perf tools: Per event max-stack settings

The tooling counterpart, now it is possible to do:

  # perf record -e sched:sched_switch/max-stack=10/ -e cycles/call-graph=dwarf,max-stack=4/ -e cpu-cycles/call-graph=dwarf,max-stack=1024/ usleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.052 MB perf.data (5 samples) ]
  # perf evlist -v
  sched:sched_switch: type: 2, size: 112, config: 0x110, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|RAW|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, sample_max_stack: 10
  cycles/call-graph=dwarf,max-stack=4/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 4
  cpu-cycles/call-graph=dwarf,max-stack=1024/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 1024
  # Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events

Using just /max-stack=N/ means /call-graph=fp,max-stack=N/, that should
be further configurable by means of some .perfconfig knob.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/n/tip-kolmn1yo40p7jhswxwrc7rrd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

7 files changed, 29 insertions, 2 deletions

diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 65e2a4f..a70f6b5 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -94,6 +94,7 @@ struct callchain_param {
 	enum perf_call_graph_mode record_mode;
 	u32			dump_size;
 	enum chain_mode 	mode;
+	u16			max_stack;
 	u32			print_limit;
 	double			min_percent;
 	sort_chain_func_t	sort;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 02c177d..245ac50 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -572,6 +572,8 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel,
 
 	perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
+	attr->sample_max_stack = param->max_stack;
+
 	if (param->record_mode == CALLCHAIN_LBR) {
 		if (!opts->branch_stack) {
 			if (attr->exclude_user) {
@@ -635,7 +637,8 @@ static void apply_config_terms(struct perf_evsel *evsel,
 	struct perf_event_attr *attr = &evsel->attr;
 	struct callchain_param param;
 	u32 dump_size = 0;
-	char *callgraph_buf = NULL;
+	int max_stack = 0;
+	const char *callgraph_buf = NULL;
 
 	/* callgraph default */
 	param.record_mode = callchain_param.record_mode;
@@ -662,6 +665,9 @@ static void apply_config_terms(struct perf_evsel *evsel,
 		case PERF_EVSEL__CONFIG_TERM_STACK_USER:
 			dump_size = term->val.stack_user;
 			break;
+		case PERF_EVSEL__CONFIG_TERM_MAX_STACK:
+			max_stack = term->val.max_stack;
+			break;
 		case PERF_EVSEL__CONFIG_TERM_INHERIT:
 			/*
 			 * attr->inherit should has already been set by
@@ -677,7 +683,12 @@ static void apply_config_terms(struct perf_evsel *evsel,
 	}
 
 	/* User explicitly set per-event callgraph, clear the old setting and reset. */
-	if ((callgraph_buf != NULL) || (dump_size > 0)) {
+	if ((callgraph_buf != NULL) || (dump_size > 0) || max_stack) {
+		if (max_stack) {
+			param.max_stack = max_stack;
+			if (callgraph_buf == NULL)
+				callgraph_buf = "fp";
+		}
 
 		/* parse callgraph parameters */
 		if (callgraph_buf != NULL) {
@@ -1329,6 +1340,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(clockid, p_signed);
 	PRINT_ATTRf(sample_regs_intr, p_hex);
 	PRINT_ATTRf(aux_watermark, p_unsigned);
+	PRINT_ATTRf(sample_max_stack, p_unsigned);
 
 	return ret;
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index c1f1015..028412b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -44,6 +44,7 @@ enum {
 	PERF_EVSEL__CONFIG_TERM_CALLGRAPH,
 	PERF_EVSEL__CONFIG_TERM_STACK_USER,
 	PERF_EVSEL__CONFIG_TERM_INHERIT,
+	PERF_EVSEL__CONFIG_TERM_MAX_STACK,
 	PERF_EVSEL__CONFIG_TERM_MAX,
 };
 
@@ -56,6 +57,7 @@ struct perf_evsel_config_term {
 		bool	time;
 		char	*callgraph;
 		u64	stack_user;
+		int	max_stack;
 		bool	inherit;
 	} val;
 };
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index bcbc983..89d40bb 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -900,6 +900,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
 	[PARSE_EVENTS__TERM_TYPE_STACKSIZE]		= "stack-size",
 	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
 	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
+	[PARSE_EVENTS__TERM_TYPE_MAX_STACK]		= "max-stack",
 };
 
 static bool config_term_shrinked;
@@ -995,6 +996,9 @@ do {									   \
 	case PARSE_EVENTS__TERM_TYPE_NAME:
 		CHECK_TYPE_VAL(STR);
 		break;
+	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+		CHECK_TYPE_VAL(NUM);
+		break;
 	default:
 		err->str = strdup("unknown term");
 		err->idx = term->err_term;
@@ -1040,6 +1044,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
 	case PARSE_EVENTS__TERM_TYPE_INHERIT:
 	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
+	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 		return config_term_common(attr, term, err);
 	default:
 		if (err) {
@@ -1109,6 +1114,9 @@ do {								\
 		case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
 			ADD_CONFIG_TERM(INHERIT, inherit, term->val.num ? 0 : 1);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+			ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num);
+			break;
 		default:
 			break;
 		}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index d740c3c..46c05cc 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -68,6 +68,7 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_STACKSIZE,
 	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
 	PARSE_EVENTS__TERM_TYPE_INHERIT,
+	PARSE_EVENTS__TERM_TYPE_MAX_STACK,
 	__PARSE_EVENTS__TERM_TYPE_NR,
 };
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 1477fbc..01af1ee 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -199,6 +199,7 @@ branch_type		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE
 time			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); }
 call-graph		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); }
 stack-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); }
+max-stack		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_STACK); }
 inherit			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); }
 no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 ,			{ return ','; }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 2335b28..43d30ea 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -593,6 +593,7 @@ do { 						\
 	if (bswap_safe(f, 0))			\
 		attr->f = bswap_##sz(attr->f);	\
 } while(0)
+#define bswap_field_16(f) bswap_field(f, 16)
 #define bswap_field_32(f) bswap_field(f, 32)
 #define bswap_field_64(f) bswap_field(f, 64)
 
@@ -608,6 +609,7 @@ do { 						\
 	bswap_field_64(sample_regs_user);
 	bswap_field_32(sample_stack_user);
 	bswap_field_32(aux_watermark);
+	bswap_field_16(sample_max_stack);
 
 	/*
 	 * After read_format are bitfields. Check read_format because