udp: implement memory accounting helpers

Avoid using the generic helpers.
Use the receive queue spin lock to protect the memory
accounting operation, both on enqueue and on dequeue.

On dequeue perform partial memory reclaiming, trying to
leave a quantum of forward allocated memory.

On enqueue use a custom helper, to allow some optimizations:
- use a plain spin_lock() variant instead of the slightly
  costly spin_lock_irqsave(),
- avoid dst_force check, since the calling code has already
  dropped the skb dst
- avoid orphaning the skb, since skb_steal_sock() already did
  the work for us

The above needs custom memory reclaiming on shutdown, provided
by the udp_destruct_sock().

v5 -> v6:
  - don't orphan the skb on enqueue

v4 -> v5:
  - replace the mem_lock with the receive queue spin lock
  - ensure that the bh is always allowed to enqueue at least
    a skb, even if sk_rcvbuf is exceeded

v3 -> v4:
  - reworked memory accunting, simplifying the schema
  - provide an helper for both memory scheduling and enqueuing

v1 -> v2:
  - use a udp specific destrctor to perform memory reclaiming
  - remove a couple of helpers, unneeded after the above cleanup
  - do not reclaim memory on dequeue if not under memory
    pressure
  - reworked the fwd accounting schema to avoid potential
    integer overflow

Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 106 insertions, 0 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7d96dc2d3d08..be3c3312df8d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1172,6 +1172,112 @@ out:
 	return ret;
 }
 
+static void udp_rmem_release(struct sock *sk, int size, int partial)
+{
+	int amt;
+
+	atomic_sub(size, &sk->sk_rmem_alloc);
+
+	spin_lock_bh(&sk->sk_receive_queue.lock);
+	sk->sk_forward_alloc += size;
+	amt = (sk->sk_forward_alloc - partial) & ~(SK_MEM_QUANTUM - 1);
+	sk->sk_forward_alloc -= amt;
+	spin_unlock_bh(&sk->sk_receive_queue.lock);
+
+	if (amt)
+		__sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT);
+}
+
+static void udp_rmem_free(struct sk_buff *skb)
+{
+	udp_rmem_release(skb->sk, skb->truesize, 1);
+}
+
+int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct sk_buff_head *list = &sk->sk_receive_queue;
+	int rmem, delta, amt, err = -ENOMEM;
+	int size = skb->truesize;
+
+	/* try to avoid the costly atomic add/sub pair when the receive
+	 * queue is full; always allow at least a packet
+	 */
+	rmem = atomic_read(&sk->sk_rmem_alloc);
+	if (rmem && (rmem + size > sk->sk_rcvbuf))
+		goto drop;
+
+	/* we drop only if the receive buf is full and the receive
+	 * queue contains some other skb
+	 */
+	rmem = atomic_add_return(size, &sk->sk_rmem_alloc);
+	if ((rmem > sk->sk_rcvbuf) && (rmem > size))
+		goto uncharge_drop;
+
+	spin_lock(&list->lock);
+	if (size >= sk->sk_forward_alloc) {
+		amt = sk_mem_pages(size);
+		delta = amt << SK_MEM_QUANTUM_SHIFT;
+		if (!__sk_mem_raise_allocated(sk, delta, amt, SK_MEM_RECV)) {
+			err = -ENOBUFS;
+			spin_unlock(&list->lock);
+			goto uncharge_drop;
+		}
+
+		sk->sk_forward_alloc += delta;
+	}
+
+	sk->sk_forward_alloc -= size;
+
+	/* the skb owner in now the udp socket */
+	skb->sk = sk;
+	skb->destructor = udp_rmem_free;
+	skb->dev = NULL;
+	sock_skb_set_dropcount(sk, skb);
+
+	__skb_queue_tail(list, skb);
+	spin_unlock(&list->lock);
+
+	if (!sock_flag(sk, SOCK_DEAD))
+		sk->sk_data_ready(sk);
+
+	return 0;
+
+uncharge_drop:
+	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
+
+drop:
+	atomic_inc(&sk->sk_drops);
+	return err;
+}
+EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb);
+
+static void udp_destruct_sock(struct sock *sk)
+{
+	/* reclaim completely the forward allocated memory */
+	__skb_queue_purge(&sk->sk_receive_queue);
+	udp_rmem_release(sk, 0, 0);
+	inet_sock_destruct(sk);
+}
+
+int udp_init_sock(struct sock *sk)
+{
+	sk->sk_destruct = udp_destruct_sock;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(udp_init_sock);
+
+void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
+{
+	if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) {
+		bool slow = lock_sock_fast(sk);
+
+		sk_peek_offset_bwd(sk, len);
+		unlock_sock_fast(sk, slow);
+	}
+	consume_skb(skb);
+}
+EXPORT_SYMBOL_GPL(skb_consume_udp);
+
 /**
  *	first_packet_length	- return length of first packet in receive queue
  *	@sk: socket