[PATCH v3 12/16] accel/thames: Install memory mappings populated and dirty

[Tomeu Vizoso]

The GEM DMA mmap helper maps the whole buffer up front, but with pages
that fault on their first write, since the A53 in the J722S has no
hardware dirty-bit management. The GEM shmem helper maps by page fault,
one at each page's first touch and another at its first write, which
its write-notify needs. Neither helper can install the pages writable
and dirty, so the driver sets the protection itself: for contiguous
buffers it calls dma_mmap_pages() with it, and for the others it
installs the pages with remap_pfn_range().

This saves 20% of the total time in the first invoke of a model on the
J722S.

Assisted-by: LLM
Signed-off-by: Tomeu Vizoso <tomeu@xxxxxxxxxxxxxxx>
---
 drivers/accel/thames/thames_gem.c | 76 +++++++++++++++++++++++++++++++++++++--
 1 file changed, 73 insertions(+), 3 deletions(-)

diff --git a/drivers/accel/thames/thames_gem.c b/drivers/accel/thames/thames_gem.c
index 5a4dc497768f..9f55169c6370 100644
--- a/drivers/accel/thames/thames_gem.c
+++ b/drivers/accel/thames/thames_gem.c
@@ -808,12 +808,82 @@ static void thames_gem_shmem_bo_free(struct drm_gem_object *obj)
 	drm_gem_shmem_free(&bo->shmem);
 }
 
+/*
+ * Installed dirty and writable: the A53s have no hardware dirty-bit management,
+ * so every first write would fault.
+ */
+static int thames_gem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
+{
+	struct drm_gem_dma_object *dma_obj = to_drm_gem_dma_obj(obj);
+	pgprot_t prot;
+	int ret;
+
+	vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node);
+	vm_flags_mod(vma, VM_DONTDUMP | VM_DONTEXPAND, VM_PFNMAP);
+
+	prot = vm_get_page_prot(vma->vm_flags);
+	if (vma->vm_flags & VM_WRITE)
+		prot = pte_pgprot(pte_mkdirty(pte_mkwrite_novma(pfn_pte(0, prot))));
+	vma->vm_page_prot = prot;
+
+	ret = dma_mmap_pages(drm_dev_dma_dev(obj->dev), vma, vma->vm_end - vma->vm_start,
+			     virt_to_page(dma_obj->vaddr));
+	if (ret)
+		drm_gem_vm_close(vma);
+
+	return ret;
+}
+
+/*
+ * Every page installed now, dirty and writable: they are pinned for the
+ * object's life, and the helper would take two faults on each.
+ */
+static int thames_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
+{
+	struct thames_gem_object *bo = to_thames_bo(obj);
+	unsigned long addr = vma->vm_start;
+	struct scatterlist *sg;
+	pgprot_t prot;
+	unsigned int i;
+	int ret;
+
+	if (vma_is_cow_mapping(vma))
+		return -EINVAL;
+
+	vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
+
+	prot = vm_get_page_prot(vma->vm_flags);
+	if (vma->vm_flags & VM_WRITE)
+		prot = pte_pgprot(pte_mkdirty(pte_mkwrite_novma(pfn_pte(0, prot))));
+	vma->vm_page_prot = prot;
+
+	for_each_sgtable_sg(bo->shmem.sgt, sg, i) {
+		unsigned long len = min_t(unsigned long, sg->length, vma->vm_end - addr);
+
+		ret = remap_pfn_range(vma, addr, page_to_pfn(sg_page(sg)), len, prot);
+		if (ret)
+			return ret;
+
+		addr += len;
+		if (addr == vma->vm_end)
+			break;
+	}
+
+	return 0;
+}
+
+/* Only the GEM reference: the pages are pinned for the object's life. */
+static const struct vm_operations_struct thames_gem_shmem_vm_ops = {
+	.open = drm_gem_vm_open,
+	.close = drm_gem_vm_close,
+};
+
 static const struct drm_gem_object_funcs thames_gem_funcs = {
 	.free = thames_gem_bo_free,
 	.print_info = drm_gem_dma_object_print_info,
 	.get_sg_table = drm_gem_dma_object_get_sg_table,
 	.vmap = drm_gem_dma_object_vmap,
-	.mmap = drm_gem_dma_object_mmap,
+	.mmap = thames_gem_mmap,
 	.vm_ops = &drm_gem_dma_vm_ops,
 };
 
@@ -825,8 +895,8 @@ static const struct drm_gem_object_funcs thames_gem_shmem_funcs = {
 	.get_sg_table = drm_gem_shmem_object_get_sg_table,
 	.vmap = drm_gem_shmem_object_vmap,
 	.vunmap = drm_gem_shmem_object_vunmap,
-	.mmap = drm_gem_shmem_object_mmap,
-	.vm_ops = &drm_gem_shmem_vm_ops,
+	.mmap = thames_gem_shmem_mmap,
+	.vm_ops = &thames_gem_shmem_vm_ops,
 };
 
 int thames_ioctl_bo_create(struct drm_device *ddev, void *data, struct drm_file *file)

-- 
2.54.0