inet: limit length of fragment queue hash table bucket lists

This patch introduces a constant limit of the fragment queue hash
table bucket list lengths. Currently the limit 128 is choosen somewhat
arbitrary and just ensures that we can fill up the fragment cache with
empty packets up to the default ip_frag_high_thresh limits. It should
just protect from list iteration eating considerable amounts of cpu.

If we reach the maximum length in one hash bucket a warning is printed.
This is implemented on the caller side of inet_frag_find to distinguish
between the different users of inet_fragment.c.

I dropped the out of memory warning in the ipv4 fragment lookup path,
because we already get a warning by the slab allocator.

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Jesper Dangaard Brouer <jbrouer@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/inet_frag.h

@@ -43,6 +43,13 @@ struct inet_frag_queue {
 
 #define INETFRAGS_HASHSZ		64
 
+/* averaged:
+ * max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ /
+ *	       rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or
+ *	       struct frag_queue))
+ */
+#define INETFRAGS_MAXDEPTH		128
+
 struct inet_frags {
 	struct hlist_head	hash[INETFRAGS_HASHSZ];
 	/* This rwlock is a global lock (seperate per IPv4, IPv6 and
@@ -76,6 +83,8 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force);
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 		struct inet_frags *f, void *key, unsigned int hash)
 	__releases(&f->lock);
+void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
+				   const char *prefix);
 
 static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f)
 {

net/ipv4/inet_fragment.c

@@ -21,6 +21,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/slab.h>
 
+#include <net/sock.h>
 #include <net/inet_frag.h>
 
 static void inet_frag_secret_rebuild(unsigned long dummy)
@@ -277,6 +278,7 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 	__releases(&f->lock)
 {
 	struct inet_frag_queue *q;
+	int depth = 0;
 
 	hlist_for_each_entry(q, &f->hash[hash], list) {
 		if (q->net == nf && f->match(q, key)) {
@@ -284,9 +286,25 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 			read_unlock(&f->lock);
 			return q;
 		}
+		depth++;
 	}
 	read_unlock(&f->lock);
 
+	if (depth <= INETFRAGS_MAXDEPTH)
 		return inet_frag_create(nf, f, key);
+	else
+		return ERR_PTR(-ENOBUFS);
 }
 EXPORT_SYMBOL(inet_frag_find);
+
+void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
+				   const char *prefix)
+{
+	static const char msg[] = "inet_frag_find: Fragment hash bucket"
+		" list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
+		". Dropping fragment.\n";
+
+	if (PTR_ERR(q) == -ENOBUFS)
+		LIMIT_NETDEBUG(KERN_WARNING "%s%s", prefix, msg);
+}
+EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);

net/ipv4/ip_fragment.c

@@ -292,14 +292,11 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user)
 	hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
 
 	q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
-	if (q == NULL)
-		goto out_nomem;
-
-	return container_of(q, struct ipq, q);
-
-out_nomem:
-	LIMIT_NETDEBUG(KERN_ERR pr_fmt("ip_frag_create: no memory left !\n"));
+	if (IS_ERR_OR_NULL(q)) {
+		inet_frag_maybe_warn_overflow(q, pr_fmt());
 		return NULL;
+	}
+	return container_of(q, struct ipq, q);
 }
 
 /* Is the fragment too far ahead to be part of ipq? */

net/ipv6/netfilter/nf_conntrack_reasm.c

@@ -14,6 +14,8 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) "IPv6-nf: " fmt
+
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/string.h>
@@ -180,13 +182,11 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
 
 	q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
 	local_bh_enable();
-	if (q == NULL)
-		goto oom;
-
-	return container_of(q, struct frag_queue, q);
-
-oom:
+	if (IS_ERR_OR_NULL(q)) {
+		inet_frag_maybe_warn_overflow(q, pr_fmt());
 		return NULL;
+	}
+	return container_of(q, struct frag_queue, q);
 }
 
 

net/ipv6/reassembly.c

@@ -26,6 +26,9 @@
  *	YOSHIFUJI,H. @USAGI	Always remove fragment header to
  *				calculate ICV correctly.
  */
+
+#define pr_fmt(fmt) "IPv6: " fmt
+
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/string.h>
@@ -185,9 +188,10 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src, const struct in6
 	hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd);
 
 	q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
-	if (q == NULL)
+	if (IS_ERR_OR_NULL(q)) {
+		inet_frag_maybe_warn_overflow(q, pr_fmt());
 		return NULL;
-
+	}
 	return container_of(q, struct frag_queue, q);
 }