From: Salil Date: Wed, 2 Aug 2017 15:59:45 +0000 (+0100) Subject: net: hns3: Add support of HNS3 Ethernet Driver for hip08 SoC X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=76ad4f0ee747;p=GitHub%2Fmoto-9609%2Fandroid_kernel_motorola_exynos9610.git net: hns3: Add support of HNS3 Ethernet Driver for hip08 SoC This patch adds the support of Hisilicon Network Subsystem 3 Ethernet driver to hip08 family of SoCs. This driver includes basic Rx/Tx functionality. It also includes the client registration code with the HNAE3(Hisilicon Network Acceleration Engine 3) framework. This work provides the initial support to the hip08 SoC and would incrementally add features or enhancements. Signed-off-by: Daode Huang Signed-off-by: lipeng Signed-off-by: Salil Mehta Signed-off-by: Yisen Zhuang Signed-off-by: Wei Hu (Xavier) Signed-off-by: David S. Miller --- diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c new file mode 100644 index 000000000000..ad9481c7ceae --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c @@ -0,0 +1,2848 @@ +/* + * Copyright (c) 2016~2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "hnae3.h" +#include "hns3_enet.h" + +const char hns3_driver_name[] = "hns3"; +const char hns3_driver_version[] = VERMAGIC_STRING; +static const char hns3_driver_string[] = + "Hisilicon Ethernet Network Driver for Hip08 Family"; +static const char hns3_copyright[] = "Copyright (c) 2017 Huawei Corporation."; +static struct hnae3_client client; + +/* hns3_pci_tbl - PCI Device ID Table + * + * Last entry must be all 0s + * + * { Vendor ID, Device ID, SubVendor ID, SubDevice ID, + * Class, Class Mask, private data (not used) } + */ +static const struct pci_device_id hns3_pci_tbl[] = { + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_GE), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0}, + /* required last entry */ + {0, } +}; +MODULE_DEVICE_TABLE(pci, hns3_pci_tbl); + +static irqreturn_t hns3_irq_handle(int irq, void *dev) +{ + struct hns3_enet_tqp_vector *tqp_vector = dev; + + napi_schedule(&tqp_vector->napi); + + return IRQ_HANDLED; +} + +static void hns3_nic_uninit_irq(struct hns3_nic_priv *priv) +{ + struct hns3_enet_tqp_vector *tqp_vectors; + unsigned int i; + + for (i = 0; i < priv->vector_num; i++) { + tqp_vectors = &priv->tqp_vector[i]; + + if (tqp_vectors->irq_init_flag != HNS3_VECTOR_INITED) + continue; + + /* release the irq resource */ + free_irq(tqp_vectors->vector_irq, tqp_vectors); + tqp_vectors->irq_init_flag = HNS3_VECTOR_NOT_INITED; + } +} + +static int hns3_nic_init_irq(struct hns3_nic_priv *priv) +{ + struct hns3_enet_tqp_vector *tqp_vectors; + int txrx_int_idx = 0; + int rx_int_idx = 0; + int tx_int_idx = 0; + unsigned int i; + int ret; + + for (i = 0; i < priv->vector_num; i++) { + tqp_vectors = &priv->tqp_vector[i]; + + if (tqp_vectors->irq_init_flag == HNS3_VECTOR_INITED) + continue; + + if (tqp_vectors->tx_group.ring && tqp_vectors->rx_group.ring) { + snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN - 1, + "%s-%s-%d", priv->netdev->name, "TxRx", + txrx_int_idx++); + txrx_int_idx++; + } else if (tqp_vectors->rx_group.ring) { + snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN - 1, + "%s-%s-%d", priv->netdev->name, "Rx", + rx_int_idx++); + } else if (tqp_vectors->tx_group.ring) { + snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN - 1, + "%s-%s-%d", priv->netdev->name, "Tx", + tx_int_idx++); + } else { + /* Skip this unused q_vector */ + continue; + } + + tqp_vectors->name[HNAE3_INT_NAME_LEN - 1] = '\0'; + + ret = request_irq(tqp_vectors->vector_irq, hns3_irq_handle, 0, + tqp_vectors->name, + tqp_vectors); + if (ret) { + netdev_err(priv->netdev, "request irq(%d) fail\n", + tqp_vectors->vector_irq); + return ret; + } + + tqp_vectors->irq_init_flag = HNS3_VECTOR_INITED; + } + + return 0; +} + +static void hns3_mask_vector_irq(struct hns3_enet_tqp_vector *tqp_vector, + u32 mask_en) +{ + writel(mask_en, tqp_vector->mask_addr); +} + +static void hns3_vector_enable(struct hns3_enet_tqp_vector *tqp_vector) +{ + napi_enable(&tqp_vector->napi); + + /* enable vector */ + hns3_mask_vector_irq(tqp_vector, 1); +} + +static void hns3_vector_disable(struct hns3_enet_tqp_vector *tqp_vector) +{ + /* disable vector */ + hns3_mask_vector_irq(tqp_vector, 0); + + disable_irq(tqp_vector->vector_irq); + napi_disable(&tqp_vector->napi); +} + +static void hns3_set_vector_coalesc_gl(struct hns3_enet_tqp_vector *tqp_vector, + u32 gl_value) +{ + /* this defines the configuration for GL (Interrupt Gap Limiter) + * GL defines inter interrupt gap. + * GL and RL(Rate Limiter) are 2 ways to acheive interrupt coalescing + */ + writel(gl_value, tqp_vector->mask_addr + HNS3_VECTOR_GL0_OFFSET); + writel(gl_value, tqp_vector->mask_addr + HNS3_VECTOR_GL1_OFFSET); + writel(gl_value, tqp_vector->mask_addr + HNS3_VECTOR_GL2_OFFSET); +} + +static void hns3_set_vector_coalesc_rl(struct hns3_enet_tqp_vector *tqp_vector, + u32 rl_value) +{ + /* this defines the configuration for RL (Interrupt Rate Limiter). + * Rl defines rate of interrupts i.e. number of interrupts-per-second + * GL and RL(Rate Limiter) are 2 ways to acheive interrupt coalescing + */ + writel(rl_value, tqp_vector->mask_addr + HNS3_VECTOR_RL_OFFSET); +} + +static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector) +{ + /* initialize the configuration for interrupt coalescing. + * 1. GL (Interrupt Gap Limiter) + * 2. RL (Interrupt Rate Limiter) + */ + + /* Default :enable interrupt coalesce */ + tqp_vector->rx_group.int_gl = HNS3_INT_GL_50K; + tqp_vector->tx_group.int_gl = HNS3_INT_GL_50K; + hns3_set_vector_coalesc_gl(tqp_vector, HNS3_INT_GL_50K); + /* for now we are disabling Interrupt RL - we + * will re-enable later + */ + hns3_set_vector_coalesc_rl(tqp_vector, 0); + tqp_vector->rx_group.flow_level = HNS3_FLOW_LOW; + tqp_vector->tx_group.flow_level = HNS3_FLOW_LOW; +} + +static int hns3_nic_net_up(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + int i, j; + int ret; + + /* get irq resource for all vectors */ + ret = hns3_nic_init_irq(priv); + if (ret) { + netdev_err(netdev, "hns init irq failed! ret=%d\n", ret); + return ret; + } + + /* enable the vectors */ + for (i = 0; i < priv->vector_num; i++) + hns3_vector_enable(&priv->tqp_vector[i]); + + /* start the ae_dev */ + ret = h->ae_algo->ops->start ? h->ae_algo->ops->start(h) : 0; + if (ret) + goto out_start_err; + + return 0; + +out_start_err: + for (j = i - 1; j >= 0; j--) + hns3_vector_disable(&priv->tqp_vector[j]); + + hns3_nic_uninit_irq(priv); + + return ret; +} + +static int hns3_nic_net_open(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + int ret; + + netif_carrier_off(netdev); + + ret = netif_set_real_num_tx_queues(netdev, h->kinfo.num_tqps); + if (ret) { + netdev_err(netdev, + "netif_set_real_num_tx_queues fail, ret=%d!\n", + ret); + return ret; + } + + ret = netif_set_real_num_rx_queues(netdev, h->kinfo.num_tqps); + if (ret) { + netdev_err(netdev, + "netif_set_real_num_rx_queues fail, ret=%d!\n", ret); + return ret; + } + + ret = hns3_nic_net_up(netdev); + if (ret) { + netdev_err(netdev, + "hns net up fail, ret=%d!\n", ret); + return ret; + } + + return 0; +} + +static void hns3_nic_net_down(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + const struct hnae3_ae_ops *ops; + int i; + + /* stop ae_dev */ + ops = priv->ae_handle->ae_algo->ops; + if (ops->stop) + ops->stop(priv->ae_handle); + + /* disable vectors */ + for (i = 0; i < priv->vector_num; i++) + hns3_vector_disable(&priv->tqp_vector[i]); + + /* free irq resources */ + hns3_nic_uninit_irq(priv); +} + +static int hns3_nic_net_stop(struct net_device *netdev) +{ + netif_tx_stop_all_queues(netdev); + netif_carrier_off(netdev); + + hns3_nic_net_down(netdev); + + return 0; +} + +void hns3_set_multicast_list(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + struct netdev_hw_addr *ha = NULL; + + if (h->ae_algo->ops->set_mc_addr) { + netdev_for_each_mc_addr(ha, netdev) + if (h->ae_algo->ops->set_mc_addr(h, ha->addr)) + netdev_err(netdev, "set multicast fail\n"); + } +} + +static int hns3_nic_uc_sync(struct net_device *netdev, + const unsigned char *addr) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->ae_algo->ops->add_uc_addr) + return h->ae_algo->ops->add_uc_addr(h, addr); + + return 0; +} + +static int hns3_nic_uc_unsync(struct net_device *netdev, + const unsigned char *addr) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->ae_algo->ops->rm_uc_addr) + return h->ae_algo->ops->rm_uc_addr(h, addr); + + return 0; +} + +static int hns3_nic_mc_sync(struct net_device *netdev, + const unsigned char *addr) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->ae_algo->ops->add_uc_addr) + return h->ae_algo->ops->add_mc_addr(h, addr); + + return 0; +} + +static int hns3_nic_mc_unsync(struct net_device *netdev, + const unsigned char *addr) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->ae_algo->ops->rm_uc_addr) + return h->ae_algo->ops->rm_mc_addr(h, addr); + + return 0; +} + +void hns3_nic_set_rx_mode(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->ae_algo->ops->set_promisc_mode) { + if (netdev->flags & IFF_PROMISC) + h->ae_algo->ops->set_promisc_mode(h, 1); + else + h->ae_algo->ops->set_promisc_mode(h, 0); + } + if (__dev_uc_sync(netdev, hns3_nic_uc_sync, hns3_nic_uc_unsync)) + netdev_err(netdev, "sync uc address fail\n"); + if (netdev->flags & IFF_MULTICAST) + if (__dev_mc_sync(netdev, hns3_nic_mc_sync, hns3_nic_mc_unsync)) + netdev_err(netdev, "sync mc address fail\n"); +} + +static int hns3_set_tso(struct sk_buff *skb, u32 *paylen, + u16 *mss, u32 *type_cs_vlan_tso) +{ + u32 l4_offset, hdr_len; + union l3_hdr_info l3; + union l4_hdr_info l4; + u32 l4_paylen; + int ret; + + if (!skb_is_gso(skb)) + return 0; + + ret = skb_cow_head(skb, 0); + if (ret) + return ret; + + l3.hdr = skb_network_header(skb); + l4.hdr = skb_transport_header(skb); + + /* Software should clear the IPv4's checksum field when tso is + * needed. + */ + if (l3.v4->version == 4) + l3.v4->check = 0; + + /* tunnel packet.*/ + if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | + SKB_GSO_GRE_CSUM | + SKB_GSO_UDP_TUNNEL | + SKB_GSO_UDP_TUNNEL_CSUM)) { + if ((!(skb_shinfo(skb)->gso_type & + SKB_GSO_PARTIAL)) && + (skb_shinfo(skb)->gso_type & + SKB_GSO_UDP_TUNNEL_CSUM)) { + /* Software should clear the udp's checksum + * field when tso is needed. + */ + l4.udp->check = 0; + } + /* reset l3&l4 pointers from outer to inner headers */ + l3.hdr = skb_inner_network_header(skb); + l4.hdr = skb_inner_transport_header(skb); + + /* Software should clear the IPv4's checksum field when + * tso is needed. + */ + if (l3.v4->version == 4) + l3.v4->check = 0; + } + + /* normal or tunnel packet*/ + l4_offset = l4.hdr - skb->data; + hdr_len = (l4.tcp->doff * 4) + l4_offset; + + /* remove payload length from inner pseudo checksum when tso*/ + l4_paylen = skb->len - l4_offset; + csum_replace_by_diff(&l4.tcp->check, + (__force __wsum)htonl(l4_paylen)); + + /* find the txbd field values */ + *paylen = skb->len - hdr_len; + hnae_set_bit(*type_cs_vlan_tso, + HNS3_TXD_TSO_B, 1); + + /* get MSS for TSO */ + *mss = skb_shinfo(skb)->gso_size; + + return 0; +} + +static void hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto, + u8 *il4_proto) +{ + union { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; + } l3; + unsigned char *l4_hdr; + unsigned char *exthdr; + u8 l4_proto_tmp; + __be16 frag_off; + + /* find outer header point */ + l3.hdr = skb_network_header(skb); + l4_hdr = skb_inner_transport_header(skb); + + if (skb->protocol == htons(ETH_P_IPV6)) { + exthdr = l3.hdr + sizeof(*l3.v6); + l4_proto_tmp = l3.v6->nexthdr; + if (l4_hdr != exthdr) + ipv6_skip_exthdr(skb, exthdr - skb->data, + &l4_proto_tmp, &frag_off); + } else if (skb->protocol == htons(ETH_P_IP)) { + l4_proto_tmp = l3.v4->protocol; + } + + *ol4_proto = l4_proto_tmp; + + /* tunnel packet */ + if (!skb->encapsulation) { + *il4_proto = 0; + return; + } + + /* find inner header point */ + l3.hdr = skb_inner_network_header(skb); + l4_hdr = skb_inner_transport_header(skb); + + if (l3.v6->version == 6) { + exthdr = l3.hdr + sizeof(*l3.v6); + l4_proto_tmp = l3.v6->nexthdr; + if (l4_hdr != exthdr) + ipv6_skip_exthdr(skb, exthdr - skb->data, + &l4_proto_tmp, &frag_off); + } else if (l3.v4->version == 4) { + l4_proto_tmp = l3.v4->protocol; + } + + *il4_proto = l4_proto_tmp; +} + +static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto, + u8 il4_proto, u32 *type_cs_vlan_tso, + u32 *ol_type_vlan_len_msec) +{ + union { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; + } l3; + union { + struct tcphdr *tcp; + struct udphdr *udp; + struct gre_base_hdr *gre; + unsigned char *hdr; + } l4; + unsigned char *l2_hdr; + u8 l4_proto = ol4_proto; + u32 ol2_len; + u32 ol3_len; + u32 ol4_len; + u32 l2_len; + u32 l3_len; + + l3.hdr = skb_network_header(skb); + l4.hdr = skb_transport_header(skb); + + /* compute L2 header size for normal packet, defined in 2 Bytes */ + l2_len = l3.hdr - skb->data; + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M, + HNS3_TXD_L2LEN_S, l2_len >> 1); + + /* tunnel packet*/ + if (skb->encapsulation) { + /* compute OL2 header size, defined in 2 Bytes */ + ol2_len = l2_len; + hnae_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_L2LEN_M, + HNS3_TXD_L2LEN_S, ol2_len >> 1); + + /* compute OL3 header size, defined in 4 Bytes */ + ol3_len = l4.hdr - l3.hdr; + hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_M, + HNS3_TXD_L3LEN_S, ol3_len >> 2); + + /* MAC in UDP, MAC in GRE (0x6558)*/ + if ((ol4_proto == IPPROTO_UDP) || (ol4_proto == IPPROTO_GRE)) { + /* switch MAC header ptr from outer to inner header.*/ + l2_hdr = skb_inner_mac_header(skb); + + /* compute OL4 header size, defined in 4 Bytes. */ + ol4_len = l2_hdr - l4.hdr; + hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L4LEN_M, + HNS3_TXD_L4LEN_S, ol4_len >> 2); + + /* switch IP header ptr from outer to inner header */ + l3.hdr = skb_inner_network_header(skb); + + /* compute inner l2 header size, defined in 2 Bytes. */ + l2_len = l3.hdr - l2_hdr; + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M, + HNS3_TXD_L2LEN_S, l2_len >> 1); + } else { + /* skb packet types not supported by hardware, + * txbd len fild doesn't be filled. + */ + return; + } + + /* switch L4 header pointer from outer to inner */ + l4.hdr = skb_inner_transport_header(skb); + + l4_proto = il4_proto; + } + + /* compute inner(/normal) L3 header size, defined in 4 Bytes */ + l3_len = l4.hdr - l3.hdr; + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_M, + HNS3_TXD_L3LEN_S, l3_len >> 2); + + /* compute inner(/normal) L4 header size, defined in 4 Bytes */ + switch (l4_proto) { + case IPPROTO_TCP: + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M, + HNS3_TXD_L4LEN_S, l4.tcp->doff); + break; + case IPPROTO_SCTP: + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M, + HNS3_TXD_L4LEN_S, (sizeof(struct sctphdr) >> 2)); + break; + case IPPROTO_UDP: + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M, + HNS3_TXD_L4LEN_S, (sizeof(struct udphdr) >> 2)); + break; + default: + /* skb packet types not supported by hardware, + * txbd len fild doesn't be filled. + */ + return; + } +} + +static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto, + u8 il4_proto, u32 *type_cs_vlan_tso, + u32 *ol_type_vlan_len_msec) +{ + union { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; + } l3; + u32 l4_proto = ol4_proto; + + l3.hdr = skb_network_header(skb); + + /* define OL3 type and tunnel type(OL4).*/ + if (skb->encapsulation) { + /* define outer network header type.*/ + if (skb->protocol == htons(ETH_P_IP)) { + if (skb_is_gso(skb)) + hnae_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_OL3T_M, HNS3_TXD_OL3T_S, + HNS3_OL3T_IPV4_CSUM); + else + hnae_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_OL3T_M, HNS3_TXD_OL3T_S, + HNS3_OL3T_IPV4_NO_CSUM); + + } else if (skb->protocol == htons(ETH_P_IPV6)) { + hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_M, + HNS3_TXD_OL3T_S, HNS3_OL3T_IPV6); + } + + /* define tunnel type(OL4).*/ + switch (l4_proto) { + case IPPROTO_UDP: + hnae_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_TUNTYPE_M, + HNS3_TXD_TUNTYPE_S, + HNS3_TUN_MAC_IN_UDP); + break; + case IPPROTO_GRE: + hnae_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_TUNTYPE_M, + HNS3_TXD_TUNTYPE_S, + HNS3_TUN_NVGRE); + break; + default: + /* drop the skb tunnel packet if hardware don't support, + * because hardware can't calculate csum when TSO. + */ + if (skb_is_gso(skb)) + return -EDOM; + + /* the stack computes the IP header already, + * driver calculate l4 checksum when not TSO. + */ + skb_checksum_help(skb); + return 0; + } + + l3.hdr = skb_inner_network_header(skb); + l4_proto = il4_proto; + } + + if (l3.v4->version == 4) { + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M, + HNS3_TXD_L3T_S, HNS3_L3T_IPV4); + + /* the stack computes the IP header already, the only time we + * need the hardware to recompute it is in the case of TSO. + */ + if (skb_is_gso(skb)) + hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1); + + hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1); + } else if (l3.v6->version == 6) { + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M, + HNS3_TXD_L3T_S, HNS3_L3T_IPV6); + hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1); + } + + switch (l4_proto) { + case IPPROTO_TCP: + hnae_set_field(*type_cs_vlan_tso, + HNS3_TXD_L4T_M, + HNS3_TXD_L4T_S, + HNS3_L4T_TCP); + break; + case IPPROTO_UDP: + hnae_set_field(*type_cs_vlan_tso, + HNS3_TXD_L4T_M, + HNS3_TXD_L4T_S, + HNS3_L4T_UDP); + break; + case IPPROTO_SCTP: + hnae_set_field(*type_cs_vlan_tso, + HNS3_TXD_L4T_M, + HNS3_TXD_L4T_S, + HNS3_L4T_SCTP); + break; + default: + /* drop the skb tunnel packet if hardware don't support, + * because hardware can't calculate csum when TSO. + */ + if (skb_is_gso(skb)) + return -EDOM; + + /* the stack computes the IP header already, + * driver calculate l4 checksum when not TSO. + */ + skb_checksum_help(skb); + return 0; + } + + return 0; +} + +static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end) +{ + /* Config bd buffer end */ + hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_BDTYPE_M, + HNS3_TXD_BDTYPE_M, 0); + hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end); + hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1); + hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 1); +} + +static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, + int size, dma_addr_t dma, int frag_end, + enum hns_desc_type type) +{ + struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; + struct hns3_desc *desc = &ring->desc[ring->next_to_use]; + u32 ol_type_vlan_len_msec = 0; + u16 bdtp_fe_sc_vld_ra_ri = 0; + u32 type_cs_vlan_tso = 0; + struct sk_buff *skb; + u32 paylen = 0; + u16 mss = 0; + __be16 protocol; + u8 ol4_proto; + u8 il4_proto; + int ret; + + /* The txbd's baseinfo of DESC_TYPE_PAGE & DESC_TYPE_SKB */ + desc_cb->priv = priv; + desc_cb->length = size; + desc_cb->dma = dma; + desc_cb->type = type; + + /* now, fill the descriptor */ + desc->addr = cpu_to_le64(dma); + desc->tx.send_size = cpu_to_le16((u16)size); + hns3_set_txbd_baseinfo(&bdtp_fe_sc_vld_ra_ri, frag_end); + desc->tx.bdtp_fe_sc_vld_ra_ri = cpu_to_le16(bdtp_fe_sc_vld_ra_ri); + + if (type == DESC_TYPE_SKB) { + skb = (struct sk_buff *)priv; + paylen = cpu_to_le16(skb->len); + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + skb_reset_mac_len(skb); + protocol = skb->protocol; + + /* vlan packet*/ + if (protocol == htons(ETH_P_8021Q)) { + protocol = vlan_get_protocol(skb); + skb->protocol = protocol; + } + hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto); + hns3_set_l2l3l4_len(skb, ol4_proto, il4_proto, + &type_cs_vlan_tso, + &ol_type_vlan_len_msec); + ret = hns3_set_l3l4_type_csum(skb, ol4_proto, il4_proto, + &type_cs_vlan_tso, + &ol_type_vlan_len_msec); + if (ret) + return ret; + + ret = hns3_set_tso(skb, &paylen, &mss, + &type_cs_vlan_tso); + if (ret) + return ret; + } + + /* Set txbd */ + desc->tx.ol_type_vlan_len_msec = + cpu_to_le32(ol_type_vlan_len_msec); + desc->tx.type_cs_vlan_tso_len = + cpu_to_le32(type_cs_vlan_tso); + desc->tx.paylen = cpu_to_le16(paylen); + desc->tx.mss = cpu_to_le16(mss); + } + + /* move ring pointer to next.*/ + ring_ptr_move_fw(ring, next_to_use); + + return 0; +} + +static int hns3_fill_desc_tso(struct hns3_enet_ring *ring, void *priv, + int size, dma_addr_t dma, int frag_end, + enum hns_desc_type type) +{ + unsigned int frag_buf_num; + unsigned int k; + int sizeoflast; + int ret; + + frag_buf_num = (size + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE; + sizeoflast = size % HNS3_MAX_BD_SIZE; + sizeoflast = sizeoflast ? sizeoflast : HNS3_MAX_BD_SIZE; + + /* When the frag size is bigger than hardware, split this frag */ + for (k = 0; k < frag_buf_num; k++) { + ret = hns3_fill_desc(ring, priv, + (k == frag_buf_num - 1) ? + sizeoflast : HNS3_MAX_BD_SIZE, + dma + HNS3_MAX_BD_SIZE * k, + frag_end && (k == frag_buf_num - 1) ? 1 : 0, + (type == DESC_TYPE_SKB && !k) ? + DESC_TYPE_SKB : DESC_TYPE_PAGE); + if (ret) + return ret; + } + + return 0; +} + +static int hns3_nic_maybe_stop_tso(struct sk_buff **out_skb, int *bnum, + struct hns3_enet_ring *ring) +{ + struct sk_buff *skb = *out_skb; + struct skb_frag_struct *frag; + int bdnum_for_frag; + int frag_num; + int buf_num; + int size; + int i; + + size = skb_headlen(skb); + buf_num = (size + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE; + + frag_num = skb_shinfo(skb)->nr_frags; + for (i = 0; i < frag_num; i++) { + frag = &skb_shinfo(skb)->frags[i]; + size = skb_frag_size(frag); + bdnum_for_frag = + (size + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE; + if (bdnum_for_frag > HNS3_MAX_BD_PER_FRAG) + return -ENOMEM; + + buf_num += bdnum_for_frag; + } + + if (buf_num > ring_space(ring)) + return -EBUSY; + + *bnum = buf_num; + return 0; +} + +static int hns3_nic_maybe_stop_tx(struct sk_buff **out_skb, int *bnum, + struct hns3_enet_ring *ring) +{ + struct sk_buff *skb = *out_skb; + int buf_num; + + /* No. of segments (plus a header) */ + buf_num = skb_shinfo(skb)->nr_frags + 1; + + if (buf_num > ring_space(ring)) + return -EBUSY; + + *bnum = buf_num; + + return 0; +} + +static void hns_nic_dma_unmap(struct hns3_enet_ring *ring, int next_to_use_orig) +{ + struct device *dev = ring_to_dev(ring); + unsigned int i; + + for (i = 0; i < ring->desc_num; i++) { + /* check if this is where we started */ + if (ring->next_to_use == next_to_use_orig) + break; + + /* unmap the descriptor dma address */ + if (ring->desc_cb[ring->next_to_use].type == DESC_TYPE_SKB) + dma_unmap_single(dev, + ring->desc_cb[ring->next_to_use].dma, + ring->desc_cb[ring->next_to_use].length, + DMA_TO_DEVICE); + else + dma_unmap_page(dev, + ring->desc_cb[ring->next_to_use].dma, + ring->desc_cb[ring->next_to_use].length, + DMA_TO_DEVICE); + + /* rollback one */ + ring_ptr_move_bw(ring, next_to_use); + } +} + +static netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hns3_nic_ring_data *ring_data = + &tx_ring_data(priv, skb->queue_mapping); + struct hns3_enet_ring *ring = ring_data->ring; + struct device *dev = priv->dev; + struct netdev_queue *dev_queue; + struct skb_frag_struct *frag; + int next_to_use_head; + int next_to_use_frag; + dma_addr_t dma; + int buf_num; + int seg_num; + int size; + int ret; + int i; + + /* Prefetch the data used later */ + prefetch(skb->data); + + switch (priv->ops.maybe_stop_tx(&skb, &buf_num, ring)) { + case -EBUSY: + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_busy++; + u64_stats_update_end(&ring->syncp); + + goto out_net_tx_busy; + case -ENOMEM: + u64_stats_update_begin(&ring->syncp); + ring->stats.sw_err_cnt++; + u64_stats_update_end(&ring->syncp); + netdev_err(netdev, "no memory to xmit!\n"); + + goto out_err_tx_ok; + default: + break; + } + + /* No. of segments (plus a header) */ + seg_num = skb_shinfo(skb)->nr_frags + 1; + /* Fill the first part */ + size = skb_headlen(skb); + + next_to_use_head = ring->next_to_use; + + dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma)) { + netdev_err(netdev, "TX head DMA map failed\n"); + ring->stats.sw_err_cnt++; + goto out_err_tx_ok; + } + + ret = priv->ops.fill_desc(ring, skb, size, dma, seg_num == 1 ? 1 : 0, + DESC_TYPE_SKB); + if (ret) + goto head_dma_map_err; + + next_to_use_frag = ring->next_to_use; + /* Fill the fragments */ + for (i = 1; i < seg_num; i++) { + frag = &skb_shinfo(skb)->frags[i - 1]; + size = skb_frag_size(frag); + dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma)) { + netdev_err(netdev, "TX frag(%d) DMA map failed\n", i); + ring->stats.sw_err_cnt++; + goto frag_dma_map_err; + } + ret = priv->ops.fill_desc(ring, skb_frag_page(frag), size, dma, + seg_num - 1 == i ? 1 : 0, + DESC_TYPE_PAGE); + + if (ret) + goto frag_dma_map_err; + } + + /* Complete translate all packets */ + dev_queue = netdev_get_tx_queue(netdev, ring_data->queue_index); + netdev_tx_sent_queue(dev_queue, skb->len); + + wmb(); /* Commit all data before submit */ + + hnae_queue_xmit(ring->tqp, buf_num); + + return NETDEV_TX_OK; + +frag_dma_map_err: + hns_nic_dma_unmap(ring, next_to_use_frag); + +head_dma_map_err: + hns_nic_dma_unmap(ring, next_to_use_head); + +out_err_tx_ok: + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + +out_net_tx_busy: + netif_stop_subqueue(netdev, ring_data->queue_index); + smp_mb(); /* Commit all data before submit */ + + return NETDEV_TX_BUSY; +} + +static int hns3_nic_net_set_mac_address(struct net_device *netdev, void *p) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + struct sockaddr *mac_addr = p; + int ret; + + if (!mac_addr || !is_valid_ether_addr((const u8 *)mac_addr->sa_data)) + return -EADDRNOTAVAIL; + + ret = h->ae_algo->ops->set_mac_addr(h, mac_addr->sa_data); + if (ret) { + netdev_err(netdev, "set_mac_address fail, ret=%d!\n", ret); + return ret; + } + + ether_addr_copy(netdev->dev_addr, mac_addr->sa_data); + + return 0; +} + +static int hns3_nic_set_features(struct net_device *netdev, + netdev_features_t features) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + + if (features & (NETIF_F_TSO | NETIF_F_TSO6)) { + priv->ops.fill_desc = hns3_fill_desc_tso; + priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tso; + } else { + priv->ops.fill_desc = hns3_fill_desc; + priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tx; + } + + netdev->features = features; + return 0; +} + +static void +hns3_nic_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + int queue_num = priv->ae_handle->kinfo.num_tqps; + struct hns3_enet_ring *ring; + unsigned int start; + unsigned int idx; + u64 tx_bytes = 0; + u64 rx_bytes = 0; + u64 tx_pkts = 0; + u64 rx_pkts = 0; + + for (idx = 0; idx < queue_num; idx++) { + /* fetch the tx stats */ + ring = priv->ring_data[idx].ring; + do { + tx_bytes += ring->stats.tx_bytes; + tx_pkts += ring->stats.tx_pkts; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + + /* fetch the rx stats */ + ring = priv->ring_data[idx + queue_num].ring; + do { + rx_bytes += ring->stats.rx_bytes; + rx_pkts += ring->stats.rx_pkts; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } + + stats->tx_bytes = tx_bytes; + stats->tx_packets = tx_pkts; + stats->rx_bytes = rx_bytes; + stats->rx_packets = rx_pkts; + + stats->rx_errors = netdev->stats.rx_errors; + stats->multicast = netdev->stats.multicast; + stats->rx_length_errors = netdev->stats.rx_length_errors; + stats->rx_crc_errors = netdev->stats.rx_crc_errors; + stats->rx_missed_errors = netdev->stats.rx_missed_errors; + + stats->tx_errors = netdev->stats.tx_errors; + stats->rx_dropped = netdev->stats.rx_dropped; + stats->tx_dropped = netdev->stats.tx_dropped; + stats->collisions = netdev->stats.collisions; + stats->rx_over_errors = netdev->stats.rx_over_errors; + stats->rx_frame_errors = netdev->stats.rx_frame_errors; + stats->rx_fifo_errors = netdev->stats.rx_fifo_errors; + stats->tx_aborted_errors = netdev->stats.tx_aborted_errors; + stats->tx_carrier_errors = netdev->stats.tx_carrier_errors; + stats->tx_fifo_errors = netdev->stats.tx_fifo_errors; + stats->tx_heartbeat_errors = netdev->stats.tx_heartbeat_errors; + stats->tx_window_errors = netdev->stats.tx_window_errors; + stats->rx_compressed = netdev->stats.rx_compressed; + stats->tx_compressed = netdev->stats.tx_compressed; +} + +static void hns3_add_tunnel_port(struct net_device *netdev, u16 port, + enum hns3_udp_tnl_type type) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hns3_udp_tunnel *udp_tnl = &priv->udp_tnl[type]; + struct hnae3_handle *h = priv->ae_handle; + + if (udp_tnl->used && udp_tnl->dst_port == port) { + udp_tnl->used++; + return; + } + + if (udp_tnl->used) { + netdev_warn(netdev, + "UDP tunnel [%d], port [%d] offload\n", type, port); + return; + } + + udp_tnl->dst_port = port; + udp_tnl->used = 1; + /* TBD send command to hardware to add port */ + if (h->ae_algo->ops->add_tunnel_udp) + h->ae_algo->ops->add_tunnel_udp(h, port); +} + +static void hns3_del_tunnel_port(struct net_device *netdev, u16 port, + enum hns3_udp_tnl_type type) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hns3_udp_tunnel *udp_tnl = &priv->udp_tnl[type]; + struct hnae3_handle *h = priv->ae_handle; + + if (!udp_tnl->used || udp_tnl->dst_port != port) { + netdev_warn(netdev, + "Invalid UDP tunnel port %d\n", port); + return; + } + + udp_tnl->used--; + if (udp_tnl->used) + return; + + udp_tnl->dst_port = 0; + /* TBD send command to hardware to del port */ + if (h->ae_algo->ops->del_tunnel_udp) + h->ae_algo->ops->add_tunnel_udp(h, port); +} + +/* hns3_nic_udp_tunnel_add - Get notifiacetion about UDP tunnel ports + * @netdev: This physical ports's netdev + * @ti: Tunnel information + */ +static void hns3_nic_udp_tunnel_add(struct net_device *netdev, + struct udp_tunnel_info *ti) +{ + u16 port_n = ntohs(ti->port); + + switch (ti->type) { + case UDP_TUNNEL_TYPE_VXLAN: + hns3_add_tunnel_port(netdev, port_n, HNS3_UDP_TNL_VXLAN); + break; + case UDP_TUNNEL_TYPE_GENEVE: + hns3_add_tunnel_port(netdev, port_n, HNS3_UDP_TNL_GENEVE); + break; + default: + netdev_err(netdev, "unsupported tunnel type %d\n", ti->type); + break; + } +} + +static void hns3_nic_udp_tunnel_del(struct net_device *netdev, + struct udp_tunnel_info *ti) +{ + u16 port_n = ntohs(ti->port); + + switch (ti->type) { + case UDP_TUNNEL_TYPE_VXLAN: + hns3_del_tunnel_port(netdev, port_n, HNS3_UDP_TNL_VXLAN); + break; + case UDP_TUNNEL_TYPE_GENEVE: + hns3_del_tunnel_port(netdev, port_n, HNS3_UDP_TNL_GENEVE); + break; + default: + break; + } +} + +static int hns3_setup_tc(struct net_device *netdev, u8 tc) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + struct hnae3_knic_private_info *kinfo = &h->kinfo; + unsigned int i; + int ret; + + if (tc > HNAE3_MAX_TC) + return -EINVAL; + + if (kinfo->num_tc == tc) + return 0; + + if (!netdev) + return -EINVAL; + + if (!tc) { + netdev_reset_tc(netdev); + return 0; + } + + /* Set num_tc for netdev */ + ret = netdev_set_num_tc(netdev, tc); + if (ret) + return ret; + + /* Set per TC queues for the VSI */ + for (i = 0; i < HNAE3_MAX_TC; i++) { + if (kinfo->tc_info[i].enable) + netdev_set_tc_queue(netdev, + kinfo->tc_info[i].tc, + kinfo->tc_info[i].tqp_count, + kinfo->tc_info[i].tqp_offset); + } + + return 0; +} + +static int hns3_nic_setup_tc(struct net_device *dev, u32 handle, + u32 chain_index, __be16 protocol, + struct tc_to_netdev *tc) +{ + if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO) + return -EINVAL; + + return hns3_setup_tc(dev, tc->mqprio->num_tc); +} + +static int hns3_vlan_rx_add_vid(struct net_device *netdev, + __be16 proto, u16 vid) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + int ret = -EIO; + + if (h->ae_algo->ops->set_vlan_filter) + ret = h->ae_algo->ops->set_vlan_filter(h, proto, vid, false); + + return ret; +} + +static int hns3_vlan_rx_kill_vid(struct net_device *netdev, + __be16 proto, u16 vid) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + int ret = -EIO; + + if (h->ae_algo->ops->set_vlan_filter) + ret = h->ae_algo->ops->set_vlan_filter(h, proto, vid, true); + + return ret; +} + +static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, + u8 qos, __be16 vlan_proto) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + int ret = -EIO; + + if (h->ae_algo->ops->set_vf_vlan_filter) + ret = h->ae_algo->ops->set_vf_vlan_filter(h, vf, vlan, + qos, vlan_proto); + + return ret; +} + +static const struct net_device_ops hns3_nic_netdev_ops = { + .ndo_open = hns3_nic_net_open, + .ndo_stop = hns3_nic_net_stop, + .ndo_start_xmit = hns3_nic_net_xmit, + .ndo_set_mac_address = hns3_nic_net_set_mac_address, + .ndo_set_features = hns3_nic_set_features, + .ndo_get_stats64 = hns3_nic_get_stats64, + .ndo_setup_tc = hns3_nic_setup_tc, + .ndo_set_rx_mode = hns3_nic_set_rx_mode, + .ndo_udp_tunnel_add = hns3_nic_udp_tunnel_add, + .ndo_udp_tunnel_del = hns3_nic_udp_tunnel_del, + .ndo_vlan_rx_add_vid = hns3_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = hns3_vlan_rx_kill_vid, + .ndo_set_vf_vlan = hns3_ndo_set_vf_vlan, +}; + +/* hns3_probe - Device initialization routine + * @pdev: PCI device information struct + * @ent: entry in hns3_pci_tbl + * + * hns3_probe initializes a PF identified by a pci_dev structure. + * The OS initialization, configuring of the PF private structure, + * and a hardware reset occur. + * + * Returns 0 on success, negative on failure + */ +static int hns3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct hnae3_ae_dev *ae_dev; + int ret; + + ae_dev = devm_kzalloc(&pdev->dev, sizeof(*ae_dev), + GFP_KERNEL); + if (!ae_dev) { + ret = -ENOMEM; + return ret; + } + + ae_dev->pdev = pdev; + ae_dev->dev_type = HNAE3_DEV_KNIC; + pci_set_drvdata(pdev, ae_dev); + + return hnae3_register_ae_dev(ae_dev); +} + +/* hns3_remove - Device removal routine + * @pdev: PCI device information struct + */ +static void hns3_remove(struct pci_dev *pdev) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev); + + hnae3_unregister_ae_dev(ae_dev); + + devm_kfree(&pdev->dev, ae_dev); + + pci_set_drvdata(pdev, NULL); +} + +static struct pci_driver hns3_driver = { + .name = hns3_driver_name, + .id_table = hns3_pci_tbl, + .probe = hns3_probe, + .remove = hns3_remove, +}; + +/* set default feature to hns3 */ +static void hns3_set_default_feature(struct net_device *netdev) +{ + netdev->priv_flags |= IFF_UNICAST_FLT; + + netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | + NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; + + netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; + + netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM; + + netdev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | + NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; + + netdev->vlan_features |= + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | + NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO | + NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; + + netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | + NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; +} + +static int hns3_alloc_buffer(struct hns3_enet_ring *ring, + struct hns3_desc_cb *cb) +{ + unsigned int order = hnae_page_order(ring); + struct page *p; + + p = dev_alloc_pages(order); + if (!p) + return -ENOMEM; + + cb->priv = p; + cb->page_offset = 0; + cb->reuse_flag = 0; + cb->buf = page_address(p); + cb->length = hnae_page_size(ring); + cb->type = DESC_TYPE_PAGE; + + memset(cb->buf, 0, cb->length); + + return 0; +} + +static void hns3_free_buffer(struct hns3_enet_ring *ring, + struct hns3_desc_cb *cb) +{ + if (cb->type == DESC_TYPE_SKB) + dev_kfree_skb_any((struct sk_buff *)cb->priv); + else if (!HNAE3_IS_TX_RING(ring)) + put_page((struct page *)cb->priv); + memset(cb, 0, sizeof(*cb)); +} + +static int hns3_map_buffer(struct hns3_enet_ring *ring, struct hns3_desc_cb *cb) +{ + cb->dma = dma_map_page(ring_to_dev(ring), cb->priv, 0, + cb->length, ring_to_dma_dir(ring)); + + if (dma_mapping_error(ring_to_dev(ring), cb->dma)) + return -EIO; + + return 0; +} + +static void hns3_unmap_buffer(struct hns3_enet_ring *ring, + struct hns3_desc_cb *cb) +{ + if (cb->type == DESC_TYPE_SKB) + dma_unmap_single(ring_to_dev(ring), cb->dma, cb->length, + ring_to_dma_dir(ring)); + else + dma_unmap_page(ring_to_dev(ring), cb->dma, cb->length, + ring_to_dma_dir(ring)); +} + +static void hns3_buffer_detach(struct hns3_enet_ring *ring, int i) +{ + hns3_unmap_buffer(ring, &ring->desc_cb[i]); + ring->desc[i].addr = 0; +} + +static void hns3_free_buffer_detach(struct hns3_enet_ring *ring, int i) +{ + struct hns3_desc_cb *cb = &ring->desc_cb[i]; + + if (!ring->desc_cb[i].dma) + return; + + hns3_buffer_detach(ring, i); + hns3_free_buffer(ring, cb); +} + +static void hns3_free_buffers(struct hns3_enet_ring *ring) +{ + int i; + + for (i = 0; i < ring->desc_num; i++) + hns3_free_buffer_detach(ring, i); +} + +/* free desc along with its attached buffer */ +static void hns3_free_desc(struct hns3_enet_ring *ring) +{ + hns3_free_buffers(ring); + + dma_unmap_single(ring_to_dev(ring), ring->desc_dma_addr, + ring->desc_num * sizeof(ring->desc[0]), + DMA_BIDIRECTIONAL); + ring->desc_dma_addr = 0; + kfree(ring->desc); + ring->desc = NULL; +} + +static int hns3_alloc_desc(struct hns3_enet_ring *ring) +{ + int size = ring->desc_num * sizeof(ring->desc[0]); + + ring->desc = kzalloc(size, GFP_KERNEL); + if (!ring->desc) + return -ENOMEM; + + ring->desc_dma_addr = dma_map_single(ring_to_dev(ring), ring->desc, + size, DMA_BIDIRECTIONAL); + if (dma_mapping_error(ring_to_dev(ring), ring->desc_dma_addr)) { + ring->desc_dma_addr = 0; + kfree(ring->desc); + ring->desc = NULL; + return -ENOMEM; + } + + return 0; +} + +static int hns3_reserve_buffer_map(struct hns3_enet_ring *ring, + struct hns3_desc_cb *cb) +{ + int ret; + + ret = hns3_alloc_buffer(ring, cb); + if (ret) + goto out; + + ret = hns3_map_buffer(ring, cb); + if (ret) + goto out_with_buf; + + return 0; + +out_with_buf: + hns3_free_buffers(ring); +out: + return ret; +} + +static int hns3_alloc_buffer_attach(struct hns3_enet_ring *ring, int i) +{ + int ret = hns3_reserve_buffer_map(ring, &ring->desc_cb[i]); + + if (ret) + return ret; + + ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma); + + return 0; +} + +/* Allocate memory for raw pkg, and map with dma */ +static int hns3_alloc_ring_buffers(struct hns3_enet_ring *ring) +{ + int i, j, ret; + + for (i = 0; i < ring->desc_num; i++) { + ret = hns3_alloc_buffer_attach(ring, i); + if (ret) + goto out_buffer_fail; + } + + return 0; + +out_buffer_fail: + for (j = i - 1; j >= 0; j--) + hns3_free_buffer_detach(ring, j); + return ret; +} + +/* detach a in-used buffer and replace with a reserved one */ +static void hns3_replace_buffer(struct hns3_enet_ring *ring, int i, + struct hns3_desc_cb *res_cb) +{ + hns3_map_buffer(ring, &ring->desc_cb[i]); + ring->desc_cb[i] = *res_cb; + ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma); +} + +static void hns3_reuse_buffer(struct hns3_enet_ring *ring, int i) +{ + ring->desc_cb[i].reuse_flag = 0; + ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma + + ring->desc_cb[i].page_offset); +} + +static void hns3_nic_reclaim_one_desc(struct hns3_enet_ring *ring, int *bytes, + int *pkts) +{ + struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_clean]; + + (*pkts) += (desc_cb->type == DESC_TYPE_SKB); + (*bytes) += desc_cb->length; + /* desc_cb will be cleaned, after hnae_free_buffer_detach*/ + hns3_free_buffer_detach(ring, ring->next_to_clean); + + ring_ptr_move_fw(ring, next_to_clean); +} + +static int is_valid_clean_head(struct hns3_enet_ring *ring, int h) +{ + int u = ring->next_to_use; + int c = ring->next_to_clean; + + if (unlikely(h > ring->desc_num)) + return 0; + + return u > c ? (h > c && h <= u) : (h > c || h <= u); +} + +int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget) +{ + struct net_device *netdev = ring->tqp->handle->kinfo.netdev; + struct netdev_queue *dev_queue; + int bytes, pkts; + int head; + + head = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_HEAD_REG); + rmb(); /* Make sure head is ready before touch any data */ + + if (is_ring_empty(ring) || head == ring->next_to_clean) + return 0; /* no data to poll */ + + if (!is_valid_clean_head(ring, head)) { + netdev_err(netdev, "wrong head (%d, %d-%d)\n", head, + ring->next_to_use, ring->next_to_clean); + + u64_stats_update_begin(&ring->syncp); + ring->stats.io_err_cnt++; + u64_stats_update_end(&ring->syncp); + return -EIO; + } + + bytes = 0; + pkts = 0; + while (head != ring->next_to_clean && budget) { + hns3_nic_reclaim_one_desc(ring, &bytes, &pkts); + /* Issue prefetch for next Tx descriptor */ + prefetch(&ring->desc_cb[ring->next_to_clean]); + budget--; + } + + ring->tqp_vector->tx_group.total_bytes += bytes; + ring->tqp_vector->tx_group.total_packets += pkts; + + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_bytes += bytes; + ring->stats.tx_pkts += pkts; + u64_stats_update_end(&ring->syncp); + + dev_queue = netdev_get_tx_queue(netdev, ring->tqp->tqp_index); + netdev_tx_completed_queue(dev_queue, pkts, bytes); + + if (unlikely(pkts && netif_carrier_ok(netdev) && + (ring_space(ring) > HNS3_MAX_BD_PER_PKT))) { + /* Make sure that anybody stopping the queue after this + * sees the new next_to_clean. + */ + smp_mb(); + if (netif_tx_queue_stopped(dev_queue)) { + netif_tx_wake_queue(dev_queue); + ring->stats.restart_queue++; + } + } + + return !!budget; +} + +static int hns3_desc_unused(struct hns3_enet_ring *ring) +{ + int ntc = ring->next_to_clean; + int ntu = ring->next_to_use; + + return ((ntc >= ntu) ? 0 : ring->desc_num) + ntc - ntu; +} + +static void +hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring, int cleand_count) +{ + struct hns3_desc_cb *desc_cb; + struct hns3_desc_cb res_cbs; + int i, ret; + + for (i = 0; i < cleand_count; i++) { + desc_cb = &ring->desc_cb[ring->next_to_use]; + if (desc_cb->reuse_flag) { + u64_stats_update_begin(&ring->syncp); + ring->stats.reuse_pg_cnt++; + u64_stats_update_end(&ring->syncp); + + hns3_reuse_buffer(ring, ring->next_to_use); + } else { + ret = hns3_reserve_buffer_map(ring, &res_cbs); + if (ret) { + u64_stats_update_begin(&ring->syncp); + ring->stats.sw_err_cnt++; + u64_stats_update_end(&ring->syncp); + + netdev_err(ring->tqp->handle->kinfo.netdev, + "hnae reserve buffer map failed.\n"); + break; + } + hns3_replace_buffer(ring, ring->next_to_use, &res_cbs); + } + + ring_ptr_move_fw(ring, next_to_use); + } + + wmb(); /* Make all data has been write before submit */ + writel_relaxed(i, ring->tqp->io_base + HNS3_RING_RX_RING_HEAD_REG); +} + +/* hns3_nic_get_headlen - determine size of header for LRO/GRO + * @data: pointer to the start of the headers + * @max: total length of section to find headers in + * + * This function is meant to determine the length of headers that will + * be recognized by hardware for LRO, GRO, and RSC offloads. The main + * motivation of doing this is to only perform one pull for IPv4 TCP + * packets so that we can do basic things like calculating the gso_size + * based on the average data per packet. + */ +static unsigned int hns3_nic_get_headlen(unsigned char *data, u32 flag, + unsigned int max_size) +{ + unsigned char *network; + u8 hlen; + + /* This should never happen, but better safe than sorry */ + if (max_size < ETH_HLEN) + return max_size; + + /* Initialize network frame pointer */ + network = data; + + /* Set first protocol and move network header forward */ + network += ETH_HLEN; + + /* Handle any vlan tag if present */ + if (hnae_get_field(flag, HNS3_RXD_VLAN_M, HNS3_RXD_VLAN_S) + == HNS3_RX_FLAG_VLAN_PRESENT) { + if ((typeof(max_size))(network - data) > (max_size - VLAN_HLEN)) + return max_size; + + network += VLAN_HLEN; + } + + /* Handle L3 protocols */ + if (hnae_get_field(flag, HNS3_RXD_L3ID_M, HNS3_RXD_L3ID_S) + == HNS3_RX_FLAG_L3ID_IPV4) { + if ((typeof(max_size))(network - data) > + (max_size - sizeof(struct iphdr))) + return max_size; + + /* Access ihl as a u8 to avoid unaligned access on ia64 */ + hlen = (network[0] & 0x0F) << 2; + + /* Verify hlen meets minimum size requirements */ + if (hlen < sizeof(struct iphdr)) + return network - data; + + /* Record next protocol if header is present */ + } else if (hnae_get_field(flag, HNS3_RXD_L3ID_M, HNS3_RXD_L3ID_S) + == HNS3_RX_FLAG_L3ID_IPV6) { + if ((typeof(max_size))(network - data) > + (max_size - sizeof(struct ipv6hdr))) + return max_size; + + /* Record next protocol */ + hlen = sizeof(struct ipv6hdr); + } else { + return network - data; + } + + /* Relocate pointer to start of L4 header */ + network += hlen; + + /* Finally sort out TCP/UDP */ + if (hnae_get_field(flag, HNS3_RXD_L4ID_M, HNS3_RXD_L4ID_S) + == HNS3_RX_FLAG_L4ID_TCP) { + if ((typeof(max_size))(network - data) > + (max_size - sizeof(struct tcphdr))) + return max_size; + + /* Access doff as a u8 to avoid unaligned access on ia64 */ + hlen = (network[12] & 0xF0) >> 2; + + /* Verify hlen meets minimum size requirements */ + if (hlen < sizeof(struct tcphdr)) + return network - data; + + network += hlen; + } else if (hnae_get_field(flag, HNS3_RXD_L4ID_M, HNS3_RXD_L4ID_S) + == HNS3_RX_FLAG_L4ID_UDP) { + if ((typeof(max_size))(network - data) > + (max_size - sizeof(struct udphdr))) + return max_size; + + network += sizeof(struct udphdr); + } + + /* If everything has gone correctly network should be the + * data section of the packet and will be the end of the header. + * If not then it probably represents the end of the last recognized + * header. + */ + if ((typeof(max_size))(network - data) < max_size) + return network - data; + else + return max_size; +} + +static void hns3_nic_reuse_page(struct sk_buff *skb, int i, + struct hns3_enet_ring *ring, int pull_len, + struct hns3_desc_cb *desc_cb) +{ + struct hns3_desc *desc; + int truesize, size; + int last_offset; + bool twobufs; + + twobufs = ((PAGE_SIZE < 8192) && + hnae_buf_size(ring) == HNS3_BUFFER_SIZE_2048); + + desc = &ring->desc[ring->next_to_clean]; + size = le16_to_cpu(desc->rx.size); + + if (twobufs) { + truesize = hnae_buf_size(ring); + } else { + truesize = ALIGN(size, L1_CACHE_BYTES); + last_offset = hnae_page_size(ring) - hnae_buf_size(ring); + } + + skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len, + size - pull_len, truesize - pull_len); + + /* Avoid re-using remote pages,flag default unreuse */ + if (unlikely(page_to_nid(desc_cb->priv) != numa_node_id())) + return; + + if (twobufs) { + /* If we are only owner of page we can reuse it */ + if (likely(page_count(desc_cb->priv) == 1)) { + /* Flip page offset to other buffer */ + desc_cb->page_offset ^= truesize; + + desc_cb->reuse_flag = 1; + /* bump ref count on page before it is given*/ + get_page(desc_cb->priv); + } + return; + } + + /* Move offset up to the next cache line */ + desc_cb->page_offset += truesize; + + if (desc_cb->page_offset <= last_offset) { + desc_cb->reuse_flag = 1; + /* Bump ref count on page before it is given*/ + get_page(desc_cb->priv); + } +} + +static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb, + struct hns3_desc *desc) +{ + struct net_device *netdev = ring->tqp->handle->kinfo.netdev; + int l3_type, l4_type; + u32 bd_base_info; + int ol4_type; + u32 l234info; + + bd_base_info = le32_to_cpu(desc->rx.bd_base_info); + l234info = le32_to_cpu(desc->rx.l234_info); + + skb->ip_summed = CHECKSUM_NONE; + + skb_checksum_none_assert(skb); + + if (!(netdev->features & NETIF_F_RXCSUM)) + return; + + /* check if hardware has done checksum */ + if (!hnae_get_bit(bd_base_info, HNS3_RXD_L3L4P_B)) + return; + + if (unlikely(hnae_get_bit(l234info, HNS3_RXD_L3E_B) || + hnae_get_bit(l234info, HNS3_RXD_L4E_B) || + hnae_get_bit(l234info, HNS3_RXD_OL3E_B) || + hnae_get_bit(l234info, HNS3_RXD_OL4E_B))) { + netdev_err(netdev, "L3/L4 error pkt\n"); + u64_stats_update_begin(&ring->syncp); + ring->stats.l3l4_csum_err++; + u64_stats_update_end(&ring->syncp); + + return; + } + + l3_type = hnae_get_field(l234info, HNS3_RXD_L3ID_M, + HNS3_RXD_L3ID_S); + l4_type = hnae_get_field(l234info, HNS3_RXD_L4ID_M, + HNS3_RXD_L4ID_S); + + ol4_type = hnae_get_field(l234info, HNS3_RXD_OL4ID_M, HNS3_RXD_OL4ID_S); + switch (ol4_type) { + case HNS3_OL4_TYPE_MAC_IN_UDP: + case HNS3_OL4_TYPE_NVGRE: + skb->csum_level = 1; + case HNS3_OL4_TYPE_NO_TUN: + /* Can checksum ipv4 or ipv6 + UDP/TCP/SCTP packets */ + if (l3_type == HNS3_L3_TYPE_IPV4 || + (l3_type == HNS3_L3_TYPE_IPV6 && + (l4_type == HNS3_L4_TYPE_UDP || + l4_type == HNS3_L4_TYPE_TCP || + l4_type == HNS3_L4_TYPE_SCTP))) + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } +} + +static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, + struct sk_buff **out_skb, int *out_bnum) +{ + struct net_device *netdev = ring->tqp->handle->kinfo.netdev; + struct hns3_desc_cb *desc_cb; + struct hns3_desc *desc; + struct sk_buff *skb; + unsigned char *va; + u32 bd_base_info; + int pull_len; + u32 l234info; + int length; + int bnum; + + desc = &ring->desc[ring->next_to_clean]; + desc_cb = &ring->desc_cb[ring->next_to_clean]; + + prefetch(desc); + + length = le16_to_cpu(desc->rx.pkt_len); + bd_base_info = le32_to_cpu(desc->rx.bd_base_info); + l234info = le32_to_cpu(desc->rx.l234_info); + + /* Check valid BD */ + if (!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B)) + return -EFAULT; + + va = (unsigned char *)desc_cb->buf + desc_cb->page_offset; + + /* Prefetch first cache line of first page + * Idea is to cache few bytes of the header of the packet. Our L1 Cache + * line size is 64B so need to prefetch twice to make it 128B. But in + * actual we can have greater size of caches with 128B Level 1 cache + * lines. In such a case, single fetch would suffice to cache in the + * relevant part of the header. + */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + + skb = *out_skb = napi_alloc_skb(&ring->tqp_vector->napi, + HNS3_RX_HEAD_SIZE); + if (unlikely(!skb)) { + netdev_err(netdev, "alloc rx skb fail\n"); + + u64_stats_update_begin(&ring->syncp); + ring->stats.sw_err_cnt++; + u64_stats_update_end(&ring->syncp); + + return -ENOMEM; + } + + prefetchw(skb->data); + + bnum = 1; + if (length <= HNS3_RX_HEAD_SIZE) { + memcpy(__skb_put(skb, length), va, ALIGN(length, sizeof(long))); + + /* We can reuse buffer as-is, just make sure it is local */ + if (likely(page_to_nid(desc_cb->priv) == numa_node_id())) + desc_cb->reuse_flag = 1; + else /* This page cannot be reused so discard it */ + put_page(desc_cb->priv); + + ring_ptr_move_fw(ring, next_to_clean); + } else { + u64_stats_update_begin(&ring->syncp); + ring->stats.seg_pkt_cnt++; + u64_stats_update_end(&ring->syncp); + + pull_len = hns3_nic_get_headlen(va, l234info, + HNS3_RX_HEAD_SIZE); + memcpy(__skb_put(skb, pull_len), va, + ALIGN(pull_len, sizeof(long))); + + hns3_nic_reuse_page(skb, 0, ring, pull_len, desc_cb); + ring_ptr_move_fw(ring, next_to_clean); + + while (!hnae_get_bit(bd_base_info, HNS3_RXD_FE_B)) { + desc = &ring->desc[ring->next_to_clean]; + desc_cb = &ring->desc_cb[ring->next_to_clean]; + bd_base_info = le32_to_cpu(desc->rx.bd_base_info); + hns3_nic_reuse_page(skb, bnum, ring, 0, desc_cb); + ring_ptr_move_fw(ring, next_to_clean); + bnum++; + } + } + + *out_bnum = bnum; + + if (unlikely(!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B))) { + netdev_err(netdev, "no valid bd,%016llx,%016llx\n", + ((u64 *)desc)[0], ((u64 *)desc)[1]); + u64_stats_update_begin(&ring->syncp); + ring->stats.non_vld_descs++; + u64_stats_update_end(&ring->syncp); + + dev_kfree_skb_any(skb); + return -EINVAL; + } + + if (unlikely((!desc->rx.pkt_len) || + hnae_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) { + netdev_err(netdev, "truncated pkt\n"); + u64_stats_update_begin(&ring->syncp); + ring->stats.err_pkt_len++; + u64_stats_update_end(&ring->syncp); + + dev_kfree_skb_any(skb); + return -EFAULT; + } + + if (unlikely(hnae_get_bit(l234info, HNS3_RXD_L2E_B))) { + netdev_err(netdev, "L2 error pkt\n"); + u64_stats_update_begin(&ring->syncp); + ring->stats.l2_err++; + u64_stats_update_end(&ring->syncp); + + dev_kfree_skb_any(skb); + return -EFAULT; + } + + u64_stats_update_begin(&ring->syncp); + ring->stats.rx_pkts++; + ring->stats.rx_bytes += skb->len; + u64_stats_update_end(&ring->syncp); + + ring->tqp_vector->rx_group.total_bytes += skb->len; + + hns3_rx_checksum(ring, skb, desc); + return 0; +} + +static int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget) +{ +#define RCB_NOF_ALLOC_RX_BUFF_ONCE 16 + struct net_device *netdev = ring->tqp->handle->kinfo.netdev; + int recv_pkts, recv_bds, clean_count, err; + int unused_count = hns3_desc_unused(ring); + struct sk_buff *skb = NULL; + int num, bnum = 0; + + num = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_FBDNUM_REG); + rmb(); /* Make sure num taken effect before the other data is touched */ + + recv_pkts = 0, recv_bds = 0, clean_count = 0; + num -= unused_count; + + while (recv_pkts < budget && recv_bds < num) { + /* Reuse or realloc buffers */ + if (clean_count + unused_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) { + hns3_nic_alloc_rx_buffers(ring, + clean_count + unused_count); + clean_count = 0; + unused_count = hns3_desc_unused(ring); + } + + /* Poll one pkt */ + err = hns3_handle_rx_bd(ring, &skb, &bnum); + if (unlikely(!skb)) /* This fault cannot be repaired */ + goto out; + + recv_bds += bnum; + clean_count += bnum; + if (unlikely(err)) { /* Do jump the err */ + recv_pkts++; + continue; + } + + /* Do update ip stack process */ + skb->protocol = eth_type_trans(skb, netdev); + (void)napi_gro_receive(&ring->tqp_vector->napi, skb); + + recv_pkts++; + } + +out: + /* Make all data has been write before submit */ + if (clean_count + unused_count > 0) + hns3_nic_alloc_rx_buffers(ring, + clean_count + unused_count); + + return recv_pkts; +} + +static bool hns3_get_new_int_gl(struct hns3_enet_ring_group *ring_group) +{ +#define HNS3_RX_ULTRA_PACKET_RATE 40000 + enum hns3_flow_level_range new_flow_level; + struct hns3_enet_tqp_vector *tqp_vector; + int packets_per_secs; + int bytes_per_usecs; + u16 new_int_gl; + int usecs; + + if (!ring_group->int_gl) + return false; + + if (ring_group->total_packets == 0) { + ring_group->int_gl = HNS3_INT_GL_50K; + ring_group->flow_level = HNS3_FLOW_LOW; + return true; + } + + /* Simple throttlerate management + * 0-10MB/s lower (50000 ints/s) + * 10-20MB/s middle (20000 ints/s) + * 20-1249MB/s high (18000 ints/s) + * > 40000pps ultra (8000 ints/s) + */ + new_flow_level = ring_group->flow_level; + new_int_gl = ring_group->int_gl; + tqp_vector = ring_group->ring->tqp_vector; + usecs = (ring_group->int_gl << 1); + bytes_per_usecs = ring_group->total_bytes / usecs; + /* 1000000 microseconds */ + packets_per_secs = ring_group->total_packets * 1000000 / usecs; + + switch (new_flow_level) { + case HNS3_FLOW_LOW: + if (bytes_per_usecs > 10) + new_flow_level = HNS3_FLOW_MID; + break; + case HNS3_FLOW_MID: + if (bytes_per_usecs > 20) + new_flow_level = HNS3_FLOW_HIGH; + else if (bytes_per_usecs <= 10) + new_flow_level = HNS3_FLOW_LOW; + break; + case HNS3_FLOW_HIGH: + case HNS3_FLOW_ULTRA: + default: + if (bytes_per_usecs <= 20) + new_flow_level = HNS3_FLOW_MID; + break; + } + + if ((packets_per_secs > HNS3_RX_ULTRA_PACKET_RATE) && + (&tqp_vector->rx_group == ring_group)) + new_flow_level = HNS3_FLOW_ULTRA; + + switch (new_flow_level) { + case HNS3_FLOW_LOW: + new_int_gl = HNS3_INT_GL_50K; + break; + case HNS3_FLOW_MID: + new_int_gl = HNS3_INT_GL_20K; + break; + case HNS3_FLOW_HIGH: + new_int_gl = HNS3_INT_GL_18K; + break; + case HNS3_FLOW_ULTRA: + new_int_gl = HNS3_INT_GL_8K; + break; + default: + break; + } + + ring_group->total_bytes = 0; + ring_group->total_packets = 0; + ring_group->flow_level = new_flow_level; + if (new_int_gl != ring_group->int_gl) { + ring_group->int_gl = new_int_gl; + return true; + } + return false; +} + +static void hns3_update_new_int_gl(struct hns3_enet_tqp_vector *tqp_vector) +{ + u16 rx_int_gl, tx_int_gl; + bool rx, tx; + + rx = hns3_get_new_int_gl(&tqp_vector->rx_group); + tx = hns3_get_new_int_gl(&tqp_vector->tx_group); + rx_int_gl = tqp_vector->rx_group.int_gl; + tx_int_gl = tqp_vector->tx_group.int_gl; + if (rx && tx) { + if (rx_int_gl > tx_int_gl) { + tqp_vector->tx_group.int_gl = rx_int_gl; + tqp_vector->tx_group.flow_level = + tqp_vector->rx_group.flow_level; + hns3_set_vector_coalesc_gl(tqp_vector, rx_int_gl); + } else { + tqp_vector->rx_group.int_gl = tx_int_gl; + tqp_vector->rx_group.flow_level = + tqp_vector->tx_group.flow_level; + hns3_set_vector_coalesc_gl(tqp_vector, tx_int_gl); + } + } +} + +static int hns3_nic_common_poll(struct napi_struct *napi, int budget) +{ + struct hns3_enet_ring *ring; + int rx_pkt_total = 0; + + struct hns3_enet_tqp_vector *tqp_vector = + container_of(napi, struct hns3_enet_tqp_vector, napi); + bool clean_complete = true; + int rx_budget; + + /* Since the actual Tx work is minimal, we can give the Tx a larger + * budget and be more aggressive about cleaning up the Tx descriptors. + */ + hns3_for_each_ring(ring, tqp_vector->tx_group) { + if (!hns3_clean_tx_ring(ring, budget)) + clean_complete = false; + } + + /* make sure rx ring budget not smaller than 1 */ + rx_budget = max(budget / tqp_vector->num_tqps, 1); + + hns3_for_each_ring(ring, tqp_vector->rx_group) { + int rx_cleaned = hns3_clean_rx_ring(ring, rx_budget); + + if (rx_cleaned >= rx_budget) + clean_complete = false; + + rx_pkt_total += rx_cleaned; + } + + tqp_vector->rx_group.total_packets += rx_pkt_total; + + if (!clean_complete) + return budget; + + napi_complete(napi); + hns3_update_new_int_gl(tqp_vector); + hns3_mask_vector_irq(tqp_vector, 1); + + return rx_pkt_total; +} + +static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, + struct hnae3_ring_chain_node *head) +{ + struct pci_dev *pdev = tqp_vector->handle->pdev; + struct hnae3_ring_chain_node *cur_chain = head; + struct hnae3_ring_chain_node *chain; + struct hns3_enet_ring *tx_ring; + struct hns3_enet_ring *rx_ring; + + tx_ring = tqp_vector->tx_group.ring; + if (tx_ring) { + cur_chain->tqp_index = tx_ring->tqp->tqp_index; + hnae_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B, + HNAE3_RING_TYPE_TX); + + cur_chain->next = NULL; + + while (tx_ring->next) { + tx_ring = tx_ring->next; + + chain = devm_kzalloc(&pdev->dev, sizeof(*chain), + GFP_KERNEL); + if (!chain) + return -ENOMEM; + + cur_chain->next = chain; + chain->tqp_index = tx_ring->tqp->tqp_index; + hnae_set_bit(chain->flag, HNAE3_RING_TYPE_B, + HNAE3_RING_TYPE_TX); + + cur_chain = chain; + } + } + + rx_ring = tqp_vector->rx_group.ring; + if (!tx_ring && rx_ring) { + cur_chain->next = NULL; + cur_chain->tqp_index = rx_ring->tqp->tqp_index; + hnae_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B, + HNAE3_RING_TYPE_RX); + + rx_ring = rx_ring->next; + } + + while (rx_ring) { + chain = devm_kzalloc(&pdev->dev, sizeof(*chain), GFP_KERNEL); + if (!chain) + return -ENOMEM; + + cur_chain->next = chain; + chain->tqp_index = rx_ring->tqp->tqp_index; + hnae_set_bit(chain->flag, HNAE3_RING_TYPE_B, + HNAE3_RING_TYPE_RX); + cur_chain = chain; + + rx_ring = rx_ring->next; + } + + return 0; +} + +static void hns3_free_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, + struct hnae3_ring_chain_node *head) +{ + struct pci_dev *pdev = tqp_vector->handle->pdev; + struct hnae3_ring_chain_node *chain_tmp, *chain; + + chain = head->next; + + while (chain) { + chain_tmp = chain->next; + devm_kfree(&pdev->dev, chain); + chain = chain_tmp; + } +} + +static void hns3_add_ring_to_group(struct hns3_enet_ring_group *group, + struct hns3_enet_ring *ring) +{ + ring->next = group->ring; + group->ring = ring; + + group->count++; +} + +static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv) +{ + struct hnae3_ring_chain_node vector_ring_chain; + struct hnae3_handle *h = priv->ae_handle; + struct hns3_enet_tqp_vector *tqp_vector; + struct hnae3_vector_info *vector; + struct pci_dev *pdev = h->pdev; + u16 tqp_num = h->kinfo.num_tqps; + u16 vector_num; + int ret = 0; + u16 i; + + /* RSS size, cpu online and vector_num should be the same */ + /* Should consider 2p/4p later */ + vector_num = min_t(u16, num_online_cpus(), tqp_num); + vector = devm_kcalloc(&pdev->dev, vector_num, sizeof(*vector), + GFP_KERNEL); + if (!vector) + return -ENOMEM; + + vector_num = h->ae_algo->ops->get_vector(h, vector_num, vector); + + priv->vector_num = vector_num; + priv->tqp_vector = (struct hns3_enet_tqp_vector *) + devm_kcalloc(&pdev->dev, vector_num, sizeof(*priv->tqp_vector), + GFP_KERNEL); + if (!priv->tqp_vector) + return -ENOMEM; + + for (i = 0; i < tqp_num; i++) { + u16 vector_i = i % vector_num; + + tqp_vector = &priv->tqp_vector[vector_i]; + + hns3_add_ring_to_group(&tqp_vector->tx_group, + priv->ring_data[i].ring); + + hns3_add_ring_to_group(&tqp_vector->rx_group, + priv->ring_data[i + tqp_num].ring); + + tqp_vector->idx = vector_i; + tqp_vector->mask_addr = vector[vector_i].io_addr; + tqp_vector->vector_irq = vector[vector_i].vector; + tqp_vector->num_tqps++; + + priv->ring_data[i].ring->tqp_vector = tqp_vector; + priv->ring_data[i + tqp_num].ring->tqp_vector = tqp_vector; + } + + for (i = 0; i < vector_num; i++) { + tqp_vector = &priv->tqp_vector[i]; + + tqp_vector->rx_group.total_bytes = 0; + tqp_vector->rx_group.total_packets = 0; + tqp_vector->tx_group.total_bytes = 0; + tqp_vector->tx_group.total_packets = 0; + hns3_vector_gl_rl_init(tqp_vector); + tqp_vector->handle = h; + + ret = hns3_get_vector_ring_chain(tqp_vector, + &vector_ring_chain); + if (ret) + goto out; + + ret = h->ae_algo->ops->map_ring_to_vector(h, + tqp_vector->vector_irq, &vector_ring_chain); + if (ret) + goto out; + + hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain); + + netif_napi_add(priv->netdev, &tqp_vector->napi, + hns3_nic_common_poll, NAPI_POLL_WEIGHT); + } + +out: + devm_kfree(&pdev->dev, vector); + return ret; +} + +static int hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv) +{ + struct hnae3_ring_chain_node vector_ring_chain; + struct hnae3_handle *h = priv->ae_handle; + struct hns3_enet_tqp_vector *tqp_vector; + struct pci_dev *pdev = h->pdev; + int i, ret; + + for (i = 0; i < priv->vector_num; i++) { + tqp_vector = &priv->tqp_vector[i]; + + ret = hns3_get_vector_ring_chain(tqp_vector, + &vector_ring_chain); + if (ret) + return ret; + + ret = h->ae_algo->ops->unmap_ring_from_vector(h, + tqp_vector->vector_irq, &vector_ring_chain); + if (ret) + return ret; + + hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain); + + if (priv->tqp_vector[i].irq_init_flag == HNS3_VECTOR_INITED) { + (void)irq_set_affinity_hint( + priv->tqp_vector[i].vector_irq, + NULL); + devm_free_irq(&pdev->dev, + priv->tqp_vector[i].vector_irq, + &priv->tqp_vector[i]); + } + + priv->ring_data[i].ring->irq_init_flag = HNS3_VECTOR_NOT_INITED; + + netif_napi_del(&priv->tqp_vector[i].napi); + } + + devm_kfree(&pdev->dev, priv->tqp_vector); + + return 0; +} + +static int hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv, + int ring_type) +{ + struct hns3_nic_ring_data *ring_data = priv->ring_data; + int queue_num = priv->ae_handle->kinfo.num_tqps; + struct pci_dev *pdev = priv->ae_handle->pdev; + struct hns3_enet_ring *ring; + + ring = devm_kzalloc(&pdev->dev, sizeof(*ring), GFP_KERNEL); + if (!ring) + return -ENOMEM; + + if (ring_type == HNAE3_RING_TYPE_TX) { + ring_data[q->tqp_index].ring = ring; + ring->io_base = (u8 __iomem *)q->io_base + HNS3_TX_REG_OFFSET; + } else { + ring_data[q->tqp_index + queue_num].ring = ring; + ring->io_base = q->io_base; + } + + hnae_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type); + + ring_data[q->tqp_index].queue_index = q->tqp_index; + + ring->tqp = q; + ring->desc = NULL; + ring->desc_cb = NULL; + ring->dev = priv->dev; + ring->desc_dma_addr = 0; + ring->buf_size = q->buf_size; + ring->desc_num = q->desc_num; + ring->next_to_use = 0; + ring->next_to_clean = 0; + + return 0; +} + +static int hns3_queue_to_ring(struct hnae3_queue *tqp, + struct hns3_nic_priv *priv) +{ + int ret; + + ret = hns3_ring_get_cfg(tqp, priv, HNAE3_RING_TYPE_TX); + if (ret) + return ret; + + ret = hns3_ring_get_cfg(tqp, priv, HNAE3_RING_TYPE_RX); + if (ret) + return ret; + + return 0; +} + +static int hns3_get_ring_config(struct hns3_nic_priv *priv) +{ + struct hnae3_handle *h = priv->ae_handle; + struct pci_dev *pdev = h->pdev; + int i, ret; + + priv->ring_data = devm_kzalloc(&pdev->dev, h->kinfo.num_tqps * + sizeof(*priv->ring_data) * 2, + GFP_KERNEL); + if (!priv->ring_data) + return -ENOMEM; + + for (i = 0; i < h->kinfo.num_tqps; i++) { + ret = hns3_queue_to_ring(h->kinfo.tqp[i], priv); + if (ret) + goto err; + } + + return 0; +err: + devm_kfree(&pdev->dev, priv->ring_data); + return ret; +} + +static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring) +{ + int ret; + + if (ring->desc_num <= 0 || ring->buf_size <= 0) + return -EINVAL; + + ring->desc_cb = kcalloc(ring->desc_num, sizeof(ring->desc_cb[0]), + GFP_KERNEL); + if (!ring->desc_cb) { + ret = -ENOMEM; + goto out; + } + + ret = hns3_alloc_desc(ring); + if (ret) + goto out_with_desc_cb; + + if (!HNAE3_IS_TX_RING(ring)) { + ret = hns3_alloc_ring_buffers(ring); + if (ret) + goto out_with_desc; + } + + return 0; + +out_with_desc: + hns3_free_desc(ring); +out_with_desc_cb: + kfree(ring->desc_cb); + ring->desc_cb = NULL; +out: + return ret; +} + +static void hns3_fini_ring(struct hns3_enet_ring *ring) +{ + hns3_free_desc(ring); + kfree(ring->desc_cb); + ring->desc_cb = NULL; + ring->next_to_clean = 0; + ring->next_to_use = 0; +} + +int hns3_buf_size2type(u32 buf_size) +{ + int bd_size_type; + + switch (buf_size) { + case 512: + bd_size_type = HNS3_BD_SIZE_512_TYPE; + break; + case 1024: + bd_size_type = HNS3_BD_SIZE_1024_TYPE; + break; + case 2048: + bd_size_type = HNS3_BD_SIZE_2048_TYPE; + break; + case 4096: + bd_size_type = HNS3_BD_SIZE_4096_TYPE; + break; + default: + bd_size_type = HNS3_BD_SIZE_2048_TYPE; + } + + return bd_size_type; +} + +static void hns3_init_ring_hw(struct hns3_enet_ring *ring) +{ + dma_addr_t dma = ring->desc_dma_addr; + struct hnae3_queue *q = ring->tqp; + + if (!HNAE3_IS_TX_RING(ring)) { + hns3_write_dev(q, HNS3_RING_RX_RING_BASEADDR_L_REG, + (u32)dma); + hns3_write_dev(q, HNS3_RING_RX_RING_BASEADDR_H_REG, + (u32)((dma >> 31) >> 1)); + + hns3_write_dev(q, HNS3_RING_RX_RING_BD_LEN_REG, + hns3_buf_size2type(ring->buf_size)); + hns3_write_dev(q, HNS3_RING_RX_RING_BD_NUM_REG, + ring->desc_num / 8 - 1); + + } else { + hns3_write_dev(q, HNS3_RING_TX_RING_BASEADDR_L_REG, + (u32)dma); + hns3_write_dev(q, HNS3_RING_TX_RING_BASEADDR_H_REG, + (u32)((dma >> 31) >> 1)); + + hns3_write_dev(q, HNS3_RING_TX_RING_BD_LEN_REG, + hns3_buf_size2type(ring->buf_size)); + hns3_write_dev(q, HNS3_RING_TX_RING_BD_NUM_REG, + ring->desc_num / 8 - 1); + } +} + +static int hns3_init_all_ring(struct hns3_nic_priv *priv) +{ + struct hnae3_handle *h = priv->ae_handle; + int ring_num = h->kinfo.num_tqps * 2; + int i, j; + int ret; + + for (i = 0; i < ring_num; i++) { + ret = hns3_alloc_ring_memory(priv->ring_data[i].ring); + if (ret) { + dev_err(priv->dev, + "Alloc ring memory fail! ret=%d\n", ret); + goto out_when_alloc_ring_memory; + } + + hns3_init_ring_hw(priv->ring_data[i].ring); + + u64_stats_init(&priv->ring_data[i].ring->syncp); + } + + return 0; + +out_when_alloc_ring_memory: + for (j = i - 1; j >= 0; j--) + hns3_fini_ring(priv->ring_data[i].ring); + + return -ENOMEM; +} + +static int hns3_uninit_all_ring(struct hns3_nic_priv *priv) +{ + struct hnae3_handle *h = priv->ae_handle; + int i; + + for (i = 0; i < h->kinfo.num_tqps; i++) { + if (h->ae_algo->ops->reset_queue) + h->ae_algo->ops->reset_queue(h, i); + + hns3_fini_ring(priv->ring_data[i].ring); + hns3_fini_ring(priv->ring_data[i + h->kinfo.num_tqps].ring); + } + + return 0; +} + +/* Set mac addr if it is configured. or leave it to the AE driver */ +static void hns3_init_mac_addr(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + u8 mac_addr_temp[ETH_ALEN]; + + if (h->ae_algo->ops->get_mac_addr) { + h->ae_algo->ops->get_mac_addr(h, mac_addr_temp); + ether_addr_copy(netdev->dev_addr, mac_addr_temp); + } + + /* Check if the MAC address is valid, if not get a random one */ + if (!is_valid_ether_addr(netdev->dev_addr)) { + eth_hw_addr_random(netdev); + dev_warn(priv->dev, "using random MAC address %pM\n", + netdev->dev_addr); + /* Also copy this new MAC address into hdev */ + if (h->ae_algo->ops->set_mac_addr) + h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr); + } +} + +static void hns3_nic_set_priv_ops(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + + if ((netdev->features & NETIF_F_TSO) || + (netdev->features & NETIF_F_TSO6)) { + priv->ops.fill_desc = hns3_fill_desc_tso; + priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tso; + } else { + priv->ops.fill_desc = hns3_fill_desc; + priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tx; + } +} + +static int hns3_client_init(struct hnae3_handle *handle) +{ + struct pci_dev *pdev = handle->pdev; + struct hns3_nic_priv *priv; + struct net_device *netdev; + int ret; + + netdev = alloc_etherdev_mq(sizeof(struct hns3_nic_priv), + handle->kinfo.num_tqps); + if (!netdev) + return -ENOMEM; + + priv = netdev_priv(netdev); + priv->dev = &pdev->dev; + priv->netdev = netdev; + priv->ae_handle = handle; + + handle->kinfo.netdev = netdev; + handle->priv = (void *)priv; + + hns3_init_mac_addr(netdev); + + hns3_set_default_feature(netdev); + + netdev->watchdog_timeo = HNS3_TX_TIMEOUT; + netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->netdev_ops = &hns3_nic_netdev_ops; + SET_NETDEV_DEV(netdev, &pdev->dev); + hns3_ethtool_set_ops(netdev); + hns3_nic_set_priv_ops(netdev); + + /* Carrier off reporting is important to ethtool even BEFORE open */ + netif_carrier_off(netdev); + + ret = hns3_get_ring_config(priv); + if (ret) { + ret = -ENOMEM; + goto out_get_ring_cfg; + } + + ret = hns3_nic_init_vector_data(priv); + if (ret) { + ret = -ENOMEM; + goto out_init_vector_data; + } + + ret = hns3_init_all_ring(priv); + if (ret) { + ret = -ENOMEM; + goto out_init_ring_data; + } + + ret = register_netdev(netdev); + if (ret) { + dev_err(priv->dev, "probe register netdev fail!\n"); + goto out_reg_netdev_fail; + } + + return ret; + +out_reg_netdev_fail: +out_init_ring_data: + (void)hns3_nic_uninit_vector_data(priv); + priv->ring_data = NULL; +out_init_vector_data: +out_get_ring_cfg: + priv->ae_handle = NULL; + free_netdev(netdev); + return ret; +} + +static void hns3_client_uninit(struct hnae3_handle *handle, bool reset) +{ + struct net_device *netdev = handle->kinfo.netdev; + struct hns3_nic_priv *priv = netdev_priv(netdev); + int ret; + + if (netdev->reg_state != NETREG_UNINITIALIZED) + unregister_netdev(netdev); + + ret = hns3_nic_uninit_vector_data(priv); + if (ret) + netdev_err(netdev, "uninit vector error\n"); + + ret = hns3_uninit_all_ring(priv); + if (ret) + netdev_err(netdev, "uninit ring error\n"); + + priv->ring_data = NULL; + + free_netdev(netdev); +} + +static void hns3_link_status_change(struct hnae3_handle *handle, bool linkup) +{ + struct net_device *netdev = handle->kinfo.netdev; + + if (!netdev) + return; + + if (linkup) { + netif_carrier_on(netdev); + netif_tx_wake_all_queues(netdev); + netdev_info(netdev, "link up\n"); + } else { + netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); + netdev_info(netdev, "link down\n"); + } +} + +const struct hnae3_client_ops client_ops = { + .init_instance = hns3_client_init, + .uninit_instance = hns3_client_uninit, + .link_status_change = hns3_link_status_change, +}; + +/* hns3_init_module - Driver registration routine + * hns3_init_module is the first routine called when the driver is + * loaded. All it does is register with the PCI subsystem. + */ +static int __init hns3_init_module(void) +{ + int ret; + + pr_info("%s: %s - version\n", hns3_driver_name, hns3_driver_string); + pr_info("%s: %s\n", hns3_driver_name, hns3_copyright); + + client.type = HNAE3_CLIENT_KNIC; + snprintf(client.name, HNAE3_CLIENT_NAME_LENGTH - 1, "%s", + hns3_driver_name); + + client.ops = &client_ops; + + ret = hnae3_register_client(&client); + if (ret) + return ret; + + ret = pci_register_driver(&hns3_driver); + if (ret) + hnae3_unregister_client(&client); + + return ret; +} +module_init(hns3_init_module); + +/* hns3_exit_module - Driver exit cleanup routine + * hns3_exit_module is called just before the driver is removed + * from memory. + */ +static void __exit hns3_exit_module(void) +{ + pci_unregister_driver(&hns3_driver); + hnae3_unregister_client(&client); +} +module_exit(hns3_exit_module); + +MODULE_DESCRIPTION("HNS3: Hisilicon Ethernet Driver"); +MODULE_AUTHOR("Huawei Tech. Co., Ltd."); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("pci:hns-nic"); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h new file mode 100644 index 000000000000..a6e8f15a4669 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h @@ -0,0 +1,592 @@ +/* + * Copyright (c) 2016 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __HNS3_ENET_H +#define __HNS3_ENET_H + +#include "hnae3.h" + +extern const char hns3_driver_version[]; + +enum hns3_nic_state { + HNS3_NIC_STATE_TESTING, + HNS3_NIC_STATE_RESETTING, + HNS3_NIC_STATE_REINITING, + HNS3_NIC_STATE_DOWN, + HNS3_NIC_STATE_DISABLED, + HNS3_NIC_STATE_REMOVING, + HNS3_NIC_STATE_SERVICE_INITED, + HNS3_NIC_STATE_SERVICE_SCHED, + HNS3_NIC_STATE2_RESET_REQUESTED, + HNS3_NIC_STATE_MAX +}; + +#define HNS3_RING_RX_RING_BASEADDR_L_REG 0x00000 +#define HNS3_RING_RX_RING_BASEADDR_H_REG 0x00004 +#define HNS3_RING_RX_RING_BD_NUM_REG 0x00008 +#define HNS3_RING_RX_RING_BD_LEN_REG 0x0000C +#define HNS3_RING_RX_RING_TAIL_REG 0x00018 +#define HNS3_RING_RX_RING_HEAD_REG 0x0001C +#define HNS3_RING_RX_RING_FBDNUM_REG 0x00020 +#define HNS3_RING_RX_RING_PKTNUM_RECORD_REG 0x0002C + +#define HNS3_RING_TX_RING_BASEADDR_L_REG 0x00040 +#define HNS3_RING_TX_RING_BASEADDR_H_REG 0x00044 +#define HNS3_RING_TX_RING_BD_NUM_REG 0x00048 +#define HNS3_RING_TX_RING_BD_LEN_REG 0x0004C +#define HNS3_RING_TX_RING_TAIL_REG 0x00058 +#define HNS3_RING_TX_RING_HEAD_REG 0x0005C +#define HNS3_RING_TX_RING_FBDNUM_REG 0x00060 +#define HNS3_RING_TX_RING_OFFSET_REG 0x00064 +#define HNS3_RING_TX_RING_PKTNUM_RECORD_REG 0x0006C + +#define HNS3_RING_PREFETCH_EN_REG 0x0007C +#define HNS3_RING_CFG_VF_NUM_REG 0x00080 +#define HNS3_RING_ASID_REG 0x0008C +#define HNS3_RING_RX_VM_REG 0x00090 +#define HNS3_RING_T0_BE_RST 0x00094 +#define HNS3_RING_COULD_BE_RST 0x00098 +#define HNS3_RING_WRR_WEIGHT_REG 0x0009c + +#define HNS3_RING_INTMSK_RXWL_REG 0x000A0 +#define HNS3_RING_INTSTS_RX_RING_REG 0x000A4 +#define HNS3_RX_RING_INT_STS_REG 0x000A8 +#define HNS3_RING_INTMSK_TXWL_REG 0x000AC +#define HNS3_RING_INTSTS_TX_RING_REG 0x000B0 +#define HNS3_TX_RING_INT_STS_REG 0x000B4 +#define HNS3_RING_INTMSK_RX_OVERTIME_REG 0x000B8 +#define HNS3_RING_INTSTS_RX_OVERTIME_REG 0x000BC +#define HNS3_RING_INTMSK_TX_OVERTIME_REG 0x000C4 +#define HNS3_RING_INTSTS_TX_OVERTIME_REG 0x000C8 + +#define HNS3_RING_MB_CTRL_REG 0x00100 +#define HNS3_RING_MB_DATA_BASE_REG 0x00200 + +#define HNS3_TX_REG_OFFSET 0x40 + +#define HNS3_RX_HEAD_SIZE 256 + +#define HNS3_TX_TIMEOUT (5 * HZ) +#define HNS3_RING_NAME_LEN 16 +#define HNS3_BUFFER_SIZE_2048 2048 +#define HNS3_RING_MAX_PENDING 32768 + +#define HNS3_BD_SIZE_512_TYPE 0 +#define HNS3_BD_SIZE_1024_TYPE 1 +#define HNS3_BD_SIZE_2048_TYPE 2 +#define HNS3_BD_SIZE_4096_TYPE 3 + +#define HNS3_RX_FLAG_VLAN_PRESENT 0x1 +#define HNS3_RX_FLAG_L3ID_IPV4 0x0 +#define HNS3_RX_FLAG_L3ID_IPV6 0x1 +#define HNS3_RX_FLAG_L4ID_UDP 0x0 +#define HNS3_RX_FLAG_L4ID_TCP 0x1 + +#define HNS3_RXD_DMAC_S 0 +#define HNS3_RXD_DMAC_M (0x3 << HNS3_RXD_DMAC_S) +#define HNS3_RXD_VLAN_S 2 +#define HNS3_RXD_VLAN_M (0x3 << HNS3_RXD_VLAN_S) +#define HNS3_RXD_L3ID_S 4 +#define HNS3_RXD_L3ID_M (0xf << HNS3_RXD_L3ID_S) +#define HNS3_RXD_L4ID_S 8 +#define HNS3_RXD_L4ID_M (0xf << HNS3_RXD_L4ID_S) +#define HNS3_RXD_FRAG_B 12 +#define HNS3_RXD_L2E_B 16 +#define HNS3_RXD_L3E_B 17 +#define HNS3_RXD_L4E_B 18 +#define HNS3_RXD_TRUNCAT_B 19 +#define HNS3_RXD_HOI_B 20 +#define HNS3_RXD_DOI_B 21 +#define HNS3_RXD_OL3E_B 22 +#define HNS3_RXD_OL4E_B 23 + +#define HNS3_RXD_ODMAC_S 0 +#define HNS3_RXD_ODMAC_M (0x3 << HNS3_RXD_ODMAC_S) +#define HNS3_RXD_OVLAN_S 2 +#define HNS3_RXD_OVLAN_M (0x3 << HNS3_RXD_OVLAN_S) +#define HNS3_RXD_OL3ID_S 4 +#define HNS3_RXD_OL3ID_M (0xf << HNS3_RXD_OL3ID_S) +#define HNS3_RXD_OL4ID_S 8 +#define HNS3_RXD_OL4ID_M (0xf << HNS3_RXD_OL4ID_S) +#define HNS3_RXD_FBHI_S 12 +#define HNS3_RXD_FBHI_M (0x3 << HNS3_RXD_FBHI_S) +#define HNS3_RXD_FBLI_S 14 +#define HNS3_RXD_FBLI_M (0x3 << HNS3_RXD_FBLI_S) + +#define HNS3_RXD_BDTYPE_S 0 +#define HNS3_RXD_BDTYPE_M (0xf << HNS3_RXD_BDTYPE_S) +#define HNS3_RXD_VLD_B 4 +#define HNS3_RXD_UDP0_B 5 +#define HNS3_RXD_EXTEND_B 7 +#define HNS3_RXD_FE_B 8 +#define HNS3_RXD_LUM_B 9 +#define HNS3_RXD_CRCP_B 10 +#define HNS3_RXD_L3L4P_B 11 +#define HNS3_RXD_TSIND_S 12 +#define HNS3_RXD_TSIND_M (0x7 << HNS3_RXD_TSIND_S) +#define HNS3_RXD_LKBK_B 15 +#define HNS3_RXD_HDL_S 16 +#define HNS3_RXD_HDL_M (0x7ff << HNS3_RXD_HDL_S) +#define HNS3_RXD_HSIND_B 31 + +#define HNS3_TXD_L3T_S 0 +#define HNS3_TXD_L3T_M (0x3 << HNS3_TXD_L3T_S) +#define HNS3_TXD_L4T_S 2 +#define HNS3_TXD_L4T_M (0x3 << HNS3_TXD_L4T_S) +#define HNS3_TXD_L3CS_B 4 +#define HNS3_TXD_L4CS_B 5 +#define HNS3_TXD_VLAN_B 6 +#define HNS3_TXD_TSO_B 7 + +#define HNS3_TXD_L2LEN_S 8 +#define HNS3_TXD_L2LEN_M (0xff << HNS3_TXD_L2LEN_S) +#define HNS3_TXD_L3LEN_S 16 +#define HNS3_TXD_L3LEN_M (0xff << HNS3_TXD_L3LEN_S) +#define HNS3_TXD_L4LEN_S 24 +#define HNS3_TXD_L4LEN_M (0xff << HNS3_TXD_L4LEN_S) + +#define HNS3_TXD_OL3T_S 0 +#define HNS3_TXD_OL3T_M (0x3 << HNS3_TXD_OL3T_S) +#define HNS3_TXD_OVLAN_B 2 +#define HNS3_TXD_MACSEC_B 3 +#define HNS3_TXD_TUNTYPE_S 4 +#define HNS3_TXD_TUNTYPE_M (0xf << HNS3_TXD_TUNTYPE_S) + +#define HNS3_TXD_BDTYPE_S 0 +#define HNS3_TXD_BDTYPE_M (0xf << HNS3_TXD_BDTYPE_S) +#define HNS3_TXD_FE_B 4 +#define HNS3_TXD_SC_S 5 +#define HNS3_TXD_SC_M (0x3 << HNS3_TXD_SC_S) +#define HNS3_TXD_EXTEND_B 7 +#define HNS3_TXD_VLD_B 8 +#define HNS3_TXD_RI_B 9 +#define HNS3_TXD_RA_B 10 +#define HNS3_TXD_TSYN_B 11 +#define HNS3_TXD_DECTTL_S 12 +#define HNS3_TXD_DECTTL_M (0xf << HNS3_TXD_DECTTL_S) + +#define HNS3_TXD_MSS_S 0 +#define HNS3_TXD_MSS_M (0x3fff << HNS3_TXD_MSS_S) + +#define HNS3_VECTOR_TX_IRQ BIT_ULL(0) +#define HNS3_VECTOR_RX_IRQ BIT_ULL(1) + +#define HNS3_VECTOR_NOT_INITED 0 +#define HNS3_VECTOR_INITED 1 + +#define HNS3_MAX_BD_SIZE 65535 +#define HNS3_MAX_BD_PER_FRAG 8 +#define HNS3_MAX_BD_PER_PKT MAX_SKB_FRAGS + +#define HNS3_VECTOR_GL0_OFFSET 0x100 +#define HNS3_VECTOR_GL1_OFFSET 0x200 +#define HNS3_VECTOR_GL2_OFFSET 0x300 +#define HNS3_VECTOR_RL_OFFSET 0x900 +#define HNS3_VECTOR_RL_EN_B 6 + +enum hns3_pkt_l3t_type { + HNS3_L3T_NONE, + HNS3_L3T_IPV6, + HNS3_L3T_IPV4, + HNS3_L3T_RESERVED +}; + +enum hns3_pkt_l4t_type { + HNS3_L4T_UNKNOWN, + HNS3_L4T_TCP, + HNS3_L4T_UDP, + HNS3_L4T_SCTP +}; + +enum hns3_pkt_ol3t_type { + HNS3_OL3T_NONE, + HNS3_OL3T_IPV6, + HNS3_OL3T_IPV4_NO_CSUM, + HNS3_OL3T_IPV4_CSUM +}; + +enum hns3_pkt_tun_type { + HNS3_TUN_NONE, + HNS3_TUN_MAC_IN_UDP, + HNS3_TUN_NVGRE, + HNS3_TUN_OTHER +}; + +/* hardware spec ring buffer format */ +struct __packed hns3_desc { + __le64 addr; + union { + struct { + __le16 vlan_tag; + __le16 send_size; + union { + __le32 type_cs_vlan_tso_len; + struct { + __u8 type_cs_vlan_tso; + __u8 l2_len; + __u8 l3_len; + __u8 l4_len; + }; + }; + __le16 outer_vlan_tag; + __le16 tv; + + union { + __le32 ol_type_vlan_len_msec; + struct { + __u8 ol_type_vlan_msec; + __u8 ol2_len; + __u8 ol3_len; + __u8 ol4_len; + }; + }; + + __le32 paylen; + __le16 bdtp_fe_sc_vld_ra_ri; + __le16 mss; + } tx; + + struct { + __le32 l234_info; + __le16 pkt_len; + __le16 size; + + __le32 rss_hash; + __le16 fd_id; + __le16 vlan_tag; + + union { + __le32 ol_info; + struct { + __le16 o_dm_vlan_id_fb; + __le16 ot_vlan_tag; + }; + }; + + __le32 bd_base_info; + } rx; + }; +}; + +struct hns3_desc_cb { + dma_addr_t dma; /* dma address of this desc */ + void *buf; /* cpu addr for a desc */ + + /* priv data for the desc, e.g. skb when use with ip stack*/ + void *priv; + u16 page_offset; + u16 reuse_flag; + + u16 length; /* length of the buffer */ + + /* desc type, used by the ring user to mark the type of the priv data */ + u16 type; +}; + +enum hns3_pkt_l3type { + HNS3_L3_TYPE_IPV4, + HNS3_L3_TYPE_IPV6, + HNS3_L3_TYPE_ARP, + HNS3_L3_TYPE_RARP, + HNS3_L3_TYPE_IPV4_OPT, + HNS3_L3_TYPE_IPV6_EXT, + HNS3_L3_TYPE_LLDP, + HNS3_L3_TYPE_BPDU, + HNS3_L3_TYPE_MAC_PAUSE, + HNS3_L3_TYPE_PFC_PAUSE,/* 0x9*/ + + /* reserved for 0xA~0xB*/ + + HNS3_L3_TYPE_CNM = 0xc, + + /* reserved for 0xD~0xE*/ + + HNS3_L3_TYPE_PARSE_FAIL = 0xf /* must be last */ +}; + +enum hns3_pkt_l4type { + HNS3_L4_TYPE_UDP, + HNS3_L4_TYPE_TCP, + HNS3_L4_TYPE_GRE, + HNS3_L4_TYPE_SCTP, + HNS3_L4_TYPE_IGMP, + HNS3_L4_TYPE_ICMP, + + /* reserved for 0x6~0xE */ + + HNS3_L4_TYPE_PARSE_FAIL = 0xf /* must be last */ +}; + +enum hns3_pkt_ol3type { + HNS3_OL3_TYPE_IPV4 = 0, + HNS3_OL3_TYPE_IPV6, + /* reserved for 0x2~0x3 */ + HNS3_OL3_TYPE_IPV4_OPT = 4, + HNS3_OL3_TYPE_IPV6_EXT, + + /* reserved for 0x6~0xE*/ + + HNS3_OL3_TYPE_PARSE_FAIL = 0xf /* must be last */ +}; + +enum hns3_pkt_ol4type { + HNS3_OL4_TYPE_NO_TUN, + HNS3_OL4_TYPE_MAC_IN_UDP, + HNS3_OL4_TYPE_NVGRE, + HNS3_OL4_TYPE_UNKNOWN +}; + +struct ring_stats { + u64 io_err_cnt; + u64 sw_err_cnt; + u64 seg_pkt_cnt; + union { + struct { + u64 tx_pkts; + u64 tx_bytes; + u64 tx_err_cnt; + u64 restart_queue; + u64 tx_busy; + }; + struct { + u64 rx_pkts; + u64 rx_bytes; + u64 rx_err_cnt; + u64 reuse_pg_cnt; + u64 err_pkt_len; + u64 non_vld_descs; + u64 err_bd_num; + u64 l2_err; + u64 l3l4_csum_err; + }; + }; +}; + +struct hns3_enet_ring { + u8 __iomem *io_base; /* base io address for the ring */ + struct hns3_desc *desc; /* dma map address space */ + struct hns3_desc_cb *desc_cb; + struct hns3_enet_ring *next; + struct hns3_enet_tqp_vector *tqp_vector; + struct hnae3_queue *tqp; + char ring_name[HNS3_RING_NAME_LEN]; + struct device *dev; /* will be used for DMA mapping of descriptors */ + + /* statistic */ + struct ring_stats stats; + struct u64_stats_sync syncp; + + dma_addr_t desc_dma_addr; + u32 buf_size; /* size for hnae_desc->addr, preset by AE */ + u16 desc_num; /* total number of desc */ + u16 max_desc_num_per_pkt; + u16 max_raw_data_sz_per_desc; + u16 max_pkt_size; + int next_to_use; /* idx of next spare desc */ + + /* idx of lastest sent desc, the ring is empty when equal to + * next_to_use + */ + int next_to_clean; + + u32 flag; /* ring attribute */ + int irq_init_flag; + + int numa_node; + cpumask_t affinity_mask; +}; + +struct hns_queue; + +struct hns3_nic_ring_data { + struct hns3_enet_ring *ring; + struct napi_struct napi; + int queue_index; + int (*poll_one)(struct hns3_nic_ring_data *, int, void *); + void (*ex_process)(struct hns3_nic_ring_data *, struct sk_buff *); + void (*fini_process)(struct hns3_nic_ring_data *); +}; + +struct hns3_nic_ops { + int (*fill_desc)(struct hns3_enet_ring *ring, void *priv, + int size, dma_addr_t dma, int frag_end, + enum hns_desc_type type); + int (*maybe_stop_tx)(struct sk_buff **out_skb, + int *bnum, struct hns3_enet_ring *ring); + void (*get_rxd_bnum)(u32 bnum_flag, int *out_bnum); +}; + +enum hns3_flow_level_range { + HNS3_FLOW_LOW = 0, + HNS3_FLOW_MID = 1, + HNS3_FLOW_HIGH = 2, + HNS3_FLOW_ULTRA = 3, +}; + +enum hns3_link_mode_bits { + HNS3_LM_FIBRE_BIT = BIT(0), + HNS3_LM_AUTONEG_BIT = BIT(1), + HNS3_LM_TP_BIT = BIT(2), + HNS3_LM_PAUSE_BIT = BIT(3), + HNS3_LM_BACKPLANE_BIT = BIT(4), + HNS3_LM_10BASET_HALF_BIT = BIT(5), + HNS3_LM_10BASET_FULL_BIT = BIT(6), + HNS3_LM_100BASET_HALF_BIT = BIT(7), + HNS3_LM_100BASET_FULL_BIT = BIT(8), + HNS3_LM_1000BASET_FULL_BIT = BIT(9), + HNS3_LM_10000BASEKR_FULL_BIT = BIT(10), + HNS3_LM_25000BASEKR_FULL_BIT = BIT(11), + HNS3_LM_40000BASELR4_FULL_BIT = BIT(12), + HNS3_LM_50000BASEKR2_FULL_BIT = BIT(13), + HNS3_LM_100000BASEKR4_FULL_BIT = BIT(14), + HNS3_LM_COUNT = 15 +}; + +#define HNS3_INT_GL_50K 0x000A +#define HNS3_INT_GL_20K 0x0019 +#define HNS3_INT_GL_18K 0x001B +#define HNS3_INT_GL_8K 0x003E + +struct hns3_enet_ring_group { + /* array of pointers to rings */ + struct hns3_enet_ring *ring; + u64 total_bytes; /* total bytes processed this group */ + u64 total_packets; /* total packets processed this group */ + u16 count; + enum hns3_flow_level_range flow_level; + u16 int_gl; +}; + +struct hns3_enet_tqp_vector { + struct hnae3_handle *handle; + u8 __iomem *mask_addr; + int vector_irq; + int irq_init_flag; + + u16 idx; /* index in the TQP vector array per handle. */ + + struct napi_struct napi; + + struct hns3_enet_ring_group rx_group; + struct hns3_enet_ring_group tx_group; + + u16 num_tqps; /* total number of tqps in TQP vector */ + + cpumask_t affinity_mask; + char name[HNAE3_INT_NAME_LEN]; + + /* when 0 should adjust interrupt coalesce parameter */ + u8 int_adapt_down; +} ____cacheline_internodealigned_in_smp; + +enum hns3_udp_tnl_type { + HNS3_UDP_TNL_VXLAN, + HNS3_UDP_TNL_GENEVE, + HNS3_UDP_TNL_MAX, +}; + +struct hns3_udp_tunnel { + u16 dst_port; + int used; +}; + +struct hns3_nic_priv { + struct hnae3_handle *ae_handle; + u32 enet_ver; + u32 port_id; + struct net_device *netdev; + struct device *dev; + struct hns3_nic_ops ops; + + /** + * the cb for nic to manage the ring buffer, the first half of the + * array is for tx_ring and vice versa for the second half + */ + struct hns3_nic_ring_data *ring_data; + struct hns3_enet_tqp_vector *tqp_vector; + u16 vector_num; + + /* The most recently read link state */ + int link; + u64 tx_timeout_count; + + unsigned long state; + + struct timer_list service_timer; + + struct work_struct service_task; + + struct notifier_block notifier_block; + /* Vxlan/Geneve information */ + struct hns3_udp_tunnel udp_tnl[HNS3_UDP_TNL_MAX]; +}; + +union l3_hdr_info { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; +}; + +union l4_hdr_info { + struct tcphdr *tcp; + struct udphdr *udp; + unsigned char *hdr; +}; + +/* the distance between [begin, end) in a ring buffer + * note: there is a unuse slot between the begin and the end + */ +static inline int ring_dist(struct hns3_enet_ring *ring, int begin, int end) +{ + return (end - begin + ring->desc_num) % ring->desc_num; +} + +static inline int ring_space(struct hns3_enet_ring *ring) +{ + return ring->desc_num - + ring_dist(ring, ring->next_to_clean, ring->next_to_use) - 1; +} + +static inline int is_ring_empty(struct hns3_enet_ring *ring) +{ + return ring->next_to_use == ring->next_to_clean; +} + +static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value) +{ + u8 __iomem *reg_addr = READ_ONCE(base); + + writel(value, reg_addr + reg); +} + +#define hns3_write_dev(a, reg, value) \ + hns3_write_reg((a)->io_base, (reg), (value)) + +#define hnae_queue_xmit(tqp, buf_num) writel_relaxed(buf_num, \ + (tqp)->io_base + HNS3_RING_TX_RING_TAIL_REG) + +#define ring_to_dev(ring) (&(ring)->tqp->handle->pdev->dev) + +#define ring_to_dma_dir(ring) (HNAE3_IS_TX_RING(ring) ? \ + DMA_TO_DEVICE : DMA_FROM_DEVICE) + +#define tx_ring_data(priv, idx) ((priv)->ring_data[idx]) + +#define hnae_buf_size(_ring) ((_ring)->buf_size) +#define hnae_page_order(_ring) (get_order(hnae_buf_size(_ring))) +#define hnae_page_size(_ring) (PAGE_SIZE << hnae_page_order(_ring)) + +/* iterator for handling rings in ring group */ +#define hns3_for_each_ring(pos, head) \ + for (pos = (head).ring; pos; pos = pos->next) + +void hns3_ethtool_set_ops(struct net_device *netdev); + +int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget); +#endif