From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, Dmitri Epshtein <dima@marvell.com>,
Marcin Wojtas <mw@semihalf.com>, Willy Tarreau <w@1wt.eu>,
"David S. Miller" <davem@davemloft.net>
Subject: [PATCH 3.14 21/21] net: mvneta: set real interrupt per packet for tx_done
Date: Mon, 8 Aug 2016 21:09:52 +0200 [thread overview]
Message-ID: <20160808180144.814635309@linuxfoundation.org> (raw)
In-Reply-To: <20160808180143.919366850@linuxfoundation.org>
3.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dmitri Epshtein <dima@marvell.com>
commit 06708f81528725148473c0869d6af5f809c6824b upstream.
Commit aebea2ba0f74 ("net: mvneta: fix Tx interrupt delay") intended to
set coalescing threshold to a value guaranteeing interrupt generation
per each sent packet, so that buffers can be released with no delay.
In fact setting threshold to '1' was wrong, because it causes interrupt
every two packets. According to the documentation a reason behind it is
following - interrupt occurs once sent buffers counter reaches a value,
which is higher than one specified in MVNETA_TXQ_SIZE_REG(q). This
behavior was confirmed during tests. Also when testing the SoC working
as a NAS device, better performance was observed with int-per-packet,
as it strongly depends on the fact that all transmitted packets are
released immediately.
This commit enables NETA controller work in interrupt per sent packet mode
by setting coalescing threshold to 0.
Signed-off-by: Dmitri Epshtein <dima@marvell.com>
Signed-off-by: Marcin Wojtas <mw@semihalf.com>
Fixes aebea2ba0f74 ("net: mvneta: fix Tx interrupt delay")
Acked-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/net/ethernet/marvell/mvneta.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -213,7 +213,7 @@
/* Various constants */
/* Coalescing */
-#define MVNETA_TXDONE_COAL_PKTS 1
+#define MVNETA_TXDONE_COAL_PKTS 0 /* interrupt per packet */
#define MVNETA_RX_COAL_PKTS 32
#define MVNETA_RX_COAL_USEC 100
next prev parent reply other threads:[~2016-08-08 19:09 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20160808191004uscas1p26944bddcdda269e11e609e5ab288a7dc@uscas1p2.samsung.com>
2016-08-08 19:09 ` [PATCH 3.14 00/21] 3.14.75-stable review Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 01/21] fs/nilfs2: fix potential underflow in call to crc32_le Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 02/21] arc: unwind: warn only once if DW2_UNWIND is disabled Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 03/21] xen/pciback: Fix conf_space read/write overlap check Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 07/21] Input: wacom_w8001 - w8001_MAX_LENGTH should be 13 Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 08/21] Input: xpad - validate USB endpoint count during probe Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 09/21] pinctrl: single: Fix missing flush of posted write for a wakeirq Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 10/21] Revert "ecryptfs: forbid opening files without mmap handler" Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 11/21] ecryptfs: dont allow mmap when the lower fs doesnt support it Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 12/21] ARC: use ASL assembler mnemonic Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 13/21] ext4: verify extent header depth Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 14/21] qeth: delete napi struct when removing a qeth device Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 15/21] mmc: block: fix packed command header endianness Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 16/21] can: at91_can: RX queue could get stuck at high bus load Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 17/21] can: fix handling of unmodifiable configuration options fix Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 18/21] can: fix oops caused by wrong rtnl dellink usage Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 19/21] ipr: Clear interrupt on croc/crocodile when running with LSI Greg Kroah-Hartman
2016-08-08 19:09 ` [PATCH 3.14 20/21] libceph: apply new_state before new_up_client on incrementals Greg Kroah-Hartman
2016-08-08 19:09 ` Greg Kroah-Hartman [this message]
2016-08-09 4:16 ` [PATCH 3.14 00/21] 3.14.75-stable review Guenter Roeck
2016-08-09 8:19 ` Greg Kroah-Hartman
2016-08-09 15:09 ` Shuah Khan
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=20160808180144.814635309@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=davem@davemloft.net \
--cc=dima@marvell.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mw@semihalf.com \
--cc=stable@vger.kernel.org \
--cc=w@1wt.eu \
/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).