Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Christian König" <christian.koenig@amd.com>
To: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
	intel-xe@lists.freedesktop.org
Cc: Matthew Brost <matthew.brost@intel.com>, dri-devel@lists.freedesktop.org
Subject: Re: [PATCH 2/2] drm/ttm: Move pinned objects off LRU lists when pinning
Date: Tue, 3 Sep 2024 09:57:01 +0200	[thread overview]
Message-ID: <2faa3873-9d17-4f48-8d19-85a22f970aad@amd.com> (raw)
In-Reply-To: <20240902154159.78871-3-thomas.hellstrom@linux.intel.com>

Am 02.09.24 um 17:41 schrieb Thomas Hellström:
> The ttm_bo_pin() and ttm_bo_unpin() functions weren't moving their
> resources off the LRU list to the unevictable list.
>
> Make sure that happens so that pinned objects don't accidently linger
> on the LRU lists, and also make sure to move them back once they
> are unpinned.
>
> Cc: Christian König <christian.koenig@amd.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: <dri-devel@lists.freedesktop.org>
> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>

I really can't figure out why we removed that. Anyway Reviewed-by: 
Christian König <christian.koenig@amd.com> for now.

> ---
>   drivers/gpu/drm/ttm/ttm_bo.c | 10 ++++++----
>   1 file changed, 6 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
> index d244566a7e48..057a65f51969 100644
> --- a/drivers/gpu/drm/ttm/ttm_bo.c
> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
> @@ -592,9 +592,10 @@ void ttm_bo_pin(struct ttm_buffer_object *bo)
>   	dma_resv_assert_held(bo->base.resv);
>   	WARN_ON_ONCE(!kref_read(&bo->kref));
>   	spin_lock(&bo->bdev->lru_lock);
> -	if (bo->resource)
> +	if (!bo->pin_count++ && bo->resource) {
>   		ttm_resource_del_bulk_move(bo->resource, bo);
> -	++bo->pin_count;
> +		ttm_resource_move_to_lru_tail(bo->resource);
> +	}
>   	spin_unlock(&bo->bdev->lru_lock);
>   }
>   EXPORT_SYMBOL(ttm_bo_pin);
> @@ -613,9 +614,10 @@ void ttm_bo_unpin(struct ttm_buffer_object *bo)
>   		return;
>   
>   	spin_lock(&bo->bdev->lru_lock);
> -	--bo->pin_count;
> -	if (bo->resource)
> +	if (!--bo->pin_count && bo->resource) {
>   		ttm_resource_add_bulk_move(bo->resource, bo);
> +		ttm_resource_move_to_lru_tail(bo->resource);
> +	}
>   	spin_unlock(&bo->bdev->lru_lock);
>   }
>   EXPORT_SYMBOL(ttm_bo_unpin);


  reply	other threads:[~2024-09-03  7:57 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-09-02 15:41 [PATCH 0/2] drm/ttm: Really use a separate LRU list for swapped- and pinned objects Thomas Hellström
2024-09-02 15:41 ` [PATCH 1/2] drm/ttm: Move swapped objects off the manager's LRU list Thomas Hellström
2024-09-03  7:49   ` Christian König
2024-09-03  8:55     ` Thomas Hellström
2024-09-02 15:41 ` [PATCH 2/2] drm/ttm: Move pinned objects off LRU lists when pinning Thomas Hellström
2024-09-03  7:57   ` Christian König [this message]
2024-09-02 17:59 ` ✓ CI.Patch_applied: success for drm/ttm: Really use a separate LRU list for swapped- and pinned objects Patchwork
2024-09-02 17:59 ` ✓ CI.checkpatch: " Patchwork
2024-09-02 18:00 ` ✗ CI.KUnit: failure " Patchwork

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=2faa3873-9d17-4f48-8d19-85a22f970aad@amd.com \
    --to=christian.koenig@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.brost@intel.com \
    --cc=thomas.hellstrom@linux.intel.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