perf record: Apply affinity masks when reading mmap buffers

Build node cpu masks for mmap data buffers. Apply node cpu masks to tool
thread every time it references data buffers cross node or cross cpu.

Signed-off-by: Alexey Budankov <[e-mail]>
Reviewed-by: Jiri Olsa <[e-mail]>
Cc: Alexander Shishkin <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
[ Use cpu-set-sched.h to get the CPU_{EQUAL,OR}() fallbacks for older systems ]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/builtin-record.c

···
 #include "util/bpf-loader.h"
 #include "util/trigger.h"
 #include "util/perf-hooks.h"
+#include "util/cpu-set-sched.h"
 #include "util/time-utils.h"
 #include "util/units.h"
 #include "util/bpf-event.h"
···
 	struct record_opts *opts = &rec->opts;
 	char msg[512];
 
+	if (opts->affinity != PERF_AFFINITY_SYS)
+		cpu__setup_cpunode_map();
+
 	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 				 opts->auxtrace_mmap_pages,
 				 opts->auxtrace_snapshot_mode,
···
 	.type = PERF_RECORD_FINISHED_ROUND,
 };
 
+static void record__adjust_affinity(struct record *rec, struct perf_mmap *map)
+{
+	if (rec->opts.affinity != PERF_AFFINITY_SYS &&
+	    !CPU_EQUAL(&rec->affinity_mask, &map->affinity_mask)) {
+		CPU_ZERO(&rec->affinity_mask);
+		CPU_OR(&rec->affinity_mask, &rec->affinity_mask, &map->affinity_mask);
+		sched_setaffinity(0, sizeof(rec->affinity_mask), &rec->affinity_mask);
+	}
+}
+
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
 				    bool overwrite)
 {
···
 		struct perf_mmap *map = &maps[i];
 
 		if (map->base) {
+			record__adjust_affinity(rec, map);
 			if (!record__aio_enabled(rec)) {
 				if (perf_mmap__push(map, rec, record__pushfn) != 0) {
 					rc = -1;

tools/perf/util/cpumap.c

···
 	buf[size - 1] = '\0';
 	return ptr - buf;
 }
+
+const struct cpu_map *cpu_map__online(void) /* thread unsafe */
+{
+	static const struct cpu_map *online = NULL;
+
+	if (!online)
+		online = cpu_map__new(NULL); /* from /sys/devices/system/cpu/online */
+
+	return online;
+}

tools/perf/util/cpumap.h

···
 int cpu_map__get_core(struct cpu_map *map, int idx, void *data);
 int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
 int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep);
+const struct cpu_map *cpu_map__online(void); /* thread unsafe */
 
 struct cpu_map *cpu_map__get(struct cpu_map *map);
 void cpu_map__put(struct cpu_map *map);

tools/perf/util/mmap.c

···
 	auxtrace_mmap__munmap(&map->auxtrace_mmap);
 }
 
+static void build_node_mask(int node, cpu_set_t *mask)
+{
+	int c, cpu, nr_cpus;
+	const struct cpu_map *cpu_map = NULL;
+
+	cpu_map = cpu_map__online();
+	if (!cpu_map)
+		return;
+
+	nr_cpus = cpu_map__nr(cpu_map);
+	for (c = 0; c < nr_cpus; c++) {
+		cpu = cpu_map->map[c]; /* map c index to online cpu index */
+		if (cpu__get_node(cpu) == node)
+			CPU_SET(cpu, mask);
+	}
+}
+
+static void perf_mmap__setup_affinity_mask(struct perf_mmap *map, struct mmap_params *mp)
+{
+	CPU_ZERO(&map->affinity_mask);
+	if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1)
+		build_node_mask(cpu__get_node(map->cpu), &map->affinity_mask);
+	else if (mp->affinity == PERF_AFFINITY_CPU)
+		CPU_SET(map->cpu, &map->affinity_mask);
+}
+
 int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu)
 {
 	/*
···
 	map->fd = fd;
 	map->cpu = cpu;
 
-	CPU_ZERO(&map->affinity_mask);
+	perf_mmap__setup_affinity_mask(map, mp);
 
 	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
 				&mp->auxtrace_mp, map->base, fd))