perf annotate: Cache debuginfo for data type profiling

In find_data_type(), it creates and deletes a debug info whenver it
tries to find data type for a sample.  This is inefficient and it most
likely accesses the same binary again and again.

Let's add a single entry cache the debug info structure for the last DSO.
Depending on sample data, it usually gives me 2~3x (and sometimes more)
speed ups.

Note that this will introduce a little difference in the output due to
the order of checking stack operations.  It used to check the stack ops
before checking the availability of debug info but I moved it after the
symbol check.  So it'll report stack operations in DSOs without debug
info as unknown.  But I think it's ok and better to have the checking
near the caching logic.

Committer testing:

  root@x1:~# perf mem record -a sleep 5s
  root@x1:~# perf evlist
  cpu_atom/mem-loads,ldlat=30/P
  cpu_atom/mem-stores/P
  dummy:u
  root@x1:~# diff -u before after
  --- before	2024-08-08 09:33:53.880780784 -0300
  +++ after	2024-08-08 09:35:13.917325041 -0300
  @@ -81,8 +81,8 @@
   # Overhead  Data Type
   # ........  .........
   #
  -    55.43%  (unknown)
  -    11.61%  (stack operation)
  +    55.56%  (unknown)
  +    11.48%  (stack operation)
        4.93%  struct pcpu_hot
        3.26%  unsigned int
        2.48%  struct

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: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240805234648.1453689-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/annotate-data.c

@@ -1345,16 +1345,9 @@ out:
  */
 struct annotated_data_type *find_data_type(struct data_loc_info *dloc)
 {
-	struct annotated_data_type *result = NULL;
 	struct dso *dso = map__dso(dloc->ms->map);
 	Dwarf_Die type_die;
 
-	dloc->di = debuginfo__new(dso__long_name(dso));
-	if (dloc->di == NULL) {
-		pr_debug_dtp("cannot get the debug info\n");
-		return NULL;
-	}
-
 	/*
 	 * The type offset is the same as instruction offset by default.
 	 * But when finding a global variable, the offset won't be valid.
@@ -1364,13 +1357,9 @@ struct annotated_data_type *find_data_type(struct data_loc_info *dloc)
 	dloc->fbreg = -1;
 
 	if (find_data_type_die(dloc, &type_die) < 0)
-		goto out;
+		return NULL;
 
-	result = dso__findnew_data_type(dso, &type_die);
-
-out:
-	debuginfo__delete(dloc->di);
-	return result;
+	return dso__findnew_data_type(dso, &type_die);
 }
 
 static int alloc_data_type_histograms(struct annotated_data_type *adt, int nr_entries)

tools/perf/util/annotate-data.h

@@ -123,9 +123,9 @@ struct data_loc_info {
 	u64 var_addr;
 	u8 cpumode;
 	struct annotated_op_loc *op;
+	struct debuginfo *di;
 
 	/* These are used internally */
-	struct debuginfo *di;
 	int fbreg;
 	bool fb_cfa;
 

tools/perf/util/annotate.c

@@ -25,6 +25,7 @@
 #include "srcline.h"
 #include "units.h"
 #include "debug.h"
+#include "debuginfo.h"
 #include "annotate.h"
 #include "annotate-data.h"
 #include "evsel.h"
@@ -2333,6 +2334,20 @@ u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset,
 	return map__rip_2objdump(ms->map, addr);
 }
 
+static struct debuginfo_cache {
+	struct dso *dso;
+	struct debuginfo *dbg;
+} di_cache;
+
+void debuginfo_cache__delete(void)
+{
+	dso__put(di_cache.dso);
+	di_cache.dso = NULL;
+
+	debuginfo__delete(di_cache.dbg);
+	di_cache.dbg = NULL;
+}
+
 /**
  * hist_entry__get_data_type - find data type for given hist entry
  * @he: hist entry
@@ -2367,6 +2382,27 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 		return NULL;
 	}
 
+	/*
+	 * di_cache holds a pair of values, but code below assumes
+	 * di_cache.dso can be compared/updated and di_cache.dbg can be
+	 * read/updated independently from each other. That assumption only
+	 * holds in single threaded code.
+	 */
+	assert(perf_singlethreaded);
+
+	if (map__dso(ms->map) != di_cache.dso) {
+		dso__put(di_cache.dso);
+		di_cache.dso = dso__get(map__dso(ms->map));
+
+		debuginfo__delete(di_cache.dbg);
+		di_cache.dbg = debuginfo__new(dso__long_name(di_cache.dso));
+	}
+
+	if (di_cache.dbg == NULL) {
+		ann_data_stat.no_dbginfo++;
+		return NULL;
+	}
+
 	/* Make sure it has the disasm of the function */
 	if (symbol__annotate(ms, evsel, &arch) < 0) {
 		ann_data_stat.no_insn++;
@@ -2411,6 +2447,7 @@ retry:
 			.ip = ms->sym->start + dl->al.offset,
 			.cpumode = he->cpumode,
 			.op = op_loc,
+			.di = di_cache.dbg,
 		};
 
 		if (!op_loc->mem_ref && op_loc->segment == INSN_SEG_NONE)

tools/perf/util/annotate.h

@@ -543,4 +543,6 @@ struct annotated_basic_block {
 int annotate_get_basic_blocks(struct symbol *sym, s64 src, s64 dst,
 			      struct list_head *head);
 
+void debuginfo_cache__delete(void);
+
 #endif	/* __PERF_ANNOTATE_H */

tools/perf/util/session.c

@@ -36,6 +36,7 @@
 #include "util.h"
 #include "arch/common.h"
 #include "units.h"
+#include "annotate.h"
 #include <internal/lib.h>
 
 #ifdef HAVE_ZSTD_SUPPORT
@@ -304,6 +305,7 @@ void perf_session__delete(struct perf_session *session)
 		return;
 	auxtrace__free(session);
 	auxtrace_index__free(&session->auxtrace_index);
+	debuginfo_cache__delete();
 	perf_session__destroy_kernel_maps(session);
 	perf_decomp__release_events(session->decomp_data.decomp);
 	perf_env__exit(&session->header.env);