[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZlYbupL5XgzgA0MX@andrea>
Date: Tue, 28 May 2024 20:00:26 +0200
From: Andrea Parri <parri.andrea@...il.com>
To: Alexandre Ghiti <alexghiti@...osinc.com>
Cc: Jonathan Corbet <corbet@....net>,
Paul Walmsley <paul.walmsley@...ive.com>,
Palmer Dabbelt <palmer@...belt.com>,
Albert Ou <aou@...s.berkeley.edu>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>, Will Deacon <will@...nel.org>,
Waiman Long <longman@...hat.com>, Boqun Feng <boqun.feng@...il.com>,
Arnd Bergmann <arnd@...db.de>, Leonardo Bras <leobras@...hat.com>,
Guo Ren <guoren@...nel.org>, linux-doc@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-riscv@...ts.infradead.org,
linux-arch@...r.kernel.org
Subject: Re: [PATCH 4/7] riscv: Implement xchg8/16() using Zabha
> -#define __arch_xchg_masked(prepend, append, r, p, n) \
> +#define __arch_xchg_masked(swap_sfx, prepend, append, r, p, n) \
This actually indicates a problem in the current (aka, no Zabha)
implementation: without your series, xchg16() gets mapped to
lr.w a2,(a3)
and a1,a2,a5
or a1,a1,a4
sc.w a1,a1,(a3)
bnez a1,43c <.L0^B1>
which is clearly wrong... (other "fully-ordered LR/SC sequences"
instead follow the mapping
lr.w a2,(a3)
and a1,a2,a5
or a1,a1,a4
sc.w.rl a1,a1,(a3)
bnez a1,43c <.L0^B1>
fence rw,rw )
A similar consideration for xchg8().
Andrea
Powered by blists - more mailing lists