From: Keith Busch <kbusch@kernel.org>
To: Caleb Sander Mateos <csander@purestorage.com>
Cc: Keith Busch <kbusch@meta.com>,
linux-block@vger.kernel.org, linux-nvme@lists.infradead.org
Subject: Re: [PATCH 3/5] nvme: add support for copy offload
Date: Wed, 21 May 2025 22:29:59 -0600 [thread overview]
Message-ID: <aC6oR90OFDSITndh@kbusch-mbp> (raw)
In-Reply-To: <CADUfDZr8DJUPhLvVFK9OPSv015VDSBGNv7z_rrioHFAqOALUOg@mail.gmail.com>
On Wed, May 21, 2025 at 08:41:40PM -0700, Caleb Sander Mateos wrote:
> For the record, that change broke Linux hosts sending DSM commands to
> our NVMe controller, which was validating that the SGL length exactly
> matches the number of data bytes implied by the command. I'm sure
> we're in the minority of NVMe controller vendors in aggressively
> validating the NVMe command parameters, but it was unfortunate to
> discover this change in Linux's behavior.
This is a fabrics target you're talking about? I assume so because pci
would use PRP for a 4k payload, which doesn't encode transfer lengths.
All the offending controllers were pci, so maybe we could have
constrained the DSM over-allocation to that transport if we knew this
was causing problems for fabrics.
next prev parent reply other threads:[~2025-05-22 4:30 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-21 22:31 [PATCH 0/5] block: another block copy offload Keith Busch
2025-05-21 22:31 ` [PATCH 1/5] block: new sector copy api Keith Busch
2025-05-22 10:02 ` Hannes Reinecke
2025-05-22 16:43 ` Keith Busch
2025-05-22 19:22 ` Bart Van Assche
2025-05-22 20:04 ` Keith Busch
2025-05-23 12:45 ` Christoph Hellwig
2025-05-23 17:02 ` Keith Busch
2025-05-26 5:18 ` Christoph Hellwig
2025-05-27 17:45 ` Keith Busch
2025-05-28 7:46 ` Christoph Hellwig
2025-05-28 22:41 ` Keith Busch
2025-06-02 4:58 ` Christoph Hellwig
2025-05-21 22:31 ` [PATCH 2/5] block: add support for copy offload Keith Busch
2025-05-22 13:49 ` Hannes Reinecke
2025-05-23 12:46 ` Christoph Hellwig
2025-05-23 13:26 ` Keith Busch
2025-05-23 13:37 ` Christoph Hellwig
2025-05-23 13:48 ` Keith Busch
2025-05-26 5:22 ` Christoph Hellwig
2025-05-27 21:33 ` Keith Busch
2025-05-28 7:47 ` Christoph Hellwig
2025-05-21 22:31 ` [PATCH 3/5] nvme: " Keith Busch
2025-05-22 0:47 ` Caleb Sander Mateos
2025-05-22 0:51 ` Caleb Sander Mateos
2025-05-22 3:23 ` Keith Busch
2025-05-22 3:41 ` Caleb Sander Mateos
2025-05-22 4:29 ` Keith Busch [this message]
2025-05-22 14:16 ` Caleb Sander Mateos
2025-05-23 12:49 ` Christoph Hellwig
2025-05-23 12:48 ` Christoph Hellwig
2025-05-22 13:54 ` Hannes Reinecke
2025-05-23 12:50 ` Christoph Hellwig
2025-05-23 14:22 ` Caleb Sander Mateos
2025-06-09 9:29 ` Niklas Cassel
2025-05-21 22:31 ` [PATCH 4/5] block: add support for vectored copies Keith Busch
2025-05-22 13:58 ` Hannes Reinecke
2025-05-22 16:36 ` Keith Busch
2025-05-21 22:31 ` [PATCH 5/5] nvmet: implement copy support for bdev backed target Keith Busch
2025-05-22 13:59 ` Hannes Reinecke
2025-05-23 13:18 ` Christoph Hellwig
2025-05-23 14:00 ` Keith Busch
2025-05-23 14:02 ` Christoph Hellwig
2025-05-22 15:52 ` [PATCH 0/5] block: another block copy offload Bart Van Assche
2025-05-23 12:53 ` Christoph Hellwig
2025-07-03 14:47 ` Niklas Cassel
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=aC6oR90OFDSITndh@kbusch-mbp \
--to=kbusch@kernel.org \
--cc=csander@purestorage.com \
--cc=kbusch@meta.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-nvme@lists.infradead.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