[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <8c4f103b-8f04-d0ad-b30a-2db7e52b36a3@arm.com>
Date: Tue, 20 Sep 2022 14:15:34 +0530
From: Anshuman Khandual <anshuman.khandual@....com>
To: Barry Song <21cnbao@...il.com>
Cc: Yicong Yang <yangyicong@...wei.com>, akpm@...ux-foundation.org,
linux-mm@...ck.org, linux-arm-kernel@...ts.infradead.org,
x86@...nel.org, catalin.marinas@....com, will@...nel.org,
linux-doc@...r.kernel.org, corbet@....net, peterz@...radead.org,
arnd@...db.de, linux-kernel@...r.kernel.org,
darren@...amperecomputing.com, yangyicong@...ilicon.com,
huzhanyuan@...o.com, lipeifeng@...o.com, zhangshiming@...o.com,
guojian@...o.com, realmz6@...il.com, linux-mips@...r.kernel.org,
openrisc@...ts.librecores.org, linuxppc-dev@...ts.ozlabs.org,
linux-riscv@...ts.infradead.org, linux-s390@...r.kernel.org,
wangkefeng.wang@...wei.com, xhao@...ux.alibaba.com,
prime.zeng@...ilicon.com, Barry Song <v-songbaohua@...o.com>,
Nadav Amit <namit@...are.com>, Mel Gorman <mgorman@...e.de>
Subject: Re: [PATCH v3 4/4] arm64: support batched/deferred tlb shootdown
during page reclamation
On 9/20/22 09:09, Barry Song wrote:
> On Tue, Sep 20, 2022 at 3:00 PM Anshuman Khandual
> <anshuman.khandual@....com> wrote:
>>
>>
>> On 8/22/22 13:51, Yicong Yang wrote:
>>> +static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
>>> +{
>>> + return true;
>>> +}
>>
>> This needs to be conditional on systems, where there will be performance
>> improvements, and should not just be enabled all the time on all systems.
>> num_online_cpus() > X, which does not hold any cpu hotplug lock would be
>> a good metric ?
>
> for a small system, i don't see how this patch will help, e.g. cpus <= 4;
> so we can actually disable tlb-batch on small systems.
Do not subscribe ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH based on NR_CPUS ?
That might not help much as the default value is 256 for NR_CPUS.
OR
arch_tlbbatch_should_defer() checks on
1. online cpus (dont enable batched TLB if <= X)
2. ARM64_WORKAROUND_REPEAT_TLBI (dont enable batched TLB)
> just need to check if we will have any race condition since hotplug will
> make the condition true and false dynamically.
If should_defer_flush() evaluate to be false, then ptep_clear_flush()
clears and flushes the entry right away. This should not race with other
queued up TLBI requests, which will be flushed separately. Wondering how
there can be a race here !
Powered by blists - more mailing lists