* for udp at least is 'valid'.
* Alan Cox : Fixed icmp handling properly
* Alan Cox : Correct error for oversized datagrams
- * Alan Cox : Tidied select() semantics.
- * Alan Cox : udp_err() fixed properly, also now
+ * Alan Cox : Tidied select() semantics.
+ * Alan Cox : udp_err() fixed properly, also now
* select and read wake correctly on errors
* Alan Cox : udp_send verify_area moved to avoid mem leak
* Alan Cox : UDP can count its memory
* does have a high hit rate.
* Olaf Kirch : Don't linearise iovec on sendmsg.
* Andi Kleen : Some cleanups, cache destination entry
- * for connect.
+ * for connect.
* Vitaly E. Lavrov : Transparent proxy revived after year coma.
* Melvin Smith : Check msg_name not msg_namelen in sendto(),
* return ENOTCONN for unconnected sockets (POSIX)
* 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
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
-
+
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
+#include <linux/bootmem.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>
*/
DEFINE_SNMP_STAT(struct udp_mib, udp_statistics) __read_mostly;
+EXPORT_SYMBOL(udp_statistics);
+
+DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6) __read_mostly;
+EXPORT_SYMBOL(udp_stats_in6);
struct hlist_head udp_hash[UDP_HTABLE_SIZE];
DEFINE_RWLOCK(udp_hash_lock);
-static int udp_port_rover;
+int sysctl_udp_mem[3] __read_mostly;
+int sysctl_udp_rmem_min __read_mostly;
+int sysctl_udp_wmem_min __read_mostly;
+
+EXPORT_SYMBOL(sysctl_udp_mem);
+EXPORT_SYMBOL(sysctl_udp_rmem_min);
+EXPORT_SYMBOL(sysctl_udp_wmem_min);
+
+atomic_t udp_memory_allocated;
+EXPORT_SYMBOL(udp_memory_allocated);
-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_for_each(sk, node, &udptable[num & (UDP_HTABLE_SIZE - 1)])
- if (inet_sk(sk)->num == num)
+ if (sk->sk_hash == num)
return 1;
return 0;
}
* @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;
+
+ sk_for_each(sk2, node, head) {
+ if (++size >= best_size_so_far)
+ goto next;
}
- size = 0;
- sk_for_each(sk2, node, head)
- if (++size < best_size_so_far) {
- best_size_so_far = size;
- best = result;
- }
+ best_size_so_far = size;
+ 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)];
sk_for_each(sk2, node, head)
- if (inet_sk(sk2)->num == snum &&
+ if (sk2->sk_hash == snum &&
sk2 != sk &&
(!sk2->sk_reuse || !sk->sk_reuse) &&
(!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
(*saddr_comp)(sk, sk2) )
goto fail;
}
+
inet_sk(sk)->num = snum;
+ sk->sk_hash = snum;
if (sk_unhashed(sk)) {
head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
sk_add_node(sk, head);
return error;
}
-__inline__ int udp_get_port(struct sock *sk, unsigned short snum,
+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);
}
-inline int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
+int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
{
struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);
sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) {
struct inet_sock *inet = inet_sk(sk);
- if (inet->num == hnum && !ipv6_only_sock(sk)) {
+ if (sk->sk_hash == hnum && !ipv6_only_sock(sk)) {
int score = (sk->sk_family == PF_INET ? 1 : 0);
if (inet->rcv_saddr) {
if (inet->rcv_saddr != daddr)
continue;
score+=2;
}
- if(score == 9) {
+ if (score == 9) {
result = sk;
break;
- } else if(score > badness) {
+ } else if (score > badness) {
result = sk;
badness = score;
}
sk_for_each_from(s, node) {
struct inet_sock *inet = inet_sk(s);
- if (inet->num != hnum ||
+ if (s->sk_hash != hnum ||
(inet->daddr && inet->daddr != rmt_addr) ||
(inet->dport != rmt_port && inet->dport) ||
(inet->rcv_saddr && inet->rcv_saddr != loc_addr) ||
if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif))
continue;
goto found;
- }
+ }
s = NULL;
found:
- return s;
+ return s;
}
/*
* This routine is called by the ICMP module when it gets some
* sort of error condition. If err < 0 then the socket should
* be closed and the error returned to the user. If err > 0
- * it's just the icmp type << 8 | icmp code.
+ * it's just the icmp type << 8 | icmp code.
* Header points to the ip header of the error packet. We move
* on past this. Then (as it used to claim before adjustment)
* header points to the first 8 bytes of the udp header. We need
struct inet_sock *inet;
struct iphdr *iph = (struct iphdr*)skb->data;
struct udphdr *uh = (struct udphdr*)(skb->data+(iph->ihl<<2));
- int type = skb->h.icmph->type;
- int code = skb->h.icmph->code;
+ const int type = icmp_hdr(skb)->type;
+ const int code = icmp_hdr(skb)->code;
struct sock *sk;
int harderr;
int err;
skb->dev->ifindex, udptable );
if (sk == NULL) {
ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
- return; /* No socket for error */
+ return; /* No socket for error */
}
err = 0;
}
/*
- * RFC1122: OK. Passes ICMP errors back to application, as per
+ * RFC1122: OK. Passes ICMP errors back to application, as per
* 4.1.3.3.
*/
if (!inet->recverr) {
sock_put(sk);
}
-__inline__ void udp_err(struct sk_buff *skb, u32 info)
+void udp_err(struct sk_buff *skb, u32 info)
{
return __udp4_lib_err(skb, info, udp_hash);
}
__be32 src, __be32 dst, int len )
{
unsigned int offset;
- struct udphdr *uh = skb->h.uh;
+ struct udphdr *uh = udp_hdr(skb);
__wsum csum = 0;
if (skb_queue_len(&sk->sk_write_queue) == 1) {
/*
* Only one fragment on the socket.
*/
+ skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct udphdr, check);
uh->check = ~csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, 0);
} else {
* fragments on the socket so that all csums of sk_buffs
* should be together
*/
- offset = skb->h.raw - skb->data;
+ offset = skb_transport_offset(skb);
skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
skb->ip_summed = CHECKSUM_NONE;
/*
* Push out all pending data as one UDP datagram. Socket is locked.
*/
-static int udp_push_pending_frames(struct sock *sk, struct udp_sock *up)
+static int udp_push_pending_frames(struct sock *sk)
{
+ struct udp_sock *up = udp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
struct flowi *fl = &inet->cork.fl;
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. */
/*
* Create a UDP header
*/
- uh = skb->h.uh;
+ uh = udp_hdr(skb);
uh->source = fl->fl_ip_sport;
uh->dest = fl->fl_ip_dport;
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(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 *);
if (len > 0xFFFF)
return -EMSGSIZE;
- /*
+ /*
* Check the flags.
*/
if (up->pending) {
/*
* There are pending frames.
- * The socket lock must be held while it's corked.
+ * The socket lock must be held while it's corked.
*/
lock_sock(sk);
if (likely(up->pending)) {
release_sock(sk);
return -EINVAL;
}
- goto do_append_data;
+ goto do_append_data;
}
release_sock(sk);
}
ulen += sizeof(struct udphdr);
/*
- * Get and verify the address.
+ * Get and verify the address.
*/
if (msg->msg_name) {
struct sockaddr_in * usin = (struct sockaddr_in*)msg->msg_name;
Route will not be used, if at least one option is set.
*/
connected = 1;
- }
+ }
ipc.addr = inet->saddr;
ipc.oif = sk->sk_bound_dev_if;
}
tos = RT_TOS(inet->tos);
if (sock_flag(sk, SOCK_LOCALROUTE) ||
- (msg->msg_flags & MSG_DONTROUTE) ||
+ (msg->msg_flags & MSG_DONTROUTE) ||
(ipc.opt && ipc.opt->is_strictroute)) {
tos |= RTO_ONLINK;
connected = 0;
}
- if (MULTICAST(daddr)) {
+ if (ipv4_is_multicast(daddr)) {
if (!ipc.oif)
ipc.oif = inet->mc_index;
if (!saddr)
{ .sport = inet->sport,
.dport = dport } } };
security_sk_classify_flow(sk, &fl);
- err = ip_route_output_flow(&rt, &fl, sk, !(msg->msg_flags&MSG_DONTWAIT));
- if (err)
+ err = ip_route_output_flow(&rt, &fl, sk, 1);
+ if (err) {
+ if (err == -ENETUNREACH)
+ IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
goto out;
+ }
err = -EACCES;
if ((rt->rt_flags & RTCF_BROADCAST) &&
if (err)
udp_flush_pending_frames(sk);
else if (!corkreq)
- err = udp_push_pending_frames(sk, up);
+ err = udp_push_pending_frames(sk);
else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
up->pending = 0;
release_sock(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
up->len += size;
if (!(up->corkflag || (flags&MSG_MORE)))
- ret = udp_push_pending_frames(sk, up);
+ ret = udp_push_pending_frames(sk);
if (!ret)
ret = size;
out:
/*
* IOCTL requests applicable to the UDP protocol
*/
-
+
int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
- switch(cmd)
+ switch (cmd) {
+ case SIOCOUTQ:
{
- case SIOCOUTQ:
- {
- int amount = atomic_read(&sk->sk_wmem_alloc);
- return put_user(amount, (int __user *)arg);
- }
+ int amount = atomic_read(&sk->sk_wmem_alloc);
+ return put_user(amount, (int __user *)arg);
+ }
- case SIOCINQ:
- {
- struct sk_buff *skb;
- unsigned long amount;
-
- amount = 0;
- spin_lock_bh(&sk->sk_receive_queue.lock);
- skb = skb_peek(&sk->sk_receive_queue);
- if (skb != NULL) {
- /*
- * We will only return the amount
- * of this packet since that is all
- * that will be read.
- */
- amount = skb->len - sizeof(struct udphdr);
- }
- spin_unlock_bh(&sk->sk_receive_queue.lock);
- return put_user(amount, (int __user *)arg);
+ case SIOCINQ:
+ {
+ struct sk_buff *skb;
+ unsigned long amount;
+
+ amount = 0;
+ spin_lock_bh(&sk->sk_receive_queue.lock);
+ skb = skb_peek(&sk->sk_receive_queue);
+ if (skb != NULL) {
+ /*
+ * We will only return the amount
+ * of this packet since that is all
+ * that will be read.
+ */
+ amount = skb->len - sizeof(struct udphdr);
}
+ spin_unlock_bh(&sk->sk_receive_queue.lock);
+ return put_user(amount, (int __user *)arg);
+ }
- default:
- return -ENOIOCTLCMD;
+ default:
+ return -ENOIOCTLCMD;
}
- return(0);
+
+ return 0;
}
/*
*/
int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
- size_t len, int noblock, int flags, int *addr_len)
+ size_t len, int noblock, int flags, int *addr_len)
{
struct inet_sock *inet = inet_sk(sk);
- struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
- struct sk_buff *skb;
- int copied, err, copy_only, is_udplite = IS_UDPLITE(sk);
+ 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);
/*
* Check any passed addresses
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;
-
- copied = skb->len - sizeof(struct udphdr);
- if (copied > len) {
- copied = len;
+
+ ulen = skb->len - sizeof(struct udphdr);
+ copied = len;
+ if (copied > ulen)
+ copied = ulen;
+ else if (copied < ulen)
msg->msg_flags |= MSG_TRUNC;
- }
/*
- * Decide whether to checksum and/or copy data.
- *
- * UDP: checksum may have been computed in HW,
- * (re-)compute it if message is truncated.
- * UDP-Lite: always needs to checksum, no HW support.
+ * If checksum is needed at all, try to do it while copying the
+ * data. If the data is truncated, or if we only want a partial
+ * coverage checksum (UDP-Lite), do it before the copy.
*/
- copy_only = (skb->ip_summed==CHECKSUM_UNNECESSARY);
- if (is_udplite || (!copy_only && msg->msg_flags&MSG_TRUNC)) {
- if (__udp_lib_checksum_complete(skb))
+ if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
+ if (udp_lib_checksum_complete(skb))
goto csum_copy_err;
- copy_only = 1;
}
- if (copy_only)
+ if (skb_csum_unnecessary(skb))
err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
msg->msg_iov, copied );
else {
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. */
if (sin)
{
sin->sin_family = AF_INET;
- sin->sin_port = skb->h.uh->source;
- sin->sin_addr.s_addr = skb->nh.iph->saddr;
+ sin->sin_port = udp_hdr(skb)->source;
+ sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
- }
+ }
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
err = copied;
if (flags & MSG_TRUNC)
- err = skb->len - sizeof(struct udphdr);
-
+ err = ulen;
+
out_free:
- skb_free_datagram(sk, skb);
+ lock_sock(sk);
+ skb_free_datagram(sk, skb);
+ release_sock(sk);
out:
- return err;
+ 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(UDP_MIB_INERRORS, is_udplite);
+ release_sock(sk);
if (noblock)
- return -EAGAIN;
+ return -EAGAIN;
goto try_again;
}
/*
* 1003.1g - break association.
*/
-
+
sk->sk_state = TCP_CLOSE;
inet->daddr = 0;
inet->dport = 0;
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)
-{
-#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 = skb->h.uh;
- 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;
- }
-
- /* 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;
-
- /* Now we can update and verify the packet length... */
- iph = skb->nh.iph;
- iphlen = iph->ihl << 2;
- iph->tot_len = htons(ntohs(iph->tot_len) - len);
- if (skb->len < iphlen + len) {
- /* packet is too small!?! */
- return 0;
- }
-
- /* 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->h.raw = skb_pull(skb, len);
-
- /* modify the protocol (it's ESP!) */
- iph->protocol = IPPROTO_ESP;
-
- /* and let the caller know to send this into the ESP processor... */
- return -1;
-#endif
-}
-
/* returns:
* -1: error
* 0: success
{
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(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
}
}
- if (sk->sk_filter && skb->ip_summed != CHECKSUM_UNNECESSARY) {
- if (__udp_lib_checksum_complete(skb))
+ if (sk->sk_filter) {
+ if (udp_lib_checksum_complete(skb))
goto drop;
- skb->ip_summed = CHECKSUM_UNNECESSARY;
}
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;
}
sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr,
uh->source, saddr, dif);
- if(sknext)
+ if (sknext)
skb1 = skb_clone(skb, GFP_ATOMIC);
- if(skb1) {
- int ret = udp_queue_rcv_skb(sk, skb1);
+ if (skb1) {
+ int ret = 0;
+
+ bh_lock_sock_nested(sk);
+ if (!sock_owned_by_user(sk))
+ ret = udp_queue_rcv_skb(sk, skb1);
+ else
+ sk_add_backlog(sk, skb1);
+ bh_unlock_sock(sk);
+
if (ret > 0)
/* we should probably re-process instead
* of dropping packets here. */
kfree_skb(skb1);
}
sk = sknext;
- } while(sknext);
+ } while (sknext);
} else
kfree_skb(skb);
read_unlock(&udp_hash_lock);
* Otherwise, csum completion requires chacksumming packet body,
* including udp header and folding it to skb->csum.
*/
-static inline void udp4_csum_init(struct sk_buff *skb, struct udphdr *uh)
+static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
+ int proto)
{
+ const struct iphdr *iph;
+ int err;
+
+ UDP_SKB_CB(skb)->partial_cov = 0;
+ UDP_SKB_CB(skb)->cscov = skb->len;
+
+ if (proto == IPPROTO_UDPLITE) {
+ err = udplite_checksum_init(skb, uh);
+ if (err)
+ return err;
+ }
+
+ iph = ip_hdr(skb);
if (uh->check == 0) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
} else if (skb->ip_summed == CHECKSUM_COMPLETE) {
- if (!csum_tcpudp_magic(skb->nh.iph->saddr, skb->nh.iph->daddr,
- skb->len, IPPROTO_UDP, skb->csum ))
+ if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
+ proto, skb->csum))
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
- if (skb->ip_summed != CHECKSUM_UNNECESSARY)
- skb->csum = csum_tcpudp_nofold(skb->nh.iph->saddr,
- skb->nh.iph->daddr,
- skb->len, IPPROTO_UDP, 0);
+ if (!skb_csum_unnecessary(skb))
+ skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
+ skb->len, proto, 0);
/* Probably, we should checksum udp header (it should be in cache
* in any case) and data in tiny packets (< rx copybreak).
*/
- /* UDP = UDP-Lite with a non-partial checksum coverage */
- UDP_SKB_CB(skb)->partial_cov = 0;
+ return 0;
}
/*
- * All we need to do is get the socket, and then do a checksum.
+ * 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 is_udplite)
+ int proto)
{
- struct sock *sk;
- struct udphdr *uh = skb->h.uh;
+ struct sock *sk;
+ struct udphdr *uh = udp_hdr(skb);
unsigned short ulen;
struct rtable *rt = (struct rtable*)skb->dst;
- __be32 saddr = skb->nh.iph->saddr;
- __be32 daddr = skb->nh.iph->daddr;
+ __be32 saddr = ip_hdr(skb)->saddr;
+ __be32 daddr = ip_hdr(skb)->daddr;
/*
* Validate the packet.
if (ulen > skb->len)
goto short_packet;
- if(! is_udplite ) { /* UDP validates ulen. */
-
+ if (proto == IPPROTO_UDP) {
+ /* UDP validates ulen. */
if (ulen < sizeof(*uh) || pskb_trim_rcsum(skb, ulen))
goto short_packet;
-
- udp4_csum_init(skb, uh);
-
- } else { /* UDP-Lite validates cscov. */
- if (udplite4_csum_init(skb, uh))
- goto csum_error;
+ uh = udp_hdr(skb);
}
- if(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
+ if (udp4_csum_init(skb, uh, proto))
+ goto csum_error;
+
+ if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
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);
+ int ret = 0;
+ bh_lock_sock_nested(sk);
+ if (!sock_owned_by_user(sk))
+ ret = udp_queue_rcv_skb(sk, skb);
+ else
+ sk_add_backlog(sk, skb);
+ bh_unlock_sock(sk);
sock_put(sk);
/* a return value > 0 means to resubmit the input, but
if (udp_lib_checksum_complete(skb))
goto csum_error;
- UDP_INC_STATS_BH(UDP_MIB_NOPORTS, is_udplite);
+ UDP_INC_STATS_BH(UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
/*
* don't wanna listen. Ignore it.
*/
kfree_skb(skb);
- return(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",
- is_udplite? "-Lite" : "",
+ proto == IPPROTO_UDPLITE ? "-Lite" : "",
NIPQUAD(saddr),
ntohs(uh->source),
ulen,
goto drop;
csum_error:
- /*
- * RFC1122: OK. Discards the bad packet silently (as far as
- * the network is concerned, anyway) as per 4.1.3.4 (MUST).
+ /*
+ * 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",
- is_udplite? "-Lite" : "",
+ proto == IPPROTO_UDPLITE ? "-Lite" : "",
NIPQUAD(saddr),
ntohs(uh->source),
NIPQUAD(daddr),
ntohs(uh->dest),
ulen);
drop:
- UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);
+ UDP_INC_STATS_BH(UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
kfree_skb(skb);
- return(0);
+ return 0;
}
-__inline__ int udp_rcv(struct sk_buff *skb)
+int udp_rcv(struct sk_buff *skb)
{
- return __udp4_lib_rcv(skb, udp_hash, 0);
+ return __udp4_lib_rcv(skb, udp_hash, IPPROTO_UDP);
}
int udp_destroy_sock(struct sock *sk)
/*
* Socket option code for UDP
*/
-static int do_udp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
+int udp_lib_setsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int optlen,
+ int (*push_pending_frames)(struct sock *))
{
struct udp_sock *up = udp_sk(sk);
int val;
int err = 0;
+ int is_udplite = IS_UDPLITE(sk);
- if(optlen<sizeof(int))
+ if (optlen<sizeof(int))
return -EINVAL;
if (get_user(val, (int __user *)optval))
return -EFAULT;
- switch(optname) {
+ switch (optname) {
case UDP_CORK:
if (val != 0) {
up->corkflag = 1;
} else {
up->corkflag = 0;
lock_sock(sk);
- udp_push_pending_frames(sk, up);
+ (*push_pending_frames)(sk);
release_sock(sk);
}
break;
-
+
case UDP_ENCAP:
switch (val) {
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;
up->pcflag |= UDPLITE_SEND_CC;
break;
- /* The receiver specifies a minimum checksum coverage value. To make
- * sense, this should be set to at least 8 (as done below). If zero is
+ /* The receiver specifies a minimum checksum coverage value. To make
+ * 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;
default:
err = -ENOPROTOOPT;
break;
- };
+ }
return err;
}
char __user *optval, int optlen)
{
if (level == SOL_UDP || level == SOL_UDPLITE)
- return do_udp_setsockopt(sk, level, optname, optval, optlen);
+ return udp_lib_setsockopt(sk, level, optname, optval, optlen,
+ udp_push_pending_frames);
return ip_setsockopt(sk, level, optname, optval, optlen);
}
char __user *optval, int optlen)
{
if (level == SOL_UDP || level == SOL_UDPLITE)
- return do_udp_setsockopt(sk, level, optname, optval, optlen);
+ return udp_lib_setsockopt(sk, level, optname, optval, optlen,
+ udp_push_pending_frames);
return compat_ip_setsockopt(sk, level, optname, optval, optlen);
}
#endif
-static int do_udp_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
+int udp_lib_getsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int __user *optlen)
{
struct udp_sock *up = udp_sk(sk);
int val, len;
- if(get_user(len,optlen))
+ if (get_user(len,optlen))
return -EFAULT;
len = min_t(unsigned int, len, sizeof(int));
-
- if(len < 0)
+
+ if (len < 0)
return -EINVAL;
- switch(optname) {
+ switch (optname) {
case UDP_CORK:
val = up->corkflag;
break;
default:
return -ENOPROTOOPT;
- };
+ }
- if(put_user(len, optlen))
- return -EFAULT;
- if(copy_to_user(optval, &val,len))
+ if (put_user(len, optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, &val,len))
return -EFAULT;
- return 0;
+ return 0;
}
int udp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
if (level == SOL_UDP || level == SOL_UDPLITE)
- return do_udp_getsockopt(sk, level, optname, optval, optlen);
+ return udp_lib_getsockopt(sk, level, optname, optval, optlen);
return ip_getsockopt(sk, level, optname, optval, optlen);
}
char __user *optval, int __user *optlen)
{
if (level == SOL_UDP || level == SOL_UDPLITE)
- return do_udp_getsockopt(sk, level, optname, optval, optlen);
+ return udp_lib_getsockopt(sk, level, optname, optval, optlen);
return compat_ip_getsockopt(sk, level, optname, optval, optlen);
}
#endif
* @sock - socket
* @wait - poll table
*
- * This is same as datagram poll, except for the special case of
+ * This is same as datagram poll, except for the special case of
* blocking sockets. If application is using a blocking fd
* and a packet with checksum error is in the queue;
* then it could get return from select indicating data available
struct sk_buff *skb;
spin_lock_bh(&rcvq->lock);
- while ((skb = skb_peek(rcvq)) != NULL) {
- if (udp_lib_checksum_complete(skb)) {
- UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_lite);
- __skb_unlink(skb, rcvq);
- kfree_skb(skb);
- } else {
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- break;
- }
+ while ((skb = skb_peek(rcvq)) != NULL &&
+ udp_lib_checksum_complete(skb)) {
+ UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_lite);
+ __skb_unlink(skb, rcvq);
+ kfree_skb(skb);
}
spin_unlock_bh(&rcvq->lock);
}
return mask;
-
+
}
+DEFINE_PROTO_INUSE(udp)
+
struct proto udp_prot = {
- .name = "UDP",
+ .name = "UDP",
.owner = THIS_MODULE,
.close = udp_lib_close,
.connect = ip4_datagram_connect,
.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),
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udp_setsockopt,
.compat_getsockopt = compat_udp_getsockopt,
#endif
+ REF_PROTO_INUSE(udp)
};
/* ------------------------------------------------------------------------ */
struct sock *sk = udp_get_first(seq);
if (sk)
- while(pos && (sk = udp_get_next(seq, sk)) != NULL)
+ while (pos && (sk = udp_get_next(seq, sk)) != NULL)
--pos;
return pos ? NULL : sk;
}
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));
}
sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
" %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p",
- bucket, src, srcp, dest, destp, sp->sk_state,
+ 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),
}
#endif /* CONFIG_PROC_FS */
+void __init udp_init(void)
+{
+ unsigned long limit;
+
+ /* 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.
+ */
+ limit = min(nr_all_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT);
+ limit = (limit * (nr_all_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_get_port);
EXPORT_SYMBOL(udp_prot);
EXPORT_SYMBOL(udp_sendmsg);
+EXPORT_SYMBOL(udp_lib_getsockopt);
+EXPORT_SYMBOL(udp_lib_setsockopt);
EXPORT_SYMBOL(udp_poll);
#ifdef CONFIG_PROC_FS