bpf: Support socket migration by eBPF.

This patch introduces a new bpf_attach_type for BPF_PROG_TYPE_SK_REUSEPORT
to check if the attached eBPF program is capable of migrating sockets. When
the eBPF program is attached, we run it for socket migration if the
expected_attach_type is BPF_SK_REUSEPORT_SELECT_OR_MIGRATE or
net.ipv4.tcp_migrate_req is enabled.

Currently, the expected_attach_type is not enforced for the
BPF_PROG_TYPE_SK_REUSEPORT type of program. Thus, this commit follows the
earlier idea in the commit aac3fc320d94 ("bpf: Post-hooks for sys_bind") to
fix up the zero expected_attach_type in bpf_prog_load_fixup_attach_type().

Moreover, this patch adds a new field (migrating_sk) to sk_reuseport_md to
select a new listener based on the child socket. migrating_sk varies
depending on if it is migrating a request in the accept queue or during
3WHS.

  - accept_queue : sock (ESTABLISHED/SYN_RECV)
  - 3WHS         : request_sock (NEW_SYN_RECV)

In the eBPF program, we can select a new listener by
BPF_FUNC_sk_select_reuseport(). Also, we can cancel migration by returning
SK_DROP. This feature is useful when listeners have different settings at
the socket API level or when we want to free resources as soon as possible.

  - SK_PASS with selected_sk, select it as a new listener
  - SK_PASS with selected_sk NULL, fallbacks to the random selection
  - SK_DROP, cancel the migration.

There is a noteworthy point. We select a listening socket in three places,
but we do not have struct skb at closing a listener or retransmitting a
SYN+ACK. On the other hand, some helper functions do not expect skb is NULL
(e.g. skb_header_pointer() in BPF_FUNC_skb_load_bytes(), skb_tail_pointer()
in BPF_FUNC_skb_load_bytes_relative()). So we allocate an empty skb
temporarily before running the eBPF program.

Suggested-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/netdev/20201123003828.xjpjdtk4ygl6tg6h@kafai-mbp.dhcp.thefacebook.com/
Link: https://lore.kernel.org/netdev/20201203042402.6cskdlit5f3mw4ru@kafai-mbp.dhcp.thefacebook.com/
Link: https://lore.kernel.org/netdev/20201209030903.hhow5r53l6fmozjn@kafai-mbp.dhcp.thefacebook.com/
Link: https://lore.kernel.org/bpf/20210612123224.12525-10-kuniyu@amazon.co.jp

3 files changed, 18 insertions, 0 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 86dec5001ae2..f309fc1509f2 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2048,6 +2048,7 @@ struct sk_reuseport_kern {
 	struct sk_buff *skb;
 	struct sock *sk;
 	struct sock *selected_sk;
+	struct sock *migrating_sk;
 	void *data_end;
 	u32 hash;
 	u32 reuseport_id;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index c5ad7df029ed..688856e0b28a 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -996,11 +996,13 @@ void bpf_warn_invalid_xdp_action(u32 act);
 #ifdef CONFIG_INET
 struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
 				  struct bpf_prog *prog, struct sk_buff *skb,
+				  struct sock *migrating_sk,
 				  u32 hash);
 #else
 static inline struct sock *
 bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
 		     struct bpf_prog *prog, struct sk_buff *skb,
+		     struct sock *migrating_sk,
 		     u32 hash)
 {
 	return NULL;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f3b72588442b..bf9252c7381e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -994,6 +994,8 @@ enum bpf_attach_type {
 	BPF_SK_LOOKUP,
 	BPF_XDP,
 	BPF_SK_SKB_VERDICT,
+	BPF_SK_REUSEPORT_SELECT,
+	BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -5416,7 +5418,20 @@ struct sk_reuseport_md {
 	__u32 ip_protocol;	/* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
 	__u32 bind_inany;	/* Is sock bound to an INANY address? */
 	__u32 hash;		/* A hash of the packet 4 tuples */
+	/* When reuse->migrating_sk is NULL, it is selecting a sk for the
+	 * new incoming connection request (e.g. selecting a listen sk for
+	 * the received SYN in the TCP case).  reuse->sk is one of the sk
+	 * in the reuseport group. The bpf prog can use reuse->sk to learn
+	 * the local listening ip/port without looking into the skb.
+	 *
+	 * When reuse->migrating_sk is not NULL, reuse->sk is closed and
+	 * reuse->migrating_sk is the socket that needs to be migrated
+	 * to another listening socket.  migrating_sk could be a fullsock
+	 * sk that is fully established or a reqsk that is in-the-middle
+	 * of 3-way handshake.
+	 */
 	__bpf_md_ptr(struct bpf_sock *, sk);
+	__bpf_md_ptr(struct bpf_sock *, migrating_sk);
 };
 
 #define BPF_TAG_SIZE	8