/*
 * Copyright 2013 Advanced Micro Devices, Inc.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 * OTHER DEALINGS IN THE SOFTWARE.
 *
 * Authors: Alex Deucher
 */

#include "radeon.h"
#include "radeon_asic.h"
#include "rv770d.h"

/**
 * rv770_copy_dma - copy pages using the DMA engine
 *
 * @rdev: radeon_device pointer
 * @src_offset: src GPU address
 * @dst_offset: dst GPU address
 * @num_gpu_pages: number of GPU pages to xfer
 * @resv: reservation object to sync to
 *
 * Copy GPU paging using the DMA engine (r7xx).
 * Used by the radeon ttm implementation to move pages if
 * registered as the asic copy callback.
 */
struct radeon_fence *rv770_copy_dma(struct radeon_device *rdev,
				    uint64_t src_offset, uint64_t dst_offset,
				    unsigned num_gpu_pages,
				    struct dma_resv *resv)
{
	struct radeon_fence *fence;
	struct radeon_sync sync;
	int ring_index = rdev->asic->copy.dma_ring_index;
	struct radeon_ring *ring = &rdev->ring[ring_index];
	u32 size_in_dw, cur_size_in_dw;
	int i, num_loops;
	int r = 0;

	radeon_sync_create(&sync);

	size_in_dw = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT) / 4;
	num_loops = DIV_ROUND_UP(size_in_dw, 0xFFFF);
	r = radeon_ring_lock(rdev, ring, num_loops * 5 + 8);
	if (r) {
		DRM_ERROR("radeon: moving bo (%d).\n", r);
		radeon_sync_free(rdev, &sync, NULL);
		return ERR_PTR(r);
	}

	radeon_sync_resv(rdev, &sync, resv, false);
	radeon_sync_rings(rdev, &sync, ring->idx);

	for (i = 0; i < num_loops; i++) {
		cur_size_in_dw = size_in_dw;
		if (cur_size_in_dw > 0xFFFF)
			cur_size_in_dw = 0xFFFF;
		size_in_dw -= cur_size_in_dw;
		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_COPY, 0, 0, cur_size_in_dw));
		radeon_ring_write(ring, dst_offset & 0xfffffffc);
		radeon_ring_write(ring, src_offset & 0xfffffffc);
		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xff);
		radeon_ring_write(ring, upper_32_bits(src_offset) & 0xff);
		src_offset += cur_size_in_dw * 4;
		dst_offset += cur_size_in_dw * 4;
	}

	r = radeon_fence_emit(rdev, &fence, ring->idx);
	if (r) {
		radeon_ring_unlock_undo(rdev, ring);
		radeon_sync_free(rdev, &sync, NULL);
		return ERR_PTR(r);
	}

	radeon_ring_unlock_commit(rdev, ring, false);
	radeon_sync_free(rdev, &sync, fence);

	return fence;
}