All of lore.kernel.org
 help / color / mirror / Atom feed
From: Niklas Cassel <cassel@kernel.org>
To: Keith Busch <kbusch@meta.com>
Cc: linux-block@vger.kernel.org, linux-nvme@lists.infradead.org,
	Keith Busch <kbusch@kernel.org>
Subject: Re: [PATCH 3/5] nvme: add support for copy offload
Date: Mon, 9 Jun 2025 11:29:27 +0200	[thread overview]
Message-ID: <aEapdy-c6G35Q-vx@ryzen> (raw)
In-Reply-To: <20250521223107.709131-4-kbusch@meta.com>

Hello Keith,

On Wed, May 21, 2025 at 03:31:05PM -0700, Keith Busch wrote:
> From: Keith Busch <kbusch@kernel.org>
> 
> Register the nvme namespace copy capablities with the request_queue
> limits and implement support for the REQ_OP_COPY operation.

Since you never initialize Descriptor Format (DESFMT), you will use
Descriptor Format 0 (No SNSID, 16b Guard PI).

That is understandable, since your block layer API intentionally does not
support cross-device copies. But I would have expected you to somehow
mention the descriptor type format used somewhere in the commit message and
somewhere in the code (as a comment).


I haven't followed all the work that has happened wrt. PI in the block
layer recently, so I don't know, but I can see that nvme_set_app_tag()
can set a app tag in the request itself, and that nvme_set_ref_tag()
supports both 16b Guard PI and 64b Guard PI.

Do we ever want to set the ELBT/ELBAT/ELBATM in the nvme_copy_range struct?
And if the namespace is using 64b Guard PI, do we want to use Descriptor
Format 1 (No SNSID, 32b/64b Guard PI) rather than Descriptor Format 0 ?


Kind regards,
Niklas

  parent reply	other threads:[~2025-06-09  9:29 UTC|newest]

Thread overview: 49+ 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 10:04   ` kernel test robot
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
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 [this message]
2025-05-21 22:31 ` [PATCH 4/5] block: add support for vectored copies Keith Busch
2025-05-22  9:33   ` kernel test robot
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 12:51   ` kernel test robot
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=aEapdy-c6G35Q-vx@ryzen \
    --to=cassel@kernel.org \
    --cc=kbusch@kernel.org \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.