Add support for creating and destroying page tracker object.
This object is used to control/report the device dirty pages.
As part of creating the tracker need to consider the device capabilities
for max ranges and adapt/combine ranges accordingly.
Signed-off-by: Yishai Hadas <yishaih@xxxxxxxxxx>
---
drivers/vfio/pci/mlx5/cmd.c | 147 ++++++++++++++++++++++++++++++++++++
drivers/vfio/pci/mlx5/cmd.h | 1 +
2 files changed, 148 insertions(+)
diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c
index 0a362796d567..f1cad96af6ab 100644
--- a/drivers/vfio/pci/mlx5/cmd.c
+++ b/drivers/vfio/pci/mlx5/cmd.c
@@ -410,6 +410,148 @@ int mlx5vf_cmd_load_vhca_state(struct
mlx5vf_pci_core_device *mvdev,
return err;
}
+static void combine_ranges(struct rb_root_cached *root, u32
cur_nodes,
+ u32 req_nodes)
+{
+ struct interval_tree_node *prev, *curr, *comb_start, *comb_end;
+ unsigned long min_gap;
+ unsigned long curr_gap;
+
+ /* Special shortcut when a single range is required */
+ if (req_nodes == 1) {
+ unsigned long last;
+
+ curr = comb_start = interval_tree_iter_first(root, 0,
ULONG_MAX);
+ while (curr) {
+ last = curr->last;
+ prev = curr;
+ curr = interval_tree_iter_next(curr, 0, ULONG_MAX);
+ if (prev != comb_start)
+ interval_tree_remove(prev, root);
+ }
+ comb_start->last = last;
+ return;
+ }
+
+ /* Combine ranges which have the smallest gap */
+ while (cur_nodes > req_nodes) {
+ prev = NULL;
+ min_gap = ULONG_MAX;
+ curr = interval_tree_iter_first(root, 0, ULONG_MAX);
+ while (curr) {
+ if (prev) {
+ curr_gap = curr->start - prev->last;
+ if (curr_gap < min_gap) {
+ min_gap = curr_gap;
+ comb_start = prev;
+ comb_end = curr;
+ }
+ }
+ prev = curr;
+ curr = interval_tree_iter_next(curr, 0, ULONG_MAX);
+ }
+ comb_start->last = comb_end->last;
+ interval_tree_remove(comb_end, root);
+ cur_nodes--;
+ }
+}
+
+static int mlx5vf_create_tracker(struct mlx5_core_dev *mdev,
+ struct mlx5vf_pci_core_device *mvdev,
+ struct rb_root_cached *ranges, u32 nnodes)
+{
+ int max_num_range =
+ MLX5_CAP_ADV_VIRTUALIZATION(mdev, pg_track_max_num_range);
+ struct mlx5_vhca_page_tracker *tracker = &mvdev->tracker;
+ int record_size = MLX5_ST_SZ_BYTES(page_track_range);
+ u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {};
+ struct interval_tree_node *node = NULL;
+ u64 total_ranges_len = 0;
+ u32 num_ranges = nnodes;
+ u8 log_addr_space_size;
+ void *range_list_ptr;
+ void *obj_context;
+ void *cmd_hdr;
+ int inlen;
+ void *in;
+ int err;
+ int i;
+
+ if (num_ranges > max_num_range) {
+ combine_ranges(ranges, nnodes, max_num_range);
+ num_ranges = max_num_range;
+ }
+
+ inlen = MLX5_ST_SZ_BYTES(create_page_track_obj_in) +
+ record_size * num_ranges;
+ in = kzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ cmd_hdr = MLX5_ADDR_OF(create_page_track_obj_in, in,
+ general_obj_in_cmd_hdr);
+ MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, opcode,
+ MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+ MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_type,
+ MLX5_OBJ_TYPE_PAGE_TRACK);
+ obj_context = MLX5_ADDR_OF(create_page_track_obj_in, in,
obj_context);
+ MLX5_SET(page_track, obj_context, vhca_id, mvdev->vhca_id);
+ MLX5_SET(page_track, obj_context, track_type, 1);
+ MLX5_SET(page_track, obj_context, log_page_size,
+ ilog2(tracker->host_qp->tracked_page_size));
+ MLX5_SET(page_track, obj_context, log_msg_size,
+ ilog2(tracker->host_qp->max_msg_size));
+ MLX5_SET(page_track, obj_context, reporting_qpn,
tracker->fw_qp->qpn);
+ MLX5_SET(page_track, obj_context, num_ranges, num_ranges);
+
+ range_list_ptr = MLX5_ADDR_OF(page_track, obj_context,
track_range);
+ node = interval_tree_iter_first(ranges, 0, ULONG_MAX);
+ for (i = 0; i < num_ranges; i++) {
+ void *addr_range_i_base = range_list_ptr + record_size * i;
+ unsigned long length = node->last - node->start;
+
+ MLX5_SET64(page_track_range, addr_range_i_base, start_address,
+ node->start);
+ MLX5_SET64(page_track_range, addr_range_i_base, length,
length);
+ total_ranges_len += length;
+ node = interval_tree_iter_next(node, 0, ULONG_MAX);
+ }
+
+ WARN_ON(node);
+ log_addr_space_size = ilog2(total_ranges_len);
+ if (log_addr_space_size <
+ (MLX5_CAP_ADV_VIRTUALIZATION(mdev,
pg_track_log_min_addr_space)) ||
+ log_addr_space_size >
+ (MLX5_CAP_ADV_VIRTUALIZATION(mdev,
pg_track_log_max_addr_space))) {
+ err = -EOPNOTSUPP;
+ goto out;
+ }
