summaryrefslogtreecommitdiffstats
path: root/tools/perf/util/intel-pt.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util/intel-pt.c')
-rw-r--r--tools/perf/util/intel-pt.c65
1 files changed, 45 insertions, 20 deletions
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 0effaff57020..149ff361ca78 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -206,6 +206,16 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf,
intel_pt_dump(pt, buf, len);
}
+static void intel_pt_log_event(union perf_event *event)
+{
+ FILE *f = intel_pt_log_fp();
+
+ if (!intel_pt_enable_logging || !f)
+ return;
+
+ perf_event__fprintf(event, f);
+}
+
static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
struct auxtrace_buffer *b)
{
@@ -407,6 +417,13 @@ intel_pt_cache_lookup(struct dso *dso, struct machine *machine, u64 offset)
return auxtrace_cache__lookup(dso->auxtrace_cache, offset);
}
+static inline u8 intel_pt_cpumode(struct intel_pt *pt, uint64_t ip)
+{
+ return ip >= pt->kernel_start ?
+ PERF_RECORD_MISC_KERNEL :
+ PERF_RECORD_MISC_USER;
+}
+
static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
uint64_t *insn_cnt_ptr, uint64_t *ip,
uint64_t to_ip, uint64_t max_insn_cnt,
@@ -429,10 +446,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
if (to_ip && *ip == to_ip)
goto out_no_cache;
- if (*ip >= ptq->pt->kernel_start)
- cpumode = PERF_RECORD_MISC_KERNEL;
- else
- cpumode = PERF_RECORD_MISC_USER;
+ cpumode = intel_pt_cpumode(ptq->pt, *ip);
thread = ptq->thread;
if (!thread) {
@@ -442,8 +456,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
}
while (1) {
- thread__find_addr_map(thread, cpumode, MAP__FUNCTION, *ip, &al);
- if (!al.map || !al.map->dso)
+ if (!thread__find_map(thread, cpumode, *ip, &al) || !al.map->dso)
return -EINVAL;
if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
@@ -596,8 +609,7 @@ static int __intel_pt_pgd_ip(uint64_t ip, void *data)
if (!thread)
return -EINVAL;
- thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al);
- if (!al.map || !al.map->dso)
+ if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso)
return -EINVAL;
offset = al.map->map_ip(al.map, ip);
@@ -751,6 +763,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
unsigned int queue_nr)
{
struct intel_pt_params params = { .get_trace = 0, };
+ struct perf_env *env = pt->machine->env;
struct intel_pt_queue *ptq;
ptq = zalloc(sizeof(struct intel_pt_queue));
@@ -760,7 +773,8 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
if (pt->synth_opts.callchain) {
size_t sz = sizeof(struct ip_callchain);
- sz += pt->synth_opts.callchain_sz * sizeof(u64);
+ /* Add 1 to callchain_sz for callchain context */
+ sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
ptq->chain = zalloc(sz);
if (!ptq->chain)
goto out_free;
@@ -832,6 +846,9 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
}
}
+ if (env->cpuid && !strncmp(env->cpuid, "GenuineIntel,6,92,", 18))
+ params.flags |= INTEL_PT_FUP_WITH_NLIP;
+
ptq->decoder = intel_pt_decoder_new(&params);
if (!ptq->decoder)
goto out_free;
@@ -906,6 +923,11 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
ptq->insn_len = ptq->state->insn_len;
memcpy(ptq->insn, ptq->state->insn, INTEL_PT_INSN_BUF_SZ);
}
+
+ if (ptq->state->type & INTEL_PT_TRACE_BEGIN)
+ ptq->flags |= PERF_IP_FLAG_TRACE_BEGIN;
+ if (ptq->state->type & INTEL_PT_TRACE_END)
+ ptq->flags |= PERF_IP_FLAG_TRACE_END;
}
static int intel_pt_setup_queue(struct intel_pt *pt,
@@ -1051,15 +1073,11 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
union perf_event *event,
struct perf_sample *sample)
{
- event->sample.header.type = PERF_RECORD_SAMPLE;
- event->sample.header.misc = PERF_RECORD_MISC_USER;
- event->sample.header.size = sizeof(struct perf_event_header);
-
if (!pt->timeless_decoding)
sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
- sample->cpumode = PERF_RECORD_MISC_USER;
sample->ip = ptq->state->from_ip;
+ sample->cpumode = intel_pt_cpumode(pt, sample->ip);
sample->pid = ptq->pid;
sample->tid = ptq->tid;
sample->addr = ptq->state->to_ip;
@@ -1068,6 +1086,10 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
sample->flags = ptq->flags;
sample->insn_len = ptq->insn_len;
memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
+
+ event->sample.header.type = PERF_RECORD_SAMPLE;
+ event->sample.header.misc = sample->cpumode;
+ event->sample.header.size = sizeof(struct perf_event_header);
}
static int intel_pt_inject_event(union perf_event *event,
@@ -1153,7 +1175,8 @@ static void intel_pt_prep_sample(struct intel_pt *pt,
if (pt->synth_opts.callchain) {
thread_stack__sample(ptq->thread, ptq->chain,
- pt->synth_opts.callchain_sz, sample->ip);
+ pt->synth_opts.callchain_sz + 1,
+ sample->ip, pt->kernel_start);
sample->callchain = ptq->chain;
}
@@ -1523,6 +1546,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
if (intel_pt_is_switch_ip(ptq, state->to_ip)) {
switch (ptq->switch_state) {
+ case INTEL_PT_SS_NOT_TRACING:
case INTEL_PT_SS_UNKNOWN:
case INTEL_PT_SS_EXPECTING_SWITCH_IP:
err = intel_pt_next_tid(pt, ptq);
@@ -1565,7 +1589,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip)
if (map__load(map))
return 0;
- start = dso__first_symbol(map->dso, MAP__FUNCTION);
+ start = dso__first_symbol(map->dso);
for (sym = start; sym; sym = dso__next_symbol(sym)) {
if (sym->binding == STB_GLOBAL &&
@@ -1996,9 +2020,9 @@ static int intel_pt_process_event(struct perf_session *session,
event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)
err = intel_pt_context_switch(pt, event, sample);
- intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n",
- perf_event__name(event->header.type), event->header.type,
- sample->cpu, sample->time, timestamp);
+ intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ",
+ event->header.type, sample->cpu, sample->time, timestamp);
+ intel_pt_log_event(event);
return err;
}
@@ -2551,7 +2575,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
pt->synth_opts = *session->itrace_synth_opts;
} else {
- itrace_synth_opts__set_default(&pt->synth_opts);
+ itrace_synth_opts__set_default(&pt->synth_opts,
+ session->itrace_synth_opts->default_no_sample);
if (use_browser != -1) {
pt->synth_opts.branches = false;
pt->synth_opts.callchain = true;
OpenPOWER on IntegriCloud