[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Z8tKe5O7ICE3xK80@mini-arch>
Date: Fri, 7 Mar 2025 11:35:23 -0800
From: Stanislav Fomichev <stfomichev@...il.com>
To: Jakub Kicinski <kuba@...nel.org>
Cc: Stanislav Fomichev <sdf@...ichev.me>, netdev@...r.kernel.org,
davem@...emloft.net, edumazet@...gle.com, pabeni@...hat.com,
linux-kernel@...r.kernel.org, horms@...nel.org,
donald.hunter@...il.com, michael.chan@...adcom.com,
pavan.chebbi@...adcom.com, andrew+netdev@...n.ch,
jdamato@...tly.com, xuanzhuo@...ux.alibaba.com,
almasrymina@...gle.com, asml.silence@...il.com, dw@...idwei.uk
Subject: Re: [PATCH net-next v1 3/4] net: add granular lock for the netdev
netlink socket
On 03/07, Jakub Kicinski wrote:
> On Fri, 7 Mar 2025 07:57:24 -0800 Stanislav Fomichev wrote:
> > As we move away from rtnl_lock for queue ops, introduce
> > per-netdev_nl_sock lock.
>
> What is it protecting?
The 'bindings' field of the netlink socket:
struct netdev_nl_sock {
struct mutex lock;
struct list_head bindings; <<<
};
I'm assuming it's totally valid to have several bindings per socket?
(attached to different rx queues)
Powered by blists - more mailing lists