[PATCH bpf-next] selftests/bpf: Fix RELEASE build failure with gcc14

[PATCH bpf-next] selftests/bpf: Fix RELEASE build failure with gcc14

[Yonghong Song]

With gcc14, when building with RELEASE=1, I hit four below compilation
failure:

Error 1:
  In file included from test_loader.c:6:
  test_loader.c: In function ‘run_subtest’: test_progs.h:194:17:
      error: ‘retval’ may be used uninitialized in this function
   [-Werror=maybe-uninitialized]
    194 |                 fprintf(stdout, ##format);           \
        |                 ^~~~~~~
  test_loader.c:958:13: note: ‘retval’ was declared here
    958 |         int retval, err, i;
        |             ^~~~~~

  The uninitialized var 'retval' actaully could cause incorrect result.

Error 2:
  In function ‘test_fd_array_cnt’:
  prog_tests/fd_array.c:71:14: error: ‘btf_id’ may be used uninitialized in this
      function [-Werror=maybe-uninitialized]
     71 |         fd = bpf_btf_get_fd_by_id(id);
        |              ^~~~~~~~~~~~~~~~~~~~~~~~
  prog_tests/fd_array.c:302:15: note: ‘btf_id’ was declared here
    302 |         __u32 btf_id;
        |               ^~~~~~

  Changing ASSERT_GE to ASSERT_EQ can fix the compilation error. Otherwise,
  there is no functionality change.

Error 3:
  prog_tests/tailcalls.c: In function ‘test_tailcall_hierarchy_count’:
  prog_tests/tailcalls.c:1402:23: error: ‘fentry_data_fd’ may be used uninitialized
      in this function [-Werror=maybe-uninitialized]
     1402 |                 err = bpf_map_lookup_elem(fentry_data_fd, &i, &val);
          |                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

  The code is correct. The change intends to slient gcc errors.

Error 4: (this error only happens on arm64)
  In file included from prog_tests/log_buf.c:4:
  prog_tests/log_buf.c: In function ‘bpf_prog_load_log_buf’:
  ./test_progs.h:390:22: error: ‘log_buf’ may be used uninitialized [-Werror=maybe-uninitialized]
    390 |         int ___err = libbpf_get_error(___res);             \
        |                      ^~~~~~~~~~~~~~~~~~~~~~~~
  prog_tests/log_buf.c:158:14: note: in expansion of macro ‘ASSERT_OK_PTR’
    158 |         if (!ASSERT_OK_PTR(log_buf, "log_buf_alloc"))
        |              ^~~~~~~~~~~~~
  In file included from selftests/bpf/tools/include/bpf/bpf.h:32,
                 from ./test_progs.h:36:
  selftests/bpf/tools/include/bpf/libbpf_legacy.h:113:17:
    note: by argument 1 of type ‘const void *’ to ‘libbpf_get_error’ declared here
    113 | LIBBPF_API long libbpf_get_error(const void *ptr);
        |                 ^~~~~~~~~~~~~~~~

  Adding a pragma to disable maybe-uninitialized fixed the issue.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 tools/testing/selftests/bpf/prog_tests/fd_array.c  | 2 +-
 tools/testing/selftests/bpf/prog_tests/log_buf.c   | 4 ++++
 tools/testing/selftests/bpf/prog_tests/tailcalls.c | 2 +-
 tools/testing/selftests/bpf/test_loader.c          | 6 +++---
 4 files changed, 9 insertions(+), 5 deletions(-)

NOTE: I found these issues when I tried to compare usdt.test.o binaries
      when building selftests with and without RELEASE=1.

diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c
index 9add890c2d37..241b2c8c6e0f 100644
--- a/tools/testing/selftests/bpf/prog_tests/fd_array.c
+++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c
@@ -312,7 +312,7 @@ static void check_fd_array_cnt__referenced_btfs(void)
 
 	/* btf should still exist when original file descriptor is closed */
 	err = get_btf_id_by_fd(extra_fds[0], &btf_id);
-	if (!ASSERT_GE(err, 0, "get_btf_id_by_fd"))
+	if (!ASSERT_EQ(err, 0, "get_btf_id_by_fd"))
 		goto cleanup;
 
 	Close(extra_fds[0]);
diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c
index 169ce689b97c..d6f14a232002 100644
--- a/tools/testing/selftests/bpf/prog_tests/log_buf.c
+++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c
@@ -7,6 +7,10 @@
 #include "test_log_buf.skel.h"
 #include "bpf_util.h"
 
+#if !defined(__clang__)
+#pragma GCC diagnostic ignored "-Wmaybe-uninitialized"
+#endif
+
 static size_t libbpf_log_pos;
 static char libbpf_log_buf[1024 * 1024];
 static bool libbpf_log_error;
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index 66a900327f91..0ab36503c3b2 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -1195,7 +1195,7 @@ static void test_tailcall_hierarchy_count(const char *which, bool test_fentry,
 					  bool test_fexit,
 					  bool test_fentry_entry)
 {
-	int err, map_fd, prog_fd, main_data_fd, fentry_data_fd, fexit_data_fd, i, val;
+	int err, map_fd, prog_fd, main_data_fd, fentry_data_fd = 0, fexit_data_fd = 0, i, val;
 	struct bpf_object *obj = NULL, *fentry_obj = NULL, *fexit_obj = NULL;
 	struct bpf_link *fentry_link = NULL, *fexit_link = NULL;
 	struct bpf_program *prog, *fentry_prog;
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 9551d8d5f8f9..2c7e9729d5fe 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -1103,9 +1103,9 @@ void run_subtest(struct test_loader *tester,
 			}
 		}
 
-		do_prog_test_run(bpf_program__fd(tprog), &retval,
-				 bpf_program__type(tprog) == BPF_PROG_TYPE_SYSCALL ? true : false);
-		if (retval != subspec->retval && subspec->retval != POINTER_VALUE) {
+		err = do_prog_test_run(bpf_program__fd(tprog), &retval,
+				       bpf_program__type(tprog) == BPF_PROG_TYPE_SYSCALL ? true : false);
+		if (!err && retval != subspec->retval && subspec->retval != POINTER_VALUE) {
 			PRINT_FAIL("Unexpected retval: %d != %d\n", retval, subspec->retval);
 			goto tobj_cleanup;
 		}
-- 
2.47.1

Re: [PATCH bpf-next] selftests/bpf: Fix RELEASE build failure with gcc14

[Alexei Starovoitov]

On Mon, Jun 16, 2025 at 9:50 PM Yonghong Song <yonghong.song@linux.dev> wrote:
>
> With gcc14, when building with RELEASE=1, I hit four below compilation
> failure:
>
> Error 1:
>   In file included from test_loader.c:6:
>   test_loader.c: In function ‘run_subtest’: test_progs.h:194:17:
>       error: ‘retval’ may be used uninitialized in this function
>    [-Werror=maybe-uninitialized]
>     194 |                 fprintf(stdout, ##format);           \
>         |                 ^~~~~~~
>   test_loader.c:958:13: note: ‘retval’ was declared here
>     958 |         int retval, err, i;
>         |             ^~~~~~
>
>   The uninitialized var 'retval' actaully could cause incorrect result.

actually

> Error 2:
>   In function ‘test_fd_array_cnt’:
>   prog_tests/fd_array.c:71:14: error: ‘btf_id’ may be used uninitialized in this
>       function [-Werror=maybe-uninitialized]
>      71 |         fd = bpf_btf_get_fd_by_id(id);
>         |              ^~~~~~~~~~~~~~~~~~~~~~~~
>   prog_tests/fd_array.c:302:15: note: ‘btf_id’ was declared here
>     302 |         __u32 btf_id;
>         |               ^~~~~~
>
>   Changing ASSERT_GE to ASSERT_EQ can fix the compilation error. Otherwise,
>   there is no functionality change.
>
> Error 3:
>   prog_tests/tailcalls.c: In function ‘test_tailcall_hierarchy_count’:
>   prog_tests/tailcalls.c:1402:23: error: ‘fentry_data_fd’ may be used uninitialized
>       in this function [-Werror=maybe-uninitialized]
>      1402 |                 err = bpf_map_lookup_elem(fentry_data_fd, &i, &val);
>           |                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>
>   The code is correct. The change intends to slient gcc errors.

to silence.

Fixed the typos while applying.
Pls use spell check.

Re: [PATCH bpf-next] selftests/bpf: Fix RELEASE build failure with gcc14

[Yonghong Song]

On 6/17/25 10:24 AM, Alexei Starovoitov wrote:
> On Mon, Jun 16, 2025 at 9:50 PM Yonghong Song <yonghong.song@linux.dev> wrote:
>> With gcc14, when building with RELEASE=1, I hit four below compilation
>> failure:
>>
>> Error 1:
>>    In file included from test_loader.c:6:
>>    test_loader.c: In function ‘run_subtest’: test_progs.h:194:17:
>>        error: ‘retval’ may be used uninitialized in this function
>>     [-Werror=maybe-uninitialized]
>>      194 |                 fprintf(stdout, ##format);           \
>>          |                 ^~~~~~~
>>    test_loader.c:958:13: note: ‘retval’ was declared here
>>      958 |         int retval, err, i;
>>          |             ^~~~~~
>>
>>    The uninitialized var 'retval' actaully could cause incorrect result.
> actually
>
>> Error 2:
>>    In function ‘test_fd_array_cnt’:
>>    prog_tests/fd_array.c:71:14: error: ‘btf_id’ may be used uninitialized in this
>>        function [-Werror=maybe-uninitialized]
>>       71 |         fd = bpf_btf_get_fd_by_id(id);
>>          |              ^~~~~~~~~~~~~~~~~~~~~~~~
>>    prog_tests/fd_array.c:302:15: note: ‘btf_id’ was declared here
>>      302 |         __u32 btf_id;
>>          |               ^~~~~~
>>
>>    Changing ASSERT_GE to ASSERT_EQ can fix the compilation error. Otherwise,
>>    there is no functionality change.
>>
>> Error 3:
>>    prog_tests/tailcalls.c: In function ‘test_tailcall_hierarchy_count’:
>>    prog_tests/tailcalls.c:1402:23: error: ‘fentry_data_fd’ may be used uninitialized
>>        in this function [-Werror=maybe-uninitialized]
>>       1402 |                 err = bpf_map_lookup_elem(fentry_data_fd, &i, &val);
>>            |                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>>
>>    The code is correct. The change intends to slient gcc errors.
> to silence.
>
> Fixed the typos while applying.
> Pls use spell check.

Sorry about typo's. Will pay attention to spell check for later patches.

Re: [PATCH bpf-next] selftests/bpf: Fix RELEASE build failure with gcc14

[patchwork-bot+netdevbpf]

Hello:

This patch was applied to bpf/bpf-next.git (master)
by Alexei Starovoitov <ast@kernel.org>:

On Mon, 16 Jun 2025 21:49:56 -0700 you wrote:
> With gcc14, when building with RELEASE=1, I hit four below compilation
> failure:
> 
> Error 1:
>   In file included from test_loader.c:6:
>   test_loader.c: In function ‘run_subtest’: test_progs.h:194:17:
>       error: ‘retval’ may be used uninitialized in this function
>    [-Werror=maybe-uninitialized]
>     194 |                 fprintf(stdout, ##format);           \
>         |                 ^~~~~~~
>   test_loader.c:958:13: note: ‘retval’ was declared here
>     958 |         int retval, err, i;
>         |             ^~~~~~
> 
> [...]

Here is the summary with links:
  - [bpf-next] selftests/bpf: Fix RELEASE build failure with gcc14
    https://git.kernel.org/bpf/bpf-next/c/a633dab4b4d2

You are awesome, thank you!
-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html