int rpl_ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
int (*output)(OVS_VPORT_OUTPUT_PARAMS))
{
struct iphdr *iph;
int ptr;
struct net_device *dev;
struct sk_buff *skb2;
unsigned int mtu, hlen, left, len, ll_rs;
int offset;
__be16 not_last_frag;
struct rtable *rt = skb_rtable(skb);
int err = 0;
dev = rt->dst.dev;
/* for offloaded checksums cleanup checksum before fragmentation */
if (skb->ip_summed == CHECKSUM_PARTIAL &&
(err = skb_checksum_help(skb)))
goto fail;
/*
* Point into the IP datagram header.
*/
iph = ip_hdr(skb);
mtu = ip_skb_dst_mtu(skb);
if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu)
mtu = IPCB(skb)->frag_max_size;
/*
* Setup starting values.
*/
hlen = iph->ihl * 4;
mtu = mtu - hlen; /* Size of data space */
IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE;
/* When frag_list is given, use it. First, check its validity:
* some transformers could create wrong frag_list or break existing
* one, it is not prohibited. In this case fall back to copying.
*
* LATER: this step can be merged to real generation of fragments,
* we can switch to copy when see the first bad fragment.
*/
if (skb_has_frag_list(skb)) {
struct sk_buff *frag, *frag2;
int first_len = skb_pagelen(skb);
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
ip_is_fragment(iph) ||
skb_cloned(skb))
goto slow_path;
skb_walk_frags(skb, frag) {
/* Correct geometry. */
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen)
goto slow_path_clean;
/* Partially cloned skb? */
if (skb_shared(frag))
goto slow_path_clean;
BUG_ON(frag->sk);
if (skb->sk) {
frag->sk = skb->sk;
frag->destructor = sock_wfree;
}
skb->truesize -= frag->truesize;
}
/* Everything is OK. Generate! */
err = 0;
offset = 0;
frag = skb_shinfo(skb)->frag_list;
skb_frag_list_init(skb);
skb->data_len = first_len - skb_headlen(skb);
skb->len = first_len;
iph->tot_len = htons(first_len);
iph->frag_off = htons(IP_MF);
ip_send_check(iph);
for (;;) {
/* Prepare header of the next frame,
* before previous one went down. */
if (frag) {
frag->ip_summed = CHECKSUM_NONE;
skb_reset_transport_header(frag);
__skb_push(frag, hlen);
skb_reset_network_header(frag);
memcpy(skb_network_header(frag), iph, hlen);
iph = ip_hdr(frag);
iph->tot_len = htons(frag->len);
ip_copy_metadata(frag, skb);
if (offset == 0)
ip_options_fragment(frag);
offset += skb->len - hlen;
iph->frag_off = htons(offset>>3);
if (frag->next)
iph->frag_off |= htons(IP_MF);
/* Ready, complete checksum */
ip_send_check(iph);
}
err = OUTPUT(net, sk, skb);
if (!err)
IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
if (err || !frag)
break;
skb = frag;
frag = skb->next;
skb->next = NULL;
}
if (err == 0) {
IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS);
return 0;
}
while (frag) {
skb = frag->next;
kfree_skb(frag);
frag = skb;
}
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
return err;
slow_path_clean:
skb_walk_frags(skb, frag2) {
if (frag2 == frag)
break;
frag2->sk = NULL;
frag2->destructor = NULL;
skb->truesize += frag2->truesize;
}
}
slow_path:
iph = ip_hdr(skb);
left = skb->len - hlen; /* Space per frame */
ptr = hlen; /* Where to start from */
ll_rs = LL_RESERVED_SPACE(rt->dst.dev);
/*
* Fragment the datagram.
*/
offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3;
not_last_frag = iph->frag_off & htons(IP_MF);
/*
* Keep copying data until we run out.
*/
while (left > 0) {
len = left;
/* IF: it doesn't fit, use 'mtu' - the data space left */
if (len > mtu)
len = mtu;
/* IF: we are not sending up to and including the packet end
then align the next start on an eight byte boundary */
if (len < left) {
len &= ~7;
}
/* Allocate buffer */
skb2 = alloc_skb(len + hlen + ll_rs, GFP_ATOMIC);
if (!skb2) {
err = -ENOMEM;
goto fail;
}
/*
* Set up data on packet
*/
ip_copy_metadata(skb2, skb);
skb_reserve(skb2, ll_rs);
skb_put(skb2, len + hlen);
skb_reset_network_header(skb2);
skb2->transport_header = skb2->network_header + hlen;
/*
* Charge the memory for the fragment to any owner
* it might possess
*/
if (skb->sk)
skb_set_owner_w(skb2, skb->sk);
/*
* Copy the packet header into the new buffer.
*/
skb_copy_from_linear_data(skb, skb_network_header(skb2), hlen);
/*
* Copy a block of the IP datagram.
*/
if (skb_copy_bits(skb, ptr, skb_transport_header(skb2), len))
BUG();
left -= len;
/*
* Fill in the new header fields.
*/
iph = ip_hdr(skb2);
iph->frag_off = htons((offset >> 3));
if (IPCB(skb)->flags & IPSKB_FRAG_PMTU)
iph->frag_off |= htons(IP_DF);
/* ANK: dirty, but effective trick. Upgrade options only if
* the segment to be fragmented was THE FIRST (otherwise,
* options are already fixed) and make it ONCE
* on the initial skb, so that all the following fragments
* will inherit fixed options.
*/
if (offset == 0)
ip_options_fragment(skb);
/*
* Added AC : If we are fragmenting a fragment that's not the
* last fragment then keep MF on each bit
*/
if (left > 0 || not_last_frag)
iph->frag_off |= htons(IP_MF);
ptr += len;
offset += len;
/*
* Put this fragment into the sending queue.
*/
iph->tot_len = htons(len + hlen);
ip_send_check(iph);
err = OUTPUT(net, sk, skb2);
if (err)
goto fail;
IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
}
consume_skb(skb);
IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS);
return err;
fail:
kfree_skb(skb);
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
return err;
}
/* 会话转发发送报文前的分片处理 */
int ip_session_out_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*))
{
struct iphdr *iph;
int raw = 0;
int ptr;
struct net_device *dev = skb->dev;
struct sk_buff *skb2;
unsigned int mtu, hlen, left, len, ll_rs, pad;
int offset;
__be16 not_last_frag;
int err = 0;
struct nf_conn* ct = (struct nf_conn*)skb->nfct;
struct drv_ff_cache_info *ff_info =
&((struct ff_cache_info_ex*)ct)->ff_info[IP_CT_DIR_REPLY];
//u32 out_inf = ff_info->out_inf;
mtu = 1500;
iph = skb->nh.iph;
if (unlikely((iph->frag_off & htons(IP_DF)) && !skb->local_df)) {
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGFAILS);
if(g_icmp_status.fragment_unreach == IP_OPTION_SUPPORT)
{
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
}
kfree_skb(skb);
return -EMSGSIZE;
}
/*
* Setup starting values.
*/
hlen = iph->ihl * 4;
IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE;
/* When frag_list is given, use it. First, check its validity:
* some transformers could create wrong frag_list or break existing
* one, it is not prohibited. In this case fall back to copying.
*
* LATER: this step can be merged to real generation of fragments,
* we can switch to copy when see the first bad fragment.
*/
if (skb_shinfo(skb)->frag_list) {
struct sk_buff *frag;
int first_len = skb_pagelen(skb);
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
(iph->frag_off & htons(IP_MF|IP_OFFSET)) ||
skb_cloned(skb))
goto slow_path;
for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) {
/* Correct geometry. */
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen)
goto slow_path;
/* Partially cloned skb? */
if (skb_shared(frag))
goto slow_path;
BUG_ON(frag->sk);
if (skb->sk) {
sock_hold(skb->sk);
frag->sk = skb->sk;
frag->destructor = sock_wfree;
skb->truesize -= frag->truesize;
}
}
/* Everything is OK. Generate! */
err = 0;
offset = 0;
frag = skb_shinfo(skb)->frag_list;
skb_shinfo(skb)->frag_list = NULL;
skb->data_len = first_len - skb_headlen(skb);
skb->len = first_len;
iph->tot_len = htons(first_len);
iph->frag_off = htons(IP_MF);
ip_send_check(iph);
/* process for session forward l2header */
skb_push(skb, ETH_HLEN);
memcpy(skb->data, (u8*)ff_info->gw_ether_mac, ETH_ALEN);
memcpy(skb->data+ETH_ALEN, (u8*)ff_info->gw_ether_mac+ETH_ALEN, ETH_ALEN);
memcpy(skb->data+2*ETH_ALEN, (u8*)ff_info->gw_ether_mac+2*ETH_ALEN, 2);
for (;;) {
/* Prepare header of the next frame,
* before previous one went down. */
if (frag) {
frag->ip_summed = CHECKSUM_NONE;
frag->h.raw = frag->data;
frag->nh.raw = __skb_push(frag, hlen);
memcpy(frag->nh.raw, iph, hlen);
iph = frag->nh.iph;
iph->tot_len = htons(frag->len);
ip_copy_metadata(frag, skb);
if (offset == 0)
ip_options_fragment(frag);
offset += skb->len - hlen - ETH_HLEN;
iph->frag_off = htons(offset>>3);
if (frag->next != NULL)
iph->frag_off |= htons(IP_MF);
/* Ready, complete checksum */
ip_send_check(iph);
/* process for session forward l2header */
skb_push(frag, ETH_HLEN);
memcpy(frag->data, (u8*)ff_info->gw_ether_mac, ETH_ALEN);
memcpy(frag->data+ETH_ALEN,
(u8*)ff_info->gw_ether_mac+ETH_ALEN, ETH_ALEN);
memcpy(frag->data+2*ETH_ALEN,
(u8*)ff_info->gw_ether_mac+2*ETH_ALEN, 2);
}
g_session_forward_count++;
err = output(skb);
if (!err)
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGCREATES);
if (err || !frag)
break;
skb = frag;
frag = skb->next;
skb->next = NULL;
}
if (err == 0) {
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGOKS);
return 0;
}
while (frag) {
skb = frag->next;
kfree_skb(frag);
frag = skb;
}
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGFAILS);
return err;
}
slow_path:
left = skb->len - hlen; /* Space per frame */
ptr = raw + hlen; /* Where to start from */
/* for bridged IP traffic encapsulated inside f.e. a vlan header,
* we need to make room for the encapsulating header
*/
pad = nf_bridge_pad(skb);
ll_rs = ((ETH_HLEN+pad)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD;
mtu -= pad;
/*
* Fragment the datagram.
*/
offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3;
not_last_frag = iph->frag_off & htons(IP_MF);
/*
* Keep copying data until we run out.
*/
while(left > 0) {
len = left;
/* IF: it doesn't fit, use 'mtu' - the data space left */
if (len > mtu)
len = mtu;
/* IF: we are not sending upto and including the packet end
then align the next start on an eight byte boundary */
if (len < left) {
len &= ~7;
}
/*
* Allocate buffer.
*/
if ((skb2 = alloc_skb(len+hlen+ll_rs, GFP_ATOMIC)) == NULL) {
NETDEBUG(KERN_INFO "IP: frag: no memory for new fragment!\n");
err = -ENOMEM;
goto fail;
}
/*
* Set up data on packet
*/
ip_copy_metadata(skb2, skb);
skb2->mac_len = skb->mac_len;
skb2->ff_flag = skb->ff_flag;
skb2->in_if = skb->in_if;
skb_reserve(skb2, ll_rs);
skb_put(skb2, len + hlen);
skb2->mac.raw = skb2->data - skb2->mac_len;
skb2->nh.raw = skb2->data;
skb2->h.raw = skb2->data + hlen;
/*
* Charge the memory for the fragment to any owner
* it might possess
*/
if (skb->sk)
skb_set_owner_w(skb2, skb->sk);
/*
* Copy the packet header into the new buffer.
*/
memcpy(skb2->nh.raw, skb->data, hlen);
/*
* Copy a block of the IP datagram.
*/
if (skb_copy_bits(skb, ptr, skb2->h.raw, len))
BUG();
left -= len;
/*
* Fill in the new header fields.
*/
iph = skb2->nh.iph;
iph->frag_off = htons((offset >> 3));
/* ANK: dirty, but effective trick. Upgrade options only if
* the segment to be fragmented was THE FIRST (otherwise,
* options are already fixed) and make it ONCE
* on the initial skb, so that all the following fragments
* will inherit fixed options.
*/
if (offset == 0)
ip_options_fragment(skb);
/*
* Added AC : If we are fragmenting a fragment that's not the
* last fragment then keep MF on each bit
*/
if (left > 0 || not_last_frag)
iph->frag_off |= htons(IP_MF);
ptr += len;
offset += len;
/*
* Put this fragment into the sending queue.
*/
iph->tot_len = htons(len + hlen);
ip_send_check(iph);
/* process for session forward l2header */
memcpy(skb2->mac.raw, (u8*)ff_info->gw_ether_mac, ETH_ALEN);
memcpy(skb2->mac.raw+ETH_ALEN, (u8*)ff_info->gw_ether_mac+ETH_ALEN, ETH_ALEN);
memcpy(skb2->mac.raw+2*ETH_ALEN, (u8*)ff_info->gw_ether_mac+2*ETH_ALEN, 2);
err = output(skb2);
if (err)
goto fail;
g_session_forward_count++;
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGCREATES);
}
kfree_skb(skb);
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGOKS);
return err;
fail:
kfree_skb(skb);
IP_INC_STATS(if_dev_vrf(dev), IPSTATS_MIB_FRAGFAILS);
return err;
}
