[PATCH 11/17] perf cs-etm: Support sample flags 'insn' and 'insnlen'

[Arnaldo Carvalho de Melo]

From: Leo Yan <leo.yan@xxxxxxxxxx>

The synthetic branch and instruction samples are missed to set
instruction related info, thus the perf tool fails to display samples
with flags '-F,+insn,+insnlen'.

The CoreSight trace decoder provides sufficient information to decide
the instruction size based on the ISA type: A64/A32 instructions are
32-bit size, but one exception is the T32 instruction size, which might
be 32-bit or 16-bit.

This patch handles these cases and it reads the instruction values from
DSO file; thus can support the flags '-F,+insn,+insnlen'.

Before:

  # perf script -F,insn,insnlen,ip,sym
                0 [unknown] ilen: 0
     ffff97174044 _start ilen: 0
     ffff97174938 _dl_start ilen: 0
     ffff97174938 _dl_start ilen: 0
     ffff97174938 _dl_start ilen: 0
     ffff97174938 _dl_start ilen: 0
     ffff97174938 _dl_start ilen: 0
     ffff97174938 _dl_start ilen: 0
     ffff97174938 _dl_start ilen: 0
     ffff97174938 _dl_start ilen: 0

  [...]

After:

  # perf script -F,insn,insnlen,ip,sym
                0 [unknown] ilen: 0
     ffff97174044 _start ilen: 4 insn: 2f 02 00 94
     ffff97174938 _dl_start ilen: 4 insn: c1 ff ff 54
     ffff97174938 _dl_start ilen: 4 insn: c1 ff ff 54
     ffff97174938 _dl_start ilen: 4 insn: c1 ff ff 54
     ffff97174938 _dl_start ilen: 4 insn: c1 ff ff 54
     ffff97174938 _dl_start ilen: 4 insn: c1 ff ff 54
     ffff97174938 _dl_start ilen: 4 insn: c1 ff ff 54
     ffff97174938 _dl_start ilen: 4 insn: c1 ff ff 54
     ffff97174938 _dl_start ilen: 4 insn: c1 ff ff 54

  [...]

Signed-off-by: Leo Yan <leo.yan@xxxxxxxxxx>
Reviewed-by: Mathieu Poirier <mathieu.poirier@xxxxxxxxxx>
Tested-by: Mathieu Poirier <mathieu.poirier@xxxxxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Mike Leach <mike.leach@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Robert Walker <robert.walker@xxxxxxx>
Cc: Suzuki Poulouse <suzuki.poulose@xxxxxxx>
Cc: coresight@xxxxxxxxxxxxxxxx
Cc: linux-arm-kernel@xxxxxxxxxxxxxxxxxxx
Link: http://lkml.kernel.org/r/20190815082854.18191-1-leo.yan@xxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 tools/perf/util/cs-etm.c | 35 ++++++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index ed6f7fd5b90b..b3a5daaf1a8f 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1076,6 +1076,35 @@ bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq)
 	return !!etmq->etm->timeless_decoding;
 }
 
+static void cs_etm__copy_insn(struct cs_etm_queue *etmq,
+			      u64 trace_chan_id,
+			      const struct cs_etm_packet *packet,
+			      struct perf_sample *sample)
+{
+	/*
+	 * It's pointless to read instructions for the CS_ETM_DISCONTINUITY
+	 * packet, so directly bail out with 'insn_len' = 0.
+	 */
+	if (packet->sample_type == CS_ETM_DISCONTINUITY) {
+		sample->insn_len = 0;
+		return;
+	}
+
+	/*
+	 * T32 instruction size might be 32-bit or 16-bit, decide by calling
+	 * cs_etm__t32_instr_size().
+	 */
+	if (packet->isa == CS_ETM_ISA_T32)
+		sample->insn_len = cs_etm__t32_instr_size(etmq, trace_chan_id,
+							  sample->ip);
+	/* Otherwise, A64 and A32 instruction size are always 32-bit. */
+	else
+		sample->insn_len = 4;
+
+	cs_etm__mem_access(etmq, trace_chan_id, sample->ip,
+			   sample->insn_len, (void *)sample->insn);
+}
+
 static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 					    struct cs_etm_traceid_queue *tidq,
 					    u64 addr, u64 period)
@@ -1097,9 +1126,10 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	sample.period = period;
 	sample.cpu = tidq->packet->cpu;
 	sample.flags = tidq->prev_packet->flags;
-	sample.insn_len = 1;
 	sample.cpumode = event->sample.header.misc;
 
+	cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);
+
 	if (etm->synth_opts.last_branch) {
 		cs_etm__copy_last_branch_rb(etmq, tidq);
 		sample.branch_stack = tidq->last_branch;
@@ -1159,6 +1189,9 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	sample.flags = tidq->prev_packet->flags;
 	sample.cpumode = event->sample.header.misc;
 
+	cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->prev_packet,
+			  &sample);
+
 	/*
 	 * perf report cannot handle events without a branch stack
 	 */
-- 
2.21.0