Re: Something about loongson_llsc_mb

From: Huang Pei <huangpei@loongson.cn>
To: ambrosehua@icloud.com
Cc: Paul Burton <paul.burton@mips.com>, jhogan <jhogan@kernel.org>,
	"jiaxun.yang" <jiaxun.yang@flygoat.com>,
	linux-mips <linux-mips@vger.kernel.org>
Subject: Re: Something about loongson_llsc_mb
Date: Wed, 4 Sep 2019 20:57:38 +0800	[thread overview]
Message-ID: <270f90f1-cbe5-b8e3-4f67-dc13781719e5@loongson.cn> (raw)
In-Reply-To: <20190904092154.GC2349@hirez.programming.kicks-ass.net>

On 09/04/2019 05:21 PM, Peter Zijlstra wrote:
> 
> *why* are you replying to some random unrelated thread?

Chen ask me if whether your patch has more sync than needed, but I'm not sure 
whether sync before and after *cmpxchg_local* is.
> 
> Also, please use a sane MUA and wrap your lines <80 chars.

Sorry, I finally got thunderbird in plain text mode with < 80 chars. It wont 
happen again.

> 
> On Wed, Sep 04, 2019 at 10:03:31AM +0800, huangpei@loongson.cn wrote:
>>> Hi, Peter,
>>>
>>> I found that this patch has been merged but I haven't received the e-mail for some unknown reasons.
>>> https://git.kernel.org/pub/scm/linux/kernel/git/mips/linux.git/commit/?id=1c6c1ca318585f1096d4d04bc722297c85e9fb8a
>>>
>>> Firstly, your comments are correct, so the barrier.h part is perfect.
>>>
>>> Secondly, most of the rest is useless, because smp_mb__before_llsc, loongson_llsc_mb and other memory barriers are the same thing on Loongson-3. We don't need to add loongson_llsc_mb if there is already a smp_mb__before_llsc.
> 
> There wasn't. Take for example set_bit(), that didn't have
> smp_mb__before_llsc on.
> 
> Also; MIPS should probably convert to asm-generic/bitops/atomic.h.
> 
>>> Thirdly, maybe the only exception is syscall.c, but mips_atomic_set is not used on Loongson-3. And if in some cases we use it, I think the user-to-kernel context switch has the same effect of a memory barrier.
> 
> And how is some random person trying to make sense of MIPS to know that?
> 
> You all created a badly documented inconsitent trainwreck. You're
> 'lucky' the MIPS maintainers accepted that mess in the first place.
> 
> Anyway, yes there are too many barrers now in some cases, in a previous
> version I had:
> 
>    https://lkml.kernel.org/r/20190424124421.693353463@infradead.org
> 
> But because I dropped changes to local.h that might not be true anymore;
> it needs careful consideration. Please audit carefully and if you find
> all smp_mb__before_llsc() usage is now superfluous for this 'funny' chip
> of yours, then re-submit the above patch.
> 
>> +. per-cpu like local_t *should only* be written by local cpu, and may be read by remote cpu sometimes
>>
>> +. if and only if local cpu can write per-cpu, then Loongson3's llsc bug would not be triggerd.
>>
>> same as this_cpu_cmpxchg_double
>>
>> If so, then no need to add sync before and after cmpxchg_local
> 
> Correct, we already dropped the change for other local.h stuff.
> 

What about cmpxchg_local? Your patch add sync before and after ll/sc in 
__cmpxchg, so *cmpxchg_local* has sync around it. But cmpxchg_local operate on 
per-cpu, which *shall not* trigger loongson's LLSC bug, since only *this* cpu 
write, other cpus read.