perf record: Add --call-graph fp,defer option for deferred callchains

Add a new callchain record mode option for deferred callchains.  For now
it only works with FP (frame-pointer) mode.

And add the missing feature detection logic to clear the flag on old
kernels.

  $ perf record --call-graph fp,defer -vv true
  ...
  ------------------------------------------------------------
  perf_event_attr:
    type                             0 (PERF_TYPE_HARDWARE)
    size                             136
    config                           0 (PERF_COUNT_HW_CPU_CYCLES)
    { sample_period, sample_freq }   4000
    sample_type                      IP|TID|TIME|CALLCHAIN|PERIOD
    read_format                      ID|LOST
    disabled                         1
    inherit                          1
    mmap                             1
    comm                             1
    freq                             1
    enable_on_exec                   1
    task                             1
    sample_id_all                    1
    mmap2                            1
    comm_exec                        1
    ksymbol                          1
    bpf_event                        1
    defer_callchain                  1
    defer_output                     1
  ------------------------------------------------------------
  sys_perf_event_open: pid 162755  cpu 0  group_fd -1  flags 0x8
  sys_perf_event_open failed, error -22
  switching off deferred callchain support

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

tools/perf/Documentation/perf-config.txt

@@ -452,6 +452,9 @@ call-graph.*::
 		kernel space is controlled not by this option but by the
 		kernel config (CONFIG_UNWINDER_*).
 
+		The 'defer' mode can be used with 'fp' mode to enable deferred
+		user callchains (like 'fp,defer').
+
 	call-graph.dump-size::
 		The size of stack to dump in order to do post-unwinding. Default is 8192 (byte).
 		When using dwarf into record-mode, the default size will be used if omitted.

tools/perf/Documentation/perf-record.txt

@@ -325,6 +325,10 @@ OPTIONS
 	by default.  User can change the number by passing it after comma
 	like "--call-graph fp,32".
 
+	Also "defer" can be used with "fp" (like "--call-graph fp,defer") to
+	enable deferred user callchain which will collect user-space callchains
+	when the thread returns to the user space.
+
 -q::
 --quiet::
 	Don't print any warnings or messages, useful for scripting.

tools/perf/util/callchain.c

@@ -275,9 +275,13 @@ int parse_callchain_record(const char *arg, struct callchain_param *param)
 			if (tok) {
 				unsigned long size;
 
-				size = strtoul(tok, &name, 0);
-				if (size < (unsigned) sysctl__max_stack())
-					param->max_stack = size;
+				if (!strncmp(tok, "defer", sizeof("defer"))) {
+					param->defer = true;
+				} else {
+					size = strtoul(tok, &name, 0);
+					if (size < (unsigned) sysctl__max_stack())
+						param->max_stack = size;
+				}
 			}
 			break;
 
@@ -314,6 +318,12 @@ int parse_callchain_record(const char *arg, struct callchain_param *param)
 	} while (0);
 
 	free(buf);
+
+	if (param->defer && param->record_mode != CALLCHAIN_FP) {
+		pr_err("callchain: deferred callchain only works with FP\n");
+		return -EINVAL;
+	}
+
 	return ret;
 }
 

tools/perf/util/callchain.h

@@ -98,6 +98,7 @@ extern bool dwarf_callchain_users;
 
 struct callchain_param {
 	bool			enabled;
+	bool			defer;
 	enum perf_call_graph_mode record_mode;
 	u32			dump_size;
 	enum chain_mode 	mode;

tools/perf/util/evsel.c

@@ -1066,6 +1066,9 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
 		pr_info("Disabling user space callchains for function trace event.\n");
 		attr->exclude_callchain_user = 1;
 	}
+
+	if (param->defer && !attr->exclude_callchain_user)
+		attr->defer_callchain = 1;
 }
 
 void evsel__config_callchain(struct evsel *evsel, struct record_opts *opts,
@@ -1512,6 +1515,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 	attr->mmap2    = track && !perf_missing_features.mmap2;
 	attr->comm     = track;
 	attr->build_id = track && opts->build_id;
+	attr->defer_output = track && callchain && callchain->defer;
 
 	/*
 	 * ksymbol is tracked separately with text poke because it needs to be
@@ -2200,6 +2204,10 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 
 static void evsel__disable_missing_features(struct evsel *evsel)
 {
+	if (perf_missing_features.defer_callchain && evsel->core.attr.defer_callchain)
+		evsel->core.attr.defer_callchain = 0;
+	if (perf_missing_features.defer_callchain && evsel->core.attr.defer_output)
+		evsel->core.attr.defer_output = 0;
 	if (perf_missing_features.inherit_sample_read && evsel->core.attr.inherit &&
 	    (evsel->core.attr.sample_type & PERF_SAMPLE_READ))
 		evsel->core.attr.inherit = 0;
@@ -2474,6 +2482,13 @@ static bool evsel__detect_missing_features(struct evsel *evsel, struct perf_cpu
 
 	/* Please add new feature detection here. */
 
+	attr.defer_callchain = true;
+	if (has_attr_feature(&attr, /*flags=*/0))
+		goto found;
+	perf_missing_features.defer_callchain = true;
+	pr_debug2("switching off deferred callchain support\n");
+	attr.defer_callchain = false;
+
 	attr.inherit = true;
 	attr.sample_type = PERF_SAMPLE_READ | PERF_SAMPLE_TID;
 	if (has_attr_feature(&attr, /*flags=*/0))
@@ -2585,6 +2600,10 @@ static bool evsel__detect_missing_features(struct evsel *evsel, struct perf_cpu
 	errno = old_errno;
 
 check:
+	if ((evsel->core.attr.defer_callchain || evsel->core.attr.defer_output) &&
+	    perf_missing_features.defer_callchain)
+		return true;
+
 	if (evsel->core.attr.inherit &&
 	    (evsel->core.attr.sample_type & PERF_SAMPLE_READ) &&
 	    perf_missing_features.inherit_sample_read)

tools/perf/util/evsel.h

@@ -221,6 +221,7 @@ struct perf_missing_features {
 	bool branch_counters;
 	bool aux_action;
 	bool inherit_sample_read;
+	bool defer_callchain;
 };
 
 extern struct perf_missing_features perf_missing_features;