drm/xe: fix pat[2] programming with 2M/1G pages

Bit 7 in the leaf node is normally programmed with pat[2], however with
2M/1G pages that same bit in the PDE/PDPE also toggles 2M/1G pages. For
2M/1G entries the pat[2] is rather moved to bit 12, which is now free
given that the address must be aligned to 2M or 1G, leaving bit 7 for
toggling 2M/1G pages.

Bspec: 59510, 45038
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

drivers/gpu/drm/xe/xe_bo.h

@@ -50,6 +50,7 @@
 
 #define XELPG_PPGTT_PTE_PAT3		BIT_ULL(62)
 #define XE2_PPGTT_PTE_PAT4		BIT_ULL(61)
+#define XE_PPGTT_PDE_PDPE_PAT2		BIT_ULL(12)
 #define XE_PPGTT_PTE_PAT2		BIT_ULL(7)
 #define XE_PPGTT_PTE_PAT1		BIT_ULL(4)
 #define XE_PPGTT_PTE_PAT0		BIT_ULL(3)

drivers/gpu/drm/xe/xe_vm.c

@@ -1229,7 +1229,8 @@ static u64 pde_encode_pat_index(struct xe_device *xe, u16 pat_index)
 	return pte;
 }
 
-static u64 pte_encode_pat_index(struct xe_device *xe, u16 pat_index)
+static u64 pte_encode_pat_index(struct xe_device *xe, u16 pat_index,
+				u32 pt_level)
 {
 	u64 pte = 0;
 
@@ -1239,8 +1240,12 @@ static u64 pte_encode_pat_index(struct xe_device *xe, u16 pat_index)
 	if (pat_index & BIT(1))
 		pte |= XE_PPGTT_PTE_PAT1;
 
-	if (pat_index & BIT(2))
+	if (pat_index & BIT(2)) {
+		if (pt_level)
+			pte |= XE_PPGTT_PDE_PDPE_PAT2;
+		else
 			pte |= XE_PPGTT_PTE_PAT2;
+	}
 
 	if (pat_index & BIT(3))
 		pte |= XELPG_PPGTT_PTE_PAT3;
@@ -1284,7 +1289,7 @@ static u64 xelp_pte_encode_bo(struct xe_bo *bo, u64 bo_offset,
 
 	pte = xe_bo_addr(bo, bo_offset, XE_PAGE_SIZE);
 	pte |= XE_PAGE_PRESENT | XE_PAGE_RW;
-	pte |= pte_encode_pat_index(xe, pat_index);
+	pte |= pte_encode_pat_index(xe, pat_index, pt_level);
 	pte |= pte_encode_ps(pt_level);
 
 	if (xe_bo_is_vram(bo) || xe_bo_is_stolen_devmem(bo))
@@ -1303,7 +1308,7 @@ static u64 xelp_pte_encode_vma(u64 pte, struct xe_vma *vma,
 	if (likely(!xe_vma_read_only(vma)))
 		pte |= XE_PAGE_RW;
 
-	pte |= pte_encode_pat_index(xe, pat_index);
+	pte |= pte_encode_pat_index(xe, pat_index, pt_level);
 	pte |= pte_encode_ps(pt_level);
 
 	if (unlikely(xe_vma_is_null(vma)))
@@ -1323,7 +1328,7 @@ static u64 xelp_pte_encode_addr(struct xe_device *xe, u64 addr,
 
 	pte = addr;
 	pte |= XE_PAGE_PRESENT | XE_PAGE_RW;
-	pte |= pte_encode_pat_index(xe, pat_index);
+	pte |= pte_encode_pat_index(xe, pat_index, pt_level);
 	pte |= pte_encode_ps(pt_level);
 
 	if (devmem)