blob: acb796cc10d0bbe2ee701db1fabeba198a527dd6 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0+
// Copyright (c) 2016-2017 Hisilicon Limited.
#include <linux/dma-mapping.h>
#include <linux/etherdevice.h>
#include <linux/interrupt.h>
#ifdef CONFIG_RFS_ACCEL
#include <linux/cpu_rmap.h>
#endif
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/aer.h>
#include <linux/skbuff.h>
#include <linux/sctp.h>
#include <linux/vermagic.h>
#include <net/gre.h>
#include <net/ip6_checksum.h>
#include <net/pkt_cls.h>
#include <net/tcp.h>
#include <net/vxlan.h>
#include "hnae3.h"
#include "hns3_enet.h"
/* All hns3 tracepoints are defined by the include below, which
* must be included exactly once across the whole kernel with
* CREATE_TRACE_POINTS defined
*/
#define CREATE_TRACE_POINTS
#include "hns3_trace.h"
#define hns3_set_field(origin, shift, val) ((origin) |= ((val) << (shift)))
#define hns3_tx_bd_count(S) DIV_ROUND_UP(S, HNS3_MAX_BD_SIZE)
#define hns3_rl_err(fmt, ...) \
do { \
if (net_ratelimit()) \
netdev_err(fmt, ##__VA_ARGS__); \
} while (0)
static void hns3_clear_all_ring(struct hnae3_handle *h, bool force);
static void hns3_remove_hw_addr(struct net_device *netdev);
static 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;
static int debug = -1;
module_param(debug, int, 0);
MODULE_PARM_DESC(debug, " Network interface message level setting");
#define DEFAULT_MSG_LEVEL (NETIF_MSG_PROBE | NETIF_MSG_LINK | \
NETIF_MSG_IFDOWN | NETIF_MSG_IFUP)
#define HNS3_INNER_VLAN_TAG 1
#define HNS3_OUTER_VLAN_TAG 2
#define HNS3_MIN_TX_LEN 33U
/* 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),
HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC),
HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA),
HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC),
HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC),
HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_VF), 0},
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF),
HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
/* required last entry */
{0, }
};
MODULE_DEVICE_TABLE(pci, hns3_pci_tbl);
static irqreturn_t hns3_irq_handle(int irq, void *vector)
{
struct hns3_enet_tqp_vector *tqp_vector = vector;
napi_schedule_irqoff(&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;
/* clear the affinity mask */
irq_set_affinity_hint(tqp_vectors->vector_irq, NULL);
/* 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,
"%s-%s-%s-%d", hns3_driver_name,
pci_name(priv->ae_handle->pdev),
"TxRx", txrx_int_idx++);
txrx_int_idx++;
} else if (tqp_vectors->rx_group.ring) {
snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN,
"%s-%s-%s-%d", hns3_driver_name,
pci_name(priv->ae_handle->pdev),
"Rx", rx_int_idx++);
} else if (tqp_vectors->tx_group.ring) {
snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN,
"%s-%s-%s-%d", hns3_driver_name,
pci_name(priv->ae_handle->pdev),
"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);
hns3_nic_uninit_irq(priv);
return ret;
}
disable_irq(tqp_vectors->vector_irq);
irq_set_affinity_hint(tqp_vectors->vector_irq,
&tqp_vectors->affinity_mask);
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_irq(tqp_vector->vector_irq);
/* 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);
}
void hns3_set_vector_coalesce_rl(struct hns3_enet_tqp_vector *tqp_vector,
u32 rl_value)
{
u32 rl_reg = hns3_rl_usec_to_reg(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
*/
if (rl_reg > 0 && !tqp_vector->tx_group.coal.gl_adapt_enable &&
!tqp_vector->rx_group.coal.gl_adapt_enable)
/* According to the hardware, the range of rl_reg is
* 0-59 and the unit is 4.
*/
rl_reg |= HNS3_INT_RL_ENABLE_MASK;
writel(rl_reg, tqp_vector->mask_addr + HNS3_VECTOR_RL_OFFSET);
}
void hns3_set_vector_coalesce_rx_gl(struct hns3_enet_tqp_vector *tqp_vector,
u32 gl_value)
{
u32 rx_gl_reg = hns3_gl_usec_to_reg(gl_value);
writel(rx_gl_reg, tqp_vector->mask_addr + HNS3_VECTOR_GL0_OFFSET);
}
void hns3_set_vector_coalesce_tx_gl(struct hns3_enet_tqp_vector *tqp_vector,
u32 gl_value)
{
u32 tx_gl_reg = hns3_gl_usec_to_reg(gl_value);
writel(tx_gl_reg, tqp_vector->mask_addr + HNS3_VECTOR_GL1_OFFSET);
}
static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector,
struct hns3_nic_priv *priv)
{
/* initialize the configuration for interrupt coalescing.
* 1. GL (Interrupt Gap Limiter)
* 2. RL (Interrupt Rate Limiter)
*
* Default: enable interrupt coalescing self-adaptive and GL
*/
tqp_vector->tx_group.coal.gl_adapt_enable = 1;
tqp_vector->rx_group.coal.gl_adapt_enable = 1;
tqp_vector->tx_group.coal.int_gl = HNS3_INT_GL_50K;
tqp_vector->rx_group.coal.int_gl = HNS3_INT_GL_50K;
tqp_vector->rx_group.coal.flow_level = HNS3_FLOW_LOW;
tqp_vector->tx_group.coal.flow_level = HNS3_FLOW_LOW;
}
static void hns3_vector_gl_rl_init_hw(struct hns3_enet_tqp_vector *tqp_vector,
struct hns3_nic_priv *priv)
{
struct hnae3_handle *h = priv->ae_handle;
hns3_set_vector_coalesce_tx_gl(tqp_vector,
tqp_vector->tx_group.coal.int_gl);
hns3_set_vector_coalesce_rx_gl(tqp_vector,
tqp_vector->rx_group.coal.int_gl);
hns3_set_vector_coalesce_rl(tqp_vector, h->kinfo.int_rl_setting);
}
static int hns3_nic_set_real_num_queue(struct net_device *netdev)
{
struct hnae3_handle *h = hns3_get_handle(netdev);
struct hnae3_knic_private_info *kinfo = &h->kinfo;
unsigned int queue_size = kinfo->rss_size * kinfo->num_tc;
int i, ret;
if (kinfo->num_tc <= 1) {
netdev_reset_tc(netdev);
} else {
ret = netdev_set_num_tc(netdev, kinfo->num_tc);
if (ret) {
netdev_err(netdev,
"netdev_set_num_tc fail, ret=%d!\n", ret);
return ret;
}
for (i = 0; i < HNAE3_MAX_TC; i++) {
if (!kinfo->tc_info[i].enable)
continue;
netdev_set_tc_queue(netdev,
kinfo->tc_info[i].tc,
kinfo->tc_info[i].tqp_count,
kinfo->tc_info[i].tqp_offset);
}
}
ret = netif_set_real_num_tx_queues(netdev, queue_size);
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, queue_size);
if (ret) {
netdev_err(netdev,
"netif_set_real_num_rx_queues fail, ret=%d!\n", ret);
return ret;
}
return 0;
}
static u16 hns3_get_max_available_channels(struct hnae3_handle *h)
{
u16 alloc_tqps, max_rss_size, rss_size;
h->ae_algo->ops->get_tqps_and_rss_info(h, &alloc_tqps, &max_rss_size);
rss_size = alloc_tqps / h->kinfo.num_tc;
return min_t(u16, rss_size, max_rss_size);
}
static void hns3_tqp_enable(struct hnae3_queue *tqp)
{
u32 rcb_reg;
rcb_reg = hns3_read_dev(tqp, HNS3_RING_EN_REG);
rcb_reg |= BIT(HNS3_RING_EN_B);
hns3_write_dev(tqp, HNS3_RING_EN_REG, rcb_reg);
}
static void hns3_tqp_disable(struct hnae3_queue *tqp)
{
u32 rcb_reg;
rcb_reg = hns3_read_dev(tqp, HNS3_RING_EN_REG);
rcb_reg &= ~BIT(HNS3_RING_EN_B);
hns3_write_dev(tqp, HNS3_RING_EN_REG, rcb_reg);
}
static void hns3_free_rx_cpu_rmap(struct net_device *netdev)
{
#ifdef CONFIG_RFS_ACCEL
free_irq_cpu_rmap(netdev->rx_cpu_rmap);
netdev->rx_cpu_rmap = NULL;
#endif
}
static int hns3_set_rx_cpu_rmap(struct net_device *netdev)
{
#ifdef CONFIG_RFS_ACCEL
struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hns3_enet_tqp_vector *tqp_vector;
int i, ret;
if (!netdev->rx_cpu_rmap) {
netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(priv->vector_num);
if (!netdev->rx_cpu_rmap)
return -ENOMEM;
}
for (i = 0; i < priv->vector_num; i++) {
tqp_vector = &priv->tqp_vector[i];
ret = irq_cpu_rmap_add(netdev->rx_cpu_rmap,
tqp_vector->vector_irq);
if (ret) {
hns3_free_rx_cpu_rmap(netdev);
return ret;
}
}
#endif
return 0;
}
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;
ret = hns3_nic_reset_all_ring(h);
if (ret)
return ret;
clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
/* enable the vectors */
for (i = 0; i < priv->vector_num; i++)
hns3_vector_enable(&priv->tqp_vector[i]);
/* enable rcb */
for (j = 0; j < h->kinfo.num_tqps; j++)
hns3_tqp_enable(h->kinfo.tqp[j]);
/* start the ae_dev */
ret = h->ae_algo->ops->start ? h->ae_algo->ops->start(h) : 0;
if (ret) {
set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
while (j--)
hns3_tqp_disable(h->kinfo.tqp[j]);
for (j = i - 1; j >= 0; j--)
hns3_vector_disable(&priv->tqp_vector[j]);
}
return ret;
}
static void hns3_config_xps(struct hns3_nic_priv *priv)
{
int i;
for (i = 0; i < priv->vector_num; i++) {
struct hns3_enet_tqp_vector *tqp_vector = &priv->tqp_vector[i];
struct hns3_enet_ring *ring = tqp_vector->tx_group.ring;
while (ring) {
int ret;
ret = netif_set_xps_queue(priv->netdev,
&tqp_vector->affinity_mask,
ring->tqp->tqp_index);
if (ret)
netdev_warn(priv->netdev,
"set xps queue failed: %d", ret);
ring = ring->next;
}
}
}
static int hns3_nic_net_open(struct net_device *netdev)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hnae3_handle *h = hns3_get_handle(netdev);
struct hnae3_knic_private_info *kinfo;
int i, ret;
if (hns3_nic_resetting(netdev))
return -EBUSY;
netif_carrier_off(netdev);
ret = hns3_nic_set_real_num_queue(netdev);
if (ret)
return ret;
ret = hns3_nic_net_up(netdev);
if (ret) {
netdev_err(netdev, "net up fail, ret=%d!\n", ret);
return ret;
}
kinfo = &h->kinfo;
for (i = 0; i < HNAE3_MAX_USER_PRIO; i++)
netdev_set_prio_tc_map(netdev, i, kinfo->prio_tc[i]);
if (h->ae_algo->ops->set_timer_task)
h->ae_algo->ops->set_timer_task(priv->ae_handle, true);
hns3_config_xps(priv);
netif_dbg(h, drv, netdev, "net open\n");
return 0;
}
static void hns3_reset_tx_queue(struct hnae3_handle *h)
{
struct net_device *ndev = h->kinfo.netdev;
struct hns3_nic_priv *priv = netdev_priv(ndev);
struct netdev_queue *dev_queue;
u32 i;
for (i = 0; i < h->kinfo.num_tqps; i++) {
dev_queue = netdev_get_tx_queue(ndev,
priv->ring[i].queue_index);
netdev_tx_reset_queue(dev_queue);
}
}
static void hns3_nic_net_down(struct net_device *netdev)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hnae3_handle *h = hns3_get_handle(netdev);
const struct hnae3_ae_ops *ops;
int i;
/* disable vectors */
for (i = 0; i < priv->vector_num; i++)
hns3_vector_disable(&priv->tqp_vector[i]);
/* disable rcb */
for (i = 0; i < h->kinfo.num_tqps; i++)
hns3_tqp_disable(h->kinfo.tqp[i]);
/* stop ae_dev */
ops = priv->ae_handle->ae_algo->ops;
if (ops->stop)
ops->stop(priv->ae_handle);
/* delay ring buffer clearing to hns3_reset_notify_uninit_enet
* during reset process, because driver may not be able
* to disable the ring through firmware when downing the netdev.
*/
if (!hns3_nic_resetting(netdev))
hns3_clear_all_ring(priv->ae_handle, false);
hns3_reset_tx_queue(priv->ae_handle);
}
static int hns3_nic_net_stop(struct net_device *netdev)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hnae3_handle *h = hns3_get_handle(netdev);
if (test_and_set_bit(HNS3_NIC_STATE_DOWN, &priv->state))
return 0;
netif_dbg(h, drv, netdev, "net stop\n");
if (h->ae_algo->ops->set_timer_task)
h->ae_algo->ops->set_timer_task(priv->ae_handle, false);
netif_tx_stop_all_queues(netdev);
netif_carrier_off(netdev);
hns3_nic_net_down(netdev);
return 0;
}
static int hns3_nic_uc_sync(struct net_device *netdev,
const unsigned char *addr)
{
struct hnae3_handle *h = hns3_get_handle(netdev);
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 hnae3_handle *h = hns3_get_handle(netdev);
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 hnae3_handle *h = hns3_get_handle(netdev);
if (h->ae_algo->ops->add_mc_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 hnae3_handle *h = hns3_get_handle(netdev);
if (h->ae_algo->ops->rm_mc_addr)
return h->ae_algo->ops->rm_mc_addr(h, addr);
return 0;
}
static u8 hns3_get_netdev_flags(struct net_device *netdev)
{
u8 flags = 0;
if (netdev->flags & IFF_PROMISC) {
flags = HNAE3_USER_UPE | HNAE3_USER_MPE | HNAE3_BPE;
} else {
flags |= HNAE3_VLAN_FLTR;
if (netdev->flags & IFF_ALLMULTI)
flags |= HNAE3_USER_MPE;
}
return flags;
}
static void hns3_nic_set_rx_mode(struct net_device *netdev)
{
struct hnae3_handle *h = hns3_get_handle(netdev);
u8 new_flags;
int ret;
new_flags = hns3_get_netdev_flags(netdev);
ret = __dev_uc_sync(netdev, hns3_nic_uc_sync, hns3_nic_uc_unsync);
if (ret) {
netdev_err(netdev, "sync uc address fail\n");
if (ret == -ENOSPC)
new_flags |= HNAE3_OVERFLOW_UPE;
}
if (netdev->flags & IFF_MULTICAST) {
ret = __dev_mc_sync(netdev, hns3_nic_mc_sync,
hns3_nic_mc_unsync);
if (ret) {
netdev_err(netdev, "sync mc address fail\n");
if (ret == -ENOSPC)
new_flags |= HNAE3_OVERFLOW_MPE;
}
}
/* User mode Promisc mode enable and vlan filtering is disabled to
* let all packets in. MAC-VLAN Table overflow Promisc enabled and
* vlan fitering is enabled
*/
hns3_enable_vlan_filter(netdev, new_flags & HNAE3_VLAN_FLTR);
h->netdev_flags = new_flags;
hns3_update_promisc_mode(netdev, new_flags);
}
int hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hnae3_handle *h = priv->ae_handle;
if (h->ae_algo->ops->set_promisc_mode) {
return h->ae_algo->ops->set_promisc_mode(h,
promisc_flags & HNAE3_UPE,
promisc_flags & HNAE3_MPE);
}
return 0;
}
void hns3_enable_vlan_filter(struct net_device *netdev, bool enable)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hnae3_handle *h = priv->ae_handle;
bool last_state;
if (h->pdev->revision >= 0x21 && h->ae_algo->ops->enable_vlan_filter) {
last_state = h->netdev_flags & HNAE3_VLAN_FLTR ? true : false;
if (enable != last_state) {
netdev_info(netdev,
"%s vlan filter\n",
enable ? "enable" : "disable");
h->ae_algo->ops->enable_vlan_filter(h, enable);
}
}
}
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 (unlikely(ret < 0))
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 << 2) + 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;
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_TSO_B, 1);
/* get MSS for TSO */
*mss = skb_shinfo(skb)->gso_size;
trace_hns3_tso(skb);
return 0;
}
static int hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto,
u8 *il4_proto)
{
union l3_hdr_info 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_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;
} else {
return -EINVAL;
}
*ol4_proto = l4_proto_tmp;
/* tunnel packet */
if (!skb->encapsulation) {
*il4_proto = 0;
return 0;
}
/* 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;
return 0;
}
/* when skb->encapsulation is 0, skb->ip_summed is CHECKSUM_PARTIAL
* and it is udp packet, which has a dest port as the IANA assigned.
* the hardware is expected to do the checksum offload, but the
* hardware will not do the checksum offload when udp dest port is
* 4789.
*/
static bool hns3_tunnel_csum_bug(struct sk_buff *skb)
{
union l4_hdr_info l4;
l4.hdr = skb_transport_header(skb);
if (!(!skb->encapsulation &&
l4.udp->dest == htons(IANA_VXLAN_UDP_PORT)))
return false;
skb_checksum_help(skb);
return true;
}
static void hns3_set_outer_l2l3l4(struct sk_buff *skb, u8 ol4_proto,
u32 *ol_type_vlan_len_msec)
{
u32 l2_len, l3_len, l4_len;
unsigned char *il2_hdr;
union l3_hdr_info l3;
union l4_hdr_info l4;
l3.hdr = skb_network_header(skb);
l4.hdr = skb_transport_header(skb);
/* compute OL2 header size, defined in 2 Bytes */
l2_len = l3.hdr - skb->data;
hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L2LEN_S, l2_len >> 1);
/* compute OL3 header size, defined in 4 Bytes */
l3_len = l4.hdr - l3.hdr;
hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_S, l3_len >> 2);
il2_hdr = skb_inner_mac_header(skb);
/* compute OL4 header size, defined in 4 Bytes */
l4_len = il2_hdr - l4.hdr;
hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L4LEN_S, l4_len >> 2);
/* define outer network header type */
if (skb->protocol == htons(ETH_P_IP)) {
if (skb_is_gso(skb))
hns3_set_field(*ol_type_vlan_len_msec,
HNS3_TXD_OL3T_S,
HNS3_OL3T_IPV4_CSUM);
else
hns3_set_field(*ol_type_vlan_len_msec,
HNS3_TXD_OL3T_S,
HNS3_OL3T_IPV4_NO_CSUM);
} else if (skb->protocol == htons(ETH_P_IPV6)) {
hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_S,
HNS3_OL3T_IPV6);
}
if (ol4_proto == IPPROTO_UDP)
hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_TUNTYPE_S,
HNS3_TUN_MAC_IN_UDP);
else if (ol4_proto == IPPROTO_GRE)
hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_TUNTYPE_S,
HNS3_TUN_NVGRE);
}
static int hns3_set_l2l3l4(struct sk_buff *skb, u8 ol4_proto,
u8 il4_proto, u32 *type_cs_vlan_tso,
u32 *ol_type_vlan_len_msec)
{
unsigned char *l2_hdr = skb->data;
u32 l4_proto = ol4_proto;
union l4_hdr_info l4;
union l3_hdr_info l3;
u32 l2_len, l3_len;
l4.hdr = skb_transport_header(skb);
l3.hdr = skb_network_header(skb);
/* handle encapsulation skb */
if (skb->encapsulation) {
/* If this is a not UDP/GRE encapsulation skb */
if (!(ol4_proto == IPPROTO_UDP || ol4_proto == IPPROTO_GRE)) {
/* 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;
}
hns3_set_outer_l2l3l4(skb, ol4_proto, ol_type_vlan_len_msec);
/* switch to inner header */
l2_hdr = skb_inner_mac_header(skb);
l3.hdr = skb_inner_network_header(skb);
l4.hdr = skb_inner_transport_header(skb);
l4_proto = il4_proto;
}
if (l3.v4->version == 4) {
hns3_set_field(*type_cs_vlan_tso, 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))
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1);
} else if (l3.v6->version == 6) {
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_S,
HNS3_L3T_IPV6);
}
/* compute inner(/normal) L2 header size, defined in 2 Bytes */
l2_len = l3.hdr - l2_hdr;
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_S, l2_len >> 1);
/* compute inner(/normal) L3 header size, defined in 4 Bytes */
l3_len = l4.hdr - l3.hdr;
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_S, l3_len >> 2);
/* compute inner(/normal) L4 header size, defined in 4 Bytes */
switch (l4_proto) {
case IPPROTO_TCP:
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S,
HNS3_L4T_TCP);
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_S,
l4.tcp->doff);
break;
case IPPROTO_UDP:
if (hns3_tunnel_csum_bug(skb))
break;
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S,
HNS3_L4T_UDP);
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_S,
(sizeof(struct udphdr) >> 2));
break;
case IPPROTO_SCTP:
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S,
HNS3_L4T_SCTP);
hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_S,
(sizeof(struct sctphdr) >> 2));
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 int hns3_handle_vtags(struct hns3_enet_ring *tx_ring,
struct sk_buff *skb)
{
struct hnae3_handle *handle = tx_ring->tqp->handle;
struct vlan_ethhdr *vhdr;
int rc;
if (!(skb->protocol == htons(ETH_P_8021Q) ||
skb_vlan_tag_present(skb)))
return 0;
/* Since HW limitation, if port based insert VLAN enabled, only one VLAN
* header is allowed in skb, otherwise it will cause RAS error.
*/
if (unlikely(skb_vlan_tagged_multi(skb) &&
handle->port_base_vlan_state ==
HNAE3_PORT_BASE_VLAN_ENABLE))
return -EINVAL;
if (skb->protocol == htons(ETH_P_8021Q) &&
!(handle->kinfo.netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) {
/* When HW VLAN acceleration is turned off, and the stack
* sets the protocol to 802.1q, the driver just need to
* set the protocol to the encapsulated ethertype.
*/
skb->protocol = vlan_get_protocol(skb);
return 0;
}
if (skb_vlan_tag_present(skb)) {
/* Based on hw strategy, use out_vtag in two layer tag case,
* and use inner_vtag in one tag case.
*/
if (skb->protocol == htons(ETH_P_8021Q) &&
handle->port_base_vlan_state ==
HNAE3_PORT_BASE_VLAN_DISABLE)
rc = HNS3_OUTER_VLAN_TAG;
else
rc = HNS3_INNER_VLAN_TAG;
skb->protocol = vlan_get_protocol(skb);
return rc;
}
rc = skb_cow_head(skb, 0);
if (unlikely(rc < 0))
return rc;
vhdr = (struct vlan_ethhdr *)skb->data;
vhdr->h_vlan_TCI |= cpu_to_be16((skb->priority << VLAN_PRIO_SHIFT)
& VLAN_PRIO_MASK);
skb->protocol = vlan_get_protocol(skb);
return 0;
}
static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
struct sk_buff *skb, struct hns3_desc *desc)
{
u32 ol_type_vlan_len_msec = 0;
u32 type_cs_vlan_tso = 0;
u32 paylen = skb->len;
u16 inner_vtag = 0;
u16 out_vtag = 0;
u16 mss = 0;
int ret;
ret = hns3_handle_vtags(ring, skb);
if (unlikely(ret < 0)) {
u64_stats_update_begin(&ring->syncp);
ring->stats.tx_vlan_err++;
u64_stats_update_end(&ring->syncp);
return ret;
} else if (ret == HNS3_INNER_VLAN_TAG) {
inner_vtag = skb_vlan_tag_get(skb);
inner_vtag |= (skb->priority << VLAN_PRIO_SHIFT) &
VLAN_PRIO_MASK;
hns3_set_field(type_cs_vlan_tso, HNS3_TXD_VLAN_B, 1);
} else if (ret == HNS3_OUTER_VLAN_TAG) {
out_vtag = skb_vlan_tag_get(skb);
out_vtag |= (skb->priority << VLAN_PRIO_SHIFT) &
VLAN_PRIO_MASK;
hns3_set_field(ol_type_vlan_len_msec, HNS3_TXD_OVLAN_B,
1);
}
if (skb->ip_summed == CHECKSUM_PARTIAL) {
u8 ol4_proto, il4_proto;
skb_reset_mac_len(skb);
ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto);
if (unlikely(ret < 0)) {
u64_stats_update_begin(&ring->syncp);
ring->stats.tx_l4_proto_err++;
u64_stats_update_end(&ring->syncp);
return ret;
}
ret = hns3_set_l2l3l4(skb, ol4_proto, il4_proto,
&type_cs_vlan_tso,
&ol_type_vlan_len_msec);
if (unlikely(ret < 0)) {
u64_stats_update_begin(&ring->syncp);
ring->stats.tx_l2l3l4_err++;
u64_stats_update_end(&ring->syncp);
return ret;
}
ret = hns3_set_tso(skb, &paylen, &mss,
&type_cs_vlan_tso);
if (unlikely(ret < 0)) {
u64_stats_update_begin(&ring->syncp);
ring->stats.tx_tso_err++;
u64_stats_update_end(&ring->syncp);
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_le32(paylen);
desc->tx.mss = cpu_to_le16(mss);
desc->tx.vlan_tag = cpu_to_le16(inner_vtag);
desc->tx.outer_vlan_tag = cpu_to_le16(out_vtag);
return 0;
}
static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
unsigned int size, enum hns_desc_type type)
{
#define HNS3_LIKELY_BD_NUM 1
struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
struct hns3_desc *desc = &ring->desc[ring->next_to_use];
struct device *dev = ring_to_dev(ring);
skb_frag_t *frag;
unsigned int frag_buf_num;
int k, sizeoflast;
dma_addr_t dma;
if (type == DESC_TYPE_SKB) {
struct sk_buff *skb = (struct sk_buff *)priv;
int ret;
ret = hns3_fill_skb_desc(ring, skb, desc);
if (unlikely(ret < 0))
return ret;
dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE);
} else {
frag = (skb_frag_t *)priv;
dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE);
}
if (unlikely(dma_mapping_error(dev, dma))) {
u64_stats_update_begin(&ring->syncp);
ring->stats.sw_err_cnt++;
u64_stats_update_end(&ring->syncp);
return -ENOMEM;
}
desc_cb->length = size;
if (likely(size <= HNS3_MAX_BD_SIZE)) {
desc_cb->priv = priv;
desc_cb->dma = dma;
desc_cb->type = type;
desc->addr = cpu_to_le64(dma);
desc->tx.send_size = cpu_to_le16(size);
desc->tx.bdtp_fe_sc_vld_ra_ri =
cpu_to_le16(BIT(HNS3_TXD_VLD_B));
trace_hns3_tx_desc(ring, ring->next_to_use);
ring_ptr_move_fw(ring, next_to_use);
return HNS3_LIKELY_BD_NUM;
}
frag_buf_num = hns3_tx_bd_count(size);
sizeoflast = size & HNS3_TX_LAST_SIZE_M;
sizeoflast = sizeoflast ? sizeoflast : HNS3_MAX_BD_SIZE;
/* When frag size is bigger than hardware limit, split this frag */
for (k = 0; k < frag_buf_num; k++) {
/* The txbd's baseinfo of DESC_TYPE_PAGE & DESC_TYPE_SKB */
desc_cb->priv = priv;
desc_cb->dma = dma + HNS3_MAX_BD_SIZE * k;
desc_cb->type = (type == DESC_TYPE_SKB && !k) ?
DESC_TYPE_SKB : DESC_TYPE_PAGE;
/* now, fill the descriptor */
desc->addr = cpu_to_le64(dma + HNS3_MAX_BD_SIZE * k);
desc->tx.send_size = cpu_to_le16((k == frag_buf_num - 1) ?
(u16)sizeoflast : (u16)HNS3_MAX_BD_SIZE);
desc->tx.bdtp_fe_sc_vld_ra_ri =
cpu_to_le16(BIT(HNS3_TXD_VLD_B));
trace_hns3_tx_desc(ring, ring->next_to_use);
/* move ring pointer to next */
ring_ptr_move_fw(ring, next_to_use);
desc_cb = &ring->desc_cb[ring->next_to_use];
desc = &ring->desc[ring->next_to_use];
}
return frag_buf_num;
}
static unsigned int hns3_skb_bd_num(struct sk_buff *skb, unsigned int *bd_size,
unsigned int bd_num)
{
unsigned int size;
int i;
size = skb_headlen(skb);
while (size > HNS3_MAX_BD_SIZE) {
bd_size[bd_num++] = HNS3_MAX_BD_SIZE;
size -= HNS3_MAX_BD_SIZE;
if (bd_num > HNS3_MAX_TSO_BD_NUM)
return bd_num;
}
if (size) {
bd_size[bd_num++] = size;
if (bd_num > HNS3_MAX_TSO_BD_NUM)
return bd_num;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
size = skb_frag_size(frag);
if (!size)
continue;
while (size > HNS3_MAX_BD_SIZE) {
bd_size[bd_num++] = HNS3_MAX_BD_SIZE;
size -= HNS3_MAX_BD_SIZE;
if (bd_num > HNS3_MAX_TSO_BD_NUM)
return bd_num;
}
bd_size[bd_num++] = size;
if (bd_num > HNS3_MAX_TSO_BD_NUM)
return bd_num;
}
return bd_num;
}
static unsigned int hns3_tx_bd_num(struct sk_buff *skb, unsigned int *bd_size)
{
struct sk_buff *frag_skb;
unsigned int bd_num = 0;
/* If the total len is within the max bd limit */
if (likely(skb->len <= HNS3_MAX_BD_SIZE && !skb_has_frag_list(skb) &&
skb_shinfo(skb)->nr_frags < HNS3_MAX_NON_TSO_BD_NUM))
return skb_shinfo(skb)->nr_frags + 1U;
/* The below case will always be linearized, return
* HNS3_MAX_BD_NUM_TSO + 1U to make sure it is linearized.
*/
if (unlikely(skb->len > HNS3_MAX_TSO_SIZE ||
(!skb_is_gso(skb) && skb->len > HNS3_MAX_NON_TSO_SIZE)))
return HNS3_MAX_TSO_BD_NUM + 1U;
bd_num = hns3_skb_bd_num(skb, bd_size, bd_num);
if (!skb_has_frag_list(skb) || bd_num > HNS3_MAX_TSO_BD_NUM)
return bd_num;
skb_walk_frags(skb, frag_skb) {
bd_num = hns3_skb_bd_num(frag_skb, bd_size, bd_num);
if (bd_num > HNS3_MAX_TSO_BD_NUM)
return bd_num;
}
return bd_num;
}
static unsigned int hns3_gso_hdr_len(struct sk_buff *skb)
{
if (!skb->encapsulation)
return skb_transport_offset(skb) + tcp_hdrlen(skb);
return skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb);
}
/* HW need every continuous 8 buffer data to be larger than MSS,
* we simplify it by ensuring skb_headlen + the first continuous
* 7 frags to to be larger than gso header len + mss, and the remaining
* continuous 7 frags to be larger than MSS except the last 7 frags.
*/
static bool hns3_skb_need_linearized(struct sk_buff *skb, unsigned int *bd_size,
unsigned int bd_num)
{
unsigned int tot_len = 0;
int i;
for (i = 0; i < HNS3_MAX_NON_TSO_BD_NUM - 1U; i++)
tot_len += bd_size[i];
/* ensure the first 8 frags is greater than mss + header */
if (tot_len + bd_size[HNS3_MAX_NON_TSO_BD_NUM - 1U] <
skb_shinfo(skb)->gso_size + hns3_gso_hdr_len(skb))
return true;
/* ensure every continuous 7 buffer is greater than mss
* except the last one.
*/
for (i = 0; i < bd_num - HNS3_MAX_NON_TSO_BD_NUM; i++) {
tot_len -= bd_size[i];
tot_len += bd_size[i + HNS3_MAX_NON_TSO_BD_NUM - 1U];
if (tot_len < skb_shinfo(skb)->gso_size)
return true;
}
return false;
}
void hns3_shinfo_pack(struct skb_shared_info *shinfo, __u32 *size)
{
int i = 0;
for (i = 0; i < MAX_SKB_FRAGS; i++)
size[i] = skb_frag_size(&shinfo->frags[i]);
}
static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
struct net_device *netdev,
struct sk_buff *skb)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
unsigned int bd_size[HNS3_MAX_TSO_BD_NUM + 1U];
unsigned int bd_num;
bd_num = hns3_tx_bd_num(skb, bd_size);
if (unlikely(bd_num > HNS3_MAX_NON_TSO_BD_NUM)) {
if (bd_num <= HNS3_MAX_TSO_BD_NUM && skb_is_gso(skb) &&
!hns3_skb_need_linearized(skb, bd_size, bd_num)) {
trace_hns3_over_8bd(skb);
goto out;
}
if (__skb_linearize(skb))
return -ENOMEM;
bd_num = hns3_tx_bd_count(skb->len);
if ((skb_is_gso(skb) && bd_num > HNS3_MAX_TSO_BD_NUM) ||
(!skb_is_gso(skb) &&
bd_num > HNS3_MAX_NON_TSO_BD_NUM)) {
trace_hns3_over_8bd(skb);
return -ENOMEM;
}
u64_stats_update_begin(&ring->syncp);
ring->stats.tx_copy++;
u64_stats_update_end(&ring->syncp);
}
out:
if (likely(ring_space(ring) >= bd_num))
return bd_num;
netif_stop_subqueue(netdev, ring->queue_index);
smp_mb(); /* Memory barrier before checking ring_space */
/* Start queue in case hns3_clean_tx_ring has just made room
* available and has not seen the queue stopped state performed
* by netif_stop_subqueue above.
*/
if (ring_space(ring) >= bd_num && netif_carrier_ok(netdev) &&
!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) {
netif_start_subqueue(netdev, ring->queue_index);
return bd_num;
}
return -EBUSY;
}
static void hns3_clear_desc(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;
/* rollback one */
ring_ptr_move_bw(ring, next_to_use);
/* 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 if (ring->desc_cb[ring->next_to_use].length)
dma_unmap_page(dev,
ring->desc_cb[ring->next_to_use].dma,
ring->desc_cb[ring->next_to_use].length,
DMA_TO_DEVICE);
ring->desc_cb[ring->next_to_use].length = 0;
ring->desc_cb[ring->next_to_use].dma = 0;
}
}
static int hns3_fill_skb_to_desc(struct hns3_enet_ring *ring,
struct sk_buff *skb, enum hns_desc_type type)
{
unsigned int size = skb_headlen(skb);
int i, ret, bd_num = 0;
if (size) {
ret = hns3_fill_desc(ring, skb, size, type);
if (unlikely(ret < 0))
return ret;
bd_num += ret;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
size = skb_frag_size(frag);
if (!size)
continue;
ret = hns3_fill_desc(ring, frag, size, DESC_TYPE_PAGE);
if (unlikely(ret < 0))
return ret;
bd_num += ret;
}
return bd_num;
}
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_enet_ring *ring = &priv->ring[skb->queue_mapping];
struct netdev_queue *dev_queue;
int pre_ntu, next_to_use_head;
struct sk_buff *frag_skb;
int bd_num = 0;
int ret;
/* Hardware can only handle short frames above 32 bytes */
if (skb_put_padto(skb, HNS3_MIN_TX_LEN))
return NETDEV_TX_OK;
/* Prefetch the data used later */
prefetch(skb->data);
ret = hns3_nic_maybe_stop_tx(ring, netdev, skb);
if (unlikely(ret <= 0)) {
if (ret == -EBUSY) {
u64_stats_update_begin(&ring->syncp);
ring->stats.tx_busy++;
u64_stats_update_end(&ring->syncp);
return NETDEV_TX_BUSY;
} else if (ret == -ENOMEM) {
u64_stats_update_begin(&ring->syncp);
ring->stats.sw_err_cnt++;
u64_stats_update_end(&ring->syncp);
}
hns3_rl_err(netdev, "xmit error: %d!\n", ret);
goto out_err_tx_ok;
}
next_to_use_head = ring->next_to_use;
ret = hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB);
if (unlikely(ret < 0))
goto fill_err;
bd_num += ret;
if (!skb_has_frag_list(skb))
goto out;
skb_walk_frags(skb, frag_skb) {
ret = hns3_fill_skb_to_desc(ring, frag_skb, DESC_TYPE_PAGE);
if (unlikely(ret < 0))
goto fill_err;
bd_num += ret;
}
out:
pre_ntu = ring->next_to_use ? (ring->next_to_use - 1) :
(ring->desc_num - 1);
ring->desc[pre_ntu].tx.bdtp_fe_sc_vld_ra_ri |=
cpu_to_le16(BIT(HNS3_TXD_FE_B));
trace_hns3_tx_desc(ring, pre_ntu);
/* Complete translate all packets */
dev_queue = netdev_get_tx_queue(netdev, ring->queue_index);
netdev_tx_sent_queue(dev_queue, skb->len);
wmb(); /* Commit all data before submit */
hnae3_queue_xmit(ring->tqp, bd_num);
return NETDEV_TX_OK;
fill_err:
hns3_clear_desc(ring, next_to_use_head);
out_err_tx_ok:
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
static int hns3_nic_net_set_mac_address(struct net_device *netdev, void *p)
{
struct hnae3_handle *h = hns3_get_handle(netdev);
struct sockaddr *mac_addr = p;
int ret;
if (!mac_addr || !is_valid_ether_addr((const u8 *)mac_addr->sa_data))
return -EADDRNOTAVAIL;
if (ether_addr_equal(netdev->dev_addr, mac_addr->sa_data)) {
netdev_info(netdev, "already using mac address %pM\n",
mac_addr->sa_data);
return 0;
}
/* For VF device, if there is a perm_addr, then the user will not
* be allowed to change the address.
*/
if (!hns3_is_phys_func(h->pdev) &&
!is_zero_ether_addr(netdev->perm_addr)) {
netdev_err(netdev, "has permanent MAC %pM, user MAC %pM not allow\n",
netdev->perm_addr, mac_addr->sa_data);
return -EPERM;
}
ret = h->ae_algo->ops->set_mac_addr(h, mac_addr->sa_data, false);
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_do_ioctl(struct net_device *netdev,
struct ifreq *ifr, int cmd)
{
struct hnae3_handle *h = hns3_get_handle(netdev);
if (!netif_running(netdev))
return -EINVAL;
if (!h->ae_algo->ops->do_ioctl)
return -EOPNOTSUPP;
return h->ae_algo->ops->do_ioctl(h, ifr, cmd);
}
static int hns3_nic_set_features(struct net_device *netdev,
netdev_features_t features)
{
netdev_features_t changed = netdev->features ^ features;
struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hnae3_handle *h = priv->ae_handle;
bool enable;
int ret;
if (changed & (NETIF_F_GRO_HW) && h->ae_algo->ops->set_gro_en) {
enable = !!(features & NETIF_F_GRO_HW);
ret = h->ae_algo->ops->set_gro_en(h, enable);
if (ret)
return ret;
}
if ((changed & NETIF_F_HW_VLAN_CTAG_FILTER) &&
h->ae_algo->ops->enable_vlan_filter) {
enable = !!(features & NETIF_F_HW_VLAN_CTAG_FILTER);
h->ae_algo->ops->enable_vlan_filter(h, enable);
}
if ((changed & NETIF_F_HW_VLAN_CTAG_RX) &&
h->ae_algo->ops->enable_hw_strip_rxvtag) {
enable = !!(features & NETIF_F_HW_VLAN_CTAG_RX);
ret = h->ae_algo->ops->enable_hw_strip_rxvtag(h, enable);
if (ret)
return ret;
}
if ((changed & NETIF_F_NTUPLE) && h->ae_algo->ops->enable_fd) {
enable = !!(features & NETIF_F_NTUPLE);
h->ae_algo->ops->enable_fd(h, enable);
}
netdev->features = features;
return 0;
}
static netdev_features_t hns3_features_check(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features)
{
#define HNS3_MAX_HDR_LEN 480U
#define HNS3_MAX_L4_HDR_LEN 60U
size_t len;
if (skb->ip_summed != CHECKSUM_PARTIAL)
return features;
if (skb->encapsulation)
len = skb_inner_transport_header(skb) - skb->data;
else
len = skb_transport_header(skb) - skb->data;
/* Assume L4 is 60 byte as TCP is the only protocol with a
* a flexible value, and it's max len is 60 bytes.
*/
len += HNS3_MAX_L4_HDR_LEN;
/* Hardware only supports checksum on the skb with a max header
* len of 480 bytes.
*/
if (len > HNS3_MAX_HDR_LEN)
features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
return features;
}
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 hnae3_handle *handle = priv->ae_handle;
struct hns3_enet_ring *ring;
u64 rx_length_errors = 0;
u64 rx_crc_errors = 0;
u64 rx_multicast = 0;
unsigned int start;
u64 tx_errors = 0;
u64 rx_errors = 0;
unsigned int idx;
u64 tx_bytes = 0;
u64 rx_bytes = 0;
u64 tx_pkts = 0;
u64 rx_pkts = 0;
u64 tx_drop = 0;
u64 rx_drop = 0;
if (test_bit(HNS3_NIC_STATE_DOWN, &priv->state))
return;
handle->ae_algo->ops->update_stats(handle, &netdev->stats);
for (idx = 0; idx < queue_num; idx++) {
/* fetch the tx stats */
ring = &priv->ring[idx];
do {
start = u64_stats_fetch_begin_irq(&ring->syncp);
tx_bytes += ring->stats.tx_bytes;
tx_pkts += ring->stats.tx_pkts;
tx_drop += ring->stats.sw_err_cnt;
tx_drop += ring->stats.tx_vlan_err;
tx_drop += ring->stats.tx_l4_proto_err;
tx_drop += ring->stats.tx_l2l3l4_err;
tx_drop += ring->stats.tx_tso_err;
tx_errors += ring->stats.sw_err_cnt;
tx_errors += ring->stats.tx_vlan_err;
tx_errors += ring->stats.tx_l4_proto_err;
tx_errors += ring->stats.tx_l2l3l4_err;
tx_errors += ring->stats.tx_tso_err;
} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
/* fetch the rx stats */
ring = &priv->ring[idx + queue_num];
do {
start = u64_stats_fetch_begin_irq(&ring->syncp);
rx_bytes += ring->stats.rx_bytes;
rx_pkts += ring->stats.rx_pkts;
rx_drop += ring->stats.l2_err;
rx_errors += ring->stats.l2_err;
rx_errors += ring->stats.l3l4_csum_err;
rx_crc_errors += ring->stats.l2_err;
rx_multicast += ring->stats.rx_multicast;
rx_length_errors += ring->stats.err_pkt_len;
} 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 = rx_errors;
stats->multicast = rx_multicast;
stats->rx_length_errors = rx_length_errors;
stats->rx_crc_errors = rx_crc_errors;
stats->rx_missed_errors = netdev->stats.rx_missed_errors;
stats->tx_errors = tx_errors;
stats->rx_dropped = rx_drop;
stats->tx_dropped = tx_drop;
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 int hns3_setup_tc(struct net_device *netdev, void *type_data)
{
struct tc_mqprio_qopt_offload *mqprio_qopt = type_data;
u8 *prio_tc = mqprio_qopt->qopt.prio_tc_map;
struct hnae3_knic_private_info *kinfo;
u8 tc = mqprio_qopt->qopt.num_tc;
u16 mode = mqprio_qopt->mode;
u8 hw = mqprio_qopt->qopt.hw;
struct hnae3_handle *h;
if (!((hw == TC_MQPRIO_HW_OFFLOAD_TCS &&
mode == TC_MQPRIO_MODE_CHANNEL) || (!hw && tc == 0)))
return -EOPNOTSUPP;
if (tc > HNAE3_MAX_TC)
return -EINVAL;
if (!netdev)
return -EINVAL;
h = hns3_get_handle(netdev);
kinfo = &h->kinfo;
netif_dbg(h, drv, netdev, "setup tc: num_tc=%u\n", tc);
return (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ?
kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP;
}
static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
if (type != TC_SETUP_QDISC_MQPRIO)
return -EOPNOTSUPP;
return hns3_setup_tc(dev, type_data);
}
static int hns3_vlan_rx_add_vid(struct net_device *netdev,
__be16 proto, u16 vid)
{
struct hnae3_handle *h = hns3_get_handle(netdev);
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 hnae3_handle *h = hns3_get_handle(netdev);
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 hnae3_handle *h = hns3_get_handle(netdev);
int ret = -EIO;
netif_dbg(h, drv, netdev,
"set vf vlan: vf=%d, vlan=%u, qos=%u, vlan_proto=0x%x\n",
vf, vlan, qos, ntohs(vlan_proto));
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 int hns3_set_vf_spoofchk(struct net_device *netdev, int vf, bool enable)
{
struct hnae3_handle *handle = hns3_get_handle(netdev);
if (hns3_nic_resetting(netdev))
return -EBUSY;
if (!handle->ae_algo->ops->set_vf_spoofchk)
return -EOPNOTSUPP;
return handle->ae_algo->ops->set_vf_spoofchk(handle, vf, enable);
}
static int hns3_set_vf_trust(struct net_device *netdev, int vf, bool enable)
{
struct hnae3_handle *handle = hns3_get_handle(netdev);
if (!handle->ae_algo->ops->set_vf_trust)
return -EOPNOTSUPP;
return handle->ae_algo->ops->set_vf_trust(handle, vf, enable);
}
static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu)
{
struct hnae3_handle *h = hns3_get_handle(netdev);
int ret;
if (hns3_nic_resetting(netdev))
return -EBUSY;
if (!h->ae_algo->ops->set_mtu)
return -EOPNOTSUPP;
netif_dbg(h, drv, netdev,
"change mtu from %u to %d\n", netdev->mtu, new_mtu);
ret = h->ae_algo->ops->set_mtu(h, new_mtu);
if (ret)
netdev_err(netdev, "failed to change MTU in hardware %d\n",
ret);
else
netdev->mtu = new_mtu;
return ret;
}
static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev)
{
struct hns3_nic_priv *priv = netdev_priv(ndev);
struct hnae3_handle *h = hns3_get_handle(ndev);
struct hns3_enet_ring *tx_ring;
struct napi_struct *napi;
int timeout_queue = 0;
int hw_head, hw_tail;
int fbd_num, fbd_oft;
int ebd_num, ebd_oft;
int bd_num, bd_err;
int ring_en, tc;
int i;
/* Find the stopped queue the same way the stack does */
for (i = 0; i < ndev->num_tx_queues; i++) {
struct netdev_queue *q;
unsigned long trans_start;
q = netdev_get_tx_queue(ndev, i);
trans_start = q->trans_start;
if (netif_xmit_stopped(q) &&
time_after(jiffies,
(trans_start + ndev->watchdog_timeo))) {
timeout_queue = i;
netdev_info(ndev, "queue state: 0x%lx, delta msecs: %u\n",
q->state,
jiffies_to_msecs(jiffies - trans_start));
break;
}
}
if (i == ndev->num_tx_queues) {
netdev_info(ndev,
"no netdev TX timeout queue found, timeout count: %llu\n",
priv->tx_timeout_count);
return false;
}
priv->tx_timeout_count++;
tx_ring = &priv->ring[timeout_queue];
napi = &tx_ring->tqp_vector->napi;
netdev_info(ndev,
"tx_timeout count: %llu, queue id: %d, SW_NTU: 0x%x, SW_NTC: 0x%x, napi state: %lu\n",
priv->tx_timeout_count, timeout_queue, tx_ring->next_to_use,
tx_ring->next_to_clean, napi->state);
netdev_info(ndev,
"tx_pkts: %llu, tx_bytes: %llu, io_err_cnt: %llu, sw_err_cnt: %llu\n",
tx_ring->stats.tx_pkts, tx_ring->stats.tx_bytes,
tx_ring->stats.io_err_cnt, tx_ring->stats.sw_err_cnt);
netdev_info(ndev,
"seg_pkt_cnt: %llu, tx_err_cnt: %llu, restart_queue: %llu, tx_busy: %llu\n",
tx_ring->stats.seg_pkt_cnt, tx_ring->stats.tx_err_cnt,
tx_ring->stats.restart_queue, tx_ring->stats.tx_busy);
/* When mac received many pause frames continuous, it's unable to send
* packets, which may cause tx timeout
*/
if (h->ae_algo->ops->get_mac_stats) {
struct hns3_mac_stats mac_stats;
h->ae_algo->ops->get_mac_stats(h, &mac_stats);
netdev_info(ndev, "tx_pause_cnt: %llu, rx_pause_cnt: %llu\n",
mac_stats.tx_pause_cnt, mac_stats.rx_pause_cnt);
}
hw_head = readl_relaxed(tx_ring->tqp->io_base +
HNS3_RING_TX_RING_HEAD_REG);
hw_tail = readl_relaxed(tx_ring->tqp->io_base +
HNS3_RING_TX_RING_TAIL_REG);
fbd_num = readl_relaxed(tx_ring->tqp->io_base +
HNS3_RING_TX_RING_FBDNUM_REG);
fbd_oft = readl_relaxed(tx_ring->tqp->io_base +
HNS3_RING_TX_RING_OFFSET_REG);
ebd_num = readl_relaxed(tx_ring->tqp->io_base +
HNS3_RING_TX_RING_EBDNUM_REG);
ebd_oft = readl_relaxed(tx_ring->tqp->io_base +
HNS3_RING_TX_RING_EBD_OFFSET_REG);
bd_num = readl_relaxed(tx_ring->tqp->io_base +
HNS3_RING_TX_RING_BD_NUM_REG);
bd_err = readl_relaxed(tx_ring->tqp->io_base +
HNS3_RING_TX_RING_BD_ERR_REG);
ring_en = readl_relaxed(tx_ring->tqp->io_base + HNS3_RING_EN_REG);
tc = readl_relaxed(tx_ring->tqp->io_base + HNS3_RING_TX_RING_TC_REG);
netdev_info(ndev,
"BD_NUM: 0x%x HW_HEAD: 0x%x, HW_TAIL: 0x%x, BD_ERR: 0x%x, INT: 0x%x\n",
bd_num, hw_head, hw_tail, bd_err,
readl(tx_ring->tqp_vector->mask_addr));
netdev_info(ndev,
"RING_EN: 0x%x, TC: 0x%x, FBD_NUM: 0x%x FBD_OFT: 0x%x, EBD_NUM: 0x%x, EBD_OFT: 0x%x\n",
ring_en, tc, fbd_num, fbd_oft, ebd_num, ebd_oft);
return true;
}
static void hns3_nic_net_timeout(struct net_device *ndev, unsigned int txqueue)
{
struct hns3_nic_priv *priv = netdev_priv(ndev);
struct hnae3_handle *h = priv->ae_handle;
if (!hns3_get_tx_timeo_queue_info(ndev))
return;
/* request the reset, and let the hclge to determine
* which reset level should be done
*/
if (h->ae_algo->ops->reset_event)
h->ae_algo->ops->reset_event(h->pdev, h);
}
#ifdef CONFIG_RFS_ACCEL
static int hns3_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
u16 rxq_index, u32 flow_id)
{
struct hnae3_handle *h = hns3_get_handle(dev);
struct flow_keys fkeys;
if (!h->ae_algo->ops->add_arfs_entry)
return -EOPNOTSUPP;
if (skb->encapsulation)
return -EPROTONOSUPPORT;
if (!skb_flow_dissect_flow_keys(skb, &fkeys, 0))
return -EPROTONOSUPPORT;
if ((fkeys.basic.n_proto != htons(ETH_P_IP) &&
fkeys.basic.n_proto != htons(ETH_P_IPV6)) ||
(fkeys.basic.ip_proto != IPPROTO_TCP &&
fkeys.basic.ip_proto != IPPROTO_UDP))
return -EPROTONOSUPPORT;
return h->ae_algo->ops->add_arfs_entry(h, rxq_index, flow_id, &fkeys);
}
#endif
static int hns3_nic_get_vf_config(struct net_device *ndev, int vf,
struct ifla_vf_info *ivf)
{
struct hnae3_handle *h = hns3_get_handle(ndev);
if (!h->ae_algo->ops->get_vf_config)
return -EOPNOTSUPP;
return h->ae_algo->ops->get_vf_config(h, vf, ivf);
}
static int hns3_nic_set_vf_link_state(struct net_device *ndev, int vf,
int link_state)
{
struct hnae3_handle *h = hns3_get_handle(ndev);
if (!h->ae_algo->ops->set_vf_link_state)
return -EOPNOTSUPP;
return h->ae_algo->ops->set_vf_link_state(h, vf, link_state);
}
static int hns3_nic_set_vf_rate(struct net_device *ndev, int vf,
int min_tx_rate, int max_tx_rate)
{
struct hnae3_handle *h = hns3_get_handle(ndev);
if (!h->ae_algo->ops->set_vf_rate)
return -EOPNOTSUPP;
return h->ae_algo->ops->set_vf_rate(h, vf, min_tx_rate, max_tx_rate,
false);
}
static int hns3_nic_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
{
struct hnae3_handle *h = hns3_get_handle(netdev);
if (!h->ae_algo->ops->set_vf_mac)
return -EOPNOTSUPP;
if (is_multicast_ether_addr(mac)) {
netdev_err(netdev,
"Invalid MAC:%pM specified. Could not set MAC\n",
mac);
return -EINVAL;
}
return h->ae_algo->ops->set_vf_mac(h, vf_id, mac);
}
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_tx_timeout = hns3_nic_net_timeout,
.ndo_set_mac_address = hns3_nic_net_set_mac_address,
.ndo_do_ioctl = hns3_nic_do_ioctl,
.ndo_change_mtu = hns3_nic_change_mtu,
.ndo_set_features = hns3_nic_set_features,
.ndo_features_check = hns3_features_check,
.ndo_get_stats64 = hns3_nic_get_stats64,
.ndo_setup_tc = hns3_nic_setup_tc,
.ndo_set_rx_mode = hns3_nic_set_rx_mode,
.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,
.ndo_set_vf_spoofchk = hns3_set_vf_spoofchk,
.ndo_set_vf_trust = hns3_set_vf_trust,
#ifdef CONFIG_RFS_ACCEL
.ndo_rx_flow_steer = hns3_rx_flow_steer,
#endif
.ndo_get_vf_config = hns3_nic_get_vf_config,
.ndo_set_vf_link_state = hns3_nic_set_vf_link_state,
.ndo_set_vf_rate = hns3_nic_set_vf_rate,
.ndo_set_vf_mac = hns3_nic_set_vf_mac,
};
bool hns3_is_phys_func(struct pci_dev *pdev)
{
u32 dev_id = pdev->device;
switch (dev_id) {
case HNAE3_DEV_ID_GE:
case HNAE3_DEV_ID_25GE:
case HNAE3_DEV_ID_25GE_RDMA:
case HNAE3_DEV_ID_25GE_RDMA_MACSEC:
case HNAE3_DEV_ID_50GE_RDMA:
case HNAE3_DEV_ID_50GE_RDMA_MACSEC:
case HNAE3_DEV_ID_100G_RDMA_MACSEC:
return true;
case HNAE3_DEV_ID_100G_VF:
case HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF:
return false;
default:
dev_warn(&pdev->dev, "un-recognized pci device-id %u",
dev_id);
}
return false;
}
static void hns3_disable_sriov(struct pci_dev *pdev)
{
/* If our VFs are assigned we cannot shut down SR-IOV
* without causing issues, so just leave the hardware
* available but disabled
*/
if (pci_vfs_assigned(pdev)) {
dev_warn(&pdev->dev,
"disabling driver while VFs are assigned\n");
return;
}
pci_disable_sriov(pdev);
}
static void hns3_get_dev_capability(struct pci_dev *pdev,
struct hnae3_ae_dev *ae_dev)
{
if (pdev->revision >= 0x21) {
hnae3_set_bit(ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B, 1);
hnae3_set_bit(ae_dev->flag, HNAE3_DEV_SUPPORT_GRO_B, 1);
}
}
/* 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)
return -ENOMEM;
ae_dev->pdev = pdev;
ae_dev->flag = ent->driver_data;
ae_dev->reset_type = HNAE3_NONE_RESET;
hns3_get_dev_capability(pdev, ae_dev);
pci_set_drvdata(pdev, ae_dev);
ret = hnae3_register_ae_dev(ae_dev);
if (ret) {
devm_kfree(&pdev->dev, ae_dev);
pci_set_drvdata(pdev, NULL);
}
return ret;
}
/* 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);
if (hns3_is_phys_func(pdev) && IS_ENABLED(CONFIG_PCI_IOV))
hns3_disable_sriov(pdev);
hnae3_unregister_ae_dev(ae_dev);
pci_set_drvdata(pdev, NULL);
}
/**
* hns3_pci_sriov_configure
* @pdev: pointer to a pci_dev structure
* @num_vfs: number of VFs to allocate
*
* Enable or change the number of VFs. Called when the user updates the number
* of VFs in sysfs.
**/
static int hns3_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
{
int ret;
if (!(hns3_is_phys_func(pdev) && IS_ENABLED(CONFIG_PCI_IOV))) {
dev_warn(&pdev->dev, "Can not config SRIOV\n");
return -EINVAL;
}
if (num_vfs) {
ret = pci_enable_sriov(pdev, num_vfs);
if (ret)
dev_err(&pdev->dev, "SRIOV enable failed %d\n", ret);
else
return num_vfs;
} else if (!pci_vfs_assigned(pdev)) {
pci_disable_sriov(pdev);
} else {
dev_warn(&pdev->dev,
"Unable to free VFs because some are assigned to VMs.\n");
}
return 0;
}
static void hns3_shutdown(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);
if (system_state == SYSTEM_POWER_OFF)
pci_set_power_state(pdev, PCI_D3hot);
}
static pci_ers_result_t hns3_error_detected(struct pci_dev *pdev,
pci_channel_state_t state)
{
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
pci_ers_result_t ret;
dev_info(&pdev->dev, "PCI error detected, state(=%d)!!\n", state);
if (state == pci_channel_io_perm_failure)
return PCI_ERS_RESULT_DISCONNECT;
if (!ae_dev || !ae_dev->ops) {
dev_err(&pdev->dev,
"Can't recover - error happened before device initialized\n");
return PCI_ERS_RESULT_NONE;
}
if (ae_dev->ops->handle_hw_ras_error)
ret = ae_dev->ops->handle_hw_ras_error(ae_dev);
else
return PCI_ERS_RESULT_NONE;
return ret;
}
static pci_ers_result_t hns3_slot_reset(struct pci_dev *pdev)
{
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
const struct hnae3_ae_ops *ops;
enum hnae3_reset_type reset_type;
struct device *dev = &pdev->dev;
if (!ae_dev || !ae_dev->ops)
return PCI_ERS_RESULT_NONE;
ops = ae_dev->ops;
/* request the reset */
if (ops->reset_event && ops->get_reset_level &&
ops->set_default_reset_request) {
if (ae_dev->hw_err_reset_req) {
reset_type = ops->get_reset_level(ae_dev,
&ae_dev->hw_err_reset_req);
ops->set_default_reset_request(ae_dev, reset_type);
dev_info(dev, "requesting reset due to PCI error\n");
ops->reset_event(pdev, NULL);
}
return PCI_ERS_RESULT_RECOVERED;
}
return PCI_ERS_RESULT_DISCONNECT;
}
static void hns3_reset_prepare(struct pci_dev *pdev)
{
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
dev_info(&pdev->dev, "hns3 flr prepare\n");
if (ae_dev && ae_dev->ops && ae_dev->ops->flr_prepare)
ae_dev->ops->flr_prepare(ae_dev);
}
static void hns3_reset_done(struct pci_dev *pdev)
{
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
dev_info(&pdev->dev, "hns3 flr done\n");
if (ae_dev && ae_dev->ops && ae_dev->ops->flr_done)
ae_dev->ops->flr_done(ae_dev);
}
static const struct pci_error_handlers hns3_err_handler = {
.error_detected = hns3_error_detected,
.slot_reset = hns3_slot_reset,
.reset_prepare = hns3_reset_prepare,
.reset_done = hns3_reset_done,
};
static struct pci_driver hns3_driver = {
.name = hns3_driver_name,
.id_table = hns3_pci_tbl,
.probe = hns3_probe,
.remove = hns3_remove,
.shutdown = hns3_shutdown,
.sriov_configure = hns3_pci_sriov_configure,
.err_handler = &hns3_err_handler,
};
/* set default feature to hns3 */
static void hns3_set_default_feature(struct net_device *netdev)
{
struct hnae3_handle *h = hns3_get_handle(netdev);
struct pci_dev *pdev = h->pdev;
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 | NETIF_F_SCTP_CRC |
NETIF_F_TSO_MANGLEID | NETIF_F_FRAGLIST;
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_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
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 | NETIF_F_SCTP_CRC |
NETIF_F_FRAGLIST;
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 | NETIF_F_SCTP_CRC |
NETIF_F_FRAGLIST;
netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
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 | NETIF_F_SCTP_CRC |
NETIF_F_FRAGLIST;
if (pdev->revision >= 0x21) {
netdev->hw_features |= NETIF_F_GRO_HW;
netdev->features |= NETIF_F_GRO_HW;
if (!(h->flags & HNAE3_SUPPORT_VF)) {
netdev->hw_features |= NETIF_F_NTUPLE;
netdev->features |= NETIF_F_NTUPLE;
}
}
}
static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
struct hns3_desc_cb *cb)
{
unsigned int order = hns3_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 = hns3_page_size(ring);
cb->type = DESC_TYPE_PAGE;
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 (unlikely(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 if (cb->length)
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)
{
int size = ring->desc_num * sizeof(ring->desc[0]);
hns3_free_buffers(ring);
if (ring->desc) {
dma_free_coherent(ring_to_dev(ring), size,
ring->desc, ring->desc_dma_addr);
ring->desc = NULL;
}
}
static int hns3_alloc_desc(struct hns3_enet_ring *ring)
{
int size = ring->desc_num * sizeof(ring->desc[0]);
ring->desc = dma_alloc_coherent(ring_to_dev(ring), size,
&ring->desc_dma_addr, GFP_KERNEL);
if (!ring->desc)
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_buffer(ring, cb);
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_unmap_buffer(ring, &ring->desc_cb[i]);
ring->desc_cb[i] = *res_cb;
ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma);
ring->desc[i].rx.bd_base_info = 0;
}
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);
ring->desc[i].rx.bd_base_info = 0;
}
static void hns3_nic_reclaim_desc(struct hns3_enet_ring *ring, int head,
int *bytes, int *pkts)
{
int ntc = ring->next_to_clean;
struct hns3_desc_cb *desc_cb;
while (head != ntc) {
desc_cb = &ring->desc_cb[ntc];
(*pkts) += (desc_cb->type == DESC_TYPE_SKB);
(*bytes) += desc_cb->length;
/* desc_cb will be cleaned, after hnae3_free_buffer_detach */
hns3_free_buffer_detach(ring, ntc);
if (++ntc == ring->desc_num)
ntc = 0;
/* Issue prefetch for next Tx descriptor */
prefetch(&ring->desc_cb[ntc]);
}
/* This smp_store_release() pairs with smp_load_acquire() in
* ring_space called by hns3_nic_net_xmit.
*/
smp_store_release(&ring->next_to_clean, ntc);
}
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);
}
void hns3_clean_tx_ring(struct hns3_enet_ring *ring)
{
struct net_device *netdev = ring_to_netdev(ring);
struct hns3_nic_priv *priv = netdev_priv(netdev);
struct netdev_queue *dev_queue;
int bytes, pkts;
int head;
head = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_HEAD_REG);
if (is_ring_empty(ring) || head == ring->next_to_clean)
return; /* no data to poll */
rmb(); /* Make sure head is ready before touch any data */
if (unlikely(!is_valid_clean_head(ring, head))) {
hns3_rl_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;
}
bytes = 0;
pkts = 0;
hns3_nic_reclaim_desc(ring, head, &bytes, &pkts);
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(netif_carrier_ok(netdev) &&
ring_space(ring) > HNS3_MAX_TSO_BD_NUM)) {
/* Make sure that anybody stopping the queue after this
* sees the new next_to_clean.
*/
smp_mb();
if (netif_tx_queue_stopped(dev_queue) &&
!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) {
netif_tx_wake_queue(dev_queue);
ring->stats.restart_queue++;
}
}
}
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);
hns3_rl_err(ring_to_netdev(ring),
"alloc rx buffer failed: %d\n",
ret);
break;
}
hns3_replace_buffer(ring, ring->next_to_use, &res_cbs);
u64_stats_update_begin(&ring->syncp);
ring->stats.non_reuse_pg++;
u64_stats_update_end(&ring->syncp);
}
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);
}
static bool hns3_page_is_reusable(struct page *page)
{
return page_to_nid(page) == numa_mem_id() &&
!page_is_pfmemalloc(page);
}
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 = &ring->desc[ring->next_to_clean];
int size = le16_to_cpu(desc->rx.size);
u32 truesize = hns3_buf_size(ring);
skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len,
size - pull_len, truesize);
/* Avoid re-using remote pages, or the stack is still using the page
* when page_offset rollback to zero, flag default unreuse
*/
if (unlikely(!hns3_page_is_reusable(desc_cb->priv)) ||
(!desc_cb->page_offset && page_count(desc_cb->priv) > 1))
return;
/* Move offset up to the next cache line */
desc_cb->page_offset += truesize;
if (desc_cb->page_offset + truesize <= hns3_page_size(ring)) {
desc_cb->reuse_flag = 1;
/* Bump ref count on page before it is given */
get_page(desc_cb->priv);
} else if (page_count(desc_cb->priv) == 1) {
desc_cb->reuse_flag = 1;
desc_cb->page_offset = 0;
get_page(desc_cb->priv);
}
}
static int hns3_gro_complete(struct sk_buff *skb, u32 l234info)
{
__be16 type = skb->protocol;
struct tcphdr *th;
int depth = 0;
while (eth_type_vlan(type)) {
struct vlan_hdr *vh;
if ((depth + VLAN_HLEN) > skb_headlen(skb))
return -EFAULT;
vh = (struct vlan_hdr *)(skb->data + depth);
type = vh->h_vlan_encapsulated_proto;
depth += VLAN_HLEN;
}
skb_set_network_header(skb, depth);
if (type == htons(ETH_P_IP)) {
const struct iphdr *iph = ip_hdr(skb);
depth += sizeof(struct iphdr);
skb_set_transport_header(skb, depth);
th = tcp_hdr(skb);
th->check = ~tcp_v4_check(skb->len - depth, iph->saddr,
iph->daddr, 0);
} else if (type == htons(ETH_P_IPV6)) {
const struct ipv6hdr *iph = ipv6_hdr(skb);
depth += sizeof(struct ipv6hdr);
skb_set_transport_header(skb, depth);
th = tcp_hdr(skb);
th->check = ~tcp_v6_check(skb->len - depth, &iph->saddr,
&iph->daddr, 0);
} else {
hns3_rl_err(skb->dev,
"Error: FW GRO supports only IPv4/IPv6, not 0x%04x, depth: %d\n",
be16_to_cpu(type), depth);
return -EFAULT;
}
skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;