Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/gi…

…t/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>

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
 =============

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;

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);

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;

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;

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

@@ -523,6 +523,156 @@ ice_devlink_reload_empr_finish(struct ice_pf *pf,
 	return 0;
 }
 
+/**
+ * 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)