summaryrefslogtreecommitdiff
path: root/net/ipv6/ndisc.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/ndisc.c')
-rw-r--r--net/ipv6/ndisc.c725
1 files changed, 413 insertions, 312 deletions
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 659ecf4e4b3c..59d17b6f06bf 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Neighbour Discovery for IPv6
* Linux INET6 implementation
@@ -5,11 +6,6 @@
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
* Mike Shaver <shaver@ingenia.com>
- *
- * 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.
*/
/*
@@ -77,12 +73,15 @@ static u32 ndisc_hash(const void *pkey,
const struct net_device *dev,
__u32 *hash_rnd);
static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey);
+static bool ndisc_allow_add(const struct net_device *dev,
+ struct netlink_ext_ack *extack);
static int ndisc_constructor(struct neighbour *neigh);
static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
static int pndisc_constructor(struct pneigh_entry *n);
static void pndisc_destructor(struct pneigh_entry *n);
static void pndisc_redo(struct sk_buff *skb);
+static int ndisc_is_multicast(const void *pkey);
static const struct neigh_ops ndisc_generic_ops = {
.family = AF_INET6,
@@ -117,6 +116,8 @@ struct neigh_table nd_tbl = {
.pconstructor = pndisc_constructor,
.pdestructor = pndisc_destructor,
.proxy_redo = pndisc_redo,
+ .is_multicast = ndisc_is_multicast,
+ .allow_add = ndisc_allow_add,
.id = "ndisc_cache",
.parms = {
.tbl = &nd_tbl,
@@ -127,8 +128,9 @@ struct neigh_table nd_tbl = {
[NEIGH_VAR_RETRANS_TIME] = ND_RETRANS_TIMER,
[NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME,
[NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ,
+ [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ,
[NEIGH_VAR_GC_STALETIME] = 60 * HZ,
- [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX,
+ [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_DEFAULT,
[NEIGH_VAR_PROXY_QLEN] = 64,
[NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ,
[NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10,
@@ -141,7 +143,7 @@ struct neigh_table nd_tbl = {
};
EXPORT_SYMBOL_GPL(nd_tbl);
-void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data,
+void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data,
int data_len, int pad)
{
int space = __ndisc_opt_addr_space(data_len, pad);
@@ -164,7 +166,7 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data,
EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option);
static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type,
- void *data, u8 icmp6_type)
+ const void *data, u8 icmp6_type)
{
__ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len,
ndisc_addr_option_pad(skb->dev->type));
@@ -195,9 +197,12 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
static inline int ndisc_is_useropt(const struct net_device *dev,
struct nd_opt_hdr *opt)
{
- return opt->nd_opt_type == ND_OPT_RDNSS ||
+ return opt->nd_opt_type == ND_OPT_PREFIX_INFO ||
+ opt->nd_opt_type == ND_OPT_RDNSS ||
opt->nd_opt_type == ND_OPT_DNSSL ||
- ndisc_ops_is_useropt(dev, opt->nd_opt_type);
+ opt->nd_opt_type == ND_OPT_6CO ||
+ opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL ||
+ opt->nd_opt_type == ND_OPT_PREF64;
}
static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev,
@@ -222,6 +227,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
return NULL;
memset(ndopts, 0, sizeof(*ndopts));
while (opt_len) {
+ bool unknown = false;
int l;
if (opt_len < sizeof(struct nd_opt_hdr))
return NULL;
@@ -237,9 +243,8 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
case ND_OPT_NONCE:
case ND_OPT_REDIRECT_HDR:
if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) {
- ND_PRINTK(2, warn,
- "%s: duplicated ND6 option found: type=%d\n",
- __func__, nd_opt->nd_opt_type);
+ net_dbg_ratelimited("%s: duplicated ND6 option found: type=%d\n",
+ __func__, nd_opt->nd_opt_type);
} else {
ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt;
}
@@ -257,22 +262,20 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
break;
#endif
default:
- if (ndisc_is_useropt(dev, nd_opt)) {
- ndopts->nd_useropts_end = nd_opt;
- if (!ndopts->nd_useropts)
- ndopts->nd_useropts = nd_opt;
- } else {
- /*
- * Unknown options must be silently ignored,
- * to accommodate future extension to the
- * protocol.
- */
- ND_PRINTK(2, notice,
- "%s: ignored unsupported option; type=%d, len=%d\n",
- __func__,
- nd_opt->nd_opt_type,
- nd_opt->nd_opt_len);
- }
+ unknown = true;
+ }
+ if (ndisc_is_useropt(dev, nd_opt)) {
+ ndopts->nd_useropts_end = nd_opt;
+ if (!ndopts->nd_useropts)
+ ndopts->nd_useropts = nd_opt;
+ } else if (unknown) {
+ /*
+ * Unknown options must be silently ignored,
+ * to accommodate future extension to the
+ * protocol.
+ */
+ net_dbg_ratelimited("%s: ignored unsupported option; type=%d, len=%d\n",
+ __func__, nd_opt->nd_opt_type, nd_opt->nd_opt_len);
}
next_opt:
opt_len -= l;
@@ -370,42 +373,53 @@ static int ndisc_constructor(struct neighbour *neigh)
static int pndisc_constructor(struct pneigh_entry *n)
{
struct in6_addr *addr = (struct in6_addr *)&n->key;
- struct in6_addr maddr;
struct net_device *dev = n->dev;
+ struct in6_addr maddr;
- if (!dev || !__in6_dev_get(dev))
+ if (!dev)
return -EINVAL;
+
addrconf_addr_solict_mult(addr, &maddr);
- ipv6_dev_mc_inc(dev, &maddr);
- return 0;
+ return ipv6_dev_mc_inc(dev, &maddr);
}
static void pndisc_destructor(struct pneigh_entry *n)
{
struct in6_addr *addr = (struct in6_addr *)&n->key;
- struct in6_addr maddr;
struct net_device *dev = n->dev;
+ struct in6_addr maddr;
- if (!dev || !__in6_dev_get(dev))
+ if (!dev)
return;
+
addrconf_addr_solict_mult(addr, &maddr);
ipv6_dev_mc_dec(dev, &maddr);
}
+/* called with rtnl held */
+static bool ndisc_allow_add(const struct net_device *dev,
+ struct netlink_ext_ack *extack)
+{
+ struct inet6_dev *idev = __in6_dev_get(dev);
+
+ if (!idev || idev->cnf.disable_ipv6) {
+ NL_SET_ERR_MSG(extack, "IPv6 is disabled on this device");
+ return false;
+ }
+
+ return true;
+}
+
static struct sk_buff *ndisc_alloc_skb(struct net_device *dev,
int len)
{
int hlen = LL_RESERVED_SPACE(dev);
int tlen = dev->needed_tailroom;
- struct sock *sk = dev_net(dev)->ipv6.ndisc_sk;
struct sk_buff *skb;
skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC);
- if (!skb) {
- ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb\n",
- __func__);
+ if (!skb)
return NULL;
- }
skb->protocol = htons(ETH_P_IPV6);
skb->dev = dev;
@@ -416,7 +430,9 @@ static struct sk_buff *ndisc_alloc_skb(struct net_device *dev,
/* Manually assign socket ownership as we avoid calling
* sock_alloc_send_pskb() to bypass wmem buffer limits
*/
- skb_set_owner_w(skb, sk);
+ rcu_read_lock();
+ skb_set_owner_w(skb, dev_net_rcu(dev)->ipv6.ndisc_sk);
+ rcu_read_unlock();
return skb;
}
@@ -432,7 +448,7 @@ static void ip6_nd_hdr(struct sk_buff *skb,
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
- tclass = idev ? idev->cnf.ndisc_tclass : 0;
+ tclass = idev ? READ_ONCE(idev->cnf.ndisc_tclass) : 0;
rcu_read_unlock();
skb_push(skb, sizeof(*hdr));
@@ -449,20 +465,24 @@ static void ip6_nd_hdr(struct sk_buff *skb,
hdr->daddr = *daddr;
}
-static void ndisc_send_skb(struct sk_buff *skb,
- const struct in6_addr *daddr,
- const struct in6_addr *saddr)
+void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr,
+ const struct in6_addr *saddr)
{
+ struct icmp6hdr *icmp6h = icmp6_hdr(skb);
struct dst_entry *dst = skb_dst(skb);
- struct net *net = dev_net(skb->dev);
- struct sock *sk = net->ipv6.ndisc_sk;
+ struct net_device *dev;
struct inet6_dev *idev;
+ struct net *net;
+ struct sock *sk;
int err;
- struct icmp6hdr *icmp6h = icmp6_hdr(skb);
u8 type;
type = icmp6h->icmp6_type;
+ rcu_read_lock();
+
+ net = dev_net_rcu(skb->dev);
+ sk = net->ipv6.ndisc_sk;
if (!dst) {
struct flowi6 fl6;
int oif = skb->dev->ifindex;
@@ -470,6 +490,7 @@ static void ndisc_send_skb(struct sk_buff *skb,
icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif);
dst = icmp6_dst_alloc(skb->dev, &fl6);
if (IS_ERR(dst)) {
+ rcu_read_unlock();
kfree_skb(skb);
return;
}
@@ -482,14 +503,14 @@ static void ndisc_send_skb(struct sk_buff *skb,
csum_partial(icmp6h,
skb->len, 0));
- ip6_nd_hdr(skb, saddr, daddr, inet6_sk(sk)->hop_limit, skb->len);
+ ip6_nd_hdr(skb, saddr, daddr, READ_ONCE(inet6_sk(sk)->hop_limit), skb->len);
- rcu_read_lock();
- idev = __in6_dev_get(dst->dev);
- IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len);
+ dev = dst_dev_rcu(dst);
+ idev = __in6_dev_get(dev);
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS);
err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
- net, sk, skb, NULL, dst->dev,
+ net, sk, skb, NULL, dev,
dst_output);
if (!err) {
ICMP6MSGOUT_INC_STATS(net, idev, type);
@@ -498,6 +519,7 @@ static void ndisc_send_skb(struct sk_buff *skb,
rcu_read_unlock();
}
+EXPORT_SYMBOL(ndisc_send_skb);
void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr,
const struct in6_addr *solicited_addr,
@@ -516,7 +538,7 @@ void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr,
src_addr = solicited_addr;
if (ifp->flags & IFA_F_OPTIMISTIC)
override = false;
- inc_opt |= ifp->idev->cnf.force_tllao;
+ inc_opt |= READ_ONCE(ifp->idev->cnf.force_tllao);
in6_ifa_put(ifp);
} else {
if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr,
@@ -581,22 +603,16 @@ static void ndisc_send_unsol_na(struct net_device *dev)
in6_dev_put(idev);
}
-void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
- const struct in6_addr *daddr, const struct in6_addr *saddr,
- u64 nonce)
+struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit,
+ const struct in6_addr *saddr, u64 nonce)
{
- struct sk_buff *skb;
- struct in6_addr addr_buf;
int inc_opt = dev->addr_len;
- int optlen = 0;
+ struct sk_buff *skb;
struct nd_msg *msg;
+ int optlen = 0;
- if (!saddr) {
- if (ipv6_get_lladdr(dev, &addr_buf,
- (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)))
- return;
- saddr = &addr_buf;
- }
+ if (!saddr)
+ return NULL;
if (ipv6_addr_any(saddr))
inc_opt = false;
@@ -608,7 +624,7 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
if (!skb)
- return;
+ return NULL;
msg = skb_put(skb, sizeof(*msg));
*msg = (struct nd_msg) {
@@ -630,7 +646,28 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
memcpy(opt + 2, &nonce, 6);
}
- ndisc_send_skb(skb, daddr, saddr);
+ return skb;
+}
+EXPORT_SYMBOL(ndisc_ns_create);
+
+void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
+ const struct in6_addr *daddr, const struct in6_addr *saddr,
+ u64 nonce)
+{
+ struct in6_addr addr_buf;
+ struct sk_buff *skb;
+
+ if (!saddr) {
+ if (ipv6_get_lladdr(dev, &addr_buf,
+ (IFA_F_TENTATIVE | IFA_F_OPTIMISTIC)))
+ return;
+ saddr = &addr_buf;
+ }
+
+ skb = ndisc_ns_create(dev, solicit, saddr, nonce);
+
+ if (skb)
+ ndisc_send_skb(skb, daddr, saddr);
}
void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr,
@@ -712,10 +749,9 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
saddr = &ipv6_hdr(skb)->saddr;
probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES);
if (probes < 0) {
- if (!(neigh->nud_state & NUD_VALID)) {
- ND_PRINTK(1, dbg,
- "%s: trying to ucast probe in NUD_INVALID: %pI6\n",
- __func__, target);
+ if (!(READ_ONCE(neigh->nud_state) & NUD_VALID)) {
+ net_dbg_ratelimited("%s: trying to ucast probe in NUD_INVALID: %pI6\n",
+ __func__, target);
}
ndisc_send_ns(dev, target, target, saddr, 0);
} else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) {
@@ -732,11 +768,9 @@ static int pndisc_is_router(const void *pkey,
struct pneigh_entry *n;
int ret = -1;
- read_lock_bh(&nd_tbl.lock);
- n = __pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev);
+ n = pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev);
if (n)
- ret = !!(n->flags & NTF_ROUTER);
- read_unlock_bh(&nd_tbl.lock);
+ ret = !!(READ_ONCE(n->flags) & NTF_ROUTER);
return ret;
}
@@ -750,7 +784,7 @@ void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts);
}
-static void ndisc_recv_ns(struct sk_buff *skb)
+static enum skb_drop_reason ndisc_recv_ns(struct sk_buff *skb)
{
struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
@@ -764,18 +798,17 @@ static void ndisc_recv_ns(struct sk_buff *skb)
struct inet6_dev *idev = NULL;
struct neighbour *neigh;
int dad = ipv6_addr_any(saddr);
- bool inc;
int is_router = -1;
+ SKB_DR(reason);
u64 nonce = 0;
+ bool inc;
- if (skb->len < sizeof(struct nd_msg)) {
- ND_PRINTK(2, warn, "NS: packet too short\n");
- return;
- }
+ if (skb->len < sizeof(struct nd_msg))
+ return SKB_DROP_REASON_PKT_TOO_SMALL;
if (ipv6_addr_is_multicast(&msg->target)) {
- ND_PRINTK(2, warn, "NS: multicast target address\n");
- return;
+ net_dbg_ratelimited("NS: multicast target address\n");
+ return reason;
}
/*
@@ -783,21 +816,18 @@ static void ndisc_recv_ns(struct sk_buff *skb)
* DAD has to be destined for solicited node multicast address.
*/
if (dad && !ipv6_addr_is_solict_mult(daddr)) {
- ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n");
- return;
+ net_dbg_ratelimited("NS: bad DAD packet (wrong destination)\n");
+ return reason;
}
- if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) {
- ND_PRINTK(2, warn, "NS: invalid ND options\n");
- return;
- }
+ if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts))
+ return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS;
if (ndopts.nd_opts_src_lladdr) {
lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev);
if (!lladdr) {
- ND_PRINTK(2, warn,
- "NS: invalid link-layer address length\n");
- return;
+ net_dbg_ratelimited("NS: invalid link-layer address length\n");
+ return reason;
}
/* RFC2461 7.1.1:
@@ -806,9 +836,8 @@ static void ndisc_recv_ns(struct sk_buff *skb)
* in the message.
*/
if (dad) {
- ND_PRINTK(2, warn,
- "NS: bad DAD packet (link-layer address option)\n");
- return;
+ net_dbg_ratelimited("NS: bad DAD packet (link-layer address option)\n");
+ return reason;
}
}
if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1)
@@ -824,10 +853,8 @@ have_ifp:
if (nonce != 0 && ifp->dad_nonce == nonce) {
u8 *np = (u8 *)&nonce;
/* Matching nonce if looped back */
- ND_PRINTK(2, notice,
- "%s: IPv6 DAD loopback for address %pI6c nonce %pM ignored\n",
- ifp->idev->dev->name,
- &ifp->addr, np);
+ net_dbg_ratelimited("%s: IPv6 DAD loopback for address %pI6c nonce %pM ignored\n",
+ ifp->idev->dev->name, &ifp->addr, np);
goto out;
}
/*
@@ -836,7 +863,7 @@ have_ifp:
* so fail our DAD process
*/
addrconf_dad_failure(skb, ifp);
- return;
+ return reason;
} else {
/*
* This is not a dad solicitation.
@@ -868,12 +895,13 @@ have_ifp:
idev = in6_dev_get(dev);
if (!idev) {
/* XXX: count this drop? */
- return;
+ return reason;
}
if (ipv6_chk_acast_addr(net, dev, &msg->target) ||
- (idev->cnf.forwarding &&
- (net->ipv6.devconf_all->proxy_ndp || idev->cnf.proxy_ndp) &&
+ (READ_ONCE(idev->cnf.forwarding) &&
+ (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) ||
+ READ_ONCE(idev->cnf.proxy_ndp)) &&
(is_router = pndisc_is_router(&msg->target, dev)) >= 0)) {
if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) &&
skb->pkt_type != PACKET_HOST &&
@@ -891,12 +919,14 @@ have_ifp:
pneigh_enqueue(&nd_tbl, idev->nd_parms, n);
goto out;
}
- } else
+ } else {
+ SKB_DR_SET(reason, IPV6_NDISC_NS_OTHERHOST);
goto out;
+ }
}
if (is_router < 0)
- is_router = idev->cnf.forwarding;
+ is_router = READ_ONCE(idev->cnf.forwarding);
if (dad) {
ndisc_send_na(dev, &in6addr_linklocal_allnodes, &msg->target,
@@ -925,6 +955,7 @@ have_ifp:
true, (ifp != NULL && inc), inc);
if (neigh)
neigh_release(neigh);
+ reason = SKB_CONSUMED;
}
out:
@@ -932,9 +963,29 @@ out:
in6_ifa_put(ifp);
else
in6_dev_put(idev);
+ return reason;
+}
+
+static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr)
+{
+ struct inet6_dev *idev = __in6_dev_get(dev);
+
+ switch (READ_ONCE(idev->cnf.accept_untracked_na)) {
+ case 0: /* Don't accept untracked na (absent in neighbor cache) */
+ return 0;
+ case 1: /* Create new entries from na if currently untracked */
+ return 1;
+ case 2: /* Create new entries from untracked na only if saddr is in the
+ * same subnet as an address configured on the interface that
+ * received the na
+ */
+ return !!ipv6_chk_prefix(saddr, dev);
+ default:
+ return 0;
+ }
}
-static void ndisc_recv_na(struct sk_buff *skb)
+static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb)
{
struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
@@ -947,41 +998,40 @@ static void ndisc_recv_na(struct sk_buff *skb)
struct inet6_dev *idev = __in6_dev_get(dev);
struct inet6_ifaddr *ifp;
struct neighbour *neigh;
+ SKB_DR(reason);
+ u8 new_state;
- if (skb->len < sizeof(struct nd_msg)) {
- ND_PRINTK(2, warn, "NA: packet too short\n");
- return;
- }
+ if (skb->len < sizeof(struct nd_msg))
+ return SKB_DROP_REASON_PKT_TOO_SMALL;
if (ipv6_addr_is_multicast(&msg->target)) {
- ND_PRINTK(2, warn, "NA: target address is multicast\n");
- return;
+ net_dbg_ratelimited("NA: target address is multicast\n");
+ return reason;
}
if (ipv6_addr_is_multicast(daddr) &&
msg->icmph.icmp6_solicited) {
- ND_PRINTK(2, warn, "NA: solicited NA is multicasted\n");
- return;
+ net_dbg_ratelimited("NA: solicited NA is multicasted\n");
+ return reason;
}
/* For some 802.11 wireless deployments (and possibly other networks),
* there will be a NA proxy and unsolicitd packets are attacks
* and thus should not be accepted.
+ * drop_unsolicited_na takes precedence over accept_untracked_na
*/
if (!msg->icmph.icmp6_solicited && idev &&
- idev->cnf.drop_unsolicited_na)
- return;
+ READ_ONCE(idev->cnf.drop_unsolicited_na))
+ return reason;
+
+ if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts))
+ return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS;
- if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) {
- ND_PRINTK(2, warn, "NS: invalid ND option\n");
- return;
- }
if (ndopts.nd_opts_tgt_lladdr) {
lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, dev);
if (!lladdr) {
- ND_PRINTK(2, warn,
- "NA: invalid link-layer address length\n");
- return;
+ net_dbg_ratelimited("NA: invalid link-layer address length\n");
+ return reason;
}
}
ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1);
@@ -989,7 +1039,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
if (skb->pkt_type != PACKET_LOOPBACK
&& (ifp->flags & IFA_F_TENTATIVE)) {
addrconf_dad_failure(skb, ifp);
- return;
+ return reason;
}
/* What should we make now? The advertisement
is invalid, but ndisc specs say nothing
@@ -1001,19 +1051,43 @@ static void ndisc_recv_na(struct sk_buff *skb)
unsolicited advertisement.
*/
if (skb->pkt_type != PACKET_LOOPBACK)
- ND_PRINTK(1, warn,
- "NA: %pM advertised our address %pI6c on %s!\n",
- eth_hdr(skb)->h_source, &ifp->addr, ifp->idev->dev->name);
+ net_warn_ratelimited("NA: %pM advertised our address %pI6c on %s!\n",
+ eth_hdr(skb)->h_source, &ifp->addr,
+ ifp->idev->dev->name);
in6_ifa_put(ifp);
- return;
+ return reason;
}
+
neigh = neigh_lookup(&nd_tbl, &msg->target, dev);
- if (neigh) {
+ /* RFC 9131 updates original Neighbour Discovery RFC 4861.
+ * NAs with Target LL Address option without a corresponding
+ * entry in the neighbour cache can now create a STALE neighbour
+ * cache entry on routers.
+ *
+ * entry accept fwding solicited behaviour
+ * ------- ------ ------ --------- ----------------------
+ * present X X 0 Set state to STALE
+ * present X X 1 Set state to REACHABLE
+ * absent 0 X X Do nothing
+ * absent 1 0 X Do nothing
+ * absent 1 1 X Add a new STALE entry
+ *
+ * Note that we don't do a (daddr == all-routers-mcast) check.
+ */
+ new_state = msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE;
+ if (!neigh && lladdr && idev && READ_ONCE(idev->cnf.forwarding)) {
+ if (accept_untracked_na(dev, saddr)) {
+ neigh = neigh_create(&nd_tbl, &msg->target, dev);
+ new_state = NUD_STALE;
+ }
+ }
+
+ if (neigh && !IS_ERR(neigh)) {
u8 old_flags = neigh->flags;
struct net *net = dev_net(dev);
- if (neigh->nud_state & NUD_FAILED)
+ if (READ_ONCE(neigh->nud_state) & NUD_FAILED)
goto out;
/*
@@ -1022,14 +1096,15 @@ static void ndisc_recv_na(struct sk_buff *skb)
* has already sent a NA to us.
*/
if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) &&
- net->ipv6.devconf_all->forwarding && net->ipv6.devconf_all->proxy_ndp &&
- pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) {
+ READ_ONCE(net->ipv6.devconf_all->forwarding) &&
+ READ_ONCE(net->ipv6.devconf_all->proxy_ndp) &&
+ pneigh_lookup(&nd_tbl, net, &msg->target, dev)) {
/* XXX: idev->cnf.proxy_ndp */
goto out;
}
ndisc_update(dev, neigh, lladdr,
- msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE,
+ new_state,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
(msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)|
NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
@@ -1042,13 +1117,14 @@ static void ndisc_recv_na(struct sk_buff *skb)
*/
rt6_clean_tohost(dev_net(dev), saddr);
}
-
+ reason = SKB_CONSUMED;
out:
neigh_release(neigh);
}
+ return reason;
}
-static void ndisc_recv_rs(struct sk_buff *skb)
+static enum skb_drop_reason ndisc_recv_rs(struct sk_buff *skb)
{
struct rs_msg *rs_msg = (struct rs_msg *)skb_transport_header(skb);
unsigned long ndoptlen = skb->len - sizeof(*rs_msg);
@@ -1057,18 +1133,19 @@ static void ndisc_recv_rs(struct sk_buff *skb)
const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
struct ndisc_options ndopts;
u8 *lladdr = NULL;
+ SKB_DR(reason);
if (skb->len < sizeof(*rs_msg))
- return;
+ return SKB_DROP_REASON_PKT_TOO_SMALL;
idev = __in6_dev_get(skb->dev);
if (!idev) {
- ND_PRINTK(1, err, "RS: can't find in6 device\n");
- return;
+ net_err_ratelimited("RS: can't find in6 device\n");
+ return reason;
}
/* Don't accept RS if we're not in router mode */
- if (!idev->cnf.forwarding)
+ if (!READ_ONCE(idev->cnf.forwarding))
goto out;
/*
@@ -1079,10 +1156,8 @@ static void ndisc_recv_rs(struct sk_buff *skb)
goto out;
/* Parse ND options */
- if (!ndisc_parse_options(skb->dev, rs_msg->opt, ndoptlen, &ndopts)) {
- ND_PRINTK(2, notice, "NS: invalid ND option, ignored\n");
- goto out;
- }
+ if (!ndisc_parse_options(skb->dev, rs_msg->opt, ndoptlen, &ndopts))
+ return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS;
if (ndopts.nd_opts_src_lladdr) {
lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr,
@@ -1099,9 +1174,10 @@ static void ndisc_recv_rs(struct sk_buff *skb)
NEIGH_UPDATE_F_OVERRIDE_ISROUTER,
NDISC_ROUTER_SOLICITATION, &ndopts);
neigh_release(neigh);
+ reason = SKB_CONSUMED;
}
out:
- return;
+ return reason;
}
static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt)
@@ -1150,73 +1226,63 @@ errout:
rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err);
}
-static void ndisc_router_discovery(struct sk_buff *skb)
+static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
{
struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb);
+ bool send_ifinfo_notify = false;
struct neighbour *neigh = NULL;
- struct inet6_dev *in6_dev;
+ struct ndisc_options ndopts;
struct fib6_info *rt = NULL;
+ struct inet6_dev *in6_dev;
+ struct fib6_table *table;
+ u32 defrtr_usr_metric;
+ unsigned int pref = 0;
+ __u32 old_if_flags;
struct net *net;
+ SKB_DR(reason);
int lifetime;
- struct ndisc_options ndopts;
int optlen;
- unsigned int pref = 0;
- __u32 old_if_flags;
- bool send_ifinfo_notify = false;
__u8 *opt = (__u8 *)(ra_msg + 1);
optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) -
sizeof(struct ra_msg);
- ND_PRINTK(2, info,
- "RA: %s, dev: %s\n",
- __func__, skb->dev->name);
+ net_dbg_ratelimited("RA: %s, dev: %s\n", __func__, skb->dev->name);
if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) {
- ND_PRINTK(2, warn, "RA: source address is not link-local\n");
- return;
- }
- if (optlen < 0) {
- ND_PRINTK(2, warn, "RA: packet too short\n");
- return;
+ net_dbg_ratelimited("RA: source address is not link-local\n");
+ return reason;
}
+ if (optlen < 0)
+ return SKB_DROP_REASON_PKT_TOO_SMALL;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
if (skb->ndisc_nodetype == NDISC_NODETYPE_HOST) {
- ND_PRINTK(2, warn, "RA: from host or unauthorized router\n");
- return;
+ net_dbg_ratelimited("RA: from host or unauthorized router\n");
+ return reason;
}
#endif
- /*
- * set the RA_RECV flag in the interface
- */
-
in6_dev = __in6_dev_get(skb->dev);
if (!in6_dev) {
- ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n",
- skb->dev->name);
- return;
+ net_err_ratelimited("RA: can't find inet6 device for %s\n", skb->dev->name);
+ return reason;
}
- if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts)) {
- ND_PRINTK(2, warn, "RA: invalid ND options\n");
- return;
- }
+ if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts))
+ return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS;
if (!ipv6_accept_ra(in6_dev)) {
- ND_PRINTK(2, info,
- "RA: %s, did not accept ra for dev: %s\n",
- __func__, skb->dev->name);
+ net_dbg_ratelimited("RA: %s, did not accept ra for dev: %s\n", __func__,
+ skb->dev->name);
goto skip_linkparms;
}
#ifdef CONFIG_IPV6_NDISC_NODETYPE
/* skip link-specific parameters from interior routers */
if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) {
- ND_PRINTK(2, info,
- "RA: %s, nodetype is NODEFAULT, dev: %s\n",
- __func__, skb->dev->name);
+ net_dbg_ratelimited("RA: %s, nodetype is NODEFAULT, dev: %s\n", __func__,
+ skb->dev->name);
goto skip_linkparms;
}
#endif
@@ -1244,10 +1310,17 @@ static void ndisc_router_discovery(struct sk_buff *skb)
if (old_if_flags != in6_dev->if_flags)
send_ifinfo_notify = true;
- if (!in6_dev->cnf.accept_ra_defrtr) {
- ND_PRINTK(2, info,
- "RA: %s, defrtr is false for dev: %s\n",
- __func__, skb->dev->name);
+ if (!READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) {
+ net_dbg_ratelimited("RA: %s, defrtr is false for dev: %s\n", __func__,
+ skb->dev->name);
+ goto skip_defrtr;
+ }
+
+ lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime);
+ if (lifetime != 0 &&
+ lifetime < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) {
+ net_dbg_ratelimited("RA: router lifetime (%ds) is too short: %s\n", lifetime,
+ skb->dev->name);
goto skip_defrtr;
}
@@ -1255,82 +1328,94 @@ static void ndisc_router_discovery(struct sk_buff *skb)
* accept_ra_from_local is set to true.
*/
net = dev_net(in6_dev->dev);
- if (!in6_dev->cnf.accept_ra_from_local &&
+ if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) &&
ipv6_chk_addr(net, &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) {
- ND_PRINTK(2, info,
- "RA from local address detected on dev: %s: default router ignored\n",
- skb->dev->name);
+ net_dbg_ratelimited("RA from local address detected on dev: %s: default router ignored\n",
+ skb->dev->name);
goto skip_defrtr;
}
- lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime);
-
#ifdef CONFIG_IPV6_ROUTER_PREF
pref = ra_msg->icmph.icmp6_router_pref;
/* 10b is handled as if it were 00b (medium) */
if (pref == ICMPV6_ROUTER_PREF_INVALID ||
- !in6_dev->cnf.accept_ra_rtr_pref)
+ !READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref))
pref = ICMPV6_ROUTER_PREF_MEDIUM;
#endif
-
+ /* routes added from RAs do not use nexthop objects */
rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev);
-
if (rt) {
- neigh = ip6_neigh_lookup(&rt->fib6_nh.nh_gw,
- rt->fib6_nh.nh_dev, NULL,
+ neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6,
+ rt->fib6_nh->fib_nh_dev, NULL,
&ipv6_hdr(skb)->saddr);
if (!neigh) {
- ND_PRINTK(0, err,
- "RA: %s got default router without neighbour\n",
- __func__);
+ net_err_ratelimited("RA: %s got default router without neighbour\n",
+ __func__);
fib6_info_release(rt);
- return;
+ return reason;
}
}
- if (rt && lifetime == 0) {
- ip6_del_rt(net, rt);
+ /* Set default route metric as specified by user */
+ defrtr_usr_metric = in6_dev->cnf.ra_defrtr_metric;
+ /* delete the route if lifetime is 0 or if metric needs change */
+ if (rt && (lifetime == 0 || rt->fib6_metric != defrtr_usr_metric)) {
+ ip6_del_rt(net, rt, false);
rt = NULL;
}
- ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, for dev: %s\n",
- rt, lifetime, skb->dev->name);
+ net_dbg_ratelimited("RA: rt: %p lifetime: %d, metric: %d, for dev: %s\n", rt, lifetime,
+ defrtr_usr_metric, skb->dev->name);
if (!rt && lifetime) {
- ND_PRINTK(3, info, "RA: adding default router\n");
+ net_dbg_ratelimited("RA: adding default router\n");
+
+ if (neigh)
+ neigh_release(neigh);
rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr,
- skb->dev, pref);
+ skb->dev, pref, defrtr_usr_metric,
+ lifetime);
if (!rt) {
- ND_PRINTK(0, err,
- "RA: %s failed to add default route\n",
- __func__);
- return;
+ net_err_ratelimited("RA: %s failed to add default route\n", __func__);
+ return reason;
}
- neigh = ip6_neigh_lookup(&rt->fib6_nh.nh_gw,
- rt->fib6_nh.nh_dev, NULL,
+ neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6,
+ rt->fib6_nh->fib_nh_dev, NULL,
&ipv6_hdr(skb)->saddr);
if (!neigh) {
- ND_PRINTK(0, err,
- "RA: %s got default router without neighbour\n",
- __func__);
+ net_err_ratelimited("RA: %s got default router without neighbour\n",
+ __func__);
fib6_info_release(rt);
- return;
+ return reason;
}
neigh->flags |= NTF_ROUTER;
- } else if (rt) {
+ } else if (rt && IPV6_EXTRACT_PREF(rt->fib6_flags) != pref) {
+ struct nl_info nlinfo = {
+ .nl_net = net,
+ };
rt->fib6_flags = (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
+ inet6_rt_notify(RTM_NEWROUTE, rt, &nlinfo, NLM_F_REPLACE);
}
- if (rt)
+ if (rt) {
+ table = rt->fib6_table;
+ spin_lock_bh(&table->tb6_lock);
+
fib6_set_expires(rt, jiffies + (HZ * lifetime));
- if (in6_dev->cnf.accept_ra_min_hop_limit < 256 &&
+ fib6_add_gc_list(rt);
+
+ spin_unlock_bh(&table->tb6_lock);
+ }
+ if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) < 256 &&
ra_msg->icmph.icmp6_hop_limit) {
- if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) {
- in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+ if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) <=
+ ra_msg->icmph.icmp6_hop_limit) {
+ WRITE_ONCE(in6_dev->cnf.hop_limit,
+ ra_msg->icmph.icmp6_hop_limit);
fib6_metric_set(rt, RTAX_HOPLIMIT,
ra_msg->icmph.icmp6_hop_limit);
} else {
- ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n");
+ net_dbg_ratelimited("RA: Got route advertisement with lower hop_limit than minimum\n");
}
}
@@ -1345,8 +1430,8 @@ skip_defrtr:
if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/HZ) {
rtime = (rtime*HZ)/1000;
- if (rtime < HZ/10)
- rtime = HZ/10;
+ if (rtime < HZ/100)
+ rtime = HZ/100;
NEIGH_VAR_SET(in6_dev->nd_parms, RETRANS_TIME, rtime);
in6_dev->tstamp = jiffies;
send_ifinfo_notify = true;
@@ -1364,19 +1449,13 @@ skip_defrtr:
BASE_REACHABLE_TIME, rtime);
NEIGH_VAR_SET(in6_dev->nd_parms,
GC_STALETIME, 3 * rtime);
- in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime);
+ neigh_set_reach_time(in6_dev->nd_parms);
in6_dev->tstamp = jiffies;
send_ifinfo_notify = true;
}
}
}
- /*
- * Send a notify if RA changed managed/otherconf flags or timer settings
- */
- if (send_ifinfo_notify)
- inet6_ifinfo_notify(RTM_NEWLINK, in6_dev);
-
skip_linkparms:
/*
@@ -1392,8 +1471,7 @@ skip_linkparms:
lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr,
skb->dev);
if (!lladdr) {
- ND_PRINTK(2, warn,
- "RA: invalid link-layer address length\n");
+ net_dbg_ratelimited("RA: invalid link-layer address length\n");
goto out;
}
}
@@ -1403,26 +1481,25 @@ skip_linkparms:
NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
NEIGH_UPDATE_F_ISROUTER,
NDISC_ROUTER_ADVERTISEMENT, &ndopts);
+ reason = SKB_CONSUMED;
}
if (!ipv6_accept_ra(in6_dev)) {
- ND_PRINTK(2, info,
- "RA: %s, accept_ra is false for dev: %s\n",
- __func__, skb->dev->name);
+ net_dbg_ratelimited("RA: %s, accept_ra is false for dev: %s\n", __func__,
+ skb->dev->name);
goto out;
}
#ifdef CONFIG_IPV6_ROUTE_INFO
- if (!in6_dev->cnf.accept_ra_from_local &&
+ if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) &&
ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr,
in6_dev->dev, 0)) {
- ND_PRINTK(2, info,
- "RA from local address detected on dev: %s: router info ignored.\n",
- skb->dev->name);
+ net_dbg_ratelimited("RA from local address detected on dev: %s: router info ignored.\n",
+ skb->dev->name);
goto skip_routeinfo;
}
- if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) {
+ if (READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref) && ndopts.nd_opts_ri) {
struct nd_opt_hdr *p;
for (p = ndopts.nd_opts_ri;
p;
@@ -1434,11 +1511,14 @@ skip_linkparms:
continue;
#endif
if (ri->prefix_len == 0 &&
- !in6_dev->cnf.accept_ra_defrtr)
+ !READ_ONCE(in6_dev->cnf.accept_ra_defrtr))
+ continue;
+ if (ri->lifetime != 0 &&
+ ntohl(ri->lifetime) < READ_ONCE(in6_dev->cnf.accept_ra_min_lft))
continue;
- if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen)
+ if (ri->prefix_len < READ_ONCE(in6_dev->cnf.accept_ra_rt_info_min_plen))
continue;
- if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen)
+ if (ri->prefix_len > READ_ONCE(in6_dev->cnf.accept_ra_rt_info_max_plen))
continue;
rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3,
&ipv6_hdr(skb)->saddr);
@@ -1451,14 +1531,13 @@ skip_routeinfo:
#ifdef CONFIG_IPV6_NDISC_NODETYPE
/* skip link-specific ndopts from interior routers */
if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) {
- ND_PRINTK(2, info,
- "RA: %s, nodetype is NODEFAULT (interior routes), dev: %s\n",
- __func__, skb->dev->name);
+ net_dbg_ratelimited("RA: %s, nodetype is NODEFAULT (interior routes), dev: %s\n",
+ __func__, skb->dev->name);
goto out;
}
#endif
- if (in6_dev->cnf.accept_ra_pinfo && ndopts.nd_opts_pi) {
+ if (READ_ONCE(in6_dev->cnf.accept_ra_pinfo) && ndopts.nd_opts_pi) {
struct nd_opt_hdr *p;
for (p = ndopts.nd_opts_pi;
p;
@@ -1469,17 +1548,22 @@ skip_routeinfo:
}
}
- if (ndopts.nd_opts_mtu && in6_dev->cnf.accept_ra_mtu) {
+ if (ndopts.nd_opts_mtu && READ_ONCE(in6_dev->cnf.accept_ra_mtu)) {
__be32 n;
u32 mtu;
memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu));
mtu = ntohl(n);
+ if (in6_dev->ra_mtu != mtu) {
+ in6_dev->ra_mtu = mtu;
+ send_ifinfo_notify = true;
+ }
+
if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) {
- ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu);
- } else if (in6_dev->cnf.mtu6 != mtu) {
- in6_dev->cnf.mtu6 = mtu;
+ net_dbg_ratelimited("RA: invalid mtu: %d\n", mtu);
+ } else if (READ_ONCE(in6_dev->cnf.mtu6) != mtu) {
+ WRITE_ONCE(in6_dev->cnf.mtu6, mtu);
fib6_metric_set(rt, RTAX_MTU, mtu);
rt6_mtu_change(skb->dev, mtu);
}
@@ -1496,53 +1580,59 @@ skip_routeinfo:
}
if (ndopts.nd_opts_tgt_lladdr || ndopts.nd_opts_rh) {
- ND_PRINTK(2, warn, "RA: invalid RA options\n");
+ net_dbg_ratelimited("RA: invalid RA options\n");
}
out:
+ /* Send a notify if RA changed managed/otherconf flags or
+ * timer settings or ra_mtu value
+ */
+ if (send_ifinfo_notify)
+ inet6_ifinfo_notify(RTM_NEWLINK, in6_dev);
+
fib6_info_release(rt);
if (neigh)
neigh_release(neigh);
+ return reason;
}
-static void ndisc_redirect_rcv(struct sk_buff *skb)
+static enum skb_drop_reason ndisc_redirect_rcv(struct sk_buff *skb)
{
- u8 *hdr;
- struct ndisc_options ndopts;
struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb);
u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
offsetof(struct rd_msg, opt));
+ struct ndisc_options ndopts;
+ SKB_DR(reason);
+ u8 *hdr;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
switch (skb->ndisc_nodetype) {
case NDISC_NODETYPE_HOST:
case NDISC_NODETYPE_NODEFAULT:
- ND_PRINTK(2, warn,
- "Redirect: from host or unauthorized router\n");
- return;
+ net_dbg_ratelimited("Redirect: from host or unauthorized router\n");
+ return reason;
}
#endif
if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) {
- ND_PRINTK(2, warn,
- "Redirect: source address is not link-local\n");
- return;
+ net_dbg_ratelimited("Redirect: source address is not link-local\n");
+ return reason;
}
if (!ndisc_parse_options(skb->dev, msg->opt, ndoptlen, &ndopts))
- return;
+ return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS;
if (!ndopts.nd_opts_rh) {
ip6_redirect_no_header(skb, dev_net(skb->dev),
skb->dev->ifindex);
- return;
+ return reason;
}
hdr = (u8 *)ndopts.nd_opts_rh;
hdr += 8;
if (!pskb_pull(skb, hdr - skb_transport_header(skb)))
- return;
+ return SKB_DROP_REASON_PKT_TOO_SMALL;
- icmpv6_notify(skb, NDISC_REDIRECT, 0, 0);
+ return icmpv6_notify(skb, NDISC_REDIRECT, 0, 0);
}
static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb,
@@ -1563,7 +1653,7 @@ static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb,
void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
{
struct net_device *dev = skb->dev;
- struct net *net = dev_net(dev);
+ struct net *net = dev_net_rcu(dev);
struct sock *sk = net->ipv6.ndisc_sk;
int optlen = 0;
struct inet_peer *peer;
@@ -1578,22 +1668,20 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL;
bool ret;
- if (netif_is_l3_master(skb->dev)) {
- dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif);
+ if (netif_is_l3_master(dev)) {
+ dev = dev_get_by_index_rcu(net, IPCB(skb)->iif);
if (!dev)
return;
}
if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) {
- ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n",
- dev->name);
+ net_dbg_ratelimited("Redirect: no link-local address on %s\n", dev->name);
return;
}
if (!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, target) &&
ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) {
- ND_PRINTK(2, warn,
- "Redirect: target address is not link-local unicast\n");
+ net_dbg_ratelimited("Redirect: target address is not link-local unicast\n");
return;
}
@@ -1609,25 +1697,23 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
if (IS_ERR(dst))
return;
- rt = (struct rt6_info *) dst;
+ rt = dst_rt6_info(dst);
if (rt->rt6i_flags & RTF_GATEWAY) {
- ND_PRINTK(2, warn,
- "Redirect: destination is not a neighbour\n");
+ net_dbg_ratelimited("Redirect: destination is not a neighbour\n");
goto release;
}
- peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr, 1);
+
+ peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr);
ret = inet_peer_xrlim_allow(peer, 1*HZ);
- if (peer)
- inet_putpeer(peer);
+
if (!ret)
goto release;
if (dev->addr_len) {
struct neighbour *neigh = dst_neigh_lookup(skb_dst(skb), target);
if (!neigh) {
- ND_PRINTK(2, warn,
- "Redirect: no neigh for target address\n");
+ net_dbg_ratelimited("Redirect: no neigh for target address\n");
goto release;
}
@@ -1688,8 +1774,14 @@ release:
static void pndisc_redo(struct sk_buff *skb)
{
- ndisc_recv_ns(skb);
- kfree_skb(skb);
+ enum skb_drop_reason reason = ndisc_recv_ns(skb);
+
+ kfree_skb_reason(skb, reason);
+}
+
+static int ndisc_is_multicast(const void *pkey)
+{
+ return ipv6_addr_is_multicast((struct in6_addr *)pkey);
}
static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb)
@@ -1699,63 +1791,62 @@ static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb)
if (!idev)
return true;
if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED &&
- idev->cnf.suppress_frag_ndisc) {
+ READ_ONCE(idev->cnf.suppress_frag_ndisc)) {
net_warn_ratelimited("Received fragmented ndisc packet. Carefully consider disabling suppress_frag_ndisc.\n");
return true;
}
return false;
}
-int ndisc_rcv(struct sk_buff *skb)
+enum skb_drop_reason ndisc_rcv(struct sk_buff *skb)
{
struct nd_msg *msg;
+ SKB_DR(reason);
if (ndisc_suppress_frag_ndisc(skb))
- return 0;
+ return SKB_DROP_REASON_IPV6_NDISC_FRAG;
if (skb_linearize(skb))
- return 0;
+ return SKB_DROP_REASON_NOMEM;
msg = (struct nd_msg *)skb_transport_header(skb);
__skb_push(skb, skb->data - skb_transport_header(skb));
if (ipv6_hdr(skb)->hop_limit != 255) {
- ND_PRINTK(2, warn, "NDISC: invalid hop-limit: %d\n",
- ipv6_hdr(skb)->hop_limit);
- return 0;
+ net_dbg_ratelimited("NDISC: invalid hop-limit: %d\n", ipv6_hdr(skb)->hop_limit);
+ return SKB_DROP_REASON_IPV6_NDISC_HOP_LIMIT;
}
if (msg->icmph.icmp6_code != 0) {
- ND_PRINTK(2, warn, "NDISC: invalid ICMPv6 code: %d\n",
- msg->icmph.icmp6_code);
- return 0;
+ net_dbg_ratelimited("NDISC: invalid ICMPv6 code: %d\n", msg->icmph.icmp6_code);
+ return SKB_DROP_REASON_IPV6_NDISC_BAD_CODE;
}
switch (msg->icmph.icmp6_type) {
case NDISC_NEIGHBOUR_SOLICITATION:
memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
- ndisc_recv_ns(skb);
+ reason = ndisc_recv_ns(skb);
break;
case NDISC_NEIGHBOUR_ADVERTISEMENT:
- ndisc_recv_na(skb);
+ reason = ndisc_recv_na(skb);
break;
case NDISC_ROUTER_SOLICITATION:
- ndisc_recv_rs(skb);
+ reason = ndisc_recv_rs(skb);
break;
case NDISC_ROUTER_ADVERTISEMENT:
- ndisc_router_discovery(skb);
+ reason = ndisc_router_discovery(skb);
break;
case NDISC_REDIRECT:
- ndisc_redirect_rcv(skb);
+ reason = ndisc_redirect_rcv(skb);
break;
}
- return 0;
+ return reason;
}
static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
@@ -1764,26 +1855,36 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
struct netdev_notifier_change_info *change_info;
struct net *net = dev_net(dev);
struct inet6_dev *idev;
+ bool evict_nocarrier;
switch (event) {
case NETDEV_CHANGEADDR:
neigh_changeaddr(&nd_tbl, dev);
fib6_run_gc(0, net, false);
- /* fallthrough */
+ fallthrough;
case NETDEV_UP:
idev = in6_dev_get(dev);
if (!idev)
break;
- if (idev->cnf.ndisc_notify ||
- net->ipv6.devconf_all->ndisc_notify)
+ if (READ_ONCE(idev->cnf.ndisc_notify) ||
+ READ_ONCE(net->ipv6.devconf_all->ndisc_notify))
ndisc_send_unsol_na(dev);
in6_dev_put(idev);
break;
case NETDEV_CHANGE:
+ idev = in6_dev_get(dev);
+ if (!idev)
+ evict_nocarrier = true;
+ else {
+ evict_nocarrier = READ_ONCE(idev->cnf.ndisc_evict_nocarrier) &&
+ READ_ONCE(net->ipv6.devconf_all->ndisc_evict_nocarrier);
+ in6_dev_put(idev);
+ }
+
change_info = ptr;
if (change_info->flags_changed & IFF_NOARP)
neigh_changeaddr(&nd_tbl, dev);
- if (!netif_carrier_ok(dev))
+ if (evict_nocarrier && !netif_carrier_ok(dev))
neigh_carrier_down(&nd_tbl, dev);
break;
case NETDEV_DOWN:
@@ -1806,13 +1907,13 @@ static struct notifier_block ndisc_netdev_notifier = {
};
#ifdef CONFIG_SYSCTL
-static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl,
+static void ndisc_warn_deprecated_sysctl(const struct ctl_table *ctl,
const char *func, const char *dev_name)
{
static char warncomm[TASK_COMM_LEN];
static int warned;
if (strcmp(warncomm, current->comm) && warned < 5) {
- strcpy(warncomm, current->comm);
+ strscpy(warncomm, current->comm);
pr_warn("process `%s' is using deprecated sysctl (%s) net.ipv6.neigh.%s.%s - use net.ipv6.neigh.%s.%s_ms instead\n",
warncomm, func,
dev_name, ctl->procname,
@@ -1821,7 +1922,8 @@ static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl,
}
}
-int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos)
+int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
{
struct net_device *dev = ctl->extra1;
struct inet6_dev *idev;
@@ -1846,10 +1948,10 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *bu
ret = -1;
if (write && ret == 0 && dev && (idev = in6_dev_get(dev)) != NULL) {
- if (ctl->data == &NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME))
- idev->nd_parms->reachable_time =
- neigh_rand_reach_time(NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME));
- idev->tstamp = jiffies;
+ if (ctl->data == NEIGH_VAR_PTR(idev->nd_parms, BASE_REACHABLE_TIME))
+ neigh_set_reach_time(idev->nd_parms);
+
+ WRITE_ONCE(idev->tstamp, jiffies);
inet6_ifinfo_notify(RTM_NEWLINK, idev);
in6_dev_put(idev);
}
@@ -1868,9 +1970,8 @@ static int __net_init ndisc_net_init(struct net *net)
err = inet_ctl_sock_create(&sk, PF_INET6,
SOCK_RAW, IPPROTO_ICMPV6, net);
if (err < 0) {
- ND_PRINTK(0, err,
- "NDISC: Failed to initialize the control socket (err %d)\n",
- err);
+ net_err_ratelimited("NDISC: Failed to initialize the control socket (err %d)\n",
+ err);
return err;
}
@@ -1879,7 +1980,7 @@ static int __net_init ndisc_net_init(struct net *net)
np = inet6_sk(sk);
np->hop_limit = 255;
/* Do not loopback ndisc messages */
- np->mc_loop = 0;
+ inet6_clear_bit(MC6_LOOP, sk);
return 0;
}
generated by cgit (git 2.34.1) at 2025-12-24 20:08:14 +0000