[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ebd284ad-5fa9-2269-c40e-f385420b27c3@intel.com>
Date: Fri, 21 Jul 2023 17:37:57 +0200
From: Alexander Lobakin <aleksander.lobakin@...el.com>
To: Yunsheng Lin <linyunsheng@...wei.com>,
Jakub Kicinski <kuba@...nel.org>
CC: "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Paolo Abeni <pabeni@...hat.com>,
Maciej Fijalkowski <maciej.fijalkowski@...el.com>,
Larysa Zaremba <larysa.zaremba@...el.com>,
Alexander Duyck <alexanderduyck@...com>,
Jesper Dangaard Brouer <hawk@...nel.org>,
Ilias Apalodimas <ilias.apalodimas@...aro.org>,
<netdev@...r.kernel.org>, <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH RFC net-next v2 7/7] net: skbuff: always try to recycle PP
pages directly when in softirq
From: Yunsheng Lin <linyunsheng@...wei.com>
Date: Fri, 21 Jul 2023 19:53:33 +0800
> On 2023/7/21 3:46, Jakub Kicinski wrote:
>> On Thu, 20 Jul 2023 21:33:40 +0200 Alexander Lobakin wrote:
>>>> We can as well check
>>>> (in_softirq() && !irqs_disabled() && !in_hardirq())
>>>> ?
>>>
>>> Yes, something like that. Messy, but I see no other options...
>>>
>>> So, I guess you want to add an assertion to make sure that we're *not*
>>> in this:
>>>
>>> in_hardirq() || irqs_disabled()
>>>
>>> Does this mean that after it's added, my patch is sane? :p
>>
>> Well... it's acceptable. Make sure you add a good, informative
>> but concise comment :)
>>
>
> Does it mean ptr_ring_produce_any() is needed in
> page_pool_recycle_in_ring() too?
>
> As it is assumed that page pool API can be called in the context with
> irqs_disabled() || in_hardirq(), and force recylcling happens in the
> prt_ring.
>
> Isn't it conflit with the below patch? as the below patch assume page
> pool API can not be called in the context with irqs_disabled() || in_hardirq():
> [PATCH net-next] page_pool: add a lockdep check for recycling in hardirq
>
> Or am I missing something obvious here?
No, Page Pool is *not* intended to be called when IRQs are disabled,
hence the fix Jakub's posted in the separate thread.
Thanks,
Olek
Powered by blists - more mailing lists