Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking update from David S. Miller:
 "I think Eric Dumazet and I have dealt with all of the known routing
  cache removal fallout.  Some other minor fixes all around.

  1) Fix RCU of cached routes, particular of output routes which require
     liberation via call_rcu() instead of call_rcu_bh().  From Eric
     Dumazet.

  2) Make sure we purge net device references in cached routes properly.

  3) TG3 driver bug fixes from Michael Chan.

  4) Fix reported 'expires' value in ipv6 routes, from Li Wei.

  5) TUN driver ioctl leaks kernel bytes to userspace, from Mathias
     Krause."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (22 commits)
  ipv4: Properly purge netdev references on uncached routes.
  ipv4: Cache routes in nexthop exception entries.
  ipv4: percpu nh_rth_output cache
  ipv4: Restore old dst_free() behavior.
  bridge: make port attributes const
  ipv4: remove rt_cache_rebuild_count
  net: ipv4: fix RCU races on dst refcounts
  net: TCP early demux cleanup
  tun: Fix formatting.
  net/tun: fix ioctl() based info leaks
  tg3: Update version to 3.124
  tg3: Fix race condition in tg3_get_stats64()
  tg3: Add New 5719 Read DMA workaround
  tg3: Fix Read DMA workaround for 5719 A0.
  tg3: Request APE_LOCK_PHY before PHY access
  ipv6: fix incorrect route 'expires' value passed to userspace
  mISDN: Bugfix only few bytes are transfered on a connection
  seeq: use PTR_RET at init_module of driver
  bnx2x: remove cast around the kmalloc in bnx2x_prev_mark_path
  ipv4: clean up put_child
  ...

14 files changed, 216 insertions, 119 deletions

diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 6229b62749e8..13b36bdc76a7 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -27,7 +27,7 @@ struct brport_attribute {
 };
 
 #define BRPORT_ATTR(_name,_mode,_show,_store)                   \
-struct brport_attribute brport_attr_##_name = {                 \
+const struct brport_attribute brport_attr_##_name = {           \
         .attr = {.name = __stringify(_name),                    \
                  .mode = _mode },                               \
         .show   = _show,                                        \
@@ -164,7 +164,7 @@ static BRPORT_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router,
                    store_multicast_router);
 #endif
 
-static struct brport_attribute *brport_attrs[] = {
+static const struct brport_attribute *brport_attrs[] = {
         &brport_attr_path_cost,
         &brport_attr_priority,
         &brport_attr_port_id,
@@ -241,7 +241,7 @@ const struct sysfs_ops brport_sysfs_ops = {
 int br_sysfs_addif(struct net_bridge_port *p)
 {
         struct net_bridge *br = p->br;
-        struct brport_attribute **a;
+        const struct brport_attribute **a;
         int err;
 
         err = sysfs_create_link(&p->kobj, &br->dev->dev.kobj,
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index bc9e380f0abf..5ff949dc954f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -625,9 +625,13 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
                 .rta_id =  id,
         };
 
-        if (expires)
-                ci.rta_expires = jiffies_to_clock_t(expires);
+        if (expires) {
+                unsigned long clock;
 
+                clock = jiffies_to_clock_t(abs(expires));
+                clock = min_t(unsigned long, clock, INT_MAX);
+                ci.rta_expires = (expires > 0) ? clock : -clock;
+        }
         return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci);
 }
 EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 8732cc7920ed..c43ae3fba792 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1046,6 +1046,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 
         if (event == NETDEV_UNREGISTER) {
                 fib_disable_ip(dev, 2, -1);
+                rt_flush_dev(dev);
                 return NOTIFY_DONE;
         }
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index da0cc2e6b250..da80dc14cc76 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -140,6 +140,21 @@ const struct fib_prop fib_props[RTN_MAX + 1] = {
         },
 };
 
+static void rt_fibinfo_free(struct rtable __rcu **rtp)
+{
+        struct rtable *rt = rcu_dereference_protected(*rtp, 1);
+
+        if (!rt)
+                return;
+
+        /* Not even needed : RCU_INIT_POINTER(*rtp, NULL);
+         * because we waited an RCU grace period before calling
+         * free_fib_info_rcu()
+         */
+
+        dst_free(&rt->dst);
+}
+
 static void free_nh_exceptions(struct fib_nh *nh)
 {
         struct fnhe_hash_bucket *hash = nh->nh_exceptions;
@@ -153,6 +168,9 @@ static void free_nh_exceptions(struct fib_nh *nh)
                         struct fib_nh_exception *next;
                         
                         next = rcu_dereference_protected(fnhe->fnhe_next, 1);
+
+                        rt_fibinfo_free(&fnhe->fnhe_rth);
+
                         kfree(fnhe);
 
                         fnhe = next;
@@ -161,6 +179,23 @@ static void free_nh_exceptions(struct fib_nh *nh)
         kfree(hash);
 }
 
+static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
+{
+        int cpu;
+
+        if (!rtp)
+                return;
+
+        for_each_possible_cpu(cpu) {
+                struct rtable *rt;
+
+                rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1);
+                if (rt)
+                        dst_free(&rt->dst);
+        }
+        free_percpu(rtp);
+}
+
 /* Release a nexthop info record */
 static void free_fib_info_rcu(struct rcu_head *head)
 {
@@ -171,10 +206,8 @@ static void free_fib_info_rcu(struct rcu_head *head)
                         dev_put(nexthop_nh->nh_dev);
                 if (nexthop_nh->nh_exceptions)
                         free_nh_exceptions(nexthop_nh);
-                if (nexthop_nh->nh_rth_output)
-                        dst_free(&nexthop_nh->nh_rth_output->dst);
-                if (nexthop_nh->nh_rth_input)
-                        dst_free(&nexthop_nh->nh_rth_input->dst);
+                rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output);
+                rt_fibinfo_free(&nexthop_nh->nh_rth_input);
         } endfor_nexthops(fi);
 
         release_net(fi->fib_net);
@@ -804,6 +837,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
         fi->fib_nhs = nhs;
         change_nexthops(fi) {
                 nexthop_nh->nh_parent = fi;
+                nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
         } endfor_nexthops(fi)
 
         if (cfg->fc_mx) {
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 18cbc15b20d5..f0cdb30921c0 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -159,7 +159,6 @@ struct trie {
 #endif
 };
 
-static void put_child(struct trie *t, struct tnode *tn, int i, struct rt_trie_node *n);
 static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n,
                                   int wasfull);
 static struct rt_trie_node *resize(struct trie *t, struct tnode *tn);
@@ -473,7 +472,7 @@ static struct tnode *tnode_new(t_key key, int pos, int bits)
         }
 
         pr_debug("AT %p s=%zu %zu\n", tn, sizeof(struct tnode),
-                 sizeof(struct rt_trie_node) << bits);
+                 sizeof(struct rt_trie_node *) << bits);
         return tn;
 }
 
@@ -490,7 +489,7 @@ static inline int tnode_full(const struct tnode *tn, const struct rt_trie_node *
         return ((struct tnode *) n)->pos == tn->pos + tn->bits;
 }
 
-static inline void put_child(struct trie *t, struct tnode *tn, int i,
+static inline void put_child(struct tnode *tn, int i,
                              struct rt_trie_node *n)
 {
         tnode_put_child_reorg(tn, i, n, -1);
@@ -754,8 +753,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn)
                                 goto nomem;
                         }
 
-                        put_child(t, tn, 2*i, (struct rt_trie_node *) left);
-                        put_child(t, tn, 2*i+1, (struct rt_trie_node *) right);
+                        put_child(tn, 2*i, (struct rt_trie_node *) left);
+                        put_child(tn, 2*i+1, (struct rt_trie_node *) right);
                 }
         }
 
@@ -776,9 +775,9 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn)
                         if (tkey_extract_bits(node->key,
                                               oldtnode->pos + oldtnode->bits,
                                               1) == 0)
-                                put_child(t, tn, 2*i, node);
+                                put_child(tn, 2*i, node);
                         else
-                                put_child(t, tn, 2*i+1, node);
+                                put_child(tn, 2*i+1, node);
                         continue;
                 }
 
@@ -786,8 +785,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn)
                 inode = (struct tnode *) node;
 
                 if (inode->bits == 1) {
-                        put_child(t, tn, 2*i, rtnl_dereference(inode->child[0]));
-                        put_child(t, tn, 2*i+1, rtnl_dereference(inode->child[1]));
+                        put_child(tn, 2*i, rtnl_dereference(inode->child[0]));
+                        put_child(tn, 2*i+1, rtnl_dereference(inode->child[1]));
 
                         tnode_free_safe(inode);
                         continue;
@@ -817,22 +816,22 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn)
                  */
 
                 left = (struct tnode *) tnode_get_child(tn, 2*i);
-                put_child(t, tn, 2*i, NULL);
+                put_child(tn, 2*i, NULL);
 
                 BUG_ON(!left);
 
                 right = (struct tnode *) tnode_get_child(tn, 2*i+1);
-                put_child(t, tn, 2*i+1, NULL);
+                put_child(tn, 2*i+1, NULL);
 
                 BUG_ON(!right);
 
                 size = tnode_child_length(left);
                 for (j = 0; j < size; j++) {
-                        put_child(t, left, j, rtnl_dereference(inode->child[j]));
-                        put_child(t, right, j, rtnl_dereference(inode->child[j + size]));
+                        put_child(left, j, rtnl_dereference(inode->child[j]));
+                        put_child(right, j, rtnl_dereference(inode->child[j + size]));
                 }
-                put_child(t, tn, 2*i, resize(t, left));
-                put_child(t, tn, 2*i+1, resize(t, right));
+                put_child(tn, 2*i, resize(t, left));
+                put_child(tn, 2*i+1, resize(t, right));
 
                 tnode_free_safe(inode);
         }
@@ -877,7 +876,7 @@ static struct tnode *halve(struct trie *t, struct tnode *tn)
                         if (!newn)
                                 goto nomem;
 
-                        put_child(t, tn, i/2, (struct rt_trie_node *)newn);
+                        put_child(tn, i/2, (struct rt_trie_node *)newn);
                 }
 
         }
@@ -892,21 +891,21 @@ static struct tnode *halve(struct trie *t, struct tnode *tn)
                 if (left == NULL) {
                         if (right == NULL)    /* Both are empty */
                                 continue;
-                        put_child(t, tn, i/2, right);
+                        put_child(tn, i/2, right);
                         continue;
                 }
 
                 if (right == NULL) {
-                        put_child(t, tn, i/2, left);
+                        put_child(tn, i/2, left);
                         continue;
                 }
 
                 /* Two nonempty children */
                 newBinNode = (struct tnode *) tnode_get_child(tn, i/2);
-                put_child(t, tn, i/2, NULL);
-                put_child(t, newBinNode, 0, left);
-                put_child(t, newBinNode, 1, right);
-                put_child(t, tn, i/2, resize(t, newBinNode));
+                put_child(tn, i/2, NULL);
+                put_child(newBinNode, 0, left);
+                put_child(newBinNode, 1, right);
+                put_child(tn, i/2, resize(t, newBinNode));
         }
         tnode_free_safe(oldtnode);
         return tn;
@@ -1125,7 +1124,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen)
                 node_set_parent((struct rt_trie_node *)l, tp);
 
                 cindex = tkey_extract_bits(key, tp->pos, tp->bits);
-                put_child(t, tp, cindex, (struct rt_trie_node *)l);
+                put_child(tp, cindex, (struct rt_trie_node *)l);
         } else {
                 /* Case 3: n is a LEAF or a TNODE and the key doesn't match. */
                 /*
@@ -1155,12 +1154,12 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen)
                 node_set_parent((struct rt_trie_node *)tn, tp);
 
                 missbit = tkey_extract_bits(key, newpos, 1);
-                put_child(t, tn, missbit, (struct rt_trie_node *)l);
-                put_child(t, tn, 1-missbit, n);
+                put_child(tn, missbit, (struct rt_trie_node *)l);
+                put_child(tn, 1-missbit, n);
 
                 if (tp) {
                         cindex = tkey_extract_bits(key, tp->pos, tp->bits);
-                        put_child(t, tp, cindex, (struct rt_trie_node *)tn);
+                        put_child(tp, cindex, (struct rt_trie_node *)tn);
                 } else {
                         rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn);
                         tp = tn;
@@ -1619,7 +1618,7 @@ static void trie_leaf_remove(struct trie *t, struct leaf *l)
 
         if (tp) {
                 t_key cindex = tkey_extract_bits(l->key, tp->pos, tp->bits);
-                put_child(t, tp, cindex, NULL);
+                put_child(tp, cindex, NULL);
                 trie_rebalance(t, tp);
         } else
                 RCU_INIT_POINTER(t->trie, NULL);
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 981ff1eef28c..f1395a6fb35f 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -325,14 +325,12 @@ static int ip_rcv_finish(struct sk_buff *skb)
                 const struct net_protocol *ipprot;
                 int protocol = iph->protocol;
 
-                rcu_read_lock();
                 ipprot = rcu_dereference(inet_protos[protocol]);
                 if (ipprot && ipprot->early_demux) {
                         ipprot->early_demux(skb);
                         /* must reload iph, skb->head might have changed */
                         iph = ip_hdr(skb);
                 }
-                rcu_read_unlock();
         }
 
         /*
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index fc1a81ca79a7..c035251beb07 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -147,6 +147,7 @@ static void		 ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
                                            struct sk_buff *skb, u32 mtu);
 static void              ip_do_redirect(struct dst_entry *dst, struct sock *sk,
                                         struct sk_buff *skb);
+static void             ipv4_dst_destroy(struct dst_entry *dst);
 
 static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
                             int how)
@@ -170,6 +171,7 @@ static struct dst_ops ipv4_dst_ops = {
         .default_advmss =       ipv4_default_advmss,
         .mtu =                  ipv4_mtu,
         .cow_metrics =          ipv4_cow_metrics,
+        .destroy =              ipv4_dst_destroy,
         .ifdown =               ipv4_dst_ifdown,
         .negative_advice =      ipv4_negative_advice,
         .link_failure =         ipv4_link_failure,
@@ -587,11 +589,17 @@ static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk,
                 build_sk_flow_key(fl4, sk);
 }
 
-static DEFINE_SEQLOCK(fnhe_seqlock);
+static inline void rt_free(struct rtable *rt)
+{
+        call_rcu(&rt->dst.rcu_head, dst_rcu_free);
+}
+
+static DEFINE_SPINLOCK(fnhe_lock);
 
 static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash)
 {
         struct fib_nh_exception *fnhe, *oldest;
+        struct rtable *orig;
 
         oldest = rcu_dereference(hash->chain);
         for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe;
@@ -599,6 +607,11 @@ static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash)
                 if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp))
                         oldest = fnhe;
         }
+        orig = rcu_dereference(oldest->fnhe_rth);
+        if (orig) {
+                RCU_INIT_POINTER(oldest->fnhe_rth, NULL);
+                rt_free(orig);
+        }
         return oldest;
 }
 
@@ -620,7 +633,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
         int depth;
         u32 hval = fnhe_hashfun(daddr);
 
-        write_seqlock_bh(&fnhe_seqlock);
+        spin_lock_bh(&fnhe_lock);
 
         hash = nh->nh_exceptions;
         if (!hash) {
@@ -667,7 +680,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
         fnhe->fnhe_stamp = jiffies;
 
 out_unlock:
-        write_sequnlock_bh(&fnhe_seqlock);
+        spin_unlock_bh(&fnhe_lock);
         return;
 }
 
@@ -1164,53 +1177,62 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
         return NULL;
 }
 
-static void rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
+static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
                               __be32 daddr)
 {
-        __be32 fnhe_daddr, gw;
-        unsigned long expires;
-        unsigned int seq;
-        u32 pmtu;
-
-restart:
-        seq = read_seqbegin(&fnhe_seqlock);
-        fnhe_daddr = fnhe->fnhe_daddr;
-        gw = fnhe->fnhe_gw;
-        pmtu = fnhe->fnhe_pmtu;
-        expires = fnhe->fnhe_expires;
-        if (read_seqretry(&fnhe_seqlock, seq))
-                goto restart;
-
-        if (daddr != fnhe_daddr)
-                return;
+        bool ret = false;
+
+        spin_lock_bh(&fnhe_lock);
 
-        if (pmtu) {
-                unsigned long diff = expires - jiffies;
+        if (daddr == fnhe->fnhe_daddr) {
+                struct rtable *orig;
 
-                if (time_before(jiffies, expires)) {
-                        rt->rt_pmtu = pmtu;
-                        dst_set_expires(&rt->dst, diff);
+                if (fnhe->fnhe_pmtu) {
+                        unsigned long expires = fnhe->fnhe_expires;
+                        unsigned long diff = expires - jiffies;
+
+                        if (time_before(jiffies, expires)) {
+                                rt->rt_pmtu = fnhe->fnhe_pmtu;
+                                dst_set_expires(&rt->dst, diff);
+                        }
                 }
+                if (fnhe->fnhe_gw) {
+                        rt->rt_flags |= RTCF_REDIRECTED;
+                        rt->rt_gateway = fnhe->fnhe_gw;
+                }
+
+                orig = rcu_dereference(fnhe->fnhe_rth);
+                rcu_assign_pointer(fnhe->fnhe_rth, rt);
+                if (orig)
+                        rt_free(orig);
+
+                fnhe->fnhe_stamp = jiffies;
+                ret = true;
+        } else {
+                /* Routes we intend to cache in nexthop exception have
+                 * the DST_NOCACHE bit clear.  However, if we are
+                 * unsuccessful at storing this route into the cache
+                 * we really need to set it.
+                 */
+                rt->dst.flags |= DST_NOCACHE;
         }
-        if (gw) {
-                rt->rt_flags |= RTCF_REDIRECTED;
-                rt->rt_gateway = gw;
-        }
-        fnhe->fnhe_stamp = jiffies;
-}
+        spin_unlock_bh(&fnhe_lock);
 
-static inline void rt_free(struct rtable *rt)
-{
-        call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
+        return ret;
 }
 
-static void rt_cache_route(struct fib_nh *nh, struct rtable *rt)
+static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
 {
-        struct rtable *orig, *prev, **p = &nh->nh_rth_output;
-
-        if (rt_is_input_route(rt))
-                p = &nh->nh_rth_input;
+        struct rtable *orig, *prev, **p;
+        bool ret = true;
 
+        if (rt_is_input_route(rt)) {
+                p = (struct rtable **)&nh->nh_rth_input;
+        } else {
+                if (!nh->nh_pcpu_rth_output)
+                        goto nocache;
+                p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output);
+        }
         orig = *p;
 
         prev = cmpxchg(p, orig, rt);
@@ -1223,7 +1245,50 @@ static void rt_cache_route(struct fib_nh *nh, struct rtable *rt)
                  * unsuccessful at storing this route into the cache
                  * we really need to set it.
                  */
+nocache:
                 rt->dst.flags |= DST_NOCACHE;
+                ret = false;
+        }
+
+        return ret;
+}
+
+static DEFINE_SPINLOCK(rt_uncached_lock);
+static LIST_HEAD(rt_uncached_list);
+
+static void rt_add_uncached_list(struct rtable *rt)
+{
+        spin_lock_bh(&rt_uncached_lock);
+        list_add_tail(&rt->rt_uncached, &rt_uncached_list);
+        spin_unlock_bh(&rt_uncached_lock);
+}
+
+static void ipv4_dst_destroy(struct dst_entry *dst)
+{
+        struct rtable *rt = (struct rtable *) dst;
+
+        if (dst->flags & DST_NOCACHE) {
+                spin_lock_bh(&rt_uncached_lock);
+                list_del(&rt->rt_uncached);
+                spin_unlock_bh(&rt_uncached_lock);
+        }
+}
+
+void rt_flush_dev(struct net_device *dev)
+{
+        if (!list_empty(&rt_uncached_list)) {
+                struct net *net = dev_net(dev);
+                struct rtable *rt;
+
+                spin_lock_bh(&rt_uncached_lock);
+                list_for_each_entry(rt, &rt_uncached_list, rt_uncached) {
+                        if (rt->dst.dev != dev)
+                                continue;
+                        rt->dst.dev = net->loopback_dev;
+                        dev_hold(rt->dst.dev);
+                        dev_put(dev);
+                }
+                spin_unlock_bh(&rt_uncached_lock);
         }
 }
 
@@ -1239,20 +1304,24 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
                            struct fib_nh_exception *fnhe,
                            struct fib_info *fi, u16 type, u32 itag)
 {
+        bool cached = false;
+
         if (fi) {
                 struct fib_nh *nh = &FIB_RES_NH(*res);
 
                 if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK)
                         rt->rt_gateway = nh->nh_gw;
-                if (unlikely(fnhe))
-                        rt_bind_exception(rt, fnhe, daddr);
                 dst_init_metrics(&rt->dst, fi->fib_metrics, true);
 #ifdef CONFIG_IP_ROUTE_CLASSID
                 rt->dst.tclassid = nh->nh_tclassid;
 #endif
-                if (!(rt->dst.flags & DST_NOCACHE))
-                        rt_cache_route(nh, rt);
+                if (unlikely(fnhe))
+                        cached = rt_bind_exception(rt, fnhe, daddr);
+                else if (!(rt->dst.flags & DST_NOCACHE))
+                        cached = rt_cache_route(nh, rt);
         }
+        if (unlikely(!cached))
+                rt_add_uncached_list(rt);
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
 #ifdef CONFIG_IP_MULTIPLE_TABLES
@@ -1319,6 +1388,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
         rth->rt_iif     = 0;
         rth->rt_pmtu    = 0;
         rth->rt_gateway = 0;
+        INIT_LIST_HEAD(&rth->rt_uncached);
         if (our) {
                 rth->dst.input= ip_local_deliver;
                 rth->rt_flags |= RTCF_LOCAL;
@@ -1420,7 +1490,7 @@ static int __mkroute_input(struct sk_buff *skb,
         do_cache = false;
         if (res->fi) {
                 if (!itag) {
-                        rth = FIB_RES_NH(*res).nh_rth_input;
+                        rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
                         if (rt_cache_valid(rth)) {
                                 skb_dst_set_noref(skb, &rth->dst);
                                 goto out;
@@ -1444,6 +1514,7 @@ static int __mkroute_input(struct sk_buff *skb,
         rth->rt_iif     = 0;
         rth->rt_pmtu    = 0;
         rth->rt_gateway = 0;
+        INIT_LIST_HEAD(&rth->rt_uncached);
 
         rth->dst.input = ip_forward;
         rth->dst.output = ip_output;
@@ -1582,7 +1653,7 @@ local_input:
         do_cache = false;
         if (res.fi) {
                 if (!itag) {
-                        rth = FIB_RES_NH(res).nh_rth_input;
+                        rth = rcu_dereference(FIB_RES_NH(res).nh_rth_input);
                         if (rt_cache_valid(rth)) {
                                 skb_dst_set_noref(skb, &rth->dst);
                                 err = 0;
@@ -1610,6 +1681,7 @@ local_input:
         rth->rt_iif     = 0;
         rth->rt_pmtu    = 0;
         rth->rt_gateway = 0;
+        INIT_LIST_HEAD(&rth->rt_uncached);
         if (res.type == RTN_UNREACHABLE) {
                 rth->dst.input= ip_error;
                 rth->dst.error= -err;
@@ -1748,19 +1820,23 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 
         fnhe = NULL;
         if (fi) {
+                struct rtable __rcu **prth;
+
                 fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr);
-                if (!fnhe) {
-                        rth = FIB_RES_NH(*res).nh_rth_output;
-                        if (rt_cache_valid(rth)) {
-                                dst_hold(&rth->dst);
-                                return rth;
-                        }
+                if (fnhe)
+                        prth = &fnhe->fnhe_rth;
+                else
+                        prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output);
+                rth = rcu_dereference(*prth);
+                if (rt_cache_valid(rth)) {
+                        dst_hold(&rth->dst);
+                        return rth;
                 }
         }
         rth = rt_dst_alloc(dev_out,
                            IN_DEV_CONF_GET(in_dev, NOPOLICY),
                            IN_DEV_CONF_GET(in_dev, NOXFRM),
-                           fi && !fnhe);
+                           fi);
         if (!rth)
                 return ERR_PTR(-ENOBUFS);
 
@@ -1773,6 +1849,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
         rth->rt_iif     = orig_oif ? : 0;
         rth->rt_pmtu    = 0;
         rth->rt_gateway = 0;
+        INIT_LIST_HEAD(&rth->rt_uncached);
 
         RT_CACHE_STAT_INC(out_slow_tot);
 
@@ -2052,6 +2129,8 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
                 rt->rt_type = ort->rt_type;
                 rt->rt_gateway = ort->rt_gateway;
 
+                INIT_LIST_HEAD(&rt->rt_uncached);
+
                 dst_free(new);
         }
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 5840c3255721..4b6487a68279 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -784,13 +784,6 @@ static struct ctl_table ipv4_net_table[] = {
                 .proc_handler   = proc_dointvec
         },
         {
-                .procname       = "rt_cache_rebuild_count",
-                .data           = &init_net.ipv4.sysctl_rt_cache_rebuild_count,
-                .maxlen         = sizeof(int),
-                .mode           = 0644,
-                .proc_handler   = proc_dointvec
-        },
-        {
                 .procname       = "ping_group_range",
                 .data           = &init_net.ipv4.sysctl_ping_group_range,
                 .maxlen         = sizeof(init_net.ipv4.sysctl_ping_group_range),
@@ -829,8 +822,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
                 table[5].data =
                         &net->ipv4.sysctl_icmp_ratemask;
                 table[6].data =
-                        &net->ipv4.sysctl_rt_cache_rebuild_count;
-                table[7].data =
                         &net->ipv4.sysctl_ping_group_range;
 
         }
@@ -842,8 +833,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
         net->ipv4.sysctl_ping_group_range[0] = 1;
         net->ipv4.sysctl_ping_group_range[1] = 0;
 
-        net->ipv4.sysctl_rt_cache_rebuild_count = 4;
-
         tcp_init_mem(net);
 
         net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a356e1fecf9a..9be30b039ae3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5604,8 +5604,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
         tcp_set_state(sk, TCP_ESTABLISHED);
 
         if (skb != NULL) {
-                sk->sk_rx_dst = dst_clone(skb_dst(skb));
-                inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+                inet_sk_rx_dst_set(sk, skb);
                 security_inet_conn_established(sk, skb);
         }
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2fbd9921253f..7f91e5ac8277 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1617,19 +1617,19 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 #endif
 
         if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
+                struct dst_entry *dst = sk->sk_rx_dst;
+
                 sock_rps_save_rxhash(sk, skb);
-                if (sk->sk_rx_dst) {
-                        struct dst_entry *dst = sk->sk_rx_dst;
+                if (dst) {
                         if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
                             dst->ops->check(dst, 0) == NULL) {
                                 dst_release(dst);
                                 sk->sk_rx_dst = NULL;
                         }
                 }
-                if (unlikely(sk->sk_rx_dst == NULL)) {
-                        sk->sk_rx_dst = dst_clone(skb_dst(skb));
-                        inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
-                }
+                if (unlikely(sk->sk_rx_dst == NULL))
+                        inet_sk_rx_dst_set(sk, skb);
+
                 if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
                         rsk = sk;
                         goto reset;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 3f1cc2028edd..232a90c3ec86 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -387,8 +387,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
                 struct tcp_sock *oldtp = tcp_sk(sk);
                 struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
 
-                newsk->sk_rx_dst = dst_clone(skb_dst(skb));
-                inet_sk(newsk)->rx_dst_ifindex = skb->skb_iif;
+                inet_sk_rx_dst_set(newsk, skb);
 
                 /* TCP Cookie Transactions require space for the cookie pair,
                  * as it differs for each connection.  There is no need to
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index c6281847f16a..681ea2f413e2 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -92,6 +92,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
         xdst->u.rt.rt_type = rt->rt_type;
         xdst->u.rt.rt_gateway = rt->rt_gateway;
         xdst->u.rt.rt_pmtu = rt->rt_pmtu;
+        INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
 
         return 0;
 }
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 47975e363fcd..a52d864d562b 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -52,11 +52,9 @@ int ip6_rcv_finish(struct sk_buff *skb)
         if (sysctl_ip_early_demux && !skb_dst(skb)) {
                 const struct inet6_protocol *ipprot;
 
-                rcu_read_lock();
                 ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
                 if (ipprot && ipprot->early_demux)
                         ipprot->early_demux(skb);
-                rcu_read_unlock();
         }
         if (!skb_dst(skb))
                 ip6_route_input(skb);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index cf02cb97bbdd..8e80fd279100 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2480,12 +2480,8 @@ static int rt6_fill_node(struct net *net,
                 goto nla_put_failure;
         if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric))
                 goto nla_put_failure;
-        if (!(rt->rt6i_flags & RTF_EXPIRES))
-                expires = 0;
-        else if (rt->dst.expires - jiffies < INT_MAX)
-                expires = rt->dst.expires - jiffies;
-        else
-                expires = INT_MAX;
+
+        expires = (rt->rt6i_flags & RTF_EXPIRES) ? rt->dst.expires - jiffies : 0;
 
         if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0)
                 goto nla_put_failure;