xdp: fix race on generic receive path

Unlike driver mode, generic xdp receive could be triggered
by different threads on different CPU cores at the same time
leading to the fill and rx queue breakage. For example, this
could happen while sending packets from two processes to the
first interface of veth pair while the second part of it is
open with AF_XDP socket.

Need to take a lock for each generic receive to avoid race.

Fixes: c497176c ("xsk: add Rx receive functions and poll support")
Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Tested-by: William Tu <u9012063@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

include/net/xdp_sock.h

@@ -67,6 +67,8 @@ struct xdp_sock {
 	 * in the SKB destructor callback.
 	 */
 	spinlock_t tx_completion_lock;
+	/* Protects generic receive. */
+	spinlock_t rx_lock;
 	u64 rx_dropped;
 };
 

net/xdp/xsk.c

@@ -129,13 +129,17 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	u64 addr;
 	int err;
 
-	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
-		return -EINVAL;
+	spin_lock_bh(&xs->rx_lock);
+
+	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 
 	if (!xskq_peek_addr(xs->umem->fq, &addr) ||
 	    len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) {
-		xs->rx_dropped++;
-		return -ENOSPC;
+		err = -ENOSPC;
+		goto out_drop;
 	}
 
 	addr += xs->umem->headroom;
@@ -144,13 +148,21 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	memcpy(buffer, xdp->data_meta, len + metalen);
 	addr += metalen;
 	err = xskq_produce_batch_desc(xs->rx, addr, len);
-	if (!err) {
+	if (err)
+		goto out_drop;
+
 	xskq_discard_addr(xs->umem->fq);
-		xsk_flush(xs);
+	xskq_produce_flush_desc(xs->rx);
+
+	spin_unlock_bh(&xs->rx_lock);
+
+	xs->sk.sk_data_ready(&xs->sk);
 	return 0;
-	}
 
+out_drop:
 	xs->rx_dropped++;
+out_unlock:
+	spin_unlock_bh(&xs->rx_lock);
 	return err;
 }
 
@@ -787,6 +799,7 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 
 	xs = xdp_sk(sk);
 	mutex_init(&xs->mutex);
+	spin_lock_init(&xs->rx_lock);
 	spin_lock_init(&xs->tx_completion_lock);
 
 	mutex_lock(&net->xdp.lock);