perf parse-events: Add "cpu" term to set the CPU an event is recorded on

The -C option allows the CPUs for a list of events to be specified but
its not possible to set the CPU for a single event. Add a term to
allow this. The term isn't a general CPU list due to ',' already being
a special character in event parsing instead multiple cpu= terms may
be provided and they will be merged/unioned together.

An example of mixing different types of events counted on different CPUs:
```
$ perf stat -A -C 0,4-5,8 -e "instructions/cpu=0/,l1d-misses/cpu=4,cpu=5/,inst_retired.any/cpu=8/,cycles" -a sleep 0.1

 Performance counter stats for 'system wide':

CPU0            6,979,225      instructions/cpu=0/              #    0.89  insn per cycle
CPU4               75,138      cpu/l1d-misses/
CPU5            1,418,939      cpu/l1d-misses/
CPU8              797,553      cpu/inst_retired.any,cpu=8/
CPU0            7,845,302      cycles
CPU4            6,546,859      cycles
CPU5          185,915,438      cycles
CPU8            2,065,668      cycles

       0.112449242 seconds time elapsed
```

Committer testing:

  root@number:~# grep -m1 "model name" /proc/cpuinfo
  model name	: AMD Ryzen 9 9950X3D 16-Core Processor
  root@number:~# perf stat -A -e "instructions/cpu=0/,instructions,l1d-misses/cpu=4,cpu=5/,cycles" -a sleep 0.1

   Performance counter stats for 'system wide':

  CPU0    2,398,351   instructions/cpu=0/    #  0.44  insn per cycle
  CPU0    2,398,152   instructions           #  0.44  insn per cycle
  CPU1    1,265,634   instructions           #  0.49  insn per cycle
  CPU2      606,087   instructions           #  0.50  insn per cycle
  CPU3    4,025,752   instructions           #  0.52  insn per cycle
  CPU4    4,236,810   instructions           #  0.53  insn per cycle
  CPU5    3,984,832   instructions           #  0.66  insn per cycle
  CPU6      434,132   instructions           #  0.44  insn per cycle
  CPU7       65,752   instructions           #  0.41  insn per cycle
  CPU8      459,083   instructions           #  0.48  insn per cycle
  CPU9    6,464,161   instructions           #  1.31  insn per cycle
  <SNIP>
  root@number:~# perf stat -e "instructions/cpu=0/,instructions,l1d-misses/cpu=4,cpu=5/,cycles" -a sleep 0.

   Performance counter stats for 'system wide':

             144,822      instructions/cpu=0/              #    0.03  insn per cycle
           4,666,114      instructions                     #    0.93  insn per cycle
               2,583      l1d-misses
           4,993,633      cycles

         0.000868512 seconds time elapsed

  root@number:~#

Signed-off-by: Ian Rogers <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Tested-by: Kan Liang <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Dominique Martinet <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: James Clark <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Leo Yan <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Weilin Wang <[email protected]>
Cc: Yicong Yang <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

Author: captain5050

tools/perf/Documentation/perf-list.txt

@@ -289,6 +289,15 @@ 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:
+
+
+  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
+
 
 EVENT GROUPS
 ------------

tools/perf/util/evsel_config.h

@@ -48,6 +48,7 @@ struct evsel_config_term {
 		u32	      aux_sample_size;
 		u64	      cfg_chg;
 		char	      *str;
+		int	      cpu;
 	} val;
 	bool weak;
 };

tools/perf/util/parse-events.c

@@ -7,6 +7,7 @@
 #include <errno.h>
 #include <sys/ioctl.h>
 #include <sys/param.h>
+#include "cpumap.h"
 #include "term.h"
 #include "env.h"
 #include "evlist.h"
@@ -180,6 +181,26 @@ static char *get_config_name(const struct parse_events_terms *head_terms)
 	return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_NAME);
 }
 
+static struct perf_cpu_map *get_config_cpu(const struct parse_events_terms *head_terms)
+{
+	struct parse_events_term *term;
+	struct perf_cpu_map *cpus = NULL;
+
+	if (!head_terms)
+		return NULL;
+
+	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);
+		}
+	}
+
+	return cpus;
+}
+
 /**
  * fix_raw - For each raw term see if there is an event (aka alias) in pmu that
  *           matches the raw's string value. If the string value matches an
@@ -443,11 +464,12 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 	bool found_supported = false;
 	const char *config_name = get_config_name(parsed_terms);
 	const char *metric_id = get_config_metric_id(parsed_terms);
+	struct perf_cpu_map *cpus = get_config_cpu(parsed_terms);
+	int ret = 0;
 
 	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
 		LIST_HEAD(config_terms);
 		struct perf_event_attr attr;
-		int ret;
 
 		if (parse_events__filter_pmu(parse_state, pmu))
 			continue;
@@ -462,7 +484,7 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 						   perf_pmu__auto_merge_stats(pmu),
 						   /*alternate_hw_config=*/PERF_COUNT_HW_MAX);
 			if (ret)
-				return ret;
+				goto out_err;
 			continue;
 		}
 
@@ -482,21 +504,27 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 
 		if (parsed_terms) {
 			if (config_attr(&attr, parsed_terms, parse_state->error,
-					config_term_common))
-				return -EINVAL;
-
-			if (get_config_terms(parsed_terms, &config_terms))
-				return -ENOMEM;
+					config_term_common)) {
+				ret = -EINVAL;
+				goto out_err;
+			}
+			if (get_config_terms(parsed_terms, &config_terms)) {
+				ret = -ENOMEM;
+				goto out_err;
+			}
 		}
 
 		if (__add_event(list, idx, &attr, /*init_attr*/true, config_name ?: name,
 				metric_id, pmu, &config_terms, /*auto_merge_stats=*/false,
-				/*cpu_list=*/NULL,
-				/*alternate_hw_config=*/PERF_COUNT_HW_MAX) == NULL)
-			return -ENOMEM;
+				cpus, /*alternate_hw_config=*/PERF_COUNT_HW_MAX) == NULL)
+			ret = -ENOMEM;
 
 		free_config_terms(&config_terms);
+		if (ret)
+			goto out_err;
 	}
+out_err:
+	perf_cpu_map__put(cpus);
 	return found_supported ? 0 : -EINVAL;
 }
 
@@ -815,6 +843,7 @@ const char *parse_events__term_type_str(enum parse_events__term_type term_type)
 		[PARSE_EVENTS__TERM_TYPE_RAW]                   = "raw",
 		[PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE]          = "legacy-cache",
 		[PARSE_EVENTS__TERM_TYPE_HARDWARE]              = "hardware",
+		[PARSE_EVENTS__TERM_TYPE_CPU]			= "cpu",
 	};
 	if ((unsigned int)term_type >= __PARSE_EVENTS__TERM_TYPE_NR)
 		return "unknown term";
@@ -844,6 +873,7 @@ config_term_avail(enum parse_events__term_type term_type, struct parse_events_er
 	case PARSE_EVENTS__TERM_TYPE_METRIC_ID:
 	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
 	case PARSE_EVENTS__TERM_TYPE_PERCORE:
+	case PARSE_EVENTS__TERM_TYPE_CPU:
 		return true;
 	case PARSE_EVENTS__TERM_TYPE_USER:
 	case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ:
@@ -991,6 +1021,15 @@ do {									   \
 			return -EINVAL;
 		}
 		break;
+	case PARSE_EVENTS__TERM_TYPE_CPU:
+		CHECK_TYPE_VAL(NUM);
+		if (term->val.num >= (u64)cpu__max_present_cpu().cpu) {
+			parse_events_error__handle(err, term->err_val,
+						strdup("too big"),
+						NULL);
+			return -EINVAL;
+		}
+		break;
 	case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
 	case PARSE_EVENTS__TERM_TYPE_USER:
 	case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
@@ -1118,6 +1157,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_RAW:
 	case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
 	case PARSE_EVENTS__TERM_TYPE_HARDWARE:
+	case PARSE_EVENTS__TERM_TYPE_CPU:
 	default:
 		if (err) {
 			parse_events_error__handle(err, term->err_term,
@@ -1252,6 +1292,7 @@ do {								\
 		case PARSE_EVENTS__TERM_TYPE_RAW:
 		case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
 		case PARSE_EVENTS__TERM_TYPE_HARDWARE:
+		case PARSE_EVENTS__TERM_TYPE_CPU:
 		default:
 			break;
 		}
@@ -1306,6 +1347,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct parse_events_terms *head
 		case PARSE_EVENTS__TERM_TYPE_RAW:
 		case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
 		case PARSE_EVENTS__TERM_TYPE_HARDWARE:
+		case PARSE_EVENTS__TERM_TYPE_CPU:
 		default:
 			break;
 		}
@@ -1350,6 +1392,7 @@ static int __parse_events_add_numeric(struct parse_events_state *parse_state,
 	struct perf_event_attr attr;
 	LIST_HEAD(config_terms);
 	const char *name, *metric_id;
+	struct perf_cpu_map *cpus;
 	int ret;
 
 	memset(&attr, 0, sizeof(attr));
@@ -1371,10 +1414,11 @@ static int __parse_events_add_numeric(struct parse_events_state *parse_state,
 
 	name = get_config_name(head_config);
 	metric_id = get_config_metric_id(head_config);
+	cpus = get_config_cpu(head_config);
 	ret = __add_event(list, &parse_state->idx, &attr, /*init_attr*/true, name,
-			  metric_id, pmu, &config_terms, /*auto_merge_stats=*/false,
-			  /*cpu_list=*/NULL, /*alternate_hw_config=*/PERF_COUNT_HW_MAX
-		) == NULL ? -ENOMEM : 0;
+			metric_id, pmu, &config_terms, /*auto_merge_stats=*/false,
+			cpus, /*alternate_hw_config=*/PERF_COUNT_HW_MAX) ? 0 : -ENOMEM;
+	perf_cpu_map__put(cpus);
 	free_config_terms(&config_terms);
 	return ret;
 }
@@ -1434,6 +1478,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 	LIST_HEAD(config_terms);
 	struct parse_events_terms parsed_terms;
 	bool alias_rewrote_terms = false;
+	struct perf_cpu_map *term_cpu = NULL;
 
 	if (verbose > 1) {
 		struct strbuf sb;
@@ -1528,11 +1573,12 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 		return -EINVAL;
 	}
 
+	term_cpu = get_config_cpu(&parsed_terms);
 	evsel = __add_event(list, &parse_state->idx, &attr, /*init_attr=*/true,
 			    get_config_name(&parsed_terms),
 			    get_config_metric_id(&parsed_terms), pmu,
-			    &config_terms, auto_merge_stats, /*cpu_list=*/NULL,
-			    alternate_hw_config);
+			    &config_terms, auto_merge_stats, term_cpu, alternate_hw_config);
+	perf_cpu_map__put(term_cpu);
 	if (!evsel) {
 		parse_events_terms__exit(&parsed_terms);
 		return -ENOMEM;

tools/perf/util/parse-events.h

@@ -80,7 +80,8 @@ enum parse_events__term_type {
 	PARSE_EVENTS__TERM_TYPE_RAW,
 	PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE,
 	PARSE_EVENTS__TERM_TYPE_HARDWARE,
-#define	__PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_HARDWARE + 1)
+	PARSE_EVENTS__TERM_TYPE_CPU,
+#define	__PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_CPU + 1)
 };
 
 struct parse_events_term {

tools/perf/util/parse-events.l

@@ -335,6 +335,7 @@ aux-output		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
 aux-action		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_ACTION); }
 aux-sample-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); }
 metric-id		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); }
+cpu			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CPU); }
 cpu-cycles|cycles				{ return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); }
 stalled-cycles-frontend|idle-cycles-frontend	{ return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
 stalled-cycles-backend|idle-cycles-backend	{ return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }

tools/perf/util/pmu.c

@@ -1470,7 +1470,7 @@ static int pmu_config_term(const struct perf_pmu *pmu,
 			break;
 		case PARSE_EVENTS__TERM_TYPE_USER: /* Not hardcoded. */
 			return -EINVAL;
-		case PARSE_EVENTS__TERM_TYPE_NAME ... PARSE_EVENTS__TERM_TYPE_HARDWARE:
+		case PARSE_EVENTS__TERM_TYPE_NAME ... PARSE_EVENTS__TERM_TYPE_CPU:
 			/* Skip non-config terms. */
 			break;
 		default:
@@ -1852,6 +1852,7 @@ int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_call
 		"aux-output",
 		"aux-action=(pause|resume|start-paused)",
 		"aux-sample-size=number",
+		"cpu=number",
 	};
 	struct perf_pmu_format *format;
 	int ret;