drm/i915: enforce min GTT alignment for discrete cards

For local-memory objects we need to align the GTT addresses
to 64K, both for the ppgtt and ggtt.

We need to support vm->min_alignment > 4K, depending
on the vm itself and the type of object we are inserting.
With this in mind update the GTT selftests to take this
into account.

For compact-pt we further align and pad lmem object GTT addresses
to 2MB to ensure PDEs contain consistent page sizes as
required by the HW.

v3:
	* use needs_compact_pt flag to discriminate between
	  64K and 64K with compact-pt
	* add i915_vm_obj_min_alignment
	* use i915_vm_obj_min_alignment to round up vma reservation
	  if compact-pt instead of hard coding
v5:
	* fix i915_vm_obj_min_alignment for internal objects which
	  have no memory region
v6:
	* tiled_blits_create correctly pick largest required alignment
v8:
	* i915_vm_min_alignment protect against array overflow for mock region
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Signed-off-by: Robert Beckett <bob.beckett@collabora.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220218184752.7524-7-ramalingam.c@intel.com

drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c

@@ -39,6 +39,7 @@ struct tiled_blits {
 	struct blit_buffer scratch;
 	struct i915_vma *batch;
 	u64 hole;
+	u64 align;
 	u32 width;
 	u32 height;
 };
@@ -410,14 +411,19 @@ tiled_blits_create(struct intel_engine_cs *engine, struct rnd_state *prng)
 		goto err_free;
 	}
 
-	hole_size = 2 * PAGE_ALIGN(WIDTH * HEIGHT * 4);
+	t->align = i915_vm_min_alignment(t->ce->vm, INTEL_MEMORY_LOCAL);
+	t->align = max(t->align,
+		       i915_vm_min_alignment(t->ce->vm, INTEL_MEMORY_SYSTEM));
+
+	hole_size = 2 * round_up(WIDTH * HEIGHT * 4, t->align);
 	hole_size *= 2; /* room to maneuver */
-	hole_size += 2 * I915_GTT_MIN_ALIGNMENT;
+	hole_size += 2 * t->align; /* padding on either side */
 
 	mutex_lock(&t->ce->vm->mutex);
 	memset(&hole, 0, sizeof(hole));
 	err = drm_mm_insert_node_in_range(&t->ce->vm->mm, &hole,
-					  hole_size, 0, I915_COLOR_UNEVICTABLE,
+					  hole_size, t->align,
+					  I915_COLOR_UNEVICTABLE,
 					  0, U64_MAX,
 					  DRM_MM_INSERT_BEST);
 	if (!err)
@@ -428,7 +434,7 @@ tiled_blits_create(struct intel_engine_cs *engine, struct rnd_state *prng)
 		goto err_put;
 	}
 
-	t->hole = hole.start + I915_GTT_MIN_ALIGNMENT;
+	t->hole = hole.start + t->align;
 	pr_info("Using hole at %llx\n", t->hole);
 
 	err = tiled_blits_create_buffers(t, WIDTH, HEIGHT, prng);
@@ -455,7 +461,7 @@ static void tiled_blits_destroy(struct tiled_blits *t)
 static int tiled_blits_prepare(struct tiled_blits *t,
 			       struct rnd_state *prng)
 {
-	u64 offset = PAGE_ALIGN(t->width * t->height * 4);
+	u64 offset = round_up(t->width * t->height * 4, t->align);
 	u32 *map;
 	int err;
 	int i;
@@ -486,8 +492,7 @@ static int tiled_blits_prepare(struct tiled_blits *t,
 
 static int tiled_blits_bounce(struct tiled_blits *t, struct rnd_state *prng)
 {
-	u64 offset =
-		round_up(t->width * t->height * 4, 2 * I915_GTT_MIN_ALIGNMENT);
+	u64 offset = round_up(t->width * t->height * 4, 2 * t->align);
 	int err;
 
 	/* We want to check position invariant tiling across GTT eviction */
@@ -500,7 +505,7 @@ static int tiled_blits_bounce(struct tiled_blits *t, struct rnd_state *prng)
 
 	/* Reposition so that we overlap the old addresses, and slightly off */
 	err = tiled_blit(t,
-			 &t->buffers[2], t->hole + I915_GTT_MIN_ALIGNMENT,
+			 &t->buffers[2], t->hole + t->align,
 			 &t->buffers[1], t->hole + 3 * offset / 2);
 	if (err)
 		return err;

drivers/gpu/drm/i915/gt/intel_gtt.c

@@ -223,6 +223,18 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass)
 
 	GEM_BUG_ON(!vm->total);
 	drm_mm_init(&vm->mm, 0, vm->total);
+
+	memset64(vm->min_alignment, I915_GTT_MIN_ALIGNMENT,
+		 ARRAY_SIZE(vm->min_alignment));
+
+	if (HAS_64K_PAGES(vm->i915) && NEEDS_COMPACT_PT(vm->i915)) {
+		vm->min_alignment[INTEL_MEMORY_LOCAL] = I915_GTT_PAGE_SIZE_2M;
+		vm->min_alignment[INTEL_MEMORY_STOLEN_LOCAL] = I915_GTT_PAGE_SIZE_2M;
+	} else if (HAS_64K_PAGES(vm->i915)) {
+		vm->min_alignment[INTEL_MEMORY_LOCAL] = I915_GTT_PAGE_SIZE_64K;
+		vm->min_alignment[INTEL_MEMORY_STOLEN_LOCAL] = I915_GTT_PAGE_SIZE_64K;
+	}
+
 	vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
 
 	INIT_LIST_HEAD(&vm->bound_list);

drivers/gpu/drm/i915/gt/intel_gtt.h

@@ -29,6 +29,8 @@
 #include "i915_selftest.h"
 #include "i915_vma_resource.h"
 #include "i915_vma_types.h"
+#include "i915_params.h"
+#include "intel_memory_region.h"
 
 #define I915_GFP_ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
 
@@ -223,6 +225,7 @@ struct i915_address_space {
 	struct device *dma;
 	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
 	u64 reserved;		/* size addr space reserved */
+	u64 min_alignment[INTEL_MEMORY_STOLEN_LOCAL + 1];
 
 	unsigned int bind_async_flags;
 
@@ -384,6 +387,25 @@ i915_vm_has_scratch_64K(struct i915_address_space *vm)
 	return vm->scratch_order == get_order(I915_GTT_PAGE_SIZE_64K);
 }
 
+static inline u64 i915_vm_min_alignment(struct i915_address_space *vm,
+					enum intel_memory_type type)
+{
+	/* avoid INTEL_MEMORY_MOCK overflow */
+	if ((int)type >= ARRAY_SIZE(vm->min_alignment))
+		type = INTEL_MEMORY_SYSTEM;
+
+	return vm->min_alignment[type];
+}
+
+static inline u64 i915_vm_obj_min_alignment(struct i915_address_space *vm,
+					    struct drm_i915_gem_object  *obj)
+{
+	struct intel_memory_region *mr = READ_ONCE(obj->mm.region);
+	enum intel_memory_type type = mr ? mr->type : INTEL_MEMORY_SYSTEM;
+
+	return i915_vm_min_alignment(vm, type);
+}
+
 static inline bool
 i915_vm_has_cache_coloring(struct i915_address_space *vm)
 {

drivers/gpu/drm/i915/i915_vma.c

@@ -756,6 +756,14 @@ i915_vma_insert(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 		end = min_t(u64, end, (1ULL << 32) - I915_GTT_PAGE_SIZE);
 	GEM_BUG_ON(!IS_ALIGNED(end, I915_GTT_PAGE_SIZE));
 
+	alignment = max(alignment, i915_vm_obj_min_alignment(vma->vm, vma->obj));
+	/*
+	 * for compact-pt we round up the reservation to prevent
+	 * any smaller pages being used within the same PDE
+	 */
+	if (NEEDS_COMPACT_PT(vma->vm->i915))
+		size = round_up(size, alignment);
+
 	/* If binding the object/GGTT view requires more space than the entire
 	 * aperture has, reject it early before evicting everything in a vain
 	 * attempt to find space.
@@ -768,6 +776,7 @@ i915_vma_insert(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 	}
 
 	color = 0;
+
 	if (i915_vm_has_cache_coloring(vma->vm))
 		color = vma->obj->cache_level;