diff options
| author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-08-07 13:11:22 +0000 |
|---|---|---|
| committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-08-07 13:11:22 +0000 |
| commit | b20732900e4636a467c0183a47f7396700f5f743 (patch) | |
| tree | 42f079ff82e701ebcb76829974b4caca3e5b6798 /net/ipv6 | |
| parent | Adding upstream version 6.8.12. (diff) | |
| download | linux-b20732900e4636a467c0183a47f7396700f5f743.tar.xz linux-b20732900e4636a467c0183a47f7396700f5f743.zip | |
Adding upstream version 6.9.7.upstream/6.9.7
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'net/ipv6')
42 files changed, 980 insertions, 762 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c4e2f9d35e..779aa6ecdd 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -195,6 +195,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, + .regen_min_advance = REGEN_MIN_ADVANCE, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, @@ -257,6 +258,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, + .regen_min_advance = REGEN_MIN_ADVANCE, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, @@ -549,7 +551,8 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, goto out; if ((all || type == NETCONFA_FORWARDING) && - nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0) + nla_put_s32(skb, NETCONFA_FORWARDING, + READ_ONCE(devconf->forwarding)) < 0) goto nla_put_failure; #ifdef CONFIG_IPV6_MROUTE if ((all || type == NETCONFA_MC_FORWARDING) && @@ -558,12 +561,13 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, goto nla_put_failure; #endif if ((all || type == NETCONFA_PROXY_NEIGH) && - nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0) + nla_put_s32(skb, NETCONFA_PROXY_NEIGH, + READ_ONCE(devconf->proxy_ndp)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, - devconf->ignore_routes_with_linkdown) < 0) + READ_ONCE(devconf->ignore_routes_with_linkdown)) < 0) goto nla_put_failure; out: @@ -713,7 +717,7 @@ errout: static u32 inet6_base_seq(const struct net *net) { u32 res = atomic_read(&net->ipv6.dev_addr_genid) + - net->dev_base_seq; + READ_ONCE(net->dev_base_seq); /* Must not return 0 (see nl_dump_check_consistent()). * Chose a value far away from 0. @@ -723,17 +727,18 @@ static u32 inet6_base_seq(const struct net *net) return res; } - static int inet6_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; struct net_device *dev; struct inet6_dev *idev; - struct hlist_head *head; + int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; @@ -750,64 +755,46 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb, } } - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - rcu_read_lock(); - cb->seq = inet6_base_seq(net); - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - idev = __in6_dev_get(dev); - if (!idev) - goto cont; - - if (inet6_netconf_fill_devconf(skb, dev->ifindex, - &idev->cnf, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, - NLM_F_MULTI, - NETCONFA_ALL) < 0) { - rcu_read_unlock(); - goto done; - } - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); -cont: - idx++; - } - rcu_read_unlock(); + rcu_read_lock(); + for_each_netdev_dump(net, dev, ctx->ifindex) { + idev = __in6_dev_get(dev); + if (!idev) + continue; + err = inet6_netconf_fill_devconf(skb, dev->ifindex, + &idev->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 (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, - net->ipv6.devconf_all, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, NLM_F_MULTI, - NETCONFA_ALL) < 0) + if (ctx->all_default == 0) { + err = inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, + net->ipv6.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 (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, - net->ipv6.devconf_dflt, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, NLM_F_MULTI, - NETCONFA_ALL) < 0) + ctx->all_default++; + } + if (ctx->all_default == 1) { + err = inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, + net->ipv6.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 @@ -867,7 +854,8 @@ static void addrconf_forward_change(struct net *net, __s32 newf) idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.forwarding) ^ (!newf); - idev->cnf.forwarding = newf; + + WRITE_ONCE(idev->cnf.forwarding, newf); if (changed) dev_forward_change(idev); } @@ -884,7 +872,7 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) net = (struct net *)table->extra2; old = *p; - *p = newf; + WRITE_ONCE(*p, newf); if (p == &net->ipv6.devconf_dflt->forwarding) { if ((!newf) ^ (!old)) @@ -899,7 +887,7 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) if (p == &net->ipv6.devconf_all->forwarding) { int old_dflt = net->ipv6.devconf_dflt->forwarding; - net->ipv6.devconf_dflt->forwarding = newf; + WRITE_ONCE(net->ipv6.devconf_dflt->forwarding, newf); if ((!newf) ^ (!old_dflt)) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, @@ -931,7 +919,7 @@ static void addrconf_linkdown_change(struct net *net, __s32 newf) if (idev) { int changed = (!idev->cnf.ignore_routes_with_linkdown) ^ (!newf); - idev->cnf.ignore_routes_with_linkdown = newf; + WRITE_ONCE(idev->cnf.ignore_routes_with_linkdown, newf); if (changed) inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, @@ -952,7 +940,7 @@ static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf) net = (struct net *)table->extra2; old = *p; - *p = newf; + WRITE_ONCE(*p, newf); if (p == &net->ipv6.devconf_dflt->ignore_routes_with_linkdown) { if ((!newf) ^ (!old)) @@ -966,7 +954,7 @@ static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf) } if (p == &net->ipv6.devconf_all->ignore_routes_with_linkdown) { - net->ipv6.devconf_dflt->ignore_routes_with_linkdown = newf; + WRITE_ONCE(net->ipv6.devconf_dflt->ignore_routes_with_linkdown, newf); addrconf_linkdown_change(net, newf); if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, @@ -1270,6 +1258,7 @@ static void cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt, bool del_peer) { + struct fib6_table *table; struct fib6_info *f6i; f6i = addrconf_get_prefix_route(del_peer ? &ifp->peer_addr : &ifp->addr, @@ -1279,8 +1268,15 @@ cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, if (del_rt) ip6_del_rt(dev_net(ifp->idev->dev), f6i, false); else { - if (!(f6i->fib6_flags & RTF_EXPIRES)) + if (!(f6i->fib6_flags & RTF_EXPIRES)) { + table = f6i->fib6_table; + spin_lock_bh(&table->tb6_lock); + fib6_set_expires(f6i, expires); + fib6_add_gc_list(f6i); + + spin_unlock_bh(&table->tb6_lock); + } fib6_info_release(f6i); } } @@ -1346,12 +1342,21 @@ out: in6_ifa_put(ifp); } +static unsigned long ipv6_get_regen_advance(const struct inet6_dev *idev) +{ + return READ_ONCE(idev->cnf.regen_min_advance) + + READ_ONCE(idev->cnf.regen_max_retry) * + READ_ONCE(idev->cnf.dad_transmits) * + max(NEIGH_VAR(idev->nd_parms, RETRANS_TIME), HZ/100) / HZ; +} + static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, bool block) { struct inet6_dev *idev = ifp->idev; unsigned long tmp_tstamp, age; unsigned long regen_advance; unsigned long now = jiffies; + u32 if_public_preferred_lft; s32 cnf_temp_preferred_lft; struct inet6_ifaddr *ift; struct ifa6_config cfg; @@ -1363,7 +1368,7 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, bool block) retry: in6_dev_hold(idev); - if (idev->cnf.use_tempaddr <= 0) { + if (READ_ONCE(idev->cnf.use_tempaddr) <= 0) { write_unlock_bh(&idev->lock); pr_info("%s: use_tempaddr is disabled\n", __func__); in6_dev_put(idev); @@ -1371,8 +1376,8 @@ retry: goto out; } spin_lock_bh(&ifp->lock); - if (ifp->regen_count++ >= idev->cnf.regen_max_retry) { - idev->cnf.use_tempaddr = -1; /*XXX*/ + if (ifp->regen_count++ >= READ_ONCE(idev->cnf.regen_max_retry)) { + WRITE_ONCE(idev->cnf.use_tempaddr, -1); /*XXX*/ spin_unlock_bh(&ifp->lock); write_unlock_bh(&idev->lock); pr_warn("%s: regeneration time exceeded - disabled temporary address support\n", @@ -1387,16 +1392,14 @@ retry: age = (now - ifp->tstamp) / HZ; - regen_advance = idev->cnf.regen_max_retry * - idev->cnf.dad_transmits * - max(NEIGH_VAR(idev->nd_parms, RETRANS_TIME), HZ/100) / HZ; + regen_advance = ipv6_get_regen_advance(idev); /* recalculate max_desync_factor each time and update * idev->desync_factor if it's larger */ cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft); max_desync_factor = min_t(long, - idev->cnf.max_desync_factor, + READ_ONCE(idev->cnf.max_desync_factor), cnf_temp_preferred_lft - regen_advance); if (unlikely(idev->desync_factor > max_desync_factor)) { @@ -1409,11 +1412,13 @@ retry: } } + if_public_preferred_lft = ifp->prefered_lft; + memset(&cfg, 0, sizeof(cfg)); cfg.valid_lft = min_t(__u32, ifp->valid_lft, - idev->cnf.temp_valid_lft + age); + READ_ONCE(idev->cnf.temp_valid_lft) + age); cfg.preferred_lft = cnf_temp_preferred_lft + age - idev->desync_factor; - cfg.preferred_lft = min_t(__u32, ifp->prefered_lft, cfg.preferred_lft); + cfg.preferred_lft = min_t(__u32, if_public_preferred_lft, cfg.preferred_lft); cfg.preferred_lft = min_t(__u32, cfg.valid_lft, cfg.preferred_lft); cfg.plen = ifp->prefix_len; @@ -1422,19 +1427,41 @@ retry: write_unlock_bh(&idev->lock); - /* A temporary address is created only if this calculated Preferred - * Lifetime is greater than REGEN_ADVANCE time units. In particular, - * an implementation must not create a temporary address with a zero - * Preferred Lifetime. + /* From RFC 4941: + * + * A temporary address is created only if this calculated Preferred + * Lifetime is greater than REGEN_ADVANCE time units. In + * particular, an implementation must not create a temporary address + * with a zero Preferred Lifetime. + * + * ... + * + * When creating a temporary address, the lifetime values MUST be + * derived from the corresponding prefix as follows: + * + * ... + * + * * Its Preferred Lifetime is the lower of the Preferred Lifetime + * of the public address or TEMP_PREFERRED_LIFETIME - + * DESYNC_FACTOR. + * + * To comply with the RFC's requirements, clamp the preferred lifetime + * to a minimum of regen_advance, unless that would exceed valid_lft or + * ifp->prefered_lft. + * * Use age calculation as in addrconf_verify to avoid unnecessary * temporary addresses being generated. */ age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (cfg.preferred_lft <= regen_advance + age) { - in6_ifa_put(ifp); - in6_dev_put(idev); - ret = -1; - goto out; + cfg.preferred_lft = regen_advance + age + 1; + if (cfg.preferred_lft > cfg.valid_lft || + cfg.preferred_lft > if_public_preferred_lft) { + in6_ifa_put(ifp); + in6_dev_put(idev); + ret = -1; + goto out; + } } cfg.ifa_flags = IFA_F_TEMPORARY; @@ -1513,15 +1540,17 @@ static inline int ipv6_saddr_preferred(int type) return 0; } -static bool ipv6_use_optimistic_addr(struct net *net, - struct inet6_dev *idev) +static bool ipv6_use_optimistic_addr(const struct net *net, + const struct inet6_dev *idev) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (!idev) return false; - if (!net->ipv6.devconf_all->optimistic_dad && !idev->cnf.optimistic_dad) + if (!READ_ONCE(net->ipv6.devconf_all->optimistic_dad) && + !READ_ONCE(idev->cnf.optimistic_dad)) return false; - if (!net->ipv6.devconf_all->use_optimistic && !idev->cnf.use_optimistic) + if (!READ_ONCE(net->ipv6.devconf_all->use_optimistic) && + !READ_ONCE(idev->cnf.use_optimistic)) return false; return true; @@ -1530,13 +1559,14 @@ static bool ipv6_use_optimistic_addr(struct net *net, #endif } -static bool ipv6_allow_optimistic_dad(struct net *net, - struct inet6_dev *idev) +static bool ipv6_allow_optimistic_dad(const struct net *net, + const struct inet6_dev *idev) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (!idev) return false; - if (!net->ipv6.devconf_all->optimistic_dad && !idev->cnf.optimistic_dad) + if (!READ_ONCE(net->ipv6.devconf_all->optimistic_dad) && + !READ_ONCE(idev->cnf.optimistic_dad)) return false; return true; @@ -1642,7 +1672,7 @@ static int ipv6_get_saddr_eval(struct net *net, */ int preftmp = dst->prefs & (IPV6_PREFER_SRC_PUBLIC|IPV6_PREFER_SRC_TMP) ? !!(dst->prefs & IPV6_PREFER_SRC_TMP) : - score->ifa->idev->cnf.use_tempaddr >= 2; + READ_ONCE(score->ifa->idev->cnf.use_tempaddr) >= 2; ret = (!(score->ifa->flags & IFA_F_TEMPORARY)) ^ preftmp; break; } @@ -1818,7 +1848,7 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, idev = __in6_dev_get(dst_dev); if ((dst_type & IPV6_ADDR_MULTICAST) || dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL || - (idev && idev->cnf.use_oif_addrs_only)) { + (idev && READ_ONCE(idev->cnf.use_oif_addrs_only))) { use_oif_addr = true; } } @@ -2126,6 +2156,7 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net *net = dev_net(idev->dev); + int max_addresses; if (addrconf_dad_end(ifp)) { in6_ifa_put(ifp); @@ -2163,9 +2194,9 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) spin_unlock_bh(&ifp->lock); - if (idev->cnf.max_addresses && - ipv6_count_addresses(idev) >= - idev->cnf.max_addresses) + max_addresses = READ_ONCE(idev->cnf.max_addresses); + if (max_addresses && + ipv6_count_addresses(idev) >= max_addresses) goto lock_errdad; net_info_ratelimited("%s: generating new stable privacy address because of DAD conflict\n", @@ -2562,11 +2593,11 @@ static void manage_tempaddrs(struct inet6_dev *idev, * (TEMP_PREFERRED_LIFETIME - DESYNC_FACTOR), respectively. */ age = (now - ift->cstamp) / HZ; - max_valid = idev->cnf.temp_valid_lft - age; + max_valid = READ_ONCE(idev->cnf.temp_valid_lft) - age; if (max_valid < 0) max_valid = 0; - max_prefered = idev->cnf.temp_prefered_lft - + max_prefered = READ_ONCE(idev->cnf.temp_prefered_lft) - idev->desync_factor - age; if (max_prefered < 0) max_prefered = 0; @@ -2599,7 +2630,7 @@ static void manage_tempaddrs(struct inet6_dev *idev, if (list_empty(&idev->tempaddr_list) && (valid_lft || prefered_lft)) create = true; - if (create && idev->cnf.use_tempaddr > 0) { + if (create && READ_ONCE(idev->cnf.use_tempaddr) > 0) { /* When a new public address is created as described * in [ADDRCONF], also create a new temporary address. */ @@ -2627,7 +2658,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, int create = 0, update_lft = 0; if (!ifp && valid_lft) { - int max_addresses = in6_dev->cnf.max_addresses; + int max_addresses = READ_ONCE(in6_dev->cnf.max_addresses); struct ifa6_config cfg = { .pfx = addr, .plen = pinfo->prefix_len, @@ -2639,8 +2670,8 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, }; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD - if ((net->ipv6.devconf_all->optimistic_dad || - in6_dev->cnf.optimistic_dad) && + if ((READ_ONCE(net->ipv6.devconf_all->optimistic_dad) || + READ_ONCE(in6_dev->cnf.optimistic_dad)) && !net->ipv6.devconf_all->forwarding && sllao) cfg.ifa_flags |= IFA_F_OPTIMISTIC; #endif @@ -2689,7 +2720,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, */ update_lft = !create && stored_lft; - if (update_lft && !in6_dev->cnf.ra_honor_pio_life) { + if (update_lft && !READ_ONCE(in6_dev->cnf.ra_honor_pio_life)) { const u32 minimum_lft = min_t(u32, stored_lft, MIN_VALID_LIFETIME); valid_lft = max(valid_lft, minimum_lft); @@ -2698,7 +2729,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, if (update_lft) { ifp->valid_lft = valid_lft; ifp->prefered_lft = prefered_lft; - ifp->tstamp = now; + WRITE_ONCE(ifp->tstamp, now); flags = ifp->flags; ifp->flags &= ~IFA_F_DEPRECATED; spin_unlock_bh(&ifp->lock); @@ -2722,6 +2753,7 @@ EXPORT_SYMBOL_GPL(addrconf_prefix_rcv_add_addr); void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) { struct prefix_info *pinfo; + struct fib6_table *table; __u32 valid_lft; __u32 prefered_lft; int addr_type, err; @@ -2798,11 +2830,20 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) if (valid_lft == 0) { ip6_del_rt(net, rt, false); rt = NULL; - } else if (addrconf_finite_timeout(rt_expires)) { - /* not infinity */ - fib6_set_expires(rt, jiffies + rt_expires); } else { - fib6_clean_expires(rt); + table = rt->fib6_table; + spin_lock_bh(&table->tb6_lock); + + if (addrconf_finite_timeout(rt_expires)) { + /* not infinity */ + fib6_set_expires(rt, jiffies + rt_expires); + fib6_add_gc_list(rt); + } else { + fib6_clean_expires(rt); + fib6_remove_gc_list(rt); + } + + spin_unlock_bh(&table->tb6_lock); } } else if (valid_lft) { clock_t expires = 0; @@ -3263,8 +3304,8 @@ void addrconf_add_linklocal(struct inet6_dev *idev, struct inet6_ifaddr *ifp; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD - if ((dev_net(idev->dev)->ipv6.devconf_all->optimistic_dad || - idev->cnf.optimistic_dad) && + if ((READ_ONCE(dev_net(idev->dev)->ipv6.devconf_all->optimistic_dad) || + READ_ONCE(idev->cnf.optimistic_dad)) && !dev_net(idev->dev)->ipv6.devconf_all->forwarding) cfg.ifa_flags |= IFA_F_OPTIMISTIC; #endif @@ -3443,7 +3484,8 @@ static void addrconf_dev_config(struct net_device *dev) /* this device type has no EUI support */ if (dev->type == ARPHRD_NONE && idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) - idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_RANDOM; + WRITE_ONCE(idev->cnf.addr_gen_mode, + IN6_ADDR_GEN_MODE_RANDOM); addrconf_addr_gen(idev, false); } @@ -3621,7 +3663,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (idev) { rt6_mtu_change(dev, dev->mtu); - idev->cnf.mtu6 = dev->mtu; + WRITE_ONCE(idev->cnf.mtu6, dev->mtu); break; } @@ -3713,9 +3755,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (idev->cnf.mtu6 != dev->mtu && dev->mtu >= IPV6_MIN_MTU) { rt6_mtu_change(dev, dev->mtu); - idev->cnf.mtu6 = dev->mtu; + WRITE_ONCE(idev->cnf.mtu6, dev->mtu); } - idev->tstamp = jiffies; + WRITE_ONCE(idev->tstamp, jiffies); inet6_ifinfo_notify(RTM_NEWLINK, idev); /* @@ -3835,10 +3877,10 @@ static int addrconf_ifdown(struct net_device *dev, bool unregister) */ if (!unregister && !idev->cnf.disable_ipv6) { /* aggregate the system setting and interface setting */ - int _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; + int _keep_addr = READ_ONCE(net->ipv6.devconf_all->keep_addr_on_down); if (!_keep_addr) - _keep_addr = idev->cnf.keep_addr_on_down; + _keep_addr = READ_ONCE(idev->cnf.keep_addr_on_down); keep_addr = (_keep_addr > 0); } @@ -3957,7 +3999,7 @@ restart: ipv6_mc_down(idev); } - idev->tstamp = jiffies; + WRITE_ONCE(idev->tstamp, jiffies); idev->ra_mtu = 0; /* Last: Shot the device (if unregistered) */ @@ -3975,6 +4017,7 @@ static void addrconf_rs_timer(struct timer_list *t) struct inet6_dev *idev = from_timer(idev, t, rs_timer); struct net_device *dev = idev->dev; struct in6_addr lladdr; + int rtr_solicits; write_lock(&idev->lock); if (idev->dead || !(idev->if_flags & IF_READY)) @@ -3987,7 +4030,9 @@ static void addrconf_rs_timer(struct timer_list *t) if (idev->if_flags & IF_RA_RCVD) goto out; - if (idev->rs_probes++ < idev->cnf.rtr_solicits || idev->cnf.rtr_solicits < 0) { + rtr_solicits = READ_ONCE(idev->cnf.rtr_solicits); + + if (idev->rs_probes++ < rtr_solicits || rtr_solicits < 0) { write_unlock(&idev->lock); if (!ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE)) ndisc_send_rs(dev, &lladdr, @@ -3997,11 +4042,12 @@ static void addrconf_rs_timer(struct timer_list *t) write_lock(&idev->lock); idev->rs_interval = rfc3315_s14_backoff_update( - idev->rs_interval, idev->cnf.rtr_solicit_max_interval); + idev->rs_interval, + READ_ONCE(idev->cnf.rtr_solicit_max_interval)); /* The wait after the last probe can be shorter */ addrconf_mod_rs_timer(idev, (idev->rs_probes == - idev->cnf.rtr_solicits) ? - idev->cnf.rtr_solicit_delay : + READ_ONCE(idev->cnf.rtr_solicits)) ? + READ_ONCE(idev->cnf.rtr_solicit_delay) : idev->rs_interval); } else { /* @@ -4022,24 +4068,25 @@ put: */ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) { - unsigned long rand_num; struct inet6_dev *idev = ifp->idev; + unsigned long rand_num; u64 nonce; if (ifp->flags & IFA_F_OPTIMISTIC) rand_num = 0; else - rand_num = get_random_u32_below(idev->cnf.rtr_solicit_delay ? : 1); + rand_num = get_random_u32_below( + READ_ONCE(idev->cnf.rtr_solicit_delay) ? : 1); nonce = 0; - if (idev->cnf.enhanced_dad || - dev_net(idev->dev)->ipv6.devconf_all->enhanced_dad) { + if (READ_ONCE(idev->cnf.enhanced_dad) || + READ_ONCE(dev_net(idev->dev)->ipv6.devconf_all->enhanced_dad)) { do get_random_bytes(&nonce, 6); while (nonce == 0); } ifp->dad_nonce = nonce; - ifp->dad_probes = idev->cnf.dad_transmits; + ifp->dad_probes = READ_ONCE(idev->cnf.dad_transmits); addrconf_mod_dad_work(ifp, rand_num); } @@ -4059,8 +4106,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) net = dev_net(dev); if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || - (net->ipv6.devconf_all->accept_dad < 1 && - idev->cnf.accept_dad < 1) || + (READ_ONCE(net->ipv6.devconf_all->accept_dad) < 1 && + READ_ONCE(idev->cnf.accept_dad) < 1) || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { bool send_na = false; @@ -4152,8 +4199,8 @@ static void addrconf_dad_work(struct work_struct *w) action = DAD_ABORT; ifp->state = INET6_IFADDR_STATE_POSTDAD; - if ((dev_net(idev->dev)->ipv6.devconf_all->accept_dad > 1 || - idev->cnf.accept_dad > 1) && + if ((READ_ONCE(dev_net(idev->dev)->ipv6.devconf_all->accept_dad) > 1 || + READ_ONCE(idev->cnf.accept_dad) > 1) && !idev->cnf.disable_ipv6 && !(ifp->flags & IFA_F_STABLE_PRIVACY)) { struct in6_addr addr; @@ -4278,7 +4325,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, send_mld = ifp->scope == IFA_LINK && ipv6_lonely_lladdr(ifp); send_rs = send_mld && ipv6_accept_ra(ifp->idev) && - ifp->idev->cnf.rtr_solicits != 0 && + READ_ONCE(ifp->idev->cnf.rtr_solicits) != 0 && (dev->flags & IFF_LOOPBACK) == 0 && (dev->type != ARPHRD_TUNNEL) && !netif_is_team_port(dev); @@ -4292,8 +4339,8 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, /* send unsolicited NA if enabled */ if (send_na && - (ifp->idev->cnf.ndisc_notify || - dev_net(dev)->ipv6.devconf_all->ndisc_notify)) { + (READ_ONCE(ifp->idev->cnf.ndisc_notify) || + READ_ONCE(dev_net(dev)->ipv6.devconf_all->ndisc_notify))) { ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifp->addr, /*router=*/ !!ifp->idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, @@ -4313,7 +4360,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, write_lock_bh(&ifp->idev->lock); spin_lock(&ifp->lock); ifp->idev->rs_interval = rfc3315_s14_backoff_init( - ifp->idev->cnf.rtr_solicit_interval); + READ_ONCE(ifp->idev->cnf.rtr_solicit_interval)); ifp->idev->rs_probes = 1; ifp->idev->if_flags |= IF_RS_SENT; addrconf_mod_rs_timer(ifp->idev, ifp->idev->rs_interval); @@ -4593,9 +4640,7 @@ restart: !ifp->regen_count && ifp->ifpub) { /* This is a non-regenerated temporary addr. */ - unsigned long regen_advance = ifp->idev->cnf.regen_max_retry * - ifp->idev->cnf.dad_transmits * - max(NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME), HZ/100) / HZ; + unsigned long regen_advance = ipv6_get_regen_advance(ifp->idev); if (age + regen_advance >= ifp->prefered_lft) { struct inet6_ifaddr *ifpub = ifp->ifpub; @@ -4757,6 +4802,7 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, u32 flags, bool modify_peer) { + struct fib6_table *table; struct fib6_info *f6i; u32 prio; @@ -4777,10 +4823,18 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); } else { - if (!expires) + table = f6i->fib6_table; + spin_lock_bh(&table->tb6_lock); + + if (!(flags & RTF_EXPIRES)) { fib6_clean_expires(f6i); - else + fib6_remove_gc_list(f6i); + } else { fib6_set_expires(f6i, expires); + fib6_add_gc_list(f6i); + } + + spin_unlock_bh(&table->tb6_lock); fib6_info_release(f6i); } @@ -4843,13 +4897,13 @@ static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp, IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | IFA_F_NOPREFIXROUTE); ifp->flags |= cfg->ifa_flags; - ifp->tstamp = jiffies; - ifp->valid_lft = cfg->valid_lft; - ifp->prefered_lft = cfg->preferred_lft; - ifp->ifa_proto = cfg->ifa_proto; + WRITE_ONCE(ifp->tstamp, jiffies); + WRITE_ONCE(ifp->valid_lft, cfg->valid_lft); + WRITE_ONCE(ifp->prefered_lft, cfg->preferred_lft); + WRITE_ONCE(ifp->ifa_proto, cfg->ifa_proto); if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority) - ifp->rt_priority = cfg->rt_priority; + WRITE_ONCE(ifp->rt_priority, cfg->rt_priority); if (new_peer) ifp->peer_addr = *cfg->peer_pfx; @@ -5070,17 +5124,21 @@ struct inet6_fill_args { enum addr_type_t type; }; -static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, +static int inet6_fill_ifaddr(struct sk_buff *skb, + const struct inet6_ifaddr *ifa, struct inet6_fill_args *args) { - struct nlmsghdr *nlh; + struct nlmsghdr *nlh; u32 preferred, valid; + u32 flags, priority; + u8 proto; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; + flags = READ_ONCE(ifa->flags); put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope), ifa->idev->dev->ifindex); @@ -5088,13 +5146,14 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) goto error; - spin_lock_bh(&ifa->lock); - if (!((ifa->flags&IFA_F_PERMANENT) && - (ifa->prefered_lft == INFINITY_LIFE_TIME))) { - preferred = ifa->prefered_lft; - valid = ifa->valid_lft; + preferred = READ_ONCE(ifa->prefered_lft); + valid = READ_ONCE(ifa->valid_lft); + + if (!((flags & IFA_F_PERMANENT) && + (preferred == INFINITY_LIFE_TIME))) { if (preferred != INFINITY_LIFE_TIME) { - long tval = (jiffies - ifa->tstamp)/HZ; + long tval = (jiffies - READ_ONCE(ifa->tstamp)) / HZ; + if (preferred > tval) preferred -= tval; else @@ -5110,28 +5169,29 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, preferred = INFINITY_LIFE_TIME; valid = INFINITY_LIFE_TIME; } - spin_unlock_bh(&ifa->lock); if (!ipv6_addr_any(&ifa->peer_addr)) { if (nla_put_in6_addr(skb, IFA_LOCAL, &ifa->addr) < 0 || nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->peer_addr) < 0) goto error; - } else + } else { if (nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->addr) < 0) goto error; + } - if (ifa->rt_priority && - nla_put_u32(skb, IFA_RT_PRIORITY, ifa->rt_priority)) + priority = READ_ONCE(ifa->rt_priority); + if (priority && nla_put_u32(skb, IFA_RT_PRIORITY, priority)) goto error; - if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) + if (put_cacheinfo(skb, ifa->cstamp, READ_ONCE(ifa->tstamp), + preferred, valid) < 0) goto error; - if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0) + if (nla_put_u32(skb, IFA_FLAGS, flags) < 0) goto error; - if (ifa->ifa_proto && - nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) + proto = READ_ONCE(ifa->ifa_proto); + if (proto && nla_put_u8(skb, IFA_PROTO, proto)) goto error; nlmsg_end(skb, nlh); @@ -5142,12 +5202,13 @@ error: return -EMSGSIZE; } -static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, +static int inet6_fill_ifmcaddr(struct sk_buff *skb, + const struct ifmcaddr6 *ifmca, struct inet6_fill_args *args) { - struct nlmsghdr *nlh; - u8 scope = RT_SCOPE_UNIVERSE; int ifindex = ifmca->idev->dev->ifindex; + u8 scope = RT_SCOPE_UNIVERSE; + struct nlmsghdr *nlh; if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; @@ -5165,7 +5226,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || - put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp, + put_cacheinfo(skb, ifmca->mca_cstamp, READ_ONCE(ifmca->mca_tstamp), INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; @@ -5175,13 +5236,14 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, return 0; } -static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, +static int inet6_fill_ifacaddr(struct sk_buff *skb, + const struct ifacaddr6 *ifaca, struct inet6_fill_args *args) { struct net_device *dev = fib6_info_nh_dev(ifaca->aca_rt); int ifindex = dev ? dev->ifindex : 1; - struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; + struct nlmsghdr *nlh; if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; @@ -5199,7 +5261,7 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 || - put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp, + put_cacheinfo(skb, ifaca->aca_cstamp, READ_ONCE(ifaca->aca_tstamp), INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; @@ -5210,24 +5272,23 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, } /* called with rcu_read_lock() */ -static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, - struct netlink_callback *cb, int s_ip_idx, +static int in6_dump_addrs(const struct inet6_dev *idev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, struct inet6_fill_args *fillargs) { - struct ifmcaddr6 *ifmca; - struct ifacaddr6 *ifaca; + const struct ifmcaddr6 *ifmca; + const struct ifacaddr6 *ifaca; int ip_idx = 0; - int err = 1; + int err = 0; - read_lock_bh(&idev->lock); switch (fillargs->type) { case UNICAST_ADDR: { - struct inet6_ifaddr *ifa; + const struct inet6_ifaddr *ifa; fillargs->event = RTM_NEWADDR; /* unicast address incl. temp addr */ - list_for_each_entry(ifa, &idev->addr_list, if_list) { - if (ip_idx < s_ip_idx) + list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { + if (ip_idx < *s_ip_idx) goto next; err = inet6_fill_ifaddr(skb, ifa, fillargs); if (err < 0) @@ -5239,27 +5300,25 @@ next: break; } case MULTICAST_ADDR: - read_unlock_bh(&idev->lock); fillargs->event = RTM_GETMULTICAST; /* multicast address */ - for (ifmca = rtnl_dereference(idev->mc_list); + for (ifmca = rcu_dereference(idev->mc_list); ifmca; - ifmca = rtnl_dereference(ifmca->next), ip_idx++) { - if (ip_idx < s_ip_idx) + ifmca = rcu_dereference(ifmca->next), ip_idx++) { + if (ip_idx < *s_ip_idx) continue; err = inet6_fill_ifmcaddr(skb, ifmca, fillargs); if (err < 0) break; } - read_lock_bh(&idev->lock); break; case ANYCAST_ADDR: fillargs->event = RTM_GETANYCAST; /* anycast address */ - for (ifaca = idev->ac_list; ifaca; - ifaca = ifaca->aca_next, ip_idx++) { - if (ip_idx < s_ip_idx) + for (ifaca = rcu_dereference(idev->ac_list); ifaca; + ifaca = rcu_dereference(ifaca->aca_next), ip_idx++) { + if (ip_idx < *s_ip_idx) continue; err = inet6_fill_ifacaddr(skb, ifaca, fillargs); if (err < 0) @@ -5269,8 +5328,7 @@ next: default: break; } - read_unlock_bh(&idev->lock); - cb->args[2] = ip_idx; + *s_ip_idx = err ? ip_idx : 0; return err; } @@ -5333,6 +5391,7 @@ static int inet6_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type) { + struct net *tgt_net = sock_net(skb->sk); const struct nlmsghdr *nlh = cb->nlh; struct inet6_fill_args fillargs = { .portid = NETLINK_CB(cb->skb).portid, @@ -5341,72 +5400,53 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, .netnsid = -1, .type = type, }; - struct net *tgt_net = sock_net(skb->sk); - int idx, s_idx, s_ip_idx; - int h, s_h; + struct { + unsigned long ifindex; + int ip_idx; + } *ctx = (void *)cb->ctx; struct net_device *dev; struct inet6_dev *idev; - struct hlist_head *head; int err = 0; - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - s_ip_idx = cb->args[2]; - + rcu_read_lock(); if (cb->strict_check) { err = inet6_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) - goto put_tgt_net; + goto done; err = 0; if (fillargs.ifindex) { - dev = __dev_get_by_index(tgt_net, fillargs.ifindex); + dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); if (!dev) { err = -ENODEV; - goto put_tgt_net; + goto done; } idev = __in6_dev_get(dev); - if (idev) { - err = in6_dump_addrs(idev, skb, cb, s_ip_idx, + if (idev) + err = in6_dump_addrs(idev, skb, cb, + &ctx->ip_idx, &fillargs); - if (err > 0) - err = 0; - } - goto put_tgt_net; + goto done; } } - rcu_read_lock(); cb->seq = inet6_base_seq(tgt_net); - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &tgt_net->dev_index_head[h]; - 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; - idev = __in6_dev_get(dev); - if (!idev) - goto cont; - - if (in6_dump_addrs(idev, skb, cb, s_ip_idx, - &fillargs) < 0) - goto done; -cont: - idx++; - } + for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { + idev = __in6_dev_get(dev); + if (!idev) + continue; + err = in6_dump_addrs(idev, skb, cb, &ctx->ip_idx, + &fillargs); + if (err < 0) + goto done; } done: rcu_read_unlock(); - cb->args[0] = h; - cb->args[1] = idx; -put_tgt_net: if (fillargs.netnsid >= 0) put_net(tgt_net); - return skb->len ? : err; + return err; } static int inet6_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) @@ -5579,87 +5619,97 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); } -static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, - __s32 *array, int bytes) +static void ipv6_store_devconf(const struct ipv6_devconf *cnf, + __s32 *array, int bytes) { BUG_ON(bytes < (DEVCONF_MAX * 4)); memset(array, 0, bytes); - array[DEVCONF_FORWARDING] = cnf->forwarding; - array[DEVCONF_HOPLIMIT] = cnf->hop_limit; - array[DEVCONF_MTU6] = cnf->mtu6; - array[DEVCONF_ACCEPT_RA] = cnf->accept_ra; - array[DEVCONF_ACCEPT_REDIRECTS] = cnf->accept_redirects; - array[DEVCONF_AUTOCONF] = cnf->autoconf; - array[DEVCONF_DAD_TRANSMITS] = cnf->dad_transmits; - array[DEVCONF_RTR_SOLICITS] = cnf->rtr_solicits; + array[DEVCONF_FORWARDING] = READ_ONCE(cnf->forwarding); + array[DEVCONF_HOPLIMIT] = READ_ONCE(cnf->hop_limit); + array[DEVCONF_MTU6] = READ_ONCE(cnf->mtu6); + array[DEVCONF_ACCEPT_RA] = READ_ONCE(cnf->accept_ra); + array[DEVCONF_ACCEPT_REDIRECTS] = READ_ONCE(cnf->accept_redirects); + array[DEVCONF_AUTOCONF] = READ_ONCE(cnf->autoconf); + array[DEVCONF_DAD_TRANSMITS] = READ_ONCE(cnf->dad_transmits); + array[DEVCONF_RTR_SOLICITS] = READ_ONCE(cnf->rtr_solicits); array[DEVCONF_RTR_SOLICIT_INTERVAL] = - jiffies_to_msecs(cnf->rtr_solicit_interval); + jiffies_to_msecs(READ_ONCE(cnf->rtr_solicit_interval)); array[DEVCONF_RTR_SOLICIT_MAX_INTERVAL] = - jiffies_to_msecs(cnf->rtr_solicit_max_interval); + jiffies_to_msecs(READ_ONCE(cnf->rtr_solicit_max_interval)); array[DEVCONF_RTR_SOLICIT_DELAY] = - jiffies_to_msecs(cnf->rtr_solicit_delay); - array[DEVCONF_FORCE_MLD_VERSION] = cnf->force_mld_version; + jiffies_to_msecs(READ_ONCE(cnf->rtr_solicit_delay)); + array[DEVCONF_FORCE_MLD_VERSION] = READ_ONCE(cnf->force_mld_version); array[DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL] = - jiffies_to_msecs(cnf->mldv1_unsolicited_report_interval); + jiffies_to_msecs(READ_ONCE(cnf->mldv1_unsolicited_report_interval)); array[DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL] = - jiffies_to_msecs(cnf->mldv2_unsolicited_report_interval); - array[DEVCONF_USE_TEMPADDR] = cnf->use_tempaddr; - array[DEVCONF_TEMP_VALID_LFT] = cnf->temp_valid_lft; - array[DEVCONF_TEMP_PREFERED_LFT] = cnf->temp_prefered_lft; - array[DEVCONF_REGEN_MAX_RETRY] = cnf->regen_max_retry; - array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; - array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; - array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; - array[DEVCONF_RA_DEFRTR_METRIC] = cnf->ra_defrtr_metric; - array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit; - array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; + jiffies_to_msecs(READ_ONCE(cnf->mldv2_unsolicited_report_interval)); + array[DEVCONF_USE_TEMPADDR] = READ_ONCE(cnf->use_tempaddr); + array[DEVCONF_TEMP_VALID_LFT] = READ_ONCE(cnf->temp_valid_lft); + array[DEVCONF_TEMP_PREFERED_LFT] = READ_ONCE(cnf->temp_prefered_lft); + array[DEVCONF_REGEN_MAX_RETRY] = READ_ONCE(cnf->regen_max_retry); + array[DEVCONF_MAX_DESYNC_FACTOR] = READ_ONCE(cnf->max_desync_factor); + array[DEVCONF_MAX_ADDRESSES] = READ_ONCE(cnf->max_addresses); + array[DEVCONF_ACCEPT_RA_DEFRTR] = READ_ONCE(cnf->accept_ra_defrtr); + array[DEVCONF_RA_DEFRTR_METRIC] = READ_ONCE(cnf->ra_defrtr_metric); + array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = + READ_ONCE(cnf->accept_ra_min_hop_limit); + array[DEVCONF_ACCEPT_RA_PINFO] = READ_ONCE(cnf->accept_ra_pinfo); #ifdef CONFIG_IPV6_ROUTER_PREF - array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref; + array[DEVCONF_ACCEPT_RA_RTR_PREF] = READ_ONCE(cnf->accept_ra_rtr_pref); array[DEVCONF_RTR_PROBE_INTERVAL] = - jiffies_to_msecs(cnf->rtr_probe_interval); + jiffies_to_msecs(READ_ONCE(cnf->rtr_probe_interval)); #ifdef CONFIG_IPV6_ROUTE_INFO - array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = cnf->accept_ra_rt_info_min_plen; - array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen; + array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = + READ_ONCE(cnf->accept_ra_rt_info_min_plen); + array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = + READ_ONCE(cnf->accept_ra_rt_info_max_plen); #endif #endif - array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp; - array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route; + array[DEVCONF_PROXY_NDP] = READ_ONCE(cnf->proxy_ndp); + array[DEVCONF_ACCEPT_SOURCE_ROUTE] = + READ_ONCE(cnf->accept_source_route); #ifdef CONFIG_IPV6_OPTIMISTIC_DAD - array[DEVCONF_OPTIMISTIC_DAD] = cnf->optimistic_dad; - array[DEVCONF_USE_OPTIMISTIC] = cnf->use_optimistic; + array[DEVCONF_OPTIMISTIC_DAD] = READ_ONCE(cnf->optimistic_dad); + array[DEVCONF_USE_OPTIMISTIC] = READ_ONCE(cnf->use_optimistic); #endif #ifdef CONFIG_IPV6_MROUTE array[DEVCONF_MC_FORWARDING] = atomic_read(&cnf->mc_forwarding); #endif - array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; - array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; - array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; - array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify; - 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; - array[DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN] = cnf->ignore_routes_with_linkdown; + array[DEVCONF_DISABLE_IPV6] = READ_ONCE(cnf->disable_ipv6); + array[DEVCONF_ACCEPT_DAD] = READ_ONCE(cnf->accept_dad); + array[DEVCONF_FORCE_TLLAO] = READ_ONCE(cnf->force_tllao); + array[DEVCONF_NDISC_NOTIFY] = READ_ONCE(cnf->ndisc_notify); + array[DEVCONF_SUPPRESS_FRAG_NDISC] = + READ_ONCE(cnf->suppress_frag_ndisc); + array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = + READ_ONCE(cnf->accept_ra_from_local); + array[DEVCONF_ACCEPT_RA_MTU] = READ_ONCE(cnf->accept_ra_mtu); + array[DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN] = + READ_ONCE(cnf->ignore_routes_with_linkdown); /* we omit DEVCONF_STABLE_SECRET for now */ - array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; - array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast; - array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na; - array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down; - array[DEVCONF_SEG6_ENABLED] = cnf->seg6_enabled; + array[DEVCONF_USE_OIF_ADDRS_ONLY] = READ_ONCE(cnf->use_oif_addrs_only); + array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = + READ_ONCE(cnf->drop_unicast_in_l2_multicast); + array[DEVCONF_DROP_UNSOLICITED_NA] = READ_ONCE(cnf->drop_unsolicited_na); + array[DEVCONF_KEEP_ADDR_ON_DOWN] = READ_ONCE(cnf->keep_addr_on_down); + array[DEVCONF_SEG6_ENABLED] = READ_ONCE(cnf->seg6_enabled); #ifdef CONFIG_IPV6_SEG6_HMAC - array[DEVCONF_SEG6_REQUIRE_HMAC] = cnf->seg6_require_hmac; + array[DEVCONF_SEG6_REQUIRE_HMAC] = READ_ONCE(cnf->seg6_require_hmac); #endif - array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad; - array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode; - array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy; - array[DEVCONF_NDISC_TCLASS] = cnf->ndisc_tclass; - array[DEVCONF_RPL_SEG_ENABLED] = cnf->rpl_seg_enabled; - array[DEVCONF_IOAM6_ENABLED] = cnf->ioam6_enabled; - array[DEVCONF_IOAM6_ID] = cnf->ioam6_id; - array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; - array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier; - array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na; - array[DEVCONF_ACCEPT_RA_MIN_LFT] = cnf->accept_ra_min_lft; + array[DEVCONF_ENHANCED_DAD] = READ_ONCE(cnf->enhanced_dad); + array[DEVCONF_ADDR_GEN_MODE] = READ_ONCE(cnf->addr_gen_mode); + array[DEVCONF_DISABLE_POLICY] = READ_ONCE(cnf->disable_policy); + array[DEVCONF_NDISC_TCLASS] = READ_ONCE(cnf->ndisc_tclass); + array[DEVCONF_RPL_SEG_ENABLED] = READ_ONCE(cnf->rpl_seg_enabled); + array[DEVCONF_IOAM6_ENABLED] = READ_ONCE(cnf->ioam6_enabled); + array[DEVCONF_IOAM6_ID] = READ_ONCE(cnf->ioam6_id); + array[DEVCONF_IOAM6_ID_WIDE] = READ_ONCE(cnf->ioam6_id_wide); + array[DEVCONF_NDISC_EVICT_NOCARRIER] = + READ_ONCE(cnf->ndisc_evict_nocarrier); + array[DEVCONF_ACCEPT_UNTRACKED_NA] = + READ_ONCE(cnf->accept_untracked_na); + array[DEVCONF_ACCEPT_RA_MIN_LFT] = READ_ONCE(cnf->accept_ra_min_lft); } static inline size_t inet6_ifla6_size(void) @@ -5739,13 +5789,14 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, u32 ext_filter_mask) { - struct nlattr *nla; struct ifla_cacheinfo ci; + struct nlattr *nla; + u32 ra_mtu; - if (nla_put_u32(skb, IFLA_INET6_FLAGS, idev->if_flags)) + if (nla_put_u32(skb, IFLA_INET6_FLAGS, READ_ONCE(idev->if_flags))) goto nla_put_failure; ci.max_reasm_len = IPV6_MAXPLEN; - ci.tstamp = cstamp_delta(idev->tstamp); + ci.tstamp = cstamp_delta(READ_ONCE(idev->tstamp)); ci.reachable_time = jiffies_to_msecs(idev->nd_parms->reachable_time); ci.retrans_time = jiffies_to_msecs(NEIGH_VAR(idev->nd_parms, RETRANS_TIME)); if (nla_put(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci)) @@ -5777,11 +5828,12 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, memcpy(nla_data(nla), idev->token.s6_addr, nla_len(nla)); read_unlock_bh(&idev->lock); - if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->cnf.addr_gen_mode)) + if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, + READ_ONCE(idev->cnf.addr_gen_mode))) goto nla_put_failure; - if (idev->ra_mtu && - nla_put_u32(skb, IFLA_INET6_RA_MTU, idev->ra_mtu)) + ra_mtu = READ_ONCE(idev->ra_mtu); + if (ra_mtu && nla_put_u32(skb, IFLA_INET6_RA_MTU, ra_mtu)) goto nla_put_failure; return 0; @@ -5843,7 +5895,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token, return -EINVAL; } - if (idev->cnf.rtr_solicits == 0) { + if (READ_ONCE(idev->cnf.rtr_solicits) == 0) { NL_SET_ERR_MSG(extack, "Router solicitation is disabled on device"); return -EINVAL; @@ -5876,7 +5928,7 @@ update_lft: if (update_rs) { idev->if_flags |= IF_RS_SENT; idev->rs_interval = rfc3315_s14_backoff_init( - idev->cnf.rtr_solicit_interval); + READ_ONCE(idev->cnf.rtr_solicit_interval)); idev->rs_probes = 1; addrconf_mod_rs_timer(idev, idev->rs_interval); } @@ -5982,7 +6034,7 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla, if (tb[IFLA_INET6_ADDR_GEN_MODE]) { u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]); - idev->cnf.addr_gen_mode = mode; + WRITE_ONCE(idev->cnf.addr_gen_mode, mode); } return 0; @@ -5994,6 +6046,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, struct net_device *dev = idev->dev; struct ifinfomsg *hdr; struct nlmsghdr *nlh; + int ifindex, iflink; void *protoinfo; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags); @@ -6004,16 +6057,18 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, hdr->ifi_family = AF_INET6; hdr->__ifi_pad = 0; hdr->ifi_type = dev->type; - hdr->ifi_index = dev->ifindex; + ifindex = READ_ONCE(dev->ifindex); + hdr->ifi_index = ifindex; hdr->ifi_flags = dev_get_flags(dev); hdr->ifi_change = 0; + iflink = dev_get_iflink(dev); if (nla_put_string(skb, IFLA_IFNAME, dev->name) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || - nla_put_u32(skb, IFLA_MTU, dev->mtu) || - (dev->ifindex != dev_get_iflink(dev) && - nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) || + nla_put_u32(skb, IFLA_MTU, READ_ONCE(dev->mtu)) || + (ifindex != iflink && + nla_put_u32(skb, IFLA_LINK, iflink)) || nla_put_u8(skb, IFLA_OPERSTATE, netif_running(dev) ? READ_ONCE(dev->operstate) : IF_OPER_DOWN)) goto nla_put_failure; @@ -6061,50 +6116,39 @@ static int inet6_valid_dump_ifinfo(const struct nlmsghdr *nlh, static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - int h, s_h; - int idx = 0, s_idx; + struct { + unsigned long ifindex; + } *ctx = (void *)cb->ctx; struct net_device *dev; struct inet6_dev *idev; - struct hlist_head *head; + int err; /* only requests using strict checking can pass data to * influence the dump */ if (cb->strict_check) { - int err = inet6_valid_dump_ifinfo(cb->nlh, cb->extack); + err = inet6_valid_dump_ifinfo(cb->nlh, cb->extack); if (err < 0) return err; } - s_h = cb->args[0]; - s_idx = cb->args[1]; - + err = 0; rcu_read_lock(); - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - idev = __in6_dev_get(dev); - if (!idev) - goto cont; - if (inet6_fill_ifinfo(skb, idev, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWLINK, NLM_F_MULTI) < 0) - goto out; -cont: - idx++; - } + for_each_netdev_dump(net, dev, ctx->ifindex) { + idev = __in6_dev_get(dev); + if (!idev) + continue; + err = inet6_fill_ifinfo(skb, idev, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWLINK, NLM_F_MULTI); + if (err < 0) + break; } -out: rcu_read_unlock(); - cb->args[1] = idx; - cb->args[0] = h; - return skb->len; + return err; } void inet6_ifinfo_notify(int event, struct inet6_dev *idev) @@ -6335,21 +6379,20 @@ static void addrconf_disable_change(struct net *net, __s32 newf) static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) { - struct net *net; + struct net *net = (struct net *)table->extra2; int old; + if (p == &net->ipv6.devconf_dflt->disable_ipv6) { + WRITE_ONCE(*p, newf); + return 0; + } + if (!rtnl_trylock()) return restart_syscall(); - net = (struct net *)table->extra2; old = *p; WRITE_ONCE(*p, newf); - if (p == &net->ipv6.devconf_dflt->disable_ipv6) { - rtnl_unlock(); - return 0; - } - if (p == &net->ipv6.devconf_all->disable_ipv6) { WRITE_ONCE(net->ipv6.devconf_dflt->disable_ipv6, newf); addrconf_disable_change(net, newf); @@ -6462,24 +6505,25 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write, } if (idev->cnf.addr_gen_mode != new_val) { - idev->cnf.addr_gen_mode = new_val; + WRITE_ONCE(idev->cnf.addr_gen_mode, new_val); addrconf_init_auto_addrs(idev->dev); } } else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) { struct net_device *dev; - net->ipv6.devconf_dflt->addr_gen_mode = new_val; + WRITE_ONCE(net->ipv6.devconf_dflt->addr_gen_mode, new_val); for_each_netdev(net, dev) { idev = __in6_dev_get(dev); if (idev && idev->cnf.addr_gen_mode != new_val) { - idev->cnf.addr_gen_mode = new_val; + WRITE_ONCE(idev->cnf.addr_gen_mode, + new_val); addrconf_init_auto_addrs(idev->dev); } } } - *((u32 *)ctl->data) = new_val; + WRITE_ONCE(*((u32 *)ctl->data), new_val); } out: @@ -6538,14 +6582,15 @@ static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write, struct inet6_dev *idev = __in6_dev_get(dev); if (idev) { - idev->cnf.addr_gen_mode = - IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + WRITE_ONCE(idev->cnf.addr_gen_mode, + IN6_ADDR_GEN_MODE_STABLE_PRIVACY); } } } else { struct inet6_dev *idev = ctl->extra1; - idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + WRITE_ONCE(idev->cnf.addr_gen_mode, + IN6_ADDR_GEN_MODE_STABLE_PRIVACY); } out: @@ -6625,20 +6670,19 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) static int addrconf_disable_policy(struct ctl_table *ctl, int *valp, int val) { + struct net *net = (struct net *)ctl->extra2; struct inet6_dev *idev; - struct net *net; - if (!rtnl_trylock()) - return restart_syscall(); - - *valp = val; - - net = (struct net *)ctl->extra2; if (valp == &net->ipv6.devconf_dflt->disable_policy) { - rtnl_unlock(); + WRITE_ONCE(*valp, val); return 0; } + if (!rtnl_trylock()) + return restart_syscall(); + + WRITE_ONCE(*valp, val); + if (valp == &net->ipv6.devconf_all->disable_policy) { struct net_device *dev; @@ -6808,6 +6852,13 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = proc_dointvec, }, { + .procname = "regen_min_advance", + .data = &ipv6_devconf.regen_min_advance, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "regen_max_retry", .data = &ipv6_devconf.regen_max_retry, .maxlen = sizeof(int), @@ -7367,7 +7418,8 @@ int __init addrconf_init(void) if (err < 0) goto out_addrlabel; - addrconf_wq = create_workqueue("ipv6_addrconf"); + /* All works using addrconf_wq need to lock rtnl. */ + addrconf_wq = create_singlethread_workqueue("ipv6_addrconf"); if (!addrconf_wq) { err = -ENOMEM; goto out_nowq; @@ -7390,7 +7442,7 @@ int __init addrconf_init(void) rtnl_af_register(&inet6_ops); err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETLINK, - NULL, inet6_dump_ifinfo, 0); + NULL, inet6_dump_ifinfo, RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; @@ -7404,21 +7456,25 @@ int __init addrconf_init(void) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, inet6_dump_ifaddr, - RTNL_FLAG_DOIT_UNLOCKED); + RTNL_FLAG_DOIT_UNLOCKED | + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETMULTICAST, - NULL, inet6_dump_ifmcaddr, 0); + NULL, inet6_dump_ifmcaddr, + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETANYCAST, - NULL, inet6_dump_ifacaddr, 0); + NULL, inet6_dump_ifacaddr, + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf, inet6_netconf_dump_devconf, - RTNL_FLAG_DOIT_UNLOCKED); + RTNL_FLAG_DOIT_UNLOCKED | + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = ipv6_addr_label_rtnl_register(); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 959bfd9f63..8041dc181b 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -64,6 +64,7 @@ #include <net/xfrm.h> #include <net/ioam6.h> #include <net/rawv6.h> +#include <net/rps.h> #include <linux/uaccess.h> #include <linux/mroute6.h> @@ -736,7 +737,7 @@ const struct proto_ops inet6_dgram_ops = { .recvmsg = inet6_recvmsg, /* retpoline's sake */ .read_skb = udp_read_skb, .mmap = sock_no_mmap, - .set_peek_off = sk_set_peek_off, + .set_peek_off = udp_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index bb17f484ee..0f2506e353 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -296,7 +296,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) goto out; } - for (aca = idev->ac_list; aca; aca = aca->aca_next) { + for (aca = rtnl_dereference(idev->ac_list); aca; + aca = rtnl_dereference(aca->aca_next)) { if (ipv6_addr_equal(&aca->aca_addr, addr)) { aca->aca_users++; err = 0; @@ -317,13 +318,13 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) goto out; } - aca->aca_next = idev->ac_list; - idev->ac_list = aca; - /* Hold this for addrconf_join_solict() below before we unlock, * it is already exposed via idev->ac_list. */ aca_get(aca); + aca->aca_next = idev->ac_list; + rcu_assign_pointer(idev->ac_list, aca); + write_unlock_bh(&idev->lock); ipv6_add_acaddr_hash(net, aca); @@ -350,7 +351,8 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) write_lock_bh(&idev->lock); prev_aca = NULL; - for (aca = idev->ac_list; aca; aca = aca->aca_next) { + for (aca = rtnl_dereference(idev->ac_list); aca; + aca = rtnl_dereference(aca->aca_next)) { if (ipv6_addr_equal(&aca->aca_addr, addr)) break; prev_aca = aca; @@ -364,9 +366,9 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) return 0; } if (prev_aca) - prev_aca->aca_next = aca->aca_next; + rcu_assign_pointer(prev_aca->aca_next, aca->aca_next); else - idev->ac_list = aca->aca_next; + rcu_assign_pointer(idev->ac_list, aca->aca_next); write_unlock_bh(&idev->lock); ipv6_del_acaddr_hash(aca); addrconf_leave_solict(idev, &aca->aca_addr); @@ -392,8 +394,8 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev) struct ifacaddr6 *aca; write_lock_bh(&idev->lock); - while ((aca = idev->ac_list) != NULL) { - idev->ac_list = aca->aca_next; + while ((aca = rtnl_dereference(idev->ac_list)) != NULL) { + rcu_assign_pointer(idev->ac_list, aca->aca_next); write_unlock_bh(&idev->lock); ipv6_del_acaddr_hash(aca); @@ -420,11 +422,10 @@ static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *ad idev = __in6_dev_get(dev); if (idev) { - read_lock_bh(&idev->lock); - for (aca = idev->ac_list; aca; aca = aca->aca_next) + for (aca = rcu_dereference(idev->ac_list); aca; + aca = rcu_dereference(aca->aca_next)) if (ipv6_addr_equal(&aca->aca_addr, addr)) break; - read_unlock_bh(&idev->lock); return aca != NULL; } return false; @@ -477,30 +478,25 @@ bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev, struct ac6_iter_state { struct seq_net_private p; struct net_device *dev; - struct inet6_dev *idev; }; #define ac6_seq_private(seq) ((struct ac6_iter_state *)(seq)->private) static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq) { - struct ifacaddr6 *im = NULL; struct ac6_iter_state *state = ac6_seq_private(seq); struct net *net = seq_file_net(seq); + struct ifacaddr6 *im = NULL; - state->idev = NULL; for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; + idev = __in6_dev_get(state->dev); if (!idev) continue; - read_lock_bh(&idev->lock); - im = idev->ac_list; - if (im) { - state->idev = idev; + im = rcu_dereference(idev->ac_list); + if (im) break; - } - read_unlock_bh(&idev->lock); } return im; } @@ -508,22 +504,17 @@ static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq) static struct ifacaddr6 *ac6_get_next(struct seq_file *seq, struct ifacaddr6 *im) { struct ac6_iter_state *state = ac6_seq_private(seq); + struct inet6_dev *idev; - im = im->aca_next; + im = rcu_dereference(im->aca_next); while (!im) { - if (likely(state->idev != NULL)) - read_unlock_bh(&state->idev->lock); - state->dev = next_net_device_rcu(state->dev); - if (!state->dev) { - state->idev = NULL; + if (!state->dev) break; - } - state->idev = __in6_dev_get(state->dev); - if (!state->idev) + idev = __in6_dev_get(state->dev); + if (!idev) continue; - read_lock_bh(&state->idev->lock); - im = state->idev->ac_list; + im = rcu_dereference(idev->ac_list); } return im; } @@ -555,12 +546,6 @@ static void *ac6_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void ac6_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { - struct ac6_iter_state *state = ac6_seq_private(seq); - - if (likely(state->idev != NULL)) { - read_unlock_bh(&state->idev->lock); - state->idev = NULL; - } rcu_read_unlock(); } diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 1578ed9e97..eb8ee1e937 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -657,11 +657,8 @@ static int calipso_map_cat_ntoh(const struct calipso_doi *doi_def, net_clen_bits, spot + 1, 1); - if (spot < 0) { - if (spot == -2) - return -EFAULT; + if (spot < 0) return 0; - } ret_val = netlbl_catmap_setbit(&secattr->attr.mls.cat, spot, diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 02e9ffb63a..6789623b2b 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -50,6 +50,7 @@ #endif #include <net/rpl.h> #include <linux/ioam6.h> +#include <linux/ioam6_genl.h> #include <net/ioam6.h> #include <net/dst_metadata.h> @@ -378,9 +379,8 @@ static int ipv6_srh_rcv(struct sk_buff *skb) idev = __in6_dev_get(skb->dev); - accept_seg6 = net->ipv6.devconf_all->seg6_enabled; - if (accept_seg6 > idev->cnf.seg6_enabled) - accept_seg6 = idev->cnf.seg6_enabled; + accept_seg6 = min(READ_ONCE(net->ipv6.devconf_all->seg6_enabled), + READ_ONCE(idev->cnf.seg6_enabled)); if (!accept_seg6) { kfree_skb(skb); @@ -654,10 +654,13 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) struct ipv6_rt_hdr *hdr; struct rt0_hdr *rthdr; struct net *net = dev_net(skb->dev); - int accept_source_route = net->ipv6.devconf_all->accept_source_route; + int accept_source_route; - if (idev && accept_source_route > idev->cnf.accept_source_route) - accept_source_route = idev->cnf.accept_source_route; + accept_source_route = READ_ONCE(net->ipv6.devconf_all->accept_source_route); + + if (idev) + accept_source_route = min(accept_source_route, + READ_ONCE(idev->cnf.accept_source_route)); if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + @@ -801,7 +804,7 @@ looped_back: ip6_route_input(skb); if (skb_dst(skb)->error) { - skb_push(skb, skb->data - skb_network_header(skb)); + skb_push(skb, -skb_network_offset(skb)); dst_input(skb); return -1; } @@ -818,7 +821,7 @@ looped_back: goto looped_back; } - skb_push(skb, skb->data - skb_network_header(skb)); + skb_push(skb, -skb_network_offset(skb)); dst_input(skb); return -1; @@ -880,14 +883,6 @@ void ipv6_exthdrs_exit(void) Hop-by-hop options. **********************************/ -/* - * Note: we cannot rely on skb_dst(skb) before we assign it in ip6_route_input(). - */ -static inline struct net *ipv6_skb_net(struct sk_buff *skb) -{ - return skb_dst(skb) ? dev_net(skb_dst(skb)->dev) : dev_net(skb->dev); -} - /* Router Alert as of RFC 2711 */ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) @@ -918,7 +913,7 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) goto drop; /* Ignore if IOAM is not enabled on ingress */ - if (!__in6_dev_get(skb->dev)->cnf.ioam6_enabled) + if (!READ_ONCE(__in6_dev_get(skb->dev)->cnf.ioam6_enabled)) goto ignore; /* Truncated Option header */ @@ -938,7 +933,7 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) goto drop; /* Ignore if the IOAM namespace is unknown */ - ns = ioam6_namespace(ipv6_skb_net(skb), trace->namespace_id); + ns = ioam6_namespace(dev_net(skb->dev), trace->namespace_id); if (!ns) goto ignore; @@ -954,6 +949,9 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) + optoff + sizeof(*hdr)); ioam6_fill_trace_data(skb, ns, trace, true); + + ioam6_event(IOAM6_EVENT_TRACE, dev_net(skb->dev), + GFP_ATOMIC, (void *)trace, hdr->opt_len - 2); break; default: break; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 1635da0728..d285c1f6f1 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -212,7 +212,7 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, } else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) { res = true; } else { - struct rt6_info *rt = (struct rt6_info *)dst; + struct rt6_info *rt = dst_rt6_info(dst); int tmo = net->ipv6.sysctl.icmpv6_time; struct inet_peer *peer; @@ -241,7 +241,7 @@ static bool icmpv6_rt_has_prefsrc(struct sock *sk, u8 type, dst = ip6_route_output(net, sk, fl6); if (!dst->error) { - struct rt6_info *rt = (struct rt6_info *)dst; + struct rt6_info *rt = dst_rt6_info(dst); struct in6_addr prefsrc; rt6_get_prefsrc(rt, &prefsrc); @@ -616,7 +616,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (ip6_append_data(sk, icmpv6_getfrag, &msg, len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), - &ipc6, &fl6, (struct rt6_info *)dst, + &ipc6, &fl6, dst_rt6_info(dst), MSG_DONTWAIT)) { ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); @@ -803,7 +803,7 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb) if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), &ipc6, &fl6, - (struct rt6_info *)dst, MSG_DONTWAIT)) { + dst_rt6_info(dst), MSG_DONTWAIT)) { __ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 8c1ce78956..0601bad798 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -38,7 +38,7 @@ static inline struct ila_params *ila_params_lwtunnel( static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *orig_dst = skb_dst(skb); - struct rt6_info *rt = (struct rt6_info *)orig_dst; + struct rt6_info *rt = dst_rt6_info(orig_dst); struct ila_lwt *ilwt = ila_lwt_lwtunnel(orig_dst->lwtstate); struct dst_entry *dst; int err = -EINVAL; @@ -70,7 +70,7 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = orig_dst->dev->ifindex; fl6.flowi6_iif = LOOPBACK_IFINDEX; - fl6.daddr = *rt6_nexthop((struct rt6_info *)orig_dst, + fl6.daddr = *rt6_nexthop(dst_rt6_info(orig_dst), &ip6h->daddr); dst = ip6_route_output(net, NULL, &fl6); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b0e8d278e8..2e81383b66 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -14,6 +14,7 @@ #include <linux/random.h> #include <net/addrconf.h> +#include <net/hotdata.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> @@ -25,16 +26,13 @@ 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; - u32 lhash, fhash; net_get_random_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret)); - net_get_random_once(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); + net_get_random_once(&tcp_ipv6_hash_secret, sizeof(tcp_ipv6_hash_secret)); lhash = (__force u32)laddr->s6_addr32[3]; - fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret); + fhash = __ipv6_addr_jhash(faddr, tcp_ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, inet6_ehash_secret + net_hash_mix(net)); diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c index 571f0e4d9c..08c9295130 100644 --- a/net/ipv6/ioam6.c +++ b/net/ipv6/ioam6.c @@ -612,6 +612,68 @@ static const struct genl_ops ioam6_genl_ops[] = { }, }; +#define IOAM6_GENL_EV_GRP_OFFSET 0 + +static const struct genl_multicast_group ioam6_mcgrps[] = { + [IOAM6_GENL_EV_GRP_OFFSET] = { .name = IOAM6_GENL_EV_GRP_NAME, + .flags = GENL_MCAST_CAP_NET_ADMIN }, +}; + +static int ioam6_event_put_trace(struct sk_buff *skb, + struct ioam6_trace_hdr *trace, + unsigned int len) +{ + if (nla_put_u16(skb, IOAM6_EVENT_ATTR_TRACE_NAMESPACE, + be16_to_cpu(trace->namespace_id)) || + nla_put_u8(skb, IOAM6_EVENT_ATTR_TRACE_NODELEN, trace->nodelen) || + nla_put_u32(skb, IOAM6_EVENT_ATTR_TRACE_TYPE, + be32_to_cpu(trace->type_be32)) || + nla_put(skb, IOAM6_EVENT_ATTR_TRACE_DATA, + len - sizeof(struct ioam6_trace_hdr) - trace->remlen * 4, + trace->data + trace->remlen * 4)) + return 1; + + return 0; +} + +void ioam6_event(enum ioam6_event_type type, struct net *net, gfp_t gfp, + void *opt, unsigned int opt_len) +{ + struct nlmsghdr *nlh; + struct sk_buff *skb; + + if (!genl_has_listeners(&ioam6_genl_family, net, + IOAM6_GENL_EV_GRP_OFFSET)) + return; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); + if (!skb) + return; + + nlh = genlmsg_put(skb, 0, 0, &ioam6_genl_family, 0, type); + if (!nlh) + goto nla_put_failure; + + switch (type) { + case IOAM6_EVENT_UNSPEC: + WARN_ON_ONCE(1); + break; + case IOAM6_EVENT_TRACE: + if (ioam6_event_put_trace(skb, (struct ioam6_trace_hdr *)opt, + opt_len)) + goto nla_put_failure; + break; + } + + genlmsg_end(skb, nlh); + genlmsg_multicast_netns(&ioam6_genl_family, net, skb, 0, + IOAM6_GENL_EV_GRP_OFFSET, gfp); + return; + +nla_put_failure: + nlmsg_free(skb); +} + static struct genl_family ioam6_genl_family __ro_after_init = { .name = IOAM6_GENL_NAME, .version = IOAM6_GENL_VERSION, @@ -620,6 +682,8 @@ static struct genl_family ioam6_genl_family __ro_after_init = { .ops = ioam6_genl_ops, .n_ops = ARRAY_SIZE(ioam6_genl_ops), .resv_start_op = IOAM6_CMD_NS_SET_SCHEMA + 1, + .mcgrps = ioam6_mcgrps, + .n_mcgrps = ARRAY_SIZE(ioam6_mcgrps), .module = THIS_MODULE, }; @@ -663,7 +727,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, if (!skb->dev) raw16 = IOAM6_U16_UNAVAILABLE; else - raw16 = (__force u16)__in6_dev_get(skb->dev)->cnf.ioam6_id; + raw16 = (__force u16)READ_ONCE(__in6_dev_get(skb->dev)->cnf.ioam6_id); *(__be16 *)data = cpu_to_be16(raw16); data += sizeof(__be16); @@ -671,7 +735,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) raw16 = IOAM6_U16_UNAVAILABLE; else - raw16 = (__force u16)__in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id; + raw16 = (__force u16)READ_ONCE(__in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id); *(__be16 *)data = cpu_to_be16(raw16); data += sizeof(__be16); @@ -758,7 +822,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, if (!skb->dev) raw32 = IOAM6_U32_UNAVAILABLE; else - raw32 = __in6_dev_get(skb->dev)->cnf.ioam6_id_wide; + raw32 = READ_ONCE(__in6_dev_get(skb->dev)->cnf.ioam6_id_wide); *(__be32 *)data = cpu_to_be32(raw32); data += sizeof(__be32); @@ -766,7 +830,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) raw32 = IOAM6_U32_UNAVAILABLE; else - raw32 = __in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id_wide; + raw32 = READ_ONCE(__in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id_wide); *(__be32 *)data = cpu_to_be32(raw32); data += sizeof(__be32); diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index 7563f8c6aa..bf7120ecea 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -351,9 +351,9 @@ do_encap: goto drop; if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) { - preempt_disable(); + local_bh_disable(); dst = dst_cache_get(&ilwt->cache); - preempt_enable(); + local_bh_enable(); if (unlikely(!dst)) { struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -373,9 +373,9 @@ do_encap: goto drop; } - preempt_disable(); + local_bh_disable(); dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr); - preempt_enable(); + local_bh_enable(); } skb_dst_drop(skb); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 8184076a39..1ace4ac3ee 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -160,6 +160,8 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh) INIT_LIST_HEAD(&f6i->fib6_siblings); refcount_set(&f6i->fib6_ref, 1); + INIT_HLIST_NODE(&f6i->gc_link); + return f6i; } @@ -246,6 +248,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) net->ipv6.fib6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); + INIT_HLIST_HEAD(&table->tb6_gc_hlist); } return table; @@ -617,8 +620,11 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { - struct rt6_rtnl_dump_arg arg = { .filter.dump_exceptions = true, - .filter.dump_routes = true }; + struct rt6_rtnl_dump_arg arg = { + .filter.dump_exceptions = true, + .filter.dump_routes = true, + .filter.rtnl_held = true, + }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int h, s_h; @@ -751,8 +757,6 @@ static struct fib6_node *fib6_add_1(struct net *net, int bit; __be32 dir = 0; - RT6_TRACE("fib6_add_1\n"); - /* insert node in tree */ fn = root; @@ -961,6 +965,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, if (!fib6_nh->rt6i_pcpu) return; + rcu_read_lock(); /* release the reference to this fib entry from * all of its cached pcpu routes */ @@ -969,7 +974,9 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, struct rt6_info *pcpu_rt; ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); - pcpu_rt = *ppcpu_rt; + + /* Paired with xchg() in rt6_get_pcpu_route() */ + pcpu_rt = READ_ONCE(*ppcpu_rt); /* only dropping the 'from' reference if the cached route * is using 'match'. The cached pcpu_rt->from only changes @@ -983,6 +990,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, fib6_info_release(from); } } + rcu_read_unlock(); } struct fib6_nh_pcpu_arg { @@ -1057,6 +1065,9 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, lockdep_is_held(&table->tb6_lock)); } } + + fib6_clean_expires(rt); + fib6_remove_gc_list(rt); } /* @@ -1117,10 +1128,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, rt->fib6_nsiblings = 0; if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; - if (!(rt->fib6_flags & RTF_EXPIRES)) + if (!(rt->fib6_flags & RTF_EXPIRES)) { fib6_clean_expires(iter); - else + fib6_remove_gc_list(iter); + } else { fib6_set_expires(iter, rt->expires); + fib6_add_gc_list(iter); + } if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, @@ -1482,6 +1496,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, if (rt->nh) list_add(&rt->nh_list, &rt->nh->f6i_list); __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); + + if (rt->fib6_flags & RTF_EXPIRES) + fib6_add_gc_list(rt); + fib6_start_gc(info->nl_net, rt); } @@ -1806,7 +1824,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net, lockdep_is_held(&table->tb6_lock)); struct fib6_info *new_fn_leaf; - RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); + pr_debug("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; WARN_ON(fn->fn_flags & RTN_RTINFO); @@ -1869,7 +1887,8 @@ static struct fib6_node *fib6_repair_tree(struct net *net, FOR_WALKERS(net, w) { if (!child) { if (w->node == fn) { - RT6_TRACE("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate); + pr_debug("W %p adjusted by delnode 1, s=%d/%d\n", + w, w->state, nstate); w->node = pn; w->state = nstate; } @@ -1877,10 +1896,12 @@ static struct fib6_node *fib6_repair_tree(struct net *net, if (w->node == fn) { w->node = child; if (children&2) { - RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); + pr_debug("W %p adjusted by delnode 2, s=%d\n", + w, w->state); w->state = w->state >= FWS_R ? FWS_U : FWS_INIT; } else { - RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); + pr_debug("W %p adjusted by delnode 2, s=%d\n", + w, w->state); w->state = w->state >= FWS_C ? FWS_U : FWS_INIT; } } @@ -1908,8 +1929,6 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, struct net *net = info->nl_net; bool notify_del = false; - RT6_TRACE("fib6_del_route\n"); - /* If the deleted route is the first in the node and it is not part of * a multipath route, then we need to replace it with the next route * in the node, if exists. @@ -1958,7 +1977,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { - RT6_TRACE("walker %p adjusted by delroute\n", w); + pr_debug("walker %p adjusted by delroute\n", w); w->leaf = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); if (!w->leaf) @@ -2284,9 +2303,8 @@ static void fib6_flush_trees(struct net *net) * Garbage collection */ -static int fib6_age(struct fib6_info *rt, void *arg) +static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) { - struct fib6_gc_args *gc_args = arg; unsigned long now = jiffies; /* @@ -2296,7 +2314,7 @@ static int fib6_age(struct fib6_info *rt, void *arg) if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { if (time_after(now, rt->expires)) { - RT6_TRACE("expiring %p\n", rt); + pr_debug("expiring %p\n", rt); return -1; } gc_args->more++; @@ -2311,6 +2329,42 @@ static int fib6_age(struct fib6_info *rt, void *arg) return 0; } +static void fib6_gc_table(struct net *net, + struct fib6_table *tb6, + struct fib6_gc_args *gc_args) +{ + struct fib6_info *rt; + struct hlist_node *n; + struct nl_info info = { + .nl_net = net, + .skip_notify = false, + }; + + hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link) + if (fib6_age(rt, gc_args) == -1) + fib6_del(rt, &info); +} + +static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args) +{ + struct fib6_table *table; + struct hlist_head *head; + unsigned int h; + + rcu_read_lock(); + for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { + head = &net->ipv6.fib_table_hash[h]; + hlist_for_each_entry_rcu(table, head, tb6_hlist) { + spin_lock_bh(&table->tb6_lock); + + fib6_gc_table(net, table, gc_args); + + spin_unlock_bh(&table->tb6_lock); + } + } + rcu_read_unlock(); +} + void fib6_run_gc(unsigned long expires, struct net *net, bool force) { struct fib6_gc_args gc_args; @@ -2326,7 +2380,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force) net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = 0; - fib6_clean_all(net, fib6_age, &gc_args); + fib6_gc_all(net, &gc_args); now = jiffies; net->ipv6.ip6_rt_last_gc = now; @@ -2386,6 +2440,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); + INIT_HLIST_HEAD(&net->ipv6.fib6_main_tbl->tb6_gc_hlist); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl), @@ -2398,6 +2453,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); + INIT_HLIST_HEAD(&net->ipv6.fib6_local_tbl->tb6_gc_hlist); #endif fib6_tables_init(net); @@ -2447,10 +2503,8 @@ int __init fib6_init(void) { int ret = -ENOMEM; - fib6_node_kmem = kmem_cache_create("fib6_nodes", - sizeof(struct fib6_node), 0, - SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, - NULL); + fib6_node_kmem = KMEM_CACHE(fib6_node, + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT); if (!fib6_node_kmem) goto out; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 289b83347d..c89aef524d 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1636,21 +1636,19 @@ err_alloc_dev: return err; } -static void __net_exit ip6gre_exit_batch_net(struct list_head *net_list) +static void __net_exit ip6gre_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { struct net *net; - LIST_HEAD(list); - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) - ip6gre_destroy_tunnels(net, &list); - unregister_netdevice_many(&list); - rtnl_unlock(); + ip6gre_destroy_tunnels(net, dev_to_kill); } static struct pernet_operations ip6gre_net_ops = { .init = ip6gre_init_net, - .exit_batch = ip6gre_exit_batch_net, + .exit_batch_rtnl = ip6gre_exit_batch_rtnl, .id = &ip6gre_net_id, .size = sizeof(struct ip6gre_net), }; @@ -2410,7 +2408,7 @@ static void __exit ip6gre_fini(void) module_init(ip6gre_init); module_exit(ip6gre_fini); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)"); +MODULE_AUTHOR("D. Kozlov <xeb@mail.ru>"); MODULE_DESCRIPTION("GRE over IPv6 tunneling device"); MODULE_ALIAS_RTNL_LINK("ip6gre"); MODULE_ALIAS_RTNL_LINK("ip6gretap"); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 1ba97933c7..133610a49d 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -236,7 +236,7 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, if (!ipv6_addr_is_multicast(&hdr->daddr) && (skb->pkt_type == PACKET_BROADCAST || skb->pkt_type == PACKET_MULTICAST) && - idev->cnf.drop_unicast_in_l2_multicast) { + READ_ONCE(idev->cnf.drop_unicast_in_l2_multicast)) { SKB_DR_SET(reason, UNICAST_IN_L2_MULTICAST); goto err; } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 19ae2d4cd2..c8b909a990 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -420,14 +420,6 @@ static int ip4ip6_gro_complete(struct sk_buff *skb, int nhoff) return inet_gro_complete(skb, nhoff); } -static struct packet_offload ipv6_packet_offload __read_mostly = { - .type = cpu_to_be16(ETH_P_IPV6), - .callbacks = { - .gso_segment = ipv6_gso_segment, - .gro_receive = ipv6_gro_receive, - .gro_complete = ipv6_gro_complete, - }, -}; static struct sk_buff *sit_gso_segment(struct sk_buff *skb, netdev_features_t features) @@ -487,7 +479,15 @@ static int __init ipv6_offload_init(void) if (ipv6_exthdrs_offload_init() < 0) pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__); - dev_add_offload(&ipv6_packet_offload); + net_hotdata.ipv6_packet_offload = (struct packet_offload) { + .type = cpu_to_be16(ETH_P_IPV6), + .callbacks = { + .gso_segment = ipv6_gso_segment, + .gro_receive = ipv6_gro_receive, + .gro_complete = ipv6_gro_complete, + }, + }; + dev_add_offload(&net_hotdata.ipv6_packet_offload); inet_add_offload(&sit_offload, IPPROTO_IPV6); inet6_add_offload(&ip6ip6_offload, IPPROTO_IPV6); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 51b358f6c3..27d8725445 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -120,7 +120,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); rcu_read_lock(); - nexthop = rt6_nexthop((struct rt6_info *)dst, daddr); + nexthop = rt6_nexthop(dst_rt6_info(dst), daddr); neigh = __ipv6_neigh_lookup_noref(dev, nexthop); if (unlikely(IS_ERR_OR_NULL(neigh))) { @@ -501,7 +501,7 @@ int ip6_forward(struct sk_buff *skb) u32 mtu; idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); - if (net->ipv6.devconf_all->forwarding == 0) + if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0) goto error; if (skb->pkt_type != PACKET_HOST) @@ -513,8 +513,8 @@ int ip6_forward(struct sk_buff *skb) if (skb_warn_if_lro(skb)) goto drop; - if (!net->ipv6.devconf_all->disable_policy && - (!idev || !idev->cnf.disable_policy) && + if (!READ_ONCE(net->ipv6.devconf_all->disable_policy) && + (!idev || !READ_ONCE(idev->cnf.disable_policy)) && !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; @@ -552,7 +552,7 @@ int ip6_forward(struct sk_buff *skb) } /* XXX: idev->cnf.proxy_ndp? */ - if (net->ipv6.devconf_all->proxy_ndp && + if (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) { int proxied = ip6_forward_proxy_check(skb); if (proxied > 0) { @@ -599,7 +599,7 @@ int ip6_forward(struct sk_buff *skb) * send a redirect. */ - rt = (struct rt6_info *) dst; + rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_GATEWAY) target = &rt->rt6i_gateway; else @@ -856,7 +856,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct sk_buff *frag; - struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; bool mono_delivery_time = skb->mono_delivery_time; @@ -1063,7 +1063,7 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk, return NULL; } - rt = (struct rt6_info *)dst; + rt = dst_rt6_info(dst); /* Yes, checking route validity in not connected * case is not very simple. Take into account, * that we do not support routing by source, TOS, @@ -1118,7 +1118,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, struct rt6_info *rt; *dst = ip6_route_output(net, sk, fl6); - rt = (*dst)->error ? NULL : (struct rt6_info *)*dst; + rt = (*dst)->error ? NULL : dst_rt6_info(*dst); rcu_read_lock(); from = rt ? rcu_dereference(rt->from) : NULL; @@ -1159,7 +1159,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, * dst entry and replace it instead with the * dst entry of the nexthop router */ - rt = (struct rt6_info *) *dst; + rt = dst_rt6_info(*dst); rcu_read_lock(); n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); @@ -1423,7 +1423,7 @@ static int __ip6_append_data(struct sock *sk, int offset = 0; bool zc = false; u32 tskey = 0; - struct rt6_info *rt = (struct rt6_info *)cork->dst; + struct rt6_info *rt = dst_rt6_info(cork->dst); bool paged, hold_tskey, extra_uref = false; struct ipv6_txoptions *opt = v6_cork->opt; int csummode = CHECKSUM_NONE; @@ -1877,7 +1877,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, struct net *net = sock_net(sk); struct ipv6hdr *hdr; struct ipv6_txoptions *opt = v6_cork->opt; - struct rt6_info *rt = (struct rt6_info *)cork->base.dst; + struct rt6_info *rt = dst_rt6_info(cork->base.dst); struct flowi6 *fl6 = &cork->fl.u.ip6; unsigned char proto = fl6->flowi6_proto; @@ -1949,7 +1949,7 @@ out: int ip6_send_skb(struct sk_buff *skb) { struct net *net = sock_net(skb->sk); - struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int err; err = ip6_local_out(net, skb->sk, skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 70478027a7..e9cc315832 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -247,7 +247,6 @@ static void ip6_dev_free(struct net_device *dev) gro_cells_destroy(&t->gro_cells); dst_cache_destroy(&t->dst_cache); - free_percpu(dev->tstats); } static int ip6_tnl_create2(struct net_device *dev) @@ -1756,7 +1755,7 @@ int ip6_tnl_get_iflink(const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - return t->parms.link; + return READ_ONCE(t->parms.link); } EXPORT_SYMBOL(ip6_tnl_get_iflink); @@ -1848,6 +1847,7 @@ static void ip6_tnl_dev_setup(struct net_device *dev) dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); dev->features |= NETIF_F_LLTX; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); dev->features |= IPXIPX_FEATURES; @@ -1873,13 +1873,10 @@ ip6_tnl_dev_init_gen(struct net_device *dev) t->dev = dev; t->net = dev_net(dev); - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; ret = dst_cache_init(&t->dst_cache, GFP_KERNEL); if (ret) - goto free_stats; + return ret; ret = gro_cells_init(&t->gro_cells, dev); if (ret) @@ -1903,9 +1900,6 @@ ip6_tnl_dev_init_gen(struct net_device *dev) destroy_dst: dst_cache_destroy(&t->dst_cache); -free_stats: - free_percpu(dev->tstats); - dev->tstats = NULL; return ret; } @@ -2283,21 +2277,19 @@ err_alloc_dev: return err; } -static void __net_exit ip6_tnl_exit_batch_net(struct list_head *net_list) +static void __net_exit ip6_tnl_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { struct net *net; - LIST_HEAD(list); - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) - ip6_tnl_destroy_tunnels(net, &list); - unregister_netdevice_many(&list); - rtnl_unlock(); + ip6_tnl_destroy_tunnels(net, dev_to_kill); } static struct pernet_operations ip6_tnl_net_ops = { .init = ip6_tnl_init_net, - .exit_batch = ip6_tnl_exit_batch_net, + .exit_batch_rtnl = ip6_tnl_exit_batch_rtnl, .id = &ip6_tnl_net_id, .size = sizeof(struct ip6_tnl_net), }; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 1163ca6ea4..7f4f976aa2 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -1175,24 +1175,22 @@ err_alloc_dev: return err; } -static void __net_exit vti6_exit_batch_net(struct list_head *net_list) +static void __net_exit vti6_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { struct vti6_net *ip6n; struct net *net; - LIST_HEAD(list); - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) { ip6n = net_generic(net, vti6_net_id); - vti6_destroy_tunnels(ip6n, &list); + vti6_destroy_tunnels(ip6n, dev_to_kill); } - unregister_netdevice_many(&list); - rtnl_unlock(); } static struct pernet_operations vti6_net_ops = { .init = vti6_init_net, - .exit_batch = vti6_exit_batch_net, + .exit_batch_rtnl = vti6_exit_batch_rtnl, .id = &vti6_net_id, .size = sizeof(struct vti6_net), }; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 9782c180fe..dd342e6ecf 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1373,10 +1373,7 @@ int __init ip6_mr_init(void) { int err; - mrt_cachep = kmem_cache_create("ip6_mrt_cache", - sizeof(struct mfc6_cache), - 0, SLAB_HWCACHE_ALIGN, - NULL); + mrt_cachep = KMEM_CACHE(mfc6_cache, SLAB_HWCACHE_ALIGN); if (!mrt_cachep) return -ENOMEM; @@ -2276,7 +2273,7 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, int err; struct mr_table *mrt; struct mfc6_cache *cache; - struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) @@ -2595,7 +2592,9 @@ static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; - struct fib_dump_filter filter = {}; + struct fib_dump_filter filter = { + .rtnl_held = true, + }; int err; if (cb->strict_check) { diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 56c3c467f9..d4c28ec1bc 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -948,6 +948,8 @@ done: if (optlen < sizeof(int)) goto e_inval; retv = ip6_ra_control(sk, val); + if (retv == 0) + inet6_assign_bit(RTALERT, sk, valbool); break; case IPV6_FLOWLABEL_MGR: retv = ipv6_flowlabel_opt(sk, optval, optlen); @@ -1346,7 +1348,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, } if (val < 0) - val = sock_net(sk)->ipv6.devconf_all->hop_limit; + val = READ_ONCE(sock_net(sk)->ipv6.devconf_all->hop_limit); break; } @@ -1445,6 +1447,10 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->rxopt.bits.recvfragsize; break; + case IPV6_ROUTER_ALERT: + val = inet6_test_bit(RTALERT, sk); + break; + case IPV6_ROUTER_ALERT_ISOLATE: val = inet6_test_bit(RTALERT_ISOLATE, sk); break; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 76ee1615ff..7ba01d8cfb 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -159,9 +159,9 @@ static int unsolicited_report_interval(struct inet6_dev *idev) int iv; if (mld_in_v1_mode(idev)) - iv = idev->cnf.mldv1_unsolicited_report_interval; + iv = READ_ONCE(idev->cnf.mldv1_unsolicited_report_interval); else - iv = idev->cnf.mldv2_unsolicited_report_interval; + iv = READ_ONCE(idev->cnf.mldv2_unsolicited_report_interval); return iv > 0 ? iv : 1; } @@ -1202,15 +1202,15 @@ static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, static int mld_force_mld_version(const struct inet6_dev *idev) { + const struct net *net = dev_net(idev->dev); + int all_force; + + all_force = READ_ONCE(net->ipv6.devconf_all->force_mld_version); /* Normally, both are 0 here. If enforcement to a particular is * being used, individual device enforcement will have a lower * precedence over 'all' device (.../conf/all/force_mld_version). */ - - if (dev_net(idev->dev)->ipv6.devconf_all->force_mld_version != 0) - return dev_net(idev->dev)->ipv6.devconf_all->force_mld_version; - else - return idev->cnf.force_mld_version; + return all_force ?: READ_ONCE(idev->cnf.force_mld_version); } static bool mld_in_v2_mode_only(const struct inet6_dev *idev) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index a19999b30b..d914b23256 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -451,7 +451,7 @@ static void ip6_nd_hdr(struct sk_buff *skb, rcu_read_lock(); idev = __in6_dev_get(skb->dev); - tclass = idev ? idev->cnf.ndisc_tclass : 0; + tclass = idev ? READ_ONCE(idev->cnf.ndisc_tclass) : 0; rcu_read_unlock(); skb_push(skb, sizeof(*hdr)); @@ -535,7 +535,7 @@ void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) override = false; - inc_opt |= ifp->idev->cnf.force_tllao; + inc_opt |= READ_ONCE(ifp->idev->cnf.force_tllao); in6_ifa_put(ifp); } else { if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr, @@ -903,8 +903,9 @@ have_ifp: } if (ipv6_chk_acast_addr(net, dev, &msg->target) || - (idev->cnf.forwarding && - (net->ipv6.devconf_all->proxy_ndp || idev->cnf.proxy_ndp) && + (READ_ONCE(idev->cnf.forwarding) && + (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) || + READ_ONCE(idev->cnf.proxy_ndp)) && (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && @@ -929,7 +930,7 @@ have_ifp: } if (is_router < 0) - is_router = idev->cnf.forwarding; + is_router = READ_ONCE(idev->cnf.forwarding); if (dad) { ndisc_send_na(dev, &in6addr_linklocal_allnodes, &msg->target, @@ -973,7 +974,7 @@ static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr) { struct inet6_dev *idev = __in6_dev_get(dev); - switch (idev->cnf.accept_untracked_na) { + switch (READ_ONCE(idev->cnf.accept_untracked_na)) { case 0: /* Don't accept untracked na (absent in neighbor cache) */ return 0; case 1: /* Create new entries from na if currently untracked */ @@ -1024,7 +1025,7 @@ static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb) * drop_unsolicited_na takes precedence over accept_untracked_na */ if (!msg->icmph.icmp6_solicited && idev && - idev->cnf.drop_unsolicited_na) + READ_ONCE(idev->cnf.drop_unsolicited_na)) return reason; if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) @@ -1080,7 +1081,7 @@ static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb) * Note that we don't do a (daddr == all-routers-mcast) check. */ new_state = msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE; - if (!neigh && lladdr && idev && idev->cnf.forwarding) { + if (!neigh && lladdr && idev && READ_ONCE(idev->cnf.forwarding)) { if (accept_untracked_na(dev, saddr)) { neigh = neigh_create(&nd_tbl, &msg->target, dev); new_state = NUD_STALE; @@ -1100,7 +1101,8 @@ static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb) * has already sent a NA to us. */ if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && - net->ipv6.devconf_all->forwarding && net->ipv6.devconf_all->proxy_ndp && + READ_ONCE(net->ipv6.devconf_all->forwarding) && + READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) { /* XXX: idev->cnf.proxy_ndp */ goto out; @@ -1148,7 +1150,7 @@ static enum skb_drop_reason ndisc_recv_rs(struct sk_buff *skb) } /* Don't accept RS if we're not in router mode */ - if (!idev->cnf.forwarding) + if (!READ_ONCE(idev->cnf.forwarding)) goto out; /* @@ -1237,6 +1239,7 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) struct ndisc_options ndopts; struct fib6_info *rt = NULL; struct inet6_dev *in6_dev; + struct fib6_table *table; u32 defrtr_usr_metric; unsigned int pref = 0; __u32 old_if_flags; @@ -1317,7 +1320,7 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) if (old_if_flags != in6_dev->if_flags) send_ifinfo_notify = true; - if (!in6_dev->cnf.accept_ra_defrtr) { + if (!READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) { ND_PRINTK(2, info, "RA: %s, defrtr is false for dev: %s\n", __func__, skb->dev->name); @@ -1325,7 +1328,8 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) } lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); - if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_lft) { + if (lifetime != 0 && + lifetime < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) { ND_PRINTK(2, info, "RA: router lifetime (%ds) is too short: %s\n", lifetime, skb->dev->name); @@ -1336,7 +1340,7 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) * accept_ra_from_local is set to true. */ net = dev_net(in6_dev->dev); - if (!in6_dev->cnf.accept_ra_from_local && + if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && ipv6_chk_addr(net, &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: default router ignored\n", @@ -1348,7 +1352,7 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) pref = ra_msg->icmph.icmp6_router_pref; /* 10b is handled as if it were 00b (medium) */ if (pref == ICMPV6_ROUTER_PREF_INVALID || - !in6_dev->cnf.accept_ra_rtr_pref) + !READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref)) pref = ICMPV6_ROUTER_PREF_MEDIUM; #endif /* routes added from RAs do not use nexthop objects */ @@ -1382,7 +1386,8 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) neigh_release(neigh); rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr, - skb->dev, pref, defrtr_usr_metric); + skb->dev, pref, defrtr_usr_metric, + lifetime); if (!rt) { ND_PRINTK(0, err, "RA: %s failed to add default route\n", @@ -1409,12 +1414,21 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) inet6_rt_notify(RTM_NEWROUTE, rt, &nlinfo, NLM_F_REPLACE); } - if (rt) + if (rt) { + table = rt->fib6_table; + spin_lock_bh(&table->tb6_lock); + fib6_set_expires(rt, jiffies + (HZ * lifetime)); - if (in6_dev->cnf.accept_ra_min_hop_limit < 256 && + fib6_add_gc_list(rt); + + spin_unlock_bh(&table->tb6_lock); + } + if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) < 256 && ra_msg->icmph.icmp6_hop_limit) { - if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) { - in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) <= + ra_msg->icmph.icmp6_hop_limit) { + WRITE_ONCE(in6_dev->cnf.hop_limit, + ra_msg->icmph.icmp6_hop_limit); fib6_metric_set(rt, RTAX_HOPLIMIT, ra_msg->icmph.icmp6_hop_limit); } else { @@ -1496,7 +1510,7 @@ skip_linkparms: } #ifdef CONFIG_IPV6_ROUTE_INFO - if (!in6_dev->cnf.accept_ra_from_local && + if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, @@ -1505,7 +1519,7 @@ skip_linkparms: goto skip_routeinfo; } - if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) { + if (READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref) && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_ri; p; @@ -1517,14 +1531,14 @@ skip_linkparms: continue; #endif if (ri->prefix_len == 0 && - !in6_dev->cnf.accept_ra_defrtr) + !READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) continue; if (ri->lifetime != 0 && - ntohl(ri->lifetime) < in6_dev->cnf.accept_ra_min_lft) + ntohl(ri->lifetime) < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) continue; - if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen) + if (ri->prefix_len < READ_ONCE(in6_dev->cnf.accept_ra_rt_info_min_plen)) continue; - if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen) + if (ri->prefix_len > READ_ONCE(in6_dev->cnf.accept_ra_rt_info_max_plen)) continue; rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, &ipv6_hdr(skb)->saddr); @@ -1544,7 +1558,7 @@ skip_routeinfo: } #endif - if (in6_dev->cnf.accept_ra_pinfo && ndopts.nd_opts_pi) { + if (READ_ONCE(in6_dev->cnf.accept_ra_pinfo) && ndopts.nd_opts_pi) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_pi; p; @@ -1555,7 +1569,7 @@ skip_routeinfo: } } - if (ndopts.nd_opts_mtu && in6_dev->cnf.accept_ra_mtu) { + if (ndopts.nd_opts_mtu && READ_ONCE(in6_dev->cnf.accept_ra_mtu)) { __be32 n; u32 mtu; @@ -1569,8 +1583,8 @@ skip_routeinfo: if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) { ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu); - } else if (in6_dev->cnf.mtu6 != mtu) { - in6_dev->cnf.mtu6 = mtu; + } else if (READ_ONCE(in6_dev->cnf.mtu6) != mtu) { + WRITE_ONCE(in6_dev->cnf.mtu6, mtu); fib6_metric_set(rt, RTAX_MTU, mtu); rt6_mtu_change(skb->dev, mtu); } @@ -1708,7 +1722,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) if (IS_ERR(dst)) return; - rt = (struct rt6_info *) dst; + rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_GATEWAY) { ND_PRINTK(2, warn, @@ -1804,7 +1818,7 @@ static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb) if (!idev) return true; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED && - idev->cnf.suppress_frag_ndisc) { + READ_ONCE(idev->cnf.suppress_frag_ndisc)) { net_warn_ratelimited("Received fragmented ndisc packet. Carefully consider disabling suppress_frag_ndisc.\n"); return true; } @@ -1881,8 +1895,8 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, idev = in6_dev_get(dev); if (!idev) break; - if (idev->cnf.ndisc_notify || - net->ipv6.devconf_all->ndisc_notify) + if (READ_ONCE(idev->cnf.ndisc_notify) || + READ_ONCE(net->ipv6.devconf_all->ndisc_notify)) ndisc_send_unsol_na(dev); in6_dev_put(idev); break; @@ -1891,8 +1905,8 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, if (!idev) evict_nocarrier = true; else { - evict_nocarrier = idev->cnf.ndisc_evict_nocarrier && - net->ipv6.devconf_all->ndisc_evict_nocarrier; + evict_nocarrier = READ_ONCE(idev->cnf.ndisc_evict_nocarrier) && + READ_ONCE(net->ipv6.devconf_all->ndisc_evict_nocarrier); in6_dev_put(idev); } @@ -1966,7 +1980,7 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void *buffer, if (ctl->data == &NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)) idev->nd_parms->reachable_time = neigh_rand_reach_time(NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)); - idev->tstamp = jiffies; + WRITE_ONCE(idev->tstamp, jiffies); inet6_ifinfo_notify(RTM_NEWLINK, idev); in6_dev_put(idev); } diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 0ba62f4868..f3c8e2d918 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -6,6 +6,10 @@ menu "IPv6: Netfilter Configuration" depends on INET && IPV6 && NETFILTER +# old sockopt interface and eval loop +config IP6_NF_IPTABLES_LEGACY + tristate + config NF_SOCKET_IPV6 tristate "IPv6 socket lookup support" help @@ -147,7 +151,7 @@ config IP6_NF_MATCH_MH config IP6_NF_MATCH_RPFILTER tristate '"rpfilter" reverse path filter match support' depends on NETFILTER_ADVANCED - depends on IP6_NF_MANGLE || IP6_NF_RAW + depends on IP6_NF_MANGLE || IP6_NF_RAW || NFT_COMPAT help This option allows you to match packets whose replies would go out via the interface the packet came in. @@ -186,6 +190,8 @@ config IP6_NF_TARGET_HL config IP6_NF_FILTER tristate "Packet filtering" default m if NETFILTER_ADVANCED=n + select IP6_NF_IPTABLES_LEGACY + tristate help Packet filtering defines a table `filter', which has a series of rules for simple packet filtering at local input, forwarding and @@ -195,7 +201,7 @@ config IP6_NF_FILTER config IP6_NF_TARGET_REJECT tristate "REJECT target support" - depends on IP6_NF_FILTER + depends on IP6_NF_FILTER || NFT_COMPAT select NF_REJECT_IPV6 default m if NETFILTER_ADVANCED=n help @@ -221,6 +227,7 @@ config IP6_NF_TARGET_SYNPROXY config IP6_NF_MANGLE tristate "Packet mangling" default m if NETFILTER_ADVANCED=n + select IP6_NF_IPTABLES_LEGACY help This option adds a `mangle' table to iptables: see the man page for iptables(8). This table is used for various packet alterations @@ -230,6 +237,7 @@ config IP6_NF_MANGLE config IP6_NF_RAW tristate 'raw table support (required for TRACE)' + select IP6_NF_IPTABLES_LEGACY help This option adds a `raw' table to ip6tables. This table is the very first in the netfilter framework and hooks in at the PREROUTING @@ -243,6 +251,7 @@ config IP6_NF_SECURITY tristate "Security table" depends on SECURITY depends on NETFILTER_ADVANCED + select IP6_NF_IPTABLES_LEGACY help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. @@ -254,6 +263,7 @@ config IP6_NF_NAT depends on NF_CONNTRACK depends on NETFILTER_ADVANCED select NF_NAT + select IP6_NF_IPTABLES_LEGACY select NETFILTER_XT_NAT help This enables the `nat' table in ip6tables. This allows masquerading, @@ -262,25 +272,23 @@ config IP6_NF_NAT To compile it as a module, choose M here. If unsure, say N. -if IP6_NF_NAT - config IP6_NF_TARGET_MASQUERADE tristate "MASQUERADE target support" select NETFILTER_XT_TARGET_MASQUERADE + depends on IP6_NF_NAT help This is a backwards-compat option for the user's convenience (e.g. when running oldconfig). It selects NETFILTER_XT_TARGET_MASQUERADE. config IP6_NF_TARGET_NPT tristate "NPT (Network Prefix translation) target support" + depends on IP6_NF_NAT || NFT_COMPAT help This option adds the `SNPT' and `DNPT' target, which perform stateless IPv6-to-IPv6 Network Prefix Translation per RFC 6296. To compile it as a module, choose M here. If unsure, say N. -endif # IP6_NF_NAT - endif # IP6_NF_IPTABLES endmenu diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index b8d6dc9aee..66ce6fa5b2 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -4,7 +4,7 @@ # # Link order matters here. -obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o +obj-$(CONFIG_IP6_NF_IPTABLES_LEGACY) += ip6_tables.o obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index efbec7ee27..d0dcbaca19 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -328,9 +328,9 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, if (!reasm_data) goto err; - payload_len = ((skb->data - skb_network_header(skb)) - + payload_len = -skb_network_offset(skb) - sizeof(struct ipv6hdr) + fq->q.len - - sizeof(struct frag_hdr)); + sizeof(struct frag_hdr); if (payload_len > IPV6_MAXPLEN) { net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", payload_len); diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 196dd4ecb5..dedee264b8 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -83,7 +83,7 @@ struct sk_buff *nf_reject_skb_v6_tcp_reset(struct net *net, skb_reserve(nskb, LL_MAX_HEADER); nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, - net->ipv6.devconf_all->hop_limit); + READ_ONCE(net->ipv6.devconf_all->hop_limit)); nf_reject_ip6_tcphdr_put(nskb, oldskb, oth, otcplen); nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr)); @@ -124,7 +124,7 @@ struct sk_buff *nf_reject_skb_v6_unreach(struct net *net, skb_reserve(nskb, LL_MAX_HEADER); nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_ICMPV6, - net->ipv6.devconf_all->hop_limit); + READ_ONCE(net->ipv6.devconf_all->hop_limit)); skb_reset_transport_header(nskb); icmp6h = skb_put_zero(nskb, sizeof(struct icmp6hdr)); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index b5205311f3..806d4b5dd1 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -111,9 +111,9 @@ int ip6_dst_hoplimit(struct dst_entry *dst) rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) - hoplimit = idev->cnf.hop_limit; + hoplimit = READ_ONCE(idev->cnf.hop_limit); else - hoplimit = dev_net(dev)->ipv6.devconf_all->hop_limit; + hoplimit = READ_ONCE(dev_net(dev)->ipv6.devconf_all->hop_limit); rcu_read_unlock(); } return hoplimit; diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index ef2059c889..88b3fcacd4 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -154,7 +154,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false); if (IS_ERR(dst)) return PTR_ERR(dst); - rt = (struct rt6_info *) dst; + rt = dst_rt6_info(dst); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = READ_ONCE(np->mcast_oif); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 03dbb874c3..2eedf25560 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -160,6 +160,13 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) if (!raw_v6_match(net, sk, nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb))) continue; + + if (atomic_read(&sk->sk_rmem_alloc) >= + READ_ONCE(sk->sk_rcvbuf)) { + atomic_inc(&sk->sk_drops); + continue; + } + delivered = true; switch (nexthdr) { case IPPROTO_ICMPV6: @@ -288,8 +295,7 @@ out: } static void rawv6_err(struct sock *sk, struct sk_buff *skb, - struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { bool recverr = inet6_test_bit(RECVERR6, sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -344,7 +350,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, if (!raw_v6_match(net, sk, nexthdr, &ip6h->saddr, &ip6h->daddr, inet6_iif(skb), inet6_iif(skb))) continue; - rawv6_err(sk, skb, NULL, type, code, inner_offset, info); + rawv6_err(sk, skb, type, code, inner_offset, info); } rcu_read_unlock(); } @@ -592,7 +598,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, struct ipv6hdr *iph; struct sk_buff *skb; int err; - struct rt6_info *rt = (struct rt6_info *)*dstp; + struct rt6_info *rt = dst_rt6_info(*dstp); int hlen = LL_RESERVED_SPACE(rt->dst.dev); int tlen = rt->dst.dev->needed_tailroom; @@ -911,7 +917,7 @@ back_from_confirm: ipc6.opt = opt; lock_sock(sk); err = ip6_append_data(sk, raw6_getfrag, &rfv, - len, 0, &ipc6, &fl6, (struct rt6_info *)dst, + len, 0, &ipc6, &fl6, dst_rt6_info(dst), msg->msg_flags); if (err) @@ -935,7 +941,7 @@ do_confirm: goto done; } -static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, +static int rawv6_seticmpfilter(struct sock *sk, int optname, sockptr_t optval, int optlen) { switch (optname) { @@ -952,7 +958,7 @@ static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, return 0; } -static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, +static int rawv6_geticmpfilter(struct sock *sk, int optname, char __user *optval, int __user *optlen) { int len; @@ -1038,7 +1044,7 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; - return rawv6_seticmpfilter(sk, level, optname, optval, optlen); + return rawv6_seticmpfilter(sk, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) @@ -1099,7 +1105,7 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; - return rawv6_geticmpfilter(sk, level, optname, optval, optlen); + return rawv6_geticmpfilter(sk, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 2af98edef8..148bf9e313 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -272,9 +272,9 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, if (!reasm_data) goto out_oom; - payload_len = ((skb->data - skb_network_header(skb)) - + payload_len = -skb_network_offset(skb) - sizeof(struct ipv6hdr) + fq->q.len - - sizeof(struct frag_hdr)); + sizeof(struct frag_hdr); if (payload_len > IPV6_MAXPLEN) goto out_oversize; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ef815ba583..d7a5ca012a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -87,7 +87,8 @@ struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst); -static struct dst_entry *ip6_negative_advice(struct dst_entry *); +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev); @@ -226,7 +227,7 @@ static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { - const struct rt6_info *rt = container_of(dst, struct rt6_info, dst); + const struct rt6_info *rt = dst_rt6_info(dst); return ip6_neigh_lookup(rt6_nexthop(rt, &in6addr_any), dst->dev, skb, daddr); @@ -234,8 +235,8 @@ static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr) { + const struct rt6_info *rt = dst_rt6_info(dst); struct net_device *dev = dst->dev; - struct rt6_info *rt = (struct rt6_info *)dst; daddr = choose_neigh_daddr(rt6_nexthop(rt, &in6addr_any), NULL, daddr); if (!daddr) @@ -354,7 +355,7 @@ EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { - struct rt6_info *rt = (struct rt6_info *)dst; + struct rt6_info *rt = dst_rt6_info(dst); struct fib6_info *from; struct inet6_dev *idev; @@ -373,7 +374,7 @@ static void ip6_dst_destroy(struct dst_entry *dst) static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { - struct rt6_info *rt = (struct rt6_info *)dst; + struct rt6_info *rt = dst_rt6_info(dst); struct inet6_dev *idev = rt->rt6i_idev; if (idev && idev->dev != blackhole_netdev) { @@ -637,6 +638,8 @@ static void rt6_probe(struct fib6_nh *fib6_nh) rcu_read_lock(); last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); + if (!idev) + goto out; neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { if (READ_ONCE(neigh->nud_state) & NUD_VALID) @@ -645,14 +648,15 @@ static void rt6_probe(struct fib6_nh *fib6_nh) write_lock_bh(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, - neigh->updated + idev->cnf.rtr_probe_interval)) { + neigh->updated + + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) __neigh_set_probe_once(neigh); } write_unlock_bh(&neigh->lock); } else if (time_after(jiffies, last_probe + - idev->cnf.rtr_probe_interval)) { + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc(sizeof(*work), GFP_ATOMIC); } @@ -931,6 +935,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, struct net *net = dev_net(dev); struct route_info *rinfo = (struct route_info *) opt; struct in6_addr prefix_buf, *prefix; + struct fib6_table *table; unsigned int pref; unsigned long lifetime; struct fib6_info *rt; @@ -989,10 +994,18 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { - if (!addrconf_finite_timeout(lifetime)) + table = rt->fib6_table; + spin_lock_bh(&table->tb6_lock); + + if (!addrconf_finite_timeout(lifetime)) { fib6_clean_expires(rt); - else + fib6_remove_gc_list(rt); + } else { fib6_set_expires(rt, jiffies + HZ * lifetime); + fib6_add_gc_list(rt); + } + + spin_unlock_bh(&table->tb6_lock); fib6_info_release(rt); } @@ -1278,7 +1291,7 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, dst = fib6_rule_lookup(net, &fl6, skb, flags, ip6_pol_route_lookup); if (dst->error == 0) - return (struct rt6_info *) dst; + return dst_rt6_info(dst); dst_release(dst); @@ -1398,6 +1411,7 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) struct rt6_info *prev, **p; p = this_cpu_ptr(res->nh->rt6i_pcpu); + /* Paired with READ_ONCE() in __fib6_drop_pcpu_from() */ prev = xchg(p, NULL); if (prev) { dst_dev_put(&prev->dst); @@ -1587,7 +1601,7 @@ static unsigned int fib6_mtu(const struct fib6_result *res) rcu_read_lock(); idev = __in6_dev_get(dev); - mtu = idev->cnf.mtu6; + mtu = READ_ONCE(idev->cnf.mtu6); rcu_read_unlock(); } @@ -2085,12 +2099,12 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, */ if (!(rt->rt6i_flags & RTF_EXPIRES)) { if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { - RT6_TRACE("aging clone %p\n", rt); + pr_debug("aging clone %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } } else if (time_after(jiffies, rt->dst.expires)) { - RT6_TRACE("purging expired route %p\n", rt); + pr_debug("purging expired route %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } @@ -2101,8 +2115,8 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); if (!(neigh && (neigh->flags & NTF_ROUTER))) { - RT6_TRACE("purging route %p via non-router but gateway\n", - rt); + pr_debug("purging route %p via non-router but gateway\n", + rt); rt6_remove_exception(bucket, rt6_ex); return; } @@ -2211,7 +2225,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, strict |= flags & RT6_LOOKUP_F_IFACE; strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE; - if (net->ipv6.devconf_all->forwarding == 0) + if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0) strict |= RT6_LOOKUP_F_REACHABLE; rcu_read_lock(); @@ -2637,7 +2651,7 @@ struct dst_entry *ip6_route_output_flags(struct net *net, rcu_read_lock(); dst = ip6_route_output_flags_noref(net, sk, fl6, flags); - rt6 = (struct rt6_info *)dst; + rt6 = dst_rt6_info(dst); /* For dst cached in uncached_list, refcnt is already taken. */ if (list_empty(&rt6->dst.rt_uncached) && !dst_hold_safe(dst)) { dst = &net->ipv6.ip6_null_entry->dst; @@ -2651,7 +2665,7 @@ EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { - struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig; + struct rt6_info *rt, *ort = dst_rt6_info(dst_orig); struct net_device *loopback_dev = net->loopback_dev; struct dst_entry *new = NULL; @@ -2734,7 +2748,7 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, struct fib6_info *from; struct rt6_info *rt; - rt = container_of(dst, struct rt6_info, dst); + rt = dst_rt6_info(dst); if (rt->sernum) return rt6_is_valid(rt) ? dst : NULL; @@ -2760,24 +2774,24 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, } EXPORT_INDIRECT_CALLABLE(ip6_dst_check); -static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst) { - struct rt6_info *rt = (struct rt6_info *) dst; + struct rt6_info *rt = dst_rt6_info(dst); - if (rt) { - if (rt->rt6i_flags & RTF_CACHE) { - rcu_read_lock(); - if (rt6_check_expired(rt)) { - rt6_remove_exception_rt(rt); - dst = NULL; - } - rcu_read_unlock(); - } else { - dst_release(dst); - dst = NULL; + if (rt->rt6i_flags & RTF_CACHE) { + rcu_read_lock(); + if (rt6_check_expired(rt)) { + /* counteract the dst_release() in sk_dst_reset() */ + dst_hold(dst); + sk_dst_reset(sk); + + rt6_remove_exception_rt(rt); } + rcu_read_unlock(); + return; } - return dst; + sk_dst_reset(sk); } static void ip6_link_failure(struct sk_buff *skb) @@ -2786,7 +2800,7 @@ static void ip6_link_failure(struct sk_buff *skb) icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); - rt = (struct rt6_info *) skb_dst(skb); + rt = dst_rt6_info(skb_dst(skb)); if (rt) { rcu_read_lock(); if (rt->rt6i_flags & RTF_CACHE) { @@ -2842,7 +2856,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, bool confirm_neigh) { const struct in6_addr *daddr, *saddr; - struct rt6_info *rt6 = (struct rt6_info *)dst; + struct rt6_info *rt6 = dst_rt6_info(dst); /* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU) * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it. @@ -3240,8 +3254,8 @@ u32 ip6_mtu_from_fib6(const struct fib6_result *res, mtu = IPV6_MIN_MTU; idev = __in6_dev_get(dev); - if (idev && idev->cnf.mtu6 > mtu) - mtu = idev->cnf.mtu6; + if (idev) + mtu = max_t(u32, mtu, READ_ONCE(idev->cnf.mtu6)); } mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); @@ -3591,7 +3605,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, if (!dev) goto out; - if (idev->cnf.disable_ipv6) { + if (!idev || idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device"); err = -EACCES; goto out; @@ -3765,8 +3779,6 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, if (cfg->fc_flags & RTF_EXPIRES) fib6_set_expires(rt, jiffies + clock_t_to_jiffies(cfg->fc_expires)); - else - fib6_clean_expires(rt); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; @@ -4142,7 +4154,8 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) return; - if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects) + if (READ_ONCE(in6_dev->cnf.forwarding) || + !READ_ONCE(in6_dev->cnf.accept_redirects)) return; /* RFC2461 8.1: @@ -4165,7 +4178,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu } } - rt = (struct rt6_info *) dst; + rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_REJECT) { net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n"); return; @@ -4355,7 +4368,8 @@ struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref, - u32 defrtr_usr_metric) + u32 defrtr_usr_metric, + int lifetime) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT, @@ -4368,6 +4382,7 @@ struct fib6_info *rt6_add_dflt_router(struct net *net, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, + .fc_expires = jiffies_to_clock_t(lifetime * HZ), }; cfg.fc_gateway = *gwaddr; @@ -4434,7 +4449,7 @@ static void rtmsg_to_fib6_config(struct net *net, .fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ? : RT6_TABLE_MAIN, .fc_ifindex = rtmsg->rtmsg_ifindex, - .fc_metric = rtmsg->rtmsg_metric ? : IP6_RT_PRIO_USER, + .fc_metric = rtmsg->rtmsg_metric, .fc_expires = rtmsg->rtmsg_info, .fc_dst_len = rtmsg->rtmsg_dst_len, .fc_src_len = rtmsg->rtmsg_src_len, @@ -4464,6 +4479,9 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg) rtnl_lock(); switch (cmd) { case SIOCADDRT: + /* Only do the default setting of fc_metric in route adding */ + if (cfg.fc_metric == 0) + cfg.fc_metric = IP6_RT_PRIO_USER; err = ip6_route_add(&cfg, GFP_KERNEL, NULL); break; case SIOCDELRT: @@ -4574,8 +4592,8 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net, f6i->dst_nocount = true; if (!anycast && - (net->ipv6.devconf_all->disable_policy || - idev->cnf.disable_policy)) + (READ_ONCE(net->ipv6.devconf_all->disable_policy) || + READ_ONCE(idev->cnf.disable_policy))) f6i->dst_nopolicy = true; } @@ -5597,7 +5615,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, int iif, int type, u32 portid, u32 seq, unsigned int flags) { - struct rt6_info *rt6 = (struct rt6_info *)dst; + struct rt6_info *rt6 = dst_rt6_info(dst); struct rt6key *rt6_dst, *rt6_src; u32 *pmetrics, table, rt6_flags; unsigned char nh_flags = 0; @@ -6100,7 +6118,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, } - rt = container_of(dst, struct rt6_info, dst); + rt = dst_rt6_info(dst); if (rt->dst.error) { err = rt->dst.error; ip6_rt_put(rt); @@ -6327,12 +6345,12 @@ static int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write, if (!write) return -EINVAL; - net = (struct net *)ctl->extra1; - delay = net->ipv6.sysctl.flush_delay; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (ret) return ret; + net = (struct net *)ctl->extra1; + delay = net->ipv6.sysctl.flush_delay; fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index d43c50a731..bbf5b84a70 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -241,6 +241,7 @@ bool seg6_hmac_validate_skb(struct sk_buff *skb) struct sr6_tlv_hmac *tlv; struct ipv6_sr_hdr *srh; struct inet6_dev *idev; + int require_hmac; idev = __in6_dev_get(skb->dev); @@ -248,16 +249,17 @@ bool seg6_hmac_validate_skb(struct sk_buff *skb) tlv = seg6_get_tlv_hmac(srh); + require_hmac = READ_ONCE(idev->cnf.seg6_require_hmac); /* mandatory check but no tlv */ - if (idev->cnf.seg6_require_hmac > 0 && !tlv) + if (require_hmac > 0 && !tlv) return false; /* no check */ - if (idev->cnf.seg6_require_hmac < 0) + if (require_hmac < 0) return true; /* check only if present */ - if (idev->cnf.seg6_require_hmac == 0 && !tlv) + if (require_hmac == 0 && !tlv) return true; /* now, seg6_require_hmac >= 0 && tlv */ @@ -354,6 +356,7 @@ static int seg6_hmac_init_algo(void) struct crypto_shash *tfm; struct shash_desc *shash; int i, alg_count, cpu; + int ret = -ENOMEM; alg_count = ARRAY_SIZE(hmac_algos); @@ -364,12 +367,14 @@ static int seg6_hmac_init_algo(void) algo = &hmac_algos[i]; algo->tfms = alloc_percpu(struct crypto_shash *); if (!algo->tfms) - return -ENOMEM; + goto error_out; for_each_possible_cpu(cpu) { tfm = crypto_alloc_shash(algo->name, 0, 0); - if (IS_ERR(tfm)) - return PTR_ERR(tfm); + if (IS_ERR(tfm)) { + ret = PTR_ERR(tfm); + goto error_out; + } p_tfm = per_cpu_ptr(algo->tfms, cpu); *p_tfm = tfm; } @@ -381,18 +386,22 @@ static int seg6_hmac_init_algo(void) algo->shashs = alloc_percpu(struct shash_desc *); if (!algo->shashs) - return -ENOMEM; + goto error_out; for_each_possible_cpu(cpu) { shash = kzalloc_node(shsize, GFP_KERNEL, cpu_to_node(cpu)); if (!shash) - return -ENOMEM; + goto error_out; *per_cpu_ptr(algo->shashs, cpu) = shash; } } return 0; + +error_out: + seg6_hmac_exit(); + return ret; } int __init seg6_hmac_init(void) @@ -410,22 +419,29 @@ int __net_init seg6_hmac_net_init(struct net *net) void seg6_hmac_exit(void) { struct seg6_hmac_algo *algo = NULL; + struct crypto_shash *tfm; + struct shash_desc *shash; int i, alg_count, cpu; alg_count = ARRAY_SIZE(hmac_algos); for (i = 0; i < alg_count; i++) { algo = &hmac_algos[i]; - for_each_possible_cpu(cpu) { - struct crypto_shash *tfm; - struct shash_desc *shash; - shash = *per_cpu_ptr(algo->shashs, cpu); - kfree(shash); - tfm = *per_cpu_ptr(algo->tfms, cpu); - crypto_free_shash(tfm); + if (algo->shashs) { + for_each_possible_cpu(cpu) { + shash = *per_cpu_ptr(algo->shashs, cpu); + kfree(shash); + } + free_percpu(algo->shashs); + } + + if (algo->tfms) { + for_each_possible_cpu(cpu) { + tfm = *per_cpu_ptr(algo->tfms, cpu); + crypto_free_shash(tfm); + } + free_percpu(algo->tfms); } - free_percpu(algo->tfms); - free_percpu(algo->shashs); } } EXPORT_SYMBOL(seg6_hmac_exit); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 03b877ff45..098632adc9 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -459,34 +459,30 @@ static int seg6_input_core(struct net *net, struct sock *sk, int err; err = seg6_do_srh(skb); - if (unlikely(err)) { - kfree_skb(skb); - return err; - } + if (unlikely(err)) + goto drop; slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); - preempt_disable(); + local_bh_disable(); dst = dst_cache_get(&slwt->cache); - preempt_enable(); if (!dst) { ip6_route_input(skb); dst = skb_dst(skb); if (!dst->error) { - preempt_disable(); dst_cache_set_ip6(&slwt->cache, dst, &ipv6_hdr(skb)->saddr); - preempt_enable(); } } else { skb_dst_drop(skb); skb_dst_set(skb, dst); } + local_bh_enable(); err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); if (unlikely(err)) - return err; + goto drop; if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, @@ -494,6 +490,9 @@ static int seg6_input_core(struct net *net, struct sock *sk, skb_dst(skb)->dev, seg6_input_finish); return seg6_input_finish(dev_net(skb->dev), NULL, skb); +drop: + kfree_skb(skb); + return err; } static int seg6_input_nf(struct sk_buff *skb) @@ -535,9 +534,9 @@ static int seg6_output_core(struct net *net, struct sock *sk, slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); - preempt_disable(); + local_bh_disable(); dst = dst_cache_get(&slwt->cache); - preempt_enable(); + local_bh_enable(); if (unlikely(!dst)) { struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -557,9 +556,9 @@ static int seg6_output_core(struct net *net, struct sock *sk, goto drop; } - preempt_disable(); + local_bh_disable(); dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr); - preempt_enable(); + local_bh_enable(); } skb_dst_drop(skb); diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 24e2b4b494..c434940131 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -941,8 +941,8 @@ static int input_action_end_dx6(struct sk_buff *skb, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, NULL, - skb_dst(skb)->dev, input_action_end_dx6_finish); + dev_net(skb->dev), NULL, skb, skb->dev, + NULL, input_action_end_dx6_finish); return input_action_end_dx6_finish(dev_net(skb->dev), NULL, skb); drop: @@ -991,8 +991,8 @@ static int input_action_end_dx4(struct sk_buff *skb, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, NULL, - skb_dst(skb)->dev, input_action_end_dx4_finish); + dev_net(skb->dev), NULL, skb, skb->dev, + NULL, input_action_end_dx4_finish); return input_action_end_dx4_finish(dev_net(skb->dev), NULL, skb); drop: diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index fbad6e1c97..655c9b1a19 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1398,7 +1398,6 @@ static const struct net_device_ops ipip6_netdev_ops = { .ndo_uninit = ipip6_tunnel_uninit, .ndo_start_xmit = sit_tunnel_xmit, .ndo_siocdevprivate = ipip6_tunnel_siocdevprivate, - .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipip6_tunnel_ctl, }; @@ -1408,7 +1407,6 @@ static void ipip6_dev_free(struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); dst_cache_destroy(&tunnel->dst_cache); - free_percpu(dev->tstats); } #define SIT_FEATURES (NETIF_F_SG | \ @@ -1437,6 +1435,8 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->features |= NETIF_F_LLTX; dev->features |= SIT_FEATURES; dev->hw_features |= SIT_FEATURES; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; + } static int ipip6_tunnel_init(struct net_device *dev) @@ -1449,16 +1449,11 @@ static int ipip6_tunnel_init(struct net_device *dev) strcpy(tunnel->parms.name, dev->name); ipip6_tunnel_bind_dev(dev); - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); - if (err) { - free_percpu(dev->tstats); - dev->tstats = NULL; + if (err) return err; - } + netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); return 0; @@ -1876,22 +1871,19 @@ err_alloc_dev: return err; } -static void __net_exit sit_exit_batch_net(struct list_head *net_list) +static void __net_exit sit_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { - LIST_HEAD(list); struct net *net; - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) - sit_destroy_tunnels(net, &list); - - unregister_netdevice_many(&list); - rtnl_unlock(); + sit_destroy_tunnels(net, dev_to_kill); } static struct pernet_operations sit_net_ops = { .init = sit_init_net, - .exit_batch = sit_exit_batch_net, + .exit_batch_rtnl = sit_exit_batch_rtnl, .id = &sit_net_id, .size = sizeof(struct sit_net), }; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index c8d2ca2722..6d8286c299 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -177,24 +177,33 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) struct sock *ret = sk; __u8 rcv_wscale; int full_space; + SKB_DR(reason); if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) || !th->ack || th->rst) goto out; - req = cookie_tcp_check(net, sk, skb); - if (IS_ERR(req)) - goto out; - if (!req) + if (cookie_bpf_ok(skb)) { + req = cookie_bpf_check(sk, skb); + } else { + req = cookie_tcp_check(net, sk, skb); + if (IS_ERR(req)) + goto out; + } + if (!req) { + SKB_DR_SET(reason, NO_SOCKET); goto out_drop; + } ireq = inet_rsk(req); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; - if (security_inet_conn_request(sk, skb, req)) + if (security_inet_conn_request(sk, skb, req)) { + SKB_DR_SET(reason, SECURITY_HOOK); goto out_free; + } if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || @@ -231,8 +240,10 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) security_req_classify_flow(req, flowi6_to_flowi_common(&fl6)); dst = ip6_dst_lookup_flow(net, sk, &fl6, final_p); - if (IS_ERR(dst)) + if (IS_ERR(dst)) { + SKB_DR_SET(reason, IP_OUTNOROUTES); goto out_free; + } } req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); @@ -247,14 +258,23 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); - ireq->rcv_wscale = rcv_wscale; + /* req->syncookie is set true only if ACK is validated + * by BPF kfunc, then, rcv_wscale is already configured. + */ + if (!req->syncookie) + ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok &= cookie_ecn_ok(net, dst); ret = tcp_get_cookie_sock(sk, skb, req, dst); + if (!ret) { + SKB_DR_SET(reason, NO_SOCKET); + goto out_drop; + } out: return ret; out_free: reqsk_free(req); out_drop: + kfree_skb_reason(skb, reason); return NULL; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 57b25b1fc9..2b2eda5a28 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -58,6 +58,7 @@ #include <net/timewait_sock.h> #include <net/inet_common.h> #include <net/secure_seq.h> +#include <net/hotdata.h> #include <net/busy_poll.h> #include <linux/proc_fs.h> @@ -94,11 +95,9 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { - const struct rt6_info *rt = (const struct rt6_info *)dst; - rcu_assign_pointer(sk->sk_rx_dst, dst); sk->sk_rx_dst_ifindex = skb->skb_iif; - sk->sk_rx_dst_cookie = rt6_get_cookie(rt); + sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); } } @@ -1439,7 +1438,6 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * */ newsk->sk_gso_type = SKB_GSO_TCPV6; - ip6_dst_store(newsk, dst, NULL, NULL); inet6_sk_rx_dst_set(newsk, skb); inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk); @@ -1450,6 +1448,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * memcpy(newnp, np, sizeof(struct ipv6_pinfo)); + ip6_dst_store(newsk, dst, NULL, NULL); + newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr; newnp->saddr = ireq->ir_v6_loc_addr; newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; @@ -1623,7 +1623,6 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (np->rxopt.all) opt_skb = skb_clone_and_charge_r(skb, sk); - reason = SKB_DROP_REASON_NOT_SPECIFIED; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; @@ -1653,12 +1652,12 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (sk->sk_state == TCP_LISTEN) { struct sock *nsk = tcp_v6_cookie_check(sk, skb); - if (!nsk) - goto discard; - if (nsk != sk) { - if (tcp_child_process(sk, nsk, skb)) - goto reset; + if (nsk) { + reason = tcp_child_process(sk, nsk, skb); + if (reason) + goto reset; + } if (opt_skb) __kfree_skb(opt_skb); return 0; @@ -1666,7 +1665,8 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) } else sock_rps_save_rxhash(sk, skb); - if (tcp_rcv_state_process(sk, skb)) + reason = tcp_rcv_state_process(sk, skb); + if (reason) goto reset; if (opt_skb) goto ipv6_pktoptions; @@ -1856,10 +1856,12 @@ process: if (nsk == sk) { reqsk_put(req); tcp_v6_restore_cb(skb); - } else if (tcp_child_process(sk, nsk, skb)) { - tcp_v6_send_reset(nsk, skb); - goto discard_and_relse; } else { + drop_reason = tcp_child_process(sk, nsk, skb); + if (drop_reason) { + tcp_v6_send_reset(nsk, skb); + goto discard_and_relse; + } sock_put(sk); return 0; } @@ -2365,11 +2367,6 @@ struct proto tcpv6_prot = { }; EXPORT_SYMBOL_GPL(tcpv6_prot); -static const struct inet6_protocol tcpv6_protocol = { - .handler = tcp_v6_rcv, - .err_handler = tcp_v6_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, -}; static struct inet_protosw tcpv6_protosw = { .type = SOCK_STREAM, @@ -2406,7 +2403,12 @@ int __init tcpv6_init(void) { int ret; - ret = inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP); + net_hotdata.tcpv6_protocol = (struct inet6_protocol) { + .handler = tcp_v6_rcv, + .err_handler = tcp_v6_err, + .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, + }; + ret = inet6_add_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); if (ret) goto out; @@ -2431,7 +2433,7 @@ out_tcpv6_pernet_subsys: out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); out_tcpv6_protocol: - inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); + inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); goto out; } @@ -2439,5 +2441,5 @@ void tcpv6_exit(void) { unregister_pernet_subsys(&tcpv6_net_ops); inet6_unregister_protosw(&tcpv6_protosw); - inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); + inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index bf0c957e4b..4b07d1e6c9 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -66,15 +66,15 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, return tcp_gso_segment(skb, features); } -static const struct net_offload tcpv6_offload = { - .callbacks = { - .gso_segment = tcp6_gso_segment, - .gro_receive = tcp6_gro_receive, - .gro_complete = tcp6_gro_complete, - }, -}; int __init tcpv6_offload_init(void) { - return inet6_add_offload(&tcpv6_offload, IPPROTO_TCP); + net_hotdata.tcpv6_offload = (struct net_offload) { + .callbacks = { + .gso_segment = tcp6_gso_segment, + .gro_receive = tcp6_gro_receive, + .gro_complete = tcp6_gro_complete, + }, + }; + return inet6_add_offload(&net_hotdata.tcpv6_offload, IPPROTO_TCP); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 936b51f358..acafa0cdf7 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -79,9 +79,6 @@ u32 udp6_ehashfn(const struct net *net, const struct in6_addr *faddr, const __be16 fport) { - static u32 udp6_ehash_secret __read_mostly; - static u32 udp_ipv6_hash_secret __read_mostly; - u32 lhash, fhash; net_get_random_once(&udp6_ehash_secret, @@ -913,11 +910,8 @@ start_lookup: static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { - if (udp_sk_rx_dst_set(sk, dst)) { - const struct rt6_info *rt = (const struct rt6_info *)dst; - - sk->sk_rx_dst_cookie = rt6_get_cookie(rt); - } + if (udp_sk_rx_dst_set(sk, dst)) + sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); } /* wrapper for udp_queue_rcv_skb tacking care of csum conversion and @@ -1114,11 +1108,12 @@ void udp_v6_early_demux(struct sk_buff *skb) else return; - if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) + if (!sk) return; skb->sk = sk; - skb->destructor = sock_efree; + DEBUG_NET_WARN_ON_ONCE(sk_is_refcounted(sk)); + skb->destructor = sock_pfree; dst = rcu_dereference(sk->sk_rx_dst); if (dst) @@ -1587,7 +1582,7 @@ back_from_confirm: skb = ip6_make_skb(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, - (struct rt6_info *)dst, + dst_rt6_info(dst), msg->msg_flags, &cork); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) @@ -1614,7 +1609,7 @@ do_append_data: ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk); up->len += ulen; err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), - &ipc6, fl6, (struct rt6_info *)dst, + &ipc6, fl6, dst_rt6_info(dst), corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_v6_flush_pending_frames(sk); @@ -1716,11 +1711,6 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname, return ipv6_getsockopt(sk, level, optname, optval, optlen); } -static const struct inet6_protocol udpv6_protocol = { - .handler = udpv6_rcv, - .err_handler = udpv6_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, -}; /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS @@ -1817,7 +1807,12 @@ int __init udpv6_init(void) { int ret; - ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP); + net_hotdata.udpv6_protocol = (struct inet6_protocol) { + .handler = udpv6_rcv, + .err_handler = udpv6_err, + .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, + }; + ret = inet6_add_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); if (ret) goto out; @@ -1828,12 +1823,12 @@ out: return ret; out_udpv6_protocol: - inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); + inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); goto out; } void udpv6_exit(void) { inet6_unregister_protosw(&udpv6_protosw); - inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); + inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); } diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 639a4b506f..b41152dd42 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -187,20 +187,19 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb); } -static const struct net_offload udpv6_offload = { - .callbacks = { - .gso_segment = udp6_ufo_fragment, - .gro_receive = udp6_gro_receive, - .gro_complete = udp6_gro_complete, - }, -}; - -int udpv6_offload_init(void) +int __init udpv6_offload_init(void) { - return inet6_add_offload(&udpv6_offload, IPPROTO_UDP); + net_hotdata.udpv6_offload = (struct net_offload) { + .callbacks = { + .gso_segment = udp6_ufo_fragment, + .gro_receive = udp6_gro_receive, + .gro_complete = udp6_gro_complete, + }, + }; + return inet6_add_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } int udpv6_offload_exit(void) { - return inet6_del_offload(&udpv6_offload, IPPROTO_UDP); + return inet6_del_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 4e6dcefd63..c6b8e132e1 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -43,7 +43,7 @@ static int xfrm6_transport_finish2(struct net *net, struct sock *sk, int xfrm6_transport_finish(struct sk_buff *skb, int async) { struct xfrm_offload *xo = xfrm_offload(skb); - int nhlen = skb->data - skb_network_header(skb); + int nhlen = -skb_network_offset(skb); skb_network_header(skb)[IP6CB(skb)->nhoff] = XFRM_MODE_SKB_CB(skb)->protocol; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 42fb6996b0..4332d4b82b 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -56,12 +56,18 @@ static int xfrm6_get_saddr(struct net *net, int oif, { struct dst_entry *dst; struct net_device *dev; + struct inet6_dev *idev; dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr, mark); if (IS_ERR(dst)) return -EHOSTUNREACH; - dev = ip6_dst_idev(dst)->dev; + idev = ip6_dst_idev(dst); + if (!idev) { + dst_release(dst); + return -EHOSTUNREACH; + } + dev = idev->dev; ipv6_dev_get_saddr(dev_net(dev), dev, &daddr->in6, 0, &saddr->in6); dst_release(dst); return 0; @@ -70,7 +76,7 @@ static int xfrm6_get_saddr(struct net *net, int oif, static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl) { - struct rt6_info *rt = (struct rt6_info *)xdst->route; + struct rt6_info *rt = dst_rt6_info(xdst->route); xdst->u.dst.dev = dev; netdev_hold(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f6cb94f82c..bf140ef781 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -355,10 +355,7 @@ static int __init xfrm6_tunnel_init(void) { int rv; - xfrm6_tunnel_spi_kmem = kmem_cache_create("xfrm6_tunnel_spi", - sizeof(struct xfrm6_tunnel_spi), - 0, SLAB_HWCACHE_ALIGN, - NULL); + xfrm6_tunnel_spi_kmem = KMEM_CACHE(xfrm6_tunnel_spi, SLAB_HWCACHE_ALIGN); if (!xfrm6_tunnel_spi_kmem) return -ENOMEM; rv = register_pernet_subsys(&xfrm6_tunnel_net_ops); |