Kexec Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Jiri Bohac <jbohac@suse.cz>
To: Tao Liu <ltao@redhat.com>
Cc: Baoquan He <bhe@redhat.com>, Vivek Goyal <vgoyal@redhat.com>,
	Dave Young <dyoung@redhat.com>,
	kexec@lists.infradead.org, linux-kernel@vger.kernel.org,
	mhocko@suse.cz
Subject: Re: [PATCH 0/4] kdump: crashkernel reservation from CMA
Date: Sat, 25 Nov 2023 22:22:29 +0100	[thread overview]
Message-ID: <ZWJllXCN0SDIELrX@dwarf.suse.cz> (raw)
In-Reply-To: <CAO7dBbUVQn8xzPZQhhw1XqF+sQT0c6phk4sda+X=MrR6RmPE0A@mail.gmail.com>

Hi Tao, 

On Sat, Nov 25, 2023 at 09:51:54AM +0800, Tao Liu wrote:
> Thanks for the idea of using CMA as part of memory for the 2nd kernel.
> However I have a question:
> 
> What if there is on-going DMA/RDMA access on the CMA range when 1st
> kernel crash? There might be data corruption when 2nd kernel and
> DMA/RDMA write to the same place, how to address such an issue?

The crash kernel CMA area(s) registered via
cma_declare_contiguous() are distinct from the
dma_contiguous_default_area or device-specific CMA areas that
dma_alloc_contiguous() would use to reserve memory for DMA.

Kernel pages will not be allocated from the crash kernel CMA
area(s), because they are not GFP_MOVABLE. The CMA area will only
be used for user pages. 

User pages for RDMA, should be pinned with FOLL_LONGTERM and that
would migrate them away from the CMA area.

But you're right that DMA to user pages pinned without
FOLL_LONGTERM would still be possible. Would this be a problem in
practice? Do you see any way around it?

Thanks,

-- 
Jiri Bohac <jbohac@suse.cz>
SUSE Labs, Prague, Czechia


_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

  reply	other threads:[~2023-11-25 21:22 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-11-24 19:54 [PATCH 0/4] kdump: crashkernel reservation from CMA Jiri Bohac
2023-11-24 19:57 ` [PATCH 1/4] kdump: add crashkernel cma suffix Jiri Bohac
2023-11-25  7:24   ` kernel test robot
2023-11-24 19:58 ` [PATCH 2/4] kdump: implement reserve_crashkernel_cma Jiri Bohac
2023-11-24 19:58 ` [PATCH 3/4] kdump, x86: implement crashkernel CMA reservation Jiri Bohac
2023-11-24 19:58 ` [PATCH 4/4] kdump, documentation: describe craskernel " Jiri Bohac
2023-11-25  1:51 ` [PATCH 0/4] kdump: crashkernel reservation from CMA Tao Liu
2023-11-25 21:22   ` Jiri Bohac [this message]
2023-11-28  1:12     ` Tao Liu
2023-11-28  2:11       ` Baoquan He
2023-11-28  9:08         ` Michal Hocko
2023-11-29  7:57           ` Baoquan He
2023-11-29  9:25             ` Michal Hocko
2023-11-30  2:42               ` Baoquan He
2023-11-29 10:51             ` Jiri Bohac
2023-11-30  4:01               ` Baoquan He
2023-12-01 12:35                 ` Jiri Bohac
2023-11-29  8:10           ` Baoquan He
2023-11-29 15:03             ` Donald Dutile
2023-11-30  3:00               ` Baoquan He
2023-11-30 10:16                 ` Michal Hocko
2023-11-30 12:04                   ` Baoquan He
2023-11-30 12:31                     ` Baoquan He
2023-11-30 13:41                       ` Michal Hocko
2023-12-01 11:33                         ` Philipp Rudo
2023-12-01 11:55                           ` Michal Hocko
2023-12-01 15:51                             ` Philipp Rudo
2023-12-01 16:59                               ` Michal Hocko
2023-12-06 11:08                                 ` Philipp Rudo
2023-12-06 11:23                                   ` David Hildenbrand
2023-12-06 13:49                                   ` Michal Hocko
2023-12-06 15:19                                     ` Michal Hocko
2023-12-07  4:23                                       ` Baoquan He
2023-12-07  8:55                                         ` Michal Hocko
2023-12-07 11:13                                           ` Philipp Rudo
2023-12-07 11:52                                             ` Michal Hocko
2023-12-08  1:55                                               ` Baoquan He
2023-12-08 10:04                                                 ` Michal Hocko
2023-12-08  2:10                                           ` Baoquan He
2023-12-07 11:13                                       ` Philipp Rudo
2023-11-30 13:29                     ` Michal Hocko
2023-11-30 13:33                       ` Pingfan Liu
2023-11-30 13:43                         ` Michal Hocko
2023-12-01  0:54                           ` Pingfan Liu
2023-12-01 10:37                             ` Michal Hocko
2023-11-28  2:07     ` Pingfan Liu
2023-11-28  8:58       ` Michal Hocko
2023-12-01 11:34 ` Philipp Rudo

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=ZWJllXCN0SDIELrX@dwarf.suse.cz \
    --to=jbohac@suse.cz \
    --cc=bhe@redhat.com \
    --cc=dyoung@redhat.com \
    --cc=kexec@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ltao@redhat.com \
    --cc=mhocko@suse.cz \
    --cc=vgoyal@redhat.com \
    /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