From: Ming Lei <ming.lei@redhat.com>
To: "Raphael S. Carvalho" <raphaelsc@scylladb.com>
Cc: guazhang@redhat.com, hch@lst.de, linux-block@vger.kernel.org,
linux-nvme@lists.infradead.org
Subject: Re: About 'nvme-pci: fix DMA direction of unmapping integrity data'
Date: Thu, 30 Nov 2023 08:16:24 +0800 [thread overview]
Message-ID: <ZWfUWPsJ7AAOzqHR@fedora> (raw)
In-Reply-To: <CAKhLTr2PjPnNDccbc8OMy3fSc_U1Dk7GS+UWLUkj0zWwzcp4zw@mail.gmail.com>
On Wed, Nov 29, 2023 at 11:56:50AM -0300, Raphael S. Carvalho wrote:
> I am observing a problem where disk writes are apparently being
> misdirected. File system metadata ends up in file data range for
> example.
Please raise one report in linux-block or linux-nvme if you are asking
for help, and include the following info:
1) kernel release version
2) related drivers or device, nvme or scsi, or dm/md, and how to setup
the device
3) filesystem
4) exact reproduction steps
5) expected result
6) actual result, such as how you conclude that WRITE is misdirected
BTW, is it similar with the following one?
https://bugzilla.kernel.org/show_bug.cgi?id=218158
>
> I am not completely certain about the problem "nvme-pci: fix DMA
> direction of unmapping integrity data" is trying to fix, could you
> please describe a bit more what the problem is?
dma_unmap_page() should use DMA_TO_DEVICE or DMA_FROM_DEVICE, instead
of block request dir(READ or WRITE), and the issue is actually one
dma-debug warning.
And block request buffer or IO direction isn't supposed to change in its
lifetime, and dma-debug code check if page map & unmap direction is same.
>
> Can it cause silent data corruption?
No.
Thanks,
Ming
parent reply other threads:[~2023-11-30 0:16 UTC|newest]
Thread overview: expand[flat|nested] mbox.gz Atom feed
[parent not found: <CAKhLTr2PjPnNDccbc8OMy3fSc_U1Dk7GS+UWLUkj0zWwzcp4zw@mail.gmail.com>]
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=ZWfUWPsJ7AAOzqHR@fedora \
--to=ming.lei@redhat.com \
--cc=guazhang@redhat.com \
--cc=hch@lst.de \
--cc=linux-block@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=raphaelsc@scylladb.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).