summaryrefslogtreecommitdiffstats
path: root/net/ipv6
diff options
context:
space:
mode:
authorMichal Marek <mmarek@suse.cz>2010-08-04 13:59:13 +0200
committerMichal Marek <mmarek@suse.cz>2010-08-04 13:59:13 +0200
commit772320e84588dcbe1600ffb83e5f328f2209ac2a (patch)
treea7de21b79340aeaa17c58126f6b801b82c77b53a /net/ipv6
parent1ce53adf13a54375d2a5c7cdbe341b2558389615 (diff)
parent9fe6206f400646a2322096b56c59891d530e8d51 (diff)
downloadlinux-772320e84588dcbe1600ffb83e5f328f2209ac2a.tar.gz
linux-772320e84588dcbe1600ffb83e5f328f2209ac2a.tar.bz2
linux-772320e84588dcbe1600ffb83e5f328f2209ac2a.zip
Merge commit 'v2.6.35' into kbuild/kbuild
Conflicts: arch/powerpc/Makefile
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/Kconfig14
-rw-r--r--net/ipv6/addrconf.c1025
-rw-r--r--net/ipv6/addrconf_core.c2
-rw-r--r--net/ipv6/addrlabel.c9
-rw-r--r--net/ipv6/af_inet6.c38
-rw-r--r--net/ipv6/ah6.c3
-rw-r--r--net/ipv6/anycast.c3
-rw-r--r--net/ipv6/datagram.c117
-rw-r--r--net/ipv6/esp6.c2
-rw-r--r--net/ipv6/exthdrs.c3
-rw-r--r--net/ipv6/fib6_rules.c18
-rw-r--r--net/ipv6/icmp.c20
-rw-r--r--net/ipv6/inet6_connection_sock.c5
-rw-r--r--net/ipv6/ip6_fib.c69
-rw-r--r--net/ipv6/ip6_flowlabel.c13
-rw-r--r--net/ipv6/ip6_input.c8
-rw-r--r--net/ipv6/ip6_output.c129
-rw-r--r--net/ipv6/ip6_tunnel.c52
-rw-r--r--net/ipv6/ip6mr.c953
-rw-r--r--net/ipv6/ipcomp6.c21
-rw-r--r--net/ipv6/ipv6_sockglue.c87
-rw-r--r--net/ipv6/mcast.c181
-rw-r--r--net/ipv6/mip6.c5
-rw-r--r--net/ipv6/ndisc.c16
-rw-r--r--net/ipv6/netfilter.c25
-rw-r--r--net/ipv6/netfilter/ip6_queue.c5
-rw-r--r--net/ipv6/netfilter/ip6_tables.c791
-rw-r--r--net/ipv6/netfilter/ip6t_LOG.c20
-rw-r--r--net/ipv6/netfilter/ip6t_REJECT.c41
-rw-r--r--net/ipv6/netfilter/ip6t_ah.c18
-rw-r--r--net/ipv6/netfilter/ip6t_eui64.c4
-rw-r--r--net/ipv6/netfilter/ip6t_frag.c18
-rw-r--r--net/ipv6/netfilter/ip6t_hbh.c33
-rw-r--r--net/ipv6/netfilter/ip6t_ipv6header.c8
-rw-r--r--net/ipv6/netfilter/ip6t_mh.c21
-rw-r--r--net/ipv6/netfilter/ip6t_rt.c20
-rw-r--r--net/ipv6/netfilter/ip6table_filter.c116
-rw-r--r--net/ipv6/netfilter/ip6table_mangle.c144
-rw-r--r--net/ipv6/netfilter/ip6table_raw.c87
-rw-r--r--net/ipv6/netfilter/ip6table_security.c110
-rw-r--r--net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c28
-rw-r--r--net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c11
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c19
-rw-r--r--net/ipv6/proc.c41
-rw-r--r--net/ipv6/raw.c23
-rw-r--r--net/ipv6/reassembly.c28
-rw-r--r--net/ipv6/route.c43
-rw-r--r--net/ipv6/sit.c34
-rw-r--r--net/ipv6/syncookies.c3
-rw-r--r--net/ipv6/sysctl_net_ipv6.c5
-rw-r--r--net/ipv6/tcp_ipv6.c100
-rw-r--r--net/ipv6/tunnel6.c5
-rw-r--r--net/ipv6/udp.c97
-rw-r--r--net/ipv6/udplite.c4
-rw-r--r--net/ipv6/xfrm6_input.c4
-rw-r--r--net/ipv6/xfrm6_mode_tunnel.c1
-rw-r--r--net/ipv6/xfrm6_output.c6
-rw-r--r--net/ipv6/xfrm6_policy.c38
-rw-r--r--net/ipv6/xfrm6_tunnel.c195
59 files changed, 2689 insertions, 2250 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index a578096152ab..36d7437ac054 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -229,6 +229,20 @@ config IPV6_MROUTE
Experimental support for IPv6 multicast forwarding.
If unsure, say N.
+config IPV6_MROUTE_MULTIPLE_TABLES
+ bool "IPv6: multicast policy routing"
+ depends on IPV6_MROUTE
+ select FIB_RULES
+ help
+ Normally, a multicast router runs a userspace daemon and decides
+ what to do with a multicast packet based on the source and
+ destination addresses. If you say Y here, the multicast router
+ will also be able to take interfaces and packet marks into
+ account and run multiple instances of userspace daemons
+ simultaneously, each one handling a single table.
+
+ If unsure, say N.
+
config IPV6_PIMSM_V2
bool "IPv6: PIM-SM version 2 support (EXPERIMENTAL)"
depends on IPV6_MROUTE
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index de7a194a64ab..784f34d11fdd 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -53,6 +53,7 @@
#include <linux/route.h>
#include <linux/inetdevice.h>
#include <linux/init.h>
+#include <linux/slab.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
@@ -81,7 +82,7 @@
#include <linux/random.h>
#endif
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#include <asm/unaligned.h>
#include <linux/proc_fs.h>
@@ -97,7 +98,11 @@
#endif
#define INFINITY_LIFE_TIME 0xFFFFFFFF
-#define TIME_DELTA(a,b) ((unsigned long)((long)(a) - (long)(b)))
+#define TIME_DELTA(a, b) ((unsigned long)((long)(a) - (long)(b)))
+
+#define ADDRCONF_TIMER_FUZZ_MINUS (HZ > 50 ? HZ/50 : 1)
+#define ADDRCONF_TIMER_FUZZ (HZ / 4)
+#define ADDRCONF_TIMER_FUZZ_MAX (HZ)
#ifdef CONFIG_SYSCTL
static void addrconf_sysctl_register(struct inet6_dev *idev);
@@ -126,8 +131,8 @@ static int ipv6_count_addresses(struct inet6_dev *idev);
/*
* Configured unicast address hash table
*/
-static struct inet6_ifaddr *inet6_addr_lst[IN6_ADDR_HSIZE];
-static DEFINE_RWLOCK(addrconf_hash_lock);
+static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE];
+static DEFINE_SPINLOCK(addrconf_hash_lock);
static void addrconf_verify(unsigned long);
@@ -137,8 +142,8 @@ static DEFINE_SPINLOCK(addrconf_verify_lock);
static void addrconf_join_anycast(struct inet6_ifaddr *ifp);
static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);
-static void addrconf_bonding_change(struct net_device *dev,
- unsigned long event);
+static void addrconf_type_change(struct net_device *dev,
+ unsigned long event);
static int addrconf_ifdown(struct net_device *dev, int how);
static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags);
@@ -151,8 +156,8 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
static void inet6_prefix_notify(int event, struct inet6_dev *idev,
struct prefix_info *pinfo);
-static int ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
- struct net_device *dev);
+static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
+ struct net_device *dev);
static ATOMIC_NOTIFIER_HEAD(inet6addr_chain);
@@ -249,8 +254,7 @@ static void addrconf_del_timer(struct inet6_ifaddr *ifp)
__in6_ifa_put(ifp);
}
-enum addrconf_timer_t
-{
+enum addrconf_timer_t {
AC_NONE,
AC_DAD,
AC_RS,
@@ -270,7 +274,8 @@ static void addrconf_mod_timer(struct inet6_ifaddr *ifp,
case AC_RS:
ifp->timer.function = addrconf_rs_timer;
break;
- default:;
+ default:
+ break;
}
ifp->timer.expires = jiffies + when;
add_timer(&ifp->timer);
@@ -278,31 +283,31 @@ static void addrconf_mod_timer(struct inet6_ifaddr *ifp,
static int snmp6_alloc_dev(struct inet6_dev *idev)
{
- if (snmp_mib_init((void **)idev->stats.ipv6,
+ if (snmp_mib_init((void __percpu **)idev->stats.ipv6,
sizeof(struct ipstats_mib)) < 0)
goto err_ip;
- if (snmp_mib_init((void **)idev->stats.icmpv6,
+ if (snmp_mib_init((void __percpu **)idev->stats.icmpv6,
sizeof(struct icmpv6_mib)) < 0)
goto err_icmp;
- if (snmp_mib_init((void **)idev->stats.icmpv6msg,
+ if (snmp_mib_init((void __percpu **)idev->stats.icmpv6msg,
sizeof(struct icmpv6msg_mib)) < 0)
goto err_icmpmsg;
return 0;
err_icmpmsg:
- snmp_mib_free((void **)idev->stats.icmpv6);
+ snmp_mib_free((void __percpu **)idev->stats.icmpv6);
err_icmp:
- snmp_mib_free((void **)idev->stats.ipv6);
+ snmp_mib_free((void __percpu **)idev->stats.ipv6);
err_ip:
return -ENOMEM;
}
static void snmp6_free_dev(struct inet6_dev *idev)
{
- snmp_mib_free((void **)idev->stats.icmpv6msg);
- snmp_mib_free((void **)idev->stats.icmpv6);
- snmp_mib_free((void **)idev->stats.ipv6);
+ snmp_mib_free((void __percpu **)idev->stats.icmpv6msg);
+ snmp_mib_free((void __percpu **)idev->stats.icmpv6);
+ snmp_mib_free((void __percpu **)idev->stats.ipv6);
}
/* Nobody refers to this device, we may destroy it. */
@@ -317,7 +322,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev)
{
struct net_device *dev = idev->dev;
- WARN_ON(idev->addr_list != NULL);
+ WARN_ON(!list_empty(&idev->addr_list));
WARN_ON(idev->mc_list != NULL);
#ifdef NET_REFCNT_DEBUG
@@ -325,7 +330,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev)
#endif
dev_put(dev);
if (!idev->dead) {
- printk("Freeing alive inet6 device %p\n", idev);
+ pr_warning("Freeing alive inet6 device %p\n", idev);
return;
}
snmp6_free_dev(idev);
@@ -350,6 +355,8 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev)
rwlock_init(&ndev->lock);
ndev->dev = dev;
+ INIT_LIST_HEAD(&ndev->addr_list);
+
memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf));
ndev->cnf.mtu6 = dev->mtu;
ndev->cnf.sysctl = NULL;
@@ -401,6 +408,7 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev)
#endif
#ifdef CONFIG_IPV6_PRIVACY
+ INIT_LIST_HEAD(&ndev->tempaddr_list);
setup_timer(&ndev->regen_timer, ipv6_regen_rndid, (unsigned long)ndev);
if ((dev->flags&IFF_LOOPBACK) ||
dev->type == ARPHRD_TUNNEL ||
@@ -438,8 +446,10 @@ static struct inet6_dev * ipv6_find_idev(struct net_device *dev)
ASSERT_RTNL();
- if ((idev = __in6_dev_get(dev)) == NULL) {
- if ((idev = ipv6_add_dev(dev)) == NULL)
+ idev = __in6_dev_get(dev);
+ if (!idev) {
+ idev = ipv6_add_dev(dev);
+ if (!idev)
return NULL;
}
@@ -465,7 +475,8 @@ static void dev_forward_change(struct inet6_dev *idev)
else
ipv6_dev_mc_dec(dev, &in6addr_linklocal_allrouters);
}
- for (ifa=idev->addr_list; ifa; ifa=ifa->if_next) {
+
+ list_for_each_entry(ifa, &idev->addr_list, if_list) {
if (ifa->flags&IFA_F_TENTATIVE)
continue;
if (idev->cnf.forwarding)
@@ -502,8 +513,11 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old)
if (p == &net->ipv6.devconf_dflt->forwarding)
return 0;
- if (!rtnl_trylock())
+ if (!rtnl_trylock()) {
+ /* Restore the original values before restarting */
+ *p = old;
return restart_syscall();
+ }
if (p == &net->ipv6.devconf_all->forwarding) {
__s32 newf = net->ipv6.devconf_all->forwarding;
@@ -519,12 +533,16 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old)
}
#endif
-/* Nobody refers to this ifaddr, destroy it */
+static void inet6_ifa_finish_destroy_rcu(struct rcu_head *head)
+{
+ struct inet6_ifaddr *ifp = container_of(head, struct inet6_ifaddr, rcu);
+ kfree(ifp);
+}
+/* Nobody refers to this ifaddr, destroy it */
void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
{
- WARN_ON(ifp->if_next != NULL);
- WARN_ON(ifp->lst_next != NULL);
+ WARN_ON(!hlist_unhashed(&ifp->addr_lst));
#ifdef NET_REFCNT_DEBUG
printk(KERN_DEBUG "inet6_ifa_finish_destroy\n");
@@ -533,54 +551,46 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
in6_dev_put(ifp->idev);
if (del_timer(&ifp->timer))
- printk("Timer is still running, when freeing ifa=%p\n", ifp);
+ pr_notice("Timer is still running, when freeing ifa=%p\n", ifp);
- if (!ifp->dead) {
- printk("Freeing alive inet6 address %p\n", ifp);
+ if (ifp->state != INET6_IFADDR_STATE_DEAD) {
+ pr_warning("Freeing alive inet6 address %p\n", ifp);
return;
}
dst_release(&ifp->rt->u.dst);
- kfree(ifp);
+ call_rcu(&ifp->rcu, inet6_ifa_finish_destroy_rcu);
}
static void
ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp)
{
- struct inet6_ifaddr *ifa, **ifap;
+ struct list_head *p;
int ifp_scope = ipv6_addr_src_scope(&ifp->addr);
/*
* Each device address list is sorted in order of scope -
* global before linklocal.
*/
- for (ifap = &idev->addr_list; (ifa = *ifap) != NULL;
- ifap = &ifa->if_next) {
+ list_for_each(p, &idev->addr_list) {
+ struct inet6_ifaddr *ifa
+ = list_entry(p, struct inet6_ifaddr, if_list);
if (ifp_scope >= ipv6_addr_src_scope(&ifa->addr))
break;
}
- ifp->if_next = *ifap;
- *ifap = ifp;
+ list_add_tail(&ifp->if_list, p);
}
-/*
- * Hash function taken from net_alias.c
- */
-static u8 ipv6_addr_hash(const struct in6_addr *addr)
+static u32 ipv6_addr_hash(const struct in6_addr *addr)
{
- __u32 word;
-
/*
* We perform the hash function over the last 64 bits of the address
* This will include the IEEE address token on links that support it.
*/
-
- word = (__force u32)(addr->s6_addr32[2] ^ addr->s6_addr32[3]);
- word ^= (word >> 16);
- word ^= (word >> 8);
-
- return ((word ^ (word >> 4)) & 0x0f);
+ return jhash_2words((__force u32)addr->s6_addr32[2],
+ (__force u32)addr->s6_addr32[3], 0)
+ & (IN6_ADDR_HSIZE - 1);
}
/* On success it returns ifp with increased reference count */
@@ -591,7 +601,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
{
struct inet6_ifaddr *ifa = NULL;
struct rt6_info *rt;
- int hash;
+ unsigned int hash;
int err = 0;
int addr_type = ipv6_addr_type(addr);
@@ -612,7 +622,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
goto out2;
}
- write_lock(&addrconf_hash_lock);
+ spin_lock(&addrconf_hash_lock);
/* Ignore adding duplicate addresses on an interface */
if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) {
@@ -638,7 +648,9 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
ipv6_addr_copy(&ifa->addr, addr);
spin_lock_init(&ifa->lock);
+ spin_lock_init(&ifa->state_lock);
init_timer(&ifa->timer);
+ INIT_HLIST_NODE(&ifa->addr_lst);
ifa->timer.data = (unsigned long) ifa;
ifa->scope = scope;
ifa->prefix_len = pfxlen;
@@ -665,10 +677,8 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
/* Add to big hash table */
hash = ipv6_addr_hash(addr);
- ifa->lst_next = inet6_addr_lst[hash];
- inet6_addr_lst[hash] = ifa;
- in6_ifa_hold(ifa);
- write_unlock(&addrconf_hash_lock);
+ hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]);
+ spin_unlock(&addrconf_hash_lock);
write_lock(&idev->lock);
/* Add to inet6_dev unicast addr list. */
@@ -676,8 +686,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
#ifdef CONFIG_IPV6_PRIVACY
if (ifa->flags&IFA_F_TEMPORARY) {
- ifa->tmp_next = idev->tempaddr_list;
- idev->tempaddr_list = ifa;
+ list_add(&ifa->tmp_list, &idev->tempaddr_list);
in6_ifa_hold(ifa);
}
#endif
@@ -696,7 +705,7 @@ out2:
return ifa;
out:
- write_unlock(&addrconf_hash_lock);
+ spin_unlock(&addrconf_hash_lock);
goto out2;
}
@@ -704,52 +713,44 @@ out:
static void ipv6_del_addr(struct inet6_ifaddr *ifp)
{
- struct inet6_ifaddr *ifa, **ifap;
+ struct inet6_ifaddr *ifa, *ifn;
struct inet6_dev *idev = ifp->idev;
+ int state;
int hash;
int deleted = 0, onlink = 0;
unsigned long expires = jiffies;
hash = ipv6_addr_hash(&ifp->addr);
- ifp->dead = 1;
+ spin_lock_bh(&ifp->state_lock);
+ state = ifp->state;
+ ifp->state = INET6_IFADDR_STATE_DEAD;
+ spin_unlock_bh(&ifp->state_lock);
- write_lock_bh(&addrconf_hash_lock);
- for (ifap = &inet6_addr_lst[hash]; (ifa=*ifap) != NULL;
- ifap = &ifa->lst_next) {
- if (ifa == ifp) {
- *ifap = ifa->lst_next;
- __in6_ifa_put(ifp);
- ifa->lst_next = NULL;
- break;
- }
- }
- write_unlock_bh(&addrconf_hash_lock);
+ if (state == INET6_IFADDR_STATE_DEAD)
+ goto out;
+
+ spin_lock_bh(&addrconf_hash_lock);
+ hlist_del_init_rcu(&ifp->addr_lst);
+ spin_unlock_bh(&addrconf_hash_lock);
write_lock_bh(&idev->lock);
#ifdef CONFIG_IPV6_PRIVACY
if (ifp->flags&IFA_F_TEMPORARY) {
- for (ifap = &idev->tempaddr_list; (ifa=*ifap) != NULL;
- ifap = &ifa->tmp_next) {
- if (ifa == ifp) {
- *ifap = ifa->tmp_next;
- if (ifp->ifpub) {
- in6_ifa_put(ifp->ifpub);
- ifp->ifpub = NULL;
- }
- __in6_ifa_put(ifp);
- ifa->tmp_next = NULL;
- break;
- }
+ list_del(&ifp->tmp_list);
+ if (ifp->ifpub) {
+ in6_ifa_put(ifp->ifpub);
+ ifp->ifpub = NULL;
}
+ __in6_ifa_put(ifp);
}
#endif
- for (ifap = &idev->addr_list; (ifa=*ifap) != NULL;) {
+ list_for_each_entry_safe(ifa, ifn, &idev->addr_list, if_list) {
if (ifa == ifp) {
- *ifap = ifa->if_next;
+ list_del_init(&ifp->if_list);
__in6_ifa_put(ifp);
- ifa->if_next = NULL;
+
if (!(ifp->flags & IFA_F_PERMANENT) || onlink > 0)
break;
deleted = 1;
@@ -782,7 +783,6 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
}
}
}
- ifap = &ifa->if_next;
}
write_unlock_bh(&idev->lock);
@@ -826,6 +826,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
dst_release(&rt->u.dst);
}
+out:
in6_ifa_put(ifp);
}
@@ -989,8 +990,7 @@ struct ipv6_saddr_dst {
static inline int ipv6_saddr_preferred(int type)
{
- if (type & (IPV6_ADDR_MAPPED|IPV6_ADDR_COMPATv4|
- IPV6_ADDR_LOOPBACK|IPV6_ADDR_RESERVED))
+ if (type & (IPV6_ADDR_MAPPED|IPV6_ADDR_COMPATv4|IPV6_ADDR_LOOPBACK))
return 1;
return 0;
}
@@ -1162,7 +1162,7 @@ int ipv6_dev_get_saddr(struct net *net, struct net_device *dst_dev,
continue;
read_lock_bh(&idev->lock);
- for (score->ifa = idev->addr_list; score->ifa; score->ifa = score->ifa->if_next) {
+ list_for_each_entry(score->ifa, &idev->addr_list, if_list) {
int i;
/*
@@ -1240,7 +1240,6 @@ try_nextdev:
in6_ifa_put(hiscore->ifa);
return 0;
}
-
EXPORT_SYMBOL(ipv6_dev_get_saddr);
int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
@@ -1250,12 +1249,14 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
int err = -EADDRNOTAVAIL;
rcu_read_lock();
- if ((idev = __in6_dev_get(dev)) != NULL) {
+ idev = __in6_dev_get(dev);
+ if (idev) {
struct inet6_ifaddr *ifp;
read_lock_bh(&idev->lock);
- for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) {
- if (ifp->scope == IFA_LINK && !(ifp->flags & banned_flags)) {
+ list_for_each_entry(ifp, &idev->addr_list, if_list) {
+ if (ifp->scope == IFA_LINK &&
+ !(ifp->flags & banned_flags)) {
ipv6_addr_copy(addr, &ifp->addr);
err = 0;
break;
@@ -1273,7 +1274,7 @@ static int ipv6_count_addresses(struct inet6_dev *idev)
struct inet6_ifaddr *ifp;
read_lock_bh(&idev->lock);
- for (ifp=idev->addr_list; ifp; ifp=ifp->if_next)
+ list_for_each_entry(ifp, &idev->addr_list, if_list)
cnt++;
read_unlock_bh(&idev->lock);
return cnt;
@@ -1282,41 +1283,44 @@ static int ipv6_count_addresses(struct inet6_dev *idev)
int ipv6_chk_addr(struct net *net, struct in6_addr *addr,
struct net_device *dev, int strict)
{
- struct inet6_ifaddr * ifp;
- u8 hash = ipv6_addr_hash(addr);
+ struct inet6_ifaddr *ifp;
+ struct hlist_node *node;
+ unsigned int hash = ipv6_addr_hash(addr);
- read_lock_bh(&addrconf_hash_lock);
- for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) {
+ rcu_read_lock_bh();
+ hlist_for_each_entry_rcu(ifp, node, &inet6_addr_lst[hash], addr_lst) {
if (!net_eq(dev_net(ifp->idev->dev), net))
continue;
if (ipv6_addr_equal(&ifp->addr, addr) &&
- !(ifp->flags&IFA_F_TENTATIVE)) {
- if (dev == NULL || ifp->idev->dev == dev ||
- !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))
- break;
+ !(ifp->flags&IFA_F_TENTATIVE) &&
+ (dev == NULL || ifp->idev->dev == dev ||
+ !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) {
+ rcu_read_unlock_bh();
+ return 1;
}
}
- read_unlock_bh(&addrconf_hash_lock);
- return ifp != NULL;
+
+ rcu_read_unlock_bh();
+ return 0;
}
EXPORT_SYMBOL(ipv6_chk_addr);
-static
-int ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
- struct net_device *dev)
+static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
+ struct net_device *dev)
{
- struct inet6_ifaddr * ifp;
- u8 hash = ipv6_addr_hash(addr);
+ unsigned int hash = ipv6_addr_hash(addr);
+ struct inet6_ifaddr *ifp;
+ struct hlist_node *node;
- for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) {
+ hlist_for_each_entry(ifp, node, &inet6_addr_lst[hash], addr_lst) {
if (!net_eq(dev_net(ifp->idev->dev), net))
continue;
if (ipv6_addr_equal(&ifp->addr, addr)) {
if (dev == NULL || ifp->idev->dev == dev)
- break;
+ return true;
}
}
- return ifp != NULL;
+ return false;
}
int ipv6_chk_prefix(struct in6_addr *addr, struct net_device *dev)
@@ -1330,7 +1334,7 @@ int ipv6_chk_prefix(struct in6_addr *addr, struct net_device *dev)
idev = __in6_dev_get(dev);
if (idev) {
read_lock_bh(&idev->lock);
- for (ifa = idev->addr_list; ifa; ifa = ifa->if_next) {
+ list_for_each_entry(ifa, &idev->addr_list, if_list) {
onlink = ipv6_prefix_equal(addr, &ifa->addr,
ifa->prefix_len);
if (onlink)
@@ -1347,24 +1351,26 @@ EXPORT_SYMBOL(ipv6_chk_prefix);
struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr,
struct net_device *dev, int strict)
{
- struct inet6_ifaddr * ifp;
- u8 hash = ipv6_addr_hash(addr);
+ struct inet6_ifaddr *ifp, *result = NULL;
+ unsigned int hash = ipv6_addr_hash(addr);
+ struct hlist_node *node;
- read_lock_bh(&addrconf_hash_lock);
- for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) {
+ rcu_read_lock_bh();
+ hlist_for_each_entry_rcu_bh(ifp, node, &inet6_addr_lst[hash], addr_lst) {
if (!net_eq(dev_net(ifp->idev->dev), net))
continue;
if (ipv6_addr_equal(&ifp->addr, addr)) {
if (dev == NULL || ifp->idev->dev == dev ||
!(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) {
+ result = ifp;
in6_ifa_hold(ifp);
break;
}
}
}
- read_unlock_bh(&addrconf_hash_lock);
+ rcu_read_unlock_bh();
- return ifp;
+ return result;
}
/* Gets referenced address, destroys ifaddr */
@@ -1378,6 +1384,8 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
if (dad_failed)
ifp->flags |= IFA_F_DADFAILED;
spin_unlock_bh(&ifp->lock);
+ if (dad_failed)
+ ipv6_ifa_notify(0, ifp);
in6_ifa_put(ifp);
#ifdef CONFIG_IPV6_PRIVACY
} else if (ifp->flags&IFA_F_TEMPORARY) {
@@ -1398,10 +1406,27 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
ipv6_del_addr(ifp);
}
+static int addrconf_dad_end(struct inet6_ifaddr *ifp)
+{
+ int err = -ENOENT;
+
+ spin_lock(&ifp->state_lock);
+ if (ifp->state == INET6_IFADDR_STATE_DAD) {
+ ifp->state = INET6_IFADDR_STATE_POSTDAD;
+ err = 0;
+ }
+ spin_unlock(&ifp->state_lock);
+
+ return err;
+}
+
void addrconf_dad_failure(struct inet6_ifaddr *ifp)
{
struct inet6_dev *idev = ifp->idev;
+ if (addrconf_dad_end(ifp))
+ return;
+
if (net_ratelimit())
printk(KERN_INFO "%s: IPv6 duplicate address %pI6c detected!\n",
ifp->idev->dev->name, &ifp->addr);
@@ -1565,7 +1590,7 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev)
struct inet6_ifaddr *ifp;
read_lock_bh(&idev->lock);
- for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) {
+ list_for_each_entry(ifp, &idev->addr_list, if_list) {
if (ifp->scope == IFA_LINK && !(ifp->flags&IFA_F_TENTATIVE)) {
memcpy(eui, ifp->addr.s6_addr+8, 8);
err = 0;
@@ -1733,8 +1758,12 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev)
ASSERT_RTNL();
- if ((idev = ipv6_find_idev(dev)) == NULL)
- return NULL;
+ idev = ipv6_find_idev(dev);
+ if (!idev)
+ return ERR_PTR(-ENOBUFS);
+
+ if (idev->cnf.disable_ipv6)
+ return ERR_PTR(-EACCES);
/* Add default multicast route */
addrconf_add_mroute(dev);
@@ -1966,7 +1995,7 @@ ok:
#ifdef CONFIG_IPV6_PRIVACY
read_lock_bh(&in6_dev->lock);
/* update all temporary addresses in the list */
- for (ift=in6_dev->tempaddr_list; ift; ift=ift->tmp_next) {
+ list_for_each_entry(ift, &in6_dev->tempaddr_list, tmp_list) {
/*
* When adjusting the lifetimes of an existing
* temporary address, only lower the lifetimes.
@@ -2103,8 +2132,9 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx,
if (!dev)
return -ENODEV;
- if ((idev = addrconf_add_dev(dev)) == NULL)
- return -ENOBUFS;
+ idev = addrconf_add_dev(dev);
+ if (IS_ERR(idev))
+ return PTR_ERR(idev);
scope = ipv6_addr_scope(pfx);
@@ -2169,7 +2199,7 @@ static int inet6_addr_del(struct net *net, int ifindex, struct in6_addr *pfx,
return -ENXIO;
read_lock_bh(&idev->lock);
- for (ifp = idev->addr_list; ifp; ifp=ifp->if_next) {
+ list_for_each_entry(ifp, &idev->addr_list, if_list) {
if (ifp->prefix_len == plen &&
ipv6_addr_equal(pfx, &ifp->addr)) {
in6_ifa_hold(ifp);
@@ -2180,7 +2210,7 @@ static int inet6_addr_del(struct net *net, int ifindex, struct in6_addr *pfx,
/* If the last address is deleted administratively,
disable IPv6 on this interface.
*/
- if (idev->addr_list == NULL)
+ if (list_empty(&idev->addr_list))
addrconf_ifdown(idev->dev, 1);
return 0;
}
@@ -2351,7 +2381,7 @@ static void addrconf_dev_config(struct net_device *dev)
}
idev = addrconf_add_dev(dev);
- if (idev == NULL)
+ if (IS_ERR(idev))
return;
memset(&addr, 0, sizeof(struct in6_addr));
@@ -2441,7 +2471,8 @@ static void addrconf_ip6_tnl_config(struct net_device *dev)
ASSERT_RTNL();
- if ((idev = addrconf_add_dev(dev)) == NULL) {
+ idev = addrconf_add_dev(dev);
+ if (IS_ERR(idev)) {
printk(KERN_DEBUG "init ip6-ip6: add_dev failed\n");
return;
}
@@ -2456,7 +2487,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
int run_pending = 0;
int err;
- switch(event) {
+ switch (event) {
case NETDEV_REGISTER:
if (!idev && dev->mtu >= IPV6_MIN_MTU) {
idev = ipv6_add_dev(dev);
@@ -2464,6 +2495,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
return notifier_from_errno(-ENOMEM);
}
break;
+
case NETDEV_UP:
case NETDEV_CHANGE:
if (dev->flags & IFF_SLAVE)
@@ -2493,10 +2525,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
}
if (idev) {
- if (idev->if_flags & IF_READY) {
+ if (idev->if_flags & IF_READY)
/* device is already configured. */
break;
- }
idev->if_flags |= IF_READY;
}
@@ -2508,7 +2539,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
run_pending = 1;
}
- switch(dev->type) {
+ switch (dev->type) {
#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
case ARPHRD_SIT:
addrconf_sit_config(dev);
@@ -2525,25 +2556,30 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
addrconf_dev_config(dev);
break;
}
+
if (idev) {
if (run_pending)
addrconf_dad_run(idev);
- /* If the MTU changed during the interface down, when the
- interface up, the changed MTU must be reflected in the
- idev as well as routers.
+ /*
+ * If the MTU changed during the interface down,
+ * when the interface up, the changed MTU must be
+ * reflected in the idev as well as routers.
*/
- if (idev->cnf.mtu6 != dev->mtu && dev->mtu >= IPV6_MIN_MTU) {
+ if (idev->cnf.mtu6 != dev->mtu &&
+ dev->mtu >= IPV6_MIN_MTU) {
rt6_mtu_change(dev, dev->mtu);
idev->cnf.mtu6 = dev->mtu;
}
idev->tstamp = jiffies;
inet6_ifinfo_notify(RTM_NEWLINK, idev);
- /* If the changed mtu during down is lower than IPV6_MIN_MTU
- stop IPv6 on this interface.
+
+ /*
+ * If the changed mtu during down is lower than
+ * IPV6_MIN_MTU stop IPv6 on this interface.
*/
if (dev->mtu < IPV6_MIN_MTU)
- addrconf_ifdown(dev, event != NETDEV_DOWN);
+ addrconf_ifdown(dev, 1);
}
break;
@@ -2560,7 +2596,10 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
break;
}
- /* MTU falled under IPV6_MIN_MTU. Stop IPv6 on this interface. */
+ /*
+ * MTU falled under IPV6_MIN_MTU.
+ * Stop IPv6 on this interface.
+ */
case NETDEV_DOWN:
case NETDEV_UNREGISTER:
@@ -2580,9 +2619,10 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
return notifier_from_errno(err);
}
break;
- case NETDEV_BONDING_OLDTYPE:
- case NETDEV_BONDING_NEWTYPE:
- addrconf_bonding_change(dev, event);
+
+ case NETDEV_PRE_TYPE_CHANGE:
+ case NETDEV_POST_TYPE_CHANGE:
+ addrconf_type_change(dev, event);
break;
}
@@ -2594,28 +2634,28 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
*/
static struct notifier_block ipv6_dev_notf = {
.notifier_call = addrconf_notify,
- .priority = 0
};
-static void addrconf_bonding_change(struct net_device *dev, unsigned long event)
+static void addrconf_type_change(struct net_device *dev, unsigned long event)
{
struct inet6_dev *idev;
ASSERT_RTNL();
idev = __in6_dev_get(dev);
- if (event == NETDEV_BONDING_NEWTYPE)
+ if (event == NETDEV_POST_TYPE_CHANGE)
ipv6_mc_remap(idev);
- else if (event == NETDEV_BONDING_OLDTYPE)
+ else if (event == NETDEV_PRE_TYPE_CHANGE)
ipv6_mc_unmap(idev);
}
static int addrconf_ifdown(struct net_device *dev, int how)
{
- struct inet6_dev *idev;
- struct inet6_ifaddr *ifa, **bifa;
struct net *net = dev_net(dev);
- int i;
+ struct inet6_dev *idev;
+ struct inet6_ifaddr *ifa;
+ LIST_HEAD(keep_list);
+ int state;
ASSERT_RTNL();
@@ -2626,8 +2666,9 @@ static int addrconf_ifdown(struct net_device *dev, int how)
if (idev == NULL)
return -ENODEV;
- /* Step 1: remove reference to ipv6 device from parent device.
- Do not dev_put!
+ /*
+ * Step 1: remove reference to ipv6 device from parent device.
+ * Do not dev_put!
*/
if (how) {
idev->dead = 1;
@@ -2640,40 +2681,21 @@ static int addrconf_ifdown(struct net_device *dev, int how)
}
- /* Step 2: clear hash table */
- for (i=0; i<IN6_ADDR_HSIZE; i++) {
- bifa = &inet6_addr_lst[i];
-
- write_lock_bh(&addrconf_hash_lock);
- while ((ifa = *bifa) != NULL) {
- if (ifa->idev == idev) {
- *bifa = ifa->lst_next;
- ifa->lst_next = NULL;
- addrconf_del_timer(ifa);
- in6_ifa_put(ifa);
- continue;
- }
- bifa = &ifa->lst_next;
- }
- write_unlock_bh(&addrconf_hash_lock);
- }
-
write_lock_bh(&idev->lock);
- /* Step 3: clear flags for stateless addrconf */
+ /* Step 2: clear flags for stateless addrconf */
if (!how)
idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY);
- /* Step 4: clear address list */
#ifdef CONFIG_IPV6_PRIVACY
if (how && del_timer(&idev->regen_timer))
in6_dev_put(idev);
- /* clear tempaddr list */
- while ((ifa = idev->tempaddr_list) != NULL) {
- idev->tempaddr_list = ifa->tmp_next;
- ifa->tmp_next = NULL;
- ifa->dead = 1;
+ /* Step 3: clear tempaddr list */
+ while (!list_empty(&idev->tempaddr_list)) {
+ ifa = list_first_entry(&idev->tempaddr_list,
+ struct inet6_ifaddr, tmp_list);
+ list_del(&ifa->tmp_list);
write_unlock_bh(&idev->lock);
spin_lock_bh(&ifa->lock);
@@ -2686,23 +2708,70 @@ static int addrconf_ifdown(struct net_device *dev, int how)
write_lock_bh(&idev->lock);
}
#endif
- while ((ifa = idev->addr_list) != NULL) {
- idev->addr_list = ifa->if_next;
- ifa->if_next = NULL;
- ifa->dead = 1;
+
+ while (!list_empty(&idev->addr_list)) {
+ ifa = list_first_entry(&idev->addr_list,
+ struct inet6_ifaddr, if_list);
addrconf_del_timer(ifa);
- write_unlock_bh(&idev->lock);
+
+ /* If just doing link down, and address is permanent
+ and not link-local, then retain it. */
+ if (!how &&
+ (ifa->flags&IFA_F_PERMANENT) &&
+ !(ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)) {
+ list_move_tail(&ifa->if_list, &keep_list);
+
+ /* If not doing DAD on this address, just keep it. */
+ if ((dev->flags&(IFF_NOARP|IFF_LOOPBACK)) ||
+ idev->cnf.accept_dad <= 0 ||
+ (ifa->flags & IFA_F_NODAD))
+ continue;
+
+ /* If it was tentative already, no need to notify */
+ if (ifa->flags & IFA_F_TENTATIVE)
+ continue;
+
+ /* Flag it for later restoration when link comes up */
+ ifa->flags |= IFA_F_TENTATIVE;
+ ifa->state = INET6_IFADDR_STATE_DAD;
+
+ write_unlock_bh(&idev->lock);
+
+ in6_ifa_hold(ifa);
+ } else {
+ list_del(&ifa->if_list);
+
+ /* clear hash table */
+ spin_lock_bh(&addrconf_hash_lock);
+ hlist_del_init_rcu(&ifa->addr_lst);
+ spin_unlock_bh(&addrconf_hash_lock);
+
+ write_unlock_bh(&idev->lock);
+ spin_lock_bh(&ifa->state_lock);
+ state = ifa->state;
+ ifa->state = INET6_IFADDR_STATE_DEAD;
+ spin_unlock_bh(&ifa->state_lock);
+
+ if (state == INET6_IFADDR_STATE_DEAD)
+ goto put_ifa;
+ }
__ipv6_ifa_notify(RTM_DELADDR, ifa);
- atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa);
+ if (ifa->state == INET6_IFADDR_STATE_DEAD)
+ atomic_notifier_call_chain(&inet6addr_chain,
+ NETDEV_DOWN, ifa);
+
+put_ifa:
in6_ifa_put(ifa);
write_lock_bh(&idev->lock);
}
+
+ list_splice(&keep_list, &idev->addr_list);
+
write_unlock_bh(&idev->lock);
/* Step 5: Discard multicast list */
-
if (how)
ipv6_mc_destroy_dev(idev);
else
@@ -2710,8 +2779,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
idev->tstamp = jiffies;
- /* Shot the device (if unregistered) */
-
+ /* Last: Shot the device (if unregistered) */
if (how) {
addrconf_sysctl_unregister(idev);
neigh_parms_release(&nd_tbl, idev->nd_parms);
@@ -2724,28 +2792,29 @@ static int addrconf_ifdown(struct net_device *dev, int how)
static void addrconf_rs_timer(unsigned long data)
{
struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data;
+ struct inet6_dev *idev = ifp->idev;
- if (ifp->idev->cnf.forwarding)
+ read_lock(&idev->lock);
+ if (idev->dead || !(idev->if_flags & IF_READY))
goto out;
- if (ifp->idev->if_flags & IF_RA_RCVD) {
- /*
- * Announcement received after solicitation
- * was sent
- */
+ if (idev->cnf.forwarding)
+ goto out;
+
+ /* Announcement received after solicitation was sent */
+ if (idev->if_flags & IF_RA_RCVD)
goto out;
- }
spin_lock(&ifp->lock);
- if (ifp->probes++ < ifp->idev->cnf.rtr_solicits) {
+ if (ifp->probes++ < idev->cnf.rtr_solicits) {
/* The wait after the last probe can be shorter */
addrconf_mod_timer(ifp, AC_RS,
- (ifp->probes == ifp->idev->cnf.rtr_solicits) ?
- ifp->idev->cnf.rtr_solicit_delay :
- ifp->idev->cnf.rtr_solicit_interval);
+ (ifp->probes == idev->cnf.rtr_solicits) ?
+ idev->cnf.rtr_solicit_delay :
+ idev->cnf.rtr_solicit_interval);
spin_unlock(&ifp->lock);
- ndisc_send_rs(ifp->idev->dev, &ifp->addr, &in6addr_linklocal_allrouters);
+ ndisc_send_rs(idev->dev, &ifp->addr, &in6addr_linklocal_allrouters);
} else {
spin_unlock(&ifp->lock);
/*
@@ -2753,10 +2822,11 @@ static void addrconf_rs_timer(unsigned long data)
* assumption any longer.
*/
printk(KERN_DEBUG "%s: no IPv6 routers present\n",
- ifp->idev->dev->name);
+ idev->dev->name);
}
out:
+ read_unlock(&idev->lock);
in6_ifa_put(ifp);
}
@@ -2787,16 +2857,16 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags)
net_srandom(ifp->addr.s6_addr32[3]);
read_lock_bh(&idev->lock);
- if (ifp->dead)
+ spin_lock(&ifp->lock);
+ if (ifp->state == INET6_IFADDR_STATE_DEAD)
goto out;
- spin_lock_bh(&ifp->lock);
if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) ||
idev->cnf.accept_dad < 1 ||
!(ifp->flags&IFA_F_TENTATIVE) ||
ifp->flags & IFA_F_NODAD) {
ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
- spin_unlock_bh(&ifp->lock);
+ spin_unlock(&ifp->lock);
read_unlock_bh(&idev->lock);
addrconf_dad_completed(ifp);
@@ -2804,7 +2874,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags)
}
if (!(idev->if_flags & IF_READY)) {
- spin_unlock_bh(&ifp->lock);
+ spin_unlock(&ifp->lock);
read_unlock_bh(&idev->lock);
/*
* If the device is not ready:
@@ -2820,12 +2890,12 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags)
* Optimistic nodes can start receiving
* Frames right away
*/
- if(ifp->flags & IFA_F_OPTIMISTIC)
+ if (ifp->flags & IFA_F_OPTIMISTIC)
ip6_ins_rt(ifp->rt);
addrconf_dad_kick(ifp);
- spin_unlock_bh(&ifp->lock);
out:
+ spin_unlock(&ifp->lock);
read_unlock_bh(&idev->lock);
}
@@ -2835,20 +2905,30 @@ static void addrconf_dad_timer(unsigned long data)
struct inet6_dev *idev = ifp->idev;
struct in6_addr mcaddr;
- read_lock_bh(&idev->lock);
- if (idev->dead) {
- read_unlock_bh(&idev->lock);
+ if (!ifp->probes && addrconf_dad_end(ifp))
+ goto out;
+
+ read_lock(&idev->lock);
+ if (idev->dead || !(idev->if_flags & IF_READY)) {
+ read_unlock(&idev->lock);
goto out;
}
- spin_lock_bh(&ifp->lock);
+
+ spin_lock(&ifp->lock);
+ if (ifp->state == INET6_IFADDR_STATE_DEAD) {
+ spin_unlock(&ifp->lock);
+ read_unlock(&idev->lock);
+ goto out;
+ }
+
if (ifp->probes == 0) {
/*
* DAD was successful
*/
ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
- spin_unlock_bh(&ifp->lock);
- read_unlock_bh(&idev->lock);
+ spin_unlock(&ifp->lock);
+ read_unlock(&idev->lock);
addrconf_dad_completed(ifp);
@@ -2857,8 +2937,8 @@ static void addrconf_dad_timer(unsigned long data)
ifp->probes--;
addrconf_mod_timer(ifp, AC_DAD, ifp->idev->nd_parms->retrans_time);
- spin_unlock_bh(&ifp->lock);
- read_unlock_bh(&idev->lock);
+ spin_unlock(&ifp->lock);
+ read_unlock(&idev->lock);
/* send a neighbour solicitation for our addr */
addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
@@ -2869,7 +2949,7 @@ out:
static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
{
- struct net_device * dev = ifp->idev->dev;
+ struct net_device *dev = ifp->idev->dev;
/*
* Configure the address for reception. Now it is valid.
@@ -2900,18 +2980,17 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
}
}
-static void addrconf_dad_run(struct inet6_dev *idev) {
+static void addrconf_dad_run(struct inet6_dev *idev)
+{
struct inet6_ifaddr *ifp;
read_lock_bh(&idev->lock);
- for (ifp = idev->addr_list; ifp; ifp = ifp->if_next) {
- spin_lock_bh(&ifp->lock);
- if (!(ifp->flags & IFA_F_TENTATIVE)) {
- spin_unlock_bh(&ifp->lock);
- continue;
- }
- spin_unlock_bh(&ifp->lock);
- addrconf_dad_kick(ifp);
+ list_for_each_entry(ifp, &idev->addr_list, if_list) {
+ spin_lock(&ifp->lock);
+ if (ifp->flags & IFA_F_TENTATIVE &&
+ ifp->state == INET6_IFADDR_STATE_DAD)
+ addrconf_dad_kick(ifp);
+ spin_unlock(&ifp->lock);
}
read_unlock_bh(&idev->lock);
}
@@ -2929,36 +3008,35 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq)
struct net *net = seq_file_net(seq);
for (state->bucket = 0; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) {
- ifa = inet6_addr_lst[state->bucket];
-
- while (ifa && !net_eq(dev_net(ifa->idev->dev), net))
- ifa = ifa->lst_next;
- if (ifa)
- break;
+ struct hlist_node *n;
+ hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket],
+ addr_lst)
+ if (net_eq(dev_net(ifa->idev->dev), net))
+ return ifa;
}
- return ifa;
+ return NULL;
}
-static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct inet6_ifaddr *ifa)
+static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
+ struct inet6_ifaddr *ifa)
{
struct if6_iter_state *state = seq->private;
struct net *net = seq_file_net(seq);
+ struct hlist_node *n = &ifa->addr_lst;
- ifa = ifa->lst_next;
-try_again:
- if (ifa) {
- if (!net_eq(dev_net(ifa->idev->dev), net)) {
- ifa = ifa->lst_next;
- goto try_again;
- }
- }
+ hlist_for_each_entry_continue_rcu_bh(ifa, n, addr_lst)
+ if (net_eq(dev_net(ifa->idev->dev), net))
+ return ifa;
- if (!ifa && ++state->bucket < IN6_ADDR_HSIZE) {
- ifa = inet6_addr_lst[state->bucket];
- goto try_again;
+ while (++state->bucket < IN6_ADDR_HSIZE) {
+ hlist_for_each_entry_rcu_bh(ifa, n,
+ &inet6_addr_lst[state->bucket], addr_lst) {
+ if (net_eq(dev_net(ifa->idev->dev), net))
+ return ifa;
+ }
}
- return ifa;
+ return NULL;
}
static struct inet6_ifaddr *if6_get_idx(struct seq_file *seq, loff_t pos)
@@ -2966,15 +3044,15 @@ static struct inet6_ifaddr *if6_get_idx(struct seq_file *seq, loff_t pos)
struct inet6_ifaddr *ifa = if6_get_first(seq);
if (ifa)
- while(pos && (ifa = if6_get_next(seq, ifa)) != NULL)
+ while (pos && (ifa = if6_get_next(seq, ifa)) != NULL)
--pos;
return pos ? NULL : ifa;
}
static void *if6_seq_start(struct seq_file *seq, loff_t *pos)
- __acquires(addrconf_hash_lock)
+ __acquires(rcu_bh)
{
- read_lock_bh(&addrconf_hash_lock);
+ rcu_read_lock_bh();
return if6_get_idx(seq, *pos);
}
@@ -2988,9 +3066,9 @@ static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos)
}
static void if6_seq_stop(struct seq_file *seq, void *v)
- __releases(addrconf_hash_lock)
+ __releases(rcu_bh)
{
- read_unlock_bh(&addrconf_hash_lock);
+ rcu_read_unlock_bh();
}
static int if6_seq_show(struct seq_file *seq, void *v)
@@ -3027,14 +3105,14 @@ static const struct file_operations if6_fops = {
.release = seq_release_net,
};
-static int if6_proc_net_init(struct net *net)
+static int __net_init if6_proc_net_init(struct net *net)
{
if (!proc_net_fops_create(net, "if_inet6", S_IRUGO, &if6_fops))
return -ENOMEM;
return 0;
}
-static void if6_proc_net_exit(struct net *net)
+static void __net_exit if6_proc_net_exit(struct net *net)
{
proc_net_remove(net, "if_inet6");
}
@@ -3060,10 +3138,12 @@ void if6_proc_exit(void)
int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr)
{
int ret = 0;
- struct inet6_ifaddr * ifp;
- u8 hash = ipv6_addr_hash(addr);
- read_lock_bh(&addrconf_hash_lock);
- for (ifp = inet6_addr_lst[hash]; ifp; ifp = ifp->lst_next) {
+ struct inet6_ifaddr *ifp = NULL;
+ struct hlist_node *n;
+ unsigned int hash = ipv6_addr_hash(addr);
+
+ rcu_read_lock_bh();
+ hlist_for_each_entry_rcu_bh(ifp, n, &inet6_addr_lst[hash], addr_lst) {
if (!net_eq(dev_net(ifp->idev->dev), net))
continue;
if (ipv6_addr_equal(&ifp->addr, addr) &&
@@ -3072,7 +3152,7 @@ int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr)
break;
}
}
- read_unlock_bh(&addrconf_hash_lock);
+ rcu_read_unlock_bh();
return ret;
}
#endif
@@ -3083,43 +3163,35 @@ int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr)
static void addrconf_verify(unsigned long foo)
{
+ unsigned long now, next, next_sec, next_sched;
struct inet6_ifaddr *ifp;
- unsigned long now, next;
+ struct hlist_node *node;
int i;
- spin_lock_bh(&addrconf_verify_lock);
+ rcu_read_lock_bh();
+ spin_lock(&addrconf_verify_lock);
now = jiffies;
- next = now + ADDR_CHECK_FREQUENCY;
+ next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
del_timer(&addr_chk_timer);
- for (i=0; i < IN6_ADDR_HSIZE; i++) {
-
+ for (i = 0; i < IN6_ADDR_HSIZE; i++) {
restart:
- read_lock(&addrconf_hash_lock);
- for (ifp=inet6_addr_lst[i]; ifp; ifp=ifp->lst_next) {
+ hlist_for_each_entry_rcu_bh(ifp, node,
+ &inet6_addr_lst[i], addr_lst) {
unsigned long age;
-#ifdef CONFIG_IPV6_PRIVACY
- unsigned long regen_advance;
-#endif
if (ifp->flags & IFA_F_PERMANENT)
continue;
spin_lock(&ifp->lock);
- age = (now - ifp->tstamp) / HZ;
-
-#ifdef CONFIG_IPV6_PRIVACY
- regen_advance = ifp->idev->cnf.regen_max_retry *
- ifp->idev->cnf.dad_transmits *
- ifp->idev->nd_parms->retrans_time / HZ;
-#endif
+ /* We try to batch several events at once. */
+ age = (now - ifp->tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
if (ifp->valid_lft != INFINITY_LIFE_TIME &&
age >= ifp->valid_lft) {
spin_unlock(&ifp->lock);
in6_ifa_hold(ifp);
- read_unlock(&addrconf_hash_lock);
ipv6_del_addr(ifp);
goto restart;
} else if (ifp->prefered_lft == INFINITY_LIFE_TIME) {
@@ -3141,7 +3213,6 @@ restart:
if (deprecate) {
in6_ifa_hold(ifp);
- read_unlock(&addrconf_hash_lock);
ipv6_ifa_notify(0, ifp);
in6_ifa_put(ifp);
@@ -3150,6 +3221,10 @@ restart:
#ifdef CONFIG_IPV6_PRIVACY
} else if ((ifp->flags&IFA_F_TEMPORARY) &&
!(ifp->flags&IFA_F_TENTATIVE)) {
+ unsigned long regen_advance = ifp->idev->cnf.regen_max_retry *
+ ifp->idev->cnf.dad_transmits *
+ ifp->idev->nd_parms->retrans_time / HZ;
+
if (age >= ifp->prefered_lft - regen_advance) {
struct inet6_ifaddr *ifpub = ifp->ifpub;
if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next))
@@ -3159,7 +3234,7 @@ restart:
in6_ifa_hold(ifp);
in6_ifa_hold(ifpub);
spin_unlock(&ifp->lock);
- read_unlock(&addrconf_hash_lock);
+
spin_lock(&ifpub->lock);
ifpub->regen_count = 0;
spin_unlock(&ifpub->lock);
@@ -3179,12 +3254,26 @@ restart:
spin_unlock(&ifp->lock);
}
}
- read_unlock(&addrconf_hash_lock);
}
- addr_chk_timer.expires = time_before(next, jiffies + HZ) ? jiffies + HZ : next;
+ next_sec = round_jiffies_up(next);
+ next_sched = next;
+
+ /* If rounded timeout is accurate enough, accept it. */
+ if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ))
+ next_sched = next_sec;
+
+ /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */
+ if (time_before(next_sched, jiffies + ADDRCONF_TIMER_FUZZ_MAX))
+ next_sched = jiffies + ADDRCONF_TIMER_FUZZ_MAX;
+
+ ADBG((KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n",
+ now, next, next_sec, next_sched));
+
+ addr_chk_timer.expires = next_sched;
add_timer(&addr_chk_timer);
- spin_unlock_bh(&addrconf_verify_lock);
+ spin_unlock(&addrconf_verify_lock);
+ rcu_read_unlock_bh();
}
static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local)
@@ -3474,8 +3563,7 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
return nlmsg_end(skb, nlh);
}
-enum addr_type_t
-{
+enum addr_type_t {
UNICAST_ADDR,
MULTICAST_ADDR,
ANYCAST_ADDR,
@@ -3486,7 +3574,6 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
struct netlink_callback *cb, enum addr_type_t type,
int s_ip_idx, int *p_ip_idx)
{
- struct inet6_ifaddr *ifa;
struct ifmcaddr6 *ifmca;
struct ifacaddr6 *ifaca;
int err = 1;
@@ -3494,11 +3581,12 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
read_lock_bh(&idev->lock);
switch (type) {
- case UNICAST_ADDR:
+ case UNICAST_ADDR: {
+ struct inet6_ifaddr *ifa;
+
/* unicast address incl. temp addr */
- for (ifa = idev->addr_list; ifa;
- ifa = ifa->if_next, ip_idx++) {
- if (ip_idx < s_ip_idx)
+ list_for_each_entry(ifa, &idev->addr_list, if_list) {
+ if (++ip_idx < s_ip_idx)
continue;
err = inet6_fill_ifaddr(skb, ifa,
NETLINK_CB(cb->skb).pid,
@@ -3509,6 +3597,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
break;
}
break;
+ }
case MULTICAST_ADDR:
/* multicast address */
for (ifmca = idev->mc_list; ifmca;
@@ -3570,10 +3659,11 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
hlist_for_each_entry_rcu(dev, node, head, index_hlist) {
if (idx < s_idx)
goto cont;
- if (idx > s_idx)
+ if (h > s_h || idx > s_idx)
s_ip_idx = 0;
ip_idx = 0;
- if ((idev = __in6_dev_get(dev)) == NULL)
+ idev = __in6_dev_get(dev);
+ if (!idev)
goto cont;
if (in6_dump_addrs(idev, skb, cb, type,
@@ -3640,12 +3730,14 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr* nlh,
if (ifm->ifa_index)
dev = __dev_get_by_index(net, ifm->ifa_index);
- if ((ifa = ipv6_get_ifaddr(net, addr, dev, 1)) == NULL) {
+ ifa = ipv6_get_ifaddr(net, addr, dev, 1);
+ if (!ifa) {
err = -EADDRNOTAVAIL;
goto errout;
}
- if ((skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_KERNEL)) == NULL) {
+ skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_KERNEL);
+ if (!skb) {
err = -ENOBUFS;
goto errout_ifa;
}
@@ -3752,8 +3844,8 @@ static inline size_t inet6_if_nlmsg_size(void)
);
}
-static inline void __snmp6_fill_stats(u64 *stats, void **mib, int items,
- int bytes)
+static inline void __snmp6_fill_stats(u64 *stats, void __percpu **mib,
+ int items, int bytes)
{
int i;
int pad = bytes - sizeof(u64) * items;
@@ -3770,12 +3862,12 @@ static inline void __snmp6_fill_stats(u64 *stats, void **mib, int items,
static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype,
int bytes)
{
- switch(attrtype) {
+ switch (attrtype) {
case IFLA_INET6_STATS:
- __snmp6_fill_stats(stats, (void **)idev->stats.ipv6, IPSTATS_MIB_MAX, bytes);
+ __snmp6_fill_stats(stats, (void __percpu **)idev->stats.ipv6, IPSTATS_MIB_MAX, bytes);
break;
case IFLA_INET6_ICMP6STATS:
- __snmp6_fill_stats(stats, (void **)idev->stats.icmpv6, ICMP6_MIB_MAX, bytes);
+ __snmp6_fill_stats(stats, (void __percpu **)idev->stats.icmpv6, ICMP6_MIB_MAX, bytes);
break;
}
}
@@ -4006,7 +4098,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
addrconf_leave_anycast(ifp);
addrconf_leave_solict(ifp->idev, &ifp->addr);
dst_hold(&ifp->rt->u.dst);
- if (ip6_del_rt(ifp->rt))
+
+ if (ifp->state == INET6_IFADDR_STATE_DEAD &&
+ ip6_del_rt(ifp->rt))
dst_free(&ifp->rt->u.dst);
break;
}
@@ -4028,12 +4122,15 @@ int addrconf_sysctl_forward(ctl_table *ctl, int write,
{
int *valp = ctl->data;
int val = *valp;
+ loff_t pos = *ppos;
int ret;
ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
if (write)
ret = addrconf_fixup_forwarding(ctl, valp, val);
+ if (ret)
+ *ppos = pos;
return ret;
}
@@ -4075,8 +4172,11 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int old)
if (p == &net->ipv6.devconf_dflt->disable_ipv6)
return 0;
- if (!rtnl_trylock())
+ if (!rtnl_trylock()) {
+ /* Restore the original values before restarting */
+ *p = old;
return restart_syscall();
+ }
if (p == &net->ipv6.devconf_all->disable_ipv6) {
__s32 newf = net->ipv6.devconf_all->disable_ipv6;
@@ -4095,12 +4195,15 @@ int addrconf_sysctl_disable(ctl_table *ctl, int write,
{
int *valp = ctl->data;
int val = *valp;
+ loff_t pos = *ppos;
int ret;
ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
if (write)
ret = addrconf_disable_ipv6(ctl, valp, val);
+ if (ret)
+ *ppos = pos;
return ret;
}
@@ -4113,211 +4216,211 @@ static struct addrconf_sysctl_table
.sysctl_header = NULL,
.addrconf_vars = {
{
- .procname = "forwarding",
- .data = &ipv6_devconf.forwarding,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = addrconf_sysctl_forward,
+ .procname = "forwarding",
+ .data = &ipv6_devconf.forwarding,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = addrconf_sysctl_forward,
},
{
- .procname = "hop_limit",
- .data = &ipv6_devconf.hop_limit,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "hop_limit",
+ .data = &ipv6_devconf.hop_limit,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "mtu",
- .data = &ipv6_devconf.mtu6,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "mtu",
+ .data = &ipv6_devconf.mtu6,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "accept_ra",
- .data = &ipv6_devconf.accept_ra,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "accept_ra",
+ .data = &ipv6_devconf.accept_ra,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "accept_redirects",
- .data = &ipv6_devconf.accept_redirects,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "accept_redirects",
+ .data = &ipv6_devconf.accept_redirects,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "autoconf",
- .data = &ipv6_devconf.autoconf,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "autoconf",
+ .data = &ipv6_devconf.autoconf,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "dad_transmits",
- .data = &ipv6_devconf.dad_transmits,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "dad_transmits",
+ .data = &ipv6_devconf.dad_transmits,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "router_solicitations",
- .data = &ipv6_devconf.rtr_solicits,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "router_solicitations",
+ .data = &ipv6_devconf.rtr_solicits,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "router_solicitation_interval",
- .data = &ipv6_devconf.rtr_solicit_interval,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
+ .procname = "router_solicitation_interval",
+ .data = &ipv6_devconf.rtr_solicit_interval,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .procname = "router_solicitation_delay",
- .data = &ipv6_devconf.rtr_solicit_delay,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
+ .procname = "router_solicitation_delay",
+ .data = &ipv6_devconf.rtr_solicit_delay,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .procname = "force_mld_version",
- .data = &ipv6_devconf.force_mld_version,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "force_mld_version",
+ .data = &ipv6_devconf.force_mld_version,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
#ifdef CONFIG_IPV6_PRIVACY
{
- .procname = "use_tempaddr",
- .data = &ipv6_devconf.use_tempaddr,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "use_tempaddr",
+ .data = &ipv6_devconf.use_tempaddr,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "temp_valid_lft",
- .data = &ipv6_devconf.temp_valid_lft,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "temp_valid_lft",
+ .data = &ipv6_devconf.temp_valid_lft,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "temp_prefered_lft",
- .data = &ipv6_devconf.temp_prefered_lft,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "temp_prefered_lft",
+ .data = &ipv6_devconf.temp_prefered_lft,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "regen_max_retry",
- .data = &ipv6_devconf.regen_max_retry,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "regen_max_retry",
+ .data = &ipv6_devconf.regen_max_retry,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "max_desync_factor",
- .data = &ipv6_devconf.max_desync_factor,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "max_desync_factor",
+ .data = &ipv6_devconf.max_desync_factor,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
#endif
{
- .procname = "max_addresses",
- .data = &ipv6_devconf.max_addresses,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "max_addresses",
+ .data = &ipv6_devconf.max_addresses,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "accept_ra_defrtr",
- .data = &ipv6_devconf.accept_ra_defrtr,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "accept_ra_defrtr",
+ .data = &ipv6_devconf.accept_ra_defrtr,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "accept_ra_pinfo",
- .data = &ipv6_devconf.accept_ra_pinfo,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "accept_ra_pinfo",
+ .data = &ipv6_devconf.accept_ra_pinfo,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
#ifdef CONFIG_IPV6_ROUTER_PREF
{
- .procname = "accept_ra_rtr_pref",
- .data = &ipv6_devconf.accept_ra_rtr_pref,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "accept_ra_rtr_pref",
+ .data = &ipv6_devconf.accept_ra_rtr_pref,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "router_probe_interval",
- .data = &ipv6_devconf.rtr_probe_interval,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
+ .procname = "router_probe_interval",
+ .data = &ipv6_devconf.rtr_probe_interval,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
},
#ifdef CONFIG_IPV6_ROUTE_INFO
{
- .procname = "accept_ra_rt_info_max_plen",
- .data = &ipv6_devconf.accept_ra_rt_info_max_plen,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "accept_ra_rt_info_max_plen",
+ .data = &ipv6_devconf.accept_ra_rt_info_max_plen,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
#endif
#endif
{
- .procname = "proxy_ndp",
- .data = &ipv6_devconf.proxy_ndp,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "proxy_ndp",
+ .data = &ipv6_devconf.proxy_ndp,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
- .procname = "accept_source_route",
- .data = &ipv6_devconf.accept_source_route,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "accept_source_route",
+ .data = &ipv6_devconf.accept_source_route,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
{
- .procname = "optimistic_dad",
- .data = &ipv6_devconf.optimistic_dad,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "optimistic_dad",
+ .data = &ipv6_devconf.optimistic_dad,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_IPV6_MROUTE
{
- .procname = "mc_forwarding",
- .data = &ipv6_devconf.mc_forwarding,
- .maxlen = sizeof(int),
- .mode = 0444,
- .proc_handler = proc_dointvec,
+ .procname = "mc_forwarding",
+ .data = &ipv6_devconf.mc_forwarding,
+ .maxlen = sizeof(int),
+ .mode = 0444,
+ .proc_handler = proc_dointvec,
},
#endif
{
- .procname = "disable_ipv6",
- .data = &ipv6_devconf.disable_ipv6,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = addrconf_sysctl_disable,
+ .procname = "disable_ipv6",
+ .data = &ipv6_devconf.disable_ipv6,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = addrconf_sysctl_disable,
},
{
- .procname = "accept_dad",
- .data = &ipv6_devconf.accept_dad,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "accept_dad",
+ .data = &ipv6_devconf.accept_dad,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
{
.procname = "force_tllao",
@@ -4353,8 +4456,8 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name,
if (t == NULL)
goto out;
- for (i=0; t->addrconf_vars[i].data; i++) {
- t->addrconf_vars[i].data += (char*)p - (char*)&ipv6_devconf;
+ for (i = 0; t->addrconf_vars[i].data; i++) {
+ t->addrconf_vars[i].data += (char *)p - (char *)&ipv6_devconf;
t->addrconf_vars[i].extra1 = idev; /* embedded; no ref */
t->addrconf_vars[i].extra2 = net;
}
@@ -4402,8 +4505,7 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p)
static void addrconf_sysctl_register(struct inet6_dev *idev)
{
- neigh_sysctl_register(idev->dev, idev->nd_parms, NET_IPV6,
- NET_IPV6_NEIGH, "ipv6",
+ neigh_sysctl_register(idev->dev, idev->nd_parms, "ipv6",
&ndisc_ifinfo_sysctl_change);
__addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name,
idev, &idev->cnf);
@@ -4418,7 +4520,7 @@ static void addrconf_sysctl_unregister(struct inet6_dev *idev)
#endif
-static int addrconf_init_net(struct net *net)
+static int __net_init addrconf_init_net(struct net *net)
{
int err;
struct ipv6_devconf *all, *dflt;
@@ -4467,7 +4569,7 @@ err_alloc_all:
return err;
}
-static void addrconf_exit_net(struct net *net)
+static void __net_exit addrconf_exit_net(struct net *net)
{
#ifdef CONFIG_SYSCTL
__addrconf_sysctl_unregister(net->ipv6.devconf_dflt);
@@ -4492,14 +4594,12 @@ int register_inet6addr_notifier(struct notifier_block *nb)
{
return atomic_notifier_chain_register(&inet6addr_chain, nb);
}
-
EXPORT_SYMBOL(register_inet6addr_notifier);
int unregister_inet6addr_notifier(struct notifier_block *nb)
{
- return atomic_notifier_chain_unregister(&inet6addr_chain,nb);
+ return atomic_notifier_chain_unregister(&inet6addr_chain, nb);
}
-
EXPORT_SYMBOL(unregister_inet6addr_notifier);
/*
@@ -4508,11 +4608,12 @@ EXPORT_SYMBOL(unregister_inet6addr_notifier);
int __init addrconf_init(void)
{
- int err;
+ int i, err;
- if ((err = ipv6_addr_label_init()) < 0) {
- printk(KERN_CRIT "IPv6 Addrconf: cannot initialize default policy table: %d.\n",
- err);
+ err = ipv6_addr_label_init();
+ if (err < 0) {
+ printk(KERN_CRIT "IPv6 Addrconf:"
+ " cannot initialize default policy table: %d.\n", err);
return err;
}
@@ -4543,6 +4644,9 @@ int __init addrconf_init(void)
if (err)
goto errlo;
+ for (i = 0; i < IN6_ADDR_HSIZE; i++)
+ INIT_HLIST_HEAD(&inet6_addr_lst[i]);
+
register_netdevice_notifier(&ipv6_dev_notf);
addrconf_verify(0);
@@ -4571,7 +4675,6 @@ errlo:
void addrconf_cleanup(void)
{
- struct inet6_ifaddr *ifa;
struct net_device *dev;
int i;
@@ -4591,20 +4694,10 @@ void addrconf_cleanup(void)
/*
* Check hash table.
*/
- write_lock_bh(&addrconf_hash_lock);
- for (i=0; i < IN6_ADDR_HSIZE; i++) {
- for (ifa=inet6_addr_lst[i]; ifa; ) {
- struct inet6_ifaddr *bifa;
-
- bifa = ifa;
- ifa = ifa->lst_next;
- printk(KERN_DEBUG "bug: IPv6 address leakage detected: ifa=%p\n", bifa);
- /* Do not free it; something is wrong.
- Now we can investigate it with debugger.
- */
- }
- }
- write_unlock_bh(&addrconf_hash_lock);
+ spin_lock_bh(&addrconf_hash_lock);
+ for (i = 0; i < IN6_ADDR_HSIZE; i++)
+ WARN_ON(!hlist_empty(&inet6_addr_lst[i]));
+ spin_unlock_bh(&addrconf_hash_lock);
del_timer(&addr_chk_timer);
rtnl_unlock();
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 3f82e9542eda..6b03826552e1 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -72,7 +72,7 @@ int __ipv6_addr_type(const struct in6_addr *addr)
IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.3 */
}
- return (IPV6_ADDR_RESERVED |
+ return (IPV6_ADDR_UNICAST |
IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.4 */
}
EXPORT_SYMBOL(__ipv6_addr_type);
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 6ff73c4c126a..8c4348cb1950 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -13,6 +13,7 @@
#include <linux/list.h>
#include <linux/rcupdate.h>
#include <linux/in6.h>
+#include <linux/slab.h>
#include <net/addrconf.h>
#include <linux/if_addrlabel.h>
#include <linux/netlink.h>
@@ -421,10 +422,6 @@ static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh,
ifal->ifal_prefixlen > 128)
return -EINVAL;
- if (ifal->ifal_index &&
- !__dev_get_by_index(net, ifal->ifal_index))
- return -EINVAL;
-
if (!tb[IFAL_ADDRESS])
return -EINVAL;
@@ -440,6 +437,10 @@ static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh,
switch(nlh->nlmsg_type) {
case RTM_NEWADDRLABEL:
+ if (ifal->ifal_index &&
+ !__dev_get_by_index(net, ifal->ifal_index))
+ return -EINVAL;
+
err = ip6addrlbl_add(net, pfx, ifal->ifal_prefixlen,
ifal->ifal_index, label,
nlh->nlmsg_flags & NLM_F_REPLACE);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 12e69d364dd5..e733942dafe1 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -36,6 +36,7 @@
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>
+#include <linux/slab.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
@@ -199,7 +200,7 @@ lookup_protocol:
inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk);
np->hop_limit = -1;
- np->mcast_hops = -1;
+ np->mcast_hops = IPV6_DEFAULT_MCASTHOPS;
np->mc_loop = 1;
np->pmtudisc = IPV6_PMTUDISC_WANT;
np->ipv6only = net->ipv6.sysctl.bindv6only;
@@ -416,6 +417,9 @@ void inet6_destroy_sock(struct sock *sk)
if ((skb = xchg(&np->pktoptions, NULL)) != NULL)
kfree_skb(skb);
+ if ((skb = xchg(&np->rxpmtu, NULL)) != NULL)
+ kfree_skb(skb);
+
/* Free flowlabels */
fl6_free_socklist(sk);
@@ -971,41 +975,41 @@ static void ipv6_packet_cleanup(void)
static int __net_init ipv6_init_mibs(struct net *net)
{
- if (snmp_mib_init((void **)net->mib.udp_stats_in6,
+ if (snmp_mib_init((void __percpu **)net->mib.udp_stats_in6,
sizeof (struct udp_mib)) < 0)
return -ENOMEM;
- if (snmp_mib_init((void **)net->mib.udplite_stats_in6,
+ if (snmp_mib_init((void __percpu **)net->mib.udplite_stats_in6,
sizeof (struct udp_mib)) < 0)
goto err_udplite_mib;
- if (snmp_mib_init((void **)net->mib.ipv6_statistics,
+ if (snmp_mib_init((void __percpu **)net->mib.ipv6_statistics,
sizeof(struct ipstats_mib)) < 0)
goto err_ip_mib;
- if (snmp_mib_init((void **)net->mib.icmpv6_statistics,
+ if (snmp_mib_init((void __percpu **)net->mib.icmpv6_statistics,
sizeof(struct icmpv6_mib)) < 0)
goto err_icmp_mib;
- if (snmp_mib_init((void **)net->mib.icmpv6msg_statistics,
+ if (snmp_mib_init((void __percpu **)net->mib.icmpv6msg_statistics,
sizeof(struct icmpv6msg_mib)) < 0)
goto err_icmpmsg_mib;
return 0;
err_icmpmsg_mib:
- snmp_mib_free((void **)net->mib.icmpv6_statistics);
+ snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics);
err_icmp_mib:
- snmp_mib_free((void **)net->mib.ipv6_statistics);
+ snmp_mib_free((void __percpu **)net->mib.ipv6_statistics);
err_ip_mib:
- snmp_mib_free((void **)net->mib.udplite_stats_in6);
+ snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6);
err_udplite_mib:
- snmp_mib_free((void **)net->mib.udp_stats_in6);
+ snmp_mib_free((void __percpu **)net->mib.udp_stats_in6);
return -ENOMEM;
}
-static void __net_exit ipv6_cleanup_mibs(struct net *net)
+static void ipv6_cleanup_mibs(struct net *net)
{
- snmp_mib_free((void **)net->mib.udp_stats_in6);
- snmp_mib_free((void **)net->mib.udplite_stats_in6);
- snmp_mib_free((void **)net->mib.ipv6_statistics);
- snmp_mib_free((void **)net->mib.icmpv6_statistics);
- snmp_mib_free((void **)net->mib.icmpv6msg_statistics);
+ snmp_mib_free((void __percpu **)net->mib.udp_stats_in6);
+ snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6);
+ snmp_mib_free((void __percpu **)net->mib.ipv6_statistics);
+ snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics);
+ snmp_mib_free((void __percpu **)net->mib.icmpv6msg_statistics);
}
static int __net_init inet6_net_init(struct net *net)
@@ -1042,7 +1046,7 @@ out:
#endif
}
-static void inet6_net_exit(struct net *net)
+static void __net_exit inet6_net_exit(struct net *net)
{
#ifdef CONFIG_PROC_FS
udp6_proc_exit(net);
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index c2f300c314be..ee82d4ef26ce 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -26,6 +26,7 @@
#include <crypto/hash.h>
#include <linux/module.h>
+#include <linux/slab.h>
#include <net/ip.h>
#include <net/ah.h>
#include <linux/crypto.h>
@@ -614,7 +615,7 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
type != ICMPV6_PKT_TOOBIG)
return;
- x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6);
+ x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6);
if (!x)
return;
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index f1c74c8ef9de..b5b07054508a 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -29,6 +29,7 @@
#include <linux/init.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/sock.h>
@@ -538,7 +539,7 @@ static const struct file_operations ac6_seq_fops = {
.release = seq_release_net,
};
-int ac6_proc_init(struct net *net)
+int __net_init ac6_proc_init(struct net *net)
{
if (!proc_net_fops_create(net, "anycast6", S_IRUGO, &ac6_seq_fops))
return -ENOMEM;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index e6f9cdf780fe..712684687c9a 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -21,6 +21,7 @@
#include <linux/in6.h>
#include <linux/ipv6.h>
#include <linux/route.h>
+#include <linux/slab.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
@@ -221,6 +222,8 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
if (!skb)
return;
+ skb->protocol = htons(ETH_P_IPV6);
+
serr = SKB_EXT_ERR(skb);
serr->ee.ee_errno = err;
serr->ee.ee_origin = SO_EE_ORIGIN_ICMP6;
@@ -254,6 +257,8 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info)
if (!skb)
return;
+ skb->protocol = htons(ETH_P_IPV6);
+
skb_put(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
iph = ipv6_hdr(skb);
@@ -277,6 +282,45 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info)
kfree_skb(skb);
}
+void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu)
+{
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6hdr *iph;
+ struct sk_buff *skb;
+ struct ip6_mtuinfo *mtu_info;
+
+ if (!np->rxopt.bits.rxpmtu)
+ return;
+
+ skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC);
+ if (!skb)
+ return;
+
+ skb_put(skb, sizeof(struct ipv6hdr));
+ skb_reset_network_header(skb);
+ iph = ipv6_hdr(skb);
+ ipv6_addr_copy(&iph->daddr, &fl->fl6_dst);
+
+ mtu_info = IP6CBMTU(skb);
+ if (!mtu_info) {
+ kfree_skb(skb);
+ return;
+ }
+
+ mtu_info->ip6m_mtu = mtu;
+ mtu_info->ip6m_addr.sin6_family = AF_INET6;
+ mtu_info->ip6m_addr.sin6_port = 0;
+ mtu_info->ip6m_addr.sin6_flowinfo = 0;
+ mtu_info->ip6m_addr.sin6_scope_id = fl->oif;
+ ipv6_addr_copy(&mtu_info->ip6m_addr.sin6_addr, &ipv6_hdr(skb)->daddr);
+
+ __skb_pull(skb, skb_tail_pointer(skb) - skb->data);
+ skb_reset_transport_header(skb);
+
+ skb = xchg(&np->rxpmtu, skb);
+ kfree_skb(skb);
+}
+
/*
* Handle MSG_ERRQUEUE
*/
@@ -318,7 +362,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
sin->sin6_flowinfo = 0;
sin->sin6_port = serr->port;
sin->sin6_scope_id = 0;
- if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) {
+ if (skb->protocol == htons(ETH_P_IPV6)) {
ipv6_addr_copy(&sin->sin6_addr,
(struct in6_addr *)(nh + serr->addr_offset));
if (np->sndflow)
@@ -340,7 +384,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
sin->sin6_family = AF_INET6;
sin->sin6_flowinfo = 0;
sin->sin6_scope_id = 0;
- if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) {
+ if (skb->protocol == htons(ETH_P_IPV6)) {
ipv6_addr_copy(&sin->sin6_addr, &ipv6_hdr(skb)->saddr);
if (np->rxopt.all)
datagram_recv_ctl(sk, msg, skb);
@@ -380,6 +424,54 @@ out:
return err;
}
+/*
+ * Handle IPV6_RECVPATHMTU
+ */
+int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
+{
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct sk_buff *skb;
+ struct sockaddr_in6 *sin;
+ struct ip6_mtuinfo mtu_info;
+ int err;
+ int copied;
+
+ err = -EAGAIN;
+ skb = xchg(&np->rxpmtu, NULL);
+ if (skb == NULL)
+ goto out;
+
+ copied = skb->len;
+ if (copied > len) {
+ msg->msg_flags |= MSG_TRUNC;
+ copied = len;
+ }
+ err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+ if (err)
+ goto out_free_skb;
+
+ sock_recv_timestamp(msg, sk, skb);
+
+ memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info));
+
+ sin = (struct sockaddr_in6 *)msg->msg_name;
+ if (sin) {
+ sin->sin6_family = AF_INET6;
+ sin->sin6_flowinfo = 0;
+ sin->sin6_port = 0;
+ sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
+ ipv6_addr_copy(&sin->sin6_addr, &mtu_info.ip6m_addr.sin6_addr);
+ }
+
+ put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);
+
+ err = copied;
+
+out_free_skb:
+ kfree_skb(skb);
+out:
+ return err;
+}
int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
@@ -496,7 +588,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
int datagram_send_ctl(struct net *net,
struct msghdr *msg, struct flowi *fl,
struct ipv6_txoptions *opt,
- int *hlimit, int *tclass)
+ int *hlimit, int *tclass, int *dontfrag)
{
struct in6_pktinfo *src_info;
struct cmsghdr *cmsg;
@@ -736,6 +828,25 @@ int datagram_send_ctl(struct net *net,
break;
}
+
+ case IPV6_DONTFRAG:
+ {
+ int df;
+
+ err = -EINVAL;
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) {
+ goto exit_f;
+ }
+
+ df = *(int *)CMSG_DATA(cmsg);
+ if (df < 0 || df > 1)
+ goto exit_f;
+
+ err = 0;
+ *dontfrag = df;
+
+ break;
+ }
default:
LIMIT_NETDEBUG(KERN_DEBUG "invalid cmsg type: %d\n",
cmsg->cmsg_type);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 668a46b655e6..ee9b93bdd6a2 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -365,7 +365,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
type != ICMPV6_PKT_TOOBIG)
return;
- x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6);
+ x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6);
if (!x)
return;
printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%pI6\n",
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 4bac362b1335..8a659f92d17a 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -29,6 +29,7 @@
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/icmpv6.h>
+#include <linux/slab.h>
#include <net/dst.h>
#include <net/sock.h>
@@ -481,7 +482,7 @@ looped_back:
IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_INHDRERRORS);
icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
- 0, skb->dev);
+ 0);
kfree_skb(skb);
return -1;
}
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index b7aa7c64cc4a..8e44f8f9c188 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -84,18 +84,11 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
if ((rule->flags & FIB_RULE_FIND_SADDR) &&
r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) {
struct in6_addr saddr;
- unsigned int srcprefs = 0;
-
- if (flags & RT6_LOOKUP_F_SRCPREF_TMP)
- srcprefs |= IPV6_PREFER_SRC_TMP;
- if (flags & RT6_LOOKUP_F_SRCPREF_PUBLIC)
- srcprefs |= IPV6_PREFER_SRC_PUBLIC;
- if (flags & RT6_LOOKUP_F_SRCPREF_COA)
- srcprefs |= IPV6_PREFER_SRC_COA;
if (ipv6_dev_get_saddr(net,
ip6_dst_idev(&rt->u.dst)->dev,
- &flp->fl6_dst, srcprefs,
+ &flp->fl6_dst,
+ rt6_flags2srcprefs(flags),
&saddr))
goto again;
if (!ipv6_prefix_equal(&saddr, &r->src.addr,
@@ -215,7 +208,6 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
{
struct fib6_rule *rule6 = (struct fib6_rule *) rule;
- frh->family = AF_INET6;
frh->dst_len = rule6->dst.plen;
frh->src_len = rule6->src.plen;
frh->tos = rule6->tclass;
@@ -245,7 +237,7 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule)
+ nla_total_size(16); /* src */
}
-static struct fib_rules_ops fib6_rules_ops_template = {
+static const struct fib_rules_ops __net_initdata fib6_rules_ops_template = {
.family = AF_INET6,
.rule_size = sizeof(struct fib6_rule),
.addr_size = sizeof(struct in6_addr),
@@ -262,7 +254,7 @@ static struct fib_rules_ops fib6_rules_ops_template = {
.fro_net = &init_net,
};
-static int fib6_rules_net_init(struct net *net)
+static int __net_init fib6_rules_net_init(struct net *net)
{
struct fib_rules_ops *ops;
int err = -ENOMEM;
@@ -291,7 +283,7 @@ out_fib6_rules_ops:
goto out;
}
-static void fib6_rules_net_exit(struct net *net)
+static void __net_exit fib6_rules_net_exit(struct net *net)
{
fib_rules_unregister(net->ipv6.fib6_rules_ops);
}
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 4ae661bc3677..03e62f94ff8e 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -40,6 +40,7 @@
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/netfilter.h>
+#include <linux/slab.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
@@ -67,11 +68,6 @@
#include <asm/uaccess.h>
#include <asm/system.h>
-DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics) __read_mostly;
-EXPORT_SYMBOL(icmpv6_statistics);
-DEFINE_SNMP_STAT(struct icmpv6msg_mib, icmpv6msg_statistics) __read_mostly;
-EXPORT_SYMBOL(icmpv6msg_statistics);
-
/*
* The ICMP socket(s). This is the most convenient way to flow control
* our ICMP output as well as maintain a clean interface throughout
@@ -119,7 +115,7 @@ static __inline__ void icmpv6_xmit_unlock(struct sock *sk)
*/
void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
{
- icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev);
+ icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos);
kfree_skb(skb);
}
@@ -305,8 +301,7 @@ static inline void mip6_addr_swap(struct sk_buff *skb) {}
/*
* Send an ICMP message in response to a packet in error
*/
-void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
- struct net_device *dev)
+void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
{
struct net *net = dev_net(skb->dev);
struct inet6_dev *idev = NULL;
@@ -486,8 +481,9 @@ route_done:
len + sizeof(struct icmp6hdr),
sizeof(struct icmp6hdr), hlimit,
np->tclass, NULL, &fl, (struct rt6_info*)dst,
- MSG_DONTWAIT);
+ MSG_DONTWAIT, np->dontfrag);
if (err) {
+ ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
ip6_flush_pending_frames(sk);
goto out_put;
}
@@ -565,9 +561,11 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),
sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl,
- (struct rt6_info*)dst, MSG_DONTWAIT);
+ (struct rt6_info*)dst, MSG_DONTWAIT,
+ np->dontfrag);
if (err) {
+ ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
ip6_flush_pending_frames(sk);
goto out_put;
}
@@ -951,7 +949,7 @@ ctl_table ipv6_icmp_table_template[] = {
{ },
};
-struct ctl_table *ipv6_icmp_sysctl_init(struct net *net)
+struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
{
struct ctl_table *table;
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 3516e6fe2e56..0c5e3c3b7fd5 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -17,6 +17,7 @@
#include <linux/in6.h>
#include <linux/ipv6.h>
#include <linux/jhash.h>
+#include <linux/slab.h>
#include <net/addrconf.h>
#include <net/inet_connection_sock.h>
@@ -177,7 +178,7 @@ struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie)
return dst;
}
-int inet6_csk_xmit(struct sk_buff *skb, int ipfragok)
+int inet6_csk_xmit(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
struct inet_sock *inet = inet_sk(sk);
@@ -233,7 +234,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok)
/* Restore final destination back after routing done */
ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
- return ip6_xmit(sk, skb, &fl, np->opt, 0);
+ return ip6_xmit(sk, skb, &fl, np->opt);
}
EXPORT_SYMBOL_GPL(inet6_csk_xmit);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 0e93ca56eb69..92a122b7795d 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -26,6 +26,7 @@
#include <linux/in6.h>
#include <linux/init.h>
#include <linux/list.h>
+#include <linux/slab.h>
#ifdef CONFIG_PROC_FS
#include <linux/proc_fs.h>
@@ -93,29 +94,20 @@ static __u32 rt_sernum;
static void fib6_gc_timer_cb(unsigned long arg);
-static struct fib6_walker_t fib6_walker_list = {
- .prev = &fib6_walker_list,
- .next = &fib6_walker_list,
-};
-
-#define FOR_WALKERS(w) for ((w)=fib6_walker_list.next; (w) != &fib6_walker_list; (w)=(w)->next)
+static LIST_HEAD(fib6_walkers);
+#define FOR_WALKERS(w) list_for_each_entry(w, &fib6_walkers, lh)
static inline void fib6_walker_link(struct fib6_walker_t *w)
{
write_lock_bh(&fib6_walker_lock);
- w->next = fib6_walker_list.next;
- w->prev = &fib6_walker_list;
- w->next->prev = w;
- w->prev->next = w;
+ list_add(&w->lh, &fib6_walkers);
write_unlock_bh(&fib6_walker_lock);
}
static inline void fib6_walker_unlink(struct fib6_walker_t *w)
{
write_lock_bh(&fib6_walker_lock);
- w->next->prev = w->prev;
- w->prev->next = w->next;
- w->prev = w->next = w;
+ list_del(&w->lh);
write_unlock_bh(&fib6_walker_lock);
}
static __inline__ u32 fib6_new_sernum(void)
@@ -136,12 +128,24 @@ static __inline__ u32 fib6_new_sernum(void)
/*
* test bit
*/
+#if defined(__LITTLE_ENDIAN)
+# define BITOP_BE32_SWIZZLE (0x1F & ~7)
+#else
+# define BITOP_BE32_SWIZZLE 0
+#endif
static __inline__ __be32 addr_bit_set(void *token, int fn_bit)
{
__be32 *addr = token;
-
- return htonl(1 << ((~fn_bit)&0x1F)) & addr[fn_bit>>5];
+ /*
+ * Here,
+ * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)
+ * is optimized version of
+ * htonl(1 << ((~fn_bit)&0x1F))
+ * See include/asm-generic/bitops/le.h.
+ */
+ return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) &
+ addr[fn_bit >> 5];
}
static __inline__ struct fib6_node * node_alloc(void)
@@ -239,7 +243,7 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id)
return NULL;
}
-static void fib6_tables_init(struct net *net)
+static void __net_init fib6_tables_init(struct net *net)
{
fib6_link_table(net, net->ipv6.fib6_main_tbl);
fib6_link_table(net, net->ipv6.fib6_local_tbl);
@@ -262,7 +266,7 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl,
return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl, flags);
}
-static void fib6_tables_init(struct net *net)
+static void __net_init fib6_tables_init(struct net *net)
{
fib6_link_table(net, net->ipv6.fib6_main_tbl);
}
@@ -319,12 +323,26 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb,
w->root = &table->tb6_root;
if (cb->args[4] == 0) {
+ w->count = 0;
+ w->skip = 0;
+
read_lock_bh(&table->tb6_lock);
res = fib6_walk(w);
read_unlock_bh(&table->tb6_lock);
- if (res > 0)
+ if (res > 0) {
cb->args[4] = 1;
+ cb->args[5] = w->root->fn_sernum;
+ }
} else {
+ if (cb->args[5] != w->root->fn_sernum) {
+ /* Begin at the root if the tree changed */
+ cb->args[5] = w->root->fn_sernum;
+ w->state = FWS_INIT;
+ w->node = w->root;
+ w->skip = w->count;
+ } else
+ w->skip = 0;
+
read_lock_bh(&table->tb6_lock);
res = fib6_walk_continue(w);
read_unlock_bh(&table->tb6_lock);
@@ -1250,9 +1268,18 @@ static int fib6_walk_continue(struct fib6_walker_t *w)
w->leaf = fn->leaf;
case FWS_C:
if (w->leaf && fn->fn_flags&RTN_RTINFO) {
- int err = w->func(w);
+ int err;
+
+ if (w->count < w->skip) {
+ w->count++;
+ continue;
+ }
+
+ err = w->func(w);
if (err)
return err;
+
+ w->count++;
continue;
}
w->state = FWS_U;
@@ -1346,6 +1373,8 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
c.w.root = root;
c.w.func = fib6_clean_node;
c.w.prune = prune;
+ c.w.count = 0;
+ c.w.skip = 0;
c.func = func;
c.arg = arg;
c.net = net;
@@ -1469,7 +1498,7 @@ static void fib6_gc_timer_cb(unsigned long arg)
fib6_run_gc(0, (struct net *)arg);
}
-static int fib6_net_init(struct net *net)
+static int __net_init fib6_net_init(struct net *net)
{
setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net);
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 6e7bffa2205e..13654686aeab 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -20,6 +20,7 @@
#include <linux/route.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/sock.h>
@@ -154,7 +155,7 @@ static void ip6_fl_gc(unsigned long dummy)
write_unlock(&ip6_fl_lock);
}
-static void ip6_fl_purge(struct net *net)
+static void __net_exit ip6_fl_purge(struct net *net)
{
int i;
@@ -359,7 +360,8 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval,
msg.msg_control = (void*)(fl->opt+1);
flowi.oif = 0;
- err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk, &junk);
+ err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk,
+ &junk, &junk);
if (err)
goto done;
err = -EINVAL;
@@ -735,7 +737,7 @@ static const struct file_operations ip6fl_seq_fops = {
.release = seq_release_net,
};
-static int ip6_flowlabel_proc_init(struct net *net)
+static int __net_init ip6_flowlabel_proc_init(struct net *net)
{
if (!proc_net_fops_create(net, "ip6_flowlabel",
S_IRUGO, &ip6fl_seq_fops))
@@ -743,7 +745,7 @@ static int ip6_flowlabel_proc_init(struct net *net)
return 0;
}
-static void ip6_flowlabel_proc_fini(struct net *net)
+static void __net_exit ip6_flowlabel_proc_fini(struct net *net)
{
proc_net_remove(net, "ip6_flowlabel");
}
@@ -754,11 +756,10 @@ static inline int ip6_flowlabel_proc_init(struct net *net)
}
static inline void ip6_flowlabel_proc_fini(struct net *net)
{
- return ;
}
#endif
-static inline void ip6_flowlabel_net_exit(struct net *net)
+static void __net_exit ip6_flowlabel_net_exit(struct net *net)
{
ip6_fl_purge(net);
ip6_flowlabel_proc_fini(net);
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 237e2dba6e94..a83e9209cecc 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -28,6 +28,7 @@
#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>
@@ -142,7 +143,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
/* Must drop socket now because of tproxy. */
skb_orphan(skb);
- return NF_HOOK(PF_INET6, NF_INET_PRE_ROUTING, skb, dev, NULL,
+ return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, dev, NULL,
ip6_rcv_finish);
err:
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS);
@@ -216,8 +217,7 @@ resubmit:
IP6_INC_STATS_BH(net, idev,
IPSTATS_MIB_INUNKNOWNPROTOS);
icmpv6_send(skb, ICMPV6_PARAMPROB,
- ICMPV6_UNK_NEXTHDR, nhoff,
- skb->dev);
+ ICMPV6_UNK_NEXTHDR, nhoff);
}
} else
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS);
@@ -236,7 +236,7 @@ discard:
int ip6_input(struct sk_buff *skb)
{
- return NF_HOOK(PF_INET6, NF_INET_LOCAL_IN, skb, skb->dev, NULL,
+ return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN, skb, skb->dev, NULL,
ip6_input_finish);
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index eb6d09728633..89425af0684c 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -37,6 +37,7 @@
#include <linux/tcp.h>
#include <linux/route.h>
#include <linux/module.h>
+#include <linux/slab.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
@@ -66,8 +67,8 @@ int __ip6_local_out(struct sk_buff *skb)
len = 0;
ipv6_hdr(skb)->payload_len = htons(len);
- return nf_hook(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
- dst_output);
+ return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
+ skb_dst(skb)->dev, dst_output);
}
int ip6_local_out(struct sk_buff *skb)
@@ -82,22 +83,6 @@ int ip6_local_out(struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(ip6_local_out);
-static int ip6_output_finish(struct sk_buff *skb)
-{
- struct dst_entry *dst = skb_dst(skb);
-
- if (dst->hh)
- return neigh_hh_output(dst->hh, skb);
- else if (dst->neighbour)
- return dst->neighbour->output(skb);
-
- IP6_INC_STATS_BH(dev_net(dst->dev),
- ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
- kfree_skb(skb);
- return -EINVAL;
-
-}
-
/* dev_loopback_xmit for use with netfilter. */
static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
{
@@ -107,12 +92,11 @@ static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
newskb->ip_summed = CHECKSUM_UNNECESSARY;
WARN_ON(!skb_dst(newskb));
- netif_rx(newskb);
+ netif_rx_ni(newskb);
return 0;
}
-
-static int ip6_output2(struct sk_buff *skb)
+static int ip6_finish_output2(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
@@ -124,7 +108,7 @@ static int ip6_output2(struct sk_buff *skb)
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) &&
- ((mroute6_socket(dev_net(dev)) &&
+ ((mroute6_socket(dev_net(dev), skb) &&
!(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
&ipv6_hdr(skb)->saddr))) {
@@ -134,8 +118,8 @@ static int ip6_output2(struct sk_buff *skb)
is not supported in any case.
*/
if (newskb)
- NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, newskb,
- NULL, newskb->dev,
+ NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
+ newskb, NULL, newskb->dev,
ip6_dev_loopback_xmit);
if (ipv6_hdr(skb)->hop_limit == 0) {
@@ -150,8 +134,15 @@ static int ip6_output2(struct sk_buff *skb)
skb->len);
}
- return NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, skb, NULL, skb->dev,
- ip6_output_finish);
+ if (dst->hh)
+ return neigh_hh_output(dst->hh, skb);
+ else if (dst->neighbour)
+ return dst->neighbour->output(skb);
+
+ IP6_INC_STATS_BH(dev_net(dst->dev),
+ ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+ kfree_skb(skb);
+ return -EINVAL;
}
static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
@@ -162,29 +153,37 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
}
+static int ip6_finish_output(struct sk_buff *skb)
+{
+ if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
+ dst_allfrag(skb_dst(skb)))
+ return ip6_fragment(skb, ip6_finish_output2);
+ else
+ return ip6_finish_output2(skb);
+}
+
int ip6_output(struct sk_buff *skb)
{
+ struct net_device *dev = skb_dst(skb)->dev;
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
if (unlikely(idev->cnf.disable_ipv6)) {
- IP6_INC_STATS(dev_net(skb_dst(skb)->dev), idev,
+ IP6_INC_STATS(dev_net(dev), idev,
IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return 0;
}
- if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
- dst_allfrag(skb_dst(skb)))
- return ip6_fragment(skb, ip6_output2);
- else
- return ip6_output2(skb);
+ return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, dev,
+ ip6_finish_output,
+ !(IP6CB(skb)->flags & IP6SKB_REROUTED));
}
/*
- * xmit an sk_buff (used by TCP)
+ * xmit an sk_buff (used by TCP, SCTP and DCCP)
*/
int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
- struct ipv6_txoptions *opt, int ipfragok)
+ struct ipv6_txoptions *opt)
{
struct net *net = sock_net(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -217,8 +216,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
}
kfree_skb(skb);
skb = skb2;
- if (sk)
- skb_set_owner_w(skb, sk);
+ skb_set_owner_w(skb, sk);
}
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
@@ -230,10 +228,6 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
skb_reset_network_header(skb);
hdr = ipv6_hdr(skb);
- /* Allow local fragmentation. */
- if (ipfragok)
- skb->local_df = 1;
-
/*
* Fill in the IPv6 header
*/
@@ -260,14 +254,14 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) {
IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUT, skb->len);
- return NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev,
- dst_output);
+ return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
+ dst->dev, dst_output);
}
if (net_ratelimit())
printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n");
skb->dev = dst->dev;
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev);
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
@@ -402,6 +396,7 @@ int ip6_forward(struct sk_buff *skb)
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct inet6_skb_parm *opt = IP6CB(skb);
struct net *net = dev_net(dst->dev);
+ u32 mtu;
if (net->ipv6.devconf_all->forwarding == 0)
goto error;
@@ -441,8 +436,7 @@ int ip6_forward(struct sk_buff *skb)
if (hdr->hop_limit <= 1) {
/* Force OUTPUT device used as source address */
skb->dev = dst->dev;
- icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
- 0, skb->dev);
+ icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
IP6_INC_STATS_BH(net,
ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS);
@@ -504,15 +498,19 @@ int ip6_forward(struct sk_buff *skb)
goto error;
if (addrtype & IPV6_ADDR_LINKLOCAL) {
icmpv6_send(skb, ICMPV6_DEST_UNREACH,
- ICMPV6_NOT_NEIGHBOUR, 0, skb->dev);
+ ICMPV6_NOT_NEIGHBOUR, 0);
goto error;
}
}
- if (skb->len > dst_mtu(dst)) {
+ mtu = dst_mtu(dst);
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
+
+ if (skb->len > mtu && !skb_is_gso(skb)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, dst_mtu(dst), skb->dev);
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP6_INC_STATS_BH(net,
ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS);
IP6_INC_STATS_BH(net,
@@ -533,7 +531,7 @@ int ip6_forward(struct sk_buff *skb)
hdr->hop_limit--;
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
- return NF_HOOK(PF_INET6, NF_INET_FORWARD, skb, skb->dev, dst->dev,
+ return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dst->dev,
ip6_forward_finish);
error:
@@ -622,12 +620,11 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
mtu = ip6_skb_dst_mtu(skb);
/* We must not fragment if the socket is set to force MTU discovery
- * or if the skb it not generated by a local socket. (This last
- * check should be redundant, but it's free.)
+ * or if the skb it not generated by a local socket.
*/
- if (!skb->local_df) {
+ if (!skb->local_df && skb->len > mtu) {
skb->dev = skb_dst(skb)->dev;
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev);
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
@@ -1105,7 +1102,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi *fl,
- struct rt6_info *rt, unsigned int flags)
+ struct rt6_info *rt, unsigned int flags, int dontfrag)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -1219,15 +1216,23 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
*/
inet->cork.length += length;
- if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) &&
- (rt->u.dst.dev->features & NETIF_F_UFO)) {
+ if (length > mtu) {
+ int proto = sk->sk_protocol;
+ if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
+ ipv6_local_rxpmtu(sk, fl, mtu-exthdrlen);
+ return -EMSGSIZE;
+ }
- err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len,
- fragheaderlen, transhdrlen, mtu,
- flags);
- if (err)
- goto error;
- return 0;
+ if (proto == IPPROTO_UDP &&
+ (rt->u.dst.dev->features & NETIF_F_UFO)) {
+
+ err = ip6_ufo_append_data(sk, getfrag, from, length,
+ hh_len, fragheaderlen,
+ transhdrlen, mtu, flags);
+ if (err)
+ goto error;
+ return 0;
+ }
}
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index d453d07b0dfe..8f39893d8081 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -37,6 +37,7 @@
#include <linux/route.h>
#include <linux/rtnetlink.h>
#include <linux/netfilter_ipv6.h>
+#include <linux/slab.h>
#include <asm/uaccess.h>
#include <asm/atomic.h>
@@ -74,7 +75,6 @@ MODULE_LICENSE("GPL");
(addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \
(HASH_SIZE - 1))
-static void ip6_fb_tnl_dev_init(struct net_device *dev);
static void ip6_tnl_dev_init(struct net_device *dev);
static void ip6_tnl_dev_setup(struct net_device *dev);
@@ -623,7 +623,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (rt && rt->rt6i_dev)
skb2->dev = rt->rt6i_dev;
- icmpv6_send(skb2, rel_type, rel_code, rel_info, skb2->dev);
+ icmpv6_send(skb2, rel_type, rel_code, rel_info);
if (rt)
dst_release(&rt->u.dst);
@@ -723,14 +723,10 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
skb->protocol = htons(protocol);
skb->pkt_type = PACKET_HOST;
memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
- skb->dev = t->dev;
- skb_dst_drop(skb);
- nf_reset(skb);
- dscp_ecn_decapsulate(t, ipv6h, skb);
+ skb_tunnel_rx(skb, t->dev);
- t->dev->stats.rx_packets++;
- t->dev->stats.rx_bytes += skb->len;
+ dscp_ecn_decapsulate(t, ipv6h, skb);
netif_rx(skb);
rcu_read_unlock();
return 0;
@@ -1015,7 +1011,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
if (tel->encap_limit == 0) {
icmpv6_send(skb, ICMPV6_PARAMPROB,
- ICMPV6_HDR_FIELD, offset + 2, skb->dev);
+ ICMPV6_HDR_FIELD, offset + 2);
return -1;
}
encap_limit = tel->encap_limit - 1;
@@ -1034,7 +1030,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu);
if (err != 0) {
if (err == -EMSGSIZE)
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
return -1;
}
@@ -1364,7 +1360,7 @@ static void ip6_tnl_dev_init(struct net_device *dev)
* Return: 0
**/
-static void ip6_fb_tnl_dev_init(struct net_device *dev)
+static void __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = dev_net(dev);
@@ -1388,7 +1384,7 @@ static struct xfrm6_tunnel ip6ip6_handler = {
.priority = 1,
};
-static void ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
+static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
{
int h;
struct ip6_tnl *t;
@@ -1407,7 +1403,7 @@ static void ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
unregister_netdevice_many(&list);
}
-static int ip6_tnl_init_net(struct net *net)
+static int __net_init ip6_tnl_init_net(struct net *net)
{
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
int err;
@@ -1436,7 +1432,7 @@ err_alloc_dev:
return err;
}
-static void ip6_tnl_exit_net(struct net *net)
+static void __net_exit ip6_tnl_exit_net(struct net *net)
{
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
@@ -1462,27 +1458,29 @@ static int __init ip6_tunnel_init(void)
{
int err;
- if (xfrm6_tunnel_register(&ip4ip6_handler, AF_INET)) {
+ err = register_pernet_device(&ip6_tnl_net_ops);
+ if (err < 0)
+ goto out_pernet;
+
+ err = xfrm6_tunnel_register(&ip4ip6_handler, AF_INET);
+ if (err < 0) {
printk(KERN_ERR "ip6_tunnel init: can't register ip4ip6\n");
- err = -EAGAIN;
- goto out;
+ goto out_ip4ip6;
}
- if (xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6)) {
+ err = xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6);
+ if (err < 0) {
printk(KERN_ERR "ip6_tunnel init: can't register ip6ip6\n");
- err = -EAGAIN;
- goto unreg_ip4ip6;
+ goto out_ip6ip6;
}
- err = register_pernet_device(&ip6_tnl_net_ops);
- if (err < 0)
- goto err_pernet;
return 0;
-err_pernet:
- xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6);
-unreg_ip4ip6:
+
+out_ip6ip6:
xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET);
-out:
+out_ip4ip6:
+ unregister_pernet_device(&ip6_tnl_net_ops);
+out_pernet:
return err;
}
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 52e0f74fdfe0..66078dad7fe8 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -33,6 +33,7 @@
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
+#include <linux/slab.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/sock.h>
@@ -41,6 +42,7 @@
#include <linux/if_arp.h>
#include <net/checksum.h>
#include <net/netlink.h>
+#include <net/fib_rules.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
@@ -50,6 +52,34 @@
#include <linux/netfilter_ipv6.h>
#include <net/ip6_checksum.h>
+struct mr6_table {
+ struct list_head list;
+#ifdef CONFIG_NET_NS
+ struct net *net;
+#endif
+ u32 id;
+ struct sock *mroute6_sk;
+ struct timer_list ipmr_expire_timer;
+ struct list_head mfc6_unres_queue;
+ struct list_head mfc6_cache_array[MFC6_LINES];
+ struct mif_device vif6_table[MAXMIFS];
+ int maxvif;
+ atomic_t cache_resolve_queue_len;
+ int mroute_do_assert;
+ int mroute_do_pim;
+#ifdef CONFIG_IPV6_PIMSM_V2
+ int mroute_reg_vif_num;
+#endif
+};
+
+struct ip6mr_rule {
+ struct fib_rule common;
+};
+
+struct ip6mr_result {
+ struct mr6_table *mrt;
+};
+
/* Big lock, protecting vif table, mrt cache and mroute socket state.
Note that the changes are semaphored via rtnl_lock.
*/
@@ -60,9 +90,7 @@ static DEFINE_RWLOCK(mrt_lock);
* Multicast router control variables
*/
-#define MIF_EXISTS(_net, _idx) ((_net)->ipv6.vif6_table[_idx].dev != NULL)
-
-static struct mfc6_cache *mfc_unres_queue; /* Queue of unresolved entries */
+#define MIF_EXISTS(_mrt, _idx) ((_mrt)->vif6_table[_idx].dev != NULL)
/* Special spinlock for queue of unresolved entries */
static DEFINE_SPINLOCK(mfc_unres_lock);
@@ -77,20 +105,235 @@ static DEFINE_SPINLOCK(mfc_unres_lock);
static struct kmem_cache *mrt_cachep __read_mostly;
-static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache);
-static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt,
+static struct mr6_table *ip6mr_new_table(struct net *net, u32 id);
+static void ip6mr_free_table(struct mr6_table *mrt);
+
+static int ip6_mr_forward(struct net *net, struct mr6_table *mrt,
+ struct sk_buff *skb, struct mfc6_cache *cache);
+static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
mifi_t mifi, int assert);
-static int ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm);
-static void mroute_clean_tables(struct net *net);
+static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
+ struct mfc6_cache *c, struct rtmsg *rtm);
+static int ip6mr_rtm_dumproute(struct sk_buff *skb,
+ struct netlink_callback *cb);
+static void mroute_clean_tables(struct mr6_table *mrt);
+static void ipmr_expire_process(unsigned long arg);
+
+#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
+#define ip6mr_for_each_table(mrt, net) \
+ list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list)
+
+static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
+{
+ struct mr6_table *mrt;
+
+ ip6mr_for_each_table(mrt, net) {
+ if (mrt->id == id)
+ return mrt;
+ }
+ return NULL;
+}
+
+static int ip6mr_fib_lookup(struct net *net, struct flowi *flp,
+ struct mr6_table **mrt)
+{
+ struct ip6mr_result res;
+ struct fib_lookup_arg arg = { .result = &res, };
+ int err;
+
+ err = fib_rules_lookup(net->ipv6.mr6_rules_ops, flp, 0, &arg);
+ if (err < 0)
+ return err;
+ *mrt = res.mrt;
+ return 0;
+}
+
+static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp,
+ int flags, struct fib_lookup_arg *arg)
+{
+ struct ip6mr_result *res = arg->result;
+ struct mr6_table *mrt;
+
+ switch (rule->action) {
+ case FR_ACT_TO_TBL:
+ break;
+ case FR_ACT_UNREACHABLE:
+ return -ENETUNREACH;
+ case FR_ACT_PROHIBIT:
+ return -EACCES;
+ case FR_ACT_BLACKHOLE:
+ default:
+ return -EINVAL;
+ }
+
+ mrt = ip6mr_get_table(rule->fr_net, rule->table);
+ if (mrt == NULL)
+ return -EAGAIN;
+ res->mrt = mrt;
+ return 0;
+}
+
+static int ip6mr_rule_match(struct fib_rule *rule, struct flowi *flp, int flags)
+{
+ return 1;
+}
-static struct timer_list ipmr_expire_timer;
+static const struct nla_policy ip6mr_rule_policy[FRA_MAX + 1] = {
+ FRA_GENERIC_POLICY,
+};
+static int ip6mr_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
+ struct fib_rule_hdr *frh, struct nlattr **tb)
+{
+ return 0;
+}
+
+static int ip6mr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
+ struct nlattr **tb)
+{
+ return 1;
+}
+
+static int ip6mr_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
+ struct fib_rule_hdr *frh)
+{
+ frh->dst_len = 0;
+ frh->src_len = 0;
+ frh->tos = 0;
+ return 0;
+}
+
+static const struct fib_rules_ops __net_initdata ip6mr_rules_ops_template = {
+ .family = RTNL_FAMILY_IP6MR,
+ .rule_size = sizeof(struct ip6mr_rule),
+ .addr_size = sizeof(struct in6_addr),
+ .action = ip6mr_rule_action,
+ .match = ip6mr_rule_match,
+ .configure = ip6mr_rule_configure,
+ .compare = ip6mr_rule_compare,
+ .default_pref = fib_default_rule_pref,
+ .fill = ip6mr_rule_fill,
+ .nlgroup = RTNLGRP_IPV6_RULE,
+ .policy = ip6mr_rule_policy,
+ .owner = THIS_MODULE,
+};
+
+static int __net_init ip6mr_rules_init(struct net *net)
+{
+ struct fib_rules_ops *ops;
+ struct mr6_table *mrt;
+ int err;
+
+ ops = fib_rules_register(&ip6mr_rules_ops_template, net);
+ if (IS_ERR(ops))
+ return PTR_ERR(ops);
+
+ INIT_LIST_HEAD(&net->ipv6.mr6_tables);
+
+ mrt = ip6mr_new_table(net, RT6_TABLE_DFLT);
+ if (mrt == NULL) {
+ err = -ENOMEM;
+ goto err1;
+ }
+
+ err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT, 0);
+ if (err < 0)
+ goto err2;
+
+ net->ipv6.mr6_rules_ops = ops;
+ return 0;
+
+err2:
+ kfree(mrt);
+err1:
+ fib_rules_unregister(ops);
+ return err;
+}
+
+static void __net_exit ip6mr_rules_exit(struct net *net)
+{
+ struct mr6_table *mrt, *next;
+
+ list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) {
+ list_del(&mrt->list);
+ ip6mr_free_table(mrt);
+ }
+ fib_rules_unregister(net->ipv6.mr6_rules_ops);
+}
+#else
+#define ip6mr_for_each_table(mrt, net) \
+ for (mrt = net->ipv6.mrt6; mrt; mrt = NULL)
+
+static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
+{
+ return net->ipv6.mrt6;
+}
+
+static int ip6mr_fib_lookup(struct net *net, struct flowi *flp,
+ struct mr6_table **mrt)
+{
+ *mrt = net->ipv6.mrt6;
+ return 0;
+}
+
+static int __net_init ip6mr_rules_init(struct net *net)
+{
+ net->ipv6.mrt6 = ip6mr_new_table(net, RT6_TABLE_DFLT);
+ return net->ipv6.mrt6 ? 0 : -ENOMEM;
+}
+
+static void __net_exit ip6mr_rules_exit(struct net *net)
+{
+ ip6mr_free_table(net->ipv6.mrt6);
+}
+#endif
+
+static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
+{
+ struct mr6_table *mrt;
+ unsigned int i;
+
+ mrt = ip6mr_get_table(net, id);
+ if (mrt != NULL)
+ return mrt;
+
+ mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
+ if (mrt == NULL)
+ return NULL;
+ mrt->id = id;
+ write_pnet(&mrt->net, net);
+
+ /* Forwarding cache */
+ for (i = 0; i < MFC6_LINES; i++)
+ INIT_LIST_HEAD(&mrt->mfc6_cache_array[i]);
+
+ INIT_LIST_HEAD(&mrt->mfc6_unres_queue);
+
+ setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process,
+ (unsigned long)mrt);
+
+#ifdef CONFIG_IPV6_PIMSM_V2
+ mrt->mroute_reg_vif_num = -1;
+#endif
+#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
+ list_add_tail_rcu(&mrt->list, &net->ipv6.mr6_tables);
+#endif
+ return mrt;
+}
+
+static void ip6mr_free_table(struct mr6_table *mrt)
+{
+ del_timer(&mrt->ipmr_expire_timer);
+ mroute_clean_tables(mrt);
+ kfree(mrt);
+}
#ifdef CONFIG_PROC_FS
struct ipmr_mfc_iter {
struct seq_net_private p;
- struct mfc6_cache **cache;
+ struct mr6_table *mrt;
+ struct list_head *cache;
int ct;
};
@@ -98,22 +341,22 @@ struct ipmr_mfc_iter {
static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net,
struct ipmr_mfc_iter *it, loff_t pos)
{
+ struct mr6_table *mrt = it->mrt;
struct mfc6_cache *mfc;
- it->cache = net->ipv6.mfc6_cache_array;
read_lock(&mrt_lock);
- for (it->ct = 0; it->ct < MFC6_LINES; it->ct++)
- for (mfc = net->ipv6.mfc6_cache_array[it->ct];
- mfc; mfc = mfc->next)
+ for (it->ct = 0; it->ct < MFC6_LINES; it->ct++) {
+ it->cache = &mrt->mfc6_cache_array[it->ct];
+ list_for_each_entry(mfc, it->cache, list)
if (pos-- == 0)
return mfc;
+ }
read_unlock(&mrt_lock);
- it->cache = &mfc_unres_queue;
spin_lock_bh(&mfc_unres_lock);
- for (mfc = mfc_unres_queue; mfc; mfc = mfc->next)
- if (net_eq(mfc6_net(mfc), net) &&
- pos-- == 0)
+ it->cache = &mrt->mfc6_unres_queue;
+ list_for_each_entry(mfc, it->cache, list)
+ if (pos-- == 0)
return mfc;
spin_unlock_bh(&mfc_unres_lock);
@@ -121,15 +364,13 @@ static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net,
return NULL;
}
-
-
-
/*
* The /proc interfaces to multicast routing /proc/ip6_mr_cache /proc/ip6_mr_vif
*/
struct ipmr_vif_iter {
struct seq_net_private p;
+ struct mr6_table *mrt;
int ct;
};
@@ -137,11 +378,13 @@ static struct mif_device *ip6mr_vif_seq_idx(struct net *net,
struct ipmr_vif_iter *iter,
loff_t pos)
{
- for (iter->ct = 0; iter->ct < net->ipv6.maxvif; ++iter->ct) {
- if (!MIF_EXISTS(net, iter->ct))
+ struct mr6_table *mrt = iter->mrt;
+
+ for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) {
+ if (!MIF_EXISTS(mrt, iter->ct))
continue;
if (pos-- == 0)
- return &net->ipv6.vif6_table[iter->ct];
+ return &mrt->vif6_table[iter->ct];
}
return NULL;
}
@@ -149,7 +392,15 @@ static struct mif_device *ip6mr_vif_seq_idx(struct net *net,
static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(mrt_lock)
{
+ struct ipmr_vif_iter *iter = seq->private;
struct net *net = seq_file_net(seq);
+ struct mr6_table *mrt;
+
+ mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
+ if (mrt == NULL)
+ return ERR_PTR(-ENOENT);
+
+ iter->mrt = mrt;
read_lock(&mrt_lock);
return *pos ? ip6mr_vif_seq_idx(net, seq->private, *pos - 1)
@@ -160,15 +411,16 @@ static void *ip6mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct ipmr_vif_iter *iter = seq->private;
struct net *net = seq_file_net(seq);
+ struct mr6_table *mrt = iter->mrt;
++*pos;
if (v == SEQ_START_TOKEN)
return ip6mr_vif_seq_idx(net, iter, 0);
- while (++iter->ct < net->ipv6.maxvif) {
- if (!MIF_EXISTS(net, iter->ct))
+ while (++iter->ct < mrt->maxvif) {
+ if (!MIF_EXISTS(mrt, iter->ct))
continue;
- return &net->ipv6.vif6_table[iter->ct];
+ return &mrt->vif6_table[iter->ct];
}
return NULL;
}
@@ -181,7 +433,8 @@ static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v)
static int ip6mr_vif_seq_show(struct seq_file *seq, void *v)
{
- struct net *net = seq_file_net(seq);
+ struct ipmr_vif_iter *iter = seq->private;
+ struct mr6_table *mrt = iter->mrt;
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
@@ -192,7 +445,7 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v)
seq_printf(seq,
"%2td %-10s %8ld %7ld %8ld %7ld %05X\n",
- vif - net->ipv6.vif6_table,
+ vif - mrt->vif6_table,
name, vif->bytes_in, vif->pkt_in,
vif->bytes_out, vif->pkt_out,
vif->flags);
@@ -223,8 +476,15 @@ static const struct file_operations ip6mr_vif_fops = {
static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
{
+ struct ipmr_mfc_iter *it = seq->private;
struct net *net = seq_file_net(seq);
+ struct mr6_table *mrt;
+
+ mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
+ if (mrt == NULL)
+ return ERR_PTR(-ENOENT);
+ it->mrt = mrt;
return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1)
: SEQ_START_TOKEN;
}
@@ -234,35 +494,36 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
struct mfc6_cache *mfc = v;
struct ipmr_mfc_iter *it = seq->private;
struct net *net = seq_file_net(seq);
+ struct mr6_table *mrt = it->mrt;
++*pos;
if (v == SEQ_START_TOKEN)
return ipmr_mfc_seq_idx(net, seq->private, 0);
- if (mfc->next)
- return mfc->next;
+ if (mfc->list.next != it->cache)
+ return list_entry(mfc->list.next, struct mfc6_cache, list);
- if (it->cache == &mfc_unres_queue)
+ if (it->cache == &mrt->mfc6_unres_queue)
goto end_of_list;
- BUG_ON(it->cache != net->ipv6.mfc6_cache_array);
+ BUG_ON(it->cache != &mrt->mfc6_cache_array[it->ct]);
while (++it->ct < MFC6_LINES) {
- mfc = net->ipv6.mfc6_cache_array[it->ct];
- if (mfc)
- return mfc;
+ it->cache = &mrt->mfc6_cache_array[it->ct];
+ if (list_empty(it->cache))
+ continue;
+ return list_first_entry(it->cache, struct mfc6_cache, list);
}
/* exhausted cache_array, show unresolved */
read_unlock(&mrt_lock);
- it->cache = &mfc_unres_queue;
+ it->cache = &mrt->mfc6_unres_queue;
it->ct = 0;
spin_lock_bh(&mfc_unres_lock);
- mfc = mfc_unres_queue;
- if (mfc)
- return mfc;
+ if (!list_empty(it->cache))
+ return list_first_entry(it->cache, struct mfc6_cache, list);
end_of_list:
spin_unlock_bh(&mfc_unres_lock);
@@ -274,18 +535,17 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
{
struct ipmr_mfc_iter *it = seq->private;
- struct net *net = seq_file_net(seq);
+ struct mr6_table *mrt = it->mrt;
- if (it->cache == &mfc_unres_queue)
+ if (it->cache == &mrt->mfc6_unres_queue)
spin_unlock_bh(&mfc_unres_lock);
- else if (it->cache == net->ipv6.mfc6_cache_array)
+ else if (it->cache == mrt->mfc6_cache_array)
read_unlock(&mrt_lock);
}
static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
{
int n;
- struct net *net = seq_file_net(seq);
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
@@ -295,19 +555,20 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
} else {
const struct mfc6_cache *mfc = v;
const struct ipmr_mfc_iter *it = seq->private;
+ struct mr6_table *mrt = it->mrt;
seq_printf(seq, "%pI6 %pI6 %-3hd",
&mfc->mf6c_mcastgrp, &mfc->mf6c_origin,
mfc->mf6c_parent);
- if (it->cache != &mfc_unres_queue) {
+ if (it->cache != &mrt->mfc6_unres_queue) {
seq_printf(seq, " %8lu %8lu %8lu",
mfc->mfc_un.res.pkt,
mfc->mfc_un.res.bytes,
mfc->mfc_un.res.wrong_if);
for (n = mfc->mfc_un.res.minvif;
n < mfc->mfc_un.res.maxvif; n++) {
- if (MIF_EXISTS(net, n) &&
+ if (MIF_EXISTS(mrt, n) &&
mfc->mfc_un.res.ttls[n] < 255)
seq_printf(seq,
" %2d:%-3d",
@@ -354,7 +615,12 @@ static int pim6_rcv(struct sk_buff *skb)
struct ipv6hdr *encap;
struct net_device *reg_dev = NULL;
struct net *net = dev_net(skb->dev);
- int reg_vif_num = net->ipv6.mroute_reg_vif_num;
+ struct mr6_table *mrt;
+ struct flowi fl = {
+ .iif = skb->dev->ifindex,
+ .mark = skb->mark,
+ };
+ int reg_vif_num;
if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap)))
goto drop;
@@ -377,9 +643,13 @@ static int pim6_rcv(struct sk_buff *skb)
ntohs(encap->payload_len) + sizeof(*pim) > skb->len)
goto drop;
+ if (ip6mr_fib_lookup(net, &fl, &mrt) < 0)
+ goto drop;
+ reg_vif_num = mrt->mroute_reg_vif_num;
+
read_lock(&mrt_lock);
if (reg_vif_num >= 0)
- reg_dev = net->ipv6.vif6_table[reg_vif_num].dev;
+ reg_dev = mrt->vif6_table[reg_vif_num].dev;
if (reg_dev)
dev_hold(reg_dev);
read_unlock(&mrt_lock);
@@ -390,14 +660,12 @@ static int pim6_rcv(struct sk_buff *skb)
skb->mac_header = skb->network_header;
skb_pull(skb, (u8 *)encap - skb->data);
skb_reset_network_header(skb);
- skb->dev = reg_dev;
skb->protocol = htons(ETH_P_IPV6);
skb->ip_summed = 0;
skb->pkt_type = PACKET_HOST;
- skb_dst_drop(skb);
- reg_dev->stats.rx_bytes += skb->len;
- reg_dev->stats.rx_packets++;
- nf_reset(skb);
+
+ skb_tunnel_rx(skb, reg_dev);
+
netif_rx(skb);
dev_put(reg_dev);
return 0;
@@ -416,12 +684,22 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct net *net = dev_net(dev);
+ struct mr6_table *mrt;
+ struct flowi fl = {
+ .oif = dev->ifindex,
+ .iif = skb->skb_iif,
+ .mark = skb->mark,
+ };
+ int err;
+
+ err = ip6mr_fib_lookup(net, &fl, &mrt);
+ if (err < 0)
+ return err;
read_lock(&mrt_lock);
dev->stats.tx_bytes += skb->len;
dev->stats.tx_packets++;
- ip6mr_cache_report(net, skb, net->ipv6.mroute_reg_vif_num,
- MRT6MSG_WHOLEPKT);
+ ip6mr_cache_report(mrt, skb, mrt->mroute_reg_vif_num, MRT6MSG_WHOLEPKT);
read_unlock(&mrt_lock);
kfree_skb(skb);
return NETDEV_TX_OK;
@@ -441,11 +719,17 @@ static void reg_vif_setup(struct net_device *dev)
dev->features |= NETIF_F_NETNS_LOCAL;
}
-static struct net_device *ip6mr_reg_vif(struct net *net)
+static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt)
{
struct net_device *dev;
+ char name[IFNAMSIZ];
- dev = alloc_netdev(0, "pim6reg", reg_vif_setup);
+ if (mrt->id == RT6_TABLE_DFLT)
+ sprintf(name, "pim6reg");
+ else
+ sprintf(name, "pim6reg%u", mrt->id);
+
+ dev = alloc_netdev(0, name, reg_vif_setup);
if (dev == NULL)
return NULL;
@@ -477,15 +761,16 @@ failure:
* Delete a VIF entry
*/
-static int mif6_delete(struct net *net, int vifi, struct list_head *head)
+static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
{
struct mif_device *v;
struct net_device *dev;
struct inet6_dev *in6_dev;
- if (vifi < 0 || vifi >= net->ipv6.maxvif)
+
+ if (vifi < 0 || vifi >= mrt->maxvif)
return -EADDRNOTAVAIL;
- v = &net->ipv6.vif6_table[vifi];
+ v = &mrt->vif6_table[vifi];
write_lock_bh(&mrt_lock);
dev = v->dev;
@@ -497,17 +782,17 @@ static int mif6_delete(struct net *net, int vifi, struct list_head *head)
}
#ifdef CONFIG_IPV6_PIMSM_V2
- if (vifi == net->ipv6.mroute_reg_vif_num)
- net->ipv6.mroute_reg_vif_num = -1;
+ if (vifi == mrt->mroute_reg_vif_num)
+ mrt->mroute_reg_vif_num = -1;
#endif
- if (vifi + 1 == net->ipv6.maxvif) {
+ if (vifi + 1 == mrt->maxvif) {
int tmp;
for (tmp = vifi - 1; tmp >= 0; tmp--) {
- if (MIF_EXISTS(net, tmp))
+ if (MIF_EXISTS(mrt, tmp))
break;
}
- net->ipv6.maxvif = tmp + 1;
+ mrt->maxvif = tmp + 1;
}
write_unlock_bh(&mrt_lock);
@@ -527,7 +812,6 @@ static int mif6_delete(struct net *net, int vifi, struct list_head *head)
static inline void ip6mr_cache_free(struct mfc6_cache *c)
{
- release_net(mfc6_net(c));
kmem_cache_free(mrt_cachep, c);
}
@@ -535,12 +819,12 @@ static inline void ip6mr_cache_free(struct mfc6_cache *c)
and reporting error to netlink readers.
*/
-static void ip6mr_destroy_unres(struct mfc6_cache *c)
+static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c)
{
+ struct net *net = read_pnet(&mrt->net);
struct sk_buff *skb;
- struct net *net = mfc6_net(c);
- atomic_dec(&net->ipv6.cache_resolve_queue_len);
+ atomic_dec(&mrt->cache_resolve_queue_len);
while((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) {
if (ipv6_hdr(skb)->version == 0) {
@@ -558,60 +842,59 @@ static void ip6mr_destroy_unres(struct mfc6_cache *c)
}
-/* Single timer process for all the unresolved queue. */
+/* Timer process for all the unresolved queue. */
-static void ipmr_do_expire_process(unsigned long dummy)
+static void ipmr_do_expire_process(struct mr6_table *mrt)
{
unsigned long now = jiffies;
unsigned long expires = 10 * HZ;
- struct mfc6_cache *c, **cp;
+ struct mfc6_cache *c, *next;
- cp = &mfc_unres_queue;
-
- while ((c = *cp) != NULL) {
+ list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) {
if (time_after(c->mfc_un.unres.expires, now)) {
/* not yet... */
unsigned long interval = c->mfc_un.unres.expires - now;
if (interval < expires)
expires = interval;
- cp = &c->next;
continue;
}
- *cp = c->next;
- ip6mr_destroy_unres(c);
+ list_del(&c->list);
+ ip6mr_destroy_unres(mrt, c);
}
- if (mfc_unres_queue != NULL)
- mod_timer(&ipmr_expire_timer, jiffies + expires);
+ if (!list_empty(&mrt->mfc6_unres_queue))
+ mod_timer(&mrt->ipmr_expire_timer, jiffies + expires);
}
-static void ipmr_expire_process(unsigned long dummy)
+static void ipmr_expire_process(unsigned long arg)
{
+ struct mr6_table *mrt = (struct mr6_table *)arg;
+
if (!spin_trylock(&mfc_unres_lock)) {
- mod_timer(&ipmr_expire_timer, jiffies + 1);
+ mod_timer(&mrt->ipmr_expire_timer, jiffies + 1);
return;
}
- if (mfc_unres_queue != NULL)
- ipmr_do_expire_process(dummy);
+ if (!list_empty(&mrt->mfc6_unres_queue))
+ ipmr_do_expire_process(mrt);
spin_unlock(&mfc_unres_lock);
}
/* Fill oifs list. It is called under write locked mrt_lock. */
-static void ip6mr_update_thresholds(struct mfc6_cache *cache, unsigned char *ttls)
+static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *cache,
+ unsigned char *ttls)
{
int vifi;
- struct net *net = mfc6_net(cache);
cache->mfc_un.res.minvif = MAXMIFS;
cache->mfc_un.res.maxvif = 0;
memset(cache->mfc_un.res.ttls, 255, MAXMIFS);
- for (vifi = 0; vifi < net->ipv6.maxvif; vifi++) {
- if (MIF_EXISTS(net, vifi) &&
+ for (vifi = 0; vifi < mrt->maxvif; vifi++) {
+ if (MIF_EXISTS(mrt, vifi) &&
ttls[vifi] && ttls[vifi] < 255) {
cache->mfc_un.res.ttls[vifi] = ttls[vifi];
if (cache->mfc_un.res.minvif > vifi)
@@ -622,16 +905,17 @@ static void ip6mr_update_thresholds(struct mfc6_cache *cache, unsigned char *ttl
}
}
-static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock)
+static int mif6_add(struct net *net, struct mr6_table *mrt,
+ struct mif6ctl *vifc, int mrtsock)
{
int vifi = vifc->mif6c_mifi;
- struct mif_device *v = &net->ipv6.vif6_table[vifi];
+ struct mif_device *v = &mrt->vif6_table[vifi];
struct net_device *dev;
struct inet6_dev *in6_dev;
int err;
/* Is vif busy ? */
- if (MIF_EXISTS(net, vifi))
+ if (MIF_EXISTS(mrt, vifi))
return -EADDRINUSE;
switch (vifc->mif6c_flags) {
@@ -641,9 +925,9 @@ static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock)
* Special Purpose VIF in PIM
* All the packets will be sent to the daemon
*/
- if (net->ipv6.mroute_reg_vif_num >= 0)
+ if (mrt->mroute_reg_vif_num >= 0)
return -EADDRINUSE;
- dev = ip6mr_reg_vif(net);
+ dev = ip6mr_reg_vif(net, mrt);
if (!dev)
return -ENOBUFS;
err = dev_set_allmulti(dev, 1);
@@ -693,50 +977,48 @@ static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock)
v->dev = dev;
#ifdef CONFIG_IPV6_PIMSM_V2
if (v->flags & MIFF_REGISTER)
- net->ipv6.mroute_reg_vif_num = vifi;
+ mrt->mroute_reg_vif_num = vifi;
#endif
- if (vifi + 1 > net->ipv6.maxvif)
- net->ipv6.maxvif = vifi + 1;
+ if (vifi + 1 > mrt->maxvif)
+ mrt->maxvif = vifi + 1;
write_unlock_bh(&mrt_lock);
return 0;
}
-static struct mfc6_cache *ip6mr_cache_find(struct net *net,
+static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt,
struct in6_addr *origin,
struct in6_addr *mcastgrp)
{
int line = MFC6_HASH(mcastgrp, origin);
struct mfc6_cache *c;
- for (c = net->ipv6.mfc6_cache_array[line]; c; c = c->next) {
+ list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) {
if (ipv6_addr_equal(&c->mf6c_origin, origin) &&
ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp))
- break;
+ return c;
}
- return c;
+ return NULL;
}
/*
* Allocate a multicast cache entry
*/
-static struct mfc6_cache *ip6mr_cache_alloc(struct net *net)
+static struct mfc6_cache *ip6mr_cache_alloc(void)
{
struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
if (c == NULL)
return NULL;
c->mfc_un.res.minvif = MAXMIFS;
- mfc6_net_set(c, net);
return c;
}
-static struct mfc6_cache *ip6mr_cache_alloc_unres(struct net *net)
+static struct mfc6_cache *ip6mr_cache_alloc_unres(void)
{
struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC);
if (c == NULL)
return NULL;
skb_queue_head_init(&c->mfc_un.unres.unresolved);
c->mfc_un.unres.expires = jiffies + 10 * HZ;
- mfc6_net_set(c, net);
return c;
}
@@ -744,7 +1026,8 @@ static struct mfc6_cache *ip6mr_cache_alloc_unres(struct net *net)
* A cache entry has gone into a resolved state from queued
*/
-static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c)
+static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt,
+ struct mfc6_cache *uc, struct mfc6_cache *c)
{
struct sk_buff *skb;
@@ -757,7 +1040,7 @@ static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c)
int err;
struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr));
- if (ip6mr_fill_mroute(skb, c, NLMSG_DATA(nlh)) > 0) {
+ if (__ip6mr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) {
nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh;
} else {
nlh->nlmsg_type = NLMSG_ERROR;
@@ -765,9 +1048,9 @@ static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c)
skb_trim(skb, nlh->nlmsg_len);
((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -EMSGSIZE;
}
- err = rtnl_unicast(skb, mfc6_net(uc), NETLINK_CB(skb).pid);
+ err = rtnl_unicast(skb, net, NETLINK_CB(skb).pid);
} else
- ip6_mr_forward(skb, c);
+ ip6_mr_forward(net, mrt, skb, c);
}
}
@@ -778,8 +1061,8 @@ static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c)
* Called under mrt_lock.
*/
-static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi,
- int assert)
+static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
+ mifi_t mifi, int assert)
{
struct sk_buff *skb;
struct mrt6msg *msg;
@@ -815,7 +1098,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi,
msg = (struct mrt6msg *)skb_transport_header(skb);
msg->im6_mbz = 0;
msg->im6_msgtype = MRT6MSG_WHOLEPKT;
- msg->im6_mif = net->ipv6.mroute_reg_vif_num;
+ msg->im6_mif = mrt->mroute_reg_vif_num;
msg->im6_pad = 0;
ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr);
ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr);
@@ -850,7 +1133,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi,
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
- if (net->ipv6.mroute6_sk == NULL) {
+ if (mrt->mroute6_sk == NULL) {
kfree_skb(skb);
return -EINVAL;
}
@@ -858,7 +1141,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi,
/*
* Deliver to user space multicast routing algorithms
*/
- ret = sock_queue_rcv_skb(net->ipv6.mroute6_sk, skb);
+ ret = sock_queue_rcv_skb(mrt->mroute6_sk, skb);
if (ret < 0) {
if (net_ratelimit())
printk(KERN_WARNING "mroute6: pending queue full, dropping entries.\n");
@@ -873,26 +1156,28 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi,
*/
static int
-ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb)
+ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb)
{
+ bool found = false;
int err;
struct mfc6_cache *c;
spin_lock_bh(&mfc_unres_lock);
- for (c = mfc_unres_queue; c; c = c->next) {
- if (net_eq(mfc6_net(c), net) &&
- ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) &&
- ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr))
+ list_for_each_entry(c, &mrt->mfc6_unres_queue, list) {
+ if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) &&
+ ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) {
+ found = true;
break;
+ }
}
- if (c == NULL) {
+ if (!found) {
/*
* Create a new entry if allowable
*/
- if (atomic_read(&net->ipv6.cache_resolve_queue_len) >= 10 ||
- (c = ip6mr_cache_alloc_unres(net)) == NULL) {
+ if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 ||
+ (c = ip6mr_cache_alloc_unres()) == NULL) {
spin_unlock_bh(&mfc_unres_lock);
kfree_skb(skb);
@@ -909,7 +1194,7 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb)
/*
* Reflect first query at pim6sd
*/
- err = ip6mr_cache_report(net, skb, mifi, MRT6MSG_NOCACHE);
+ err = ip6mr_cache_report(mrt, skb, mifi, MRT6MSG_NOCACHE);
if (err < 0) {
/* If the report failed throw the cache entry
out - Brad Parker
@@ -921,11 +1206,10 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb)
return err;
}
- atomic_inc(&net->ipv6.cache_resolve_queue_len);
- c->next = mfc_unres_queue;
- mfc_unres_queue = c;
+ atomic_inc(&mrt->cache_resolve_queue_len);
+ list_add(&c->list, &mrt->mfc6_unres_queue);
- ipmr_do_expire_process(1);
+ ipmr_do_expire_process(mrt);
}
/*
@@ -947,19 +1231,18 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb)
* MFC6 cache manipulation by user space
*/
-static int ip6mr_mfc_delete(struct net *net, struct mf6cctl *mfc)
+static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc)
{
int line;
- struct mfc6_cache *c, **cp;
+ struct mfc6_cache *c, *next;
line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr);
- for (cp = &net->ipv6.mfc6_cache_array[line];
- (c = *cp) != NULL; cp = &c->next) {
+ list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[line], list) {
if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) &&
ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) {
write_lock_bh(&mrt_lock);
- *cp = c->next;
+ list_del(&c->list);
write_unlock_bh(&mrt_lock);
ip6mr_cache_free(c);
@@ -974,6 +1257,7 @@ static int ip6mr_device_event(struct notifier_block *this,
{
struct net_device *dev = ptr;
struct net *net = dev_net(dev);
+ struct mr6_table *mrt;
struct mif_device *v;
int ct;
LIST_HEAD(list);
@@ -981,10 +1265,12 @@ static int ip6mr_device_event(struct notifier_block *this,
if (event != NETDEV_UNREGISTER)
return NOTIFY_DONE;
- v = &net->ipv6.vif6_table[0];
- for (ct = 0; ct < net->ipv6.maxvif; ct++, v++) {
- if (v->dev == dev)
- mif6_delete(net, ct, &list);
+ ip6mr_for_each_table(mrt, net) {
+ v = &mrt->vif6_table[0];
+ for (ct = 0; ct < mrt->maxvif; ct++, v++) {
+ if (v->dev == dev)
+ mif6_delete(mrt, ct, &list);
+ }
}
unregister_netdevice_many(&list);
@@ -1001,26 +1287,11 @@ static struct notifier_block ip6_mr_notifier = {
static int __net_init ip6mr_net_init(struct net *net)
{
- int err = 0;
- net->ipv6.vif6_table = kcalloc(MAXMIFS, sizeof(struct mif_device),
- GFP_KERNEL);
- if (!net->ipv6.vif6_table) {
- err = -ENOMEM;
- goto fail;
- }
-
- /* Forwarding cache */
- net->ipv6.mfc6_cache_array = kcalloc(MFC6_LINES,
- sizeof(struct mfc6_cache *),
- GFP_KERNEL);
- if (!net->ipv6.mfc6_cache_array) {
- err = -ENOMEM;
- goto fail_mfc6_cache;
- }
+ int err;
-#ifdef CONFIG_IPV6_PIMSM_V2
- net->ipv6.mroute_reg_vif_num = -1;
-#endif
+ err = ip6mr_rules_init(net);
+ if (err < 0)
+ goto fail;
#ifdef CONFIG_PROC_FS
err = -ENOMEM;
@@ -1029,16 +1300,15 @@ static int __net_init ip6mr_net_init(struct net *net)
if (!proc_net_fops_create(net, "ip6_mr_cache", 0, &ip6mr_mfc_fops))
goto proc_cache_fail;
#endif
+
return 0;
#ifdef CONFIG_PROC_FS
proc_cache_fail:
proc_net_remove(net, "ip6_mr_vif");
proc_vif_fail:
- kfree(net->ipv6.mfc6_cache_array);
+ ip6mr_rules_exit(net);
#endif
-fail_mfc6_cache:
- kfree(net->ipv6.vif6_table);
fail:
return err;
}
@@ -1049,9 +1319,7 @@ static void __net_exit ip6mr_net_exit(struct net *net)
proc_net_remove(net, "ip6_mr_cache");
proc_net_remove(net, "ip6_mr_vif");
#endif
- mroute_clean_tables(net);
- kfree(net->ipv6.mfc6_cache_array);
- kfree(net->ipv6.vif6_table);
+ ip6mr_rules_exit(net);
}
static struct pernet_operations ip6mr_net_ops = {
@@ -1074,7 +1342,6 @@ int __init ip6_mr_init(void)
if (err)
goto reg_pernet_fail;
- setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0);
err = register_netdevice_notifier(&ip6_mr_notifier);
if (err)
goto reg_notif_fail;
@@ -1085,13 +1352,13 @@ int __init ip6_mr_init(void)
goto add_proto_fail;
}
#endif
+ rtnl_register(RTNL_FAMILY_IP6MR, RTM_GETROUTE, NULL, ip6mr_rtm_dumproute);
return 0;
#ifdef CONFIG_IPV6_PIMSM_V2
add_proto_fail:
unregister_netdevice_notifier(&ip6_mr_notifier);
#endif
reg_notif_fail:
- del_timer(&ipmr_expire_timer);
unregister_pernet_subsys(&ip6mr_net_ops);
reg_pernet_fail:
kmem_cache_destroy(mrt_cachep);
@@ -1101,18 +1368,22 @@ reg_pernet_fail:
void ip6_mr_cleanup(void)
{
unregister_netdevice_notifier(&ip6_mr_notifier);
- del_timer(&ipmr_expire_timer);
unregister_pernet_subsys(&ip6mr_net_ops);
kmem_cache_destroy(mrt_cachep);
}
-static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock)
+static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
+ struct mf6cctl *mfc, int mrtsock)
{
+ bool found = false;
int line;
- struct mfc6_cache *uc, *c, **cp;
+ struct mfc6_cache *uc, *c;
unsigned char ttls[MAXMIFS];
int i;
+ if (mfc->mf6cc_parent >= MAXMIFS)
+ return -ENFILE;
+
memset(ttls, 255, MAXMIFS);
for (i = 0; i < MAXMIFS; i++) {
if (IF_ISSET(i, &mfc->mf6cc_ifset))
@@ -1122,17 +1393,18 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock)
line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr);
- for (cp = &net->ipv6.mfc6_cache_array[line];
- (c = *cp) != NULL; cp = &c->next) {
+ list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) {
if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) &&
- ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr))
+ ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) {
+ found = true;
break;
+ }
}
- if (c != NULL) {
+ if (found) {
write_lock_bh(&mrt_lock);
c->mf6c_parent = mfc->mf6cc_parent;
- ip6mr_update_thresholds(c, ttls);
+ ip6mr_update_thresholds(mrt, c, ttls);
if (!mrtsock)
c->mfc_flags |= MFC_STATIC;
write_unlock_bh(&mrt_lock);
@@ -1142,43 +1414,42 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock)
if (!ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr))
return -EINVAL;
- c = ip6mr_cache_alloc(net);
+ c = ip6mr_cache_alloc();
if (c == NULL)
return -ENOMEM;
c->mf6c_origin = mfc->mf6cc_origin.sin6_addr;
c->mf6c_mcastgrp = mfc->mf6cc_mcastgrp.sin6_addr;
c->mf6c_parent = mfc->mf6cc_parent;
- ip6mr_update_thresholds(c, ttls);
+ ip6mr_update_thresholds(mrt, c, ttls);
if (!mrtsock)
c->mfc_flags |= MFC_STATIC;
write_lock_bh(&mrt_lock);
- c->next = net->ipv6.mfc6_cache_array[line];
- net->ipv6.mfc6_cache_array[line] = c;
+ list_add(&c->list, &mrt->mfc6_cache_array[line]);
write_unlock_bh(&mrt_lock);
/*
* Check to see if we resolved a queued list. If so we
* need to send on the frames and tidy up.
*/
+ found = false;
spin_lock_bh(&mfc_unres_lock);
- for (cp = &mfc_unres_queue; (uc = *cp) != NULL;
- cp = &uc->next) {
- if (net_eq(mfc6_net(uc), net) &&
- ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) &&
+ list_for_each_entry(uc, &mrt->mfc6_unres_queue, list) {
+ if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) &&
ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) {
- *cp = uc->next;
- atomic_dec(&net->ipv6.cache_resolve_queue_len);
+ list_del(&uc->list);
+ atomic_dec(&mrt->cache_resolve_queue_len);
+ found = true;
break;
}
}
- if (mfc_unres_queue == NULL)
- del_timer(&ipmr_expire_timer);
+ if (list_empty(&mrt->mfc6_unres_queue))
+ del_timer(&mrt->ipmr_expire_timer);
spin_unlock_bh(&mfc_unres_lock);
- if (uc) {
- ip6mr_cache_resolve(uc, c);
+ if (found) {
+ ip6mr_cache_resolve(net, mrt, uc, c);
ip6mr_cache_free(uc);
}
return 0;
@@ -1188,17 +1459,18 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock)
* Close the multicast socket, and clear the vif tables etc
*/
-static void mroute_clean_tables(struct net *net)
+static void mroute_clean_tables(struct mr6_table *mrt)
{
int i;
LIST_HEAD(list);
+ struct mfc6_cache *c, *next;
/*
* Shut down all active vif entries
*/
- for (i = 0; i < net->ipv6.maxvif; i++) {
- if (!(net->ipv6.vif6_table[i].flags & VIFF_STATIC))
- mif6_delete(net, i, &list);
+ for (i = 0; i < mrt->maxvif; i++) {
+ if (!(mrt->vif6_table[i].flags & VIFF_STATIC))
+ mif6_delete(mrt, i, &list);
}
unregister_netdevice_many(&list);
@@ -1206,48 +1478,36 @@ static void mroute_clean_tables(struct net *net)
* Wipe the cache
*/
for (i = 0; i < MFC6_LINES; i++) {
- struct mfc6_cache *c, **cp;
-
- cp = &net->ipv6.mfc6_cache_array[i];
- while ((c = *cp) != NULL) {
- if (c->mfc_flags & MFC_STATIC) {
- cp = &c->next;
+ list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) {
+ if (c->mfc_flags & MFC_STATIC)
continue;
- }
write_lock_bh(&mrt_lock);
- *cp = c->next;
+ list_del(&c->list);
write_unlock_bh(&mrt_lock);
ip6mr_cache_free(c);
}
}
- if (atomic_read(&net->ipv6.cache_resolve_queue_len) != 0) {
- struct mfc6_cache *c, **cp;
-
+ if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
spin_lock_bh(&mfc_unres_lock);
- cp = &mfc_unres_queue;
- while ((c = *cp) != NULL) {
- if (!net_eq(mfc6_net(c), net)) {
- cp = &c->next;
- continue;
- }
- *cp = c->next;
- ip6mr_destroy_unres(c);
+ list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) {
+ list_del(&c->list);
+ ip6mr_destroy_unres(mrt, c);
}
spin_unlock_bh(&mfc_unres_lock);
}
}
-static int ip6mr_sk_init(struct sock *sk)
+static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk)
{
int err = 0;
struct net *net = sock_net(sk);
rtnl_lock();
write_lock_bh(&mrt_lock);
- if (likely(net->ipv6.mroute6_sk == NULL)) {
- net->ipv6.mroute6_sk = sk;
+ if (likely(mrt->mroute6_sk == NULL)) {
+ mrt->mroute6_sk = sk;
net->ipv6.devconf_all->mc_forwarding++;
}
else
@@ -1261,24 +1521,43 @@ static int ip6mr_sk_init(struct sock *sk)
int ip6mr_sk_done(struct sock *sk)
{
- int err = 0;
+ int err = -EACCES;
struct net *net = sock_net(sk);
+ struct mr6_table *mrt;
rtnl_lock();
- if (sk == net->ipv6.mroute6_sk) {
- write_lock_bh(&mrt_lock);
- net->ipv6.mroute6_sk = NULL;
- net->ipv6.devconf_all->mc_forwarding--;
- write_unlock_bh(&mrt_lock);
+ ip6mr_for_each_table(mrt, net) {
+ if (sk == mrt->mroute6_sk) {
+ write_lock_bh(&mrt_lock);
+ mrt->mroute6_sk = NULL;
+ net->ipv6.devconf_all->mc_forwarding--;
+ write_unlock_bh(&mrt_lock);
- mroute_clean_tables(net);
- } else
- err = -EACCES;
+ mroute_clean_tables(mrt);
+ err = 0;
+ break;
+ }
+ }
rtnl_unlock();
return err;
}
+struct sock *mroute6_socket(struct net *net, struct sk_buff *skb)
+{
+ struct mr6_table *mrt;
+ struct flowi fl = {
+ .iif = skb->skb_iif,
+ .oif = skb->dev->ifindex,
+ .mark = skb->mark,
+ };
+
+ if (ip6mr_fib_lookup(net, &fl, &mrt) < 0)
+ return NULL;
+
+ return mrt->mroute6_sk;
+}
+
/*
* Socket options and virtual interface manipulation. The whole
* virtual interface system is a complete heap, but unfortunately
@@ -1293,9 +1572,14 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
struct mf6cctl mfc;
mifi_t mifi;
struct net *net = sock_net(sk);
+ struct mr6_table *mrt;
+
+ mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
+ if (mrt == NULL)
+ return -ENOENT;
if (optname != MRT6_INIT) {
- if (sk != net->ipv6.mroute6_sk && !capable(CAP_NET_ADMIN))
+ if (sk != mrt->mroute6_sk && !capable(CAP_NET_ADMIN))
return -EACCES;
}
@@ -1307,7 +1591,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
if (optlen < sizeof(int))
return -EINVAL;
- return ip6mr_sk_init(sk);
+ return ip6mr_sk_init(mrt, sk);
case MRT6_DONE:
return ip6mr_sk_done(sk);
@@ -1320,7 +1604,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
if (vif.mif6c_mifi >= MAXMIFS)
return -ENFILE;
rtnl_lock();
- ret = mif6_add(net, &vif, sk == net->ipv6.mroute6_sk);
+ ret = mif6_add(net, mrt, &vif, sk == mrt->mroute6_sk);
rtnl_unlock();
return ret;
@@ -1330,7 +1614,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
if (copy_from_user(&mifi, optval, sizeof(mifi_t)))
return -EFAULT;
rtnl_lock();
- ret = mif6_delete(net, mifi, NULL);
+ ret = mif6_delete(mrt, mifi, NULL);
rtnl_unlock();
return ret;
@@ -1346,10 +1630,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
return -EFAULT;
rtnl_lock();
if (optname == MRT6_DEL_MFC)
- ret = ip6mr_mfc_delete(net, &mfc);
+ ret = ip6mr_mfc_delete(mrt, &mfc);
else
- ret = ip6mr_mfc_add(net, &mfc,
- sk == net->ipv6.mroute6_sk);
+ ret = ip6mr_mfc_add(net, mrt, &mfc, sk == mrt->mroute6_sk);
rtnl_unlock();
return ret;
@@ -1361,7 +1644,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
int v;
if (get_user(v, (int __user *)optval))
return -EFAULT;
- net->ipv6.mroute_do_assert = !!v;
+ mrt->mroute_do_assert = !!v;
return 0;
}
@@ -1374,15 +1657,36 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
v = !!v;
rtnl_lock();
ret = 0;
- if (v != net->ipv6.mroute_do_pim) {
- net->ipv6.mroute_do_pim = v;
- net->ipv6.mroute_do_assert = v;
+ if (v != mrt->mroute_do_pim) {
+ mrt->mroute_do_pim = v;
+ mrt->mroute_do_assert = v;
}
rtnl_unlock();
return ret;
}
#endif
+#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
+ case MRT6_TABLE:
+ {
+ u32 v;
+
+ if (optlen != sizeof(u32))
+ return -EINVAL;
+ if (get_user(v, (u32 __user *)optval))
+ return -EFAULT;
+ if (sk == mrt->mroute6_sk)
+ return -EBUSY;
+
+ rtnl_lock();
+ ret = 0;
+ if (!ip6mr_new_table(net, v))
+ ret = -ENOMEM;
+ raw6_sk(sk)->ip6mr_table = v;
+ rtnl_unlock();
+ return ret;
+ }
+#endif
/*
* Spurious command, or MRT6_VERSION which you cannot
* set.
@@ -1402,6 +1706,11 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
int olr;
int val;
struct net *net = sock_net(sk);
+ struct mr6_table *mrt;
+
+ mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
+ if (mrt == NULL)
+ return -ENOENT;
switch (optname) {
case MRT6_VERSION:
@@ -1409,11 +1718,11 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
break;
#ifdef CONFIG_IPV6_PIMSM_V2
case MRT6_PIM:
- val = net->ipv6.mroute_do_pim;
+ val = mrt->mroute_do_pim;
break;
#endif
case MRT6_ASSERT:
- val = net->ipv6.mroute_do_assert;
+ val = mrt->mroute_do_assert;
break;
default:
return -ENOPROTOOPT;
@@ -1444,16 +1753,21 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
struct mif_device *vif;
struct mfc6_cache *c;
struct net *net = sock_net(sk);
+ struct mr6_table *mrt;
+
+ mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
+ if (mrt == NULL)
+ return -ENOENT;
switch (cmd) {
case SIOCGETMIFCNT_IN6:
if (copy_from_user(&vr, arg, sizeof(vr)))
return -EFAULT;
- if (vr.mifi >= net->ipv6.maxvif)
+ if (vr.mifi >= mrt->maxvif)
return -EINVAL;
read_lock(&mrt_lock);
- vif = &net->ipv6.vif6_table[vr.mifi];
- if (MIF_EXISTS(net, vr.mifi)) {
+ vif = &mrt->vif6_table[vr.mifi];
+ if (MIF_EXISTS(mrt, vr.mifi)) {
vr.icount = vif->pkt_in;
vr.ocount = vif->pkt_out;
vr.ibytes = vif->bytes_in;
@@ -1471,7 +1785,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
return -EFAULT;
read_lock(&mrt_lock);
- c = ip6mr_cache_find(net, &sr.src.sin6_addr, &sr.grp.sin6_addr);
+ c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr);
if (c) {
sr.pktcnt = c->mfc_un.res.pkt;
sr.bytecnt = c->mfc_un.res.bytes;
@@ -1501,11 +1815,11 @@ static inline int ip6mr_forward2_finish(struct sk_buff *skb)
* Processing handlers for ip6mr_forward
*/
-static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi)
+static int ip6mr_forward2(struct net *net, struct mr6_table *mrt,
+ struct sk_buff *skb, struct mfc6_cache *c, int vifi)
{
struct ipv6hdr *ipv6h;
- struct net *net = mfc6_net(c);
- struct mif_device *vif = &net->ipv6.vif6_table[vifi];
+ struct mif_device *vif = &mrt->vif6_table[vifi];
struct net_device *dev;
struct dst_entry *dst;
struct flowi fl;
@@ -1519,7 +1833,7 @@ static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi)
vif->bytes_out += skb->len;
vif->dev->stats.tx_bytes += skb->len;
vif->dev->stats.tx_packets++;
- ip6mr_cache_report(net, skb, vifi, MRT6MSG_WHOLEPKT);
+ ip6mr_cache_report(mrt, skb, vifi, MRT6MSG_WHOLEPKT);
goto out_free;
}
#endif
@@ -1566,7 +1880,7 @@ static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi)
IP6CB(skb)->flags |= IP6SKB_FORWARDED;
- return NF_HOOK(PF_INET6, NF_INET_FORWARD, skb, skb->dev, dev,
+ return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dev,
ip6mr_forward2_finish);
out_free:
@@ -1574,22 +1888,22 @@ out_free:
return 0;
}
-static int ip6mr_find_vif(struct net_device *dev)
+static int ip6mr_find_vif(struct mr6_table *mrt, struct net_device *dev)
{
- struct net *net = dev_net(dev);
int ct;
- for (ct = net->ipv6.maxvif - 1; ct >= 0; ct--) {
- if (net->ipv6.vif6_table[ct].dev == dev)
+
+ for (ct = mrt->maxvif - 1; ct >= 0; ct--) {
+ if (mrt->vif6_table[ct].dev == dev)
break;
}
return ct;
}
-static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache)
+static int ip6_mr_forward(struct net *net, struct mr6_table *mrt,
+ struct sk_buff *skb, struct mfc6_cache *cache)
{
int psend = -1;
int vif, ct;
- struct net *net = mfc6_net(cache);
vif = cache->mf6c_parent;
cache->mfc_un.res.pkt++;
@@ -1598,30 +1912,30 @@ static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache)
/*
* Wrong interface: drop packet and (maybe) send PIM assert.
*/
- if (net->ipv6.vif6_table[vif].dev != skb->dev) {
+ if (mrt->vif6_table[vif].dev != skb->dev) {
int true_vifi;
cache->mfc_un.res.wrong_if++;
- true_vifi = ip6mr_find_vif(skb->dev);
+ true_vifi = ip6mr_find_vif(mrt, skb->dev);
- if (true_vifi >= 0 && net->ipv6.mroute_do_assert &&
+ if (true_vifi >= 0 && mrt->mroute_do_assert &&
/* pimsm uses asserts, when switching from RPT to SPT,
so that we cannot check that packet arrived on an oif.
It is bad, but otherwise we would need to move pretty
large chunk of pimd to kernel. Ough... --ANK
*/
- (net->ipv6.mroute_do_pim ||
+ (mrt->mroute_do_pim ||
cache->mfc_un.res.ttls[true_vifi] < 255) &&
time_after(jiffies,
cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) {
cache->mfc_un.res.last_assert = jiffies;
- ip6mr_cache_report(net, skb, true_vifi, MRT6MSG_WRONGMIF);
+ ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRONGMIF);
}
goto dont_forward;
}
- net->ipv6.vif6_table[vif].pkt_in++;
- net->ipv6.vif6_table[vif].bytes_in += skb->len;
+ mrt->vif6_table[vif].pkt_in++;
+ mrt->vif6_table[vif].bytes_in += skb->len;
/*
* Forward the frame
@@ -1631,13 +1945,13 @@ static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache)
if (psend != -1) {
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2)
- ip6mr_forward2(skb2, cache, psend);
+ ip6mr_forward2(net, mrt, skb2, cache, psend);
}
psend = ct;
}
}
if (psend != -1) {
- ip6mr_forward2(skb, cache, psend);
+ ip6mr_forward2(net, mrt, skb, cache, psend);
return 0;
}
@@ -1655,9 +1969,19 @@ int ip6_mr_input(struct sk_buff *skb)
{
struct mfc6_cache *cache;
struct net *net = dev_net(skb->dev);
+ struct mr6_table *mrt;
+ struct flowi fl = {
+ .iif = skb->dev->ifindex,
+ .mark = skb->mark,
+ };
+ int err;
+
+ err = ip6mr_fib_lookup(net, &fl, &mrt);
+ if (err < 0)
+ return err;
read_lock(&mrt_lock);
- cache = ip6mr_cache_find(net,
+ cache = ip6mr_cache_find(mrt,
&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr);
/*
@@ -1666,9 +1990,9 @@ int ip6_mr_input(struct sk_buff *skb)
if (cache == NULL) {
int vif;
- vif = ip6mr_find_vif(skb->dev);
+ vif = ip6mr_find_vif(mrt, skb->dev);
if (vif >= 0) {
- int err = ip6mr_cache_unresolved(net, vif, skb);
+ int err = ip6mr_cache_unresolved(mrt, vif, skb);
read_unlock(&mrt_lock);
return err;
@@ -1678,7 +2002,7 @@ int ip6_mr_input(struct sk_buff *skb)
return -ENODEV;
}
- ip6_mr_forward(skb, cache);
+ ip6_mr_forward(net, mrt, skb, cache);
read_unlock(&mrt_lock);
@@ -1686,29 +2010,31 @@ int ip6_mr_input(struct sk_buff *skb)
}
-static int
-ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm)
+static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
+ struct mfc6_cache *c, struct rtmsg *rtm)
{
int ct;
struct rtnexthop *nhp;
- struct net *net = mfc6_net(c);
- struct net_device *dev = net->ipv6.vif6_table[c->mf6c_parent].dev;
u8 *b = skb_tail_pointer(skb);
struct rtattr *mp_head;
- if (dev)
- RTA_PUT(skb, RTA_IIF, 4, &dev->ifindex);
+ /* If cache is unresolved, don't try to parse IIF and OIF */
+ if (c->mf6c_parent >= MAXMIFS)
+ return -ENOENT;
+
+ if (MIF_EXISTS(mrt, c->mf6c_parent))
+ RTA_PUT(skb, RTA_IIF, 4, &mrt->vif6_table[c->mf6c_parent].dev->ifindex);
mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0));
for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
- if (c->mfc_un.res.ttls[ct] < 255) {
+ if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4))
goto rtattr_failure;
nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp)));
nhp->rtnh_flags = 0;
nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
- nhp->rtnh_ifindex = net->ipv6.vif6_table[ct].dev->ifindex;
+ nhp->rtnh_ifindex = mrt->vif6_table[ct].dev->ifindex;
nhp->rtnh_len = sizeof(*nhp);
}
}
@@ -1726,11 +2052,16 @@ int ip6mr_get_route(struct net *net,
struct sk_buff *skb, struct rtmsg *rtm, int nowait)
{
int err;
+ struct mr6_table *mrt;
struct mfc6_cache *cache;
struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
+ mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
+ if (mrt == NULL)
+ return -ENOENT;
+
read_lock(&mrt_lock);
- cache = ip6mr_cache_find(net, &rt->rt6i_src.addr, &rt->rt6i_dst.addr);
+ cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr);
if (!cache) {
struct sk_buff *skb2;
@@ -1744,7 +2075,7 @@ int ip6mr_get_route(struct net *net,
}
dev = skb->dev;
- if (dev == NULL || (vif = ip6mr_find_vif(dev)) < 0) {
+ if (dev == NULL || (vif = ip6mr_find_vif(mrt, dev)) < 0) {
read_unlock(&mrt_lock);
return -ENODEV;
}
@@ -1773,7 +2104,7 @@ int ip6mr_get_route(struct net *net,
ipv6_addr_copy(&iph->saddr, &rt->rt6i_src.addr);
ipv6_addr_copy(&iph->daddr, &rt->rt6i_dst.addr);
- err = ip6mr_cache_unresolved(net, vif, skb2);
+ err = ip6mr_cache_unresolved(mrt, vif, skb2);
read_unlock(&mrt_lock);
return err;
@@ -1782,8 +2113,88 @@ int ip6mr_get_route(struct net *net,
if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY))
cache->mfc_flags |= MFC_NOTIFY;
- err = ip6mr_fill_mroute(skb, cache, rtm);
+ err = __ip6mr_fill_mroute(mrt, skb, cache, rtm);
read_unlock(&mrt_lock);
return err;
}
+static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
+ u32 pid, u32 seq, struct mfc6_cache *c)
+{
+ struct nlmsghdr *nlh;
+ struct rtmsg *rtm;
+
+ nlh = nlmsg_put(skb, pid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI);
+ if (nlh == NULL)
+ return -EMSGSIZE;
+
+ rtm = nlmsg_data(nlh);
+ rtm->rtm_family = RTNL_FAMILY_IPMR;
+ rtm->rtm_dst_len = 128;
+ rtm->rtm_src_len = 128;
+ rtm->rtm_tos = 0;
+ rtm->rtm_table = mrt->id;
+ NLA_PUT_U32(skb, RTA_TABLE, mrt->id);
+ rtm->rtm_scope = RT_SCOPE_UNIVERSE;
+ rtm->rtm_protocol = RTPROT_UNSPEC;
+ rtm->rtm_flags = 0;
+
+ NLA_PUT(skb, RTA_SRC, 16, &c->mf6c_origin);
+ NLA_PUT(skb, RTA_DST, 16, &c->mf6c_mcastgrp);
+
+ if (__ip6mr_fill_mroute(mrt, skb, c, rtm) < 0)
+ goto nla_put_failure;
+
+ return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+ return -EMSGSIZE;
+}
+
+static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ struct mr6_table *mrt;
+ struct mfc6_cache *mfc;
+ unsigned int t = 0, s_t;
+ unsigned int h = 0, s_h;
+ unsigned int e = 0, s_e;
+
+ s_t = cb->args[0];
+ s_h = cb->args[1];
+ s_e = cb->args[2];
+
+ read_lock(&mrt_lock);
+ ip6mr_for_each_table(mrt, net) {
+ if (t < s_t)
+ goto next_table;
+ if (t > s_t)
+ s_h = 0;
+ for (h = s_h; h < MFC6_LINES; h++) {
+ list_for_each_entry(mfc, &mrt->mfc6_cache_array[h], list) {
+ if (e < s_e)
+ goto next_entry;
+ if (ip6mr_fill_mroute(mrt, skb,
+ NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq,
+ mfc) < 0)
+ goto done;
+next_entry:
+ e++;
+ }
+ e = s_e = 0;
+ }
+ s_h = 0;
+next_table:
+ t++;
+ }
+done:
+ read_unlock(&mrt_lock);
+
+ cb->args[2] = e;
+ cb->args[1] = h;
+ cb->args[0] = t;
+
+ return skb->len;
+}
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 2f2a5ca2c878..85cccd6ed0b7 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -53,6 +53,7 @@
static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
+ struct net *net = dev_net(skb->dev);
__be32 spi;
struct ipv6hdr *iph = (struct ipv6hdr*)skb->data;
struct ip_comp_hdr *ipcomph =
@@ -63,7 +64,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return;
spi = htonl(ntohs(ipcomph->cpi));
- x = xfrm_state_lookup(&init_net, (xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6);
+ x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6);
if (!x)
return;
@@ -74,14 +75,15 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x)
{
+ struct net *net = xs_net(x);
struct xfrm_state *t = NULL;
- t = xfrm_state_alloc(&init_net);
+ t = xfrm_state_alloc(net);
if (!t)
goto out;
t->id.proto = IPPROTO_IPV6;
- t->id.spi = xfrm6_tunnel_alloc_spi((xfrm_address_t *)&x->props.saddr);
+ t->id.spi = xfrm6_tunnel_alloc_spi(net, (xfrm_address_t *)&x->props.saddr);
if (!t->id.spi)
goto error;
@@ -90,6 +92,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x)
t->props.family = AF_INET6;
t->props.mode = x->props.mode;
memcpy(t->props.saddr.a6, x->props.saddr.a6, sizeof(struct in6_addr));
+ memcpy(&t->mark, &x->mark, sizeof(t->mark));
if (xfrm_init_state(t))
goto error;
@@ -108,13 +111,15 @@ error:
static int ipcomp6_tunnel_attach(struct xfrm_state *x)
{
+ struct net *net = xs_net(x);
int err = 0;
struct xfrm_state *t = NULL;
__be32 spi;
+ u32 mark = x->mark.m & x->mark.v;
- spi = xfrm6_tunnel_spi_lookup((xfrm_address_t *)&x->props.saddr);
+ spi = xfrm6_tunnel_spi_lookup(net, (xfrm_address_t *)&x->props.saddr);
if (spi)
- t = xfrm_state_lookup(&init_net, (xfrm_address_t *)&x->id.daddr,
+ t = xfrm_state_lookup(net, mark, (xfrm_address_t *)&x->id.daddr,
spi, IPPROTO_IPV6, AF_INET6);
if (!t) {
t = ipcomp6_tunnel_create(x);
@@ -154,16 +159,12 @@ static int ipcomp6_init_state(struct xfrm_state *x)
if (x->props.mode == XFRM_MODE_TUNNEL) {
err = ipcomp6_tunnel_attach(x);
if (err)
- goto error_tunnel;
+ goto out;
}
err = 0;
out:
return err;
-error_tunnel:
- ipcomp_destroy(x);
-
- goto out;
}
static const struct xfrm_type ipcomp6_type =
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 430454ee5ead..bd43f0152c21 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -36,6 +36,7 @@
#include <linux/init.h>
#include <linux/sysctl.h>
#include <linux/netfilter.h>
+#include <linux/slab.h>
#include <net/sock.h>
#include <net/snmp.h>
@@ -113,9 +114,9 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
}
opt = xchg(&inet6_sk(sk)->opt, opt);
} else {
- write_lock(&sk->sk_dst_lock);
+ spin_lock(&sk->sk_dst_lock);
opt = xchg(&inet6_sk(sk)->opt, opt);
- write_unlock(&sk->sk_dst_lock);
+ spin_unlock(&sk->sk_dst_lock);
}
sk_dst_reset(sk);
@@ -336,6 +337,13 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
retv = 0;
break;
+ case IPV6_RECVPATHMTU:
+ if (optlen < sizeof(int))
+ goto e_inval;
+ np->rxopt.bits.rxpmtu = valbool;
+ retv = 0;
+ break;
+
case IPV6_HOPOPTS:
case IPV6_RTHDRDSTOPTS:
case IPV6_RTHDR:
@@ -450,7 +458,8 @@ sticky_done:
msg.msg_controllen = optlen;
msg.msg_control = (void*)(opt+1);
- retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk);
+ retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk,
+ &junk);
if (retv)
goto done;
update:
@@ -766,6 +775,17 @@ pref_skip_coa:
break;
}
+ case IPV6_MINHOPCOUNT:
+ if (optlen < sizeof(int))
+ goto e_inval;
+ if (val < 0 || val > 255)
+ goto e_inval;
+ np->min_hopcount = val;
+ break;
+ case IPV6_DONTFRAG:
+ np->dontfrag = valbool;
+ retv = 0;
+ break;
}
release_sock(sk);
@@ -970,14 +990,13 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
case IPV6_MTU:
{
struct dst_entry *dst;
+
val = 0;
- lock_sock(sk);
- dst = sk_dst_get(sk);
- if (dst) {
+ rcu_read_lock();
+ dst = __sk_dst_get(sk);
+ if (dst)
val = dst_mtu(dst);
- dst_release(dst);
- }
- release_sock(sk);
+ rcu_read_unlock();
if (!val)
return -ENOTCONN;
break;
@@ -1055,6 +1074,38 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
val = np->rxopt.bits.rxflow;
break;
+ case IPV6_RECVPATHMTU:
+ val = np->rxopt.bits.rxpmtu;
+ break;
+
+ case IPV6_PATHMTU:
+ {
+ struct dst_entry *dst;
+ struct ip6_mtuinfo mtuinfo;
+
+ if (len < sizeof(mtuinfo))
+ return -EINVAL;
+
+ len = sizeof(mtuinfo);
+ memset(&mtuinfo, 0, sizeof(mtuinfo));
+
+ rcu_read_lock();
+ dst = __sk_dst_get(sk);
+ if (dst)
+ mtuinfo.ip6m_mtu = dst_mtu(dst);
+ rcu_read_unlock();
+ if (!mtuinfo.ip6m_mtu)
+ return -ENOTCONN;
+
+ if (put_user(len, optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, &mtuinfo, len))
+ return -EFAULT;
+
+ return 0;
+ break;
+ }
+
case IPV6_UNICAST_HOPS:
case IPV6_MULTICAST_HOPS:
{
@@ -1065,12 +1116,14 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
else
val = np->mcast_hops;
- dst = sk_dst_get(sk);
- if (dst) {
- if (val < 0)
+ if (val < 0) {
+ rcu_read_lock();
+ dst = __sk_dst_get(sk);
+ if (dst)
val = ip6_dst_hoplimit(dst);
- dst_release(dst);
+ rcu_read_unlock();
}
+
if (val < 0)
val = sock_net(sk)->ipv6.devconf_all->hop_limit;
break;
@@ -1114,6 +1167,14 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
val |= IPV6_PREFER_SRC_HOME;
break;
+ case IPV6_MINHOPCOUNT:
+ val = np->min_hopcount;
+ break;
+
+ case IPV6_DONTFRAG:
+ val = np->dontfrag;
+ break;
+
default:
return -ENOPROTOOPT;
}
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 1f9c44442e65..ab1622d7d409 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -43,6 +43,8 @@
#include <linux/init.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <net/mld.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
@@ -70,54 +72,11 @@
#define MDBG(x)
#endif
-/*
- * These header formats should be in a separate include file, but icmpv6.h
- * doesn't have in6_addr defined in all cases, there is no __u128, and no
- * other files reference these.
- *
- * +-DLS 4/14/03
- */
-
-/* Multicast Listener Discovery version 2 headers */
-
-struct mld2_grec {
- __u8 grec_type;
- __u8 grec_auxwords;
- __be16 grec_nsrcs;
- struct in6_addr grec_mca;
- struct in6_addr grec_src[0];
-};
-
-struct mld2_report {
- __u8 type;
- __u8 resv1;
- __sum16 csum;
- __be16 resv2;
- __be16 ngrec;
- struct mld2_grec grec[0];
-};
-
-struct mld2_query {
- __u8 type;
- __u8 code;
- __sum16 csum;
- __be16 mrc;
- __be16 resv1;
- struct in6_addr mca;
-#if defined(__LITTLE_ENDIAN_BITFIELD)
- __u8 qrv:3,
- suppress:1,
- resv2:4;
-#elif defined(__BIG_ENDIAN_BITFIELD)
- __u8 resv2:4,
- suppress:1,
- qrv:3;
-#else
-#error "Please fix <asm/byteorder.h>"
-#endif
- __u8 qqic;
- __be16 nsrcs;
- struct in6_addr srcs[0];
+/* Ensure that we have struct in6_addr aligned on 32bit word. */
+static void *__mld2_query_bugs[] __attribute__((__unused__)) = {
+ BUILD_BUG_ON_NULL(offsetof(struct mld2_query, mld2q_srcs) % 4),
+ BUILD_BUG_ON_NULL(offsetof(struct mld2_report, mld2r_grec) % 4),
+ BUILD_BUG_ON_NULL(offsetof(struct mld2_grec, grec_mca) % 4)
};
static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT;
@@ -156,14 +115,6 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
((idev)->mc_v1_seen && \
time_before(jiffies, (idev)->mc_v1_seen)))
-#define MLDV2_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value))
-#define MLDV2_EXP(thresh, nbmant, nbexp, value) \
- ((value) < (thresh) ? (value) : \
- ((MLDV2_MASK(value, nbmant) | (1<<(nbmant))) << \
- (MLDV2_MASK((value) >> (nbmant), nbexp) + (nbexp))))
-
-#define MLDV2_MRC(value) MLDV2_EXP(0x8000, 12, 3, value)
-
#define IPV6_MLD_MAX_MSF 64
int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF;
@@ -714,7 +665,7 @@ static void igmp6_group_added(struct ifmcaddr6 *mc)
if (!(mc->mca_flags&MAF_LOADED)) {
mc->mca_flags |= MAF_LOADED;
if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0)
- dev_mc_add(dev, buf, dev->addr_len, 0);
+ dev_mc_add(dev, buf);
}
spin_unlock_bh(&mc->mca_lock);
@@ -740,7 +691,7 @@ static void igmp6_group_dropped(struct ifmcaddr6 *mc)
if (mc->mca_flags&MAF_LOADED) {
mc->mca_flags &= ~MAF_LOADED;
if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0)
- dev_mc_delete(dev, buf, dev->addr_len, 0);
+ dev_mc_del(dev, buf);
}
if (mc->mca_flags & MAF_NOREPORT)
@@ -793,10 +744,10 @@ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
}
spin_unlock_bh(&im->mca_lock);
- write_lock_bh(&idev->mc_lock);
+ spin_lock_bh(&idev->mc_lock);
pmc->next = idev->mc_tomb;
idev->mc_tomb = pmc;
- write_unlock_bh(&idev->mc_lock);
+ spin_unlock_bh(&idev->mc_lock);
}
static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *pmca)
@@ -804,7 +755,7 @@ static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *pmca)
struct ifmcaddr6 *pmc, *pmc_prev;
struct ip6_sf_list *psf, *psf_next;
- write_lock_bh(&idev->mc_lock);
+ spin_lock_bh(&idev->mc_lock);
pmc_prev = NULL;
for (pmc=idev->mc_tomb; pmc; pmc=pmc->next) {
if (ipv6_addr_equal(&pmc->mca_addr, pmca))
@@ -817,7 +768,8 @@ static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *pmca)
else
idev->mc_tomb = pmc->next;
}
- write_unlock_bh(&idev->mc_lock);
+ spin_unlock_bh(&idev->mc_lock);
+
if (pmc) {
for (psf=pmc->mca_tomb; psf; psf=psf_next) {
psf_next = psf->sf_next;
@@ -832,10 +784,10 @@ static void mld_clear_delrec(struct inet6_dev *idev)
{
struct ifmcaddr6 *pmc, *nextpmc;
- write_lock_bh(&idev->mc_lock);
+ spin_lock_bh(&idev->mc_lock);
pmc = idev->mc_tomb;
idev->mc_tomb = NULL;
- write_unlock_bh(&idev->mc_lock);
+ spin_unlock_bh(&idev->mc_lock);
for (; pmc; pmc = nextpmc) {
nextpmc = pmc->next;
@@ -1159,7 +1111,7 @@ int igmp6_event_query(struct sk_buff *skb)
struct in6_addr *group;
unsigned long max_delay;
struct inet6_dev *idev;
- struct icmp6hdr *hdr;
+ struct mld_msg *mld;
int group_type;
int mark = 0;
int len;
@@ -1180,8 +1132,8 @@ int igmp6_event_query(struct sk_buff *skb)
if (idev == NULL)
return 0;
- hdr = icmp6_hdr(skb);
- group = (struct in6_addr *) (hdr + 1);
+ mld = (struct mld_msg *)icmp6_hdr(skb);
+ group = &mld->mld_mca;
group_type = ipv6_addr_type(group);
if (group_type != IPV6_ADDR_ANY &&
@@ -1195,7 +1147,7 @@ int igmp6_event_query(struct sk_buff *skb)
/* MLDv1 router present */
/* Translate milliseconds to jiffies */
- max_delay = (ntohs(hdr->icmp6_maxdelay)*HZ)/1000;
+ max_delay = (ntohs(mld->mld_maxdelay)*HZ)/1000;
switchback = (idev->mc_qrv + 1) * max_delay;
idev->mc_v1_seen = jiffies + switchback;
@@ -1214,14 +1166,14 @@ int igmp6_event_query(struct sk_buff *skb)
return -EINVAL;
}
mlh2 = (struct mld2_query *)skb_transport_header(skb);
- max_delay = (MLDV2_MRC(ntohs(mlh2->mrc))*HZ)/1000;
+ max_delay = (MLDV2_MRC(ntohs(mlh2->mld2q_mrc))*HZ)/1000;
if (!max_delay)
max_delay = 1;
idev->mc_maxdelay = max_delay;
- if (mlh2->qrv)
- idev->mc_qrv = mlh2->qrv;
+ if (mlh2->mld2q_qrv)
+ idev->mc_qrv = mlh2->mld2q_qrv;
if (group_type == IPV6_ADDR_ANY) { /* general query */
- if (mlh2->nsrcs) {
+ if (mlh2->mld2q_nsrcs) {
in6_dev_put(idev);
return -EINVAL; /* no sources allowed */
}
@@ -1230,9 +1182,9 @@ int igmp6_event_query(struct sk_buff *skb)
return 0;
}
/* mark sources to include, if group & source-specific */
- if (mlh2->nsrcs != 0) {
+ if (mlh2->mld2q_nsrcs != 0) {
if (!pskb_may_pull(skb, srcs_offset +
- ntohs(mlh2->nsrcs) * sizeof(struct in6_addr))) {
+ ntohs(mlh2->mld2q_nsrcs) * sizeof(struct in6_addr))) {
in6_dev_put(idev);
return -EINVAL;
}
@@ -1268,7 +1220,7 @@ int igmp6_event_query(struct sk_buff *skb)
ma->mca_flags &= ~MAF_GSQUERY;
}
if (!(ma->mca_flags & MAF_GSQUERY) ||
- mld_marksources(ma, ntohs(mlh2->nsrcs), mlh2->srcs))
+ mld_marksources(ma, ntohs(mlh2->mld2q_nsrcs), mlh2->mld2q_srcs))
igmp6_group_queried(ma, max_delay);
spin_unlock_bh(&ma->mca_lock);
break;
@@ -1284,9 +1236,8 @@ int igmp6_event_query(struct sk_buff *skb)
int igmp6_event_report(struct sk_buff *skb)
{
struct ifmcaddr6 *ma;
- struct in6_addr *addrp;
struct inet6_dev *idev;
- struct icmp6hdr *hdr;
+ struct mld_msg *mld;
int addr_type;
/* Our own report looped back. Ignore it. */
@@ -1298,10 +1249,10 @@ int igmp6_event_report(struct sk_buff *skb)
skb->pkt_type != PACKET_BROADCAST)
return 0;
- if (!pskb_may_pull(skb, sizeof(struct in6_addr)))
+ if (!pskb_may_pull(skb, sizeof(*mld) - sizeof(struct icmp6hdr)))
return -EINVAL;
- hdr = icmp6_hdr(skb);
+ mld = (struct mld_msg *)icmp6_hdr(skb);
/* Drop reports with not link local source */
addr_type = ipv6_addr_type(&ipv6_hdr(skb)->saddr);
@@ -1309,8 +1260,6 @@ int igmp6_event_report(struct sk_buff *skb)
!(addr_type&IPV6_ADDR_LINKLOCAL))
return -EINVAL;
- addrp = (struct in6_addr *) (hdr + 1);
-
idev = in6_dev_get(skb->dev);
if (idev == NULL)
return -ENODEV;
@@ -1321,7 +1270,7 @@ int igmp6_event_report(struct sk_buff *skb)
read_lock_bh(&idev->lock);
for (ma = idev->mc_list; ma; ma=ma->next) {
- if (ipv6_addr_equal(&ma->mca_addr, addrp)) {
+ if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) {
spin_lock(&ma->mca_lock);
if (del_timer(&ma->mca_timer))
atomic_dec(&ma->mca_refcnt);
@@ -1407,7 +1356,10 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size)
IPV6_TLV_PADN, 0 };
/* we assume size > sizeof(ra) here */
- skb = sock_alloc_send_skb(sk, size + LL_ALLOCATED_SPACE(dev), 1, &err);
+ size += LL_ALLOCATED_SPACE(dev);
+ /* limit our allocations to order-0 page */
+ size = min_t(int, size, SKB_MAX_ORDER(0, 0));
+ skb = sock_alloc_send_skb(sk, size, 1, &err);
if (!skb)
return NULL;
@@ -1430,11 +1382,11 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size)
skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data);
skb_put(skb, sizeof(*pmr));
pmr = (struct mld2_report *)skb_transport_header(skb);
- pmr->type = ICMPV6_MLD2_REPORT;
- pmr->resv1 = 0;
- pmr->csum = 0;
- pmr->resv2 = 0;
- pmr->ngrec = 0;
+ pmr->mld2r_type = ICMPV6_MLD2_REPORT;
+ pmr->mld2r_resv1 = 0;
+ pmr->mld2r_cksum = 0;
+ pmr->mld2r_resv2 = 0;
+ pmr->mld2r_ngrec = 0;
return skb;
}
@@ -1456,9 +1408,10 @@ static void mld_sendpack(struct sk_buff *skb)
mldlen = skb->tail - skb->transport_header;
pip6->payload_len = htons(payload_len);
- pmr->csum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen,
- IPPROTO_ICMPV6, csum_partial(skb_transport_header(skb),
- mldlen, 0));
+ pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen,
+ IPPROTO_ICMPV6,
+ csum_partial(skb_transport_header(skb),
+ mldlen, 0));
dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr);
@@ -1478,7 +1431,7 @@ static void mld_sendpack(struct sk_buff *skb)
payload_len = skb->len;
- err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev,
+ err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev,
dst_output);
out:
if (!err) {
@@ -1519,7 +1472,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc,
pgr->grec_nsrcs = 0;
pgr->grec_mca = pmc->mca_addr; /* structure copy */
pmr = (struct mld2_report *)skb_transport_header(skb);
- pmr->ngrec = htons(ntohs(pmr->ngrec)+1);
+ pmr->mld2r_ngrec = htons(ntohs(pmr->mld2r_ngrec)+1);
*ppgr = pgr;
return skb;
}
@@ -1555,7 +1508,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
/* EX and TO_EX get a fresh packet, if needed */
if (truncate) {
- if (pmr && pmr->ngrec &&
+ if (pmr && pmr->mld2r_ngrec &&
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
mld_sendpack(skb);
@@ -1696,7 +1649,7 @@ static void mld_send_cr(struct inet6_dev *idev)
int type, dtype;
read_lock_bh(&idev->lock);
- write_lock_bh(&idev->mc_lock);
+ spin_lock(&idev->mc_lock);
/* deleted MCA's */
pmc_prev = NULL;
@@ -1730,7 +1683,7 @@ static void mld_send_cr(struct inet6_dev *idev)
} else
pmc_prev = pmc;
}
- write_unlock_bh(&idev->mc_lock);
+ spin_unlock(&idev->mc_lock);
/* change recs */
for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
@@ -1768,9 +1721,8 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
struct sock *sk = net->ipv6.igmp_sk;
struct inet6_dev *idev;
struct sk_buff *skb;
- struct icmp6hdr *hdr;
+ struct mld_msg *hdr;
const struct in6_addr *snd_addr, *saddr;
- struct in6_addr *addrp;
struct in6_addr addr_buf;
int err, len, payload_len, full_len;
u8 ra[8] = { IPPROTO_ICMPV6, 0,
@@ -1818,16 +1770,14 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra));
- hdr = (struct icmp6hdr *) skb_put(skb, sizeof(struct icmp6hdr));
- memset(hdr, 0, sizeof(struct icmp6hdr));
- hdr->icmp6_type = type;
+ hdr = (struct mld_msg *) skb_put(skb, sizeof(struct mld_msg));
+ memset(hdr, 0, sizeof(struct mld_msg));
+ hdr->mld_type = type;
+ ipv6_addr_copy(&hdr->mld_mca, addr);
- addrp = (struct in6_addr *) skb_put(skb, sizeof(struct in6_addr));
- ipv6_addr_copy(addrp, addr);
-
- hdr->icmp6_cksum = csum_ipv6_magic(saddr, snd_addr, len,
- IPPROTO_ICMPV6,
- csum_partial(hdr, len, 0));
+ hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len,
+ IPPROTO_ICMPV6,
+ csum_partial(hdr, len, 0));
idev = in6_dev_get(skb->dev);
@@ -1846,7 +1796,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
goto err_out;
skb_dst_set(skb, dst);
- err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev,
+ err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev,
dst_output);
out:
if (!err) {
@@ -2311,7 +2261,7 @@ void ipv6_mc_up(struct inet6_dev *idev)
void ipv6_mc_init_dev(struct inet6_dev *idev)
{
write_lock_bh(&idev->lock);
- rwlock_init(&idev->mc_lock);
+ spin_lock_init(&idev->mc_lock);
idev->mc_gq_running = 0;
setup_timer(&idev->mc_gq_timer, mld_gq_timer_expire,
(unsigned long)idev);
@@ -2646,7 +2596,7 @@ static const struct file_operations igmp6_mcf_seq_fops = {
.release = seq_release_net,
};
-static int igmp6_proc_init(struct net *net)
+static int __net_init igmp6_proc_init(struct net *net)
{
int err;
@@ -2666,23 +2616,22 @@ out_proc_net_igmp6:
goto out;
}
-static void igmp6_proc_exit(struct net *net)
+static void __net_exit igmp6_proc_exit(struct net *net)
{
proc_net_remove(net, "mcfilter6");
proc_net_remove(net, "igmp6");
}
#else
-static int igmp6_proc_init(struct net *net)
+static inline int igmp6_proc_init(struct net *net)
{
return 0;
}
-static void igmp6_proc_exit(struct net *net)
+static inline void igmp6_proc_exit(struct net *net)
{
- ;
}
#endif
-static int igmp6_net_init(struct net *net)
+static int __net_init igmp6_net_init(struct net *net)
{
int err;
@@ -2708,7 +2657,7 @@ out_sock_create:
goto out;
}
-static void igmp6_net_exit(struct net *net)
+static void __net_exit igmp6_net_exit(struct net *net)
{
inet_ctl_sock_destroy(net->ipv6.igmp_sk);
igmp6_proc_exit(net);
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index f797e8c6f3b3..d6e9599d0705 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -56,7 +56,7 @@ static inline void *mip6_padn(__u8 *data, __u8 padlen)
static inline void mip6_param_prob(struct sk_buff *skb, u8 code, int pos)
{
- icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev);
+ icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos);
}
static int mip6_mh_len(int type)
@@ -347,11 +347,12 @@ static const struct xfrm_type mip6_destopt_type =
static int mip6_rthdr_input(struct xfrm_state *x, struct sk_buff *skb)
{
+ struct ipv6hdr *iph = ipv6_hdr(skb);
struct rt2_hdr *rt2 = (struct rt2_hdr *)skb->data;
int err = rt2->rt_hdr.nexthdr;
spin_lock(&x->lock);
- if (!ipv6_addr_equal(&rt2->addr, (struct in6_addr *)x->coaddr) &&
+ if (!ipv6_addr_equal(&iph->daddr, (struct in6_addr *)x->coaddr) &&
!ipv6_addr_any((struct in6_addr *)x->coaddr))
err = -ENOENT;
spin_unlock(&x->lock);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index c45852798092..2efef52fb461 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -59,6 +59,7 @@
#include <linux/route.h>
#include <linux/init.h>
#include <linux/rcupdate.h>
+#include <linux/slab.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
@@ -535,7 +536,7 @@ void ndisc_send_skb(struct sk_buff *skb,
idev = in6_dev_get(dst->dev);
IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len);
- err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev,
+ err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev,
dst_output);
if (!err) {
ICMP6MSGOUT_INC_STATS(net, idev, type);
@@ -585,6 +586,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
src_addr = solicited_addr;
if (ifp->flags & IFA_F_OPTIMISTIC)
override = 0;
+ inc_opt |= ifp->idev->cnf.force_tllao;
in6_ifa_put(ifp);
} else {
if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr,
@@ -598,7 +600,6 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
icmp6h.icmp6_solicited = solicited;
icmp6h.icmp6_override = override;
- inc_opt |= ifp->idev->cnf.force_tllao;
__ndisc_send(dev, neigh, daddr, src_addr,
&icmp6h, solicited_addr,
inc_opt ? ND_OPT_TARGET_LL_ADDR : 0);
@@ -889,8 +890,6 @@ out:
in6_ifa_put(ifp);
else
in6_dev_put(idev);
-
- return;
}
static void ndisc_recv_na(struct sk_buff *skb)
@@ -1617,7 +1616,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
skb_dst_set(buff, dst);
idev = in6_dev_get(dst->dev);
IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len);
- err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, buff, NULL, dst->dev,
+ err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, buff, NULL, dst->dev,
dst_output);
if (!err) {
ICMP6MSGOUT_INC_STATS(net, idev, NDISC_REDIRECT);
@@ -1772,7 +1771,7 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *bu
#endif
-static int ndisc_net_init(struct net *net)
+static int __net_init ndisc_net_init(struct net *net)
{
struct ipv6_pinfo *np;
struct sock *sk;
@@ -1797,7 +1796,7 @@ static int ndisc_net_init(struct net *net)
return 0;
}
-static void ndisc_net_exit(struct net *net)
+static void __net_exit ndisc_net_exit(struct net *net)
{
inet_ctl_sock_destroy(net->ipv6.ndisc_sk);
}
@@ -1820,8 +1819,7 @@ int __init ndisc_init(void)
neigh_table_init(&nd_tbl);
#ifdef CONFIG_SYSCTL
- err = neigh_sysctl_register(NULL, &nd_tbl.parms, NET_IPV6,
- NET_IPV6_NEIGH, "ipv6",
+ err = neigh_sysctl_register(NULL, &nd_tbl.parms, "ipv6",
&ndisc_ifinfo_sysctl_change);
if (err)
goto out_unregister_pernet;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index d5ed92b14346..a74951c039b6 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -25,20 +25,6 @@ int ip6_route_me_harder(struct sk_buff *skb)
};
dst = ip6_route_output(net, skb->sk, &fl);
-
-#ifdef CONFIG_XFRM
- if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
- xfrm_decode_session(skb, &fl, AF_INET6) == 0) {
- struct dst_entry *dst2 = skb_dst(skb);
-
- if (xfrm_lookup(net, &dst2, &fl, skb->sk, 0)) {
- skb_dst_set(skb, NULL);
- return -1;
- }
- skb_dst_set(skb, dst2);
- }
-#endif
-
if (dst->error) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
@@ -50,6 +36,17 @@ int ip6_route_me_harder(struct sk_buff *skb)
skb_dst_drop(skb);
skb_dst_set(skb, dst);
+
+#ifdef CONFIG_XFRM
+ if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
+ xfrm_decode_session(skb, &fl, AF_INET6) == 0) {
+ skb_dst_set(skb, NULL);
+ if (xfrm_lookup(net, &dst, &fl, skb->sk, 0))
+ return -1;
+ skb_dst_set(skb, dst);
+ }
+#endif
+
return 0;
}
EXPORT_SYMBOL(ip6_route_me_harder);
diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c
index 7854052be60b..8c201743d96d 100644
--- a/net/ipv6/netfilter/ip6_queue.c
+++ b/net/ipv6/netfilter/ip6_queue.c
@@ -25,6 +25,7 @@
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/mutex.h>
+#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/ipv6.h>
@@ -161,8 +162,7 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
break;
case IPQ_COPY_PACKET:
- if ((entry->skb->ip_summed == CHECKSUM_PARTIAL ||
- entry->skb->ip_summed == CHECKSUM_COMPLETE) &&
+ if (entry->skb->ip_summed == CHECKSUM_PARTIAL &&
(*errp = skb_checksum_help(entry->skb))) {
read_unlock_bh(&queue_lock);
return NULL;
@@ -462,7 +462,6 @@ __ipq_rcv_skb(struct sk_buff *skb)
if (flags & NLM_F_ACK)
netlink_ack(skb, nlh, 0);
- return;
}
static void
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 480d7f8c9802..9d2d68f0e605 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -29,6 +29,7 @@
#include <linux/netfilter_ipv6/ip6_tables.h>
#include <linux/netfilter/x_tables.h>
#include <net/netfilter/nf_log.h>
+#include "../../netfilter/xt_repldata.h"
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
@@ -39,24 +40,19 @@ MODULE_DESCRIPTION("IPv6 packet filter");
/*#define DEBUG_IP_FIREWALL_USER*/
#ifdef DEBUG_IP_FIREWALL
-#define dprintf(format, args...) printk(format , ## args)
+#define dprintf(format, args...) pr_info(format , ## args)
#else
#define dprintf(format, args...)
#endif
#ifdef DEBUG_IP_FIREWALL_USER
-#define duprintf(format, args...) printk(format , ## args)
+#define duprintf(format, args...) pr_info(format , ## args)
#else
#define duprintf(format, args...)
#endif
#ifdef CONFIG_NETFILTER_DEBUG
-#define IP_NF_ASSERT(x) \
-do { \
- if (!(x)) \
- printk("IP_NF_ASSERT: %s:%s:%u\n", \
- __func__, __FILE__, __LINE__); \
-} while(0)
+#define IP_NF_ASSERT(x) WARN_ON(!(x))
#else
#define IP_NF_ASSERT(x)
#endif
@@ -67,6 +63,12 @@ do { \
#define inline
#endif
+void *ip6t_alloc_initial_table(const struct xt_table *info)
+{
+ return xt_alloc_initial_table(ip6t, IP6T);
+}
+EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table);
+
/*
We keep a set of rules for each CPU, so we can avoid write-locking
them in the softirq when updating the counters and therefore
@@ -190,32 +192,16 @@ ip6_checkentry(const struct ip6t_ip6 *ipv6)
}
static unsigned int
-ip6t_error(struct sk_buff *skb, const struct xt_target_param *par)
+ip6t_error(struct sk_buff *skb, const struct xt_action_param *par)
{
if (net_ratelimit())
- printk("ip6_tables: error: `%s'\n",
- (const char *)par->targinfo);
+ pr_info("error: `%s'\n", (const char *)par->targinfo);
return NF_DROP;
}
-/* Performance critical - called for every packet */
-static inline bool
-do_match(struct ip6t_entry_match *m, const struct sk_buff *skb,
- struct xt_match_param *par)
-{
- par->match = m->u.kernel.match;
- par->matchinfo = m->data;
-
- /* Stop iteration if it doesn't match */
- if (!m->u.kernel.match->match(skb, par))
- return true;
- else
- return false;
-}
-
static inline struct ip6t_entry *
-get_entry(void *base, unsigned int offset)
+get_entry(const void *base, unsigned int offset)
{
return (struct ip6t_entry *)(base + offset);
}
@@ -229,6 +215,12 @@ static inline bool unconditional(const struct ip6t_ip6 *ipv6)
return memcmp(ipv6, &uncond, sizeof(uncond)) == 0;
}
+static inline const struct ip6t_entry_target *
+ip6t_get_target_c(const struct ip6t_entry *e)
+{
+ return ip6t_get_target((struct ip6t_entry *)e);
+}
+
#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
/* This cries for unification! */
@@ -264,11 +256,11 @@ static struct nf_loginfo trace_loginfo = {
/* Mildly perf critical (only if packet tracing is on) */
static inline int
-get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e,
+get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e,
const char *hookname, const char **chainname,
const char **comment, unsigned int *rulenum)
{
- struct ip6t_standard_target *t = (void *)ip6t_get_target(s);
+ const struct ip6t_standard_target *t = (void *)ip6t_get_target_c(s);
if (strcmp(t->target.u.kernel.target->name, IP6T_ERROR_TARGET) == 0) {
/* Head of user chain: ERROR target with chainname */
@@ -294,17 +286,18 @@ get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e,
return 0;
}
-static void trace_packet(struct sk_buff *skb,
+static void trace_packet(const struct sk_buff *skb,
unsigned int hook,
const struct net_device *in,
const struct net_device *out,
const char *tablename,
- struct xt_table_info *private,
- struct ip6t_entry *e)
+ const struct xt_table_info *private,
+ const struct ip6t_entry *e)
{
- void *table_base;
+ const void *table_base;
const struct ip6t_entry *root;
const char *hookname, *chainname, *comment;
+ const struct ip6t_entry *iter;
unsigned int rulenum = 0;
table_base = private->entries[smp_processor_id()];
@@ -313,10 +306,10 @@ static void trace_packet(struct sk_buff *skb,
hookname = chainname = hooknames[hook];
comment = comments[NF_IP6_TRACE_COMMENT_RULE];
- IP6T_ENTRY_ITERATE(root,
- private->size - private->hook_entry[hook],
- get_chainname_rulenum,
- e, hookname, &chainname, &comment, &rulenum);
+ xt_entry_foreach(iter, root, private->size - private->hook_entry[hook])
+ if (get_chainname_rulenum(iter, e, hookname,
+ &chainname, &comment, &rulenum) != 0)
+ break;
nf_log_packet(AF_INET6, hook, skb, in, out, &trace_loginfo,
"TRACE: %s:%s:%s:%u ",
@@ -338,18 +331,15 @@ ip6t_do_table(struct sk_buff *skb,
const struct net_device *out,
struct xt_table *table)
{
-#define tb_comefrom ((struct ip6t_entry *)table_base)->comefrom
-
static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
- bool hotdrop = false;
/* Initializing verdict to NF_DROP keeps gcc happy. */
unsigned int verdict = NF_DROP;
const char *indev, *outdev;
- void *table_base;
- struct ip6t_entry *e, *back;
- struct xt_table_info *private;
- struct xt_match_param mtpar;
- struct xt_target_param tgpar;
+ const void *table_base;
+ struct ip6t_entry *e, **jumpstack;
+ unsigned int *stackptr, origptr, cpu;
+ const struct xt_table_info *private;
+ struct xt_action_param acpar;
/* Initialization */
indev = in ? in->name : nulldevname;
@@ -360,40 +350,48 @@ ip6t_do_table(struct sk_buff *skb,
* things we don't know, ie. tcp syn flag or ports). If the
* rule is also a fragment-specific rule, non-fragments won't
* match it. */
- mtpar.hotdrop = &hotdrop;
- mtpar.in = tgpar.in = in;
- mtpar.out = tgpar.out = out;
- mtpar.family = tgpar.family = NFPROTO_IPV6;
- mtpar.hooknum = tgpar.hooknum = hook;
+ acpar.hotdrop = false;
+ acpar.in = in;
+ acpar.out = out;
+ acpar.family = NFPROTO_IPV6;
+ acpar.hooknum = hook;
IP_NF_ASSERT(table->valid_hooks & (1 << hook));
xt_info_rdlock_bh();
private = table->private;
- table_base = private->entries[smp_processor_id()];
+ cpu = smp_processor_id();
+ table_base = private->entries[cpu];
+ jumpstack = (struct ip6t_entry **)private->jumpstack[cpu];
+ stackptr = per_cpu_ptr(private->stackptr, cpu);
+ origptr = *stackptr;
e = get_entry(table_base, private->hook_entry[hook]);
- /* For return from builtin chain */
- back = get_entry(table_base, private->underflow[hook]);
-
do {
- struct ip6t_entry_target *t;
+ const struct ip6t_entry_target *t;
+ const struct xt_entry_match *ematch;
IP_NF_ASSERT(e);
- IP_NF_ASSERT(back);
if (!ip6_packet_match(skb, indev, outdev, &e->ipv6,
- &mtpar.thoff, &mtpar.fragoff, &hotdrop) ||
- IP6T_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0) {
+ &acpar.thoff, &acpar.fragoff, &acpar.hotdrop)) {
+ no_match:
e = ip6t_next_entry(e);
continue;
}
+ xt_ematch_foreach(ematch, e) {
+ acpar.match = ematch->u.kernel.match;
+ acpar.matchinfo = ematch->data;
+ if (!acpar.match->match(skb, &acpar))
+ goto no_match;
+ }
+
ADD_COUNTER(e->counters,
ntohs(ipv6_hdr(skb)->payload_len) +
sizeof(struct ipv6hdr), 1);
- t = ip6t_get_target(e);
+ t = ip6t_get_target_c(e);
IP_NF_ASSERT(t->u.kernel.target);
#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
@@ -414,68 +412,53 @@ ip6t_do_table(struct sk_buff *skb,
verdict = (unsigned)(-v) - 1;
break;
}
- e = back;
- back = get_entry(table_base, back->comefrom);
+ if (*stackptr == 0)
+ e = get_entry(table_base,
+ private->underflow[hook]);
+ else
+ e = ip6t_next_entry(jumpstack[--*stackptr]);
continue;
}
if (table_base + v != ip6t_next_entry(e) &&
!(e->ipv6.flags & IP6T_F_GOTO)) {
- /* Save old back ptr in next entry */
- struct ip6t_entry *next = ip6t_next_entry(e);
- next->comefrom = (void *)back - table_base;
- /* set back pointer to next entry */
- back = next;
+ if (*stackptr >= private->stacksize) {
+ verdict = NF_DROP;
+ break;
+ }
+ jumpstack[(*stackptr)++] = e;
}
e = get_entry(table_base, v);
continue;
}
- /* Targets which reenter must return
- abs. verdicts */
- tgpar.target = t->u.kernel.target;
- tgpar.targinfo = t->data;
-
-#ifdef CONFIG_NETFILTER_DEBUG
- tb_comefrom = 0xeeeeeeec;
-#endif
- verdict = t->u.kernel.target->target(skb, &tgpar);
+ acpar.target = t->u.kernel.target;
+ acpar.targinfo = t->data;
-#ifdef CONFIG_NETFILTER_DEBUG
- if (tb_comefrom != 0xeeeeeeec && verdict == IP6T_CONTINUE) {
- printk("Target %s reentered!\n",
- t->u.kernel.target->name);
- verdict = NF_DROP;
- }
- tb_comefrom = 0x57acc001;
-#endif
+ verdict = t->u.kernel.target->target(skb, &acpar);
if (verdict == IP6T_CONTINUE)
e = ip6t_next_entry(e);
else
/* Verdict */
break;
- } while (!hotdrop);
+ } while (!acpar.hotdrop);
-#ifdef CONFIG_NETFILTER_DEBUG
- tb_comefrom = NETFILTER_LINK_POISON;
-#endif
xt_info_rdunlock_bh();
+ *stackptr = origptr;
#ifdef DEBUG_ALLOW_ALL
return NF_ACCEPT;
#else
- if (hotdrop)
+ if (acpar.hotdrop)
return NF_DROP;
else return verdict;
#endif
-
-#undef tb_comefrom
}
/* Figures out from what hook each rule can be called: returns 0 if
there are loops. Puts hook bitmask in comefrom. */
static int
-mark_source_chains(struct xt_table_info *newinfo,
+mark_source_chains(const struct xt_table_info *newinfo,
unsigned int valid_hooks, void *entry0)
{
unsigned int hook;
@@ -493,12 +476,12 @@ mark_source_chains(struct xt_table_info *newinfo,
e->counters.pcnt = pos;
for (;;) {
- struct ip6t_standard_target *t
- = (void *)ip6t_get_target(e);
+ const struct ip6t_standard_target *t
+ = (void *)ip6t_get_target_c(e);
int visited = e->comefrom & (1 << hook);
if (e->comefrom & (1 << NF_INET_NUMHOOKS)) {
- printk("iptables: loop hook %u pos %u %08X.\n",
+ pr_err("iptables: loop hook %u pos %u %08X.\n",
hook, pos, e->comefrom);
return 0;
}
@@ -584,27 +567,23 @@ mark_source_chains(struct xt_table_info *newinfo,
return 1;
}
-static int
-cleanup_match(struct ip6t_entry_match *m, unsigned int *i)
+static void cleanup_match(struct ip6t_entry_match *m, struct net *net)
{
struct xt_mtdtor_param par;
- if (i && (*i)-- == 0)
- return 1;
-
+ par.net = net;
par.match = m->u.kernel.match;
par.matchinfo = m->data;
par.family = NFPROTO_IPV6;
if (par.match->destroy != NULL)
par.match->destroy(&par);
module_put(par.match->me);
- return 0;
}
static int
-check_entry(struct ip6t_entry *e, const char *name)
+check_entry(const struct ip6t_entry *e, const char *name)
{
- struct ip6t_entry_target *t;
+ const struct ip6t_entry_target *t;
if (!ip6_checkentry(&e->ipv6)) {
duprintf("ip_tables: ip check failed %p %s.\n", e, name);
@@ -615,15 +594,14 @@ check_entry(struct ip6t_entry *e, const char *name)
e->next_offset)
return -EINVAL;
- t = ip6t_get_target(e);
+ t = ip6t_get_target_c(e);
if (e->target_offset + t->u.target_size > e->next_offset)
return -EINVAL;
return 0;
}
-static int check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par,
- unsigned int *i)
+static int check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par)
{
const struct ip6t_ip6 *ipv6 = par->entryinfo;
int ret;
@@ -638,27 +616,24 @@ static int check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par,
par.match->name);
return ret;
}
- ++*i;
return 0;
}
static int
-find_check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par,
- unsigned int *i)
+find_check_match(struct ip6t_entry_match *m, struct xt_mtchk_param *par)
{
struct xt_match *match;
int ret;
- match = try_then_request_module(xt_find_match(AF_INET6, m->u.user.name,
- m->u.user.revision),
- "ip6t_%s", m->u.user.name);
- if (IS_ERR(match) || !match) {
+ match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name,
+ m->u.user.revision);
+ if (IS_ERR(match)) {
duprintf("find_check_match: `%s' not found\n", m->u.user.name);
- return match ? PTR_ERR(match) : -ENOENT;
+ return PTR_ERR(match);
}
m->u.kernel.match = match;
- ret = check_match(m, par, i);
+ ret = check_match(m, par);
if (ret)
goto err;
@@ -668,10 +643,11 @@ err:
return ret;
}
-static int check_target(struct ip6t_entry *e, const char *name)
+static int check_target(struct ip6t_entry *e, struct net *net, const char *name)
{
struct ip6t_entry_target *t = ip6t_get_target(e);
struct xt_tgchk_param par = {
+ .net = net,
.table = name,
.entryinfo = e,
.target = t->u.kernel.target,
@@ -693,61 +669,66 @@ static int check_target(struct ip6t_entry *e, const char *name)
}
static int
-find_check_entry(struct ip6t_entry *e, const char *name, unsigned int size,
- unsigned int *i)
+find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
+ unsigned int size)
{
struct ip6t_entry_target *t;
struct xt_target *target;
int ret;
unsigned int j;
struct xt_mtchk_param mtpar;
+ struct xt_entry_match *ematch;
ret = check_entry(e, name);
if (ret)
return ret;
j = 0;
+ mtpar.net = net;
mtpar.table = name;
mtpar.entryinfo = &e->ipv6;
mtpar.hook_mask = e->comefrom;
mtpar.family = NFPROTO_IPV6;
- ret = IP6T_MATCH_ITERATE(e, find_check_match, &mtpar, &j);
- if (ret != 0)
- goto cleanup_matches;
+ xt_ematch_foreach(ematch, e) {
+ ret = find_check_match(ematch, &mtpar);
+ if (ret != 0)
+ goto cleanup_matches;
+ ++j;
+ }
t = ip6t_get_target(e);
- target = try_then_request_module(xt_find_target(AF_INET6,
- t->u.user.name,
- t->u.user.revision),
- "ip6t_%s", t->u.user.name);
- if (IS_ERR(target) || !target) {
+ target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name,
+ t->u.user.revision);
+ if (IS_ERR(target)) {
duprintf("find_check_entry: `%s' not found\n", t->u.user.name);
- ret = target ? PTR_ERR(target) : -ENOENT;
+ ret = PTR_ERR(target);
goto cleanup_matches;
}
t->u.kernel.target = target;
- ret = check_target(e, name);
+ ret = check_target(e, net, name);
if (ret)
goto err;
-
- (*i)++;
return 0;
err:
module_put(t->u.kernel.target->me);
cleanup_matches:
- IP6T_MATCH_ITERATE(e, cleanup_match, &j);
+ xt_ematch_foreach(ematch, e) {
+ if (j-- == 0)
+ break;
+ cleanup_match(ematch, net);
+ }
return ret;
}
-static bool check_underflow(struct ip6t_entry *e)
+static bool check_underflow(const struct ip6t_entry *e)
{
const struct ip6t_entry_target *t;
unsigned int verdict;
if (!unconditional(&e->ipv6))
return false;
- t = ip6t_get_target(e);
+ t = ip6t_get_target_c(e);
if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
return false;
verdict = ((struct ip6t_standard_target *)t)->verdict;
@@ -758,12 +739,11 @@ static bool check_underflow(struct ip6t_entry *e)
static int
check_entry_size_and_hooks(struct ip6t_entry *e,
struct xt_table_info *newinfo,
- unsigned char *base,
- unsigned char *limit,
+ const unsigned char *base,
+ const unsigned char *limit,
const unsigned int *hook_entries,
const unsigned int *underflows,
- unsigned int valid_hooks,
- unsigned int *i)
+ unsigned int valid_hooks)
{
unsigned int h;
@@ -800,50 +780,41 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
/* Clear counters and comefrom */
e->counters = ((struct xt_counters) { 0, 0 });
e->comefrom = 0;
-
- (*i)++;
return 0;
}
-static int
-cleanup_entry(struct ip6t_entry *e, unsigned int *i)
+static void cleanup_entry(struct ip6t_entry *e, struct net *net)
{
struct xt_tgdtor_param par;
struct ip6t_entry_target *t;
-
- if (i && (*i)-- == 0)
- return 1;
+ struct xt_entry_match *ematch;
/* Cleanup all matches */
- IP6T_MATCH_ITERATE(e, cleanup_match, NULL);
+ xt_ematch_foreach(ematch, e)
+ cleanup_match(ematch, net);
t = ip6t_get_target(e);
+ par.net = net;
par.target = t->u.kernel.target;
par.targinfo = t->data;
par.family = NFPROTO_IPV6;
if (par.target->destroy != NULL)
par.target->destroy(&par);
module_put(par.target->me);
- return 0;
}
/* Checks and translates the user-supplied table segment (held in
newinfo) */
static int
-translate_table(const char *name,
- unsigned int valid_hooks,
- struct xt_table_info *newinfo,
- void *entry0,
- unsigned int size,
- unsigned int number,
- const unsigned int *hook_entries,
- const unsigned int *underflows)
+translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
+ const struct ip6t_replace *repl)
{
+ struct ip6t_entry *iter;
unsigned int i;
- int ret;
+ int ret = 0;
- newinfo->size = size;
- newinfo->number = number;
+ newinfo->size = repl->size;
+ newinfo->number = repl->num_entries;
/* Init all hooks to impossible value. */
for (i = 0; i < NF_INET_NUMHOOKS; i++) {
@@ -854,49 +825,61 @@ translate_table(const char *name,
duprintf("translate_table: size %u\n", newinfo->size);
i = 0;
/* Walk through entries, checking offsets. */
- ret = IP6T_ENTRY_ITERATE(entry0, newinfo->size,
- check_entry_size_and_hooks,
- newinfo,
- entry0,
- entry0 + size,
- hook_entries, underflows, valid_hooks, &i);
- if (ret != 0)
- return ret;
+ xt_entry_foreach(iter, entry0, newinfo->size) {
+ ret = check_entry_size_and_hooks(iter, newinfo, entry0,
+ entry0 + repl->size,
+ repl->hook_entry,
+ repl->underflow,
+ repl->valid_hooks);
+ if (ret != 0)
+ return ret;
+ ++i;
+ if (strcmp(ip6t_get_target(iter)->u.user.name,
+ XT_ERROR_TARGET) == 0)
+ ++newinfo->stacksize;
+ }
- if (i != number) {
+ if (i != repl->num_entries) {
duprintf("translate_table: %u not %u entries\n",
- i, number);
+ i, repl->num_entries);
return -EINVAL;
}
/* Check hooks all assigned */
for (i = 0; i < NF_INET_NUMHOOKS; i++) {
/* Only hooks which are valid */
- if (!(valid_hooks & (1 << i)))
+ if (!(repl->valid_hooks & (1 << i)))
continue;
if (newinfo->hook_entry[i] == 0xFFFFFFFF) {
duprintf("Invalid hook entry %u %u\n",
- i, hook_entries[i]);
+ i, repl->hook_entry[i]);
return -EINVAL;
}
if (newinfo->underflow[i] == 0xFFFFFFFF) {
duprintf("Invalid underflow %u %u\n",
- i, underflows[i]);
+ i, repl->underflow[i]);
return -EINVAL;
}
}
- if (!mark_source_chains(newinfo, valid_hooks, entry0))
+ if (!mark_source_chains(newinfo, repl->valid_hooks, entry0))
return -ELOOP;
/* Finally, each sanity check must pass */
i = 0;
- ret = IP6T_ENTRY_ITERATE(entry0, newinfo->size,
- find_check_entry, name, size, &i);
+ xt_entry_foreach(iter, entry0, newinfo->size) {
+ ret = find_check_entry(iter, net, repl->name, repl->size);
+ if (ret != 0)
+ break;
+ ++i;
+ }
if (ret != 0) {
- IP6T_ENTRY_ITERATE(entry0, newinfo->size,
- cleanup_entry, &i);
+ xt_entry_foreach(iter, entry0, newinfo->size) {
+ if (i-- == 0)
+ break;
+ cleanup_entry(iter, net);
+ }
return ret;
}
@@ -909,33 +892,11 @@ translate_table(const char *name,
return ret;
}
-/* Gets counters. */
-static inline int
-add_entry_to_counter(const struct ip6t_entry *e,
- struct xt_counters total[],
- unsigned int *i)
-{
- ADD_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt);
-
- (*i)++;
- return 0;
-}
-
-static inline int
-set_entry_to_counter(const struct ip6t_entry *e,
- struct ip6t_counters total[],
- unsigned int *i)
-{
- SET_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt);
-
- (*i)++;
- return 0;
-}
-
static void
get_counters(const struct xt_table_info *t,
struct xt_counters counters[])
{
+ struct ip6t_entry *iter;
unsigned int cpu;
unsigned int i;
unsigned int curcpu;
@@ -951,32 +912,32 @@ get_counters(const struct xt_table_info *t,
curcpu = smp_processor_id();
i = 0;
- IP6T_ENTRY_ITERATE(t->entries[curcpu],
- t->size,
- set_entry_to_counter,
- counters,
- &i);
+ xt_entry_foreach(iter, t->entries[curcpu], t->size) {
+ SET_COUNTER(counters[i], iter->counters.bcnt,
+ iter->counters.pcnt);
+ ++i;
+ }
for_each_possible_cpu(cpu) {
if (cpu == curcpu)
continue;
i = 0;
xt_info_wrlock(cpu);
- IP6T_ENTRY_ITERATE(t->entries[cpu],
- t->size,
- add_entry_to_counter,
- counters,
- &i);
+ xt_entry_foreach(iter, t->entries[cpu], t->size) {
+ ADD_COUNTER(counters[i], iter->counters.bcnt,
+ iter->counters.pcnt);
+ ++i;
+ }
xt_info_wrunlock(cpu);
}
local_bh_enable();
}
-static struct xt_counters *alloc_counters(struct xt_table *table)
+static struct xt_counters *alloc_counters(const struct xt_table *table)
{
unsigned int countersize;
struct xt_counters *counters;
- struct xt_table_info *private = table->private;
+ const struct xt_table_info *private = table->private;
/* We need atomic snapshot of counters: rest doesn't change
(other than comefrom, which userspace doesn't care
@@ -994,11 +955,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table)
static int
copy_entries_to_user(unsigned int total_size,
- struct xt_table *table,
+ const struct xt_table *table,
void __user *userptr)
{
unsigned int off, num;
- struct ip6t_entry *e;
+ const struct ip6t_entry *e;
struct xt_counters *counters;
const struct xt_table_info *private = table->private;
int ret = 0;
@@ -1050,7 +1011,7 @@ copy_entries_to_user(unsigned int total_size,
}
}
- t = ip6t_get_target(e);
+ t = ip6t_get_target_c(e);
if (copy_to_user(userptr + off + e->target_offset
+ offsetof(struct ip6t_entry_target,
u.user.name),
@@ -1067,7 +1028,7 @@ copy_entries_to_user(unsigned int total_size,
}
#ifdef CONFIG_COMPAT
-static void compat_standard_from_user(void *dst, void *src)
+static void compat_standard_from_user(void *dst, const void *src)
{
int v = *(compat_int_t *)src;
@@ -1076,7 +1037,7 @@ static void compat_standard_from_user(void *dst, void *src)
memcpy(dst, &v, sizeof(v));
}
-static int compat_standard_to_user(void __user *dst, void *src)
+static int compat_standard_to_user(void __user *dst, const void *src)
{
compat_int_t cv = *(int *)src;
@@ -1085,25 +1046,20 @@ static int compat_standard_to_user(void __user *dst, void *src)
return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0;
}
-static inline int
-compat_calc_match(struct ip6t_entry_match *m, int *size)
-{
- *size += xt_compat_match_offset(m->u.kernel.match);
- return 0;
-}
-
-static int compat_calc_entry(struct ip6t_entry *e,
+static int compat_calc_entry(const struct ip6t_entry *e,
const struct xt_table_info *info,
- void *base, struct xt_table_info *newinfo)
+ const void *base, struct xt_table_info *newinfo)
{
- struct ip6t_entry_target *t;
+ const struct xt_entry_match *ematch;
+ const struct ip6t_entry_target *t;
unsigned int entry_offset;
int off, i, ret;
off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry);
entry_offset = (void *)e - base;
- IP6T_MATCH_ITERATE(e, compat_calc_match, &off);
- t = ip6t_get_target(e);
+ xt_ematch_foreach(ematch, e)
+ off += xt_compat_match_offset(ematch->u.kernel.match);
+ t = ip6t_get_target_c(e);
off += xt_compat_target_offset(t->u.kernel.target);
newinfo->size -= off;
ret = xt_compat_add_offset(AF_INET6, entry_offset, off);
@@ -1124,7 +1080,9 @@ static int compat_calc_entry(struct ip6t_entry *e,
static int compat_table_info(const struct xt_table_info *info,
struct xt_table_info *newinfo)
{
+ struct ip6t_entry *iter;
void *loc_cpu_entry;
+ int ret;
if (!newinfo || !info)
return -EINVAL;
@@ -1133,13 +1091,17 @@ static int compat_table_info(const struct xt_table_info *info,
memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
newinfo->initial_entries = 0;
loc_cpu_entry = info->entries[raw_smp_processor_id()];
- return IP6T_ENTRY_ITERATE(loc_cpu_entry, info->size,
- compat_calc_entry, info, loc_cpu_entry,
- newinfo);
+ xt_entry_foreach(iter, loc_cpu_entry, info->size) {
+ ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
+ if (ret != 0)
+ return ret;
+ }
+ return 0;
}
#endif
-static int get_info(struct net *net, void __user *user, int *len, int compat)
+static int get_info(struct net *net, void __user *user,
+ const int *len, int compat)
{
char name[IP6T_TABLE_MAXNAMELEN];
struct xt_table *t;
@@ -1164,10 +1126,10 @@ static int get_info(struct net *net, void __user *user, int *len, int compat)
if (t && !IS_ERR(t)) {
struct ip6t_getinfo info;
const struct xt_table_info *private = t->private;
-
#ifdef CONFIG_COMPAT
+ struct xt_table_info tmp;
+
if (compat) {
- struct xt_table_info tmp;
ret = compat_table_info(private, &tmp);
xt_compat_flush_offsets(AF_INET6);
private = &tmp;
@@ -1199,7 +1161,8 @@ static int get_info(struct net *net, void __user *user, int *len, int compat)
}
static int
-get_entries(struct net *net, struct ip6t_get_entries __user *uptr, int *len)
+get_entries(struct net *net, struct ip6t_get_entries __user *uptr,
+ const int *len)
{
int ret;
struct ip6t_get_entries get;
@@ -1247,6 +1210,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
struct xt_table_info *oldinfo;
struct xt_counters *counters;
const void *loc_cpu_old_entry;
+ struct ip6t_entry *iter;
ret = 0;
counters = vmalloc_node(num_counters * sizeof(struct xt_counters),
@@ -1290,8 +1254,9 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
/* Decrease module usage counts and free resource */
loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()];
- IP6T_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,
- NULL);
+ xt_entry_foreach(iter, loc_cpu_old_entry, oldinfo->size)
+ cleanup_entry(iter, net);
+
xt_free_table_info(oldinfo);
if (copy_to_user(counters_ptr, counters,
sizeof(struct xt_counters) * num_counters) != 0)
@@ -1310,12 +1275,13 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
}
static int
-do_replace(struct net *net, void __user *user, unsigned int len)
+do_replace(struct net *net, const void __user *user, unsigned int len)
{
int ret;
struct ip6t_replace tmp;
struct xt_table_info *newinfo;
void *loc_cpu_entry;
+ struct ip6t_entry *iter;
if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
return -EFAULT;
@@ -1336,9 +1302,7 @@ do_replace(struct net *net, void __user *user, unsigned int len)
goto free_newinfo;
}
- ret = translate_table(tmp.name, tmp.valid_hooks,
- newinfo, loc_cpu_entry, tmp.size, tmp.num_entries,
- tmp.hook_entry, tmp.underflow);
+ ret = translate_table(net, newinfo, loc_cpu_entry, &tmp);
if (ret != 0)
goto free_newinfo;
@@ -1351,27 +1315,15 @@ do_replace(struct net *net, void __user *user, unsigned int len)
return 0;
free_newinfo_untrans:
- IP6T_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL);
+ xt_entry_foreach(iter, loc_cpu_entry, newinfo->size)
+ cleanup_entry(iter, net);
free_newinfo:
xt_free_table_info(newinfo);
return ret;
}
-/* We're lazy, and add to the first CPU; overflow works its fey magic
- * and everything is OK. */
-static int
-add_counter_to_entry(struct ip6t_entry *e,
- const struct xt_counters addme[],
- unsigned int *i)
-{
- ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
-
- (*i)++;
- return 0;
-}
-
static int
-do_add_counters(struct net *net, void __user *user, unsigned int len,
+do_add_counters(struct net *net, const void __user *user, unsigned int len,
int compat)
{
unsigned int i, curcpu;
@@ -1385,6 +1337,7 @@ do_add_counters(struct net *net, void __user *user, unsigned int len,
const struct xt_table_info *private;
int ret = 0;
const void *loc_cpu_entry;
+ struct ip6t_entry *iter;
#ifdef CONFIG_COMPAT
struct compat_xt_counters_info compat_tmp;
@@ -1443,11 +1396,10 @@ do_add_counters(struct net *net, void __user *user, unsigned int len,
curcpu = smp_processor_id();
xt_info_wrlock(curcpu);
loc_cpu_entry = private->entries[curcpu];
- IP6T_ENTRY_ITERATE(loc_cpu_entry,
- private->size,
- add_counter_to_entry,
- paddc,
- &i);
+ xt_entry_foreach(iter, loc_cpu_entry, private->size) {
+ ADD_COUNTER(iter->counters, paddc[i].bcnt, paddc[i].pcnt);
+ ++i;
+ }
xt_info_wrunlock(curcpu);
unlock_up_free:
@@ -1476,45 +1428,40 @@ struct compat_ip6t_replace {
static int
compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr,
unsigned int *size, struct xt_counters *counters,
- unsigned int *i)
+ unsigned int i)
{
struct ip6t_entry_target *t;
struct compat_ip6t_entry __user *ce;
u_int16_t target_offset, next_offset;
compat_uint_t origsize;
- int ret;
+ const struct xt_entry_match *ematch;
+ int ret = 0;
- ret = -EFAULT;
origsize = *size;
ce = (struct compat_ip6t_entry __user *)*dstptr;
- if (copy_to_user(ce, e, sizeof(struct ip6t_entry)))
- goto out;
-
- if (copy_to_user(&ce->counters, &counters[*i], sizeof(counters[*i])))
- goto out;
+ if (copy_to_user(ce, e, sizeof(struct ip6t_entry)) != 0 ||
+ copy_to_user(&ce->counters, &counters[i],
+ sizeof(counters[i])) != 0)
+ return -EFAULT;
*dstptr += sizeof(struct compat_ip6t_entry);
*size -= sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry);
- ret = IP6T_MATCH_ITERATE(e, xt_compat_match_to_user, dstptr, size);
+ xt_ematch_foreach(ematch, e) {
+ ret = xt_compat_match_to_user(ematch, dstptr, size);
+ if (ret != 0)
+ return ret;
+ }
target_offset = e->target_offset - (origsize - *size);
- if (ret)
- goto out;
t = ip6t_get_target(e);
ret = xt_compat_target_to_user(t, dstptr, size);
if (ret)
- goto out;
- ret = -EFAULT;
+ return ret;
next_offset = e->next_offset - (origsize - *size);
- if (put_user(target_offset, &ce->target_offset))
- goto out;
- if (put_user(next_offset, &ce->next_offset))
- goto out;
-
- (*i)++;
+ if (put_user(target_offset, &ce->target_offset) != 0 ||
+ put_user(next_offset, &ce->next_offset) != 0)
+ return -EFAULT;
return 0;
-out:
- return ret;
}
static int
@@ -1522,61 +1469,45 @@ compat_find_calc_match(struct ip6t_entry_match *m,
const char *name,
const struct ip6t_ip6 *ipv6,
unsigned int hookmask,
- int *size, unsigned int *i)
+ int *size)
{
struct xt_match *match;
- match = try_then_request_module(xt_find_match(AF_INET6, m->u.user.name,
- m->u.user.revision),
- "ip6t_%s", m->u.user.name);
- if (IS_ERR(match) || !match) {
+ match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name,
+ m->u.user.revision);
+ if (IS_ERR(match)) {
duprintf("compat_check_calc_match: `%s' not found\n",
m->u.user.name);
- return match ? PTR_ERR(match) : -ENOENT;
+ return PTR_ERR(match);
}
m->u.kernel.match = match;
*size += xt_compat_match_offset(match);
-
- (*i)++;
- return 0;
-}
-
-static int
-compat_release_match(struct ip6t_entry_match *m, unsigned int *i)
-{
- if (i && (*i)-- == 0)
- return 1;
-
- module_put(m->u.kernel.match->me);
return 0;
}
-static int
-compat_release_entry(struct compat_ip6t_entry *e, unsigned int *i)
+static void compat_release_entry(struct compat_ip6t_entry *e)
{
struct ip6t_entry_target *t;
-
- if (i && (*i)-- == 0)
- return 1;
+ struct xt_entry_match *ematch;
/* Cleanup all matches */
- COMPAT_IP6T_MATCH_ITERATE(e, compat_release_match, NULL);
+ xt_ematch_foreach(ematch, e)
+ module_put(ematch->u.kernel.match->me);
t = compat_ip6t_get_target(e);
module_put(t->u.kernel.target->me);
- return 0;
}
static int
check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
struct xt_table_info *newinfo,
unsigned int *size,
- unsigned char *base,
- unsigned char *limit,
- unsigned int *hook_entries,
- unsigned int *underflows,
- unsigned int *i,
+ const unsigned char *base,
+ const unsigned char *limit,
+ const unsigned int *hook_entries,
+ const unsigned int *underflows,
const char *name)
{
+ struct xt_entry_match *ematch;
struct ip6t_entry_target *t;
struct xt_target *target;
unsigned int entry_offset;
@@ -1605,20 +1536,21 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry);
entry_offset = (void *)e - (void *)base;
j = 0;
- ret = COMPAT_IP6T_MATCH_ITERATE(e, compat_find_calc_match, name,
- &e->ipv6, e->comefrom, &off, &j);
- if (ret != 0)
- goto release_matches;
+ xt_ematch_foreach(ematch, e) {
+ ret = compat_find_calc_match(ematch, name,
+ &e->ipv6, e->comefrom, &off);
+ if (ret != 0)
+ goto release_matches;
+ ++j;
+ }
t = compat_ip6t_get_target(e);
- target = try_then_request_module(xt_find_target(AF_INET6,
- t->u.user.name,
- t->u.user.revision),
- "ip6t_%s", t->u.user.name);
- if (IS_ERR(target) || !target) {
+ target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name,
+ t->u.user.revision);
+ if (IS_ERR(target)) {
duprintf("check_compat_entry_size_and_hooks: `%s' not found\n",
t->u.user.name);
- ret = target ? PTR_ERR(target) : -ENOENT;
+ ret = PTR_ERR(target);
goto release_matches;
}
t->u.kernel.target = target;
@@ -1640,14 +1572,16 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
/* Clear counters and comefrom */
memset(&e->counters, 0, sizeof(e->counters));
e->comefrom = 0;
-
- (*i)++;
return 0;
out:
module_put(t->u.kernel.target->me);
release_matches:
- IP6T_MATCH_ITERATE(e, compat_release_match, &j);
+ xt_ematch_foreach(ematch, e) {
+ if (j-- == 0)
+ break;
+ module_put(ematch->u.kernel.match->me);
+ }
return ret;
}
@@ -1661,6 +1595,7 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
struct ip6t_entry *de;
unsigned int origsize;
int ret, h;
+ struct xt_entry_match *ematch;
ret = 0;
origsize = *size;
@@ -1671,10 +1606,11 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
*dstptr += sizeof(struct ip6t_entry);
*size += sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry);
- ret = COMPAT_IP6T_MATCH_ITERATE(e, xt_compat_match_from_user,
- dstptr, size);
- if (ret)
- return ret;
+ xt_ematch_foreach(ematch, e) {
+ ret = xt_compat_match_from_user(ematch, dstptr, size);
+ if (ret != 0)
+ return ret;
+ }
de->target_offset = e->target_offset - (origsize - *size);
t = compat_ip6t_get_target(e);
target = t->u.kernel.target;
@@ -1690,36 +1626,44 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
return ret;
}
-static int compat_check_entry(struct ip6t_entry *e, const char *name,
- unsigned int *i)
+static int compat_check_entry(struct ip6t_entry *e, struct net *net,
+ const char *name)
{
unsigned int j;
- int ret;
+ int ret = 0;
struct xt_mtchk_param mtpar;
+ struct xt_entry_match *ematch;
j = 0;
+ mtpar.net = net;
mtpar.table = name;
mtpar.entryinfo = &e->ipv6;
mtpar.hook_mask = e->comefrom;
mtpar.family = NFPROTO_IPV6;
- ret = IP6T_MATCH_ITERATE(e, check_match, &mtpar, &j);
- if (ret)
- goto cleanup_matches;
+ xt_ematch_foreach(ematch, e) {
+ ret = check_match(ematch, &mtpar);
+ if (ret != 0)
+ goto cleanup_matches;
+ ++j;
+ }
- ret = check_target(e, name);
+ ret = check_target(e, net, name);
if (ret)
goto cleanup_matches;
-
- (*i)++;
return 0;
cleanup_matches:
- IP6T_MATCH_ITERATE(e, cleanup_match, &j);
+ xt_ematch_foreach(ematch, e) {
+ if (j-- == 0)
+ break;
+ cleanup_match(ematch, net);
+ }
return ret;
}
static int
-translate_compat_table(const char *name,
+translate_compat_table(struct net *net,
+ const char *name,
unsigned int valid_hooks,
struct xt_table_info **pinfo,
void **pentry0,
@@ -1731,8 +1675,10 @@ translate_compat_table(const char *name,
unsigned int i, j;
struct xt_table_info *newinfo, *info;
void *pos, *entry0, *entry1;
+ struct compat_ip6t_entry *iter0;
+ struct ip6t_entry *iter1;
unsigned int size;
- int ret;
+ int ret = 0;
info = *pinfo;
entry0 = *pentry0;
@@ -1749,13 +1695,17 @@ translate_compat_table(const char *name,
j = 0;
xt_compat_lock(AF_INET6);
/* Walk through entries, checking offsets. */
- ret = COMPAT_IP6T_ENTRY_ITERATE(entry0, total_size,
- check_compat_entry_size_and_hooks,
- info, &size, entry0,
- entry0 + total_size,
- hook_entries, underflows, &j, name);
- if (ret != 0)
- goto out_unlock;
+ xt_entry_foreach(iter0, entry0, total_size) {
+ ret = check_compat_entry_size_and_hooks(iter0, info, &size,
+ entry0,
+ entry0 + total_size,
+ hook_entries,
+ underflows,
+ name);
+ if (ret != 0)
+ goto out_unlock;
+ ++j;
+ }
ret = -EINVAL;
if (j != number) {
@@ -1794,9 +1744,12 @@ translate_compat_table(const char *name,
entry1 = newinfo->entries[raw_smp_processor_id()];
pos = entry1;
size = total_size;
- ret = COMPAT_IP6T_ENTRY_ITERATE(entry0, total_size,
- compat_copy_entry_from_user,
- &pos, &size, name, newinfo, entry1);
+ xt_entry_foreach(iter0, entry0, total_size) {
+ ret = compat_copy_entry_from_user(iter0, &pos, &size,
+ name, newinfo, entry1);
+ if (ret != 0)
+ break;
+ }
xt_compat_flush_offsets(AF_INET6);
xt_compat_unlock(AF_INET6);
if (ret)
@@ -1807,13 +1760,32 @@ translate_compat_table(const char *name,
goto free_newinfo;
i = 0;
- ret = IP6T_ENTRY_ITERATE(entry1, newinfo->size, compat_check_entry,
- name, &i);
+ xt_entry_foreach(iter1, entry1, newinfo->size) {
+ ret = compat_check_entry(iter1, net, name);
+ if (ret != 0)
+ break;
+ ++i;
+ }
if (ret) {
+ /*
+ * The first i matches need cleanup_entry (calls ->destroy)
+ * because they had called ->check already. The other j-i
+ * entries need only release.
+ */
+ int skip = i;
j -= i;
- COMPAT_IP6T_ENTRY_ITERATE_CONTINUE(entry0, newinfo->size, i,
- compat_release_entry, &j);
- IP6T_ENTRY_ITERATE(entry1, newinfo->size, cleanup_entry, &i);
+ xt_entry_foreach(iter0, entry0, newinfo->size) {
+ if (skip-- > 0)
+ continue;
+ if (j-- == 0)
+ break;
+ compat_release_entry(iter0);
+ }
+ xt_entry_foreach(iter1, entry1, newinfo->size) {
+ if (i-- == 0)
+ break;
+ cleanup_entry(iter1, net);
+ }
xt_free_table_info(newinfo);
return ret;
}
@@ -1831,7 +1803,11 @@ translate_compat_table(const char *name,
free_newinfo:
xt_free_table_info(newinfo);
out:
- COMPAT_IP6T_ENTRY_ITERATE(entry0, total_size, compat_release_entry, &j);
+ xt_entry_foreach(iter0, entry0, total_size) {
+ if (j-- == 0)
+ break;
+ compat_release_entry(iter0);
+ }
return ret;
out_unlock:
xt_compat_flush_offsets(AF_INET6);
@@ -1846,6 +1822,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
struct compat_ip6t_replace tmp;
struct xt_table_info *newinfo;
void *loc_cpu_entry;
+ struct ip6t_entry *iter;
if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
return -EFAULT;
@@ -1868,7 +1845,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
goto free_newinfo;
}
- ret = translate_compat_table(tmp.name, tmp.valid_hooks,
+ ret = translate_compat_table(net, tmp.name, tmp.valid_hooks,
&newinfo, &loc_cpu_entry, tmp.size,
tmp.num_entries, tmp.hook_entry,
tmp.underflow);
@@ -1884,7 +1861,8 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
return 0;
free_newinfo_untrans:
- IP6T_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL);
+ xt_entry_foreach(iter, loc_cpu_entry, newinfo->size)
+ cleanup_entry(iter, net);
free_newinfo:
xt_free_table_info(newinfo);
return ret;
@@ -1933,6 +1911,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
int ret = 0;
const void *loc_cpu_entry;
unsigned int i = 0;
+ struct ip6t_entry *iter;
counters = alloc_counters(table);
if (IS_ERR(counters))
@@ -1945,9 +1924,12 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
loc_cpu_entry = private->entries[raw_smp_processor_id()];
pos = userptr;
size = total_size;
- ret = IP6T_ENTRY_ITERATE(loc_cpu_entry, total_size,
- compat_copy_entry_to_user,
- &pos, &size, counters, &i);
+ xt_entry_foreach(iter, loc_cpu_entry, total_size) {
+ ret = compat_copy_entry_to_user(iter, &pos,
+ &size, counters, i++);
+ if (ret != 0)
+ break;
+ }
vfree(counters);
return ret;
@@ -2106,8 +2088,7 @@ struct xt_table *ip6t_register_table(struct net *net,
{
int ret;
struct xt_table_info *newinfo;
- struct xt_table_info bootstrap
- = { 0, 0, 0, { 0 }, { 0 }, { } };
+ struct xt_table_info bootstrap = {0};
void *loc_cpu_entry;
struct xt_table *new_table;
@@ -2121,11 +2102,7 @@ struct xt_table *ip6t_register_table(struct net *net,
loc_cpu_entry = newinfo->entries[raw_smp_processor_id()];
memcpy(loc_cpu_entry, repl->entries, repl->size);
- ret = translate_table(table->name, table->valid_hooks,
- newinfo, loc_cpu_entry, repl->size,
- repl->num_entries,
- repl->hook_entry,
- repl->underflow);
+ ret = translate_table(net, newinfo, loc_cpu_entry, repl);
if (ret != 0)
goto out_free;
@@ -2142,17 +2119,19 @@ out:
return ERR_PTR(ret);
}
-void ip6t_unregister_table(struct xt_table *table)
+void ip6t_unregister_table(struct net *net, struct xt_table *table)
{
struct xt_table_info *private;
void *loc_cpu_entry;
struct module *table_owner = table->me;
+ struct ip6t_entry *iter;
private = xt_unregister_table(table);
/* Decrease module usage counts and free resources */
loc_cpu_entry = private->entries[raw_smp_processor_id()];
- IP6T_ENTRY_ITERATE(loc_cpu_entry, private->size, cleanup_entry, NULL);
+ xt_entry_foreach(iter, loc_cpu_entry, private->size)
+ cleanup_entry(iter, net);
if (private->number > private->initial_entries)
module_put(table_owner);
xt_free_table_info(private);
@@ -2169,7 +2148,7 @@ icmp6_type_code_match(u_int8_t test_type, u_int8_t min_code, u_int8_t max_code,
}
static bool
-icmp6_match(const struct sk_buff *skb, const struct xt_match_param *par)
+icmp6_match(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct icmp6hdr *ic;
struct icmp6hdr _icmph;
@@ -2185,7 +2164,7 @@ icmp6_match(const struct sk_buff *skb, const struct xt_match_param *par)
* can't. Hence, no choice but to drop.
*/
duprintf("Dropping evil ICMP tinygram.\n");
- *par->hotdrop = true;
+ par->hotdrop = true;
return false;
}
@@ -2197,31 +2176,32 @@ icmp6_match(const struct sk_buff *skb, const struct xt_match_param *par)
}
/* Called when user tries to insert an entry of this type. */
-static bool icmp6_checkentry(const struct xt_mtchk_param *par)
+static int icmp6_checkentry(const struct xt_mtchk_param *par)
{
const struct ip6t_icmp *icmpinfo = par->matchinfo;
/* Must specify no unknown invflags */
- return !(icmpinfo->invflags & ~IP6T_ICMP_INV);
+ return (icmpinfo->invflags & ~IP6T_ICMP_INV) ? -EINVAL : 0;
}
/* The built-in targets: standard (NULL) and error. */
-static struct xt_target ip6t_standard_target __read_mostly = {
- .name = IP6T_STANDARD_TARGET,
- .targetsize = sizeof(int),
- .family = NFPROTO_IPV6,
+static struct xt_target ip6t_builtin_tg[] __read_mostly = {
+ {
+ .name = IP6T_STANDARD_TARGET,
+ .targetsize = sizeof(int),
+ .family = NFPROTO_IPV6,
#ifdef CONFIG_COMPAT
- .compatsize = sizeof(compat_int_t),
- .compat_from_user = compat_standard_from_user,
- .compat_to_user = compat_standard_to_user,
+ .compatsize = sizeof(compat_int_t),
+ .compat_from_user = compat_standard_from_user,
+ .compat_to_user = compat_standard_to_user,
#endif
-};
-
-static struct xt_target ip6t_error_target __read_mostly = {
- .name = IP6T_ERROR_TARGET,
- .target = ip6t_error,
- .targetsize = IP6T_FUNCTION_MAXNAMELEN,
- .family = NFPROTO_IPV6,
+ },
+ {
+ .name = IP6T_ERROR_TARGET,
+ .target = ip6t_error,
+ .targetsize = IP6T_FUNCTION_MAXNAMELEN,
+ .family = NFPROTO_IPV6,
+ },
};
static struct nf_sockopt_ops ip6t_sockopts = {
@@ -2241,13 +2221,15 @@ static struct nf_sockopt_ops ip6t_sockopts = {
.owner = THIS_MODULE,
};
-static struct xt_match icmp6_matchstruct __read_mostly = {
- .name = "icmp6",
- .match = icmp6_match,
- .matchsize = sizeof(struct ip6t_icmp),
- .checkentry = icmp6_checkentry,
- .proto = IPPROTO_ICMPV6,
- .family = NFPROTO_IPV6,
+static struct xt_match ip6t_builtin_mt[] __read_mostly = {
+ {
+ .name = "icmp6",
+ .match = icmp6_match,
+ .matchsize = sizeof(struct ip6t_icmp),
+ .checkentry = icmp6_checkentry,
+ .proto = IPPROTO_ICMPV6,
+ .family = NFPROTO_IPV6,
+ },
};
static int __net_init ip6_tables_net_init(struct net *net)
@@ -2274,13 +2256,10 @@ static int __init ip6_tables_init(void)
goto err1;
/* Noone else will be downing sem now, so we won't sleep */
- ret = xt_register_target(&ip6t_standard_target);
+ ret = xt_register_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg));
if (ret < 0)
goto err2;
- ret = xt_register_target(&ip6t_error_target);
- if (ret < 0)
- goto err3;
- ret = xt_register_match(&icmp6_matchstruct);
+ ret = xt_register_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt));
if (ret < 0)
goto err4;
@@ -2289,15 +2268,13 @@ static int __init ip6_tables_init(void)
if (ret < 0)
goto err5;
- printk(KERN_INFO "ip6_tables: (C) 2000-2006 Netfilter Core Team\n");
+ pr_info("(C) 2000-2006 Netfilter Core Team\n");
return 0;
err5:
- xt_unregister_match(&icmp6_matchstruct);
+ xt_unregister_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt));
err4:
- xt_unregister_target(&ip6t_error_target);
-err3:
- xt_unregister_target(&ip6t_standard_target);
+ xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg));
err2:
unregister_pernet_subsys(&ip6_tables_net_ops);
err1:
@@ -2308,10 +2285,8 @@ static void __exit ip6_tables_fini(void)
{
nf_unregister_sockopt(&ip6t_sockopts);
- xt_unregister_match(&icmp6_matchstruct);
- xt_unregister_target(&ip6t_error_target);
- xt_unregister_target(&ip6t_standard_target);
-
+ xt_unregister_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt));
+ xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg));
unregister_pernet_subsys(&ip6_tables_net_ops);
}
diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c
index b285fdf19050..af4ee11f2066 100644
--- a/net/ipv6/netfilter/ip6t_LOG.c
+++ b/net/ipv6/netfilter/ip6t_LOG.c
@@ -9,9 +9,8 @@
* 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/moduleparam.h>
#include <linux/skbuff.h>
#include <linux/if_arp.h>
#include <linux/ip.h>
@@ -378,7 +377,7 @@ static struct nf_loginfo default_loginfo = {
.type = NF_LOG_TYPE_LOG,
.u = {
.log = {
- .level = 0,
+ .level = 5,
.logflags = NF_LOG_MASK,
},
},
@@ -437,7 +436,7 @@ ip6t_log_packet(u_int8_t pf,
}
static unsigned int
-log_tg6(struct sk_buff *skb, const struct xt_target_param *par)
+log_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ip6t_log_info *loginfo = par->targinfo;
struct nf_loginfo li;
@@ -452,20 +451,19 @@ log_tg6(struct sk_buff *skb, const struct xt_target_param *par)
}
-static bool log_tg6_check(const struct xt_tgchk_param *par)
+static int log_tg6_check(const struct xt_tgchk_param *par)
{
const struct ip6t_log_info *loginfo = par->targinfo;
if (loginfo->level >= 8) {
- pr_debug("LOG: level %u >= 8\n", loginfo->level);
- return false;
+ pr_debug("level %u >= 8\n", loginfo->level);
+ return -EINVAL;
}
if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') {
- pr_debug("LOG: prefix term %i\n",
- loginfo->prefix[sizeof(loginfo->prefix)-1]);
- return false;
+ pr_debug("prefix not null-terminated\n");
+ return -EINVAL;
}
- return true;
+ return 0;
}
static struct xt_target log_tg6_reg __read_mostly = {
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index 8311ca31816a..2933396e0281 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -14,7 +14,9 @@
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/gfp.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/icmpv6.h>
@@ -49,7 +51,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
(!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
- pr_debug("ip6t_REJECT: addr is not unicast.\n");
+ pr_debug("addr is not unicast.\n");
return;
}
@@ -57,7 +59,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto);
if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
- pr_debug("ip6t_REJECT: Can't get TCP header.\n");
+ pr_debug("Cannot get TCP header.\n");
return;
}
@@ -65,7 +67,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
/* IP header checks: fragment, too short. */
if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) {
- pr_debug("ip6t_REJECT: proto(%d) != IPPROTO_TCP, "
+ pr_debug("proto(%d) != IPPROTO_TCP, "
"or too short. otcplen = %d\n",
proto, otcplen);
return;
@@ -76,14 +78,14 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
/* No RST for RST. */
if (otcph.rst) {
- pr_debug("ip6t_REJECT: RST is set\n");
+ pr_debug("RST is set\n");
return;
}
/* Check checksum. */
if (csum_ipv6_magic(&oip6h->saddr, &oip6h->daddr, otcplen, IPPROTO_TCP,
skb_checksum(oldskb, tcphoff, otcplen, 0))) {
- pr_debug("ip6t_REJECT: TCP checksum is invalid\n");
+ pr_debug("TCP checksum is invalid\n");
return;
}
@@ -95,9 +97,11 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
fl.fl_ip_dport = otcph.source;
security_skb_classify_flow(oldskb, &fl);
dst = ip6_route_output(net, NULL, &fl);
- if (dst == NULL)
+ if (dst == NULL || dst->error) {
+ dst_release(dst);
return;
- if (dst->error || xfrm_lookup(net, &dst, &fl, NULL, 0))
+ }
+ if (xfrm_lookup(net, &dst, &fl, NULL, 0))
return;
hh_len = (dst->dev->hard_header_len + 15)&~15;
@@ -107,7 +111,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
if (!nskb) {
if (net_ratelimit())
- printk("ip6t_REJECT: Can't alloc skb\n");
+ pr_debug("cannot alloc skb\n");
dst_release(dst);
return;
}
@@ -169,19 +173,16 @@ send_unreach(struct net *net, struct sk_buff *skb_in, unsigned char code,
if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL)
skb_in->dev = net->loopback_dev;
- icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0, NULL);
+ icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);
}
static unsigned int
-reject_tg6(struct sk_buff *skb, const struct xt_target_param *par)
+reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ip6t_reject_info *reject = par->targinfo;
struct net *net = dev_net((par->in != NULL) ? par->in : par->out);
pr_debug("%s: medium point\n", __func__);
- /* WARNING: This code causes reentry within ip6tables.
- This means that the ip6tables jump stack is now crap. We
- must return an absolute verdict. --RR */
switch (reject->with) {
case IP6T_ICMP6_NO_ROUTE:
send_unreach(net, skb, ICMPV6_NOROUTE, par->hooknum);
@@ -206,30 +207,30 @@ reject_tg6(struct sk_buff *skb, const struct xt_target_param *par)
break;
default:
if (net_ratelimit())
- printk(KERN_WARNING "ip6t_REJECT: case %u not handled yet\n", reject->with);
+ pr_info("case %u not handled yet\n", reject->with);
break;
}
return NF_DROP;
}
-static bool reject_tg6_check(const struct xt_tgchk_param *par)
+static int reject_tg6_check(const struct xt_tgchk_param *par)
{
const struct ip6t_reject_info *rejinfo = par->targinfo;
const struct ip6t_entry *e = par->entryinfo;
if (rejinfo->with == IP6T_ICMP6_ECHOREPLY) {
- printk("ip6t_REJECT: ECHOREPLY is not supported.\n");
- return false;
+ pr_info("ECHOREPLY is not supported.\n");
+ return -EINVAL;
} else if (rejinfo->with == IP6T_TCP_RESET) {
/* Must specify that it's a TCP packet */
if (e->ipv6.proto != IPPROTO_TCP ||
(e->ipv6.invflags & XT_INV_PROTO)) {
- printk("ip6t_REJECT: TCP_RESET illegal for non-tcp\n");
- return false;
+ pr_info("TCP_RESET illegal for non-tcp\n");
+ return -EINVAL;
}
}
- return true;
+ return 0;
}
static struct xt_target reject_tg6_reg __read_mostly = {
diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c
index ac0b7c629d78..89cccc5a9c92 100644
--- a/net/ipv6/netfilter/ip6t_ah.c
+++ b/net/ipv6/netfilter/ip6t_ah.c
@@ -6,7 +6,7 @@
* 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 <linux/ip.h>
@@ -29,14 +29,14 @@ spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert)
{
bool r;
- pr_debug("ah spi_match:%c 0x%x <= 0x%x <= 0x%x",
+ pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n",
invert ? '!' : ' ', min, spi, max);
r = (spi >= min && spi <= max) ^ invert;
pr_debug(" result %s\n", r ? "PASS" : "FAILED");
return r;
}
-static bool ah_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
+static bool ah_mt6(const struct sk_buff *skb, struct xt_action_param *par)
{
struct ip_auth_hdr _ah;
const struct ip_auth_hdr *ah;
@@ -48,13 +48,13 @@ static bool ah_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
err = ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH, NULL);
if (err < 0) {
if (err != -ENOENT)
- *par->hotdrop = true;
+ par->hotdrop = true;
return false;
}
ah = skb_header_pointer(skb, ptr, sizeof(_ah), &_ah);
if (ah == NULL) {
- *par->hotdrop = true;
+ par->hotdrop = true;
return false;
}
@@ -87,15 +87,15 @@ static bool ah_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
!(ahinfo->hdrres && ah->reserved);
}
-static bool ah_mt6_check(const struct xt_mtchk_param *par)
+static int ah_mt6_check(const struct xt_mtchk_param *par)
{
const struct ip6t_ah *ahinfo = par->matchinfo;
if (ahinfo->invflags & ~IP6T_AH_INV_MASK) {
- pr_debug("ip6t_ah: unknown flags %X\n", ahinfo->invflags);
- return false;
+ pr_debug("unknown flags %X\n", ahinfo->invflags);
+ return -EINVAL;
}
- return true;
+ return 0;
}
static struct xt_match ah_mt6_reg __read_mostly = {
diff --git a/net/ipv6/netfilter/ip6t_eui64.c b/net/ipv6/netfilter/ip6t_eui64.c
index ca287f6d2bce..aab0706908c5 100644
--- a/net/ipv6/netfilter/ip6t_eui64.c
+++ b/net/ipv6/netfilter/ip6t_eui64.c
@@ -20,14 +20,14 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
static bool
-eui64_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
+eui64_mt6(const struct sk_buff *skb, struct xt_action_param *par)
{
unsigned char eui64[8];
if (!(skb_mac_header(skb) >= skb->head &&
skb_mac_header(skb) + ETH_HLEN <= skb->data) &&
par->fragoff != 0) {
- *par->hotdrop = true;
+ par->hotdrop = true;
return false;
}
diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c
index 7b91c2598ed5..eda898fda6ca 100644
--- a/net/ipv6/netfilter/ip6t_frag.c
+++ b/net/ipv6/netfilter/ip6t_frag.c
@@ -6,7 +6,7 @@
* 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 <linux/ipv6.h>
@@ -27,7 +27,7 @@ static inline bool
id_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert)
{
bool r;
- pr_debug("frag id_match:%c 0x%x <= 0x%x <= 0x%x", invert ? '!' : ' ',
+ pr_debug("id_match:%c 0x%x <= 0x%x <= 0x%x\n", invert ? '!' : ' ',
min, id, max);
r = (id >= min && id <= max) ^ invert;
pr_debug(" result %s\n", r ? "PASS" : "FAILED");
@@ -35,7 +35,7 @@ id_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert)
}
static bool
-frag_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
+frag_mt6(const struct sk_buff *skb, struct xt_action_param *par)
{
struct frag_hdr _frag;
const struct frag_hdr *fh;
@@ -46,13 +46,13 @@ frag_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
err = ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL);
if (err < 0) {
if (err != -ENOENT)
- *par->hotdrop = true;
+ par->hotdrop = true;
return false;
}
fh = skb_header_pointer(skb, ptr, sizeof(_frag), &_frag);
if (fh == NULL) {
- *par->hotdrop = true;
+ par->hotdrop = true;
return false;
}
@@ -102,15 +102,15 @@ frag_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
(ntohs(fh->frag_off) & IP6_MF));
}
-static bool frag_mt6_check(const struct xt_mtchk_param *par)
+static int frag_mt6_check(const struct xt_mtchk_param *par)
{
const struct ip6t_frag *fraginfo = par->matchinfo;
if (fraginfo->invflags & ~IP6T_FRAG_INV_MASK) {
- pr_debug("ip6t_frag: unknown flags %X\n", fraginfo->invflags);
- return false;
+ pr_debug("unknown flags %X\n", fraginfo->invflags);
+ return -EINVAL;
}
- return true;
+ return 0;
}
static struct xt_match frag_mt6_reg __read_mostly = {
diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c
index cbe8dec9744b..59df051eaef6 100644
--- a/net/ipv6/netfilter/ip6t_hbh.c
+++ b/net/ipv6/netfilter/ip6t_hbh.c
@@ -6,7 +6,7 @@
* 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 <linux/ipv6.h>
@@ -41,8 +41,10 @@ MODULE_ALIAS("ip6t_dst");
* 5 -> RTALERT 2 x x
*/
+static struct xt_match hbh_mt6_reg[] __read_mostly;
+
static bool
-hbh_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
+hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par)
{
struct ipv6_opt_hdr _optsh;
const struct ipv6_opt_hdr *oh;
@@ -58,16 +60,18 @@ hbh_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
unsigned int optlen;
int err;
- err = ipv6_find_hdr(skb, &ptr, par->match->data, NULL);
+ err = ipv6_find_hdr(skb, &ptr,
+ (par->match == &hbh_mt6_reg[0]) ?
+ NEXTHDR_HOP : NEXTHDR_DEST, NULL);
if (err < 0) {
if (err != -ENOENT)
- *par->hotdrop = true;
+ par->hotdrop = true;
return false;
}
oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh);
if (oh == NULL) {
- *par->hotdrop = true;
+ par->hotdrop = true;
return false;
}
@@ -141,11 +145,11 @@ hbh_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
}
/* Step to the next */
- pr_debug("len%04X \n", optlen);
+ pr_debug("len%04X\n", optlen);
if ((ptr > skb->len - optlen || hdrlen < optlen) &&
temp < optinfo->optsnr - 1) {
- pr_debug("new pointer is too large! \n");
+ pr_debug("new pointer is too large!\n");
break;
}
ptr += optlen;
@@ -160,32 +164,32 @@ hbh_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
return false;
}
-static bool hbh_mt6_check(const struct xt_mtchk_param *par)
+static int hbh_mt6_check(const struct xt_mtchk_param *par)
{
const struct ip6t_opts *optsinfo = par->matchinfo;
if (optsinfo->invflags & ~IP6T_OPTS_INV_MASK) {
- pr_debug("ip6t_opts: unknown flags %X\n", optsinfo->invflags);
- return false;
+ pr_debug("unknown flags %X\n", optsinfo->invflags);
+ return -EINVAL;
}
if (optsinfo->flags & IP6T_OPTS_NSTRICT) {
- pr_debug("ip6t_opts: Not strict - not implemented");
- return false;
+ pr_debug("Not strict - not implemented");
+ return -EINVAL;
}
- return true;
+ return 0;
}
static struct xt_match hbh_mt6_reg[] __read_mostly = {
{
+ /* Note, hbh_mt6 relies on the order of hbh_mt6_reg */
.name = "hbh",
.family = NFPROTO_IPV6,
.match = hbh_mt6,
.matchsize = sizeof(struct ip6t_opts),
.checkentry = hbh_mt6_check,
.me = THIS_MODULE,
- .data = NEXTHDR_HOP,
},
{
.name = "dst",
@@ -194,7 +198,6 @@ static struct xt_match hbh_mt6_reg[] __read_mostly = {
.matchsize = sizeof(struct ip6t_opts),
.checkentry = hbh_mt6_check,
.me = THIS_MODULE,
- .data = NEXTHDR_DEST,
},
};
diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c
index 91490ad9302c..54bd9790603f 100644
--- a/net/ipv6/netfilter/ip6t_ipv6header.c
+++ b/net/ipv6/netfilter/ip6t_ipv6header.c
@@ -27,7 +27,7 @@ MODULE_DESCRIPTION("Xtables: IPv6 header types match");
MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
static bool
-ipv6header_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
+ipv6header_mt6(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct ip6t_ipv6header_info *info = par->matchinfo;
unsigned int temp;
@@ -118,16 +118,16 @@ ipv6header_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
}
}
-static bool ipv6header_mt6_check(const struct xt_mtchk_param *par)
+static int ipv6header_mt6_check(const struct xt_mtchk_param *par)
{
const struct ip6t_ipv6header_info *info = par->matchinfo;
/* invflags is 0 or 0xff in hard mode */
if ((!info->modeflag) && info->invflags != 0x00 &&
info->invflags != 0xFF)
- return false;
+ return -EINVAL;
- return true;
+ return 0;
}
static struct xt_match ipv6header_mt6_reg __read_mostly = {
diff --git a/net/ipv6/netfilter/ip6t_mh.c b/net/ipv6/netfilter/ip6t_mh.c
index aafe4e66577b..0c90c66b1992 100644
--- a/net/ipv6/netfilter/ip6t_mh.c
+++ b/net/ipv6/netfilter/ip6t_mh.c
@@ -11,6 +11,7 @@
* Based on net/netfilter/xt_tcpudp.c
*
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/types.h>
#include <linux/module.h>
#include <net/ip.h>
@@ -24,12 +25,6 @@
MODULE_DESCRIPTION("Xtables: IPv6 Mobility Header match");
MODULE_LICENSE("GPL");
-#ifdef DEBUG_IP_FIREWALL_USER
-#define duprintf(format, args...) printk(format , ## args)
-#else
-#define duprintf(format, args...)
-#endif
-
/* Returns 1 if the type is matched by the range, 0 otherwise */
static inline bool
type_match(u_int8_t min, u_int8_t max, u_int8_t type, bool invert)
@@ -37,7 +32,7 @@ type_match(u_int8_t min, u_int8_t max, u_int8_t type, bool invert)
return (type >= min && type <= max) ^ invert;
}
-static bool mh_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
+static bool mh_mt6(const struct sk_buff *skb, struct xt_action_param *par)
{
struct ip6_mh _mh;
const struct ip6_mh *mh;
@@ -51,15 +46,15 @@ static bool mh_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
if (mh == NULL) {
/* We've been asked to examine this packet, and we
can't. Hence, no choice but to drop. */
- duprintf("Dropping evil MH tinygram.\n");
- *par->hotdrop = true;
+ pr_debug("Dropping evil MH tinygram.\n");
+ par->hotdrop = true;
return false;
}
if (mh->ip6mh_proto != IPPROTO_NONE) {
- duprintf("Dropping invalid MH Payload Proto: %u\n",
+ pr_debug("Dropping invalid MH Payload Proto: %u\n",
mh->ip6mh_proto);
- *par->hotdrop = true;
+ par->hotdrop = true;
return false;
}
@@ -67,12 +62,12 @@ static bool mh_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
!!(mhinfo->invflags & IP6T_MH_INV_TYPE));
}
-static bool mh_mt6_check(const struct xt_mtchk_param *par)
+static int mh_mt6_check(const struct xt_mtchk_param *par)
{
const struct ip6t_mh *mhinfo = par->matchinfo;
/* Must specify no unknown invflags */
- return !(mhinfo->invflags & ~IP6T_MH_INV_MASK);
+ return (mhinfo->invflags & ~IP6T_MH_INV_MASK) ? -EINVAL : 0;
}
static struct xt_match mh_mt6_reg __read_mostly = {
diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c
index b77307fc8743..d8488c50a8e0 100644
--- a/net/ipv6/netfilter/ip6t_rt.c
+++ b/net/ipv6/netfilter/ip6t_rt.c
@@ -6,7 +6,7 @@
* 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 <linux/ipv6.h>
@@ -29,14 +29,14 @@ static inline bool
segsleft_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert)
{
bool r;
- pr_debug("rt segsleft_match:%c 0x%x <= 0x%x <= 0x%x",
+ pr_debug("segsleft_match:%c 0x%x <= 0x%x <= 0x%x\n",
invert ? '!' : ' ', min, id, max);
r = (id >= min && id <= max) ^ invert;
pr_debug(" result %s\n", r ? "PASS" : "FAILED");
return r;
}
-static bool rt_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
+static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
{
struct ipv6_rt_hdr _route;
const struct ipv6_rt_hdr *rh;
@@ -52,13 +52,13 @@ static bool rt_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
err = ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING, NULL);
if (err < 0) {
if (err != -ENOENT)
- *par->hotdrop = true;
+ par->hotdrop = true;
return false;
}
rh = skb_header_pointer(skb, ptr, sizeof(_route), &_route);
if (rh == NULL) {
- *par->hotdrop = true;
+ par->hotdrop = true;
return false;
}
@@ -183,23 +183,23 @@ static bool rt_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
return false;
}
-static bool rt_mt6_check(const struct xt_mtchk_param *par)
+static int rt_mt6_check(const struct xt_mtchk_param *par)
{
const struct ip6t_rt *rtinfo = par->matchinfo;
if (rtinfo->invflags & ~IP6T_RT_INV_MASK) {
- pr_debug("ip6t_rt: unknown flags %X\n", rtinfo->invflags);
- return false;
+ pr_debug("unknown flags %X\n", rtinfo->invflags);
+ return -EINVAL;
}
if ((rtinfo->flags & (IP6T_RT_RES | IP6T_RT_FST_MASK)) &&
(!(rtinfo->flags & IP6T_RT_TYP) ||
(rtinfo->rt_type != 0) ||
(rtinfo->invflags & IP6T_RT_INV_TYP))) {
pr_debug("`--rt-type 0' required before `--rt-0-*'");
- return false;
+ return -EINVAL;
}
- return true;
+ return 0;
}
static struct xt_match rt_mt6_reg __read_mostly = {
diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index ad378efd0eb8..c9e37c8fd62c 100644
--- a/net/ipv6/netfilter/ip6table_filter.c
+++ b/net/ipv6/netfilter/ip6table_filter.c
@@ -12,6 +12,7 @@
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/slab.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
@@ -21,99 +22,26 @@ MODULE_DESCRIPTION("ip6tables filter table");
(1 << NF_INET_FORWARD) | \
(1 << NF_INET_LOCAL_OUT))
-static struct
-{
- struct ip6t_replace repl;
- struct ip6t_standard entries[3];
- struct ip6t_error term;
-} initial_table __net_initdata = {
- .repl = {
- .name = "filter",
- .valid_hooks = FILTER_VALID_HOOKS,
- .num_entries = 4,
- .size = sizeof(struct ip6t_standard) * 3 + sizeof(struct ip6t_error),
- .hook_entry = {
- [NF_INET_LOCAL_IN] = 0,
- [NF_INET_FORWARD] = sizeof(struct ip6t_standard),
- [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2
- },
- .underflow = {
- [NF_INET_LOCAL_IN] = 0,
- [NF_INET_FORWARD] = sizeof(struct ip6t_standard),
- [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2
- },
- },
- .entries = {
- IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */
- IP6T_STANDARD_INIT(NF_ACCEPT), /* FORWARD */
- IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */
- },
- .term = IP6T_ERROR_INIT, /* ERROR */
-};
-
static const struct xt_table packet_filter = {
.name = "filter",
.valid_hooks = FILTER_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV6,
+ .priority = NF_IP6_PRI_FILTER,
};
/* The work comes in here from netfilter.c. */
static unsigned int
-ip6t_in_hook(unsigned int hook,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- return ip6t_do_table(skb, hook, in, out,
- dev_net(in)->ipv6.ip6table_filter);
-}
-
-static unsigned int
-ip6t_local_out_hook(unsigned int hook,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
+ip6table_filter_hook(unsigned int hook, struct sk_buff *skb,
+ const struct net_device *in, const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
{
-#if 0
- /* root is playing with raw sockets. */
- if (skb->len < sizeof(struct iphdr) ||
- ip_hdrlen(skb) < sizeof(struct iphdr)) {
- if (net_ratelimit())
- printk("ip6t_hook: happy cracking.\n");
- return NF_ACCEPT;
- }
-#endif
+ const struct net *net = dev_net((in != NULL) ? in : out);
- return ip6t_do_table(skb, hook, in, out,
- dev_net(out)->ipv6.ip6table_filter);
+ return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_filter);
}
-static struct nf_hook_ops ip6t_ops[] __read_mostly = {
- {
- .hook = ip6t_in_hook,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_LOCAL_IN,
- .priority = NF_IP6_PRI_FILTER,
- },
- {
- .hook = ip6t_in_hook,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_FORWARD,
- .priority = NF_IP6_PRI_FILTER,
- },
- {
- .hook = ip6t_local_out_hook,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_LOCAL_OUT,
- .priority = NF_IP6_PRI_FILTER,
- },
-};
+static struct nf_hook_ops *filter_ops __read_mostly;
/* Default to forward because I got too much mail already. */
static int forward = NF_ACCEPT;
@@ -121,9 +49,18 @@ module_param(forward, bool, 0000);
static int __net_init ip6table_filter_net_init(struct net *net)
{
- /* Register table */
+ struct ip6t_replace *repl;
+
+ repl = ip6t_alloc_initial_table(&packet_filter);
+ if (repl == NULL)
+ return -ENOMEM;
+ /* Entry 1 is the FORWARD hook */
+ ((struct ip6t_standard *)repl->entries)[1].target.verdict =
+ -forward - 1;
+
net->ipv6.ip6table_filter =
- ip6t_register_table(net, &packet_filter, &initial_table.repl);
+ ip6t_register_table(net, &packet_filter, repl);
+ kfree(repl);
if (IS_ERR(net->ipv6.ip6table_filter))
return PTR_ERR(net->ipv6.ip6table_filter);
return 0;
@@ -131,7 +68,7 @@ static int __net_init ip6table_filter_net_init(struct net *net)
static void __net_exit ip6table_filter_net_exit(struct net *net)
{
- ip6t_unregister_table(net->ipv6.ip6table_filter);
+ ip6t_unregister_table(net, net->ipv6.ip6table_filter);
}
static struct pernet_operations ip6table_filter_net_ops = {
@@ -144,21 +81,20 @@ static int __init ip6table_filter_init(void)
int ret;
if (forward < 0 || forward > NF_MAX_VERDICT) {
- printk("iptables forward must be 0 or 1\n");
+ pr_err("iptables forward must be 0 or 1\n");
return -EINVAL;
}
- /* Entry 1 is the FORWARD hook */
- initial_table.entries[1].target.verdict = -forward - 1;
-
ret = register_pernet_subsys(&ip6table_filter_net_ops);
if (ret < 0)
return ret;
/* Register hooks */
- ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops));
- if (ret < 0)
+ filter_ops = xt_hook_link(&packet_filter, ip6table_filter_hook);
+ if (IS_ERR(filter_ops)) {
+ ret = PTR_ERR(filter_ops);
goto cleanup_table;
+ }
return ret;
@@ -169,7 +105,7 @@ static int __init ip6table_filter_init(void)
static void __exit ip6table_filter_fini(void)
{
- nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops));
+ xt_hook_unlink(&packet_filter, filter_ops);
unregister_pernet_subsys(&ip6table_filter_net_ops);
}
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index a929c19d30e3..679a0a3b7b3c 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -10,6 +10,7 @@
*/
#include <linux/module.h>
#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/slab.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
@@ -21,80 +22,17 @@ MODULE_DESCRIPTION("ip6tables mangle table");
(1 << NF_INET_LOCAL_OUT) | \
(1 << NF_INET_POST_ROUTING))
-static const struct
-{
- struct ip6t_replace repl;
- struct ip6t_standard entries[5];
- struct ip6t_error term;
-} initial_table __net_initdata = {
- .repl = {
- .name = "mangle",
- .valid_hooks = MANGLE_VALID_HOOKS,
- .num_entries = 6,
- .size = sizeof(struct ip6t_standard) * 5 + sizeof(struct ip6t_error),
- .hook_entry = {
- [NF_INET_PRE_ROUTING] = 0,
- [NF_INET_LOCAL_IN] = sizeof(struct ip6t_standard),
- [NF_INET_FORWARD] = sizeof(struct ip6t_standard) * 2,
- [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 3,
- [NF_INET_POST_ROUTING] = sizeof(struct ip6t_standard) * 4,
- },
- .underflow = {
- [NF_INET_PRE_ROUTING] = 0,
- [NF_INET_LOCAL_IN] = sizeof(struct ip6t_standard),
- [NF_INET_FORWARD] = sizeof(struct ip6t_standard) * 2,
- [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 3,
- [NF_INET_POST_ROUTING] = sizeof(struct ip6t_standard) * 4,
- },
- },
- .entries = {
- IP6T_STANDARD_INIT(NF_ACCEPT), /* PRE_ROUTING */
- IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */
- IP6T_STANDARD_INIT(NF_ACCEPT), /* FORWARD */
- IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */
- IP6T_STANDARD_INIT(NF_ACCEPT), /* POST_ROUTING */
- },
- .term = IP6T_ERROR_INIT, /* ERROR */
-};
-
static const struct xt_table packet_mangler = {
.name = "mangle",
.valid_hooks = MANGLE_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV6,
+ .priority = NF_IP6_PRI_MANGLE,
};
-/* The work comes in here from netfilter.c. */
-static unsigned int
-ip6t_in_hook(unsigned int hook,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- return ip6t_do_table(skb, hook, in, out,
- dev_net(in)->ipv6.ip6table_mangle);
-}
-
-static unsigned int
-ip6t_post_routing_hook(unsigned int hook,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- return ip6t_do_table(skb, hook, in, out,
- dev_net(out)->ipv6.ip6table_mangle);
-}
-
static unsigned int
-ip6t_local_out_hook(unsigned int hook,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
+ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out)
{
-
unsigned int ret;
struct in6_addr saddr, daddr;
u_int8_t hop_limit;
@@ -105,7 +43,7 @@ ip6t_local_out_hook(unsigned int hook,
if (skb->len < sizeof(struct iphdr) ||
ip_hdrlen(skb) < sizeof(struct iphdr)) {
if (net_ratelimit())
- printk("ip6t_hook: happy cracking.\n");
+ pr_warning("ip6t_hook: happy cracking.\n");
return NF_ACCEPT;
}
#endif
@@ -119,7 +57,7 @@ ip6t_local_out_hook(unsigned int hook,
/* flowlabel and prio (includes version, which shouldn't change either */
flowlabel = *((u_int32_t *)ipv6_hdr(skb));
- ret = ip6t_do_table(skb, hook, in, out,
+ ret = ip6t_do_table(skb, NF_INET_LOCAL_OUT, NULL, out,
dev_net(out)->ipv6.ip6table_mangle);
if (ret != NF_DROP && ret != NF_STOLEN &&
@@ -132,49 +70,33 @@ ip6t_local_out_hook(unsigned int hook,
return ret;
}
-static struct nf_hook_ops ip6t_ops[] __read_mostly = {
- {
- .hook = ip6t_in_hook,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_PRE_ROUTING,
- .priority = NF_IP6_PRI_MANGLE,
- },
- {
- .hook = ip6t_in_hook,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_LOCAL_IN,
- .priority = NF_IP6_PRI_MANGLE,
- },
- {
- .hook = ip6t_in_hook,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_FORWARD,
- .priority = NF_IP6_PRI_MANGLE,
- },
- {
- .hook = ip6t_local_out_hook,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_LOCAL_OUT,
- .priority = NF_IP6_PRI_MANGLE,
- },
- {
- .hook = ip6t_post_routing_hook,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_POST_ROUTING,
- .priority = NF_IP6_PRI_MANGLE,
- },
-};
+/* The work comes in here from netfilter.c. */
+static unsigned int
+ip6table_mangle_hook(unsigned int hook, struct sk_buff *skb,
+ const struct net_device *in, const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ if (hook == NF_INET_LOCAL_OUT)
+ return ip6t_mangle_out(skb, out);
+ if (hook == NF_INET_POST_ROUTING)
+ return ip6t_do_table(skb, hook, in, out,
+ dev_net(out)->ipv6.ip6table_mangle);
+ /* INPUT/FORWARD */
+ return ip6t_do_table(skb, hook, in, out,
+ dev_net(in)->ipv6.ip6table_mangle);
+}
+static struct nf_hook_ops *mangle_ops __read_mostly;
static int __net_init ip6table_mangle_net_init(struct net *net)
{
- /* Register table */
+ struct ip6t_replace *repl;
+
+ repl = ip6t_alloc_initial_table(&packet_mangler);
+ if (repl == NULL)
+ return -ENOMEM;
net->ipv6.ip6table_mangle =
- ip6t_register_table(net, &packet_mangler, &initial_table.repl);
+ ip6t_register_table(net, &packet_mangler, repl);
+ kfree(repl);
if (IS_ERR(net->ipv6.ip6table_mangle))
return PTR_ERR(net->ipv6.ip6table_mangle);
return 0;
@@ -182,7 +104,7 @@ static int __net_init ip6table_mangle_net_init(struct net *net)
static void __net_exit ip6table_mangle_net_exit(struct net *net)
{
- ip6t_unregister_table(net->ipv6.ip6table_mangle);
+ ip6t_unregister_table(net, net->ipv6.ip6table_mangle);
}
static struct pernet_operations ip6table_mangle_net_ops = {
@@ -199,9 +121,11 @@ static int __init ip6table_mangle_init(void)
return ret;
/* Register hooks */
- ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops));
- if (ret < 0)
+ mangle_ops = xt_hook_link(&packet_mangler, ip6table_mangle_hook);
+ if (IS_ERR(mangle_ops)) {
+ ret = PTR_ERR(mangle_ops);
goto cleanup_table;
+ }
return ret;
@@ -212,7 +136,7 @@ static int __init ip6table_mangle_init(void)
static void __exit ip6table_mangle_fini(void)
{
- nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops));
+ xt_hook_unlink(&packet_mangler, mangle_ops);
unregister_pernet_subsys(&ip6table_mangle_net_ops);
}
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index ed1a1180f3b3..5b9926a011bd 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -5,88 +5,41 @@
*/
#include <linux/module.h>
#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/slab.h>
#define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT))
-static const struct
-{
- struct ip6t_replace repl;
- struct ip6t_standard entries[2];
- struct ip6t_error term;
-} initial_table __net_initdata = {
- .repl = {
- .name = "raw",
- .valid_hooks = RAW_VALID_HOOKS,
- .num_entries = 3,
- .size = sizeof(struct ip6t_standard) * 2 + sizeof(struct ip6t_error),
- .hook_entry = {
- [NF_INET_PRE_ROUTING] = 0,
- [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard)
- },
- .underflow = {
- [NF_INET_PRE_ROUTING] = 0,
- [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard)
- },
- },
- .entries = {
- IP6T_STANDARD_INIT(NF_ACCEPT), /* PRE_ROUTING */
- IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */
- },
- .term = IP6T_ERROR_INIT, /* ERROR */
-};
-
static const struct xt_table packet_raw = {
.name = "raw",
.valid_hooks = RAW_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV6,
+ .priority = NF_IP6_PRI_RAW,
};
/* The work comes in here from netfilter.c. */
static unsigned int
-ip6t_pre_routing_hook(unsigned int hook,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
+ip6table_raw_hook(unsigned int hook, struct sk_buff *skb,
+ const struct net_device *in, const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
{
- return ip6t_do_table(skb, hook, in, out,
- dev_net(in)->ipv6.ip6table_raw);
-}
+ const struct net *net = dev_net((in != NULL) ? in : out);
-static unsigned int
-ip6t_local_out_hook(unsigned int hook,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- return ip6t_do_table(skb, hook, in, out,
- dev_net(out)->ipv6.ip6table_raw);
+ return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_raw);
}
-static struct nf_hook_ops ip6t_ops[] __read_mostly = {
- {
- .hook = ip6t_pre_routing_hook,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_PRE_ROUTING,
- .priority = NF_IP6_PRI_FIRST,
- .owner = THIS_MODULE,
- },
- {
- .hook = ip6t_local_out_hook,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_LOCAL_OUT,
- .priority = NF_IP6_PRI_FIRST,
- .owner = THIS_MODULE,
- },
-};
+static struct nf_hook_ops *rawtable_ops __read_mostly;
static int __net_init ip6table_raw_net_init(struct net *net)
{
- /* Register table */
+ struct ip6t_replace *repl;
+
+ repl = ip6t_alloc_initial_table(&packet_raw);
+ if (repl == NULL)
+ return -ENOMEM;
net->ipv6.ip6table_raw =
- ip6t_register_table(net, &packet_raw, &initial_table.repl);
+ ip6t_register_table(net, &packet_raw, repl);
+ kfree(repl);
if (IS_ERR(net->ipv6.ip6table_raw))
return PTR_ERR(net->ipv6.ip6table_raw);
return 0;
@@ -94,7 +47,7 @@ static int __net_init ip6table_raw_net_init(struct net *net)
static void __net_exit ip6table_raw_net_exit(struct net *net)
{
- ip6t_unregister_table(net->ipv6.ip6table_raw);
+ ip6t_unregister_table(net, net->ipv6.ip6table_raw);
}
static struct pernet_operations ip6table_raw_net_ops = {
@@ -111,9 +64,11 @@ static int __init ip6table_raw_init(void)
return ret;
/* Register hooks */
- ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops));
- if (ret < 0)
+ rawtable_ops = xt_hook_link(&packet_raw, ip6table_raw_hook);
+ if (IS_ERR(rawtable_ops)) {
+ ret = PTR_ERR(rawtable_ops);
goto cleanup_table;
+ }
return ret;
@@ -124,7 +79,7 @@ static int __init ip6table_raw_init(void)
static void __exit ip6table_raw_fini(void)
{
- nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops));
+ xt_hook_unlink(&packet_raw, rawtable_ops);
unregister_pernet_subsys(&ip6table_raw_net_ops);
}
diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c
index 41b444c60934..91aa2b4d83c9 100644
--- a/net/ipv6/netfilter/ip6table_security.c
+++ b/net/ipv6/netfilter/ip6table_security.c
@@ -17,6 +17,7 @@
*/
#include <linux/module.h>
#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/slab.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("James Morris <jmorris <at> redhat.com>");
@@ -26,106 +27,37 @@ MODULE_DESCRIPTION("ip6tables security table, for MAC rules");
(1 << NF_INET_FORWARD) | \
(1 << NF_INET_LOCAL_OUT)
-static const struct
-{
- struct ip6t_replace repl;
- struct ip6t_standard entries[3];
- struct ip6t_error term;
-} initial_table __net_initdata = {
- .repl = {
- .name = "security",
- .valid_hooks = SECURITY_VALID_HOOKS,
- .num_entries = 4,
- .size = sizeof(struct ip6t_standard) * 3 + sizeof(struct ip6t_error),
- .hook_entry = {
- [NF_INET_LOCAL_IN] = 0,
- [NF_INET_FORWARD] = sizeof(struct ip6t_standard),
- [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2,
- },
- .underflow = {
- [NF_INET_LOCAL_IN] = 0,
- [NF_INET_FORWARD] = sizeof(struct ip6t_standard),
- [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2,
- },
- },
- .entries = {
- IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */
- IP6T_STANDARD_INIT(NF_ACCEPT), /* FORWARD */
- IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */
- },
- .term = IP6T_ERROR_INIT, /* ERROR */
-};
-
static const struct xt_table security_table = {
.name = "security",
.valid_hooks = SECURITY_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV6,
+ .priority = NF_IP6_PRI_SECURITY,
};
static unsigned int
-ip6t_local_in_hook(unsigned int hook,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- return ip6t_do_table(skb, hook, in, out,
- dev_net(in)->ipv6.ip6table_security);
-}
-
-static unsigned int
-ip6t_forward_hook(unsigned int hook,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
+ip6table_security_hook(unsigned int hook, struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
{
- return ip6t_do_table(skb, hook, in, out,
- dev_net(in)->ipv6.ip6table_security);
-}
+ const struct net *net = dev_net((in != NULL) ? in : out);
-static unsigned int
-ip6t_local_out_hook(unsigned int hook,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- /* TBD: handle short packets via raw socket */
- return ip6t_do_table(skb, hook, in, out,
- dev_net(out)->ipv6.ip6table_security);
+ return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_security);
}
-static struct nf_hook_ops ip6t_ops[] __read_mostly = {
- {
- .hook = ip6t_local_in_hook,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_LOCAL_IN,
- .priority = NF_IP6_PRI_SECURITY,
- },
- {
- .hook = ip6t_forward_hook,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_FORWARD,
- .priority = NF_IP6_PRI_SECURITY,
- },
- {
- .hook = ip6t_local_out_hook,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_LOCAL_OUT,
- .priority = NF_IP6_PRI_SECURITY,
- },
-};
+static struct nf_hook_ops *sectbl_ops __read_mostly;
static int __net_init ip6table_security_net_init(struct net *net)
{
- net->ipv6.ip6table_security =
- ip6t_register_table(net, &security_table, &initial_table.repl);
+ struct ip6t_replace *repl;
+ repl = ip6t_alloc_initial_table(&security_table);
+ if (repl == NULL)
+ return -ENOMEM;
+ net->ipv6.ip6table_security =
+ ip6t_register_table(net, &security_table, repl);
+ kfree(repl);
if (IS_ERR(net->ipv6.ip6table_security))
return PTR_ERR(net->ipv6.ip6table_security);
@@ -134,7 +66,7 @@ static int __net_init ip6table_security_net_init(struct net *net)
static void __net_exit ip6table_security_net_exit(struct net *net)
{
- ip6t_unregister_table(net->ipv6.ip6table_security);
+ ip6t_unregister_table(net, net->ipv6.ip6table_security);
}
static struct pernet_operations ip6table_security_net_ops = {
@@ -150,9 +82,11 @@ static int __init ip6table_security_init(void)
if (ret < 0)
return ret;
- ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops));
- if (ret < 0)
+ sectbl_ops = xt_hook_link(&security_table, ip6table_security_hook);
+ if (IS_ERR(sectbl_ops)) {
+ ret = PTR_ERR(sectbl_ops);
goto cleanup_table;
+ }
return ret;
@@ -163,7 +97,7 @@ cleanup_table:
static void __exit ip6table_security_fini(void)
{
- nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops));
+ xt_hook_unlink(&security_table, sectbl_ops);
unregister_pernet_subsys(&ip6table_security_net_ops);
}
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 0956ebabbff2..ff43461704be 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -27,6 +27,7 @@
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
#include <net/netfilter/nf_log.h>
@@ -191,15 +192,20 @@ out:
static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
struct sk_buff *skb)
{
+ u16 zone = NF_CT_DEFAULT_ZONE;
+
+ if (skb->nfct)
+ zone = nf_ct_zone((struct nf_conn *)skb->nfct);
+
#ifdef CONFIG_BRIDGE_NETFILTER
if (skb->nf_bridge &&
skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
- return IP6_DEFRAG_CONNTRACK_BRIDGE_IN;
+ return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
#endif
if (hooknum == NF_INET_PRE_ROUTING)
- return IP6_DEFRAG_CONNTRACK_IN;
+ return IP6_DEFRAG_CONNTRACK_IN + zone;
else
- return IP6_DEFRAG_CONNTRACK_OUT;
+ return IP6_DEFRAG_CONNTRACK_OUT + zone;
}
@@ -212,7 +218,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum,
struct sk_buff *reasm;
/* Previously seen (loopback)? */
- if (skb->nfct)
+ if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct))
return NF_ACCEPT;
reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb));
@@ -274,7 +280,7 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum,
/* root is playing with raw sockets. */
if (skb->len < sizeof(struct ipv6hdr)) {
if (net_ratelimit())
- printk("ipv6_conntrack_local: packet too short\n");
+ pr_notice("ipv6_conntrack_local: packet too short\n");
return NF_ACCEPT;
}
return __ipv6_conntrack_in(dev_net(out), hooknum, skb, okfn);
@@ -400,37 +406,37 @@ static int __init nf_conntrack_l3proto_ipv6_init(void)
ret = nf_ct_frag6_init();
if (ret < 0) {
- printk("nf_conntrack_ipv6: can't initialize frag6.\n");
+ pr_err("nf_conntrack_ipv6: can't initialize frag6.\n");
return ret;
}
ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_tcp6);
if (ret < 0) {
- printk("nf_conntrack_ipv6: can't register tcp.\n");
+ pr_err("nf_conntrack_ipv6: can't register tcp.\n");
goto cleanup_frag6;
}
ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udp6);
if (ret < 0) {
- printk("nf_conntrack_ipv6: can't register udp.\n");
+ pr_err("nf_conntrack_ipv6: can't register udp.\n");
goto cleanup_tcp;
}
ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_icmpv6);
if (ret < 0) {
- printk("nf_conntrack_ipv6: can't register icmpv6.\n");
+ pr_err("nf_conntrack_ipv6: can't register icmpv6.\n");
goto cleanup_udp;
}
ret = nf_conntrack_l3proto_register(&nf_conntrack_l3proto_ipv6);
if (ret < 0) {
- printk("nf_conntrack_ipv6: can't register ipv6\n");
+ pr_err("nf_conntrack_ipv6: can't register ipv6\n");
goto cleanup_icmpv6;
}
ret = nf_register_hooks(ipv6_conntrack_ops,
ARRAY_SIZE(ipv6_conntrack_ops));
if (ret < 0) {
- printk("nf_conntrack_ipv6: can't register pre-routing defrag "
+ pr_err("nf_conntrack_ipv6: can't register pre-routing defrag "
"hook.\n");
goto cleanup_ipv6;
}
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index c7b8bd1d7984..9be81776415e 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -23,6 +23,7 @@
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/ipv6/nf_conntrack_icmpv6.h>
#include <net/netfilter/nf_log.h>
@@ -128,7 +129,7 @@ static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb,
}
static int
-icmpv6_error_message(struct net *net,
+icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
struct sk_buff *skb,
unsigned int icmp6off,
enum ip_conntrack_info *ctinfo,
@@ -137,6 +138,7 @@ icmpv6_error_message(struct net *net,
struct nf_conntrack_tuple intuple, origtuple;
const struct nf_conntrack_tuple_hash *h;
const struct nf_conntrack_l4proto *inproto;
+ u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
NF_CT_ASSERT(skb->nfct == NULL);
@@ -163,7 +165,7 @@ icmpv6_error_message(struct net *net,
*ctinfo = IP_CT_RELATED;
- h = nf_conntrack_find_get(net, &intuple);
+ h = nf_conntrack_find_get(net, zone, &intuple);
if (!h) {
pr_debug("icmpv6_error: no match\n");
return -NF_ACCEPT;
@@ -179,7 +181,8 @@ icmpv6_error_message(struct net *net,
}
static int
-icmpv6_error(struct net *net, struct sk_buff *skb, unsigned int dataoff,
+icmpv6_error(struct net *net, struct nf_conn *tmpl,
+ struct sk_buff *skb, unsigned int dataoff,
enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum)
{
const struct icmp6hdr *icmp6h;
@@ -215,7 +218,7 @@ icmpv6_error(struct net *net, struct sk_buff *skb, unsigned int dataoff,
if (icmp6h->icmp6_type >= 128)
return NF_ACCEPT;
- return icmpv6_error_message(net, skb, dataoff, ctinfo, hooknum);
+ return icmpv6_error_message(net, tmpl, skb, dataoff, ctinfo, hooknum);
}
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 312c20adc83f..6fb890187de0 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -27,6 +27,7 @@
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
+#include <linux/slab.h>
#include <net/sock.h>
#include <net/snmp.h>
@@ -45,9 +46,6 @@
#include <linux/kernel.h>
#include <linux/module.h>
-#define NF_CT_FRAG6_HIGH_THRESH 262144 /* == 256*1024 */
-#define NF_CT_FRAG6_LOW_THRESH 196608 /* == 192*1024 */
-#define NF_CT_FRAG6_TIMEOUT IPV6_FRAG_TIMEOUT
struct nf_ct_frag6_skb_cb
{
@@ -63,6 +61,7 @@ struct nf_ct_frag6_queue
struct inet_frag_queue q;
__be32 id; /* fragment id */
+ u32 user;
struct in6_addr saddr;
struct in6_addr daddr;
@@ -471,7 +470,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev)
/* all original skbs are linked into the NFCT_FRAG6_CB(head).orig */
fp = skb_shinfo(head)->frag_list;
- if (NFCT_FRAG6_CB(fp)->orig == NULL)
+ if (fp && NFCT_FRAG6_CB(fp)->orig == NULL)
/* at above code, head skb is divided into two skbs. */
fp = fp->next;
@@ -597,12 +596,6 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
hdr = ipv6_hdr(clone);
fhdr = (struct frag_hdr *)skb_transport_header(clone);
- if (!(fhdr->frag_off & htons(0xFFF9))) {
- pr_debug("Invalid fragment offset\n");
- /* It is not a fragmented frame */
- goto ret_orig;
- }
-
if (atomic_read(&nf_init_frags.mem) > nf_init_frags.high_thresh)
nf_ct_frag6_evictor();
@@ -651,7 +644,7 @@ void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
s2 = s->next;
s->next = NULL;
- NF_HOOK_THRESH(PF_INET6, hooknum, s, in, out, okfn,
+ NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s, in, out, okfn,
NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
s = s2;
}
@@ -669,8 +662,8 @@ int nf_ct_frag6_init(void)
nf_frags.frag_expire = nf_ct_frag6_expire;
nf_frags.secret_interval = 10 * 60 * HZ;
nf_init_frags.timeout = IPV6_FRAG_TIMEOUT;
- nf_init_frags.high_thresh = 256 * 1024;
- nf_init_frags.low_thresh = 192 * 1024;
+ nf_init_frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
+ nf_init_frags.low_thresh = IPV6_FRAG_LOW_THRESH;
inet_frags_init_net(&nf_init_frags);
inet_frags_init(&nf_frags);
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index c9605c3ad91f..566798d69f37 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -59,7 +59,7 @@ static const struct file_operations sockstat6_seq_fops = {
.release = single_release_net,
};
-static struct snmp_mib snmp6_ipstats_list[] = {
+static const struct snmp_mib snmp6_ipstats_list[] = {
/* ipv6 mib according to RFC 2465 */
SNMP_MIB_ITEM("Ip6InReceives", IPSTATS_MIB_INPKTS),
SNMP_MIB_ITEM("Ip6InHdrErrors", IPSTATS_MIB_INHDRERRORS),
@@ -92,11 +92,12 @@ static struct snmp_mib snmp6_ipstats_list[] = {
SNMP_MIB_SENTINEL
};
-static struct snmp_mib snmp6_icmp6_list[] = {
+static const struct snmp_mib snmp6_icmp6_list[] = {
/* icmpv6 mib according to RFC 2466 */
SNMP_MIB_ITEM("Icmp6InMsgs", ICMP6_MIB_INMSGS),
SNMP_MIB_ITEM("Icmp6InErrors", ICMP6_MIB_INERRORS),
SNMP_MIB_ITEM("Icmp6OutMsgs", ICMP6_MIB_OUTMSGS),
+ SNMP_MIB_ITEM("Icmp6OutErrors", ICMP6_MIB_OUTERRORS),
SNMP_MIB_SENTINEL
};
@@ -120,7 +121,7 @@ static const char *const icmp6type2name[256] = {
};
-static struct snmp_mib snmp6_udp6_list[] = {
+static const struct snmp_mib snmp6_udp6_list[] = {
SNMP_MIB_ITEM("Udp6InDatagrams", UDP_MIB_INDATAGRAMS),
SNMP_MIB_ITEM("Udp6NoPorts", UDP_MIB_NOPORTS),
SNMP_MIB_ITEM("Udp6InErrors", UDP_MIB_INERRORS),
@@ -128,7 +129,7 @@ static struct snmp_mib snmp6_udp6_list[] = {
SNMP_MIB_SENTINEL
};
-static struct snmp_mib snmp6_udplite6_list[] = {
+static const struct snmp_mib snmp6_udplite6_list[] = {
SNMP_MIB_ITEM("UdpLite6InDatagrams", UDP_MIB_INDATAGRAMS),
SNMP_MIB_ITEM("UdpLite6NoPorts", UDP_MIB_NOPORTS),
SNMP_MIB_ITEM("UdpLite6InErrors", UDP_MIB_INERRORS),
@@ -136,7 +137,7 @@ static struct snmp_mib snmp6_udplite6_list[] = {
SNMP_MIB_SENTINEL
};
-static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib)
+static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **mib)
{
char name[32];
int i;
@@ -167,11 +168,10 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib)
i & 0x100 ? "Out" : "In", i & 0xff);
seq_printf(seq, "%-32s\t%lu\n", name, val);
}
- return;
}
-static inline void
-snmp6_seq_show_item(struct seq_file *seq, void **mib, struct snmp_mib *itemlist)
+static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **mib,
+ const struct snmp_mib *itemlist)
{
int i;
for (i=0; itemlist[i].name; i++)
@@ -183,14 +183,15 @@ static int snmp6_seq_show(struct seq_file *seq, void *v)
{
struct net *net = (struct net *)seq->private;
- snmp6_seq_show_item(seq, (void **)net->mib.ipv6_statistics,
+ snmp6_seq_show_item(seq, (void __percpu **)net->mib.ipv6_statistics,
snmp6_ipstats_list);
- snmp6_seq_show_item(seq, (void **)net->mib.icmpv6_statistics,
+ snmp6_seq_show_item(seq, (void __percpu **)net->mib.icmpv6_statistics,
snmp6_icmp6_list);
- snmp6_seq_show_icmpv6msg(seq, (void **)net->mib.icmpv6msg_statistics);
- snmp6_seq_show_item(seq, (void **)net->mib.udp_stats_in6,
+ snmp6_seq_show_icmpv6msg(seq,
+ (void __percpu **)net->mib.icmpv6msg_statistics);
+ snmp6_seq_show_item(seq, (void __percpu **)net->mib.udp_stats_in6,
snmp6_udp6_list);
- snmp6_seq_show_item(seq, (void **)net->mib.udplite_stats_in6,
+ snmp6_seq_show_item(seq, (void __percpu **)net->mib.udplite_stats_in6,
snmp6_udplite6_list);
return 0;
}
@@ -213,9 +214,11 @@ static int snmp6_dev_seq_show(struct seq_file *seq, void *v)
struct inet6_dev *idev = (struct inet6_dev *)seq->private;
seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex);
- snmp6_seq_show_item(seq, (void **)idev->stats.ipv6, snmp6_ipstats_list);
- snmp6_seq_show_item(seq, (void **)idev->stats.icmpv6, snmp6_icmp6_list);
- snmp6_seq_show_icmpv6msg(seq, (void **)idev->stats.icmpv6msg);
+ snmp6_seq_show_item(seq, (void __percpu **)idev->stats.ipv6,
+ snmp6_ipstats_list);
+ snmp6_seq_show_item(seq, (void __percpu **)idev->stats.icmpv6,
+ snmp6_icmp6_list);
+ snmp6_seq_show_icmpv6msg(seq, (void __percpu **)idev->stats.icmpv6msg);
return 0;
}
@@ -259,7 +262,7 @@ int snmp6_unregister_dev(struct inet6_dev *idev)
struct net *net = dev_net(idev->dev);
if (!net->mib.proc_net_devsnmp6)
return -ENOENT;
- if (!idev || !idev->stats.proc_dir_entry)
+ if (!idev->stats.proc_dir_entry)
return -EINVAL;
remove_proc_entry(idev->stats.proc_dir_entry->name,
net->mib.proc_net_devsnmp6);
@@ -267,7 +270,7 @@ int snmp6_unregister_dev(struct inet6_dev *idev)
return 0;
}
-static int ipv6_proc_init_net(struct net *net)
+static int __net_init ipv6_proc_init_net(struct net *net)
{
if (!proc_net_fops_create(net, "sockstat6", S_IRUGO,
&sockstat6_seq_fops))
@@ -288,7 +291,7 @@ proc_dev_snmp6_fail:
return -ENOMEM;
}
-static void ipv6_proc_exit_net(struct net *net)
+static void __net_exit ipv6_proc_exit_net(struct net *net)
{
proc_net_remove(net, "sockstat6");
proc_net_remove(net, "dev_snmp6");
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 926ce8eeffaf..4a4dcbe4f8b2 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -21,6 +21,7 @@
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
+#include <linux/slab.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in6.h>
@@ -380,7 +381,7 @@ static inline int rawv6_rcv_skb(struct sock * sk, struct sk_buff * skb)
}
/* Charge it to the socket. */
- if (sock_queue_rcv_skb(sk, skb) < 0) {
+ if (ip_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
return NET_RX_DROP;
}
@@ -460,6 +461,9 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
if (flags & MSG_ERRQUEUE)
return ipv6_recv_error(sk, msg, len);
+ if (np->rxpmtu && np->rxopt.bits.rxpmtu)
+ return ipv6_recv_rxpmtu(sk, msg, len);
+
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
goto out;
@@ -636,8 +640,8 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
goto error_fault;
IP6_UPD_PO_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
- err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
- dst_output);
+ err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
+ rt->u.dst.dev, dst_output);
if (err > 0)
err = net_xmit_errno(err);
if (err)
@@ -732,6 +736,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
int addr_len = msg->msg_namelen;
int hlimit = -1;
int tclass = -1;
+ int dontfrag = -1;
u16 proto;
int err;
@@ -810,7 +815,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
memset(opt, 0, sizeof(struct ipv6_txoptions));
opt->tot_len = sizeof(struct ipv6_txoptions);
- err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass);
+ err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit,
+ &tclass, &dontfrag);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
@@ -879,6 +885,9 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
if (tclass < 0)
tclass = np->tclass;
+ if (dontfrag < 0)
+ dontfrag = np->dontfrag;
+
if (msg->msg_flags&MSG_CONFIRM)
goto do_confirm;
@@ -889,7 +898,7 @@ back_from_confirm:
lock_sock(sk);
err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
len, 0, hlimit, tclass, opt, &fl, (struct rt6_info*)dst,
- msg->msg_flags);
+ msg->msg_flags, dontfrag);
if (err)
ip6_flush_pending_frames(sk);
@@ -1275,7 +1284,7 @@ static const struct file_operations raw6_seq_fops = {
.release = seq_release_net,
};
-static int raw6_init_net(struct net *net)
+static int __net_init raw6_init_net(struct net *net)
{
if (!proc_net_fops_create(net, "raw6", S_IRUGO, &raw6_seq_fops))
return -ENOMEM;
@@ -1283,7 +1292,7 @@ static int raw6_init_net(struct net *net)
return 0;
}
-static void raw6_exit_net(struct net *net)
+static void __net_exit raw6_exit_net(struct net *net)
{
proc_net_remove(net, "raw6");
}
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 2cddea3bd6be..6d4292ff5854 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -41,6 +41,7 @@
#include <linux/random.h>
#include <linux/jhash.h>
#include <linux/skbuff.h>
+#include <linux/slab.h>
#include <net/sock.h>
#include <net/snmp.h>
@@ -228,7 +229,7 @@ static void ip6_frag_expire(unsigned long data)
pointer directly, device might already disappeared.
*/
fq->q.fragments->dev = dev;
- icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0, dev);
+ icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
out_rcu_unlock:
rcu_read_unlock();
out:
@@ -237,8 +238,7 @@ out:
}
static __inline__ struct frag_queue *
-fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst,
- struct inet6_dev *idev)
+fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst)
{
struct inet_frag_queue *q;
struct ip6_create_arg arg;
@@ -254,13 +254,9 @@ fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst,
q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
if (q == NULL)
- goto oom;
+ return NULL;
return container_of(q, struct frag_queue, q);
-
-oom:
- IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_REASMFAILS);
- return NULL;
}
static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
@@ -606,8 +602,8 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
if (atomic_read(&net->ipv6.frags.mem) > net->ipv6.frags.high_thresh)
ip6_evictor(net, ip6_dst_idev(skb_dst(skb)));
- if ((fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
- ip6_dst_idev(skb_dst(skb)))) != NULL) {
+ fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr);
+ if (fq != NULL) {
int ret;
spin_lock(&fq->q.lock);
@@ -672,7 +668,7 @@ static struct ctl_table ip6_frags_ctl_table[] = {
{ }
};
-static int ip6_frags_ns_sysctl_register(struct net *net)
+static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
{
struct ctl_table *table;
struct ctl_table_header *hdr;
@@ -702,7 +698,7 @@ err_alloc:
return -ENOMEM;
}
-static void ip6_frags_ns_sysctl_unregister(struct net *net)
+static void __net_exit ip6_frags_ns_sysctl_unregister(struct net *net)
{
struct ctl_table *table;
@@ -745,10 +741,10 @@ static inline void ip6_frags_sysctl_unregister(void)
}
#endif
-static int ipv6_frags_init_net(struct net *net)
+static int __net_init ipv6_frags_init_net(struct net *net)
{
- net->ipv6.frags.high_thresh = 256 * 1024;
- net->ipv6.frags.low_thresh = 192 * 1024;
+ net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
+ net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
inet_frags_init_net(&net->ipv6.frags);
@@ -756,7 +752,7 @@ static int ipv6_frags_init_net(struct net *net)
return ip6_frags_ns_sysctl_register(net);
}
-static void ipv6_frags_exit_net(struct net *net)
+static void __net_exit ipv6_frags_exit_net(struct net *net)
{
ip6_frags_ns_sysctl_unregister(net);
inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c2bd74c5f8d9..252d76199c41 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -40,6 +40,7 @@
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/nsproxy.h>
+#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/snmp.h>
#include <net/ipv6.h>
@@ -315,7 +316,6 @@ static void rt6_probe(struct rt6_info *rt)
#else
static inline void rt6_probe(struct rt6_info *rt)
{
- return;
}
#endif
@@ -814,20 +814,13 @@ struct dst_entry * ip6_route_output(struct net *net, struct sock *sk,
{
int flags = 0;
- if (rt6_need_strict(&fl->fl6_dst))
+ if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl->fl6_dst))
flags |= RT6_LOOKUP_F_IFACE;
if (!ipv6_addr_any(&fl->fl6_src))
flags |= RT6_LOOKUP_F_HAS_SADDR;
- else if (sk) {
- unsigned int prefs = inet6_sk(sk)->srcprefs;
- if (prefs & IPV6_PREFER_SRC_TMP)
- flags |= RT6_LOOKUP_F_SRCPREF_TMP;
- if (prefs & IPV6_PREFER_SRC_PUBLIC)
- flags |= RT6_LOOKUP_F_SRCPREF_PUBLIC;
- if (prefs & IPV6_PREFER_SRC_COA)
- flags |= RT6_LOOKUP_F_SRCPREF_COA;
- }
+ else if (sk)
+ flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs);
return fib6_rule_lookup(net, fl, flags, ip6_pol_route_output);
}
@@ -886,7 +879,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
rt = (struct rt6_info *) dst;
- if (rt && rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
+ if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
return dst;
return NULL;
@@ -897,19 +890,24 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
struct rt6_info *rt = (struct rt6_info *) dst;
if (rt) {
- if (rt->rt6i_flags & RTF_CACHE)
- ip6_del_rt(rt);
- else
+ if (rt->rt6i_flags & RTF_CACHE) {
+ if (rt6_check_expired(rt)) {
+ ip6_del_rt(rt);
+ dst = NULL;
+ }
+ } else {
dst_release(dst);
+ dst = NULL;
+ }
}
- return NULL;
+ return dst;
}
static void ip6_link_failure(struct sk_buff *skb)
{
struct rt6_info *rt;
- icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0, skb->dev);
+ icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
rt = (struct rt6_info *) skb_dst(skb);
if (rt) {
@@ -1554,7 +1552,6 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *src,
out:
dst_release(&rt->u.dst);
- return;
}
/*
@@ -1873,7 +1870,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
switch (ipstats_mib_noroutes) {
case IPSTATS_MIB_INNOROUTES:
type = ipv6_addr_type(&ipv6_hdr(skb)->daddr);
- if (type == IPV6_ADDR_ANY || type == IPV6_ADDR_RESERVED) {
+ if (type == IPV6_ADDR_ANY) {
IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
IPSTATS_MIB_INADDRERRORS);
break;
@@ -1884,7 +1881,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
ipstats_mib_noroutes);
break;
}
- icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0, skb->dev);
+ icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0);
kfree_skb(skb);
return 0;
}
@@ -2612,7 +2609,7 @@ ctl_table ipv6_route_table_template[] = {
{ }
};
-struct ctl_table *ipv6_route_sysctl_init(struct net *net)
+struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net)
{
struct ctl_table *table;
@@ -2637,7 +2634,7 @@ struct ctl_table *ipv6_route_sysctl_init(struct net *net)
}
#endif
-static int ip6_route_net_init(struct net *net)
+static int __net_init ip6_route_net_init(struct net *net)
{
int ret = -ENOMEM;
@@ -2702,7 +2699,7 @@ out_ip6_dst_ops:
goto out;
}
-static void ip6_route_net_exit(struct net *net)
+static void __net_exit ip6_route_net_exit(struct net *net)
{
#ifdef CONFIG_PROC_FS
proc_net_remove(net, "ipv6_route");
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 976e68244b99..e51e650ea80b 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -28,6 +28,7 @@
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/icmp.h>
+#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/init.h>
#include <linux/netfilter_ipv4.h>
@@ -62,7 +63,6 @@
#define HASH_SIZE 16
#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
-static void ipip6_fb_tunnel_init(struct net_device *dev);
static void ipip6_tunnel_init(struct net_device *dev);
static void ipip6_tunnel_setup(struct net_device *dev);
@@ -364,7 +364,6 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg)
goto out;
}
- INIT_RCU_HEAD(&p->rcu_head);
p->next = t->prl;
p->addr = a->addr;
p->flags = a->flags;
@@ -567,11 +566,9 @@ static int ipip6_rcv(struct sk_buff *skb)
kfree_skb(skb);
return 0;
}
- tunnel->dev->stats.rx_packets++;
- tunnel->dev->stats.rx_bytes += skb->len;
- skb->dev = tunnel->dev;
- skb_dst_drop(skb);
- nf_reset(skb);
+
+ skb_tunnel_rx(skb, tunnel->dev);
+
ipip6_ecn_decapsulate(iph, skb);
netif_rx(skb);
rcu_read_unlock();
@@ -745,7 +742,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
if (skb->len > mtu) {
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
ip_rt_put(rt);
goto tx_error;
}
@@ -1120,7 +1117,7 @@ static void ipip6_tunnel_init(struct net_device *dev)
ipip6_tunnel_bind_dev(dev);
}
-static void ipip6_fb_tunnel_init(struct net_device *dev)
+static void __net_init ipip6_fb_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
@@ -1145,7 +1142,7 @@ static struct xfrm_tunnel sit_handler = {
.priority = 1,
};
-static void sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head)
+static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head)
{
int prio;
@@ -1162,7 +1159,7 @@ static void sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head)
}
}
-static int sit_init_net(struct net *net)
+static int __net_init sit_init_net(struct net *net)
{
struct sit_net *sitn = net_generic(net, sit_net_id);
int err;
@@ -1195,7 +1192,7 @@ err_alloc_dev:
return err;
}
-static void sit_exit_net(struct net *net)
+static void __net_exit sit_exit_net(struct net *net)
{
struct sit_net *sitn = net_generic(net, sit_net_id);
LIST_HEAD(list);
@@ -1228,15 +1225,14 @@ static int __init sit_init(void)
printk(KERN_INFO "IPv6 over IPv4 tunneling driver\n");
- if (xfrm4_tunnel_register(&sit_handler, AF_INET6) < 0) {
- printk(KERN_INFO "sit init: Can't add protocol\n");
- return -EAGAIN;
- }
-
err = register_pernet_device(&sit_net_ops);
if (err < 0)
- xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
-
+ return err;
+ err = xfrm4_tunnel_register(&sit_handler, AF_INET6);
+ if (err < 0) {
+ unregister_pernet_device(&sit_net_ops);
+ printk(KERN_INFO "sit init: Can't add protocol\n");
+ }
return err;
}
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 7208a06576c6..34d1f0690d7e 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -269,7 +269,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
tcp_select_initial_window(tcp_full_space(sk), req->mss,
&req->rcv_wnd, &req->window_clamp,
- ireq->wscale_ok, &rcv_wscale);
+ ireq->wscale_ok, &rcv_wscale,
+ dst_metric(dst, RTAX_INITRWND));
ireq->rcv_wscale = rcv_wscale;
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index c690736885b4..fa1d8f4e0051 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -9,6 +9,7 @@
#include <linux/sysctl.h>
#include <linux/in6.h>
#include <linux/ipv6.h>
+#include <linux/slab.h>
#include <net/ndisc.h>
#include <net/ipv6.h>
#include <net/addrconf.h>
@@ -55,7 +56,7 @@ struct ctl_path net_ipv6_ctl_path[] = {
};
EXPORT_SYMBOL_GPL(net_ipv6_ctl_path);
-static int ipv6_sysctl_net_init(struct net *net)
+static int __net_init ipv6_sysctl_net_init(struct net *net)
{
struct ctl_table *ipv6_table;
struct ctl_table *ipv6_route_table;
@@ -98,7 +99,7 @@ out_ipv6_table:
goto out;
}
-static void ipv6_sysctl_net_exit(struct net *net)
+static void __net_exit ipv6_sysctl_net_exit(struct net *net)
{
struct ctl_table *ipv6_table;
struct ctl_table *ipv6_route_table;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index febfd595a40d..2b7c3a100e2c 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -38,6 +38,7 @@
#include <linux/jhash.h>
#include <linux/ipsec.h>
#include <linux/times.h>
+#include <linux/slab.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
@@ -74,6 +75,9 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
struct request_sock *req);
static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
+static void __tcp_v6_send_check(struct sk_buff *skb,
+ struct in6_addr *saddr,
+ struct in6_addr *daddr);
static const struct inet_connection_sock_af_ops ipv6_mapped;
static const struct inet_connection_sock_af_ops ipv6_specific;
@@ -349,6 +353,11 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (sk->sk_state == TCP_CLOSE)
goto out;
+ if (ipv6_hdr(skb)->hop_limit < inet6_sk(sk)->min_hopcount) {
+ NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
+ goto out;
+ }
+
tp = tcp_sk(sk);
seq = ntohl(th->seq);
if (sk->sk_state != TCP_LISTEN &&
@@ -502,14 +511,10 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
skb = tcp_make_synack(sk, dst, req, rvp);
if (skb) {
- struct tcphdr *th = tcp_hdr(skb);
-
- th->check = tcp_v6_check(skb->len,
- &treq->loc_addr, &treq->rmt_addr,
- csum_partial(th, skb->len, skb->csum));
+ __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
- err = ip6_xmit(sk, skb, &fl, opt, 0);
+ err = ip6_xmit(sk, skb, &fl, opt);
err = net_xmit_eval(err);
}
@@ -520,6 +525,13 @@ done:
return err;
}
+static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req,
+ struct request_values *rvp)
+{
+ TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
+ return tcp_v6_send_synack(sk, req, rvp);
+}
+
static inline void syn_flood_warning(struct sk_buff *skb)
{
#ifdef CONFIG_SYN_COOKIES
@@ -592,7 +604,7 @@ static int tcp_v6_md5_do_add(struct sock *sk, struct in6_addr *peer,
kfree(newkey);
return -ENOMEM;
}
- sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
+ sk_nocaps_add(sk, NETIF_F_GSO_MASK);
}
if (tcp_alloc_md5sig_pool(sk) == NULL) {
kfree(newkey);
@@ -729,7 +741,7 @@ static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval,
return -ENOMEM;
tp->md5sig_info = p;
- sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
+ sk_nocaps_add(sk, NETIF_F_GSO_MASK);
}
newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
@@ -876,7 +888,7 @@ static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb)
if (genhash || memcmp(hash_location, newhash, 16) != 0) {
if (net_ratelimit()) {
- printk(KERN_INFO "MD5 Hash %s for (%pI6, %u)->(%pI6, %u)\n",
+ printk(KERN_INFO "MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n",
genhash ? "failed" : "mismatch",
&ip6h->saddr, ntohs(th->source),
&ip6h->daddr, ntohs(th->dest));
@@ -890,10 +902,11 @@ static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb)
struct request_sock_ops tcp6_request_sock_ops __read_mostly = {
.family = AF_INET6,
.obj_size = sizeof(struct tcp6_request_sock),
- .rtx_syn_ack = tcp_v6_send_synack,
+ .rtx_syn_ack = tcp_v6_rtx_synack,
.send_ack = tcp_v6_reqsk_send_ack,
.destructor = tcp_v6_reqsk_destructor,
- .send_reset = tcp_v6_send_reset
+ .send_reset = tcp_v6_send_reset,
+ .syn_ack_timeout = tcp_syn_ack_timeout,
};
#ifdef CONFIG_TCP_MD5SIG
@@ -909,22 +922,29 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = {
.twsk_destructor= tcp_twsk_destructor,
};
-static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb)
+static void __tcp_v6_send_check(struct sk_buff *skb,
+ struct in6_addr *saddr, struct in6_addr *daddr)
{
- struct ipv6_pinfo *np = inet6_sk(sk);
struct tcphdr *th = tcp_hdr(skb);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
- th->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, 0);
+ th->check = ~tcp_v6_check(skb->len, saddr, daddr, 0);
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct tcphdr, check);
} else {
- th->check = csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP,
- csum_partial(th, th->doff<<2,
- skb->csum));
+ th->check = tcp_v6_check(skb->len, saddr, daddr,
+ csum_partial(th, th->doff << 2,
+ skb->csum));
}
}
+static void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
+{
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ __tcp_v6_send_check(skb, &np->saddr, &np->daddr);
+}
+
static int tcp_v6_gso_send_check(struct sk_buff *skb)
{
struct ipv6hdr *ipv6h;
@@ -937,11 +957,8 @@ static int tcp_v6_gso_send_check(struct sk_buff *skb)
th = tcp_hdr(skb);
th->check = 0;
- th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len,
- IPPROTO_TCP, 0);
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct tcphdr, check);
skb->ip_summed = CHECKSUM_PARTIAL;
+ __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr);
return 0;
}
@@ -1006,7 +1023,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len);
t1 = (struct tcphdr *) skb_push(buff, tot_len);
- skb_reset_transport_header(skb);
+ skb_reset_transport_header(buff);
/* Swap the send and the receive. */
memset(t1, 0, sizeof(*t1));
@@ -1038,15 +1055,14 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
}
#endif
- buff->csum = csum_partial(t1, tot_len, 0);
-
memset(&fl, 0, sizeof(fl));
ipv6_addr_copy(&fl.fl6_dst, &ipv6_hdr(skb)->saddr);
ipv6_addr_copy(&fl.fl6_src, &ipv6_hdr(skb)->daddr);
- t1->check = csum_ipv6_magic(&fl.fl6_src, &fl.fl6_dst,
- tot_len, IPPROTO_TCP,
- buff->csum);
+ buff->ip_summed = CHECKSUM_PARTIAL;
+ buff->csum = 0;
+
+ __tcp_v6_send_check(buff, &fl.fl6_src, &fl.fl6_dst);
fl.proto = IPPROTO_TCP;
fl.oif = inet6_iif(skb);
@@ -1061,7 +1077,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) {
if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) {
skb_dst_set(buff, dst);
- ip6_xmit(ctl_sk, buff, &fl, NULL, 0);
+ ip6_xmit(ctl_sk, buff, &fl, NULL);
TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
if (rst)
TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
@@ -1224,12 +1240,12 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
goto drop_and_free;
/* Secret recipe starts with IP addresses */
- d = &ipv6_hdr(skb)->daddr.s6_addr32[0];
+ d = (__force u32 *)&ipv6_hdr(skb)->daddr.s6_addr32[0];
*mess++ ^= *d++;
*mess++ ^= *d++;
*mess++ ^= *d++;
*mess++ ^= *d++;
- d = &ipv6_hdr(skb)->saddr.s6_addr32[0];
+ d = (__force u32 *)&ipv6_hdr(skb)->saddr.s6_addr32[0];
*mess++ ^= *d++;
*mess++ ^= *d++;
*mess++ ^= *d++;
@@ -1667,6 +1683,7 @@ ipv6_pktoptions:
static int tcp_v6_rcv(struct sk_buff *skb)
{
struct tcphdr *th;
+ struct ipv6hdr *hdr;
struct sock *sk;
int ret;
struct net *net = dev_net(skb->dev);
@@ -1693,12 +1710,13 @@ static int tcp_v6_rcv(struct sk_buff *skb)
goto bad_packet;
th = tcp_hdr(skb);
+ hdr = ipv6_hdr(skb);
TCP_SKB_CB(skb)->seq = ntohl(th->seq);
TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
skb->len - th->doff*4);
TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
TCP_SKB_CB(skb)->when = 0;
- TCP_SKB_CB(skb)->flags = ipv6_get_dsfield(ipv6_hdr(skb));
+ TCP_SKB_CB(skb)->flags = ipv6_get_dsfield(hdr);
TCP_SKB_CB(skb)->sacked = 0;
sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest);
@@ -1709,6 +1727,11 @@ process:
if (sk->sk_state == TCP_TIME_WAIT)
goto do_time_wait;
+ if (hdr->hop_limit < inet6_sk(sk)->min_hopcount) {
+ NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
+ goto discard_and_relse;
+ }
+
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
@@ -1732,8 +1755,11 @@ process:
if (!tcp_prequeue(sk, skb))
ret = tcp_v6_do_rcv(sk, skb);
}
- } else
- sk_add_backlog(sk, skb);
+ } else if (unlikely(sk_add_backlog(sk, skb))) {
+ bh_unlock_sock(sk);
+ NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
+ goto discard_and_relse;
+ }
bh_unlock_sock(sk);
sock_put(sk);
@@ -2105,7 +2131,7 @@ static struct tcp_seq_afinfo tcp6_seq_afinfo = {
},
};
-int tcp6_proc_init(struct net *net)
+int __net_init tcp6_proc_init(struct net *net)
{
return tcp_proc_register(net, &tcp6_seq_afinfo);
}
@@ -2174,18 +2200,18 @@ static struct inet_protosw tcpv6_protosw = {
INET_PROTOSW_ICSK,
};
-static int tcpv6_net_init(struct net *net)
+static int __net_init tcpv6_net_init(struct net *net)
{
return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6,
SOCK_RAW, IPPROTO_TCP, net);
}
-static void tcpv6_net_exit(struct net *net)
+static void __net_exit tcpv6_net_exit(struct net *net)
{
inet_ctl_sock_destroy(net->ipv6.tcp_sk);
}
-static void tcpv6_net_exit_batch(struct list_head *net_exit_list)
+static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list)
{
inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET6);
}
diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c
index 51e2832d13a6..fc3c86a47452 100644
--- a/net/ipv6/tunnel6.c
+++ b/net/ipv6/tunnel6.c
@@ -25,6 +25,7 @@
#include <linux/mutex.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
+#include <linux/slab.h>
#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/xfrm.h>
@@ -98,7 +99,7 @@ static int tunnel6_rcv(struct sk_buff *skb)
if (!handler->handler(skb))
return 0;
- icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, skb->dev);
+ icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
drop:
kfree_skb(skb);
@@ -116,7 +117,7 @@ static int tunnel46_rcv(struct sk_buff *skb)
if (!handler->handler(skb))
return 0;
- icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, skb->dev);
+ icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
drop:
kfree_skb(skb);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 69ebdbe78c47..87be58673b55 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -34,6 +34,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/skbuff.h>
+#include <linux/slab.h>
#include <asm/uaccess.h>
#include <net/ndisc.h>
@@ -90,9 +91,9 @@ static unsigned int udp6_portaddr_hash(struct net *net,
if (ipv6_addr_any(addr6))
hash = jhash_1word(0, mix);
else if (ipv6_addr_v4mapped(addr6))
- hash = jhash_1word(addr6->s6_addr32[3], mix);
+ hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix);
else
- hash = jhash2(addr6->s6_addr32, 4, mix);
+ hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix);
return hash ^ port;
}
@@ -258,8 +259,8 @@ static struct sock *__udp6_lib_lookup(struct net *net,
if (hslot->count < hslot2->count)
goto begin;
- result = udp6_lib_lookup2(net, &in6addr_any, sport,
- daddr, hnum, dif,
+ result = udp6_lib_lookup2(net, saddr, sport,
+ &in6addr_any, hnum, dif,
hslot2, slot2);
}
rcu_read_unlock();
@@ -322,11 +323,12 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_sock *inet = inet_sk(sk);
struct sk_buff *skb;
- unsigned int ulen, copied;
+ unsigned int ulen;
int peeked;
int err;
int is_udplite = IS_UDPLITE(sk);
int is_udp4;
+ bool slow;
if (addr_len)
*addr_len=sizeof(struct sockaddr_in6);
@@ -334,6 +336,9 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
if (flags & MSG_ERRQUEUE)
return ipv6_recv_error(sk, msg, len);
+ if (np->rxpmtu && np->rxopt.bits.rxpmtu)
+ return ipv6_recv_rxpmtu(sk, msg, len);
+
try_again:
skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
&peeked, &err);
@@ -341,10 +346,9 @@ try_again:
goto out;
ulen = skb->len - sizeof(struct udphdr);
- copied = len;
- if (copied > ulen)
- copied = ulen;
- else if (copied < ulen)
+ if (len > ulen)
+ len = ulen;
+ else if (len < ulen)
msg->msg_flags |= MSG_TRUNC;
is_udp4 = (skb->protocol == htons(ETH_P_IP));
@@ -355,14 +359,14 @@ try_again:
* coverage checksum (UDP-Lite), do it before the copy.
*/
- if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
+ if (len < ulen || UDP_SKB_CB(skb)->partial_cov) {
if (udp_lib_checksum_complete(skb))
goto csum_copy_err;
}
if (skb_csum_unnecessary(skb))
err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
- msg->msg_iov, copied );
+ msg->msg_iov,len);
else {
err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov);
if (err == -EINVAL)
@@ -411,7 +415,7 @@ try_again:
datagram_recv_ctl(sk, msg, skb);
}
- err = copied;
+ err = len;
if (flags & MSG_TRUNC)
err = ulen;
@@ -421,7 +425,7 @@ out:
return err;
csum_copy_err:
- lock_sock(sk);
+ slow = lock_sock_fast(sk);
if (!skb_kill_datagram(sk, skb, flags)) {
if (is_udp4)
UDP_INC_STATS_USER(sock_net(sk),
@@ -430,7 +434,7 @@ csum_copy_err:
UDP6_INC_STATS_USER(sock_net(sk),
UDP_MIB_INERRORS, is_udplite);
}
- release_sock(sk);
+ unlock_sock_fast(sk, slow);
if (flags & MSG_DONTWAIT)
return -EAGAIN;
@@ -511,7 +515,7 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
goto drop;
}
- if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) {
+ if ((rc = ip_queue_rcv_skb(sk, skb)) < 0) {
/* Note that an ENOMEM error is charged twice */
if (rc == -ENOMEM)
UDP6_INC_STATS_BH(sock_net(sk),
@@ -581,19 +585,27 @@ static void flush_stack(struct sock **stack, unsigned int count,
sk = stack[i];
if (skb1) {
+ if (sk_rcvqueues_full(sk, skb)) {
+ kfree_skb(skb1);
+ goto drop;
+ }
bh_lock_sock(sk);
if (!sock_owned_by_user(sk))
udpv6_queue_rcv_skb(sk, skb1);
- else
- sk_add_backlog(sk, skb1);
+ else if (sk_add_backlog(sk, skb1)) {
+ kfree_skb(skb1);
+ bh_unlock_sock(sk);
+ goto drop;
+ }
bh_unlock_sock(sk);
- } else {
- atomic_inc(&sk->sk_drops);
- UDP6_INC_STATS_BH(sock_net(sk),
- UDP_MIB_RCVBUFERRORS, IS_UDPLITE(sk));
- UDP6_INC_STATS_BH(sock_net(sk),
- UDP_MIB_INERRORS, IS_UDPLITE(sk));
+ continue;
}
+drop:
+ atomic_inc(&sk->sk_drops);
+ UDP6_INC_STATS_BH(sock_net(sk),
+ UDP_MIB_RCVBUFERRORS, IS_UDPLITE(sk));
+ UDP6_INC_STATS_BH(sock_net(sk),
+ UDP_MIB_INERRORS, IS_UDPLITE(sk));
}
}
/*
@@ -681,15 +693,14 @@ static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh,
int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
int proto)
{
+ struct net *net = dev_net(skb->dev);
struct sock *sk;
struct udphdr *uh;
- struct net_device *dev = skb->dev;
struct in6_addr *saddr, *daddr;
u32 ulen = 0;
- struct net *net = dev_net(skb->dev);
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
- goto short_packet;
+ goto discard;
saddr = &ipv6_hdr(skb)->saddr;
daddr = &ipv6_hdr(skb)->daddr;
@@ -745,7 +756,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
UDP6_INC_STATS_BH(net, UDP_MIB_NOPORTS,
proto == IPPROTO_UDPLITE);
- icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev);
+ icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
kfree_skb(skb);
return 0;
@@ -753,19 +764,32 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
/* deliver */
+ if (sk_rcvqueues_full(sk, skb)) {
+ sock_put(sk);
+ goto discard;
+ }
bh_lock_sock(sk);
if (!sock_owned_by_user(sk))
udpv6_queue_rcv_skb(sk, skb);
- else
- sk_add_backlog(sk, skb);
+ else if (sk_add_backlog(sk, skb)) {
+ atomic_inc(&sk->sk_drops);
+ bh_unlock_sock(sk);
+ sock_put(sk);
+ goto discard;
+ }
bh_unlock_sock(sk);
sock_put(sk);
return 0;
short_packet:
- LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: %d/%u\n",
+ LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n",
proto == IPPROTO_UDPLITE ? "-Lite" : "",
- ulen, skb->len);
+ saddr,
+ ntohs(uh->source),
+ ulen,
+ skb->len,
+ daddr,
+ ntohs(uh->dest));
discard:
UDP6_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
@@ -912,6 +936,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
int ulen = len;
int hlimit = -1;
int tclass = -1;
+ int dontfrag = -1;
int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
int err;
int connected = 0;
@@ -1042,7 +1067,8 @@ do_udp_sendmsg:
memset(opt, 0, sizeof(struct ipv6_txoptions));
opt->tot_len = sizeof(*opt);
- err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass);
+ err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit,
+ &tclass, &dontfrag);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
@@ -1113,6 +1139,9 @@ do_udp_sendmsg:
if (tclass < 0)
tclass = np->tclass;
+ if (dontfrag < 0)
+ dontfrag = np->dontfrag;
+
if (msg->msg_flags&MSG_CONFIRM)
goto do_confirm;
back_from_confirm:
@@ -1136,7 +1165,7 @@ do_append_data:
err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen,
sizeof(struct udphdr), hlimit, tclass, opt, &fl,
(struct rt6_info*)dst,
- corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
+ corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag);
if (err)
udp_v6_flush_pending_frames(sk);
else if (!corkreq)
@@ -1396,7 +1425,7 @@ static struct udp_seq_afinfo udp6_seq_afinfo = {
},
};
-int udp6_proc_init(struct net *net)
+int __net_init udp6_proc_init(struct net *net)
{
return udp_proc_register(net, &udp6_seq_afinfo);
}
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 6ea6938919e6..5f48fadc27f7 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -104,12 +104,12 @@ static struct udp_seq_afinfo udplite6_seq_afinfo = {
},
};
-static int udplite6_proc_init_net(struct net *net)
+static int __net_init udplite6_proc_init_net(struct net *net)
{
return udp_proc_register(net, &udplite6_seq_afinfo);
}
-static void udplite6_proc_exit_net(struct net *net)
+static void __net_exit udplite6_proc_exit_net(struct net *net)
{
udp_proc_unregister(net, &udplite6_seq_afinfo);
}
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 9084582d236b..f8c3cf842f53 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -42,7 +42,7 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
ipv6_hdr(skb)->payload_len = htons(skb->len);
__skb_push(skb, skb->data - skb_network_header(skb));
- NF_HOOK(PF_INET6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
+ NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
ip6_rcv_finish);
return -1;
}
@@ -101,7 +101,7 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
break;
}
- x = xfrm_state_lookup_byaddr(net, dst, src, proto, AF_INET6);
+ x = xfrm_state_lookup_byaddr(net, skb->mark, dst, src, proto, AF_INET6);
if (!x)
continue;
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 3927832227b9..b809812c8d30 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -5,6 +5,7 @@
* Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au>
*/
+#include <linux/gfp.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index c4f4eef032a3..6434bd5ce088 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -38,7 +38,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
if (!skb->local_df && skb->len > mtu) {
skb->dev = dst->dev;
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev);
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
ret = -EMSGSIZE;
}
@@ -90,6 +90,6 @@ static int xfrm6_output_finish(struct sk_buff *skb)
int xfrm6_output(struct sk_buff *skb)
{
- return NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, skb, NULL, skb_dst(skb)->dev,
- xfrm6_output_finish);
+ return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL,
+ skb_dst(skb)->dev, xfrm6_output_finish);
}
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index dbdc696f5fc5..6baeabbbca82 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -67,36 +67,6 @@ static int xfrm6_get_saddr(struct net *net,
return 0;
}
-static struct dst_entry *
-__xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
-{
- struct dst_entry *dst;
-
- /* Still not clear if we should set fl->fl6_{src,dst}... */
- read_lock_bh(&policy->lock);
- for (dst = policy->bundles; dst; dst = dst->next) {
- struct xfrm_dst *xdst = (struct xfrm_dst*)dst;
- struct in6_addr fl_dst_prefix, fl_src_prefix;
-
- ipv6_addr_prefix(&fl_dst_prefix,
- &fl->fl6_dst,
- xdst->u.rt6.rt6i_dst.plen);
- ipv6_addr_prefix(&fl_src_prefix,
- &fl->fl6_src,
- xdst->u.rt6.rt6i_src.plen);
- if (ipv6_addr_equal(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) &&
- ipv6_addr_equal(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) &&
- xfrm_bundle_ok(policy, xdst, fl, AF_INET6,
- (xdst->u.rt6.rt6i_dst.plen != 128 ||
- xdst->u.rt6.rt6i_src.plen != 128))) {
- dst_clone(dst);
- break;
- }
- }
- read_unlock_bh(&policy->lock);
- return dst;
-}
-
static int xfrm6_get_tos(struct flowi *fl)
{
return 0;
@@ -116,14 +86,15 @@ static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
return 0;
}
-static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev)
+static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
+ struct flowi *fl)
{
struct rt6_info *rt = (struct rt6_info*)xdst->route;
xdst->u.dst.dev = dev;
dev_hold(dev);
- xdst->u.rt6.rt6i_idev = in6_dev_get(rt->u.dst.dev);
+ xdst->u.rt6.rt6i_idev = in6_dev_get(dev);
if (!xdst->u.rt6.rt6i_idev)
return -ENODEV;
@@ -153,6 +124,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
u8 nexthdr = nh[IP6CB(skb)->nhoff];
memset(fl, 0, sizeof(struct flowi));
+ fl->mark = skb->mark;
+
ipv6_addr_copy(&fl->fl6_dst, reverse ? &hdr->saddr : &hdr->daddr);
ipv6_addr_copy(&fl->fl6_src, reverse ? &hdr->daddr : &hdr->saddr);
@@ -290,7 +263,6 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
.dst_ops = &xfrm6_dst_ops,
.dst_lookup = xfrm6_dst_lookup,
.get_saddr = xfrm6_get_saddr,
- .find_bundle = __xfrm6_find_bundle,
.decode_session = _decode_session6,
.get_tos = xfrm6_get_tos,
.init_path = xfrm6_init_path,
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 438831d33593..2ce3a8278f26 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -23,6 +23,7 @@
*/
#include <linux/module.h>
#include <linux/xfrm.h>
+#include <linux/slab.h>
#include <linux/rculist.h>
#include <net/ip.h>
#include <net/xfrm.h>
@@ -30,6 +31,25 @@
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/mutex.h>
+#include <net/netns/generic.h>
+
+#define XFRM6_TUNNEL_SPI_BYADDR_HSIZE 256
+#define XFRM6_TUNNEL_SPI_BYSPI_HSIZE 256
+
+#define XFRM6_TUNNEL_SPI_MIN 1
+#define XFRM6_TUNNEL_SPI_MAX 0xffffffff
+
+struct xfrm6_tunnel_net {
+ struct hlist_head spi_byaddr[XFRM6_TUNNEL_SPI_BYADDR_HSIZE];
+ struct hlist_head spi_byspi[XFRM6_TUNNEL_SPI_BYSPI_HSIZE];
+ u32 spi;
+};
+
+static 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);
+}
/*
* xfrm_tunnel_spi things are for allocating unique id ("spi")
@@ -46,19 +66,8 @@ struct xfrm6_tunnel_spi {
static DEFINE_SPINLOCK(xfrm6_tunnel_spi_lock);
-static u32 xfrm6_tunnel_spi;
-
-#define XFRM6_TUNNEL_SPI_MIN 1
-#define XFRM6_TUNNEL_SPI_MAX 0xffffffff
-
static struct kmem_cache *xfrm6_tunnel_spi_kmem __read_mostly;
-#define XFRM6_TUNNEL_SPI_BYADDR_HSIZE 256
-#define XFRM6_TUNNEL_SPI_BYSPI_HSIZE 256
-
-static struct hlist_head xfrm6_tunnel_spi_byaddr[XFRM6_TUNNEL_SPI_BYADDR_HSIZE];
-static struct hlist_head xfrm6_tunnel_spi_byspi[XFRM6_TUNNEL_SPI_BYSPI_HSIZE];
-
static inline unsigned xfrm6_tunnel_spi_hash_byaddr(xfrm_address_t *addr)
{
unsigned h;
@@ -76,50 +85,14 @@ static inline unsigned xfrm6_tunnel_spi_hash_byspi(u32 spi)
return spi % XFRM6_TUNNEL_SPI_BYSPI_HSIZE;
}
-
-static int xfrm6_tunnel_spi_init(void)
-{
- int i;
-
- xfrm6_tunnel_spi = 0;
- xfrm6_tunnel_spi_kmem = kmem_cache_create("xfrm6_tunnel_spi",
- sizeof(struct xfrm6_tunnel_spi),
- 0, SLAB_HWCACHE_ALIGN,
- NULL);
- if (!xfrm6_tunnel_spi_kmem)
- return -ENOMEM;
-
- for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
- INIT_HLIST_HEAD(&xfrm6_tunnel_spi_byaddr[i]);
- for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++)
- INIT_HLIST_HEAD(&xfrm6_tunnel_spi_byspi[i]);
- return 0;
-}
-
-static void xfrm6_tunnel_spi_fini(void)
-{
- int i;
-
- for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) {
- if (!hlist_empty(&xfrm6_tunnel_spi_byaddr[i]))
- return;
- }
- for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++) {
- if (!hlist_empty(&xfrm6_tunnel_spi_byspi[i]))
- return;
- }
- rcu_barrier();
- kmem_cache_destroy(xfrm6_tunnel_spi_kmem);
- xfrm6_tunnel_spi_kmem = NULL;
-}
-
-static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr)
+static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(struct net *net, xfrm_address_t *saddr)
{
+ struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net);
struct xfrm6_tunnel_spi *x6spi;
struct hlist_node *pos;
hlist_for_each_entry_rcu(x6spi, pos,
- &xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)],
+ &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)],
list_byaddr) {
if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0)
return x6spi;
@@ -128,13 +101,13 @@ static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr)
return NULL;
}
-__be32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr)
+__be32 xfrm6_tunnel_spi_lookup(struct net *net, xfrm_address_t *saddr)
{
struct xfrm6_tunnel_spi *x6spi;
u32 spi;
rcu_read_lock_bh();
- x6spi = __xfrm6_tunnel_spi_lookup(saddr);
+ x6spi = __xfrm6_tunnel_spi_lookup(net, saddr);
spi = x6spi ? x6spi->spi : 0;
rcu_read_unlock_bh();
return htonl(spi);
@@ -142,14 +115,15 @@ __be32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr)
EXPORT_SYMBOL(xfrm6_tunnel_spi_lookup);
-static int __xfrm6_tunnel_spi_check(u32 spi)
+static int __xfrm6_tunnel_spi_check(struct net *net, u32 spi)
{
+ struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net);
struct xfrm6_tunnel_spi *x6spi;
int index = xfrm6_tunnel_spi_hash_byspi(spi);
struct hlist_node *pos;
hlist_for_each_entry(x6spi, pos,
- &xfrm6_tunnel_spi_byspi[index],
+ &xfrm6_tn->spi_byspi[index],
list_byspi) {
if (x6spi->spi == spi)
return -1;
@@ -157,61 +131,61 @@ static int __xfrm6_tunnel_spi_check(u32 spi)
return index;
}
-static u32 __xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr)
+static u32 __xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr)
{
+ struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net);
u32 spi;
struct xfrm6_tunnel_spi *x6spi;
int index;
- if (xfrm6_tunnel_spi < XFRM6_TUNNEL_SPI_MIN ||
- xfrm6_tunnel_spi >= XFRM6_TUNNEL_SPI_MAX)
- xfrm6_tunnel_spi = XFRM6_TUNNEL_SPI_MIN;
+ if (xfrm6_tn->spi < XFRM6_TUNNEL_SPI_MIN ||
+ xfrm6_tn->spi >= XFRM6_TUNNEL_SPI_MAX)
+ xfrm6_tn->spi = XFRM6_TUNNEL_SPI_MIN;
else
- xfrm6_tunnel_spi++;
+ xfrm6_tn->spi++;
- for (spi = xfrm6_tunnel_spi; spi <= XFRM6_TUNNEL_SPI_MAX; spi++) {
- index = __xfrm6_tunnel_spi_check(spi);
+ for (spi = xfrm6_tn->spi; spi <= XFRM6_TUNNEL_SPI_MAX; spi++) {
+ index = __xfrm6_tunnel_spi_check(net, spi);
if (index >= 0)
goto alloc_spi;
}
- for (spi = XFRM6_TUNNEL_SPI_MIN; spi < xfrm6_tunnel_spi; spi++) {
- index = __xfrm6_tunnel_spi_check(spi);
+ for (spi = XFRM6_TUNNEL_SPI_MIN; spi < xfrm6_tn->spi; spi++) {
+ index = __xfrm6_tunnel_spi_check(net, spi);
if (index >= 0)
goto alloc_spi;
}
spi = 0;
goto out;
alloc_spi:
- xfrm6_tunnel_spi = spi;
+ xfrm6_tn->spi = spi;
x6spi = kmem_cache_alloc(xfrm6_tunnel_spi_kmem, GFP_ATOMIC);
if (!x6spi)
goto out;
- INIT_RCU_HEAD(&x6spi->rcu_head);
memcpy(&x6spi->addr, saddr, sizeof(x6spi->addr));
x6spi->spi = spi;
atomic_set(&x6spi->refcnt, 1);
- hlist_add_head_rcu(&x6spi->list_byspi, &xfrm6_tunnel_spi_byspi[index]);
+ hlist_add_head_rcu(&x6spi->list_byspi, &xfrm6_tn->spi_byspi[index]);
index = xfrm6_tunnel_spi_hash_byaddr(saddr);
- hlist_add_head_rcu(&x6spi->list_byaddr, &xfrm6_tunnel_spi_byaddr[index]);
+ hlist_add_head_rcu(&x6spi->list_byaddr, &xfrm6_tn->spi_byaddr[index]);
out:
return spi;
}
-__be32 xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr)
+__be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr)
{
struct xfrm6_tunnel_spi *x6spi;
u32 spi;
spin_lock_bh(&xfrm6_tunnel_spi_lock);
- x6spi = __xfrm6_tunnel_spi_lookup(saddr);
+ x6spi = __xfrm6_tunnel_spi_lookup(net, saddr);
if (x6spi) {
atomic_inc(&x6spi->refcnt);
spi = x6spi->spi;
} else
- spi = __xfrm6_tunnel_alloc_spi(saddr);
+ spi = __xfrm6_tunnel_alloc_spi(net, saddr);
spin_unlock_bh(&xfrm6_tunnel_spi_lock);
return htonl(spi);
@@ -225,15 +199,16 @@ static void x6spi_destroy_rcu(struct rcu_head *head)
container_of(head, struct xfrm6_tunnel_spi, rcu_head));
}
-void xfrm6_tunnel_free_spi(xfrm_address_t *saddr)
+void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr)
{
+ struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net);
struct xfrm6_tunnel_spi *x6spi;
struct hlist_node *pos, *n;
spin_lock_bh(&xfrm6_tunnel_spi_lock);
hlist_for_each_entry_safe(x6spi, pos, n,
- &xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)],
+ &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)],
list_byaddr)
{
if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) {
@@ -263,10 +238,11 @@ static int xfrm6_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
static int xfrm6_tunnel_rcv(struct sk_buff *skb)
{
+ struct net *net = dev_net(skb->dev);
struct ipv6hdr *iph = ipv6_hdr(skb);
__be32 spi;
- spi = xfrm6_tunnel_spi_lookup((xfrm_address_t *)&iph->saddr);
+ spi = xfrm6_tunnel_spi_lookup(net, (xfrm_address_t *)&iph->saddr);
return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi) > 0 ? : 0;
}
@@ -326,7 +302,9 @@ static int xfrm6_tunnel_init_state(struct xfrm_state *x)
static void xfrm6_tunnel_destroy(struct xfrm_state *x)
{
- xfrm6_tunnel_free_spi((xfrm_address_t *)&x->props.saddr);
+ struct net *net = xs_net(x);
+
+ xfrm6_tunnel_free_spi(net, (xfrm_address_t *)&x->props.saddr);
}
static const struct xfrm_type xfrm6_tunnel_type = {
@@ -351,34 +329,73 @@ static struct xfrm6_tunnel xfrm46_tunnel_handler = {
.priority = 2,
};
+static int __net_init xfrm6_tunnel_net_init(struct net *net)
+{
+ struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net);
+ unsigned int i;
+
+ for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
+ INIT_HLIST_HEAD(&xfrm6_tn->spi_byaddr[i]);
+ for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++)
+ INIT_HLIST_HEAD(&xfrm6_tn->spi_byspi[i]);
+ xfrm6_tn->spi = 0;
+
+ return 0;
+}
+
+static void __net_exit xfrm6_tunnel_net_exit(struct net *net)
+{
+}
+
+static struct pernet_operations xfrm6_tunnel_net_ops = {
+ .init = xfrm6_tunnel_net_init,
+ .exit = xfrm6_tunnel_net_exit,
+ .id = &xfrm6_tunnel_net_id,
+ .size = sizeof(struct xfrm6_tunnel_net),
+};
+
static int __init xfrm6_tunnel_init(void)
{
- if (xfrm_register_type(&xfrm6_tunnel_type, AF_INET6) < 0)
- goto err;
- if (xfrm6_tunnel_register(&xfrm6_tunnel_handler, AF_INET6))
- goto unreg;
- if (xfrm6_tunnel_register(&xfrm46_tunnel_handler, AF_INET))
- goto dereg6;
- if (xfrm6_tunnel_spi_init() < 0)
- goto dereg46;
+ int rv;
+
+ xfrm6_tunnel_spi_kmem = kmem_cache_create("xfrm6_tunnel_spi",
+ sizeof(struct xfrm6_tunnel_spi),
+ 0, SLAB_HWCACHE_ALIGN,
+ NULL);
+ if (!xfrm6_tunnel_spi_kmem)
+ return -ENOMEM;
+ rv = register_pernet_subsys(&xfrm6_tunnel_net_ops);
+ if (rv < 0)
+ goto out_pernet;
+ rv = xfrm_register_type(&xfrm6_tunnel_type, AF_INET6);
+ if (rv < 0)
+ goto out_type;
+ rv = xfrm6_tunnel_register(&xfrm6_tunnel_handler, AF_INET6);
+ if (rv < 0)
+ goto out_xfrm6;
+ rv = xfrm6_tunnel_register(&xfrm46_tunnel_handler, AF_INET);
+ if (rv < 0)
+ goto out_xfrm46;
return 0;
-dereg46:
- xfrm6_tunnel_deregister(&xfrm46_tunnel_handler, AF_INET);
-dereg6:
+out_xfrm46:
xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6);
-unreg:
+out_xfrm6:
xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6);
-err:
- return -EAGAIN;
+out_type:
+ unregister_pernet_subsys(&xfrm6_tunnel_net_ops);
+out_pernet:
+ kmem_cache_destroy(xfrm6_tunnel_spi_kmem);
+ return rv;
}
static void __exit xfrm6_tunnel_fini(void)
{
- xfrm6_tunnel_spi_fini();
xfrm6_tunnel_deregister(&xfrm46_tunnel_handler, AF_INET);
xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6);
xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6);
+ unregister_pernet_subsys(&xfrm6_tunnel_net_ops);
+ kmem_cache_destroy(xfrm6_tunnel_spi_kmem);
}
module_init(xfrm6_tunnel_init);