*
* 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.
#include <linux/netdevice.h>
#include <linux/jhash.h>
#include <linux/random.h>
+#include <net/route.h>
+#include <net/dst.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
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 {
struct inet_peer *peer;
};
-static struct inet_frags_ctl ip4_frags_ctl __read_mostly = {
- /*
- * Fragment cache limits. We will commit 256K at one time. Should we
- * cross that limit we will prune down to 192K. This should cope with
- * even the most extreme cases without allowing an attacker to
- * measurably harm machine performance.
- */
- .high_thresh = 256 * 1024,
- .low_thresh = 192 * 1024,
-
- /*
- * Important NOTE! Fragment queue must be destroyed before MSL expires.
- * RFC791 is wrong proposing to prolongate timer each fragment arrival
- * by TTL.
- */
- .timeout = IP_FRAG_TIME,
- .secret_interval = 10 * 60 * HZ,
-};
-
static struct inet_frags ip4_frags;
int ip_frag_nqueues(struct net *net)
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) {
- icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
- dev_put(head->dev);
+
+ rcu_read_lock();
+ head->dev = dev_get_by_index_rcu(net, qp->iif);
+ if (!head->dev)
+ goto out_rcu_unlock;
+
+ /*
+ * Only search router table for the head fragment,
+ * when defraging timeout at PRE_ROUTING HOOK.
+ */
+ if (qp->user == IP_DEFRAG_CONNTRACK_IN && !skb_dst(head)) {
+ const struct iphdr *iph = ip_hdr(head);
+ int err = ip_route_input(head, iph->daddr, iph->saddr,
+ iph->tos, head->dev);
+ if (unlikely(err))
+ goto out_rcu_unlock;
+
+ /*
+ * Only an end host needs to send an ICMP
+ * "Fragment Reassembly Timeout" message, per RFC792.
+ */
+ if (skb_rtable(head)->rt_type != RTN_LOCAL)
+ goto out_rcu_unlock;
+
}
+
+ /* Send an ICMP "Fragment Reassembly Timeout" message. */
+ icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
+out_rcu_unlock:
+ rcu_read_unlock();
}
out:
spin_unlock(&qp->q.lock);
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;
{
struct sk_buff *fp;
- if (!mod_timer(&qp->q.timer, jiffies + ip4_frags_ctl.timeout)) {
+ if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) {
atomic_inc(&qp->q.refcnt);
return -ETIMEDOUT;
}
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);
- list_move_tail(&qp->q.lru_list, &ip4_frags.lru_list);
+ list_move_tail(&qp->q.lru_list, &qp->q.net->lru_list);
write_unlock(&ip4_frags.lock);
return -EINPROGRESS;
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev)
{
+ struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct iphdr *iph;
struct sk_buff *fp, *head = qp->q.fragments;
int len;
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);
/* 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;
iph = ip_hdr(head);
iph->frag_off = 0;
iph->tot_len = htons(len);
- IP_INC_STATS_BH(IPSTATS_MIB_REASMOKS);
+ IP_INC_STATS_BH(net, 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(net, 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(skb)->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) > ip4_frags_ctl.high_thresh)
+ if (atomic_read(&net->ipv4.frags.mem) > net->ipv4.frags.high_thresh)
ip_evictor(net);
/* Lookup (or create) queue header */
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 = &ip4_frags_ctl.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,
.procname = "ipfrag_low_thresh",
- .data = &ip4_frags_ctl.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,
.procname = "ipfrag_time",
- .data = &ip4_frags_ctl.timeout,
+ .data = &init_net.ipv4.frags.timeout,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
- .strategy = &sysctl_jiffies
+ .proc_handler = proc_dointvec_jiffies,
},
+ { }
+};
+
+static struct ctl_table ip4_frags_ctl_table[] = {
{
- .ctl_name = NET_IPV4_IPFRAG_SECRET_INTERVAL,
.procname = "ipfrag_secret_interval",
- .data = &ip4_frags_ctl.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,
},
{
.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 __net_init ip4_frags_ns_ctl_register(struct net *net)
{
struct ctl_table *table;
struct ctl_table_header *hdr;
- table = ip4_frags_ctl_table;
- if (net != &init_net) {
- table = kmemdup(table, sizeof(ip4_frags_ctl_table), GFP_KERNEL);
+ table = ip4_frags_ns_ctl_table;
+ if (!net_eq(net, &init_net)) {
+ table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL);
if (table == NULL)
goto err_alloc;
- table[0].mode &= ~0222;
- table[1].mode &= ~0222;
- table[2].mode &= ~0222;
- table[3].mode &= ~0222;
- table[4].mode &= ~0222;
+ table[0].data = &net->ipv4.frags.high_thresh;
+ table[1].data = &net->ipv4.frags.low_thresh;
+ table[2].data = &net->ipv4.frags.timeout;
}
hdr = register_net_sysctl_table(net, net_ipv4_ctl_path, table);
return 0;
err_reg:
- if (net != &init_net)
+ if (!net_eq(net, &init_net))
kfree(table);
err_alloc:
return -ENOMEM;
}
-static void ip4_frags_ctl_unregister(struct net *net)
+static void __net_exit 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
-static int ipv4_frags_init_net(struct net *net)
+static int __net_init ipv4_frags_init_net(struct net *net)
{
+ /*
+ * Fragment cache limits. We will commit 256K at one time. Should we
+ * cross that limit we will prune down to 192K. This should cope with
+ * even the most extreme cases without allowing an attacker to
+ * measurably harm machine performance.
+ */
+ net->ipv4.frags.high_thresh = 256 * 1024;
+ net->ipv4.frags.low_thresh = 192 * 1024;
+ /*
+ * Important NOTE! Fragment queue must be destroyed before MSL expires.
+ * RFC791 is wrong proposing to prolongate timer each fragment arrival
+ * by TTL.
+ */
+ net->ipv4.frags.timeout = IP_FRAG_TIME;
+
inet_frags_init_net(&net->ipv4.frags);
- return ip4_frags_ctl_register(net);
+ return ip4_frags_ns_ctl_register(net);
+}
+
+static void __net_exit 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 = &ip4_frags_ctl;
+ 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;
ip4_frags.qsize = sizeof(struct ipq);
ip4_frags.match = ip4_frag_match;
ip4_frags.frag_expire = ip_expire;
+ ip4_frags.secret_interval = 10 * 60 * HZ;
inet_frags_init(&ip4_frags);
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff