perf auxtrace: Add four itrace options

This patch is to add four options to synthesize events which are
described as below:

 'f': synthesize first level cache events
 'm': synthesize last level cache events
 't': synthesize TLB events
 'a': synthesize remote access events

This four options will be used by ARM SPE as their first consumer.

Signed-off-by: Tan Xiaojun <tanxiaojun@huawei.com>
Tested-by: James Clark <james.clark@arm.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Al Grant <al.grant@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Leo Yan <leo.yan@linaro.org>
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: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lore.kernel.org/lkml/20200530122442.490-3-leo.yan@linaro.org
Signed-off-by: James Clark <james.clark@arm.com>
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/itrace.txt

@@ -1,5 +1,5 @@
 		i	synthesize instructions events
-		b	synthesize branches events
+		b	synthesize branches events (branch misses for Arm SPE)
 		c	synthesize branches events (calls only)
 		r	synthesize branches events (returns only)
 		x	synthesize transactions events
@@ -9,6 +9,10 @@
 			of aux-output (refer to perf record)
 		e	synthesize error events
 		d	create a debug log
+		f	synthesize first level cache events
+		m	synthesize last level cache events
+		t	synthesize TLB events
+		a	synthesize remote access events
 		g	synthesize a call chain (use with i or x)
 		G	synthesize a call chain on existing event records
 		l	synthesize last branch entries (use with i or x)

tools/perf/util/auxtrace.c

@@ -1331,6 +1331,11 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
 	synth_opts->pwr_events = true;
 	synth_opts->other_events = true;
 	synth_opts->errors = true;
+	synth_opts->flc = true;
+	synth_opts->llc = true;
+	synth_opts->tlb = true;
+	synth_opts->remote_access = true;
+
 	if (no_sample) {
 		synth_opts->period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS;
 		synth_opts->period = 1;
@@ -1491,6 +1496,18 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 				goto out_err;
 			p = endptr;
 			break;
+		case 'f':
+			synth_opts->flc = true;
+			break;
+		case 'm':
+			synth_opts->llc = true;
+			break;
+		case 't':
+			synth_opts->tlb = true;
+			break;
+		case 'a':
+			synth_opts->remote_access = true;
+			break;
 		case ' ':
 		case ',':
 			break;

tools/perf/util/auxtrace.h

@@ -63,6 +63,7 @@ enum itrace_period_type {
  *          because 'perf inject' will write it out
  * @instructions: whether to synthesize 'instructions' events
  * @branches: whether to synthesize 'branches' events
+ *            (branch misses only for Arm SPE)
  * @transactions: whether to synthesize events for transactions
  * @ptwrites: whether to synthesize events for ptwrites
  * @pwr_events: whether to synthesize power events
@@ -78,6 +79,10 @@ enum itrace_period_type {
  * @thread_stack: feed branches to the thread_stack
  * @last_branch: add branch context to 'instruction' events
  * @add_last_branch: add branch context to existing event records
+ * @flc: whether to synthesize first level cache events
+ * @llc: whether to synthesize last level cache events
+ * @tlb: whether to synthesize TLB events
+ * @remote_access: whether to synthesize remote access events
  * @callchain_sz: maximum callchain size
  * @last_branch_sz: branch context size
  * @period: 'instructions' events period
@@ -107,6 +112,10 @@ struct itrace_synth_opts {
 	bool			thread_stack;
 	bool			last_branch;
 	bool			add_last_branch;
+	bool			flc;
+	bool			llc;
+	bool			tlb;
+	bool			remote_access;
 	unsigned int		callchain_sz;
 	unsigned int		last_branch_sz;
 	unsigned long long	period;
@@ -596,7 +605,7 @@ bool auxtrace__evsel_is_auxtrace(struct perf_session *session,
 
 #define ITRACE_HELP \
 "				i:	    		synthesize instructions events\n"		\
-"				b:	    		synthesize branches events\n"		\
+"				b:	    		synthesize branches events (branch misses for Arm SPE)\n" \
 "				c:	    		synthesize branches events (calls only)\n"	\
 "				r:	    		synthesize branches events (returns only)\n" \
 "				x:	    		synthesize transactions events\n"		\
@@ -604,6 +613,10 @@ bool auxtrace__evsel_is_auxtrace(struct perf_session *session,
 "				p:	    		synthesize power events\n"			\
 "				e:	    		synthesize error events\n"			\
 "				d:	    		create a debug log\n"			\
+"				f:	    		synthesize first level cache events\n" \
+"				m:	    		synthesize last level cache events\n" \
+"				t:	    		synthesize TLB events\n" \
+"				a:	    		synthesize remote access events\n" \
 "				g[len]:     		synthesize a call chain (use with i or x)\n" \
 "				l[len]:     		synthesize last branch entries (use with i or x)\n" \
 "				sNUMBER:    		skip initial number of events\n"		\