Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Auld <matthew.auld@intel.com>
To: Matthew Brost <matthew.brost@intel.com>,
	intel-xe@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: thomas.hellstrom@linux.intel.com
Subject: Re: [PATCH v3 6/6] drm/xe: Only allow contiguous BOs to use xe_bo_vmap
Date: Mon, 21 Oct 2024 10:32:31 +0100	[thread overview]
Message-ID: <73e19e35-4deb-4337-8ba7-30cd84dcfed0@intel.com> (raw)
In-Reply-To: <20241019192030.1505020-7-matthew.brost@intel.com>

On 19/10/2024 20:20, Matthew Brost wrote:
> xe_bo_vmap only works on contiguous BOs, disallow xe_bo_vmap on BO
> unless we are certain the BO is contiguous.
> 
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> ---
>   drivers/gpu/drm/xe/xe_bo.c | 23 ++++++++++++++---------
>   1 file changed, 14 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
> index 0a7b91df69c2..46c640f8db9e 100644
> --- a/drivers/gpu/drm/xe/xe_bo.c
> +++ b/drivers/gpu/drm/xe/xe_bo.c
> @@ -162,6 +162,15 @@ static void try_add_system(struct xe_device *xe, struct xe_bo *bo,
>   	}
>   }
>   
> +static bool force_contiguous(u32 bo_flags)
> +{
> +	/*
> +	 * For eviction / restore on suspend / resume objects pinned in VRAM
> +	 * must be contiguous, also only contiguous BOs support xe_bo_vmap.
> +	 */
> +	return bo_flags & (XE_BO_FLAG_PINNED | XE_BO_FLAG_GGTT);
> +}
> +
>   static void add_vram(struct xe_device *xe, struct xe_bo *bo,
>   		     struct ttm_place *places, u32 bo_flags, u32 mem_type, u32 *c)
>   {
> @@ -175,12 +184,7 @@ static void add_vram(struct xe_device *xe, struct xe_bo *bo,
>   	xe_assert(xe, vram && vram->usable_size);
>   	io_size = vram->io_size;
>   
> -	/*
> -	 * For eviction / restore on suspend / resume objects
> -	 * pinned in VRAM must be contiguous
> -	 */
> -	if (bo_flags & (XE_BO_FLAG_PINNED |
> -			XE_BO_FLAG_GGTT))
> +	if (force_contiguous(bo_flags))
>   		place.flags |= TTM_PL_FLAG_CONTIGUOUS;
>   
>   	if (io_size < vram->usable_size) {
> @@ -212,8 +216,7 @@ static void try_add_stolen(struct xe_device *xe, struct xe_bo *bo,
>   
>   		bo->placements[*c] = (struct ttm_place) {
>   			.mem_type = XE_PL_STOLEN,
> -			.flags = bo_flags & (XE_BO_FLAG_PINNED |
> -					     XE_BO_FLAG_GGTT) ?
> +			.flags = force_contiguous(bo_flags) ?
>   				TTM_PL_FLAG_CONTIGUOUS : 0,
>   		};
>   		*c += 1;
> @@ -2024,13 +2027,15 @@ dma_addr_t xe_bo_addr(struct xe_bo *bo, u64 offset, size_t page_size)
>   
>   int xe_bo_vmap(struct xe_bo *bo)
>   {
> +	struct xe_device *xe = ttm_to_xe_device(bo->ttm.bdev);
>   	void *virtual;
>   	bool is_iomem;
>   	int ret;
>   
>   	xe_bo_assert_held(bo);
>   
> -	if (!(bo->flags & XE_BO_FLAG_NEEDS_CPU_ACCESS))
> +	if (drm_WARN_ON(&xe->drm, !(bo->flags & XE_BO_FLAG_NEEDS_CPU_ACCESS) ||
> +			!force_contiguous(bo->flags)))

Hmm was confused why this is not popping in CI for the clear color case, 
but looks like that is directly calling ttm_bo_kmap()...

Anyway, for this patch,
Reviewed-by: Matthew Auld <matthew.auld@intel.com>

>   		return -EINVAL;
>   
>   	if (!iosys_map_is_null(&bo->vmap))

  reply	other threads:[~2024-10-21  9:32 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-19 19:20 [PATCH v3 0/6] Fix non-contiguous VRAM BO access in Xe Matthew Brost
2024-10-19 19:20 ` [PATCH v3 1/6] drm/ttm: Add ttm_bo_access Matthew Brost
2024-10-19 19:20 ` [PATCH v3 2/6] drm/xe: Add xe_ttm_access_memory Matthew Brost
2024-10-19 19:20 ` [PATCH v3 3/6] drm/xe: Update xe_ttm_access_memory to use GPU for non-visible access Matthew Brost
2024-10-21 10:15   ` Matthew Auld
2024-10-21 11:01     ` Thomas Hellström
2024-10-21 17:18       ` Matthew Brost
2024-10-21 17:02     ` Matthew Brost
2024-10-19 19:20 ` [PATCH v3 4/6] drm/xe: Use ttm_bo_access in xe_vm_snapshot_capture_delayed Matthew Brost
2024-10-21  9:07   ` Matthew Auld
2024-10-21 16:58     ` Matthew Brost
2024-10-19 19:20 ` [PATCH v3 5/6] drm/xe: Set XE_BO_FLAG_PINNED in migrate selftest BOs Matthew Brost
2024-10-21  9:50   ` Matthew Auld
2024-10-19 19:20 ` [PATCH v3 6/6] drm/xe: Only allow contiguous BOs to use xe_bo_vmap Matthew Brost
2024-10-21  9:32   ` Matthew Auld [this message]
2024-10-19 19:25 ` ✓ CI.Patch_applied: success for Fix non-contiguous VRAM BO access in Xe (rev3) Patchwork
2024-10-19 19:25 ` ✗ CI.checkpatch: warning " Patchwork
2024-10-19 19:27 ` ✓ CI.KUnit: success " Patchwork
2024-10-19 19:38 ` ✓ CI.Build: " Patchwork
2024-10-19 19:40 ` ✓ CI.Hooks: " Patchwork
2024-10-19 19:42 ` ✗ CI.checksparse: warning " Patchwork
2024-10-19 20:07 ` ✓ CI.BAT: success " Patchwork
2024-10-19 21:06 ` ✗ CI.FULL: 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=73e19e35-4deb-4337-8ba7-30cd84dcfed0@intel.com \
    --to=matthew.auld@intel.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