[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <E9CF24C7-3080-4720-B540-BAF03068336B@gmail.com>
Date: Fri, 21 Jul 2023 03:59:33 +0800
From: Alan Huang <mmpgouride@...il.com>
To: Eric Dumazet <edumazet@...gle.com>
Cc: linux-kernel@...r.kernel.org, netdev@...r.kernel.org,
rcu@...r.kernel.org, "Paul E. McKenney" <paulmck@...nel.org>,
roman.gushchin@...ux.dev
Subject: Re: Question about the barrier() in hlist_nulls_for_each_entry_rcu()
> 2023年7月21日 03:22,Eric Dumazet <edumazet@...gle.com> 写道:
>
> On Thu, Jul 20, 2023 at 8:54 PM Alan Huang <mmpgouride@...il.com> wrote:
>>
>> Hi,
>>
>> I noticed a commit c87a124a5d5e(“net: force a reload of first item in hlist_nulls_for_each_entry_rcu”)
>> and a related discussion [1].
>>
>> After reading the whole discussion, it seems like that ptr->field was cached by gcc even with the deprecated
>> ACCESS_ONCE(), so my question is:
>>
>> Is that a compiler bug? If so, has this bug been fixed today, ten years later?
>>
>> What about READ_ONCE(ptr->field)?
>
> Make sure sparse is happy.
It caused a problem without barrier(), and the deprecated ACCESS_ONCE() didn’t help:
https://lore.kernel.org/all/519D19DA.50400@yandex-team.ru/
So, my real question is: With READ_ONCE(ptr->field), are there still some unusual cases where gcc
decides not to reload ptr->field?
>
> Do you have a patch for review ?
Possibly next month. :)
>
>
>>
>>
>> [1] https://lore.kernel.org/all/1369699930.3301.494.camel@edumazet-glaptop/
>>
>> Thanks,
>> Alan
Powered by blists - more mailing lists