summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c68
-rw-r--r--net/ipv6/calipso.c29
-rw-r--r--net/ipv6/esp6.c53
-rw-r--r--net/ipv6/esp6_offload.c6
-rw-r--r--net/ipv6/fib6_rules.c4
-rw-r--r--net/ipv6/icmp.c48
-rw-r--r--net/ipv6/ila/ila_common.c6
-rw-r--r--net/ipv6/ila/ila_lwt.c4
-rw-r--r--net/ipv6/ioam6_iptunnel.c79
-rw-r--r--net/ipv6/ip6_fib.c24
-rw-r--r--net/ipv6/ip6_gre.c2
-rw-r--r--net/ipv6/ip6_offload.c4
-rw-r--r--net/ipv6/ip6_output.c17
-rw-r--r--net/ipv6/ip6_tunnel.c7
-rw-r--r--net/ipv6/ip6_vti.c3
-rw-r--r--net/ipv6/ip6mr.c31
-rw-r--r--net/ipv6/mcast.c58
-rw-r--r--net/ipv6/ndisc.c32
-rw-r--r--net/ipv6/netfilter.c12
-rw-r--r--net/ipv6/netfilter/nf_reject_ipv6.c5
-rw-r--r--net/ipv6/netfilter/nf_socket_ipv6.c23
-rw-r--r--net/ipv6/netfilter/nft_fib_ipv6.c36
-rw-r--r--net/ipv6/raw.c8
-rw-r--r--net/ipv6/route.c111
-rw-r--r--net/ipv6/rpl_iptunnel.c79
-rw-r--r--net/ipv6/seg6_hmac.c6
-rw-r--r--net/ipv6/seg6_iptunnel.c110
-rw-r--r--net/ipv6/seg6_local.c6
-rw-r--r--net/ipv6/sit.c8
-rw-r--r--net/ipv6/tcpv6_offload.c23
-rw-r--r--net/ipv6/udp.c61
-rw-r--r--net/ipv6/xfrm6_input.c21
32 files changed, 596 insertions, 388 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f7c17388ff6a..49ec223f2eda 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2228,13 +2228,12 @@ errdad:
in6_ifa_put(ifp);
}
-/* Join to solicited addr multicast group.
- * caller must hold RTNL */
+/* Join to solicited addr multicast group. */
void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr)
{
struct in6_addr maddr;
- if (dev->flags&(IFF_LOOPBACK|IFF_NOARP))
+ if (READ_ONCE(dev->flags) & (IFF_LOOPBACK | IFF_NOARP))
return;
addrconf_addr_solict_mult(addr, &maddr);
@@ -3237,16 +3236,13 @@ static void add_v4_addrs(struct inet6_dev *idev)
struct in6_addr addr;
struct net_device *dev;
struct net *net = dev_net(idev->dev);
- int scope, plen, offset = 0;
+ int scope, plen;
u32 pflags = 0;
ASSERT_RTNL();
memset(&addr, 0, sizeof(struct in6_addr));
- /* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */
- if (idev->dev->addr_len == sizeof(struct in6_addr))
- offset = sizeof(struct in6_addr) - 4;
- memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4);
+ memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4);
if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) {
scope = IPV6_ADDR_COMPATv4;
@@ -3551,21 +3547,22 @@ static void addrconf_gre_config(struct net_device *dev)
ASSERT_RTNL();
- idev = ipv6_find_idev(dev);
- if (IS_ERR(idev)) {
- pr_debug("%s: add_dev failed\n", __func__);
+ idev = addrconf_add_dev(dev);
+ if (IS_ERR(idev))
return;
- }
- if (dev->type == ARPHRD_ETHER) {
+ /* Generate the IPv6 link-local address using addrconf_addr_gen(),
+ * unless we have an IPv4 GRE device not bound to an IP address and
+ * which is in EUI64 mode (as __ipv6_isatap_ifid() would fail in this
+ * case). Such devices fall back to add_v4_addrs() instead.
+ */
+ if (!(dev->type == ARPHRD_IPGRE && *(__be32 *)dev->dev_addr == 0 &&
+ idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)) {
addrconf_addr_gen(idev, true);
return;
}
add_v4_addrs(idev);
-
- if (dev->flags & IFF_POINTOPOINT)
- addrconf_add_mroute(dev);
}
#endif
@@ -3885,7 +3882,7 @@ static int addrconf_ifdown(struct net_device *dev, bool unregister)
* Do not dev_put!
*/
if (unregister) {
- idev->dead = 1;
+ WRITE_ONCE(idev->dead, 1);
/* protected by rtnl_lock */
RCU_INIT_POINTER(dev->ip6_ptr, NULL);
@@ -5807,6 +5804,27 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype,
}
}
+static int inet6_fill_ifla6_stats_attrs(struct sk_buff *skb,
+ struct inet6_dev *idev)
+{
+ struct nlattr *nla;
+
+ nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
+ if (!nla)
+ goto nla_put_failure;
+ snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla));
+
+ nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64));
+ if (!nla)
+ goto nla_put_failure;
+ snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
u32 ext_filter_mask)
{
@@ -5829,18 +5847,10 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
/* XXX - MC not implemented */
- if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS)
- return 0;
-
- nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
- if (!nla)
- goto nla_put_failure;
- snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla));
-
- nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64));
- if (!nla)
- goto nla_put_failure;
- snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));
+ if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS)) {
+ if (inet6_fill_ifla6_stats_attrs(skb, idev) < 0)
+ goto nla_put_failure;
+ }
nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr));
if (!nla)
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index dbcea9fee626..a247bb93908b 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -1072,8 +1072,13 @@ static int calipso_sock_getattr(struct sock *sk,
struct ipv6_opt_hdr *hop;
int opt_len, len, ret_val = -ENOMSG, offset;
unsigned char *opt;
- struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+ struct ipv6_pinfo *pinfo = inet6_sk(sk);
+ struct ipv6_txoptions *txopts;
+
+ if (!pinfo)
+ return -EAFNOSUPPORT;
+ txopts = txopt_get(pinfo);
if (!txopts || !txopts->hopopt)
goto done;
@@ -1125,8 +1130,13 @@ static int calipso_sock_setattr(struct sock *sk,
{
int ret_val;
struct ipv6_opt_hdr *old, *new;
- struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+ struct ipv6_pinfo *pinfo = inet6_sk(sk);
+ struct ipv6_txoptions *txopts;
+ if (!pinfo)
+ return -EAFNOSUPPORT;
+
+ txopts = txopt_get(pinfo);
old = NULL;
if (txopts)
old = txopts->hopopt;
@@ -1153,8 +1163,13 @@ static int calipso_sock_setattr(struct sock *sk,
static void calipso_sock_delattr(struct sock *sk)
{
struct ipv6_opt_hdr *new_hop;
- struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+ struct ipv6_pinfo *pinfo = inet6_sk(sk);
+ struct ipv6_txoptions *txopts;
+ if (!pinfo)
+ return;
+
+ txopts = txopt_get(pinfo);
if (!txopts || !txopts->hopopt)
goto done;
@@ -1192,6 +1207,10 @@ static int calipso_req_setattr(struct request_sock *req,
struct ipv6_opt_hdr *old, *new;
struct sock *sk = sk_to_full_sk(req_to_sk(req));
+ /* sk is NULL for SYN+ACK w/ SYN Cookie */
+ if (!sk)
+ return -ENOMEM;
+
if (req_inet->ipv6_opt && req_inet->ipv6_opt->hopopt)
old = req_inet->ipv6_opt->hopopt;
else
@@ -1232,6 +1251,10 @@ static void calipso_req_delattr(struct request_sock *req)
struct ipv6_txoptions *txopts;
struct sock *sk = sk_to_full_sk(req_to_sk(req));
+ /* sk is NULL for SYN+ACK w/ SYN Cookie */
+ if (!sk)
+ return;
+
if (!req_inet->ipv6_opt || !req_inet->ipv6_opt->hopopt)
return;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index b2400c226a32..62d17d7f6d9a 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -137,47 +137,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
}
#ifdef CONFIG_INET6_ESPINTCP
-struct esp_tcp_sk {
- struct sock *sk;
- struct rcu_head rcu;
-};
-
-static void esp_free_tcp_sk(struct rcu_head *head)
-{
- struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
-
- sock_put(esk->sk);
- kfree(esk);
-}
-
static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
{
struct xfrm_encap_tmpl *encap = x->encap;
struct net *net = xs_net(x);
- struct esp_tcp_sk *esk;
__be16 sport, dport;
- struct sock *nsk;
struct sock *sk;
- sk = rcu_dereference(x->encap_sk);
- if (sk && sk->sk_state == TCP_ESTABLISHED)
- return sk;
-
spin_lock_bh(&x->lock);
sport = encap->encap_sport;
dport = encap->encap_dport;
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (sk && sk == nsk) {
- esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
- if (!esk) {
- spin_unlock_bh(&x->lock);
- return ERR_PTR(-ENOMEM);
- }
- RCU_INIT_POINTER(x->encap_sk, NULL);
- esk->sk = sk;
- call_rcu(&esk->rcu, esp_free_tcp_sk);
- }
spin_unlock_bh(&x->lock);
sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &x->id.daddr.in6,
@@ -190,20 +159,6 @@ static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
return ERR_PTR(-EINVAL);
}
- spin_lock_bh(&x->lock);
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (encap->encap_sport != sport ||
- encap->encap_dport != dport) {
- sock_put(sk);
- sk = nsk ?: ERR_PTR(-EREMCHG);
- } else if (sk == nsk) {
- sock_put(sk);
- } else {
- rcu_assign_pointer(x->encap_sk, sk);
- }
- spin_unlock_bh(&x->lock);
-
return sk;
}
@@ -216,8 +171,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
sk = esp6_find_tcp_sk(x);
err = PTR_ERR_OR_ZERO(sk);
- if (err)
+ if (err) {
+ kfree_skb(skb);
goto out;
+ }
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
@@ -226,6 +183,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
err = espintcp_push_skb(sk, skb);
bh_unlock_sock(sk);
+ sock_put(sk);
+
out:
rcu_read_unlock();
return err;
@@ -422,6 +381,8 @@ static struct ip_esp_hdr *esp6_output_tcp_encap(struct xfrm_state *x,
if (IS_ERR(sk))
return ERR_CAST(sk);
+ sock_put(sk);
+
*lenp = htons(len);
esph = (struct ip_esp_hdr *)(lenp + 1);
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 919ebfabbe4e..7b41fb4f00b5 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -80,9 +80,9 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
if (sp->len == XFRM_MAX_DEPTH)
goto out_reset;
- x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
- (xfrm_address_t *)&ipv6_hdr(skb)->daddr,
- spi, IPPROTO_ESP, AF_INET6);
+ x = xfrm_input_state_lookup(dev_net(skb->dev), skb->mark,
+ (xfrm_address_t *)&ipv6_hdr(skb)->daddr,
+ spi, IPPROTO_ESP, AF_INET6);
if (unlikely(x && x->dir && x->dir != XFRM_SA_DIR_IN)) {
/* non-offload path will record the error and audit log */
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 04a9ed5e8310..29185c9ebd02 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -365,9 +365,9 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
struct nlattr **tb,
struct netlink_ext_ack *extack)
{
+ struct fib6_rule *rule6 = (struct fib6_rule *)rule;
+ struct net *net = rule->fr_net;
int err = -EINVAL;
- struct net *net = sock_net(skb->sk);
- struct fib6_rule *rule6 = (struct fib6_rule *) rule;
if (!inet_validate_dscp(frh->tos)) {
NL_SET_ERR_MSG(extack,
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 071b0bc1179d..4d14ab7f7e99 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -76,7 +76,7 @@ static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
{
/* 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, skb->dev->ifindex, 0, sock_net_uid(net, NULL));
@@ -222,10 +222,10 @@ static 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, &fl6->daddr, 1);
+ rcu_read_lock();
+ 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, ip6_dst_idev(dst),
@@ -473,7 +473,10 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
if (!skb->dev)
return;
- net = dev_net(skb->dev);
+
+ rcu_read_lock();
+
+ net = dev_net_rcu(skb->dev);
mark = IP6_REPLY_MARK(net, skb->mark);
/*
* Make sure we respect the rules
@@ -496,7 +499,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
!(type == ICMPV6_PARAMPROB &&
code == ICMPV6_UNK_OPTION &&
(opt_unrec(skb, info))))
- return;
+ goto out;
saddr = NULL;
}
@@ -526,7 +529,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
net_dbg_ratelimited("icmp6_send: addr_any/mcast source [%pI6c > %pI6c]\n",
&hdr->saddr, &hdr->daddr);
- return;
+ goto out;
}
/*
@@ -535,7 +538,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
if (is_ineligible(skb)) {
net_dbg_ratelimited("icmp6_send: no reply to icmp error [%pI6c > %pI6c]\n",
&hdr->saddr, &hdr->daddr);
- return;
+ goto out;
}
/* Needed by both icmpv6_global_allow and icmpv6_xmit_lock */
@@ -582,7 +585,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
np = inet6_sk(sk);
if (!icmpv6_xrlim_allow(sk, type, &fl6, apply_ratelimit))
- goto out;
+ goto out_unlock;
tmp_hdr.icmp6_type = type;
tmp_hdr.icmp6_code = code;
@@ -600,7 +603,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
dst = icmpv6_route_lookup(net, skb, sk, &fl6);
if (IS_ERR(dst))
- goto out;
+ goto out_unlock;
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
@@ -616,7 +619,6 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
goto out_dst_release;
}
- rcu_read_lock();
idev = __in6_dev_get(skb->dev);
if (ip6_append_data(sk, icmpv6_getfrag, &msg,
@@ -630,13 +632,15 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
len + sizeof(struct icmp6hdr));
}
- rcu_read_unlock();
+
out_dst_release:
dst_release(dst);
-out:
+out_unlock:
icmpv6_xmit_unlock(sk);
out_bh_enable:
local_bh_enable();
+out:
+ rcu_read_unlock();
}
EXPORT_SYMBOL(icmp6_send);
@@ -679,8 +683,8 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
skb_pull(skb2, nhs);
skb_reset_network_header(skb2);
- rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0,
- skb, 0);
+ 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;
@@ -717,7 +721,7 @@ EXPORT_SYMBOL(ip6_err_gen_icmpv6_unreach);
static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb)
{
- struct net *net = dev_net(skb->dev);
+ struct net *net = dev_net_rcu(skb->dev);
struct sock *sk;
struct inet6_dev *idev;
struct ipv6_pinfo *np;
@@ -832,7 +836,7 @@ 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(skb->dev);
+ struct net *net = dev_net_rcu(skb->dev);
const struct inet6_protocol *ipprot;
enum skb_drop_reason reason;
int inner_offset;
@@ -889,7 +893,7 @@ out:
static int icmpv6_rcv(struct sk_buff *skb)
{
enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
- struct net *net = dev_net(skb->dev);
+ 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;
@@ -921,7 +925,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
skb_set_network_header(skb, nh);
}
- __ICMP6_INC_STATS(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;
@@ -939,7 +943,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
type = hdr->icmp6_type;
- ICMP6MSGIN_INC_STATS(dev_net(dev), idev, type);
+ ICMP6MSGIN_INC_STATS(dev_net_rcu(dev), idev, type);
switch (type) {
case ICMPV6_ECHO_REQUEST:
@@ -1034,9 +1038,9 @@ static int icmpv6_rcv(struct sk_buff *skb)
csum_error:
reason = SKB_DROP_REASON_ICMP_CSUM;
- __ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_CSUMERRORS);
+ __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_CSUMERRORS);
discard_it:
- __ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INERRORS);
+ __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INERRORS);
drop_no_count:
kfree_skb_reason(skb, reason);
return 0;
diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c
index 95e9146918cc..b8d43ed4689d 100644
--- a/net/ipv6/ila/ila_common.c
+++ b/net/ipv6/ila/ila_common.c
@@ -86,7 +86,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb,
diff = get_csum_diff(ip6h, p);
inet_proto_csum_replace_by_diff(&th->check, skb,
- diff, true);
+ diff, true, true);
}
break;
case NEXTHDR_UDP:
@@ -97,7 +97,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb,
if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
diff = get_csum_diff(ip6h, p);
inet_proto_csum_replace_by_diff(&uh->check, skb,
- diff, true);
+ diff, true, true);
if (!uh->check)
uh->check = CSUM_MANGLED_0;
}
@@ -111,7 +111,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb,
diff = get_csum_diff(ip6h, p);
inet_proto_csum_replace_by_diff(&ih->icmp6_cksum, skb,
- diff, true);
+ diff, true, true);
}
break;
}
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index ff7e734e335b..7d574f5132e2 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -88,13 +88,15 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
goto drop;
}
- if (ilwt->connected) {
+ /* cache only if we don't create a dst reference loop */
+ if (ilwt->connected && orig_dst->lwtstate != dst->lwtstate) {
local_bh_disable();
dst_cache_set_ip6(&ilwt->dst_cache, dst, &fl6.saddr);
local_bh_enable();
}
}
+ skb_dst_drop(skb);
skb_dst_set(skb, dst);
return dst_output(net, sk, skb);
diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index beb6b4cfc551..647dd8417c6c 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -255,14 +255,15 @@ static int ioam6_do_fill(struct net *net, struct sk_buff *skb)
}
static int ioam6_do_inline(struct net *net, struct sk_buff *skb,
- struct ioam6_lwt_encap *tuninfo)
+ struct ioam6_lwt_encap *tuninfo,
+ struct dst_entry *cache_dst)
{
struct ipv6hdr *oldhdr, *hdr;
int hdrlen, err;
hdrlen = (tuninfo->eh.hdrlen + 1) << 3;
- err = skb_cow_head(skb, hdrlen + skb->mac_len);
+ err = skb_cow_head(skb, hdrlen + dst_dev_overhead(cache_dst, skb));
if (unlikely(err))
return err;
@@ -293,7 +294,8 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
struct ioam6_lwt_encap *tuninfo,
bool has_tunsrc,
struct in6_addr *tunsrc,
- struct in6_addr *tundst)
+ struct in6_addr *tundst,
+ struct dst_entry *cache_dst)
{
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr, *inner_hdr;
@@ -302,7 +304,7 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
hdrlen = (tuninfo->eh.hdrlen + 1) << 3;
len = sizeof(*hdr) + hdrlen;
- err = skb_cow_head(skb, len + skb->mac_len);
+ err = skb_cow_head(skb, len + dst_dev_overhead(cache_dst, skb));
if (unlikely(err))
return err;
@@ -336,8 +338,7 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct dst_entry *dst = skb_dst(skb);
- struct in6_addr orig_daddr;
+ struct dst_entry *dst = skb_dst(skb), *cache_dst = NULL;
struct ioam6_lwt *ilwt;
int err = -EINVAL;
u32 pkt_cnt;
@@ -352,7 +353,9 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (pkt_cnt % ilwt->freq.n >= ilwt->freq.k)
goto out;
- orig_daddr = ipv6_hdr(skb)->daddr;
+ local_bh_disable();
+ cache_dst = dst_cache_get(&ilwt->cache);
+ local_bh_enable();
switch (ilwt->mode) {
case IOAM6_IPTUNNEL_MODE_INLINE:
@@ -361,7 +364,7 @@ do_inline:
if (ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP)
goto out;
- err = ioam6_do_inline(net, skb, &ilwt->tuninfo);
+ err = ioam6_do_inline(net, skb, &ilwt->tuninfo, cache_dst);
if (unlikely(err))
goto drop;
@@ -371,7 +374,7 @@ do_encap:
/* Encapsulation (ip6ip6) */
err = ioam6_do_encap(net, skb, &ilwt->tuninfo,
ilwt->has_tunsrc, &ilwt->tunsrc,
- &ilwt->tundst);
+ &ilwt->tundst, cache_dst);
if (unlikely(err))
goto drop;
@@ -389,46 +392,48 @@ do_encap:
goto drop;
}
- err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
- if (unlikely(err))
- goto drop;
+ if (unlikely(!cache_dst)) {
+ struct ipv6hdr *hdr = ipv6_hdr(skb);
+ struct flowi6 fl6;
- if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) {
- local_bh_disable();
- dst = dst_cache_get(&ilwt->cache);
- local_bh_enable();
-
- if (unlikely(!dst)) {
- struct ipv6hdr *hdr = ipv6_hdr(skb);
- struct flowi6 fl6;
-
- memset(&fl6, 0, sizeof(fl6));
- fl6.daddr = hdr->daddr;
- fl6.saddr = hdr->saddr;
- fl6.flowlabel = ip6_flowinfo(hdr);
- fl6.flowi6_mark = skb->mark;
- fl6.flowi6_proto = hdr->nexthdr;
-
- dst = ip6_route_output(net, NULL, &fl6);
- if (dst->error) {
- err = dst->error;
- dst_release(dst);
- goto drop;
- }
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.daddr = hdr->daddr;
+ fl6.saddr = hdr->saddr;
+ fl6.flowlabel = ip6_flowinfo(hdr);
+ fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_proto = hdr->nexthdr;
+
+ cache_dst = ip6_route_output(net, NULL, &fl6);
+ if (cache_dst->error) {
+ err = cache_dst->error;
+ goto drop;
+ }
+ /* cache only if we don't create a dst reference loop */
+ if (dst->lwtstate != cache_dst->lwtstate) {
local_bh_disable();
- dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr);
+ dst_cache_set_ip6(&ilwt->cache, cache_dst, &fl6.saddr);
local_bh_enable();
}
- skb_dst_drop(skb);
- skb_dst_set(skb, dst);
+ err = skb_cow_head(skb, LL_RESERVED_SPACE(cache_dst->dev));
+ if (unlikely(err))
+ goto drop;
+ }
+ /* avoid lwtunnel_output() reentry loop when destination is the same
+ * after transformation (e.g., with the inline mode)
+ */
+ if (dst->lwtstate != cache_dst->lwtstate) {
+ skb_dst_drop(skb);
+ skb_dst_set(skb, cache_dst);
return dst_output(net, sk, skb);
}
out:
+ dst_release(cache_dst);
return dst->lwtstate->orig_output(net, sk, skb);
drop:
+ dst_release(cache_dst);
kfree_skb(skb);
return err;
}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 9a1c59275a10..aa1046fbf28e 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -440,15 +440,17 @@ struct fib6_dump_arg {
static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg)
{
enum fib_event_type fib_event = FIB_EVENT_ENTRY_REPLACE;
+ unsigned int nsiblings;
int err;
if (!rt || rt == arg->net->ipv6.fib6_null_entry)
return 0;
- if (rt->fib6_nsiblings)
+ nsiblings = READ_ONCE(rt->fib6_nsiblings);
+ if (nsiblings)
err = call_fib6_multipath_entry_notifier(arg->nb, fib_event,
rt,
- rt->fib6_nsiblings,
+ nsiblings,
arg->extack);
else
err = call_fib6_entry_notifier(arg->nb, fib_event, rt,
@@ -1126,7 +1128,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
if (rt6_duplicate_nexthop(iter, rt)) {
if (rt->fib6_nsiblings)
- rt->fib6_nsiblings = 0;
+ WRITE_ONCE(rt->fib6_nsiblings, 0);
if (!(iter->fib6_flags & RTF_EXPIRES))
return -EEXIST;
if (!(rt->fib6_flags & RTF_EXPIRES)) {
@@ -1155,7 +1157,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
*/
if (rt_can_ecmp &&
rt6_qualify_for_ecmp(iter))
- rt->fib6_nsiblings++;
+ WRITE_ONCE(rt->fib6_nsiblings,
+ rt->fib6_nsiblings + 1);
}
if (iter->fib6_metric > rt->fib6_metric)
@@ -1205,7 +1208,8 @@ next_iter:
fib6_nsiblings = 0;
list_for_each_entry_safe(sibling, temp_sibling,
&rt->fib6_siblings, fib6_siblings) {
- sibling->fib6_nsiblings++;
+ WRITE_ONCE(sibling->fib6_nsiblings,
+ sibling->fib6_nsiblings + 1);
BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings);
fib6_nsiblings++;
}
@@ -1250,8 +1254,9 @@ add:
list_for_each_entry_safe(sibling, next_sibling,
&rt->fib6_siblings,
fib6_siblings)
- sibling->fib6_nsiblings--;
- rt->fib6_nsiblings = 0;
+ WRITE_ONCE(sibling->fib6_nsiblings,
+ sibling->fib6_nsiblings - 1);
+ WRITE_ONCE(rt->fib6_nsiblings, 0);
list_del_rcu(&rt->fib6_siblings);
rt6_multipath_rebalance(next_sibling);
return err;
@@ -1968,8 +1973,9 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
notify_del = true;
list_for_each_entry_safe(sibling, next_sibling,
&rt->fib6_siblings, fib6_siblings)
- sibling->fib6_nsiblings--;
- rt->fib6_nsiblings = 0;
+ WRITE_ONCE(sibling->fib6_nsiblings,
+ sibling->fib6_nsiblings - 1);
+ WRITE_ONCE(rt->fib6_nsiblings, 0);
list_del_rcu(&rt->fib6_siblings);
rt6_multipath_rebalance(next_sibling);
}
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 235808cfec70..68e9a41eed49 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1498,7 +1498,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
tunnel = netdev_priv(dev);
tunnel->dev = dev;
- tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
@@ -1882,7 +1881,6 @@ static int ip6erspan_tap_init(struct net_device *dev)
tunnel = netdev_priv(dev);
tunnel->dev = dev;
- tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 9822163428b0..fce91183797a 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -148,7 +148,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
ops = rcu_dereference(inet6_offloads[proto]);
if (likely(ops && ops->callbacks.gso_segment)) {
- skb_reset_transport_header(skb);
+ if (!skb_reset_transport_header_careful(skb))
+ goto out;
+
segs = ops->callbacks.gso_segment(skb, features);
if (!segs)
skb->network_header = skb_mac_header(skb) + nhoff - skb->head;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f26841f1490f..f0e5431c2d46 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -613,15 +613,15 @@ int ip6_forward(struct sk_buff *skb)
else
target = &hdr->daddr;
- peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr, 1);
+ rcu_read_lock();
+ peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr);
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
*/
if (inet_peer_xrlim_allow(peer, 1*HZ))
ndisc_send_redirect(skb, target);
- if (peer)
- inet_putpeer(peer);
+ rcu_read_unlock();
} else {
int addrtype = ipv6_addr_type(&hdr->saddr);
@@ -1386,6 +1386,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
}
v6_cork->hop_limit = ipc6->hlimit;
v6_cork->tclass = ipc6->tclass;
+ v6_cork->dontfrag = ipc6->dontfrag;
if (rt->dst.flags & DST_XFRM_TUNNEL)
mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst);
@@ -1417,7 +1418,7 @@ static int __ip6_append_data(struct sock *sk,
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
void *from, size_t length, int transhdrlen,
- unsigned int flags, struct ipcm6_cookie *ipc6)
+ unsigned int flags)
{
struct sk_buff *skb, *skb_prev = NULL;
struct inet_cork *cork = &cork_full->base;
@@ -1471,7 +1472,7 @@ static int __ip6_append_data(struct sock *sk,
if (headersize + transhdrlen > mtu)
goto emsgsize;
- if (cork->length + length > mtu - headersize && ipc6->dontfrag &&
+ if (cork->length + length > mtu - headersize && v6_cork->dontfrag &&
(sk->sk_protocol == IPPROTO_UDP ||
sk->sk_protocol == IPPROTO_ICMPV6 ||
sk->sk_protocol == IPPROTO_RAW)) {
@@ -1843,7 +1844,7 @@ int ip6_append_data(struct sock *sk,
return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork,
&np->cork, sk_page_frag(sk), getfrag,
- from, length, transhdrlen, flags, ipc6);
+ from, length, transhdrlen, flags);
}
EXPORT_SYMBOL_GPL(ip6_append_data);
@@ -2042,13 +2043,11 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
ip6_cork_release(cork, &v6_cork);
return ERR_PTR(err);
}
- if (ipc6->dontfrag < 0)
- ipc6->dontfrag = inet6_test_bit(DONTFRAG, sk);
err = __ip6_append_data(sk, &queue, cork, &v6_cork,
&current->task_frag, getfrag, from,
length + exthdrlen, transhdrlen + exthdrlen,
- flags, ipc6);
+ flags);
if (err) {
__ip6_flush_pending_frames(sk, &queue, cork, &v6_cork);
return ERR_PTR(err);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index b60e13c42bca..5350c9bb2319 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -630,8 +630,8 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
}
skb_dst_set(skb2, &rt->dst);
} else {
- if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
- skb2->dev) ||
+ if (ip_route_input(skb2, eiph->daddr, eiph->saddr,
+ ip4h_dscp(eiph), skb2->dev) ||
skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6)
goto out;
}
@@ -1878,7 +1878,6 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
int t_hlen;
t->dev = dev;
- t->net = dev_net(dev);
ret = dst_cache_init(&t->dst_cache, GFP_KERNEL);
if (ret)
@@ -1940,6 +1939,7 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+ t->net = net;
t->parms.proto = IPPROTO_IPV6;
rcu_assign_pointer(ip6n->tnls_wc[0], t);
@@ -2013,6 +2013,7 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
int err;
nt = netdev_priv(dev);
+ nt->net = net;
if (ip_tunnel_netlink_encap_parms(data, &ipencap)) {
err = ip6_tnl_encap_setup(nt, &ipencap);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 590737c27537..012350469144 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -925,7 +925,6 @@ static inline int vti6_dev_init_gen(struct net_device *dev)
struct ip6_tnl *t = netdev_priv(dev);
t->dev = dev;
- t->net = dev_net(dev);
netdev_hold(dev, &t->dev_tracker, GFP_KERNEL);
netdev_lockdep_set_classes(dev);
return 0;
@@ -958,6 +957,7 @@ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev)
struct net *net = dev_net(dev);
struct vti6_net *ip6n = net_generic(net, vti6_net_id);
+ t->net = net;
t->parms.proto = IPPROTO_IPV6;
rcu_assign_pointer(ip6n->tnls_wc[0], t);
@@ -1008,6 +1008,7 @@ static int vti6_newlink(struct net *src_net, struct net_device *dev,
vti6_netlink_parms(data, &nt->parms);
nt->parms.proto = IPPROTO_IPV6;
+ nt->net = net;
if (vti6_locate(net, &nt->parms, 0))
return -EEXIST;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index d5057401701c..68bc518500f9 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -506,9 +506,9 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
if (it->cache != &mrt->mfc_unres_queue) {
seq_printf(seq, " %8lu %8lu %8lu",
- mfc->_c.mfc_un.res.pkt,
- mfc->_c.mfc_un.res.bytes,
- mfc->_c.mfc_un.res.wrong_if);
+ atomic_long_read(&mfc->_c.mfc_un.res.pkt),
+ atomic_long_read(&mfc->_c.mfc_un.res.bytes),
+ atomic_long_read(&mfc->_c.mfc_un.res.wrong_if));
for (n = mfc->_c.mfc_un.res.minvif;
n < mfc->_c.mfc_un.res.maxvif; n++) {
if (VIF_EXISTS(mrt, n) &&
@@ -870,7 +870,7 @@ static void ip6mr_update_thresholds(struct mr_table *mrt,
cache->mfc_un.res.maxvif = vifi + 1;
}
}
- cache->mfc_un.res.lastuse = jiffies;
+ WRITE_ONCE(cache->mfc_un.res.lastuse, jiffies);
}
static int mif6_add(struct net *net, struct mr_table *mrt,
@@ -1928,9 +1928,9 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void *arg)
c = ip6mr_cache_find(mrt, &sr->src.sin6_addr,
&sr->grp.sin6_addr);
if (c) {
- sr->pktcnt = c->_c.mfc_un.res.pkt;
- sr->bytecnt = c->_c.mfc_un.res.bytes;
- sr->wrong_if = c->_c.mfc_un.res.wrong_if;
+ sr->pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt);
+ sr->bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes);
+ sr->wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if);
rcu_read_unlock();
return 0;
}
@@ -2000,9 +2000,9 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
rcu_read_lock();
c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr);
if (c) {
- sr.pktcnt = c->_c.mfc_un.res.pkt;
- sr.bytecnt = c->_c.mfc_un.res.bytes;
- sr.wrong_if = c->_c.mfc_un.res.wrong_if;
+ sr.pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt);
+ sr.bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes);
+ sr.wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if);
rcu_read_unlock();
if (copy_to_user(arg, &sr, sizeof(sr)))
@@ -2032,6 +2032,7 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt,
struct sk_buff *skb, int vifi)
{
struct vif_device *vif = &mrt->vif_table[vifi];
+ struct net_device *indev = skb->dev;
struct net_device *vif_dev;
struct ipv6hdr *ipv6h;
struct dst_entry *dst;
@@ -2094,7 +2095,7 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt,
IP6CB(skb)->flags |= IP6SKB_FORWARDED;
return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
- net, NULL, skb, skb->dev, vif_dev,
+ net, NULL, skb, indev, skb->dev,
ip6mr_forward2_finish);
out_free:
@@ -2125,9 +2126,9 @@ static void ip6_mr_forward(struct net *net, struct mr_table *mrt,
int true_vifi = ip6mr_find_vif(mrt, dev);
vif = c->_c.mfc_parent;
- c->_c.mfc_un.res.pkt++;
- c->_c.mfc_un.res.bytes += skb->len;
- c->_c.mfc_un.res.lastuse = jiffies;
+ atomic_long_inc(&c->_c.mfc_un.res.pkt);
+ atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes);
+ WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies);
if (ipv6_addr_any(&c->mf6c_origin) && true_vifi >= 0) {
struct mfc6_cache *cache_proxy;
@@ -2145,7 +2146,7 @@ static void ip6_mr_forward(struct net *net, struct mr_table *mrt,
* Wrong interface: drop packet and (maybe) send PIM assert.
*/
if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) {
- c->_c.mfc_un.res.wrong_if++;
+ atomic_long_inc(&c->_c.mfc_un.res.wrong_if);
if (true_vifi >= 0 && mrt->mroute_do_assert &&
/* pimsm uses asserts, when switching from RPT to SPT,
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index b244dbf61d5f..e2a11a2f3b25 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -804,8 +804,8 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
} else {
im->mca_crcount = idev->mc_qrv;
}
- in6_dev_put(pmc->idev);
ip6_mc_clear_src(pmc);
+ in6_dev_put(pmc->idev);
kfree_rcu(pmc, rcu);
}
}
@@ -907,23 +907,22 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev,
static int __ipv6_dev_mc_inc(struct net_device *dev,
const struct in6_addr *addr, unsigned int mode)
{
- struct ifmcaddr6 *mc;
struct inet6_dev *idev;
-
- ASSERT_RTNL();
+ struct ifmcaddr6 *mc;
/* we need to take a reference on idev */
idev = in6_dev_get(dev);
-
if (!idev)
return -EINVAL;
- if (idev->dead) {
+ mutex_lock(&idev->mc_lock);
+
+ if (READ_ONCE(idev->dead)) {
+ mutex_unlock(&idev->mc_lock);
in6_dev_put(idev);
return -ENODEV;
}
- mutex_lock(&idev->mc_lock);
for_each_mc_mclock(idev, mc) {
if (ipv6_addr_equal(&mc->mca_addr, addr)) {
mc->mca_users++;
@@ -1730,21 +1729,19 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
struct net_device *dev = idev->dev;
int hlen = LL_RESERVED_SPACE(dev);
int tlen = dev->needed_tailroom;
- struct net *net = dev_net(dev);
const struct in6_addr *saddr;
struct in6_addr addr_buf;
struct mld2_report *pmr;
struct sk_buff *skb;
unsigned int size;
struct sock *sk;
- int err;
+ struct net *net;
- sk = net->ipv6.igmp_sk;
/* we assume size > sizeof(ra) here
* Also try to not allocate high-order pages for big MTU
*/
size = min_t(int, mtu, PAGE_SIZE / 2) + hlen + tlen;
- skb = sock_alloc_send_skb(sk, size, 1, &err);
+ skb = alloc_skb(size, GFP_KERNEL);
if (!skb)
return NULL;
@@ -1752,6 +1749,12 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
skb_reserve(skb, hlen);
skb_tailroom_reserve(skb, mtu, tlen);
+ rcu_read_lock();
+
+ net = dev_net_rcu(dev);
+ sk = net->ipv6.igmp_sk;
+ skb_set_owner_w(skb, sk);
+
if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) {
/* <draft-ietf-magma-mld-source-05.txt>:
* use unspecified address as the source address
@@ -1763,6 +1766,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
ip6_mc_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0);
+ rcu_read_unlock();
+
skb_put_data(skb, ra, sizeof(ra));
skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data);
@@ -2122,21 +2127,21 @@ static void mld_send_cr(struct inet6_dev *idev)
static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
{
- struct net *net = dev_net(dev);
- struct sock *sk = net->ipv6.igmp_sk;
+ const struct in6_addr *snd_addr, *saddr;
+ int err, len, payload_len, full_len;
+ struct in6_addr addr_buf;
struct inet6_dev *idev;
struct sk_buff *skb;
struct mld_msg *hdr;
- const struct in6_addr *snd_addr, *saddr;
- struct in6_addr addr_buf;
int hlen = LL_RESERVED_SPACE(dev);
int tlen = dev->needed_tailroom;
- int err, len, payload_len, full_len;
u8 ra[8] = { IPPROTO_ICMPV6, 0,
IPV6_TLV_ROUTERALERT, 2, 0, 0,
IPV6_TLV_PADN, 0 };
- struct flowi6 fl6;
struct dst_entry *dst;
+ struct flowi6 fl6;
+ struct net *net;
+ struct sock *sk;
if (type == ICMPV6_MGM_REDUCTION)
snd_addr = &in6addr_linklocal_allrouters;
@@ -2147,19 +2152,21 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
payload_len = len + sizeof(ra);
full_len = sizeof(struct ipv6hdr) + payload_len;
- rcu_read_lock();
- IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTREQUESTS);
- rcu_read_unlock();
+ skb = alloc_skb(hlen + tlen + full_len, GFP_KERNEL);
- skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err);
+ rcu_read_lock();
+ net = dev_net_rcu(dev);
+ idev = __in6_dev_get(dev);
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS);
if (!skb) {
- rcu_read_lock();
- IP6_INC_STATS(net, __in6_dev_get(dev),
- IPSTATS_MIB_OUTDISCARDS);
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
rcu_read_unlock();
return;
}
+ sk = net->ipv6.igmp_sk;
+ skb_set_owner_w(skb, sk);
+
skb->priority = TC_PRIO_CONTROL;
skb_reserve(skb, hlen);
@@ -2184,9 +2191,6 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
IPPROTO_ICMPV6,
csum_partial(hdr, len, 0));
- rcu_read_lock();
- idev = __in6_dev_get(skb->dev);
-
icmpv6_flow_init(sk, &fl6, type,
&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
skb->dev->ifindex);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index aba94a348673..8699d1a188dc 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -418,15 +418,11 @@ static struct sk_buff *ndisc_alloc_skb(struct net_device *dev,
{
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;
@@ -437,7 +433,9 @@ 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;
}
@@ -473,16 +471,20 @@ static void ip6_nd_hdr(struct sk_buff *skb,
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 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;
@@ -490,6 +492,7 @@ void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr,
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;
}
@@ -504,7 +507,6 @@ void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr,
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_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS);
@@ -1694,7 +1696,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
bool ret;
if (netif_is_l3_master(skb->dev)) {
- dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif);
+ dev = dev_get_by_index_rcu(dev_net(skb->dev), IPCB(skb)->iif);
if (!dev)
return;
}
@@ -1731,10 +1733,12 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
"Redirect: destination is not a neighbour\n");
goto release;
}
- peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr, 1);
+
+ rcu_read_lock();
+ peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr);
ret = inet_peer_xrlim_allow(peer, 1*HZ);
- if (peer)
- inet_putpeer(peer);
+ rcu_read_unlock();
+
if (!ret)
goto release;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 581ce055bf52..4541836ee3da 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -164,20 +164,20 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
struct ip6_fraglist_iter iter;
struct sk_buff *frag2;
- if (first_len - hlen > mtu ||
- skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
+ if (first_len - hlen > mtu)
goto blackhole;
- if (skb_cloned(skb))
+ if (skb_cloned(skb) ||
+ skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
goto slow_path;
skb_walk_frags(skb, frag2) {
- if (frag2->len > mtu ||
- skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
+ if (frag2->len > mtu)
goto blackhole;
/* Partially cloned skb? */
- if (skb_shared(frag2))
+ if (skb_shared(frag2) ||
+ skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
goto slow_path;
}
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 9ae2b2725bf9..c3d64c4b69d7 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -293,7 +293,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
fl6.fl6_sport = otcph->dest;
fl6.fl6_dport = otcph->source;
- if (hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) {
+ if (!skb_dst(oldskb)) {
nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false);
if (!dst)
return;
@@ -397,8 +397,7 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in,
if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL)
skb_in->dev = net->loopback_dev;
- if ((hooknum == NF_INET_PRE_ROUTING || hooknum == NF_INET_INGRESS) &&
- nf_reject6_fill_skb_dst(skb_in) < 0)
+ if (!skb_dst(skb_in) && nf_reject6_fill_skb_dst(skb_in) < 0)
return;
icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);
diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
index a7690ec62325..9ea5ef56cb27 100644
--- a/net/ipv6/netfilter/nf_socket_ipv6.c
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -103,6 +103,10 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
struct sk_buff *data_skb = NULL;
int doff = 0;
int thoff = 0, tproto;
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn const *ct;
+#endif
tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
if (tproto < 0) {
@@ -136,6 +140,25 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
return NULL;
}
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ /* Do the lookup with the original socket address in
+ * case this is a reply packet of an established
+ * SNAT-ted connection.
+ */
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct &&
+ ((tproto != IPPROTO_ICMPV6 &&
+ ctinfo == IP_CT_ESTABLISHED_REPLY) ||
+ (tproto == IPPROTO_ICMPV6 &&
+ ctinfo == IP_CT_RELATED_REPLY)) &&
+ (ct->status & IPS_SRC_NAT_DONE)) {
+ daddr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in6;
+ dport = (tproto == IPPROTO_TCP) ?
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port :
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port;
+ }
+#endif
+
return nf_socket_get_sock_v6(net, data_skb, doff, tproto, saddr, daddr,
sport, dport, indev);
}
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index c9f1634b3838..421036a3605b 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -50,6 +50,7 @@ static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv,
fl6->flowi6_mark = pkt->skb->mark;
fl6->flowlabel = (*(__be32 *)iph) & IPV6_FLOWINFO_MASK;
+ fl6->flowi6_l3mdev = nft_fib_l3mdev_master_ifindex_rcu(pkt, dev);
return lookup_flags;
}
@@ -73,8 +74,6 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv,
else if (priv->flags & NFTA_FIB_F_OIF)
dev = nft_out(pkt);
- fl6.flowi6_l3mdev = l3mdev_master_ifindex_rcu(dev);
-
nft_fib6_flowi_init(&fl6, priv, pkt, dev, iph);
if (dev && nf_ipv6_chk_addr(nft_net(pkt), &fl6.daddr, dev, true))
@@ -158,6 +157,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
{
const struct nft_fib *priv = nft_expr_priv(expr);
int noff = skb_network_offset(pkt->skb);
+ const struct net_device *found = NULL;
const struct net_device *oif = NULL;
u32 *dest = &regs->data[priv->dreg];
struct ipv6hdr *iph, _iph;
@@ -165,11 +165,15 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
.flowi6_iif = LOOPBACK_IFINDEX,
.flowi6_proto = pkt->tprot,
.flowi6_uid = sock_net_uid(nft_net(pkt), NULL),
- .flowi6_l3mdev = l3mdev_master_ifindex_rcu(nft_in(pkt)),
};
struct rt6_info *rt;
int lookup_flags;
+ if (nft_fib_can_skip(pkt)) {
+ nft_fib_store_result(dest, priv, nft_in(pkt));
+ return;
+ }
+
if (priv->flags & NFTA_FIB_F_IIF)
oif = nft_in(pkt);
else if (priv->flags & NFTA_FIB_F_OIF)
@@ -181,17 +185,13 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
return;
}
- lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph);
-
- if (nft_hook(pkt) == NF_INET_PRE_ROUTING ||
- nft_hook(pkt) == NF_INET_INGRESS) {
- if (nft_fib_is_loopback(pkt->skb, nft_in(pkt)) ||
- nft_fib_v6_skip_icmpv6(pkt->skb, pkt->tprot, iph)) {
- nft_fib_store_result(dest, priv, nft_in(pkt));
- return;
- }
+ if (nft_fib_v6_skip_icmpv6(pkt->skb, pkt->tprot, iph)) {
+ nft_fib_store_result(dest, priv, nft_in(pkt));
+ return;
}
+ lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph);
+
*dest = 0;
rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, pkt->skb,
lookup_flags);
@@ -202,11 +202,15 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL))
goto put_rt_err;
- if (oif && oif != rt->rt6i_idev->dev &&
- l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) != oif->ifindex)
- goto put_rt_err;
+ if (!oif) {
+ found = rt->rt6i_idev->dev;
+ } else {
+ if (oif == rt->rt6i_idev->dev ||
+ l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == oif->ifindex)
+ found = oif;
+ }
- nft_fib_store_result(dest, priv, rt->rt6i_idev->dev);
+ nft_fib_store_result(dest, priv, found);
put_rt_err:
ip6_rt_put(rt);
}
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 608fa9d05b55..328419e05c81 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -777,7 +777,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowi6_mark = READ_ONCE(sk->sk_mark);
fl6.flowi6_uid = sk->sk_uid;
- ipcm6_init(&ipc6);
+ ipcm6_init_sk(&ipc6, sk);
ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
ipc6.sockc.mark = fl6.flowi6_mark;
@@ -890,9 +890,6 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (hdrincl)
fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
- if (ipc6.tclass < 0)
- ipc6.tclass = np->tclass;
-
fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
@@ -903,9 +900,6 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (ipc6.hlimit < 0)
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
- if (ipc6.dontfrag < 0)
- ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk);
-
if (msg->msg_flags&MSG_CONFIRM)
goto do_confirm;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8ebfed5d6323..22866444efc0 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -412,12 +412,37 @@ static bool rt6_check_expired(const struct rt6_info *rt)
return false;
}
+static struct fib6_info *
+rt6_multipath_first_sibling_rcu(const struct fib6_info *rt)
+{
+ struct fib6_info *iter;
+ struct fib6_node *fn;
+
+ fn = rcu_dereference(rt->fib6_node);
+ if (!fn)
+ goto out;
+ iter = rcu_dereference(fn->leaf);
+ if (!iter)
+ goto out;
+
+ while (iter) {
+ if (iter->fib6_metric == rt->fib6_metric &&
+ rt6_qualify_for_ecmp(iter))
+ return iter;
+ iter = rcu_dereference(iter->fib6_next);
+ }
+
+out:
+ return NULL;
+}
+
void fib6_select_path(const struct net *net, struct fib6_result *res,
struct flowi6 *fl6, int oif, bool have_oif_match,
const struct sk_buff *skb, int strict)
{
- struct fib6_info *match = res->f6i;
+ struct fib6_info *first, *match = res->f6i;
struct fib6_info *sibling;
+ int hash;
if (!match->nh && (!match->fib6_nsiblings || have_oif_match))
goto out;
@@ -440,16 +465,25 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
return;
}
- if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound))
+ first = rt6_multipath_first_sibling_rcu(match);
+ if (!first)
goto out;
- list_for_each_entry_rcu(sibling, &match->fib6_siblings,
+ hash = fl6->mp_hash;
+ if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound)) {
+ if (rt6_score_route(first->fib6_nh, first->fib6_flags, oif,
+ strict) >= 0)
+ match = first;
+ goto out;
+ }
+
+ list_for_each_entry_rcu(sibling, &first->fib6_siblings,
fib6_siblings) {
const struct fib6_nh *nh = sibling->fib6_nh;
int nh_upper_bound;
nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound);
- if (fl6->mp_hash > nh_upper_bound)
+ if (hash > nh_upper_bound)
continue;
if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0)
break;
@@ -1737,6 +1771,7 @@ out:
if (!err) {
spin_lock_bh(&f6i->fib6_table->tb6_lock);
fib6_update_sernum(net, f6i);
+ fib6_add_gc_list(f6i);
spin_unlock_bh(&f6i->fib6_table->tb6_lock);
fib6_force_start_gc(net);
}
@@ -3196,13 +3231,18 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst)
{
struct net_device *dev = dst->dev;
unsigned int mtu = dst_mtu(dst);
- struct net *net = dev_net(dev);
+ struct net *net;
mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);
+ rcu_read_lock();
+
+ net = dev_net_rcu(dev);
if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss)
mtu = net->ipv6.sysctl.ip6_rt_min_advmss;
+ rcu_read_unlock();
+
/*
* Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and
* corresponding MSS is IPV6_MAXPLEN - tcp_header_size.
@@ -3639,7 +3679,8 @@ out:
in6_dev_put(idev);
if (err) {
- lwtstate_put(fib6_nh->fib_nh_lws);
+ fib_nh_common_release(&fib6_nh->nh_common);
+ fib6_nh->nh_common.nhc_pcpu_rth_output = NULL;
fib6_nh->fib_nh_lws = NULL;
netdev_put(dev, dev_tracker);
}
@@ -3797,10 +3838,12 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
if (nh) {
if (rt->fib6_src.plen) {
NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+ err = -EINVAL;
goto out_free;
}
if (!nexthop_get(nh)) {
NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+ err = -ENOENT;
goto out_free;
}
rt->nh = nh;
@@ -5197,7 +5240,8 @@ static void ip6_route_mpath_notify(struct fib6_info *rt,
*/
rcu_read_lock();
- if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) {
+ if ((nlflags & NLM_F_APPEND) && rt_last &&
+ READ_ONCE(rt_last->fib6_nsiblings)) {
rt = list_first_or_null_rcu(&rt_last->fib6_siblings,
struct fib6_info,
fib6_siblings);
@@ -5544,32 +5588,34 @@ static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg)
static size_t rt6_nlmsg_size(struct fib6_info *f6i)
{
+ struct fib6_info *sibling;
+ struct fib6_nh *nh;
int nexthop_len;
if (f6i->nh) {
nexthop_len = nla_total_size(4); /* RTA_NH_ID */
nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size,
&nexthop_len);
- } else {
- struct fib6_nh *nh = f6i->fib6_nh;
- struct fib6_info *sibling;
-
- nexthop_len = 0;
- if (f6i->fib6_nsiblings) {
- rt6_nh_nlmsg_size(nh, &nexthop_len);
-
- rcu_read_lock();
+ goto common;
+ }
- list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
- fib6_siblings) {
- rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
- }
+ rcu_read_lock();
+retry:
+ nh = f6i->fib6_nh;
+ nexthop_len = 0;
+ if (READ_ONCE(f6i->fib6_nsiblings)) {
+ rt6_nh_nlmsg_size(nh, &nexthop_len);
- rcu_read_unlock();
+ list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
+ fib6_siblings) {
+ rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
+ if (!READ_ONCE(f6i->fib6_nsiblings))
+ goto retry;
}
- nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
}
-
+ rcu_read_unlock();
+ nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
+common:
return NLMSG_ALIGN(sizeof(struct rtmsg))
+ nla_total_size(16) /* RTA_SRC */
+ nla_total_size(16) /* RTA_DST */
@@ -5728,7 +5774,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
if (dst->lwtstate &&
lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
goto nla_put_failure;
- } else if (rt->fib6_nsiblings) {
+ } else if (READ_ONCE(rt->fib6_nsiblings)) {
struct fib6_info *sibling;
struct nlattr *mp;
@@ -5830,16 +5876,21 @@ static bool fib6_info_uses_dev(const struct fib6_info *f6i,
if (f6i->fib6_nh->fib_nh_dev == dev)
return true;
- if (f6i->fib6_nsiblings) {
- struct fib6_info *sibling, *next_sibling;
+ if (READ_ONCE(f6i->fib6_nsiblings)) {
+ const struct fib6_info *sibling;
- list_for_each_entry_safe(sibling, next_sibling,
- &f6i->fib6_siblings, fib6_siblings) {
- if (sibling->fib6_nh->fib_nh_dev == dev)
+ rcu_read_lock();
+ list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
+ fib6_siblings) {
+ if (sibling->fib6_nh->fib_nh_dev == dev) {
+ rcu_read_unlock();
return true;
+ }
+ if (!READ_ONCE(f6i->fib6_nsiblings))
+ break;
}
+ rcu_read_unlock();
}
-
return false;
}
diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index db3c19a42e1c..eccfa4203e96 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -125,16 +125,17 @@ static void rpl_destroy_state(struct lwtunnel_state *lwt)
}
static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt,
- const struct ipv6_rpl_sr_hdr *srh)
+ const struct ipv6_rpl_sr_hdr *srh,
+ struct dst_entry *cache_dst)
{
struct ipv6_rpl_sr_hdr *isrh, *csrh;
- const struct ipv6hdr *oldhdr;
+ struct ipv6hdr oldhdr;
struct ipv6hdr *hdr;
unsigned char *buf;
size_t hdrlen;
int err;
- oldhdr = ipv6_hdr(skb);
+ memcpy(&oldhdr, ipv6_hdr(skb), sizeof(oldhdr));
buf = kcalloc(struct_size(srh, segments.addr, srh->segments_left), 2, GFP_ATOMIC);
if (!buf)
@@ -146,14 +147,14 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt,
memcpy(isrh, srh, sizeof(*isrh));
memcpy(isrh->rpl_segaddr, &srh->rpl_segaddr[1],
(srh->segments_left - 1) * 16);
- isrh->rpl_segaddr[srh->segments_left - 1] = oldhdr->daddr;
+ isrh->rpl_segaddr[srh->segments_left - 1] = oldhdr.daddr;
ipv6_rpl_srh_compress(csrh, isrh, &srh->rpl_segaddr[0],
isrh->segments_left - 1);
hdrlen = ((csrh->hdrlen + 1) << 3);
- err = skb_cow_head(skb, hdrlen + skb->mac_len);
+ err = skb_cow_head(skb, hdrlen + dst_dev_overhead(cache_dst, skb));
if (unlikely(err)) {
kfree(buf);
return err;
@@ -168,7 +169,7 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt,
skb_mac_header_rebuild(skb);
hdr = ipv6_hdr(skb);
- memmove(hdr, oldhdr, sizeof(*hdr));
+ memmove(hdr, &oldhdr, sizeof(*hdr));
isrh = (void *)hdr + sizeof(*hdr);
memcpy(isrh, csrh, hdrlen);
@@ -186,7 +187,8 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt,
return 0;
}
-static int rpl_do_srh(struct sk_buff *skb, const struct rpl_lwt *rlwt)
+static int rpl_do_srh(struct sk_buff *skb, const struct rpl_lwt *rlwt,
+ struct dst_entry *cache_dst)
{
struct dst_entry *dst = skb_dst(skb);
struct rpl_iptunnel_encap *tinfo;
@@ -196,7 +198,7 @@ static int rpl_do_srh(struct sk_buff *skb, const struct rpl_lwt *rlwt)
tinfo = rpl_encap_lwtunnel(dst->lwtstate);
- return rpl_do_srh_inline(skb, rlwt, tinfo->srh);
+ return rpl_do_srh_inline(skb, rlwt, tinfo->srh, cache_dst);
}
static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
@@ -208,14 +210,14 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate);
- err = rpl_do_srh(skb, rlwt);
- if (unlikely(err))
- goto drop;
-
local_bh_disable();
dst = dst_cache_get(&rlwt->cache);
local_bh_enable();
+ err = rpl_do_srh(skb, rlwt, dst);
+ if (unlikely(err))
+ goto drop;
+
if (unlikely(!dst)) {
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct flowi6 fl6;
@@ -230,25 +232,28 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
err = dst->error;
- dst_release(dst);
goto drop;
}
- local_bh_disable();
- dst_cache_set_ip6(&rlwt->cache, dst, &fl6.saddr);
- local_bh_enable();
+ /* cache only if we don't create a dst reference loop */
+ if (orig_dst->lwtstate != dst->lwtstate) {
+ local_bh_disable();
+ dst_cache_set_ip6(&rlwt->cache, dst, &fl6.saddr);
+ local_bh_enable();
+ }
+
+ err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+ if (unlikely(err))
+ goto drop;
}
skb_dst_drop(skb);
skb_dst_set(skb, dst);
- err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
- if (unlikely(err))
- goto drop;
-
return dst_output(net, sk, skb);
drop:
+ dst_release(dst);
kfree_skb(skb);
return err;
}
@@ -257,34 +262,48 @@ static int rpl_input(struct sk_buff *skb)
{
struct dst_entry *orig_dst = skb_dst(skb);
struct dst_entry *dst = NULL;
+ struct lwtunnel_state *lwtst;
struct rpl_lwt *rlwt;
int err;
- rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate);
+ /* We cannot dereference "orig_dst" once ip6_route_input() or
+ * skb_dst_drop() is called. However, in order to detect a dst loop, we
+ * need the address of its lwtstate. So, save the address of lwtstate
+ * now and use it later as a comparison.
+ */
+ lwtst = orig_dst->lwtstate;
- err = rpl_do_srh(skb, rlwt);
- if (unlikely(err))
- goto drop;
+ rlwt = rpl_lwt_lwtunnel(lwtst);
local_bh_disable();
dst = dst_cache_get(&rlwt->cache);
+ local_bh_enable();
+
+ err = rpl_do_srh(skb, rlwt, dst);
+ if (unlikely(err)) {
+ dst_release(dst);
+ goto drop;
+ }
if (!dst) {
ip6_route_input(skb);
dst = skb_dst(skb);
- if (!dst->error) {
+
+ /* cache only if we don't create a dst reference loop */
+ if (!dst->error && lwtst != dst->lwtstate) {
+ local_bh_disable();
dst_cache_set_ip6(&rlwt->cache, dst,
&ipv6_hdr(skb)->saddr);
+ local_bh_enable();
}
+
+ err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+ if (unlikely(err))
+ goto drop;
} else {
skb_dst_drop(skb);
skb_dst_set(skb, dst);
}
- local_bh_enable();
-
- err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
- if (unlikely(err))
- goto drop;
return dst_input(skb);
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index bbf5b84a70fc..5d21a74c1165 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -35,6 +35,7 @@
#include <net/xfrm.h>
#include <crypto/hash.h>
+#include <crypto/utils.h>
#include <net/seg6.h>
#include <net/genetlink.h>
#include <net/seg6_hmac.h>
@@ -271,7 +272,7 @@ bool seg6_hmac_validate_skb(struct sk_buff *skb)
if (seg6_hmac_compute(hinfo, srh, &ipv6_hdr(skb)->saddr, hmac_output))
return false;
- if (memcmp(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN) != 0)
+ if (crypto_memneq(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN))
return false;
return true;
@@ -295,6 +296,9 @@ int seg6_hmac_info_add(struct net *net, u32 key, struct seg6_hmac_info *hinfo)
struct seg6_pernet_data *sdata = seg6_pernet(net);
int err;
+ if (!__hmac_get_algo(hinfo->alg_id))
+ return -EINVAL;
+
err = rhashtable_lookup_insert_fast(&sdata->hmac_infos, &hinfo->node,
rht_params);
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 098632adc9b5..51583461ae29 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -124,8 +124,8 @@ static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb,
return flowlabel;
}
-/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
-int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
+static int __seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh,
+ int proto, struct dst_entry *cache_dst)
{
struct dst_entry *dst = skb_dst(skb);
struct net *net = dev_net(dst->dev);
@@ -137,7 +137,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
hdrlen = (osrh->hdrlen + 1) << 3;
tot_len = hdrlen + sizeof(*hdr);
- err = skb_cow_head(skb, tot_len + skb->mac_len);
+ err = skb_cow_head(skb, tot_len + dst_dev_overhead(cache_dst, skb));
if (unlikely(err))
return err;
@@ -197,11 +197,18 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
return 0;
}
+
+/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
+int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
+{
+ return __seg6_do_srh_encap(skb, osrh, proto, NULL);
+}
EXPORT_SYMBOL_GPL(seg6_do_srh_encap);
/* encapsulate an IPv6 packet within an outer IPv6 header with reduced SRH */
static int seg6_do_srh_encap_red(struct sk_buff *skb,
- struct ipv6_sr_hdr *osrh, int proto)
+ struct ipv6_sr_hdr *osrh, int proto,
+ struct dst_entry *cache_dst)
{
__u8 first_seg = osrh->first_segment;
struct dst_entry *dst = skb_dst(skb);
@@ -230,7 +237,7 @@ static int seg6_do_srh_encap_red(struct sk_buff *skb,
tot_len = red_hdrlen + sizeof(struct ipv6hdr);
- err = skb_cow_head(skb, tot_len + skb->mac_len);
+ err = skb_cow_head(skb, tot_len + dst_dev_overhead(cache_dst, skb));
if (unlikely(err))
return err;
@@ -317,8 +324,8 @@ out:
return 0;
}
-/* insert an SRH within an IPv6 packet, just after the IPv6 header */
-int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
+static int __seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh,
+ struct dst_entry *cache_dst)
{
struct ipv6hdr *hdr, *oldhdr;
struct ipv6_sr_hdr *isrh;
@@ -326,7 +333,7 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
hdrlen = (osrh->hdrlen + 1) << 3;
- err = skb_cow_head(skb, hdrlen + skb->mac_len);
+ err = skb_cow_head(skb, hdrlen + dst_dev_overhead(cache_dst, skb));
if (unlikely(err))
return err;
@@ -369,9 +376,8 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
return 0;
}
-EXPORT_SYMBOL_GPL(seg6_do_srh_inline);
-static int seg6_do_srh(struct sk_buff *skb)
+static int seg6_do_srh(struct sk_buff *skb, struct dst_entry *cache_dst)
{
struct dst_entry *dst = skb_dst(skb);
struct seg6_iptunnel_encap *tinfo;
@@ -384,7 +390,7 @@ static int seg6_do_srh(struct sk_buff *skb)
if (skb->protocol != htons(ETH_P_IPV6))
return -EINVAL;
- err = seg6_do_srh_inline(skb, tinfo->srh);
+ err = __seg6_do_srh_inline(skb, tinfo->srh, cache_dst);
if (err)
return err;
break;
@@ -402,9 +408,11 @@ static int seg6_do_srh(struct sk_buff *skb)
return -EINVAL;
if (tinfo->mode == SEG6_IPTUN_MODE_ENCAP)
- err = seg6_do_srh_encap(skb, tinfo->srh, proto);
+ err = __seg6_do_srh_encap(skb, tinfo->srh,
+ proto, cache_dst);
else
- err = seg6_do_srh_encap_red(skb, tinfo->srh, proto);
+ err = seg6_do_srh_encap_red(skb, tinfo->srh,
+ proto, cache_dst);
if (err)
return err;
@@ -425,11 +433,13 @@ static int seg6_do_srh(struct sk_buff *skb)
skb_push(skb, skb->mac_len);
if (tinfo->mode == SEG6_IPTUN_MODE_L2ENCAP)
- err = seg6_do_srh_encap(skb, tinfo->srh,
- IPPROTO_ETHERNET);
+ err = __seg6_do_srh_encap(skb, tinfo->srh,
+ IPPROTO_ETHERNET,
+ cache_dst);
else
err = seg6_do_srh_encap_red(skb, tinfo->srh,
- IPPROTO_ETHERNET);
+ IPPROTO_ETHERNET,
+ cache_dst);
if (err)
return err;
@@ -444,6 +454,13 @@ static int seg6_do_srh(struct sk_buff *skb)
return 0;
}
+/* insert an SRH within an IPv6 packet, just after the IPv6 header */
+int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
+{
+ return __seg6_do_srh_inline(skb, osrh, NULL);
+}
+EXPORT_SYMBOL_GPL(seg6_do_srh_inline);
+
static int seg6_input_finish(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
@@ -455,34 +472,48 @@ static int seg6_input_core(struct net *net, struct sock *sk,
{
struct dst_entry *orig_dst = skb_dst(skb);
struct dst_entry *dst = NULL;
+ struct lwtunnel_state *lwtst;
struct seg6_lwt *slwt;
int err;
- err = seg6_do_srh(skb);
- if (unlikely(err))
- goto drop;
+ /* We cannot dereference "orig_dst" once ip6_route_input() or
+ * skb_dst_drop() is called. However, in order to detect a dst loop, we
+ * need the address of its lwtstate. So, save the address of lwtstate
+ * now and use it later as a comparison.
+ */
+ lwtst = orig_dst->lwtstate;
- slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
+ slwt = seg6_lwt_lwtunnel(lwtst);
local_bh_disable();
dst = dst_cache_get(&slwt->cache);
+ local_bh_enable();
+
+ err = seg6_do_srh(skb, dst);
+ if (unlikely(err)) {
+ dst_release(dst);
+ goto drop;
+ }
if (!dst) {
ip6_route_input(skb);
dst = skb_dst(skb);
- if (!dst->error) {
+
+ /* cache only if we don't create a dst reference loop */
+ if (!dst->error && lwtst != dst->lwtstate) {
+ local_bh_disable();
dst_cache_set_ip6(&slwt->cache, dst,
&ipv6_hdr(skb)->saddr);
+ local_bh_enable();
}
+
+ err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+ if (unlikely(err))
+ goto drop;
} else {
skb_dst_drop(skb);
skb_dst_set(skb, dst);
}
- local_bh_enable();
-
- err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
- if (unlikely(err))
- goto drop;
if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
@@ -528,16 +559,16 @@ static int seg6_output_core(struct net *net, struct sock *sk,
struct seg6_lwt *slwt;
int err;
- err = seg6_do_srh(skb);
- if (unlikely(err))
- goto drop;
-
slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
local_bh_disable();
dst = dst_cache_get(&slwt->cache);
local_bh_enable();
+ err = seg6_do_srh(skb, dst);
+ if (unlikely(err))
+ goto drop;
+
if (unlikely(!dst)) {
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct flowi6 fl6;
@@ -552,28 +583,31 @@ static int seg6_output_core(struct net *net, struct sock *sk,
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
err = dst->error;
- dst_release(dst);
goto drop;
}
- local_bh_disable();
- dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
- local_bh_enable();
+ /* cache only if we don't create a dst reference loop */
+ if (orig_dst->lwtstate != dst->lwtstate) {
+ local_bh_disable();
+ dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
+ local_bh_enable();
+ }
+
+ err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+ if (unlikely(err))
+ goto drop;
}
skb_dst_drop(skb);
skb_dst_set(skb, dst);
- err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
- if (unlikely(err))
- goto drop;
-
if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb,
NULL, skb_dst(skb)->dev, dst_output);
return dst_output(net, sk, skb);
drop:
+ dst_release(dst);
kfree_skb(skb);
return err;
}
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index c74705ead984..e445a0a45568 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -1644,10 +1644,8 @@ static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = {
[SEG6_LOCAL_SRH] = { .type = NLA_BINARY },
[SEG6_LOCAL_TABLE] = { .type = NLA_U32 },
[SEG6_LOCAL_VRFTABLE] = { .type = NLA_U32 },
- [SEG6_LOCAL_NH4] = { .type = NLA_BINARY,
- .len = sizeof(struct in_addr) },
- [SEG6_LOCAL_NH6] = { .type = NLA_BINARY,
- .len = sizeof(struct in6_addr) },
+ [SEG6_LOCAL_NH4] = NLA_POLICY_EXACT_LEN(sizeof(struct in_addr)),
+ [SEG6_LOCAL_NH6] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
[SEG6_LOCAL_IIF] = { .type = NLA_U32 },
[SEG6_LOCAL_OIF] = { .type = NLA_U32 },
[SEG6_LOCAL_BPF] = { .type = NLA_NESTED },
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 39bd8951bfca..3c15a0ae228e 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -269,6 +269,7 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
nt = netdev_priv(dev);
+ nt->net = net;
nt->parms = *parms;
if (ipip6_tunnel_create(dev) < 0)
goto failed_free;
@@ -1449,7 +1450,6 @@ static int ipip6_tunnel_init(struct net_device *dev)
int err;
tunnel->dev = dev;
- tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
ipip6_tunnel_bind_dev(dev);
@@ -1563,6 +1563,7 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
int err;
nt = netdev_priv(dev);
+ nt->net = net;
if (ip_tunnel_netlink_encap_parms(data, &ipencap)) {
err = ip_tunnel_encap_setup(nt, &ipencap);
@@ -1858,6 +1859,9 @@ static int __net_init sit_init_net(struct net *net)
*/
sitn->fb_tunnel_dev->netns_local = true;
+ t = netdev_priv(sitn->fb_tunnel_dev);
+ t->net = net;
+
err = register_netdev(sitn->fb_tunnel_dev);
if (err)
goto err_reg_dev;
@@ -1865,8 +1869,6 @@ static int __net_init sit_init_net(struct net *net)
ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
- t = netdev_priv(sitn->fb_tunnel_dev);
-
strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
return 0;
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index a45bf17cb2a1..5ab509a5fbdf 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -42,7 +42,7 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
iif, sdif);
NAPI_GRO_CB(skb)->is_flist = !sk;
if (sk)
- sock_put(sk);
+ sock_gen_put(sk);
#endif /* IS_ENABLED(CONFIG_IPV6) */
}
@@ -94,14 +94,23 @@ INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
}
static void __tcpv6_gso_segment_csum(struct sk_buff *seg,
+ struct in6_addr *oldip,
+ const struct in6_addr *newip,
__be16 *oldport, __be16 newport)
{
- struct tcphdr *th;
+ struct tcphdr *th = tcp_hdr(seg);
+
+ if (!ipv6_addr_equal(oldip, newip)) {
+ inet_proto_csum_replace16(&th->check, seg,
+ oldip->s6_addr32,
+ newip->s6_addr32,
+ true);
+ *oldip = *newip;
+ }
if (*oldport == newport)
return;
- th = tcp_hdr(seg);
inet_proto_csum_replace2(&th->check, seg, *oldport, newport, false);
*oldport = newport;
}
@@ -129,10 +138,10 @@ static struct sk_buff *__tcpv6_gso_segment_list_csum(struct sk_buff *segs)
th2 = tcp_hdr(seg);
iph2 = ipv6_hdr(seg);
- iph2->saddr = iph->saddr;
- iph2->daddr = iph->daddr;
- __tcpv6_gso_segment_csum(seg, &th2->source, th->source);
- __tcpv6_gso_segment_csum(seg, &th2->dest, th->dest);
+ __tcpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr,
+ &th2->source, th->source);
+ __tcpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr,
+ &th2->dest, th->dest);
}
return segs;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 0cef8ae5d1ea..57e38e5e4be9 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -159,6 +159,49 @@ static int compute_score(struct sock *sk, const struct net *net,
return score;
}
+/**
+ * udp6_lib_lookup1() - Simplified lookup using primary hash (destination port)
+ * @net: Network namespace
+ * @saddr: Source address, network order
+ * @sport: Source port, network order
+ * @daddr: Destination address, network order
+ * @hnum: Destination port, host order
+ * @dif: Destination interface index
+ * @sdif: Destination bridge port index, if relevant
+ * @udptable: Set of UDP hash tables
+ *
+ * Simplified lookup to be used as fallback if no sockets are found due to a
+ * potential race between (receive) address change, and lookup happening before
+ * the rehash operation. This function ignores SO_REUSEPORT groups while scoring
+ * result sockets, because if we have one, we don't need the fallback at all.
+ *
+ * Called under rcu_read_lock().
+ *
+ * Return: socket with highest matching score if any, NULL if none
+ */
+static struct sock *udp6_lib_lookup1(const struct net *net,
+ const struct in6_addr *saddr, __be16 sport,
+ const struct in6_addr *daddr,
+ unsigned int hnum, int dif, int sdif,
+ const struct udp_table *udptable)
+{
+ unsigned int slot = udp_hashfn(net, hnum, udptable->mask);
+ struct udp_hslot *hslot = &udptable->hash[slot];
+ struct sock *sk, *result = NULL;
+ int score, badness = 0;
+
+ sk_for_each_rcu(sk, &hslot->head) {
+ score = compute_score(sk, net,
+ saddr, sport, daddr, hnum, dif, sdif);
+ if (score > badness) {
+ result = sk;
+ badness = score;
+ }
+ }
+
+ return result;
+}
+
/* called with rcu_read_lock() */
static struct sock *udp6_lib_lookup2(const struct net *net,
const struct in6_addr *saddr, __be16 sport,
@@ -263,6 +306,13 @@ struct sock *__udp6_lib_lookup(const struct net *net,
result = udp6_lib_lookup2(net, saddr, sport,
&in6addr_any, hnum, dif, sdif,
hslot2, skb);
+ if (!IS_ERR_OR_NULL(result))
+ goto done;
+
+ /* Cover address change/lookup/rehash race: see __udp4_lib_lookup() */
+ result = udp6_lib_lookup1(net, saddr, sport, daddr, hnum, dif, sdif,
+ udptable);
+
done:
if (IS_ERR(result))
return NULL;
@@ -1244,9 +1294,9 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
const int hlen = skb_network_header_len(skb) +
sizeof(struct udphdr);
- if (hlen + cork->gso_size > cork->fragsize) {
+ if (hlen + min(datalen, cork->gso_size) > cork->fragsize) {
kfree_skb(skb);
- return -EINVAL;
+ return -EMSGSIZE;
}
if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
kfree_skb(skb);
@@ -1349,7 +1399,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
int is_udplite = IS_UDPLITE(sk);
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
- ipcm6_init(&ipc6);
+ ipcm6_init_sk(&ipc6, sk);
ipc6.gso_size = READ_ONCE(up->gso_size);
ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
@@ -1558,9 +1608,6 @@ do_udp_sendmsg:
security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
- if (ipc6.tclass < 0)
- ipc6.tclass = np->tclass;
-
fl6->flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6->flowlabel);
dst = ip6_sk_dst_lookup_flow(sk, fl6, final_p, connected);
@@ -1606,8 +1653,6 @@ back_from_confirm:
WRITE_ONCE(up->pending, AF_INET6);
do_append_data:
- if (ipc6.dontfrag < 0)
- ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk);
up->len += ulen;
err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr),
&ipc6, fl6, dst_rt6_info(dst),
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 4abc5e9d6322..9005fc156a20 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -179,14 +179,18 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
int offset = skb_gro_offset(skb);
const struct net_offload *ops;
struct sk_buff *pp = NULL;
- int ret;
+ int len, dlen;
+ __u8 *udpdata;
+ __be32 *udpdata32;
if (skb->protocol == htons(ETH_P_IP))
return xfrm4_gro_udp_encap_rcv(sk, head, skb);
- offset = offset - sizeof(struct udphdr);
-
- if (!pskb_pull(skb, offset))
+ len = skb->len - offset;
+ dlen = offset + min(len, 8);
+ udpdata = skb_gro_header(skb, dlen, offset);
+ udpdata32 = (__be32 *)udpdata;
+ if (unlikely(!udpdata))
return NULL;
rcu_read_lock();
@@ -194,11 +198,13 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
if (!ops || !ops->callbacks.gro_receive)
goto out;
- ret = __xfrm6_udp_encap_rcv(sk, skb, false);
- if (ret)
+ /* check if it is a keepalive or IKE packet */
+ if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0)
goto out;
- skb_push(skb, offset);
+ /* set the transport header to ESP */
+ skb_set_transport_header(skb, offset);
+
NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
@@ -208,7 +214,6 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
out:
rcu_read_unlock();
- skb_push(skb, offset);
NAPI_GRO_CB(skb)->same_flow = 0;
NAPI_GRO_CB(skb)->flush = 1;