aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorEric Dumazet2018-07-23 09:28:17 -0700
committerDavid S. Miller2018-07-23 12:01:36 -0700
commit72cd43ba64fc172a443410ce01645895850844c8 (patch)
tree37fdff3fb8646f8324564338ee992ddb1d3bb980
parent3dd1c9a1270736029ffca670e9bd0265f4120600 (diff)
tcp: free batches of packets in tcp_prune_ofo_queue()
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") 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>
-rw-r--r--net/ipv4/tcp_input.c15
1 files changed, 11 insertions, 4 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6bade06aaf72..64e45b279431 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4942,6 +4942,7 @@ new_range:
* 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.
*/
@@ -4949,20 +4950,26 @@ 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_to_skb(node));
- 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_to_skb(prev);