Re: [PATCH] bpf: Fix build in minimal configurations, again

[Martin Lau]

On Tue, Dec 10, 2019 at 09:35:46PM +0100, Arnd Bergmann wrote:
> Building with -Werror showed another failure:
> 
> kernel/bpf/btf.c: In function 'btf_get_prog_ctx_type.isra.31':
> kernel/bpf/btf.c:3508:63: error: array subscript 0 is above array bounds of 'u8[0]' {aka 'unsigned char[0]'} [-Werror=array-bounds]
>   ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2;
> 
> I don't actually understand why the array is empty, but a similar
> fix has addressed a related problem, so I suppose we can do the
> same thing here.
> 
> Fixes: ce27709b8162 ("bpf: Fix build in minimal configurations")
> Signed-off-by: Arnd Bergmann <arnd@xxxxxxxx>
> ---
>  kernel/bpf/btf.c | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
> index 7d40da240891..ed2075884724 100644
> --- a/kernel/bpf/btf.c
> +++ b/kernel/bpf/btf.c
> @@ -3470,6 +3470,7 @@ static u8 bpf_ctx_convert_map[] = {
>  	[_id] = __ctx_convert##_id,
>  #include <linux/bpf_types.h>
>  #undef BPF_PROG_TYPE
> +	0, /* avoid empty array */
If bpf_types.h is empty, the prog should have already failed
earlier in find_prog_type() in syscall.c, so 0 here should
be fine.

Acked-by: Martin KaFai Lau <kafai@xxxxxx>