| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1411140380.26859.28.camel@edumazet-glaptop2.roam.corp.google.com>
Date: Fri, 19 Sep 2014 08:26:20 -0700
From: Eric Dumazet <eric.dumazet@...il.com>
To: David Miller <davem@...emloft.net>
Cc: netdev <netdev@...r.kernel.org>,
Neal Cardwell <ncardwell@...gle.com>,
Yuchung Cheng <ycheng@...gle.com>
Subject: [PATCH net-next] tcp: add coalescing attempt in tcp_ofo_queue()
From: Eric Dumazet <edumazet@...gle.com>
In order to make TCP more resilient in presence of reorders, we need
to allow coalescing to happen when skbs from out of order queue are
transferred into receive queue. LRO/GRO can be completely canceled
in some pathological cases, like per packet load balancing on aggregated
links.
I had to move tcp_try_coalesce() up in the file above tcp_ofo_queue()
Signed-off-by: Eric Dumazet <edumazet@...gle.com>
---
Note: I am not sure we really need this part in tcp_try_coalesce(),
as I doubt we need ack_seq in the skbs stored in receive queues ?
TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq;
net/ipv4/tcp_input.c | 89 +++++++++++++++++++++--------------------
1 file changed, 47 insertions(+), 42 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ea92f23ffaf1..44ff50aac96c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4060,6 +4060,44 @@ static void tcp_sack_remove(struct tcp_sock *tp)
tp->rx_opt.num_sacks = num_sacks;
}
+/**
+ * tcp_try_coalesce - try to merge skb to prior one
+ * @sk: socket
+ * @to: prior buffer
+ * @from: buffer to add in queue
+ * @fragstolen: pointer to boolean
+ *
+ * Before queueing skb @from after @to, try to merge them
+ * to reduce overall memory use and queue lengths, if cost is small.
+ * Packets in ofo or receive queues can stay a long time.
+ * Better try to coalesce them right now to avoid future collapses.
+ * Returns true if caller should free @from instead of queueing it
+ */
+static bool tcp_try_coalesce(struct sock *sk,
+ struct sk_buff *to,
+ struct sk_buff *from,
+ bool *fragstolen)
+{
+ int delta;
+
+ *fragstolen = false;
+
+ /* Its possible this segment overlaps with prior segment in queue */
+ if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
+ return false;
+
+ if (!skb_try_coalesce(to, from, fragstolen, &delta))
+ return false;
+
+ atomic_add(delta, &sk->sk_rmem_alloc);
+ sk_mem_charge(sk, delta);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRCVCOALESCE);
+ TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq;
+ TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq;
+ TCP_SKB_CB(to)->tcp_flags |= TCP_SKB_CB(from)->tcp_flags;
+ return true;
+}
+
/* This one checks to see if we can put data from the
* out_of_order queue into the receive_queue.
*/
@@ -4067,7 +4105,8 @@ static void tcp_ofo_queue(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
__u32 dsack_high = tp->rcv_nxt;
- struct sk_buff *skb;
+ struct sk_buff *skb, *tail;
+ bool fragstolen, eaten;
while ((skb = skb_peek(&tp->out_of_order_queue)) != NULL) {
if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
@@ -4080,9 +4119,9 @@ static void tcp_ofo_queue(struct sock *sk)
tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack);
}
+ __skb_unlink(skb, &tp->out_of_order_queue);
if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
SOCK_DEBUG(sk, "ofo packet was already received\n");
- __skb_unlink(skb, &tp->out_of_order_queue);
__kfree_skb(skb);
continue;
}
@@ -4090,11 +4129,15 @@ static void tcp_ofo_queue(struct sock *sk)
tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
TCP_SKB_CB(skb)->end_seq);
- __skb_unlink(skb, &tp->out_of_order_queue);
- __skb_queue_tail(&sk->sk_receive_queue, skb);
+ tail = skb_peek_tail(&sk->sk_receive_queue);
+ eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ if (!eaten)
+ __skb_queue_tail(&sk->sk_receive_queue, skb);
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
tcp_fin(sk);
+ if (eaten)
+ kfree_skb_partial(skb, fragstolen);
}
}
@@ -4121,44 +4164,6 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
return 0;
}
-/**
- * tcp_try_coalesce - try to merge skb to prior one
- * @sk: socket
- * @to: prior buffer
- * @from: buffer to add in queue
- * @fragstolen: pointer to boolean
- *
- * Before queueing skb @from after @to, try to merge them
- * to reduce overall memory use and queue lengths, if cost is small.
- * Packets in ofo or receive queues can stay a long time.
- * Better try to coalesce them right now to avoid future collapses.
- * Returns true if caller should free @from instead of queueing it
- */
-static bool tcp_try_coalesce(struct sock *sk,
- struct sk_buff *to,
- struct sk_buff *from,
- bool *fragstolen)
-{
- int delta;
-
- *fragstolen = false;
-
- /* Its possible this segment overlaps with prior segment in queue */
- if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
- return false;
-
- if (!skb_try_coalesce(to, from, fragstolen, &delta))
- return false;
-
- atomic_add(delta, &sk->sk_rmem_alloc);
- sk_mem_charge(sk, delta);
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRCVCOALESCE);
- TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq;
- TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq;
- TCP_SKB_CB(to)->tcp_flags |= TCP_SKB_CB(from)->tcp_flags;
- return true;
-}
-
static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists