#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <net/net_namespace.h>
#include <net/icmp.h>
#include <net/route.h>
#include <net/checksum.h>
*/
DEFINE_SNMP_STAT(struct udp_mib, udp_statistics) __read_mostly;
+EXPORT_SYMBOL(udp_statistics);
struct hlist_head udp_hash[UDP_HTABLE_SIZE];
DEFINE_RWLOCK(udp_hash_lock);
-static int udp_port_rover;
-
-static inline int __udp_lib_lport_inuse(__u16 num, struct hlist_head udptable[])
+static inline int __udp_lib_lport_inuse(__u16 num,
+ const struct hlist_head udptable[])
{
struct sock *sk;
struct hlist_node *node;
* @sk: socket struct in question
* @snum: port number to look up
* @udptable: hash list table, must be of UDP_HTABLE_SIZE
- * @port_rover: pointer to record of last unallocated port
* @saddr_comp: AF-dependent comparison of bound local IP addresses
*/
int __udp_lib_get_port(struct sock *sk, unsigned short snum,
- struct hlist_head udptable[], int *port_rover,
+ struct hlist_head udptable[],
int (*saddr_comp)(const struct sock *sk1,
const struct sock *sk2 ) )
{
int error = 1;
write_lock_bh(&udp_hash_lock);
- if (snum == 0) {
- int best_size_so_far, best, result, i;
-
- if (*port_rover > sysctl_local_port_range[1] ||
- *port_rover < sysctl_local_port_range[0])
- *port_rover = sysctl_local_port_range[0];
- best_size_so_far = 32767;
- best = result = *port_rover;
- for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) {
- int size;
-
- head = &udptable[result & (UDP_HTABLE_SIZE - 1)];
- if (hlist_empty(head)) {
- if (result > sysctl_local_port_range[1])
- result = sysctl_local_port_range[0] +
- ((result - sysctl_local_port_range[0]) &
- (UDP_HTABLE_SIZE - 1));
+
+ if (!snum) {
+ int i, low, high, remaining;
+ unsigned rover, best, best_size_so_far;
+
+ inet_get_local_port_range(&low, &high);
+ remaining = (high - low) + 1;
+
+ best_size_so_far = UINT_MAX;
+ best = rover = net_random() % remaining + low;
+
+ /* 1st pass: look for empty (or shortest) hash chain */
+ for (i = 0; i < UDP_HTABLE_SIZE; i++) {
+ int size = 0;
+
+ head = &udptable[rover & (UDP_HTABLE_SIZE - 1)];
+ if (hlist_empty(head))
goto gotit;
- }
- size = 0;
+
sk_for_each(sk2, node, head) {
if (++size >= best_size_so_far)
goto next;
}
best_size_so_far = size;
- best = result;
+ best = rover;
next:
- ;
+ /* fold back if end of range */
+ if (++rover > high)
+ rover = low + ((rover - low)
+ & (UDP_HTABLE_SIZE - 1));
+
+
}
- result = best;
- for (i = 0; i < (1 << 16) / UDP_HTABLE_SIZE;
- i++, result += UDP_HTABLE_SIZE) {
- if (result > sysctl_local_port_range[1])
- result = sysctl_local_port_range[0]
- + ((result - sysctl_local_port_range[0]) &
- (UDP_HTABLE_SIZE - 1));
- if (! __udp_lib_lport_inuse(result, udptable))
- break;
+
+ /* 2nd pass: find hole in shortest hash chain */
+ rover = best;
+ for (i = 0; i < (1 << 16) / UDP_HTABLE_SIZE; i++) {
+ if (! __udp_lib_lport_inuse(rover, udptable))
+ goto gotit;
+ rover += UDP_HTABLE_SIZE;
+ if (rover > high)
+ rover = low + ((rover - low)
+ & (UDP_HTABLE_SIZE - 1));
}
- if (i >= (1 << 16) / UDP_HTABLE_SIZE)
- goto fail;
+
+
+ /* All ports in use! */
+ goto fail;
+
gotit:
- *port_rover = snum = result;
+ snum = rover;
} else {
head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
(*saddr_comp)(sk, sk2) )
goto fail;
}
+
inet_sk(sk)->num = snum;
sk->sk_hash = snum;
if (sk_unhashed(sk)) {
int udp_get_port(struct sock *sk, unsigned short snum,
int (*scmp)(const struct sock *, const struct sock *))
{
- return __udp_lib_get_port(sk, snum, udp_hash, &udp_port_rover, scmp);
+ return __udp_lib_get_port(sk, snum, udp_hash, scmp);
}
int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
struct sk_buff *skb;
struct udphdr *uh;
int err = 0;
+ int is_udplite = IS_UDPLITE(sk);
__wsum csum = 0;
/* Grab the skbuff where UDP header space exists. */
uh->len = htons(up->len);
uh->check = 0;
- if (up->pcflag) /* UDP-Lite */
+ if (is_udplite) /* UDP-Lite */
csum = udplite_csum_outgoing(sk, skb);
else if (sk->sk_no_check == UDP_CSUM_NOXMIT) { /* UDP csum disabled */
up->len = 0;
up->pending = 0;
if (!err)
- UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, up->pcflag);
+ UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite);
return err;
}
__be32 daddr, faddr, saddr;
__be16 dport;
u8 tos;
- int err, is_udplite = up->pcflag;
+ int err, is_udplite = IS_UDPLITE(sk);
int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
struct sk_buff *skb;
unsigned int ulen, copied;
+ int peeked;
int err;
int is_udplite = IS_UDPLITE(sk);
return ip_recv_error(sk, msg, len);
try_again:
- skb = skb_recv_datagram(sk, flags, noblock, &err);
+ skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
+ &peeked, &err);
if (!skb)
goto out;
if (err)
goto out_free;
+ if (!peeked)
+ UDP_INC_STATS_USER(UDP_MIB_INDATAGRAMS, is_udplite);
+
sock_recv_timestamp(msg, sk, skb);
/* Copy the address. */
return err;
csum_copy_err:
- UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);
-
- skb_kill_datagram(sk, skb, flags);
+ if (!skb_kill_datagram(sk, skb, flags))
+ UDP_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite);
if (noblock)
return -EAGAIN;
{
struct udp_sock *up = udp_sk(sk);
int rc;
+ int is_udplite = IS_UDPLITE(sk);
/*
* Charge it to the socket, dropping if the queue is full.
ret = (*up->encap_rcv)(sk, skb);
if (ret <= 0) {
- UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag);
+ UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS,
+ is_udplite);
return -ret;
}
}
/*
* UDP-Lite specific tests, ignored on UDP sockets
*/
- if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) {
+ if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) {
/*
* MIB statistics other than incrementing the error count are
if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) {
/* Note that an ENOMEM error is charged twice */
if (rc == -ENOMEM)
- UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, up->pcflag);
+ UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, is_udplite);
goto drop;
}
- UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag);
return 0;
drop:
- UDP_INC_STATS_BH(UDP_MIB_INERRORS, up->pcflag);
+ UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);
kfree_skb(skb);
return -1;
}
return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable);
sk = __udp4_lib_lookup(saddr, uh->source, daddr, uh->dest,
- skb->dev->ifindex, udptable );
+ inet_iif(skb), udptable);
if (sk != NULL) {
int ret = udp_queue_rcv_skb(sk, skb);
struct udp_sock *up = udp_sk(sk);
int val;
int err = 0;
+ int is_udplite = IS_UDPLITE(sk);
if (optlen<sizeof(int))
return -EINVAL;
/* The sender sets actual checksum coverage length via this option.
* The case coverage > packet length is handled by send module. */
case UDPLITE_SEND_CSCOV:
- if (!up->pcflag) /* Disable the option on UDP sockets */
+ if (!is_udplite) /* Disable the option on UDP sockets */
return -ENOPROTOOPT;
if (val != 0 && val < 8) /* Illegal coverage: use default (8) */
val = 8;
* sense, this should be set to at least 8 (as done below). If zero is
* used, this again means full checksum coverage. */
case UDPLITE_RECV_CSCOV:
- if (!up->pcflag) /* Disable the option on UDP sockets */
+ if (!is_udplite) /* Disable the option on UDP sockets */
return -ENOPROTOOPT;
if (val != 0 && val < 8) /* Avoid silly minimal values. */
val = 8;
}
+DEFINE_PROTO_INUSE(udp)
+
struct proto udp_prot = {
.name = "UDP",
.owner = THIS_MODULE,
.compat_setsockopt = compat_udp_setsockopt,
.compat_getsockopt = compat_udp_getsockopt,
#endif
+ REF_PROTO_INUSE(udp)
};
/* ------------------------------------------------------------------------ */
afinfo->seq_fops->llseek = seq_lseek;
afinfo->seq_fops->release = seq_release_private;
- p = proc_net_fops_create(afinfo->name, S_IRUGO, afinfo->seq_fops);
+ p = proc_net_fops_create(&init_net, afinfo->name, S_IRUGO, afinfo->seq_fops);
if (p)
p->data = afinfo;
else
{
if (!afinfo)
return;
- proc_net_remove(afinfo->name);
+ proc_net_remove(&init_net, afinfo->name);
memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops));
}