#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>
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 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 == &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;
int try_loading_module = 0;
int err;
+ if (sock->type != SOCK_RAW &&
+ sock->type != SOCK_DGRAM &&
+ !inet_ehash_secret)
+ build_ehash_secret();
+
sock->state = SS_UNCONNECTED;
/* Look for the requested type/protocol pair. */
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;
BUG_TRAP(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 &&
+ addr->sin_addr.s_addr != htonl(INADDR_ANY) &&
chk_addr_ret != RTN_LOCAL &&
chk_addr_ret != RTN_MULTICAST &&
chk_addr_ret != RTN_BROADCAST)
{
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));
}
};
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);
if (unlikely(!pskb_may_pull(skb, ihl)))
goto out;
- skb->h.raw = __skb_pull(skb, ihl);
+ __skb_pull(skb, ihl);
+ skb_reset_transport_header(skb);
iph = ip_hdr(skb);
proto = iph->protocol & (MAX_INET_PROTOS - 1);
err = -EPROTONOSUPPORT;
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 |
if (unlikely(!pskb_may_pull(skb, ihl)))
goto out;
- skb->h.raw = __skb_pull(skb, ihl);
+ __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 = 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;
+ 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,
.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)
{
- 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);
- udplite_statistics[0] = alloc_percpu(struct udp_mib);
- udplite_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]
- && udplite_statistics[0] && udplite_statistics[1] ) )
- return -ENOMEM;
-
- (void) tcp_mib_init();
+ 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,
+ sizeof(struct tcp_mib)) < 0)
+ goto err_tcp_mib;
+ if (snmp_mib_init((void **)udp_statistics,
+ sizeof(struct udp_mib)) < 0)
+ goto err_udp_mib;
+ if (snmp_mib_init((void **)udplite_statistics,
+ sizeof(struct udp_mib)) < 0)
+ goto err_udplite_mib;
+
+ tcp_mib_init();
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);
+err_icmp_mib:
+ snmp_mib_free((void **)ip_statistics);
+err_ip_mib:
+ snmp_mib_free((void **)net_statistics);
+err_net_mib:
+ return -ENOMEM;
}
static int ipv4_proc_init(void);
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
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();