aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/af_inet.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/af_inet.c')
-rw-r--r--net/ipv4/af_inet.c1019
1 files changed, 682 insertions, 337 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 0d109504ed8..d156b3c5f36 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -5,8 +5,6 @@
*
* 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>
@@ -67,6 +65,8 @@
* 2 of the License, or (at your option) any later version.
*/
+#define pr_fmt(fmt) "IPv4: " fmt
+
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/types.h>
@@ -88,14 +88,15 @@
#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>
#include <linux/inet.h>
#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>
@@ -105,20 +106,19 @@
#include <net/tcp.h>
#include <net/udp.h>
#include <net/udplite.h>
+#include <net/ping.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/raw.h>
#include <net/icmp.h>
-#include <net/ipip.h>
#include <net/inet_common.h>
#include <net/xfrm.h>
+#include <net/net_namespace.h>
+#include <net/secure_seq.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
* build a new socket.
@@ -126,10 +126,6 @@ extern void ip_mc_drop_socket(struct sock *sk);
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)
@@ -142,24 +138,26 @@ void inet_sock_destruct(struct sock *sk)
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",
+ pr_err("Attempt to release TCP socket in state %d %p\n",
sk->sk_state, sk);
return;
}
if (!sock_flag(sk, SOCK_DEAD)) {
- printk("Attempt to release alive inet socket %p\n", sk);
+ pr_err("Attempt to release alive inet socket %p\n", 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);
+ kfree(rcu_dereference_protected(inet->inet_opt, 1));
+ dst_release(rcu_dereference_check(sk->sk_dst_cache, 1));
+ dst_release(sk->sk_rx_dst);
sk_refcnt_debug_dec(sk);
}
+EXPORT_SYMBOL(inet_sock_destruct);
/*
* The routines beyond this point handle the behaviour of an AF_INET
@@ -177,12 +175,12 @@ static int inet_autobind(struct sock *sk)
/* 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;
@@ -211,6 +209,26 @@ int inet_listen(struct socket *sock, int backlog)
* we can only allow the backlog to be adjusted.
*/
if (old_state != TCP_LISTEN) {
+ /* Check special setups for testing purpose to enable TFO w/o
+ * requiring TCP_FASTOPEN sockopt.
+ * Note that only TCP sockets (SOCK_STREAM) will reach here.
+ * Also fastopenq may already been allocated because this
+ * socket was in TCP_LISTEN state previously but was
+ * shutdown() (rather than close()).
+ */
+ if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) != 0 &&
+ inet_csk(sk)->icsk_accept_queue.fastopenq == NULL) {
+ if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) != 0)
+ err = fastopen_init_queue(sk, backlog);
+ else if ((sysctl_tcp_fastopen &
+ TFO_SERVER_WO_SOCKOPT2) != 0)
+ err = fastopen_init_queue(sk,
+ ((uint)sysctl_tcp_fastopen) >> 16);
+ else
+ err = 0;
+ if (err)
+ goto out;
+ }
err = inet_csk_listen_start(sk, backlog);
if (err)
goto out;
@@ -222,61 +240,32 @@ out:
release_sock(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);
+EXPORT_SYMBOL(inet_listen);
/*
* 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 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;
- if (net != &init_net)
- return -EAFNOSUPPORT;
-
- 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. */
- 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)
@@ -291,10 +280,9 @@ lookup_protocol:
break;
}
err = -EPROTONOSUPPORT;
- answer = NULL;
}
- if (unlikely(answer == NULL)) {
+ if (unlikely(err)) {
if (try_loading_module < 2) {
rcu_read_unlock();
/*
@@ -317,16 +305,16 @@ lookup_protocol:
}
err = -EPERM;
- if (answer->capability > 0 && !capable(answer->capability))
+ if (sock->type == SOCK_RAW && !kern &&
+ !ns_capable(net->user_ns, CAP_NET_RAW))
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(net, PF_INET, GFP_KERNEL, answer_prot);
@@ -334,48 +322,50 @@ lookup_protocol:
goto out;
err = 0;
- sk->sk_no_check = answer_no_check;
if (INET_PROTOSW_REUSE & answer_flags)
- sk->sk_reuse = 1;
+ sk->sk_reuse = SK_CAN_REUSE;
inet = inet_sk(sk);
inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
+ inet->nodefrag = 0;
+
if (SOCK_RAW == sock->type) {
- inet->num = protocol;
+ inet->inet_num = protocol;
if (IPPROTO_RAW == protocol)
inet->hdrincl = 1;
}
- if (ipv4_config.no_pmtu_disc)
+ if (net->ipv4.sysctl_ip_no_pmtu_disc)
inet->pmtudisc = IP_PMTUDISC_DONT;
else
inet->pmtudisc = IP_PMTUDISC_WANT;
- inet->id = 0;
+ inet->inet_id = 0;
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;
inet->uc_ttl = -1;
inet->mc_loop = 1;
inet->mc_ttl = 1;
+ inet->mc_all = 1;
inet->mc_index = 0;
inet->mc_list = NULL;
+ inet->rcv_tos = 0;
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);
}
@@ -405,6 +395,8 @@ int inet_release(struct socket *sock)
if (sk) {
long timeout;
+ sock_rps_reset_flow(sk);
+
/* Applications forget to leave groups before exiting */
ip_mc_drop_socket(sk);
@@ -424,15 +416,18 @@ int inet_release(struct socket *sock)
}
return 0;
}
+EXPORT_SYMBOL(inet_release);
/* It is off by default, see below. */
int sysctl_ip_nonlocal_bind __read_mostly;
+EXPORT_SYMBOL(sysctl_ip_nonlocal_bind);
int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
struct sock *sk = sock->sk;
struct inet_sock *inet = inet_sk(sk);
+ struct net *net = sock_net(sk);
unsigned short snum;
int chk_addr_ret;
int err;
@@ -446,7 +441,17 @@ 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(&init_net, addr->sin_addr.s_addr);
+ if (addr->sin_family != AF_INET) {
+ /* Compatibility games : accept AF_UNSPEC (mapped to AF_INET)
+ * only if s_addr is INADDR_ANY.
+ */
+ err = -EAFNOSUPPORT;
+ if (addr->sin_family != AF_UNSPEC ||
+ addr->sin_addr.s_addr != htonl(INADDR_ANY))
+ goto out;
+ }
+
+ chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr);
/* Not specified by any standard per-se, however it breaks too
* many applications when removed. It is unfortunate since
@@ -457,7 +462,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
*/
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 &&
@@ -466,7 +471,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
snum = ntohs(addr->sin_port);
err = -EACCES;
- if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
+ if (snum && snum < PROT_SOCK &&
+ !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE))
goto out;
/* We keep a pair of addresses. rcv_saddr is the one
@@ -480,27 +486,27 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
/* 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:
@@ -508,25 +514,30 @@ out_release_sock:
out:
return err;
}
+EXPORT_SYMBOL(inet_bind);
-int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr,
+int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags)
{
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);
+ return sk->sk_prot->connect(sk, uaddr, addr_len);
}
+EXPORT_SYMBOL(inet_dgram_connect);
-static long inet_wait_for_connect(struct sock *sk, long timeo)
+static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
{
DEFINE_WAIT(wait);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ sk->sk_write_pending += writebias;
/* Basic assumption: if someone sets sk->sk_err, he _must_
* change state of the socket from TCP_SYN_*.
@@ -539,9 +550,10 @@ static long inet_wait_for_connect(struct sock *sk, long timeo)
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);
+ sk->sk_write_pending -= writebias;
return timeo;
}
@@ -549,14 +561,15 @@ static long inet_wait_for_connect(struct sock *sk, long timeo)
* Connect to a remote host. There is regrettably still a little
* TCP 'magic' in here.
*/
-int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
- int addr_len, int flags)
+int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+ int addr_len, int flags)
{
struct sock *sk = sock->sk;
int err;
long timeo;
- lock_sock(sk);
+ if (addr_len < sizeof(uaddr->sa_family))
+ return -EINVAL;
if (uaddr->sa_family == AF_UNSPEC) {
err = sk->sk_prot->disconnect(sk, flags);
@@ -597,8 +610,12 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
+ int writebias = (sk->sk_protocol == IPPROTO_TCP) &&
+ tcp_sk(sk)->fastopen_req &&
+ tcp_sk(sk)->fastopen_req->data ? 1 : 0;
+
/* Error code is set above */
- if (!timeo || !inet_wait_for_connect(sk, timeo))
+ if (!timeo || !inet_wait_for_connect(sk, timeo, writebias))
goto out;
err = sock_intr_errno(timeo);
@@ -620,7 +637,6 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
sock->state = SS_CONNECTED;
err = 0;
out:
- release_sock(sk);
return err;
sock_error:
@@ -630,6 +646,19 @@ sock_error:
sock->state = SS_DISCONNECTING;
goto out;
}
+EXPORT_SYMBOL(__inet_stream_connect);
+
+int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+ int addr_len, int flags)
+{
+ int err;
+
+ lock_sock(sock->sk);
+ err = __inet_stream_connect(sock, uaddr, addr_len, flags);
+ release_sock(sock->sk);
+ return err;
+}
+EXPORT_SYMBOL(inet_stream_connect);
/*
* Accept a pending connection. The TCP layer now gives BSD semantics.
@@ -646,8 +675,10 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags)
lock_sock(sk2);
- BUG_TRAP((1 << sk2->sk_state) &
- (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE));
+ sock_rps_record_flow(sk2);
+ WARN_ON(!((1 << sk2->sk_state) &
+ (TCPF_ESTABLISHED | TCPF_SYN_RECV |
+ TCPF_CLOSE_WAIT | TCPF_CLOSE)));
sock_graft(sk2, newsock);
@@ -657,6 +688,7 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags)
do_err:
return err;
}
+EXPORT_SYMBOL(inet_accept);
/*
@@ -667,54 +699,79 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr,
{
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));
*uaddr_len = sizeof(*sin);
return 0;
}
+EXPORT_SYMBOL(inet_getname);
int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
size_t size)
{
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 && !sk->sk_prot->no_autobind &&
+ 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)
+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 && !sk->sk_prot->no_autobind &&
+ inet_autobind(sk))
return -EAGAIN;
if (sk->sk_prot->sendpage)
return sk->sk_prot->sendpage(sk, page, offset, size, flags);
return sock_no_sendpage(sock, page, offset, size, flags);
}
+EXPORT_SYMBOL(inet_sendpage);
+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)
{
@@ -769,6 +826,7 @@ int inet_shutdown(struct socket *sock, int how)
release_sock(sk);
return err;
}
+EXPORT_SYMBOL(inet_shutdown);
/*
* ioctl() calls you can issue on an INET socket. Most of these are
@@ -784,46 +842,61 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
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(sk->sk_net, cmd, (void __user *)arg);
- break;
- case SIOCDARP:
- case SIOCGARP:
- case SIOCSARP:
- err = arp_ioctl(sk->sk_net, cmd, (void __user *)arg);
- break;
- case SIOCGIFADDR:
- case SIOCSIFADDR:
- case SIOCGIFBRDADDR:
- case SIOCSIFBRDADDR:
- case SIOCGIFNETMASK:
- case SIOCSIFNETMASK:
- case SIOCGIFDSTADDR:
- case SIOCSIFDSTADDR:
- case SIOCSIFPFLAGS:
- case SIOCGIFPFLAGS:
- case SIOCSIFFLAGS:
- err = devinet_ioctl(cmd, (void __user *)arg);
- break;
- default:
- if (sk->sk_prot->ioctl)
- err = sk->sk_prot->ioctl(sk, cmd, arg);
- else
- err = -ENOIOCTLCMD;
- break;
+ 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(net, cmd, (void __user *)arg);
+ break;
+ case SIOCDARP:
+ case SIOCGARP:
+ case SIOCSARP:
+ err = arp_ioctl(net, cmd, (void __user *)arg);
+ break;
+ case SIOCGIFADDR:
+ case SIOCSIFADDR:
+ case SIOCGIFBRDADDR:
+ case SIOCSIFBRDADDR:
+ case SIOCGIFNETMASK:
+ case SIOCSIFNETMASK:
+ case SIOCGIFDSTADDR:
+ case SIOCSIFDSTADDR:
+ case SIOCSIFPFLAGS:
+ case SIOCGIFPFLAGS:
+ case SIOCSIFFLAGS:
+ err = devinet_ioctl(net, cmd, (void __user *)arg);
+ break;
+ default:
+ if (sk->sk_prot->ioctl)
+ err = sk->sk_prot->ioctl(sk, cmd, arg);
+ else
+ err = -ENOIOCTLCMD;
+ break;
}
return err;
}
+EXPORT_SYMBOL(inet_ioctl);
+
+#ifdef CONFIG_COMPAT
+static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+ struct sock *sk = sock->sk;
+ int err = -ENOIOCTLCMD;
+
+ if (sk->sk_prot->compat_ioctl)
+ err = sk->sk_prot->compat_ioctl(sk, cmd, arg);
+
+ return err;
+}
+#endif
const struct proto_ops inet_stream_ops = {
.family = PF_INET,
@@ -840,16 +913,18 @@ const struct proto_ops inet_stream_ops = {
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
- .sendmsg = tcp_sendmsg,
- .recvmsg = sock_common_recvmsg,
+ .sendmsg = inet_sendmsg,
+ .recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = tcp_sendpage,
+ .sendpage = inet_sendpage,
.splice_read = tcp_splice_read,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_sock_common_setsockopt,
.compat_getsockopt = compat_sock_common_getsockopt,
+ .compat_ioctl = inet_compat_ioctl,
#endif
};
+EXPORT_SYMBOL(inet_stream_ops);
const struct proto_ops inet_dgram_ops = {
.family = PF_INET,
@@ -867,14 +942,16 @@ const struct proto_ops inet_dgram_ops = {
.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
.compat_setsockopt = compat_sock_common_setsockopt,
.compat_getsockopt = compat_sock_common_getsockopt,
+ .compat_ioctl = inet_compat_ioctl,
#endif
};
+EXPORT_SYMBOL(inet_dgram_ops);
/*
* For SOCK_RAW sockets; should be the same as inet_dgram_ops but without
@@ -896,16 +973,17 @@ static const struct proto_ops inet_sockraw_ops = {
.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
.compat_setsockopt = compat_sock_common_setsockopt,
.compat_getsockopt = compat_sock_common_getsockopt,
+ .compat_ioctl = inet_compat_ioctl,
#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,
@@ -921,8 +999,6 @@ static struct inet_protosw inetsw_array[] =
.protocol = IPPROTO_TCP,
.prot = &tcp_prot,
.ops = &inet_stream_ops,
- .capability = -1,
- .no_check = 0,
.flags = INET_PROTOSW_PERMANENT |
INET_PROTOSW_ICSK,
},
@@ -932,19 +1008,22 @@ static struct inet_protosw inetsw_array[] =
.protocol = IPPROTO_UDP,
.prot = &udp_prot,
.ops = &inet_dgram_ops,
- .capability = -1,
- .no_check = UDP_CSUM_DEFAULT,
.flags = INET_PROTOSW_PERMANENT,
},
+ {
+ .type = SOCK_DGRAM,
+ .protocol = IPPROTO_ICMP,
+ .prot = &ping_prot,
+ .ops = &inet_dgram_ops,
+ .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,
}
};
@@ -991,27 +1070,23 @@ void inet_register_protosw(struct inet_protosw *p)
out:
spin_unlock_bh(&inetsw_lock);
- synchronize_net();
-
return;
out_permanent:
- printk(KERN_ERR "Attempt to override permanent protocol %d.\n",
- protocol);
+ pr_err("Attempt to override permanent protocol %d\n", protocol);
goto out;
out_illegal:
- printk(KERN_ERR
- "Ignoring attempt to register invalid socket type %d.\n",
+ pr_err("Ignoring attempt to register invalid socket type %d\n",
p->type);
goto out;
}
+EXPORT_SYMBOL(inet_register_protosw);
void inet_unregister_protosw(struct inet_protosw *p)
{
if (INET_PROTOSW_PERMANENT & p->flags) {
- printk(KERN_ERR
- "Attempt to unregister permanent protocol %d.\n",
+ pr_err("Attempt to unregister permanent protocol %d\n",
p->protocol);
} else {
spin_lock_bh(&inetsw_lock);
@@ -1021,6 +1096,7 @@ void inet_unregister_protosw(struct inet_protosw *p)
synchronize_net();
}
}
+EXPORT_SYMBOL(inet_unregister_protosw);
/*
* Shall we try to damage output packets if routing dev changes?
@@ -1031,40 +1107,39 @@ int sysctl_ip_dynaddr __read_mostly;
static int inet_sk_reselect_saddr(struct sock *sk)
{
struct inet_sock *inet = inet_sk(sk);
- int err;
+ __be32 old_saddr = inet->inet_saddr;
+ __be32 daddr = inet->inet_daddr;
+ struct flowi4 *fl4;
struct rtable *rt;
- __be32 old_saddr = inet->saddr;
__be32 new_saddr;
- __be32 daddr = inet->daddr;
+ struct ip_options_rcu *inet_opt;
- if (inet->opt && inet->opt->srr)
- daddr = inet->opt->faddr;
+ inet_opt = rcu_dereference_protected(inet->inet_opt,
+ sock_owned_by_user(sk));
+ if (inet_opt && inet_opt->opt.srr)
+ daddr = inet_opt->opt.faddr;
/* Query new route. */
- err = ip_route_connect(&rt, daddr, 0,
- RT_CONN_FLAGS(sk),
- sk->sk_bound_dev_if,
- sk->sk_protocol,
- inet->sport, inet->dport, sk, 0);
- if (err)
- return err;
+ fl4 = &inet->cork.fl.u.ip4;
+ rt = ip_route_connect(fl4, daddr, 0, RT_CONN_FLAGS(sk),
+ sk->sk_bound_dev_if, sk->sk_protocol,
+ inet->inet_sport, inet->inet_dport, sk);
+ if (IS_ERR(rt))
+ return PTR_ERR(rt);
- sk_setup_caps(sk, &rt->u.dst);
+ sk_setup_caps(sk, &rt->dst);
- new_saddr = rt->rt_src;
+ new_saddr = fl4->saddr;
if (new_saddr == old_saddr)
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));
+ pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n",
+ __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
@@ -1083,6 +1158,8 @@ int inet_sk_rebuild_header(struct sock *sk)
struct inet_sock *inet = inet_sk(sk);
struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0);
__be32 daddr;
+ struct ip_options_rcu *inet_opt;
+ struct flowi4 *fl4;
int err;
/* Route is OK, nothing to do. */
@@ -1090,34 +1167,23 @@ int inet_sk_rebuild_header(struct sock *sk)
return 0;
/* Reroute. */
- daddr = inet->daddr;
- if (inet->opt && inet->opt->srr)
- daddr = inet->opt->faddr;
-{
- struct flowi fl = {
- .oif = sk->sk_bound_dev_if,
- .nl_u = {
- .ip4_u = {
- .daddr = daddr,
- .saddr = inet->saddr,
- .tos = RT_CONN_FLAGS(sk),
- },
- },
- .proto = sk->sk_protocol,
- .uli_u = {
- .ports = {
- .sport = inet->sport,
- .dport = inet->dport,
- },
- },
- };
-
- security_sk_classify_flow(sk, &fl);
- err = ip_route_output_flow(&init_net, &rt, &fl, sk, 0);
-}
- if (!err)
- sk_setup_caps(sk, &rt->u.dst);
- else {
+ rcu_read_lock();
+ inet_opt = rcu_dereference(inet->inet_opt);
+ daddr = inet->inet_daddr;
+ if (inet_opt && inet_opt->opt.srr)
+ daddr = inet_opt->opt.faddr;
+ rcu_read_unlock();
+ fl4 = &inet->cork.fl.u.ip4;
+ rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr,
+ inet->inet_dport, inet->inet_sport,
+ sk->sk_protocol, RT_CONN_FLAGS(sk),
+ sk->sk_bound_dev_if);
+ if (!IS_ERR(rt)) {
+ err = 0;
+ sk_setup_caps(sk, &rt->dst);
+ } else {
+ err = PTR_ERR(rt);
+
/* Routing failed... */
sk->sk_route_caps = 0;
/*
@@ -1133,13 +1199,12 @@ int inet_sk_rebuild_header(struct sock *sk)
return err;
}
-
EXPORT_SYMBOL(inet_sk_rebuild_header);
static int inet_gso_send_check(struct sk_buff *skb)
{
- struct iphdr *iph;
- struct net_protocol *ops;
+ const struct net_offload *ops;
+ const struct iphdr *iph;
int proto;
int ihl;
int err = -EINVAL;
@@ -1152,45 +1217,55 @@ static int inet_gso_send_check(struct sk_buff *skb)
if (ihl < sizeof(*iph))
goto out;
+ proto = iph->protocol;
+
+ /* Warning: after this point, iph might be no longer valid */
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();
+ ops = rcu_dereference(inet_offloads[proto]);
+ if (likely(ops && ops->callbacks.gso_send_check))
+ err = ops->callbacks.gso_send_check(skb);
out:
return err;
}
-static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
+static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
+ const struct net_offload *ops;
+ unsigned int offset = 0;
+ bool udpfrag, encap;
struct iphdr *iph;
- struct net_protocol *ops;
int proto;
+ int nhoff;
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 |
+ SKB_GSO_GRE |
+ SKB_GSO_GRE_CSUM |
+ SKB_GSO_IPIP |
+ SKB_GSO_SIT |
+ SKB_GSO_TCPV6 |
+ SKB_GSO_UDP_TUNNEL |
+ SKB_GSO_UDP_TUNNEL_CSUM |
+ SKB_GSO_MPLS |
0)))
goto out;
+ skb_reset_network_header(skb);
+ nhoff = skb_network_header(skb) - skb_mac_header(skb);
if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
goto out;
@@ -1199,168 +1274,434 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
if (ihl < sizeof(*iph))
goto out;
+ id = ntohs(iph->id);
+ proto = iph->protocol;
+
+ /* Warning: after this point, iph might be no longer valid */
if (unlikely(!pskb_may_pull(skb, ihl)))
goto out;
-
__skb_pull(skb, ihl);
+
+ encap = SKB_GSO_CB(skb)->encap_level > 0;
+ if (encap)
+ features = skb->dev->hw_enc_features & netif_skb_features(skb);
+ SKB_GSO_CB(skb)->encap_level += 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 (skb->encapsulation &&
+ skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+ udpfrag = proto == IPPROTO_UDP && encap;
+ else
+ udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
+
+ ops = rcu_dereference(inet_offloads[proto]);
+ if (likely(ops && ops->callbacks.gso_segment))
+ segs = ops->callbacks.gso_segment(skb, features);
- if (!segs || unlikely(IS_ERR(segs)))
+ if (IS_ERR_OR_NULL(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);
+ iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
+ if (udpfrag) {
+ iph->id = htons(id);
+ iph->frag_off = htons(offset >> 3);
+ if (skb->next != NULL)
+ iph->frag_off |= htons(IP_MF);
+ offset += skb->len - nhoff - ihl;
+ } else {
+ iph->id = htons(id++);
+ }
+ iph->tot_len = htons(skb->len - nhoff);
+ ip_send_check(iph);
+ if (encap)
+ skb_reset_inner_headers(skb);
+ skb->network_header = (u8 *)iph - skb->head;
} while ((skb = skb->next));
out:
return segs;
}
-unsigned long snmp_fold_field(void *mib[], int offt)
+static struct sk_buff **inet_gro_receive(struct sk_buff **head,
+ struct sk_buff *skb)
+{
+ const struct net_offload *ops;
+ struct sk_buff **pp = NULL;
+ struct sk_buff *p;
+ const struct iphdr *iph;
+ unsigned int hlen;
+ unsigned int off;
+ unsigned int id;
+ int flush = 1;
+ int proto;
+
+ off = skb_gro_offset(skb);
+ hlen = off + sizeof(*iph);
+ iph = skb_gro_header_fast(skb, off);
+ if (skb_gro_header_hard(skb, hlen)) {
+ iph = skb_gro_header_slow(skb, hlen, off);
+ if (unlikely(!iph))
+ goto out;
+ }
+
+ proto = iph->protocol;
+
+ rcu_read_lock();
+ ops = rcu_dereference(inet_offloads[proto]);
+ if (!ops || !ops->callbacks.gro_receive)
+ goto out_unlock;
+
+ if (*(u8 *)iph != 0x45)
+ goto out_unlock;
+
+ if (unlikely(ip_fast_csum((u8 *)iph, 5)))
+ goto out_unlock;
+
+ 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) {
+ struct iphdr *iph2;
+
+ if (!NAPI_GRO_CB(p)->same_flow)
+ continue;
+
+ iph2 = (struct iphdr *)(p->data + off);
+ /* The above works because, with the exception of the top
+ * (inner most) layer, we only aggregate pkts with the same
+ * hdr length so all the hdrs we'll need to verify will start
+ * at the same offset.
+ */
+ if ((iph->protocol ^ iph2->protocol) |
+ ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) |
+ ((__force u32)iph->daddr ^ (__force u32)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) |
+ (iph->tos ^ iph2->tos) |
+ ((iph->frag_off ^ iph2->frag_off) & htons(IP_DF));
+
+ /* Save the IP ID check to be included later when we get to
+ * the transport layer so only the inner most IP ID is checked.
+ * This is because some GSO/TSO implementations do not
+ * correctly increment the IP ID for the outer hdrs.
+ */
+ NAPI_GRO_CB(p)->flush_id =
+ ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
+ NAPI_GRO_CB(p)->flush |= flush;
+ }
+
+ NAPI_GRO_CB(skb)->flush |= flush;
+ skb_set_network_header(skb, off);
+ /* The above will be needed by the transport layer if there is one
+ * immediately following this IP hdr.
+ */
+
+ skb_gro_pull(skb, sizeof(*iph));
+ skb_set_transport_header(skb, skb_gro_offset(skb));
+
+ pp = ops->callbacks.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, int nhoff)
+{
+ __be16 newlen = htons(skb->len - nhoff);
+ struct iphdr *iph = (struct iphdr *)(skb->data + nhoff);
+ const struct net_offload *ops;
+ int proto = iph->protocol;
+ int err = -ENOSYS;
+
+ if (skb->encapsulation)
+ skb_set_inner_network_header(skb, nhoff);
+
+ csum_replace2(&iph->check, iph->tot_len, newlen);
+ iph->tot_len = newlen;
+
+ rcu_read_lock();
+ ops = rcu_dereference(inet_offloads[proto]);
+ if (WARN_ON(!ops || !ops->callbacks.gro_complete))
+ goto out_unlock;
+
+ /* Only need to add sizeof(*iph) to get to the next hdr below
+ * because any hdr with option will have been flushed in
+ * inet_gro_receive().
+ */
+ err = ops->callbacks.gro_complete(skb, nhoff + sizeof(*iph));
+
+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)
+{
+ 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 __percpu *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);
- }
+ for_each_possible_cpu(i)
+ res += *(((unsigned long *) per_cpu_ptr(mib, 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);
+#if BITS_PER_LONG==32
-void snmp_mib_free(void *ptr[2])
+u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_offset)
{
- BUG_ON(ptr == NULL);
- free_percpu(ptr[0]);
- free_percpu(ptr[1]);
- ptr[0] = ptr[1] = NULL;
+ u64 res = 0;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ void *bhptr;
+ struct u64_stats_sync *syncp;
+ u64 v;
+ unsigned int start;
+
+ bhptr = per_cpu_ptr(mib, cpu);
+ syncp = (struct u64_stats_sync *)(bhptr + syncp_offset);
+ do {
+ start = u64_stats_fetch_begin_irq(syncp);
+ v = *(((u64 *) bhptr) + offt);
+ } while (u64_stats_fetch_retry_irq(syncp, start));
+
+ res += v;
+ }
+ return res;
}
-EXPORT_SYMBOL_GPL(snmp_mib_free);
+EXPORT_SYMBOL_GPL(snmp_fold_field64);
+#endif
#ifdef CONFIG_IP_MULTICAST
-static struct net_protocol igmp_protocol = {
+static const struct net_protocol igmp_protocol = {
.handler = igmp_rcv,
+ .netns_ok = 1,
};
#endif
-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,
+static const struct net_protocol tcp_protocol = {
+ .early_demux = tcp_v4_early_demux,
+ .handler = tcp_v4_rcv,
+ .err_handler = tcp_v4_err,
+ .no_policy = 1,
+ .netns_ok = 1,
+ .icmp_strict_tag_validation = 1,
};
-static struct net_protocol udp_protocol = {
+static const struct net_protocol udp_protocol = {
+ .early_demux = udp_v4_early_demux,
.handler = udp_rcv,
.err_handler = udp_err,
.no_policy = 1,
+ .netns_ok = 1,
};
-static struct net_protocol icmp_protocol = {
+static const struct net_protocol icmp_protocol = {
.handler = icmp_rcv,
+ .err_handler = icmp_err,
.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)) < 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)
+ int i;
+
+ net->mib.tcp_statistics = alloc_percpu(struct tcp_mib);
+ if (!net->mib.tcp_statistics)
goto err_tcp_mib;
- if (snmp_mib_init((void **)udp_statistics,
- sizeof(struct udp_mib)) < 0)
+ net->mib.ip_statistics = alloc_percpu(struct ipstats_mib);
+ if (!net->mib.ip_statistics)
+ goto err_ip_mib;
+
+ for_each_possible_cpu(i) {
+ struct ipstats_mib *af_inet_stats;
+ af_inet_stats = per_cpu_ptr(net->mib.ip_statistics, i);
+ u64_stats_init(&af_inet_stats->syncp);
+ }
+
+ net->mib.net_statistics = alloc_percpu(struct linux_mib);
+ if (!net->mib.net_statistics)
+ goto err_net_mib;
+ net->mib.udp_statistics = alloc_percpu(struct udp_mib);
+ if (!net->mib.udp_statistics)
goto err_udp_mib;
- if (snmp_mib_init((void **)udplite_statistics,
- sizeof(struct udp_mib)) < 0)
+ net->mib.udplite_statistics = alloc_percpu(struct udp_mib);
+ if (!net->mib.udplite_statistics)
goto err_udplite_mib;
+ net->mib.icmp_statistics = alloc_percpu(struct icmp_mib);
+ if (!net->mib.icmp_statistics)
+ goto err_icmp_mib;
+ net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib),
+ GFP_KERNEL);
+ if (!net->mib.icmpmsg_statistics)
+ 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);
+ free_percpu(net->mib.icmp_statistics);
err_icmp_mib:
- snmp_mib_free((void **)ip_statistics);
-err_ip_mib:
- snmp_mib_free((void **)net_statistics);
+ free_percpu(net->mib.udplite_statistics);
+err_udplite_mib:
+ free_percpu(net->mib.udp_statistics);
+err_udp_mib:
+ free_percpu(net->mib.net_statistics);
err_net_mib:
+ free_percpu(net->mib.ip_statistics);
+err_ip_mib:
+ free_percpu(net->mib.tcp_statistics);
+err_tcp_mib:
return -ENOMEM;
}
+static __net_exit void ipv4_mib_exit_net(struct net *net)
+{
+ kfree(net->mib.icmpmsg_statistics);
+ free_percpu(net->mib.icmp_statistics);
+ free_percpu(net->mib.udplite_statistics);
+ free_percpu(net->mib.udp_statistics);
+ free_percpu(net->mib.net_statistics);
+ free_percpu(net->mib.ip_statistics);
+ free_percpu(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 __net_init int inet_init_net(struct net *net)
+{
+ /*
+ * Set defaults for local port range
+ */
+ seqlock_init(&net->ipv4.ip_local_ports.lock);
+ net->ipv4.ip_local_ports.range[0] = 32768;
+ net->ipv4.ip_local_ports.range[1] = 61000;
+
+ seqlock_init(&net->ipv4.ping_group_range.lock);
+ /*
+ * Sane defaults - nobody may create ping sockets.
+ * Boot scripts should set this to distro-specific group.
+ */
+ net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1);
+ net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0);
+ return 0;
+}
+
+static __net_exit void inet_exit_net(struct net *net)
+{
+}
+
+static __net_initdata struct pernet_operations af_inet_ops = {
+ .init = inet_init_net,
+ .exit = inet_exit_net,
+};
+
+static int __init init_inet_pernet_ops(void)
+{
+ return register_pernet_subsys(&af_inet_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_offload ip_packet_offload __read_mostly = {
+ .type = cpu_to_be16(ETH_P_IP),
+ .callbacks = {
+ .gso_send_check = inet_gso_send_check,
+ .gso_segment = inet_gso_segment,
+ .gro_receive = inet_gro_receive,
+ .gro_complete = inet_gro_complete,
+ },
+};
+
+static const struct net_offload ipip_offload = {
+ .callbacks = {
+ .gso_send_check = inet_gso_send_check,
+ .gso_segment = inet_gso_segment,
+ },
+};
+
+static int __init ipv4_offload_init(void)
+{
+ /*
+ * Add offloads
+ */
+ if (udpv4_offload_init() < 0)
+ pr_crit("%s: Cannot add UDP protocol offload\n", __func__);
+ if (tcpv4_offload_init() < 0)
+ pr_crit("%s: Cannot add TCP protocol offload\n", __func__);
+
+ dev_add_offload(&ip_packet_offload);
+ inet_add_offload(&ipip_offload, IPPROTO_IPIP);
+ return 0;
+}
+
+fs_initcall(ipv4_offload_init);
+
+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,
};
static int __init inet_init(void)
{
- struct sk_buff *dummy_skb;
struct inet_protosw *q;
struct list_head *r;
int rc = -EINVAL;
- BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb));
+ BUILD_BUG_ON(sizeof(struct inet_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb));
rc = proto_register(&tcp_prot, 1);
if (rc)
@@ -1374,25 +1715,33 @@ static int __init inet_init(void)
if (rc)
goto out_unregister_udp_proto;
+ rc = proto_register(&ping_prot, 1);
+ if (rc)
+ goto out_unregister_raw_proto;
+
/*
* Tell SOCKET that we are alive...
*/
(void)sock_register(&inet_family_ops);
+#ifdef CONFIG_SYSCTL
+ ip_static_sysctl_init();
+#endif
+
/*
* Add all the base protocols.
*/
if (inet_add_protocol(&icmp_protocol, IPPROTO_ICMP) < 0)
- printk(KERN_CRIT "inet_init: Cannot add ICMP protocol\n");
+ pr_crit("%s: Cannot add ICMP protocol\n", __func__);
if (inet_add_protocol(&udp_protocol, IPPROTO_UDP) < 0)
- printk(KERN_CRIT "inet_init: Cannot add UDP protocol\n");
+ pr_crit("%s: Cannot add UDP protocol\n", __func__);
if (inet_add_protocol(&tcp_protocol, IPPROTO_TCP) < 0)
- printk(KERN_CRIT "inet_init: Cannot add TCP protocol\n");
+ pr_crit("%s: Cannot add TCP protocol\n", __func__);
#ifdef CONFIG_IP_MULTICAST
if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0)
- printk(KERN_CRIT "inet_init: Cannot add IGMP protocol\n");
+ pr_crit("%s: Cannot add IGMP protocol\n", __func__);
#endif
/* Register the socket-side information for inet_create. */
@@ -1414,7 +1763,7 @@ static int __init inet_init(void)
ip_init();
- tcp_v4_init(&inet_family_ops);
+ tcp_v4_init();
/* Setup TCP slab cache for open requests. */
tcp_init();
@@ -1425,24 +1774,31 @@ static int __init inet_init(void)
/* Add UDP-Lite (RFC 3828) */
udplite4_register();
+ ping_init();
+
/*
* 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())
+ pr_crit("%s: Cannot init ipv4 mroute\n", __func__);
#endif
+
+ if (init_inet_pernet_ops())
+ pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__);
/*
* Initialise per-cpu ipv4 mibs
*/
if (init_ipv4_mibs())
- printk(KERN_CRIT "inet_init: Cannot init ipv4 mibs\n"); ;
+ pr_crit("%s: Cannot init ipv4 mibs\n", __func__);
ipv4_proc_init();
@@ -1453,6 +1809,8 @@ static int __init inet_init(void)
rc = 0;
out:
return rc;
+out_unregister_raw_proto:
+ proto_unregister(&raw_prot);
out_unregister_udp_proto:
proto_unregister(&udp_prot);
out_unregister_tcp_proto:
@@ -1475,11 +1833,15 @@ static int __init ipv4_proc_init(void)
goto out_tcp;
if (udp4_proc_init())
goto out_udp;
+ if (ping_proc_init())
+ goto out_ping;
if (ip_misc_proc_init())
goto out_misc;
out:
return rc;
out_misc:
+ ping_proc_exit();
+out_ping:
udp4_proc_exit();
out_udp:
tcp4_proc_exit();
@@ -1499,20 +1861,3 @@ static int __init ipv4_proc_init(void)
MODULE_ALIAS_NETPROTO(PF_INET);
-EXPORT_SYMBOL(inet_accept);
-EXPORT_SYMBOL(inet_bind);
-EXPORT_SYMBOL(inet_dgram_connect);
-EXPORT_SYMBOL(inet_dgram_ops);
-EXPORT_SYMBOL(inet_getname);
-EXPORT_SYMBOL(inet_ioctl);
-EXPORT_SYMBOL(inet_listen);
-EXPORT_SYMBOL(inet_register_protosw);
-EXPORT_SYMBOL(inet_release);
-EXPORT_SYMBOL(inet_sendmsg);
-EXPORT_SYMBOL(inet_shutdown);
-EXPORT_SYMBOL(inet_sock_destruct);
-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);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 02:03:17 +0000