drm/xe/lrc: Use a temporary buffer for WA BB

[ Upstream commit 9c7632f ]

In case the BO is in iomem, we can't simply take the vaddr and write to
it. Instead, prepare a separate buffer that is later copied into io
memory. Right now it's just a few words that could be using
xe_map_write32(), but the intention is to grow the WA BB for other
uses.

Fixes: 617d824 ("drm/xe: Add WA BB to capture active context utilization")
Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Link: https://lore.kernel.org/r/20250604-wa-bb-fix-v1-1-0dfc5dafcef0@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit ef48715b2d3df17c060e23b9aa636af3d95652f8)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

Author: lucasdemarchi

drivers/gpu/drm/xe/xe_lrc.c

@@ -941,11 +941,18 @@ static void xe_lrc_finish(struct xe_lrc *lrc)
  * store it in the PPHSWP.
  */
 #define CONTEXT_ACTIVE 1ULL
-static void xe_lrc_setup_utilization(struct xe_lrc *lrc)
+static int xe_lrc_setup_utilization(struct xe_lrc *lrc)
 {
-	u32 *cmd;
+	u32 *cmd, *buf = NULL;
 
-	cmd = lrc->bb_per_ctx_bo->vmap.vaddr;
+	if (lrc->bb_per_ctx_bo->vmap.is_iomem) {
+		buf = kmalloc(lrc->bb_per_ctx_bo->size, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+		cmd = buf;
+	} else {
+		cmd = lrc->bb_per_ctx_bo->vmap.vaddr;
+	}
 
 	*cmd++ = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET;
 	*cmd++ = ENGINE_ID(0).addr;
@@ -966,9 +973,16 @@ static void xe_lrc_setup_utilization(struct xe_lrc *lrc)
 
 	*cmd++ = MI_BATCH_BUFFER_END;
 
+	if (buf) {
+		xe_map_memcpy_to(gt_to_xe(lrc->gt), &lrc->bb_per_ctx_bo->vmap, 0,
+				 buf, (cmd - buf) * sizeof(*cmd));
+		kfree(buf);
+	}
+
 	xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR,
 			     xe_bo_ggtt_addr(lrc->bb_per_ctx_bo) | 1);
 
+	return 0;
 }
 
 #define PVC_CTX_ASID		(0x2e + 1)
@@ -1123,7 +1137,9 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	map = __xe_lrc_start_seqno_map(lrc);
 	xe_map_write32(lrc_to_xe(lrc), &map, lrc->fence_ctx.next_seqno - 1);
 
-	xe_lrc_setup_utilization(lrc);
+	err = xe_lrc_setup_utilization(lrc);
+	if (err)
+		goto err_lrc_finish;
 
 	return 0;