[PATCH v6 2/5] perf symbols: Split out name-independent duplicate symbol selection

[Alireza Haghdoost via B4 Relay]

From: Alireza Haghdoost <haghdoost@xxxxxxxx>

This patch is a refactoring and does not change behavior. It moves the
size, type and binding checks from choose_best_symbol() to
choose_best_symbol_by_attrs(). It also adds symbol__choice_needs_names()
to report whether choosing between two symbols requires their names.

symbols__fixup_duplicate() keeps one of the symbols that share a start
address. It compares size, type and binding first. If those attributes
are equal, it compares leading underscores, name lengths and the result
of arch__choose_best_symbol().

An unresolved lazy symbol stores a file offset instead of a name
pointer. Thus, the lazy loader cannot call choose_best_symbol() until it
loads both names. The new helper lets the loader keep the names
unresolved when the attributes select a winner. It loads names only when
the attributes are equal and duplicate selection needs them.

Signed-off-by: Alireza Haghdoost <haghdoost@xxxxxxxx>
---
 tools/perf/util/symbol.c | 26 ++++++++++++++++++++++++--
 tools/perf/util/symbol.h |  1 +
 2 files changed, 25 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b61a574ce9a3..2d611c05d000 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -157,11 +157,15 @@ int __weak arch__choose_best_symbol(struct symbol *syma,
 	return SYMBOL_A;
 }
 
-static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
+/*
+ * Choose between two symbols at the same address by size, type and binding.
+ * Returns SYMBOL_A or SYMBOL_B, or -1 if only their names can decide.
+ */
+static int choose_best_symbol_by_attrs(const struct symbol *syma,
+				       const struct symbol *symb)
 {
 	s64 a;
 	s64 b;
-	size_t na, nb;
 
 	/* Prefer a symbol with non zero length */
 	a = syma->end - syma->start;
@@ -194,6 +198,24 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
 	if (b && !a)
 		return SYMBOL_B;
 
+	return -1;
+}
+
+bool symbol__choice_needs_names(const struct symbol *syma, const struct symbol *symb)
+{
+	return choose_best_symbol_by_attrs(syma, symb) < 0;
+}
+
+static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
+{
+	int ret = choose_best_symbol_by_attrs(syma, symb);
+	s64 a;
+	s64 b;
+	size_t na, nb;
+
+	if (ret >= 0)
+		return ret;
+
 	/* Prefer a symbol with less underscores */
 	a = prefix_underscores_count(syma->name);
 	b = prefix_underscores_count(symb->name);
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 46b1649c64fc..d8386c4a7fc5 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -303,6 +303,7 @@ int arch__compare_symbol_names(const char *namea, const char *nameb);
 int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 				 unsigned int n);
 int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
+bool symbol__choice_needs_names(const struct symbol *syma, const struct symbol *symb);
 
 enum symbol_tag_include {
 	SYMBOL_TAG_INCLUDE__NONE = 0,

-- 
Git-157)