#include <linux/igmp.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
+#include <net/checksum.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.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
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);
int hash;
struct net_protocol *ipprot;
- if (net == &init_net)
+ if (net_eq(net, &init_net))
return 1;
hash = protocol & (MAX_INET_PROTOS - 1);
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;
int try_loading_module = 0;
int err;
- if (sock->type != SOCK_RAW &&
- sock->type != SOCK_DGRAM &&
- !inet_ehash_secret)
- build_ehash_secret();
+ 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)
break;
}
err = -EPROTONOSUPPORT;
- answer = NULL;
}
- if (unlikely(answer == NULL)) {
+ if (unlikely(err)) {
if (try_loading_module < 2) {
rcu_read_unlock();
/*
answer_flags = answer->flags;
rcu_read_unlock();
- BUG_TRAP(answer_prot->slab != NULL);
+ WARN_ON(answer_prot->slab == NULL);
err = -ENOBUFS;
sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
sock_init_data(sock, sk);
sk->sk_destruct = inet_sock_destruct;
- sk->sk_family = PF_INET;
sk->sk_protocol = protocol;
sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
*/
err = -EADDRNOTAVAIL;
if (!sysctl_ip_nonlocal_bind &&
- !inet->freebind &&
+ !(inet->freebind || inet->transparent) &&
addr->sin_addr.s_addr != htonl(INADDR_ANY) &&
chk_addr_ret != RTN_LOCAL &&
chk_addr_ret != RTN_MULTICAST &&
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);
return 0;
if (sysctl_ip_dynaddr > 1) {
- printk(KERN_INFO "%s(): shifting inet->"
- "saddr from " NIPQUAD_FMT " to " NIPQUAD_FMT "\n",
- __func__,
- 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;
},
},
.proto = sk->sk_protocol,
+ .flags = inet_sk_flowi_flags(sk),
.uli_u = {
.ports = {
.sport = inet->sport,
return segs;
}
+static struct sk_buff **inet_gro_receive(struct sk_buff **head,
+ struct sk_buff *skb)
+{
+ struct net_protocol *ops;
+ struct sk_buff **pp = NULL;
+ struct sk_buff *p;
+ struct iphdr *iph;
+ int flush = 1;
+ int proto;
+ int id;
+
+ iph = skb_gro_header(skb, sizeof(*iph));
+ if (unlikely(!iph))
+ goto out;
+
+ proto = iph->protocol & (MAX_INET_PROTOS - 1);
+
+ rcu_read_lock();
+ ops = rcu_dereference(inet_protos[proto]);
+ if (!ops || !ops->gro_receive)
+ goto out_unlock;
+
+ if (*(u8 *)iph != 0x45)
+ goto out_unlock;
+
+ if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
+ goto out_unlock;
+
+ flush = ntohs(iph->tot_len) != skb_gro_len(skb) ||
+ iph->frag_off != htons(IP_DF);
+ id = ntohs(iph->id);
+
+ for (p = *head; p; p = p->next) {
+ struct iphdr *iph2;
+
+ if (!NAPI_GRO_CB(p)->same_flow)
+ continue;
+
+ iph2 = ip_hdr(p);
+
+ if ((iph->protocol ^ iph2->protocol) |
+ (iph->tos ^ iph2->tos) |
+ (iph->saddr ^ iph2->saddr) |
+ (iph->daddr ^ iph2->daddr)) {
+ NAPI_GRO_CB(p)->same_flow = 0;
+ continue;
+ }
+
+ /* All fields must match except length and checksum. */
+ NAPI_GRO_CB(p)->flush |=
+ (iph->ttl ^ iph2->ttl) |
+ ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
+
+ NAPI_GRO_CB(p)->flush |= flush;
+ }
+
+ NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_pull(skb, sizeof(*iph));
+ skb_set_transport_header(skb, skb_gro_offset(skb));
+
+ pp = ops->gro_receive(head, skb);
+
+out_unlock:
+ rcu_read_unlock();
+
+out:
+ NAPI_GRO_CB(skb)->flush |= flush;
+
+ return pp;
+}
+
+static int inet_gro_complete(struct sk_buff *skb)
+{
+ struct net_protocol *ops;
+ struct iphdr *iph = ip_hdr(skb);
+ int proto = iph->protocol & (MAX_INET_PROTOS - 1);
+ int err = -ENOSYS;
+ __be16 newlen = htons(skb->len - skb_network_offset(skb));
+
+ csum_replace2(&iph->check, iph->tot_len, newlen);
+ iph->tot_len = newlen;
+
+ rcu_read_lock();
+ ops = rcu_dereference(inet_protos[proto]);
+ if (WARN_ON(!ops || !ops->gro_complete))
+ goto out_unlock;
+
+ err = ops->gro_complete(skb);
+
+out_unlock:
+ rcu_read_unlock();
+
+ return err;
+}
+
int inet_ctl_sock_create(struct sock **sk, unsigned short family,
unsigned short type, unsigned char protocol,
struct net *net)
#ifdef CONFIG_IP_MULTICAST
static struct net_protocol igmp_protocol = {
.handler = igmp_rcv,
+ .netns_ok = 1,
};
#endif
.err_handler = tcp_v4_err,
.gso_send_check = tcp_v4_gso_send_check,
.gso_segment = tcp_tso_segment,
+ .gro_receive = tcp4_gro_receive,
+ .gro_complete = tcp4_gro_complete,
.no_policy = 1,
.netns_ok = 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)) < 0)
- goto err_net_mib;
- if (snmp_mib_init((void **)ip_statistics,
- sizeof(struct ipstats_mib)) < 0)
- goto err_ip_mib;
- if (snmp_mib_init((void **)icmp_statistics,
- sizeof(struct icmp_mib)) < 0)
- goto err_icmp_mib;
- if (snmp_mib_init((void **)icmpmsg_statistics,
- sizeof(struct icmpmsg_mib)) < 0)
- goto err_icmpmsg_mib;
- if (snmp_mib_init((void **)tcp_statistics,
+ 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,
+ 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,
+ 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_udplite_mib:
- snmp_mib_free((void **)udp_statistics);
-err_udp_mib:
- snmp_mib_free((void **)tcp_statistics);
-err_tcp_mib:
- snmp_mib_free((void **)icmpmsg_statistics);
err_icmpmsg_mib:
- snmp_mib_free((void **)icmp_statistics);
+ snmp_mib_free((void **)net->mib.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.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);
/*
* IP protocol layer initialiser
*/
-static struct packet_type ip_packet_type = {
- .type = __constant_htons(ETH_P_IP),
+static struct packet_type ip_packet_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_IP),
.func = ip_rcv,
.gso_send_check = inet_gso_send_check,
.gso_segment = inet_gso_segment,
+ .gro_receive = inet_gro_receive,
+ .gro_complete = inet_gro_complete,
};
static int __init inet_init(void)
(void)sock_register(&inet_family_ops);
+#ifdef CONFIG_SYSCTL
+ ip_static_sysctl_init();
+#endif
+
/*
* Add all the base protocols.
*/
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);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff