From: Wright Feng <Wright.Feng@cypress.com>
To: "linux-wireless@vger.kernel.org" <linux-wireless@vger.kernel.org>
Cc: Wright Feng <Wright.Feng@cypress.com>,
"arend.vanspriel@broadcom.com" <arend.vanspriel@broadcom.com>,
"franky.lin@broadcom.com" <franky.lin@broadcom.com>,
"hante.meuleman@broadcom.com" <hante.meuleman@broadcom.com>,
"kvalo@codeaurora.org" <kvalo@codeaurora.org>,
Chi-Hsien Lin <Chi-Hsien.Lin@cypress.com>,
"brcm80211-dev-list.pdl@broadcom.com"
<brcm80211-dev-list.pdl@broadcom.com>
Subject: [PATCH 1/3] brcmfmac: calling skb_orphan before sending skb to SDIO bus
Date: Mon, 29 Oct 2018 10:27:15 +0000 [thread overview]
Message-ID: <1540808552-28738-2-git-send-email-wright.feng@cypress.com> (raw)
In-Reply-To: <1540808552-28738-1-git-send-email-wright.feng@cypress.com>
Linux 3.6 introduces TSQ which has a per socket threshold for TCP Tx
packets to reduce latency. In fcmode 1 and fcmode 2, host driver enqueues
skb in hanger and TCP doesn't push new skb until host frees the skb when
receiving fwstatus event. So using skb_orphan before sending skb to bus
will make the skb removing the ownership of socket. With this patch, we
are able to get better throughput in fcmode 1 and fcmode 2.
Tested 43455 TCP throughput in 20 MHz bandwidth with / without this patch.
fcmode 0: 59.5 / 59.6 (mbps)
fcmode 1: 59.3 / 23.4 (mbps)
fcmode 2: 59.6 / 21.5 (mbps)
Signed-off-by: Wright Feng <wright.feng@cypress.com>
---
drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index b2e1ab5..519b25d 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -2298,6 +2298,7 @@ static uint brcmf_sdio_sendfromq(struct brcmf_sdio *bus, uint maxframes)
&prec_out);
if (pkt == NULL)
break;
+ skb_orphan(pkt);
__skb_queue_tail(&pktq, pkt);
}
spin_unlock_bh(&bus->txq_lock);
--
1.9.1
next prev parent reply other threads:[~2018-10-29 10:27 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-29 10:27 [PATCH 0/3] brcmfmac: throughput enhancement for SDIO and flow control mode Wright Feng
2018-10-29 10:27 ` Wright Feng [this message]
2018-10-29 18:50 ` [PATCH 1/3] brcmfmac: calling skb_orphan before sending skb to SDIO bus Franky Lin
2018-11-02 3:08 ` Wright Feng
2018-11-02 19:51 ` Franky Lin
2018-11-03 1:36 ` Wright Feng
2018-10-29 10:27 ` [PATCH 2/3] brcmfmac: add credit numbers updating support Wright Feng
2018-10-30 11:04 ` Arend van Spriel
2018-11-02 7:54 ` Wright Feng
2018-10-29 10:27 ` [PATCH 3/3] brcmfmac: make firmware frameburst mode a module parameter Wright Feng
2018-10-30 11:33 ` Arend van Spriel
2018-11-02 3:22 ` Wright Feng
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1540808552-28738-2-git-send-email-wright.feng@cypress.com \
--to=wright.feng@cypress.com \
--cc=Chi-Hsien.Lin@cypress.com \
--cc=arend.vanspriel@broadcom.com \
--cc=brcm80211-dev-list.pdl@broadcom.com \
--cc=franky.lin@broadcom.com \
--cc=hante.meuleman@broadcom.com \
--cc=kvalo@codeaurora.org \
--cc=linux-wireless@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).