perf symbols: Add some heuristics for choosing the best duplicate symbol

Try and pick the best symbol based on a few heuristics: - Prefer a non weak symbol over a weak one - Prefer a global symbol over a non global one - Prefer a symbol with less underscores (idea taken from kallsyms.c) - If all else fails, choose the symbol with the longest name Cc: Eric B Munson <emunson@mgebm.net> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110824065243.161953371@samba.org Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf symbols: Add some heuristics for choosing the best duplicate symbol
Try and pick the best symbol based on a few heuristics: - Prefer a non weak symbol over a weak one - Prefer a global symbol over a non global one - Prefer a symbol with less underscores (idea taken from kallsyms.c) - If all else fails, choose the symbol with the longest name Cc: Eric B Munson <emunson@mgebm.net> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110824065243.161953371@samba.org Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Anton Blanchard · Arnaldo Carvalho de Melo
1 parent 3187790860
Showing 1 changed file with 88 additions and 0 deletions Side-by-side Diff
tools/perf/util/symbol.c
@@ -86,6 +86,92 @@
 	}
 }
  
+static int prefix_underscores_count(const char *str)
+{
+	const char *tail = str;
+
+	while (*tail == '_')
+		tail++;
+
+	return tail - str;
+}
+
+#define SYMBOL_A 0
+#define SYMBOL_B 1
+
+static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
+{
+	s64 a;
+	s64 b;
+
+	/* Prefer a symbol with non zero length */
+	a = syma->end - syma->start;
+	b = symb->end - symb->start;
+	if ((b == 0) && (a > 0))
+		return SYMBOL_A;
+	else if ((a == 0) && (b > 0))
+		return SYMBOL_B;
+
+	/* Prefer a non weak symbol over a weak one */
+	a = syma->binding == STB_WEAK;
+	b = symb->binding == STB_WEAK;
+	if (b && !a)
+		return SYMBOL_A;
+	if (a && !b)
+		return SYMBOL_B;
+
+	/* Prefer a global symbol over a non global one */
+	a = syma->binding == STB_GLOBAL;
+	b = symb->binding == STB_GLOBAL;
+	if (a && !b)
+		return SYMBOL_A;
+	if (b && !a)
+		return SYMBOL_B;
+
+	/* Prefer a symbol with less underscores */
+	a = prefix_underscores_count(syma->name);
+	b = prefix_underscores_count(symb->name);
+	if (b > a)
+		return SYMBOL_A;
+	else if (a > b)
+		return SYMBOL_B;
+
+	/* If all else fails, choose the symbol with the longest name */
+	if (strlen(syma->name) >= strlen(symb->name))
+		return SYMBOL_A;
+	else
+		return SYMBOL_B;
+}
+
+static void symbols__fixup_duplicate(struct rb_root *symbols)
+{
+	struct rb_node *nd;
+	struct symbol *curr, *next;
+
+	nd = rb_first(symbols);
+
+	while (nd) {
+		curr = rb_entry(nd, struct symbol, rb_node);
+again:
+		nd = rb_next(&curr->rb_node);
+		next = rb_entry(nd, struct symbol, rb_node);
+
+		if (!nd)
+			break;
+
+		if (curr->start != next->start)
+			continue;
+
+		if (choose_best_symbol(curr, next) == SYMBOL_A) {
+			rb_erase(&next->rb_node, symbols);
+			goto again;
+		} else {
+			nd = rb_next(&curr->rb_node);
+			rb_erase(&curr->rb_node, symbols);
+		}
+	}
+}
+
 static void symbols__fixup_end(struct rb_root *symbols)
 {
 	struct rb_node *nd, *prevnd = rb_first(symbols);
@@ -692,6 +778,7 @@
 	if (dso__load_all_kallsyms(dso, filename, map) < 0)
 		return -1;
  
+	symbols__fixup_duplicate(&dso->symbols[map->type]);
 	symbols__fixup_end(&dso->symbols[map->type]);
  
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
@@ -1269,6 +1356,7 @@
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
+		symbols__fixup_duplicate(&dso->symbols[map->type]);
 		symbols__fixup_end(&dso->symbols[map->type]);
 		if (kmap) {
 			/*
...	...	@@ -86,6 +86,92 @@
86	86	}
87	87	}
88	88
	89	+static int prefix_underscores_count(const char *str)
	90	+{
	91	+ const char *tail = str;
	92	+
	93	+ while (*tail == '_')
	94	+ tail++;
	95	+
	96	+ return tail - str;
	97	+}
	98	+
	99	+#define SYMBOL_A 0
	100	+#define SYMBOL_B 1
	101	+
	102	+static int choose_best_symbol(struct symbol syma, struct symbol symb)
	103	+{
	104	+ s64 a;
	105	+ s64 b;
	106	+
	107	+ /* Prefer a symbol with non zero length */
	108	+ a = syma->end - syma->start;
	109	+ b = symb->end - symb->start;
	110	+ if ((b == 0) && (a > 0))
	111	+ return SYMBOL_A;
	112	+ else if ((a == 0) && (b > 0))
	113	+ return SYMBOL_B;
	114	+
	115	+ /* Prefer a non weak symbol over a weak one */
	116	+ a = syma->binding == STB_WEAK;
	117	+ b = symb->binding == STB_WEAK;
	118	+ if (b && !a)
	119	+ return SYMBOL_A;
	120	+ if (a && !b)
	121	+ return SYMBOL_B;
	122	+
	123	+ /* Prefer a global symbol over a non global one */
	124	+ a = syma->binding == STB_GLOBAL;
	125	+ b = symb->binding == STB_GLOBAL;
	126	+ if (a && !b)
	127	+ return SYMBOL_A;
	128	+ if (b && !a)
	129	+ return SYMBOL_B;
	130	+
	131	+ /* Prefer a symbol with less underscores */
	132	+ a = prefix_underscores_count(syma->name);
	133	+ b = prefix_underscores_count(symb->name);
	134	+ if (b > a)
	135	+ return SYMBOL_A;
	136	+ else if (a > b)
	137	+ return SYMBOL_B;
	138	+
	139	+ /* If all else fails, choose the symbol with the longest name */
	140	+ if (strlen(syma->name) >= strlen(symb->name))
	141	+ return SYMBOL_A;
	142	+ else
	143	+ return SYMBOL_B;
	144	+}
	145	+
	146	+static void symbols__fixup_duplicate(struct rb_root *symbols)
	147	+{
	148	+ struct rb_node *nd;
	149	+ struct symbol curr, next;
	150	+
	151	+ nd = rb_first(symbols);
	152	+
	153	+ while (nd) {
	154	+ curr = rb_entry(nd, struct symbol, rb_node);
	155	+again:
	156	+ nd = rb_next(&curr->rb_node);
	157	+ next = rb_entry(nd, struct symbol, rb_node);
	158	+
	159	+ if (!nd)
	160	+ break;
	161	+
	162	+ if (curr->start != next->start)
	163	+ continue;
	164	+
	165	+ if (choose_best_symbol(curr, next) == SYMBOL_A) {
	166	+ rb_erase(&next->rb_node, symbols);
	167	+ goto again;
	168	+ } else {
	169	+ nd = rb_next(&curr->rb_node);
	170	+ rb_erase(&curr->rb_node, symbols);
	171	+ }
	172	+ }
	173	+}
	174	+
89	175	static void symbols__fixup_end(struct rb_root *symbols)
90	176	{
91	177	struct rb_node nd, prevnd = rb_first(symbols);
...	...	@@ -692,6 +778,7 @@
692	778	if (dso__load_all_kallsyms(dso, filename, map) < 0)
693	779	return -1;
694	780
	781	+ symbols__fixup_duplicate(&dso->symbols[map->type]);
695	782	symbols__fixup_end(&dso->symbols[map->type]);
696	783
697	784	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
...	...	@@ -1269,6 +1356,7 @@
1269	1356	* For misannotated, zeroed, ASM function sizes.
1270	1357	*/
1271	1358	if (nr > 0) {
	1359	+ symbols__fixup_duplicate(&dso->symbols[map->type]);
1272	1360	symbols__fixup_end(&dso->symbols[map->type]);
1273	1361	if (kmap) {
1274	1362	/*