1 files changed, 118 insertions, 35 deletions

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 469c0264ed29..40eeaf07725b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -74,16 +74,104 @@ static void dso__set_sorted_by_name(struct dso *dso, enum map_type type)
 
 bool symbol_type__is_a(char symbol_type, enum map_type map_type)
 {
+	symbol_type = toupper(symbol_type);
+
 	switch (map_type) {
 	case MAP__FUNCTION:
 		return symbol_type == 'T' || symbol_type == 'W';
 	case MAP__VARIABLE:
-		return symbol_type == 'D' || symbol_type == 'd';
+		return symbol_type == 'D';
 	default:
 		return false;
 	}
 }
 
+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);
@@ -438,18 +526,11 @@ int kallsyms__parse(const char *filename, void *arg,
 	char *line = NULL;
 	size_t n;
 	int err = -1;
-	u64 prev_start = 0;
-	char prev_symbol_type = 0;
-	char *prev_symbol_name;
 	FILE *file = fopen(filename, "r");
 
 	if (file == NULL)
 		goto out_failure;
 
-	prev_symbol_name = malloc(KSYM_NAME_LEN);
-	if (prev_symbol_name == NULL)
-		goto out_close;
-
 	err = 0;
 
 	while (!feof(file)) {
@@ -470,7 +551,7 @@ int kallsyms__parse(const char *filename, void *arg,
 		if (len + 2 >= line_len)
 			continue;
 
-		symbol_type = toupper(line[len]);
+		symbol_type = line[len];
 		len += 2;
 		symbol_name = line + len;
 		len = line_len - len;
@@ -480,24 +561,18 @@ int kallsyms__parse(const char *filename, void *arg,
 			break;
 		}
 
-		if (prev_symbol_type) {
-			u64 end = start;
-			if (end != prev_start)
-				--end;
-			err = process_symbol(arg, prev_symbol_name,
-					     prev_symbol_type, prev_start, end);
-			if (err)
-				break;
-		}
-
-		memcpy(prev_symbol_name, symbol_name, len + 1);
-		prev_symbol_type = symbol_type;
-		prev_start = start;
+		/*
+		 * module symbols are not sorted so we add all
+		 * symbols with zero length and rely on
+		 * symbols__fixup_end() to fix it up.
+		 */
+		err = process_symbol(arg, symbol_name,
+				     symbol_type, start, start);
+		if (err)
+			break;
 	}
 
-	free(prev_symbol_name);
 	free(line);
-out_close:
 	fclose(file);
 	return err;
 
@@ -703,6 +778,9 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 	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)
 		dso->symtab_type = SYMTAB__GUEST_KALLSYMS;
 	else
@@ -1092,8 +1170,7 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 	if (dso->has_build_id) {
 		u8 build_id[BUILD_ID_SIZE];
 
-		if (elf_read_build_id(elf, build_id,
-				      BUILD_ID_SIZE) != BUILD_ID_SIZE)
+		if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0)
 			goto out_elf_end;
 
 		if (!dso__build_id_equal(dso, build_id))
@@ -1111,6 +1188,8 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 	}
 
 	opdsec = elf_section_by_name(elf, &ehdr, &opdshdr, ".opd", &opdidx);
+	if (opdshdr.sh_type != SHT_PROGBITS)
+		opdsec = NULL;
 	if (opdsec)
 		opddata = elf_rawdata(opdsec, NULL);
 
@@ -1276,6 +1355,7 @@ new_symbol:
 	 * 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) {
 			/*
@@ -1362,8 +1442,8 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size)
 	ptr = data->d_buf;
 	while (ptr < (data->d_buf + data->d_size)) {
 		GElf_Nhdr *nhdr = ptr;
-		int namesz = NOTE_ALIGN(nhdr->n_namesz),
-		    descsz = NOTE_ALIGN(nhdr->n_descsz);
+		size_t namesz = NOTE_ALIGN(nhdr->n_namesz),
+		       descsz = NOTE_ALIGN(nhdr->n_descsz);
 		const char *name;
 
 		ptr += sizeof(*nhdr);
@@ -1372,8 +1452,10 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size)
 		if (nhdr->n_type == NT_GNU_BUILD_ID &&
 		    nhdr->n_namesz == sizeof("GNU")) {
 			if (memcmp(name, "GNU", sizeof("GNU")) == 0) {
-				memcpy(bf, ptr, BUILD_ID_SIZE);
-				err = BUILD_ID_SIZE;
+				size_t sz = min(size, descsz);
+				memcpy(bf, ptr, sz);
+				memset(bf + sz, 0, size - sz);
+				err = descsz;
 				break;
 			}
 		}
@@ -1425,7 +1507,7 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
 	while (1) {
 		char bf[BUFSIZ];
 		GElf_Nhdr nhdr;
-		int namesz, descsz;
+		size_t namesz, descsz;
 
 		if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr))
 			break;
@@ -1434,15 +1516,16 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
 		descsz = NOTE_ALIGN(nhdr.n_descsz);
 		if (nhdr.n_type == NT_GNU_BUILD_ID &&
 		    nhdr.n_namesz == sizeof("GNU")) {
-			if (read(fd, bf, namesz) != namesz)
+			if (read(fd, bf, namesz) != (ssize_t)namesz)
 				break;
 			if (memcmp(bf, "GNU", sizeof("GNU")) == 0) {
-				if (read(fd, build_id,
-				    BUILD_ID_SIZE) == BUILD_ID_SIZE) {
+				size_t sz = min(descsz, size);
+				if (read(fd, build_id, sz) == (ssize_t)sz) {
+					memset(build_id + sz, 0, size - sz);
 					err = 0;
 					break;
 				}
-			} else if (read(fd, bf, descsz) != descsz)
+			} else if (read(fd, bf, descsz) != (ssize_t)descsz)
 				break;
 		} else {
 			int n = namesz + descsz;