[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <806eda1a-de5a-22f3-b5bf-3189878b8b55@gmail.com>
Date: Fri, 22 May 2020 08:52:36 -0700
From: Eric Dumazet <eric.dumazet@...il.com>
To: Xin Long <lucien.xin@...il.com>, Eric Dumazet <edumazet@...gle.com>
Cc: "David S . Miller" <davem@...emloft.net>,
netdev <netdev@...r.kernel.org>,
Eric Dumazet <eric.dumazet@...il.com>,
syzbot <syzkaller@...glegroups.com>,
tipc-discussion@...ts.sourceforge.net, jmaloy@...hat.com
Subject: Re: [PATCH net] tipc: block BH before using dst_cache
On 5/21/20 11:18 PM, Xin Long wrote:
> On Fri, May 22, 2020 at 1:55 PM Eric Dumazet <edumazet@...gle.com> wrote:
>>
>> Resend to the list in non HTML form
>>
>>
>> On Thu, May 21, 2020 at 10:53 PM Eric Dumazet <edumazet@...gle.com> wrote:
>>>
>>>
>>>
>>> On Thu, May 21, 2020 at 10:50 PM Xin Long <lucien.xin@...il.com> wrote:
>>>>
>>>> On Fri, May 22, 2020 at 2:30 AM Eric Dumazet <edumazet@...gle.com> wrote:
>>>>>
>>>>> dst_cache_get() documents it must be used with BH disabled.
>>>> Interesting, I thought under rcu_read_lock() is enough, which calls
>>>> preempt_disable().
>>>
>>>
>>> rcu_read_lock() does not disable BH, never.
>>>
>>> And rcu_read_lock() does not necessarily disable preemption.
> Then I need to think again if it's really worth using dst_cache here.
>
> Also add tipc-discussion and Jon to CC list.
>
> Thanks.
What improvements you got with your patch ?
Disabling BH a bit earlier wont make any difference.
Powered by blists - more mailing lists