static int packet_getname(struct socket *sock, struct sockaddr *uaddr,
int *uaddr_len, int peer)
{
struct net_device *dev;
struct sock *sk = sock->sk;
struct packet_sock *po = pkt_sk(sk);
struct sockaddr_ll *sll = (struct sockaddr_ll*)uaddr;
if (peer)
return -EOPNOTSUPP;
sll->sll_family = AF_PACKET;
sll->sll_ifindex = po->ifindex;
sll->sll_protocol = po->num;
dev = dev_get_by_index(po->ifindex);
if (dev) {
sll->sll_hatype = dev->type;
sll->sll_halen = dev->addr_len;
memcpy(sll->sll_addr, dev->dev_addr, dev->addr_len);
dev_put(dev);
} else {
sll->sll_hatype = 0; /* Bad: we have no ARPHRD_UNSPEC */
sll->sll_halen = 0;
}
*uaddr_len = sizeof(*sll);
return 0;
}
static int packet_mc_drop(struct sock *sk, struct packet_mreq *mreq)
{
struct packet_mclist *ml, **mlp;
rtnl_lock();
for (mlp = &pkt_sk(sk)->mclist; (ml = *mlp) != NULL; mlp = &ml->next) {
if (ml->ifindex == mreq->mr_ifindex &&
ml->type == mreq->mr_type &&
ml->alen == mreq->mr_alen &&
memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) {
if (--ml->count == 0) {
struct net_device *dev;
*mlp = ml->next;
dev = dev_get_by_index(ml->ifindex);
if (dev) {
packet_dev_mc(dev, ml, -1);
dev_put(dev);
}
kfree(ml);
}
rtnl_unlock();
return 0;
}
}
rtnl_unlock();
return -EADDRNOTAVAIL;
}
void packet_sock_destruct(struct sock *sk)
{
BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc));
BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc));
if (!sock_flag(sk, SOCK_DEAD)) {
printk("Attempt to release alive packet socket: %p\n", sk);
return;
}
if (pkt_sk(sk))
kfree(pkt_sk(sk));
atomic_dec(&packet_socks_nr);
#ifdef PACKET_REFCNT_DEBUG
printk(KERN_DEBUG "PACKET socket %p is free, %d are alive\n", sk, atomic_read(&packet_socks_nr));
#endif
}
static int
packet_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen)
{
struct sock *sk = sock->sk;
int ret;
if (level != SOL_PACKET)
return -ENOPROTOOPT;
switch(optname) {
#ifdef CONFIG_PACKET_MULTICAST
case PACKET_ADD_MEMBERSHIP:
case PACKET_DROP_MEMBERSHIP:
{
struct packet_mreq mreq;
if (optlen<sizeof(mreq))
return -EINVAL;
if (copy_from_user(&mreq,optval,sizeof(mreq)))
return -EFAULT;
if (optname == PACKET_ADD_MEMBERSHIP)
ret = packet_mc_add(sk, &mreq);
else
ret = packet_mc_drop(sk, &mreq);
return ret;
}
#endif
#ifdef CONFIG_PACKET_MMAP
case PACKET_RX_RING:
{
struct tpacket_req req;
if (optlen<sizeof(req))
return -EINVAL;
if (copy_from_user(&req,optval,sizeof(req)))
return -EFAULT;
return packet_set_ring(sk, &req, 0);
}
case PACKET_COPY_THRESH:
{
int val;
if (optlen!=sizeof(val))
return -EINVAL;
if (copy_from_user(&val,optval,sizeof(val)))
return -EFAULT;
pkt_sk(sk)->copy_thresh = val;
return 0;
}
#endif
default:
return -ENOPROTOOPT;
}
}
static int packet_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct packet_sock *po;
if (!sk)
return 0;
po = pkt_sk(sk);
write_lock_bh(&packet_sklist_lock);
sk_del_node_init(sk);
write_unlock_bh(&packet_sklist_lock);
/*
* Unhook packet receive handler.
*/
if (po->running) {
/*
* Remove the protocol hook
*/
dev_remove_pack(&po->prot_hook);
po->running = 0;
po->num = 0;
__sock_put(sk);
}
#ifdef CONFIG_PACKET_MULTICAST
packet_flush_mclist(sk);
#endif
#ifdef CONFIG_PACKET_MMAP
if (po->pg_vec) {
struct tpacket_req req;
memset(&req, 0, sizeof(req));
packet_set_ring(sk, &req, 1);
}
#endif
/*
* Now the socket is dead. No more input will appear.
*/
sock_orphan(sk);
sock->sk = NULL;
/* Purge queues */
skb_queue_purge(&sk->sk_receive_queue);
sock_put(sk);
return 0;
}
static int packet_do_bind(struct sock *sk, struct net_device *dev, int protocol)
{
struct packet_sock *po = pkt_sk(sk);
/*
* Detach an existing hook if present.
*/
lock_sock(sk);
spin_lock(&po->bind_lock);
if (po->running) {
__sock_put(sk);
po->running = 0;
po->num = 0;
spin_unlock(&po->bind_lock);
dev_remove_pack(&po->prot_hook);
spin_lock(&po->bind_lock);
}
po->num = protocol;
po->prot_hook.type = protocol;
po->prot_hook.dev = dev;
po->ifindex = dev ? dev->ifindex : 0;
if (protocol == 0)
goto out_unlock;
if (dev) {
if (dev->flags&IFF_UP) {
dev_add_pack(&po->prot_hook);
sock_hold(sk);
po->running = 1;
} else {
sk->sk_err = ENETDOWN;
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_error_report(sk);
}
} else {
dev_add_pack(&po->prot_hook);
sock_hold(sk);
po->running = 1;
}
out_unlock:
spin_unlock(&po->bind_lock);
release_sock(sk);
return 0;
}
static int packet_mc_add(struct sock *sk, struct packet_mreq *mreq)
{
struct packet_sock *po = pkt_sk(sk);
struct packet_mclist *ml, *i;
struct net_device *dev;
int err;
rtnl_lock();
err = -ENODEV;
dev = __dev_get_by_index(mreq->mr_ifindex);
if (!dev)
goto done;
err = -EINVAL;
if (mreq->mr_alen > dev->addr_len)
goto done;
err = -ENOBUFS;
i = (struct packet_mclist *)kmalloc(sizeof(*i), GFP_KERNEL);
if (i == NULL)
goto done;
err = 0;
for (ml = po->mclist; ml; ml = ml->next) {
if (ml->ifindex == mreq->mr_ifindex &&
ml->type == mreq->mr_type &&
ml->alen == mreq->mr_alen &&
memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) {
ml->count++;
/* Free the new element ... */
kfree(i);
goto done;
}
}
i->type = mreq->mr_type;
i->ifindex = mreq->mr_ifindex;
i->alen = mreq->mr_alen;
memcpy(i->addr, mreq->mr_address, i->alen);
i->count = 1;
i->next = po->mclist;
po->mclist = i;
packet_dev_mc(dev, i, +1);
done:
rtnl_unlock();
return err;
}
static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr,
int *uaddr_len, int peer)
{
struct net_device *dev;
struct sock *sk = sock->sk;
if (peer)
return -EOPNOTSUPP;
uaddr->sa_family = AF_PACKET;
dev = dev_get_by_index(pkt_sk(sk)->ifindex);
if (dev) {
strlcpy(uaddr->sa_data, dev->name, 15);
dev_put(dev);
} else
memset(uaddr->sa_data, 0, 14);
*uaddr_len = sizeof(*uaddr);
return 0;
}
static int packet_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
int len;
struct sock *sk = sock->sk;
struct packet_sock *po = pkt_sk(sk);
if (level != SOL_PACKET)
return -ENOPROTOOPT;
if (get_user(len,optlen))
return -EFAULT;
if (len < 0)
return -EINVAL;
switch(optname) {
case PACKET_STATISTICS:
{
struct tpacket_stats st;
if (len > sizeof(struct tpacket_stats))
len = sizeof(struct tpacket_stats);
spin_lock_bh(&sk->sk_receive_queue.lock);
st = po->stats;
memset(&po->stats, 0, sizeof(st));
spin_unlock_bh(&sk->sk_receive_queue.lock);
st.tp_packets += st.tp_drops;
if (copy_to_user(optval, &st, len))
return -EFAULT;
break;
}
default:
return -ENOPROTOOPT;
}
if (put_user(len, optlen))
return -EFAULT;
return 0;
}
static void packet_flush_mclist(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
struct packet_mclist *ml;
if (!po->mclist)
return;
rtnl_lock();
while ((ml = po->mclist) != NULL) {
struct net_device *dev;
po->mclist = ml->next;
if ((dev = dev_get_by_index(ml->ifindex)) != NULL) {
packet_dev_mc(dev, ml, -1);
dev_put(dev);
}
kfree(ml);
}
rtnl_unlock();
}
static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
struct sock *sk=sock->sk;
char name[15];
struct net_device *dev;
int err = -ENODEV;
/*
* Check legality
*/
if(addr_len!=sizeof(struct sockaddr))
return -EINVAL;
strlcpy(name,uaddr->sa_data,sizeof(name));
dev = dev_get_by_name(name);
if (dev) {
err = packet_do_bind(sk, dev, pkt_sk(sk)->num);
dev_put(dev);
}
return err;
}
static int packet_sendmsg(struct kiocb *iocb, 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;
unsigned short proto;
unsigned char *addr;
int ifindex, err, reserve = 0;
/*
* Get and verify the address.
*/
if (saddr == NULL) {
struct packet_opt *po = pkt_sk(sk);
ifindex = po->ifindex;
proto = po->num;
addr = NULL;
} else {
err = -EINVAL;
if (msg->msg_namelen < sizeof(struct sockaddr_ll))
goto out;
ifindex = saddr->sll_ifindex;
proto = saddr->sll_protocol;
addr = saddr->sll_addr;
}
dev = dev_get_by_index(ifindex);
err = -ENXIO;
if (dev == NULL)
goto out_unlock;
if (sock->type == SOCK_RAW)
reserve = dev->hard_header_len;
err = -EMSGSIZE;
if (len > dev->mtu+reserve)
goto out_unlock;
skb = sock_alloc_send_skb(sk, len + LL_RESERVED_SPACE(dev),
msg->msg_flags & MSG_DONTWAIT, &err);
if (skb==NULL)
goto out_unlock;
skb_reserve(skb, LL_RESERVED_SPACE(dev));
skb->nh.raw = skb->data;
if (dev->hard_header) {
int res;
err = -EINVAL;
res = dev->hard_header(skb, dev, ntohs(proto), addr, NULL, len);
if (sock->type != SOCK_DGRAM) {
skb->tail = skb->data;
skb->len = 0;
} else if (res < 0)
goto out_free;
}
/* Returns -EFAULT on error */
err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len);
if (err)
goto out_free;
skb->protocol = proto;
skb->dev = dev;
skb->priority = sk->sk_priority;
err = -ENETDOWN;
if (!(dev->flags & IFF_UP))
goto out_free;
/*
* Now send it
*/
/*add by p44980 2008.07.30 将dhcp交互报文的优先级设置为中*/
{
if (skb->protocol == __constant_htons(ETH_P_IP))
{
struct iphdr *iph = skb->nh.iph;
if (iph->protocol == __constant_htons(IPPROTO_UDP))
{
struct udphdr *udph = (void *)iph + iph->ihl*4;
if (udph->dest == 67 || udph->dest == 68)
{
u_int16_t diffs[2];
//优先级设置为中
skb->nfmark = (skb->nfmark & 0xFFFFFF00) | 0x00000022;
diffs[0] = htons(iph->tos) ^ 0xFFFF;
//dscp标记为100010 (AF41)
iph->tos = 0x88;
//重新计算校验和
diffs[1] = htons(iph->tos);
iph->check = csum_fold(csum_partial((char *)diffs,
sizeof(diffs),
iph->check^0xFFFF));
}
}
}
}
/*end by p44980 2008.07.30 将dhcp交互报文的优先级设置为中*/
err = dev_queue_xmit(skb);
if (err > 0 && (err = net_xmit_errno(err)) != 0)
goto out_unlock;
dev_put(dev);
return(len);
out_free:
kfree_skb(skb);
out_unlock:
if (dev)
dev_put(dev);
out:
return err;
}
static int packet_sendmsg(struct kiocb *iocb, 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;
unsigned short proto;
unsigned char *addr;
int ifindex, err, reserve = 0;
/*
* Get and verify the address.
*/
if (saddr == NULL) {
struct packet_sock *po = pkt_sk(sk);
ifindex = po->ifindex;
proto = po->num;
addr = NULL;
} else {
err = -EINVAL;
if (msg->msg_namelen < sizeof(struct sockaddr_ll))
goto out;
ifindex = saddr->sll_ifindex;
proto = saddr->sll_protocol;
addr = saddr->sll_addr;
}
dev = dev_get_by_index(ifindex);
err = -ENXIO;
if (dev == NULL)
goto out_unlock;
if (sock->type == SOCK_RAW)
reserve = dev->hard_header_len;
err = -EMSGSIZE;
if (len > dev->mtu+reserve)
goto out_unlock;
skb = sock_alloc_send_skb(sk, len + LL_RESERVED_SPACE(dev),
msg->msg_flags & MSG_DONTWAIT, &err);
if (skb==NULL)
goto out_unlock;
skb_reserve(skb, LL_RESERVED_SPACE(dev));
skb->nh.raw = skb->data;
if (dev->hard_header) {
int res;
err = -EINVAL;
res = dev->hard_header(skb, dev, ntohs(proto), addr, NULL, len);
if (sock->type != SOCK_DGRAM) {
skb->tail = skb->data;
skb->len = 0;
} else if (res < 0)
goto out_free;
}
/* Returns -EFAULT on error */
err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len);
if (err)
goto out_free;
skb->protocol = proto;
skb->dev = dev;
skb->priority = sk->sk_priority;
err = -ENETDOWN;
if (!(dev->flags & IFF_UP))
goto out_free;
/*
* Now send it
*/
err = dev_queue_xmit(skb);
if (err > 0 && (err = net_xmit_errno(err)) != 0)
goto out_unlock;
dev_put(dev);
return(len);
out_free:
kfree_skb(skb);
out_unlock:
if (dev)
dev_put(dev);
out:
return err;
}
static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt)
{
struct sock *sk;
struct packet_sock *po;
struct sockaddr_ll *sll;
struct tpacket_hdr *h;
u8 * skb_head = skb->data;
int skb_len = skb->len;
unsigned snaplen;
unsigned long status = TP_STATUS_LOSING|TP_STATUS_USER;
unsigned short macoff, netoff;
struct sk_buff *copy_skb = NULL;
if (skb->pkt_type == PACKET_LOOPBACK)
goto drop;
sk = pt->af_packet_priv;
po = pkt_sk(sk);
if (dev->hard_header) {
if (sk->sk_type != SOCK_DGRAM)
skb_push(skb, skb->data - skb->mac.raw);
else if (skb->pkt_type == PACKET_OUTGOING) {
/* Special case: outgoing packets have ll header at head */
skb_pull(skb, skb->nh.raw - skb->data);
if (skb->ip_summed == CHECKSUM_HW)
status |= TP_STATUS_CSUMNOTREADY;
}
}
snaplen = skb->len;
if (sk->sk_filter) {
unsigned res = run_filter(skb, sk, snaplen);
if (res == 0)
goto drop_n_restore;
if (snaplen > res)
snaplen = res;
}
if (sk->sk_type == SOCK_DGRAM) {
macoff = netoff = TPACKET_ALIGN(TPACKET_HDRLEN) + 16;
} else {
unsigned maclen = skb->nh.raw - skb->data;
netoff = TPACKET_ALIGN(TPACKET_HDRLEN + (maclen < 16 ? 16 : maclen));
macoff = netoff - maclen;
}
if (macoff + snaplen > po->frame_size) {
if (po->copy_thresh &&
atomic_read(&sk->sk_rmem_alloc) + skb->truesize <
(unsigned)sk->sk_rcvbuf) {
if (skb_shared(skb)) {
copy_skb = skb_clone(skb, GFP_ATOMIC);
} else {
copy_skb = skb_get(skb);
skb_head = skb->data;
}
if (copy_skb)
skb_set_owner_r(copy_skb, sk);
}
snaplen = po->frame_size - macoff;
if ((int)snaplen < 0)
snaplen = 0;
}
if (snaplen > skb->len-skb->data_len)
snaplen = skb->len-skb->data_len;
spin_lock(&sk->sk_receive_queue.lock);
h = (struct tpacket_hdr *)packet_lookup_frame(po, po->head);
if (h->tp_status)
goto ring_is_full;
po->head = po->head != po->frame_max ? po->head+1 : 0;
po->stats.tp_packets++;
if (copy_skb) {
status |= TP_STATUS_COPY;
__skb_queue_tail(&sk->sk_receive_queue, copy_skb);
}
if (!po->stats.tp_drops)
status &= ~TP_STATUS_LOSING;
spin_unlock(&sk->sk_receive_queue.lock);
memcpy((u8*)h + macoff, skb->data, snaplen);
h->tp_len = skb->len;
h->tp_snaplen = snaplen;
h->tp_mac = macoff;
h->tp_net = netoff;
if (skb->stamp.tv_sec == 0) {
do_gettimeofday(&skb->stamp);
sock_enable_timestamp(sk);
}
h->tp_sec = skb->stamp.tv_sec;
h->tp_usec = skb->stamp.tv_usec;
sll = (struct sockaddr_ll*)((u8*)h + TPACKET_ALIGN(sizeof(*h)));
sll->sll_halen = 0;
if (dev->hard_header_parse)
sll->sll_halen = dev->hard_header_parse(skb, sll->sll_addr);
sll->sll_family = AF_PACKET;
sll->sll_hatype = dev->type;
sll->sll_protocol = skb->protocol;
sll->sll_pkttype = skb->pkt_type;
sll->sll_ifindex = dev->ifindex;
h->tp_status = status;
mb();
{
struct page *p_start, *p_end;
u8 *h_end = (u8 *)h + macoff + snaplen - 1;
p_start = virt_to_page(h);
p_end = virt_to_page(h_end);
while (p_start <= p_end) {
flush_dcache_page(p_start);
p_start++;
}
}
sk->sk_data_ready(sk, 0);
drop_n_restore:
if (skb_head != skb->data && skb_shared(skb)) {
skb->data = skb_head;
skb->len = skb_len;
}
drop:
kfree_skb(skb);
return 0;
ring_is_full:
po->stats.tp_drops++;
spin_unlock(&sk->sk_receive_queue.lock);
sk->sk_data_ready(sk, 0);
if (copy_skb)
kfree_skb(copy_skb);
goto drop_n_restore;
}
static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt)
{
struct sock *sk;
struct sockaddr_ll *sll;
struct packet_sock *po;
u8 * skb_head = skb->data;
int skb_len = skb->len;
unsigned snaplen;
if (skb->pkt_type == PACKET_LOOPBACK)
goto drop;
sk = pt->af_packet_priv;
po = pkt_sk(sk);
skb->dev = dev;
if (dev->hard_header) {
/* The device has an explicit notion of ll header,
exported to higher levels.
Otherwise, the device hides datails of it frame
structure, so that corresponding packet head
never delivered to user.
*/
if (sk->sk_type != SOCK_DGRAM)
skb_push(skb, skb->data - skb->mac.raw);
else if (skb->pkt_type == PACKET_OUTGOING) {
/* Special case: outgoing packets have ll header at head */
skb_pull(skb, skb->nh.raw - skb->data);
}
}
snaplen = skb->len;
if (sk->sk_filter) {
unsigned res = run_filter(skb, sk, snaplen);
if (res == 0)
goto drop_n_restore;
if (snaplen > res)
snaplen = res;
}
if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
(unsigned)sk->sk_rcvbuf)
goto drop_n_acct;
if (skb_shared(skb)) {
struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
if (nskb == NULL)
goto drop_n_acct;
if (skb_head != skb->data) {
skb->data = skb_head;
skb->len = skb_len;
}
kfree_skb(skb);
skb = nskb;
}
sll = (struct sockaddr_ll*)skb->cb;
sll->sll_family = AF_PACKET;
sll->sll_hatype = dev->type;
sll->sll_protocol = skb->protocol;
sll->sll_pkttype = skb->pkt_type;
sll->sll_ifindex = dev->ifindex;
sll->sll_halen = 0;
if (dev->hard_header_parse)
sll->sll_halen = dev->hard_header_parse(skb, sll->sll_addr);
if (pskb_trim(skb, snaplen))
goto drop_n_acct;
skb_set_owner_r(skb, sk);
skb->dev = NULL;
dst_release(skb->dst);
skb->dst = NULL;
spin_lock(&sk->sk_receive_queue.lock);
po->stats.tp_packets++;
__skb_queue_tail(&sk->sk_receive_queue, skb);
spin_unlock(&sk->sk_receive_queue.lock);
sk->sk_data_ready(sk, skb->len);
return 0;
drop_n_acct:
spin_lock(&sk->sk_receive_queue.lock);
po->stats.tp_drops++;
spin_unlock(&sk->sk_receive_queue.lock);
drop_n_restore:
if (skb_head != skb->data && skb_shared(skb)) {
skb->data = skb_head;
skb->len = skb_len;
}
drop:
kfree_skb(skb);
return 0;
}
if (put_user(len, optlen))
return -EFAULT;
return 0;
}
static int packet_notifier(struct notifier_block *this, unsigned long msg, void *data)
{
struct sock *sk;
struct hlist_node *node;
struct net_device *dev = (struct net_device*)data;
read_lock(&packet_sklist_lock);
sk_for_each(sk, node, &packet_sklist) {
struct packet_sock *po = pkt_sk(sk);
switch (msg) {
case NETDEV_UNREGISTER:
#ifdef CONFIG_PACKET_MULTICAST
if (po->mclist)
packet_dev_mclist(dev, po->mclist, -1);
// fallthrough
#endif
case NETDEV_DOWN:
if (dev->ifindex == po->ifindex) {
spin_lock(&po->bind_lock);
if (po->running) {
__dev_remove_pack(&po->prot_hook);
__sock_put(sk);
po->running = 0;
static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t len, int flags)
{
struct sock *sk = sock->sk;
struct sk_buff *skb;
int copied, err;
err = -EINVAL;
if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT))
goto out;
#if 0
/* What error should we return now? EUNATTACH? */
if (pkt_sk(sk)->ifindex < 0)
return -ENODEV;
#endif
/*
* 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
msg->msg_namelen = sizeof(struct sockaddr_ll);
/*
* Call the generic datagram receiver. This handles all sorts
* of horrible races and re-entrancy so we can forget about it
* in the protocol layers.
*
* Now it will return ENETDOWN, if device have just gone down,
* but then it will block.
*/
skb=skb_recv_datagram(sk,flags,flags&MSG_DONTWAIT,&err);
/*
* An error occurred so return it. Because skb_recv_datagram()
* handles the blocking we don't see and worry about blocking
* retries.
*/
if(skb==NULL)
goto out;
/*
* 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;
msg->msg_flags|=MSG_TRUNC;
}
err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
if (err)
goto out_free;
sock_recv_timestamp(msg, sk, skb);
if (msg->msg_name)
memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
/*
* Free or return the buffer as appropriate. Again this
* hides all the races and re-entrancy issues from us.
*/
err = (flags&MSG_TRUNC) ? skb->len : copied;
out_free:
skb_free_datagram(sk, skb);
out:
return err;
}
static int packet_create(struct socket *sock, int protocol)
{
struct sock *sk;
struct packet_sock *po;
int err;
if (!capable(CAP_NET_RAW))
return -EPERM;
if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW
#ifdef CONFIG_SOCK_PACKET
&& sock->type != SOCK_PACKET
#endif
)
return -ESOCKTNOSUPPORT;
sock->state = SS_UNCONNECTED;
err = -ENOBUFS;
sk = sk_alloc(PF_PACKET, GFP_KERNEL, &packet_proto, 1);
if (sk == NULL)
goto out;
sock->ops = &packet_ops;
#ifdef CONFIG_SOCK_PACKET
if (sock->type == SOCK_PACKET)
sock->ops = &packet_ops_spkt;
#endif
sock_init_data(sock, sk);
po = pkt_sk(sk);
sk->sk_family = PF_PACKET;
po->num = protocol;
sk->sk_destruct = packet_sock_destruct;
atomic_inc(&packet_socks_nr);
/*
* Attach a protocol block
*/
spin_lock_init(&po->bind_lock);
po->prot_hook.func = packet_rcv;
#ifdef CONFIG_SOCK_PACKET
if (sock->type == SOCK_PACKET)
po->prot_hook.func = packet_rcv_spkt;
#endif
po->prot_hook.af_packet_priv = sk;
if (protocol) {
po->prot_hook.type = protocol;
dev_add_pack(&po->prot_hook);
sock_hold(sk);
po->running = 1;
}
write_lock_bh(&packet_sklist_lock);
sk_add_node(sk, &packet_sklist);
write_unlock_bh(&packet_sklist_lock);
return(0);
out:
return err;
}
if (put_user(len, optlen))
return -EFAULT;
return 0;
}
static int packet_notifier(struct notifier_block *this, unsigned long msg, void *data)
{
struct sock *sk;
struct hlist_node *node;
struct net_device *dev = (struct net_device*)data;
read_lock(&packet_sklist_lock);
sk_for_each(sk, node, &packet_sklist) {
struct packet_opt *po = pkt_sk(sk);
switch (msg) {
case NETDEV_UNREGISTER:
#ifdef CONFIG_PACKET_MULTICAST
if (po->mclist)
packet_dev_mclist(dev, po->mclist, -1);
// fallthrough
#endif
case NETDEV_DOWN:
if (dev->ifindex == po->ifindex) {
spin_lock(&po->bind_lock);
if (po->running) {
__dev_remove_pack(&po->prot_hook);
__sock_put(sk);
po->running = 0;