Commit 49310710 authored by Eric Dumazet's avatar Eric Dumazet Committed by Greg Kroah-Hartman

inet: frags: use rhashtables for reassembly units

commit 648700f76b03b7e8149d13cc2bdb3355035258a9 upstream.

Some applications still rely on IP fragmentation, and to be fair linux
reassembly unit is not working under any serious load.

It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!)

A work queue is supposed to garbage collect items when host is under memory
pressure, and doing a hash rebuild, changing seed used in hash computations.

This work queue blocks softirqs for up to 25 ms when doing a hash rebuild,
occurring every 5 seconds if host is under fire.

Then there is the problem of sharing this hash table for all netns.

It is time to switch to rhashtables, and allocate one of them per netns
to speedup netns dismantle, since this is a critical metric these days.

Lookup is now using RCU. A followup patch will even remove
the refcount hold/release left from prior implementation and save
a couple of atomic operations.

Before this patch, 16 cpus (16 RX queue NIC) could not handle more
than 1 Mpps frags DDOS.

After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB
of storage for the fragments (exact number depends on frags being evicted
after timeout)

$ grep FRAG /proc/net/sockstat
FRAG: inuse 1966916 memory 2140004608

A followup patch will change the limits for 64bit arches.
Signed-off-by: 's avatarEric Dumazet <edumazet@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Florian Westphal <fw@strlen.de>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Alexander Aring <alex.aring@gmail.com>
Cc: Stefan Schmidt <stefan@osg.samsung.com>
Signed-off-by: 's avatarDavid S. Miller <davem@davemloft.net>
[bwh: Backported to 4.4: adjust context]
Signed-off-by: 's avatarBen Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: 's avatarGreg Kroah-Hartman <gregkh@linuxfoundation.org>
parent bf5ea30f
......@@ -113,13 +113,10 @@ min_adv_mss - INTEGER
IP Fragmentation:
ipfrag_high_thresh - INTEGER
Maximum memory used to reassemble IP fragments. When
ipfrag_high_thresh bytes of memory is allocated for this purpose,
the fragment handler will toss packets until ipfrag_low_thresh
is reached. This also serves as a maximum limit to namespaces
different from the initial one.
Maximum memory used to reassemble IP fragments.
ipfrag_low_thresh - INTEGER
(Obsolete since linux-4.17)
Maximum memory used to reassemble IP fragments before the kernel
begins to remove incomplete fragment queues to free up resources.
The kernel still accepts new fragments for defragmentation.
......
#ifndef __NET_FRAG_H__
#define __NET_FRAG_H__
#include <linux/rhashtable.h>
struct netns_frags {
struct rhashtable rhashtable ____cacheline_aligned_in_smp;
/* Keep atomic mem on separate cachelines in structs that include it */
atomic_t mem ____cacheline_aligned_in_smp;
/* sysctls */
......@@ -24,12 +28,30 @@ enum {
INET_FRAG_COMPLETE = BIT(2),
};
struct frag_v4_compare_key {
__be32 saddr;
__be32 daddr;
u32 user;
u32 vif;
__be16 id;
u16 protocol;
};
struct frag_v6_compare_key {
struct in6_addr saddr;
struct in6_addr daddr;
u32 user;
__be32 id;
u32 iif;
};
/**
* struct inet_frag_queue - fragment queue
*
* @lock: spinlock protecting the queue
* @node: rhash node
* @key: keys identifying this frag.
* @timer: queue expiration timer
* @list: hash bucket list
* @lock: spinlock protecting this frag
* @refcnt: reference count of the queue
* @fragments: received fragments head
* @fragments_tail: received fragments tail
......@@ -39,12 +61,16 @@ enum {
* @flags: fragment queue flags
* @max_size: maximum received fragment size
* @net: namespace that this frag belongs to
* @list_evictor: list of queues to forcefully evict (e.g. due to low memory)
* @rcu: rcu head for freeing deferall
*/
struct inet_frag_queue {
spinlock_t lock;
struct rhash_head node;
union {
struct frag_v4_compare_key v4;
struct frag_v6_compare_key v6;
} key;
struct timer_list timer;
struct hlist_node list;
spinlock_t lock;
atomic_t refcnt;
struct sk_buff *fragments;
struct sk_buff *fragments_tail;
......@@ -53,45 +79,13 @@ struct inet_frag_queue {
int meat;
__u8 flags;
u16 max_size;
struct netns_frags *net;
struct hlist_node list_evictor;
};
#define INETFRAGS_HASHSZ 1024
/* averaged:
* max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ /
* rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or
* struct frag_queue))
*/
#define INETFRAGS_MAXDEPTH 128
struct inet_frag_bucket {
struct hlist_head chain;
spinlock_t chain_lock;
struct netns_frags *net;
struct rcu_head rcu;
};
struct inet_frags {
struct inet_frag_bucket hash[INETFRAGS_HASHSZ];
struct work_struct frags_work;
unsigned int next_bucket;
unsigned long last_rebuild_jiffies;
bool rebuild;
/* The first call to hashfn is responsible to initialize
* rnd. This is best done with net_get_random_once.
*
* rnd_seqlock is used to let hash insertion detect
* when it needs to re-lookup the hash chain to use.
*/
u32 rnd;
seqlock_t rnd_seqlock;
int qsize;
unsigned int (*hashfn)(const struct inet_frag_queue *);
bool (*match)(const struct inet_frag_queue *q,
const void *arg);
void (*constructor)(struct inet_frag_queue *q,
const void *arg);
void (*destructor)(struct inet_frag_queue *);
......@@ -99,6 +93,7 @@ struct inet_frags {
void (*frag_expire)(unsigned long data);
struct kmem_cache *frags_cachep;
const char *frags_cache_name;
struct rhashtable_params rhash_params;
};
int inet_frags_init(struct inet_frags *);
......@@ -107,15 +102,13 @@ void inet_frags_fini(struct inet_frags *);
static inline int inet_frags_init_net(struct netns_frags *nf)
{
atomic_set(&nf->mem, 0);
return 0;
return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
}
void inet_frags_exit_net(struct netns_frags *nf);
void inet_frag_kill(struct inet_frag_queue *q);
void inet_frag_destroy(struct inet_frag_queue *q);
struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
struct inet_frags *f, void *key, unsigned int hash);
struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix);
......@@ -127,7 +120,7 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
static inline bool inet_frag_evicting(struct inet_frag_queue *q)
{
return !hlist_unhashed(&q->list_evictor);
return false;
}
/* Memory Tracking Functions. */
......
......@@ -505,17 +505,8 @@ enum ip6_defrag_users {
__IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
};
struct ip6_create_arg {
__be32 id;
u32 user;
const struct in6_addr *src;
const struct in6_addr *dst;
int iif;
u8 ecn;
};
void ip6_frag_init(struct inet_frag_queue *q, const void *a);
bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
extern const struct rhashtable_params ip6_rhash_params;
/*
* Equivalent of ipv4 struct ip
......@@ -523,11 +514,6 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
struct frag_queue {
struct inet_frag_queue q;
__be32 id; /* fragment id */
u32 user;
struct in6_addr saddr;
struct in6_addr daddr;
int iif;
unsigned int csum;
__u16 nhoffset;
......
......@@ -16,37 +16,19 @@ typedef unsigned __bitwise__ lowpan_rx_result;
#define LOWPAN_DISPATCH_FRAG1 0xc0
#define LOWPAN_DISPATCH_FRAGN 0xe0
struct lowpan_create_arg {
struct frag_lowpan_compare_key {
u16 tag;
u16 d_size;
const struct ieee802154_addr *src;
const struct ieee802154_addr *dst;
const struct ieee802154_addr src;
const struct ieee802154_addr dst;
};
/* Equivalent of ipv4 struct ip
/* Equivalent of ipv4 struct ipq
*/
struct lowpan_frag_queue {
struct inet_frag_queue q;
u16 tag;
u16 d_size;
struct ieee802154_addr saddr;
struct ieee802154_addr daddr;
};
static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a)
{
switch (a->mode) {
case IEEE802154_ADDR_LONG:
return (((__force u64)a->extended_addr) >> 32) ^
(((__force u64)a->extended_addr) & 0xffffffff);
case IEEE802154_ADDR_SHORT:
return (__force u32)(a->short_addr);
default:
return 0;
}
}
/* private device info */
struct lowpan_dev_info {
struct net_device *wdev; /* wpan device ptr */
......
......@@ -37,47 +37,15 @@ static struct inet_frags lowpan_frags;
static int lowpan_frag_reasm(struct lowpan_frag_queue *fq,
struct sk_buff *prev, struct net_device *ldev);
static unsigned int lowpan_hash_frag(u16 tag, u16 d_size,
const struct ieee802154_addr *saddr,
const struct ieee802154_addr *daddr)
{
net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd));
return jhash_3words(ieee802154_addr_hash(saddr),
ieee802154_addr_hash(daddr),
(__force u32)(tag + (d_size << 16)),
lowpan_frags.rnd);
}
static unsigned int lowpan_hashfn(const struct inet_frag_queue *q)
{
const struct lowpan_frag_queue *fq;
fq = container_of(q, struct lowpan_frag_queue, q);
return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr);
}
static bool lowpan_frag_match(const struct inet_frag_queue *q, const void *a)
{
const struct lowpan_frag_queue *fq;
const struct lowpan_create_arg *arg = a;
fq = container_of(q, struct lowpan_frag_queue, q);
return fq->tag == arg->tag && fq->d_size == arg->d_size &&
ieee802154_addr_equal(&fq->saddr, arg->src) &&
ieee802154_addr_equal(&fq->daddr, arg->dst);
}
static void lowpan_frag_init(struct inet_frag_queue *q, const void *a)
{
const struct lowpan_create_arg *arg = a;
const struct frag_lowpan_compare_key *key = a;
struct lowpan_frag_queue *fq;
fq = container_of(q, struct lowpan_frag_queue, q);
fq->tag = arg->tag;
fq->d_size = arg->d_size;
fq->saddr = *arg->src;
fq->daddr = *arg->dst;
BUILD_BUG_ON(sizeof(*key) > sizeof(q->key));
memcpy(&q->key, key, sizeof(*key));
}
static void lowpan_frag_expire(unsigned long data)
......@@ -104,21 +72,17 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
const struct ieee802154_addr *src,
const struct ieee802154_addr *dst)
{
struct inet_frag_queue *q;
struct lowpan_create_arg arg;
unsigned int hash;
struct netns_ieee802154_lowpan *ieee802154_lowpan =
net_ieee802154_lowpan(net);
struct frag_lowpan_compare_key key = {
.tag = cb->d_tag,
.d_size = cb->d_size,
.src = *src,
.dst = *dst,
};
struct inet_frag_queue *q;
arg.tag = cb->d_tag;
arg.d_size = cb->d_size;
arg.src = src;
arg.dst = dst;
hash = lowpan_hash_frag(cb->d_tag, cb->d_size, src, dst);
q = inet_frag_find(&ieee802154_lowpan->frags,
&lowpan_frags, &arg, hash);
q = inet_frag_find(&ieee802154_lowpan->frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
......@@ -610,18 +574,47 @@ static struct pernet_operations lowpan_frags_ops = {
.exit = lowpan_frags_exit_net,
};
static u32 lowpan_key_hashfn(const void *data, u32 len, u32 seed)
{
return jhash2(data,
sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
}
static u32 lowpan_obj_hashfn(const void *data, u32 len, u32 seed)
{
const struct inet_frag_queue *fq = data;
return jhash2((const u32 *)&fq->key,
sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
}
static int lowpan_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
{
const struct frag_lowpan_compare_key *key = arg->key;
const struct inet_frag_queue *fq = ptr;
return !!memcmp(&fq->key, key, sizeof(*key));
}
static const struct rhashtable_params lowpan_rhash_params = {
.head_offset = offsetof(struct inet_frag_queue, node),
.hashfn = lowpan_key_hashfn,
.obj_hashfn = lowpan_obj_hashfn,
.obj_cmpfn = lowpan_obj_cmpfn,
.automatic_shrinking = true,
};
int __init lowpan_net_frag_init(void)
{
int ret;
lowpan_frags.hashfn = lowpan_hashfn;
lowpan_frags.constructor = lowpan_frag_init;
lowpan_frags.destructor = NULL;
lowpan_frags.skb_free = NULL;
lowpan_frags.qsize = sizeof(struct frag_queue);
lowpan_frags.match = lowpan_frag_match;
lowpan_frags.frag_expire = lowpan_frag_expire;
lowpan_frags.frags_cache_name = lowpan_frags_cache_name;
lowpan_frags.rhash_params = lowpan_rhash_params;
ret = inet_frags_init(&lowpan_frags);
if (ret)
goto out;
......
This diff is collapsed.
......@@ -70,15 +70,9 @@ struct ipfrag_skb_cb
struct ipq {
struct inet_frag_queue q;
u32 user;
__be32 saddr;
__be32 daddr;
__be16 id;
u8 protocol;
u8 ecn; /* RFC3168 support */
u16 max_df_size; /* largest frag with DF set seen */
int iif;
int vif; /* L3 master device index */
unsigned int rid;
struct inet_peer *peer;
};
......@@ -98,41 +92,6 @@ int ip_frag_mem(struct net *net)
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev);
struct ip4_create_arg {
struct iphdr *iph;
u32 user;
int vif;
};
static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
{
net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd));
return jhash_3words((__force u32)id << 16 | prot,
(__force u32)saddr, (__force u32)daddr,
ip4_frags.rnd);
}
static unsigned int ip4_hashfn(const struct inet_frag_queue *q)
{
const struct ipq *ipq;
ipq = container_of(q, struct ipq, q);
return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
}
static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a)
{
const struct ipq *qp;
const struct ip4_create_arg *arg = a;
qp = container_of(q, struct ipq, q);
return qp->id == arg->iph->id &&
qp->saddr == arg->iph->saddr &&
qp->daddr == arg->iph->daddr &&
qp->protocol == arg->iph->protocol &&
qp->user == arg->user &&
qp->vif == arg->vif;
}
static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
{
......@@ -141,17 +100,12 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
frags);
struct net *net = container_of(ipv4, struct net, ipv4);
const struct ip4_create_arg *arg = a;
const struct frag_v4_compare_key *key = a;
qp->protocol = arg->iph->protocol;
qp->id = arg->iph->id;
qp->ecn = ip4_frag_ecn(arg->iph->tos);
qp->saddr = arg->iph->saddr;
qp->daddr = arg->iph->daddr;
qp->vif = arg->vif;
qp->user = arg->user;
q->key.v4 = *key;
qp->ecn = 0;
qp->peer = sysctl_ipfrag_max_dist ?
inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) :
inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) :
NULL;
}
......@@ -234,7 +188,7 @@ static void ip_expire(unsigned long arg)
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
if (frag_expire_skip_icmp(qp->user) &&
if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
(skb_rtable(head)->rt_type != RTN_LOCAL))
goto out;
......@@ -262,17 +216,17 @@ out_rcu_unlock:
static struct ipq *ip_find(struct net *net, struct iphdr *iph,
u32 user, int vif)
{
struct frag_v4_compare_key key = {
.saddr = iph->saddr,
.daddr = iph->daddr,
.user = user,
.vif = vif,
.id = iph->id,
.protocol = iph->protocol,
};
struct inet_frag_queue *q;
struct ip4_create_arg arg;
unsigned int hash;
arg.iph = iph;
arg.user = user;
arg.vif = vif;
hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
q = inet_frag_find(&net->ipv4.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
......@@ -656,7 +610,7 @@ out_nomem:
err = -ENOMEM;
goto out_fail;
out_oversize:
net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr);
out_fail:
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
return err;
......@@ -900,16 +854,48 @@ static struct pernet_operations ip4_frags_ops = {
.exit = ipv4_frags_exit_net,
};
static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed)
{
return jhash2(data,
sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
}
static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed)
{
const struct inet_frag_queue *fq = data;
return jhash2((const u32 *)&fq->key.v4,
sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
}
static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
{
const struct frag_v4_compare_key *key = arg->key;
const struct inet_frag_queue *fq = ptr;
return !!memcmp(&fq->key, key, sizeof(*key));
}
static const struct rhashtable_params ip4_rhash_params = {
.head_offset = offsetof(struct inet_frag_queue, node),
.key_offset = offsetof(struct inet_frag_queue, key),
.key_len = sizeof(struct frag_v4_compare_key),
.hashfn = ip4_key_hashfn,
.obj_hashfn = ip4_obj_hashfn,
.obj_cmpfn = ip4_obj_cmpfn,
.automatic_shrinking = true,
};
void __init ipfrag_init(void)
{
ip4_frags.hashfn = ip4_hashfn;
ip4_frags.constructor = ip4_frag_init;
ip4_frags.destructor = ip4_frag_free;
ip4_frags.skb_free = NULL;
ip4_frags.qsize = sizeof(struct ipq);
ip4_frags.match = ip4_frag_match;
ip4_frags.frag_expire = ip_expire;
ip4_frags.frags_cache_name = ip_frag_cache_name;
ip4_frags.rhash_params = ip4_rhash_params;
if (inet_frags_init(&ip4_frags))
panic("IP: failed to allocate ip4_frags cache\n");
ip4_frags_ctl_register();
......
......@@ -153,23 +153,6 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
}
static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr,
const struct in6_addr *daddr)
{
net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd));
return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
(__force u32)id, nf_frags.rnd);
}
static unsigned int nf_hashfn(const struct inet_frag_queue *q)
{
const struct frag_queue *nq;
nq = container_of(q, struct frag_queue, q);
return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr);
}
static void nf_skb_free(struct sk_buff *skb)
{
if (NFCT_FRAG6_CB(skb)->orig)
......@@ -188,26 +171,19 @@ static void nf_ct_frag6_expire(unsigned long data)
}
/* Creation primitives. */
static inline struct frag_queue *fq_find(struct net *net, __be32 id,
u32 user, struct in6_addr *src,
struct in6_addr *dst, int iif, u8 ecn)
static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
const struct ipv6hdr *hdr, int iif)
{
struct frag_v6_compare_key key = {
.id = id,
.saddr = hdr->saddr,
.daddr = hdr->daddr,
.user = user,
.iif = iif,
};
struct inet_frag_queue *q;
struct ip6_create_arg arg;
unsigned int hash;
arg.id = id;
arg.user = user;
arg.src = src;
arg.dst = dst;
arg.iif = iif;
arg.ecn = ecn;
local_bh_disable();
hash = nf_hash_frag(id, src, dst);
q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
local_bh_enable();
q = inet_frag_find(&net->nf_frag.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
......@@ -602,8 +578,8 @@ struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 use
fhdr = (struct frag_hdr *)skb_transport_header(clone);
skb_orphan(skb);
fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
fq = fq_find(net, fhdr->identification, user, hdr,
skb->dev ? skb->dev->ifindex : 0);
if (fq == NULL) {
pr_debug("Can't find and can't create new queue\n");
goto ret_orig;
......@@ -681,14 +657,13 @@ int nf_ct_frag6_init(void)
{
int ret = 0;
nf_frags.hashfn = nf_hashfn;
nf_frags.constructor = ip6_frag_init;
nf_frags.destructor = NULL;
nf_frags.skb_free = nf_skb_free;
nf_frags.qsize = sizeof(struct frag_queue);
nf_frags.match = ip6_frag_match;
nf_frags.frag_expire = nf_ct_frag6_expire;
nf_frags.frags_cache_name = nf_frags_cache_name;
nf_frags.rhash_params = ip6_rhash_params;
ret = inet_frags_init(&nf_frags);
if (ret)
goto out;
......
......@@ -79,52 +79,13 @@ static struct inet_frags ip6_frags;
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev);
/*
* callers should be careful not to use the hash value outside the ipfrag_lock
* as doing so could race with ipfrag_hash_rnd being recalculated.
*/
static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
const struct in6_addr *daddr)
{
net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd));
return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
(__force u32)id, ip6_frags.rnd);
}
static unsigned int ip6_hashfn(const struct inet_frag_queue *q)
{
const struct frag_queue *fq;
fq = container_of(q, struct frag_queue, q);
return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr);
}
bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
{
const struct frag_queue *fq;
const struct ip6_create_arg *arg = a;
fq = container_of(q, struct frag_queue, q);
return fq->id == arg->id &&
fq->user == arg->user &&
ipv6_addr_equal(&fq->saddr, arg->src) &&
ipv6_addr_equal(&fq->daddr, arg->dst) &&
(arg->iif == fq->iif ||
!(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
IPV6_ADDR_LINKLOCAL)));
}
EXPORT_SYMBOL(ip6_frag_match);
void ip6_frag_init(struct inet_frag_queue *q, const void *a)
{
struct frag_queue *fq = container_of(q, struct frag_queue, q);
const struct ip6_create_arg *arg = a;
const struct frag_v6_compare_key *key = a;
fq->id = arg->id;
fq->user = arg->user;
fq->saddr = *arg->src;
fq->daddr = *arg->dst;
fq->ecn = arg->ecn;
q->key.v6 = *key;
fq->ecn = 0;
}
EXPORT_SYMBOL(ip6_frag_init);
......@@ -181,23 +142,22 @@ static void ip6_frag_expire(unsigned long data)
}
static struct frag_queue *
fq_find(struct net *net, __be32 id, const struct in6_addr *src,
const struct in6_addr *dst, int iif, u8 ecn)
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;
struct ip6_create_arg arg;
unsigned int hash;
arg.id = id;
arg.user = IP6_DEFRAG_LOCAL_DELIVER;
arg.src = src;
arg.dst = dst;
arg.iif = iif;
arg.ecn = ecn;
hash = inet6_hash_frag(id, src, dst);
if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
IPV6_ADDR_LINKLOCAL)))
key.iif = 0;
q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
q = inet_frag_find(&net->ipv6.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
......@@ -523,6 +483,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
struct frag_queue *fq;
const struct ipv6hdr *hdr = ipv6_hdr(skb);
struct net *net = dev_net(skb_dst(skb)->dev);
int iif;
if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)