perf record: Introduce thread affinity and mmap masks

Introduce affinity and mmap thread masks. Thread affinity mask
defines CPUs that a thread is allowed to run on. Thread maps
mask defines mmap data buffers the thread serves to stream
profiling data from.

Reviewed-by: Riccardo Mancini <rickyman7@gmail.com>
Signed-off-by: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Tested-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Riccardo Mancini <rickyman7@gmail.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Antonov <alexander.antonov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Budankov <abudankov@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/9042bf7daf988e17e17e6acbf5d29590bde869cd.1642440724.git.alexey.v.bayduraev@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-record.c

@@ -87,6 +87,11 @@ struct switch_output {
 	int		 cur_file;
 };
 
+struct thread_mask {
+	struct mmap_cpu_mask	maps;
+	struct mmap_cpu_mask	affinity;
+};
+
 struct record {
 	struct perf_tool	tool;
 	struct record_opts	opts;
@@ -112,6 +117,8 @@ struct record {
 	struct mmap_cpu_mask	affinity_mask;
 	unsigned long		output_max_size;	/* = 0: unlimited */
 	struct perf_debuginfod	debuginfod;
+	int			nr_threads;
+	struct thread_mask	*thread_masks;
 };
 
 static volatile int done;
@@ -2204,6 +2211,47 @@ static int record__parse_affinity(const struct option *opt, const char *str, int
 	return 0;
 }
 
+static int record__mmap_cpu_mask_alloc(struct mmap_cpu_mask *mask, int nr_bits)
+{
+	mask->nbits = nr_bits;
+	mask->bits = bitmap_zalloc(mask->nbits);
+	if (!mask->bits)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void record__mmap_cpu_mask_free(struct mmap_cpu_mask *mask)
+{
+	bitmap_free(mask->bits);
+	mask->nbits = 0;
+}
+
+static int record__thread_mask_alloc(struct thread_mask *mask, int nr_bits)
+{
+	int ret;
+
+	ret = record__mmap_cpu_mask_alloc(&mask->maps, nr_bits);
+	if (ret) {
+		mask->affinity.bits = NULL;
+		return ret;
+	}
+
+	ret = record__mmap_cpu_mask_alloc(&mask->affinity, nr_bits);
+	if (ret) {
+		record__mmap_cpu_mask_free(&mask->maps);
+		mask->maps.bits = NULL;
+	}
+
+	return ret;
+}
+
+static void record__thread_mask_free(struct thread_mask *mask)
+{
+	record__mmap_cpu_mask_free(&mask->maps);
+	record__mmap_cpu_mask_free(&mask->affinity);
+}
+
 static int parse_output_max_size(const struct option *opt,
 				 const char *str, int unset)
 {
@@ -2683,6 +2731,73 @@ static struct option __record_options[] = {
 
 struct option *record_options = __record_options;
 
+static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cpu_map *cpus)
+{
+	int c;
+
+	for (c = 0; c < cpus->nr; c++)
+		set_bit(cpus->map[c].cpu, mask->bits);
+}
+
+static void record__free_thread_masks(struct record *rec, int nr_threads)
+{
+	int t;
+
+	if (rec->thread_masks)
+		for (t = 0; t < nr_threads; t++)
+			record__thread_mask_free(&rec->thread_masks[t]);
+
+	zfree(&rec->thread_masks);
+}
+
+static int record__alloc_thread_masks(struct record *rec, int nr_threads, int nr_bits)
+{
+	int t, ret;
+
+	rec->thread_masks = zalloc(nr_threads * sizeof(*(rec->thread_masks)));
+	if (!rec->thread_masks) {
+		pr_err("Failed to allocate thread masks\n");
+		return -ENOMEM;
+	}
+
+	for (t = 0; t < nr_threads; t++) {
+		ret = record__thread_mask_alloc(&rec->thread_masks[t], nr_bits);
+		if (ret) {
+			pr_err("Failed to allocate thread masks[%d]\n", t);
+			goto out_free;
+		}
+	}
+
+	return 0;
+
+out_free:
+	record__free_thread_masks(rec, nr_threads);
+
+	return ret;
+}
+
+static int record__init_thread_default_masks(struct record *rec, struct perf_cpu_map *cpus)
+{
+	int ret;
+
+	ret = record__alloc_thread_masks(rec, 1, cpu__max_cpu().cpu);
+	if (ret)
+		return ret;
+
+	record__mmap_cpu_mask_init(&rec->thread_masks->maps, cpus);
+
+	rec->nr_threads = 1;
+
+	return 0;
+}
+
+static int record__init_thread_masks(struct record *rec)
+{
+	struct perf_cpu_map *cpus = rec->evlist->core.cpus;
+
+	return record__init_thread_default_masks(rec, cpus);
+}
+
 int cmd_record(int argc, const char **argv)
 {
 	int err;
@@ -2948,6 +3063,12 @@ int cmd_record(int argc, const char **argv)
 		goto out;
 	}
 
+	err = record__init_thread_masks(rec);
+	if (err) {
+		pr_err("Failed to initialize parallel data streaming masks\n");
+		goto out;
+	}
+
 	if (rec->opts.nr_cblocks > nr_cblocks_max)
 		rec->opts.nr_cblocks = nr_cblocks_max;
 	pr_debug("nr_cblocks: %d\n", rec->opts.nr_cblocks);
@@ -2966,6 +3087,8 @@ out:
 	symbol__exit();
 	auxtrace_record__free(rec->itr);
 out_opts:
+	record__free_thread_masks(rec, rec->nr_threads);
+	rec->nr_threads = 0;
 	evlist__close_control(rec->opts.ctl_fd, rec->opts.ctl_fd_ack, &rec->opts.ctl_fd_close);
 	return err;
 }