summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/Makefile2
-rw-r--r--net/ipv6/addrconf.c40
-rw-r--r--net/ipv6/af_inet6.c49
-rw-r--r--net/ipv6/exthdrs_core.c13
-rw-r--r--net/ipv6/icmp.c25
-rw-r--r--net/ipv6/inet6_connection_sock.c2
-rw-r--r--net/ipv6/netfilter/Kconfig12
-rw-r--r--net/ipv6/netfilter/ip6t_REJECT.c9
-rw-r--r--net/ipv6/ping.c224
-rw-r--r--net/ipv6/route.c9
-rw-r--r--net/ipv6/syncookies.c4
-rw-r--r--net/ipv6/sysctl_net_ipv6.c7
-rw-r--r--net/ipv6/tcp_ipv6.c2
13 files changed, 376 insertions, 22 deletions
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 9af088d2cdaa..470a9c008e9b 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_IPV6) += ipv6.o
ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \
addrlabel.o \
route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \
- raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o \
+ raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \
exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o
ipv6-offload := ip6_offload.o tcpv6_offload.o udp_offload.o exthdrs_offload.o
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index b78a3ee93d52..d4cad1d5e9fd 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -198,6 +198,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
+ .accept_ra_rt_table = 0,
.proxy_ndp = 0,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
@@ -232,6 +233,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
+ .accept_ra_rt_table = 0,
.proxy_ndp = 0,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
@@ -1943,6 +1945,31 @@ static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmp
}
#endif
+u32 addrconf_rt_table(const struct net_device *dev, u32 default_table) {
+ /* Determines into what table to put autoconf PIO/RIO/default routes
+ * learned on this device.
+ *
+ * - If 0, use the same table for every device. This puts routes into
+ * one of RT_TABLE_{PREFIX,INFO,DFLT} depending on the type of route
+ * (but note that these three are currently all equal to
+ * RT6_TABLE_MAIN).
+ * - If > 0, use the specified table.
+ * - If < 0, put routes into table dev->ifindex + (-rt_table).
+ */
+ struct inet6_dev *idev = in6_dev_get(dev);
+ u32 table;
+ int sysctl = idev->cnf.accept_ra_rt_table;
+ if (sysctl == 0) {
+ table = default_table;
+ } else if (sysctl > 0) {
+ table = (u32) sysctl;
+ } else {
+ table = (unsigned) dev->ifindex + (-sysctl);
+ }
+ in6_dev_put(idev);
+ return table;
+}
+
/*
* Add prefix route.
*/
@@ -1952,7 +1979,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
unsigned long expires, u32 flags)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_PREFIX,
+ .fc_table = addrconf_rt_table(dev, RT6_TABLE_PREFIX),
.fc_metric = IP6_RT_PRIO_ADDRCONF,
.fc_ifindex = dev->ifindex,
.fc_expires = expires,
@@ -1986,7 +2013,8 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
struct rt6_info *rt = NULL;
struct fib6_table *table;
- table = fib6_get_table(dev_net(dev), RT6_TABLE_PREFIX);
+ table = fib6_get_table(dev_net(dev),
+ addrconf_rt_table(dev, RT6_TABLE_PREFIX));
if (table == NULL)
return NULL;
@@ -4192,6 +4220,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen;
#endif
#endif
+ array[DEVCONF_ACCEPT_RA_RT_TABLE] = cnf->accept_ra_rt_table;
array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp;
array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
@@ -4901,6 +4930,13 @@ static struct addrconf_sysctl_table
#endif
#endif
{
+ .procname = "accept_ra_rt_table",
+ .data = &ipv6_devconf.accept_ra_rt_table,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "proxy_ndp",
.data = &ipv6_devconf.proxy_ndp,
.maxlen = sizeof(int),
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index ab5c7ad482cd..a4cfde67fcb7 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -49,6 +49,7 @@
#include <net/udp.h>
#include <net/udplite.h>
#include <net/tcp.h>
+#include <net/ping.h>
#include <net/protocol.h>
#include <net/inet_common.h>
#include <net/route.h>
@@ -62,6 +63,20 @@
#include <asm/uaccess.h>
#include <linux/mroute6.h>
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+#include <linux/android_aid.h>
+
+static inline int current_has_network(void)
+{
+ return in_egroup_p(AID_INET) || capable(CAP_NET_RAW);
+}
+#else
+static inline int current_has_network(void)
+{
+ return 1;
+}
+#endif
+
MODULE_AUTHOR("Cast of dozens");
MODULE_DESCRIPTION("IPv6 protocol stack for Linux");
MODULE_LICENSE("GPL");
@@ -108,6 +123,9 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
int try_loading_module = 0;
int err;
+ if (!current_has_network())
+ return -EACCES;
+
if (sock->type != SOCK_RAW &&
sock->type != SOCK_DGRAM &&
!inet_ehash_secret)
@@ -159,8 +177,7 @@ lookup_protocol:
}
err = -EPERM;
- if (sock->type == SOCK_RAW && !kern &&
- !ns_capable(net->user_ns, CAP_NET_RAW))
+ if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
goto out_rcu_unlock;
sock->ops = answer->ops;
@@ -477,6 +494,21 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
}
EXPORT_SYMBOL(inet6_getname);
+int inet6_killaddr_ioctl(struct net *net, void __user *arg) {
+ struct in6_ifreq ireq;
+ struct sockaddr_in6 sin6;
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EACCES;
+
+ if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq)))
+ return -EFAULT;
+
+ sin6.sin6_family = AF_INET6;
+ sin6.sin6_addr = ireq.ifr6_addr;
+ return tcp_nuke_addr(net, (struct sockaddr *) &sin6);
+}
+
int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct sock *sk = sock->sk;
@@ -500,6 +532,8 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
return addrconf_del_ifaddr(net, (void __user *) arg);
case SIOCSIFDSTADDR:
return addrconf_set_dstaddr(net, (void __user *) arg);
+ case SIOCKILLADDR:
+ return inet6_killaddr_ioctl(net, (void __user *) arg);
default:
if (!sk->sk_prot->ioctl)
return -ENOIOCTLCMD;
@@ -840,6 +874,9 @@ static int __init inet6_init(void)
if (err)
goto out_unregister_udplite_proto;
+ err = proto_register(&pingv6_prot, 1);
+ if (err)
+ goto out_unregister_ping_proto;
/* We MUST register RAW sockets before we create the ICMP6,
* IGMP6, or NDISC control sockets.
@@ -930,6 +967,10 @@ static int __init inet6_init(void)
if (err)
goto ipv6_packet_fail;
+ err = pingv6_init();
+ if (err)
+ goto pingv6_fail;
+
#ifdef CONFIG_SYSCTL
err = ipv6_sysctl_register();
if (err)
@@ -942,6 +983,8 @@ out:
sysctl_fail:
ipv6_packet_cleanup();
#endif
+pingv6_fail:
+ pingv6_exit();
ipv6_packet_fail:
tcpv6_exit();
tcpv6_fail:
@@ -985,6 +1028,8 @@ register_pernet_fail:
rtnl_unregister_all(PF_INET6);
out_sock_register_fail:
rawv6_exit();
+out_unregister_ping_proto:
+ proto_unregister(&pingv6_prot);
out_unregister_raw_proto:
proto_unregister(&rawv6_prot);
out_unregister_udplite_proto:
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index c5e83fae4df4..23eed2365fe7 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -166,15 +166,15 @@ EXPORT_SYMBOL_GPL(ipv6_find_tlv);
* to explore inner IPv6 header, eg. ICMPv6 error messages.
*
* If target header is found, its offset is set in *offset and return protocol
- * number. Otherwise, return -1.
+ * number. Otherwise, return -ENOENT or -EBADMSG.
*
* If the first fragment doesn't contain the final protocol header or
* NEXTHDR_NONE it is considered invalid.
*
* Note that non-1st fragment is special case that "the protocol number
* of last header" is "next header" field in Fragment header. In this case,
- * *offset is meaningless and fragment offset is stored in *fragoff if fragoff
- * isn't NULL.
+ * *offset is meaningless. If fragoff is not NULL, the fragment offset is
+ * stored in *fragoff; if it is NULL, return -EINVAL.
*
* if flags is not NULL and it's a fragment, then the frag flag
* IP6_FH_F_FRAG will be set. If it's an AH header, the
@@ -253,9 +253,12 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
if (target < 0 &&
((!ipv6_ext_hdr(hp->nexthdr)) ||
hp->nexthdr == NEXTHDR_NONE)) {
- if (fragoff)
+ if (fragoff) {
*fragoff = _frag_off;
- return hp->nexthdr;
+ return hp->nexthdr;
+ } else {
+ return -EINVAL;
+ }
}
return -ENOENT;
}
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 70e704d49007..83a421c97461 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -57,6 +57,7 @@
#include <net/ipv6.h>
#include <net/ip6_checksum.h>
+#include <net/ping.h>
#include <net/protocol.h>
#include <net/raw.h>
#include <net/rawv6.h>
@@ -84,12 +85,18 @@ static inline struct sock *icmpv6_sk(struct net *net)
static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
+ /* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */
+ struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset);
struct net *net = dev_net(skb->dev);
if (type == ICMPV6_PKT_TOOBIG)
ip6_update_pmtu(skb, net, info, 0, 0);
else if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, 0, 0);
+
+ if (!(type & ICMPV6_INFOMSG_MASK))
+ if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
+ ping_err(skb, offset, info);
}
static int icmpv6_rcv(struct sk_buff *skb);
@@ -224,7 +231,8 @@ static bool opt_unrec(struct sk_buff *skb, __u32 offset)
return (*op & 0xC0) == 0x80;
}
-static int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len)
+int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
+ struct icmp6hdr *thdr, int len)
{
struct sk_buff *skb;
struct icmp6hdr *icmp6h;
@@ -307,8 +315,8 @@ static void mip6_addr_swap(struct sk_buff *skb)
static inline void mip6_addr_swap(struct sk_buff *skb) {}
#endif
-static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
- struct sock *sk, struct flowi6 *fl6)
+struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
+ struct sock *sk, struct flowi6 *fl6)
{
struct dst_entry *dst, *dst2;
struct flowi6 fl2;
@@ -389,6 +397,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
int len;
int hlimit;
int err = 0;
+ u32 mark = IP6_REPLY_MARK(net, skb->mark);
if ((u8 *)hdr < skb->head ||
(skb->network_header + sizeof(*hdr)) > skb->tail)
@@ -454,6 +463,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
fl6.daddr = hdr->saddr;
if (saddr)
fl6.saddr = *saddr;
+ fl6.flowi6_mark = mark;
fl6.flowi6_oif = iif;
fl6.fl6_icmp_type = type;
fl6.fl6_icmp_code = code;
@@ -462,6 +472,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
sk = icmpv6_xmit_lock(net);
if (sk == NULL)
return;
+ sk->sk_mark = mark;
np = inet6_sk(sk);
if (!icmpv6_xrlim_allow(sk, type, &fl6))
@@ -543,6 +554,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
struct dst_entry *dst;
int err = 0;
int hlimit;
+ u32 mark = IP6_REPLY_MARK(net, skb->mark);
saddr = &ipv6_hdr(skb)->daddr;
@@ -559,11 +571,13 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
fl6.saddr = *saddr;
fl6.flowi6_oif = skb->dev->ifindex;
fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
+ fl6.flowi6_mark = mark;
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
sk = icmpv6_xmit_lock(net);
if (sk == NULL)
return;
+ sk->sk_mark = mark;
np = inet6_sk(sk);
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
@@ -697,7 +711,8 @@ static int icmpv6_rcv(struct sk_buff *skb)
skb->csum = ~csum_unfold(csum_ipv6_magic(saddr, daddr, skb->len,
IPPROTO_ICMPV6, 0));
if (__skb_checksum_complete(skb)) {
- LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [%pI6 > %pI6]\n",
+ LIMIT_NETDEBUG(KERN_DEBUG
+ "ICMPv6 checksum failed [%pI6c > %pI6c]\n",
saddr, daddr);
goto csum_error;
}
@@ -718,7 +733,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
break;
case ICMPV6_ECHO_REPLY:
- /* we couldn't care less */
+ ping_rcv(skb);
break;
case ICMPV6_PKT_TOOBIG:
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index e4311cbc8b4e..f1493138d21e 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -81,7 +81,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
final_p = fl6_update_dst(fl6, np->opt, &final);
fl6->saddr = treq->loc_addr;
fl6->flowi6_oif = treq->iif;
- fl6->flowi6_mark = sk->sk_mark;
+ fl6->flowi6_mark = inet_rsk(req)->ir_mark;
fl6->fl6_dport = inet_rsk(req)->rmt_port;
fl6->fl6_sport = inet_rsk(req)->loc_port;
security_req_classify_flow(req, flowi6_to_flowi(fl6));
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 4433ab40e7de..7f45af3e8128 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -153,6 +153,18 @@ config IP6_NF_TARGET_REJECT
To compile it as a module, choose M here. If unsure, say N.
+config IP6_NF_TARGET_REJECT_SKERR
+ bool "Force socket error when rejecting with icmp*"
+ depends on IP6_NF_TARGET_REJECT
+ default n
+ help
+ This option enables turning a "--reject-with icmp*" into a matching
+ socket error also.
+ The REJECT target normally allows sending an ICMP message. But it
+ leaves the local socket unaware of any ingress rejects.
+
+ If unsure, say N.
+
config IP6_NF_MANGLE
tristate "Packet mangling"
default m if NETFILTER_ADVANCED=n
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index 70f9abc0efe9..573c232239b0 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -180,6 +180,15 @@ send_unreach(struct net *net, struct sk_buff *skb_in, unsigned char code,
skb_in->dev = net->loopback_dev;
icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);
+#ifdef CONFIG_IP6_NF_TARGET_REJECT_SKERR
+ if (skb_in->sk) {
+ icmpv6_err_convert(ICMPV6_DEST_UNREACH, code,
+ &skb_in->sk->sk_err);
+ skb_in->sk->sk_error_report(skb_in->sk);
+ pr_debug("ip6t_REJECT: sk_err=%d for skb=%p sk=%p\n",
+ skb_in->sk->sk_err, skb_in, skb_in->sk);
+ }
+#endif
}
static unsigned int
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
new file mode 100644
index 000000000000..84eed65526bd
--- /dev/null
+++ b/net/ipv6/ping.c
@@ -0,0 +1,224 @@
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * "Ping" sockets
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Based on ipv4/ping.c code.
+ *
+ * Authors: Lorenzo Colitti (IPv6 support)
+ * Vasiliy Kulikov / Openwall (IPv4 implementation, for Linux 2.6),
+ * Pavel Kankovsky (IPv4 implementation, for Linux 2.4.32)
+ *
+ */
+
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/protocol.h>
+#include <net/udp.h>
+#include <net/transp_v6.h>
+#include <net/ping.h>
+
+struct proto pingv6_prot = {
+ .name = "PINGv6",
+ .owner = THIS_MODULE,
+ .init = ping_init_sock,
+ .close = ping_close,
+ .connect = ip6_datagram_connect,
+ .disconnect = udp_disconnect,
+ .setsockopt = ipv6_setsockopt,
+ .getsockopt = ipv6_getsockopt,
+ .sendmsg = ping_v6_sendmsg,
+ .recvmsg = ping_recvmsg,
+ .bind = ping_bind,
+ .backlog_rcv = ping_queue_rcv_skb,
+ .hash = ping_hash,
+ .unhash = ping_unhash,
+ .get_port = ping_get_port,
+ .obj_size = sizeof(struct raw6_sock),
+};
+EXPORT_SYMBOL_GPL(pingv6_prot);
+
+static struct inet_protosw pingv6_protosw = {
+ .type = SOCK_DGRAM,
+ .protocol = IPPROTO_ICMPV6,
+ .prot = &pingv6_prot,
+ .ops = &inet6_dgram_ops,
+ .no_check = UDP_CSUM_DEFAULT,
+ .flags = INET_PROTOSW_REUSE,
+};
+
+
+/* Compatibility glue so we can support IPv6 when it's compiled as a module */
+int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
+{
+ return -EAFNOSUPPORT;
+}
+int dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
+ struct sk_buff *skb)
+{
+ return -EAFNOSUPPORT;
+}
+int dummy_icmpv6_err_convert(u8 type, u8 code, int *err)
+{
+ return -EAFNOSUPPORT;
+}
+void dummy_ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
+ __be16 port, u32 info, u8 *payload) {}
+int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
+ struct net_device *dev, int strict)
+{
+ return 0;
+}
+
+int __init pingv6_init(void)
+{
+ pingv6_ops.ipv6_recv_error = ipv6_recv_error;
+ pingv6_ops.ip6_datagram_recv_ctl = ip6_datagram_recv_ctl;
+ pingv6_ops.icmpv6_err_convert = icmpv6_err_convert;
+ pingv6_ops.ipv6_icmp_error = ipv6_icmp_error;
+ pingv6_ops.ipv6_chk_addr = ipv6_chk_addr;
+ return inet6_register_protosw(&pingv6_protosw);
+}
+
+/* This never gets called because it's not possible to unload the ipv6 module,
+ * but just in case.
+ */
+void pingv6_exit(void)
+{
+ pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error;
+ pingv6_ops.ip6_datagram_recv_ctl = dummy_ip6_datagram_recv_ctl;
+ pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert;
+ pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error;
+ pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr;
+ inet6_unregister_protosw(&pingv6_protosw);
+}
+
+int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len)
+{
+ struct inet_sock *inet = inet_sk(sk);
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct icmp6hdr user_icmph;
+ int addr_type;
+ struct in6_addr *daddr;
+ int iif = 0;
+ struct flowi6 fl6;
+ int err;
+ int hlimit;
+ struct dst_entry *dst;
+ struct rt6_info *rt;
+ struct pingfakehdr pfh;
+
+ pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
+
+ err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph,
+ sizeof(user_icmph));
+ if (err)
+ return err;
+
+ if (msg->msg_name) {
+ struct sockaddr_in6 *u = (struct sockaddr_in6 *) msg->msg_name;
+ if (msg->msg_namelen < sizeof(struct sockaddr_in6) ||
+ u->sin6_family != AF_INET6) {
+ return -EINVAL;
+ }
+ if (sk->sk_bound_dev_if &&
+ sk->sk_bound_dev_if != u->sin6_scope_id) {
+ return -EINVAL;
+ }
+ daddr = &(u->sin6_addr);
+ iif = u->sin6_scope_id;
+ } else {
+ if (sk->sk_state != TCP_ESTABLISHED)
+ return -EDESTADDRREQ;
+ daddr = &np->daddr;
+ }
+
+ if (!iif)
+ iif = sk->sk_bound_dev_if;
+
+ addr_type = ipv6_addr_type(daddr);
+ if (__ipv6_addr_needs_scope_id(addr_type) && !iif)
+ return -EINVAL;
+ if (addr_type & IPV6_ADDR_MAPPED)
+ return -EINVAL;
+
+ /* TODO: use ip6_datagram_send_ctl to get options from cmsg */
+
+ memset(&fl6, 0, sizeof(fl6));
+
+ fl6.flowi6_proto = IPPROTO_ICMPV6;
+ fl6.saddr = np->saddr;
+ fl6.daddr = *daddr;
+
+ fl6.flowi6_mark = sk->sk_mark;
+
+ fl6.fl6_icmp_type = user_icmph.icmp6_type;
+ fl6.fl6_icmp_code = user_icmph.icmp6_code;
+ security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+
+ if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
+ fl6.flowi6_oif = np->mcast_oif;
+ else if (!fl6.flowi6_oif)
+ fl6.flowi6_oif = np->ucast_oif;
+
+ dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, 1);
+ if (IS_ERR(dst))
+ return PTR_ERR(dst);
+ rt = (struct rt6_info *) dst;
+
+ np = inet6_sk(sk);
+ if (!np)
+ return -EBADF;
+
+ if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
+ fl6.flowi6_oif = np->mcast_oif;
+ else if (!fl6.flowi6_oif)
+ fl6.flowi6_oif = np->ucast_oif;
+
+ pfh.icmph.type = user_icmph.icmp6_type;
+ pfh.icmph.code = user_icmph.icmp6_code;
+ pfh.icmph.checksum = 0;
+ pfh.icmph.un.echo.id = inet->inet_sport;
+ pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence;
+ pfh.iov = msg->msg_iov;
+ pfh.wcheck = 0;
+ pfh.family = AF_INET6;
+
+ if (ipv6_addr_is_multicast(&fl6.daddr))
+ hlimit = np->mcast_hops;
+ else
+ hlimit = np->hop_limit;
+ if (hlimit < 0)
+ hlimit = ip6_dst_hoplimit(dst);
+
+ lock_sock(sk);
+ err = ip6_append_data(sk, ping_getfrag, &pfh, len,
+ 0, hlimit,
+ np->tclass, NULL, &fl6, rt,
+ MSG_DONTWAIT, np->dontfrag);
+
+ if (err) {
+ ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev,
+ ICMP6_MIB_OUTERRORS);
+ ip6_flush_pending_frames(sk);
+ } else {
+ err = icmpv6_push_pending_frames(sk, &fl6,
+ (struct icmp6hdr *) &pfh.icmph,
+ len);
+ }
+ release_sock(sk);
+
+ if (err)
+ return err;
+
+ return len;
+}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 6c389300f4e9..87f04f372ae4 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1957,26 +1957,25 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
return rt6_get_dflt_router(gwaddr, dev);
}
+
void rt6_purge_dflt_routers(struct net *net)
{
struct rt6_info *rt;
struct fib6_table *table;
-
- /* NOTE: Keep consistent with rt6_get_dflt_router */
table = fib6_get_table(net, RT6_TABLE_DFLT);
if (!table)
return;
-
restart:
read_lock_bh(&table->tb6_lock);
for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
- if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
+ if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
(!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) {
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
ip6_del_rt(rt);
goto restart;
- }
+}
+
}
read_unlock_bh(&table->tb6_lock);
}
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index d5dda20bd717..1efbc6f44a6a 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -212,6 +212,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL)
ireq6->iif = inet6_iif(skb);
+ ireq->ir_mark = inet_request_mark(sk, skb);
+
req->expires = 0UL;
req->num_retrans = 0;
ireq->ecn_ok = ecn_ok;
@@ -238,7 +240,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
final_p = fl6_update_dst(&fl6, np->opt, &final);
fl6.saddr = ireq6->loc_addr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
- fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_mark = ireq->ir_mark;
fl6.fl6_dport = inet_rsk(req)->rmt_port;
fl6.fl6_sport = inet_sk(sk)->inet_sport;
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index e85c48bd404f..53a9f5a64536 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -24,6 +24,13 @@ static ctl_table ipv6_table_template[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "fwmark_reflect",
+ .data = &init_net.ipv6.sysctl.fwmark_reflect,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
{ }
};
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 66c718854e5a..747374c98876 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -791,6 +791,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
fl6.flowi6_proto = IPPROTO_TCP;
if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL)
fl6.flowi6_oif = inet6_iif(skb);
+ fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
fl6.fl6_dport = t1->dest;
fl6.fl6_sport = t1->source;
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
@@ -999,6 +1000,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
TCP_ECN_create_request(req, skb, sock_net(sk));
treq->iif = sk->sk_bound_dev_if;
+ inet_rsk(req)->ir_mark = inet_request_mark(sk, skb);
/* So that link locals have meaning */
if (!sk->sk_bound_dev_if &&
generated by cgit v1.2.3 (git 2.0.4) at 2024-06-25 10:56:08 +0000