Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>
To: Matthew Auld <matthew.auld@intel.com>, intel-xe@lists.freedesktop.org
Cc: dri-devel@lists.freedesktop.org, Matthew Brost <matthew.brost@intel.com>
Subject: Re: [PATCH 2/7] drm/gpusvm: use more selective dma dir in get_pages()
Date: Thu, 20 Mar 2025 20:31:50 +0100	[thread overview]
Message-ID: <c2da8c4e2f4db850ad404fbcf80544e3937476b2.camel@linux.intel.com> (raw)
In-Reply-To: <20250320172956.168358-11-matthew.auld@intel.com>

On Thu, 2025-03-20 at 17:29 +0000, Matthew Auld wrote:
> If we are only reading the memory then from the device pov the
> direction
> can be DMA_TO_DEVICE. This aligns with the xe-userptr code. Using the
> most restrictive data direction to represent the access is normally a
> good idea.
> 
> Signed-off-by: Matthew Auld <matthew.auld@intel.com>
> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> Cc: Matthew Brost <matthew.brost@intel.com>

Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>

> ---
>  drivers/gpu/drm/drm_gpusvm.c | 8 +++++---
>  1 file changed, 5 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/drm_gpusvm.c
> b/drivers/gpu/drm/drm_gpusvm.c
> index 48993cef4a74..7f1cf5492bba 100644
> --- a/drivers/gpu/drm/drm_gpusvm.c
> +++ b/drivers/gpu/drm/drm_gpusvm.c
> @@ -1355,6 +1355,8 @@ int drm_gpusvm_range_get_pages(struct
> drm_gpusvm *gpusvm,
>  	int err = 0;
>  	struct dev_pagemap *pagemap;
>  	struct drm_pagemap *dpagemap;
> +	enum dma_data_direction dma_dir = ctx->read_only ?
> DMA_TO_DEVICE :
> +							  
> DMA_BIDIRECTIONAL;
>  
>  retry:
>  	hmm_range.notifier_seq = mmu_interval_read_begin(notifier);
> @@ -1459,7 +1461,7 @@ int drm_gpusvm_range_get_pages(struct
> drm_gpusvm *gpusvm,
>  				dpagemap->ops->device_map(dpagemap,
>  							  gpusvm-
> >drm->dev,
>  							  page,
> order,
> -							 
> DMA_BIDIRECTIONAL);
> +							  dma_dir);
>  			if (dma_mapping_error(gpusvm->drm->dev,
>  					      range-
> >dma_addr[j].addr)) {
>  				err = -EFAULT;
> @@ -1478,7 +1480,7 @@ int drm_gpusvm_range_get_pages(struct
> drm_gpusvm *gpusvm,
>  			addr = dma_map_page(gpusvm->drm->dev,
>  					    page, 0,
>  					    PAGE_SIZE << order,
> -					    DMA_BIDIRECTIONAL);
> +					    dma_dir);
>  			if (dma_mapping_error(gpusvm->drm->dev,
> addr)) {
>  				err = -EFAULT;
>  				goto err_unmap;
> @@ -1486,7 +1488,7 @@ int drm_gpusvm_range_get_pages(struct
> drm_gpusvm *gpusvm,
>  
>  			range->dma_addr[j] =
> drm_pagemap_device_addr_encode
>  				(addr, DRM_INTERCONNECT_SYSTEM,
> order,
> -				 DMA_BIDIRECTIONAL);
> +				 dma_dir);
>  		}
>  		i += 1 << order;
>  		num_dma_mapped = i;


  reply	other threads:[~2025-03-20 19:31 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-03-20 17:29 [PATCH 0/7] Replace xe_hmm with gpusvm Matthew Auld
2025-03-20 17:29 ` [PATCH 1/7] drm/gpusvm: fix hmm_pfn_to_map_order() usage Matthew Auld
2025-03-20 19:52   ` Thomas Hellström
2025-03-20 20:40   ` Matthew Brost
2025-03-21 11:42     ` Matthew Auld
2025-03-20 17:29 ` [PATCH 2/7] drm/gpusvm: use more selective dma dir in get_pages() Matthew Auld
2025-03-20 19:31   ` Thomas Hellström [this message]
2025-03-20 19:37   ` Matthew Brost
2025-03-20 17:30 ` [PATCH 3/7] drm/gpusvm: mark pages as dirty Matthew Auld
2025-03-20 19:29   ` Thomas Hellström
2025-03-20 19:33     ` Matthew Brost
2025-03-21 11:37       ` Matthew Auld
2025-03-20 17:30 ` [PATCH 4/7] drm/gpusvm: pull out drm_gpusvm_pages substructure Matthew Auld
2025-03-20 20:43   ` Matthew Brost
2025-03-21 11:53     ` Matthew Auld
2025-03-20 17:30 ` [PATCH 5/7] drm/gpusvm: lower get/unmap pages Matthew Auld
2025-03-20 20:59   ` Matthew Brost
2025-03-20 17:30 ` [PATCH 6/7] drm/gpusvm: support basic_range Matthew Auld
2025-03-20 21:04   ` Matthew Brost
2025-03-20 17:30 ` [PATCH 7/7] drm/xe/userptr: replace xe_hmm with gpusvm Matthew Auld
2025-03-20 20:52   ` Matthew Brost
2025-03-25  9:50     ` Ghimiray, Himal Prasad
2025-03-20 17:37 ` ✓ CI.Patch_applied: success for Replace " Patchwork
2025-03-20 17:37 ` ✗ CI.checkpatch: warning " Patchwork
2025-03-20 17:38 ` ✗ 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=c2da8c4e2f4db850ad404fbcf80544e3937476b2.camel@linux.intel.com \
    --to=thomas.hellstrom@linux.intel.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.auld@intel.com \
    --cc=matthew.brost@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