Linux IOMMU Development
 help / color / mirror / Atom feed
From: John Garry <john.g.garry@oracle.com>
To: Jerry Snitselaar <jsnitsel@redhat.com>, Joerg Roedel <joro@8bytes.org>
Cc: Vasant Hegde <vasant.hegde@amd.com>,
	Peng Zhang <zhangpeng.00@bytedance.com>,
	Robin Murphy <robin.murphy@arm.com>,
	will@kernel.org, iommu@lists.linux.dev,
	linux-kernel@vger.kernel.org, Li Bin <huawei.libin@huawei.com>,
	Xie XiuQi <xiexiuqi@huawei.com>,
	Yang Yingliang <yangyingliang@huawei.com>,
	Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Subject: Re: [PATCH] iommu: Avoid softlockup and rcu stall in fq_flush_timeout().
Date: Mon, 22 May 2023 16:35:34 +0100	[thread overview]
Message-ID: <57017dea-c453-82bc-18b1-79663e77552d@oracle.com> (raw)
In-Reply-To: <vxxh3laqaavyxx3f2c65k7zui6wkahm6fspy6hvwpofsxtialo@ne7za5hvlgk2>

On 22/05/2023 16:18, Jerry Snitselaar wrote:
>> My guess is that the allocations are too big and not covered by the
>> allocation sizes supported by the flush-queue code. But maybe this is
>> something that can be fixed. Or the flush-queue code could even be
>> changed to auto-adapt to allocation patterns of the device driver?
>>
>> Regards,
>>
>> 	Joerg
> In the case I know of it involved some proprietary test suites
> (Hazard I/O, and Medusa?), and the lpfc driver. I was able to force
> the condition using fio with a number of jobs running. I'll play
> around and see if I can figure out a point where it starts to become
> an issue.
> 
> I mentioned what the nvme driver did to the Broadcom folks for the max
> dma size, but I haven't had a chance to go looking at it myself yet to
> see if there is somewhere in the lpfc code to fix up.

JFYI, SCSI core already supports setting this in shost->opt_sectors, see 
example in sas_host_setup().

This issue may continue to pop up so we may need a better way to turn it 
on/off for all drivers or classes of drivers.

John

      reply	other threads:[~2023-05-22 15:36 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-16  7:11 [PATCH] iommu: Avoid softlockup and rcu stall in fq_flush_timeout() Peng Zhang
2023-02-16  8:49 ` Hillf Danton
2023-02-16 11:02   ` Peng Zhang
2023-02-16 11:44     ` Hillf Danton
2023-04-10 22:22 ` Jerry Snitselaar
2023-04-18 10:41   ` Vasant Hegde
2023-04-28  5:44     ` Vasant Hegde
2023-05-22 14:58       ` Joerg Roedel
2023-05-22 15:18         ` Jerry Snitselaar
2023-05-22 15:35           ` John Garry [this message]

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=57017dea-c453-82bc-18b1-79663e77552d@oracle.com \
    --to=john.g.garry@oracle.com \
    --cc=huawei.libin@huawei.com \
    --cc=iommu@lists.linux.dev \
    --cc=joro@8bytes.org \
    --cc=jsnitsel@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=robin.murphy@arm.com \
    --cc=suravee.suthikulpanit@amd.com \
    --cc=vasant.hegde@amd.com \
    --cc=will@kernel.org \
    --cc=xiexiuqi@huawei.com \
    --cc=yangyingliang@huawei.com \
    --cc=zhangpeng.00@bytedance.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