net: sk_add_backlog() take rmem_alloc into account

Current socket backlog limit is not enough to really stop DDOS attacks,
because user thread spend many time to process a full backlog each
round, and user might crazy spin on socket lock.

We should add backlog size and receive_queue size (aka rmem_alloc) to
pace writers, and let user run without being slow down too much.

Introduce a sk_rcvqueues_full() helper, to avoid taking socket lock in
stress situations.

Under huge stress from a multiqueue/RPS enabled NIC, a single flow udp
receiver can now process ~200.000 pps (instead of ~100 pps before the
patch) on a 8 core machine.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 11 insertions, 2 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 07822280d953..cf12b1e61fa6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -256,7 +256,6 @@ struct sock {
                 struct sk_buff *head;
                 struct sk_buff *tail;
                 int len;
-                int limit;
         } sk_backlog;
         wait_queue_head_t       *sk_sleep;
         struct dst_entry        *sk_dst_cache;
@@ -608,10 +607,20 @@ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
         skb->next = NULL;
 }
 
+/*
+ * Take into account size of receive queue and backlog queue
+ */
+static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff *skb)
+{
+        unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc);
+
+        return qsize + skb->truesize > sk->sk_rcvbuf;
+}
+
 /* The per-socket spinlock must be held here. */
 static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
-        if (sk->sk_backlog.len >= max(sk->sk_backlog.limit, sk->sk_rcvbuf << 1))
+        if (sk_rcvqueues_full(sk, skb))
                 return -ENOBUFS;
 
         __sk_add_backlog(sk, skb);