perf cs-etm: Optimize copying last branches

If an instruction range packet can generate multiple instruction
samples, these samples share the same last branches; it's not necessary
to copy the same last branches repeatedly for these samples within the
same packet.

This patch moves out the last branches copying from function
cs_etm__synth_instruction_sample(), and execute it prior to generating
instruction samples.
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Reviewed-by: Mike Leach <mike.leach@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Walker <robert.walker@arm.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: coresight ml <coresight@lists.linaro.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lore.kernel.org/lkml/20200219021811.20067-5-leo.yan@linaro.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/cs-etm.c

@@ -1151,10 +1151,8 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 
 	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);
+	if (etm->synth_opts.last_branch)
 		sample.branch_stack = tidq->last_branch;
-	}
 
 	if (etm->synth_opts.inject) {
 		ret = cs_etm__inject_event(event, &sample,
@@ -1431,6 +1429,10 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 		u64 offset = etm->instructions_sample_period - instrs_prev;
 		u64 addr;
 
+		/* Prepare last branches for instruction sample */
+		if (etm->synth_opts.last_branch)
+			cs_etm__copy_last_branch_rb(etmq, tidq);
+
 		while (tidq->period_instructions >=
 				etm->instructions_sample_period) {
 			/*
@@ -1508,6 +1510,11 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 
 	if (etmq->etm->synth_opts.last_branch &&
 	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+		u64 addr;
+
+		/* Prepare last branches for instruction sample */
+		cs_etm__copy_last_branch_rb(etmq, tidq);
+
 		/*
 		 * Generate a last branch event for the branches left in the
 		 * circular buffer at the end of the trace.
@@ -1515,7 +1522,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 		 * Use the address of the end of the last reported execution
 		 * range
 		 */
-		u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+		addr = cs_etm__last_executed_instr(tidq->prev_packet);
 
 		err = cs_etm__synth_instruction_sample(
 			etmq, tidq, addr,
@@ -1560,11 +1567,16 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
 	 */
 	if (etmq->etm->synth_opts.last_branch &&
 	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+		u64 addr;
+
+		/* Prepare last branches for instruction sample */
+		cs_etm__copy_last_branch_rb(etmq, tidq);
+
 		/*
 		 * Use the address of the end of the last reported execution
 		 * range.
 		 */
-		u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+		addr = cs_etm__last_executed_instr(tidq->prev_packet);
 
 		err = cs_etm__synth_instruction_sample(
 			etmq, tidq, addr,