Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 119a427..f2d1e57 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * xfrm_policy.c
  *
@@ -26,10 +27,15 @@
 #include <linux/cache.h>
 #include <linux/cpu.h>
 #include <linux/audit.h>
+#include <linux/rhashtable.h>
+#include <linux/if_tunnel.h>
 #include <net/dst.h>
 #include <net/flow.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+#include <net/mip6.h>
+#endif
 #ifdef CONFIG_XFRM_STATISTICS
 #include <net/snmp.h>
 #endif
@@ -45,6 +51,99 @@
 	u8 flags;
 };
 
+/* prefixes smaller than this are stored in lists, not trees. */
+#define INEXACT_PREFIXLEN_IPV4	16
+#define INEXACT_PREFIXLEN_IPV6	48
+
+struct xfrm_pol_inexact_node {
+	struct rb_node node;
+	union {
+		xfrm_address_t addr;
+		struct rcu_head rcu;
+	};
+	u8 prefixlen;
+
+	struct rb_root root;
+
+	/* the policies matching this node, can be empty list */
+	struct hlist_head hhead;
+};
+
+/* xfrm inexact policy search tree:
+ * xfrm_pol_inexact_bin = hash(dir,type,family,if_id);
+ *  |
+ * +---- root_d: sorted by daddr:prefix
+ * |                 |
+ * |        xfrm_pol_inexact_node
+ * |                 |
+ * |                 +- root: sorted by saddr/prefix
+ * |                 |              |
+ * |                 |         xfrm_pol_inexact_node
+ * |                 |              |
+ * |                 |              + root: unused
+ * |                 |              |
+ * |                 |              + hhead: saddr:daddr policies
+ * |                 |
+ * |                 +- coarse policies and all any:daddr policies
+ * |
+ * +---- root_s: sorted by saddr:prefix
+ * |                 |
+ * |        xfrm_pol_inexact_node
+ * |                 |
+ * |                 + root: unused
+ * |                 |
+ * |                 + hhead: saddr:any policies
+ * |
+ * +---- coarse policies and all any:any policies
+ *
+ * Lookups return four candidate lists:
+ * 1. any:any list from top-level xfrm_pol_inexact_bin
+ * 2. any:daddr list from daddr tree
+ * 3. saddr:daddr list from 2nd level daddr tree
+ * 4. saddr:any list from saddr tree
+ *
+ * This result set then needs to be searched for the policy with
+ * the lowest priority.  If two results have same prio, youngest one wins.
+ */
+
+struct xfrm_pol_inexact_key {
+	possible_net_t net;
+	u32 if_id;
+	u16 family;
+	u8 dir, type;
+};
+
+struct xfrm_pol_inexact_bin {
+	struct xfrm_pol_inexact_key k;
+	struct rhash_head head;
+	/* list containing '*:*' policies */
+	struct hlist_head hhead;
+
+	seqcount_t count;
+	/* tree sorted by daddr/prefix */
+	struct rb_root root_d;
+
+	/* tree sorted by saddr/prefix */
+	struct rb_root root_s;
+
+	/* slow path below */
+	struct list_head inexact_bins;
+	struct rcu_head rcu;
+};
+
+enum xfrm_pol_inexact_candidate_type {
+	XFRM_POL_CAND_BOTH,
+	XFRM_POL_CAND_SADDR,
+	XFRM_POL_CAND_DADDR,
+	XFRM_POL_CAND_ANY,
+
+	XFRM_POL_CAND_MAX,
+};
+
+struct xfrm_pol_inexact_candidates {
+	struct hlist_head *res[XFRM_POL_CAND_MAX];
+};
+
 static DEFINE_SPINLOCK(xfrm_if_cb_lock);
 static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly;
 
@@ -55,6 +154,9 @@
 static struct kmem_cache *xfrm_dst_cache __ro_after_init;
 static __read_mostly seqcount_t xfrm_policy_hash_generation;
 
+static struct rhashtable xfrm_policy_inexact_table;
+static const struct rhashtable_params xfrm_pol_inexact_params;
+
 static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr);
 static int stale_bundle(struct dst_entry *dst);
 static int xfrm_bundle_ok(struct xfrm_dst *xdst);
@@ -64,6 +166,25 @@
 static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 						int dir);
 
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir,
+			   u32 if_id);
+
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup_rcu(struct net *net,
+			       u8 type, u16 family, u8 dir, u32 if_id);
+static struct xfrm_policy *
+xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy,
+			bool excl);
+static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
+					    struct xfrm_policy *policy);
+
+static bool
+xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
+				    struct xfrm_pol_inexact_bin *b,
+				    const xfrm_address_t *saddr,
+				    const xfrm_address_t *daddr);
+
 static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy)
 {
 	return refcount_inc_not_zero(&policy->refcnt);
@@ -269,6 +390,7 @@
 	if (policy) {
 		write_pnet(&policy->xp_net, net);
 		INIT_LIST_HEAD(&policy->walk.all);
+		INIT_HLIST_NODE(&policy->bydst_inexact_list);
 		INIT_HLIST_NODE(&policy->bydst);
 		INIT_HLIST_NODE(&policy->byidx);
 		rwlock_init(&policy->lock);
@@ -365,7 +487,7 @@
 	hash = __sel_hash(sel, family, hmask, dbits, sbits);
 
 	if (hash == hmask + 1)
-		return &net->xfrm.policy_inexact[dir];
+		return NULL;
 
 	return rcu_dereference_check(net->xfrm.policy_bydst[dir].table,
 		     lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash;
@@ -463,9 +585,6 @@
 	odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table,
 				lockdep_is_held(&net->xfrm.xfrm_policy_lock));
 
-	odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table,
-				lockdep_is_held(&net->xfrm.xfrm_policy_lock));
-
 	for (i = hmask; i >= 0; i--)
 		xfrm_dst_hash_transfer(net, odst + i, ndst, nhashmask, dir);
 
@@ -563,6 +682,526 @@
 	mutex_unlock(&hash_resize_mutex);
 }
 
+/* Make sure *pol can be inserted into fastbin.
+ * Useful to check that later insert requests will be sucessful
+ * (provided xfrm_policy_lock is held throughout).
+ */
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
+{
+	struct xfrm_pol_inexact_bin *bin, *prev;
+	struct xfrm_pol_inexact_key k = {
+		.family = pol->family,
+		.type = pol->type,
+		.dir = dir,
+		.if_id = pol->if_id,
+	};
+	struct net *net = xp_net(pol);
+
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	write_pnet(&k.net, net);
+	bin = rhashtable_lookup_fast(&xfrm_policy_inexact_table, &k,
+				     xfrm_pol_inexact_params);
+	if (bin)
+		return bin;
+
+	bin = kzalloc(sizeof(*bin), GFP_ATOMIC);
+	if (!bin)
+		return NULL;
+
+	bin->k = k;
+	INIT_HLIST_HEAD(&bin->hhead);
+	bin->root_d = RB_ROOT;
+	bin->root_s = RB_ROOT;
+	seqcount_init(&bin->count);
+
+	prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table,
+						&bin->k, &bin->head,
+						xfrm_pol_inexact_params);
+	if (!prev) {
+		list_add(&bin->inexact_bins, &net->xfrm.inexact_bins);
+		return bin;
+	}
+
+	kfree(bin);
+
+	return IS_ERR(prev) ? NULL : prev;
+}
+
+static bool xfrm_pol_inexact_addr_use_any_list(const xfrm_address_t *addr,
+					       int family, u8 prefixlen)
+{
+	if (xfrm_addr_any(addr, family))
+		return true;
+
+	if (family == AF_INET6 && prefixlen < INEXACT_PREFIXLEN_IPV6)
+		return true;
+
+	if (family == AF_INET && prefixlen < INEXACT_PREFIXLEN_IPV4)
+		return true;
+
+	return false;
+}
+
+static bool
+xfrm_policy_inexact_insert_use_any_list(const struct xfrm_policy *policy)
+{
+	const xfrm_address_t *addr;
+	bool saddr_any, daddr_any;
+	u8 prefixlen;
+
+	addr = &policy->selector.saddr;
+	prefixlen = policy->selector.prefixlen_s;
+
+	saddr_any = xfrm_pol_inexact_addr_use_any_list(addr,
+						       policy->family,
+						       prefixlen);
+	addr = &policy->selector.daddr;
+	prefixlen = policy->selector.prefixlen_d;
+	daddr_any = xfrm_pol_inexact_addr_use_any_list(addr,
+						       policy->family,
+						       prefixlen);
+	return saddr_any && daddr_any;
+}
+
+static void xfrm_pol_inexact_node_init(struct xfrm_pol_inexact_node *node,
+				       const xfrm_address_t *addr, u8 prefixlen)
+{
+	node->addr = *addr;
+	node->prefixlen = prefixlen;
+}
+
+static struct xfrm_pol_inexact_node *
+xfrm_pol_inexact_node_alloc(const xfrm_address_t *addr, u8 prefixlen)
+{
+	struct xfrm_pol_inexact_node *node;
+
+	node = kzalloc(sizeof(*node), GFP_ATOMIC);
+	if (node)
+		xfrm_pol_inexact_node_init(node, addr, prefixlen);
+
+	return node;
+}
+
+static int xfrm_policy_addr_delta(const xfrm_address_t *a,
+				  const xfrm_address_t *b,
+				  u8 prefixlen, u16 family)
+{
+	unsigned int pdw, pbi;
+	int delta = 0;
+
+	switch (family) {
+	case AF_INET:
+		if (sizeof(long) == 4 && prefixlen == 0)
+			return ntohl(a->a4) - ntohl(b->a4);
+		return (ntohl(a->a4) & ((~0UL << (32 - prefixlen)))) -
+		       (ntohl(b->a4) & ((~0UL << (32 - prefixlen))));
+	case AF_INET6:
+		pdw = prefixlen >> 5;
+		pbi = prefixlen & 0x1f;
+
+		if (pdw) {
+			delta = memcmp(a->a6, b->a6, pdw << 2);
+			if (delta)
+				return delta;
+		}
+		if (pbi) {
+			u32 mask = ~0u << (32 - pbi);
+
+			delta = (ntohl(a->a6[pdw]) & mask) -
+				(ntohl(b->a6[pdw]) & mask);
+		}
+		break;
+	default:
+		break;
+	}
+
+	return delta;
+}
+
+static void xfrm_policy_inexact_list_reinsert(struct net *net,
+					      struct xfrm_pol_inexact_node *n,
+					      u16 family)
+{
+	unsigned int matched_s, matched_d;
+	struct xfrm_policy *policy, *p;
+
+	matched_s = 0;
+	matched_d = 0;
+
+	list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+		struct hlist_node *newpos = NULL;
+		bool matches_s, matches_d;
+
+		if (!policy->bydst_reinsert)
+			continue;
+
+		WARN_ON_ONCE(policy->family != family);
+
+		policy->bydst_reinsert = false;
+		hlist_for_each_entry(p, &n->hhead, bydst) {
+			if (policy->priority > p->priority)
+				newpos = &p->bydst;
+			else if (policy->priority == p->priority &&
+				 policy->pos > p->pos)
+				newpos = &p->bydst;
+			else
+				break;
+		}
+
+		if (newpos)
+			hlist_add_behind_rcu(&policy->bydst, newpos);
+		else
+			hlist_add_head_rcu(&policy->bydst, &n->hhead);
+
+		/* paranoia checks follow.
+		 * Check that the reinserted policy matches at least
+		 * saddr or daddr for current node prefix.
+		 *
+		 * Matching both is fine, matching saddr in one policy
+		 * (but not daddr) and then matching only daddr in another
+		 * is a bug.
+		 */
+		matches_s = xfrm_policy_addr_delta(&policy->selector.saddr,
+						   &n->addr,
+						   n->prefixlen,
+						   family) == 0;
+		matches_d = xfrm_policy_addr_delta(&policy->selector.daddr,
+						   &n->addr,
+						   n->prefixlen,
+						   family) == 0;
+		if (matches_s && matches_d)
+			continue;
+
+		WARN_ON_ONCE(!matches_s && !matches_d);
+		if (matches_s)
+			matched_s++;
+		if (matches_d)
+			matched_d++;
+		WARN_ON_ONCE(matched_s && matched_d);
+	}
+}
+
+static void xfrm_policy_inexact_node_reinsert(struct net *net,
+					      struct xfrm_pol_inexact_node *n,
+					      struct rb_root *new,
+					      u16 family)
+{
+	struct xfrm_pol_inexact_node *node;
+	struct rb_node **p, *parent;
+
+	/* we should not have another subtree here */
+	WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root));
+restart:
+	parent = NULL;
+	p = &new->rb_node;
+	while (*p) {
+		u8 prefixlen;
+		int delta;
+
+		parent = *p;
+		node = rb_entry(*p, struct xfrm_pol_inexact_node, node);
+
+		prefixlen = min(node->prefixlen, n->prefixlen);
+
+		delta = xfrm_policy_addr_delta(&n->addr, &node->addr,
+					       prefixlen, family);
+		if (delta < 0) {
+			p = &parent->rb_left;
+		} else if (delta > 0) {
+			p = &parent->rb_right;
+		} else {
+			bool same_prefixlen = node->prefixlen == n->prefixlen;
+			struct xfrm_policy *tmp;
+
+			hlist_for_each_entry(tmp, &n->hhead, bydst) {
+				tmp->bydst_reinsert = true;
+				hlist_del_rcu(&tmp->bydst);
+			}
+
+			node->prefixlen = prefixlen;
+
+			xfrm_policy_inexact_list_reinsert(net, node, family);
+
+			if (same_prefixlen) {
+				kfree_rcu(n, rcu);
+				return;
+			}
+
+			rb_erase(*p, new);
+			kfree_rcu(n, rcu);
+			n = node;
+			goto restart;
+		}
+	}
+
+	rb_link_node_rcu(&n->node, parent, p);
+	rb_insert_color(&n->node, new);
+}
+
+/* merge nodes v and n */
+static void xfrm_policy_inexact_node_merge(struct net *net,
+					   struct xfrm_pol_inexact_node *v,
+					   struct xfrm_pol_inexact_node *n,
+					   u16 family)
+{
+	struct xfrm_pol_inexact_node *node;
+	struct xfrm_policy *tmp;
+	struct rb_node *rnode;
+
+	/* To-be-merged node v has a subtree.
+	 *
+	 * Dismantle it and insert its nodes to n->root.
+	 */
+	while ((rnode = rb_first(&v->root)) != NULL) {
+		node = rb_entry(rnode, struct xfrm_pol_inexact_node, node);
+		rb_erase(&node->node, &v->root);
+		xfrm_policy_inexact_node_reinsert(net, node, &n->root,
+						  family);
+	}
+
+	hlist_for_each_entry(tmp, &v->hhead, bydst) {
+		tmp->bydst_reinsert = true;
+		hlist_del_rcu(&tmp->bydst);
+	}
+
+	xfrm_policy_inexact_list_reinsert(net, n, family);
+}
+
+static struct xfrm_pol_inexact_node *
+xfrm_policy_inexact_insert_node(struct net *net,
+				struct rb_root *root,
+				xfrm_address_t *addr,
+				u16 family, u8 prefixlen, u8 dir)
+{
+	struct xfrm_pol_inexact_node *cached = NULL;
+	struct rb_node **p, *parent = NULL;
+	struct xfrm_pol_inexact_node *node;
+
+	p = &root->rb_node;
+	while (*p) {
+		int delta;
+
+		parent = *p;
+		node = rb_entry(*p, struct xfrm_pol_inexact_node, node);
+
+		delta = xfrm_policy_addr_delta(addr, &node->addr,
+					       node->prefixlen,
+					       family);
+		if (delta == 0 && prefixlen >= node->prefixlen) {
+			WARN_ON_ONCE(cached); /* ipsec policies got lost */
+			return node;
+		}
+
+		if (delta < 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+
+		if (prefixlen < node->prefixlen) {
+			delta = xfrm_policy_addr_delta(addr, &node->addr,
+						       prefixlen,
+						       family);
+			if (delta)
+				continue;
+
+			/* This node is a subnet of the new prefix. It needs
+			 * to be removed and re-inserted with the smaller
+			 * prefix and all nodes that are now also covered
+			 * by the reduced prefixlen.
+			 */
+			rb_erase(&node->node, root);
+
+			if (!cached) {
+				xfrm_pol_inexact_node_init(node, addr,
+							   prefixlen);
+				cached = node;
+			} else {
+				/* This node also falls within the new
+				 * prefixlen. Merge the to-be-reinserted
+				 * node and this one.
+				 */
+				xfrm_policy_inexact_node_merge(net, node,
+							       cached, family);
+				kfree_rcu(node, rcu);
+			}
+
+			/* restart */
+			p = &root->rb_node;
+			parent = NULL;
+		}
+	}
+
+	node = cached;
+	if (!node) {
+		node = xfrm_pol_inexact_node_alloc(addr, prefixlen);
+		if (!node)
+			return NULL;
+	}
+
+	rb_link_node_rcu(&node->node, parent, p);
+	rb_insert_color(&node->node, root);
+
+	return node;
+}
+
+static void xfrm_policy_inexact_gc_tree(struct rb_root *r, bool rm)
+{
+	struct xfrm_pol_inexact_node *node;
+	struct rb_node *rn = rb_first(r);
+
+	while (rn) {
+		node = rb_entry(rn, struct xfrm_pol_inexact_node, node);
+
+		xfrm_policy_inexact_gc_tree(&node->root, rm);
+		rn = rb_next(rn);
+
+		if (!hlist_empty(&node->hhead) || !RB_EMPTY_ROOT(&node->root)) {
+			WARN_ON_ONCE(rm);
+			continue;
+		}
+
+		rb_erase(&node->node, r);
+		kfree_rcu(node, rcu);
+	}
+}
+
+static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool net_exit)
+{
+	write_seqcount_begin(&b->count);
+	xfrm_policy_inexact_gc_tree(&b->root_d, net_exit);
+	xfrm_policy_inexact_gc_tree(&b->root_s, net_exit);
+	write_seqcount_end(&b->count);
+
+	if (!RB_EMPTY_ROOT(&b->root_d) || !RB_EMPTY_ROOT(&b->root_s) ||
+	    !hlist_empty(&b->hhead)) {
+		WARN_ON_ONCE(net_exit);
+		return;
+	}
+
+	if (rhashtable_remove_fast(&xfrm_policy_inexact_table, &b->head,
+				   xfrm_pol_inexact_params) == 0) {
+		list_del(&b->inexact_bins);
+		kfree_rcu(b, rcu);
+	}
+}
+
+static void xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b)
+{
+	struct net *net = read_pnet(&b->k.net);
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	__xfrm_policy_inexact_prune_bin(b, false);
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+}
+
+static void __xfrm_policy_inexact_flush(struct net *net)
+{
+	struct xfrm_pol_inexact_bin *bin, *t;
+
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	list_for_each_entry_safe(bin, t, &net->xfrm.inexact_bins, inexact_bins)
+		__xfrm_policy_inexact_prune_bin(bin, false);
+}
+
+static struct hlist_head *
+xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin,
+				struct xfrm_policy *policy, u8 dir)
+{
+	struct xfrm_pol_inexact_node *n;
+	struct net *net;
+
+	net = xp_net(policy);
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	if (xfrm_policy_inexact_insert_use_any_list(policy))
+		return &bin->hhead;
+
+	if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr,
+					       policy->family,
+					       policy->selector.prefixlen_d)) {
+		write_seqcount_begin(&bin->count);
+		n = xfrm_policy_inexact_insert_node(net,
+						    &bin->root_s,
+						    &policy->selector.saddr,
+						    policy->family,
+						    policy->selector.prefixlen_s,
+						    dir);
+		write_seqcount_end(&bin->count);
+		if (!n)
+			return NULL;
+
+		return &n->hhead;
+	}
+
+	/* daddr is fixed */
+	write_seqcount_begin(&bin->count);
+	n = xfrm_policy_inexact_insert_node(net,
+					    &bin->root_d,
+					    &policy->selector.daddr,
+					    policy->family,
+					    policy->selector.prefixlen_d, dir);
+	write_seqcount_end(&bin->count);
+	if (!n)
+		return NULL;
+
+	/* saddr is wildcard */
+	if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr,
+					       policy->family,
+					       policy->selector.prefixlen_s))
+		return &n->hhead;
+
+	write_seqcount_begin(&bin->count);
+	n = xfrm_policy_inexact_insert_node(net,
+					    &n->root,
+					    &policy->selector.saddr,
+					    policy->family,
+					    policy->selector.prefixlen_s, dir);
+	write_seqcount_end(&bin->count);
+	if (!n)
+		return NULL;
+
+	return &n->hhead;
+}
+
+static struct xfrm_policy *
+xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
+{
+	struct xfrm_pol_inexact_bin *bin;
+	struct xfrm_policy *delpol;
+	struct hlist_head *chain;
+	struct net *net;
+
+	bin = xfrm_policy_inexact_alloc_bin(policy, dir);
+	if (!bin)
+		return ERR_PTR(-ENOMEM);
+
+	net = xp_net(policy);
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	chain = xfrm_policy_inexact_alloc_chain(bin, policy, dir);
+	if (!chain) {
+		__xfrm_policy_inexact_prune_bin(bin, false);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	delpol = xfrm_policy_insert_list(chain, policy, excl);
+	if (delpol && excl) {
+		__xfrm_policy_inexact_prune_bin(bin, false);
+		return ERR_PTR(-EEXIST);
+	}
+
+	chain = &net->xfrm.policy_inexact[dir];
+	xfrm_policy_insert_inexact_list(chain, policy);
+
+	if (delpol)
+		__xfrm_policy_inexact_prune_bin(bin, false);
+
+	return delpol;
+}
+
 static void xfrm_hash_rebuild(struct work_struct *work)
 {
 	struct net *net = container_of(work, struct net,
@@ -591,14 +1230,66 @@
 	} while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
 
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	write_seqcount_begin(&xfrm_policy_hash_generation);
+
+	/* make sure that we can insert the indirect policies again before
+	 * we start with destructive action.
+	 */
+	list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) {
+		struct xfrm_pol_inexact_bin *bin;
+		u8 dbits, sbits;
+
+		dir = xfrm_policy_id2dir(policy->index);
+		if (policy->walk.dead || dir >= XFRM_POLICY_MAX)
+			continue;
+
+		if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
+			if (policy->family == AF_INET) {
+				dbits = rbits4;
+				sbits = lbits4;
+			} else {
+				dbits = rbits6;
+				sbits = lbits6;
+			}
+		} else {
+			if (policy->family == AF_INET) {
+				dbits = lbits4;
+				sbits = rbits4;
+			} else {
+				dbits = lbits6;
+				sbits = rbits6;
+			}
+		}
+
+		if (policy->selector.prefixlen_d < dbits ||
+		    policy->selector.prefixlen_s < sbits)
+			continue;
+
+		bin = xfrm_policy_inexact_alloc_bin(policy, dir);
+		if (!bin)
+			goto out_unlock;
+
+		if (!xfrm_policy_inexact_alloc_chain(bin, policy, dir))
+			goto out_unlock;
+	}
 
 	/* reset the bydst and inexact table in all directions */
 	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
-		INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
+		struct hlist_node *n;
+
+		hlist_for_each_entry_safe(policy, n,
+					  &net->xfrm.policy_inexact[dir],
+					  bydst_inexact_list) {
+			hlist_del_rcu(&policy->bydst);
+			hlist_del_init(&policy->bydst_inexact_list);
+		}
+
 		hmask = net->xfrm.policy_bydst[dir].hmask;
 		odst = net->xfrm.policy_bydst[dir].table;
-		for (i = hmask; i >= 0; i--)
-			INIT_HLIST_HEAD(odst + i);
+		for (i = hmask; i >= 0; i--) {
+			hlist_for_each_entry_safe(policy, n, odst + i, bydst)
+				hlist_del_rcu(&policy->bydst);
+		}
 		if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
 			/* dir out => dst = remote, src = local */
 			net->xfrm.policy_bydst[dir].dbits4 = rbits4;
@@ -616,15 +1307,24 @@
 
 	/* re-insert all policies by order of creation */
 	list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
-		if (policy->walk.dead ||
-		    xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) {
+		if (policy->walk.dead)
+			continue;
+		dir = xfrm_policy_id2dir(policy->index);
+		if (dir >= XFRM_POLICY_MAX) {
 			/* skip socket policies */
 			continue;
 		}
 		newpos = NULL;
 		chain = policy_hash_bysel(net, &policy->selector,
-					  policy->family,
-					  xfrm_policy_id2dir(policy->index));
+					  policy->family, dir);
+
+		if (!chain) {
+			void *p = xfrm_policy_inexact_insert(policy, dir, 0);
+
+			WARN_ONCE(IS_ERR(p), "reinsert: %ld\n", PTR_ERR(p));
+			continue;
+		}
+
 		hlist_for_each_entry(pol, chain, bydst) {
 			if (policy->priority >= pol->priority)
 				newpos = &pol->bydst;
@@ -637,6 +1337,9 @@
 			hlist_add_head_rcu(&policy->bydst, chain);
 	}
 
+out_unlock:
+	__xfrm_policy_inexact_flush(net);
+	write_seqcount_end(&xfrm_policy_hash_generation);
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	mutex_unlock(&hash_resize_mutex);
@@ -740,18 +1443,97 @@
 	return false;
 }
 
-int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
+static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed)
 {
-	struct net *net = xp_net(policy);
-	struct xfrm_policy *pol;
-	struct xfrm_policy *delpol;
-	struct hlist_head *chain;
-	struct hlist_node *newpos;
+	const struct xfrm_pol_inexact_key *k = data;
+	u32 a = k->type << 24 | k->dir << 16 | k->family;
 
-	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
-	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
-	delpol = NULL;
-	newpos = NULL;
+	return jhash_3words(a, k->if_id, net_hash_mix(read_pnet(&k->net)),
+			    seed);
+}
+
+static u32 xfrm_pol_bin_obj(const void *data, u32 len, u32 seed)
+{
+	const struct xfrm_pol_inexact_bin *b = data;
+
+	return xfrm_pol_bin_key(&b->k, 0, seed);
+}
+
+static int xfrm_pol_bin_cmp(struct rhashtable_compare_arg *arg,
+			    const void *ptr)
+{
+	const struct xfrm_pol_inexact_key *key = arg->key;
+	const struct xfrm_pol_inexact_bin *b = ptr;
+	int ret;
+
+	if (!net_eq(read_pnet(&b->k.net), read_pnet(&key->net)))
+		return -1;
+
+	ret = b->k.dir ^ key->dir;
+	if (ret)
+		return ret;
+
+	ret = b->k.type ^ key->type;
+	if (ret)
+		return ret;
+
+	ret = b->k.family ^ key->family;
+	if (ret)
+		return ret;
+
+	return b->k.if_id ^ key->if_id;
+}
+
+static const struct rhashtable_params xfrm_pol_inexact_params = {
+	.head_offset		= offsetof(struct xfrm_pol_inexact_bin, head),
+	.hashfn			= xfrm_pol_bin_key,
+	.obj_hashfn		= xfrm_pol_bin_obj,
+	.obj_cmpfn		= xfrm_pol_bin_cmp,
+	.automatic_shrinking	= true,
+};
+
+static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
+					    struct xfrm_policy *policy)
+{
+	struct xfrm_policy *pol, *delpol = NULL;
+	struct hlist_node *newpos = NULL;
+	int i = 0;
+
+	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
+		if (pol->type == policy->type &&
+		    pol->if_id == policy->if_id &&
+		    !selector_cmp(&pol->selector, &policy->selector) &&
+		    xfrm_policy_mark_match(policy, pol) &&
+		    xfrm_sec_ctx_match(pol->security, policy->security) &&
+		    !WARN_ON(delpol)) {
+			delpol = pol;
+			if (policy->priority > pol->priority)
+				continue;
+		} else if (policy->priority >= pol->priority) {
+			newpos = &pol->bydst_inexact_list;
+			continue;
+		}
+		if (delpol)
+			break;
+	}
+
+	if (newpos)
+		hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos);
+	else
+		hlist_add_head_rcu(&policy->bydst_inexact_list, chain);
+
+	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
+		pol->pos = i;
+		i++;
+	}
+}
+
+static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
+						   struct xfrm_policy *policy,
+						   bool excl)
+{
+	struct xfrm_policy *pol, *newpos = NULL, *delpol = NULL;
+
 	hlist_for_each_entry(pol, chain, bydst) {
 		if (pol->type == policy->type &&
 		    pol->if_id == policy->if_id &&
@@ -759,24 +1541,45 @@
 		    xfrm_policy_mark_match(policy, pol) &&
 		    xfrm_sec_ctx_match(pol->security, policy->security) &&
 		    !WARN_ON(delpol)) {
-			if (excl) {
-				spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
-				return -EEXIST;
-			}
+			if (excl)
+				return ERR_PTR(-EEXIST);
 			delpol = pol;
 			if (policy->priority > pol->priority)
 				continue;
 		} else if (policy->priority >= pol->priority) {
-			newpos = &pol->bydst;
+			newpos = pol;
 			continue;
 		}
 		if (delpol)
 			break;
 	}
+
 	if (newpos)
-		hlist_add_behind_rcu(&policy->bydst, newpos);
+		hlist_add_behind_rcu(&policy->bydst, &newpos->bydst);
 	else
 		hlist_add_head_rcu(&policy->bydst, chain);
+
+	return delpol;
+}
+
+int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
+{
+	struct net *net = xp_net(policy);
+	struct xfrm_policy *delpol;
+	struct hlist_head *chain;
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
+	if (chain)
+		delpol = xfrm_policy_insert_list(chain, policy, excl);
+	else
+		delpol = xfrm_policy_inexact_insert(policy, dir, excl);
+
+	if (IS_ERR(delpol)) {
+		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+		return PTR_ERR(delpol);
+	}
+
 	__xfrm_policy_link(policy, dir);
 
 	/* After previous checking, family can either be AF_INET or AF_INET6 */
@@ -806,43 +1609,96 @@
 }
 EXPORT_SYMBOL(xfrm_policy_insert);
 
+static struct xfrm_policy *
+__xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id,
+			u8 type, int dir,
+			struct xfrm_selector *sel,
+			struct xfrm_sec_ctx *ctx)
+{
+	struct xfrm_policy *pol;
+
+	if (!chain)
+		return NULL;
+
+	hlist_for_each_entry(pol, chain, bydst) {
+		if (pol->type == type &&
+		    pol->if_id == if_id &&
+		    (mark & pol->mark.m) == pol->mark.v &&
+		    !selector_cmp(sel, &pol->selector) &&
+		    xfrm_sec_ctx_match(ctx, pol->security))
+			return pol;
+	}
+
+	return NULL;
+}
+
 struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
 					  u8 type, int dir,
 					  struct xfrm_selector *sel,
 					  struct xfrm_sec_ctx *ctx, int delete,
 					  int *err)
 {
-	struct xfrm_policy *pol, *ret;
+	struct xfrm_pol_inexact_bin *bin = NULL;
+	struct xfrm_policy *pol, *ret = NULL;
 	struct hlist_head *chain;
 
 	*err = 0;
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, sel, sel->family, dir);
-	ret = NULL;
-	hlist_for_each_entry(pol, chain, bydst) {
-		if (pol->type == type &&
-		    pol->if_id == if_id &&
-		    (mark & pol->mark.m) == pol->mark.v &&
-		    !selector_cmp(sel, &pol->selector) &&
-		    xfrm_sec_ctx_match(ctx, pol->security)) {
-			xfrm_pol_hold(pol);
-			if (delete) {
-				*err = security_xfrm_policy_delete(
-								pol->security);
-				if (*err) {
-					spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
-					return pol;
-				}
-				__xfrm_policy_unlink(pol, dir);
-			}
-			ret = pol;
-			break;
+	if (!chain) {
+		struct xfrm_pol_inexact_candidates cand;
+		int i;
+
+		bin = xfrm_policy_inexact_lookup(net, type,
+						 sel->family, dir, if_id);
+		if (!bin) {
+			spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+			return NULL;
 		}
+
+		if (!xfrm_policy_find_inexact_candidates(&cand, bin,
+							 &sel->saddr,
+							 &sel->daddr)) {
+			spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+			return NULL;
+		}
+
+		pol = NULL;
+		for (i = 0; i < ARRAY_SIZE(cand.res); i++) {
+			struct xfrm_policy *tmp;
+
+			tmp = __xfrm_policy_bysel_ctx(cand.res[i], mark,
+						      if_id, type, dir,
+						      sel, ctx);
+			if (!tmp)
+				continue;
+
+			if (!pol || tmp->pos < pol->pos)
+				pol = tmp;
+		}
+	} else {
+		pol = __xfrm_policy_bysel_ctx(chain, mark, if_id, type, dir,
+					      sel, ctx);
+	}
+
+	if (pol) {
+		xfrm_pol_hold(pol);
+		if (delete) {
+			*err = security_xfrm_policy_delete(pol->security);
+			if (*err) {
+				spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+				return pol;
+			}
+			__xfrm_policy_unlink(pol, dir);
+		}
+		ret = pol;
 	}
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (ret && delete)
 		xfrm_policy_kill(ret);
+	if (bin && delete)
+		xfrm_policy_inexact_prune_bin(bin);
 	return ret;
 }
 EXPORT_SYMBOL(xfrm_policy_bysel_ctx);
@@ -892,36 +1748,19 @@
 static inline int
 xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
 {
-	int dir, err = 0;
+	struct xfrm_policy *pol;
+	int err = 0;
 
-	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
-		struct xfrm_policy *pol;
-		int i;
+	list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+		if (pol->walk.dead ||
+		    xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX ||
+		    pol->type != type)
+			continue;
 
-		hlist_for_each_entry(pol,
-				     &net->xfrm.policy_inexact[dir], bydst) {
-			if (pol->type != type)
-				continue;
-			err = security_xfrm_policy_delete(pol->security);
-			if (err) {
-				xfrm_audit_policy_delete(pol, 0, task_valid);
-				return err;
-			}
-		}
-		for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) {
-			hlist_for_each_entry(pol,
-					     net->xfrm.policy_bydst[dir].table + i,
-					     bydst) {
-				if (pol->type != type)
-					continue;
-				err = security_xfrm_policy_delete(
-								pol->security);
-				if (err) {
-					xfrm_audit_policy_delete(pol, 0,
-								 task_valid);
-					return err;
-				}
-			}
+		err = security_xfrm_policy_delete(pol->security);
+		if (err) {
+			xfrm_audit_policy_delete(pol, 0, task_valid);
+			return err;
 		}
 	}
 	return err;
@@ -937,6 +1776,7 @@
 int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
 {
 	int dir, err = 0, cnt = 0;
+	struct xfrm_policy *pol;
 
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 
@@ -944,48 +1784,25 @@
 	if (err)
 		goto out;
 
-	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
-		struct xfrm_policy *pol;
-		int i;
+again:
+	list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+		dir = xfrm_policy_id2dir(pol->index);
+		if (pol->walk.dead ||
+		    dir >= XFRM_POLICY_MAX ||
+		    pol->type != type)
+			continue;
 
-	again1:
-		hlist_for_each_entry(pol,
-				     &net->xfrm.policy_inexact[dir], bydst) {
-			if (pol->type != type)
-				continue;
-			__xfrm_policy_unlink(pol, dir);
-			spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
-			cnt++;
-
-			xfrm_audit_policy_delete(pol, 1, task_valid);
-
-			xfrm_policy_kill(pol);
-
-			spin_lock_bh(&net->xfrm.xfrm_policy_lock);
-			goto again1;
-		}
-
-		for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) {
-	again2:
-			hlist_for_each_entry(pol,
-					     net->xfrm.policy_bydst[dir].table + i,
-					     bydst) {
-				if (pol->type != type)
-					continue;
-				__xfrm_policy_unlink(pol, dir);
-				spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
-				cnt++;
-
-				xfrm_audit_policy_delete(pol, 1, task_valid);
-				xfrm_policy_kill(pol);
-
-				spin_lock_bh(&net->xfrm.xfrm_policy_lock);
-				goto again2;
-			}
-		}
-
+		__xfrm_policy_unlink(pol, dir);
+		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+		cnt++;
+		xfrm_audit_policy_delete(pol, 1, task_valid);
+		xfrm_policy_kill(pol);
+		spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+		goto again;
 	}
-	if (!cnt)
+	if (cnt)
+		__xfrm_policy_inexact_flush(net);
+	else
 		err = -ESRCH;
 out:
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
@@ -1084,21 +1901,188 @@
 	if (match)
 		ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid,
 						  dir);
-
 	return ret;
 }
 
+static struct xfrm_pol_inexact_node *
+xfrm_policy_lookup_inexact_addr(const struct rb_root *r,
+				seqcount_t *count,
+				const xfrm_address_t *addr, u16 family)
+{
+	const struct rb_node *parent;
+	int seq;
+
+again:
+	seq = read_seqcount_begin(count);
+
+	parent = rcu_dereference_raw(r->rb_node);
+	while (parent) {
+		struct xfrm_pol_inexact_node *node;
+		int delta;
+
+		node = rb_entry(parent, struct xfrm_pol_inexact_node, node);
+
+		delta = xfrm_policy_addr_delta(addr, &node->addr,
+					       node->prefixlen, family);
+		if (delta < 0) {
+			parent = rcu_dereference_raw(parent->rb_left);
+			continue;
+		} else if (delta > 0) {
+			parent = rcu_dereference_raw(parent->rb_right);
+			continue;
+		}
+
+		return node;
+	}
+
+	if (read_seqcount_retry(count, seq))
+		goto again;
+
+	return NULL;
+}
+
+static bool
+xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
+				    struct xfrm_pol_inexact_bin *b,
+				    const xfrm_address_t *saddr,
+				    const xfrm_address_t *daddr)
+{
+	struct xfrm_pol_inexact_node *n;
+	u16 family;
+
+	if (!b)
+		return false;
+
+	family = b->k.family;
+	memset(cand, 0, sizeof(*cand));
+	cand->res[XFRM_POL_CAND_ANY] = &b->hhead;
+
+	n = xfrm_policy_lookup_inexact_addr(&b->root_d, &b->count, daddr,
+					    family);
+	if (n) {
+		cand->res[XFRM_POL_CAND_DADDR] = &n->hhead;
+		n = xfrm_policy_lookup_inexact_addr(&n->root, &b->count, saddr,
+						    family);
+		if (n)
+			cand->res[XFRM_POL_CAND_BOTH] = &n->hhead;
+	}
+
+	n = xfrm_policy_lookup_inexact_addr(&b->root_s, &b->count, saddr,
+					    family);
+	if (n)
+		cand->res[XFRM_POL_CAND_SADDR] = &n->hhead;
+
+	return true;
+}
+
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family,
+			       u8 dir, u32 if_id)
+{
+	struct xfrm_pol_inexact_key k = {
+		.family = family,
+		.type = type,
+		.dir = dir,
+		.if_id = if_id,
+	};
+
+	write_pnet(&k.net, net);
+
+	return rhashtable_lookup(&xfrm_policy_inexact_table, &k,
+				 xfrm_pol_inexact_params);
+}
+
+static struct xfrm_pol_inexact_bin *
+xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family,
+			   u8 dir, u32 if_id)
+{
+	struct xfrm_pol_inexact_bin *bin;
+
+	lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
+
+	rcu_read_lock();
+	bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
+	rcu_read_unlock();
+
+	return bin;
+}
+
+static struct xfrm_policy *
+__xfrm_policy_eval_candidates(struct hlist_head *chain,
+			      struct xfrm_policy *prefer,
+			      const struct flowi *fl,
+			      u8 type, u16 family, int dir, u32 if_id)
+{
+	u32 priority = prefer ? prefer->priority : ~0u;
+	struct xfrm_policy *pol;
+
+	if (!chain)
+		return NULL;
+
+	hlist_for_each_entry_rcu(pol, chain, bydst) {
+		int err;
+
+		if (pol->priority > priority)
+			break;
+
+		err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
+		if (err) {
+			if (err != -ESRCH)
+				return ERR_PTR(err);
+
+			continue;
+		}
+
+		if (prefer) {
+			/* matches.  Is it older than *prefer? */
+			if (pol->priority == priority &&
+			    prefer->pos < pol->pos)
+				return prefer;
+		}
+
+		return pol;
+	}
+
+	return NULL;
+}
+
+static struct xfrm_policy *
+xfrm_policy_eval_candidates(struct xfrm_pol_inexact_candidates *cand,
+			    struct xfrm_policy *prefer,
+			    const struct flowi *fl,
+			    u8 type, u16 family, int dir, u32 if_id)
+{
+	struct xfrm_policy *tmp;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(cand->res); i++) {
+		tmp = __xfrm_policy_eval_candidates(cand->res[i],
+						    prefer,
+						    fl, type, family, dir,
+						    if_id);
+		if (!tmp)
+			continue;
+
+		if (IS_ERR(tmp))
+			return tmp;
+		prefer = tmp;
+	}
+
+	return prefer;
+}
+
 static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 						     const struct flowi *fl,
 						     u16 family, u8 dir,
 						     u32 if_id)
 {
-	int err;
-	struct xfrm_policy *pol, *ret;
+	struct xfrm_pol_inexact_candidates cand;
 	const xfrm_address_t *daddr, *saddr;
+	struct xfrm_pol_inexact_bin *bin;
+	struct xfrm_policy *pol, *ret;
 	struct hlist_head *chain;
 	unsigned int sequence;
-	u32 priority;
+	int err;
 
 	daddr = xfrm_flowi_daddr(fl, family);
 	saddr = xfrm_flowi_saddr(fl, family);
@@ -1112,7 +2096,6 @@
 		chain = policy_hash_direct(net, daddr, saddr, family, dir);
 	} while (read_seqcount_retry(&xfrm_policy_hash_generation, sequence));
 
-	priority = ~0U;
 	ret = NULL;
 	hlist_for_each_entry_rcu(pol, chain, bydst) {
 		err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
@@ -1125,29 +2108,23 @@
 			}
 		} else {
 			ret = pol;
-			priority = ret->priority;
 			break;
 		}
 	}
-	chain = &net->xfrm.policy_inexact[dir];
-	hlist_for_each_entry_rcu(pol, chain, bydst) {
-		if ((pol->priority >= priority) && ret)
-			break;
+	bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
+	if (!bin || !xfrm_policy_find_inexact_candidates(&cand, bin, saddr,
+							 daddr))
+		goto skip_inexact;
 
-		err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
-		if (err) {
-			if (err == -ESRCH)
-				continue;
-			else {
-				ret = ERR_PTR(err);
-				goto fail;
-			}
-		} else {
-			ret = pol;
-			break;
-		}
+	pol = xfrm_policy_eval_candidates(&cand, ret, fl, type,
+					  family, dir, if_id);
+	if (pol) {
+		ret = pol;
+		if (IS_ERR(pol))
+			goto fail;
 	}
 
+skip_inexact:
 	if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence))
 		goto retry;
 
@@ -1239,6 +2216,7 @@
 	/* Socket policies are not hashed. */
 	if (!hlist_unhashed(&pol->bydst)) {
 		hlist_del_rcu(&pol->bydst);
+		hlist_del_init(&pol->bydst_inexact_list);
 		hlist_del(&pol->byidx);
 	}
 
@@ -1478,18 +2456,10 @@
 
 static int xfrm_get_tos(const struct flowi *fl, int family)
 {
-	const struct xfrm_policy_afinfo *afinfo;
-	int tos;
+	if (family == AF_INET)
+		return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos;
 
-	afinfo = xfrm_policy_get_afinfo(family);
-	if (!afinfo)
-		return 0;
-
-	tos = afinfo->get_tos(fl);
-
-	rcu_read_unlock();
-
-	return tos;
+	return 0;
 }
 
 static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
@@ -1527,21 +2497,14 @@
 	return xdst;
 }
 
-static inline int xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst,
-				 int nfheader_len)
+static void xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst,
+			   int nfheader_len)
 {
-	const struct xfrm_policy_afinfo *afinfo =
-		xfrm_policy_get_afinfo(dst->ops->family);
-	int err;
-
-	if (!afinfo)
-		return -EINVAL;
-
-	err = afinfo->init_path(path, dst, nfheader_len);
-
-	rcu_read_unlock();
-
-	return err;
+	if (dst->ops->family == AF_INET6) {
+		struct rt6_info *rt = (struct rt6_info *)dst;
+		path->path_cookie = rt6_get_cookie(rt);
+		path->u.rt6.rt6i_nfheader_len = nfheader_len;
+	}
 }
 
 static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
@@ -1573,10 +2536,11 @@
 					    const struct flowi *fl,
 					    struct dst_entry *dst)
 {
+	const struct xfrm_state_afinfo *afinfo;
+	const struct xfrm_mode *inner_mode;
 	struct net *net = xp_net(policy);
 	unsigned long now = jiffies;
 	struct net_device *dev;
-	struct xfrm_mode *inner_mode;
 	struct xfrm_dst *xdst_prev = NULL;
 	struct xfrm_dst *xdst0 = NULL;
 	int i = 0;
@@ -1622,13 +2586,16 @@
 				goto put_states;
 			}
 		} else
-			inner_mode = xfrm[i]->inner_mode;
+			inner_mode = &xfrm[i]->inner_mode;
 
 		xdst->route = dst;
 		dst_copy_metrics(dst1, dst);
 
 		if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
-			__u32 mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
+			__u32 mark = 0;
+
+			if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m)
+				mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
 
 			family = xfrm[i]->props.family;
 			dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif,
@@ -1647,7 +2614,14 @@
 		dst1->lastuse = now;
 
 		dst1->input = dst_discard;
-		dst1->output = inner_mode->afinfo->output;
+
+		rcu_read_lock();
+		afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
+		if (likely(afinfo))
+			dst1->output = afinfo->output;
+		else
+			dst1->output = dst_discard_out;
+		rcu_read_unlock();
 
 		xdst_prev = xdst;
 
@@ -1811,7 +2785,7 @@
 		pq->timeout = pq->timeout << 1;
 		if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout))
 			xfrm_pol_hold(pol);
-	goto out;
+		goto out;
 	}
 
 	dst_release(dst);
@@ -1834,7 +2808,7 @@
 			continue;
 		}
 
-		nf_reset(skb);
+		nf_reset_ct(skb);
 		skb_dst_drop(skb);
 		skb_dst_set(skb, dst);
 
@@ -2225,11 +3199,12 @@
 static inline int
 xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl)
 {
+	struct sec_path *sp = skb_sec_path(skb);
 	struct xfrm_state *x;
 
-	if (!skb->sp || idx < 0 || idx >= skb->sp->len)
+	if (!sp || idx < 0 || idx >= sp->len)
 		return 0;
-	x = skb->sp->xvec[idx];
+	x = sp->xvec[idx];
 	if (!x->type->reject)
 		return 0;
 	return x->type->reject(x, skb, fl);
@@ -2287,20 +3262,231 @@
 	return start;
 }
 
+static void
+decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	int ihl = iph->ihl;
+	u8 *xprth = skb_network_header(skb) + ihl * 4;
+	struct flowi4 *fl4 = &fl->u.ip4;
+	int oif = 0;
+
+	if (skb_dst(skb) && skb_dst(skb)->dev)
+		oif = skb_dst(skb)->dev->ifindex;
+
+	memset(fl4, 0, sizeof(struct flowi4));
+	fl4->flowi4_mark = skb->mark;
+	fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
+
+	fl4->flowi4_proto = iph->protocol;
+	fl4->daddr = reverse ? iph->saddr : iph->daddr;
+	fl4->saddr = reverse ? iph->daddr : iph->saddr;
+	fl4->flowi4_tos = iph->tos;
+
+	if (!ip_is_fragment(iph)) {
+		switch (iph->protocol) {
+		case IPPROTO_UDP:
+		case IPPROTO_UDPLITE:
+		case IPPROTO_TCP:
+		case IPPROTO_SCTP:
+		case IPPROTO_DCCP:
+			if (xprth + 4 < skb->data ||
+			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
+				__be16 *ports;
+
+				xprth = skb_network_header(skb) + ihl * 4;
+				ports = (__be16 *)xprth;
+
+				fl4->fl4_sport = ports[!!reverse];
+				fl4->fl4_dport = ports[!reverse];
+			}
+			break;
+		case IPPROTO_ICMP:
+			if (xprth + 2 < skb->data ||
+			    pskb_may_pull(skb, xprth + 2 - skb->data)) {
+				u8 *icmp;
+
+				xprth = skb_network_header(skb) + ihl * 4;
+				icmp = xprth;
+
+				fl4->fl4_icmp_type = icmp[0];
+				fl4->fl4_icmp_code = icmp[1];
+			}
+			break;
+		case IPPROTO_ESP:
+			if (xprth + 4 < skb->data ||
+			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
+				__be32 *ehdr;
+
+				xprth = skb_network_header(skb) + ihl * 4;
+				ehdr = (__be32 *)xprth;
+
+				fl4->fl4_ipsec_spi = ehdr[0];
+			}
+			break;
+		case IPPROTO_AH:
+			if (xprth + 8 < skb->data ||
+			    pskb_may_pull(skb, xprth + 8 - skb->data)) {
+				__be32 *ah_hdr;
+
+				xprth = skb_network_header(skb) + ihl * 4;
+				ah_hdr = (__be32 *)xprth;
+
+				fl4->fl4_ipsec_spi = ah_hdr[1];
+			}
+			break;
+		case IPPROTO_COMP:
+			if (xprth + 4 < skb->data ||
+			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
+				__be16 *ipcomp_hdr;
+
+				xprth = skb_network_header(skb) + ihl * 4;
+				ipcomp_hdr = (__be16 *)xprth;
+
+				fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
+			}
+			break;
+		case IPPROTO_GRE:
+			if (xprth + 12 < skb->data ||
+			    pskb_may_pull(skb, xprth + 12 - skb->data)) {
+				__be16 *greflags;
+				__be32 *gre_hdr;
+
+				xprth = skb_network_header(skb) + ihl * 4;
+				greflags = (__be16 *)xprth;
+				gre_hdr = (__be32 *)xprth;
+
+				if (greflags[0] & GRE_KEY) {
+					if (greflags[0] & GRE_CSUM)
+						gre_hdr++;
+					fl4->fl4_gre_key = gre_hdr[1];
+				}
+			}
+			break;
+		default:
+			fl4->fl4_ipsec_spi = 0;
+			break;
+		}
+	}
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static void
+decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
+{
+	struct flowi6 *fl6 = &fl->u.ip6;
+	int onlyproto = 0;
+	const struct ipv6hdr *hdr = ipv6_hdr(skb);
+	u32 offset = sizeof(*hdr);
+	struct ipv6_opt_hdr *exthdr;
+	const unsigned char *nh = skb_network_header(skb);
+	u16 nhoff = IP6CB(skb)->nhoff;
+	int oif = 0;
+	u8 nexthdr;
+
+	if (!nhoff)
+		nhoff = offsetof(struct ipv6hdr, nexthdr);
+
+	nexthdr = nh[nhoff];
+
+	if (skb_dst(skb) && skb_dst(skb)->dev)
+		oif = skb_dst(skb)->dev->ifindex;
+
+	memset(fl6, 0, sizeof(struct flowi6));
+	fl6->flowi6_mark = skb->mark;
+	fl6->flowi6_oif = reverse ? skb->skb_iif : oif;
+
+	fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
+	fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
+
+	while (nh + offset + sizeof(*exthdr) < skb->data ||
+	       pskb_may_pull(skb, nh + offset + sizeof(*exthdr) - skb->data)) {
+		nh = skb_network_header(skb);
+		exthdr = (struct ipv6_opt_hdr *)(nh + offset);
+
+		switch (nexthdr) {
+		case NEXTHDR_FRAGMENT:
+			onlyproto = 1;
+			/* fall through */
+		case NEXTHDR_ROUTING:
+		case NEXTHDR_HOP:
+		case NEXTHDR_DEST:
+			offset += ipv6_optlen(exthdr);
+			nexthdr = exthdr->nexthdr;
+			exthdr = (struct ipv6_opt_hdr *)(nh + offset);
+			break;
+		case IPPROTO_UDP:
+		case IPPROTO_UDPLITE:
+		case IPPROTO_TCP:
+		case IPPROTO_SCTP:
+		case IPPROTO_DCCP:
+			if (!onlyproto && (nh + offset + 4 < skb->data ||
+			     pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
+				__be16 *ports;
+
+				nh = skb_network_header(skb);
+				ports = (__be16 *)(nh + offset);
+				fl6->fl6_sport = ports[!!reverse];
+				fl6->fl6_dport = ports[!reverse];
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+		case IPPROTO_ICMPV6:
+			if (!onlyproto && (nh + offset + 2 < skb->data ||
+			    pskb_may_pull(skb, nh + offset + 2 - skb->data))) {
+				u8 *icmp;
+
+				nh = skb_network_header(skb);
+				icmp = (u8 *)(nh + offset);
+				fl6->fl6_icmp_type = icmp[0];
+				fl6->fl6_icmp_code = icmp[1];
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+		case IPPROTO_MH:
+			offset += ipv6_optlen(exthdr);
+			if (!onlyproto && (nh + offset + 3 < skb->data ||
+			    pskb_may_pull(skb, nh + offset + 3 - skb->data))) {
+				struct ip6_mh *mh;
+
+				nh = skb_network_header(skb);
+				mh = (struct ip6_mh *)(nh + offset);
+				fl6->fl6_mh_type = mh->ip6mh_type;
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+#endif
+		/* XXX Why are there these headers? */
+		case IPPROTO_AH:
+		case IPPROTO_ESP:
+		case IPPROTO_COMP:
+		default:
+			fl6->fl6_ipsec_spi = 0;
+			fl6->flowi6_proto = nexthdr;
+			return;
+		}
+	}
+}
+#endif
+
 int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
 			  unsigned int family, int reverse)
 {
-	const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
-	int err;
-
-	if (unlikely(afinfo == NULL))
+	switch (family) {
+	case AF_INET:
+		decode_session4(skb, fl, reverse);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		decode_session6(skb, fl, reverse);
+		break;
+#endif
+	default:
 		return -EAFNOSUPPORT;
+	}
 
-	afinfo->decode_session(skb, fl, reverse);
-
-	err = security_xfrm_decode_session(skb, &fl->flowi_secid);
-	rcu_read_unlock();
-	return err;
+	return security_xfrm_decode_session(skb, &fl->flowi_secid);
 }
 EXPORT_SYMBOL(__xfrm_decode_session);
 
@@ -2329,6 +3515,7 @@
 	struct flowi fl;
 	int xerr_idx = -1;
 	const struct xfrm_if_cb *ifcb;
+	struct sec_path *sp;
 	struct xfrm_if *xi;
 	u32 if_id = 0;
 
@@ -2336,9 +3523,11 @@
 	ifcb = xfrm_if_get_cb();
 
 	if (ifcb) {
-		xi = ifcb->decode_session(skb);
-		if (xi)
+		xi = ifcb->decode_session(skb, family);
+		if (xi) {
 			if_id = xi->p.if_id;
+			net = xi->net;
+		}
 	}
 	rcu_read_unlock();
 
@@ -2353,11 +3542,12 @@
 	nf_nat_decode_session(skb, &fl, family);
 
 	/* First, check used SA against their selectors. */
-	if (skb->sp) {
+	sp = skb_sec_path(skb);
+	if (sp) {
 		int i;
 
-		for (i = skb->sp->len-1; i >= 0; i--) {
-			struct xfrm_state *x = skb->sp->xvec[i];
+		for (i = sp->len - 1; i >= 0; i--) {
+			struct xfrm_state *x = sp->xvec[i];
 			if (!xfrm_selector_match(&x->sel, &fl, family)) {
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH);
 				return 0;
@@ -2384,7 +3574,7 @@
 	}
 
 	if (!pol) {
-		if (skb->sp && secpath_has_nontransport(skb->sp, 0, &xerr_idx)) {
+		if (sp && secpath_has_nontransport(sp, 0, &xerr_idx)) {
 			xfrm_secpath_reject(xerr_idx, skb, &fl);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS);
 			return 0;
@@ -2413,7 +3603,6 @@
 #endif
 
 	if (pol->action == XFRM_POLICY_ALLOW) {
-		struct sec_path *sp;
 		static struct sec_path dummy;
 		struct xfrm_tmpl *tp[XFRM_MAX_DEPTH];
 		struct xfrm_tmpl *stp[XFRM_MAX_DEPTH];
@@ -2421,7 +3610,8 @@
 		int ti = 0;
 		int i, k;
 
-		if ((sp = skb->sp) == NULL)
+		sp = skb_sec_path(skb);
+		if (!sp)
 			sp = &dummy;
 
 		for (pi = 0; pi < npols; pi++) {
@@ -2439,7 +3629,7 @@
 		}
 		xfrm_nr = ti;
 		if (npols > 1) {
-			xfrm_tmpl_sort(stp, tpp, xfrm_nr, family, net);
+			xfrm_tmpl_sort(stp, tpp, xfrm_nr, family);
 			tpp = stp;
 		}
 
@@ -2816,13 +4006,17 @@
 static int __net_init xfrm_policy_init(struct net *net)
 {
 	unsigned int hmask, sz;
-	int dir;
+	int dir, err;
 
-	if (net_eq(net, &init_net))
+	if (net_eq(net, &init_net)) {
 		xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache",
 					   sizeof(struct xfrm_dst),
 					   0, SLAB_HWCACHE_ALIGN|SLAB_PANIC,
 					   NULL);
+		err = rhashtable_init(&xfrm_policy_inexact_table,
+				      &xfrm_pol_inexact_params);
+		BUG_ON(err);
+	}
 
 	hmask = 8 - 1;
 	sz = (hmask+1) * sizeof(struct hlist_head);
@@ -2857,6 +4051,7 @@
 	seqlock_init(&net->xfrm.policy_hthresh.lock);
 
 	INIT_LIST_HEAD(&net->xfrm.policy_all);
+	INIT_LIST_HEAD(&net->xfrm.inexact_bins);
 	INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize);
 	INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild);
 	return 0;
@@ -2875,6 +4070,7 @@
 
 static void xfrm_policy_fini(struct net *net)
 {
+	struct xfrm_pol_inexact_bin *b, *t;
 	unsigned int sz;
 	int dir;
 
@@ -2900,6 +4096,11 @@
 	sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head);
 	WARN_ON(!hlist_empty(net->xfrm.policy_byidx));
 	xfrm_hash_free(net->xfrm.policy_byidx, sz);
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+	list_for_each_entry_safe(b, t, &net->xfrm.inexact_bins, inexact_bins)
+		__xfrm_policy_inexact_prune_bin(b, true);
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 }
 
 static int __net_init xfrm_net_init(struct net *net)
@@ -3065,7 +4266,7 @@
 		}
 	}
 	chain = &net->xfrm.policy_inexact[dir];
-	hlist_for_each_entry(pol, chain, bydst) {
+	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
 		if ((pol->priority >= priority) && ret)
 			break;