perf annotate-data: Update sample histogram for type

The annotated_data_type__update_samples() to get histogram for data type
access.

It'll be called by perf annotate to show which fields in the data type
are accessed frequently.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-12-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/annotate-data.c

@@ -13,6 +13,8 @@
 #include "debuginfo.h"
 #include "debug.h"
 #include "dso.h"
+#include "evsel.h"
+#include "evlist.h"
 #include "map.h"
 #include "map_symbol.h"
 #include "strbuf.h"
@@ -302,6 +304,44 @@ out:
 	return result;
 }
 
+static int alloc_data_type_histograms(struct annotated_data_type *adt, int nr_entries)
+{
+	int i;
+	size_t sz = sizeof(struct type_hist);
+
+	sz += sizeof(struct type_hist_entry) * adt->self.size;
+
+	/* Allocate a table of pointers for each event */
+	adt->nr_histograms = nr_entries;
+	adt->histograms = calloc(nr_entries, sizeof(*adt->histograms));
+	if (adt->histograms == NULL)
+		return -ENOMEM;
+
+	/*
+	 * Each histogram is allocated for the whole size of the type.
+	 * TODO: Probably we can move the histogram to members.
+	 */
+	for (i = 0; i < nr_entries; i++) {
+		adt->histograms[i] = zalloc(sz);
+		if (adt->histograms[i] == NULL)
+			goto err;
+	}
+	return 0;
+
+err:
+	while (--i >= 0)
+		free(adt->histograms[i]);
+	free(adt->histograms);
+	return -ENOMEM;
+}
+
+static void delete_data_type_histograms(struct annotated_data_type *adt)
+{
+	for (int i = 0; i < adt->nr_histograms; i++)
+		free(adt->histograms[i]);
+	free(adt->histograms);
+}
+
 void annotated_data_type__tree_delete(struct rb_root *root)
 {
 	struct annotated_data_type *pos;
@@ -312,7 +352,48 @@ void annotated_data_type__tree_delete(struct rb_root *root)
 		rb_erase(node, root);
 		pos = rb_entry(node, struct annotated_data_type, node);
 		delete_members(&pos->self);
+		delete_data_type_histograms(pos);
 		free(pos->self.type_name);
 		free(pos);
 	}
 }
+
+/**
+ * annotated_data_type__update_samples - Update histogram
+ * @adt: Data type to update
+ * @evsel: Event to update
+ * @offset: Offset in the type
+ * @nr_samples: Number of samples at this offset
+ * @period: Event count at this offset
+ *
+ * This function updates type histogram at @ofs for @evsel.  Samples are
+ * aggregated before calling this function so it can be called with more
+ * than one samples at a certain offset.
+ */
+int annotated_data_type__update_samples(struct annotated_data_type *adt,
+					struct evsel *evsel, int offset,
+					int nr_samples, u64 period)
+{
+	struct type_hist *h;
+
+	if (adt == NULL)
+		return 0;
+
+	if (adt->histograms == NULL) {
+		int nr = evsel->evlist->core.nr_entries;
+
+		if (alloc_data_type_histograms(adt, nr) < 0)
+			return -1;
+	}
+
+	if (offset < 0 || offset >= adt->self.size)
+		return -1;
+
+	h = adt->histograms[evsel->core.idx];
+
+	h->nr_samples += nr_samples;
+	h->addr[offset].nr_samples += nr_samples;
+	h->period += period;
+	h->addr[offset].period += period;
+	return 0;
+}

tools/perf/util/annotate-data.h

@@ -7,6 +7,7 @@
 #include <linux/rbtree.h>
 #include <linux/types.h>
 
+struct evsel;
 struct map_symbol;
 
 /**
@@ -29,16 +30,42 @@ struct annotated_member {
 	int size;
 };
 
+/**
+ * struct type_hist_entry - Histogram entry per offset
+ * @nr_samples: Number of samples
+ * @period: Count of event
+ */
+struct type_hist_entry {
+	int nr_samples;
+	u64 period;
+};
+
+/**
+ * struct type_hist - Type histogram for each event
+ * @nr_samples: Total number of samples in this data type
+ * @period: Total count of the event in this data type
+ * @offset: Array of histogram entry
+ */
+struct type_hist {
+	u64			nr_samples;
+	u64			period;
+	struct type_hist_entry	addr[];
+};
+
 /**
  * struct annotated_data_type - Data type to profile
  * @node: RB-tree node for dso->type_tree
  * @self: Actual type information
+ * @nr_histogram: Number of histogram entries
+ * @histograms: An array of pointers to histograms
  *
  * This represents a data type accessed by samples in the profile data.
  */
 struct annotated_data_type {
 	struct rb_node node;
 	struct annotated_member self;
+	int nr_histograms;
+	struct type_hist **histograms;
 };
 
 extern struct annotated_data_type unknown_type;
@@ -49,6 +76,11 @@ extern struct annotated_data_type unknown_type;
 struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
 					   int reg, int offset);
 
+/* Update type access histogram at the given offset */
+int annotated_data_type__update_samples(struct annotated_data_type *adt,
+					struct evsel *evsel, int offset,
+					int nr_samples, u64 period);
+
 /* Release all data type information in the tree */
 void annotated_data_type__tree_delete(struct rb_root *root);
 
@@ -61,6 +93,16 @@ find_data_type(struct map_symbol *ms __maybe_unused, u64 ip __maybe_unused,
 	return NULL;
 }
 
+static inline int
+annotated_data_type__update_samples(struct annotated_data_type *adt __maybe_unused,
+				    struct evsel *evsel __maybe_unused,
+				    int offset __maybe_unused,
+				    int nr_samples __maybe_unused,
+				    u64 period __maybe_unused)
+{
+	return -1;
+}
+
 static inline void annotated_data_type__tree_delete(struct rb_root *root __maybe_unused)
 {
 }

tools/perf/util/annotate.c

@@ -3679,6 +3679,7 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 	struct disasm_line *dl;
 	struct annotated_insn_loc loc;
 	struct annotated_op_loc *op_loc;
+	struct annotated_data_type *mem_type;
 	u64 ip = he->ip;
 	int i;
 
@@ -3709,7 +3710,13 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 		if (!op_loc->mem_ref)
 			continue;
 
-		return find_data_type(ms, ip, op_loc->reg, op_loc->offset);
+		mem_type = find_data_type(ms, ip, op_loc->reg, op_loc->offset);
+
+		annotated_data_type__update_samples(mem_type, evsel,
+						    op_loc->offset,
+						    he->stat.nr_events,
+						    he->stat.period);
+		return mem_type;
 	}
 	return NULL;
 }