*
* The User Datagram Protocol (UDP).
*
- * Version: $Id: udp.c,v 1.102 2002/02/01 22:01:04 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
- * Alan Cox, <Alan.Cox@linux.org>
+ * Alan Cox, <alan@lxorguk.ukuu.org.uk>
* Hirokazu Takahashi, <taka@valinux.co.jp>
*
* Fixes:
* Alexey Kuznetsov: allow both IPv4 and IPv6 sockets to bind
* a single port at the same time.
* Derek Atkins <derek@ihtfp.com>: Add Encapulation Support
+ * James Chapman : Add L2TP encapsulation type.
*
*
* This program is free software; you can redistribute it and/or
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
+#include <linux/bootmem.h>
+#include <linux/highmem.h>
+#include <linux/swap.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/module.h>
#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>
#include <net/xfrm.h>
#include "udp_impl.h"
-/*
- * Snmp MIB for the UDP layer
- */
+struct udp_table udp_table;
+EXPORT_SYMBOL(udp_table);
-DEFINE_SNMP_STAT(struct udp_mib, udp_statistics) __read_mostly;
+int sysctl_udp_mem[3] __read_mostly;
+int sysctl_udp_rmem_min __read_mostly;
+int sysctl_udp_wmem_min __read_mostly;
-struct hlist_head udp_hash[UDP_HTABLE_SIZE];
-DEFINE_RWLOCK(udp_hash_lock);
+EXPORT_SYMBOL(sysctl_udp_mem);
+EXPORT_SYMBOL(sysctl_udp_rmem_min);
+EXPORT_SYMBOL(sysctl_udp_wmem_min);
-static int udp_port_rover;
+atomic_t udp_memory_allocated;
+EXPORT_SYMBOL(udp_memory_allocated);
-/*
- * Note about this hash function :
- * Typical use is probably daddr = 0, only dport is going to vary hash
- */
-static inline unsigned int hash_port_and_addr(__u16 port, __be32 addr)
-{
- addr ^= addr >> 16;
- addr ^= addr >> 8;
- return port ^ addr;
-}
+#define PORTS_PER_CHAIN (65536 / UDP_HTABLE_SIZE)
-static inline int __udp_lib_port_inuse(unsigned int hash, int port,
- __be32 daddr, struct hlist_head udptable[])
+static int udp_lib_lport_inuse(struct net *net, __u16 num,
+ const struct udp_hslot *hslot,
+ unsigned long *bitmap,
+ struct sock *sk,
+ int (*saddr_comp)(const struct sock *sk1,
+ const struct sock *sk2))
{
- struct sock *sk;
- struct hlist_node *node;
- struct inet_sock *inet;
-
- sk_for_each(sk, node, &udptable[hash & (UDP_HTABLE_SIZE - 1)]) {
- if (sk->sk_hash != hash)
- continue;
- inet = inet_sk(sk);
- if (inet->num != port)
- continue;
- if (inet->rcv_saddr == daddr)
- return 1;
- }
+ struct sock *sk2;
+ struct hlist_nulls_node *node;
+
+ sk_nulls_for_each(sk2, node, &hslot->head)
+ if (net_eq(sock_net(sk2), net) &&
+ sk2 != sk &&
+ (bitmap || sk2->sk_hash == num) &&
+ (!sk2->sk_reuse || !sk->sk_reuse) &&
+ (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
+ || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
+ (*saddr_comp)(sk, sk2)) {
+ if (bitmap)
+ __set_bit(sk2->sk_hash / UDP_HTABLE_SIZE,
+ bitmap);
+ else
+ return 1;
+ }
return 0;
}
/**
- * __udp_lib_get_port - UDP/-Lite port lookup for IPv4 and IPv6
+ * udp_lib_get_port - UDP/-Lite port lookup for IPv4 and IPv6
*
* @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,
+int udp_lib_get_port(struct sock *sk, unsigned short snum,
int (*saddr_comp)(const struct sock *sk1,
const struct sock *sk2 ) )
{
- struct hlist_node *node;
- struct hlist_head *head;
- struct sock *sk2;
- unsigned int hash;
+ struct udp_hslot *hslot;
+ struct udp_table *udptable = sk->sk_prot->h.udp_table;
int error = 1;
+ struct net *net = sock_net(sk);
- 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;
-
- hash = hash_port_and_addr(result,
- inet_sk(sk)->rcv_saddr);
- head = &udptable[hash & (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));
- 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;
- next:
- ;
- }
- 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));
- hash = hash_port_and_addr(result,
- inet_sk(sk)->rcv_saddr);
- if (! __udp_lib_port_inuse(hash, result,
- inet_sk(sk)->rcv_saddr, udptable))
- break;
+ if (!snum) {
+ int low, high, remaining;
+ unsigned rand;
+ unsigned short first, last;
+ DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);
+
+ inet_get_local_port_range(&low, &high);
+ remaining = (high - low) + 1;
+
+ rand = net_random();
+ first = (((u64)rand * remaining) >> 32) + low;
+ /*
+ * force rand to be an odd multiple of UDP_HTABLE_SIZE
+ */
+ rand = (rand | 1) * UDP_HTABLE_SIZE;
+ for (last = first + UDP_HTABLE_SIZE; first != last; first++) {
+ hslot = &udptable->hash[udp_hashfn(net, first)];
+ bitmap_zero(bitmap, PORTS_PER_CHAIN);
+ spin_lock_bh(&hslot->lock);
+ udp_lib_lport_inuse(net, snum, hslot, bitmap, sk,
+ saddr_comp);
+
+ snum = first;
+ /*
+ * Iterate on all possible values of snum for this hash.
+ * Using steps of an odd multiple of UDP_HTABLE_SIZE
+ * give us randomization and full range coverage.
+ */
+ do {
+ if (low <= snum && snum <= high &&
+ !test_bit(snum / UDP_HTABLE_SIZE, bitmap))
+ goto found;
+ snum += rand;
+ } while (snum != first);
+ spin_unlock_bh(&hslot->lock);
}
- if (i >= (1 << 16) / UDP_HTABLE_SIZE)
- goto fail;
-gotit:
- *port_rover = snum = result;
+ goto fail;
} else {
- hash = hash_port_and_addr(snum, inet_sk(sk)->rcv_saddr);
- head = &udptable[hash & (UDP_HTABLE_SIZE - 1)];
-
- sk_for_each(sk2, node, head)
- if (sk2->sk_hash == hash &&
- sk2 != sk &&
- inet_sk(sk2)->num == snum &&
- (!sk2->sk_reuse || !sk->sk_reuse) &&
- (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
- || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
- (*saddr_comp)(sk, sk2) )
- goto fail;
+ hslot = &udptable->hash[udp_hashfn(net, snum)];
+ spin_lock_bh(&hslot->lock);
+ if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, saddr_comp))
+ goto fail_unlock;
}
+found:
inet_sk(sk)->num = snum;
- sk->sk_hash = hash;
+ sk->sk_hash = snum;
if (sk_unhashed(sk)) {
- head = &udptable[hash & (UDP_HTABLE_SIZE - 1)];
- sk_add_node(sk, head);
- sock_prot_inc_use(sk->sk_prot);
+ sk_nulls_add_node_rcu(sk, &hslot->head);
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
}
error = 0;
+fail_unlock:
+ spin_unlock_bh(&hslot->lock);
fail:
- write_unlock_bh(&udp_hash_lock);
return error;
}
-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);
-}
-
-int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
+static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
{
struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);
inet1->rcv_saddr == inet2->rcv_saddr ));
}
-static inline int udp_v4_get_port(struct sock *sk, unsigned short snum)
+int udp_v4_get_port(struct sock *sk, unsigned short snum)
{
- return udp_get_port(sk, snum, ipv4_rcv_saddr_equal);
+ return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal);
}
-/* UDP is nearly always wildcards out the wazoo, it makes no sense to try
- * harder than this. -DaveM
- */
-static struct sock *__udp4_lib_lookup(__be32 saddr, __be16 sport,
- __be32 daddr, __be16 dport,
- int dif, struct hlist_head udptable[])
+static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr,
+ unsigned short hnum,
+ __be16 sport, __be32 daddr, __be16 dport, int dif)
{
- struct sock *sk, *result = NULL;
- struct hlist_node *node;
- unsigned int hash, hashwild;
- int score, best = -1, hport = ntohs(dport);
+ int score = -1;
- hash = hash_port_and_addr(hport, daddr);
- hashwild = hash_port_and_addr(hport, 0);
-
- read_lock(&udp_hash_lock);
-
-lookup:
-
- sk_for_each(sk, node, &udptable[hash & (UDP_HTABLE_SIZE - 1)]) {
+ if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum &&
+ !ipv6_only_sock(sk)) {
struct inet_sock *inet = inet_sk(sk);
- if (sk->sk_hash != hash || ipv6_only_sock(sk) ||
- inet->num != hport)
- continue;
-
score = (sk->sk_family == PF_INET ? 1 : 0);
if (inet->rcv_saddr) {
if (inet->rcv_saddr != daddr)
- continue;
- score+=2;
+ return -1;
+ score += 2;
}
if (inet->daddr) {
if (inet->daddr != saddr)
- continue;
- score+=2;
+ return -1;
+ score += 2;
}
if (inet->dport) {
if (inet->dport != sport)
- continue;
- score+=2;
+ return -1;
+ score += 2;
}
if (sk->sk_bound_dev_if) {
if (sk->sk_bound_dev_if != dif)
- continue;
- score+=2;
+ return -1;
+ score += 2;
}
- if (score == 9) {
- result = sk;
- goto found;
- } else if (score > best) {
+ }
+ return score;
+}
+
+/* UDP is nearly always wildcards out the wazoo, it makes no sense to try
+ * harder than this. -DaveM
+ */
+static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
+ __be16 sport, __be32 daddr, __be16 dport,
+ int dif, struct udp_table *udptable)
+{
+ struct sock *sk, *result;
+ struct hlist_nulls_node *node;
+ unsigned short hnum = ntohs(dport);
+ unsigned int hash = udp_hashfn(net, hnum);
+ struct udp_hslot *hslot = &udptable->hash[hash];
+ int score, badness;
+
+ rcu_read_lock();
+begin:
+ result = NULL;
+ badness = -1;
+ sk_nulls_for_each_rcu(sk, node, &hslot->head) {
+ score = compute_score(sk, net, saddr, hnum, sport,
+ daddr, dport, dif);
+ if (score > badness) {
result = sk;
- best = score;
+ badness = score;
}
}
-
- if (hash != hashwild) {
- hash = hashwild;
- goto lookup;
+ /*
+ * if the nulls value we got at the end of this lookup is
+ * not the expected one, we must restart lookup.
+ * We probably met an item that was moved to another chain.
+ */
+ if (get_nulls_value(node) != hash)
+ goto begin;
+
+ if (result) {
+ if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
+ result = NULL;
+ else if (unlikely(compute_score(result, net, saddr, hnum, sport,
+ daddr, dport, dif) < badness)) {
+ sock_put(result);
+ goto begin;
+ }
}
-found:
- if (result)
- sock_hold(result);
- read_unlock(&udp_hash_lock);
+ rcu_read_unlock();
return result;
}
-static inline struct sock *udp_v4_mcast_next(struct sock *sk, unsigned int hnum,
- int hport, __be32 loc_addr,
+static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
+ __be16 sport, __be16 dport,
+ struct udp_table *udptable)
+{
+ struct sock *sk;
+ const struct iphdr *iph = ip_hdr(skb);
+
+ if (unlikely(sk = skb_steal_sock(skb)))
+ return sk;
+ else
+ return __udp4_lib_lookup(dev_net(skb->dst->dev), iph->saddr, sport,
+ iph->daddr, dport, inet_iif(skb),
+ udptable);
+}
+
+struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
+ __be32 daddr, __be16 dport, int dif)
+{
+ return __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table);
+}
+EXPORT_SYMBOL_GPL(udp4_lib_lookup);
+
+static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
+ __be16 loc_port, __be32 loc_addr,
__be16 rmt_port, __be32 rmt_addr,
int dif)
{
- struct hlist_node *node;
+ struct hlist_nulls_node *node;
struct sock *s = sk;
+ unsigned short hnum = ntohs(loc_port);
- sk_for_each_from(s, node) {
+ sk_nulls_for_each_from(s, node) {
struct inet_sock *inet = inet_sk(s);
- if (s->sk_hash != hnum ||
- inet->num != hport ||
+ if (!net_eq(sock_net(s), net) ||
+ s->sk_hash != hnum ||
(inet->daddr && inet->daddr != rmt_addr) ||
(inet->dport != rmt_port && inet->dport) ||
(inet->rcv_saddr && inet->rcv_saddr != loc_addr) ||
* to find the appropriate port.
*/
-void __udp4_lib_err(struct sk_buff *skb, u32 info, struct hlist_head udptable[])
+void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
{
struct inet_sock *inet;
struct iphdr *iph = (struct iphdr*)skb->data;
struct sock *sk;
int harderr;
int err;
+ struct net *net = dev_net(skb->dev);
- sk = __udp4_lib_lookup(iph->daddr, uh->dest, iph->saddr, uh->source,
- skb->dev->ifindex, udptable );
+ sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
+ iph->saddr, uh->source, skb->dev->ifindex, udptable);
if (sk == NULL) {
- ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
+ ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
return; /* No socket for error */
}
void udp_err(struct sk_buff *skb, u32 info)
{
- return __udp4_lib_err(skb, info, udp_hash);
+ __udp4_lib_err(skb, info, &udp_table);
}
/*
* Throw away all pending data and cancel the corking. Socket is locked.
*/
-static void udp_flush_pending_frames(struct sock *sk)
+void udp_flush_pending_frames(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
ip_flush_pending_frames(sk);
}
}
+EXPORT_SYMBOL(udp_flush_pending_frames);
/**
* udp4_hwcsum_outgoing - handle outgoing HW checksumming
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 */
out:
up->len = 0;
up->pending = 0;
+ if (!err)
+ UDP_INC_STATS_USER(sock_net(sk),
+ 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 *);
return -EOPNOTSUPP;
ipc.opt = NULL;
+ ipc.shtx.flags = 0;
if (up->pending) {
/*
ipc.addr = inet->saddr;
ipc.oif = sk->sk_bound_dev_if;
+ err = sock_tx_timestamp(msg, sk, &ipc.shtx);
+ if (err)
+ return err;
if (msg->msg_controllen) {
- err = ip_cmsg_send(msg, &ipc);
+ err = ip_cmsg_send(sock_net(sk), msg, &ipc);
if (err)
return err;
if (ipc.opt)
connected = 0;
}
- if (MULTICAST(daddr)) {
+ if (ipv4_is_multicast(daddr)) {
if (!ipc.oif)
ipc.oif = inet->mc_index;
if (!saddr)
.saddr = saddr,
.tos = tos } },
.proto = sk->sk_protocol,
+ .flags = inet_sk_flowi_flags(sk),
.uli_u = { .ports =
{ .sport = inet->sport,
.dport = dport } } };
+ struct net *net = sock_net(sk);
+
security_sk_classify_flow(sk, &fl);
- err = ip_route_output_flow(&rt, &fl, sk, 1);
- if (err)
+ err = ip_route_output_flow(net, &rt, &fl, sk, 1);
+ if (err) {
+ if (err == -ENETUNREACH)
+ IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
goto out;
+ }
err = -EACCES;
if ((rt->rt_flags & RTCF_BROADCAST) &&
up->len += ulen;
getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
err = ip_append_data(sk, getfrag, msg->msg_iov, ulen,
- sizeof(struct udphdr), &ipc, rt,
+ sizeof(struct udphdr), &ipc, &rt,
corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
if (err)
udp_flush_pending_frames(sk);
ip_rt_put(rt);
if (free)
kfree(ipc.opt);
- if (!err) {
- UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite);
+ if (!err)
return len;
- }
/*
* ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting
* ENOBUFS might not be good (it's not tunable per se), but otherwise
* seems like overkill.
*/
if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
- UDP_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite);
+ UDP_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_SNDBUFERRORS, is_udplite);
}
return err;
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(sock_net(sk),
+ UDP_MIB_INDATAGRAMS, is_udplite);
+
sock_recv_timestamp(msg, sk, skb);
/* Copy the address. */
err = ulen;
out_free:
+ lock_sock(sk);
skb_free_datagram(sk, skb);
+ release_sock(sk);
out:
return err;
csum_copy_err:
- UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);
-
- skb_kill_datagram(sk, skb, flags);
+ lock_sock(sk);
+ if (!skb_kill_datagram(sk, skb, flags))
+ UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
+ release_sock(sk);
if (noblock)
return -EAGAIN;
return 0;
}
-/* return:
- * 1 if the the UDP system should process it
- * 0 if we should drop this packet
- * -1 if it should get processed by xfrm4_rcv_encap
- */
-static int udp_encap_rcv(struct sock * sk, struct sk_buff *skb)
+void udp_lib_unhash(struct sock *sk)
{
-#ifndef CONFIG_XFRM
- return 1;
-#else
- struct udp_sock *up = udp_sk(sk);
- struct udphdr *uh;
- struct iphdr *iph;
- int iphlen, len;
-
- __u8 *udpdata;
- __be32 *udpdata32;
- __u16 encap_type = up->encap_type;
-
- /* if we're overly short, let UDP handle it */
- len = skb->len - sizeof(struct udphdr);
- if (len <= 0)
- return 1;
-
- /* if this is not encapsulated socket, then just return now */
- if (!encap_type)
- return 1;
-
- /* If this is a paged skb, make sure we pull up
- * whatever data we need to look at. */
- if (!pskb_may_pull(skb, sizeof(struct udphdr) + min(len, 8)))
- return 1;
-
- /* Now we can get the pointers */
- uh = udp_hdr(skb);
- udpdata = (__u8 *)uh + sizeof(struct udphdr);
- udpdata32 = (__be32 *)udpdata;
-
- switch (encap_type) {
- default:
- case UDP_ENCAP_ESPINUDP:
- /* Check if this is a keepalive packet. If so, eat it. */
- if (len == 1 && udpdata[0] == 0xff) {
- return 0;
- } else if (len > sizeof(struct ip_esp_hdr) && udpdata32[0] != 0) {
- /* ESP Packet without Non-ESP header */
- len = sizeof(struct udphdr);
- } else
- /* Must be an IKE packet.. pass it through */
- return 1;
- break;
- case UDP_ENCAP_ESPINUDP_NON_IKE:
- /* Check if this is a keepalive packet. If so, eat it. */
- if (len == 1 && udpdata[0] == 0xff) {
- return 0;
- } else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) &&
- udpdata32[0] == 0 && udpdata32[1] == 0) {
-
- /* ESP Packet with Non-IKE marker */
- len = sizeof(struct udphdr) + 2 * sizeof(u32);
- } else
- /* Must be an IKE packet.. pass it through */
- return 1;
- break;
+ if (sk_hashed(sk)) {
+ struct udp_table *udptable = sk->sk_prot->h.udp_table;
+ unsigned int hash = udp_hashfn(sock_net(sk), sk->sk_hash);
+ struct udp_hslot *hslot = &udptable->hash[hash];
+
+ spin_lock_bh(&hslot->lock);
+ if (sk_nulls_del_node_init_rcu(sk)) {
+ inet_sk(sk)->num = 0;
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+ }
+ spin_unlock_bh(&hslot->lock);
}
+}
+EXPORT_SYMBOL(udp_lib_unhash);
- /* At this point we are sure that this is an ESPinUDP packet,
- * so we need to remove 'len' bytes from the packet (the UDP
- * header and optional ESP marker bytes) and then modify the
- * protocol to ESP, and then call into the transform receiver.
- */
- if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
- return 0;
+static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ int is_udplite = IS_UDPLITE(sk);
+ int rc;
- /* Now we can update and verify the packet length... */
- iph = ip_hdr(skb);
- iphlen = iph->ihl << 2;
- iph->tot_len = htons(ntohs(iph->tot_len) - len);
- if (skb->len < iphlen + len) {
- /* packet is too small!?! */
- return 0;
+ if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) {
+ /* Note that an ENOMEM error is charged twice */
+ if (rc == -ENOMEM) {
+ UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
+ is_udplite);
+ atomic_inc(&sk->sk_drops);
+ }
+ goto drop;
}
- /* pull the data buffer up to the ESP header and set the
- * transport header to point to ESP. Keep UDP on the stack
- * for later.
- */
- __skb_pull(skb, len);
- skb_reset_transport_header(skb);
-
- /* modify the protocol (it's ESP!) */
- iph->protocol = IPPROTO_ESP;
+ return 0;
- /* and let the caller know to send this into the ESP processor... */
+drop:
+ UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
+ kfree_skb(skb);
return -1;
-#endif
}
/* returns:
{
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.
if (up->encap_type) {
/*
- * This is an encapsulation socket, so let's see if this is
- * an encapsulated packet.
- * If it's a keepalive packet, then just eat it.
- * If it's an encapsulateed packet, then pass it to the
- * IPsec xfrm input and return the response
- * appropriately. Otherwise, just fall through and
- * pass this up the UDP socket.
+ * This is an encapsulation socket so pass the skb to
+ * the socket's udp_encap_rcv() hook. Otherwise, just
+ * fall through and pass this up the UDP socket.
+ * up->encap_rcv() returns the following value:
+ * =0 if skb was successfully passed to the encap
+ * handler or was discarded by it.
+ * >0 if skb should be passed on to UDP.
+ * <0 if skb should be resubmitted as proto -N
*/
- int ret;
- ret = udp_encap_rcv(sk, skb);
- if (ret == 0) {
- /* Eat the packet .. */
- kfree_skb(skb);
- return 0;
- }
- if (ret < 0) {
- /* process the ESP packet */
- ret = xfrm4_rcv_encap(skb, up->encap_type);
- UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag);
- return -ret;
+ /* if we're overly short, let UDP handle it */
+ if (skb->len > sizeof(struct udphdr) &&
+ up->encap_rcv != NULL) {
+ int ret;
+
+ ret = (*up->encap_rcv)(sk, skb);
+ if (ret <= 0) {
+ UDP_INC_STATS_BH(sock_net(sk),
+ UDP_MIB_INDATAGRAMS,
+ is_udplite);
+ return -ret;
+ }
}
+
/* FALLTHROUGH -- it's a UDP Packet */
}
/*
* 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
goto drop;
}
- 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);
- goto drop;
- }
+ rc = 0;
- UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag);
- return 0;
+ bh_lock_sock(sk);
+ if (!sock_owned_by_user(sk))
+ rc = __udp_queue_rcv_skb(sk, skb);
+ else
+ sk_add_backlog(sk, skb);
+ bh_unlock_sock(sk);
+
+ return rc;
drop:
- UDP_INC_STATS_BH(UDP_MIB_INERRORS, up->pcflag);
+ UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
kfree_skb(skb);
return -1;
}
* Note: called only from the BH handler context,
* so we don't need to lock the hashes.
*/
-static int __udp4_lib_mcast_deliver(struct sk_buff *skb,
+static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
struct udphdr *uh,
__be32 saddr, __be32 daddr,
- struct hlist_head udptable[])
+ struct udp_table *udptable)
{
- struct sock *sk, *skw, *sknext;
+ struct sock *sk;
+ struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))];
int dif;
- int hport = ntohs(uh->dest);
- unsigned int hash = hash_port_and_addr(hport, daddr);
- unsigned int hashwild = hash_port_and_addr(hport, 0);
+ spin_lock(&hslot->lock);
+ sk = sk_nulls_head(&hslot->head);
dif = skb->dev->ifindex;
-
- read_lock(&udp_hash_lock);
-
- sk = sk_head(&udptable[hash & (UDP_HTABLE_SIZE - 1)]);
- skw = sk_head(&udptable[hashwild & (UDP_HTABLE_SIZE - 1)]);
-
- sk = udp_v4_mcast_next(sk, hash, hport, daddr, uh->source, saddr, dif);
- if (!sk) {
- hash = hashwild;
- sk = udp_v4_mcast_next(skw, hash, hport, daddr, uh->source,
- saddr, dif);
- }
+ sk = udp_v4_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif);
if (sk) {
+ struct sock *sknext = NULL;
+
do {
struct sk_buff *skb1 = skb;
- sknext = udp_v4_mcast_next(sk_next(sk), hash, hport,
- daddr, uh->source, saddr, dif);
- if (!sknext && hash != hashwild) {
- hash = hashwild;
- sknext = udp_v4_mcast_next(skw, hash, hport,
- daddr, uh->source, saddr, dif);
- }
+
+ sknext = udp_v4_mcast_next(net, sk_nulls_next(sk), uh->dest,
+ daddr, uh->source, saddr,
+ dif);
if (sknext)
skb1 = skb_clone(skb, GFP_ATOMIC);
if (skb1) {
int ret = udp_queue_rcv_skb(sk, skb1);
if (ret > 0)
- /*
- * we should probably re-process
- * instead of dropping packets here.
- */
+ /* we should probably re-process instead
+ * of dropping packets here. */
kfree_skb(skb1);
}
sk = sknext;
} while (sknext);
} else
kfree_skb(skb);
- read_unlock(&udp_hash_lock);
+ spin_unlock(&hslot->lock);
return 0;
}
* All we need to do is get the socket, and then do a checksum.
*/
-int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
+int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
int proto)
{
struct sock *sk;
- struct udphdr *uh = udp_hdr(skb);
+ struct udphdr *uh;
unsigned short ulen;
struct rtable *rt = (struct rtable*)skb->dst;
- __be32 saddr = ip_hdr(skb)->saddr;
- __be32 daddr = ip_hdr(skb)->daddr;
+ __be32 saddr, daddr;
+ struct net *net = dev_net(skb->dev);
/*
* Validate the packet.
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto drop; /* No space for header. */
+ uh = udp_hdr(skb);
ulen = ntohs(uh->len);
if (ulen > skb->len)
goto short_packet;
if (udp4_csum_init(skb, uh, proto))
goto csum_error;
+ saddr = ip_hdr(skb)->saddr;
+ daddr = ip_hdr(skb)->daddr;
+
if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
- return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable);
+ return __udp4_lib_mcast_deliver(net, skb, uh,
+ saddr, daddr, udptable);
- sk = __udp4_lib_lookup(saddr, uh->source, daddr, uh->dest,
- skb->dev->ifindex, udptable);
+ sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
if (sk != NULL) {
int ret = udp_queue_rcv_skb(sk, skb);
if (udp_lib_checksum_complete(skb))
goto csum_error;
- UDP_INC_STATS_BH(UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
+ UDP_INC_STATS_BH(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
/*
return 0;
short_packet:
- LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %u.%u.%u.%u:%u %d/%d to %u.%u.%u.%u:%u\n",
+ LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n",
proto == IPPROTO_UDPLITE ? "-Lite" : "",
- NIPQUAD(saddr),
+ &saddr,
ntohs(uh->source),
ulen,
skb->len,
- NIPQUAD(daddr),
+ &daddr,
ntohs(uh->dest));
goto drop;
* RFC1122: OK. Discards the bad packet silently (as far as
* the network is concerned, anyway) as per 4.1.3.4 (MUST).
*/
- LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %d.%d.%d.%d:%d to %d.%d.%d.%d:%d ulen %d\n",
+ LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n",
proto == IPPROTO_UDPLITE ? "-Lite" : "",
- NIPQUAD(saddr),
+ &saddr,
ntohs(uh->source),
- NIPQUAD(daddr),
+ &daddr,
ntohs(uh->dest),
ulen);
drop:
- UDP_INC_STATS_BH(UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
+ UDP_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
kfree_skb(skb);
return 0;
}
int udp_rcv(struct sk_buff *skb)
{
- return __udp4_lib_rcv(skb, udp_hash, IPPROTO_UDP);
+ return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP);
}
-int udp_destroy_sock(struct sock *sk)
+void udp_destroy_sock(struct sock *sk)
{
lock_sock(sk);
udp_flush_pending_frames(sk);
release_sock(sk);
- return 0;
}
/*
struct udp_sock *up = udp_sk(sk);
int val;
int err = 0;
+ int is_udplite = IS_UDPLITE(sk);
if (optlen<sizeof(int))
return -EINVAL;
case 0:
case UDP_ENCAP_ESPINUDP:
case UDP_ENCAP_ESPINUDP_NON_IKE:
+ up->encap_rcv = xfrm4_udp_encap_rcv;
+ /* FALLTHROUGH */
+ case UDP_ENCAP_L2TPINUDP:
up->encap_type = val;
break;
default:
/* 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;
+ else if (val > USHORT_MAX)
+ val = USHORT_MAX;
up->pcslen = val;
up->pcflag |= UDPLITE_SEND_CC;
break;
* 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;
+ else if (val > USHORT_MAX)
+ val = USHORT_MAX;
up->pcrlen = val;
up->pcflag |= UDPLITE_RECV_CC;
break;
spin_lock_bh(&rcvq->lock);
while ((skb = skb_peek(rcvq)) != NULL &&
udp_lib_checksum_complete(skb)) {
- UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_lite);
+ UDP_INC_STATS_BH(sock_net(sk),
+ UDP_MIB_INERRORS, is_lite);
__skb_unlink(skb, rcvq);
kfree_skb(skb);
}
.sendmsg = udp_sendmsg,
.recvmsg = udp_recvmsg,
.sendpage = udp_sendpage,
- .backlog_rcv = udp_queue_rcv_skb,
+ .backlog_rcv = __udp_queue_rcv_skb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
.get_port = udp_v4_get_port,
+ .memory_allocated = &udp_memory_allocated,
+ .sysctl_mem = sysctl_udp_mem,
+ .sysctl_wmem = &sysctl_udp_wmem_min,
+ .sysctl_rmem = &sysctl_udp_rmem_min,
.obj_size = sizeof(struct udp_sock),
+ .slab_flags = SLAB_DESTROY_BY_RCU,
+ .h.udp_table = &udp_table,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udp_setsockopt,
.compat_getsockopt = compat_udp_getsockopt,
/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS
-static struct sock *udp_get_first(struct seq_file *seq)
+static struct sock *udp_get_first(struct seq_file *seq, int start)
{
struct sock *sk;
struct udp_iter_state *state = seq->private;
-
- for (state->bucket = 0; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) {
- struct hlist_node *node;
- sk_for_each(sk, node, state->hashtable + state->bucket) {
+ struct net *net = seq_file_net(seq);
+
+ for (state->bucket = start; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) {
+ struct hlist_nulls_node *node;
+ struct udp_hslot *hslot = &state->udp_table->hash[state->bucket];
+ spin_lock_bh(&hslot->lock);
+ sk_nulls_for_each(sk, node, &hslot->head) {
+ if (!net_eq(sock_net(sk), net))
+ continue;
if (sk->sk_family == state->family)
goto found;
}
+ spin_unlock_bh(&hslot->lock);
}
sk = NULL;
found:
static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
{
struct udp_iter_state *state = seq->private;
+ struct net *net = seq_file_net(seq);
do {
- sk = sk_next(sk);
-try_again:
- ;
- } while (sk && sk->sk_family != state->family);
+ sk = sk_nulls_next(sk);
+ } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family));
- if (!sk && ++state->bucket < UDP_HTABLE_SIZE) {
- sk = sk_head(state->hashtable + state->bucket);
- goto try_again;
+ if (!sk) {
+ spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
+ return udp_get_first(seq, state->bucket + 1);
}
return sk;
}
static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos)
{
- struct sock *sk = udp_get_first(seq);
+ struct sock *sk = udp_get_first(seq, 0);
if (sk)
while (pos && (sk = udp_get_next(seq, sk)) != NULL)
static void *udp_seq_start(struct seq_file *seq, loff_t *pos)
{
- read_lock(&udp_hash_lock);
- return *pos ? udp_get_idx(seq, *pos-1) : (void *)1;
+ return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
}
static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct sock *sk;
- if (v == (void *)1)
+ if (v == SEQ_START_TOKEN)
sk = udp_get_idx(seq, 0);
else
sk = udp_get_next(seq, v);
static void udp_seq_stop(struct seq_file *seq, void *v)
{
- read_unlock(&udp_hash_lock);
+ struct udp_iter_state *state = seq->private;
+
+ if (state->bucket < UDP_HTABLE_SIZE)
+ spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
}
static int udp_seq_open(struct inode *inode, struct file *file)
{
struct udp_seq_afinfo *afinfo = PDE(inode)->data;
- struct seq_file *seq;
- int rc = -ENOMEM;
- struct udp_iter_state *s = kzalloc(sizeof(*s), GFP_KERNEL);
+ struct udp_iter_state *s;
+ int err;
- if (!s)
- goto out;
+ err = seq_open_net(inode, file, &afinfo->seq_ops,
+ sizeof(struct udp_iter_state));
+ if (err < 0)
+ return err;
+
+ s = ((struct seq_file *)file->private_data)->private;
s->family = afinfo->family;
- s->hashtable = afinfo->hashtable;
- s->seq_ops.start = udp_seq_start;
- s->seq_ops.next = udp_seq_next;
- s->seq_ops.show = afinfo->seq_show;
- s->seq_ops.stop = udp_seq_stop;
-
- rc = seq_open(file, &s->seq_ops);
- if (rc)
- goto out_kfree;
-
- seq = file->private_data;
- seq->private = s;
-out:
- return rc;
-out_kfree:
- kfree(s);
- goto out;
+ s->udp_table = afinfo->udp_table;
+ return err;
}
/* ------------------------------------------------------------------------ */
-int udp_proc_register(struct udp_seq_afinfo *afinfo)
+int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo)
{
struct proc_dir_entry *p;
int rc = 0;
- if (!afinfo)
- return -EINVAL;
- afinfo->seq_fops->owner = afinfo->owner;
- afinfo->seq_fops->open = udp_seq_open;
- afinfo->seq_fops->read = seq_read;
- 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);
- if (p)
- p->data = afinfo;
- else
+ afinfo->seq_fops.open = udp_seq_open;
+ afinfo->seq_fops.read = seq_read;
+ afinfo->seq_fops.llseek = seq_lseek;
+ afinfo->seq_fops.release = seq_release_net;
+
+ afinfo->seq_ops.start = udp_seq_start;
+ afinfo->seq_ops.next = udp_seq_next;
+ afinfo->seq_ops.stop = udp_seq_stop;
+
+ p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net,
+ &afinfo->seq_fops, afinfo);
+ if (!p)
rc = -ENOMEM;
return rc;
}
-void udp_proc_unregister(struct udp_seq_afinfo *afinfo)
+void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo)
{
- if (!afinfo)
- return;
- proc_net_remove(afinfo->name);
- memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops));
+ proc_net_remove(net, afinfo->name);
}
/* ------------------------------------------------------------------------ */
-static void udp4_format_sock(struct sock *sp, char *tmpbuf, int bucket)
+static void udp4_format_sock(struct sock *sp, struct seq_file *f,
+ int bucket, int *len)
{
struct inet_sock *inet = inet_sk(sp);
__be32 dest = inet->daddr;
__u16 destp = ntohs(inet->dport);
__u16 srcp = ntohs(inet->sport);
- sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
- " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p",
+ seq_printf(f, "%4d: %08X:%04X %08X:%04X"
+ " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d%n",
bucket, src, srcp, dest, destp, sp->sk_state,
atomic_read(&sp->sk_wmem_alloc),
atomic_read(&sp->sk_rmem_alloc),
0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp),
- atomic_read(&sp->sk_refcnt), sp);
+ atomic_read(&sp->sk_refcnt), sp,
+ atomic_read(&sp->sk_drops), len);
}
int udp4_seq_show(struct seq_file *seq, void *v)
seq_printf(seq, "%-127s\n",
" sl local_address rem_address st tx_queue "
"rx_queue tr tm->when retrnsmt uid timeout "
- "inode");
+ "inode ref pointer drops");
else {
- char tmpbuf[129];
struct udp_iter_state *state = seq->private;
+ int len;
- udp4_format_sock(v, tmpbuf, state->bucket);
- seq_printf(seq, "%-127s\n", tmpbuf);
+ udp4_format_sock(v, seq, state->bucket, &len);
+ seq_printf(seq, "%*s\n", 127 - len ,"");
}
return 0;
}
/* ------------------------------------------------------------------------ */
-static struct file_operations udp4_seq_fops;
static struct udp_seq_afinfo udp4_seq_afinfo = {
- .owner = THIS_MODULE,
.name = "udp",
.family = AF_INET,
- .hashtable = udp_hash,
- .seq_show = udp4_seq_show,
- .seq_fops = &udp4_seq_fops,
+ .udp_table = &udp_table,
+ .seq_fops = {
+ .owner = THIS_MODULE,
+ },
+ .seq_ops = {
+ .show = udp4_seq_show,
+ },
+};
+
+static int udp4_proc_init_net(struct net *net)
+{
+ return udp_proc_register(net, &udp4_seq_afinfo);
+}
+
+static void udp4_proc_exit_net(struct net *net)
+{
+ udp_proc_unregister(net, &udp4_seq_afinfo);
+}
+
+static struct pernet_operations udp4_net_ops = {
+ .init = udp4_proc_init_net,
+ .exit = udp4_proc_exit_net,
};
int __init udp4_proc_init(void)
{
- return udp_proc_register(&udp4_seq_afinfo);
+ return register_pernet_subsys(&udp4_net_ops);
}
void udp4_proc_exit(void)
{
- udp_proc_unregister(&udp4_seq_afinfo);
+ unregister_pernet_subsys(&udp4_net_ops);
}
#endif /* CONFIG_PROC_FS */
+void __init udp_table_init(struct udp_table *table)
+{
+ int i;
+
+ for (i = 0; i < UDP_HTABLE_SIZE; i++) {
+ INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i);
+ spin_lock_init(&table->hash[i].lock);
+ }
+}
+
+void __init udp_init(void)
+{
+ unsigned long nr_pages, limit;
+
+ udp_table_init(&udp_table);
+ /* Set the pressure threshold up by the same strategy of TCP. It is a
+ * fraction of global memory that is up to 1/2 at 256 MB, decreasing
+ * toward zero with the amount of memory, with a floor of 128 pages.
+ */
+ nr_pages = totalram_pages - totalhigh_pages;
+ limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT);
+ limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11);
+ limit = max(limit, 128UL);
+ sysctl_udp_mem[0] = limit / 4 * 3;
+ sysctl_udp_mem[1] = limit;
+ sysctl_udp_mem[2] = sysctl_udp_mem[0] * 2;
+
+ sysctl_udp_rmem_min = SK_MEM_QUANTUM;
+ sysctl_udp_wmem_min = SK_MEM_QUANTUM;
+}
+
EXPORT_SYMBOL(udp_disconnect);
-EXPORT_SYMBOL(udp_hash);
-EXPORT_SYMBOL(udp_hash_lock);
EXPORT_SYMBOL(udp_ioctl);
-EXPORT_SYMBOL(udp_get_port);
EXPORT_SYMBOL(udp_prot);
EXPORT_SYMBOL(udp_sendmsg);
EXPORT_SYMBOL(udp_lib_getsockopt);
EXPORT_SYMBOL(udp_lib_setsockopt);
EXPORT_SYMBOL(udp_poll);
+EXPORT_SYMBOL(udp_lib_get_port);
#ifdef CONFIG_PROC_FS
EXPORT_SYMBOL(udp_proc_register);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff