Merge tag 'perf-tools-for-v6.13-2024-11-24' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Namhyung Kim:
 "perf record:

   - Enable leader sampling for inherited task events. It was supported
     only for system-wide events but the kernel started to support such
     a setup since v6.12.

     This is to reduce the number of PMU interrupts. The samples of the
     leader event will contain counts of other events and no samples
     will be generated for the other member events.

       $ perf record -e '{cycles,instructions}:S'  ${MYPROG}

  perf report:

   - Fix --branch-history option to display more branch-related
     information like prediction, abort and cycles which is available
     on Intel machines.

       $ perf record -bg -- perf test -w brstack

       $ perf report --branch-history
       ...
       #
       # Overhead  Source:Line               Symbol          Shared Object         Predicted  Abort  Cycles  IPC   [IPC Coverage]
       # ........  ........................  ..............  ....................  .........  .....  ......  ....................
       #
            8.17%  copy_page_64.S:19         [k] copy_page   [kernel.kallsyms]     50.0%      0      5       -      -
                   |
                   ---xas_load xarray.h:171
                      |
                      |--5.68%--xas_load xarray.c:245 (cycles:1)
                      |          xas_load xarray.c:242
                      |          xas_load xarray.h:1260 (cycles:1)
                      |          xas_descend xarray.c:146
                      |          xas_load xarray.c:244 (cycles:2)
                      |          xas_load xarray.c:245
                      |          xas_descend xarray.c:218 (cycles:10)
       ...

  perf stat:

   - Add HWMON PMU support.

     The HWMON provides various system information like CPU/GPU
     temperature, fan speed and so on. Expose them as PMU events so that
     users can see the values using perf stat commands.

       $ perf stat -e temp_cpu,fan1 true

        Performance counter stats for 'true':

                    60.00 'C   temp_cpu
                        0 rpm  fan1

              0.000745382 seconds time elapsed

              0.000883000 seconds user
              0.000000000 seconds sys

   - Display metric threshold in JSON output.

     Some metrics define thresholds to classify value ranges. It used to
     be in a different color but it won't work for JSON.

     Add "metric-threshold" field to the JSON that can be one of "good",
     "less good", "nearly bad" and "bad".

       # perf stat -a -M TopdownL1 -j true
       {"counter-value" : "18693525.000000", "unit" : "", "event" : "TOPDOWN.SLOTS", "event-runtime" : 5552708, "pcnt-running" : 100.00, "metric-value" : "43.226002", "metric-unit" : "%  tma_backend_bound", "metric-threshold" : "bad"}
       {"metric-value" : "29.212267", "metric-unit" : "%  tma_frontend_bound", "metric-threshold" : "bad"}
       {"metric-value" : "7.138972", "metric-unit" : "%  tma_bad_speculation", "metric-threshold" : "good"}
       {"metric-value" : "20.422759", "metric-unit" : "%  tma_retiring", "metric-threshold" : "good"}
       {"counter-value" : "3817732.000000", "unit" : "", "event" : "topdown-retiring", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
       {"counter-value" : "5472824.000000", "unit" : "", "event" : "topdown-fe-bound", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
       {"counter-value" : "7984780.000000", "unit" : "", "event" : "topdown-be-bound", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
       {"counter-value" : "1418181.000000", "unit" : "", "event" : "topdown-bad-spec", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
       ...

  perf sched:

   - Add -P/--pre-migrations option for 'timehist' sub-command to track
     time a task waited on a run-queue before migrating to a different
     CPU.

       $ perf sched timehist -P
                  time    cpu  task name                       wait time  sch delay   run time  pre-mig time
                               [tid/pid]                          (msec)     (msec)     (msec)     (msec)
       --------------- ------  ------------------------------  ---------  ---------  ---------  ---------
         585940.535527 [0000]  perf[584885]                        0.000      0.000      0.000      0.000
         585940.535535 [0000]  migration/0[20]                     0.000      0.002      0.008      0.000
         585940.535559 [0001]  perf[584885]                        0.000      0.000      0.000      0.000
         585940.535563 [0001]  migration/1[25]                     0.000      0.001      0.004      0.000
         585940.535678 [0002]  perf[584885]                        0.000      0.000      0.000      0.000
         585940.535686 [0002]  migration/2[31]                     0.000      0.002      0.008      0.000
         585940.535905 [0001]  <idle>                              0.000      0.000      0.342      0.000
         585940.535938 [0003]  perf[584885]                        0.000      0.000      0.000      0.000
         585940.537048 [0001]  sleep[584886]                       0.000      0.019      1.142      0.001
         585940.537749 [0002]  <idle>                              0.000      0.000      2.062      0.000
       ...

  Build:

   - Make libunwind opt-in (LIBUNWIND=1) rather than opt-out.

     The perf tools are generally built with libelf and libdw which has
     unwinder functionality. The libunwind support predates it and no
     need to have duplicate unwinders by default.

   - Rename NO_DWARF=1 build option to NO_LIBDW=1 in order to clarify
     it's using libdw for handling DWARF information.

  Internals:

   - Do not set exclude_guest bit in the perf_event_attr by default.

     This was causing a trouble in AMD IBS PMU as it doesn't support the
     bit. The bit will be set when it's needed later by the fallback
     logic. Also update the missing feature detection logic to make sure
     not clear supported bits unnecessarily.

   - Run perf test in parallel by default and mark flaky tests
     "exclusive" to run them serially at the end. Some test numbers are
     changed but the test can complete in less than half the time.

  JSON vendor events:

   - Add AMD Zen 5 events and metrics.

   - Add i.MX91 and i.MX95 DDR metrics

   - Fix HiSilicon HIP08 Topdown metric name.

   - Support compat events on PowerPC"

* tag 'perf-tools-for-v6.13-2024-11-24' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (232 commits)
  perf tests: Fix hwmon parsing with PMU name test
  perf hwmon_pmu: Ensure hwmon key union is zeroed before use
  perf tests hwmon_pmu: Remove double evlist__delete()
  perf/test: fix perf ftrace test on s390
  perf bpf-filter: Return -ENOMEM directly when pfi allocation fails
  perf test: Correct hwmon test PMU detection
  perf: Remove unused del_perf_probe_events()
  perf pmu: Move pmu_metrics_table__find and remove ARM override
  perf jevents: Add map_for_cpu()
  perf header: Pass a perf_cpu rather than a PMU to get_cpuid_str
  perf header: Avoid transitive PMU includes
  perf arm64 header: Use cpu argument in get_cpuid
  perf header: Refactor get_cpuid to take a CPU for ARM
  perf header: Move is_cpu_online to numa bench
  perf jevents: fix breakage when do perf stat on system metric
  perf test: Add missing __exit calls in tool/hwmon tests
  perf tests: Make leader sampling test work without branch event
  perf util: Remove kernel version deadcode
  perf test shell trace_exit_race: Use --no-comm to avoid cases where COMM isn't resolved
  perf test shell trace_exit_race: Show what went wrong in verbose mode
  ...

1 files changed, 50 insertions, 75 deletions

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 9a8be1e46d674..afeb8d815bbff 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -228,7 +228,7 @@ __add_event(struct list_head *list, int *idx,
 	    bool init_attr,
 	    const char *name, const char *metric_id, struct perf_pmu *pmu,
 	    struct list_head *config_terms, bool auto_merge_stats,
-	    struct perf_cpu_map *cpu_list)
+	    struct perf_cpu_map *cpu_list, u64 alternate_hw_config)
 {
 	struct evsel *evsel;
 	struct perf_cpu_map *cpus = perf_cpu_map__is_empty(cpu_list) && pmu ? pmu->cpus : cpu_list;
@@ -263,7 +263,7 @@ __add_event(struct list_head *list, int *idx,
 	evsel->core.is_pmu_core = pmu ? pmu->is_core : false;
 	evsel->auto_merge_stats = auto_merge_stats;
 	evsel->pmu = pmu;
-	evsel->pmu_name = pmu ? strdup(pmu->name) : NULL;
+	evsel->alternate_hw_config = alternate_hw_config;
 
 	if (name)
 		evsel->name = strdup(name);
@@ -286,47 +286,19 @@ struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr,
 {
 	return __add_event(/*list=*/NULL, &idx, attr, /*init_attr=*/false, name,
 			   metric_id, pmu, /*config_terms=*/NULL,
-			   /*auto_merge_stats=*/false, /*cpu_list=*/NULL);
+			   /*auto_merge_stats=*/false, /*cpu_list=*/NULL,
+			   /*alternate_hw_config=*/PERF_COUNT_HW_MAX);
 }
 
 static int add_event(struct list_head *list, int *idx,
 		     struct perf_event_attr *attr, const char *name,
-		     const char *metric_id, struct list_head *config_terms)
+		     const char *metric_id, struct list_head *config_terms,
+		     u64 alternate_hw_config)
 {
 	return __add_event(list, idx, attr, /*init_attr*/true, name, metric_id,
 			   /*pmu=*/NULL, config_terms,
-			   /*auto_merge_stats=*/false, /*cpu_list=*/NULL) ? 0 : -ENOMEM;
-}
-
-static int add_event_tool(struct list_head *list, int *idx,
-			  enum perf_tool_event tool_event)
-{
-	struct evsel *evsel;
-	struct perf_event_attr attr = {
-		.type = PERF_TYPE_SOFTWARE,
-		.config = PERF_COUNT_SW_DUMMY,
-	};
-	struct perf_cpu_map *cpu_list = NULL;
-
-	if (tool_event == PERF_TOOL_DURATION_TIME) {
-		/* Duration time is gathered globally, pretend it is only on CPU0. */
-		cpu_list = perf_cpu_map__new("0");
-	}
-	evsel = __add_event(list, idx, &attr, /*init_attr=*/true, /*name=*/NULL,
-			    /*metric_id=*/NULL, /*pmu=*/NULL,
-			    /*config_terms=*/NULL, /*auto_merge_stats=*/false,
-			    cpu_list);
-	perf_cpu_map__put(cpu_list);
-	if (!evsel)
-		return -ENOMEM;
-	evsel->tool_event = tool_event;
-	if (tool_event == PERF_TOOL_DURATION_TIME
-	    || tool_event == PERF_TOOL_USER_TIME
-	    || tool_event == PERF_TOOL_SYSTEM_TIME) {
-		free((char *)evsel->unit);
-		evsel->unit = strdup("ns");
-	}
-	return 0;
+			   /*auto_merge_stats=*/false, /*cpu_list=*/NULL,
+			   alternate_hw_config) ? 0 : -ENOMEM;
 }
 
 /**
@@ -450,7 +422,7 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
 static int parse_events_add_pmu(struct parse_events_state *parse_state,
 				struct list_head *list, struct perf_pmu *pmu,
 				const struct parse_events_terms *const_parsed_terms,
-				bool auto_merge_stats);
+				bool auto_merge_stats, u64 alternate_hw_config);
 
 int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			   struct parse_events_state *parse_state,
@@ -476,7 +448,8 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			 */
 			ret = parse_events_add_pmu(parse_state, list, pmu,
 						   parsed_terms,
-						   perf_pmu__auto_merge_stats(pmu));
+						   perf_pmu__auto_merge_stats(pmu),
+						   /*alternate_hw_config=*/PERF_COUNT_HW_MAX);
 			if (ret)
 				return ret;
 			continue;
@@ -507,7 +480,8 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 
 		if (__add_event(list, idx, &attr, /*init_attr*/true, config_name ?: name,
 				metric_id, pmu, &config_terms, /*auto_merge_stats=*/false,
-				/*cpu_list=*/NULL) == NULL)
+				/*cpu_list=*/NULL,
+				/*alternate_hw_config=*/PERF_COUNT_HW_MAX) == NULL)
 			return -ENOMEM;
 
 		free_config_terms(&config_terms);
@@ -772,7 +746,7 @@ int parse_events_add_breakpoint(struct parse_events_state *parse_state,
 	name = get_config_name(head_config);
 
 	return add_event(list, &parse_state->idx, &attr, name, /*mertic_id=*/NULL,
-			 &config_terms);
+			&config_terms, /*alternate_hw_config=*/PERF_COUNT_HW_MAX);
 }
 
 static int check_type_val(struct parse_events_term *term,
@@ -794,7 +768,7 @@ static int check_type_val(struct parse_events_term *term,
 
 static bool config_term_shrinked;
 
-static const char *config_term_name(enum parse_events__term_type term_type)
+const char *parse_events__term_type_str(enum parse_events__term_type term_type)
 {
 	/*
 	 * Update according to parse-events.l
@@ -880,7 +854,7 @@ config_term_avail(enum parse_events__term_type term_type, struct parse_events_er
 
 		/* term_type is validated so indexing is safe */
 		if (asprintf(&err_str, "'%s' is not usable in 'perf stat'",
-			     config_term_name(term_type)) >= 0)
+			     parse_events__term_type_str(term_type)) >= 0)
 			parse_events_error__handle(err, -1, err_str, NULL);
 		return false;
 	}
@@ -1004,7 +978,7 @@ do {									   \
 	case PARSE_EVENTS__TERM_TYPE_HARDWARE:
 	default:
 		parse_events_error__handle(err, term->err_term,
-					strdup(config_term_name(term->type_term)),
+					strdup(parse_events__term_type_str(term->type_term)),
 					parse_events_formats_error_string(NULL));
 		return -EINVAL;
 	}
@@ -1072,6 +1046,7 @@ static int config_term_pmu(struct perf_event_attr *attr,
 		if (perf_pmu__have_event(pmu, term->config)) {
 			term->type_term = PARSE_EVENTS__TERM_TYPE_USER;
 			term->no_value = true;
+			term->alternate_hw_config = true;
 		} else {
 			attr->type = PERF_TYPE_HARDWARE;
 			attr->config = term->val.num;
@@ -1127,8 +1102,9 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	default:
 		if (err) {
 			parse_events_error__handle(err, term->err_term,
-						   strdup(config_term_name(term->type_term)),
-				strdup("valid terms: call-graph,stack-size\n"));
+					strdup(parse_events__term_type_str(term->type_term)),
+					strdup("valid terms: call-graph,stack-size\n")
+				);
 		}
 		return -EINVAL;
 	}
@@ -1384,8 +1360,9 @@ 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);
 	ret = __add_event(list, &parse_state->idx, &attr, /*init_attr*/true, name,
-			metric_id, pmu, &config_terms, /*auto_merge_stats=*/false,
-			/*cpu_list=*/NULL) ? 0 : -ENOMEM;
+			  metric_id, pmu, &config_terms, /*auto_merge_stats=*/false,
+			  /*cpu_list=*/NULL, /*alternate_hw_config=*/PERF_COUNT_HW_MAX
+		) == NULL ? -ENOMEM : 0;
 	free_config_terms(&config_terms);
 	return ret;
 }
@@ -1421,13 +1398,6 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 					type, /*extended_type=*/0, config, head_config);
 }
 
-int parse_events_add_tool(struct parse_events_state *parse_state,
-			  struct list_head *list,
-			  int tool_event)
-{
-	return add_event_tool(list, &parse_state->idx, tool_event);
-}
-
 static bool config_term_percore(struct list_head *config_terms)
 {
 	struct evsel_config_term *term;
@@ -1443,7 +1413,7 @@ static bool config_term_percore(struct list_head *config_terms)
 static int parse_events_add_pmu(struct parse_events_state *parse_state,
 				struct list_head *list, struct perf_pmu *pmu,
 				const struct parse_events_terms *const_parsed_terms,
-				bool auto_merge_stats)
+				bool auto_merge_stats, u64 alternate_hw_config)
 {
 	struct perf_event_attr attr;
 	struct perf_pmu_info info;
@@ -1480,7 +1450,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 				    /*init_attr=*/true, /*name=*/NULL,
 				    /*metric_id=*/NULL, pmu,
 				    /*config_terms=*/NULL, auto_merge_stats,
-				    /*cpu_list=*/NULL);
+				    /*cpu_list=*/NULL, alternate_hw_config);
 		return evsel ? 0 : -ENOMEM;
 	}
 
@@ -1501,7 +1471,8 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	/* Look for event names in the terms and rewrite into format based terms. */
 	if (perf_pmu__check_alias(pmu, &parsed_terms,
-				  &info, &alias_rewrote_terms, err)) {
+				  &info, &alias_rewrote_terms,
+				  &alternate_hw_config, err)) {
 		parse_events_terms__exit(&parsed_terms);
 		return -EINVAL;
 	}
@@ -1537,7 +1508,9 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 		return -ENOMEM;
 	}
 
-	if (perf_pmu__config(pmu, &attr, &parsed_terms, parse_state->error)) {
+	/* Skip configuring hard coded terms that were applied by config_attr. */
+	if (perf_pmu__config(pmu, &attr, &parsed_terms, /*apply_hardcoded=*/false,
+			     parse_state->error)) {
 		free_config_terms(&config_terms);
 		parse_events_terms__exit(&parsed_terms);
 		return -EINVAL;
@@ -1546,7 +1519,8 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 	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);
+			    &config_terms, auto_merge_stats, /*cpu_list=*/NULL,
+			    alternate_hw_config);
 	if (!evsel) {
 		parse_events_terms__exit(&parsed_terms);
 		return -ENOMEM;
@@ -1567,7 +1541,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 }
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
-			       const char *event_name,
+			       const char *event_name, u64 hw_config,
 			       const struct parse_events_terms *const_parsed_terms,
 			       struct list_head **listp, void *loc_)
 {
@@ -1620,7 +1594,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 
 		auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
 		if (!parse_events_add_pmu(parse_state, list, pmu,
-					  &parsed_terms, auto_merge_stats)) {
+					  &parsed_terms, auto_merge_stats, hw_config)) {
 			struct strbuf sb;
 
 			strbuf_init(&sb, /*hint=*/ 0);
@@ -1633,7 +1607,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 
 	if (parse_state->fake_pmu) {
 		if (!parse_events_add_pmu(parse_state, list, perf_pmus__fake_pmu(), &parsed_terms,
-					  /*auto_merge_stats=*/true)) {
+					  /*auto_merge_stats=*/true, hw_config)) {
 			struct strbuf sb;
 
 			strbuf_init(&sb, /*hint=*/ 0);
@@ -1674,13 +1648,15 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state
 	/* Attempt to add to list assuming event_or_pmu is a PMU name. */
 	pmu = perf_pmus__find(event_or_pmu);
 	if (pmu && !parse_events_add_pmu(parse_state, *listp, pmu, const_parsed_terms,
-					/*auto_merge_stats=*/false))
+					 /*auto_merge_stats=*/false,
+					 /*alternate_hw_config=*/PERF_COUNT_HW_MAX))
 		return 0;
 
 	if (parse_state->fake_pmu) {
 		if (!parse_events_add_pmu(parse_state, *listp, perf_pmus__fake_pmu(),
 					  const_parsed_terms,
-					  /*auto_merge_stats=*/false))
+					  /*auto_merge_stats=*/false,
+					  /*alternate_hw_config=*/PERF_COUNT_HW_MAX))
 			return 0;
 	}
 
@@ -1693,7 +1669,8 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state
 
 			if (!parse_events_add_pmu(parse_state, *listp, pmu,
 						  const_parsed_terms,
-						  auto_merge_stats)) {
+						  auto_merge_stats,
+						  /*alternate_hw_config=*/PERF_COUNT_HW_MAX)) {
 				ok++;
 				parse_state->wild_card_pmus = true;
 			}
@@ -1704,7 +1681,8 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state
 
 	/* Failure to add, assume event_or_pmu is an event name. */
 	zfree(listp);
-	if (!parse_events_multi_pmu_add(parse_state, event_or_pmu, const_parsed_terms, listp, loc))
+	if (!parse_events_multi_pmu_add(parse_state, event_or_pmu, PERF_COUNT_HW_MAX,
+					const_parsed_terms, listp, loc))
 		return 0;
 
 	if (asprintf(&help, "Unable to find PMU or event on a PMU of '%s'", event_or_pmu) < 0)
@@ -1755,14 +1733,10 @@ static int parse_events__modifier_list(struct parse_events_state *parse_state,
 		int exclude = eu | ek | eh;
 		int exclude_GH = group ? evsel->exclude_GH : 0;
 
-		if (mod.precise) {
-			/* use of precise requires exclude_guest */
-			eG = 1;
-		}
 		if (mod.user) {
 			if (!exclude)
 				exclude = eu = ek = eh = 1;
-			if (!exclude_GH && !perf_guest)
+			if (!exclude_GH && !perf_guest && exclude_GH_default)
 				eG = 1;
 			eu = 0;
 		}
@@ -2566,7 +2540,7 @@ int parse_events_term__num(struct parse_events_term **term,
 	struct parse_events_term temp = {
 		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
 		.type_term = type_term,
-		.config    = config ? : strdup(config_term_name(type_term)),
+		.config    = config ? : strdup(parse_events__term_type_str(type_term)),
 		.no_value  = no_value,
 		.err_term  = loc_term ? loc_term->first_column : 0,
 		.err_val   = loc_val  ? loc_val->first_column  : 0,
@@ -2600,7 +2574,7 @@ int parse_events_term__term(struct parse_events_term **term,
 			    void *loc_term, void *loc_val)
 {
 	return parse_events_term__str(term, term_lhs, NULL,
-				      strdup(config_term_name(term_rhs)),
+				      strdup(parse_events__term_type_str(term_rhs)),
 				      loc_term, loc_val);
 }
 
@@ -2707,7 +2681,8 @@ int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct
 				if (ret < 0)
 					return ret;
 			} else if ((unsigned int)term->type_term < __PARSE_EVENTS__TERM_TYPE_NR) {
-				ret = strbuf_addf(sb, "%s=", config_term_name(term->type_term));
+				ret = strbuf_addf(sb, "%s=",
+						  parse_events__term_type_str(term->type_term));
 				if (ret < 0)
 					return ret;
 			}
@@ -2727,7 +2702,7 @@ static void config_terms_list(char *buf, size_t buf_sz)
 
 	buf[0] = '\0';
 	for (i = 0; i < __PARSE_EVENTS__TERM_TYPE_NR; i++) {
-		const char *name = config_term_name(i);
+		const char *name = parse_events__term_type_str(i);
 
 		if (!config_term_avail(i, NULL))
 			continue;