RE: [PATCH v2 bpf-next 3/4] bpf: inline bpf_map_lookup_elem() for PERCPU_ARRAY maps

[John Fastabend <john.fastabend@gmail.com>]

Andrii Nakryiko wrote:
> Using new per-CPU BPF instruction implement inlining for per-CPU ARRAY
> map lookup helper, if BPF JIT support is present.
> 
> Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
> ---
>  kernel/bpf/arraymap.c | 33 +++++++++++++++++++++++++++++++++
>  1 file changed, 33 insertions(+)
> 
> diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
> index 13358675ff2e..8c1e6d7654bb 100644
> --- a/kernel/bpf/arraymap.c
> +++ b/kernel/bpf/arraymap.c
> @@ -246,6 +246,38 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
>  	return this_cpu_ptr(array->pptrs[index & array->index_mask]);
>  }
>  
> +/* emit BPF instructions equivalent to C code of percpu_array_map_lookup_elem() */
> +static int percpu_array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
> +{
> +	struct bpf_array *array = container_of(map, struct bpf_array, map);
> +	struct bpf_insn *insn = insn_buf;

Nit, If you wanted to be consistent with array_*_map_gen_lookup,

	const int ret = BPF_REG_0;
	const int map_ptr = BPF_REG_1;
	const int index = BPF_REG_2;

But, I think its easier to read as is.

> +
> +	if (!bpf_jit_supports_percpu_insn())
> +		return -EOPNOTSUPP;
> +
> +	if (map->map_flags & BPF_F_INNER_MAP)
> +		return -EOPNOTSUPP;
> +
> +	BUILD_BUG_ON(offsetof(struct bpf_array, map) != 0);
> +	*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct bpf_array, pptrs));
> +
> +	*insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0);
> +	if (!map->bypass_spec_v1) {
> +		*insn++ = BPF_JMP_IMM(BPF_JGE, BPF_REG_0, map->max_entries, 6);
> +		*insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_0, array->index_mask);
> +	} else {
> +		*insn++ = BPF_JMP_IMM(BPF_JGE, BPF_REG_0, map->max_entries, 5);
> +	}
> +
> +	*insn++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3);
> +	*insn++ = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1);
> +	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0);
> +	*insn++ = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0);
> +	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
> +	*insn++ = BPF_MOV64_IMM(BPF_REG_0, 0);
> +	return insn - insn_buf;
> +}
> +
>  static void *percpu_array_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu)
>  {
>  	struct bpf_array *array = container_of(map, struct bpf_array, map);
> @@ -776,6 +808,7 @@ const struct bpf_map_ops percpu_array_map_ops = {
>  	.map_free = array_map_free,
>  	.map_get_next_key = array_map_get_next_key,
>  	.map_lookup_elem = percpu_array_map_lookup_elem,
> +	.map_gen_lookup = percpu_array_map_gen_lookup,
>  	.map_update_elem = array_map_update_elem,
>  	.map_delete_elem = array_map_delete_elem,
>  	.map_lookup_percpu_elem = percpu_array_map_lookup_percpu_elem,

Acked-by: John Fastabend <john.fastabend@gmail.com>