#include <linux/wireless.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
+#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <linux/mutex.h>
#include <linux/if_vlan.h>
#include <linux/virtio_net.h>
+#include <linux/errqueue.h>
#ifdef CONFIG_INET
#include <net/inet_common.h>
unsigned char mr_address[MAX_ADDR_LEN];
};
-#ifdef CONFIG_PACKET_MMAP
static int packet_set_ring(struct sock *sk, struct tpacket_req *req,
int closing, int tx_ring);
struct packet_sock;
static int tpacket_snd(struct packet_sock *po, struct msghdr *msg);
-#endif
static void packet_flush_mclist(struct sock *sk);
/* struct sock has to be the first member of packet_sock */
struct sock sk;
struct tpacket_stats stats;
-#ifdef CONFIG_PACKET_MMAP
struct packet_ring_buffer rx_ring;
struct packet_ring_buffer tx_ring;
int copy_thresh;
-#endif
spinlock_t bind_lock;
struct mutex pg_vec_lock;
unsigned int running:1, /* prot_hook is attached*/
int ifindex; /* bound device */
__be16 num;
struct packet_mclist *mclist;
-#ifdef CONFIG_PACKET_MMAP
atomic_t mapped;
enum tpacket_versions tp_version;
unsigned int tp_hdrlen;
unsigned int tp_reserve;
unsigned int tp_loss:1;
-#endif
struct packet_type prot_hook ____cacheline_aligned_in_smp;
};
#define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb))
-#ifdef CONFIG_PACKET_MMAP
-
static void __packet_set_status(struct packet_sock *po, void *frame, int status)
{
union {
buff->head = buff->head != buff->frame_max ? buff->head+1 : 0;
}
-#endif
-
static inline struct packet_sock *pkt_sk(struct sock *sk)
{
return (struct packet_sock *)sk;
static void packet_sock_destruct(struct sock *sk)
{
+ skb_queue_purge(&sk->sk_error_queue);
+
WARN_ON(atomic_read(&sk->sk_rmem_alloc));
WARN_ON(atomic_read(&sk->sk_wmem_alloc));
skb->dev = dev;
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
+ err = sock_tx_timestamp(msg, sk, skb_tx(skb));
+ if (err < 0)
+ goto out_unlock;
dev_queue_xmit(skb);
rcu_read_unlock();
struct sk_filter *filter;
rcu_read_lock_bh();
- filter = rcu_dereference(sk->sk_filter);
+ filter = rcu_dereference_bh(sk->sk_filter);
if (filter != NULL)
res = sk_run_filter(skb, filter->insns, filter->len);
rcu_read_unlock_bh();
return 0;
}
-#ifdef CONFIG_PACKET_MMAP
static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
mutex_unlock(&po->pg_vec_lock);
return err;
}
-#endif
static inline struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad,
size_t reserve, size_t len,
err = skb_copy_datagram_from_iovec(skb, offset, msg->msg_iov, 0, len);
if (err)
goto out_free;
+ err = sock_tx_timestamp(msg, sk, skb_tx(skb));
+ if (err < 0)
+ goto out_free;
skb->protocol = proto;
skb->dev = dev;
static int packet_sendmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t len)
{
-#ifdef CONFIG_PACKET_MMAP
struct sock *sk = sock->sk;
struct packet_sock *po = pkt_sk(sk);
if (po->tx_ring.pg_vec)
return tpacket_snd(po, msg);
else
-#endif
return packet_snd(sock, msg, len);
}
struct sock *sk = sock->sk;
struct packet_sock *po;
struct net *net;
-#ifdef CONFIG_PACKET_MMAP
struct tpacket_req req;
-#endif
if (!sk)
return 0;
net = sock_net(sk);
po = pkt_sk(sk);
- write_lock_bh(&net->packet.sklist_lock);
- sk_del_node_init(sk);
+ spin_lock_bh(&net->packet.sklist_lock);
+ sk_del_node_init_rcu(sk);
sock_prot_inuse_add(net, sk->sk_prot, -1);
- write_unlock_bh(&net->packet.sklist_lock);
-
- /*
- * Unhook packet receive handler.
- */
+ spin_unlock_bh(&net->packet.sklist_lock);
+ spin_lock(&po->bind_lock);
if (po->running) {
/*
- * Remove the protocol hook
+ * Remove from protocol table
*/
- dev_remove_pack(&po->prot_hook);
po->running = 0;
po->num = 0;
+ __dev_remove_pack(&po->prot_hook);
__sock_put(sk);
}
+ spin_unlock(&po->bind_lock);
packet_flush_mclist(sk);
-#ifdef CONFIG_PACKET_MMAP
memset(&req, 0, sizeof(req));
if (po->rx_ring.pg_vec)
if (po->tx_ring.pg_vec)
packet_set_ring(sk, &req, 1, 1);
-#endif
+ synchronize_net();
/*
* Now the socket is dead. No more input will appear.
*/
-
sock_orphan(sk);
sock->sk = NULL;
po->running = 1;
}
- write_lock_bh(&net->packet.sklist_lock);
- sk_add_node(sk, &net->packet.sklist);
+ spin_lock_bh(&net->packet.sklist_lock);
+ sk_add_node_rcu(sk, &net->packet.sklist);
sock_prot_inuse_add(net, &packet_proto, 1);
- write_unlock_bh(&net->packet.sklist_lock);
+ spin_unlock_bh(&net->packet.sklist_lock);
+
return 0;
out:
return err;
}
+static int packet_recv_error(struct sock *sk, struct msghdr *msg, int len)
+{
+ struct sock_exterr_skb *serr;
+ struct sk_buff *skb, *skb2;
+ int copied, err;
+
+ err = -EAGAIN;
+ skb = skb_dequeue(&sk->sk_error_queue);
+ if (skb == NULL)
+ goto out;
+
+ copied = skb->len;
+ if (copied > len) {
+ msg->msg_flags |= MSG_TRUNC;
+ copied = len;
+ }
+ err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+ if (err)
+ goto out_free_skb;
+
+ sock_recv_timestamp(msg, sk, skb);
+
+ serr = SKB_EXT_ERR(skb);
+ put_cmsg(msg, SOL_PACKET, PACKET_TX_TIMESTAMP,
+ sizeof(serr->ee), &serr->ee);
+
+ msg->msg_flags |= MSG_ERRQUEUE;
+ err = copied;
+
+ /* Reset and regenerate socket error */
+ spin_lock_bh(&sk->sk_error_queue.lock);
+ sk->sk_err = 0;
+ if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
+ sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
+ spin_unlock_bh(&sk->sk_error_queue.lock);
+ sk->sk_error_report(sk);
+ } else
+ spin_unlock_bh(&sk->sk_error_queue.lock);
+
+out_free_skb:
+ kfree_skb(skb);
+out:
+ return err;
+}
+
/*
* Pull a packet from our receive queue and hand it to the user.
* If necessary we block.
int vnet_hdr_len = 0;
err = -EINVAL;
- if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT))
+ if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT|MSG_ERRQUEUE))
goto out;
#if 0
return -ENODEV;
#endif
+ if (flags & MSG_ERRQUEUE) {
+ err = packet_recv_error(sk, msg, len);
+ goto out;
+ }
+
/*
* Call the generic datagram receiver. This handles all sorts
* of horrible races and re-entrancy so we can forget about it
{
switch (i->type) {
case PACKET_MR_MULTICAST:
+ if (i->alen != dev->addr_len)
+ return -EINVAL;
if (what > 0)
- return dev_mc_add(dev, i->addr, i->alen, 0);
+ return dev_mc_add(dev, i->addr);
else
- return dev_mc_delete(dev, i->addr, i->alen, 0);
+ return dev_mc_del(dev, i->addr);
break;
case PACKET_MR_PROMISC:
return dev_set_promiscuity(dev, what);
return dev_set_allmulti(dev, what);
break;
case PACKET_MR_UNICAST:
+ if (i->alen != dev->addr_len)
+ return -EINVAL;
if (what > 0)
- return dev_unicast_add(dev, i->addr);
+ return dev_uc_add(dev, i->addr);
else
- return dev_unicast_delete(dev, i->addr);
+ return dev_uc_del(dev, i->addr);
break;
default:
break;
return ret;
}
-#ifdef CONFIG_PACKET_MMAP
case PACKET_RX_RING:
case PACKET_TX_RING:
{
po->tp_loss = !!val;
return 0;
}
-#endif
case PACKET_AUXDATA:
{
int val;
data = &val;
break;
-#ifdef CONFIG_PACKET_MMAP
case PACKET_VERSION:
if (len > sizeof(int))
len = sizeof(int);
val = po->tp_loss;
data = &val;
break;
-#endif
default:
return -ENOPROTOOPT;
}
struct net_device *dev = data;
struct net *net = dev_net(dev);
- read_lock(&net->packet.sklist_lock);
- sk_for_each(sk, node, &net->packet.sklist) {
+ rcu_read_lock();
+ sk_for_each_rcu(sk, node, &net->packet.sklist) {
struct packet_sock *po = pkt_sk(sk);
switch (msg) {
}
break;
case NETDEV_UP:
- spin_lock(&po->bind_lock);
- if (dev->ifindex == po->ifindex && po->num &&
- !po->running) {
- dev_add_pack(&po->prot_hook);
- sock_hold(sk);
- po->running = 1;
+ if (dev->ifindex == po->ifindex) {
+ spin_lock(&po->bind_lock);
+ if (po->num && !po->running) {
+ dev_add_pack(&po->prot_hook);
+ sock_hold(sk);
+ po->running = 1;
+ }
+ spin_unlock(&po->bind_lock);
}
- spin_unlock(&po->bind_lock);
break;
}
}
- read_unlock(&net->packet.sklist_lock);
+ rcu_read_unlock();
return NOTIFY_DONE;
}
case SIOCGIFDSTADDR:
case SIOCSIFDSTADDR:
case SIOCSIFFLAGS:
- if (!net_eq(sock_net(sk), &init_net))
- return -ENOIOCTLCMD;
return inet_dgram_ops.ioctl(sock, cmd, arg);
#endif
return 0;
}
-#ifndef CONFIG_PACKET_MMAP
-#define packet_mmap sock_no_mmap
-#define packet_poll datagram_poll
-#else
-
static unsigned int packet_poll(struct file *file, struct socket *sock,
poll_table *wait)
{
mutex_unlock(&po->pg_vec_lock);
return err;
}
-#endif
-
static const struct proto_ops packet_ops_spkt = {
.family = PF_PACKET,
};
#ifdef CONFIG_PROC_FS
-static inline struct sock *packet_seq_idx(struct net *net, loff_t off)
-{
- struct sock *s;
- struct hlist_node *node;
-
- sk_for_each(s, node, &net->packet.sklist) {
- if (!off--)
- return s;
- }
- return NULL;
-}
static void *packet_seq_start(struct seq_file *seq, loff_t *pos)
- __acquires(seq_file_net(seq)->packet.sklist_lock)
+ __acquires(RCU)
{
struct net *net = seq_file_net(seq);
- read_lock(&net->packet.sklist_lock);
- return *pos ? packet_seq_idx(net, *pos - 1) : SEQ_START_TOKEN;
+
+ rcu_read_lock();
+ return seq_hlist_start_head_rcu(&net->packet.sklist, *pos);
}
static void *packet_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct net *net = seq_file_net(seq);
- ++*pos;
- return (v == SEQ_START_TOKEN)
- ? sk_head(&net->packet.sklist)
- : sk_next((struct sock *)v) ;
+ return seq_hlist_next_rcu(v, &net->packet.sklist, pos);
}
static void packet_seq_stop(struct seq_file *seq, void *v)
- __releases(seq_file_net(seq)->packet.sklist_lock)
+ __releases(RCU)
{
- struct net *net = seq_file_net(seq);
- read_unlock(&net->packet.sklist_lock);
+ rcu_read_unlock();
}
static int packet_seq_show(struct seq_file *seq, void *v)
if (v == SEQ_START_TOKEN)
seq_puts(seq, "sk RefCnt Type Proto Iface R Rmem User Inode\n");
else {
- struct sock *s = v;
+ struct sock *s = sk_entry(v);
const struct packet_sock *po = pkt_sk(s);
seq_printf(seq,
static int __net_init packet_net_init(struct net *net)
{
- rwlock_init(&net->packet.sklist_lock);
+ spin_lock_init(&net->packet.sklist_lock);
INIT_HLIST_HEAD(&net->packet.sklist);
if (!proc_net_fops_create(net, "packet", 0, &packet_seq_fops))