diff options
Diffstat (limited to 'net/ipv6')
-rw-r--r-- | net/ipv6/addrconf.c | 331 | ||||
-rw-r--r-- | net/ipv6/addrlabel.c | 11 | ||||
-rw-r--r-- | net/ipv6/af_inet6.c | 4 | ||||
-rw-r--r-- | net/ipv6/anycast.c | 12 | ||||
-rw-r--r-- | net/ipv6/inet6_connection_sock.c | 23 | ||||
-rw-r--r-- | net/ipv6/inet6_hashtables.c | 58 | ||||
-rw-r--r-- | net/ipv6/ip6_flowlabel.c | 3 | ||||
-rw-r--r-- | net/ipv6/ip6_tunnel.c | 6 | ||||
-rw-r--r-- | net/ipv6/ip6mr.c | 4 | ||||
-rw-r--r-- | net/ipv6/ipv6_sockglue.c | 32 | ||||
-rw-r--r-- | net/ipv6/mcast.c | 36 | ||||
-rw-r--r-- | net/ipv6/ndisc.c | 8 | ||||
-rw-r--r-- | net/ipv6/netfilter/Kconfig | 18 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6t_REJECT.c | 3 | ||||
-rw-r--r-- | net/ipv6/netfilter/nf_reject_ipv6.c | 37 | ||||
-rw-r--r-- | net/ipv6/ping.c | 3 | ||||
-rw-r--r-- | net/ipv6/raw.c | 10 | ||||
-rw-r--r-- | net/ipv6/route.c | 18 | ||||
-rw-r--r-- | net/ipv6/syncookies.c | 13 | ||||
-rw-r--r-- | net/ipv6/sysctl_net_ipv6.c | 16 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 96 | ||||
-rw-r--r-- | net/ipv6/tcpv6_offload.c | 4 | ||||
-rw-r--r-- | net/ipv6/udp.c | 26 | ||||
-rw-r--r-- | net/ipv6/udp_impl.h | 7 | ||||
-rw-r--r-- | net/ipv6/xfrm6_policy.c | 1 |
25 files changed, 525 insertions, 255 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b6030025f411..d2d238334a11 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -46,6 +46,7 @@ #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> +#include <linux/inet.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_addr.h> @@ -102,6 +103,9 @@ #define INFINITY_LIFE_TIME 0xFFFFFFFF +#define IPV6_MAX_STRLEN \ + sizeof("ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255") + static inline u32 cstamp_delta(unsigned long cstamp) { return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; @@ -127,6 +131,9 @@ static void ipv6_regen_rndid(unsigned long data); static int ipv6_generate_eui64(u8 *eui, struct net_device *dev); static int ipv6_count_addresses(struct inet6_dev *idev); +static int ipv6_generate_stable_address(struct in6_addr *addr, + u8 dad_count, + const struct inet6_dev *idev); /* * Configured unicast address hash table @@ -202,6 +209,9 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .accept_dad = 1, .suppress_frag_ndisc = 1, .accept_ra_mtu = 1, + .stable_secret = { + .initialized = false, + } }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -240,6 +250,9 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .accept_dad = 1, .suppress_frag_ndisc = 1, .accept_ra_mtu = 1, + .stable_secret = { + .initialized = false, + }, }; /* Check if a valid qdisc is available */ @@ -860,7 +873,6 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa->peer_addr = *peer_addr; spin_lock_init(&ifa->lock); - spin_lock_init(&ifa->state_lock); INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work); INIT_HLIST_NODE(&ifa->addr_lst); ifa->scope = scope; @@ -1003,10 +1015,10 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) ASSERT_RTNL(); - spin_lock_bh(&ifp->state_lock); + spin_lock_bh(&ifp->lock); state = ifp->state; ifp->state = INET6_IFADDR_STATE_DEAD; - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); if (state == INET6_IFADDR_STATE_DEAD) goto out; @@ -1686,19 +1698,21 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp) { int err = -ENOENT; - spin_lock_bh(&ifp->state_lock); + spin_lock_bh(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DAD) { ifp->state = INET6_IFADDR_STATE_POSTDAD; err = 0; } - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); return err; } void addrconf_dad_failure(struct inet6_ifaddr *ifp) { + struct in6_addr addr; struct inet6_dev *idev = ifp->idev; + struct net *net = dev_net(ifp->idev->dev); if (addrconf_dad_end(ifp)) { in6_ifa_put(ifp); @@ -1708,9 +1722,57 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) net_info_ratelimited("%s: IPv6 duplicate address %pI6c detected!\n", ifp->idev->dev->name, &ifp->addr); - if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { - struct in6_addr addr; + spin_lock_bh(&ifp->lock); + + if (ifp->flags & IFA_F_STABLE_PRIVACY) { + int scope = ifp->scope; + u32 flags = ifp->flags; + struct in6_addr new_addr; + struct inet6_ifaddr *ifp2; + u32 valid_lft, preferred_lft; + int pfxlen = ifp->prefix_len; + int retries = ifp->stable_privacy_retry + 1; + + if (retries > net->ipv6.sysctl.idgen_retries) { + net_info_ratelimited("%s: privacy stable address generation failed because of DAD conflicts!\n", + ifp->idev->dev->name); + goto errdad; + } + + new_addr = ifp->addr; + if (ipv6_generate_stable_address(&new_addr, retries, + idev)) + goto errdad; + + valid_lft = ifp->valid_lft; + preferred_lft = ifp->prefered_lft; + + spin_unlock_bh(&ifp->lock); + + if (idev->cnf.max_addresses && + ipv6_count_addresses(idev) >= + idev->cnf.max_addresses) + goto lock_errdad; + + net_info_ratelimited("%s: generating new stable privacy address because of DAD conflict\n", + ifp->idev->dev->name); + + ifp2 = ipv6_add_addr(idev, &new_addr, NULL, pfxlen, + scope, flags, valid_lft, + preferred_lft); + if (IS_ERR(ifp2)) + goto lock_errdad; + spin_lock_bh(&ifp2->lock); + ifp2->stable_privacy_retry = retries; + ifp2->state = INET6_IFADDR_STATE_PREDAD; + spin_unlock_bh(&ifp2->lock); + + addrconf_mod_dad_work(ifp2, net->ipv6.sysctl.idgen_delay); + in6_ifa_put(ifp2); +lock_errdad: + spin_lock_bh(&ifp->lock); + } else if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { addr.s6_addr32[0] = htonl(0xfe800000); addr.s6_addr32[1] = 0; @@ -1724,10 +1786,10 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) } } - spin_lock_bh(&ifp->state_lock); +errdad: /* transition from _POSTDAD to _ERRDAD */ ifp->state = INET6_IFADDR_STATE_ERRDAD; - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); addrconf_mod_dad_work(ifp, 0); } @@ -2186,6 +2248,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) __u32 valid_lft; __u32 prefered_lft; int addr_type; + u32 addr_flags = 0; struct inet6_dev *in6_dev; struct net *net = dev_net(dev); @@ -2292,6 +2355,12 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) in6_dev->token.s6_addr + 8, 8); read_unlock_bh(&in6_dev->lock); tokenized = true; + } else if (in6_dev->addr_gen_mode == + IN6_ADDR_GEN_MODE_STABLE_PRIVACY && + !ipv6_generate_stable_address(&addr, 0, + in6_dev)) { + addr_flags |= IFA_F_STABLE_PRIVACY; + goto ok; } else if (ipv6_generate_eui64(addr.s6_addr + 8, dev) && ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) { in6_dev_put(in6_dev); @@ -2310,7 +2379,6 @@ ok: if (ifp == NULL && valid_lft) { int max_addresses = in6_dev->cnf.max_addresses; - u32 addr_flags = 0; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (in6_dev->cnf.optimistic_dad && @@ -2350,7 +2418,7 @@ ok: u32 stored_lft; /* update lifetime (RFC2462 5.5.3 e) */ - spin_lock(&ifp->lock); + spin_lock_bh(&ifp->lock); now = jiffies; if (ifp->valid_lft > (now - ifp->tstamp) / HZ) stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; @@ -2380,12 +2448,12 @@ ok: ifp->tstamp = now; flags = ifp->flags; ifp->flags &= ~IFA_F_DEPRECATED; - spin_unlock(&ifp->lock); + spin_unlock_bh(&ifp->lock); if (!(flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ifp); } else - spin_unlock(&ifp->lock); + spin_unlock_bh(&ifp->lock); manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft, create, now); @@ -2464,6 +2532,23 @@ err_exit: return err; } +static int ipv6_mc_config(struct sock *sk, bool join, + const struct in6_addr *addr, int ifindex) +{ + int ret; + + ASSERT_RTNL(); + + lock_sock(sk); + if (join) + ret = ipv6_sock_mc_join(sk, ifindex, addr); + else + ret = ipv6_sock_mc_drop(sk, ifindex, addr); + release_sock(sk); + + return ret; +} + /* * Manual configuration of address on an interface */ @@ -2476,10 +2561,10 @@ static int inet6_addr_add(struct net *net, int ifindex, struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; + unsigned long timeout; + clock_t expires; int scope; u32 flags; - clock_t expires; - unsigned long timeout; ASSERT_RTNL(); @@ -2501,6 +2586,14 @@ static int inet6_addr_add(struct net *net, int ifindex, if (IS_ERR(idev)) return PTR_ERR(idev); + if (ifa_flags & IFA_F_MCAUTOJOIN) { + int ret = ipv6_mc_config(net->ipv6.mc_autojoin_sk, + true, pfx, ifindex); + + if (ret < 0) + return ret; + } + scope = ipv6_addr_scope(pfx); timeout = addrconf_timeout_fixup(valid_lft, HZ); @@ -2542,6 +2635,9 @@ static int inet6_addr_add(struct net *net, int ifindex, in6_ifa_put(ifp); addrconf_verify_rtnl(); return 0; + } else if (ifa_flags & IFA_F_MCAUTOJOIN) { + ipv6_mc_config(net->ipv6.mc_autojoin_sk, + false, pfx, ifindex); } return PTR_ERR(ifp); @@ -2578,6 +2674,10 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, jiffies); ipv6_del_addr(ifp); addrconf_verify_rtnl(); + if (ipv6_addr_is_multicast(pfx)) { + ipv6_mc_config(net->ipv6.mc_autojoin_sk, + false, pfx, dev->ifindex); + } return 0; } } @@ -2757,10 +2857,11 @@ static void init_loopback(struct net_device *dev) } } -static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr) +static void addrconf_add_linklocal(struct inet6_dev *idev, + const struct in6_addr *addr, u32 flags) { struct inet6_ifaddr *ifp; - u32 addr_flags = IFA_F_PERMANENT; + u32 addr_flags = flags | IFA_F_PERMANENT; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (idev->cnf.optimistic_dad && @@ -2768,7 +2869,6 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr addr_flags |= IFA_F_OPTIMISTIC; #endif - ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); if (!IS_ERR(ifp)) { @@ -2778,18 +2878,103 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr } } +static bool ipv6_reserved_interfaceid(struct in6_addr address) +{ + if ((address.s6_addr32[2] | address.s6_addr32[3]) == 0) + return true; + + if (address.s6_addr32[2] == htonl(0x02005eff) && + ((address.s6_addr32[3] & htonl(0xfe000000)) == htonl(0xfe000000))) + return true; + + if (address.s6_addr32[2] == htonl(0xfdffffff) && + ((address.s6_addr32[3] & htonl(0xffffff80)) == htonl(0xffffff80))) + return true; + + return false; +} + +static int ipv6_generate_stable_address(struct in6_addr *address, + u8 dad_count, + const struct inet6_dev *idev) +{ + static DEFINE_SPINLOCK(lock); + static __u32 digest[SHA_DIGEST_WORDS]; + static __u32 workspace[SHA_WORKSPACE_WORDS]; + + static union { + char __data[SHA_MESSAGE_BYTES]; + struct { + struct in6_addr secret; + __be64 prefix; + unsigned char hwaddr[MAX_ADDR_LEN]; + u8 dad_count; + } __packed; + } data; + + struct in6_addr secret; + struct in6_addr temp; + struct net *net = dev_net(idev->dev); + + BUILD_BUG_ON(sizeof(data.__data) != sizeof(data)); + + if (idev->cnf.stable_secret.initialized) + secret = idev->cnf.stable_secret.secret; + else if (net->ipv6.devconf_dflt->stable_secret.initialized) + secret = net->ipv6.devconf_dflt->stable_secret.secret; + else + return -1; + +retry: + spin_lock_bh(&lock); + + sha_init(digest); + memset(&data, 0, sizeof(data)); + memset(workspace, 0, sizeof(workspace)); + memcpy(data.hwaddr, idev->dev->perm_addr, idev->dev->addr_len); + data.prefix = ((__be64)address->s6_addr32[0] << 32) | + (__be64)address->s6_addr32[1]; + data.secret = secret; + data.dad_count = dad_count; + + sha_transform(digest, data.__data, workspace); + + temp = *address; + temp.s6_addr32[2] = digest[0]; + temp.s6_addr32[3] = digest[1]; + + spin_unlock_bh(&lock); + + if (ipv6_reserved_interfaceid(temp)) { + dad_count++; + if (dad_count > dev_net(idev->dev)->ipv6.sysctl.idgen_retries) + return -1; + goto retry; + } + + *address = temp; + return 0; +} + static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) { - if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) { - struct in6_addr addr; + struct in6_addr addr; + + ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); - ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); + if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY) { + if (!ipv6_generate_stable_address(&addr, 0, idev)) + addrconf_add_linklocal(idev, &addr, + IFA_F_STABLE_PRIVACY); + else if (prefix_route) + addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); + } else if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) { /* addrconf_add_linklocal also adds a prefix_route and we * only need to care about prefix routes if ipv6_generate_eui64 * couldn't generate one. */ if (ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) == 0) - addrconf_add_linklocal(idev, &addr); + addrconf_add_linklocal(idev, &addr, 0); else if (prefix_route) addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); } @@ -3127,10 +3312,10 @@ restart: write_unlock_bh(&idev->lock); - spin_lock_bh(&ifa->state_lock); + spin_lock_bh(&ifa->lock); state = ifa->state; ifa->state = INET6_IFADDR_STATE_DEAD; - spin_unlock_bh(&ifa->state_lock); + spin_unlock_bh(&ifa->lock); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); @@ -3288,12 +3473,12 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp) { bool begin_dad = false; - spin_lock_bh(&ifp->state_lock); + spin_lock_bh(&ifp->lock); if (ifp->state != INET6_IFADDR_STATE_DEAD) { ifp->state = INET6_IFADDR_STATE_PREDAD; begin_dad = true; } - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); if (begin_dad) addrconf_mod_dad_work(ifp, 0); @@ -3315,7 +3500,7 @@ static void addrconf_dad_work(struct work_struct *w) rtnl_lock(); - spin_lock_bh(&ifp->state_lock); + spin_lock_bh(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_PREDAD) { action = DAD_BEGIN; ifp->state = INET6_IFADDR_STATE_DAD; @@ -3323,7 +3508,7 @@ static void addrconf_dad_work(struct work_struct *w) action = DAD_ABORT; ifp->state = INET6_IFADDR_STATE_POSTDAD; } - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); if (action == DAD_BEGIN) { addrconf_dad_begin(ifp); @@ -3945,7 +4130,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) /* We ignore other flags so far. */ ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | - IFA_F_NOPREFIXROUTE; + IFA_F_NOPREFIXROUTE | IFA_F_MCAUTOJOIN; ifa = ipv6_get_ifaddr(net, pfx, dev, 1); if (ifa == NULL) { @@ -4398,6 +4583,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc; array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local; array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu; + /* we omit DEVCONF_STABLE_SECRET for now */ } static inline size_t inet6_ifla6_size(void) @@ -4632,8 +4818,15 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]); if (mode != IN6_ADDR_GEN_MODE_EUI64 && - mode != IN6_ADDR_GEN_MODE_NONE) + mode != IN6_ADDR_GEN_MODE_NONE && + mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY) + return -EINVAL; + + if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY && + !idev->cnf.stable_secret.initialized && + !dev_net(dev)->ipv6.devconf_dflt->stable_secret.initialized) return -EINVAL; + idev->addr_gen_mode = mode; err = 0; } @@ -5042,6 +5235,74 @@ int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write, return ret; } +static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int err; + struct in6_addr addr; + char str[IPV6_MAX_STRLEN]; + struct ctl_table lctl = *ctl; + struct net *net = ctl->extra2; + struct ipv6_stable_secret *secret = ctl->data; + + if (&net->ipv6.devconf_all->stable_secret == ctl->data) + return -EIO; + + lctl.maxlen = IPV6_MAX_STRLEN; + lctl.data = str; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (!write && !secret->initialized) { + err = -EIO; + goto out; + } + + if (!write) { + err = snprintf(str, sizeof(str), "%pI6", + &secret->secret); + if (err >= sizeof(str)) { + err = -EIO; + goto out; + } + } + + err = proc_dostring(&lctl, write, buffer, lenp, ppos); + if (err || !write) + goto out; + + if (in6_pton(str, -1, addr.in6_u.u6_addr8, -1, NULL) != 1) { + err = -EIO; + goto out; + } + + secret->initialized = true; + secret->secret = addr; + + if (&net->ipv6.devconf_dflt->stable_secret == ctl->data) { + struct net_device *dev; + + for_each_netdev(net, dev) { + struct inet6_dev *idev = __in6_dev_get(dev); + + if (idev) { + idev->addr_gen_mode = + IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + } + } + } else { + struct inet6_dev *idev = ctl->extra1; + + idev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + } + +out: + rtnl_unlock(); + + return err; +} static struct addrconf_sysctl_table { @@ -5315,6 +5576,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { + .procname = "stable_secret", + .data = &ipv6_devconf.stable_secret, + .maxlen = IPV6_MAX_STRLEN, + .mode = 0600, + .proc_handler = addrconf_sysctl_stable_secret, + }, + { /* sentinel */ } }, @@ -5410,6 +5678,9 @@ static int __net_init addrconf_init_net(struct net *net) dflt->autoconf = ipv6_defaults.autoconf; dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; + dflt->stable_secret.initialized = false; + all->stable_secret.initialized = false; + net->ipv6.devconf_all = all; net->ipv6.devconf_dflt = dflt; diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index e43e79d0a612..3cc50e2d3bf5 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -29,9 +29,7 @@ * Policy Table */ struct ip6addrlbl_entry { -#ifdef CONFIG_NET_NS - struct net *lbl_net; -#endif + possible_net_t lbl_net; struct in6_addr prefix; int prefixlen; int ifindex; @@ -129,9 +127,6 @@ static const __net_initconst struct ip6addrlbl_init_table /* Object management */ static inline void ip6addrlbl_free(struct ip6addrlbl_entry *p) { -#ifdef CONFIG_NET_NS - release_net(p->lbl_net); -#endif kfree(p); } @@ -240,9 +235,7 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, newp->addrtype = addrtype; newp->label = label; INIT_HLIST_NODE(&newp->list); -#ifdef CONFIG_NET_NS - newp->lbl_net = hold_net(net); -#endif + write_pnet(&newp->lbl_net, net); atomic_set(&newp->refcnt, 1); return newp; } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index e8c4400f23e9..d8dcc526339e 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -766,6 +766,8 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.icmpv6_time = 1*HZ; net->ipv6.sysctl.flowlabel_consistency = 1; net->ipv6.sysctl.auto_flowlabels = 0; + net->ipv6.sysctl.idgen_retries = 3; + net->ipv6.sysctl.idgen_delay = 1 * HZ; atomic_set(&net->ipv6.fib6_sernum, 1); err = ipv6_init_mibs(net); @@ -824,7 +826,7 @@ static int __init inet6_init(void) struct list_head *r; int err = 0; - BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb)); + sock_skb_cb_check_size(sizeof(struct inet6_skb_parm)); /* Register the socket-side information for inet6_create. */ for (r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index baf2742d1ec4..9e6b0ee563f0 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -60,6 +60,8 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) int ishost = !net->ipv6.devconf_all->forwarding; int err = 0; + ASSERT_RTNL(); + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (ipv6_addr_is_multicast(addr)) @@ -73,7 +75,6 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) pac->acl_next = NULL; pac->acl_addr = *addr; - rtnl_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -130,7 +131,6 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) } error: - rtnl_unlock(); if (pac) sock_kfree_s(sk, pac, sizeof(*pac)); return err; @@ -146,7 +146,8 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) struct ipv6_ac_socklist *pac, *prev_pac; struct net *net = sock_net(sk); - rtnl_lock(); + ASSERT_RTNL(); + prev_pac = NULL; for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) { if ((ifindex == 0 || pac->acl_ifindex == ifindex) && @@ -154,10 +155,8 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) break; prev_pac = pac; } - if (!pac) { - rtnl_unlock(); + if (!pac) return -ENOENT; - } if (prev_pac) prev_pac->acl_next = pac->acl_next; else @@ -166,7 +165,6 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) dev = __dev_get_by_index(net, pac->acl_ifindex); if (dev) ipv6_dev_ac_dec(dev, &pac->acl_addr); - rtnl_unlock(); sock_kfree_s(sk, pac, sizeof(*pac)); return 0; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 29b32206e494..6927f3fb5597 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -112,22 +112,20 @@ static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport, return c & (synq_hsize - 1); } -struct request_sock *inet6_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, +struct request_sock *inet6_csk_search_req(struct sock *sk, const __be16 rport, const struct in6_addr *raddr, const struct in6_addr *laddr, const int iif) { - const struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - struct request_sock *req, **prev; + struct request_sock *req; + u32 hash = inet6_synq_hash(raddr, rport, lopt->hash_rnd, + lopt->nr_table_entries); - for (prev = &lopt->syn_table[inet6_synq_hash(raddr, rport, - lopt->hash_rnd, - lopt->nr_table_entries)]; - (req = *prev) != NULL; - prev = &req->dl_next) { + spin_lock(&icsk->icsk_accept_queue.syn_wait_lock); + for (req = lopt->syn_table[hash]; req != NULL; req = req->dl_next) { const struct inet_request_sock *ireq = inet_rsk(req); if (ireq->ir_rmt_port == rport && @@ -135,13 +133,14 @@ struct request_sock *inet6_csk_search_req(const struct sock *sk, ipv6_addr_equal(&ireq->ir_v6_rmt_addr, raddr) && ipv6_addr_equal(&ireq->ir_v6_loc_addr, laddr) && (!ireq->ir_iif || ireq->ir_iif == iif)) { + atomic_inc(&req->rsk_refcnt); WARN_ON(req->sk != NULL); - *prevp = prev; - return req; + break; } } + spin_unlock(&icsk->icsk_accept_queue.syn_wait_lock); - return NULL; + return req; } EXPORT_SYMBOL_GPL(inet6_csk_search_req); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 051dffb49c90..033f17816ef4 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -23,11 +23,9 @@ #include <net/secure_seq.h> #include <net/ip.h> -static unsigned int inet6_ehashfn(struct net *net, - const struct in6_addr *laddr, - const u16 lport, - const struct in6_addr *faddr, - const __be16 fport) +u32 inet6_ehashfn(const struct net *net, + const struct in6_addr *laddr, const u16 lport, + const struct in6_addr *faddr, const __be16 fport) { static u32 inet6_ehash_secret __read_mostly; static u32 ipv6_hash_secret __read_mostly; @@ -44,54 +42,6 @@ static unsigned int inet6_ehashfn(struct net *net, inet6_ehash_secret + net_hash_mix(net)); } -static int inet6_sk_ehashfn(const struct sock *sk) -{ - const struct inet_sock *inet = inet_sk(sk); - const struct in6_addr *laddr = &sk->sk_v6_rcv_saddr; - const struct in6_addr *faddr = &sk->sk_v6_daddr; - const __u16 lport = inet->inet_num; - const __be16 fport = inet->inet_dport; - struct net *net = sock_net(sk); - - return inet6_ehashfn(net, laddr, lport, faddr, fport); -} - -int __inet6_hash(struct sock *sk, struct inet_timewait_sock *tw) -{ - struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; - int twrefcnt = 0; - - WARN_ON(!sk_unhashed(sk)); - - if (sk->sk_state == TCP_LISTEN) { - struct inet_listen_hashbucket *ilb; - - ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; - spin_lock(&ilb->lock); - __sk_nulls_add_node_rcu(sk, &ilb->head); - spin_unlock(&ilb->lock); - } else { - unsigned int hash; - struct hlist_nulls_head *list; - spinlock_t *lock; - - sk->sk_hash = hash = inet6_sk_ehashfn(sk); - list = &inet_ehash_bucket(hashinfo, hash)->chain; - lock = inet_ehash_lockp(hashinfo, hash); - spin_lock(lock); - __sk_nulls_add_node_rcu(sk, list); - if (tw) { - WARN_ON(sk->sk_hash != tw->tw_hash); - twrefcnt = inet_twsk_unhash(tw); - } - spin_unlock(lock); - } - - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - return twrefcnt; -} -EXPORT_SYMBOL(__inet6_hash); - /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM @@ -320,6 +270,6 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { return __inet_hash_connect(death_row, sk, inet6_sk_port_offset(sk), - __inet6_check_established, __inet6_hash); + __inet6_check_established); } EXPORT_SYMBOL_GPL(inet6_hash_connect); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index f45d6db50a45..457303886fd4 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -100,7 +100,6 @@ static void fl_free(struct ip6_flowlabel *fl) if (fl) { if (fl->share == IPV6_FL_S_PROCESS) put_pid(fl->owner.pid); - release_net(fl->fl_net); kfree(fl->opt); kfree_rcu(fl, rcu); } @@ -403,7 +402,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, } } - fl->fl_net = hold_net(net); + fl->fl_net = net; fl->expires = jiffies; err = fl6_renew(fl, freq->flr_linger, freq->flr_expires); if (err) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index ddd94eca19b3..41f84f76ad9d 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -64,12 +64,6 @@ MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("ip6tnl"); MODULE_ALIAS_NETDEV("ip6tnl0"); -#ifdef IP6_TNL_DEBUG -#define IP6_TNL_TRACE(x...) pr_debug("%s:" x "\n", __func__) -#else -#define IP6_TNL_TRACE(x...) do {;} while(0) -#endif - #define HASH_SIZE_SHIFT 5 #define HASH_SIZE (1 << HASH_SIZE_SHIFT) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 34b682617f50..4b9315aa273e 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -56,9 +56,7 @@ struct mr6_table { struct list_head list; -#ifdef CONFIG_NET_NS - struct net *net; -#endif + possible_net_t net; u32 id; struct sock *mroute6_sk; struct timer_list ipmr_expire_timer; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 8d766d9100cb..9b2cb1444230 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -117,6 +117,25 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, return opt; } +static bool setsockopt_needs_rtnl(int optname) +{ + switch (optname) { + case IPV6_ADD_MEMBERSHIP: + case IPV6_DROP_MEMBERSHIP: + case IPV6_JOIN_ANYCAST: + case IPV6_LEAVE_ANYCAST: + case MCAST_JOIN_GROUP: + case MCAST_LEAVE_GROUP: + case MCAST_JOIN_SOURCE_GROUP: + case MCAST_LEAVE_SOURCE_GROUP: + case MCAST_BLOCK_SOURCE: + case MCAST_UNBLOCK_SOURCE: + case MCAST_MSFILTER: + return true; + } + return false; +} + static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { @@ -124,6 +143,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, struct net *net = sock_net(sk); int val, valbool; int retv = -ENOPROTOOPT; + bool needs_rtnl = setsockopt_needs_rtnl(optname); if (optval == NULL) val = 0; @@ -140,6 +160,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (ip6_mroute_opt(optname)) return ip6_mroute_setsockopt(sk, optname, optval, optlen); + if (needs_rtnl) + rtnl_lock(); lock_sock(sk); switch (optname) { @@ -624,10 +646,10 @@ done: psin6 = (struct sockaddr_in6 *)&greq.gr_group; if (optname == MCAST_JOIN_GROUP) retv = ipv6_sock_mc_join(sk, greq.gr_interface, - &psin6->sin6_addr); + &psin6->sin6_addr); else retv = ipv6_sock_mc_drop(sk, greq.gr_interface, - &psin6->sin6_addr); + &psin6->sin6_addr); break; } case MCAST_JOIN_SOURCE_GROUP: @@ -660,7 +682,7 @@ done: psin6 = (struct sockaddr_in6 *)&greqs.gsr_group; retv = ipv6_sock_mc_join(sk, greqs.gsr_interface, - &psin6->sin6_addr); + &psin6->sin6_addr); /* prior join w/ different source is ok */ if (retv && retv != -EADDRINUSE) break; @@ -837,11 +859,15 @@ pref_skip_coa: } release_sock(sk); + if (needs_rtnl) + rtnl_unlock(); return retv; e_inval: release_sock(sk); + if (needs_rtnl) + rtnl_unlock(); return -EINVAL; } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 5ce107c8aab3..cbb66fd3da6d 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -140,6 +140,8 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) struct net *net = sock_net(sk); int err; + ASSERT_RTNL(); + if (!ipv6_addr_is_multicast(addr)) return -EINVAL; @@ -161,7 +163,6 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) mc_lst->next = NULL; mc_lst->addr = *addr; - rtnl_lock(); if (ifindex == 0) { struct rt6_info *rt; rt = rt6_lookup(net, addr, NULL, 0, 0); @@ -173,7 +174,6 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) dev = __dev_get_by_index(net, ifindex); if (dev == NULL) { - rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } @@ -190,7 +190,6 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) err = ipv6_dev_mc_inc(dev, addr); if (err) { - rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return err; } @@ -198,10 +197,9 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) mc_lst->next = np->ipv6_mc_list; rcu_assign_pointer(np->ipv6_mc_list, mc_lst); - rtnl_unlock(); - return 0; } +EXPORT_SYMBOL(ipv6_sock_mc_join); /* * socket leave on multicast group @@ -213,10 +211,11 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) struct ipv6_mc_socklist __rcu **lnk; struct net *net = sock_net(sk); + ASSERT_RTNL(); + if (!ipv6_addr_is_multicast(addr)) return -EINVAL; - rtnl_lock(); for (lnk = &np->ipv6_mc_list; (mc_lst = rtnl_dereference(*lnk)) != NULL; lnk = &mc_lst->next) { @@ -235,17 +234,16 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) __ipv6_dev_mc_dec(idev, &mc_lst->addr); } else (void) ip6_mc_leave_src(sk, mc_lst, NULL); - rtnl_unlock(); atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); return 0; } } - rtnl_unlock(); return -EADDRNOTAVAIL; } +EXPORT_SYMBOL(ipv6_sock_mc_drop); /* called with rcu_read_lock() */ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net, @@ -438,7 +436,7 @@ done: read_unlock_bh(&idev->lock); rcu_read_unlock(); if (leavegroup) - return ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group); + err = ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group); return err; } @@ -2907,20 +2905,32 @@ static int __net_init igmp6_net_init(struct net *net) inet6_sk(net->ipv6.igmp_sk)->hop_limit = 1; + err = inet_ctl_sock_create(&net->ipv6.mc_autojoin_sk, PF_INET6, + SOCK_RAW, IPPROTO_ICMPV6, net); + if (err < 0) { + pr_err("Failed to initialize the IGMP6 autojoin socket (err %d)\n", + err); + goto out_sock_create; + } + err = igmp6_proc_init(net); if (err) - goto out_sock_create; -out: - return err; + goto out_sock_create_autojoin; + return 0; + +out_sock_create_autojoin: + inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); out_sock_create: inet_ctl_sock_destroy(net->ipv6.igmp_sk); - goto out; +out: + return err; } static void __net_exit igmp6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.igmp_sk); + inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); igmp6_proc_exit(net); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 471ed24aabae..247ad7c298f7 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -84,6 +84,7 @@ do { \ static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); +static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey); static int ndisc_constructor(struct neighbour *neigh); static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); @@ -117,7 +118,9 @@ static const struct neigh_ops ndisc_direct_ops = { struct neigh_table nd_tbl = { .family = AF_INET6, .key_len = sizeof(struct in6_addr), + .protocol = cpu_to_be16(ETH_P_IPV6), .hash = ndisc_hash, + .key_eq = ndisc_key_eq, .constructor = ndisc_constructor, .pconstructor = pndisc_constructor, .pdestructor = pndisc_destructor, @@ -294,6 +297,11 @@ static u32 ndisc_hash(const void *pkey, return ndisc_hashfn(pkey, dev, hash_rnd); } +static bool ndisc_key_eq(const struct neighbour *n, const void *pkey) +{ + return neigh_key_eq128(n, pkey); +} + static int ndisc_constructor(struct neighbour *neigh) { struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key; diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index a069822936e6..ca6998345b42 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -25,14 +25,16 @@ config NF_CONNTRACK_IPV6 To compile it as a module, choose M here. If unsure, say N. +if NF_TABLES + config NF_TABLES_IPV6 - depends on NF_TABLES tristate "IPv6 nf_tables support" help This option enables the IPv6 support for nf_tables. +if NF_TABLES_IPV6 + config NFT_CHAIN_ROUTE_IPV6 - depends on NF_TABLES_IPV6 tristate "IPv6 nf_tables route chain support" help This option enables the "route" chain for IPv6 in nf_tables. This @@ -40,16 +42,18 @@ config NFT_CHAIN_ROUTE_IPV6 fields such as the source, destination, flowlabel, hop-limit and the packet mark. -config NF_REJECT_IPV6 - tristate "IPv6 packet rejection" - default m if NETFILTER_ADVANCED=n - config NFT_REJECT_IPV6 - depends on NF_TABLES_IPV6 select NF_REJECT_IPV6 default NFT_REJECT tristate +endif # NF_TABLES_IPV6 +endif # NF_TABLES + +config NF_REJECT_IPV6 + tristate "IPv6 packet rejection" + default m if NETFILTER_ADVANCED=n + config NF_LOG_IPV6 tristate "IPv6 packet logging" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 544b0a9da1b5..12331efd49cf 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -83,7 +83,8 @@ static int reject_tg6_check(const struct xt_tgchk_param *par) return -EINVAL; } else if (rejinfo->with == IP6T_TCP_RESET) { /* Must specify that it's a TCP packet */ - if (e->ipv6.proto != IPPROTO_TCP || + if (!(e->ipv6.flags & IP6T_F_PROTO) || + e->ipv6.proto != IPPROTO_TCP || (e->ipv6.invflags & XT_INV_PROTO)) { pr_info("TCP_RESET illegal for non-tcp\n"); return -EINVAL; diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index d05b36440e8b..3afdce03d94e 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -65,7 +65,7 @@ EXPORT_SYMBOL_GPL(nf_reject_ip6_tcphdr_get); struct ipv6hdr *nf_reject_ip6hdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, - __be16 protocol, int hoplimit) + __u8 protocol, int hoplimit) { struct ipv6hdr *ip6h; const struct ipv6hdr *oip6h = ipv6_hdr(oldskb); @@ -208,4 +208,39 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) } EXPORT_SYMBOL_GPL(nf_send_reset6); +static bool reject6_csum_ok(struct sk_buff *skb, int hook) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + int thoff; + __be16 fo; + u8 proto; + + if (skb->csum_bad) + return false; + + if (skb_csum_unnecessary(skb)) + return true; + + proto = ip6h->nexthdr; + thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo); + + if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0) + return false; + + return nf_ip6_checksum(skb, hook, thoff, proto) == 0; +} + +void nf_send_unreach6(struct net *net, struct sk_buff *skb_in, + unsigned char code, unsigned int hooknum) +{ + if (!reject6_csum_ok(skb_in, hooknum)) + return; + + if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL) + skb_in->dev = net->loopback_dev; + + icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0); +} +EXPORT_SYMBOL_GPL(nf_send_unreach6); + MODULE_LICENSE("GPL"); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index a2dfff6ff227..263a5164a6f5 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -77,8 +77,7 @@ static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, return 0; } -int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len) +int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index dae7f1a1e464..a5287b3582a4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -32,7 +32,7 @@ #include <linux/netfilter_ipv6.h> #include <linux/skbuff.h> #include <linux/compat.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/net_namespace.h> @@ -456,9 +456,8 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) * we return it, otherwise we block. */ -static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, - int noblock, int flags, int *addr_len) +static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); @@ -730,8 +729,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd, return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb); } -static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len) +static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4688bd4d7f59..58c0e6a4d15d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -194,7 +194,6 @@ static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, - .protocol = cpu_to_be16(ETH_P_IPV6), .gc = ip6_dst_gc, .gc_thresh = 1024, .check = ip6_dst_check, @@ -236,7 +235,6 @@ static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst, static struct dst_ops ip6_dst_blackhole_ops = { .family = AF_INET6, - .protocol = cpu_to_be16(ETH_P_IPV6), .destroy = ip6_dst_destroy, .check = ip6_dst_check, .mtu = ip6_blackhole_mtu, @@ -2400,6 +2398,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, + [RTA_PREF] = { .type = NLA_U8 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2407,6 +2406,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, { struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; + unsigned int pref; int err; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy); @@ -2482,6 +2482,14 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); } + if (tb[RTA_PREF]) { + pref = nla_get_u8(tb[RTA_PREF]); + if (pref != ICMPV6_ROUTER_PREF_LOW && + pref != ICMPV6_ROUTER_PREF_HIGH) + pref = ICMPV6_ROUTER_PREF_MEDIUM; + cfg->fc_flags |= RTF_PREF(pref); + } + err = 0; errout: return err; @@ -2585,7 +2593,8 @@ static inline size_t rt6_nlmsg_size(void) + nla_total_size(4) /* RTA_PRIORITY */ + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */ + nla_total_size(sizeof(struct rta_cacheinfo)) - + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */ + + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */ + + nla_total_size(1); /* RTA_PREF */ } static int rt6_fill_node(struct net *net, @@ -2726,6 +2735,9 @@ static int rt6_fill_node(struct net *net, if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) goto nla_put_failure; + if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags))) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 7337fc7947e2..2819137fc87d 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -49,11 +49,12 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct sock *child; child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst); - if (child) + if (child) { + atomic_set(&req->rsk_refcnt, 1); inet_csk_reqsk_queue_add(sk, req, child); - else + } else { reqsk_free(req); - + } return child; } @@ -189,13 +190,14 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp6_request_sock_ops); + req = inet_reqsk_alloc(&tcp6_request_sock_ops, sk); if (!req) goto out; ireq = inet_rsk(req); treq = tcp_rsk(req); - treq->listener = NULL; + treq->tfo_listener = false; + ireq->ireq_family = AF_INET6; if (security_inet_conn_request(sk, skb, req)) goto out_free; @@ -220,7 +222,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->ir_mark = inet_request_mark(sk, skb); - req->expires = 0UL; req->num_retrans = 0; ireq->snd_wscale = tcp_opt.snd_wscale; ireq->sack_ok = tcp_opt.sack_ok; diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index c5c10fafcfe2..30f5a4ad04eb 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -54,6 +54,20 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "idgen_retries", + .data = &init_net.ipv6.sysctl.idgen_retries, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "idgen_delay", + .data = &init_net.ipv6.sysctl.idgen_delay, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, { } }; @@ -93,6 +107,8 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[2].data = &net->ipv6.sysctl.flowlabel_consistency; ipv6_table[3].data = &net->ipv6.sysctl.auto_flowlabels; ipv6_table[4].data = &net->ipv6.sysctl.fwmark_reflect; + ipv6_table[5].data = &net->ipv6.sysctl.idgen_retries; + ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5d46832c6f72..4a4e6d30c448 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -104,19 +104,6 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) } } -static void tcp_v6_hash(struct sock *sk) -{ - if (sk->sk_state != TCP_CLOSE) { - if (inet_csk(sk)->icsk_af_ops == &ipv6_mapped) { - tcp_prot.hash(sk); - return; - } - local_bh_disable(); - __inet6_hash(sk, NULL); - local_bh_enable(); - } -} - static __u32 tcp_v6_init_sequence(const struct sk_buff *skb) { return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, @@ -233,11 +220,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tp->af_specific = &tcp_sock_ipv6_specific; #endif goto failure; - } else { - ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, - &sk->sk_v6_rcv_saddr); } + np->saddr = sk->sk_v6_rcv_saddr; return err; } @@ -340,18 +324,20 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); + struct net *net = dev_net(skb->dev); + struct request_sock *fastopen; struct ipv6_pinfo *np; - struct sock *sk; - int err; struct tcp_sock *tp; - struct request_sock *fastopen; __u32 seq, snd_una; - struct net *net = dev_net(skb->dev); + struct sock *sk; + int err; - sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr, - th->dest, &hdr->saddr, th->source, skb->dev->ifindex); + sk = __inet6_lookup_established(net, &tcp_hashinfo, + &hdr->daddr, th->dest, + &hdr->saddr, ntohs(th->source), + skb->dev->ifindex); - if (sk == NULL) { + if (!sk) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; @@ -361,6 +347,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, inet_twsk_put(inet_twsk(sk)); return; } + seq = ntohl(th->seq); + if (sk->sk_state == TCP_NEW_SYN_RECV) + return tcp_req_err(sk, seq); bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) @@ -375,7 +364,6 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } tp = tcp_sk(sk); - seq = ntohl(th->seq); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = tp->fastopen_rsk; snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; @@ -419,31 +407,6 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* Might be for an request_sock */ switch (sk->sk_state) { - struct request_sock *req, **prev; - case TCP_LISTEN: - if (sock_owned_by_user(sk)) - goto out; - - /* Note : We use inet6_iif() here, not tcp_v6_iif() */ - req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr, - &hdr->saddr, inet6_iif(skb)); - if (!req) - goto out; - - /* ICMPs are not backlogged, hence we cannot get - * an established socket here. - */ - WARN_ON(req->sk != NULL); - - if (seq != tcp_rsk(req)->snt_isn) { - NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - goto out; - } - - inet_csk_reqsk_queue_drop(sk, req, prev); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); - goto out; - case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is @@ -734,8 +697,6 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk, ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; - ireq->ir_iif = sk->sk_bound_dev_if; - /* So that link locals have meaning */ if (!sk->sk_bound_dev_if && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) @@ -749,6 +710,7 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk, atomic_inc(&skb->users); ireq->pktopts = skb; } + ireq->ireq_family = AF_INET6; } static struct dst_entry *tcp_v6_route_req(struct sock *sk, struct flowi *fl, @@ -997,17 +959,19 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) { - struct request_sock *req, **prev; const struct tcphdr *th = tcp_hdr(skb); + struct request_sock *req; struct sock *nsk; /* Find possible connection requests. */ - req = inet6_csk_search_req(sk, &prev, th->source, + req = inet6_csk_search_req(sk, th->source, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb)); - if (req) - return tcp_check_req(sk, skb, req, prev, false); - + if (req) { + nsk = tcp_check_req(sk, skb, req, false); + reqsk_put(req); + return nsk; + } nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, ntohs(th->dest), @@ -1079,11 +1043,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr); - - ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - - newsk->sk_v6_rcv_saddr = newnp->saddr; + newnp->saddr = newsk->sk_v6_rcv_saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; newsk->sk_backlog_rcv = tcp_v4_do_rcv; @@ -1232,7 +1192,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, tcp_done(newsk); goto out; } - __inet6_hash(newsk, NULL); + __inet_hash(newsk, NULL); return newsk; @@ -1584,7 +1544,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb) if (sk) { skb->sk = sk; skb->destructor = sock_edemux; - if (sk->sk_state != TCP_TIME_WAIT) { + if (sk_fullsock(sk)) { struct dst_entry *dst = sk->sk_rx_dst; if (dst) @@ -1689,9 +1649,9 @@ static void tcp_v6_destroy_sock(struct sock *sk) #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, - const struct sock *sk, struct request_sock *req, int i, kuid_t uid) + struct request_sock *req, int i, kuid_t uid) { - int ttd = req->expires - jiffies; + long ttd = req->rsk_timer.expires - jiffies; const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr; const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr; @@ -1827,7 +1787,7 @@ static int tcp6_seq_show(struct seq_file *seq, void *v) get_tcp6_sock(seq, v, st->num); break; case TCP_SEQ_STATE_OPENREQ: - get_openreq6(seq, st->syn_wait_sk, v, st->num, st->uid); + get_openreq6(seq, v, st->num, st->uid); break; } out: @@ -1891,7 +1851,7 @@ struct proto tcpv6_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, - .hash = tcp_v6_hash, + .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index c1ab77105b4c..d883c9204c01 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -41,8 +41,8 @@ static int tcp6_gro_complete(struct sk_buff *skb, int thoff) return tcp_gro_complete(skb); } -struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, - netdev_features_t features) +static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, + netdev_features_t features) { struct tcphdr *th; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d048d46779fc..7fe0329c0d37 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -53,11 +53,11 @@ #include <trace/events/skb.h> #include "udp_impl.h" -static unsigned int udp6_ehashfn(struct net *net, - const struct in6_addr *laddr, - const u16 lport, - const struct in6_addr *faddr, - const __be16 fport) +static u32 udp6_ehashfn(const struct net *net, + const struct in6_addr *laddr, + const u16 lport, + const struct in6_addr *faddr, + const __be16 fport) { static u32 udp6_ehash_secret __read_mostly; static u32 udp_ipv6_hash_secret __read_mostly; @@ -104,9 +104,9 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) return 0; } -static unsigned int udp6_portaddr_hash(struct net *net, - const struct in6_addr *addr6, - unsigned int port) +static u32 udp6_portaddr_hash(const struct net *net, + const struct in6_addr *addr6, + unsigned int port) { unsigned int hash, mix = net_hash_mix(net); @@ -391,8 +391,7 @@ EXPORT_SYMBOL_GPL(udp6_lib_lookup); * return it, otherwise we block. */ -int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, +int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); @@ -1101,8 +1100,7 @@ out: return err; } -int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len) +int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; struct udp_sock *up = udp_sk(sk); @@ -1164,12 +1162,12 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, do_udp_sendmsg: if (__ipv6_only_sock(sk)) return -ENETUNREACH; - return udp_sendmsg(iocb, sk, msg, len); + return udp_sendmsg(sk, msg, len); } } if (up->pending == AF_INET) - return udp_sendmsg(iocb, sk, msg, len); + return udp_sendmsg(sk, msg, len); /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index c779c3c90b9d..0682c031ccdc 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -23,10 +23,9 @@ int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #endif -int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len); -int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, int *addr_len); +int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); +int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, + int flags, int *addr_len); int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); void udpv6_destroy_sock(struct sock *sk); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 8d2d01b4800a..11dbcc1790d2 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -293,7 +293,6 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, static struct dst_ops xfrm6_dst_ops = { .family = AF_INET6, - .protocol = cpu_to_be16(ETH_P_IPV6), .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, .redirect = xfrm6_redirect, |