All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Christian König" <deathsimple@vodafone.de>
To: "Michel Dänzer" <michel@daenzer.net>, dri-devel@lists.freedesktop.org
Subject: Re: [PATCH 1/2] drm/radeon: Try placing NO_CPU_ACCESS BOs outside of CPU accessible VRAM
Date: Thu, 09 Oct 2014 13:30:12 +0200	[thread overview]
Message-ID: <543671C4.1000000@vodafone.de> (raw)
In-Reply-To: <1412848504-3060-1-git-send-email-michel@daenzer.net>

Am 09.10.2014 um 11:55 schrieb Michel Dänzer:
> From: Michel Dänzer <michel.daenzer@amd.com>
>
> This avoids them getting in the way of BOs which might be accessed by
> the CPU. They can still go to the CPU accessible part of VRAM though if
> there's no space outside of it.

That sounds to me like you want to increase the size of 
radeon_bo.placements as well, cause we can now have one more.

Christian.

>
> Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
> ---
>   drivers/gpu/drm/radeon/radeon_object.c | 42 ++++++++++++++++++++++++++++------
>   1 file changed, 35 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
> index 99a960a..7f3b1e1 100644
> --- a/drivers/gpu/drm/radeon/radeon_object.c
> +++ b/drivers/gpu/drm/radeon/radeon_object.c
> @@ -99,22 +99,39 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
>   
>   	rbo->placement.placement = rbo->placements;
>   	rbo->placement.busy_placement = rbo->placements;
> -	if (domain & RADEON_GEM_DOMAIN_VRAM)
> +	if (domain & RADEON_GEM_DOMAIN_VRAM) {
> +		/* Try placing BOs which don't need CPU access outside of the
> +		 * CPU accessible part of VRAM
> +		 */
> +		if ((rbo->flags & RADEON_GEM_NO_CPU_ACCESS) &&
> +		    rbo->rdev->mc.visible_vram_size < rbo->rdev->mc.real_vram_size) {
> +			rbo->placements[c].fpfn =
> +				rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
> +			rbo->placements[c++].flags = TTM_PL_FLAG_WC |
> +						     TTM_PL_FLAG_UNCACHED |
> +						     TTM_PL_FLAG_VRAM;
> +		}
> +
> +		rbo->placements[c].fpfn = 0;
>   		rbo->placements[c++].flags = TTM_PL_FLAG_WC |
>   					     TTM_PL_FLAG_UNCACHED |
>   					     TTM_PL_FLAG_VRAM;
> +	}
>   
>   	if (domain & RADEON_GEM_DOMAIN_GTT) {
>   		if (rbo->flags & RADEON_GEM_GTT_UC) {
> +			rbo->placements[c].fpfn = 0;
>   			rbo->placements[c++].flags = TTM_PL_FLAG_UNCACHED |
>   				TTM_PL_FLAG_TT;
>   
>   		} else if ((rbo->flags & RADEON_GEM_GTT_WC) ||
>   			   (rbo->rdev->flags & RADEON_IS_AGP)) {
> +			rbo->placements[c].fpfn = 0;
>   			rbo->placements[c++].flags = TTM_PL_FLAG_WC |
>   				TTM_PL_FLAG_UNCACHED |
>   				TTM_PL_FLAG_TT;
>   		} else {
> +			rbo->placements[c].fpfn = 0;
>   			rbo->placements[c++].flags = TTM_PL_FLAG_CACHED |
>   						     TTM_PL_FLAG_TT;
>   		}
> @@ -122,30 +139,35 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
>   
>   	if (domain & RADEON_GEM_DOMAIN_CPU) {
>   		if (rbo->flags & RADEON_GEM_GTT_UC) {
> +			rbo->placements[c].fpfn = 0;
>   			rbo->placements[c++].flags = TTM_PL_FLAG_UNCACHED |
>   				TTM_PL_FLAG_SYSTEM;
>   
>   		} else if ((rbo->flags & RADEON_GEM_GTT_WC) ||
>   		    rbo->rdev->flags & RADEON_IS_AGP) {
> +			rbo->placements[c].fpfn = 0;
>   			rbo->placements[c++].flags = TTM_PL_FLAG_WC |
>   				TTM_PL_FLAG_UNCACHED |
>   				TTM_PL_FLAG_SYSTEM;
>   		} else {
> +			rbo->placements[c].fpfn = 0;
>   			rbo->placements[c++].flags = TTM_PL_FLAG_CACHED |
>   						     TTM_PL_FLAG_SYSTEM;
>   		}
>   	}
> -	if (!c)
> +	if (!c) {
> +		rbo->placements[c].fpfn = 0;
>   		rbo->placements[c++].flags = TTM_PL_MASK_CACHING |
>   					     TTM_PL_FLAG_SYSTEM;
> +	}
>   
>   	rbo->placement.num_placement = c;
>   	rbo->placement.num_busy_placement = c;
>   
>   	for (i = 0; i < c; ++i) {
> -		rbo->placements[i].fpfn = 0;
>   		if ((rbo->flags & RADEON_GEM_CPU_ACCESS) &&
> -		    (rbo->placements[i].flags & TTM_PL_FLAG_VRAM))
> +		    (rbo->placements[i].flags & TTM_PL_FLAG_VRAM) &&
> +		    !rbo->placements[i].fpfn)
>   			rbo->placements[i].lpfn =
>   				rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
>   		else
> @@ -743,8 +765,8 @@ int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
>   {
>   	struct radeon_device *rdev;
>   	struct radeon_bo *rbo;
> -	unsigned long offset, size;
> -	int r;
> +	unsigned long offset, size, lpfn;
> +	int i, r;
>   
>   	if (!radeon_ttm_bo_is_radeon_bo(bo))
>   		return 0;
> @@ -761,7 +783,13 @@ int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
>   
>   	/* hurrah the memory is not visible ! */
>   	radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
> -	rbo->placements[0].lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
> +	lpfn =	rdev->mc.visible_vram_size >> PAGE_SHIFT;
> +	for (i = 0; i < rbo->placement.num_placement; i++) {
> +		/* Force into visible VRAM */
> +		if ((rbo->placements[i].flags & TTM_PL_FLAG_VRAM) &&
> +		    (!rbo->placements[i].lpfn || rbo->placements[i].lpfn > lpfn))
> +			rbo->placements[i].lpfn = lpfn;
> +	}
>   	r = ttm_bo_validate(bo, &rbo->placement, false, false);
>   	if (unlikely(r == -ENOMEM)) {
>   		radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT);

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

  parent reply	other threads:[~2014-10-09 11:30 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-10-09  9:55 [PATCH 1/2] drm/radeon: Try placing NO_CPU_ACCESS BOs outside of CPU accessible VRAM Michel Dänzer
2014-10-09  9:55 ` [PATCH 2/2] drm/radeon: Try evicting from CPU accessible to inaccessible VRAM first Michel Dänzer
2014-10-09 11:30 ` Christian König [this message]
2014-10-10  3:28   ` [PATCH v2 1/2] drm/radeon: Try placing NO_CPU_ACCESS BOs outside of CPU accessible VRAM Michel Dänzer
2014-10-13 18:25     ` Alex Deucher

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=543671C4.1000000@vodafone.de \
    --to=deathsimple@vodafone.de \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=michel@daenzer.net \
    /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.