From 510c321b557121861601f9d259aadd65aa274f35 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 14 Feb 2018 19:06:02 +0800 Subject: xfrm: reuse uncached_list to track xdsts In early time, when freeing a xdst, it would be inserted into dst_garbage.list first. Then if it's refcnt was still held somewhere, later it would be put into dst_busy_list in dst_gc_task(). When one dev was being unregistered, the dev of these dsts in dst_busy_list would be set with loopback_dev and put this dev. So that this dev's removal wouldn't get blocked, and avoid the kmsg warning: kernel:unregister_netdevice: waiting for veth0 to become \ free. Usage count = 2 However after Commit 52df157f17e5 ("xfrm: take refcnt of dst when creating struct xfrm_dst bundle"), the xdst will not be freed with dst gc, and this warning happens. To fix it, we need to find these xdsts that are still held by others when removing the dev, and free xdst's dev and set it with loopback_dev. But unfortunately after flow_cache for xfrm was deleted, no list tracks them anymore. So we need to save these xdsts somewhere to release the xdst's dev later. To make this easier, this patch is to reuse uncached_list to track xdsts, so that the dev refcnt can be released in the event NETDEV_UNREGISTER process of fib_netdev_notifier. Thanks to Florian, we could move forward this fix quickly. Fixes: 52df157f17e5 ("xfrm: take refcnt of dst when creating struct xfrm_dst bundle") Reported-by: Jianlin Shi Reported-by: Hangbin Liu Tested-by: Eyal Birger Signed-off-by: Xin Long Signed-off-by: Steffen Klassert --- net/ipv6/route.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv6/route.c') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fb2d251c0500..38b75e9d6eae 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -128,7 +128,7 @@ struct uncached_list { static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); -static void rt6_uncached_list_add(struct rt6_info *rt) +void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); @@ -139,7 +139,7 @@ static void rt6_uncached_list_add(struct rt6_info *rt) spin_unlock_bh(&ul->lock); } -static void rt6_uncached_list_del(struct rt6_info *rt) +void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->rt6i_uncached)) { struct uncached_list *ul = rt->rt6i_uncached_list; -- cgit v1.2.1 From e9fa1495d738e34fcec88a3d2ec9101a9ee5b310 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Tue, 6 Mar 2018 11:10:19 +0100 Subject: ipv6: Reflect MTU changes on PMTU of exceptions for MTU-less routes Currently, administrative MTU changes on a given netdevice are not reflected on route exceptions for MTU-less routes, with a set PMTU value, for that device: # ip -6 route get 2001:db8::b 2001:db8::b from :: dev vti_a proto kernel src 2001:db8::a metric 256 pref medium # ping6 -c 1 -q -s10000 2001:db8::b > /dev/null # ip netns exec a ip -6 route get 2001:db8::b 2001:db8::b from :: dev vti_a src 2001:db8::a metric 0 cache expires 571sec mtu 4926 pref medium # ip link set dev vti_a mtu 3000 # ip -6 route get 2001:db8::b 2001:db8::b from :: dev vti_a src 2001:db8::a metric 0 cache expires 571sec mtu 4926 pref medium # ip link set dev vti_a mtu 9000 # ip -6 route get 2001:db8::b 2001:db8::b from :: dev vti_a src 2001:db8::a metric 0 cache expires 571sec mtu 4926 pref medium The first issue is that since commit fb56be83e43d ("net-ipv6: on device mtu change do not add mtu to mtu-less routes") we don't call rt6_exceptions_update_pmtu() from rt6_mtu_change_route(), which handles administrative MTU changes, if the regular route is MTU-less. However, PMTU exceptions should be always updated, as long as RTAX_MTU is not locked. Keep the check for MTU-less main route, as introduced by that commit, but, for exceptions, call rt6_exceptions_update_pmtu() regardless of that check. Once that is fixed, one problem remains: MTU changes are not reflected if the new MTU is higher than the previous one, because rt6_exceptions_update_pmtu() doesn't allow that. We should instead allow PMTU increase if the old PMTU matches the local MTU, as that implies that the old MTU was the lowest in the path, and PMTU discovery might lead to different results. The existing check in rt6_mtu_change_route() correctly took that case into account (for regular routes only), so factor it out and re-use it also in rt6_exceptions_update_pmtu(). While at it, fix comments style and grammar, and try to be a bit more descriptive. Reported-by: Xiumei Mu Fixes: fb56be83e43d ("net-ipv6: on device mtu change do not add mtu to mtu-less routes") Fixes: f5bbe7ee79c2 ("ipv6: prepare rt6_mtu_change() for exception table") Signed-off-by: Stefano Brivio Acked-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/route.c | 71 +++++++++++++++++++++++++++++++++----------------------- 1 file changed, 42 insertions(+), 29 deletions(-) (limited to 'net/ipv6/route.c') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9dcfadddd800..0db4218c9186 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1509,7 +1509,30 @@ static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt) } } -static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) +static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, + struct rt6_info *rt, int mtu) +{ + /* If the new MTU is lower than the route PMTU, this new MTU will be the + * lowest MTU in the path: always allow updating the route PMTU to + * reflect PMTU decreases. + * + * If the new MTU is higher, and the route PMTU is equal to the local + * MTU, this means the old MTU is the lowest in the path, so allow + * updating it: if other nodes now have lower MTUs, PMTU discovery will + * handle this. + */ + + if (dst_mtu(&rt->dst) >= mtu) + return true; + + if (dst_mtu(&rt->dst) == idev->cnf.mtu6) + return true; + + return false; +} + +static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, + struct rt6_info *rt, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; @@ -1518,20 +1541,22 @@ static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, lockdep_is_held(&rt6_exception_lock)); - if (bucket) { - for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { - hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { - struct rt6_info *entry = rt6_ex->rt6i; - /* For RTF_CACHE with rt6i_pmtu == 0 - * (i.e. a redirected route), - * the metrics of its rt->dst.from has already - * been updated. - */ - if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu) - entry->rt6i_pmtu = mtu; - } - bucket++; + if (!bucket) + return; + + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + + /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected + * route), the metrics of its rt->dst.from have already + * been updated. + */ + if (entry->rt6i_pmtu && + rt6_mtu_change_route_allowed(idev, entry, mtu)) + entry->rt6i_pmtu = mtu; } + bucket++; } } @@ -3809,25 +3834,13 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) Since RFC 1981 doesn't include administrative MTU increase update PMTU increase is a MUST. (i.e. jumbo frame) */ - /* - If new MTU is less than route PMTU, this new MTU will be the - lowest MTU in the path, update the route PMTU to reflect PMTU - decreases; if new MTU is greater than route PMTU, and the - old MTU is the lowest MTU in the path, update the route PMTU - to reflect the increase. In this case if the other nodes' MTU - also have the lowest MTU, TOO BIG MESSAGE will be lead to - PMTU discovery. - */ if (rt->dst.dev == arg->dev && - dst_metric_raw(&rt->dst, RTAX_MTU) && !dst_metric_locked(&rt->dst, RTAX_MTU)) { spin_lock_bh(&rt6_exception_lock); - if (dst_mtu(&rt->dst) >= arg->mtu || - (dst_mtu(&rt->dst) < arg->mtu && - dst_mtu(&rt->dst) == idev->cnf.mtu6)) { + if (dst_metric_raw(&rt->dst, RTAX_MTU) && + rt6_mtu_change_route_allowed(idev, rt, arg->mtu)) dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); - } - rt6_exceptions_update_pmtu(rt, arg->mtu); + rt6_exceptions_update_pmtu(idev, rt, arg->mtu); spin_unlock_bh(&rt6_exception_lock); } return 0; -- cgit v1.2.1 From 68e2ffdeb5dbf54bc3a0684aa4e73c6db8675eed Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 20 Mar 2018 10:06:59 -0700 Subject: net/ipv6: Handle onlink flag with multipath routes For multipath routes the ONLINK flag can be specified per nexthop in rtnh_flags or globally in rtm_flags. Update ip6_route_multipath_add to consider the ONLINK setting coming from rtnh_flags. Each loop over nexthops the config for the sibling route is initialized to the global config and then per nexthop settings overlayed. The flag is 'or'ed into fib6_config to handle the ONLINK flag coming from either rtm_flags or rtnh_flags. Fixes: fc1e64e1092f ("net/ipv6: Add support for onlink flag") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/route.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv6/route.c') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b3c1137ad0b8..b0d5c64e1978 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4112,6 +4112,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, r_cfg.fc_encap_type = nla_get_u16(nla); } + r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK); rt = ip6_route_info_create(&r_cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); -- cgit v1.2.1