diff options
Diffstat (limited to 'net/ipv4/devinet.c')
| -rw-r--r-- | net/ipv4/devinet.c | 1778 |
1 files changed, 1191 insertions, 587 deletions
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 8d48c392adcc..942a887bf089 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * NET3 IP device support routines. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Derived from the IP parts of dev.c 1.0.19 * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> @@ -26,12 +22,13 @@ */ -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> +#include <linux/sched/signal.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> @@ -49,6 +46,7 @@ #include <linux/notifier.h> #include <linux/inetdevice.h> #include <linux/igmp.h> +#include "igmp_internal.h" #include <linux/slab.h> #include <linux/hash.h> #ifdef CONFIG_SYSCTL @@ -65,7 +63,10 @@ #include <net/net_namespace.h> #include <net/addrconf.h> -#include "fib_lookup.h" +#define IPV6ONLY_FLAGS \ + (IFA_F_NODAD | IFA_F_OPTIMISTIC | IFA_F_DADFAILED | \ + IFA_F_HOMEADDRESS | IFA_F_TENTATIVE | \ + IFA_F_MANAGETEMPADDR | IFA_F_STABLE_PRIVACY) static struct ipv4_devconf ipv4_devconf = { .data = { @@ -73,6 +74,9 @@ static struct ipv4_devconf ipv4_devconf = { [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, + [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, + [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, + [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; @@ -83,6 +87,9 @@ static struct ipv4_devconf ipv4_devconf_dflt = { [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1, + [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, + [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, + [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; @@ -95,17 +102,18 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_BROADCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, + [IFA_FLAGS] = { .type = NLA_U32 }, + [IFA_RT_PRIORITY] = { .type = NLA_U32 }, + [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, + [IFA_PROTO] = { .type = NLA_U8 }, }; #define IN4_ADDR_HSIZE_SHIFT 8 #define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT) -static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE]; -static DEFINE_SPINLOCK(inet_addr_hash_lock); - -static u32 inet_addr_hash(struct net *net, __be32 addr) +static u32 inet_addr_hash(const struct net *net, __be32 addr) { - u32 val = (__force u32) addr ^ net_hash_mix(net); + u32 val = __ipv4_addr_hash(addr, net_hash_mix(net)); return hash_32(val, IN4_ADDR_HSIZE_SHIFT); } @@ -114,16 +122,14 @@ static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa) { u32 hash = inet_addr_hash(net, ifa->ifa_local); - spin_lock(&inet_addr_hash_lock); - hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]); - spin_unlock(&inet_addr_hash_lock); + ASSERT_RTNL(); + hlist_add_head_rcu(&ifa->addr_lst, &net->ipv4.inet_addr_lst[hash]); } static void inet_hash_remove(struct in_ifaddr *ifa) { - spin_lock(&inet_addr_hash_lock); - hlist_del_init_rcu(&ifa->hash); - spin_unlock(&inet_addr_hash_lock); + ASSERT_RTNL(); + hlist_del_init_rcu(&ifa->addr_lst); } /** @@ -136,22 +142,12 @@ static void inet_hash_remove(struct in_ifaddr *ifa) */ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) { - u32 hash = inet_addr_hash(net, addr); struct net_device *result = NULL; struct in_ifaddr *ifa; rcu_read_lock(); - hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) { - if (ifa->ifa_local == addr) { - struct net_device *dev = ifa->ifa_dev->dev; - - if (!net_eq(dev_net(dev), net)) - continue; - result = dev; - break; - } - } - if (!result) { + ifa = inet_lookup_ifaddr_rcu(net, addr); + if (!ifa) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res = { 0 }; struct fib_table *local; @@ -164,6 +160,8 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) && res.type == RTN_LOCAL) result = FIB_RES_DEV(res); + } else { + result = ifa->ifa_dev->dev; } if (result && devref) dev_hold(result); @@ -172,17 +170,33 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) } EXPORT_SYMBOL(__ip_dev_find); +/* called under RCU lock */ +struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr) +{ + u32 hash = inet_addr_hash(net, addr); + struct in_ifaddr *ifa; + + hlist_for_each_entry_rcu(ifa, &net->ipv4.inet_addr_lst[hash], addr_lst) + if (ifa->ifa_local == addr) + return ifa; + + return NULL; +} + static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); -static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, +static BLOCKING_NOTIFIER_HEAD(inetaddr_validator_chain); +static void inet_del_ifa(struct in_device *in_dev, + struct in_ifaddr __rcu **ifap, int destroy); #ifdef CONFIG_SYSCTL -static void devinet_sysctl_register(struct in_device *idev); +static int devinet_sysctl_register(struct in_device *idev); static void devinet_sysctl_unregister(struct in_device *idev); #else -static void devinet_sysctl_register(struct in_device *idev) +static int devinet_sysctl_register(struct in_device *idev) { + return 0; } static void devinet_sysctl_unregister(struct in_device *idev) { @@ -191,22 +205,45 @@ static void devinet_sysctl_unregister(struct in_device *idev) /* Locks all the inet devices. */ -static struct in_ifaddr *inet_alloc_ifa(void) +static struct in_ifaddr *inet_alloc_ifa(struct in_device *in_dev) { - return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL); + struct in_ifaddr *ifa; + + ifa = kzalloc(sizeof(*ifa), GFP_KERNEL_ACCOUNT); + if (!ifa) + return NULL; + + in_dev_hold(in_dev); + ifa->ifa_dev = in_dev; + + INIT_HLIST_NODE(&ifa->addr_lst); + + return ifa; } static void inet_rcu_free_ifa(struct rcu_head *head) { struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head); - if (ifa->ifa_dev) - in_dev_put(ifa->ifa_dev); + + in_dev_put(ifa->ifa_dev); kfree(ifa); } static void inet_free_ifa(struct in_ifaddr *ifa) { - call_rcu(&ifa->rcu_head, inet_rcu_free_ifa); + /* Our reference to ifa->ifa_dev must be freed ASAP + * to release the reference to the netdev the same way. + * in_dev_put() -> in_dev_finish_destroy() -> netdev_put() + */ + call_rcu_hurry(&ifa->rcu_head, inet_rcu_free_ifa); +} + +static void in_dev_free_rcu(struct rcu_head *head) +{ + struct in_device *idev = container_of(head, struct in_device, rcu_head); + + kfree(rcu_dereference_protected(idev->mc_hash, 1)); + kfree(idev); } void in_dev_finish_destroy(struct in_device *idev) @@ -215,21 +252,21 @@ void in_dev_finish_destroy(struct in_device *idev) WARN_ON(idev->ifa_list); WARN_ON(idev->mc_list); - kfree(rcu_dereference_protected(idev->mc_hash, 1)); #ifdef NET_REFCNT_DEBUG pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL"); #endif - dev_put(dev); + netdev_put(dev, &idev->dev_tracker); if (!idev->dead) pr_err("Freeing alive in_device %p\n", idev); else - kfree(idev); + call_rcu(&idev->rcu_head, in_dev_free_rcu); } EXPORT_SYMBOL(in_dev_finish_destroy); static struct in_device *inetdev_init(struct net_device *dev) { struct in_device *in_dev; + int err = -ENOMEM; ASSERT_RTNL(); @@ -244,37 +281,40 @@ static struct in_device *inetdev_init(struct net_device *dev) if (!in_dev->arp_parms) goto out_kfree; if (IPV4_DEVCONF(in_dev->cnf, FORWARDING)) - dev_disable_lro(dev); + netif_disable_lro(dev); /* Reference in_dev->dev */ - dev_hold(dev); + netdev_hold(dev, &in_dev->dev_tracker, GFP_KERNEL); /* Account for reference dev->ip_ptr (below) */ - in_dev_hold(in_dev); - - devinet_sysctl_register(in_dev); - ip_mc_init_dev(in_dev); - if (dev->flags & IFF_UP) - ip_mc_up(in_dev); + refcount_set(&in_dev->refcnt, 1); + + if (dev != blackhole_netdev) { + err = devinet_sysctl_register(in_dev); + if (err) { + in_dev->dead = 1; + neigh_parms_release(&arp_tbl, in_dev->arp_parms); + in_dev_put(in_dev); + in_dev = NULL; + goto out; + } + ip_mc_init_dev(in_dev); + if (dev->flags & IFF_UP) + ip_mc_up(in_dev); + } /* we can receive as soon as ip_ptr is set -- do this last */ rcu_assign_pointer(dev->ip_ptr, in_dev); out: - return in_dev; + return in_dev ?: ERR_PTR(err); out_kfree: kfree(in_dev); in_dev = NULL; goto out; } -static void in_dev_rcu_put(struct rcu_head *head) -{ - struct in_device *idev = container_of(head, struct in_device, rcu_head); - in_dev_put(idev); -} - static void inetdev_destroy(struct in_device *in_dev) { - struct in_ifaddr *ifa; struct net_device *dev; + struct in_ifaddr *ifa; ASSERT_RTNL(); @@ -284,7 +324,7 @@ static void inetdev_destroy(struct in_device *in_dev) ip_mc_destroy_dev(in_dev); - while ((ifa = in_dev->ifa_list) != NULL) { + while ((ifa = rtnl_dereference(in_dev->ifa_list)) != NULL) { inet_del_ifa(in_dev, &in_dev->ifa_list, 0); inet_free_ifa(ifa); } @@ -295,46 +335,66 @@ static void inetdev_destroy(struct in_device *in_dev) neigh_parms_release(&arp_tbl, in_dev->arp_parms); arp_ifdown(dev); - call_rcu(&in_dev->rcu_head, in_dev_rcu_put); + in_dev_put(in_dev); } +static int __init inet_blackhole_dev_init(void) +{ + struct in_device *in_dev; + + rtnl_lock(); + in_dev = inetdev_init(blackhole_netdev); + rtnl_unlock(); + + return PTR_ERR_OR_ZERO(in_dev); +} +late_initcall(inet_blackhole_dev_init); + int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b) { + const struct in_ifaddr *ifa; + rcu_read_lock(); - for_primary_ifa(in_dev) { + in_dev_for_each_ifa_rcu(ifa, in_dev) { if (inet_ifa_match(a, ifa)) { if (!b || inet_ifa_match(b, ifa)) { rcu_read_unlock(); return 1; } } - } endfor_ifa(in_dev); + } rcu_read_unlock(); return 0; } -static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, - int destroy, struct nlmsghdr *nlh, u32 portid) +static void __inet_del_ifa(struct in_device *in_dev, + struct in_ifaddr __rcu **ifap, + int destroy, struct nlmsghdr *nlh, u32 portid) { struct in_ifaddr *promote = NULL; - struct in_ifaddr *ifa, *ifa1 = *ifap; - struct in_ifaddr *last_prim = in_dev->ifa_list; + struct in_ifaddr *ifa, *ifa1; + struct in_ifaddr __rcu **last_prim; struct in_ifaddr *prev_prom = NULL; int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev); ASSERT_RTNL(); + ifa1 = rtnl_dereference(*ifap); + last_prim = ifap; + if (in_dev->dead) + goto no_promotions; + /* 1. Deleting primary ifaddr forces deletion all secondaries * unless alias promotion is set **/ if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) { - struct in_ifaddr **ifap1 = &ifa1->ifa_next; + struct in_ifaddr __rcu **ifap1 = &ifa1->ifa_next; - while ((ifa = *ifap1) != NULL) { + while ((ifa = rtnl_dereference(*ifap1)) != NULL) { if (!(ifa->ifa_flags & IFA_F_SECONDARY) && ifa1->ifa_scope <= ifa->ifa_scope) - last_prim = ifa; + last_prim = &ifa->ifa_next; if (!(ifa->ifa_flags & IFA_F_SECONDARY) || ifa1->ifa_mask != ifa->ifa_mask || @@ -364,12 +424,13 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, * and later to add them back with new prefsrc. Do this * while all addresses are on the device list. */ - for (ifa = promote; ifa; ifa = ifa->ifa_next) { + for (ifa = promote; ifa; ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa)) fib_del_ifaddr(ifa, ifa1); } +no_promotions: /* 2. Unlink it */ *ifap = ifa1->ifa_next; @@ -389,19 +450,25 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1); if (promote) { - struct in_ifaddr *next_sec = promote->ifa_next; + struct in_ifaddr *next_sec; + next_sec = rtnl_dereference(promote->ifa_next); if (prev_prom) { - prev_prom->ifa_next = promote->ifa_next; - promote->ifa_next = last_prim->ifa_next; - last_prim->ifa_next = promote; + struct in_ifaddr *last_sec; + + rcu_assign_pointer(prev_prom->ifa_next, next_sec); + + last_sec = rtnl_dereference(*last_prim); + rcu_assign_pointer(promote->ifa_next, last_sec); + rcu_assign_pointer(*last_prim, promote); } promote->ifa_flags &= ~IFA_F_SECONDARY; rtmsg_ifa(RTM_NEWADDR, promote, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote); - for (ifa = next_sec; ifa; ifa = ifa->ifa_next) { + for (ifa = next_sec; ifa; + ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) continue; @@ -413,34 +480,35 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, inet_free_ifa(ifa1); } -static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, +static void inet_del_ifa(struct in_device *in_dev, + struct in_ifaddr __rcu **ifap, int destroy) { __inet_del_ifa(in_dev, ifap, destroy, NULL, 0); } -static void check_lifetime(struct work_struct *work); - -static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime); - static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, - u32 portid) + u32 portid, struct netlink_ext_ack *extack) { + struct in_ifaddr __rcu **last_primary, **ifap; struct in_device *in_dev = ifa->ifa_dev; - struct in_ifaddr *ifa1, **ifap, **last_primary; + struct net *net = dev_net(in_dev->dev); + struct in_validator_info ivi; + struct in_ifaddr *ifa1; + int ret; ASSERT_RTNL(); - if (!ifa->ifa_local) { - inet_free_ifa(ifa); - return 0; - } - ifa->ifa_flags &= ~IFA_F_SECONDARY; last_primary = &in_dev->ifa_list; - for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL; - ifap = &ifa1->ifa_next) { + /* Don't set IPv6 only flags to IPv4 addresses */ + ifa->ifa_flags &= ~IPV6ONLY_FLAGS; + + ifap = &in_dev->ifa_list; + ifa1 = rtnl_dereference(*ifap); + + while (ifa1) { if (!(ifa1->ifa_flags & IFA_F_SECONDARY) && ifa->ifa_scope <= ifa1->ifa_scope) last_primary = &ifa1->ifa_next; @@ -451,25 +519,45 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, return -EEXIST; } if (ifa1->ifa_scope != ifa->ifa_scope) { + NL_SET_ERR_MSG(extack, "ipv4: Invalid scope value"); inet_free_ifa(ifa); return -EINVAL; } ifa->ifa_flags |= IFA_F_SECONDARY; } + + ifap = &ifa1->ifa_next; + ifa1 = rtnl_dereference(*ifap); } - if (!(ifa->ifa_flags & IFA_F_SECONDARY)) { - net_srandom(ifa->ifa_local); - ifap = last_primary; + /* Allow any devices that wish to register ifaddr validtors to weigh + * in now, before changes are committed. The rntl lock is serializing + * access here, so the state should not change between a validator call + * and a final notify on commit. This isn't invoked on promotion under + * the assumption that validators are checking the address itself, and + * not the flags. + */ + ivi.ivi_addr = ifa->ifa_address; + ivi.ivi_dev = ifa->ifa_dev; + ivi.extack = extack; + ret = blocking_notifier_call_chain(&inetaddr_validator_chain, + NETDEV_UP, &ivi); + ret = notifier_to_errno(ret); + if (ret) { + inet_free_ifa(ifa); + return ret; } - ifa->ifa_next = *ifap; - *ifap = ifa; + if (!(ifa->ifa_flags & IFA_F_SECONDARY)) + ifap = last_primary; + + rcu_assign_pointer(ifa->ifa_next, *ifap); + rcu_assign_pointer(*ifap, ifa); inet_hash_insert(dev_net(in_dev->dev), ifa); - cancel_delayed_work(&check_lifetime_work); - schedule_delayed_work(&check_lifetime_work, 0); + cancel_delayed_work(&net->ipv4.addr_chk_work); + queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, 0); /* Send message first, then call notifier. Notifier will trigger FIB update, so that @@ -482,25 +570,21 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, static int inet_insert_ifa(struct in_ifaddr *ifa) { - return __inet_insert_ifa(ifa, NULL, 0); + if (!ifa->ifa_local) { + inet_free_ifa(ifa); + return 0; + } + + return __inet_insert_ifa(ifa, NULL, 0, NULL); } static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) { - struct in_device *in_dev = __in_dev_get_rtnl(dev); - - ASSERT_RTNL(); + struct in_device *in_dev = __in_dev_get_rtnl_net(dev); - if (!in_dev) { - inet_free_ifa(ifa); - return -ENOBUFS; - } ipv4_devconf_setall(in_dev); - if (ifa->ifa_dev != in_dev) { - WARN_ON(ifa->ifa_dev); - in_dev_hold(in_dev); - ifa->ifa_dev = in_dev; - } + neigh_parms_data_state_setall(in_dev->arp_parms); + if (ipv4_is_loopback(ifa->ifa_local)) ifa->ifa_scope = RT_SCOPE_HOST; return inet_insert_ifa(ifa); @@ -528,41 +612,75 @@ EXPORT_SYMBOL(inetdev_by_index); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask) { + struct in_ifaddr *ifa; + ASSERT_RTNL(); - for_primary_ifa(in_dev) { + in_dev_for_each_ifa_rtnl(ifa, in_dev) { if (ifa->ifa_mask == mask && inet_ifa_match(prefix, ifa)) return ifa; - } endfor_ifa(in_dev); + } return NULL; } -static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) +static int ip_mc_autojoin_config(struct net *net, bool join, + const struct in_ifaddr *ifa) +{ +#if defined(CONFIG_IP_MULTICAST) + struct ip_mreqn mreq = { + .imr_multiaddr.s_addr = ifa->ifa_address, + .imr_ifindex = ifa->ifa_dev->dev->ifindex, + }; + struct sock *sk = net->ipv4.mc_autojoin_sk; + int ret; + + ASSERT_RTNL_NET(net); + + lock_sock(sk); + if (join) + ret = ip_mc_join_group(sk, &mreq); + else + ret = ip_mc_leave_group(sk, &mreq); + release_sock(sk); + + return ret; +#else + return -EOPNOTSUPP; +#endif +} + +static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); + struct in_ifaddr __rcu **ifap; struct nlattr *tb[IFA_MAX+1]; struct in_device *in_dev; struct ifaddrmsg *ifm; - struct in_ifaddr *ifa, **ifap; - int err = -EINVAL; - - ASSERT_RTNL(); + struct in_ifaddr *ifa; + int err; - err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy); + err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, + ifa_ipv4_policy, extack); if (err < 0) - goto errout; + goto out; ifm = nlmsg_data(nlh); + + rtnl_net_lock(net); + in_dev = inetdev_by_index(net, ifm->ifa_index); - if (in_dev == NULL) { + if (!in_dev) { + NL_SET_ERR_MSG(extack, "ipv4: Device not found"); err = -ENODEV; - goto errout; + goto unlock; } - for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; + for (ifap = &in_dev->ifa_list; + (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && - ifa->ifa_local != nla_get_be32(tb[IFA_LOCAL])) + ifa->ifa_local != nla_get_in_addr(tb[IFA_LOCAL])) continue; if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label)) @@ -570,70 +688,81 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) if (tb[IFA_ADDRESS] && (ifm->ifa_prefixlen != ifa->ifa_prefixlen || - !inet_ifa_match(nla_get_be32(tb[IFA_ADDRESS]), ifa))) + !inet_ifa_match(nla_get_in_addr(tb[IFA_ADDRESS]), ifa))) continue; + if (ipv4_is_multicast(ifa->ifa_address)) + ip_mc_autojoin_config(net, false, ifa); + __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid); - return 0; + goto unlock; } + NL_SET_ERR_MSG(extack, "ipv4: Address not found"); err = -EADDRNOTAVAIL; -errout: +unlock: + rtnl_net_unlock(net); +out: return err; } -#define INFINITY_LIFE_TIME 0xFFFFFFFF - static void check_lifetime(struct work_struct *work) { unsigned long now, next, next_sec, next_sched; struct in_ifaddr *ifa; struct hlist_node *n; + struct net *net; int i; + net = container_of(to_delayed_work(work), struct net, ipv4.addr_chk_work); now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); for (i = 0; i < IN4_ADDR_HSIZE; i++) { + struct hlist_head *head = &net->ipv4.inet_addr_lst[i]; bool change_needed = false; rcu_read_lock(); - hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) { - unsigned long age; - - if (ifa->ifa_flags & IFA_F_PERMANENT) + hlist_for_each_entry_rcu(ifa, head, addr_lst) { + unsigned long age, tstamp; + u32 preferred_lft; + u32 valid_lft; + u32 flags; + + flags = READ_ONCE(ifa->ifa_flags); + if (flags & IFA_F_PERMANENT) continue; + preferred_lft = READ_ONCE(ifa->ifa_preferred_lft); + valid_lft = READ_ONCE(ifa->ifa_valid_lft); + tstamp = READ_ONCE(ifa->ifa_tstamp); /* We try to batch several events at once. */ - age = (now - ifa->ifa_tstamp + + age = (now - tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; - if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && - age >= ifa->ifa_valid_lft) { + if (valid_lft != INFINITY_LIFE_TIME && + age >= valid_lft) { change_needed = true; - } else if (ifa->ifa_preferred_lft == + } else if (preferred_lft == INFINITY_LIFE_TIME) { continue; - } else if (age >= ifa->ifa_preferred_lft) { - if (time_before(ifa->ifa_tstamp + - ifa->ifa_valid_lft * HZ, next)) - next = ifa->ifa_tstamp + - ifa->ifa_valid_lft * HZ; + } else if (age >= preferred_lft) { + if (time_before(tstamp + valid_lft * HZ, next)) + next = tstamp + valid_lft * HZ; - if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) + if (!(flags & IFA_F_DEPRECATED)) change_needed = true; - } else if (time_before(ifa->ifa_tstamp + - ifa->ifa_preferred_lft * HZ, + } else if (time_before(tstamp + preferred_lft * HZ, next)) { - next = ifa->ifa_tstamp + - ifa->ifa_preferred_lft * HZ; + next = tstamp + preferred_lft * HZ; } } rcu_read_unlock(); if (!change_needed) continue; - rtnl_lock(); - hlist_for_each_entry_safe(ifa, n, &inet_addr_lst[i], hash) { + + rtnl_net_lock(net); + hlist_for_each_entry_safe(ifa, n, head, addr_lst) { unsigned long age; if (ifa->ifa_flags & IFA_F_PERMANENT) @@ -645,15 +774,19 @@ static void check_lifetime(struct work_struct *work) if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_valid_lft) { - struct in_ifaddr **ifap; + struct in_ifaddr __rcu **ifap; + struct in_ifaddr *tmp; - for (ifap = &ifa->ifa_dev->ifa_list; - *ifap != NULL; ifap = &(*ifap)->ifa_next) { - if (*ifap == ifa) { + ifap = &ifa->ifa_dev->ifa_list; + tmp = rtnl_net_dereference(net, *ifap); + while (tmp) { + if (tmp == ifa) { inet_del_ifa(ifa->ifa_dev, ifap, 1); break; } + ifap = &tmp->ifa_next; + tmp = rtnl_net_dereference(net, *ifap); } } else if (ifa->ifa_preferred_lft != INFINITY_LIFE_TIME && @@ -663,7 +796,7 @@ static void check_lifetime(struct work_struct *work) rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } } - rtnl_unlock(); + rtnl_net_unlock(net); } next_sec = round_jiffies_up(next); @@ -678,64 +811,98 @@ static void check_lifetime(struct work_struct *work) if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX)) next_sched = now + ADDRCONF_TIMER_FUZZ_MAX; - schedule_delayed_work(&check_lifetime_work, next_sched - now); + queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, + next_sched - now); } static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft, __u32 prefered_lft) { unsigned long timeout; + u32 flags; - ifa->ifa_flags &= ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); + flags = ifa->ifa_flags & ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); timeout = addrconf_timeout_fixup(valid_lft, HZ); if (addrconf_finite_timeout(timeout)) - ifa->ifa_valid_lft = timeout; + WRITE_ONCE(ifa->ifa_valid_lft, timeout); else - ifa->ifa_flags |= IFA_F_PERMANENT; + flags |= IFA_F_PERMANENT; timeout = addrconf_timeout_fixup(prefered_lft, HZ); if (addrconf_finite_timeout(timeout)) { if (timeout == 0) - ifa->ifa_flags |= IFA_F_DEPRECATED; - ifa->ifa_preferred_lft = timeout; + flags |= IFA_F_DEPRECATED; + WRITE_ONCE(ifa->ifa_preferred_lft, timeout); } - ifa->ifa_tstamp = jiffies; + WRITE_ONCE(ifa->ifa_flags, flags); + WRITE_ONCE(ifa->ifa_tstamp, jiffies); if (!ifa->ifa_cstamp) - ifa->ifa_cstamp = ifa->ifa_tstamp; + WRITE_ONCE(ifa->ifa_cstamp, ifa->ifa_tstamp); } -static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, - __u32 *pvalid_lft, __u32 *pprefered_lft) +static int inet_validate_rtm(struct nlmsghdr *nlh, struct nlattr **tb, + struct netlink_ext_ack *extack, + __u32 *valid_lft, __u32 *prefered_lft) { - struct nlattr *tb[IFA_MAX+1]; - struct in_ifaddr *ifa; - struct ifaddrmsg *ifm; - struct net_device *dev; - struct in_device *in_dev; + struct ifaddrmsg *ifm = nlmsg_data(nlh); int err; - err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy); + err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, + ifa_ipv4_policy, extack); if (err < 0) - goto errout; + return err; - ifm = nlmsg_data(nlh); - err = -EINVAL; - if (ifm->ifa_prefixlen > 32 || tb[IFA_LOCAL] == NULL) - goto errout; + if (ifm->ifa_prefixlen > 32) { + NL_SET_ERR_MSG(extack, "ipv4: Invalid prefix length"); + return -EINVAL; + } + + if (!tb[IFA_LOCAL]) { + NL_SET_ERR_MSG(extack, "ipv4: Local address is not supplied"); + return -EINVAL; + } + + if (tb[IFA_CACHEINFO]) { + struct ifa_cacheinfo *ci; + + ci = nla_data(tb[IFA_CACHEINFO]); + if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) { + NL_SET_ERR_MSG(extack, "ipv4: address lifetime invalid"); + return -EINVAL; + } + + *valid_lft = ci->ifa_valid; + *prefered_lft = ci->ifa_prefered; + } + + return 0; +} + +static struct in_ifaddr *inet_rtm_to_ifa(struct net *net, struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct ifaddrmsg *ifm = nlmsg_data(nlh); + struct in_device *in_dev; + struct net_device *dev; + struct in_ifaddr *ifa; + int err; dev = __dev_get_by_index(net, ifm->ifa_index); err = -ENODEV; - if (dev == NULL) + if (!dev) { + NL_SET_ERR_MSG(extack, "ipv4: Device not found"); goto errout; + } - in_dev = __in_dev_get_rtnl(dev); + in_dev = __in_dev_get_rtnl_net(dev); err = -ENOBUFS; - if (in_dev == NULL) + if (!in_dev) goto errout; - ifa = inet_alloc_ifa(); - if (ifa == NULL) + ifa = inet_alloc_ifa(in_dev); + if (!ifa) /* * A potential indev allocation can be left alive, it stays * assigned to its device and is destroy with it. @@ -743,40 +910,31 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, goto errout; ipv4_devconf_setall(in_dev); - in_dev_hold(in_dev); + neigh_parms_data_state_setall(in_dev->arp_parms); - if (tb[IFA_ADDRESS] == NULL) + if (!tb[IFA_ADDRESS]) tb[IFA_ADDRESS] = tb[IFA_LOCAL]; - INIT_HLIST_NODE(&ifa->hash); ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); - ifa->ifa_flags = ifm->ifa_flags; + ifa->ifa_flags = nla_get_u32_default(tb[IFA_FLAGS], ifm->ifa_flags); ifa->ifa_scope = ifm->ifa_scope; - ifa->ifa_dev = in_dev; - - ifa->ifa_local = nla_get_be32(tb[IFA_LOCAL]); - ifa->ifa_address = nla_get_be32(tb[IFA_ADDRESS]); + ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]); + ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]); if (tb[IFA_BROADCAST]) - ifa->ifa_broadcast = nla_get_be32(tb[IFA_BROADCAST]); + ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]); if (tb[IFA_LABEL]) - nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); + nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); - if (tb[IFA_CACHEINFO]) { - struct ifa_cacheinfo *ci; + if (tb[IFA_RT_PRIORITY]) + ifa->ifa_rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]); - ci = nla_data(tb[IFA_CACHEINFO]); - if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) { - err = -EINVAL; - goto errout; - } - *pvalid_lft = ci->ifa_valid; - *pprefered_lft = ci->ifa_prefered; - } + if (tb[IFA_PROTO]) + ifa->ifa_proto = nla_get_u8(tb[IFA_PROTO]); return ifa; @@ -784,59 +942,95 @@ errout: return ERR_PTR(err); } -static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa) +static struct in_ifaddr *find_matching_ifa(struct net *net, struct in_ifaddr *ifa) { struct in_device *in_dev = ifa->ifa_dev; - struct in_ifaddr *ifa1, **ifap; - - if (!ifa->ifa_local) - return NULL; + struct in_ifaddr *ifa1; - for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL; - ifap = &ifa1->ifa_next) { + in_dev_for_each_ifa_rtnl_net(net, ifa1, in_dev) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa) && ifa1->ifa_local == ifa->ifa_local) return ifa1; } + return NULL; } -static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) +static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) { + __u32 prefered_lft = INFINITY_LIFE_TIME; + __u32 valid_lft = INFINITY_LIFE_TIME; struct net *net = sock_net(skb->sk); - struct in_ifaddr *ifa; struct in_ifaddr *ifa_existing; - __u32 valid_lft = INFINITY_LIFE_TIME; - __u32 prefered_lft = INFINITY_LIFE_TIME; + struct nlattr *tb[IFA_MAX + 1]; + struct in_ifaddr *ifa; + int ret; - ASSERT_RTNL(); + ret = inet_validate_rtm(nlh, tb, extack, &valid_lft, &prefered_lft); + if (ret < 0) + return ret; + + if (!nla_get_in_addr(tb[IFA_LOCAL])) + return 0; - ifa = rtm_to_ifaddr(net, nlh, &valid_lft, &prefered_lft); - if (IS_ERR(ifa)) - return PTR_ERR(ifa); + rtnl_net_lock(net); - ifa_existing = find_matching_ifa(ifa); + ifa = inet_rtm_to_ifa(net, nlh, tb, extack); + if (IS_ERR(ifa)) { + ret = PTR_ERR(ifa); + goto unlock; + } + + ifa_existing = find_matching_ifa(net, ifa); if (!ifa_existing) { /* It would be best to check for !NLM_F_CREATE here but - * userspace alreay relies on not having to provide this. + * userspace already relies on not having to provide this. */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); - return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); + if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) { + ret = ip_mc_autojoin_config(net, true, ifa); + if (ret < 0) { + NL_SET_ERR_MSG(extack, "ipv4: Multicast auto join failed"); + inet_free_ifa(ifa); + goto unlock; + } + } + + ret = __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid, extack); } else { + u32 new_metric = ifa->ifa_rt_priority; + u8 new_proto = ifa->ifa_proto; + inet_free_ifa(ifa); if (nlh->nlmsg_flags & NLM_F_EXCL || - !(nlh->nlmsg_flags & NLM_F_REPLACE)) - return -EEXIST; + !(nlh->nlmsg_flags & NLM_F_REPLACE)) { + NL_SET_ERR_MSG(extack, "ipv4: Address already assigned"); + ret = -EEXIST; + goto unlock; + } ifa = ifa_existing; + + if (ifa->ifa_rt_priority != new_metric) { + fib_modify_prefix_metric(ifa, new_metric); + ifa->ifa_rt_priority = new_metric; + } + + ifa->ifa_proto = new_proto; + set_ifa_lifetime(ifa, valid_lft, prefered_lft); - cancel_delayed_work(&check_lifetime_work); - schedule_delayed_work(&check_lifetime_work, 0); + cancel_delayed_work(&net->ipv4.addr_chk_work); + queue_delayed_work(system_power_efficient_wq, + &net->ipv4.addr_chk_work, 0); rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); - blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); } - return 0; + +unlock: + rtnl_net_unlock(net); + + return ret; } /* @@ -847,52 +1041,46 @@ static int inet_abc_len(__be32 addr) { int rc = -1; /* Something else, probably a multicast. */ - if (ipv4_is_zeronet(addr)) + if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) rc = 0; else { __u32 haddr = ntohl(addr); - if (IN_CLASSA(haddr)) rc = 8; else if (IN_CLASSB(haddr)) rc = 16; else if (IN_CLASSC(haddr)) rc = 24; + else if (IN_CLASSE(haddr)) + rc = 32; } return rc; } -int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) +int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) { - struct ifreq ifr; struct sockaddr_in sin_orig; - struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr; + struct sockaddr_in *sin = (struct sockaddr_in *)&ifr->ifr_addr; + struct in_ifaddr __rcu **ifap = NULL; struct in_device *in_dev; - struct in_ifaddr **ifap = NULL; struct in_ifaddr *ifa = NULL; struct net_device *dev; char *colon; int ret = -EFAULT; int tryaddrmatch = 0; - /* - * Fetch the caller's info block into kernel space - */ - - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) - goto out; - ifr.ifr_name[IFNAMSIZ - 1] = 0; + ifr->ifr_name[IFNAMSIZ - 1] = 0; /* save original address for comparison */ memcpy(&sin_orig, sin, sizeof(*sin)); - colon = strchr(ifr.ifr_name, ':'); + colon = strchr(ifr->ifr_name, ':'); if (colon) *colon = 0; - dev_load(net, ifr.ifr_name); + dev_load(net, ifr->ifr_name); switch (cmd) { case SIOCGIFADDR: /* Get interface address */ @@ -929,17 +1117,17 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) goto out; } - rtnl_lock(); + rtnl_net_lock(net); ret = -ENODEV; - dev = __dev_get_by_name(net, ifr.ifr_name); + dev = __dev_get_by_name(net, ifr->ifr_name); if (!dev) goto done; if (colon) *colon = ':'; - in_dev = __in_dev_get_rtnl(dev); + in_dev = __in_dev_get_rtnl_net(dev); if (in_dev) { if (tryaddrmatch) { /* Matthias Andree */ @@ -947,9 +1135,11 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) /* note: we only do this for a limited set of ioctls and only if the original address family was AF_INET. This is checked above. */ - for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; + + for (ifap = &in_dev->ifa_list; + (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) { - if (!strcmp(ifr.ifr_name, ifa->ifa_label) && + if (!strcmp(ifr->ifr_name, ifa->ifa_label) && sin_orig.sin_addr.s_addr == ifa->ifa_local) { break; /* found */ @@ -960,9 +1150,10 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) 4.3BSD-style and passed in junk so we fall back to comparing just the label */ if (!ifa) { - for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; + for (ifap = &in_dev->ifa_list; + (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) - if (!strcmp(ifr.ifr_name, ifa->ifa_label)) + if (!strcmp(ifr->ifr_name, ifa->ifa_label)) break; } } @@ -973,20 +1164,24 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) switch (cmd) { case SIOCGIFADDR: /* Get interface address */ + ret = 0; sin->sin_addr.s_addr = ifa->ifa_local; - goto rarok; + break; case SIOCGIFBRDADDR: /* Get the broadcast address */ + ret = 0; sin->sin_addr.s_addr = ifa->ifa_broadcast; - goto rarok; + break; case SIOCGIFDSTADDR: /* Get the destination address */ + ret = 0; sin->sin_addr.s_addr = ifa->ifa_address; - goto rarok; + break; case SIOCGIFNETMASK: /* Get the netmask for the interface */ + ret = 0; sin->sin_addr.s_addr = ifa->ifa_mask; - goto rarok; + break; case SIOCSIFFLAGS: if (colon) { @@ -994,11 +1189,14 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (!ifa) break; ret = 0; - if (!(ifr.ifr_flags & IFF_UP)) + if (!(ifr->ifr_flags & IFF_UP)) inet_del_ifa(in_dev, ifap, 1); break; } - ret = dev_change_flags(dev, ifr.ifr_flags); + + /* NETDEV_UP/DOWN/CHANGE could touch a peer dev */ + ASSERT_RTNL(); + ret = dev_change_flags(dev, ifr->ifr_flags, NULL); break; case SIOCSIFADDR: /* Set interface address (and family) */ @@ -1008,12 +1206,14 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (!ifa) { ret = -ENOBUFS; - ifa = inet_alloc_ifa(); + if (!in_dev) + break; + ifa = inet_alloc_ifa(in_dev); if (!ifa) break; - INIT_HLIST_NODE(&ifa->hash); + if (colon) - memcpy(ifa->ifa_label, ifr.ifr_name, IFNAMSIZ); + memcpy(ifa->ifa_label, ifr->ifr_name, IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); } else { @@ -1097,67 +1297,87 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) break; } done: - rtnl_unlock(); + rtnl_net_unlock(net); out: return ret; -rarok: - rtnl_unlock(); - ret = copy_to_user(arg, &ifr, sizeof(struct ifreq)) ? -EFAULT : 0; - goto out; } -static int inet_gifconf(struct net_device *dev, char __user *buf, int len) +int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { - struct in_device *in_dev = __in_dev_get_rtnl(dev); - struct in_ifaddr *ifa; + struct in_device *in_dev = __in_dev_get_rtnl_net(dev); + const struct in_ifaddr *ifa; struct ifreq ifr; int done = 0; + if (WARN_ON(size > sizeof(struct ifreq))) + goto out; + if (!in_dev) goto out; - for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { + in_dev_for_each_ifa_rtnl_net(dev_net(dev), ifa, in_dev) { if (!buf) { - done += sizeof(ifr); + done += size; continue; } - if (len < (int) sizeof(ifr)) + if (len < size) break; memset(&ifr, 0, sizeof(struct ifreq)); - if (ifa->ifa_label) - strcpy(ifr.ifr_name, ifa->ifa_label); - else - strcpy(ifr.ifr_name, dev->name); + strcpy(ifr.ifr_name, ifa->ifa_label); (*(struct sockaddr_in *)&ifr.ifr_addr).sin_family = AF_INET; (*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr = ifa->ifa_local; - if (copy_to_user(buf, &ifr, sizeof(struct ifreq))) { + if (copy_to_user(buf + done, &ifr, size)) { done = -EFAULT; break; } - buf += sizeof(struct ifreq); - len -= sizeof(struct ifreq); - done += sizeof(struct ifreq); + len -= size; + done += size; } out: return done; } +static __be32 in_dev_select_addr(const struct in_device *in_dev, + int scope) +{ + const struct in_ifaddr *ifa; + + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) + continue; + if (ifa->ifa_scope != RT_SCOPE_LINK && + ifa->ifa_scope <= scope) + return ifa->ifa_local; + } + + return 0; +} + __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { + const struct in_ifaddr *ifa; __be32 addr = 0; + unsigned char localnet_scope = RT_SCOPE_HOST; struct in_device *in_dev; - struct net *net = dev_net(dev); + struct net *net; + int master_idx; rcu_read_lock(); + net = dev_net_rcu(dev); in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto no_in_dev; - for_primary_ifa(in_dev) { - if (ifa->ifa_scope > scope) + if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) + localnet_scope = RT_SCOPE_LINK; + + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) + continue; + if (min(ifa->ifa_scope, localnet_scope) > scope) continue; if (!dst || inet_ifa_match(dst, ifa)) { addr = ifa->ifa_local; @@ -1165,28 +1385,41 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) } if (!addr) addr = ifa->ifa_local; - } endfor_ifa(in_dev); + } if (addr) goto out_unlock; no_in_dev: + master_idx = l3mdev_master_ifindex_rcu(dev); + + /* For VRFs, the VRF device takes the place of the loopback device, + * with addresses on it being preferred. Note in such cases the + * loopback device will be among the devices that fail the master_idx + * equality check in the loop below. + */ + if (master_idx && + (dev = dev_get_by_index_rcu(net, master_idx)) && + (in_dev = __in_dev_get_rcu(dev))) { + addr = in_dev_select_addr(in_dev, scope); + if (addr) + goto out_unlock; + } /* Not loopback addresses on loopback should be preferred - in this case. It is importnat that lo is the first interface + in this case. It is important that lo is the first interface in dev_base list. */ for_each_netdev_rcu(net, dev) { + if (l3mdev_master_ifindex_rcu(dev) != master_idx) + continue; + in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; - for_primary_ifa(in_dev) { - if (ifa->ifa_scope != RT_SCOPE_LINK && - ifa->ifa_scope <= scope) { - addr = ifa->ifa_local; - goto out_unlock; - } - } endfor_ifa(in_dev); + addr = in_dev_select_addr(in_dev, scope); + if (addr) + goto out_unlock; } out_unlock: rcu_read_unlock(); @@ -1197,13 +1430,20 @@ EXPORT_SYMBOL(inet_select_addr); static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, __be32 local, int scope) { - int same = 0; + unsigned char localnet_scope = RT_SCOPE_HOST; + const struct in_ifaddr *ifa; __be32 addr = 0; + int same = 0; + + if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) + localnet_scope = RT_SCOPE_LINK; + + in_dev_for_each_ifa_rcu(ifa, in_dev) { + unsigned char min_scope = min(ifa->ifa_scope, localnet_scope); - for_ifa(in_dev) { if (!addr && (local == ifa->ifa_local || !local) && - ifa->ifa_scope <= scope) { + min_scope <= scope) { addr = ifa->ifa_local; if (same) break; @@ -1218,7 +1458,7 @@ static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, if (inet_ifa_match(addr, ifa)) break; /* No, then can we use new local src? */ - if (ifa->ifa_scope <= scope) { + if (min_scope <= scope) { addr = ifa->ifa_local; break; } @@ -1226,29 +1466,28 @@ static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, same = 0; } } - } endfor_ifa(in_dev); + } return same ? addr : 0; } /* * Confirm that local IP address exists using wildcards: - * - in_dev: only on this interface, 0=any interface + * - net: netns to check, cannot be NULL + * - in_dev: only on this interface, NULL=any interface * - dst: only in the same subnet as dst, 0=any dst * - local: address, 0=autoselect the local address * - scope: maximum allowed scope value for the local address */ -__be32 inet_confirm_addr(struct in_device *in_dev, +__be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope) { __be32 addr = 0; struct net_device *dev; - struct net *net; - if (scope != RT_SCOPE_LINK) + if (in_dev) return confirm_addr_indev(in_dev, dst, local, scope); - net = dev_net(in_dev->dev); rcu_read_lock(); for_each_netdev_rcu(net, dev) { in_dev = __in_dev_get_rcu(dev); @@ -1280,6 +1519,19 @@ int unregister_inetaddr_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_inetaddr_notifier); +int register_inetaddr_validator_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&inetaddr_validator_chain, nb); +} +EXPORT_SYMBOL(register_inetaddr_validator_notifier); + +int unregister_inetaddr_validator_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&inetaddr_validator_chain, + nb); +} +EXPORT_SYMBOL(unregister_inetaddr_validator_notifier); + /* Rename ifa_labels for a device name change. Make some effort to preserve * existing alias numbering and to create unique labels if possible. */ @@ -1288,7 +1540,7 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) struct in_ifaddr *ifa; int named = 0; - for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { + in_dev_for_each_ifa_rtnl(ifa, in_dev) { char old[IFNAMSIZ], *dot; memcpy(old, ifa->ifa_label, IFNAMSIZ); @@ -1296,7 +1548,7 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) if (named++ == 0) goto skip; dot = strchr(old, ':'); - if (dot == NULL) { + if (!dot) { sprintf(old, ":%d", named); dot = old; } @@ -1309,19 +1561,13 @@ skip: } } -static bool inetdev_valid_mtu(unsigned int mtu) -{ - return mtu >= 68; -} - static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) { - struct in_ifaddr *ifa; + const struct in_ifaddr *ifa; - for (ifa = in_dev->ifa_list; ifa; - ifa = ifa->ifa_next) { + in_dev_for_each_ifa_rtnl(ifa, in_dev) { arp_send(ARPOP_REQUEST, ETH_P_ARP, ifa->ifa_local, dev, ifa->ifa_local, NULL, @@ -1342,8 +1588,8 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (!in_dev) { if (event == NETDEV_REGISTER) { in_dev = inetdev_init(dev); - if (!in_dev) - return notifier_from_errno(-ENOMEM); + if (IS_ERR(in_dev)) + return notifier_from_errno(PTR_ERR(in_dev)); if (dev->flags & IFF_LOOPBACK) { IN_DEV_CONF_SET(in_dev, NOXFRM, 1); IN_DEV_CONF_SET(in_dev, NOPOLICY, 1); @@ -1365,29 +1611,28 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (!inetdev_valid_mtu(dev->mtu)) break; if (dev->flags & IFF_LOOPBACK) { - struct in_ifaddr *ifa = inet_alloc_ifa(); + struct in_ifaddr *ifa = inet_alloc_ifa(in_dev); if (ifa) { - INIT_HLIST_NODE(&ifa->hash); ifa->ifa_local = ifa->ifa_address = htonl(INADDR_LOOPBACK); ifa->ifa_prefixlen = 8; ifa->ifa_mask = inet_make_mask(8); - in_dev_hold(in_dev); - ifa->ifa_dev = in_dev; ifa->ifa_scope = RT_SCOPE_HOST; memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + ipv4_devconf_setall(in_dev); + neigh_parms_data_state_setall(in_dev->arp_parms); inet_insert_ifa(ifa); } } ip_mc_up(in_dev); - /* fall through */ + fallthrough; case NETDEV_CHANGEADDR: if (!IN_DEV_ARP_NOTIFY(in_dev)) break; - /* fall through */ + fallthrough; case NETDEV_NOTIFY_PEERS: /* Send gratuitous ARP to notify of link change */ inetdev_send_gratuitous_arp(dev, in_dev); @@ -1405,6 +1650,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (inetdev_valid_mtu(dev->mtu)) break; /* disable IP when MTU is not enough */ + fallthrough; case NETDEV_UNREGISTER: inetdev_destroy(in_dev); break; @@ -1432,7 +1678,11 @@ static size_t inet_nlmsg_size(void) + nla_total_size(4) /* IFA_ADDRESS */ + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ - + nla_total_size(IFNAMSIZ); /* IFA_LABEL */ + + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ + + nla_total_size(4) /* IFA_FLAGS */ + + nla_total_size(1) /* IFA_PROTO */ + + nla_total_size(4) /* IFA_RT_PRIORITY */ + + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */ } static inline u32 cstamp_delta(unsigned long cstamp) @@ -1453,29 +1703,43 @@ static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); } -static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, - u32 portid, u32 seq, int event, unsigned int flags) +static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa, + struct inet_fill_args *args) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; + unsigned long tstamp; u32 preferred, valid; + u32 flags; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); - if (nlh == NULL) + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(*ifm), + args->flags); + if (!nlh) return -EMSGSIZE; ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; - ifm->ifa_flags = ifa->ifa_flags; + + flags = READ_ONCE(ifa->ifa_flags); + /* Warning : ifm->ifa_flags is an __u8, it holds only 8 bits. + * The 32bit value is given in IFA_FLAGS attribute. + */ + ifm->ifa_flags = (__u8)flags; + ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; - if (!(ifm->ifa_flags & IFA_F_PERMANENT)) { - preferred = ifa->ifa_preferred_lft; - valid = ifa->ifa_valid_lft; + if (args->netnsid >= 0 && + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + goto nla_put_failure; + + tstamp = READ_ONCE(ifa->ifa_tstamp); + if (!(flags & IFA_F_PERMANENT)) { + preferred = READ_ONCE(ifa->ifa_preferred_lft); + valid = READ_ONCE(ifa->ifa_valid_lft); if (preferred != INFINITY_LIFE_TIME) { - long tval = (jiffies - ifa->ifa_tstamp) / HZ; + long tval = (jiffies - tstamp) / HZ; if (preferred > tval) preferred -= tval; @@ -1493,95 +1757,265 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, valid = INFINITY_LIFE_TIME; } if ((ifa->ifa_address && - nla_put_be32(skb, IFA_ADDRESS, ifa->ifa_address)) || + nla_put_in_addr(skb, IFA_ADDRESS, ifa->ifa_address)) || (ifa->ifa_local && - nla_put_be32(skb, IFA_LOCAL, ifa->ifa_local)) || + nla_put_in_addr(skb, IFA_LOCAL, ifa->ifa_local)) || (ifa->ifa_broadcast && - nla_put_be32(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || + nla_put_in_addr(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || (ifa->ifa_label[0] && nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || - put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp, + (ifa->ifa_proto && + nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) || + nla_put_u32(skb, IFA_FLAGS, flags) || + (ifa->ifa_rt_priority && + nla_put_u32(skb, IFA_RT_PRIORITY, ifa->ifa_rt_priority)) || + put_cacheinfo(skb, READ_ONCE(ifa->ifa_cstamp), tstamp, preferred, valid)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } -static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) +static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, + struct inet_fill_args *fillargs, + struct net **tgt_net, struct sock *sk, + struct netlink_callback *cb) +{ + struct netlink_ext_ack *extack = cb->extack; + struct nlattr *tb[IFA_MAX+1]; + struct ifaddrmsg *ifm; + int err, i; + + ifm = nlmsg_payload(nlh, sizeof(*ifm)); + if (!ifm) { + NL_SET_ERR_MSG(extack, "ipv4: Invalid header for address dump request"); + return -EINVAL; + } + + if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { + NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for address dump request"); + return -EINVAL; + } + + fillargs->ifindex = ifm->ifa_index; + if (fillargs->ifindex) { + cb->answer_flags |= NLM_F_DUMP_FILTERED; + fillargs->flags |= NLM_F_DUMP_FILTERED; + } + + err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, + ifa_ipv4_policy, extack); + if (err < 0) + return err; + + for (i = 0; i <= IFA_MAX; ++i) { + if (!tb[i]) + continue; + + if (i == IFA_TARGET_NETNSID) { + struct net *net; + + fillargs->netnsid = nla_get_s32(tb[i]); + + net = rtnl_get_net_ns_capable(sk, fillargs->netnsid); + if (IS_ERR(net)) { + fillargs->netnsid = -1; + NL_SET_ERR_MSG(extack, "ipv4: Invalid target network namespace id"); + return PTR_ERR(net); + } + *tgt_net = net; + } else { + NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in dump request"); + return -EINVAL; + } + } + + return 0; +} + +static int in_dev_dump_ifmcaddr(struct in_device *in_dev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, + struct inet_fill_args *fillargs) +{ + struct ip_mc_list *im; + int ip_idx = 0; + int err; + + for (im = rcu_dereference(in_dev->mc_list); + im; + im = rcu_dereference(im->next_rcu)) { + if (ip_idx < *s_ip_idx) { + ip_idx++; + continue; + } + err = inet_fill_ifmcaddr(skb, in_dev->dev, im, fillargs); + if (err < 0) + goto done; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + ip_idx++; + } + err = 0; + ip_idx = 0; +done: + *s_ip_idx = ip_idx; + return err; +} + +static int in_dev_dump_ifaddr(struct in_device *in_dev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, + struct inet_fill_args *fillargs) { + struct in_ifaddr *ifa; + int ip_idx = 0; + int err; + + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (ip_idx < *s_ip_idx) { + ip_idx++; + continue; + } + err = inet_fill_ifaddr(skb, ifa, fillargs); + if (err < 0) + goto done; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + ip_idx++; + } + err = 0; + ip_idx = 0; +done: + *s_ip_idx = ip_idx; + + return err; +} + +static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, + struct inet_fill_args *fillargs) +{ + switch (fillargs->event) { + case RTM_NEWADDR: + return in_dev_dump_ifaddr(in_dev, skb, cb, s_ip_idx, fillargs); + case RTM_GETMULTICAST: + return in_dev_dump_ifmcaddr(in_dev, skb, cb, s_ip_idx, + fillargs); + default: + return -EINVAL; + } +} + +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv4.dev_addr_genid) + + READ_ONCE(net->dev_base_seq); + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + +static int inet_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, + int event) +{ + const struct nlmsghdr *nlh = cb->nlh; + struct inet_fill_args fillargs = { + .portid = NETLINK_CB(cb->skb).portid, + .seq = nlh->nlmsg_seq, + .event = event, + .flags = NLM_F_MULTI, + .netnsid = -1, + }; struct net *net = sock_net(skb->sk); - int h, s_h; - int idx, s_idx; - int ip_idx, s_ip_idx; - struct net_device *dev; + struct net *tgt_net = net; + struct { + unsigned long ifindex; + int ip_idx; + } *ctx = (void *)cb->ctx; struct in_device *in_dev; - struct in_ifaddr *ifa; - struct hlist_head *head; + struct net_device *dev; + int err = 0; - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - s_ip_idx = ip_idx = cb->args[2]; + rcu_read_lock(); + if (cb->strict_check) { + err = inet_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, + skb->sk, cb); + if (err < 0) + goto done; - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - rcu_read_lock(); - cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ - net->dev_base_seq; - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - if (h > s_h || idx > s_idx) - s_ip_idx = 0; + if (fillargs.ifindex) { + dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); + if (!dev) { + err = -ENODEV; + goto done; + } in_dev = __in_dev_get_rcu(dev); if (!in_dev) - goto cont; - - for (ifa = in_dev->ifa_list, ip_idx = 0; ifa; - ifa = ifa->ifa_next, ip_idx++) { - if (ip_idx < s_ip_idx) - continue; - if (inet_fill_ifaddr(skb, ifa, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWADDR, NLM_F_MULTI) <= 0) { - rcu_read_unlock(); - goto done; - } - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); - } -cont: - idx++; + goto done; + err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, + &fillargs); + goto done; } - rcu_read_unlock(); } + cb->seq = inet_base_seq(tgt_net); + + for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) + continue; + err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, + &fillargs); + if (err < 0) + goto done; + } done: - cb->args[0] = h; - cb->args[1] = idx; - cb->args[2] = ip_idx; + if (fillargs.netnsid >= 0) + put_net(tgt_net); + rcu_read_unlock(); + return err; +} - return skb->len; +static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) +{ + return inet_dump_addr(skb, cb, RTM_NEWADDR); +} + +static int inet_dump_ifmcaddr(struct sk_buff *skb, struct netlink_callback *cb) +{ + return inet_dump_addr(skb, cb, RTM_GETMULTICAST); } static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { + struct inet_fill_args fillargs = { + .portid = portid, + .seq = nlh ? nlh->nlmsg_seq : 0, + .event = event, + .flags = 0, + .netnsid = -1, + }; struct sk_buff *skb; - u32 seq = nlh ? nlh->nlmsg_seq : 0; int err = -ENOBUFS; struct net *net; net = dev_net(ifa->ifa_dev->dev); skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL); - if (skb == NULL) + if (!skb) goto errout; - err = inet_fill_ifaddr(skb, ifa, portid, seq, event, 0); + err = inet_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -1591,11 +2025,11 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); + rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); } -static size_t inet_get_link_af_size(const struct net_device *dev) +static size_t inet_get_link_af_size(const struct net_device *dev, + u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); @@ -1605,7 +2039,8 @@ static size_t inet_get_link_af_size(const struct net_device *dev) return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */ } -static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev) +static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev, + u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); struct nlattr *nla; @@ -1615,11 +2050,11 @@ static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev) return -ENODATA; nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4); - if (nla == NULL) + if (!nla) return -EMSGSIZE; for (i = 0; i < IPV4_DEVCONF_MAX; i++) - ((u32 *) nla_data(nla))[i] = in_dev->cnf.data[i]; + ((u32 *) nla_data(nla))[i] = READ_ONCE(in_dev->cnf.data[i]); return 0; } @@ -1629,7 +2064,8 @@ static const struct nla_policy inet_af_policy[IFLA_INET_MAX+1] = { }; static int inet_validate_link_af(const struct net_device *dev, - const struct nlattr *nla) + const struct nlattr *nla, + struct netlink_ext_ack *extack) { struct nlattr *a, *tb[IFLA_INET_MAX+1]; int err, rem; @@ -1637,7 +2073,8 @@ static int inet_validate_link_af(const struct net_device *dev, if (dev && !__in_dev_get_rtnl(dev)) return -EAFNOSUPPORT; - err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy); + err = nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, + inet_af_policy, extack); if (err < 0) return err; @@ -1656,7 +2093,8 @@ static int inet_validate_link_af(const struct net_device *dev, return 0; } -static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) +static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla, + struct netlink_ext_ack *extack) { struct in_device *in_dev = __in_dev_get_rtnl(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; @@ -1665,8 +2103,8 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) if (!in_dev) return -EAFNOSUPPORT; - if (nla_parse_nested(tb, IFLA_INET_MAX, nla, NULL) < 0) - BUG(); + if (nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0) + return -EINVAL; if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) @@ -1680,110 +2118,178 @@ static int inet_netconf_msgsize_devconf(int type) { int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + nla_total_size(4); /* NETCONFA_IFINDEX */ + bool all = false; - /* type -1 is used for ALL */ - if (type == -1 || type == NETCONFA_FORWARDING) + if (type == NETCONFA_ALL) + all = true; + + if (all || type == NETCONFA_FORWARDING) + size += nla_total_size(4); + if (all || type == NETCONFA_RP_FILTER) size += nla_total_size(4); - if (type == -1 || type == NETCONFA_RP_FILTER) + if (all || type == NETCONFA_MC_FORWARDING) size += nla_total_size(4); - if (type == -1 || type == NETCONFA_MC_FORWARDING) + if (all || type == NETCONFA_BC_FORWARDING) + size += nla_total_size(4); + if (all || type == NETCONFA_PROXY_NEIGH) + size += nla_total_size(4); + if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) size += nla_total_size(4); return size; } static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, - struct ipv4_devconf *devconf, u32 portid, - u32 seq, int event, unsigned int flags, - int type) + const struct ipv4_devconf *devconf, + u32 portid, u32 seq, int event, + unsigned int flags, int type) { struct nlmsghdr *nlh; struct netconfmsg *ncm; + bool all = false; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; + if (type == NETCONFA_ALL) + all = true; + ncm = nlmsg_data(nlh); ncm->ncm_family = AF_INET; if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) goto nla_put_failure; - /* type -1 is used for ALL */ - if ((type == -1 || type == NETCONFA_FORWARDING) && + if (!devconf) + goto out; + + if ((all || type == NETCONFA_FORWARDING) && nla_put_s32(skb, NETCONFA_FORWARDING, - IPV4_DEVCONF(*devconf, FORWARDING)) < 0) + IPV4_DEVCONF_RO(*devconf, FORWARDING)) < 0) goto nla_put_failure; - if ((type == -1 || type == NETCONFA_RP_FILTER) && + if ((all || type == NETCONFA_RP_FILTER) && nla_put_s32(skb, NETCONFA_RP_FILTER, - IPV4_DEVCONF(*devconf, RP_FILTER)) < 0) + IPV4_DEVCONF_RO(*devconf, RP_FILTER)) < 0) goto nla_put_failure; - if ((type == -1 || type == NETCONFA_MC_FORWARDING) && + if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, - IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0) + IPV4_DEVCONF_RO(*devconf, MC_FORWARDING)) < 0) + goto nla_put_failure; + if ((all || type == NETCONFA_BC_FORWARDING) && + nla_put_s32(skb, NETCONFA_BC_FORWARDING, + IPV4_DEVCONF_RO(*devconf, BC_FORWARDING)) < 0) + goto nla_put_failure; + if ((all || type == NETCONFA_PROXY_NEIGH) && + nla_put_s32(skb, NETCONFA_PROXY_NEIGH, + IPV4_DEVCONF_RO(*devconf, PROXY_ARP)) < 0) + goto nla_put_failure; + if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && + nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + IPV4_DEVCONF_RO(*devconf, + IGNORE_ROUTES_WITH_LINKDOWN)) < 0) goto nla_put_failure; - return nlmsg_end(skb, nlh); +out: + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } -void inet_netconf_notify_devconf(struct net *net, int type, int ifindex, - struct ipv4_devconf *devconf) +void inet_netconf_notify_devconf(struct net *net, int event, int type, + int ifindex, struct ipv4_devconf *devconf) { struct sk_buff *skb; int err = -ENOBUFS; - skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_ATOMIC); - if (skb == NULL) + skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_KERNEL); + if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, - RTM_NEWNETCONF, 0, type); + event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } - rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_ATOMIC); + rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); + rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); } static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, [NETCONFA_FORWARDING] = { .len = sizeof(int) }, [NETCONFA_RP_FILTER] = { .len = sizeof(int) }, + [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, + [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; +static int inet_netconf_valid_get_req(struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + int i, err; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct netconfmsg))) { + NL_SET_ERR_MSG(extack, "ipv4: Invalid header for netconf get request"); + return -EINVAL; + } + + if (!netlink_strict_get_check(skb)) + return nlmsg_parse_deprecated(nlh, sizeof(struct netconfmsg), + tb, NETCONFA_MAX, + devconf_ipv4_policy, extack); + + err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct netconfmsg), + tb, NETCONFA_MAX, + devconf_ipv4_policy, extack); + if (err) + return err; + + for (i = 0; i <= NETCONFA_MAX; i++) { + if (!tb[i]) + continue; + + switch (i) { + case NETCONFA_IFINDEX: + break; + default: + NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in netconf get request"); + return -EINVAL; + } + } + + return 0; +} + static int inet_netconf_get_devconf(struct sk_buff *in_skb, - struct nlmsghdr *nlh) + struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); - struct nlattr *tb[NETCONFA_MAX+1]; - struct netconfmsg *ncm; + struct nlattr *tb[NETCONFA_MAX + 1]; + const struct ipv4_devconf *devconf; + struct in_device *in_dev = NULL; + struct net_device *dev = NULL; struct sk_buff *skb; - struct ipv4_devconf *devconf; - struct in_device *in_dev; - struct net_device *dev; int ifindex; int err; - err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, - devconf_ipv4_policy); - if (err < 0) - goto errout; + err = inet_netconf_valid_get_req(in_skb, nlh, tb, extack); + if (err) + return err; - err = EINVAL; if (!tb[NETCONFA_IFINDEX]) - goto errout; + return -EINVAL; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { @@ -1794,25 +2300,25 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, devconf = net->ipv4.devconf_dflt; break; default: - dev = __dev_get_by_index(net, ifindex); - if (dev == NULL) - goto errout; - in_dev = __in_dev_get_rtnl(dev); - if (in_dev == NULL) + err = -ENODEV; + dev = dev_get_by_index(net, ifindex); + if (dev) + in_dev = in_dev_get(dev); + if (!in_dev) goto errout; devconf = &in_dev->cnf; break; } err = -ENOBUFS; - skb = nlmsg_new(inet_netconf_msgsize_devconf(-1), GFP_ATOMIC); - if (skb == NULL) + skb = nlmsg_new(inet_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); + if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, 0, - -1); + NETCONFA_ALL); if (err < 0) { /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); @@ -1821,78 +2327,79 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: + if (in_dev) + in_dev_put(in_dev); + dev_put(dev); return err; } static int inet_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { + const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); - int h, s_h; - int idx, s_idx; + struct { + unsigned long ifindex; + unsigned int all_default; + } *ctx = (void *)cb->ctx; + const struct in_device *in_dev; struct net_device *dev; - struct in_device *in_dev; - struct hlist_head *head; + int err = 0; - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; + if (cb->strict_check) { + struct netlink_ext_ack *extack = cb->extack; + struct netconfmsg *ncm; - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - rcu_read_lock(); - cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ - net->dev_base_seq; - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - in_dev = __in_dev_get_rcu(dev); - if (!in_dev) - goto cont; - - if (inet_netconf_fill_devconf(skb, dev->ifindex, - &in_dev->cnf, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWNETCONF, - NLM_F_MULTI, - -1) <= 0) { - rcu_read_unlock(); - goto done; - } - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); -cont: - idx++; + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ncm))) { + NL_SET_ERR_MSG(extack, "ipv4: Invalid header for netconf dump request"); + return -EINVAL; } - rcu_read_unlock(); + + if (nlmsg_attrlen(nlh, sizeof(*ncm))) { + NL_SET_ERR_MSG(extack, "ipv4: Invalid data after header in netconf dump request"); + return -EINVAL; + } + } + + rcu_read_lock(); + for_each_netdev_dump(net, dev, ctx->ifindex) { + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) + continue; + err = inet_netconf_fill_devconf(skb, dev->ifindex, + &in_dev->cnf, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) + goto done; } - if (h == NETDEV_HASHENTRIES) { - if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, - net->ipv4.devconf_all, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWNETCONF, NLM_F_MULTI, - -1) <= 0) + if (ctx->all_default == 0) { + err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, + net->ipv4.devconf_all, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) goto done; - else - h++; - } - if (h == NETDEV_HASHENTRIES + 1) { - if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, - net->ipv4.devconf_dflt, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWNETCONF, NLM_F_MULTI, - -1) <= 0) + ctx->all_default++; + } + if (ctx->all_default == 1) { + err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, + net->ipv4.devconf_dflt, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) goto done; - else - h++; + ctx->all_default++; } done: - cb->args[0] = h; - cb->args[1] = idx; - - return skb->len; + rcu_read_unlock(); + return err; } #ifdef CONFIG_SYSCTL @@ -1920,31 +2427,46 @@ static void inet_forward_change(struct net *net) IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on; IPV4_DEVCONF_DFLT(net, FORWARDING) = on; - inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); - inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); for_each_netdev(net, dev) { struct in_device *in_dev; + if (on) dev_disable_lro(dev); - rcu_read_lock(); - in_dev = __in_dev_get_rcu(dev); + + in_dev = __in_dev_get_rtnl_net(dev); if (in_dev) { IN_DEV_CONF_SET(in_dev, FORWARDING, on); - inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORWARDING, dev->ifindex, &in_dev->cnf); } - rcu_read_unlock(); } } -static int devinet_conf_proc(struct ctl_table *ctl, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) +static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf) +{ + if (cnf == net->ipv4.devconf_dflt) + return NETCONFA_IFINDEX_DEFAULT; + else if (cnf == net->ipv4.devconf_all) + return NETCONFA_IFINDEX_ALL; + else { + struct in_device *idev + = container_of(cnf, struct in_device, cnf); + return idev->dev->ifindex; + } +} + +static int devinet_conf_proc(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) { int old_value = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); @@ -1954,6 +2476,7 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write, struct ipv4_devconf *cnf = ctl->extra1; struct net *net = ctl->extra2; int i = (int *)ctl->data - cnf->data; + int ifindex; set_bit(i, cnf->state); @@ -1963,21 +2486,30 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write, i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) rt_cache_flush(net); + + if (i == IPV4_DEVCONF_BC_FORWARDING - 1 && + new_value != old_value) + rt_cache_flush(net); + if (i == IPV4_DEVCONF_RP_FILTER - 1 && new_value != old_value) { - int ifindex; - - if (cnf == net->ipv4.devconf_dflt) - ifindex = NETCONFA_IFINDEX_DEFAULT; - else if (cnf == net->ipv4.devconf_all) - ifindex = NETCONFA_IFINDEX_ALL; - else { - struct in_device *idev = - container_of(cnf, struct in_device, - cnf); - ifindex = idev->dev->ifindex; - } - inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER, + ifindex = devinet_conf_ifindex(net, cnf); + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_RP_FILTER, + ifindex, cnf); + } + if (i == IPV4_DEVCONF_PROXY_ARP - 1 && + new_value != old_value) { + ifindex = devinet_conf_ifindex(net, cnf); + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_PROXY_NEIGH, + ifindex, cnf); + } + if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 && + new_value != old_value) { + ifindex = devinet_conf_ifindex(net, cnf); + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, ifindex, cnf); } } @@ -1985,20 +2517,23 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write, return ret; } -static int devinet_sysctl_forward(struct ctl_table *ctl, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) +static int devinet_sysctl_forward(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; - int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + struct net *net = ctl->extra2; + int ret; - if (write && *valp != val) { - struct net *net = ctl->extra2; + if (write && !ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + + if (write && *valp != val) { if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) { - if (!rtnl_trylock()) { + if (!rtnl_net_trylock(net)) { /* Restore the original values before restarting */ *valp = val; *ppos = pos; @@ -2012,15 +2547,16 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write, container_of(cnf, struct in_device, cnf); if (*valp) dev_disable_lro(idev->dev); - inet_netconf_notify_devconf(net, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, idev->dev->ifindex, cnf); } - rtnl_unlock(); + rtnl_net_unlock(net); rt_cache_flush(net); } else - inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); } @@ -2028,9 +2564,8 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write, return ret; } -static int ipv4_doint_and_flush(struct ctl_table *ctl, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) +static int ipv4_doint_and_flush(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; @@ -2068,12 +2603,13 @@ static int ipv4_doint_and_flush(struct ctl_table *ctl, int write, static struct devinet_sysctl_table { struct ctl_table_header *sysctl_header; - struct ctl_table devinet_vars[__IPV4_DEVCONF_MAX]; + struct ctl_table devinet_vars[IPV4_DEVCONF_MAX]; } devinet_sysctl = { .devinet_vars = { DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding", devinet_sysctl_forward), DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"), + DEVINET_SYSCTL_RW_ENTRY(BC_FORWARDING, "bc_forwarding"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"), DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"), @@ -2094,31 +2630,43 @@ static struct devinet_sysctl_table { DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"), DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"), DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"), + DEVINET_SYSCTL_RW_ENTRY(ARP_EVICT_NOCARRIER, + "arp_evict_nocarrier"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"), + DEVINET_SYSCTL_RW_ENTRY(FORCE_IGMP_VERSION, + "force_igmp_version"), + DEVINET_SYSCTL_RW_ENTRY(IGMPV2_UNSOLICITED_REPORT_INTERVAL, + "igmpv2_unsolicited_report_interval"), + DEVINET_SYSCTL_RW_ENTRY(IGMPV3_UNSOLICITED_REPORT_INTERVAL, + "igmpv3_unsolicited_report_interval"), + DEVINET_SYSCTL_RW_ENTRY(IGNORE_ROUTES_WITH_LINKDOWN, + "ignore_routes_with_linkdown"), + DEVINET_SYSCTL_RW_ENTRY(DROP_GRATUITOUS_ARP, + "drop_gratuitous_arp"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"), - DEVINET_SYSCTL_FLUSHING_ENTRY(FORCE_IGMP_VERSION, - "force_igmp_version"), DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES, "promote_secondaries"), DEVINET_SYSCTL_FLUSHING_ENTRY(ROUTE_LOCALNET, "route_localnet"), + DEVINET_SYSCTL_FLUSHING_ENTRY(DROP_UNICAST_IN_L2_MULTICAST, + "drop_unicast_in_l2_multicast"), }, }; static int __devinet_sysctl_register(struct net *net, char *dev_name, - struct ipv4_devconf *p) + int ifindex, struct ipv4_devconf *p) { int i; struct devinet_sysctl_table *t; char path[sizeof("net/ipv4/conf/") + IFNAMSIZ]; - t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL); + t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL_ACCOUNT); if (!t) goto out; - for (i = 0; i < ARRAY_SIZE(t->devinet_vars) - 1; i++) { + for (i = 0; i < ARRAY_SIZE(t->devinet_vars); i++) { t->devinet_vars[i].data += (char *)p - (char *)&ipv4_devconf; t->devinet_vars[i].extra1 = p; t->devinet_vars[i].extra2 = net; @@ -2131,36 +2679,53 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, goto free; p->sysctl = t; + + inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, + ifindex, p); return 0; free: kfree(t); out: - return -ENOBUFS; + return -ENOMEM; } -static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf) +static void __devinet_sysctl_unregister(struct net *net, + struct ipv4_devconf *cnf, int ifindex) { struct devinet_sysctl_table *t = cnf->sysctl; - if (t == NULL) - return; + if (t) { + cnf->sysctl = NULL; + unregister_net_sysctl_table(t->sysctl_header); + kfree(t); + } - cnf->sysctl = NULL; - unregister_net_sysctl_table(t->sysctl_header); - kfree(t); + inet_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL); } -static void devinet_sysctl_register(struct in_device *idev) +static int devinet_sysctl_register(struct in_device *idev) { - neigh_sysctl_register(idev->dev, idev->arp_parms, "ipv4", NULL); - __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, - &idev->cnf); + int err; + + if (!sysctl_dev_name_is_allowed(idev->dev->name)) + return -EINVAL; + + err = neigh_sysctl_register(idev->dev, idev->arp_parms, NULL); + if (err) + return err; + err = __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, + idev->dev->ifindex, &idev->cnf); + if (err) + neigh_sysctl_unregister(idev->arp_parms); + return err; } static void devinet_sysctl_unregister(struct in_device *idev) { - __devinet_sysctl_unregister(&idev->cnf); + struct net *net = dev_net(idev->dev); + + __devinet_sysctl_unregister(net, &idev->cnf, idev->dev->ifindex); neigh_sysctl_unregister(idev->arp_parms); } @@ -2175,95 +2740,133 @@ static struct ctl_table ctl_forward_entry[] = { .extra1 = &ipv4_devconf, .extra2 = &init_net, }, - { }, }; #endif static __net_init int devinet_init_net(struct net *net) { - int err; - struct ipv4_devconf *all, *dflt; #ifdef CONFIG_SYSCTL - struct ctl_table *tbl = ctl_forward_entry; struct ctl_table_header *forw_hdr; + struct ctl_table *tbl; #endif + struct ipv4_devconf *all, *dflt; + int err; + int i; err = -ENOMEM; - all = &ipv4_devconf; - dflt = &ipv4_devconf_dflt; + net->ipv4.inet_addr_lst = kmalloc_array(IN4_ADDR_HSIZE, + sizeof(struct hlist_head), + GFP_KERNEL); + if (!net->ipv4.inet_addr_lst) + goto err_alloc_hash; - if (!net_eq(net, &init_net)) { - all = kmemdup(all, sizeof(ipv4_devconf), GFP_KERNEL); - if (all == NULL) - goto err_alloc_all; + all = kmemdup(&ipv4_devconf, sizeof(ipv4_devconf), GFP_KERNEL); + if (!all) + goto err_alloc_all; - dflt = kmemdup(dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL); - if (dflt == NULL) - goto err_alloc_dflt; + dflt = kmemdup(&ipv4_devconf_dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL); + if (!dflt) + goto err_alloc_dflt; #ifdef CONFIG_SYSCTL - tbl = kmemdup(tbl, sizeof(ctl_forward_entry), GFP_KERNEL); - if (tbl == NULL) - goto err_alloc_ctl; + tbl = kmemdup(ctl_forward_entry, sizeof(ctl_forward_entry), GFP_KERNEL); + if (!tbl) + goto err_alloc_ctl; - tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1]; - tbl[0].extra1 = all; - tbl[0].extra2 = net; + tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1]; + tbl[0].extra1 = all; + tbl[0].extra2 = net; #endif + + if (!net_eq(net, &init_net)) { + switch (net_inherit_devconf()) { + case 3: + /* copy from the current netns */ + memcpy(all, current->nsproxy->net_ns->ipv4.devconf_all, + sizeof(ipv4_devconf)); + memcpy(dflt, + current->nsproxy->net_ns->ipv4.devconf_dflt, + sizeof(ipv4_devconf_dflt)); + break; + case 0: + case 1: + /* copy from init_net */ + memcpy(all, init_net.ipv4.devconf_all, + sizeof(ipv4_devconf)); + memcpy(dflt, init_net.ipv4.devconf_dflt, + sizeof(ipv4_devconf_dflt)); + break; + case 2: + /* use compiled values */ + break; + } } #ifdef CONFIG_SYSCTL - err = __devinet_sysctl_register(net, "all", all); + err = __devinet_sysctl_register(net, "all", NETCONFA_IFINDEX_ALL, all); if (err < 0) goto err_reg_all; - err = __devinet_sysctl_register(net, "default", dflt); + err = __devinet_sysctl_register(net, "default", + NETCONFA_IFINDEX_DEFAULT, dflt); if (err < 0) goto err_reg_dflt; err = -ENOMEM; - forw_hdr = register_net_sysctl(net, "net/ipv4", tbl); - if (forw_hdr == NULL) + forw_hdr = register_net_sysctl_sz(net, "net/ipv4", tbl, + ARRAY_SIZE(ctl_forward_entry)); + if (!forw_hdr) goto err_reg_ctl; net->ipv4.forw_hdr = forw_hdr; #endif + for (i = 0; i < IN4_ADDR_HSIZE; i++) + INIT_HLIST_HEAD(&net->ipv4.inet_addr_lst[i]); + + INIT_DEFERRABLE_WORK(&net->ipv4.addr_chk_work, check_lifetime); + net->ipv4.devconf_all = all; net->ipv4.devconf_dflt = dflt; return 0; #ifdef CONFIG_SYSCTL err_reg_ctl: - __devinet_sysctl_unregister(dflt); + __devinet_sysctl_unregister(net, dflt, NETCONFA_IFINDEX_DEFAULT); err_reg_dflt: - __devinet_sysctl_unregister(all); + __devinet_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: - if (tbl != ctl_forward_entry) - kfree(tbl); + kfree(tbl); err_alloc_ctl: #endif - if (dflt != &ipv4_devconf_dflt) - kfree(dflt); + kfree(dflt); err_alloc_dflt: - if (all != &ipv4_devconf) - kfree(all); + kfree(all); err_alloc_all: + kfree(net->ipv4.inet_addr_lst); +err_alloc_hash: return err; } static __net_exit void devinet_exit_net(struct net *net) { #ifdef CONFIG_SYSCTL - struct ctl_table *tbl; + const struct ctl_table *tbl; +#endif + cancel_delayed_work_sync(&net->ipv4.addr_chk_work); + +#ifdef CONFIG_SYSCTL tbl = net->ipv4.forw_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.forw_hdr); - __devinet_sysctl_unregister(net->ipv4.devconf_dflt); - __devinet_sysctl_unregister(net->ipv4.devconf_all); + __devinet_sysctl_unregister(net, net->ipv4.devconf_dflt, + NETCONFA_IFINDEX_DEFAULT); + __devinet_sysctl_unregister(net, net->ipv4.devconf_all, + NETCONFA_IFINDEX_ALL); kfree(tbl); #endif kfree(net->ipv4.devconf_dflt); kfree(net->ipv4.devconf_all); + kfree(net->ipv4.inet_addr_lst); } static __net_initdata struct pernet_operations devinet_ops = { @@ -2271,7 +2874,7 @@ static __net_initdata struct pernet_operations devinet_ops = { .exit = devinet_exit_net, }; -static struct rtnl_af_ops inet_af_ops = { +static struct rtnl_af_ops inet_af_ops __read_mostly = { .family = AF_INET, .fill_link_af = inet_fill_link_af, .get_link_af_size = inet_get_link_af_size, @@ -2279,26 +2882,27 @@ static struct rtnl_af_ops inet_af_ops = { .set_link_af = inet_set_link_af, }; +static const struct rtnl_msg_handler devinet_rtnl_msg_handlers[] __initconst = { + {.protocol = PF_INET, .msgtype = RTM_NEWADDR, .doit = inet_rtm_newaddr, + .flags = RTNL_FLAG_DOIT_PERNET}, + {.protocol = PF_INET, .msgtype = RTM_DELADDR, .doit = inet_rtm_deladdr, + .flags = RTNL_FLAG_DOIT_PERNET}, + {.protocol = PF_INET, .msgtype = RTM_GETADDR, .dumpit = inet_dump_ifaddr, + .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, + {.protocol = PF_INET, .msgtype = RTM_GETNETCONF, + .doit = inet_netconf_get_devconf, .dumpit = inet_netconf_dump_devconf, + .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, + {.owner = THIS_MODULE, .protocol = PF_INET, .msgtype = RTM_GETMULTICAST, + .dumpit = inet_dump_ifmcaddr, .flags = RTNL_FLAG_DUMP_UNLOCKED}, +}; + void __init devinet_init(void) { - int i; - - for (i = 0; i < IN4_ADDR_HSIZE; i++) - INIT_HLIST_HEAD(&inet_addr_lst[i]); - register_pernet_subsys(&devinet_ops); - - register_gifconf(PF_INET, inet_gifconf); register_netdevice_notifier(&ip_netdev_notifier); - schedule_delayed_work(&check_lifetime_work, 0); - - rtnl_af_register(&inet_af_ops); + if (rtnl_af_register(&inet_af_ops)) + panic("Unable to register inet_af_ops\n"); - rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL); - rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, NULL); - rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, NULL); - rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf, - inet_netconf_dump_devconf, NULL); + rtnl_register_many(devinet_rtnl_msg_handlers); } - |