drm/i915/lmem: Bypass aperture when lmem is available

In the scenario where local memory is available, we have
rely on CPU access via lmem directly instead of aperture.

v2:
gmch is only relevant for much older hw, therefore we can drop the
has_aperture check since it should always be present on such platforms.
(Chris)

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Chris P Wilson <chris.p.wilson@intel.com>
Cc: Daniel Vetter <daniel.vetter@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: CQ Tang <cq.tang@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210427085417.120246-6-matthew.auld@intel.com

drivers/gpu/drm/i915/display/intel_fbdev.c

@@ -139,14 +139,22 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 	size = mode_cmd.pitches[0] * mode_cmd.height;
 	size = PAGE_ALIGN(size);
 
-	/* If the FB is too big, just don't use it since fbdev is not very
-	 * important and we should probably use that space with FBC or other
-	 * features. */
 	obj = ERR_PTR(-ENODEV);
-	if (size * 2 < dev_priv->stolen_usable_size)
-		obj = i915_gem_object_create_stolen(dev_priv, size);
-	if (IS_ERR(obj))
-		obj = i915_gem_object_create_shmem(dev_priv, size);
+	if (HAS_LMEM(dev_priv)) {
+		obj = i915_gem_object_create_lmem(dev_priv, size,
+						  I915_BO_ALLOC_CONTIGUOUS);
+	} else {
+		/*
+		 * If the FB is too big, just don't use it since fbdev is not very
+		 * important and we should probably use that space with FBC or other
+		 * features.
+		 */
+		if (size * 2 < dev_priv->stolen_usable_size)
+			obj = i915_gem_object_create_stolen(dev_priv, size);
+		if (IS_ERR(obj))
+			obj = i915_gem_object_create_shmem(dev_priv, size);
+	}
+
 	if (IS_ERR(obj)) {
 		drm_err(&dev_priv->drm, "failed to allocate framebuffer\n");
 		return PTR_ERR(obj);

drivers/gpu/drm/i915/gem/i915_gem_lmem.c

@@ -17,6 +17,21 @@ const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = {
 	.release = i915_gem_object_release_memory_region,
 };
 
+void __iomem *
+i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
+			    unsigned long n,
+			    unsigned long size)
+{
+	resource_size_t offset;
+
+	GEM_BUG_ON(!i915_gem_object_is_contiguous(obj));
+
+	offset = i915_gem_object_get_dma_address(obj, n);
+	offset -= obj->mm.region->region.start;
+
+	return io_mapping_map_wc(&obj->mm.region->iomap, offset, size);
+}
+
 bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj)
 {
 	struct intel_memory_region *mr = obj->mm.region;

drivers/gpu/drm/i915/gem/i915_gem_lmem.h

@@ -14,6 +14,11 @@ struct intel_memory_region;
 
 extern const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops;
 
+void __iomem *
+i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
+			    unsigned long n,
+			    unsigned long size);
+
 bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj);
 
 struct drm_i915_gem_object *

drivers/gpu/drm/i915/i915_vma.c

@@ -27,6 +27,7 @@
 
 #include "display/intel_frontbuffer.h"
 
+#include "gem/i915_gem_lmem.h"
 #include "gt/intel_engine.h"
 #include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_gt.h"
@@ -448,9 +449,11 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 	void __iomem *ptr;
 	int err;
 
-	if (GEM_WARN_ON(!i915_vma_is_map_and_fenceable(vma))) {
-		err = -ENODEV;
-		goto err;
+	if (!i915_gem_object_is_lmem(vma->obj)) {
+		if (GEM_WARN_ON(!i915_vma_is_map_and_fenceable(vma))) {
+			err = -ENODEV;
+			goto err;
+		}
 	}
 
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
@@ -458,9 +461,19 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 
 	ptr = READ_ONCE(vma->iomap);
 	if (ptr == NULL) {
-		ptr = io_mapping_map_wc(&i915_vm_to_ggtt(vma->vm)->iomap,
-					vma->node.start,
-					vma->node.size);
+		/*
+		 * TODO: consider just using i915_gem_object_pin_map() for lmem
+		 * instead, which already supports mapping non-contiguous chunks
+		 * of pages, that way we can also drop the
+		 * I915_BO_ALLOC_CONTIGUOUS when allocating the object.
+		 */
+		if (i915_gem_object_is_lmem(vma->obj))
+			ptr = i915_gem_object_lmem_io_map(vma->obj, 0,
+							  vma->obj->base.size);
+		else
+			ptr = io_mapping_map_wc(&i915_vm_to_ggtt(vma->vm)->iomap,
+						vma->node.start,
+						vma->node.size);
 		if (ptr == NULL) {
 			err = -ENOMEM;
 			goto err;