[PATCH v2 6/6] drm/amdgpu: do not allocate entries separately

[Nirmoy Das]

Allocate PD/PT entries while allocating VM BOs and use that
instead of allocating those entries separately.

v2: create a new var for num entries.

Signed-off-by: Nirmoy Das <nirmoy.das at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 34 +++++++++++++++-----------
 1 file changed, 20 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index d723873df765..70df453863cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -876,6 +876,7 @@ static int amdgpu_vm_pt_create(struct amdgpu_device *adev,
 	struct amdgpu_bo *bo;
 	struct dma_resv *resv;
 	int r;
+	unsigned int num_entries;

 	memset(&bp, 0, sizeof(bp));

@@ -885,7 +886,14 @@ static int amdgpu_vm_pt_create(struct amdgpu_device *adev,
 	bp.domain = amdgpu_bo_get_preferred_pin_domain(adev, bp.domain);
 	bp.flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |
 		AMDGPU_GEM_CREATE_CPU_GTT_USWC;
-	bp.bo_ptr_size = sizeof(struct amdgpu_bo_vm);
+
+	if (level < AMDGPU_VM_PTB)
+		num_entries = amdgpu_vm_num_entries(adev, level);
+	else
+		num_entries = 0;
+
+	bp.bo_ptr_size = struct_size((*vmbo), entries, num_entries);
+
 	if (vm->use_cpu_for_update)
 		bp.flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;

@@ -956,19 +964,14 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
 	struct amdgpu_bo_vm *pt;
 	int r;

-	if (cursor->level < AMDGPU_VM_PTB && !entry->entries) {
-		unsigned num_entries;
-
-		num_entries = amdgpu_vm_num_entries(adev, cursor->level);
-		entry->entries = kvmalloc_array(num_entries,
-						sizeof(*entry->entries),
-						GFP_KERNEL | __GFP_ZERO);
-		if (!entry->entries)
-			return -ENOMEM;
-	}
-
-	if (entry->base.bo)
+	if (entry->base.bo) {
+		if (cursor->level < AMDGPU_VM_PTB)
+			entry->entries =
+				to_amdgpu_bo_vm(entry->base.bo)->entries;
+		else
+			entry->entries = NULL;
 		return 0;
+	}

 	r = amdgpu_vm_pt_create(adev, vm, cursor->level, immediate, &pt);
 	if (r)
@@ -980,6 +983,10 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
 	pt_bo = &pt->bo;
 	pt_bo->parent = amdgpu_bo_ref(cursor->parent->base.bo);
 	amdgpu_vm_bo_base_init(&entry->base, vm, pt_bo);
+	if (cursor->level < AMDGPU_VM_PTB)
+		entry->entries = pt->entries;
+	else
+		entry->entries = NULL;

 	r = amdgpu_vm_clear_bo(adev, vm, pt_bo, immediate);
 	if (r)
@@ -1009,7 +1016,6 @@ static void amdgpu_vm_free_table(struct amdgpu_vm_pt *entry)
 		amdgpu_bo_unref(&shadow);
 		amdgpu_bo_unref(&entry->base.bo);
 	}
-	kvfree(entry->entries);
 	entry->entries = NULL;
 }

--
2.31.1