ice: Configure VSIs for Tx/Rx

This patch configures the VSIs to be able to send and receive
packets by doing the following:

1) Initialize flexible parser to extract and include certain
   fields in the Rx descriptor.

2) Add Tx queues by programming the Tx queue context (implemented in
   ice_vsi_cfg_txqs). Note that adding the queues also enables (starts)
   the queues.

3) Add Rx queues by programming Rx queue context (implemented in
   ice_vsi_cfg_rxqs). Note that this only adds queues but doesn't start
   them. The rings will be started by calling ice_vsi_start_rx_rings on
   interface up.

4) Configure interrupts for VSI queues.

5) Implement ice_open and ice_stop.

Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

drivers/net/ethernet/intel/ice/Makefile

@@ -12,4 +12,5 @@ ice-y := ice_main.o	\
 	 ice_common.o	\
 	 ice_nvm.o	\
 	 ice_switch.o	\
-	 ice_sched.o
+	 ice_sched.o	\
+	 ice_txrx.o

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

@@ -11,8 +11,10 @@
 #include <linux/netdevice.h>
 #include <linux/compiler.h>
 #include <linux/etherdevice.h>
+#include <linux/skbuff.h>
 #include <linux/cpumask.h>
 #include <linux/if_vlan.h>
+#include <linux/dma-mapping.h>
 #include <linux/pci.h>
 #include <linux/workqueue.h>
 #include <linux/aer.h>
@@ -43,6 +45,8 @@
 #define ICE_VSI_MAP_SCATTER	1
 #define ICE_MAX_SCATTER_TXQS	16
 #define ICE_MAX_SCATTER_RXQS	16
+#define ICE_Q_WAIT_RETRY_LIMIT	10
+#define ICE_Q_WAIT_MAX_RETRY	(5 * ICE_Q_WAIT_RETRY_LIMIT)
 #define ICE_RES_VALID_BIT	0x8000
 #define ICE_RES_MISC_VEC_ID	(ICE_RES_VALID_BIT - 1)
 #define ICE_INVAL_Q_INDEX	0xffff
@@ -56,6 +60,14 @@
 		(((val) << ICE_AQ_VSI_UP_TABLE_UP##i##_S) & \
 		  ICE_AQ_VSI_UP_TABLE_UP##i##_M)
 
+#define ICE_RX_DESC(R, i) (&(((union ice_32b_rx_flex_desc *)((R)->desc))[i]))
+
+#define ice_for_each_txq(vsi, i) \
+	for ((i) = 0; (i) < (vsi)->num_txq; (i)++)
+
+#define ice_for_each_rxq(vsi, i) \
+	for ((i) = 0; (i) < (vsi)->num_rxq; (i)++)
+
 struct ice_tc_info {
 	u16 qoffset;
 	u16 qcount;
@@ -96,6 +108,9 @@ struct ice_vsi {
 	struct ice_ring **rx_rings;	 /* rx ring array */
 	struct ice_ring **tx_rings;	 /* tx ring array */
 	struct ice_q_vector **q_vectors; /* q_vector array */
+
+	irqreturn_t (*irq_handler)(int irq, void *data);
+
 	DECLARE_BITMAP(state, __ICE_STATE_NBITS);
 	int num_q_vectors;
 	int base_vector;
@@ -106,8 +121,14 @@ struct ice_vsi {
 	/* Interrupt thresholds */
 	u16 work_lmt;
 
+	u16 max_frame;
+	u16 rx_buf_len;
+
 	struct ice_aqc_vsi_props info;	 /* VSI properties */
 
+	bool irqs_ready;
+	bool current_isup;		 /* Sync 'link up' logging */
+
 	/* queue information */
 	u8 tx_mapping_mode;		 /* ICE_MAP_MODE_[CONTIG|SCATTER] */
 	u8 rx_mapping_mode;		 /* ICE_MAP_MODE_[CONTIG|SCATTER] */
@@ -128,9 +149,11 @@ struct ice_q_vector {
 	struct napi_struct napi;
 	struct ice_ring_container rx;
 	struct ice_ring_container tx;
+	struct irq_affinity_notify affinity_notify;
 	u16 v_idx;			/* index in the vsi->q_vector array. */
 	u8 num_ring_tx;			/* total number of tx rings in vector */
 	u8 num_ring_rx;			/* total number of rx rings in vector */
+	char name[ICE_INT_NAME_STR_LEN];
 } ____cacheline_internodealigned_in_smp;
 
 enum ice_pf_flags {
@@ -178,10 +201,14 @@ struct ice_netdev_priv {
 /**
  * ice_irq_dynamic_ena - Enable default interrupt generation settings
  * @hw: pointer to hw struct
+ * @vsi: pointer to vsi struct, can be NULL
+ * @q_vector: pointer to q_vector, can be NULL
  */
-static inline void ice_irq_dynamic_ena(struct ice_hw *hw)
+static inline void ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi,
+				       struct ice_q_vector *q_vector)
 {
-	u32 vector = ((struct ice_pf *)hw->back)->oicr_idx;
+	u32 vector = (vsi && q_vector) ? vsi->base_vector + q_vector->v_idx :
+					((struct ice_pf *)hw->back)->oicr_idx;
 	int itr = ICE_ITR_NONE;
 	u32 val;
 
@@ -190,7 +217,10 @@ static inline void ice_irq_dynamic_ena(struct ice_hw *hw)
 	 */
 	val = GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M |
 	      (itr << GLINT_DYN_CTL_ITR_INDX_S);
-
+	if (vsi)
+		if (test_bit(__ICE_DOWN, vsi->state))
+			return;
 	wr32(hw, GLINT_DYN_CTL(vector), val);
 }
+
 #endif /* _ICE_H_ */

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

@@ -968,6 +968,87 @@ struct ice_aqc_nvm {
 	__le32	addr_low;
 };
 
+/* Add TX LAN Queues (indirect 0x0C30) */
+struct ice_aqc_add_txqs {
+	u8 num_qgrps;
+	u8 reserved[3];
+	__le32 reserved1;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* This is the descriptor of each queue entry for the Add TX LAN Queues
+ * command (0x0C30). Only used within struct ice_aqc_add_tx_qgrp.
+ */
+struct ice_aqc_add_txqs_perq {
+	__le16 txq_id;
+	u8 rsvd[2];
+	__le32 q_teid;
+	u8 txq_ctx[22];
+	u8 rsvd2[2];
+	struct ice_aqc_txsched_elem info;
+};
+
+/* The format of the command buffer for Add TX LAN Queues (0x0C30)
+ * is an array of the following structs. Please note that the length of
+ * each struct ice_aqc_add_tx_qgrp is variable due
+ * to the variable number of queues in each group!
+ */
+struct ice_aqc_add_tx_qgrp {
+	__le32 parent_teid;
+	u8 num_txqs;
+	u8 rsvd[3];
+	struct ice_aqc_add_txqs_perq txqs[1];
+};
+
+/* Disable TX LAN Queues (indirect 0x0C31) */
+struct ice_aqc_dis_txqs {
+	u8 cmd_type;
+#define ICE_AQC_Q_DIS_CMD_S		0
+#define ICE_AQC_Q_DIS_CMD_M		(0x3 << ICE_AQC_Q_DIS_CMD_S)
+#define ICE_AQC_Q_DIS_CMD_NO_FUNC_RESET	(0 << ICE_AQC_Q_DIS_CMD_S)
+#define ICE_AQC_Q_DIS_CMD_VM_RESET	BIT(ICE_AQC_Q_DIS_CMD_S)
+#define ICE_AQC_Q_DIS_CMD_VF_RESET	(2 << ICE_AQC_Q_DIS_CMD_S)
+#define ICE_AQC_Q_DIS_CMD_PF_RESET	(3 << ICE_AQC_Q_DIS_CMD_S)
+#define ICE_AQC_Q_DIS_CMD_SUBSEQ_CALL	BIT(2)
+#define ICE_AQC_Q_DIS_CMD_FLUSH_PIPE	BIT(3)
+	u8 num_entries;
+	__le16 vmvf_and_timeout;
+#define ICE_AQC_Q_DIS_VMVF_NUM_S	0
+#define ICE_AQC_Q_DIS_VMVF_NUM_M	(0x3FF << ICE_AQC_Q_DIS_VMVF_NUM_S)
+#define ICE_AQC_Q_DIS_TIMEOUT_S		10
+#define ICE_AQC_Q_DIS_TIMEOUT_M		(0x3F << ICE_AQC_Q_DIS_TIMEOUT_S)
+	__le32 blocked_cgds;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* The buffer for Disable TX LAN Queues (indirect 0x0C31)
+ * contains the following structures, arrayed one after the
+ * other.
+ * Note: Since the q_id is 16 bits wide, if the
+ * number of queues is even, then 2 bytes of alignment MUST be
+ * added before the start of the next group, to allow correct
+ * alignment of the parent_teid field.
+ */
+struct ice_aqc_dis_txq_item {
+	__le32 parent_teid;
+	u8 num_qs;
+	u8 rsvd;
+	/* The length of the q_id array varies according to num_qs */
+	__le16 q_id[1];
+	/* This only applies from F8 onward */
+#define ICE_AQC_Q_DIS_BUF_ELEM_TYPE_S		15
+#define ICE_AQC_Q_DIS_BUF_ELEM_TYPE_LAN_Q	\
+			(0 << ICE_AQC_Q_DIS_BUF_ELEM_TYPE_S)
+#define ICE_AQC_Q_DIS_BUF_ELEM_TYPE_RDMA_QSET	\
+			(1 << ICE_AQC_Q_DIS_BUF_ELEM_TYPE_S)
+};
+
+struct ice_aqc_dis_txq {
+	struct ice_aqc_dis_txq_item qgrps[1];
+};
+
 /**
  * struct ice_aq_desc - Admin Queue (AQ) descriptor
  * @flags: ICE_AQ_FLAG_* flags
@@ -1008,6 +1089,8 @@ struct ice_aq_desc {
 		struct ice_aqc_query_txsched_res query_sched_res;
 		struct ice_aqc_add_move_delete_elem add_move_delete_elem;
 		struct ice_aqc_nvm nvm;
+		struct ice_aqc_add_txqs add_txqs;
+		struct ice_aqc_dis_txqs dis_txqs;
 		struct ice_aqc_add_get_update_free_vsi vsi_cmd;
 		struct ice_aqc_alloc_free_res_cmd sw_res_ctrl;
 		struct ice_aqc_get_link_status get_link_status;
@@ -1088,6 +1171,9 @@ enum ice_adminq_opc {
 	/* NVM commands */
 	ice_aqc_opc_nvm_read				= 0x0701,
 
+	/* TX queue handling commands/events */
+	ice_aqc_opc_add_txqs				= 0x0C30,
+	ice_aqc_opc_dis_txqs				= 0x0C31,
 };
 
 #endif /* _ICE_ADMINQ_CMD_H_ */

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

@@ -7,6 +7,25 @@
 
 #define ICE_PF_RESET_WAIT_COUNT	200
 
+#define ICE_NIC_FLX_ENTRY(hw, mdid, idx) \
+	wr32((hw), GLFLXP_RXDID_FLX_WRD_##idx(ICE_RXDID_FLEX_NIC), \
+	     ((ICE_RX_OPC_MDID << \
+	       GLFLXP_RXDID_FLX_WRD_##idx##_RXDID_OPCODE_S) & \
+	      GLFLXP_RXDID_FLX_WRD_##idx##_RXDID_OPCODE_M) | \
+	     (((mdid) << GLFLXP_RXDID_FLX_WRD_##idx##_PROT_MDID_S) & \
+	      GLFLXP_RXDID_FLX_WRD_##idx##_PROT_MDID_M))
+
+#define ICE_NIC_FLX_FLG_ENTRY(hw, flg_0, flg_1, flg_2, flg_3, idx) \
+	wr32((hw), GLFLXP_RXDID_FLAGS(ICE_RXDID_FLEX_NIC, idx), \
+	     (((flg_0) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) & \
+	      GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M) | \
+	     (((flg_1) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S) & \
+	      GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_M) | \
+	     (((flg_2) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_S) & \
+	      GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_M) | \
+	     (((flg_3) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_S) & \
+	      GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_M))
+
 /**
  * ice_set_mac_type - Sets MAC type
  * @hw: pointer to the HW structure
@@ -258,6 +277,33 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 	return status;
 }
 
+/**
+ * ice_init_flex_parser - initialize rx flex parser
+ * @hw: pointer to the hardware structure
+ *
+ * Function to initialize flex descriptors
+ */
+static void ice_init_flex_parser(struct ice_hw *hw)
+{
+	u8 idx = 0;
+
+	ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_HASH_LOW, 0);
+	ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_HASH_HIGH, 1);
+	ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_FLOW_ID_LOWER, 2);
+	ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_FLOW_ID_HIGH, 3);
+	ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_PKT_FRG, ICE_RXFLG_UDP_GRE,
+			      ICE_RXFLG_PKT_DSI, ICE_RXFLG_FIN, idx++);
+	ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_SYN, ICE_RXFLG_RST,
+			      ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx++);
+	ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI,
+			      ICE_RXFLG_EVLAN_x8100, ICE_RXFLG_EVLAN_x9100,
+			      idx++);
+	ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_VLAN_x8100, ICE_RXFLG_TNL_VLAN,
+			      ICE_RXFLG_TNL_MAC, ICE_RXFLG_TNL0, idx++);
+	ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_TNL1, ICE_RXFLG_TNL2,
+			      ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx);
+}
+
 /**
  * ice_init_fltr_mgmt_struct - initializes filter management list and locks
  * @hw: pointer to the hw struct
@@ -431,6 +477,8 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 	if (status)
 		goto err_unroll_fltr_mgmt_struct;
 
+	ice_init_flex_parser(hw);
+
 	return 0;
 
 err_unroll_fltr_mgmt_struct:
@@ -597,6 +645,114 @@ enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req)
 	return ice_check_reset(hw);
 }
 
+/**
+ * ice_copy_rxq_ctx_to_hw
+ * @hw: pointer to the hardware structure
+ * @ice_rxq_ctx: pointer to the rxq context
+ * @rxq_index: the index of the rx queue
+ *
+ * Copies rxq context from dense structure to hw register space
+ */
+static enum ice_status
+ice_copy_rxq_ctx_to_hw(struct ice_hw *hw, u8 *ice_rxq_ctx, u32 rxq_index)
+{
+	u8 i;
+
+	if (!ice_rxq_ctx)
+		return ICE_ERR_BAD_PTR;
+
+	if (rxq_index > QRX_CTRL_MAX_INDEX)
+		return ICE_ERR_PARAM;
+
+	/* Copy each dword separately to hw */
+	for (i = 0; i < ICE_RXQ_CTX_SIZE_DWORDS; i++) {
+		wr32(hw, QRX_CONTEXT(i, rxq_index),
+		     *((u32 *)(ice_rxq_ctx + (i * sizeof(u32)))));
+
+		ice_debug(hw, ICE_DBG_QCTX, "qrxdata[%d]: %08X\n", i,
+			  *((u32 *)(ice_rxq_ctx + (i * sizeof(u32)))));
+	}
+
+	return 0;
+}
+
+/* LAN Rx Queue Context */
+static const struct ice_ctx_ele ice_rlan_ctx_info[] = {
+	/* Field		Width	LSB */
+	ICE_CTX_STORE(ice_rlan_ctx, head,		13,	0),
+	ICE_CTX_STORE(ice_rlan_ctx, cpuid,		8,	13),
+	ICE_CTX_STORE(ice_rlan_ctx, base,		57,	32),
+	ICE_CTX_STORE(ice_rlan_ctx, qlen,		13,	89),
+	ICE_CTX_STORE(ice_rlan_ctx, dbuf,		7,	102),
+	ICE_CTX_STORE(ice_rlan_ctx, hbuf,		5,	109),
+	ICE_CTX_STORE(ice_rlan_ctx, dtype,		2,	114),
+	ICE_CTX_STORE(ice_rlan_ctx, dsize,		1,	116),
+	ICE_CTX_STORE(ice_rlan_ctx, crcstrip,		1,	117),
+	ICE_CTX_STORE(ice_rlan_ctx, l2tsel,		1,	119),
+	ICE_CTX_STORE(ice_rlan_ctx, hsplit_0,		4,	120),
+	ICE_CTX_STORE(ice_rlan_ctx, hsplit_1,		2,	124),
+	ICE_CTX_STORE(ice_rlan_ctx, showiv,		1,	127),
+	ICE_CTX_STORE(ice_rlan_ctx, rxmax,		14,	174),
+	ICE_CTX_STORE(ice_rlan_ctx, tphrdesc_ena,	1,	193),
+	ICE_CTX_STORE(ice_rlan_ctx, tphwdesc_ena,	1,	194),
+	ICE_CTX_STORE(ice_rlan_ctx, tphdata_ena,	1,	195),
+	ICE_CTX_STORE(ice_rlan_ctx, tphhead_ena,	1,	196),
+	ICE_CTX_STORE(ice_rlan_ctx, lrxqthresh,		3,	198),
+	{ 0 }
+};
+
+/**
+ * ice_write_rxq_ctx
+ * @hw: pointer to the hardware structure
+ * @rlan_ctx: pointer to the rxq context
+ * @rxq_index: the index of the rx queue
+ *
+ * Converts rxq context from sparse to dense structure and then writes
+ * it to hw register space
+ */
+enum ice_status
+ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
+		  u32 rxq_index)
+{
+	u8 ctx_buf[ICE_RXQ_CTX_SZ] = { 0 };
+
+	ice_set_ctx((u8 *)rlan_ctx, ctx_buf, ice_rlan_ctx_info);
+	return ice_copy_rxq_ctx_to_hw(hw, ctx_buf, rxq_index);
+}
+
+/* LAN Tx Queue Context */
+const struct ice_ctx_ele ice_tlan_ctx_info[] = {
+				    /* Field			Width	LSB */
+	ICE_CTX_STORE(ice_tlan_ctx, base,			57,	0),
+	ICE_CTX_STORE(ice_tlan_ctx, port_num,			3,	57),
+	ICE_CTX_STORE(ice_tlan_ctx, cgd_num,			5,	60),
+	ICE_CTX_STORE(ice_tlan_ctx, pf_num,			3,	65),
+	ICE_CTX_STORE(ice_tlan_ctx, vmvf_num,			10,	68),
+	ICE_CTX_STORE(ice_tlan_ctx, vmvf_type,			2,	78),
+	ICE_CTX_STORE(ice_tlan_ctx, src_vsi,			10,	80),
+	ICE_CTX_STORE(ice_tlan_ctx, tsyn_ena,			1,	90),
+	ICE_CTX_STORE(ice_tlan_ctx, alt_vlan,			1,	92),
+	ICE_CTX_STORE(ice_tlan_ctx, cpuid,			8,	93),
+	ICE_CTX_STORE(ice_tlan_ctx, wb_mode,			1,	101),
+	ICE_CTX_STORE(ice_tlan_ctx, tphrd_desc,			1,	102),
+	ICE_CTX_STORE(ice_tlan_ctx, tphrd,			1,	103),
+	ICE_CTX_STORE(ice_tlan_ctx, tphwr_desc,			1,	104),
+	ICE_CTX_STORE(ice_tlan_ctx, cmpq_id,			9,	105),
+	ICE_CTX_STORE(ice_tlan_ctx, qnum_in_func,		14,	114),
+	ICE_CTX_STORE(ice_tlan_ctx, itr_notification_mode,	1,	128),
+	ICE_CTX_STORE(ice_tlan_ctx, adjust_prof_id,		6,	129),
+	ICE_CTX_STORE(ice_tlan_ctx, qlen,			13,	135),
+	ICE_CTX_STORE(ice_tlan_ctx, quanta_prof_idx,		4,	148),
+	ICE_CTX_STORE(ice_tlan_ctx, tso_ena,			1,	152),
+	ICE_CTX_STORE(ice_tlan_ctx, tso_qnum,			11,	153),
+	ICE_CTX_STORE(ice_tlan_ctx, legacy_int,			1,	164),
+	ICE_CTX_STORE(ice_tlan_ctx, drop_ena,			1,	165),
+	ICE_CTX_STORE(ice_tlan_ctx, cache_prof_idx,		2,	166),
+	ICE_CTX_STORE(ice_tlan_ctx, pkt_shaper_prof_idx,	3,	168),
+	ICE_CTX_STORE(ice_tlan_ctx, int_q_state,		110,	171),
+	{ 0 }
+};
+
 /**
  * ice_debug_cq
  * @hw: pointer to the hardware structure
@@ -1104,3 +1260,449 @@ void ice_clear_pxe_mode(struct ice_hw *hw)
 	if (ice_check_sq_alive(hw, &hw->adminq))
 		ice_aq_clear_pxe_mode(hw);
 }
+
+/**
+ * ice_aq_add_lan_txq
+ * @hw: pointer to the hardware structure
+ * @num_qgrps: Number of added queue groups
+ * @qg_list: list of queue groups to be added
+ * @buf_size: size of buffer for indirect command
+ * @cd: pointer to command details structure or NULL
+ *
+ * Add Tx LAN queue (0x0C30)
+ *
+ * NOTE:
+ * Prior to calling add Tx LAN queue:
+ * Initialize the following as part of the Tx queue context:
+ * Completion queue ID if the queue uses Completion queue, Quanta profile,
+ * Cache profile and Packet shaper profile.
+ *
+ * After add Tx LAN queue AQ command is completed:
+ * Interrupts should be associated with specific queues,
+ * Association of Tx queue to Doorbell queue is not part of Add LAN Tx queue
+ * flow.
+ */
+static enum ice_status
+ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps,
+		   struct ice_aqc_add_tx_qgrp *qg_list, u16 buf_size,
+		   struct ice_sq_cd *cd)
+{
+	u16 i, sum_header_size, sum_q_size = 0;
+	struct ice_aqc_add_tx_qgrp *list;
+	struct ice_aqc_add_txqs *cmd;
+	struct ice_aq_desc desc;
+
+	cmd = &desc.params.add_txqs;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_txqs);
+
+	if (!qg_list)
+		return ICE_ERR_PARAM;
+
+	if (num_qgrps > ICE_LAN_TXQ_MAX_QGRPS)
+		return ICE_ERR_PARAM;
+
+	sum_header_size = num_qgrps *
+		(sizeof(*qg_list) - sizeof(*qg_list->txqs));
+
+	list = qg_list;
+	for (i = 0; i < num_qgrps; i++) {
+		struct ice_aqc_add_txqs_perq *q = list->txqs;
+
+		sum_q_size += list->num_txqs * sizeof(*q);
+		list = (struct ice_aqc_add_tx_qgrp *)(q + list->num_txqs);
+	}
+
+	if (buf_size != (sum_header_size + sum_q_size))
+		return ICE_ERR_PARAM;
+
+	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+	cmd->num_qgrps = num_qgrps;
+
+	return ice_aq_send_cmd(hw, &desc, qg_list, buf_size, cd);
+}
+
+/**
+ * ice_aq_dis_lan_txq
+ * @hw: pointer to the hardware structure
+ * @num_qgrps: number of groups in the list
+ * @qg_list: the list of groups to disable
+ * @buf_size: the total size of the qg_list buffer in bytes
+ * @cd: pointer to command details structure or NULL
+ *
+ * Disable LAN Tx queue (0x0C31)
+ */
+static enum ice_status
+ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
+		   struct ice_aqc_dis_txq_item *qg_list, u16 buf_size,
+		   struct ice_sq_cd *cd)
+{
+	struct ice_aqc_dis_txqs *cmd;
+	struct ice_aq_desc desc;
+	u16 i, sz = 0;
+
+	cmd = &desc.params.dis_txqs;
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_dis_txqs);
+
+	if (!qg_list)
+		return ICE_ERR_PARAM;
+
+	if (num_qgrps > ICE_LAN_TXQ_MAX_QGRPS)
+		return ICE_ERR_PARAM;
+	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	cmd->num_entries = num_qgrps;
+
+	for (i = 0; i < num_qgrps; ++i) {
+		/* Calculate the size taken up by the queue IDs in this group */
+		sz += qg_list[i].num_qs * sizeof(qg_list[i].q_id);
+
+		/* Add the size of the group header */
+		sz += sizeof(qg_list[i]) - sizeof(qg_list[i].q_id);
+
+		/* If the num of queues is even, add 2 bytes of padding */
+		if ((qg_list[i].num_qs % 2) == 0)
+			sz += 2;
+	}
+
+	if (buf_size != sz)
+		return ICE_ERR_PARAM;
+
+	return ice_aq_send_cmd(hw, &desc, qg_list, buf_size, cd);
+}
+
+/* End of FW Admin Queue command wrappers */
+
+/**
+ * ice_write_byte - write a byte to a packed context structure
+ * @src_ctx:  the context structure to read from
+ * @dest_ctx: the context to be written to
+ * @ce_info:  a description of the struct to be filled
+ */
+static void ice_write_byte(u8 *src_ctx, u8 *dest_ctx,
+			   const struct ice_ctx_ele *ce_info)
+{
+	u8 src_byte, dest_byte, mask;
+	u8 *from, *dest;
+	u16 shift_width;
+
+	/* copy from the next struct field */
+	from = src_ctx + ce_info->offset;
+
+	/* prepare the bits and mask */
+	shift_width = ce_info->lsb % 8;
+	mask = (u8)(BIT(ce_info->width) - 1);
+
+	src_byte = *from;
+	src_byte &= mask;
+
+	/* shift to correct alignment */
+	mask <<= shift_width;
+	src_byte <<= shift_width;
+
+	/* get the current bits from the target bit string */
+	dest = dest_ctx + (ce_info->lsb / 8);
+
+	memcpy(&dest_byte, dest, sizeof(dest_byte));
+
+	dest_byte &= ~mask;	/* get the bits not changing */
+	dest_byte |= src_byte;	/* add in the new bits */
+
+	/* put it all back */
+	memcpy(dest, &dest_byte, sizeof(dest_byte));
+}
+
+/**
+ * ice_write_word - write a word to a packed context structure
+ * @src_ctx:  the context structure to read from
+ * @dest_ctx: the context to be written to
+ * @ce_info:  a description of the struct to be filled
+ */
+static void ice_write_word(u8 *src_ctx, u8 *dest_ctx,
+			   const struct ice_ctx_ele *ce_info)
+{
+	u16 src_word, mask;
+	__le16 dest_word;
+	u8 *from, *dest;
+	u16 shift_width;
+
+	/* copy from the next struct field */
+	from = src_ctx + ce_info->offset;
+
+	/* prepare the bits and mask */
+	shift_width = ce_info->lsb % 8;
+	mask = BIT(ce_info->width) - 1;
+
+	/* don't swizzle the bits until after the mask because the mask bits
+	 * will be in a different bit position on big endian machines
+	 */
+	src_word = *(u16 *)from;
+	src_word &= mask;
+
+	/* shift to correct alignment */
+	mask <<= shift_width;
+	src_word <<= shift_width;
+
+	/* get the current bits from the target bit string */
+	dest = dest_ctx + (ce_info->lsb / 8);
+
+	memcpy(&dest_word, dest, sizeof(dest_word));
+
+	dest_word &= ~(cpu_to_le16(mask));	/* get the bits not changing */
+	dest_word |= cpu_to_le16(src_word);	/* add in the new bits */
+
+	/* put it all back */
+	memcpy(dest, &dest_word, sizeof(dest_word));
+}
+
+/**
+ * ice_write_dword - write a dword to a packed context structure
+ * @src_ctx:  the context structure to read from
+ * @dest_ctx: the context to be written to
+ * @ce_info:  a description of the struct to be filled
+ */
+static void ice_write_dword(u8 *src_ctx, u8 *dest_ctx,
+			    const struct ice_ctx_ele *ce_info)
+{
+	u32 src_dword, mask;
+	__le32 dest_dword;
+	u8 *from, *dest;
+	u16 shift_width;
+
+	/* copy from the next struct field */
+	from = src_ctx + ce_info->offset;
+
+	/* prepare the bits and mask */
+	shift_width = ce_info->lsb % 8;
+
+	/* if the field width is exactly 32 on an x86 machine, then the shift
+	 * operation will not work because the SHL instructions count is masked
+	 * to 5 bits so the shift will do nothing
+	 */
+	if (ce_info->width < 32)
+		mask = BIT(ce_info->width) - 1;
+	else
+		mask = (u32)~0;
+
+	/* don't swizzle the bits until after the mask because the mask bits
+	 * will be in a different bit position on big endian machines
+	 */
+	src_dword = *(u32 *)from;
+	src_dword &= mask;
+
+	/* shift to correct alignment */
+	mask <<= shift_width;
+	src_dword <<= shift_width;
+
+	/* get the current bits from the target bit string */
+	dest = dest_ctx + (ce_info->lsb / 8);
+
+	memcpy(&dest_dword, dest, sizeof(dest_dword));
+
+	dest_dword &= ~(cpu_to_le32(mask));	/* get the bits not changing */
+	dest_dword |= cpu_to_le32(src_dword);	/* add in the new bits */
+
+	/* put it all back */
+	memcpy(dest, &dest_dword, sizeof(dest_dword));
+}
+
+/**
+ * ice_write_qword - write a qword to a packed context structure
+ * @src_ctx:  the context structure to read from
+ * @dest_ctx: the context to be written to
+ * @ce_info:  a description of the struct to be filled
+ */
+static void ice_write_qword(u8 *src_ctx, u8 *dest_ctx,
+			    const struct ice_ctx_ele *ce_info)
+{
+	u64 src_qword, mask;
+	__le64 dest_qword;
+	u8 *from, *dest;
+	u16 shift_width;
+
+	/* copy from the next struct field */
+	from = src_ctx + ce_info->offset;
+
+	/* prepare the bits and mask */
+	shift_width = ce_info->lsb % 8;
+
+	/* if the field width is exactly 64 on an x86 machine, then the shift
+	 * operation will not work because the SHL instructions count is masked
+	 * to 6 bits so the shift will do nothing
+	 */
+	if (ce_info->width < 64)
+		mask = BIT_ULL(ce_info->width) - 1;
+	else
+		mask = (u64)~0;
+
+	/* don't swizzle the bits until after the mask because the mask bits
+	 * will be in a different bit position on big endian machines
+	 */
+	src_qword = *(u64 *)from;
+	src_qword &= mask;
+
+	/* shift to correct alignment */
+	mask <<= shift_width;
+	src_qword <<= shift_width;
+
+	/* get the current bits from the target bit string */
+	dest = dest_ctx + (ce_info->lsb / 8);
+
+	memcpy(&dest_qword, dest, sizeof(dest_qword));
+
+	dest_qword &= ~(cpu_to_le64(mask));	/* get the bits not changing */
+	dest_qword |= cpu_to_le64(src_qword);	/* add in the new bits */
+
+	/* put it all back */
+	memcpy(dest, &dest_qword, sizeof(dest_qword));
+}
+
+/**
+ * ice_set_ctx - set context bits in packed structure
+ * @src_ctx:  pointer to a generic non-packed context structure
+ * @dest_ctx: pointer to memory for the packed structure
+ * @ce_info:  a description of the structure to be transformed
+ */
+enum ice_status
+ice_set_ctx(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info)
+{
+	int f;
+
+	for (f = 0; ce_info[f].width; f++) {
+		/* We have to deal with each element of the FW response
+		 * using the correct size so that we are correct regardless
+		 * of the endianness of the machine.
+		 */
+		switch (ce_info[f].size_of) {
+		case sizeof(u8):
+			ice_write_byte(src_ctx, dest_ctx, &ce_info[f]);
+			break;
+		case sizeof(u16):
+			ice_write_word(src_ctx, dest_ctx, &ce_info[f]);
+			break;
+		case sizeof(u32):
+			ice_write_dword(src_ctx, dest_ctx, &ce_info[f]);
+			break;
+		case sizeof(u64):
+			ice_write_qword(src_ctx, dest_ctx, &ce_info[f]);
+			break;
+		default:
+			return ICE_ERR_INVAL_SIZE;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ena_vsi_txq
+ * @pi: port information structure
+ * @vsi_id: VSI id
+ * @tc: tc number
+ * @num_qgrps: Number of added queue groups
+ * @buf: list of queue groups to be added
+ * @buf_size: size of buffer for indirect command
+ * @cd: pointer to command details structure or NULL
+ *
+ * This function adds one lan q
+ */
+enum ice_status
+ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 num_qgrps,
+		struct ice_aqc_add_tx_qgrp *buf, u16 buf_size,
+		struct ice_sq_cd *cd)
+{
+	struct ice_aqc_txsched_elem_data node = { 0 };
+	struct ice_sched_node *parent;
+	enum ice_status status;
+	struct ice_hw *hw;
+
+	if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY)
+		return ICE_ERR_CFG;
+
+	if (num_qgrps > 1 || buf->num_txqs > 1)
+		return ICE_ERR_MAX_LIMIT;
+
+	hw = pi->hw;
+
+	mutex_lock(&pi->sched_lock);
+
+	/* find a parent node */
+	parent = ice_sched_get_free_qparent(pi, vsi_id, tc,
+					    ICE_SCHED_NODE_OWNER_LAN);
+	if (!parent) {
+		status = ICE_ERR_PARAM;
+		goto ena_txq_exit;
+	}
+	buf->parent_teid = parent->info.node_teid;
+	node.parent_teid = parent->info.node_teid;
+	/* Mark that the values in the "generic" section as valid. The default
+	 * value in the "generic" section is zero. This means that :
+	 * - Scheduling mode is Bytes Per Second (BPS), indicated by Bit 0.
+	 * - 0 priority among siblings, indicated by Bit 1-3.
+	 * - WFQ, indicated by Bit 4.
+	 * - 0 Adjustment value is used in PSM credit update flow, indicated by
+	 * Bit 5-6.
+	 * - Bit 7 is reserved.
+	 * Without setting the generic section as valid in valid_sections, the
+	 * Admin Q command will fail with error code ICE_AQ_RC_EINVAL.
+	 */
+	buf->txqs[0].info.valid_sections = ICE_AQC_ELEM_VALID_GENERIC;
+
+	/* add the lan q */
+	status = ice_aq_add_lan_txq(hw, num_qgrps, buf, buf_size, cd);
+	if (status)
+		goto ena_txq_exit;
+
+	node.node_teid = buf->txqs[0].q_teid;
+	node.data.elem_type = ICE_AQC_ELEM_TYPE_LEAF;
+
+	/* add a leaf node into schduler tree q layer */
+	status = ice_sched_add_node(pi, hw->num_tx_sched_layers - 1, &node);
+
+ena_txq_exit:
+	mutex_unlock(&pi->sched_lock);
+	return status;
+}
+
+/**
+ * ice_dis_vsi_txq
+ * @pi: port information structure
+ * @num_queues: number of queues
+ * @q_ids: pointer to the q_id array
+ * @q_teids: pointer to queue node teids
+ * @cd: pointer to command details structure or NULL
+ *
+ * This function removes queues and their corresponding nodes in SW DB
+ */
+enum ice_status
+ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
+		u32 *q_teids, struct ice_sq_cd *cd)
+{
+	enum ice_status status = ICE_ERR_DOES_NOT_EXIST;
+	struct ice_aqc_dis_txq_item qg_list;
+	u16 i;
+
+	if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY)
+		return ICE_ERR_CFG;
+
+	mutex_lock(&pi->sched_lock);
+
+	for (i = 0; i < num_queues; i++) {
+		struct ice_sched_node *node;
+
+		node = ice_sched_find_node_by_teid(pi->root, q_teids[i]);
+		if (!node)
+			continue;
+		qg_list.parent_teid = node->info.parent_teid;
+		qg_list.num_qs = 1;
+		qg_list.q_id[0] = cpu_to_le16(q_ids[i]);
+		status = ice_aq_dis_lan_txq(pi->hw, 1, &qg_list,
+					    sizeof(qg_list), cd);
+
+		if (status)
+			break;
+		ice_free_sched_node(pi, node);
+	}
+	mutex_unlock(&pi->sched_lock);
+	return status;
+}

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

@@ -30,9 +30,15 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		struct ice_sq_cd *cd);
 void ice_clear_pxe_mode(struct ice_hw *hw);
 enum ice_status ice_get_caps(struct ice_hw *hw);
+enum ice_status
+ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
+		  u32 rxq_index);
 bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq);
 enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading);
 void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode);
+extern const struct ice_ctx_ele ice_tlan_ctx_info[];
+enum ice_status
+ice_set_ctx(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info);
 enum ice_status
 ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc,
 		void *buf, u16 buf_size, struct ice_sq_cd *cd);
@@ -41,4 +47,11 @@ enum ice_status ice_clear_pf_cfg(struct ice_hw *hw);
 enum ice_status
 ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 		     struct ice_link_status *link, struct ice_sq_cd *cd);
+enum ice_status
+ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
+		u32 *q_teids, struct ice_sq_cd *cmd_details);
+enum ice_status
+ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 num_qgrps,
+		struct ice_aqc_add_tx_qgrp *buf, u16 buf_size,
+		struct ice_sq_cd *cd);
 #endif /* _ICE_COMMON_H_ */

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

@@ -6,6 +6,7 @@
 #ifndef _ICE_HW_AUTOGEN_H_
 #define _ICE_HW_AUTOGEN_H_
 
+#define QTX_COMM_DBELL(_DBQM)		(0x002C0000 + ((_DBQM) * 4))
 #define PF_FW_ARQBAH			0x00080180
 #define PF_FW_ARQBAL			0x00080080
 #define PF_FW_ARQH			0x00080380
@@ -40,6 +41,44 @@
 #define PF_FW_ATQLEN_ATQENABLE_S	31
 #define PF_FW_ATQLEN_ATQENABLE_M	BIT(PF_FW_ATQLEN_ATQENABLE_S)
 #define PF_FW_ATQT			0x00080400
+
+#define GLFLXP_RXDID_FLAGS(_i, _j)		(0x0045D000 + ((_i) * 4 + (_j) * 256))
+#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S	0
+#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M	ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S)
+#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S	8
+#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_M	ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S)
+#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_S	16
+#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_M	ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_S)
+#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_S	24
+#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_M	ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_S)
+#define GLFLXP_RXDID_FLX_WRD_0(_i)		(0x0045c800 + ((_i) * 4))
+#define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_S	0
+#define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_M	ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_S)
+#define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_S	30
+#define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_M	ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_S)
+#define GLFLXP_RXDID_FLX_WRD_1(_i)		(0x0045c900 + ((_i) * 4))
+#define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_S	0
+#define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_M	ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_S)
+#define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_S	30
+#define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_M	ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_S)
+#define GLFLXP_RXDID_FLX_WRD_2(_i)		(0x0045ca00 + ((_i) * 4))
+#define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_S	0
+#define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_M	ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_S)
+#define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_S	30
+#define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_M	ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_S)
+#define GLFLXP_RXDID_FLX_WRD_3(_i)		(0x0045cb00 + ((_i) * 4))
+#define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_S	0
+#define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_M	ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_S)
+#define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_S	30
+#define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_M	ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_S)
+
+#define QRXFLXP_CNTXT(_QRX)		(0x00480000 + ((_QRX) * 4))
+#define QRXFLXP_CNTXT_RXDID_IDX_S	0
+#define QRXFLXP_CNTXT_RXDID_IDX_M	ICE_M(0x3F, QRXFLXP_CNTXT_RXDID_IDX_S)
+#define QRXFLXP_CNTXT_RXDID_PRIO_S	8
+#define QRXFLXP_CNTXT_RXDID_PRIO_M	ICE_M(0x7, QRXFLXP_CNTXT_RXDID_PRIO_S)
+#define QRXFLXP_CNTXT_TS_S		11
+#define QRXFLXP_CNTXT_TS_M		BIT(QRXFLXP_CNTXT_TS_S)
 #define GLGEN_RSTAT			0x000B8188
 #define GLGEN_RSTAT_DEVSTATE_S		0
 #define GLGEN_RSTAT_DEVSTATE_M		ICE_M(0x3, GLGEN_RSTAT_DEVSTATE_S)
@@ -62,6 +101,8 @@
 #define GLINT_DYN_CTL_INTENA_M		BIT(GLINT_DYN_CTL_INTENA_S)
 #define GLINT_DYN_CTL_CLEARPBA_S	1
 #define GLINT_DYN_CTL_CLEARPBA_M	BIT(GLINT_DYN_CTL_CLEARPBA_S)
+#define GLINT_DYN_CTL_SWINT_TRIG_S	2
+#define GLINT_DYN_CTL_SWINT_TRIG_M	BIT(GLINT_DYN_CTL_SWINT_TRIG_S)
 #define GLINT_DYN_CTL_ITR_INDX_S	3
 #define GLINT_DYN_CTL_SW_ITR_INDX_S	25
 #define GLINT_DYN_CTL_SW_ITR_INDX_M	ICE_M(0x3, GLINT_DYN_CTL_SW_ITR_INDX_S)
@@ -106,7 +147,25 @@
 #define PFINT_OICR_CTL_CAUSE_ENA_S	30
 #define PFINT_OICR_CTL_CAUSE_ENA_M	BIT(PFINT_OICR_CTL_CAUSE_ENA_S)
 #define PFINT_OICR_ENA			0x0016C900
+#define QINT_RQCTL(_QRX)		(0x00150000 + ((_QRX) * 4))
+#define QINT_RQCTL_MSIX_INDX_S		0
+#define QINT_RQCTL_ITR_INDX_S		11
+#define QINT_RQCTL_CAUSE_ENA_S		30
+#define QINT_RQCTL_CAUSE_ENA_M		BIT(QINT_RQCTL_CAUSE_ENA_S)
+#define QINT_TQCTL(_DBQM)		(0x00140000 + ((_DBQM) * 4))
+#define QINT_TQCTL_MSIX_INDX_S		0
+#define QINT_TQCTL_ITR_INDX_S		11
+#define QINT_TQCTL_CAUSE_ENA_S		30
+#define QINT_TQCTL_CAUSE_ENA_M		BIT(QINT_TQCTL_CAUSE_ENA_S)
 #define GLLAN_RCTL_0			0x002941F8
+#define QRX_CONTEXT(_i, _QRX)		(0x00280000 + ((_i) * 8192 + (_QRX) * 4))
+#define QRX_CTRL(_QRX)			(0x00120000 + ((_QRX) * 4))
+#define QRX_CTRL_MAX_INDEX		2047
+#define QRX_CTRL_QENA_REQ_S		0
+#define QRX_CTRL_QENA_REQ_M		BIT(QRX_CTRL_QENA_REQ_S)
+#define QRX_CTRL_QENA_STAT_S		2
+#define QRX_CTRL_QENA_STAT_M		BIT(QRX_CTRL_QENA_STAT_S)
+#define QRX_TAIL(_QRX)			(0x00290000 + ((_QRX) * 4))
 #define GLNVM_FLA			0x000B6108
 #define GLNVM_FLA_LOCKED_S		6
 #define GLNVM_FLA_LOCKED_M		BIT(GLNVM_FLA_LOCKED_S)

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

@@ -0,0 +1,246 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018, Intel Corporation. */
+
+#ifndef _ICE_LAN_TX_RX_H_
+#define _ICE_LAN_TX_RX_H_
+
+union ice_32byte_rx_desc {
+	struct {
+		__le64  pkt_addr; /* Packet buffer address */
+		__le64  hdr_addr; /* Header buffer address */
+			/* bit 0 of hdr_addr is DD bit */
+		__le64  rsvd1;
+		__le64  rsvd2;
+	} read;
+	struct {
+		struct {
+			struct {
+				__le16 mirroring_status;
+				__le16 l2tag1;
+			} lo_dword;
+			union {
+				__le32 rss; /* RSS Hash */
+				__le32 fd_id; /* Flow Director filter id */
+			} hi_dword;
+		} qword0;
+		struct {
+			/* status/error/PTYPE/length */
+			__le64 status_error_len;
+		} qword1;
+		struct {
+			__le16 ext_status; /* extended status */
+			__le16 rsvd;
+			__le16 l2tag2_1;
+			__le16 l2tag2_2;
+		} qword2;
+		struct {
+			__le32 reserved;
+			__le32 fd_id;
+		} qword3;
+	} wb; /* writeback */
+};
+
+/* RX Flex Descriptor
+ * This descriptor is used instead of the legacy version descriptor when
+ * ice_rlan_ctx.adv_desc is set
+ */
+union ice_32b_rx_flex_desc {
+	struct {
+		__le64  pkt_addr; /* Packet buffer address */
+		__le64  hdr_addr; /* Header buffer address */
+				  /* bit 0 of hdr_addr is DD bit */
+		__le64  rsvd1;
+		__le64  rsvd2;
+	} read;
+	struct {
+		/* Qword 0 */
+		u8 rxdid; /* descriptor builder profile id */
+		u8 mir_id_umb_cast; /* mirror=[5:0], umb=[7:6] */
+		__le16 ptype_flex_flags0; /* ptype=[9:0], ff0=[15:10] */
+		__le16 pkt_len; /* [15:14] are reserved */
+		__le16 hdr_len_sph_flex_flags1; /* header=[10:0] */
+						/* sph=[11:11] */
+						/* ff1/ext=[15:12] */
+
+		/* Qword 1 */
+		__le16 status_error0;
+		__le16 l2tag1;
+		__le16 flex_meta0;
+		__le16 flex_meta1;
+
+		/* Qword 2 */
+		__le16 status_error1;
+		u8 flex_flags2;
+		u8 time_stamp_low;
+		__le16 l2tag2_1st;
+		__le16 l2tag2_2nd;
+
+		/* Qword 3 */
+		__le16 flex_meta2;
+		__le16 flex_meta3;
+		union {
+			struct {
+				__le16 flex_meta4;
+				__le16 flex_meta5;
+			} flex;
+			__le32 ts_high;
+		} flex_ts;
+	} wb; /* writeback */
+};
+
+/* Receive Flex Descriptor profile IDs: There are a total
+ * of 64 profiles where profile IDs 0/1 are for legacy; and
+ * profiles 2-63 are flex profiles that can be programmed
+ * with a specific metadata (profile 7 reserved for HW)
+ */
+enum ice_rxdid {
+	ICE_RXDID_START			= 0,
+	ICE_RXDID_LEGACY_0		= ICE_RXDID_START,
+	ICE_RXDID_LEGACY_1,
+	ICE_RXDID_FLX_START,
+	ICE_RXDID_FLEX_NIC		= ICE_RXDID_FLX_START,
+	ICE_RXDID_FLX_LAST		= 63,
+	ICE_RXDID_LAST			= ICE_RXDID_FLX_LAST
+};
+
+/* Receive Flex Descriptor Rx opcode values */
+#define ICE_RX_OPC_MDID		0x01
+
+/* Receive Descriptor MDID values */
+#define ICE_RX_MDID_FLOW_ID_LOWER	5
+#define ICE_RX_MDID_FLOW_ID_HIGH	6
+#define ICE_RX_MDID_HASH_LOW		56
+#define ICE_RX_MDID_HASH_HIGH		57
+
+/* Rx Flag64 packet flag bits */
+enum ice_rx_flg64_bits {
+	ICE_RXFLG_PKT_DSI	= 0,
+	ICE_RXFLG_EVLAN_x8100	= 15,
+	ICE_RXFLG_EVLAN_x9100,
+	ICE_RXFLG_VLAN_x8100,
+	ICE_RXFLG_TNL_MAC	= 22,
+	ICE_RXFLG_TNL_VLAN,
+	ICE_RXFLG_PKT_FRG,
+	ICE_RXFLG_FIN		= 32,
+	ICE_RXFLG_SYN,
+	ICE_RXFLG_RST,
+	ICE_RXFLG_TNL0		= 38,
+	ICE_RXFLG_TNL1,
+	ICE_RXFLG_TNL2,
+	ICE_RXFLG_UDP_GRE,
+	ICE_RXFLG_RSVD		= 63
+};
+
+#define ICE_RXQ_CTX_SIZE_DWORDS		8
+#define ICE_RXQ_CTX_SZ			(ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32))
+
+/* RLAN Rx queue context data
+ *
+ * The sizes of the variables may be larger than needed due to crossing byte
+ * boundaries. If we do not have the width of the variable set to the correct
+ * size then we could end up shifting bits off the top of the variable when the
+ * variable is at the top of a byte and crosses over into the next byte.
+ */
+struct ice_rlan_ctx {
+	u16 head;
+	u16 cpuid; /* bigger than needed, see above for reason */
+	u64 base;
+	u16 qlen;
+#define ICE_RLAN_CTX_DBUF_S 7
+	u16 dbuf; /* bigger than needed, see above for reason */
+#define ICE_RLAN_CTX_HBUF_S 6
+	u16 hbuf; /* bigger than needed, see above for reason */
+	u8  dtype;
+	u8  dsize;
+	u8  crcstrip;
+	u8  l2tsel;
+	u8  hsplit_0;
+	u8  hsplit_1;
+	u8  showiv;
+	u32 rxmax; /* bigger than needed, see above for reason */
+	u8  tphrdesc_ena;
+	u8  tphwdesc_ena;
+	u8  tphdata_ena;
+	u8  tphhead_ena;
+	u16 lrxqthresh; /* bigger than needed, see above for reason */
+};
+
+struct ice_ctx_ele {
+	u16 offset;
+	u16 size_of;
+	u16 width;
+	u16 lsb;
+};
+
+#define ICE_CTX_STORE(_struct, _ele, _width, _lsb) {	\
+	.offset = offsetof(struct _struct, _ele),	\
+	.size_of = FIELD_SIZEOF(struct _struct, _ele),	\
+	.width = _width,				\
+	.lsb = _lsb,					\
+}
+
+/* for hsplit_0 field of Rx RLAN context */
+enum ice_rlan_ctx_rx_hsplit_0 {
+	ICE_RLAN_RX_HSPLIT_0_NO_SPLIT		= 0,
+	ICE_RLAN_RX_HSPLIT_0_SPLIT_L2		= 1,
+	ICE_RLAN_RX_HSPLIT_0_SPLIT_IP		= 2,
+	ICE_RLAN_RX_HSPLIT_0_SPLIT_TCP_UDP	= 4,
+	ICE_RLAN_RX_HSPLIT_0_SPLIT_SCTP		= 8,
+};
+
+/* for hsplit_1 field of Rx RLAN context */
+enum ice_rlan_ctx_rx_hsplit_1 {
+	ICE_RLAN_RX_HSPLIT_1_NO_SPLIT		= 0,
+	ICE_RLAN_RX_HSPLIT_1_SPLIT_L2		= 1,
+	ICE_RLAN_RX_HSPLIT_1_SPLIT_ALWAYS	= 2,
+};
+
+/* TX Descriptor */
+struct ice_tx_desc {
+	__le64 buf_addr; /* Address of descriptor's data buf */
+	__le64 cmd_type_offset_bsz;
+};
+
+#define ICE_LAN_TXQ_MAX_QGRPS	127
+#define ICE_LAN_TXQ_MAX_QDIS	1023
+
+/* Tx queue context data
+ *
+ * The sizes of the variables may be larger than needed due to crossing byte
+ * boundaries. If we do not have the width of the variable set to the correct
+ * size then we could end up shifting bits off the top of the variable when the
+ * variable is at the top of a byte and crosses over into the next byte.
+ */
+struct ice_tlan_ctx {
+#define ICE_TLAN_CTX_BASE_S	7
+	u64 base;		/* base is defined in 128-byte units */
+	u8  port_num;
+	u16 cgd_num;		/* bigger than needed, see above for reason */
+	u8  pf_num;
+	u16 vmvf_num;
+	u8  vmvf_type;
+#define ICE_TLAN_CTX_VMVF_TYPE_VMQ	1
+#define ICE_TLAN_CTX_VMVF_TYPE_PF	2
+	u16 src_vsi;
+	u8  tsyn_ena;
+	u8  alt_vlan;
+	u16 cpuid;		/* bigger than needed, see above for reason */
+	u8  wb_mode;
+	u8  tphrd_desc;
+	u8  tphrd;
+	u8  tphwr_desc;
+	u16 cmpq_id;
+	u16 qnum_in_func;
+	u8  itr_notification_mode;
+	u8  adjust_prof_id;
+	u32 qlen;		/* bigger than needed, see above for reason */
+	u8  quanta_prof_idx;
+	u8  tso_ena;
+	u16 tso_qnum;
+	u8  legacy_int;
+	u8  drop_ena;
+	u8  cache_prof_idx;
+	u8  pkt_shaper_prof_idx;
+	u8  int_q_state;	/* width not needed - internal do not write */
+};
+#endif /* _ICE_LAN_TX_RX_H_ */

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

@@ -27,6 +27,7 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)");
 #endif /* !CONFIG_DYNAMIC_DEBUG */
 
 static struct workqueue_struct *ice_wq;
+static const struct net_device_ops ice_netdev_ops;
 
 static int ice_vsi_release(struct ice_vsi *vsi);
 
@@ -213,6 +214,75 @@ static void ice_free_fltr_list(struct device *dev, struct list_head *h)
 	}
 }
 
+/**
+ * ice_print_link_msg - print link up or down message
+ * @vsi: the VSI whose link status is being queried
+ * @isup: boolean for if the link is now up or down
+ */
+static void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
+{
+	const char *speed;
+	const char *fc;
+
+	if (vsi->current_isup == isup)
+		return;
+
+	vsi->current_isup = isup;
+
+	if (!isup) {
+		netdev_info(vsi->netdev, "NIC Link is Down\n");
+		return;
+	}
+
+	switch (vsi->port_info->phy.link_info.link_speed) {
+	case ICE_AQ_LINK_SPEED_40GB:
+		speed = "40 G";
+		break;
+	case ICE_AQ_LINK_SPEED_25GB:
+		speed = "25 G";
+		break;
+	case ICE_AQ_LINK_SPEED_20GB:
+		speed = "20 G";
+		break;
+	case ICE_AQ_LINK_SPEED_10GB:
+		speed = "10 G";
+		break;
+	case ICE_AQ_LINK_SPEED_5GB:
+		speed = "5 G";
+		break;
+	case ICE_AQ_LINK_SPEED_2500MB:
+		speed = "2.5 G";
+		break;
+	case ICE_AQ_LINK_SPEED_1000MB:
+		speed = "1 G";
+		break;
+	case ICE_AQ_LINK_SPEED_100MB:
+		speed = "100 M";
+		break;
+	default:
+		speed = "Unknown";
+		break;
+	}
+
+	switch (vsi->port_info->fc.current_mode) {
+	case ICE_FC_FULL:
+		fc = "RX/TX";
+		break;
+	case ICE_FC_TX_PAUSE:
+		fc = "TX";
+		break;
+	case ICE_FC_RX_PAUSE:
+		fc = "RX";
+		break;
+	default:
+		fc = "Unknown";
+		break;
+	}
+
+	netdev_info(vsi->netdev, "NIC Link is up %sbps, Flow Control: %s\n",
+		    speed, fc);
+}
+
 /**
  * __ice_clean_ctrlq - helper function to clean controlq rings
  * @pf: ptr to struct ice_pf
@@ -408,6 +478,104 @@ static void ice_set_ctrlq_len(struct ice_hw *hw)
 	hw->adminq.sq_buf_size = ICE_AQ_MAX_BUF_LEN;
 }
 
+/**
+ * ice_irq_affinity_notify - Callback for affinity changes
+ * @notify: context as to what irq was changed
+ * @mask: the new affinity mask
+ *
+ * This is a callback function used by the irq_set_affinity_notifier function
+ * so that we may register to receive changes to the irq affinity masks.
+ */
+static void ice_irq_affinity_notify(struct irq_affinity_notify *notify,
+				    const cpumask_t *mask)
+{
+	struct ice_q_vector *q_vector =
+		container_of(notify, struct ice_q_vector, affinity_notify);
+
+	cpumask_copy(&q_vector->affinity_mask, mask);
+}
+
+/**
+ * ice_irq_affinity_release - Callback for affinity notifier release
+ * @ref: internal core kernel usage
+ *
+ * This is a callback function used by the irq_set_affinity_notifier function
+ * to inform the current notification subscriber that they will no longer
+ * receive notifications.
+ */
+static void ice_irq_affinity_release(struct kref __always_unused *ref) {}
+
+/**
+ * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI
+ * @vsi: the VSI being un-configured
+ */
+static void ice_vsi_dis_irq(struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+	int base = vsi->base_vector;
+	u32 val;
+	int i;
+
+	/* disable interrupt causation from each queue */
+	if (vsi->tx_rings) {
+		ice_for_each_txq(vsi, i) {
+			if (vsi->tx_rings[i]) {
+				u16 reg;
+
+				reg = vsi->tx_rings[i]->reg_idx;
+				val = rd32(hw, QINT_TQCTL(reg));
+				val &= ~QINT_TQCTL_CAUSE_ENA_M;
+				wr32(hw, QINT_TQCTL(reg), val);
+			}
+		}
+	}
+
+	if (vsi->rx_rings) {
+		ice_for_each_rxq(vsi, i) {
+			if (vsi->rx_rings[i]) {
+				u16 reg;
+
+				reg = vsi->rx_rings[i]->reg_idx;
+				val = rd32(hw, QINT_RQCTL(reg));
+				val &= ~QINT_RQCTL_CAUSE_ENA_M;
+				wr32(hw, QINT_RQCTL(reg), val);
+			}
+		}
+	}
+
+	/* disable each interrupt */
+	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
+		for (i = vsi->base_vector;
+		     i < (vsi->num_q_vectors + vsi->base_vector); i++)
+			wr32(hw, GLINT_DYN_CTL(i), 0);
+
+		ice_flush(hw);
+		for (i = 0; i < vsi->num_q_vectors; i++)
+			synchronize_irq(pf->msix_entries[i + base].vector);
+	}
+}
+
+/**
+ * ice_vsi_ena_irq - Enable IRQ for the given VSI
+ * @vsi: the VSI being configured
+ */
+static int ice_vsi_ena_irq(struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+
+	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
+		int i;
+
+		for (i = 0; i < vsi->num_q_vectors; i++)
+			ice_irq_dynamic_ena(hw, vsi, vsi->q_vectors[i]);
+	}
+
+	ice_flush(hw);
+	return 0;
+}
+
 /**
  * ice_vsi_delete - delete a VSI from the switch
  * @vsi: pointer to VSI being removed
@@ -428,6 +596,73 @@ static void ice_vsi_delete(struct ice_vsi *vsi)
 			vsi->vsi_num);
 }
 
+/**
+ * ice_vsi_req_irq_msix - get MSI-X vectors from the OS for the VSI
+ * @vsi: the VSI being configured
+ * @basename: name for the vector
+ */
+static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
+{
+	int q_vectors = vsi->num_q_vectors;
+	struct ice_pf *pf = vsi->back;
+	int base = vsi->base_vector;
+	int rx_int_idx = 0;
+	int tx_int_idx = 0;
+	int vector, err;
+	int irq_num;
+
+	for (vector = 0; vector < q_vectors; vector++) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[vector];
+
+		irq_num = pf->msix_entries[base + vector].vector;
+
+		if (q_vector->tx.ring && q_vector->rx.ring) {
+			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
+				 "%s-%s-%d", basename, "TxRx", rx_int_idx++);
+			tx_int_idx++;
+		} else if (q_vector->rx.ring) {
+			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
+				 "%s-%s-%d", basename, "rx", rx_int_idx++);
+		} else if (q_vector->tx.ring) {
+			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
+				 "%s-%s-%d", basename, "tx", tx_int_idx++);
+		} else {
+			/* skip this unused q_vector */
+			continue;
+		}
+		err = devm_request_irq(&pf->pdev->dev,
+				       pf->msix_entries[base + vector].vector,
+				       vsi->irq_handler, 0, q_vector->name,
+				       q_vector);
+		if (err) {
+			netdev_err(vsi->netdev,
+				   "MSIX request_irq failed, error: %d\n", err);
+			goto free_q_irqs;
+		}
+
+		/* register for affinity change notifications */
+		q_vector->affinity_notify.notify = ice_irq_affinity_notify;
+		q_vector->affinity_notify.release = ice_irq_affinity_release;
+		irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);
+
+		/* assign the mask for this irq */
+		irq_set_affinity_hint(irq_num, &q_vector->affinity_mask);
+	}
+
+	vsi->irqs_ready = true;
+	return 0;
+
+free_q_irqs:
+	while (vector) {
+		vector--;
+		irq_num = pf->msix_entries[base + vector].vector,
+		irq_set_affinity_notifier(irq_num, NULL);
+		irq_set_affinity_hint(irq_num, NULL);
+		devm_free_irq(&pf->pdev->dev, irq_num, &vsi->q_vectors[vector]);
+	}
+	return err;
+}
+
 /**
  * ice_vsi_setup_q_map - Setup a VSI queue map
  * @vsi: the VSI being configured
@@ -590,6 +825,38 @@ static int ice_vsi_add(struct ice_vsi *vsi)
 	return ret;
 }
 
+/**
+ * ice_vsi_release_msix - Clear the queue to Interrupt mapping in HW
+ * @vsi: the VSI being cleaned up
+ */
+static void ice_vsi_release_msix(struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	u16 vector = vsi->base_vector;
+	struct ice_hw *hw = &pf->hw;
+	u32 txq = 0;
+	u32 rxq = 0;
+	int i, q;
+
+	for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[i];
+
+		wr32(hw, GLINT_ITR(ICE_RX_ITR, vector), 0);
+		wr32(hw, GLINT_ITR(ICE_TX_ITR, vector), 0);
+		for (q = 0; q < q_vector->num_ring_tx; q++) {
+			wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0);
+			txq++;
+		}
+
+		for (q = 0; q < q_vector->num_ring_rx; q++) {
+			wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), 0);
+			rxq++;
+		}
+	}
+
+	ice_flush(hw);
+}
+
 /**
  * ice_vsi_clear_rings - Deallocates the Tx and Rx rings for VSI
  * @vsi: the VSI having rings deallocated
@@ -672,6 +939,118 @@ err_out:
 	return -ENOMEM;
 }
 
+/**
+ * ice_vsi_free_irq - Free the irq association with the OS
+ * @vsi: the VSI being configured
+ */
+static void ice_vsi_free_irq(struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	int base = vsi->base_vector;
+
+	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
+		int i;
+
+		if (!vsi->q_vectors || !vsi->irqs_ready)
+			return;
+
+		vsi->irqs_ready = false;
+		for (i = 0; i < vsi->num_q_vectors; i++) {
+			u16 vector = i + base;
+			int irq_num;
+
+			irq_num = pf->msix_entries[vector].vector;
+
+			/* free only the irqs that were actually requested */
+			if (!vsi->q_vectors[i] ||
+			    !(vsi->q_vectors[i]->num_ring_tx ||
+			      vsi->q_vectors[i]->num_ring_rx))
+				continue;
+
+			/* clear the affinity notifier in the IRQ descriptor */
+			irq_set_affinity_notifier(irq_num, NULL);
+
+			/* clear the affinity_mask in the IRQ descriptor */
+			irq_set_affinity_hint(irq_num, NULL);
+			synchronize_irq(irq_num);
+			devm_free_irq(&pf->pdev->dev, irq_num,
+				      vsi->q_vectors[i]);
+		}
+		ice_vsi_release_msix(vsi);
+	}
+}
+
+/**
+ * ice_vsi_cfg_msix - MSIX mode Interrupt Config in the HW
+ * @vsi: the VSI being configured
+ */
+static void ice_vsi_cfg_msix(struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	u16 vector = vsi->base_vector;
+	struct ice_hw *hw = &pf->hw;
+	u32 txq = 0, rxq = 0;
+	int i, q, itr;
+	u8 itr_gran;
+
+	for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[i];
+
+		itr_gran = hw->itr_gran_200;
+
+		if (q_vector->num_ring_rx) {
+			q_vector->rx.itr =
+				ITR_TO_REG(vsi->rx_rings[rxq]->rx_itr_setting,
+					   itr_gran);
+			q_vector->rx.latency_range = ICE_LOW_LATENCY;
+		}
+
+		if (q_vector->num_ring_tx) {
+			q_vector->tx.itr =
+				ITR_TO_REG(vsi->tx_rings[txq]->tx_itr_setting,
+					   itr_gran);
+			q_vector->tx.latency_range = ICE_LOW_LATENCY;
+		}
+		wr32(hw, GLINT_ITR(ICE_RX_ITR, vector), q_vector->rx.itr);
+		wr32(hw, GLINT_ITR(ICE_TX_ITR, vector), q_vector->tx.itr);
+
+		/* Both Transmit Queue Interrupt Cause Control register
+		 * and Receive Queue Interrupt Cause control register
+		 * expects MSIX_INDX field to be the vector index
+		 * within the function space and not the absolute
+		 * vector index across PF or across device.
+		 * For SR-IOV VF VSIs queue vector index always starts
+		 * with 1 since first vector index(0) is used for OICR
+		 * in VF space. Since VMDq and other PF VSIs are withtin
+		 * the PF function space, use the vector index thats
+		 * tracked for this PF.
+		 */
+		for (q = 0; q < q_vector->num_ring_tx; q++) {
+			u32 val;
+
+			itr = ICE_TX_ITR;
+			val = QINT_TQCTL_CAUSE_ENA_M |
+			      (itr << QINT_TQCTL_ITR_INDX_S)  |
+			      (vector << QINT_TQCTL_MSIX_INDX_S);
+			wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), val);
+			txq++;
+		}
+
+		for (q = 0; q < q_vector->num_ring_rx; q++) {
+			u32 val;
+
+			itr = ICE_RX_ITR;
+			val = QINT_RQCTL_CAUSE_ENA_M |
+			      (itr << QINT_RQCTL_ITR_INDX_S)  |
+			      (vector << QINT_RQCTL_MSIX_INDX_S);
+			wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), val);
+			rxq++;
+		}
+	}
+
+	ice_flush(hw);
+}
+
 /**
  * ice_ena_misc_vector - enable the non-queue interrupts
  * @pf: board private structure
@@ -752,7 +1131,7 @@ ena_intr:
 	wr32(hw, PFINT_OICR_ENA, ena_mask);
 	if (!test_bit(__ICE_DOWN, pf->state)) {
 		ice_service_task_schedule(pf);
-		ice_irq_dynamic_ena(hw);
+		ice_irq_dynamic_ena(hw, NULL, NULL);
 	}
 
 	return ret;
@@ -1017,7 +1396,7 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 	     ITR_TO_REG(ICE_ITR_8K, itr_gran));
 
 	ice_flush(hw);
-	ice_irq_dynamic_ena(hw);
+	ice_irq_dynamic_ena(hw, NULL, NULL);
 
 	return 0;
 }
@@ -1262,6 +1641,9 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
+	/* assign netdev_ops */
+	netdev->netdev_ops = &ice_netdev_ops;
+
 	/* setup watchdog timeout value to be 5 second */
 	netdev->watchdog_timeo = 5 * HZ;
 
@@ -2080,39 +2462,793 @@ static void __exit ice_module_exit(void)
 module_exit(ice_module_exit);
 
 /**
- * ice_vsi_release - Delete a VSI and free its resources
- * @vsi: the VSI being removed
+ * ice_setup_tx_ctx - setup a struct ice_tlan_ctx instance
+ * @ring: The Tx ring to configure
+ * @tlan_ctx: Pointer to the Tx LAN queue context structure to be initialized
+ * @pf_q: queue index in the PF space
  *
- * Returns 0 on success or < 0 on error
+ * Configure the Tx descriptor ring in TLAN context.
  */
-static int ice_vsi_release(struct ice_vsi *vsi)
+static void
+ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q)
 {
-	struct ice_pf *pf;
+	struct ice_vsi *vsi = ring->vsi;
+	struct ice_hw *hw = &vsi->back->hw;
 
-	if (!vsi->back)
-		return -ENODEV;
-	pf = vsi->back;
+	tlan_ctx->base = ring->dma >> ICE_TLAN_CTX_BASE_S;
 
-	if (vsi->netdev) {
-		unregister_netdev(vsi->netdev);
-		free_netdev(vsi->netdev);
-		vsi->netdev = NULL;
+	tlan_ctx->port_num = vsi->port_info->lport;
+
+	/* Transmit Queue Length */
+	tlan_ctx->qlen = ring->count;
+
+	/* PF number */
+	tlan_ctx->pf_num = hw->pf_id;
+
+	/* queue belongs to a specific VSI type
+	 * VF / VM index should be programmed per vmvf_type setting:
+	 * for vmvf_type = VF, it is VF number between 0-256
+	 * for vmvf_type = VM, it is VM number between 0-767
+	 * for PF or EMP this field should be set to zero
+	 */
+	switch (vsi->type) {
+	case ICE_VSI_PF:
+		tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF;
+		break;
+	default:
+		return;
 	}
 
-	/* reclaim interrupt vectors back to PF */
-	ice_free_res(vsi->back->irq_tracker, vsi->base_vector, vsi->idx);
-	pf->num_avail_msix += vsi->num_q_vectors;
+	/* make sure the context is associated with the right VSI */
+	tlan_ctx->src_vsi = vsi->vsi_num;
 
-	ice_remove_vsi_fltr(&pf->hw, vsi->vsi_num);
-	ice_vsi_delete(vsi);
-	ice_vsi_free_q_vectors(vsi);
-	ice_vsi_clear_rings(vsi);
+	tlan_ctx->tso_ena = ICE_TX_LEGACY;
+	tlan_ctx->tso_qnum = pf_q;
 
-	ice_vsi_put_qs(vsi);
-	pf->q_left_tx += vsi->alloc_txq;
-	pf->q_left_rx += vsi->alloc_rxq;
+	/* Legacy or Advanced Host Interface:
+	 * 0: Advanced Host Interface
+	 * 1: Legacy Host Interface
+	 */
+	tlan_ctx->legacy_int = ICE_TX_LEGACY;
+}
 
-	ice_vsi_clear(vsi);
+/**
+ * ice_vsi_cfg_txqs - Configure the VSI for Tx
+ * @vsi: the VSI being configured
+ *
+ * Return 0 on success and a negative value on error
+ * Configure the Tx VSI for operation.
+ */
+static int ice_vsi_cfg_txqs(struct ice_vsi *vsi)
+{
+	struct ice_aqc_add_tx_qgrp *qg_buf;
+	struct ice_aqc_add_txqs_perq *txq;
+	struct ice_pf *pf = vsi->back;
+	enum ice_status status;
+	u16 buf_len, i, pf_q;
+	int err = 0, tc = 0;
+	u8 num_q_grps;
+
+	buf_len = sizeof(struct ice_aqc_add_tx_qgrp);
+	qg_buf = devm_kzalloc(&pf->pdev->dev, buf_len, GFP_KERNEL);
+	if (!qg_buf)
+		return -ENOMEM;
+
+	if (vsi->num_txq > ICE_MAX_TXQ_PER_TXQG) {
+		err = -EINVAL;
+		goto err_cfg_txqs;
+	}
+	qg_buf->num_txqs = 1;
+	num_q_grps = 1;
+
+	/* set up and configure the tx queues */
+	ice_for_each_txq(vsi, i) {
+		struct ice_tlan_ctx tlan_ctx = { 0 };
+
+		pf_q = vsi->txq_map[i];
+		ice_setup_tx_ctx(vsi->tx_rings[i], &tlan_ctx, pf_q);
+		/* copy context contents into the qg_buf */
+		qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q);
+		ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx,
+			    ice_tlan_ctx_info);
+
+		/* init queue specific tail reg. It is referred as transmit
+		 * comm scheduler queue doorbell.
+		 */
+		vsi->tx_rings[i]->tail = pf->hw.hw_addr + QTX_COMM_DBELL(pf_q);
+		status = ice_ena_vsi_txq(vsi->port_info, vsi->vsi_num, tc,
+					 num_q_grps, qg_buf, buf_len, NULL);
+		if (status) {
+			dev_err(&vsi->back->pdev->dev,
+				"Failed to set LAN Tx queue context, error: %d\n",
+				status);
+			err = -ENODEV;
+			goto err_cfg_txqs;
+		}
+
+		/* Add Tx Queue TEID into the VSI tx ring from the response
+		 * This will complete configuring and enabling the queue.
+		 */
+		txq = &qg_buf->txqs[0];
+		if (pf_q == le16_to_cpu(txq->txq_id))
+			vsi->tx_rings[i]->txq_teid =
+				le32_to_cpu(txq->q_teid);
+	}
+err_cfg_txqs:
+	devm_kfree(&pf->pdev->dev, qg_buf);
+	return err;
+}
+
+/**
+ * ice_setup_rx_ctx - Configure a receive ring context
+ * @ring: The Rx ring to configure
+ *
+ * Configure the Rx descriptor ring in RLAN context.
+ */
+static int ice_setup_rx_ctx(struct ice_ring *ring)
+{
+	struct ice_vsi *vsi = ring->vsi;
+	struct ice_hw *hw = &vsi->back->hw;
+	u32 rxdid = ICE_RXDID_FLEX_NIC;
+	struct ice_rlan_ctx rlan_ctx;
+	u32 regval;
+	u16 pf_q;
+	int err;
+
+	/* what is RX queue number in global space of 2K rx queues */
+	pf_q = vsi->rxq_map[ring->q_index];
+
+	/* clear the context structure first */
+	memset(&rlan_ctx, 0, sizeof(rlan_ctx));
+
+	rlan_ctx.base = ring->dma >> 7;
+
+	rlan_ctx.qlen = ring->count;
+
+	/* Receive Packet Data Buffer Size.
+	 * The Packet Data Buffer Size is defined in 128 byte units.
+	 */
+	rlan_ctx.dbuf = vsi->rx_buf_len >> ICE_RLAN_CTX_DBUF_S;
+
+	/* use 32 byte descriptors */
+	rlan_ctx.dsize = 1;
+
+	/* Strip the Ethernet CRC bytes before the packet is posted to host
+	 * memory.
+	 */
+	rlan_ctx.crcstrip = 1;
+
+	/* L2TSEL flag defines the reported L2 Tags in the receive descriptor */
+	rlan_ctx.l2tsel = 1;
+
+	rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT;
+	rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT;
+	rlan_ctx.hsplit_1 = ICE_RLAN_RX_HSPLIT_1_NO_SPLIT;
+
+	/* This controls whether VLAN is stripped from inner headers
+	 * The VLAN in the inner L2 header is stripped to the receive
+	 * descriptor if enabled by this flag.
+	 */
+	rlan_ctx.showiv = 0;
+
+	/* Max packet size for this queue - must not be set to a larger value
+	 * than 5 x DBUF
+	 */
+	rlan_ctx.rxmax = min_t(u16, vsi->max_frame,
+			       ICE_MAX_CHAINED_RX_BUFS * vsi->rx_buf_len);
+
+	/* Rx queue threshold in units of 64 */
+	rlan_ctx.lrxqthresh = 1;
+
+	 /* Enable Flexible Descriptors in the queue context which
+	  * allows this driver to select a specific receive descriptor format
+	  */
+	regval = rd32(hw, QRXFLXP_CNTXT(pf_q));
+	regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) &
+		QRXFLXP_CNTXT_RXDID_IDX_M;
+
+	/* increasing context priority to pick up profile id;
+	 * default is 0x01; setting to 0x03 to ensure profile
+	 * is programming if prev context is of same priority
+	 */
+	regval |= (0x03 << QRXFLXP_CNTXT_RXDID_PRIO_S) &
+		QRXFLXP_CNTXT_RXDID_PRIO_M;
+
+	wr32(hw, QRXFLXP_CNTXT(pf_q), regval);
+
+	/* Absolute queue number out of 2K needs to be passed */
+	err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q);
+	if (err) {
+		dev_err(&vsi->back->pdev->dev,
+			"Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n",
+			pf_q, err);
+		return -EIO;
+	}
+
+	/* init queue specific tail register */
+	ring->tail = hw->hw_addr + QRX_TAIL(pf_q);
+	writel(0, ring->tail);
+	ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring));
 
 	return 0;
 }
+
+/**
+ * ice_vsi_cfg_rxqs - Configure the VSI for Rx
+ * @vsi: the VSI being configured
+ *
+ * Return 0 on success and a negative value on error
+ * Configure the Rx VSI for operation.
+ */
+static int ice_vsi_cfg_rxqs(struct ice_vsi *vsi)
+{
+	int err = 0;
+	u16 i;
+
+	if (vsi->netdev && vsi->netdev->mtu > ETH_DATA_LEN)
+		vsi->max_frame = vsi->netdev->mtu +
+			ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+	else
+		vsi->max_frame = ICE_RXBUF_2048;
+
+	vsi->rx_buf_len = ICE_RXBUF_2048;
+	/* set up individual rings */
+	for (i = 0; i < vsi->num_rxq && !err; i++)
+		err = ice_setup_rx_ctx(vsi->rx_rings[i]);
+
+	if (err) {
+		dev_err(&vsi->back->pdev->dev, "ice_setup_rx_ctx failed\n");
+		return -EIO;
+	}
+	return err;
+}
+
+/**
+ * ice_vsi_cfg - Setup the VSI
+ * @vsi: the VSI being configured
+ *
+ * Return 0 on success and negative value on error
+ */
+static int ice_vsi_cfg(struct ice_vsi *vsi)
+{
+	int err;
+
+	err = ice_vsi_cfg_txqs(vsi);
+	if (!err)
+		err = ice_vsi_cfg_rxqs(vsi);
+
+	return err;
+}
+
+/**
+ * ice_vsi_stop_tx_rings - Disable Tx rings
+ * @vsi: the VSI being configured
+ */
+static int ice_vsi_stop_tx_rings(struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+	enum ice_status status;
+	u32 *q_teids, val;
+	u16 *q_ids, i;
+	int err = 0;
+
+	if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS)
+		return -EINVAL;
+
+	q_teids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_teids),
+			       GFP_KERNEL);
+	if (!q_teids)
+		return -ENOMEM;
+
+	q_ids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_ids),
+			     GFP_KERNEL);
+	if (!q_ids) {
+		err = -ENOMEM;
+		goto err_alloc_q_ids;
+	}
+
+	/* set up the tx queue list to be disabled */
+	ice_for_each_txq(vsi, i) {
+		u16 v_idx;
+
+		if (!vsi->tx_rings || !vsi->tx_rings[i]) {
+			err = -EINVAL;
+			goto err_out;
+		}
+
+		q_ids[i] = vsi->txq_map[i];
+		q_teids[i] = vsi->tx_rings[i]->txq_teid;
+
+		/* clear cause_ena bit for disabled queues */
+		val = rd32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx));
+		val &= ~QINT_TQCTL_CAUSE_ENA_M;
+		wr32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx), val);
+
+		/* software is expected to wait for 100 ns */
+		ndelay(100);
+
+		/* trigger a software interrupt for the vector associated to
+		 * the queue to schedule napi handler
+		 */
+		v_idx = vsi->tx_rings[i]->q_vector->v_idx;
+		wr32(hw, GLINT_DYN_CTL(vsi->base_vector + v_idx),
+		     GLINT_DYN_CTL_SWINT_TRIG_M | GLINT_DYN_CTL_INTENA_MSK_M);
+	}
+	status = ice_dis_vsi_txq(vsi->port_info, vsi->num_txq, q_ids, q_teids,
+				 NULL);
+	if (status) {
+		dev_err(&pf->pdev->dev,
+			"Failed to disable LAN Tx queues, error: %d\n",
+			status);
+		err = -ENODEV;
+	}
+
+err_out:
+	devm_kfree(&pf->pdev->dev, q_ids);
+
+err_alloc_q_ids:
+	devm_kfree(&pf->pdev->dev, q_teids);
+
+	return err;
+}
+
+/**
+ * ice_pf_rxq_wait - Wait for a PF's Rx queue to be enabled or disabled
+ * @pf: the PF being configured
+ * @pf_q: the PF queue
+ * @ena: enable or disable state of the queue
+ *
+ * This routine will wait for the given Rx queue of the PF to reach the
+ * enabled or disabled state.
+ * Returns -ETIMEDOUT in case of failing to reach the requested state after
+ * multiple retries; else will return 0 in case of success.
+ */
+static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena)
+{
+	int i;
+
+	for (i = 0; i < ICE_Q_WAIT_RETRY_LIMIT; i++) {
+		u32 rx_reg = rd32(&pf->hw, QRX_CTRL(pf_q));
+
+		if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M))
+			break;
+
+		usleep_range(10, 20);
+	}
+	if (i >= ICE_Q_WAIT_RETRY_LIMIT)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+/**
+ * ice_vsi_ctrl_rx_rings - Start or stop a VSI's rx rings
+ * @vsi: the VSI being configured
+ * @ena: start or stop the rx rings
+ */
+static int ice_vsi_ctrl_rx_rings(struct ice_vsi *vsi, bool ena)
+{
+	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+	int i, j, ret = 0;
+
+	for (i = 0; i < vsi->num_rxq; i++) {
+		int pf_q = vsi->rxq_map[i];
+		u32 rx_reg;
+
+		for (j = 0; j < ICE_Q_WAIT_MAX_RETRY; j++) {
+			rx_reg = rd32(hw, QRX_CTRL(pf_q));
+			if (((rx_reg >> QRX_CTRL_QENA_REQ_S) & 1) ==
+			    ((rx_reg >> QRX_CTRL_QENA_STAT_S) & 1))
+				break;
+			usleep_range(1000, 2000);
+		}
+
+		/* Skip if the queue is already in the requested state */
+		if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M))
+			continue;
+
+		/* turn on/off the queue */
+		if (ena)
+			rx_reg |= QRX_CTRL_QENA_REQ_M;
+		else
+			rx_reg &= ~QRX_CTRL_QENA_REQ_M;
+		wr32(hw, QRX_CTRL(pf_q), rx_reg);
+
+		/* wait for the change to finish */
+		ret = ice_pf_rxq_wait(pf, pf_q, ena);
+		if (ret) {
+			dev_err(&pf->pdev->dev,
+				"VSI idx %d Rx ring %d %sable timeout\n",
+				vsi->idx, pf_q, (ena ? "en" : "dis"));
+			break;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * ice_vsi_start_rx_rings - start VSI's rx rings
+ * @vsi: the VSI whose rings are to be started
+ *
+ * Returns 0 on success and a negative value on error
+ */
+static int ice_vsi_start_rx_rings(struct ice_vsi *vsi)
+{
+	return ice_vsi_ctrl_rx_rings(vsi, true);
+}
+
+/**
+ * ice_vsi_stop_rx_rings - stop VSI's rx rings
+ * @vsi: the VSI
+ *
+ * Returns 0 on success and a negative value on error
+ */
+static int ice_vsi_stop_rx_rings(struct ice_vsi *vsi)
+{
+	return ice_vsi_ctrl_rx_rings(vsi, false);
+}
+
+/**
+ * ice_vsi_stop_tx_rx_rings - stop VSI's tx and rx rings
+ * @vsi: the VSI
+ * Returns 0 on success and a negative value on error
+ */
+static int ice_vsi_stop_tx_rx_rings(struct ice_vsi *vsi)
+{
+	int err_tx, err_rx;
+
+	err_tx = ice_vsi_stop_tx_rings(vsi);
+	if (err_tx)
+		dev_dbg(&vsi->back->pdev->dev, "Failed to disable Tx rings\n");
+
+	err_rx = ice_vsi_stop_rx_rings(vsi);
+	if (err_rx)
+		dev_dbg(&vsi->back->pdev->dev, "Failed to disable Rx rings\n");
+
+	if (err_tx || err_rx)
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * ice_up_complete - Finish the last steps of bringing up a connection
+ * @vsi: The VSI being configured
+ *
+ * Return 0 on success and negative value on error
+ */
+static int ice_up_complete(struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	int err;
+
+	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
+		ice_vsi_cfg_msix(vsi);
+	else
+		return -ENOTSUPP;
+
+	/* Enable only Rx rings, Tx rings were enabled by the FW when the
+	 * Tx queue group list was configured and the context bits were
+	 * programmed using ice_vsi_cfg_txqs
+	 */
+	err = ice_vsi_start_rx_rings(vsi);
+	if (err)
+		return err;
+
+	clear_bit(__ICE_DOWN, vsi->state);
+	ice_vsi_ena_irq(vsi);
+
+	if (vsi->port_info &&
+	    (vsi->port_info->phy.link_info.link_info & ICE_AQ_LINK_UP) &&
+	    vsi->netdev) {
+		ice_print_link_msg(vsi, true);
+		netif_tx_start_all_queues(vsi->netdev);
+		netif_carrier_on(vsi->netdev);
+	}
+
+	ice_service_task_schedule(pf);
+
+	return err;
+}
+
+/**
+ * ice_down - Shutdown the connection
+ * @vsi: The VSI being stopped
+ */
+static int ice_down(struct ice_vsi *vsi)
+{
+	int i, err;
+
+	/* Caller of this function is expected to set the
+	 * vsi->state __ICE_DOWN bit
+	 */
+	if (vsi->netdev) {
+		netif_carrier_off(vsi->netdev);
+		netif_tx_disable(vsi->netdev);
+	}
+
+	ice_vsi_dis_irq(vsi);
+	err = ice_vsi_stop_tx_rx_rings(vsi);
+
+	ice_for_each_txq(vsi, i)
+		ice_clean_tx_ring(vsi->tx_rings[i]);
+
+	ice_for_each_rxq(vsi, i)
+		ice_clean_rx_ring(vsi->rx_rings[i]);
+
+	if (err)
+		netdev_err(vsi->netdev, "Failed to close VSI 0x%04X on switch 0x%04X\n",
+			   vsi->vsi_num, vsi->vsw->sw_id);
+	return err;
+}
+
+/**
+ * ice_vsi_setup_tx_rings - Allocate VSI Tx queue resources
+ * @vsi: VSI having resources allocated
+ *
+ * Return 0 on success, negative on failure
+ */
+static int ice_vsi_setup_tx_rings(struct ice_vsi *vsi)
+{
+	int i, err;
+
+	if (!vsi->num_txq) {
+		dev_err(&vsi->back->pdev->dev, "VSI %d has 0 Tx queues\n",
+			vsi->vsi_num);
+		return -EINVAL;
+	}
+
+	ice_for_each_txq(vsi, i) {
+		err = ice_setup_tx_ring(vsi->tx_rings[i]);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+/**
+ * ice_vsi_setup_rx_rings - Allocate VSI Rx queue resources
+ * @vsi: VSI having resources allocated
+ *
+ * Return 0 on success, negative on failure
+ */
+static int ice_vsi_setup_rx_rings(struct ice_vsi *vsi)
+{
+	int i, err;
+
+	if (!vsi->num_rxq) {
+		dev_err(&vsi->back->pdev->dev, "VSI %d has 0 Rx queues\n",
+			vsi->vsi_num);
+		return -EINVAL;
+	}
+
+	ice_for_each_rxq(vsi, i) {
+		err = ice_setup_rx_ring(vsi->rx_rings[i]);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+/**
+ * ice_vsi_req_irq - Request IRQ from the OS
+ * @vsi: The VSI IRQ is being requested for
+ * @basename: name for the vector
+ *
+ * Return 0 on success and a negative value on error
+ */
+static int ice_vsi_req_irq(struct ice_vsi *vsi, char *basename)
+{
+	struct ice_pf *pf = vsi->back;
+	int err = -EINVAL;
+
+	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
+		err = ice_vsi_req_irq_msix(vsi, basename);
+
+	return err;
+}
+
+/**
+ * ice_vsi_free_tx_rings - Free Tx resources for VSI queues
+ * @vsi: the VSI having resources freed
+ */
+static void ice_vsi_free_tx_rings(struct ice_vsi *vsi)
+{
+	int i;
+
+	if (!vsi->tx_rings)
+		return;
+
+	ice_for_each_txq(vsi, i)
+		if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc)
+			ice_free_tx_ring(vsi->tx_rings[i]);
+}
+
+/**
+ * ice_vsi_free_rx_rings - Free Rx resources for VSI queues
+ * @vsi: the VSI having resources freed
+ */
+static void ice_vsi_free_rx_rings(struct ice_vsi *vsi)
+{
+	int i;
+
+	if (!vsi->rx_rings)
+		return;
+
+	ice_for_each_rxq(vsi, i)
+		if (vsi->rx_rings[i] && vsi->rx_rings[i]->desc)
+			ice_free_rx_ring(vsi->rx_rings[i]);
+}
+
+/**
+ * ice_vsi_open - Called when a network interface is made active
+ * @vsi: the VSI to open
+ *
+ * Initialization of the VSI
+ *
+ * Returns 0 on success, negative value on error
+ */
+static int ice_vsi_open(struct ice_vsi *vsi)
+{
+	char int_name[ICE_INT_NAME_STR_LEN];
+	struct ice_pf *pf = vsi->back;
+	int err;
+
+	/* allocate descriptors */
+	err = ice_vsi_setup_tx_rings(vsi);
+	if (err)
+		goto err_setup_tx;
+
+	err = ice_vsi_setup_rx_rings(vsi);
+	if (err)
+		goto err_setup_rx;
+
+	err = ice_vsi_cfg(vsi);
+	if (err)
+		goto err_setup_rx;
+
+	snprintf(int_name, sizeof(int_name) - 1, "%s-%s",
+		 dev_driver_string(&pf->pdev->dev), vsi->netdev->name);
+	err = ice_vsi_req_irq(vsi, int_name);
+	if (err)
+		goto err_setup_rx;
+
+	/* Notify the stack of the actual queue counts. */
+	err = netif_set_real_num_tx_queues(vsi->netdev, vsi->num_txq);
+	if (err)
+		goto err_set_qs;
+
+	err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_rxq);
+	if (err)
+		goto err_set_qs;
+
+	err = ice_up_complete(vsi);
+	if (err)
+		goto err_up_complete;
+
+	return 0;
+
+err_up_complete:
+	ice_down(vsi);
+err_set_qs:
+	ice_vsi_free_irq(vsi);
+err_setup_rx:
+	ice_vsi_free_rx_rings(vsi);
+err_setup_tx:
+	ice_vsi_free_tx_rings(vsi);
+
+	return err;
+}
+
+/**
+ * ice_vsi_close - Shut down a VSI
+ * @vsi: the VSI being shut down
+ */
+static void ice_vsi_close(struct ice_vsi *vsi)
+{
+	if (!test_and_set_bit(__ICE_DOWN, vsi->state))
+		ice_down(vsi);
+
+	ice_vsi_free_irq(vsi);
+	ice_vsi_free_tx_rings(vsi);
+	ice_vsi_free_rx_rings(vsi);
+}
+
+/**
+ * ice_vsi_release - Delete a VSI and free its resources
+ * @vsi: the VSI being removed
+ *
+ * Returns 0 on success or < 0 on error
+ */
+static int ice_vsi_release(struct ice_vsi *vsi)
+{
+	struct ice_pf *pf;
+
+	if (!vsi->back)
+		return -ENODEV;
+	pf = vsi->back;
+
+	if (vsi->netdev) {
+		unregister_netdev(vsi->netdev);
+		free_netdev(vsi->netdev);
+		vsi->netdev = NULL;
+	}
+
+	ice_vsi_dis_irq(vsi);
+	ice_vsi_close(vsi);
+
+	/* reclaim interrupt vectors back to PF */
+	ice_free_res(vsi->back->irq_tracker, vsi->base_vector, vsi->idx);
+	pf->num_avail_msix += vsi->num_q_vectors;
+
+	ice_remove_vsi_fltr(&pf->hw, vsi->vsi_num);
+	ice_vsi_delete(vsi);
+	ice_vsi_free_q_vectors(vsi);
+	ice_vsi_clear_rings(vsi);
+
+	ice_vsi_put_qs(vsi);
+	pf->q_left_tx += vsi->alloc_txq;
+	pf->q_left_rx += vsi->alloc_rxq;
+
+	ice_vsi_clear(vsi);
+
+	return 0;
+}
+
+/**
+ * ice_open - Called when a network interface becomes active
+ * @netdev: network interface device structure
+ *
+ * The open entry point is called when a network interface is made
+ * active by the system (IFF_UP).  At this point all resources needed
+ * for transmit and receive operations are allocated, the interrupt
+ * handler is registered with the OS, the netdev watchdog is enabled,
+ * and the stack is notified that the interface is ready.
+ *
+ * Returns 0 on success, negative value on failure
+ */
+static int ice_open(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+	int err;
+
+	netif_carrier_off(netdev);
+
+	err = ice_vsi_open(vsi);
+
+	if (err)
+		netdev_err(netdev, "Failed to open VSI 0x%04X on switch 0x%04X\n",
+			   vsi->vsi_num, vsi->vsw->sw_id);
+	return err;
+}
+
+/**
+ * ice_stop - Disables a network interface
+ * @netdev: network interface device structure
+ *
+ * The stop entry point is called when an interface is de-activated by the OS,
+ * and the netdevice enters the DOWN state.  The hardware is still under the
+ * driver's control, but the netdev interface is disabled.
+ *
+ * Returns success only - not allowed to fail
+ */
+static int ice_stop(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+
+	ice_vsi_close(vsi);
+
+	return 0;
+}
+
+static const struct net_device_ops ice_netdev_ops = {
+	.ndo_open = ice_open,
+	.ndo_stop = ice_stop,
+};

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

@@ -462,6 +462,18 @@ void ice_sched_cleanup_all(struct ice_hw *hw)
 	hw->max_cgds = 0;
 }
 
+/**
+ * ice_sched_get_qgrp_layer - get the current queue group layer number
+ * @hw: pointer to the hw struct
+ *
+ * This function returns the current queue group layer number
+ */
+static u8 ice_sched_get_qgrp_layer(struct ice_hw *hw)
+{
+	/* It's always total layers - 1, the array is 0 relative so -2 */
+	return hw->num_tx_sched_layers - ICE_QGRP_LAYER_OFFSET;
+}
+
 /**
  * ice_rm_dflt_leaf_node - remove the default leaf node in the tree
  * @pi: port information structure
@@ -666,3 +678,96 @@ sched_query_out:
 	devm_kfree(ice_hw_to_dev(hw), buf);
 	return status;
 }
+
+/**
+ * ice_sched_get_vsi_info_entry - Get the vsi entry list for given vsi_id
+ * @pi: port information structure
+ * @vsi_id: vsi id
+ *
+ * This function retrieves the vsi list for the given vsi id
+ */
+static struct ice_sched_vsi_info *
+ice_sched_get_vsi_info_entry(struct ice_port_info *pi, u16 vsi_id)
+{
+	struct ice_sched_vsi_info *list_elem;
+
+	if (!pi)
+		return NULL;
+
+	list_for_each_entry(list_elem, &pi->vsi_info_list, list_entry)
+		if (list_elem->vsi_id == vsi_id)
+			return list_elem;
+	return NULL;
+}
+
+/**
+ * ice_sched_find_node_in_subtree - Find node in part of base node subtree
+ * @hw: pointer to the hw struct
+ * @base: pointer to the base node
+ * @node: pointer to the node to search
+ *
+ * This function checks whether a given node is part of the base node
+ * subtree or not
+ */
+static bool
+ice_sched_find_node_in_subtree(struct ice_hw *hw, struct ice_sched_node *base,
+			       struct ice_sched_node *node)
+{
+	u8 i;
+
+	for (i = 0; i < base->num_children; i++) {
+		struct ice_sched_node *child = base->children[i];
+
+		if (node == child)
+			return true;
+		if (child->tx_sched_layer > node->tx_sched_layer)
+			return false;
+		/* this recursion is intentional, and wouldn't
+		 * go more than 8 calls
+		 */
+		if (ice_sched_find_node_in_subtree(hw, child, node))
+			return true;
+	}
+	return false;
+}
+
+/**
+ * ice_sched_get_free_qparent - Get a free lan or rdma q group node
+ * @pi: port information structure
+ * @vsi_id: vsi id
+ * @tc: branch number
+ * @owner: lan or rdma
+ *
+ * This function retrieves a free lan or rdma q group node
+ */
+struct ice_sched_node *
+ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_id, u8 tc,
+			   u8 owner)
+{
+	struct ice_sched_node *vsi_node, *qgrp_node = NULL;
+	struct ice_sched_vsi_info *list_elem;
+	u16 max_children;
+	u8 qgrp_layer;
+
+	qgrp_layer = ice_sched_get_qgrp_layer(pi->hw);
+	max_children = le16_to_cpu(pi->hw->layer_info[qgrp_layer].max_children);
+	list_elem = ice_sched_get_vsi_info_entry(pi, vsi_id);
+	if (!list_elem)
+		goto lan_q_exit;
+	vsi_node = list_elem->vsi_node[tc];
+	/* validate invalid VSI id */
+	if (!vsi_node)
+		goto lan_q_exit;
+	/* get the first q group node from VSI sub-tree */
+	qgrp_node = ice_sched_get_first_node(pi->hw, vsi_node, qgrp_layer);
+	while (qgrp_node) {
+		/* make sure the qgroup node is part of the VSI subtree */
+		if (ice_sched_find_node_in_subtree(pi->hw, vsi_node, qgrp_node))
+			if (qgrp_node->num_children < max_children &&
+			    qgrp_node->owner == owner)
+				break;
+		qgrp_node = qgrp_node->sibling;
+	}
+lan_q_exit:
+	return qgrp_node;
+}

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

@@ -6,6 +6,8 @@
 
 #include "ice_common.h"
 
+#define ICE_QGRP_LAYER_OFFSET	2
+
 struct ice_sched_agg_vsi_info {
 	struct list_head list_entry;
 	DECLARE_BITMAP(tc_bitmap, ICE_MAX_TRAFFIC_CLASS);
@@ -31,4 +33,7 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer,
 		   struct ice_aqc_txsched_elem_data *info);
 void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node);
 struct ice_sched_node *ice_sched_get_tc_node(struct ice_port_info *pi, u8 tc);
+struct ice_sched_node *
+ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_id, u8 tc,
+			   u8 owner);
 #endif /* _ICE_SCHED_H_ */

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

@@ -9,6 +9,7 @@ enum ice_status {
 	ICE_ERR_PARAM				= -1,
 	ICE_ERR_NOT_IMPL			= -2,
 	ICE_ERR_NOT_READY			= -3,
+	ICE_ERR_BAD_PTR				= -5,
 	ICE_ERR_INVAL_SIZE			= -6,
 	ICE_ERR_DEVICE_NOT_SUPPORTED		= -8,
 	ICE_ERR_RESET_FAILED			= -9,
@@ -18,6 +19,7 @@ enum ice_status {
 	ICE_ERR_OUT_OF_RANGE			= -13,
 	ICE_ERR_ALREADY_EXISTS			= -14,
 	ICE_ERR_DOES_NOT_EXIST			= -15,
+	ICE_ERR_MAX_LIMIT			= -17,
 	ICE_ERR_BUF_TOO_SHORT			= -52,
 	ICE_ERR_NVM_BLANK_MODE			= -53,
 	ICE_ERR_AQ_ERROR			= -100,

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

@@ -0,0 +1,361 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018, Intel Corporation. */
+
+/* The driver transmit and receive code */
+
+#include <linux/prefetch.h>
+#include <linux/mm.h>
+#include "ice.h"
+
+/**
+ * ice_unmap_and_free_tx_buf - Release a Tx buffer
+ * @ring: the ring that owns the buffer
+ * @tx_buf: the buffer to free
+ */
+static void
+ice_unmap_and_free_tx_buf(struct ice_ring *ring, struct ice_tx_buf *tx_buf)
+{
+	if (tx_buf->skb) {
+		dev_kfree_skb_any(tx_buf->skb);
+		if (dma_unmap_len(tx_buf, len))
+			dma_unmap_single(ring->dev,
+					 dma_unmap_addr(tx_buf, dma),
+					 dma_unmap_len(tx_buf, len),
+					 DMA_TO_DEVICE);
+	} else if (dma_unmap_len(tx_buf, len)) {
+		dma_unmap_page(ring->dev,
+			       dma_unmap_addr(tx_buf, dma),
+			       dma_unmap_len(tx_buf, len),
+			       DMA_TO_DEVICE);
+	}
+
+	tx_buf->next_to_watch = NULL;
+	tx_buf->skb = NULL;
+	dma_unmap_len_set(tx_buf, len, 0);
+	/* tx_buf must be completely set up in the transmit path */
+}
+
+static struct netdev_queue *txring_txq(const struct ice_ring *ring)
+{
+	return netdev_get_tx_queue(ring->netdev, ring->q_index);
+}
+
+/**
+ * ice_clean_tx_ring - Free any empty Tx buffers
+ * @tx_ring: ring to be cleaned
+ */
+void ice_clean_tx_ring(struct ice_ring *tx_ring)
+{
+	unsigned long size;
+	u16 i;
+
+	/* ring already cleared, nothing to do */
+	if (!tx_ring->tx_buf)
+		return;
+
+	/* Free all the Tx ring sk_bufss */
+	for (i = 0; i < tx_ring->count; i++)
+		ice_unmap_and_free_tx_buf(tx_ring, &tx_ring->tx_buf[i]);
+
+	size = sizeof(struct ice_tx_buf) * tx_ring->count;
+	memset(tx_ring->tx_buf, 0, size);
+
+	/* Zero out the descriptor ring */
+	memset(tx_ring->desc, 0, tx_ring->size);
+
+	tx_ring->next_to_use = 0;
+	tx_ring->next_to_clean = 0;
+
+	if (!tx_ring->netdev)
+		return;
+
+	/* cleanup Tx queue statistics */
+	netdev_tx_reset_queue(txring_txq(tx_ring));
+}
+
+/**
+ * ice_free_tx_ring - Free Tx resources per queue
+ * @tx_ring: Tx descriptor ring for a specific queue
+ *
+ * Free all transmit software resources
+ */
+void ice_free_tx_ring(struct ice_ring *tx_ring)
+{
+	ice_clean_tx_ring(tx_ring);
+	devm_kfree(tx_ring->dev, tx_ring->tx_buf);
+	tx_ring->tx_buf = NULL;
+
+	if (tx_ring->desc) {
+		dmam_free_coherent(tx_ring->dev, tx_ring->size,
+				   tx_ring->desc, tx_ring->dma);
+		tx_ring->desc = NULL;
+	}
+}
+
+/**
+ * ice_setup_tx_ring - Allocate the Tx descriptors
+ * @tx_ring: the tx ring to set up
+ *
+ * Return 0 on success, negative on error
+ */
+int ice_setup_tx_ring(struct ice_ring *tx_ring)
+{
+	struct device *dev = tx_ring->dev;
+	int bi_size;
+
+	if (!dev)
+		return -ENOMEM;
+
+	/* warn if we are about to overwrite the pointer */
+	WARN_ON(tx_ring->tx_buf);
+	bi_size = sizeof(struct ice_tx_buf) * tx_ring->count;
+	tx_ring->tx_buf = devm_kzalloc(dev, bi_size, GFP_KERNEL);
+	if (!tx_ring->tx_buf)
+		return -ENOMEM;
+
+	/* round up to nearest 4K */
+	tx_ring->size = tx_ring->count * sizeof(struct ice_tx_desc);
+	tx_ring->size = ALIGN(tx_ring->size, 4096);
+	tx_ring->desc = dmam_alloc_coherent(dev, tx_ring->size, &tx_ring->dma,
+					    GFP_KERNEL);
+	if (!tx_ring->desc) {
+		dev_err(dev, "Unable to allocate memory for the Tx descriptor ring, size=%d\n",
+			tx_ring->size);
+		goto err;
+	}
+
+	tx_ring->next_to_use = 0;
+	tx_ring->next_to_clean = 0;
+	return 0;
+
+err:
+	devm_kfree(dev, tx_ring->tx_buf);
+	tx_ring->tx_buf = NULL;
+	return -ENOMEM;
+}
+
+/**
+ * ice_clean_rx_ring - Free Rx buffers
+ * @rx_ring: ring to be cleaned
+ */
+void ice_clean_rx_ring(struct ice_ring *rx_ring)
+{
+	struct device *dev = rx_ring->dev;
+	unsigned long size;
+	u16 i;
+
+	/* ring already cleared, nothing to do */
+	if (!rx_ring->rx_buf)
+		return;
+
+	/* Free all the Rx ring sk_buffs */
+	for (i = 0; i < rx_ring->count; i++) {
+		struct ice_rx_buf *rx_buf = &rx_ring->rx_buf[i];
+
+		if (rx_buf->skb) {
+			dev_kfree_skb(rx_buf->skb);
+			rx_buf->skb = NULL;
+		}
+		if (!rx_buf->page)
+			continue;
+
+		dma_unmap_page(dev, rx_buf->dma, PAGE_SIZE, DMA_FROM_DEVICE);
+		__free_pages(rx_buf->page, 0);
+
+		rx_buf->page = NULL;
+		rx_buf->page_offset = 0;
+	}
+
+	size = sizeof(struct ice_rx_buf) * rx_ring->count;
+	memset(rx_ring->rx_buf, 0, size);
+
+	/* Zero out the descriptor ring */
+	memset(rx_ring->desc, 0, rx_ring->size);
+
+	rx_ring->next_to_alloc = 0;
+	rx_ring->next_to_clean = 0;
+	rx_ring->next_to_use = 0;
+}
+
+/**
+ * ice_free_rx_ring - Free Rx resources
+ * @rx_ring: ring to clean the resources from
+ *
+ * Free all receive software resources
+ */
+void ice_free_rx_ring(struct ice_ring *rx_ring)
+{
+	ice_clean_rx_ring(rx_ring);
+	devm_kfree(rx_ring->dev, rx_ring->rx_buf);
+	rx_ring->rx_buf = NULL;
+
+	if (rx_ring->desc) {
+		dmam_free_coherent(rx_ring->dev, rx_ring->size,
+				   rx_ring->desc, rx_ring->dma);
+		rx_ring->desc = NULL;
+	}
+}
+
+/**
+ * ice_setup_rx_ring - Allocate the Rx descriptors
+ * @rx_ring: the rx ring to set up
+ *
+ * Return 0 on success, negative on error
+ */
+int ice_setup_rx_ring(struct ice_ring *rx_ring)
+{
+	struct device *dev = rx_ring->dev;
+	int bi_size;
+
+	if (!dev)
+		return -ENOMEM;
+
+	/* warn if we are about to overwrite the pointer */
+	WARN_ON(rx_ring->rx_buf);
+	bi_size = sizeof(struct ice_rx_buf) * rx_ring->count;
+	rx_ring->rx_buf = devm_kzalloc(dev, bi_size, GFP_KERNEL);
+	if (!rx_ring->rx_buf)
+		return -ENOMEM;
+
+	/* round up to nearest 4K */
+	rx_ring->size = rx_ring->count * sizeof(union ice_32byte_rx_desc);
+	rx_ring->size = ALIGN(rx_ring->size, 4096);
+	rx_ring->desc = dmam_alloc_coherent(dev, rx_ring->size, &rx_ring->dma,
+					    GFP_KERNEL);
+	if (!rx_ring->desc) {
+		dev_err(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n",
+			rx_ring->size);
+		goto err;
+	}
+
+	rx_ring->next_to_use = 0;
+	rx_ring->next_to_clean = 0;
+	return 0;
+
+err:
+	devm_kfree(dev, rx_ring->rx_buf);
+	rx_ring->rx_buf = NULL;
+	return -ENOMEM;
+}
+
+/**
+ * ice_release_rx_desc - Store the new tail and head values
+ * @rx_ring: ring to bump
+ * @val: new head index
+ */
+static void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val)
+{
+	rx_ring->next_to_use = val;
+
+	/* update next to alloc since we have filled the ring */
+	rx_ring->next_to_alloc = val;
+
+	/* Force memory writes to complete before letting h/w
+	 * know there are new descriptors to fetch.  (Only
+	 * applicable for weak-ordered memory model archs,
+	 * such as IA-64).
+	 */
+	wmb();
+	writel(val, rx_ring->tail);
+}
+
+/**
+ * ice_alloc_mapped_page - recycle or make a new page
+ * @rx_ring: ring to use
+ * @bi: rx_buf struct to modify
+ *
+ * Returns true if the page was successfully allocated or
+ * reused.
+ */
+static bool ice_alloc_mapped_page(struct ice_ring *rx_ring,
+				  struct ice_rx_buf *bi)
+{
+	struct page *page = bi->page;
+	dma_addr_t dma;
+
+	/* since we are recycling buffers we should seldom need to alloc */
+	if (likely(page))
+		return true;
+
+	/* alloc new page for storage */
+	page = alloc_page(GFP_ATOMIC | __GFP_NOWARN);
+	if (unlikely(!page))
+		return false;
+
+	/* map page for use */
+	dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+
+	/* if mapping failed free memory back to system since
+	 * there isn't much point in holding memory we can't use
+	 */
+	if (dma_mapping_error(rx_ring->dev, dma)) {
+		__free_pages(page, 0);
+		return false;
+	}
+
+	bi->dma = dma;
+	bi->page = page;
+	bi->page_offset = 0;
+
+	return true;
+}
+
+/**
+ * ice_alloc_rx_bufs - Replace used receive buffers
+ * @rx_ring: ring to place buffers on
+ * @cleaned_count: number of buffers to replace
+ *
+ * Returns false if all allocations were successful, true if any fail
+ */
+bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count)
+{
+	union ice_32b_rx_flex_desc *rx_desc;
+	u16 ntu = rx_ring->next_to_use;
+	struct ice_rx_buf *bi;
+
+	/* do nothing if no valid netdev defined */
+	if (!rx_ring->netdev || !cleaned_count)
+		return false;
+
+	/* get the RX descriptor and buffer based on next_to_use */
+	rx_desc = ICE_RX_DESC(rx_ring, ntu);
+	bi = &rx_ring->rx_buf[ntu];
+
+	do {
+		if (!ice_alloc_mapped_page(rx_ring, bi))
+			goto no_bufs;
+
+		/* Refresh the desc even if buffer_addrs didn't change
+		 * because each write-back erases this info.
+		 */
+		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
+
+		rx_desc++;
+		bi++;
+		ntu++;
+		if (unlikely(ntu == rx_ring->count)) {
+			rx_desc = ICE_RX_DESC(rx_ring, 0);
+			bi = rx_ring->rx_buf;
+			ntu = 0;
+		}
+
+		/* clear the status bits for the next_to_use descriptor */
+		rx_desc->wb.status_error0 = 0;
+
+		cleaned_count--;
+	} while (cleaned_count);
+
+	if (rx_ring->next_to_use != ntu)
+		ice_release_rx_desc(rx_ring, ntu);
+
+	return false;
+
+no_bufs:
+	if (rx_ring->next_to_use != ntu)
+		ice_release_rx_desc(rx_ring, ntu);
+
+	/* make sure to come back via polling to try again after
+	 * allocation failure
+	 */
+	return true;
+}

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

@@ -5,6 +5,30 @@
 #define _ICE_TXRX_H_
 
 #define ICE_DFLT_IRQ_WORK	256
+#define ICE_RXBUF_2048		2048
+#define ICE_MAX_CHAINED_RX_BUFS	5
+#define ICE_MAX_TXQ_PER_TXQG	128
+
+#define ICE_DESC_UNUSED(R)	\
+	((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
+	(R)->next_to_clean - (R)->next_to_use - 1)
+
+struct ice_tx_buf {
+	struct ice_tx_desc *next_to_watch;
+	struct sk_buff *skb;
+	unsigned int bytecount;
+	unsigned short gso_segs;
+	u32 tx_flags;
+	DEFINE_DMA_UNMAP_ADDR(dma);
+	DEFINE_DMA_UNMAP_LEN(len);
+};
+
+struct ice_rx_buf {
+	struct sk_buff *skb;
+	dma_addr_t dma;
+	struct page *page;
+	unsigned int page_offset;
+};
 
 /* this enum matches hardware bits and is meant to be used by DYN_CTLN
  * registers and QINT registers or more generally anywhere in the manual
@@ -18,33 +42,77 @@ enum ice_dyn_idx_t {
 	ICE_ITR_NONE = 3	/* ITR_NONE must not be used as an index */
 };
 
+/* Header split modes defined by DTYPE field of Rx RLAN context */
+enum ice_rx_dtype {
+	ICE_RX_DTYPE_NO_SPLIT		= 0,
+	ICE_RX_DTYPE_HEADER_SPLIT	= 1,
+	ICE_RX_DTYPE_SPLIT_ALWAYS	= 2,
+};
+
 /* indices into GLINT_ITR registers */
 #define ICE_RX_ITR	ICE_IDX_ITR0
+#define ICE_TX_ITR	ICE_IDX_ITR1
 #define ICE_ITR_DYNAMIC	0x8000  /* use top bit as a flag */
 #define ICE_ITR_8K	0x003E
 
 /* apply ITR HW granularity translation to program the HW registers */
 #define ITR_TO_REG(val, itr_gran) (((val) & ~ICE_ITR_DYNAMIC) >> (itr_gran))
 
+/* Legacy or Advanced Mode Queue */
+#define ICE_TX_ADVANCED	0
+#define ICE_TX_LEGACY	1
+
 /* descriptor ring, associated with a VSI */
 struct ice_ring {
 	struct ice_ring *next;		/* pointer to next ring in q_vector */
+	void *desc;			/* Descriptor ring memory */
 	struct device *dev;		/* Used for DMA mapping */
 	struct net_device *netdev;	/* netdev ring maps to */
 	struct ice_vsi *vsi;		/* Backreference to associated VSI */
 	struct ice_q_vector *q_vector;	/* Backreference to associated vector */
+	u8 __iomem *tail;
+	union {
+		struct ice_tx_buf *tx_buf;
+		struct ice_rx_buf *rx_buf;
+	};
 	u16 q_index;			/* Queue number of ring */
+	u32 txq_teid;			/* Added Tx queue TEID */
+
+	/* high bit set means dynamic, use accessor routines to read/write.
+	 * hardware supports 2us/1us resolution for the ITR registers.
+	 * these values always store the USER setting, and must be converted
+	 * before programming to a register.
+	 */
+	u16 rx_itr_setting;
+	u16 tx_itr_setting;
+
 	u16 count;			/* Number of descriptors */
 	u16 reg_idx;			/* HW register index of the ring */
+
+	/* used in interrupt processing */
+	u16 next_to_use;
+	u16 next_to_clean;
+
 	bool ring_active;		/* is ring online or not */
+	unsigned int size;		/* length of descriptor ring in bytes */
+	dma_addr_t dma;			/* physical address of ring */
 	struct rcu_head rcu;		/* to avoid race on free */
+	u16 next_to_alloc;
 } ____cacheline_internodealigned_in_smp;
 
+enum ice_latency_range {
+	ICE_LOWEST_LATENCY = 0,
+	ICE_LOW_LATENCY = 1,
+	ICE_BULK_LATENCY = 2,
+	ICE_ULTRA_LATENCY = 3,
+};
+
 struct ice_ring_container {
 	/* array of pointers to rings */
 	struct ice_ring *ring;
 	unsigned int total_bytes;	/* total bytes processed this int */
 	unsigned int total_pkts;	/* total packets processed this int */
+	enum ice_latency_range latency_range;
 	u16 itr;
 };
 
@@ -52,4 +120,11 @@ struct ice_ring_container {
 #define ice_for_each_ring(pos, head) \
 	for (pos = (head).ring; pos; pos = pos->next)
 
+bool ice_alloc_rx_bufs(struct ice_ring *rxr, u16 cleaned_count);
+void ice_clean_tx_ring(struct ice_ring *tx_ring);
+void ice_clean_rx_ring(struct ice_ring *rx_ring);
+int ice_setup_tx_ring(struct ice_ring *tx_ring);
+int ice_setup_rx_ring(struct ice_ring *rx_ring);
+void ice_free_tx_ring(struct ice_ring *tx_ring);
+void ice_free_rx_ring(struct ice_ring *rx_ring);
 #endif /* _ICE_TXRX_H_ */

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

@@ -8,9 +8,11 @@
 #include "ice_hw_autogen.h"
 #include "ice_osdep.h"
 #include "ice_controlq.h"
+#include "ice_lan_tx_rx.h"
 
 /* debug masks - set these bits in hw->debug_mask to control output */
 #define ICE_DBG_INIT		BIT_ULL(1)
+#define ICE_DBG_QCTX		BIT_ULL(6)
 #define ICE_DBG_NVM		BIT_ULL(7)
 #define ICE_DBG_LAN		BIT_ULL(8)
 #define ICE_DBG_SW		BIT_ULL(13)