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.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

+/* 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_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 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw)
 	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

+// 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)