RDMA/mlx5: Rely on RoCE fw cap instead of devlink when setting profile

When the RDMA auxiliary driver probes, it sets its profile based on
devlink driverinit value. The latter might not be in sync with FW yet
(In case devlink reload is not performed), thus causing a mismatch
between RDMA driver and FW. This results in the following FW syndrome
when the RDMA driver tries to adjust RoCE state, which fails the probe:

"0xC1F678 | modify_nic_vport_context: roce_en set on a vport that
doesn't support roce"

To prevent this, select the PF profile based on FW RoCE capability
instead of relying on devlink driverinit value.
To provide backward compatibility of the RoCE disable feature, on older
FW's where roce_rw is not set (FW RoCE capability is read-only), keep
the current behavior e.g., rely on devlink driverinit value.

Fixes: fbfa97b4d79f ("net/mlx5: Disable roce at HCA level")
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Link: https://lore.kernel.org/r/cb34ce9a1df4a24c135cb804db87f7d2418bd6cc.1661763459.git.leonro@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index fc94a1b25485d7ba65cada9af61496e1fe89d432..883d7c60143e8a8cd8289976e4aec2f69212dba6 100644 (file)
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -4336,7 +4336,7 @@ static int mlx5r_probe(struct auxiliary_device *adev,
        dev->mdev = mdev;
        dev->num_ports = num_ports;
 
-       if (ll == IB_LINK_LAYER_ETHERNET && !mlx5_is_roce_init_enabled(mdev))
+       if (ll == IB_LINK_LAYER_ETHERNET && !mlx5_get_roce_state(mdev))
                profile = &raw_eth_profile;
        else
                profile = &pf_profile;

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index bec8d6d0b5f67690513237f03bfc525045dc2319..4870a88cecb7ac38e34282e120117a1423fd4dd0 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -494,6 +494,24 @@ static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev)
        return err;
 }
 
+bool mlx5_is_roce_on(struct mlx5_core_dev *dev)
+{
+       struct devlink *devlink = priv_to_devlink(dev);
+       union devlink_param_value val;
+       int err;
+
+       err = devlink_param_driverinit_value_get(devlink,
+                                                DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
+                                                &val);
+
+       if (!err)
+               return val.vbool;
+
+       mlx5_core_dbg(dev, "Failed to get param. err = %d\n", err);
+       return MLX5_CAP_GEN(dev, roce);
+}
+EXPORT_SYMBOL(mlx5_is_roce_on);
+
 static int handle_hca_cap_2(struct mlx5_core_dev *dev, void *set_ctx)
 {
        void *set_hca_cap;
@@ -597,7 +615,8 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
                         MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix));
 
        if (MLX5_CAP_GEN(dev, roce_rw_supported))
-               MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev));
+               MLX5_SET(cmd_hca_cap, set_hca_cap, roce,
+                        mlx5_is_roce_on(dev));
 
        max_uc_list = max_uc_list_get_devlink_param(dev);
        if (max_uc_list > 0)
@@ -623,7 +642,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
  */
 static bool is_roce_fw_disabled(struct mlx5_core_dev *dev)
 {
-       return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_init_enabled(dev)) ||
+       return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_on(dev)) ||
                (!MLX5_CAP_GEN(dev, roce_rw_supported) && !MLX5_CAP_GEN(dev, roce));
 }
 

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 96b16fbe1aa45932b52158da10007956fe081fcc..d6338fb449c83f74070fb2fd67054f98586097c8 100644 (file)
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1279,16 +1279,17 @@ enum {
        MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32,
 };
 
-static inline bool mlx5_is_roce_init_enabled(struct mlx5_core_dev *dev)
+bool mlx5_is_roce_on(struct mlx5_core_dev *dev);
+
+static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev)
 {
-       struct devlink *devlink = priv_to_devlink(dev);
-       union devlink_param_value val;
-       int err;
-
-       err = devlink_param_driverinit_value_get(devlink,
-                                                DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
-                                                &val);
-       return err ? MLX5_CAP_GEN(dev, roce) : val.vbool;
+       if (MLX5_CAP_GEN(dev, roce_rw_supported))
+               return MLX5_CAP_GEN(dev, roce);
+
+       /* If RoCE cap is read-only in FW, get RoCE state from devlink
+        * in order to support RoCE enable/disable feature
+        */
+       return mlx5_is_roce_on(dev);
 }
 
 #endif /* MLX5_DRIVER_H */