selftests/bpf: Fix RELEASE build failure with gcc14
Subsystems (3)
Yonghong Song
reviewerPATCH 1/1 selftests/bpf: Fix RELEASE build failure with gcc14
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.
--- 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.
tools/testing/selftests/bpf/prog_tests/fd_array.c +1 -1
@@ -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 ]);
tools/testing/selftests/bpf/prog_tests/log_buf.c +4 -0
@@ -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;
tools/testing/selftests/bpf/prog_tests/tailcalls.c +1 -1
@@ -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;
tools/testing/selftests/bpf/test_loader.c +3 -3
@@ -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; }
Signature · 1 line
2.47.1
Quoted 9 lines · 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]
Quoted 7 lines
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
Quoted 13 lines
Error 2:
In function ‘test_fd_array_cnt’:
prog_tests/fd_array.c:71:14: error: ‘btf_id’ may be used uninitialized in thisfunction [-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_GEtoASSERT_EQcan fix the compilation error. Otherwise, there is no functionality change.
Quoted 8 lines
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 uninitializedin 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.
Yonghong Song
reviewerQuoted 38 lines · Alexei Starovoitov
Quoted 14 lines · 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; | ^~~~~~Quoted 1 line
The uninitialized var 'retval' actaully could cause incorrect result.
actually
Quoted 20 lines
Error 2:
In function ‘test_fd_array_cnt’:
prog_tests/fd_array.c:71:14: error: ‘btf_id’ may be used uninitialized in thisfunction [-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_GEtoASSERT_EQcan 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 uninitializedin this function [-Werror=maybe-uninitialized] 1402 | err = bpf_map_lookup_elem(fentry_data_fd, &i, &val); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Quoted 5 lines
Quoted 1 line
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.
This patch was applied to bpf/bpf-next.git (master) by Alexei Starovoitov <[email protected]>:
Hello:
This patch was applied to bpf/bpf-next.git (master) by Alexei Starovoitov <[email protected]>:
Quoted 8 lines · 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]
Quoted 7 lines
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!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html