#include <linux/poll.h>
#include <linux/netfilter_ipv4.h>
#include <linux/random.h>
+#include <linux/slab.h>
#include <asm/uaccess.h>
#include <asm/system.h>
WARN_ON(sk->sk_forward_alloc);
kfree(inet->opt);
- dst_release(sk->sk_dst_cache);
+ dst_release(rcu_dereference_check(sk->sk_dst_cache, 1));
sk_refcnt_debug_dec(sk);
}
EXPORT_SYMBOL(inet_sock_destruct);
/* We may need to bind the socket. */
lock_sock(sk);
inet = inet_sk(sk);
- if (!inet->num) {
+ if (!inet->inet_num) {
if (sk->sk_prot->get_port(sk, 0)) {
release_sock(sk);
return -EAGAIN;
}
- inet->sport = htons(inet->num);
+ inet->inet_sport = htons(inet->inet_num);
}
release_sock(sk);
return 0;
* Create an inet socket.
*/
-static int inet_create(struct net *net, struct socket *sock, int protocol)
+static int inet_create(struct net *net, struct socket *sock, int protocol,
+ int kern)
{
struct sock *sk;
struct inet_protosw *answer;
}
err = -EPERM;
- if (answer->capability > 0 && !capable(answer->capability))
+ if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
goto out_rcu_unlock;
err = -EAFNOSUPPORT;
inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
if (SOCK_RAW == sock->type) {
- inet->num = protocol;
+ inet->inet_num = protocol;
if (IPPROTO_RAW == protocol)
inet->hdrincl = 1;
}
else
inet->pmtudisc = IP_PMTUDISC_WANT;
- inet->id = 0;
+ inet->inet_id = 0;
sock_init_data(sock, sk);
sk_refcnt_debug_inc(sk);
- if (inet->num) {
+ if (inet->inet_num) {
/* It assumes that any protocol which allows
* the user to assign a number at socket
* creation time automatically
* shares.
*/
- inet->sport = htons(inet->num);
+ inet->inet_sport = htons(inet->inet_num);
/* Add to protocol hash chains. */
sk->sk_prot->hash(sk);
}
if (sk) {
long timeout;
+ sock_rps_reset_flow(sk);
+
/* Applications forget to leave groups before exiting */
ip_mc_drop_socket(sk);
/* Check these errors (active socket, double bind). */
err = -EINVAL;
- if (sk->sk_state != TCP_CLOSE || inet->num)
+ if (sk->sk_state != TCP_CLOSE || inet->inet_num)
goto out_release_sock;
- inet->rcv_saddr = inet->saddr = addr->sin_addr.s_addr;
+ inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr;
if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
- inet->saddr = 0; /* Use device */
+ inet->inet_saddr = 0; /* Use device */
/* Make sure we are allowed to bind here. */
if (sk->sk_prot->get_port(sk, snum)) {
- inet->saddr = inet->rcv_saddr = 0;
+ inet->inet_saddr = inet->inet_rcv_saddr = 0;
err = -EADDRINUSE;
goto out_release_sock;
}
- if (inet->rcv_saddr)
+ if (inet->inet_rcv_saddr)
sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
if (snum)
sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
- inet->sport = htons(inet->num);
- inet->daddr = 0;
- inet->dport = 0;
+ inet->inet_sport = htons(inet->inet_num);
+ inet->inet_daddr = 0;
+ inet->inet_dport = 0;
sk_dst_reset(sk);
err = 0;
out_release_sock:
{
struct sock *sk = sock->sk;
+ if (addr_len < sizeof(uaddr->sa_family))
+ return -EINVAL;
if (uaddr->sa_family == AF_UNSPEC)
return sk->sk_prot->disconnect(sk, flags);
- if (!inet_sk(sk)->num && inet_autobind(sk))
+ if (!inet_sk(sk)->inet_num && inet_autobind(sk))
return -EAGAIN;
return sk->sk_prot->connect(sk, (struct sockaddr *)uaddr, addr_len);
}
{
DEFINE_WAIT(wait);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
/* Basic assumption: if someone sets sk->sk_err, he _must_
* change state of the socket from TCP_SYN_*.
lock_sock(sk);
if (signal_pending(current) || !timeo)
break;
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return timeo;
}
int err;
long timeo;
+ if (addr_len < sizeof(uaddr->sa_family))
+ return -EINVAL;
+
lock_sock(sk);
if (uaddr->sa_family == AF_UNSPEC) {
{
struct sock *sk = sock->sk;
struct inet_sock *inet = inet_sk(sk);
- struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
+ DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr);
sin->sin_family = AF_INET;
if (peer) {
- if (!inet->dport ||
+ if (!inet->inet_dport ||
(((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) &&
peer == 1))
return -ENOTCONN;
- sin->sin_port = inet->dport;
- sin->sin_addr.s_addr = inet->daddr;
+ sin->sin_port = inet->inet_dport;
+ sin->sin_addr.s_addr = inet->inet_daddr;
} else {
- __be32 addr = inet->rcv_saddr;
+ __be32 addr = inet->inet_rcv_saddr;
if (!addr)
- addr = inet->saddr;
- sin->sin_port = inet->sport;
+ addr = inet->inet_saddr;
+ sin->sin_port = inet->inet_sport;
sin->sin_addr.s_addr = addr;
}
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
{
struct sock *sk = sock->sk;
+ sock_rps_record_flow(sk);
+
/* We may need to bind the socket. */
- if (!inet_sk(sk)->num && inet_autobind(sk))
+ if (!inet_sk(sk)->inet_num && inet_autobind(sk))
return -EAGAIN;
return sk->sk_prot->sendmsg(iocb, sk, msg, size);
}
EXPORT_SYMBOL(inet_sendmsg);
-
static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
size_t size, int flags)
{
struct sock *sk = sock->sk;
+ sock_rps_record_flow(sk);
+
/* We may need to bind the socket. */
- if (!inet_sk(sk)->num && inet_autobind(sk))
+ if (!inet_sk(sk)->inet_num && inet_autobind(sk))
return -EAGAIN;
if (sk->sk_prot->sendpage)
return sock_no_sendpage(sock, page, offset, size, flags);
}
+int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
+ size_t size, int flags)
+{
+ struct sock *sk = sock->sk;
+ int addr_len = 0;
+ int err;
+
+ sock_rps_record_flow(sk);
+
+ err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT,
+ flags & ~MSG_DONTWAIT, &addr_len);
+ if (err >= 0)
+ msg->msg_namelen = addr_len;
+ return err;
+}
+EXPORT_SYMBOL(inet_recvmsg);
int inet_shutdown(struct socket *sock, int how)
{
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = tcp_sendmsg,
- .recvmsg = sock_common_recvmsg,
+ .recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
.sendpage = tcp_sendpage,
.splice_read = tcp_splice_read,
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = inet_sendmsg,
- .recvmsg = sock_common_recvmsg,
+ .recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
.sendpage = inet_sendpage,
#ifdef CONFIG_COMPAT
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = inet_sendmsg,
- .recvmsg = sock_common_recvmsg,
+ .recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
.sendpage = inet_sendpage,
#ifdef CONFIG_COMPAT
#endif
};
-static struct net_proto_family inet_family_ops = {
+static const struct net_proto_family inet_family_ops = {
.family = PF_INET,
.create = inet_create,
.owner = THIS_MODULE,
.protocol = IPPROTO_TCP,
.prot = &tcp_prot,
.ops = &inet_stream_ops,
- .capability = -1,
.no_check = 0,
.flags = INET_PROTOSW_PERMANENT |
INET_PROTOSW_ICSK,
.protocol = IPPROTO_UDP,
.prot = &udp_prot,
.ops = &inet_dgram_ops,
- .capability = -1,
.no_check = UDP_CSUM_DEFAULT,
.flags = INET_PROTOSW_PERMANENT,
},
.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,
}
struct inet_sock *inet = inet_sk(sk);
int err;
struct rtable *rt;
- __be32 old_saddr = inet->saddr;
+ __be32 old_saddr = inet->inet_saddr;
__be32 new_saddr;
- __be32 daddr = inet->daddr;
+ __be32 daddr = inet->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, 0);
+ inet->inet_sport, inet->inet_dport, sk, 0);
if (err)
return err;
__func__, &old_saddr, &new_saddr);
}
- inet->saddr = inet->rcv_saddr = new_saddr;
+ inet->inet_saddr = inet->inet_rcv_saddr = new_saddr;
/*
* XXX The only one ugly spot where we need to
return 0;
/* Reroute. */
- daddr = inet->daddr;
+ daddr = inet->inet_daddr;
if (inet->opt && inet->opt->srr)
daddr = inet->opt->faddr;
{
struct flowi fl = {
.oif = sk->sk_bound_dev_if,
+ .mark = sk->sk_mark,
.nl_u = {
.ip4_u = {
.daddr = daddr,
- .saddr = inet->saddr,
+ .saddr = inet->inet_saddr,
.tos = RT_CONN_FLAGS(sk),
},
},
.flags = inet_sk_flowi_flags(sk),
.uli_u = {
.ports = {
- .sport = inet->sport,
- .dport = inet->dport,
+ .sport = inet->inet_sport,
+ .dport = inet->inet_dport,
},
},
};
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto out_unlock;
- id = ntohl(*(u32 *)&iph->id);
- flush = (u16)((ntohl(*(u32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
+ id = ntohl(*(__be32 *)&iph->id);
+ flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
id >>= 16;
for (p = *head; p; p = p->next) {
if ((iph->protocol ^ iph2->protocol) |
(iph->tos ^ iph2->tos) |
- (iph->saddr ^ iph2->saddr) |
- (iph->daddr ^ iph2->daddr)) {
+ ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) |
+ ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
}
EXPORT_SYMBOL_GPL(inet_ctl_sock_create);
-unsigned long snmp_fold_field(void *mib[], int offt)
+unsigned long snmp_fold_field(void __percpu *mib[], int offt)
{
unsigned long res = 0;
int i;
}
EXPORT_SYMBOL_GPL(snmp_fold_field);
-int snmp_mib_init(void *ptr[2], size_t mibsize)
+int snmp_mib_init(void __percpu *ptr[2], size_t mibsize)
{
BUG_ON(ptr == NULL);
- ptr[0] = __alloc_percpu(mibsize, __alignof__(unsigned long long));
+ ptr[0] = __alloc_percpu(mibsize, __alignof__(unsigned long));
if (!ptr[0])
goto err0;
- ptr[1] = __alloc_percpu(mibsize, __alignof__(unsigned long long));
+ ptr[1] = __alloc_percpu(mibsize, __alignof__(unsigned long));
if (!ptr[1])
goto err1;
return 0;
}
EXPORT_SYMBOL_GPL(snmp_mib_init);
-void snmp_mib_free(void *ptr[2])
+void snmp_mib_free(void __percpu *ptr[2])
{
BUG_ON(ptr == NULL);
free_percpu(ptr[0]);
static __net_init int ipv4_mib_init_net(struct net *net)
{
- if (snmp_mib_init((void **)net->mib.tcp_statistics,
+ if (snmp_mib_init((void __percpu **)net->mib.tcp_statistics,
sizeof(struct tcp_mib)) < 0)
goto err_tcp_mib;
- if (snmp_mib_init((void **)net->mib.ip_statistics,
+ if (snmp_mib_init((void __percpu **)net->mib.ip_statistics,
sizeof(struct ipstats_mib)) < 0)
goto err_ip_mib;
- if (snmp_mib_init((void **)net->mib.net_statistics,
+ if (snmp_mib_init((void __percpu **)net->mib.net_statistics,
sizeof(struct linux_mib)) < 0)
goto err_net_mib;
- if (snmp_mib_init((void **)net->mib.udp_statistics,
+ if (snmp_mib_init((void __percpu **)net->mib.udp_statistics,
sizeof(struct udp_mib)) < 0)
goto err_udp_mib;
- if (snmp_mib_init((void **)net->mib.udplite_statistics,
+ if (snmp_mib_init((void __percpu **)net->mib.udplite_statistics,
sizeof(struct udp_mib)) < 0)
goto err_udplite_mib;
- if (snmp_mib_init((void **)net->mib.icmp_statistics,
+ if (snmp_mib_init((void __percpu **)net->mib.icmp_statistics,
sizeof(struct icmp_mib)) < 0)
goto err_icmp_mib;
- if (snmp_mib_init((void **)net->mib.icmpmsg_statistics,
+ if (snmp_mib_init((void __percpu **)net->mib.icmpmsg_statistics,
sizeof(struct icmpmsg_mib)) < 0)
goto err_icmpmsg_mib;
return 0;
err_icmpmsg_mib:
- snmp_mib_free((void **)net->mib.icmp_statistics);
+ snmp_mib_free((void __percpu **)net->mib.icmp_statistics);
err_icmp_mib:
- snmp_mib_free((void **)net->mib.udplite_statistics);
+ snmp_mib_free((void __percpu **)net->mib.udplite_statistics);
err_udplite_mib:
- snmp_mib_free((void **)net->mib.udp_statistics);
+ snmp_mib_free((void __percpu **)net->mib.udp_statistics);
err_udp_mib:
- snmp_mib_free((void **)net->mib.net_statistics);
+ snmp_mib_free((void __percpu **)net->mib.net_statistics);
err_net_mib:
- snmp_mib_free((void **)net->mib.ip_statistics);
+ snmp_mib_free((void __percpu **)net->mib.ip_statistics);
err_ip_mib:
- snmp_mib_free((void **)net->mib.tcp_statistics);
+ snmp_mib_free((void __percpu **)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);
+ snmp_mib_free((void __percpu **)net->mib.icmpmsg_statistics);
+ snmp_mib_free((void __percpu **)net->mib.icmp_statistics);
+ snmp_mib_free((void __percpu **)net->mib.udplite_statistics);
+ snmp_mib_free((void __percpu **)net->mib.udp_statistics);
+ snmp_mib_free((void __percpu **)net->mib.net_statistics);
+ snmp_mib_free((void __percpu **)net->mib.ip_statistics);
+ snmp_mib_free((void __percpu **)net->mib.tcp_statistics);
}
static __net_initdata struct pernet_operations ipv4_mib_ops = {
BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb));
+ sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
+ if (!sysctl_local_reserved_ports)
+ goto out;
+
rc = proto_register(&tcp_prot, 1);
if (rc)
- goto out;
+ goto out_free_reserved_ports;
rc = proto_register(&udp_prot, 1);
if (rc)
proto_unregister(&udp_prot);
out_unregister_tcp_proto:
proto_unregister(&tcp_prot);
+out_free_reserved_ports:
+ kfree(sysctl_local_reserved_ports);
goto out;
}