Merge tag 'perf-tools-fixes-for-v5.9-2020-09-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Set PERF_SAMPLE_PERIOD if attr->freq is set.

 - Remove trailing commas from AMD JSON vendor event files.

 - Don't clear event's period if set by a event definition term.

 - Leader sampling shouldn't clear sample period in 'perf test'.

 - Fix the "signal" test inline assembly when built with DEBUG=1.

 - Fix memory leaks detected by ASAN, some in normal paths, some in
   error paths.

 - Fix 2 memory sanitizer warnings in 'perf bench'.

 - Fix the ratio comments of miss-events in 'perf stat'.

 - Prevent override of attr->sample_period for libpfm4 events.

 - Sync kvm.h and in.h headers with the kernel sources.

* tag 'perf-tools-fixes-for-v5.9-2020-09-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf stat: Fix the ratio comments of miss-events
  perf test: Free formats for perf pmu parse test
  perf metric: Do not free metric when failed to resolve
  perf metric: Free metric when it failed to resolve
  perf metric: Release expr_parse_ctx after testing
  perf test: Fix memory leaks in parse-metric test
  perf parse-event: Fix memory leak in evsel->unit
  perf evlist: Fix cpu/thread map leak
  perf metric: Fix some memory leaks - part 2
  perf metric: Fix some memory leaks
  perf test: Free aliases for PMU event map aliases test
  perf vendor events amd: Remove trailing commas
  perf test: Leader sampling shouldn't clear sample period
  perf record: Don't clear event's period if set by a term
  tools headers UAPI: update linux/in.h copy
  tools headers UAPI: Sync kvm.h headers with the kernel sources
  perf record: Prevent override of attr->sample_period for libpfm4 events
  perf record: Set PERF_RECORD_PERIOD if attr->freq is set.
  perf bench: Fix 2 memory sanitizer warnings
  perf test: Fix the "signal" test inline assembly

17 files changed, 149 insertions, 49 deletions

diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 71d830d7b923..cecce93ccc63 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -66,11 +66,10 @@ static void fdpair(int fds[2])
 /* Block until we're ready to go */
 static void ready(int ready_out, int wakefd)
 {
-	char dummy;
 	struct pollfd pollfd = { .fd = wakefd, .events = POLLIN };
 
 	/* Tell them we're ready. */
-	if (write(ready_out, &dummy, 1) != 1)
+	if (write(ready_out, "R", 1) != 1)
 		err(EXIT_FAILURE, "CLIENT: ready write");
 
 	/* Wait for "GO" signal */
@@ -85,6 +84,7 @@ static void *sender(struct sender_context *ctx)
 	unsigned int i, j;
 
 	ready(ctx->ready_out, ctx->wakefd);
+	memset(data, 'S', sizeof(data));
 
 	/* Now pump to every receiver. */
 	for (i = 0; i < nr_loops; i++) {
diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/core.json b/tools/perf/pmu-events/arch/x86/amdzen1/core.json
index 7e1aa8273935..653b11b23399 100644
--- a/tools/perf/pmu-events/arch/x86/amdzen1/core.json
+++ b/tools/perf/pmu-events/arch/x86/amdzen1/core.json
@@ -61,7 +61,7 @@
   {
     "EventName": "ex_ret_brn_ind_misp",
     "EventCode": "0xca",
-    "BriefDescription": "Retired Indirect Branch Instructions Mispredicted.",
+    "BriefDescription": "Retired Indirect Branch Instructions Mispredicted."
   },
   {
     "EventName": "ex_ret_mmx_fp_instr.sse_instr",
diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/core.json b/tools/perf/pmu-events/arch/x86/amdzen2/core.json
index de89e5a44ff1..4b75183da94a 100644
--- a/tools/perf/pmu-events/arch/x86/amdzen2/core.json
+++ b/tools/perf/pmu-events/arch/x86/amdzen2/core.json
@@ -125,6 +125,6 @@
   {
     "EventName": "ex_ret_fus_brnch_inst",
     "EventCode": "0x1d0",
-    "BriefDescription": "Retired Fused Instructions. The number of fuse-branch instructions retired per cycle. The number of events logged per cycle can vary from 0-8.",
+    "BriefDescription": "Retired Fused Instructions. The number of fuse-branch instructions retired per cycle. The number of events logged per cycle can vary from 0-8."
   }
 ]
diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
index 6cd408108595..a36f49fb4dbe 100644
--- a/tools/perf/tests/attr/README
+++ b/tools/perf/tests/attr/README
@@ -49,6 +49,7 @@ Following tests are defined (with perf commands):
   perf record --call-graph fp kill              (test-record-graph-fp)
   perf record --group -e cycles,instructions kill (test-record-group)
   perf record -e '{cycles,instructions}' kill   (test-record-group1)
+  perf record -e '{cycles/period=1/,instructions/period=2/}:S' kill (test-record-group2)
   perf record -D kill                           (test-record-no-delay)
   perf record -i kill                           (test-record-no-inherit)
   perf record -n kill                           (test-record-no-samples)
diff --git a/tools/perf/tests/attr/test-record-group2 b/tools/perf/tests/attr/test-record-group2
new file mode 100644
index 000000000000..6b9f8d182ce1
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group2
@@ -0,0 +1,29 @@
+[config]
+command = record
+args    = --no-bpf-event -e '{cycles/period=1234000/,instructions/period=6789000/}:S' kill >/dev/null 2>&1
+ret     = 1
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+config=0|1
+sample_period=1234000
+sample_type=87
+read_format=12
+inherit=0
+freq=0
+
+[event-2:base-record]
+fd=2
+group_fd=1
+config=0|1
+sample_period=6789000
+sample_type=87
+read_format=12
+disabled=0
+inherit=0
+mmap=0
+comm=0
+freq=0
+enable_on_exec=0
+task=0
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index da8ec1e8e064..cc9fbcedb364 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -45,10 +45,13 @@ volatile long the_var;
 #if defined (__x86_64__)
 extern void __test_function(volatile long *ptr);
 asm (
+	".pushsection .text;"
 	".globl __test_function\n"
+	".type __test_function, @function;"
 	"__test_function:\n"
 	"incq (%rdi)\n"
-	"ret\n");
+	"ret\n"
+	".popsection\n");
 #else
 static void __test_function(volatile long *ptr)
 {
diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c
index 23db8acc492d..cd7331aac3bd 100644
--- a/tools/perf/tests/parse-metric.c
+++ b/tools/perf/tests/parse-metric.c
@@ -153,8 +153,10 @@ static int __compute_metric(const char *name, struct value *vals,
 		return -ENOMEM;
 
 	cpus = perf_cpu_map__new("0");
-	if (!cpus)
+	if (!cpus) {
+		evlist__delete(evlist);
 		return -ENOMEM;
+	}
 
 	perf_evlist__set_maps(&evlist->core, cpus, NULL);
 
@@ -163,10 +165,11 @@ static int __compute_metric(const char *name, struct value *vals,
 					     false, false,
 					     &metric_events);
 	if (err)
-		return err;
+		goto out;
 
-	if (perf_evlist__alloc_stats(evlist, false))
-		return -1;
+	err = perf_evlist__alloc_stats(evlist, false);
+	if (err)
+		goto out;
 
 	/* Load the runtime stats with given numbers for events. */
 	runtime_stat__init(&st);
@@ -178,13 +181,14 @@ static int __compute_metric(const char *name, struct value *vals,
 	if (name2 && ratio2)
 		*ratio2 = compute_single(&metric_events, evlist, &st, name2);
 
+out:
 	/* ... clenup. */
 	metricgroup__rblist_exit(&metric_events);
 	runtime_stat__exit(&st);
 	perf_evlist__free_stats(evlist);
 	perf_cpu_map__put(cpus);
 	evlist__delete(evlist);
-	return 0;
+	return err;
 }
 
 static int compute_metric(const char *name, struct value *vals, double *ratio)
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index eb19f9a0bc15..d3517a74d95e 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -274,6 +274,7 @@ static int __test__pmu_event_aliases(char *pmu_name, int *count)
 	int res = 0;
 	bool use_uncore_table;
 	struct pmu_events_map *map = __test_pmu_get_events_map();
+	struct perf_pmu_alias *a, *tmp;
 
 	if (!map)
 		return -1;
@@ -347,6 +348,10 @@ static int __test__pmu_event_aliases(char *pmu_name, int *count)
 			  pmu_name, alias->name);
 	}
 
+	list_for_each_entry_safe(a, tmp, &aliases, list) {
+		list_del(&a->list);
+		perf_pmu_free_alias(a);
+	}
 	free(pmu);
 	return res;
 }
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 5c11fe2b3040..714e6830a758 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -173,6 +173,7 @@ int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused)
 		ret = 0;
 	} while (0);
 
+	perf_pmu__del_formats(&formats);
 	test_format_dir_put(format);
 	return ret;
 }
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e3fa3bf7498a..c0768c61eb43 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -946,6 +946,10 @@ int perf_evlist__create_maps(struct evlist *evlist, struct target *target)
 
 	perf_evlist__set_maps(&evlist->core, cpus, threads);
 
+	/* as evlist now has references, put count here */
+	perf_cpu_map__put(cpus);
+	perf_thread_map__put(threads);
+
 	return 0;
 
 out_delete_threads:
@@ -1273,11 +1277,12 @@ static int perf_evlist__create_syswide_maps(struct evlist *evlist)
 		goto out_put;
 
 	perf_evlist__set_maps(&evlist->core, cpus, threads);
-out:
-	return err;
+
+	perf_thread_map__put(threads);
 out_put:
 	perf_cpu_map__put(cpus);
-	goto out;
+out:
+	return err;
 }
 
 int evlist__open(struct evlist *evlist)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index fd865002cbbd..459b51e90063 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -976,16 +976,20 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 	 * We default some events to have a default interval. But keep
 	 * it a weak assumption overridable by the user.
 	 */
-	if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
-				     opts->user_interval != ULLONG_MAX)) {
+	if (!attr->sample_period) {
 		if (opts->freq) {
-			evsel__set_sample_bit(evsel, PERIOD);
 			attr->freq		= 1;
 			attr->sample_freq	= opts->freq;
 		} else {
 			attr->sample_period = opts->default_interval;
 		}
 	}
+	/*
+	 * If attr->freq was set (here or earlier), ask for period
+	 * to be sampled.
+	 */
+	if (attr->freq)
+		evsel__set_sample_bit(evsel, PERIOD);
 
 	if (opts->no_samples)
 		attr->sample_freq = 0;
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 8831b964288f..ab5030fcfed4 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -85,6 +85,7 @@ static void metric_event_delete(struct rblist *rblist __maybe_unused,
 
 	list_for_each_entry_safe(expr, tmp, &me->head, nd) {
 		free(expr->metric_refs);
+		free(expr->metric_events);
 		free(expr);
 	}
 
@@ -316,6 +317,7 @@ static int metricgroup__setup_events(struct list_head *groups,
 			if (!metric_refs) {
 				ret = -ENOMEM;
 				free(metric_events);
+				free(expr);
 				break;
 			}
 
@@ -530,6 +532,9 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 						continue;
 					strlist__add(me->metrics, s);
 				}
+
+				if (!raw)
+					free(s);
 			}
 			free(omg);
 		}
@@ -667,7 +672,6 @@ static int __add_metric(struct list_head *metric_list,
 		m->has_constraint = metric_no_group || metricgroup__has_constraint(pe);
 		INIT_LIST_HEAD(&m->metric_refs);
 		m->metric_refs_cnt = 0;
-		*mp = m;
 
 		parent = expr_ids__alloc(ids);
 		if (!parent) {
@@ -680,6 +684,7 @@ static int __add_metric(struct list_head *metric_list,
 			free(m);
 			return -ENOMEM;
 		}
+		*mp = m;
 	} else {
 		/*
 		 * We got here for the referenced metric, via the
@@ -714,8 +719,11 @@ static int __add_metric(struct list_head *metric_list,
 	 * all the metric's IDs and add it to the parent context.
 	 */
 	if (expr__find_other(pe->metric_expr, NULL, &m->pctx, runtime) < 0) {
-		expr__ctx_clear(&m->pctx);
-		free(m);
+		if (m->metric_refs_cnt == 0) {
+			expr__ctx_clear(&m->pctx);
+			free(m);
+			*mp = NULL;
+		}
 		return -EINVAL;
 	}
 
@@ -934,7 +942,7 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group,
 
 		ret = add_metric(&list, pe, metric_no_group, &m, NULL, &ids);
 		if (ret)
-			return ret;
+			goto out;
 
 		/*
 		 * Process any possible referenced metrics
@@ -943,12 +951,14 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group,
 		ret = resolve_metric(metric_no_group,
 				     &list, map, &ids);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	/* End of pmu events. */
-	if (!has_match)
-		return -EINVAL;
+	if (!has_match) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	list_for_each_entry(m, &list, nd) {
 		if (events->len > 0)
@@ -963,9 +973,14 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group,
 		}
 	}
 
+out:
+	/*
+	 * add to metric_list so that they can be released
+	 * even if it's failed
+	 */
 	list_splice(&list, metric_list);
 	expr_ids__exit(&ids);
-	return 0;
+	return ret;
 }
 
 static int metricgroup__add_metric_list(const char *list, bool metric_no_group,
@@ -1040,7 +1055,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
 	ret = metricgroup__add_metric_list(str, metric_no_group,
 					   &extra_events, &metric_list, map);
 	if (ret)
-		return ret;
+		goto out;
 	pr_debug("adding %s\n", extra_events.buf);
 	bzero(&parse_error, sizeof(parse_error));
 	ret = __parse_events(perf_evlist, extra_events.buf, &parse_error, fake_pmu);
@@ -1048,11 +1063,11 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
 		parse_events_print_error(&parse_error, extra_events.buf);
 		goto out;
 	}
-	strbuf_release(&extra_events);
 	ret = metricgroup__setup_events(&metric_list, metric_no_merge,
 					perf_evlist, metric_events);
 out:
 	metricgroup__free_metrics(&metric_list);
+	strbuf_release(&extra_events);
 	return ret;
 }
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c4d2394e2b2d..667cbca1547a 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -411,7 +411,7 @@ static int add_event_tool(struct list_head *list, int *idx,
 		return -ENOMEM;
 	evsel->tool_event = tool_event;
 	if (tool_event == PERF_TOOL_DURATION_TIME)
-		evsel->unit = strdup("ns");
+		evsel->unit = "ns";
 	return 0;
 }
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index f1688e1f6ed7..d41caeb35cf6 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -274,7 +274,7 @@ static void perf_pmu_update_alias(struct perf_pmu_alias *old,
 }
 
 /* Delete an alias entry. */
-static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
 {
 	zfree(&newalias->name);
 	zfree(&newalias->desc);
@@ -1354,6 +1354,17 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to)
 		set_bit(b, bits);
 }
 
+void perf_pmu__del_formats(struct list_head *formats)
+{
+	struct perf_pmu_format *fmt, *tmp;
+
+	list_for_each_entry_safe(fmt, tmp, formats, list) {
+		list_del(&fmt->list);
+		free(fmt->name);
+		free(fmt);
+	}
+}
+
 static int sub_non_neg(int a, int b)
 {
 	if (b > a)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 44ccbdbb1c37..a64e9c9ce731 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -94,6 +94,7 @@ int perf_pmu__new_format(struct list_head *list, char *name,
 			 int config, unsigned long *bits);
 void perf_pmu__set_format(unsigned long *bits, long from, long to);
 int perf_pmu__format_parse(char *dir, struct list_head *head);
+void perf_pmu__del_formats(struct list_head *formats);
 
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
@@ -113,6 +114,7 @@ void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu,
 
 struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu);
 bool pmu_uncore_alias_match(const char *pmu_name, const char *name);
+void perf_pmu_free_alias(struct perf_pmu_alias *alias);
 
 int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
 
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index a4cc11592f6b..ea9aa1d7cf50 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -2,6 +2,7 @@
 #include "debug.h"
 #include "evlist.h"
 #include "evsel.h"
+#include "evsel_config.h"
 #include "parse-events.h"
 #include <errno.h>
 #include <limits.h>
@@ -33,11 +34,24 @@ static struct evsel *evsel__read_sampler(struct evsel *evsel, struct evlist *evl
 	return leader;
 }
 
+static u64 evsel__config_term_mask(struct evsel *evsel)
+{
+	struct evsel_config_term *term;
+	struct list_head *config_terms = &evsel->config_terms;
+	u64 term_types = 0;
+
+	list_for_each_entry(term, config_terms, list) {
+		term_types |= 1 << term->type;
+	}
+	return term_types;
+}
+
 static void evsel__config_leader_sampling(struct evsel *evsel, struct evlist *evlist)
 {
 	struct perf_event_attr *attr = &evsel->core.attr;
 	struct evsel *leader = evsel->leader;
 	struct evsel *read_sampler;
+	u64 term_types, freq_mask;
 
 	if (!leader->sample_read)
 		return;
@@ -47,16 +61,20 @@ static void evsel__config_leader_sampling(struct evsel *evsel, struct evlist *ev
 	if (evsel == read_sampler)
 		return;
 
+	term_types = evsel__config_term_mask(evsel);
 	/*
-	 * Disable sampling for all group members other than the leader in
-	 * case the leader 'leads' the sampling, except when the leader is an
-	 * AUX area event, in which case the 2nd event in the group is the one
-	 * that 'leads' the sampling.
+	 * Disable sampling for all group members except those with explicit
+	 * config terms or the leader. In the case of an AUX area event, the 2nd
+	 * event in the group is the one that 'leads' the sampling.
 	 */
-	attr->freq           = 0;
-	attr->sample_freq    = 0;
-	attr->sample_period  = 0;
-	attr->write_backward = 0;
+	freq_mask = (1 << EVSEL__CONFIG_TERM_FREQ) | (1 << EVSEL__CONFIG_TERM_PERIOD);
+	if ((term_types & freq_mask) == 0) {
+		attr->freq           = 0;
+		attr->sample_freq    = 0;
+		attr->sample_period  = 0;
+	}
+	if ((term_types & (1 << EVSEL__CONFIG_TERM_OVERWRITE)) == 0)
+		attr->write_backward = 0;
 
 	/*
 	 * We don't get a sample for slave events, we make them when delivering
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index e1ba6c1b916a..924b54d15d54 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -517,7 +517,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache accesses", ratio);
 }
 
 static void print_l1_icache_misses(struct perf_stat_config *config,
@@ -538,7 +538,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache accesses", ratio);
 }
 
 static void print_dtlb_cache_misses(struct perf_stat_config *config,
@@ -558,7 +558,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache accesses", ratio);
 }
 
 static void print_itlb_cache_misses(struct perf_stat_config *config,
@@ -578,7 +578,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache accesses", ratio);
 }
 
 static void print_ll_cache_misses(struct perf_stat_config *config,
@@ -598,7 +598,7 @@ static void print_ll_cache_misses(struct perf_stat_config *config,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache accesses", ratio);
 }
 
 /*
@@ -853,14 +853,16 @@ static void generic_metric(struct perf_stat_config *config,
 double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st)
 {
 	struct expr_parse_ctx pctx;
-	double ratio;
+	double ratio = 0.0;
 
 	if (prepare_metric(mexp->metric_events, mexp->metric_refs, &pctx, cpu, st) < 0)
-		return 0.;
+		goto out;
 
 	if (expr__parse(&ratio, &pctx, mexp->metric_expr, 1))
-		return 0.;
+		ratio = 0.0;
 
+out:
+	expr__ctx_clear(&pctx);
 	return ratio;
 }
 
@@ -918,7 +920,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
 			print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0);
 	} else if (
 		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
@@ -928,7 +930,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
 			print_l1_icache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0);
 	} else if (
 		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
@@ -938,7 +940,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
 			print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0);
 	} else if (
 		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
@@ -948,7 +950,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
 			print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0);
 	} else if (
 		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
@@ -958,7 +960,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
 			print_ll_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0);
 	} else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);