Received-SPF: pass (google.com: domain of linux-kernel+bounces-165995-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>,
	Ian Rogers <irogers@google.com>,
	Kan Liang <kan.liang@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>,
	LKML <linux-kernel@vger.kernel.org>,
	linux-perf-users@vger.kernel.org
Subject: [PATCH 2/6] perf annotate-data: Collect global variables in advance
Date: Wed,  1 May 2024 23:00:07 -0700
Message-ID: <20240502060011.1838090-3-namhyung@kernel.org>
In-Reply-To: <20240502060011.1838090-1-namhyung@kernel.org>
References: <20240502060011.1838090-1-namhyung@kernel.org>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

Currently it looks up global variables from the current CU using address
and name.  But it sometimes fails to find a variable as the variable can
come from a different CU - but it's still strange it failed to find a
declaration for some reason.

Anyway, it can collect all global variables from all CU once and then
lookup them later on.  This slightly improves the success rate of my
test data set.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/annotate-data.c | 57 +++++++++++++++++++++++++++++++--
 1 file changed, 55 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index 12d5faff3b7a..4dd0911904f2 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -28,6 +28,8 @@
 /* register number of the stack pointer */
 #define X86_REG_SP 7
 
+static void delete_var_types(struct die_var_type *var_types);
+
 enum type_state_kind {
 	TSR_KIND_INVALID = 0,
 	TSR_KIND_TYPE,
@@ -557,8 +559,8 @@ static bool global_var__add(struct data_loc_info *dloc, u64 addr,
 	if (gvar == NULL)
 		return false;
 
-	gvar->name = strdup(name);
-	if (gvar->name == NULL) {
+	gvar->name = name ? strdup(name) : NULL;
+	if (name && gvar->name == NULL) {
 		free(gvar);
 		return false;
 	}
@@ -612,6 +614,53 @@ static bool get_global_var_info(struct data_loc_info *dloc, u64 addr,
 	return true;
 }
 
+static void global_var__collect(struct data_loc_info *dloc)
+{
+	Dwarf *dwarf = dloc->di->dbg;
+	Dwarf_Off off, next_off;
+	Dwarf_Die cu_die, type_die;
+	size_t header_size;
+
+	/* Iterate all CU and collect global variables that have no location in a register. */
+	off = 0;
+	while (dwarf_nextcu(dwarf, off, &next_off, &header_size,
+			    NULL, NULL, NULL) == 0) {
+		struct die_var_type *var_types = NULL;
+		struct die_var_type *pos;
+
+		if (dwarf_offdie(dwarf, off + header_size, &cu_die) == NULL) {
+			off = next_off;
+			continue;
+		}
+
+		die_collect_global_vars(&cu_die, &var_types);
+
+		for (pos = var_types; pos; pos = pos->next) {
+			const char *var_name = NULL;
+			int var_offset = 0;
+
+			if (pos->reg != -1)
+				continue;
+
+			if (!dwarf_offdie(dwarf, pos->die_off, &type_die))
+				continue;
+
+			if (!get_global_var_info(dloc, pos->addr, &var_name,
+						 &var_offset))
+				continue;
+
+			if (var_offset != 0)
+				continue;
+
+			global_var__add(dloc, pos->addr, var_name, &type_die);
+		}
+
+		delete_var_types(var_types);
+
+		off = next_off;
+	}
+}
+
 static bool get_global_var_type(Dwarf_Die *cu_die, struct data_loc_info *dloc,
 				u64 ip, u64 var_addr, int *var_offset,
 				Dwarf_Die *type_die)
@@ -620,8 +669,12 @@ static bool get_global_var_type(Dwarf_Die *cu_die, struct data_loc_info *dloc,
 	int offset;
 	const char *var_name = NULL;
 	struct global_var_entry *gvar;
+	struct dso *dso = map__dso(dloc->ms->map);
 	Dwarf_Die var_die;
 
+	if (RB_EMPTY_ROOT(&dso->global_vars))
+		global_var__collect(dloc);
+
 	gvar = global_var__find(dloc, var_addr);
 	if (gvar) {
 		if (!dwarf_offdie(dloc->di->dbg, gvar->die_offset, type_die))
-- 
2.45.0.rc1.225.g2a3ae87e7f-goog