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/ipv4/route.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'net/ipv4/route.c') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 49cc1c1df1ba..1d1e4abe04b0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1383,7 +1383,7 @@ struct uncached_list { static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); -static void rt_add_uncached_list(struct rtable *rt) +void rt_add_uncached_list(struct rtable *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list); @@ -1394,14 +1394,8 @@ static void rt_add_uncached_list(struct rtable *rt) spin_unlock_bh(&ul->lock); } -static void ipv4_dst_destroy(struct dst_entry *dst) +void rt_del_uncached_list(struct rtable *rt) { - struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); - struct rtable *rt = (struct rtable *) dst; - - if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) - kfree(p); - if (!list_empty(&rt->rt_uncached)) { struct uncached_list *ul = rt->rt_uncached_list; @@ -1411,6 +1405,17 @@ static void ipv4_dst_destroy(struct dst_entry *dst) } } +static void ipv4_dst_destroy(struct dst_entry *dst) +{ + struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); + struct rtable *rt = (struct rtable *)dst; + + if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) + kfree(p); + + rt_del_uncached_list(rt); +} + void rt_flush_dev(struct net_device *dev) { struct net *net = dev_net(dev); -- cgit v1.2.3-59-g8ed1b From d52e5a7e7ca49457dd31fc8b42fb7c0d58a31221 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Wed, 14 Mar 2018 10:21:14 +0100 Subject: ipv4: lock mtu in fnhe when received PMTU < net.ipv4.route.min_pmtu Prior to the rework of PMTU information storage in commit 2c8cec5c10bc ("ipv4: Cache learned PMTU information in inetpeer."), when a PMTU event advertising a PMTU smaller than net.ipv4.route.min_pmtu was received, we would disable setting the DF flag on packets by locking the MTU metric, and set the PMTU to net.ipv4.route.min_pmtu. Since then, we don't disable DF, and set PMTU to net.ipv4.route.min_pmtu, so the intermediate router that has this link with a small MTU will have to drop the packets. This patch reestablishes pre-2.6.39 behavior by splitting rtable->rt_pmtu into a bitfield with rt_mtu_locked and rt_pmtu. rt_mtu_locked indicates that we shouldn't set the DF bit on that path, and is checked in ip_dont_fragment(). One possible workaround is to set net.ipv4.route.min_pmtu to a value low enough to accommodate the lowest MTU encountered. Fixes: 2c8cec5c10bc ("ipv4: Cache learned PMTU information in inetpeer.") Signed-off-by: Sabrina Dubroca Reviewed-by: Stefano Brivio Signed-off-by: David S. Miller --- include/net/ip.h | 11 +++++++++-- include/net/ip_fib.h | 1 + include/net/route.h | 3 ++- net/ipv4/route.c | 26 +++++++++++++++++++------- net/ipv4/xfrm4_policy.c | 1 + 5 files changed, 32 insertions(+), 10 deletions(-) (limited to 'net/ipv4/route.c') diff --git a/include/net/ip.h b/include/net/ip.h index 746abff9ce51..f49b3a576bec 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -328,6 +328,13 @@ int ip_decrease_ttl(struct iphdr *iph) return --iph->ttl; } +static inline int ip_mtu_locked(const struct dst_entry *dst) +{ + const struct rtable *rt = (const struct rtable *)dst; + + return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU); +} + static inline int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst) { @@ -335,7 +342,7 @@ int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst) return pmtudisc == IP_PMTUDISC_DO || (pmtudisc == IP_PMTUDISC_WANT && - !(dst_metric_locked(dst, RTAX_MTU))); + !ip_mtu_locked(dst)); } static inline bool ip_sk_accept_pmtu(const struct sock *sk) @@ -361,7 +368,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, struct net *net = dev_net(dst->dev); if (net->ipv4.sysctl_ip_fwd_use_pmtu || - dst_metric_locked(dst, RTAX_MTU) || + ip_mtu_locked(dst) || !forwarding) return dst_mtu(dst); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index f80524396c06..77d0a78cf7d2 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -59,6 +59,7 @@ struct fib_nh_exception { int fnhe_genid; __be32 fnhe_daddr; u32 fnhe_pmtu; + bool fnhe_mtu_locked; __be32 fnhe_gw; unsigned long fnhe_expires; struct rtable __rcu *fnhe_rth_input; diff --git a/include/net/route.h b/include/net/route.h index 40b870d58f38..20a92ca9e115 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -63,7 +63,8 @@ struct rtable { __be32 rt_gateway; /* Miscellaneous cached information */ - u32 rt_pmtu; + u32 rt_mtu_locked:1, + rt_pmtu:31; u32 rt_table_id; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f9dbb8cb66bf..299e247b2032 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -634,6 +634,7 @@ static inline u32 fnhe_hashfun(__be32 daddr) static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) { rt->rt_pmtu = fnhe->fnhe_pmtu; + rt->rt_mtu_locked = fnhe->fnhe_mtu_locked; rt->dst.expires = fnhe->fnhe_expires; if (fnhe->fnhe_gw) { @@ -644,7 +645,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh } static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, - u32 pmtu, unsigned long expires) + u32 pmtu, bool lock, unsigned long expires) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; @@ -681,8 +682,10 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_genid = genid; if (gw) fnhe->fnhe_gw = gw; - if (pmtu) + if (pmtu) { fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_mtu_locked = lock; + } fnhe->fnhe_expires = max(1UL, expires); /* Update all cached dsts too */ rt = rcu_dereference(fnhe->fnhe_rth_input); @@ -706,6 +709,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = expires; /* Exception created; mark the cached routes for the nexthop @@ -787,7 +791,8 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, jiffies + ip_rt_gc_timeout); + 0, false, + jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -1009,15 +1014,18 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; struct fib_result res; + bool lock = false; - if (dst_metric_locked(dst, RTAX_MTU)) + if (ip_mtu_locked(dst)) return; if (ipv4_mtu(dst) < mtu) return; - if (mtu < ip_rt_min_pmtu) + if (mtu < ip_rt_min_pmtu) { + lock = true; mtu = ip_rt_min_pmtu; + } if (rt->rt_pmtu == mtu && time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2)) @@ -1027,7 +1035,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) { struct fib_nh *nh = &FIB_RES_NH(res); - update_or_create_fnhe(nh, fl4->daddr, 0, mtu, + update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock, jiffies + ip_rt_mtu_expires); } rcu_read_unlock(); @@ -1280,7 +1288,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = READ_ONCE(dst->dev->mtu); - if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { + if (unlikely(ip_mtu_locked(dst))) { if (rt->rt_uses_gateway && mtu > 576) mtu = 576; } @@ -1521,6 +1529,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_is_input = 0; rt->rt_iif = 0; rt->rt_pmtu = 0; + rt->rt_mtu_locked = 0; rt->rt_gateway = 0; rt->rt_uses_gateway = 0; rt->rt_table_id = 0; @@ -2546,6 +2555,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; + rt->rt_mtu_locked = ort->rt_mtu_locked; rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; @@ -2648,6 +2658,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); if (rt->rt_pmtu && expires) metrics[RTAX_MTU - 1] = rt->rt_pmtu; + if (rt->rt_mtu_locked && expires) + metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU); if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 8d33f7b311f4..fbebda67ac1b 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -100,6 +100,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_gateway = rt->rt_gateway; xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; + xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked; xdst->u.rt.rt_table_id = rt->rt_table_id; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); rt_add_uncached_list(&xdst->u.rt); -- cgit v1.2.3-59-g8ed1b