diff mbox series

[v4,6/8] drm/v3d: Support Big/Super Pages when writing out PTEs

Message ID 20240428124426.309096-7-mcanal@igalia.com (mailing list archive)
State New, archived
Headers show
Series drm/v3d: Enable Big and Super Pages | expand

Commit Message

Maíra Canal April 28, 2024, 12:40 p.m. UTC
The V3D MMU also supports 64KB and 1MB pages, called big and super pages,
respectively. In order to set a 64KB page or 1MB page in the MMU, we need
to make sure that page table entries for all 4KB pages within a big/super
page must be correctly configured.

In order to create a big/super page, we need a contiguous memory region.
That's why we use a separate mountpoint with THP enabled. In order to
place the page table entries in the MMU, we iterate over the 16 4KB pages
(for big pages) or 256 4KB pages (for super pages) and insert the PTE.

Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
---
 drivers/gpu/drm/v3d/v3d_drv.h |  1 +
 drivers/gpu/drm/v3d/v3d_mmu.c | 52 ++++++++++++++++++++++++++---------
 2 files changed, 40 insertions(+), 13 deletions(-)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index e1f291db68de..3276eef280ef 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -18,6 +18,7 @@  struct platform_device;
 struct reset_control;
 
 #define V3D_MMU_PAGE_SHIFT 12
+#define V3D_PAGE_FACTOR (PAGE_SIZE >> V3D_MMU_PAGE_SHIFT)
 
 #define V3D_MAX_QUEUES (V3D_CPU + 1)
 
diff --git a/drivers/gpu/drm/v3d/v3d_mmu.c b/drivers/gpu/drm/v3d/v3d_mmu.c
index 14f3af40d6f6..2e0b31e373b2 100644
--- a/drivers/gpu/drm/v3d/v3d_mmu.c
+++ b/drivers/gpu/drm/v3d/v3d_mmu.c
@@ -25,9 +25,16 @@ 
  * superpage bit set.
  */
 #define V3D_PTE_SUPERPAGE BIT(31)
+#define V3D_PTE_BIGPAGE BIT(30)
 #define V3D_PTE_WRITEABLE BIT(29)
 #define V3D_PTE_VALID BIT(28)
 
+static bool v3d_mmu_is_aligned(u32 page, u32 page_address, size_t alignment)
+{
+	return IS_ALIGNED(page, alignment >> V3D_MMU_PAGE_SHIFT) &&
+		IS_ALIGNED(page_address, alignment >> V3D_MMU_PAGE_SHIFT);
+}
+
 static int v3d_mmu_flush_all(struct v3d_dev *v3d)
 {
 	int ret;
@@ -87,19 +94,38 @@  void v3d_mmu_insert_ptes(struct v3d_bo *bo)
 	struct drm_gem_shmem_object *shmem_obj = &bo->base;
 	struct v3d_dev *v3d = to_v3d_dev(shmem_obj->base.dev);
 	u32 page = bo->node.start;
-	u32 page_prot = V3D_PTE_WRITEABLE | V3D_PTE_VALID;
-	struct sg_dma_page_iter dma_iter;
-
-	for_each_sgtable_dma_page(shmem_obj->sgt, &dma_iter, 0) {
-		dma_addr_t dma_addr = sg_page_iter_dma_address(&dma_iter);
-		u32 page_address = dma_addr >> V3D_MMU_PAGE_SHIFT;
-		u32 pte = page_prot | page_address;
-		u32 i;
-
-		BUG_ON(page_address + (PAGE_SIZE >> V3D_MMU_PAGE_SHIFT) >=
-		       BIT(24));
-		for (i = 0; i < PAGE_SIZE >> V3D_MMU_PAGE_SHIFT; i++)
-			v3d->pt[page++] = pte + i;
+	struct scatterlist *sgl;
+	unsigned int count;
+
+	for_each_sgtable_dma_sg(shmem_obj->sgt, sgl, count) {
+		dma_addr_t dma_addr = sg_dma_address(sgl);
+		u32 pfn = dma_addr >> V3D_MMU_PAGE_SHIFT;
+		unsigned int len = sg_dma_len(sgl);
+
+		while (len > 0) {
+			u32 page_prot = V3D_PTE_WRITEABLE | V3D_PTE_VALID;
+			u32 page_address = page_prot | pfn;
+			unsigned int i, page_size;
+
+			BUG_ON(pfn + V3D_PAGE_FACTOR >= BIT(24));
+
+			if (len >= SZ_1M && v3d_mmu_is_aligned(page, page_address, SZ_1M)) {
+				page_size = SZ_1M;
+				page_address |= V3D_PTE_SUPERPAGE;
+			} else if (len >= SZ_64K && v3d_mmu_is_aligned(page, page_address, SZ_64K)) {
+				page_size = SZ_64K;
+				page_address |= V3D_PTE_BIGPAGE;
+			} else {
+				page_size = SZ_4K;
+			}
+
+			for (i = 0; i < page_size >> V3D_MMU_PAGE_SHIFT; i++) {
+				v3d->pt[page++] = page_address + i;
+				pfn++;
+			}
+
+			len -= page_size;
+		}
 	}
 
 	WARN_ON_ONCE(page - bo->node.start !=