Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue

Tony Nguyen says:

====================
ice: Support 5 layer Tx scheduler topology

Mateusz Polchlopek says:

For performance reasons there is a need to have support for selectable
Tx scheduler topology. Currently firmware supports only the default
9-layer and 5-layer topology. This patch series enables switch from
default to 5-layer topology, if user decides to opt-in.

* '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
  ice: Document tx_scheduling_layers parameter
  ice: Add tx_scheduling_layers devlink param
  ice: Enable switching default Tx scheduler topology
  ice: Adjust the VSI/Aggregator layers
  ice: Support 5 layer topology
  devlink: extend devlink_param *set pointer
====================

Link: https://lore.kernel.org/r/20240422203913.225151-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

35 files changed, 663 insertions, 84 deletions

diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst
index 7f30ebd5debb75..830c04354222f8 100644
--- a/Documentation/networking/devlink/ice.rst
+++ b/Documentation/networking/devlink/ice.rst
@@ -21,6 +21,53 @@ Parameters
    * - ``enable_iwarp``
      - runtime
      - mutually exclusive with ``enable_roce``
+   * - ``tx_scheduling_layers``
+     - permanent
+     - The ice hardware uses hierarchical scheduling for Tx with a fixed
+       number of layers in the scheduling tree. Each of them are decision
+       points. Root node represents a port, while all the leaves represent
+       the queues. This way of configuring the Tx scheduler allows features
+       like DCB or devlink-rate (documented below) to configure how much
+       bandwidth is given to any given queue or group of queues, enabling
+       fine-grained control because scheduling parameters can be configured
+       at any given layer of the tree.
+
+       The default 9-layer tree topology was deemed best for most workloads,
+       as it gives an optimal ratio of performance to configurability. However,
+       for some specific cases, this 9-layer topology might not be desired.
+       One example would be sending traffic to queues that are not a multiple
+       of 8. Because the maximum radix is limited to 8 in 9-layer topology,
+       the 9th queue has a different parent than the rest, and it's given
+       more bandwidth credits. This causes a problem when the system is
+       sending traffic to 9 queues:
+
+       | tx_queue_0_packets: 24163396
+       | tx_queue_1_packets: 24164623
+       | tx_queue_2_packets: 24163188
+       | tx_queue_3_packets: 24163701
+       | tx_queue_4_packets: 24163683
+       | tx_queue_5_packets: 24164668
+       | tx_queue_6_packets: 23327200
+       | tx_queue_7_packets: 24163853
+       | tx_queue_8_packets: 91101417 < Too much traffic is sent from 9th
+
+       To address this need, you can switch to a 5-layer topology, which
+       changes the maximum topology radix to 512. With this enhancement,
+       the performance characteristic is equal as all queues can be assigned
+       to the same parent in the tree. The obvious drawback of this solution
+       is a lower configuration depth of the tree.
+
+       Use the ``tx_scheduling_layer`` parameter with the devlink command
+       to change the transmit scheduler topology. To use 5-layer topology,
+       use a value of 5. For example:
+       $ devlink dev param set pci/0000:16:00.0 name tx_scheduling_layers
+       value 5 cmode permanent
+       Use a value of 9 to set it back to the default value.
+
+       You must do PCI slot powercycle for the selected topology to take effect.
+
+       To verify that value has been set:
+       $ devlink dev param show pci/0000:16:00.0 name tx_scheduling_layers
 
 Info versions
 =============
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c b/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c
index d2b8d26db968a6..215a1a8ba7e9f5 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c
@@ -4,7 +4,8 @@
 #include "otx2_cpt_devlink.h"
 
 static int otx2_cpt_dl_egrp_create(struct devlink *dl, u32 id,
-				   struct devlink_param_gset_ctx *ctx)
+				   struct devlink_param_gset_ctx *ctx,
+				   struct netlink_ext_ack *extack)
 {
 	struct otx2_cpt_devlink *cpt_dl = devlink_priv(dl);
 	struct otx2_cptpf_dev *cptpf = cpt_dl->cptpf;
@@ -13,7 +14,8 @@ static int otx2_cpt_dl_egrp_create(struct devlink *dl, u32 id,
 }
 
 static int otx2_cpt_dl_egrp_delete(struct devlink *dl, u32 id,
-				   struct devlink_param_gset_ctx *ctx)
+				   struct devlink_param_gset_ctx *ctx,
+				   struct netlink_ext_ack *extack)
 {
 	struct otx2_cpt_devlink *cpt_dl = devlink_priv(dl);
 	struct otx2_cptpf_dev *cptpf = cpt_dl->cptpf;
@@ -45,7 +47,8 @@ static int otx2_cpt_dl_t106_mode_get(struct devlink *dl, u32 id,
 }
 
 static int otx2_cpt_dl_t106_mode_set(struct devlink *dl, u32 id,
-				     struct devlink_param_gset_ctx *ctx)
+				     struct devlink_param_gset_ctx *ctx,
+				     struct netlink_ext_ack *extack)
 {
 	struct otx2_cpt_devlink *cpt_dl = devlink_priv(dl);
 	struct otx2_cptpf_dev *cptpf = cpt_dl->cptpf;
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index a3e17a0c187a6a..14522d6d5f86bb 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -256,7 +256,8 @@ int pdsc_dl_flash_update(struct devlink *dl,
 int pdsc_dl_enable_get(struct devlink *dl, u32 id,
 		       struct devlink_param_gset_ctx *ctx);
 int pdsc_dl_enable_set(struct devlink *dl, u32 id,
-		       struct devlink_param_gset_ctx *ctx);
+		       struct devlink_param_gset_ctx *ctx,
+		       struct netlink_ext_ack *extack);
 int pdsc_dl_enable_validate(struct devlink *dl, u32 id,
 			    union devlink_param_value val,
 			    struct netlink_ext_ack *extack);
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index 54864f27c87a9e..2681889162a25e 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -37,7 +37,8 @@ int pdsc_dl_enable_get(struct devlink *dl, u32 id,
 }
 
 int pdsc_dl_enable_set(struct devlink *dl, u32 id,
-		       struct devlink_param_gset_ctx *ctx)
+		       struct devlink_param_gset_ctx *ctx,
+		       struct netlink_ext_ack *extack)
 {
 	struct pdsc *pdsc = devlink_priv(dl);
 	struct pdsc_viftype *vt_entry;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index ae4529c043f0b2..d9ea6fa23923bb 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -1096,7 +1096,8 @@ static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id,
 }
 
 static int bnxt_dl_nvm_param_set(struct devlink *dl, u32 id,
-				 struct devlink_param_gset_ctx *ctx)
+				 struct devlink_param_gset_ctx *ctx,
+				 struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
 	struct hwrm_nvm_set_variable_input *req;
@@ -1145,7 +1146,8 @@ static int bnxt_remote_dev_reset_get(struct devlink *dl, u32 id,
 }
 
 static int bnxt_remote_dev_reset_set(struct devlink *dl, u32 id,
-				     struct devlink_param_gset_ctx *ctx)
+				     struct devlink_param_gset_ctx *ctx,
+				     struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
 	int rc;
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index be9244bb8bbcd6..d191c5709899d2 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -524,6 +524,156 @@ ice_devlink_reload_empr_finish(struct ice_pf *pf,
 }
 
 /**
+ * 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
  *
@@ -1144,9 +1294,9 @@ ice_devlink_enable_roce_get(struct devlink *devlink, u32 id,
 	return 0;
 }
 
-static int
-ice_devlink_enable_roce_set(struct devlink *devlink, u32 id,
-			    struct devlink_param_gset_ctx *ctx)
+static int ice_devlink_enable_roce_set(struct devlink *devlink, u32 id,
+				       struct devlink_param_gset_ctx *ctx,
+				       struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
 	bool roce_ena = ctx->val.vbool;
@@ -1195,9 +1345,9 @@ ice_devlink_enable_iw_get(struct devlink *devlink, u32 id,
 	return 0;
 }
 
-static int
-ice_devlink_enable_iw_set(struct devlink *devlink, u32 id,
-			  struct devlink_param_gset_ctx *ctx)
+static int ice_devlink_enable_iw_set(struct devlink *devlink, u32 id,
+				     struct devlink_param_gset_ctx *ctx,
+				     struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
 	bool iw_ena = ctx->val.vbool;
@@ -1235,6 +1385,11 @@ ice_devlink_enable_iw_validate(struct devlink *devlink, u32 id,
 	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,
@@ -1244,7 +1399,13 @@ static const struct devlink_param ice_devlink_params[] = {
 			      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)
@@ -1304,9 +1465,16 @@ void ice_devlink_unregister(struct ice_pf *pf)
 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)
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 540c0bdca93654..e76c388b99055f 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -121,6 +121,7 @@ struct ice_aqc_list_caps_elem {
 #define ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE		0x0076
 #define ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT		0x0077
 #define ICE_AQC_CAPS_NVM_MGMT				0x0080
+#define ICE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE		0x0085
 #define ICE_AQC_CAPS_FW_LAG_SUPPORT			0x0092
 #define ICE_AQC_BIT_ROCEV2_LAG				0x01
 #define ICE_AQC_BIT_SRIOV_LAG				0x02
@@ -810,6 +811,23 @@ struct ice_aqc_get_topo {
 	__le32 addr_low;
 };
 
+/* Get/Set Tx Topology (indirect 0x0418/0x0417) */
+struct ice_aqc_get_set_tx_topo {
+	u8 set_flags;
+#define ICE_AQC_TX_TOPO_FLAGS_CORRER		BIT(0)
+#define ICE_AQC_TX_TOPO_FLAGS_SRC_RAM		BIT(1)
+#define ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW		BIT(4)
+#define ICE_AQC_TX_TOPO_FLAGS_ISSUED		BIT(5)
+
+	u8 get_flags;
+#define ICE_AQC_TX_TOPO_GET_RAM		2
+
+	__le16 reserved1;
+	__le32 reserved2;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
 /* Update TSE (indirect 0x0403)
  * Get TSE (indirect 0x0404)
  * Add TSE (indirect 0x0401)
@@ -1666,6 +1684,15 @@ struct ice_aqc_nvm {
 
 #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;
@@ -2538,6 +2565,7 @@ struct ice_aq_desc {
 		struct ice_aqc_get_link_topo get_link_topo;
 		struct ice_aqc_i2c read_write_i2c;
 		struct ice_aqc_read_i2c_resp read_i2c_resp;
+		struct ice_aqc_get_set_tx_topo get_set_tx_topo;
 	} params;
 };
 
@@ -2644,6 +2672,10 @@ enum ice_adminq_opc {
 	ice_aqc_opc_query_sched_res			= 0x0412,
 	ice_aqc_opc_remove_rl_profiles			= 0x0415,
 
+	/* tx topology commands */
+	ice_aqc_opc_set_tx_topo				= 0x0417,
+	ice_aqc_opc_get_tx_topo				= 0x0418,
+
 	/* PHY commands */
 	ice_aqc_opc_get_phy_caps			= 0x0600,
 	ice_aqc_opc_set_phy_cfg				= 0x0601,
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index f301000aa8a6a0..f4bc8723ffa9ec 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1617,6 +1617,8 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf,
 	case ice_aqc_opc_set_port_params:
 	case ice_aqc_opc_get_vlan_mode_parameters:
 	case ice_aqc_opc_set_vlan_mode_parameters:
+	case ice_aqc_opc_set_tx_topo:
+	case ice_aqc_opc_get_tx_topo:
 	case ice_aqc_opc_add_recipe:
 	case ice_aqc_opc_recipe_to_profile:
 	case ice_aqc_opc_get_recipe:
@@ -2173,6 +2175,9 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 		ice_debug(hw, ICE_DBG_INIT, "%s: sriov_lag = %u\n",
 			  prefix, caps->sriov_lag);
 		break;
+	case ICE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE:
+		caps->tx_sched_topo_comp_mode_en = (number == 1);
+		break;
 	default:
 		/* Not one of the recognized common capabilities */
 		found = false;
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index 2ffa11fa2df1ba..87d86d8897ad96 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -4,6 +4,7 @@
 #include "ice_common.h"
 #include "ice.h"
 #include "ice_ddp.h"
+#include "ice_sched.h"
 
 /* For supporting double VLAN mode, it is necessary to enable or disable certain
  * boost tcam entries. The metadata labels names that match the following
@@ -2272,3 +2273,211 @@ enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf,
 
 	return state;
 }
+
+/**
+ * ice_get_set_tx_topo - get or set Tx topology
+ * @hw: pointer to the HW struct
+ * @buf: pointer to Tx topology buffer
+ * @buf_size: buffer size
+ * @cd: pointer to command details structure or NULL
+ * @flags: pointer to descriptor flags
+ * @set: 0-get, 1-set topology
+ *
+ * The function will get or set Tx topology
+ *
+ * Return: zero when set was successful, negative values otherwise.
+ */
+static int
+ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
+		    struct ice_sq_cd *cd, u8 *flags, bool set)
+{
+	struct ice_aqc_get_set_tx_topo *cmd;
+	struct ice_aq_desc desc;
+	int status;
+
+	cmd = &desc.params.get_set_tx_topo;
+	if (set) {
+		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_tx_topo);
+		cmd->set_flags = ICE_AQC_TX_TOPO_FLAGS_ISSUED;
+		/* requested to update a new topology, not a default topology */
+		if (buf)
+			cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM |
+					  ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW;
+
+		if (ice_is_e825c(hw))
+			desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	} else {
+		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo);
+		cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM;
+	}
+
+	if (!ice_is_e825c(hw))
+		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
+	if (status)
+		return status;
+	/* read the return flag values (first byte) for get operation */
+	if (!set && flags)
+		*flags = desc.params.get_set_tx_topo.set_flags;
+
+	return 0;
+}
+
+/**
+ * ice_cfg_tx_topo - Initialize new Tx topology if available
+ * @hw: pointer to the HW struct
+ * @buf: pointer to Tx topology buffer
+ * @len: buffer size
+ *
+ * The function will apply the new Tx topology from the package buffer
+ * if available.
+ *
+ * Return: zero when update was successful, negative values otherwise.
+ */
+int ice_cfg_tx_topo(struct ice_hw *hw, u8 *buf, u32 len)
+{
+	u8 *current_topo, *new_topo = NULL;
+	struct ice_run_time_cfg_seg *seg;
+	struct ice_buf_hdr *section;
+	struct ice_pkg_hdr *pkg_hdr;
+	enum ice_ddp_state state;
+	u16 offset, size = 0;
+	u32 reg = 0;
+	int status;
+	u8 flags;
+
+	if (!buf || !len)
+		return -EINVAL;
+
+	/* Does FW support new Tx topology mode ? */
+	if (!hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) {
+		ice_debug(hw, ICE_DBG_INIT, "FW doesn't support compatibility mode\n");
+		return -EOPNOTSUPP;
+	}
+
+	current_topo = kzalloc(ICE_AQ_MAX_BUF_LEN, GFP_KERNEL);
+	if (!current_topo)
+		return -ENOMEM;
+
+	/* Get the current Tx topology */
+	status = ice_get_set_tx_topo(hw, current_topo, ICE_AQ_MAX_BUF_LEN, NULL,
+				     &flags, false);
+
+	kfree(current_topo);
+
+	if (status) {
+		ice_debug(hw, ICE_DBG_INIT, "Get current topology is failed\n");
+		return status;
+	}
+
+	/* Is default topology already applied ? */
+	if (!(flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) &&
+	    hw->num_tx_sched_layers == ICE_SCHED_9_LAYERS) {
+		ice_debug(hw, ICE_DBG_INIT, "Default topology already applied\n");
+		return -EEXIST;
+	}
+
+	/* Is new topology already applied ? */
+	if ((flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) &&
+	    hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS) {
+		ice_debug(hw, ICE_DBG_INIT, "New topology already applied\n");
+		return -EEXIST;
+	}
+
+	/* Setting topology already issued? */
+	if (flags & ICE_AQC_TX_TOPO_FLAGS_ISSUED) {
+		ice_debug(hw, ICE_DBG_INIT, "Update Tx topology was done by another PF\n");
+		/* Add a small delay before exiting */
+		msleep(2000);
+		return -EEXIST;
+	}
+
+	/* Change the topology from new to default (5 to 9) */
+	if (!(flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) &&
+	    hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS) {
+		ice_debug(hw, ICE_DBG_INIT, "Change topology from 5 to 9 layers\n");
+		goto update_topo;
+	}
+
+	pkg_hdr = (struct ice_pkg_hdr *)buf;
+	state = ice_verify_pkg(pkg_hdr, len);
+	if (state) {
+		ice_debug(hw, ICE_DBG_INIT, "Failed to verify pkg (err: %d)\n",
+			  state);
+		return -EIO;
+	}
+
+	/* Find runtime configuration segment */
+	seg = (struct ice_run_time_cfg_seg *)
+	      ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE_RUN_TIME_CFG, pkg_hdr);
+	if (!seg) {
+		ice_debug(hw, ICE_DBG_INIT, "5 layer topology segment is missing\n");
+		return -EIO;
+	}
+
+	if (le32_to_cpu(seg->buf_table.buf_count) < ICE_MIN_S_COUNT) {
+		ice_debug(hw, ICE_DBG_INIT, "5 layer topology segment count(%d) is wrong\n",
+			  seg->buf_table.buf_count);
+		return -EIO;
+	}
+
+	section = ice_pkg_val_buf(seg->buf_table.buf_array);
+	if (!section || le32_to_cpu(section->section_entry[0].type) !=
+		ICE_SID_TX_5_LAYER_TOPO) {
+		ice_debug(hw, ICE_DBG_INIT, "5 layer topology section type is wrong\n");
+		return -EIO;
+	}
+
+	size = le16_to_cpu(section->section_entry[0].size);
+	offset = le16_to_cpu(section->section_entry[0].offset);
+	if (size < ICE_MIN_S_SZ || size > ICE_MAX_S_SZ) {
+		ice_debug(hw, ICE_DBG_INIT, "5 layer topology section size is wrong\n");
+		return -EIO;
+	}
+
+	/* Make sure the section fits in the buffer */
+	if (offset + size > ICE_PKG_BUF_SIZE) {
+		ice_debug(hw, ICE_DBG_INIT, "5 layer topology buffer > 4K\n");
+		return -EIO;
+	}
+
+	/* Get the new topology buffer */
+	new_topo = ((u8 *)section) + offset;
+
+update_topo:
+	/* Acquire global lock to make sure that set topology issued
+	 * by one PF.
+	 */
+	status = ice_acquire_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID, ICE_RES_WRITE,
+				 ICE_GLOBAL_CFG_LOCK_TIMEOUT);
+	if (status) {
+		ice_debug(hw, ICE_DBG_INIT, "Failed to acquire global lock\n");
+		return status;
+	}
+
+	/* Check if reset was triggered already. */
+	reg = rd32(hw, GLGEN_RSTAT);
+	if (reg & GLGEN_RSTAT_DEVSTATE_M) {
+		/* Reset is in progress, re-init the HW again */
+		ice_debug(hw, ICE_DBG_INIT, "Reset is in progress. Layer topology might be applied already\n");
+		ice_check_reset(hw);
+		return 0;
+	}
+
+	/* Set new topology */
+	status = ice_get_set_tx_topo(hw, new_topo, size, NULL, NULL, true);
+	if (status) {
+		ice_debug(hw, ICE_DBG_INIT, "Failed setting Tx topology\n");
+		return status;
+	}
+
+	/* New topology is updated, delay 1 second before issuing the CORER */
+	msleep(1000);
+	ice_reset(hw, ICE_RESET_CORER);
+	/* CORER will clear the global lock, so no explicit call
+	 * required for release.
+	 */
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.h b/drivers/net/ethernet/intel/ice/ice_ddp.h
index ff66c2ffb1a247..622543f08b4313 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.h
@@ -454,4 +454,6 @@ u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld);
 void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state,
 			   u32 sect_type);
 
+int ice_cfg_tx_topo(struct ice_hw *hw, u8 *buf, u32 len);
+
 #endif
diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c
index 319a2d6fe26c77..f81db6c107c8ef 100644
--- a/drivers/net/ethernet/intel/ice/ice_fw_update.c
+++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c
@@ -286,10 +286,9 @@ ice_send_component_table(struct pldmfw *context, struct pldmfw_component *compon
  *
  * 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);
diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.h b/drivers/net/ethernet/intel/ice/ice_fw_update.h
index 7505748857165a..04b20046275709 100644
--- a/drivers/net/ethernet/intel/ice/ice_fw_update.h
+++ b/drivers/net/ethernet/intel/ice/ice_fw_update.h
@@ -9,5 +9,8 @@ int ice_devlink_flash_update(struct devlink *devlink,
 			     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
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 2b173638b877af..6adfd7e11460e1 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4453,11 +4453,13 @@ static char *ice_get_opt_fw_name(struct ice_pf *pf)
 /**
  * ice_request_fw - Device initialization routine
  * @pf: pointer to the PF instance
+ * @firmware: double pointer to firmware struct
+ *
+ * Return: zero when successful, negative values otherwise.
  */
-static void ice_request_fw(struct ice_pf *pf)
+static int ice_request_fw(struct ice_pf *pf, const struct firmware **firmware)
 {
 	char *opt_fw_filename = ice_get_opt_fw_name(pf);
-	const struct firmware *firmware = NULL;
 	struct device *dev = ice_pf_to_dev(pf);
 	int err = 0;
 
@@ -4466,29 +4468,95 @@ static void ice_request_fw(struct ice_pf *pf)
 	 * and warning messages for other errors.
 	 */
 	if (opt_fw_filename) {
-		err = firmware_request_nowarn(&firmware, opt_fw_filename, dev);
-		if (err) {
-			kfree(opt_fw_filename);
-			goto dflt_pkg_load;
-		}
-
-		/* request for firmware was successful. Download to device */
-		ice_load_pkg(firmware, pf);
+		err = firmware_request_nowarn(firmware, opt_fw_filename, dev);
 		kfree(opt_fw_filename);
-		release_firmware(firmware);
-		return;
+		if (!err)
+			return err;
 	}
+	err = request_firmware(firmware, ICE_DDP_PKG_FILE, dev);
+	if (err)
+		dev_err(dev, "The DDP package file was not found or could not be read. Entering Safe Mode\n");
+
+	return err;
+}
+
+/**
+ * ice_init_tx_topology - performs Tx topology initialization
+ * @hw: pointer to the hardware structure
+ * @firmware: pointer to firmware structure
+ *
+ * Return: zero when init was successful, negative values otherwise.
+ */
+static int
+ice_init_tx_topology(struct ice_hw *hw, const struct firmware *firmware)
+{
+	u8 num_tx_sched_layers = hw->num_tx_sched_layers;
+	struct ice_pf *pf = hw->back;
+	struct device *dev;
+	u8 *buf_copy;
+	int err;
+
+	dev = ice_pf_to_dev(pf);
+	/* ice_cfg_tx_topo buf argument is not a constant,
+	 * so we have to make a copy
+	 */
+	buf_copy = kmemdup(firmware->data, firmware->size, GFP_KERNEL);
+
+	err = ice_cfg_tx_topo(hw, buf_copy, firmware->size);
+	if (!err) {
+		if (hw->num_tx_sched_layers > num_tx_sched_layers)
+			dev_info(dev, "Tx scheduling layers switching feature disabled\n");
+		else
+			dev_info(dev, "Tx scheduling layers switching feature enabled\n");
+		/* if there was a change in topology ice_cfg_tx_topo triggered
+		 * a CORER and we need to re-init hw
+		 */
+		ice_deinit_hw(hw);
+		err = ice_init_hw(hw);
 
-dflt_pkg_load:
-	err = request_firmware(&firmware, ICE_DDP_PKG_FILE, dev);
+		return err;
+	} else if (err == -EIO) {
+		dev_info(dev, "DDP package does not support Tx scheduling layers switching feature - please update to the latest DDP package and try again\n");
+	}
+
+	return 0;
+}
+
+/**
+ * ice_init_ddp_config - DDP related configuration
+ * @hw: pointer to the hardware structure
+ * @pf: pointer to pf structure
+ *
+ * This function loads DDP file from the disk, then initializes Tx
+ * topology. At the end DDP package is loaded on the card.
+ *
+ * Return: zero when init was successful, negative values otherwise.
+ */
+static int ice_init_ddp_config(struct ice_hw *hw, struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	const struct firmware *firmware = NULL;
+	int err;
+
+	err = ice_request_fw(pf, &firmware);
 	if (err) {
-		dev_err(dev, "The DDP package file was not found or could not be read. Entering Safe Mode\n");
-		return;
+		dev_err(dev, "Fail during requesting FW: %d\n", err);
+		return err;
+	}
+
+	err = ice_init_tx_topology(hw, firmware);
+	if (err) {
+		dev_err(dev, "Fail during initialization of Tx topology: %d\n",
+			err);
+		release_firmware(firmware);
+		return err;
 	}
 
-	/* request for firmware was successful. Download to device */
+	/* Download firmware to device */
 	ice_load_pkg(firmware, pf);
 	release_firmware(firmware);
+
+	return 0;
 }
 
 /**
@@ -4661,9 +4729,11 @@ int ice_init_dev(struct ice_pf *pf)
 
 	ice_init_feature_support(pf);
 
-	ice_request_fw(pf);
+	err = ice_init_ddp_config(hw, pf);
+	if (err)
+		return err;
 
-	/* if ice_request_fw fails, ICE_FLAG_ADV_FEATURES bit won't be
+	/* if ice_init_ddp_config fails, ICE_FLAG_ADV_FEATURES bit won't be
 	 * set in pf->state, which will cause ice_is_safe_mode to return
 	 * true
 	 */
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index d4e05d2cb30c4f..84eab92dc03cfe 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -18,10 +18,9 @@
  *
  * 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;
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.h b/drivers/net/ethernet/intel/ice/ice_nvm.h
index 774c2317967d73..63cdc6bdac5899 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.h
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.h
@@ -14,6 +14,9 @@ struct ice_orom_civd_info {
 
 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);
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index a1525992d14bc7..ecf8f5d6029219 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -1128,12 +1128,11 @@ u8 ice_sched_get_vsi_layer(struct ice_hw *hw)
 	 *     5 or less       sw_entry_point_layer
 	 */
 	/* calculate the VSI layer based on number of layers. */
-	if (hw->num_tx_sched_layers > ICE_VSI_LAYER_OFFSET + 1) {
-		u8 layer = hw->num_tx_sched_layers - ICE_VSI_LAYER_OFFSET;
-
-		if (layer > hw->sw_entry_point_layer)
-			return layer;
-	}
+	if (hw->num_tx_sched_layers == ICE_SCHED_9_LAYERS)
+		return hw->num_tx_sched_layers - ICE_VSI_LAYER_OFFSET;
+	else if (hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS)
+		/* qgroup and VSI layers are same */
+		return hw->num_tx_sched_layers - ICE_QGRP_LAYER_OFFSET;
 	return hw->sw_entry_point_layer;
 }
 
@@ -1150,13 +1149,10 @@ u8 ice_sched_get_agg_layer(struct ice_hw *hw)
 	 *     7 or less       sw_entry_point_layer
 	 */
 	/* calculate the aggregator layer based on number of layers. */
-	if (hw->num_tx_sched_layers > ICE_AGG_LAYER_OFFSET + 1) {
-		u8 layer = hw->num_tx_sched_layers - ICE_AGG_LAYER_OFFSET;
-
-		if (layer > hw->sw_entry_point_layer)
-			return layer;
-	}
-	return hw->sw_entry_point_layer;
+	if (hw->num_tx_sched_layers == ICE_SCHED_9_LAYERS)
+		return hw->num_tx_sched_layers - ICE_AGG_LAYER_OFFSET;
+	else
+		return hw->sw_entry_point_layer;
 }
 
 /**
@@ -1510,10 +1506,11 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
 {
 	struct ice_sched_node *vsi_node, *qgrp_node;
 	struct ice_vsi_ctx *vsi_ctx;
+	u8 qgrp_layer, vsi_layer;
 	u16 max_children;
-	u8 qgrp_layer;
 
 	qgrp_layer = ice_sched_get_qgrp_layer(pi->hw);
+	vsi_layer = ice_sched_get_vsi_layer(pi->hw);
 	max_children = pi->hw->max_children[qgrp_layer];
 
 	vsi_ctx = ice_get_vsi_ctx(pi->hw, vsi_handle);
@@ -1524,6 +1521,12 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
 	if (!vsi_node)
 		return NULL;
 
+	/* If the queue group and VSI layer are same then queues
+	 * are all attached directly to VSI
+	 */
+	if (qgrp_layer == vsi_layer)
+		return vsi_node;
+
 	/* get the first queue group node from VSI sub-tree */
 	qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer);
 	while (qgrp_node) {
@@ -3199,7 +3202,7 @@ ice_sched_add_rl_profile(struct ice_port_info *pi,
 	u8 profile_type;
 	int status;
 
-	if (layer_num >= ICE_AQC_TOPO_MAX_LEVEL_NUM)
+	if (!pi || layer_num >= pi->hw->num_tx_sched_layers)
 		return NULL;
 	switch (rl_type) {
 	case ICE_MIN_BW:
@@ -3215,8 +3218,6 @@ ice_sched_add_rl_profile(struct ice_port_info *pi,
 		return NULL;
 	}
 
-	if (!pi)
-		return NULL;
 	hw = pi->hw;
 	list_for_each_entry(rl_prof_elem, &pi->rl_prof_list[layer_num],
 			    list_entry)
@@ -3446,7 +3447,7 @@ ice_sched_rm_rl_profile(struct ice_port_info *pi, u8 layer_num, u8 profile_type,
 	struct ice_aqc_rl_profile_info *rl_prof_elem;
 	int status = 0;
 
-	if (layer_num >= ICE_AQC_TOPO_MAX_LEVEL_NUM)
+	if (layer_num >= pi->hw->num_tx_sched_layers)
 		return -EINVAL;
 	/* Check the existing list for RL profile */
 	list_for_each_entry(rl_prof_elem, &pi->rl_prof_list[layer_num],
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h
index 1aef05ea5a5756..7b668083be07b0 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.h
+++ b/drivers/net/ethernet/intel/ice/ice_sched.h
@@ -6,6 +6,17 @@
 
 #include "ice_common.h"
 
+/**
+ * DOC: ice_sched.h
+ *
+ * This header file stores everything that is needed for broadly understood
+ * scheduler. It consists of defines related to layers, structures related to
+ * aggregator, functions declarations and others.
+ */
+
+#define ICE_SCHED_5_LAYERS	5
+#define ICE_SCHED_9_LAYERS	9
+
 #define SCHED_NODE_NAME_MAX_LEN 32
 
 #define ICE_QGRP_LAYER_OFFSET	2
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 4049ae40c4fbe6..f0796a93f4287e 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -296,6 +296,7 @@ struct ice_hw_common_caps {
 	bool pcie_reset_avoidance;
 	/* Post update reset restriction */
 	bool reset_restrict_support;
+	bool tx_sched_topo_comp_mode_en;
 };
 
 /* IEEE 1588 TIME_SYNC specific info */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index 96c04f7d93f8b5..7498ab429963d4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -1202,7 +1202,8 @@ static int rvu_af_dl_dwrr_mtu_validate(struct devlink *devlink, u32 id,
 }
 
 static int rvu_af_dl_dwrr_mtu_set(struct devlink *devlink, u32 id,
-				  struct devlink_param_gset_ctx *ctx)
+				  struct devlink_param_gset_ctx *ctx,
+				  struct netlink_ext_ack *extack)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
 	struct rvu *rvu = rvu_dl->rvu;
@@ -1256,7 +1257,8 @@ static int rvu_af_npc_exact_feature_get(struct devlink *devlink, u32 id,
 }
 
 static int rvu_af_npc_exact_feature_disable(struct devlink *devlink, u32 id,
-					    struct devlink_param_gset_ctx *ctx)
+					    struct devlink_param_gset_ctx *ctx,
+					    struct netlink_ext_ack *extack)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
 	struct rvu *rvu = rvu_dl->rvu;
@@ -1310,7 +1312,8 @@ static int rvu_af_dl_npc_mcam_high_zone_percent_get(struct devlink *devlink, u32
 }
 
 static int rvu_af_dl_npc_mcam_high_zone_percent_set(struct devlink *devlink, u32 id,
-						    struct devlink_param_gset_ctx *ctx)
+						    struct devlink_param_gset_ctx *ctx,
+						    struct netlink_ext_ack *extack)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
 	struct rvu *rvu = rvu_dl->rvu;
@@ -1367,7 +1370,8 @@ static int rvu_af_dl_nix_maxlf_get(struct devlink *devlink, u32 id,
 }
 
 static int rvu_af_dl_nix_maxlf_set(struct devlink *devlink, u32 id,
-				   struct devlink_param_gset_ctx *ctx)
+				   struct devlink_param_gset_ctx *ctx,
+				   struct netlink_ext_ack *extack)
 {
 	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
 	struct rvu *rvu = rvu_dl->rvu;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
index 4e1130496573ef..99ddf31269d963 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
@@ -32,7 +32,8 @@ static int otx2_dl_mcam_count_validate(struct devlink *devlink, u32 id,
 }
 
 static int otx2_dl_mcam_count_set(struct devlink *devlink, u32 id,
-				  struct devlink_param_gset_ctx *ctx)
+				  struct devlink_param_gset_ctx *ctx,
+				  struct netlink_ext_ack *extack)
 {
 	struct otx2_devlink *otx2_dl = devlink_priv(devlink);
 	struct otx2_nic *pfvf = otx2_dl->pfvf;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 7b02ff61126de4..98688e4dbec5e3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -185,7 +185,8 @@ static int mlx4_devlink_ierr_reset_get(struct devlink *devlink, u32 id,
 }
 
 static int mlx4_devlink_ierr_reset_set(struct devlink *devlink, u32 id,
-				       struct devlink_param_gset_ctx *ctx)
+				       struct devlink_param_gset_ctx *ctx,
+				       struct netlink_ext_ack *extack)
 {
 	mlx4_internal_err_reset = ctx->val.vbool;
 	return 0;
@@ -202,7 +203,8 @@ static int mlx4_devlink_crdump_snapshot_get(struct devlink *devlink, u32 id,
 }
 
 static int mlx4_devlink_crdump_snapshot_set(struct devlink *devlink, u32 id,
-					    struct devlink_param_gset_ctx *ctx)
+					    struct devlink_param_gset_ctx *ctx,
+					    struct netlink_ext_ack *extack)
 {
 	struct mlx4_priv *priv = devlink_priv(devlink);
 	struct mlx4_dev *dev = &priv->dev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 1789800faaeb62..17f78091ad30ef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1805,7 +1805,8 @@ err:
 }
 
 static int mlx5_devlink_esw_multiport_set(struct devlink *devlink, u32 id,
-					  struct devlink_param_gset_ctx *ctx)
+					  struct devlink_param_gset_ctx *ctx,
+					  struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index dfcc7e85e0a3f7..f378b8176e47c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2413,7 +2413,8 @@ err:
 }
 
 static int esw_port_metadata_set(struct devlink *devlink, u32 id,
-				 struct devlink_param_gset_ctx *ctx)
+				 struct devlink_param_gset_ctx *ctx,
+				 struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index cf085a478e3e4c..32cdacc34a0d66 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -3332,7 +3332,8 @@ static int mlx5_fs_mode_validate(struct devlink *devlink, u32 id,
 }
 
 static int mlx5_fs_mode_set(struct devlink *devlink, u32 id,
-			    struct devlink_param_gset_ctx *ctx)
+			    struct devlink_param_gset_ctx *ctx,
+			    struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	enum mlx5_flow_steering_mode mode;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 2911aa34a5be3f..979c49ae6b5cc9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -52,7 +52,8 @@ static void mlx5_set_fw_rst_ack(struct mlx5_core_dev *dev)
 }
 
 static int mlx5_fw_reset_enable_remote_dev_reset_set(struct devlink *devlink, u32 id,
-						     struct devlink_param_gset_ctx *ctx)
+						     struct devlink_param_gset_ctx *ctx,
+						     struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	struct mlx5_fw_reset *fw_reset;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index f20052776b3f2e..baedf0d45e855a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -1465,7 +1465,8 @@ mlxsw_sp_acl_tcam_region_rehash_intrvl_get(struct devlink *devlink, u32 id,
 
 static int
 mlxsw_sp_acl_tcam_region_rehash_intrvl_set(struct devlink *devlink, u32 id,
-					   struct devlink_param_gset_ctx *ctx)
+					   struct devlink_param_gset_ctx *ctx,
+					   struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
 	struct mlxsw_sp_acl_tcam_vregion *vregion;
diff --git a/drivers/net/ethernet/netronome/nfp/devlink_param.c b/drivers/net/ethernet/netronome/nfp/devlink_param.c
index a655f9e69a7b1e..0e1a3800f371cf 100644
--- a/drivers/net/ethernet/netronome/nfp/devlink_param.c
+++ b/drivers/net/ethernet/netronome/nfp/devlink_param.c
@@ -132,7 +132,8 @@ exit_close_nsp:
 
 static int
 nfp_devlink_param_u8_set(struct devlink *devlink, u32 id,
-			 struct devlink_param_gset_ctx *ctx)
+			 struct devlink_param_gset_ctx *ctx,
+			 struct netlink_ext_ack *extack)
 {
 	const struct nfp_devlink_param_u8_arg *arg;
 	struct nfp_pf *pf = devlink_priv(devlink);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c
index dad8e617c39347..1adc7fbb3f2fce 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_devlink.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c
@@ -132,7 +132,8 @@ static int qed_dl_param_get(struct devlink *dl, u32 id,
 }
 
 static int qed_dl_param_set(struct devlink *dl, u32 id,
-			    struct devlink_param_gset_ctx *ctx)
+			    struct devlink_param_gset_ctx *ctx,
+			    struct netlink_ext_ack *extack)
 {
 	struct qed_devlink *qed_dl = devlink_priv(dl);
 	struct qed_dev *cdev;
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 67b3a94e5efa85..4e50b379288859 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -3056,7 +3056,8 @@ static void am65_cpsw_init_port_switch_ale(struct am65_cpsw_port *port)
 }
 
 static int am65_cpsw_dl_switch_mode_set(struct devlink *dl, u32 id,
-					struct devlink_param_gset_ctx *ctx)
+					struct devlink_param_gset_ctx *ctx,
+					struct netlink_ext_ack *extack)
 {
 	struct am65_cpsw_devlink *dl_priv = devlink_priv(dl);
 	struct am65_cpsw_common *cpsw = dl_priv->common;
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 087dcb67505a2d..2baa198ebfa090 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -1625,7 +1625,8 @@ static int cpsw_dl_switch_mode_get(struct devlink *dl, u32 id,
 }
 
 static int cpsw_dl_switch_mode_set(struct devlink *dl, u32 id,
-				   struct devlink_param_gset_ctx *ctx)
+				   struct devlink_param_gset_ctx *ctx,
+				   struct netlink_ext_ack *extack)
 {
 	struct cpsw_devlink *dl_priv = devlink_priv(dl);
 	struct cpsw_common *cpsw = dl_priv->cpsw;
@@ -1762,7 +1763,8 @@ static int cpsw_dl_ale_ctrl_get(struct devlink *dl, u32 id,
 }
 
 static int cpsw_dl_ale_ctrl_set(struct devlink *dl, u32 id,
-				struct devlink_param_gset_ctx *ctx)
+				struct devlink_param_gset_ctx *ctx,
+				struct netlink_ext_ack *extack)
 {
 	struct cpsw_devlink *dl_priv = devlink_priv(dl);
 	struct cpsw_common *cpsw = dl_priv->cpsw;
diff --git a/drivers/net/wwan/iosm/iosm_ipc_devlink.c b/drivers/net/wwan/iosm/iosm_ipc_devlink.c
index 2fe724d623c061..bef6819986e939 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_devlink.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_devlink.c
@@ -33,7 +33,8 @@ static int ipc_devlink_get_param(struct devlink *dl, u32 id,
 
 /* Set the param values for the specific param ID's */
 static int ipc_devlink_set_param(struct devlink *dl, u32 id,
-				 struct devlink_param_gset_ctx *ctx)
+				 struct devlink_param_gset_ctx *ctx,
+				 struct netlink_ext_ack *extack)
 {
 	struct iosm_devlink *ipc_devlink = devlink_priv(dl);
 
diff --git a/include/net/devlink.h b/include/net/devlink.h
index d31769a116cef2..35eb0f88438617 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -483,7 +483,8 @@ struct devlink_param {
 	int (*get)(struct devlink *devlink, u32 id,
 		   struct devlink_param_gset_ctx *ctx);
 	int (*set)(struct devlink *devlink, u32 id,
-		   struct devlink_param_gset_ctx *ctx);
+		   struct devlink_param_gset_ctx *ctx,
+		   struct netlink_ext_ack *extack);
 	int (*validate)(struct devlink *devlink, u32 id,
 			union devlink_param_value val,
 			struct netlink_ext_ack *extack);
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 7edfd8de8882fe..a6ef7e4c503ff3 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -1258,7 +1258,8 @@ struct dsa_switch_ops {
 int dsa_devlink_param_get(struct devlink *dl, u32 id,
 			  struct devlink_param_gset_ctx *ctx);
 int dsa_devlink_param_set(struct devlink *dl, u32 id,
-			  struct devlink_param_gset_ctx *ctx);
+			  struct devlink_param_gset_ctx *ctx,
+			  struct netlink_ext_ack *extack);
 int dsa_devlink_params_register(struct dsa_switch *ds,
 				const struct devlink_param *params,
 				size_t params_count);
diff --git a/net/devlink/param.c b/net/devlink/param.c
index 22bc3b50051897..dcf0d1ccebbabe 100644
--- a/net/devlink/param.c
+++ b/net/devlink/param.c
@@ -158,11 +158,12 @@ static int devlink_param_get(struct devlink *devlink,
 
 static int devlink_param_set(struct devlink *devlink,
 			     const struct devlink_param *param,
-			     struct devlink_param_gset_ctx *ctx)
+			     struct devlink_param_gset_ctx *ctx,
+			     struct netlink_ext_ack *extack)
 {
 	if (!param->set)
 		return -EOPNOTSUPP;
-	return param->set(devlink, param->id, ctx);
+	return param->set(devlink, param->id, ctx, extack);
 }
 
 static int
@@ -571,7 +572,7 @@ static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink,
 			return -EOPNOTSUPP;
 		ctx.val = value;
 		ctx.cmode = cmode;
-		err = devlink_param_set(devlink, param, &ctx);
+		err = devlink_param_set(devlink, param, &ctx, info->extack);
 		if (err)
 			return err;
 	}
diff --git a/net/dsa/devlink.c b/net/dsa/devlink.c
index 431bf52290a1cf..0aac887d009804 100644
--- a/net/dsa/devlink.c
+++ b/net/dsa/devlink.c
@@ -194,7 +194,8 @@ int dsa_devlink_param_get(struct devlink *dl, u32 id,
 EXPORT_SYMBOL_GPL(dsa_devlink_param_get);
 
 int dsa_devlink_param_set(struct devlink *dl, u32 id,
-			  struct devlink_param_gset_ctx *ctx)
+			  struct devlink_param_gset_ctx *ctx,
+			  struct netlink_ext_ack *extack)
 {
 	struct dsa_switch *ds = dsa_devlink_to_ds(dl);