1 files changed, 108 insertions, 25 deletions

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 88cfbc189558..279467b74eb7 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -237,6 +237,48 @@ struct packet_skb_cb {
 static void __fanout_unlink(struct sock *sk, struct packet_sock *po);
 static void __fanout_link(struct sock *sk, struct packet_sock *po);
 
+static int packet_direct_xmit(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	const struct net_device_ops *ops = dev->netdev_ops;
+	netdev_features_t features;
+	struct netdev_queue *txq;
+	u16 queue_map;
+	int ret;
+
+	if (unlikely(!netif_running(dev) ||
+		     !netif_carrier_ok(dev))) {
+		kfree_skb(skb);
+		return NET_XMIT_DROP;
+	}
+
+	features = netif_skb_features(skb);
+	if (skb_needs_linearize(skb, features) &&
+	    __skb_linearize(skb)) {
+		kfree_skb(skb);
+		return NET_XMIT_DROP;
+	}
+
+	queue_map = skb_get_queue_mapping(skb);
+	txq = netdev_get_tx_queue(dev, queue_map);
+
+	__netif_tx_lock_bh(txq);
+	if (unlikely(netif_xmit_frozen_or_stopped(txq))) {
+		ret = NETDEV_TX_BUSY;
+		kfree_skb(skb);
+		goto out;
+	}
+
+	ret = ops->ndo_start_xmit(skb, dev);
+	if (likely(dev_xmit_complete(ret)))
+		txq_trans_update(txq);
+	else
+		kfree_skb(skb);
+out:
+	__netif_tx_unlock_bh(txq);
+	return ret;
+}
+
 static struct net_device *packet_cached_dev_get(struct packet_sock *po)
 {
 	struct net_device *dev;
@@ -261,6 +303,16 @@ static void packet_cached_dev_reset(struct packet_sock *po)
 	RCU_INIT_POINTER(po->cached_dev, NULL);
 }
 
+static bool packet_use_direct_xmit(const struct packet_sock *po)
+{
+	return po->xmit == packet_direct_xmit;
+}
+
+static u16 packet_pick_tx_queue(struct net_device *dev)
+{
+	return (u16) raw_smp_processor_id() % dev->real_num_tx_queues;
+}
+
 /* register_prot_hook must be invoked with the po->bind_lock held,
  * or from a context in which asynchronous accesses to the packet
  * socket is not possible (packet_create()).
@@ -458,7 +510,8 @@ static void prb_shutdown_retire_blk_timer(struct packet_sock *po,
 {
 	struct tpacket_kbdq_core *pkc;
 
-	pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc;
+	pkc = tx_ring ? GET_PBDQC_FROM_RB(&po->tx_ring) :
+			GET_PBDQC_FROM_RB(&po->rx_ring);
 
 	spin_lock_bh(&rb_queue->lock);
 	pkc->delete_blk_timer = 1;
@@ -484,7 +537,8 @@ static void prb_setup_retire_blk_timer(struct packet_sock *po, int tx_ring)
 	if (tx_ring)
 		BUG();
 
-	pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc;
+	pkc = tx_ring ? GET_PBDQC_FROM_RB(&po->tx_ring) :
+			GET_PBDQC_FROM_RB(&po->rx_ring);
 	prb_init_blk_timer(po, pkc, prb_retire_rx_blk_timer_expired);
 }
 
@@ -542,7 +596,7 @@ static void init_prb_bdqc(struct packet_sock *po,
 			struct pgv *pg_vec,
 			union tpacket_req_u *req_u, int tx_ring)
 {
-	struct tpacket_kbdq_core *p1 = &rb->prb_bdqc;
+	struct tpacket_kbdq_core *p1 = GET_PBDQC_FROM_RB(rb);
 	struct tpacket_block_desc *pbd;
 
 	memset(p1, 0x0, sizeof(*p1));
@@ -606,7 +660,7 @@ static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc)
 static void prb_retire_rx_blk_timer_expired(unsigned long data)
 {
 	struct packet_sock *po = (struct packet_sock *)data;
-	struct tpacket_kbdq_core *pkc = &po->rx_ring.prb_bdqc;
+	struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
 	unsigned int frozen;
 	struct tpacket_block_desc *pbd;
 
@@ -909,7 +963,7 @@ static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb)
 static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc,
 			struct tpacket3_hdr *ppd)
 {
-	ppd->hv1.tp_rxhash = skb_get_rxhash(pkc->skb);
+	ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb);
 }
 
 static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc,
@@ -923,9 +977,11 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
 {
 	if (vlan_tx_tag_present(pkc->skb)) {
 		ppd->hv1.tp_vlan_tci = vlan_tx_tag_get(pkc->skb);
-		ppd->tp_status = TP_STATUS_VLAN_VALID;
+		ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto);
+		ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 	} else {
 		ppd->hv1.tp_vlan_tci = 0;
+		ppd->hv1.tp_vlan_tpid = 0;
 		ppd->tp_status = TP_STATUS_AVAILABLE;
 	}
 }
@@ -933,6 +989,7 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
 static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc,
 			struct tpacket3_hdr *ppd)
 {
+	ppd->hv1.tp_padding = 0;
 	prb_fill_vlan_info(pkc, ppd);
 
 	if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH)
@@ -1241,7 +1298,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 			if (!skb)
 				return 0;
 		}
-		skb_get_rxhash(skb);
+		skb_get_hash(skb);
 		idx = fanout_demux_hash(f, skb, num);
 		break;
 	case PACKET_FANOUT_LB:
@@ -1299,9 +1356,9 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
 	spin_unlock(&f->lock);
 }
 
-static bool match_fanout_group(struct packet_type *ptype, struct sock * sk)
+static bool match_fanout_group(struct packet_type *ptype, struct sock *sk)
 {
-	if (ptype->af_packet_priv == (void*)((struct packet_sock *)sk)->fanout)
+	if (ptype->af_packet_priv == (void *)((struct packet_sock *)sk)->fanout)
 		return true;
 
 	return false;
@@ -1758,6 +1815,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct timespec ts;
 	__u32 ts_status;
 
+	/* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT.
+	 * We may add members to them until current aligned size without forcing
+	 * userspace to call getsockopt(..., PACKET_HDRLEN, ...).
+	 */
+	BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h2)) != 32);
+	BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h3)) != 48);
+
 	if (skb->pkt_type == PACKET_LOOPBACK)
 		goto drop;
 
@@ -1864,11 +1928,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		h.h2->tp_nsec = ts.tv_nsec;
 		if (vlan_tx_tag_present(skb)) {
 			h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
-			status |= TP_STATUS_VLAN_VALID;
+			h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto);
+			status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 		} else {
 			h.h2->tp_vlan_tci = 0;
+			h.h2->tp_vlan_tpid = 0;
 		}
-		h.h2->tp_padding = 0;
+		memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding));
 		hdrlen = sizeof(*h.h2);
 		break;
 	case TPACKET_V3:
@@ -1882,6 +1948,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		h.h3->tp_net = netoff;
 		h.h3->tp_sec  = ts.tv_sec;
 		h.h3->tp_nsec = ts.tv_nsec;
+		memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding));
 		hdrlen = sizeof(*h.h3);
 		break;
 	default:
@@ -1992,9 +2059,10 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
-	skb_probe_transport_header(skb, 0);
 
-	if (po->tp_tx_has_off) {
+	if (!packet_use_direct_xmit(po))
+		skb_probe_transport_header(skb, 0);
+	if (unlikely(po->tp_tx_has_off)) {
 		int off_min, off_max, off;
 		off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll);
 		off_max = po->tx_ring.frame_size - tp_len;
@@ -2164,12 +2232,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 			}
 		}
 
+		skb_set_queue_mapping(skb, packet_pick_tx_queue(dev));
 		skb->destructor = tpacket_destruct_skb;
 		__packet_set_status(po, ph, TP_STATUS_SENDING);
 		atomic_inc(&po->tx_ring.pending);
 
 		status = TP_STATUS_SEND_REQUEST;
-		err = dev_queue_xmit(skb);
+		err = po->xmit(skb);
 		if (unlikely(err > 0)) {
 			err = net_xmit_errno(err);
 			if (err && __packet_get_status(po, ph) ==
@@ -2228,8 +2297,7 @@ static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad,
 	return skb;
 }
 
-static int packet_snd(struct socket *sock,
-			  struct msghdr *msg, size_t len)
+static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
@@ -2374,6 +2442,7 @@ static int packet_snd(struct socket *sock,
 	skb->dev = dev;
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
+	skb_set_queue_mapping(skb, packet_pick_tx_queue(dev));
 
 	if (po->has_vnet_hdr) {
 		if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
@@ -2394,16 +2463,12 @@ static int packet_snd(struct socket *sock,
 		len += vnet_hdr_len;
 	}
 
-	skb_probe_transport_header(skb, reserve);
-
+	if (!packet_use_direct_xmit(po))
+		skb_probe_transport_header(skb, reserve);
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
 
-	/*
-	 *	Now send it
-	 */
-
-	err = dev_queue_xmit(skb);
+	err = po->xmit(skb);
 	if (err > 0 && (err = net_xmit_errno(err)) != 0)
 		goto out_unlock;
 
@@ -2425,6 +2490,7 @@ static int packet_sendmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po = pkt_sk(sk);
+
 	if (po->tx_ring.pg_vec)
 		return tpacket_snd(po, msg);
 	else
@@ -2639,6 +2705,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	po = pkt_sk(sk);
 	sk->sk_family = PF_PACKET;
 	po->num = proto;
+	po->xmit = dev_queue_xmit;
 
 	packet_cached_dev_reset(po);
 
@@ -2813,11 +2880,12 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 		aux.tp_net = skb_network_offset(skb);
 		if (vlan_tx_tag_present(skb)) {
 			aux.tp_vlan_tci = vlan_tx_tag_get(skb);
-			aux.tp_status |= TP_STATUS_VLAN_VALID;
+			aux.tp_vlan_tpid = ntohs(skb->vlan_proto);
+			aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 		} else {
 			aux.tp_vlan_tci = 0;
+			aux.tp_vlan_tpid = 0;
 		}
-		aux.tp_padding = 0;
 		put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux);
 	}
 
@@ -3218,6 +3286,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		po->tp_tx_has_off = !!val;
 		return 0;
 	}
+	case PACKET_QDISC_BYPASS:
+	{
+		int val;
+
+		if (optlen != sizeof(val))
+			return -EINVAL;
+		if (copy_from_user(&val, optval, sizeof(val)))
+			return -EFAULT;
+
+		po->xmit = val ? packet_direct_xmit : dev_queue_xmit;
+		return 0;
+	}
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -3310,6 +3390,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	case PACKET_TX_HAS_OFF:
 		val = po->tp_tx_has_off;
 		break;
+	case PACKET_QDISC_BYPASS:
+		val = packet_use_direct_xmit(po);
+		break;
 	default:
 		return -ENOPROTOOPT;
 	}