From: Andrew Lunn <andrew@lunn.ch>
To: Marek Vasut <marex@denx.de>
Cc: Lukas Wunner <lukas@wunner.de>,
netdev@vger.kernel.org, "David S . Miller" <davem@davemloft.net>,
Petr Stetiar <ynezz@true.cz>, YueHaibing <yuehaibing@huawei.com>
Subject: Re: [PATCH V4 07/19] net: ks8851: Remove ks8851_rdreg32()
Date: Mon, 20 Apr 2020 17:50:57 +0200 [thread overview]
Message-ID: <20200420155057.GC917792@lunn.ch> (raw)
In-Reply-To: <0edb18eb-0c18-c3cd-a0b7-4ba23428f354@denx.de>
On Mon, Apr 20, 2020 at 05:38:16PM +0200, Marek Vasut wrote:
> On 4/20/20 4:44 PM, Lukas Wunner wrote:
> > On Mon, Apr 20, 2020 at 04:24:05PM +0200, Marek Vasut wrote:
> >> On 4/20/20 4:20 PM, Lukas Wunner wrote:
> >>> On Mon, Apr 20, 2020 at 04:12:59PM +0200, Marek Vasut wrote:
> >>>> On 4/20/20 4:07 PM, Lukas Wunner wrote:
> >>>>> On Tue, Apr 14, 2020 at 08:20:17PM +0200, Marek Vasut wrote:
> >>>>>> The ks8851_rdreg32() is used only in one place, to read two registers
> >>>>>> using a single read. To make it easier to support 16-bit accesses via
> >>>>>> parallel bus later on, replace this single read with two 16-bit reads
> >>>>>> from each of the registers and drop the ks8851_rdreg32() altogether.
> >>>>>>
> >>>>>> If this has noticeable performance impact on the SPI variant of KS8851,
> >>>>>> then we should consider using regmap to abstract the SPI and parallel
> >>>>>> bus options and in case of SPI, permit regmap to merge register reads
> >>>>>> of neighboring registers into single, longer, read.
> >>>>>
> >>>>> Bisection has shown this patch to be the biggest cause of the performance
> >>>>> regression introduced by this series: Latency increases by about 9 usec.
> >>>>
> >>>> Just for completeness, did you perform this bisect on current linux-next
> >>>> without any patches except this series OR your patched rpi downstream
> >>>> vendor tree Linux 4.19 with preempt-rt patch applied ?
> >>>
> >>> The latter because latency without CONFIG_PREEMPT_RT_FULL=y is too imprecise
> >>> to really see the difference and that's the configuration we care about.
> >>
> >> Why am I not able to see the same on the RPi3 then ?
> >> How can I replicate this observation ?
> >
> > Compile this branch with CONFIG_PREEMPT_RT_FULL=y:
> >
> > https://github.com/l1k/linux/commits/revpi-4.19-marek-v4
> >
> > Alternatively, download this file:
> >
> > http://wunner.de/ks8851-marekv4.tar
> >
> > Install the "raspberrypi-kernel" deb-package included in the tarball on a
> > stock Raspbian image and copy one of the included ks8851.ko to:
> > /lib/modules/4.19.95-rt38-v7+/kernel/drivers/net/ethernet/micrel
>
> Why don't you rather try to replicate this problem in linux-next?
Hi Lukas
4.19 is dead in terms of development work. It is now over 18 months
old. All mainline development work is done against either the last
-rc1 kernel, or a subsystems specific 'for-next' branch.
Please test Marek patches against net-next. If there are performance
regressions with net-next, they should be addressed, but mainline does
not care about some random long time dead tree.
Andrew
next prev parent reply other threads:[~2020-04-20 15:51 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-28 0:31 [PATCH V3 00/18] net: ks8851: Unify KS8851 SPI and MLL drivers Marek Vasut
2020-03-28 0:31 ` [PATCH V3 01/18] net: ks8851: Factor out spi->dev in probe()/remove() Marek Vasut
2020-03-28 0:31 ` [PATCH V3 02/18] net: ks8851: Rename ndev to netdev in probe Marek Vasut
2020-03-28 0:31 ` [PATCH V3 03/18] net: ks8851: Replace dev_err() with netdev_err() in IRQ handler Marek Vasut
2020-03-28 0:31 ` [PATCH V3 04/18] net: ks8851: Pass device node into ks8851_init_mac() Marek Vasut
2020-03-28 0:31 ` [PATCH V3 05/18] net: ks8851: Use devm_alloc_etherdev() Marek Vasut
2020-03-28 0:31 ` [PATCH V3 06/18] net: ks8851: Use dev_{get,set}_drvdata() Marek Vasut
2020-03-28 0:31 ` [PATCH V3 07/18] net: ks8851: Remove ks8851_rdreg32() Marek Vasut
2020-03-28 0:31 ` [PATCH V3 08/18] net: ks8851: Use 16-bit writes to program MAC address Marek Vasut
2020-03-28 0:31 ` [PATCH V3 09/18] net: ks8851: Use 16-bit read of RXFC register Marek Vasut
2020-03-28 0:31 ` [PATCH V3 10/18] net: ks8851: Factor out bus lock handling Marek Vasut
2020-03-28 0:31 ` [PATCH V3 11/18] net: ks8851: Factor out SKB receive function Marek Vasut
2020-03-28 0:31 ` [PATCH V3 12/18] net: ks8851: Split out SPI specific entries in struct ks8851_net Marek Vasut
2020-03-28 0:31 ` [PATCH V3 13/18] net: ks8851: Split out SPI specific code from probe() and remove() Marek Vasut
2020-03-28 0:31 ` [PATCH V3 14/18] net: ks8851: Factor out TX work flush function Marek Vasut
2020-03-28 0:31 ` [PATCH V3 15/18] net: ks8851: Permit overridding interrupt enable register Marek Vasut
2020-03-28 0:31 ` [PATCH V3 16/18] net: ks8851: Separate SPI operations into separate file Marek Vasut
2020-03-28 2:45 ` kbuild test robot
2020-03-28 4:11 ` kbuild test robot
2020-03-28 0:31 ` [PATCH V3 17/18] net: ks8851: Implement Parallel bus operations Marek Vasut
2020-03-28 0:31 ` [PATCH V3 18/18] net: ks8851: Remove ks8851_mll.c Marek Vasut
2020-03-29 16:15 ` [PATCH V3 00/18] net: ks8851: Unify KS8851 SPI and MLL drivers Marek Vasut
2020-04-06 3:16 ` Lukas Wunner
2020-04-06 11:20 ` Marek Vasut
2020-04-08 19:49 ` Marek Vasut
2020-04-10 11:01 ` Lukas Wunner
2020-04-10 18:10 ` Marek Vasut
2020-04-14 18:20 ` [PATCH V4 00/19] " Marek Vasut
2020-04-14 18:20 ` [PATCH V4 01/19] net: ks8851: Factor out spi->dev in probe()/remove() Marek Vasut
2020-04-14 18:20 ` [PATCH V4 02/19] net: ks8851: Rename ndev to netdev in probe Marek Vasut
2020-04-14 18:20 ` [PATCH V4 03/19] net: ks8851: Replace dev_err() with netdev_err() in IRQ handler Marek Vasut
2020-04-14 18:20 ` [PATCH V4 04/19] net: ks8851: Pass device node into ks8851_init_mac() Marek Vasut
2020-04-14 18:20 ` [PATCH V4 05/19] net: ks8851: Use devm_alloc_etherdev() Marek Vasut
2020-04-14 18:20 ` [PATCH V4 06/19] net: ks8851: Use dev_{get,set}_drvdata() Marek Vasut
2020-04-14 18:20 ` [PATCH V4 07/19] net: ks8851: Remove ks8851_rdreg32() Marek Vasut
2020-04-20 14:07 ` Lukas Wunner
2020-04-20 14:12 ` Marek Vasut
2020-04-20 14:20 ` Lukas Wunner
2020-04-20 14:24 ` Marek Vasut
2020-04-20 14:44 ` Lukas Wunner
2020-04-20 15:38 ` Marek Vasut
2020-04-20 15:50 ` Andrew Lunn [this message]
2020-05-07 14:22 ` Marek Vasut
2020-04-14 18:20 ` [PATCH V4 08/19] net: ks8851: Use 16-bit writes to program MAC address Marek Vasut
2020-04-14 18:20 ` [PATCH V4 09/19] net: ks8851: Use 16-bit read of RXFC register Marek Vasut
2020-04-14 18:20 ` [PATCH V4 10/19] net: ks8851: Factor out bus lock handling Marek Vasut
2020-04-14 18:20 ` [PATCH V4 11/19] net: ks8851: Factor out SKB receive function Marek Vasut
2020-04-14 18:20 ` [PATCH V4 12/19] net: ks8851: Split out SPI specific entries in struct ks8851_net Marek Vasut
2020-04-14 18:20 ` [PATCH V4 13/19] net: ks8851: Split out SPI specific code from probe() and remove() Marek Vasut
2020-04-14 18:20 ` [PATCH V4 14/19] net: ks8851: Factor out TX work flush function Marek Vasut
2020-04-14 18:20 ` [PATCH V4 15/19] net: ks8851: Permit overridding interrupt enable register Marek Vasut
2020-04-14 18:20 ` [PATCH V4 16/19] net: ks8851: Implement register, FIFO, lock accessor callbacks Marek Vasut
2020-04-14 18:20 ` [PATCH V4 17/19] net: ks8851: Separate SPI operations into separate file Marek Vasut
2020-04-15 14:56 ` Lukas Wunner
2020-04-16 9:58 ` Marek Vasut
2020-04-14 18:20 ` [PATCH V4 18/19] net: ks8851: Implement Parallel bus operations Marek Vasut
2020-04-14 18:20 ` [PATCH V4 19/19] net: ks8851: Remove ks8851_mll.c Marek Vasut
2020-04-14 20:13 ` [PATCH V4 00/19] net: ks8851: Unify KS8851 SPI and MLL drivers David Miller
2020-04-15 14:39 ` Lukas Wunner
2020-04-15 14:51 ` Marek Vasut
2020-04-15 15:12 ` Lukas Wunner
2020-04-16 10:18 ` Marek Vasut
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=20200420155057.GC917792@lunn.ch \
--to=andrew@lunn.ch \
--cc=davem@davemloft.net \
--cc=lukas@wunner.de \
--cc=marex@denx.de \
--cc=netdev@vger.kernel.org \
--cc=ynezz@true.cz \
--cc=yuehaibing@huawei.com \
/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).