/*
* IPv6 fragment reassembly
- * Linux INET6 implementation
+ * Linux INET6 implementation
*
* Authors:
- * Pedro Roque <roque@di.fc.ul.pt>
- *
- * $Id: reassembly.c,v 1.26 2001/03/07 22:00:57 davem Exp $
+ * Pedro Roque <roque@di.fc.ul.pt>
*
* Based on: net/ipv4/ip_fragment.c
*
* 2 of the License, or (at your option) any later version.
*/
-/*
- * Fixes:
+/*
+ * Fixes:
* Andi Kleen Make it work with multiple hosts.
* More RFC compliance.
*
* YOSHIFUJI,H. @USAGI Always remove fragment header to
* calculate ICV correctly.
*/
-#include <linux/config.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
#include <linux/jhash.h>
+#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ipv6.h>
+#include <net/ip6_route.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/rawv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
-
-int sysctl_ip6frag_high_thresh = 256*1024;
-int sysctl_ip6frag_low_thresh = 192*1024;
-
-int sysctl_ip6frag_time = IPV6_FRAG_TIMEOUT;
+#include <net/inet_frag.h>
struct ip6frag_skb_cb
{
struct frag_queue
{
- struct hlist_node list;
- struct list_head lru_list; /* lru list member */
+ struct inet_frag_queue q;
- __u32 id; /* fragment id */
+ __be32 id; /* fragment id */
struct in6_addr saddr;
struct in6_addr daddr;
- spinlock_t lock;
- atomic_t refcnt;
- struct timer_list timer; /* expire timer */
- struct sk_buff *fragments;
- int len;
- int meat;
int iif;
- struct timeval stamp;
unsigned int csum;
- __u8 last_in; /* has first/last segment arrived? */
-#define COMPLETE 4
-#define FIRST_IN 2
-#define LAST_IN 1
__u16 nhoffset;
};
-/* Hash table. */
-
-#define IP6Q_HASHSZ 64
+static struct inet_frags ip6_frags;
-static struct hlist_head ip6_frag_hash[IP6Q_HASHSZ];
-static DEFINE_RWLOCK(ip6_frag_lock);
-static u32 ip6_frag_hash_rnd;
-static LIST_HEAD(ip6_frag_lru_list);
-int ip6_frag_nqueues = 0;
-
-static __inline__ void __fq_unlink(struct frag_queue *fq)
+int ip6_frag_nqueues(struct net *net)
{
- hlist_del(&fq->list);
- list_del(&fq->lru_list);
- ip6_frag_nqueues--;
+ return net->ipv6.frags.nqueues;
}
-static __inline__ void fq_unlink(struct frag_queue *fq)
+int ip6_frag_mem(struct net *net)
{
- write_lock(&ip6_frag_lock);
- __fq_unlink(fq);
- write_unlock(&ip6_frag_lock);
+ return atomic_read(&net->ipv6.frags.mem);
}
-static unsigned int ip6qhashfn(u32 id, struct in6_addr *saddr,
- struct in6_addr *daddr)
+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.
+ */
+unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
+ const struct in6_addr *daddr, u32 rnd)
{
u32 a, b, c;
- a = saddr->s6_addr32[0];
- b = saddr->s6_addr32[1];
- c = saddr->s6_addr32[2];
+ a = (__force u32)saddr->s6_addr32[0];
+ b = (__force u32)saddr->s6_addr32[1];
+ c = (__force u32)saddr->s6_addr32[2];
a += JHASH_GOLDEN_RATIO;
b += JHASH_GOLDEN_RATIO;
- c += ip6_frag_hash_rnd;
+ c += rnd;
__jhash_mix(a, b, c);
- a += saddr->s6_addr32[3];
- b += daddr->s6_addr32[0];
- c += daddr->s6_addr32[1];
+ a += (__force u32)saddr->s6_addr32[3];
+ b += (__force u32)daddr->s6_addr32[0];
+ c += (__force u32)daddr->s6_addr32[1];
__jhash_mix(a, b, c);
- a += daddr->s6_addr32[2];
- b += daddr->s6_addr32[3];
- c += id;
+ a += (__force u32)daddr->s6_addr32[2];
+ b += (__force u32)daddr->s6_addr32[3];
+ c += (__force u32)id;
__jhash_mix(a, b, c);
- return c & (IP6Q_HASHSZ - 1);
+ return c & (INETFRAGS_HASHSZ - 1);
}
+EXPORT_SYMBOL_GPL(inet6_hash_frag);
-static struct timer_list ip6_frag_secret_timer;
-int sysctl_ip6frag_secret_interval = 10 * 60 * HZ;
-
-static void ip6_frag_secret_rebuild(unsigned long dummy)
+static unsigned int ip6_hashfn(struct inet_frag_queue *q)
{
- unsigned long now = jiffies;
- int i;
-
- write_lock(&ip6_frag_lock);
- get_random_bytes(&ip6_frag_hash_rnd, sizeof(u32));
- for (i = 0; i < IP6Q_HASHSZ; i++) {
- struct frag_queue *q;
- struct hlist_node *p, *n;
-
- hlist_for_each_entry_safe(q, p, n, &ip6_frag_hash[i], list) {
- unsigned int hval = ip6qhashfn(q->id,
- &q->saddr,
- &q->daddr);
-
- if (hval != i) {
- hlist_del(&q->list);
+ struct frag_queue *fq;
- /* Relink to new hash chain. */
- hlist_add_head(&q->list,
- &ip6_frag_hash[hval]);
+ fq = container_of(q, struct frag_queue, q);
+ return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr, ip6_frags.rnd);
+}
- }
- }
- }
- write_unlock(&ip6_frag_lock);
+int ip6_frag_match(struct inet_frag_queue *q, void *a)
+{
+ struct frag_queue *fq;
+ struct ip6_create_arg *arg = a;
- mod_timer(&ip6_frag_secret_timer, now + sysctl_ip6frag_secret_interval);
+ fq = container_of(q, struct frag_queue, q);
+ return (fq->id == arg->id &&
+ ipv6_addr_equal(&fq->saddr, arg->src) &&
+ ipv6_addr_equal(&fq->daddr, arg->dst));
}
-
-atomic_t ip6_frag_mem = ATOMIC_INIT(0);
+EXPORT_SYMBOL(ip6_frag_match);
/* Memory Tracking Functions. */
-static inline void frag_kfree_skb(struct sk_buff *skb, int *work)
+static inline void frag_kfree_skb(struct netns_frags *nf,
+ struct sk_buff *skb, int *work)
{
if (work)
*work -= skb->truesize;
- atomic_sub(skb->truesize, &ip6_frag_mem);
+ atomic_sub(skb->truesize, &nf->mem);
kfree_skb(skb);
}
-static inline void frag_free_queue(struct frag_queue *fq, int *work)
-{
- if (work)
- *work -= sizeof(struct frag_queue);
- atomic_sub(sizeof(struct frag_queue), &ip6_frag_mem);
- kfree(fq);
-}
-
-static inline struct frag_queue *frag_alloc_queue(void)
+void ip6_frag_init(struct inet_frag_queue *q, void *a)
{
- struct frag_queue *fq = kmalloc(sizeof(struct frag_queue), GFP_ATOMIC);
+ struct frag_queue *fq = container_of(q, struct frag_queue, q);
+ struct ip6_create_arg *arg = a;
- if(!fq)
- return NULL;
- atomic_add(sizeof(struct frag_queue), &ip6_frag_mem);
- return fq;
+ fq->id = arg->id;
+ ipv6_addr_copy(&fq->saddr, arg->src);
+ ipv6_addr_copy(&fq->daddr, arg->dst);
}
+EXPORT_SYMBOL(ip6_frag_init);
/* Destruction primitives. */
-/* Complete destruction of fq. */
-static void ip6_frag_destroy(struct frag_queue *fq, int *work)
-{
- struct sk_buff *fp;
-
- BUG_TRAP(fq->last_in&COMPLETE);
- BUG_TRAP(del_timer(&fq->timer) == 0);
-
- /* Release all fragment data. */
- fp = fq->fragments;
- while (fp) {
- struct sk_buff *xp = fp->next;
-
- frag_kfree_skb(fp, work);
- fp = xp;
- }
-
- frag_free_queue(fq, work);
-}
-
-static __inline__ void fq_put(struct frag_queue *fq, int *work)
+static __inline__ void fq_put(struct frag_queue *fq)
{
- if (atomic_dec_and_test(&fq->refcnt))
- ip6_frag_destroy(fq, work);
+ inet_frag_put(&fq->q, &ip6_frags);
}
/* Kill fq entry. It is not destroyed immediately,
*/
static __inline__ void fq_kill(struct frag_queue *fq)
{
- if (del_timer(&fq->timer))
- atomic_dec(&fq->refcnt);
-
- if (!(fq->last_in & COMPLETE)) {
- fq_unlink(fq);
- atomic_dec(&fq->refcnt);
- fq->last_in |= COMPLETE;
- }
+ inet_frag_kill(&fq->q, &ip6_frags);
}
-static void ip6_evictor(void)
+static void ip6_evictor(struct net *net, struct inet6_dev *idev)
{
- struct frag_queue *fq;
- struct list_head *tmp;
- int work;
-
- work = atomic_read(&ip6_frag_mem) - sysctl_ip6frag_low_thresh;
- if (work <= 0)
- return;
-
- while(work > 0) {
- read_lock(&ip6_frag_lock);
- if (list_empty(&ip6_frag_lru_list)) {
- read_unlock(&ip6_frag_lock);
- return;
- }
- tmp = ip6_frag_lru_list.next;
- fq = list_entry(tmp, struct frag_queue, lru_list);
- atomic_inc(&fq->refcnt);
- read_unlock(&ip6_frag_lock);
-
- spin_lock(&fq->lock);
- if (!(fq->last_in&COMPLETE))
- fq_kill(fq);
- spin_unlock(&fq->lock);
-
- fq_put(fq, &work);
- IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
- }
+ int evicted;
+
+ evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags);
+ if (evicted)
+ IP6_ADD_STATS_BH(net, idev, IPSTATS_MIB_REASMFAILS, evicted);
}
static void ip6_frag_expire(unsigned long data)
{
- struct frag_queue *fq = (struct frag_queue *) data;
+ struct frag_queue *fq;
+ struct net_device *dev = NULL;
+ struct net *net;
+
+ fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
- spin_lock(&fq->lock);
+ spin_lock(&fq->q.lock);
- if (fq->last_in & COMPLETE)
+ if (fq->q.last_in & INET_FRAG_COMPLETE)
goto out;
fq_kill(fq);
- IP6_INC_STATS_BH(IPSTATS_MIB_REASMTIMEOUT);
- IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+ net = container_of(fq->q.net, struct net, ipv6.frags);
+ dev = dev_get_by_index(net, fq->iif);
+ if (!dev)
+ goto out;
- /* Send error only if the first segment arrived. */
- if (fq->last_in&FIRST_IN && fq->fragments) {
- struct net_device *dev = dev_get_by_index(fq->iif);
+ rcu_read_lock();
+ IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
+ IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
+ rcu_read_unlock();
- /*
- But use as source device on which LAST ARRIVED
- segment was received. And do not use fq->dev
- pointer directly, device might already disappeared.
- */
- if (dev) {
- fq->fragments->dev = dev;
- icmpv6_send(fq->fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0,
- dev);
- dev_put(dev);
- }
- }
+ /* Don't send error if the first segment did not arrive. */
+ if (!(fq->q.last_in & INET_FRAG_FIRST_IN) || !fq->q.fragments)
+ goto out;
+
+ /*
+ But use as source device on which LAST ARRIVED
+ segment was received. And do not use fq->dev
+ pointer directly, device might already disappeared.
+ */
+ fq->q.fragments->dev = dev;
+ icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0, dev);
out:
- spin_unlock(&fq->lock);
- fq_put(fq, NULL);
+ if (dev)
+ dev_put(dev);
+ spin_unlock(&fq->q.lock);
+ fq_put(fq);
}
-/* Creation primitives. */
-
-
-static struct frag_queue *ip6_frag_intern(unsigned int hash,
- struct frag_queue *fq_in)
+static __inline__ struct frag_queue *
+fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst,
+ struct inet6_dev *idev)
{
- struct frag_queue *fq;
-#ifdef CONFIG_SMP
- struct hlist_node *n;
-#endif
+ struct inet_frag_queue *q;
+ struct ip6_create_arg arg;
+ unsigned int hash;
- write_lock(&ip6_frag_lock);
-#ifdef CONFIG_SMP
- hlist_for_each_entry(fq, n, &ip6_frag_hash[hash], list) {
- if (fq->id == fq_in->id &&
- ipv6_addr_equal(&fq_in->saddr, &fq->saddr) &&
- ipv6_addr_equal(&fq_in->daddr, &fq->daddr)) {
- atomic_inc(&fq->refcnt);
- write_unlock(&ip6_frag_lock);
- fq_in->last_in |= COMPLETE;
- fq_put(fq_in, NULL);
- return fq;
- }
- }
-#endif
- fq = fq_in;
-
- if (!mod_timer(&fq->timer, jiffies + sysctl_ip6frag_time))
- atomic_inc(&fq->refcnt);
-
- atomic_inc(&fq->refcnt);
- hlist_add_head(&fq->list, &ip6_frag_hash[hash]);
- INIT_LIST_HEAD(&fq->lru_list);
- list_add_tail(&fq->lru_list, &ip6_frag_lru_list);
- ip6_frag_nqueues++;
- write_unlock(&ip6_frag_lock);
- return fq;
-}
+ arg.id = id;
+ arg.src = src;
+ arg.dst = dst;
+ read_lock(&ip6_frags.lock);
+ hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd);
-static struct frag_queue *
-ip6_frag_create(unsigned int hash, u32 id, struct in6_addr *src, struct in6_addr *dst)
-{
- struct frag_queue *fq;
-
- if ((fq = frag_alloc_queue()) == NULL)
+ q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
+ if (q == NULL)
goto oom;
- memset(fq, 0, sizeof(struct frag_queue));
-
- fq->id = id;
- ipv6_addr_copy(&fq->saddr, src);
- ipv6_addr_copy(&fq->daddr, dst);
-
- init_timer(&fq->timer);
- fq->timer.function = ip6_frag_expire;
- fq->timer.data = (long) fq;
- spin_lock_init(&fq->lock);
- atomic_set(&fq->refcnt, 1);
-
- return ip6_frag_intern(hash, fq);
+ return container_of(q, struct frag_queue, q);
oom:
- IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+ IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_REASMFAILS);
return NULL;
}
-static __inline__ struct frag_queue *
-fq_find(u32 id, struct in6_addr *src, struct in6_addr *dst)
-{
- struct frag_queue *fq;
- struct hlist_node *n;
- unsigned int hash = ip6qhashfn(id, src, dst);
-
- read_lock(&ip6_frag_lock);
- hlist_for_each_entry(fq, n, &ip6_frag_hash[hash], list) {
- if (fq->id == id &&
- ipv6_addr_equal(src, &fq->saddr) &&
- ipv6_addr_equal(dst, &fq->daddr)) {
- atomic_inc(&fq->refcnt);
- read_unlock(&ip6_frag_lock);
- return fq;
- }
- }
- read_unlock(&ip6_frag_lock);
-
- return ip6_frag_create(hash, id, src, dst);
-}
-
-
-static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
+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;
+ struct net *net = dev_net(skb_dst(skb)->dev);
- if (fq->last_in & COMPLETE)
+ if (fq->q.last_in & INET_FRAG_COMPLETE)
goto err;
offset = ntohs(fhdr->frag_off) & ~0x7;
- end = offset + (ntohs(skb->nh.ipv6h->payload_len) -
- ((u8 *) (fhdr + 1) - (u8 *) (skb->nh.ipv6h + 1)));
+ 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_BH(IPSTATS_MIB_INHDRERRORS);
- icmpv6_param_prob(skb,ICMPV6_HDR_FIELD, (u8*)&fhdr->frag_off - skb->nh.raw);
- return;
+ IP6_INC_STATS_BH(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;
}
- if (skb->ip_summed == CHECKSUM_HW)
- skb->csum = csum_sub(skb->csum,
- csum_partial(skb->nh.raw, (u8*)(fhdr+1)-skb->nh.raw, 0));
+ 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->len ||
- ((fq->last_in & LAST_IN) && end != fq->len))
+ if (end < fq->q.len ||
+ ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len))
goto err;
- fq->last_in |= LAST_IN;
- fq->len = end;
+ fq->q.last_in |= INET_FRAG_LAST_IN;
+ fq->q.len = end;
} else {
/* Check if the fragment is rounded to 8 bytes.
* Required by the RFC.
/* RFC2460 says always send parameter problem in
* this case. -DaveM
*/
- IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
+ IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_INHDRERRORS);
+ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
offsetof(struct ipv6hdr, payload_len));
- return;
+ return -1;
}
- if (end > fq->len) {
+ if (end > fq->q.len) {
/* Some bits beyond end -> corruption. */
- if (fq->last_in & LAST_IN)
+ if (fq->q.last_in & INET_FRAG_LAST_IN)
goto err;
- fq->len = end;
+ fq->q.len = end;
}
}
/* 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;
* this fragment, right?
*/
prev = NULL;
- for(next = fq->fragments; next != NULL; next = next->next) {
+ for(next = fq->q.fragments; next != NULL; next = next->next) {
if (FRAG6_CB(next)->offset >= offset)
break; /* bingo! */
prev = next;
if (!pskb_pull(next, i))
goto err;
FRAG6_CB(next)->offset += i; /* next fragment */
- fq->meat -= i;
+ fq->q.meat -= i;
if (next->ip_summed != CHECKSUM_UNNECESSARY)
next->ip_summed = CHECKSUM_NONE;
break;
if (prev)
prev->next = next;
else
- fq->fragments = next;
+ fq->q.fragments = next;
- fq->meat -= free_it->len;
- frag_kfree_skb(free_it, NULL);
+ fq->q.meat -= free_it->len;
+ frag_kfree_skb(fq->q.net, free_it, NULL);
}
}
if (prev)
prev->next = skb;
else
- fq->fragments = skb;
+ fq->q.fragments = skb;
- if (skb->dev)
- fq->iif = skb->dev->ifindex;
- skb->dev = NULL;
- skb_get_timestamp(skb, &fq->stamp);
- fq->meat += skb->len;
- atomic_add(skb->truesize, &ip6_frag_mem);
+ dev = skb->dev;
+ if (dev) {
+ fq->iif = dev->ifindex;
+ skb->dev = NULL;
+ }
+ fq->q.stamp = skb->tstamp;
+ fq->q.meat += skb->len;
+ atomic_add(skb->truesize, &fq->q.net->mem);
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
*/
if (offset == 0) {
fq->nhoffset = nhoff;
- fq->last_in |= FIRST_IN;
+ fq->q.last_in |= INET_FRAG_FIRST_IN;
}
- write_lock(&ip6_frag_lock);
- list_move_tail(&fq->lru_list, &ip6_frag_lru_list);
- write_unlock(&ip6_frag_lock);
- return;
+
+ if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
+ fq->q.meat == fq->q.len)
+ return ip6_frag_reasm(fq, prev, dev);
+
+ write_lock(&ip6_frags.lock);
+ list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list);
+ write_unlock(&ip6_frags.lock);
+ return -1;
err:
- IP6_INC_STATS(IPSTATS_MIB_REASMFAILS);
+ IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
+ return -1;
}
/*
* 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 **skb_in,
- unsigned int *nhoffp,
+static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev)
{
- struct sk_buff *fp, *head = fq->fragments;
+ 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;
fq_kill(fq);
- BUG_TRAP(head != NULL);
- BUG_TRAP(FRAG6_CB(head)->offset == 0);
+ /* 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;
+ prev->next = fp;
+
+ skb_morph(head, fq->q.fragments);
+ head->next = fq->q.fragments->next;
+
+ kfree_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 - head->nh.raw) - sizeof(struct ipv6hdr) + fq->len - sizeof(struct frag_hdr);
+ 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;
/* 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_shinfo(head)->frag_list) {
+ if (skb_has_frags(head)) {
struct sk_buff *clone;
int i, plen = 0;
clone->next = head->next;
head->next = clone;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
- skb_shinfo(head)->frag_list = NULL;
+ skb_frag_list_init(head);
for (i=0; i<skb_shinfo(head)->nr_frags; i++)
plen += skb_shinfo(head)->frags[i].size;
clone->len = clone->data_len = head->data_len - plen;
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
- atomic_add(clone->truesize, &ip6_frag_mem);
+ atomic_add(clone->truesize, &fq->q.net->mem);
}
/* We have to remove fragment header from datagram and to relocate
* header in order to calculate ICV correctly. */
nhoff = fq->nhoffset;
- head->nh.raw[nhoff] = head->h.raw[0];
- memmove(head->head + sizeof(struct frag_hdr), head->head,
+ 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));
- head->mac.raw += sizeof(struct frag_hdr);
- head->nh.raw += sizeof(struct frag_hdr);
+ head->mac_header += sizeof(struct frag_hdr);
+ head->network_header += sizeof(struct frag_hdr);
skb_shinfo(head)->frag_list = head->next;
- head->h.raw = head->data;
- skb_push(head, head->data - head->nh.raw);
- atomic_sub(head->truesize, &ip6_frag_mem);
+ skb_reset_transport_header(head);
+ skb_push(head, head->data - skb_network_header(head));
+ atomic_sub(head->truesize, &fq->q.net->mem);
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_HW)
+ else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
- atomic_sub(fp->truesize, &ip6_frag_mem);
+ atomic_sub(fp->truesize, &fq->q.net->mem);
}
head->next = NULL;
head->dev = dev;
- skb_set_timestamp(head, &fq->stamp);
- head->nh.ipv6h->payload_len = htons(payload_len);
-
- *skb_in = head;
+ head->tstamp = fq->q.stamp;
+ ipv6_hdr(head)->payload_len = htons(payload_len);
+ IP6CB(head)->nhoff = nhoff;
/* Yes, and fold redundant checksum back. 8) */
- if (head->ip_summed == CHECKSUM_HW)
- head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum);
-
- IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS);
- fq->fragments = NULL;
- *nhoffp = nhoff;
+ if (head->ip_summed == CHECKSUM_COMPLETE)
+ head->csum = csum_partial(skb_network_header(head),
+ skb_network_header_len(head),
+ head->csum);
+
+ rcu_read_lock();
+ IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
+ rcu_read_unlock();
+ fq->q.fragments = NULL;
return 1;
out_oversize:
if (net_ratelimit())
printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n");
out_fail:
- IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+ rcu_read_lock();
+ IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
+ rcu_read_unlock();
return -1;
}
-static int ipv6_frag_rcv(struct sk_buff **skbp, unsigned int *nhoffp)
+static int ipv6_frag_rcv(struct sk_buff *skb)
{
- struct sk_buff *skb = *skbp;
- struct net_device *dev = skb->dev;
struct frag_hdr *fhdr;
struct frag_queue *fq;
- struct ipv6hdr *hdr;
+ struct ipv6hdr *hdr = ipv6_hdr(skb);
+ struct net *net = dev_net(skb_dst(skb)->dev);
- hdr = skb->nh.ipv6h;
-
- IP6_INC_STATS_BH(IPSTATS_MIB_REASMREQDS);
+ IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);
/* Jumbo payload inhibits frag. header */
- if (hdr->payload_len==0) {
- IP6_INC_STATS(IPSTATS_MIB_INHDRERRORS);
- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw);
- return -1;
- }
- if (!pskb_may_pull(skb, (skb->h.raw-skb->data)+sizeof(struct frag_hdr))) {
- IP6_INC_STATS(IPSTATS_MIB_INHDRERRORS);
- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw);
- return -1;
- }
+ if (hdr->payload_len==0)
+ goto fail_hdr;
+
+ if (!pskb_may_pull(skb, (skb_transport_offset(skb) +
+ sizeof(struct frag_hdr))))
+ goto fail_hdr;
- hdr = skb->nh.ipv6h;
- fhdr = (struct frag_hdr *)skb->h.raw;
+ hdr = ipv6_hdr(skb);
+ fhdr = (struct frag_hdr *)skb_transport_header(skb);
if (!(fhdr->frag_off & htons(0xFFF9))) {
/* It is not a fragmented frame */
- skb->h.raw += sizeof(struct frag_hdr);
- IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS);
+ skb->transport_header += sizeof(struct frag_hdr);
+ IP6_INC_STATS_BH(net,
+ ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS);
- *nhoffp = (u8*)fhdr - skb->nh.raw;
+ IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb);
return 1;
}
- if (atomic_read(&ip6_frag_mem) > sysctl_ip6frag_high_thresh)
- ip6_evictor();
-
- if ((fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr)) != NULL) {
- int ret = -1;
+ if (atomic_read(&net->ipv6.frags.mem) > net->ipv6.frags.high_thresh)
+ ip6_evictor(net, ip6_dst_idev(skb_dst(skb)));
- spin_lock(&fq->lock);
+ if ((fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
+ ip6_dst_idev(skb_dst(skb)))) != NULL) {
+ int ret;
- ip6_frag_queue(fq, skb, fhdr, *nhoffp);
+ spin_lock(&fq->q.lock);
- if (fq->last_in == (FIRST_IN|LAST_IN) &&
- fq->meat == fq->len)
- ret = ip6_frag_reasm(fq, skbp, nhoffp, dev);
+ ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
- spin_unlock(&fq->lock);
- fq_put(fq, NULL);
+ spin_unlock(&fq->q.lock);
+ fq_put(fq);
return ret;
}
- IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+ IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -1;
+
+fail_hdr:
+ IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS);
+ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb));
+ return -1;
}
-static struct inet6_protocol frag_protocol =
+static const struct inet6_protocol frag_protocol =
{
.handler = ipv6_frag_rcv,
.flags = INET6_PROTO_NOPOLICY,
};
-void __init ipv6_frag_init(void)
+#ifdef CONFIG_SYSCTL
+static struct ctl_table ip6_frags_ns_ctl_table[] = {
+ {
+ .procname = "ip6frag_high_thresh",
+ .data = &init_net.ipv6.frags.high_thresh,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "ip6frag_low_thresh",
+ .data = &init_net.ipv6.frags.low_thresh,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "ip6frag_time",
+ .data = &init_net.ipv6.frags.timeout,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
+ { }
+};
+
+static struct ctl_table ip6_frags_ctl_table[] = {
+ {
+ .procname = "ip6frag_secret_interval",
+ .data = &ip6_frags.secret_interval,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
+ { }
+};
+
+static int ip6_frags_ns_sysctl_register(struct net *net)
+{
+ struct ctl_table *table;
+ struct ctl_table_header *hdr;
+
+ table = ip6_frags_ns_ctl_table;
+ if (net != &init_net) {
+ table = kmemdup(table, sizeof(ip6_frags_ns_ctl_table), GFP_KERNEL);
+ if (table == NULL)
+ goto err_alloc;
+
+ table[0].data = &net->ipv6.frags.high_thresh;
+ table[1].data = &net->ipv6.frags.low_thresh;
+ table[2].data = &net->ipv6.frags.timeout;
+ }
+
+ hdr = register_net_sysctl_table(net, net_ipv6_ctl_path, table);
+ if (hdr == NULL)
+ goto err_reg;
+
+ net->ipv6.sysctl.frags_hdr = hdr;
+ return 0;
+
+err_reg:
+ if (net != &init_net)
+ kfree(table);
+err_alloc:
+ return -ENOMEM;
+}
+
+static void ip6_frags_ns_sysctl_unregister(struct net *net)
+{
+ struct ctl_table *table;
+
+ table = net->ipv6.sysctl.frags_hdr->ctl_table_arg;
+ unregister_net_sysctl_table(net->ipv6.sysctl.frags_hdr);
+ kfree(table);
+}
+
+static struct ctl_table_header *ip6_ctl_header;
+
+static int ip6_frags_sysctl_register(void)
+{
+ ip6_ctl_header = register_net_sysctl_rotable(net_ipv6_ctl_path,
+ ip6_frags_ctl_table);
+ return ip6_ctl_header == NULL ? -ENOMEM : 0;
+}
+
+static void ip6_frags_sysctl_unregister(void)
+{
+ unregister_net_sysctl_table(ip6_ctl_header);
+}
+#else
+static inline int ip6_frags_ns_sysctl_register(struct net *net)
+{
+ return 0;
+}
+
+static inline void ip6_frags_ns_sysctl_unregister(struct net *net)
+{
+}
+
+static inline int ip6_frags_sysctl_register(void)
+{
+ return 0;
+}
+
+static inline void ip6_frags_sysctl_unregister(void)
+{
+}
+#endif
+
+static int ipv6_frags_init_net(struct net *net)
+{
+ net->ipv6.frags.high_thresh = 256 * 1024;
+ net->ipv6.frags.low_thresh = 192 * 1024;
+ net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
+
+ inet_frags_init_net(&net->ipv6.frags);
+
+ return ip6_frags_ns_sysctl_register(net);
+}
+
+static void ipv6_frags_exit_net(struct net *net)
+{
+ ip6_frags_ns_sysctl_unregister(net);
+ inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+}
+
+static struct pernet_operations ip6_frags_ops = {
+ .init = ipv6_frags_init_net,
+ .exit = ipv6_frags_exit_net,
+};
+
+int __init ipv6_frag_init(void)
{
- if (inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT) < 0)
- printk(KERN_ERR "ipv6_frag_init: Could not register protocol\n");
+ int ret;
- ip6_frag_hash_rnd = (u32) ((num_physpages ^ (num_physpages>>7)) ^
- (jiffies ^ (jiffies >> 6)));
+ ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+ if (ret)
+ goto out;
- init_timer(&ip6_frag_secret_timer);
- ip6_frag_secret_timer.function = ip6_frag_secret_rebuild;
- ip6_frag_secret_timer.expires = jiffies + sysctl_ip6frag_secret_interval;
- add_timer(&ip6_frag_secret_timer);
+ ret = ip6_frags_sysctl_register();
+ if (ret)
+ goto err_sysctl;
+
+ ret = register_pernet_subsys(&ip6_frags_ops);
+ if (ret)
+ goto err_pernet;
+
+ ip6_frags.hashfn = ip6_hashfn;
+ ip6_frags.constructor = ip6_frag_init;
+ ip6_frags.destructor = NULL;
+ ip6_frags.skb_free = NULL;
+ ip6_frags.qsize = sizeof(struct frag_queue);
+ ip6_frags.match = ip6_frag_match;
+ ip6_frags.frag_expire = ip6_frag_expire;
+ ip6_frags.secret_interval = 10 * 60 * HZ;
+ inet_frags_init(&ip6_frags);
+out:
+ return ret;
+
+err_pernet:
+ ip6_frags_sysctl_unregister();
+err_sysctl:
+ inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+ goto out;
+}
+
+void ipv6_frag_exit(void)
+{
+ inet_frags_fini(&ip6_frags);
+ ip6_frags_sysctl_unregister();
+ unregister_pernet_subsys(&ip6_frags_ops);
+ inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
}