perf callchain: Add a for_each callback style API

Add a for_each callback style API to callchain with
sample__for_each_callchain_node().

Possibly in the future such an API can avoid the overhead of
constructing the call chain list.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Casey Chen <cachen@purestorage.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tom Zanussi <tzanussi@gmail.com>
Link: https://lore.kernel.org/r/20240812224119.744968-1-irogers@google.com
[ Split from a larger patch that introduced the API and use it ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/callchain.c

@@ -1797,3 +1797,38 @@ s64 callchain_avg_cycles(struct callchain_node *cnode)
 
 	return cycles;
 }
+
+int sample__for_each_callchain_node(struct thread *thread, struct evsel *evsel,
+				    struct perf_sample *sample, int max_stack,
+				    callchain_iter_fn cb, void *data)
+{
+	struct callchain_cursor *cursor = get_tls_callchain_cursor();
+	int ret;
+
+	if (!cursor)
+		return -ENOMEM;
+
+	/* Fill in the callchain. */
+	ret = thread__resolve_callchain(thread, cursor, evsel, sample,
+					/*parent=*/NULL, /*root_al=*/NULL,
+					max_stack);
+	if (ret)
+		return ret;
+
+	/* Switch from writing the callchain to reading it. */
+	callchain_cursor_commit(cursor);
+
+	while (1) {
+		struct callchain_cursor_node *node = callchain_cursor_current(cursor);
+
+		if (!node)
+			break;
+
+		ret = cb(node, data);
+		if (ret)
+			return ret;
+
+		callchain_cursor_advance(cursor);
+	}
+	return 0;
+}

tools/perf/util/callchain.h

@@ -311,4 +311,10 @@ u64 callchain_total_hits(struct hists *hists);
 
 s64 callchain_avg_cycles(struct callchain_node *cnode);
 
+typedef int (*callchain_iter_fn)(struct callchain_cursor_node *node, void *data);
+
+int sample__for_each_callchain_node(struct thread *thread, struct evsel *evsel,
+				    struct perf_sample *sample, int max_stack,
+				    callchain_iter_fn cb, void *data);
+
 #endif	/* __PERF_CALLCHAIN_H */