summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c9
-rw-r--r--net/ipv4/arp.c31
-rw-r--r--net/ipv4/igmp.c9
-rw-r--r--net/ipv4/inetpeer.c4
-rw-r--r--net/ipv4/ip_output.c56
-rw-r--r--net/ipv4/ip_sockglue.c38
-rw-r--r--net/ipv4/netfilter/ip_fw_compat.c4
-rw-r--r--net/ipv4/netfilter/ip_fw_compat_masq.c7
-rw-r--r--net/ipv4/netfilter/ip_nat_ftp.c5
-rw-r--r--net/ipv4/netfilter/ip_nat_standalone.c42
-rw-r--r--net/ipv4/netfilter/ip_queue.c2
-rw-r--r--net/ipv4/netfilter/ipt_MIRROR.c2
-rw-r--r--net/ipv4/netfilter/ipt_REJECT.c15
-rw-r--r--net/ipv4/netfilter/iptable_mangle.c56
-rw-r--r--net/ipv4/protocol.c5
-rw-r--r--net/ipv4/route.c80
-rw-r--r--net/ipv4/sysctl_net_ipv4.c25
-rw-r--r--net/ipv4/tcp.c76
-rw-r--r--net/ipv4/tcp_input.c19
-rw-r--r--net/ipv4/tcp_ipv4.c13
-rw-r--r--net/ipv4/tcp_minisocks.c8
-rw-r--r--net/ipv4/tcp_timer.c2
-rw-r--r--net/ipv4/udp.c69
-rw-r--r--net/ipv4/utils.c6
24 files changed, 364 insertions, 219 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 6e80ed912..69c6ff036 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -5,7 +5,7 @@
*
* PF_INET protocol family socket handler.
*
- * Version: $Id: af_inet.c,v 1.112 2000/08/16 16:20:56 davem Exp $
+ * Version: $Id: af_inet.c,v 1.114 2000/09/18 05:59:48 davem Exp $
*
* Authors: Ross Biro, <bir7@leland.Stanford.Edu>
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
@@ -258,7 +258,6 @@ static int inet_autobind(struct sock *sk)
return -EAGAIN;
}
sk->sport = htons(sk->num);
- sk->prot->hash(sk);
}
release_sock(sk);
return 0;
@@ -390,7 +389,6 @@ static int inet_create(struct socket *sock, int protocol)
if (sk->prot->init) {
int err = sk->prot->init(sk);
if (err != 0) {
- sk->dead = 1;
inet_sock_release(sk);
return(err);
}
@@ -460,7 +458,7 @@ static int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
-
+
chk_addr_ret = inet_addr_type(addr->sin_addr.s_addr);
snum = ntohs(addr->sin_port);
@@ -495,10 +493,11 @@ static int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
if (sk->rcv_saddr)
sk->userlocks |= SOCK_BINDADDR_LOCK;
+ if (snum)
+ sk->userlocks |= SOCK_BINDPORT_LOCK;
sk->sport = htons(sk->num);
sk->daddr = 0;
sk->dport = 0;
- sk->prot->hash(sk);
sk_dst_reset(sk);
err = 0;
out:
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 2dfd1763c..c173b9eb3 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1066,16 +1066,13 @@ static int arp_get_info(char *buffer, char **start, off_t offset, int length)
{
char tbuf[16];
sprintf(tbuf, "%u.%u.%u.%u", NIPQUAD(*(u32*)n->primary_key));
-
- size = sprintf(buffer+len, "%-16s 0x%-10x0x%-10x%s",
+ size = sprintf(buffer+len, "%-16s 0x%-10x0x%-10x%s"
+ " * %s\n",
tbuf,
hatype,
arp_state_to_flags(n),
- hbuffer);
-
- size += sprintf(buffer+len+size,
- " %-8s %s\n",
- "*", dev->name);
+ hbuffer,
+ dev->name);
}
read_unlock(&n->lock);
@@ -1099,15 +1096,17 @@ static int arp_get_info(char *buffer, char **start, off_t offset, int length)
struct net_device *dev = n->dev;
int hatype = dev ? dev->type : 0;
- size = sprintf(buffer+len,
- "%u.%u.%u.%u0x%-10x0x%-10x%s",
- NIPQUAD(*(u32*)n->key),
- hatype,
- ATF_PUBL|ATF_PERM,
- "00:00:00:00:00:00");
- size += sprintf(buffer+len+size,
- " %-17s %s\n",
- "*", dev ? dev->name : "*");
+ {
+ char tbuf[16];
+ sprintf(tbuf, "%u.%u.%u.%u", NIPQUAD(*(u32*)n->key));
+ size = sprintf(buffer+len, "%-16s 0x%-10x0x%-10x%s"
+ " * %s\n",
+ tbuf,
+ hatype,
+ ATF_PUBL|ATF_PERM,
+ "00:00:00:00:00:00",
+ dev ? dev->name : "*");
+ }
len += size;
pos += size;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 0af9ec321..1d8002bdd 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -8,7 +8,7 @@
* the older version didn't come out right using gcc 2.5.8, the newer one
* seems to fall out with gcc 2.6.2.
*
- * Version: $Id: igmp.c,v 1.40 2000/07/26 01:04:16 davem Exp $
+ * Version: $Id: igmp.c,v 1.41 2000/08/31 23:39:12 davem Exp $
*
* Authors:
* Alan Cox <Alan.Cox@linux.org>
@@ -184,7 +184,10 @@ static void igmp_mod_timer(struct ip_mc_list *im, int max_delay)
#define IGMP_SIZE (sizeof(struct igmphdr)+sizeof(struct iphdr)+4)
-static inline int igmp_send_report2(struct sk_buff *skb)
+/* Don't just hand NF_HOOK skb->dst->output, in case netfilter hook
+ changes route */
+static inline int
+output_maybe_reroute(struct sk_buff *skb)
{
return skb->dst->output(skb);
}
@@ -247,7 +250,7 @@ static int igmp_send_report(struct net_device *dev, u32 group, int type)
ih->csum=ip_compute_csum((void *)ih, sizeof(struct igmphdr));
return NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
- igmp_send_report2);
+ output_maybe_reroute);
}
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 40bf288ac..cda89659c 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -82,12 +82,12 @@ static struct inet_peer *peer_root = peer_avl_empty;
static rwlock_t peer_pool_lock = RW_LOCK_UNLOCKED;
#define PEER_MAXDEPTH 40 /* sufficient for about 2^27 nodes */
-static volatile int peer_total = 0;
+static volatile int peer_total;
int inet_peer_threshold = 65536 + 128; /* start to throw entries more
* aggressively at this stage */
int inet_peer_minttl = 120 * HZ; /* TTL under high load: 120 sec */
int inet_peer_maxttl = 10 * 60 * HZ; /* usual time to live: 10 min */
-struct inet_peer *inet_peer_unused_head = NULL,
+struct inet_peer *inet_peer_unused_head,
**inet_peer_unused_tailp = &inet_peer_unused_head;
spinlock_t inet_peer_unused_lock = SPIN_LOCK_UNLOCKED;
#define PEER_MAX_CLEANUP_WORK 30
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 3d0e2b4aa..056767890 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -5,7 +5,7 @@
*
* The Internet Protocol (IP) output module.
*
- * Version: $Id: ip_output.c,v 1.84 2000/08/25 02:15:47 davem Exp $
+ * Version: $Id: ip_output.c,v 1.85 2000/08/31 23:39:12 davem Exp $
*
* Authors: Ross Biro, <bir7@leland.Stanford.Edu>
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
@@ -107,42 +107,11 @@ static int ip_dev_loopback_xmit(struct sk_buff *newskb)
return 0;
}
-#ifdef CONFIG_NETFILTER
-/* To preserve the cute illusion that a locally-generated packet can
- be mangled before routing, we actually reroute if a hook altered
- the packet. -RR */
-static int route_me_harder(struct sk_buff *skb)
-{
- struct iphdr *iph = skb->nh.iph;
- struct rtable *rt;
-
- if (ip_route_output(&rt, iph->daddr, iph->saddr,
- RT_TOS(iph->tos) | RTO_CONN,
- skb->sk ? skb->sk->bound_dev_if : 0)) {
- printk("route_me_harder: No more route.\n");
- return -EINVAL;
- }
-
- /* Drop old route. */
- dst_release(skb->dst);
-
- skb->dst = &rt->u.dst;
- return 0;
-}
-#endif
-
-/* Do route recalc if netfilter changes skb. */
+/* Don't just hand NF_HOOK skb->dst->output, in case netfilter hook
+ changes route */
static inline int
output_maybe_reroute(struct sk_buff *skb)
{
-#ifdef CONFIG_NETFILTER
- if (skb->nfcache & NFC_ALTERED) {
- if (route_me_harder(skb) != 0) {
- kfree_skb(skb);
- return -EINVAL;
- }
- }
-#endif
return skb->dst->output(skb);
}
@@ -312,25 +281,6 @@ static inline int ip_queue_xmit2(struct sk_buff *skb)
struct net_device *dev;
struct iphdr *iph = skb->nh.iph;
-#ifdef CONFIG_NETFILTER
- /* BLUE-PEN-FOR-ALEXEY. I don't understand; you mean I can't
- hold the route as I pass the packet to userspace? -- RR
-
- You may hold it, if you really hold it. F.e. if netfilter
- does not destroy handed skb with skb->dst attached, it
- will be held. When it was stored in info->arg, then
- it was not held apparently. Now (without second arg) it is evident,
- that it is clean. --ANK
- */
- if (rt==NULL || (skb->nfcache & NFC_ALTERED)) {
- if (route_me_harder(skb) != 0) {
- kfree_skb(skb);
- return -EHOSTUNREACH;
- }
- rt = (struct rtable *)skb->dst;
- }
-#endif
-
dev = rt->u.dst.dev;
/* This can happen when the transport layer has segments queued
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 4287c7525..a82e4be1f 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -5,7 +5,7 @@
*
* The IP to API glue.
*
- * Version: $Id: ip_sockglue.c,v 1.51 2000/08/09 11:59:04 davem Exp $
+ * Version: $Id: ip_sockglue.c,v 1.52 2000/09/09 08:26:04 davem Exp $
*
* Authors: see ip.c
*
@@ -380,31 +380,39 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char *optval, int opt
{
int val=0,err;
- if(optlen>=sizeof(int)) {
- if(get_user(val, (int *) optval))
- return -EFAULT;
- } else if(optlen>=sizeof(char)) {
- unsigned char ucval;
- if(get_user(ucval, (unsigned char *) optval))
- return -EFAULT;
- val = (int)ucval;
+ if (optname == IP_PKTINFO || optname == IP_RECVTTL ||
+ optname == IP_RECVTOS || optname == IP_RECVOPTS ||
+ optname == IP_RETOPTS || optname == IP_TOS ||
+ optname == IP_TTL || optname == IP_HDRINCL ||
+ optname == IP_MTU_DISCOVER || optname == IP_RECVERR ||
+ optname == IP_MULTICAST_TTL || optname == IP_MULTICAST_LOOP ||
+ optname == IP_ROUTER_ALERT) {
+ if (optlen >= sizeof(int)) {
+ if (get_user(val, (int *) optval))
+ return -EFAULT;
+ } else if (optlen >= sizeof(char)) {
+ unsigned char ucval;
+
+ if (get_user(ucval, (unsigned char *) optval))
+ return -EFAULT;
+ val = (int) ucval;
+ }
}
+
/* If optlen==0, it is equivalent to val == 0 */
- if(level!=SOL_IP)
+ if (level != SOL_IP)
return -ENOPROTOOPT;
+
#ifdef CONFIG_IP_MROUTE
- if(optname>=MRT_BASE && optname <=MRT_BASE+10)
- {
+ if (optname >= MRT_BASE && optname <= (MRT_BASE + 10))
return ip_mroute_setsockopt(sk,optname,optval,optlen);
- }
#endif
err = 0;
lock_sock(sk);
- switch(optname)
- {
+ switch (optname) {
case IP_OPTIONS:
{
struct ip_options * opt = NULL;
diff --git a/net/ipv4/netfilter/ip_fw_compat.c b/net/ipv4/netfilter/ip_fw_compat.c
index 6bb1b240c..cc3d2fb9c 100644
--- a/net/ipv4/netfilter/ip_fw_compat.c
+++ b/net/ipv4/netfilter/ip_fw_compat.c
@@ -15,6 +15,10 @@ struct notifier_block;
#include <linux/netfilter_ipv4/ip_conntrack.h>
#include <linux/netfilter_ipv4/ip_conntrack_core.h>
+/* Theoretically, we could one day use 2.4 helpers, but for now it
+ just confuses depmod --RR */
+EXPORT_NO_SYMBOLS;
+
static struct firewall_ops *fwops;
/* From ip_fw_compat_redir.c */
diff --git a/net/ipv4/netfilter/ip_fw_compat_masq.c b/net/ipv4/netfilter/ip_fw_compat_masq.c
index ce3180d39..e68804d65 100644
--- a/net/ipv4/netfilter/ip_fw_compat_masq.c
+++ b/net/ipv4/netfilter/ip_fw_compat_masq.c
@@ -85,7 +85,12 @@ do_masquerade(struct sk_buff **pskb, const struct net_device *dev)
newsrc, newsrc,
{ htons(61000) }, { htons(65095) } } } });
- ip_nat_setup_info(ct, &range, NF_IP_POST_ROUTING);
+ ret = ip_nat_setup_info(ct, &range, NF_IP_POST_ROUTING);
+ if (ret != NF_ACCEPT) {
+ WRITE_UNLOCK(&ip_nat_lock);
+ return ret;
+ }
+
place_in_hashes(ct, info);
info->initialized = 1;
} else
diff --git a/net/ipv4/netfilter/ip_nat_ftp.c b/net/ipv4/netfilter/ip_nat_ftp.c
index c3d8ccab0..54f89f765 100644
--- a/net/ipv4/netfilter/ip_nat_ftp.c
+++ b/net/ipv4/netfilter/ip_nat_ftp.c
@@ -372,8 +372,9 @@ static unsigned int help(struct ip_conntrack *ct,
newseq = ntohl(tcph->seq) + ftp[dir].syn_offset_before;
newseq = htonl(newseq);
- /* Ack adjust */
- if (after(ntohl(tcph->ack_seq), ftp[!dir].syn_correction_pos))
+ /* Ack adjust: other dir sees offset seq numbers */
+ if (after(ntohl(tcph->ack_seq) - ftp[!dir].syn_offset_before,
+ ftp[!dir].syn_correction_pos))
newack = ntohl(tcph->ack_seq) - ftp[!dir].syn_offset_after;
else
newack = ntohl(tcph->ack_seq) - ftp[!dir].syn_offset_before;
diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c
index 3334a64c2..10d09a6bd 100644
--- a/net/ipv4/netfilter/ip_nat_standalone.c
+++ b/net/ipv4/netfilter/ip_nat_standalone.c
@@ -7,6 +7,7 @@
/* (c) 1999 Paul `Rusty' Russell. Licenced under the GNU General
Public Licence. */
+#include <linux/config.h>
#include <linux/types.h>
#include <linux/ip.h>
#include <linux/netfilter.h>
@@ -161,6 +162,34 @@ ip_nat_out(unsigned int hooknum,
return ip_nat_fn(hooknum, pskb, in, out, okfn);
}
+/* FIXME: change in oif may mean change in hh_len. Check and realloc
+ --RR */
+static int
+route_me_harder(struct sk_buff *skb)
+{
+ struct iphdr *iph = skb->nh.iph;
+ struct rtable *rt;
+ struct rt_key key = { dst:iph->daddr,
+ src:iph->saddr,
+ oif:skb->sk ? skb->sk->bound_dev_if : 0,
+ tos:RT_TOS(iph->tos)|RTO_CONN,
+#ifdef CONFIG_IP_ROUTE_FWMARK
+ fwmark:skb->nfmark
+#endif
+ };
+
+ if (ip_route_output_key(&rt, &key) != 0) {
+ printk("route_me_harder: No more route.\n");
+ return -EINVAL;
+ }
+
+ /* Drop old route. */
+ dst_release(skb->dst);
+
+ skb->dst = &rt->u.dst;
+ return 0;
+}
+
static unsigned int
ip_nat_local_fn(unsigned int hooknum,
struct sk_buff **pskb,
@@ -168,12 +197,23 @@ ip_nat_local_fn(unsigned int hooknum,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
+ u_int32_t saddr, daddr;
+ unsigned int ret;
+
/* root is playing with raw sockets. */
if ((*pskb)->len < sizeof(struct iphdr)
|| (*pskb)->nh.iph->ihl * 4 < sizeof(struct iphdr))
return NF_ACCEPT;
- return ip_nat_fn(hooknum, pskb, in, out, okfn);
+ saddr = (*pskb)->nh.iph->saddr;
+ daddr = (*pskb)->nh.iph->daddr;
+
+ ret = ip_nat_fn(hooknum, pskb, in, out, okfn);
+ if (ret != NF_DROP && ret != NF_STOLEN
+ && ((*pskb)->nh.iph->saddr != saddr
+ || (*pskb)->nh.iph->daddr != daddr))
+ return route_me_harder(*pskb) == 0 ? ret : NF_DROP;
+ return ret;
}
/* We must be after connection tracking and before packet filtering. */
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index 85787ed88..73fd4eaf7 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -414,7 +414,7 @@ static struct sk_buff *netlink_build_message(ipq_queue_element_t *e, int *errp)
return skb;
nlmsg_failure:
if (skb)
- kfree(skb);
+ kfree_skb(skb);
*errp = 0;
printk(KERN_ERR "ip_queue: error creating netlink message\n");
return NULL;
diff --git a/net/ipv4/netfilter/ipt_MIRROR.c b/net/ipv4/netfilter/ipt_MIRROR.c
index d7718b557..cb5362dc2 100644
--- a/net/ipv4/netfilter/ipt_MIRROR.c
+++ b/net/ipv4/netfilter/ipt_MIRROR.c
@@ -89,7 +89,7 @@ static void ip_direct_send(struct sk_buff *skb)
dst->neighbour->output(skb);
else {
printk(KERN_DEBUG "khm in MIRROR\n");
- kfree(skb);
+ kfree_skb(skb);
}
}
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index 2d8ad255f..9c1088e76 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -21,12 +21,13 @@ struct in_device;
#endif
/* Send RST reply */
-static void send_reset(struct sk_buff *oldskb)
+static void send_reset(struct sk_buff *oldskb, int local)
{
struct sk_buff *nskb;
struct tcphdr *otcph, *tcph;
struct rtable *rt;
unsigned int otcplen;
+ u_int16_t tmp;
int needs_ack;
/* IP header checks: fragment, too short. */
@@ -64,8 +65,11 @@ static void send_reset(struct sk_buff *oldskb)
tcph = (struct tcphdr *)((u_int32_t*)nskb->nh.iph + nskb->nh.iph->ihl);
+ /* Swap source and dest */
nskb->nh.iph->daddr = xchg(&nskb->nh.iph->saddr, nskb->nh.iph->daddr);
- tcph->source = xchg(&tcph->dest, tcph->source);
+ tmp = tcph->source;
+ tcph->source = tcph->dest;
+ tcph->dest = tmp;
/* Truncate to length (no data) */
tcph->doff = sizeof(struct tcphdr)/4;
@@ -110,8 +114,9 @@ static void send_reset(struct sk_buff *oldskb)
nskb->nh.iph->check = ip_fast_csum((unsigned char *)nskb->nh.iph,
nskb->nh.iph->ihl);
- /* Routing */
- if (ip_route_output(&rt, nskb->nh.iph->daddr, nskb->nh.iph->saddr,
+ /* Routing: if not headed for us, route won't like source */
+ if (ip_route_output(&rt, nskb->nh.iph->daddr,
+ local ? nskb->nh.iph->saddr : 0,
RT_TOS(nskb->nh.iph->tos) | RTO_CONN,
0) != 0)
goto free_nskb;
@@ -184,7 +189,7 @@ static unsigned int reject(struct sk_buff **pskb,
}
break;
case IPT_TCP_RESET:
- send_reset(*pskb);
+ send_reset(*pskb, hooknum == NF_IP_LOCAL_IN);
break;
}
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index cb9f18da3..c52ada64e 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -3,8 +3,14 @@
*
* Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
*/
+#include <linux/config.h>
#include <linux/module.h>
#include <linux/netfilter_ipv4/ip_tables.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <net/route.h>
+#include <linux/ip.h>
#define MANGLE_VALID_HOOKS ((1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_OUT))
@@ -86,6 +92,34 @@ ipt_hook(unsigned int hook,
return ipt_do_table(pskb, hook, in, out, &packet_mangler, NULL);
}
+/* FIXME: change in oif may mean change in hh_len. Check and realloc
+ --RR */
+static int
+route_me_harder(struct sk_buff *skb)
+{
+ struct iphdr *iph = skb->nh.iph;
+ struct rtable *rt;
+ struct rt_key key = { dst:iph->daddr,
+ src:iph->saddr,
+ oif:skb->sk ? skb->sk->bound_dev_if : 0,
+ tos:RT_TOS(iph->tos)|RTO_CONN,
+#ifdef CONFIG_IP_ROUTE_FWMARK
+ fwmark:skb->nfmark
+#endif
+ };
+
+ if (ip_route_output_key(&rt, &key) != 0) {
+ printk("route_me_harder: No more route.\n");
+ return -EINVAL;
+ }
+
+ /* Drop old route. */
+ dst_release(skb->dst);
+
+ skb->dst = &rt->u.dst;
+ return 0;
+}
+
static unsigned int
ipt_local_out_hook(unsigned int hook,
struct sk_buff **pskb,
@@ -93,6 +127,11 @@ ipt_local_out_hook(unsigned int hook,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
+ unsigned int ret;
+ u_int8_t tos;
+ u_int32_t saddr, daddr;
+ unsigned long nfmark;
+
/* root is playing with raw sockets. */
if ((*pskb)->len < sizeof(struct iphdr)
|| (*pskb)->nh.iph->ihl * 4 < sizeof(struct iphdr)) {
@@ -101,7 +140,22 @@ ipt_local_out_hook(unsigned int hook,
return NF_ACCEPT;
}
- return ipt_do_table(pskb, hook, in, out, &packet_mangler, NULL);
+ /* Save things which could affect route */
+ nfmark = (*pskb)->nfmark;
+ saddr = (*pskb)->nh.iph->saddr;
+ daddr = (*pskb)->nh.iph->daddr;
+ tos = (*pskb)->nh.iph->tos;
+
+ ret = ipt_do_table(pskb, hook, in, out, &packet_mangler, NULL);
+ /* Reroute for ANY change. */
+ if (ret != NF_DROP && ret != NF_STOLEN
+ && ((*pskb)->nh.iph->saddr != saddr
+ || (*pskb)->nh.iph->daddr != daddr
+ || (*pskb)->nfmark != nfmark
+ || (*pskb)->nh.iph->tos != tos))
+ return route_me_harder(*pskb) == 0 ? ret : NF_DROP;
+
+ return ret;
}
static struct nf_hook_ops ipt_ops[]
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index 4839764e8..db57fedb9 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -112,10 +112,7 @@ static struct inet_protocol icmp_protocol =
struct inet_protocol *inet_protocol_base = IPPROTO_PREVIOUS;
-struct inet_protocol *inet_protos[MAX_INET_PROTOS] =
-{
- NULL
-};
+struct inet_protocol *inet_protos[MAX_INET_PROTOS];
/*
* Add a protocol handler to the hash tables
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d4e9806a0..4734d8087 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -5,7 +5,7 @@
*
* ROUTE - implementation of the IP router.
*
- * Version: $Id: route.c,v 1.89 2000/08/09 11:59:04 davem Exp $
+ * Version: $Id: route.c,v 1.90 2000/08/31 23:39:12 davem Exp $
*
* Authors: Ross Biro, <bir7@leland.Stanford.Edu>
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
@@ -117,7 +117,7 @@ int ip_rt_mtu_expires = 10*60*HZ;
int ip_rt_min_pmtu = 512+20+20;
int ip_rt_min_advmss = 536;
-static unsigned long rt_deadline = 0;
+static unsigned long rt_deadline;
#define RTprint(a...) printk(KERN_DEBUG a)
@@ -1610,7 +1610,7 @@ int ip_route_input(struct sk_buff *skb, u32 daddr, u32 saddr,
* Major route resolver routine.
*/
-int ip_route_output_slow(struct rtable **rp, u32 daddr, u32 saddr, u32 tos, int oif)
+int ip_route_output_slow(struct rtable **rp, const struct rt_key *oldkey)
{
struct rt_key key;
struct fib_result res;
@@ -1620,25 +1620,31 @@ int ip_route_output_slow(struct rtable **rp, u32 daddr, u32 saddr, u32 tos, int
unsigned hash;
int free_res = 0;
int err;
+ u32 tos;
- tos &= IPTOS_RT_MASK|RTO_ONLINK;
- key.dst = daddr;
- key.src = saddr;
+ tos = oldkey->tos & (IPTOS_RT_MASK|RTO_ONLINK);
+ key.dst = oldkey->dst;
+ key.src = oldkey->src;
key.tos = tos&IPTOS_RT_MASK;
key.iif = loopback_dev.ifindex;
- key.oif = oif;
+ key.oif = oldkey->oif;
+#ifdef CONFIG_IP_ROUTE_FWMARK
+ key.fwmark = oldkey->fwmark;
+#endif
key.scope = (tos&RTO_ONLINK) ? RT_SCOPE_LINK : RT_SCOPE_UNIVERSE;
res.fi = NULL;
#ifdef CONFIG_IP_MULTIPLE_TABLES
res.r = NULL;
#endif
- if (saddr) {
- if (MULTICAST(saddr) || BADCLASS(saddr) || ZERONET(saddr))
+ if (oldkey->src) {
+ if (MULTICAST(oldkey->src)
+ || BADCLASS(oldkey->src)
+ || ZERONET(oldkey->src))
return -EINVAL;
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
- dev_out = ip_dev_find(saddr);
+ dev_out = ip_dev_find(oldkey->src);
if (dev_out == NULL)
return -EINVAL;
@@ -1650,8 +1656,8 @@ int ip_route_output_slow(struct rtable **rp, u32 daddr, u32 saddr, u32 tos, int
of another iface. --ANK
*/
- if (oif == 0 &&
- (MULTICAST(daddr) || daddr == 0xFFFFFFFF)) {
+ if (oldkey->oif == 0
+ && (MULTICAST(oldkey->dst) || oldkey->dst == 0xFFFFFFFF)) {
/* Special hack: user can direct multicasts
and limited broadcast via necessary interface
without fiddling with IP_MULTICAST_IF or IP_PKTINFO.
@@ -1674,8 +1680,8 @@ int ip_route_output_slow(struct rtable **rp, u32 daddr, u32 saddr, u32 tos, int
dev_put(dev_out);
dev_out = NULL;
}
- if (oif) {
- dev_out = dev_get_by_index(oif);
+ if (oldkey->oif) {
+ dev_out = dev_get_by_index(oldkey->oif);
if (dev_out == NULL)
return -ENODEV;
if (__in_dev_get(dev_out) == NULL) {
@@ -1683,15 +1689,15 @@ int ip_route_output_slow(struct rtable **rp, u32 daddr, u32 saddr, u32 tos, int
return -ENODEV; /* Wrong error code */
}
- if (LOCAL_MCAST(daddr) || daddr == 0xFFFFFFFF) {
+ if (LOCAL_MCAST(oldkey->dst) || oldkey->dst == 0xFFFFFFFF) {
if (!key.src)
key.src = inet_select_addr(dev_out, 0, RT_SCOPE_LINK);
goto make_route;
}
if (!key.src) {
- if (MULTICAST(daddr))
+ if (MULTICAST(oldkey->dst))
key.src = inet_select_addr(dev_out, 0, key.scope);
- else if (!daddr)
+ else if (!oldkey->dst)
key.src = inet_select_addr(dev_out, 0, RT_SCOPE_HOST);
}
}
@@ -1712,7 +1718,7 @@ int ip_route_output_slow(struct rtable **rp, u32 daddr, u32 saddr, u32 tos, int
if (fib_lookup(&key, &res)) {
res.fi = NULL;
- if (oif) {
+ if (oldkey->oif) {
/* Apparently, routing tables are wrong. Assume,
that the destination is on link.
@@ -1800,7 +1806,7 @@ make_route:
} else if (res.type == RTN_MULTICAST) {
flags |= RTCF_MULTICAST|RTCF_LOCAL;
read_lock(&inetdev_lock);
- if (!__in_dev_get(dev_out) || !ip_check_mc(__in_dev_get(dev_out), daddr))
+ if (!__in_dev_get(dev_out) || !ip_check_mc(__in_dev_get(dev_out), oldkey->dst))
flags &= ~RTCF_LOCAL;
read_unlock(&inetdev_lock);
/* If multicast route do not exist use
@@ -1819,18 +1825,21 @@ make_route:
atomic_set(&rth->u.dst.__refcnt, 1);
rth->u.dst.flags= DST_HOST;
- rth->key.dst = daddr;
+ rth->key.dst = oldkey->dst;
rth->key.tos = tos;
- rth->key.src = saddr;
+ rth->key.src = oldkey->src;
rth->key.iif = 0;
- rth->key.oif = oif;
+ rth->key.oif = oldkey->oif;
+#ifdef CONFIG_IP_ROUTE_FWMARK
+ rth->key.fwmark = oldkey->fwmark;
+#endif
rth->rt_dst = key.dst;
rth->rt_src = key.src;
#ifdef CONFIG_IP_ROUTE_NAT
rth->rt_dst_map = key.dst;
rth->rt_src_map = key.src;
#endif
- rth->rt_iif = oif ? : dev_out->ifindex;
+ rth->rt_iif = oldkey->oif ? : dev_out->ifindex;
rth->u.dst.dev = dev_out;
dev_hold(dev_out);
rth->rt_gateway = key.dst;
@@ -1850,7 +1859,7 @@ make_route:
if (res.type == RTN_MULTICAST) {
struct in_device *in_dev = in_dev_get(dev_out);
if (in_dev) {
- if (IN_DEV_MFORWARD(in_dev) && !LOCAL_MCAST(daddr)) {
+ if (IN_DEV_MFORWARD(in_dev) && !LOCAL_MCAST(oldkey->dst)) {
rth->u.dst.input = ip_mr_input;
rth->u.dst.output = ip_mc_output;
}
@@ -1864,7 +1873,7 @@ make_route:
rth->rt_flags = flags;
- hash = rt_hash_code(daddr, saddr^(oif<<5), tos);
+ hash = rt_hash_code(oldkey->dst, oldkey->src^(oldkey->oif<<5), tos);
err = rt_intern_hash(hash, rth, rp);
done:
if (free_res)
@@ -1881,21 +1890,24 @@ e_nobufs:
goto done;
}
-int ip_route_output(struct rtable **rp, u32 daddr, u32 saddr, u32 tos, int oif)
+int ip_route_output_key(struct rtable **rp, const struct rt_key *key)
{
unsigned hash;
struct rtable *rth;
- hash = rt_hash_code(daddr, saddr^(oif<<5), tos);
+ hash = rt_hash_code(key->dst, key->src^(key->oif<<5), key->tos);
read_lock_bh(&rt_hash_table[hash].lock);
for (rth=rt_hash_table[hash].chain; rth; rth=rth->u.rt_next) {
- if (rth->key.dst == daddr &&
- rth->key.src == saddr &&
+ if (rth->key.dst == key->dst &&
+ rth->key.src == key->src &&
rth->key.iif == 0 &&
- rth->key.oif == oif &&
- !((rth->key.tos^tos)&(IPTOS_RT_MASK|RTO_ONLINK)) &&
- ((tos&RTO_TPROXY) || !(rth->rt_flags&RTCF_TPROXY))
+ rth->key.oif == key->oif &&
+#ifdef CONFIG_IP_ROUTE_FWMARK
+ rth->key.fwmark == key->fwmark &&
+#endif
+ !((rth->key.tos^key->tos)&(IPTOS_RT_MASK|RTO_ONLINK)) &&
+ ((key->tos&RTO_TPROXY) || !(rth->rt_flags&RTCF_TPROXY))
) {
rth->u.dst.lastuse = jiffies;
dst_hold(&rth->u.dst);
@@ -1907,8 +1919,8 @@ int ip_route_output(struct rtable **rp, u32 daddr, u32 saddr, u32 tos, int oif)
}
read_unlock_bh(&rt_hash_table[hash].lock);
- return ip_route_output_slow(rp, daddr, saddr, tos, oif);
-}
+ return ip_route_output_slow(rp, key);
+}
#ifdef CONFIG_RTNETLINK
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 4274045e8..d9f05c671 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1,7 +1,7 @@
/*
* sysctl_net_ipv4.c: sysctl interface to net IPV4 subsystem.
*
- * $Id: sysctl_net_ipv4.c,v 1.44 2000/08/09 11:59:04 davem Exp $
+ * $Id: sysctl_net_ipv4.c,v 1.46 2000/09/16 09:38:30 davem Exp $
*
* Begun April 1, 1996, Mike Shaver.
* Added /proc/sys/net/ipv4 directory entry (empty =) ). [MS]
@@ -15,19 +15,6 @@
#include <net/route.h>
#include <net/tcp.h>
-/*
- * TCP configuration parameters
- */
-
-#define TCP_PMTU_DISC 0x00000001 /* perform PMTU discovery */
-#define TCP_CONG_AVOID 0x00000002 /* congestion avoidance algorithm */
-#define TCP_DELAY_ACKS 0x00000003 /* delayed ack stategy */
-
-#if 0
-static int boolean_min = 0;
-static int boolean_max = 1;
-#endif
-
/* From icmp.c */
extern int sysctl_icmp_echo_ignore_all;
extern int sysctl_icmp_echo_ignore_broadcasts;
@@ -57,7 +44,10 @@ extern int inet_peer_maxttl;
extern int inet_peer_gc_mintime;
extern int inet_peer_gc_maxtime;
-int tcp_retr1_max = 255;
+static int tcp_retr1_max = 255;
+
+static int ip_local_port_range_min[] = { 1, 1 };
+static int ip_local_port_range_max[] = { 65535, 65535 };
struct ipv4_config ipv4_config;
@@ -170,7 +160,8 @@ ctl_table ipv4_table[] = {
sizeof(int), 0644, NULL, &proc_dointvec},
{NET_IPV4_LOCAL_PORT_RANGE, "ip_local_port_range",
&sysctl_local_port_range, sizeof(sysctl_local_port_range), 0644,
- NULL, &proc_dointvec},
+ NULL, &proc_dointvec_minmax, &sysctl_intvec, NULL,
+ ip_local_port_range_min, ip_local_port_range_max },
{NET_IPV4_ICMP_ECHO_IGNORE_ALL, "icmp_echo_ignore_all",
&sysctl_icmp_echo_ignore_all, sizeof(int), 0644, NULL,
&proc_dointvec},
@@ -213,8 +204,10 @@ ctl_table ipv4_table[] = {
&sysctl_tcp_fack, sizeof(int), 0644, NULL, &proc_dointvec},
{NET_TCP_REORDERING, "tcp_reordering",
&sysctl_tcp_reordering, sizeof(int), 0644, NULL, &proc_dointvec},
+#ifdef CONFIG_INET_ECN
{NET_TCP_ECN, "tcp_ecn",
&sysctl_tcp_ecn, sizeof(int), 0644, NULL, &proc_dointvec},
+#endif
{NET_TCP_DSACK, "tcp_dsack",
&sysctl_tcp_dsack, sizeof(int), 0644, NULL, &proc_dointvec},
{NET_TCP_MEM, "tcp_mem",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d828a7f3f..05027bc93 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -5,7 +5,7 @@
*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp.c,v 1.173 2000/08/15 20:15:23 davem Exp $
+ * Version: $Id: tcp.c,v 1.174 2000/09/18 05:59:48 davem Exp $
*
* Authors: Ross Biro, <bir7@leland.Stanford.Edu>
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
@@ -436,7 +436,7 @@ kmem_cache_t *tcp_timewait_cachep;
atomic_t tcp_orphan_count = ATOMIC_INIT(0);
-int sysctl_tcp_mem[3] = { 0, };
+int sysctl_tcp_mem[3];
int sysctl_tcp_wmem[3] = { 4*1024, 16*1024, 128*1024 };
int sysctl_tcp_rmem[3] = { 4*1024, 87380, 87380*2 };
@@ -1952,12 +1952,14 @@ int tcp_disconnect(struct sock *sk, int flags)
sk->dport = 0;
- sk->rcv_saddr = 0;
- sk->saddr = 0;
+ if (!(sk->userlocks&SOCK_BINDADDR_LOCK)) {
+ sk->rcv_saddr = 0;
+ sk->saddr = 0;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
- memset(&sk->net_pinfo.af_inet6.saddr, 0, 16);
- memset(&sk->net_pinfo.af_inet6.rcv_saddr, 0, 16);
+ memset(&sk->net_pinfo.af_inet6.saddr, 0, 16);
+ memset(&sk->net_pinfo.af_inet6.rcv_saddr, 0, 16);
#endif
+ }
sk->shutdown = 0;
sk->done = 0;
@@ -2281,6 +2283,68 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char *optval,
case TCP_WINDOW_CLAMP:
val = tp->window_clamp;
break;
+ case TCP_INFO:
+ {
+ struct tcp_info info;
+ u32 now = tcp_time_stamp;
+
+ if(get_user(len,optlen))
+ return -EFAULT;
+ info.tcpi_state = sk->state;
+ info.tcpi_ca_state = tp->ca_state;
+ info.tcpi_retransmits = tp->retransmits;
+ info.tcpi_probes = tp->probes_out;
+ info.tcpi_backoff = tp->backoff;
+ info.tcpi_options = 0;
+ if (tp->tstamp_ok)
+ info.tcpi_options |= TCPI_OPT_TIMESTAMPS;
+ if (tp->sack_ok)
+ info.tcpi_options |= TCPI_OPT_SACK;
+ if (tp->wscale_ok) {
+ info.tcpi_options |= TCPI_OPT_WSCALE;
+ info.tcpi_snd_wscale = tp->snd_wscale;
+ info.tcpi_rcv_wscale = tp->rcv_wscale;
+ } else {
+ info.tcpi_snd_wscale = 0;
+ info.tcpi_rcv_wscale = 0;
+ }
+#ifdef CONFIG_INET_ECN
+ if (tp->ecn_flags&TCP_ECN_OK)
+ info.tcpi_options |= TCPI_OPT_ECN;
+#endif
+
+ info.tcpi_rto = (1000000*tp->rto)/HZ;
+ info.tcpi_ato = (1000000*tp->ack.ato)/HZ;
+ info.tcpi_snd_mss = tp->mss_cache;
+ info.tcpi_rcv_mss = tp->ack.rcv_mss;
+
+ info.tcpi_unacked = tp->packets_out;
+ info.tcpi_sacked = tp->sacked_out;
+ info.tcpi_lost = tp->lost_out;
+ info.tcpi_retrans = tp->retrans_out;
+ info.tcpi_fackets = tp->fackets_out;
+
+ info.tcpi_last_data_sent = ((now - tp->lsndtime)*1000)/HZ;
+ info.tcpi_last_ack_sent = 0;
+ info.tcpi_last_data_recv = ((now - tp->ack.lrcvtime)*1000)/HZ;
+ info.tcpi_last_ack_recv = ((now - tp->rcv_tstamp)*1000)/HZ;
+
+ info.tcpi_pmtu = tp->pmtu_cookie;
+ info.tcpi_rcv_ssthresh = tp->rcv_ssthresh;
+ info.tcpi_rtt = ((1000000*tp->srtt)/HZ)>>3;
+ info.tcpi_rttvar = ((1000000*tp->mdev)/HZ)>>2;
+ info.tcpi_snd_ssthresh = tp->snd_ssthresh;
+ info.tcpi_snd_cwnd = tp->snd_cwnd;
+ info.tcpi_advmss = tp->advmss;
+ info.tcpi_reordering = tp->reordering;
+
+ len = min(len, sizeof(info));
+ if(put_user(len, optlen))
+ return -EFAULT;
+ if(copy_to_user(optval, &info,len))
+ return -EFAULT;
+ return 0;
+ }
default:
return -ENOPROTOOPT;
};
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 76791d724..ea9d18d97 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5,7 +5,7 @@
*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp_input.c,v 1.198 2000/08/15 20:15:23 davem Exp $
+ * Version: $Id: tcp_input.c,v 1.202 2000/09/21 01:05:38 davem Exp $
*
* Authors: Ross Biro, <bir7@leland.Stanford.Edu>
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
@@ -58,6 +58,7 @@
* J Hadi Salim: ECN support
*/
+#include <linux/config.h>
#include <linux/mm.h>
#include <linux/sysctl.h>
#include <net/tcp.h>
@@ -73,7 +74,11 @@ int sysctl_tcp_window_scaling = 1;
int sysctl_tcp_sack = 1;
int sysctl_tcp_fack = 1;
int sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH;
+#ifdef CONFIG_INET_ECN
int sysctl_tcp_ecn = 1;
+#else
+int sysctl_tcp_ecn = 0;
+#endif
int sysctl_tcp_dsack = 1;
int sysctl_tcp_app_win = 31;
int sysctl_tcp_adv_win_scale = 2;
@@ -1488,10 +1493,8 @@ tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
case TCP_CA_Disorder:
tcp_try_undo_dsack(sk, tp);
- if (IsReno(tp) || !tp->undo_marker) {
- tp->undo_marker = 0;
- tp->ca_state = TCP_CA_Open;
- }
+ tp->undo_marker = 0;
+ tp->ca_state = TCP_CA_Open;
break;
case TCP_CA_Recovery:
@@ -1819,7 +1822,9 @@ static int tcp_ack_update_window(struct sock *sk, struct tcp_opt *tp,
#ifdef TCP_DEBUG
if (before(tp->snd_una + tp->snd_wnd, tp->snd_nxt)) {
if (net_ratelimit())
- printk(KERN_DEBUG "TCP: peer shrinks window. Bad, what else can I say?\n");
+ printk(KERN_DEBUG "TCP: peer %u.%u.%u.%u:%u/%u shrinks window %u:%u:%u. Bad, what else can I say?\n",
+ NIPQUAD(sk->daddr), htons(sk->dport), sk->num,
+ tp->snd_una, tp->snd_wnd, tp->snd_nxt);
}
#endif
@@ -1948,7 +1953,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_opt *tp)
if (opsize < 2) /* "silly options" */
return;
if (opsize > length)
- break; /* don't parse partial options */
+ return; /* don't parse partial options */
switch(opcode) {
case TCPOPT_MSS:
if(opsize==TCPOLEN_MSS && th->syn) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 0c1e678ef..d2a79b4b1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -5,7 +5,7 @@
*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp_ipv4.c,v 1.212 2000/08/18 17:10:04 davem Exp $
+ * Version: $Id: tcp_ipv4.c,v 1.213 2000/09/18 05:59:48 davem Exp $
*
* IPv4 specific functions
*
@@ -82,21 +82,21 @@ void tcp_v4_send_check(struct sock *sk, struct tcphdr *th, int len,
* First half of the table is for sockets not in TIME_WAIT, second half
* is for TIME_WAIT sockets only.
*/
-struct tcp_ehash_bucket *tcp_ehash = NULL;
+struct tcp_ehash_bucket *tcp_ehash;
/* Ok, let's try this, I give up, we do need a local binding
* TCP hash as well as the others for fast bind/connect.
*/
-struct tcp_bind_hashbucket *tcp_bhash = NULL;
+struct tcp_bind_hashbucket *tcp_bhash;
-int tcp_bhash_size = 0;
-int tcp_ehash_size = 0;
+int tcp_bhash_size;
+int tcp_ehash_size;
/* All sockets in TCP_LISTEN state will be in here. This is the only table
* where wildcard'd TCP sockets can exist. Hash function here is just local
* port number.
*/
-struct sock *tcp_listening_hash[TCP_LHTABLE_SIZE] = { NULL, };
+struct sock *tcp_listening_hash[TCP_LHTABLE_SIZE];
char __tcp_clean_cacheline_pad[(SMP_CACHE_BYTES -
(((sizeof(void *) * (TCP_LHTABLE_SIZE + 2)) +
(sizeof(int) * 2)) % SMP_CACHE_BYTES))] = { 0, };
@@ -300,6 +300,7 @@ __inline__ void __tcp_put_port(struct sock *sk)
sk->bind_next->bind_pprev = sk->bind_pprev;
*(sk->bind_pprev) = sk->bind_next;
sk->prev = NULL;
+ sk->num = 0;
if (tb->owners == NULL) {
if (tb->next)
tb->next->pprev = tb->pprev;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ef7fc36cb..fea27faea 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -5,7 +5,7 @@
*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp_minisocks.c,v 1.1 2000/08/09 11:59:04 davem Exp $
+ * Version: $Id: tcp_minisocks.c,v 1.4 2000/09/18 05:59:48 davem Exp $
*
* Authors: Ross Biro, <bir7@leland.Stanford.Edu>
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
@@ -662,6 +662,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req,
sock_lock_init(newsk);
bh_lock_sock(newsk);
+ newsk->dst_lock = RW_LOCK_UNLOCKED;
atomic_set(&newsk->rmem_alloc, 0);
skb_queue_head_init(&newsk->receive_queue);
atomic_set(&newsk->wmem_alloc, 0);
@@ -671,8 +672,10 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req,
newsk->forward_alloc = 0;
newsk->done = 0;
+ newsk->userlocks = sk->userlocks & ~SOCK_BINDPORT_LOCK;
newsk->proc = 0;
newsk->backlog.head = newsk->backlog.tail = NULL;
+ newsk->callback_lock = RW_LOCK_UNLOCKED;
skb_queue_head_init(&newsk->error_queue);
newsk->write_space = tcp_write_space;
#ifdef CONFIG_FILTER
@@ -742,7 +745,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req,
/* Back to base struct sock members. */
newsk->err = 0;
newsk->priority = 0;
- atomic_set(&newsk->refcnt, 1);
+ atomic_set(&newsk->refcnt, 2);
#ifdef INET_REFCNT_DEBUG
atomic_inc(&inet_sock_nr);
#endif
@@ -966,5 +969,6 @@ int tcp_child_process(struct sock *parent, struct sock *child,
}
bh_unlock_sock(child);
+ sock_put(child);
return ret;
}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index d98376840..5e5af83c2 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -29,7 +29,7 @@ int sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES;
int sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL;
int sysctl_tcp_retries1 = TCP_RETR1;
int sysctl_tcp_retries2 = TCP_RETR2;
-int sysctl_tcp_orphan_retries = 0;
+int sysctl_tcp_orphan_retries;
static void tcp_write_timer(unsigned long);
static void tcp_delack_timer(unsigned long);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 59afc3cee..ff8a3d109 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -5,7 +5,7 @@
*
* The User Datagram Protocol (UDP).
*
- * Version: $Id: udp.c,v 1.85 2000/08/09 11:59:04 davem Exp $
+ * Version: $Id: udp.c,v 1.87 2000/09/20 02:11:34 davem Exp $
*
* Authors: Ross Biro, <bir7@leland.Stanford.Edu>
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
@@ -126,7 +126,7 @@ struct sock *udp_hash[UDP_HTABLE_SIZE];
rwlock_t udp_hash_lock = RW_LOCK_UNLOCKED;
/* Shared by v4/v6 udp. */
-int udp_port_rover = 0;
+int udp_port_rover;
static int udp_v4_get_port(struct sock *sk, unsigned short snum)
{
@@ -188,6 +188,15 @@ gotit:
}
}
sk->num = snum;
+ if (sk->pprev == NULL) {
+ struct sock **skp = &udp_hash[snum & (UDP_HTABLE_SIZE - 1)];
+ if ((sk->next = *skp) != NULL)
+ (*skp)->pprev = &sk->next;
+ *skp = sk;
+ sk->pprev = skp;
+ sock_prot_inc_use(sk->prot);
+ sock_hold(sk);
+ }
write_unlock_bh(&udp_hash_lock);
return 0;
@@ -198,16 +207,7 @@ fail:
static void udp_v4_hash(struct sock *sk)
{
- struct sock **skp = &udp_hash[sk->num & (UDP_HTABLE_SIZE - 1)];
-
- write_lock_bh(&udp_hash_lock);
- if ((sk->next = *skp) != NULL)
- (*skp)->pprev = &sk->next;
- *skp = sk;
- sk->pprev = skp;
- sock_prot_inc_use(sk->prot);
- sock_hold(sk);
- write_unlock_bh(&udp_hash_lock);
+ BUG();
}
static void udp_v4_unhash(struct sock *sk)
@@ -218,6 +218,7 @@ static void udp_v4_unhash(struct sock *sk)
sk->next->pprev = sk->pprev;
*sk->pprev = sk->next;
sk->pprev = NULL;
+ sk->num = 0;
sock_prot_dec_use(sk->prot);
__sock_put(sk);
}
@@ -493,8 +494,6 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, int len)
if (usin->sin_family != AF_INET) {
if (usin->sin_family != AF_UNSPEC)
return -EINVAL;
- if (net_ratelimit())
- printk("Remind Kuznetsov, he has to repair %s eventually\n", current->comm);
}
ufh.daddr = usin->sin_addr.s_addr;
@@ -678,6 +677,8 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, int len,
if (flags & MSG_ERRQUEUE)
return ip_recv_error(sk, msg, len);
+
+ retry:
/*
* From here the generic datagram does a lot of the work. Come
* the finished NET3, it will do _ALL_ the work!
@@ -733,26 +734,21 @@ out:
csum_copy_err:
UDP_INC_STATS_BH(UdpInErrors);
- /* Clear queue. */
- if (flags&MSG_PEEK) {
- int clear = 0;
+ if (flags&(MSG_PEEK|MSG_DONTWAIT)) {
+ struct sk_buff *skb2;
+
spin_lock_irq(&sk->receive_queue.lock);
- if (skb == skb_peek(&sk->receive_queue)) {
+ skb2 = skb_peek(&sk->receive_queue);
+ if ((flags & MSG_PEEK) && skb == skb2) {
__skb_unlink(skb, &sk->receive_queue);
- clear = 1;
}
spin_unlock_irq(&sk->receive_queue.lock);
- if (clear)
- kfree_skb(skb);
- }
-
- skb_free_datagram(sk, skb);
-
- /*
- * Error for blocking case is chosen to masquerade
- * as some normal condition.
- */
- return (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH;
+ skb_free_datagram(sk, skb);
+ if ((flags & MSG_DONTWAIT) && !skb2)
+ return -EAGAIN;
+ } else
+ skb_free_datagram(sk, skb);
+ goto retry;
}
int udp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
@@ -797,10 +793,21 @@ int udp_disconnect(struct sock *sk, int flags)
*/
sk->state = TCP_CLOSE;
- sk->rcv_saddr = 0;
sk->daddr = 0;
sk->dport = 0;
sk->bound_dev_if = 0;
+ if (!(sk->userlocks&SOCK_BINDADDR_LOCK)) {
+ sk->rcv_saddr = 0;
+ sk->saddr = 0;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ memset(&sk->net_pinfo.af_inet6.saddr, 0, 16);
+ memset(&sk->net_pinfo.af_inet6.rcv_saddr, 0, 16);
+#endif
+ }
+ if (!(sk->userlocks&SOCK_BINDPORT_LOCK)) {
+ sk->prot->unhash(sk);
+ sk->sport = 0;
+ }
sk_dst_reset(sk);
return 0;
}
diff --git a/net/ipv4/utils.c b/net/ipv4/utils.c
index 5992cbc55..c6494d87f 100644
--- a/net/ipv4/utils.c
+++ b/net/ipv4/utils.c
@@ -57,12 +57,6 @@ char *in_ntoa(__u32 in)
return(buff);
}
-char *in_ntoa2(__u32 in, char *buff)
-{
- sprintf(buff, "%d.%d.%d.%d", NIPQUAD(in));
- return buff;
-}
-
/*
* Convert an ASCII string to binary IP.
*/
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-10 02:49:08 +0000