[PATCH v2 bpf-next/net 1/8] tcp: Save lock_sock() for memcg in inet_csk_accept().

[Kuniyuki Iwashima <kuniyu@google.com>]

If memcg is enabled, accept() acquires lock_sock() twice for each new
TCP/MPTCP socket in inet_csk_accept() and __inet_accept().

Let's move memcg operations from inet_csk_accept() to __inet_accept().

This makes easier to add a BPF hook that covers sk_prot.memory_allocated
users (TCP, MPTCP, SCTP) in a single place.

Two notes:

1)
SCTP somehow allocates a new socket by sk_alloc() in sk->sk_prot->accept()
and clones fields manually, instead of using sk_clone_lock().

For SCTP, mem_cgroup_sk_alloc() has been called before __inet_accept(),
so I added the protocol tests in __inet_accept(), but this can be removed
once SCTP uses sk_clone_lock().

2)
The single if block is separated into two because we will add a new bpf
hook between the blocks, where a bpf prog can add a flag in sk->sk_memcg.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 net/ipv4/af_inet.c              | 22 ++++++++++++++++++++++
 net/ipv4/inet_connection_sock.c | 25 -------------------------
 2 files changed, 22 insertions(+), 25 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 76e38092cd8a..ae83ecda3983 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -753,6 +753,28 @@ EXPORT_SYMBOL(inet_stream_connect);
 
 void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *newsk)
 {
+	gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL;
+
+	/* TODO: use sk_clone_lock() in SCTP and remove protocol checks */
+	if (mem_cgroup_sockets_enabled &&
+	    (!IS_ENABLED(CONFIG_IP_SCTP) ||
+	     sk_is_tcp(newsk) || sk_is_mptcp(newsk))) {
+		mem_cgroup_sk_alloc(newsk);
+		kmem_cache_charge(newsk, gfp);
+	}
+
+	if (mem_cgroup_sk_enabled(newsk)) {
+		int amt;
+
+		/* The socket has not been accepted yet, no need
+		 * to look at newsk->sk_wmem_queued.
+		 */
+		amt = sk_mem_pages(newsk->sk_forward_alloc +
+				   atomic_read(&newsk->sk_rmem_alloc));
+		if (amt)
+			mem_cgroup_sk_charge(newsk, amt, gfp);
+	}
+
 	sock_rps_record_flow(newsk);
 	WARN_ON(!((1 << newsk->sk_state) &
 		  (TCPF_ESTABLISHED | TCPF_SYN_RECV |
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 0ef1eacd539d..ed10b959a906 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -708,31 +708,6 @@ struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg)
 
 	release_sock(sk);
 
-	if (mem_cgroup_sockets_enabled) {
-		gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL;
-		int amt = 0;
-
-		/* atomically get the memory usage, set and charge the
-		 * newsk->sk_memcg.
-		 */
-		lock_sock(newsk);
-
-		mem_cgroup_sk_alloc(newsk);
-		if (mem_cgroup_from_sk(newsk)) {
-			/* The socket has not been accepted yet, no need
-			 * to look at newsk->sk_wmem_queued.
-			 */
-			amt = sk_mem_pages(newsk->sk_forward_alloc +
-					   atomic_read(&newsk->sk_rmem_alloc));
-		}
-
-		if (amt)
-			mem_cgroup_sk_charge(newsk, amt, gfp);
-		kmem_cache_charge(newsk, gfp);
-
-		release_sock(newsk);
-	}
-
 	if (req)
 		reqsk_put(req);
 
-- 
2.51.0.261.g7ce5a0a67e-goog