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;
+
+ rcu_read_lock();
+ dev = rcu_dereference(po->cached_dev);
+ if (likely(dev))
+ dev_hold(dev);
+ rcu_read_unlock();
+
+ return dev;
+}
+
+static void packet_cached_dev_assign(struct packet_sock *po,
+ struct net_device *dev)
+{
+ rcu_assign_pointer(po->cached_dev, dev);
+}
+
+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) 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()).
static void register_prot_hook(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
+
if (!po->running) {
if (po->fanout)
__fanout_link(sk, po);
else
dev_add_pack(&po->prot_hook);
+
sock_hold(sk);
po->running = 1;
}
struct packet_sock *po = pkt_sk(sk);
po->running = 0;
+
if (po->fanout)
__fanout_unlink(sk, po);
else
__dev_remove_pack(&po->prot_hook);
+
__sock_put(sk);
if (sync) {
{
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(&rb_queue->lock);
+ spin_lock_bh(&rb_queue->lock);
pkc->delete_blk_timer = 1;
- spin_unlock(&rb_queue->lock);
+ spin_unlock_bh(&rb_queue->lock);
prb_del_retire_blk_timer(pkc);
}
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);
}
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));
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;
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;
struct sk_buff *skb;
struct net_device *dev;
__be16 proto;
- bool need_rls_dev = false;
int err, reserve = 0;
void *ph;
struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
mutex_lock(&po->pg_vec_lock);
- if (saddr == NULL) {
- dev = po->prot_hook.dev;
+ if (likely(saddr == NULL)) {
+ dev = packet_cached_dev_get(po);
proto = po->num;
addr = NULL;
} else {
proto = saddr->sll_protocol;
addr = saddr->sll_addr;
dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
- need_rls_dev = true;
}
err = -ENXIO;
if (unlikely(dev == NULL))
goto out;
-
- reserve = dev->hard_header_len;
-
err = -ENETDOWN;
if (unlikely(!(dev->flags & IFF_UP)))
goto out_put;
+ reserve = dev->hard_header_len;
+
size_max = po->tx_ring.frame_size
- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
}
}
+ 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) ==
__packet_set_status(po, ph, status);
kfree_skb(skb);
out_put:
- if (need_rls_dev)
- dev_put(dev);
+ dev_put(dev);
out:
mutex_unlock(&po->pg_vec_lock);
return err;
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;
struct sk_buff *skb;
struct net_device *dev;
__be16 proto;
- bool need_rls_dev = false;
unsigned char *addr;
int err, reserve = 0;
struct virtio_net_hdr vnet_hdr = { 0 };
* Get and verify the address.
*/
- if (saddr == NULL) {
- dev = po->prot_hook.dev;
+ if (likely(saddr == NULL)) {
+ dev = packet_cached_dev_get(po);
proto = po->num;
addr = NULL;
} else {
proto = saddr->sll_protocol;
addr = saddr->sll_addr;
dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
- need_rls_dev = true;
}
err = -ENXIO;
- if (dev == NULL)
+ if (unlikely(dev == NULL))
goto out_unlock;
- if (sock->type == SOCK_RAW)
- reserve = dev->hard_header_len;
-
err = -ENETDOWN;
- if (!(dev->flags & IFF_UP))
+ if (unlikely(!(dev->flags & IFF_UP)))
goto out_unlock;
+ if (sock->type == SOCK_RAW)
+ reserve = dev->hard_header_len;
if (po->has_vnet_hdr) {
vnet_hdr_len = sizeof(vnet_hdr);
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) {
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;
- if (need_rls_dev)
- dev_put(dev);
+ dev_put(dev);
return len;
out_free:
kfree_skb(skb);
out_unlock:
- if (dev && need_rls_dev)
+ if (dev)
dev_put(dev);
out:
return err;
{
struct sock *sk = sock->sk;
struct packet_sock *po = pkt_sk(sk);
+
if (po->tx_ring.pg_vec)
return tpacket_snd(po, msg);
else
spin_lock(&po->bind_lock);
unregister_prot_hook(sk, false);
+ packet_cached_dev_reset(po);
+
if (po->prot_hook.dev) {
dev_put(po->prot_hook.dev);
po->prot_hook.dev = NULL;
spin_lock(&po->bind_lock);
unregister_prot_hook(sk, true);
+
po->num = protocol;
po->prot_hook.type = protocol;
if (po->prot_hook.dev)
dev_put(po->prot_hook.dev);
- po->prot_hook.dev = dev;
+ po->prot_hook.dev = dev;
po->ifindex = dev ? dev->ifindex : 0;
+ packet_cached_dev_assign(po, dev);
+
if (protocol == 0)
goto out_unlock;
po = pkt_sk(sk);
sk->sk_family = PF_PACKET;
po->num = proto;
+ po->xmit = dev_queue_xmit;
+
+ packet_cached_dev_reset(po);
sk->sk_destruct = packet_sock_destruct;
sk_refcnt_debug_inc(sk);
struct sock *sk = sock->sk;
struct sk_buff *skb;
int copied, err;
- struct sockaddr_ll *sll;
int vnet_hdr_len = 0;
err = -EINVAL;
goto out_free;
}
- /*
- * If the address length field is there to be filled in, we fill
- * it in now.
- */
-
- sll = &PACKET_SKB_CB(skb)->sa.ll;
- if (sock->type == SOCK_PACKET)
- msg->msg_namelen = sizeof(struct sockaddr_pkt);
- else
- msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr);
-
- /*
- * You lose any data beyond the buffer you gave. If it worries a
- * user program they can ask the device for its MTU anyway.
+ /* You lose any data beyond the buffer you gave. If it worries
+ * a user program they can ask the device for its MTU
+ * anyway.
*/
-
copied = skb->len;
if (copied > len) {
copied = len;
sock_recv_ts_and_drops(msg, sk, skb);
- if (msg->msg_name)
+ if (msg->msg_name) {
+ /* If the address length field is there to be filled
+ * in, we fill it in now.
+ */
+ if (sock->type == SOCK_PACKET) {
+ msg->msg_namelen = sizeof(struct sockaddr_pkt);
+ } else {
+ struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+ msg->msg_namelen = sll->sll_halen +
+ offsetof(struct sockaddr_ll, sll_addr);
+ }
memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
msg->msg_namelen);
+ }
if (pkt_sk(sk)->auxdata) {
struct tpacket_auxdata aux;
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;
}
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;
}
sk->sk_error_report(sk);
}
if (msg == NETDEV_UNREGISTER) {
+ packet_cached_dev_reset(po);
po->ifindex = -1;
if (po->prot_hook.dev)
dev_put(po->prot_hook.dev);