[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20140114004637.27138.50365.stgit@viggo.jf.intel.com>
Date: Mon, 13 Jan 2014 16:47:14 -0800
From: Dan Williams <dan.j.williams@...el.com>
To: dmaengine@...r.kernel.org
Cc: Hideaki YOSHIFUJI <yoshfuji@...ux-ipv6.org>,
netdev@...r.kernel.org, Ali Saidi <saidi@...in.umich.edu>,
James Morris <jmorris@...ei.org>,
"David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Alexey Kuznetsov <kuznet@....inr.ac.ru>,
Dave Jones <davej@...hat.com>,
Neal Cardwell <ncardwell@...gle.com>,
Patrick McHardy <kaber@...sh.net>, linux-kernel@...r.kernel.org
Subject: [PATCH v3 2/4] net_dma: revert 'copied_early'
Now that tcp_dma_try_early_copy() is gone nothing ever sets
copied_early.
Also reverts "53240c208776 tcp: Fix possible double-ack w/ user dma"
since it is no longer necessary.
Cc: Ali Saidi <saidi@...in.umich.edu>
Cc: James Morris <jmorris@...ei.org>
Cc: Patrick McHardy <kaber@...sh.net>
Cc: Eric Dumazet <edumazet@...gle.com>
Cc: David S. Miller <davem@...emloft.net>
Cc: Alexey Kuznetsov <kuznet@....inr.ac.ru>
Cc: Hideaki YOSHIFUJI <yoshfuji@...ux-ipv6.org>
Cc: Neal Cardwell <ncardwell@...gle.com>
Reported-by: Dave Jones <davej@...hat.com>
Signed-off-by: Dan Williams <dan.j.williams@...el.com>
---
Looking for an ack for this one, no changes since v2.
net/ipv4/tcp_input.c | 22 ++++++++--------------
1 files changed, 8 insertions(+), 14 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 33ef18e550c5..15911a280485 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5145,19 +5145,15 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
}
} else {
int eaten = 0;
- int copied_early = 0;
bool fragstolen = false;
- if (tp->copied_seq == tp->rcv_nxt &&
- len - tcp_header_len <= tp->ucopy.len) {
- if (tp->ucopy.task == current &&
- sock_owned_by_user(sk) && !copied_early) {
- __set_current_state(TASK_RUNNING);
+ if (tp->ucopy.task == current &&
+ tp->copied_seq == tp->rcv_nxt &&
+ len - tcp_header_len <= tp->ucopy.len &&
+ sock_owned_by_user(sk)) {
+ __set_current_state(TASK_RUNNING);
- if (!tcp_copy_to_iovec(sk, skb, tcp_header_len))
- eaten = 1;
- }
- if (eaten) {
+ if (!tcp_copy_to_iovec(sk, skb, tcp_header_len)) {
/* Predicted packet is in window by definition.
* seq == rcv_nxt and rcv_wup <= rcv_nxt.
* Hence, check seq<=rcv_wup reduces to:
@@ -5173,9 +5169,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
__skb_pull(skb, tcp_header_len);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITSTOUSER);
+ eaten = 1;
}
- if (copied_early)
- tcp_cleanup_rbuf(sk, skb->len);
}
if (!eaten) {
if (tcp_checksum_complete_user(sk, skb))
@@ -5212,8 +5207,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
goto no_ack;
}
- if (!copied_early || tp->rcv_nxt != tp->rcv_wup)
- __tcp_ack_snd_check(sk, 0);
+ __tcp_ack_snd_check(sk, 0);
no_ack:
if (eaten)
kfree_skb_partial(skb, fragstolen);
--
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