/*
 * Driver for Marvell NETA network card for Armada XP and Armada 370 SoCs.
 *
 * Copyright (C) 2012 Marvell
 *
 * Rami Rosen <rosenr@marvell.com>
 * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
 *
 * This file is licensed under the terms of the GNU General Public
 * License version 2. This program is licensed "as is" without any
 * warranty of any kind, whether express or implied.
 */

#include <linux/clk.h>
#include <linux/cpu.h>
#include <linux/etherdevice.h>
#include <linux/if_vlan.h>
#include <linux/inetdevice.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/mbus.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
#include <linux/of_mdio.h>
#include <linux/of_net.h>
#include <linux/phy/phy.h>
#include <linux/phy.h>
#include <linux/phylink.h>
#include <linux/platform_device.h>
#include <linux/skbuff.h>
#include <net/hwbm.h>
#include "mvneta_bm.h"
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/tso.h>
#include <net/page_pool.h>
#include <linux/bpf_trace.h>

/* Registers */
#define MVNETA_RXQ_CONFIG_REG(q)                (0x1400 + ((q) << 2))
#define      MVNETA_RXQ_HW_BUF_ALLOC            BIT(0)
#define      MVNETA_RXQ_SHORT_POOL_ID_SHIFT     4
#define      MVNETA_RXQ_SHORT_POOL_ID_MASK      0x30
#define      MVNETA_RXQ_LONG_POOL_ID_SHIFT      6
#define      MVNETA_RXQ_LONG_POOL_ID_MASK       0xc0
#define      MVNETA_RXQ_PKT_OFFSET_ALL_MASK     (0xf    << 8)
#define      MVNETA_RXQ_PKT_OFFSET_MASK(offs)   ((offs) << 8)
#define MVNETA_RXQ_THRESHOLD_REG(q)             (0x14c0 + ((q) << 2))
#define      MVNETA_RXQ_NON_OCCUPIED(v)         ((v) << 16)
#define MVNETA_RXQ_BASE_ADDR_REG(q)             (0x1480 + ((q) << 2))
#define MVNETA_RXQ_SIZE_REG(q)                  (0x14a0 + ((q) << 2))
#define      MVNETA_RXQ_BUF_SIZE_SHIFT          19
#define      MVNETA_RXQ_BUF_SIZE_MASK           (0x1fff << 19)
#define MVNETA_RXQ_STATUS_REG(q)                (0x14e0 + ((q) << 2))
#define      MVNETA_RXQ_OCCUPIED_ALL_MASK       0x3fff
#define MVNETA_RXQ_STATUS_UPDATE_REG(q)         (0x1500 + ((q) << 2))
#define      MVNETA_RXQ_ADD_NON_OCCUPIED_SHIFT  16
#define      MVNETA_RXQ_ADD_NON_OCCUPIED_MAX    255
#define MVNETA_PORT_POOL_BUFFER_SZ_REG(pool)    (0x1700 + ((pool) << 2))
#define      MVNETA_PORT_POOL_BUFFER_SZ_SHIFT   3
#define      MVNETA_PORT_POOL_BUFFER_SZ_MASK    0xfff8
#define MVNETA_PORT_RX_RESET                    0x1cc0
#define      MVNETA_PORT_RX_DMA_RESET           BIT(0)
#define MVNETA_PHY_ADDR                         0x2000
#define      MVNETA_PHY_ADDR_MASK               0x1f
#define MVNETA_MBUS_RETRY                       0x2010
#define MVNETA_UNIT_INTR_CAUSE                  0x2080
#define MVNETA_UNIT_CONTROL                     0x20B0
#define      MVNETA_PHY_POLLING_ENABLE          BIT(1)
#define MVNETA_WIN_BASE(w)                      (0x2200 + ((w) << 3))
#define MVNETA_WIN_SIZE(w)                      (0x2204 + ((w) << 3))
#define MVNETA_WIN_REMAP(w)                     (0x2280 + ((w) << 2))
#define MVNETA_BASE_ADDR_ENABLE                 0x2290
#define MVNETA_ACCESS_PROTECT_ENABLE            0x2294
#define MVNETA_PORT_CONFIG                      0x2400
#define      MVNETA_UNI_PROMISC_MODE            BIT(0)
#define      MVNETA_DEF_RXQ(q)                  ((q) << 1)
#define      MVNETA_DEF_RXQ_ARP(q)              ((q) << 4)
#define      MVNETA_TX_UNSET_ERR_SUM            BIT(12)
#define      MVNETA_DEF_RXQ_TCP(q)              ((q) << 16)
#define      MVNETA_DEF_RXQ_UDP(q)              ((q) << 19)
#define      MVNETA_DEF_RXQ_BPDU(q)             ((q) << 22)
#define      MVNETA_RX_CSUM_WITH_PSEUDO_HDR     BIT(25)
#define      MVNETA_PORT_CONFIG_DEFL_VALUE(q)   (MVNETA_DEF_RXQ(q)       | \
                                                 MVNETA_DEF_RXQ_ARP(q)   | \
                                                 MVNETA_DEF_RXQ_TCP(q)   | \
                                                 MVNETA_DEF_RXQ_UDP(q)   | \
                                                 MVNETA_DEF_RXQ_BPDU(q)  | \
                                                 MVNETA_TX_UNSET_ERR_SUM | \
                                                 MVNETA_RX_CSUM_WITH_PSEUDO_HDR)
#define MVNETA_PORT_CONFIG_EXTEND                0x2404
#define MVNETA_MAC_ADDR_LOW                      0x2414
#define MVNETA_MAC_ADDR_HIGH                     0x2418
#define MVNETA_SDMA_CONFIG                       0x241c
#define      MVNETA_SDMA_BRST_SIZE_16            4
#define      MVNETA_RX_BRST_SZ_MASK(burst)       ((burst) << 1)
#define      MVNETA_RX_NO_DATA_SWAP              BIT(4)
#define      MVNETA_TX_NO_DATA_SWAP              BIT(5)
#define      MVNETA_DESC_SWAP                    BIT(6)
#define      MVNETA_TX_BRST_SZ_MASK(burst)       ((burst) << 22)
#define MVNETA_PORT_STATUS                       0x2444
#define      MVNETA_TX_IN_PRGRS                  BIT(1)
#define      MVNETA_TX_FIFO_EMPTY                BIT(8)
#define MVNETA_RX_MIN_FRAME_SIZE                 0x247c
/* Only exists on Armada XP and Armada 370 */
#define MVNETA_SERDES_CFG                        0x24A0
#define      MVNETA_SGMII_SERDES_PROTO           0x0cc7
#define      MVNETA_QSGMII_SERDES_PROTO          0x0667
#define      MVNETA_HSGMII_SERDES_PROTO          0x1107
#define MVNETA_TYPE_PRIO                         0x24bc
#define      MVNETA_FORCE_UNI                    BIT(21)
#define MVNETA_TXQ_CMD_1                         0x24e4
#define MVNETA_TXQ_CMD                           0x2448
#define      MVNETA_TXQ_DISABLE_SHIFT            8
#define      MVNETA_TXQ_ENABLE_MASK              0x000000ff
#define MVNETA_RX_DISCARD_FRAME_COUNT            0x2484
#define MVNETA_OVERRUN_FRAME_COUNT               0x2488
#define MVNETA_GMAC_CLOCK_DIVIDER                0x24f4
#define      MVNETA_GMAC_1MS_CLOCK_ENABLE        BIT(31)
#define MVNETA_ACC_MODE                          0x2500
#define MVNETA_BM_ADDRESS                        0x2504
#define MVNETA_CPU_MAP(cpu)                      (0x2540 + ((cpu) << 2))
#define      MVNETA_CPU_RXQ_ACCESS_ALL_MASK      0x000000ff
#define      MVNETA_CPU_TXQ_ACCESS_ALL_MASK      0x0000ff00
#define      MVNETA_CPU_RXQ_ACCESS(rxq)          BIT(rxq)
#define      MVNETA_CPU_TXQ_ACCESS(txq)          BIT(txq + 8)
#define MVNETA_RXQ_TIME_COAL_REG(q)              (0x2580 + ((q) << 2))

/* Exception Interrupt Port/Queue Cause register
 *
 * Their behavior depend of the mapping done using the PCPX2Q
 * registers. For a given CPU if the bit associated to a queue is not
 * set, then for the register a read from this CPU will always return
 * 0 and a write won't do anything
 */

#define MVNETA_INTR_NEW_CAUSE                    0x25a0
#define MVNETA_INTR_NEW_MASK                     0x25a4

/* bits  0..7  = TXQ SENT, one bit per queue.
 * bits  8..15 = RXQ OCCUP, one bit per queue.
 * bits 16..23 = RXQ FREE, one bit per queue.
 * bit  29 = OLD_REG_SUM, see old reg ?
 * bit  30 = TX_ERR_SUM, one bit for 4 ports
 * bit  31 = MISC_SUM,   one bit for 4 ports
 */
#define      MVNETA_TX_INTR_MASK(nr_txqs)        (((1 << nr_txqs) - 1) << 0)
#define      MVNETA_TX_INTR_MASK_ALL             (0xff << 0)
#define      MVNETA_RX_INTR_MASK(nr_rxqs)        (((1 << nr_rxqs) - 1) << 8)
#define      MVNETA_RX_INTR_MASK_ALL             (0xff << 8)
#define      MVNETA_MISCINTR_INTR_MASK           BIT(31)

#define MVNETA_INTR_OLD_CAUSE                    0x25a8
#define MVNETA_INTR_OLD_MASK                     0x25ac

/* Data Path Port/Queue Cause Register */
#define MVNETA_INTR_MISC_CAUSE                   0x25b0
#define MVNETA_INTR_MISC_MASK                    0x25b4

#define      MVNETA_CAUSE_PHY_STATUS_CHANGE      BIT(0)
#define      MVNETA_CAUSE_LINK_CHANGE            BIT(1)
#define      MVNETA_CAUSE_PTP                    BIT(4)

#define      MVNETA_CAUSE_INTERNAL_ADDR_ERR      BIT(7)
#define      MVNETA_CAUSE_RX_OVERRUN             BIT(8)
#define      MVNETA_CAUSE_RX_CRC_ERROR           BIT(9)
#define      MVNETA_CAUSE_RX_LARGE_PKT           BIT(10)
#define      MVNETA_CAUSE_TX_UNDERUN             BIT(11)
#define      MVNETA_CAUSE_PRBS_ERR               BIT(12)
#define      MVNETA_CAUSE_PSC_SYNC_CHANGE        BIT(13)
#define      MVNETA_CAUSE_SERDES_SYNC_ERR        BIT(14)

#define      MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT    16
#define      MVNETA_CAUSE_BMU_ALLOC_ERR_ALL_MASK   (0xF << MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT)
#define      MVNETA_CAUSE_BMU_ALLOC_ERR_MASK(pool) (1 << (MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT + (pool)))

#define      MVNETA_CAUSE_TXQ_ERROR_SHIFT        24
#define      MVNETA_CAUSE_TXQ_ERROR_ALL_MASK     (0xFF << MVNETA_CAUSE_TXQ_ERROR_SHIFT)
#define      MVNETA_CAUSE_TXQ_ERROR_MASK(q)      (1 << (MVNETA_CAUSE_TXQ_ERROR_SHIFT + (q)))

#define MVNETA_INTR_ENABLE                       0x25b8
#define      MVNETA_TXQ_INTR_ENABLE_ALL_MASK     0x0000ff00
#define      MVNETA_RXQ_INTR_ENABLE_ALL_MASK     0x000000ff

#define MVNETA_RXQ_CMD                           0x2680
#define      MVNETA_RXQ_DISABLE_SHIFT            8
#define      MVNETA_RXQ_ENABLE_MASK              0x000000ff
#define MVETH_TXQ_TOKEN_COUNT_REG(q)             (0x2700 + ((q) << 4))
#define MVETH_TXQ_TOKEN_CFG_REG(q)               (0x2704 + ((q) << 4))
#define MVNETA_GMAC_CTRL_0                       0x2c00
#define      MVNETA_GMAC_MAX_RX_SIZE_SHIFT       2
#define      MVNETA_GMAC_MAX_RX_SIZE_MASK        0x7ffc
#define      MVNETA_GMAC0_PORT_1000BASE_X        BIT(1)
#define      MVNETA_GMAC0_PORT_ENABLE            BIT(0)
#define MVNETA_GMAC_CTRL_2                       0x2c08
#define      MVNETA_GMAC2_INBAND_AN_ENABLE       BIT(0)
#define      MVNETA_GMAC2_PCS_ENABLE             BIT(3)
#define      MVNETA_GMAC2_PORT_RGMII             BIT(4)
#define      MVNETA_GMAC2_PORT_RESET             BIT(6)
#define MVNETA_GMAC_STATUS                       0x2c10
#define      MVNETA_GMAC_LINK_UP                 BIT(0)
#define      MVNETA_GMAC_SPEED_1000              BIT(1)
#define      MVNETA_GMAC_SPEED_100               BIT(2)
#define      MVNETA_GMAC_FULL_DUPLEX             BIT(3)
#define      MVNETA_GMAC_RX_FLOW_CTRL_ENABLE     BIT(4)
#define      MVNETA_GMAC_TX_FLOW_CTRL_ENABLE     BIT(5)
#define      MVNETA_GMAC_RX_FLOW_CTRL_ACTIVE     BIT(6)
#define      MVNETA_GMAC_TX_FLOW_CTRL_ACTIVE     BIT(7)
#define      MVNETA_GMAC_AN_COMPLETE             BIT(11)
#define      MVNETA_GMAC_SYNC_OK                 BIT(14)
#define MVNETA_GMAC_AUTONEG_CONFIG               0x2c0c
#define      MVNETA_GMAC_FORCE_LINK_DOWN         BIT(0)
#define      MVNETA_GMAC_FORCE_LINK_PASS         BIT(1)
#define      MVNETA_GMAC_INBAND_AN_ENABLE        BIT(2)
#define      MVNETA_GMAC_AN_BYPASS_ENABLE        BIT(3)
#define      MVNETA_GMAC_INBAND_RESTART_AN       BIT(4)
#define      MVNETA_GMAC_CONFIG_MII_SPEED        BIT(5)
#define      MVNETA_GMAC_CONFIG_GMII_SPEED       BIT(6)
#define      MVNETA_GMAC_AN_SPEED_EN             BIT(7)
#define      MVNETA_GMAC_CONFIG_FLOW_CTRL        BIT(8)
#define      MVNETA_GMAC_ADVERT_SYM_FLOW_CTRL    BIT(9)
#define      MVNETA_GMAC_AN_FLOW_CTRL_EN         BIT(11)
#define      MVNETA_GMAC_CONFIG_FULL_DUPLEX      BIT(12)
#define      MVNETA_GMAC_AN_DUPLEX_EN            BIT(13)
#define MVNETA_GMAC_CTRL_4                       0x2c90
#define      MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE  BIT(1)
#define MVNETA_MIB_COUNTERS_BASE                 0x3000
#define      MVNETA_MIB_LATE_COLLISION           0x7c
#define MVNETA_DA_FILT_SPEC_MCAST                0x3400
#define MVNETA_DA_FILT_OTH_MCAST                 0x3500
#define MVNETA_DA_FILT_UCAST_BASE                0x3600
#define MVNETA_TXQ_BASE_ADDR_REG(q)              (0x3c00 + ((q) << 2))
#define MVNETA_TXQ_SIZE_REG(q)                   (0x3c20 + ((q) << 2))
#define      MVNETA_TXQ_SENT_THRESH_ALL_MASK     0x3fff0000
#define      MVNETA_TXQ_SENT_THRESH_MASK(coal)   ((coal) << 16)
#define MVNETA_TXQ_UPDATE_REG(q)                 (0x3c60 + ((q) << 2))
#define      MVNETA_TXQ_DEC_SENT_SHIFT           16
#define      MVNETA_TXQ_DEC_SENT_MASK            0xff
#define MVNETA_TXQ_STATUS_REG(q)                 (0x3c40 + ((q) << 2))
#define      MVNETA_TXQ_SENT_DESC_SHIFT          16
#define      MVNETA_TXQ_SENT_DESC_MASK           0x3fff0000
#define MVNETA_PORT_TX_RESET                     0x3cf0
#define      MVNETA_PORT_TX_DMA_RESET            BIT(0)
#define MVNETA_TX_MTU                            0x3e0c
#define MVNETA_TX_TOKEN_SIZE                     0x3e14
#define      MVNETA_TX_TOKEN_SIZE_MAX            0xffffffff
#define MVNETA_TXQ_TOKEN_SIZE_REG(q)             (0x3e40 + ((q) << 2))
#define      MVNETA_TXQ_TOKEN_SIZE_MAX           0x7fffffff

#define MVNETA_LPI_CTRL_0                        0x2cc0
#define MVNETA_LPI_CTRL_1                        0x2cc4
#define      MVNETA_LPI_REQUEST_ENABLE           BIT(0)
#define MVNETA_LPI_CTRL_2                        0x2cc8
#define MVNETA_LPI_STATUS                        0x2ccc

#define MVNETA_CAUSE_TXQ_SENT_DESC_ALL_MASK      0xff

/* Descriptor ring Macros */
#define MVNETA_QUEUE_NEXT_DESC(q, index)        \
        (((index) < (q)->last_desc) ? ((index) + 1) : 0)

/* Various constants */

/* Coalescing */
#define MVNETA_TXDONE_COAL_PKTS         0       /* interrupt per packet */
#define MVNETA_RX_COAL_PKTS             32
#define MVNETA_RX_COAL_USEC             100

/* The two bytes Marvell header. Either contains a special value used
 * by Marvell switches when a specific hardware mode is enabled (not
 * supported by this driver) or is filled automatically by zeroes on
 * the RX side. Those two bytes being at the front of the Ethernet
 * header, they allow to have the IP header aligned on a 4 bytes
 * boundary automatically: the hardware skips those two bytes on its
 * own.
 */
#define MVNETA_MH_SIZE                  2

#define MVNETA_VLAN_TAG_LEN             4

#define MVNETA_TX_CSUM_DEF_SIZE         1600
#define MVNETA_TX_CSUM_MAX_SIZE         9800
#define MVNETA_ACC_MODE_EXT1            1
#define MVNETA_ACC_MODE_EXT2            2

#define MVNETA_MAX_DECODE_WIN           6

/* Timeout constants */
#define MVNETA_TX_DISABLE_TIMEOUT_MSEC  1000
#define MVNETA_RX_DISABLE_TIMEOUT_MSEC  1000
#define MVNETA_TX_FIFO_EMPTY_TIMEOUT    10000

#define MVNETA_TX_MTU_MAX               0x3ffff

/* The RSS lookup table actually has 256 entries but we do not use
 * them yet
 */
#define MVNETA_RSS_LU_TABLE_SIZE        1

/* Max number of Rx descriptors */
#define MVNETA_MAX_RXD 512

/* Max number of Tx descriptors */
#define MVNETA_MAX_TXD 1024

/* Max number of allowed TCP segments for software TSO */
#define MVNETA_MAX_TSO_SEGS 100

#define MVNETA_MAX_SKB_DESCS (MVNETA_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)

/* descriptor aligned size */
#define MVNETA_DESC_ALIGNED_SIZE        32

/* Number of bytes to be taken into account by HW when putting incoming data
 * to the buffers. It is needed in case NET_SKB_PAD exceeds maximum packet
 * offset supported in MVNETA_RXQ_CONFIG_REG(q) registers.
 */
#define MVNETA_RX_PKT_OFFSET_CORRECTION         64

#define MVNETA_RX_PKT_SIZE(mtu) \
        ALIGN((mtu) + MVNETA_MH_SIZE + MVNETA_VLAN_TAG_LEN + \
              ETH_HLEN + ETH_FCS_LEN,                        \
              cache_line_size())

/* Driver assumes that the last 3 bits are 0 */
#define MVNETA_SKB_HEADROOM     ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8)
#define MVNETA_SKB_PAD  (SKB_DATA_ALIGN(sizeof(struct skb_shared_info) + \
                         MVNETA_SKB_HEADROOM))
#define MVNETA_MAX_RX_BUF_SIZE  (PAGE_SIZE - MVNETA_SKB_PAD)

#define IS_TSO_HEADER(txq, addr) \
        ((addr >= txq->tso_hdrs_phys) && \
         (addr < txq->tso_hdrs_phys + txq->size * TSO_HEADER_SIZE))

#define MVNETA_RX_GET_BM_POOL_ID(rxd) \
        (((rxd)->status & MVNETA_RXD_BM_POOL_MASK) >> MVNETA_RXD_BM_POOL_SHIFT)

enum {
        ETHTOOL_STAT_EEE_WAKEUP,
        ETHTOOL_STAT_SKB_ALLOC_ERR,
        ETHTOOL_STAT_REFILL_ERR,
        ETHTOOL_XDP_REDIRECT,
        ETHTOOL_XDP_PASS,
        ETHTOOL_XDP_DROP,
        ETHTOOL_XDP_TX,
        ETHTOOL_XDP_TX_ERR,
        ETHTOOL_XDP_XMIT,
        ETHTOOL_XDP_XMIT_ERR,
        ETHTOOL_MAX_STATS,
};

struct mvneta_statistic {
        unsigned short offset;
        unsigned short type;
        const char name[ETH_GSTRING_LEN];
};

#define T_REG_32        32
#define T_REG_64        64
#define T_SW            1

#define MVNETA_XDP_PASS         0
#define MVNETA_XDP_DROPPED      BIT(0)
#define MVNETA_XDP_TX           BIT(1)
#define MVNETA_XDP_REDIR        BIT(2)

static const struct mvneta_statistic mvneta_statistics[] = {
        { 0x3000, T_REG_64, "good_octets_received", },
        { 0x3010, T_REG_32, "good_frames_received", },
        { 0x3008, T_REG_32, "bad_octets_received", },
        { 0x3014, T_REG_32, "bad_frames_received", },
        { 0x3018, T_REG_32, "broadcast_frames_received", },
        { 0x301c, T_REG_32, "multicast_frames_received", },
        { 0x3050, T_REG_32, "unrec_mac_control_received", },
        { 0x3058, T_REG_32, "good_fc_received", },
        { 0x305c, T_REG_32, "bad_fc_received", },
        { 0x3060, T_REG_32, "undersize_received", },
        { 0x3064, T_REG_32, "fragments_received", },
        { 0x3068, T_REG_32, "oversize_received", },
        { 0x306c, T_REG_32, "jabber_received", },
        { 0x3070, T_REG_32, "mac_receive_error", },
        { 0x3074, T_REG_32, "bad_crc_event", },
        { 0x3078, T_REG_32, "collision", },
        { 0x307c, T_REG_32, "late_collision", },
        { 0x2484, T_REG_32, "rx_discard", },
        { 0x2488, T_REG_32, "rx_overrun", },
        { 0x3020, T_REG_32, "frames_64_octets", },
        { 0x3024, T_REG_32, "frames_65_to_127_octets", },
        { 0x3028, T_REG_32, "frames_128_to_255_octets", },
        { 0x302c, T_REG_32, "frames_256_to_511_octets", },
        { 0x3030, T_REG_32, "frames_512_to_1023_octets", },
        { 0x3034, T_REG_32, "frames_1024_to_max_octets", },
        { 0x3038, T_REG_64, "good_octets_sent", },
        { 0x3040, T_REG_32, "good_frames_sent", },
        { 0x3044, T_REG_32, "excessive_collision", },
        { 0x3048, T_REG_32, "multicast_frames_sent", },
        { 0x304c, T_REG_32, "broadcast_frames_sent", },
        { 0x3054, T_REG_32, "fc_sent", },
        { 0x300c, T_REG_32, "internal_mac_transmit_err", },
        { ETHTOOL_STAT_EEE_WAKEUP, T_SW, "eee_wakeup_errors", },
        { ETHTOOL_STAT_SKB_ALLOC_ERR, T_SW, "skb_alloc_errors", },
        { ETHTOOL_STAT_REFILL_ERR, T_SW, "refill_errors", },
        { ETHTOOL_XDP_REDIRECT, T_SW, "rx_xdp_redirect", },
        { ETHTOOL_XDP_PASS, T_SW, "rx_xdp_pass", },
        { ETHTOOL_XDP_DROP, T_SW, "rx_xdp_drop", },
        { ETHTOOL_XDP_TX, T_SW, "rx_xdp_tx", },
        { ETHTOOL_XDP_TX_ERR, T_SW, "rx_xdp_tx_errors", },
        { ETHTOOL_XDP_XMIT, T_SW, "tx_xdp_xmit", },
        { ETHTOOL_XDP_XMIT_ERR, T_SW, "tx_xdp_xmit_errors", },
};

struct mvneta_stats {
        u64     rx_packets;
        u64     rx_bytes;
        u64     tx_packets;
        u64     tx_bytes;
        /* xdp */
        u64     xdp_redirect;
        u64     xdp_pass;
        u64     xdp_drop;
        u64     xdp_xmit;
        u64     xdp_xmit_err;
        u64     xdp_tx;
        u64     xdp_tx_err;
};

struct mvneta_ethtool_stats {
        struct mvneta_stats ps;
        u64     skb_alloc_error;
        u64     refill_error;
};

struct mvneta_pcpu_stats {
        struct u64_stats_sync syncp;

        struct mvneta_ethtool_stats es;
        u64     rx_dropped;
        u64     rx_errors;
};

struct mvneta_pcpu_port {
        /* Pointer to the shared port */
        struct mvneta_port      *pp;

        /* Pointer to the CPU-local NAPI struct */
        struct napi_struct      napi;

        /* Cause of the previous interrupt */
        u32                     cause_rx_tx;
};

enum {
        __MVNETA_DOWN,
};

struct mvneta_port {
        u8 id;
        struct mvneta_pcpu_port __percpu        *ports;
        struct mvneta_pcpu_stats __percpu       *stats;

        unsigned long state;

        int pkt_size;
        void __iomem *base;
        struct mvneta_rx_queue *rxqs;
        struct mvneta_tx_queue *txqs;
        struct net_device *dev;
        struct hlist_node node_online;
        struct hlist_node node_dead;
        int rxq_def;
        /* Protect the access to the percpu interrupt registers,
         * ensuring that the configuration remains coherent.
         */
        spinlock_t lock;
        bool is_stopped;

        u32 cause_rx_tx;
        struct napi_struct napi;

        struct bpf_prog *xdp_prog;

        /* Core clock */
        struct clk *clk;
        /* AXI clock */
        struct clk *clk_bus;
        u8 mcast_count[256];
        u16 tx_ring_size;
        u16 rx_ring_size;

        phy_interface_t phy_interface;
        struct device_node *dn;
        unsigned int tx_csum_limit;
        struct phylink *phylink;
        struct phylink_config phylink_config;
        struct phy *comphy;

        struct mvneta_bm *bm_priv;
        struct mvneta_bm_pool *pool_long;
        struct mvneta_bm_pool *pool_short;
        int bm_win_id;

        bool eee_enabled;
        bool eee_active;
        bool tx_lpi_enabled;

        u64 ethtool_stats[ARRAY_SIZE(mvneta_statistics)];

        u32 indir[MVNETA_RSS_LU_TABLE_SIZE];

        /* Flags for special SoC configurations */
        bool neta_armada3700;
        u16 rx_offset_correction;
        const struct mbus_dram_target_info *dram_target_info;
};

/* The mvneta_tx_desc and mvneta_rx_desc structures describe the
 * layout of the transmit and reception DMA descriptors, and their
 * layout is therefore defined by the hardware design
 */

#define MVNETA_TX_L3_OFF_SHIFT  0
#define MVNETA_TX_IP_HLEN_SHIFT 8
#define MVNETA_TX_L4_UDP        BIT(16)
#define MVNETA_TX_L3_IP6        BIT(17)
#define MVNETA_TXD_IP_CSUM      BIT(18)
#define MVNETA_TXD_Z_PAD        BIT(19)
#define MVNETA_TXD_L_DESC       BIT(20)
#define MVNETA_TXD_F_DESC       BIT(21)
#define MVNETA_TXD_FLZ_DESC     (MVNETA_TXD_Z_PAD  | \
                                 MVNETA_TXD_L_DESC | \
                                 MVNETA_TXD_F_DESC)
#define MVNETA_TX_L4_CSUM_FULL  BIT(30)
#define MVNETA_TX_L4_CSUM_NOT   BIT(31)

#define MVNETA_RXD_ERR_CRC              0x0
#define MVNETA_RXD_BM_POOL_SHIFT        13
#define MVNETA_RXD_BM_POOL_MASK         (BIT(13) | BIT(14))
#define MVNETA_RXD_ERR_SUMMARY          BIT(16)
#define MVNETA_RXD_ERR_OVERRUN          BIT(17)
#define MVNETA_RXD_ERR_LEN              BIT(18)
#define MVNETA_RXD_ERR_RESOURCE         (BIT(17) | BIT(18))
#define MVNETA_RXD_ERR_CODE_MASK        (BIT(17) | BIT(18))
#define MVNETA_RXD_L3_IP4               BIT(25)
#define MVNETA_RXD_LAST_DESC            BIT(26)
#define MVNETA_RXD_FIRST_DESC           BIT(27)
#define MVNETA_RXD_FIRST_LAST_DESC      (MVNETA_RXD_FIRST_DESC | \
                                         MVNETA_RXD_LAST_DESC)
#define MVNETA_RXD_L4_CSUM_OK           BIT(30)

#if defined(__LITTLE_ENDIAN)
struct mvneta_tx_desc {
        u32  command;           /* Options used by HW for packet transmitting.*/
        u16  reserved1;         /* csum_l4 (for future use)             */
        u16  data_size;         /* Data size of transmitted packet in bytes */
        u32  buf_phys_addr;     /* Physical addr of transmitted buffer  */
        u32  reserved2;         /* hw_cmd - (for future use, PMT)       */
        u32  reserved3[4];      /* Reserved - (for future use)          */
};

struct mvneta_rx_desc {
        u32  status;            /* Info about received packet           */
        u16  reserved1;         /* pnc_info - (for future use, PnC)     */
        u16  data_size;         /* Size of received packet in bytes     */

        u32  buf_phys_addr;     /* Physical address of the buffer       */
        u32  reserved2;         /* pnc_flow_id  (for future use, PnC)   */

        u32  buf_cookie;        /* cookie for access to RX buffer in rx path */
        u16  reserved3;         /* prefetch_cmd, for future use         */
        u16  reserved4;         /* csum_l4 - (for future use, PnC)      */

        u32  reserved5;         /* pnc_extra PnC (for future use, PnC)  */
        u32  reserved6;         /* hw_cmd (for future use, PnC and HWF) */
};
#else
struct mvneta_tx_desc {
        u16  data_size;         /* Data size of transmitted packet in bytes */
        u16  reserved1;         /* csum_l4 (for future use)             */
        u32  command;           /* Options used by HW for packet transmitting.*/
        u32  reserved2;         /* hw_cmd - (for future use, PMT)       */
        u32  buf_phys_addr;     /* Physical addr of transmitted buffer  */
        u32  reserved3[4];      /* Reserved - (for future use)          */
};

struct mvneta_rx_desc {
        u16  data_size;         /* Size of received packet in bytes     */
        u16  reserved1;         /* pnc_info - (for future use, PnC)     */
        u32  status;            /* Info about received packet           */

        u32  reserved2;         /* pnc_flow_id  (for future use, PnC)   */
        u32  buf_phys_addr;     /* Physical address of the buffer       */

        u16  reserved4;         /* csum_l4 - (for future use, PnC)      */
        u16  reserved3;         /* prefetch_cmd, for future use         */
        u32  buf_cookie;        /* cookie for access to RX buffer in rx path */

        u32  reserved5;         /* pnc_extra PnC (for future use, PnC)  */
        u32  reserved6;         /* hw_cmd (for future use, PnC and HWF) */
};
#endif

enum mvneta_tx_buf_type {
        MVNETA_TYPE_SKB,
        MVNETA_TYPE_XDP_TX,
        MVNETA_TYPE_XDP_NDO,
};

struct mvneta_tx_buf {
        enum mvneta_tx_buf_type type;
        union {
                struct xdp_frame *xdpf;
                struct sk_buff *skb;
        };
};

struct mvneta_tx_queue {
        /* Number of this TX queue, in the range 0-7 */
        u8 id;

        /* Number of TX DMA descriptors in the descriptor ring */
        int size;

        /* Number of currently used TX DMA descriptor in the
         * descriptor ring
         */
        int count;
        int pending;
        int tx_stop_threshold;
        int tx_wake_threshold;

        /* Array of transmitted buffers */
        struct mvneta_tx_buf *buf;

        /* Index of last TX DMA descriptor that was inserted */
        int txq_put_index;

        /* Index of the TX DMA descriptor to be cleaned up */
        int txq_get_index;

        u32 done_pkts_coal;

        /* Virtual address of the TX DMA descriptors array */
        struct mvneta_tx_desc *descs;

        /* DMA address of the TX DMA descriptors array */
        dma_addr_t descs_phys;

        /* Index of the last TX DMA descriptor */
        int last_desc;

        /* Index of the next TX DMA descriptor to process */
        int next_desc_to_proc;

        /* DMA buffers for TSO headers */
        char *tso_hdrs;

        /* DMA address of TSO headers */
        dma_addr_t tso_hdrs_phys;

        /* Affinity mask for CPUs*/
        cpumask_t affinity_mask;
};

struct mvneta_rx_queue {
        /* rx queue number, in the range 0-7 */
        u8 id;

        /* num of rx descriptors in the rx descriptor ring */
        int size;

        u32 pkts_coal;
        u32 time_coal;

        /* page_pool */
        struct page_pool *page_pool;
        struct xdp_rxq_info xdp_rxq;

        /* Virtual address of the RX buffer */
        void  **buf_virt_addr;

        /* Virtual address of the RX DMA descriptors array */
        struct mvneta_rx_desc *descs;

        /* DMA address of the RX DMA descriptors array */
        dma_addr_t descs_phys;

        /* Index of the last RX DMA descriptor */
        int last_desc;

        /* Index of the next RX DMA descriptor to process */
        int next_desc_to_proc;

        /* Index of first RX DMA descriptor to refill */
        int first_to_refill;
        u32 refill_num;
};

static enum cpuhp_state online_hpstate;
/* The hardware supports eight (8) rx queues, but we are only allowing
 * the first one to be used. Therefore, let's just allocate one queue.
 */
static int rxq_number = 8;
static int txq_number = 8;

static int rxq_def;

static int rx_copybreak __read_mostly = 256;

/* HW BM need that each port be identify by a unique ID */
static int global_port_id;

#define MVNETA_DRIVER_NAME "mvneta"
#define MVNETA_DRIVER_VERSION "1.0"

/* Utility/helper methods */

/* Write helper method */
static void mvreg_write(struct mvneta_port *pp, u32 offset, u32 data)
{
        writel(data, pp->base + offset);
}

/* Read helper method */
static u32 mvreg_read(struct mvneta_port *pp, u32 offset)
{
        return readl(pp->base + offset);
}

/* Increment txq get counter */
static void mvneta_txq_inc_get(struct mvneta_tx_queue *txq)
{
        txq->txq_get_index++;
        if (txq->txq_get_index == txq->size)
                txq->txq_get_index = 0;
}

/* Increment txq put counter */
static void mvneta_txq_inc_put(struct mvneta_tx_queue *txq)
{
        txq->txq_put_index++;
        if (txq->txq_put_index == txq->size)
                txq->txq_put_index = 0;
}


/* Clear all MIB counters */
static void mvneta_mib_counters_clear(struct mvneta_port *pp)
{
        int i;

        /* Perform dummy reads from MIB counters */
        for (i = 0; i < MVNETA_MIB_LATE_COLLISION; i += 4)
                mvreg_read(pp, (MVNETA_MIB_COUNTERS_BASE + i));
        mvreg_read(pp, MVNETA_RX_DISCARD_FRAME_COUNT);
        mvreg_read(pp, MVNETA_OVERRUN_FRAME_COUNT);
}

/* Get System Network Statistics */
static void
mvneta_get_stats64(struct net_device *dev,
                   struct rtnl_link_stats64 *stats)
{
        struct mvneta_port *pp = netdev_priv(dev);
        unsigned int start;
        int cpu;

        for_each_possible_cpu(cpu) {
                struct mvneta_pcpu_stats *cpu_stats;
                u64 rx_packets;
                u64 rx_bytes;
                u64 rx_dropped;
                u64 rx_errors;
                u64 tx_packets;
                u64 tx_bytes;

                cpu_stats = per_cpu_ptr(pp->stats, cpu);
                do {
                        start = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
                        rx_packets = cpu_stats->es.ps.rx_packets;
                        rx_bytes   = cpu_stats->es.ps.rx_bytes;
                        rx_dropped = cpu_stats->rx_dropped;
                        rx_errors  = cpu_stats->rx_errors;
                        tx_packets = cpu_stats->es.ps.tx_packets;
                        tx_bytes   = cpu_stats->es.ps.tx_bytes;
                } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start));

                stats->rx_packets += rx_packets;
                stats->rx_bytes   += rx_bytes;
                stats->rx_dropped += rx_dropped;
                stats->rx_errors  += rx_errors;
                stats->tx_packets += tx_packets;
                stats->tx_bytes   += tx_bytes;
        }

        stats->tx_dropped       = dev->stats.tx_dropped;
}

/* Rx descriptors helper methods */

/* Checks whether the RX descriptor having this status is both the first
 * and the last descriptor for the RX packet. Each RX packet is currently
 * received through a single RX descriptor, so not having each RX
 * descriptor with its first and last bits set is an error
 */
static int mvneta_rxq_desc_is_first_last(u32 status)
{
        return (status & MVNETA_RXD_FIRST_LAST_DESC) ==
                MVNETA_RXD_FIRST_LAST_DESC;
}

/* Add number of descriptors ready to receive new packets */
static void mvneta_rxq_non_occup_desc_add(struct mvneta_port *pp,
                                          struct mvneta_rx_queue *rxq,
                                          int ndescs)
{
        /* Only MVNETA_RXQ_ADD_NON_OCCUPIED_MAX (255) descriptors can
         * be added at once
         */
        while (ndescs > MVNETA_RXQ_ADD_NON_OCCUPIED_MAX) {
                mvreg_write(pp, MVNETA_RXQ_STATUS_UPDATE_REG(rxq->id),
                            (MVNETA_RXQ_ADD_NON_OCCUPIED_MAX <<
                             MVNETA_RXQ_ADD_NON_OCCUPIED_SHIFT));
                ndescs -= MVNETA_RXQ_ADD_NON_OCCUPIED_MAX;
        }

        mvreg_write(pp, MVNETA_RXQ_STATUS_UPDATE_REG(rxq->id),
                    (ndescs << MVNETA_RXQ_ADD_NON_OCCUPIED_SHIFT));
}

/* Get number of RX descriptors occupied by received packets */
static int mvneta_rxq_busy_desc_num_get(struct mvneta_port *pp,
                                        struct mvneta_rx_queue *rxq)
{
        u32 val;

        val = mvreg_read(pp, MVNETA_RXQ_STATUS_REG(rxq->id));
        return val & MVNETA_RXQ_OCCUPIED_ALL_MASK;
}

/* Update num of rx desc called upon return from rx path or
 * from mvneta_rxq_drop_pkts().
 */
static void mvneta_rxq_desc_num_update(struct mvneta_port *pp,
                                       struct mvneta_rx_queue *rxq,
                                       int rx_done, int rx_filled)
{
        u32 val;

        if ((rx_done <= 0xff) && (rx_filled <= 0xff)) {
                val = rx_done |
                  (rx_filled << MVNETA_RXQ_ADD_NON_OCCUPIED_SHIFT);
                mvreg_write(pp, MVNETA_RXQ_STATUS_UPDATE_REG(rxq->id), val);
                return;
        }

        /* Only 255 descriptors can be added at once */
        while ((rx_done > 0) || (rx_filled > 0)) {
                if (rx_done <= 0xff) {
                        val = rx_done;
                        rx_done = 0;
                } else {
                        val = 0xff;
                        rx_done -= 0xff;
                }
                if (rx_filled <= 0xff) {
                        val |= rx_filled << MVNETA_RXQ_ADD_NON_OCCUPIED_SHIFT;
                        rx_filled = 0;
                } else {
                        val |= 0xff << MVNETA_RXQ_ADD_NON_OCCUPIED_SHIFT;
                        rx_filled -= 0xff;
                }
                mvreg_write(pp, MVNETA_RXQ_STATUS_UPDATE_REG(rxq->id), val);
        }
}

/* Get pointer to next RX descriptor to be processed by SW */
static struct mvneta_rx_desc *
mvneta_rxq_next_desc_get(struct mvneta_rx_queue *rxq)
{
        int rx_desc = rxq->next_desc_to_proc;

        rxq->next_desc_to_proc = MVNETA_QUEUE_NEXT_DESC(rxq, rx_desc);
        prefetch(rxq->descs + rxq->next_desc_to_proc);
        return rxq->descs + rx_desc;
}

/* Change maximum receive size of the port. */
static void mvneta_max_rx_size_set(struct mvneta_port *pp, int max_rx_size)
{
        u32 val;

        val =  mvreg_read(pp, MVNETA_GMAC_CTRL_0);
        val &= ~MVNETA_GMAC_MAX_RX_SIZE_MASK;
        val |= ((max_rx_size - MVNETA_MH_SIZE) / 2) <<
                MVNETA_GMAC_MAX_RX_SIZE_SHIFT;
        mvreg_write(pp, MVNETA_GMAC_CTRL_0, val);
}


/* Set rx queue offset */
static void mvneta_rxq_offset_set(struct mvneta_port *pp,
                                  struct mvneta_rx_queue *rxq,
                                  int offset)
{
        u32 val;

        val = mvreg_read(pp, MVNETA_RXQ_CONFIG_REG(rxq->id));
        val &= ~MVNETA_RXQ_PKT_OFFSET_ALL_MASK;

        /* Offset is in */
        val |= MVNETA_RXQ_PKT_OFFSET_MASK(offset >> 3);
        mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
}


/* Tx descriptors helper methods */

/* Update HW with number of TX descriptors to be sent */
static void mvneta_txq_pend_desc_add(struct mvneta_port *pp,
                                     struct mvneta_tx_queue *txq,
                                     int pend_desc)
{
        u32 val;

        pend_desc += txq->pending;

        /* Only 255 Tx descriptors can be added at once */
        do {
                val = min(pend_desc, 255);
                mvreg_write(pp, MVNETA_TXQ_UPDATE_REG(txq->id), val);
                pend_desc -= val;
        } while (pend_desc > 0);
        txq->pending = 0;
}

/* Get pointer to next TX descriptor to be processed (send) by HW */
static struct mvneta_tx_desc *
mvneta_txq_next_desc_get(struct mvneta_tx_queue *txq)
{
        int tx_desc = txq->next_desc_to_proc;

        txq->next_desc_to_proc = MVNETA_QUEUE_NEXT_DESC(txq, tx_desc);
        return txq->descs + tx_desc;
}

/* Release the last allocated TX descriptor. Useful to handle DMA
 * mapping failures in the TX path.
 */
static void mvneta_txq_desc_put(struct mvneta_tx_queue *txq)
{
        if (txq->next_desc_to_proc == 0)
                txq->next_desc_to_proc = txq->last_desc - 1;
        else
                txq->next_desc_to_proc--;
}

/* Set rxq buf size */
static void mvneta_rxq_buf_size_set(struct mvneta_port *pp,
                                    struct mvneta_rx_queue *rxq,
                                    int buf_size)
{
        u32 val;

        val = mvreg_read(pp, MVNETA_RXQ_SIZE_REG(rxq->id));

        val &= ~MVNETA_RXQ_BUF_SIZE_MASK;
        val |= ((buf_size >> 3) << MVNETA_RXQ_BUF_SIZE_SHIFT);

        mvreg_write(pp, MVNETA_RXQ_SIZE_REG(rxq->id), val);
}

/* Disable buffer management (BM) */
static void mvneta_rxq_bm_disable(struct mvneta_port *pp,
                                  struct mvneta_rx_queue *rxq)
{
        u32 val;

        val = mvreg_read(pp, MVNETA_RXQ_CONFIG_REG(rxq->id));
        val &= ~MVNETA_RXQ_HW_BUF_ALLOC;
        mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
}

/* Enable buffer management (BM) */
static void mvneta_rxq_bm_enable(struct mvneta_port *pp,
                                 struct mvneta_rx_queue *rxq)
{
        u32 val;

        val = mvreg_read(pp, MVNETA_RXQ_CONFIG_REG(rxq->id));
        val |= MVNETA_RXQ_HW_BUF_ALLOC;
        mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
}

/* Notify HW about port's assignment of pool for bigger packets */
static void mvneta_rxq_long_pool_set(struct mvneta_port *pp,
                                     struct mvneta_rx_queue *rxq)

{
        u32 val;

        val = mvreg_read(pp, MVNETA_RXQ_CONFIG_REG(rxq->id));
        val &= ~MVNETA_RXQ_LONG_POOL_ID_MASK;
        val |= (pp->pool_long->id << MVNETA_RXQ_LONG_POOL_ID_SHIFT);

        mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
}

/* Notify HW about port's assignment of pool for smaller packets */
static void mvneta_rxq_short_pool_set(struct mvneta_port *pp,
                                      struct mvneta_rx_queue *rxq)
{
        u32 val;

        val = mvreg_read(pp, MVNETA_RXQ_CONFIG_REG(rxq->id));
        val &= ~MVNETA_RXQ_SHORT_POOL_ID_MASK;
        val |= (pp->pool_short->id << MVNETA_RXQ_SHORT_POOL_ID_SHIFT);

        mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
}

/* Set port's receive buffer size for assigned BM pool */
static inline void mvneta_bm_pool_bufsize_set(struct mvneta_port *pp,
                                              int buf_size,
                                              u8 pool_id)
{
        u32 val;

        if (!IS_ALIGNED(buf_size, 8)) {
                dev_warn(pp->dev->dev.parent,
                         "illegal buf_size value %d, round to %d\n",
                         buf_size, ALIGN(buf_size, 8));
                buf_size = ALIGN(buf_size, 8);
        }

        val = mvreg_read(pp, MVNETA_PORT_POOL_BUFFER_SZ_REG(pool_id));
        val |= buf_size & MVNETA_PORT_POOL_BUFFER_SZ_MASK;
        mvreg_write(pp, MVNETA_PORT_POOL_BUFFER_SZ_REG(pool_id), val);
}

/* Configure MBUS window in order to enable access BM internal SRAM */
static int mvneta_mbus_io_win_set(struct mvneta_port *pp, u32 base, u32 wsize,
                                  u8 target, u8 attr)
{
        u32 win_enable, win_protect;
        int i;

        win_enable = mvreg_read(pp, MVNETA_BASE_ADDR_ENABLE);

        if (pp->bm_win_id < 0) {
                /* Find first not occupied window */
                for (i = 0; i < MVNETA_MAX_DECODE_WIN; i++) {
                        if (win_enable & (1 << i)) {
                                pp->bm_win_id = i;
                                break;
                        }
                }
                if (i == MVNETA_MAX_DECODE_WIN)
                        return -ENOMEM;
        } else {
                i = pp->bm_win_id;
        }

        mvreg_write(pp, MVNETA_WIN_BASE(i), 0);
        mvreg_write(pp, MVNETA_WIN_SIZE(i), 0);

        if (i < 4)
                mvreg_write(pp, MVNETA_WIN_REMAP(i), 0);

        mvreg_write(pp, MVNETA_WIN_BASE(i), (base & 0xffff0000) |
                    (attr << 8) | target);

        mvreg_write(pp, MVNETA_WIN_SIZE(i), (wsize - 1) & 0xffff0000);

        win_protect = mvreg_read(pp, MVNETA_ACCESS_PROTECT_ENABLE);
        win_protect |= 3 << (2 * i);
        mvreg_write(pp, MVNETA_ACCESS_PROTECT_ENABLE, win_protect);

        win_enable &= ~(1 << i);
        mvreg_write(pp, MVNETA_BASE_ADDR_ENABLE, win_enable);

        return 0;
}

static  int mvneta_bm_port_mbus_init(struct mvneta_port *pp)
{
        u32 wsize;
        u8 target, attr;
        int err;

        /* Get BM window information */
        err = mvebu_mbus_get_io_win_info(pp->bm_priv->bppi_phys_addr, &wsize,
                                         &target, &attr);
        if (err < 0)
                return err;

        pp->bm_win_id = -1;

        /* Open NETA -> BM window */
        err = mvneta_mbus_io_win_set(pp, pp->bm_priv->bppi_phys_addr, wsize,
                                     target, attr);
        if (err < 0) {
                netdev_info(pp->dev, "fail to configure mbus window to BM\n");
                return err;
        }
        return 0;
}

/* Assign and initialize pools for port. In case of fail
 * buffer manager will remain disabled for current port.
 */
static int mvneta_bm_port_init(struct platform_device *pdev,
                               struct mvneta_port *pp)
{
        struct device_node *dn = pdev->dev.of_node;
        u32 long_pool_id, short_pool_id;

        if (!pp->neta_armada3700) {
                int ret;

                ret = mvneta_bm_port_mbus_init(pp);
                if (ret)
                        return ret;
        }

        if (of_property_read_u32(dn, "bm,pool-long", &long_pool_id)) {
                netdev_info(pp->dev, "missing long pool id\n");
                return -EINVAL;
        }

        /* Create port's long pool depending on mtu */
        pp->pool_long = mvneta_bm_pool_use(pp->bm_priv, long_pool_id,
                                           MVNETA_BM_LONG, pp->id,
                                           MVNETA_RX_PKT_SIZE(pp->dev->mtu));
        if (!pp->pool_long) {
                netdev_info(pp->dev, "fail to obtain long pool for port\n");
                return -ENOMEM;
        }

        pp->pool_long->port_map |= 1 << pp->id;

        mvneta_bm_pool_bufsize_set(pp, pp->pool_long->buf_size,
                                   pp->pool_long->id);

        /* If short pool id is not defined, assume using single pool */
        if (of_property_read_u32(dn, "bm,pool-short", &short_pool_id))
                short_pool_id = long_pool_id;

        /* Create port's short pool */
        pp->pool_short = mvneta_bm_pool_use(pp->bm_priv, short_pool_id,
                                            MVNETA_BM_SHORT, pp->id,
                                            MVNETA_BM_SHORT_PKT_SIZE);
        if (!pp->pool_short) {
                netdev_info(pp->dev, "fail to obtain short pool for port\n");
                mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id);
                return -ENOMEM;
        }

        if (short_pool_id != long_pool_id) {
                pp->pool_short->port_map |= 1 << pp->id;
                mvneta_bm_pool_bufsize_set(pp, pp->pool_short->buf_size,
                                           pp->pool_short->id);
        }

        return 0;
}

/* Update settings of a pool for bigger packets */
static void mvneta_bm_update_mtu(struct mvneta_port *pp, int mtu)
{
        struct mvneta_bm_pool *bm_pool = pp->pool_long;
        struct hwbm_pool *hwbm_pool = &bm_pool->hwbm_pool;
        int num;

        /* Release all buffers from long pool */
        mvneta_bm_bufs_free(pp->bm_priv, bm_pool, 1 << pp->id);
        if (hwbm_pool->buf_num) {
                WARN(1, "cannot free all buffers in pool %d\n",
                     bm_pool->id);
                goto bm_mtu_err;
        }

        bm_pool->pkt_size = MVNETA_RX_PKT_SIZE(mtu);
        bm_pool->buf_size = MVNETA_RX_BUF_SIZE(bm_pool->pkt_size);
        hwbm_pool->frag_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
                        SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(bm_pool->pkt_size));

        /* Fill entire long pool */
        num = hwbm_pool_add(hwbm_pool, hwbm_pool->size);
        if (num != hwbm_pool->size) {
                WARN(1, "pool %d: %d of %d allocated\n",
                     bm_pool->id, num, hwbm_pool->size);
                goto bm_mtu_err;
        }
        mvneta_bm_pool_bufsize_set(pp, bm_pool->buf_size, bm_pool->id);

        return;

bm_mtu_err:
        mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id);
        mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short, 1 << pp->id);

        pp->bm_priv = NULL;
        pp->rx_offset_correction = MVNETA_SKB_HEADROOM;
        mvreg_write(pp, MVNETA_ACC_MODE, MVNETA_ACC_MODE_EXT1);
        netdev_info(pp->dev, "fail to update MTU, fall back to software BM\n");
}

/* Start the Ethernet port RX and TX activity */
static void mvneta_port_up(struct mvneta_port *pp)
{
        int queue;
        u32 q_map;

        /* Enable all initialized TXs. */
        q_map = 0;
        for (queue = 0; queue < txq_number; queue++) {
                struct mvneta_tx_queue *txq = &pp->txqs[queue];
                if (txq->descs)
                        q_map |= (1 << queue);
        }
        mvreg_write(pp, MVNETA_TXQ_CMD, q_map);

        q_map = 0;
        /* Enable all initialized RXQs. */
        for (queue = 0; queue < rxq_number; queue++) {
                struct mvneta_rx_queue *rxq = &pp->rxqs[queue];

                if (rxq->descs)
                        q_map |= (1 << queue);
        }
        mvreg_write(pp, MVNETA_RXQ_CMD, q_map);
}

/* Stop the Ethernet port activity */
static void mvneta_port_down(struct mvneta_port *pp)
{
        u32 val;
        int count;

        /* Stop Rx port activity. Check port Rx activity. */
        val = mvreg_read(pp, MVNETA_RXQ_CMD) & MVNETA_RXQ_ENABLE_MASK;

        /* Issue stop command for active channels only */
        if (val != 0)
                mvreg_write(pp, MVNETA_RXQ_CMD,
                            val << MVNETA_RXQ_DISABLE_SHIFT);

        /* Wait for all Rx activity to terminate. */
        count = 0;
        do {
                if (count++ >= MVNETA_RX_DISABLE_TIMEOUT_MSEC) {
                        netdev_warn(pp->dev,
                                    "TIMEOUT for RX stopped ! rx_queue_cmd: 0x%08x\n",
                                    val);
                        break;
                }
                mdelay(1);

                val = mvreg_read(pp, MVNETA_RXQ_CMD);
        } while (val & MVNETA_RXQ_ENABLE_MASK);

        /* Stop Tx port activity. Check port Tx activity. Issue stop
         * command for active channels only
         */
        val = (mvreg_read(pp, MVNETA_TXQ_CMD)) & MVNETA_TXQ_ENABLE_MASK;

        if (val != 0)
                mvreg_write(pp, MVNETA_TXQ_CMD,
                            (val << MVNETA_TXQ_DISABLE_SHIFT));

        /* Wait for all Tx activity to terminate. */
        count = 0;
        do {
                if (count++ >= MVNETA_TX_DISABLE_TIMEOUT_MSEC) {
                        netdev_warn(pp->dev,
                                    "TIMEOUT for TX stopped status=0x%08x\n",
                                    val);
                        break;
                }
                mdelay(1);

                /* Check TX Command reg that all Txqs are stopped */
                val = mvreg_read(pp, MVNETA_TXQ_CMD);

        } while (val & MVNETA_TXQ_ENABLE_MASK);

        /* Double check to verify that TX FIFO is empty */
        count = 0;
        do {
                if (count++ >= MVNETA_TX_FIFO_EMPTY_TIMEOUT) {
                        netdev_warn(pp->dev,
                                    "TX FIFO empty timeout status=0x%08x\n",
                                    val);
                        break;
                }
                mdelay(1);

                val = mvreg_read(pp, MVNETA_PORT_STATUS);
        } while (!(val & MVNETA_TX_FIFO_EMPTY) &&
                 (val & MVNETA_TX_IN_PRGRS));

        udelay(200);
}

/* Enable the port by setting the port enable bit of the MAC control register */
static void mvneta_port_enable(struct mvneta_port *pp)
{
        u32 val;

        /* Enable port */
        val = mvreg_read(pp, MVNETA_GMAC_CTRL_0);
        val |= MVNETA_GMAC0_PORT_ENABLE;
        mvreg_write(pp, MVNETA_GMAC_CTRL_0, val);
}

/* Disable the port and wait for about 200 usec before retuning */
static void mvneta_port_disable(struct mvneta_port *pp)
{
        u32 val;

        /* Reset the Enable bit in the Serial Control Register */
        val = mvreg_read(pp, MVNETA_GMAC_CTRL_0);
        val &= ~MVNETA_GMAC0_PORT_ENABLE;
        mvreg_write(pp, MVNETA_GMAC_CTRL_0, val);

        udelay(200);
}

/* Multicast tables methods */

/* Set all entries in Unicast MAC Table; queue==-1 means reject all */
static void mvneta_set_ucast_table(struct mvneta_port *pp, int queue)
{
        int offset;
        u32 val;

        if (queue == -1) {
                val = 0;
        } else {
                val = 0x1 | (queue << 1);
                val |= (val << 24) | (val << 16) | (val << 8);
        }

        for (offset = 0; offset <= 0xc; offset += 4)
                mvreg_write(pp, MVNETA_DA_FILT_UCAST_BASE + offset, val);
}

/* Set all entries in Special Multicast MAC Table; queue==-1 means reject all */
static void mvneta_set_special_mcast_table(struct mvneta_port *pp, int queue)
{
        int offset;
        u32 val;

        if (queue == -1) {
                val = 0;
        } else {
                val = 0x1 | (queue << 1);
                val |= (val << 24) | (val << 16) | (val << 8);
        }

        for (offset = 0; offset <= 0xfc; offset += 4)
                mvreg_write(pp, MVNETA_DA_FILT_SPEC_MCAST + offset, val);

}

/* Set all entries in Other Multicast MAC Table. queue==-1 means reject all */
static void mvneta_set_other_mcast_table(struct mvneta_port *pp, int queue)
{
        int offset;
        u32 val;

        if (queue == -1) {
                memset(pp->mcast_count, 0, sizeof(pp->mcast_count));
                val = 0;
        } else {
                memset(pp->mcast_count, 1, sizeof(pp->mcast_count));
                val = 0x1 | (queue << 1);
                val |= (val << 24) | (val << 16) | (val << 8);
        }

        for (offset = 0; offset <= 0xfc; offset += 4)
                mvreg_write(pp, MVNETA_DA_FILT_OTH_MCAST + offset, val);
}

static void mvneta_percpu_unmask_interrupt(void *arg)
{
        struct mvneta_port *pp = arg;

        /* All the queue are unmasked, but actually only the ones
         * mapped to this CPU will be unmasked
         */
        mvreg_write(pp, MVNETA_INTR_NEW_MASK,
                    MVNETA_RX_INTR_MASK_ALL |
                    MVNETA_TX_INTR_MASK_ALL |
                    MVNETA_MISCINTR_INTR_MASK);
}

static void mvneta_percpu_mask_interrupt(void *arg)
{
        struct mvneta_port *pp = arg;

        /* All the queue are masked, but actually only the ones
         * mapped to this CPU will be masked
         */
        mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
        mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
        mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
}

static void mvneta_percpu_clear_intr_cause(void *arg)
{
        struct mvneta_port *pp = arg;

        /* All the queue are cleared, but actually only the ones
         * mapped to this CPU will be cleared
         */
        mvreg_write(pp, MVNETA_INTR_NEW_CAUSE, 0);
        mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0);
        mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0);
}

/* This method sets defaults to the NETA port:
 *      Clears interrupt Cause and Mask registers.
 *      Clears all MAC tables.
 *      Sets defaults to all registers.
 *      Resets RX and TX descriptor rings.
 *      Resets PHY.
 * This method can be called after mvneta_port_down() to return the port
 *      settings to defaults.
 */
static void mvneta_defaults_set(struct mvneta_port *pp)
{
        int cpu;
        int queue;
        u32 val;
        int max_cpu = num_present_cpus();

        /* Clear all Cause registers */
        on_each_cpu(mvneta_percpu_clear_intr_cause, pp, true);

        /* Mask all interrupts */
        on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
        mvreg_write(pp, MVNETA_INTR_ENABLE, 0);

        /* Enable MBUS Retry bit16 */
        mvreg_write(pp, MVNETA_MBUS_RETRY, 0x20);

        /* Set CPU queue access map. CPUs are assigned to the RX and
         * TX queues modulo their number. If there is only one TX
         * queue then it is assigned to the CPU associated to the
         * default RX queue.
         */
        for_each_present_cpu(cpu) {
                int rxq_map = 0, txq_map = 0;
                int rxq, txq;
                if (!pp->neta_armada3700) {
                        for (rxq = 0; rxq < rxq_number; rxq++)
                                if ((rxq % max_cpu) == cpu)
                                        rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);

                        for (txq = 0; txq < txq_number; txq++)
                                if ((txq % max_cpu) == cpu)
                                        txq_map |= MVNETA_CPU_TXQ_ACCESS(txq);

                        /* With only one TX queue we configure a special case
                         * which will allow to get all the irq on a single
                         * CPU
                         */
                        if (txq_number == 1)
                                txq_map = (cpu == pp->rxq_def) ?
                                        MVNETA_CPU_TXQ_ACCESS(1) : 0;

                } else {
                        txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
                        rxq_map = MVNETA_CPU_RXQ_ACCESS_ALL_MASK;
                }

                mvreg_write(pp, MVNETA_CPU_MAP(cpu), rxq_map | txq_map);
        }

        /* Reset RX and TX DMAs */
        mvreg_write(pp, MVNETA_PORT_RX_RESET, MVNETA_PORT_RX_DMA_RESET);
        mvreg_write(pp, MVNETA_PORT_TX_RESET, MVNETA_PORT_TX_DMA_RESET);

        /* Disable Legacy WRR, Disable EJP, Release from reset */
        mvreg_write(pp, MVNETA_TXQ_CMD_1, 0);
        for (queue = 0; queue < txq_number; queue++) {
                mvreg_write(pp, MVETH_TXQ_TOKEN_COUNT_REG(queue), 0);
                mvreg_write(pp, MVETH_TXQ_TOKEN_CFG_REG(queue), 0);
        }

        mvreg_write(pp, MVNETA_PORT_TX_RESET, 0);
        mvreg_write(pp, MVNETA_PORT_RX_RESET, 0);

        /* Set Port Acceleration Mode */
        if (pp->bm_priv)
                /* HW buffer management + legacy parser */
                val = MVNETA_ACC_MODE_EXT2;
        else
                /* SW buffer management + legacy parser */
                val = MVNETA_ACC_MODE_EXT1;
        mvreg_write(pp, MVNETA_ACC_MODE, val);

        if (pp->bm_priv)
                mvreg_write(pp, MVNETA_BM_ADDRESS, pp->bm_priv->bppi_phys_addr);

        /* Update val of portCfg register accordingly with all RxQueue types */
        val = MVNETA_PORT_CONFIG_DEFL_VALUE(pp->rxq_def);
        mvreg_write(pp, MVNETA_PORT_CONFIG, val);

        val = 0;
        mvreg_write(pp, MVNETA_PORT_CONFIG_EXTEND, val);
        mvreg_write(pp, MVNETA_RX_MIN_FRAME_SIZE, 64);

        /* Build PORT_SDMA_CONFIG_REG */
        val = 0;

        /* Default burst size */
        val |= MVNETA_TX_BRST_SZ_MASK(MVNETA_SDMA_BRST_SIZE_16);
        val |= MVNETA_RX_BRST_SZ_MASK(MVNETA_SDMA_BRST_SIZE_16);
        val |= MVNETA_RX_NO_DATA_SWAP | MVNETA_TX_NO_DATA_SWAP;

#if defined(__BIG_ENDIAN)
        val |= MVNETA_DESC_SWAP;
#endif

        /* Assign port SDMA configuration */
        mvreg_write(pp, MVNETA_SDMA_CONFIG, val);

        /* Disable PHY polling in hardware, since we're using the
         * kernel phylib to do this.
         */
        val = mvreg_read(pp, MVNETA_UNIT_CONTROL);
        val &= ~MVNETA_PHY_POLLING_ENABLE;
        mvreg_write(pp, MVNETA_UNIT_CONTROL, val);

        mvneta_set_ucast_table(pp, -1);
        mvneta_set_special_mcast_table(pp, -1);
        mvneta_set_other_mcast_table(pp, -1);

        /* Set port interrupt enable register - default enable all */
        mvreg_write(pp, MVNETA_INTR_ENABLE,
                    (MVNETA_RXQ_INTR_ENABLE_ALL_MASK
                     | MVNETA_TXQ_INTR_ENABLE_ALL_MASK));

        mvneta_mib_counters_clear(pp);
}

/* Set max sizes for tx queues */
static void mvneta_txq_max_tx_size_set(struct mvneta_port *pp, int max_tx_size)

{
        u32 val, size, mtu;
        int queue;

        mtu = max_tx_size * 8;
        if (mtu > MVNETA_TX_MTU_MAX)
                mtu = MVNETA_TX_MTU_MAX;

        /* Set MTU */
        val = mvreg_read(pp, MVNETA_TX_MTU);
        val &= ~MVNETA_TX_MTU_MAX;
        val |= mtu;
        mvreg_write(pp, MVNETA_TX_MTU, val);

        /* TX token size and all TXQs token size must be larger that MTU */
        val = mvreg_read(pp, MVNETA_TX_TOKEN_SIZE);

        size = val & MVNETA_TX_TOKEN_SIZE_MAX;
        if (size < mtu) {
                size = mtu;
                val &= ~MVNETA_TX_TOKEN_SIZE_MAX;
                val |= size;
                mvreg_write(pp, MVNETA_TX_TOKEN_SIZE, val);
        }
        for (queue = 0; queue < txq_number; queue++) {
                val = mvreg_read(pp, MVNETA_TXQ_TOKEN_SIZE_REG(queue));

                size = val & MVNETA_TXQ_TOKEN_SIZE_MAX;
                if (size < mtu) {
                        size = mtu;
                        val &= ~MVNETA_TXQ_TOKEN_SIZE_MAX;
                        val |= size;
                        mvreg_write(pp, MVNETA_TXQ_TOKEN_SIZE_REG(queue), val);
                }
        }
}

/* Set unicast address */
static void mvneta_set_ucast_addr(struct mvneta_port *pp, u8 last_nibble,
                                  int queue)
{
        unsigned int unicast_reg;
        unsigned int tbl_offset;
        unsigned int reg_offset;

        /* Locate the Unicast table entry */
        last_nibble = (0xf & last_nibble);

        /* offset from unicast tbl base */
        tbl_offset = (last_nibble / 4) * 4;

        /* offset within the above reg  */
        reg_offset = last_nibble % 4;

        unicast_reg = mvreg_read(pp, (MVNETA_DA_FILT_UCAST_BASE + tbl_offset));

        if (queue == -1) {
                /* Clear accepts frame bit at specified unicast DA tbl entry */
                unicast_reg &= ~(0xff << (8 * reg_offset));
        } else {
                unicast_reg &= ~(0xff << (8 * reg_offset));
                unicast_reg |= ((0x01 | (queue << 1)) << (8 * reg_offset));
        }

        mvreg_write(pp, (MVNETA_DA_FILT_UCAST_BASE + tbl_offset), unicast_reg);
}

/* Set mac address */
static void mvneta_mac_addr_set(struct mvneta_port *pp, unsigned char *addr,
                                int queue)
{
        unsigned int mac_h;
        unsigned int mac_l;

        if (queue != -1) {
                mac_l = (addr[4] << 8) | (addr[5]);
                mac_h = (addr[0] << 24) | (addr[1] << 16) |
                        (addr[2] << 8) | (addr[3] << 0);

                mvreg_write(pp, MVNETA_MAC_ADDR_LOW, mac_l);
                mvreg_write(pp, MVNETA_MAC_ADDR_HIGH, mac_h);
        }

        /* Accept frames of this address */
        mvneta_set_ucast_addr(pp, addr[5], queue);
}

/* Set the number of packets that will be received before RX interrupt
 * will be generated by HW.
 */
static void mvneta_rx_pkts_coal_set(struct mvneta_port *pp,
                                    struct mvneta_rx_queue *rxq, u32 value)
{
        mvreg_write(pp, MVNETA_RXQ_THRESHOLD_REG(rxq->id),
                    value | MVNETA_RXQ_NON_OCCUPIED(0));
}

/* Set the time delay in usec before RX interrupt will be generated by
 * HW.
 */
static void mvneta_rx_time_coal_set(struct mvneta_port *pp,
                                    struct mvneta_rx_queue *rxq, u32 value)
{
        u32 val;
        unsigned long clk_rate;

        clk_rate = clk_get_rate(pp->clk);
        val = (clk_rate / 1000000) * value;

        mvreg_write(pp, MVNETA_RXQ_TIME_COAL_REG(rxq->id), val);
}

/* Set threshold for TX_DONE pkts coalescing */
static void mvneta_tx_done_pkts_coal_set(struct mvneta_port *pp,
                                         struct mvneta_tx_queue *txq, u32 value)
{
        u32 val;

        val = mvreg_read(pp, MVNETA_TXQ_SIZE_REG(txq->id));

        val &= ~MVNETA_TXQ_SENT_THRESH_ALL_MASK;
        val |= MVNETA_TXQ_SENT_THRESH_MASK(value);

        mvreg_write(pp, MVNETA_TXQ_SIZE_REG(txq->id), val);
}

/* Handle rx descriptor fill by setting buf_cookie and buf_phys_addr */
static void mvneta_rx_desc_fill(struct mvneta_rx_desc *rx_desc,
                                u32 phys_addr, void *virt_addr,
                                struct mvneta_rx_queue *rxq)
{
        int i;

        rx_desc->buf_phys_addr = phys_addr;
        i = rx_desc - rxq->descs;
        rxq->buf_virt_addr[i] = virt_addr;
}

/* Decrement sent descriptors counter */
static void mvneta_txq_sent_desc_dec(struct mvneta_port *pp,
                                     struct mvneta_tx_queue *txq,
                                     int sent_desc)
{
        u32 val;

        /* Only 255 TX descriptors can be updated at once */
        while (sent_desc > 0xff) {
                val = 0xff << MVNETA_TXQ_DEC_SENT_SHIFT;
                mvreg_write(pp, MVNETA_TXQ_UPDATE_REG(txq->id), val);
                sent_desc = sent_desc - 0xff;
        }

        val = sent_desc << MVNETA_TXQ_DEC_SENT_SHIFT;
        mvreg_write(pp, MVNETA_TXQ_UPDATE_REG(txq->id), val);
}

/* Get number of TX descriptors already sent by HW */
static int mvneta_txq_sent_desc_num_get(struct mvneta_port *pp,
                                        struct mvneta_tx_queue *txq)
{
        u32 val;
        int sent_desc;

        val = mvreg_read(pp, MVNETA_TXQ_STATUS_REG(txq->id));
        sent_desc = (val & MVNETA_TXQ_SENT_DESC_MASK) >>
                MVNETA_TXQ_SENT_DESC_SHIFT;

        return sent_desc;
}

/* Get number of sent descriptors and decrement counter.
 *  The number of sent descriptors is returned.
 */
static int mvneta_txq_sent_desc_proc(struct mvneta_port *pp,
                                     struct mvneta_tx_queue *txq)
{
        int sent_desc;

        /* Get number of sent descriptors */
        sent_desc = mvneta_txq_sent_desc_num_get(pp, txq);

        /* Decrement sent descriptors counter */
        if (sent_desc)
                mvneta_txq_sent_desc_dec(pp, txq, sent_desc);

        return sent_desc;
}

/* Set TXQ descriptors fields relevant for CSUM calculation */
static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto,
                                int ip_hdr_len, int l4_proto)
{
        u32 command;

        /* Fields: L3_offset, IP_hdrlen, L3_type, G_IPv4_chk,
         * G_L4_chk, L4_type; required only for checksum
         * calculation
         */
        command =  l3_offs    << MVNETA_TX_L3_OFF_SHIFT;
        command |= ip_hdr_len << MVNETA_TX_IP_HLEN_SHIFT;

        if (l3_proto == htons(ETH_P_IP))
                command |= MVNETA_TXD_IP_CSUM;
        else
                command |= MVNETA_TX_L3_IP6;

        if (l4_proto == IPPROTO_TCP)
                command |=  MVNETA_TX_L4_CSUM_FULL;
        else if (l4_proto == IPPROTO_UDP)
                command |= MVNETA_TX_L4_UDP | MVNETA_TX_L4_CSUM_FULL;
        else
                command |= MVNETA_TX_L4_CSUM_NOT;

        return command;
}


/* Display more error info */
static void mvneta_rx_error(struct mvneta_port *pp,
                            struct mvneta_rx_desc *rx_desc)
{
        struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
        u32 status = rx_desc->status;

        /* update per-cpu counter */
        u64_stats_update_begin(&stats->syncp);
        stats->rx_errors++;
        u64_stats_update_end(&stats->syncp);

        switch (status & MVNETA_RXD_ERR_CODE_MASK) {
        case MVNETA_RXD_ERR_CRC:
                netdev_err(pp->dev, "bad rx status %08x (crc error), size=%d\n",
                           status, rx_desc->data_size);
                break;
        case MVNETA_RXD_ERR_OVERRUN:
                netdev_err(pp->dev, "bad rx status %08x (overrun error), size=%d\n",
                           status, rx_desc->data_size);
                break;
        case MVNETA_RXD_ERR_LEN:
                netdev_err(pp->dev, "bad rx status %08x (max frame length error), size=%d\n",
                           status, rx_desc->data_size);
                break;
        case MVNETA_RXD_ERR_RESOURCE:
                netdev_err(pp->dev, "bad rx status %08x (resource error), size=%d\n",
                           status, rx_desc->data_size);
                break;
        }
}

/* Handle RX checksum offload based on the descriptor's status */
static void mvneta_rx_csum(struct mvneta_port *pp, u32 status,
                           struct sk_buff *skb)
{
        if ((pp->dev->features & NETIF_F_RXCSUM) &&
            (status & MVNETA_RXD_L3_IP4) &&
            (status & MVNETA_RXD_L4_CSUM_OK)) {
                skb->csum = 0;
                skb->ip_summed = CHECKSUM_UNNECESSARY;
                return;
        }

        skb->ip_summed = CHECKSUM_NONE;
}

/* Return tx queue pointer (find last set bit) according to <cause> returned
 * form tx_done reg. <cause> must not be null. The return value is always a
 * valid queue for matching the first one found in <cause>.
 */
static struct mvneta_tx_queue *mvneta_tx_done_policy(struct mvneta_port *pp,
                                                     u32 cause)
{
        int queue = fls(cause) - 1;

        return &pp->txqs[queue];
}

/* Free tx queue skbuffs */
static void mvneta_txq_bufs_free(struct mvneta_port *pp,
                                 struct mvneta_tx_queue *txq, int num,
                                 struct netdev_queue *nq, bool napi)
{
        unsigned int bytes_compl = 0, pkts_compl = 0;
        struct xdp_frame_bulk bq;
        int i;

        xdp_frame_bulk_init(&bq);

        rcu_read_lock(); /* need for xdp_return_frame_bulk */

        for (i = 0; i < num; i++) {
                struct mvneta_tx_buf *buf = &txq->buf[txq->txq_get_index];
                struct mvneta_tx_desc *tx_desc = txq->descs +
                        txq->txq_get_index;

                mvneta_txq_inc_get(txq);

                if (!IS_TSO_HEADER(txq, tx_desc->buf_phys_addr) &&
                    buf->type != MVNETA_TYPE_XDP_TX)
                        dma_unmap_single(pp->dev->dev.parent,
                                         tx_desc->buf_phys_addr,
                                         tx_desc->data_size, DMA_TO_DEVICE);
                if (buf->type == MVNETA_TYPE_SKB && buf->skb) {
                        bytes_compl += buf->skb->len;
                        pkts_compl++;
                        dev_kfree_skb_any(buf->skb);
                } else if (buf->type == MVNETA_TYPE_XDP_TX ||
                           buf->type == MVNETA_TYPE_XDP_NDO) {
                        if (napi && buf->type == MVNETA_TYPE_XDP_TX)
                                xdp_return_frame_rx_napi(buf->xdpf);
                        else
                                xdp_return_frame_bulk(buf->xdpf, &bq);
                }
        }
        xdp_flush_frame_bulk(&bq);

        rcu_read_unlock();

        netdev_tx_completed_queue(nq, pkts_compl, bytes_compl);
}

/* Handle end of transmission */
static void mvneta_txq_done(struct mvneta_port *pp,
                           struct mvneta_tx_queue *txq)
{
        struct netdev_queue *nq = netdev_get_tx_queue(pp->dev, txq->id);
        int tx_done;

        tx_done = mvneta_txq_sent_desc_proc(pp, txq);
        if (!tx_done)
                return;

        mvneta_txq_bufs_free(pp, txq, tx_done, nq, true);

        txq->count -= tx_done;

        if (netif_tx_queue_stopped(nq)) {
                if (txq->count <= txq->tx_wake_threshold)
                        netif_tx_wake_queue(nq);
        }
}

/* Refill processing for SW buffer management */
/* Allocate page per descriptor */
static int mvneta_rx_refill(struct mvneta_port *pp,
                            struct mvneta_rx_desc *rx_desc,
                            struct mvneta_rx_queue *rxq,
                            gfp_t gfp_mask)
{
        dma_addr_t phys_addr;
        struct page *page;

        page = page_pool_alloc_pages(rxq->page_pool,
                                     gfp_mask | __GFP_NOWARN);
        if (!page)
                return -ENOMEM;

        phys_addr = page_pool_get_dma_addr(page) + pp->rx_offset_correction;
        mvneta_rx_desc_fill(rx_desc, phys_addr, page, rxq);

        return 0;
}

/* Handle tx checksum */
static u32 mvneta_skb_tx_csum(struct mvneta_port *pp, struct sk_buff *skb)
{
        if (skb->ip_summed == CHECKSUM_PARTIAL) {
                int ip_hdr_len = 0;
                __be16 l3_proto = vlan_get_protocol(skb);
                u8 l4_proto;

                if (l3_proto == htons(ETH_P_IP)) {
                        struct iphdr *ip4h = ip_hdr(skb);

                        /* Calculate IPv4 checksum and L4 checksum */
                        ip_hdr_len = ip4h->ihl;
                        l4_proto = ip4h->protocol;
                } else if (l3_proto == htons(ETH_P_IPV6)) {
                        struct ipv6hdr *ip6h = ipv6_hdr(skb);

                        /* Read l4_protocol from one of IPv6 extra headers */
                        if (skb_network_header_len(skb) > 0)
                                ip_hdr_len = (skb_network_header_len(skb) >> 2);
                        l4_proto = ip6h->nexthdr;
                } else
                        return MVNETA_TX_L4_CSUM_NOT;

                return mvneta_txq_desc_csum(skb_network_offset(skb),
                                            l3_proto, ip_hdr_len, l4_proto);
        }

        return MVNETA_TX_L4_CSUM_NOT;
}

/* Drop packets received by the RXQ and free buffers */
static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
                                 struct mvneta_rx_queue *rxq)
{
        int rx_done, i;

        rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq);
        if (rx_done)
                mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_done);

        if (pp->bm_priv) {
                for (i = 0; i < rx_done; i++) {
                        struct mvneta_rx_desc *rx_desc =
                                                  mvneta_rxq_next_desc_get(rxq);
                        u8 pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc);
                        struct mvneta_bm_pool *bm_pool;

                        bm_pool = &pp->bm_priv->bm_pools[pool_id];
                        /* Return dropped buffer to the pool */
                        mvneta_bm_pool_put_bp(pp->bm_priv, bm_pool,
                                              rx_desc->buf_phys_addr);
                }
                return;
        }

        for (i = 0; i < rxq->size; i++) {
                struct mvneta_rx_desc *rx_desc = rxq->descs + i;
                void *data = rxq->buf_virt_addr[i];
                if (!data || !(rx_desc->buf_phys_addr))
                        continue;

                page_pool_put_full_page(rxq->page_pool, data, false);
        }
        if (xdp_rxq_info_is_reg(&rxq->xdp_rxq))
                xdp_rxq_info_unreg(&rxq->xdp_rxq);
        page_pool_destroy(rxq->page_pool);
        rxq->page_pool = NULL;
}

static void
mvneta_update_stats(struct mvneta_port *pp,
                    struct mvneta_stats *ps)
{
        struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);

        u64_stats_update_begin(&stats->syncp);
        stats->es.ps.rx_packets += ps->rx_packets;
        stats->es.ps.rx_bytes += ps->rx_bytes;
        /* xdp */
        stats->es.ps.xdp_redirect += ps->xdp_redirect;
        stats->es.ps.xdp_pass += ps->xdp_pass;
        stats->es.ps.xdp_drop += ps->xdp_drop;
        u64_stats_update_end(&stats->syncp);

}

static inline
int mvneta_rx_refill_queue(struct mvneta_port *pp, struct mvneta_rx_queue *rxq)
{
        struct mvneta_rx_desc *rx_desc;
        int curr_desc = rxq->first_to_refill;
        int i;

        for (i = 0; (i < rxq->refill_num) && (i < 64); i++) {
                rx_desc = rxq->descs + curr_desc;
                if (!(rx_desc->buf_phys_addr)) {
                        if (mvneta_rx_refill(pp, rx_desc, rxq, GFP_ATOMIC)) {
                                struct mvneta_pcpu_stats *stats;

                                pr_err("Can't refill queue %d. Done %d from %d\n",
                                       rxq->id, i, rxq->refill_num);

                                stats = this_cpu_ptr(pp->stats);
                                u64_stats_update_begin(&stats->syncp);
                                stats->es.refill_error++;
                                u64_stats_update_end(&stats->syncp);
                                break;
                        }
                }
                curr_desc = MVNETA_QUEUE_NEXT_DESC(rxq, curr_desc);
        }
        rxq->refill_num -= i;
        rxq->first_to_refill = curr_desc;

        return i;
}

static void
mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
                    struct xdp_buff *xdp, struct skb_shared_info *sinfo,
                    int sync_len)
{
        int i;

        for (i = 0; i < sinfo->nr_frags; i++)
                page_pool_put_full_page(rxq->page_pool,
                                        skb_frag_page(&sinfo->frags[i]), true);
        page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data),
                           sync_len, true);
}

static int
mvneta_xdp_submit_frame(struct mvneta_port *pp, struct mvneta_tx_queue *txq,
                        struct xdp_frame *xdpf, bool dma_map)
{
        struct mvneta_tx_desc *tx_desc;
        struct mvneta_tx_buf *buf;
        dma_addr_t dma_addr;

        if (txq->count >= txq->tx_stop_threshold)
                return MVNETA_XDP_DROPPED;

        tx_desc = mvneta_txq_next_desc_get(txq);

        buf = &txq->buf[txq->txq_put_index];
        if (dma_map) {
                /* ndo_xdp_xmit */
                dma_addr = dma_map_single(pp->dev->dev.parent, xdpf->data,
                                          xdpf->len, DMA_TO_DEVICE);
                if (dma_mapping_error(pp->dev->dev.parent, dma_addr)) {
                        mvneta_txq_desc_put(txq);
                        return MVNETA_XDP_DROPPED;
                }
                buf->type = MVNETA_TYPE_XDP_NDO;
        } else {
                struct page *page = virt_to_page(xdpf->data);

                dma_addr = page_pool_get_dma_addr(page) +
                           sizeof(*xdpf) + xdpf->headroom;
                dma_sync_single_for_device(pp->dev->dev.parent, dma_addr,
                                           xdpf->len, DMA_BIDIRECTIONAL);
                buf->type = MVNETA_TYPE_XDP_TX;
        }
        buf->xdpf = xdpf;

        tx_desc->command = MVNETA_TXD_FLZ_DESC;
        tx_desc->buf_phys_addr = dma_addr;
        tx_desc->data_size = xdpf->len;

        mvneta_txq_inc_put(txq);
        txq->pending++;
        txq->count++;

        return MVNETA_XDP_TX;
}

static int
mvneta_xdp_xmit_back(struct mvneta_port *pp, struct xdp_buff *xdp)
{
        struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
        struct mvneta_tx_queue *txq;
        struct netdev_queue *nq;
        struct xdp_frame *xdpf;
        int cpu;
        u32 ret;

        xdpf = xdp_convert_buff_to_frame(xdp);
        if (unlikely(!xdpf))
                return MVNETA_XDP_DROPPED;

        cpu = smp_processor_id();
        txq = &pp->txqs[cpu % txq_number];
        nq = netdev_get_tx_queue(pp->dev, txq->id);

        __netif_tx_lock(nq, cpu);
        ret = mvneta_xdp_submit_frame(pp, txq, xdpf, false);
        if (ret == MVNETA_XDP_TX) {
                u64_stats_update_begin(&stats->syncp);
                stats->es.ps.tx_bytes += xdpf->len;
                stats->es.ps.tx_packets++;
                stats->es.ps.xdp_tx++;
                u64_stats_update_end(&stats->syncp);

                mvneta_txq_pend_desc_add(pp, txq, 0);
        } else {
                u64_stats_update_begin(&stats->syncp);
                stats->es.ps.xdp_tx_err++;
                u64_stats_update_end(&stats->syncp);
        }
        __netif_tx_unlock(nq);

        return ret;
}

static int
mvneta_xdp_xmit(struct net_device *dev, int num_frame,
                struct xdp_frame **frames, u32 flags)
{
        struct mvneta_port *pp = netdev_priv(dev);
        struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
        int i, nxmit_byte = 0, nxmit = num_frame;
        int cpu = smp_processor_id();
        struct mvneta_tx_queue *txq;
        struct netdev_queue *nq;
        u32 ret;

        if (unlikely(test_bit(__MVNETA_DOWN, &pp->state)))
                return -ENETDOWN;

        if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
                return -EINVAL;

        txq = &pp->txqs[cpu % txq_number];
        nq = netdev_get_tx_queue(pp->dev, txq->id);

        __netif_tx_lock(nq, cpu);
        for (i = 0; i < num_frame; i++) {
                ret = mvneta_xdp_submit_frame(pp, txq, frames[i], true);
                if (ret == MVNETA_XDP_TX) {
                        nxmit_byte += frames[i]->len;
                } else {
                        xdp_return_frame_rx_napi(frames[i]);
                        nxmit--;
                }
        }

        if (unlikely(flags & XDP_XMIT_FLUSH))
                mvneta_txq_pend_desc_add(pp, txq, 0);
        __netif_tx_unlock(nq);

        u64_stats_update_begin(&stats->syncp);
        stats->es.ps.tx_bytes += nxmit_byte;
        stats->es.ps.tx_packets += nxmit;
        stats->es.ps.xdp_xmit += nxmit;
        stats->es.ps.xdp_xmit_err += num_frame - nxmit;
        u64_stats_update_end(&stats->syncp);

        return nxmit;
}

static int
mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
               struct bpf_prog *prog, struct xdp_buff *xdp,
               u32 frame_sz, struct mvneta_stats *stats)
{
        struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
        unsigned int len, data_len, sync;
        u32 ret, act;

        len = xdp->data_end - xdp->data_hard_start - pp->rx_offset_correction;
        data_len = xdp->data_end - xdp->data;
        act = bpf_prog_run_xdp(prog, xdp);

        /* Due xdp_adjust_tail: DMA sync for_device cover max len CPU touch */
        sync = xdp->data_end - xdp->data_hard_start - pp->rx_offset_correction;
        sync = max(sync, len);

        switch (act) {
        case XDP_PASS:
                stats->xdp_pass++;
                return MVNETA_XDP_PASS;
        case XDP_REDIRECT: {
                int err;

                err = xdp_do_redirect(pp->dev, xdp, prog);
                if (unlikely(err)) {
                        mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync);
                        ret = MVNETA_XDP_DROPPED;
                } else {
                        ret = MVNETA_XDP_REDIR;
                        stats->xdp_redirect++;
                }
                break;
        }
        case XDP_TX:
                ret = mvneta_xdp_xmit_back(pp, xdp);
                if (ret != MVNETA_XDP_TX)
                        mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync);
                break;
        default:
                bpf_warn_invalid_xdp_action(act);
                fallthrough;
        case XDP_ABORTED:
                trace_xdp_exception(pp->dev, prog, act);
                fallthrough;
        case XDP_DROP:
                mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync);
                ret = MVNETA_XDP_DROPPED;
                stats->xdp_drop++;
                break;
        }

        stats->rx_bytes += frame_sz + xdp->data_end - xdp->data - data_len;
        stats->rx_packets++;

        return ret;
}

static void
mvneta_swbm_rx_frame(struct mvneta_port *pp,
                     struct mvneta_rx_desc *rx_desc,
                     struct mvneta_rx_queue *rxq,
                     struct xdp_buff *xdp, int *size,
                     struct page *page)
{
        unsigned char *data = page_address(page);
        int data_len = -MVNETA_MH_SIZE, len;
        struct net_device *dev = pp->dev;
        enum dma_data_direction dma_dir;
        struct skb_shared_info *sinfo;

        if (*size > MVNETA_MAX_RX_BUF_SIZE) {
                len = MVNETA_MAX_RX_BUF_SIZE;
                data_len += len;
        } else {
                len = *size;
                data_len += len - ETH_FCS_LEN;
        }
        *size = *size - len;

        dma_dir = page_pool_get_dma_dir(rxq->page_pool);
        dma_sync_single_for_cpu(dev->dev.parent,
                                rx_desc->buf_phys_addr,
                                len, dma_dir);

        rx_desc->buf_phys_addr = 0;

        /* Prefetch header */
        prefetch(data);

        xdp->data_hard_start = data;
        xdp->data = data + pp->rx_offset_correction + MVNETA_MH_SIZE;
        xdp->data_end = xdp->data + data_len;
        xdp_set_data_meta_invalid(xdp);

        sinfo = xdp_get_shared_info_from_buff(xdp);
        sinfo->nr_frags = 0;
}

static void
mvneta_swbm_add_rx_fragment(struct mvneta_port *pp,
                            struct mvneta_rx_desc *rx_desc,
                            struct mvneta_rx_queue *rxq,
                            struct xdp_buff *xdp, int *size,
                            struct skb_shared_info *xdp_sinfo,
                            struct page *page)
{
        struct net_device *dev = pp->dev;
        enum dma_data_direction dma_dir;
        int data_len, len;

        if (*size > MVNETA_MAX_RX_BUF_SIZE) {
                len = MVNETA_MAX_RX_BUF_SIZE;
                data_len = len;
        } else {
                len = *size;
                data_len = len - ETH_FCS_LEN;
        }
        dma_dir = page_pool_get_dma_dir(rxq->page_pool);
        dma_sync_single_for_cpu(dev->dev.parent,
                                rx_desc->buf_phys_addr,
                                len, dma_dir);
        rx_desc->buf_phys_addr = 0;

        if (data_len > 0 && xdp_sinfo->nr_frags < MAX_SKB_FRAGS) {
                skb_frag_t *frag = &xdp_sinfo->frags[xdp_sinfo->nr_frags++];

                skb_frag_off_set(frag, pp->rx_offset_correction);
                skb_frag_size_set(frag, data_len);
                __skb_frag_set_page(frag, page);

                /* last fragment */
                if (len == *size) {
                        struct skb_shared_info *sinfo;

                        sinfo = xdp_get_shared_info_from_buff(xdp);
                        sinfo->nr_frags = xdp_sinfo->nr_frags;
                        memcpy(sinfo->frags, xdp_sinfo->frags,
                               sinfo->nr_frags * sizeof(skb_frag_t));
                }
        } else {
                page_pool_put_full_page(rxq->page_pool, page, true);
        }
        *size -= len;
}

static struct sk_buff *
mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
                      struct xdp_buff *xdp, u32 desc_status)
{
        struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
        int i, num_frags = sinfo->nr_frags;
        struct sk_buff *skb;

        skb = build_skb(xdp->data_hard_start, PAGE_SIZE);
        if (!skb)
                return ERR_PTR(-ENOMEM);

        page_pool_release_page(rxq->page_pool, virt_to_page(xdp->data));

        skb_reserve(skb, xdp->data - xdp->data_hard_start);
        skb_put(skb, xdp->data_end - xdp->data);
        mvneta_rx_csum(pp, desc_status, skb);

        for (i = 0; i < num_frags; i++) {
                skb_frag_t *frag = &sinfo->frags[i];

                skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
                                skb_frag_page(frag), skb_frag_off(frag),
                                skb_frag_size(frag), PAGE_SIZE);
                page_pool_release_page(rxq->page_pool, skb_frag_page(frag));
        }

        return skb;
}

/* Main rx processing when using software buffer management */
static int mvneta_rx_swbm(struct napi_struct *napi,
                          struct mvneta_port *pp, int budget,
                          struct mvneta_rx_queue *rxq)
{
        int rx_proc = 0, rx_todo, refill, size = 0;
        struct net_device *dev = pp->dev;
        struct skb_shared_info sinfo;
        struct mvneta_stats ps = {};
        struct bpf_prog *xdp_prog;
        u32 desc_status, frame_sz;
        struct xdp_buff xdp_buf;

        xdp_buf.data_hard_start = NULL;
        xdp_buf.frame_sz = PAGE_SIZE;
        xdp_buf.rxq = &rxq->xdp_rxq;

        sinfo.nr_frags = 0;

        /* Get number of received packets */
        rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq);

        rcu_read_lock();
        xdp_prog = READ_ONCE(pp->xdp_prog);

        /* Fairness NAPI loop */
        while (rx_proc < budget && rx_proc < rx_todo) {
                struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq);
                u32 rx_status, index;
                struct sk_buff *skb;
                struct page *page;

                index = rx_desc - rxq->descs;
                page = (struct page *)rxq->buf_virt_addr[index];

                rx_status = rx_desc->status;
                rx_proc++;
                rxq->refill_num++;

                if (rx_status & MVNETA_RXD_FIRST_DESC) {
                        /* Check errors only for FIRST descriptor */
                        if (rx_status & MVNETA_RXD_ERR_SUMMARY) {
                                mvneta_rx_error(pp, rx_desc);
                                goto next;
                        }

                        size = rx_desc->data_size;
                        frame_sz = size - ETH_FCS_LEN;
                        desc_status = rx_status;

                        mvneta_swbm_rx_frame(pp, rx_desc, rxq, &xdp_buf,
                                             &size, page);
                } else {
                        if (unlikely(!xdp_buf.data_hard_start)) {
                                rx_desc->buf_phys_addr = 0;
                                page_pool_put_full_page(rxq->page_pool, page,
                                                        true);
                                goto next;
                        }

                        mvneta_swbm_add_rx_fragment(pp, rx_desc, rxq, &xdp_buf,
                                                    &size, &sinfo, page);
                } /* Middle or Last descriptor */

                if (!(rx_status & MVNETA_RXD_LAST_DESC))
                        /* no last descriptor this time */
                        continue;

                if (size) {
                        mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);
                        goto next;
                }

                if (xdp_prog &&
                    mvneta_run_xdp(pp, rxq, xdp_prog, &xdp_buf, frame_sz, &ps))
                        goto next;

                skb = mvneta_swbm_build_skb(pp, rxq, &xdp_buf, desc_status);
                if (IS_ERR(skb)) {
                        struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);

                        mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);

                        u64_stats_update_begin(&stats->syncp);
                        stats->es.skb_alloc_error++;
                        stats->rx_dropped++;
                        u64_stats_update_end(&stats->syncp);

                        goto next;
                }

                ps.rx_bytes += skb->len;
                ps.rx_packets++;

                skb->protocol = eth_type_trans(skb, dev);
                napi_gro_receive(napi, skb);
next:
                xdp_buf.data_hard_start = NULL;
                sinfo.nr_frags = 0;
        }
        rcu_read_unlock();

        if (xdp_buf.data_hard_start)
                mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);

        if (ps.xdp_redirect)
                xdp_do_flush_map();

        if (ps.rx_packets)
                mvneta_update_stats(pp, &ps);

        /* return some buffers to hardware queue, one at a time is too slow */
        refill = mvneta_rx_refill_queue(pp, rxq);

        /* Update rxq management counters */
        mvneta_rxq_desc_num_update(pp, rxq, rx_proc, refill);

        return ps.rx_packets;
}

/* Main rx processing when using hardware buffer management */
static int mvneta_rx_hwbm(struct napi_struct *napi,
                          struct mvneta_port *pp, int rx_todo,
                          struct mvneta_rx_queue *rxq)
{
        struct net_device *dev = pp->dev;
        int rx_done;
        u32 rcvd_pkts = 0;
        u32 rcvd_bytes = 0;

        /* Get number of received packets */
        rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq);

        if (rx_todo > rx_done)
                rx_todo = rx_done;

        rx_done = 0;

        /* Fairness NAPI loop */
        while (rx_done < rx_todo) {
                struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq);
                struct mvneta_bm_pool *bm_pool = NULL;
                struct sk_buff *skb;
                unsigned char *data;
                dma_addr_t phys_addr;
                u32 rx_status, frag_size;
                int rx_bytes, err;
                u8 pool_id;

                rx_done++;
                rx_status = rx_desc->status;
                rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
                data = (u8 *)(uintptr_t)rx_desc->buf_cookie;
                phys_addr = rx_desc->buf_phys_addr;
                pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc);
                bm_pool = &pp->bm_priv->bm_pools[pool_id];

                if (!mvneta_rxq_desc_is_first_last(rx_status) ||
                    (rx_status & MVNETA_RXD_ERR_SUMMARY)) {
err_drop_frame_ret_pool:
                        /* Return the buffer to the pool */
                        mvneta_bm_pool_put_bp(pp->bm_priv, bm_pool,
                                              rx_desc->buf_phys_addr);
err_drop_frame:
                        mvneta_rx_error(pp, rx_desc);
                        /* leave the descriptor untouched */
                        continue;
                }

                if (rx_bytes <= rx_copybreak) {
                        /* better copy a small frame and not unmap the DMA region */
                        skb = netdev_alloc_skb_ip_align(dev, rx_bytes);
                        if (unlikely(!skb))
                                goto err_drop_frame_ret_pool;

                        dma_sync_single_range_for_cpu(&pp->bm_priv->pdev->dev,
                                                      rx_desc->buf_phys_addr,
                                                      MVNETA_MH_SIZE + NET_SKB_PAD,
                                                      rx_bytes,
                                                      DMA_FROM_DEVICE);
                        skb_put_data(skb, data + MVNETA_MH_SIZE + NET_SKB_PAD,
                                     rx_bytes);

                        skb->protocol = eth_type_trans(skb, dev);
                        mvneta_rx_csum(pp, rx_status, skb);
                        napi_gro_receive(napi, skb);

                        rcvd_pkts++;
                        rcvd_bytes += rx_bytes;

                        /* Return the buffer to the pool */
                        mvneta_bm_pool_put_bp(pp->bm_priv, bm_pool,
                                              rx_desc->buf_phys_addr);

                        /* leave the descriptor and buffer untouched */
                        continue;
                }

                /* Refill processing */
                err = hwbm_pool_refill(&bm_pool->hwbm_pool, GFP_ATOMIC);
                if (err) {
                        struct mvneta_pcpu_stats *stats;

                        netdev_err(dev, "Linux processing - Can't refill\n");

                        stats = this_cpu_ptr(pp->stats);
                        u64_stats_update_begin(&stats->syncp);
                        stats->es.refill_error++;
                        u64_stats_update_end(&stats->syncp);

                        goto err_drop_frame_ret_pool;
                }

                frag_size = bm_pool->hwbm_pool.frag_size;

                skb = build_skb(data, frag_size > PAGE_SIZE ? 0 : frag_size);

                /* After refill old buffer has to be unmapped regardless
                 * the skb is successfully built or not.
                 */
                dma_unmap_single(&pp->bm_priv->pdev->dev, phys_addr,
                                 bm_pool->buf_size, DMA_FROM_DEVICE);
                if (!skb)
                        goto err_drop_frame;

                rcvd_pkts++;
                rcvd_bytes += rx_bytes;

                /* Linux processing */
                skb_reserve(skb, MVNETA_MH_SIZE + NET_SKB_PAD);
                skb_put(skb, rx_bytes);

                skb->protocol = eth_type_trans(skb, dev);

                mvneta_rx_csum(pp, rx_status, skb);

                napi_gro_receive(napi, skb);
        }

        if (rcvd_pkts) {
                struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);

                u64_stats_update_begin(&stats->syncp);
                stats->es.ps.rx_packets += rcvd_pkts;
                stats->es.ps.rx_bytes += rcvd_bytes;
                u64_stats_update_end(&stats->syncp);
        }

        /* Update rxq management counters */
        mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_done);

        return rx_done;
}

static inline void
mvneta_tso_put_hdr(struct sk_buff *skb,
                   struct mvneta_port *pp, struct mvneta_tx_queue *txq)
{
        int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
        struct mvneta_tx_buf *buf = &txq->buf[txq->txq_put_index];
        struct mvneta_tx_desc *tx_desc;

        tx_desc = mvneta_txq_next_desc_get(txq);
        tx_desc->data_size = hdr_len;
        tx_desc->command = mvneta_skb_tx_csum(pp, skb);
        tx_desc->command |= MVNETA_TXD_F_DESC;
        tx_desc->buf_phys_addr = txq->tso_hdrs_phys +
                                 txq->txq_put_index * TSO_HEADER_SIZE;
        buf->type = MVNETA_TYPE_SKB;
        buf->skb = NULL;

        mvneta_txq_inc_put(txq);
}

static inline int
mvneta_tso_put_data(struct net_device *dev, struct mvneta_tx_queue *txq,
                    struct sk_buff *skb, char *data, int size,
                    bool last_tcp, bool is_last)
{
        struct mvneta_tx_buf *buf = &txq->buf[txq->txq_put_index];
        struct mvneta_tx_desc *tx_desc;

        tx_desc = mvneta_txq_next_desc_get(txq);
        tx_desc->data_size = size;
        tx_desc->buf_phys_addr = dma_map_single(dev->dev.parent, data,
                                                size, DMA_TO_DEVICE);
        if (unlikely(dma_mapping_error(dev->dev.parent,
                     tx_desc->buf_phys_addr))) {
                mvneta_txq_desc_put(txq);
                return -ENOMEM;
        }

        tx_desc->command = 0;
        buf->type = MVNETA_TYPE_SKB;
        buf->skb = NULL;

        if (last_tcp) {
                /* last descriptor in the TCP packet */
                tx_desc->command = MVNETA_TXD_L_DESC;

                /* last descriptor in SKB */
                if (is_last)
                        buf->skb = skb;
        }
        mvneta_txq_inc_put(txq);
        return 0;
}

static int mvneta_tx_tso(struct sk_buff *skb, struct net_device *dev,
                         struct mvneta_tx_queue *txq)
{
        int hdr_len, total_len, data_left;
        int desc_count = 0;
        struct mvneta_port *pp = netdev_priv(dev);
        struct tso_t tso;
        int i;

        /* Count needed descriptors */
        if ((txq->count + tso_count_descs(skb)) >= txq->size)
                return 0;

        if (skb_headlen(skb) < (skb_transport_offset(skb) + tcp_hdrlen(skb))) {
                pr_info("*** Is this even  possible???!?!?\n");
                return 0;
        }

        /* Initialize the TSO handler, and prepare the first payload */
        hdr_len = tso_start(skb, &tso);

        total_len = skb->len - hdr_len;
        while (total_len > 0) {
                char *hdr;

                data_left = min_t(int, skb_shinfo(skb)->gso_size, total_len);
                total_len -= data_left;
                desc_count++;

                /* prepare packet headers: MAC + IP + TCP */
                hdr = txq->tso_hdrs + txq->txq_put_index * TSO_HEADER_SIZE;
                tso_build_hdr(skb, hdr, &tso, data_left, total_len == 0);

                mvneta_tso_put_hdr(skb, pp, txq);

                while (data_left > 0) {
                        int size;
                        desc_count++;

                        size = min_t(int, tso.size, data_left);

                        if (mvneta_tso_put_data(dev, txq, skb,
                                                 tso.data, size,
                                                 size == data_left,
                                                 total_len == 0))
                                goto err_release;
                        data_left -= size;

                        tso_build_data(skb, &tso, size);
                }
        }

        return desc_count;

err_release:
        /* Release all used data descriptors; header descriptors must not
         * be DMA-unmapped.
         */
        for (i = desc_count - 1; i >= 0; i--) {
                struct mvneta_tx_desc *tx_desc = txq->descs + i;
                if (!IS_TSO_HEADER(txq, tx_desc->buf_phys_addr))
                        dma_unmap_single(pp->dev->dev.parent,
                                         tx_desc->buf_phys_addr,
                                         tx_desc->data_size,
                                         DMA_TO_DEVICE);
                mvneta_txq_desc_put(txq);
        }
        return 0;
}

/* Handle tx fragmentation processing */
static int mvneta_tx_frag_process(struct mvneta_port *pp, struct sk_buff *skb,
                                  struct mvneta_tx_queue *txq)
{
        struct mvneta_tx_desc *tx_desc;
        int i, nr_frags = skb_shinfo(skb)->nr_frags;

        for (i = 0; i < nr_frags; i++) {
                struct mvneta_tx_buf *buf = &txq->buf[txq->txq_put_index];
                skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
                void *addr = skb_frag_address(frag);

                tx_desc = mvneta_txq_next_desc_get(txq);
                tx_desc->data_size = skb_frag_size(frag);

                tx_desc->buf_phys_addr =
                        dma_map_single(pp->dev->dev.parent, addr,
                                       tx_desc->data_size, DMA_TO_DEVICE);

                if (dma_mapping_error(pp->dev->dev.parent,
                                      tx_desc->buf_phys_addr)) {
                        mvneta_txq_desc_put(txq);
                        goto error;
                }

                if (i == nr_frags - 1) {
                        /* Last descriptor */
                        tx_desc->command = MVNETA_TXD_L_DESC | MVNETA_TXD_Z_PAD;
                        buf->skb = skb;
                } else {
                        /* Descriptor in the middle: Not First, Not Last */
                        tx_desc->command = 0;
                        buf->skb = NULL;
                }
                buf->type = MVNETA_TYPE_SKB;
                mvneta_txq_inc_put(txq);
        }

        return 0;

error:
        /* Release all descriptors that were used to map fragments of
         * this packet, as well as the corresponding DMA mappings
         */
        for (i = i - 1; i >= 0; i--) {
                tx_desc = txq->descs + i;
                dma_unmap_single(pp->dev->dev.parent,
                                 tx_desc->buf_phys_addr,
                                 tx_desc->data_size,
                                 DMA_TO_DEVICE);
                mvneta_txq_desc_put(txq);
        }

        return -ENOMEM;
}

/* Main tx processing */
static netdev_tx_t mvneta_tx(struct sk_buff *skb, struct net_device *dev)
{
        struct mvneta_port *pp = netdev_priv(dev);
        u16 txq_id = skb_get_queue_mapping(skb);
        struct mvneta_tx_queue *txq = &pp->txqs[txq_id];
        struct mvneta_tx_buf *buf = &txq->buf[txq->txq_put_index];
        struct mvneta_tx_desc *tx_desc;
        int len = skb->len;
        int frags = 0;
        u32 tx_cmd;

        if (!netif_running(dev))
                goto out;

        if (skb_is_gso(skb)) {
                frags = mvneta_tx_tso(skb, dev, txq);
                goto out;
        }

        frags = skb_shinfo(skb)->nr_frags + 1;

        /* Get a descriptor for the first part of the packet */
        tx_desc = mvneta_txq_next_desc_get(txq);

        tx_cmd = mvneta_skb_tx_csum(pp, skb);

        tx_desc->data_size = skb_headlen(skb);

        tx_desc->buf_phys_addr = dma_map_single(dev->dev.parent, skb->data,
                                                tx_desc->data_size,
                                                DMA_TO_DEVICE);
        if (unlikely(dma_mapping_error(dev->dev.parent,
                                       tx_desc->buf_phys_addr))) {
                mvneta_txq_desc_put(txq);
                frags = 0;
                goto out;
        }

        buf->type = MVNETA_TYPE_SKB;
        if (frags == 1) {
                /* First and Last descriptor */
                tx_cmd |= MVNETA_TXD_FLZ_DESC;
                tx_desc->command = tx_cmd;
                buf->skb = skb;
                mvneta_txq_inc_put(txq);
        } else {
                /* First but not Last */
                tx_cmd |= MVNETA_TXD_F_DESC;
                buf->skb = NULL;
                mvneta_txq_inc_put(txq);
                tx_desc->command = tx_cmd;
                /* Continue with other skb fragments */
                if (mvneta_tx_frag_process(pp, skb, txq)) {
                        dma_unmap_single(dev->dev.parent,
                                         tx_desc->buf_phys_addr,
                                         tx_desc->data_size,
                                         DMA_TO_DEVICE);
                        mvneta_txq_desc_put(txq);
                        frags = 0;
                        goto out;
                }
        }

out:
        if (frags > 0) {
                struct netdev_queue *nq = netdev_get_tx_queue(dev, txq_id);
                struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);

                netdev_tx_sent_queue(nq, len);

                txq->count += frags;
                if (txq->count >= txq->tx_stop_threshold)
                        netif_tx_stop_queue(nq);

                if (!netdev_xmit_more() || netif_xmit_stopped(nq) ||
                    txq->pending + frags > MVNETA_TXQ_DEC_SENT_MASK)
                        mvneta_txq_pend_desc_add(pp, txq, frags);
                else
                        txq->pending += frags;

                u64_stats_update_begin(&stats->syncp);
                stats->es.ps.tx_bytes += len;
                stats->es.ps.tx_packets++;
                u64_stats_update_end(&stats->syncp);
        } else {
                dev->stats.tx_dropped++;
                dev_kfree_skb_any(skb);
        }

        return NETDEV_TX_OK;
}


/* Free tx resources, when resetting a port */
static void mvneta_txq_done_force(struct mvneta_port *pp,
                                  struct mvneta_tx_queue *txq)

{
        struct netdev_queue *nq = netdev_get_tx_queue(pp->dev, txq->id);
        int tx_done = txq->count;

        mvneta_txq_bufs_free(pp, txq, tx_done, nq, false);

        /* reset txq */
        txq->count = 0;
        txq->txq_put_index = 0;
        txq->txq_get_index = 0;
}

/* Handle tx done - called in softirq context. The <cause_tx_done> argument
 * must be a valid cause according to MVNETA_TXQ_INTR_MASK_ALL.
 */
static void mvneta_tx_done_gbe(struct mvneta_port *pp, u32 cause_tx_done)
{
        struct mvneta_tx_queue *txq;
        struct netdev_queue *nq;
        int cpu = smp_processor_id();

        while (cause_tx_done) {
                txq = mvneta_tx_done_policy(pp, cause_tx_done);

                nq = netdev_get_tx_queue(pp->dev, txq->id);
                __netif_tx_lock(nq, cpu);

                if (txq->count)
                        mvneta_txq_done(pp, txq);

                __netif_tx_unlock(nq);
                cause_tx_done &= ~((1 << txq->id));
        }
}

/* Compute crc8 of the specified address, using a unique algorithm ,
 * according to hw spec, different than generic crc8 algorithm
 */
static int mvneta_addr_crc(unsigned char *addr)
{
        int crc = 0;
        int i;

        for (i = 0; i < ETH_ALEN; i++) {
                int j;

                crc = (crc ^ addr[i]) << 8;
                for (j = 7; j >= 0; j--) {
                        if (crc & (0x100 << j))
                                crc ^= 0x107 << j;
                }
        }

        return crc;
}

/* This method controls the net device special MAC multicast support.
 * The Special Multicast Table for MAC addresses supports MAC of the form
 * 0x01-00-5E-00-00-XX (where XX is between 0x00 and 0xFF).
 * The MAC DA[7:0] bits are used as a pointer to the Special Multicast
 * Table entries in the DA-Filter table. This method set the Special
 * Multicast Table appropriate entry.
 */
static void mvneta_set_special_mcast_addr(struct mvneta_port *pp,
                                          unsigned char last_byte,
                                          int queue)
{
        unsigned int smc_table_reg;
        unsigned int tbl_offset;
        unsigned int reg_offset;

        /* Register offset from SMC table base    */
        tbl_offset = (last_byte / 4);
        /* Entry offset within the above reg */
        reg_offset = last_byte % 4;

        smc_table_reg = mvreg_read(pp, (MVNETA_DA_FILT_SPEC_MCAST
                                        + tbl_offset * 4));

        if (queue == -1)
                smc_table_reg &= ~(0xff << (8 * reg_offset));
        else {
                smc_table_reg &= ~(0xff << (8 * reg_offset));
                smc_table_reg |= ((0x01 | (queue << 1)) << (8 * reg_offset));
        }

        mvreg_write(pp, MVNETA_DA_FILT_SPEC_MCAST + tbl_offset * 4,
                    smc_table_reg);
}

/* This method controls the network device Other MAC multicast support.
 * The Other Multicast Table is used for multicast of another type.
 * A CRC-8 is used as an index to the Other Multicast Table entries
 * in the DA-Filter table.
 * The method gets the CRC-8 value from the calling routine and
 * sets the Other Multicast Table appropriate entry according to the
 * specified CRC-8 .
 */
static void mvneta_set_other_mcast_addr(struct mvneta_port *pp,
                                        unsigned char crc8,
                                        int queue)
{
        unsigned int omc_table_reg;
        unsigned int tbl_offset;
        unsigned int reg_offset;

        tbl_offset = (crc8 / 4) * 4; /* Register offset from OMC table base */
        reg_offset = crc8 % 4;       /* Entry offset within the above reg   */

        omc_table_reg = mvreg_read(pp, MVNETA_DA_FILT_OTH_MCAST + tbl_offset);

        if (queue == -1) {
                /* Clear accepts frame bit at specified Other DA table entry */
                omc_table_reg &= ~(0xff << (8 * reg_offset));
        } else {
                omc_table_reg &= ~(0xff << (8 * reg_offset));