From: Joerg Roedel <joro-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
To: Jan Vesely <jan.vesely-kgbqMDwikbSVc3sceRu5cw@public.gmane.org>
Cc: Tom Lendacky <thomas.lendacky-5C7GfCeVMHo@public.gmane.org>,
"Nath, Arindam" <Arindam.Nath-5C7GfCeVMHo@public.gmane.org>,
"iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org"
<iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org>,
Craig Stein <stein12c-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Subject: Re: [PATCH v1 3/3] iommu/amd: Optimize the IOMMU queue flush
Date: Mon, 26 Jun 2017 14:14:30 +0200 [thread overview]
Message-ID: <20170626121430.GX30388@8bytes.org> (raw)
In-Reply-To: <1498227647.17007.31.camel-kgbqMDwikbSVc3sceRu5cw@public.gmane.org>
On Fri, Jun 23, 2017 at 10:20:47AM -0400, Jan Vesely wrote:
> I was able to trigger "Completion-Wait loop timed out" messages in the
> following situation:
> Hung OpenCL task running on dGPU.
> dGPU goes to sleep.
> sigterm to hung task.
> it seems to recover OK after the dGPU is powered back on
How does that 'dGPU goes to sleep' work? Do you put it to sleep manually
via sysfs or something? Or is that something that amdgpu does on its
own?
It looks like the GPU just switches the ATS unit off when it goes to
sleep and doesn't answer the invalidation anymore, which explains the
completion-wait timeouts.
Joerg
next prev parent reply other threads:[~2017-06-26 12:14 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-06-05 19:52 [PATCH v1 0/3] iommu/amd: AMD IOMMU performance updates 2017-06-05 Tom Lendacky
[not found] ` <20170605195203.11512.20579.stgit-qCXWGYdRb2BnqfbPTmsdiZQ+2ll4COg0XqFh9Ls21Oc@public.gmane.org>
2017-06-05 19:52 ` [PATCH v1 1/3] iommu/amd: Reduce amount of MMIO when submitting commands Tom Lendacky
2017-06-05 19:52 ` [PATCH v1 2/3] iommu/amd: Reduce delay waiting for command buffer space Tom Lendacky
2017-06-05 19:52 ` [PATCH v1 3/3] iommu/amd: Optimize the IOMMU queue flush Tom Lendacky
[not found] ` <20170605195235.11512.52995.stgit-qCXWGYdRb2BnqfbPTmsdiZQ+2ll4COg0XqFh9Ls21Oc@public.gmane.org>
2017-06-06 10:02 ` Nath, Arindam
[not found] ` <MWHPR12MB15181A6A020ACA2F53DF70339CCB0-Gy0DoCVfaSXKu+HfpMNLNQdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2017-06-08 20:33 ` Jan Vesely
[not found] ` <1496954035.4188.1.camel-kgbqMDwikbSVc3sceRu5cw@public.gmane.org>
2017-06-08 23:31 ` Craig Stein
2017-06-21 16:20 ` Jan Vesely
[not found] ` <1498062018.17007.6.camel-kgbqMDwikbSVc3sceRu5cw@public.gmane.org>
2017-06-21 17:01 ` Tom Lendacky
[not found] ` <bf685f44-019c-4c21-25d4-6a6ea647b7cc-5C7GfCeVMHo@public.gmane.org>
2017-06-21 21:09 ` Jan Vesely
[not found] ` <1498079371.17007.18.camel-kgbqMDwikbSVc3sceRu5cw@public.gmane.org>
2017-06-22 9:20 ` Joerg Roedel
[not found] ` <20170622092053.GV30388-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2017-06-22 15:13 ` Jan Vesely
[not found] ` <1498144389.17007.25.camel-kgbqMDwikbSVc3sceRu5cw@public.gmane.org>
2017-06-22 21:57 ` Joerg Roedel
[not found] ` <20170622215735.GW30388-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2017-06-23 14:20 ` Jan Vesely
[not found] ` <1498227647.17007.31.camel-kgbqMDwikbSVc3sceRu5cw@public.gmane.org>
2017-06-26 12:14 ` Joerg Roedel [this message]
[not found] ` <20170626121430.GX30388-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2017-06-27 16:24 ` Jan Vesely
[not found] ` <1498580675.10525.3.camel-kgbqMDwikbSVc3sceRu5cw@public.gmane.org>
2017-06-28 8:36 ` Joerg Roedel
[not found] ` <20170628083659.GA30388-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2017-06-28 22:14 ` Deucher, Alexander
[not found] ` <BN6PR12MB16525D2E89F4AB61DC36EFBEF7DD0-/b2+HYfkarQqUD6E6FAiowdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2017-07-04 16:29 ` Craig Stein
2017-06-06 12:05 ` Joerg Roedel
[not found] ` <20170606120516.GD30388-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2017-06-06 13:36 ` Tom Lendacky
[not found] ` <85356483-1d5e-251f-57e3-d9f761239100-5C7GfCeVMHo@public.gmane.org>
2017-06-07 14:03 ` Tom Lendacky
[not found] ` <32599b14-c138-3c89-6834-0335fec0b3f6-5C7GfCeVMHo@public.gmane.org>
2017-06-07 14:17 ` Joerg Roedel
2017-06-08 12:43 ` [PATCH v1 0/3] iommu/amd: AMD IOMMU performance updates 2017-06-05 Joerg Roedel
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=20170626121430.GX30388@8bytes.org \
--to=joro-zlv9swrftaidnm+yrofe0a@public.gmane.org \
--cc=Arindam.Nath-5C7GfCeVMHo@public.gmane.org \
--cc=iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org \
--cc=jan.vesely-kgbqMDwikbSVc3sceRu5cw@public.gmane.org \
--cc=stein12c-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org \
--cc=thomas.lendacky-5C7GfCeVMHo@public.gmane.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