perf annotate: Add --data-type option

Support data type annotation with new --data-type option.  It internally
uses type sort key to collect sample histogram for the type and display
every members like below.

  $ perf annotate --data-type
  ...
  Annotate type: 'struct cfs_rq' in [kernel.kallsyms] (13 samples):
  ============================================================================
      samples     offset       size  field
           13          0        640  struct cfs_rq         {
            2          0         16      struct load_weight       load {
            2          0          8          unsigned long        weight;
            0          8          4          u32  inv_weight;
                                         };
            0         16          8      unsigned long    runnable_weight;
            0         24          4      unsigned int     nr_running;
            1         28          4      unsigned int     h_nr_running;
  ...

For simplicity it prints the number of samples per field for now.
But it should be easy to show the overhead percentage instead.

The number at the outer struct is a sum of the numbers of the inner
members.  For example, struct cfs_rq got total 13 samples, and 2 came
from the load (struct load_weight) and 1 from h_nr_running.  Similarly,
the struct load_weight got total 2 samples and they all came from the
weight field.

I've added two new flags in the symbol_conf for this.  The
annotate_data_member is to get the members of the type.  This is also
needed for perf report with typeoff sort key.  The annotate_data_sample
is to update sample stats for each offset and used only in annotate.

Currently it only support stdio output mode, TUI support can be added
later.

Committer testing:

With the perf.data from the previous csets, a very simple, short
duration one:

  # perf annotate --data-type
  Annotate type: 'struct list_head' in [kernel.kallsyms] (1 samples):
  ============================================================================
      samples     offset       size  field
            1          0         16  struct list_head      {
            0          0          8      struct list_head*        next;
            1          8          8      struct list_head*        prev;
                                     };

  Annotate type: 'char' in [kernel.kallsyms] (1 samples):
  ============================================================================
      samples     offset       size  field
            1          0          1  char ;

  #
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
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/20231213001323.718046-15-namhyung@kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-annotate.txt

@@ -155,6 +155,14 @@ include::itrace.txt[]
 	stdio or stdio2 (Default: 0).  Note that this is about selection of
 	functions to display, not about lines within the function.
 
+--data-type[=TYPE_NAME]::
+	Display data type annotation instead of code.  It infers data type of
+	samples (if they are memory accessing instructions) using DWARF debug
+	information.  It can take an optional argument of data type name.  In
+	that case it'd show annotation for the type only, otherwise it'd show
+	all data types it finds.
+
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]

tools/perf/builtin-annotate.c

@@ -20,6 +20,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/annotate.h"
+#include "util/annotate-data.h"
 #include "util/event.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-events.h"
@@ -55,9 +56,11 @@ struct perf_annotate {
 	bool	   skip_missing;
 	bool	   has_br_stack;
 	bool	   group_set;
+	bool	   data_type;
 	float	   min_percent;
 	const char *sym_hist_filter;
 	const char *cpu_list;
+	const char *target_data_type;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
@@ -322,6 +325,32 @@ static int hist_entry__tty_annotate(struct hist_entry *he,
 	return symbol__tty_annotate2(&he->ms, evsel);
 }
 
+static void print_annotated_data_type(struct annotated_data_type *mem_type,
+				      struct annotated_member *member,
+				      struct evsel *evsel, int indent)
+{
+	struct annotated_member *child;
+	struct type_hist *h = mem_type->histograms[evsel->core.idx];
+	int i, samples = 0;
+
+	for (i = 0; i < member->size; i++)
+		samples += h->addr[member->offset + i].nr_samples;
+
+	printf(" %10d %10d %10d  %*s%s\t%s",
+	       samples, member->offset, member->size, indent, "", member->type_name,
+	       member->var_name ?: "");
+
+	if (!list_empty(&member->children))
+		printf(" {\n");
+
+	list_for_each_entry(child, &member->children, node)
+		print_annotated_data_type(mem_type, child, evsel, indent + 4);
+
+	if (!list_empty(&member->children))
+		printf("%*s}", 35 + indent, "");
+	printf(";\n");
+}
+
 static void hists__find_annotations(struct hists *hists,
 				    struct evsel *evsel,
 				    struct perf_annotate *ann)
@@ -361,6 +390,40 @@ static void hists__find_annotations(struct hists *hists,
 			continue;
 		}
 
+		if (ann->data_type) {
+			struct dso *dso = map__dso(he->ms.map);
+
+			/* skip unknown type */
+			if (he->mem_type->histograms == NULL)
+				goto find_next;
+
+			if (ann->target_data_type) {
+				const char *type_name = he->mem_type->self.type_name;
+
+				/* skip 'struct ' prefix in the type name */
+				if (strncmp(ann->target_data_type, "struct ", 7) &&
+				    !strncmp(type_name, "struct ", 7))
+					type_name += 7;
+
+				/* skip 'union ' prefix in the type name */
+				if (strncmp(ann->target_data_type, "union ", 6) &&
+				    !strncmp(type_name, "union ", 6))
+					type_name += 6;
+
+				if (strcmp(ann->target_data_type, type_name))
+					goto find_next;
+			}
+
+			printf("Annotate type: '%s' in %s (%d samples):\n",
+				he->mem_type->self.type_name, dso->name, he->stat.nr_events);
+			printf("============================================================================\n");
+			printf(" %10s %10s %10s  %s\n", "samples", "offset", "size", "field");
+
+			print_annotated_data_type(he->mem_type, &he->mem_type->self, evsel, 0);
+			printf("\n");
+			goto find_next;
+		}
+
 		if (use_browser == 2) {
 			int ret;
 			int (*annotate)(struct hist_entry *he,
@@ -496,6 +559,17 @@ static int parse_percent_limit(const struct option *opt, const char *str,
 	return 0;
 }
 
+static int parse_data_type(const struct option *opt, const char *str, int unset)
+{
+	struct perf_annotate *ann = opt->value;
+
+	ann->data_type = !unset;
+	if (str)
+		ann->target_data_type = strdup(str);
+
+	return 0;
+}
+
 static const char * const annotate_usage[] = {
 	"perf annotate [<options>]",
 	NULL
@@ -607,6 +681,9 @@ int cmd_annotate(int argc, const char **argv)
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
 			    "Instruction Tracing options\n" ITRACE_HELP,
 			    itrace_parse_synth_opts),
+	OPT_CALLBACK_OPTARG(0, "data-type", &annotate, NULL, "name",
+			    "Show data type annotate for the memory accesses",
+			    parse_data_type),
 
 	OPT_END()
 	};
@@ -661,6 +738,13 @@ int cmd_annotate(int argc, const char **argv)
 	}
 #endif
 
+#ifndef HAVE_DWARF_GETLOCATIONS_SUPPORT
+	if (annotate.data_type) {
+		pr_err("Error: Data type profiling is disabled due to missing DWARF support\n");
+		return -ENOTSUP;
+	}
+#endif
+
 	ret = symbol__validate_sym_arguments();
 	if (ret)
 		return ret;
@@ -703,6 +787,14 @@ int cmd_annotate(int argc, const char **argv)
 		use_browser = 2;
 #endif
 
+	/* FIXME: only support stdio for now */
+	if (annotate.data_type) {
+		use_browser = 0;
+		annotate_opts.annotate_src = false;
+		symbol_conf.annotate_data_member = true;
+		symbol_conf.annotate_data_sample = true;
+	}
+
 	setup_browser(true);
 
 	/*
@@ -710,7 +802,10 @@ int cmd_annotate(int argc, const char **argv)
 	 * symbol, we do not care about the processes in annotate,
 	 * set sort order to avoid repeated output.
 	 */
-	sort_order = "dso,symbol";
+	if (annotate.data_type)
+		sort_order = "dso,type";
+	else
+		sort_order = "dso,symbol";
 
 	/*
 	 * Set SORT_MODE__BRANCH so that annotate display IPC/Cycle

tools/perf/util/annotate-data.c

@@ -19,6 +19,7 @@
 #include "map_symbol.h"
 #include "strbuf.h"
 #include "symbol.h"
+#include "symbol_conf.h"
 
 /*
  * Compare type name and size to maintain them in a tree.
@@ -158,11 +159,8 @@ static struct annotated_data_type *dso__findnew_data_type(struct dso *dso,
 	result->self.size = size;
 	INIT_LIST_HEAD(&result->self.children);
 
-	/*
-	 * Fill member info unconditionally for now,
-	 * later perf annotate would need it.
-	 */
-	add_member_types(result, type_die);
+	if (symbol_conf.annotate_data_member)
+		add_member_types(result, type_die);
 
 	rb_add(&result->node, &dso->data_types, data_type_less);
 	return result;

tools/perf/util/annotate.c

@@ -3712,10 +3712,12 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 
 		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);
+		if (symbol_conf.annotate_data_sample) {
+			annotated_data_type__update_samples(mem_type, evsel,
+							    op_loc->offset,
+							    he->stat.nr_events,
+							    he->stat.period);
+		}
 		he->mem_type_off = op_loc->offset;
 		return mem_type;
 	}

tools/perf/util/sort.c

@@ -3401,6 +3401,8 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 			list->thread = 1;
 		} else if (sd->entry == &sort_comm) {
 			list->comm = 1;
+		} else if (sd->entry == &sort_type_offset) {
+			symbol_conf.annotate_data_member = true;
 		}
 
 		return __sort_dimension__add(sd, list, level);

tools/perf/util/symbol_conf.h

@@ -44,7 +44,9 @@ struct symbol_conf {
 			buildid_mmap2,
 			guest_code,
 			lazy_load_kernel_maps,
-			keep_exited_threads;
+			keep_exited_threads,
+			annotate_data_member,
+			annotate_data_sample;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,