[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <AS1PR10MB5675F191C6EC49ED8BEA9BECEB8B9@AS1PR10MB5675.EURPRD10.PROD.OUTLOOK.COM>
Date: Mon, 27 Mar 2023 05:44:30 +0000
From: "Bouska, Zdenek" <zdenek.bouska@...mens.com>
To: Catalin Marinas <catalin.marinas@....com>
CC: Thomas Gleixner <tglx@...utronix.de>,
Will Deacon <will@...nel.org>,
"linux-arm-kernel@...ts.infradead.org"
<linux-arm-kernel@...ts.infradead.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"Kiszka, Jan" <jan.kiszka@...mens.com>,
"linux-rt-users@...r.kernel.org" <linux-rt-users@...r.kernel.org>,
Nishanth Menon <nm@...com>, Puranjay Mohan <p-mohan@...com>
Subject: Re: Unfair qspinlocks on ARM64 without LSE atomics => 3ms delay in
interrupt handling
>> So I confirmed that atomic operations from
>> arch/arm64/include/asm/atomic_ll_sc.h can be quite slow when they are
>> contested from second CPU.
>>
>> Do you think that it is possible to create fair qspinlock implementation
>> on top of atomic instructions supported by ARM64 version 8 (no LSE atomic
>> instructions) without compromising performance in the uncontested case?
>> For example ARM64 could have custom queued_fetch_set_pending_acquire
>> implementation same as x86 has in arch/x86/include/asm/qspinlock.h. Is the
>> retry loop in irq_finalize_oneshot() ok together with the current ARM64
>> cpu_relax() implementation for processor with no LSE atomic instructions?
>
>So is the queued_fetch_set_pending_acquire() where it gets stuck or the
>earlier atomic_try_cmpxchg_acquire() before entering on the slow path? I
>guess both can fail in a similar way.
For me it was stuck on queued_fetch_set_pending_acquire().
Zdenek Bouska
--
Siemens, s.r.o
Siemens Advanta Development
Powered by blists - more mailing lists