summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c61
-rw-r--r--net/ipv6/af_inet6.c9
-rw-r--r--net/ipv6/datagram.c10
-rw-r--r--net/ipv6/esp6.c6
-rw-r--r--net/ipv6/exthdrs.c44
-rw-r--r--net/ipv6/icmp.c33
-rw-r--r--net/ipv6/inet6_hashtables.c11
-rw-r--r--net/ipv6/ip6_gre.c49
-rw-r--r--net/ipv6/ip6_input.c64
-rw-r--r--net/ipv6/ip6_offload.c56
-rw-r--r--net/ipv6/ip6_output.c62
-rw-r--r--net/ipv6/ip6_tunnel.c2
-rw-r--r--net/ipv6/mcast.c14
-rw-r--r--net/ipv6/ndisc.c30
-rw-r--r--net/ipv6/netfilter.c3
-rw-r--r--net/ipv6/netfilter/nf_reject_ipv6.c4
-rw-r--r--net/ipv6/netfilter/nft_fib_ipv6.c4
-rw-r--r--net/ipv6/ping.c14
-rw-r--r--net/ipv6/raw.c6
-rw-r--r--net/ipv6/route.c17
-rw-r--r--net/ipv6/seg6_hmac.c2
-rw-r--r--net/ipv6/seg6_iptunnel.c5
-rw-r--r--net/ipv6/seg6_local.c3
-rw-r--r--net/ipv6/sit.c8
-rw-r--r--net/ipv6/syncookies.c3
-rw-r--r--net/ipv6/sysctl_net_ipv6.c6
-rw-r--r--net/ipv6/tcp_ipv6.c19
-rw-r--r--net/ipv6/udp.c32
-rw-r--r--net/ipv6/udp_impl.h4
29 files changed, 364 insertions, 217 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index b22504176588..49cc6587dd77 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -335,7 +335,7 @@ static int snmp6_alloc_dev(struct inet6_dev *idev)
{
int i;
- idev->stats.ipv6 = alloc_percpu(struct ipstats_mib);
+ idev->stats.ipv6 = alloc_percpu_gfp(struct ipstats_mib, GFP_KERNEL_ACCOUNT);
if (!idev->stats.ipv6)
goto err_ip;
@@ -351,7 +351,7 @@ static int snmp6_alloc_dev(struct inet6_dev *idev)
if (!idev->stats.icmpv6dev)
goto err_icmp;
idev->stats.icmpv6msgdev = kzalloc(sizeof(struct icmpv6msg_mib_device),
- GFP_KERNEL);
+ GFP_KERNEL_ACCOUNT);
if (!idev->stats.icmpv6msgdev)
goto err_icmpmsg;
@@ -375,7 +375,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
if (dev->mtu < IPV6_MIN_MTU && dev != blackhole_netdev)
return ERR_PTR(-EINVAL);
- ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL);
+ ndev = kzalloc(sizeof(*ndev), GFP_KERNEL_ACCOUNT);
if (!ndev)
return ERR_PTR(err);
@@ -797,6 +797,7 @@ static void dev_forward_change(struct inet6_dev *idev)
{
struct net_device *dev;
struct inet6_ifaddr *ifa;
+ LIST_HEAD(tmp_addr_list);
if (!idev)
return;
@@ -815,14 +816,24 @@ static void dev_forward_change(struct inet6_dev *idev)
}
}
+ read_lock_bh(&idev->lock);
list_for_each_entry(ifa, &idev->addr_list, if_list) {
if (ifa->flags&IFA_F_TENTATIVE)
continue;
+ list_add_tail(&ifa->if_list_aux, &tmp_addr_list);
+ }
+ read_unlock_bh(&idev->lock);
+
+ while (!list_empty(&tmp_addr_list)) {
+ ifa = list_first_entry(&tmp_addr_list,
+ struct inet6_ifaddr, if_list_aux);
+ list_del(&ifa->if_list_aux);
if (idev->cnf.forwarding)
addrconf_join_anycast(ifa);
else
addrconf_leave_anycast(ifa);
}
+
inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
NETCONFA_FORWARDING,
dev->ifindex, &idev->cnf);
@@ -1098,10 +1109,6 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
goto out;
}
- if (net->ipv6.devconf_all->disable_policy ||
- idev->cnf.disable_policy)
- f6i->dst_nopolicy = true;
-
neigh_parms_data_state_setall(idev->nd_parms);
ifa->addr = *cfg->pfx;
@@ -3728,7 +3735,8 @@ static int addrconf_ifdown(struct net_device *dev, bool unregister)
unsigned long event = unregister ? NETDEV_UNREGISTER : NETDEV_DOWN;
struct net *net = dev_net(dev);
struct inet6_dev *idev;
- struct inet6_ifaddr *ifa, *tmp;
+ struct inet6_ifaddr *ifa;
+ LIST_HEAD(tmp_addr_list);
bool keep_addr = false;
bool was_ready;
int state, i;
@@ -3820,16 +3828,23 @@ restart:
write_lock_bh(&idev->lock);
}
- list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
+ list_for_each_entry(ifa, &idev->addr_list, if_list)
+ list_add_tail(&ifa->if_list_aux, &tmp_addr_list);
+ write_unlock_bh(&idev->lock);
+
+ while (!list_empty(&tmp_addr_list)) {
struct fib6_info *rt = NULL;
bool keep;
+ ifa = list_first_entry(&tmp_addr_list,
+ struct inet6_ifaddr, if_list_aux);
+ list_del(&ifa->if_list_aux);
+
addrconf_del_dad_work(ifa);
keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
!addr_is_local(&ifa->addr);
- write_unlock_bh(&idev->lock);
spin_lock_bh(&ifa->lock);
if (keep) {
@@ -3860,15 +3875,14 @@ restart:
addrconf_leave_solict(ifa->idev, &ifa->addr);
}
- write_lock_bh(&idev->lock);
if (!keep) {
+ write_lock_bh(&idev->lock);
list_del_rcu(&ifa->if_list);
+ write_unlock_bh(&idev->lock);
in6_ifa_put(ifa);
}
}
- write_unlock_bh(&idev->lock);
-
/* Step 5: Discard anycast and multicast list */
if (unregister) {
ipv6_ac_destroy_dev(idev);
@@ -3972,8 +3986,6 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
addrconf_join_solict(dev, &ifp->addr);
- prandom_seed((__force u32) ifp->addr.s6_addr32[3]);
-
read_lock_bh(&idev->lock);
spin_lock(&ifp->lock);
if (ifp->state == INET6_IFADDR_STATE_DEAD)
@@ -4201,7 +4213,8 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
send_rs = send_mld &&
ipv6_accept_ra(ifp->idev) &&
ifp->idev->cnf.rtr_solicits != 0 &&
- (dev->flags&IFF_LOOPBACK) == 0;
+ (dev->flags & IFF_LOOPBACK) == 0 &&
+ (dev->type != ARPHRD_TUNNEL);
read_unlock_bh(&ifp->idev->lock);
/* While dad is in progress mld report's source address is in6_addrany.
@@ -5155,9 +5168,9 @@ next:
fillargs->event = RTM_GETMULTICAST;
/* multicast address */
- for (ifmca = rcu_dereference(idev->mc_list);
+ for (ifmca = rtnl_dereference(idev->mc_list);
ifmca;
- ifmca = rcu_dereference(ifmca->next), ip_idx++) {
+ ifmca = rtnl_dereference(ifmca->next), ip_idx++) {
if (ip_idx < s_ip_idx)
continue;
err = inet6_fill_ifmcaddr(skb, ifmca, fillargs);
@@ -5569,6 +5582,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_IOAM6_ID] = cnf->ioam6_id;
array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide;
array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier;
+ array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na;
}
static inline size_t inet6_ifla6_size(void)
@@ -7020,6 +7034,15 @@ static const struct ctl_table addrconf_sysctl[] = {
.extra2 = (void *)SYSCTL_ONE,
},
{
+ .procname = "accept_untracked_na",
+ .data = &ipv6_devconf.accept_untracked_na,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (void *)SYSCTL_ZERO,
+ .extra2 = (void *)SYSCTL_ONE,
+ },
+ {
/* sentinel */
}
};
@@ -7031,7 +7054,7 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name,
struct ctl_table *table;
char path[sizeof("net/ipv6/conf/") + IFNAMSIZ];
- table = kmemdup(addrconf_sysctl, sizeof(addrconf_sysctl), GFP_KERNEL);
+ table = kmemdup(addrconf_sysctl, sizeof(addrconf_sysctl), GFP_KERNEL_ACCOUNT);
if (!table)
goto out;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 7d7b7523d126..6f354f8be2c5 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -226,7 +226,7 @@ lookup_protocol:
RCU_INIT_POINTER(inet->mc_list, NULL);
inet->rcv_tos = 0;
- if (net->ipv4.sysctl_ip_no_pmtu_disc)
+ if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc))
inet->pmtudisc = IP_PMTUDISC_DONT;
else
inet->pmtudisc = IP_PMTUDISC_WANT;
@@ -318,7 +318,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
/* Binding to v4-mapped address on a v6-only socket
* makes no sense
*/
- if (sk->sk_ipv6only) {
+ if (ipv6_only_sock(sk)) {
err = -EINVAL;
goto out;
}
@@ -654,7 +654,7 @@ int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
}
INDIRECT_CALLABLE_DECLARE(int udpv6_recvmsg(struct sock *, struct msghdr *,
- size_t, int, int, int *));
+ size_t, int, int *));
int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags)
{
@@ -669,8 +669,7 @@ int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
/* IPV6_ADDRFORM can change sk->sk_prot under us. */
prot = READ_ONCE(sk->sk_prot);
err = INDIRECT_CALL_2(prot->recvmsg, tcp_recvmsg, udpv6_recvmsg,
- sk, msg, size, flags & MSG_DONTWAIT,
- flags & ~MSG_DONTWAIT, &addr_len);
+ sk, msg, size, flags, &addr_len);
if (err >= 0)
msg->msg_namelen = addr_len;
return err;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 206f66310a88..df665d4e8f0f 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -145,7 +145,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
int err;
if (usin->sin6_family == AF_INET) {
- if (__ipv6_only_sock(sk))
+ if (ipv6_only_sock(sk))
return -EAFNOSUPPORT;
err = __ip4_datagram_connect(sk, uaddr, addr_len);
goto ipv4_connected;
@@ -178,7 +178,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
if (addr_type & IPV6_ADDR_MAPPED) {
struct sockaddr_in sin;
- if (__ipv6_only_sock(sk)) {
+ if (ipv6_only_sock(sk)) {
err = -ENETUNREACH;
goto out;
}
@@ -218,11 +218,11 @@ ipv4_connected:
err = -EINVAL;
goto out;
}
- sk->sk_bound_dev_if = usin->sin6_scope_id;
+ WRITE_ONCE(sk->sk_bound_dev_if, usin->sin6_scope_id);
}
if (!sk->sk_bound_dev_if && (addr_type & IPV6_ADDR_MULTICAST))
- sk->sk_bound_dev_if = np->mcast_oif;
+ WRITE_ONCE(sk->sk_bound_dev_if, np->mcast_oif);
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if) {
@@ -798,7 +798,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
if (src_idx) {
if (fl6->flowi6_oif &&
src_idx != fl6->flowi6_oif &&
- (sk->sk_bound_dev_if != fl6->flowi6_oif ||
+ (READ_ONCE(sk->sk_bound_dev_if) != fl6->flowi6_oif ||
!sk_dev_equal_l3scope(sk, src_idx)))
return -EINVAL;
fl6->flowi6_oif = src_idx;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index f2120e92caf1..36e1d0f8dd06 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -741,7 +741,6 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
static inline int esp_remove_trailer(struct sk_buff *skb)
{
struct xfrm_state *x = xfrm_input_state(skb);
- struct xfrm_offload *xo = xfrm_offload(skb);
struct crypto_aead *aead = x->data;
int alen, hlen, elen;
int padlen, trimlen;
@@ -753,11 +752,6 @@ static inline int esp_remove_trailer(struct sk_buff *skb)
hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead);
elen = skb->len - hlen;
- if (xo && (xo->flags & XFRM_ESP_NO_TRAILER)) {
- ret = xo->proto;
- goto out;
- }
-
ret = skb_copy_bits(skb, skb->len - alen - 2, nexthdr, 2);
BUG_ON(ret);
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 658d5eabaf7e..a8d961d3a477 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -90,12 +90,13 @@ static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff,
break;
fallthrough;
case 2: /* send ICMP PARM PROB regardless and drop packet */
- icmpv6_param_prob(skb, ICMPV6_UNK_OPTION, optoff);
+ icmpv6_param_prob_reason(skb, ICMPV6_UNK_OPTION, optoff,
+ SKB_DROP_REASON_UNHANDLED_PROTO);
return false;
}
drop:
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO);
return false;
}
@@ -218,7 +219,7 @@ static bool ip6_parse_tlv(bool hopbyhop,
if (len == 0)
return true;
bad:
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR);
return false;
}
@@ -232,6 +233,7 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
struct ipv6_destopt_hao *hao;
struct inet6_skb_parm *opt = IP6CB(skb);
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ SKB_DR(reason);
int ret;
if (opt->dsthao) {
@@ -246,19 +248,23 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
if (hao->length != 16) {
net_dbg_ratelimited("hao invalid option length = %d\n",
hao->length);
+ SKB_DR_SET(reason, IP_INHDR);
goto discard;
}
if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) {
net_dbg_ratelimited("hao is not an unicast addr: %pI6\n",
&hao->addr);
+ SKB_DR_SET(reason, INVALID_PROTO);
goto discard;
}
ret = xfrm6_input_addr(skb, (xfrm_address_t *)&ipv6h->daddr,
(xfrm_address_t *)&hao->addr, IPPROTO_DSTOPTS);
- if (unlikely(ret < 0))
+ if (unlikely(ret < 0)) {
+ SKB_DR_SET(reason, XFRM_POLICY);
goto discard;
+ }
if (skb_cloned(skb)) {
if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
@@ -281,7 +287,7 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
return true;
discard:
- kfree_skb(skb);
+ kfree_skb_reason(skb, reason);
return false;
}
#endif
@@ -487,7 +493,6 @@ static int ipv6_rpl_srh_rcv(struct sk_buff *skb)
struct net *net = dev_net(skb->dev);
struct inet6_dev *idev;
struct ipv6hdr *oldhdr;
- struct in6_addr addr;
unsigned char *buf;
int accept_rpl_seg;
int i, err;
@@ -616,9 +621,7 @@ looped_back:
return -1;
}
- addr = ipv6_hdr(skb)->daddr;
- ipv6_hdr(skb)->daddr = ohdr->rpl_segaddr[i];
- ohdr->rpl_segaddr[i] = addr;
+ swap(ipv6_hdr(skb)->daddr, ohdr->rpl_segaddr[i]);
ipv6_rpl_srh_compress(chdr, ohdr, &ipv6_hdr(skb)->daddr, n);
@@ -934,7 +937,7 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff)
}
net_dbg_ratelimited("ipv6_hop_ra: wrong RA length %d\n",
nh[optoff + 1]);
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR);
return false;
}
@@ -988,7 +991,7 @@ ignore:
return true;
drop:
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR);
return false;
}
@@ -997,31 +1000,30 @@ drop:
static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff)
{
const unsigned char *nh = skb_network_header(skb);
- struct inet6_dev *idev = __in6_dev_get_safely(skb->dev);
- struct net *net = ipv6_skb_net(skb);
+ SKB_DR(reason);
u32 pkt_len;
if (nh[optoff + 1] != 4 || (optoff & 3) != 2) {
net_dbg_ratelimited("ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n",
nh[optoff+1]);
- __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
+ SKB_DR_SET(reason, IP_INHDR);
goto drop;
}
pkt_len = ntohl(*(__be32 *)(nh + optoff + 2));
if (pkt_len <= IPV6_MAXPLEN) {
- __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff+2);
+ icmpv6_param_prob_reason(skb, ICMPV6_HDR_FIELD, optoff + 2,
+ SKB_DROP_REASON_IP_INHDR);
return false;
}
if (ipv6_hdr(skb)->payload_len) {
- __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff);
+ icmpv6_param_prob_reason(skb, ICMPV6_HDR_FIELD, optoff,
+ SKB_DROP_REASON_IP_INHDR);
return false;
}
if (pkt_len > skb->len - sizeof(struct ipv6hdr)) {
- __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTRUNCATEDPKTS);
+ SKB_DR_SET(reason, PKT_TOO_SMALL);
goto drop;
}
@@ -1032,7 +1034,7 @@ static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff)
return true;
drop:
- kfree_skb(skb);
+ kfree_skb_reason(skb, reason);
return false;
}
@@ -1054,7 +1056,7 @@ static bool ipv6_hop_calipso(struct sk_buff *skb, int optoff)
return true;
drop:
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR);
return false;
}
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index e6b978ea0e87..9d92d51c4757 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -629,12 +629,13 @@ out_bh_enable:
}
EXPORT_SYMBOL(icmp6_send);
-/* Slightly more convenient version of icmp6_send.
+/* Slightly more convenient version of icmp6_send with drop reasons.
*/
-void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
+void icmpv6_param_prob_reason(struct sk_buff *skb, u8 code, int pos,
+ enum skb_drop_reason reason)
{
icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb));
- kfree_skb(skb);
+ kfree_skb_reason(skb, reason);
}
/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
@@ -864,21 +865,23 @@ 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_device *dev = icmp6_dev(skb);
struct inet6_dev *idev = __in6_dev_get(dev);
const struct in6_addr *saddr, *daddr;
struct icmp6hdr *hdr;
u8 type;
- bool success = false;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
struct sec_path *sp = skb_sec_path(skb);
int nh;
if (!(sp && sp->xvec[sp->len - 1]->props.flags &
- XFRM_STATE_ICMP))
+ XFRM_STATE_ICMP)) {
+ reason = SKB_DROP_REASON_XFRM_POLICY;
goto drop_no_count;
+ }
if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr)))
goto drop_no_count;
@@ -886,8 +889,11 @@ static int icmpv6_rcv(struct sk_buff *skb)
nh = skb_network_offset(skb);
skb_set_network_header(skb, sizeof(*hdr));
- if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN, skb))
+ if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN,
+ skb)) {
+ reason = SKB_DROP_REASON_XFRM_POLICY;
goto drop_no_count;
+ }
skb_set_network_header(skb, nh);
}
@@ -919,16 +925,16 @@ static int icmpv6_rcv(struct sk_buff *skb)
break;
case ICMPV6_EXT_ECHO_REQUEST:
if (!net->ipv6.sysctl.icmpv6_echo_ignore_all &&
- net->ipv4.sysctl_icmp_echo_enable_probe)
+ READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe))
icmpv6_echo_reply(skb);
break;
case ICMPV6_ECHO_REPLY:
- success = ping_rcv(skb);
+ reason = ping_rcv(skb);
break;
case ICMPV6_EXT_ECHO_REPLY:
- success = ping_rcv(skb);
+ reason = ping_rcv(skb);
break;
case ICMPV6_PKT_TOOBIG:
@@ -994,19 +1000,20 @@ static int icmpv6_rcv(struct sk_buff *skb)
/* until the v6 path can be better sorted assume failure and
* preserve the status quo behaviour for the rest of the paths to here
*/
- if (success)
- consume_skb(skb);
+ if (reason)
+ kfree_skb_reason(skb, reason);
else
- kfree_skb(skb);
+ consume_skb(skb);
return 0;
csum_error:
+ reason = SKB_DROP_REASON_ICMP_CSUM;
__ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_CSUMERRORS);
discard_it:
__ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INERRORS);
drop_no_count:
- kfree_skb(skb);
+ kfree_skb_reason(skb, reason);
return 0;
}
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 32ccac10bd62..7d53d62783b1 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -71,12 +71,12 @@ begin:
sk_nulls_for_each_rcu(sk, node, &head->chain) {
if (sk->sk_hash != hash)
continue;
- if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif, sdif))
+ if (!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))
continue;
if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
goto out;
- if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif, sdif))) {
+ if (unlikely(!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))) {
sock_gen_put(sk);
goto begin;
}
@@ -138,12 +138,11 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
const __be16 sport, const struct in6_addr *daddr,
const unsigned short hnum, const int dif, const int sdif)
{
- struct inet_connection_sock *icsk;
struct sock *sk, *result = NULL;
+ struct hlist_nulls_node *node;
int score, hiscore = 0;
- inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {
- sk = (struct sock *)icsk;
+ sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) {
score = compute_score(sk, net, hnum, daddr, dif, sdif);
if (score > hiscore) {
result = lookup_reuseport(net, sk, skb, doff,
@@ -269,7 +268,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
if (sk2->sk_hash != hash)
continue;
- if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports,
+ if (likely(inet6_match(net, sk2, saddr, daddr, ports,
dif, sdif))) {
if (sk2->sk_state == TCP_TIME_WAIT) {
tw = inet_twsk(sk2);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 5136959b3dc5..a9051df0625d 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -382,11 +382,6 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net,
goto failed_free;
ip6gre_tnl_link_config(nt, 1);
-
- /* Can use a lockless transmit, unless we generate output sequences */
- if (!(nt->parms.o_flags & TUNNEL_SEQ))
- dev->features |= NETIF_F_LLTX;
-
ip6gre_tunnel_link(ign, nt);
return nt;
@@ -944,7 +939,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
__be16 proto;
__u32 mtu;
int nhoff;
- int thoff;
if (!pskb_inet_may_pull(skb))
goto tx_err;
@@ -965,10 +959,16 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
(ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff))
truncate = true;
- thoff = skb_transport_header(skb) - skb_mac_header(skb);
- if (skb->protocol == htons(ETH_P_IPV6) &&
- (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff))
- truncate = true;
+ if (skb->protocol == htons(ETH_P_IPV6)) {
+ int thoff;
+
+ if (skb_transport_header_was_set(skb))
+ thoff = skb_transport_header(skb) - skb_mac_header(skb);
+ else
+ thoff = nhoff + sizeof(struct ipv6hdr);
+ if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)
+ truncate = true;
+ }
if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen))
goto tx_err;
@@ -1445,26 +1445,23 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
static void ip6gre_tnl_init_features(struct net_device *dev)
{
struct ip6_tnl *nt = netdev_priv(dev);
+ __be16 flags;
- dev->features |= GRE6_FEATURES;
+ dev->features |= GRE6_FEATURES | NETIF_F_LLTX;
dev->hw_features |= GRE6_FEATURES;
- if (!(nt->parms.o_flags & TUNNEL_SEQ)) {
- /* TCP offload with GRE SEQ is not supported, nor
- * can we support 2 levels of outer headers requiring
- * an update.
- */
- if (!(nt->parms.o_flags & TUNNEL_CSUM) ||
- nt->encap.type == TUNNEL_ENCAP_NONE) {
- dev->features |= NETIF_F_GSO_SOFTWARE;
- dev->hw_features |= NETIF_F_GSO_SOFTWARE;
- }
+ flags = nt->parms.o_flags;
- /* Can use a lockless transmit, unless we generate
- * output sequences
- */
- dev->features |= NETIF_F_LLTX;
- }
+ /* TCP offload with GRE SEQ is not supported, nor can we support 2
+ * levels of outer headers requiring an update.
+ */
+ if (flags & TUNNEL_SEQ)
+ return;
+ if (flags & TUNNEL_CSUM && nt->encap.type != TUNNEL_ENCAP_NONE)
+ return;
+
+ dev->features |= NETIF_F_GSO_SOFTWARE;
+ dev->hw_features |= NETIF_F_GSO_SOFTWARE;
}
static int ip6gre_tunnel_init_common(struct net_device *dev)
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 5b5ea35635f9..e1ebf5e42ebe 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -45,20 +45,23 @@
#include <net/inet_ecn.h>
#include <net/dst_metadata.h>
-INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *));
static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
- void (*edemux)(struct sk_buff *skb);
-
- if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
- const struct inet6_protocol *ipprot;
-
- ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
- if (ipprot && (edemux = READ_ONCE(ipprot->early_demux)))
- INDIRECT_CALL_2(edemux, tcp_v6_early_demux,
- udp_v6_early_demux, skb);
+ if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) &&
+ !skb_dst(skb) && !skb->sk) {
+ switch (ipv6_hdr(skb)->nexthdr) {
+ case IPPROTO_TCP:
+ if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux))
+ tcp_v6_early_demux(skb);
+ break;
+ case IPPROTO_UDP:
+ if (READ_ONCE(net->ipv4.sysctl_udp_early_demux))
+ udp_v6_early_demux(skb);
+ break;
+ }
}
+
if (!skb_valid_dst(skb))
ip6_route_input(skb);
}
@@ -145,12 +148,14 @@ static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
struct net *net)
{
+ enum skb_drop_reason reason;
const struct ipv6hdr *hdr;
u32 pkt_len;
struct inet6_dev *idev;
if (skb->pkt_type == PACKET_OTHERHOST) {
- kfree_skb(skb);
+ dev_core_stats_rx_otherhost_dropped_inc(skb->dev);
+ kfree_skb_reason(skb, SKB_DROP_REASON_OTHERHOST);
return NULL;
}
@@ -160,9 +165,12 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
__IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_IN, skb->len);
+ SKB_DR_SET(reason, NOT_SPECIFIED);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
!idev || unlikely(idev->cnf.disable_ipv6)) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
+ if (idev && unlikely(idev->cnf.disable_ipv6))
+ SKB_DR_SET(reason, IPV6DISABLED);
goto drop;
}
@@ -186,8 +194,10 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
hdr = ipv6_hdr(skb);
- if (hdr->version != 6)
+ if (hdr->version != 6) {
+ SKB_DR_SET(reason, UNHANDLED_PROTO);
goto err;
+ }
__IP6_ADD_STATS(net, idev,
IPSTATS_MIB_NOECTPKTS +
@@ -225,8 +235,10 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
if (!ipv6_addr_is_multicast(&hdr->daddr) &&
(skb->pkt_type == PACKET_BROADCAST ||
skb->pkt_type == PACKET_MULTICAST) &&
- idev->cnf.drop_unicast_in_l2_multicast)
+ idev->cnf.drop_unicast_in_l2_multicast) {
+ SKB_DR_SET(reason, UNICAST_IN_L2_MULTICAST);
goto err;
+ }
/* RFC4291 2.7
* Nodes must not originate a packet to a multicast address whose scope
@@ -255,12 +267,11 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
__IP6_INC_STATS(net,
idev, IPSTATS_MIB_INTRUNCATEDPKTS);
+ SKB_DR_SET(reason, PKT_TOO_SMALL);
goto drop;
}
- if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
- __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
- goto drop;
- }
+ if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr)))
+ goto err;
hdr = ipv6_hdr(skb);
}
@@ -281,9 +292,10 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
return skb;
err:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
+ SKB_DR_OR(reason, IP_INHDR);
drop:
rcu_read_unlock();
- kfree_skb(skb);
+ kfree_skb_reason(skb, reason);
return NULL;
}
@@ -353,6 +365,7 @@ void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
const struct inet6_protocol *ipprot;
struct inet6_dev *idev;
unsigned int nhoff;
+ SKB_DR(reason);
bool raw;
/*
@@ -412,12 +425,16 @@ resubmit_final:
if (ipv6_addr_is_multicast(&hdr->daddr) &&
!ipv6_chk_mcast_addr(dev, &hdr->daddr,
&hdr->saddr) &&
- !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
+ !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb))) {
+ SKB_DR_SET(reason, IP_INADDRERRORS);
goto discard;
+ }
}
if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
- !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
+ !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+ SKB_DR_SET(reason, XFRM_POLICY);
goto discard;
+ }
ret = INDIRECT_CALL_2(ipprot->handler, tcp_v6_rcv, udpv6_rcv,
skb);
@@ -443,8 +460,11 @@ resubmit_final:
IPSTATS_MIB_INUNKNOWNPROTOS);
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_UNK_NEXTHDR, nhoff);
+ SKB_DR_SET(reason, IP_NOPROTO);
+ } else {
+ SKB_DR_SET(reason, XFRM_POLICY);
}
- kfree_skb(skb);
+ kfree_skb_reason(skb, reason);
} else {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
consume_skb(skb);
@@ -454,7 +474,7 @@ resubmit_final:
discard:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
- kfree_skb(skb);
+ kfree_skb_reason(skb, reason);
}
static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index c4fc03c1ac99..d12dba2dd535 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -77,7 +77,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct ipv6hdr *ipv6h;
const struct net_offload *ops;
- int proto;
+ int proto, nexthdr;
struct frag_hdr *fptr;
unsigned int payload_len;
u8 *prevhdr;
@@ -87,6 +87,28 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
bool gso_partial;
skb_reset_network_header(skb);
+ nexthdr = ipv6_has_hopopt_jumbo(skb);
+ if (nexthdr) {
+ const int hophdr_len = sizeof(struct hop_jumbo_hdr);
+ int err;
+
+ err = skb_cow_head(skb, 0);
+ if (err < 0)
+ return ERR_PTR(err);
+
+ /* remove the HBH header.
+ * Layout: [Ethernet header][IPv6 header][HBH][TCP header]
+ */
+ memmove(skb_mac_header(skb) + hophdr_len,
+ skb_mac_header(skb),
+ ETH_HLEN + sizeof(struct ipv6hdr));
+ skb->data += hophdr_len;
+ skb->len -= hophdr_len;
+ skb->network_header += hophdr_len;
+ skb->mac_header += hophdr_len;
+ ipv6h = (struct ipv6hdr *)skb->data;
+ ipv6h->nexthdr = nexthdr;
+ }
nhoff = skb_network_header(skb) - skb_mac_header(skb);
if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
goto out;
@@ -320,15 +342,43 @@ static struct sk_buff *ip4ip6_gro_receive(struct list_head *head,
INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
{
const struct net_offload *ops;
- struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
+ struct ipv6hdr *iph;
int err = -ENOSYS;
+ u32 payload_len;
if (skb->encapsulation) {
skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
skb_set_inner_network_header(skb, nhoff);
}
- iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
+ payload_len = skb->len - nhoff - sizeof(*iph);
+ if (unlikely(payload_len > IPV6_MAXPLEN)) {
+ struct hop_jumbo_hdr *hop_jumbo;
+ int hoplen = sizeof(*hop_jumbo);
+
+ /* Move network header left */
+ memmove(skb_mac_header(skb) - hoplen, skb_mac_header(skb),
+ skb->transport_header - skb->mac_header);
+ skb->data -= hoplen;
+ skb->len += hoplen;
+ skb->mac_header -= hoplen;
+ skb->network_header -= hoplen;
+ iph = (struct ipv6hdr *)(skb->data + nhoff);
+ hop_jumbo = (struct hop_jumbo_hdr *)(iph + 1);
+
+ /* Build hop-by-hop options */
+ hop_jumbo->nexthdr = iph->nexthdr;
+ hop_jumbo->hdrlen = 0;
+ hop_jumbo->tlv_type = IPV6_TLV_JUMBO;
+ hop_jumbo->tlv_len = 4;
+ hop_jumbo->jumbo_payload_len = htonl(payload_len + hoplen);
+
+ iph->nexthdr = NEXTHDR_HOP;
+ iph->payload_len = 0;
+ } else {
+ iph = (struct ipv6hdr *)(skb->data + nhoff);
+ iph->payload_len = htons(payload_len);
+ }
nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops);
if (WARN_ON(!ops || !ops->callbacks.gro_complete))
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index fa63ef2bd99c..77e3f5970ce4 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -119,19 +119,21 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
rcu_read_lock_bh();
nexthop = rt6_nexthop((struct rt6_info *)dst, daddr);
neigh = __ipv6_neigh_lookup_noref(dev, nexthop);
- if (unlikely(!neigh))
- neigh = __neigh_create(&nd_tbl, nexthop, dev, false);
- if (!IS_ERR(neigh)) {
- sock_confirm_neigh(skb, neigh);
- ret = neigh_output(neigh, skb, false);
- rcu_read_unlock_bh();
- return ret;
+
+ if (unlikely(IS_ERR_OR_NULL(neigh))) {
+ if (unlikely(!neigh))
+ neigh = __neigh_create(&nd_tbl, nexthop, dev, false);
+ if (IS_ERR(neigh)) {
+ rcu_read_unlock_bh();
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES);
+ kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL);
+ return -EINVAL;
+ }
}
+ sock_confirm_neigh(skb, neigh);
+ ret = neigh_output(neigh, skb, false);
rcu_read_unlock_bh();
-
- IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES);
- kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL);
- return -EINVAL;
+ return ret;
}
static int
@@ -180,7 +182,9 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
#endif
mtu = ip6_skb_dst_mtu(skb);
- if (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))
+ if (skb_is_gso(skb) &&
+ !(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
+ !skb_gso_validate_network_len(skb, mtu))
return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
if ((skb->len > mtu && !skb_is_gso(skb)) ||
@@ -198,7 +202,6 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
switch (ret) {
case NET_XMIT_SUCCESS:
- return __ip6_finish_output(net, sk, skb);
case NET_XMIT_CN:
return __ip6_finish_output(net, sk, skb) ? : ret;
default:
@@ -251,6 +254,8 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
struct inet6_dev *idev = ip6_dst_idev(dst);
+ struct hop_jumbo_hdr *hop_jumbo;
+ int hoplen = sizeof(*hop_jumbo);
unsigned int head_room;
struct ipv6hdr *hdr;
u8 proto = fl6->flowi6_proto;
@@ -258,7 +263,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
int hlimit = -1;
u32 mtu;
- head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dev);
+ head_room = sizeof(struct ipv6hdr) + hoplen + LL_RESERVED_SPACE(dev);
if (opt)
head_room += opt->opt_nflen + opt->opt_flen;
@@ -281,6 +286,20 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
&fl6->saddr);
}
+ if (unlikely(seg_len > IPV6_MAXPLEN)) {
+ hop_jumbo = skb_push(skb, hoplen);
+
+ hop_jumbo->nexthdr = proto;
+ hop_jumbo->hdrlen = 0;
+ hop_jumbo->tlv_type = IPV6_TLV_JUMBO;
+ hop_jumbo->tlv_len = 4;
+ hop_jumbo->jumbo_payload_len = htonl(seg_len + hoplen);
+
+ proto = IPPROTO_HOPOPTS;
+ seg_len = 0;
+ IP6CB(skb)->flags |= IP6SKB_FAKEJUMBO;
+ }
+
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
hdr = ipv6_hdr(skb);
@@ -469,6 +488,7 @@ int ip6_forward(struct sk_buff *skb)
struct inet6_skb_parm *opt = IP6CB(skb);
struct net *net = dev_net(dst->dev);
struct inet6_dev *idev;
+ SKB_DR(reason);
u32 mtu;
idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
@@ -518,7 +538,7 @@ int ip6_forward(struct sk_buff *skb)
icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR);
return -ETIMEDOUT;
}
@@ -537,6 +557,7 @@ int ip6_forward(struct sk_buff *skb)
if (!xfrm6_route_forward(skb)) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
+ SKB_DR_SET(reason, XFRM_POLICY);
goto drop;
}
dst = skb_dst(skb);
@@ -596,7 +617,7 @@ int ip6_forward(struct sk_buff *skb)
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INTOOBIGERRORS);
__IP6_INC_STATS(net, ip6_dst_idev(dst),
IPSTATS_MIB_FRAGFAILS);
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG);
return -EMSGSIZE;
}
@@ -618,8 +639,9 @@ int ip6_forward(struct sk_buff *skb)
error:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS);
+ SKB_DR_SET(reason, IP_INADDRERRORS);
drop:
- kfree_skb(skb);
+ kfree_skb_reason(skb, reason);
return -EINVAL;
}
@@ -1428,7 +1450,7 @@ static int __ip6_append_data(struct sock *sk,
struct page_frag *pfrag,
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
- void *from, int length, int transhdrlen,
+ void *from, size_t length, int transhdrlen,
unsigned int flags, struct ipcm6_cookie *ipc6)
{
struct sk_buff *skb, *skb_prev = NULL;
@@ -1776,7 +1798,7 @@ error:
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, int length, int transhdrlen,
+ void *from, size_t length, int transhdrlen,
struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
struct rt6_info *rt, unsigned int flags)
{
@@ -1973,7 +1995,7 @@ EXPORT_SYMBOL_GPL(ip6_flush_pending_frames);
struct sk_buff *ip6_make_skb(struct sock *sk,
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
- void *from, int length, int transhdrlen,
+ void *from, size_t length, int transhdrlen,
struct ipcm6_cookie *ipc6, struct rt6_info *rt,
unsigned int flags, struct inet_cork_full *cork)
{
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 53f632a560ec..19325b7600bb 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -257,8 +257,6 @@ static int ip6_tnl_create2(struct net_device *dev)
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
int err;
- t = netdev_priv(dev);
-
dev->rtnl_link_ops = &ip6_link_ops;
err = register_netdevice(dev);
if (err < 0)
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 7f695c39d9a8..87c699d57b36 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1522,7 +1522,6 @@ static void mld_query_work(struct work_struct *work)
if (++cnt >= MLD_MAX_QUEUE) {
rework = true;
- schedule_delayed_work(&idev->mc_query_work, 0);
break;
}
}
@@ -1533,8 +1532,10 @@ static void mld_query_work(struct work_struct *work)
__mld_query_work(skb);
mutex_unlock(&idev->mc_lock);
- if (!rework)
- in6_dev_put(idev);
+ if (rework && queue_delayed_work(mld_wq, &idev->mc_query_work, 0))
+ return;
+
+ in6_dev_put(idev);
}
/* called with rcu_read_lock() */
@@ -1624,7 +1625,6 @@ static void mld_report_work(struct work_struct *work)
if (++cnt >= MLD_MAX_QUEUE) {
rework = true;
- schedule_delayed_work(&idev->mc_report_work, 0);
break;
}
}
@@ -1635,8 +1635,10 @@ static void mld_report_work(struct work_struct *work)
__mld_report_work(skb);
mutex_unlock(&idev->mc_lock);
- if (!rework)
- in6_dev_put(idev);
+ if (rework && queue_delayed_work(mld_wq, &idev->mc_report_work, 0))
+ return;
+
+ in6_dev_put(idev);
}
static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type,
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index fcb288b0ae13..b0dfe97ea4ee 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -979,6 +979,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
struct inet6_dev *idev = __in6_dev_get(dev);
struct inet6_ifaddr *ifp;
struct neighbour *neigh;
+ u8 new_state;
if (skb->len < sizeof(struct nd_msg)) {
ND_PRINTK(2, warn, "NA: packet too short\n");
@@ -999,6 +1000,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
/* 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)
@@ -1039,9 +1041,33 @@ static void ndisc_recv_na(struct sk_buff *skb)
in6_ifa_put(ifp);
return;
}
+
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 && idev->cnf.forwarding &&
+ idev->cnf.accept_untracked_na) {
+ 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);
@@ -1061,7 +1087,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
}
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|
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 8ce60ab89015..857713d7a38a 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -31,6 +31,7 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff
int strict = (ipv6_addr_type(&iph->daddr) &
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
struct flowi6 fl6 = {
+ .flowi6_l3mdev = l3mdev_master_ifindex(dev),
.flowi6_mark = skb->mark,
.flowi6_uid = sock_net_uid(net, sk),
.daddr = iph->daddr,
@@ -42,8 +43,6 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff
fl6.flowi6_oif = sk->sk_bound_dev_if;
else if (strict)
fl6.flowi6_oif = dev->ifindex;
- else
- fl6.flowi6_oif = l3mdev_master_ifindex(dev);
fib6_rules_early_flow_dissect(net, skb, &fl6, &flkeys);
dst = ip6_route_output(net, sk, &fl6);
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index dffeaaaadcde..f61d4f18e1cf 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -31,7 +31,7 @@ static bool nf_reject_v6_csum_ok(struct sk_buff *skb, int hook)
if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0)
return false;
- if (!nf_reject_verify_csum(proto))
+ if (!nf_reject_verify_csum(skb, thoff, proto))
return true;
return nf_ip6_checksum(skb, hook, thoff, proto) == 0;
@@ -388,7 +388,7 @@ static bool reject6_csum_ok(struct sk_buff *skb, int hook)
if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0)
return false;
- if (!nf_reject_verify_csum(proto))
+ if (!nf_reject_verify_csum(skb, thoff, proto))
return true;
return nf_ip6_checksum(skb, hook, thoff, proto) == 0;
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index b3f163b40c2b..8970d0b4faeb 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -30,6 +30,10 @@ static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv,
fl6->daddr = iph->daddr;
fl6->saddr = iph->saddr;
} else {
+ if (nft_hook(pkt) == NF_INET_FORWARD &&
+ priv->flags & NFTA_FIB_F_IIF)
+ fl6->flowi6_iif = nft_out(pkt)->ifindex;
+
fl6->daddr = iph->saddr;
fl6->saddr = iph->daddr;
}
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index ff033d16549e..8c6c2d82c1cd 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -22,6 +22,11 @@
#include <linux/proc_fs.h>
#include <net/ping.h>
+static void ping_v6_destroy(struct sock *sk)
+{
+ inet6_destroy_sock(sk);
+}
+
/* Compatibility glue so we can support IPv6 when it's compiled as a module */
static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
int *addr_len)
@@ -101,6 +106,9 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipc6.sockc.tsflags = sk->sk_tsflags;
ipc6.sockc.mark = sk->sk_mark;
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_oif = oif;
+
if (msg->msg_controllen) {
struct ipv6_txoptions opt = {};
@@ -112,17 +120,14 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
return err;
/* Changes to txoptions and flow info are not implemented, yet.
- * Drop the options, fl6 is wiped below.
+ * Drop the options.
*/
ipc6.opt = NULL;
}
- memset(&fl6, 0, sizeof(fl6));
-
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.saddr = np->saddr;
fl6.daddr = *daddr;
- fl6.flowi6_oif = oif;
fl6.flowi6_mark = ipc6.sockc.mark;
fl6.flowi6_uid = sk->sk_uid;
fl6.fl6_icmp_type = user_icmph.icmp6_type;
@@ -181,6 +186,7 @@ struct proto pingv6_prot = {
.owner = THIS_MODULE,
.init = ping_init_sock,
.close = ping_close,
+ .destroy = ping_v6_destroy,
.connect = ip6_datagram_connect_v6_only,
.disconnect = __udp_disconnect,
.setsockopt = ipv6_setsockopt,
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index c51d5ce3711c..3b7cbd522b54 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -460,7 +460,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb)
*/
static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
- int noblock, int flags, int *addr_len)
+ int flags, int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
@@ -477,7 +477,7 @@ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
if (np->rxpmtu && np->rxopt.bits.rxpmtu)
return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
- skb = skb_recv_datagram(sk, flags, noblock, &err);
+ skb = skb_recv_datagram(sk, flags, &err);
if (!skb)
goto out;
@@ -512,7 +512,7 @@ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
*addr_len = sizeof(*sin6);
}
- sock_recv_ts_and_drops(msg, sk, skb);
+ sock_recv_cmsgs(msg, sk, skb);
if (np->rxopt.all)
ip6_datagram_recv_ctl(sk, msg, skb);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c4b6ce017d5e..916417944ec8 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4483,6 +4483,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
struct dst_entry *dst = skb_dst(skb);
struct net *net = dev_net(dst->dev);
struct inet6_dev *idev;
+ SKB_DR(reason);
int type;
if (netif_is_l3_master(skb->dev) ||
@@ -4495,11 +4496,14 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
case IPSTATS_MIB_INNOROUTES:
type = ipv6_addr_type(&ipv6_hdr(skb)->daddr);
if (type == IPV6_ADDR_ANY) {
+ SKB_DR_SET(reason, IP_INADDRERRORS);
IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS);
break;
}
+ SKB_DR_SET(reason, IP_INNOROUTES);
fallthrough;
case IPSTATS_MIB_OUTNOROUTES:
+ SKB_DR_OR(reason, IP_OUTNOROUTES);
IP6_INC_STATS(net, idev, ipstats_mib_noroutes);
break;
}
@@ -4509,7 +4513,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
skb_dst_drop(skb);
icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0);
- kfree_skb(skb);
+ kfree_skb_reason(skb, reason);
return 0;
}
@@ -4565,8 +4569,15 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
}
f6i = ip6_route_info_create(&cfg, gfp_flags, NULL);
- if (!IS_ERR(f6i))
+ if (!IS_ERR(f6i)) {
f6i->dst_nocount = true;
+
+ if (!anycast &&
+ (net->ipv6.devconf_all->disable_policy ||
+ idev->cnf.disable_policy))
+ f6i->dst_nopolicy = true;
+ }
+
return f6i;
}
@@ -5730,7 +5741,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
if (nexthop_is_blackhole(rt->nh))
rtm->rtm_type = RTN_BLACKHOLE;
- if (net->ipv4.sysctl_nexthop_compat_mode &&
+ if (READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode) &&
rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0)
goto nla_put_failure;
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 29bc4e7c3046..d43c50a7310d 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -399,7 +399,6 @@ int __init seg6_hmac_init(void)
{
return seg6_hmac_init_algo();
}
-EXPORT_SYMBOL(seg6_hmac_init);
int __net_init seg6_hmac_net_init(struct net *net)
{
@@ -407,7 +406,6 @@ int __net_init seg6_hmac_net_init(struct net *net)
return rhashtable_init(&sdata->hmac_infos, &rht_params);
}
-EXPORT_SYMBOL(seg6_hmac_net_init);
void seg6_hmac_exit(void)
{
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index d64855010948..e756ba705fd9 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -189,6 +189,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
}
#endif
+ hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
skb_postpush_rcsum(skb, hdr, tot_len);
return 0;
@@ -241,6 +243,8 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
}
#endif
+ hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen);
return 0;
@@ -302,7 +306,6 @@ static int seg6_do_srh(struct sk_buff *skb)
break;
}
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
nf_reset_ct(skb);
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 9fbe243a0e81..2cd4a8d3b30a 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -218,6 +218,7 @@ seg6_lookup_any_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
struct flowi6 fl6;
int dev_flags = 0;
+ memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_iif = skb->dev->ifindex;
fl6.daddr = nhaddr ? *nhaddr : hdr->daddr;
fl6.saddr = hdr->saddr;
@@ -825,7 +826,6 @@ static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt)
if (err)
goto drop;
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_nexthop(skb, NULL, 0);
@@ -857,7 +857,6 @@ static int input_action_end_b6_encap(struct sk_buff *skb,
if (err)
goto drop;
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_nexthop(skb, NULL, 0);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index c0b138c20992..6bcd5e419a08 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -323,8 +323,6 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u
kcalloc(cmax, sizeof(*kp), GFP_KERNEL_ACCOUNT | __GFP_NOWARN) :
NULL;
- rcu_read_lock();
-
ca = min(t->prl_count, cmax);
if (!kp) {
@@ -341,7 +339,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u
}
}
- c = 0;
+ rcu_read_lock();
for_each_prl_rcu(t->prl) {
if (c >= cmax)
break;
@@ -353,7 +351,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u
if (kprl.addr != htonl(INADDR_ANY))
break;
}
-out:
+
rcu_read_unlock();
len = sizeof(*kp) * c;
@@ -362,7 +360,7 @@ out:
ret = -EFAULT;
kfree(kp);
-
+out:
return ret;
}
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 9cc123f000fb..5014aa663452 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -141,7 +141,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
__u8 rcv_wscale;
u32 tsoff = 0;
- if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) ||
+ !th->ack || th->rst)
goto out;
if (tcp_synq_no_recent_overflow(sk))
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index d53dd142bf87..94a0a294c6a1 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -23,8 +23,6 @@
#endif
#include <linux/ioam6.h>
-static int two = 2;
-static int three = 3;
static int flowlabel_reflect_max = 0x7;
static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
static u32 rt6_multipath_hash_fields_all_mask =
@@ -172,7 +170,7 @@ static struct ctl_table ipv6_table_template[] = {
.mode = 0644,
.proc_handler = proc_rt6_multipath_hash_policy,
.extra1 = SYSCTL_ZERO,
- .extra2 = &three,
+ .extra2 = SYSCTL_THREE,
},
{
.procname = "fib_multipath_hash_fields",
@@ -197,7 +195,7 @@ static struct ctl_table ipv6_table_template[] = {
.mode = 0644,
.proc_handler = proc_dou8vec_minmax,
.extra1 = SYSCTL_ZERO,
- .extra2 = &two,
+ .extra2 = SYSCTL_TWO,
},
{
.procname = "ioam6_id",
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index faaddaf43c90..be09941fe6d9 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -230,7 +230,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
- if (__ipv6_only_sock(sk))
+ if (ipv6_only_sock(sk))
return -ENETUNREACH;
sin.sin_family = AF_INET;
@@ -546,7 +546,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
if (np->repflow && ireq->pktopts)
fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
- tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
(np->tclass & INET_ECN_MASK) :
np->tclass;
@@ -1314,7 +1314,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
/* Set ToS of the new socket based upon the value of incoming SYN.
* ECT bits are set later in tcp_init_transfer().
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
/* Clone native IPv6 options from listening socket (if any)
@@ -1728,7 +1728,6 @@ process:
sk_incoming_cpu_update(sk);
- sk_defer_free_flush(sk);
bh_lock_sock_nested(sk);
tcp_segs_in(tcp_sk(sk), skb);
ret = 0;
@@ -1763,6 +1762,7 @@ bad_packet:
}
discard_it:
+ SKB_DR_OR(drop_reason, NOT_SPECIFIED);
kfree_skb_reason(skb, drop_reason);
return 0;
@@ -1822,7 +1822,7 @@ do_time_wait:
goto discard_it;
}
-INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb)
+void tcp_v6_early_demux(struct sk_buff *skb)
{
const struct ipv6hdr *hdr;
const struct tcphdr *th;
@@ -2044,7 +2044,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
jiffies_to_clock_t(icsk->icsk_rto),
jiffies_to_clock_t(icsk->icsk_ack.ato),
(icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sp),
- tp->snd_cwnd,
+ tcp_snd_cwnd(tp),
state == TCP_LISTEN ?
fastopenq->max_qlen :
(tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)
@@ -2176,12 +2176,7 @@ struct proto tcpv6_prot = {
};
EXPORT_SYMBOL_GPL(tcpv6_prot);
-/* thinking of making this const? Don't.
- * early_demux can change based on sysctl.
- */
-static struct inet6_protocol tcpv6_protocol = {
- .early_demux = tcp_v6_early_demux,
- .early_demux_handler = tcp_v6_early_demux,
+static const struct inet6_protocol tcpv6_protocol = {
.handler = tcp_v6_rcv,
.err_handler = tcp_v6_err,
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 7f0fa9bd9ffe..e2f2e087a753 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -105,7 +105,7 @@ static int compute_score(struct sock *sk, struct net *net,
const struct in6_addr *daddr, unsigned short hnum,
int dif, int sdif)
{
- int score;
+ int bound_dev_if, score;
struct inet_sock *inet;
bool dev_match;
@@ -132,10 +132,11 @@ static int compute_score(struct sock *sk, struct net *net,
score++;
}
- dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif);
+ bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
+ dev_match = udp_sk_bound_dev_eq(net, bound_dev_if, dif, sdif);
if (!dev_match)
return -1;
- if (sk->sk_bound_dev_if)
+ if (bound_dev_if)
score++;
if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
@@ -322,7 +323,7 @@ static int udp6_skb_len(struct sk_buff *skb)
*/
int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
- int noblock, int flags, int *addr_len)
+ int flags, int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_sock *inet = inet_sk(sk);
@@ -342,7 +343,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
try_again:
off = sk_peek_offset(sk, flags);
- skb = __skb_recv_udp(sk, flags, noblock, &off, &err);
+ skb = __skb_recv_udp(sk, flags, &off, &err);
if (!skb)
return err;
@@ -391,7 +392,7 @@ try_again:
if (!peeking)
SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS);
- sock_recv_ts_and_drops(msg, sk, skb);
+ sock_recv_cmsgs(msg, sk, skb);
/* Copy the address. */
if (msg->msg_name) {
@@ -789,7 +790,7 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
(inet->inet_dport && inet->inet_dport != rmt_port) ||
(!ipv6_addr_any(&sk->sk_v6_daddr) &&
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
- !udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif) ||
+ !udp_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif, sdif) ||
(!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
return false;
@@ -1043,7 +1044,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net,
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
if (sk->sk_state == TCP_ESTABLISHED &&
- INET6_MATCH(sk, net, rmt_addr, loc_addr, ports, dif, sdif))
+ inet6_match(net, sk, rmt_addr, loc_addr, ports, dif, sdif))
return sk;
/* Only check first socket in chain */
break;
@@ -1051,7 +1052,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net,
return NULL;
}
-INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb)
+void udp_v6_early_demux(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
const struct udphdr *uh;
@@ -1123,7 +1124,7 @@ static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
* bytes that are out of the bound specified by user in addr_len.
*/
if (uaddr->sa_family == AF_INET) {
- if (__ipv6_only_sock(sk))
+ if (ipv6_only_sock(sk))
return -EAFNOSUPPORT;
return udp_pre_connect(sk, uaddr, addr_len);
}
@@ -1359,7 +1360,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
msg->msg_name = &sin;
msg->msg_namelen = sizeof(sin);
do_udp_sendmsg:
- if (__ipv6_only_sock(sk))
+ if (ipv6_only_sock(sk))
return -ENETUNREACH;
return udp_sendmsg(sk, msg, len);
}
@@ -1433,7 +1434,7 @@ do_udp_sendmsg:
}
if (!fl6->flowi6_oif)
- fl6->flowi6_oif = sk->sk_bound_dev_if;
+ fl6->flowi6_oif = READ_ONCE(sk->sk_bound_dev_if);
if (!fl6->flowi6_oif)
fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
@@ -1659,12 +1660,7 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname,
return ipv6_getsockopt(sk, level, optname, optval, optlen);
}
-/* thinking of making this const? Don't.
- * early_demux can change based on sysctl.
- */
-static struct inet6_protocol udpv6_protocol = {
- .early_demux = udp_v6_early_demux,
- .early_demux_handler = udp_v6_early_demux,
+static const struct inet6_protocol udpv6_protocol = {
.handler = udpv6_rcv,
.err_handler = udpv6_err,
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h
index b2fcc46c1630..4251e49d32a0 100644
--- a/net/ipv6/udp_impl.h
+++ b/net/ipv6/udp_impl.h
@@ -20,8 +20,8 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname,
int udpv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
unsigned int optlen);
int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
-int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
- int flags, int *addr_len);
+int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
+ int *addr_len);
void udpv6_destroy_sock(struct sock *sk);
#ifdef CONFIG_PROC_FS
generated by cgit v1.2.3 (git 2.25.1) at 2025-04-08 15:17:56 +0000