/**
* tipc_msg_build - create buffer chain containing specified header and data
* @mhdr: Message header, to be prepended to data
* @m: User message
* @offset: Posision in iov to start copying from
* @dsz: Total length of user data
* @pktmax: Max packet size that can be used
* @list: Buffer or chain of buffers to be returned to caller
*
* Returns message data size or errno: -ENOMEM, -EFAULT
*/
int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset,
int dsz, int pktmax, struct sk_buff_head *list)
{
int mhsz = msg_hdr_sz(mhdr);
int msz = mhsz + dsz;
int pktno = 1;
int pktsz;
int pktrem = pktmax;
int drem = dsz;
struct tipc_msg pkthdr;
struct sk_buff *skb;
char *pktpos;
int rc;
msg_set_size(mhdr, msz);
/* No fragmentation needed? */
if (likely(msz <= pktmax)) {
skb = tipc_buf_acquire(msz);
if (unlikely(!skb))
return -ENOMEM;
__skb_queue_tail(list, skb);
skb_copy_to_linear_data(skb, mhdr, mhsz);
pktpos = skb->data + mhsz;
if (!dsz || !memcpy_fromiovecend(pktpos, m->msg_iter.iov, offset,
dsz))
return dsz;
rc = -EFAULT;
goto error;
}
/* Prepare reusable fragment header */
tipc_msg_init(&pkthdr, MSG_FRAGMENTER, FIRST_FRAGMENT,
INT_H_SIZE, msg_destnode(mhdr));
msg_set_size(&pkthdr, pktmax);
msg_set_fragm_no(&pkthdr, pktno);
/* Prepare first fragment */
skb = tipc_buf_acquire(pktmax);
if (!skb)
return -ENOMEM;
__skb_queue_tail(list, skb);
pktpos = skb->data;
skb_copy_to_linear_data(skb, &pkthdr, INT_H_SIZE);
pktpos += INT_H_SIZE;
pktrem -= INT_H_SIZE;
skb_copy_to_linear_data_offset(skb, INT_H_SIZE, mhdr, mhsz);
pktpos += mhsz;
pktrem -= mhsz;
do {
if (drem < pktrem)
pktrem = drem;
if (memcpy_fromiovecend(pktpos, m->msg_iter.iov, offset, pktrem)) {
rc = -EFAULT;
goto error;
}
drem -= pktrem;
offset += pktrem;
if (!drem)
break;
/* Prepare new fragment: */
if (drem < (pktmax - INT_H_SIZE))
pktsz = drem + INT_H_SIZE;
else
pktsz = pktmax;
skb = tipc_buf_acquire(pktsz);
if (!skb) {
rc = -ENOMEM;
goto error;
}
__skb_queue_tail(list, skb);
msg_set_type(&pkthdr, FRAGMENT);
msg_set_size(&pkthdr, pktsz);
msg_set_fragm_no(&pkthdr, ++pktno);
skb_copy_to_linear_data(skb, &pkthdr, INT_H_SIZE);
pktpos = skb->data + INT_H_SIZE;
pktrem = pktsz - INT_H_SIZE;
} while (1);
msg_set_type(buf_msg(skb), LAST_FRAGMENT);
return dsz;
error:
__skb_queue_purge(list);
__skb_queue_head_init(list);
return rc;
}
static int rawv6_getfrag(const void *data, struct in6_addr *saddr,
char *buff, unsigned int offset, unsigned int len)
{
struct iovec *iov = (struct iovec *) data;
return memcpy_fromiovecend(buff, iov, offset, len);
}
static int raw_getrawfrag(const void *p, char *to, unsigned int offset,
unsigned int fraglen, struct sk_buff *skb)
{
struct rawfakehdr *rfh = (struct rawfakehdr *) p;
if (memcpy_fromiovecend(to, rfh->iov, offset, fraglen))
return -EFAULT;
if (!offset) {
struct iphdr *iph = (struct iphdr *)to;
if (!iph->saddr)
iph->saddr = rfh->saddr;
iph->check = 0;
iph->tot_len = htons(fraglen); /* This is right as you can't
frag RAW packets */
/*
* Deliberate breach of modularity to keep
* ip_build_xmit clean (well less messy).
*/
if (!iph->id)
ip_select_ident(iph, rfh->dst, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
return 0;
}
/**
* tipc_msg_build - create message using specified header and data
*
* Note: Caller must not hold any locks in case copy_from_user() is interrupted!
*
* Returns message data size or errno
*/
int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect,
unsigned int len, int max_size, struct sk_buff **buf)
{
int dsz, sz, hsz;
unsigned char *to;
dsz = len;
hsz = msg_hdr_sz(hdr);
sz = hsz + dsz;
msg_set_size(hdr, sz);
if (unlikely(sz > max_size)) {
*buf = NULL;
return dsz;
}
*buf = tipc_buf_acquire(sz);
if (!(*buf))
return -ENOMEM;
skb_copy_to_linear_data(*buf, hdr, hsz);
to = (*buf)->data + hsz;
if (len && memcpy_fromiovecend(to, msg_sect, 0, dsz)) {
kfree_skb(*buf);
*buf = NULL;
return -EFAULT;
}
return dsz;
}
static int raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
{
struct icmphdr icmph;
int err;
if (fl->proto != IPPROTO_ICMP)
return 0;
/* We only need the first two bytes. */
err = memcpy_fromiovecend((void *)&icmph, msg->msg_iov, 0, 2);
if (err)
return err;
fl->fl_icmp_type = icmph.type;
fl->fl_icmp_code = icmph.code;
return 0;
}
static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
void *from, size_t length,
struct rtable **rtp,
unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
struct iphdr *iph;
struct sk_buff *skb;
unsigned int iphlen;
int err;
struct rtable *rt = *rtp;
int hlen, tlen;
if (length > rt->dst.dev->mtu) {
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
rt->dst.dev->mtu);
return -EMSGSIZE;
}
if (flags&MSG_PROBE)
goto out;
hlen = LL_RESERVED_SPACE(rt->dst.dev);
tlen = rt->dst.dev->needed_tailroom;
skb = sock_alloc_send_skb(sk,
length + hlen + tlen + 15,
flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto error;
skb_reserve(skb, hlen);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
skb_dst_set(skb, &rt->dst);
*rtp = NULL;
skb_reset_network_header(skb);
iph = ip_hdr(skb);
skb_put(skb, length);
skb->ip_summed = CHECKSUM_NONE;
skb->transport_header = skb->network_header;
err = -EFAULT;
if (memcpy_fromiovecend((void *)iph, from, 0, length))
goto error_free;
iphlen = iph->ihl * 4;
/*
* We don't want to modify the ip header, but we do need to
* be sure that it won't cause problems later along the network
* stack. Specifically we want to make sure that iph->ihl is a
* sane value. If ihl points beyond the length of the buffer passed
* in, reject the frame as invalid
*/
err = -EINVAL;
if (iphlen > length)
goto error_free;
if (iphlen >= sizeof(*iph)) {
if (!iph->saddr)
iph->saddr = fl4->saddr;
iph->check = 0;
iph->tot_len = htons(length);
if (!iph->id)
ip_select_ident(skb, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
if (iph->protocol == IPPROTO_ICMP)
icmp_out_count(net, ((struct icmphdr *)
skb_transport_header(skb))->type);
err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL,
rt->dst.dev, dst_output);
if (err > 0)
err = net_xmit_errno(err);
if (err)
goto error;
out:
return 0;
error_free:
kfree_skb(skb);
error:
IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
if (err == -ENOBUFS && !inet->recverr)
err = 0;
return err;
}
static int raw_send_hdrinc(struct sock *sk, void *from, size_t length,
struct rtable *rt,
unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
struct iphdr *iph;
struct sk_buff *skb;
unsigned int iphlen;
int err;
if (length > rt->u.dst.dev->mtu) {
ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport,
rt->u.dst.dev->mtu);
return -EMSGSIZE;
}
if (flags&MSG_PROBE)
goto out;
skb = sock_alloc_send_skb(sk,
length + LL_ALLOCATED_SPACE(rt->u.dst.dev) + 15,
flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto error;
skb_reserve(skb, LL_RESERVED_SPACE(rt->u.dst.dev));
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
skb_dst_set(skb, dst_clone(&rt->u.dst));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
skb_put(skb, length);
skb->ip_summed = CHECKSUM_NONE;
skb->transport_header = skb->network_header;
err = memcpy_fromiovecend((void *)iph, from, 0, length);
if (err)
goto error_fault;
/* We don't modify invalid header */
iphlen = iph->ihl * 4;
if (iphlen >= sizeof(*iph) && iphlen <= length) {
if (!iph->saddr)
iph->saddr = rt->rt_src;
iph->check = 0;
iph->tot_len = htons(length);
if (!iph->id)
ip_select_ident(iph, &rt->u.dst, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
if (iph->protocol == IPPROTO_ICMP)
icmp_out_count(net, ((struct icmphdr *)
skb_transport_header(skb))->type);
err = NF_HOOK(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
dst_output);
if (err > 0)
err = net_xmit_errno(err);
if (err)
goto error;
out:
return 0;
error_fault:
err = -EFAULT;
kfree_skb(skb);
error:
IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
if (err == -ENOBUFS && !inet->recverr)
err = 0;
return err;
}
static int raw_send_hdrinc(struct sock *sk, void *from, int length,
struct rtable *rt,
unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
int hh_len;
struct iphdr *iph;
struct sk_buff *skb;
int err;
if (length > rt->u.dst.dev->mtu) {
ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport,
rt->u.dst.dev->mtu);
return -EMSGSIZE;
}
if (flags&MSG_PROBE)
goto out;
hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
skb = sock_alloc_send_skb(sk, length+hh_len+15,
flags&MSG_DONTWAIT, &err);
if (skb == NULL)
goto error;
skb_reserve(skb, hh_len);
skb->priority = sk->sk_priority;
skb->dst = dst_clone(&rt->u.dst);
skb->nh.iph = iph = (struct iphdr *)skb_put(skb, length);
skb->ip_summed = CHECKSUM_NONE;
skb->h.raw = skb->nh.raw;
err = memcpy_fromiovecend((void *)iph, from, 0, length);
if (err)
goto error_fault;
/* We don't modify invalid header */
if (length >= sizeof(*iph) && iph->ihl * 4 <= length) {
if (!iph->saddr)
iph->saddr = rt->rt_src;
iph->check = 0;
iph->tot_len = htons(length);
if (!iph->id)
ip_select_ident(iph, &rt->u.dst, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
err = NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
dst_output);
if (err > 0)
err = inet->recverr ? net_xmit_errno(err) : 0;
if (err)
goto error;
out:
return 0;
error_fault:
err = -EFAULT;
kfree_skb(skb);
error:
IP_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
return err;
}
static inline int
kni_vhost_net_tx(struct kni_dev *kni, struct msghdr *m,
unsigned offset, unsigned len)
{
struct rte_kni_mbuf *pkt_kva = NULL;
struct rte_kni_mbuf *pkt_va = NULL;
int ret;
KNI_DBG_TX("tx offset=%d, len=%d, iovlen=%d\n",
#ifdef HAVE_IOV_ITER_MSGHDR
offset, len, (int)m->msg_iter.iov->iov_len);
#else
offset, len, (int)m->msg_iov->iov_len);
#endif
/**
* Check if it has at least one free entry in tx_q and
* one entry in alloc_q.
*/
if (kni_fifo_free_count(kni->tx_q) == 0 ||
kni_fifo_count(kni->alloc_q) == 0) {
/**
* If no free entry in tx_q or no entry in alloc_q,
* drops skb and goes out.
*/
goto drop;
}
/* dequeue a mbuf from alloc_q */
ret = kni_fifo_get(kni->alloc_q, (void **)&pkt_va, 1);
if (likely(ret == 1)) {
void *data_kva;
pkt_kva = (void *)pkt_va - kni->mbuf_va + kni->mbuf_kva;
data_kva = pkt_kva->buf_addr + pkt_kva->data_off
- kni->mbuf_va + kni->mbuf_kva;
#ifdef HAVE_IOV_ITER_MSGHDR
copy_from_iter(data_kva, len, &m->msg_iter);
#else
memcpy_fromiovecend(data_kva, m->msg_iov, offset, len);
#endif
if (unlikely(len < ETH_ZLEN)) {
memset(data_kva + len, 0, ETH_ZLEN - len);
len = ETH_ZLEN;
}
pkt_kva->pkt_len = len;
pkt_kva->data_len = len;
/* enqueue mbuf into tx_q */
ret = kni_fifo_put(kni->tx_q, (void **)&pkt_va, 1);
if (unlikely(ret != 1)) {
/* Failing should not happen */
KNI_ERR("Fail to enqueue mbuf into tx_q\n");
goto drop;
}
} else {
/* Failing should not happen */
KNI_ERR("Fail to dequeue mbuf from alloc_q\n");
goto drop;
}
/* update statistics */
kni->stats.tx_bytes += len;
kni->stats.tx_packets++;
return 0;
drop:
/* update statistics */
kni->stats.tx_dropped++;
return 0;
}
static int raw_getfrag(const void *p, char *to, unsigned int offset,
unsigned int fraglen, struct sk_buff *skb)
{
struct rawfakehdr *rfh = (struct rawfakehdr *) p;
return memcpy_fromiovecend(to, rfh->iov, offset, fraglen);
}