From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 49ECBC61CE8 for ; Mon, 9 Jun 2025 09:42:45 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender:List-Subscribe:List-Help :List-Post:List-Archive:List-Unsubscribe:List-Id:In-Reply-To:Content-Type: MIME-Version:References:Message-ID:Subject:Cc:To:From:Date:Reply-To: Content-Transfer-Encoding:Content-ID:Content-Description:Resent-Date: Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:List-Owner; bh=1LTOO+ykzs3i46FrydtkJyj4Q7gGo0Ib8nnYqxvNaO0=; b=sRJEqZJqc5kfwj8NAqRRR5YHiW 9gSyQKIuyeqDBQ8+eq+xUv2v8nFLxjsespxFkUIKXNCZw17quaFIUKs4+ebrDyhmGpXFtca29M9xS JWqlertAnq35i0dWX5O8Z2Y/xTUun9RaoUslP9DCU7TTK2HG2N60MT49sldAql6C3AXJPbrT9DUMf Cc3yEU0tp8W5yoE5oqo27MraYuVOGC2/JpVJZPeFG0/LX82UFep8oAX64GVfCzprtr4N2J/LNJn+0 tt2Ezyp2O05fFmCcB/GCvCp4IgkrnzVZigmYAMjAasvcavNsyTb/JJwiiEF9781ZsRSbD2ZPh04+R +AcOx7HQ==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.98.2 #2 (Red Hat Linux)) id 1uOZ1e-00000003oHa-2GVI; Mon, 09 Jun 2025 09:42:42 +0000 Received: from tor.source.kernel.org ([2600:3c04:e001:324:0:1991:8:25]) by bombadil.infradead.org with esmtps (Exim 4.98.2 #2 (Red Hat Linux)) id 1uOYou-00000003mei-1wDI for linux-nvme@lists.infradead.org; Mon, 09 Jun 2025 09:29:32 +0000 Received: from smtp.kernel.org (transwarp.subspace.kernel.org [100.75.92.58]) by tor.source.kernel.org (Postfix) with ESMTP id 9A07361156; Mon, 9 Jun 2025 09:29:31 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id 4007CC4CEEB; Mon, 9 Jun 2025 09:29:30 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1749461371; bh=x/EnJWl/k0jsWW6PMMleDnU0RrJaBN65jDQeKCebf9E=; h=Date:From:To:Cc:Subject:References:In-Reply-To:From; b=LcCM6Xef1yXTIWZcPmZjtcgsQzFN2XcKqh4ZFgV/ssN08Df0aKJHSfW//3gGknsq4 WAAVwhOUqvFQIwxv3rTywGa505tQWx/zpxsFsZzwo9mD6MGKmnby8DbAQlAXmp9Xg6 eFXBxwvw6SfZbk/imnjKFjU5HvxLFkcz26baZpWESbsVhgp7wWWAlyj0/HDaCxSdPh AP3oJSH6CU+mTNrtuzcW+tVnuvFC9V8xLGQVhaml2twXc4LLF4iioOMA4i8TBgTU/X NYSq+NV8ws968V9Peb1nASUuJTkJJrWdIqfwfXLb0+9A8RgPkWWgcWgpx6j4vSJWvz +qSltiFz1+BLw== Date: Mon, 9 Jun 2025 11:29:27 +0200 From: Niklas Cassel To: Keith Busch Cc: linux-block@vger.kernel.org, linux-nvme@lists.infradead.org, Keith Busch Subject: Re: [PATCH 3/5] nvme: add support for copy offload Message-ID: References: <20250521223107.709131-1-kbusch@meta.com> <20250521223107.709131-4-kbusch@meta.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20250521223107.709131-4-kbusch@meta.com> X-BeenThere: linux-nvme@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "Linux-nvme" Errors-To: linux-nvme-bounces+linux-nvme=archiver.kernel.org@lists.infradead.org Hello Keith, On Wed, May 21, 2025 at 03:31:05PM -0700, Keith Busch wrote: > From: Keith Busch > > 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