[PATCH v3 3/4] tools/perf: Correctly calculate sample period for inherited SAMPLE_READ values

[Ben Gainey]

Sample period calculation is updated to take into account the fact that
the stream-id for events with inherit+inherit_stat+PERF_SAMPLE_READ
is now unique per thread, rather than globally unique.

perf_sample_id is modified to support tracking per-stream+per-thread
values, along with the existing global per-stream values. In the
per-thread case, values are stored in a hash by tid. 

deliver_sample_value is modified to correctly locate the previous
sample storage based on the attribute, stream id and thread id.

Signed-off-by: Ben Gainey <ben.gainey@xxxxxxx>
---
 tools/lib/perf/evsel.c                  | 41 ++++++++++++++++++++++
 tools/lib/perf/include/internal/evsel.h | 46 +++++++++++++++++++++++--
 tools/perf/util/session.c               | 11 ++++--
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index dd60ee0557d8..2bdba78cc43e 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -5,6 +5,7 @@
 #include <perf/evsel.h>
 #include <perf/cpumap.h>
 #include <perf/threadmap.h>
+#include <linux/hash.h>
 #include <linux/list.h>
 #include <internal/evsel.h>
 #include <linux/zalloc.h>
@@ -23,6 +24,7 @@ void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr,
 		      int idx)
 {
 	INIT_LIST_HEAD(&evsel->node);
+	INIT_LIST_HEAD(&evsel->period_per_thread_periods);
 	evsel->attr = *attr;
 	evsel->idx  = idx;
 	evsel->leader = evsel;
@@ -531,10 +533,17 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 void perf_evsel__free_id(struct perf_evsel *evsel)
 {
+	struct perf_sample_id_period *pos, *n;
+
 	xyarray__delete(evsel->sample_id);
 	evsel->sample_id = NULL;
 	zfree(&evsel->id);
 	evsel->ids = 0;
+
+	perf_evsel_for_each_per_thread_period_safe(evsel, n, pos) {
+		list_del_init(&pos->node);
+		zfree(pos);
+	}
 }
 
 bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel)
@@ -544,6 +553,38 @@ bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel)
 		&& evsel->attr.inherit_stat;
 }
 
+u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 tid)
+{
+	struct hlist_head *head;
+	struct perf_sample_id_period *res;
+	int hash;
+
+	if (!sid->period_per_thread)
+		return &sid->period;
+
+	hash = hash_32(tid, PERF_SAMPLE_ID__HLIST_BITS);
+	head = &sid->periods[hash];
+
+	hlist_for_each_entry(res, head, hnode)
+		if (res->tid == tid)
+			return &res->period;
+
+	if (sid->evsel == NULL)
+		return NULL;
+
+	res = zalloc(sizeof(struct perf_sample_id_period));
+	if (res == NULL)
+		return NULL;
+
+	INIT_LIST_HEAD(&res->node);
+	res->tid = tid;
+
+	list_add_tail(&res->node, &sid->evsel->period_per_thread_periods);
+	hlist_add_head(&res->hnode, &sid->periods[hash]);
+
+	return &res->period;
+}
+
 void perf_counts_values__scale(struct perf_counts_values *count,
 			       bool scale, __s8 *pscaled)
 {
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index 8dd58149986c..52ec2edf628b 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -11,6 +11,32 @@
 struct perf_thread_map;
 struct xyarray;
 
+/**
+ * The per-thread accumulated period storage node.
+ */
+struct perf_sample_id_period {
+	struct list_head	node;
+	struct hlist_node	hnode;
+	/* The thread that the values belongs to */
+	u32			tid;
+	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
+	u64			period;
+};
+
+/**
+ * perf_evsel_for_each_per_thread_period_safe - safely iterate thru all the
+ * period_per_thread_periods
+ * @evlist:perf_evsel instance to iterate
+ * @item: struct perf_sample_id_period iterator
+ * @tmp: struct perf_sample_id_period temp iterator
+ */
+#define perf_evsel_for_each_per_thread_period_safe(evsel, tmp, item) \
+	list_for_each_entry_safe(item, tmp, &(evsel)->period_per_thread_periods, node)
+
+
+#define PERF_SAMPLE_ID__HLIST_BITS 4
+#define PERF_SAMPLE_ID__HLIST_SIZE (1 << PERF_SAMPLE_ID__HLIST_BITS)
+
 /*
  * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
  * more than one entry in the evlist.
@@ -19,6 +45,7 @@ struct perf_sample_id {
 	struct hlist_node	 node;
 	u64			 id;
 	struct perf_evsel	*evsel;
+
        /*
 	* 'idx' will be used for AUX area sampling. A sample will have AUX area
 	* data that will be queued for decoding, where there are separate
@@ -34,8 +61,18 @@ struct perf_sample_id {
 	pid_t			 machine_pid;
 	struct perf_cpu		 vcpu;
 
-	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
-	u64			 period;
+	union {
+		/*
+		 * Holds total ID period value for PERF_SAMPLE_READ processing
+		 * (when period is not per-thread).
+		 */
+		u64			period;
+		/*
+		 * Holds total ID period value for PERF_SAMPLE_READ processing
+		 * (when period is per-thread).
+		 */
+		struct hlist_head	periods[PERF_SAMPLE_ID__HLIST_SIZE];
+	};
 
 	/*
 	 * When inherit+inherit_stat is combined with PERF_SAMPLE_READ, the
@@ -65,6 +102,9 @@ struct perf_evsel {
 	u32			 ids;
 	struct perf_evsel	*leader;
 
+	/* Where period_per_thread is true, stores the per-thread values */
+	struct list_head	period_per_thread_periods;
+
 	/* parse modifier helper */
 	int			 nr_members;
 	/*
@@ -97,4 +137,6 @@ void perf_evsel__free_id(struct perf_evsel *evsel);
 
 bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel);
 
+u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 tid);
+
 #endif /* __LIBPERF_INTERNAL_EVSEL_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 199d3e8df315..2d6a92374847 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1478,14 +1478,19 @@ static int deliver_sample_value(struct evlist *evlist,
 {
 	struct perf_sample_id *sid = evlist__id2sid(evlist, v->id);
 	struct evsel *evsel;
+	u64 *storage = NULL;
 
 	if (sid) {
+		storage  = perf_sample_id__get_period_storage(sid, sample->tid);
+	}
+
+	if (storage) {
 		sample->id     = v->id;
-		sample->period = v->value - sid->period;
-		sid->period    = v->value;
+		sample->period = v->value - *storage;
+		*storage       = v->value;
 	}
 
-	if (!sid || sid->evsel == NULL) {
+	if (!storage || sid->evsel == NULL) {
 		++evlist->stats.nr_unknown_id;
 		return 0;
 	}
-- 
2.44.0