static void __fanout_unlink(struct sock *sk, struct packet_sock *po);
static void __fanout_link(struct sock *sk, struct packet_sock *po);
+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);
+}
+
/* 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) {
pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc;
- 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);
}
p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov);
p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv;
+ p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv);
prb_init_ft_ops(p1, req_u);
prb_setup_retire_blk_timer(po, tx_ring);
prb_open_block(p1, pbd);
if ((int)snaplen < 0)
snaplen = 0;
}
+ } else if (unlikely(macoff + snaplen >
+ GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) {
+ u32 nval;
+
+ nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff;
+ pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n",
+ snaplen, nval, macoff);
+ snaplen = nval;
+ if (unlikely((int)snaplen < 0)) {
+ snaplen = 0;
+ macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len;
+ }
}
spin_lock(&sk->sk_receive_queue.lock);
h.raw = packet_current_rx_frame(po, skb,
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));
__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;
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);
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;
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;
sk->sk_family = PF_PACKET;
po->num = proto;
+ 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;
return -EOPNOTSUPP;
uaddr->sa_family = AF_PACKET;
+ memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data));
rcu_read_lock();
dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex);
if (dev)
- strncpy(uaddr->sa_data, dev->name, 14);
- else
- memset(uaddr->sa_data, 0, 14);
+ strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data));
rcu_read_unlock();
*uaddr_len = sizeof(*uaddr);
if (optlen != sizeof(val))
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
switch (val) {
case TPACKET_V1:
case TPACKET_V2:
case TPACKET_V3:
- po->tp_version = val;
- return 0;
+ break;
default:
return -EINVAL;
}
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->tp_version = val;
+ ret = 0;
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_RESERVE:
{
return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ if (val > INT_MAX)
+ return -EINVAL;
po->tp_reserve = val;
return 0;
}
if (po->tp_version == TPACKET_V3) {
lv = sizeof(struct tpacket_stats_v3);
+ st.stats3.tp_packets += st.stats3.tp_drops;
data = &st.stats3;
} else {
lv = sizeof(struct tpacket_stats);
+ st.stats1.tp_packets += st.stats1.tp_drops;
data = &st.stats1;
}
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);
/* Added to avoid minimal code churn */
struct tpacket_req *req = &req_u->req;
+ lock_sock(sk);
/* Opening a Tx-ring is NOT supported in TPACKET_V3 */
if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) {
WARN(1, "Tx-ring is not supported.\n");
goto out;
if (unlikely(req->tp_block_size & (PAGE_SIZE - 1)))
goto out;
+ if (po->tp_version >= TPACKET_V3 &&
+ (int)(req->tp_block_size -
+ BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0)
+ goto out;
if (unlikely(req->tp_frame_size < po->tp_hdrlen +
po->tp_reserve))
goto out;
rb->frames_per_block = req->tp_block_size/req->tp_frame_size;
if (unlikely(rb->frames_per_block <= 0))
goto out;
+ if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+ goto out;
if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
req->tp_frame_nr))
goto out;
goto out;
}
- lock_sock(sk);
/* Detach socket from network */
spin_lock(&po->bind_lock);
if (!tx_ring)
prb_shutdown_retire_blk_timer(po, tx_ring, rb_queue);
}
- release_sock(sk);
if (pg_vec)
free_pg_vec(pg_vec, order, req->tp_block_nr);
out:
+ release_sock(sk);
return err;
}