+static struct ibv_device *
+mlx5_vdpa_get_ib_device_match(struct rte_pci_addr *addr)
+{
+ int n;
+ struct ibv_device **ibv_list = mlx5_glue->get_device_list(&n);
+ struct ibv_device *ibv_match = NULL;
+
+ if (!ibv_list) {
+ rte_errno = ENOSYS;
+ return NULL;
+ }
+ while (n-- > 0) {
+ struct rte_pci_addr pci_addr;
+
+ DRV_LOG(DEBUG, "Checking device \"%s\"..", ibv_list[n]->name);
+ if (mlx5_dev_to_pci_addr(ibv_list[n]->ibdev_path, &pci_addr))
+ continue;
+ if (memcmp(addr, &pci_addr, sizeof(pci_addr)))
+ continue;
+ ibv_match = ibv_list[n];
+ break;
+ }
+ if (!ibv_match)
+ rte_errno = ENOENT;
+ mlx5_glue->free_device_list(ibv_list);
+ return ibv_match;
+}
+
+/* Try to disable ROCE by Netlink\Devlink. */
+static int
+mlx5_vdpa_nl_roce_disable(const char *addr)
+{
+ int nlsk_fd = mlx5_nl_init(NETLINK_GENERIC);
+ int devlink_id;
+ int enable;
+ int ret;
+
+ if (nlsk_fd < 0)
+ return nlsk_fd;
+ devlink_id = mlx5_nl_devlink_family_id_get(nlsk_fd);
+ if (devlink_id < 0) {
+ ret = devlink_id;
+ DRV_LOG(DEBUG, "Failed to get devlink id for ROCE operations by"
+ " Netlink.");
+ goto close;
+ }
+ ret = mlx5_nl_enable_roce_get(nlsk_fd, devlink_id, addr, &enable);
+ if (ret) {
+ DRV_LOG(DEBUG, "Failed to get ROCE enable by Netlink: %d.",
+ ret);
+ goto close;
+ } else if (!enable) {
+ DRV_LOG(INFO, "ROCE has already disabled(Netlink).");
+ goto close;
+ }
+ ret = mlx5_nl_enable_roce_set(nlsk_fd, devlink_id, addr, 0);
+ if (ret)
+ DRV_LOG(DEBUG, "Failed to disable ROCE by Netlink: %d.", ret);
+ else
+ DRV_LOG(INFO, "ROCE is disabled by Netlink successfully.");
+close:
+ close(nlsk_fd);
+ return ret;
+}
+
+/* Try to disable ROCE by sysfs. */
+static int
+mlx5_vdpa_sys_roce_disable(const char *addr)
+{
+ FILE *file_o;
+ int enable;
+ int ret;
+
+ MKSTR(file_p, "/sys/bus/pci/devices/%s/roce_enable", addr);
+ file_o = fopen(file_p, "rb");
+ if (!file_o) {
+ rte_errno = ENOTSUP;
+ return -ENOTSUP;
+ }
+ ret = fscanf(file_o, "%d", &enable);
+ if (ret != 1) {
+ rte_errno = EINVAL;
+ ret = EINVAL;
+ goto close;
+ } else if (!enable) {
+ ret = 0;
+ DRV_LOG(INFO, "ROCE has already disabled(sysfs).");
+ goto close;
+ }
+ fclose(file_o);
+ file_o = fopen(file_p, "wb");
+ if (!file_o) {
+ rte_errno = ENOTSUP;
+ return -ENOTSUP;
+ }
+ fprintf(file_o, "0\n");
+ ret = 0;
+close:
+ if (ret)
+ DRV_LOG(DEBUG, "Failed to disable ROCE by sysfs: %d.", ret);
+ else
+ DRV_LOG(INFO, "ROCE is disabled by sysfs successfully.");
+ fclose(file_o);
+ return ret;
+}
+
+#define MLX5_VDPA_MAX_RETRIES 20
+#define MLX5_VDPA_USEC 1000
+static int
+mlx5_vdpa_roce_disable(struct rte_pci_addr *addr, struct ibv_device **ibv)
+{
+ char addr_name[64] = {0};
+
+ rte_pci_device_name(addr, addr_name, sizeof(addr_name));
+ /* Firstly try to disable ROCE by Netlink and fallback to sysfs. */
+ if (mlx5_vdpa_nl_roce_disable(addr_name) == 0 ||
+ mlx5_vdpa_sys_roce_disable(addr_name) == 0) {
+ /*
+ * Succeed to disable ROCE, wait for the IB device to appear
+ * again after reload.
+ */
+ int r;
+ struct ibv_device *ibv_new;
+
+ for (r = MLX5_VDPA_MAX_RETRIES; r; r--) {
+ ibv_new = mlx5_vdpa_get_ib_device_match(addr);
+ if (ibv_new) {
+ *ibv = ibv_new;
+ return 0;
+ }
+ usleep(MLX5_VDPA_USEC);
+ }
+ DRV_LOG(ERR, "Cannot much device %s after ROCE disable, "
+ "retries exceed %d", addr_name, MLX5_VDPA_MAX_RETRIES);
+ rte_errno = EAGAIN;
+ }
+ return -rte_errno;
+}
+