On Tue, 4 Apr 2023 12:01:39 -0700
Brett Creeley <brett.creeley@xxxxxxx> wrote:
> +static int
> +pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio,
> + struct rb_root_cached *ranges, u32 nnodes,
> + u64 *page_size)
> +{
> + struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
> + u64 region_start, region_size, region_page_size;
> + struct pds_lm_dirty_region_info *region_info;
> + struct interval_tree_node *node = NULL;
> + struct pci_dev *pdev = pds_vfio->pdev;
> + u8 max_regions = 0, num_regions;
> + dma_addr_t regions_dma = 0;
> + u32 num_ranges = nnodes;
> + u32 page_count;
> + u16 len;
> + int err;
> +
> + dev_dbg(&pdev->dev, "vf%u: Start dirty page tracking\n", pds_vfio->vf_id);
> +
> + if (pds_vfio_dirty_is_enabled(pds_vfio))
> + return -EINVAL;
> +
> + pds_vfio_dirty_set_enabled(pds_vfio);
> +
> + /* find if dirty tracking is disabled, i.e. num_regions == 0 */
> + err = pds_vfio_dirty_status_cmd(pds_vfio, 0, &max_regions, &num_regions);
> + if (num_regions) {
> + dev_err(&pdev->dev, "Dirty tracking already enabled for %d regions\n",
> + num_regions);
> + err = -EEXIST;
> + goto err_out;
> + } else if (!max_regions) {
> + dev_err(&pdev->dev, "Device doesn't support dirty tracking, max_regions %d\n",
> + max_regions);
> + err = -EOPNOTSUPP;
> + goto err_out;
> + } else if (err) {
> + dev_err(&pdev->dev, "Failed to get dirty status, err %pe\n",
> + ERR_PTR(err));
> + goto err_out;
> + }
> +
> + /* Only support 1 region for now. If there are any large gaps in the
> + * VM's address regions, then this would be a waste of memory as we are
> + * generating 2 bitmaps (ack/seq) from the min address to the max
> + * address of the VM's address regions. In the future, if we support
> + * more than one region in the device/driver we can split the bitmaps
> + * on the largest address region gaps. We can do this split up to the
> + * max_regions times returned from the dirty_status command.
> + */
Large gaps in a VM are very possible, particularly after QEMU has
relocated RAM above 4GB to above the reserved hypertransport range on
AMD systems. Thanks,
Alex
> + max_regions = 1;
> + if (num_ranges > max_regions) {
> + vfio_combine_iova_ranges(ranges, nnodes, max_regions);
> + num_ranges = max_regions;
> + }
> +
> + node = interval_tree_iter_first(ranges, 0, ULONG_MAX);
> + if (!node) {
> + err = -EINVAL;
> + goto err_out;
> + }
> +
> + region_size = node->last - node->start + 1;
> + region_start = node->start;
> + region_page_size = *page_size;
> +
> + len = sizeof(*region_info);
> + region_info = kzalloc(len, GFP_KERNEL);
> + if (!region_info) {
> + err = -ENOMEM;
> + goto err_out;
> + }
> +
> + page_count = DIV_ROUND_UP(region_size, region_page_size);
> +
> + region_info->dma_base = cpu_to_le64(region_start);
> + region_info->page_count = cpu_to_le32(page_count);
> + region_info->page_size_log2 = ilog2(region_page_size);
> +
> + regions_dma = dma_map_single(pds_vfio->coredev, (void *)region_info, len,
> + DMA_BIDIRECTIONAL);
> + if (dma_mapping_error(pds_vfio->coredev, regions_dma)) {
> + err = -ENOMEM;
> + kfree(region_info);
> + goto err_out;
> + }
> +
> + err = pds_vfio_dirty_enable_cmd(pds_vfio, regions_dma, max_regions);
> + dma_unmap_single(pds_vfio->coredev, regions_dma, len, DMA_BIDIRECTIONAL);
> + /* page_count might be adjusted by the device,
> + * update it before freeing region_info DMA
> + */
> + page_count = le32_to_cpu(region_info->page_count);
> +
> + dev_dbg(&pdev->dev, "region_info: regions_dma 0x%llx dma_base 0x%llx page_count %u page_size_log2 %u\n",
> + regions_dma, region_start, page_count, (u8)ilog2(region_page_size));
> +
> + kfree(region_info);
> + if (err)
> + goto err_out;
> +
> + err = pds_vfio_dirty_alloc_bitmaps(dirty, page_count);
> + if (err) {
> + dev_err(&pdev->dev, "Failed to alloc dirty bitmaps: %pe\n",
> + ERR_PTR(err));
> + goto err_out;
> + }
> +
> + err = pds_vfio_dirty_alloc_sgl(pds_vfio, page_count);
> + if (err) {
> + dev_err(&pdev->dev, "Failed to alloc dirty sg lists: %pe\n",
> + ERR_PTR(err));
> + goto err_free_bitmaps;
> + }
> +
> + dirty->region_start = region_start;
> + dirty->region_size = region_size;
> + dirty->region_page_size = region_page_size;
> +
> + pds_vfio_print_guest_region_info(pds_vfio, max_regions);
> +
> + return 0;
> +
> +err_free_bitmaps:
> + pds_vfio_dirty_free_bitmaps(dirty);
> +err_out:
> + pds_vfio_dirty_set_disabled(pds_vfio);
> + return err;
> +}
