[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <5744b473-f655-4de2-a895-105ccd60fa1c@linux.ibm.com>
Date: Mon, 4 Mar 2024 11:05:53 +0100
From: Wenjia Zhang <wenjia@...ux.ibm.com>
To: Eric Dumazet <edumazet@...gle.com>,
"David S . Miller"
<davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>
Cc: netdev@...r.kernel.org, eric.dumazet@...il.com,
Jan Karcher <jaka@...ux.ibm.com>,
"D. Wythe" <alibuda@...ux.alibaba.com>,
Tony Lu <tonylu@...ux.alibaba.com>, Wen Gu <guwen@...ux.alibaba.com>
Subject: Re: [PATCH net-next] net/smc: reduce rtnl pressure in
smc_pnet_create_pnetids_list()
On 02.03.24 11:07, Eric Dumazet wrote:
> Many syzbot reports show extreme rtnl pressure, and many of them hint
> that smc acquires rtnl in netns creation for no good reason [1]
>
> This patch returns early from smc_pnet_net_init()
> if there is no netdevice yet.
>
> I am not even sure why smc_pnet_create_pnetids_list() even exists,
> because smc_pnet_netdev_event() is also calling
> smc_pnet_add_base_pnetid() when handling NETDEV_UP event.
>
Hi Eric,
I think that was because of double check. But I do not see the necessary
of the function. I'll check it later if there is any scenario which
would need the function. Before we decide if we need some clean up on
it, the patch looks good to me! Thank you for fixing it!
Reviewed-by: Wenjia Zhang <wenjia@...ux.ibm.com>
Thanks,
Wenjia
Powered by blists - more mailing lists