drm/radeon: add proper support for RADEON_VM_BLOCK_SIZE v2

This patch makes it possible to decide how many address
bits are spend on the page directory vs the page tables.

v2: remove unintended change

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index dbb5b2e..8d0f177 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -5378,6 +5378,7 @@
 	       (u32)(rdev->dummy_page.addr >> 12));
 	WREG32(VM_CONTEXT1_CNTL2, 4);
 	WREG32(VM_CONTEXT1_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(1) |
+				PAGE_TABLE_BLOCK_SIZE(RADEON_VM_BLOCK_SIZE - 9) |
 				RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
 				RANGE_PROTECTION_FAULT_ENABLE_DEFAULT |
 				DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h
index 2138732..0b27ea0 100644
--- a/drivers/gpu/drm/radeon/cikd.h
+++ b/drivers/gpu/drm/radeon/cikd.h
@@ -482,6 +482,7 @@
 #define		READ_PROTECTION_FAULT_ENABLE_DEFAULT		(1 << 16)
 #define		WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT		(1 << 18)
 #define		WRITE_PROTECTION_FAULT_ENABLE_DEFAULT		(1 << 19)
+#define		PAGE_TABLE_BLOCK_SIZE(x)			(((x) & 0xF) << 24)
 #define VM_CONTEXT1_CNTL				0x1414
 #define VM_CONTEXT0_CNTL2				0x1430
 #define VM_CONTEXT1_CNTL2				0x1434
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 5e8db9b..1d3209f 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1268,6 +1268,7 @@
 	       (u32)(rdev->dummy_page.addr >> 12));
 	WREG32(VM_CONTEXT1_CNTL2, 4);
 	WREG32(VM_CONTEXT1_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(1) |
+				PAGE_TABLE_BLOCK_SIZE(RADEON_VM_BLOCK_SIZE - 9) |
 				RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
 				RANGE_PROTECTION_FAULT_ENABLE_DEFAULT |
 				DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h
index d996033..2e12e4d 100644
--- a/drivers/gpu/drm/radeon/nid.h
+++ b/drivers/gpu/drm/radeon/nid.h
@@ -128,6 +128,7 @@
 #define		READ_PROTECTION_FAULT_ENABLE_DEFAULT		(1 << 16)
 #define		WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT		(1 << 18)
 #define		WRITE_PROTECTION_FAULT_ENABLE_DEFAULT		(1 << 19)
+#define		PAGE_TABLE_BLOCK_SIZE(x)			(((x) & 0xF) << 24)
 #define VM_CONTEXT1_CNTL				0x1414
 #define VM_CONTEXT0_CNTL2				0x1430
 #define VM_CONTEXT1_CNTL2				0x1434
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index f8d5b65..a128a4f 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -964,6 +964,8 @@
  */
 int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm)
 {
+	const unsigned align = min(RADEON_VM_PTB_ALIGN_SIZE,
+		RADEON_VM_PTE_COUNT * 8);
 	unsigned pd_size, pd_entries, pts_size;
 	int r;
 
@@ -985,7 +987,7 @@
 		return -ENOMEM;
 	}
 
-	r = radeon_bo_create(rdev, pd_size, RADEON_VM_PTB_ALIGN_SIZE, false,
+	r = radeon_bo_create(rdev, pd_size, align, false,
 			     RADEON_GEM_DOMAIN_VRAM, NULL,
 			     &vm->page_directory);
 	if (r)
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 22ecbc0..9739d71 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -4095,6 +4095,7 @@
 	       (u32)(rdev->dummy_page.addr >> 12));
 	WREG32(VM_CONTEXT1_CNTL2, 4);
 	WREG32(VM_CONTEXT1_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(1) |
+				PAGE_TABLE_BLOCK_SIZE(RADEON_VM_BLOCK_SIZE - 9) |
 				RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
 				RANGE_PROTECTION_FAULT_ENABLE_DEFAULT |
 				DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 683532f..da8f867 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -362,6 +362,7 @@
 #define		READ_PROTECTION_FAULT_ENABLE_DEFAULT		(1 << 16)
 #define		WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT		(1 << 18)
 #define		WRITE_PROTECTION_FAULT_ENABLE_DEFAULT		(1 << 19)
+#define		PAGE_TABLE_BLOCK_SIZE(x)			(((x) & 0xF) << 24)
 #define VM_CONTEXT1_CNTL				0x1414
 #define VM_CONTEXT0_CNTL2				0x1430
 #define VM_CONTEXT1_CNTL2				0x1434