drm/i915/ttm: Calculate the object placement at get_pages time

Instead of relying on a static placement, calculate at get_pages() time.
This should work for LMEM regions and system for now. For stolen we need
to take preallocated range into account. That will if needed be added
later.

Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210616152501.394518-3-matthew.auld@intel.com

1 files changed, 69 insertions, 24 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index cdf36d3cf02a..d7595688e182 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -24,6 +24,11 @@
 #define I915_TTM_PRIO_NO_PAGES  1
 #define I915_TTM_PRIO_HAS_PAGES 2
 
+/*
+ * Size of struct ttm_place vector in on-stack struct ttm_placement allocs
+ */
+#define I915_TTM_MAX_PLACEMENTS INTEL_REGION_UNKNOWN
+
 /**
  * struct i915_ttm_tt - TTM page vector with additional private information
  * @ttm: The base TTM page vector.
@@ -42,36 +47,71 @@ struct i915_ttm_tt {
 	struct sg_table *cached_st;
 };
 
-static const struct ttm_place lmem0_sys_placement_flags[] = {
-	{
-		.fpfn = 0,
-		.lpfn = 0,
-		.mem_type = I915_PL_LMEM0,
-		.flags = 0,
-	}, {
-		.fpfn = 0,
-		.lpfn = 0,
-		.mem_type = I915_PL_SYSTEM,
-		.flags = 0,
-	}
-};
-
-static struct ttm_placement i915_lmem0_placement = {
-	.num_placement = 1,
-	.placement = &lmem0_sys_placement_flags[0],
-	.num_busy_placement = 1,
-	.busy_placement = &lmem0_sys_placement_flags[0],
+static const struct ttm_place sys_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.mem_type = I915_PL_SYSTEM,
+	.flags = 0,
 };
 
 static struct ttm_placement i915_sys_placement = {
 	.num_placement = 1,
-	.placement = &lmem0_sys_placement_flags[1],
+	.placement = &sys_placement_flags,
 	.num_busy_placement = 1,
-	.busy_placement = &lmem0_sys_placement_flags[1],
+	.busy_placement = &sys_placement_flags,
 };
 
 static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj);
 
+static enum ttm_caching
+i915_ttm_select_tt_caching(const struct drm_i915_gem_object *obj)
+{
+	/*
+	 * Objects only allowed in system get cached cpu-mappings.
+	 * Other objects get WC mapping for now. Even if in system.
+	 */
+	if (obj->mm.region->type == INTEL_MEMORY_SYSTEM &&
+	    obj->mm.n_placements <= 1)
+		return ttm_cached;
+
+	return ttm_write_combined;
+}
+
+static void
+i915_ttm_place_from_region(const struct intel_memory_region *mr,
+			   struct ttm_place *place)
+{
+	memset(place, 0, sizeof(*place));
+	place->mem_type = intel_region_to_ttm_type(mr);
+}
+
+static void
+i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj,
+			    struct ttm_place *requested,
+			    struct ttm_place *busy,
+			    struct ttm_placement *placement)
+{
+	unsigned int num_allowed = obj->mm.n_placements;
+	unsigned int i;
+
+	placement->num_placement = 1;
+	i915_ttm_place_from_region(num_allowed ? obj->mm.placements[0] :
+				   obj->mm.region, requested);
+
+	/* Cache this on object? */
+	placement->num_busy_placement = num_allowed;
+	for (i = 0; i < placement->num_busy_placement; ++i)
+		i915_ttm_place_from_region(obj->mm.placements[i], busy + i);
+
+	if (num_allowed == 0) {
+		*busy = *requested;
+		placement->num_busy_placement = 1;
+	}
+
+	placement->placement = requested;
+	placement->busy_placement = busy;
+}
+
 static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
 					 uint32_t page_flags)
 {
@@ -89,7 +129,8 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
 	    man->use_tt)
 		page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC;
 
-	ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags, ttm_write_combined);
+	ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags,
+			  i915_ttm_select_tt_caching(obj));
 	if (ret) {
 		kfree(i915_tt);
 		return NULL;
@@ -416,10 +457,15 @@ static int i915_ttm_get_pages(struct drm_i915_gem_object *obj)
 		.no_wait_gpu = false,
 	};
 	struct sg_table *st;
+	struct ttm_place requested, busy[I915_TTM_MAX_PLACEMENTS];
+	struct ttm_placement placement;
 	int ret;
 
+	GEM_BUG_ON(obj->mm.n_placements > I915_TTM_MAX_PLACEMENTS);
+
 	/* Move to the requested placement. */
-	ret = ttm_bo_validate(bo, &i915_lmem0_placement, &ctx);
+	i915_ttm_placement_from_obj(obj, &requested, busy, &placement);
+	ret = ttm_bo_validate(bo, &placement, &ctx);
 	if (ret)
 		return ret == -ENOSPC ? -ENXIO : ret;
 
@@ -625,7 +671,6 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem,
 	i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
 	INIT_RADIX_TREE(&obj->ttm.get_io_page.radix, GFP_KERNEL | __GFP_NOWARN);
 	mutex_init(&obj->ttm.get_io_page.lock);
-
 	bo_type = (obj->flags & I915_BO_ALLOC_USER) ? ttm_bo_type_device :
 		ttm_bo_type_kernel;