netdev - Re: [PATCH net v2 0/2] fix two bugs related to page

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: <20241014171406.43e730c9@kernel.org>
Date: Mon, 14 Oct 2024 17:14:06 -0700
From: Jakub Kicinski <kuba@...nel.org>
To: Yunsheng Lin <linyunsheng@...wei.com>
Cc: <davem@...emloft.net>, <pabeni@...hat.com>, <liuyonglong@...wei.com>,
 <fanghaiqing@...wei.com>, <zhangkun09@...wei.com>, Alexander Lobakin
 <aleksander.lobakin@...el.com>, Robin Murphy <robin.murphy@....com>,
 Alexander Duyck <alexander.duyck@...il.com>, IOMMU <iommu@...ts.linux.dev>,
 Alexei Starovoitov <ast@...nel.org>, Daniel Borkmann
 <daniel@...earbox.net>, Jesper Dangaard Brouer <hawk@...nel.org>, John
 Fastabend <john.fastabend@...il.com>, Matthias Brugger
 <matthias.bgg@...il.com>, AngeloGioacchino Del Regno
 <angelogioacchino.delregno@...labora.com>, <netdev@...r.kernel.org>,
 <intel-wired-lan@...ts.osuosl.org>, <bpf@...r.kernel.org>,
 <linux-kernel@...r.kernel.org>, <linux-arm-kernel@...ts.infradead.org>,
 <linux-mediatek@...ts.infradead.org>
Subject: Re: [PATCH net v2 0/2] fix two bugs related to page_pool

On Sat, 12 Oct 2024 20:05:31 +0800 Yunsheng Lin wrote:
> 1. Semantics changing of supporting unlimited inflight pages
>    to limited inflight pages that are as large as the pool_size
>    of page_pool.

How can this possibly work?

The main thing stopping me from reposting my fix that it'd be nice to
figure out if a real IOMMU device is bound or not. If we don't have
real per-device mappings we presumably don't have to wait. If we can 
check this condition we are guaranteed not to introduce regressions,
since we would be replacing a crash by a wait, which is strictly better.

If we'd need to fiddle with too many internals to find out if we have
to wait - let's just always wait and see if anyone complains.