From: Sudeep Holla <sudeep.holla@arm.com>
To: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Rob Herring <robh@kernel.org>,
Jassi Brar <jassisinghbrar@gmail.com>,
Arnd Bergmann <arnd@arndb.de>,
Frank Rowand <frowand.list@gmail.com>,
Bjorn Andersson <bjorn.andersson@linaro.org>,
Vincent Guittot <vincent.guittot@linaro.org>,
linux-arm-kernel@lists.infradead.org, devicetree@vger.kernel.org,
Sudeep Holla <sudeep.holla@arm.com>,
linux-kernel@vger.kernel.org
Subject: Re: [RFC] dt-bindings: mailbox: add doorbell support to ARM MHU
Date: Wed, 3 Jun 2020 19:04:35 +0100 [thread overview]
Message-ID: <20200603180435.GB23722@bogus> (raw)
In-Reply-To: <20200529040758.kneg2j4n3gxh2rfv@vireshk-i7>
On Fri, May 29, 2020 at 09:37:58AM +0530, Viresh Kumar wrote:
> On 28-05-20, 13:20, Rob Herring wrote:
> > Whether Linux
> > requires serializing mailbox accesses is a separate issue. On that side,
> > it seems silly to not allow driving the h/w in the most efficient way
> > possible.
>
> That's exactly what we are trying to say. The hardware allows us to
> write all 32 bits in parallel, without any hardware issues, why
> shouldn't we do that ? The delay (which Sudeep will find out, he is
> facing issues with hardware access because of lockdown right now)
OK, I was able to access the setup today. I couldn't reach a point
where I can do measurements as the system just became unusable with
one physical channel instead of 2 virtual channels as in my patches.
My test was simple. Switch to schedutil and read sensors periodically
via sysfs.
arm-scmi firmware:scmi: message for 1 is not expected!
arm-scmi firmware:scmi: timed out in resp(caller: scmi_sensor_reading_get+0xf4/0x120)
arm-scmi firmware:scmi: timed out in resp(caller: scmi_sensor_reading_get+0xf4/0x120)
arm-scmi firmware:scmi: message for 1 is not expected!
arm-scmi firmware:scmi: timed out in resp(caller: scmi_sensor_reading_get+0xf4/0x120)
arm-scmi firmware:scmi: message for 1 is not expected!
With trace enabled I can see even cpufreq_set timing out. Sample trace
output:
bash-1019 [005] 1149.452340: scmi_xfer_begin: transfer_id=1537 msg_id=7 protocol_id=19 seq=0 poll=1
bash-1019 [005] 1149.452407: scmi_xfer_end: transfer_id=1537 msg_id=7 protocol_id=19 seq=0 status=0
bash-1526 [000] 1149.472553: scmi_xfer_begin: transfer_id=1538 msg_id=6 protocol_id=21 seq=0 poll=0
<idle>-0 [001] 1149.472733: scmi_xfer_begin: transfer_id=1539 msg_id=7 protocol_id=19 seq=1 poll=1
<idle>-0 [001] 1149.472842: scmi_xfer_end: transfer_id=1539 msg_id=7 protocol_id=19 seq=1 status=-110
<idle>-0 [001] 1149.483040: scmi_xfer_begin: transfer_id=1540 msg_id=7 protocol_id=19 seq=1 poll=1
<idle>-0 [001] 1149.483043: scmi_xfer_end: transfer_id=1540 msg_id=7 protocol_id=19 seq=1 status=0
rs:main-543 [003] 1149.493031: scmi_xfer_begin: transfer_id=1541 msg_id=7 protocol_id=19 seq=1 poll=1
rs:main-543 [003] 1149.493047: scmi_xfer_end: transfer_id=1541 msg_id=7 protocol_id=19 seq=1 status=0
<idle>-0 [000] 1149.507033: scmi_xfer_begin: transfer_id=1542 msg_id=7 protocol_id=19 seq=1 poll=1
<idle>-0 [000] 1149.507044: scmi_xfer_end: transfer_id=1542 msg_id=7 protocol_id=19 seq=1 status=0
bash-1526 [000] 1149.516068: scmi_xfer_end: transfer_id=1538 msg_id=6 protocol_id=21 seq=0 status=-110
bash-1526 [000] 1149.516559: scmi_xfer_begin: transfer_id=1543 msg_id=6 protocol_id=21 seq=0 poll=0
<idle>-0 [001] 1149.516729: scmi_xfer_begin: transfer_id=1544 msg_id=7 protocol_id=19 seq=1 poll=1
<idle>-0 [001] 1149.516837: scmi_xfer_end: transfer_id=1544 msg_id=7 protocol_id=19 seq=1 status=-110
ksoftirqd/0-9 [000] 1149.519065: scmi_xfer_begin: transfer_id=1545 msg_id=7 protocol_id=19 seq=1 poll=1
ksoftirqd/0-9 [000] 1149.519072: scmi_xfer_end: transfer_id=1545 msg_id=7 protocol_id=19 seq=1 status=0
<idle>-0 [001] 1149.526878: scmi_xfer_begin: transfer_id=1546 msg_id=7 protocol_id=19 seq=1 poll=1
<idle>-0 [001] 1149.526882: scmi_xfer_end: transfer_id=1546 msg_id=7 protocol_id=19 seq=1 status=0
<idle>-0 [000] 1149.551119: scmi_xfer_begin: transfer_id=1547 msg_id=7 protocol_id=19 seq=1 poll=1
<idle>-0 [000] 1149.551138: scmi_xfer_end: transfer_id=1547 msg_id=7 protocol_id=19 seq=1 status=0
bash-1526 [000] 1149.560191: scmi_xfer_end: transfer_id=1543 msg_id=6 protocol_id=21 seq=0 status=-110
bash-1526 [000] 1149.560690: scmi_xfer_begin: transfer_id=1548 msg_id=6 protocol_id=21 seq=0 poll=0
<idle>-0 [001] 1149.560859: scmi_xfer_begin: transfer_id=1549 msg_id=7 protocol_id=19 seq=1 poll=1
<idle>-0 [001] 1149.560968: scmi_xfer_end: transfer_id=1549 msg_id=7 protocol_id=19 seq=1 status=-110
protocol_id=19 is cpufreq and 21 is sensor. This is simplest test and
I can easily generate more timeouts starting some stress test with DVFS.
--
Regards,
Sudeep
next prev parent reply other threads:[~2020-06-03 18:04 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-15 5:17 [RFC] dt-bindings: mailbox: add doorbell support to ARM MHU Viresh Kumar
2020-05-15 16:46 ` Jassi Brar
2020-05-18 7:35 ` Viresh Kumar
2020-05-19 0:53 ` Jassi Brar
2020-05-19 4:39 ` Viresh Kumar
2020-05-19 1:29 ` Bjorn Andersson
2020-05-19 3:40 ` Viresh Kumar
2020-05-19 4:05 ` Jassi Brar
2020-06-03 18:31 ` Sudeep Holla
2020-06-03 18:42 ` Jassi Brar
2020-06-03 18:28 ` Sudeep Holla
2020-05-28 19:20 ` Rob Herring
2020-05-29 4:07 ` Viresh Kumar
2020-06-03 18:04 ` Sudeep Holla [this message]
2020-06-03 18:17 ` Sudeep Holla
2020-06-04 5:59 ` Viresh Kumar
2020-06-04 8:28 ` Sudeep Holla
2020-06-03 18:32 ` Jassi Brar
2020-06-04 9:20 ` Sudeep Holla
2020-06-04 15:15 ` Jassi Brar
2020-06-05 4:56 ` Sudeep Holla
2020-06-05 6:30 ` Jassi Brar
2020-06-05 8:58 ` Sudeep Holla
2020-06-05 15:42 ` Jassi Brar
2020-06-10 9:33 ` Viresh Kumar
2020-06-11 10:00 ` Sudeep Holla
2020-06-12 0:34 ` Jassi Brar
2020-06-12 5:28 ` Viresh Kumar
2020-09-08 9:14 ` Arnd Bergmann
2020-09-08 9:27 ` Viresh Kumar
2020-09-08 13:26 ` Sudeep Holla
2020-09-09 3:23 ` Jassi Brar
2020-09-09 4:46 ` Viresh Kumar
2020-09-09 9:31 ` Sudeep Holla
2020-05-29 5:20 ` Jassi Brar
2020-05-29 6:27 ` Viresh Kumar
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=20200603180435.GB23722@bogus \
--to=sudeep.holla@arm.com \
--cc=arnd@arndb.de \
--cc=bjorn.andersson@linaro.org \
--cc=devicetree@vger.kernel.org \
--cc=frowand.list@gmail.com \
--cc=jassisinghbrar@gmail.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=robh@kernel.org \
--cc=vincent.guittot@linaro.org \
--cc=viresh.kumar@linaro.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).