[PATCH v3 04/15] perf parse-events: Allow the cpu term to be a PMU or CPU range

[Ian Rogers <irogers@google.com>]

On hybrid systems, events like msr/tsc/ will aggregate counts across
all CPUs. Often metrics only want a value like msr/tsc/ for the cores
on which the metric is being computed. Listing each CPU with terms
cpu=0,cpu=1.. is laborious and would need to be encoded for all
variations of a CPU model.

Allow the cpumask from a PMU to be an argument to the cpu term. For
example in the following the cpumask of the cstate_pkg PMU selects the
CPUs to count msr/tsc/ counter upon:
```
$ cat /sys/bus/event_source/devices/cstate_pkg/cpumask
0
$ perf stat -A -e 'msr/tsc,cpu=cstate_pkg/' -a sleep 0.1

 Performance counter stats for 'system wide':

CPU0          252,621,253      msr/tsc,cpu=cstate_pkg/

       0.101184092 seconds time elapsed
```

As the cpu term is now also allowed to be a string, allow it to encode
a range of CPUs (a list can't be supported as ',' is already a special
token).

The "event qualifiers" section of the `perf list` man page is updated
to detail the additional behavior.  The man page formatting is tidied
up in this section, as it was incorrectly appearing within the
"parameterized events" section.

Reviewed-by: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/Documentation/perf-list.txt | 25 +++++++++-----
 tools/perf/util/parse-events.c         | 47 +++++++++++++++++++++-----
 2 files changed, 54 insertions(+), 18 deletions(-)

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index ce0735021473..28215306a78a 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -278,26 +278,33 @@ also be supplied. For example:
 
   perf stat -C 0 -e 'hv_gpci/dtbp_ptitc,phys_processor_idx=0x2/' ...
 
-EVENT QUALIFIERS:
+EVENT QUALIFIERS
+----------------
 
 It is also possible to add extra qualifiers to an event:
 
 percore:
 
-Sums up the event counts for all hardware threads in a core, e.g.:
-
-
-  perf stat -e cpu/event=0,umask=0x3,percore=1/
+  Sums up the event counts for all hardware threads in a core, e.g.:
+    perf stat -e cpu/event=0,umask=0x3,percore=1/
 
 cpu:
 
-Specifies the CPU to open the event upon. The value may be repeated to
-specify opening the event on multiple CPUs:
+  Specifies a CPU or a range of CPUs to open the event upon. It may
+  also reference a PMU to copy the CPU mask from. The value may be
+  repeated to specify opening the event on multiple CPUs.
 
+  Example 1: to open the instructions event on CPUs 0 and 2, the
+  cycles event on CPUs 1 and 2:
+    perf stat -e instructions/cpu=0,cpu=2/,cycles/cpu=1-2/ -a sleep 1
 
-  perf stat -e instructions/cpu=0,cpu=2/,cycles/cpu=1,cpu=2/ -a sleep 1
-  perf stat -e data_read/cpu=0/,data_write/cpu=1/ -a sleep 1
+  Example 2: to open the data_read uncore event on CPU 0 and the
+  data_write uncore event on CPU 1:
+    perf stat -e data_read/cpu=0/,data_write/cpu=1/ -a sleep 1
 
+  Example 3: to open the software msr/tsc/ event only on the CPUs
+  matching those from the cpu_core PMU:
+    perf stat -e msr/tsc,cpu=cpu_core/ -a sleep 1
 
 EVENT GROUPS
 ------------
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 3fd6cc0c2794..a337e4d22ff2 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -187,10 +187,22 @@ static struct perf_cpu_map *get_config_cpu(const struct parse_events_terms *head
 
 	list_for_each_entry(term, &head_terms->terms, list) {
 		if (term->type_term == PARSE_EVENTS__TERM_TYPE_CPU) {
-			struct perf_cpu_map *cpu = perf_cpu_map__new_int(term->val.num);
-
-			perf_cpu_map__merge(&cpus, cpu);
-			perf_cpu_map__put(cpu);
+			struct perf_cpu_map *term_cpus;
+
+			if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
+				term_cpus = perf_cpu_map__new_int(term->val.num);
+			} else {
+				struct perf_pmu *pmu = perf_pmus__find(term->val.str);
+
+				if (pmu && perf_cpu_map__is_empty(pmu->cpus))
+					term_cpus = pmu->is_core ? cpu_map__online() : NULL;
+				else if (pmu)
+					term_cpus = perf_cpu_map__get(pmu->cpus);
+				else
+					term_cpus = perf_cpu_map__new(term->val.str);
+			}
+			perf_cpu_map__merge(&cpus, term_cpus);
+			perf_cpu_map__put(term_cpus);
 		}
 	}
 
@@ -1048,15 +1060,32 @@ do {									   \
 			return -EINVAL;
 		}
 		break;
-	case PARSE_EVENTS__TERM_TYPE_CPU:
-		CHECK_TYPE_VAL(NUM);
-		if (term->val.num >= (u64)cpu__max_present_cpu().cpu) {
+	case PARSE_EVENTS__TERM_TYPE_CPU: {
+		struct perf_cpu_map *map;
+
+		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
+			if (term->val.num >= (u64)cpu__max_present_cpu().cpu) {
+				parse_events_error__handle(err, term->err_val,
+							strdup("too big"),
+							/*help=*/NULL);
+				return -EINVAL;
+			}
+			break;
+		}
+		assert(term->type_val == PARSE_EVENTS__TERM_TYPE_STR);
+		if (perf_pmus__find(term->val.str) != NULL)
+			break;
+
+		map = perf_cpu_map__new(term->val.str);
+		if (!map) {
 			parse_events_error__handle(err, term->err_val,
-						strdup("too big"),
-						NULL);
+						   strdup("not a valid PMU or CPU number"),
+						   /*help=*/NULL);
 			return -EINVAL;
 		}
+		perf_cpu_map__put(map);
 		break;
+	}
 	case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
 	case PARSE_EVENTS__TERM_TYPE_USER:
 	case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
-- 
2.50.0.727.gbf7dc18ff4-goog