perf cs-etm: Use previous thread for branch sample source IP

Branch samples currently use the IP of the previous packet as the from
IP, and the IP of the current packet as the to IP. But it incorrectly
uses the current thread. In some cases like a jump into a different
exception level this will attribute to the incorrect process.

Fix it by tracking the previous thread in the same way the previous
packet is tracked.

Committer notes:

Resolved conflicts with:

  perf addr_location: Add init/exit/copy functions
  perf thread: Add accessor functions for thread
Reviewed-by: Mike Leach <mike.leach@linaro.org>
Signed-off-by: James Clark <james.clark@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lore.kernel.org/lkml/20230612111403.100613-3-james.clark@arm.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/cs-etm.c

@@ -86,6 +86,7 @@ struct cs_etm_traceid_queue {
 	size_t last_branch_pos;
 	union perf_event *event_buf;
 	struct thread *thread;
+	struct thread *prev_packet_thread;
 	struct branch_stack *last_branch;
 	struct branch_stack *last_branch_rb;
 	struct cs_etm_packet *prev_packet;
@@ -480,6 +481,7 @@ static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq,
 	tidq->trace_chan_id = trace_chan_id;
 	tidq->thread = machine__findnew_thread(&etm->session->machines.host, -1,
 					       queue->tid);
+	tidq->prev_packet_thread = machine__idle_thread(&etm->session->machines.host);
 
 	tidq->packet = zalloc(sizeof(struct cs_etm_packet));
 	if (!tidq->packet)
@@ -612,10 +614,20 @@ static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm,
 		/*
 		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
 		 * the next incoming packet.
+		 *
+		 * Threads and exception levels are also tracked for both the
+		 * previous and current packets. This is because the previous
+		 * packet is used for the 'from' IP for branch samples, so the
+		 * thread at that time must also be assigned to that sample.
+		 * Across discontinuity packets the thread can change, so by
+		 * tracking the thread for the previous packet the branch sample
+		 * will have the correct info.
 		 */
 		tmp = tidq->packet;
 		tidq->packet = tidq->prev_packet;
 		tidq->prev_packet = tmp;
+		thread__put(tidq->prev_packet_thread);
+		tidq->prev_packet_thread = thread__get(tidq->thread);
 	}
 }
 
@@ -791,6 +803,7 @@ static void cs_etm__free_traceid_queues(struct cs_etm_queue *etmq)
 		/* Free this traceid_queue from the array */
 		tidq = etmq->traceid_queues[idx];
 		thread__zput(tidq->thread);
+		thread__zput(tidq->prev_packet_thread);
 		zfree(&tidq->event_buf);
 		zfree(&tidq->last_branch);
 		zfree(&tidq->last_branch_rb);
@@ -1454,8 +1467,8 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	sample.time = cs_etm__resolve_sample_time(etmq, tidq);
 
 	sample.ip = ip;
-	sample.pid = thread__pid(tidq->thread);
-	sample.tid = thread__tid(tidq->thread);
+	sample.pid = thread__pid(tidq->prev_packet_thread);
+	sample.tid = thread__tid(tidq->prev_packet_thread);
 	sample.addr = cs_etm__first_executed_instr(tidq->packet);
 	sample.id = etmq->etm->branches_id;
 	sample.stream_id = etmq->etm->branches_id;