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

2 files changed, 42 insertions, 5 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index f753ab550525..5b86e47ef079 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -10044,11 +10044,13 @@ out:
 static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
 				    struct sock_reuseport *reuse,
 				    struct sock *sk, struct sk_buff *skb,
+				    struct sock *migrating_sk,
 				    u32 hash)
 {
 	reuse_kern->skb = skb;
 	reuse_kern->sk = sk;
 	reuse_kern->selected_sk = NULL;
+	reuse_kern->migrating_sk = migrating_sk;
 	reuse_kern->data_end = skb->data + skb_headlen(skb);
 	reuse_kern->hash = hash;
 	reuse_kern->reuseport_id = reuse->reuseport_id;
@@ -10057,12 +10059,13 @@ static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
 
 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)
 {
 	struct sk_reuseport_kern reuse_kern;
 	enum sk_action action;
 
-	bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash);
+	bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash);
 	action = BPF_PROG_RUN(prog, &reuse_kern);
 
 	if (action == SK_PASS)
@@ -10207,6 +10210,10 @@ sk_reuseport_is_valid_access(int off, int size,
 		info->reg_type = PTR_TO_SOCKET;
 		return size == sizeof(__u64);
 
+	case offsetof(struct sk_reuseport_md, migrating_sk):
+		info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL;
+		return size == sizeof(__u64);
+
 	/* Fields that allow narrowing */
 	case bpf_ctx_range(struct sk_reuseport_md, eth_protocol):
 		if (size < sizeof_field(struct sk_buff, protocol))
@@ -10283,6 +10290,10 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct sk_reuseport_md, sk):
 		SK_REUSEPORT_LOAD_FIELD(sk);
 		break;
+
+	case offsetof(struct sk_reuseport_md, migrating_sk):
+		SK_REUSEPORT_LOAD_FIELD(migrating_sk);
+		break;
 	}
 
 	return insn - insn_buf;
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index b239f8cd9d39..de5ee3ae86d5 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -377,13 +377,17 @@ void reuseport_stop_listen_sock(struct sock *sk)
 {
 	if (sk->sk_protocol == IPPROTO_TCP) {
 		struct sock_reuseport *reuse;
+		struct bpf_prog *prog;
 
 		spin_lock_bh(&reuseport_lock);
 
 		reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
 						  lockdep_is_held(&reuseport_lock));
+		prog = rcu_dereference_protected(reuse->prog,
+						 lockdep_is_held(&reuseport_lock));
 
-		if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req) {
+		if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req ||
+		    (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) {
 			/* Migration capable, move sk from the listening section
 			 * to the closed section.
 			 */
@@ -488,7 +492,7 @@ struct sock *reuseport_select_sock(struct sock *sk,
 			goto select_by_hash;
 
 		if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
-			sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash);
+			sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, NULL, hash);
 		else
 			sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len);
 
@@ -519,6 +523,8 @@ struct sock *reuseport_migrate_sock(struct sock *sk,
 {
 	struct sock_reuseport *reuse;
 	struct sock *nsk = NULL;
+	bool allocated = false;
+	struct bpf_prog *prog;
 	u16 socks;
 	u32 hash;
 
@@ -536,10 +542,30 @@ struct sock *reuseport_migrate_sock(struct sock *sk,
 	smp_rmb();
 
 	hash = migrating_sk->sk_hash;
-	if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req)
+	prog = rcu_dereference(reuse->prog);
+	if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) {
+		if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req)
+			goto select_by_hash;
+		goto out;
+	}
+
+	if (!skb) {
+		skb = alloc_skb(0, GFP_ATOMIC);
+		if (!skb)
+			goto out;
+		allocated = true;
+	}
+
+	nsk = bpf_run_sk_reuseport(reuse, sk, prog, skb, migrating_sk, hash);
+
+	if (allocated)
+		kfree_skb(skb);
+
+select_by_hash:
+	if (!nsk)
 		nsk = reuseport_select_sock_by_hash(reuse, hash, socks);
 
-	if (nsk && unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt)))
+	if (IS_ERR_OR_NULL(nsk) || unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt)))
 		nsk = NULL;
 
 out: