*
* The IP fragmentation functionality.
*
- * Version: $Id: ip_fragment.c,v 1.59 2002/01/12 07:54:56 davem Exp $
- *
* Authors: Fred N. van Kempen <waltje@uWalt.NL.Mugnet.ORG>
- * Alan Cox <Alan.Cox@linux.org>
+ * Alan Cox <alan@lxorguk.ukuu.org.uk>
*
* Fixes:
* Alan Cox : Split from ip.c , see ip_input.c for history.
int offset;
};
-#define FRAG_CB(skb) ((struct ipfrag_skb_cb*)((skb)->cb))
+#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb))
/* Describe an entry in the "incomplete datagrams" queue. */
struct ipq {
evicted = inet_frag_evictor(&net->ipv4.frags, &ip4_frags);
if (evicted)
- IP_ADD_STATS_BH(IPSTATS_MIB_REASMFAILS, evicted);
+ IP_ADD_STATS_BH(net, IPSTATS_MIB_REASMFAILS, evicted);
}
/*
static void ip_expire(unsigned long arg)
{
struct ipq *qp;
+ struct net *net;
qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
+ net = container_of(qp->q.net, struct net, ipv4.frags);
spin_lock(&qp->q.lock);
- if (qp->q.last_in & COMPLETE)
+ if (qp->q.last_in & INET_FRAG_COMPLETE)
goto out;
ipq_kill(qp);
- IP_INC_STATS_BH(IPSTATS_MIB_REASMTIMEOUT);
- IP_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
- if ((qp->q.last_in&FIRST_IN) && qp->q.fragments != NULL) {
+ if ((qp->q.last_in & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) {
struct sk_buff *head = qp->q.fragments;
+
/* Send an ICMP "Fragment Reassembly Timeout" message. */
- if ((head->dev = dev_get_by_index(&init_net, qp->iif)) != NULL) {
+ if ((head->dev = dev_get_by_index(net, qp->iif)) != NULL) {
icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
dev_put(head->dev);
}
arg.iph = iph;
arg.user = user;
+
+ read_lock(&ip4_frags.lock);
hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
rc = qp->q.fragments && (end - start) > max;
if (rc) {
- IP_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+ struct net *net;
+
+ net = container_of(qp->q.net, struct net, ipv4.frags);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
}
return rc;
int ihl, end;
int err = -ENOENT;
- if (qp->q.last_in & COMPLETE)
+ if (qp->q.last_in & INET_FRAG_COMPLETE)
goto err;
if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) &&
* or have different end, the segment is corrrupted.
*/
if (end < qp->q.len ||
- ((qp->q.last_in & LAST_IN) && end != qp->q.len))
+ ((qp->q.last_in & INET_FRAG_LAST_IN) && end != qp->q.len))
goto err;
- qp->q.last_in |= LAST_IN;
+ qp->q.last_in |= INET_FRAG_LAST_IN;
qp->q.len = end;
} else {
if (end&7) {
}
if (end > qp->q.len) {
/* Some bits beyond end -> corruption. */
- if (qp->q.last_in & LAST_IN)
+ if (qp->q.last_in & INET_FRAG_LAST_IN)
goto err;
qp->q.len = end;
}
qp->q.meat += skb->len;
atomic_add(skb->truesize, &qp->q.net->mem);
if (offset == 0)
- qp->q.last_in |= FIRST_IN;
+ qp->q.last_in |= INET_FRAG_FIRST_IN;
- if (qp->q.last_in == (FIRST_IN | LAST_IN) && qp->q.meat == qp->q.len)
+ if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
+ qp->q.meat == qp->q.len)
return ip_frag_reasm(qp, prev, dev);
write_lock(&ip4_frags.lock);
qp->q.fragments = head;
}
- BUG_TRAP(head != NULL);
- BUG_TRAP(FRAG_CB(head)->offset == 0);
+ WARN_ON(head == NULL);
+ WARN_ON(FRAG_CB(head)->offset != 0);
/* Allocate a new buffer for the datagram. */
ihlen = ip_hdrlen(head);
iph = ip_hdr(head);
iph->frag_off = 0;
iph->tot_len = htons(len);
- IP_INC_STATS_BH(IPSTATS_MIB_REASMOKS);
+ IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
return 0;
goto out_fail;
out_oversize:
if (net_ratelimit())
- printk(KERN_INFO
- "Oversized IP packet from %d.%d.%d.%d.\n",
- NIPQUAD(qp->saddr));
+ printk(KERN_INFO "Oversized IP packet from %pI4.\n",
+ &qp->saddr);
out_fail:
- IP_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+ IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_REASMFAILS);
return err;
}
struct ipq *qp;
struct net *net;
- IP_INC_STATS_BH(IPSTATS_MIB_REASMREQDS);
+ net = skb->dev ? dev_net(skb->dev) : dev_net(skb->dst->dev);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
- net = skb->dev->nd_net;
/* Start by cleaning up the memory. */
if (atomic_read(&net->ipv4.frags.mem) > net->ipv4.frags.high_thresh)
ip_evictor(net);
return ret;
}
- IP_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -ENOMEM;
}
#ifdef CONFIG_SYSCTL
static int zero;
-static struct ctl_table ip4_frags_ctl_table[] = {
+static struct ctl_table ip4_frags_ns_ctl_table[] = {
{
.ctl_name = NET_IPV4_IPFRAG_HIGH_THRESH,
.procname = "ipfrag_high_thresh",
.data = &init_net.ipv4.frags.high_thresh,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec
+ .proc_handler = proc_dointvec
},
{
.ctl_name = NET_IPV4_IPFRAG_LOW_THRESH,
.data = &init_net.ipv4.frags.low_thresh,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec
+ .proc_handler = proc_dointvec
},
{
.ctl_name = NET_IPV4_IPFRAG_TIME,
.data = &init_net.ipv4.frags.timeout,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
- .strategy = &sysctl_jiffies
+ .proc_handler = proc_dointvec_jiffies,
+ .strategy = sysctl_jiffies
},
+ { }
+};
+
+static struct ctl_table ip4_frags_ctl_table[] = {
{
.ctl_name = NET_IPV4_IPFRAG_SECRET_INTERVAL,
.procname = "ipfrag_secret_interval",
.data = &ip4_frags.secret_interval,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
- .strategy = &sysctl_jiffies
+ .proc_handler = proc_dointvec_jiffies,
+ .strategy = sysctl_jiffies
},
{
.procname = "ipfrag_max_dist",
.data = &sysctl_ipfrag_max_dist,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &zero
},
{ }
};
-static int ip4_frags_ctl_register(struct net *net)
+static int ip4_frags_ns_ctl_register(struct net *net)
{
struct ctl_table *table;
struct ctl_table_header *hdr;
- table = ip4_frags_ctl_table;
+ table = ip4_frags_ns_ctl_table;
if (net != &init_net) {
- table = kmemdup(table, sizeof(ip4_frags_ctl_table), GFP_KERNEL);
+ table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL);
if (table == NULL)
goto err_alloc;
table[0].data = &net->ipv4.frags.high_thresh;
table[1].data = &net->ipv4.frags.low_thresh;
table[2].data = &net->ipv4.frags.timeout;
- table[3].mode &= ~0222;
- table[4].mode &= ~0222;
}
hdr = register_net_sysctl_table(net, net_ipv4_ctl_path, table);
return -ENOMEM;
}
-static void ip4_frags_ctl_unregister(struct net *net)
+static void ip4_frags_ns_ctl_unregister(struct net *net)
{
struct ctl_table *table;
unregister_net_sysctl_table(net->ipv4.frags_hdr);
kfree(table);
}
+
+static void ip4_frags_ctl_register(void)
+{
+ register_net_sysctl_rotable(net_ipv4_ctl_path, ip4_frags_ctl_table);
+}
#else
-static inline int ip4_frags_ctl_register(struct net *net)
+static inline int ip4_frags_ns_ctl_register(struct net *net)
{
return 0;
}
-static inline void ip4_frags_ctl_unregister(struct net *net)
+static inline void ip4_frags_ns_ctl_unregister(struct net *net)
+{
+}
+
+static inline void ip4_frags_ctl_register(void)
{
}
#endif
inet_frags_init_net(&net->ipv4.frags);
- return ip4_frags_ctl_register(net);
+ return ip4_frags_ns_ctl_register(net);
}
+static void ipv4_frags_exit_net(struct net *net)
+{
+ ip4_frags_ns_ctl_unregister(net);
+ inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+}
+
+static struct pernet_operations ip4_frags_ops = {
+ .init = ipv4_frags_init_net,
+ .exit = ipv4_frags_exit_net,
+};
+
void __init ipfrag_init(void)
{
- ipv4_frags_init_net(&init_net);
+ ip4_frags_ctl_register();
+ register_pernet_subsys(&ip4_frags_ops);
ip4_frags.hashfn = ip4_hashfn;
ip4_frags.constructor = ip4_frag_init;
ip4_frags.destructor = ip4_frag_free;