Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec

Steffen Klassert says:

====================
pull request (net): ipsec 2018-03-13

1) Refuse to insert 32 bit userspace socket policies on 64
   bit systems like we do it for standard policies. We don't
   have a compat layer, so inserting socket policies from
   32 bit userspace will lead to a broken configuration.

2) Make the policy hold queue work without the flowcache.
   Dummy bundles are not chached anymore, so we need to
   generate a new one on each lookup as long as the SAs
   are not yet in place.

3) Fix the validation of the esn replay attribute. The
   The sanity check in verify_replay() is bypassed if
   the XFRM_STATE_ESN flag is not set. Fix this by doing
   the sanity check uncoditionally.
   From Florian Westphal.

4) After most of the dst_entry garbage collection code
   is removed, we may leak xfrm_dst entries as they are
   neither cached nor tracked somewhere. Fix this by
   reusing the 'uncached_list' to track xfrm_dst entries
   too. From Xin Long.

5) Fix a rcu_read_lock/rcu_read_unlock imbalance in
   xfrm_get_tos() From Xin Long.

6) Fix an infinite loop in xfrm_get_dst_nexthop. On
   transport mode we fetch the child dst_entry after
   we continue, so this pointer is never updated.
   Fix this by fetching it before we continue.

7) Fix ESN sequence number gap after IPsec GSO packets.
    We accidentally increment the sequence number counter
    on the xfrm_state by one packet too much in the ESN
    case. Fix this by setting the sequence number to the
    correct value.

8) Reset the ethernet protocol after decapsulation only if a
   mac header was set. Otherwise it breaks configurations
   with TUN devices. From Yossi Kuperman.

9) Fix __this_cpu_read() usage in preemptible code. Use
   this_cpu_read() instead in ipcomp_alloc_tfms().
   From Greg Hackmann.

Please pull or let me know if there are problems.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 50 insertions, 33 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 860b3fd..f9dbb8c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1393,7 +1393,7 @@ struct uncached_list {
 
 static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list);
 
-static void rt_add_uncached_list(struct rtable *rt)
+void rt_add_uncached_list(struct rtable *rt)
 {
 	struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list);
 
@@ -1404,14 +1404,8 @@ static void rt_add_uncached_list(struct rtable *rt)
 	spin_unlock_bh(&ul->lock);
 }
 
-static void ipv4_dst_destroy(struct dst_entry *dst)
+void rt_del_uncached_list(struct rtable *rt)
 {
-	struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
-	struct rtable *rt = (struct rtable *) dst;
-
-	if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
-		kfree(p);
-
 	if (!list_empty(&rt->rt_uncached)) {
 		struct uncached_list *ul = rt->rt_uncached_list;
 
@@ -1421,6 +1415,17 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
 	}
 }
 
+static void ipv4_dst_destroy(struct dst_entry *dst)
+{
+	struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
+	struct rtable *rt = (struct rtable *)dst;
+
+	if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
+		kfree(p);
+
+	rt_del_uncached_list(rt);
+}
+
 void rt_flush_dev(struct net_device *dev)
 {
 	struct net *net = dev_net(dev);
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 63faeee..2a9764b 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -92,7 +92,8 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 
 	skb_reset_network_header(skb);
 	skb_mac_header_rebuild(skb);
-	eth_hdr(skb)->h_proto = skb->protocol;
+	if (skb->mac_len)
+		eth_hdr(skb)->h_proto = skb->protocol;
 
 	err = 0;
 
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 05017e2..8d33f7b 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -102,6 +102,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	xdst->u.rt.rt_pmtu = rt->rt_pmtu;
 	xdst->u.rt.rt_table_id = rt->rt_table_id;
 	INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
+	rt_add_uncached_list(&xdst->u.rt);
 
 	return 0;
 }
@@ -241,7 +242,8 @@ static void xfrm4_dst_destroy(struct dst_entry *dst)
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 
 	dst_destroy_metrics_generic(dst);
-
+	if (xdst->u.rt.rt_uncached_list)
+		rt_del_uncached_list(&xdst->u.rt);
 	xfrm_dst_destroy(xdst);
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0db4218..b3c1137 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -128,7 +128,7 @@ struct uncached_list {
 
 static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list);
 
-static void rt6_uncached_list_add(struct rt6_info *rt)
+void rt6_uncached_list_add(struct rt6_info *rt)
 {
 	struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list);
 
@@ -139,7 +139,7 @@ static void rt6_uncached_list_add(struct rt6_info *rt)
 	spin_unlock_bh(&ul->lock);
 }
 
-static void rt6_uncached_list_del(struct rt6_info *rt)
+void rt6_uncached_list_del(struct rt6_info *rt)
 {
 	if (!list_empty(&rt->rt6i_uncached)) {
 		struct uncached_list *ul = rt->rt6i_uncached_list;
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index bb935a3..de1b0b8 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -92,7 +92,8 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 
 	skb_reset_network_header(skb);
 	skb_mac_header_rebuild(skb);
-	eth_hdr(skb)->h_proto = skb->protocol;
+	if (skb->mac_len)
+		eth_hdr(skb)->h_proto = skb->protocol;
 
 	err = 0;
 
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 09fb44e..416fe67 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -113,6 +113,9 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway;
 	xdst->u.rt6.rt6i_dst = rt->rt6i_dst;
 	xdst->u.rt6.rt6i_src = rt->rt6i_src;
+	INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached);
+	rt6_uncached_list_add(&xdst->u.rt6);
+	atomic_inc(&dev_net(dev)->ipv6.rt6_stats->fib_rt_uncache);
 
 	return 0;
 }
@@ -244,6 +247,8 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
 	if (likely(xdst->u.rt6.rt6i_idev))
 		in6_dev_put(xdst->u.rt6.rt6i_idev);
 	dst_destroy_metrics_generic(dst);
+	if (xdst->u.rt6.rt6i_uncached_list)
+		rt6_uncached_list_del(&xdst->u.rt6);
 	xfrm_dst_destroy(xdst);
 }
 
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
index ccfdc71..a00ec71 100644
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -283,7 +283,7 @@ static struct crypto_comp * __percpu *ipcomp_alloc_tfms(const char *alg_name)
 		struct crypto_comp *tfm;
 
 		/* This can be any valid CPU ID so we don't need locking. */
-		tfm = __this_cpu_read(*pos->tfms);
+		tfm = this_cpu_read(*pos->tfms);
 
 		if (!strcmp(crypto_comp_name(tfm), alg_name)) {
 			pos->users++;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 7a23078..625b3fc 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1458,10 +1458,13 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl,
 static int xfrm_get_tos(const struct flowi *fl, int family)
 {
 	const struct xfrm_policy_afinfo *afinfo;
-	int tos = 0;
+	int tos;
 
 	afinfo = xfrm_policy_get_afinfo(family);
-	tos = afinfo ? afinfo->get_tos(fl) : 0;
+	if (!afinfo)
+		return 0;
+
+	tos = afinfo->get_tos(fl);
 
 	rcu_read_unlock();
 
@@ -1891,7 +1894,7 @@ static void xfrm_policy_queue_process(struct timer_list *t)
 	spin_unlock(&pq->hold_queue.lock);
 
 	dst_hold(xfrm_dst_path(dst));
-	dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, 0);
+	dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, XFRM_LOOKUP_QUEUE);
 	if (IS_ERR(dst))
 		goto purge_queue;
 
@@ -2729,14 +2732,14 @@ static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst,
 	while (dst->xfrm) {
 		const struct xfrm_state *xfrm = dst->xfrm;
 
+		dst = xfrm_dst_child(dst);
+
 		if (xfrm->props.mode == XFRM_MODE_TRANSPORT)
 			continue;
 		if (xfrm->type->flags & XFRM_TYPE_REMOTE_COADDR)
 			daddr = xfrm->coaddr;
 		else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR))
 			daddr = &xfrm->id.daddr;
-
-		dst = xfrm_dst_child(dst);
 	}
 	return daddr;
 }
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
index 1d38c6a..9e3a5e85 100644
--- a/net/xfrm/xfrm_replay.c
+++ b/net/xfrm/xfrm_replay.c
@@ -660,7 +660,7 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff
 		} else {
 			XFRM_SKB_CB(skb)->seq.output.low = oseq + 1;
 			XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi;
-			xo->seq.low = oseq = oseq + 1;
+			xo->seq.low = oseq + 1;
 			xo->seq.hi = oseq_hi;
 			oseq += skb_shinfo(skb)->gso_segs;
 		}
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 54e21f1..f9d2f22 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2056,6 +2056,11 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen
 	struct xfrm_mgr *km;
 	struct xfrm_policy *pol = NULL;
 
+#ifdef CONFIG_COMPAT
+	if (in_compat_syscall())
+		return -EOPNOTSUPP;
+#endif
+
 	if (!optval && !optlen) {
 		xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL);
 		xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 7f52b8e..080035f 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -121,22 +121,17 @@ static inline int verify_replay(struct xfrm_usersa_info *p,
 	struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL];
 	struct xfrm_replay_state_esn *rs;
 
-	if (p->flags & XFRM_STATE_ESN) {
-		if (!rt)
-			return -EINVAL;
+	if (!rt)
+		return (p->flags & XFRM_STATE_ESN) ? -EINVAL : 0;
 
-		rs = nla_data(rt);
+	rs = nla_data(rt);
 
-		if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8)
-			return -EINVAL;
-
-		if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) &&
-		    nla_len(rt) != sizeof(*rs))
-			return -EINVAL;
-	}
+	if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8)
+		return -EINVAL;
 
-	if (!rt)
-		return 0;
+	if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) &&
+	    nla_len(rt) != sizeof(*rs))
+		return -EINVAL;
 
 	/* As only ESP and AH support ESN feature. */
 	if ((p->id.proto != IPPROTO_ESP) && (p->id.proto != IPPROTO_AH))