ip: add helpers to process in-order fragments faster.

This patch introduces several helper functions/macros that will be
used in the follow-up patch. No runtime changes yet.

The new logic (fully implemented in the second patch) is as follows:

* Nodes in the rb-tree will now contain not single fragments, but lists
  of consecutive fragments ("runs").

* At each point in time, the current "active" run at the tail is
  maintained/tracked. Fragments that arrive in-order, adjacent
  to the previous tail fragment, are added to this tail run without
  triggering the re-balancing of the rb-tree.

* If a fragment arrives out of order with the offset _before_ the tail run,
  it is inserted into the rb-tree as a single fragment.

* If a fragment arrives after the current tail fragment (with a gap),
  it starts a new "tail" run, as is inserted into the rb-tree
  at the end as the head of the new run.

skb->cb is used to store additional information
needed here (suggested by Eric Dumazet).

Reported-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 353c9cb360874e737fb000545f783df756c06f9a)
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

2 files changed, 79 insertions, 0 deletions

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 1ff0433d94a7..a3812e9c8fee 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -56,7 +56,9 @@ struct frag_v6_compare_key {
  * @lock: spinlock protecting this frag
  * @refcnt: reference count of the queue
  * @fragments: received fragments head
+ * @rb_fragments: received fragments rb-tree root
  * @fragments_tail: received fragments tail
+ * @last_run_head: the head of the last "run". see ip_fragment.c
  * @stamp: timestamp of the last received fragment
  * @len: total length of the original datagram
  * @meat: length of received fragments so far
@@ -77,6 +79,7 @@ struct inet_frag_queue {
 	struct sk_buff		*fragments;  /* Used in IPv6. */
 	struct rb_root		rb_fragments; /* Used in IPv4. */
 	struct sk_buff		*fragments_tail;
+	struct sk_buff		*last_run_head;
 	ktime_t			stamp;
 	int			len;
 	int			meat;
@@ -112,6 +115,9 @@ void inet_frag_kill(struct inet_frag_queue *q);
 void inet_frag_destroy(struct inet_frag_queue *q);
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
 
+/* Free all skbs in the queue; return the sum of their truesizes. */
+unsigned int inet_frag_rbtree_purge(struct rb_root *root);
+
 static inline void inet_frag_put(struct inet_frag_queue *q)
 {
 	if (atomic_dec_and_test(&q->refcnt))
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 11d3dc649ef0..5e2121b82588 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -56,6 +56,57 @@
  */
 static const char ip_frag_cache_name[] = "ip4-frags";
 
+/* Use skb->cb to track consecutive/adjacent fragments coming at
+ * the end of the queue. Nodes in the rb-tree queue will
+ * contain "runs" of one or more adjacent fragments.
+ *
+ * Invariants:
+ * - next_frag is NULL at the tail of a "run";
+ * - the head of a "run" has the sum of all fragment lengths in frag_run_len.
+ */
+struct ipfrag_skb_cb {
+	struct inet_skb_parm	h;
+	struct sk_buff		*next_frag;
+	int			frag_run_len;
+};
+
+#define FRAG_CB(skb)		((struct ipfrag_skb_cb *)((skb)->cb))
+
+static void ip4_frag_init_run(struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb));
+
+	FRAG_CB(skb)->next_frag = NULL;
+	FRAG_CB(skb)->frag_run_len = skb->len;
+}
+
+/* Append skb to the last "run". */
+static void ip4_frag_append_to_last_run(struct inet_frag_queue *q,
+					struct sk_buff *skb)
+{
+	RB_CLEAR_NODE(&skb->rbnode);
+	FRAG_CB(skb)->next_frag = NULL;
+
+	FRAG_CB(q->last_run_head)->frag_run_len += skb->len;
+	FRAG_CB(q->fragments_tail)->next_frag = skb;
+	q->fragments_tail = skb;
+}
+
+/* Create a new "run" with the skb. */
+static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb)
+{
+	if (q->last_run_head)
+		rb_link_node(&skb->rbnode, &q->last_run_head->rbnode,
+			     &q->last_run_head->rbnode.rb_right);
+	else
+		rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node);
+	rb_insert_color(&skb->rbnode, &q->rb_fragments);
+
+	ip4_frag_init_run(skb);
+	q->fragments_tail = skb;
+	q->last_run_head = skb;
+}
+
 /* Describe an entry in the "incomplete datagrams" queue. */
 struct ipq {
 	struct inet_frag_queue q;
@@ -652,6 +703,28 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 }
 EXPORT_SYMBOL(ip_check_defrag);
 
+unsigned int inet_frag_rbtree_purge(struct rb_root *root)
+{
+	struct rb_node *p = rb_first(root);
+	unsigned int sum = 0;
+
+	while (p) {
+		struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
+
+		p = rb_next(p);
+		rb_erase(&skb->rbnode, root);
+		while (skb) {
+			struct sk_buff *next = FRAG_CB(skb)->next_frag;
+
+			sum += skb->truesize;
+			kfree_skb(skb);
+			skb = next;
+		}
+	}
+	return sum;
+}
+EXPORT_SYMBOL(inet_frag_rbtree_purge);
+
 #ifdef CONFIG_SYSCTL
 static int dist_min;