summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c21
-rw-r--r--net/ipv6/inet6_hashtables.c54
-rw-r--r--net/ipv6/ip6_gre.c6
-rw-r--r--net/ipv6/ip6_input.c4
-rw-r--r--net/ipv6/ip6_offload.c35
-rw-r--r--net/ipv6/ip6_output.c90
-rw-r--r--net/ipv6/ip6_udp_tunnel.c16
-rw-r--r--net/ipv6/ip6mr.c9
-rw-r--r--net/ipv6/netfilter.c3
-rw-r--r--net/ipv6/netfilter/ip6t_MASQUERADE.c8
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c8
-rw-r--r--net/ipv6/netfilter/nf_nat_masquerade_ipv6.c49
-rw-r--r--net/ipv6/netfilter/nft_masq_ipv6.c4
-rw-r--r--net/ipv6/reassembly.c8
-rw-r--r--net/ipv6/route.c14
-rw-r--r--net/ipv6/seg6_iptunnel.c1
-rw-r--r--net/ipv6/tcp_ipv6.c3
-rw-r--r--net/ipv6/tcpv6_offload.c7
-rw-r--r--net/ipv6/udp.c115
-rw-r--r--net/ipv6/udp_offload.c7
20 files changed, 242 insertions, 220 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 63a808d5af15..521e471f1cf9 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -179,7 +179,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp);
static void addrconf_dad_work(struct work_struct *w);
static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
bool send_na);
-static void addrconf_dad_run(struct inet6_dev *idev);
+static void addrconf_dad_run(struct inet6_dev *idev, bool restart);
static void addrconf_rs_timer(struct timer_list *t);
static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
@@ -2820,7 +2820,7 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg)
dev = __dev_get_by_name(net, p.name);
if (!dev)
goto err_exit;
- err = dev_open(dev);
+ err = dev_open(dev, NULL);
}
}
#endif
@@ -3439,6 +3439,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct netdev_notifier_change_info *change_info;
struct netdev_notifier_changeupper_info *info;
struct inet6_dev *idev = __in6_dev_get(dev);
struct net *net = dev_net(dev);
@@ -3513,7 +3514,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
break;
}
- if (idev) {
+ if (!IS_ERR_OR_NULL(idev)) {
if (idev->if_flags & IF_READY) {
/* device is already configured -
* but resend MLD reports, we might
@@ -3521,6 +3522,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
* multicast snooping switches
*/
ipv6_mc_up(idev);
+ change_info = ptr;
+ if (change_info->flags_changed & IFF_NOARP)
+ addrconf_dad_run(idev, true);
rt6_sync_up(dev, RTNH_F_LINKDOWN);
break;
}
@@ -3555,7 +3559,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
if (!IS_ERR_OR_NULL(idev)) {
if (run_pending)
- addrconf_dad_run(idev);
+ addrconf_dad_run(idev, false);
/* Device has an address by now */
rt6_sync_up(dev, RTNH_F_DEAD);
@@ -4173,16 +4177,19 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
addrconf_verify_rtnl();
}
-static void addrconf_dad_run(struct inet6_dev *idev)
+static void addrconf_dad_run(struct inet6_dev *idev, bool restart)
{
struct inet6_ifaddr *ifp;
read_lock_bh(&idev->lock);
list_for_each_entry(ifp, &idev->addr_list, if_list) {
spin_lock(&ifp->lock);
- if (ifp->flags & IFA_F_TENTATIVE &&
- ifp->state == INET6_IFADDR_STATE_DAD)
+ if ((ifp->flags & IFA_F_TENTATIVE &&
+ ifp->state == INET6_IFADDR_STATE_DAD) || restart) {
+ if (restart)
+ ifp->state = INET6_IFADDR_STATE_PREDAD;
addrconf_dad_kick(ifp);
+ }
spin_unlock(&ifp->lock);
}
read_unlock_bh(&idev->lock);
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 5eeeba7181a1..f3515ebe9b3a 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -99,23 +99,16 @@ static inline int compute_score(struct sock *sk, struct net *net,
const int dif, const int sdif, bool exact_dif)
{
int score = -1;
- bool dev_match;
if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
sk->sk_family == PF_INET6) {
+ if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+ return -1;
- score = 1;
- if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
- if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
- return -1;
- score++;
- }
- dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
- dif, sdif);
- if (!dev_match)
+ if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
return -1;
- score++;
+ score = 1;
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
}
@@ -164,26 +157,12 @@ struct sock *inet6_lookup_listener(struct net *net,
const __be16 sport, const struct in6_addr *daddr,
const unsigned short hnum, const int dif, const int sdif)
{
- unsigned int hash = inet_lhashfn(net, hnum);
- struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
- bool exact_dif = inet6_exact_dif_match(net, skb);
struct inet_listen_hashbucket *ilb2;
- struct sock *sk, *result = NULL;
- int score, hiscore = 0;
+ struct sock *result = NULL;
unsigned int hash2;
- u32 phash = 0;
-
- if (ilb->count <= 10 || !hashinfo->lhash2)
- goto port_lookup;
-
- /* Too many sk in the ilb bucket (which is hashed by port alone).
- * Try lhash2 (which is hashed by port and addr) instead.
- */
hash2 = ipv6_portaddr_hash(net, daddr, hnum);
ilb2 = inet_lhash2_bucket(hashinfo, hash2);
- if (ilb2->count > ilb->count)
- goto port_lookup;
result = inet6_lhash2_lookup(net, ilb2, skb, doff,
saddr, sport, daddr, hnum,
@@ -192,33 +171,12 @@ struct sock *inet6_lookup_listener(struct net *net,
goto done;
/* Lookup lhash2 with in6addr_any */
-
hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
ilb2 = inet_lhash2_bucket(hashinfo, hash2);
- if (ilb2->count > ilb->count)
- goto port_lookup;
result = inet6_lhash2_lookup(net, ilb2, skb, doff,
- saddr, sport, daddr, hnum,
+ saddr, sport, &in6addr_any, hnum,
dif, sdif);
- goto done;
-
-port_lookup:
- sk_for_each(sk, &ilb->head) {
- score = compute_score(sk, net, hnum, daddr, dif, sdif, exact_dif);
- if (score > hiscore) {
- if (sk->sk_reuseport) {
- phash = inet6_ehashfn(net, daddr, hnum,
- saddr, sport);
- result = reuseport_select_sock(sk, phash,
- skb, doff);
- if (result)
- goto done;
- }
- result = sk;
- hiscore = score;
- }
- }
done:
if (unlikely(IS_ERR(result)))
return NULL;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 81b69bcee714..229e55c99021 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1885,12 +1885,6 @@ static void ip6gre_tap_setup(struct net_device *dev)
netif_keep_dst(dev);
}
-bool is_ip6gretap_dev(const struct net_device *dev)
-{
- return dev->netdev_ops == &ip6gre_tap_netdev_ops;
-}
-EXPORT_SYMBOL_GPL(is_ip6gretap_dev);
-
static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
struct ip_tunnel_encap *ipencap)
{
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 3c06cc9e9b79..c7ed2b6d5a1d 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -95,7 +95,7 @@ static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
list_for_each_entry_safe(skb, next, head, list) {
struct dst_entry *dst;
- list_del(&skb->list);
+ skb_list_del_init(skb);
/* if ingress device is enslaved to an L3 master device pass the
* skb to its handler for processing
*/
@@ -296,7 +296,7 @@ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
struct net_device *dev = skb->dev;
struct net *net = dev_net(dev);
- list_del(&skb->list);
+ skb_list_del_init(skb);
skb = ip6_rcv_core(skb, dev, net);
if (skb == NULL)
continue;
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 70f525c33cb6..5c045691c302 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -20,6 +20,23 @@
#include "ip6_offload.h"
+/* All GRO functions are always builtin, except UDP over ipv6, which lays in
+ * ipv6 module, as it depends on UDPv6 lookup function, so we need special care
+ * when ipv6 is built as a module
+ */
+#if IS_BUILTIN(CONFIG_IPV6)
+#define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__)
+#else
+#define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__)
+#endif
+
+#define indirect_call_gro_receive_l4(f2, f1, cb, head, skb) \
+({ \
+ unlikely(gro_recursion_inc_test(skb)) ? \
+ NAPI_GRO_CB(skb)->flush |= 1, NULL : \
+ INDIRECT_CALL_L4(cb, f2, f1, head, skb); \
+})
+
static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
{
const struct net_offload *ops = NULL;
@@ -164,8 +181,12 @@ static int ipv6_exthdrs_len(struct ipv6hdr *iph,
return len;
}
-static struct sk_buff *ipv6_gro_receive(struct list_head *head,
- struct sk_buff *skb)
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *,
+ struct sk_buff *));
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *,
+ struct sk_buff *));
+INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
+ struct sk_buff *skb)
{
const struct net_offload *ops;
struct sk_buff *pp = NULL;
@@ -260,7 +281,8 @@ not_same_flow:
skb_gro_postpull_rcsum(skb, iph, nlen);
- pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
+ pp = indirect_call_gro_receive_l4(tcp6_gro_receive, udp6_gro_receive,
+ ops->callbacks.gro_receive, head, skb);
out_unlock:
rcu_read_unlock();
@@ -301,7 +323,9 @@ static struct sk_buff *ip4ip6_gro_receive(struct list_head *head,
return inet_gro_receive(head, skb);
}
-static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
+INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *, int));
+INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int));
+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);
@@ -320,7 +344,8 @@ static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
if (WARN_ON(!ops || !ops->callbacks.gro_complete))
goto out_unlock;
- err = ops->callbacks.gro_complete(skb, nhoff);
+ err = INDIRECT_CALL_L4(ops->callbacks.gro_complete, tcp6_gro_complete,
+ udp6_gro_complete, skb, nhoff);
out_unlock:
rcu_read_unlock();
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 89e0d5118afe..9d55ee33b7f9 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -195,37 +195,37 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
const struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *first_hop = &fl6->daddr;
struct dst_entry *dst = skb_dst(skb);
+ unsigned int head_room;
struct ipv6hdr *hdr;
u8 proto = fl6->flowi6_proto;
int seg_len = skb->len;
int hlimit = -1;
u32 mtu;
- if (opt) {
- unsigned int head_room;
+ head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
+ if (opt)
+ head_room += opt->opt_nflen + opt->opt_flen;
- /* First: exthdrs may take lots of space (~8K for now)
- MAX_HEADER is not enough.
- */
- head_room = opt->opt_nflen + opt->opt_flen;
- seg_len += head_room;
- head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
-
- if (skb_headroom(skb) < head_room) {
- struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
- if (!skb2) {
- IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
- IPSTATS_MIB_OUTDISCARDS);
- kfree_skb(skb);
- return -ENOBUFS;
- }
- if (skb->sk)
- skb_set_owner_w(skb2, skb->sk);
- consume_skb(skb);
- skb = skb2;
+ if (unlikely(skb_headroom(skb) < head_room)) {
+ struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
+ if (!skb2) {
+ IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_OUTDISCARDS);
+ kfree_skb(skb);
+ return -ENOBUFS;
}
+ if (skb->sk)
+ skb_set_owner_w(skb2, skb->sk);
+ consume_skb(skb);
+ skb = skb2;
+ }
+
+ if (opt) {
+ seg_len += opt->opt_nflen + opt->opt_flen;
+
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
+
if (opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop,
&fl6->saddr);
@@ -378,6 +378,13 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk,
__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
+#ifdef CONFIG_NET_SWITCHDEV
+ if (skb->offload_l3_fwd_mark) {
+ consume_skb(skb);
+ return 0;
+ }
+#endif
+
return dst_output(net, sk, skb);
}
@@ -1245,6 +1252,7 @@ static int __ip6_append_data(struct sock *sk,
{
struct sk_buff *skb, *skb_prev = NULL;
unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu;
+ struct ubuf_info *uarg = NULL;
int exthdrlen = 0;
int dst_exthdrlen = 0;
int hh_len;
@@ -1257,7 +1265,7 @@ static int __ip6_append_data(struct sock *sk,
int csummode = CHECKSUM_NONE;
unsigned int maxnonfragsize, headersize;
unsigned int wmem_alloc_delta = 0;
- bool paged;
+ bool paged, extra_uref;
skb = skb_peek_tail(queue);
if (!skb) {
@@ -1322,6 +1330,20 @@ emsgsize:
rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
csummode = CHECKSUM_PARTIAL;
+ if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) {
+ uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb));
+ if (!uarg)
+ return -ENOBUFS;
+ extra_uref = true;
+ if (rt->dst.dev->features & NETIF_F_SG &&
+ csummode == CHECKSUM_PARTIAL) {
+ paged = true;
+ } else {
+ uarg->zerocopy = 0;
+ skb_zcopy_set(skb, uarg, &extra_uref);
+ }
+ }
+
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
@@ -1354,7 +1376,7 @@ emsgsize:
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
- unsigned int pagedlen = 0;
+ unsigned int pagedlen;
alloc_new_skb:
/* There's no room in the current skb */
if (skb)
@@ -1378,6 +1400,7 @@ alloc_new_skb:
if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
fraglen = datalen + fragheaderlen;
+ pagedlen = 0;
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
@@ -1439,12 +1462,6 @@ alloc_new_skb:
skb_reserve(skb, hh_len + sizeof(struct frag_hdr) +
dst_exthdrlen);
- /* Only the initial fragment is time stamped */
- skb_shinfo(skb)->tx_flags = cork->tx_flags;
- cork->tx_flags = 0;
- skb_shinfo(skb)->tskey = tskey;
- tskey = 0;
-
/*
* Find where to start putting bytes
*/
@@ -1476,6 +1493,13 @@ alloc_new_skb:
exthdrlen = 0;
dst_exthdrlen = 0;
+ /* Only the initial fragment is time stamped */
+ skb_shinfo(skb)->tx_flags = cork->tx_flags;
+ cork->tx_flags = 0;
+ skb_shinfo(skb)->tskey = tskey;
+ tskey = 0;
+ skb_zcopy_set(skb, uarg, &extra_uref);
+
if ((flags & MSG_CONFIRM) && !skb_prev)
skb_set_dst_pending_confirm(skb, 1);
@@ -1505,7 +1529,7 @@ alloc_new_skb:
err = -EFAULT;
goto error;
}
- } else {
+ } else if (!uarg || !uarg->zerocopy) {
int i = skb_shinfo(skb)->nr_frags;
err = -ENOMEM;
@@ -1535,6 +1559,10 @@ alloc_new_skb:
skb->data_len += copy;
skb->truesize += copy;
wmem_alloc_delta += copy;
+ } else {
+ err = skb_zerocopy_iter_dgram(skb, from, copy);
+ if (err < 0)
+ goto error;
}
offset += copy;
length -= copy;
@@ -1547,6 +1575,8 @@ alloc_new_skb:
error_efault:
err = -EFAULT;
error:
+ if (uarg)
+ sock_zerocopy_put_abort(uarg, extra_uref);
cork->length -= length;
IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index b283f293ee4a..3965d5396b0a 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -31,6 +31,22 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
if (err < 0)
goto error;
}
+ if (cfg->bind_ifindex) {
+ struct net_device *dev;
+
+ dev = dev_get_by_index(net, cfg->bind_ifindex);
+ if (!dev) {
+ err = -ENODEV;
+ goto error;
+ }
+
+ err = kernel_setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE,
+ dev->name, strlen(dev->name) + 1);
+ dev_put(dev);
+
+ if (err < 0)
+ goto error;
+ }
udp6_addr.sin6_family = AF_INET6;
memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6,
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index e2ea691e42c6..34b8a90e6be2 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -655,7 +655,7 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt)
return NULL;
}
- if (dev_open(dev))
+ if (dev_open(dev, NULL))
goto failure;
dev_hold(dev);
@@ -1968,7 +1968,7 @@ static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct
*/
static int ip6mr_forward2(struct net *net, struct mr_table *mrt,
- struct sk_buff *skb, struct mfc6_cache *c, int vifi)
+ struct sk_buff *skb, int vifi)
{
struct ipv6hdr *ipv6h;
struct vif_device *vif = &mrt->vif_table[vifi];
@@ -2134,15 +2134,14 @@ forward:
if (psend != -1) {
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2)
- ip6mr_forward2(net, mrt, skb2,
- c, psend);
+ ip6mr_forward2(net, mrt, skb2, psend);
}
psend = ct;
}
}
last_forward:
if (psend != -1) {
- ip6mr_forward2(net, mrt, skb, c, psend);
+ ip6mr_forward2(net, mrt, skb, psend);
return;
}
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 5ae8e1c51079..8b075f0bc351 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -24,7 +24,8 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
unsigned int hh_len;
struct dst_entry *dst;
struct flowi6 fl6 = {
- .flowi6_oif = sk ? sk->sk_bound_dev_if : 0,
+ .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if :
+ rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0,
.flowi6_mark = skb->mark,
.flowi6_uid = sock_net_uid(net, sk),
.daddr = iph->daddr,
diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c
index 491f808e356a..29c7f1915a96 100644
--- a/net/ipv6/netfilter/ip6t_MASQUERADE.c
+++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c
@@ -58,8 +58,12 @@ static int __init masquerade_tg6_init(void)
int err;
err = xt_register_target(&masquerade_tg6_reg);
- if (err == 0)
- nf_nat_masquerade_ipv6_register_notifier();
+ if (err)
+ return err;
+
+ err = nf_nat_masquerade_ipv6_register_notifier();
+ if (err)
+ xt_unregister_target(&masquerade_tg6_reg);
return err;
}
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index d219979c3e52..181da2c40f9a 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -341,7 +341,7 @@ static bool
nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev)
{
struct sk_buff *fp, *head = fq->q.fragments;
- int payload_len;
+ int payload_len, delta;
u8 ecn;
inet_frag_kill(&fq->q);
@@ -363,10 +363,16 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic
return false;
}
+ delta = - head->truesize;
+
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
return false;
+ delta += head->truesize;
+ if (delta)
+ add_frag_mem_limit(fq->q.net, delta);
+
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
index 3e4bf2286abe..0ad0da5a2600 100644
--- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -132,8 +132,8 @@ static void iterate_cleanup_work(struct work_struct *work)
* of ipv6 addresses being deleted), we also need to add an upper
* limit to the number of queued work items.
*/
-static int masq_inet_event(struct notifier_block *this,
- unsigned long event, void *ptr)
+static int masq_inet6_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
{
struct inet6_ifaddr *ifa = ptr;
const struct net_device *dev;
@@ -171,30 +171,53 @@ static int masq_inet_event(struct notifier_block *this,
return NOTIFY_DONE;
}
-static struct notifier_block masq_inet_notifier = {
- .notifier_call = masq_inet_event,
+static struct notifier_block masq_inet6_notifier = {
+ .notifier_call = masq_inet6_event,
};
-static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+static int masq_refcnt;
+static DEFINE_MUTEX(masq_mutex);
-void nf_nat_masquerade_ipv6_register_notifier(void)
+int nf_nat_masquerade_ipv6_register_notifier(void)
{
+ int ret = 0;
+
+ mutex_lock(&masq_mutex);
/* check if the notifier is already set */
- if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
- return;
+ if (++masq_refcnt > 1)
+ goto out_unlock;
+
+ ret = register_netdevice_notifier(&masq_dev_notifier);
+ if (ret)
+ goto err_dec;
+
+ ret = register_inet6addr_notifier(&masq_inet6_notifier);
+ if (ret)
+ goto err_unregister;
- register_netdevice_notifier(&masq_dev_notifier);
- register_inet6addr_notifier(&masq_inet_notifier);
+ mutex_unlock(&masq_mutex);
+ return ret;
+
+err_unregister:
+ unregister_netdevice_notifier(&masq_dev_notifier);
+err_dec:
+ masq_refcnt--;
+out_unlock:
+ mutex_unlock(&masq_mutex);
+ return ret;
}
EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier);
void nf_nat_masquerade_ipv6_unregister_notifier(void)
{
+ mutex_lock(&masq_mutex);
/* check if the notifier still has clients */
- if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
- return;
+ if (--masq_refcnt > 0)
+ goto out_unlock;
- unregister_inet6addr_notifier(&masq_inet_notifier);
+ unregister_inet6addr_notifier(&masq_inet6_notifier);
unregister_netdevice_notifier(&masq_dev_notifier);
+out_unlock:
+ mutex_unlock(&masq_mutex);
}
EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier);
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
index dd0122f3cffe..e06c82e9dfcd 100644
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -70,7 +70,9 @@ static int __init nft_masq_ipv6_module_init(void)
if (ret < 0)
return ret;
- nf_nat_masquerade_ipv6_register_notifier();
+ ret = nf_nat_masquerade_ipv6_register_notifier();
+ if (ret)
+ nft_unregister_expr(&nft_masq_ipv6_type);
return ret;
}
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 5c3c92713096..aa26c45486d9 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -281,7 +281,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
{
struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
struct sk_buff *fp, *head = fq->q.fragments;
- int payload_len;
+ int payload_len, delta;
unsigned int nhoff;
int sum_truesize;
u8 ecn;
@@ -322,10 +322,16 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
if (payload_len > IPV6_MAXPLEN)
goto out_oversize;
+ delta = - head->truesize;
+
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
goto out_oom;
+ delta += head->truesize;
+ if (delta)
+ add_frag_mem_limit(fq->q.net, delta);
+
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index b2447b7c7303..194bc162866d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2232,8 +2232,7 @@ static void ip6_link_failure(struct sk_buff *skb)
if (rt) {
rcu_read_lock();
if (rt->rt6i_flags & RTF_CACHE) {
- if (dst_hold_safe(&rt->dst))
- rt6_remove_exception_rt(rt);
+ rt6_remove_exception_rt(rt);
} else {
struct fib6_info *from;
struct fib6_node *fn;
@@ -2360,10 +2359,13 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu);
void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
{
+ int oif = sk->sk_bound_dev_if;
struct dst_entry *dst;
- ip6_update_pmtu(skb, sock_net(sk), mtu,
- sk->sk_bound_dev_if, sk->sk_mark, sk->sk_uid);
+ if (!oif && skb->dev)
+ oif = l3mdev_master_ifindex(skb->dev);
+
+ ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid);
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete ||
@@ -3215,8 +3217,8 @@ static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg)
if (cfg->fc_flags & RTF_GATEWAY &&
!ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
goto out;
- if (dst_hold_safe(&rt->dst))
- rc = rt6_remove_exception_rt(rt);
+
+ rc = rt6_remove_exception_rt(rt);
out:
return rc;
}
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index a8854dd3e9c5..8181ee7e1e27 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -347,6 +347,7 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
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);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index a3f559162521..b81eb7cb815e 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -737,6 +737,7 @@ static void tcp_v6_init_req(struct request_sock *req,
const struct sock *sk_listener,
struct sk_buff *skb)
{
+ bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
struct inet_request_sock *ireq = inet_rsk(req);
const struct ipv6_pinfo *np = inet6_sk(sk_listener);
@@ -744,7 +745,7 @@ static void tcp_v6_init_req(struct request_sock *req,
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
/* So that link locals have meaning */
- if (!sk_listener->sk_bound_dev_if &&
+ if ((!sk_listener->sk_bound_dev_if || l3_slave) &&
ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
ireq->ir_iif = tcp_v6_iif(skb);
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index e72947c99454..3179c425d7ff 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -9,14 +9,15 @@
*
* TCPv6 GSO/GRO support
*/
+#include <linux/indirect_call_wrapper.h>
#include <linux/skbuff.h>
#include <net/protocol.h>
#include <net/tcp.h>
#include <net/ip6_checksum.h>
#include "ip6_offload.h"
-static struct sk_buff *tcp6_gro_receive(struct list_head *head,
- struct sk_buff *skb)
+INDIRECT_CALLABLE_SCOPE
+struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)
{
/* Don't bother verifying checksum if we're going to flush anyway. */
if (!NAPI_GRO_CB(skb)->flush &&
@@ -29,7 +30,7 @@ static struct sk_buff *tcp6_gro_receive(struct list_head *head,
return tcp_gro_receive(head, skb);
}
-static int tcp6_gro_complete(struct sk_buff *skb, int thoff)
+INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct tcphdr *th = tcp_hdr(skb);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 0c0cb1611aef..9cbf363172bd 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -125,6 +125,9 @@ static int compute_score(struct sock *sk, struct net *net,
sk->sk_family != PF_INET6)
return -1;
+ if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+ return -1;
+
score = 0;
inet = inet_sk(sk);
@@ -134,12 +137,6 @@ static int compute_score(struct sock *sk, struct net *net,
score++;
}
- if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
- if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
- return -1;
- score++;
- }
-
if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
return -1;
@@ -197,66 +194,32 @@ struct sock *__udp6_lib_lookup(struct net *net,
int dif, int sdif, struct udp_table *udptable,
struct sk_buff *skb)
{
- struct sock *sk, *result;
unsigned short hnum = ntohs(dport);
- unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
- struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
+ unsigned int hash2, slot2;
+ struct udp_hslot *hslot2;
+ struct sock *result;
bool exact_dif = udp6_lib_exact_dif_match(net, skb);
- int score, badness;
- u32 hash = 0;
- if (hslot->count > 10) {
- hash2 = ipv6_portaddr_hash(net, daddr, hnum);
+ hash2 = ipv6_portaddr_hash(net, daddr, hnum);
+ slot2 = hash2 & udptable->mask;
+ hslot2 = &udptable->hash2[slot2];
+
+ result = udp6_lib_lookup2(net, saddr, sport,
+ daddr, hnum, dif, sdif, exact_dif,
+ hslot2, skb);
+ if (!result) {
+ hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
slot2 = hash2 & udptable->mask;
+
hslot2 = &udptable->hash2[slot2];
- if (hslot->count < hslot2->count)
- goto begin;
result = udp6_lib_lookup2(net, saddr, sport,
- daddr, hnum, dif, sdif, exact_dif,
- hslot2, skb);
- if (!result) {
- unsigned int old_slot2 = slot2;
- hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
- slot2 = hash2 & udptable->mask;
- /* avoid searching the same slot again. */
- if (unlikely(slot2 == old_slot2))
- return result;
-
- hslot2 = &udptable->hash2[slot2];
- if (hslot->count < hslot2->count)
- goto begin;
-
- result = udp6_lib_lookup2(net, saddr, sport,
- daddr, hnum, dif, sdif,
- exact_dif, hslot2,
- skb);
- }
- if (unlikely(IS_ERR(result)))
- return NULL;
- return result;
- }
-begin:
- result = NULL;
- badness = -1;
- sk_for_each_rcu(sk, &hslot->head) {
- score = compute_score(sk, net, saddr, sport, daddr, hnum, dif,
- sdif, exact_dif);
- if (score > badness) {
- if (sk->sk_reuseport) {
- hash = udp6_ehashfn(net, daddr, hnum,
- saddr, sport);
- result = reuseport_select_sock(sk, hash, skb,
- sizeof(struct udphdr));
- if (unlikely(IS_ERR(result)))
- return NULL;
- if (result)
- return result;
- }
- result = sk;
- badness = score;
- }
+ &in6addr_any, hnum, dif, sdif,
+ exact_dif, hslot2,
+ skb);
}
+ if (unlikely(IS_ERR(result)))
+ return NULL;
return result;
}
EXPORT_SYMBOL_GPL(__udp6_lib_lookup);
@@ -326,6 +289,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int err;
int is_udplite = IS_UDPLITE(sk);
bool checksum_valid = false;
+ struct udp_mib *mib;
int is_udp4;
if (flags & MSG_ERRQUEUE)
@@ -349,6 +313,7 @@ try_again:
msg->msg_flags |= MSG_TRUNC;
is_udp4 = (skb->protocol == htons(ETH_P_IP));
+ mib = __UDPX_MIB(sk, is_udp4);
/*
* If checksum is needed at all, try to do it while copying the
@@ -377,24 +342,13 @@ try_again:
if (unlikely(err)) {
if (!peeked) {
atomic_inc(&sk->sk_drops);
- if (is_udp4)
- UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
- is_udplite);
- else
- UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
- is_udplite);
+ SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
}
kfree_skb(skb);
return err;
}
- if (!peeked) {
- if (is_udp4)
- UDP_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS,
- is_udplite);
- else
- UDP6_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS,
- is_udplite);
- }
+ if (!peeked)
+ SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS);
sock_recv_ts_and_drops(msg, sk, skb);
@@ -443,17 +397,8 @@ try_again:
csum_copy_err:
if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags,
udp_skb_destructor)) {
- if (is_udp4) {
- UDP_INC_STATS(sock_net(sk),
- UDP_MIB_CSUMERRORS, is_udplite);
- UDP_INC_STATS(sock_net(sk),
- UDP_MIB_INERRORS, is_udplite);
- } else {
- UDP6_INC_STATS(sock_net(sk),
- UDP_MIB_CSUMERRORS, is_udplite);
- UDP6_INC_STATS(sock_net(sk),
- UDP_MIB_INERRORS, is_udplite);
- }
+ SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS);
+ SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
}
kfree_skb(skb);
@@ -466,7 +411,7 @@ csum_copy_err:
DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
void udpv6_encap_enable(void)
{
- static_branch_enable(&udpv6_encap_needed_key);
+ static_branch_inc(&udpv6_encap_needed_key);
}
EXPORT_SYMBOL(udpv6_encap_enable);
@@ -1597,7 +1542,7 @@ void udpv6_destroy_sock(struct sock *sk)
encap_destroy(sk);
}
if (up->encap_enabled)
- static_branch_disable(&udpv6_encap_needed_key);
+ static_branch_dec(&udpv6_encap_needed_key);
}
inet6_destroy_sock(sk);
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 828b2457f97b..83b11d0ac091 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -11,6 +11,7 @@
*/
#include <linux/skbuff.h>
#include <linux/netdevice.h>
+#include <linux/indirect_call_wrapper.h>
#include <net/protocol.h>
#include <net/ipv6.h>
#include <net/udp.h>
@@ -114,8 +115,8 @@ out:
return segs;
}
-static struct sk_buff *udp6_gro_receive(struct list_head *head,
- struct sk_buff *skb)
+INDIRECT_CALLABLE_SCOPE
+struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
@@ -142,7 +143,7 @@ flush:
return NULL;
}
-static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
+INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff)
{
const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-22 05:22:29 +0300