ice: Add tx_scheduling_layers devlink param

It was observed that Tx performance was inconsistent across all queues
and/or VSIs and that it was directly connected to existing 9-layer
topology of the Tx scheduler.

Introduce new private devlink param - tx_scheduling_layers. This parameter
gives user flexibility to choose the 5-layer transmit scheduler topology
which helps to smooth out the transmit performance.

Allowed parameter values are 5 and 9.

Example usage:

Show:
devlink dev param show pci/0000:4b:00.0 name tx_scheduling_layers
pci/0000:4b:00.0:
name tx_scheduling_layers type driver-specific
values:
cmode permanent value 9

Set:
devlink dev param set pci/0000:4b:00.0 name tx_scheduling_layers value 5
cmode permanent

devlink dev param set pci/0000:4b:00.0 name tx_scheduling_layers value 9
cmode permanent

Signed-off-by: Lukasz Czapnik <[e-mail]>
Reviewed-by: Przemek Kitszel <[e-mail]>
Co-developed-by: Mateusz Polchlopek <[e-mail]>
Signed-off-by: Mateusz Polchlopek <[e-mail]>
Tested-by: Pucha Himasekhar Reddy <[e-mail]>
Signed-off-by: Tony Nguyen <[e-mail]>

drivers/net/ethernet/intel/ice/devlink/devlink.c

···
 }
 
 /**
+ * ice_get_tx_topo_user_sel - Read user's choice from flash
+ * @pf: pointer to pf structure
+ * @layers: value read from flash will be saved here
+ *
+ * Reads user's preference for Tx Scheduler Topology Tree from PFA TLV.
+ *
+ * Return: zero when read was successful, negative values otherwise.
+ */
+static int ice_get_tx_topo_user_sel(struct ice_pf *pf, uint8_t *layers)
+{
+	struct ice_aqc_nvm_tx_topo_user_sel usr_sel = {};
+	struct ice_hw *hw = &pf->hw;
+	int err;
+
+	err = ice_acquire_nvm(hw, ICE_RES_READ);
+	if (err)
+		return err;
+
+	err = ice_aq_read_nvm(hw, ICE_AQC_NVM_TX_TOPO_MOD_ID, 0,
+			      sizeof(usr_sel), &usr_sel, true, true, NULL);
+	if (err)
+		goto exit_release_res;
+
+	if (usr_sel.data & ICE_AQC_NVM_TX_TOPO_USER_SEL)
+		*layers = ICE_SCHED_5_LAYERS;
+	else
+		*layers = ICE_SCHED_9_LAYERS;
+
+exit_release_res:
+	ice_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ice_update_tx_topo_user_sel - Save user's preference in flash
+ * @pf: pointer to pf structure
+ * @layers: value to be saved in flash
+ *
+ * Variable "layers" defines user's preference about number of layers in Tx
+ * Scheduler Topology Tree. This choice should be stored in PFA TLV field
+ * and be picked up by driver, next time during init.
+ *
+ * Return: zero when save was successful, negative values otherwise.
+ */
+static int ice_update_tx_topo_user_sel(struct ice_pf *pf, int layers)
+{
+	struct ice_aqc_nvm_tx_topo_user_sel usr_sel = {};
+	struct ice_hw *hw = &pf->hw;
+	int err;
+
+	err = ice_acquire_nvm(hw, ICE_RES_WRITE);
+	if (err)
+		return err;
+
+	err = ice_aq_read_nvm(hw, ICE_AQC_NVM_TX_TOPO_MOD_ID, 0,
+			      sizeof(usr_sel), &usr_sel, true, true, NULL);
+	if (err)
+		goto exit_release_res;
+
+	if (layers == ICE_SCHED_5_LAYERS)
+		usr_sel.data |= ICE_AQC_NVM_TX_TOPO_USER_SEL;
+	else
+		usr_sel.data &= ~ICE_AQC_NVM_TX_TOPO_USER_SEL;
+
+	err = ice_write_one_nvm_block(pf, ICE_AQC_NVM_TX_TOPO_MOD_ID, 2,
+				      sizeof(usr_sel.data), &usr_sel.data,
+				      true, NULL, NULL);
+exit_release_res:
+	ice_release_nvm(hw);
+
+	return err;
+}
+
+/**
+ * ice_devlink_tx_sched_layers_get - Get tx_scheduling_layers parameter
+ * @devlink: pointer to the devlink instance
+ * @id: the parameter ID to set
+ * @ctx: context to store the parameter value
+ *
+ * Return: zero on success and negative value on failure.
+ */
+static int ice_devlink_tx_sched_layers_get(struct devlink *devlink, u32 id,
+					   struct devlink_param_gset_ctx *ctx)
+{
+	struct ice_pf *pf = devlink_priv(devlink);
+	int err;
+
+	err = ice_get_tx_topo_user_sel(pf, &ctx->val.vu8);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+/**
+ * ice_devlink_tx_sched_layers_set - Set tx_scheduling_layers parameter
+ * @devlink: pointer to the devlink instance
+ * @id: the parameter ID to set
+ * @ctx: context to get the parameter value
+ * @extack: netlink extended ACK structure
+ *
+ * Return: zero on success and negative value on failure.
+ */
+static int ice_devlink_tx_sched_layers_set(struct devlink *devlink, u32 id,
+					   struct devlink_param_gset_ctx *ctx,
+					   struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_priv(devlink);
+	int err;
+
+	err = ice_update_tx_topo_user_sel(pf, ctx->val.vu8);
+	if (err)
+		return err;
+
+	NL_SET_ERR_MSG_MOD(extack,
+			   "Tx scheduling layers have been changed on this device. You must do the PCI slot powercycle for the change to take effect.");
+
+	return 0;
+}
+
+/**
+ * ice_devlink_tx_sched_layers_validate - Validate passed tx_scheduling_layers
+ *                                        parameter value
+ * @devlink: unused pointer to devlink instance
+ * @id: the parameter ID to validate
+ * @val: value to validate
+ * @extack: netlink extended ACK structure
+ *
+ * Supported values are:
+ * - 5 - five layers Tx Scheduler Topology Tree
+ * - 9 - nine layers Tx Scheduler Topology Tree
+ *
+ * Return: zero when passed parameter value is supported. Negative value on
+ * error.
+ */
+static int ice_devlink_tx_sched_layers_validate(struct devlink *devlink, u32 id,
+						union devlink_param_value val,
+						struct netlink_ext_ack *extack)
+{
+	if (val.vu8 != ICE_SCHED_5_LAYERS && val.vu8 != ICE_SCHED_9_LAYERS) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Wrong number of tx scheduler layers provided.");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
  * ice_tear_down_devlink_rate_tree - removes devlink-rate exported tree
  * @pf: pf struct
  *
···
 	return 0;
 }
 
+enum ice_param_id {
+	ICE_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
+};
+
 static const struct devlink_param ice_devlink_params[] = {
 	DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_RUNTIME),
 			      ice_devlink_enable_roce_get,
···
 			      ice_devlink_enable_iw_get,
 			      ice_devlink_enable_iw_set,
 			      ice_devlink_enable_iw_validate),
-
+	DEVLINK_PARAM_DRIVER(ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
+			     "tx_scheduling_layers",
+			     DEVLINK_PARAM_TYPE_U8,
+			     BIT(DEVLINK_PARAM_CMODE_PERMANENT),
+			     ice_devlink_tx_sched_layers_get,
+			     ice_devlink_tx_sched_layers_set,
+			     ice_devlink_tx_sched_layers_validate),
 };
 
 static void ice_devlink_free(void *devlink_ptr)
···
 int ice_devlink_register_params(struct ice_pf *pf)
 {
 	struct devlink *devlink = priv_to_devlink(pf);
+	struct ice_hw *hw = &pf->hw;
+	size_t params_size;
+
+	params_size =  ARRAY_SIZE(ice_devlink_params);
+
+	if (!hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
+		params_size--;
 
 	return devl_params_register(devlink, ice_devlink_params,
-				    ARRAY_SIZE(ice_devlink_params));
+				    params_size);
 }
 
 void ice_devlink_unregister_params(struct ice_pf *pf)

drivers/net/ethernet/intel/ice/ice_adminq_cmd.h

···
 
 #define ICE_AQC_NVM_START_POINT			0
 
+#define ICE_AQC_NVM_TX_TOPO_MOD_ID		0x14B
+
+struct ice_aqc_nvm_tx_topo_user_sel {
+	__le16 length;
+	u8 data;
+#define ICE_AQC_NVM_TX_TOPO_USER_SEL	BIT(4)
+	u8 reserved;
+};
+
 /* NVM Checksum Command (direct, 0x0706) */
 struct ice_aqc_nvm_checksum {
 	u8 flags;

drivers/net/ethernet/intel/ice/ice_fw_update.c

···
  *
  * Returns: zero on success, or a negative error code on failure.
  */
-static int
-ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
-			u16 block_size, u8 *block, bool last_cmd,
-			u8 *reset_level, struct netlink_ext_ack *extack)
+int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
+			    u16 block_size, u8 *block, bool last_cmd,
+			    u8 *reset_level, struct netlink_ext_ack *extack)
 {
 	u16 completion_module, completion_retval;
 	struct device *dev = ice_pf_to_dev(pf);

drivers/net/ethernet/intel/ice/ice_fw_update.h

···
 			     struct netlink_ext_ack *extack);
 int ice_get_pending_updates(struct ice_pf *pf, u8 *pending,
 			    struct netlink_ext_ack *extack);
+int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
+			    u16 block_size, u8 *block, bool last_cmd,
+			    u8 *reset_level, struct netlink_ext_ack *extack);
 
 #endif

drivers/net/ethernet/intel/ice/ice_nvm.c

···
  *
  * Read the NVM using the admin queue commands (0x0701)
  */
-static int
-ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, u16 length,
-		void *data, bool last_command, bool read_shadow_ram,
-		struct ice_sq_cd *cd)
+int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
+		    u16 length, void *data, bool last_command,
+		    bool read_shadow_ram, struct ice_sq_cd *cd)
 {
 	struct ice_aq_desc desc;
 	struct ice_aqc_nvm *cmd;

drivers/net/ethernet/intel/ice/ice_nvm.h

···
 
 int ice_acquire_nvm(struct ice_hw *hw, enum ice_aq_res_access_type access);
 void ice_release_nvm(struct ice_hw *hw);
+int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
+		    u16 length, void *data, bool last_command,
+		    bool read_shadow_ram, struct ice_sq_cd *cd);
 int
 ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data,
 		  bool read_shadow_ram);