM_ADDR_UNKNOWN:
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 62d2f9b9ce1b..c283223fb31f 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -94,6 +94,9 @@ struct cs_etm_queue {
struct cs_etm_traceid_queue **traceid_queues;
};
+/* RB tree for quick conversion between traceID and metadata pointers */
+static struct intlist *traceid_list;
+
static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
static int cs_etm__process_queues(struct cs_etm_auxtrace *etm);
static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
@@ -631,6 +634,16 @@ static void cs_etm__free(struct perf_session *session)
zfree(&aux);
}
+static bool cs_etm__evsel_is_auxtrace(struct perf_session *session,
+ struct evsel *evsel)
+{
+ struct cs_etm_auxtrace *aux = container_of(session->auxtrace,
+ struct cs_etm_auxtrace,
+ auxtrace);
+
+ return evsel->core.attr.type == aux->pmu_type;
+}
+
static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address)
{
struct machine *machine;
@@ -2618,6 +2631,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
etm->auxtrace.flush_events = cs_etm__flush_events;
etm->auxtrace.free_events = cs_etm__free_events;
etm->auxtrace.free = cs_etm__free;
+ etm->auxtrace.evsel_is_auxtrace = cs_etm__evsel_is_auxtrace;
session->auxtrace = &etm->auxtrace;
etm->unknown_thread = thread__new(999999999, 999999999);
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 650ecc2a6349..4ad925d6d799 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -114,9 +114,6 @@ enum cs_etm_isa {
CS_ETM_ISA_T32,
};
-/* RB tree for quick conversion between traceID and metadata pointers */
-struct intlist *traceid_list;
-
struct cs_etm_queue;
struct cs_etm_packet {
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index dbc772bfb04e..5f36fc6a5578 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -835,7 +835,7 @@ static int process_sample_event(struct perf_tool *tool,
return -1;
}
- if (perf_evsel__is_bpf_output(evsel)) {
+ if (evsel__is_bpf_output(evsel)) {
ret = add_bpf_output_values(event_class, event, sample);
if (ret)
return -1;
@@ -1155,7 +1155,7 @@ static int add_event(struct ctf_writer *cw, struct evsel *evsel)
{
struct bt_ctf_event_class *event_class;
struct evsel_priv *priv;
- const char *name = perf_evsel__name(evsel);
+ const char *name = evsel__name(evsel);
int ret;
pr("Adding event '%s' (type %d)\n", name, evsel->core.attr.type);
@@ -1174,7 +1174,7 @@ static int add_event(struct ctf_writer *cw, struct evsel *evsel)
goto err;
}
- if (perf_evsel__is_bpf_output(evsel)) {
+ if (evsel__is_bpf_output(evsel)) {
ret = add_bpf_output_types(cw, event_class);
if (ret)
goto err;
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 91f21239608b..f338990e0fe6 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -191,6 +191,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
case DSO_BINARY_TYPE__GUEST_KALLSYMS:
case DSO_BINARY_TYPE__JAVA_JIT:
case DSO_BINARY_TYPE__BPF_PROG_INFO:
+ case DSO_BINARY_TYPE__BPF_IMAGE:
case DSO_BINARY_TYPE__NOT_FOUND:
ret = -1;
break;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 2db64b79617a..9553a1fd9e8a 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -40,6 +40,7 @@ enum dso_binary_type {
DSO_BINARY_TYPE__GUEST_KCORE,
DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
DSO_BINARY_TYPE__BPF_PROG_INFO,
+ DSO_BINARY_TYPE__BPF_IMAGE,
DSO_BINARY_TYPE__NOT_FOUND,
};
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 7632075a8792..1ab2682d5d2b 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -48,6 +48,7 @@ struct perf_env {
char *cpuid;
unsigned long long total_mem;
unsigned int msr_pmu_type;
+ unsigned int max_branches;
int nr_cmdline;
int nr_sibling_cores;
@@ -57,12 +58,14 @@ struct perf_env {
int nr_memory_nodes;
int nr_pmu_mappings;
int nr_groups;
+ int nr_cpu_pmu_caps;
char *cmdline;
const char **cmdline_argv;
char *sibling_cores;
char *sibling_dies;
char *sibling_threads;
char *pmu_mappings;
+ char *cpu_pmu_caps;
struct cpu_topology_map *cpu;
struct cpu_cache_level *caches;
int caches_cnt;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index dc0e11214ae1..f581550a3015 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -626,7 +626,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
ret = strlist__has_entry(symbol_conf.sym_list,
al->sym->name);
}
- if (!(ret && al->sym)) {
+ if (!ret && al->sym) {
snprintf(al_addr_str, sz, "0x%"PRIx64,
al->map->unmap_ip(al->map, al->sym->start));
ret = strlist__has_entry(symbol_conf.sym_list,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 1548237b6558..0a0b760d6948 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -23,6 +23,7 @@
#include "asm/bug.h"
#include "bpf-event.h"
#include "util/string2.h"
+#include "util/perf_api_probe.h"
#include <signal.h>
#include <unistd.h>
#include <sched.h>
@@ -118,7 +119,7 @@ static void perf_evlist__update_id_pos(struct evlist *evlist)
struct evsel *evsel;
evlist__for_each_entry(evlist, evsel)
- perf_evsel__calc_id_pos(evsel);
+ evsel__calc_id_pos(evsel);
perf_evlist__set_id_pos(evlist);
}
@@ -390,14 +391,14 @@ void evlist__disable(struct evlist *evlist)
evlist__for_each_entry(evlist, pos) {
if (evsel__cpu_iter_skip(pos, cpu))
continue;
- if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd)
+ if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
continue;
evsel__disable_cpu(pos, pos->cpu_iter - 1);
}
}
affinity__cleanup(&affinity);
evlist__for_each_entry(evlist, pos) {
- if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
+ if (!evsel__is_group_leader(pos) || !pos->core.fd)
continue;
pos->disabled = true;
}
@@ -420,14 +421,14 @@ void evlist__enable(struct evlist *evlist)
evlist__for_each_entry(evlist, pos) {
if (evsel__cpu_iter_skip(pos, cpu))
continue;
- if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
+ if (!evsel__is_group_leader(pos) || !pos->core.fd)
continue;
evsel__enable_cpu(pos, pos->cpu_iter - 1);
}
}
affinity__cleanup(&affinity);
evlist__for_each_entry(evlist, pos) {
- if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
+ if (!evsel__is_group_leader(pos) || !pos->core.fd)
continue;
pos->disabled = false;
}
@@ -947,7 +948,7 @@ void __perf_evlist__set_sample_bit(struct evlist *evlist,
struct evsel *evsel;
evlist__for_each_entry(evlist, evsel)
- __perf_evsel__set_sample_bit(evsel, bit);
+ __evsel__set_sample_bit(evsel, bit);
}
void __perf_evlist__reset_sample_bit(struct evlist *evlist,
@@ -956,7 +957,7 @@ void __perf_evlist__reset_sample_bit(struct evlist *evlist,
struct evsel *evsel;
evlist__for_each_entry(evlist, evsel)
- __perf_evsel__reset_sample_bit(evsel, bit);
+ __evsel__reset_sample_bit(evsel, bit);
}
int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel)
@@ -994,7 +995,7 @@ int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter)
if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT)
continue;
- err = perf_evsel__set_filter(evsel, filter);
+ err = evsel__set_filter(evsel, filter);
if (err)
break;
}
@@ -1014,7 +1015,7 @@ int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter)
if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT)
continue;
- err = perf_evsel__append_tp_filter(evsel, filter);
+ err = evsel__append_tp_filter(evsel, filter);
if (err)
break;
}
@@ -1131,8 +1132,10 @@ bool perf_evlist__valid_read_format(struct evlist *evlist)
u64 sample_type = first->core.attr.sample_type;
evlist__for_each_entry(evlist, pos) {
- if (read_format != pos->core.attr.read_format)
- return false;
+ if (read_format != pos->core.attr.read_format) {
+ pr_debug("Read format differs %#" PRIx64 " vs %#" PRIx64 "\n",
+ read_format, (u64)pos->core.attr.read_format);
+ }
}
/* PERF_SAMPLE_READ imples PERF_FORMAT_ID. */
@@ -1436,7 +1439,7 @@ int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event,
if (!evsel)
return -EFAULT;
- return perf_evsel__parse_sample(evsel, event, sample);
+ return evsel__parse_sample(evsel, event, sample);
}
int perf_evlist__parse_sample_timestamp(struct evlist *evlist,
@@ -1447,7 +1450,7 @@ int perf_evlist__parse_sample_timestamp(struct evlist *evlist,
if (!evsel)
return -EFAULT;
- return perf_evsel__parse_sample_timestamp(evsel, event, timestamp);
+ return evsel__parse_sample_timestamp(evsel, event, timestamp);
}
int perf_evlist__strerror_open(struct evlist *evlist,
@@ -1701,133 +1704,3 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,
}
return leader;
}
-
-int perf_evlist__add_sb_event(struct evlist **evlist,
- struct perf_event_attr *attr,
- perf_evsel__sb_cb_t cb,
- void *data)
-{
- struct evsel *evsel;
- bool new_evlist = (*evlist) == NULL;
-
- if (*evlist == NULL)
- *evlist = evlist__new();
- if (*evlist == NULL)
- return -1;
-
- if (!attr->sample_id_all) {
- pr_warning("enabling sample_id_all for all side band events\n");
- attr->sample_id_all = 1;
- }
-
- evsel = perf_evsel__new_idx(attr, (*evlist)->core.nr_entries);
- if (!evsel)
- goto out_err;
-
- evsel->side_band.cb = cb;
- evsel->side_band.data = data;
- evlist__add(*evlist, evsel);
- return 0;
-
-out_err:
- if (new_evlist) {
- evlist__delete(*evlist);
- *evlist = NULL;
- }
- return -1;
-}
-
-static void *perf_evlist__poll_thread(void *arg)
-{
- struct evlist *evlist = arg;
- bool draining = false;
- int i, done = 0;
- /*
- * In order to read symbols from other namespaces perf to needs to call
- * setns(2). This isn't permitted if the struct_fs has multiple users.
- * unshare(2) the fs so that we may continue to setns into namespaces
- * that we're observing when, for instance, reading the build-ids at
- * the end of a 'perf record' session.
- */
- unshare(CLONE_FS);
-
- while (!done) {
- bool got_data = false;
-
- if (evlist->thread.done)
- draining = true;
-
- if (!draining)
- evlist__poll(evlist, 1000);
-
- for (i = 0; i < evlist->core.nr_mmaps; i++) {
- struct mmap *map = &evlist->mmap[i];
- union perf_event *event;
-
- if (perf_mmap__read_init(&map->core))
- continue;
- while ((event = perf_mmap__read_event(&map->core)) != NULL) {
- struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
-
- if (evsel && evsel->side_band.cb)
- evsel->side_band.cb(event, evsel->side_band.data);
- else
- pr_warning("cannot locate proper evsel for the side band event\n");
-
- perf_mmap__consume(&map->core);
- got_data = true;
- }
- perf_mmap__read_done(&map->core);
- }
-
- if (draining && !got_data)
- break;
- }
- return NULL;
-}
-
-int perf_evlist__start_sb_thread(struct evlist *evlist,
- struct target *target)
-{
- struct evsel *counter;
-
- if (!evlist)
- return 0;
-
- if (perf_evlist__create_maps(evlist, target))
- goto out_delete_evlist;
-
- evlist__for_each_entry(evlist, counter) {
- if (evsel__open(counter, evlist->core.cpus,
- evlist->core.threads) < 0)
- goto out_delete_evlist;
- }
-
- if (evlist__mmap(evlist, UINT_MAX))
- goto out_delete_evlist;
-
- evlist__for_each_entry(evlist, counter) {
- if (evsel__enable(counter))
- goto out_delete_evlist;
- }
-
- evlist->thread.done = 0;
- if (pthread_create(&evlist->thread.th, NULL, perf_evlist__poll_thread, evlist))
- goto out_delete_evlist;
-
- return 0;
-
-out_delete_evlist:
- evlist__delete(evlist);
- evlist = NULL;
- return -1;
-}
-
-void perf_evlist__stop_sb_thread(struct evlist *evlist)
-{
- if (!evlist)
- return;
- evlist->thread.done = 1;
- pthread_join(evlist->thread.th, NULL);
- evlist__delete(evlist);
-}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index f5bd5c386df1..b6f325dfb4d2 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -107,10 +107,11 @@ int __perf_evlist__add_default_attrs(struct evlist *evlist,
int perf_evlist__add_dummy(struct evlist *evlist);
-int perf_evlist__add_sb_event(struct evlist **evlist,
+int perf_evlist__add_sb_event(struct evlist *evlist,
struct perf_event_attr *attr,
- perf_evsel__sb_cb_t cb,
+ evsel__sb_cb_t cb,
void *data);
+void evlist__set_cb(struct evlist *evlist, evsel__sb_cb_t cb, void *data);
int perf_evlist__start_sb_thread(struct evlist *evlist,
struct target *target);
void perf_evlist__stop_sb_thread(struct evlist *evlist);
@@ -173,10 +174,6 @@ void evlist__close(struct evlist *evlist);
struct callchain_param;
void perf_evlist__set_id_pos(struct evlist *evlist);
-bool perf_can_sample_identifier(void);
-bool perf_can_record_switch_events(void);
-bool perf_can_record_cpu_wide(void);
-bool perf_can_aux_sample(void);
void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
struct callchain_param *callchain);
int record_opts__config(struct record_opts *opts);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index eb880efbce16..f3e60c45d59a 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -102,7 +102,7 @@ set_methods:
#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y))
-int __perf_evsel__sample_size(u64 sample_type)
+int __evsel__sample_size(u64 sample_type)
{
u64 mask = sample_type & PERF_SAMPLE_MASK;
int size = 0;
@@ -178,53 +178,53 @@ static int __perf_evsel__calc_is_pos(u64 sample_type)
return idx;
}
-void perf_evsel__calc_id_pos(struct evsel *evsel)
+void evsel__calc_id_pos(struct evsel *evsel)
{
evsel->id_pos = __perf_evsel__calc_id_pos(evsel->core.attr.sample_type);
evsel->is_pos = __perf_evsel__calc_is_pos(evsel->core.attr.sample_type);
}
-void __perf_evsel__set_sample_bit(struct evsel *evsel,
+void __evsel__set_sample_bit(struct evsel *evsel,
enum perf_event_sample_format bit)
{
if (!(evsel->core.attr.sample_type & bit)) {
evsel->core.attr.sample_type |= bit;
evsel->sample_size += sizeof(u64);
- perf_evsel__calc_id_pos(evsel);
+ evsel__calc_id_pos(evsel);
}
}
-void __perf_evsel__reset_sample_bit(struct evsel *evsel,
+void __evsel__reset_sample_bit(struct evsel *evsel,
enum perf_event_sample_format bit)
{
if (evsel->core.attr.sample_type & bit) {
evsel->core.attr.sample_type &= ~bit;
evsel->sample_size -= sizeof(u64);
- perf_evsel__calc_id_pos(evsel);
+ evsel__calc_id_pos(evsel);
}
}
-void perf_evsel__set_sample_id(struct evsel *evsel,
+void evsel__set_sample_id(struct evsel *evsel,
bool can_sample_identifier)
{
if (can_sample_identifier) {
- perf_evsel__reset_sample_bit(evsel, ID);
- perf_evsel__set_sample_bit(evsel, IDENTIFIER);
+ evsel__reset_sample_bit(evsel, ID);
+ evsel__set_sample_bit(evsel, IDENTIFIER);
} else {
- perf_evsel__set_sample_bit(evsel, ID);
+ evsel__set_sample_bit(evsel, ID);
}
evsel->core.attr.read_format |= PERF_FORMAT_ID;
}
/**
- * perf_evsel__is_function_event - Return whether given evsel is a function
+ * evsel__is_function_event - Return whether given evsel is a function
* trace event
*
* @evsel - evsel selector to be tested
*
* Return %true if event is function trace event
*/
-bool perf_evsel__is_function_event(struct evsel *evsel)
+bool evsel__is_function_event(struct evsel *evsel)
{
#define FUNCTION_EVENT "ftrace:function"
@@ -249,8 +249,8 @@ void evsel__init(struct evsel *evsel,
evsel->bpf_fd = -1;
INIT_LIST_HEAD(&evsel->config_terms);
perf_evsel__object.init(evsel);
- evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
- perf_evsel__calc_id_pos(evsel);
+ evsel->sample_size = __evsel__sample_size(attr->sample_type);
+ evsel__calc_id_pos(evsel);
evsel->cmdline_group_boundary = false;
evsel->metric_expr = NULL;
evsel->metric_name = NULL;
@@ -267,13 +267,13 @@ struct evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
return NULL;
evsel__init(evsel, attr, idx);
- if (perf_evsel__is_bpf_output(evsel)) {
+ if (evsel__is_bpf_output(evsel)) {
evsel->core.attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD),
evsel->core.attr.sample_period = 1;
}
- if (perf_evsel__is_clock(evsel)) {
+ if (evsel__is_clock(evsel)) {
/*
* The evsel->unit points to static alias->unit
* so it's ok to use static string in here.
@@ -385,7 +385,7 @@ const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = {
"ref-cycles",
};
-static const char *__perf_evsel__hw_name(u64 config)
+static const char *__evsel__hw_name(u64 config)
{
if (config < PERF_COUNT_HW_MAX && perf_evsel__hw_names[config])
return perf_evsel__hw_names[config];
@@ -429,9 +429,9 @@ static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)
return r;
}
-static int perf_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
+static int evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
{
- int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->core.attr.config));
+ int r = scnprintf(bf, size, "%s", __evsel__hw_name(evsel->core.attr.config));
return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
}
@@ -448,20 +448,20 @@ const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = {
"dummy",
};
-static const char *__perf_evsel__sw_name(u64 config)
+static const char *__evsel__sw_name(u64 config)
{
if (config < PERF_COUNT_SW_MAX && perf_evsel__sw_names[config])
return perf_evsel__sw_names[config];
return "unknown-software";
}
-static int perf_evsel__sw_name(struct evsel *evsel, char *bf, size_t size)
+static int evsel__sw_name(struct evsel *evsel, char *bf, size_t size)
{
- int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->core.attr.config));
+ int r = scnprintf(bf, size, "%s", __evsel__sw_name(evsel->core.attr.config));
return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
}
-static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
+static int __evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
{
int r;
@@ -479,10 +479,10 @@ static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
return r;
}
-static int perf_evsel__bp_name(struct evsel *evsel, char *bf, size_t size)
+static int evsel__bp_name(struct evsel *evsel, char *bf, size_t size)
{
struct perf_event_attr *attr = &evsel->core.attr;
- int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
+ int r = __evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
}
@@ -531,7 +531,7 @@ static unsigned long perf_evsel__hw_cache_stat[C(MAX)] = {
[C(NODE)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
};
-bool perf_evsel__is_cache_op_valid(u8 type, u8 op)
+bool evsel__is_cache_op_valid(u8 type, u8 op)
{
if (perf_evsel__hw_cache_stat[type] & COP(op))
return true; /* valid */
@@ -539,8 +539,7 @@ bool perf_evsel__is_cache_op_valid(u8 type, u8 op)
return false; /* invalid */
}
-int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
- char *bf, size_t size)
+int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size)
{
if (result) {
return scnprintf(bf, size, "%s-%s-%s", perf_evsel__hw_cache[type][0],
@@ -552,7 +551,7 @@ int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
perf_evsel__hw_cache_op[op][1]);
}
-static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size)
+static int __evsel__hw_cache_name(u64 config, char *bf, size_t size)
{
u8 op, result, type = (config >> 0) & 0xff;
const char *err = "unknown-ext-hardware-cache-type";
@@ -571,33 +570,33 @@ static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size)
goto out_err;
err = "invalid-cache";
- if (!perf_evsel__is_cache_op_valid(type, op))
+ if (!evsel__is_cache_op_valid(type, op))
goto out_err;
- return __perf_evsel__hw_cache_type_op_res_name(type, op, result, bf, size);
+ return __evsel__hw_cache_type_op_res_name(type, op, result, bf, size);
out_err:
return scnprintf(bf, size, "%s", err);
}
-static int perf_evsel__hw_cache_name(struct evsel *evsel, char *bf, size_t size)
+static int evsel__hw_cache_name(struct evsel *evsel, char *bf, size_t size)
{
- int ret = __perf_evsel__hw_cache_name(evsel->core.attr.config, bf, size);
+ int ret = __evsel__hw_cache_name(evsel->core.attr.config, bf, size);
return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
}
-static int perf_evsel__raw_name(struct evsel *evsel, char *bf, size_t size)
+static int evsel__raw_name(struct evsel *evsel, char *bf, size_t size)
{
int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->core.attr.config);
return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
}
-static int perf_evsel__tool_name(char *bf, size_t size)
+static int evsel__tool_name(char *bf, size_t size)
{
int ret = scnprintf(bf, size, "duration_time");
return ret;
}
-const char *perf_evsel__name(struct evsel *evsel)
+const char *evsel__name(struct evsel *evsel)
{
char bf[128];
@@ -609,22 +608,22 @@ const char *perf_evsel__name(struct evsel *evsel)
switch (evsel->core.attr.type) {
case PERF_TYPE_RAW:
- perf_evsel__raw_name(evsel, bf, sizeof(bf));
+ evsel__raw_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_HARDWARE:
- perf_evsel__hw_name(evsel, bf, sizeof(bf));
+ evsel__hw_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_HW_CACHE:
- perf_evsel__hw_cache_name(evsel, bf, sizeof(bf));
+ evsel__hw_cache_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_SOFTWARE:
if (evsel->tool_event)
- perf_evsel__tool_name(bf, sizeof(bf));
+ evsel__tool_name(bf, sizeof(bf));
else
- perf_evsel__sw_name(evsel, bf, sizeof(bf));
+ evsel__sw_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_TRACEPOINT:
@@ -632,7 +631,7 @@ const char *perf_evsel__name(struct evsel *evsel)
break;
case PERF_TYPE_BREAKPOINT:
- perf_evsel__bp_name(evsel, bf, sizeof(bf));
+ evsel__bp_name(evsel, bf, sizeof(bf));
break;
default:
@@ -649,7 +648,7 @@ out_unknown:
return "unknown";
}
-const char *perf_evsel__group_name(struct evsel *evsel)
+const char *evsel__group_name(struct evsel *evsel)
{
return evsel->group_name ?: "anon group";
}
@@ -664,21 +663,19 @@ const char *perf_evsel__group_name(struct evsel *evsel)
* For record -e 'cycles,instructions' and report --group
* 'cycles:u, instructions:u'
*/
-int perf_evsel__group_desc(struct evsel *evsel, char *buf, size_t size)
+int evsel__group_desc(struct evsel *evsel, char *buf, size_t size)
{
int ret = 0;
struct evsel *pos;
- const char *group_name = perf_evsel__group_name(evsel);
+ const char *group_name = evsel__group_name(evsel);
if (!evsel->forced_leader)
ret = scnprintf(buf, size, "%s { ", group_name);
- ret += scnprintf(buf + ret, size - ret, "%s",
- perf_evsel__name(evsel));
+ ret += scnprintf(buf + ret, size - ret, "%s", evsel__name(evsel));
for_each_group_member(pos, evsel)
- ret += scnprintf(buf + ret, size - ret, ", %s",
- perf_evsel__name(pos));
+ ret += scnprintf(buf + ret, size - ret, ", %s", evsel__name(pos));
if (!evsel->forced_leader)
ret += scnprintf(buf + ret, size - ret, " }");
@@ -686,14 +683,13 @@ int perf_evsel__group_desc(struct evsel *evsel, char *buf, size_t size)
return ret;
}
-static void __perf_evsel__config_callchain(struct evsel *evsel,
- struct record_opts *opts,
- struct callchain_param *param)
+static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *opts,
+ struct callchain_param *param)
{
- bool function = perf_evsel__is_function_event(evsel);
+ bool function = evsel__is_function_event(evsel);
struct perf_event_attr *attr = &evsel->core.attr;
- perf_evsel__set_sample_bit(evsel, CALLCHAIN);
+ evsel__set_sample_bit(evsel, CALLCHAIN);
attr->sample_max_stack = param->max_stack;
@@ -708,7 +704,7 @@ static void __perf_evsel__config_callchain(struct evsel *evsel,
"to get user callchain information. "
"Falling back to framepointers.\n");
} else {
- perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
+ evsel__set_sample_bit(evsel, BRANCH_STACK);
attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER |
PERF_SAMPLE_BRANCH_CALL_STACK |
PERF_SAMPLE_BRANCH_NO_CYCLES |
@@ -722,8 +718,8 @@ static void __perf_evsel__config_callchain(struct evsel *evsel,
if (param->record_mode == CALLCHAIN_DWARF) {
if (!function) {
- perf_evsel__set_sample_bit(evsel, REGS_USER);
- perf_evsel__set_sample_bit(evsel, STACK_USER);
+ evsel__set_sample_bit(evsel, REGS_USER);
+ evsel__set_sample_bit(evsel, STACK_USER);
if (opts->sample_user_regs && DWARF_MINIMAL_REGS != PERF_REGS_MASK) {
attr->sample_regs_user |= DWARF_MINIMAL_REGS;
pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, "
@@ -746,12 +742,11 @@ static void __perf_evsel__config_callchain(struct evsel *evsel,
}
}
-void perf_evsel__config_callchain(struct evsel *evsel,
- struct record_opts *opts,
- struct callchain_param *param)
+void evsel__config_callchain(struct evsel *evsel, struct record_opts *opts,
+ struct callchain_param *param)
{
if (param->enabled)
- return __perf_evsel__config_callchain(evsel, opts, param);
+ return __evsel__config_callchain(evsel, opts, param);
}
static void
@@ -760,16 +755,16 @@ perf_evsel__reset_callgraph(struct evsel *evsel,
{
struct perf_event_attr *attr = &evsel->core.attr;
- perf_evsel__reset_sample_bit(evsel, CALLCHAIN);
+ evsel__reset_sample_bit(evsel, CALLCHAIN);
if (param->record_mode == CALLCHAIN_LBR) {
- perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
+ evsel__reset_sample_bit(evsel, BRANCH_STACK);
attr->branch_sample_type &= ~(PERF_SAMPLE_BRANCH_USER |
PERF_SAMPLE_BRANCH_CALL_STACK |
PERF_SAMPLE_BRANCH_HW_INDEX);
}
if (param->record_mode == CALLCHAIN_DWARF) {
- perf_evsel__reset_sample_bit(evsel, REGS_USER);
- perf_evsel__reset_sample_bit(evsel, STACK_USER);
+ evsel__reset_sample_bit(evsel, REGS_USER);
+ evsel__reset_sample_bit(evsel, STACK_USER);
}
}
@@ -793,32 +788,32 @@ static void apply_config_terms(struct evsel *evsel,
if (!(term->weak && opts->user_interval != ULLONG_MAX)) {
attr->sample_period = term->val.period;
attr->freq = 0;
- perf_evsel__reset_sample_bit(evsel, PERIOD);
+ evsel__reset_sample_bit(evsel, PERIOD);
}
break;
case PERF_EVSEL__CONFIG_TERM_FREQ:
if (!(term->weak && opts->user_freq != UINT_MAX)) {
attr->sample_freq = term->val.freq;
attr->freq = 1;
- perf_evsel__set_sample_bit(evsel, PERIOD);
+ evsel__set_sample_bit(evsel, PERIOD);
}
break;
case PERF_EVSEL__CONFIG_TERM_TIME:
if (term->val.time)
- perf_evsel__set_sample_bit(evsel, TIME);
+ evsel__set_sample_bit(evsel, TIME);
else
- perf_evsel__reset_sample_bit(evsel, TIME);
+ evsel__reset_sample_bit(evsel, TIME);
break;
case PERF_EVSEL__CONFIG_TERM_CALLGRAPH:
callgraph_buf = term->val.str;
break;
case PERF_EVSEL__CONFIG_TERM_BRANCH:
if (term->val.str && strcmp(term->val.str, "no")) {
- perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
+ evsel__set_sample_bit(evsel, BRANCH_STACK);
parse_branch_str(term->val.str,
&attr->branch_sample_type);
} else
- perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
+ evsel__reset_sample_bit(evsel, BRANCH_STACK);
break;
case PERF_EVSEL__CONFIG_TERM_STACK_USER:
dump_size = term->val.stack_user;
@@ -832,7 +827,7 @@ static void apply_config_terms(struct evsel *evsel,
case PERF_EVSEL__CONFIG_TERM_INHERIT:
/*
* attr->inherit should has already been set by
- * perf_evsel__config. If user explicitly set
+ * evsel__config. If user explicitly set
* inherit using config terms, override global
* opt->no_inherit setting.
*/
@@ -897,11 +892,11 @@ static void apply_config_terms(struct evsel *evsel,
/* set perf-event callgraph */
if (param.enabled) {
if (sample_address) {
- perf_evsel__set_sample_bit(evsel, ADDR);
- perf_evsel__set_sample_bit(evsel, DATA_SRC);
+ evsel__set_sample_bit(evsel, ADDR);
+ evsel__set_sample_bit(evsel, DATA_SRC);
evsel->core.attr.mmap_data = track;
}
- perf_evsel__config_callchain(evsel, opts, &param);
+ evsel__config_callchain(evsel, opts, &param);
}
}
}
@@ -953,8 +948,8 @@ struct perf_evsel_config_term *__perf_evsel__get_config_term(struct evsel *evsel
* enable/disable events specifically, as there's no
* initial traced exec call.
*/
-void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
- struct callchain_param *callchain)
+void evsel__config(struct evsel *evsel, struct record_opts *opts,
+ struct callchain_param *callchain)
{
struct evsel *leader = evsel->leader;
struct perf_event_attr *attr = &evsel->core.attr;
@@ -965,17 +960,17 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
attr->inherit = !opts->no_inherit;
attr->write_backward = opts->overwrite ? 1 : 0;
- perf_evsel__set_sample_bit(evsel, IP);
- perf_evsel__set_sample_bit(evsel, TID);
+ evsel__set_sample_bit(evsel, IP);
+ evsel__set_sample_bit(evsel, TID);
if (evsel->sample_read) {
- perf_evsel__set_sample_bit(evsel, READ);
+ evsel__set_sample_bit(evsel, READ);
/*
* We need ID even in case of single event, because
* PERF_SAMPLE_READ process ID specific data.
*/
- perf_evsel__set_sample_id(evsel, false);
+ evsel__set_sample_id(evsel, false);
/*
* Apply group format only if we belong to group
@@ -994,7 +989,7 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
opts->user_interval != ULLONG_MAX)) {
if (opts->freq) {
- perf_evsel__set_sample_bit(evsel, PERIOD);
+ evsel__set_sample_bit(evsel, PERIOD);
attr->freq = 1;
attr->sample_freq = opts->freq;
} else {
@@ -1002,25 +997,6 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
}
}
- /*
- * Disable sampling for all group members other
- * than leader in case leader 'leads' the sampling.
- */
- if ((leader != evsel) && leader->sample_read) {
- attr->freq = 0;
- attr->sample_freq = 0;
- attr->sample_period = 0;
- attr->write_backward = 0;
-
- /*
- * We don't get sample for slave events, we make them
- * when delivering group leader sample. Set the slave
- * event to follow the master sample_type to ease up
- * report.
- */
- attr->sample_type = leader->core.attr.sample_type;
- }
-
if (opts->no_samples)
attr->sample_freq = 0;
@@ -1033,7 +1009,7 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
}
if (opts->sample_address) {
- perf_evsel__set_sample_bit(evsel, ADDR);
+ evsel__set_sample_bit(evsel, ADDR);
attr->mmap_data = track;
}
@@ -1042,24 +1018,24 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
* event, due to issues with page faults while tracing page
* fault handler and its overall trickiness nature.
*/
- if (perf_evsel__is_function_event(evsel))
+ if (evsel__is_function_event(evsel))
evsel->core.attr.exclude_callchain_user = 1;
if (callchain && callchain->enabled && !evsel->no_aux_samples)
- perf_evsel__config_callchain(evsel, opts, callchain);
+ evsel__config_callchain(evsel, opts, callchain);
if (opts->sample_intr_regs) {
attr->sample_regs_intr = opts->sample_intr_regs;
- perf_evsel__set_sample_bit(evsel, REGS_INTR);
+ evsel__set_sample_bit(evsel, REGS_INTR);
}
if (opts->sample_user_regs) {
attr->sample_regs_user |= opts->sample_user_regs;
- perf_evsel__set_sample_bit(evsel, REGS_USER);
+ evsel__set_sample_bit(evsel, REGS_USER);
}
if (target__has_cpu(&opts->target) || opts->sample_cpu)
- perf_evsel__set_sample_bit(evsel, CPU);
+ evsel__set_sample_bit(evsel, CPU);
/*
* When the user explicitly disabled time don't force it here.
@@ -1068,31 +1044,31 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
(!perf_missing_features.sample_id_all &&
(!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu ||
opts->sample_time_set)))
- perf_evsel__set_sample_bit(evsel, TIME);
+ evsel__set_sample_bit(evsel, TIME);
if (opts->raw_samples && !evsel->no_aux_samples) {
- perf_evsel__set_sample_bit(evsel, TIME);
- perf_evsel__set_sample_bit(evsel, RAW);
- perf_evsel__set_sample_bit(evsel, CPU);
+ evsel__set_sample_bit(evsel, TIME);
+ evsel__set_sample_bit(evsel, RAW);
+ evsel__set_sample_bit(evsel, CPU);
}
if (opts->sample_address)
- perf_evsel__set_sample_bit(evsel, DATA_SRC);
+ evsel__set_sample_bit(evsel, DATA_SRC);
if (opts->sample_phys_addr)
- perf_evsel__set_sample_bit(evsel, PHYS_ADDR);
+ evsel__set_sample_bit(evsel, PHYS_ADDR);
if (opts->no_buffering) {
attr->watermark = 0;
attr->wakeup_events = 1;
}
if (opts->branch_stack && !evsel->no_aux_samples) {
- perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
+ evsel__set_sample_bit(evsel, BRANCH_STACK);
attr->branch_sample_type = opts->branch_stack;
}
if (opts->sample_weight)
- perf_evsel__set_sample_bit(evsel, WEIGHT);
+ evsel__set_sample_bit(evsel, WEIGHT);
attr->task = track;
attr->mmap = track;
@@ -1106,14 +1082,14 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
if (opts->record_cgroup) {
attr->cgroup = track && !perf_missing_features.cgroup;
- perf_evsel__set_sample_bit(evsel, CGROUP);
+ evsel__set_sample_bit(evsel, CGROUP);
}
if (opts->record_switch_events)
attr->context_switch = track;
if (opts->sample_transaction)
- perf_evsel__set_sample_bit(evsel, TRANSACTION);
+ evsel__set_sample_bit(evsel, TRANSACTION);
if (opts->running_time) {
evsel->core.attr.read_format |=
@@ -1127,15 +1103,15 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
* Disabling only independent events or group leaders,
* keeping group members enabled.
*/
- if (perf_evsel__is_group_leader(evsel))
+ if (evsel__is_group_leader(evsel))
attr->disabled = 1;
/*
* Setting enable_on_exec for independent events and
* group leaders for traced executed by perf.
*/
- if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) &&
- !opts->initial_delay)
+ if (target__none(&opts->target) && evsel__is_group_leader(evsel) &&
+ !opts->initial_delay)
attr->enable_on_exec = 1;
if (evsel->immediate) {
@@ -1176,9 +1152,9 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
/* The --period option takes the precedence. */
if (opts->period_set) {
if (opts->period)
- perf_evsel__set_sample_bit(evsel, PERIOD);
+ evsel__set_sample_bit(evsel, PERIOD);
else
- perf_evsel__reset_sample_bit(evsel, PERIOD);
+ evsel__reset_sample_bit(evsel, PERIOD);
}
/*
@@ -1187,10 +1163,10 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
* if BRANCH_STACK bit is set.
*/
if (opts->initial_delay && is_dummy_event(evsel))
- perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
+ evsel__reset_sample_bit(evsel, BRANCH_STACK);
}
-int perf_evsel__set_filter(struct evsel *evsel, const char *filter)
+int evsel__set_filter(struct evsel *evsel, const char *filter)
{
char *new_filter = strdup(filter);
@@ -1203,13 +1179,12 @@ int perf_evsel__set_filter(struct evsel *evsel, const char *filter)
return -1;
}
-static int perf_evsel__append_filter(struct evsel *evsel,
- const char *fmt, const char *filter)
+static int evsel__append_filter(struct evsel *evsel, const char *fmt, const char *filter)
{
char *new_filter;
if (evsel->filter == NULL)
- return perf_evsel__set_filter(evsel, filter);
+ return evsel__set_filter(evsel, filter);
if (asprintf(&new_filter, fmt, evsel->filter, filter) > 0) {
free(evsel->filter);
@@ -1220,14 +1195,14 @@ static int perf_evsel__append_filter(struct evsel *evsel,
return -1;
}
-int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter)
+int evsel__append_tp_filter(struct evsel *evsel, const char *filter)
{
- return perf_evsel__append_filter(evsel, "(%s) && (%s)", filter);
+ return evsel__append_filter(evsel, "(%s) && (%s)", filter);
}
-int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter)
+int evsel__append_addr_filter(struct evsel *evsel, const char *filter)
{
- return perf_evsel__append_filter(evsel, "%s,%s", filter);
+ return evsel__append_filter(evsel, "%s,%s", filter);
}
/* Caller has to clear disabled after going through all CPUs. */
@@ -1278,7 +1253,7 @@ static void perf_evsel__free_config_terms(struct evsel *evsel)
}
}
-void perf_evsel__exit(struct evsel *evsel)
+void evsel__exit(struct evsel *evsel)
{
assert(list_empty(&evsel->core.node));
assert(evsel->evlist == NULL);
@@ -1298,12 +1273,12 @@ void perf_evsel__exit(struct evsel *evsel)
void evsel__delete(struct evsel *evsel)
{
- perf_evsel__exit(evsel);
+ evsel__exit(evsel);
free(evsel);
}
-void perf_evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
- struct perf_counts_values *count)
+void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
+ struct perf_counts_values *count)
{
struct perf_counts_values tmp;
@@ -1342,8 +1317,7 @@ void perf_counts_values__scale(struct perf_counts_values *count,
*pscaled = scaled;
}
-static int
-perf_evsel__read_one(struct evsel *evsel, int cpu, int thread)
+static int evsel__read_one(struct evsel *evsel, int cpu, int thread)
{
struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread);
@@ -1403,8 +1377,7 @@ perf_evsel__process_group_data(struct evsel *leader,
return 0;
}
-static int
-perf_evsel__read_group(struct evsel *leader, int cpu, int thread)
+static int evsel__read_group(struct evsel *leader, int cpu, int thread)
{
struct perf_stat_evsel *ps = leader->stats;
u64 read_format = leader->core.attr.read_format;
@@ -1414,7 +1387,7 @@ perf_evsel__read_group(struct evsel *leader, int cpu, int thread)
if (!(read_format & PERF_FORMAT_ID))
return -EINVAL;
- if (!perf_evsel__is_group_leader(leader))
+ if (!evsel__is_group_leader(leader))
return -EINVAL;
if (!data) {
@@ -1434,18 +1407,17 @@ perf_evsel__read_group(struct evsel *leader, int cpu, int thread)
return perf_evsel__process_group_data(leader, cpu, thread, data);
}
-int perf_evsel__read_counter(struct evsel *evsel, int cpu, int thread)
+int evsel__read_counter(struct evsel *evsel, int cpu, int thread)
{
u64 read_format = evsel->core.attr.read_format;
if (read_format & PERF_FORMAT_GROUP)
- return perf_evsel__read_group(evsel, cpu, thread);
- else
- return perf_evsel__read_one(evsel, cpu, thread);
+ return evsel__read_group(evsel, cpu, thread);
+
+ return evsel__read_one(evsel, cpu, thread);
}
-int __perf_evsel__read_on_cpu(struct evsel *evsel,
- int cpu, int thread, bool scale)
+int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale)
{
struct perf_counts_values count;
size_t nv = scale ? 3 : 1;
@@ -1459,7 +1431,7 @@ int __perf_evsel__read_on_cpu(struct evsel *evsel,
if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0)
return -errno;
- perf_evsel__compute_deltas(evsel, cpu, thread, &count);
+ evsel__compute_deltas(evsel, cpu, thread, &count);
perf_counts_values__scale(&count, scale, NULL);
*perf_counts(evsel->counts, cpu, thread) = count;
return 0;
@@ -1470,7 +1442,7 @@ static int get_group_fd(struct evsel *evsel, int cpu, int thread)
struct evsel *leader = evsel->leader;
int fd;
- if (perf_evsel__is_group_leader(evsel))
+ if (evsel__is_group_leader(evsel))
return -1;
/*
@@ -1749,8 +1721,7 @@ retry_open:
/*
* If we succeeded but had to kill clockid, fail and
- * have perf_evsel__open_strerror() print us a nice
- * error.
+ * have evsel__open_strerror() print us a nice error.
*/
if (perf_missing_features.clockid ||
perf_missing_features.clockid_wrong) {
@@ -1854,7 +1825,7 @@ try_fallback:
} else if (!perf_missing_features.group_read &&
evsel->core.attr.inherit &&
(evsel->core.attr.read_format & PERF_FORMAT_GROUP) &&
- perf_evsel__is_group_leader(evsel)) {
+ evsel__is_group_leader(evsel)) {
perf_missing_features.group_read = true;
pr_debug2_peo("switching off group read\n");
goto fallback_missing_features;
@@ -1888,9 +1859,7 @@ void evsel__close(struct evsel *evsel)
perf_evsel__free_id(&evsel->core);
}
-int perf_evsel__open_per_cpu(struct evsel *evsel,
- struct perf_cpu_map *cpus,
- int cpu)
+int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu)
{
if (cpu == -1)
return evsel__open_cpu(evsel, cpus, NULL, 0,
@@ -1899,8 +1868,7 @@ int perf_evsel__open_per_cpu(struct evsel *evsel,
return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1);
}
-int perf_evsel__open_per_thread(struct evsel *evsel,
- struct perf_thread_map *threads)
+int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads)
{
return evsel__open(evsel, NULL, threads);
}
@@ -1995,8 +1963,8 @@ perf_event__check_size(union perf_event *event, unsigned int sample_size)
return 0;
}
-int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
- struct perf_sample *data)
+int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
+ struct perf_sample *data)
{
u64 type = evsel->core.attr.sample_type;
bool swapped = evsel->needs_swap;
@@ -2136,7 +2104,7 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
}
}
- if (evsel__has_callchain(evsel)) {
+ if (type & PERF_SAMPLE_CALLCHAIN) {
const u64 max_callchain_nr = UINT64_MAX / sizeof(u64);
OVERFLOW_CHECK_u64(array);
@@ -2190,7 +2158,7 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
return -EFAULT;
sz = data->branch_stack->nr * sizeof(struct branch_entry);
- if (perf_evsel__has_branch_hw_idx(evsel))
+ if (evsel__has_branch_hw_idx(evsel))
sz += sizeof(u64);
else
data->no_hw_idx = true;
@@ -2298,9 +2266,8 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
return 0;
}
-int perf_evsel__parse_sample_timestamp(struct evsel *evsel,
- union perf_event *event,
- u64 *timestamp)
+int evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event,
+ u64 *timestamp)
{
u64 type = evsel->core.attr.sample_type;
const __u64 *array;
@@ -2342,15 +2309,14 @@ int perf_evsel__parse_sample_timestamp(struct evsel *evsel,
return 0;
}
-struct tep_format_field *perf_evsel__field(struct evsel *evsel, const char *name)
+struct tep_format_field *evsel__field(struct evsel *evsel, const char *name)
{
return tep_find_field(evsel->tp_format, name);
}
-void *perf_evsel__rawptr(struct evsel *evsel, struct perf_sample *sample,
- const char *name)
+void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name)
{
- struct tep_format_field *field = perf_evsel__field(evsel, name);
+ struct tep_format_field *field = evsel__field(evsel, name);
int offset;
if (!field)
@@ -2405,10 +2371,9 @@ u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sam
return 0;
}
-u64 perf_evsel__intval(struct evsel *evsel, struct perf_sample *sample,
- const char *name)
+u64 evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *name)
{
- struct tep_format_field *field = perf_evsel__field(evsel, name);
+ struct tep_format_field *field = evsel__field(evsel, name);
if (!field)
return 0;
@@ -2416,8 +2381,7 @@ u64 perf_evsel__intval(struct evsel *evsel, struct perf_sample *sample,
return field ? format_field__intval(field, sample, evsel->needs_swap) : 0;
}
-bool perf_evsel__fallback(struct evsel *evsel, int err,
- char *msg, size_t msgsize)
+bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize)
{
int paranoid;
@@ -2442,10 +2406,14 @@ bool perf_evsel__fallback(struct evsel *evsel, int err,
return true;
} else if (err == EACCES && !evsel->core.attr.exclude_kernel &&
(paranoid = perf_event_paranoid()) > 1) {
- const char *name = perf_evsel__name(evsel);
+ const char *name = evsel__name(evsel);
char *new_name;
const char *sep = ":";
+ /* If event has exclude user then don't exclude kernel. */
+ if (evsel->core.attr.exclude_user)
+ return false;
+
/* Is there already the separator in the name. */
if (strchr(name, '/') ||
strchr(name, ':'))
@@ -2505,8 +2473,8 @@ static bool find_process(const char *name)
return ret ? false : true;
}
-int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
- int err, char *msg, size_t size)
+int evsel__open_strerror(struct evsel *evsel, struct target *target,
+ int err, char *msg, size_t size)
{
char sbuf[STRERR_BUFSIZE];
int printed = 0;
@@ -2516,28 +2484,26 @@ int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
case EACCES:
if (err == EPERM)
printed = scnprintf(msg, size,
- "No permission to enable %s event.\n\n",
- perf_evsel__name(evsel));
+ "No permission to enable %s event.\n\n", evsel__name(evsel));
return scnprintf(msg + printed, size - printed,
"You may not have permission to collect %sstats.\n\n"
"Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
"which controls use of the performance events system by\n"
- "unprivileged users (without CAP_SYS_ADMIN).\n\n"
+ "unprivileged users (without CAP_PERFMON or CAP_SYS_ADMIN).\n\n"
"The current value is %d:\n\n"
" -1: Allow use of (almost) all events by all users\n"
" Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n"
- ">= 0: Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN\n"
- " Disallow raw tracepoint access by users without CAP_SYS_ADMIN\n"
- ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
- ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n"
+ ">= 0: Disallow ftrace function tracepoint by users without CAP_PERFMON or CAP_SYS_ADMIN\n"
+ " Disallow raw tracepoint access by users without CAP_SYS_PERFMON or CAP_SYS_ADMIN\n"
+ ">= 1: Disallow CPU event access by users without CAP_PERFMON or CAP_SYS_ADMIN\n"
+ ">= 2: Disallow kernel profiling by users without CAP_PERFMON or CAP_SYS_ADMIN\n\n"
"To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n"
" kernel.perf_event_paranoid = -1\n" ,
target->system_wide ? "system-wide " : "",
perf_event_paranoid());
case ENOENT:
- return scnprintf(msg, size, "The %s event is not supported.",
- perf_evsel__name(evsel));
+ return scnprintf(msg, size, "The %s event is not supported.", evsel__name(evsel));
case EMFILE:
return scnprintf(msg, size, "%s",
"Too many events are opened.\n"
@@ -2561,7 +2527,7 @@ int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
if (evsel->core.attr.sample_period != 0)
return scnprintf(msg, size,
"%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'",
- perf_evsel__name(evsel));
+ evsel__name(evsel));
if (evsel->core.attr.precise_ip)
return scnprintf(msg, size, "%s",
"\'precise\' request may not be supported. Try removing 'p' modifier.");
@@ -2594,11 +2560,10 @@ int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
return scnprintf(msg, size,
"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
"/bin/dmesg | grep -i perf may provide additional information.\n",
- err, str_error_r(err, sbuf, sizeof(sbuf)),
- perf_evsel__name(evsel));
+ err, str_error_r(err, sbuf, sizeof(sbuf)), evsel__name(evsel));
}
-struct perf_env *perf_evsel__env(struct evsel *evsel)
+struct perf_env *evsel__env(struct evsel *evsel)
{
if (evsel && evsel->evlist)
return evsel->evlist->env;
@@ -2623,7 +2588,7 @@ static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist)
return 0;
}
-int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist)
+int evsel__store_ids(struct evsel *evsel, struct evlist *evlist)
{
struct perf_cpu_map *cpus = evsel->core.cpus;
struct perf_thread_map *threads = evsel->core.threads;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 53187c501ee8..351c0aaf2a11 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -18,7 +18,7 @@ struct perf_counts;
struct perf_stat_evsel;
union perf_event;
-typedef int (perf_evsel__sb_cb_t)(union perf_event *event, void *data);
+typedef int (evsel__sb_cb_t)(union perf_event *event, void *data);
enum perf_tool_event {
PERF_TOOL_NONE = 0,
@@ -101,9 +101,17 @@ struct evsel {
int cpu_iter;
const char *pmu_name;
struct {
- perf_evsel__sb_cb_t *cb;
- void *data;
+ evsel__sb_cb_t *cb;
+ void *data;
} side_band;
+ /*
+ * For reporting purposes, an evsel sample can have a callchain
+ * synthesized from AUX area data. Keep track of synthesized sample
+ * types here. Note, the recorded sample_type cannot be changed because
+ * it is needed to continue to parse events.
+ * See also evsel__has_callchain().
+ */
+ __u64 synth_sample_type;
};
struct perf_missing_features {
@@ -135,7 +143,7 @@ static inline struct perf_cpu_map *evsel__cpus(struct evsel *evsel)
return perf_evsel__cpus(&evsel->core);
}
-static inline int perf_evsel__nr_cpus(struct evsel *evsel)
+static inline int evsel__nr_cpus(struct evsel *evsel)
{
return evsel__cpus(evsel)->nr;
}
@@ -143,13 +151,16 @@ static inline int perf_evsel__nr_cpus(struct evsel *evsel)
void perf_counts_values__scale(struct perf_counts_values *count,
bool scale, s8 *pscaled);
-void perf_evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
- struct perf_counts_values *count);
+void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
+ struct perf_counts_values *count);
int perf_evsel__object_config(size_t object_size,
int (*init)(struct evsel *evsel),
void (*fini)(struct evsel *evsel));
+struct perf_pmu *evsel__find_pmu(struct evsel *evsel);
+bool evsel__is_aux_event(struct evsel *evsel);
+
struct evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx);
static inline struct evsel *evsel__new(struct perf_event_attr *attr)
@@ -172,22 +183,20 @@ struct evsel *perf_evsel__new_cycles(bool precise);
struct tep_event *event_format__new(const char *sys, const char *name);
void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx);
-void perf_evsel__exit(struct evsel *evsel);
+void evsel__exit(struct evsel *evsel);
void evsel__delete(struct evsel *evsel);
struct callchain_param;
-void perf_evsel__config(struct evsel *evsel,
- struct record_opts *opts,
- struct callchain_param *callchain);
-void perf_evsel__config_callchain(struct evsel *evsel,
- struct record_opts *opts,
- struct callchain_param *callchain);
+void evsel__config(struct evsel *evsel, struct record_opts *opts,
+ struct callchain_param *callchain);
+void evsel__config_callchain(struct evsel *evsel, struct record_opts *opts,
+ struct callchain_param *callchain);
-int __perf_evsel__sample_size(u64 sample_type);
-void perf_evsel__calc_id_pos(struct evsel *evsel);
+int __evsel__sample_size(u64 sample_type);
+void evsel__calc_id_pos(struct evsel *evsel);
-bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
+bool evsel__is_cache_op_valid(u8 type, u8 op);
#define PERF_EVSEL__MAX_ALIASES 8
@@ -199,177 +208,153 @@ extern const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
[PERF_EVSEL__MAX_ALIASES];
extern const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX];
extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX];
-int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
- char *bf, size_t size);
-const char *perf_evsel__name(struct evsel *evsel);
+int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size);
+const char *evsel__name(struct evsel *evsel);
-const char *perf_evsel__group_name(struct evsel *evsel);
-int perf_evsel__group_desc(struct evsel *evsel, char *buf, size_t size);
+const char *evsel__group_name(struct evsel *evsel);
+int evsel__group_desc(struct evsel *evsel, char *buf, size_t size);
-void __perf_evsel__set_sample_bit(struct evsel *evsel,
- enum perf_event_sample_format bit);
-void __perf_evsel__reset_sample_bit(struct evsel *evsel,
- enum perf_event_sample_format bit);
+void __evsel__set_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit);
+void __evsel__reset_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit);
-#define perf_evsel__set_sample_bit(evsel, bit) \
- __perf_evsel__set_sample_bit(evsel, PERF_SAMPLE_##bit)
+#define evsel__set_sample_bit(evsel, bit) \
+ __evsel__set_sample_bit(evsel, PERF_SAMPLE_##bit)
-#define perf_evsel__reset_sample_bit(evsel, bit) \
- __perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
+#define evsel__reset_sample_bit(evsel, bit) \
+ __evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
-void perf_evsel__set_sample_id(struct evsel *evsel,
- bool use_sample_identifier);
+void evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier);
-int perf_evsel__set_filter(struct evsel *evsel, const char *filter);
-int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter);
-int perf_evsel__append_addr_filter(struct evsel *evsel,
- const char *filter);
+int evsel__set_filter(struct evsel *evsel, const char *filter);
+int evsel__append_tp_filter(struct evsel *evsel, const char *filter);
+int evsel__append_addr_filter(struct evsel *evsel, const char *filter);
int evsel__enable_cpu(struct evsel *evsel, int cpu);
int evsel__enable(struct evsel *evsel);
int evsel__disable(struct evsel *evsel);
int evsel__disable_cpu(struct evsel *evsel, int cpu);
-int perf_evsel__open_per_cpu(struct evsel *evsel,
- struct perf_cpu_map *cpus,
- int cpu);
-int perf_evsel__open_per_thread(struct evsel *evsel,
- struct perf_thread_map *threads);
+int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu);
+int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads);
int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads);
void evsel__close(struct evsel *evsel);
struct perf_sample;
-void *perf_evsel__rawptr(struct evsel *evsel, struct perf_sample *sample,
- const char *name);
-u64 perf_evsel__intval(struct evsel *evsel, struct perf_sample *sample,
- const char *name);
+void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name);
+u64 evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *name);
-static inline char *perf_evsel__strval(struct evsel *evsel,
- struct perf_sample *sample,
- const char *name)
+static inline char *evsel__strval(struct evsel *evsel, struct perf_sample *sample, const char *name)
{
- return perf_evsel__rawptr(evsel, sample, name);
+ return evsel__rawptr(evsel, sample, name);
}
struct tep_format_field;
u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap);
-struct tep_format_field *perf_evsel__field(struct evsel *evsel, const char *name);
+struct tep_format_field *evsel__field(struct evsel *evsel, const char *name);
-#define perf_evsel__match(evsel, t, c) \
+#define evsel__match(evsel, t, c) \
(evsel->core.attr.type == PERF_TYPE_##t && \
evsel->core.attr.config == PERF_COUNT_##c)
-static inline bool perf_evsel__match2(struct evsel *e1,
- struct evsel *e2)
+static inline bool evsel__match2(struct evsel *e1, struct evsel *e2)
{
return (e1->core.attr.type == e2->core.attr.type) &&
(e1->core.attr.config == e2->core.attr.config);
}
-#define perf_evsel__cmp(a, b) \
- ((a) && \
- (b) && \
- (a)->core.attr.type == (b)->core.attr.type && \
- (a)->core.attr.config == (b)->core.attr.config)
-
-int perf_evsel__read_counter(struct evsel *evsel, int cpu, int thread);
+int evsel__read_counter(struct evsel *evsel, int cpu, int thread);
-int __perf_evsel__read_on_cpu(struct evsel *evsel,
- int cpu, int thread, bool scale);
+int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale);
/**
- * perf_evsel__read_on_cpu - Read out the results on a CPU and thread
+ * evsel__read_on_cpu - Read out the results on a CPU and thread
*
* @evsel - event selector to read value
* @cpu - CPU of interest
* @thread - thread of interest
*/
-static inline int perf_evsel__read_on_cpu(struct evsel *evsel,
- int cpu, int thread)
+static inline int evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread)
{
- return __perf_evsel__read_on_cpu(evsel, cpu, thread, false);
+ return __evsel__read_on_cpu(evsel, cpu, thread, false);
}
/**
- * perf_evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled
+ * evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled
*
* @evsel - event selector to read value
* @cpu - CPU of interest
* @thread - thread of interest
*/
-static inline int perf_evsel__read_on_cpu_scaled(struct evsel *evsel,
- int cpu, int thread)
+static inline int evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu, int thread)
{
- return __perf_evsel__read_on_cpu(evsel, cpu, thread, true);
+ return __evsel__read_on_cpu(evsel, cpu, thread, true);
}
-int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
- struct perf_sample *sample);
+int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
+ struct perf_sample *sample);
-int perf_evsel__parse_sample_timestamp(struct evsel *evsel,
- union perf_event *event,
- u64 *timestamp);
+int evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event,
+ u64 *timestamp);
-static inline struct evsel *perf_evsel__next(struct evsel *evsel)
+static inline struct evsel *evsel__next(struct evsel *evsel)
{
return list_entry(evsel->core.node.next, struct evsel, core.node);
}
-static inline struct evsel *perf_evsel__prev(struct evsel *evsel)
+static inline struct evsel *evsel__prev(struct evsel *evsel)
{
return list_entry(evsel->core.node.prev, struct evsel, core.node);
}
/**
- * perf_evsel__is_group_leader - Return whether given evsel is a leader event
+ * evsel__is_group_leader - Return whether given evsel is a leader event
*
* @evsel - evsel selector to be tested
*
* Return %true if @evsel is a group leader or a stand-alone event
*/
-static inline bool perf_evsel__is_group_leader(const struct evsel *evsel)
+static inline bool evsel__is_group_leader(const struct evsel *evsel)
{
return evsel->leader == evsel;
}
/**
- * perf_evsel__is_group_event - Return whether given evsel is a group event
+ * evsel__is_group_event - Return whether given evsel is a group event
*
* @evsel - evsel selector to be tested
*
* Return %true iff event group view is enabled and @evsel is a actual group
* leader which has other members in the group
*/
-static inline bool perf_evsel__is_group_event(struct evsel *evsel)
+static inline bool evsel__is_group_event(struct evsel *evsel)
{
if (!symbol_conf.event_group)
return false;
- return perf_evsel__is_group_leader(evsel) && evsel->core.nr_members > 1;
+ return evsel__is_group_leader(evsel) && evsel->core.nr_members > 1;
}
-bool perf_evsel__is_function_event(struct evsel *evsel);
+bool evsel__is_function_event(struct evsel *evsel);
-static inline bool perf_evsel__is_bpf_output(struct evsel *evsel)
+static inline bool evsel__is_bpf_output(struct evsel *evsel)
{
- return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT);
+ return evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT);
}
-static inline bool perf_evsel__is_clock(struct evsel *evsel)
+static inline bool evsel__is_clock(struct evsel *evsel)
{
- return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
- perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
+ return evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
+ evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
}
-bool perf_evsel__fallback(struct evsel *evsel, int err,
- char *msg, size_t msgsize);
-int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
- int err, char *msg, size_t size);
+bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize);
+int evsel__open_strerror(struct evsel *evsel, struct target *target,
+ int err, char *msg, size_t size);
-static inline int perf_evsel__group_idx(struct evsel *evsel)
+static inline int evsel__group_idx(struct evsel *evsel)
{
return evsel->idx - evsel->leader->idx;
}
@@ -386,22 +371,37 @@ for ((_evsel) = _leader; \
(_evsel) && (_evsel)->leader == (_leader); \
(_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node))
-static inline bool perf_evsel__has_branch_callstack(const struct evsel *evsel)
+static inline bool evsel__has_branch_callstack(const struct evsel *evsel)
{
return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
}
-static inline bool perf_evsel__has_branch_hw_idx(const struct evsel *evsel)
+static inline bool evsel__has_branch_hw_idx(const struct evsel *evsel)
{
return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
}
static inline bool evsel__has_callchain(const struct evsel *evsel)
{
- return (evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0;
+ /*
+ * For reporting purposes, an evsel sample can have a recorded callchain
+ * or a callchain synthesized from AUX area data.
+ */
+ return evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN ||
+ evsel->synth_sample_type & PERF_SAMPLE_CALLCHAIN;
+}
+
+static inline bool evsel__has_br_stack(const struct evsel *evsel)
+{
+ /*
+ * For reporting purposes, an evsel sample can have a recorded branch
+ * stack or a branch stack synthesized from AUX area data.
+ */
+ return evsel->core.attr.sample_type & PERF_SAMPLE_BRANCH_STACK ||
+ evsel->synth_sample_type & PERF_SAMPLE_BRANCH_STACK;
}
-struct perf_env *perf_evsel__env(struct evsel *evsel);
+struct perf_env *evsel__env(struct evsel *evsel);
-int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist);
+int evsel__store_ids(struct evsel *evsel, struct evlist *evlist);
#endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h
index e026ab67b008..f8938916577c 100644
--- a/tools/perf/util/evsel_config.h
+++ b/tools/perf/util/evsel_config.h
@@ -7,7 +7,7 @@
/*
* The 'struct perf_evsel_config_term' is used to pass event
- * specific configuration data to perf_evsel__config routine.
+ * specific configuration data to evsel__config routine.
* It is allocated within event parsing and attached to
* perf_evsel::config_terms list head.
*/
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 3b4842840db0..99aed708bd5a 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -44,22 +44,22 @@ int perf_evsel__fprintf(struct evsel *evsel,
if (details->event_group) {
struct evsel *pos;
- if (!perf_evsel__is_group_leader(evsel))
+ if (!evsel__is_group_leader(evsel))
return 0;
if (evsel->core.nr_members > 1)
printed += fprintf(fp, "%s{", evsel->group_name ?: "");
- printed += fprintf(fp, "%s", perf_evsel__name(evsel));
+ printed += fprintf(fp, "%s", evsel__name(evsel));
for_each_group_member(pos, evsel)
- printed += fprintf(fp, ",%s", perf_evsel__name(pos));
+ printed += fprintf(fp, ",%s", evsel__name(pos));
if (evsel->core.nr_members > 1)
printed += fprintf(fp, "}");
goto out;
}
- printed += fprintf(fp, "%s", perf_evsel__name(evsel));
+ printed += fprintf(fp, "%s", evsel__name(evsel));
if (details->verbose) {
printed += perf_event_attr__fprintf(fp, &evsel->core.attr,
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index fd192ddf93c1..aa631e37ad1e 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -3,7 +3,6 @@
#include <assert.h>
#include "expr.h"
#include "expr-bison.h"
-#define YY_EXTRA_TYPE int
#include "expr-flex.h"
#ifdef PARSER_DEBUG
@@ -11,7 +10,7 @@ extern int expr_debug;
#endif
/* Caller must make sure id is allocated */
-void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
+void expr__add_id(struct expr_parse_ctx *ctx, const char *name, double val)
{
int idx;
@@ -21,20 +20,24 @@ void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
ctx->ids[idx].val = val;
}
-void expr__ctx_init(struct parse_ctx *ctx)
+void expr__ctx_init(struct expr_parse_ctx *ctx)
{
ctx->num_ids = 0;
}
static int
-__expr__parse(double *val, struct parse_ctx *ctx, const char *expr,
- int start)
+__expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr,
+ int start, int runtime)
{
+ struct expr_scanner_ctx scanner_ctx = {
+ .start_token = start,
+ .runtime = runtime,
+ };
YY_BUFFER_STATE buffer;
void *scanner;
int ret;
- ret = expr_lex_init_extra(start, &scanner);
+ ret = expr_lex_init_extra(&scanner_ctx, &scanner);
if (ret)
return ret;
@@ -52,9 +55,9 @@ __expr__parse(double *val, struct parse_ctx *ctx, const char *expr,
return ret;
}
-int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr)
+int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr, int runtime)
{
- return __expr__parse(final_val, ctx, expr, EXPR_PARSE) ? -1 : 0;
+ return __expr__parse(final_val, ctx, expr, EXPR_PARSE, runtime) ? -1 : 0;
}
static bool
@@ -72,13 +75,13 @@ already_seen(const char *val, const char *one, const char **other,
}
int expr__find_other(const char *expr, const char *one, const char ***other,
- int *num_other)
+ int *num_other, int runtime)
{
int err, i = 0, j = 0;
- struct parse_ctx ctx;
+ struct expr_parse_ctx ctx;
expr__ctx_init(&ctx);
- err = __expr__parse(NULL, &ctx, expr, EXPR_OTHER);
+ err = __expr__parse(NULL, &ctx, expr, EXPR_OTHER, runtime);
if (err)
return -1;
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index 9377538f4097..87d627bb699b 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -5,20 +5,25 @@
#define EXPR_MAX_OTHER 20
#define MAX_PARSE_ID EXPR_MAX_OTHER
-struct parse_id {
+struct expr_parse_id {
const char *name;
double val;
};
-struct parse_ctx {
+struct expr_parse_ctx {
int num_ids;
- struct parse_id ids[MAX_PARSE_ID];
+ struct expr_parse_id ids[MAX_PARSE_ID];
};
-void expr__ctx_init(struct parse_ctx *ctx);
-void expr__add_id(struct parse_ctx *ctx, const char *id, double val);
-int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr);
+struct expr_scanner_ctx {
+ int start_token;
+ int runtime;
+};
+
+void expr__ctx_init(struct expr_parse_ctx *ctx);
+void expr__add_id(struct expr_parse_ctx *ctx, const char *id, double val);
+int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr, int runtime);
int expr__find_other(const char *expr, const char *one, const char ***other,
- int *num_other);
+ int *num_other, int runtime);
#endif
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
index eaad29243c23..74b9b59b1aa5 100644
--- a/tools/perf/util/expr.l
+++ b/tools/perf/util/expr.l
@@ -35,7 +35,7 @@ static int value(yyscan_t scanner, int base)
* Allow @ instead of / to be able to specify pmu/event/ without
* conflicts with normal division.
*/
-static char *normalize(char *str)
+static char *normalize(char *str, int runtime)
{
char *ret = str;
char *dst = str;
@@ -45,6 +45,19 @@ static char *normalize(char *str)
*dst++ = '/';
else if (*str == '\\')
*dst++ = *++str;
+ else if (*str == '?') {
+ char *paramval;
+ int i = 0;
+ int size = asprintf(&paramval, "%d", runtime);
+
+ if (size < 0)
+ *dst++ = '0';
+ else {
+ while (i < size)
+ *dst++ = paramval[i++];
+ free(paramval);
+ }
+ }
else
*dst++ = *str;
str++;
@@ -54,16 +67,16 @@ static char *normalize(char *str)
return ret;
}
-static int str(yyscan_t scanner, int token)
+static int str(yyscan_t scanner, int token, int runtime)
{
YYSTYPE *yylval = expr_get_lval(scanner);
char *text = expr_get_text(scanner);
- yylval->str = normalize(strdup(text));
+ yylval->str = normalize(strdup(text), runtime);
if (!yylval->str)
return EXPR_ERROR;
- yylval->str = normalize(yylval->str);
+ yylval->str = normalize(yylval->str, runtime);
return token;
}
%}
@@ -72,17 +85,17 @@ number [0-9]+
sch [-,=]
spec \\{sch}
-sym [0-9a-zA-Z_\.:@]+
-symbol {spec}*{sym}*{spec}*{sym}*
+sym [0-9a-zA-Z_\.:@?]+
+symbol {spec}*{sym}*{spec}*{sym}*{spec}*{sym}
%%
- {
- int start_token;
+ struct expr_scanner_ctx *sctx = expr_get_extra(yyscanner);
- start_token = expr_get_extra(yyscanner);
+ {
+ int start_token = sctx->start_token;
- if (start_token) {
- expr_set_extra(NULL, yyscanner);
+ if (sctx->start_token) {
+ sctx->start_token = 0;
return start_token;
}
}
@@ -93,7 +106,7 @@ if { return IF; }
else { return ELSE; }
#smt_on { return SMT_ON; }
{number} { return value(yyscanner, 10); }
-{symbol} { return str(yyscanner, ID); }
+{symbol} { return str(yyscanner, ID, sctx->runtime); }
"|" { return '|'; }
"^" { return '^'; }
"&" { return '&'; }
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index 4720cbe79357..cd17486c1c5d 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -15,7 +15,7 @@
%define api.pure full
%parse-param { double *final_val }
-%parse-param { struct parse_ctx *ctx }
+%parse-param { struct expr_parse_ctx *ctx }
%parse-param {void *scanner}
%lex-param {void* scanner}
@@ -39,14 +39,14 @@
%{
static void expr_error(double *final_val __maybe_unused,
- struct parse_ctx *ctx __maybe_unused,
+ struct expr_parse_ctx *ctx __maybe_unused,
void *scanner,
const char *s)
{
pr_debug("%s\n", s);
}
-static int lookup_id(struct parse_ctx *ctx, char *id, double *val)
+static int lookup_id(struct expr_parse_ctx *ctx, char *id, double *val)
{
int i;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index acbd046bf95c..0ce47283a8a1 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -525,7 +525,7 @@ static int write_event_desc(struct feat_fd *ff,
/*
* write event string as passed on cmdline
*/
- ret = do_write_string(ff, perf_evsel__name(evsel));
+ ret = do_write_string(ff, evsel__name(evsel));
if (ret < 0)
return ret;
/*
@@ -783,8 +783,7 @@ static int write_group_desc(struct feat_fd *ff,
return ret;
evlist__for_each_entry(evlist, evsel) {
- if (perf_evsel__is_group_leader(evsel) &&
- evsel->core.nr_members > 1) {
+ if (evsel__is_group_leader(evsel) && evsel->core.nr_members > 1) {
const char *name = evsel->group_name ?: "{anon_group}";
u32 leader_idx = evsel->idx;
u32 nr_members = evsel->core.nr_members;
@@ -1395,6 +1394,38 @@ static int write_compressed(struct feat_fd *ff __maybe_unused,
return do_write(ff, &(ff->ph->env.comp_mmap_len), sizeof(ff->ph->env.comp_mmap_len));
}
+static int write_cpu_pmu_caps(struct feat_fd *ff,
+ struct evlist *evlist __maybe_unused)
+{
+ struct perf_pmu *cpu_pmu = perf_pmu__find("cpu");
+ struct perf_pmu_caps *caps = NULL;
+ int nr_caps;
+ int ret;
+
+ if (!cpu_pmu)
+ return -ENOENT;
+
+ nr_caps = perf_pmu__caps_parse(cpu_pmu);
+ if (nr_caps < 0)
+ return nr_caps;
+
+ ret = do_write(ff, &nr_caps, sizeof(nr_caps));
+ if (ret < 0)
+ return ret;
+
+ list_for_each_entry(caps, &cpu_pmu->caps, list) {
+ ret = do_write_string(ff, caps->name);
+ if (ret < 0)
+ return ret;
+
+ ret = do_write_string(ff, caps->value);
+ if (ret < 0)
+ return ret;
+ }
+
+ return ret;
+}
+
static void print_hostname(struct feat_fd *ff, FILE *fp)
{
fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname);
@@ -1809,6 +1840,27 @@ static void print_compressed(struct feat_fd *ff, FILE *fp)
ff->ph->env.comp_level, ff->ph->env.comp_ratio);
}
+static void print_cpu_pmu_caps(struct feat_fd *ff, FILE *fp)
+{
+ const char *delimiter = "# cpu pmu capabilities: ";
+ u32 nr_caps = ff->ph->env.nr_cpu_pmu_caps;
+ char *str;
+
+ if (!nr_caps) {
+ fprintf(fp, "# cpu pmu capabilities: not available\n");
+ return;
+ }
+
+ str = ff->ph->env.cpu_pmu_caps;
+ while (nr_caps--) {
+ fprintf(fp, "%s%s", delimiter, str);
+ delimiter = ", ";
+ str += strlen(str) + 1;
+ }
+
+ fprintf(fp, "\n");
+}
+
static void print_pmu_mappings(struct feat_fd *ff, FILE *fp)
{
const char *delimiter = "# pmu mappings: ";
@@ -1854,14 +1906,12 @@ static void print_group_desc(struct feat_fd *ff, FILE *fp)
session = container_of(ff->ph, struct perf_session, header);
evlist__for_each_entry(session->evlist, evsel) {
- if (perf_evsel__is_group_leader(evsel) &&
- evsel->core.nr_members > 1) {
- fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
- perf_evsel__name(evsel));
+ if (evsel__is_group_leader(evsel) && evsel->core.nr_members > 1) {
+ fprintf(fp, "# group: %s{%s", evsel->group_name ?: "", evsel__name(evsel));
nr = evsel->core.nr_members - 1;
} else if (nr) {
- fprintf(fp, ",%s", perf_evsel__name(evsel));
+ fprintf(fp, ",%s", evsel__name(evsel));
if (--nr == 0)
fprintf(fp, "}\n");
@@ -2846,6 +2896,60 @@ static int process_compressed(struct feat_fd *ff,
return 0;
}
+static int process_cpu_pmu_caps(struct feat_fd *ff,
+ void *data __maybe_unused)
+{
+ char *name, *value;
+ struct strbuf sb;
+ u32 nr_caps;
+
+ if (do_read_u32(ff, &nr_caps))
+ return -1;
+
+ if (!nr_caps) {
+ pr_debug("cpu pmu capabilities not available\n");
+ return 0;
+ }
+
+ ff->ph->env.nr_cpu_pmu_caps = nr_caps;
+
+ if (strbuf_init(&sb, 128) < 0)
+ return -1;
+
+ while (nr_caps--) {
+ name = do_read_string(ff);
+ if (!name)
+ goto error;
+
+ value = do_read_string(ff);
+ if (!value)
+ goto free_name;
+
+ if (strbuf_addf(&sb, "%s=%s", name, value) < 0)
+ goto free_value;
+
+ /* include a NULL character at the end */
+ if (strbuf_add(&sb, "", 1) < 0)
+ goto free_value;
+
+ if (!strcmp(name, "branches"))
+ ff->ph->env.max_branches = atoi(value);
+
+ free(value);
+ free(name);
+ }
+ ff->ph->env.cpu_pmu_caps = strbuf_detach(&sb, NULL);
+ return 0;
+
+free_value:
+ free(value);
+free_name:
+ free(name);
+error:
+ strbuf_release(&sb);
+ return -1;
+}
+
#define FEAT_OPR(n, func, __full_only) \
[HEADER_##n] = { \
.name = __stringify(n), \
@@ -2903,6 +3007,7 @@ const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = {
FEAT_OPR(BPF_PROG_INFO, bpf_prog_info, false),
FEAT_OPR(BPF_BTF, bpf_btf, false),
FEAT_OPR(COMPRESSED, compressed, false),
+ FEAT_OPR(CPU_PMU_CAPS, cpu_pmu_caps, false),
};
struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 840f95cee349..650bd1c7a99b 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -43,6 +43,7 @@ enum {
HEADER_BPF_PROG_INFO,
HEADER_BPF_BTF,
HEADER_COMPRESSED,
+ HEADER_CPU_PMU_CAPS,
HEADER_LAST_FEATURE,
HEADER_FEAT_BITS = 256,
};
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 283a69ff6a3d..12b65d00cf65 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1070,6 +1070,20 @@ iter_next_cumulative_entry(struct hist_entry_iter *iter,
return fill_callchain_info(al, node, iter->hide_unresolved);
}
+static bool
+hist_entry__fast__sym_diff(struct hist_entry *left,
+ struct hist_entry *right)
+{
+ struct symbol *sym_l = left->ms.sym;
+ struct symbol *sym_r = right->ms.sym;
+
+ if (!sym_l && !sym_r)
+ return left->ip != right->ip;
+
+ return !!_sort__sym_cmp(sym_l, sym_r);
+}
+
+
static int
iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
struct addr_location *al)
@@ -1096,6 +1110,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
};
int i;
struct callchain_cursor cursor;
+ bool fast = hists__has(he_tmp.hists, sym);
callchain_cursor_snapshot(&cursor, &callchain_cursor);
@@ -1106,6 +1121,14 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
* It's possible that it has cycles or recursive calls.
*/
for (i = 0; i < iter->curr; i++) {
+ /*
+ * For most cases, there are no duplicate entries in callchain.
+ * The symbols are usually different. Do a quick check for
+ * symbols first.
+ */
+ if (fast && hist_entry__fast__sym_diff(he_cache[i], &he_tmp))
+ continue;
+
if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) {
/* to avoid calling callback function */
iter->he = NULL;
@@ -2637,7 +2660,7 @@ size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp)
size_t ret = 0;
evlist__for_each_entry(evlist, pos) {
- ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
+ ret += fprintf(fp, "%s stats:\n", evsel__name(pos));
ret += events_stats__fprintf(&evsel__hists(pos)->stats, fp);
}
@@ -2661,7 +2684,7 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh
unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
u64 nr_events = hists->stats.total_period;
struct evsel *evsel = hists_to_evsel(hists);
- const char *ev_name = perf_evsel__name(evsel);
+ const char *ev_name = evsel__name(evsel);
char buf[512], sample_freq_str[64] = "";
size_t buflen = sizeof(buf);
char ref[30] = " show reference callgraph, ";
@@ -2672,10 +2695,10 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh
nr_events = hists->stats.total_non_filtered_period;
}
- if (perf_evsel__is_group_event(evsel)) {
+ if (evsel__is_group_event(evsel)) {
struct evsel *pos;
- perf_evsel__group_desc(evsel, buf, buflen);
+ evsel__group_desc(evsel, buf, buflen);
ev_name = buf;
for_each_group_member(pos, evsel) {
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 34cb380d19a3..af1e78d76228 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -432,7 +432,7 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
le64_to_cpu(branch->from),
le64_to_cpu(branch->to),
btsq->intel_pt_insn.length,
- buffer->buffer_nr + 1);
+ buffer->buffer_nr + 1, true, 0, 0);
if (filter && !(filter & btsq->sample_flags))
continue;
err = intel_bts_synth_branch_sample(btsq, branch);
@@ -728,6 +728,15 @@ static void intel_bts_free(struct perf_session *session)
free(bts);
}
+static bool intel_bts_evsel_is_auxtrace(struct perf_session *session,
+ struct evsel *evsel)
+{
+ struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
+ auxtrace);
+
+ return evsel->core.attr.type == bts->pmu_type;
+}
+
struct intel_bts_synth {
struct perf_tool dummy_tool;
struct perf_session *session;
@@ -816,10 +825,10 @@ static int intel_bts_synth_events(struct intel_bts *bts,
bts->branches_id = id;
/*
* We only use sample types from PERF_SAMPLE_MASK so we can use
- * __perf_evsel__sample_size() here.
+ * __evsel__sample_size() here.
*/
bts->branches_event_size = sizeof(struct perf_record_sample) +
- __perf_evsel__sample_size(attr.sample_type);
+ __evsel__sample_size(attr.sample_type);
}
return 0;
@@ -883,6 +892,7 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
bts->auxtrace.flush_events = intel_bts_flush;
bts->auxtrace.free_events = intel_bts_free_events;
bts->auxtrace.free = intel_bts_free;
+ bts->auxtrace.evsel_is_auxtrace = intel_bts_evsel_is_auxtrace;
session->auxtrace = &bts->auxtrace;
intel_bts_print_info(&auxtrace_info->priv[0], INTEL_BTS_PMU_TYPE,
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index 0ccf10a0bf44..4ce109993e74 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -552,7 +552,7 @@ static int intel_pt_do_get_packet(const unsigned char *buf, size_t len,
break;
default:
break;
- };
+ }
if (!(byte & BIT(0))) {
if (byte == 0)
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 23c8289c2472..f17b1e769ae4 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -33,6 +33,7 @@
#include "tsc.h"
#include "intel-pt.h"
#include "config.h"
+#include "util/perf_api_probe.h"
#include "util/synthetic-events.h"
#include "time-utils.h"
@@ -68,6 +69,10 @@ struct intel_pt {
bool est_tsc;
bool sync_switch;
bool mispred_all;
+ bool use_thread_stack;
+ bool callstack;
+ unsigned int br_stack_sz;
+ unsigned int br_stack_sz_plus;
int have_sched_switch;
u32 pmu_type;
u64 kernel_start;
@@ -124,6 +129,9 @@ struct intel_pt {
struct range *time_ranges;
unsigned int range_cnt;
+
+ struct ip_callchain *chain;
+ struct branch_stack *br_stack;
};
enum switch_state {
@@ -143,8 +151,6 @@ struct intel_pt_queue {
const struct intel_pt_state *state;
struct ip_callchain *chain;
struct branch_stack *last_branch;
- struct branch_stack *last_branch_rb;
- size_t last_branch_pos;
union perf_event *event_buf;
bool on_heap;
bool stop;
@@ -868,6 +874,83 @@ static u64 intel_pt_ns_to_ticks(const struct intel_pt *pt, u64 ns)
pt->tc.time_mult;
}
+static struct ip_callchain *intel_pt_alloc_chain(struct intel_pt *pt)
+{
+ size_t sz = sizeof(struct ip_callchain);
+
+ /* Add 1 to callchain_sz for callchain context */
+ sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
+ return zalloc(sz);
+}
+
+static int intel_pt_callchain_init(struct intel_pt *pt)
+{
+ struct evsel *evsel;
+
+ evlist__for_each_entry(pt->session->evlist, evsel) {
+ if (!(evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN))
+ evsel->synth_sample_type |= PERF_SAMPLE_CALLCHAIN;
+ }
+
+ pt->chain = intel_pt_alloc_chain(pt);
+ if (!pt->chain)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void intel_pt_add_callchain(struct intel_pt *pt,
+ struct perf_sample *sample)
+{
+ struct thread *thread = machine__findnew_thread(pt->machine,
+ sample->pid,
+ sample->tid);
+
+ thread_stack__sample_late(thread, sample->cpu, pt->chain,
+ pt->synth_opts.callchain_sz + 1, sample->ip,
+ pt->kernel_start);
+
+ sample->callchain = pt->chain;
+}
+
+static struct branch_stack *intel_pt_alloc_br_stack(struct intel_pt *pt)
+{
+ size_t sz = sizeof(struct branch_stack);
+
+ sz += pt->br_stack_sz * sizeof(struct branch_entry);
+ return zalloc(sz);
+}
+
+static int intel_pt_br_stack_init(struct intel_pt *pt)
+{
+ struct evsel *evsel;
+
+ evlist__for_each_entry(pt->session->evlist, evsel) {
+ if (!(evsel->core.attr.sample_type & PERF_SAMPLE_BRANCH_STACK))
+ evsel->synth_sample_type |= PERF_SAMPLE_BRANCH_STACK;
+ }
+
+ pt->br_stack = intel_pt_alloc_br_stack(pt);
+ if (!pt->br_stack)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void intel_pt_add_br_stack(struct intel_pt *pt,
+ struct perf_sample *sample)
+{
+ struct thread *thread = machine__findnew_thread(pt->machine,
+ sample->pid,
+ sample->tid);
+
+ thread_stack__br_sample_late(thread, sample->cpu, pt->br_stack,
+ pt->br_stack_sz, sample->ip,
+ pt->kernel_start);
+
+ sample->branch_stack = pt->br_stack;
+}
+
static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
unsigned int queue_nr)
{
@@ -880,26 +963,15 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
return NULL;
if (pt->synth_opts.callchain) {
- size_t sz = sizeof(struct ip_callchain);
-
- /* Add 1 to callchain_sz for callchain context */
- sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
- ptq->chain = zalloc(sz);
+ ptq->chain = intel_pt_alloc_chain(pt);
if (!ptq->chain)
goto out_free;
}
if (pt->synth_opts.last_branch) {
- size_t sz = sizeof(struct branch_stack);
-
- sz += pt->synth_opts.last_branch_sz *
- sizeof(struct branch_entry);
- ptq->last_branch = zalloc(sz);
+ ptq->last_branch = intel_pt_alloc_br_stack(pt);
if (!ptq->last_branch)
goto out_free;
- ptq->last_branch_rb = zalloc(sz);
- if (!ptq->last_branch_rb)
- goto out_free;
}
ptq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
@@ -968,7 +1040,6 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
out_free:
zfree(&ptq->event_buf);
zfree(&ptq->last_branch);
- zfree(&ptq->last_branch_rb);
zfree(&ptq->chain);
free(ptq);
return NULL;
@@ -984,7 +1055,6 @@ static void intel_pt_free_queue(void *priv)
intel_pt_decoder_free(ptq->decoder);
zfree(&ptq->event_buf);
zfree(&ptq->last_branch);
- zfree(&ptq->last_branch_rb);
zfree(&ptq->chain);
free(ptq);
}
@@ -1152,58 +1222,6 @@ static int intel_pt_setup_queues(struct intel_pt *pt)
return 0;
}
-static inline void intel_pt_copy_last_branch_rb(struct intel_pt_queue *ptq)
-{
- struct branch_stack *bs_src = ptq->last_branch_rb;
- struct branch_stack *bs_dst = ptq->last_branch;
- size_t nr = 0;
-
- bs_dst->nr = bs_src->nr;
-
- if (!bs_src->nr)
- return;
-
- nr = ptq->pt->synth_opts.last_branch_sz - ptq->last_branch_pos;
- memcpy(&bs_dst->entries[0],
- &bs_src->entries[ptq->last_branch_pos],
- sizeof(struct branch_entry) * nr);
-
- if (bs_src->nr >= ptq->pt->synth_opts.last_branch_sz) {
- memcpy(&bs_dst->entries[nr],
- &bs_src->entries[0],
- sizeof(struct branch_entry) * ptq->last_branch_pos);
- }
-}
-
-static inline void intel_pt_reset_last_branch_rb(struct intel_pt_queue *ptq)
-{
- ptq->last_branch_pos = 0;
- ptq->last_branch_rb->nr = 0;
-}
-
-static void intel_pt_update_last_branch_rb(struct intel_pt_queue *ptq)
-{
- const struct intel_pt_state *state = ptq->state;
- struct branch_stack *bs = ptq->last_branch_rb;
- struct branch_entry *be;
-
- if (!ptq->last_branch_pos)
- ptq->last_branch_pos = ptq->pt->synth_opts.last_branch_sz;
-
- ptq->last_branch_pos -= 1;
-
- be = &bs->entries[ptq->last_branch_pos];
- be->from = state->from_ip;
- be->to = state->to_ip;
- be->flags.abort = !!(state->flags & INTEL_PT_ABORT_TX);
- be->flags.in_tx = !!(state->flags & INTEL_PT_IN_TX);
- /* No support for mispredict */
- be->flags.mispred = ptq->pt->mispred_all;
-
- if (bs->nr < ptq->pt->synth_opts.last_branch_sz)
- bs->nr += 1;
-}
-
static inline bool intel_pt_skip_event(struct intel_pt *pt)
{
return pt->synth_opts.initial_skip &&
@@ -1271,9 +1289,9 @@ static inline int intel_pt_opt_inject(struct intel_pt *pt,
return intel_pt_inject_event(event, sample, type);
}
-static int intel_pt_deliver_synth_b_event(struct intel_pt *pt,
- union perf_event *event,
- struct perf_sample *sample, u64 type)
+static int intel_pt_deliver_synth_event(struct intel_pt *pt,
+ union perf_event *event,
+ struct perf_sample *sample, u64 type)
{
int ret;
@@ -1333,8 +1351,8 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
ptq->last_br_cyc_cnt = ptq->ipc_cyc_cnt;
}
- return intel_pt_deliver_synth_b_event(pt, event, &sample,
- pt->branches_sample_type);
+ return intel_pt_deliver_synth_event(pt, event, &sample,
+ pt->branches_sample_type);
}
static void intel_pt_prep_sample(struct intel_pt *pt,
@@ -1352,27 +1370,12 @@ static void intel_pt_prep_sample(struct intel_pt *pt,
}
if (pt->synth_opts.last_branch) {
- intel_pt_copy_last_branch_rb(ptq);
+ thread_stack__br_sample(ptq->thread, ptq->cpu, ptq->last_branch,
+ pt->br_stack_sz);
sample->branch_stack = ptq->last_branch;
}
}
-static inline int intel_pt_deliver_synth_event(struct intel_pt *pt,
- struct intel_pt_queue *ptq,
- union perf_event *event,
- struct perf_sample *sample,
- u64 type)
-{
- int ret;
-
- ret = intel_pt_deliver_synth_b_event(pt, event, sample, type);
-
- if (pt->synth_opts.last_branch)
- intel_pt_reset_last_branch_rb(ptq);
-
- return ret;
-}
-
static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
{
struct intel_pt *pt = ptq->pt;
@@ -1397,7 +1400,7 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
ptq->last_insn_cnt = ptq->state->tot_insn_cnt;
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->instructions_sample_type);
}
@@ -1415,7 +1418,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
sample.id = ptq->pt->transactions_id;
sample.stream_id = ptq->pt->transactions_id;
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->transactions_sample_type);
}
@@ -1456,7 +1459,7 @@ static int intel_pt_synth_ptwrite_sample(struct intel_pt_queue *ptq)
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->ptwrites_sample_type);
}
@@ -1486,7 +1489,7 @@ static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq)
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1511,7 +1514,7 @@ static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq)
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1536,7 +1539,7 @@ static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq)
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1561,7 +1564,7 @@ static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq)
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1586,7 +1589,7 @@ static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq)
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1680,15 +1683,14 @@ static u64 intel_pt_lbr_flags(u64 info)
union {
struct branch_flags flags;
u64 result;
- } u = {
- .flags = {
- .mispred = !!(info & LBR_INFO_MISPRED),
- .predicted = !(info & LBR_INFO_MISPRED),
- .in_tx = !!(info & LBR_INFO_IN_TX),
- .abort = !!(info & LBR_INFO_ABORT),
- .cycles = info & LBR_INFO_CYCLES,
- }
- };
+ } u;
+
+ u.result = 0;
+ u.flags.mispred = !!(info & LBR_INFO_MISPRED);
+ u.flags.predicted = !(info & LBR_INFO_MISPRED);
+ u.flags.in_tx = !!(info & LBR_INFO_IN_TX);
+ u.flags.abort = !!(info & LBR_INFO_ABORT);
+ u.flags.cycles = info & LBR_INFO_CYCLES;
return u.result;
}
@@ -1807,7 +1809,9 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
intel_pt_add_lbrs(&br.br_stack, items);
sample.branch_stack = &br.br_stack;
} else if (pt->synth_opts.last_branch) {
- intel_pt_copy_last_branch_rb(ptq);
+ thread_stack__br_sample(ptq->thread, ptq->cpu,
+ ptq->last_branch,
+ pt->br_stack_sz);
sample.branch_stack = ptq->last_branch;
} else {
br.br_stack.nr = 0;
@@ -1842,7 +1846,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
sample.transaction = txn;
}
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample, sample_type);
+ return intel_pt_deliver_synth_event(pt, event, &sample, sample_type);
}
static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
@@ -1992,12 +1996,15 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
if (!(state->type & INTEL_PT_BRANCH))
return 0;
- if (pt->synth_opts.callchain || pt->synth_opts.thread_stack)
- thread_stack__event(ptq->thread, ptq->cpu, ptq->flags, state->from_ip,
- state->to_ip, ptq->insn_len,
- state->trace_nr);
- else
+ if (pt->use_thread_stack) {
+ thread_stack__event(ptq->thread, ptq->cpu, ptq->flags,
+ state->from_ip, state->to_ip, ptq->insn_len,
+ state->trace_nr, pt->callstack,
+ pt->br_stack_sz_plus,
+ pt->mispred_all);
+ } else {
thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr);
+ }
if (pt->sample_branches) {
err = intel_pt_synth_branch_sample(ptq);
@@ -2005,9 +2012,6 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
return err;
}
- if (pt->synth_opts.last_branch)
- intel_pt_update_last_branch_rb(ptq);
-
if (!ptq->sync_switch)
return 0;
@@ -2484,7 +2488,7 @@ static int intel_pt_process_switch(struct intel_pt *pt,
if (evsel != pt->switch_evsel)
return 0;
- tid = perf_evsel__intval(evsel, sample, "next_pid");
+ tid = evsel__intval(evsel, sample, "next_pid");
cpu = sample->cpu;
intel_pt_log("sched_switch: cpu %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
@@ -2639,6 +2643,13 @@ static int intel_pt_process_event(struct perf_session *session,
if (err)
return err;
+ if (event->header.type == PERF_RECORD_SAMPLE) {
+ if (pt->synth_opts.add_callchain && !sample->callchain)
+ intel_pt_add_callchain(pt, sample);
+ if (pt->synth_opts.add_last_branch && !sample->branch_stack)
+ intel_pt_add_br_stack(pt, sample);
+ }
+
if (event->header.type == PERF_RECORD_AUX &&
(event->aux.flags & PERF_AUX_FLAG_TRUNCATED) &&
pt->synth_opts.errors) {
@@ -2710,11 +2721,21 @@ static void intel_pt_free(struct perf_session *session)
session->auxtrace = NULL;
thread__put(pt->unknown_thread);
addr_filters__exit(&pt->filts);
+ zfree(&pt->chain);
zfree(&pt->filter);
zfree(&pt->time_ranges);
free(pt);
}
+static bool intel_pt_evsel_is_auxtrace(struct perf_session *session,
+ struct evsel *evsel)
+{
+ struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+ auxtrace);
+
+ return evsel->core.attr.type == pt->pmu_type;
+}
+
static int intel_pt_process_auxtrace_event(struct perf_session *session,
union perf_event *event,
struct perf_tool *tool __maybe_unused)
@@ -3016,7 +3037,7 @@ static struct evsel *intel_pt_find_sched_switch(struct evlist *evlist)
struct evsel *evsel;
evlist__for_each_entry_reverse(evlist, evsel) {
- const char *name = perf_evsel__name(evsel);
+ const char *name = evsel__name(evsel);
if (!strcmp(name, "sched:sched_switch"))
return evsel;
@@ -3310,6 +3331,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
pt->auxtrace.flush_events = intel_pt_flush;
pt->auxtrace.free_events = intel_pt_free_events;
pt->auxtrace.free = intel_pt_free;
+ pt->auxtrace.evsel_is_auxtrace = intel_pt_evsel_is_auxtrace;
session->auxtrace = &pt->auxtrace;
if (dump_trace)
@@ -3338,6 +3360,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
!session->itrace_synth_opts->inject) {
pt->synth_opts.branches = false;
pt->synth_opts.callchain = true;
+ pt->synth_opts.add_callchain = true;
}
pt->synth_opts.thread_stack =
session->itrace_synth_opts->thread_stack;
@@ -3370,14 +3393,54 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
pt->branches_filter |= PERF_IP_FLAG_RETURN |
PERF_IP_FLAG_TRACE_BEGIN;
- if (pt->synth_opts.callchain && !symbol_conf.use_callchain) {
+ if ((pt->synth_opts.callchain || pt->synth_opts.add_callchain) &&
+ !symbol_conf.use_callchain) {
symbol_conf.use_callchain = true;
if (callchain_register_param(&callchain_param) < 0) {
symbol_conf.use_callchain = false;
pt->synth_opts.callchain = false;
+ pt->synth_opts.add_callchain = false;
}
}
+ if (pt->synth_opts.add_callchain) {
+ err = intel_pt_callchain_init(pt);
+ if (err)
+ goto err_delete_thread;
+ }
+
+ if (pt->synth_opts.last_branch || pt->synth_opts.add_last_branch) {
+ pt->br_stack_sz = pt->synth_opts.last_branch_sz;
+ pt->br_stack_sz_plus = pt->br_stack_sz;
+ }
+
+ if (pt->synth_opts.add_last_branch) {
+ err = intel_pt_br_stack_init(pt);
+ if (err)
+ goto err_delete_thread;
+ /*
+ * Additional branch stack size to cater for tracing from the
+ * actual sample ip to where the sample time is recorded.
+ * Measured at about 200 branches, but generously set to 1024.
+ * If kernel space is not being traced, then add just 1 for the
+ * branch to kernel space.
+ */
+ if (intel_pt_tracing_kernel(pt))
+ pt->br_stack_sz_plus += 1024;
+ else
+ pt->br_stack_sz_plus += 1;
+ }
+
+ pt->use_thread_stack = pt->synth_opts.callchain ||
+ pt->synth_opts.add_callchain ||
+ pt->synth_opts.thread_stack ||
+ pt->synth_opts.last_branch ||
+ pt->synth_opts.add_last_branch;
+
+ pt->callstack = pt->synth_opts.callchain ||
+ pt->synth_opts.add_callchain ||
+ pt->synth_opts.thread_stack;
+
err = intel_pt_synth_events(pt, session);
if (err)
goto err_delete_thread;
@@ -3400,6 +3463,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
return 0;
err_delete_thread:
+ zfree(&pt->chain);
thread__zput(pt->unknown_thread);
err_free_queues:
intel_pt_log_disable();
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 97142e9671be..8ed2135893bb 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -736,6 +736,12 @@ int machine__process_switch_event(struct machine *machine __maybe_unused,
return 0;
}
+static int is_bpf_image(const char *name)
+{
+ return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) ||
+ strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1);
+}
+
static int machine__process_ksymbol_register(struct machine *machine,
union perf_event *event,
struct perf_sample *sample __maybe_unused)
@@ -759,6 +765,12 @@ static int machine__process_ksymbol_register(struct machine *machine,
map->start = event->ksymbol.addr;
map->end = map->start + event->ksymbol.len;
maps__insert(&machine->kmaps, map);
+ dso__set_loaded(dso);
+
+ if (is_bpf_image(event->ksymbol.name)) {
+ dso->binary_type = DSO_BINARY_TYPE__BPF_IMAGE;
+ dso__set_long_name(dso, "", false);
+ }
}
sym = symbol__new(map->map_ip(map, map->start),
@@ -2178,6 +2190,303 @@ static int remove_loops(struct branch_entry *l, int nr,
return nr;
}
+static int lbr_callchain_add_kernel_ip(struct thread *thread,
+ struct callchain_cursor *cursor,
+ struct perf_sample *sample,
+ struct symbol **parent,
+ struct addr_location *root_al,
+ u64 branch_from,
+ bool callee, int end)
+{
+ struct ip_callchain *chain = sample->callchain;
+ u8 cpumode = PERF_RECORD_MISC_USER;
+ int err, i;
+
+ if (callee) {
+ for (i = 0; i < end + 1; i++) {
+ err = add_callchain_ip(thread, cursor, parent,
+ root_al, &cpumode, chain->ips[i],
+ false, NULL, NULL, branch_from);
+ if (err)
+ return err;
+ }
+ return 0;
+ }
+
+ for (i = end; i >= 0; i--) {
+ err = add_callchain_ip(thread, cursor, parent,
+ root_al, &cpumode, chain->ips[i],
+ false, NULL, NULL, branch_from);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static void save_lbr_cursor_node(struct thread *thread,
+ struct callchain_cursor *cursor,
+ int idx)
+{
+ struct lbr_stitch *lbr_stitch = thread->lbr_stitch;
+
+ if (!lbr_stitch)
+ return;
+
+ if (cursor->pos == cursor->nr) {
+ lbr_stitch->prev_lbr_cursor[idx].valid = false;
+ return;
+ }
+
+ if (!cursor->curr)
+ cursor->curr = cursor->first;
+ else
+ cursor->curr = cursor->curr->next;
+ memcpy(&lbr_stitch->prev_lbr_cursor[idx], cursor->curr,
+ sizeof(struct callchain_cursor_node));
+
+ lbr_stitch->prev_lbr_cursor[idx].valid = true;
+ cursor->pos++;
+}
+
+static int lbr_callchain_add_lbr_ip(struct thread *thread,
+ struct callchain_cursor *cursor,
+ struct perf_sample *sample,
+ struct symbol **parent,
+ struct addr_location *root_al,
+ u64 *branch_from,
+ bool callee)
+{
+ struct branch_stack *lbr_stack = sample->branch_stack;
+ struct branch_entry *entries = perf_sample__branch_entries(sample);
+ u8 cpumode = PERF_RECORD_MISC_USER;
+ int lbr_nr = lbr_stack->nr;
+ struct branch_flags *flags;
+ int err, i;
+ u64 ip;
+
+ /*
+ * The curr and pos are not used in writing session. They are cleared
+ * in callchain_cursor_commit() when the writing session is closed.
+ * Using curr and pos to track the current cursor node.
+ */
+ if (thread->lbr_stitch) {
+ cursor->curr = NULL;
+ cursor->pos = cursor->nr;
+ if (cursor->nr) {
+ cursor->curr = cursor->first;
+ for (i = 0; i < (int)(cursor->nr - 1); i++)
+ cursor->curr = cursor->curr->next;
+ }
+ }
+
+ if (callee) {
+ /* Add LBR ip from first entries.to */
+ ip = entries[0].to;
+ flags = &entries[0].flags;
+ *branch_from = entries[0].from;
+ err = add_callchain_ip(thread, cursor, parent,
+ root_al, &cpumode, ip,
+ true, flags, NULL,
+ *branch_from);
+ if (err)
+ return err;
+
+ /*
+ * The number of cursor node increases.
+ * Move the current cursor node.
+ * But does not need to save current cursor node for entry 0.
+ * It's impossible to stitch the whole LBRs of previous sample.
+ */
+ if (thread->lbr_stitch && (cursor->pos != cursor->nr)) {
+ if (!cursor->curr)
+ cursor->curr = cursor->first;
+ else
+ cursor->curr = cursor->curr->next;
+ cursor->pos++;
+ }
+
+ /* Add LBR ip from entries.from one by one. */
+ for (i = 0; i < lbr_nr; i++) {
+ ip = entries[i].from;
+ flags = &entries[i].flags;
+ err = add_callchain_ip(thread, cursor, parent,
+ root_al, &cpumode, ip,
+ true, flags, NULL,
+ *branch_from);
+ if (err)
+ return err;
+ save_lbr_cursor_node(thread, cursor, i);
+ }
+ return 0;
+ }
+
+ /* Add LBR ip from entries.from one by one. */
+ for (i = lbr_nr - 1; i >= 0; i--) {
+ ip = entries[i].from;
+ flags = &entries[i].flags;
+ err = add_callchain_ip(thread, cursor, parent,
+ root_al, &cpumode, ip,
+ true, flags, NULL,
+ *branch_from);
+ if (err)
+ return err;
+ save_lbr_cursor_node(thread, cursor, i);
+ }
+
+ /* Add LBR ip from first entries.to */
+ ip = entries[0].to;
+ flags = &entries[0].flags;
+ *branch_from = entries[0].from;
+ err = add_callchain_ip(thread, cursor, parent,
+ root_al, &cpumode, ip,
+ true, flags, NULL,
+ *branch_from);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static int lbr_callchain_add_stitched_lbr_ip(struct thread *thread,
+ struct callchain_cursor *cursor)
+{
+ struct lbr_stitch *lbr_stitch = thread->lbr_stitch;
+ struct callchain_cursor_node *cnode;
+ struct stitch_list *stitch_node;
+ int err;
+
+ list_for_each_entry(stitch_node, &lbr_stitch->lists, node) {
+ cnode = &stitch_node->cursor;
+
+ err = callchain_cursor_append(cursor, cnode->ip,
+ &cnode->ms,
+ cnode->branch,
+ &cnode->branch_flags,
+ cnode->nr_loop_iter,
+ cnode->iter_cycles,
+ cnode->branch_from,
+ cnode->srcline);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+static struct stitch_list *get_stitch_node(struct thread *thread)
+{
+ struct lbr_stitch *lbr_stitch = thread->lbr_stitch;
+ struct stitch_list *stitch_node;
+
+ if (!list_empty(&lbr_stitch->free_lists)) {
+ stitch_node = list_first_entry(&lbr_stitch->free_lists,
+ struct stitch_list, node);
+ list_del(&stitch_node->node);
+
+ return stitch_node;
+ }
+
+ return malloc(sizeof(struct stitch_list));
+}
+
+static bool has_stitched_lbr(struct thread *thread,
+ struct perf_sample *cur,
+ struct perf_sample *prev,
+ unsigned int max_lbr,
+ bool callee)
+{
+ struct branch_stack *cur_stack = cur->branch_stack;
+ struct branch_entry *cur_entries = perf_sample__branch_entries(cur);
+ struct branch_stack *prev_stack = prev->branch_stack;
+ struct branch_entry *prev_entries = perf_sample__branch_entries(prev);
+ struct lbr_stitch *lbr_stitch = thread->lbr_stitch;
+ int i, j, nr_identical_branches = 0;
+ struct stitch_list *stitch_node;
+ u64 cur_base, distance;
+
+ if (!cur_stack || !prev_stack)
+ return false;
+
+ /* Find the physical index of the base-of-stack for current sample. */
+ cur_base = max_lbr - cur_stack->nr + cur_stack->hw_idx + 1;
+
+ distance = (prev_stack->hw_idx > cur_base) ? (prev_stack->hw_idx - cur_base) :
+ (max_lbr + prev_stack->hw_idx - cur_base);
+ /* Previous sample has shorter stack. Nothing can be stitched. */
+ if (distance + 1 > prev_stack->nr)
+ return false;
+
+ /*
+ * Check if there are identical LBRs between two samples.
+ * Identicall LBRs must have same from, to and flags values. Also,
+ * they have to be saved in the same LBR registers (same physical
+ * index).
+ *
+ * Starts from the base-of-stack of current sample.
+ */
+ for (i = distance, j = cur_stack->nr - 1; (i >= 0) && (j >= 0); i--, j--) {
+ if ((prev_entries[i].from != cur_entries[j].from) ||
+ (prev_entries[i].to != cur_entries[j].to) ||
+ (prev_entries[i].flags.value != cur_entries[j].flags.value))
+ break;
+ nr_identical_branches++;
+ }
+
+ if (!nr_identical_branches)
+ return false;
+
+ /*
+ * Save the LBRs between the base-of-stack of previous sample
+ * and the base-of-stack of current sample into lbr_stitch->lists.
+ * These LBRs will be stitched later.
+ */
+ for (i = prev_stack->nr - 1; i > (int)distance; i--) {
+
+ if (!lbr_stitch->prev_lbr_cursor[i].valid)
+ continue;
+
+ stitch_node = get_stitch_node(thread);
+ if (!stitch_node)
+ return false;
+
+ memcpy(&stitch_node->cursor, &lbr_stitch->prev_lbr_cursor[i],
+ sizeof(struct callchain_cursor_node));
+
+ if (callee)
+ list_add(&stitch_node->node, &lbr_stitch->lists);
+ else
+ list_add_tail(&stitch_node->node, &lbr_stitch->lists);
+ }
+
+ return true;
+}
+
+static bool alloc_lbr_stitch(struct thread *thread, unsigned int max_lbr)
+{
+ if (thread->lbr_stitch)
+ return true;
+
+ thread->lbr_stitch = zalloc(sizeof(*thread->lbr_stitch));
+ if (!thread->lbr_stitch)
+ goto err;
+
+ thread->lbr_stitch->prev_lbr_cursor = calloc(max_lbr + 1, sizeof(struct callchain_cursor_node));
+ if (!thread->lbr_stitch->prev_lbr_cursor)
+ goto free_lbr_stitch;
+
+ INIT_LIST_HEAD(&thread->lbr_stitch->lists);
+ INIT_LIST_HEAD(&thread->lbr_stitch->free_lists);
+
+ return true;
+
+free_lbr_stitch:
+ zfree(&thread->lbr_stitch);
+err:
+ pr_warning("Failed to allocate space for stitched LBRs. Disable LBR stitch\n");
+ thread->lbr_stitch_enable = false;
+ return false;
+}
+
/*
* Recolve LBR callstack chain sample
* Return:
@@ -2190,12 +2499,16 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
struct perf_sample *sample,
struct symbol **parent,
struct addr_location *root_al,
- int max_stack)
+ int max_stack,
+ unsigned int max_lbr)
{
+ bool callee = (callchain_param.order == ORDER_CALLEE);
struct ip_callchain *chain = sample->callchain;
int chain_nr = min(max_stack, (int)chain->nr), i;
- u8 cpumode = PERF_RECORD_MISC_USER;
- u64 ip, branch_from = 0;
+ struct lbr_stitch *lbr_stitch;
+ bool stitched_lbr = false;
+ u64 branch_from = 0;
+ int err;
for (i = 0; i < chain_nr; i++) {
if (chain->ips[i] == PERF_CONTEXT_USER)
@@ -2203,71 +2516,65 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
}
/* LBR only affects the user callchain */
- if (i != chain_nr) {
- struct branch_stack *lbr_stack = sample->branch_stack;
- struct branch_entry *entries = perf_sample__branch_entries(sample);
- int lbr_nr = lbr_stack->nr, j, k;
- bool branch;
- struct branch_flags *flags;
- /*
- * LBR callstack can only get user call chain.
- * The mix_chain_nr is kernel call chain
- * number plus LBR user call chain number.
- * i is kernel call chain number,
- * 1 is PERF_CONTEXT_USER,
- * lbr_nr + 1 is the user call chain number.
- * For details, please refer to the comments
- * in callchain__printf
- */
- int mix_chain_nr = i + 1 + lbr_nr + 1;
+ if (i == chain_nr)
+ return 0;
- for (j = 0; j < mix_chain_nr; j++) {
- int err;
- branch = false;
- flags = NULL;
+ if (thread->lbr_stitch_enable && !sample->no_hw_idx &&
+ (max_lbr > 0) && alloc_lbr_stitch(thread, max_lbr)) {
+ lbr_stitch = thread->lbr_stitch;
- if (callchain_param.order == ORDER_CALLEE) {
- if (j < i + 1)
- ip = chain->ips[j];
- else if (j > i + 1) {
- k = j - i - 2;
- ip = entries[k].from;
- branch = true;
- flags = &entries[k].flags;
- } else {
- ip = entries[0].to;
- branch = true;
- flags = &entries[0].flags;
- branch_from = entries[0].from;
- }
- } else {
- if (j < lbr_nr) {
- k = lbr_nr - j - 1;
- ip = entries[k].from;
- branch = true;
- flags = &entries[k].flags;
- }
- else if (j > lbr_nr)
- ip = chain->ips[i + 1 - (j - lbr_nr)];
- else {
- ip = entries[0].to;
- branch = true;
- flags = &entries[0].flags;
- branch_from = entries[0].from;
- }
- }
+ stitched_lbr = has_stitched_lbr(thread, sample,
+ &lbr_stitch->prev_sample,
+ max_lbr, callee);
- err = add_callchain_ip(thread, cursor, parent,
- root_al, &cpumode, ip,
- branch, flags, NULL,
- branch_from);
+ if (!stitched_lbr && !list_empty(&lbr_stitch->lists)) {
+ list_replace_init(&lbr_stitch->lists,
+ &lbr_stitch->free_lists);
+ }
+ memcpy(&lbr_stitch->prev_sample, sample, sizeof(*sample));
+ }
+
+ if (callee) {
+ /* Add kernel ip */
+ err = lbr_callchain_add_kernel_ip(thread, cursor, sample,
+ parent, root_al, branch_from,
+ true, i);
+ if (err)
+ goto error;
+
+ err = lbr_callchain_add_lbr_ip(thread, cursor, sample, parent,
+ root_al, &branch_from, true);
+ if (err)
+ goto error;
+
+ if (stitched_lbr) {
+ err = lbr_callchain_add_stitched_lbr_ip(thread, cursor);
if (err)
- return (err < 0) ? err : 0;
+ goto error;
}
- return 1;
+
+ } else {
+ if (stitched_lbr) {
+ err = lbr_callchain_add_stitched_lbr_ip(thread, cursor);
+ if (err)
+ goto error;
+ }
+ err = lbr_callchain_add_lbr_ip(thread, cursor, sample, parent,
+ root_al, &branch_from, false);
+ if (err)
+ goto error;
+
+ /* Add kernel ip */
+ err = lbr_callchain_add_kernel_ip(thread, cursor, sample,
+ parent, root_al, branch_from,
+ false, i);
+ if (err)
+ goto error;
}
+ return 1;
- return 0;
+error:
+ return (err < 0) ? err : 0;
}
static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
@@ -2311,9 +2618,12 @@ static int thread__resolve_callchain_sample(struct thread *thread,
if (chain)
chain_nr = chain->nr;
- if (perf_evsel__has_branch_callstack(evsel)) {
+ if (evsel__has_branch_callstack(evsel)) {
+ struct perf_env *env = evsel__env(evsel);
+
err = resolve_lbr_callchain_sample(thread, cursor, sample, parent,
- root_al, max_stack);
+ root_al, max_stack,
+ !env ? 0 : env->max_branches);
if (err)
return (err < 0) ? err : 0;
}
diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c
index 797d86a1ab09..c84f5841c7ab 100644
--- a/tools/perf/util/mem2node.c
+++ b/tools/perf/util/mem2node.c
@@ -1,5 +1,6 @@
#include <errno.h>
#include <inttypes.h>
+#include <asm/bug.h>
#include <linux/bitmap.h>
#include <linux/kernel.h>
#include <linux/zalloc.h>
@@ -95,7 +96,7 @@ int mem2node__init(struct mem2node *map, struct perf_env *env)
/* Cut unused entries, due to merging. */
tmp_entries = realloc(entries, sizeof(*entries) * j);
- if (tmp_entries)
+ if (tmp_entries || WARN_ON_ONCE(j == 0))
entries = tmp_entries;
for (i = 0; i < j; i++) {
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 926449a7cdbf..b071df373f8b 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -90,6 +90,7 @@ struct egroup {
const char *metric_name;
const char *metric_expr;
const char *metric_unit;
+ int runtime;
};
static struct evsel *find_evsel_group(struct evlist *perf_evlist,
@@ -202,6 +203,7 @@ static int metricgroup__setup_events(struct list_head *groups,
expr->metric_name = eg->metric_name;
expr->metric_unit = eg->metric_unit;
expr->metric_events = metric_events;
+ expr->runtime = eg->runtime;
list_add(&expr->nd, &me->head);
}
@@ -485,6 +487,45 @@ static bool metricgroup__has_constraint(struct pmu_event *pe)
return false;
}
+int __weak arch_get_runtimeparam(void)
+{
+ return 1;
+}
+
+static int __metricgroup__add_metric(struct strbuf *events,
+ struct list_head *group_list, struct pmu_event *pe, int runtime)
+{
+
+ const char **ids;
+ int idnum;
+ struct egroup *eg;
+
+ if (expr__find_other(pe->metric_expr, NULL, &ids, &idnum, runtime) < 0)
+ return -EINVAL;
+
+ if (events->len > 0)
+ strbuf_addf(events, ",");
+
+ if (metricgroup__has_constraint(pe))
+ metricgroup__add_metric_non_group(events, ids, idnum);
+ else
+ metricgroup__add_metric_weak_group(events, ids, idnum);
+
+ eg = malloc(sizeof(*eg));
+ if (!eg)
+ return -ENOMEM;
+
+ eg->ids = ids;
+ eg->idnum = idnum;
+ eg->metric_name = pe->metric_name;
+ eg->metric_expr = pe->metric_expr;
+ eg->metric_unit = pe->unit;
+ eg->runtime = runtime;
+ list_add_tail(&eg->nd, group_list);
+
+ return 0;
+}
+
static int metricgroup__add_metric(const char *metric, struct strbuf *events,
struct list_head *group_list)
{
@@ -504,35 +545,26 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
continue;
if (match_metric(pe->metric_group, metric) ||
match_metric(pe->metric_name, metric)) {
- const char **ids;
- int idnum;
- struct egroup *eg;
pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
- if (expr__find_other(pe->metric_expr,
- NULL, &ids, &idnum) < 0)
- continue;
- if (events->len > 0)
- strbuf_addf(events, ",");
+ if (!strstr(pe->metric_expr, "?")) {
+ ret = __metricgroup__add_metric(events, group_list, pe, 1);
+ } else {
+ int j, count;
- if (metricgroup__has_constraint(pe))
- metricgroup__add_metric_non_group(events, ids, idnum);
- else
- metricgroup__add_metric_weak_group(events, ids, idnum);
+ count = arch_get_runtimeparam();
- eg = malloc(sizeof(struct egroup));
- if (!eg) {
- ret = -ENOMEM;
- break;
+ /* This loop is added to create multiple
+ * events depend on count value and add
+ * those events to group_list.
+ */
+
+ for (j = 0; j < count; j++)
+ ret = __metricgroup__add_metric(events, group_list, pe, j);
}
- eg->ids = ids;
- eg->idnum = idnum;
- eg->metric_name = pe->metric_name;
- eg->metric_expr = pe->metric_expr;
- eg->metric_unit = pe->unit;
- list_add_tail(&eg->nd, group_list);
- ret = 0;
+ if (ret == -ENOMEM)
+ break;
}
}
return ret;
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 475c7f912864..6b09eb30b4ec 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -22,6 +22,7 @@ struct metric_expr {
const char *metric_name;
const char *metric_unit;
struct evsel **metric_events;
+ int runtime;
};
struct metric_event *metricgroup__lookup(struct rblist *metric_events,
@@ -34,4 +35,5 @@ int metricgroup__parse_groups(const struct option *opt,
void metricgroup__print(bool metrics, bool groups, char *filter,
bool raw, bool details);
bool metricgroup__has_metric(const char *metric);
+int arch_get_runtimeparam(void);
#endif
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 359db2b1fcef..48c8f609441b 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -314,7 +314,7 @@ static int __ordered_events__flush(struct ordered_events *oe, enum oe_flush how,
case OE_FLUSH__NONE:
default:
break;
- };
+ }
pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush PRE %s, nr_events %u\n",
str[how], oe->nr_events);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 10107747b361..b7a0518d607d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -461,7 +461,7 @@ int parse_events_add_cache(struct list_head *list, int *idx,
cache_op = parse_aliases(str, perf_evsel__hw_cache_op,
PERF_COUNT_HW_CACHE_OP_MAX);
if (cache_op >= 0) {
- if (!perf_evsel__is_cache_op_valid(cache_type, cache_op))
+ if (!evsel__is_cache_op_valid(cache_type, cache_op))
return -EINVAL;
continue;
}
@@ -1482,6 +1482,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
list_for_each_entry_safe(pos, tmp, &config_terms, list) {
list_del_init(&pos->list);
+ zfree(&pos->val.str);
free(pos);
}
return -EINVAL;
@@ -1870,7 +1871,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
evsel->precise_max = mod.precise_max;
evsel->weak_group = mod.weak;
- if (perf_evsel__is_group_leader(evsel))
+ if (evsel__is_group_leader(evsel))
evsel->core.attr.pinned = mod.pinned;
}
@@ -2190,6 +2191,29 @@ int parse_events_option(const struct option *opt, const char *str,
return ret;
}
+int parse_events_option_new_evlist(const struct option *opt, const char *str, int unset)
+{
+ struct evlist **evlistp = opt->value;
+ int ret;
+
+ if (*evlistp == NULL) {
+ *evlistp = evlist__new();
+
+ if (*evlistp == NULL) {
+ fprintf(stderr, "Not enough memory to create evlist\n");
+ return -1;
+ }
+ }
+
+ ret = parse_events_option(opt, str, unset);
+ if (ret) {
+ evlist__delete(*evlistp);
+ *evlistp = NULL;
+ }
+
+ return ret;
+}
+
static int
foreach_evsel_in_last_glob(struct evlist *evlist,
int (*func)(struct evsel *evsel,
@@ -2237,7 +2261,7 @@ static int set_filter(struct evsel *evsel, const void *arg)
}
if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) {
- if (perf_evsel__append_tp_filter(evsel, str) < 0) {
+ if (evsel__append_tp_filter(evsel, str) < 0) {
fprintf(stderr,
"not enough memory to hold filter string\n");
return -1;
@@ -2262,7 +2286,7 @@ static int set_filter(struct evsel *evsel, const void *arg)
return -1;
}
- if (perf_evsel__append_addr_filter(evsel, str) < 0) {
+ if (evsel__append_addr_filter(evsel, str) < 0) {
fprintf(stderr,
"not enough memory to hold filter string\n");
return -1;
@@ -2293,7 +2317,7 @@ static int add_exclude_perf_filter(struct evsel *evsel,
snprintf(new_filter, sizeof(new_filter), "common_pid != %d", getpid());
- if (perf_evsel__append_tp_filter(evsel, new_filter) < 0) {
+ if (evsel__append_tp_filter(evsel, new_filter) < 0) {
fprintf(stderr,
"not enough memory to hold filter string\n");
return -1;
@@ -2603,12 +2627,11 @@ restart:
for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
/* skip invalid cache type */
- if (!perf_evsel__is_cache_op_valid(type, op))
+ if (!evsel__is_cache_op_valid(type, op))
continue;
for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
- __perf_evsel__hw_cache_type_op_res_name(type, op, i,
- name, sizeof(name));
+ __evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name));
if (event_glob != NULL && !strglobmatch(name, event_glob))
continue;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 27596cbd0ba0..6ead9661238c 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -31,6 +31,7 @@ bool have_tracepoints(struct list_head *evlist);
const char *event_type(int type);
int parse_events_option(const struct option *opt, const char *str, int unset);
+int parse_events_option_new_evlist(const struct option *opt, const char *str, int unset);
int parse_events(struct evlist *evlist, const char *str,
struct parse_events_error *error);
int parse_events_terms(struct list_head *terms, const char *str);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index baa48f28d57d..c589fc42f058 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -286,6 +286,7 @@ no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); }
percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); }
aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); }
+r{num_raw_hex} { return raw(yyscanner); }
, { return ','; }
"/" { BEGIN(INITIAL); return '/'; }
{name_minus} { return str(yyscanner, PE_NAME); }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 94f8bcd83582..c4ca932d092d 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -44,7 +44,7 @@ static void free_list_evsel(struct list_head* list_evsel)
list_for_each_entry_safe(evsel, tmp, list_evsel, core.node) {
list_del_init(&evsel->core.node);
- perf_evsel__delete(evsel);
+ evsel__delete(evsel);
}
free(list_evsel);
}
@@ -326,6 +326,7 @@ PE_NAME opt_pmu_config
}
parse_events_terms__delete($2);
parse_events_terms__delete(orig_terms);
+ free(pattern);
free($1);
$$ = list;
#undef CLEANUP_YYABORT
@@ -706,6 +707,15 @@ event_term
}
event_term:
+PE_RAW
+{
+ struct parse_events_term *term;
+
+ ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_CONFIG,
+ NULL, $1, false, &@1, NULL));
+ $$ = term;
+}
+|
PE_NAME '=' PE_NAME
{
struct parse_events_term *term;
diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c
new file mode 100644
index 000000000000..1337965673d7
--- /dev/null
+++ b/tools/perf/util/perf_api_probe.c
@@ -0,0 +1,164 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include "perf-sys.h"
+#include "util/cloexec.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/parse-events.h"
+#include "util/perf_api_probe.h"
+#include <perf/cpumap.h>
+#include <errno.h>
+
+typedef void (*setup_probe_fn_t)(struct evsel *evsel);
+
+static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
+{
+ struct evlist *evlist;
+ struct evsel *evsel;
+ unsigned long flags = perf_event_open_cloexec_flag();
+ int err = -EAGAIN, fd;
+ static pid_t pid = -1;
+
+ evlist = evlist__new();
+ if (!evlist)
+ return -ENOMEM;
+
+ if (parse_events(evlist, str, NULL))
+ goto out_delete;
+
+ evsel = evlist__first(evlist);
+
+ while (1) {
+ fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
+ if (fd < 0) {
+ if (pid == -1 && errno == EACCES) {
+ pid = 0;
+ continue;
+ }
+ goto out_delete;
+ }
+ break;
+ }
+ close(fd);
+
+ fn(evsel);
+
+ fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
+ if (fd < 0) {
+ if (errno == EINVAL)
+ err = -EINVAL;
+ goto out_delete;
+ }
+ close(fd);
+ err = 0;
+
+out_delete:
+ evlist__delete(evlist);
+ return err;
+}
+
+static bool perf_probe_api(setup_probe_fn_t fn)
+{
+ const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
+ struct perf_cpu_map *cpus;
+ int cpu, ret, i = 0;
+
+ cpus = perf_cpu_map__new(NULL);
+ if (!cpus)
+ return false;
+ cpu = cpus->map[0];
+ perf_cpu_map__put(cpus);
+
+ do {
+ ret = perf_do_probe_api(fn, cpu, try[i++]);
+ if (!ret)
+ return true;
+ } while (ret == -EAGAIN && try[i]);
+
+ return false;
+}
+
+static void perf_probe_sample_identifier(struct evsel *evsel)
+{
+ evsel->core.attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
+}
+
+static void perf_probe_comm_exec(struct evsel *evsel)
+{
+ evsel->core.attr.comm_exec = 1;
+}
+
+static void perf_probe_context_switch(struct evsel *evsel)
+{
+ evsel->core.attr.context_switch = 1;
+}
+
+bool perf_can_sample_identifier(void)
+{
+ return perf_probe_api(perf_probe_sample_identifier);
+}
+
+bool perf_can_comm_exec(void)
+{
+ return perf_probe_api(perf_probe_comm_exec);
+}
+
+bool perf_can_record_switch_events(void)
+{
+ return perf_probe_api(perf_probe_context_switch);
+}
+
+bool perf_can_record_cpu_wide(void)
+{
+ struct perf_event_attr attr = {
+ .type = PERF_TYPE_SOFTWARE,
+ .config = PERF_COUNT_SW_CPU_CLOCK,
+ .exclude_kernel = 1,
+ };
+ struct perf_cpu_map *cpus;
+ int cpu, fd;
+
+ cpus = perf_cpu_map__new(NULL);
+ if (!cpus)
+ return false;
+ cpu = cpus->map[0];
+ perf_cpu_map__put(cpus);
+
+ fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
+ if (fd < 0)
+ return false;
+ close(fd);
+
+ return true;
+}
+
+/*
+ * Architectures are expected to know if AUX area sampling is supported by the
+ * hardware. Here we check for kernel support.
+ */
+bool perf_can_aux_sample(void)
+{
+ struct perf_event_attr attr = {
+ .size = sizeof(struct perf_event_attr),
+ .exclude_kernel = 1,
+ /*
+ * Non-zero value causes the kernel to calculate the effective
+ * attribute size up to that byte.
+ */
+ .aux_sample_size = 1,
+ };
+ int fd;
+
+ fd = sys_perf_event_open(&attr, -1, 0, -1, 0);
+ /*
+ * If the kernel attribute is big enough to contain aux_sample_size
+ * then we assume that it is supported. We are relying on the kernel to
+ * validate the attribute size before anything else that could be wrong.
+ */
+ if (fd < 0 && errno == E2BIG)
+ return false;
+ if (fd >= 0)
+ close(fd);
+
+ return true;
+}
diff --git a/tools/perf/util/perf_api_probe.h b/tools/perf/util/perf_api_probe.h
new file mode 100644
index 000000000000..706c3c6426e2
--- /dev/null
+++ b/tools/perf/util/perf_api_probe.h
@@ -0,0 +1,14 @@
+
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_API_PROBE_H
+#define __PERF_API_PROBE_H
+
+#include <stdbool.h>
+
+bool perf_can_aux_sample(void);
+bool perf_can_comm_exec(void);
+bool perf_can_record_cpu_wide(void);
+bool perf_can_record_switch_events(void);
+bool perf_can_sample_identifier(void);
+
+#endif // __PERF_API_PROBE_H
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index ef6a63f3d386..92bd7fafcce6 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -18,6 +18,7 @@
#include <regex.h>
#include <perf/cpumap.h>
#include "debug.h"
+#include "evsel.h"
#include "pmu.h"
#include "parse-events.h"
#include "header.h"
@@ -849,6 +850,7 @@ static struct perf_pmu *pmu_lookup(const char *name)
INIT_LIST_HEAD(&pmu->format);
INIT_LIST_HEAD(&pmu->aliases);
+ INIT_LIST_HEAD(&pmu->caps);
list_splice(&format, &pmu->format);
list_splice(&aliases, &pmu->aliases);
list_add_tail(&pmu->list, &pmus);
@@ -869,6 +871,17 @@ static struct perf_pmu *pmu_find(const char *name)
return NULL;
}
+struct perf_pmu *perf_pmu__find_by_type(unsigned int type)
+{
+ struct perf_pmu *pmu;
+
+ list_for_each_entry(pmu, &pmus, list)
+ if (pmu->type == type)
+ return pmu;
+
+ return NULL;
+}
+
struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu)
{
/*
@@ -884,6 +897,25 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu)
return NULL;
}
+struct perf_pmu *evsel__find_pmu(struct evsel *evsel)
+{
+ struct perf_pmu *pmu = NULL;
+
+ while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+ if (pmu->type == evsel->core.attr.type)
+ break;
+ }
+
+ return pmu;
+}
+
+bool evsel__is_aux_event(struct evsel *evsel)
+{
+ struct perf_pmu *pmu = evsel__find_pmu(evsel);
+
+ return pmu && pmu->auxtrace;
+}
+
struct perf_pmu *perf_pmu__find(const char *name)
{
struct perf_pmu *pmu;
@@ -1574,3 +1606,84 @@ int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
va_end(args);
return ret;
}
+
+static int perf_pmu__new_caps(struct list_head *list, char *name, char *value)
+{
+ struct perf_pmu_caps *caps = zalloc(sizeof(*caps));
+
+ if (!caps)
+ return -ENOMEM;
+
+ caps->name = strdup(name);
+ if (!caps->name)
+ goto free_caps;
+ caps->value = strndup(value, strlen(value) - 1);
+ if (!caps->value)
+ goto free_name;
+ list_add_tail(&caps->list, list);
+ return 0;
+
+free_name:
+ zfree(caps->name);
+free_caps:
+ free(caps);
+
+ return -ENOMEM;
+}
+
+/*
+ * Reading/parsing the given pmu capabilities, which should be located at:
+ * /sys/bus/event_source/devices/<dev>/caps as sysfs group attributes.
+ * Return the number of capabilities
+ */
+int perf_pmu__caps_parse(struct perf_pmu *pmu)
+{
+ struct stat st;
+ char caps_path[PATH_MAX];
+ const char *sysfs = sysfs__mountpoint();
+ DIR *caps_dir;
+ struct dirent *evt_ent;
+ int nr_caps = 0;
+
+ if (!sysfs)
+ return -1;
+
+ snprintf(caps_path, PATH_MAX,
+ "%s" EVENT_SOURCE_DEVICE_PATH "%s/caps", sysfs, pmu->name);
+
+ if (stat(caps_path, &st) < 0)
+ return 0; /* no error if caps does not exist */
+
+ caps_dir = opendir(caps_path);
+ if (!caps_dir)
+ return -EINVAL;
+
+ while ((evt_ent = readdir(caps_dir)) != NULL) {
+ char path[PATH_MAX + NAME_MAX + 1];
+ char *name = evt_ent->d_name;
+ char value[128];
+ FILE *file;
+
+ if (!strcmp(name, ".") || !strcmp(name, ".."))
+ continue;
+
+ snprintf(path, sizeof(path), "%s/%s", caps_path, name);
+
+ file = fopen(path, "r");
+ if (!file)
+ continue;
+
+ if (!fgets(value, sizeof(value), file) ||
+ (perf_pmu__new_caps(&pmu->caps, name, value) < 0)) {
+ fclose(file);
+ continue;
+ }
+
+ nr_caps++;
+ fclose(file);
+ }
+
+ closedir(caps_dir);
+
+ return nr_caps;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 5fb3f16828df..cb6fbec50313 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -22,6 +22,12 @@ enum {
struct perf_event_attr;
+struct perf_pmu_caps {
+ char *name;
+ char *value;
+ struct list_head list;
+};
+
struct perf_pmu {
char *name;
__u32 type;
@@ -33,6 +39,7 @@ struct perf_pmu {
struct perf_cpu_map *cpus;
struct list_head format; /* HEAD struct perf_pmu_format -> list */
struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */
+ struct list_head caps; /* HEAD struct perf_pmu_caps -> list */
struct list_head list; /* ELEM */
};
@@ -65,6 +72,7 @@ struct perf_pmu_alias {
};
struct perf_pmu *perf_pmu__find(const char *name);
+struct perf_pmu *perf_pmu__find_by_type(unsigned int type);
int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
struct list_head *head_terms,
struct parse_events_error *error);
@@ -107,4 +115,6 @@ bool pmu_uncore_alias_match(const char *pmu_name, const char *name);
int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
+int perf_pmu__caps_parse(struct perf_pmu *pmu);
+
#endif /* __PMU_H */
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 83212c65848b..75a9b1d62bba 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -801,7 +801,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
static void pyrf_evsel__delete(struct pyrf_evsel *pevsel)
{
- perf_evsel__exit(&pevsel->evsel);
+ evsel__exit(&pevsel->evsel);
Py_TYPE(pevsel)->tp_free((PyObject*)pevsel);
}
@@ -1044,7 +1044,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
pevent->evsel = evsel;
- err = perf_evsel__parse_sample(evsel, event, &pevent->sample);
+ err = evsel__parse_sample(evsel, event, &pevent->sample);
/* Consume the even only after we parsed it out. */
perf_mmap__consume(&md->core);
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 7def66168503..a4cc11592f6b 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -10,161 +10,64 @@
#include <subcmd/parse-options.h>
#include <perf/cpumap.h>
#include "cloexec.h"
+#include "util/perf_api_probe.h"
#include "record.h"
#include "../perf-sys.h"
-typedef void (*setup_probe_fn_t)(struct evsel *evsel);
-
-static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
+/*
+ * evsel__config_leader_sampling() uses special rules for leader sampling.
+ * However, if the leader is an AUX area event, then assume the event to sample
+ * is the next event.
+ */
+static struct evsel *evsel__read_sampler(struct evsel *evsel, struct evlist *evlist)
{
- struct evlist *evlist;
- struct evsel *evsel;
- unsigned long flags = perf_event_open_cloexec_flag();
- int err = -EAGAIN, fd;
- static pid_t pid = -1;
-
- evlist = evlist__new();
- if (!evlist)
- return -ENOMEM;
-
- if (parse_events(evlist, str, NULL))
- goto out_delete;
-
- evsel = evlist__first(evlist);
+ struct evsel *leader = evsel->leader;
- while (1) {
- fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
- if (fd < 0) {
- if (pid == -1 && errno == EACCES) {
- pid = 0;
- continue;
- }
- goto out_delete;
+ if (evsel__is_aux_event(leader)) {
+ evlist__for_each_entry(evlist, evsel) {
+ if (evsel->leader == leader && evsel != evsel->leader)
+ return evsel;
}
- break;
- }
- close(fd);
-
- fn(evsel);
-
- fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
- if (fd < 0) {
- if (errno == EINVAL)
- err = -EINVAL;
- goto out_delete;
}
- close(fd);
- err = 0;
-
-out_delete:
- evlist__delete(evlist);
- return err;
-}
-
-static bool perf_probe_api(setup_probe_fn_t fn)
-{
- const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
- struct perf_cpu_map *cpus;
- int cpu, ret, i = 0;
-
- cpus = perf_cpu_map__new(NULL);
- if (!cpus)
- return false;
- cpu = cpus->map[0];
- perf_cpu_map__put(cpus);
-
- do {
- ret = perf_do_probe_api(fn, cpu, try[i++]);
- if (!ret)
- return true;
- } while (ret == -EAGAIN && try[i]);
- return false;
+ return leader;
}
-static void perf_probe_sample_identifier(struct evsel *evsel)
+static void evsel__config_leader_sampling(struct evsel *evsel, struct evlist *evlist)
{
- evsel->core.attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
-}
-
-static void perf_probe_comm_exec(struct evsel *evsel)
-{
- evsel->core.attr.comm_exec = 1;
-}
-
-static void perf_probe_context_switch(struct evsel *evsel)
-{
- evsel->core.attr.context_switch = 1;
-}
-
-bool perf_can_sample_identifier(void)
-{
- return perf_probe_api(perf_probe_sample_identifier);
-}
+ struct perf_event_attr *attr = &evsel->core.attr;
+ struct evsel *leader = evsel->leader;
+ struct evsel *read_sampler;
-static bool perf_can_comm_exec(void)
-{
- return perf_probe_api(perf_probe_comm_exec);
-}
+ if (!leader->sample_read)
+ return;
-bool perf_can_record_switch_events(void)
-{
- return perf_probe_api(perf_probe_context_switch);
-}
+ read_sampler = evsel__read_sampler(evsel, evlist);
-bool perf_can_record_cpu_wide(void)
-{
- struct perf_event_attr attr = {
- .type = PERF_TYPE_SOFTWARE,
- .config = PERF_COUNT_SW_CPU_CLOCK,
- .exclude_kernel = 1,
- };
- struct perf_cpu_map *cpus;
- int cpu, fd;
-
- cpus = perf_cpu_map__new(NULL);
- if (!cpus)
- return false;
- cpu = cpus->map[0];
- perf_cpu_map__put(cpus);
+ if (evsel == read_sampler)
+ return;
- fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
- if (fd < 0)
- return false;
- close(fd);
-
- return true;
-}
-
-/*
- * Architectures are expected to know if AUX area sampling is supported by the
- * hardware. Here we check for kernel support.
- */
-bool perf_can_aux_sample(void)
-{
- struct perf_event_attr attr = {
- .size = sizeof(struct perf_event_attr),
- .exclude_kernel = 1,
- /*
- * Non-zero value causes the kernel to calculate the effective
- * attribute size up to that byte.
- */
- .aux_sample_size = 1,
- };
- int fd;
-
- fd = sys_perf_event_open(&attr, -1, 0, -1, 0);
/*
- * If the kernel attribute is big enough to contain aux_sample_size
- * then we assume that it is supported. We are relying on the kernel to
- * validate the attribute size before anything else that could be wrong.
+ * Disable sampling for all group members other than the leader in
+ * case the leader 'leads' the sampling, except when the leader is an
+ * AUX area event, in which case the 2nd event in the group is the one
+ * that 'leads' the sampling.
*/
- if (fd < 0 && errno == E2BIG)
- return false;
- if (fd >= 0)
- close(fd);
+ attr->freq = 0;
+ attr->sample_freq = 0;
+ attr->sample_period = 0;
+ attr->write_backward = 0;
- return true;
+ /*
+ * We don't get a sample for slave events, we make them when delivering
+ * the group leader sample. Set the slave event to follow the master
+ * sample_type to ease up reporting.
+ * An AUX area event also has sample_type requirements, so also include
+ * the sample type bits from the leader's sample_type to cover that
+ * case.
+ */
+ attr->sample_type = read_sampler->core.attr.sample_type |
+ leader->core.attr.sample_type;
}
void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
@@ -188,11 +91,15 @@ void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
use_comm_exec = perf_can_comm_exec();
evlist__for_each_entry(evlist, evsel) {
- perf_evsel__config(evsel, opts, callchain);
+ evsel__config(evsel, opts, callchain);
if (evsel->tracking && use_comm_exec)
evsel->core.attr.comm_exec = 1;
}
+ /* Configure leader sampling here now that the sample type is known */
+ evlist__for_each_entry(evlist, evsel)
+ evsel__config_leader_sampling(evsel, evlist);
+
if (opts->full_auxtrace) {
/*
* Need to be able to synthesize and parse selected events with
@@ -215,7 +122,7 @@ void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
if (sample_id) {
evlist__for_each_entry(evlist, evsel)
- perf_evsel__set_sample_id(evsel, use_sample_identifier);
+ evsel__set_sample_id(evsel, use_sample_identifier);
}
perf_evlist__set_id_pos(evlist);
diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h
index 24316458be20..923565c3b155 100644
--- a/tools/perf/util/record.h
+++ b/tools/perf/util/record.h
@@ -68,6 +68,7 @@ struct record_opts {
int affinity;
int mmap_flush;
unsigned int comp_level;
+ unsigned int nr_threads_synthesize;
};
extern const char * const *record_usage;
diff --git a/tools/perf/util/s390-cpumcf-kernel.h b/tools/perf/util/s390-cpumcf-kernel.h
index d4356030b504..f55ca07f3ca1 100644
--- a/tools/perf/util/s390-cpumcf-kernel.h
+++ b/tools/perf/util/s390-cpumcf-kernel.h
@@ -11,6 +11,7 @@
#define S390_CPUMCF_DIAG_DEF 0xfeef /* Counter diagnostic entry ID */
#define PERF_EVENT_CPUM_CF_DIAG 0xBC000 /* Event: Counter sets */
+#define PERF_EVENT_CPUM_SF_DIAG 0xBD000 /* Event: Combined-sampling */
struct cf_ctrset_entry { /* CPU-M CF counter set entry (8 byte) */
unsigned int def:16; /* 0-15 Data Entry Format */
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index 6785cd87aa4d..f8861998e5bd 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -1047,6 +1047,14 @@ static void s390_cpumsf_free(struct perf_session *session)
free(sf);
}
+static bool
+s390_cpumsf_evsel_is_auxtrace(struct perf_session *session __maybe_unused,
+ struct evsel *evsel)
+{
+ return evsel->core.attr.type == PERF_TYPE_RAW &&
+ evsel->core.attr.config == PERF_EVENT_CPUM_SF_DIAG;
+}
+
static int s390_cpumsf_get_type(const char *cpuid)
{
int ret, family = 0;
@@ -1071,7 +1079,8 @@ static bool check_auxtrace_itrace(struct itrace_synth_opts *itops)
itops->pwr_events || itops->errors ||
itops->dont_decode || itops->calls || itops->returns ||
itops->callchain || itops->thread_stack ||
- itops->last_branch;
+ itops->last_branch || itops->add_callchain ||
+ itops->add_last_branch;
if (!ison)
return true;
pr_err("Unsupported --itrace options specified\n");
@@ -1142,6 +1151,7 @@ int s390_cpumsf_process_auxtrace_info(union perf_event *event,
sf->auxtrace.flush_events = s390_cpumsf_flush;
sf->auxtrace.free_events = s390_cpumsf_free_events;
sf->auxtrace.free = s390_cpumsf_free;
+ sf->auxtrace.evsel_is_auxtrace = s390_cpumsf_evsel_is_auxtrace;
session->auxtrace = &sf->auxtrace;
if (dump_trace)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 2c372cf5495e..739516fdf6e3 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -741,7 +741,7 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
if (!dict_sample)
Py_FatalError("couldn't create Python dictionary");
- pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(perf_evsel__name(evsel)));
+ pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(evsel__name(evsel)));
pydict_set_item_string_decref(dict, "attr", _PyBytes_FromStringAndSize((const char *)&evsel->core.attr, sizeof(evsel->core.attr)));
pydict_set_item_string_decref(dict_sample, "pid",
@@ -968,7 +968,7 @@ static int python_export_evsel(struct db_export *dbe, struct evsel *evsel)
t = tuple_new(2);
tuple_set_u64(t, 0, evsel->db_id);
- tuple_set_string(t, 1, perf_evsel__name(evsel));
+ tuple_set_string(t, 1, evsel__name(evsel));
call_object(tables->evsel_handler, t, "evsel_table");
@@ -1349,7 +1349,7 @@ static void get_handler_name(char *str, size_t size,
{
char *p = str;
- scnprintf(str, size, "stat__%s", perf_evsel__name(evsel));
+ scnprintf(str, size, "stat__%s", evsel__name(evsel));
while ((p = strchr(p, ':'))) {
*p = '_';
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0b0bfe5bef17..c11d89e0ee55 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1059,7 +1059,7 @@ static void callchain__printf(struct evsel *evsel,
unsigned int i;
struct ip_callchain *callchain = sample->callchain;
- if (perf_evsel__has_branch_callstack(evsel))
+ if (evsel__has_branch_callstack(evsel))
callchain__lbr_callstack_printf(sample);
printf("... FP chain: nr:%" PRIu64 "\n", callchain->nr);
@@ -1243,8 +1243,8 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
if (evsel__has_callchain(evsel))
callchain__printf(evsel, sample);
- if (sample_type & PERF_SAMPLE_BRANCH_STACK)
- branch_stack__printf(sample, perf_evsel__has_branch_callstack(evsel));
+ if (evsel__has_br_stack(evsel))
+ branch_stack__printf(sample, evsel__has_branch_callstack(evsel));
if (sample_type & PERF_SAMPLE_REGS_USER)
regs_user__printf(sample);
@@ -1280,8 +1280,7 @@ static void dump_read(struct evsel *evsel, union perf_event *event)
return;
printf(": %d %d %s %" PRI_lu64 "\n", event->read.pid, event->read.tid,
- perf_evsel__name(evsel),
- event->read.value);
+ evsel__name(evsel), event->read.value);
if (!evsel)
return;
diff --git a/tools/perf/util/sideband_evlist.c b/tools/perf/util/sideband_evlist.c
new file mode 100644
index 000000000000..1580a3cbec2d
--- /dev/null
+++ b/tools/perf/util/sideband_evlist.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "util/debug.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/mmap.h"
+#include "util/perf_api_probe.h"
+#include <perf/mmap.h>
+#include <linux/perf_event.h>
+#include <limits.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdbool.h>
+
+int perf_evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr,
+ evsel__sb_cb_t cb, void *data)
+{
+ struct evsel *evsel;
+
+ if (!attr->sample_id_all) {
+ pr_warning("enabling sample_id_all for all side band events\n");
+ attr->sample_id_all = 1;
+ }
+
+ evsel = perf_evsel__new_idx(attr, evlist->core.nr_entries);
+ if (!evsel)
+ return -1;
+
+ evsel->side_band.cb = cb;
+ evsel->side_band.data = data;
+ evlist__add(evlist, evsel);
+ return 0;
+}
+
+static void *perf_evlist__poll_thread(void *arg)
+{
+ struct evlist *evlist = arg;
+ bool draining = false;
+ int i, done = 0;
+ /*
+ * In order to read symbols from other namespaces perf to needs to call
+ * setns(2). This isn't permitted if the struct_fs has multiple users.
+ * unshare(2) the fs so that we may continue to setns into namespaces
+ * that we're observing when, for instance, reading the build-ids at
+ * the end of a 'perf record' session.
+ */
+ unshare(CLONE_FS);
+
+ while (!done) {
+ bool got_data = false;
+
+ if (evlist->thread.done)
+ draining = true;
+
+ if (!draining)
+ evlist__poll(evlist, 1000);
+
+ for (i = 0; i < evlist->core.nr_mmaps; i++) {
+ struct mmap *map = &evlist->mmap[i];
+ union perf_event *event;
+
+ if (perf_mmap__read_init(&map->core))
+ continue;
+ while ((event = perf_mmap__read_event(&map->core)) != NULL) {
+ struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
+
+ if (evsel && evsel->side_band.cb)
+ evsel->side_band.cb(event, evsel->side_band.data);
+ else
+ pr_warning("cannot locate proper evsel for the side band event\n");
+
+ perf_mmap__consume(&map->core);
+ got_data = true;
+ }
+ perf_mmap__read_done(&map->core);
+ }
+
+ if (draining && !got_data)
+ break;
+ }
+ return NULL;
+}
+
+void evlist__set_cb(struct evlist *evlist, evsel__sb_cb_t cb, void *data)
+{
+ struct evsel *evsel;
+
+ evlist__for_each_entry(evlist, evsel) {
+ evsel->core.attr.sample_id_all = 1;
+ evsel->core.attr.watermark = 1;
+ evsel->core.attr.wakeup_watermark = 1;
+ evsel->side_band.cb = cb;
+ evsel->side_band.data = data;
+ }
+}
+
+int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target)
+{
+ struct evsel *counter;
+
+ if (!evlist)
+ return 0;
+
+ if (perf_evlist__create_maps(evlist, target))
+ goto out_delete_evlist;
+
+ if (evlist->core.nr_entries > 1) {
+ bool can_sample_identifier = perf_can_sample_identifier();
+
+ evlist__for_each_entry(evlist, counter)
+ evsel__set_sample_id(counter, can_sample_identifier);
+
+ perf_evlist__set_id_pos(evlist);
+ }
+
+ evlist__for_each_entry(evlist, counter) {
+ if (evsel__open(counter, evlist->core.cpus, evlist->core.threads) < 0)
+ goto out_delete_evlist;
+ }
+
+ if (evlist__mmap(evlist, UINT_MAX))
+ goto out_delete_evlist;
+
+ evlist__for_each_entry(evlist, counter) {
+ if (evsel__enable(counter))
+ goto out_delete_evlist;
+ }
+
+ evlist->thread.done = 0;
+ if (pthread_create(&evlist->thread.th, NULL, perf_evlist__poll_thread, evlist))
+ goto out_delete_evlist;
+
+ return 0;
+
+out_delete_evlist:
+ evlist__delete(evlist);
+ evlist = NULL;
+ return -1;
+}
+
+void perf_evlist__stop_sb_thread(struct evlist *evlist)
+{
+ if (!evlist)
+ return;
+ evlist->thread.done = 1;
+ pthread_join(evlist->thread.th, NULL);
+ evlist__delete(evlist);
+}
diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c
index 3b791ef2cd50..20bacd5972ad 100644
--- a/tools/perf/util/smt.c
+++ b/tools/perf/util/smt.c
@@ -15,6 +15,9 @@ int smt_on(void)
if (cached)
return cached_result;
+ if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) > 0)
+ goto done;
+
ncpu = sysconf(_SC_NPROCESSORS_CONF);
for (cpu = 0; cpu < ncpu; cpu++) {
unsigned long long siblings;
@@ -24,13 +27,13 @@ int smt_on(void)
snprintf(fn, sizeof fn,
"devices/system/cpu/cpu%d/topology/core_cpus", cpu);
- if (access(fn, F_OK) == -1) {
+ if (sysfs__read_str(fn, &str, &strlen) < 0) {
snprintf(fn, sizeof fn,
"devices/system/cpu/cpu%d/topology/thread_siblings",
cpu);
+ if (sysfs__read_str(fn, &str, &strlen) < 0)
+ continue;
}
- if (sysfs__read_str(fn, &str, &strlen) < 0)
- continue;
/* Entry is hex, but does not have 0x, so need custom parser */
siblings = strtoull(str, NULL, 16);
free(str);
@@ -42,6 +45,7 @@ int smt_on(void)
}
if (!cached) {
cached_result = 0;
+done:
cached = true;
}
return cached_result;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index f14cc728c358..c1f8879f92cc 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -237,7 +237,7 @@ static int64_t _sort__addr_cmp(u64 left_ip, u64 right_ip)
return (int64_t)(right_ip - left_ip);
}
-static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
+int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
{
if (!sym_l || !sym_r)
return cmp_null(sym_l, sym_r);
@@ -300,8 +300,14 @@ static int _hist_entry__sym_snprintf(struct map_symbol *ms,
if (verbose > 0) {
char o = map ? dso__symtab_origin(map->dso) : '!';
+ u64 rip = ip;
+
+ if (map && map->dso && map->dso->kernel
+ && map->dso->adjust_symbols)
+ rip = map->unmap_ip(map, ip);
+
ret += repsep_snprintf(bf, size, "%-#*llx %c ",
- BITS_PER_LONG / 4 + 2, ip, o);
+ BITS_PER_LONG / 4 + 2, rip, o);
}
ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
@@ -2354,7 +2360,7 @@ static struct evsel *find_evsel(struct evlist *evlist, char *event_name)
evsel = evlist__first(evlist);
while (--nr > 0)
- evsel = perf_evsel__next(evsel);
+ evsel = evsel__next(evsel);
return evsel;
}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index cfa6ac6f7d06..66d39c4cfe2b 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -311,5 +311,7 @@ int64_t
sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right);
int64_t
sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right);
+int64_t
+_sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r);
char *hist_entry__srcline(struct hist_entry *he);
#endif /* __PERF_SORT_H */
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 9e757d18d713..3c6976f7574c 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -237,8 +237,6 @@ static bool valid_only_metric(const char *unit)
if (!unit)
return false;
if (strstr(unit, "/sec") ||
- strstr(unit, "hz") ||
- strstr(unit, "Hz") ||
strstr(unit, "CPUs utilized"))
return false;
return true;
@@ -248,7 +246,7 @@ static const char *fixunit(char *buf, struct evsel *evsel,
const char *unit)
{
if (!strncmp(unit, "of all", 6)) {
- snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+ snprintf(buf, 1024, "%s %s", evsel__name(evsel),
unit);
return buf;
}
@@ -335,7 +333,7 @@ static int first_shadow_cpu(struct perf_stat_config *config,
if (config->aggr_mode == AGGR_GLOBAL)
return 0;
- for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
+ for (i = 0; i < evsel__nr_cpus(evsel); i++) {
int cpu2 = evsel__cpus(evsel)->map[i];
if (config->aggr_get_id(config, evlist->core.cpus, cpu2) == id)
@@ -369,7 +367,7 @@ static void abs_printout(struct perf_stat_config *config,
config->csv_output ? 0 : config->unit_width,
evsel->unit, config->csv_sep);
- fprintf(output, "%-*s", config->csv_output ? 0 : 25, perf_evsel__name(evsel));
+ fprintf(output, "%-*s", config->csv_output ? 0 : 25, evsel__name(evsel));
print_cgroup(config, evsel);
}
@@ -463,8 +461,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
counter->unit, config->csv_sep);
fprintf(config->output, "%*s",
- config->csv_output ? 0 : -25,
- perf_evsel__name(counter));
+ config->csv_output ? 0 : -25, evsel__name(counter));
print_cgroup(config, counter);
@@ -510,7 +507,7 @@ static void aggr_update_shadow(struct perf_stat_config *config,
id = config->aggr_map->map[s];
evlist__for_each_entry(evlist, counter) {
val = 0;
- for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+ for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
s2 = config->aggr_get_id(config, evlist->core.cpus, cpu);
if (s2 != id)
continue;
@@ -561,11 +558,11 @@ static void collect_all_aliases(struct perf_stat_config *config, struct evsel *c
alias = list_prepare_entry(counter, &(evlist->core.entries), core.node);
list_for_each_entry_continue (alias, &evlist->core.entries, core.node) {
- if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
+ if (strcmp(evsel__name(alias), evsel__name(counter)) ||
alias->scale != counter->scale ||
alias->cgrp != counter->cgrp ||
strcmp(alias->unit, counter->unit) ||
- perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter) ||
+ evsel__is_clock(alias) != evsel__is_clock(counter) ||
!strcmp(alias->pmu_name, counter->pmu_name))
break;
alias->merged_stat = true;
@@ -601,7 +598,7 @@ static void aggr_cb(struct perf_stat_config *config,
struct aggr_data *ad = data;
int cpu, s2;
- for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+ for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
struct perf_counts_values *counts;
s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu);
@@ -849,7 +846,7 @@ static void print_counter(struct perf_stat_config *config,
double uval;
int cpu;
- for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+ for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
struct aggr_data ad = { .cpu = cpu };
if (!collect_data(config, counter, counter_cb, &ad))
@@ -1150,7 +1147,7 @@ static void print_percore_thread(struct perf_stat_config *config,
int s, s2, id;
bool first = true;
- for (int i = 0; i < perf_evsel__nr_cpus(counter); i++) {
+ for (int i = 0; i < evsel__nr_cpus(counter); i++) {
s2 = config->aggr_get_id(config, evsel__cpus(counter), i);
for (s = 0; s < config->aggr_map->nr; s++) {
id = config->aggr_map->map[s];
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 03ecb8cd0eec..129b8c5f2538 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -216,9 +216,9 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
count *= counter->scale;
- if (perf_evsel__is_clock(counter))
+ if (evsel__is_clock(counter))
update_runtime_stat(st, STAT_NSECS, 0, cpu, count_ns);
- else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+ else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
update_runtime_stat(st, STAT_CYCLES, ctx, cpu, count);
else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
update_runtime_stat(st, STAT_CYCLES_IN_TX, ctx, cpu, count);
@@ -241,25 +241,25 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
ctx, cpu, count);
- else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
+ else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
ctx, cpu, count);
- else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
+ else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_BACK,
ctx, cpu, count);
- else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+ else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
update_runtime_stat(st, STAT_BRANCHES, ctx, cpu, count);
- else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
+ else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
update_runtime_stat(st, STAT_CACHEREFS, ctx, cpu, count);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
+ else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
update_runtime_stat(st, STAT_L1_DCACHE, ctx, cpu, count);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
+ else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
update_runtime_stat(st, STAT_L1_ICACHE, ctx, cpu, count);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
+ else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL))
update_runtime_stat(st, STAT_LL_CACHE, ctx, cpu, count);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
+ else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
update_runtime_stat(st, STAT_DTLB_CACHE, ctx, cpu, count);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
+ else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
update_runtime_stat(st, STAT_ITLB_CACHE, ctx, cpu, count);
else if (perf_stat_evsel__is(counter, SMI_NUM))
update_runtime_stat(st, STAT_SMI_NUM, ctx, cpu, count);
@@ -336,7 +336,7 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
metric_events = counter->metric_events;
if (!metric_events) {
if (expr__find_other(counter->metric_expr, counter->name,
- &metric_names, &num_metric_names) < 0)
+ &metric_names, &num_metric_names, 1) < 0)
continue;
metric_events = calloc(sizeof(struct evsel *),
@@ -723,13 +723,14 @@ static void generic_metric(struct perf_stat_config *config,
char *name,
const char *metric_name,
const char *metric_unit,
+ int runtime,
double avg,
int cpu,
struct perf_stat_output_ctx *out,
struct runtime_stat *st)
{
print_metric_t print_metric = out->print_metric;
- struct parse_ctx pctx;
+ struct expr_parse_ctx pctx;
double ratio, scale;
int i;
void *ctxp = out->ctx;
@@ -777,7 +778,7 @@ static void generic_metric(struct perf_stat_config *config,
}
if (!metric_events[i]) {
- if (expr__parse(&ratio, &pctx, metric_expr) == 0) {
+ if (expr__parse(&ratio, &pctx, metric_expr, runtime) == 0) {
char *unit;
char metric_bf[64];
@@ -786,9 +787,13 @@ static void generic_metric(struct perf_stat_config *config,
&unit, &scale) >= 0) {
ratio *= scale;
}
-
- scnprintf(metric_bf, sizeof(metric_bf),
+ if (strstr(metric_expr, "?"))
+ scnprintf(metric_bf, sizeof(metric_bf),
+ "%s %s_%d", unit, metric_name, runtime);
+ else
+ scnprintf(metric_bf, sizeof(metric_bf),
"%s %s", unit, metric_name);
+
print_metric(config, ctxp, NULL, "%8.1f",
metric_bf, ratio);
} else {
@@ -828,7 +833,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
struct metric_event *me;
int num = 1;
- if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
+ if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
if (total) {
@@ -853,7 +858,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
"stalled cycles per insn",
ratio);
}
- } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
+ } else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
print_branch_misses(config, cpu, evsel, avg, out, st);
else
@@ -908,7 +913,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_ll_cache_misses(config, cpu, evsel, avg, out, st);
else
print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
+ } else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
if (total)
@@ -919,11 +924,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
"of all cache refs", ratio);
else
print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
+ } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
+ } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
+ } else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
if (total) {
@@ -974,7 +979,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
ratio = total / avg;
print_metric(config, ctxp, NULL, "%8.0f", "cycles / elision", ratio);
- } else if (perf_evsel__is_clock(evsel)) {
+ } else if (evsel__is_clock(evsel)) {
if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized",
avg / (ratio * evsel->scale));
@@ -1022,7 +1027,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, name, 0);
} else if (evsel->metric_expr) {
generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
- evsel->metric_name, NULL, avg, cpu, out, st);
+ evsel->metric_name, NULL, 1, avg, cpu, out, st);
} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
char unit = 'M';
char unit_buf[10];
@@ -1051,7 +1056,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
out->new_line(config, ctxp);
generic_metric(config, mexp->metric_expr, mexp->metric_events,
evsel->name, mexp->metric_name,
- mexp->metric_unit, avg, cpu, out, st);
+ mexp->metric_unit, mexp->runtime, avg, cpu, out, st);
}
}
if (num == 0)
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 5f26137b8d60..774468341851 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -108,7 +108,7 @@ static void perf_stat_evsel_id_init(struct evsel *evsel)
/* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */
for (i = 0; i < PERF_STAT_EVSEL_ID__MAX; i++) {
- if (!strcmp(perf_evsel__name(evsel), id_str[i])) {
+ if (!strcmp(evsel__name(evsel), id_str[i])) {
ps->id = i;
break;
}
@@ -173,7 +173,7 @@ static void perf_evsel__reset_prev_raw_counts(struct evsel *evsel)
static int perf_evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
{
- int ncpus = perf_evsel__nr_cpus(evsel);
+ int ncpus = evsel__nr_cpus(evsel);
int nthreads = perf_thread_map__nr(evsel->core.threads);
if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
@@ -302,7 +302,7 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
case AGGR_NODE:
case AGGR_NONE:
if (!evsel->snapshot)
- perf_evsel__compute_deltas(evsel, cpu, thread, count);
+ evsel__compute_deltas(evsel, cpu, thread, count);
perf_counts_values__scale(count, config->scale, NULL);
if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) {
perf_stat__update_shadow_stats(evsel, count->val,
@@ -334,7 +334,7 @@ static int process_counter_maps(struct perf_stat_config *config,
struct evsel *counter)
{
int nthreads = perf_thread_map__nr(counter->core.threads);
- int ncpus = perf_evsel__nr_cpus(counter);
+ int ncpus = evsel__nr_cpus(counter);
int cpu, thread;
if (counter->core.system_wide)
@@ -368,8 +368,10 @@ int perf_stat_process_counter(struct perf_stat_config *config,
* interval mode, otherwise overall avg running
* averages will be shown for each interval.
*/
- if (config->interval)
- init_stats(ps->res_stats);
+ if (config->interval) {
+ for (i = 0; i < 3; i++)
+ init_stats(&ps->res_stats[i]);
+ }
if (counter->per_pkg)
zero_per_pkg(counter);
@@ -382,7 +384,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
return 0;
if (!counter->snapshot)
- perf_evsel__compute_deltas(counter, -1, -1, aggr);
+ evsel__compute_deltas(counter, -1, -1, aggr);
perf_counts_values__scale(aggr, config->scale, &counter->counts->scaled);
for (i = 0; i < 3; i++)
@@ -390,7 +392,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
if (verbose > 0) {
fprintf(config->output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
- perf_evsel__name(counter), count[0], count[1], count[2]);
+ evsel__name(counter), count[0], count[1], count[2]);
}
/*
@@ -507,7 +509,7 @@ int create_perf_stat_counter(struct evsel *evsel,
* either manually by us or by kernel via enable_on_exec
* set later.
*/
- if (perf_evsel__is_group_leader(evsel)) {
+ if (evsel__is_group_leader(evsel)) {
attr->disabled = 1;
/*
@@ -519,7 +521,7 @@ int create_perf_stat_counter(struct evsel *evsel,
}
if (target__has_cpu(target) && !target__has_per_thread(target))
- return perf_evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu);
+ return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu);
- return perf_evsel__open_per_thread(evsel, evsel->core.threads);
+ return evsel__open_per_thread(evsel, evsel->core.threads);
}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 26bc6a0096ce..381da6b39f89 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -566,6 +566,20 @@ void dso__sort_by_name(struct dso *dso)
return symbols__sort_by_name(&dso->symbol_names, &dso->symbols);
}
+/*
+ * While we find nice hex chars, build a long_val.
+ * Return number of chars processed.
+ */
+static int hex2u64(const char *ptr, u64 *long_val)
+{
+ char *p;
+
+ *long_val = strtoull(ptr, &p, 16);
+
+ return p - ptr;
+}
+
+
int modules__parse(const char *filename, void *arg,
int (*process_module)(void *arg, const char *name,
u64 start, u64 size))
@@ -1544,6 +1558,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
return true;
case DSO_BINARY_TYPE__BPF_PROG_INFO:
+ case DSO_BINARY_TYPE__BPF_IMAGE:
case DSO_BINARY_TYPE__NOT_FOUND:
default:
return false;
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index a661b122d9d8..89b390623b63 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -37,6 +37,7 @@
#include <string.h>
#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
#include <api/fs/fs.h>
+#include <api/io.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
@@ -71,7 +72,6 @@ int perf_tool__process_synth_event(struct perf_tool *tool,
static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
pid_t *tgid, pid_t *ppid)
{
- char filename[PATH_MAX];
char bf[4096];
int fd;
size_t size = 0;
@@ -81,11 +81,11 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
*tgid = -1;
*ppid = -1;
- snprintf(filename, sizeof(filename), "/proc/%d/status", pid);
+ snprintf(bf, sizeof(bf), "/proc/%d/status", pid);
- fd = open(filename, O_RDONLY);
+ fd = open(bf, O_RDONLY);
if (fd < 0) {
- pr_debug("couldn't open %s\n", filename);
+ pr_debug("couldn't open %s\n", bf);
return -1;
}
@@ -274,6 +274,79 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
return 0;
}
+static bool read_proc_maps_line(struct io *io, __u64 *start, __u64 *end,
+ u32 *prot, u32 *flags, __u64 *offset,
+ u32 *maj, u32 *min,
+ __u64 *inode,
+ ssize_t pathname_size, char *pathname)
+{
+ __u64 temp;
+ int ch;
+ char *start_pathname = pathname;
+
+ if (io__get_hex(io, start) != '-')
+ return false;
+ if (io__get_hex(io, end) != ' ')
+ return false;
+
+ /* map protection and flags bits */
+ *prot = 0;
+ ch = io__get_char(io);
+ if (ch == 'r')
+ *prot |= PROT_READ;
+ else if (ch != '-')
+ return false;
+ ch = io__get_char(io);
+ if (ch == 'w')
+ *prot |= PROT_WRITE;
+ else if (ch != '-')
+ return false;
+ ch = io__get_char(io);
+ if (ch == 'x')
+ *prot |= PROT_EXEC;
+ else if (ch != '-')
+ return false;
+ ch = io__get_char(io);
+ if (ch == 's')
+ *flags = MAP_SHARED;
+ else if (ch == 'p')
+ *flags = MAP_PRIVATE;
+ else
+ return false;
+ if (io__get_char(io) != ' ')
+ return false;
+
+ if (io__get_hex(io, offset) != ' ')
+ return false;
+
+ if (io__get_hex(io, &temp) != ':')
+ return false;
+ *maj = temp;
+ if (io__get_hex(io, &temp) != ' ')
+ return false;
+ *min = temp;
+
+ ch = io__get_dec(io, inode);
+ if (ch != ' ') {
+ *pathname = '\0';
+ return ch == '\n';
+ }
+ do {
+ ch = io__get_char(io);
+ } while (ch == ' ');
+ while (true) {
+ if (ch < 0)
+ return false;
+ if (ch == '\0' || ch == '\n' ||
+ (pathname + 1 - start_pathname) >= pathname_size) {
+ *pathname = '\0';
+ return true;
+ }
+ *pathname++ = ch;
+ ch = io__get_char(io);
+ }
+}
+
int perf_event__synthesize_mmap_events(struct perf_tool *tool,
union perf_event *event,
pid_t pid, pid_t tgid,
@@ -281,9 +354,9 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
struct machine *machine,
bool mmap_data)
{
- char filename[PATH_MAX];
- FILE *fp;
unsigned long long t;
+ char bf[BUFSIZ];
+ struct io io;
bool truncation = false;
unsigned long long timeout = proc_map_timeout * 1000000ULL;
int rc = 0;
@@ -293,59 +366,52 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
if (machine__is_default_guest(machine))
return 0;
- snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps",
- machine->root_dir, pid, pid);
+ snprintf(bf, sizeof(bf), "%s/proc/%d/task/%d/maps",
+ machine->root_dir, pid, pid);
- fp = fopen(filename, "r");
- if (fp == NULL) {
+ io.fd = open(bf, O_RDONLY, 0);
+ if (io.fd < 0) {
/*
* We raced with a task exiting - just return:
*/
- pr_debug("couldn't open %s\n", filename);
+ pr_debug("couldn't open %s\n", bf);
return -1;
}
+ io__init(&io, io.fd, bf, sizeof(bf));
event->header.type = PERF_RECORD_MMAP2;
t = rdclock();
- while (1) {
- char bf[BUFSIZ];
- char prot[5];
- char execname[PATH_MAX];
- char anonstr[] = "//anon";
- unsigned int ino;
+ while (!io.eof) {
+ static const char anonstr[] = "//anon";
size_t size;
- ssize_t n;
- if (fgets(bf, sizeof(bf), fp) == NULL)
- break;
+ /* ensure null termination since stack will be reused. */
+ event->mmap2.filename[0] = '\0';
+
+ /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */
+ if (!read_proc_maps_line(&io,
+ &event->mmap2.start,
+ &event->mmap2.len,
+ &event->mmap2.prot,
+ &event->mmap2.flags,
+ &event->mmap2.pgoff,
+ &event->mmap2.maj,
+ &event->mmap2.min,
+ &event->mmap2.ino,
+ sizeof(event->mmap2.filename),
+ event->mmap2.filename))
+ continue;
if ((rdclock() - t) > timeout) {
- pr_warning("Reading %s time out. "
+ pr_warning("Reading %s/proc/%d/task/%d/maps time out. "
"You may want to increase "
"the time limit by --proc-map-timeout\n",
- filename);
+ machine->root_dir, pid, pid);
truncation = true;
goto out;
}
- /* ensure null termination since stack will be reused. */
- strcpy(execname, "");
-
- /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */
- n = sscanf(bf, "%"PRI_lx64"-%"PRI_lx64" %s %"PRI_lx64" %x:%x %u %[^\n]\n",
- &event->mmap2.start, &event->mmap2.len, prot,
- &event->mmap2.pgoff, &event->mmap2.maj,
- &event->mmap2.min,
- &ino, execname);
-
- /*
- * Anon maps don't have the execname.
- */
- if (n < 7)
- continue;
-
- event->mmap2.ino = (u64)ino;
event->mmap2.ino_generation = 0;
/*
@@ -356,23 +422,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
else
event->header.misc = PERF_RECORD_MISC_GUEST_USER;
- /* map protection and flags bits */
- event->mmap2.prot = 0;
- event->mmap2.flags = 0;
- if (prot[0] == 'r')
- event->mmap2.prot |= PROT_READ;
- if (prot[1] == 'w')
- event->mmap2.prot |= PROT_WRITE;
- if (prot[2] == 'x')
- event->mmap2.prot |= PROT_EXEC;
-
- if (prot[3] == 's')
- event->mmap2.flags |= MAP_SHARED;
- else
- event->mmap2.flags |= MAP_PRIVATE;
-
- if (prot[2] != 'x') {
- if (!mmap_data || prot[0] != 'r')
+ if ((event->mmap2.prot & PROT_EXEC) == 0) {
+ if (!mmap_data || (event->mmap2.prot & PROT_READ) == 0)
continue;
event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
@@ -382,17 +433,17 @@ out:
if (truncation)
event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
- if (!strcmp(execname, ""))
- strcpy(execname, anonstr);
+ if (!strcmp(event->mmap2.filename, ""))
+ strcpy(event->mmap2.filename, anonstr);
if (hugetlbfs_mnt_len &&
- !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) {
- strcpy(execname, anonstr);
+ !strncmp(event->mmap2.filename, hugetlbfs_mnt,
+ hugetlbfs_mnt_len)) {
+ strcpy(event->mmap2.filename, anonstr);
event->mmap2.flags |= MAP_HUGETLB;
}
- size = strlen(execname) + 1;
- memcpy(event->mmap2.filename, execname, size);
+ size = strlen(event->mmap2.filename) + 1;
size = PERF_ALIGN(size, sizeof(u64));
event->mmap2.len -= event->mmap.start;
event->mmap2.header.size = (sizeof(event->mmap2) -
@@ -411,7 +462,7 @@ out:
break;
}
- fclose(fp);
+ close(io.fd);
return rc;
}
@@ -1130,7 +1181,7 @@ void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf
synthesize_mask((struct perf_record_record_cpu_map *)data->data, map, max);
default:
break;
- };
+ }
}
static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map)
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 0885967d5bc3..1b992bbba4e8 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -80,6 +80,10 @@ struct thread_stack_entry {
* @comm: current comm
* @arr_sz: size of array if this is the first element of an array
* @rstate: used to detect retpolines
+ * @br_stack_rb: branch stack (ring buffer)
+ * @br_stack_sz: maximum branch stack size
+ * @br_stack_pos: current position in @br_stack_rb
+ * @mispred_all: mark all branches as mispredicted
*/
struct thread_stack {
struct thread_stack_entry *stack;
@@ -95,6 +99,10 @@ struct thread_stack {
struct comm *comm;
unsigned int arr_sz;
enum retpoline_state_t rstate;
+ struct branch_stack *br_stack_rb;
+ unsigned int br_stack_sz;
+ unsigned int br_stack_pos;
+ bool mispred_all;
};
/*
@@ -126,13 +134,26 @@ static int thread_stack__grow(struct thread_stack *ts)
}
static int thread_stack__init(struct thread_stack *ts, struct thread *thread,
- struct call_return_processor *crp)
+ struct call_return_processor *crp,
+ bool callstack, unsigned int br_stack_sz)
{
int err;
- err = thread_stack__grow(ts);
- if (err)
- return err;
+ if (callstack) {
+ err = thread_stack__grow(ts);
+ if (err)
+ return err;
+ }
+
+ if (br_stack_sz) {
+ size_t sz = sizeof(struct branch_stack);
+
+ sz += br_stack_sz * sizeof(struct branch_entry);
+ ts->br_stack_rb = zalloc(sz);
+ if (!ts->br_stack_rb)
+ return -ENOMEM;
+ ts->br_stack_sz = br_stack_sz;
+ }
if (thread->maps && thread->maps->machine) {
struct machine *machine = thread->maps->machine;
@@ -150,7 +171,9 @@ static int thread_stack__init(struct thread_stack *ts, struct thread *thread,
}
static struct thread_stack *thread_stack__new(struct thread *thread, int cpu,
- struct call_return_processor *crp)
+ struct call_return_processor *crp,
+ bool callstack,
+ unsigned int br_stack_sz)
{
struct thread_stack *ts = thread->ts, *new_ts;
unsigned int old_sz = ts ? ts->arr_sz : 0;
@@ -176,7 +199,7 @@ static struct thread_stack *thread_stack__new(struct thread *thread, int cpu,
ts += cpu;
if (!ts->stack &&
- thread_stack__init(ts, thread, crp))
+ thread_stack__init(ts, thread, crp, callstack, br_stack_sz))
return NULL;
return ts;
@@ -319,6 +342,9 @@ static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts)
if (!crp) {
ts->cnt = 0;
+ ts->br_stack_pos = 0;
+ if (ts->br_stack_rb)
+ ts->br_stack_rb->nr = 0;
return 0;
}
@@ -353,8 +379,33 @@ int thread_stack__flush(struct thread *thread)
return err;
}
+static void thread_stack__update_br_stack(struct thread_stack *ts, u32 flags,
+ u64 from_ip, u64 to_ip)
+{
+ struct branch_stack *bs = ts->br_stack_rb;
+ struct branch_entry *be;
+
+ if (!ts->br_stack_pos)
+ ts->br_stack_pos = ts->br_stack_sz;
+
+ ts->br_stack_pos -= 1;
+
+ be = &bs->entries[ts->br_stack_pos];
+ be->from = from_ip;
+ be->to = to_ip;
+ be->flags.value = 0;
+ be->flags.abort = !!(flags & PERF_IP_FLAG_TX_ABORT);
+ be->flags.in_tx = !!(flags & PERF_IP_FLAG_IN_TX);
+ /* No support for mispredict */
+ be->flags.mispred = ts->mispred_all;
+
+ if (bs->nr < ts->br_stack_sz)
+ bs->nr += 1;
+}
+
int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
- u64 to_ip, u16 insn_len, u64 trace_nr)
+ u64 to_ip, u16 insn_len, u64 trace_nr, bool callstack,
+ unsigned int br_stack_sz, bool mispred_all)
{
struct thread_stack *ts = thread__stack(thread, cpu);
@@ -362,12 +413,13 @@ int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
return -EINVAL;
if (!ts) {
- ts = thread_stack__new(thread, cpu, NULL);
+ ts = thread_stack__new(thread, cpu, NULL, callstack, br_stack_sz);
if (!ts) {
pr_warning("Out of memory: no thread stack\n");
return -ENOMEM;
}
ts->trace_nr = trace_nr;
+ ts->mispred_all = mispred_all;
}
/*
@@ -381,8 +433,14 @@ int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
ts->trace_nr = trace_nr;
}
- /* Stop here if thread_stack__process() is in use */
- if (ts->crp)
+ if (br_stack_sz)
+ thread_stack__update_br_stack(ts, flags, from_ip, to_ip);
+
+ /*
+ * Stop here if thread_stack__process() is in use, or not recording call
+ * stack.
+ */
+ if (ts->crp || !callstack)
return 0;
if (flags & PERF_IP_FLAG_CALL) {
@@ -430,6 +488,7 @@ static void __thread_stack__free(struct thread *thread, struct thread_stack *ts)
{
__thread_stack__flush(thread, ts);
zfree(&ts->stack);
+ zfree(&ts->br_stack_rb);
}
static void thread_stack__reset(struct thread *thread, struct thread_stack *ts)
@@ -497,6 +556,199 @@ void thread_stack__sample(struct thread *thread, int cpu,
chain->nr = i;
}
+/*
+ * Hardware sample records, created some time after the event occurred, need to
+ * have subsequent addresses removed from the call chain.
+ */
+void thread_stack__sample_late(struct thread *thread, int cpu,
+ struct ip_callchain *chain, size_t sz,
+ u64 sample_ip, u64 kernel_start)
+{
+ struct thread_stack *ts = thread__stack(thread, cpu);
+ u64 sample_context = callchain_context(sample_ip, kernel_start);
+ u64 last_context, context, ip;
+ size_t nr = 0, j;
+
+ if (sz < 2) {
+ chain->nr = 0;
+ return;
+ }
+
+ if (!ts)
+ goto out;
+
+ /*
+ * When tracing kernel space, kernel addresses occur at the top of the
+ * call chain after the event occurred but before tracing stopped.
+ * Skip them.
+ */
+ for (j = 1; j <= ts->cnt; j++) {
+ ip = ts->stack[ts->cnt - j].ret_addr;
+ context = callchain_context(ip, kernel_start);
+ if (context == PERF_CONTEXT_USER ||
+ (context == sample_context && ip == sample_ip))
+ break;
+ }
+
+ last_context = sample_ip; /* Use sample_ip as an invalid context */
+
+ for (; nr < sz && j <= ts->cnt; nr++, j++) {
+ ip = ts->stack[ts->cnt - j].ret_addr;
+ context = callchain_context(ip, kernel_start);
+ if (context != last_context) {
+ if (nr >= sz - 1)
+ break;
+ chain->ips[nr++] = context;
+ last_context = context;
+ }
+ chain->ips[nr] = ip;
+ }
+out:
+ if (nr) {
+ chain->nr = nr;
+ } else {
+ chain->ips[0] = sample_context;
+ chain->ips[1] = sample_ip;
+ chain->nr = 2;
+ }
+}
+
+void thread_stack__br_sample(struct thread *thread, int cpu,
+ struct branch_stack *dst, unsigned int sz)
+{
+ struct thread_stack *ts = thread__stack(thread, cpu);
+ const size_t bsz = sizeof(struct branch_entry);
+ struct branch_stack *src;
+ struct branch_entry *be;
+ unsigned int nr;
+
+ dst->nr = 0;
+
+ if (!ts)
+ return;
+
+ src = ts->br_stack_rb;
+ if (!src->nr)
+ return;
+
+ dst->nr = min((unsigned int)src->nr, sz);
+
+ be = &dst->entries[0];
+ nr = min(ts->br_stack_sz - ts->br_stack_pos, (unsigned int)dst->nr);
+ memcpy(be, &src->entries[ts->br_stack_pos], bsz * nr);
+
+ if (src->nr >= ts->br_stack_sz) {
+ sz -= nr;
+ be = &dst->entries[nr];
+ nr = min(ts->br_stack_pos, sz);
+ memcpy(be, &src->entries[0], bsz * ts->br_stack_pos);
+ }
+}
+
+/* Start of user space branch entries */
+static bool us_start(struct branch_entry *be, u64 kernel_start, bool *start)
+{
+ if (!*start)
+ *start = be->to && be->to < kernel_start;
+
+ return *start;
+}
+
+/*
+ * Start of branch entries after the ip fell in between 2 branches, or user
+ * space branch entries.
+ */
+static bool ks_start(struct branch_entry *be, u64 sample_ip, u64 kernel_start,
+ bool *start, struct branch_entry *nb)
+{
+ if (!*start) {
+ *start = (nb && sample_ip >= be->to && sample_ip <= nb->from) ||
+ be->from < kernel_start ||
+ (be->to && be->to < kernel_start);
+ }
+
+ return *start;
+}
+
+/*
+ * Hardware sample records, created some time after the event occurred, need to
+ * have subsequent addresses removed from the branch stack.
+ */
+void thread_stack__br_sample_late(struct thread *thread, int cpu,
+ struct branch_stack *dst, unsigned int sz,
+ u64 ip, u64 kernel_start)
+{
+ struct thread_stack *ts = thread__stack(thread, cpu);
+ struct branch_entry *d, *s, *spos, *ssz;
+ struct branch_stack *src;
+ unsigned int nr = 0;
+ bool start = false;
+
+ dst->nr = 0;
+
+ if (!ts)
+ return;
+
+ src = ts->br_stack_rb;
+ if (!src->nr)
+ return;
+
+ spos = &src->entries[ts->br_stack_pos];
+ ssz = &src->entries[ts->br_stack_sz];
+
+ d = &dst->entries[0];
+ s = spos;
+
+ if (ip < kernel_start) {
+ /*
+ * User space sample: start copying branch entries when the
+ * branch is in user space.
+ */
+ for (s = spos; s < ssz && nr < sz; s++) {
+ if (us_start(s, kernel_start, &start)) {
+ *d++ = *s;
+ nr += 1;
+ }
+ }
+
+ if (src->nr >= ts->br_stack_sz) {
+ for (s = &src->entries[0]; s < spos && nr < sz; s++) {
+ if (us_start(s, kernel_start, &start)) {
+ *d++ = *s;
+ nr += 1;
+ }
+ }
+ }
+ } else {
+ struct branch_entry *nb = NULL;
+
+ /*
+ * Kernel space sample: start copying branch entries when the ip
+ * falls in between 2 branches (or the branch is in user space
+ * because then the start must have been missed).
+ */
+ for (s = spos; s < ssz && nr < sz; s++) {
+ if (ks_start(s, ip, kernel_start, &start, nb)) {
+ *d++ = *s;
+ nr += 1;
+ }
+ nb = s;
+ }
+
+ if (src->nr >= ts->br_stack_sz) {
+ for (s = &src->entries[0]; s < spos && nr < sz; s++) {
+ if (ks_start(s, ip, kernel_start, &start, nb)) {
+ *d++ = *s;
+ nr += 1;
+ }
+ nb = s;
+ }
+ }
+ }
+
+ dst->nr = nr;
+}
+
struct call_return_processor *
call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data),
void *data)
@@ -864,7 +1116,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
}
if (!ts) {
- ts = thread_stack__new(thread, sample->cpu, crp);
+ ts = thread_stack__new(thread, sample->cpu, crp, true, 0);
if (!ts)
return -ENOMEM;
ts->comm = comm;
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index e1ec5a58f1b2..3bc47a42af8e 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -81,10 +81,19 @@ struct call_return_processor {
};
int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
- u64 to_ip, u16 insn_len, u64 trace_nr);
+ u64 to_ip, u16 insn_len, u64 trace_nr, bool callstack,
+ unsigned int br_stack_sz, bool mispred_all);
void thread_stack__set_trace_nr(struct thread *thread, int cpu, u64 trace_nr);
void thread_stack__sample(struct thread *thread, int cpu, struct ip_callchain *chain,
size_t sz, u64 ip, u64 kernel_start);
+void thread_stack__sample_late(struct thread *thread, int cpu,
+ struct ip_callchain *chain, size_t sz, u64 ip,
+ u64 kernel_start);
+void thread_stack__br_sample(struct thread *thread, int cpu,
+ struct branch_stack *dst, unsigned int sz);
+void thread_stack__br_sample_late(struct thread *thread, int cpu,
+ struct branch_stack *dst, unsigned int sz,
+ u64 sample_ip, u64 kernel_start);
int thread_stack__flush(struct thread *thread);
void thread_stack__free(struct thread *thread);
size_t thread_stack__depth(struct thread *thread, int cpu);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 28b719388028..665e5c0618ed 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -47,6 +47,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
thread->tid = tid;
thread->ppid = -1;
thread->cpu = -1;
+ thread->lbr_stitch_enable = false;
INIT_LIST_HEAD(&thread->namespaces_list);
INIT_LIST_HEAD(&thread->comm_list);
init_rwsem(&thread->namespaces_lock);
@@ -110,6 +111,7 @@ void thread__delete(struct thread *thread)
exit_rwsem(&thread->namespaces_lock);
exit_rwsem(&thread->comm_lock);
+ thread__free_stitch_list(thread);
free(thread);
}
@@ -452,3 +454,25 @@ int thread__memcpy(struct thread *thread, struct machine *machine,
return dso__data_read_offset(al.map->dso, machine, offset, buf, len);
}
+
+void thread__free_stitch_list(struct thread *thread)
+{
+ struct lbr_stitch *lbr_stitch = thread->lbr_stitch;
+ struct stitch_list *pos, *tmp;
+
+ if (!lbr_stitch)
+ return;
+
+ list_for_each_entry_safe(pos, tmp, &lbr_stitch->lists, node) {
+ list_del_init(&pos->node);
+ free(pos);
+ }
+
+ list_for_each_entry_safe(pos, tmp, &lbr_stitch->free_lists, node) {
+ list_del_init(&pos->node);
+ free(pos);
+ }
+
+ zfree(&lbr_stitch->prev_lbr_cursor);
+ zfree(&thread->lbr_stitch);
+}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 20b96b5d1f15..b066fb30d203 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -13,6 +13,8 @@
#include <strlist.h>
#include <intlist.h>
#include "rwsem.h"
+#include "event.h"
+#include "callchain.h"
struct addr_location;
struct map;
@@ -20,6 +22,13 @@ struct perf_record_namespaces;
struct thread_stack;
struct unwind_libunwind_ops;
+struct lbr_stitch {
+ struct list_head lists;
+ struct list_head free_lists;
+ struct perf_sample prev_sample;
+ struct callchain_cursor_node *prev_lbr_cursor;
+};
+
struct thread {
union {
struct rb_node rb_node;
@@ -46,6 +55,10 @@ struct thread {
struct srccode_state srccode_state;
bool filter;
int filter_entry_depth;
+
+ /* LBR call stack stitch */
+ bool lbr_stitch_enable;
+ struct lbr_stitch *lbr_stitch;
};
struct machine;
@@ -142,4 +155,6 @@ static inline bool thread__is_filtered(struct thread *thread)
return false;
}
+void thread__free_stitch_list(struct thread *thread);
+
#endif /* __PERF_THREAD_H */
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index 3dce2de9d005..27945eeb0cb5 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -77,7 +77,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
opts->freq ? "Hz" : "");
}
- ret += SNPRINTF(bf + ret, size - ret, "%s", perf_evsel__name(top->sym_evsel));
+ ret += SNPRINTF(bf + ret, size - ret, "%s", evsel__name(top->sym_evsel));
ret += SNPRINTF(bf + ret, size - ret, "], ");
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index f117d4f4821e..ff8391208ecd 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -18,7 +18,7 @@ struct perf_session;
struct perf_top {
struct perf_tool tool;
- struct evlist *evlist;
+ struct evlist *evlist, *sb_evlist;
struct record_opts record_opts;
struct annotation_options annotation_opts;
struct evswitch evswitch;
@@ -36,6 +36,7 @@ struct perf_top {
bool use_tui, use_stdio;
bool vmlinux_warned;
bool dump_symtab;
+ bool stitch_lbr;
struct hist_entry *sym_filter_entry;
struct evsel *sym_evsel;
struct perf_session *session;
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 8593d3c200c6..f507dff713c9 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -75,7 +75,7 @@ static void skip(int size)
r = size > BUFSIZ ? BUFSIZ : size;
do_read(buf, r);
size -= r;
- };
+ }
}
static unsigned int read4(struct tep_handle *pevent)
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index d707c9624dd9..37a9492edb3e 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -290,6 +290,7 @@ int perf_event_paranoid(void)
bool perf_event_paranoid_check(int max_level)
{
return perf_cap__capable(CAP_SYS_ADMIN) ||
+ perf_cap__capable(CAP_PERFMON) ||
perf_event_paranoid() <= max_level;
}