1 files changed, 142 insertions, 131 deletions

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index dbda08ec566e..e392d8d05e0c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -31,15 +31,17 @@
 #include <linux/if_tunnel.h>
 #include <net/dst.h>
 #include <net/flow.h>
+#include <net/inet_ecn.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
+#include <net/gre.h>
 #if IS_ENABLED(CONFIG_IPV6_MIP6)
 #include <net/mip6.h>
 #endif
 #ifdef CONFIG_XFRM_STATISTICS
 #include <net/snmp.h>
 #endif
-#ifdef CONFIG_INET_ESPINTCP
+#ifdef CONFIG_XFRM_ESPINTCP
 #include <net/espintcp.h>
 #endif
 
@@ -122,7 +124,7 @@ struct xfrm_pol_inexact_bin {
 	/* list containing '*:*' policies */
 	struct hlist_head hhead;
 
-	seqcount_t count;
+	seqcount_spinlock_t count;
 	/* tree sorted by daddr/prefix */
 	struct rb_root root_d;
 
@@ -155,7 +157,6 @@ static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1]
 						__read_mostly;
 
 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;
@@ -434,7 +435,9 @@ EXPORT_SYMBOL(xfrm_policy_destroy);
 
 static void xfrm_policy_kill(struct xfrm_policy *policy)
 {
+	write_lock_bh(&policy->lock);
 	policy->walk.dead = 1;
+	write_unlock_bh(&policy->lock);
 
 	atomic_inc(&policy->genid);
 
@@ -583,7 +586,7 @@ static void xfrm_bydst_resize(struct net *net, int dir)
 		return;
 
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
-	write_seqcount_begin(&xfrm_policy_hash_generation);
+	write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
 
 	odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table,
 				lockdep_is_held(&net->xfrm.xfrm_policy_lock));
@@ -594,7 +597,7 @@ static void xfrm_bydst_resize(struct net *net, int dir)
 	rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst);
 	net->xfrm.policy_bydst[dir].hmask = nhashmask;
 
-	write_seqcount_end(&xfrm_policy_hash_generation);
+	write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation);
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	synchronize_rcu();
@@ -686,7 +689,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 }
 
 /* Make sure *pol can be inserted into fastbin.
- * Useful to check that later insert requests will be sucessful
+ * Useful to check that later insert requests will be successful
  * (provided xfrm_policy_lock is held throughout).
  */
 static struct xfrm_pol_inexact_bin *
@@ -717,7 +720,7 @@ xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
 	INIT_HLIST_HEAD(&bin->hhead);
 	bin->root_d = RB_ROOT;
 	bin->root_s = RB_ROOT;
-	seqcount_init(&bin->count);
+	seqcount_spinlock_init(&bin->count, &net->xfrm.xfrm_policy_lock);
 
 	prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table,
 						&bin->k, &bin->head,
@@ -791,15 +794,22 @@ static int xfrm_policy_addr_delta(const xfrm_address_t *a,
 				  const xfrm_address_t *b,
 				  u8 prefixlen, u16 family)
 {
+	u32 ma, mb, mask;
 	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))));
+		if (prefixlen == 0)
+			return 0;
+		mask = ~0U << (32 - prefixlen);
+		ma = ntohl(a->a4) & mask;
+		mb = ntohl(b->a4) & mask;
+		if (ma < mb)
+			delta = -1;
+		else if (ma > mb)
+			delta = 1;
+		break;
 	case AF_INET6:
 		pdw = prefixlen >> 5;
 		pbi = prefixlen & 0x1f;
@@ -810,10 +820,13 @@ static int xfrm_policy_addr_delta(const xfrm_address_t *a,
 				return delta;
 		}
 		if (pbi) {
-			u32 mask = ~0u << (32 - pbi);
-
-			delta = (ntohl(a->a6[pdw]) & mask) -
-				(ntohl(b->a6[pdw]) & mask);
+			mask = ~0U << (32 - pbi);
+			ma = ntohl(a->a6[pdw]) & mask;
+			mb = ntohl(b->a6[pdw]) & mask;
+			if (ma < mb)
+				delta = -1;
+			else if (ma > mb)
+				delta = 1;
 		}
 		break;
 	default:
@@ -1233,7 +1246,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 	} while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
 
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
-	write_seqcount_begin(&xfrm_policy_hash_generation);
+	write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
 
 	/* make sure that we can insert the indirect policies again before
 	 * we start with destructive action.
@@ -1342,7 +1355,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 
 out_unlock:
 	__xfrm_policy_inexact_flush(net);
-	write_seqcount_end(&xfrm_policy_hash_generation);
+	write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation);
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	mutex_unlock(&hash_resize_mutex);
@@ -1431,19 +1444,10 @@ static void xfrm_policy_requeue(struct xfrm_policy *old,
 	spin_unlock_bh(&pq->hold_queue.lock);
 }
 
-static bool xfrm_policy_mark_match(struct xfrm_policy *policy,
-				   struct xfrm_policy *pol)
+static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark,
+					  struct xfrm_policy *pol)
 {
-	u32 mark = policy->mark.v & policy->mark.m;
-
-	if (policy->mark.v == pol->mark.v && policy->mark.m == pol->mark.m)
-		return true;
-
-	if ((mark & pol->mark.m) == pol->mark.v &&
-	    policy->priority == pol->priority)
-		return true;
-
-	return false;
+	return mark->v == pol->mark.v && mark->m == pol->mark.m;
 }
 
 static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed)
@@ -1506,7 +1510,7 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
 		if (pol->type == policy->type &&
 		    pol->if_id == policy->if_id &&
 		    !selector_cmp(&pol->selector, &policy->selector) &&
-		    xfrm_policy_mark_match(policy, pol) &&
+		    xfrm_policy_mark_match(&policy->mark, pol) &&
 		    xfrm_sec_ctx_match(pol->security, policy->security) &&
 		    !WARN_ON(delpol)) {
 			delpol = pol;
@@ -1541,7 +1545,7 @@ static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
 		if (pol->type == policy->type &&
 		    pol->if_id == policy->if_id &&
 		    !selector_cmp(&pol->selector, &policy->selector) &&
-		    xfrm_policy_mark_match(policy, pol) &&
+		    xfrm_policy_mark_match(&policy->mark, pol) &&
 		    xfrm_sec_ctx_match(pol->security, policy->security) &&
 		    !WARN_ON(delpol)) {
 			if (excl)
@@ -1613,9 +1617,8 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 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,
+__xfrm_policy_bysel_ctx(struct hlist_head *chain, const struct xfrm_mark *mark,
+			u32 if_id, u8 type, int dir, struct xfrm_selector *sel,
 			struct xfrm_sec_ctx *ctx)
 {
 	struct xfrm_policy *pol;
@@ -1626,7 +1629,7 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id,
 	hlist_for_each_entry(pol, chain, bydst) {
 		if (pol->type == type &&
 		    pol->if_id == if_id &&
-		    (mark & pol->mark.m) == pol->mark.v &&
+		    xfrm_policy_mark_match(mark, pol) &&
 		    !selector_cmp(sel, &pol->selector) &&
 		    xfrm_sec_ctx_match(ctx, pol->security))
 			return pol;
@@ -1635,11 +1638,10 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id,
 	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 *
+xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id,
+		      u8 type, int dir, struct xfrm_selector *sel,
+		      struct xfrm_sec_ctx *ctx, int delete, int *err)
 {
 	struct xfrm_pol_inexact_bin *bin = NULL;
 	struct xfrm_policy *pol, *ret = NULL;
@@ -1706,9 +1708,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
 }
 EXPORT_SYMBOL(xfrm_policy_bysel_ctx);
 
-struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id,
-				     u8 type, int dir, u32 id, int delete,
-				     int *err)
+struct xfrm_policy *
+xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id,
+		 u8 type, int dir, u32 id, int delete, int *err)
 {
 	struct xfrm_policy *pol, *ret;
 	struct hlist_head *chain;
@@ -1723,8 +1725,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id,
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, byidx) {
 		if (pol->type == type && pol->index == id &&
-		    pol->if_id == if_id &&
-		    (mark & pol->mark.m) == pol->mark.v) {
+		    pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) {
 			xfrm_pol_hold(pol);
 			if (delete) {
 				*err = security_xfrm_policy_delete(
@@ -1888,7 +1889,7 @@ EXPORT_SYMBOL(xfrm_policy_walk_done);
  */
 static int xfrm_policy_match(const struct xfrm_policy *pol,
 			     const struct flowi *fl,
-			     u8 type, u16 family, int dir, u32 if_id)
+			     u8 type, u16 family, u32 if_id)
 {
 	const struct xfrm_selector *sel = &pol->selector;
 	int ret = -ESRCH;
@@ -1902,14 +1903,13 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
 
 	match = xfrm_selector_match(sel, fl, family);
 	if (match)
-		ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid,
-						  dir);
+		ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid);
 	return ret;
 }
 
 static struct xfrm_pol_inexact_node *
 xfrm_policy_lookup_inexact_addr(const struct rb_root *r,
-				seqcount_t *count,
+				seqcount_spinlock_t *count,
 				const xfrm_address_t *addr, u16 family)
 {
 	const struct rb_node *parent;
@@ -2014,7 +2014,7 @@ 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)
+			      u8 type, u16 family, u32 if_id)
 {
 	u32 priority = prefer ? prefer->priority : ~0u;
 	struct xfrm_policy *pol;
@@ -2028,7 +2028,7 @@ __xfrm_policy_eval_candidates(struct hlist_head *chain,
 		if (pol->priority > priority)
 			break;
 
-		err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
+		err = xfrm_policy_match(pol, fl, type, family, if_id);
 		if (err) {
 			if (err != -ESRCH)
 				return ERR_PTR(err);
@@ -2053,7 +2053,7 @@ 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)
+			    u8 type, u16 family, u32 if_id)
 {
 	struct xfrm_policy *tmp;
 	int i;
@@ -2061,8 +2061,7 @@ xfrm_policy_eval_candidates(struct xfrm_pol_inexact_candidates *cand,
 	for (i = 0; i < ARRAY_SIZE(cand->res); i++) {
 		tmp = __xfrm_policy_eval_candidates(cand->res[i],
 						    prefer,
-						    fl, type, family, dir,
-						    if_id);
+						    fl, type, family, if_id);
 		if (!tmp)
 			continue;
 
@@ -2095,13 +2094,13 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 	rcu_read_lock();
  retry:
 	do {
-		sequence = read_seqcount_begin(&xfrm_policy_hash_generation);
+		sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
 		chain = policy_hash_direct(net, daddr, saddr, family, dir);
-	} while (read_seqcount_retry(&xfrm_policy_hash_generation, sequence));
+	} while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence));
 
 	ret = NULL;
 	hlist_for_each_entry_rcu(pol, chain, bydst) {
-		err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
+		err = xfrm_policy_match(pol, fl, type, family, if_id);
 		if (err) {
 			if (err == -ESRCH)
 				continue;
@@ -2120,7 +2119,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 		goto skip_inexact;
 
 	pol = xfrm_policy_eval_candidates(&cand, ret, fl, type,
-					  family, dir, if_id);
+					  family, if_id);
 	if (pol) {
 		ret = pol;
 		if (IS_ERR(pol))
@@ -2128,7 +2127,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 	}
 
 skip_inexact:
-	if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence))
+	if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence))
 		goto retry;
 
 	if (ret && !xfrm_pol_hold_rcu(ret))
@@ -2181,8 +2180,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
 				goto out;
 			}
 			err = security_xfrm_policy_lookup(pol->security,
-						      fl->flowi_secid,
-						      dir);
+						      fl->flowi_secid);
 			if (!err) {
 				if (!xfrm_pol_hold_rcu(pol))
 					goto again;
@@ -2489,9 +2487,7 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
 	xdst = dst_alloc(dst_ops, NULL, 1, DST_OBSOLETE_NONE, 0);
 
 	if (likely(xdst)) {
-		struct dst_entry *dst = &xdst->u.dst;
-
-		memset(dst + 1, 0, sizeof(*xdst) - sizeof(*dst));
+		memset_after(xdst, 0, u.dst);
 	} else
 		xdst = ERR_PTR(-ENOBUFS);
 
@@ -2596,12 +2592,14 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 
 		if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
 			__u32 mark = 0;
+			int oif;
 
 			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,
+			oif = fl->flowi_oif ? : fl->flowi_l3mdev;
+			dst = xfrm_dst_lookup(xfrm[i], tos, oif,
 					      &saddr, &daddr, family, mark);
 			err = PTR_ERR(dst);
 			if (IS_ERR(dst))
@@ -2613,7 +2611,6 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 		xdst->xfrm_genid = xfrm[i]->genid;
 
 		dst1->obsolete = DST_OBSOLETE_FORCE_CHK;
-		dst1->flags |= DST_HOST;
 		dst1->lastuse = now;
 
 		dst1->input = dst_discard;
@@ -2680,13 +2677,15 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family,
 		*num_xfrms = 0;
 		return 0;
 	}
-	if (IS_ERR(pols[0]))
+	if (IS_ERR(pols[0])) {
+		*num_pols = 0;
 		return PTR_ERR(pols[0]);
+	}
 
 	*num_xfrms = pols[0]->xfrm_nr;
 
 #ifdef CONFIG_XFRM_SUB_POLICY
-	if (pols[0] && pols[0]->action == XFRM_POLICY_ALLOW &&
+	if (pols[0]->action == XFRM_POLICY_ALLOW &&
 	    pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
 		pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]),
 						    XFRM_POLICY_TYPE_MAIN,
@@ -2696,6 +2695,7 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family,
 		if (pols[1]) {
 			if (IS_ERR(pols[1])) {
 				xfrm_pols_put(pols, *num_pols);
+				*num_pols = 0;
 				return PTR_ERR(pols[1]);
 			}
 			(*num_pols)++;
@@ -2762,6 +2762,7 @@ static void xfrm_policy_queue_process(struct timer_list *t)
 	struct xfrm_policy_queue *pq = &pol->polq;
 	struct flowi fl;
 	struct sk_buff_head list;
+	__u32 skb_mark;
 
 	spin_lock(&pq->hold_queue.lock);
 	skb = skb_peek(&pq->hold_queue);
@@ -2771,7 +2772,12 @@ static void xfrm_policy_queue_process(struct timer_list *t)
 	}
 	dst = skb_dst(skb);
 	sk = skb->sk;
+
+	/* Fixup the mark to support VTI. */
+	skb_mark = skb->mark;
+	skb->mark = pol->mark.v;
 	xfrm_decode_session(skb, &fl, dst->ops->family);
+	skb->mark = skb_mark;
 	spin_unlock(&pq->hold_queue.lock);
 
 	dst_hold(xfrm_dst_path(dst));
@@ -2803,7 +2809,12 @@ static void xfrm_policy_queue_process(struct timer_list *t)
 	while (!skb_queue_empty(&list)) {
 		skb = __skb_dequeue(&list);
 
+		/* Fixup the mark to support VTI. */
+		skb_mark = skb->mark;
+		skb->mark = pol->mark.v;
 		xfrm_decode_session(skb, &fl, skb_dst(skb)->ops->family);
+		skb->mark = skb_mark;
+
 		dst_hold(xfrm_dst_path(skb_dst(skb)));
 		dst = xfrm_lookup(net, xfrm_dst_path(skb_dst(skb)), &fl, skb->sk, 0);
 		if (IS_ERR(dst)) {
@@ -2899,7 +2910,7 @@ static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net,
 	dst_copy_metrics(dst1, dst);
 
 	dst1->obsolete = DST_OBSOLETE_FORCE_CHK;
-	dst1->flags |= DST_HOST | DST_XFRM_QUEUE;
+	dst1->flags |= DST_XFRM_QUEUE;
 	dst1->lastuse = jiffies;
 
 	dst1->input = dst_discard;
@@ -3078,8 +3089,8 @@ struct dst_entry *xfrm_lookup_with_ifid(struct net *net,
 		xflo.flags = flags;
 
 		/* To accelerate a bit...  */
-		if ((dst_orig->flags & DST_NOXFRM) ||
-		    !net->xfrm.policy_count[XFRM_POLICY_OUT])
+		if (!if_id && ((dst_orig->flags & DST_NOXFRM) ||
+			       !net->xfrm.policy_count[XFRM_POLICY_OUT]))
 			goto nopol;
 
 		xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id);
@@ -3150,6 +3161,11 @@ ok:
 	return dst;
 
 nopol:
+	if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) &&
+	    net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
+		err = -EPERM;
+		goto error;
+	}
 	if (!(flags & XFRM_LOOKUP_ICMP)) {
 		dst = dst_orig;
 		goto ok;
@@ -3237,7 +3253,7 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x,
 
 /*
  * 0 or more than 0 is returned when validation is succeeded (either bypass
- * because of optional transport mode, or next index of the mathced secpath
+ * because of optional transport mode, or next index of the matched secpath
  * state with the template.
  * -1 is returned when no matching template is found.
  * Otherwise "-2 - errored_index" is returned.
@@ -3284,7 +3300,7 @@ decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse)
 	fl4->flowi4_proto = iph->protocol;
 	fl4->daddr = reverse ? iph->saddr : iph->daddr;
 	fl4->saddr = reverse ? iph->daddr : iph->saddr;
-	fl4->flowi4_tos = iph->tos;
+	fl4->flowi4_tos = iph->tos & ~INET_ECN_MASK;
 
 	if (!ip_is_fragment(iph)) {
 		switch (iph->protocol) {
@@ -3316,39 +3332,6 @@ decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse)
 				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)) {
@@ -3367,7 +3350,6 @@ decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse)
 			}
 			break;
 		default:
-			fl4->fl4_ipsec_spi = 0;
 			break;
 		}
 	}
@@ -3410,13 +3392,12 @@ decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
 		switch (nexthdr) {
 		case NEXTHDR_FRAGMENT:
 			onlyproto = 1;
-			/* fall through */
+			fallthrough;
 		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:
@@ -3446,6 +3427,26 @@ decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
 			}
 			fl6->flowi6_proto = nexthdr;
 			return;
+		case IPPROTO_GRE:
+			if (!onlyproto &&
+			    (nh + offset + 12 < skb->data ||
+			     pskb_may_pull(skb, nh + offset + 12 - skb->data))) {
+				struct gre_base_hdr *gre_hdr;
+				__be32 *gre_key;
+
+				nh = skb_network_header(skb);
+				gre_hdr = (struct gre_base_hdr *)(nh + offset);
+				gre_key = (__be32 *)(gre_hdr + 1);
+
+				if (gre_hdr->flags & GRE_KEY) {
+					if (gre_hdr->flags & GRE_CSUM)
+						gre_key++;
+					fl6->fl6_gre_key = *gre_key;
+				}
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+
 #if IS_ENABLED(CONFIG_IPV6_MIP6)
 		case IPPROTO_MH:
 			offset += ipv6_optlen(exthdr);
@@ -3460,12 +3461,7 @@ decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
 			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;
 		}
@@ -3519,17 +3515,17 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	int xerr_idx = -1;
 	const struct xfrm_if_cb *ifcb;
 	struct sec_path *sp;
-	struct xfrm_if *xi;
 	u32 if_id = 0;
 
 	rcu_read_lock();
 	ifcb = xfrm_if_get_cb();
 
 	if (ifcb) {
-		xi = ifcb->decode_session(skb, family);
-		if (xi) {
-			if_id = xi->p.if_id;
-			net = xi->net;
+		struct xfrm_if_decode_session_result r;
+
+		if (ifcb->decode_session(skb, family, &r)) {
+			if_id = r.if_id;
+			net = r.net;
 		}
 	}
 	rcu_read_unlock();
@@ -3577,6 +3573,11 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	}
 
 	if (!pol) {
+		if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS);
+			return 0;
+		}
+
 		if (sp && secpath_has_nontransport(sp, 0, &xerr_idx)) {
 			xfrm_secpath_reject(xerr_idx, skb, &fl);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS);
@@ -3597,6 +3598,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		if (pols[1]) {
 			if (IS_ERR(pols[1])) {
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
+				xfrm_pol_put(pols[0]);
 				return 0;
 			}
 			pols[1]->curlft.use_time = ktime_get_real_seconds();
@@ -3631,6 +3633,13 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 				tpp[ti++] = &pols[pi]->xfrm_vec[i];
 		}
 		xfrm_nr = ti;
+
+		if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK &&
+		    !xfrm_nr) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
+			goto reject;
+		}
+
 		if (npols > 1) {
 			xfrm_tmpl_sort(stp, tpp, xfrm_nr, family);
 			tpp = stp;
@@ -3738,7 +3747,7 @@ static int stale_bundle(struct dst_entry *dst)
 void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
 {
 	while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) {
-		dst->dev = dev_net(dev)->loopback_dev;
+		dst->dev = blackhole_netdev;
 		dev_hold(dst->dev);
 		dev_put(dev);
 	}
@@ -4113,7 +4122,11 @@ static int __net_init xfrm_net_init(struct net *net)
 	/* Initialize the per-net locks here */
 	spin_lock_init(&net->xfrm.xfrm_state_lock);
 	spin_lock_init(&net->xfrm.xfrm_policy_lock);
+	seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock);
 	mutex_init(&net->xfrm.xfrm_cfg_mutex);
+	net->xfrm.policy_default[XFRM_POLICY_IN] = XFRM_USERPOLICY_ACCEPT;
+	net->xfrm.policy_default[XFRM_POLICY_FWD] = XFRM_USERPOLICY_ACCEPT;
+	net->xfrm.policy_default[XFRM_POLICY_OUT] = XFRM_USERPOLICY_ACCEPT;
 
 	rv = xfrm_statistics_init(net);
 	if (rv < 0)
@@ -4157,15 +4170,11 @@ void __init xfrm_init(void)
 {
 	register_pernet_subsys(&xfrm_net_ops);
 	xfrm_dev_init();
-	seqcount_init(&xfrm_policy_hash_generation);
 	xfrm_input_init();
 
-#ifdef CONFIG_INET_ESPINTCP
+#ifdef CONFIG_XFRM_ESPINTCP
 	espintcp_init();
 #endif
-
-	RCU_INIT_POINTER(xfrm_if_cb, NULL);
-	synchronize_rcu();
 }
 
 #ifdef CONFIG_AUDITSYSCALL
@@ -4256,7 +4265,7 @@ static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp,
 }
 
 static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel,
-						    u8 dir, u8 type, struct net *net)
+						    u8 dir, u8 type, struct net *net, u32 if_id)
 {
 	struct xfrm_policy *pol, *ret = NULL;
 	struct hlist_head *chain;
@@ -4265,7 +4274,8 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir);
 	hlist_for_each_entry(pol, chain, bydst) {
-		if (xfrm_migrate_selector_match(sel, &pol->selector) &&
+		if ((if_id == 0 || pol->if_id == if_id) &&
+		    xfrm_migrate_selector_match(sel, &pol->selector) &&
 		    pol->type == type) {
 			ret = pol;
 			priority = ret->priority;
@@ -4277,7 +4287,8 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *
 		if ((pol->priority >= priority) && ret)
 			break;
 
-		if (xfrm_migrate_selector_match(sel, &pol->selector) &&
+		if ((if_id == 0 || pol->if_id == if_id) &&
+		    xfrm_migrate_selector_match(sel, &pol->selector) &&
 		    pol->type == type) {
 			ret = pol;
 			break;
@@ -4393,7 +4404,7 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate)
 int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		 struct xfrm_migrate *m, int num_migrate,
 		 struct xfrm_kmaddress *k, struct net *net,
-		 struct xfrm_encap_tmpl *encap)
+		 struct xfrm_encap_tmpl *encap, u32 if_id)
 {
 	int i, err, nx_cur = 0, nx_new = 0;
 	struct xfrm_policy *pol = NULL;
@@ -4412,14 +4423,14 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	}
 
 	/* Stage 1 - find policy */
-	if ((pol = xfrm_migrate_policy_find(sel, dir, type, net)) == NULL) {
+	if ((pol = xfrm_migrate_policy_find(sel, dir, type, net, if_id)) == NULL) {
 		err = -ENOENT;
 		goto out;
 	}
 
 	/* Stage 2 - find and update state(s) */
 	for (i = 0, mp = m; i < num_migrate; i++, mp++) {
-		if ((x = xfrm_migrate_state_find(mp, net))) {
+		if ((x = xfrm_migrate_state_find(mp, net, if_id))) {
 			x_cur[nx_cur] = x;
 			nx_cur++;
 			xc = xfrm_state_migrate(x, mp, encap);