Linux RDMA and InfiniBand development
 help / color / mirror / Atom feed
From: liweihang <liweihang@huawei.com>
To: Jason Gunthorpe <jgg@nvidia.com>
Cc: Leon Romanovsky <leon@kernel.org>,
	"dledford@redhat.com" <dledford@redhat.com>,
	"linux-rdma@vger.kernel.org" <linux-rdma@vger.kernel.org>,
	"linuxarm@openeuler.org" <linuxarm@openeuler.org>
Subject: Re: [PATCH RFC 1/7] RDMA/hns: Introduce DCA for RC QP
Date: Fri, 22 Jan 2021 09:06:11 +0000	[thread overview]
Message-ID: <0afb522df2d24fe3be8d7ee2611465ef@huawei.com> (raw)
In-Reply-To: 20210121135143.GZ4147@nvidia.com

On 2021/1/21 21:52, Jason Gunthorpe wrote:
> On Thu, Jan 21, 2021 at 01:48:56PM +0000, liweihang wrote:
>> On 2021/1/21 21:36, Jason Gunthorpe wrote:
>>> On Thu, Jan 21, 2021 at 01:33:42PM +0000, liweihang wrote:
>>>
>>>> We need to allocate memory while spin_lock is hold, how about using GFP_KERNEL or
>>>> GFP_NOWAIT?
>>>
>>> You should try hard not to do that. Convert he spinlock to a mutex,
>>> for instance.
>>>
>>> Jason
>>>
>>
>> But what if some kernel users call ib_post_send() when holding a spinlock?
> 
> I doubt extensions like this would be part of kernel verbs..
> 
> Does any ULP call ib_post_send under lock? I'm not sure that is valid.
> 
> Jason
> 

I didn't find such a ULP calling ib_post_send in a spinlock either. Anyway,
I will use GFP_NOWAIT instead of GFP_ATOMIC.

Thanks
Weihang

  reply	other threads:[~2021-01-22 11:01 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-15 10:22 [PATCH RFC 0/7] RDMA/hns: Add support for Dynamic Context Attachment Weihang Li
2021-01-15 10:22 ` [PATCH RFC 1/7] RDMA/hns: Introduce DCA for RC QP Weihang Li
2021-01-20  8:10   ` Leon Romanovsky
2021-01-21  7:01     ` liweihang
2021-01-21  8:53       ` Leon Romanovsky
2021-01-21 13:33         ` liweihang
2021-01-21 13:34           ` Jason Gunthorpe
2021-01-21 13:48             ` liweihang
2021-01-21 13:51               ` Jason Gunthorpe
2021-01-22  9:06                 ` liweihang [this message]
2021-01-15 10:22 ` [PATCH RFC 2/7] RDMA/hns: Add method for shrinking DCA memory pool Weihang Li
2021-01-15 10:22 ` [PATCH RFC 3/7] RDMA/hns: Configure DCA mode for the userspace QP Weihang Li
2021-01-15 10:22 ` [PATCH RFC 4/7] RDMA/hns: Add method for attaching WQE buffer Weihang Li
2021-01-15 10:22 ` [PATCH RFC 5/7] RDMA/hns: Setup the configuration of WQE addressing to QPC Weihang Li
2021-01-15 10:22 ` [PATCH RFC 6/7] RDMA/hns: Add method to detach WQE buffer Weihang Li
2021-01-15 10:22 ` [PATCH RFC 7/7] RDMA/hns: Add method to query WQE buffer's address Weihang Li

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=0afb522df2d24fe3be8d7ee2611465ef@huawei.com \
    --to=liweihang@huawei.com \
    --cc=dledford@redhat.com \
    --cc=jgg@nvidia.com \
    --cc=leon@kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linuxarm@openeuler.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox