This patch adds skbuff fraglist splitter. The API provides an iterator
to perform this transformation, it consists of:
* ip_fraglist_init(), that initializes the internal state of the
fraglist splitter.
* ip_fraglist_prepare(), that restores the IPv4 header on the
fragments.
* ip_fraglist_next(), that retrieves the fragment from the fraglist and
it updates the internal state of the splitter to point to the next
fragment in the fraglist.
The ip_fraglist_iter object stores the internal state of the iterator.
This code has been extracted from ip_do_fragment(). Symbols are also
exported to allow to reuse this iterator from the bridge codepath to
build its own refragmentation routine by reusing the existing codebase.
Signed-off-by: Pablo Neira Ayuso <pablo@xxxxxxxxxxxxx>
---
v2: Fix English typo in patch description.
include/net/ip.h | 23 ++++++++++++++
net/ipv4/ip_output.c | 88 ++++++++++++++++++++++++++++++++--------------------
2 files changed, 78 insertions(+), 33 deletions(-)
diff --git a/include/net/ip.h b/include/net/ip.h
index 2d3cce7c3e8a..be899677504b 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -165,6 +165,29 @@ int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb);
int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb);
int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
int (*output)(struct net *, struct sock *, struct sk_buff *));
+
+struct ip_fraglist_iter {
+ struct sk_buff *frag_list;
+ struct sk_buff *frag;
+ struct iphdr *iph;
+ int offset;
+ unsigned int hlen;
+};
+
+void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph,
+ unsigned int hlen, struct ip_fraglist_iter *iter);
+void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter);
+
+static inline struct sk_buff *ip_fraglist_next(struct ip_fraglist_iter *iter)
+{
+ struct sk_buff *skb = iter->frag;
+
+ iter->frag = skb->next;
+ skb_mark_not_on_list(skb);
+
+ return skb;
+}
+
void ip_send_check(struct iphdr *ip);
int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 4e42c1974ba2..c03194eb1376 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -559,6 +559,54 @@ static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
return ip_do_fragment(net, sk, skb, output);
}
+void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph,
+ unsigned int hlen, struct ip_fraglist_iter *iter)
+{
+ unsigned int first_len = skb_pagelen(skb);
+
+ iter->frag_list = skb_shinfo(skb)->frag_list;
+ iter->frag = iter->frag_list;
+ skb_frag_list_init(skb);
+
+ iter->offset = 0;
+ iter->iph = iph;
+ iter->hlen = hlen;
+
+ 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);
+}
+EXPORT_SYMBOL(ip_fraglist_init);
+
+void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter)
+{
+ unsigned int hlen = iter->hlen;
+ struct iphdr *iph = iter->iph;
+ struct sk_buff *frag;
+
+ frag = iter->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);
+ iter->iph = ip_hdr(frag);
+ iph = iter->iph;
+ iph->tot_len = htons(frag->len);
+ ip_copy_metadata(frag, skb);
+ if (iter->offset == 0)
+ ip_options_fragment(frag);
+ iter->offset += skb->len - hlen;
+ iph->frag_off = htons(iter->offset >> 3);
+ if (frag->next)
+ iph->frag_off |= htons(IP_MF);
+ /* Ready, complete checksum */
+ ip_send_check(iph);
+}
+EXPORT_SYMBOL(ip_fraglist_prepare);
+
/*
* This IP datagram is too large to be sent in one piece. Break it up into
* smaller pieces (each of size equal to IP header plus
@@ -576,6 +624,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
int offset;
__be16 not_last_frag;
struct rtable *rt = skb_rtable(skb);
+ struct ip_fraglist_iter iter;
int err = 0;
/* for offloaded checksums cleanup checksum before fragmentation */
@@ -640,49 +689,22 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
}
/* 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);
+ ip_fraglist_init(skb, iph, hlen, &iter);
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);
- }
+ if (iter.frag)
+ ip_fraglist_prepare(skb, &iter);
err = output(net, sk, skb);
if (!err)
IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
- if (err || !frag)
+ if (err || !iter.frag)
break;
- skb = frag;
- frag = skb->next;
- skb_mark_not_on_list(skb);
+ skb = ip_fraglist_next(&iter);
}
if (err == 0) {
@@ -690,7 +712,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
return 0;
}
- kfree_skb_list(frag);
+ kfree_skb_list(iter.frag_list);
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
return err;
--
2.11.0
