1 files changed, 102 insertions, 16 deletions

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 9b7cc5f909b0..09756aeeb841 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"
 
@@ -124,6 +125,8 @@ struct intel_pt {
 
 	struct range *time_ranges;
 	unsigned int range_cnt;
+
+	struct ip_callchain *chain;
 };
 
 enum switch_state {
@@ -233,6 +236,24 @@ static void intel_pt_log_event(union perf_event *event)
 	perf_event__fprintf(event, f);
 }
 
+static bool intel_pt_log_events(struct intel_pt *pt, u64 tm)
+{
+	struct perf_time_interval *range = pt->synth_opts.ptime_range;
+	int n = pt->synth_opts.range_num;
+
+	if (pt->synth_opts.log_plus_flags & AUXTRACE_LOG_FLG_ALL_PERF_EVTS)
+		return true;
+
+	if (pt->synth_opts.log_minus_flags & AUXTRACE_LOG_FLG_ALL_PERF_EVTS)
+		return false;
+
+	/* perf_time__ranges_skip_sample does not work if time is zero */
+	if (!tm)
+		tm = 1;
+
+	return !n || !perf_time__ranges_skip_sample(range, n, tm);
+}
+
 static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
 				   struct auxtrace_buffer *b)
 {
@@ -848,6 +869,45 @@ 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 intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 						   unsigned int queue_nr)
 {
@@ -860,11 +920,7 @@ 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;
 	}
@@ -1970,7 +2026,8 @@ 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)
+	if (pt->synth_opts.callchain || pt->synth_opts.add_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);
@@ -2492,10 +2549,6 @@ static int intel_pt_context_switch(struct intel_pt *pt, union perf_event *event,
 	if (tid == -1)
 		intel_pt_log("context_switch event has no tid\n");
 
-	intel_pt_log("context_switch: cpu %d pid %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
-		     cpu, pid, tid, sample->time, perf_time_to_tsc(sample->time,
-		     &pt->tc));
-
 	ret = intel_pt_sync_switch(pt, cpu, tid, sample->time);
 	if (ret <= 0)
 		return ret;
@@ -2561,6 +2614,11 @@ 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 (event->header.type == PERF_RECORD_AUX &&
 	    (event->aux.flags & PERF_AUX_FLAG_TRUNCATED) &&
 	    pt->synth_opts.errors) {
@@ -2577,9 +2635,11 @@ 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 %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ",
-		     event->header.type, sample->cpu, sample->time, timestamp);
-	intel_pt_log_event(event);
+	if (intel_pt_enable_logging && intel_pt_log_events(pt, sample->time)) {
+		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;
 }
@@ -2632,11 +2692,21 @@ 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)
@@ -3038,6 +3108,7 @@ static const char * const intel_pt_info_fmts[] = {
 	[INTEL_PT_SNAPSHOT_MODE]	= "  Snapshot mode       %"PRId64"\n",
 	[INTEL_PT_PER_CPU_MMAPS]	= "  Per-cpu maps        %"PRId64"\n",
 	[INTEL_PT_MTC_BIT]		= "  MTC bit             %#"PRIx64"\n",
+	[INTEL_PT_MTC_FREQ_BITS]	= "  MTC freq bits       %#"PRIx64"\n",
 	[INTEL_PT_TSC_CTC_N]		= "  TSC:CTC numerator   %"PRIu64"\n",
 	[INTEL_PT_TSC_CTC_D]		= "  TSC:CTC denominator %"PRIu64"\n",
 	[INTEL_PT_CYC_BIT]		= "  CYC bit             %#"PRIx64"\n",
@@ -3052,8 +3123,12 @@ static void intel_pt_print_info(__u64 *arr, int start, int finish)
 	if (!dump_trace)
 		return;
 
-	for (i = start; i <= finish; i++)
-		fprintf(stdout, intel_pt_info_fmts[i], arr[i]);
+	for (i = start; i <= finish; i++) {
+		const char *fmt = intel_pt_info_fmts[i];
+
+		if (fmt)
+			fprintf(stdout, fmt, arr[i]);
+	}
 }
 
 static void intel_pt_print_info_str(const char *name, const char *str)
@@ -3208,6 +3283,7 @@ 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)
@@ -3236,6 +3312,7 @@ 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;
@@ -3268,14 +3345,22 @@ 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;
+	}
+
 	err = intel_pt_synth_events(pt, session);
 	if (err)
 		goto err_delete_thread;
@@ -3295,6 +3380,7 @@ 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();