static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev)
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct iphdr *iph;
struct sk_buff *fp, *head = qp->q.fragments;
int len;
int ihlen;
int err;
int sum_truesize;
u8 ecn;
ipq_kill(qp);
ecn = ip_frag_ecn_table[qp->ecn];
if (unlikely(ecn == 0xff)) {
err = -EINVAL;
goto out_fail;
}
/* Make the one we just received the head. */
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (!fp)
goto out_nomem;
fp->next = head->next;
if (!fp->next)
qp->q.fragments_tail = fp;
prev->next = fp;
skb_morph(head, qp->q.fragments);
head->next = qp->q.fragments->next;
consume_skb(qp->q.fragments);
qp->q.fragments = head;
}
WARN_ON(head == NULL);
WARN_ON(FRAG_CB(head)->offset != 0);
/* Allocate a new buffer for the datagram. */
ihlen = ip_hdrlen(head);
len = ihlen + qp->q.len;
err = -E2BIG;
if (len > 65535)
goto out_oversize;
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
goto out_nomem;
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
if (skb_has_frag_list(head)) {
struct sk_buff *clone;
int i, plen = 0;
if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
goto out_nomem;
clone->next = head->next;
head->next = clone;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
clone->len = clone->data_len = head->data_len - plen;
head->data_len -= clone->len;
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
add_frag_mem_limit(&qp->q, clone->truesize);
}
skb_push(head, head->data - skb_network_header(head));
sum_truesize = head->truesize;
for (fp = head->next; fp;) {
bool headstolen;
int delta;
struct sk_buff *next = fp->next;
sum_truesize += fp->truesize;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
if (skb_try_coalesce(head, fp, &headstolen, &delta)) {
kfree_skb_partial(fp, headstolen);
} else {
if (!skb_shinfo(head)->frag_list)
skb_shinfo(head)->frag_list = fp;
head->data_len += fp->len;
head->len += fp->len;
head->truesize += fp->truesize;
}
fp = next;
}
sub_frag_mem_limit(&qp->q, sum_truesize);
head->next = NULL;
head->dev = dev;
head->tstamp = qp->q.stamp;
IPCB(head)->frag_max_size = qp->q.max_size;
iph = ip_hdr(head);
/* max_size != 0 implies at least one fragment had IP_DF set */
iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0;
iph->tot_len = htons(len);
iph->tos |= ecn;
ip_send_check(iph);
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.fragments_tail = NULL;
return 0;
out_nomem:
LIMIT_NETDEBUG(KERN_ERR pr_fmt("queue_glue: no memory for gluing queue %p\n"),
qp);
err = -ENOMEM;
goto out_fail;
out_oversize:
net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
out_fail:
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
return err;
}
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev)
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct iphdr *iph;
struct sk_buff *fp, *head = qp->q.fragments;
int len;
int ihlen;
int err;
u8 ecn;
ipq_kill(qp);
ecn = ip_frag_ecn_table[qp->ecn];
if (unlikely(ecn == 0xff)) {
err = -EINVAL;
goto out_fail;
}
/* Make the one we just received the head. */
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (!fp)
goto out_nomem;
fp->next = head->next;
if (!fp->next)
qp->q.fragments_tail = fp;
prev->next = fp;
skb_morph(head, qp->q.fragments);
head->next = qp->q.fragments->next;
consume_skb(qp->q.fragments);
qp->q.fragments = head;
}
WARN_ON(!head);
WARN_ON(FRAG_CB(head)->offset != 0);
/* Allocate a new buffer for the datagram. */
ihlen = ip_hdrlen(head);
len = ihlen + qp->q.len;
err = -E2BIG;
if (len > 65535)
goto out_oversize;
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
goto out_nomem;
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
if (skb_has_frag_list(head)) {
struct sk_buff *clone;
int i, plen = 0;
clone = alloc_skb(0, GFP_ATOMIC);
if (!clone)
goto out_nomem;
clone->next = head->next;
head->next = clone;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
clone->len = clone->data_len = head->data_len - plen;
head->data_len -= clone->len;
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
add_frag_mem_limit(qp->q.net, clone->truesize);
}
skb_shinfo(head)->frag_list = head->next;
skb_push(head, head->data - skb_network_header(head));
for (fp=head->next; fp; fp = fp->next) {
head->data_len += fp->len;
head->len += fp->len;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
}
sub_frag_mem_limit(qp->q.net, head->truesize);
head->next = NULL;
head->dev = dev;
head->tstamp = qp->q.stamp;
IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
iph = ip_hdr(head);
iph->tot_len = htons(len);
iph->tos |= ecn;
/* When we set IP_DF on a refragmented skb we must also force a
* call to ip_fragment to avoid forwarding a DF-skb of size s while
* original sender only sent fragments of size f (where f < s).
*
* We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest
* frag seen to avoid sending tiny DF-fragments in case skb was built
* from one very small df-fragment and one large non-df frag.
*/
if (qp->max_df_size == qp->q.max_size) {
IPCB(head)->flags |= IPSKB_FRAG_PMTU;
iph->frag_off = htons(IP_DF);
} else {
iph->frag_off = 0;
}
ip_send_check(iph);
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.fragments_tail = NULL;
return 0;
out_nomem:
net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp);
err = -ENOMEM;
goto out_fail;
out_oversize:
net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
out_fail:
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
return err;
}
/* Add new segment to existing queue. */
static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
{
struct sk_buff *prev, *next;
struct net_device *dev;
int flags, offset;
int ihl, end;
int err = -ENOENT;
u8 ecn;
if (qp->q.last_in & INET_FRAG_COMPLETE)
goto err;
if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) &&
unlikely(ip_frag_too_far(qp)) &&
unlikely(err = ip_frag_reinit(qp))) {
ipq_kill(qp);
goto err;
}
ecn = ip4_frag_ecn(ip_hdr(skb)->tos);
offset = ntohs(ip_hdr(skb)->frag_off);
flags = offset & ~IP_OFFSET;
offset &= IP_OFFSET;
offset <<= 3; /* offset is in 8-byte chunks */
ihl = ip_hdrlen(skb);
/* Determine the position of this fragment. */
end = offset + skb->len - skb_network_offset(skb) - ihl;
err = -EINVAL;
/* Is this the final fragment? */
if ((flags & IP_MF) == 0) {
/* If we already have some bits beyond end
* or have different end, the segment is corrupted.
*/
if (end < qp->q.len ||
((qp->q.last_in & INET_FRAG_LAST_IN) && end != qp->q.len))
goto err;
qp->q.last_in |= INET_FRAG_LAST_IN;
qp->q.len = end;
} else {
if (end&7) {
end &= ~7;
if (skb->ip_summed != CHECKSUM_UNNECESSARY)
skb->ip_summed = CHECKSUM_NONE;
}
if (end > qp->q.len) {
/* Some bits beyond end -> corruption. */
if (qp->q.last_in & INET_FRAG_LAST_IN)
goto err;
qp->q.len = end;
}
}
if (end == offset)
goto err;
err = -ENOMEM;
if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
goto err;
err = pskb_trim_rcsum(skb, end - offset);
if (err)
goto err;
/* Find out which fragments are in front and at the back of us
* in the chain of fragments so far. We must know where to put
* this fragment, right?
*/
prev = qp->q.fragments_tail;
if (!prev || FRAG_CB(prev)->offset < offset) {
next = NULL;
goto found;
}
prev = NULL;
for (next = qp->q.fragments; next != NULL; next = next->next) {
if (FRAG_CB(next)->offset >= offset)
break; /* bingo! */
prev = next;
}
found:
/* We found where to put this one. Check for overlap with
* preceding fragment, and, if needed, align things so that
* any overlaps are eliminated.
*/
if (prev) {
int i = (FRAG_CB(prev)->offset + prev->len) - offset;
if (i > 0) {
offset += i;
err = -EINVAL;
if (end <= offset)
goto err;
err = -ENOMEM;
if (!pskb_pull(skb, i))
goto err;
if (skb->ip_summed != CHECKSUM_UNNECESSARY)
skb->ip_summed = CHECKSUM_NONE;
}
}
err = -ENOMEM;
while (next && FRAG_CB(next)->offset < end) {
int i = end - FRAG_CB(next)->offset; /* overlap is 'i' bytes */
if (i < next->len) {
/* Eat head of the next overlapped fragment
* and leave the loop. The next ones cannot overlap.
*/
if (!pskb_pull(next, i))
goto err;
FRAG_CB(next)->offset += i;
qp->q.meat -= i;
if (next->ip_summed != CHECKSUM_UNNECESSARY)
next->ip_summed = CHECKSUM_NONE;
break;
} else {
struct sk_buff *free_it = next;
/* Old fragment is completely overridden with
* new one drop it.
*/
next = next->next;
if (prev)
prev->next = next;
else
qp->q.fragments = next;
qp->q.meat -= free_it->len;
sub_frag_mem_limit(&qp->q, free_it->truesize);
kfree_skb(free_it);
}
}
FRAG_CB(skb)->offset = offset;
/* Insert this fragment in the chain of fragments. */
skb->next = next;
if (!next)
qp->q.fragments_tail = skb;
if (prev)
prev->next = skb;
else
qp->q.fragments = skb;
dev = skb->dev;
if (dev) {
qp->iif = dev->ifindex;
skb->dev = NULL;
}
qp->q.stamp = skb->tstamp;
qp->q.meat += skb->len;
qp->ecn |= ecn;
add_frag_mem_limit(&qp->q, skb->truesize);
if (offset == 0)
qp->q.last_in |= INET_FRAG_FIRST_IN;
if (ip_hdr(skb)->frag_off & htons(IP_DF) &&
skb->len + ihl > qp->q.max_size)
qp->q.max_size = skb->len + ihl;
if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
qp->q.meat == qp->q.len) {
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
err = ip_frag_reasm(qp, prev, dev);
skb->_skb_refdst = orefdst;
return err;
}
skb_dst_drop(skb);
inet_frag_lru_move(&qp->q);
return -EINPROGRESS;
err:
kfree_skb(skb);
return err;
}
static int lowpan_frag_queue(struct lowpan_frag_queue *fq,
struct sk_buff *skb, const u8 frag_type)
{
struct sk_buff *prev, *next;
struct net_device *dev;
int end, offset;
if (fq->q.flags & INET_FRAG_COMPLETE)
goto err;
offset = lowpan_cb(skb)->d_offset << 3;
end = lowpan_cb(skb)->d_size;
/* Is this the final fragment? */
if (offset + skb->len == end) {
/* If we already have some bits beyond end
* or have different end, the segment is corrupted.
*/
if (end < fq->q.len ||
((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len))
goto err;
fq->q.flags |= INET_FRAG_LAST_IN;
fq->q.len = end;
} else {
if (end > fq->q.len) {
/* Some bits beyond end -> corruption. */
if (fq->q.flags & INET_FRAG_LAST_IN)
goto err;
fq->q.len = end;
}
}
/* Find out which fragments are in front and at the back of us
* in the chain of fragments so far. We must know where to put
* this fragment, right?
*/
prev = fq->q.fragments_tail;
if (!prev || lowpan_cb(prev)->d_offset < lowpan_cb(skb)->d_offset) {
next = NULL;
goto found;
}
prev = NULL;
for (next = fq->q.fragments; next != NULL; next = next->next) {
if (lowpan_cb(next)->d_offset >= lowpan_cb(skb)->d_offset)
break; /* bingo! */
prev = next;
}
found:
/* Insert this fragment in the chain of fragments. */
skb->next = next;
if (!next)
fq->q.fragments_tail = skb;
if (prev)
prev->next = skb;
else
fq->q.fragments = skb;
dev = skb->dev;
if (dev)
skb->dev = NULL;
fq->q.stamp = skb->tstamp;
if (frag_type == LOWPAN_DISPATCH_FRAG1) {
/* Calculate uncomp. 6lowpan header to estimate full size */
fq->q.meat += lowpan_uncompress_size(skb, NULL);
fq->q.flags |= INET_FRAG_FIRST_IN;
} else {
fq->q.meat += skb->len;
}
add_frag_mem_limit(&fq->q, skb->truesize);
if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
fq->q.meat == fq->q.len) {
int res;
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
res = lowpan_frag_reasm(fq, prev, dev);
skb->_skb_refdst = orefdst;
return res;
}
return -1;
err:
kfree_skb(skb);
return -1;
}
/* Check if this packet is complete.
* Returns NULL on failure by any reason, and pointer
* to current nexthdr field in reassembled frame.
*
* It is called with locked fq, and caller must check that
* queue is eligible for reassembly i.e. it is not COMPLETE,
* the last and the first frames arrived and all the bits are here.
*/
static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev,
struct net_device *dev)
{
struct sk_buff *fp, *head = fq->q.fragments;
int sum_truesize;
inet_frag_kill(&fq->q, &lowpan_frags);
/* Make the one we just received the head. */
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (!fp)
goto out_oom;
fp->next = head->next;
if (!fp->next)
fq->q.fragments_tail = fp;
prev->next = fp;
skb_morph(head, fq->q.fragments);
head->next = fq->q.fragments->next;
consume_skb(fq->q.fragments);
fq->q.fragments = head;
}
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
goto out_oom;
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments.
*/
if (skb_has_frag_list(head)) {
struct sk_buff *clone;
int i, plen = 0;
clone = alloc_skb(0, GFP_ATOMIC);
if (!clone)
goto out_oom;
clone->next = head->next;
head->next = clone;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
clone->len = head->data_len - plen;
clone->data_len = clone->len;
head->data_len -= clone->len;
head->len -= clone->len;
add_frag_mem_limit(&fq->q, clone->truesize);
}
WARN_ON(head == NULL);
sum_truesize = head->truesize;
for (fp = head->next; fp;) {
bool headstolen;
int delta;
struct sk_buff *next = fp->next;
sum_truesize += fp->truesize;
if (skb_try_coalesce(head, fp, &headstolen, &delta)) {
kfree_skb_partial(fp, headstolen);
} else {
if (!skb_shinfo(head)->frag_list)
skb_shinfo(head)->frag_list = fp;
head->data_len += fp->len;
head->len += fp->len;
head->truesize += fp->truesize;
}
fp = next;
}
sub_frag_mem_limit(&fq->q, sum_truesize);
head->next = NULL;
head->dev = dev;
head->tstamp = fq->q.stamp;
fq->q.fragments = NULL;
fq->q.fragments_tail = NULL;
return 1;
out_oom:
net_dbg_ratelimited("lowpan_frag_reasm: no memory for reassembly\n");
return -1;
}
static struct frag_queue *
fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
{
struct frag_v6_compare_key key = {
.id = id,
.saddr = hdr->saddr,
.daddr = hdr->daddr,
.user = IP6_DEFRAG_LOCAL_DELIVER,
.iif = iif,
};
struct inet_frag_queue *q;
if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
IPV6_ADDR_LINKLOCAL)))
key.iif = 0;
q = inet_frag_find(&net->ipv6.frags, &key);
if (!q)
return NULL;
return container_of(q, struct frag_queue, q);
}
static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
struct frag_hdr *fhdr, int nhoff,
u32 *prob_offset)
{
struct net *net = dev_net(skb_dst(skb)->dev);
int offset, end, fragsize;
struct sk_buff *prev_tail;
struct net_device *dev;
int err = -ENOENT;
u8 ecn;
if (fq->q.flags & INET_FRAG_COMPLETE)
goto err;
err = -EINVAL;
offset = ntohs(fhdr->frag_off) & ~0x7;
end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));
if ((unsigned int)end > IPV6_MAXPLEN) {
*prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb);
/* note that if prob_offset is set, the skb is freed elsewhere,
* we do not free it here.
*/
return -1;
}
ecn = ip6_frag_ecn(ipv6_hdr(skb));
if (skb->ip_summed == CHECKSUM_COMPLETE) {
const unsigned char *nh = skb_network_header(skb);
skb->csum = csum_sub(skb->csum,
csum_partial(nh, (u8 *)(fhdr + 1) - nh,
0));
}
/* Is this the final fragment? */
if (!(fhdr->frag_off & htons(IP6_MF))) {
/* If we already have some bits beyond end
* or have different end, the segment is corrupted.
*/
if (end < fq->q.len ||
((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len))
goto discard_fq;
fq->q.flags |= INET_FRAG_LAST_IN;
fq->q.len = end;
} else {
/* Check if the fragment is rounded to 8 bytes.
* Required by the RFC.
*/
if (end & 0x7) {
/* RFC2460 says always send parameter problem in
* this case. -DaveM
*/
*prob_offset = offsetof(struct ipv6hdr, payload_len);
return -1;
}
if (end > fq->q.len) {
/* Some bits beyond end -> corruption. */
if (fq->q.flags & INET_FRAG_LAST_IN)
goto discard_fq;
fq->q.len = end;
}
}
if (end == offset)
goto discard_fq;
err = -ENOMEM;
/* Point into the IP datagram 'data' part. */
if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
goto discard_fq;
err = pskb_trim_rcsum(skb, end - offset);
if (err)
goto discard_fq;
/* Note : skb->rbnode and skb->dev share the same location. */
dev = skb->dev;
/* Makes sure compiler wont do silly aliasing games */
barrier();
prev_tail = fq->q.fragments_tail;
err = inet_frag_queue_insert(&fq->q, skb, offset, end);
if (err)
goto insert_error;
if (dev)
fq->iif = dev->ifindex;
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
fq->ecn |= ecn;
add_frag_mem_limit(fq->q.net, skb->truesize);
fragsize = -skb_network_offset(skb) + skb->len;
if (fragsize > fq->q.max_size)
fq->q.max_size = fragsize;
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
*/
if (offset == 0) {
fq->nhoffset = nhoff;
fq->q.flags |= INET_FRAG_FIRST_IN;
}
if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
fq->q.meat == fq->q.len) {
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
err = ip6_frag_reasm(fq, skb, prev_tail, dev);
skb->_skb_refdst = orefdst;
return err;
}
skb_dst_drop(skb);
return -EINPROGRESS;
insert_error:
if (err == IPFRAG_DUP) {
kfree_skb(skb);
return -EINVAL;
}
err = -EINVAL;
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASM_OVERLAPS);
discard_fq:
inet_frag_kill(&fq->q);
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
err:
kfree_skb(skb);
return err;
}
/*
* Check if this packet is complete.
* Returns NULL on failure by any reason, and pointer
* to current nexthdr field in reassembled frame.
*
* It is called with locked fq, and caller must check that
* queue is eligible for reassembly i.e. it is not COMPLETE,
* the last and the first frames arrived and all the bits are here.
*/
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev)
{
struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
struct sk_buff *fp, *head = fq->q.fragments;
int payload_len;
unsigned int nhoff;
int sum_truesize;
u8 ecn;
inet_frag_kill(&fq->q, &ip6_frags);
ecn = ip_frag_ecn_table[fq->ecn];
if (unlikely(ecn == 0xff))
goto out_fail;
/* Make the one we just received the head. */
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (!fp)
goto out_oom;
fp->next = head->next;
if (!fp->next)
fq->q.fragments_tail = fp;
prev->next = fp;
skb_morph(head, fq->q.fragments);
head->next = fq->q.fragments->next;
consume_skb(fq->q.fragments);
fq->q.fragments = head;
}
WARN_ON(head == NULL);
WARN_ON(FRAG6_CB(head)->offset != 0);
/* Unfragmented part is taken from the first segment. */
payload_len = ((head->data - skb_network_header(head)) -
sizeof(struct ipv6hdr) + fq->q.len -
sizeof(struct frag_hdr));
if (payload_len > IPV6_MAXPLEN)
goto out_oversize;
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
goto out_oom;
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
if (skb_has_frag_list(head)) {
struct sk_buff *clone;
int i, plen = 0;
clone = alloc_skb(0, GFP_ATOMIC);
if (!clone)
goto out_oom;
clone->next = head->next;
head->next = clone;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
clone->len = clone->data_len = head->data_len - plen;
head->data_len -= clone->len;
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
add_frag_mem_limit(fq->q.net, clone->truesize);
}
/* We have to remove fragment header from datagram and to relocate
* header in order to calculate ICV correctly. */
nhoff = fq->nhoffset;
skb_network_header(head)[nhoff] = skb_transport_header(head)[0];
memmove(head->head + sizeof(struct frag_hdr), head->head,
(head->data - head->head) - sizeof(struct frag_hdr));
if (skb_mac_header_was_set(head))
head->mac_header += sizeof(struct frag_hdr);
head->network_header += sizeof(struct frag_hdr);
skb_reset_transport_header(head);
skb_push(head, head->data - skb_network_header(head));
sum_truesize = head->truesize;
for (fp = head->next; fp;) {
bool headstolen;
int delta;
struct sk_buff *next = fp->next;
sum_truesize += fp->truesize;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
if (skb_try_coalesce(head, fp, &headstolen, &delta)) {
kfree_skb_partial(fp, headstolen);
} else {
if (!skb_shinfo(head)->frag_list)
skb_shinfo(head)->frag_list = fp;
head->data_len += fp->len;
head->len += fp->len;
head->truesize += fp->truesize;
}
fp = next;
}
sub_frag_mem_limit(fq->q.net, sum_truesize);
head->next = NULL;
head->dev = dev;
head->tstamp = fq->q.stamp;
ipv6_hdr(head)->payload_len = htons(payload_len);
ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn);
IP6CB(head)->nhoff = nhoff;
IP6CB(head)->flags |= IP6SKB_FRAGMENTED;
IP6CB(head)->frag_max_size = fq->q.max_size;
/* Yes, and fold redundant checksum back. 8) */
skb_postpush_rcsum(head, skb_network_header(head),
skb_network_header_len(head));
rcu_read_lock();
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
rcu_read_unlock();
fq->q.fragments = NULL;
fq->q.fragments_tail = NULL;
return 1;
out_oversize:
net_dbg_ratelimited("ip6_frag_reasm: payload len = %d\n", payload_len);
goto out_fail;
out_oom:
net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n");
out_fail:
rcu_read_lock();
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
rcu_read_unlock();
return -1;
}
static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
struct frag_hdr *fhdr, int nhoff)
{
struct sk_buff *prev, *next;
struct net_device *dev;
int offset, end, fragsize;
struct net *net = dev_net(skb_dst(skb)->dev);
u8 ecn;
if (fq->q.flags & INET_FRAG_COMPLETE)
goto err;
offset = ntohs(fhdr->frag_off) & ~0x7;
end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));
if ((unsigned int)end > IPV6_MAXPLEN) {
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_INHDRERRORS);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
((u8 *)&fhdr->frag_off -
skb_network_header(skb)));
return -1;
}
ecn = ip6_frag_ecn(ipv6_hdr(skb));
if (skb->ip_summed == CHECKSUM_COMPLETE) {
const unsigned char *nh = skb_network_header(skb);
skb->csum = csum_sub(skb->csum,
csum_partial(nh, (u8 *)(fhdr + 1) - nh,
0));
}
/* Is this the final fragment? */
if (!(fhdr->frag_off & htons(IP6_MF))) {
/* If we already have some bits beyond end
* or have different end, the segment is corrupted.
*/
if (end < fq->q.len ||
((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len))
goto err;
fq->q.flags |= INET_FRAG_LAST_IN;
fq->q.len = end;
} else {
/* Check if the fragment is rounded to 8 bytes.
* Required by the RFC.
*/
if (end & 0x7) {
/* RFC2460 says always send parameter problem in
* this case. -DaveM
*/
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_INHDRERRORS);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
offsetof(struct ipv6hdr, payload_len));
return -1;
}
if (end > fq->q.len) {
/* Some bits beyond end -> corruption. */
if (fq->q.flags & INET_FRAG_LAST_IN)
goto err;
fq->q.len = end;
}
}
if (end == offset)
goto err;
/* Point into the IP datagram 'data' part. */
if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
goto err;
if (pskb_trim_rcsum(skb, end - offset))
goto err;
/* Find out which fragments are in front and at the back of us
* in the chain of fragments so far. We must know where to put
* this fragment, right?
*/
prev = fq->q.fragments_tail;
if (!prev || FRAG6_CB(prev)->offset < offset) {
next = NULL;
goto found;
}
prev = NULL;
for (next = fq->q.fragments; next != NULL; next = next->next) {
if (FRAG6_CB(next)->offset >= offset)
break; /* bingo! */
prev = next;
}
found:
/* RFC5722, Section 4, amended by Errata ID : 3089
* When reassembling an IPv6 datagram, if
* one or more its constituent fragments is determined to be an
* overlapping fragment, the entire datagram (and any constituent
* fragments) MUST be silently discarded.
*/
/* Check for overlap with preceding fragment. */
if (prev &&
(FRAG6_CB(prev)->offset + prev->len) > offset)
goto discard_fq;
/* Look for overlap with succeeding segment. */
if (next && FRAG6_CB(next)->offset < end)
goto discard_fq;
FRAG6_CB(skb)->offset = offset;
/* Insert this fragment in the chain of fragments. */
skb->next = next;
if (!next)
fq->q.fragments_tail = skb;
if (prev)
prev->next = skb;
else
fq->q.fragments = skb;
dev = skb->dev;
if (dev) {
fq->iif = dev->ifindex;
skb->dev = NULL;
}
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
fq->ecn |= ecn;
add_frag_mem_limit(fq->q.net, skb->truesize);
fragsize = -skb_network_offset(skb) + skb->len;
if (fragsize > fq->q.max_size)
fq->q.max_size = fragsize;
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
*/
if (offset == 0) {
fq->nhoffset = nhoff;
fq->q.flags |= INET_FRAG_FIRST_IN;
}
if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
fq->q.meat == fq->q.len) {
int res;
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
res = ip6_frag_reasm(fq, prev, dev);
skb->_skb_refdst = orefdst;
return res;
}
skb_dst_drop(skb);
return -1;
discard_fq:
inet_frag_kill(&fq->q, &ip6_frags);
err:
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -1;
}
/* Build a new IP datagram from all its fragments. */
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
struct sk_buff *prev_tail, struct net_device *dev)
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct iphdr *iph;
struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments);
struct sk_buff **nextp; /* To build frag_list. */
struct rb_node *rbn;
int len;
int ihlen;
int err;
u8 ecn;
ipq_kill(qp);
ecn = ip_frag_ecn_table[qp->ecn];
if (unlikely(ecn == 0xff)) {
err = -EINVAL;
goto out_fail;
}
/* Make the one we just received the head. */
if (head != skb) {
fp = skb_clone(skb, GFP_ATOMIC);
if (!fp)
goto out_nomem;
FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
if (RB_EMPTY_NODE(&skb->rbnode))
FRAG_CB(prev_tail)->next_frag = fp;
else
rb_replace_node(&skb->rbnode, &fp->rbnode,
&qp->q.rb_fragments);
if (qp->q.fragments_tail == skb)
qp->q.fragments_tail = fp;
skb_morph(skb, head);
FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
rb_replace_node(&head->rbnode, &skb->rbnode,
&qp->q.rb_fragments);
consume_skb(head);
head = skb;
}
WARN_ON(head->ip_defrag_offset != 0);
/* Allocate a new buffer for the datagram. */
ihlen = ip_hdrlen(head);
len = ihlen + qp->q.len;
err = -E2BIG;
if (len > 65535)
goto out_oversize;
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
goto out_nomem;
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
if (skb_has_frag_list(head)) {
struct sk_buff *clone;
int i, plen = 0;
clone = alloc_skb(0, GFP_ATOMIC);
if (!clone)
goto out_nomem;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
clone->len = clone->data_len = head->data_len - plen;
head->truesize += clone->truesize;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
add_frag_mem_limit(qp->q.net, clone->truesize);
skb_shinfo(head)->frag_list = clone;
nextp = &clone->next;
} else {
nextp = &skb_shinfo(head)->frag_list;
}
skb_push(head, head->data - skb_network_header(head));
/* Traverse the tree in order, to build frag_list. */
fp = FRAG_CB(head)->next_frag;
rbn = rb_next(&head->rbnode);
rb_erase(&head->rbnode, &qp->q.rb_fragments);
while (rbn || fp) {
/* fp points to the next sk_buff in the current run;
* rbn points to the next run.
*/
/* Go through the current run. */
while (fp) {
*nextp = fp;
nextp = &fp->next;
fp->prev = NULL;
memset(&fp->rbnode, 0, sizeof(fp->rbnode));
head->data_len += fp->len;
head->len += fp->len;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
fp = FRAG_CB(fp)->next_frag;
}
/* Move to the next run. */
if (rbn) {
struct rb_node *rbnext = rb_next(rbn);
fp = rb_to_skb(rbn);
rb_erase(rbn, &qp->q.rb_fragments);
rbn = rbnext;
}
}
sub_frag_mem_limit(qp->q.net, head->truesize);
*nextp = NULL;
head->next = NULL;
head->prev = NULL;
head->dev = dev;
head->tstamp = qp->q.stamp;
IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
iph = ip_hdr(head);
iph->tot_len = htons(len);
iph->tos |= ecn;
/* When we set IP_DF on a refragmented skb we must also force a
* call to ip_fragment to avoid forwarding a DF-skb of size s while
* original sender only sent fragments of size f (where f < s).
*
* We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest
* frag seen to avoid sending tiny DF-fragments in case skb was built
* from one very small df-fragment and one large non-df frag.
*/
if (qp->max_df_size == qp->q.max_size) {
IPCB(head)->flags |= IPSKB_FRAG_PMTU;
iph->frag_off = htons(IP_DF);
} else {
iph->frag_off = 0;
}
ip_send_check(iph);
__IP_INC_STATS(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.rb_fragments = RB_ROOT;
qp->q.fragments_tail = NULL;
qp->q.last_run_head = NULL;
return 0;
out_nomem:
net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp);
err = -ENOMEM;
goto out_fail;
out_oversize:
net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr);
out_fail:
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
return err;
}
/* Add new segment to existing queue. */
static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct rb_node **rbn, *parent;
struct sk_buff *skb1, *prev_tail;
struct net_device *dev;
unsigned int fragsize;
int flags, offset;
int ihl, end;
int err = -ENOENT;
u8 ecn;
if (qp->q.flags & INET_FRAG_COMPLETE)
goto err;
if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) &&
unlikely(ip_frag_too_far(qp)) &&
unlikely(err = ip_frag_reinit(qp))) {
ipq_kill(qp);
goto err;
}
ecn = ip4_frag_ecn(ip_hdr(skb)->tos);
offset = ntohs(ip_hdr(skb)->frag_off);
flags = offset & ~IP_OFFSET;
offset &= IP_OFFSET;
offset <<= 3; /* offset is in 8-byte chunks */
ihl = ip_hdrlen(skb);
/* Determine the position of this fragment. */
end = offset + skb->len - skb_network_offset(skb) - ihl;
err = -EINVAL;
/* Is this the final fragment? */
if ((flags & IP_MF) == 0) {
/* If we already have some bits beyond end
* or have different end, the segment is corrupted.
*/
if (end < qp->q.len ||
((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len))
goto err;
qp->q.flags |= INET_FRAG_LAST_IN;
qp->q.len = end;
} else {
if (end&7) {
end &= ~7;
if (skb->ip_summed != CHECKSUM_UNNECESSARY)
skb->ip_summed = CHECKSUM_NONE;
}
if (end > qp->q.len) {
/* Some bits beyond end -> corruption. */
if (qp->q.flags & INET_FRAG_LAST_IN)
goto err;
qp->q.len = end;
}
}
if (end == offset)
goto err;
err = -ENOMEM;
if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
goto err;
err = pskb_trim_rcsum(skb, end - offset);
if (err)
goto err;
/* Note : skb->rbnode and skb->dev share the same location. */
dev = skb->dev;
/* Makes sure compiler wont do silly aliasing games */
barrier();
/* RFC5722, Section 4, amended by Errata ID : 3089
* When reassembling an IPv6 datagram, if
* one or more its constituent fragments is determined to be an
* overlapping fragment, the entire datagram (and any constituent
* fragments) MUST be silently discarded.
*
* We do the same here for IPv4 (and increment an snmp counter).
*/
/* Find out where to put this fragment. */
prev_tail = qp->q.fragments_tail;
if (!prev_tail)
ip4_frag_create_run(&qp->q, skb); /* First fragment. */
else if (prev_tail->ip_defrag_offset + prev_tail->len < end) {
/* This is the common case: skb goes to the end. */
/* Detect and discard overlaps. */
if (offset < prev_tail->ip_defrag_offset + prev_tail->len)
goto discard_qp;
if (offset == prev_tail->ip_defrag_offset + prev_tail->len)
ip4_frag_append_to_last_run(&qp->q, skb);
else
ip4_frag_create_run(&qp->q, skb);
} else {
/* Binary search. Note that skb can become the first fragment,
* but not the last (covered above).
*/
rbn = &qp->q.rb_fragments.rb_node;
do {
parent = *rbn;
skb1 = rb_to_skb(parent);
if (end <= skb1->ip_defrag_offset)
rbn = &parent->rb_left;
else if (offset >= skb1->ip_defrag_offset +
FRAG_CB(skb1)->frag_run_len)
rbn = &parent->rb_right;
else /* Found an overlap with skb1. */
goto discard_qp;
} while (*rbn);
/* Here we have parent properly set, and rbn pointing to
* one of its NULL left/right children. Insert skb.
*/
ip4_frag_init_run(skb);
rb_link_node(&skb->rbnode, parent, rbn);
rb_insert_color(&skb->rbnode, &qp->q.rb_fragments);
}
if (dev)
qp->iif = dev->ifindex;
skb->ip_defrag_offset = offset;
qp->q.stamp = skb->tstamp;
qp->q.meat += skb->len;
qp->ecn |= ecn;
add_frag_mem_limit(qp->q.net, skb->truesize);
if (offset == 0)
qp->q.flags |= INET_FRAG_FIRST_IN;
fragsize = skb->len + ihl;
if (fragsize > qp->q.max_size)
qp->q.max_size = fragsize;
if (ip_hdr(skb)->frag_off & htons(IP_DF) &&
fragsize > qp->max_df_size)
qp->max_df_size = fragsize;
if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
qp->q.meat == qp->q.len) {
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
err = ip_frag_reasm(qp, skb, prev_tail, dev);
skb->_skb_refdst = orefdst;
return err;
}
skb_dst_drop(skb);
return -EINPROGRESS;
discard_qp:
inet_frag_kill(&qp->q);
err = -EINVAL;
__IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS);
err:
kfree_skb(skb);
return err;
}