perf stat aggregation: Add separate socket member
Add socket as a separate member so that it doesn't have to be packed
into the int value.
When the socket ID was larger than 8 bits the output appeared corrupted
or incomplete.
For example, here on ThunderX2 'perf stat' reports a socket of -1 and an
invalid die number:
./perf stat -a --per-die
The socket id number is too big.
Performance counter stats for 'system wide':
S-1-D255 128 687.99 msec cpu-clock # 57.240 CPUs utilized
...
S36-D0 128 842.34 msec cpu-clock # 70.081 CPUs utilized
...
And with --per-core there is an entry with an invalid core ID:
./perf stat record -a --per-core
The socket id number is too big.
Performance counter stats for 'system wide':
S-1-D255-C65535 128 671.04 msec cpu-clock # 54.112 CPUs utilized
...
S36-D0-C0 4 28.27 msec cpu-clock # 2.279 CPUs utilized
...
This fixes the "Session topology" self test on ThunderX2.
After this fix the output contains the correct socket and die IDs and no
longer prints a warning about the size of the socket ID:
./perf stat --per-die -a
Performance counter stats for 'system wide':
S36-D0 128 169,869.39 msec cpu-clock # 127.501 CPUs utilized
...
S3612-D0 128 169,733.05 msec cpu-clock # 127.398 CPUs utilized
Signed-off-by: James Clark <james.clark@arm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: John Garry <john.garry@huawei.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: https://lore.kernel.org/r/20201126141328.6509-10-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e51c546..6248baa 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1369,7 +1369,7 @@ static struct aggr_cpu_id perf_env__get_socket(struct perf_cpu_map *map, int idx
struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
if (cpu != -1)
- id.id = env->cpu[cpu].socket_id;
+ id.socket = env->cpu[cpu].socket_id;
return id;
}
@@ -1382,18 +1382,16 @@ static struct aggr_cpu_id perf_env__get_die(struct perf_cpu_map *map, int idx, v
if (cpu != -1) {
/*
- * Encode socket in bit range 15:8
- * die_id is relative to socket,
- * we need a global id. So we combine
- * socket + die id
+ * die_id is relative to socket, so start
+ * with the socket ID and then add die to
+ * make a unique ID.
*/
- if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n"))
- return cpu_map__empty_aggr_cpu_id();
+ id.socket = env->cpu[cpu].socket_id;
if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n"))
return cpu_map__empty_aggr_cpu_id();
- id.id = (env->cpu[cpu].socket_id << 8) | (env->cpu[cpu].die_id & 0xff);
+ id.id = env->cpu[cpu].die_id & 0xff;
}
return id;
@@ -1407,23 +1405,19 @@ static struct aggr_cpu_id perf_env__get_core(struct perf_cpu_map *map, int idx,
if (cpu != -1) {
/*
- * Encode socket in bit range 31:24
* encode die id in bit range 23:16
* core_id is relative to socket and die,
* we need a global id. So we combine
* socket + die id + core id
*/
- if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n"))
- return cpu_map__empty_aggr_cpu_id();
-
if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n"))
return cpu_map__empty_aggr_cpu_id();
if (WARN_ONCE(env->cpu[cpu].core_id >> 16, "The core id number is too big.\n"))
return cpu_map__empty_aggr_cpu_id();
- id.id = (env->cpu[cpu].socket_id << 24) |
- (env->cpu[cpu].die_id << 16) |
+ id.socket = env->cpu[cpu].socket_id;
+ id.id = (env->cpu[cpu].die_id << 16) |
(env->cpu[cpu].core_id & 0xffff);
}