perf trace: Ignore thread hashing in summary

Commit 91e467b ("perf machine: Use hashtable for machine
threads") made the iteration of thread tids unordered. The perf trace
--summary output sorts and prints each hash bucket, rather than all
threads globally. Change this behavior by turn all threads into a
list, sort the list by number of trace events then by tids, finally
print the list. This also allows the rbtree in threads to be not
accessed outside of machine.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240301053646.1449657-3-irogers@google.com

Author: captain5050

tools/perf/builtin-trace.c

@@ -74,6 +74,7 @@
 #include <linux/err.h>
 #include <linux/filter.h>
 #include <linux/kernel.h>
+#include <linux/list_sort.h>
 #include <linux/random.h>
 #include <linux/stringify.h>
 #include <linux/time64.h>
@@ -4312,34 +4313,38 @@ static unsigned long thread__nr_events(struct thread_trace *ttrace)
 	return ttrace ? ttrace->nr_events : 0;
 }
 
-DEFINE_RESORT_RB(threads,
-		(thread__nr_events(thread__priv(a->thread)) <
-		 thread__nr_events(thread__priv(b->thread))),
-	struct thread *thread;
-)
+static int trace_nr_events_cmp(void *priv __maybe_unused,
+			       const struct list_head *la,
+			       const struct list_head *lb)
 {
-	entry->thread = rb_entry(nd, struct thread_rb_node, rb_node)->thread;
+	struct thread_list *a = list_entry(la, struct thread_list, list);
+	struct thread_list *b = list_entry(lb, struct thread_list, list);
+	unsigned long a_nr_events = thread__nr_events(thread__priv(a->thread));
+	unsigned long b_nr_events = thread__nr_events(thread__priv(b->thread));
+
+	if (a_nr_events != b_nr_events)
+		return a_nr_events < b_nr_events ? -1 : 1;
+
+	/* Identical number of threads, place smaller tids first. */
+	return thread__tid(a->thread) < thread__tid(b->thread)
+		? -1
+		: (thread__tid(a->thread) > thread__tid(b->thread) ? 1 : 0);
 }
 
 static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
 {
 	size_t printed = trace__fprintf_threads_header(fp);
-	struct rb_node *nd;
-	int i;
-
-	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
-		DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host, i);
+	LIST_HEAD(threads);
 
-		if (threads == NULL) {
-			fprintf(fp, "%s", "Error sorting output by nr_events!\n");
-			return 0;
-		}
+	if (machine__thread_list(trace->host, &threads) == 0) {
+		struct thread_list *pos;
 
-		resort_rb__for_each_entry(nd, threads)
-			printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
+		list_sort(NULL, &threads, trace_nr_events_cmp);
 
-		resort_rb__delete(threads);
+		list_for_each_entry(pos, &threads, list)
+			printed += trace__fprintf_thread(fp, pos->thread, trace);
 	}
+	thread_list__delete(&threads);
 	return printed;
 }
 

tools/perf/util/rb_resort.h

@@ -143,9 +143,4 @@ struct __name##_sorted *__name = __name##_sorted__new
 	DECLARE_RESORT_RB(__name)(&__ilist->rblist.entries.rb_root,		\
 				  __ilist->rblist.nr_entries)
 
-/* For 'struct machine->threads' */
-#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine, hash_bucket)    \
- DECLARE_RESORT_RB(__name)(&__machine->threads[hash_bucket].entries.rb_root, \
-			   __machine->threads[hash_bucket].nr)
-
 #endif /* _PERF_RESORT_RB_H_ */