* Patrick McHardy : LRU queue of frag heads for evictor.
*/
-#include <linux/config.h>
+#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/checksum.h>
+#include <net/inetpeer.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/inet.h>
int sysctl_ipfrag_high_thresh = 256*1024;
int sysctl_ipfrag_low_thresh = 192*1024;
+int sysctl_ipfrag_max_dist = 64;
+
/* Important NOTE! Fragment queue must be destroyed before MSL expires.
* RFC791 is wrong proposing to prolongate timer each fragment arrival by TTL.
*/
spinlock_t lock;
atomic_t refcnt;
struct timer_list timer; /* when will this queue expire? */
- int iif;
struct timeval stamp;
+ int iif;
+ unsigned int rid;
+ struct inet_peer *peer;
};
/* Hash table. */
BUG_TRAP(qp->last_in&COMPLETE);
BUG_TRAP(del_timer(&qp->timer) == 0);
+ if (qp->peer)
+ inet_putpeer(qp->peer);
+
/* Release all fragment data. */
fp = qp->fragments;
while (fp) {
/* Creation primitives. */
-static struct ipq *ip_frag_intern(unsigned int hash, struct ipq *qp_in)
+static struct ipq *ip_frag_intern(struct ipq *qp_in)
{
struct ipq *qp;
#ifdef CONFIG_SMP
struct hlist_node *n;
#endif
+ unsigned int hash;
+
write_lock(&ipfrag_lock);
+ hash = ipqhashfn(qp_in->id, qp_in->saddr, qp_in->daddr,
+ qp_in->protocol);
#ifdef CONFIG_SMP
/* With SMP race we have to recheck hash table, because
* such entry could be created on other cpu, while we
}
/* Add an entry to the 'ipq' queue for a newly received IP datagram. */
-static struct ipq *ip_frag_create(unsigned hash, struct iphdr *iph, u32 user)
+static struct ipq *ip_frag_create(struct iphdr *iph, u32 user)
{
struct ipq *qp;
qp->meat = 0;
qp->fragments = NULL;
qp->iif = 0;
+ qp->peer = sysctl_ipfrag_max_dist ? inet_getpeer(iph->saddr, 1) : NULL;
/* Initialize a timer for this entry. */
init_timer(&qp->timer);
spin_lock_init(&qp->lock);
atomic_set(&qp->refcnt, 1);
- return ip_frag_intern(hash, qp);
+ return ip_frag_intern(qp);
out_nomem:
LIMIT_NETDEBUG(KERN_ERR "ip_frag_create: no memory left !\n");
*/
static inline struct ipq *ip_find(struct iphdr *iph, u32 user)
{
- __u16 id = iph->id;
+ __be16 id = iph->id;
__u32 saddr = iph->saddr;
__u32 daddr = iph->daddr;
__u8 protocol = iph->protocol;
- unsigned int hash = ipqhashfn(id, saddr, daddr, protocol);
+ unsigned int hash;
struct ipq *qp;
struct hlist_node *n;
read_lock(&ipfrag_lock);
+ hash = ipqhashfn(id, saddr, daddr, protocol);
hlist_for_each_entry(qp, n, &ipq_hash[hash], list) {
if(qp->id == id &&
qp->saddr == saddr &&
}
read_unlock(&ipfrag_lock);
- return ip_frag_create(hash, iph, user);
+ return ip_frag_create(iph, user);
+}
+
+/* Is the fragment too far ahead to be part of ipq? */
+static inline int ip_frag_too_far(struct ipq *qp)
+{
+ struct inet_peer *peer = qp->peer;
+ unsigned int max = sysctl_ipfrag_max_dist;
+ unsigned int start, end;
+
+ int rc;
+
+ if (!peer || !max)
+ return 0;
+
+ start = qp->rid;
+ end = atomic_inc_return(&peer->rid);
+ qp->rid = end;
+
+ rc = qp->fragments && (end - start) > max;
+
+ if (rc) {
+ IP_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+ }
+
+ return rc;
+}
+
+static int ip_frag_reinit(struct ipq *qp)
+{
+ struct sk_buff *fp;
+
+ if (!mod_timer(&qp->timer, jiffies + sysctl_ipfrag_time)) {
+ atomic_inc(&qp->refcnt);
+ return -ETIMEDOUT;
+ }
+
+ fp = qp->fragments;
+ do {
+ struct sk_buff *xp = fp->next;
+ frag_kfree_skb(fp, NULL);
+ fp = xp;
+ } while (fp);
+
+ qp->last_in = 0;
+ qp->len = 0;
+ qp->meat = 0;
+ qp->fragments = NULL;
+ qp->iif = 0;
+
+ return 0;
}
/* Add new segment to existing queue. */
if (qp->last_in & COMPLETE)
goto err;
+ if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) &&
+ unlikely(ip_frag_too_far(qp)) && unlikely(ip_frag_reinit(qp))) {
+ ipq_kill(qp);
+ goto err;
+ }
+
offset = ntohs(skb->nh.iph->frag_off);
flags = offset & ~IP_OFFSET;
offset &= IP_OFFSET;