[PATCH v2 mptcp-next] Squash-to: "mptcp: leverage the backlog for RX packet processing"

[Paolo Abeni <pabeni@redhat.com>]

If a subflow receives data before gaining the memcg while the msk
socket lock is held at accept time, or the PM locks the msk socket
while still unaccepted and subflows push data to it at the same time,
the mptcp_graph_subflows() can complete with a non empty backlog.

The msk will try to borrow such memory, but (some) of the skbs there
where not memcg charged. When the msk finally will return such accounted
memory, we should hit the same splat of #597.
[even if so far I was unable to replicate this scenario]

This patch tries to address such potential issue by:
- preventing the subflow from queuing data into the backlog after
  gaining the memcg. This ensure that at the end of the look all the
  skbs in the backlog (if any) are _not_ memory accounted.
- mem charge the backlog to msk
- 'restart' the subflow and spool any data waiting there.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/protocol.c | 46 ++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 44 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 5e9325c7ea9c..d6b08e1de358 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -4082,10 +4082,12 @@ static void mptcp_graph_subflows(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct sock *ssk;
+	int old_amt, amt;
+	bool slow;
 
 	mptcp_for_each_subflow(msk, subflow) {
-		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-		bool slow;
+		ssk = mptcp_subflow_tcp_sock(subflow);
 
 		slow = lock_sock_fast(ssk);
 
@@ -4095,8 +4097,48 @@ static void mptcp_graph_subflows(struct sock *sk)
 		if (!ssk->sk_socket)
 			mptcp_sock_graft(ssk, sk->sk_socket);
 
+		if (!mem_cgroup_from_sk(sk))
+			goto unlock;
+
 		__mptcp_inherit_cgrp_data(sk, ssk);
 		__mptcp_inherit_memcg(sk, ssk, GFP_KERNEL);
+
+		/* Prevent subflows from queueing data into the backlog
+		 * as soon as cg is set; note that we can't race
+		 * with __mptcp_close_ssk setting this bit for a really
+		 * closing socket, because we hold the msk socket lock here.
+		 */
+		subflow->closing = 1;
+
+unlock:
+		unlock_sock_fast(ssk, slow);
+	}
+
+	if (!mem_cgroup_from_sk(sk))
+		return;
+
+	/* Charge the bl memory, note that __sk_charge accounted for
+	 * fwd memory and rmem only
+	 */
+	mptcp_data_lock(sk);
+	old_amt = sk_mem_pages(sk->sk_forward_alloc +
+			       atomic_read(&sk->sk_rmem_alloc));
+	amt = sk_mem_pages(msk->backlog_len + sk->sk_forward_alloc +
+		     atomic_read(&sk->sk_rmem_alloc));
+	amt -= old_amt;
+	if (amt)
+		mem_cgroup_sk_charge(sk, amt, GFP_ATOMIC | __GFP_NOFAIL);
+	mptcp_data_unlock(sk);
+
+	/* Finally let the subflow restart queuing data. */
+	mptcp_for_each_subflow(msk, subflow) {
+		ssk = mptcp_subflow_tcp_sock(subflow);
+
+		slow = lock_sock_fast(ssk);
+		subflow->closing = 0;
+
+		if (mptcp_subflow_data_available(ssk))
+			mptcp_data_ready(sk, ssk);
 		unlock_sock_fast(ssk, slow);
 	}
 }
-- 
2.51.0