On Wed, May 06, 2020 at 02:54:58PM +0200, Jakub Sitnicki wrote:
> Add a new program type BPF_PROG_TYPE_SK_LOOKUP and a dedicated attach type
> called BPF_SK_LOOKUP. The new program kind is to be invoked by the
> transport layer when looking up a socket for a received packet.
>
> When called, SK_LOOKUP program can select a socket that will receive the
> packet. This serves as a mechanism to overcome the limits of what bind()
> API allows to express. Two use-cases driving this work are:
>
> (1) steer packets destined to an IP range, fixed port to a socket
>
> 192.0.2.0/24, port 80 -> NGINX socket
>
> (2) steer packets destined to an IP address, any port to a socket
>
> 198.51.100.1, any port -> L7 proxy socket
>
> In its run-time context, program receives information about the packet that
> triggered the socket lookup. Namely IP version, L4 protocol identifier, and
> address 4-tuple. Context can be further extended to include ingress
> interface identifier.
>
> To select a socket BPF program fetches it from a map holding socket
> references, like SOCKMAP or SOCKHASH, and calls bpf_sk_assign(ctx, sk, ...)
> helper to record the selection. Transport layer then uses the selected
> socket as a result of socket lookup.
>
> This patch only enables the user to attach an SK_LOOKUP program to a
> network namespace. Subsequent patches hook it up to run on local delivery
> path in ipv4 and ipv6 stacks.
>
> Suggested-by: Marek Majkowski <marek@xxxxxxxxxxxxxx>
> Reviewed-by: Lorenz Bauer <lmb@xxxxxxxxxxxxxx>
> Signed-off-by: Jakub Sitnicki <jakub@xxxxxxxxxxxxxx>
> ---
> include/linux/bpf_types.h | 2 +
> include/linux/filter.h | 23 ++++
> include/net/net_namespace.h | 1 +
> include/uapi/linux/bpf.h | 53 ++++++++
> kernel/bpf/syscall.c | 9 ++
> net/core/filter.c | 247 ++++++++++++++++++++++++++++++++++++
> scripts/bpf_helpers_doc.py | 9 +-
> 7 files changed, 343 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
> index 8345cdf553b8..08c2aef674ac 100644
> --- a/include/linux/bpf_types.h
> +++ b/include/linux/bpf_types.h
> @@ -64,6 +64,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2,
> #ifdef CONFIG_INET
> BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport,
> struct sk_reuseport_md, struct sk_reuseport_kern)
> +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_LOOKUP, sk_lookup,
> + struct bpf_sk_lookup, struct bpf_sk_lookup_kern)
> #endif
> #if defined(CONFIG_BPF_JIT)
> BPF_PROG_TYPE(BPF_PROG_TYPE_STRUCT_OPS, bpf_struct_ops,
> diff --git a/include/linux/filter.h b/include/linux/filter.h
> index af37318bb1c5..33254e840c8d 100644
> --- a/include/linux/filter.h
> +++ b/include/linux/filter.h
> @@ -1280,4 +1280,27 @@ struct bpf_sockopt_kern {
> s32 retval;
> };
>
> +struct bpf_sk_lookup_kern {
> + unsigned short family;
> + u16 protocol;
> + union {
> + struct {
> + __be32 saddr;
> + __be32 daddr;
> + } v4;
> + struct {
> + struct in6_addr saddr;
> + struct in6_addr daddr;
> + } v6;
> + };
> + __be16 sport;
> + u16 dport;
> + struct sock *selected_sk;
> +};
> +
> +int sk_lookup_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
> +int sk_lookup_prog_detach(const union bpf_attr *attr);
> +int sk_lookup_prog_query(const union bpf_attr *attr,
> + union bpf_attr __user *uattr);
> +
> #endif /* __LINUX_FILTER_H__ */
> diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
> index ab96fb59131c..70bf4888c94d 100644
> --- a/include/net/net_namespace.h
> +++ b/include/net/net_namespace.h
> @@ -163,6 +163,7 @@ struct net {
> struct net_generic __rcu *gen;
>
> struct bpf_prog __rcu *flow_dissector_prog;
> + struct bpf_prog __rcu *sk_lookup_prog;
>
> /* Note : following structs are cache line aligned */
> #ifdef CONFIG_XFRM
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index b3643e27e264..e4c61b63d4bc 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -187,6 +187,7 @@ enum bpf_prog_type {
> BPF_PROG_TYPE_STRUCT_OPS,
> BPF_PROG_TYPE_EXT,
> BPF_PROG_TYPE_LSM,
> + BPF_PROG_TYPE_SK_LOOKUP,
> };
>
> enum bpf_attach_type {
> @@ -218,6 +219,7 @@ enum bpf_attach_type {
> BPF_TRACE_FEXIT,
> BPF_MODIFY_RETURN,
> BPF_LSM_MAC,
> + BPF_SK_LOOKUP,
> __MAX_BPF_ATTACH_TYPE
> };
>
> @@ -3041,6 +3043,10 @@ union bpf_attr {
> *
> * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
> * Description
> + * Helper is overloaded depending on BPF program type. This
> + * description applies to **BPF_PROG_TYPE_SCHED_CLS** and
> + * **BPF_PROG_TYPE_SCHED_ACT** programs.
> + *
> * Assign the *sk* to the *skb*. When combined with appropriate
> * routing configuration to receive the packet towards the socket,
> * will cause *skb* to be delivered to the specified socket.
> @@ -3061,6 +3067,39 @@ union bpf_attr {
> * call from outside of TC ingress.
> * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport).
> *
> + * int bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
> + * Description
> + * Helper is overloaded depending on BPF program type. This
> + * description applies to **BPF_PROG_TYPE_SK_LOOKUP** programs.
> + *
> + * Select the *sk* as a result of a socket lookup.
> + *
> + * For the operation to succeed passed socket must be compatible
> + * with the packet description provided by the *ctx* object.
> + *
> + * L4 protocol (*IPPROTO_TCP* or *IPPROTO_UDP*) must be an exact
> + * match. While IP family (*AF_INET* or *AF_INET6*) must be
> + * compatible, that is IPv6 sockets that are not v6-only can be
> + * selected for IPv4 packets.
> + *
> + * Only full sockets can be selected. However, there is no need to
> + * call bpf_fullsock() before passing a socket as an argument to
> + * this helper.
> + *
> + * The *flags* argument must be zero.
> + * Return
> + * 0 on success, or a negative errno in case of failure.
> + *
> + * **-EAFNOSUPPORT** is socket family (*sk->family*) is not
> + * compatible with packet family (*ctx->family*).
> + *
> + * **-EINVAL** if unsupported flags were specified.
> + *
> + * **-EPROTOTYPE** if socket L4 protocol (*sk->protocol*) doesn't
> + * match packet protocol (*ctx->protocol*).
> + *
> + * **-ESOCKTNOSUPPORT** if socket is not a full socket.
> + *
> * u64 bpf_ktime_get_boot_ns(void)
> * Description
> * Return the time elapsed since system boot, in nanoseconds.
> @@ -4012,4 +4051,18 @@ struct bpf_pidns_info {
> __u32 pid;
> __u32 tgid;
> };
> +
> +/* User accessible data for SK_LOOKUP programs. Add new fields at the end. */
> +struct bpf_sk_lookup {
> + __u32 family; /* AF_INET, AF_INET6 */
> + __u32 protocol; /* IPPROTO_TCP, IPPROTO_UDP */
> + /* IP addresses allows 1, 2, and 4 bytes access */
> + __u32 src_ip4;
> + __u32 src_ip6[4];
> + __u32 src_port; /* network byte order */
> + __u32 dst_ip4;
> + __u32 dst_ip6[4];
> + __u32 dst_port; /* host byte order */
> +};
> +
> #endif /* _UAPI__LINUX_BPF_H__ */
> diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
> index bb1ab7da6103..26d643c171fd 100644
> --- a/kernel/bpf/syscall.c
> +++ b/kernel/bpf/syscall.c
> @@ -2729,6 +2729,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
> case BPF_CGROUP_GETSOCKOPT:
> case BPF_CGROUP_SETSOCKOPT:
> return BPF_PROG_TYPE_CGROUP_SOCKOPT;
> + case BPF_SK_LOOKUP:
It may be a good idea to enforce the "expected_attach_type ==
BPF_SK_LOOKUP" during prog load time in bpf_prog_load_check_attach().
The attr->expected_attach_type could be anything right now if I read
it correctly.
> + return BPF_PROG_TYPE_SK_LOOKUP;
> default:
> return BPF_PROG_TYPE_UNSPEC;
> }
> @@ -2778,6 +2780,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
> case BPF_PROG_TYPE_FLOW_DISSECTOR:
> ret = skb_flow_dissector_bpf_prog_attach(attr, prog);
> break;
> + case BPF_PROG_TYPE_SK_LOOKUP:
> + ret = sk_lookup_prog_attach(attr, prog);
> + break;
> case BPF_PROG_TYPE_CGROUP_DEVICE:
> case BPF_PROG_TYPE_CGROUP_SKB:
> case BPF_PROG_TYPE_CGROUP_SOCK:
> @@ -2818,6 +2823,8 @@ static int bpf_prog_detach(const union bpf_attr *attr)
> return lirc_prog_detach(attr);
> case BPF_PROG_TYPE_FLOW_DISSECTOR:
> return skb_flow_dissector_bpf_prog_detach(attr);
> + case BPF_PROG_TYPE_SK_LOOKUP:
> + return sk_lookup_prog_detach(attr);
> case BPF_PROG_TYPE_CGROUP_DEVICE:
> case BPF_PROG_TYPE_CGROUP_SKB:
> case BPF_PROG_TYPE_CGROUP_SOCK:
> @@ -2867,6 +2874,8 @@ static int bpf_prog_query(const union bpf_attr *attr,
> return lirc_prog_query(attr, uattr);
> case BPF_FLOW_DISSECTOR:
> return skb_flow_dissector_prog_query(attr, uattr);
> + case BPF_SK_LOOKUP:
> + return sk_lookup_prog_query(attr, uattr);
"# CONFIG_NET is not set" needs to be taken care.
> default:
> return -EINVAL;
> }
> diff --git a/net/core/filter.c b/net/core/filter.c
> index bc25bb1085b1..a00bdc70041c 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -9054,6 +9054,253 @@ const struct bpf_verifier_ops sk_reuseport_verifier_ops = {
>
> const struct bpf_prog_ops sk_reuseport_prog_ops = {
> };
> +
> +static DEFINE_MUTEX(sk_lookup_prog_mutex);
> +
> +int sk_lookup_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
> +{
> + struct net *net = current->nsproxy->net_ns;
> + int ret;
> +
> + if (unlikely(attr->attach_flags))
> + return -EINVAL;
> +
> + mutex_lock(&sk_lookup_prog_mutex);
> + ret = bpf_prog_attach_one(&net->sk_lookup_prog,
> + &sk_lookup_prog_mutex, prog,
> + attr->attach_flags);
> + mutex_unlock(&sk_lookup_prog_mutex);
> +
> + return ret;
> +}
> +
> +int sk_lookup_prog_detach(const union bpf_attr *attr)
> +{
> + struct net *net = current->nsproxy->net_ns;
> + int ret;
> +
> + if (unlikely(attr->attach_flags))
> + return -EINVAL;
> +
> + mutex_lock(&sk_lookup_prog_mutex);
> + ret = bpf_prog_detach_one(&net->sk_lookup_prog,
> + &sk_lookup_prog_mutex);
> + mutex_unlock(&sk_lookup_prog_mutex);
> +
> + return ret;
> +}
> +
> +int sk_lookup_prog_query(const union bpf_attr *attr,
> + union bpf_attr __user *uattr)
> +{
> + struct net *net;
> + int ret;
> +
> + net = get_net_ns_by_fd(attr->query.target_fd);
> + if (IS_ERR(net))
> + return PTR_ERR(net);
> +
> + ret = bpf_prog_query_one(&net->sk_lookup_prog, attr, uattr);
> +
> + put_net(net);
> + return ret;
> +}
> +
> +BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx,
> + struct sock *, sk, u64, flags)
> +{
> + if (unlikely(flags != 0))
> + return -EINVAL;
> + if (unlikely(!sk_fullsock(sk)))
May be ARG_PTR_TO_SOCKET instead?
> + return -ESOCKTNOSUPPORT;
> +
> + /* Check if socket is suitable for packet L3/L4 protocol */
> + if (sk->sk_protocol != ctx->protocol)
> + return -EPROTOTYPE;
> + if (sk->sk_family != ctx->family &&
> + (sk->sk_family == AF_INET || ipv6_only_sock(sk)))
> + return -EAFNOSUPPORT;
> +
> + /* Select socket as lookup result */
> + ctx->selected_sk = sk;
Could sk be a TCP_ESTABLISHED sk?
> + return 0;
> +}
> +
