summaryrefslogtreecommitdiff
path: root/net/ipv6/icmp.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/icmp.c')
-rw-r--r--net/ipv6/icmp.c982
1 files changed, 716 insertions, 266 deletions
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 7cfc8d284870..5d2f90babaa5 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Internet Control Message Protocol (ICMPv6)
* Linux INET6 implementation
@@ -8,11 +9,6 @@
* Based on net/ipv4/icmp.c
*
* RFC 1885
- *
- * 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.
*/
/*
@@ -61,42 +57,38 @@
#include <net/protocol.h>
#include <net/raw.h>
#include <net/rawv6.h>
+#include <net/seg6.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/icmp.h>
#include <net/xfrm.h>
#include <net/inet_common.h>
+#include <net/dsfield.h>
+#include <net/l3mdev.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
-/*
- * The ICMP socket(s). This is the most convenient way to flow control
- * our ICMP output as well as maintain a clean interface throughout
- * all layers. All Socketless IP sends will soon be gone.
- *
- * On SMP we have one ICMP socket per-cpu.
- */
-static inline struct sock *icmpv6_sk(struct net *net)
-{
- return net->ipv6.icmp_sk[smp_processor_id()];
-}
+static DEFINE_PER_CPU(struct sock *, ipv6_icmp_sk);
-static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int 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);
+ struct net *net = dev_net_rcu(skb->dev);
if (type == ICMPV6_PKT_TOOBIG)
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, sock_net_uid(net, NULL));
else if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, 0, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
if (!(type & ICMPV6_INFOMSG_MASK))
if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
- ping_err(skb, offset, info);
+ ping_err(skb, offset, ntohl(info));
+
+ return 0;
}
static int icmpv6_rcv(struct sk_buff *skb);
@@ -107,27 +99,27 @@ static const struct inet6_protocol icmpv6_protocol = {
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
};
-static __inline__ struct sock *icmpv6_xmit_lock(struct net *net)
+/* Called with BH disabled */
+static struct sock *icmpv6_xmit_lock(struct net *net)
{
struct sock *sk;
- local_bh_disable();
-
- sk = icmpv6_sk(net);
+ sk = this_cpu_read(ipv6_icmp_sk);
if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
/* This can happen if the output path (f.e. SIT or
* ip6ip6 tunnel) signals dst_link_failure() for an
* outgoing ICMP6 packet.
*/
- local_bh_enable();
return NULL;
}
+ sock_net_set(sk, net);
return sk;
}
-static __inline__ void icmpv6_xmit_unlock(struct sock *sk)
+static void icmpv6_xmit_unlock(struct sock *sk)
{
- spin_unlock_bh(&sk->sk_lock.slock);
+ sock_net_set(sk, &init_net);
+ spin_unlock(&sk->sk_lock.slock);
}
/*
@@ -159,29 +151,56 @@ static bool is_ineligible(const struct sk_buff *skb)
tp = skb_header_pointer(skb,
ptr+offsetof(struct icmp6hdr, icmp6_type),
sizeof(_type), &_type);
- if (tp == NULL ||
- !(*tp & ICMPV6_INFOMSG_MASK))
+
+ /* Based on RFC 8200, Section 4.5 Fragment Header, return
+ * false if this is a fragment packet with no icmp header info.
+ */
+ if (!tp && frag_off != 0)
+ return false;
+ else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
return true;
}
return false;
}
+static bool icmpv6_mask_allow(struct net *net, int type)
+{
+ if (type > ICMPV6_MSG_MAX)
+ return true;
+
+ /* Limit if icmp type is set in ratemask. */
+ if (!test_bit(type, net->ipv6.sysctl.icmpv6_ratemask))
+ return true;
+
+ return false;
+}
+
+static bool icmpv6_global_allow(struct net *net, int type,
+ bool *apply_ratelimit)
+{
+ if (icmpv6_mask_allow(net, type))
+ return true;
+
+ if (icmp_global_allow(net)) {
+ *apply_ratelimit = true;
+ return true;
+ }
+ __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL);
+ return false;
+}
+
/*
* Check the ICMP output rate limit
*/
-static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
- struct flowi6 *fl6)
+static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
+ struct flowi6 *fl6, bool apply_ratelimit)
{
- struct dst_entry *dst;
struct net *net = sock_net(sk);
+ struct net_device *dev;
+ struct dst_entry *dst;
bool res = false;
- /* Informational messages are not limited. */
- if (type & ICMPV6_INFOMSG_MASK)
- return true;
-
- /* Do not limit pmtu discovery, it would break it. */
- if (type == ICMPV6_PKT_TOOBIG)
+ if (!apply_ratelimit)
return true;
/*
@@ -190,13 +209,15 @@ static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
* this lookup should be more aggressive (not longer than timeout).
*/
dst = ip6_route_output(net, sk, fl6);
+ rcu_read_lock();
+ dev = dst_dev_rcu(dst);
if (dst->error) {
IP6_INC_STATS(net, ip6_dst_idev(dst),
IPSTATS_MIB_OUTNOROUTES);
- } else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) {
+ } else if (dev && (dev->flags & IFF_LOOPBACK)) {
res = true;
} else {
- struct rt6_info *rt = (struct rt6_info *)dst;
+ struct rt6_info *rt = dst_rt6_info(dst);
int tmo = net->ipv6.sysctl.icmpv6_time;
struct inet_peer *peer;
@@ -204,10 +225,32 @@ static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
if (rt->rt6i_dst.plen < 128)
tmo >>= ((128 - rt->rt6i_dst.plen)>>5);
- peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
+ peer = inet_getpeer_v6(net->ipv6.peers, &fl6->daddr);
res = inet_peer_xrlim_allow(peer, tmo);
- if (peer)
- inet_putpeer(peer);
+ }
+ rcu_read_unlock();
+ if (!res)
+ __ICMP6_INC_STATS(net, NULL, ICMP6_MIB_RATELIMITHOST);
+ else
+ icmp_global_consume(net);
+ dst_release(dst);
+ return res;
+}
+
+static bool icmpv6_rt_has_prefsrc(struct sock *sk, u8 type,
+ struct flowi6 *fl6)
+{
+ struct net *net = sock_net(sk);
+ struct dst_entry *dst;
+ bool res = false;
+
+ dst = ip6_route_output(net, sk, fl6);
+ if (!dst->error) {
+ struct rt6_info *rt = dst_rt6_info(dst);
+ struct in6_addr prefsrc;
+
+ rt6_get_prefsrc(rt, &prefsrc);
+ res = !ipv6_addr_any(&prefsrc);
}
dst_release(dst);
return res;
@@ -226,20 +269,20 @@ static bool opt_unrec(struct sk_buff *skb, __u32 offset)
offset += skb_network_offset(skb);
op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval);
- if (op == NULL)
+ if (!op)
return true;
return (*op & 0xC0) == 0x80;
}
-int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
- struct icmp6hdr *thdr, int len)
+void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
+ struct icmp6hdr *thdr, int len)
{
struct sk_buff *skb;
struct icmp6hdr *icmp6h;
- int err = 0;
- if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
- goto out;
+ skb = skb_peek(&sk->sk_write_queue);
+ if (!skb)
+ return;
icmp6h = icmp6_hdr(skb);
memcpy(icmp6h, thdr, sizeof(struct icmp6hdr));
@@ -267,8 +310,6 @@ int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
tmp_csum);
}
ip6_push_pending_frames(sk);
-out:
- return err;
}
struct icmpv6_msg {
@@ -281,10 +322,10 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st
{
struct icmpv6_msg *msg = (struct icmpv6_msg *) from;
struct sk_buff *org_skb = msg->skb;
- __wsum csum = 0;
+ __wsum csum;
csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset,
- to, len, csum);
+ to, len);
skb->csum = csum_block_add(skb->csum, csum, odd);
if (!(msg->type & ICMPV6_INFOMSG_MASK))
nf_ct_attach(skb, org_skb);
@@ -292,12 +333,10 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st
}
#if IS_ENABLED(CONFIG_IPV6_MIP6)
-static void mip6_addr_swap(struct sk_buff *skb)
+static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt)
{
struct ipv6hdr *iph = ipv6_hdr(skb);
- struct inet6_skb_parm *opt = IP6CB(skb);
struct ipv6_destopt_hao *hao;
- struct in6_addr tmp;
int off;
if (opt->dsthao) {
@@ -305,33 +344,34 @@ static void mip6_addr_swap(struct sk_buff *skb)
if (likely(off >= 0)) {
hao = (struct ipv6_destopt_hao *)
(skb_network_header(skb) + off);
- tmp = iph->saddr;
- iph->saddr = hao->addr;
- hao->addr = tmp;
+ swap(iph->saddr, hao->addr);
}
}
}
#else
-static inline void mip6_addr_swap(struct sk_buff *skb) {}
+static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {}
#endif
-struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
- struct sock *sk, struct flowi6 *fl6)
+static 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;
int err;
- err = ip6_dst_lookup(sk, &dst, fl6);
+ err = ip6_dst_lookup(net, sk, &dst, fl6);
if (err)
return ERR_PTR(err);
/*
* We won't send icmp if the destination is known
- * anycast.
+ * anycast unless we need to treat anycast as unicast.
*/
- if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) {
- LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: acast source\n");
+ if (!READ_ONCE(net->ipv6.sysctl.icmpv6_error_anycast_as_unicast) &&
+ ipv6_anycast_destination(dst, &fl6->daddr)) {
+ net_dbg_ratelimited("icmp6_send: acast source\n");
dst_release(dst);
return ERR_PTR(-EINVAL);
}
@@ -350,11 +390,11 @@ struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
return dst;
}
- err = xfrm_decode_session_reverse(skb, flowi6_to_flowi(&fl2), AF_INET6);
+ err = xfrm_decode_session_reverse(net, skb, flowi6_to_flowi(&fl2), AF_INET6);
if (err)
goto relookup_failed;
- err = ip6_dst_lookup(sk, &dst2, &fl2);
+ err = ip6_dst_lookup(net, sk, &dst2, &fl2);
if (err)
goto relookup_failed;
@@ -377,31 +417,257 @@ relookup_failed:
return ERR_PTR(err);
}
+static struct net_device *icmp6_dev(const struct sk_buff *skb)
+{
+ struct net_device *dev = skb->dev;
+
+ /* for local traffic to local address, skb dev is the loopback
+ * device. Check if there is a dst attached to the skb and if so
+ * get the real device index. Same is needed for replies to a link
+ * local address on a device enslaved to an L3 master device
+ */
+ if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
+ const struct rt6_info *rt6 = skb_rt6_info(skb);
+
+ /* The destination could be an external IP in Ext Hdr (SRv6, RPL, etc.),
+ * and ip6_null_entry could be set to skb if no route is found.
+ */
+ if (rt6 && rt6->rt6i_idev)
+ dev = rt6->rt6i_idev->dev;
+ }
+
+ return dev;
+}
+
+static int icmp6_iif(const struct sk_buff *skb)
+{
+ return icmp6_dev(skb)->ifindex;
+}
+
+struct icmp6_ext_iio_addr6_subobj {
+ __be16 afi;
+ __be16 reserved;
+ struct in6_addr addr6;
+};
+
+static unsigned int icmp6_ext_iio_len(void)
+{
+ return sizeof(struct icmp_extobj_hdr) +
+ /* ifIndex */
+ sizeof(__be32) +
+ /* Interface Address Sub-Object */
+ sizeof(struct icmp6_ext_iio_addr6_subobj) +
+ /* Interface Name Sub-Object. Length must be a multiple of 4
+ * bytes.
+ */
+ ALIGN(sizeof(struct icmp_ext_iio_name_subobj), 4) +
+ /* MTU */
+ sizeof(__be32);
+}
+
+static unsigned int icmp6_ext_max_len(u8 ext_objs)
+{
+ unsigned int ext_max_len;
+
+ ext_max_len = sizeof(struct icmp_ext_hdr);
+
+ if (ext_objs & BIT(ICMP_ERR_EXT_IIO_IIF))
+ ext_max_len += icmp6_ext_iio_len();
+
+ return ext_max_len;
+}
+
+static struct in6_addr *icmp6_ext_iio_addr6_find(const struct net_device *dev)
+{
+ struct inet6_dev *in6_dev;
+ struct inet6_ifaddr *ifa;
+
+ in6_dev = __in6_dev_get(dev);
+ if (!in6_dev)
+ return NULL;
+
+ /* It is unclear from RFC 5837 which IP address should be chosen, but
+ * it makes sense to choose a global unicast address.
+ */
+ list_for_each_entry_rcu(ifa, &in6_dev->addr_list, if_list) {
+ if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DADFAILED))
+ continue;
+ if (ipv6_addr_type(&ifa->addr) != IPV6_ADDR_UNICAST ||
+ ipv6_addr_src_scope(&ifa->addr) != IPV6_ADDR_SCOPE_GLOBAL)
+ continue;
+ return &ifa->addr;
+ }
+
+ return NULL;
+}
+
+static void icmp6_ext_iio_iif_append(struct net *net, struct sk_buff *skb,
+ int iif)
+{
+ struct icmp_ext_iio_name_subobj *name_subobj;
+ struct icmp_extobj_hdr *objh;
+ struct net_device *dev;
+ struct in6_addr *addr6;
+ __be32 data;
+
+ if (!iif)
+ return;
+
+ /* Add the fields in the order specified by RFC 5837. */
+ objh = skb_put(skb, sizeof(*objh));
+ objh->class_num = ICMP_EXT_OBJ_CLASS_IIO;
+ objh->class_type = ICMP_EXT_CTYPE_IIO_ROLE(ICMP_EXT_CTYPE_IIO_ROLE_IIF);
+
+ data = htonl(iif);
+ skb_put_data(skb, &data, sizeof(__be32));
+ objh->class_type |= ICMP_EXT_CTYPE_IIO_IFINDEX;
+
+ rcu_read_lock();
+
+ dev = dev_get_by_index_rcu(net, iif);
+ if (!dev)
+ goto out;
+
+ addr6 = icmp6_ext_iio_addr6_find(dev);
+ if (addr6) {
+ struct icmp6_ext_iio_addr6_subobj *addr6_subobj;
+
+ addr6_subobj = skb_put_zero(skb, sizeof(*addr6_subobj));
+ addr6_subobj->afi = htons(ICMP_AFI_IP6);
+ addr6_subobj->addr6 = *addr6;
+ objh->class_type |= ICMP_EXT_CTYPE_IIO_IPADDR;
+ }
+
+ name_subobj = skb_put_zero(skb, ALIGN(sizeof(*name_subobj), 4));
+ name_subobj->len = ALIGN(sizeof(*name_subobj), 4);
+ netdev_copy_name(dev, name_subobj->name);
+ objh->class_type |= ICMP_EXT_CTYPE_IIO_NAME;
+
+ data = htonl(READ_ONCE(dev->mtu));
+ skb_put_data(skb, &data, sizeof(__be32));
+ objh->class_type |= ICMP_EXT_CTYPE_IIO_MTU;
+
+out:
+ rcu_read_unlock();
+ objh->length = htons(skb_tail_pointer(skb) - (unsigned char *)objh);
+}
+
+static void icmp6_ext_objs_append(struct net *net, struct sk_buff *skb,
+ u8 ext_objs, int iif)
+{
+ if (ext_objs & BIT(ICMP_ERR_EXT_IIO_IIF))
+ icmp6_ext_iio_iif_append(net, skb, iif);
+}
+
+static struct sk_buff *
+icmp6_ext_append(struct net *net, struct sk_buff *skb_in,
+ struct icmp6hdr *icmp6h, unsigned int room, int iif)
+{
+ unsigned int payload_len, ext_max_len, ext_len;
+ struct icmp_ext_hdr *ext_hdr;
+ struct sk_buff *skb;
+ u8 ext_objs;
+ int nhoff;
+
+ switch (icmp6h->icmp6_type) {
+ case ICMPV6_DEST_UNREACH:
+ case ICMPV6_TIME_EXCEED:
+ break;
+ default:
+ return NULL;
+ }
+
+ /* Do not overwrite existing extensions. This can happen when we
+ * receive an ICMPv4 message with extensions from a tunnel and
+ * translate it to an ICMPv6 message towards an IPv6 host in the
+ * overlay network.
+ */
+ if (icmp6h->icmp6_datagram_len)
+ return NULL;
+
+ ext_objs = READ_ONCE(net->ipv6.sysctl.icmpv6_errors_extension_mask);
+ if (!ext_objs)
+ return NULL;
+
+ ext_max_len = icmp6_ext_max_len(ext_objs);
+ if (ICMP_EXT_ORIG_DGRAM_MIN_LEN + ext_max_len > room)
+ return NULL;
+
+ skb = skb_clone(skb_in, GFP_ATOMIC);
+ if (!skb)
+ return NULL;
+
+ nhoff = skb_network_offset(skb);
+ payload_len = min(skb->len - nhoff, ICMP_EXT_ORIG_DGRAM_MIN_LEN);
+
+ if (!pskb_network_may_pull(skb, payload_len))
+ goto free_skb;
+
+ if (pskb_trim(skb, nhoff + ICMP_EXT_ORIG_DGRAM_MIN_LEN) ||
+ __skb_put_padto(skb, nhoff + ICMP_EXT_ORIG_DGRAM_MIN_LEN, false))
+ goto free_skb;
+
+ if (pskb_expand_head(skb, 0, ext_max_len, GFP_ATOMIC))
+ goto free_skb;
+
+ ext_hdr = skb_put_zero(skb, sizeof(*ext_hdr));
+ ext_hdr->version = ICMP_EXT_VERSION_2;
+
+ icmp6_ext_objs_append(net, skb, ext_objs, iif);
+
+ /* Do not send an empty extension structure. */
+ ext_len = skb_tail_pointer(skb) - (unsigned char *)ext_hdr;
+ if (ext_len == sizeof(*ext_hdr))
+ goto free_skb;
+
+ ext_hdr->checksum = ip_compute_csum(ext_hdr, ext_len);
+ /* The length of the original datagram in 64-bit words (RFC 4884). */
+ icmp6h->icmp6_datagram_len = ICMP_EXT_ORIG_DGRAM_MIN_LEN / sizeof(u64);
+
+ return skb;
+
+free_skb:
+ consume_skb(skb);
+ return NULL;
+}
+
/*
* Send an ICMP message in response to a packet in error
*/
-static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
+void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+ const struct in6_addr *force_saddr,
+ const struct inet6_skb_parm *parm)
{
- struct net *net = dev_net(skb->dev);
struct inet6_dev *idev = NULL;
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct sock *sk;
+ struct net *net;
struct ipv6_pinfo *np;
const struct in6_addr *saddr = NULL;
+ bool apply_ratelimit = false;
+ struct sk_buff *ext_skb;
struct dst_entry *dst;
+ unsigned int room;
struct icmp6hdr tmp_hdr;
struct flowi6 fl6;
struct icmpv6_msg msg;
+ struct ipcm6_cookie ipc6;
int iif = 0;
int addr_type = 0;
int len;
- int hlimit;
- int err = 0;
+ u32 mark;
if ((u8 *)hdr < skb->head ||
(skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb))
return;
+ if (!skb->dev)
+ return;
+
+ rcu_read_lock();
+
+ net = dev_net_rcu(skb->dev);
+ mark = IP6_REPLY_MARK(net, skb->mark);
/*
* Make sure we respect the rules
* i.e. RFC 1885 2.4(e)
@@ -410,19 +676,20 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
*/
addr_type = ipv6_addr_type(&hdr->daddr);
- if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0))
+ if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) ||
+ ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr))
saddr = &hdr->daddr;
/*
* Dest addr check
*/
- if ((addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST)) {
+ if (addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST) {
if (type != ICMPV6_PKT_TOOBIG &&
!(type == ICMPV6_PARAMPROB &&
code == ICMPV6_UNK_OPTION &&
(opt_unrec(skb, info))))
- return;
+ goto out;
saddr = NULL;
}
@@ -433,8 +700,15 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
* Source addr check
*/
- if (__ipv6_addr_needs_scope_id(addr_type))
- iif = skb->dev->ifindex;
+ if (__ipv6_addr_needs_scope_id(addr_type)) {
+ iif = icmp6_iif(skb);
+ } else {
+ /*
+ * The source device is used for looking up which routing table
+ * to use for sending an ICMP error.
+ */
+ iif = l3mdev_master_ifindex(skb->dev);
+ }
/*
* Must not send error if the source does not uniquely
@@ -443,37 +717,65 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
* and anycast addresses will be checked later.
*/
if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
- LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: addr_any/mcast source\n");
- return;
+ net_dbg_ratelimited("icmp6_send: addr_any/mcast source [%pI6c > %pI6c]\n",
+ &hdr->saddr, &hdr->daddr);
+ goto out;
}
/*
* Never answer to a ICMP packet.
*/
if (is_ineligible(skb)) {
- LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: no reply to icmp error\n");
- return;
+ net_dbg_ratelimited("icmp6_send: no reply to icmp error [%pI6c > %pI6c]\n",
+ &hdr->saddr, &hdr->daddr);
+ goto out;
}
- mip6_addr_swap(skb);
+ /* Needed by both icmpv6_global_allow and icmpv6_xmit_lock */
+ local_bh_disable();
+
+ /* Check global sysctl_icmp_msgs_per_sec ratelimit */
+ if (!(skb->dev->flags & IFF_LOOPBACK) &&
+ !icmpv6_global_allow(net, type, &apply_ratelimit))
+ goto out_bh_enable;
+
+ mip6_addr_swap(skb, parm);
+
+ sk = icmpv6_xmit_lock(net);
+ if (!sk)
+ goto out_bh_enable;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.daddr = hdr->saddr;
- if (saddr)
+ if (force_saddr)
+ saddr = force_saddr;
+ if (saddr) {
fl6.saddr = *saddr;
+ } else if (!icmpv6_rt_has_prefsrc(sk, type, &fl6)) {
+ /* select a more meaningful saddr from input if */
+ struct net_device *in_netdev;
+
+ in_netdev = dev_get_by_index(net, parm->iif);
+ if (in_netdev) {
+ ipv6_dev_get_saddr(net, in_netdev, &fl6.daddr,
+ inet6_sk(sk)->srcprefs,
+ &fl6.saddr);
+ dev_put(in_netdev);
+ }
+ }
+ fl6.flowi6_mark = mark;
fl6.flowi6_oif = iif;
fl6.fl6_icmp_type = type;
fl6.fl6_icmp_code = code;
- security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
+ fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL);
+ security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6));
- sk = icmpv6_xmit_lock(net);
- if (sk == NULL)
- return;
np = inet6_sk(sk);
- if (!icmpv6_xrlim_allow(sk, type, &fl6))
- goto out;
+ if (!icmpv6_xrlim_allow(sk, type, &fl6, apply_ratelimit))
+ goto out_unlock;
tmp_hdr.icmp6_type = type;
tmp_hdr.icmp6_code = code;
@@ -481,165 +783,286 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
tmp_hdr.icmp6_pointer = htonl(info);
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
- fl6.flowi6_oif = np->mcast_oif;
+ fl6.flowi6_oif = READ_ONCE(np->mcast_oif);
else if (!fl6.flowi6_oif)
- fl6.flowi6_oif = np->ucast_oif;
+ fl6.flowi6_oif = READ_ONCE(np->ucast_oif);
+
+ ipcm6_init_sk(&ipc6, sk);
+ ipc6.sockc.mark = mark;
+ fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
dst = icmpv6_route_lookup(net, skb, sk, &fl6);
if (IS_ERR(dst))
- goto out;
+ goto out_unlock;
- if (ipv6_addr_is_multicast(&fl6.daddr))
- hlimit = np->mcast_hops;
- else
- hlimit = np->hop_limit;
- if (hlimit < 0)
- hlimit = ip6_dst_hoplimit(dst);
+ ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
msg.skb = skb;
msg.offset = skb_network_offset(skb);
msg.type = type;
- len = skb->len - msg.offset;
- len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) -sizeof(struct icmp6hdr));
+ room = IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr);
+ ext_skb = icmp6_ext_append(net, skb, &tmp_hdr, room, parm->iif);
+ if (ext_skb)
+ msg.skb = ext_skb;
+
+ len = msg.skb->len - msg.offset;
+ len = min_t(unsigned int, len, room);
if (len < 0) {
- LIMIT_NETDEBUG(KERN_DEBUG "icmp: len problem\n");
+ net_dbg_ratelimited("icmp: len problem [%pI6c > %pI6c]\n",
+ &hdr->saddr, &hdr->daddr);
goto out_dst_release;
}
- rcu_read_lock();
idev = __in6_dev_get(skb->dev);
- err = ip6_append_data(sk, icmpv6_getfrag, &msg,
- len + sizeof(struct icmp6hdr),
- sizeof(struct icmp6hdr), hlimit,
- np->tclass, NULL, &fl6, (struct rt6_info *)dst,
- MSG_DONTWAIT, np->dontfrag);
- if (err) {
- ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
+ if (ip6_append_data(sk, icmpv6_getfrag, &msg,
+ len + sizeof(struct icmp6hdr),
+ sizeof(struct icmp6hdr),
+ &ipc6, &fl6, dst_rt6_info(dst),
+ MSG_DONTWAIT)) {
+ ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
ip6_flush_pending_frames(sk);
} else {
- err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
- len + sizeof(struct icmp6hdr));
+ icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
+ len + sizeof(struct icmp6hdr));
}
- rcu_read_unlock();
+
out_dst_release:
+ if (ext_skb)
+ consume_skb(ext_skb);
dst_release(dst);
-out:
+out_unlock:
icmpv6_xmit_unlock(sk);
+out_bh_enable:
+ local_bh_enable();
+out:
+ rcu_read_unlock();
}
+EXPORT_SYMBOL(icmp6_send);
-/* Slightly more convenient version of icmp6_send.
+/* Slightly more convenient version of icmp6_send with drop reasons.
*/
-void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
+void icmpv6_param_prob_reason(struct sk_buff *skb, u8 code, int pos,
+ enum skb_drop_reason reason)
{
- icmp6_send(skb, ICMPV6_PARAMPROB, code, pos);
- kfree_skb(skb);
+ icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb));
+ kfree_skb_reason(skb, reason);
}
-static void icmpv6_echo_reply(struct sk_buff *skb)
+/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
+ * if sufficient data bytes are available
+ * @nhs is the size of the tunnel header(s) :
+ * Either an IPv4 header for SIT encap
+ * an IPv4 header + GRE header for GRE encap
+ */
+int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
+ unsigned int data_len)
{
- struct net *net = dev_net(skb->dev);
+ struct in6_addr temp_saddr;
+ struct rt6_info *rt;
+ struct sk_buff *skb2;
+ u32 info = 0;
+
+ if (!pskb_may_pull(skb, nhs + sizeof(struct ipv6hdr) + 8))
+ return 1;
+
+ /* RFC 4884 (partial) support for ICMP extensions */
+ if (data_len < 128 || (data_len & 7) || skb->len < data_len)
+ data_len = 0;
+
+ skb2 = data_len ? skb_copy(skb, GFP_ATOMIC) : skb_clone(skb, GFP_ATOMIC);
+
+ if (!skb2)
+ return 1;
+
+ skb_dst_drop(skb2);
+ skb_pull(skb2, nhs);
+ skb_reset_network_header(skb2);
+
+ rt = rt6_lookup(dev_net_rcu(skb->dev), &ipv6_hdr(skb2)->saddr,
+ NULL, 0, skb, 0);
+
+ if (rt && rt->dst.dev)
+ skb2->dev = rt->dst.dev;
+
+ ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &temp_saddr);
+
+ if (data_len) {
+ /* RFC 4884 (partial) support :
+ * insert 0 padding at the end, before the extensions
+ */
+ __skb_push(skb2, nhs);
+ skb_reset_network_header(skb2);
+ memmove(skb2->data, skb2->data + nhs, data_len - nhs);
+ memset(skb2->data + data_len - nhs, 0, nhs);
+ /* RFC 4884 4.5 : Length is measured in 64-bit words,
+ * and stored in reserved[0]
+ */
+ info = (data_len/8) << 24;
+ }
+ if (type == ICMP_TIME_EXCEEDED)
+ icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
+ info, &temp_saddr, IP6CB(skb2));
+ else
+ icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH,
+ info, &temp_saddr, IP6CB(skb2));
+ if (rt)
+ ip6_rt_put(rt);
+
+ kfree_skb(skb2);
+
+ return 0;
+}
+EXPORT_SYMBOL(ip6_err_gen_icmpv6_unreach);
+
+static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb)
+{
+ struct net *net = dev_net_rcu(skb->dev);
struct sock *sk;
struct inet6_dev *idev;
struct ipv6_pinfo *np;
const struct in6_addr *saddr = NULL;
struct icmp6hdr *icmph = icmp6_hdr(skb);
+ bool apply_ratelimit = false;
struct icmp6hdr tmp_hdr;
struct flowi6 fl6;
struct icmpv6_msg msg;
struct dst_entry *dst;
- int err = 0;
- int hlimit;
+ struct ipcm6_cookie ipc6;
+ u32 mark = IP6_REPLY_MARK(net, skb->mark);
+ SKB_DR(reason);
+ bool acast;
+ u8 type;
+
+ if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) &&
+ net->ipv6.sysctl.icmpv6_echo_ignore_multicast)
+ return reason;
saddr = &ipv6_hdr(skb)->daddr;
- if (!ipv6_unicast_destination(skb))
+ acast = ipv6_anycast_destination(skb_dst(skb), saddr);
+ if (acast && net->ipv6.sysctl.icmpv6_echo_ignore_anycast)
+ return reason;
+
+ if (!ipv6_unicast_destination(skb) &&
+ !(net->ipv6.sysctl.anycast_src_echo_reply && acast))
saddr = NULL;
+ if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST)
+ type = ICMPV6_EXT_ECHO_REPLY;
+ else
+ type = ICMPV6_ECHO_REPLY;
+
memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr));
- tmp_hdr.icmp6_type = ICMPV6_ECHO_REPLY;
+ tmp_hdr.icmp6_type = type;
memset(&fl6, 0, sizeof(fl6));
+ if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES)
+ fl6.flowlabel = ip6_flowlabel(ipv6_hdr(skb));
+
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.daddr = ipv6_hdr(skb)->saddr;
if (saddr)
fl6.saddr = *saddr;
- fl6.flowi6_oif = skb->dev->ifindex;
- fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
- security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
+ fl6.flowi6_oif = icmp6_iif(skb);
+ fl6.fl6_icmp_type = type;
+ fl6.flowi6_mark = mark;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
+ security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6));
+ local_bh_disable();
sk = icmpv6_xmit_lock(net);
- if (sk == NULL)
- return;
+ if (!sk)
+ goto out_bh_enable;
np = inet6_sk(sk);
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
- fl6.flowi6_oif = np->mcast_oif;
+ fl6.flowi6_oif = READ_ONCE(np->mcast_oif);
else if (!fl6.flowi6_oif)
- fl6.flowi6_oif = np->ucast_oif;
+ fl6.flowi6_oif = READ_ONCE(np->ucast_oif);
- err = ip6_dst_lookup(sk, &dst, &fl6);
- if (err)
+ if (ip6_dst_lookup(net, sk, &dst, &fl6))
goto out;
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0);
if (IS_ERR(dst))
goto out;
- if (ipv6_addr_is_multicast(&fl6.daddr))
- hlimit = np->mcast_hops;
- else
- hlimit = np->hop_limit;
- if (hlimit < 0)
- hlimit = ip6_dst_hoplimit(dst);
+ /* Check the ratelimit */
+ if ((!(skb->dev->flags & IFF_LOOPBACK) &&
+ !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY, &apply_ratelimit)) ||
+ !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6, apply_ratelimit))
+ goto out_dst_release;
idev = __in6_dev_get(skb->dev);
msg.skb = skb;
msg.offset = 0;
- msg.type = ICMPV6_ECHO_REPLY;
+ msg.type = type;
+
+ ipcm6_init_sk(&ipc6, sk);
+ ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
+ ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb));
+ ipc6.sockc.mark = mark;
- err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),
- sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl6,
- (struct rt6_info *)dst, MSG_DONTWAIT,
- np->dontfrag);
+ if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST)
+ if (!icmp_build_probe(skb, (struct icmphdr *)&tmp_hdr))
+ goto out_dst_release;
- if (err) {
- ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
+ if (ip6_append_data(sk, icmpv6_getfrag, &msg,
+ skb->len + sizeof(struct icmp6hdr),
+ sizeof(struct icmp6hdr), &ipc6, &fl6,
+ dst_rt6_info(dst), MSG_DONTWAIT)) {
+ __ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
ip6_flush_pending_frames(sk);
} else {
- err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
- skb->len + sizeof(struct icmp6hdr));
+ icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
+ skb->len + sizeof(struct icmp6hdr));
+ reason = SKB_CONSUMED;
}
+out_dst_release:
dst_release(dst);
out:
icmpv6_xmit_unlock(sk);
+out_bh_enable:
+ local_bh_enable();
+ return reason;
}
-void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)
+enum skb_drop_reason icmpv6_notify(struct sk_buff *skb, u8 type,
+ u8 code, __be32 info)
{
+ struct inet6_skb_parm *opt = IP6CB(skb);
+ struct net *net = dev_net_rcu(skb->dev);
const struct inet6_protocol *ipprot;
+ enum skb_drop_reason reason;
int inner_offset;
__be16 frag_off;
u8 nexthdr;
- if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
- return;
+ reason = pskb_may_pull_reason(skb, sizeof(struct ipv6hdr));
+ if (reason != SKB_NOT_DROPPED_YET)
+ goto out;
+
+ seg6_icmp_srh(skb, opt);
nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr;
if (ipv6_ext_hdr(nexthdr)) {
/* now skip over extension headers */
inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
&nexthdr, &frag_off);
- if (inner_offset<0)
- return;
+ if (inner_offset < 0) {
+ SKB_DR_SET(reason, IPV6_BAD_EXTHDR);
+ goto out;
+ }
} else {
inner_offset = sizeof(struct ipv6hdr);
}
/* Checkin header including 8 bytes of inner protocol header. */
- if (!pskb_may_pull(skb, inner_offset+8))
- return;
+ reason = pskb_may_pull_reason(skb, inner_offset + 8);
+ if (reason != SKB_NOT_DROPPED_YET)
+ goto out;
/* BUGGG_FUTURE: we should try to parse exthdrs in this packet.
Without this we will not able f.e. to make source routed
@@ -648,13 +1071,16 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)
--ANK (980726)
*/
- rcu_read_lock();
ipprot = rcu_dereference(inet6_protos[nexthdr]);
if (ipprot && ipprot->err_handler)
- ipprot->err_handler(skb, NULL, type, code, inner_offset, info);
- rcu_read_unlock();
+ ipprot->err_handler(skb, opt, type, code, inner_offset, info);
raw6_icmp_error(skb, nexthdr, type, code, inner_offset, info);
+ return SKB_CONSUMED;
+
+out:
+ __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
+ return reason;
}
/*
@@ -663,7 +1089,9 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)
static int icmpv6_rcv(struct sk_buff *skb)
{
- struct net_device *dev = skb->dev;
+ enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
+ struct net *net = dev_net_rcu(skb->dev);
+ struct net_device *dev = icmp6_dev(skb);
struct inet6_dev *idev = __in6_dev_get(dev);
const struct in6_addr *saddr, *daddr;
struct icmp6hdr *hdr;
@@ -674,8 +1102,10 @@ static int icmpv6_rcv(struct sk_buff *skb)
int nh;
if (!(sp && sp->xvec[sp->len - 1]->props.flags &
- XFRM_STATE_ICMP))
+ XFRM_STATE_ICMP)) {
+ reason = SKB_DROP_REASON_XFRM_POLICY;
goto drop_no_count;
+ }
if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr)))
goto drop_no_count;
@@ -683,33 +1113,24 @@ static int icmpv6_rcv(struct sk_buff *skb)
nh = skb_network_offset(skb);
skb_set_network_header(skb, sizeof(*hdr));
- if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN, skb))
+ if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN,
+ skb)) {
+ reason = SKB_DROP_REASON_XFRM_POLICY;
goto drop_no_count;
+ }
skb_set_network_header(skb, nh);
}
- ICMP6_INC_STATS_BH(dev_net(dev), idev, ICMP6_MIB_INMSGS);
+ __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INMSGS);
saddr = &ipv6_hdr(skb)->saddr;
daddr = &ipv6_hdr(skb)->daddr;
- /* Perform checksum. */
- switch (skb->ip_summed) {
- case CHECKSUM_COMPLETE:
- if (!csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6,
- skb->csum))
- break;
- /* fall through */
- case CHECKSUM_NONE:
- 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 [%pI6c > %pI6c]\n",
- saddr, daddr);
- goto csum_error;
- }
+ if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) {
+ net_dbg_ratelimited("ICMPv6 checksum failed [%pI6c > %pI6c]\n",
+ saddr, daddr);
+ goto csum_error;
}
if (!pskb_pull(skb, sizeof(*hdr)))
@@ -719,16 +1140,23 @@ static int icmpv6_rcv(struct sk_buff *skb)
type = hdr->icmp6_type;
- ICMP6MSGIN_INC_STATS_BH(dev_net(dev), idev, type);
+ ICMP6MSGIN_INC_STATS(dev_net_rcu(dev), idev, type);
switch (type) {
case ICMPV6_ECHO_REQUEST:
- icmpv6_echo_reply(skb);
+ if (!net->ipv6.sysctl.icmpv6_echo_ignore_all)
+ reason = icmpv6_echo_reply(skb);
+ break;
+ case ICMPV6_EXT_ECHO_REQUEST:
+ if (!net->ipv6.sysctl.icmpv6_echo_ignore_all &&
+ READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe))
+ reason = icmpv6_echo_reply(skb);
break;
case ICMPV6_ECHO_REPLY:
+ case ICMPV6_EXT_ECHO_REPLY:
ping_rcv(skb);
- break;
+ return 0;
case ICMPV6_PKT_TOOBIG:
/* BUGGG_FUTURE: if packet contains rthdr, we cannot update
@@ -740,14 +1168,13 @@ static int icmpv6_rcv(struct sk_buff *skb)
goto discard_it;
hdr = icmp6_hdr(skb);
- /*
- * Drop through to notify
- */
-
+ /* to notify */
+ fallthrough;
case ICMPV6_DEST_UNREACH:
case ICMPV6_TIME_EXCEED:
case ICMPV6_PARAMPROB:
- icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
+ reason = icmpv6_notify(skb, type, hdr->icmp6_code,
+ hdr->icmp6_mtu);
break;
case NDISC_ROUTER_SOLICITATION:
@@ -755,16 +1182,16 @@ static int icmpv6_rcv(struct sk_buff *skb)
case NDISC_NEIGHBOUR_SOLICITATION:
case NDISC_NEIGHBOUR_ADVERTISEMENT:
case NDISC_REDIRECT:
- ndisc_rcv(skb);
+ reason = ndisc_rcv(skb);
break;
case ICMPV6_MGM_QUERY:
igmp6_event_query(skb);
- break;
+ return 0;
case ICMPV6_MGM_REPORT:
igmp6_event_report(skb);
- break;
+ return 0;
case ICMPV6_MGM_REDUCTION:
case ICMPV6_NI_QUERY:
@@ -777,119 +1204,77 @@ static int icmpv6_rcv(struct sk_buff *skb)
break;
default:
- LIMIT_NETDEBUG(KERN_DEBUG "icmpv6: msg of unknown type\n");
-
/* informational */
if (type & ICMPV6_INFOMSG_MASK)
break;
+ net_dbg_ratelimited("icmpv6: msg of unknown type [%pI6c > %pI6c]\n",
+ saddr, daddr);
+
/*
* error of unknown type.
* must pass to upper level
*/
- icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
+ reason = icmpv6_notify(skb, type, hdr->icmp6_code,
+ hdr->icmp6_mtu);
}
- kfree_skb(skb);
+ /* until the v6 path can be better sorted assume failure and
+ * preserve the status quo behaviour for the rest of the paths to here
+ */
+ if (reason)
+ kfree_skb_reason(skb, reason);
+ else
+ consume_skb(skb);
+
return 0;
csum_error:
- ICMP6_INC_STATS_BH(dev_net(dev), idev, ICMP6_MIB_CSUMERRORS);
+ reason = SKB_DROP_REASON_ICMP_CSUM;
+ __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_CSUMERRORS);
discard_it:
- ICMP6_INC_STATS_BH(dev_net(dev), idev, ICMP6_MIB_INERRORS);
+ __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INERRORS);
drop_no_count:
- kfree_skb(skb);
+ kfree_skb_reason(skb, reason);
return 0;
}
-void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
- u8 type,
+void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type,
const struct in6_addr *saddr,
- const struct in6_addr *daddr,
- int oif)
+ const struct in6_addr *daddr, int oif)
{
memset(fl6, 0, sizeof(*fl6));
fl6->saddr = *saddr;
fl6->daddr = *daddr;
- fl6->flowi6_proto = IPPROTO_ICMPV6;
+ fl6->flowi6_proto = IPPROTO_ICMPV6;
fl6->fl6_icmp_type = type;
fl6->fl6_icmp_code = 0;
fl6->flowi6_oif = oif;
- security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
+ security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
}
-/*
- * Special lock-class for __icmpv6_sk:
- */
-static struct lock_class_key icmpv6_socket_sk_dst_lock_key;
-
-static int __net_init icmpv6_sk_init(struct net *net)
+int __init icmpv6_init(void)
{
struct sock *sk;
- int err, i, j;
-
- net->ipv6.icmp_sk =
- kzalloc(nr_cpu_ids * sizeof(struct sock *), GFP_KERNEL);
- if (net->ipv6.icmp_sk == NULL)
- return -ENOMEM;
+ int err, i;
for_each_possible_cpu(i) {
err = inet_ctl_sock_create(&sk, PF_INET6,
- SOCK_RAW, IPPROTO_ICMPV6, net);
+ SOCK_RAW, IPPROTO_ICMPV6, &init_net);
if (err < 0) {
pr_err("Failed to initialize the ICMP6 control socket (err %d)\n",
err);
- goto fail;
+ return err;
}
- net->ipv6.icmp_sk[i] = sk;
-
- /*
- * Split off their lock-class, because sk->sk_dst_lock
- * gets used from softirqs, which is safe for
- * __icmpv6_sk (because those never get directly used
- * via userspace syscalls), but unsafe for normal sockets.
- */
- lockdep_set_class(&sk->sk_dst_lock,
- &icmpv6_socket_sk_dst_lock_key);
+ per_cpu(ipv6_icmp_sk, i) = sk;
/* Enough space for 2 64K ICMP packets, including
* sk_buff struct overhead.
*/
sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024);
}
- return 0;
-
- fail:
- for (j = 0; j < i; j++)
- inet_ctl_sock_destroy(net->ipv6.icmp_sk[j]);
- kfree(net->ipv6.icmp_sk);
- return err;
-}
-
-static void __net_exit icmpv6_sk_exit(struct net *net)
-{
- int i;
-
- for_each_possible_cpu(i) {
- inet_ctl_sock_destroy(net->ipv6.icmp_sk[i]);
- }
- kfree(net->ipv6.icmp_sk);
-}
-
-static struct pernet_operations icmpv6_sk_ops = {
- .init = icmpv6_sk_init,
- .exit = icmpv6_sk_exit,
-};
-
-int __init icmpv6_init(void)
-{
- int err;
-
- err = register_pernet_subsys(&icmpv6_sk_ops);
- if (err < 0)
- return err;
err = -EAGAIN;
if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0)
@@ -904,14 +1289,12 @@ sender_reg_err:
inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
fail:
pr_err("Failed to register ICMP6 protocol\n");
- unregister_pernet_subsys(&icmpv6_sk_ops);
return err;
}
void icmpv6_cleanup(void)
{
inet6_unregister_icmp_sender(icmp6_send);
- unregister_pernet_subsys(&icmpv6_sk_ops);
inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
}
@@ -940,6 +1323,14 @@ static const struct icmp6_err {
.err = ECONNREFUSED,
.fatal = 1,
},
+ { /* POLICY_FAIL */
+ .err = EACCES,
+ .fatal = 1,
+ },
+ { /* REJECT_ROUTE */
+ .err = EACCES,
+ .fatal = 1,
+ },
};
int icmpv6_err_convert(u8 type, u8 code, int *err)
@@ -951,7 +1342,7 @@ int icmpv6_err_convert(u8 type, u8 code, int *err)
switch (type) {
case ICMPV6_DEST_UNREACH:
fatal = 1;
- if (code <= ICMPV6_PORT_UNREACH) {
+ if (code < ARRAY_SIZE(tab_unreach)) {
*err = tab_unreach[code].err;
fatal = tab_unreach[code].fatal;
}
@@ -976,7 +1367,11 @@ int icmpv6_err_convert(u8 type, u8 code, int *err)
EXPORT_SYMBOL(icmpv6_err_convert);
#ifdef CONFIG_SYSCTL
-struct ctl_table ipv6_icmp_table_template[] = {
+
+static u32 icmpv6_errors_extension_mask_all =
+ GENMASK_U8(ICMP_ERR_EXT_COUNT - 1, 0);
+
+static struct ctl_table ipv6_icmp_table_template[] = {
{
.procname = "ratelimit",
.data = &init_net.ipv6.sysctl.icmpv6_time,
@@ -984,7 +1379,52 @@ struct ctl_table ipv6_icmp_table_template[] = {
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
- { },
+ {
+ .procname = "echo_ignore_all",
+ .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_all,
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ },
+ {
+ .procname = "echo_ignore_multicast",
+ .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_multicast,
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ },
+ {
+ .procname = "echo_ignore_anycast",
+ .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_anycast,
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ },
+ {
+ .procname = "ratemask",
+ .data = &init_net.ipv6.sysctl.icmpv6_ratemask_ptr,
+ .maxlen = ICMPV6_MSG_MAX + 1,
+ .mode = 0644,
+ .proc_handler = proc_do_large_bitmap,
+ },
+ {
+ .procname = "error_anycast_as_unicast",
+ .data = &init_net.ipv6.sysctl.icmpv6_error_anycast_as_unicast,
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
+ {
+ .procname = "errors_extension_mask",
+ .data = &init_net.ipv6.sysctl.icmpv6_errors_extension_mask,
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = &icmpv6_errors_extension_mask_all,
+ },
};
struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
@@ -995,10 +1435,20 @@ struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
sizeof(ipv6_icmp_table_template),
GFP_KERNEL);
- if (table)
+ if (table) {
table[0].data = &net->ipv6.sysctl.icmpv6_time;
-
+ table[1].data = &net->ipv6.sysctl.icmpv6_echo_ignore_all;
+ table[2].data = &net->ipv6.sysctl.icmpv6_echo_ignore_multicast;
+ table[3].data = &net->ipv6.sysctl.icmpv6_echo_ignore_anycast;
+ table[4].data = &net->ipv6.sysctl.icmpv6_ratemask_ptr;
+ table[5].data = &net->ipv6.sysctl.icmpv6_error_anycast_as_unicast;
+ table[6].data = &net->ipv6.sysctl.icmpv6_errors_extension_mask;
+ }
return table;
}
-#endif
+size_t ipv6_icmp_sysctl_table_size(void)
+{
+ return ARRAY_SIZE(ipv6_icmp_table_template);
+}
+#endif
generated by cgit (git 2.34.1) at 2025-12-21 23:51:16 +0000