drm/i915: add I915_BO_ALLOC_GPU_ONLY

If the user doesn't require CPU access for the buffer, then
ALLOC_GPU_ONLY should be used, in order to prioritise allocating in the
non-mappable portion of LMEM, on devices with small BAR.

v2(Thomas):
  - The BO_ALLOC_TOPDOWN naming here is poor, since this is pure lies on
    systems that don't even have small BAR. A better name is GPU_ONLY,
    which is accurate regardless of the configuration.
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Acked-by: Nirmoy Das <nirmoy.das@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220225145502.331818-3-matthew.auld@intel.com

drivers/gpu/drm/i915/gem/i915_gem_object_types.h

@@ -319,16 +319,23 @@ struct drm_i915_gem_object {
 #define I915_BO_ALLOC_PM_VOLATILE BIT(4)
 /* Object needs to be restored early using memcpy during resume */
 #define I915_BO_ALLOC_PM_EARLY    BIT(5)
+/*
+ * Object is likely never accessed by the CPU. This will prioritise the BO to be
+ * allocated in the non-mappable portion of lmem. This is merely a hint, and if
+ * dealing with userspace objects the CPU fault handler is free to ignore this.
+ */
+#define I915_BO_ALLOC_GPU_ONLY	  BIT(6)
 #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | \
 			     I915_BO_ALLOC_VOLATILE | \
 			     I915_BO_ALLOC_CPU_CLEAR | \
 			     I915_BO_ALLOC_USER | \
 			     I915_BO_ALLOC_PM_VOLATILE | \
-			     I915_BO_ALLOC_PM_EARLY)
-#define I915_BO_READONLY          BIT(6)
-#define I915_TILING_QUIRK_BIT     7 /* unknown swizzling; do not release! */
-#define I915_BO_PROTECTED         BIT(8)
-#define I915_BO_WAS_BOUND_BIT     9
+			     I915_BO_ALLOC_PM_EARLY | \
+			     I915_BO_ALLOC_GPU_ONLY)
+#define I915_BO_READONLY          BIT(7)
+#define I915_TILING_QUIRK_BIT     8 /* unknown swizzling; do not release! */
+#define I915_BO_PROTECTED         BIT(9)
+#define I915_BO_WAS_BOUND_BIT     10
 	/**
 	 * @mem_flags - Mutable placement-related flags
 	 *

drivers/gpu/drm/i915/gem/i915_gem_pages.c

@@ -358,6 +358,9 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 	    !i915_gem_object_has_iomem(obj))
 		return ERR_PTR(-ENXIO);
 
+	if (WARN_ON_ONCE(obj->flags & I915_BO_ALLOC_GPU_ONLY))
+		return ERR_PTR(-EINVAL);
+
 	assert_object_held(obj);
 
 	pinned = !(type & I915_MAP_OVERRIDE);

drivers/gpu/drm/i915/gem/i915_gem_region.c

@@ -45,6 +45,11 @@ i915_gem_object_create_region(struct intel_memory_region *mem,
 
 	GEM_BUG_ON(flags & ~I915_BO_ALLOC_FLAGS);
 
+	if (WARN_ON_ONCE(flags & I915_BO_ALLOC_GPU_ONLY &&
+			 (flags & I915_BO_ALLOC_CPU_CLEAR ||
+			  flags & I915_BO_ALLOC_PM_EARLY)))
+		return ERR_PTR(-EINVAL);
+
 	if (!mem)
 		return ERR_PTR(-ENODEV);
 

drivers/gpu/drm/i915/gem/i915_gem_ttm.c

@@ -129,11 +129,15 @@ i915_ttm_place_from_region(const struct intel_memory_region *mr,
 	place->mem_type = intel_region_to_ttm_type(mr);
 
 	if (flags & I915_BO_ALLOC_CONTIGUOUS)
-		place->flags = TTM_PL_FLAG_CONTIGUOUS;
+		place->flags |= TTM_PL_FLAG_CONTIGUOUS;
 	if (mr->io_size && mr->io_size < mr->total) {
+		if (flags & I915_BO_ALLOC_GPU_ONLY) {
+			place->flags |= TTM_PL_FLAG_TOPDOWN;
+		} else {
 			place->fpfn = 0;
 			place->lpfn = mr->io_size >> PAGE_SHIFT;
 		}
+	}
 }
 
 static void
@@ -890,6 +894,9 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf)
 	if (!obj)
 		return VM_FAULT_SIGBUS;
 
+	if (obj->flags & I915_BO_ALLOC_GPU_ONLY)
+		return -EINVAL;
+
 	/* Sanity check that we allow writing into this object */
 	if (unlikely(i915_gem_object_is_readonly(obj) &&
 		     area->vm_flags & VM_WRITE))

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

@@ -456,7 +456,9 @@ static int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size)
 	struct i915_vma *vma;
 	int ret;
 
-	obj = i915_gem_object_create_lmem(i915, size, I915_BO_ALLOC_VOLATILE);
+	obj = i915_gem_object_create_lmem(i915, size,
+					  I915_BO_ALLOC_VOLATILE |
+					  I915_BO_ALLOC_GPU_ONLY);
 	if (IS_ERR(obj))
 		obj = i915_gem_object_create_stolen(i915, size);
 	if (IS_ERR(obj))

drivers/gpu/drm/i915/i915_vma.c

@@ -540,6 +540,9 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 	void __iomem *ptr;
 	int err;
 
+	if (WARN_ON_ONCE(vma->obj->flags & I915_BO_ALLOC_GPU_ONLY))
+		return IO_ERR_PTR(-EINVAL);
+
 	if (!i915_gem_object_is_lmem(vma->obj)) {
 		if (GEM_WARN_ON(!i915_vma_is_map_and_fenceable(vma))) {
 			err = -ENODEV;

drivers/gpu/drm/i915/intel_region_ttm.c

@@ -199,14 +199,19 @@ intel_region_ttm_resource_alloc(struct intel_memory_region *mem,
 	struct ttm_resource *res;
 	int ret;
 
+	if (flags & I915_BO_ALLOC_CONTIGUOUS)
+		place.flags |= TTM_PL_FLAG_CONTIGUOUS;
 	if (mem->io_size && mem->io_size < mem->total) {
+		if (flags & I915_BO_ALLOC_GPU_ONLY) {
+			place.flags |= TTM_PL_FLAG_TOPDOWN;
+		} else {
 			place.fpfn = 0;
 			place.lpfn = mem->io_size >> PAGE_SHIFT;
 		}
+	}
 
 	mock_bo.base.size = size;
 	mock_bo.bdev = &mem->i915->bdev;
-	place.flags = flags;
 
 	ret = man->func->alloc(man, &mock_bo, &place, &res);
 	if (ret == -ENOSPC)

drivers/gpu/drm/i915/selftests/mock_region.c

@@ -22,17 +22,12 @@ static void mock_region_put_pages(struct drm_i915_gem_object *obj,
 
 static int mock_region_get_pages(struct drm_i915_gem_object *obj)
 {
-	unsigned int flags;
 	struct sg_table *pages;
 	int err;
 
-	flags = 0;
-	if (obj->flags & I915_BO_ALLOC_CONTIGUOUS)
-		flags |= TTM_PL_FLAG_CONTIGUOUS;
-
 	obj->mm.res = intel_region_ttm_resource_alloc(obj->mm.region,
 						      obj->base.size,
-						      flags);
+						      obj->flags);
 	if (IS_ERR(obj->mm.res))
 		return PTR_ERR(obj->mm.res);