*
* 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>
* 2 of the License, or (at your option) any later version.
*/
-#include <linux/config.h>
+#include <linux/err.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
+#include <linux/capability.h>
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/netfilter_ipv4.h>
+#include <linux/random.h>
#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 <linux/netdevice.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/inet_connection_sock.h>
#include <net/tcp.h>
#include <net/udp.h>
+#include <net/udplite.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/raw.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);
-
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);
- if (inet->opt)
- kfree(inet->opt);
+ kfree(inet->opt);
dst_release(sk->sk_dst_cache);
sk_refcnt_debug_dec(sk);
}
* we can only allow the backlog to be adjusted.
*/
if (old_state != TCP_LISTEN) {
- err = inet_csk_listen_start(sk, TCP_SYNQ_HSIZE);
+ err = inet_csk_listen_start(sk, backlog);
if (err)
goto out;
}
return err;
}
+u32 inet_ehash_secret __read_mostly;
+EXPORT_SYMBOL(inet_ehash_secret);
+
+/*
+ * inet_ehash_secret must be set exactly once
+ * Instead of using a dedicated spinlock, we (ab)use inetsw_lock
+ */
+void build_ehash_secret(void)
+{
+ u32 rnd;
+ do {
+ get_random_bytes(&rnd, sizeof(rnd));
+ } while (rnd == 0);
+ spin_lock_bh(&inetsw_lock);
+ if (!inet_ehash_secret)
+ inet_ehash_secret = rnd;
+ spin_unlock_bh(&inetsw_lock);
+}
+EXPORT_SYMBOL(build_ehash_secret);
+
+static inline int inet_netns_ok(struct net *net, int protocol)
+{
+ int hash;
+ struct net_protocol *ipprot;
+
+ if (net_eq(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;
unsigned char answer_flags;
char answer_no_check;
int try_loading_module = 0;
- int err = -ESOCKTNOSUPPORT;
+ int err;
+
+ if (unlikely(!inet_ehash_secret))
+ if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
+ build_ehash_secret();
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)
if (IPPROTO_IP == answer->protocol)
break;
}
- answer = NULL;
+ err = -EPROTONOSUPPORT;
}
- if (unlikely(answer == NULL)) {
+ if (unlikely(err)) {
if (try_loading_module < 2) {
rcu_read_unlock();
/*
err = -EPERM;
if (answer->capability > 0 && !capable(answer->capability))
goto out_rcu_unlock;
- err = -EPROTONOSUPPORT;
- if (!protocol)
+
+ err = -EAFNOSUPPORT;
+ if (!inet_netns_ok(net, protocol))
goto out_rcu_unlock;
sock->ops = answer->ops;
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;
sk->sk_reuse = 1;
inet = inet_sk(sk);
+ inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
if (SOCK_RAW == sock->type) {
inet->num = protocol;
}
/* It is off by default, see below. */
-int sysctl_ip_nonlocal_bind;
+int sysctl_ip_nonlocal_bind __read_mostly;
int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
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)
if (err < 0)
goto out;
- sock->state = SS_CONNECTING;
+ sock->state = SS_CONNECTING;
/* Just entered SS_CONNECTING state; the only
* difference is that return value in non-blocking
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);
sin->sin_port = inet->dport;
sin->sin_addr.s_addr = inet->daddr;
} else {
- __u32 addr = inet->rcv_saddr;
+ __be32 addr = inet->rcv_saddr;
if (!addr)
addr = inet->saddr;
sin->sin_port = inet->sport;
{
struct sock *sk = sock->sk;
int err = 0;
+ struct net *net = sock_net(sk);
switch (cmd) {
case SIOCGSTAMP:
err = sock_get_timestamp(sk, (struct timeval __user *)arg);
break;
+ case SIOCGSTAMPNS:
+ err = sock_get_timestampns(sk, (struct timespec __user *)arg);
+ break;
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 ||
- (err = sk->sk_prot->ioctl(sk, cmd, arg)) ==
- -ENOIOCTLCMD)
- err = dev_ioctl(cmd, (void __user *)arg);
+ if (sk->sk_prot->ioctl)
+ err = sk->sk_prot->ioctl(sk, cmd, arg);
+ else
+ err = -ENOIOCTLCMD;
break;
}
return err;
}
-struct proto_ops inet_stream_ops = {
- .family = PF_INET,
- .owner = THIS_MODULE,
- .release = inet_release,
- .bind = inet_bind,
- .connect = inet_stream_connect,
- .socketpair = sock_no_socketpair,
- .accept = inet_accept,
- .getname = inet_getname,
- .poll = tcp_poll,
- .ioctl = inet_ioctl,
- .listen = inet_listen,
- .shutdown = inet_shutdown,
- .setsockopt = sock_common_setsockopt,
- .getsockopt = sock_common_getsockopt,
- .sendmsg = inet_sendmsg,
- .recvmsg = sock_common_recvmsg,
- .mmap = sock_no_mmap,
- .sendpage = tcp_sendpage
+const struct proto_ops inet_stream_ops = {
+ .family = PF_INET,
+ .owner = THIS_MODULE,
+ .release = inet_release,
+ .bind = inet_bind,
+ .connect = inet_stream_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = inet_accept,
+ .getname = inet_getname,
+ .poll = tcp_poll,
+ .ioctl = inet_ioctl,
+ .listen = inet_listen,
+ .shutdown = inet_shutdown,
+ .setsockopt = sock_common_setsockopt,
+ .getsockopt = sock_common_getsockopt,
+ .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,
+#endif
};
-struct proto_ops inet_dgram_ops = {
- .family = PF_INET,
- .owner = THIS_MODULE,
- .release = inet_release,
- .bind = inet_bind,
- .connect = inet_dgram_connect,
- .socketpair = sock_no_socketpair,
- .accept = sock_no_accept,
- .getname = inet_getname,
- .poll = udp_poll,
- .ioctl = inet_ioctl,
- .listen = sock_no_listen,
- .shutdown = inet_shutdown,
- .setsockopt = sock_common_setsockopt,
- .getsockopt = sock_common_getsockopt,
- .sendmsg = inet_sendmsg,
- .recvmsg = sock_common_recvmsg,
- .mmap = sock_no_mmap,
- .sendpage = inet_sendpage,
+const struct proto_ops inet_dgram_ops = {
+ .family = PF_INET,
+ .owner = THIS_MODULE,
+ .release = inet_release,
+ .bind = inet_bind,
+ .connect = inet_dgram_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = inet_getname,
+ .poll = udp_poll,
+ .ioctl = inet_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = inet_shutdown,
+ .setsockopt = sock_common_setsockopt,
+ .getsockopt = sock_common_getsockopt,
+ .sendmsg = inet_sendmsg,
+ .recvmsg = sock_common_recvmsg,
+ .mmap = sock_no_mmap,
+ .sendpage = inet_sendpage,
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_sock_common_setsockopt,
+ .compat_getsockopt = compat_sock_common_getsockopt,
+#endif
};
/*
* For SOCK_RAW sockets; should be the same as inet_dgram_ops but without
* udp_poll
*/
-static struct proto_ops inet_sockraw_ops = {
- .family = PF_INET,
- .owner = THIS_MODULE,
- .release = inet_release,
- .bind = inet_bind,
- .connect = inet_dgram_connect,
- .socketpair = sock_no_socketpair,
- .accept = sock_no_accept,
- .getname = inet_getname,
- .poll = datagram_poll,
- .ioctl = inet_ioctl,
- .listen = sock_no_listen,
- .shutdown = inet_shutdown,
- .setsockopt = sock_common_setsockopt,
- .getsockopt = sock_common_getsockopt,
- .sendmsg = inet_sendmsg,
- .recvmsg = sock_common_recvmsg,
- .mmap = sock_no_mmap,
- .sendpage = inet_sendpage,
+static const struct proto_ops inet_sockraw_ops = {
+ .family = PF_INET,
+ .owner = THIS_MODULE,
+ .release = inet_release,
+ .bind = inet_bind,
+ .connect = inet_dgram_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = inet_getname,
+ .poll = datagram_poll,
+ .ioctl = inet_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = inet_shutdown,
+ .setsockopt = sock_common_setsockopt,
+ .getsockopt = sock_common_getsockopt,
+ .sendmsg = inet_sendmsg,
+ .recvmsg = sock_common_recvmsg,
+ .mmap = sock_no_mmap,
+ .sendpage = inet_sendpage,
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_sock_common_setsockopt,
+ .compat_getsockopt = compat_sock_common_getsockopt,
+#endif
};
static struct net_proto_family inet_family_ops = {
.owner = THIS_MODULE,
};
-
-extern void tcp_init(void);
-extern void tcp_v4_init(struct net_proto_family *);
-
/* Upon startup we insert all the elements in inetsw_array[] into
* the linked list inetsw.
*/
static struct inet_protosw inetsw_array[] =
{
- {
- .type = SOCK_STREAM,
- .protocol = IPPROTO_TCP,
- .prot = &tcp_prot,
- .ops = &inet_stream_ops,
- .capability = -1,
- .no_check = 0,
- .flags = INET_PROTOSW_PERMANENT,
- },
-
- {
- .type = SOCK_DGRAM,
- .protocol = IPPROTO_UDP,
- .prot = &udp_prot,
- .ops = &inet_dgram_ops,
- .capability = -1,
- .no_check = UDP_CSUM_DEFAULT,
- .flags = INET_PROTOSW_PERMANENT,
+ {
+ .type = SOCK_STREAM,
+ .protocol = IPPROTO_TCP,
+ .prot = &tcp_prot,
+ .ops = &inet_stream_ops,
+ .capability = -1,
+ .no_check = 0,
+ .flags = INET_PROTOSW_PERMANENT |
+ INET_PROTOSW_ICSK,
+ },
+
+ {
+ .type = SOCK_DGRAM,
+ .protocol = IPPROTO_UDP,
+ .prot = &udp_prot,
+ .ops = &inet_dgram_ops,
+ .capability = -1,
+ .no_check = UDP_CSUM_DEFAULT,
+ .flags = INET_PROTOSW_PERMANENT,
},
-
+
{
- .type = SOCK_RAW,
- .protocol = IPPROTO_IP, /* wild card */
- .prot = &raw_prot,
- .ops = &inet_sockraw_ops,
- .capability = CAP_NET_RAW,
- .no_check = UDP_CSUM_DEFAULT,
- .flags = INET_PROTOSW_REUSE,
+ .type = SOCK_RAW,
+ .protocol = IPPROTO_IP, /* wild card */
+ .prot = &raw_prot,
+ .ops = &inet_sockraw_ops,
+ .capability = CAP_NET_RAW,
+ .no_check = UDP_CSUM_DEFAULT,
+ .flags = INET_PROTOSW_REUSE,
}
};
-#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)
{
/* Add the new entry after the last permanent entry if any, so that
* the new entry does not override a permanent entry when matched with
* a wild-card protocol. But it is allowed to override any existing
- * non-permanent entry. This means that when we remove this entry, the
+ * non-permanent entry. This means that when we remove this entry, the
* system automatically returns to the old behavior.
*/
list_add_rcu(&p->list, last_perm);
* Shall we try to damage output packets if routing dev changes?
*/
-int sysctl_ip_dynaddr;
+int sysctl_ip_dynaddr __read_mostly;
static int inet_sk_reselect_saddr(struct sock *sk)
{
struct inet_sock *inet = inet_sk(sk);
int err;
struct rtable *rt;
- __u32 old_saddr = inet->saddr;
- __u32 new_saddr;
- __u32 daddr = inet->daddr;
+ __be32 old_saddr = inet->saddr;
+ __be32 new_saddr;
+ __be32 daddr = inet->daddr;
if (inet->opt && inet->opt->srr)
daddr = inet->opt->faddr;
RT_CONN_FLAGS(sk),
sk->sk_bound_dev_if,
sk->sk_protocol,
- inet->sport, inet->dport, sk);
+ inet->sport, inet->dport, sk, 0);
if (err)
return err;
return 0;
if (sysctl_ip_dynaddr > 1) {
- printk(KERN_INFO "%s(): shifting inet->"
- "saddr from %d.%d.%d.%d to %d.%d.%d.%d\n",
- __FUNCTION__,
- NIPQUAD(old_saddr),
- NIPQUAD(new_saddr));
+ printk(KERN_INFO "%s(): shifting inet->saddr from %pI4 to %pI4\n",
+ __func__, &old_saddr, &new_saddr);
}
inet->saddr = inet->rcv_saddr = new_saddr;
{
struct inet_sock *inet = inet_sk(sk);
struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0);
- u32 daddr;
+ __be32 daddr;
int err;
/* Route is OK, nothing to do. */
},
},
.proto = sk->sk_protocol,
+ .flags = inet_sk_flowi_flags(sk),
.uli_u = {
.ports = {
.sport = inet->sport,
},
},
};
-
- err = ip_route_output_flow(&rt, &fl, sk, 0);
+
+ security_sk_classify_flow(sk, &fl);
+ err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0);
}
if (!err)
sk_setup_caps(sk, &rt->u.dst);
EXPORT_SYMBOL(inet_sk_rebuild_header);
+static int inet_gso_send_check(struct sk_buff *skb)
+{
+ struct iphdr *iph;
+ struct net_protocol *ops;
+ int proto;
+ int ihl;
+ int err = -EINVAL;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
+ goto out;
+
+ iph = ip_hdr(skb);
+ ihl = iph->ihl * 4;
+ if (ihl < sizeof(*iph))
+ goto out;
+
+ if (unlikely(!pskb_may_pull(skb, ihl)))
+ goto out;
+
+ __skb_pull(skb, ihl);
+ skb_reset_transport_header(skb);
+ iph = ip_hdr(skb);
+ proto = iph->protocol & (MAX_INET_PROTOS - 1);
+ err = -EPROTONOSUPPORT;
+
+ rcu_read_lock();
+ ops = rcu_dereference(inet_protos[proto]);
+ if (likely(ops && ops->gso_send_check))
+ err = ops->gso_send_check(skb);
+ rcu_read_unlock();
+
+out:
+ return err;
+}
+
+static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
+{
+ struct sk_buff *segs = ERR_PTR(-EINVAL);
+ struct iphdr *iph;
+ struct net_protocol *ops;
+ int proto;
+ 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 |
+ SKB_GSO_DODGY |
+ SKB_GSO_TCP_ECN |
+ 0)))
+ goto out;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
+ goto out;
+
+ iph = ip_hdr(skb);
+ ihl = iph->ihl * 4;
+ if (ihl < sizeof(*iph))
+ goto out;
+
+ if (unlikely(!pskb_may_pull(skb, ihl)))
+ goto out;
+
+ __skb_pull(skb, ihl);
+ skb_reset_transport_header(skb);
+ iph = ip_hdr(skb);
+ id = ntohs(iph->id);
+ proto = iph->protocol & (MAX_INET_PROTOS - 1);
+ segs = ERR_PTR(-EPROTONOSUPPORT);
+
+ rcu_read_lock();
+ ops = rcu_dereference(inet_protos[proto]);
+ if (likely(ops && ops->gso_segment))
+ segs = ops->gso_segment(skb, features);
+ rcu_read_unlock();
+
+ if (!segs || IS_ERR(segs))
+ goto out;
+
+ skb = segs;
+ do {
+ iph = ip_hdr(skb);
+ iph->id = htons(id++);
+ iph->tot_len = htons(skb->len - skb->mac_len);
+ iph->check = 0;
+ iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl);
+ } while ((skb = skb->next));
+
+out:
+ 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;
+ int i;
+
+ for_each_possible_cpu(i) {
+ res += *(((unsigned long *) per_cpu_ptr(mib[0], i)) + offt);
+ res += *(((unsigned long *) per_cpu_ptr(mib[1], i)) + offt);
+ }
+ return res;
+}
+EXPORT_SYMBOL_GPL(snmp_fold_field);
+
+int snmp_mib_init(void *ptr[2], size_t mibsize)
+{
+ BUG_ON(ptr == NULL);
+ ptr[0] = __alloc_percpu(mibsize);
+ if (!ptr[0])
+ goto err0;
+ ptr[1] = __alloc_percpu(mibsize);
+ if (!ptr[1])
+ goto err1;
+ return 0;
+err1:
+ free_percpu(ptr[0]);
+ ptr[0] = NULL;
+err0:
+ return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(snmp_mib_init);
+
+void snmp_mib_free(void *ptr[2])
+{
+ BUG_ON(ptr == NULL);
+ free_percpu(ptr[0]);
+ free_percpu(ptr[1]);
+ ptr[0] = ptr[1] = NULL;
+}
+EXPORT_SYMBOL_GPL(snmp_mib_free);
+
#ifdef CONFIG_IP_MULTICAST
static struct net_protocol igmp_protocol = {
.handler = igmp_rcv,
static struct net_protocol tcp_protocol = {
.handler = tcp_v4_rcv,
.err_handler = tcp_v4_err,
+ .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)
{
- net_statistics[0] = alloc_percpu(struct linux_mib);
- net_statistics[1] = alloc_percpu(struct linux_mib);
- ip_statistics[0] = alloc_percpu(struct ipstats_mib);
- ip_statistics[1] = alloc_percpu(struct ipstats_mib);
- icmp_statistics[0] = alloc_percpu(struct icmp_mib);
- icmp_statistics[1] = alloc_percpu(struct icmp_mib);
- tcp_statistics[0] = alloc_percpu(struct tcp_mib);
- tcp_statistics[1] = alloc_percpu(struct tcp_mib);
- udp_statistics[0] = alloc_percpu(struct udp_mib);
- udp_statistics[1] = alloc_percpu(struct udp_mib);
- if (!
- (net_statistics[0] && net_statistics[1] && ip_statistics[0]
- && ip_statistics[1] && tcp_statistics[0] && tcp_statistics[1]
- && udp_statistics[0] && udp_statistics[1]))
- return -ENOMEM;
-
- (void) tcp_mib_init();
-
+ if (snmp_mib_init((void **)net->mib.tcp_statistics,
+ sizeof(struct tcp_mib)) < 0)
+ goto err_tcp_mib;
+ 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 **)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(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 **)net->mib.udp_statistics);
+err_udp_mib:
+ 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);
-extern void ipfrag_init(void);
/*
* IP protocol layer initialiser
static struct packet_type ip_packet_type = {
.type = __constant_htons(ETH_P_IP),
.func = ip_rcv,
+ .gso_send_check = inet_gso_send_check,
+ .gso_segment = inet_gso_segment,
};
static int __init inet_init(void)
struct list_head *r;
int rc = -EINVAL;
- if (sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb)) {
- printk(KERN_CRIT "%s: panic\n", __FUNCTION__);
- goto out;
- }
+ BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb));
rc = proto_register(&tcp_prot, 1);
if (rc)
goto out_unregister_udp_proto;
/*
- * Tell SOCKET that we are alive...
+ * Tell SOCKET that we are alive...
*/
- (void)sock_register(&inet_family_ops);
+ (void)sock_register(&inet_family_ops);
+
+#ifdef CONFIG_SYSCTL
+ ip_static_sysctl_init();
+#endif
/*
* Add all the base protocols.
arp_init();
- /*
- * Set the IP module up
- */
+ /*
+ * Set the IP module up
+ */
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");
- if(init_ipv4_mibs())
- printk(KERN_CRIT "inet_init: Cannot init ipv4 mibs\n"); ;
-
ipv4_proc_init();
ipfrag_init();
rc = 0;
out:
return rc;
-out_unregister_tcp_proto:
- proto_unregister(&tcp_prot);
out_unregister_udp_proto:
proto_unregister(&udp_prot);
+out_unregister_tcp_proto:
+ proto_unregister(&tcp_prot);
goto out;
}
-module_init(inet_init);
+fs_initcall(inet_init);
/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS
-extern int fib_proc_init(void);
-extern void fib_proc_exit(void);
-#ifdef CONFIG_IP_FIB_TRIE
-extern int fib_stat_proc_init(void);
-extern void fib_stat_proc_exit(void);
-#endif
-extern int ip_misc_proc_init(void);
-extern int raw_proc_init(void);
-extern void raw_proc_exit(void);
-extern int tcp4_proc_init(void);
-extern void tcp4_proc_exit(void);
-extern int udp4_proc_init(void);
-extern void udp4_proc_exit(void);
-
static int __init ipv4_proc_init(void)
{
int rc = 0;
goto out_tcp;
if (udp4_proc_init())
goto out_udp;
- if (fib_proc_init())
- goto out_fib;
-#ifdef CONFIG_IP_FIB_TRIE
- if (fib_stat_proc_init())
- goto out_fib_stat;
-#endif
if (ip_misc_proc_init())
goto out_misc;
out:
return rc;
out_misc:
-#ifdef CONFIG_IP_FIB_TRIE
- fib_stat_proc_exit();
-out_fib_stat:
-#endif
- 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);