drm/amdgpu: use 256 bit buffers for all wb allocations (v2)

May waste a bit of memory, but simplifies the interface
significantly.

v2: convert internal accounting to use 256bit slots
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -1131,10 +1131,6 @@ struct amdgpu_wb {
 
 int amdgpu_wb_get(struct amdgpu_device *adev, u32 *wb);
 void amdgpu_wb_free(struct amdgpu_device *adev, u32 wb);
-int amdgpu_wb_get_64bit(struct amdgpu_device *adev, u32 *wb);
-int amdgpu_wb_get_256bit(struct amdgpu_device *adev, u32 *wb);
-void amdgpu_wb_free_64bit(struct amdgpu_device *adev, u32 wb);
-void amdgpu_wb_free_256bit(struct amdgpu_device *adev, u32 wb);
 
 void amdgpu_get_pcie_info(struct amdgpu_device *adev);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -504,7 +504,8 @@ static int amdgpu_wb_init(struct amdgpu_device *adev)
 	int r;
 
 	if (adev->wb.wb_obj == NULL) {
-		r = amdgpu_bo_create_kernel(adev, AMDGPU_MAX_WB * sizeof(uint32_t),
+		/* AMDGPU_MAX_WB * sizeof(uint32_t) * 8 = AMDGPU_MAX_WB 256bit slots */
+		r = amdgpu_bo_create_kernel(adev, AMDGPU_MAX_WB * sizeof(uint32_t) * 8,
 					    PAGE_SIZE, AMDGPU_GEM_DOMAIN_GTT,
 					    &adev->wb.wb_obj, &adev->wb.gpu_addr,
 					    (void **)&adev->wb.wb);
@@ -535,47 +536,10 @@ static int amdgpu_wb_init(struct amdgpu_device *adev)
 int amdgpu_wb_get(struct amdgpu_device *adev, u32 *wb)
 {
 	unsigned long offset = find_first_zero_bit(adev->wb.used, adev->wb.num_wb);
-	if (offset < adev->wb.num_wb) {
-		__set_bit(offset, adev->wb.used);
-		*wb = offset;
-		return 0;
-	} else {
-		return -EINVAL;
-	}
-}
 
-/**
- * amdgpu_wb_get_64bit - Allocate a wb entry
- *
- * @adev: amdgpu_device pointer
- * @wb: wb index
- *
- * Allocate a wb slot for use by the driver (all asics).
- * Returns 0 on success or -EINVAL on failure.
- */
-int amdgpu_wb_get_64bit(struct amdgpu_device *adev, u32 *wb)
-{
-	unsigned long offset = bitmap_find_next_zero_area_off(adev->wb.used,
-				adev->wb.num_wb, 0, 2, 7, 0);
-	if ((offset + 1) < adev->wb.num_wb) {
+	if (offset < adev->wb.num_wb) {
 		__set_bit(offset, adev->wb.used);
-		__set_bit(offset + 1, adev->wb.used);
-		*wb = offset;
-		return 0;
-	} else {
-		return -EINVAL;
-	}
-}
-
-int amdgpu_wb_get_256bit(struct amdgpu_device *adev, u32 *wb)
-{
-	int i = 0;
-	unsigned long offset = bitmap_find_next_zero_area_off(adev->wb.used,
-				adev->wb.num_wb, 0, 8, 63, 0);
-	if ((offset + 7) < adev->wb.num_wb) {
-		for (i = 0; i < 8; i++)
-			__set_bit(offset + i, adev->wb.used);
-		*wb = offset;
+		*wb = offset * 8; /* convert to dw offset */
 		return 0;
 	} else {
 		return -EINVAL;
@@ -596,39 +560,6 @@ void amdgpu_wb_free(struct amdgpu_device *adev, u32 wb)
 		__clear_bit(wb, adev->wb.used);
 }
 
-/**
- * amdgpu_wb_free_64bit - Free a wb entry
- *
- * @adev: amdgpu_device pointer
- * @wb: wb index
- *
- * Free a wb slot allocated for use by the driver (all asics)
- */
-void amdgpu_wb_free_64bit(struct amdgpu_device *adev, u32 wb)
-{
-	if ((wb + 1) < adev->wb.num_wb) {
-		__clear_bit(wb, adev->wb.used);
-		__clear_bit(wb + 1, adev->wb.used);
-	}
-}
-
-/**
- * amdgpu_wb_free_256bit - Free a wb entry
- *
- * @adev: amdgpu_device pointer
- * @wb: wb index
- *
- * Free a wb slot allocated for use by the driver (all asics)
- */
-void amdgpu_wb_free_256bit(struct amdgpu_device *adev, u32 wb)
-{
-	int i = 0;
-
-	if ((wb + 7) < adev->wb.num_wb)
-		for (i = 0; i < 8; i++)
-			__clear_bit(wb + i, adev->wb.used);
-}
-
 /**
  * amdgpu_vram_location - try to find VRAM location
  * @adev: amdgpu device structure holding all necessary informations

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c

@@ -184,20 +184,6 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 			return r;
 	}
 
-	if (ring->funcs->support_64bit_ptrs) {
-		r = amdgpu_wb_get_64bit(adev, &ring->rptr_offs);
-		if (r) {
-			dev_err(adev->dev, "(%d) ring rptr_offs wb alloc failed\n", r);
-			return r;
-		}
-
-		r = amdgpu_wb_get_64bit(adev, &ring->wptr_offs);
-		if (r) {
-			dev_err(adev->dev, "(%d) ring wptr_offs wb alloc failed\n", r);
-			return r;
-		}
-
-	} else {
 	r = amdgpu_wb_get(adev, &ring->rptr_offs);
 	if (r) {
 		dev_err(adev->dev, "(%d) ring rptr_offs wb alloc failed\n", r);
@@ -210,22 +196,11 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		return r;
 	}
 
-	}
-
-	if (amdgpu_sriov_vf(adev) && ring->funcs->type == AMDGPU_RING_TYPE_GFX) {
-		r = amdgpu_wb_get_256bit(adev, &ring->fence_offs);
-		if (r) {
-			dev_err(adev->dev, "(%d) ring fence_offs wb alloc failed\n", r);
-			return r;
-		}
-
-	} else {
 	r = amdgpu_wb_get(adev, &ring->fence_offs);
 	if (r) {
 		dev_err(adev->dev, "(%d) ring fence_offs wb alloc failed\n", r);
 		return r;
 	}
-	}
 
 	r = amdgpu_wb_get(adev, &ring->cond_exe_offs);
 	if (r) {
@@ -286,18 +261,10 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring)
 {
 	ring->ready = false;
 
-	if (ring->funcs->support_64bit_ptrs) {
-		amdgpu_wb_free_64bit(ring->adev, ring->rptr_offs);
-		amdgpu_wb_free_64bit(ring->adev, ring->wptr_offs);
-	} else {
 	amdgpu_wb_free(ring->adev, ring->rptr_offs);
 	amdgpu_wb_free(ring->adev, ring->wptr_offs);
-	}
 
 	amdgpu_wb_free(ring->adev, ring->cond_exe_offs);
-	if (amdgpu_sriov_vf(ring->adev) && ring->funcs->type == AMDGPU_RING_TYPE_GFX)
-		amdgpu_wb_free_256bit(ring->adev, ring->fence_offs);
-	else
 	amdgpu_wb_free(ring->adev, ring->fence_offs);
 
 	amdgpu_bo_free_kernel(&ring->ring_obj,