Merge branch 'fib6-rcu'

Wei Wang says:

====================
ipv6: replace rwlock with rcu and spinlock in fib6 table

Currently, fib6 table is protected by rwlock. During route lookup,
reader lock is taken and during route insertion, deletion or
modification, writer lock is taken. This is a very inefficient
implementation because the fastpath always has to do the operation
to grab the reader lock.
According to my latest syn flood test on an iota ivybridage machine
with 2 10G mlx nics bonded together, each with 8 rx queues on 2 NUMA
nodes, and with the upstream net-next kernel:
ipv4 stack can handle around 4.2Mpps
ipv6 stack can handle around 1.3Mpps

In order to close the gap of the performance number between ipv4
and ipv6 stack, this patch series tries to get rid of the usage of
the rwlock and replace it with rcu and spinlock protection. This will
greatly speed up the fastpath performance as it only needs to hold
rcu which is much less expensive than grabbing the reader lock. It
also makes ipv6 fib implementation more consistent with ipv4.

In order to be able to replace the current rwlock with rcu and
spinlock, some preparation work is needed:
Patch 1-8 introduces a per-route hash table (protected by rcu and a
different spinlock) to store all cached routes created by pmtu and ip
redirect under its main route. This makes the main fib6 tree only
contain static routes.
Patch 9-14 prepares all the reader path to be ready to tolerate
concurrent writer.
Patch 15 finally does the rwlock to rcu and spinlock conversion.
Patch 16 takes care of rt6_stats.

After this patch series, in the same syn flood test,
ipv6 stack can now handle around 3.5Mpps compared to previous 1.3Mpps
in my test setup.

After this patch series, there are still some improvements that should
be done in ipv6 stack:
1. During route lookup, dst_use() is called everytime on the selected
route to update dst->__use and dst->lastuse. This dirties the cacheline
and causes extra cacheline miss and should be avoided.
2. when no route is found in the current table, net->ip6.ipv6_null_entry
is used and refcnt is taken on it. As there is no pcpu cache for this
specific route, frequent change on the refcnt for this route causes
quite some cacheline misses.
And to make things worse, if CONFIG_IPV6_MULTIPLE_TABLES is defined,
output path route lookup always starts with local table first and
guarantees to hit net->ipv6.ip6_null_entry before continuing to do
lookup in the main table.
These operations on net->ipv6.ip6_null_entry could potentially be
avoided.
3. ipv6 input path route lookup grabs refcnt on dst. This is different
from ipv4. We could potentially change this behavior to let ipv6 input
path route lookup not to grab refcnt on dst. However, it does not give
us much performance boost as we currently have pcpu route cache for
input path as well in ipv6. But this work probably is still worth doing
to unify ipv6 and ipv4 route lookup behavior.

The above issues will be addressed separately after this patch series
has been accepted.

This is a joint work with Martin KaFai Lau and Eric Dumazet. And many
many thanks to them for their inspiring ideas and big big code review
efforts.
====================

Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/dst.h

@@ -101,7 +101,7 @@ struct dst_entry {
 	union {
 		struct dst_entry	*next;
 		struct rtable __rcu	*rt_next;
-		struct rt6_info		*rt6_next;
+		struct rt6_info __rcu	*rt6_next;
 		struct dn_route __rcu	*dn_next;
 	};
 };

include/net/ip6_fib.h

@@ -29,6 +29,14 @@
 #define FIB6_TABLE_HASHSZ 1
 #endif
 
+#define RT6_DEBUG 2
+
+#if RT6_DEBUG >= 3
+#define RT6_TRACE(x...) pr_debug(x)
+#else
+#define RT6_TRACE(x...) do { ; } while (0)
+#endif
+
 struct rt6_info;
 
 struct fib6_config {
@@ -60,25 +68,30 @@ struct fib6_config {
 };
 
 struct fib6_node {
-	struct fib6_node	*parent;
-	struct fib6_node	*left;
-	struct fib6_node	*right;
+	struct fib6_node __rcu	*parent;
+	struct fib6_node __rcu	*left;
+	struct fib6_node __rcu	*right;
 #ifdef CONFIG_IPV6_SUBTREES
-	struct fib6_node	*subtree;
+	struct fib6_node __rcu	*subtree;
 #endif
-	struct rt6_info		*leaf;
+	struct rt6_info __rcu	*leaf;
 
 	__u16			fn_bit;		/* bit key */
 	__u16			fn_flags;
 	int			fn_sernum;
-	struct rt6_info		*rr_ptr;
+	struct rt6_info __rcu	*rr_ptr;
 	struct rcu_head		rcu;
 };
 
+struct fib6_gc_args {
+	int			timeout;
+	int			more;
+};
+
 #ifndef CONFIG_IPV6_SUBTREES
 #define FIB6_SUBTREE(fn)	NULL
 #else
-#define FIB6_SUBTREE(fn)	((fn)->subtree)
+#define FIB6_SUBTREE(fn)	(rcu_dereference_protected((fn)->subtree, 1))
 #endif
 
 struct mx6_config {
@@ -98,6 +111,22 @@ struct rt6key {
 
 struct fib6_table;
 
+struct rt6_exception_bucket {
+	struct hlist_head	chain;
+	int			depth;
+};
+
+struct rt6_exception {
+	struct hlist_node	hlist;
+	struct rt6_info		*rt6i;
+	unsigned long		stamp;
+	struct rcu_head		rcu;
+};
+
+#define FIB6_EXCEPTION_BUCKET_SIZE_SHIFT 10
+#define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT)
+#define FIB6_MAX_DEPTH 5
+
 struct rt6_info {
 	struct dst_entry		dst;
 
@@ -134,14 +163,25 @@ struct rt6_info {
 
 	struct inet6_dev		*rt6i_idev;
 	struct rt6_info * __percpu	*rt6i_pcpu;
+	struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
 
 	u32				rt6i_metric;
 	u32				rt6i_pmtu;
 	/* more non-fragment space at head required */
 	unsigned short			rt6i_nfheader_len;
 	u8				rt6i_protocol;
+	u8				exception_bucket_flushed:1,
+					unused:7;
 };
 
+#define for_each_fib6_node_rt_rcu(fn)					\
+	for (rt = rcu_dereference((fn)->leaf); rt;			\
+	     rt = rcu_dereference(rt->dst.rt6_next))
+
+#define for_each_fib6_walker_rt(w)					\
+	for (rt = (w)->leaf; rt;					\
+	     rt = rcu_dereference_protected(rt->dst.rt6_next, 1))
+
 static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
 {
 	return ((struct rt6_info *)dst)->rt6i_idev;
@@ -188,6 +228,8 @@ static inline bool rt6_get_cookie_safe(const struct rt6_info *rt,
 
 	if (fn) {
 		*cookie = fn->fn_sernum;
+		/* pairs with smp_wmb() in fib6_update_sernum_upto_root() */
+		smp_rmb();
 		status = true;
 	}
 
@@ -248,7 +290,6 @@ struct fib6_walker {
 	struct fib6_node *root, *node;
 	struct rt6_info *leaf;
 	enum fib6_walk_state state;
-	bool prune;
 	unsigned int skip;
 	unsigned int count;
 	int (*func)(struct fib6_walker *);
@@ -256,12 +297,15 @@ struct fib6_walker {
 };
 
 struct rt6_statistics {
-	__u32		fib_nodes;
-	__u32		fib_route_nodes;
-	__u32		fib_rt_alloc;		/* permanent routes	*/
-	__u32		fib_rt_entries;		/* rt entries in table	*/
-	__u32		fib_rt_cache;		/* cache routes		*/
-	__u32		fib_discarded_routes;
+	__u32		fib_nodes;		/* all fib6 nodes */
+	__u32		fib_route_nodes;	/* intermediate nodes */
+	__u32		fib_rt_entries;		/* rt entries in fib table */
+	__u32		fib_rt_cache;		/* cached rt entries in exception table */
+	__u32		fib_discarded_routes;	/* total number of routes delete */
+
+	/* The following stats are not protected by any lock */
+	atomic_t	fib_rt_alloc;		/* total number of routes alloced */
+	atomic_t	fib_rt_uncache;		/* rt entries in uncached list */
 };
 
 #define RTN_TL_ROOT	0x0001
@@ -277,7 +321,7 @@ struct rt6_statistics {
 struct fib6_table {
 	struct hlist_node	tb6_hlist;
 	u32			tb6_id;
-	rwlock_t		tb6_lock;
+	spinlock_t		tb6_lock;
 	struct fib6_node	tb6_root;
 	struct inet_peer_base	tb6_peers;
 	unsigned int		flags;
@@ -325,7 +369,8 @@ struct fib6_node *fib6_lookup(struct fib6_node *root,
 
 struct fib6_node *fib6_locate(struct fib6_node *root,
 			      const struct in6_addr *daddr, int dst_len,
-			      const struct in6_addr *saddr, int src_len);
+			      const struct in6_addr *saddr, int src_len,
+			      bool exact_match);
 
 void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
 		    void *arg);
@@ -358,6 +403,8 @@ void __net_exit fib6_notifier_exit(struct net *net);
 unsigned int fib6_tables_seq_read(struct net *net);
 int fib6_tables_dump(struct net *net, struct notifier_block *nb);
 
+void fib6_update_sernum(struct rt6_info *rt);
+
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 int fib6_rules_init(void);
 void fib6_rules_cleanup(void);

include/net/ip6_route.h

@@ -95,6 +95,11 @@ int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack);
 int ip6_ins_rt(struct rt6_info *);
 int ip6_del_rt(struct rt6_info *);
 
+void rt6_flush_exceptions(struct rt6_info *rt);
+int rt6_remove_exception_rt(struct rt6_info *rt);
+void rt6_age_exceptions(struct rt6_info *rt, struct fib6_gc_args *gc_args,
+			unsigned long now);
+
 static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
 				      const struct in6_addr *daddr,
 				      unsigned int prefs,

net/ipv6/addrconf.c

@@ -2321,24 +2321,24 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 	if (!table)
 		return NULL;
 
-	read_lock_bh(&table->tb6_lock);
-	fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0);
+	rcu_read_lock();
+	fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0, true);
 	if (!fn)
 		goto out;
 
-	noflags |= RTF_CACHE;
-	for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
+	for_each_fib6_node_rt_rcu(fn) {
 		if (rt->dst.dev->ifindex != dev->ifindex)
 			continue;
 		if ((rt->rt6i_flags & flags) != flags)
 			continue;
 		if ((rt->rt6i_flags & noflags) != 0)
 			continue;
-		dst_hold(&rt->dst);
+		if (!dst_hold_safe(&rt->dst))
+			rt = NULL;
 		break;
 	}
 out:
-	read_unlock_bh(&table->tb6_lock);
+	rcu_read_unlock();
 	return rt;
 }
 
@@ -5898,10 +5898,9 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
 		spin_lock(&ifa->lock);
 		if (ifa->rt) {
 			struct rt6_info *rt = ifa->rt;
-			struct fib6_table *table = rt->rt6i_table;
 			int cpu;
 
-			read_lock(&table->tb6_lock);
+			rcu_read_lock();
 			addrconf_set_nopolicy(ifa->rt, val);
 			if (rt->rt6i_pcpu) {
 				for_each_possible_cpu(cpu) {
@@ -5911,7 +5910,7 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
 					addrconf_set_nopolicy(*rtp, val);
 				}
 			}
-			read_unlock(&table->tb6_lock);
+			rcu_read_unlock();
 		}
 		spin_unlock(&ifa->lock);
 	}

net/ipv6/ip6_fib.c

@@ -38,14 +38,6 @@
 #include <net/ip6_fib.h>
 #include <net/ip6_route.h>
 
-#define RT6_DEBUG 2
-
-#if RT6_DEBUG >= 3
-#define RT6_TRACE(x...) pr_debug(x)
-#else
-#define RT6_TRACE(x...) do { ; } while (0)
-#endif
-
 static struct kmem_cache *fib6_node_kmem __read_mostly;
 
 struct fib6_cleaner {
@@ -62,9 +54,12 @@ struct fib6_cleaner {
 #define FWS_INIT FWS_L
 #endif
 
-static void fib6_prune_clones(struct net *net, struct fib6_node *fn);
-static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn);
-static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn);
+static struct rt6_info *fib6_find_prefix(struct net *net,
+					 struct fib6_table *table,
+					 struct fib6_node *fn);
+static struct fib6_node *fib6_repair_tree(struct net *net,
+					  struct fib6_table *table,
+					  struct fib6_node *fn);
 static int fib6_walk(struct net *net, struct fib6_walker *w);
 static int fib6_walk_continue(struct fib6_walker *w);
 
@@ -110,6 +105,20 @@ enum {
 	FIB6_NO_SERNUM_CHANGE = 0,
 };
 
+void fib6_update_sernum(struct rt6_info *rt)
+{
+	struct fib6_table *table = rt->rt6i_table;
+	struct net *net = dev_net(rt->dst.dev);
+	struct fib6_node *fn;
+
+	spin_lock_bh(&table->tb6_lock);
+	fn = rcu_dereference_protected(rt->rt6i_node,
+			lockdep_is_held(&table->tb6_lock));
+	if (fn)
+		fn->fn_sernum = fib6_new_sernum(net);
+	spin_unlock_bh(&table->tb6_lock);
+}
+
 /*
  *	Auxiliary address test functions for the radix tree.
  *
@@ -140,18 +149,21 @@ static __be32 addr_bit_set(const void *token, int fn_bit)
 	       addr[fn_bit >> 5];
 }
 
-static struct fib6_node *node_alloc(void)
+static struct fib6_node *node_alloc(struct net *net)
 {
 	struct fib6_node *fn;
 
 	fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC);
+	if (fn)
+		net->ipv6.rt6_stats->fib_nodes++;
 
 	return fn;
 }
 
-static void node_free_immediate(struct fib6_node *fn)
+static void node_free_immediate(struct net *net, struct fib6_node *fn)
 {
 	kmem_cache_free(fib6_node_kmem, fn);
+	net->ipv6.rt6_stats->fib_nodes--;
 }
 
 static void node_free_rcu(struct rcu_head *head)
@@ -161,9 +173,10 @@ static void node_free_rcu(struct rcu_head *head)
 	kmem_cache_free(fib6_node_kmem, fn);
 }
 
-static void node_free(struct fib6_node *fn)
+static void node_free(struct net *net, struct fib6_node *fn)
 {
 	call_rcu(&fn->rcu, node_free_rcu);
+	net->ipv6.rt6_stats->fib_nodes--;
 }
 
 void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
@@ -185,9 +198,6 @@ void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
 			*ppcpu_rt = NULL;
 		}
 	}
-
-	free_percpu(non_pcpu_rt->rt6i_pcpu);
-	non_pcpu_rt->rt6i_pcpu = NULL;
 }
 EXPORT_SYMBOL_GPL(rt6_free_pcpu);
 
@@ -205,8 +215,7 @@ static void fib6_link_table(struct net *net, struct fib6_table *tb)
 	 * Initialize table lock at a single place to give lockdep a key,
 	 * tables aren't visible prior to being linked to the list.
 	 */
-	rwlock_init(&tb->tb6_lock);
-
+	spin_lock_init(&tb->tb6_lock);
 	h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1);
 
 	/*
@@ -225,7 +234,8 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
 	table = kzalloc(sizeof(*table), GFP_ATOMIC);
 	if (table) {
 		table->tb6_id = id;
-		table->tb6_root.leaf = net->ipv6.ip6_null_entry;
+		rcu_assign_pointer(table->tb6_root.leaf,
+				   net->ipv6.ip6_null_entry);
 		table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 		inet_peer_base_init(&table->tb6_peers);
 	}
@@ -322,11 +332,8 @@ unsigned int fib6_tables_seq_read(struct net *net)
 		struct hlist_head *head = &net->ipv6.fib_table_hash[h];
 		struct fib6_table *tb;
 
-		hlist_for_each_entry_rcu(tb, head, tb6_hlist) {
-			read_lock_bh(&tb->tb6_lock);
+		hlist_for_each_entry_rcu(tb, head, tb6_hlist)
 			fib_seq += tb->fib_seq;
-			read_unlock_bh(&tb->tb6_lock);
-		}
 	}
 	rcu_read_unlock();
 
@@ -372,7 +379,7 @@ static int fib6_node_dump(struct fib6_walker *w)
 {
 	struct rt6_info *rt;
 
-	for (rt = w->leaf; rt; rt = rt->dst.rt6_next)
+	for_each_fib6_walker_rt(w)
 		fib6_rt_dump(rt, w->args);
 	w->leaf = NULL;
 	return 0;
@@ -382,9 +389,9 @@ static void fib6_table_dump(struct net *net, struct fib6_table *tb,
 			    struct fib6_walker *w)
 {
 	w->root = &tb->tb6_root;
-	read_lock_bh(&tb->tb6_lock);
+	spin_lock_bh(&tb->tb6_lock);
 	fib6_walk(net, w);
-	read_unlock_bh(&tb->tb6_lock);
+	spin_unlock_bh(&tb->tb6_lock);
 }
 
 /* Called with rcu_read_lock() */
@@ -421,7 +428,7 @@ static int fib6_dump_node(struct fib6_walker *w)
 	int res;
 	struct rt6_info *rt;
 
-	for (rt = w->leaf; rt; rt = rt->dst.rt6_next) {
+	for_each_fib6_walker_rt(w) {
 		res = rt6_dump_route(rt, w->args);
 		if (res < 0) {
 			/* Frame is full, suspend walking */
@@ -480,9 +487,9 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb,
 		w->count = 0;
 		w->skip = 0;
 
-		read_lock_bh(&table->tb6_lock);
+		spin_lock_bh(&table->tb6_lock);
 		res = fib6_walk(net, w);
-		read_unlock_bh(&table->tb6_lock);
+		spin_unlock_bh(&table->tb6_lock);
 		if (res > 0) {
 			cb->args[4] = 1;
 			cb->args[5] = w->root->fn_sernum;
@@ -497,9 +504,9 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb,
 		} else
 			w->skip = 0;
 
-		read_lock_bh(&table->tb6_lock);
+		spin_lock_bh(&table->tb6_lock);
 		res = fib6_walk_continue(w);
-		read_unlock_bh(&table->tb6_lock);
+		spin_unlock_bh(&table->tb6_lock);
 		if (res <= 0) {
 			fib6_walker_unlink(net, w);
 			cb->args[4] = 0;
@@ -580,11 +587,13 @@ out:
  *	node.
  */
 
-static struct fib6_node *fib6_add_1(struct fib6_node *root,
-				     struct in6_addr *addr, int plen,
-				     int offset, int allow_create,
-				     int replace_required, int sernum,
-				     struct netlink_ext_ack *extack)
+static struct fib6_node *fib6_add_1(struct net *net,
+				    struct fib6_table *table,
+				    struct fib6_node *root,
+				    struct in6_addr *addr, int plen,
+				    int offset, int allow_create,
+				    int replace_required,
+				    struct netlink_ext_ack *extack)
 {
 	struct fib6_node *fn, *in, *ln;
 	struct fib6_node *pn = NULL;
@@ -599,7 +608,9 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
 	fn = root;
 
 	do {
-		key = (struct rt6key *)((u8 *)fn->leaf + offset);
+		struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
+					    lockdep_is_held(&table->tb6_lock));
+		key = (struct rt6key *)((u8 *)leaf + offset);
 
 		/*
 		 *	Prefix match
@@ -625,12 +636,10 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
 		if (plen == fn->fn_bit) {
 			/* clean up an intermediate node */
 			if (!(fn->fn_flags & RTN_RTINFO)) {
-				rt6_release(fn->leaf);
-				fn->leaf = NULL;
+				RCU_INIT_POINTER(fn->leaf, NULL);
+				rt6_release(leaf);
 			}
 
-			fn->fn_sernum = sernum;
-
 			return fn;
 		}
 
@@ -639,10 +648,13 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
 		 */
 
 		/* Try to walk down on tree. */
-		fn->fn_sernum = sernum;
 		dir = addr_bit_set(addr, fn->fn_bit);
 		pn = fn;
-		fn = dir ? fn->right : fn->left;
+		fn = dir ?
+		     rcu_dereference_protected(fn->right,
+					lockdep_is_held(&table->tb6_lock)) :
+		     rcu_dereference_protected(fn->left,
+					lockdep_is_held(&table->tb6_lock));
 	} while (fn);
 
 	if (!allow_create) {
@@ -668,19 +680,17 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
 	 *	Create new leaf node without children.
 	 */
 
-	ln = node_alloc();
+	ln = node_alloc(net);
 
 	if (!ln)
 		return ERR_PTR(-ENOMEM);
 	ln->fn_bit = plen;
-
-	ln->parent = pn;
-	ln->fn_sernum = sernum;
+	RCU_INIT_POINTER(ln->parent, pn);
 
 	if (dir)
-		pn->right = ln;
+		rcu_assign_pointer(pn->right, ln);
 	else
-		pn->left  = ln;
+		rcu_assign_pointer(pn->left, ln);
 
 	return ln;
 
@@ -694,7 +704,8 @@ insert_above:
 	 * and the current
 	 */
 
-	pn = fn->parent;
+	pn = rcu_dereference_protected(fn->parent,
+				       lockdep_is_held(&table->tb6_lock));
 
 	/* find 1st bit in difference between the 2 addrs.
 
@@ -710,14 +721,14 @@ insert_above:
 	 *	(new leaf node)[ln] (old node)[fn]
 	 */
 	if (plen > bit) {
-		in = node_alloc();
-		ln = node_alloc();
+		in = node_alloc(net);
+		ln = node_alloc(net);
 
 		if (!in || !ln) {
 			if (in)
-				node_free_immediate(in);
+				node_free_immediate(net, in);
 			if (ln)
-				node_free_immediate(ln);
+				node_free_immediate(net, ln);
 			return ERR_PTR(-ENOMEM);
 		}
 
@@ -731,31 +742,28 @@ insert_above:
 
 		in->fn_bit = bit;
 
-		in->parent = pn;
+		RCU_INIT_POINTER(in->parent, pn);
 		in->leaf = fn->leaf;
-		atomic_inc(&in->leaf->rt6i_ref);
-
-		in->fn_sernum = sernum;
+		atomic_inc(&rcu_dereference_protected(in->leaf,
+				lockdep_is_held(&table->tb6_lock))->rt6i_ref);
 
 		/* update parent pointer */
 		if (dir)
-			pn->right = in;
+			rcu_assign_pointer(pn->right, in);
 		else
-			pn->left  = in;
+			rcu_assign_pointer(pn->left, in);
 
 		ln->fn_bit = plen;
 
-		ln->parent = in;
-		fn->parent = in;
-
-		ln->fn_sernum = sernum;
+		RCU_INIT_POINTER(ln->parent, in);
+		rcu_assign_pointer(fn->parent, in);
 
 		if (addr_bit_set(addr, bit)) {
-			in->right = ln;
-			in->left  = fn;
+			rcu_assign_pointer(in->right, ln);
+			rcu_assign_pointer(in->left, fn);
 		} else {
-			in->left  = ln;
-			in->right = fn;
+			rcu_assign_pointer(in->left, ln);
+			rcu_assign_pointer(in->right, fn);
 		}
 	} else { /* plen <= bit */
 
@@ -765,28 +773,26 @@ insert_above:
 		 *	     (old node)[fn] NULL
 		 */
 
-		ln = node_alloc();
+		ln = node_alloc(net);
 
 		if (!ln)
 			return ERR_PTR(-ENOMEM);
 
 		ln->fn_bit = plen;
 
-		ln->parent = pn;
-
-		ln->fn_sernum = sernum;
-
-		if (dir)
-			pn->right = ln;
-		else
-			pn->left  = ln;
+		RCU_INIT_POINTER(ln->parent, pn);
 
 		if (addr_bit_set(&key->addr, plen))
-			ln->right = fn;
+			RCU_INIT_POINTER(ln->right, fn);
 		else
-			ln->left  = fn;
+			RCU_INIT_POINTER(ln->left, fn);
+
+		rcu_assign_pointer(fn->parent, ln);
 
-		fn->parent = ln;
+		if (dir)
+			rcu_assign_pointer(pn->right, ln);
+		else
+			rcu_assign_pointer(pn->left, ln);
 	}
 	return ln;
 }
@@ -832,6 +838,8 @@ static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc)
 static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
 			  struct net *net)
 {
+	struct fib6_table *table = rt->rt6i_table;
+
 	if (atomic_read(&rt->rt6i_ref) != 1) {
 		/* This route is used as dummy address holder in some split
 		 * nodes. It is not leaked, but it still holds other resources,
@@ -840,12 +848,17 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
 		 * to still alive ones.
 		 */
 		while (fn) {
-			if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
-				fn->leaf = fib6_find_prefix(net, fn);
-				atomic_inc(&fn->leaf->rt6i_ref);
+			struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
+					    lockdep_is_held(&table->tb6_lock));
+			struct rt6_info *new_leaf;
+			if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) {
+				new_leaf = fib6_find_prefix(net, table, fn);
+				atomic_inc(&new_leaf->rt6i_ref);
+				rcu_assign_pointer(fn->leaf, new_leaf);
 				rt6_release(rt);
 			}
-			fn = fn->parent;
+			fn = rcu_dereference_protected(fn->parent,
+				    lockdep_is_held(&table->tb6_lock));
 		}
 	}
 }
@@ -857,9 +870,11 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
 static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			    struct nl_info *info, struct mx6_config *mxc)
 {
+	struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
+				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 	struct rt6_info *iter = NULL;
-	struct rt6_info **ins;
-	struct rt6_info **fallback_ins = NULL;
+	struct rt6_info __rcu **ins;
+	struct rt6_info __rcu **fallback_ins = NULL;
 	int replace = (info->nlh &&
 		       (info->nlh->nlmsg_flags & NLM_F_REPLACE));
 	int add = (!info->nlh ||
@@ -874,7 +889,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 
 	ins = &fn->leaf;
 
-	for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) {
+	for (iter = leaf; iter;
+	     iter = rcu_dereference_protected(iter->dst.rt6_next,
+				lockdep_is_held(&rt->rt6i_table->tb6_lock))) {
 		/*
 		 *	Search for duplicates
 		 */
@@ -936,7 +953,8 @@ next_iter:
 	if (fallback_ins && !found) {
 		/* No ECMP-able route found, replace first non-ECMP one */
 		ins = fallback_ins;
-		iter = *ins;
+		iter = rcu_dereference_protected(*ins,
+				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 		found++;
 	}
 
@@ -950,7 +968,7 @@ next_iter:
 		struct rt6_info *sibling, *temp_sibling;
 
 		/* Find the first route that have the same metric */
-		sibling = fn->leaf;
+		sibling = leaf;
 		while (sibling) {
 			if (sibling->rt6i_metric == rt->rt6i_metric &&
 			    rt6_qualify_for_ecmp(sibling)) {
@@ -958,7 +976,8 @@ next_iter:
 					      &sibling->rt6i_siblings);
 				break;
 			}
-			sibling = sibling->dst.rt6_next;
+			sibling = rcu_dereference_protected(sibling->dst.rt6_next,
+				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 		}
 		/* For each sibling in the list, increment the counter of
 		 * siblings. BUG() if counters does not match, list of siblings
@@ -987,10 +1006,10 @@ add:
 		if (err)
 			return err;
 
-		rt->dst.rt6_next = iter;
-		*ins = rt;
-		rcu_assign_pointer(rt->rt6i_node, fn);
+		rcu_assign_pointer(rt->dst.rt6_next, iter);
 		atomic_inc(&rt->rt6i_ref);
+		rcu_assign_pointer(rt->rt6i_node, fn);
+		rcu_assign_pointer(*ins, rt);
 		call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_ADD,
 					  rt);
 		if (!info->skip_notify)
@@ -1016,10 +1035,10 @@ add:
 		if (err)
 			return err;
 
-		*ins = rt;
+		atomic_inc(&rt->rt6i_ref);
 		rcu_assign_pointer(rt->rt6i_node, fn);
 		rt->dst.rt6_next = iter->dst.rt6_next;
-		atomic_inc(&rt->rt6i_ref);
+		rcu_assign_pointer(*ins, rt);
 		call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE,
 					  rt);
 		if (!info->skip_notify)
@@ -1031,14 +1050,15 @@ add:
 		nsiblings = iter->rt6i_nsiblings;
 		iter->rt6i_node = NULL;
 		fib6_purge_rt(iter, fn, info->nl_net);
-		if (fn->rr_ptr == iter)
+		if (rcu_access_pointer(fn->rr_ptr) == iter)
 			fn->rr_ptr = NULL;
 		rt6_release(iter);
 
 		if (nsiblings) {
 			/* Replacing an ECMP route, remove all siblings */
 			ins = &rt->dst.rt6_next;
-			iter = *ins;
+			iter = rcu_dereference_protected(*ins,
+				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 			while (iter) {
 				if (iter->rt6i_metric > rt->rt6i_metric)
 					break;
@@ -1046,14 +1066,16 @@ add:
 					*ins = iter->dst.rt6_next;
 					iter->rt6i_node = NULL;
 					fib6_purge_rt(iter, fn, info->nl_net);
-					if (fn->rr_ptr == iter)
+					if (rcu_access_pointer(fn->rr_ptr) == iter)
 						fn->rr_ptr = NULL;
 					rt6_release(iter);
 					nsiblings--;
+					info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
 				} else {
 					ins = &iter->dst.rt6_next;
 				}
-				iter = *ins;
+				iter = rcu_dereference_protected(*ins,
+					lockdep_is_held(&rt->rt6i_table->tb6_lock));
 			}
 			WARN_ON(nsiblings != 0);
 		}
@@ -1077,16 +1099,33 @@ void fib6_force_start_gc(struct net *net)
 			  jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
 }
 
+static void fib6_update_sernum_upto_root(struct rt6_info *rt,
+					 int sernum)
+{
+	struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
+				lockdep_is_held(&rt->rt6i_table->tb6_lock));
+
+	/* paired with smp_rmb() in rt6_get_cookie_safe() */
+	smp_wmb();
+	while (fn) {
+		fn->fn_sernum = sernum;
+		fn = rcu_dereference_protected(fn->parent,
+				lockdep_is_held(&rt->rt6i_table->tb6_lock));
+	}
+}
+
 /*
  *	Add routing information to the routing tree.
  *	<destination addr>/<source addr>
  *	with source addr info in sub-trees
+ *	Need to own table->tb6_lock
  */
 
 int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 	     struct nl_info *info, struct mx6_config *mxc,
 	     struct netlink_ext_ack *extack)
 {
+	struct fib6_table *table = rt->rt6i_table;
 	struct fib6_node *fn, *pn = NULL;
 	int err = -ENOMEM;
 	int allow_create = 1;
@@ -1095,6 +1134,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 
 	if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt)))
 		return -EINVAL;
+	if (WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE))
+		return -EINVAL;
 
 	if (info->nlh) {
 		if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
@@ -1105,9 +1146,10 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 	if (!allow_create && !replace_required)
 		pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n");
 
-	fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen,
+	fn = fib6_add_1(info->nl_net, table, root,
+			&rt->rt6i_dst.addr, rt->rt6i_dst.plen,
 			offsetof(struct rt6_info, rt6i_dst), allow_create,
-			replace_required, sernum, extack);
+			replace_required, extack);
 	if (IS_ERR(fn)) {
 		err = PTR_ERR(fn);
 		fn = NULL;
@@ -1120,7 +1162,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 	if (rt->rt6i_src.plen) {
 		struct fib6_node *sn;
 
-		if (!fn->subtree) {
+		if (!rcu_access_pointer(fn->subtree)) {
 			struct fib6_node *sfn;
 
 			/*
@@ -1134,42 +1176,40 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			 */
 
 			/* Create subtree root node */
-			sfn = node_alloc();
+			sfn = node_alloc(info->nl_net);
 			if (!sfn)
 				goto failure;
 
-			sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
 			atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
+			rcu_assign_pointer(sfn->leaf,
+					   info->nl_net->ipv6.ip6_null_entry);
 			sfn->fn_flags = RTN_ROOT;
-			sfn->fn_sernum = sernum;
 
 			/* Now add the first leaf node to new subtree */
 
-			sn = fib6_add_1(sfn, &rt->rt6i_src.addr,
-					rt->rt6i_src.plen,
+			sn = fib6_add_1(info->nl_net, table, sfn,
+					&rt->rt6i_src.addr, rt->rt6i_src.plen,
 					offsetof(struct rt6_info, rt6i_src),
-					allow_create, replace_required, sernum,
-					extack);
+					allow_create, replace_required, extack);
 
 			if (IS_ERR(sn)) {
 				/* If it is failed, discard just allocated
 				   root, and then (in failure) stale node
 				   in main tree.
 				 */
-				node_free_immediate(sfn);
+				node_free_immediate(info->nl_net, sfn);
 				err = PTR_ERR(sn);
 				goto failure;
 			}
 
 			/* Now link new subtree to main tree */
-			sfn->parent = fn;
-			fn->subtree = sfn;
+			rcu_assign_pointer(sfn->parent, fn);
+			rcu_assign_pointer(fn->subtree, sfn);
 		} else {
-			sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr,
-					rt->rt6i_src.plen,
+			sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn),
+					&rt->rt6i_src.addr, rt->rt6i_src.plen,
 					offsetof(struct rt6_info, rt6i_src),
-					allow_create, replace_required, sernum,
-					extack);
+					allow_create, replace_required, extack);
 
 			if (IS_ERR(sn)) {
 				err = PTR_ERR(sn);
@@ -1177,9 +1217,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			}
 		}
 
-		if (!fn->leaf) {
-			fn->leaf = rt;
+		if (!rcu_access_pointer(fn->leaf)) {
 			atomic_inc(&rt->rt6i_ref);
+			rcu_assign_pointer(fn->leaf, rt);
 		}
 		fn = sn;
 	}
@@ -1187,9 +1227,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 
 	err = fib6_add_rt2node(fn, rt, info, mxc);
 	if (!err) {
+		fib6_update_sernum_upto_root(rt, sernum);
 		fib6_start_gc(info->nl_net, rt);
-		if (!(rt->rt6i_flags & RTF_CACHE))
-			fib6_prune_clones(info->nl_net, pn);
 	}
 
 out:
@@ -1199,19 +1238,23 @@ out:
 		 * If fib6_add_1 has cleared the old leaf pointer in the
 		 * super-tree leaf node we have to find a new one for it.
 		 */
-		if (pn != fn && pn->leaf == rt) {
-			pn->leaf = NULL;
+		struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf,
+					    lockdep_is_held(&table->tb6_lock));
+		if (pn != fn && pn_leaf == rt) {
+			pn_leaf = NULL;
+			RCU_INIT_POINTER(pn->leaf, NULL);
 			atomic_dec(&rt->rt6i_ref);
 		}
-		if (pn != fn && !pn->leaf && !(pn->fn_flags & RTN_RTINFO)) {
-			pn->leaf = fib6_find_prefix(info->nl_net, pn);
+		if (pn != fn && !pn_leaf && !(pn->fn_flags & RTN_RTINFO)) {
+			pn_leaf = fib6_find_prefix(info->nl_net, table, pn);
 #if RT6_DEBUG >= 2
-			if (!pn->leaf) {
-				WARN_ON(pn->leaf == NULL);
-				pn->leaf = info->nl_net->ipv6.ip6_null_entry;
+			if (!pn_leaf) {
+				WARN_ON(!pn_leaf);
+				pn_leaf = info->nl_net->ipv6.ip6_null_entry;
 			}
 #endif
-			atomic_inc(&pn->leaf->rt6i_ref);
+			atomic_inc(&pn_leaf->rt6i_ref);
+			rcu_assign_pointer(pn->leaf, pn_leaf);
 		}
 #endif
 		goto failure;
@@ -1226,7 +1269,7 @@ failure:
 	 * fn->leaf.
 	 */
 	if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)))
-		fib6_repair_tree(info->nl_net, fn);
+		fib6_repair_tree(info->nl_net, table, fn);
 	/* Always release dst as dst->__refcnt is guaranteed
 	 * to be taken before entering this function
 	 */
@@ -1264,7 +1307,8 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
 
 		dir = addr_bit_set(args->addr, fn->fn_bit);
 
-		next = dir ? fn->right : fn->left;
+		next = dir ? rcu_dereference(fn->right) :
+			     rcu_dereference(fn->left);
 
 		if (next) {
 			fn = next;
@@ -1274,18 +1318,22 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
 	}
 
 	while (fn) {
-		if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) {
+		struct fib6_node *subtree = FIB6_SUBTREE(fn);
+
+		if (subtree || fn->fn_flags & RTN_RTINFO) {
+			struct rt6_info *leaf = rcu_dereference(fn->leaf);
 			struct rt6key *key;
 
-			key = (struct rt6key *) ((u8 *) fn->leaf +
-						 args->offset);
+			if (!leaf)
+				goto backtrack;
+
+			key = (struct rt6key *) ((u8 *)leaf + args->offset);
 
 			if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) {
 #ifdef CONFIG_IPV6_SUBTREES
-				if (fn->subtree) {
+				if (subtree) {
 					struct fib6_node *sfn;
-					sfn = fib6_lookup_1(fn->subtree,
-							    args + 1);
+					sfn = fib6_lookup_1(subtree, args + 1);
 					if (!sfn)
 						goto backtrack;
 					fn = sfn;
@@ -1295,18 +1343,18 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
 					return fn;
 			}
 		}
-#ifdef CONFIG_IPV6_SUBTREES
 backtrack:
-#endif
 		if (fn->fn_flags & RTN_ROOT)
 			break;
 
-		fn = fn->parent;
+		fn = rcu_dereference(fn->parent);
 	}
 
 	return NULL;
 }
 
+/* called with rcu_read_lock() held
+ */
 struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr,
 			      const struct in6_addr *saddr)
 {
@@ -1337,54 +1385,84 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *dad
 /*
  *	Get node with specified destination prefix (and source prefix,
  *	if subtrees are used)
+ *	exact_match == true means we try to find fn with exact match of
+ *	the passed in prefix addr
+ *	exact_match == false means we try to find fn with longest prefix
+ *	match of the passed in prefix addr. This is useful for finding fn
+ *	for cached route as it will be stored in the exception table under
+ *	the node with longest prefix length.
  */
 
 
 static struct fib6_node *fib6_locate_1(struct fib6_node *root,
 				       const struct in6_addr *addr,
-				       int plen, int offset)
+				       int plen, int offset,
+				       bool exact_match)
 {
-	struct fib6_node *fn;
+	struct fib6_node *fn, *prev = NULL;
 
 	for (fn = root; fn ; ) {
-		struct rt6key *key = (struct rt6key *)((u8 *)fn->leaf + offset);
+		struct rt6_info *leaf = rcu_dereference(fn->leaf);
+		struct rt6key *key;
+
+		/* This node is being deleted */
+		if (!leaf) {
+			if (plen <= fn->fn_bit)
+				goto out;
+			else
+				goto next;
+		}
+
+		key = (struct rt6key *)((u8 *)leaf + offset);
 
 		/*
 		 *	Prefix match
 		 */
 		if (plen < fn->fn_bit ||
 		    !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit))
-			return NULL;
+			goto out;
 
 		if (plen == fn->fn_bit)
 			return fn;
 
+		prev = fn;
+
+next:
 		/*
 		 *	We have more bits to go
 		 */
 		if (addr_bit_set(addr, fn->fn_bit))
-			fn = fn->right;
+			fn = rcu_dereference(fn->right);
 		else
-			fn = fn->left;
+			fn = rcu_dereference(fn->left);
 	}
-	return NULL;
+out:
+	if (exact_match)
+		return NULL;
+	else
+		return prev;
 }
 
 struct fib6_node *fib6_locate(struct fib6_node *root,
 			      const struct in6_addr *daddr, int dst_len,
-			      const struct in6_addr *saddr, int src_len)
+			      const struct in6_addr *saddr, int src_len,
+			      bool exact_match)
 {
 	struct fib6_node *fn;
 
 	fn = fib6_locate_1(root, daddr, dst_len,
-			   offsetof(struct rt6_info, rt6i_dst));
+			   offsetof(struct rt6_info, rt6i_dst),
+			   exact_match);
 
 #ifdef CONFIG_IPV6_SUBTREES
 	if (src_len) {
+		struct fib6_node *subtree = FIB6_SUBTREE(fn);
+
 		WARN_ON(saddr == NULL);
-		if (fn && fn->subtree)
-			fn = fib6_locate_1(fn->subtree, saddr, src_len,
-					   offsetof(struct rt6_info, rt6i_src));
+		if (fn && subtree)
+			fn = fib6_locate_1(subtree, saddr, src_len,
+					   offsetof(struct rt6_info, rt6i_src),
+					   exact_match);
 	}
 #endif
 
@@ -1400,16 +1478,26 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
  *
  */
 
-static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn)
+static struct rt6_info *fib6_find_prefix(struct net *net,
+					 struct fib6_table *table,
+					 struct fib6_node *fn)
 {
+	struct fib6_node *child_left, *child_right;
+
 	if (fn->fn_flags & RTN_ROOT)
 		return net->ipv6.ip6_null_entry;
 
 	while (fn) {
-		if (fn->left)
-			return fn->left->leaf;
-		if (fn->right)
-			return fn->right->leaf;
+		child_left = rcu_dereference_protected(fn->left,
+				    lockdep_is_held(&table->tb6_lock));
+		child_right = rcu_dereference_protected(fn->right,
+				    lockdep_is_held(&table->tb6_lock));
+		if (child_left)
+			return rcu_dereference_protected(child_left->leaf,
+					lockdep_is_held(&table->tb6_lock));
+		if (child_right)
+			return rcu_dereference_protected(child_right->leaf,
+					lockdep_is_held(&table->tb6_lock));
 
 		fn = FIB6_SUBTREE(fn);
 	}
@@ -1419,31 +1507,49 @@ static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn)
 /*
  *	Called to trim the tree of intermediate nodes when possible. "fn"
  *	is the node we want to try and remove.
+ *	Need to own table->tb6_lock
  */
 
 static struct fib6_node *fib6_repair_tree(struct net *net,
-					   struct fib6_node *fn)
+					  struct fib6_table *table,
+					  struct fib6_node *fn)
 {
 	int children;
 	int nstate;
-	struct fib6_node *child, *pn;
+	struct fib6_node *child;
 	struct fib6_walker *w;
 	int iter = 0;
 
 	for (;;) {
+		struct fib6_node *fn_r = rcu_dereference_protected(fn->right,
+					    lockdep_is_held(&table->tb6_lock));
+		struct fib6_node *fn_l = rcu_dereference_protected(fn->left,
+					    lockdep_is_held(&table->tb6_lock));
+		struct fib6_node *pn = rcu_dereference_protected(fn->parent,
+					    lockdep_is_held(&table->tb6_lock));
+		struct fib6_node *pn_r = rcu_dereference_protected(pn->right,
+					    lockdep_is_held(&table->tb6_lock));
+		struct fib6_node *pn_l = rcu_dereference_protected(pn->left,
+					    lockdep_is_held(&table->tb6_lock));
+		struct rt6_info *fn_leaf = rcu_dereference_protected(fn->leaf,
+					    lockdep_is_held(&table->tb6_lock));
+		struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf,
+					    lockdep_is_held(&table->tb6_lock));
+		struct rt6_info *new_fn_leaf;
+
 		RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter);
 		iter++;
 
 		WARN_ON(fn->fn_flags & RTN_RTINFO);
 		WARN_ON(fn->fn_flags & RTN_TL_ROOT);
-		WARN_ON(fn->leaf);
+		WARN_ON(fn_leaf);
 
 		children = 0;
 		child = NULL;
-		if (fn->right)
-			child = fn->right, children |= 1;
-		if (fn->left)
-			child = fn->left, children |= 2;
+		if (fn_r)
+			child = fn_r, children |= 1;
+		if (fn_l)
+			child = fn_l, children |= 2;
 
 		if (children == 3 || FIB6_SUBTREE(fn)
 #ifdef CONFIG_IPV6_SUBTREES
@@ -1451,36 +1557,36 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 		    || (children && fn->fn_flags & RTN_ROOT)
 #endif
 		    ) {
-			fn->leaf = fib6_find_prefix(net, fn);
+			new_fn_leaf = fib6_find_prefix(net, table, fn);
 #if RT6_DEBUG >= 2
-			if (!fn->leaf) {
-				WARN_ON(!fn->leaf);
-				fn->leaf = net->ipv6.ip6_null_entry;
+			if (!new_fn_leaf) {
+				WARN_ON(!new_fn_leaf);
+				new_fn_leaf = net->ipv6.ip6_null_entry;
 			}
 #endif
-			atomic_inc(&fn->leaf->rt6i_ref);
-			return fn->parent;
+			atomic_inc(&new_fn_leaf->rt6i_ref);
+			rcu_assign_pointer(fn->leaf, new_fn_leaf);
+			return pn;
 		}
 
-		pn = fn->parent;
 #ifdef CONFIG_IPV6_SUBTREES
 		if (FIB6_SUBTREE(pn) == fn) {
 			WARN_ON(!(fn->fn_flags & RTN_ROOT));
-			FIB6_SUBTREE(pn) = NULL;
+			RCU_INIT_POINTER(pn->subtree, NULL);
 			nstate = FWS_L;
 		} else {
 			WARN_ON(fn->fn_flags & RTN_ROOT);
 #endif
-			if (pn->right == fn)
-				pn->right = child;
-			else if (pn->left == fn)
-				pn->left = child;
+			if (pn_r == fn)
+				rcu_assign_pointer(pn->right, child);
+			else if (pn_l == fn)
+				rcu_assign_pointer(pn->left, child);
 #if RT6_DEBUG >= 2
 			else
 				WARN_ON(1);
 #endif
 			if (child)
-				child->parent = pn;
+				rcu_assign_pointer(child->parent, pn);
 			nstate = FWS_R;
 #ifdef CONFIG_IPV6_SUBTREES
 		}
@@ -1489,19 +1595,12 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 		read_lock(&net->ipv6.fib6_walker_lock);
 		FOR_WALKERS(net, w) {
 			if (!child) {
-				if (w->root == fn) {
-					w->root = w->node = NULL;
-					RT6_TRACE("W %p adjusted by delroot 1\n", w);
-				} else if (w->node == fn) {
+				if (w->node == fn) {
 					RT6_TRACE("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate);
 					w->node = pn;
 					w->state = nstate;
 				}
 			} else {
-				if (w->root == fn) {
-					w->root = child;
-					RT6_TRACE("W %p adjusted by delroot 2\n", w);
-				}
 				if (w->node == fn) {
 					w->node = child;
 					if (children&2) {
@@ -1516,33 +1615,39 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 		}
 		read_unlock(&net->ipv6.fib6_walker_lock);
 
-		node_free(fn);
+		node_free(net, fn);
 		if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn))
 			return pn;
 
-		rt6_release(pn->leaf);
-		pn->leaf = NULL;
+		RCU_INIT_POINTER(pn->leaf, NULL);
+		rt6_release(pn_leaf);
 		fn = pn;
 	}
 }
 
-static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
-			   struct nl_info *info)
+static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
+			   struct rt6_info __rcu **rtp, struct nl_info *info)
 {
 	struct fib6_walker *w;
-	struct rt6_info *rt = *rtp;
+	struct rt6_info *rt = rcu_dereference_protected(*rtp,
+				    lockdep_is_held(&table->tb6_lock));
 	struct net *net = info->nl_net;
 
 	RT6_TRACE("fib6_del_route\n");
 
+	WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE);
+
 	/* Unlink it */
 	*rtp = rt->dst.rt6_next;
 	rt->rt6i_node = NULL;
 	net->ipv6.rt6_stats->fib_rt_entries--;
 	net->ipv6.rt6_stats->fib_discarded_routes++;
 
+	/* Flush all cached dst in exception table */
+	rt6_flush_exceptions(rt);
+
 	/* Reset round-robin state, if necessary */
-	if (fn->rr_ptr == rt)
+	if (rcu_access_pointer(fn->rr_ptr) == rt)
 		fn->rr_ptr = NULL;
 
 	/* Remove this entry from other siblings */
@@ -1561,20 +1666,19 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 	FOR_WALKERS(net, w) {
 		if (w->state == FWS_C && w->leaf == rt) {
 			RT6_TRACE("walker %p adjusted by delroute\n", w);
-			w->leaf = rt->dst.rt6_next;
+			w->leaf = rcu_dereference_protected(rt->dst.rt6_next,
+					    lockdep_is_held(&table->tb6_lock));
 			if (!w->leaf)
 				w->state = FWS_U;
 		}
 	}
 	read_unlock(&net->ipv6.fib6_walker_lock);
 
-	rt->dst.rt6_next = NULL;
-
 	/* If it was last route, expunge its radix tree node */
-	if (!fn->leaf) {
+	if (!rcu_access_pointer(fn->leaf)) {
 		fn->fn_flags &= ~RTN_RTINFO;
 		net->ipv6.rt6_stats->fib_route_nodes--;
-		fn = fib6_repair_tree(net, fn);
+		fn = fib6_repair_tree(net, table, fn);
 	}
 
 	fib6_purge_rt(rt, fn, net);
@@ -1585,12 +1689,15 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 	rt6_release(rt);
 }
 
+/* Need to own table->tb6_lock */
 int fib6_del(struct rt6_info *rt, struct nl_info *info)
 {
 	struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
 				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
+	struct fib6_table *table = rt->rt6i_table;
 	struct net *net = info->nl_net;
-	struct rt6_info **rtp;
+	struct rt6_info __rcu **rtp;
+	struct rt6_info __rcu **rtp_next;
 
 #if RT6_DEBUG >= 2
 	if (rt->dst.obsolete > 0) {
@@ -1603,28 +1710,22 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
 
 	WARN_ON(!(fn->fn_flags & RTN_RTINFO));
 
-	if (!(rt->rt6i_flags & RTF_CACHE)) {
-		struct fib6_node *pn = fn;
-#ifdef CONFIG_IPV6_SUBTREES
-		/* clones of this route might be in another subtree */
-		if (rt->rt6i_src.plen) {
-			while (!(pn->fn_flags & RTN_ROOT))
-				pn = pn->parent;
-			pn = pn->parent;
-		}
-#endif
-		fib6_prune_clones(info->nl_net, pn);
-	}
+	/* remove cached dst from exception table */
+	if (rt->rt6i_flags & RTF_CACHE)
+		return rt6_remove_exception_rt(rt);
 
 	/*
 	 *	Walk the leaf entries looking for ourself
 	 */
 
-	for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->dst.rt6_next) {
-		if (*rtp == rt) {
-			fib6_del_route(fn, rtp, info);
+	for (rtp = &fn->leaf; *rtp; rtp = rtp_next) {
+		struct rt6_info *cur = rcu_dereference_protected(*rtp,
+					lockdep_is_held(&table->tb6_lock));
+		if (rt == cur) {
+			fib6_del_route(table, fn, rtp, info);
 			return 0;
 		}
+		rtp_next = &cur->dst.rt6_next;
 	}
 	return -ENOENT;
 }
@@ -1651,22 +1752,22 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
  *	0   -> walk is complete.
  *	>0  -> walk is incomplete (i.e. suspended)
  *	<0  -> walk is terminated by an error.
+ *
+ *	This function is called with tb6_lock held.
  */
 
 static int fib6_walk_continue(struct fib6_walker *w)
 {
-	struct fib6_node *fn, *pn;
+	struct fib6_node *fn, *pn, *left, *right;
+
+	/* w->root should always be table->tb6_root */
+	WARN_ON_ONCE(!(w->root->fn_flags & RTN_TL_ROOT));
 
 	for (;;) {
 		fn = w->node;
 		if (!fn)
 			return 0;
 
-		if (w->prune && fn != w->root &&
-		    fn->fn_flags & RTN_RTINFO && w->state < FWS_C) {
-			w->state = FWS_C;
-			w->leaf = fn->leaf;
-		}
 		switch (w->state) {
 #ifdef CONFIG_IPV6_SUBTREES
 		case FWS_S:
@@ -1677,20 +1778,22 @@ static int fib6_walk_continue(struct fib6_walker *w)
 			w->state = FWS_L;
 #endif
 		case FWS_L:
-			if (fn->left) {
-				w->node = fn->left;
+			left = rcu_dereference_protected(fn->left, 1);
+			if (left) {
+				w->node = left;
 				w->state = FWS_INIT;
 				continue;
 			}
 			w->state = FWS_R;
 		case FWS_R:
-			if (fn->right) {
-				w->node = fn->right;
+			right = rcu_dereference_protected(fn->right, 1);
+			if (right) {
+				w->node = right;
 				w->state = FWS_INIT;
 				continue;
 			}
 			w->state = FWS_C;
-			w->leaf = fn->leaf;
+			w->leaf = rcu_dereference_protected(fn->leaf, 1);
 		case FWS_C:
 			if (w->leaf && fn->fn_flags & RTN_RTINFO) {
 				int err;
@@ -1712,7 +1815,9 @@ skip:
 		case FWS_U:
 			if (fn == w->root)
 				return 0;
-			pn = fn->parent;
+			pn = rcu_dereference_protected(fn->parent, 1);
+			left = rcu_dereference_protected(pn->left, 1);
+			right = rcu_dereference_protected(pn->right, 1);
 			w->node = pn;
 #ifdef CONFIG_IPV6_SUBTREES
 			if (FIB6_SUBTREE(pn) == fn) {
@@ -1721,13 +1826,13 @@ skip:
 				continue;
 			}
 #endif
-			if (pn->left == fn) {
+			if (left == fn) {
 				w->state = FWS_R;
 				continue;
 			}
-			if (pn->right == fn) {
+			if (right == fn) {
 				w->state = FWS_C;
-				w->leaf = w->node->leaf;
+				w->leaf = rcu_dereference_protected(w->node->leaf, 1);
 				continue;
 			}
 #if RT6_DEBUG >= 2
@@ -1770,7 +1875,7 @@ static int fib6_clean_node(struct fib6_walker *w)
 		return 0;
 	}
 
-	for (rt = w->leaf; rt; rt = rt->dst.rt6_next) {
+	for_each_fib6_walker_rt(w) {
 		res = c->func(rt, c->arg);
 		if (res < 0) {
 			w->leaf = rt;
@@ -1798,20 +1903,16 @@ static int fib6_clean_node(struct fib6_walker *w)
  *	func is called on each route.
  *		It may return -1 -> delete this route.
  *		              0  -> continue walking
- *
- *	prune==1 -> only immediate children of node (certainly,
- *	ignoring pure split nodes) will be scanned.
  */
 
 static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 			    int (*func)(struct rt6_info *, void *arg),
-			    bool prune, int sernum, void *arg)
+			    int sernum, void *arg)
 {
 	struct fib6_cleaner c;
 
 	c.w.root = root;
 	c.w.func = fib6_clean_node;
-	c.w.prune = prune;
 	c.w.count = 0;
 	c.w.skip = 0;
 	c.func = func;
@@ -1834,10 +1935,10 @@ static void __fib6_clean_all(struct net *net,
 	for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
 		head = &net->ipv6.fib_table_hash[h];
 		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
-			write_lock_bh(&table->tb6_lock);
+			spin_lock_bh(&table->tb6_lock);
 			fib6_clean_tree(net, &table->tb6_root,
-					func, false, sernum, arg);
-			write_unlock_bh(&table->tb6_lock);
+					func, sernum, arg);
+			spin_unlock_bh(&table->tb6_lock);
 		}
 	}
 	rcu_read_unlock();
@@ -1849,22 +1950,6 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *),
 	__fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg);
 }
 
-static int fib6_prune_clone(struct rt6_info *rt, void *arg)
-{
-	if (rt->rt6i_flags & RTF_CACHE) {
-		RT6_TRACE("pruning clone %p\n", rt);
-		return -1;
-	}
-
-	return 0;
-}
-
-static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
-{
-	fib6_clean_tree(net, fn, fib6_prune_clone, true,
-			FIB6_NO_SERNUM_CHANGE, NULL);
-}
-
 static void fib6_flush_trees(struct net *net)
 {
 	int new_sernum = fib6_new_sernum(net);
@@ -1876,12 +1961,6 @@ static void fib6_flush_trees(struct net *net)
  *	Garbage collection
  */
 
-struct fib6_gc_args
-{
-	int			timeout;
-	int			more;
-};
-
 static int fib6_age(struct rt6_info *rt, void *arg)
 {
 	struct fib6_gc_args *gc_args = arg;
@@ -1890,9 +1969,6 @@ static int fib6_age(struct rt6_info *rt, void *arg)
 	/*
 	 *	check addrconf expiration here.
 	 *	Routes are expired even if they are in use.
-	 *
-	 *	Also age clones. Note, that clones are aged out
-	 *	only if they are not in use now.
 	 */
 
 	if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) {
@@ -1901,31 +1977,14 @@ static int fib6_age(struct rt6_info *rt, void *arg)
 			return -1;
 		}
 		gc_args->more++;
-	} else if (rt->rt6i_flags & RTF_CACHE) {
-		if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout))
-			rt->dst.obsolete = DST_OBSOLETE_KILL;
-		if (atomic_read(&rt->dst.__refcnt) == 1 &&
-		    rt->dst.obsolete == DST_OBSOLETE_KILL) {
-			RT6_TRACE("aging clone %p\n", rt);
-			return -1;
-		} else if (rt->rt6i_flags & RTF_GATEWAY) {
-			struct neighbour *neigh;
-			__u8 neigh_flags = 0;
-
-			neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway);
-			if (neigh) {
-				neigh_flags = neigh->flags;
-				neigh_release(neigh);
-			}
-			if (!(neigh_flags & NTF_ROUTER)) {
-				RT6_TRACE("purging route %p via non-router but gateway\n",
-					  rt);
-				return -1;
-			}
-		}
-		gc_args->more++;
 	}
 
+	/*	Also age clones in the exception table.
+	 *	Note, that clones are aged out
+	 *	only if they are not in use now.
+	 */
+	rt6_age_exceptions(rt, gc_args, now);
+
 	return 0;
 }
 
@@ -1993,7 +2052,8 @@ static int __net_init fib6_net_init(struct net *net)
 		goto out_fib_table_hash;
 
 	net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN;
-	net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry;
+	rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf,
+			   net->ipv6.ip6_null_entry);
 	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);
@@ -2004,7 +2064,8 @@ static int __net_init fib6_net_init(struct net *net)
 	if (!net->ipv6.fib6_local_tbl)
 		goto out_fib6_main_tbl;
 	net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL;
-	net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry;
+	rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf,
+			   net->ipv6.ip6_null_entry);
 	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);
@@ -2134,7 +2195,9 @@ static int ipv6_route_yield(struct fib6_walker *w)
 		return 1;
 
 	do {
-		iter->w.leaf = iter->w.leaf->dst.rt6_next;
+		iter->w.leaf = rcu_dereference_protected(
+				iter->w.leaf->dst.rt6_next,
+				lockdep_is_held(&iter->tbl->tb6_lock));
 		iter->skip--;
 		if (!iter->skip && iter->w.leaf)
 			return 1;
@@ -2199,7 +2262,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	if (!v)
 		goto iter_table;
 
-	n = ((struct rt6_info *)v)->dst.rt6_next;
+	n = rcu_dereference(((struct rt6_info *)v)->dst.rt6_next);
 	if (n) {
 		++*pos;
 		return n;
@@ -2207,9 +2270,9 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 iter_table:
 	ipv6_route_check_sernum(iter);
-	read_lock(&iter->tbl->tb6_lock);
+	spin_lock_bh(&iter->tbl->tb6_lock);
 	r = fib6_walk_continue(&iter->w);
-	read_unlock(&iter->tbl->tb6_lock);
+	spin_unlock_bh(&iter->tbl->tb6_lock);
 	if (r > 0) {
 		if (v)
 			++*pos;

net/ipv6/route.c

@@ -44,6 +44,7 @@
 #include <linux/seq_file.h>
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
+#include <linux/jhash.h>
 #include <net/net_namespace.h>
 #include <net/snmp.h>
 #include <net/ipv6.h>
@@ -104,6 +105,9 @@ static int rt6_fill_node(struct net *net,
 			 struct in6_addr *dst, struct in6_addr *src,
 			 int iif, int type, u32 portid, u32 seq,
 			 unsigned int flags);
+static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
+					   struct in6_addr *daddr,
+					   struct in6_addr *saddr);
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct rt6_info *rt6_add_route_info(struct net *net,
@@ -139,9 +143,11 @@ static void rt6_uncached_list_del(struct rt6_info *rt)
 {
 	if (!list_empty(&rt->rt6i_uncached)) {
 		struct uncached_list *ul = rt->rt6i_uncached_list;
+		struct net *net = dev_net(rt->dst.dev);
 
 		spin_lock_bh(&ul->lock);
 		list_del(&rt->rt6i_uncached);
+		atomic_dec(&net->ipv6.rt6_stats->fib_rt_uncache);
 		spin_unlock_bh(&ul->lock);
 	}
 }
@@ -355,8 +361,10 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net,
 	struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
 					1, DST_OBSOLETE_FORCE_CHK, flags);
 
-	if (rt)
+	if (rt) {
 		rt6_info_init(rt);
+		atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc);
+	}
 
 	return rt;
 }
@@ -392,6 +400,7 @@ EXPORT_SYMBOL(ip6_dst_alloc);
 static void ip6_dst_destroy(struct dst_entry *dst)
 {
 	struct rt6_info *rt = (struct rt6_info *)dst;
+	struct rt6_exception_bucket *bucket;
 	struct dst_entry *from = dst->from;
 	struct inet6_dev *idev;
 
@@ -404,6 +413,11 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 		rt->rt6i_idev = NULL;
 		in6_dev_put(idev);
 	}
+	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, 1);
+	if (bucket) {
+		rt->rt6i_exception_bucket = NULL;
+		kfree(bucket);
+	}
 
 	dst->from = NULL;
 	dst_release(from);
@@ -478,7 +492,7 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
 }
 
 /*
- *	Route lookup. Any table->tb6_lock is implied.
+ *	Route lookup. rcu_read_lock() should be held.
  */
 
 static inline struct rt6_info *rt6_device_match(struct net *net,
@@ -493,7 +507,7 @@ static inline struct rt6_info *rt6_device_match(struct net *net,
 	if (!oif && ipv6_addr_any(saddr))
 		goto out;
 
-	for (sprt = rt; sprt; sprt = sprt->dst.rt6_next) {
+	for (sprt = rt; sprt; sprt = rcu_dereference(sprt->dst.rt6_next)) {
 		struct net_device *dev = sprt->dst.dev;
 
 		if (oif) {
@@ -702,6 +716,7 @@ out:
 }
 
 static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
+				     struct rt6_info *leaf,
 				     struct rt6_info *rr_head,
 				     u32 metric, int oif, int strict,
 				     bool *do_rr)
@@ -711,7 +726,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
 
 	match = NULL;
 	cont = NULL;
-	for (rt = rr_head; rt; rt = rt->dst.rt6_next) {
+	for (rt = rr_head; rt; rt = rcu_dereference(rt->dst.rt6_next)) {
 		if (rt->rt6i_metric != metric) {
 			cont = rt;
 			break;
@@ -720,7 +735,8 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
 		match = find_match(rt, oif, strict, &mpri, match, do_rr);
 	}
 
-	for (rt = fn->leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) {
+	for (rt = leaf; rt && rt != rr_head;
+	     rt = rcu_dereference(rt->dst.rt6_next)) {
 		if (rt->rt6i_metric != metric) {
 			cont = rt;
 			break;
@@ -732,37 +748,59 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
 	if (match || !cont)
 		return match;
 
-	for (rt = cont; rt; rt = rt->dst.rt6_next)
+	for (rt = cont; rt; rt = rcu_dereference(rt->dst.rt6_next))
 		match = find_match(rt, oif, strict, &mpri, match, do_rr);
 
 	return match;
 }
 
-static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
+static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
+				   int oif, int strict)
 {
+	struct rt6_info *leaf = rcu_dereference(fn->leaf);
 	struct rt6_info *match, *rt0;
-	struct net *net;
 	bool do_rr = false;
+	int key_plen;
+
+	if (!leaf)
+		return net->ipv6.ip6_null_entry;
 
-	rt0 = fn->rr_ptr;
+	rt0 = rcu_dereference(fn->rr_ptr);
 	if (!rt0)
-		fn->rr_ptr = rt0 = fn->leaf;
+		rt0 = leaf;
 
-	match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict,
+	/* Double check to make sure fn is not an intermediate node
+	 * and fn->leaf does not points to its child's leaf
+	 * (This might happen if all routes under fn are deleted from
+	 * the tree and fib6_repair_tree() is called on the node.)
+	 */
+	key_plen = rt0->rt6i_dst.plen;
+#ifdef CONFIG_IPV6_SUBTREES
+	if (rt0->rt6i_src.plen)
+		key_plen = rt0->rt6i_src.plen;
+#endif
+	if (fn->fn_bit != key_plen)
+		return net->ipv6.ip6_null_entry;
+
+	match = find_rr_leaf(fn, leaf, rt0, rt0->rt6i_metric, oif, strict,
 			     &do_rr);
 
 	if (do_rr) {
-		struct rt6_info *next = rt0->dst.rt6_next;
+		struct rt6_info *next = rcu_dereference(rt0->dst.rt6_next);
 
 		/* no entries matched; do round-robin */
 		if (!next || next->rt6i_metric != rt0->rt6i_metric)
-			next = fn->leaf;
-
-		if (next != rt0)
-			fn->rr_ptr = next;
+			next = leaf;
+
+		if (next != rt0) {
+			spin_lock_bh(&leaf->rt6i_table->tb6_lock);
+			/* make sure next is not being deleted from the tree */
+			if (next->rt6i_node)
+				rcu_assign_pointer(fn->rr_ptr, next);
+			spin_unlock_bh(&leaf->rt6i_table->tb6_lock);
+		}
 	}
 
-	net = dev_net(rt0->dst.dev);
 	return match ? match : net->ipv6.ip6_null_entry;
 }
 
@@ -850,13 +888,14 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
 					struct in6_addr *saddr)
 {
-	struct fib6_node *pn;
+	struct fib6_node *pn, *sn;
 	while (1) {
 		if (fn->fn_flags & RTN_TL_ROOT)
 			return NULL;
-		pn = fn->parent;
-		if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn)
-			fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr);
+		pn = rcu_dereference(fn->parent);
+		sn = FIB6_SUBTREE(pn);
+		if (sn && sn != fn)
+			fn = fib6_lookup(sn, NULL, saddr);
 		else
 			fn = pn;
 		if (fn->fn_flags & RTN_RTINFO)
@@ -864,27 +903,57 @@ static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
 	}
 }
 
+static bool ip6_hold_safe(struct net *net, struct rt6_info **prt,
+			  bool null_fallback)
+{
+	struct rt6_info *rt = *prt;
+
+	if (dst_hold_safe(&rt->dst))
+		return true;
+	if (null_fallback) {
+		rt = net->ipv6.ip6_null_entry;
+		dst_hold(&rt->dst);
+	} else {
+		rt = NULL;
+	}
+	*prt = rt;
+	return false;
+}
+
 static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 					     struct fib6_table *table,
 					     struct flowi6 *fl6, int flags)
 {
+	struct rt6_info *rt, *rt_cache;
 	struct fib6_node *fn;
-	struct rt6_info *rt;
 
-	read_lock_bh(&table->tb6_lock);
+	rcu_read_lock();
 	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
-	rt = fn->leaf;
-	rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags);
-	if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
-		rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif, flags);
+	rt = rcu_dereference(fn->leaf);
+	if (!rt) {
+		rt = net->ipv6.ip6_null_entry;
+	} else {
+		rt = rt6_device_match(net, rt, &fl6->saddr,
+				      fl6->flowi6_oif, flags);
+		if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
+			rt = rt6_multipath_select(rt, fl6,
+						  fl6->flowi6_oif, flags);
+	}
 	if (rt == net->ipv6.ip6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
 			goto restart;
 	}
-	dst_use(&rt->dst, jiffies);
-	read_unlock_bh(&table->tb6_lock);
+	/* Search through exception table */
+	rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr);
+	if (rt_cache)
+		rt = rt_cache;
+
+	if (ip6_hold_safe(net, &rt, true))
+		dst_use_noref(&rt->dst, jiffies);
+
+	rcu_read_unlock();
 
 	trace_fib6_table_lookup(net, rt, table->tb6_id, fl6);
 
@@ -938,9 +1007,9 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
 	struct fib6_table *table;
 
 	table = rt->rt6i_table;
-	write_lock_bh(&table->tb6_lock);
+	spin_lock_bh(&table->tb6_lock);
 	err = fib6_add(&table->tb6_root, rt, info, mxc, extack);
-	write_unlock_bh(&table->tb6_lock);
+	spin_unlock_bh(&table->tb6_lock);
 
 	return err;
 }
@@ -1038,7 +1107,7 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt)
 	return pcpu_rt;
 }
 
-/* It should be called with read_lock_bh(&tb6_lock) acquired */
+/* It should be called with rcu_read_lock() acquired */
 static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
 {
 	struct rt6_info *pcpu_rt, **p;
@@ -1046,16 +1115,14 @@ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
 	p = this_cpu_ptr(rt->rt6i_pcpu);
 	pcpu_rt = *p;
 
-	if (pcpu_rt) {
-		dst_hold(&pcpu_rt->dst);
+	if (pcpu_rt && ip6_hold_safe(NULL, &pcpu_rt, false))
 		rt6_dst_from_metrics_check(pcpu_rt);
-	}
+
 	return pcpu_rt;
 }
 
 static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt)
 {
-	struct fib6_table *table = rt->rt6i_table;
 	struct rt6_info *pcpu_rt, *prev, **p;
 
 	pcpu_rt = ip6_rt_pcpu_alloc(rt);
@@ -1066,36 +1133,520 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt)
 		return net->ipv6.ip6_null_entry;
 	}
 
-	read_lock_bh(&table->tb6_lock);
-	if (rt->rt6i_pcpu) {
-		p = this_cpu_ptr(rt->rt6i_pcpu);
-		prev = cmpxchg(p, NULL, pcpu_rt);
-		if (prev) {
-			/* If someone did it before us, return prev instead */
-			dst_release_immediate(&pcpu_rt->dst);
-			pcpu_rt = prev;
-		}
-	} else {
-		/* rt has been removed from the fib6 tree
-		 * before we have a chance to acquire the read_lock.
-		 * In this case, don't brother to create a pcpu rt
-		 * since rt is going away anyway.  The next
-		 * dst_check() will trigger a re-lookup.
-		 */
+	dst_hold(&pcpu_rt->dst);
+	p = this_cpu_ptr(rt->rt6i_pcpu);
+	prev = cmpxchg(p, NULL, pcpu_rt);
+	if (prev) {
+		/* If someone did it before us, return prev instead */
+		/* release refcnt taken by ip6_rt_pcpu_alloc() */
+		dst_release_immediate(&pcpu_rt->dst);
+		/* release refcnt taken by above dst_hold() */
 		dst_release_immediate(&pcpu_rt->dst);
-		pcpu_rt = rt;
+		dst_hold(&prev->dst);
+		pcpu_rt = prev;
 	}
-	dst_hold(&pcpu_rt->dst);
+
 	rt6_dst_from_metrics_check(pcpu_rt);
-	read_unlock_bh(&table->tb6_lock);
 	return pcpu_rt;
 }
 
+/* exception hash table implementation
+ */
+static DEFINE_SPINLOCK(rt6_exception_lock);
+
+/* Remove rt6_ex from hash table and free the memory
+ * Caller must hold rt6_exception_lock
+ */
+static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
+				 struct rt6_exception *rt6_ex)
+{
+	struct net *net = dev_net(rt6_ex->rt6i->dst.dev);
+
+	if (!bucket || !rt6_ex)
+		return;
+	rt6_ex->rt6i->rt6i_node = NULL;
+	hlist_del_rcu(&rt6_ex->hlist);
+	rt6_release(rt6_ex->rt6i);
+	kfree_rcu(rt6_ex, rcu);
+	WARN_ON_ONCE(!bucket->depth);
+	bucket->depth--;
+	net->ipv6.rt6_stats->fib_rt_cache--;
+}
+
+/* Remove oldest rt6_ex in bucket and free the memory
+ * Caller must hold rt6_exception_lock
+ */
+static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket)
+{
+	struct rt6_exception *rt6_ex, *oldest = NULL;
+
+	if (!bucket)
+		return;
+
+	hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
+		if (!oldest || time_before(rt6_ex->stamp, oldest->stamp))
+			oldest = rt6_ex;
+	}
+	rt6_remove_exception(bucket, oldest);
+}
+
+static u32 rt6_exception_hash(const struct in6_addr *dst,
+			      const struct in6_addr *src)
+{
+	static u32 seed __read_mostly;
+	u32 val;
+
+	net_get_random_once(&seed, sizeof(seed));
+	val = jhash(dst, sizeof(*dst), seed);
+
+#ifdef CONFIG_IPV6_SUBTREES
+	if (src)
+		val = jhash(src, sizeof(*src), val);
+#endif
+	return hash_32(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT);
+}
+
+/* Helper function to find the cached rt in the hash table
+ * and update bucket pointer to point to the bucket for this
+ * (daddr, saddr) pair
+ * Caller must hold rt6_exception_lock
+ */
+static struct rt6_exception *
+__rt6_find_exception_spinlock(struct rt6_exception_bucket **bucket,
+			      const struct in6_addr *daddr,
+			      const struct in6_addr *saddr)
+{
+	struct rt6_exception *rt6_ex;
+	u32 hval;
+
+	if (!(*bucket) || !daddr)
+		return NULL;
+
+	hval = rt6_exception_hash(daddr, saddr);
+	*bucket += hval;
+
+	hlist_for_each_entry(rt6_ex, &(*bucket)->chain, hlist) {
+		struct rt6_info *rt6 = rt6_ex->rt6i;
+		bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr);
+
+#ifdef CONFIG_IPV6_SUBTREES
+		if (matched && saddr)
+			matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr);
+#endif
+		if (matched)
+			return rt6_ex;
+	}
+	return NULL;
+}
+
+/* Helper function to find the cached rt in the hash table
+ * and update bucket pointer to point to the bucket for this
+ * (daddr, saddr) pair
+ * Caller must hold rcu_read_lock()
+ */
+static struct rt6_exception *
+__rt6_find_exception_rcu(struct rt6_exception_bucket **bucket,
+			 const struct in6_addr *daddr,
+			 const struct in6_addr *saddr)
+{
+	struct rt6_exception *rt6_ex;
+	u32 hval;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	if (!(*bucket) || !daddr)
+		return NULL;
+
+	hval = rt6_exception_hash(daddr, saddr);
+	*bucket += hval;
+
+	hlist_for_each_entry_rcu(rt6_ex, &(*bucket)->chain, hlist) {
+		struct rt6_info *rt6 = rt6_ex->rt6i;
+		bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr);
+
+#ifdef CONFIG_IPV6_SUBTREES
+		if (matched && saddr)
+			matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr);
+#endif
+		if (matched)
+			return rt6_ex;
+	}
+	return NULL;
+}
+
+static int rt6_insert_exception(struct rt6_info *nrt,
+				struct rt6_info *ort)
+{
+	struct net *net = dev_net(ort->dst.dev);
+	struct rt6_exception_bucket *bucket;
+	struct in6_addr *src_key = NULL;
+	struct rt6_exception *rt6_ex;
+	int err = 0;
+
+	/* ort can't be a cache or pcpu route */
+	if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
+		ort = (struct rt6_info *)ort->dst.from;
+	WARN_ON_ONCE(ort->rt6i_flags & (RTF_CACHE | RTF_PCPU));
+
+	spin_lock_bh(&rt6_exception_lock);
+
+	if (ort->exception_bucket_flushed) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	bucket = rcu_dereference_protected(ort->rt6i_exception_bucket,
+					lockdep_is_held(&rt6_exception_lock));
+	if (!bucket) {
+		bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket),
+				 GFP_ATOMIC);
+		if (!bucket) {
+			err = -ENOMEM;
+			goto out;
+		}
+		rcu_assign_pointer(ort->rt6i_exception_bucket, bucket);
+	}
+
+#ifdef CONFIG_IPV6_SUBTREES
+	/* rt6i_src.plen != 0 indicates ort is in subtree
+	 * and exception table is indexed by a hash of
+	 * both rt6i_dst and rt6i_src.
+	 * Otherwise, the exception table is indexed by
+	 * a hash of only rt6i_dst.
+	 */
+	if (ort->rt6i_src.plen)
+		src_key = &nrt->rt6i_src.addr;
+#endif
+
+	/* Update rt6i_prefsrc as it could be changed
+	 * in rt6_remove_prefsrc()
+	 */
+	nrt->rt6i_prefsrc = ort->rt6i_prefsrc;
+	/* rt6_mtu_change() might lower mtu on ort.
+	 * Only insert this exception route if its mtu
+	 * is less than ort's mtu value.
+	 */
+	if (nrt->rt6i_pmtu >= dst_mtu(&ort->dst)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr,
+					       src_key);
+	if (rt6_ex)
+		rt6_remove_exception(bucket, rt6_ex);
+
+	rt6_ex = kzalloc(sizeof(*rt6_ex), GFP_ATOMIC);
+	if (!rt6_ex) {
+		err = -ENOMEM;
+		goto out;
+	}
+	rt6_ex->rt6i = nrt;
+	rt6_ex->stamp = jiffies;
+	atomic_inc(&nrt->rt6i_ref);
+	nrt->rt6i_node = ort->rt6i_node;
+	hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain);
+	bucket->depth++;
+	net->ipv6.rt6_stats->fib_rt_cache++;
+
+	if (bucket->depth > FIB6_MAX_DEPTH)
+		rt6_exception_remove_oldest(bucket);
+
+out:
+	spin_unlock_bh(&rt6_exception_lock);
+
+	/* Update fn->fn_sernum to invalidate all cached dst */
+	if (!err)
+		fib6_update_sernum(ort);
+
+	return err;
+}
+
+void rt6_flush_exceptions(struct rt6_info *rt)
+{
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+	struct hlist_node *tmp;
+	int i;
+
+	spin_lock_bh(&rt6_exception_lock);
+	/* Prevent rt6_insert_exception() to recreate the bucket list */
+	rt->exception_bucket_flushed = 1;
+
+	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
+				    lockdep_is_held(&rt6_exception_lock));
+	if (!bucket)
+		goto out;
+
+	for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+		hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist)
+			rt6_remove_exception(bucket, rt6_ex);
+		WARN_ON_ONCE(bucket->depth);
+		bucket++;
+	}
+
+out:
+	spin_unlock_bh(&rt6_exception_lock);
+}
+
+/* Find cached rt in the hash table inside passed in rt
+ * Caller has to hold rcu_read_lock()
+ */
+static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
+					   struct in6_addr *daddr,
+					   struct in6_addr *saddr)
+{
+	struct rt6_exception_bucket *bucket;
+	struct in6_addr *src_key = NULL;
+	struct rt6_exception *rt6_ex;
+	struct rt6_info *res = NULL;
+
+	bucket = rcu_dereference(rt->rt6i_exception_bucket);
+
+#ifdef CONFIG_IPV6_SUBTREES
+	/* rt6i_src.plen != 0 indicates rt is in subtree
+	 * and exception table is indexed by a hash of
+	 * both rt6i_dst and rt6i_src.
+	 * Otherwise, the exception table is indexed by
+	 * a hash of only rt6i_dst.
+	 */
+	if (rt->rt6i_src.plen)
+		src_key = saddr;
+#endif
+	rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
+
+	if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
+		res = rt6_ex->rt6i;
+
+	return res;
+}
+
+/* Remove the passed in cached rt from the hash table that contains it */
+int rt6_remove_exception_rt(struct rt6_info *rt)
+{
+	struct rt6_info *from = (struct rt6_info *)rt->dst.from;
+	struct rt6_exception_bucket *bucket;
+	struct in6_addr *src_key = NULL;
+	struct rt6_exception *rt6_ex;
+	int err;
+
+	if (!from ||
+	    !(rt->rt6i_flags | RTF_CACHE))
+		return -EINVAL;
+
+	if (!rcu_access_pointer(from->rt6i_exception_bucket))
+		return -ENOENT;
+
+	spin_lock_bh(&rt6_exception_lock);
+	bucket = rcu_dereference_protected(from->rt6i_exception_bucket,
+				    lockdep_is_held(&rt6_exception_lock));
+#ifdef CONFIG_IPV6_SUBTREES
+	/* rt6i_src.plen != 0 indicates 'from' is in subtree
+	 * and exception table is indexed by a hash of
+	 * both rt6i_dst and rt6i_src.
+	 * Otherwise, the exception table is indexed by
+	 * a hash of only rt6i_dst.
+	 */
+	if (from->rt6i_src.plen)
+		src_key = &rt->rt6i_src.addr;
+#endif
+	rt6_ex = __rt6_find_exception_spinlock(&bucket,
+					       &rt->rt6i_dst.addr,
+					       src_key);
+	if (rt6_ex) {
+		rt6_remove_exception(bucket, rt6_ex);
+		err = 0;
+	} else {
+		err = -ENOENT;
+	}
+
+	spin_unlock_bh(&rt6_exception_lock);
+	return err;
+}
+
+/* Find rt6_ex which contains the passed in rt cache and
+ * refresh its stamp
+ */
+static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
+{
+	struct rt6_info *from = (struct rt6_info *)rt->dst.from;
+	struct rt6_exception_bucket *bucket;
+	struct in6_addr *src_key = NULL;
+	struct rt6_exception *rt6_ex;
+
+	if (!from ||
+	    !(rt->rt6i_flags | RTF_CACHE))
+		return;
+
+	rcu_read_lock();
+	bucket = rcu_dereference(from->rt6i_exception_bucket);
+
+#ifdef CONFIG_IPV6_SUBTREES
+	/* rt6i_src.plen != 0 indicates 'from' is in subtree
+	 * and exception table is indexed by a hash of
+	 * both rt6i_dst and rt6i_src.
+	 * Otherwise, the exception table is indexed by
+	 * a hash of only rt6i_dst.
+	 */
+	if (from->rt6i_src.plen)
+		src_key = &rt->rt6i_src.addr;
+#endif
+	rt6_ex = __rt6_find_exception_rcu(&bucket,
+					  &rt->rt6i_dst.addr,
+					  src_key);
+	if (rt6_ex)
+		rt6_ex->stamp = jiffies;
+
+	rcu_read_unlock();
+}
+
+static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt)
+{
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+	int i;
+
+	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) {
+				rt6_ex->rt6i->rt6i_prefsrc.plen = 0;
+			}
+			bucket++;
+		}
+	}
+}
+
+static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu)
+{
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+	int i;
+
+	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++;
+		}
+	}
+}
+
+#define RTF_CACHE_GATEWAY	(RTF_GATEWAY | RTF_CACHE)
+
+static void rt6_exceptions_clean_tohost(struct rt6_info *rt,
+					struct in6_addr *gateway)
+{
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+	struct hlist_node *tmp;
+	int i;
+
+	if (!rcu_access_pointer(rt->rt6i_exception_bucket))
+		return;
+
+	spin_lock_bh(&rt6_exception_lock);
+	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_safe(rt6_ex, tmp,
+						  &bucket->chain, hlist) {
+				struct rt6_info *entry = rt6_ex->rt6i;
+
+				if ((entry->rt6i_flags & RTF_CACHE_GATEWAY) ==
+				    RTF_CACHE_GATEWAY &&
+				    ipv6_addr_equal(gateway,
+						    &entry->rt6i_gateway)) {
+					rt6_remove_exception(bucket, rt6_ex);
+				}
+			}
+			bucket++;
+		}
+	}
+
+	spin_unlock_bh(&rt6_exception_lock);
+}
+
+static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
+				      struct rt6_exception *rt6_ex,
+				      struct fib6_gc_args *gc_args,
+				      unsigned long now)
+{
+	struct rt6_info *rt = rt6_ex->rt6i;
+
+	if (atomic_read(&rt->dst.__refcnt) == 1 &&
+	    time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) {
+		RT6_TRACE("aging clone %p\n", rt);
+		rt6_remove_exception(bucket, rt6_ex);
+		return;
+	} else if (rt->rt6i_flags & RTF_GATEWAY) {
+		struct neighbour *neigh;
+		__u8 neigh_flags = 0;
+
+		neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway);
+		if (neigh) {
+			neigh_flags = neigh->flags;
+			neigh_release(neigh);
+		}
+		if (!(neigh_flags & NTF_ROUTER)) {
+			RT6_TRACE("purging route %p via non-router but gateway\n",
+				  rt);
+			rt6_remove_exception(bucket, rt6_ex);
+			return;
+		}
+	}
+	gc_args->more++;
+}
+
+void rt6_age_exceptions(struct rt6_info *rt,
+			struct fib6_gc_args *gc_args,
+			unsigned long now)
+{
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+	struct hlist_node *tmp;
+	int i;
+
+	if (!rcu_access_pointer(rt->rt6i_exception_bucket))
+		return;
+
+	spin_lock_bh(&rt6_exception_lock);
+	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_safe(rt6_ex, tmp,
+						  &bucket->chain, hlist) {
+				rt6_age_examine_exception(bucket, rt6_ex,
+							  gc_args, now);
+			}
+			bucket++;
+		}
+	}
+	spin_unlock_bh(&rt6_exception_lock);
+}
+
 struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 			       int oif, struct flowi6 *fl6, int flags)
 {
 	struct fib6_node *fn, *saved_fn;
-	struct rt6_info *rt;
+	struct rt6_info *rt, *rt_cache;
 	int strict = 0;
 
 	strict |= flags & RT6_LOOKUP_F_IFACE;
@@ -1103,7 +1654,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 	if (net->ipv6.devconf_all->forwarding == 0)
 		strict |= RT6_LOOKUP_F_REACHABLE;
 
-	read_lock_bh(&table->tb6_lock);
+	rcu_read_lock();
 
 	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 	saved_fn = fn;
@@ -1112,7 +1663,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 		oif = 0;
 
 redo_rt6_select:
-	rt = rt6_select(fn, oif, strict);
+	rt = rt6_select(net, fn, oif, strict);
 	if (rt->rt6i_nsiblings)
 		rt = rt6_multipath_select(rt, fl6, oif, strict);
 	if (rt == net->ipv6.ip6_null_entry) {
@@ -1127,13 +1678,22 @@ redo_rt6_select:
 		}
 	}
 
+	/*Search through exception table */
+	rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr);
+	if (rt_cache)
+		rt = rt_cache;
 
-	if (rt == net->ipv6.ip6_null_entry || (rt->rt6i_flags & RTF_CACHE)) {
-		dst_use(&rt->dst, jiffies);
-		read_unlock_bh(&table->tb6_lock);
-
-		rt6_dst_from_metrics_check(rt);
-
+	if (rt == net->ipv6.ip6_null_entry) {
+		rcu_read_unlock();
+		dst_hold(&rt->dst);
+		trace_fib6_table_lookup(net, rt, table->tb6_id, fl6);
+		return rt;
+	} else if (rt->rt6i_flags & RTF_CACHE) {
+		if (ip6_hold_safe(net, &rt, true)) {
+			dst_use_noref(&rt->dst, jiffies);
+			rt6_dst_from_metrics_check(rt);
+		}
+		rcu_read_unlock();
 		trace_fib6_table_lookup(net, rt, table->tb6_id, fl6);
 		return rt;
 	} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
@@ -1146,8 +1706,14 @@ redo_rt6_select:
 
 		struct rt6_info *uncached_rt;
 
-		dst_use(&rt->dst, jiffies);
-		read_unlock_bh(&table->tb6_lock);
+		if (ip6_hold_safe(net, &rt, true)) {
+			dst_use_noref(&rt->dst, jiffies);
+		} else {
+			rcu_read_unlock();
+			uncached_rt = rt;
+			goto uncached_rt_out;
+		}
+		rcu_read_unlock();
 
 		uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL);
 		dst_release(&rt->dst);
@@ -1157,11 +1723,13 @@ redo_rt6_select:
 			 * No need for another dst_hold()
 			 */
 			rt6_uncached_list_add(uncached_rt);
+			atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache);
 		} else {
 			uncached_rt = net->ipv6.ip6_null_entry;
 			dst_hold(&uncached_rt->dst);
 		}
 
+uncached_rt_out:
 		trace_fib6_table_lookup(net, uncached_rt, table->tb6_id, fl6);
 		return uncached_rt;
 
@@ -1170,26 +1738,34 @@ redo_rt6_select:
 
 		struct rt6_info *pcpu_rt;
 
-		rt->dst.lastuse = jiffies;
-		rt->dst.__use++;
+		dst_use_noref(&rt->dst, jiffies);
 		pcpu_rt = rt6_get_pcpu_route(rt);
 
 		if (pcpu_rt) {
-			read_unlock_bh(&table->tb6_lock);
+			rcu_read_unlock();
 		} else {
-			/* We have to do the read_unlock first
-			 * because rt6_make_pcpu_route() may trigger
-			 * ip6_dst_gc() which will take the write_lock.
-			 */
-			dst_hold(&rt->dst);
-			read_unlock_bh(&table->tb6_lock);
-			pcpu_rt = rt6_make_pcpu_route(rt);
-			dst_release(&rt->dst);
+			/* atomic_inc_not_zero() is needed when using rcu */
+			if (atomic_inc_not_zero(&rt->rt6i_ref)) {
+				/* We have to do the read_unlock first
+				 * because rt6_make_pcpu_route() may trigger
+				 * ip6_dst_gc() which will take the write_lock.
+				 *
+				 * No dst_hold() on rt is needed because grabbing
+				 * rt->rt6i_ref makes sure rt can't be released.
+				 */
+				rcu_read_unlock();
+				pcpu_rt = rt6_make_pcpu_route(rt);
+				rt6_release(rt);
+			} else {
+				/* rt is already removed from tree */
+				rcu_read_unlock();
+				pcpu_rt = net->ipv6.ip6_null_entry;
+				dst_hold(&pcpu_rt->dst);
+			}
 		}
 
 		trace_fib6_table_lookup(net, pcpu_rt, table->tb6_id, fl6);
 		return pcpu_rt;
-
 	}
 }
 EXPORT_SYMBOL_GPL(ip6_pol_route);
@@ -1328,6 +1904,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 		       DST_OBSOLETE_NONE, 0);
 	if (rt) {
 		rt6_info_init(rt);
+		atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc);
 
 		new = &rt->dst;
 		new->__use = 1;
@@ -1491,23 +2068,17 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 
 	if (!rt6_cache_allowed_for_pmtu(rt6)) {
 		rt6_do_update_pmtu(rt6, mtu);
+		/* update rt6_ex->stamp for cache */
+		if (rt6->rt6i_flags & RTF_CACHE)
+			rt6_update_exception_stamp_rt(rt6);
 	} else if (daddr) {
 		struct rt6_info *nrt6;
 
 		nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr);
 		if (nrt6) {
 			rt6_do_update_pmtu(nrt6, mtu);
-
-			/* ip6_ins_rt(nrt6) will bump the
-			 * rt6->rt6i_node->fn_sernum
-			 * which will fail the next rt6_check() and
-			 * invalidate the sk->sk_dst_cache.
-			 */
-			ip6_ins_rt(nrt6);
-			/* Release the reference taken in
-			 * ip6_rt_cache_alloc()
-			 */
-			dst_release(&nrt6->dst);
+			if (rt6_insert_exception(nrt6, rt6))
+				dst_release_immediate(&nrt6->dst);
 		}
 	}
 }
@@ -1571,7 +2142,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 					     int flags)
 {
 	struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
-	struct rt6_info *rt;
+	struct rt6_info *rt, *rt_cache;
 	struct fib6_node *fn;
 
 	/* Get the "current" route for this destination and
@@ -1584,10 +2155,10 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 	 * routes.
 	 */
 
-	read_lock_bh(&table->tb6_lock);
+	rcu_read_lock();
 	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
-	for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
+	for_each_fib6_node_rt_rcu(fn) {
 		if (rt6_check_expired(rt))
 			continue;
 		if (rt->dst.error)
@@ -1596,8 +2167,23 @@ restart:
 			continue;
 		if (fl6->flowi6_oif != rt->dst.dev->ifindex)
 			continue;
-		if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway))
+		/* rt_cache's gateway might be different from its 'parent'
+		 * in the case of an ip redirect.
+		 * So we keep searching in the exception table if the gateway
+		 * is different.
+		 */
+		if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) {
+			rt_cache = rt6_find_cached_rt(rt,
+						      &fl6->daddr,
+						      &fl6->saddr);
+			if (rt_cache &&
+			    ipv6_addr_equal(&rdfl->gateway,
+					    &rt_cache->rt6i_gateway)) {
+				rt = rt_cache;
+				break;
+			}
 			continue;
+		}
 		break;
 	}
 
@@ -1615,9 +2201,9 @@ restart:
 	}
 
 out:
-	dst_hold(&rt->dst);
+	ip6_hold_safe(net, &rt, true);
 
-	read_unlock_bh(&table->tb6_lock);
+	rcu_read_unlock();
 
 	trace_fib6_table_lookup(net, rt, table->tb6_id, fl6);
 	return rt;
@@ -1766,6 +2352,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 	 * do proper release of the net_device
 	 */
 	rt6_uncached_list_add(rt);
+	atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache);
 
 	dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0);
 
@@ -2216,9 +2803,9 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
 	}
 
 	table = rt->rt6i_table;
-	write_lock_bh(&table->tb6_lock);
+	spin_lock_bh(&table->tb6_lock);
 	err = fib6_del(rt, info);
-	write_unlock_bh(&table->tb6_lock);
+	spin_unlock_bh(&table->tb6_lock);
 
 out:
 	ip6_rt_put(rt);
@@ -2244,7 +2831,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
 	if (rt == net->ipv6.ip6_null_entry)
 		goto out_put;
 	table = rt->rt6i_table;
-	write_lock_bh(&table->tb6_lock);
+	spin_lock_bh(&table->tb6_lock);
 
 	if (rt->rt6i_nsiblings && cfg->fc_delete_all_nh) {
 		struct rt6_info *sibling, *next_sibling;
@@ -2274,7 +2861,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
 
 	err = fib6_del(rt, info);
 out_unlock:
-	write_unlock_bh(&table->tb6_lock);
+	spin_unlock_bh(&table->tb6_lock);
 out_put:
 	ip6_rt_put(rt);
 
@@ -2288,9 +2875,9 @@ out_put:
 static int ip6_route_del(struct fib6_config *cfg,
 			 struct netlink_ext_ack *extack)
 {
+	struct rt6_info *rt, *rt_cache;
 	struct fib6_table *table;
 	struct fib6_node *fn;
-	struct rt6_info *rt;
 	int err = -ESRCH;
 
 	table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table);
@@ -2299,17 +2886,22 @@ static int ip6_route_del(struct fib6_config *cfg,
 		return err;
 	}
 
-	read_lock_bh(&table->tb6_lock);
+	rcu_read_lock();
 
 	fn = fib6_locate(&table->tb6_root,
 			 &cfg->fc_dst, cfg->fc_dst_len,
-			 &cfg->fc_src, cfg->fc_src_len);
+			 &cfg->fc_src, cfg->fc_src_len,
+			 !(cfg->fc_flags & RTF_CACHE));
 
 	if (fn) {
-		for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
-			if ((rt->rt6i_flags & RTF_CACHE) &&
-			    !(cfg->fc_flags & RTF_CACHE))
-				continue;
+		for_each_fib6_node_rt_rcu(fn) {
+			if (cfg->fc_flags & RTF_CACHE) {
+				rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst,
+							      &cfg->fc_src);
+				if (!rt_cache)
+					continue;
+				rt = rt_cache;
+			}
 			if (cfg->fc_ifindex &&
 			    (!rt->dst.dev ||
 			     rt->dst.dev->ifindex != cfg->fc_ifindex))
@@ -2321,8 +2913,9 @@ static int ip6_route_del(struct fib6_config *cfg,
 				continue;
 			if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol)
 				continue;
-			dst_hold(&rt->dst);
-			read_unlock_bh(&table->tb6_lock);
+			if (!dst_hold_safe(&rt->dst))
+				break;
+			rcu_read_unlock();
 
 			/* if gateway was specified only delete the one hop */
 			if (cfg->fc_flags & RTF_GATEWAY)
@@ -2331,7 +2924,7 @@ static int ip6_route_del(struct fib6_config *cfg,
 			return __ip6_del_rt_siblings(rt, cfg);
 		}
 	}
-	read_unlock_bh(&table->tb6_lock);
+	rcu_read_unlock();
 
 	return err;
 }
@@ -2435,8 +3028,14 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	nrt->rt6i_protocol = RTPROT_REDIRECT;
 	nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
 
-	if (ip6_ins_rt(nrt))
-		goto out_release;
+	/* No need to remove rt from the exception table if rt is
+	 * a cached route because rt6_insert_exception() will
+	 * takes care of it
+	 */
+	if (rt6_insert_exception(nrt, rt)) {
+		dst_release_immediate(&nrt->dst);
+		goto out;
+	}
 
 	netevent.old = &rt->dst;
 	netevent.new = &nrt->dst;
@@ -2444,17 +3043,6 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	netevent.neigh = neigh;
 	call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
 
-	if (rt->rt6i_flags & RTF_CACHE) {
-		rt = (struct rt6_info *) dst_clone(&rt->dst);
-		ip6_del_rt(rt);
-	}
-
-out_release:
-	/* Release the reference taken in
-	 * ip6_rt_cache_alloc()
-	 */
-	dst_release(&nrt->dst);
-
 out:
 	neigh_release(neigh);
 }
@@ -2511,23 +3099,23 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
 	if (!table)
 		return NULL;
 
-	read_lock_bh(&table->tb6_lock);
-	fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0);
+	rcu_read_lock();
+	fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0, true);
 	if (!fn)
 		goto out;
 
-	for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
+	for_each_fib6_node_rt_rcu(fn) {
 		if (rt->dst.dev->ifindex != ifindex)
 			continue;
 		if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
 			continue;
 		if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr))
 			continue;
-		dst_hold(&rt->dst);
+		ip6_hold_safe(NULL, &rt, false);
 		break;
 	}
 out:
-	read_unlock_bh(&table->tb6_lock);
+	rcu_read_unlock();
 	return rt;
 }
 
@@ -2573,16 +3161,16 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev
 	if (!table)
 		return NULL;
 
-	read_lock_bh(&table->tb6_lock);
-	for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
+	rcu_read_lock();
+	for_each_fib6_node_rt_rcu(&table->tb6_root) {
 		if (dev == rt->dst.dev &&
 		    ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
 		    ipv6_addr_equal(&rt->rt6i_gateway, addr))
 			break;
 	}
 	if (rt)
-		dst_hold(&rt->dst);
-	read_unlock_bh(&table->tb6_lock);
+		ip6_hold_safe(NULL, &rt, false);
+	rcu_read_unlock();
 	return rt;
 }
 
@@ -2620,17 +3208,20 @@ static void __rt6_purge_dflt_routers(struct fib6_table *table)
 	struct rt6_info *rt;
 
 restart:
-	read_lock_bh(&table->tb6_lock);
-	for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
+	rcu_read_lock();
+	for_each_fib6_node_rt_rcu(&table->tb6_root) {
 		if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
 		    (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) {
-			dst_hold(&rt->dst);
-			read_unlock_bh(&table->tb6_lock);
-			ip6_del_rt(rt);
+			if (dst_hold_safe(&rt->dst)) {
+				rcu_read_unlock();
+				ip6_del_rt(rt);
+			} else {
+				rcu_read_unlock();
+			}
 			goto restart;
 		}
 	}
-	read_unlock_bh(&table->tb6_lock);
+	rcu_read_unlock();
 
 	table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER;
 }
@@ -2818,8 +3409,12 @@ static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg)
 	if (((void *)rt->dst.dev == dev || !dev) &&
 	    rt != net->ipv6.ip6_null_entry &&
 	    ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) {
+		spin_lock_bh(&rt6_exception_lock);
 		/* remove prefsrc entry */
 		rt->rt6i_prefsrc.plen = 0;
+		/* need to update cache as well */
+		rt6_exceptions_remove_prefsrc(rt);
+		spin_unlock_bh(&rt6_exception_lock);
 	}
 	return 0;
 }
@@ -2836,18 +3431,23 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
 }
 
 #define RTF_RA_ROUTER		(RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)
-#define RTF_CACHE_GATEWAY	(RTF_GATEWAY | RTF_CACHE)
 
 /* Remove routers and update dst entries when gateway turn into host. */
 static int fib6_clean_tohost(struct rt6_info *rt, void *arg)
 {
 	struct in6_addr *gateway = (struct in6_addr *)arg;
 
-	if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) ||
-	     ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) &&
-	     ipv6_addr_equal(gateway, &rt->rt6i_gateway)) {
+	if (((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) &&
+	    ipv6_addr_equal(gateway, &rt->rt6i_gateway)) {
 		return -1;
 	}
+
+	/* Further clean up cached routes in exception table.
+	 * This is needed because cached route may have a different
+	 * gateway than its 'parent' in the case of an ip redirect.
+	 */
+	rt6_exceptions_clean_tohost(rt, gateway);
+
 	return 0;
 }
 
@@ -2926,19 +3526,14 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
 	if (rt->dst.dev == arg->dev &&
 	    dst_metric_raw(&rt->dst, RTAX_MTU) &&
 	    !dst_metric_locked(&rt->dst, RTAX_MTU)) {
-		if (rt->rt6i_flags & RTF_CACHE) {
-			/* For RTF_CACHE with rt6i_pmtu == 0
-			 * (i.e. a redirected route),
-			 * the metrics of its rt->dst.from has already
-			 * been updated.
-			 */
-			if (rt->rt6i_pmtu && rt->rt6i_pmtu > arg->mtu)
-				rt->rt6i_pmtu = arg->mtu;
-		} else if (dst_mtu(&rt->dst) >= arg->mtu ||
-			   (dst_mtu(&rt->dst) < arg->mtu &&
-			    dst_mtu(&rt->dst) == idev->cnf.mtu6)) {
+		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)) {
 			dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
 		}
+		rt6_exceptions_update_pmtu(rt, arg->mtu);
+		spin_unlock_bh(&rt6_exception_lock);
 	}
 	return 0;
 }
@@ -3839,7 +4434,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v)
 	seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n",
 		   net->ipv6.rt6_stats->fib_nodes,
 		   net->ipv6.rt6_stats->fib_route_nodes,
-		   net->ipv6.rt6_stats->fib_rt_alloc,
+		   atomic_read(&net->ipv6.rt6_stats->fib_rt_alloc),
 		   net->ipv6.rt6_stats->fib_rt_entries,
 		   net->ipv6.rt6_stats->fib_rt_cache,
 		   dst_entries_get_slow(&net->ipv6.ip6_dst_ops),