summaryrefslogtreecommitdiffstats
path: root/net/ipv6/addrconf.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-06-03 16:27:18 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-06-03 16:27:18 -0700
commitcb8e59cc87201af93dfbb6c3dccc8fcad72a09c2 (patch)
treea334db9022f89654b777bbce8c4c6632e65b9031 /net/ipv6/addrconf.c
parent2e63f6ce7ed2c4ff83ba30ad9ccad422289a6c63 (diff)
parent065fcfd49763ec71ae345bb5c5a74f961031e70e (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller: 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz Augusto von Dentz. 2) Add GSO partial support to igc, from Sasha Neftin. 3) Several cleanups and improvements to r8169 from Heiner Kallweit. 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a device self-test. From Andrew Lunn. 5) Start moving away from custom driver versions, use the globally defined kernel version instead, from Leon Romanovsky. 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin. 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet. 8) Add sriov and vf support to hinic, from Luo bin. 9) Support Media Redundancy Protocol (MRP) in the bridging code, from Horatiu Vultur. 10) Support netmap in the nft_nat code, from Pablo Neira Ayuso. 11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina Dubroca. Also add ipv6 support for espintcp. 12) Lots of ReST conversions of the networking documentation, from Mauro Carvalho Chehab. 13) Support configuration of ethtool rxnfc flows in bcmgenet driver, from Doug Berger. 14) Allow to dump cgroup id and filter by it in inet_diag code, from Dmitry Yakunin. 15) Add infrastructure to export netlink attribute policies to userspace, from Johannes Berg. 16) Several optimizations to sch_fq scheduler, from Eric Dumazet. 17) Fallback to the default qdisc if qdisc init fails because otherwise a packet scheduler init failure will make a device inoperative. From Jesper Dangaard Brouer. 18) Several RISCV bpf jit optimizations, from Luke Nelson. 19) Correct the return type of the ->ndo_start_xmit() method in several drivers, it's netdev_tx_t but many drivers were using 'int'. From Yunjian Wang. 20) Add an ethtool interface for PHY master/slave config, from Oleksij Rempel. 21) Add BPF iterators, from Yonghang Song. 22) Add cable test infrastructure, including ethool interfaces, from Andrew Lunn. Marvell PHY driver is the first to support this facility. 23) Remove zero-length arrays all over, from Gustavo A. R. Silva. 24) Calculate and maintain an explicit frame size in XDP, from Jesper Dangaard Brouer. 25) Add CAP_BPF, from Alexei Starovoitov. 26) Support terse dumps in the packet scheduler, from Vlad Buslov. 27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei. 28) Add devm_register_netdev(), from Bartosz Golaszewski. 29) Minimize qdisc resets, from Cong Wang. 30) Get rid of kernel_getsockopt and kernel_setsockopt in order to eliminate set_fs/get_fs calls. From Christoph Hellwig. * git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits) selftests: net: ip_defrag: ignore EPERM net_failover: fixed rollback in net_failover_open() Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv" Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv" vmxnet3: allow rx flow hash ops only when rss is enabled hinic: add set_channels ethtool_ops support selftests/bpf: Add a default $(CXX) value tools/bpf: Don't use $(COMPILE.c) bpf, selftests: Use bpf_probe_read_kernel s390/bpf: Use bcr 0,%0 as tail call nop filler s390/bpf: Maintain 8-byte stack alignment selftests/bpf: Fix verifier test selftests/bpf: Fix sample_cnt shared between two threads bpf, selftests: Adapt cls_redirect to call csum_level helper bpf: Add csum_level helper for fixing up csum levels bpf: Fix up bpf_skb_adjust_room helper's skb csum setting sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf() crypto/chtls: IPv6 support for inline TLS Crypto/chcr: Fixes a coccinile check error Crypto/chcr: Fixes compilations warnings ...
Diffstat (limited to 'net/ipv6/addrconf.c')
-rw-r--r--net/ipv6/addrconf.c271
1 files changed, 120 insertions, 151 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f131cedf5ba6..840bfdb3d7bd 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -135,8 +135,7 @@ static inline void addrconf_sysctl_unregister(struct inet6_dev *idev)
}
#endif
-static void ipv6_regen_rndid(struct inet6_dev *idev);
-static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr);
+static void ipv6_gen_rnd_iid(struct in6_addr *addr);
static int ipv6_generate_eui64(u8 *eui, struct net_device *dev);
static int ipv6_count_addresses(const struct inet6_dev *idev);
@@ -432,8 +431,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
dev->type == ARPHRD_SIT ||
dev->type == ARPHRD_NONE) {
ndev->cnf.use_tempaddr = -1;
- } else
- ipv6_regen_rndid(ndev);
+ }
ndev->token = in6addr_any;
@@ -1238,7 +1236,7 @@ cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires,
ifp->idev->dev, 0, RTF_DEFAULT, true);
if (f6i) {
if (del_rt)
- ip6_del_rt(dev_net(ifp->idev->dev), f6i);
+ ip6_del_rt(dev_net(ifp->idev->dev), f6i, false);
else {
if (!(f6i->fib6_flags & RTF_EXPIRES))
fib6_set_expires(f6i, expires);
@@ -1306,29 +1304,21 @@ out:
in6_ifa_put(ifp);
}
-static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp,
- struct inet6_ifaddr *ift,
- bool block)
+static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, bool block)
{
struct inet6_dev *idev = ifp->idev;
- struct in6_addr addr, *tmpaddr;
unsigned long tmp_tstamp, age;
unsigned long regen_advance;
- struct ifa6_config cfg;
- int ret = 0;
unsigned long now = jiffies;
- long max_desync_factor;
s32 cnf_temp_preferred_lft;
+ struct inet6_ifaddr *ift;
+ struct ifa6_config cfg;
+ long max_desync_factor;
+ struct in6_addr addr;
+ int ret = 0;
write_lock_bh(&idev->lock);
- if (ift) {
- spin_lock_bh(&ift->lock);
- memcpy(&addr.s6_addr[8], &ift->addr.s6_addr[8], 8);
- spin_unlock_bh(&ift->lock);
- tmpaddr = &addr;
- } else {
- tmpaddr = NULL;
- }
+
retry:
in6_dev_hold(idev);
if (idev->cnf.use_tempaddr <= 0) {
@@ -1351,8 +1341,8 @@ retry:
}
in6_ifa_hold(ifp);
memcpy(addr.s6_addr, ifp->addr.s6_addr, 8);
- ipv6_try_regen_rndid(idev, tmpaddr);
- memcpy(&addr.s6_addr[8], idev->rndid, 8);
+ ipv6_gen_rnd_iid(&addr);
+
age = (now - ifp->tstamp) / HZ;
regen_advance = idev->cnf.regen_max_retry *
@@ -1417,7 +1407,6 @@ retry:
in6_ifa_put(ifp);
in6_dev_put(idev);
pr_info("%s: retry temporary address regeneration\n", __func__);
- tmpaddr = &addr;
write_lock_bh(&idev->lock);
goto retry;
}
@@ -2032,7 +2021,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
if (ifpub) {
in6_ifa_hold(ifpub);
spin_unlock_bh(&ifp->lock);
- ipv6_create_tempaddr(ifpub, ifp, true);
+ ipv6_create_tempaddr(ifpub, true);
in6_ifa_put(ifpub);
} else {
spin_unlock_bh(&ifp->lock);
@@ -2329,40 +2318,38 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev)
return err;
}
-/* (re)generation of randomized interface identifier (RFC 3041 3.2, 3.5) */
-static void ipv6_regen_rndid(struct inet6_dev *idev)
+/* Generation of a randomized Interface Identifier
+ * draft-ietf-6man-rfc4941bis, Section 3.3.1
+ */
+
+static void ipv6_gen_rnd_iid(struct in6_addr *addr)
{
regen:
- get_random_bytes(idev->rndid, sizeof(idev->rndid));
- idev->rndid[0] &= ~0x02;
+ get_random_bytes(&addr->s6_addr[8], 8);
- /*
- * <draft-ietf-ipngwg-temp-addresses-v2-00.txt>:
- * check if generated address is not inappropriate
+ /* <draft-ietf-6man-rfc4941bis-08.txt>, Section 3.3.1:
+ * check if generated address is not inappropriate:
*
- * - Reserved subnet anycast (RFC 2526)
- * 11111101 11....11 1xxxxxxx
- * - ISATAP (RFC4214) 6.1
- * 00-00-5E-FE-xx-xx-xx-xx
- * - value 0
- * - XXX: already assigned to an address on the device
+ * - Reserved IPv6 Interface Identifers
+ * - XXX: already assigned to an address on the device
*/
- if (idev->rndid[0] == 0xfd &&
- (idev->rndid[1]&idev->rndid[2]&idev->rndid[3]&idev->rndid[4]&idev->rndid[5]&idev->rndid[6]) == 0xff &&
- (idev->rndid[7]&0x80))
+
+ /* Subnet-router anycast: 0000:0000:0000:0000 */
+ if (!(addr->s6_addr32[2] | addr->s6_addr32[3]))
goto regen;
- if ((idev->rndid[0]|idev->rndid[1]) == 0) {
- if (idev->rndid[2] == 0x5e && idev->rndid[3] == 0xfe)
- goto regen;
- if ((idev->rndid[2]|idev->rndid[3]|idev->rndid[4]|idev->rndid[5]|idev->rndid[6]|idev->rndid[7]) == 0x00)
- goto regen;
- }
-}
-static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr)
-{
- if (tmpaddr && memcmp(idev->rndid, &tmpaddr->s6_addr[8], 8) == 0)
- ipv6_regen_rndid(idev);
+ /* IANA Ethernet block: 0200:5EFF:FE00:0000-0200:5EFF:FE00:5212
+ * Proxy Mobile IPv6: 0200:5EFF:FE00:5213
+ * IANA Ethernet block: 0200:5EFF:FE00:5214-0200:5EFF:FEFF:FFFF
+ */
+ if (ntohl(addr->s6_addr32[2]) == 0x02005eff &&
+ (ntohl(addr->s6_addr32[3]) & 0Xff000000) == 0xfe000000)
+ goto regen;
+
+ /* Reserved subnet anycast addresses */
+ if (ntohl(addr->s6_addr32[2]) == 0xfdffffff &&
+ ntohl(addr->s6_addr32[3]) >= 0Xffffff80)
+ goto regen;
}
/*
@@ -2544,7 +2531,7 @@ static void manage_tempaddrs(struct inet6_dev *idev,
* no temporary address currently exists.
*/
read_unlock_bh(&idev->lock);
- ipv6_create_tempaddr(ifp, NULL, false);
+ ipv6_create_tempaddr(ifp, false);
} else {
read_unlock_bh(&idev->lock);
}
@@ -2564,7 +2551,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
__u32 valid_lft, u32 prefered_lft)
{
struct inet6_ifaddr *ifp = ipv6_get_ifaddr(net, addr, dev, 1);
- int create = 0, update_lft = 0;
+ int create = 0;
if (!ifp && valid_lft) {
int max_addresses = in6_dev->cnf.max_addresses;
@@ -2608,32 +2595,19 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
unsigned long now;
u32 stored_lft;
- /* update lifetime (RFC2462 5.5.3 e) */
+ /* Update lifetime (RFC4862 5.5.3 e)
+ * We deviate from RFC4862 by honoring all Valid Lifetimes to
+ * improve the reaction of SLAAC to renumbering events
+ * (draft-gont-6man-slaac-renum-06, Section 4.2)
+ */
spin_lock_bh(&ifp->lock);
now = jiffies;
if (ifp->valid_lft > (now - ifp->tstamp) / HZ)
stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ;
else
stored_lft = 0;
- if (!create && stored_lft) {
- const u32 minimum_lft = min_t(u32,
- stored_lft, MIN_VALID_LIFETIME);
- valid_lft = max(valid_lft, minimum_lft);
-
- /* RFC4862 Section 5.5.3e:
- * "Note that the preferred lifetime of the
- * corresponding address is always reset to
- * the Preferred Lifetime in the received
- * Prefix Information option, regardless of
- * whether the valid lifetime is also reset or
- * ignored."
- *
- * So we should always update prefered_lft here.
- */
- update_lft = 1;
- }
- if (update_lft) {
+ if (!create && stored_lft) {
ifp->valid_lft = valid_lft;
ifp->prefered_lft = prefered_lft;
ifp->tstamp = now;
@@ -2731,7 +2705,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
if (rt) {
/* Autoconf prefix route */
if (valid_lft == 0) {
- ip6_del_rt(net, rt);
+ ip6_del_rt(net, rt, false);
rt = NULL;
} else if (addrconf_finite_timeout(rt_expires)) {
/* not infinity */
@@ -2809,6 +2783,33 @@ put:
in6_dev_put(in6_dev);
}
+static int addrconf_set_sit_dstaddr(struct net *net, struct net_device *dev,
+ struct in6_ifreq *ireq)
+{
+ struct ip_tunnel_parm p = { };
+ int err;
+
+ if (!(ipv6_addr_type(&ireq->ifr6_addr) & IPV6_ADDR_COMPATv4))
+ return -EADDRNOTAVAIL;
+
+ p.iph.daddr = ireq->ifr6_addr.s6_addr32[3];
+ p.iph.version = 4;
+ p.iph.ihl = 5;
+ p.iph.protocol = IPPROTO_IPV6;
+ p.iph.ttl = 64;
+
+ if (!dev->netdev_ops->ndo_tunnel_ctl)
+ return -EOPNOTSUPP;
+ err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, SIOCADDTUNNEL);
+ if (err)
+ return err;
+
+ dev = __dev_get_by_name(net, p.name);
+ if (!dev)
+ return -ENOBUFS;
+ return dev_open(dev, NULL);
+}
+
/*
* Set destination address.
* Special case for SIT interfaces where we create a new "virtual"
@@ -2816,61 +2817,19 @@ put:
*/
int addrconf_set_dstaddr(struct net *net, void __user *arg)
{
- struct in6_ifreq ireq;
struct net_device *dev;
- int err = -EINVAL;
-
- rtnl_lock();
+ struct in6_ifreq ireq;
+ int err = -ENODEV;
- err = -EFAULT;
+ if (!IS_ENABLED(CONFIG_IPV6_SIT))
+ return -ENODEV;
if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq)))
- goto err_exit;
+ return -EFAULT;
+ rtnl_lock();
dev = __dev_get_by_index(net, ireq.ifr6_ifindex);
-
- err = -ENODEV;
- if (!dev)
- goto err_exit;
-
-#if IS_ENABLED(CONFIG_IPV6_SIT)
- if (dev->type == ARPHRD_SIT) {
- const struct net_device_ops *ops = dev->netdev_ops;
- struct ifreq ifr;
- struct ip_tunnel_parm p;
-
- err = -EADDRNOTAVAIL;
- if (!(ipv6_addr_type(&ireq.ifr6_addr) & IPV6_ADDR_COMPATv4))
- goto err_exit;
-
- memset(&p, 0, sizeof(p));
- p.iph.daddr = ireq.ifr6_addr.s6_addr32[3];
- p.iph.saddr = 0;
- p.iph.version = 4;
- p.iph.ihl = 5;
- p.iph.protocol = IPPROTO_IPV6;
- p.iph.ttl = 64;
- ifr.ifr_ifru.ifru_data = (__force void __user *)&p;
-
- if (ops->ndo_do_ioctl) {
- mm_segment_t oldfs = get_fs();
-
- set_fs(KERNEL_DS);
- err = ops->ndo_do_ioctl(dev, &ifr, SIOCADDTUNNEL);
- set_fs(oldfs);
- } else
- err = -EOPNOTSUPP;
-
- if (err == 0) {
- err = -ENOBUFS;
- dev = __dev_get_by_name(net, p.name);
- if (!dev)
- goto err_exit;
- err = dev_open(dev, NULL);
- }
- }
-#endif
-
-err_exit:
+ if (dev && dev->type == ARPHRD_SIT)
+ err = addrconf_set_sit_dstaddr(net, dev, &ireq);
rtnl_unlock();
return err;
}
@@ -3826,7 +3785,7 @@ restart:
spin_unlock_bh(&ifa->lock);
if (rt)
- ip6_del_rt(net, rt);
+ ip6_del_rt(net, rt, false);
if (state != INET6_IFADDR_STATE_DEAD) {
__ipv6_ifa_notify(RTM_DELADDR, ifa);
@@ -4544,7 +4503,7 @@ restart:
ifpub->regen_count = 0;
spin_unlock(&ifpub->lock);
rcu_read_unlock_bh();
- ipv6_create_tempaddr(ifpub, ifp, true);
+ ipv6_create_tempaddr(ifpub, true);
in6_ifa_put(ifpub);
in6_ifa_put(ifp);
rcu_read_lock_bh();
@@ -4665,7 +4624,7 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
prio = ifp->rt_priority ? : IP6_RT_PRIO_ADDRCONF;
if (f6i->fib6_metric != prio) {
/* delete old one */
- ip6_del_rt(dev_net(ifp->idev->dev), f6i);
+ ip6_del_rt(dev_net(ifp->idev->dev), f6i, false);
/* add new one */
addrconf_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr,
@@ -6086,10 +6045,10 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
ifp->idev->dev, 0, 0,
false);
if (rt)
- ip6_del_rt(net, rt);
+ ip6_del_rt(net, rt, false);
}
if (ifp->rt) {
- ip6_del_rt(net, ifp->rt);
+ ip6_del_rt(net, ifp->rt, false);
ifp->rt = NULL;
}
rt_genid_bump_ipv6(net);
@@ -6108,9 +6067,8 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
#ifdef CONFIG_SYSCTL
-static
-int addrconf_sysctl_forward(struct ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos)
+static int addrconf_sysctl_forward(struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
{
int *valp = ctl->data;
int val = *valp;
@@ -6134,9 +6092,8 @@ int addrconf_sysctl_forward(struct ctl_table *ctl, int write,
return ret;
}
-static
-int addrconf_sysctl_mtu(struct ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos)
+static int addrconf_sysctl_mtu(struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
{
struct inet6_dev *idev = ctl->extra1;
int min_mtu = IPV6_MIN_MTU;
@@ -6206,9 +6163,8 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
return 0;
}
-static
-int addrconf_sysctl_disable(struct ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos)
+static int addrconf_sysctl_disable(struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
{
int *valp = ctl->data;
int val = *valp;
@@ -6232,9 +6188,8 @@ int addrconf_sysctl_disable(struct ctl_table *ctl, int write,
return ret;
}
-static
-int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos)
+static int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
{
int *valp = ctl->data;
int ret;
@@ -6275,7 +6230,7 @@ int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write,
}
static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp,
+ void *buffer, size_t *lenp,
loff_t *ppos)
{
int ret = 0;
@@ -6337,7 +6292,7 @@ out:
}
static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp,
+ void *buffer, size_t *lenp,
loff_t *ppos)
{
int err;
@@ -6404,8 +6359,7 @@ out:
static
int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl,
- int write,
- void __user *buffer,
+ int write, void *buffer,
size_t *lenp,
loff_t *ppos)
{
@@ -6505,10 +6459,8 @@ int addrconf_disable_policy(struct ctl_table *ctl, int *valp, int val)
return 0;
}
-static
-int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
+static int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
{
int *valp = ctl->data;
int val = *valp;
@@ -7024,9 +6976,26 @@ static int __net_init addrconf_init_net(struct net *net)
goto err_alloc_dflt;
if (IS_ENABLED(CONFIG_SYSCTL) &&
- sysctl_devconf_inherit_init_net == 1 && !net_eq(net, &init_net)) {
- memcpy(all, init_net.ipv6.devconf_all, sizeof(ipv6_devconf));
- memcpy(dflt, init_net.ipv6.devconf_dflt, sizeof(ipv6_devconf_dflt));
+ !net_eq(net, &init_net)) {
+ switch (sysctl_devconf_inherit_init_net) {
+ case 1: /* copy from init_net */
+ memcpy(all, init_net.ipv6.devconf_all,
+ sizeof(ipv6_devconf));
+ memcpy(dflt, init_net.ipv6.devconf_dflt,
+ sizeof(ipv6_devconf_dflt));
+ break;
+ case 3: /* copy from the current netns */
+ memcpy(all, current->nsproxy->net_ns->ipv6.devconf_all,
+ sizeof(ipv6_devconf));
+ memcpy(dflt,
+ current->nsproxy->net_ns->ipv6.devconf_dflt,
+ sizeof(ipv6_devconf_dflt));
+ break;
+ case 0:
+ case 2:
+ /* use compiled values */
+ break;
+ }
}
/* these will be inherited by all namespaces */