#include <net/addrconf.h>
#include <net/inet_frag.h>
-int sysctl_ip6frag_high_thresh __read_mostly = 256*1024;
-int sysctl_ip6frag_low_thresh __read_mostly = 192*1024;
-
-int sysctl_ip6frag_time __read_mostly = IPV6_FRAG_TIMEOUT;
-
struct ip6frag_skb_cb
{
struct inet6_skb_parm h;
static struct inet_frags ip6_frags;
-int ip6_frag_nqueues(void)
+int ip6_frag_nqueues(struct net *net)
{
- return ip6_frags.nqueues;
+ return net->ipv6.frags.nqueues;
}
-int ip6_frag_mem(void)
+int ip6_frag_mem(struct net *net)
{
- return atomic_read(&ip6_frags.mem);
+ return atomic_read(&net->ipv6.frags.mem);
}
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev);
-static __inline__ void __fq_unlink(struct frag_queue *fq)
-{
- hlist_del(&fq->q.list);
- list_del(&fq->q.lru_list);
- ip6_frags.nqueues--;
-}
-
-static __inline__ void fq_unlink(struct frag_queue *fq)
-{
- write_lock(&ip6_frags.lock);
- __fq_unlink(fq);
- write_unlock(&ip6_frags.lock);
-}
-
/*
* 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.
return c & (INETFRAGS_HASHSZ - 1);
}
-int sysctl_ip6frag_secret_interval __read_mostly = 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_frags.lock);
- get_random_bytes(&ip6_frags.rnd, sizeof(u32));
- for (i = 0; i < INETFRAGS_HASHSZ; i++) {
- struct frag_queue *q;
- struct hlist_node *p, *n;
-
- hlist_for_each_entry_safe(q, p, n, &ip6_frags.hash[i], q.list) {
- unsigned int hval = ip6qhashfn(q->id,
- &q->saddr,
- &q->daddr);
-
- if (hval != i) {
- hlist_del(&q->q.list);
+ struct frag_queue *fq;
- /* Relink to new hash chain. */
- hlist_add_head(&q->q.list,
- &ip6_frags.hash[hval]);
+ fq = container_of(q, struct frag_queue, q);
+ return ip6qhashfn(fq->id, &fq->saddr, &fq->daddr);
+}
- }
- }
- }
- write_unlock(&ip6_frags.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_frags.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));
}
+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_frags.mem);
+ atomic_sub(skb->truesize, &nf->mem);
kfree_skb(skb);
}
-static inline void frag_free_queue(struct frag_queue *fq, int *work)
+void ip6_frag_init(struct inet_frag_queue *q, void *a)
{
- if (work)
- *work -= sizeof(struct frag_queue);
- atomic_sub(sizeof(struct frag_queue), &ip6_frags.mem);
- kfree(fq);
-}
-
-static inline struct frag_queue *frag_alloc_queue(void)
-{
- struct frag_queue *fq = kzalloc(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_frags.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)
+static __inline__ void fq_put(struct frag_queue *fq)
{
- struct sk_buff *fp;
-
- BUG_TRAP(fq->q.last_in&COMPLETE);
- BUG_TRAP(del_timer(&fq->q.timer) == 0);
-
- /* Release all fragment data. */
- fp = fq->q.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)
-{
- if (atomic_dec_and_test(&fq->q.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->q.timer))
- atomic_dec(&fq->q.refcnt);
-
- if (!(fq->q.last_in & COMPLETE)) {
- fq_unlink(fq);
- atomic_dec(&fq->q.refcnt);
- fq->q.last_in |= COMPLETE;
- }
+ inet_frag_kill(&fq->q, &ip6_frags);
}
-static void ip6_evictor(struct inet6_dev *idev)
+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_frags.mem) - sysctl_ip6frag_low_thresh;
- if (work <= 0)
- return;
-
- while(work > 0) {
- read_lock(&ip6_frags.lock);
- if (list_empty(&ip6_frags.lru_list)) {
- read_unlock(&ip6_frags.lock);
- return;
- }
- tmp = ip6_frags.lru_list.next;
- fq = list_entry(tmp, struct frag_queue, q.lru_list);
- atomic_inc(&fq->q.refcnt);
- read_unlock(&ip6_frags.lock);
+ int evicted;
- spin_lock(&fq->q.lock);
- if (!(fq->q.last_in&COMPLETE))
- fq_kill(fq);
- spin_unlock(&fq->q.lock);
-
- fq_put(fq, &work);
- IP6_INC_STATS_BH(idev, IPSTATS_MIB_REASMFAILS);
- }
+ evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags);
+ if (evicted)
+ IP6_ADD_STATS_BH(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;
+ fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+
spin_lock(&fq->q.lock);
if (fq->q.last_in & COMPLETE)
if (dev)
dev_put(dev);
spin_unlock(&fq->q.lock);
- fq_put(fq, NULL);
+ fq_put(fq);
}
-/* Creation primitives. */
-
-
-static struct frag_queue *ip6_frag_intern(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;
+ struct inet_frag_queue *q;
+ struct ip6_create_arg arg;
unsigned int hash;
-#ifdef CONFIG_SMP
- struct hlist_node *n;
-#endif
- write_lock(&ip6_frags.lock);
- hash = ip6qhashfn(fq_in->id, &fq_in->saddr, &fq_in->daddr);
-#ifdef CONFIG_SMP
- hlist_for_each_entry(fq, n, &ip6_frags.hash[hash], q.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->q.refcnt);
- write_unlock(&ip6_frags.lock);
- fq_in->q.last_in |= COMPLETE;
- fq_put(fq_in, NULL);
- return fq;
- }
- }
-#endif
- fq = fq_in;
-
- if (!mod_timer(&fq->q.timer, jiffies + sysctl_ip6frag_time))
- atomic_inc(&fq->q.refcnt);
-
- atomic_inc(&fq->q.refcnt);
- hlist_add_head(&fq->q.list, &ip6_frags.hash[hash]);
- INIT_LIST_HEAD(&fq->q.lru_list);
- list_add_tail(&fq->q.lru_list, &ip6_frags.lru_list);
- ip6_frags.nqueues++;
- write_unlock(&ip6_frags.lock);
- return fq;
-}
-
-
-static struct frag_queue *
-ip6_frag_create(__be32 id, struct in6_addr *src, struct in6_addr *dst,
- struct inet6_dev *idev)
-{
- struct frag_queue *fq;
+ arg.id = id;
+ arg.src = src;
+ arg.dst = dst;
+ hash = ip6qhashfn(id, src, dst);
- if ((fq = frag_alloc_queue()) == NULL)
+ q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
+ if (q == NULL)
goto oom;
- fq->id = id;
- ipv6_addr_copy(&fq->saddr, src);
- ipv6_addr_copy(&fq->daddr, dst);
-
- init_timer(&fq->q.timer);
- fq->q.timer.function = ip6_frag_expire;
- fq->q.timer.data = (long) fq;
- spin_lock_init(&fq->q.lock);
- atomic_set(&fq->q.refcnt, 1);
-
- return ip6_frag_intern(fq);
+ return container_of(q, struct frag_queue, q);
oom:
IP6_INC_STATS_BH(idev, IPSTATS_MIB_REASMFAILS);
return NULL;
}
-static __inline__ struct frag_queue *
-fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst,
- struct inet6_dev *idev)
-{
- struct frag_queue *fq;
- struct hlist_node *n;
- unsigned int hash;
-
- read_lock(&ip6_frags.lock);
- hash = ip6qhashfn(id, src, dst);
- hlist_for_each_entry(fq, n, &ip6_frags.hash[hash], q.list) {
- if (fq->id == id &&
- ipv6_addr_equal(src, &fq->saddr) &&
- ipv6_addr_equal(dst, &fq->daddr)) {
- atomic_inc(&fq->q.refcnt);
- read_unlock(&ip6_frags.lock);
- return fq;
- }
- }
- read_unlock(&ip6_frags.lock);
-
- return ip6_frag_create(id, src, dst, idev);
-}
-
-
static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
struct frag_hdr *fhdr, int nhoff)
{
fq->q.fragments = next;
fq->q.meat -= free_it->len;
- frag_kfree_skb(free_it, NULL);
+ frag_kfree_skb(fq->q.net, free_it, NULL);
}
}
}
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
- atomic_add(skb->truesize, &ip6_frags.mem);
+ atomic_add(skb->truesize, &fq->q.net->mem);
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
return ip6_frag_reasm(fq, prev, dev);
write_lock(&ip6_frags.lock);
- list_move_tail(&fq->q.lru_list, &ip6_frags.lru_list);
+ list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list);
write_unlock(&ip6_frags.lock);
return -1;
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
- atomic_add(clone->truesize, &ip6_frags.mem);
+ atomic_add(clone->truesize, &fq->q.net->mem);
}
/* We have to remove fragment header from datagram and to relocate
skb_shinfo(head)->frag_list = head->next;
skb_reset_transport_header(head);
skb_push(head, head->data - skb_network_header(head));
- atomic_sub(head->truesize, &ip6_frags.mem);
+ atomic_sub(head->truesize, &fq->q.net->mem);
for (fp=head->next; fp; fp = fp->next) {
head->data_len += fp->len;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
- atomic_sub(fp->truesize, &ip6_frags.mem);
+ atomic_sub(fp->truesize, &fq->q.net->mem);
}
head->next = NULL;
return -1;
}
-static int ipv6_frag_rcv(struct sk_buff **skbp)
+static int ipv6_frag_rcv(struct sk_buff *skb)
{
- struct sk_buff *skb = *skbp;
struct frag_hdr *fhdr;
struct frag_queue *fq;
struct ipv6hdr *hdr = ipv6_hdr(skb);
+ struct net *net;
IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMREQDS);
return 1;
}
- if (atomic_read(&ip6_frags.mem) > sysctl_ip6frag_high_thresh)
- ip6_evictor(ip6_dst_idev(skb->dst));
+ net = skb->dev->nd_net;
+ if (atomic_read(&net->ipv6.frags.mem) > net->ipv6.frags.high_thresh)
+ ip6_evictor(net, ip6_dst_idev(skb->dst));
- if ((fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr,
+ if ((fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
ip6_dst_idev(skb->dst))) != NULL) {
int ret;
ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
spin_unlock(&fq->q.lock);
- fq_put(fq, NULL);
+ fq_put(fq);
return ret;
}
.flags = INET6_PROTO_NOPOLICY,
};
-void __init ipv6_frag_init(void)
+#ifdef CONFIG_SYSCTL
+static struct ctl_table ip6_frags_ctl_table[] = {
+ {
+ .ctl_name = NET_IPV6_IP6FRAG_HIGH_THRESH,
+ .procname = "ip6frag_high_thresh",
+ .data = &init_net.ipv6.frags.high_thresh,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec
+ },
+ {
+ .ctl_name = NET_IPV6_IP6FRAG_LOW_THRESH,
+ .procname = "ip6frag_low_thresh",
+ .data = &init_net.ipv6.frags.low_thresh,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec
+ },
+ {
+ .ctl_name = NET_IPV6_IP6FRAG_TIME,
+ .procname = "ip6frag_time",
+ .data = &init_net.ipv6.frags.timeout,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_jiffies,
+ .strategy = &sysctl_jiffies,
+ },
+ {
+ .ctl_name = NET_IPV6_IP6FRAG_SECRET_INTERVAL,
+ .procname = "ip6frag_secret_interval",
+ .data = &ip6_frags.secret_interval,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_jiffies,
+ .strategy = &sysctl_jiffies
+ },
+ { }
+};
+
+static int ip6_frags_sysctl_register(struct net *net)
+{
+ struct ctl_table *table;
+ struct ctl_table_header *hdr;
+
+ table = ip6_frags_ctl_table;
+ if (net != &init_net) {
+ table = kmemdup(table, sizeof(ip6_frags_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;
+ table[3].mode &= ~0222;
+ }
+
+ 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_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);
+}
+#else
+static inline int ip6_frags_sysctl_register(struct net *net)
+{
+ return 0;
+}
+
+static inline void ip6_frags_sysctl_unregister(struct net *net)
+{
+}
+#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_sysctl_register(net);
+}
+
+static void ipv6_frags_exit_net(struct net *net)
+{
+ ip6_frags_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;
+
+ ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+ if (ret)
+ goto out;
- init_timer(&ip6_frags.secret_timer);
- ip6_frags.secret_timer.function = ip6_frag_secret_rebuild;
- ip6_frags.secret_timer.expires = jiffies + sysctl_ip6frag_secret_interval;
- add_timer(&ip6_frags.secret_timer);
+ register_pernet_subsys(&ip6_frags_ops);
+ 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;
+}
+
+void ipv6_frag_exit(void)
+{
+ inet_frags_fini(&ip6_frags);
+ unregister_pernet_subsys(&ip6_frags_ops);
+ inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
}