Re: [PATCH bpf-next v3 07/15] bpf: introduce new bpf AF_XDP map type BPF_MAP_TYPE_XSKMAP

[Eric Dumazet <eric.dumazet@gmail.com>]

On 05/02/2018 04:01 AM, Björn Töpel wrote:
> From: Björn Töpel <bjorn.topel@intel.com>
> 
> The xskmap is yet another BPF map, very much inspired by
> dev/cpu/sockmap, and is a holder of AF_XDP sockets. A user application
> adds AF_XDP sockets into the map, and by using the bpf_redirect_map
> helper, an XDP program can redirect XDP frames to an AF_XDP socket.
> 
> Note that a socket that is bound to certain ifindex/queue index will
> *only* accept XDP frames from that netdev/queue index. If an XDP
> program tries to redirect from a netdev/queue index other than what
> the socket is bound to, the frame will not be received on the socket.
> 
> A socket can reside in multiple maps.
> 
> v3: Fixed race and simplified code.
> v2: Removed one indirection in map lookup.
> 
> Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
> ---
>  include/linux/bpf.h       |  25 +++++
>  include/linux/bpf_types.h |   3 +
>  include/net/xdp_sock.h    |   7 ++
>  include/uapi/linux/bpf.h  |   1 +
>  kernel/bpf/Makefile       |   3 +
>  kernel/bpf/verifier.c     |   8 +-
>  kernel/bpf/xskmap.c       | 239 ++++++++++++++++++++++++++++++++++++++++++++++
>  net/xdp/xsk.c             |   5 +
>  8 files changed, 289 insertions(+), 2 deletions(-)
>  create mode 100644 kernel/bpf/xskmap.c
> 

This function is called under rcu_read_lock() , from map_update_elem()

> +
> +static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
> +			       u64 map_flags)
> +{
> +	struct xsk_map *m = container_of(map, struct xsk_map, map);
> +	u32 i = *(u32 *)key, fd = *(u32 *)value;
> +	struct xdp_sock *xs, *old_xs;
> +	struct socket *sock;
> +	int err;
> +
> +	if (unlikely(map_flags > BPF_EXIST))
> +		return -EINVAL;
> +	if (unlikely(i >= m->map.max_entries))
> +		return -E2BIG;
> +	if (unlikely(map_flags == BPF_NOEXIST))
> +		return -EEXIST;
> +
> +	sock = sockfd_lookup(fd, &err);
> +	if (!sock)
> +		return err;
> +
> +	if (sock->sk->sk_family != PF_XDP) {
> +		sockfd_put(sock);
> +		return -EOPNOTSUPP;
> +	}
> +
> +	xs = (struct xdp_sock *)sock->sk;
> +
> +	if (!xsk_is_setup_for_bpf_map(xs)) {
> +		sockfd_put(sock);
> +		return -EOPNOTSUPP;
> +	}
> +
> +	sock_hold(sock->sk);
> +
> +	old_xs = xchg(&m->xsk_map[i], xs);
> +	if (old_xs) {
> +		/* Make sure we've flushed everything. */

So it is illegal to call synchronize_net(), since it is a reschedule point.

> +		synchronize_net();
> +		sock_put((struct sock *)old_xs);
> +	}
> +
> +	sockfd_put(sock);
> +	return 0;
> +}
>