[PATCH 2/3] drm/xe/guc_ads: allocate UM queues in VRAM on dGFX

[Jia Yao <jia.yao@intel.com>]

On iGPU, the UM queue BO is allocated in system memory. On dGFX, the BO
was previously created in system memory and later reallocated in
xe_guc_realloc_post_hwconfig().  Allocate the UM queue BO directly in
VRAM on dGFX, where it is ultimately required.

Fixes: 9c57bc08652a ("drm/xe/lnl: Drop force_probe requirement")
Cc: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: <stable@vger.kernel.org> # v6.12+
Signed-off-by: Jia Yao <jia.yao@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patch.msgid.link/20260804165057.129529-3-jia.yao@intel.com
(cherry picked from commit ace076ef0a854ab5940bacc539bf66afd61d118c)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
(cherry picked from commit f342810a141f8a7e8b3786a6e4b6c0695a078a74)
---
 drivers/gpu/drm/xe/xe_guc.c     | 6 ------
 drivers/gpu/drm/xe/xe_guc_ads.c | 8 +++++---
 2 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index 75ab0730c6cc..bedd9894e182 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -293,12 +293,6 @@ static int xe_guc_realloc_post_hwconfig(struct xe_guc *guc)
 	if (ret)
 		return ret;
 
-	if (guc->ads.um_queue_bo) {
-		ret = xe_managed_bo_reinit_in_vram(xe, tile, &guc->ads.um_queue_bo);
-		if (ret)
-			return ret;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index 1bb74e04ed77..35168447a90b 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -400,15 +400,17 @@ int xe_guc_ads_init(struct xe_guc_ads *ads)
 		/*
 		 * Allocate a separate BO for the HW fault ring (UM queues).
 		 *
-		 * Round the size up to the next power of two so that
+		 * Round the size up to the next power of two so that on iGPU
 		 * (system memory, no IOMMU) the TTM pool issues a single
 		 * alloc_pages(order=N) call, maximising the chance of getting
 		 * a physically contiguous block.  GuC requires contiguous DPA.
 		 */
-		size_t um_size = roundup_pow_of_two(GUC_UM_QUEUE_SIZE *
+		size_t um_size = IS_DGFX(xe) ?
+				 GUC_UM_QUEUE_SIZE * GUC_UM_HW_QUEUE_MAX :
+				 roundup_pow_of_two(GUC_UM_QUEUE_SIZE *
 						    GUC_UM_HW_QUEUE_MAX);
 
-		u32 um_flags = XE_BO_FLAG_SYSTEM |
+		u32 um_flags = XE_BO_FLAG_VRAM_IF_DGFX(tile) |
 			       XE_BO_FLAG_GGTT |
 			       XE_BO_FLAG_GGTT_INVALIDATE |
 			       XE_BO_FLAG_PINNED_NORESTORE;
-- 
2.43.0