tcp: CVE-2018-5390

tcp: free batches of packets in tcp_prune_ofo_queue()

Reference:
https://nvd.nist.gov/vuln/detail/CVE-2018-5390
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=linux-4.14.y&id=f3a5ba6310e11df370f6888ed716d1486896d983

Change-Id: Ia58e99e96a8d07e081c92b3e6d206ffb44dd4a7d
Signed-off-by: Andreas Wellving <andreas.wellving@enea.com>

1 files changed, 98 insertions, 0 deletions

diff --git a/patches/cve/CVE-2018-5390-tcp-free-batches-of-packets-in-tcp_prune_ofo_queue.patch b/patches/cve/CVE-2018-5390-tcp-free-batches-of-packets-in-tcp_prune_ofo_queue.patch
new file mode 100644
index 0000000..f13f1f1
--- /dev/null
+++ b/patches/cve/CVE-2018-5390-tcp-free-batches-of-packets-in-tcp_prune_ofo_queue.patch
@@ -0,0 +1,98 @@
+From f3a5ba6310e11df370f6888ed716d1486896d983 Mon Sep 17 00:00:00 2001
+From: Eric Dumazet <edumazet@google.com>
+Date: Mon, 23 Jul 2018 09:28:17 -0700
+Subject: [PATCH] tcp: free batches of packets in tcp_prune_ofo_queue()
+
+[ Upstream commit 72cd43ba64fc172a443410ce01645895850844c8 ]
+
+Juha-Matti Tilli reported that malicious peers could inject tiny
+packets in out_of_order_queue, forcing very expensive calls
+to tcp_collapse_ofo_queue() and tcp_prune_ofo_queue() for
+every incoming packet. out_of_order_queue rb-tree can contain
+thousands of nodes, iterating over all of them is not nice.
+
+Before linux-4.9, we would have pruned all packets in ofo_queue
+in one go, every XXXX packets. XXXX depends on sk_rcvbuf and skbs
+truesize, but is about 7000 packets with tcp_rmem[2] default of 6 MB.
+
+Since we plan to increase tcp_rmem[2] in the future to cope with
+modern BDP, can not revert to the old behavior, without great pain.
+
+Strategy taken in this patch is to purge ~12.5 % of the queue capacity.
+
+Fixes: 36a6503fedda ("tcp: refine tcp_prune_ofo_queue() to not drop all packets")
+
+CVE: CVE-2018-5390
+Upstream-Status: Backport [https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=linux-4.14.y&id=f3a5ba6310e11df370f6888ed716d1486896d983]
+
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Reported-by: Juha-Matti Tilli <juha-matti.tilli@iki.fi>
+Acked-by: Yuchung Cheng <ycheng@google.com>
+Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+Signed-off-by: Andreas Wellving <andreas.wellving@enea.com>
+---
+ include/linux/skbuff.h |  2 ++
+ net/ipv4/tcp_input.c   | 15 +++++++++++----
+ 2 files changed, 13 insertions(+), 4 deletions(-)
+
+diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
+index 9cf971c68401..6dd77767fd5b 100644
+--- a/include/linux/skbuff.h
++++ b/include/linux/skbuff.h
+@@ -3167,6 +3167,8 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len)
+        return __skb_grow(skb, len);
+ }
+ 
++#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode)
++
+ #define skb_queue_walk(queue, skb) \
+                for (skb = (queue)->next;                                       \
+                     skb != (struct sk_buff *)(queue);                          \
+diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
+index 03fd2ff4007b..1e7175bd3b59 100644
+--- a/net/ipv4/tcp_input.c
++++ b/net/ipv4/tcp_input.c
+@@ -4924,6 +4924,7 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
+  * 2) not add too big latencies if thousands of packets sit there.
+  *    (But if application shrinks SO_RCVBUF, we could still end up
+  *     freeing whole queue here)
++ * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
+  *
+  * Return true if queue has shrunk.
+  */
+@@ -4931,20 +4932,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
+ {
+        struct tcp_sock *tp = tcp_sk(sk);
+        struct rb_node *node, *prev;
++       int goal;
+ 
+        if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
+                return false;
+ 
+        NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
++       goal = sk->sk_rcvbuf >> 3;
+        node = &tp->ooo_last_skb->rbnode;
+        do {
+                prev = rb_prev(node);
+                rb_erase(node, &tp->out_of_order_queue);
++               goal -= rb_to_skb(node)->truesize;
+                tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode));
+-               sk_mem_reclaim(sk);
+-               if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+-                   !tcp_under_memory_pressure(sk))
+-                       break;
++               if (!prev || goal <= 0) {
++                       sk_mem_reclaim(sk);
++                       if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
++                           !tcp_under_memory_pressure(sk))
++                               break;
++                       goal = sk->sk_rcvbuf >> 3;
++               }
+                node = prev;
+        } while (node);
+        tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode);
+-- 
+2.20.1
+