netdev - Re: [PATCH v13 1/7] net: split off __napi_busy_poll from napi_busy

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] [day] [month] [year] [list]

Message-ID: <20230601212604.3f5e2342@kernel.org>
Date: Thu, 1 Jun 2023 21:26:04 -0700
From: Jakub Kicinski <kuba@...nel.org>
To: Stefan Roesch <shr@...kernel.io>
Cc: io-uring@...r.kernel.org, kernel-team@...com, axboe@...nel.dk,
 ammarfaizi2@...weeb.org, netdev@...r.kernel.org, olivier@...llion01.com
Subject: Re: [PATCH v13 1/7] net: split off __napi_busy_poll from
 napi_busy_poll

On Thu, 01 Jun 2023 21:12:10 -0700 Stefan Roesch wrote:
> The problem with checking need_resched in loop_end is that need_resched
> can be false in loop_end, however the check for need_resched in
> napi_busy_loop succeeds. This means that we unlock the rcu read lock and
> call schedule. However the code in io_napi_blocking_busy_loop still
> believes we hold the read lock.

Ah, yes, now it makes sense. 
Yeah, that's a race, scratch the workaround idea then.
Let's work on revising the patches, we'll see where we 
are in the development process when they're ready.