perf trace: Add --switch-on/--switch-off events

Just like with 'perf script':

  # perf trace -e sched:*,syscalls:*sleep* sleep 1
       0.000 :28345/28345 sched:sched_waking:comm=perf pid=28346 prio=120 target_cpu=005
       0.005 :28345/28345 sched:sched_wakeup:perf:28346 [120] success=1 CPU:005
       0.383 sleep/28346 sched:sched_process_exec:filename=/usr/bin/sleep pid=28346 old_pid=28346
       0.613 sleep/28346 sched:sched_stat_runtime:comm=sleep pid=28346 runtime=607375 [ns] vruntime=23289041218 [ns]
       0.689 sleep/28346 syscalls:sys_enter_nanosleep:rqtp: 0x7ffc491789b0
       0.693 sleep/28346 sched:sched_stat_runtime:comm=sleep pid=28346 runtime=72021 [ns] vruntime=23289113239 [ns]
       0.694 sleep/28346 sched:sched_switch:sleep:28346 [120] S ==> swapper/5:0 [120]
    1000.787 :0/0 sched:sched_waking:comm=sleep pid=28346 prio=120 target_cpu=005
    1000.824 :0/0 sched:sched_wakeup:sleep:28346 [120] success=1 CPU:005
    1000.908 sleep/28346 syscalls:sys_exit_nanosleep:0x0
    1001.218 sleep/28346 sched:sched_process_exit:comm=sleep pid=28346 prio=120
  # perf trace -e sched:*,syscalls:*sleep* --switch-on=syscalls:sys_enter_nanosleep sleep 1
       0.000 sleep/28349 sched:sched_stat_runtime:comm=sleep pid=28349 runtime=603036 [ns] vruntime=23873537697 [ns]
       0.001 sleep/28349 sched:sched_switch:sleep:28349 [120] S ==> swapper/4:0 [120]
    1000.392 :0/0 sched:sched_waking:comm=sleep pid=28349 prio=120 target_cpu=004
    1000.443 :0/0 sched:sched_wakeup:sleep:28349 [120] success=1 CPU:004
    1000.540 sleep/28349 syscalls:sys_exit_nanosleep:0x0
    1000.852 sleep/28349 sched:sched_process_exit:comm=sleep pid=28349 prio=120
  # perf trace -e sched:*,syscalls:*sleep* --switch-on=syscalls:sys_enter_nanosleep --switch-off=syscalls:sys_exit_nanosleep sleep 1
       0.000 sleep/28352 sched:sched_stat_runtime:comm=sleep pid=28352 runtime=610543 [ns] vruntime=24811686681 [ns]
       0.001 sleep/28352 sched:sched_switch:sleep:28352 [120] S ==> swapper/0:0 [120]
    1000.397 :0/0 sched:sched_waking:comm=sleep pid=28352 prio=120 target_cpu=000
    1000.440 :0/0 sched:sched_wakeup:sleep:28352 [120] success=1 CPU:000
  #
  # perf trace -e sched:*,syscalls:*sleep* --switch-on=syscalls:sys_enter_nanosleep --switch-off=syscalls:sys_exit_nanosleep --show-on-off sleep 1
       0.000 sleep/28367 syscalls:sys_enter_nanosleep:rqtp: 0x7fffd1a25fc0
       0.004 sleep/28367 sched:sched_stat_runtime:comm=sleep pid=28367 runtime=628760 [ns] vruntime=22170052672 [ns]
       0.005 sleep/28367 sched:sched_switch:sleep:28367 [120] S ==> swapper/2:0 [120]
    1000.367 :0/0 sched:sched_waking:comm=sleep pid=28367 prio=120 target_cpu=002
    1000.412 :0/0 sched:sched_wakeup:sleep:28367 [120] success=1 CPU:002
    1000.512 sleep/28367 syscalls:sys_exit_nanosleep:0x0
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: William Cohen <wcohen@redhat.com>
Link: https://lkml.kernel.org/n/tip-t3ngpt1brcc1fm9gep9gxm4q@git.kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-trace.txt

@@ -176,6 +176,15 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 	only at exit time or when a syscall is interrupted, i.e. in those cases this
 	option is equivalent to the number of lines printed.
 
+--switch-on EVENT_NAME::
+	Only consider events after this event is found.
+
+--switch-off EVENT_NAME::
+	Stop considering events after this event is found.
+
+--show-on-off-events::
+	Show the --switch-on/off events too.
+
 --max-stack::
         Set the stack depth limit when parsing the callchain, anything
         beyond the specified depth will be ignored. Note that at this point

tools/perf/builtin-trace.c

@@ -27,6 +27,7 @@
 #include "util/env.h"
 #include "util/event.h"
 #include "util/evlist.h"
+#include "util/evswitch.h"
 #include <subcmd/exec-cmd.h>
 #include "util/machine.h"
 #include "util/map.h"
@@ -106,6 +107,7 @@ struct trace {
 	unsigned long		nr_events;
 	unsigned long		nr_events_printed;
 	unsigned long		max_events;
+	struct evswitch		evswitch;
 	struct strlist		*ev_qualifier;
 	struct {
 		size_t		nr;
@@ -2680,6 +2682,9 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st
 		return;
 	}
 
+	if (evswitch__discard(&trace->evswitch, evsel))
+		return;
+
 	trace__set_base_time(trace, evsel, sample);
 
 	if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT &&
@@ -4157,6 +4162,7 @@ int cmd_trace(int argc, const char **argv)
 	OPT_UINTEGER('D', "delay", &trace.opts.initial_delay,
 		     "ms to wait before starting measurement after program "
 		     "start"),
+	OPTS_EVSWITCH(&trace.evswitch),
 	OPT_END()
 	};
 	bool __maybe_unused max_stack_user_set = true;
@@ -4380,6 +4386,10 @@ int cmd_trace(int argc, const char **argv)
 		}
 	}
 
+	err = evswitch__init(&trace.evswitch, trace.evlist, stderr);
+	if (err)
+		goto out_close;
+
 	err = target__validate(&trace.opts.target);
 	if (err) {
 		target__strerror(&trace.opts.target, err, bf, sizeof(bf));