*
* PF_INET protocol family socket handler.
*
- * Version: $Id: af_inet.c,v 1.137 2002/02/01 22:01:03 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Florian La Roche, <flla@stud.uni-sb.de>
#include <asm/uaccess.h>
#include <asm/system.h>
-#include <linux/smp_lock.h>
#include <linux/inet.h>
#include <linux/igmp.h>
#include <linux/inetdevice.h>
#include <net/ipip.h>
#include <net/inet_common.h>
#include <net/xfrm.h>
+#include <net/net_namespace.h>
#ifdef CONFIG_IP_MROUTE
#include <linux/mroute.h>
#endif
-DEFINE_SNMP_STAT(struct linux_mib, net_statistics) __read_mostly;
-
extern void ip_mc_drop_socket(struct sock *sk);
/* The inetsw table contains everything that inet_create needs to
static struct list_head inetsw[SOCK_MAX];
static DEFINE_SPINLOCK(inetsw_lock);
+struct ipv4_config ipv4_config;
+
+EXPORT_SYMBOL(ipv4_config);
+
/* New destruction routine */
void inet_sock_destruct(struct sock *sk)
__skb_queue_purge(&sk->sk_receive_queue);
__skb_queue_purge(&sk->sk_error_queue);
+ sk_mem_reclaim(sk);
+
if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) {
printk("Attempt to release TCP socket in state %d %p\n",
sk->sk_state, sk);
return;
}
- BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc));
- BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc));
- BUG_TRAP(!sk->sk_wmem_queued);
- BUG_TRAP(!sk->sk_forward_alloc);
+ WARN_ON(atomic_read(&sk->sk_rmem_alloc));
+ WARN_ON(atomic_read(&sk->sk_wmem_alloc));
+ WARN_ON(sk->sk_wmem_queued);
+ WARN_ON(sk->sk_forward_alloc);
kfree(inet->opt);
dst_release(sk->sk_dst_cache);
}
EXPORT_SYMBOL(build_ehash_secret);
+static inline int inet_netns_ok(struct net *net, int protocol)
+{
+ int hash;
+ struct net_protocol *ipprot;
+
+ if (net == &init_net)
+ return 1;
+
+ hash = protocol & (MAX_INET_PROTOS - 1);
+ ipprot = rcu_dereference(inet_protos[hash]);
+
+ if (ipprot == NULL)
+ /* raw IP is OK */
+ return 1;
+ return ipprot->netns_ok;
+}
+
/*
* Create an inet socket.
*/
-static int inet_create(struct socket *sock, int protocol)
+static int inet_create(struct net *net, struct socket *sock, int protocol)
{
struct sock *sk;
- struct list_head *p;
struct inet_protosw *answer;
struct inet_sock *inet;
struct proto *answer_prot;
sock->state = SS_UNCONNECTED;
/* Look for the requested type/protocol pair. */
- answer = NULL;
lookup_protocol:
err = -ESOCKTNOSUPPORT;
rcu_read_lock();
- list_for_each_rcu(p, &inetsw[sock->type]) {
- answer = list_entry(p, struct inet_protosw, list);
+ list_for_each_entry_rcu(answer, &inetsw[sock->type], list) {
+ err = 0;
/* Check the non-wild match. */
if (protocol == answer->protocol) {
if (protocol != IPPROTO_IP)
break;
}
err = -EPROTONOSUPPORT;
- answer = NULL;
}
- if (unlikely(answer == NULL)) {
+ if (unlikely(err)) {
if (try_loading_module < 2) {
rcu_read_unlock();
/*
if (answer->capability > 0 && !capable(answer->capability))
goto out_rcu_unlock;
+ err = -EAFNOSUPPORT;
+ if (!inet_netns_ok(net, protocol))
+ goto out_rcu_unlock;
+
sock->ops = answer->ops;
answer_prot = answer->prot;
answer_no_check = answer->no_check;
answer_flags = answer->flags;
rcu_read_unlock();
- BUG_TRAP(answer_prot->slab != NULL);
+ WARN_ON(answer_prot->slab == NULL);
err = -ENOBUFS;
- sk = sk_alloc(PF_INET, GFP_KERNEL, answer_prot, 1);
+ sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
if (sk == NULL)
goto out;
if (addr_len < sizeof(struct sockaddr_in))
goto out;
- chk_addr_ret = inet_addr_type(addr->sin_addr.s_addr);
+ chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
/* Not specified by any standard per-se, however it breaks too
* many applications when removed. It is unfortunate since
*/
err = -EADDRNOTAVAIL;
if (!sysctl_ip_nonlocal_bind &&
- !inet->freebind &&
- addr->sin_addr.s_addr != INADDR_ANY &&
+ !(inet->freebind || inet->transparent) &&
+ addr->sin_addr.s_addr != htonl(INADDR_ANY) &&
chk_addr_ret != RTN_LOCAL &&
chk_addr_ret != RTN_MULTICAST &&
chk_addr_ret != RTN_BROADCAST)
lock_sock(sk2);
- BUG_TRAP((1 << sk2->sk_state) &
- (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE));
+ WARN_ON(!((1 << sk2->sk_state) &
+ (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE)));
sock_graft(sk2, newsock);
{
struct sock *sk = sock->sk;
int err = 0;
+ struct net *net = sock_net(sk);
switch (cmd) {
case SIOCGSTAMP:
case SIOCADDRT:
case SIOCDELRT:
case SIOCRTMSG:
- err = ip_rt_ioctl(cmd, (void __user *)arg);
+ err = ip_rt_ioctl(net, cmd, (void __user *)arg);
break;
case SIOCDARP:
case SIOCGARP:
case SIOCSARP:
- err = arp_ioctl(cmd, (void __user *)arg);
+ err = arp_ioctl(net, cmd, (void __user *)arg);
break;
case SIOCGIFADDR:
case SIOCSIFADDR:
case SIOCSIFPFLAGS:
case SIOCGIFPFLAGS:
case SIOCSIFFLAGS:
- err = devinet_ioctl(cmd, (void __user *)arg);
+ err = devinet_ioctl(net, cmd, (void __user *)arg);
break;
default:
if (sk->sk_prot->ioctl)
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
- .sendmsg = inet_sendmsg,
+ .sendmsg = tcp_sendmsg,
.recvmsg = sock_common_recvmsg,
.mmap = sock_no_mmap,
.sendpage = tcp_sendpage,
+ .splice_read = tcp_splice_read,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_sock_common_setsockopt,
.compat_getsockopt = compat_sock_common_getsockopt,
}
};
-#define INETSW_ARRAY_LEN (sizeof(inetsw_array) / sizeof(struct inet_protosw))
+#define INETSW_ARRAY_LEN ARRAY_SIZE(inetsw_array)
void inet_register_protosw(struct inet_protosw *p)
{
if (sysctl_ip_dynaddr > 1) {
printk(KERN_INFO "%s(): shifting inet->"
- "saddr from %d.%d.%d.%d to %d.%d.%d.%d\n",
- __FUNCTION__,
+ "saddr from " NIPQUAD_FMT " to " NIPQUAD_FMT "\n",
+ __func__,
NIPQUAD(old_saddr),
NIPQUAD(new_saddr));
}
},
},
.proto = sk->sk_protocol,
+ .flags = inet_sk_flowi_flags(sk),
.uli_u = {
.ports = {
.sport = inet->sport,
};
security_sk_classify_flow(sk, &fl);
- err = ip_route_output_flow(&rt, &fl, sk, 0);
+ err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0);
}
if (!err)
sk_setup_caps(sk, &rt->u.dst);
int ihl;
int id;
+ if (!(features & NETIF_F_V4_CSUM))
+ features &= ~NETIF_F_SG;
+
if (unlikely(skb_shinfo(skb)->gso_type &
~(SKB_GSO_TCPV4 |
SKB_GSO_UDP |
segs = ops->gso_segment(skb, features);
rcu_read_unlock();
- if (!segs || unlikely(IS_ERR(segs)))
+ if (!segs || IS_ERR(segs))
goto out;
skb = segs;
return segs;
}
+int inet_ctl_sock_create(struct sock **sk, unsigned short family,
+ unsigned short type, unsigned char protocol,
+ struct net *net)
+{
+ struct socket *sock;
+ int rc = sock_create_kern(family, type, protocol, &sock);
+
+ if (rc == 0) {
+ *sk = sock->sk;
+ (*sk)->sk_allocation = GFP_ATOMIC;
+ /*
+ * Unhash it so that IP input processing does not even see it,
+ * we do not wish this socket to see incoming packets.
+ */
+ (*sk)->sk_prot->unhash(*sk);
+
+ sk_change_net(*sk, net);
+ }
+ return rc;
+}
+
+EXPORT_SYMBOL_GPL(inet_ctl_sock_create);
+
unsigned long snmp_fold_field(void *mib[], int offt)
{
unsigned long res = 0;
}
EXPORT_SYMBOL_GPL(snmp_fold_field);
-int snmp_mib_init(void *ptr[2], size_t mibsize, size_t mibalign)
+int snmp_mib_init(void *ptr[2], size_t mibsize)
{
BUG_ON(ptr == NULL);
ptr[0] = __alloc_percpu(mibsize);
.gso_send_check = tcp_v4_gso_send_check,
.gso_segment = tcp_tso_segment,
.no_policy = 1,
+ .netns_ok = 1,
};
static struct net_protocol udp_protocol = {
.handler = udp_rcv,
.err_handler = udp_err,
.no_policy = 1,
+ .netns_ok = 1,
};
static struct net_protocol icmp_protocol = {
.handler = icmp_rcv,
+ .no_policy = 1,
+ .netns_ok = 1,
};
-static int __init init_ipv4_mibs(void)
+static __net_init int ipv4_mib_init_net(struct net *net)
{
- if (snmp_mib_init((void **)net_statistics,
- sizeof(struct linux_mib),
- __alignof__(struct linux_mib)) < 0)
- goto err_net_mib;
- if (snmp_mib_init((void **)ip_statistics,
- sizeof(struct ipstats_mib),
- __alignof__(struct ipstats_mib)) < 0)
- goto err_ip_mib;
- if (snmp_mib_init((void **)icmp_statistics,
- sizeof(struct icmp_mib),
- __alignof__(struct icmp_mib)) < 0)
- goto err_icmp_mib;
- if (snmp_mib_init((void **)tcp_statistics,
- sizeof(struct tcp_mib),
- __alignof__(struct tcp_mib)) < 0)
+ if (snmp_mib_init((void **)net->mib.tcp_statistics,
+ sizeof(struct tcp_mib)) < 0)
goto err_tcp_mib;
- if (snmp_mib_init((void **)udp_statistics,
- sizeof(struct udp_mib),
- __alignof__(struct udp_mib)) < 0)
+ if (snmp_mib_init((void **)net->mib.ip_statistics,
+ sizeof(struct ipstats_mib)) < 0)
+ goto err_ip_mib;
+ if (snmp_mib_init((void **)net->mib.net_statistics,
+ sizeof(struct linux_mib)) < 0)
+ goto err_net_mib;
+ if (snmp_mib_init((void **)net->mib.udp_statistics,
+ sizeof(struct udp_mib)) < 0)
goto err_udp_mib;
- if (snmp_mib_init((void **)udplite_statistics,
- sizeof(struct udp_mib),
- __alignof__(struct udp_mib)) < 0)
+ if (snmp_mib_init((void **)net->mib.udplite_statistics,
+ sizeof(struct udp_mib)) < 0)
goto err_udplite_mib;
+ if (snmp_mib_init((void **)net->mib.icmp_statistics,
+ sizeof(struct icmp_mib)) < 0)
+ goto err_icmp_mib;
+ if (snmp_mib_init((void **)net->mib.icmpmsg_statistics,
+ sizeof(struct icmpmsg_mib)) < 0)
+ goto err_icmpmsg_mib;
- tcp_mib_init();
-
+ tcp_mib_init(net);
return 0;
+err_icmpmsg_mib:
+ snmp_mib_free((void **)net->mib.icmp_statistics);
+err_icmp_mib:
+ snmp_mib_free((void **)net->mib.udplite_statistics);
err_udplite_mib:
- snmp_mib_free((void **)udp_statistics);
+ snmp_mib_free((void **)net->mib.udp_statistics);
err_udp_mib:
- snmp_mib_free((void **)tcp_statistics);
-err_tcp_mib:
- snmp_mib_free((void **)icmp_statistics);
-err_icmp_mib:
- snmp_mib_free((void **)ip_statistics);
-err_ip_mib:
- snmp_mib_free((void **)net_statistics);
+ snmp_mib_free((void **)net->mib.net_statistics);
err_net_mib:
+ snmp_mib_free((void **)net->mib.ip_statistics);
+err_ip_mib:
+ snmp_mib_free((void **)net->mib.tcp_statistics);
+err_tcp_mib:
return -ENOMEM;
}
+static __net_exit void ipv4_mib_exit_net(struct net *net)
+{
+ snmp_mib_free((void **)net->mib.icmpmsg_statistics);
+ snmp_mib_free((void **)net->mib.icmp_statistics);
+ snmp_mib_free((void **)net->mib.udplite_statistics);
+ snmp_mib_free((void **)net->mib.udp_statistics);
+ snmp_mib_free((void **)net->mib.net_statistics);
+ snmp_mib_free((void **)net->mib.ip_statistics);
+ snmp_mib_free((void **)net->mib.tcp_statistics);
+}
+
+static __net_initdata struct pernet_operations ipv4_mib_ops = {
+ .init = ipv4_mib_init_net,
+ .exit = ipv4_mib_exit_net,
+};
+
+static int __init init_ipv4_mibs(void)
+{
+ return register_pernet_subsys(&ipv4_mib_ops);
+}
+
static int ipv4_proc_init(void);
/*
(void)sock_register(&inet_family_ops);
+#ifdef CONFIG_SYSCTL
+ ip_static_sysctl_init();
+#endif
+
/*
* Add all the base protocols.
*/
ip_init();
- tcp_v4_init(&inet_family_ops);
+ tcp_v4_init();
/* Setup TCP slab cache for open requests. */
tcp_init();
+ /* Setup UDP memory threshold */
+ udp_init();
+
/* Add UDP-Lite (RFC 3828) */
udplite4_register();
* Set the ICMP layer up
*/
- icmp_init(&inet_family_ops);
+ if (icmp_init() < 0)
+ panic("Failed to create the ICMP control socket.\n");
/*
* Initialise the multicast router
*/
#if defined(CONFIG_IP_MROUTE)
- ip_mr_init();
+ if (ip_mr_init())
+ printk(KERN_CRIT "inet_init: Cannot init ipv4 mroute\n");
#endif
/*
* Initialise per-cpu ipv4 mibs
*/
if (init_ipv4_mibs())
- printk(KERN_CRIT "inet_init: Cannot init ipv4 mibs\n"); ;
+ printk(KERN_CRIT "inet_init: Cannot init ipv4 mibs\n");
ipv4_proc_init();
goto out_tcp;
if (udp4_proc_init())
goto out_udp;
- if (fib_proc_init())
- goto out_fib;
if (ip_misc_proc_init())
goto out_misc;
out:
return rc;
out_misc:
- fib_proc_exit();
-out_fib:
udp4_proc_exit();
out_udp:
tcp4_proc_exit();
EXPORT_SYMBOL(inet_stream_connect);
EXPORT_SYMBOL(inet_stream_ops);
EXPORT_SYMBOL(inet_unregister_protosw);
-EXPORT_SYMBOL(net_statistics);
EXPORT_SYMBOL(sysctl_ip_nonlocal_bind);
Code Review / linux-2.6.git / blobdiff