summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c95
-rw-r--r--net/ipv6/addrconf_core.c6
-rw-r--r--net/ipv6/addrlabel.c47
-rw-r--r--net/ipv6/af_inet6.c7
-rw-r--r--net/ipv6/ip6_gre.c4
-rw-r--r--net/ipv6/ip6_udp_tunnel.c15
-rw-r--r--net/ipv6/mcast.c2
-rw-r--r--net/ipv6/mcast_snoop.c83
-rw-r--r--net/ipv6/netfilter.c13
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c260
-rw-r--r--net/ipv6/netfilter/nf_nat_l3proto_ipv6.c19
-rw-r--r--net/ipv6/netfilter/nf_nat_masquerade_ipv6.c21
-rw-r--r--net/ipv6/netfilter/nf_reject_ipv6.c3
-rw-r--r--net/ipv6/netfilter/nft_fib_ipv6.c9
-rw-r--r--net/ipv6/reassembly.c233
-rw-r--r--net/ipv6/route.c78
-rw-r--r--net/ipv6/tcp_ipv6.c2
17 files changed, 442 insertions, 455 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 72ffd3d760ff..da5a21050ba9 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -597,6 +597,43 @@ static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = {
[NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) },
};
+static int inet6_netconf_valid_get_req(struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack)
+{
+ int i, err;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct netconfmsg))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid header for netconf get request");
+ return -EINVAL;
+ }
+
+ if (!netlink_strict_get_check(skb))
+ return nlmsg_parse(nlh, sizeof(struct netconfmsg), tb,
+ NETCONFA_MAX, devconf_ipv6_policy, extack);
+
+ err = nlmsg_parse_strict(nlh, sizeof(struct netconfmsg), tb,
+ NETCONFA_MAX, devconf_ipv6_policy, extack);
+ if (err)
+ return err;
+
+ for (i = 0; i <= NETCONFA_MAX; i++) {
+ if (!tb[i])
+ continue;
+
+ switch (i) {
+ case NETCONFA_IFINDEX:
+ break;
+ default:
+ NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in netconf get request");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
@@ -605,14 +642,12 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
struct nlattr *tb[NETCONFA_MAX+1];
struct inet6_dev *in6_dev = NULL;
struct net_device *dev = NULL;
- struct netconfmsg *ncm;
struct sk_buff *skb;
struct ipv6_devconf *devconf;
int ifindex;
int err;
- err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX,
- devconf_ipv6_policy, extack);
+ err = inet6_netconf_valid_get_req(in_skb, nlh, tb, extack);
if (err < 0)
return err;
@@ -5182,6 +5217,52 @@ static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb)
return inet6_dump_addr(skb, cb, type);
}
+static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack)
+{
+ struct ifaddrmsg *ifm;
+ int i, err;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid header for get address request");
+ return -EINVAL;
+ }
+
+ ifm = nlmsg_data(nlh);
+ if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request");
+ return -EINVAL;
+ }
+
+ if (!netlink_strict_get_check(skb))
+ return nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX,
+ ifa_ipv6_policy, extack);
+
+ err = nlmsg_parse_strict(nlh, sizeof(*ifm), tb, IFA_MAX,
+ ifa_ipv6_policy, extack);
+ if (err)
+ return err;
+
+ for (i = 0; i <= IFA_MAX; i++) {
+ if (!tb[i])
+ continue;
+
+ switch (i) {
+ case IFA_TARGET_NETNSID:
+ case IFA_ADDRESS:
+ case IFA_LOCAL:
+ break;
+ default:
+ NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get address request");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
@@ -5202,8 +5283,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
struct sk_buff *skb;
int err;
- err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy,
- extack);
+ err = inet6_rtm_valid_getaddr_req(in_skb, nlh, tb, extack);
if (err < 0)
return err;
@@ -6825,6 +6905,11 @@ static int __net_init addrconf_init_net(struct net *net)
if (!dflt)
goto err_alloc_dflt;
+ if (sysctl_devconf_inherit_init_net == 1 && !net_eq(net, &init_net)) {
+ memcpy(all, init_net.ipv6.devconf_all, sizeof(ipv6_devconf));
+ memcpy(dflt, init_net.ipv6.devconf_dflt, sizeof(ipv6_devconf_dflt));
+ }
+
/* these will be inherited by all namespaces */
dflt->autoconf = ipv6_defaults.autoconf;
dflt->disable_ipv6 = ipv6_defaults.disable_ipv6;
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 5cd0029d930e..6c79af056d9b 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -134,6 +134,11 @@ static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1,
return -EAFNOSUPPORT;
}
+static int eafnosupport_ipv6_route_input(struct sk_buff *skb)
+{
+ return -EAFNOSUPPORT;
+}
+
static struct fib6_table *eafnosupport_fib6_get_table(struct net *net, u32 id)
{
return NULL;
@@ -170,6 +175,7 @@ eafnosupport_ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
.ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup,
+ .ipv6_route_input = eafnosupport_ipv6_route_input,
.fib6_get_table = eafnosupport_fib6_get_table,
.fib6_table_lookup = eafnosupport_fib6_table_lookup,
.fib6_lookup = eafnosupport_fib6_lookup,
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 0d1ee82ee55b..d43d076c98f5 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -523,6 +523,50 @@ static inline int ip6addrlbl_msgsize(void)
+ nla_total_size(4); /* IFAL_LABEL */
}
+static int ip6addrlbl_valid_get_req(struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack)
+{
+ struct ifaddrlblmsg *ifal;
+ int i, err;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifal))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid header for addrlabel get request");
+ return -EINVAL;
+ }
+
+ if (!netlink_strict_get_check(skb))
+ return nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX,
+ ifal_policy, extack);
+
+ ifal = nlmsg_data(nlh);
+ if (ifal->__ifal_reserved || ifal->ifal_flags || ifal->ifal_seq) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for addrlabel get request");
+ return -EINVAL;
+ }
+
+ err = nlmsg_parse_strict(nlh, sizeof(*ifal), tb, IFAL_MAX,
+ ifal_policy, extack);
+ if (err)
+ return err;
+
+ for (i = 0; i <= IFAL_MAX; i++) {
+ if (!tb[i])
+ continue;
+
+ switch (i) {
+ case IFAL_ADDRESS:
+ break;
+ default:
+ NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in addrlabel get request");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
@@ -535,8 +579,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
struct ip6addrlbl_entry *p;
struct sk_buff *skb;
- err = nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy,
- extack);
+ err = ip6addrlbl_valid_get_req(in_skb, nlh, tb, extack);
if (err < 0)
return err;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index d99753b5e39b..2f45d2a3e3a3 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -900,10 +900,17 @@ static struct pernet_operations inet6_net_ops = {
.exit = inet6_net_exit,
};
+static int ipv6_route_input(struct sk_buff *skb)
+{
+ ip6_route_input(skb);
+ return skb_dst(skb)->error;
+}
+
static const struct ipv6_stub ipv6_stub_impl = {
.ipv6_sock_mc_join = ipv6_sock_mc_join,
.ipv6_sock_mc_drop = ipv6_sock_mc_drop,
.ipv6_dst_lookup = ip6_dst_lookup,
+ .ipv6_route_input = ipv6_route_input,
.fib6_get_table = fib6_get_table,
.fib6_table_lookup = fib6_table_lookup,
.fib6_lookup = fib6_lookup,
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 43890898b0b5..bb525abd860e 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -524,7 +524,7 @@ static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
return PACKET_REJECT;
}
-static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len,
+static int ip6erspan_rcv(struct sk_buff *skb,
struct tnl_ptk_info *tpi)
{
struct erspan_base_hdr *ershdr;
@@ -607,7 +607,7 @@ static int gre_rcv(struct sk_buff *skb)
if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) ||
tpi.proto == htons(ETH_P_ERSPAN2))) {
- if (ip6erspan_rcv(skb, hdr_len, &tpi) == PACKET_RCVD)
+ if (ip6erspan_rcv(skb, &tpi) == PACKET_RCVD)
return 0;
goto out;
}
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index ad1a9ccd4b44..25430c991cea 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -32,18 +32,9 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
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);
-
+ err = kernel_setsockopt(sock, SOL_SOCKET, SO_BINDTOIFINDEX,
+ (void *)&cfg->bind_ifindex,
+ sizeof(cfg->bind_ifindex));
if (err < 0)
goto error;
}
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 21f6deb2aec9..42f3f5cd349f 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -940,6 +940,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
{
return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE);
}
+EXPORT_SYMBOL(ipv6_dev_mc_inc);
/*
* device multicast group del
@@ -987,6 +988,7 @@ int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr)
return err;
}
+EXPORT_SYMBOL(ipv6_dev_mc_dec);
/*
* check if the interface/address pair is valid
diff --git a/net/ipv6/mcast_snoop.c b/net/ipv6/mcast_snoop.c
index 9405b04eecc6..55e2ac179f28 100644
--- a/net/ipv6/mcast_snoop.c
+++ b/net/ipv6/mcast_snoop.c
@@ -41,6 +41,8 @@ static int ipv6_mc_check_ip6hdr(struct sk_buff *skb)
if (skb->len < len || len <= offset)
return -EINVAL;
+ skb_set_transport_header(skb, offset);
+
return 0;
}
@@ -77,27 +79,27 @@ static int ipv6_mc_check_mld_reportv2(struct sk_buff *skb)
len += sizeof(struct mld2_report);
- return pskb_may_pull(skb, len) ? 0 : -EINVAL;
+ return ipv6_mc_may_pull(skb, len) ? 0 : -EINVAL;
}
static int ipv6_mc_check_mld_query(struct sk_buff *skb)
{
+ unsigned int transport_len = ipv6_transport_len(skb);
struct mld_msg *mld;
- unsigned int len = skb_transport_offset(skb);
+ unsigned int len;
/* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */
if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL))
return -EINVAL;
- len += sizeof(struct mld_msg);
- if (skb->len < len)
- return -EINVAL;
-
/* MLDv1? */
- if (skb->len != len) {
+ if (transport_len != sizeof(struct mld_msg)) {
/* or MLDv2? */
- len += sizeof(struct mld2_query) - sizeof(struct mld_msg);
- if (skb->len < len || !pskb_may_pull(skb, len))
+ if (transport_len < sizeof(struct mld2_query))
+ return -EINVAL;
+
+ len = skb_transport_offset(skb) + sizeof(struct mld2_query);
+ if (!ipv6_mc_may_pull(skb, len))
return -EINVAL;
}
@@ -115,7 +117,13 @@ static int ipv6_mc_check_mld_query(struct sk_buff *skb)
static int ipv6_mc_check_mld_msg(struct sk_buff *skb)
{
- struct mld_msg *mld = (struct mld_msg *)skb_transport_header(skb);
+ unsigned int len = skb_transport_offset(skb) + sizeof(struct mld_msg);
+ struct mld_msg *mld;
+
+ if (!ipv6_mc_may_pull(skb, len))
+ return -EINVAL;
+
+ mld = (struct mld_msg *)skb_transport_header(skb);
switch (mld->mld_type) {
case ICMPV6_MGM_REDUCTION:
@@ -136,49 +144,30 @@ static inline __sum16 ipv6_mc_validate_checksum(struct sk_buff *skb)
return skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo);
}
-static int __ipv6_mc_check_mld(struct sk_buff *skb,
- struct sk_buff **skb_trimmed)
-
+int ipv6_mc_check_icmpv6(struct sk_buff *skb)
{
- struct sk_buff *skb_chk = NULL;
- unsigned int transport_len;
- unsigned int len = skb_transport_offset(skb) + sizeof(struct mld_msg);
- int ret = -EINVAL;
+ unsigned int len = skb_transport_offset(skb) + sizeof(struct icmp6hdr);
+ unsigned int transport_len = ipv6_transport_len(skb);
+ struct sk_buff *skb_chk;
- transport_len = ntohs(ipv6_hdr(skb)->payload_len);
- transport_len -= skb_transport_offset(skb) - sizeof(struct ipv6hdr);
+ if (!ipv6_mc_may_pull(skb, len))
+ return -EINVAL;
skb_chk = skb_checksum_trimmed(skb, transport_len,
ipv6_mc_validate_checksum);
if (!skb_chk)
- goto err;
-
- if (!pskb_may_pull(skb_chk, len))
- goto err;
-
- ret = ipv6_mc_check_mld_msg(skb_chk);
- if (ret)
- goto err;
-
- if (skb_trimmed)
- *skb_trimmed = skb_chk;
- /* free now unneeded clone */
- else if (skb_chk != skb)
- kfree_skb(skb_chk);
-
- ret = 0;
+ return -EINVAL;
-err:
- if (ret && skb_chk && skb_chk != skb)
+ if (skb_chk != skb)
kfree_skb(skb_chk);
- return ret;
+ return 0;
}
+EXPORT_SYMBOL(ipv6_mc_check_icmpv6);
/**
* ipv6_mc_check_mld - checks whether this is a sane MLD packet
* @skb: the skb to validate
- * @skb_trimmed: to store an skb pointer trimmed to IPv6 packet tail (optional)
*
* Checks whether an IPv6 packet is a valid MLD packet. If so sets
* skb transport header accordingly and returns zero.
@@ -188,18 +177,10 @@ err:
* -ENOMSG: IP header validation succeeded but it is not an MLD packet.
* -ENOMEM: A memory allocation failure happened.
*
- * Optionally, an skb pointer might be provided via skb_trimmed (or set it
- * to NULL): After parsing an MLD packet successfully it will point to
- * an skb which has its tail aligned to the IP packet end. This might
- * either be the originally provided skb or a trimmed, cloned version if
- * the skb frame had data beyond the IP packet. A cloned skb allows us
- * to leave the original skb and its full frame unchanged (which might be
- * desirable for layer 2 frame jugglers).
- *
* Caller needs to set the skb network header and free any returned skb if it
* differs from the provided skb.
*/
-int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed)
+int ipv6_mc_check_mld(struct sk_buff *skb)
{
int ret;
@@ -211,6 +192,10 @@ int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed)
if (ret < 0)
return ret;
- return __ipv6_mc_check_mld(skb, skb_trimmed);
+ ret = ipv6_mc_check_icmpv6(skb);
+ if (ret < 0)
+ return ret;
+
+ return ipv6_mc_check_mld_msg(skb);
}
EXPORT_SYMBOL(ipv6_mc_check_mld);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 6d0b1f3e927b..1240ccd57f39 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -86,8 +86,8 @@ static int nf_ip6_reroute(struct sk_buff *skb,
return 0;
}
-static int nf_ip6_route(struct net *net, struct dst_entry **dst,
- struct flowi *fl, bool strict)
+int __nf_ip6_route(struct net *net, struct dst_entry **dst,
+ struct flowi *fl, bool strict)
{
static const struct ipv6_pinfo fake_pinfo;
static const struct inet_sock fake_sk = {
@@ -107,12 +107,17 @@ static int nf_ip6_route(struct net *net, struct dst_entry **dst,
*dst = result;
return err;
}
+EXPORT_SYMBOL_GPL(__nf_ip6_route);
static const struct nf_ipv6_ops ipv6ops = {
+#if IS_MODULE(CONFIG_IPV6)
.chk_addr = ipv6_chk_addr,
- .route_input = ip6_route_input,
+ .route_me_harder = ip6_route_me_harder,
+ .dev_get_saddr = ipv6_dev_get_saddr,
+ .route = __nf_ip6_route,
+#endif
+ .route_input = ip6_route_input,
.fragment = ip6_fragment,
- .route = nf_ip6_route,
.reroute = nf_ip6_reroute,
};
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 181da2c40f9a..cb1b4772dac0 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -136,6 +136,9 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
}
#endif
+static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
+ struct sk_buff *prev_tail, struct net_device *dev);
+
static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
{
return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
@@ -177,9 +180,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
const struct frag_hdr *fhdr, int nhoff)
{
- struct sk_buff *prev, *next;
unsigned int payload_len;
- int offset, end;
+ struct net_device *dev;
+ struct sk_buff *prev;
+ int offset, end, err;
u8 ecn;
if (fq->q.flags & INET_FRAG_COMPLETE) {
@@ -254,55 +258,18 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
goto err;
}
- /* Find out which fragments are in front and at the back of us
- * in the chain of fragments so far. We must know where to put
- * this fragment, right?
- */
- prev = fq->q.fragments_tail;
- if (!prev || prev->ip_defrag_offset < offset) {
- next = NULL;
- goto found;
- }
- prev = NULL;
- for (next = fq->q.fragments; next != NULL; next = next->next) {
- if (next->ip_defrag_offset >= offset)
- break; /* bingo! */
- prev = next;
- }
-
-found:
- /* RFC5722, Section 4:
- * When reassembling an IPv6 datagram, if
- * one or more its constituent fragments is determined to be an
- * overlapping fragment, the entire datagram (and any constituent
- * fragments, including those not yet received) MUST be silently
- * discarded.
- */
-
- /* Check for overlap with preceding fragment. */
- if (prev &&
- (prev->ip_defrag_offset + prev->len) > offset)
- goto discard_fq;
-
- /* Look for overlap with succeeding segment. */
- if (next && next->ip_defrag_offset < end)
- goto discard_fq;
-
- /* Note : skb->ip_defrag_offset and skb->dev share the same location */
- if (skb->dev)
- fq->iif = skb->dev->ifindex;
+ /* Note : skb->rbnode and skb->dev share the same location. */
+ dev = skb->dev;
/* Makes sure compiler wont do silly aliasing games */
barrier();
- skb->ip_defrag_offset = offset;
- /* Insert this fragment in the chain of fragments. */
- skb->next = next;
- if (!next)
- fq->q.fragments_tail = skb;
- if (prev)
- prev->next = skb;
- else
- fq->q.fragments = skb;
+ prev = fq->q.fragments_tail;
+ err = inet_frag_queue_insert(&fq->q, skb, offset, end);
+ if (err)
+ goto insert_error;
+
+ if (dev)
+ fq->iif = dev->ifindex;
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
@@ -319,11 +286,25 @@ found:
fq->q.flags |= INET_FRAG_FIRST_IN;
}
- return 0;
+ if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
+ fq->q.meat == fq->q.len) {
+ unsigned long orefdst = skb->_skb_refdst;
+
+ skb->_skb_refdst = 0UL;
+ err = nf_ct_frag6_reasm(fq, skb, prev, dev);
+ skb->_skb_refdst = orefdst;
+ return err;
+ }
+
+ skb_dst_drop(skb);
+ return -EINPROGRESS;
-discard_fq:
+insert_error:
+ if (err == IPFRAG_DUP)
+ goto err;
inet_frag_kill(&fq->q);
err:
+ skb_dst_drop(skb);
return -EINVAL;
}
@@ -333,147 +314,67 @@ err:
* It is called with locked fq, and caller must check that
* queue is eligible for reassembly i.e. it is not COMPLETE,
* the last and the first frames arrived and all the bits are here.
- *
- * returns true if *prev skb has been transformed into the reassembled
- * skb, false otherwise.
*/
-static bool
-nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev)
+static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
+ struct sk_buff *prev_tail, struct net_device *dev)
{
- struct sk_buff *fp, *head = fq->q.fragments;
- int payload_len, delta;
+ void *reasm_data;
+ int payload_len;
u8 ecn;
inet_frag_kill(&fq->q);
- WARN_ON(head == NULL);
- WARN_ON(head->ip_defrag_offset != 0);
-
ecn = ip_frag_ecn_table[fq->ecn];
if (unlikely(ecn == 0xff))
- return false;
+ goto err;
+
+ reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail);
+ if (!reasm_data)
+ goto err;
- /* Unfragmented part is taken from the first segment. */
- payload_len = ((head->data - skb_network_header(head)) -
+ payload_len = ((skb->data - skb_network_header(skb)) -
sizeof(struct ipv6hdr) + fq->q.len -
sizeof(struct frag_hdr));
if (payload_len > IPV6_MAXPLEN) {
net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n",
payload_len);
- 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. */
- if (skb_has_frag_list(head)) {
- struct sk_buff *clone;
- int i, plen = 0;
-
- clone = alloc_skb(0, GFP_ATOMIC);
- if (clone == NULL)
- return false;
-
- clone->next = head->next;
- head->next = clone;
- skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
- skb_frag_list_init(head);
- for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
- plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
- clone->len = clone->data_len = head->data_len - plen;
- head->data_len -= clone->len;
- head->len -= clone->len;
- clone->csum = 0;
- clone->ip_summed = head->ip_summed;
-
- add_frag_mem_limit(fq->q.net, clone->truesize);
- }
-
- /* morph head into last received skb: prev.
- *
- * This allows callers of ipv6 conntrack defrag to continue
- * to use the last skb(frag) passed into the reasm engine.
- * The last skb frag 'silently' turns into the full reassembled skb.
- *
- * Since prev is also part of q->fragments we have to clone it first.
- */
- if (head != prev) {
- struct sk_buff *iter;
-
- fp = skb_clone(prev, GFP_ATOMIC);
- if (!fp)
- return false;
-
- fp->next = prev->next;
-
- iter = head;
- while (iter) {
- if (iter->next == prev) {
- iter->next = fp;
- break;
- }
- iter = iter->next;
- }
-
- skb_morph(prev, head);
- prev->next = head->next;
- consume_skb(head);
- head = prev;
+ goto err;
}
/* We have to remove fragment header from datagram and to relocate
* header in order to calculate ICV correctly. */
- skb_network_header(head)[fq->nhoffset] = skb_transport_header(head)[0];
- memmove(head->head + sizeof(struct frag_hdr), head->head,
- (head->data - head->head) - sizeof(struct frag_hdr));
- head->mac_header += sizeof(struct frag_hdr);
- head->network_header += sizeof(struct frag_hdr);
-
- skb_shinfo(head)->frag_list = head->next;
- skb_reset_transport_header(head);
- skb_push(head, head->data - skb_network_header(head));
-
- for (fp = head->next; fp; fp = fp->next) {
- head->data_len += fp->len;
- head->len += fp->len;
- if (head->ip_summed != fp->ip_summed)
- head->ip_summed = CHECKSUM_NONE;
- else if (head->ip_summed == CHECKSUM_COMPLETE)
- head->csum = csum_add(head->csum, fp->csum);
- head->truesize += fp->truesize;
- fp->sk = NULL;
- }
- sub_frag_mem_limit(fq->q.net, head->truesize);
+ skb_network_header(skb)[fq->nhoffset] = skb_transport_header(skb)[0];
+ memmove(skb->head + sizeof(struct frag_hdr), skb->head,
+ (skb->data - skb->head) - sizeof(struct frag_hdr));
+ skb->mac_header += sizeof(struct frag_hdr);
+ skb->network_header += sizeof(struct frag_hdr);
+
+ skb_reset_transport_header(skb);
+
+ inet_frag_reasm_finish(&fq->q, skb, reasm_data);
- head->ignore_df = 1;
- skb_mark_not_on_list(head);
- head->dev = dev;
- head->tstamp = fq->q.stamp;
- ipv6_hdr(head)->payload_len = htons(payload_len);
- ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn);
- IP6CB(head)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size;
+ skb->ignore_df = 1;
+ skb->dev = dev;
+ ipv6_hdr(skb)->payload_len = htons(payload_len);
+ ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn);
+ IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size;
/* Yes, and fold redundant checksum back. 8) */
- if (head->ip_summed == CHECKSUM_COMPLETE)
- head->csum = csum_partial(skb_network_header(head),
- skb_network_header_len(head),
- head->csum);
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ skb->csum = csum_partial(skb_network_header(skb),
+ skb_network_header_len(skb),
+ skb->csum);
fq->q.fragments = NULL;
fq->q.rb_fragments = RB_ROOT;
fq->q.fragments_tail = NULL;
+ fq->q.last_run_head = NULL;
- return true;
+ return 0;
+
+err:
+ inet_frag_kill(&fq->q);
+ return -EINVAL;
}
/*
@@ -542,7 +443,6 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
{
u16 savethdr = skb->transport_header;
- struct net_device *dev = skb->dev;
int fhoff, nhoff, ret;
struct frag_hdr *fhdr;
struct frag_queue *fq;
@@ -565,10 +465,6 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
hdr = ipv6_hdr(skb);
fhdr = (struct frag_hdr *)skb_transport_header(skb);
- if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU &&
- fhdr->frag_off & htons(IP6_MF))
- return -EINVAL;
-
skb_orphan(skb);
fq = fq_find(net, fhdr->identification, user, hdr,
skb->dev ? skb->dev->ifindex : 0);
@@ -580,31 +476,17 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
spin_lock_bh(&fq->q.lock);
ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff);
- if (ret < 0) {
- if (ret == -EPROTO) {
- skb->transport_header = savethdr;
- ret = 0;
- }
- goto out_unlock;
+ if (ret == -EPROTO) {
+ skb->transport_header = savethdr;
+ ret = 0;
}
/* after queue has assumed skb ownership, only 0 or -EINPROGRESS
* must be returned.
*/
- ret = -EINPROGRESS;
- if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
- fq->q.meat == fq->q.len) {
- unsigned long orefdst = skb->_skb_refdst;
-
- skb->_skb_refdst = 0UL;
- if (nf_ct_frag6_reasm(fq, skb, dev))
- ret = 0;
- skb->_skb_refdst = orefdst;
- } else {
- skb_dst_drop(skb);
- }
+ if (ret)
+ ret = -EINPROGRESS;
-out_unlock:
spin_unlock_bh(&fq->q.lock);
inet_frag_put(&fq->q);
return ret;
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index 7a41ee3c11b4..490bfd3c9162 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -17,6 +17,7 @@
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <net/ip6_route.h>
+#include <net/xfrm.h>
#include <net/ipv6.h>
#include <net/netfilter/nf_conntrack_core.h>
@@ -225,7 +226,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
skb->len - hdrlen, 0));
}
- nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
+ nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple);
target.dst.protonum = IPPROTO_ICMPV6;
if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip))
return 0;
@@ -318,6 +319,20 @@ nf_nat_ipv6_out(void *priv, struct sk_buff *skb,
return ret;
}
+static int nat_route_me_harder(struct net *net, struct sk_buff *skb)
+{
+#ifdef CONFIG_IPV6_MODULE
+ const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
+
+ if (!v6_ops)
+ return -EHOSTUNREACH;
+
+ return v6_ops->route_me_harder(net, skb);
+#else
+ return ip6_route_me_harder(net, skb);
+#endif
+}
+
static unsigned int
nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
@@ -334,7 +349,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
&ct->tuplehash[!dir].tuple.src.u3)) {
- err = ip6_route_me_harder(state->net, skb);
+ err = nat_route_me_harder(state->net, skb);
if (err < 0)
ret = NF_DROP_ERR(err);
}
diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
index 0ad0da5a2600..fd313b726263 100644
--- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -24,6 +24,23 @@
static atomic_t v6_worker_count;
+static int
+nat_ipv6_dev_get_saddr(struct net *net, const struct net_device *dev,
+ const struct in6_addr *daddr, unsigned int srcprefs,
+ struct in6_addr *saddr)
+{
+#ifdef CONFIG_IPV6_MODULE
+ const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
+
+ if (!v6_ops)
+ return -EHOSTUNREACH;
+
+ return v6_ops->dev_get_saddr(net, dev, daddr, srcprefs, saddr);
+#else
+ return ipv6_dev_get_saddr(net, dev, daddr, srcprefs, saddr);
+#endif
+}
+
unsigned int
nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
const struct net_device *out)
@@ -38,8 +55,8 @@ nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
ctinfo == IP_CT_RELATED_REPLY)));
- if (ipv6_dev_get_saddr(nf_ct_net(ct), out,
- &ipv6_hdr(skb)->daddr, 0, &src) < 0)
+ if (nat_ipv6_dev_get_saddr(nf_ct_net(ct), out,
+ &ipv6_hdr(skb)->daddr, 0, &src) < 0)
return NF_DROP;
nat = nf_ct_nat_ext_add(ct);
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index b9c8a763c863..02e9228641e0 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -233,6 +233,9 @@ 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))
+ 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 36be3cf0adef..73cdc0bc63f7 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -59,7 +59,6 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv,
struct ipv6hdr *iph)
{
const struct net_device *dev = NULL;
- const struct nf_ipv6_ops *v6ops;
int route_err, addrtype;
struct rt6_info *rt;
struct flowi6 fl6 = {
@@ -68,10 +67,6 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv,
};
u32 ret = 0;
- v6ops = nf_get_ipv6_ops();
- if (!v6ops)
- return RTN_UNREACHABLE;
-
if (priv->flags & NFTA_FIB_F_IIF)
dev = nft_in(pkt);
else if (priv->flags & NFTA_FIB_F_OIF)
@@ -79,10 +74,10 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv,
nft_fib6_flowi_init(&fl6, priv, pkt, dev, iph);
- if (dev && v6ops->chk_addr(nft_net(pkt), &fl6.daddr, dev, true))
+ if (dev && nf_ipv6_chk_addr(nft_net(pkt), &fl6.daddr, dev, true))
ret = RTN_LOCAL;
- route_err = v6ops->route(nft_net(pkt), (struct dst_entry **)&rt,
+ route_err = nf_ip6_route(nft_net(pkt), (struct dst_entry **)&rt,
flowi6_to_flowi(&fl6), false);
if (route_err)
goto err;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 36a3d8dc61f5..24264d0a4b85 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -69,8 +69,8 @@ static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
static struct inet_frags ip6_frags;
-static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
- struct net_device *dev);
+static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
+ struct sk_buff *prev_tail, struct net_device *dev);
static void ip6_frag_expire(struct timer_list *t)
{
@@ -111,21 +111,26 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
struct frag_hdr *fhdr, int nhoff,
u32 *prob_offset)
{
- struct sk_buff *prev, *next;
- struct net_device *dev;
- int offset, end, fragsize;
struct net *net = dev_net(skb_dst(skb)->dev);
+ int offset, end, fragsize;
+ struct sk_buff *prev_tail;
+ struct net_device *dev;
+ int err = -ENOENT;
u8 ecn;
if (fq->q.flags & INET_FRAG_COMPLETE)
goto err;
+ err = -EINVAL;
offset = ntohs(fhdr->frag_off) & ~0x7;
end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));
if ((unsigned int)end > IPV6_MAXPLEN) {
*prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb);
+ /* note that if prob_offset is set, the skb is freed elsewhere,
+ * we do not free it here.
+ */
return -1;
}
@@ -170,62 +175,27 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
if (end == offset)
goto discard_fq;
+ err = -ENOMEM;
/* Point into the IP datagram 'data' part. */
if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
goto discard_fq;
- if (pskb_trim_rcsum(skb, end - offset))
+ err = pskb_trim_rcsum(skb, end - offset);
+ if (err)
goto discard_fq;
- /* Find out which fragments are in front and at the back of us
- * in the chain of fragments so far. We must know where to put
- * this fragment, right?
- */
- prev = fq->q.fragments_tail;
- if (!prev || prev->ip_defrag_offset < offset) {
- next = NULL;
- goto found;
- }
- prev = NULL;
- for (next = fq->q.fragments; next != NULL; next = next->next) {
- if (next->ip_defrag_offset >= offset)
- break; /* bingo! */
- prev = next;
- }
-
-found:
- /* RFC5722, Section 4, amended by Errata ID : 3089
- * When reassembling an IPv6 datagram, if
- * one or more its constituent fragments is determined to be an
- * overlapping fragment, the entire datagram (and any constituent
- * fragments) MUST be silently discarded.
- */
-
- /* Check for overlap with preceding fragment. */
- if (prev &&
- (prev->ip_defrag_offset + prev->len) > offset)
- goto discard_fq;
-
- /* Look for overlap with succeeding segment. */
- if (next && next->ip_defrag_offset < end)
- goto discard_fq;
-
- /* Note : skb->ip_defrag_offset and skb->sk share the same location */
+ /* Note : skb->rbnode and skb->dev share the same location. */
dev = skb->dev;
- if (dev)
- fq->iif = dev->ifindex;
/* Makes sure compiler wont do silly aliasing games */
barrier();
- skb->ip_defrag_offset = offset;
- /* Insert this fragment in the chain of fragments. */
- skb->next = next;
- if (!next)
- fq->q.fragments_tail = skb;
- if (prev)
- prev->next = skb;
- else
- fq->q.fragments = skb;
+ prev_tail = fq->q.fragments_tail;
+ err = inet_frag_queue_insert(&fq->q, skb, offset, end);
+ if (err)
+ goto insert_error;
+
+ if (dev)
+ fq->iif = dev->ifindex;
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
@@ -246,44 +216,48 @@ found:
if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
fq->q.meat == fq->q.len) {
- int res;
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
- res = ip6_frag_reasm(fq, prev, dev);
+ err = ip6_frag_reasm(fq, skb, prev_tail, dev);
skb->_skb_refdst = orefdst;
- return res;
+ return err;
}
skb_dst_drop(skb);
- return -1;
+ return -EINPROGRESS;
+insert_error:
+ if (err == IPFRAG_DUP) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
+ err = -EINVAL;
+ __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_REASM_OVERLAPS);
discard_fq:
inet_frag_kill(&fq->q);
-err:
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
+err:
kfree_skb(skb);
- return -1;
+ return err;
}
/*
* Check if this packet is complete.
- * Returns NULL on failure by any reason, and pointer
- * to current nexthdr field in reassembled frame.
*
* It is called with locked fq, and caller must check that
* queue is eligible for reassembly i.e. it is not COMPLETE,
* the last and the first frames arrived and all the bits are here.
*/
-static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
- struct net_device *dev)
+static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
+ struct sk_buff *prev_tail, struct net_device *dev)
{
struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
- struct sk_buff *fp, *head = fq->q.fragments;
- int payload_len, delta;
unsigned int nhoff;
- int sum_truesize;
+ void *reasm_data;
+ int payload_len;
u8 ecn;
inet_frag_kill(&fq->q);
@@ -292,121 +266,40 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
if (unlikely(ecn == 0xff))
goto out_fail;
- /* Make the one we just received the head. */
- if (prev) {
- head = prev->next;
- fp = skb_clone(head, GFP_ATOMIC);
-
- if (!fp)
- goto out_oom;
-
- fp->next = head->next;
- if (!fp->next)
- fq->q.fragments_tail = fp;
- prev->next = fp;
-
- skb_morph(head, fq->q.fragments);
- head->next = fq->q.fragments->next;
-
- consume_skb(fq->q.fragments);
- fq->q.fragments = head;
- }
-
- WARN_ON(head == NULL);
- WARN_ON(head->ip_defrag_offset != 0);
+ reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail);
+ if (!reasm_data)
+ goto out_oom;
- /* Unfragmented part is taken from the first segment. */
- payload_len = ((head->data - skb_network_header(head)) -
+ payload_len = ((skb->data - skb_network_header(skb)) -
sizeof(struct ipv6hdr) + fq->q.len -
sizeof(struct frag_hdr));
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. */
- if (skb_has_frag_list(head)) {
- struct sk_buff *clone;
- int i, plen = 0;
-
- clone = alloc_skb(0, GFP_ATOMIC);
- if (!clone)
- goto out_oom;
- clone->next = head->next;
- head->next = clone;
- skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
- skb_frag_list_init(head);
- for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
- plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
- clone->len = clone->data_len = head->data_len - plen;
- head->data_len -= clone->len;
- head->len -= clone->len;
- clone->csum = 0;
- clone->ip_summed = head->ip_summed;
- add_frag_mem_limit(fq->q.net, clone->truesize);
- }
-
/* We have to remove fragment header from datagram and to relocate
* header in order to calculate ICV correctly. */
nhoff = fq->nhoffset;
- skb_network_header(head)[nhoff] = skb_transport_header(head)[0];
- memmove(head->head + sizeof(struct frag_hdr), head->head,
- (head->data - head->head) - sizeof(struct frag_hdr));
- if (skb_mac_header_was_set(head))
- head->mac_header += sizeof(struct frag_hdr);
- head->network_header += sizeof(struct frag_hdr);
-
- skb_reset_transport_header(head);
- skb_push(head, head->data - skb_network_header(head));
-
- sum_truesize = head->truesize;
- for (fp = head->next; fp;) {
- bool headstolen;
- int delta;
- struct sk_buff *next = fp->next;
-
- sum_truesize += fp->truesize;
- if (head->ip_summed != fp->ip_summed)
- head->ip_summed = CHECKSUM_NONE;
- else if (head->ip_summed == CHECKSUM_COMPLETE)
- head->csum = csum_add(head->csum, fp->csum);
-
- if (skb_try_coalesce(head, fp, &headstolen, &delta)) {
- kfree_skb_partial(fp, headstolen);
- } else {
- fp->sk = NULL;
- if (!skb_shinfo(head)->frag_list)
- skb_shinfo(head)->frag_list = fp;
- head->data_len += fp->len;
- head->len += fp->len;
- head->truesize += fp->truesize;
- }
- fp = next;
- }
- sub_frag_mem_limit(fq->q.net, sum_truesize);
+ skb_network_header(skb)[nhoff] = skb_transport_header(skb)[0];
+ memmove(skb->head + sizeof(struct frag_hdr), skb->head,
+ (skb->data - skb->head) - sizeof(struct frag_hdr));
+ if (skb_mac_header_was_set(skb))
+ skb->mac_header += sizeof(struct frag_hdr);
+ skb->network_header += sizeof(struct frag_hdr);
+
+ skb_reset_transport_header(skb);
+
+ inet_frag_reasm_finish(&fq->q, skb, reasm_data);
- skb_mark_not_on_list(head);
- head->dev = dev;
- head->tstamp = fq->q.stamp;
- ipv6_hdr(head)->payload_len = htons(payload_len);
- ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn);
- IP6CB(head)->nhoff = nhoff;
- IP6CB(head)->flags |= IP6SKB_FRAGMENTED;
- IP6CB(head)->frag_max_size = fq->q.max_size;
+ skb->dev = dev;
+ ipv6_hdr(skb)->payload_len = htons(payload_len);
+ ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn);
+ IP6CB(skb)->nhoff = nhoff;
+ IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
+ IP6CB(skb)->frag_max_size = fq->q.max_size;
/* Yes, and fold redundant checksum back. 8) */
- skb_postpush_rcsum(head, skb_network_header(head),
- skb_network_header_len(head));
+ skb_postpush_rcsum(skb, skb_network_header(skb),
+ skb_network_header_len(skb));
rcu_read_lock();
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
@@ -414,6 +307,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
fq->q.fragments = NULL;
fq->q.rb_fragments = RB_ROOT;
fq->q.fragments_tail = NULL;
+ fq->q.last_run_head = NULL;
return 1;
out_oversize:
@@ -464,10 +358,6 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
return 1;
}
- if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU &&
- fhdr->frag_off & htons(IP6_MF))
- goto fail_hdr;
-
iif = skb->dev ? skb->dev->ifindex : 0;
fq = fq_find(net, fhdr->identification, hdr, iif);
if (fq) {
@@ -485,6 +375,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
if (prob_offset) {
__IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
IPSTATS_MIB_INHDRERRORS);
+ /* icmpv6_param_prob() calls kfree_skb(skb) */
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset);
}
return ret;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 964491cf3672..87a0561136dd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2277,14 +2277,8 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
{
- bool from_set;
-
- rcu_read_lock();
- from_set = !!rcu_dereference(rt->from);
- rcu_read_unlock();
-
return !(rt->rt6i_flags & RTF_CACHE) &&
- (rt->rt6i_flags & RTF_PCPU || from_set);
+ (rt->rt6i_flags & RTF_PCPU || rcu_access_pointer(rt->from));
}
static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
@@ -4812,6 +4806,73 @@ int rt6_dump_route(struct fib6_info *rt, void *p_arg)
arg->cb->nlh->nlmsg_seq, flags);
}
+static int inet6_rtm_valid_getroute_req(struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack)
+{
+ struct rtmsg *rtm;
+ int i, err;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Invalid header for get route request");
+ return -EINVAL;
+ }
+
+ if (!netlink_strict_get_check(skb))
+ return nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX,
+ rtm_ipv6_policy, extack);
+
+ rtm = nlmsg_data(nlh);
+ if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) ||
+ (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) ||
+ rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope ||
+ rtm->rtm_type) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get route request");
+ return -EINVAL;
+ }
+ if (rtm->rtm_flags & ~RTM_F_FIB_MATCH) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Invalid flags for get route request");
+ return -EINVAL;
+ }
+
+ err = nlmsg_parse_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
+ rtm_ipv6_policy, extack);
+ if (err)
+ return err;
+
+ if ((tb[RTA_SRC] && !rtm->rtm_src_len) ||
+ (tb[RTA_DST] && !rtm->rtm_dst_len)) {
+ NL_SET_ERR_MSG_MOD(extack, "rtm_src_len and rtm_dst_len must be 128 for IPv6");
+ return -EINVAL;
+ }
+
+ for (i = 0; i <= RTA_MAX; i++) {
+ if (!tb[i])
+ continue;
+
+ switch (i) {
+ case RTA_SRC:
+ case RTA_DST:
+ case RTA_IIF:
+ case RTA_OIF:
+ case RTA_MARK:
+ case RTA_UID:
+ case RTA_SPORT:
+ case RTA_DPORT:
+ case RTA_IP_PROTO:
+ break;
+ default:
+ NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
@@ -4826,8 +4887,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
struct flowi6 fl6 = {};
bool fibmatch;
- err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy,
- extack);
+ err = inet6_rtm_valid_getroute_req(in_skb, nlh, tb, extack);
if (err < 0)
goto errout;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b81eb7cb815e..e51cda79f0cc 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1864,7 +1864,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
refcount_read(&sp->sk_refcnt), sp,
jiffies_to_clock_t(icsk->icsk_rto),
jiffies_to_clock_t(icsk->icsk_ack.ato),
- (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
+ (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sp),
tp->snd_cwnd,
state == TCP_LISTEN ?
fastopenq->max_qlen :