#include <linux/pci.h>
#include <linux/dma-mapping.h>
#include <linux/slab.h>
-#include <linux/io-mapping.h>
#if defined(CONFIG_X86)
#include <asm/pat.h>
#endif
#include <linux/in.h>
#include <linux/etherdevice.h>
#include <linux/mlx5/fs.h>
-#include "user.h"
#include "mlx5_ib.h"
#define DRIVER_NAME "mlx5_ib"
break;
case NETDEV_UP:
- case NETDEV_DOWN:
- if (ndev == ibdev->roce.netdev && ibdev->ib_active) {
+ case NETDEV_DOWN: {
+ struct net_device *lag_ndev = mlx5_lag_get_roce_netdev(ibdev->mdev);
+ struct net_device *upper = NULL;
+
+ if (lag_ndev) {
+ upper = netdev_master_upper_dev_get(lag_ndev);
+ dev_put(lag_ndev);
+ }
+
+ if ((upper == ndev || (!upper && ndev == ibdev->roce.netdev))
+ && ibdev->ib_active) {
struct ib_event ibev = {0};
ibev.device = &ibdev->ib_dev;
ib_dispatch_event(&ibev);
}
break;
+ }
default:
break;
struct mlx5_ib_dev *ibdev = to_mdev(device);
struct net_device *ndev;
+ ndev = mlx5_lag_get_roce_netdev(ibdev->mdev);
+ if (ndev)
+ return ndev;
+
/* Ensure ndev does not disappear before we invoke dev_hold()
*/
read_lock(&ibdev->roce.netdev_lock);
struct ib_port_attr *props)
{
struct mlx5_ib_dev *dev = to_mdev(device);
- struct net_device *ndev;
+ struct net_device *ndev, *upper;
enum ib_mtu ndev_ib_mtu;
u16 qkey_viol_cntr;
if (!ndev)
return 0;
+ if (mlx5_lag_is_active(dev->mdev)) {
+ rcu_read_lock();
+ upper = netdev_master_upper_dev_get_rcu(ndev);
+ if (upper) {
+ dev_put(ndev);
+ ndev = upper;
+ dev_hold(ndev);
+ }
+ rcu_read_unlock();
+ }
+
if (netif_running(ndev) && netif_carrier_ok(ndev)) {
props->state = IB_PORT_ACTIVE;
props->phys_state = 5;
static int mlx5_use_mad_ifc(struct mlx5_ib_dev *dev)
{
- return !MLX5_CAP_GEN(dev->mdev, ib_virt);
+ if (MLX5_CAP_GEN(dev->mdev, port_type) == MLX5_CAP_PORT_TYPE_IB)
+ return !MLX5_CAP_GEN(dev->mdev, ib_virt);
+ return 0;
}
enum {
}
struct mlx5_reg_node_desc {
- u8 desc[64];
+ u8 desc[IB_DEVICE_NODE_DESC_MAX];
};
static int mlx5_query_node_desc(struct mlx5_ib_dev *dev, char *node_desc)
* If possible, pass node desc to FW, so it can generate
* a 144 trap. If cmd fails, just ignore.
*/
- memcpy(&in, props->node_desc, 64);
+ memcpy(&in, props->node_desc, IB_DEVICE_NODE_DESC_MAX);
err = mlx5_core_access_reg(dev->mdev, &in, sizeof(in), &out,
sizeof(out), MLX5_REG_NODE_DESC, 0, 1);
if (err)
return err;
- memcpy(ibdev->node_desc, props->node_desc, 64);
+ memcpy(ibdev->node_desc, props->node_desc, IB_DEVICE_NODE_DESC_MAX);
return err;
}
resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp);
if (mlx5_core_is_pf(dev->mdev) && MLX5_CAP_GEN(dev->mdev, bf))
resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size);
- resp.cache_line_size = L1_CACHE_BYTES;
+ resp.cache_line_size = cache_line_size();
resp.max_sq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq);
resp.max_rq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq);
resp.max_send_wqebb = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz);
dmac_47_16),
ib_spec->eth.val.dst_mac);
+ ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
+ smac_47_16),
+ ib_spec->eth.mask.src_mac);
+ ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
+ smac_47_16),
+ ib_spec->eth.val.src_mac);
+
if (ib_spec->eth.mask.vlan_tag) {
MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
vlan_tag, 1);
int domain)
{
struct mlx5_ib_dev *dev = to_mdev(qp->device);
+ struct mlx5_ib_qp *mqp = to_mqp(qp);
struct mlx5_ib_flow_handler *handler = NULL;
struct mlx5_flow_destination *dst = NULL;
struct mlx5_ib_flow_prio *ft_prio_tx = NULL;
}
dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR;
- dst->tir_num = to_mqp(qp)->raw_packet_qp.rq.tirn;
+ if (mqp->flags & MLX5_IB_QP_RSS)
+ dst->tir_num = mqp->rss_qp.tirn;
+ else
+ dst->tir_num = mqp->raw_packet_qp.rq.tirn;
if (flow_attr->type == IB_FLOW_ATTR_NORMAL) {
if (flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) {
fw_rev_min(dev->mdev), fw_rev_sub(dev->mdev));
}
+static int mlx5_roce_lag_init(struct mlx5_ib_dev *dev)
+{
+ struct mlx5_core_dev *mdev = dev->mdev;
+ struct mlx5_flow_namespace *ns = mlx5_get_flow_namespace(mdev,
+ MLX5_FLOW_NAMESPACE_LAG);
+ struct mlx5_flow_table *ft;
+ int err;
+
+ if (!ns || !mlx5_lag_is_active(mdev))
+ return 0;
+
+ err = mlx5_cmd_create_vport_lag(mdev);
+ if (err)
+ return err;
+
+ ft = mlx5_create_lag_demux_flow_table(ns, 0, 0);
+ if (IS_ERR(ft)) {
+ err = PTR_ERR(ft);
+ goto err_destroy_vport_lag;
+ }
+
+ dev->flow_db.lag_demux_ft = ft;
+ return 0;
+
+err_destroy_vport_lag:
+ mlx5_cmd_destroy_vport_lag(mdev);
+ return err;
+}
+
+static void mlx5_roce_lag_cleanup(struct mlx5_ib_dev *dev)
+{
+ struct mlx5_core_dev *mdev = dev->mdev;
+
+ if (dev->flow_db.lag_demux_ft) {
+ mlx5_destroy_flow_table(dev->flow_db.lag_demux_ft);
+ dev->flow_db.lag_demux_ft = NULL;
+
+ mlx5_cmd_destroy_vport_lag(mdev);
+ }
+}
+
static void mlx5_remove_roce_notifier(struct mlx5_ib_dev *dev)
{
if (dev->roce.nb.notifier_call) {
if (err)
goto err_unregister_netdevice_notifier;
+ err = mlx5_roce_lag_init(dev);
+ if (err)
+ goto err_disable_roce;
+
return 0;
+err_disable_roce:
+ mlx5_nic_vport_disable_roce(dev->mdev);
+
err_unregister_netdevice_notifier:
mlx5_remove_roce_notifier(dev);
return err;
static void mlx5_disable_roce(struct mlx5_ib_dev *dev)
{
+ mlx5_roce_lag_cleanup(dev);
mlx5_nic_vport_disable_roce(dev->mdev);
}
struct mlx5_ib_dev *dev;
enum rdma_link_layer ll;
int port_type_cap;
+ const char *name;
int err;
int i;
MLX5_INIT_DOORBELL_LOCK(&dev->uar_lock);
- strlcpy(dev->ib_dev.name, "mlx5_%d", IB_DEVICE_NAME_MAX);
+ if (!mlx5_lag_is_active(mdev))
+ name = "mlx5_%d";
+ else
+ name = "mlx5_bond_%d";
+
+ strlcpy(dev->ib_dev.name, name, IB_DEVICE_NAME_MAX);
dev->ib_dev.owner = THIS_MODULE;
dev->ib_dev.node_type = RDMA_NODE_IB_CA;
dev->ib_dev.local_dma_lkey = 0 /* not supported for now */;
projects / cascardo / linux.git / blobdiff