kernel_optimize_test/include/net/ipv6_frag.h
Peter Oskolkov d4289fcc9b net: IP6 defrag: use rbtrees for IPv6 defrag
Currently, IPv6 defragmentation code drops non-last fragments that
are smaller than 1280 bytes: see
commit 0ed4229b08 ("ipv6: defrag: drop non-last frags smaller than min mtu")

This behavior is not specified in IPv6 RFCs and appears to break
compatibility with some IPv6 implemenations, as reported here:
https://www.spinics.net/lists/netdev/msg543846.html

This patch re-uses common IP defragmentation queueing and reassembly
code in IPv6, removing the 1280 byte restriction.

Signed-off-by: Peter Oskolkov <posk@google.com>
Reported-by: Tom Herbert <tom@herbertland.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-25 21:37:11 -08:00

112 lines
2.6 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _IPV6_FRAG_H
#define _IPV6_FRAG_H
#include <linux/kernel.h>
#include <net/addrconf.h>
#include <net/ipv6.h>
#include <net/inet_frag.h>
enum ip6_defrag_users {
IP6_DEFRAG_LOCAL_DELIVER,
IP6_DEFRAG_CONNTRACK_IN,
__IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX,
IP6_DEFRAG_CONNTRACK_OUT,
__IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX,
IP6_DEFRAG_CONNTRACK_BRIDGE_IN,
__IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
};
/*
* Equivalent of ipv4 struct ip
*/
struct frag_queue {
struct inet_frag_queue q;
int iif;
__u16 nhoffset;
u8 ecn;
};
#if IS_ENABLED(CONFIG_IPV6)
static inline void ip6frag_init(struct inet_frag_queue *q, const void *a)
{
struct frag_queue *fq = container_of(q, struct frag_queue, q);
const struct frag_v6_compare_key *key = a;
q->key.v6 = *key;
fq->ecn = 0;
}
static inline u32 ip6frag_key_hashfn(const void *data, u32 len, u32 seed)
{
return jhash2(data,
sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
}
static inline u32 ip6frag_obj_hashfn(const void *data, u32 len, u32 seed)
{
const struct inet_frag_queue *fq = data;
return jhash2((const u32 *)&fq->key.v6,
sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
}
static inline int
ip6frag_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
{
const struct frag_v6_compare_key *key = arg->key;
const struct inet_frag_queue *fq = ptr;
return !!memcmp(&fq->key, key, sizeof(*key));
}
static inline void
ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
{
struct net_device *dev = NULL;
struct sk_buff *head;
rcu_read_lock();
spin_lock(&fq->q.lock);
if (fq->q.flags & INET_FRAG_COMPLETE)
goto out;
inet_frag_kill(&fq->q);
dev = dev_get_by_index_rcu(net, fq->iif);
if (!dev)
goto out;
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
/* Don't send error if the first segment did not arrive. */
if (!(fq->q.flags & INET_FRAG_FIRST_IN))
goto out;
/* sk_buff::dev and sk_buff::rbnode are unionized. So we
* pull the head out of the tree in order to be able to
* deal with head->dev.
*/
head = inet_frag_pull_head(&fq->q);
if (!head)
goto out;
head->dev = dev;
skb_get(head);
spin_unlock(&fq->q.lock);
icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
kfree_skb(head);
goto out_rcu_unlock;
out:
spin_unlock(&fq->q.lock);
out_rcu_unlock:
rcu_read_unlock();
inet_frag_put(&fq->q);
}
#endif
#endif