On Mon Aug 3, 2026 at 2:18 AM CEST, Changwoo Min wrote:
> bpf_arena_spin_lock.h defines its 64KB qnodes array in the header, so
> every translation unit including it emits a copy. __weak makes them all
> resolve to one instance, but bpftool gen object merges only the symbols
> and concatenates each input's .addr_space.1 bytes, leaving the surplus
> copies unreferenced in the linked object.
>
> libarena links ten such units, so nine copies were dead weight (bytes):
>
> object before after
> -----------------------------------------------------
> .addr_space.1 in libarena.bpf.o 676200 86376
> libarena.skel.h 2100123 892371
> libarena_asan.skel.h 2641124 1466477
>
> Declare qnodes in the header and let each program define it once:
> libarena in src/common.bpf.c, and the arena_spin_lock test beside the
> lock it guards.
>
> Tested with test_progs -t arena_spin_lock and -t libarena.
>
> Signed-off-by: Changwoo Min <[email protected]>
> ---
This seems ok to me. I don't have better ideas. Emil, any thoughts?
> .../selftests/bpf/libarena/include/bpf_arena_spin_lock.h | 7 +------
> tools/testing/selftests/bpf/libarena/src/common.bpf.c | 7 +++++++
> tools/testing/selftests/bpf/progs/arena_spin_lock.c | 7 +++++++
> 3 files changed, 15 insertions(+), 6 deletions(-)
>
> diff --git
> a/tools/testing/selftests/bpf/libarena/include/bpf_arena_spin_lock.h
> b/tools/testing/selftests/bpf/libarena/include/bpf_arena_spin_lock.h
> index ae6b72d15bb6..71d9db610263 100644
> --- a/tools/testing/selftests/bpf/libarena/include/bpf_arena_spin_lock.h
> +++ b/tools/testing/selftests/bpf/libarena/include/bpf_arena_spin_lock.h
> @@ -103,12 +103,7 @@ struct arena_qnode {
> #define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET)
> #define _Q_PENDING_VAL (1U << _Q_PENDING_OFFSET)
>
> -/*
> - * The qnodes are marked __weak so we can define them in the header
> - * while still ensuring all compilation units use the same struct
> - * instance.
> - */
> -struct arena_qnode __weak __arena __hidden qnodes[_Q_MAX_CPUS][_Q_MAX_NODES];
> +extern struct arena_qnode __arena __hidden qnodes[_Q_MAX_CPUS][_Q_MAX_NODES];
>
> static inline u32 encode_tail(int cpu, int idx)
> {
> diff --git a/tools/testing/selftests/bpf/libarena/src/common.bpf.c
> b/tools/testing/selftests/bpf/libarena/src/common.bpf.c
> index 50be57213dfb..06481f2a2892 100644
> --- a/tools/testing/selftests/bpf/libarena/src/common.bpf.c
> +++ b/tools/testing/selftests/bpf/libarena/src/common.bpf.c
> @@ -8,6 +8,13 @@ const volatile u32 zero = 0;
>
> struct buddy __arena buddy;
>
> +/*
> + * Storage for the queue nodes declared by bpf_arena_spin_lock.h. Each
> program
> + * linking the arena spinlock provides exactly one definition, so that the
> array
> + * is emitted once rather than once per translation unit.
> + */
> +struct arena_qnode __arena __hidden qnodes[_Q_MAX_CPUS][_Q_MAX_NODES];
> +
> int arena_fls(__u64 word)
> {
> if (!word)
> diff --git a/tools/testing/selftests/bpf/progs/arena_spin_lock.c
> b/tools/testing/selftests/bpf/progs/arena_spin_lock.c
> index cf7cda79c16c..92e75ec3844c 100644
> --- a/tools/testing/selftests/bpf/progs/arena_spin_lock.c
> +++ b/tools/testing/selftests/bpf/progs/arena_spin_lock.c
> @@ -23,6 +23,13 @@ int cs_count;
> #if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
> arena_spinlock_t __arena lock;
> int test_skip = 1;
> +
> +/*
> + * Storage for the queue nodes declared by bpf_arena_spin_lock.h. Each
> program
> + * linking the arena spinlock provides exactly one definition; libarena's
> lives
> + * in libarena/src/common.bpf.c.
> + */
> +struct arena_qnode __arena __hidden qnodes[_Q_MAX_CPUS][_Q_MAX_NODES];
> #else
> int test_skip = 2;
> #endif
