[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <59c5dabd-c06e-4982-af68-bdee9b8174fd@amazon.com>
Date: Thu, 4 Apr 2024 09:54:10 +0300
From: "Margolin, Michael" <mrgolin@...zon.com>
To: Jason Gunthorpe <jgg@...pe.ca>
CC: Tao Liu <ltao@...hat.com>, Gal Pressman <gal.pressman@...ux.dev>,
<sleybo@...zon.com>, <leon@...nel.org>, <kexec@...ts.infradead.org>,
<linux-kernel@...r.kernel.org>, <linux-rdma@...r.kernel.org>
Subject: Re: Implementing .shutdown method for efa module
Thanks, I'll send a patch.
Michael
On 4/3/2024 6:44 PM, Jason Gunthorpe wrote:
> CAUTION: This email originated from outside of the organization. Do not click links or open attachments unless you can confirm the sender and know the content is safe.
>
>
>
> On Mon, Apr 01, 2024 at 04:23:32PM +0300, Margolin, Michael wrote:
>> Jason
>>
>> Thanks for your response, efa_remove() is performing reset to the device
>> which should stop all DMA from the device.
>>
>> Except skipping cleanups that are unnecessary for shutdown flow are there
>> any other reasons to prefer a separate function for shutdown?
> Yes you should skip "cleanups" like removing the IB device and
> otherwise as there is a risk of system hang/deadlock in a shutdown
> handler context.
>
> Jason
>
Powered by blists - more mailing lists