summaryrefslogtreecommitdiffstats
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/Kconfig35
-rw-r--r--net/ipv6/Makefile4
-rw-r--r--net/ipv6/addrconf.c169
-rw-r--r--net/ipv6/af_inet6.c18
-rw-r--r--net/ipv6/ah6.c5
-rw-r--r--net/ipv6/datagram.c10
-rw-r--r--net/ipv6/esp6.c7
-rw-r--r--net/ipv6/exthdrs.c268
-rw-r--r--net/ipv6/icmp.c13
-rw-r--r--net/ipv6/ila/ila_lwt.c92
-rw-r--r--net/ipv6/ila/ila_xlat.c43
-rw-r--r--net/ipv6/inet6_connection_sock.c2
-rw-r--r--net/ipv6/inet6_hashtables.c13
-rw-r--r--net/ipv6/ip6_gre.c6
-rw-r--r--net/ipv6/ip6_offload.c4
-rw-r--r--net/ipv6/ip6_output.c18
-rw-r--r--net/ipv6/ip6_tunnel.c27
-rw-r--r--net/ipv6/ip6_udp_tunnel.c3
-rw-r--r--net/ipv6/ip6_vti.c59
-rw-r--r--net/ipv6/ip6mr.c2
-rw-r--r--net/ipv6/ipcomp6.c5
-rw-r--r--net/ipv6/ipv6_sockglue.c21
-rw-r--r--net/ipv6/mcast.c17
-rw-r--r--net/ipv6/ndisc.c29
-rw-r--r--net/ipv6/netfilter.c1
-rw-r--r--net/ipv6/netfilter/Kconfig14
-rw-r--r--net/ipv6/netfilter/Makefile3
-rw-r--r--net/ipv6/netfilter/ip6_tables.c43
-rw-r--r--net/ipv6/netfilter/ip6t_MASQUERADE.c2
-rw-r--r--net/ipv6/netfilter/ip6t_REJECT.c23
-rw-r--r--net/ipv6/netfilter/ip6t_SYNPROXY.c8
-rw-r--r--net/ipv6/netfilter/ip6t_rpfilter.c3
-rw-r--r--net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c146
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c4
-rw-r--r--net/ipv6/netfilter/nf_defrag_ipv6_hooks.c44
-rw-r--r--net/ipv6/netfilter/nf_reject_ipv6.c1
-rw-r--r--net/ipv6/netfilter/nf_socket_ipv6.c151
-rw-r--r--net/ipv6/netfilter/nft_dup_ipv6.c8
-rw-r--r--net/ipv6/netfilter/nft_fib_ipv6.c275
-rw-r--r--net/ipv6/netfilter/nft_masq_ipv6.c14
-rw-r--r--net/ipv6/netfilter/nft_redir_ipv6.c14
-rw-r--r--net/ipv6/netfilter/nft_reject_ipv6.c6
-rw-r--r--net/ipv6/output_core.c2
-rw-r--r--net/ipv6/ping.c3
-rw-r--r--net/ipv6/raw.c10
-rw-r--r--net/ipv6/reassembly.c10
-rw-r--r--net/ipv6/route.c105
-rw-r--r--net/ipv6/seg6.c495
-rw-r--r--net/ipv6/seg6_hmac.c484
-rw-r--r--net/ipv6/seg6_iptunnel.c431
-rw-r--r--net/ipv6/sit.c16
-rw-r--r--net/ipv6/syncookies.c2
-rw-r--r--net/ipv6/tcp_ipv6.c28
-rw-r--r--net/ipv6/udp.c57
-rw-r--r--net/ipv6/udp_impl.h2
-rw-r--r--net/ipv6/udplite.c3
-rw-r--r--net/ipv6/xfrm6_tunnel.c2
57 files changed, 2898 insertions, 382 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 2343e4f2e0bf..ec1267e2bd1f 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -289,4 +289,39 @@ config IPV6_PIMSM_V2
Support for IPv6 PIM multicast routing protocol PIM-SMv2.
If unsure, say N.
+config IPV6_SEG6_LWTUNNEL
+ bool "IPv6: Segment Routing Header encapsulation support"
+ depends on IPV6
+ select LWTUNNEL
+ ---help---
+ Support for encapsulation of packets within an outer IPv6
+ header and a Segment Routing Header using the lightweight
+ tunnels mechanism.
+
+ If unsure, say N.
+
+config IPV6_SEG6_INLINE
+ bool "IPv6: direct Segment Routing Header insertion "
+ depends on IPV6_SEG6_LWTUNNEL
+ ---help---
+ Support for direct insertion of the Segment Routing Header,
+ also known as inline mode. Be aware that direct insertion of
+ extension headers (as opposed to encapsulation) may break
+ multiple mechanisms such as PMTUD or IPSec AH. Use this feature
+ only if you know exactly what you are doing.
+
+ If unsure, say N.
+
+config IPV6_SEG6_HMAC
+ bool "IPv6: Segment Routing HMAC support"
+ depends on IPV6
+ select CRYPTO_HMAC
+ select CRYPTO_SHA1
+ select CRYPTO_SHA256
+ ---help---
+ Support for HMAC signature generation and verification
+ of SR-enabled packets.
+
+ If unsure, say N.
+
endif # IPV6
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index c174ccb340a1..a9e9fec387ce 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -9,7 +9,7 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \
route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \
raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \
exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \
- udp_offload.o
+ udp_offload.o seg6.o
ipv6-offload := ip6_offload.o tcpv6_offload.o exthdrs_offload.o
@@ -23,6 +23,8 @@ ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o
ipv6-$(CONFIG_PROC_FS) += proc.o
ipv6-$(CONFIG_SYN_COOKIES) += syncookies.o
ipv6-$(CONFIG_NETLABEL) += calipso.o
+ipv6-$(CONFIG_IPV6_SEG6_LWTUNNEL) += seg6_iptunnel.o
+ipv6-$(CONFIG_IPV6_SEG6_HMAC) += seg6_hmac.o
ipv6-objs += $(ipv6-y)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d8983e15f859..c1e124bc8e1e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -147,9 +147,8 @@ static inline void addrconf_sysctl_unregister(struct inet6_dev *idev)
}
#endif
-static void __ipv6_regen_rndid(struct inet6_dev *idev);
-static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr);
-static void ipv6_regen_rndid(unsigned long data);
+static void ipv6_regen_rndid(struct inet6_dev *idev);
+static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr);
static int ipv6_generate_eui64(u8 *eui, struct net_device *dev);
static int ipv6_count_addresses(struct inet6_dev *idev);
@@ -184,7 +183,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
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);
+static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id);
static void addrconf_dad_run(struct inet6_dev *idev);
static void addrconf_rs_timer(unsigned long data);
static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
@@ -239,6 +238,11 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.use_oif_addrs_only = 0,
.ignore_routes_with_linkdown = 0,
.keep_addr_on_down = 0,
+ .seg6_enabled = 0,
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ .seg6_require_hmac = 0,
+#endif
+ .enhanced_dad = 1,
};
static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -285,6 +289,11 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.use_oif_addrs_only = 0,
.ignore_routes_with_linkdown = 0,
.keep_addr_on_down = 0,
+ .seg6_enabled = 0,
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ .seg6_require_hmac = 0,
+#endif
+ .enhanced_dad = 1,
};
/* Check if a valid qdisc is available */
@@ -409,9 +418,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
goto err_release;
}
- /* One reference from device. We must do this before
- * we invoke __ipv6_regen_rndid().
- */
+ /* One reference from device. */
in6_dev_hold(ndev);
if (dev->flags & (IFF_NOARP | IFF_LOOPBACK))
@@ -425,17 +432,15 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
#endif
INIT_LIST_HEAD(&ndev->tempaddr_list);
- setup_timer(&ndev->regen_timer, ipv6_regen_rndid, (unsigned long)ndev);
+ ndev->desync_factor = U32_MAX;
if ((dev->flags&IFF_LOOPBACK) ||
dev->type == ARPHRD_TUNNEL ||
dev->type == ARPHRD_TUNNEL6 ||
dev->type == ARPHRD_SIT ||
dev->type == ARPHRD_NONE) {
ndev->cnf.use_tempaddr = -1;
- } else {
- in6_dev_hold(ndev);
- ipv6_regen_rndid((unsigned long) ndev);
- }
+ } else
+ ipv6_regen_rndid(ndev);
ndev->token = in6addr_any;
@@ -447,7 +452,6 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
err = addrconf_sysctl_register(ndev);
if (err) {
ipv6_mc_destroy_dev(ndev);
- del_timer(&ndev->regen_timer);
snmp6_unregister_dev(ndev);
goto err_release;
}
@@ -1190,6 +1194,8 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i
int ret = 0;
u32 addr_flags;
unsigned long now = jiffies;
+ long max_desync_factor;
+ s32 cnf_temp_preferred_lft;
write_lock_bh(&idev->lock);
if (ift) {
@@ -1222,23 +1228,42 @@ retry:
}
in6_ifa_hold(ifp);
memcpy(addr.s6_addr, ifp->addr.s6_addr, 8);
- __ipv6_try_regen_rndid(idev, tmpaddr);
+ ipv6_try_regen_rndid(idev, tmpaddr);
memcpy(&addr.s6_addr[8], idev->rndid, 8);
age = (now - ifp->tstamp) / HZ;
+
+ regen_advance = idev->cnf.regen_max_retry *
+ idev->cnf.dad_transmits *
+ NEIGH_VAR(idev->nd_parms, RETRANS_TIME) / HZ;
+
+ /* recalculate max_desync_factor each time and update
+ * idev->desync_factor if it's larger
+ */
+ cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft);
+ max_desync_factor = min_t(__u32,
+ idev->cnf.max_desync_factor,
+ cnf_temp_preferred_lft - regen_advance);
+
+ if (unlikely(idev->desync_factor > max_desync_factor)) {
+ if (max_desync_factor > 0) {
+ get_random_bytes(&idev->desync_factor,
+ sizeof(idev->desync_factor));
+ idev->desync_factor %= max_desync_factor;
+ } else {
+ idev->desync_factor = 0;
+ }
+ }
+
tmp_valid_lft = min_t(__u32,
ifp->valid_lft,
idev->cnf.temp_valid_lft + age);
- tmp_prefered_lft = min_t(__u32,
- ifp->prefered_lft,
- idev->cnf.temp_prefered_lft + age -
- idev->cnf.max_desync_factor);
+ tmp_prefered_lft = cnf_temp_preferred_lft + age -
+ idev->desync_factor;
+ tmp_prefered_lft = min_t(__u32, ifp->prefered_lft, tmp_prefered_lft);
tmp_plen = ifp->prefix_len;
tmp_tstamp = ifp->tstamp;
spin_unlock_bh(&ifp->lock);
- regen_advance = idev->cnf.regen_max_retry *
- idev->cnf.dad_transmits *
- NEIGH_VAR(idev->nd_parms, RETRANS_TIME) / HZ;
write_unlock_bh(&idev->lock);
/* A temporary address is created only if this calculated Preferred
@@ -2150,7 +2175,7 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev)
}
/* (re)generation of randomized interface identifier (RFC 3041 3.2, 3.5) */
-static void __ipv6_regen_rndid(struct inet6_dev *idev)
+static void ipv6_regen_rndid(struct inet6_dev *idev)
{
regen:
get_random_bytes(idev->rndid, sizeof(idev->rndid));
@@ -2179,43 +2204,10 @@ regen:
}
}
-static void ipv6_regen_rndid(unsigned long data)
-{
- struct inet6_dev *idev = (struct inet6_dev *) data;
- unsigned long expires;
-
- rcu_read_lock_bh();
- write_lock_bh(&idev->lock);
-
- if (idev->dead)
- goto out;
-
- __ipv6_regen_rndid(idev);
-
- expires = jiffies +
- idev->cnf.temp_prefered_lft * HZ -
- idev->cnf.regen_max_retry * idev->cnf.dad_transmits *
- NEIGH_VAR(idev->nd_parms, RETRANS_TIME) -
- idev->cnf.max_desync_factor * HZ;
- if (time_before(expires, jiffies)) {
- pr_warn("%s: too short regeneration interval; timer disabled for %s\n",
- __func__, idev->dev->name);
- goto out;
- }
-
- if (!mod_timer(&idev->regen_timer, expires))
- in6_dev_hold(idev);
-
-out:
- write_unlock_bh(&idev->lock);
- rcu_read_unlock_bh();
- in6_dev_put(idev);
-}
-
-static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr)
+static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr)
{
if (tmpaddr && memcmp(idev->rndid, &tmpaddr->s6_addr[8], 8) == 0)
- __ipv6_regen_rndid(idev);
+ ipv6_regen_rndid(idev);
}
/*
@@ -2356,7 +2348,7 @@ static void manage_tempaddrs(struct inet6_dev *idev,
max_valid = 0;
max_prefered = idev->cnf.temp_prefered_lft -
- idev->cnf.max_desync_factor - age;
+ idev->desync_factor - age;
if (max_prefered < 0)
max_prefered = 0;
@@ -2916,6 +2908,7 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
spin_lock_bh(&ifp->lock);
ifp->flags &= ~IFA_F_TENTATIVE;
spin_unlock_bh(&ifp->lock);
+ rt_genid_bump_ipv6(dev_net(idev->dev));
ipv6_ifa_notify(RTM_NEWADDR, ifp);
in6_ifa_put(ifp);
}
@@ -3018,7 +3011,7 @@ static void init_loopback(struct net_device *dev)
* lo device down, release this obsolete dst and
* reallocate a new router for ifa.
*/
- if (sp_ifa->rt->dst.obsolete > 0) {
+ if (!atomic_read(&sp_ifa->rt->rt6i_ref)) {
ip6_rt_put(sp_ifa->rt);
sp_ifa->rt = NULL;
} else {
@@ -3594,9 +3587,6 @@ restart:
if (!how)
idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY);
- if (how && del_timer(&idev->regen_timer))
- in6_dev_put(idev);
-
/* Step 3: clear tempaddr list */
while (!list_empty(&idev->tempaddr_list)) {
ifa = list_first_entry(&idev->tempaddr_list,
@@ -3747,12 +3737,21 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp)
{
unsigned long rand_num;
struct inet6_dev *idev = ifp->idev;
+ u64 nonce;
if (ifp->flags & IFA_F_OPTIMISTIC)
rand_num = 0;
else
rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1);
+ nonce = 0;
+ if (idev->cnf.enhanced_dad ||
+ dev_net(idev->dev)->ipv6.devconf_all->enhanced_dad) {
+ do
+ get_random_bytes(&nonce, 6);
+ while (nonce == 0);
+ }
+ ifp->dad_nonce = nonce;
ifp->dad_probes = idev->cnf.dad_transmits;
addrconf_mod_dad_work(ifp, rand_num);
}
@@ -3761,7 +3760,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
{
struct inet6_dev *idev = ifp->idev;
struct net_device *dev = idev->dev;
- bool notify = false;
+ bool bump_id, notify = false;
addrconf_join_solict(dev, &ifp->addr);
@@ -3776,11 +3775,12 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
idev->cnf.accept_dad < 1 ||
!(ifp->flags&IFA_F_TENTATIVE) ||
ifp->flags & IFA_F_NODAD) {
+ bump_id = ifp->flags & IFA_F_TENTATIVE;
ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
spin_unlock(&ifp->lock);
read_unlock_bh(&idev->lock);
- addrconf_dad_completed(ifp);
+ addrconf_dad_completed(ifp, bump_id);
return;
}
@@ -3840,8 +3840,8 @@ static void addrconf_dad_work(struct work_struct *w)
struct inet6_ifaddr,
dad_work);
struct inet6_dev *idev = ifp->idev;
+ bool bump_id, disable_ipv6 = false;
struct in6_addr mcaddr;
- bool disable_ipv6 = false;
enum {
DAD_PROCESS,
@@ -3911,11 +3911,12 @@ static void addrconf_dad_work(struct work_struct *w)
* DAD was successful
*/
+ bump_id = ifp->flags & IFA_F_TENTATIVE;
ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
spin_unlock(&ifp->lock);
write_unlock_bh(&idev->lock);
- addrconf_dad_completed(ifp);
+ addrconf_dad_completed(ifp, bump_id);
goto out;
}
@@ -3928,7 +3929,8 @@ static void addrconf_dad_work(struct work_struct *w)
/* send a neighbour solicitation for our addr */
addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
- ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any);
+ ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any,
+ ifp->dad_nonce);
out:
in6_ifa_put(ifp);
rtnl_unlock();
@@ -3952,7 +3954,7 @@ static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp)
return true;
}
-static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
+static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id)
{
struct net_device *dev = ifp->idev->dev;
struct in6_addr lladdr;
@@ -4004,6 +4006,9 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
spin_unlock(&ifp->lock);
write_unlock_bh(&ifp->idev->lock);
}
+
+ if (bump_id)
+ rt_genid_bump_ipv6(dev_net(dev));
}
static void addrconf_dad_run(struct inet6_dev *idev)
@@ -4965,6 +4970,11 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast;
array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na;
array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down;
+ array[DEVCONF_SEG6_ENABLED] = cnf->seg6_enabled;
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ array[DEVCONF_SEG6_REQUIRE_HMAC] = cnf->seg6_require_hmac;
+#endif
+ array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad;
}
static inline size_t inet6_ifla6_size(void)
@@ -6057,6 +6067,29 @@ static const struct ctl_table addrconf_sysctl[] = {
},
{
+ .procname = "seg6_enabled",
+ .data = &ipv6_devconf.seg6_enabled,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ {
+ .procname = "seg6_require_hmac",
+ .data = &ipv6_devconf.seg6_require_hmac,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#endif
+ {
+ .procname = "enhanced_dad",
+ .data = &ipv6_devconf.enhanced_dad,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
/* sentinel */
}
};
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 46ad699937fd..237e654ba717 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -61,6 +61,7 @@
#include <net/ip6_tunnel.h>
#endif
#include <net/calipso.h>
+#include <net/seg6.h>
#include <asm/uaccess.h>
#include <linux/mroute6.h>
@@ -257,6 +258,14 @@ lookup_protocol:
goto out;
}
}
+
+ if (!kern) {
+ err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk);
+ if (err) {
+ sk_common_release(sk);
+ goto out;
+ }
+ }
out:
return err;
out_rcu_unlock:
@@ -678,6 +687,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = inet->inet_dport;
fl6.fl6_sport = inet->inet_sport;
+ fl6.flowi6_uid = sk->sk_uid;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
rcu_read_lock();
@@ -990,6 +1000,10 @@ static int __init inet6_init(void)
if (err)
goto calipso_fail;
+ err = seg6_init();
+ if (err)
+ goto seg6_fail;
+
#ifdef CONFIG_SYSCTL
err = ipv6_sysctl_register();
if (err)
@@ -1000,8 +1014,10 @@ out:
#ifdef CONFIG_SYSCTL
sysctl_fail:
- calipso_exit();
+ seg6_exit();
#endif
+seg6_fail:
+ calipso_exit();
calipso_fail:
pingv6_exit();
pingv6_fail:
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 0630a4d5daaa..189eb10b742d 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -662,9 +662,10 @@ static int ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 37874e2f30ed..0489e19258ad 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -54,6 +54,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
fl6->fl6_dport = inet->inet_dport;
fl6->fl6_sport = inet->inet_sport;
fl6->flowlabel = np->flow_label;
+ fl6->flowi6_uid = sk->sk_uid;
if (!fl6->flowi6_oif)
fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
@@ -139,7 +140,8 @@ void ip6_datagram_release_cb(struct sock *sk)
}
EXPORT_SYMBOL_GPL(ip6_datagram_release_cb);
-static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
+ int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
struct inet_sock *inet = inet_sk(sk);
@@ -252,6 +254,7 @@ ipv4_connected:
out:
return err;
}
+EXPORT_SYMBOL_GPL(__ip6_datagram_connect);
int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
@@ -715,6 +718,11 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6);
}
}
+ if (np->rxopt.bits.recvfragsize && opt->frag_max_size) {
+ int val = opt->frag_max_size;
+
+ put_cmsg(msg, SOL_IPV6, IPV6_RECVFRAGSIZE, sizeof(val), &val);
+ }
}
void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 060a60b2f8a6..cbcdd5db31f4 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -418,7 +418,7 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
esph = (void *)skb_push(skb, 4);
*seqhi = esph->spi;
esph->spi = esph->seq_no;
- esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi);
+ esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi;
aead_request_set_callback(req, 0, esp_input_done_esn, skb);
}
@@ -474,9 +474,10 @@ static int esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 139ceb68bd37..926818c331e5 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -47,6 +47,11 @@
#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/xfrm.h>
#endif
+#include <linux/seg6.h>
+#include <net/seg6.h>
+#ifdef CONFIG_IPV6_SEG6_HMAC
+#include <net/seg6_hmac.h>
+#endif
#include <linux/uaccess.h>
@@ -286,6 +291,182 @@ static int ipv6_destopt_rcv(struct sk_buff *skb)
return -1;
}
+static void seg6_update_csum(struct sk_buff *skb)
+{
+ struct ipv6_sr_hdr *hdr;
+ struct in6_addr *addr;
+ __be32 from, to;
+
+ /* srh is at transport offset and seg_left is already decremented
+ * but daddr is not yet updated with next segment
+ */
+
+ hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb);
+ addr = hdr->segments + hdr->segments_left;
+
+ hdr->segments_left++;
+ from = *(__be32 *)hdr;
+
+ hdr->segments_left--;
+ to = *(__be32 *)hdr;
+
+ /* update skb csum with diff resulting from seg_left decrement */
+
+ update_csum_diff4(skb, from, to);
+
+ /* compute csum diff between current and next segment and update */
+
+ update_csum_diff16(skb, (__be32 *)(&ipv6_hdr(skb)->daddr),
+ (__be32 *)addr);
+}
+
+static int ipv6_srh_rcv(struct sk_buff *skb)
+{
+ struct inet6_skb_parm *opt = IP6CB(skb);
+ struct net *net = dev_net(skb->dev);
+ struct ipv6_sr_hdr *hdr;
+ struct inet6_dev *idev;
+ struct in6_addr *addr;
+ bool cleanup = false;
+ int accept_seg6;
+
+ hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb);
+
+ idev = __in6_dev_get(skb->dev);
+
+ accept_seg6 = net->ipv6.devconf_all->seg6_enabled;
+ if (accept_seg6 > idev->cnf.seg6_enabled)
+ accept_seg6 = idev->cnf.seg6_enabled;
+
+ if (!accept_seg6) {
+ kfree_skb(skb);
+ return -1;
+ }
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ if (!seg6_hmac_validate_skb(skb)) {
+ kfree_skb(skb);
+ return -1;
+ }
+#endif
+
+looped_back:
+ if (hdr->segments_left > 0) {
+ if (hdr->nexthdr != NEXTHDR_IPV6 && hdr->segments_left == 1 &&
+ sr_has_cleanup(hdr))
+ cleanup = true;
+ } else {
+ if (hdr->nexthdr == NEXTHDR_IPV6) {
+ int offset = (hdr->hdrlen + 1) << 3;
+
+ skb_postpull_rcsum(skb, skb_network_header(skb),
+ skb_network_header_len(skb));
+
+ if (!pskb_pull(skb, offset)) {
+ kfree_skb(skb);
+ return -1;
+ }
+ skb_postpull_rcsum(skb, skb_transport_header(skb),
+ offset);
+
+ skb_reset_network_header(skb);
+ skb_reset_transport_header(skb);
+ skb->encapsulation = 0;
+
+ __skb_tunnel_rx(skb, skb->dev, net);
+
+ netif_rx(skb);
+ return -1;
+ }
+
+ opt->srcrt = skb_network_header_len(skb);
+ opt->lastopt = opt->srcrt;
+ skb->transport_header += (hdr->hdrlen + 1) << 3;
+ opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb);
+
+ return 1;
+ }
+
+ if (hdr->segments_left >= (hdr->hdrlen >> 1)) {
+ __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_INHDRERRORS);
+ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
+ ((&hdr->segments_left) -
+ skb_network_header(skb)));
+ kfree_skb(skb);
+ return -1;
+ }
+
+ if (skb_cloned(skb)) {
+ if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) {
+ __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_OUTDISCARDS);
+ kfree_skb(skb);
+ return -1;
+ }
+ }
+
+ hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb);
+
+ hdr->segments_left--;
+ addr = hdr->segments + hdr->segments_left;
+
+ skb_push(skb, sizeof(struct ipv6hdr));
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ seg6_update_csum(skb);
+
+ ipv6_hdr(skb)->daddr = *addr;
+
+ if (cleanup) {
+ int srhlen = (hdr->hdrlen + 1) << 3;
+ int nh = hdr->nexthdr;
+
+ skb_pull_rcsum(skb, sizeof(struct ipv6hdr) + srhlen);
+ memmove(skb_network_header(skb) + srhlen,
+ skb_network_header(skb),
+ (unsigned char *)hdr - skb_network_header(skb));
+ skb->network_header += srhlen;
+ ipv6_hdr(skb)->nexthdr = nh;
+ ipv6_hdr(skb)->payload_len = htons(skb->len -
+ sizeof(struct ipv6hdr));
+ skb_push_rcsum(skb, sizeof(struct ipv6hdr));
+ }
+
+ skb_dst_drop(skb);
+
+ ip6_route_input(skb);
+
+ if (skb_dst(skb)->error) {
+ dst_input(skb);
+ return -1;
+ }
+
+ if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) {
+ if (ipv6_hdr(skb)->hop_limit <= 1) {
+ __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_INHDRERRORS);
+ icmpv6_send(skb, ICMPV6_TIME_EXCEED,
+ ICMPV6_EXC_HOPLIMIT, 0);
+ kfree_skb(skb);
+ return -1;
+ }
+ ipv6_hdr(skb)->hop_limit--;
+
+ /* be sure that srh is still present before reinjecting */
+ if (!cleanup) {
+ skb_pull(skb, sizeof(struct ipv6hdr));
+ goto looped_back;
+ }
+ skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+ IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
+ }
+
+ dst_input(skb);
+
+ return -1;
+}
+
/********************************
Routing header.
********************************/
@@ -326,6 +507,10 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb)
return -1;
}
+ /* segment routing */
+ if (hdr->type == IPV6_SRCRT_TYPE_4)
+ return ipv6_srh_rcv(skb);
+
looped_back:
if (hdr->segments_left == 0) {
switch (hdr->type) {
@@ -679,9 +864,9 @@ int ipv6_parse_hopopts(struct sk_buff *skb)
* for headers.
*/
-static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto,
- struct ipv6_rt_hdr *opt,
- struct in6_addr **addr_p)
+static void ipv6_push_rthdr0(struct sk_buff *skb, u8 *proto,
+ struct ipv6_rt_hdr *opt,
+ struct in6_addr **addr_p, struct in6_addr *saddr)
{
struct rt0_hdr *phdr, *ihdr;
int hops;
@@ -704,6 +889,62 @@ static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto,
*proto = NEXTHDR_ROUTING;
}
+static void ipv6_push_rthdr4(struct sk_buff *skb, u8 *proto,
+ struct ipv6_rt_hdr *opt,
+ struct in6_addr **addr_p, struct in6_addr *saddr)
+{
+ struct ipv6_sr_hdr *sr_phdr, *sr_ihdr;
+ int plen, hops;
+
+ sr_ihdr = (struct ipv6_sr_hdr *)opt;
+ plen = (sr_ihdr->hdrlen + 1) << 3;
+
+ sr_phdr = (struct ipv6_sr_hdr *)skb_push(skb, plen);
+ memcpy(sr_phdr, sr_ihdr, sizeof(struct ipv6_sr_hdr));
+
+ hops = sr_ihdr->first_segment + 1;
+ memcpy(sr_phdr->segments + 1, sr_ihdr->segments + 1,
+ (hops - 1) * sizeof(struct in6_addr));
+
+ sr_phdr->segments[0] = **addr_p;
+ *addr_p = &sr_ihdr->segments[hops - 1];
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ if (sr_has_hmac(sr_phdr)) {
+ struct net *net = NULL;
+
+ if (skb->dev)
+ net = dev_net(skb->dev);
+ else if (skb->sk)
+ net = sock_net(skb->sk);
+
+ WARN_ON(!net);
+
+ if (net)
+ seg6_push_hmac(net, saddr, sr_phdr);
+ }
+#endif
+
+ sr_phdr->nexthdr = *proto;
+ *proto = NEXTHDR_ROUTING;
+}
+
+static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto,
+ struct ipv6_rt_hdr *opt,
+ struct in6_addr **addr_p, struct in6_addr *saddr)
+{
+ switch (opt->type) {
+ case IPV6_SRCRT_TYPE_0:
+ ipv6_push_rthdr0(skb, proto, opt, addr_p, saddr);
+ break;
+ case IPV6_SRCRT_TYPE_4:
+ ipv6_push_rthdr4(skb, proto, opt, addr_p, saddr);
+ break;
+ default:
+ break;
+ }
+}
+
static void ipv6_push_exthdr(struct sk_buff *skb, u8 *proto, u8 type, struct ipv6_opt_hdr *opt)
{
struct ipv6_opt_hdr *h = (struct ipv6_opt_hdr *)skb_push(skb, ipv6_optlen(opt));
@@ -715,10 +956,10 @@ static void ipv6_push_exthdr(struct sk_buff *skb, u8 *proto, u8 type, struct ipv
void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
u8 *proto,
- struct in6_addr **daddr)
+ struct in6_addr **daddr, struct in6_addr *saddr)
{
if (opt->srcrt) {
- ipv6_push_rthdr(skb, proto, opt->srcrt, daddr);
+ ipv6_push_rthdr(skb, proto, opt->srcrt, daddr, saddr);
/*
* IPV6_RTHDRDSTOPTS is ignored
* unless IPV6_RTHDR is set (RFC3542).
@@ -945,7 +1186,22 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
return NULL;
*orig = fl6->daddr;
- fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr;
+
+ switch (opt->srcrt->type) {
+ case IPV6_SRCRT_TYPE_0:
+ fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr;
+ break;
+ case IPV6_SRCRT_TYPE_4:
+ {
+ struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)opt->srcrt;
+
+ fl6->daddr = srh->segments[srh->first_segment];
+ break;
+ }
+ default:
+ return NULL;
+ }
+
return orig;
}
EXPORT_SYMBOL_GPL(fl6_update_dst);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index bd59c343d35f..17fa28f7a0ff 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -92,9 +92,10 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
struct net *net = dev_net(skb->dev);
if (type == ICMPV6_PKT_TOOBIG)
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
else if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
if (!(type & ICMPV6_INFOMSG_MASK))
if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
@@ -447,8 +448,10 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
if (__ipv6_addr_needs_scope_id(addr_type))
iif = skb->dev->ifindex;
- else
- iif = l3mdev_master_ifindex(skb->dev);
+ else {
+ dst = skb_dst(skb);
+ iif = l3mdev_master_ifindex(dst ? dst->dev : skb->dev);
+ }
/*
* Must not send error if the source does not uniquely
@@ -484,6 +487,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
fl6.flowi6_oif = iif;
fl6.fl6_icmp_type = type;
fl6.fl6_icmp_code = code;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
sk = icmpv6_xmit_lock(net);
@@ -658,6 +662,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
fl6.flowi6_oif = skb->dev->ifindex;
fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
fl6.flowi6_mark = mark;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
sk = icmpv6_xmit_lock(net);
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index e50c27a93e17..a7bc54ab46e2 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -6,29 +6,88 @@
#include <linux/socket.h>
#include <linux/types.h>
#include <net/checksum.h>
+#include <net/dst_cache.h>
#include <net/ip.h>
#include <net/ip6_fib.h>
+#include <net/ip6_route.h>
#include <net/lwtunnel.h>
#include <net/protocol.h>
#include <uapi/linux/ila.h>
#include "ila.h"
+struct ila_lwt {
+ struct ila_params p;
+ struct dst_cache dst_cache;
+ u32 connected : 1;
+};
+
+static inline struct ila_lwt *ila_lwt_lwtunnel(
+ struct lwtunnel_state *lwt)
+{
+ return (struct ila_lwt *)lwt->data;
+}
+
static inline struct ila_params *ila_params_lwtunnel(
- struct lwtunnel_state *lwstate)
+ struct lwtunnel_state *lwt)
{
- return (struct ila_params *)lwstate->data;
+ return &ila_lwt_lwtunnel(lwt)->p;
}
static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct dst_entry *dst = skb_dst(skb);
+ struct dst_entry *orig_dst = skb_dst(skb);
+ struct rt6_info *rt = (struct rt6_info *)orig_dst;
+ struct ila_lwt *ilwt = ila_lwt_lwtunnel(orig_dst->lwtstate);
+ struct dst_entry *dst;
+ int err = -EINVAL;
if (skb->protocol != htons(ETH_P_IPV6))
goto drop;
- ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), true);
+ ila_update_ipv6_locator(skb, ila_params_lwtunnel(orig_dst->lwtstate),
+ true);
- return dst->lwtstate->orig_output(net, sk, skb);
+ if (rt->rt6i_flags & (RTF_GATEWAY | RTF_CACHE)) {
+ /* Already have a next hop address in route, no need for
+ * dest cache route.
+ */
+ return orig_dst->lwtstate->orig_output(net, sk, skb);
+ }
+
+ dst = dst_cache_get(&ilwt->dst_cache);
+ if (unlikely(!dst)) {
+ struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ struct flowi6 fl6;
+
+ /* Lookup a route for the new destination. Take into
+ * account that the base route may already have a gateway.
+ */
+
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_oif = orig_dst->dev->ifindex;
+ fl6.flowi6_iif = LOOPBACK_IFINDEX;
+ fl6.daddr = *rt6_nexthop((struct rt6_info *)orig_dst,
+ &ip6h->daddr);
+
+ dst = ip6_route_output(net, NULL, &fl6);
+ if (dst->error) {
+ err = -EHOSTUNREACH;
+ dst_release(dst);
+ goto drop;
+ }
+
+ dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
+ if (IS_ERR(dst)) {
+ err = PTR_ERR(dst);
+ goto drop;
+ }
+
+ if (ilwt->connected)
+ dst_cache_set_ip6(&ilwt->dst_cache, dst, &fl6.saddr);
+ }
+
+ skb_dst_set(skb, dst);
+ return dst_output(net, sk, skb);
drop:
kfree_skb(skb);
@@ -60,9 +119,9 @@ static int ila_build_state(struct net_device *dev, struct nlattr *nla,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts)
{
+ struct ila_lwt *ilwt;
struct ila_params *p;
struct nlattr *tb[ILA_ATTR_MAX + 1];
- size_t encap_len = sizeof(*p);
struct lwtunnel_state *newts;
const struct fib6_config *cfg6 = cfg;
struct ila_addr *iaddr;
@@ -71,7 +130,7 @@ static int ila_build_state(struct net_device *dev, struct nlattr *nla,
if (family != AF_INET6)
return -EINVAL;
- if (cfg6->fc_dst_len < sizeof(struct ila_locator) + 1) {
+ if (cfg6->fc_dst_len < 8 * sizeof(struct ila_locator) + 3) {
/* Need to have full locator and at least type field
* included in destination
*/
@@ -95,11 +154,17 @@ static int ila_build_state(struct net_device *dev, struct nlattr *nla,
if (!tb[ILA_ATTR_LOCATOR])
return -EINVAL;
- newts = lwtunnel_state_alloc(encap_len);
+ newts = lwtunnel_state_alloc(sizeof(*ilwt));
if (!newts)
return -ENOMEM;
- newts->len = encap_len;
+ ilwt = ila_lwt_lwtunnel(newts);
+ ret = dst_cache_init(&ilwt->dst_cache, GFP_ATOMIC);
+ if (ret) {
+ kfree(newts);
+ return ret;
+ }
+
p = ila_params_lwtunnel(newts);
p->locator.v64 = (__force __be64)nla_get_u64(tb[ILA_ATTR_LOCATOR]);
@@ -120,11 +185,19 @@ static int ila_build_state(struct net_device *dev, struct nlattr *nla,
newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT |
LWTUNNEL_STATE_INPUT_REDIRECT;
+ if (cfg6->fc_dst_len == 8 * sizeof(struct in6_addr))
+ ilwt->connected = 1;
+
*ts = newts;
return 0;
}
+static void ila_destroy_state(struct lwtunnel_state *lwt)
+{
+ dst_cache_destroy(&ila_lwt_lwtunnel(lwt)->dst_cache);
+}
+
static int ila_fill_encap_info(struct sk_buff *skb,
struct lwtunnel_state *lwtstate)
{
@@ -159,6 +232,7 @@ static int ila_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
static const struct lwtunnel_encap_ops ila_encap_ops = {
.build_state = ila_build_state,
+ .destroy_state = ila_destroy_state,
.output = ila_output,
.input = ila_input,
.fill_encap = ila_fill_encap_info,
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index e604013dd814..af8f52ee7180 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -118,15 +118,7 @@ static const struct rhashtable_params rht_params = {
.obj_cmpfn = ila_cmpfn,
};
-static struct genl_family ila_nl_family = {
- .id = GENL_ID_GENERATE,
- .hdrsize = 0,
- .name = ILA_GENL_NAME,
- .version = ILA_GENL_VERSION,
- .maxattr = ILA_ATTR_MAX,
- .netnsok = true,
- .parallel_ops = true,
-};
+static struct genl_family ila_nl_family;
static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = {
[ILA_ATTR_LOCATOR] = { .type = NLA_U64, },
@@ -482,7 +474,15 @@ static int ila_nl_dump_start(struct netlink_callback *cb)
{
struct net *net = sock_net(cb->skb->sk);
struct ila_net *ilan = net_generic(net, ila_net_id);
- struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args;
+ struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0];
+
+ if (!iter) {
+ iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter)
+ return -ENOMEM;
+
+ cb->args[0] = (long)iter;
+ }
return rhashtable_walk_init(&ilan->rhash_table, &iter->rhiter,
GFP_KERNEL);
@@ -490,16 +490,18 @@ static int ila_nl_dump_start(struct netlink_callback *cb)
static int ila_nl_dump_done(struct netlink_callback *cb)
{
- struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args;
+ struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0];
rhashtable_walk_exit(&iter->rhiter);
+ kfree(iter);
+
return 0;
}
static int ila_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args;
+ struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0];
struct rhashtable_iter *rhiter = &iter->rhiter;
struct ila_map *ila;
int ret;
@@ -561,6 +563,18 @@ static const struct genl_ops ila_nl_ops[] = {
},
};
+static struct genl_family ila_nl_family __ro_after_init = {
+ .hdrsize = 0,
+ .name = ILA_GENL_NAME,
+ .version = ILA_GENL_VERSION,
+ .maxattr = ILA_ATTR_MAX,
+ .netnsok = true,
+ .parallel_ops = true,
+ .module = THIS_MODULE,
+ .ops = ila_nl_ops,
+ .n_ops = ARRAY_SIZE(ila_nl_ops),
+};
+
#define ILA_HASH_TABLE_SIZE 1024
static __net_init int ila_init_net(struct net *net)
@@ -623,7 +637,7 @@ static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral)
return 0;
}
-int ila_xlat_init(void)
+int __init ila_xlat_init(void)
{
int ret;
@@ -631,8 +645,7 @@ int ila_xlat_init(void)
if (ret)
goto exit;
- ret = genl_register_family_with_ops(&ila_nl_family,
- ila_nl_ops);
+ ret = genl_register_family(&ila_nl_family);
if (ret < 0)
goto unregister;
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 532c3ef282c5..1c86c478f578 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -88,6 +88,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
fl6->flowi6_mark = ireq->ir_mark;
fl6->fl6_dport = ireq->ir_rmt_port;
fl6->fl6_sport = htons(ireq->ir_num);
+ fl6->flowi6_uid = sk->sk_uid;
security_req_classify_flow(req, flowi6_to_flowi(fl6));
dst = ip6_dst_lookup_flow(sk, fl6, final_p);
@@ -136,6 +137,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
fl6->flowi6_mark = sk->sk_mark;
fl6->fl6_sport = inet->inet_sport;
fl6->fl6_dport = inet->inet_dport;
+ fl6->flowi6_uid = sk->sk_uid;
security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
rcu_read_lock();
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 00cf28ad4565..02761c9fe43e 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -96,7 +96,7 @@ EXPORT_SYMBOL(__inet6_lookup_established);
static inline int compute_score(struct sock *sk, struct net *net,
const unsigned short hnum,
const struct in6_addr *daddr,
- const int dif)
+ const int dif, bool exact_dif)
{
int score = -1;
@@ -109,7 +109,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score++;
}
- if (sk->sk_bound_dev_if) {
+ if (sk->sk_bound_dev_if || exact_dif) {
if (sk->sk_bound_dev_if != dif)
return -1;
score++;
@@ -131,11 +131,12 @@ struct sock *inet6_lookup_listener(struct net *net,
unsigned int hash = inet_lhashfn(net, hnum);
struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
int score, hiscore = 0, matches = 0, reuseport = 0;
+ bool exact_dif = inet6_exact_dif_match(net, skb);
struct sock *sk, *result = NULL;
u32 phash = 0;
sk_for_each(sk, &ilb->head) {
- score = compute_score(sk, net, hnum, daddr, dif);
+ score = compute_score(sk, net, hnum, daddr, dif, exact_dif);
if (score > hiscore) {
reuseport = sk->sk_reuseport;
if (reuseport) {
@@ -263,13 +264,15 @@ EXPORT_SYMBOL_GPL(inet6_hash_connect);
int inet6_hash(struct sock *sk)
{
+ int err = 0;
+
if (sk->sk_state != TCP_CLOSE) {
local_bh_disable();
- __inet_hash(sk, NULL, ipv6_rcv_saddr_equal);
+ err = __inet_hash(sk, NULL, ipv6_rcv_saddr_equal);
local_bh_enable();
}
- return 0;
+ return err;
}
EXPORT_SYMBOL_GPL(inet6_hash);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index d7d6d3ae0b3b..75b6108234dd 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -64,7 +64,7 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
#define IP6_GRE_HASH_SIZE_SHIFT 5
#define IP6_GRE_HASH_SIZE (1 << IP6_GRE_HASH_SIZE_SHIFT)
-static int ip6gre_net_id __read_mostly;
+static unsigned int ip6gre_net_id __read_mostly;
struct ip6gre_net {
struct ip6_tnl __rcu *tunnels[4][IP6_GRE_HASH_SIZE];
@@ -548,6 +548,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM));
if (err)
return -1;
@@ -602,6 +604,8 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
if (gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)))
return -1;
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index e7bfd55899a3..89c59e656f44 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -99,7 +99,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
segs = ops->callbacks.gso_segment(skb, features);
}
- if (IS_ERR(segs))
+ if (IS_ERR_OR_NULL(segs))
goto out;
gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
@@ -246,7 +246,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
skb_gro_postpull_rcsum(skb, iph, nlen);
- pp = ops->callbacks.gro_receive(head, skb);
+ pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
out_unlock:
rcu_read_unlock();
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6001e781164e..70d0de404197 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -39,6 +39,7 @@
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/bpf-cgroup.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
@@ -131,6 +132,14 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
+ int ret;
+
+ ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
+ if (ret) {
+ kfree_skb(skb);
+ return ret;
+ }
+
if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
dst_allfrag(skb_dst(skb)) ||
(IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
@@ -203,7 +212,8 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt->opt_nflen)
- ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
+ ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop,
+ &fl6->saddr);
}
skb_push(skb, sizeof(struct ipv6hdr));
@@ -624,7 +634,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
hroom = LL_RESERVED_SPACE(rt->dst.dev);
if (skb_has_frag_list(skb)) {
- int first_len = skb_pagelen(skb);
+ unsigned int first_len = skb_pagelen(skb);
struct sk_buff *frag2;
if (first_len - hlen > mtu ||
@@ -1366,7 +1376,7 @@ emsgsize:
if (((length > mtu) ||
(skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
- (rt->dst.dev->features & NETIF_F_UFO) &&
+ (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
(sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen, exthdrlen,
@@ -1672,7 +1682,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
if (opt && opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt && opt->opt_nflen)
- ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst);
+ ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst, &fl6->saddr);
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 6a66adba0c22..8b186b56183a 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -83,7 +83,7 @@ static int ip6_tnl_dev_init(struct net_device *dev);
static void ip6_tnl_dev_setup(struct net_device *dev);
static struct rtnl_link_ops ip6_link_ops __read_mostly;
-static int ip6_tnl_net_id __read_mostly;
+static unsigned int ip6_tnl_net_id __read_mostly;
struct ip6_tnl_net {
/* the IPv6 tunnel fallback device */
struct net_device *fb_tnl_dev;
@@ -157,6 +157,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
hash = HASH(&any, local);
for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
if (ipv6_addr_equal(local, &t->parms.laddr) &&
+ ipv6_addr_any(&t->parms.raddr) &&
(t->dev->flags & IFF_UP))
return t;
}
@@ -164,6 +165,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
hash = HASH(remote, &any);
for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
if (ipv6_addr_equal(remote, &t->parms.raddr) &&
+ ipv6_addr_any(&t->parms.laddr) &&
(t->dev->flags & IFF_UP))
return t;
}
@@ -1032,6 +1034,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
int mtu;
unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen;
unsigned int max_headroom = psh_hlen;
+ bool use_cache = false;
u8 hop_limit;
int err = -1;
@@ -1064,7 +1067,15 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
neigh_release(neigh);
- } else if (!fl6->flowi6_mark)
+ } else if (!(t->parms.flags &
+ (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) {
+ /* enable the cache only only if the routing decision does
+ * not depend on the current inner header value
+ */
+ use_cache = true;
+ }
+
+ if (use_cache)
dst = dst_cache_get(&t->dst_cache);
if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr))
@@ -1148,14 +1159,14 @@ route_lookup:
if (t->encap.type != TUNNEL_ENCAP_NONE)
goto tx_err_dst_release;
} else {
- if (!fl6->flowi6_mark && ndst)
+ if (use_cache && ndst)
dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr);
}
skb_dst_set(skb, dst);
if (encap_limit >= 0) {
init_tel_txopt(&opt, encap_limit);
- ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
+ ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL, NULL);
}
/* Calculate max headroom for all the headers and adjust
@@ -1237,6 +1248,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
fl6.flowi6_mark = skb->mark;
}
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
@@ -1315,6 +1328,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
fl6.flowi6_mark = skb->mark;
}
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
@@ -1634,7 +1649,7 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
struct ip6_tnl *tnl = netdev_priv(dev);
if (tnl->parms.proto == IPPROTO_IPIP) {
- if (new_mtu < 68)
+ if (new_mtu < ETH_MIN_MTU)
return -EINVAL;
} else {
if (new_mtu < IPV6_MIN_MTU)
@@ -1787,6 +1802,8 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
dev->mtu = ETH_DATA_LEN - t_hlen;
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
dev->mtu -= 8;
+ dev->min_mtu = ETH_MIN_MTU;
+ dev->max_mtu = 0xFFF8 - dev->hard_header_len;
return 0;
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index a7520528ecd2..b283f293ee4a 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -88,9 +88,6 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
uh->len = htons(skb->len);
- memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
- IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
- | IPSKB_REROUTED);
skb_dst_set(skb, dst);
udp6_set_csum(nocheck, skb, saddr, daddr, skb->len);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 8a02ca8a11af..f4b4a4a5f4ba 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -64,7 +64,7 @@ static int vti6_dev_init(struct net_device *dev);
static void vti6_dev_setup(struct net_device *dev);
static struct rtnl_link_ops vti6_link_ops __read_mostly;
-static int vti6_net_id __read_mostly;
+static unsigned int vti6_net_id __read_mostly;
struct vti6_net {
/* the vti6 tunnel fallback device */
struct net_device *fb_tnl_dev;
@@ -608,9 +608,10 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
@@ -812,30 +813,11 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
return err;
}
-/**
- * vti6_tnl_change_mtu - change mtu manually for tunnel device
- * @dev: virtual device associated with tunnel
- * @new_mtu: the new mtu
- *
- * Return:
- * 0 on success,
- * %-EINVAL if mtu too small
- **/
-static int vti6_change_mtu(struct net_device *dev, int new_mtu)
-{
- if (new_mtu < IPV6_MIN_MTU)
- return -EINVAL;
-
- dev->mtu = new_mtu;
- return 0;
-}
-
static const struct net_device_ops vti6_netdev_ops = {
.ndo_init = vti6_dev_init,
.ndo_uninit = vti6_dev_uninit,
.ndo_start_xmit = vti6_tnl_xmit,
.ndo_do_ioctl = vti6_ioctl,
- .ndo_change_mtu = vti6_change_mtu,
.ndo_get_stats64 = ip_tunnel_get_stats64,
.ndo_get_iflink = ip6_tnl_get_iflink,
};
@@ -855,6 +837,8 @@ static void vti6_dev_setup(struct net_device *dev)
dev->type = ARPHRD_TUNNEL6;
dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr);
dev->mtu = ETH_DATA_LEN;
+ dev->min_mtu = IPV6_MIN_MTU;
+ dev->max_mtu = IP_MAX_MTU;
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
netif_keep_dst(dev);
@@ -1138,6 +1122,33 @@ static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = {
.priority = 100,
};
+static bool is_vti6_tunnel(const struct net_device *dev)
+{
+ return dev->netdev_ops == &vti6_netdev_ops;
+}
+
+static int vti6_device_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct ip6_tnl *t = netdev_priv(dev);
+
+ if (!is_vti6_tunnel(dev))
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_DOWN:
+ if (!net_eq(t->net, dev_net(dev)))
+ xfrm_garbage_collect(t->net);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block vti6_notifier_block __read_mostly = {
+ .notifier_call = vti6_device_event,
+};
+
/**
* vti6_tunnel_init - register protocol and reserve needed resources
*
@@ -1148,6 +1159,8 @@ static int __init vti6_tunnel_init(void)
const char *msg;
int err;
+ register_netdevice_notifier(&vti6_notifier_block);
+
msg = "tunnel device";
err = register_pernet_device(&vti6_net_ops);
if (err < 0)
@@ -1180,6 +1193,7 @@ xfrm_proto_ah_failed:
xfrm_proto_esp_failed:
unregister_pernet_device(&vti6_net_ops);
pernet_dev_failed:
+ unregister_netdevice_notifier(&vti6_notifier_block);
pr_err("vti6 init: failed to register %s\n", msg);
return err;
}
@@ -1194,6 +1208,7 @@ static void __exit vti6_tunnel_cleanup(void)
xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
unregister_pernet_device(&vti6_net_ops);
+ unregister_netdevice_notifier(&vti6_notifier_block);
}
module_init(vti6_tunnel_init);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 7f4265b1649b..52101b37ad6e 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -636,7 +636,7 @@ static int pim6_rcv(struct sk_buff *skb)
goto drop;
pim = (struct pimreghdr *)skb_transport_header(skb);
- if (pim->type != ((PIM_VERSION << 4) | PIM_REGISTER) ||
+ if (pim->type != ((PIM_VERSION << 4) | PIM_TYPE_REGISTER) ||
(pim->flags & PIM_NULL_REGISTER) ||
(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
sizeof(*pim), IPPROTO_PIM,
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 1b9316e1386a..54d165b9845a 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -74,9 +74,10 @@ static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 5330262ab673..3ba530373560 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -52,6 +52,7 @@
#include <net/udplite.h>
#include <net/xfrm.h>
#include <net/compat.h>
+#include <net/seg6.h>
#include <asm/uaccess.h>
@@ -120,6 +121,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
static bool setsockopt_needs_rtnl(int optname)
{
switch (optname) {
+ case IPV6_ADDRFORM:
case IPV6_ADD_MEMBERSHIP:
case IPV6_DROP_MEMBERSHIP:
case IPV6_JOIN_ANYCAST:
@@ -198,7 +200,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
}
fl6_free_socklist(sk);
- ipv6_sock_mc_close(sk);
+ __ipv6_sock_mc_close(sk);
/*
* Sock is moving from IPv6 to IPv4 (sk_prot), so
@@ -429,6 +431,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
break;
#endif
+ case IPV6_SRCRT_TYPE_4:
+ {
+ struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)
+ opt->srcrt;
+
+ if (!seg6_validate_srh(srh, optlen))
+ goto sticky_done;
+ break;
+ }
default:
goto sticky_done;
}
@@ -867,6 +878,10 @@ pref_skip_coa:
np->autoflowlabel = valbool;
retv = 0;
break;
+ case IPV6_RECVFRAGSIZE:
+ np->rxopt.bits.recvfragsize = valbool;
+ retv = 0;
+ break;
}
release_sock(sk);
@@ -1309,6 +1324,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
val = np->autoflowlabel;
break;
+ case IPV6_RECVFRAGSIZE:
+ val = np->rxopt.bits.recvfragsize;
+ break;
+
default:
return -ENOPROTOOPT;
}
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 75c1fc54f188..14a3903f1c82 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -276,16 +276,14 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net,
return idev;
}
-void ipv6_sock_mc_close(struct sock *sk)
+void __ipv6_sock_mc_close(struct sock *sk)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_mc_socklist *mc_lst;
struct net *net = sock_net(sk);
- if (!rcu_access_pointer(np->ipv6_mc_list))
- return;
+ ASSERT_RTNL();
- rtnl_lock();
while ((mc_lst = rtnl_dereference(np->ipv6_mc_list)) != NULL) {
struct net_device *dev;
@@ -303,8 +301,17 @@ void ipv6_sock_mc_close(struct sock *sk)
atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc);
kfree_rcu(mc_lst, rcu);
-
}
+}
+
+void ipv6_sock_mc_close(struct sock *sk)
+{
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ if (!rcu_access_pointer(np->ipv6_mc_list))
+ return;
+ rtnl_lock();
+ __ipv6_sock_mc_close(sk);
rtnl_unlock();
}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index d8e671457d10..7ebac630d3c6 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -233,6 +233,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
case ND_OPT_SOURCE_LL_ADDR:
case ND_OPT_TARGET_LL_ADDR:
case ND_OPT_MTU:
+ case ND_OPT_NONCE:
case ND_OPT_REDIRECT_HDR:
if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) {
ND_PRINTK(2, warn,
@@ -568,7 +569,8 @@ static void ndisc_send_unsol_na(struct net_device *dev)
}
void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
- const struct in6_addr *daddr, const struct in6_addr *saddr)
+ const struct in6_addr *daddr, const struct in6_addr *saddr,
+ u64 nonce)
{
struct sk_buff *skb;
struct in6_addr addr_buf;
@@ -588,6 +590,8 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
if (inc_opt)
optlen += ndisc_opt_addr_space(dev,
NDISC_NEIGHBOUR_SOLICITATION);
+ if (nonce != 0)
+ optlen += 8;
skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
if (!skb)
@@ -605,6 +609,13 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
dev->dev_addr,
NDISC_NEIGHBOUR_SOLICITATION);
+ if (nonce != 0) {
+ u8 *opt = skb_put(skb, 8);
+
+ opt[0] = ND_OPT_NONCE;
+ opt[1] = 8 >> 3;
+ memcpy(opt + 2, &nonce, 6);
+ }
ndisc_send_skb(skb, daddr, saddr);
}
@@ -693,12 +704,12 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
"%s: trying to ucast probe in NUD_INVALID: %pI6\n",
__func__, target);
}
- ndisc_send_ns(dev, target, target, saddr);
+ ndisc_send_ns(dev, target, target, saddr, 0);
} else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) {
neigh_app_ns(neigh);
} else {
addrconf_addr_solict_mult(target, &mcaddr);
- ndisc_send_ns(dev, target, &mcaddr, saddr);
+ ndisc_send_ns(dev, target, &mcaddr, saddr, 0);
}
}
@@ -742,6 +753,7 @@ static void ndisc_recv_ns(struct sk_buff *skb)
int dad = ipv6_addr_any(saddr);
bool inc;
int is_router = -1;
+ u64 nonce = 0;
if (skb->len < sizeof(struct nd_msg)) {
ND_PRINTK(2, warn, "NS: packet too short\n");
@@ -786,6 +798,8 @@ static void ndisc_recv_ns(struct sk_buff *skb)
return;
}
}
+ if (ndopts.nd_opts_nonce)
+ memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6);
inc = ipv6_addr_is_multicast(daddr);
@@ -794,6 +808,15 @@ static void ndisc_recv_ns(struct sk_buff *skb)
have_ifp:
if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) {
if (dad) {
+ if (nonce != 0 && ifp->dad_nonce == nonce) {
+ u8 *np = (u8 *)&nonce;
+ /* Matching nonce if looped back */
+ ND_PRINTK(2, notice,
+ "%s: IPv6 DAD loopback for address %pI6c nonce %pM ignored\n",
+ ifp->idev->dev->name,
+ &ifp->addr, np);
+ goto out;
+ }
/*
* We are colliding with another node
* who is doing DAD
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index d11c46833d61..39970e212ad5 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -26,6 +26,7 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
struct flowi6 fl6 = {
.flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
.flowi6_mark = skb->mark,
+ .flowi6_uid = sock_net_uid(net, skb->sk),
.daddr = iph->daddr,
.saddr = iph->saddr,
};
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index e10a04c9cdc7..6acb2eecd986 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -25,6 +25,12 @@ config NF_CONNTRACK_IPV6
To compile it as a module, choose M here. If unsure, say N.
+config NF_SOCKET_IPV6
+ tristate "IPv6 socket lookup support"
+ help
+ This option enables the IPv6 socket lookup infrastructure. This
+ is used by the ip6tables socket match.
+
if NF_TABLES
config NF_TABLES_IPV6
@@ -54,6 +60,14 @@ config NFT_DUP_IPV6
help
This module enables IPv6 packet duplication support for nf_tables.
+config NFT_FIB_IPV6
+ tristate "nf_tables fib / ipv6 route lookup support"
+ select NFT_FIB
+ help
+ This module enables IPv6 FIB lookups, e.g. for reverse path filtering.
+ It also allows query of the FIB for the route type, e.g. local, unicast,
+ multicast or blackhole.
+
endif # NF_TABLES_IPV6
endif # NF_TABLES
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index b4f7d0b4e2af..fe180c96040e 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -24,6 +24,8 @@ obj-$(CONFIG_NF_NAT_MASQUERADE_IPV6) += nf_nat_masquerade_ipv6.o
nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
+obj-$(CONFIG_NF_SOCKET_IPV6) += nf_socket_ipv6.o
+
# logging
obj-$(CONFIG_NF_LOG_IPV6) += nf_log_ipv6.o
@@ -40,6 +42,7 @@ obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o
obj-$(CONFIG_NFT_REDIR_IPV6) += nft_redir_ipv6.o
obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
+obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o
# matches
obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 55aacea24396..d56d8ac09a94 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -291,11 +291,7 @@ ip6t_do_table(struct sk_buff *skb,
* rule is also a fragment-specific rule, non-fragments won't
* match it. */
acpar.hotdrop = false;
- acpar.net = state->net;
- acpar.in = state->in;
- acpar.out = state->out;
- acpar.family = NFPROTO_IPV6;
- acpar.hooknum = hook;
+ acpar.state = state;
IP_NF_ASSERT(table->valid_hooks & (1 << hook));
@@ -566,7 +562,8 @@ static int check_target(struct ip6t_entry *e, struct net *net, const char *name)
static int
find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
- unsigned int size)
+ unsigned int size,
+ struct xt_percpu_counter_alloc_state *alloc_state)
{
struct xt_entry_target *t;
struct xt_target *target;
@@ -574,12 +571,9 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
unsigned int j;
struct xt_mtchk_param mtpar;
struct xt_entry_match *ematch;
- unsigned long pcnt;
- pcnt = xt_percpu_counter_alloc();
- if (IS_ERR_VALUE(pcnt))
+ if (!xt_percpu_counter_alloc(alloc_state, &e->counters))
return -ENOMEM;
- e->counters.pcnt = pcnt;
j = 0;
mtpar.net = net;
@@ -616,7 +610,7 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
cleanup_match(ematch, net);
}
- xt_percpu_counter_free(e->counters.pcnt);
+ xt_percpu_counter_free(&e->counters);
return ret;
}
@@ -703,8 +697,7 @@ static void cleanup_entry(struct ip6t_entry *e, struct net *net)
if (par.target->destroy != NULL)
par.target->destroy(&par);
module_put(par.target->me);
-
- xt_percpu_counter_free(e->counters.pcnt);
+ xt_percpu_counter_free(&e->counters);
}
/* Checks and translates the user-supplied table segment (held in
@@ -713,6 +706,7 @@ static int
translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
const struct ip6t_replace *repl)
{
+ struct xt_percpu_counter_alloc_state alloc_state = { 0 };
struct ip6t_entry *iter;
unsigned int *offsets;
unsigned int i;
@@ -772,7 +766,8 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
/* Finally, each sanity check must pass */
i = 0;
xt_entry_foreach(iter, entry0, newinfo->size) {
- ret = find_check_entry(iter, net, repl->name, repl->size);
+ ret = find_check_entry(iter, net, repl->name, repl->size,
+ &alloc_state);
if (ret != 0)
break;
++i;
@@ -1007,7 +1002,7 @@ static int get_info(struct net *net, void __user *user,
#endif
t = try_then_request_module(xt_find_table_lock(net, AF_INET6, name),
"ip6table_%s", name);
- if (!IS_ERR_OR_NULL(t)) {
+ if (t) {
struct ip6t_getinfo info;
const struct xt_table_info *private = t->private;
#ifdef CONFIG_COMPAT
@@ -1037,7 +1032,7 @@ static int get_info(struct net *net, void __user *user,
xt_table_unlock(t);
module_put(t->me);
} else
- ret = t ? PTR_ERR(t) : -ENOENT;
+ ret = -ENOENT;
#ifdef CONFIG_COMPAT
if (compat)
xt_compat_unlock(AF_INET6);
@@ -1063,7 +1058,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr,
get.name[sizeof(get.name) - 1] = '\0';
t = xt_find_table_lock(net, AF_INET6, get.name);
- if (!IS_ERR_OR_NULL(t)) {
+ if (t) {
struct xt_table_info *private = t->private;
if (get.size == private->size)
ret = copy_entries_to_user(private->size,
@@ -1074,7 +1069,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr,
module_put(t->me);
xt_table_unlock(t);
} else
- ret = t ? PTR_ERR(t) : -ENOENT;
+ ret = -ENOENT;
return ret;
}
@@ -1099,8 +1094,8 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
t = try_then_request_module(xt_find_table_lock(net, AF_INET6, name),
"ip6table_%s", name);
- if (IS_ERR_OR_NULL(t)) {
- ret = t ? PTR_ERR(t) : -ENOENT;
+ if (!t) {
+ ret = -ENOENT;
goto free_newinfo_counters_untrans;
}
@@ -1214,8 +1209,8 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len,
if (IS_ERR(paddc))
return PTR_ERR(paddc);
t = xt_find_table_lock(net, AF_INET6, tmp.name);
- if (IS_ERR_OR_NULL(t)) {
- ret = t ? PTR_ERR(t) : -ENOENT;
+ if (!t) {
+ ret = -ENOENT;
goto free;
}
@@ -1651,7 +1646,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr,
xt_compat_lock(AF_INET6);
t = xt_find_table_lock(net, AF_INET6, get.name);
- if (!IS_ERR_OR_NULL(t)) {
+ if (t) {
const struct xt_table_info *private = t->private;
struct xt_table_info info;
ret = compat_table_info(private, &info);
@@ -1665,7 +1660,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr,
module_put(t->me);
xt_table_unlock(t);
} else
- ret = t ? PTR_ERR(t) : -ENOENT;
+ ret = -ENOENT;
xt_compat_unlock(AF_INET6);
return ret;
diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c
index 7f9f45d829d2..2b1a15846f9a 100644
--- a/net/ipv6/netfilter/ip6t_MASQUERADE.c
+++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c
@@ -24,7 +24,7 @@
static unsigned int
masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
- return nf_nat_masquerade_ipv6(skb, par->targinfo, par->out);
+ return nf_nat_masquerade_ipv6(skb, par->targinfo, xt_out(par));
}
static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index db29bbf41b59..fa51a205918d 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -39,35 +39,40 @@ static unsigned int
reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ip6t_reject_info *reject = par->targinfo;
- struct net *net = par->net;
+ struct net *net = xt_net(par);
switch (reject->with) {
case IP6T_ICMP6_NO_ROUTE:
- nf_send_unreach6(net, skb, ICMPV6_NOROUTE, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_NOROUTE, xt_hooknum(par));
break;
case IP6T_ICMP6_ADM_PROHIBITED:
- nf_send_unreach6(net, skb, ICMPV6_ADM_PROHIBITED, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_ADM_PROHIBITED,
+ xt_hooknum(par));
break;
case IP6T_ICMP6_NOT_NEIGHBOUR:
- nf_send_unreach6(net, skb, ICMPV6_NOT_NEIGHBOUR, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_NOT_NEIGHBOUR,
+ xt_hooknum(par));
break;
case IP6T_ICMP6_ADDR_UNREACH:
- nf_send_unreach6(net, skb, ICMPV6_ADDR_UNREACH, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_ADDR_UNREACH,
+ xt_hooknum(par));
break;
case IP6T_ICMP6_PORT_UNREACH:
- nf_send_unreach6(net, skb, ICMPV6_PORT_UNREACH, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_PORT_UNREACH,
+ xt_hooknum(par));
break;
case IP6T_ICMP6_ECHOREPLY:
/* Do nothing */
break;
case IP6T_TCP_RESET:
- nf_send_reset6(net, skb, par->hooknum);
+ nf_send_reset6(net, skb, xt_hooknum(par));
break;
case IP6T_ICMP6_POLICY_FAIL:
- nf_send_unreach6(net, skb, ICMPV6_POLICY_FAIL, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_POLICY_FAIL, xt_hooknum(par));
break;
case IP6T_ICMP6_REJECT_ROUTE:
- nf_send_unreach6(net, skb, ICMPV6_REJECT_ROUTE, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_REJECT_ROUTE,
+ xt_hooknum(par));
break;
}
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index 06bed74cf5ee..98c8dd38575a 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -277,12 +277,12 @@ static unsigned int
synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_synproxy_info *info = par->targinfo;
- struct net *net = par->net;
+ struct net *net = xt_net(par);
struct synproxy_net *snet = synproxy_pernet(net);
struct synproxy_options opts = {};
struct tcphdr *th, _th;
- if (nf_ip6_checksum(skb, par->hooknum, par->thoff, IPPROTO_TCP))
+ if (nf_ip6_checksum(skb, xt_hooknum(par), par->thoff, IPPROTO_TCP))
return NF_DROP;
th = skb_header_pointer(skb, par->thoff, sizeof(_th), &_th);
@@ -440,12 +440,12 @@ static int synproxy_tg6_check(const struct xt_tgchk_param *par)
e->ipv6.invflags & XT_INV_PROTO)
return -EINVAL;
- return nf_ct_l3proto_try_module_get(par->family);
+ return nf_ct_netns_get(par->net, par->family);
}
static void synproxy_tg6_destroy(const struct xt_tgdtor_param *par)
{
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
}
static struct xt_target synproxy_tg6_reg __read_mostly = {
diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c
index 1ee1b25df096..d5263dc364a9 100644
--- a/net/ipv6/netfilter/ip6t_rpfilter.c
+++ b/net/ipv6/netfilter/ip6t_rpfilter.c
@@ -93,7 +93,8 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
if (unlikely(saddrtype == IPV6_ADDR_ANY))
return true ^ invert; /* not routable: forward path will drop it */
- return rpfilter_lookup_reverse6(par->net, skb, par->in, info->flags) ^ invert;
+ return rpfilter_lookup_reverse6(xt_net(par), skb, xt_in(par),
+ info->flags) ^ invert;
}
static int rpfilter_check(const struct xt_mtchk_param *par)
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 963ee3848675..4e3402486833 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -34,6 +34,13 @@
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include <net/netfilter/nf_log.h>
+static int conntrack6_net_id;
+static DEFINE_MUTEX(register_ipv6_hooks);
+
+struct conntrack6_net {
+ unsigned int users;
+};
+
static bool ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
struct nf_conntrack_tuple *tuple)
{
@@ -308,6 +315,42 @@ static int ipv6_nlattr_tuple_size(void)
}
#endif
+static int ipv6_hooks_register(struct net *net)
+{
+ struct conntrack6_net *cnet = net_generic(net, conntrack6_net_id);
+ int err = 0;
+
+ mutex_lock(&register_ipv6_hooks);
+ cnet->users++;
+ if (cnet->users > 1)
+ goto out_unlock;
+
+ err = nf_defrag_ipv6_enable(net);
+ if (err < 0) {
+ cnet->users = 0;
+ goto out_unlock;
+ }
+
+ err = nf_register_net_hooks(net, ipv6_conntrack_ops,
+ ARRAY_SIZE(ipv6_conntrack_ops));
+ if (err)
+ cnet->users = 0;
+ out_unlock:
+ mutex_unlock(&register_ipv6_hooks);
+ return err;
+}
+
+static void ipv6_hooks_unregister(struct net *net)
+{
+ struct conntrack6_net *cnet = net_generic(net, conntrack6_net_id);
+
+ mutex_lock(&register_ipv6_hooks);
+ if (cnet->users && (--cnet->users == 0))
+ nf_unregister_net_hooks(net, ipv6_conntrack_ops,
+ ARRAY_SIZE(ipv6_conntrack_ops));
+ mutex_unlock(&register_ipv6_hooks);
+}
+
struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = {
.l3proto = PF_INET6,
.name = "ipv6",
@@ -321,6 +364,8 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = {
.nlattr_to_tuple = ipv6_nlattr_to_tuple,
.nla_policy = ipv6_nla_policy,
#endif
+ .net_ns_get = ipv6_hooks_register,
+ .net_ns_put = ipv6_hooks_unregister,
.me = THIS_MODULE,
};
@@ -336,52 +381,51 @@ static struct nf_sockopt_ops so_getorigdst6 = {
.owner = THIS_MODULE,
};
+static struct nf_conntrack_l4proto *builtin_l4proto6[] = {
+ &nf_conntrack_l4proto_tcp6,
+ &nf_conntrack_l4proto_udp6,
+ &nf_conntrack_l4proto_icmpv6,
+#ifdef CONFIG_NF_CT_PROTO_DCCP
+ &nf_conntrack_l4proto_dccp6,
+#endif
+#ifdef CONFIG_NF_CT_PROTO_SCTP
+ &nf_conntrack_l4proto_sctp6,
+#endif
+#ifdef CONFIG_NF_CT_PROTO_UDPLITE
+ &nf_conntrack_l4proto_udplite6,
+#endif
+};
+
static int ipv6_net_init(struct net *net)
{
int ret = 0;
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_tcp6);
- if (ret < 0) {
- pr_err("nf_conntrack_tcp6: pernet registration failed\n");
- goto out;
- }
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udp6);
- if (ret < 0) {
- pr_err("nf_conntrack_udp6: pernet registration failed\n");
- goto cleanup_tcp6;
- }
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_icmpv6);
- if (ret < 0) {
- pr_err("nf_conntrack_icmp6: pernet registration failed\n");
- goto cleanup_udp6;
- }
+ ret = nf_ct_l4proto_pernet_register(net, builtin_l4proto6,
+ ARRAY_SIZE(builtin_l4proto6));
+ if (ret < 0)
+ return ret;
+
ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv6);
if (ret < 0) {
pr_err("nf_conntrack_ipv6: pernet registration failed.\n");
- goto cleanup_icmpv6;
+ nf_ct_l4proto_pernet_unregister(net, builtin_l4proto6,
+ ARRAY_SIZE(builtin_l4proto6));
}
- return 0;
- cleanup_icmpv6:
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmpv6);
- cleanup_udp6:
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp6);
- cleanup_tcp6:
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp6);
- out:
return ret;
}
static void ipv6_net_exit(struct net *net)
{
nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv6);
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmpv6);
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp6);
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp6);
+ nf_ct_l4proto_pernet_unregister(net, builtin_l4proto6,
+ ARRAY_SIZE(builtin_l4proto6));
}
static struct pernet_operations ipv6_net_ops = {
.init = ipv6_net_init,
.exit = ipv6_net_exit,
+ .id = &conntrack6_net_id,
+ .size = sizeof(struct conntrack6_net),
};
static int __init nf_conntrack_l3proto_ipv6_init(void)
@@ -389,7 +433,6 @@ static int __init nf_conntrack_l3proto_ipv6_init(void)
int ret = 0;
need_conntrack();
- nf_defrag_ipv6_enable();
ret = nf_register_sockopt(&so_getorigdst6);
if (ret < 0) {
@@ -401,47 +444,20 @@ static int __init nf_conntrack_l3proto_ipv6_init(void)
if (ret < 0)
goto cleanup_sockopt;
- ret = nf_register_hooks(ipv6_conntrack_ops,
- ARRAY_SIZE(ipv6_conntrack_ops));
- if (ret < 0) {
- pr_err("nf_conntrack_ipv6: can't register pre-routing defrag "
- "hook.\n");
+ ret = nf_ct_l4proto_register(builtin_l4proto6,
+ ARRAY_SIZE(builtin_l4proto6));
+ if (ret < 0)
goto cleanup_pernet;
- }
-
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp6);
- if (ret < 0) {
- pr_err("nf_conntrack_ipv6: can't register tcp6 proto.\n");
- goto cleanup_hooks;
- }
-
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp6);
- if (ret < 0) {
- pr_err("nf_conntrack_ipv6: can't register udp6 proto.\n");
- goto cleanup_tcp6;
- }
-
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_icmpv6);
- if (ret < 0) {
- pr_err("nf_conntrack_ipv6: can't register icmpv6 proto.\n");
- goto cleanup_udp6;
- }
ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv6);
if (ret < 0) {
pr_err("nf_conntrack_ipv6: can't register ipv6 proto.\n");
- goto cleanup_icmpv6;
+ goto cleanup_l4proto;
}
return ret;
-
- cleanup_icmpv6:
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmpv6);
- cleanup_udp6:
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6);
- cleanup_tcp6:
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6);
- cleanup_hooks:
- nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops));
+cleanup_l4proto:
+ nf_ct_l4proto_unregister(builtin_l4proto6,
+ ARRAY_SIZE(builtin_l4proto6));
cleanup_pernet:
unregister_pernet_subsys(&ipv6_net_ops);
cleanup_sockopt:
@@ -453,10 +469,8 @@ static void __exit nf_conntrack_l3proto_ipv6_fini(void)
{
synchronize_net();
nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv6);
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6);
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6);
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmpv6);
- nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops));
+ nf_ct_l4proto_unregister(builtin_l4proto6,
+ ARRAY_SIZE(builtin_l4proto6));
unregister_pernet_subsys(&ipv6_net_ops);
nf_unregister_sockopt(&so_getorigdst6);
}
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index e4347aeb2e65..9948b5ce52da 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -576,11 +576,11 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
/* Jumbo payload inhibits frag. header */
if (ipv6_hdr(skb)->payload_len == 0) {
pr_debug("payload len = 0\n");
- return -EINVAL;
+ return 0;
}
if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0)
- return -EINVAL;
+ return 0;
if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr)))
return -ENOMEM;
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index f7aab5ab93a5..8e0bdd058787 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -30,6 +30,8 @@
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+static DEFINE_MUTEX(defrag6_mutex);
+
static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
struct sk_buff *skb)
{
@@ -69,7 +71,7 @@ static unsigned int ipv6_defrag(void *priv,
if (err == -EINPROGRESS)
return NF_STOLEN;
- return NF_ACCEPT;
+ return err == 0 ? NF_ACCEPT : NF_DROP;
}
static struct nf_hook_ops ipv6_defrag_ops[] = {
@@ -87,6 +89,19 @@ static struct nf_hook_ops ipv6_defrag_ops[] = {
},
};
+static void __net_exit defrag6_net_exit(struct net *net)
+{
+ if (net->nf.defrag_ipv6) {
+ nf_unregister_net_hooks(net, ipv6_defrag_ops,
+ ARRAY_SIZE(ipv6_defrag_ops));
+ net->nf.defrag_ipv6 = false;
+ }
+}
+
+static struct pernet_operations defrag6_net_ops = {
+ .exit = defrag6_net_exit,
+};
+
static int __init nf_defrag_init(void)
{
int ret = 0;
@@ -96,9 +111,9 @@ static int __init nf_defrag_init(void)
pr_err("nf_defrag_ipv6: can't initialize frag6.\n");
return ret;
}
- ret = nf_register_hooks(ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops));
+ ret = register_pernet_subsys(&defrag6_net_ops);
if (ret < 0) {
- pr_err("nf_defrag_ipv6: can't register hooks\n");
+ pr_err("nf_defrag_ipv6: can't register pernet ops\n");
goto cleanup_frag6;
}
return ret;
@@ -111,12 +126,31 @@ cleanup_frag6:
static void __exit nf_defrag_fini(void)
{
- nf_unregister_hooks(ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops));
+ unregister_pernet_subsys(&defrag6_net_ops);
nf_ct_frag6_cleanup();
}
-void nf_defrag_ipv6_enable(void)
+int nf_defrag_ipv6_enable(struct net *net)
{
+ int err = 0;
+
+ might_sleep();
+
+ if (net->nf.defrag_ipv6)
+ return 0;
+
+ mutex_lock(&defrag6_mutex);
+ if (net->nf.defrag_ipv6)
+ goto out_unlock;
+
+ err = nf_register_net_hooks(net, ipv6_defrag_ops,
+ ARRAY_SIZE(ipv6_defrag_ops));
+ if (err == 0)
+ net->nf.defrag_ipv6 = true;
+
+ out_unlock:
+ mutex_unlock(&defrag6_mutex);
+ return err;
}
EXPORT_SYMBOL_GPL(nf_defrag_ipv6_enable);
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index a5400223fd74..10090400c72f 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -156,6 +156,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
fl6.daddr = oip6h->saddr;
fl6.fl6_sport = otcph->dest;
fl6.fl6_dport = otcph->source;
+ fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev);
security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
new file mode 100644
index 000000000000..ebb2bf84232a
--- /dev/null
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -0,0 +1,151 @@
+/*
+ * Copyright (C) 2007-2008 BalaBit IT Ltd.
+ * Author: Krisztian Kovacs
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <net/tcp.h>
+#include <net/udp.h>
+#include <net/icmp.h>
+#include <net/sock.h>
+#include <net/inet_sock.h>
+#include <net/inet6_hashtables.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+#include <net/netfilter/nf_socket.h>
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack.h>
+#endif
+
+static int
+extract_icmp6_fields(const struct sk_buff *skb,
+ unsigned int outside_hdrlen,
+ int *protocol,
+ const struct in6_addr **raddr,
+ const struct in6_addr **laddr,
+ __be16 *rport,
+ __be16 *lport,
+ struct ipv6hdr *ipv6_var)
+{
+ const struct ipv6hdr *inside_iph;
+ struct icmp6hdr *icmph, _icmph;
+ __be16 *ports, _ports[2];
+ u8 inside_nexthdr;
+ __be16 inside_fragoff;
+ int inside_hdrlen;
+
+ icmph = skb_header_pointer(skb, outside_hdrlen,
+ sizeof(_icmph), &_icmph);
+ if (icmph == NULL)
+ return 1;
+
+ if (icmph->icmp6_type & ICMPV6_INFOMSG_MASK)
+ return 1;
+
+ inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph),
+ sizeof(*ipv6_var), ipv6_var);
+ if (inside_iph == NULL)
+ return 1;
+ inside_nexthdr = inside_iph->nexthdr;
+
+ inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) +
+ sizeof(*ipv6_var),
+ &inside_nexthdr, &inside_fragoff);
+ if (inside_hdrlen < 0)
+ return 1; /* hjm: Packet has no/incomplete transport layer headers. */
+
+ if (inside_nexthdr != IPPROTO_TCP &&
+ inside_nexthdr != IPPROTO_UDP)
+ return 1;
+
+ ports = skb_header_pointer(skb, inside_hdrlen,
+ sizeof(_ports), &_ports);
+ if (ports == NULL)
+ return 1;
+
+ /* the inside IP packet is the one quoted from our side, thus
+ * its saddr is the local address */
+ *protocol = inside_nexthdr;
+ *laddr = &inside_iph->saddr;
+ *lport = ports[0];
+ *raddr = &inside_iph->daddr;
+ *rport = ports[1];
+
+ return 0;
+}
+
+static struct sock *
+nf_socket_get_sock_v6(struct net *net, struct sk_buff *skb, int doff,
+ const u8 protocol,
+ const struct in6_addr *saddr, const struct in6_addr *daddr,
+ const __be16 sport, const __be16 dport,
+ const struct net_device *in)
+{
+ switch (protocol) {
+ case IPPROTO_TCP:
+ return inet6_lookup(net, &tcp_hashinfo, skb, doff,
+ saddr, sport, daddr, dport,
+ in->ifindex);
+ case IPPROTO_UDP:
+ return udp6_lib_lookup(net, saddr, sport, daddr, dport,
+ in->ifindex);
+ }
+
+ return NULL;
+}
+
+struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
+ const struct net_device *indev)
+{
+ __be16 uninitialized_var(dport), uninitialized_var(sport);
+ const struct in6_addr *daddr = NULL, *saddr = NULL;
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+ struct sk_buff *data_skb = NULL;
+ int doff = 0;
+ int thoff = 0, tproto;
+
+ tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
+ if (tproto < 0) {
+ pr_debug("unable to find transport header in IPv6 packet, dropping\n");
+ return NULL;
+ }
+
+ if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) {
+ struct udphdr _hdr, *hp;
+
+ hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
+ if (hp == NULL)
+ return NULL;
+
+ saddr = &iph->saddr;
+ sport = hp->source;
+ daddr = &iph->daddr;
+ dport = hp->dest;
+ data_skb = (struct sk_buff *)skb;
+ doff = tproto == IPPROTO_TCP ?
+ thoff + __tcp_hdrlen((struct tcphdr *)hp) :
+ thoff + sizeof(*hp);
+
+ } else if (tproto == IPPROTO_ICMPV6) {
+ struct ipv6hdr ipv6_var;
+
+ if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr,
+ &sport, &dport, &ipv6_var))
+ return NULL;
+ } else {
+ return NULL;
+ }
+
+ return nf_socket_get_sock_v6(net, data_skb, doff, tproto, saddr, daddr,
+ sport, dport, indev);
+}
+EXPORT_SYMBOL_GPL(nf_sk_lookup_slow_v6);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Krisztian Kovacs, Balazs Scheidler");
+MODULE_DESCRIPTION("Netfilter IPv6 socket lookup infrastructure");
diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c
index 8bfd470cbe72..d8b5b60b7d53 100644
--- a/net/ipv6/netfilter/nft_dup_ipv6.c
+++ b/net/ipv6/netfilter/nft_dup_ipv6.c
@@ -26,9 +26,9 @@ static void nft_dup_ipv6_eval(const struct nft_expr *expr,
{
struct nft_dup_ipv6 *priv = nft_expr_priv(expr);
struct in6_addr *gw = (struct in6_addr *)&regs->data[priv->sreg_addr];
- int oif = regs->data[priv->sreg_dev];
+ int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1;
- nf_dup_ipv6(pkt->net, pkt->skb, pkt->hook, gw, oif);
+ nf_dup_ipv6(nft_net(pkt), pkt->skb, nft_hook(pkt), gw, oif);
}
static int nft_dup_ipv6_init(const struct nft_ctx *ctx,
@@ -57,7 +57,9 @@ static int nft_dup_ipv6_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
struct nft_dup_ipv6 *priv = nft_expr_priv(expr);
- if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) ||
+ if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr))
+ goto nla_put_failure;
+ if (priv->sreg_dev &&
nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev))
goto nla_put_failure;
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
new file mode 100644
index 000000000000..c947aad8bcc6
--- /dev/null
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -0,0 +1,275 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <linux/netfilter_ipv6.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_fib.h>
+
+#include <net/ip6_fib.h>
+#include <net/ip6_route.h>
+
+static bool fib6_is_local(const struct sk_buff *skb)
+{
+ const struct rt6_info *rt = (const void *)skb_dst(skb);
+
+ return rt && (rt->rt6i_flags & RTF_LOCAL);
+}
+
+static int get_ifindex(const struct net_device *dev)
+{
+ return dev ? dev->ifindex : 0;
+}
+
+static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv,
+ const struct nft_pktinfo *pkt,
+ const struct net_device *dev)
+{
+ const struct ipv6hdr *iph = ipv6_hdr(pkt->skb);
+ int lookup_flags = 0;
+
+ if (priv->flags & NFTA_FIB_F_DADDR) {
+ fl6->daddr = iph->daddr;
+ fl6->saddr = iph->saddr;
+ } else {
+ fl6->daddr = iph->saddr;
+ fl6->saddr = iph->daddr;
+ }
+
+ if (ipv6_addr_type(&fl6->daddr) & IPV6_ADDR_LINKLOCAL) {
+ lookup_flags |= RT6_LOOKUP_F_IFACE;
+ fl6->flowi6_oif = get_ifindex(dev ? dev : pkt->skb->dev);
+ }
+
+ if (ipv6_addr_type(&fl6->saddr) & IPV6_ADDR_UNICAST)
+ lookup_flags |= RT6_LOOKUP_F_HAS_SADDR;
+
+ if (priv->flags & NFTA_FIB_F_MARK)
+ fl6->flowi6_mark = pkt->skb->mark;
+
+ fl6->flowlabel = (*(__be32 *)iph) & IPV6_FLOWINFO_MASK;
+
+ return lookup_flags;
+}
+
+static u32 __nft_fib6_eval_type(const struct nft_fib *priv,
+ const struct nft_pktinfo *pkt)
+{
+ const struct net_device *dev = NULL;
+ const struct nf_ipv6_ops *v6ops;
+ const struct nf_afinfo *afinfo;
+ int route_err, addrtype;
+ struct rt6_info *rt;
+ struct flowi6 fl6 = {
+ .flowi6_iif = LOOPBACK_IFINDEX,
+ .flowi6_proto = pkt->tprot,
+ };
+ u32 ret = 0;
+
+ afinfo = nf_get_afinfo(NFPROTO_IPV6);
+ if (!afinfo)
+ return RTN_UNREACHABLE;
+
+ if (priv->flags & NFTA_FIB_F_IIF)
+ dev = nft_in(pkt);
+ else if (priv->flags & NFTA_FIB_F_OIF)
+ dev = nft_out(pkt);
+
+ nft_fib6_flowi_init(&fl6, priv, pkt, dev);
+
+ v6ops = nf_get_ipv6_ops();
+ if (dev && v6ops && v6ops->chk_addr(nft_net(pkt), &fl6.daddr, dev, true))
+ ret = RTN_LOCAL;
+
+ route_err = afinfo->route(nft_net(pkt), (struct dst_entry **)&rt,
+ flowi6_to_flowi(&fl6), false);
+ if (route_err)
+ goto err;
+
+ if (rt->rt6i_flags & RTF_REJECT) {
+ route_err = rt->dst.error;
+ dst_release(&rt->dst);
+ goto err;
+ }
+
+ if (ipv6_anycast_destination((struct dst_entry *)rt, &fl6.daddr))
+ ret = RTN_ANYCAST;
+ else if (!dev && rt->rt6i_flags & RTF_LOCAL)
+ ret = RTN_LOCAL;
+
+ dst_release(&rt->dst);
+
+ if (ret)
+ return ret;
+
+ addrtype = ipv6_addr_type(&fl6.daddr);
+
+ if (addrtype & IPV6_ADDR_MULTICAST)
+ return RTN_MULTICAST;
+ if (addrtype & IPV6_ADDR_UNICAST)
+ return RTN_UNICAST;
+
+ return RTN_UNSPEC;
+ err:
+ switch (route_err) {
+ case -EINVAL:
+ return RTN_BLACKHOLE;
+ case -EACCES:
+ return RTN_PROHIBIT;
+ case -EAGAIN:
+ return RTN_THROW;
+ default:
+ break;
+ }
+
+ return RTN_UNREACHABLE;
+}
+
+void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_fib *priv = nft_expr_priv(expr);
+ u32 *dest = &regs->data[priv->dreg];
+
+ *dest = __nft_fib6_eval_type(priv, pkt);
+}
+EXPORT_SYMBOL_GPL(nft_fib6_eval_type);
+
+void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_fib *priv = nft_expr_priv(expr);
+ const struct net_device *oif = NULL;
+ u32 *dest = &regs->data[priv->dreg];
+ struct flowi6 fl6 = {
+ .flowi6_iif = LOOPBACK_IFINDEX,
+ .flowi6_proto = pkt->tprot,
+ };
+ struct rt6_info *rt;
+ int lookup_flags;
+
+ if (priv->flags & NFTA_FIB_F_IIF)
+ oif = nft_in(pkt);
+ else if (priv->flags & NFTA_FIB_F_OIF)
+ oif = nft_out(pkt);
+
+ lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif);
+
+ if (nft_hook(pkt) == NF_INET_PRE_ROUTING && fib6_is_local(pkt->skb)) {
+ nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX);
+ return;
+ }
+
+ *dest = 0;
+ again:
+ rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, lookup_flags);
+ if (rt->dst.error)
+ goto put_rt_err;
+
+ /* Should not see RTF_LOCAL here */
+ if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL))
+ goto put_rt_err;
+
+ if (oif && oif != rt->rt6i_idev->dev) {
+ /* multipath route? Try again with F_IFACE */
+ if ((lookup_flags & RT6_LOOKUP_F_IFACE) == 0) {
+ lookup_flags |= RT6_LOOKUP_F_IFACE;
+ fl6.flowi6_oif = oif->ifindex;
+ ip6_rt_put(rt);
+ goto again;
+ }
+ }
+
+ switch (priv->result) {
+ case NFT_FIB_RESULT_OIF:
+ *dest = rt->rt6i_idev->dev->ifindex;
+ break;
+ case NFT_FIB_RESULT_OIFNAME:
+ strncpy((char *)dest, rt->rt6i_idev->dev->name, IFNAMSIZ);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ break;
+ }
+
+ put_rt_err:
+ ip6_rt_put(rt);
+}
+EXPORT_SYMBOL_GPL(nft_fib6_eval);
+
+static struct nft_expr_type nft_fib6_type;
+
+static const struct nft_expr_ops nft_fib6_type_ops = {
+ .type = &nft_fib6_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)),
+ .eval = nft_fib6_eval_type,
+ .init = nft_fib_init,
+ .dump = nft_fib_dump,
+ .validate = nft_fib_validate,
+};
+
+static const struct nft_expr_ops nft_fib6_ops = {
+ .type = &nft_fib6_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)),
+ .eval = nft_fib6_eval,
+ .init = nft_fib_init,
+ .dump = nft_fib_dump,
+ .validate = nft_fib_validate,
+};
+
+static const struct nft_expr_ops *
+nft_fib6_select_ops(const struct nft_ctx *ctx,
+ const struct nlattr * const tb[])
+{
+ enum nft_fib_result result;
+
+ if (!tb[NFTA_FIB_RESULT])
+ return ERR_PTR(-EINVAL);
+
+ result = ntohl(nla_get_be32(tb[NFTA_FIB_RESULT]));
+
+ switch (result) {
+ case NFT_FIB_RESULT_OIF:
+ return &nft_fib6_ops;
+ case NFT_FIB_RESULT_OIFNAME:
+ return &nft_fib6_ops;
+ case NFT_FIB_RESULT_ADDRTYPE:
+ return &nft_fib6_type_ops;
+ default:
+ return ERR_PTR(-EOPNOTSUPP);
+ }
+}
+
+static struct nft_expr_type nft_fib6_type __read_mostly = {
+ .name = "fib",
+ .select_ops = &nft_fib6_select_ops,
+ .policy = nft_fib_policy,
+ .maxattr = NFTA_FIB_MAX,
+ .family = NFPROTO_IPV6,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_fib6_module_init(void)
+{
+ return nft_register_expr(&nft_fib6_type);
+}
+
+static void __exit nft_fib6_module_exit(void)
+{
+ nft_unregister_expr(&nft_fib6_type);
+}
+module_init(nft_fib6_module_init);
+module_exit(nft_fib6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
+MODULE_ALIAS_NFT_AF_EXPR(10, "fib");
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
index 9597ffb74077..6c5b5b1830a7 100644
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo@debian.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -32,7 +32,14 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr,
range.max_proto.all =
*(__be16 *)&regs->data[priv->sreg_proto_max];
}
- regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out);
+ regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range,
+ nft_out(pkt));
+}
+
+static void
+nft_masq_ipv6_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ nf_ct_netns_put(ctx->net, NFPROTO_IPV6);
}
static struct nft_expr_type nft_masq_ipv6_type;
@@ -41,6 +48,7 @@ static const struct nft_expr_ops nft_masq_ipv6_ops = {
.size = NFT_EXPR_SIZE(sizeof(struct nft_masq)),
.eval = nft_masq_ipv6_eval,
.init = nft_masq_init,
+ .destroy = nft_masq_ipv6_destroy,
.dump = nft_masq_dump,
.validate = nft_masq_validate,
};
@@ -77,5 +85,5 @@ module_init(nft_masq_ipv6_module_init);
module_exit(nft_masq_ipv6_module_exit);
MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>");
MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "masq");
diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c
index aca44e89a881..f5ac080fc084 100644
--- a/net/ipv6/netfilter/nft_redir_ipv6.c
+++ b/net/ipv6/netfilter/nft_redir_ipv6.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo@debian.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -35,7 +35,14 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr,
range.flags |= priv->flags;
- regs->verdict.code = nf_nat_redirect_ipv6(pkt->skb, &range, pkt->hook);
+ regs->verdict.code =
+ nf_nat_redirect_ipv6(pkt->skb, &range, nft_hook(pkt));
+}
+
+static void
+nft_redir_ipv6_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ nf_ct_netns_put(ctx->net, NFPROTO_IPV6);
}
static struct nft_expr_type nft_redir_ipv6_type;
@@ -44,6 +51,7 @@ static const struct nft_expr_ops nft_redir_ipv6_ops = {
.size = NFT_EXPR_SIZE(sizeof(struct nft_redir)),
.eval = nft_redir_ipv6_eval,
.init = nft_redir_init,
+ .destroy = nft_redir_ipv6_destroy,
.dump = nft_redir_dump,
.validate = nft_redir_validate,
};
@@ -71,5 +79,5 @@ module_init(nft_redir_ipv6_module_init);
module_exit(nft_redir_ipv6_module_exit);
MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>");
MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "redir");
diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c
index 92bda9908bb9..057deeaff1cb 100644
--- a/net/ipv6/netfilter/nft_reject_ipv6.c
+++ b/net/ipv6/netfilter/nft_reject_ipv6.c
@@ -27,11 +27,11 @@ static void nft_reject_ipv6_eval(const struct nft_expr *expr,
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
- nf_send_unreach6(pkt->net, pkt->skb, priv->icmp_code,
- pkt->hook);
+ nf_send_unreach6(nft_net(pkt), pkt->skb, priv->icmp_code,
+ nft_hook(pkt));
break;
case NFT_REJECT_TCP_RST:
- nf_send_reset6(pkt->net, pkt->skb, pkt->hook);
+ nf_send_reset6(nft_net(pkt), pkt->skb, nft_hook(pkt));
break;
default:
break;
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 7cca8ac66fe9..cd4252346a32 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -155,6 +155,8 @@ int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
if (unlikely(!skb))
return 0;
+ skb->protocol = htons(ETH_P_IPV6);
+
return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
net, sk, skb, NULL, skb_dst(skb)->dev,
dst_output);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 0e983b694ee8..e1f8b34d7a2e 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -113,6 +113,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.daddr = *daddr;
fl6.flowi6_oif = oif;
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
fl6.fl6_icmp_type = user_icmph.icmp6_type;
fl6.fl6_icmp_code = user_icmph.icmp6_code;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
@@ -180,7 +181,7 @@ struct proto pingv6_prot = {
.init = ping_init_sock,
.close = ping_close,
.connect = ip6_datagram_connect_v6_only,
- .disconnect = udp_disconnect,
+ .disconnect = __udp_disconnect,
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
.sendmsg = ping_v6_sendmsg,
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 54404f08efcc..291ebc260e70 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -65,11 +65,12 @@
#define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */
-static struct raw_hashinfo raw_v6_hashinfo = {
+struct raw_hashinfo raw_v6_hashinfo = {
.lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock),
};
+EXPORT_SYMBOL_GPL(raw_v6_hashinfo);
-static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
+struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
unsigned short num, const struct in6_addr *loc_addr,
const struct in6_addr *rmt_addr, int dif)
{
@@ -102,6 +103,7 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
found:
return sk;
}
+EXPORT_SYMBOL_GPL(__raw_v6_lookup);
/*
* 0 - deliver
@@ -774,6 +776,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
ipc6.hlimit = -1;
ipc6.tclass = -1;
@@ -1241,7 +1244,7 @@ struct proto rawv6_prot = {
.close = rawv6_close,
.destroy = raw6_destroy,
.connect = ip6_datagram_connect_v6_only,
- .disconnect = udp_disconnect,
+ .disconnect = __udp_disconnect,
.ioctl = rawv6_ioctl,
.init = rawv6_init_sk,
.setsockopt = rawv6_setsockopt,
@@ -1259,6 +1262,7 @@ struct proto rawv6_prot = {
.compat_getsockopt = compat_rawv6_getsockopt,
.compat_ioctl = compat_rawv6_ioctl,
#endif
+ .diag_destroy = raw_abort,
};
#ifdef CONFIG_PROC_FS
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 2160d5d009cb..e1da5b888cc4 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -211,7 +211,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
{
struct sk_buff *prev, *next;
struct net_device *dev;
- int offset, end;
+ int offset, end, fragsize;
struct net *net = dev_net(skb_dst(skb)->dev);
u8 ecn;
@@ -336,6 +336,10 @@ found:
fq->ecn |= ecn;
add_frag_mem_limit(fq->q.net, skb->truesize);
+ fragsize = -skb_network_offset(skb) + skb->len;
+ if (fragsize > fq->q.max_size)
+ fq->q.max_size = fragsize;
+
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
*/
@@ -456,7 +460,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
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));
- head->mac_header += 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);
@@ -494,6 +499,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
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;
/* Yes, and fold redundant checksum back. 8) */
skb_postpush_rcsum(head, skb_network_header(head),
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index bdbc38e8bf29..2413a0637d99 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -102,11 +102,13 @@ static int rt6_score_route(struct rt6_info *rt, int oif, int strict);
#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_add_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex,
+ const struct in6_addr *gwaddr,
+ struct net_device *dev,
unsigned int pref);
static struct rt6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex);
+ const struct in6_addr *gwaddr,
+ struct net_device *dev);
#endif
struct uncached_list {
@@ -525,7 +527,7 @@ static void rt6_probe_deferred(struct work_struct *w)
container_of(w, struct __rt6_probe_work, work);
addrconf_addr_solict_mult(&work->target, &mcaddr);
- ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL);
+ ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, 0);
dev_put(work->dev);
kfree(work);
}
@@ -656,7 +658,8 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
struct net_device *dev = rt->dst.dev;
if (dev && !netif_carrier_ok(dev) &&
- idev->cnf.ignore_routes_with_linkdown)
+ idev->cnf.ignore_routes_with_linkdown &&
+ !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
goto out;
if (rt6_check_expired(rt))
@@ -803,7 +806,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
rt = rt6_get_dflt_router(gwaddr, dev);
else
rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
- gwaddr, dev->ifindex);
+ gwaddr, dev);
if (rt && !lifetime) {
ip6_del_rt(rt);
@@ -811,8 +814,8 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
}
if (!rt && lifetime)
- rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev->ifindex,
- pref);
+ rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr,
+ dev, pref);
else if (rt)
rt->rt6i_flags = RTF_ROUTEINFO |
(rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
@@ -1050,6 +1053,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
int strict = 0;
strict |= flags & RT6_LOOKUP_F_IFACE;
+ strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
if (net->ipv6.devconf_all->forwarding == 0)
strict |= RT6_LOOKUP_F_REACHABLE;
@@ -1360,6 +1364,9 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
if (rt6->rt6i_flags & RTF_LOCAL)
return;
+ if (dst_metric_locked(dst, RTAX_MTU))
+ return;
+
dst_confirm(dst);
mtu = max_t(u32, mtu, IPV6_MIN_MTU);
if (mtu >= dst_mtu(dst))
@@ -1401,7 +1408,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
}
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
- int oif, u32 mark)
+ int oif, u32 mark, kuid_t uid)
{
const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
struct dst_entry *dst;
@@ -1413,6 +1420,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
+ fl6.flowi6_uid = uid;
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
@@ -1426,7 +1434,7 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
struct dst_entry *dst;
ip6_update_pmtu(skb, sock_net(sk), mtu,
- sk->sk_bound_dev_if, sk->sk_mark);
+ sk->sk_bound_dev_if, sk->sk_mark, sk->sk_uid);
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete ||
@@ -1518,7 +1526,8 @@ static struct dst_entry *ip6_route_redirect(struct net *net,
flags, __ip6_route_redirect);
}
-void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
+void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
+ kuid_t uid)
{
const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
struct dst_entry *dst;
@@ -1531,6 +1540,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
+ fl6.flowi6_uid = uid;
dst = ip6_route_redirect(net, &fl6, &ipv6_hdr(skb)->saddr);
rt6_do_redirect(dst, NULL, skb);
@@ -1552,6 +1562,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
fl6.flowi6_mark = mark;
fl6.daddr = msg->dest;
fl6.saddr = iph->daddr;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
dst = ip6_route_redirect(net, &fl6, &iph->saddr);
rt6_do_redirect(dst, NULL, skb);
@@ -1560,7 +1571,8 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk)
{
- ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark);
+ ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark,
+ sk->sk_uid);
}
EXPORT_SYMBOL_GPL(ip6_sk_redirect);
@@ -1789,7 +1801,7 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net,
};
struct fib6_table *table;
struct rt6_info *rt;
- int flags = RT6_LOOKUP_F_IFACE;
+ int flags = RT6_LOOKUP_F_IFACE | RT6_LOOKUP_F_IGNORE_LINKSTATE;
table = fib6_get_table(net, cfg->fc_table);
if (!table)
@@ -1988,8 +2000,11 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
It is very good, but in some (rare!) circumstances
(SIT, PtP, NBMA NOARP links) it is handy to allow
some exceptions. --ANK
+ We allow IPv4-mapped nexthops to support RFC4798-type
+ addressing
*/
- if (!(gwa_type & IPV6_ADDR_UNICAST))
+ if (!(gwa_type & (IPV6_ADDR_UNICAST |
+ IPV6_ADDR_MAPPED)))
goto out;
if (cfg->fc_table) {
@@ -2325,13 +2340,16 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex)
+ const struct in6_addr *gwaddr,
+ struct net_device *dev)
{
+ u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO;
+ int ifindex = dev->ifindex;
struct fib6_node *fn;
struct rt6_info *rt = NULL;
struct fib6_table *table;
- table = fib6_get_table(net, RT6_TABLE_INFO);
+ table = fib6_get_table(net, tb_id);
if (!table)
return NULL;
@@ -2357,12 +2375,13 @@ out:
static struct rt6_info *rt6_add_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex,
+ const struct in6_addr *gwaddr,
+ struct net_device *dev,
unsigned int pref)
{
struct fib6_config cfg = {
.fc_metric = IP6_RT_PRIO_USER,
- .fc_ifindex = ifindex,
+ .fc_ifindex = dev->ifindex,
.fc_dst_len = prefixlen,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
RTF_UP | RTF_PREF(pref),
@@ -2371,7 +2390,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
.fc_nlinfo.nl_net = net,
};
- cfg.fc_table = l3mdev_fib_table_by_index(net, ifindex) ? : RT6_TABLE_INFO;
+ cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO,
cfg.fc_dst = *prefix;
cfg.fc_gateway = *gwaddr;
@@ -2381,16 +2400,17 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
ip6_route_add(&cfg);
- return rt6_get_route_info(net, prefix, prefixlen, gwaddr, ifindex);
+ return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev);
}
#endif
struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev)
{
+ u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT;
struct rt6_info *rt;
struct fib6_table *table;
- table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT);
+ table = fib6_get_table(dev_net(dev), tb_id);
if (!table)
return NULL;
@@ -2424,20 +2444,20 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
cfg.fc_gateway = *gwaddr;
- ip6_route_add(&cfg);
+ if (!ip6_route_add(&cfg)) {
+ struct fib6_table *table;
+
+ table = fib6_get_table(dev_net(dev), cfg.fc_table);
+ if (table)
+ table->flags |= RT6_TABLE_HAS_DFLT_ROUTER;
+ }
return rt6_get_dflt_router(gwaddr, dev);
}
-void rt6_purge_dflt_routers(struct net *net)
+static void __rt6_purge_dflt_routers(struct fib6_table *table)
{
struct rt6_info *rt;
- struct fib6_table *table;
-
- /* NOTE: Keep consistent with rt6_get_dflt_router */
- table = fib6_get_table(net, RT6_TABLE_DFLT);
- if (!table)
- return;
restart:
read_lock_bh(&table->tb6_lock);
@@ -2451,6 +2471,27 @@ restart:
}
}
read_unlock_bh(&table->tb6_lock);
+
+ table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER;
+}
+
+void rt6_purge_dflt_routers(struct net *net)
+{
+ struct fib6_table *table;
+ struct hlist_head *head;
+ unsigned int h;
+
+ rcu_read_lock();
+
+ for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
+ head = &net->ipv6.fib_table_hash[h];
+ hlist_for_each_entry_rcu(table, head, tb6_hlist) {
+ if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER)
+ __rt6_purge_dflt_routers(table);
+ }
+ }
+
+ rcu_read_unlock();
}
static void rtmsg_to_fib6_config(struct net *net,
@@ -2728,6 +2769,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
PMTU discouvery.
*/
if (rt->dst.dev == arg->dev &&
+ dst_metric_raw(&rt->dst, RTAX_MTU) &&
!dst_metric_locked(&rt->dst, RTAX_MTU)) {
if (rt->rt6i_flags & RTF_CACHE) {
/* For RTF_CACHE with rt6i_pmtu == 0
@@ -2767,6 +2809,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_ENCAP_TYPE] = { .type = NLA_U16 },
[RTA_ENCAP] = { .type = NLA_NESTED },
[RTA_EXPIRES] = { .type = NLA_U32 },
+ [RTA_UID] = { .type = NLA_U32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -3341,6 +3384,12 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
if (tb[RTA_MARK])
fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]);
+ if (tb[RTA_UID])
+ fl6.flowi6_uid = make_kuid(current_user_ns(),
+ nla_get_u32(tb[RTA_UID]));
+ else
+ fl6.flowi6_uid = iif ? INVALID_UID : current_uid();
+
if (iif) {
struct net_device *dev;
int flags = 0;
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
new file mode 100644
index 000000000000..b172d85c650a
--- /dev/null
+++ b/net/ipv6/seg6.c
@@ -0,0 +1,495 @@
+/*
+ * SR-IPv6 implementation
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/net.h>
+#include <linux/in6.h>
+#include <linux/slab.h>
+
+#include <net/ipv6.h>
+#include <net/protocol.h>
+
+#include <net/seg6.h>
+#include <net/genetlink.h>
+#include <linux/seg6.h>
+#include <linux/seg6_genl.h>
+#ifdef CONFIG_IPV6_SEG6_HMAC
+#include <net/seg6_hmac.h>
+#endif
+
+bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len)
+{
+ int trailing;
+ unsigned int tlv_offset;
+
+ if (srh->type != IPV6_SRCRT_TYPE_4)
+ return false;
+
+ if (((srh->hdrlen + 1) << 3) != len)
+ return false;
+
+ if (srh->segments_left != srh->first_segment)
+ return false;
+
+ tlv_offset = sizeof(*srh) + ((srh->first_segment + 1) << 4);
+
+ trailing = len - tlv_offset;
+ if (trailing < 0)
+ return false;
+
+ while (trailing) {
+ struct sr6_tlv *tlv;
+ unsigned int tlv_len;
+
+ tlv = (struct sr6_tlv *)((unsigned char *)srh + tlv_offset);
+ tlv_len = sizeof(*tlv) + tlv->len;
+
+ trailing -= tlv_len;
+ if (trailing < 0)
+ return false;
+
+ tlv_offset += tlv_len;
+ }
+
+ return true;
+}
+
+static struct genl_family seg6_genl_family;
+
+static const struct nla_policy seg6_genl_policy[SEG6_ATTR_MAX + 1] = {
+ [SEG6_ATTR_DST] = { .type = NLA_BINARY,
+ .len = sizeof(struct in6_addr) },
+ [SEG6_ATTR_DSTLEN] = { .type = NLA_S32, },
+ [SEG6_ATTR_HMACKEYID] = { .type = NLA_U32, },
+ [SEG6_ATTR_SECRET] = { .type = NLA_BINARY, },
+ [SEG6_ATTR_SECRETLEN] = { .type = NLA_U8, },
+ [SEG6_ATTR_ALGID] = { .type = NLA_U8, },
+ [SEG6_ATTR_HMACINFO] = { .type = NLA_NESTED, },
+};
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+
+static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct seg6_pernet_data *sdata;
+ struct seg6_hmac_info *hinfo;
+ u32 hmackeyid;
+ char *secret;
+ int err = 0;
+ u8 algid;
+ u8 slen;
+
+ sdata = seg6_pernet(net);
+
+ if (!info->attrs[SEG6_ATTR_HMACKEYID] ||
+ !info->attrs[SEG6_ATTR_SECRETLEN] ||
+ !info->attrs[SEG6_ATTR_ALGID])
+ return -EINVAL;
+
+ hmackeyid = nla_get_u32(info->attrs[SEG6_ATTR_HMACKEYID]);
+ slen = nla_get_u8(info->attrs[SEG6_ATTR_SECRETLEN]);
+ algid = nla_get_u8(info->attrs[SEG6_ATTR_ALGID]);
+
+ if (hmackeyid == 0)
+ return -EINVAL;
+
+ if (slen > SEG6_HMAC_SECRET_LEN)
+ return -EINVAL;
+
+ mutex_lock(&sdata->lock);
+ hinfo = seg6_hmac_info_lookup(net, hmackeyid);
+
+ if (!slen) {
+ if (!hinfo)
+ err = -ENOENT;
+
+ err = seg6_hmac_info_del(net, hmackeyid);
+
+ goto out_unlock;
+ }
+
+ if (!info->attrs[SEG6_ATTR_SECRET]) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+
+ if (hinfo) {
+ err = seg6_hmac_info_del(net, hmackeyid);
+ if (err)
+ goto out_unlock;
+ }
+
+ secret = (char *)nla_data(info->attrs[SEG6_ATTR_SECRET]);
+
+ hinfo = kzalloc(sizeof(*hinfo), GFP_KERNEL);
+ if (!hinfo) {
+ err = -ENOMEM;
+ goto out_unlock;
+ }
+
+ memcpy(hinfo->secret, secret, slen);
+ hinfo->slen = slen;
+ hinfo->alg_id = algid;
+ hinfo->hmackeyid = hmackeyid;
+
+ err = seg6_hmac_info_add(net, hmackeyid, hinfo);
+ if (err)
+ kfree(hinfo);
+
+out_unlock:
+ mutex_unlock(&sdata->lock);
+ return err;
+}
+
+#else
+
+static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info)
+{
+ return -ENOTSUPP;
+}
+
+#endif
+
+static int seg6_genl_set_tunsrc(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct in6_addr *val, *t_old, *t_new;
+ struct seg6_pernet_data *sdata;
+
+ sdata = seg6_pernet(net);
+
+ if (!info->attrs[SEG6_ATTR_DST])
+ return -EINVAL;
+
+ val = nla_data(info->attrs[SEG6_ATTR_DST]);
+ t_new = kmemdup(val, sizeof(*val), GFP_KERNEL);
+
+ mutex_lock(&sdata->lock);
+
+ t_old = sdata->tun_src;
+ rcu_assign_pointer(sdata->tun_src, t_new);
+
+ mutex_unlock(&sdata->lock);
+
+ synchronize_net();
+ kfree(t_old);
+
+ return 0;
+}
+
+static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct in6_addr *tun_src;
+ struct sk_buff *msg;
+ void *hdr;
+
+ msg = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq,
+ &seg6_genl_family, 0, SEG6_CMD_GET_TUNSRC);
+ if (!hdr)
+ goto free_msg;
+
+ rcu_read_lock();
+ tun_src = rcu_dereference(seg6_pernet(net)->tun_src);
+
+ if (nla_put(msg, SEG6_ATTR_DST, sizeof(struct in6_addr), tun_src))
+ goto nla_put_failure;
+
+ rcu_read_unlock();
+
+ genlmsg_end(msg, hdr);
+ genlmsg_reply(msg, info);
+
+ return 0;
+
+nla_put_failure:
+ rcu_read_unlock();
+ genlmsg_cancel(msg, hdr);
+free_msg:
+ nlmsg_free(msg);
+ return -ENOMEM;
+}
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+
+static int __seg6_hmac_fill_info(struct seg6_hmac_info *hinfo,
+ struct sk_buff *msg)
+{
+ if (nla_put_u32(msg, SEG6_ATTR_HMACKEYID, hinfo->hmackeyid) ||
+ nla_put_u8(msg, SEG6_ATTR_SECRETLEN, hinfo->slen) ||
+ nla_put(msg, SEG6_ATTR_SECRET, hinfo->slen, hinfo->secret) ||
+ nla_put_u8(msg, SEG6_ATTR_ALGID, hinfo->alg_id))
+ return -1;
+
+ return 0;
+}
+
+static int __seg6_genl_dumphmac_element(struct seg6_hmac_info *hinfo,
+ u32 portid, u32 seq, u32 flags,
+ struct sk_buff *skb, u8 cmd)
+{
+ void *hdr;
+
+ hdr = genlmsg_put(skb, portid, seq, &seg6_genl_family, flags, cmd);
+ if (!hdr)
+ return -ENOMEM;
+
+ if (__seg6_hmac_fill_info(hinfo, skb) < 0)
+ goto nla_put_failure;
+
+ genlmsg_end(skb, hdr);
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(skb, hdr);
+ return -EMSGSIZE;
+}
+
+static int seg6_genl_dumphmac_start(struct netlink_callback *cb)
+{
+ struct net *net = sock_net(cb->skb->sk);
+ struct seg6_pernet_data *sdata;
+ struct rhashtable_iter *iter;
+
+ sdata = seg6_pernet(net);
+ iter = (struct rhashtable_iter *)cb->args[0];
+
+ if (!iter) {
+ iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter)
+ return -ENOMEM;
+
+ cb->args[0] = (long)iter;
+ }
+
+ rhashtable_walk_enter(&sdata->hmac_infos, iter);
+
+ return 0;
+}
+
+static int seg6_genl_dumphmac_done(struct netlink_callback *cb)
+{
+ struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0];
+
+ rhashtable_walk_exit(iter);
+
+ kfree(iter);
+
+ return 0;
+}
+
+static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0];
+ struct net *net = sock_net(skb->sk);
+ struct seg6_pernet_data *sdata;
+ struct seg6_hmac_info *hinfo;
+ int ret;
+
+ sdata = seg6_pernet(net);
+
+ ret = rhashtable_walk_start(iter);
+ if (ret && ret != -EAGAIN)
+ goto done;
+
+ for (;;) {
+ hinfo = rhashtable_walk_next(iter);
+
+ if (IS_ERR(hinfo)) {
+ if (PTR_ERR(hinfo) == -EAGAIN)
+ continue;
+ ret = PTR_ERR(hinfo);
+ goto done;
+ } else if (!hinfo) {
+ break;
+ }
+
+ ret = __seg6_genl_dumphmac_element(hinfo,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI,
+ skb, SEG6_CMD_DUMPHMAC);
+ if (ret)
+ goto done;
+ }
+
+ ret = skb->len;
+
+done:
+ rhashtable_walk_stop(iter);
+ return ret;
+}
+
+#else
+
+static int seg6_genl_dumphmac_start(struct netlink_callback *cb)
+{
+ return 0;
+}
+
+static int seg6_genl_dumphmac_done(struct netlink_callback *cb)
+{
+ return 0;
+}
+
+static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ return -ENOTSUPP;
+}
+
+#endif
+
+static int __net_init seg6_net_init(struct net *net)
+{
+ struct seg6_pernet_data *sdata;
+
+ sdata = kzalloc(sizeof(*sdata), GFP_KERNEL);
+ if (!sdata)
+ return -ENOMEM;
+
+ mutex_init(&sdata->lock);
+
+ sdata->tun_src = kzalloc(sizeof(*sdata->tun_src), GFP_KERNEL);
+ if (!sdata->tun_src) {
+ kfree(sdata);
+ return -ENOMEM;
+ }
+
+ net->ipv6.seg6_data = sdata;
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ seg6_hmac_net_init(net);
+#endif
+
+ return 0;
+}
+
+static void __net_exit seg6_net_exit(struct net *net)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ seg6_hmac_net_exit(net);
+#endif
+
+ kfree(sdata->tun_src);
+ kfree(sdata);
+}
+
+static struct pernet_operations ip6_segments_ops = {
+ .init = seg6_net_init,
+ .exit = seg6_net_exit,
+};
+
+static const struct genl_ops seg6_genl_ops[] = {
+ {
+ .cmd = SEG6_CMD_SETHMAC,
+ .doit = seg6_genl_sethmac,
+ .policy = seg6_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = SEG6_CMD_DUMPHMAC,
+ .start = seg6_genl_dumphmac_start,
+ .dumpit = seg6_genl_dumphmac,
+ .done = seg6_genl_dumphmac_done,
+ .policy = seg6_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = SEG6_CMD_SET_TUNSRC,
+ .doit = seg6_genl_set_tunsrc,
+ .policy = seg6_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = SEG6_CMD_GET_TUNSRC,
+ .doit = seg6_genl_get_tunsrc,
+ .policy = seg6_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+};
+
+static struct genl_family seg6_genl_family __ro_after_init = {
+ .hdrsize = 0,
+ .name = SEG6_GENL_NAME,
+ .version = SEG6_GENL_VERSION,
+ .maxattr = SEG6_ATTR_MAX,
+ .netnsok = true,
+ .parallel_ops = true,
+ .ops = seg6_genl_ops,
+ .n_ops = ARRAY_SIZE(seg6_genl_ops),
+ .module = THIS_MODULE,
+};
+
+int __init seg6_init(void)
+{
+ int err = -ENOMEM;
+
+ err = genl_register_family(&seg6_genl_family);
+ if (err)
+ goto out;
+
+ err = register_pernet_subsys(&ip6_segments_ops);
+ if (err)
+ goto out_unregister_genl;
+
+#ifdef CONFIG_IPV6_SEG6_LWTUNNEL
+ err = seg6_iptunnel_init();
+ if (err)
+ goto out_unregister_pernet;
+#endif
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ err = seg6_hmac_init();
+ if (err)
+ goto out_unregister_iptun;
+#endif
+
+ pr_info("Segment Routing with IPv6\n");
+
+out:
+ return err;
+#ifdef CONFIG_IPV6_SEG6_HMAC
+out_unregister_iptun:
+#ifdef CONFIG_IPV6_SEG6_LWTUNNEL
+ seg6_iptunnel_exit();
+#endif
+#endif
+#ifdef CONFIG_IPV6_SEG6_LWTUNNEL
+out_unregister_pernet:
+ unregister_pernet_subsys(&ip6_segments_ops);
+#endif
+out_unregister_genl:
+ genl_unregister_family(&seg6_genl_family);
+ goto out;
+}
+
+void seg6_exit(void)
+{
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ seg6_hmac_exit();
+#endif
+#ifdef CONFIG_IPV6_SEG6_LWTUNNEL
+ seg6_iptunnel_exit();
+#endif
+ unregister_pernet_subsys(&ip6_segments_ops);
+ genl_unregister_family(&seg6_genl_family);
+}
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
new file mode 100644
index 000000000000..ef1c8a46e7ac
--- /dev/null
+++ b/net/ipv6/seg6_hmac.c
@@ -0,0 +1,484 @@
+/*
+ * SR-IPv6 implementation -- HMAC functions
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/in6.h>
+#include <linux/icmpv6.h>
+#include <linux/mroute6.h>
+#include <linux/slab.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+
+#include <net/sock.h>
+#include <net/snmp.h>
+
+#include <net/ipv6.h>
+#include <net/protocol.h>
+#include <net/transp_v6.h>
+#include <net/rawv6.h>
+#include <net/ndisc.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+#include <net/xfrm.h>
+
+#include <linux/cryptohash.h>
+#include <crypto/hash.h>
+#include <crypto/sha.h>
+#include <net/seg6.h>
+#include <net/genetlink.h>
+#include <net/seg6_hmac.h>
+#include <linux/random.h>
+
+static char * __percpu *hmac_ring;
+
+static int seg6_hmac_cmpfn(struct rhashtable_compare_arg *arg, const void *obj)
+{
+ const struct seg6_hmac_info *hinfo = obj;
+
+ return (hinfo->hmackeyid != *(__u32 *)arg->key);
+}
+
+static inline void seg6_hinfo_release(struct seg6_hmac_info *hinfo)
+{
+ kfree_rcu(hinfo, rcu);
+}
+
+static void seg6_free_hi(void *ptr, void *arg)
+{
+ struct seg6_hmac_info *hinfo = (struct seg6_hmac_info *)ptr;
+
+ if (hinfo)
+ seg6_hinfo_release(hinfo);
+}
+
+static const struct rhashtable_params rht_params = {
+ .head_offset = offsetof(struct seg6_hmac_info, node),
+ .key_offset = offsetof(struct seg6_hmac_info, hmackeyid),
+ .key_len = sizeof(u32),
+ .automatic_shrinking = true,
+ .obj_cmpfn = seg6_hmac_cmpfn,
+};
+
+static struct seg6_hmac_algo hmac_algos[] = {
+ {
+ .alg_id = SEG6_HMAC_ALGO_SHA1,
+ .name = "hmac(sha1)",
+ },
+ {
+ .alg_id = SEG6_HMAC_ALGO_SHA256,
+ .name = "hmac(sha256)",
+ },
+};
+
+static struct sr6_tlv_hmac *seg6_get_tlv_hmac(struct ipv6_sr_hdr *srh)
+{
+ struct sr6_tlv_hmac *tlv;
+
+ if (srh->hdrlen < (srh->first_segment + 1) * 2 + 5)
+ return NULL;
+
+ if (!sr_has_hmac(srh))
+ return NULL;
+
+ tlv = (struct sr6_tlv_hmac *)
+ ((char *)srh + ((srh->hdrlen + 1) << 3) - 40);
+
+ if (tlv->tlvhdr.type != SR6_TLV_HMAC || tlv->tlvhdr.len != 38)
+ return NULL;
+
+ return tlv;
+}
+
+static struct seg6_hmac_algo *__hmac_get_algo(u8 alg_id)
+{
+ struct seg6_hmac_algo *algo;
+ int i, alg_count;
+
+ alg_count = sizeof(hmac_algos) / sizeof(struct seg6_hmac_algo);
+ for (i = 0; i < alg_count; i++) {
+ algo = &hmac_algos[i];
+ if (algo->alg_id == alg_id)
+ return algo;
+ }
+
+ return NULL;
+}
+
+static int __do_hmac(struct seg6_hmac_info *hinfo, const char *text, u8 psize,
+ u8 *output, int outlen)
+{
+ struct seg6_hmac_algo *algo;
+ struct crypto_shash *tfm;
+ struct shash_desc *shash;
+ int ret, dgsize;
+
+ algo = __hmac_get_algo(hinfo->alg_id);
+ if (!algo)
+ return -ENOENT;
+
+ tfm = *this_cpu_ptr(algo->tfms);
+
+ dgsize = crypto_shash_digestsize(tfm);
+ if (dgsize > outlen) {
+ pr_debug("sr-ipv6: __do_hmac: digest size too big (%d / %d)\n",
+ dgsize, outlen);
+ return -ENOMEM;
+ }
+
+ ret = crypto_shash_setkey(tfm, hinfo->secret, hinfo->slen);
+ if (ret < 0) {
+ pr_debug("sr-ipv6: crypto_shash_setkey failed: err %d\n", ret);
+ goto failed;
+ }
+
+ shash = *this_cpu_ptr(algo->shashs);
+ shash->tfm = tfm;
+
+ ret = crypto_shash_digest(shash, text, psize, output);
+ if (ret < 0) {
+ pr_debug("sr-ipv6: crypto_shash_digest failed: err %d\n", ret);
+ goto failed;
+ }
+
+ return dgsize;
+
+failed:
+ return ret;
+}
+
+int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr,
+ struct in6_addr *saddr, u8 *output)
+{
+ __be32 hmackeyid = cpu_to_be32(hinfo->hmackeyid);
+ u8 tmp_out[SEG6_HMAC_MAX_DIGESTSIZE];
+ int plen, i, dgsize, wrsize;
+ char *ring, *off;
+
+ /* a 160-byte buffer for digest output allows to store highest known
+ * hash function (RadioGatun) with up to 1216 bits
+ */
+
+ /* saddr(16) + first_seg(1) + cleanup(1) + keyid(4) + seglist(16n) */
+ plen = 16 + 1 + 1 + 4 + (hdr->first_segment + 1) * 16;
+
+ /* this limit allows for 14 segments */
+ if (plen >= SEG6_HMAC_RING_SIZE)
+ return -EMSGSIZE;
+
+ /* Let's build the HMAC text on the ring buffer. The text is composed
+ * as follows, in order:
+ *
+ * 1. Source IPv6 address (128 bits)
+ * 2. first_segment value (8 bits)
+ * 3. cleanup flag (8 bits: highest bit is cleanup value, others are 0)
+ * 4. HMAC Key ID (32 bits)
+ * 5. All segments in the segments list (n * 128 bits)
+ */
+
+ local_bh_disable();
+ ring = *this_cpu_ptr(hmac_ring);
+ off = ring;
+
+ /* source address */
+ memcpy(off, saddr, 16);
+ off += 16;
+
+ /* first_segment value */
+ *off++ = hdr->first_segment;
+
+ /* cleanup flag */
+ *off++ = !!(sr_has_cleanup(hdr)) << 7;
+
+ /* HMAC Key ID */
+ memcpy(off, &hmackeyid, 4);
+ off += 4;
+
+ /* all segments in the list */
+ for (i = 0; i < hdr->first_segment + 1; i++) {
+ memcpy(off, hdr->segments + i, 16);
+ off += 16;
+ }
+
+ dgsize = __do_hmac(hinfo, ring, plen, tmp_out,
+ SEG6_HMAC_MAX_DIGESTSIZE);
+ local_bh_enable();
+
+ if (dgsize < 0)
+ return dgsize;
+
+ wrsize = SEG6_HMAC_FIELD_LEN;
+ if (wrsize > dgsize)
+ wrsize = dgsize;
+
+ memset(output, 0, SEG6_HMAC_FIELD_LEN);
+ memcpy(output, tmp_out, wrsize);
+
+ return 0;
+}
+EXPORT_SYMBOL(seg6_hmac_compute);
+
+/* checks if an incoming SR-enabled packet's HMAC status matches
+ * the incoming policy.
+ *
+ * called with rcu_read_lock()
+ */
+bool seg6_hmac_validate_skb(struct sk_buff *skb)
+{
+ u8 hmac_output[SEG6_HMAC_FIELD_LEN];
+ struct net *net = dev_net(skb->dev);
+ struct seg6_hmac_info *hinfo;
+ struct sr6_tlv_hmac *tlv;
+ struct ipv6_sr_hdr *srh;
+ struct inet6_dev *idev;
+
+ idev = __in6_dev_get(skb->dev);
+
+ srh = (struct ipv6_sr_hdr *)skb_transport_header(skb);
+
+ tlv = seg6_get_tlv_hmac(srh);
+
+ /* mandatory check but no tlv */
+ if (idev->cnf.seg6_require_hmac > 0 && !tlv)
+ return false;
+
+ /* no check */
+ if (idev->cnf.seg6_require_hmac < 0)
+ return true;
+
+ /* check only if present */
+ if (idev->cnf.seg6_require_hmac == 0 && !tlv)
+ return true;
+
+ /* now, seg6_require_hmac >= 0 && tlv */
+
+ hinfo = seg6_hmac_info_lookup(net, be32_to_cpu(tlv->hmackeyid));
+ if (!hinfo)
+ return false;
+
+ if (seg6_hmac_compute(hinfo, srh, &ipv6_hdr(skb)->saddr, hmac_output))
+ return false;
+
+ if (memcmp(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN) != 0)
+ return false;
+
+ return true;
+}
+EXPORT_SYMBOL(seg6_hmac_validate_skb);
+
+/* called with rcu_read_lock() */
+struct seg6_hmac_info *seg6_hmac_info_lookup(struct net *net, u32 key)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+ struct seg6_hmac_info *hinfo;
+
+ hinfo = rhashtable_lookup_fast(&sdata->hmac_infos, &key, rht_params);
+
+ return hinfo;
+}
+EXPORT_SYMBOL(seg6_hmac_info_lookup);
+
+int seg6_hmac_info_add(struct net *net, u32 key, struct seg6_hmac_info *hinfo)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+ int err;
+
+ err = rhashtable_lookup_insert_fast(&sdata->hmac_infos, &hinfo->node,
+ rht_params);
+
+ return err;
+}
+EXPORT_SYMBOL(seg6_hmac_info_add);
+
+int seg6_hmac_info_del(struct net *net, u32 key)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+ struct seg6_hmac_info *hinfo;
+ int err = -ENOENT;
+
+ hinfo = rhashtable_lookup_fast(&sdata->hmac_infos, &key, rht_params);
+ if (!hinfo)
+ goto out;
+
+ err = rhashtable_remove_fast(&sdata->hmac_infos, &hinfo->node,
+ rht_params);
+ if (err)
+ goto out;
+
+ seg6_hinfo_release(hinfo);
+
+out:
+ return err;
+}
+EXPORT_SYMBOL(seg6_hmac_info_del);
+
+int seg6_push_hmac(struct net *net, struct in6_addr *saddr,
+ struct ipv6_sr_hdr *srh)
+{
+ struct seg6_hmac_info *hinfo;
+ struct sr6_tlv_hmac *tlv;
+ int err = -ENOENT;
+
+ tlv = seg6_get_tlv_hmac(srh);
+ if (!tlv)
+ return -EINVAL;
+
+ rcu_read_lock();
+
+ hinfo = seg6_hmac_info_lookup(net, be32_to_cpu(tlv->hmackeyid));
+ if (!hinfo)
+ goto out;
+
+ memset(tlv->hmac, 0, SEG6_HMAC_FIELD_LEN);
+ err = seg6_hmac_compute(hinfo, srh, saddr, tlv->hmac);
+
+out:
+ rcu_read_unlock();
+ return err;
+}
+EXPORT_SYMBOL(seg6_push_hmac);
+
+static int seg6_hmac_init_ring(void)
+{
+ int i;
+
+ hmac_ring = alloc_percpu(char *);
+
+ if (!hmac_ring)
+ return -ENOMEM;
+
+ for_each_possible_cpu(i) {
+ char *ring = kzalloc(SEG6_HMAC_RING_SIZE, GFP_KERNEL);
+
+ if (!ring)
+ return -ENOMEM;
+
+ *per_cpu_ptr(hmac_ring, i) = ring;
+ }
+
+ return 0;
+}
+
+static int seg6_hmac_init_algo(void)
+{
+ struct seg6_hmac_algo *algo;
+ struct crypto_shash *tfm;
+ struct shash_desc *shash;
+ int i, alg_count, cpu;
+
+ alg_count = sizeof(hmac_algos) / sizeof(struct seg6_hmac_algo);
+
+ for (i = 0; i < alg_count; i++) {
+ struct crypto_shash **p_tfm;
+ int shsize;
+
+ algo = &hmac_algos[i];
+ algo->tfms = alloc_percpu(struct crypto_shash *);
+ if (!algo->tfms)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL);
+ if (IS_ERR(tfm))
+ return PTR_ERR(tfm);
+ p_tfm = per_cpu_ptr(algo->tfms, cpu);
+ *p_tfm = tfm;
+ }
+
+ p_tfm = this_cpu_ptr(algo->tfms);
+ tfm = *p_tfm;
+
+ shsize = sizeof(*shash) + crypto_shash_descsize(tfm);
+
+ algo->shashs = alloc_percpu(struct shash_desc *);
+ if (!algo->shashs)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ shash = kzalloc(shsize, GFP_KERNEL);
+ if (!shash)
+ return -ENOMEM;
+ *per_cpu_ptr(algo->shashs, cpu) = shash;
+ }
+ }
+
+ return 0;
+}
+
+int __init seg6_hmac_init(void)
+{
+ int ret;
+
+ ret = seg6_hmac_init_ring();
+ if (ret < 0)
+ goto out;
+
+ ret = seg6_hmac_init_algo();
+
+out:
+ return ret;
+}
+EXPORT_SYMBOL(seg6_hmac_init);
+
+int __net_init seg6_hmac_net_init(struct net *net)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+
+ rhashtable_init(&sdata->hmac_infos, &rht_params);
+
+ return 0;
+}
+EXPORT_SYMBOL(seg6_hmac_net_init);
+
+void seg6_hmac_exit(void)
+{
+ struct seg6_hmac_algo *algo = NULL;
+ int i, alg_count, cpu;
+
+ for_each_possible_cpu(i) {
+ char *ring = *per_cpu_ptr(hmac_ring, i);
+
+ kfree(ring);
+ }
+ free_percpu(hmac_ring);
+
+ alg_count = sizeof(hmac_algos) / sizeof(struct seg6_hmac_algo);
+ for (i = 0; i < alg_count; i++) {
+ algo = &hmac_algos[i];
+ for_each_possible_cpu(cpu) {
+ struct crypto_shash *tfm;
+ struct shash_desc *shash;
+
+ shash = *per_cpu_ptr(algo->shashs, cpu);
+ kfree(shash);
+ tfm = *per_cpu_ptr(algo->tfms, cpu);
+ crypto_free_shash(tfm);
+ }
+ free_percpu(algo->tfms);
+ free_percpu(algo->shashs);
+ }
+}
+EXPORT_SYMBOL(seg6_hmac_exit);
+
+void __net_exit seg6_hmac_net_exit(struct net *net)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+
+ rhashtable_free_and_destroy(&sdata->hmac_infos, seg6_free_hi, NULL);
+}
+EXPORT_SYMBOL(seg6_hmac_net_exit);
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
new file mode 100644
index 000000000000..bbfca22c34ae
--- /dev/null
+++ b/net/ipv6/seg6_iptunnel.c
@@ -0,0 +1,431 @@
+/*
+ * SR-IPv6 implementation
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/net.h>
+#include <linux/module.h>
+#include <net/ip.h>
+#include <net/lwtunnel.h>
+#include <net/netevent.h>
+#include <net/netns/generic.h>
+#include <net/ip6_fib.h>
+#include <net/route.h>
+#include <net/seg6.h>
+#include <linux/seg6.h>
+#include <linux/seg6_iptunnel.h>
+#include <net/addrconf.h>
+#include <net/ip6_route.h>
+#ifdef CONFIG_DST_CACHE
+#include <net/dst_cache.h>
+#endif
+#ifdef CONFIG_IPV6_SEG6_HMAC
+#include <net/seg6_hmac.h>
+#endif
+
+struct seg6_lwt {
+#ifdef CONFIG_DST_CACHE
+ struct dst_cache cache;
+#endif
+ struct seg6_iptunnel_encap tuninfo[0];
+};
+
+static inline struct seg6_lwt *seg6_lwt_lwtunnel(struct lwtunnel_state *lwt)
+{
+ return (struct seg6_lwt *)lwt->data;
+}
+
+static inline struct seg6_iptunnel_encap *
+seg6_encap_lwtunnel(struct lwtunnel_state *lwt)
+{
+ return seg6_lwt_lwtunnel(lwt)->tuninfo;
+}
+
+static const struct nla_policy seg6_iptunnel_policy[SEG6_IPTUNNEL_MAX + 1] = {
+ [SEG6_IPTUNNEL_SRH] = { .type = NLA_BINARY },
+};
+
+int nla_put_srh(struct sk_buff *skb, int attrtype,
+ struct seg6_iptunnel_encap *tuninfo)
+{
+ struct seg6_iptunnel_encap *data;
+ struct nlattr *nla;
+ int len;
+
+ len = SEG6_IPTUN_ENCAP_SIZE(tuninfo);
+
+ nla = nla_reserve(skb, attrtype, len);
+ if (!nla)
+ return -EMSGSIZE;
+
+ data = nla_data(nla);
+ memcpy(data, tuninfo, len);
+
+ return 0;
+}
+
+static void set_tun_src(struct net *net, struct net_device *dev,
+ struct in6_addr *daddr, struct in6_addr *saddr)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+ struct in6_addr *tun_src;
+
+ rcu_read_lock();
+
+ tun_src = rcu_dereference(sdata->tun_src);
+
+ if (!ipv6_addr_any(tun_src)) {
+ memcpy(saddr, tun_src, sizeof(struct in6_addr));
+ } else {
+ ipv6_dev_get_saddr(net, dev, daddr, IPV6_PREFER_SRC_PUBLIC,
+ saddr);
+ }
+
+ rcu_read_unlock();
+}
+
+/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
+static int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
+{
+ struct net *net = dev_net(skb_dst(skb)->dev);
+ struct ipv6hdr *hdr, *inner_hdr;
+ struct ipv6_sr_hdr *isrh;
+ int hdrlen, tot_len, err;
+
+ hdrlen = (osrh->hdrlen + 1) << 3;
+ tot_len = hdrlen + sizeof(*hdr);
+
+ err = pskb_expand_head(skb, tot_len, 0, GFP_ATOMIC);
+ if (unlikely(err))
+ return err;
+
+ inner_hdr = ipv6_hdr(skb);
+
+ skb_push(skb, tot_len);
+ skb_reset_network_header(skb);
+ skb_mac_header_rebuild(skb);
+ hdr = ipv6_hdr(skb);
+
+ /* inherit tc, flowlabel and hlim
+ * hlim will be decremented in ip6_forward() afterwards and
+ * decapsulation will overwrite inner hlim with outer hlim
+ */
+ ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)),
+ ip6_flowlabel(inner_hdr));
+ hdr->hop_limit = inner_hdr->hop_limit;
+ hdr->nexthdr = NEXTHDR_ROUTING;
+
+ isrh = (void *)hdr + sizeof(*hdr);
+ memcpy(isrh, osrh, hdrlen);
+
+ isrh->nexthdr = NEXTHDR_IPV6;
+
+ hdr->daddr = isrh->segments[isrh->first_segment];
+ set_tun_src(net, skb->dev, &hdr->daddr, &hdr->saddr);
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ if (sr_has_hmac(isrh)) {
+ err = seg6_push_hmac(net, &hdr->saddr, isrh);
+ if (unlikely(err))
+ return err;
+ }
+#endif
+
+ skb_postpush_rcsum(skb, hdr, tot_len);
+
+ return 0;
+}
+
+/* insert an SRH within an IPv6 packet, just after the IPv6 header */
+#ifdef CONFIG_IPV6_SEG6_INLINE
+static int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
+{
+ struct ipv6hdr *hdr, *oldhdr;
+ struct ipv6_sr_hdr *isrh;
+ int hdrlen, err;
+
+ hdrlen = (osrh->hdrlen + 1) << 3;
+
+ err = pskb_expand_head(skb, hdrlen, 0, GFP_ATOMIC);
+ if (unlikely(err))
+ return err;
+
+ oldhdr = ipv6_hdr(skb);
+
+ skb_pull(skb, sizeof(struct ipv6hdr));
+ skb_postpull_rcsum(skb, skb_network_header(skb),
+ sizeof(struct ipv6hdr));
+
+ skb_push(skb, sizeof(struct ipv6hdr) + hdrlen);
+ skb_reset_network_header(skb);
+ skb_mac_header_rebuild(skb);
+
+ hdr = ipv6_hdr(skb);
+
+ memmove(hdr, oldhdr, sizeof(*hdr));
+
+ isrh = (void *)hdr + sizeof(*hdr);
+ memcpy(isrh, osrh, hdrlen);
+
+ isrh->nexthdr = hdr->nexthdr;
+ hdr->nexthdr = NEXTHDR_ROUTING;
+
+ isrh->segments[0] = hdr->daddr;
+ hdr->daddr = isrh->segments[isrh->first_segment];
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ if (sr_has_hmac(isrh)) {
+ struct net *net = dev_net(skb_dst(skb)->dev);
+
+ err = seg6_push_hmac(net, &hdr->saddr, isrh);
+ if (unlikely(err))
+ return err;
+ }
+#endif
+
+ skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen);
+
+ return 0;
+}
+#endif
+
+static int seg6_do_srh(struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ struct seg6_iptunnel_encap *tinfo;
+ int err = 0;
+
+ tinfo = seg6_encap_lwtunnel(dst->lwtstate);
+
+ if (likely(!skb->encapsulation)) {
+ skb_reset_inner_headers(skb);
+ skb->encapsulation = 1;
+ }
+
+ switch (tinfo->mode) {
+#ifdef CONFIG_IPV6_SEG6_INLINE
+ case SEG6_IPTUN_MODE_INLINE:
+ err = seg6_do_srh_inline(skb, tinfo->srh);
+ skb_reset_inner_headers(skb);
+ break;
+#endif
+ case SEG6_IPTUN_MODE_ENCAP:
+ err = seg6_do_srh_encap(skb, tinfo->srh);
+ break;
+ }
+
+ if (err)
+ return err;
+
+ ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+ skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+
+ skb_set_inner_protocol(skb, skb->protocol);
+
+ return 0;
+}
+
+int seg6_input(struct sk_buff *skb)
+{
+ int err;
+
+ err = seg6_do_srh(skb);
+ if (unlikely(err)) {
+ kfree_skb(skb);
+ return err;
+ }
+
+ skb_dst_drop(skb);
+ ip6_route_input(skb);
+
+ return dst_input(skb);
+}
+
+int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ struct dst_entry *orig_dst = skb_dst(skb);
+ struct dst_entry *dst = NULL;
+ struct seg6_lwt *slwt;
+ int err = -EINVAL;
+
+ err = seg6_do_srh(skb);
+ if (unlikely(err))
+ goto drop;
+
+ slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
+
+#ifdef CONFIG_DST_CACHE
+ dst = dst_cache_get(&slwt->cache);
+#endif
+
+ if (unlikely(!dst)) {
+ struct ipv6hdr *hdr = ipv6_hdr(skb);
+ struct flowi6 fl6;
+
+ fl6.daddr = hdr->daddr;
+ fl6.saddr = hdr->saddr;
+ fl6.flowlabel = ip6_flowinfo(hdr);
+ fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_proto = hdr->nexthdr;
+
+ dst = ip6_route_output(net, NULL, &fl6);
+ if (dst->error) {
+ err = dst->error;
+ dst_release(dst);
+ goto drop;
+ }
+
+#ifdef CONFIG_DST_CACHE
+ dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
+#endif
+ }
+
+ skb_dst_drop(skb);
+ skb_dst_set(skb, dst);
+
+ return dst_output(net, sk, skb);
+drop:
+ kfree_skb(skb);
+ return err;
+}
+
+static int seg6_build_state(struct net_device *dev, struct nlattr *nla,
+ unsigned int family, const void *cfg,
+ struct lwtunnel_state **ts)
+{
+ struct nlattr *tb[SEG6_IPTUNNEL_MAX + 1];
+ struct seg6_iptunnel_encap *tuninfo;
+ struct lwtunnel_state *newts;
+ int tuninfo_len, min_size;
+ struct seg6_lwt *slwt;
+ int err;
+
+ err = nla_parse_nested(tb, SEG6_IPTUNNEL_MAX, nla,
+ seg6_iptunnel_policy);
+
+ if (err < 0)
+ return err;
+
+ if (!tb[SEG6_IPTUNNEL_SRH])
+ return -EINVAL;
+
+ tuninfo = nla_data(tb[SEG6_IPTUNNEL_SRH]);
+ tuninfo_len = nla_len(tb[SEG6_IPTUNNEL_SRH]);
+
+ /* tuninfo must contain at least the iptunnel encap structure,
+ * the SRH and one segment
+ */
+ min_size = sizeof(*tuninfo) + sizeof(struct ipv6_sr_hdr) +
+ sizeof(struct in6_addr);
+ if (tuninfo_len < min_size)
+ return -EINVAL;
+
+ switch (tuninfo->mode) {
+#ifdef CONFIG_IPV6_SEG6_INLINE
+ case SEG6_IPTUN_MODE_INLINE:
+ break;
+#endif
+ case SEG6_IPTUN_MODE_ENCAP:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ /* verify that SRH is consistent */
+ if (!seg6_validate_srh(tuninfo->srh, tuninfo_len - sizeof(*tuninfo)))
+ return -EINVAL;
+
+ newts = lwtunnel_state_alloc(tuninfo_len + sizeof(*slwt));
+ if (!newts)
+ return -ENOMEM;
+
+ slwt = seg6_lwt_lwtunnel(newts);
+
+#ifdef CONFIG_DST_CACHE
+ err = dst_cache_init(&slwt->cache, GFP_KERNEL);
+ if (err) {
+ kfree(newts);
+ return err;
+ }
+#endif
+
+ memcpy(&slwt->tuninfo, tuninfo, tuninfo_len);
+
+ newts->type = LWTUNNEL_ENCAP_SEG6;
+ newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT |
+ LWTUNNEL_STATE_INPUT_REDIRECT;
+ newts->headroom = seg6_lwt_headroom(tuninfo);
+
+ *ts = newts;
+
+ return 0;
+}
+
+#ifdef CONFIG_DST_CACHE
+static void seg6_destroy_state(struct lwtunnel_state *lwt)
+{
+ dst_cache_destroy(&seg6_lwt_lwtunnel(lwt)->cache);
+}
+#endif
+
+static int seg6_fill_encap_info(struct sk_buff *skb,
+ struct lwtunnel_state *lwtstate)
+{
+ struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate);
+
+ if (nla_put_srh(skb, SEG6_IPTUNNEL_SRH, tuninfo))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int seg6_encap_nlsize(struct lwtunnel_state *lwtstate)
+{
+ struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate);
+
+ return nla_total_size(SEG6_IPTUN_ENCAP_SIZE(tuninfo));
+}
+
+static int seg6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
+{
+ struct seg6_iptunnel_encap *a_hdr = seg6_encap_lwtunnel(a);
+ struct seg6_iptunnel_encap *b_hdr = seg6_encap_lwtunnel(b);
+ int len = SEG6_IPTUN_ENCAP_SIZE(a_hdr);
+
+ if (len != SEG6_IPTUN_ENCAP_SIZE(b_hdr))
+ return 1;
+
+ return memcmp(a_hdr, b_hdr, len);
+}
+
+static const struct lwtunnel_encap_ops seg6_iptun_ops = {
+ .build_state = seg6_build_state,
+#ifdef CONFIG_DST_CACHE
+ .destroy_state = seg6_destroy_state,
+#endif
+ .output = seg6_output,
+ .input = seg6_input,
+ .fill_encap = seg6_fill_encap_info,
+ .get_encap_size = seg6_encap_nlsize,
+ .cmp_encap = seg6_encap_cmp,
+};
+
+int __init seg6_iptunnel_init(void)
+{
+ return lwtunnel_encap_add_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6);
+}
+
+void seg6_iptunnel_exit(void)
+{
+ lwtunnel_encap_del_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6);
+}
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b1cdf8009d29..0355231162b8 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -76,7 +76,7 @@ static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst,
__be32 *v4dst);
static struct rtnl_link_ops sit_link_ops __read_mostly;
-static int sit_net_id __read_mostly;
+static unsigned int sit_net_id __read_mostly;
struct sit_net {
struct ip_tunnel __rcu *tunnels_r_l[IP6_SIT_HASH_SIZE];
struct ip_tunnel __rcu *tunnels_r[IP6_SIT_HASH_SIZE];
@@ -1318,23 +1318,11 @@ done:
return err;
}
-static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu)
-{
- struct ip_tunnel *tunnel = netdev_priv(dev);
- int t_hlen = tunnel->hlen + sizeof(struct iphdr);
-
- if (new_mtu < IPV6_MIN_MTU || new_mtu > 0xFFF8 - t_hlen)
- return -EINVAL;
- dev->mtu = new_mtu;
- return 0;
-}
-
static const struct net_device_ops ipip6_netdev_ops = {
.ndo_init = ipip6_tunnel_init,
.ndo_uninit = ipip6_tunnel_uninit,
.ndo_start_xmit = sit_tunnel_xmit,
.ndo_do_ioctl = ipip6_tunnel_ioctl,
- .ndo_change_mtu = ipip6_tunnel_change_mtu,
.ndo_get_stats64 = ip_tunnel_get_stats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
};
@@ -1365,6 +1353,8 @@ static void ipip6_tunnel_setup(struct net_device *dev)
dev->type = ARPHRD_SIT;
dev->hard_header_len = LL_MAX_HEADER + t_hlen;
dev->mtu = ETH_DATA_LEN - t_hlen;
+ dev->min_mtu = IPV6_MIN_MTU;
+ dev->max_mtu = 0xFFF8 - t_hlen;
dev->flags = IFF_NOARP;
netif_keep_dst(dev);
dev->addr_len = 4;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 59c483937aec..a4d49760bf43 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -209,6 +209,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
treq->snt_synack.v64 = 0;
treq->rcv_isn = ntohl(th->seq) - 1;
treq->snt_isn = cookie;
+ treq->ts_off = 0;
/*
* We need to lookup the dst_entry to get the correct window size.
@@ -227,6 +228,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
fl6.flowi6_mark = ireq->ir_mark;
fl6.fl6_dport = ireq->ir_rmt_port;
fl6.fl6_sport = inet_sk(sk)->inet_sport;
+ fl6.flowi6_uid = sk->sk_uid;
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5a27ab4eab39..73bc8fc68acd 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -101,12 +101,12 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
}
}
-static __u32 tcp_v6_init_sequence(const struct sk_buff *skb)
+static u32 tcp_v6_init_sequence(const struct sk_buff *skb, u32 *tsoff)
{
return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32,
ipv6_hdr(skb)->saddr.s6_addr32,
tcp_hdr(skb)->dest,
- tcp_hdr(skb)->source);
+ tcp_hdr(skb)->source, tsoff);
}
static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
@@ -233,6 +233,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
+ fl6.flowi6_uid = sk->sk_uid;
opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
final_p = fl6_update_dst(&fl6, opt, &final);
@@ -282,7 +283,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
sk->sk_v6_daddr.s6_addr32,
inet->inet_sport,
- inet->inet_dport);
+ inet->inet_dport,
+ &tp->tsoffset);
err = tcp_connect(sk);
if (err)
@@ -397,7 +399,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (!sock_owned_by_user(sk))
tcp_v6_mtu_reduced(sk);
else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED,
- &tp->tsq_flags))
+ &sk->sk_tsq_flags))
sock_hold(sk);
goto out;
}
@@ -818,12 +820,17 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
fl6.flowi6_proto = IPPROTO_TCP;
if (rt6_need_strict(&fl6.daddr) && !oif)
fl6.flowi6_oif = tcp_v6_iif(skb);
- else
- fl6.flowi6_oif = oif ? : skb->skb_iif;
+ else {
+ if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
+ oif = skb->skb_iif;
+
+ fl6.flowi6_oif = oif;
+ }
fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
fl6.fl6_dport = t1->dest;
fl6.fl6_sport = t1->source;
+ fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
/* Pass a socket to ip6_dst_lookup either it is for RST
@@ -950,7 +957,8 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
tcp_rsk(req)->rcv_nxt,
req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
- tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
+ tcp_time_stamp + tcp_rsk(req)->ts_off,
+ req->ts_recent, sk->sk_bound_dev_if,
tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
0, 0);
}
@@ -1225,7 +1233,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
if (skb->protocol == htons(ETH_P_IP))
return tcp_v4_do_rcv(sk, skb);
- if (sk_filter(sk, skb))
+ if (tcp_filter(sk, skb))
goto discard;
/*
@@ -1453,8 +1461,10 @@ process:
if (tcp_v6_inbound_md5_hash(sk, skb))
goto discard_and_relse;
- if (sk_filter(sk, skb))
+ if (tcp_filter(sk, skb))
goto discard_and_relse;
+ th = (const struct tcphdr *)skb->data;
+ hdr = ipv6_hdr(skb);
skb->dev = NULL;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 9aa7c1c7a9ce..649efc26a252 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -302,7 +302,8 @@ EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb);
* Does increment socket refcount.
*/
#if IS_ENABLED(CONFIG_NETFILTER_XT_MATCH_SOCKET) || \
- IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY)
+ IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY) || \
+ IS_ENABLED(CONFIG_NF_SOCKET_IPV6)
struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, __be16 dport, int dif)
{
@@ -334,7 +335,6 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int is_udplite = IS_UDPLITE(sk);
bool checksum_valid = false;
int is_udp4;
- bool slow;
if (flags & MSG_ERRQUEUE)
return ipv6_recv_error(sk, msg, len, addr_len);
@@ -344,8 +344,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
try_again:
peeking = off = sk_peek_offset(sk, flags);
- skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
- &peeked, &off, &err);
+ skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err);
if (!skb)
return err;
@@ -364,7 +363,8 @@ try_again:
* coverage checksum (UDP-Lite), do it before the copy.
*/
- if (copied < ulen || UDP_SKB_CB(skb)->partial_cov || peeking) {
+ if (copied < ulen || peeking ||
+ (is_udplite && UDP_SKB_CB(skb)->partial_cov)) {
checksum_valid = !udp_lib_checksum_complete(skb);
if (!checksum_valid)
goto csum_copy_err;
@@ -378,7 +378,6 @@ try_again:
goto csum_copy_err;
}
if (unlikely(err)) {
- trace_kfree_skb(skb, udpv6_recvmsg);
if (!peeked) {
atomic_inc(&sk->sk_drops);
if (is_udp4)
@@ -388,7 +387,7 @@ try_again:
UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
is_udplite);
}
- skb_free_datagram_locked(sk, skb);
+ kfree_skb(skb);
return err;
}
if (!peeked) {
@@ -427,7 +426,8 @@ try_again:
if (is_udp4) {
if (inet->cmsg_flags)
- ip_cmsg_recv(msg, skb);
+ ip_cmsg_recv_offset(msg, sk, skb,
+ sizeof(struct udphdr), off);
} else {
if (np->rxopt.all)
ip6_datagram_recv_specific_ctl(sk, msg, skb);
@@ -437,12 +437,11 @@ try_again:
if (flags & MSG_TRUNC)
err = ulen;
- __skb_free_datagram_locked(sk, skb, peeking ? -err : err);
+ skb_consume_udp(sk, skb, peeking ? -err : err);
return err;
csum_copy_err:
- slow = lock_sock_fast(sk);
- if (!skb_kill_datagram(sk, skb, flags)) {
+ if (!__sk_queue_drop_skb(sk, skb, flags)) {
if (is_udp4) {
UDP_INC_STATS(sock_net(sk),
UDP_MIB_CSUMERRORS, is_udplite);
@@ -455,7 +454,7 @@ csum_copy_err:
UDP_MIB_INERRORS, is_udplite);
}
}
- unlock_sock_fast(sk, slow);
+ kfree_skb(skb);
/* starting over for a new packet, but check if we need to yield */
cond_resched();
@@ -513,7 +512,7 @@ out:
return;
}
-static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int rc;
@@ -521,9 +520,11 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
sock_rps_save_rxhash(sk, skb);
sk_mark_napi_id(sk, skb);
sk_incoming_cpu_update(sk);
+ } else {
+ sk_mark_napi_id_once(sk, skb);
}
- rc = __sock_queue_rcv_skb(sk, skb);
+ rc = __udp_enqueue_schedule_skb(sk, skb);
if (rc < 0) {
int is_udplite = IS_UDPLITE(sk);
@@ -535,6 +536,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
kfree_skb(skb);
return -1;
}
+
return 0;
}
@@ -556,7 +558,6 @@ EXPORT_SYMBOL(udpv6_encap_enable);
int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
struct udp_sock *up = udp_sk(sk);
- int rc;
int is_udplite = IS_UDPLITE(sk);
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
@@ -622,25 +623,10 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
goto drop;
udp_csum_pull_header(skb);
- if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
- __UDP6_INC_STATS(sock_net(sk),
- UDP_MIB_RCVBUFERRORS, is_udplite);
- goto drop;
- }
skb_dst_drop(skb);
- bh_lock_sock(sk);
- rc = 0;
- if (!sock_owned_by_user(sk))
- rc = __udpv6_queue_rcv_skb(sk, skb);
- else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) {
- bh_unlock_sock(sk);
- goto drop;
- }
- bh_unlock_sock(sk);
-
- return rc;
+ return __udpv6_queue_rcv_skb(sk, skb);
csum_error:
__UDP6_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
@@ -705,10 +691,10 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
if (use_hash2) {
hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) &
- udp_table.mask;
- hash2 = udp6_portaddr_hash(net, daddr, hnum) & udp_table.mask;
+ udptable->mask;
+ hash2 = udp6_portaddr_hash(net, daddr, hnum) & udptable->mask;
start_lookup:
- hslot = &udp_table.hash2[hash2];
+ hslot = &udptable->hash2[hash2];
offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node);
}
@@ -1155,6 +1141,7 @@ do_udp_sendmsg:
fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
sockc.tsflags = sk->sk_tsflags;
if (msg->msg_controllen) {
@@ -1433,12 +1420,12 @@ struct proto udpv6_prot = {
.connect = ip6_datagram_connect,
.disconnect = udp_disconnect,
.ioctl = udp_ioctl,
+ .init = udp_init_sock,
.destroy = udpv6_destroy_sock,
.setsockopt = udpv6_setsockopt,
.getsockopt = udpv6_getsockopt,
.sendmsg = udpv6_sendmsg,
.recvmsg = udpv6_recvmsg,
- .backlog_rcv = __udpv6_queue_rcv_skb,
.release_cb = ip6_datagram_release_cb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h
index f6eb1ab34f4b..e78bdc76dcc3 100644
--- a/net/ipv6/udp_impl.h
+++ b/net/ipv6/udp_impl.h
@@ -26,7 +26,7 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
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_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
void udpv6_destroy_sock(struct sock *sk);
#ifdef CONFIG_PROC_FS
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 47d0d2b87106..2784cc363f2b 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -45,10 +45,11 @@ struct proto udplitev6_prot = {
.getsockopt = udpv6_getsockopt,
.sendmsg = udpv6_sendmsg,
.recvmsg = udpv6_recvmsg,
- .backlog_rcv = udpv6_queue_rcv_skb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
.get_port = udp_v6_get_port,
+ .memory_allocated = &udp_memory_allocated,
+ .sysctl_mem = sysctl_udp_mem,
.obj_size = sizeof(struct udp6_sock),
.h.udp_table = &udplite_table,
#ifdef CONFIG_COMPAT
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index e1c0bbe7996c..d7b731a78d09 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -44,7 +44,7 @@ struct xfrm6_tunnel_net {
u32 spi;
};
-static int xfrm6_tunnel_net_id __read_mostly;
+static unsigned int xfrm6_tunnel_net_id __read_mostly;
static inline struct xfrm6_tunnel_net *xfrm6_tunnel_pernet(struct net *net)
{
return net_generic(net, xfrm6_tunnel_net_id);