summaryrefslogtreecommitdiffstats
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c805
-rw-r--r--net/ipv6/af_inet6.c3
-rw-r--r--net/ipv6/datagram.c108
-rw-r--r--net/ipv6/fib6_rules.c3
-rw-r--r--net/ipv6/icmp.c7
-rw-r--r--net/ipv6/inet6_connection_sock.c4
-rw-r--r--net/ipv6/ip6_fib.c16
-rw-r--r--net/ipv6/ip6_flowlabel.c3
-rw-r--r--net/ipv6/ip6_output.c34
-rw-r--r--net/ipv6/ipv6_sockglue.c86
-rw-r--r--net/ipv6/mcast.c139
-rw-r--r--net/ipv6/netfilter/ip6t_hbh.c4
-rw-r--r--net/ipv6/proc.c1
-rw-r--r--net/ipv6/raw.c12
-rw-r--r--net/ipv6/tcp_ipv6.c64
-rw-r--r--net/ipv6/udp.c16
-rw-r--r--net/ipv6/xfrm6_policy.c31
17 files changed, 731 insertions, 605 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 413054f02aa..34d2d649e39 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -82,7 +82,7 @@
#include <linux/random.h>
#endif
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#include <asm/unaligned.h>
#include <linux/proc_fs.h>
@@ -98,7 +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);
@@ -127,8 +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);
@@ -138,8 +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);
@@ -152,8 +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);
@@ -250,8 +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,
@@ -271,7 +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);
@@ -318,7 +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
@@ -326,7 +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);
@@ -351,6 +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;
@@ -402,6 +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 ||
@@ -439,8 +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;
}
@@ -466,7 +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)
@@ -523,12 +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");
@@ -537,54 +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);
+ 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 */
@@ -595,7 +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);
@@ -616,7 +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)) {
@@ -643,6 +649,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
spin_lock_init(&ifa->lock);
init_timer(&ifa->timer);
+ INIT_HLIST_NODE(&ifa->addr_lst);
ifa->timer.data = (unsigned long) ifa;
ifa->scope = scope;
ifa->prefix_len = pfxlen;
@@ -669,10 +676,8 @@ 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. */
@@ -680,8 +685,7 @@ 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
@@ -700,7 +704,7 @@ out2:
return ifa;
out:
- write_unlock(&addrconf_hash_lock);
+ spin_unlock(&addrconf_hash_lock);
goto out2;
}
@@ -708,7 +712,7 @@ 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 hash;
int deleted = 0, onlink = 0;
@@ -718,42 +722,27 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
ifp->dead = 1;
- 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);
+ 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;
@@ -786,7 +775,6 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
}
}
}
- ifap = &ifa->if_next;
}
write_unlock_bh(&idev->lock);
@@ -1165,7 +1153,7 @@ 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;
/*
@@ -1243,7 +1231,6 @@ 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,
@@ -1253,12 +1240,14 @@ 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;
@@ -1276,7 +1265,7 @@ 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;
@@ -1285,11 +1274,12 @@ 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 = NULL;
+ 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) &&
@@ -1299,27 +1289,28 @@ int ipv6_chk_addr(struct net *net, struct in6_addr *addr,
break;
}
}
- read_unlock_bh(&addrconf_hash_lock);
+ rcu_read_unlock_bh();
+
return ifp != NULL;
}
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)
@@ -1333,7 +1324,7 @@ 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)
@@ -1350,24 +1341,26 @@ 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(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 */
@@ -1570,7 +1563,7 @@ 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;
@@ -1738,7 +1731,8 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev)
ASSERT_RTNL();
- if ((idev = ipv6_find_idev(dev)) == NULL)
+ idev = ipv6_find_idev(dev);
+ if (!idev)
return NULL;
/* Add default multicast route */
@@ -1971,7 +1965,7 @@ 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.
@@ -2174,7 +2168,7 @@ 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);
@@ -2185,7 +2179,7 @@ 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;
}
@@ -2446,7 +2440,8 @@ 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 (!idev) {
printk(KERN_DEBUG "init ip6-ip6: add_dev failed\n");
return;
}
@@ -2461,7 +2456,7 @@ 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);
@@ -2469,6 +2464,7 @@ 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)
@@ -2498,10 +2494,9 @@ 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;
}
@@ -2513,7 +2508,7 @@ 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);
@@ -2530,25 +2525,30 @@ 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;
@@ -2565,7 +2565,10 @@ 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:
@@ -2585,9 +2588,10 @@ 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;
}
@@ -2599,28 +2603,27 @@ 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, *keep_list, **bifa;
struct net *net = dev_net(dev);
- int i;
+ struct inet6_dev *idev;
+ struct inet6_ifaddr *ifa;
+ LIST_HEAD(keep_list);
ASSERT_RTNL();
@@ -2631,8 +2634,9 @@ 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;
@@ -2645,40 +2649,21 @@ 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 &&
- (how || !(ifa->flags&IFA_F_PERMANENT) ||
- ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)) {
- *bifa = ifa->lst_next;
- ifa->lst_next = NULL;
- __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;
+ /* 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);
ifa->dead = 1;
write_unlock_bh(&idev->lock);
spin_lock_bh(&ifa->lock);
@@ -2692,23 +2677,18 @@ static int addrconf_ifdown(struct net_device *dev, int how)
write_lock_bh(&idev->lock);
}
#endif
- keep_list = NULL;
- bifa = &keep_list;
- while ((ifa = idev->addr_list) != NULL) {
- idev->addr_list = ifa->if_next;
- ifa->if_next = NULL;
+ while (!list_empty(&idev->addr_list)) {
+ ifa = list_first_entry(&idev->addr_list,
+ struct inet6_ifaddr, if_list);
addrconf_del_timer(ifa);
/* If just doing link down, and address is permanent
and not link-local, then retain it. */
- if (how == 0 &&
+ if (!how &&
(ifa->flags&IFA_F_PERMANENT) &&
!(ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)) {
-
- /* Move to holding list */
- *bifa = ifa;
- bifa = &ifa->if_next;
+ 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)) ||
@@ -2723,24 +2703,32 @@ static int addrconf_ifdown(struct net_device *dev, int how)
/* Flag it for later restoration when link comes up */
ifa->flags |= IFA_F_TENTATIVE;
in6_ifa_hold(ifa);
+ write_unlock_bh(&idev->lock);
} else {
+ list_del(&ifa->if_list);
ifa->dead = 1;
+ write_unlock_bh(&idev->lock);
+
+ /* 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);
__ipv6_ifa_notify(RTM_DELADDR, ifa);
- atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa);
+ if (ifa->dead)
+ atomic_notifier_call_chain(&inet6addr_chain,
+ NETDEV_DOWN, ifa);
in6_ifa_put(ifa);
write_lock_bh(&idev->lock);
}
- idev->addr_list = keep_list;
+ 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
@@ -2748,8 +2736,7 @@ 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);
@@ -2860,7 +2847,7 @@ 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);
@@ -2910,7 +2897,7 @@ 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.
@@ -2941,11 +2928,12 @@ 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) {
+ list_for_each_entry(ifp, &idev->addr_list, if_list) {
spin_lock(&ifp->lock);
if (!(ifp->flags & IFA_F_TENTATIVE)) {
spin_unlock(&ifp->lock);
@@ -2970,36 +2958,35 @@ 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(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(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(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)
@@ -3007,15 +2994,15 @@ 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)
{
- read_lock_bh(&addrconf_hash_lock);
+ rcu_read_lock_bh();
return if6_get_idx(seq, *pos);
}
@@ -3029,9 +3016,9 @@ 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)
{
- read_unlock_bh(&addrconf_hash_lock);
+ rcu_read_unlock_bh();
}
static int if6_seq_show(struct seq_file *seq, void *v)
@@ -3101,10 +3088,12 @@ 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(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) &&
@@ -3113,7 +3102,7 @@ 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
@@ -3124,43 +3113,35 @@ 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(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) {
@@ -3182,7 +3163,6 @@ restart:
if (deprecate) {
in6_ifa_hold(ifp);
- read_unlock(&addrconf_hash_lock);
ipv6_ifa_notify(0, ifp);
in6_ifa_put(ifp);
@@ -3191,6 +3171,10 @@ 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))
@@ -3200,7 +3184,7 @@ 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);
@@ -3220,12 +3204,26 @@ 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)
@@ -3515,8 +3513,7 @@ 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,
@@ -3527,7 +3524,6 @@ 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;
@@ -3535,11 +3531,12 @@ 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,
@@ -3550,6 +3547,7 @@ 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;
@@ -3614,7 +3612,8 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
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,
@@ -3681,12 +3680,14 @@ 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;
}
@@ -3811,7 +3812,7 @@ static inline void __snmp6_fill_stats(u64 *stats, void __percpu **mib,
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 __percpu **)idev->stats.ipv6, IPSTATS_MIB_MAX, bytes);
break;
@@ -4047,7 +4048,8 @@ 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->dead && ip6_del_rt(ifp->rt))
dst_free(&ifp->rt->u.dst);
break;
}
@@ -4163,211 +4165,211 @@ 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",
@@ -4403,8 +4405,8 @@ 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;
}
@@ -4541,14 +4543,12 @@ 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);
/*
@@ -4557,11 +4557,12 @@ 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;
}
@@ -4592,6 +4593,9 @@ 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);
@@ -4620,7 +4624,6 @@ errlo:
void addrconf_cleanup(void)
{
- struct inet6_ifaddr *ifa;
struct net_device *dev;
int i;
@@ -4640,20 +4643,10 @@ 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/af_inet6.c b/net/ipv6/af_inet6.c
index 3192aa02ba5..d2df3144429 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -417,6 +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);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 622dc7939a1..5959230bc6c 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -278,6 +278,45 @@ 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
*/
@@ -381,6 +420,54 @@ 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)
@@ -497,7 +584,7 @@ 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;
@@ -737,6 +824,25 @@ 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/fib6_rules.c b/net/ipv6/fib6_rules.c
index 5e463c43fcc..8124f16f2ac 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -208,7 +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;
@@ -239,7 +238,7 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule)
}
static struct fib_rules_ops fib6_rules_ops_template = {
- .family = AF_INET6,
+ .family = FIB_RULES_IPV6,
.rule_size = sizeof(struct fib6_rule),
.addr_size = sizeof(struct in6_addr),
.action = fib6_rule_action,
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 3330a4bd615..ce799298255 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -481,8 +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_OUTMSGS);
ip6_flush_pending_frames(sk);
goto out_put;
}
@@ -560,9 +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_OUTMSGS);
ip6_flush_pending_frames(sk);
goto out_put;
}
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 3a4d92b5a83..9ca1efc923a 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -183,7 +183,7 @@ 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);
@@ -239,7 +239,7 @@ 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 6b82e02158c..92a122b7795 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -128,12 +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)
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 14e23216eb2..13654686aea 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -360,7 +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;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 75d5ef83009..7db09c3f528 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -181,11 +181,11 @@ int ip6_output(struct sk_buff *skb)
}
/*
- * 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);
@@ -231,10 +231,6 @@ 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
*/
@@ -1109,7 +1105,7 @@ 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);
@@ -1223,15 +1219,23 @@ 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/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 33f60fca7aa..bd43f0152c2 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -114,9 +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);
@@ -337,6 +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:
@@ -451,7 +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:
@@ -767,6 +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);
@@ -971,14 +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;
@@ -1056,6 +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:
{
@@ -1066,12 +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;
@@ -1115,6 +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 c483ab9fd67..006aee683a0 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -44,6 +44,7 @@
#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>
@@ -71,54 +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;
@@ -157,14 +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;
@@ -715,7 +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);
@@ -741,7 +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)
@@ -1161,7 +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;
@@ -1182,8 +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 &&
@@ -1197,7 +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;
@@ -1216,14 +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 */
}
@@ -1232,9 +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;
}
@@ -1270,7 +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;
@@ -1286,9 +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. */
@@ -1300,10 +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);
@@ -1311,8 +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;
@@ -1323,7 +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);
@@ -1432,11 +1379,11 @@ 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;
}
@@ -1458,9 +1405,10 @@ 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);
@@ -1521,7 +1469,7 @@ 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;
}
@@ -1557,7 +1505,7 @@ 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);
@@ -1770,9 +1718,8 @@ 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,
@@ -1820,16 +1767,14 @@ 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);
diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c
index cbe8dec9744..e60677519e4 100644
--- a/net/ipv6/netfilter/ip6t_hbh.c
+++ b/net/ipv6/netfilter/ip6t_hbh.c
@@ -141,11 +141,11 @@ 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;
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 58344c0fbd1..458eabfbe13 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -97,6 +97,7 @@ static const struct snmp_mib snmp6_icmp6_list[] = {
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
};
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 8763b1a0814..85627386cb0 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -461,6 +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;
@@ -733,6 +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;
@@ -811,7 +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;
@@ -880,6 +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;
@@ -890,7 +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);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 075f540ec19..6603511e367 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -75,6 +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;
@@ -350,6 +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 &&
@@ -503,14 +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);
}
@@ -918,22 +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;
@@ -946,11 +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;
}
@@ -1047,15 +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);
@@ -1070,7 +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);
@@ -1233,12 +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++;
@@ -1676,6 +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);
@@ -1702,12 +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);
@@ -1718,6 +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;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 90824852f59..2850e35cee3 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -91,9 +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;
}
@@ -335,6 +335,9 @@ 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);
@@ -919,6 +922,7 @@ 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;
@@ -1049,7 +1053,8 @@ 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;
@@ -1120,6 +1125,9 @@ 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:
@@ -1143,7 +1151,7 @@ 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)
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 00bf7c962b7..4a0e77e1446 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;
@@ -291,7 +261,6 @@ 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,
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-19 08:18:56 +0000