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

Steffen Klassert says:

====================
pull request (net): ipsec 2016-05-04

1) The flowcache can hit an OOM condition if too
   many entries are in the gc_list. Fix this by
   counting the entries in the gc_list and refuse
   new allocations if the value is too high.

2) The inner headers are invalid after a xfrm transformation,
   so reset the skb encapsulation field to ensure nobody tries
   access the inner headers. Otherwise tunnel devices stacked
   on top of xfrm may build the outer headers based on wrong
   informations.

3) Add pmtu handling to vti, we need it to report
   pmtu informations for local generated packets.

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

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

4 files changed, 35 insertions, 1 deletions

diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 730d82ad6ee52..24cd3949a9a4f 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -80,6 +80,7 @@ struct netns_xfrm {
 	struct flow_cache	flow_cache_global;
 	atomic_t		flow_cache_genid;
 	struct list_head	flow_cache_gc_list;
+	atomic_t		flow_cache_gc_count;
 	spinlock_t		flow_cache_gc_lock;
 	struct work_struct	flow_cache_gc_work;
 	struct work_struct	flow_cache_flush_work;
diff --git a/net/core/flow.c b/net/core/flow.c
index 1033725be40bd..3937b1b68d5bc 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -92,8 +92,11 @@ static void flow_cache_gc_task(struct work_struct *work)
 	list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list);
 	spin_unlock_bh(&xfrm->flow_cache_gc_lock);
 
-	list_for_each_entry_safe(fce, n, &gc_list, u.gc_list)
+	list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) {
 		flow_entry_kill(fce, xfrm);
+		atomic_dec(&xfrm->flow_cache_gc_count);
+		WARN_ON(atomic_read(&xfrm->flow_cache_gc_count) < 0);
+	}
 }
 
 static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
@@ -101,6 +104,7 @@ static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
 				     struct netns_xfrm *xfrm)
 {
 	if (deleted) {
+		atomic_add(deleted, &xfrm->flow_cache_gc_count);
 		fcp->hash_count -= deleted;
 		spin_lock_bh(&xfrm->flow_cache_gc_lock);
 		list_splice_tail(gc_list, &xfrm->flow_cache_gc_list);
@@ -232,6 +236,13 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
 		if (fcp->hash_count > fc->high_watermark)
 			flow_cache_shrink(fc, fcp);
 
+		if (fcp->hash_count > 2 * fc->high_watermark ||
+		    atomic_read(&net->xfrm.flow_cache_gc_count) > fc->high_watermark) {
+			atomic_inc(&net->xfrm.flow_cache_genid);
+			flo = ERR_PTR(-ENOBUFS);
+			goto ret_object;
+		}
+
 		fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC);
 		if (fle) {
 			fle->net = net;
@@ -446,6 +457,7 @@ int flow_cache_init(struct net *net)
 	INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task);
 	INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task);
 	mutex_init(&net->xfrm.flow_flush_sem);
+	atomic_set(&net->xfrm.flow_cache_gc_count, 0);
 
 	fc->hash_shift = 10;
 	fc->low_watermark = 2 * flow_cache_hash_size(fc);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 5cf10b777b7e4..a917903d5e974 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -156,6 +156,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;	/* Device to other host */
 	int err;
+	int mtu;
 
 	if (!dst) {
 		dev->stats.tx_carrier_errors++;
@@ -192,6 +193,23 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 			tunnel->err_count = 0;
 	}
 
+	mtu = dst_mtu(dst);
+	if (skb->len > mtu) {
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+		if (skb->protocol == htons(ETH_P_IP)) {
+			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+				  htonl(mtu));
+		} else {
+			if (mtu < IPV6_MIN_MTU)
+				mtu = IPV6_MIN_MTU;
+
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		}
+
+		dst_release(dst);
+		goto tx_error;
+	}
+
 	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
 	skb_dst_set(skb, dst);
 	skb->dev = skb_dst(skb)->dev;
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index ff4a91fcab9fd..637387bbaaea3 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -99,6 +99,9 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
 
 		skb_dst_force(skb);
 
+		/* Inner headers are invalid now. */
+		skb->encapsulation = 0;
+
 		err = x->type->output(x, skb);
 		if (err == -EINPROGRESS)
 			goto out;