netdev - Re: [PATCH net-next v2 2/3] page_pool: Turn dma_sync and dma_sync

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: <87cye4qkgd.fsf@toke.dk>
Date: Wed, 26 Mar 2025 09:12:34 +0100
From: Toke Høiland-Jørgensen <toke@...hat.com>
To: Jakub Kicinski <kuba@...nel.org>
Cc: "David S. Miller" <davem@...emloft.net>, Jesper Dangaard Brouer
 <hawk@...nel.org>, Saeed Mahameed <saeedm@...dia.com>, Leon Romanovsky
 <leon@...nel.org>, Tariq Toukan <tariqt@...dia.com>, Andrew Lunn
 <andrew+netdev@...n.ch>, Eric Dumazet <edumazet@...gle.com>, Paolo Abeni
 <pabeni@...hat.com>, Ilias Apalodimas <ilias.apalodimas@...aro.org>, Simon
 Horman <horms@...nel.org>, Andrew Morton <akpm@...ux-foundation.org>, Mina
 Almasry <almasrymina@...gle.com>, Yonglong Liu <liuyonglong@...wei.com>,
 Yunsheng Lin <linyunsheng@...wei.com>, Pavel Begunkov
 <asml.silence@...il.com>, Matthew Wilcox <willy@...radead.org>,
 netdev@...r.kernel.org, bpf@...r.kernel.org, linux-rdma@...r.kernel.org,
 linux-mm@...ck.org
Subject: Re: [PATCH net-next v2 2/3] page_pool: Turn dma_sync and
 dma_sync_cpu fields into a bitmap

Jakub Kicinski <kuba@...nel.org> writes:

> On Tue, 25 Mar 2025 16:45:43 +0100 Toke Høiland-Jørgensen wrote:
>> Change the single-bit booleans for dma_sync into an unsigned long with
>> BIT() definitions so that a subsequent patch can write them both with a
>> singe WRITE_ONCE() on teardown. Also move the check for the sync_cpu
>> side into __page_pool_dma_sync_for_cpu() so it can be disabled for
>> non-netmem providers as well.
>
> Can we make them just bools without the bit width?
> Less churn and actually fewer bytes.

Ah! Didn't realise that was possible, excellent solution :)

> I don't see why we'd need to wipe them atomically.
> In fact I don't see why we're touching dma_sync_cpu, at all,
> it's driver-facing and the driver is gone in the problematic
> scenario.

No you're right, but it felt weird to change just one of them, so
figured I'd go with both. But keeping them both as bool, and just making
dma_sync a full-width bool works, so I'll respin with that and leave
dma_sync_cpu as-is.