* 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/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: 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)
/*
* 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 {
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(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 *);
connected = 0;
}
- if (MULTICAST(daddr)) {
+ if (ipv4_is_multicast(daddr)) {
if (!ipc.oif)
ipc.oif = inet->mc_index;
if (!saddr)
.dport = dport } } };
security_sk_classify_flow(sk, &fl);
err = ip_route_output_flow(&rt, &fl, sk, 1);
- if (err)
+ if (err) {
+ if (err == -ENETUNREACH)
+ IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
goto out;
+ }
err = -EACCES;
if ((rt->rt_flags & RTCF_BROADCAST) &&
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
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;
goto csum_copy_err;
}
- if (skb->ip_summed == CHECKSUM_UNNECESSARY)
+ 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. */
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(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)
-{
-#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;
- }
-
- /* 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 = 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;
- }
-
- /* 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;
-
- /* 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 ((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;
}
skb1 = skb_clone(skb, GFP_ATOMIC);
if (skb1) {
- int ret = udp_queue_rcv_skb(sk, 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. */
proto, skb->csum))
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
- if (skb->ip_summed != CHECKSUM_UNNECESSARY)
+ 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
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
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;
* 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,
.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)
};
/* ------------------------------------------------------------------------ */
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));
}
}
#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);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff