Re: [PATCH bpf-next 1/3] bpf: implement relay map basis

[Jiri Olsa <olsajiri@gmail.com>]

On Fri, Dec 22, 2023 at 08:21:44PM +0800, Philo Lu wrote:

SNIP

> +/* bpf_attr is used as follows:
> + * - key size: must be 0
> + * - value size: value will be used as directory name by map_update_elem
> + *   (to create relay files). If passed as 0, it will be set to NAME_MAX as
> + *   default
> + *
> + * - max_entries: subbuf size
> + * - map_extra: subbuf num, default as 8
> + *
> + * When alloc, we do not set up relay files considering dir_name conflicts.
> + * Instead we use relay_late_setup_files() in map_update_elem(), and thus the
> + * value is used as dir_name, and map->name is used as base_filename.
> + */
> +static struct bpf_map *relay_map_alloc(union bpf_attr *attr)
> +{
> +	struct bpf_relay_map *rmap;
> +
> +	if (unlikely(attr->map_flags & ~RELAY_CREATE_FLAG_MASK))
> +		return ERR_PTR(-EINVAL);
> +
> +	/* key size must be 0 in relay map */
> +	if (unlikely(attr->key_size))
> +		return ERR_PTR(-EINVAL);
> +
> +	if (unlikely(attr->value_size > NAME_MAX)) {
> +		pr_warn("value_size should be no more than %d\n", NAME_MAX);
> +		return ERR_PTR(-EINVAL);
> +	} else if (attr->value_size == 0)
> +		attr->value_size = NAME_MAX;

the concept of no key with just value seems strange.. I never worked
with relay channels, so perhaps stupid question: but why not have one
relay channel for given key? having the debugfs like:

  /sys/kernel/debug/my_rmap/mychannel/<cpu>

> +
> +	/* set default subbuf num */
> +	attr->map_extra = attr->map_extra & UINT_MAX;
> +	if (!attr->map_extra)
> +		attr->map_extra = 8;
> +
> +	if (!attr->map_name || strlen(attr->map_name) == 0)

attr->map_name is allways != NULL

> +		return ERR_PTR(-EINVAL);
> +
> +	rmap = bpf_map_area_alloc(sizeof(*rmap), NUMA_NO_NODE);
> +	if (!rmap)
> +		return ERR_PTR(-ENOMEM);
> +
> +	bpf_map_init_from_attr(&rmap->map, attr);
> +
> +	rmap->relay_cb.create_buf_file = create_buf_file_handler;
> +	rmap->relay_cb.remove_buf_file = remove_buf_file_handler;
> +	if (attr->map_flags & BPF_F_OVERWRITE)
> +		rmap->relay_cb.subbuf_start = subbuf_start_overwrite;
> +
> +	rmap->relay_chan = relay_open(NULL, NULL,
> +							attr->max_entries, attr->map_extra,
> +							&rmap->relay_cb, NULL);

wrong indentation

> +	if (!rmap->relay_chan)
> +		return ERR_PTR(-EINVAL);
> +
> +	return &rmap->map;
> +}
> +
> +static void relay_map_free(struct bpf_map *map)
> +{
> +	struct bpf_relay_map *rmap;
> +
> +	rmap = container_of(map, struct bpf_relay_map, map);
> +	relay_close(rmap->relay_chan);
> +	debugfs_remove_recursive(rmap->relay_chan->parent);
> +	kfree(rmap);

should you use bpf_map_area_free instead?

jirka

> +}
> +
> +static void *relay_map_lookup_elem(struct bpf_map *map, void *key)
> +{
> +	return ERR_PTR(-EOPNOTSUPP);
> +}
> +
> +static long relay_map_update_elem(struct bpf_map *map, void *key, void *value,
> +				   u64 flags)
> +{
> +	return -EOPNOTSUPP;
> +}
> +
> +static long relay_map_delete_elem(struct bpf_map *map, void *key)
> +{
> +	return -EOPNOTSUPP;
> +}
> +
> +static int relay_map_get_next_key(struct bpf_map *map, void *key,
> +				    void *next_key)
> +{
> +	return -EOPNOTSUPP;
> +}
> +
> +static u64 relay_map_mem_usage(const struct bpf_map *map)
> +{
> +	struct bpf_relay_map *rmap;
> +	u64 usage = sizeof(struct bpf_relay_map);
> +
> +	rmap = container_of(map, struct bpf_relay_map, map);
> +	usage += sizeof(struct rchan);
> +	usage += (sizeof(struct rchan_buf) + rmap->relay_chan->alloc_size)
> +			 * num_online_cpus();
> +	return usage;
> +}
> +
> +BTF_ID_LIST_SINGLE(relay_map_btf_ids, struct, bpf_relay_map)
> +const struct bpf_map_ops relay_map_ops = {
> +	.map_meta_equal = bpf_map_meta_equal,
> +	.map_alloc = relay_map_alloc,
> +	.map_free = relay_map_free,
> +	.map_lookup_elem = relay_map_lookup_elem,
> +	.map_update_elem = relay_map_update_elem,
> +	.map_delete_elem = relay_map_delete_elem,
> +	.map_get_next_key = relay_map_get_next_key,
> +	.map_mem_usage = relay_map_mem_usage,
> +	.map_btf_id = &relay_map_btf_ids[0],
> +};
> diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
> index 1bf9805ee185..35ae54ac6736 100644
> --- a/kernel/bpf/syscall.c
> +++ b/kernel/bpf/syscall.c
> @@ -1147,6 +1147,7 @@ static int map_create(union bpf_attr *attr)
>  	}
>  
>  	if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER &&
> +	    attr->map_type != BPF_MAP_TYPE_RELAY &&
>  	    attr->map_extra != 0)
>  		return -EINVAL;
>  
> -- 
> 2.32.0.3.g01195cf9f
>