All of lore.kernel.org
 help / color / mirror / Atom feed
From: Dave Airlie <airlied@gmail.com>
To: dri-devel@lists.freedesktop.org, tj@kernel.org,
	christian.koenig@amd.com, Johannes Weiner <hannes@cmpxchg.org>,
	Michal Hocko <mhocko@kernel.org>,
	Roman Gushchin <roman.gushchin@linux.dev>,
	Shakeel Butt <shakeel.butt@linux.dev>,
	Muchun Song <muchun.song@linux.dev>
Cc: cgroups@vger.kernel.org, Waiman Long <longman@redhat.com>,
	simona@ffwll.ch
Subject: [rfc] drm/ttm/memcg: simplest initial memcg/ttm integration (v2)
Date: Fri,  2 May 2025 13:35:59 +1000	[thread overview]
Message-ID: <20250502034046.1625896-1-airlied@gmail.com> (raw)

Hey all,

This is my second attempt at adding the initial simple memcg/ttm
integration.

This varies from the first attempt in two major ways:

1. Instead of using __GFP_ACCOUNT and direct calling kmem charges
for pool memory, and directly hitting the GPU statistic, Waiman
suggested I just do what the network socket stuff did, which looks
simpler. So this adds two new memcg apis that wrap accounting.
The pages no longer get assigned the memcg, it's owned by the
larger BO object which makes more sense.

2. Christian suggested moving it up a layer to avoid the pool business,
this was a bit tricky, since I want the gfp flags, but I think it only
needs some of them and it should work. One other big difference is that
I aligned it with the dmem interaction, where it tries to get space in
the memcg before it has even allocated any pages, I'm not 100% sure
this is how things should be done, but it was easier, so please let 
me know if it is wrong.

This still doesn't do anything with evictions except ignore them,
and I've some follows up on the old thread to discuss more on them.

Dave.


             reply	other threads:[~2025-05-02  3:43 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-05-02  3:35 Dave Airlie [this message]
2025-05-02  3:36 ` [PATCH 1/5] memcg: add GPU statistic Dave Airlie
2025-05-02  3:36 ` [PATCH 2/5] memcg: add hooks for gpu memcg charging/uncharging Dave Airlie
2025-05-02  3:36 ` [PATCH 3/5] ttm: add initial memcg integration. (v2) Dave Airlie
2025-05-02 12:01   ` Christian König
2025-05-02 14:24   ` kernel test robot
2025-05-03  2:09   ` kernel test robot
2025-05-02  3:36 ` [PATCH 4/5] amdgpu: add support for memcg integration Dave Airlie
2025-05-02 14:01   ` Waiman Long
2025-05-02  3:36 ` [PATCH 5/5] nouveau: add " Dave Airlie
2025-05-06  0:37 ` [rfc] drm/ttm/memcg: simplest initial memcg/ttm integration (v2) Shakeel Butt
2025-05-06  0:59   ` Dave Airlie
2025-05-07 17:52 ` Johannes Weiner
2025-05-07 22:03   ` Dave Airlie
2025-05-07 22:11     ` Dave Airlie
2025-05-13  7:54     ` Johannes Weiner
2025-05-15  3:02       ` Dave Airlie
2025-05-15  8:55         ` Christian König
2025-05-15 15:04           ` Waiman Long
2025-05-15 15:16             ` Christian König
2025-05-15 16:08           ` Johannes Weiner
2025-05-16  6:53             ` Christian König
2025-05-16 14:53               ` Johannes Weiner
2025-05-16 15:35                 ` Christian König
2025-05-16 16:41                   ` Johannes Weiner
2025-05-16 17:42                     ` Christian König
2025-05-16 20:04                       ` Johannes Weiner
2025-05-16 20:25                         ` Dave Airlie
2025-05-18 16:28                           ` Christian König
2025-05-19  6:18                             ` Dave Airlie
2025-05-19  8:26                               ` Christian König
2025-05-22 19:51                           ` Tejun Heo
2025-05-23  7:58                             ` Christian König
2025-05-23 17:06                               ` Tejun Heo
2025-05-26  8:19                                 ` Christian König
2025-05-26 20:13                                   ` Dave Airlie
2025-05-27  8:01                                     ` Christian König
2025-05-16 16:12         ` Johannes Weiner
2025-05-21  2:23       ` Dave Airlie
2025-05-21  7:50         ` Christian König
2025-05-21 14:43         ` Johannes Weiner
2025-05-22  7:03           ` Dave Airlie

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=20250502034046.1625896-1-airlied@gmail.com \
    --to=airlied@gmail.com \
    --cc=cgroups@vger.kernel.org \
    --cc=christian.koenig@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=hannes@cmpxchg.org \
    --cc=longman@redhat.com \
    --cc=mhocko@kernel.org \
    --cc=muchun.song@linux.dev \
    --cc=roman.gushchin@linux.dev \
    --cc=shakeel.butt@linux.dev \
    --cc=simona@ffwll.ch \
    --cc=tj@kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.