[RFC dwarves] btf_encoder: Remove duplicates from functions entries

[Jiri Olsa <jolsa@kernel.org>]

Menglong reported issue where we can have function in BTF which has
multiple addresses in kallsysm [1].

Rather than filtering this in runtime, let's teach pahole to remove
such functions.

Removing duplicate records from functions entries that have more
at least one different address. This way btf_encoder__find_function
won't find such functions and they won't be added in BTF.

In my setup it removed 428 functions out of 77141.

[1] https://lore.kernel.org/bpf/20250710070835.260831-1-dongml2@chinatelecom.cn/
Reported-by: Menglong Dong <menglong8.dong@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---

Alan, 
I'd like to test this in the pahole CI, is there a way to manualy trigger it?

thanks,
jirka


---
 btf_encoder.c | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/btf_encoder.c b/btf_encoder.c
index 16739066caae..a25fe2f8bfb1 100644
--- a/btf_encoder.c
+++ b/btf_encoder.c
@@ -99,6 +99,7 @@ struct elf_function {
 	size_t		prefixlen;
 	bool		kfunc;
 	uint32_t	kfunc_flags;
+	unsigned long	addr;
 };
 
 struct elf_secinfo {
@@ -1469,6 +1470,7 @@ static void elf_functions__collect_function(struct elf_functions *functions, GEl
 
 	func = &functions->entries[functions->cnt];
 	func->name = name;
+	func->addr = sym->st_value;
 	if (strchr(name, '.')) {
 		const char *suffix = strchr(name, '.');
 
@@ -2143,6 +2145,40 @@ int btf_encoder__encode(struct btf_encoder *encoder, struct conf_load *conf)
 	return err;
 }
 
+/*
+ * Remove name duplicates from functions->entries that have
+ * at least 2 different addresses.
+ */
+static void functions_remove_dups(struct elf_functions *functions)
+{
+	struct elf_function *n = &functions->entries[0];
+	bool matched = false, diff = false;
+	int i, j;
+
+	for (i = 0, j = 1; i < functions->cnt && j < functions->cnt; i++, j++) {
+		struct elf_function *a = &functions->entries[i];
+		struct elf_function *b = &functions->entries[j];
+
+		if (!strcmp(a->name, b->name)) {
+			matched = true;
+			diff |= a->addr != b->addr;
+			continue;
+		}
+
+		/*
+		 * Keep only not-matched entries and last one of the matched/duplicates
+		 * ones if all of the matched entries had the same address.
+		 **/
+		if (!matched || !diff)
+			*n++ = *a;
+		matched = diff = false;
+	}
+
+	if (!matched || !diff)
+		*n++ = functions->entries[functions->cnt - 1];
+	functions->cnt = n - &functions->entries[0];
+}
+
 static int elf_functions__collect(struct elf_functions *functions)
 {
 	uint32_t nr_symbols = elf_symtab__nr_symbols(functions->symtab);
@@ -2168,6 +2204,7 @@ static int elf_functions__collect(struct elf_functions *functions)
 
 	if (functions->cnt) {
 		qsort(functions->entries, functions->cnt, sizeof(*functions->entries), functions_cmp);
+		functions_remove_dups(functions);
 	} else {
 		err = 0;
 		goto out_free;
-- 
2.50.1