From: Robin Murphy <robin.murphy@arm.com>
To: Mark Brown <broonie@kernel.org>
Cc: "moderated list:BROADCOM BCM2711/BCM2835 ARM ARCHITECTURE"
<linux-arm-kernel@lists.infradead.org>,
"open list:OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS"
<devicetree@vger.kernel.org>,
Florian Fainelli <f.fainelli@gmail.com>,
Scott Branden <sbranden@broadcom.com>,
lukas@wunner.de, Ray Jui <rjui@broadcom.com>,
linux-kernel@vger.kernel.org,
"open list:SPI SUBSYSTEM" <linux-spi@vger.kernel.org>,
Rob Herring <robh+dt@kernel.org>,
"maintainer:BROADCOM BCM281XX/BCM11XXX/BCM216XX ARM ARCHITE..."
<bcm-kernel-feedback-list@broadcom.com>,
"moderated list:BROADCOM BCM2711/BCM2835 ARM ARCHITECTURE"
<linux-rpi-kernel@lists.infradead.org>,
Martin Sperl <kernel@martin.sperl.org>,
Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Subject: Re: [PATCH v2] spi: bcm2835: Enable shared interrupt support
Date: Fri, 5 Jun 2020 15:41:27 +0100 [thread overview]
Message-ID: <06342e88-e130-ad7a-9f97-94f09156f868@arm.com> (raw)
In-Reply-To: <2e371a32-fb52-03a2-82e4-5733d9f139cc@arm.com>
On 2020-06-05 14:46, Robin Murphy wrote:
> On 2020-06-05 14:20, Mark Brown wrote:
>> On Fri, Jun 05, 2020 at 12:34:36PM +0100, Robin Murphy wrote:
>>> On 2020-06-04 22:28, Florian Fainelli wrote:
>>
>>>> For the BCM2835 case which is deemed performance critical, we would
>>>> like
>>>> to continue using an interrupt handler which does not have the extra
>>>> comparison on BCM2835_SPI_CS_INTR.
>>
>>> FWIW, if I'm reading the patch correctly, then with sensible codegen
>>> that
>>> "overhead" should amount to a bit test on a live register plus a
>>> not-taken
>>> conditional branch - according to the 1176 TRM that should add up to a
>>> whopping 2 cycles. If that's really significant then I'd have to wonder
>>> whether you want to be at the mercy of the whole generic IRQ stack at
>>> all,
>>> and should perhaps consider using FIQ instead.
>>
>> Yes, and indeed the compiler does seem to manage that. It *is* non-zero
>> overhead though.
>
> True, but so's the existing level of pointer-chasing indirection that
> with some straightforward refactoring could be taken right out of the
> critical path and confined to just the conditional complete() call.
> That's the kind of thing leaving me unconvinced that this is code where
> every single cycle counts ;)
Ha, and in fact having checked a build out of curiosity, this patch
as-is actually stands to make things considerably worse. At least with
GCC 8.3 and bcm2835_defconfig, bcm2835_spi_interrupt_common() doesn't
get inlined, which means bcm2835_spi_interrupt() pushes/pops a stack
frame and makes an out-of-line call to bcm2835_spi_interrupt_common(),
resulting in massively *more* work than the extra two instructions of
simply inlining the test.
So yes, the overhead of inlining the test vs. the alternative is indeed
non-zero. It's just also negative :D
Robin.
next prev parent reply other threads:[~2020-06-05 14:41 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-04 21:28 [PATCH v2] spi: bcm2835: Enable shared interrupt support Florian Fainelli
2020-06-05 8:46 ` Nicolas Saenz Julienne
2020-06-05 10:52 ` Mark Brown
2020-06-05 10:58 ` Nicolas Saenz Julienne
2020-06-05 10:51 ` Lukas Wunner
2020-06-05 11:14 ` Mark Brown
2020-06-05 12:20 ` Mark Brown
2020-06-05 11:34 ` Robin Murphy
2020-06-05 13:20 ` Mark Brown
2020-06-05 13:46 ` Robin Murphy
2020-06-05 14:41 ` Robin Murphy [this message]
2020-06-05 15:27 ` Mark Brown
2020-06-05 22:04 ` Florian Fainelli
2020-06-08 11:11 ` Robin Murphy
2020-06-08 11:28 ` Mark Brown
2020-06-15 16:34 ` Florian Fainelli
2020-06-15 17:00 ` Mark Brown
2020-06-15 17:04 ` Florian Fainelli
2020-06-15 17:30 ` Mark Brown
2020-06-15 17:31 ` Robin Murphy
2020-06-15 19:26 ` Mark Brown
2020-06-08 11:41 ` Lukas Wunner
2020-06-15 19:09 ` Robin Murphy
2020-06-15 19:42 ` Florian Fainelli
2020-06-15 20:48 ` Mark Brown
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=06342e88-e130-ad7a-9f97-94f09156f868@arm.com \
--to=robin.murphy@arm.com \
--cc=bcm-kernel-feedback-list@broadcom.com \
--cc=broonie@kernel.org \
--cc=devicetree@vger.kernel.org \
--cc=f.fainelli@gmail.com \
--cc=kernel@martin.sperl.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rpi-kernel@lists.infradead.org \
--cc=linux-spi@vger.kernel.org \
--cc=lukas@wunner.de \
--cc=nsaenzjulienne@suse.de \
--cc=rjui@broadcom.com \
--cc=robh+dt@kernel.org \
--cc=sbranden@broadcom.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).