[bpf-next,v1,1/2] bpf: sock ops: add netns in bpf context

From: Alban Crequy <alban@kinvolk.io>

sockops programs can now access the network namespace inode via
(struct bpf_sock_ops)->netns. This can be useful to apply different
policies on different network namespaces.

In the unlikely case where network namespaces are not compiled in
(CONFIG_NET_NS=n), the verifier will not allow access to ->netns.

Signed-off-by: Alban Crequy <alban@kinvolk.io>
---
 include/uapi/linux/bpf.h |  1 +
 net/core/filter.c        | 40 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+)

On Fri, Apr 12, 2019 at 3:02 AM Alban Crequy <alban.crequy@gmail.com> wrote:
>
> From: Alban Crequy <alban@kinvolk.io>
>
> sockops programs can now access the network namespace inode via
> (struct bpf_sock_ops)->netns. This can be useful to apply different
> policies on different network namespaces.
>
> In the unlikely case where network namespaces are not compiled in
> (CONFIG_NET_NS=n), the verifier will not allow access to ->netns.
>
> Signed-off-by: Alban Crequy <alban@kinvolk.io>

Acked-by: Song Liu <songliubraving@fb.com>

> ---
>  include/uapi/linux/bpf.h |  1 +
>  net/core/filter.c        | 40 ++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 41 insertions(+)
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 31a27dd337dc..5afaab25f205 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -3069,6 +3069,7 @@ struct bpf_sock_ops {
>         __u32 sk_txhash;
>         __u64 bytes_received;
>         __u64 bytes_acked;
> +       __u64 netns;
>  };
>
>  /* Definitions for bpf_sock_ops_cb_flags */
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 22eb2edf5573..f5e75b6fecb2 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -6758,6 +6758,14 @@ static bool sock_ops_is_valid_access(int off, int size,
>                 }
>         } else {
>                 switch (off) {
> +               case offsetof(struct bpf_sock_ops, netns):
> +#ifdef CONFIG_NET_NS
> +                       if (size != sizeof(__u64))
> +                               return false;
> +#else
> +                       return false;
> +#endif
> +                       break;
>                 case bpf_ctx_range_till(struct bpf_sock_ops, bytes_received,
>                                         bytes_acked):
>                         if (size != sizeof(__u64))
> @@ -7908,6 +7916,38 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
>                 SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash,
>                                           struct sock, type);
>                 break;
> +
> +       case offsetof(struct bpf_sock_ops, netns):
> +#ifdef CONFIG_NET_NS
> +               /* Loading: sk_ops->sk->__sk_common.skc_net.net->ns.inum
> +                * Type: (struct bpf_sock_ops_kern *)
> +                *       ->(struct sock *)
> +                *       ->(struct sock_common)
> +                *       .possible_net_t
> +                *       .(struct net *)
> +                *       ->(struct ns_common)
> +                *       .(unsigned int)
> +                */
> +               BUILD_BUG_ON(offsetof(struct sock, __sk_common) != 0);
> +               BUILD_BUG_ON(offsetof(possible_net_t, net) != 0);
> +               *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
> +                                               struct bpf_sock_ops_kern, sk),
> +                                     si->dst_reg, si->src_reg,
> +                                     offsetof(struct bpf_sock_ops_kern, sk));
> +               *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
> +                                               possible_net_t, net),
> +                                     si->dst_reg, si->dst_reg,
> +                                     offsetof(struct sock_common, skc_net));
> +               *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
> +                                               struct ns_common, inum),
> +                                     si->dst_reg, si->dst_reg,
> +                                     offsetof(struct net, ns) +
> +                                     offsetof(struct ns_common, inum));
> +#else
> +               *insn++ = BPF_MOV64_IMM(si->dst_reg, 0);
> +#endif
> +               break;
> +
>         }
>         return insn - insn_buf;
>  }
> --
> 2.20.1
>

On Fri, Apr 12, 2019 at 3:01 AM Alban Crequy <alban.crequy@gmail.com> wrote:
>
> From: Alban Crequy <alban@kinvolk.io>
>
> sockops programs can now access the network namespace inode via
> (struct bpf_sock_ops)->netns. This can be useful to apply different
> policies on different network namespaces.
>
> In the unlikely case where network namespaces are not compiled in
> (CONFIG_NET_NS=n), the verifier will not allow access to ->netns.
>
> Signed-off-by: Alban Crequy <alban@kinvolk.io>
> ---
>  include/uapi/linux/bpf.h |  1 +
>  net/core/filter.c        | 40 ++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 41 insertions(+)
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 31a27dd337dc..5afaab25f205 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -3069,6 +3069,7 @@ struct bpf_sock_ops {
>         __u32 sk_txhash;
>         __u64 bytes_received;
>         __u64 bytes_acked;
> +       __u64 netns;
>  };

stat /proc/self/ns/net
returns inode and device.
inum only is not enough to identify netns.
Both need to be exposed. See netns_dev/netns_ino in bpf.h