linux-kernel - Re: [PATCH v4 00/15] Add futex2 syscalls

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 for Android: free password hash cracker in your pocket

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

Date:   Tue, 8 Jun 2021 15:22:48 -0300
From:   Adhemerval Zanella <adhemerval.zanella@...aro.org>
To:     Florian Weimer <fweimer@...hat.com>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
        linux-kselftest@...r.kernel.org, joel@...lfernandes.org,
        Andrey Semashev <andrey.semashev@...il.com>,
        kernel@...labora.com, shuah@...nel.org,
        Davidlohr Bueso <dave@...olabs.net>,
        Peter Oskolkov <posk@...k.io>, corbet@....net,
        krisman@...labora.com, malteskarupke@...tmail.fm,
        Ingo Molnar <mingo@...hat.com>,
        Darren Hart <dvhart@...radead.org>, acme@...nel.org,
        Steven Rostedt <rostedt@...dmis.org>,
        André Almeida <andrealmeid@...labora.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        libc-alpha@...rceware.org, linux-api@...r.kernel.org,
        z.figura12@...il.com, Nicholas Piggin <npiggin@...il.com>,
        linux-kernel@...r.kernel.org, pgriffais@...vesoftware.com
Subject: Re: [PATCH v4 00/15] Add futex2 syscalls



On 08/06/2021 15:19, Florian Weimer wrote:
> * Adhemerval Zanella:
> 
>> Also currently we don't have a specific usage.  The proposed patch to
>> add the 'pthread_mutex_lock_any' and 'pthreada_timedlock_any' [3] 
>> also did not gave much detail in realword usages or how it can be
>> leveraged.
> 
> The current rwlock implementation in glibc uses a torn 32-bit futex read
> which is part of an atomically updated 64-bit word.  That's just really,
> really ugly, and I suspect we could make that go away with futex2.

You are right, I had in the mind the multiple wait proposed by this
patch and by the glib RFC one.  Not only rwlock, but the posix
semaphore might also be simplified on 32 bits I think.