linux-kernel - Re: [PATCH v4 0/4] Implement dmabuf direct I/O via copy_file

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <aD8cd137bWPALs4u@infradead.org>
Date: Tue, 3 Jun 2025 09:01:59 -0700
From: Christoph Hellwig <hch@...radead.org>
To: Christian König <christian.koenig@....com>
Cc: Christoph Hellwig <hch@...radead.org>, wangtao <tao.wangtao@...or.com>,
	sumit.semwal@...aro.org, kraxel@...hat.com,
	vivek.kasireddy@...el.com, viro@...iv.linux.org.uk,
	brauner@...nel.org, hughd@...gle.com, akpm@...ux-foundation.org,
	amir73il@...il.com, benjamin.gaignard@...labora.com,
	Brian.Starkey@....com, jstultz@...gle.com, tjmercier@...gle.com,
	jack@...e.cz, baolin.wang@...ux.alibaba.com,
	linux-media@...r.kernel.org, dri-devel@...ts.freedesktop.org,
	linaro-mm-sig@...ts.linaro.org, linux-kernel@...r.kernel.org,
	linux-fsdevel@...r.kernel.org, linux-mm@...ck.org,
	bintian.wang@...or.com, yipengxiang@...or.com, liulu.liu@...or.com,
	feng.han@...or.com
Subject: Re: [PATCH v4 0/4] Implement dmabuf direct I/O via copy_file_range

On Tue, Jun 03, 2025 at 05:55:18PM +0200, Christian König wrote:
> On 6/3/25 16:28, Christoph Hellwig wrote:
> > On Tue, Jun 03, 2025 at 04:18:22PM +0200, Christian König wrote:
> >>> Does it matter compared to the I/O in this case?
> >>
> >> It unfortunately does, see the numbers on patch 3 and 4.
> > 
> > That's kinda weird.  Why does the page table lookup tage so much
> > time compared to normal I/O?
> 
> I have absolutely no idea. It's rather surprising for me as well.
> 
> The user seems to have a rather slow CPU paired with fast I/O, but it still looks rather fishy to me.
> 
> Additional to that allocating memory through memfd_create() is *much* slower on that box than through dma-buf-heaps (which basically just uses GFP and an array).

Can someone try to reproduce these results on a normal system
before we're building infrastructure based on these numbers?