perf cs_etm: Set the time field in the synthetic samples

If virtual timestamps are detected, set sample time field accordingly,
otherwise warn the user that the samples will not include accurate
time data.

  | Test notes (FEAT_TRF platform)
  |
  | $ ./perf record -e cs_etm//u -a -- sleep 4
  | $ ./perf script --fields +time
  | 	    perf   422 [000]   163.375100:          1 branches:uH:                 0 [unknown] ([unknown])
  | 	    perf   422 [000]   163.375100:          1 branches:uH:      ffffb8009544 ioctl+0x14 (/lib/aarch64-linux-gnu/libc-2.27.so)
  | 	    perf   422 [000]   163.375100:          1 branches:uH:      aaaaab6bebf4 perf_evsel__run_ioctl+0x90 (/home/german/linux/tools/perf/perf)
  | [...]
  | 	    perf   422 [000]   167.393100:          1 branches:uH:      aaaaab6bda00 __xyarray__entry+0x74 (/home/german/linux/tools/perf/perf)
  | 	    perf   422 [000]   167.393099:          1 branches:uH:      aaaaab6bda0c __xyarray__entry+0x80 (/home/german/linux/tools/perf/perf)
  | 	    perf   422 [000]   167.393099:          1 branches:uH:      ffffb8009538 ioctl+0x8 (/lib/aarch64-linux-gnu/libc-2.27.so)
  |
  | The time from the first sample to the last sample is 4 seconds

Now that times are converted to nanoseconds, also try to estimate the
timestamps more accurately be dividing by some fixed value for
instructions per ns. This prevents long ranges from being estimated
too far in the past than would be realistic.

Signed-off-by: German Gomez <german.gomez@arm.com>
Acked-by: Suzuki Poulouse <suzuki.poulose@arm.com>
Tested-by: Tanmay Jagdale <tanmay@marvell.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Bharat Bhushan <bbhushan2@marvell.com>
Cc: George Cherian <gcherian@marvell.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Linu Cherian <lcherian@marvell.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Cc: Will Deacon <will@kernel.org>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230120143702.4035046-8-james.clark@arm.com
Signed-off-by: James Clark <james.clark@arm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 79 insertions, 4 deletions

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 879576d5f899..f65bac5ddbdb 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -35,6 +35,7 @@
 #include "tool.h"
 #include "thread.h"
 #include "thread-stack.h"
+#include "tsc.h"
 #include <tools/libc_compat.h>
 #include "util/synthetic-events.h"
 
@@ -46,10 +47,12 @@ struct cs_etm_auxtrace {
 	struct perf_session *session;
 	struct machine *machine;
 	struct thread *unknown_thread;
+	struct perf_tsc_conversion tc;
 
 	u8 timeless_decoding;
 	u8 snapshot_mode;
 	u8 data_queued;
+	u8 has_virtual_ts; /* Virtual/Kernel timestamps in the trace. */
 
 	int num_cpu;
 	u64 latest_kernel_timestamp;
@@ -1161,6 +1164,30 @@ static void cs_etm__copy_insn(struct cs_etm_queue *etmq,
 			   sample->insn_len, (void *)sample->insn);
 }
 
+u64 cs_etm__convert_sample_time(struct cs_etm_queue *etmq, u64 cs_timestamp)
+{
+	struct cs_etm_auxtrace *etm = etmq->etm;
+
+	if (etm->has_virtual_ts)
+		return tsc_to_perf_time(cs_timestamp, &etm->tc);
+	else
+		return cs_timestamp;
+}
+
+static inline u64 cs_etm__resolve_sample_time(struct cs_etm_queue *etmq,
+					       struct cs_etm_traceid_queue *tidq)
+{
+	struct cs_etm_auxtrace *etm = etmq->etm;
+	struct cs_etm_packet_queue *packet_queue = &tidq->packet_queue;
+
+	if (etm->timeless_decoding)
+		return 0;
+	else if (etm->has_virtual_ts)
+		return packet_queue->cs_timestamp;
+	else
+		return etm->latest_kernel_timestamp;
+}
+
 static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 					    struct cs_etm_traceid_queue *tidq,
 					    u64 addr, u64 period)
@@ -1174,8 +1201,9 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	event->sample.header.misc = cs_etm__cpu_mode(etmq, addr);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
-	if (!etm->timeless_decoding)
-		sample.time = etm->latest_kernel_timestamp;
+	/* Set time field based on etm auxtrace config. */
+	sample.time = cs_etm__resolve_sample_time(etmq, tidq);
+
 	sample.ip = addr;
 	sample.pid = tidq->pid;
 	sample.tid = tidq->tid;
@@ -1232,8 +1260,9 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	event->sample.header.misc = cs_etm__cpu_mode(etmq, ip);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
-	if (!etm->timeless_decoding)
-		sample.time = etm->latest_kernel_timestamp;
+	/* Set time field based on etm auxtrace config. */
+	sample.time = cs_etm__resolve_sample_time(etmq, tidq);
+
 	sample.ip = ip;
 	sample.pid = tidq->pid;
 	sample.tid = tidq->tid;
@@ -2746,12 +2775,42 @@ static int cs_etm__queue_aux_records(struct perf_session *session)
 	return 0;
 }
 
+#define HAS_PARAM(j, type, param) (metadata[(j)][CS_ETM_NR_TRC_PARAMS] <= \
+				  (CS_##type##_##param - CS_ETM_COMMON_BLK_MAX_V1))
+
+/*
+ * Loop through the ETMs and complain if we find at least one where ts_source != 1 (virtual
+ * timestamps).
+ */
+static bool cs_etm__has_virtual_ts(u64 **metadata, int num_cpu)
+{
+	int j;
+
+	for (j = 0; j < num_cpu; j++) {
+		switch (metadata[j][CS_ETM_MAGIC]) {
+		case __perf_cs_etmv4_magic:
+			if (HAS_PARAM(j, ETMV4, TS_SOURCE) || metadata[j][CS_ETMV4_TS_SOURCE] != 1)
+				return false;
+			break;
+		case __perf_cs_ete_magic:
+			if (HAS_PARAM(j, ETE, TS_SOURCE) || metadata[j][CS_ETE_TS_SOURCE] != 1)
+				return false;
+			break;
+		default:
+			/* Unknown / unsupported magic number. */
+			return false;
+		}
+	}
+	return true;
+}
+
 int cs_etm__process_auxtrace_info_full(union perf_event *event,
 				       struct perf_session *session)
 {
 	struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
 	struct cs_etm_auxtrace *etm = NULL;
 	struct int_node *inode;
+	struct perf_record_time_conv *tc = &session->time_conv;
 	int event_header_size = sizeof(struct perf_event_header);
 	int total_size = auxtrace_info->header.size;
 	int priv_size = 0;
@@ -2886,6 +2945,13 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
 	etm->auxtrace_type = auxtrace_info->type;
 	etm->timeless_decoding = cs_etm__is_timeless_decoding(etm);
 
+	/* Use virtual timestamps if all ETMs report ts_source = 1 */
+	etm->has_virtual_ts = cs_etm__has_virtual_ts(metadata, num_cpu);
+
+	if (!etm->has_virtual_ts)
+		ui__warning("Virtual timestamps are not enabled, or not supported by the traced system.\n"
+			    "The time field of the samples will not be set accurately.\n\n");
+
 	etm->auxtrace.process_event = cs_etm__process_event;
 	etm->auxtrace.process_auxtrace_event = cs_etm__process_auxtrace_event;
 	etm->auxtrace.flush_events = cs_etm__flush_events;
@@ -2915,6 +2981,15 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
 		goto err_delete_thread;
 	}
 
+	etm->tc.time_shift = tc->time_shift;
+	etm->tc.time_mult = tc->time_mult;
+	etm->tc.time_zero = tc->time_zero;
+	if (event_contains(*tc, time_cycles)) {
+		etm->tc.time_cycles = tc->time_cycles;
+		etm->tc.time_mask = tc->time_mask;
+		etm->tc.cap_user_time_zero = tc->cap_user_time_zero;
+		etm->tc.cap_user_time_short = tc->cap_user_time_short;
+	}
 	err = cs_etm__synth_events(etm, session);
 	if (err)
 		goto err_delete_thread;