/* Add encapsulation header.
*
* The IP header will be moved forward to make space for the encapsulation
* header.
*/
static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct iphdr *iph = ip_hdr(skb);
int ihl = iph->ihl * 4;
#if IS_ENABLED(CONFIG_RALINK_HWCRYPTO)
if (x->type->proto == IPPROTO_ESP) {
int header_len = 0;
if (x->props.mode == XFRM_MODE_TUNNEL)
header_len += sizeof(struct iphdr);
if (x->encap) {
struct xfrm_encap_tmpl *encap = x->encap;
header_len += sizeof(struct udphdr);
if (encap->encap_type == UDP_ENCAP_ESPINUDP_NON_IKE)
header_len += 2 * sizeof(u32);
}
skb_set_network_header(skb, -header_len);
} else
#endif
skb_set_network_header(skb, -x->props.header_len);
skb->mac_header = skb->network_header +
offsetof(struct iphdr, protocol);
skb->transport_header = skb->network_header + ihl;
__skb_pull(skb, ihl);
memmove(skb_network_header(skb), iph, ihl);
return 0;
}
/*
* Verify that our various assumptions about sk_buffs and the conditions
* under which TSO will be attempted hold true. Return the protocol number.
*/
static __be16 efx_tso_check_protocol(struct sk_buff *skb)
{
__be16 protocol = skb->protocol;
EFX_BUG_ON_PARANOID(((struct ethhdr *)skb->data)->h_proto !=
protocol);
if (protocol == htons(ETH_P_8021Q)) {
/* Find the encapsulated protocol; reset network header
* and transport header based on that. */
struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
skb_set_network_header(skb, sizeof(*veh));
if (protocol == htons(ETH_P_IP))
skb_set_transport_header(skb, sizeof(*veh) +
4 * ip_hdr(skb)->ihl);
else if (protocol == htons(ETH_P_IPV6))
skb_set_transport_header(skb, sizeof(*veh) +
sizeof(struct ipv6hdr));
}
if (protocol == htons(ETH_P_IP)) {
EFX_BUG_ON_PARANOID(ip_hdr(skb)->protocol != IPPROTO_TCP);
} else {
EFX_BUG_ON_PARANOID(protocol != htons(ETH_P_IPV6));
EFX_BUG_ON_PARANOID(ipv6_hdr(skb)->nexthdr != NEXTHDR_TCP);
}
EFX_BUG_ON_PARANOID((PTR_DIFF(tcp_hdr(skb), skb->data)
+ (tcp_hdr(skb)->doff << 2u)) >
skb_headlen(skb));
return protocol;
}
/* Add encapsulation header.
*
* The top IP header will be constructed per RFC 2401.
*/
static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *top_iph;
int dsfield;
skb_set_network_header(skb, -x->props.header_len);
skb->mac_header = skb->network_header +
offsetof(struct ipv6hdr, nexthdr);
skb->transport_header = skb->network_header + sizeof(*top_iph);
top_iph = ipv6_hdr(skb);
top_iph->version = 6;
memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl,
sizeof(top_iph->flow_lbl));
top_iph->nexthdr = xfrm_af2proto(skb_dst(skb)->ops->family);
dsfield = XFRM_MODE_SKB_CB(skb)->tos;
dsfield = INET_ECN_encapsulate(dsfield, dsfield);
if (x->props.flags & XFRM_STATE_NOECN)
dsfield &= ~INET_ECN_MASK;
ipv6_change_dsfield(top_iph, 0, dsfield);
top_iph->hop_limit = ip6_dst_hoplimit(dst->child);
ipv6_addr_copy(&top_iph->saddr, (const struct in6_addr *)&x->props.saddr);
ipv6_addr_copy(&top_iph->daddr, (const struct in6_addr *)&x->id.daddr);
return 0;
}
/*
* We need to grow the skb to accommodate the expanssion of the ipcomp packet.
*
* The following comment comes from the skb_decompress() which does the
* same...
*
* We have no way of knowing the exact length of the resulting
* decompressed output before we have actually done the decompression.
* For now, we guess that the packet will not be bigger than the
* attached ipsec device's mtu or 16260, whichever is biggest.
* This may be wrong, since the sender's mtu may be bigger yet.
* XXX This must be dealt with later XXX
*/
static int ipsec_ocf_ipcomp_copy_expand(struct ipsec_rcv_state *irs)
{
struct sk_buff *nskb;
unsigned grow_to, grow_by;
ptrdiff_t ptr_delta;
if (!irs->skb)
return IPSEC_RCV_IPCOMPFAILED;
if (irs->skb->dev) {
grow_to = irs->skb->dev->mtu <
16260 ? 16260 : irs->skb->dev->mtu;
} else {
int tot_len;
if (lsw_ip_hdr_version(irs) == 6)
tot_len = ntohs(lsw_ip6_hdr(irs)->payload_len) +
sizeof(struct ipv6hdr);
else
tot_len = ntohs(lsw_ip4_hdr(irs)->tot_len);
grow_to = 65520 - tot_len;
}
grow_by = grow_to - irs->skb->len;
grow_by -= skb_headroom(irs->skb);
grow_by -= skb_tailroom(irs->skb);
/* it's big enough */
if (!grow_by)
return IPSEC_RCV_OK;
nskb = skb_copy_expand(irs->skb, skb_headroom(irs->skb),
skb_tailroom(irs->skb) + grow_by, GFP_ATOMIC);
if (!nskb)
return IPSEC_RCV_ERRMEMALLOC;
memcpy(nskb->head, irs->skb->head, skb_headroom(irs->skb));
skb_set_network_header(nskb,
ipsec_skb_offset(irs->skb,
skb_network_header(irs->skb)));
skb_set_transport_header(nskb,
ipsec_skb_offset(irs->skb,
skb_transport_header(
irs->skb)));
/* update all irs pointers */
ptr_delta = nskb->data - irs->skb->data;
irs->authenticator = (void*)((char*)irs->authenticator + ptr_delta);
irs->iph = (void*)((char*)irs->iph + ptr_delta);
/* flip in the large one */
irs->pre_ipcomp_skb = irs->skb;
irs->skb = nskb;
/* move the tail up to the end to let OCF know how big the buffer is */
if (grow_by > (irs->skb->end - irs->skb->tail))
grow_by = irs->skb->end - irs->skb->tail;
skb_put(irs->skb, grow_by);
return IPSEC_RCV_OK;
}
/* UPSTACK: MASTER FUNCTION CALLED BY L2 */
int mhost_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
struct mhost_proto *mp;
struct l3_hdr *hdr;
// printk(KERN_INFO "mhost_rcv called\n");
/* error-checking here */
skb_set_network_header(skb, 0);
/* address family MUST be first member of L3 header
* so that we can quickly perform a table lookup on it.*/
hdr = (struct l3_hdr *) skb_network_header(skb);
mp = mhost_proto_for_family(hdr->family);
/* ...and pass it up the stack! */
if (mp && mp->rcv) {
mp->rcv(skb, dev, orig_dev);
return 0;
}
printk(KERN_INFO "error: no L3 handler registered! family=%x\n", hdr->family);
return -EAFNOSUPPORT;
}
/* remove VLAN header from packet and update csum accordingly. */
static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
{
struct vlan_hdr *vhdr;
int err;
err = make_writable(skb, VLAN_ETH_HLEN);
if (unlikely(err))
return err;
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_sub(skb->csum, csum_partial(skb->data
+ (2 * ETH_ALEN), VLAN_HLEN, 0));
vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
*current_tci = vhdr->h_vlan_TCI;
memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN);
__skb_pull(skb, VLAN_HLEN);
vlan_set_encap_proto(skb, vhdr);
skb->mac_header += VLAN_HLEN;
if (skb_network_offset(skb) < ETH_HLEN)
skb_set_network_header(skb, ETH_HLEN);
skb_reset_mac_len(skb);
return 0;
}
static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
const struct ovs_action_push_mpls *mpls)
{
struct mpls_shim_hdr *new_mpls_lse;
/* Networking stack do not allow simultaneous Tunnel and MPLS GSO. */
if (skb->encapsulation)
return -ENOTSUPP;
if (skb_cow_head(skb, MPLS_HLEN) < 0)
return -ENOMEM;
if (!skb->inner_protocol) {
skb_set_inner_network_header(skb, skb->mac_len);
skb_set_inner_protocol(skb, skb->protocol);
}
skb_push(skb, MPLS_HLEN);
memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
skb->mac_len);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb->mac_len);
new_mpls_lse = mpls_hdr(skb);
new_mpls_lse->label_stack_entry = mpls->mpls_lse;
skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN);
if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET)
update_ethertype(skb, eth_hdr(skb), mpls->mpls_ethertype);
skb->protocol = mpls->mpls_ethertype;
invalidate_flow_key(key);
return 0;
}
static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
const __be16 ethertype)
{
int err;
err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
skb->mac_len);
__skb_pull(skb, MPLS_HLEN);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb->mac_len);
if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET) {
struct ethhdr *hdr;
/* mpls_hdr() is used to locate the ethertype field correctly in the
* presence of VLAN tags.
*/
hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
update_ethertype(skb, hdr, ethertype);
}
if (eth_p_mpls(skb->protocol))
skb->protocol = ethertype;
invalidate_flow_key(key);
return 0;
}
static void sc_send_8023(struct sk_buff *skb, struct net_device *dev)
{
struct ethhdr *eh;
if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
return;
/* drop conntrack reference */
nf_reset(skb);
/* detach skb from CAPWAP */
skb_orphan(skb);
secpath_reset(skb);
/* drop any routing info */
skb_dst_drop(skb);
skb->dev = dev;
skb_reset_mac_header(skb);
eh = eth_hdr(skb);
if (likely(eth_proto_is_802_3(eh->h_proto)))
skb->protocol = eh->h_proto;
else
skb->protocol = htons(ETH_P_802_2);
skb_set_network_header(skb, ETH_HLEN);
/* Force the device to verify it. */
skb->ip_summed = CHECKSUM_NONE;
dev_queue_xmit(skb);
}
/*
* Probably needs some error checks and locking, not sure...
*/
static netdev_tx_t mpc_send_packet(struct sk_buff *skb,
struct net_device *dev)
{
struct mpoa_client *mpc;
struct ethhdr *eth;
int i = 0;
mpc = find_mpc_by_lec(dev); /* this should NEVER fail */
if (mpc == NULL) {
pr_info("(%s) no MPC found\n", dev->name);
goto non_ip;
}
eth = (struct ethhdr *)skb->data;
if (eth->h_proto != htons(ETH_P_IP))
goto non_ip; /* Multi-Protocol Over ATM :-) */
/* Weed out funny packets (e.g., AF_PACKET or raw). */
if (skb->len < ETH_HLEN + sizeof(struct iphdr))
goto non_ip;
skb_set_network_header(skb, ETH_HLEN);
if (skb->len < ETH_HLEN + ip_hdr(skb)->ihl * 4 || ip_hdr(skb)->ihl < 5)
goto non_ip;
while (i < mpc->number_of_mps_macs) {
if (!compare_ether_addr(eth->h_dest,
(mpc->mps_macs + i*ETH_ALEN)))
if (send_via_shortcut(skb, mpc) == 0) /* try shortcut */
return NETDEV_TX_OK;
i++;
}
non_ip:
return mpc->old_ops->ndo_start_xmit(skb, dev);
}
int skb_from_pkt(void *pkt, u32 pkt_len, struct sk_buff **skb)
{
*skb = alloc_skb(LL_MAX_HEADER + pkt_len, GFP_ATOMIC);
if (!*skb) {
log_err("Could not allocate a skb.");
return -ENOMEM;
}
skb_reserve(*skb, LL_MAX_HEADER); /* Reserve space for Link Layer data. */
skb_put(*skb, pkt_len); /* L3 + L4 + payload. */
skb_set_mac_header(*skb, 0);
skb_set_network_header(*skb, 0);
skb_set_transport_header(*skb, net_hdr_size(pkt));
(*skb)->ip_summed = CHECKSUM_UNNECESSARY;
switch (get_l3_proto(pkt)) {
case 6:
(*skb)->protocol = htons(ETH_P_IPV6);
break;
case 4:
(*skb)->protocol = htons(ETH_P_IP);
break;
default:
log_err("Invalid mode: %u.", get_l3_proto(pkt));
kfree_skb(*skb);
return -EINVAL;
}
/* Copy packet content to skb. */
memcpy(skb_network_header(*skb), pkt, pkt_len);
return 0;
}
int get_rx_buffers(void *priv, void **pkt_priv, void **buffer, int size)
{
struct net_device *dev = (struct net_device *) priv;
struct sk_buff *skb = NULL;
void *ptr = NULL;
DBG0("[%s] dev:%s\n", __func__, dev->name);
skb = __dev_alloc_skb(size, GFP_ATOMIC);
if (skb == NULL) {
DBG0("%s: unable to alloc skb\n", __func__);
return -ENOMEM;
}
/* TODO skb_reserve(skb, NET_IP_ALIGN); for ethernet mode */
/* Populate some params now. */
skb->dev = dev;
ptr = skb_put(skb, size);
skb_set_network_header(skb, 0);
/* done with skb setup, return the buffer pointer. */
*pkt_priv = skb;
*buffer = ptr;
return 0;
}
static inline int ip6_ufo_append_data(struct sock *sk,
struct sk_buff_head *queue,
int getfrag(void *from, char *to, int offset, int len,
int odd, struct sk_buff *skb),
void *from, int length, int hh_len, int fragheaderlen,
int exthdrlen, int transhdrlen, int mtu,
unsigned int flags, const struct flowi6 *fl6)
{
struct sk_buff *skb;
int err;
/* There is support for UDP large send offload by network
* device, so create one single skb packet containing complete
* udp datagram
*/
skb = skb_peek_tail(queue);
if (!skb) {
skb = sock_alloc_send_skb(sk,
hh_len + fragheaderlen + transhdrlen + 20,
(flags & MSG_DONTWAIT), &err);
if (!skb)
return err;
/* reserve space for Hardware header */
skb_reserve(skb, hh_len);
/* create space for UDP/IP header */
skb_put(skb, fragheaderlen + transhdrlen);
/* initialize network header pointer */
skb_set_network_header(skb, exthdrlen);
/* initialize protocol header pointer */
skb->transport_header = skb->network_header + fragheaderlen;
skb->protocol = htons(ETH_P_IPV6);
skb->csum = 0;
__skb_queue_tail(queue, skb);
} else if (skb_is_gso(skb)) {
goto append;
}
skb->ip_summed = CHECKSUM_PARTIAL;
/* Specify the length of each IPv6 datagram fragment.
* It has to be a multiple of 8.
*/
skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
sizeof(struct frag_hdr)) & ~7;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
skb_shinfo(skb)->ip6_frag_id = ipv6_select_ident(sock_net(sk),
&fl6->daddr,
&fl6->saddr);
append:
return skb_append_datato_frags(sk, skb, getfrag, from,
(length - transhdrlen));
}
void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
{
int total_len, eth_len, ip_len, udp_len;
struct sk_buff *skb;
struct udphdr *udph;
struct iphdr *iph;
struct ethhdr *eth;
udp_len = len + sizeof(*udph);
ip_len = eth_len = udp_len + sizeof(*iph);
total_len = eth_len + ETH_HLEN + NET_IP_ALIGN;
skb = find_skb(np, total_len, total_len - len);
if (!skb)
return;
memcpy(skb->data, msg, len);
skb->len += len;
udph = (struct udphdr *) skb_push(skb, sizeof(*udph));
udph->source = htons(np->local_port);
udph->dest = htons(np->remote_port);
udph->len = htons(udp_len);
udph->check = 0;
udph->check = csum_tcpudp_magic(htonl(np->local_ip),
htonl(np->remote_ip),
udp_len, IPPROTO_UDP,
csum_partial((unsigned char *)udph, udp_len, 0));
if (udph->check == 0)
udph->check = -1;
iph = (struct iphdr *)skb_push(skb, sizeof(*iph));
/* iph->version = 4; iph->ihl = 5; */
put_unaligned(0x45, (unsigned char *)iph);
iph->tos = 0;
put_unaligned(htons(ip_len), &(iph->tot_len));
iph->id = 0;
iph->frag_off = 0;
iph->ttl = 64;
iph->protocol = IPPROTO_UDP;
iph->check = 0;
put_unaligned(htonl(np->local_ip), &(iph->saddr));
put_unaligned(htonl(np->remote_ip), &(iph->daddr));
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
eth->h_proto = htons(ETH_P_IP);
memcpy(eth->h_source, np->local_mac, 6);
memcpy(eth->h_dest, np->remote_mac, 6);
skb->dev = np->dev;
skb_set_network_header(skb, ETH_HLEN);
netpoll_send_skb(np, skb);
}
/* Add encapsulation header.
*
* The IP header will be moved forward to make space for the encapsulation
* header.
*/
static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct iphdr *iph = ip_hdr(skb);
int ihl = iph->ihl * 4;
skb_set_network_header(skb, -x->props.header_len);
skb->mac_header = skb->network_header +
offsetof(struct iphdr, protocol);
skb->transport_header = skb->network_header + ihl;
__skb_pull(skb, ihl);
memmove(skb_network_header(skb), iph, ihl);
return 0;
}
netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dsa_slave_priv *p = netdev_priv(dev);
struct sk_buff *nskb;
int padlen;
u8 *trailer;
dev->stats.tx_packets++;
dev->stats.tx_bytes += skb->len;
/*
* We have to make sure that the trailer ends up as the very
* last 4 bytes of the packet. This means that we have to pad
* the packet to the minimum ethernet frame size, if necessary,
* before adding the trailer.
*/
padlen = 0;
if (skb->len < 60)
padlen = 60 - skb->len;
nskb = alloc_skb(NET_IP_ALIGN + skb->len + padlen + 4, GFP_ATOMIC);
if (nskb == NULL) {
kfree_skb(skb);
return NETDEV_TX_OK;
}
skb_reserve(nskb, NET_IP_ALIGN);
skb_reset_mac_header(nskb);
skb_set_network_header(nskb, skb_network_header(skb) - skb->head);
skb_set_transport_header(nskb, skb_transport_header(skb) - skb->head);
skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len));
kfree_skb(skb);
if (padlen) {
u8 *pad = skb_put(nskb, padlen);
memset(pad, 0, padlen);
}
trailer = skb_put(nskb, 4);
trailer[0] = 0x80;
trailer[1] = 1 << p->port;
trailer[2] = 0x10;
trailer[3] = 0x00;
nskb->protocol = htons(ETH_P_TRAILER);
nskb->dev = p->parent->dst->master_netdev;
dev_queue_xmit(nskb);
return NETDEV_TX_OK;
}
/**
* batadv_send_skb_packet() - send an already prepared packet
* @skb: the packet to send
* @hard_iface: the interface to use to send the broadcast packet
* @dst_addr: the payload destination
*
* Send out an already prepared packet to the given neighbor or broadcast it
* using the specified interface. Either hard_iface or neigh_node must be not
* NULL.
* If neigh_node is NULL, then the packet is broadcasted using hard_iface,
* otherwise it is sent as unicast to the given neighbor.
*
* Regardless of the return value, the skb is consumed.
*
* Return: A negative errno code is returned on a failure. A success does not
* guarantee the frame will be transmitted as it may be dropped due
* to congestion or traffic shaping.
*/
int batadv_send_skb_packet(struct sk_buff *skb,
struct batadv_hard_iface *hard_iface,
const u8 *dst_addr)
{
struct batadv_priv *bat_priv;
struct ethhdr *ethhdr;
int ret;
bat_priv = netdev_priv(hard_iface->soft_iface);
if (hard_iface->if_status != BATADV_IF_ACTIVE)
goto send_skb_err;
if (unlikely(!hard_iface->net_dev))
goto send_skb_err;
if (!(hard_iface->net_dev->flags & IFF_UP)) {
pr_warn("Interface %s is not up - can't send packet via that interface!\n",
hard_iface->net_dev->name);
goto send_skb_err;
}
/* push to the ethernet header. */
if (batadv_skb_head_push(skb, ETH_HLEN) < 0)
goto send_skb_err;
skb_reset_mac_header(skb);
ethhdr = eth_hdr(skb);
ether_addr_copy(ethhdr->h_source, hard_iface->net_dev->dev_addr);
ether_addr_copy(ethhdr->h_dest, dst_addr);
ethhdr->h_proto = htons(ETH_P_BATMAN);
skb_set_network_header(skb, ETH_HLEN);
skb->protocol = htons(ETH_P_BATMAN);
skb->dev = hard_iface->net_dev;
/* Save a clone of the skb to use when decoding coded packets */
batadv_nc_skb_store_for_decoding(bat_priv, skb);
/* dev_queue_xmit() returns a negative result on error. However on
* congestion and traffic shaping, it drops and returns NET_XMIT_DROP
* (which is > 0). This will not be treated as an error.
*/
ret = dev_queue_xmit(skb);
return net_xmit_eval(ret);
send_skb_err:
kfree_skb(skb);
return NET_XMIT_DROP;
}
static int ztdeth_transmit(void *pvt, unsigned char *msg, int msglen)
{
struct ztdeth *z;
struct sk_buff *skb;
struct ztdeth_header *zh;
unsigned long flags;
struct net_device *dev;
unsigned char addr[ETH_ALEN];
unsigned short subaddr; /* Network byte order */
spin_lock_irqsave(&zlock, flags);
z = pvt;
if (z->dev) {
/* Copy fields to local variables to remove spinlock ASAP */
dev = z->dev;
memcpy(addr, z->addr, sizeof(z->addr));
subaddr = z->subaddr;
spin_unlock_irqrestore(&zlock, flags);
skb = dev_alloc_skb(msglen + dev->hard_header_len + sizeof(struct ztdeth_header) + 32);
if (skb) {
/* Reserve header space */
skb_reserve(skb, dev->hard_header_len + sizeof(struct ztdeth_header));
/* Copy message body */
memcpy(skb_put(skb, msglen), msg, msglen);
/* Throw on header */
zh = (struct ztdeth_header *)skb_push(skb, sizeof(struct ztdeth_header));
zh->subaddr = subaddr;
/* Setup protocol and such */
skb->protocol = __constant_htons(ETH_P_DAHDI_DETH);
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,22)
skb_set_network_header(skb, 0);
#else
skb->nh.raw = skb->data;
#endif
skb->dev = dev;
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)
dev_hard_header(skb, dev, ETH_P_DAHDI_DETH, addr, dev->dev_addr, skb->len);
#else
if (dev->hard_header)
dev->hard_header(skb, dev, ETH_P_DAHDI_DETH, addr, dev->dev_addr, skb->len);
#endif
skb_queue_tail(&skbs, skb);
}
}
else
spin_unlock_irqrestore(&zlock, flags);
return 0;
}
static void init_skbuff(const struct ipq_packet_msg *ipq_msg, struct sk_buff *skb)
{
memcpy(skb->head, ipq_msg->payload, ipq_msg->data_len);
skb->len = skb->data_len = ipq_msg->data_len;
// Becasue the payload of ipq_msg l3 packet. so there is no mac header
skb_set_mac_header(skb, ~0U);
skb_set_network_header(skb, 0);
struct iphdr *iph = (struct iphdr*)skb_network_header(skb);
skb_set_transport_header(skb, iph->ihl<<2);
}
static void prepare_frame_for_deferred_tx(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb)
{
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
skb_set_mac_header(skb, 0);
skb_set_network_header(skb, 0);
skb_set_transport_header(skb, 0);
skb_set_queue_mapping(skb, IEEE80211_AC_VO);
skb->priority = 7;
info->control.vif = &sdata->vif;
ieee80211_set_qos_hdr(sdata, skb);
}
static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct ipv6hdr *iph;
u8 *prevhdr;
int hdr_len;
iph = ipv6_hdr(skb);
hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data);
skb_set_network_header(skb, -x->props.header_len);
skb->transport_header = skb->network_header + hdr_len;
__skb_pull(skb, hdr_len);
memmove(ipv6_hdr(skb), iph, hdr_len);
return 0;
}
/* Headroom is not adjusted. Caller should ensure that skb has sufficient
* headroom in case the frame is encrypted. */
static void prepare_frame_for_deferred_tx(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb)
{
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
skb_set_mac_header(skb, 0);
skb_set_network_header(skb, 0);
skb_set_transport_header(skb, 0);
/* Send all internal mgmt frames on VO. Accordingly set TID to 7. */
skb_set_queue_mapping(skb, IEEE80211_AC_VO);
skb->priority = 7;
info->control.vif = &sdata->vif;
info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
ieee80211_set_qos_hdr(sdata, skb);
}
/* Add encapsulation header.
*
* The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt.
*/
static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct ipv6hdr *top_iph;
skb_set_network_header(skb, -x->props.header_len);
skb->mac_header = skb->network_header +
offsetof(struct ipv6hdr, nexthdr);
skb->transport_header = skb->network_header + sizeof(*top_iph);
__skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl);
xfrm6_beet_make_header(skb);
top_iph = ipv6_hdr(skb);
ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
return 0;
}
/* Add encapsulation header.
*
* The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt.
*/
static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct ip_beet_phdr *ph;
struct iphdr *top_iph;
int hdrlen, optlen;
hdrlen = 0;
optlen = XFRM_MODE_SKB_CB(skb)->optlen;
if (unlikely(optlen))
hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4);
skb_set_network_header(skb, -x->props.header_len -
hdrlen + (XFRM_MODE_SKB_CB(skb)->ihl - sizeof(*top_iph)));
if (x->sel.family != AF_INET6)
skb->network_header += IPV4_BEET_PHMAXLEN;
skb->mac_header = skb->network_header +
offsetof(struct iphdr, protocol);
skb->transport_header = skb->network_header + sizeof(*top_iph);
xfrm4_beet_make_header(skb);
ph = (struct ip_beet_phdr *)
__skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen);
top_iph = ip_hdr(skb);
if (unlikely(optlen)) {
BUG_ON(optlen < 0);
ph->padlen = 4 - (optlen & 4);
ph->hdrlen = optlen / 8;
ph->nexthdr = top_iph->protocol;
if (ph->padlen)
memset(ph + 1, IPOPT_NOP, ph->padlen);
top_iph->protocol = IPPROTO_BEETPH;
top_iph->ihl = sizeof(struct iphdr) / 4;
}
top_iph->saddr = x->props.saddr.a4;
top_iph->daddr = x->id.daddr.a4;
return 0;
}
/**
* fnic_import_rq_eth_pkt() - handle received FCoE or FIP frame.
* @fnic: fnic instance.
* @skb: Ethernet Frame.
*/
static inline int fnic_import_rq_eth_pkt(struct fnic *fnic, struct sk_buff *skb)
{
struct fc_frame *fp;
struct ethhdr *eh;
struct fcoe_hdr *fcoe_hdr;
struct fcoe_crc_eof *ft;
/*
* Undo VLAN encapsulation if present.
*/
eh = (struct ethhdr *)skb->data;
if (eh->h_proto == htons(ETH_P_8021Q)) {
memmove((u8 *)eh + VLAN_HLEN, eh, ETH_ALEN * 2);
eh = (struct ethhdr *)skb_pull(skb, VLAN_HLEN);
skb_reset_mac_header(skb);
}
if (eh->h_proto == htons(ETH_P_FIP)) {
skb_pull(skb, sizeof(*eh));
fcoe_ctlr_recv(&fnic->ctlr, skb);
return 1; /* let caller know packet was used */
}
if (eh->h_proto != htons(ETH_P_FCOE))
goto drop;
skb_set_network_header(skb, sizeof(*eh));
skb_pull(skb, sizeof(*eh));
fcoe_hdr = (struct fcoe_hdr *)skb->data;
if (FC_FCOE_DECAPS_VER(fcoe_hdr) != FC_FCOE_VER)
goto drop;
fp = (struct fc_frame *)skb;
fc_frame_init(fp);
fr_sof(fp) = fcoe_hdr->fcoe_sof;
skb_pull(skb, sizeof(struct fcoe_hdr));
skb_reset_transport_header(skb);
ft = (struct fcoe_crc_eof *)(skb->data + skb->len - sizeof(*ft));
fr_eof(fp) = ft->fcoe_eof;
skb_trim(skb, skb->len - sizeof(*ft));
return 0;
drop:
dev_kfree_skb_irq(skb);
return -1;
}
/* Add encapsulation header.
*
* The top IP header will be constructed per RFC 2401.
*/
static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct iphdr *top_iph;
int flags;
skb_set_network_header(skb, -x->props.header_len);
skb->mac_header = skb->network_header +
offsetof(struct iphdr, protocol);
skb->transport_header = skb->network_header + sizeof(*top_iph);
top_iph = ip_hdr(skb);
top_iph->ihl = 5;
top_iph->version = 4;
top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family);
/* DS disclosing depends on XFRM_SA_XFLAG_DONT_ENCAP_DSCP */
if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
top_iph->tos = 0;
else
top_iph->tos = XFRM_MODE_SKB_CB(skb)->tos;
top_iph->tos = INET_ECN_encapsulate(top_iph->tos,
XFRM_MODE_SKB_CB(skb)->tos);
flags = x->props.flags;
if (flags & XFRM_STATE_NOECN)
IP_ECN_clear(top_iph);
top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
top_iph->ttl = ip4_dst_hoplimit(dst->child);
top_iph->saddr = x->props.saddr.a4;
top_iph->daddr = x->id.daddr.a4;
ip_select_ident(dev_net(dst->dev), skb, NULL);
return 0;
}
static void sc_send_80211(struct sk_buff *skb, struct net_device *dev)
{
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
struct ieee80211_hdr *hdr;
int hdrlen;
printk(KERN_DEBUG "capwap inject: %s: hdr: %p\n",
dev->name, skb->data);
/* detach skb from CAPWAP */
skb_orphan(skb);
secpath_reset(skb);
/* drop any routing info */
skb_dst_drop(skb);
/* drop conntrack reference */
nf_reset(skb);
hdr = (struct ieee80211_hdr *)skb->data;
hdrlen = ieee80211_hdrlen(hdr->frame_control);
skb->dev = dev;
skb_set_mac_header(skb, hdrlen);
skb_set_network_header(skb, hdrlen);
skb_set_transport_header(skb, hdrlen);
skb->protocol = htons(ETH_P_CONTROL);
info->flags |= IEEE80211_TX_CTL_INJECTED;
/* Force the device to verify it. */
skb->ip_summed = CHECKSUM_NONE;
dev_queue_xmit(skb);
}
/* Add encapsulation header.
*
* The top IP header will be constructed per RFC 2401.
*/
static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct iphdr *top_iph;
int flags;
skb_set_network_header(skb, -x->props.header_len);
skb->mac_header = skb->network_header +
offsetof(struct iphdr, protocol);
skb->transport_header = skb->network_header + sizeof(*top_iph);
top_iph = ip_hdr(skb);
top_iph->ihl = 5;
top_iph->version = 4;
top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family);
/* DS disclosed */
top_iph->tos = INET_ECN_encapsulate(XFRM_MODE_SKB_CB(skb)->tos,
XFRM_MODE_SKB_CB(skb)->tos);
flags = x->props.flags;
if (flags & XFRM_STATE_NOECN)
IP_ECN_clear(top_iph);
top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
ip_select_ident(top_iph, dst->child, NULL);
top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT);
top_iph->saddr = x->props.saddr.a4;
top_iph->daddr = x->id.daddr.a4;
return 0;
}
/**
* key_extract - extracts a flow key from an Ethernet frame.
* @skb: sk_buff that contains the frame, with skb->data pointing to the
* Ethernet header
* @key: output flow key
*
* The caller must ensure that skb->len >= ETH_HLEN.
*
* Returns 0 if successful, otherwise a negative errno value.
*
* Initializes @skb header pointers as follows:
*
* - skb->mac_header: the Ethernet header.
*
* - skb->network_header: just past the Ethernet header, or just past the
* VLAN header, to the first byte of the Ethernet payload.
*
* - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6
* on output, then just past the IP header, if one is present and
* of a correct length, otherwise the same as skb->network_header.
* For other key->eth.type values it is left untouched.
*/
static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
{
int error;
struct ethhdr *eth;
/* Flags are always used as part of stats */
key->tp.flags = 0;
skb_reset_mac_header(skb);
/* Link layer. We are guaranteed to have at least the 14 byte Ethernet
* header in the linear data area.
*/
eth = eth_hdr(skb);
ether_addr_copy(key->eth.src, eth->h_source);
ether_addr_copy(key->eth.dst, eth->h_dest);
__skb_pull(skb, 2 * ETH_ALEN);
/* We are going to push all headers that we pull, so no need to
* update skb->csum here.
*/
key->eth.tci = 0;
if (vlan_tx_tag_present(skb))
key->eth.tci = htons(vlan_get_tci(skb));
else if (eth->h_proto == htons(ETH_P_8021Q))
if (unlikely(parse_vlan(skb, key)))
return -ENOMEM;
key->eth.type = parse_ethertype(skb);
if (unlikely(key->eth.type == htons(0)))
return -ENOMEM;
skb_reset_network_header(skb);
skb_reset_mac_len(skb);
__skb_push(skb, skb->data - skb_mac_header(skb));
/* Network layer. */
if (key->eth.type == htons(ETH_P_IP)) {
struct iphdr *nh;
__be16 offset;
error = check_iphdr(skb);
if (unlikely(error)) {
memset(&key->ip, 0, sizeof(key->ip));
memset(&key->ipv4, 0, sizeof(key->ipv4));
if (error == -EINVAL) {
skb->transport_header = skb->network_header;
error = 0;
}
return error;
}
nh = ip_hdr(skb);
key->ipv4.addr.src = nh->saddr;
key->ipv4.addr.dst = nh->daddr;
key->ip.proto = nh->protocol;
key->ip.tos = nh->tos;
key->ip.ttl = nh->ttl;
offset = nh->frag_off & htons(IP_OFFSET);
if (offset) {
key->ip.frag = OVS_FRAG_TYPE_LATER;
return 0;
}
if (nh->frag_off & htons(IP_MF) ||
skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
key->ip.frag = OVS_FRAG_TYPE_FIRST;
else
key->ip.frag = OVS_FRAG_TYPE_NONE;
/* Transport layer. */
if (key->ip.proto == IPPROTO_TCP) {
if (tcphdr_ok(skb)) {
struct tcphdr *tcp = tcp_hdr(skb);
key->tp.src = tcp->source;
key->tp.dst = tcp->dest;
key->tp.flags = TCP_FLAGS_BE16(tcp);
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == IPPROTO_UDP) {
if (udphdr_ok(skb)) {
struct udphdr *udp = udp_hdr(skb);
key->tp.src = udp->source;
key->tp.dst = udp->dest;
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == IPPROTO_SCTP) {
if (sctphdr_ok(skb)) {
struct sctphdr *sctp = sctp_hdr(skb);
key->tp.src = sctp->source;
key->tp.dst = sctp->dest;
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == IPPROTO_ICMP) {
if (icmphdr_ok(skb)) {
struct icmphdr *icmp = icmp_hdr(skb);
/* The ICMP type and code fields use the 16-bit
* transport port fields, so we need to store
* them in 16-bit network byte order.
*/
key->tp.src = htons(icmp->type);
key->tp.dst = htons(icmp->code);
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
}
} else if (key->eth.type == htons(ETH_P_ARP) ||
key->eth.type == htons(ETH_P_RARP)) {
struct arp_eth_header *arp;
bool arp_available = arphdr_ok(skb);
arp = (struct arp_eth_header *)skb_network_header(skb);
if (arp_available &&
arp->ar_hrd == htons(ARPHRD_ETHER) &&
arp->ar_pro == htons(ETH_P_IP) &&
arp->ar_hln == ETH_ALEN &&
arp->ar_pln == 4) {
/* We only match on the lower 8 bits of the opcode. */
if (ntohs(arp->ar_op) <= 0xff)
key->ip.proto = ntohs(arp->ar_op);
else
key->ip.proto = 0;
memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src));
memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst));
ether_addr_copy(key->ipv4.arp.sha, arp->ar_sha);
ether_addr_copy(key->ipv4.arp.tha, arp->ar_tha);
} else {
memset(&key->ip, 0, sizeof(key->ip));
memset(&key->ipv4, 0, sizeof(key->ipv4));
}
} else if (eth_p_mpls(key->eth.type)) {
size_t stack_len = MPLS_HLEN;
/* In the presence of an MPLS label stack the end of the L2
* header and the beginning of the L3 header differ.
*
* Advance network_header to the beginning of the L3
* header. mac_len corresponds to the end of the L2 header.
*/
while (1) {
__be32 lse;
error = check_header(skb, skb->mac_len + stack_len);
if (unlikely(error))
return 0;
memcpy(&lse, skb_network_header(skb), MPLS_HLEN);
if (stack_len == MPLS_HLEN)
memcpy(&key->mpls.top_lse, &lse, MPLS_HLEN);
skb_set_network_header(skb, skb->mac_len + stack_len);
if (lse & htonl(MPLS_LS_S_MASK))
break;
stack_len += MPLS_HLEN;
}
} else if (key->eth.type == htons(ETH_P_IPV6)) {
int nh_len; /* IPv6 Header + Extensions */
nh_len = parse_ipv6hdr(skb, key);
if (unlikely(nh_len < 0)) {
memset(&key->ip, 0, sizeof(key->ip));
memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr));
if (nh_len == -EINVAL) {
skb->transport_header = skb->network_header;
error = 0;
} else {
error = nh_len;
}
return error;
}
if (key->ip.frag == OVS_FRAG_TYPE_LATER)
return 0;
if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
key->ip.frag = OVS_FRAG_TYPE_FIRST;
/* Transport layer. */
if (key->ip.proto == NEXTHDR_TCP) {
if (tcphdr_ok(skb)) {
struct tcphdr *tcp = tcp_hdr(skb);
key->tp.src = tcp->source;
key->tp.dst = tcp->dest;
key->tp.flags = TCP_FLAGS_BE16(tcp);
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == NEXTHDR_UDP) {
if (udphdr_ok(skb)) {
struct udphdr *udp = udp_hdr(skb);
key->tp.src = udp->source;
key->tp.dst = udp->dest;
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == NEXTHDR_SCTP) {
if (sctphdr_ok(skb)) {
struct sctphdr *sctp = sctp_hdr(skb);
key->tp.src = sctp->source;
key->tp.dst = sctp->dest;
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == NEXTHDR_ICMP) {
if (icmp6hdr_ok(skb)) {
error = parse_icmpv6(skb, key, nh_len);
if (error)
return error;
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
}
}
return 0;
}
int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
struct rt6_info *rt, unsigned int flags, int dontfrag)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_cork *cork;
struct sk_buff *skb, *skb_prev = NULL;
unsigned int maxfraglen, fragheaderlen;
int exthdrlen;
int hh_len;
int mtu;
int copy;
int err;
int offset = 0;
int csummode = CHECKSUM_NONE;
__u8 tx_flags = 0;
if (flags&MSG_PROBE)
return 0;
cork = &inet->cork.base;
if (skb_queue_empty(&sk->sk_write_queue)) {
/*
* setup for corking
*/
if (opt) {
if (WARN_ON(np->cork.opt))
return -EINVAL;
np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation);
if (unlikely(np->cork.opt == NULL))
return -ENOBUFS;
np->cork.opt->tot_len = opt->tot_len;
np->cork.opt->opt_flen = opt->opt_flen;
np->cork.opt->opt_nflen = opt->opt_nflen;
np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
sk->sk_allocation);
if (opt->dst0opt && !np->cork.opt->dst0opt)
return -ENOBUFS;
np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
sk->sk_allocation);
if (opt->dst1opt && !np->cork.opt->dst1opt)
return -ENOBUFS;
np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
sk->sk_allocation);
if (opt->hopopt && !np->cork.opt->hopopt)
return -ENOBUFS;
np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
sk->sk_allocation);
if (opt->srcrt && !np->cork.opt->srcrt)
return -ENOBUFS;
/* need source address above miyazawa*/
}
dst_hold(&rt->dst);
cork->dst = &rt->dst;
inet->cork.fl.u.ip6 = *fl6;
np->cork.hop_limit = hlimit;
np->cork.tclass = tclass;
if (rt->dst.flags & DST_XFRM_TUNNEL)
mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
rt->dst.dev->mtu : dst_mtu(&rt->dst);
else
mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
rt->dst.dev->mtu : dst_mtu(rt->dst.path);
if (np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
}
cork->fragsize = mtu;
if (dst_allfrag(rt->dst.path))
cork->flags |= IPCORK_ALLFRAG;
cork->length = 0;
sk->sk_sndmsg_page = NULL;
sk->sk_sndmsg_off = 0;
exthdrlen = rt->dst.header_len + (opt ? opt->opt_flen : 0) -
rt->rt6i_nfheader_len;
length += exthdrlen;
transhdrlen += exthdrlen;
} else {
rt = (struct rt6_info *)cork->dst;
fl6 = &inet->cork.fl.u.ip6;
opt = np->cork.opt;
transhdrlen = 0;
exthdrlen = 0;
mtu = cork->fragsize;
}
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
(opt ? opt->opt_nflen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
if (cork->length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen);
return -EMSGSIZE;
}
}
/* For UDP, check if TX timestamp is enabled */
if (sk->sk_type == SOCK_DGRAM) {
err = sock_tx_timestamp(sk, &tx_flags);
if (err)
goto error;
}
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
* Otherwise, we need to reserve fragment header and
* fragment alignment (= 8-15 octects, in total).
*
* Note that we may need to "move" the data from the tail of
* of the buffer to the new fragment when we split
* the message.
*
* FIXME: It may be fragmented into multiple chunks
* at once if non-fragmentable extension headers
* are too large.
* --yoshfuji
*/
cork->length += length;
if (length > mtu) {
int proto = sk->sk_protocol;
if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
return -EMSGSIZE;
}
if (proto == IPPROTO_UDP &&
(rt->dst.dev->features & NETIF_F_UFO)) {
err = ip6_ufo_append_data(sk, getfrag, from, length,
hh_len, fragheaderlen,
transhdrlen, mtu, flags, rt);
if (err)
goto error;
return 0;
}
}
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
goto alloc_new_skb;
while (length > 0) {
/* Check if the remaining data fits into current packet. */
copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
if (copy < length)
copy = maxfraglen - skb->len;
if (copy <= 0) {
char *data;
unsigned int datalen;
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
alloc_new_skb:
/* There's no room in the current skb */
if (skb)
fraggap = skb->len - maxfraglen;
else
fraggap = 0;
/* update mtu and maxfraglen if necessary */
if (skb == NULL || skb_prev == NULL)
ip6_append_data_mtu(&mtu, &maxfraglen,
fragheaderlen, skb, rt);
skb_prev = skb;
/*
* If remaining data exceeds the mtu,
* we know we need more fragment(s).
*/
datalen = length + fraggap;
if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
else
alloclen = datalen + fragheaderlen;
if (datalen != length + fraggap) {
/*
* this is not the last fragment, the trailer
* space is regarded as data space.
*/
datalen += rt->dst.trailer_len;
}
alloclen += rt->dst.trailer_len;
fraglen = datalen + fragheaderlen;
/*
* We just reserve space for fragment header.
* Note: this may be overallocation if the message
* (without MSG_MORE) fits into the MTU.
*/
alloclen += sizeof(struct frag_hdr);
if (transhdrlen) {
skb = sock_alloc_send_skb(sk,
alloclen + hh_len,
(flags & MSG_DONTWAIT), &err);
} else {
skb = NULL;
if (atomic_read(&sk->sk_wmem_alloc) <=
2 * sk->sk_sndbuf)
skb = sock_wmalloc(sk,
alloclen + hh_len, 1,
sk->sk_allocation);
if (unlikely(skb == NULL))
err = -ENOBUFS;
else {
/* Only the initial fragment
* is time stamped.
*/
tx_flags = 0;
}
}
if (skb == NULL)
goto error;
/*
* Fill in the control structures
*/
skb->ip_summed = csummode;
skb->csum = 0;
/* reserve for fragmentation */
skb_reserve(skb, hh_len+sizeof(struct frag_hdr));
if (sk->sk_type == SOCK_DGRAM)
skb_shinfo(skb)->tx_flags = tx_flags;
/*
* Find where to start putting bytes
*/
data = skb_put(skb, fraglen);
skb_set_network_header(skb, exthdrlen);
data += fragheaderlen;
skb->transport_header = (skb->network_header +
fragheaderlen);
if (fraggap) {
skb->csum = skb_copy_and_csum_bits(
skb_prev, maxfraglen,
data + transhdrlen, fraggap, 0);
skb_prev->csum = csum_sub(skb_prev->csum,
skb->csum);
data += fraggap;
pskb_trim_unique(skb_prev, maxfraglen);
}
copy = datalen - transhdrlen - fraggap;
if (copy < 0) {
err = -EINVAL;
kfree_skb(skb);
goto error;
} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
}
offset += copy;
length -= datalen - fraggap;
transhdrlen = 0;
exthdrlen = 0;
csummode = CHECKSUM_NONE;
/*
* Put the packet on the pending queue
*/
__skb_queue_tail(&sk->sk_write_queue, skb);
continue;
}
if (copy > length)
copy = length;
if (!(rt->dst.dev->features&NETIF_F_SG)) {
unsigned int off;
off = skb->len;
if (getfrag(from, skb_put(skb, copy),
offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
}
} else {
int i = skb_shinfo(skb)->nr_frags;
skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
struct page *page = sk->sk_sndmsg_page;
int off = sk->sk_sndmsg_off;
unsigned int left;
if (page && (left = PAGE_SIZE - off) > 0) {
if (copy >= left)
copy = left;
if (page != frag->page) {
if (i == MAX_SKB_FRAGS) {
err = -EMSGSIZE;
goto error;
}
get_page(page);
skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
frag = &skb_shinfo(skb)->frags[i];
}
} else if(i < MAX_SKB_FRAGS) {
if (copy > PAGE_SIZE)
copy = PAGE_SIZE;
page = alloc_pages(sk->sk_allocation, 0);
if (page == NULL) {
err = -ENOMEM;
goto error;
}
sk->sk_sndmsg_page = page;
sk->sk_sndmsg_off = 0;
skb_fill_page_desc(skb, i, page, 0, 0);
frag = &skb_shinfo(skb)->frags[i];
} else {
err = -EMSGSIZE;
goto error;
}
if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) {
err = -EFAULT;
goto error;
}
sk->sk_sndmsg_off += copy;
frag->size += copy;
skb->len += copy;
skb->data_len += copy;
skb->truesize += copy;
atomic_add(copy, &sk->sk_wmem_alloc);
}
offset += copy;
length -= copy;
}
return 0;
error:
cork->length -= length;
IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
return err;
}
