[PATCH v2 11/16] perf pmu: Probe memory profiling events and sample formats

[Ian Rogers]

Extend perf_pmu__probe() with try_open_mem_evlist() and
probe_mem_events() to test which perf_mem_events types (such as
ldlat-loads and ldlat-stores) can be opened on the PMU and which
additional memory sample formats (PERF_SAMPLE_WEIGHT,
PERF_SAMPLE_WEIGHT_STRUCT, PERF_SAMPLE_PHYS_ADDR,
PERF_SAMPLE_DATA_PAGE_SIZE, PERF_SAMPLE_TRANSACTION) are supported with
them.

Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 tools/perf/util/pmu.c | 139 ++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/pmu.h |   7 +++
 2 files changed, 146 insertions(+)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 80159358318e..45c557c85c5e 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -3652,6 +3652,142 @@ static void probe_pmu_regs_one(const struct perf_pmu *pmu,
 		*out_pred_precise_mask = pred_precise_mask;
 }
 
+static bool try_open_mem_evlist(struct evlist *evlist,
+				const struct perf_event_attr *base_attr,
+				pid_t pid, int cpu, unsigned long flags,
+				int precise_ip, u64 sample_type)
+{
+	int fds[16];
+	size_t nr_fds = 0;
+	int leader_fd = -1;
+	struct evsel *evsel;
+	bool ok = true;
+
+	evlist__for_each_entry(evlist, evsel) {
+		struct perf_event_attr attr = evsel->core.attr;
+		int fd;
+
+		if (nr_fds >= ARRAY_SIZE(fds)) {
+			ok = false;
+			break;
+		}
+
+		attr.disabled = (leader_fd < 0) ? 1 : 0;
+		attr.sample_period = attr.sample_period ?: 10000;
+		attr.sample_type = sample_type;
+		attr.exclude_user = base_attr->exclude_user;
+		attr.exclude_kernel = base_attr->exclude_kernel;
+		attr.exclude_hv = base_attr->exclude_hv;
+		attr.exclude_idle = base_attr->exclude_idle;
+		attr.exclude_host = base_attr->exclude_host;
+		attr.exclude_guest = base_attr->exclude_guest;
+		if (evsel->precise_max || precise_ip > 0)
+			attr.precise_ip = precise_ip;
+
+		fd = sys_perf_event_open(&attr, pid, cpu, leader_fd, flags);
+		if (fd < 0) {
+			ok = false;
+			break;
+		}
+		if (leader_fd < 0)
+			leader_fd = fd;
+		fds[nr_fds++] = fd;
+	}
+
+	for (size_t i = nr_fds; i > 0; i--)
+		close(fds[i - 1]);
+
+	return ok && nr_fds > 0;
+}
+
+/*
+ * Probe which perf_mem_events types (e.g. ldlat-loads, ldlat-stores) and
+ * additional memory sample formats can be opened on @pmu.
+ */
+static void probe_mem_events(struct perf_pmu *pmu,
+			     const struct perf_event_attr *base_attr,
+			     pid_t pid, int cpu, unsigned long flags)
+{
+	static const u64 extra_mem_stypes[] = {
+		PERF_SAMPLE_WEIGHT,
+		PERF_SAMPLE_WEIGHT_STRUCT,
+		PERF_SAMPLE_PHYS_ADDR,
+		PERF_SAMPLE_DATA_PAGE_SIZE,
+		PERF_SAMPLE_TRANSACTION,
+	};
+
+	if (!pmu->mem_events)
+		return;
+
+	perf_pmu__mem_events_init_pmu(pmu);
+
+	for (int j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		struct perf_mem_event *e = perf_pmu__mem_events_ptr(pmu, j);
+		const char *s;
+		char buf[256];
+		struct evlist *evlist;
+		struct parse_events_error err;
+		struct evsel *first;
+		int max_p, min_p, working_p = -1;
+		u64 base_stype = PERF_SAMPLE_IP | PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC;
+		int ret;
+
+		if (!e || !e->tag || !e->supported)
+			continue;
+
+		s = perf_pmu__mem_events_name(pmu, j, buf, sizeof(buf));
+		if (!s)
+			continue;
+
+		evlist = evlist__new();
+		if (!evlist)
+			continue;
+
+		parse_events_error__init(&err);
+		ret = __parse_events(evlist, s, /*pmu_filter=*/NULL,
+				     /*cputype_filter=*/false, &err, /*fake_pmu=*/false,
+				     /*warn_if_reordered=*/false, /*fake_tp=*/false);
+		parse_events_error__exit(&err);
+		if (ret || evlist__empty(evlist)) {
+			evlist__put(evlist);
+			continue;
+		}
+
+		first = evlist__first(evlist);
+		if (first->precise_max) {
+			max_p = pmu->probed.max_precise > 0 ? pmu->probed.max_precise : 3;
+			min_p = 1;
+		} else {
+			max_p = first->core.attr.precise_ip;
+			min_p = first->core.attr.precise_ip;
+		}
+
+		for (int p = max_p; p >= min_p; p--) {
+			if (try_open_mem_evlist(evlist, base_attr, pid, cpu,
+						flags, p, base_stype)) {
+				working_p = p;
+				break;
+			}
+		}
+
+		if (working_p >= 0) {
+			pmu->probed.mem_events_mask |= (1u << j);
+			pmu->probed.mem_sample_types |= PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC;
+
+			for (size_t k = 0; k < ARRAY_SIZE(extra_mem_stypes); k++) {
+				u64 st = base_stype | extra_mem_stypes[k];
+
+				if (try_open_mem_evlist(evlist, base_attr, pid, cpu,
+							flags, working_p, st)) {
+					pmu->probed.mem_sample_types |= extra_mem_stypes[k];
+				}
+			}
+		}
+
+		evlist__put(evlist);
+	}
+}
+
 /*
  * Pack @value into the perf_event_attr config field named by the sysfs format
  * @name of @pmu, e.g. "rdpmc" defined as "config1:1". Returns false if the
@@ -4073,6 +4209,9 @@ static void __perf_pmu__probe(struct perf_pmu *pmu, int pmu_cpu)
 				   &pmu->probed.intr_pred_precise_mask);
 	}
 
+	/* 3c. Memory event types and memory sample formats */
+	probe_mem_events(pmu, &base_attr, pid, cpu, flags);
+
 	/* 4. Privilege / exclusion modifiers */
 	pmu->probed.exclude_user =
 		test_exclude_flag(&base_attr, pid, cpu, flags, PROBE_EXCLUDE_USER);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 21c4b1a4b608..ee56570cac00 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -304,11 +304,18 @@ struct perf_pmu {
 		int user_regs_abi;
 		/** @probed.intr_regs_abi: ABI flags for intr_regs_mask. */
 		int intr_regs_abi;
+		/** @probed.mem_events_mask: Bitmask of memory event types verified by probing. */
+		unsigned int mem_events_mask;
 		/**
 		 * @probed.sample_types: Bitmask of supported
 		 * enum perf_event_sample_format flags.
 		 */
 		u64 sample_types;
+		/**
+		 * @probed.mem_sample_types: Bitmask of memory sample formats
+		 * verified on mem_events.
+		 */
+		u64 mem_sample_types;
 		/** @probed.user_regs_mask: Bitmask of supported sample_regs_user registers. */
 		u64 user_regs_mask;
 		/** @probed.intr_regs_mask: Bitmask of supported sample_regs_intr registers. */
-- 
2.56.1.703.gf848ed807c-goog