drm/i915/guc: Use streaming loads to speed up dumping the guc log

Use a temporary page and mempy_from_wc to reduce the time it takes to
dump the guc log to debugfs.

Signed-off-by: Chris Wilson <chris.p.wilson@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220728022028.2190627-6-John.C.Harrison@Intel.com

drivers/gpu/drm/i915/gt/uc/intel_guc_log.c

@@ -750,8 +750,9 @@ int intel_guc_log_dump(struct intel_guc_log *log, struct drm_printer *p,
 	struct intel_guc *guc = log_to_guc(log);
 	struct intel_uc *uc = container_of(guc, struct intel_uc, guc);
 	struct drm_i915_gem_object *obj = NULL;
-	u32 *map;
-	int i = 0;
+	void *map;
+	u32 *page;
+	int i, j;
 
 	if (!intel_guc_is_supported(guc))
 		return -ENODEV;
@@ -764,23 +765,34 @@ int intel_guc_log_dump(struct intel_guc_log *log, struct drm_printer *p,
 	if (!obj)
 		return 0;
 
+	page = (u32 *)__get_free_page(GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
 	intel_guc_dump_time_info(guc, p);
 
 	map = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC);
 	if (IS_ERR(map)) {
 		DRM_DEBUG("Failed to pin object\n");
 		drm_puts(p, "(log data unaccessible)\n");
+		free_page((unsigned long)page);
 		return PTR_ERR(map);
 	}
 
-	for (i = 0; i < obj->base.size / sizeof(u32); i += 4)
-		drm_printf(p, "0x%08x 0x%08x 0x%08x 0x%08x\n",
-			   *(map + i), *(map + i + 1),
-			   *(map + i + 2), *(map + i + 3));
+	for (i = 0; i < obj->base.size; i += PAGE_SIZE) {
+		if (!i915_memcpy_from_wc(page, map + i, PAGE_SIZE))
+			memcpy(page, map + i, PAGE_SIZE);
+
+		for (j = 0; j < PAGE_SIZE / sizeof(u32); j += 4)
+			drm_printf(p, "0x%08x 0x%08x 0x%08x 0x%08x\n",
+				   *(page + j + 0), *(page + j + 1),
+				   *(page + j + 2), *(page + j + 3));
+	}
 
 	drm_puts(p, "\n");
 
 	i915_gem_object_unpin_map(obj);
+	free_page((unsigned long)page);
 
 	return 0;
 }