drm/v3d: Use gemfs/THP in BO creation if available

Although Big/Super Pages could appear naturally, it would be quite hard
to have 1MB or 64KB allocated contiguously naturally. Therefore, we can
force the creation of large pages allocated contiguously by using a
mountpoint with "huge=within_size" enabled.

Therefore, as V3D has a mountpoint with "huge=within_size" (if user has
THP enabled), use this mountpoint for BO creation if available. This
will allow us to create large pages allocated contiguously and make use
of Big/Super Pages.

Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240923141348.2422499-10-mcanal@igalia.com

diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c
index 427a1c405b190f104733b57ef3da1395bd51d5cd..cd85f997b058c02da4adea5ff86c11d658eefe36 100644 (file)
--- a/drivers/gpu/drm/v3d/v3d_bo.c
+++ b/drivers/gpu/drm/v3d/v3d_bo.c
@@ -107,6 +107,7 @@ v3d_bo_create_finish(struct drm_gem_object *obj)
        struct v3d_dev *v3d = to_v3d_dev(obj->dev);
        struct v3d_bo *bo = to_v3d_bo(obj);
        struct sg_table *sgt;
+       u64 align;
        int ret;
 
        /* So far we pin the BO in the MMU for its lifetime, so use
@@ -116,6 +117,15 @@ v3d_bo_create_finish(struct drm_gem_object *obj)
        if (IS_ERR(sgt))
                return PTR_ERR(sgt);
 
+       if (!v3d->gemfs)
+               align = SZ_4K;
+       else if (obj->size >= SZ_1M)
+               align = SZ_1M;
+       else if (obj->size >= SZ_64K)
+               align = SZ_64K;
+       else
+               align = SZ_4K;
+
        spin_lock(&v3d->mm_lock);
        /* Allocate the object's space in the GPU's page tables.
         * Inserting PTEs will happen later, but the offset is for the
@@ -123,7 +133,7 @@ v3d_bo_create_finish(struct drm_gem_object *obj)
         */
        ret = drm_mm_insert_node_generic(&v3d->mm, &bo->node,
                                         obj->size >> V3D_MMU_PAGE_SHIFT,
-                                        SZ_4K >> V3D_MMU_PAGE_SHIFT, 0, 0);
+                                        align >> V3D_MMU_PAGE_SHIFT, 0, 0);
        spin_unlock(&v3d->mm_lock);
        if (ret)
                return ret;
@@ -143,10 +153,17 @@ struct v3d_bo *v3d_bo_create(struct drm_device *dev, struct drm_file *file_priv,
                             size_t unaligned_size)
 {
        struct drm_gem_shmem_object *shmem_obj;
+       struct v3d_dev *v3d = to_v3d_dev(dev);
        struct v3d_bo *bo;
        int ret;
 
-       shmem_obj = drm_gem_shmem_create(dev, unaligned_size);
+       /* Let the user opt out of allocating the BOs with THP */
+       if (v3d->gemfs)
+               shmem_obj = drm_gem_shmem_create_with_mnt(dev, unaligned_size,
+                                                         v3d->gemfs);
+       else
+               shmem_obj = drm_gem_shmem_create(dev, unaligned_size);
+
        if (IS_ERR(shmem_obj))
                return ERR_CAST(shmem_obj);
        bo = to_v3d_bo(&shmem_obj->base);