diff mbox series

[v1,bpf-next,10/11] bpf: Call bpf_run_sk_reuseport() for socket migration.

Message ID 20201201144418.35045-11-kuniyu@amazon.co.jp
State New
Headers show
Series Socket migration for SO_REUSEPORT. | expand

Commit Message

Kuniyuki Iwashima Dec. 1, 2020, 2:44 p.m. UTC 
This patch supports socket migration by eBPF. If the attached type is
BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, 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.

There are two noteworthy points. The first is that we select a listening
socket in reuseport_detach_sock() and __reuseport_select_sock(), but we do
not have struct skb at closing a listener or retransmitting a SYN+ACK.
However, 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. The second is that we do not
have struct request_sock in unhash path, and the sk_hash of the listener is
always zero. Thus, we pass zero as hash to bpf_run_sk_reuseport().

Reviewed-by: Benjamin Herrenschmidt <benh@amazon.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
---
 net/core/filter.c          | 19 +++++++++++++++++++
 net/core/sock_reuseport.c  | 19 ++++++++++---------
 net/ipv4/inet_hashtables.c |  2 +-
 3 files changed, 30 insertions(+), 10 deletions(-)
diff mbox series

Patch

diff --git a/net/core/filter.c b/net/core/filter.c
index 1059d31847ef..2f2fb77cdb72 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -9871,10 +9871,29 @@  struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
 {
 	struct sk_reuseport_kern reuse_kern;
 	enum sk_action action;
+	bool allocated = false;
+
+	if (migration) {
+		/* cancel migration for possibly incapable eBPF program */
+		if (prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)
+			return ERR_PTR(-ENOTSUPP);
+
+		if (!skb) {
+			allocated = true;
+			skb = alloc_skb(0, GFP_ATOMIC);
+			if (!skb)
+				return ERR_PTR(-ENOMEM);
+		}
+	} else if (!skb) {
+		return NULL; /* fall back to select by hash */
+	}
 
 	bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash, migration);
 	action = BPF_PROG_RUN(prog, &reuse_kern);
 
+	if (allocated)
+		kfree_skb(skb);
+
 	if (action == SK_PASS)
 		return reuse_kern.selected_sk;
 	else
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 96d65b4c6974..6b475897b496 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -247,8 +247,15 @@  struct sock *reuseport_detach_sock(struct sock *sk)
 		prog = rcu_dereference(reuse->prog);
 
 		if (sk->sk_protocol == IPPROTO_TCP) {
-			if (reuse->num_socks && !prog)
-				nsk = i == reuse->num_socks ? reuse->socks[i - 1] : reuse->socks[i];
+			if (reuse->num_socks) {
+				if (prog)
+					nsk = bpf_run_sk_reuseport(reuse, sk, prog, NULL, 0,
+								   BPF_SK_REUSEPORT_MIGRATE_QUEUE);
+
+				if (!nsk)
+					nsk = i == reuse->num_socks ?
+						reuse->socks[i - 1] : reuse->socks[i];
+			}
 
 			reuse->num_closed_socks++;
 			reuse->socks[reuse->max_socks - reuse->num_closed_socks] = sk;
@@ -342,15 +349,9 @@  struct sock *__reuseport_select_sock(struct sock *sk, u32 hash,
 		if (!prog)
 			goto select_by_hash;
 
-		if (migration)
-			goto out;
-
-		if (!skb)
-			goto select_by_hash;
-
 		if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
 			sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash, migration);
-		else
+		else if (!skb)
 			sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len);
 
 select_by_hash:
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 545538a6bfac..59f58740c20d 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -699,7 +699,7 @@  void inet_unhash(struct sock *sk)
 
 	if (rcu_access_pointer(sk->sk_reuseport_cb)) {
 		nsk = reuseport_detach_sock(sk);
-		if (nsk)
+		if (!IS_ERR_OR_NULL(nsk))
 			inet_csk_reqsk_queue_migrate(sk, nsk);
 	}