#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/init.h>
#include <linux/atomic.h>
#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/highmem.h>
#include <linux/device.h>
#include <linux/io.h>
#include <linux/delay.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
#include <linux/pci.h>
#include <linux/skbuff.h>
#include <linux/if_vlan.h>
#include <linux/in.h>
#include <linux/slab.h>
#include <linux/rtnetlink.h>
#include <linux/netpoll.h>
#include <linux/bpf.h>
#include <net/arp.h>
#include <net/netdev_lock.h>
#include <net/route.h>
#include <net/sock.h>
#include <net/pkt_sched.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include "hyperv_net.h"
#define RING_SIZE_MIN 64
#define LINKCHANGE_INT (2 * HZ)
#define VF_TAKEOVER_INT (HZ / 10)
#define VF_REG_IN_PROBE 1
#define VF_REG_IN_NOTIFIER 2
static unsigned int ring_size __ro_after_init = 128;
module_param(ring_size, uint, 0444);
MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)");
unsigned int netvsc_ring_bytes __ro_after_init;
static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
NETIF_MSG_LINK | NETIF_MSG_IFUP |
NETIF_MSG_IFDOWN | NETIF_MSG_RX_ERR |
NETIF_MSG_TX_ERR;
static int debug = -1;
module_param(debug, int, 0444);
MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
static LIST_HEAD(netvsc_dev_list);
static void netvsc_change_rx_flags(struct net_device *net, int change)
{
struct net_device_context *ndev_ctx = netdev_priv(net);
struct net_device *vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
int inc;
if (!vf_netdev)
return;
if (change & IFF_PROMISC) {
inc = (net->flags & IFF_PROMISC) ? 1 : -1;
dev_set_promiscuity(vf_netdev, inc);
}
if (change & IFF_ALLMULTI) {
inc = (net->flags & IFF_ALLMULTI) ? 1 : -1;
dev_set_allmulti(vf_netdev, inc);
}
}
static void netvsc_set_rx_mode(struct net_device *net)
{
struct net_device_context *ndev_ctx = netdev_priv(net);
struct net_device *vf_netdev;
struct netvsc_device *nvdev;
rcu_read_lock();
vf_netdev = rcu_dereference(ndev_ctx->vf_netdev);
if (vf_netdev) {
dev_uc_sync(vf_netdev, net);
dev_mc_sync(vf_netdev, net);
}
nvdev = rcu_dereference(ndev_ctx->nvdev);
if (nvdev)
rndis_filter_update(nvdev);
rcu_read_unlock();
}
static void netvsc_tx_enable(struct netvsc_device *nvscdev,
struct net_device *ndev)
{
nvscdev->tx_disable = false;
virt_wmb();
netif_tx_wake_all_queues(ndev);
}
static int netvsc_open(struct net_device *net)
{
struct net_device_context *ndev_ctx = netdev_priv(net);
struct net_device *vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
struct netvsc_device *nvdev = rtnl_dereference(ndev_ctx->nvdev);
struct rndis_device *rdev;
int ret = 0;
netif_carrier_off(net);
ret = rndis_filter_open(nvdev);
if (ret != 0) {
netdev_err(net, "unable to open device (ret %d).\n", ret);
return ret;
}
rdev = nvdev->extension;
if (!rdev->link_state) {
netif_carrier_on(net);
netvsc_tx_enable(nvdev, net);
}
if (vf_netdev) {
ret = dev_open(vf_netdev, NULL);
if (ret)
netdev_warn(net,
"unable to open slave: %s: %d\n",
vf_netdev->name, ret);
}
return 0;
}
static int netvsc_wait_until_empty(struct netvsc_device *nvdev)
{
unsigned int retry = 0;
int i;
for (;;) {
u32 aread = 0;
for (i = 0; i < nvdev->num_chn; i++) {
struct vmbus_channel *chn
= nvdev->chan_table[i].channel;
if (!chn)
continue;
napi_synchronize(&nvdev->chan_table[i].napi);
aread = hv_get_bytes_to_read(&chn->inbound);
if (aread)
break;
aread = hv_get_bytes_to_read(&chn->outbound);
if (aread)
break;
}
if (aread == 0)
return 0;
if (++retry > RETRY_MAX)
return -ETIMEDOUT;
usleep_range(RETRY_US_LO, RETRY_US_HI);
}
}
static void netvsc_tx_disable(struct netvsc_device *nvscdev,
struct net_device *ndev)
{
if (nvscdev) {
nvscdev->tx_disable = true;
virt_wmb();
}
netif_tx_disable(ndev);
}
static int netvsc_close(struct net_device *net)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
struct net_device *vf_netdev
= rtnl_dereference(net_device_ctx->vf_netdev);
struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
int ret;
netvsc_tx_disable(nvdev, net);
if (!nvdev)
return 0;
ret = rndis_filter_close(nvdev);
if (ret != 0) {
netdev_err(net, "unable to close device (ret %d).\n", ret);
return ret;
}
ret = netvsc_wait_until_empty(nvdev);
if (ret)
netdev_err(net, "Ring buffer not empty after closing rndis\n");
if (vf_netdev)
dev_close(vf_netdev);
return ret;
}
static inline void *init_ppi_data(struct rndis_message *msg,
u32 ppi_size, u32 pkt_type)
{
struct rndis_packet *rndis_pkt = &msg->msg.pkt;
struct rndis_per_packet_info *ppi;
rndis_pkt->data_offset += ppi_size;
ppi = (void *)rndis_pkt + rndis_pkt->per_pkt_info_offset
+ rndis_pkt->per_pkt_info_len;
ppi->size = ppi_size;
ppi->type = pkt_type;
ppi->internal = 0;
ppi->ppi_offset = sizeof(struct rndis_per_packet_info);
rndis_pkt->per_pkt_info_len += ppi_size;
return ppi + 1;
}
static inline int netvsc_get_tx_queue(struct net_device *ndev,
struct sk_buff *skb, int old_idx)
{
const struct net_device_context *ndc = netdev_priv(ndev);
struct sock *sk = skb->sk;
int q_idx;
q_idx = ndc->tx_table[netvsc_get_hash(skb, ndc) &
(VRSS_SEND_TAB_SIZE - 1)];
if (q_idx != old_idx &&
sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache))
sk_tx_queue_set(sk, q_idx);
return q_idx;
}
static u16 netvsc_pick_tx(struct net_device *ndev, struct sk_buff *skb)
{
int q_idx = sk_tx_queue_get(skb->sk);
if (q_idx < 0 || skb->ooo_okay || q_idx >= ndev->real_num_tx_queues) {
if (skb_rx_queue_recorded(skb))
q_idx = skb_get_rx_queue(skb);
else
q_idx = netvsc_get_tx_queue(ndev, skb, q_idx);
}
return q_idx;
}
static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
struct net_device *sb_dev)
{
struct net_device_context *ndc = netdev_priv(ndev);
struct net_device *vf_netdev;
u16 txq;
rcu_read_lock();
vf_netdev = rcu_dereference(ndc->vf_netdev);
if (vf_netdev) {
const struct net_device_ops *vf_ops = vf_netdev->netdev_ops;
if (vf_ops->ndo_select_queue)
txq = vf_ops->ndo_select_queue(vf_netdev, skb, sb_dev);
else
txq = netdev_pick_tx(vf_netdev, skb, NULL);
qdisc_skb_cb(skb)->slave_dev_queue_mapping = txq;
} else {
txq = netvsc_pick_tx(ndev, skb);
}
rcu_read_unlock();
while (txq >= ndev->real_num_tx_queues)
txq -= ndev->real_num_tx_queues;
return txq;
}
static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
struct hv_netvsc_packet *packet,
struct hv_page_buffer *pb)
{
int frags = skb_shinfo(skb)->nr_frags;
int i;
pb[0].offset = offset_in_hvpage(hdr);
pb[0].len = len;
pb[0].pfn = virt_to_hvpfn(hdr);
packet->rmsg_size = len;
pb[1].offset = offset_in_hvpage(skb->data);
pb[1].len = skb_headlen(skb);
pb[1].pfn = virt_to_hvpfn(skb->data);
for (i = 0; i < frags; i++) {
skb_frag_t *frag = skb_shinfo(skb)->frags + i;
struct hv_page_buffer *cur_pb = &pb[i + 2];
u64 pfn = page_to_hvpfn(skb_frag_page(frag));
u32 offset = skb_frag_off(frag);
cur_pb->offset = offset_in_hvpage(offset);
cur_pb->len = skb_frag_size(frag);
cur_pb->pfn = pfn + (offset >> HV_HYP_PAGE_SHIFT);
}
return frags + 2;
}
static int count_skb_frag_slots(struct sk_buff *skb)
{
int i, frags = skb_shinfo(skb)->nr_frags;
int pages = 0;
for (i = 0; i < frags; i++) {
skb_frag_t *frag = skb_shinfo(skb)->frags + i;
unsigned long size = skb_frag_size(frag);
unsigned long offset = skb_frag_off(frag);
offset &= ~HV_HYP_PAGE_MASK;
pages += HVPFN_UP(offset + size);
}
return pages;
}
static int netvsc_get_slots(struct sk_buff *skb)
{
char *data = skb->data;
unsigned int offset = offset_in_hvpage(data);
unsigned int len = skb_headlen(skb);
int slots;
int frag_slots;
slots = DIV_ROUND_UP(offset + len, HV_HYP_PAGE_SIZE);
frag_slots = count_skb_frag_slots(skb);
return slots + frag_slots;
}
static u32 net_checksum_info(struct sk_buff *skb)
{
if (skb->protocol == htons(ETH_P_IP)) {
struct iphdr *ip = ip_hdr(skb);
if (ip->protocol == IPPROTO_TCP)
return TRANSPORT_INFO_IPV4_TCP;
else if (ip->protocol == IPPROTO_UDP)
return TRANSPORT_INFO_IPV4_UDP;
} else {
struct ipv6hdr *ip6 = ipv6_hdr(skb);
if (ip6->nexthdr == IPPROTO_TCP)
return TRANSPORT_INFO_IPV6_TCP;
else if (ip6->nexthdr == IPPROTO_UDP)
return TRANSPORT_INFO_IPV6_UDP;
}
return TRANSPORT_INFO_NOT_IP;
}
static int netvsc_vf_xmit(struct net_device *net, struct net_device *vf_netdev,
struct sk_buff *skb)
{
struct net_device_context *ndev_ctx = netdev_priv(net);
unsigned int len = skb->len;
int rc;
skb->dev = vf_netdev;
skb_record_rx_queue(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping);
rc = dev_queue_xmit(skb);
if (likely(rc == NET_XMIT_SUCCESS || rc == NET_XMIT_CN)) {
struct netvsc_vf_pcpu_stats *pcpu_stats
= this_cpu_ptr(ndev_ctx->vf_stats);
u64_stats_update_begin(&pcpu_stats->syncp);
pcpu_stats->tx_packets++;
pcpu_stats->tx_bytes += len;
u64_stats_update_end(&pcpu_stats->syncp);
} else {
this_cpu_inc(ndev_ctx->vf_stats->tx_dropped);
}
return rc;
}
static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
struct hv_netvsc_packet *packet = NULL;
int ret;
unsigned int num_data_pgs;
struct rndis_message *rndis_msg;
struct net_device *vf_netdev;
u32 rndis_msg_size;
u32 hash;
struct hv_page_buffer pb[MAX_DATA_RANGES];
vf_netdev = rcu_dereference_bh(net_device_ctx->vf_netdev);
if (vf_netdev && netif_running(vf_netdev) &&
netif_carrier_ok(vf_netdev) && !netpoll_tx_running(net) &&
net_device_ctx->data_path_is_vf)
return netvsc_vf_xmit(net, vf_netdev, skb);
num_data_pgs = netvsc_get_slots(skb) + 2;
if (unlikely(num_data_pgs > MAX_PAGE_BUFFER_COUNT)) {
++net_device_ctx->eth_stats.tx_scattered;
if (skb_linearize(skb))
goto no_memory;
num_data_pgs = netvsc_get_slots(skb) + 2;
if (num_data_pgs > MAX_PAGE_BUFFER_COUNT) {
++net_device_ctx->eth_stats.tx_too_big;
goto drop;
}
}
ret = skb_cow_head(skb, RNDIS_AND_PPI_SIZE);
if (ret)
goto no_memory;
BUILD_BUG_ON(sizeof(struct hv_netvsc_packet) >
sizeof_field(struct sk_buff, cb));
packet = (struct hv_netvsc_packet *)skb->cb;
packet->q_idx = skb_get_queue_mapping(skb);
packet->total_data_buflen = skb->len;
packet->total_bytes = skb->len;
packet->total_packets = 1;
rndis_msg = (struct rndis_message *)skb->head;
rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET;
rndis_msg->msg_len = packet->total_data_buflen;
rndis_msg->msg.pkt = (struct rndis_packet) {
.data_offset = sizeof(struct rndis_packet),
.data_len = packet->total_data_buflen,
.per_pkt_info_offset = sizeof(struct rndis_packet),
};
rndis_msg_size = RNDIS_MESSAGE_SIZE(struct rndis_packet);
hash = skb_get_hash_raw(skb);
if (hash != 0 && net->real_num_tx_queues > 1) {
u32 *hash_info;
rndis_msg_size += NDIS_HASH_PPI_SIZE;
hash_info = init_ppi_data(rndis_msg, NDIS_HASH_PPI_SIZE,
NBL_HASH_VALUE);
*hash_info = hash;
}
if (skb->protocol == htons(ETH_P_8021Q)) {
u16 vlan_tci;
skb_reset_mac_header(skb);
if (eth_type_vlan(eth_hdr(skb)->h_proto)) {
if (unlikely(__skb_vlan_pop(skb, &vlan_tci) != 0)) {
++net_device_ctx->eth_stats.vlan_error;
goto drop;
}
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
packet->total_data_buflen -= VLAN_HLEN;
packet->total_bytes -= VLAN_HLEN;
rndis_msg->msg_len = packet->total_data_buflen;
rndis_msg->msg.pkt.data_len = packet->total_data_buflen;
}
}
if (skb_vlan_tag_present(skb)) {
struct ndis_pkt_8021q_info *vlan;
rndis_msg_size += NDIS_VLAN_PPI_SIZE;
vlan = init_ppi_data(rndis_msg, NDIS_VLAN_PPI_SIZE,
IEEE_8021Q_INFO);
vlan->value = 0;
vlan->vlanid = skb_vlan_tag_get_id(skb);
vlan->cfi = skb_vlan_tag_get_cfi(skb);
vlan->pri = skb_vlan_tag_get_prio(skb);
}
if (skb_is_gso(skb)) {
struct ndis_tcp_lso_info *lso_info;
rndis_msg_size += NDIS_LSO_PPI_SIZE;
lso_info = init_ppi_data(rndis_msg, NDIS_LSO_PPI_SIZE,
TCP_LARGESEND_PKTINFO);
lso_info->value = 0;
lso_info->lso_v2_transmit.type = NDIS_TCP_LARGE_SEND_OFFLOAD_V2_TYPE;
if (skb->protocol == htons(ETH_P_IP)) {
lso_info->lso_v2_transmit.ip_version =
NDIS_TCP_LARGE_SEND_OFFLOAD_IPV4;
ip_hdr(skb)->tot_len = 0;
ip_hdr(skb)->check = 0;
tcp_hdr(skb)->check =
~csum_tcpudp_magic(ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr, 0, IPPROTO_TCP, 0);
} else {
lso_info->lso_v2_transmit.ip_version =
NDIS_TCP_LARGE_SEND_OFFLOAD_IPV6;
tcp_v6_gso_csum_prep(skb);
}
lso_info->lso_v2_transmit.tcp_header_offset = skb_transport_offset(skb);
lso_info->lso_v2_transmit.mss = skb_shinfo(skb)->gso_size;
} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
if (net_checksum_info(skb) & net_device_ctx->tx_checksum_mask) {
struct ndis_tcp_ip_checksum_info *csum_info;
rndis_msg_size += NDIS_CSUM_PPI_SIZE;
csum_info = init_ppi_data(rndis_msg, NDIS_CSUM_PPI_SIZE,
TCPIP_CHKSUM_PKTINFO);
csum_info->value = 0;
csum_info->transmit.tcp_header_offset = skb_transport_offset(skb);
if (skb->protocol == htons(ETH_P_IP)) {
csum_info->transmit.is_ipv4 = 1;
if (ip_hdr(skb)->protocol == IPPROTO_TCP)
csum_info->transmit.tcp_checksum = 1;
else
csum_info->transmit.udp_checksum = 1;
} else {
csum_info->transmit.is_ipv6 = 1;
if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
csum_info->transmit.tcp_checksum = 1;
else
csum_info->transmit.udp_checksum = 1;
}
} else {
if (skb_checksum_help(skb))
goto drop;
}
}
rndis_msg->msg_len += rndis_msg_size;
packet->total_data_buflen = rndis_msg->msg_len;
packet->page_buf_cnt = init_page_array(rndis_msg, rndis_msg_size,
skb, packet, pb);
skb_tx_timestamp(skb);
ret = netvsc_send(net, packet, rndis_msg, pb, skb, xdp_tx);
if (likely(ret == 0))
return NETDEV_TX_OK;
if (ret == -EAGAIN) {
++net_device_ctx->eth_stats.tx_busy;
return NETDEV_TX_BUSY;
}
if (ret == -ENOSPC)
++net_device_ctx->eth_stats.tx_no_space;
drop:
dev_kfree_skb_any(skb);
net->stats.tx_dropped++;
return NETDEV_TX_OK;
no_memory:
++net_device_ctx->eth_stats.tx_no_memory;
goto drop;
}
static netdev_tx_t netvsc_start_xmit(struct sk_buff *skb,
struct net_device *ndev)
{
return netvsc_xmit(skb, ndev, false);
}
void netvsc_linkstatus_callback(struct net_device *net,
struct rndis_message *resp,
void *data, u32 data_buflen)
{
struct rndis_indicate_status *indicate = &resp->msg.indicate_status;
struct net_device_context *ndev_ctx = netdev_priv(net);
struct netvsc_reconfig *event;
unsigned long flags;
if (resp->msg_len - RNDIS_HEADER_SIZE < sizeof(struct rndis_indicate_status)) {
netdev_err(net, "invalid rndis_indicate_status packet, len: %u\n",
resp->msg_len);
return;
}
memcpy(indicate, data + RNDIS_HEADER_SIZE, sizeof(*indicate));
if (indicate->status == RNDIS_STATUS_LINK_SPEED_CHANGE) {
u32 speed;
if (indicate->status_buflen < sizeof(speed) ||
indicate->status_buf_offset < sizeof(*indicate) ||
data_buflen - RNDIS_HEADER_SIZE < indicate->status_buf_offset ||
data_buflen - RNDIS_HEADER_SIZE - indicate->status_buf_offset
< indicate->status_buflen) {
netdev_err(net, "invalid rndis_indicate_status packet\n");
return;
}
speed = *(u32 *)(data + RNDIS_HEADER_SIZE + indicate->status_buf_offset) / 10000;
ndev_ctx->speed = speed;
return;
}
if (indicate->status != RNDIS_STATUS_NETWORK_CHANGE &&
indicate->status != RNDIS_STATUS_MEDIA_CONNECT &&
indicate->status != RNDIS_STATUS_MEDIA_DISCONNECT)
return;
if (net->reg_state != NETREG_REGISTERED)
return;
event = kzalloc_obj(*event, GFP_ATOMIC);
if (!event)
return;
event->event = indicate->status;
spin_lock_irqsave(&ndev_ctx->lock, flags);
list_add_tail(&event->list, &ndev_ctx->reconfig_events);
spin_unlock_irqrestore(&ndev_ctx->lock, flags);
schedule_delayed_work(&ndev_ctx->dwork, 0);
}
void netvsc_xdp_xmit(struct sk_buff *skb, struct net_device *ndev)
{
int rc;
skb->queue_mapping = skb_get_rx_queue(skb);
__skb_push(skb, ETH_HLEN);
rc = netvsc_xmit(skb, ndev, true);
if (dev_xmit_complete(rc))
return;
dev_kfree_skb_any(skb);
ndev->stats.tx_dropped++;
}
static void netvsc_comp_ipcsum(struct sk_buff *skb)
{
struct iphdr *iph = (struct iphdr *)skb->data;
iph->check = 0;
iph->check = ip_fast_csum(iph, iph->ihl);
}
static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
struct netvsc_channel *nvchan,
struct xdp_buff *xdp)
{
struct napi_struct *napi = &nvchan->napi;
const struct ndis_pkt_8021q_info *vlan = &nvchan->rsc.vlan;
const struct ndis_tcp_ip_checksum_info *csum_info =
&nvchan->rsc.csum_info;
const u32 *hash_info = &nvchan->rsc.hash_info;
u8 ppi_flags = nvchan->rsc.ppi_flags;
struct sk_buff *skb;
void *xbuf = xdp->data_hard_start;
int i;
if (xbuf) {
unsigned int hdroom = xdp->data - xdp->data_hard_start;
unsigned int xlen = xdp->data_end - xdp->data;
unsigned int frag_size = xdp->frame_sz;
skb = build_skb(xbuf, frag_size);
if (!skb) {
__free_page(virt_to_page(xbuf));
return NULL;
}
skb_reserve(skb, hdroom);
skb_put(skb, xlen);
skb->dev = napi->dev;
} else {
skb = napi_alloc_skb(napi, nvchan->rsc.pktlen);
if (!skb)
return NULL;
for (i = 0; i < nvchan->rsc.cnt; i++)
skb_put_data(skb, nvchan->rsc.data[i],
nvchan->rsc.len[i]);
}
skb->protocol = eth_type_trans(skb, net);
skb_checksum_none_assert(skb);
if ((ppi_flags & NVSC_RSC_CSUM_INFO) && csum_info->receive.ip_checksum_value_invalid &&
csum_info->receive.ip_checksum_succeeded &&
skb->protocol == htons(ETH_P_IP)) {
if (skb_headlen(skb) < sizeof(struct iphdr)) {
kfree_skb(skb);
return NULL;
}
netvsc_comp_ipcsum(skb);
}
if ((ppi_flags & NVSC_RSC_CSUM_INFO) && (net->features & NETIF_F_RXCSUM)) {
if (csum_info->receive.tcp_checksum_succeeded ||
csum_info->receive.udp_checksum_succeeded)
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
if ((ppi_flags & NVSC_RSC_HASH_INFO) && (net->features & NETIF_F_RXHASH))
skb_set_hash(skb, *hash_info, PKT_HASH_TYPE_L4);
if (ppi_flags & NVSC_RSC_VLAN) {
u16 vlan_tci = vlan->vlanid | (vlan->pri << VLAN_PRIO_SHIFT) |
(vlan->cfi ? VLAN_CFI_MASK : 0);
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
vlan_tci);
}
return skb;
}
int netvsc_recv_callback(struct net_device *net,
struct netvsc_device *net_device,
struct netvsc_channel *nvchan)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
struct vmbus_channel *channel = nvchan->channel;
u16 q_idx = channel->offermsg.offer.sub_channel_index;
struct sk_buff *skb;
struct netvsc_stats_rx *rx_stats = &nvchan->rx_stats;
struct xdp_buff xdp;
u32 act;
if (net->reg_state != NETREG_REGISTERED)
return NVSP_STAT_FAIL;
act = netvsc_run_xdp(net, nvchan, &xdp);
if (act == XDP_REDIRECT)
return NVSP_STAT_SUCCESS;
if (act != XDP_PASS && act != XDP_TX) {
u64_stats_update_begin(&rx_stats->syncp);
rx_stats->xdp_drop++;
u64_stats_update_end(&rx_stats->syncp);
return NVSP_STAT_SUCCESS;
}
skb = netvsc_alloc_recv_skb(net, nvchan, &xdp);
if (unlikely(!skb)) {
++net_device_ctx->eth_stats.rx_no_memory;
return NVSP_STAT_FAIL;
}
skb_record_rx_queue(skb, q_idx);
u64_stats_update_begin(&rx_stats->syncp);
if (act == XDP_TX)
rx_stats->xdp_tx++;
rx_stats->packets++;
rx_stats->bytes += nvchan->rsc.pktlen;
if (skb->pkt_type == PACKET_BROADCAST)
++rx_stats->broadcast;
else if (skb->pkt_type == PACKET_MULTICAST)
++rx_stats->multicast;
u64_stats_update_end(&rx_stats->syncp);
if (act == XDP_TX) {
netvsc_xdp_xmit(skb, net);
return NVSP_STAT_SUCCESS;
}
napi_gro_receive(&nvchan->napi, skb);
return NVSP_STAT_SUCCESS;
}
static void netvsc_get_drvinfo(struct net_device *net,
struct ethtool_drvinfo *info)
{
strscpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
strscpy(info->fw_version, "N/A", sizeof(info->fw_version));
}
static void netvsc_get_channels(struct net_device *net,
struct ethtool_channels *channel)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
if (nvdev) {
channel->max_combined = nvdev->max_chn;
channel->combined_count = nvdev->num_chn;
}
}
static
struct netvsc_device_info *netvsc_devinfo_get(struct netvsc_device *nvdev)
{
struct netvsc_device_info *dev_info;
struct bpf_prog *prog;
dev_info = kzalloc_obj(*dev_info, GFP_ATOMIC);
if (!dev_info)
return NULL;
if (nvdev) {
ASSERT_RTNL();
dev_info->num_chn = nvdev->num_chn;
dev_info->send_sections = nvdev->send_section_cnt;
dev_info->send_section_size = nvdev->send_section_size;
dev_info->recv_sections = nvdev->recv_section_cnt;
dev_info->recv_section_size = nvdev->recv_section_size;
memcpy(dev_info->rss_key, nvdev->extension->rss_key,
NETVSC_HASH_KEYLEN);
prog = netvsc_xdp_get(nvdev);
if (prog) {
bpf_prog_inc(prog);
dev_info->bprog = prog;
}
} else {
dev_info->num_chn = max(VRSS_CHANNEL_DEFAULT,
netif_get_num_default_rss_queues());
dev_info->send_sections = NETVSC_DEFAULT_TX;
dev_info->send_section_size = NETVSC_SEND_SECTION_SIZE;
dev_info->recv_sections = NETVSC_DEFAULT_RX;
dev_info->recv_section_size = NETVSC_RECV_SECTION_SIZE;
}
return dev_info;
}
static void netvsc_devinfo_put(struct netvsc_device_info *dev_info)
{
if (dev_info->bprog) {
ASSERT_RTNL();
bpf_prog_put(dev_info->bprog);
}
kfree(dev_info);
}
static int netvsc_detach(struct net_device *ndev,
struct netvsc_device *nvdev)
{
struct net_device_context *ndev_ctx = netdev_priv(ndev);
struct hv_device *hdev = ndev_ctx->device_ctx;
int ret;
if (cancel_work_sync(&nvdev->subchan_work))
nvdev->num_chn = 1;
netvsc_xdp_set(ndev, NULL, NULL, nvdev);
if (netif_running(ndev)) {
netvsc_tx_disable(nvdev, ndev);
ret = rndis_filter_close(nvdev);
if (ret) {
netdev_err(ndev,
"unable to close device (ret %d).\n", ret);
return ret;
}
ret = netvsc_wait_until_empty(nvdev);
if (ret) {
netdev_err(ndev,
"Ring buffer not empty after closing rndis\n");
return ret;
}
}
netif_device_detach(ndev);
rndis_filter_device_remove(hdev, nvdev);
return 0;
}
static int netvsc_attach(struct net_device *ndev,
struct netvsc_device_info *dev_info)
{
struct net_device_context *ndev_ctx = netdev_priv(ndev);
struct hv_device *hdev = ndev_ctx->device_ctx;
struct netvsc_device *nvdev;
struct rndis_device *rdev;
struct bpf_prog *prog;
int ret = 0;
nvdev = rndis_filter_device_add(hdev, dev_info);
if (IS_ERR(nvdev))
return PTR_ERR(nvdev);
if (nvdev->num_chn > 1) {
ret = rndis_set_subchannel(ndev, nvdev, dev_info);
if (ret) {
nvdev->max_chn = 1;
nvdev->num_chn = 1;
}
}
prog = dev_info->bprog;
if (prog) {
bpf_prog_inc(prog);
ret = netvsc_xdp_set(ndev, prog, NULL, nvdev);
if (ret) {
bpf_prog_put(prog);
goto err1;
}
}
nvdev->tx_disable = false;
netif_device_attach(ndev);
netif_carrier_off(ndev);
if (netif_running(ndev)) {
ret = rndis_filter_open(nvdev);
if (ret)
goto err2;
rdev = nvdev->extension;
if (!rdev->link_state)
netif_carrier_on(ndev);
}
return 0;
err2:
netif_device_detach(ndev);
err1:
rndis_filter_device_remove(hdev, nvdev);
return ret;
}
static int netvsc_set_channels(struct net_device *net,
struct ethtool_channels *channels)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
unsigned int orig, count = channels->combined_count;
struct netvsc_device_info *device_info;
int ret;
if (count == 0 ||
channels->rx_count || channels->tx_count || channels->other_count)
return -EINVAL;
if (!nvdev || nvdev->destroy)
return -ENODEV;
if (nvdev->nvsp_version < NVSP_PROTOCOL_VERSION_5)
return -EINVAL;
if (count > nvdev->max_chn)
return -EINVAL;
orig = nvdev->num_chn;
device_info = netvsc_devinfo_get(nvdev);
if (!device_info)
return -ENOMEM;
device_info->num_chn = count;
ret = netvsc_detach(net, nvdev);
if (ret)
goto out;
ret = netvsc_attach(net, device_info);
if (ret) {
device_info->num_chn = orig;
if (netvsc_attach(net, device_info))
netdev_err(net, "restoring channel setting failed\n");
}
out:
netvsc_devinfo_put(device_info);
return ret;
}
static void netvsc_init_settings(struct net_device *dev)
{
struct net_device_context *ndc = netdev_priv(dev);
ndc->l4_hash = HV_DEFAULT_L4HASH;
ndc->speed = SPEED_UNKNOWN;
ndc->duplex = DUPLEX_FULL;
dev->features = NETIF_F_LRO;
}
static int netvsc_get_link_ksettings(struct net_device *dev,
struct ethtool_link_ksettings *cmd)
{
struct net_device_context *ndc = netdev_priv(dev);
struct net_device *vf_netdev;
vf_netdev = rtnl_dereference(ndc->vf_netdev);
if (vf_netdev)
return __ethtool_get_link_ksettings(vf_netdev, cmd);
cmd->base.speed = ndc->speed;
cmd->base.duplex = ndc->duplex;
cmd->base.port = PORT_OTHER;
return 0;
}
static int netvsc_set_link_ksettings(struct net_device *dev,
const struct ethtool_link_ksettings *cmd)
{
struct net_device_context *ndc = netdev_priv(dev);
struct net_device *vf_netdev = rtnl_dereference(ndc->vf_netdev);
if (vf_netdev) {
if (!vf_netdev->ethtool_ops->set_link_ksettings)
return -EOPNOTSUPP;
return vf_netdev->ethtool_ops->set_link_ksettings(vf_netdev,
cmd);
}
return ethtool_virtdev_set_link_ksettings(dev, cmd,
&ndc->speed, &ndc->duplex);
}
static int netvsc_change_mtu(struct net_device *ndev, int mtu)
{
struct net_device_context *ndevctx = netdev_priv(ndev);
struct net_device *vf_netdev = rtnl_dereference(ndevctx->vf_netdev);
struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
int orig_mtu = ndev->mtu;
struct netvsc_device_info *device_info;
int ret = 0;
if (!nvdev || nvdev->destroy)
return -ENODEV;
device_info = netvsc_devinfo_get(nvdev);
if (!device_info)
return -ENOMEM;
if (vf_netdev) {
ret = dev_set_mtu(vf_netdev, mtu);
if (ret)
goto out;
}
ret = netvsc_detach(ndev, nvdev);
if (ret)
goto rollback_vf;
WRITE_ONCE(ndev->mtu, mtu);
ret = netvsc_attach(ndev, device_info);
if (!ret)
goto out;
WRITE_ONCE(ndev->mtu, orig_mtu);
if (netvsc_attach(ndev, device_info))
netdev_err(ndev, "restoring mtu failed\n");
rollback_vf:
if (vf_netdev)
dev_set_mtu(vf_netdev, orig_mtu);
out:
netvsc_devinfo_put(device_info);
return ret;
}
static void netvsc_get_vf_stats(struct net_device *net,
struct netvsc_vf_pcpu_stats *tot)
{
struct net_device_context *ndev_ctx = netdev_priv(net);
int i;
memset(tot, 0, sizeof(*tot));
for_each_possible_cpu(i) {
const struct netvsc_vf_pcpu_stats *stats
= per_cpu_ptr(ndev_ctx->vf_stats, i);
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
unsigned int start;
do {
start = u64_stats_fetch_begin(&stats->syncp);
rx_packets = stats->rx_packets;
tx_packets = stats->tx_packets;
rx_bytes = stats->rx_bytes;
tx_bytes = stats->tx_bytes;
} while (u64_stats_fetch_retry(&stats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
tot->rx_bytes += rx_bytes;
tot->tx_bytes += tx_bytes;
tot->tx_dropped += stats->tx_dropped;
}
}
static void netvsc_get_pcpu_stats(struct net_device *net,
struct netvsc_ethtool_pcpu_stats *pcpu_tot)
{
struct net_device_context *ndev_ctx = netdev_priv(net);
struct netvsc_device *nvdev = rcu_dereference_rtnl(ndev_ctx->nvdev);
int i;
for_each_possible_cpu(i) {
const struct netvsc_vf_pcpu_stats *stats =
per_cpu_ptr(ndev_ctx->vf_stats, i);
struct netvsc_ethtool_pcpu_stats *this_tot = &pcpu_tot[i];
unsigned int start;
do {
start = u64_stats_fetch_begin(&stats->syncp);
this_tot->vf_rx_packets = stats->rx_packets;
this_tot->vf_tx_packets = stats->tx_packets;
this_tot->vf_rx_bytes = stats->rx_bytes;
this_tot->vf_tx_bytes = stats->tx_bytes;
} while (u64_stats_fetch_retry(&stats->syncp, start));
this_tot->rx_packets = this_tot->vf_rx_packets;
this_tot->tx_packets = this_tot->vf_tx_packets;
this_tot->rx_bytes = this_tot->vf_rx_bytes;
this_tot->tx_bytes = this_tot->vf_tx_bytes;
}
for (i = 0; i < nvdev->num_chn; i++) {
const struct netvsc_channel *nvchan = &nvdev->chan_table[i];
const struct netvsc_stats_tx *tx_stats;
const struct netvsc_stats_rx *rx_stats;
struct netvsc_ethtool_pcpu_stats *this_tot =
&pcpu_tot[nvchan->channel->target_cpu];
u64 packets, bytes;
unsigned int start;
tx_stats = &nvchan->tx_stats;
do {
start = u64_stats_fetch_begin(&tx_stats->syncp);
packets = tx_stats->packets;
bytes = tx_stats->bytes;
} while (u64_stats_fetch_retry(&tx_stats->syncp, start));
this_tot->tx_bytes += bytes;
this_tot->tx_packets += packets;
rx_stats = &nvchan->rx_stats;
do {
start = u64_stats_fetch_begin(&rx_stats->syncp);
packets = rx_stats->packets;
bytes = rx_stats->bytes;
} while (u64_stats_fetch_retry(&rx_stats->syncp, start));
this_tot->rx_bytes += bytes;
this_tot->rx_packets += packets;
}
}
static void netvsc_get_stats64(struct net_device *net,
struct rtnl_link_stats64 *t)
{
struct net_device_context *ndev_ctx = netdev_priv(net);
struct netvsc_device *nvdev;
struct netvsc_vf_pcpu_stats vf_tot;
int i;
rcu_read_lock();
nvdev = rcu_dereference(ndev_ctx->nvdev);
if (!nvdev)
goto out;
netdev_stats_to_stats64(t, &net->stats);
netvsc_get_vf_stats(net, &vf_tot);
t->rx_packets += vf_tot.rx_packets;
t->tx_packets += vf_tot.tx_packets;
t->rx_bytes += vf_tot.rx_bytes;
t->tx_bytes += vf_tot.tx_bytes;
t->tx_dropped += vf_tot.tx_dropped;
for (i = 0; i < nvdev->num_chn; i++) {
const struct netvsc_channel *nvchan = &nvdev->chan_table[i];
const struct netvsc_stats_tx *tx_stats;
const struct netvsc_stats_rx *rx_stats;
u64 packets, bytes, multicast;
unsigned int start;
tx_stats = &nvchan->tx_stats;
do {
start = u64_stats_fetch_begin(&tx_stats->syncp);
packets = tx_stats->packets;
bytes = tx_stats->bytes;
} while (u64_stats_fetch_retry(&tx_stats->syncp, start));
t->tx_bytes += bytes;
t->tx_packets += packets;
rx_stats = &nvchan->rx_stats;
do {
start = u64_stats_fetch_begin(&rx_stats->syncp);
packets = rx_stats->packets;
bytes = rx_stats->bytes;
multicast = rx_stats->multicast + rx_stats->broadcast;
} while (u64_stats_fetch_retry(&rx_stats->syncp, start));
t->rx_bytes += bytes;
t->rx_packets += packets;
t->multicast += multicast;
}
out:
rcu_read_unlock();
}
static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
{
struct net_device_context *ndc = netdev_priv(ndev);
struct net_device *vf_netdev = rtnl_dereference(ndc->vf_netdev);
struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
struct sockaddr_storage *addr = p;
int err;
err = eth_prepare_mac_addr_change(ndev, p);
if (err)
return err;
if (!nvdev)
return -ENODEV;
if (vf_netdev) {
err = dev_set_mac_address(vf_netdev, addr, NULL);
if (err)
return err;
}
err = rndis_filter_set_device_mac(nvdev, addr->__data);
if (!err) {
eth_commit_mac_addr_change(ndev, p);
} else if (vf_netdev) {
memcpy(addr->__data, ndev->dev_addr, ETH_ALEN);
dev_set_mac_address(vf_netdev, addr, NULL);
}
return err;
}
static const struct {
char name[ETH_GSTRING_LEN];
u16 offset;
} netvsc_stats[] = {
{ "tx_scattered", offsetof(struct netvsc_ethtool_stats, tx_scattered) },
{ "tx_no_memory", offsetof(struct netvsc_ethtool_stats, tx_no_memory) },
{ "tx_no_space", offsetof(struct netvsc_ethtool_stats, tx_no_space) },
{ "tx_too_big", offsetof(struct netvsc_ethtool_stats, tx_too_big) },
{ "tx_busy", offsetof(struct netvsc_ethtool_stats, tx_busy) },
{ "tx_send_full", offsetof(struct netvsc_ethtool_stats, tx_send_full) },
{ "rx_comp_busy", offsetof(struct netvsc_ethtool_stats, rx_comp_busy) },
{ "rx_no_memory", offsetof(struct netvsc_ethtool_stats, rx_no_memory) },
{ "stop_queue", offsetof(struct netvsc_ethtool_stats, stop_queue) },
{ "wake_queue", offsetof(struct netvsc_ethtool_stats, wake_queue) },
{ "vlan_error", offsetof(struct netvsc_ethtool_stats, vlan_error) },
}, pcpu_stats[] = {
{ "cpu%u_rx_packets",
offsetof(struct netvsc_ethtool_pcpu_stats, rx_packets) },
{ "cpu%u_rx_bytes",
offsetof(struct netvsc_ethtool_pcpu_stats, rx_bytes) },
{ "cpu%u_tx_packets",
offsetof(struct netvsc_ethtool_pcpu_stats, tx_packets) },
{ "cpu%u_tx_bytes",
offsetof(struct netvsc_ethtool_pcpu_stats, tx_bytes) },
{ "cpu%u_vf_rx_packets",
offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_packets) },
{ "cpu%u_vf_rx_bytes",
offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_bytes) },
{ "cpu%u_vf_tx_packets",
offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_packets) },
{ "cpu%u_vf_tx_bytes",
offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_bytes) },
}, vf_stats[] = {
{ "vf_rx_packets", offsetof(struct netvsc_vf_pcpu_stats, rx_packets) },
{ "vf_rx_bytes", offsetof(struct netvsc_vf_pcpu_stats, rx_bytes) },
{ "vf_tx_packets", offsetof(struct netvsc_vf_pcpu_stats, tx_packets) },
{ "vf_tx_bytes", offsetof(struct netvsc_vf_pcpu_stats, tx_bytes) },
{ "vf_tx_dropped", offsetof(struct netvsc_vf_pcpu_stats, tx_dropped) },
};
#define NETVSC_GLOBAL_STATS_LEN ARRAY_SIZE(netvsc_stats)
#define NETVSC_VF_STATS_LEN ARRAY_SIZE(vf_stats)
#define NETVSC_PCPU_STATS_LEN (num_present_cpus() * ARRAY_SIZE(pcpu_stats))
#define NETVSC_QUEUE_STATS_LEN(dev) ((dev)->num_chn * 8)
static int netvsc_get_sset_count(struct net_device *dev, int string_set)
{
struct net_device_context *ndc = netdev_priv(dev);
struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
if (!nvdev)
return -ENODEV;
switch (string_set) {
case ETH_SS_STATS:
return NETVSC_GLOBAL_STATS_LEN
+ NETVSC_VF_STATS_LEN
+ NETVSC_QUEUE_STATS_LEN(nvdev)
+ NETVSC_PCPU_STATS_LEN;
default:
return -EINVAL;
}
}
static void netvsc_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
struct net_device_context *ndc = netdev_priv(dev);
struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
const void *nds = &ndc->eth_stats;
const struct netvsc_stats_tx *tx_stats;
const struct netvsc_stats_rx *rx_stats;
struct netvsc_vf_pcpu_stats sum;
struct netvsc_ethtool_pcpu_stats *pcpu_sum;
unsigned int start;
u64 packets, bytes;
u64 xdp_drop;
u64 xdp_redirect;
u64 xdp_tx;
u64 xdp_xmit;
int i, j, cpu;
if (!nvdev)
return;
for (i = 0; i < NETVSC_GLOBAL_STATS_LEN; i++)
data[i] = *(unsigned long *)(nds + netvsc_stats[i].offset);
netvsc_get_vf_stats(dev, &sum);
for (j = 0; j < NETVSC_VF_STATS_LEN; j++)
data[i++] = *(u64 *)((void *)&sum + vf_stats[j].offset);
for (j = 0; j < nvdev->num_chn; j++) {
tx_stats = &nvdev->chan_table[j].tx_stats;
do {
start = u64_stats_fetch_begin(&tx_stats->syncp);
packets = tx_stats->packets;
bytes = tx_stats->bytes;
xdp_xmit = tx_stats->xdp_xmit;
} while (u64_stats_fetch_retry(&tx_stats->syncp, start));
data[i++] = packets;
data[i++] = bytes;
data[i++] = xdp_xmit;
rx_stats = &nvdev->chan_table[j].rx_stats;
do {
start = u64_stats_fetch_begin(&rx_stats->syncp);
packets = rx_stats->packets;
bytes = rx_stats->bytes;
xdp_drop = rx_stats->xdp_drop;
xdp_redirect = rx_stats->xdp_redirect;
xdp_tx = rx_stats->xdp_tx;
} while (u64_stats_fetch_retry(&rx_stats->syncp, start));
data[i++] = packets;
data[i++] = bytes;
data[i++] = xdp_drop;
data[i++] = xdp_redirect;
data[i++] = xdp_tx;
}
pcpu_sum = kvmalloc_objs(struct netvsc_ethtool_pcpu_stats, nr_cpu_ids);
if (!pcpu_sum)
return;
netvsc_get_pcpu_stats(dev, pcpu_sum);
for_each_present_cpu(cpu) {
struct netvsc_ethtool_pcpu_stats *this_sum = &pcpu_sum[cpu];
for (j = 0; j < ARRAY_SIZE(pcpu_stats); j++)
data[i++] = *(u64 *)((void *)this_sum
+ pcpu_stats[j].offset);
}
kvfree(pcpu_sum);
}
static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
{
struct net_device_context *ndc = netdev_priv(dev);
struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
u8 *p = data;
int i, cpu;
if (!nvdev)
return;
switch (stringset) {
case ETH_SS_STATS:
for (i = 0; i < ARRAY_SIZE(netvsc_stats); i++)
ethtool_puts(&p, netvsc_stats[i].name);
for (i = 0; i < ARRAY_SIZE(vf_stats); i++)
ethtool_puts(&p, vf_stats[i].name);
for (i = 0; i < nvdev->num_chn; i++) {
ethtool_sprintf(&p, "tx_queue_%u_packets", i);
ethtool_sprintf(&p, "tx_queue_%u_bytes", i);
ethtool_sprintf(&p, "tx_queue_%u_xdp_xmit", i);
ethtool_sprintf(&p, "rx_queue_%u_packets", i);
ethtool_sprintf(&p, "rx_queue_%u_bytes", i);
ethtool_sprintf(&p, "rx_queue_%u_xdp_drop", i);
ethtool_sprintf(&p, "rx_queue_%u_xdp_redirect", i);
ethtool_sprintf(&p, "rx_queue_%u_xdp_tx", i);
}
for_each_present_cpu(cpu) {
for (i = 0; i < ARRAY_SIZE(pcpu_stats); i++)
ethtool_sprintf(&p, pcpu_stats[i].name, cpu);
}
break;
}
}
static int
netvsc_get_rxfh_fields(struct net_device *ndev,
struct ethtool_rxfh_fields *info)
{
struct net_device_context *ndc = netdev_priv(ndev);
const u32 l4_flag = RXH_L4_B_0_1 | RXH_L4_B_2_3;
info->data = RXH_IP_SRC | RXH_IP_DST;
switch (info->flow_type) {
case TCP_V4_FLOW:
if (ndc->l4_hash & HV_TCP4_L4HASH)
info->data |= l4_flag;
break;
case TCP_V6_FLOW:
if (ndc->l4_hash & HV_TCP6_L4HASH)
info->data |= l4_flag;
break;
case UDP_V4_FLOW:
if (ndc->l4_hash & HV_UDP4_L4HASH)
info->data |= l4_flag;
break;
case UDP_V6_FLOW:
if (ndc->l4_hash & HV_UDP6_L4HASH)
info->data |= l4_flag;
break;
case IPV4_FLOW:
case IPV6_FLOW:
break;
default:
info->data = 0;
break;
}
return 0;
}
static u32 netvsc_get_rx_ring_count(struct net_device *dev)
{
struct net_device_context *ndc = netdev_priv(dev);
struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
if (!nvdev)
return 0;
return nvdev->num_chn;
}
static int
netvsc_set_rxfh_fields(struct net_device *dev,
const struct ethtool_rxfh_fields *info,
struct netlink_ext_ack *extack)
{
struct net_device_context *ndc = netdev_priv(dev);
if (info->data == (RXH_IP_SRC | RXH_IP_DST |
RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
switch (info->flow_type) {
case TCP_V4_FLOW:
ndc->l4_hash |= HV_TCP4_L4HASH;
break;
case TCP_V6_FLOW:
ndc->l4_hash |= HV_TCP6_L4HASH;
break;
case UDP_V4_FLOW:
ndc->l4_hash |= HV_UDP4_L4HASH;
break;
case UDP_V6_FLOW:
ndc->l4_hash |= HV_UDP6_L4HASH;
break;
default:
return -EOPNOTSUPP;
}
return 0;
}
if (info->data == (RXH_IP_SRC | RXH_IP_DST)) {
switch (info->flow_type) {
case TCP_V4_FLOW:
ndc->l4_hash &= ~HV_TCP4_L4HASH;
break;
case TCP_V6_FLOW:
ndc->l4_hash &= ~HV_TCP6_L4HASH;
break;
case UDP_V4_FLOW:
ndc->l4_hash &= ~HV_UDP4_L4HASH;
break;
case UDP_V6_FLOW:
ndc->l4_hash &= ~HV_UDP6_L4HASH;
break;
default:
return -EOPNOTSUPP;
}
return 0;
}
return -EOPNOTSUPP;
}
static u32 netvsc_get_rxfh_key_size(struct net_device *dev)
{
return NETVSC_HASH_KEYLEN;
}
static u32 netvsc_rss_indir_size(struct net_device *dev)
{
struct net_device_context *ndc = netdev_priv(dev);
return ndc->rx_table_sz;
}
static int netvsc_get_rxfh(struct net_device *dev,
struct ethtool_rxfh_param *rxfh)
{
struct net_device_context *ndc = netdev_priv(dev);
struct netvsc_device *ndev = rtnl_dereference(ndc->nvdev);
struct rndis_device *rndis_dev;
int i;
if (!ndev)
return -ENODEV;
rxfh->hfunc = ETH_RSS_HASH_TOP;
rndis_dev = ndev->extension;
if (rxfh->indir) {
for (i = 0; i < ndc->rx_table_sz; i++)
rxfh->indir[i] = ndc->rx_table[i];
}
if (rxfh->key)
memcpy(rxfh->key, rndis_dev->rss_key, NETVSC_HASH_KEYLEN);
return 0;
}
static int netvsc_set_rxfh(struct net_device *dev,
struct ethtool_rxfh_param *rxfh,
struct netlink_ext_ack *extack)
{
struct net_device_context *ndc = netdev_priv(dev);
struct netvsc_device *ndev = rtnl_dereference(ndc->nvdev);
struct rndis_device *rndis_dev;
u8 *key = rxfh->key;
int i;
if (!ndev)
return -ENODEV;
if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
rxfh->hfunc != ETH_RSS_HASH_TOP)
return -EOPNOTSUPP;
if (!ndc->rx_table_sz)
return -EOPNOTSUPP;
rndis_dev = ndev->extension;
if (rxfh->indir) {
for (i = 0; i < ndc->rx_table_sz; i++)
if (rxfh->indir[i] >= ndev->num_chn)
return -EINVAL;
for (i = 0; i < ndc->rx_table_sz; i++)
ndc->rx_table[i] = rxfh->indir[i];
}
if (!key) {
if (!rxfh->indir)
return 0;
key = rndis_dev->rss_key;
}
return rndis_filter_set_rss_param(rndis_dev, key);
}
static void __netvsc_get_ringparam(struct netvsc_device *nvdev,
struct ethtool_ringparam *ring)
{
u32 max_buf_size;
ring->rx_pending = nvdev->recv_section_cnt;
ring->tx_pending = nvdev->send_section_cnt;
if (nvdev->nvsp_version <= NVSP_PROTOCOL_VERSION_2)
max_buf_size = NETVSC_RECEIVE_BUFFER_SIZE_LEGACY;
else
max_buf_size = NETVSC_RECEIVE_BUFFER_SIZE;
ring->rx_max_pending = max_buf_size / nvdev->recv_section_size;
ring->tx_max_pending = NETVSC_SEND_BUFFER_SIZE
/ nvdev->send_section_size;
}
static void netvsc_get_ringparam(struct net_device *ndev,
struct ethtool_ringparam *ring,
struct kernel_ethtool_ringparam *kernel_ring,
struct netlink_ext_ack *extack)
{
struct net_device_context *ndevctx = netdev_priv(ndev);
struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
if (!nvdev)
return;
__netvsc_get_ringparam(nvdev, ring);
}
static int netvsc_set_ringparam(struct net_device *ndev,
struct ethtool_ringparam *ring,
struct kernel_ethtool_ringparam *kernel_ring,
struct netlink_ext_ack *extack)
{
struct net_device_context *ndevctx = netdev_priv(ndev);
struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
struct netvsc_device_info *device_info;
struct ethtool_ringparam orig;
u32 new_tx, new_rx;
int ret = 0;
if (!nvdev || nvdev->destroy)
return -ENODEV;
memset(&orig, 0, sizeof(orig));
__netvsc_get_ringparam(nvdev, &orig);
new_tx = clamp_t(u32, ring->tx_pending,
NETVSC_MIN_TX_SECTIONS, orig.tx_max_pending);
new_rx = clamp_t(u32, ring->rx_pending,
NETVSC_MIN_RX_SECTIONS, orig.rx_max_pending);
if (new_tx == orig.tx_pending &&
new_rx == orig.rx_pending)
return 0;
device_info = netvsc_devinfo_get(nvdev);
if (!device_info)
return -ENOMEM;
device_info->send_sections = new_tx;
device_info->recv_sections = new_rx;
ret = netvsc_detach(ndev, nvdev);
if (ret)
goto out;
ret = netvsc_attach(ndev, device_info);
if (ret) {
device_info->send_sections = orig.tx_pending;
device_info->recv_sections = orig.rx_pending;
if (netvsc_attach(ndev, device_info))
netdev_err(ndev, "restoring ringparam failed");
}
out:
netvsc_devinfo_put(device_info);
return ret;
}
static netdev_features_t netvsc_fix_features(struct net_device *ndev,
netdev_features_t features)
{
struct net_device_context *ndevctx = netdev_priv(ndev);
struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
if (!nvdev || nvdev->destroy)
return features;
if ((features & NETIF_F_LRO) && netvsc_xdp_get(nvdev)) {
features ^= NETIF_F_LRO;
netdev_info(ndev, "Skip LRO - unsupported with XDP\n");
}
return features;
}
static int netvsc_set_features(struct net_device *ndev,
netdev_features_t features)
{
netdev_features_t change = features ^ ndev->features;
struct net_device_context *ndevctx = netdev_priv(ndev);
struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
struct net_device *vf_netdev = rtnl_dereference(ndevctx->vf_netdev);
struct ndis_offload_params offloads;
int ret = 0;
if (!nvdev || nvdev->destroy)
return -ENODEV;
if (!(change & NETIF_F_LRO))
goto syncvf;
memset(&offloads, 0, sizeof(struct ndis_offload_params));
if (features & NETIF_F_LRO) {
offloads.rsc_ip_v4 = NDIS_OFFLOAD_PARAMETERS_RSC_ENABLED;
offloads.rsc_ip_v6 = NDIS_OFFLOAD_PARAMETERS_RSC_ENABLED;
} else {
offloads.rsc_ip_v4 = NDIS_OFFLOAD_PARAMETERS_RSC_DISABLED;
offloads.rsc_ip_v6 = NDIS_OFFLOAD_PARAMETERS_RSC_DISABLED;
}
ret = rndis_filter_set_offload_params(ndev, nvdev, &offloads);
if (ret) {
features ^= NETIF_F_LRO;
ndev->features = features;
}
syncvf:
if (!vf_netdev)
return ret;
vf_netdev->wanted_features = features;
netdev_update_features(vf_netdev);
return ret;
}
static int netvsc_get_regs_len(struct net_device *netdev)
{
return VRSS_SEND_TAB_SIZE * sizeof(u32);
}
static void netvsc_get_regs(struct net_device *netdev,
struct ethtool_regs *regs, void *p)
{
struct net_device_context *ndc = netdev_priv(netdev);
u32 *regs_buff = p;
regs->version = 1;
memcpy(regs_buff, ndc->tx_table, VRSS_SEND_TAB_SIZE * sizeof(u32));
}
static u32 netvsc_get_msglevel(struct net_device *ndev)
{
struct net_device_context *ndev_ctx = netdev_priv(ndev);
return ndev_ctx->msg_enable;
}
static void netvsc_set_msglevel(struct net_device *ndev, u32 val)
{
struct net_device_context *ndev_ctx = netdev_priv(ndev);
ndev_ctx->msg_enable = val;
}
static const struct ethtool_ops ethtool_ops = {
.get_drvinfo = netvsc_get_drvinfo,
.get_regs_len = netvsc_get_regs_len,
.get_regs = netvsc_get_regs,
.get_msglevel = netvsc_get_msglevel,
.set_msglevel = netvsc_set_msglevel,
.get_link = ethtool_op_get_link,
.get_ethtool_stats = netvsc_get_ethtool_stats,
.get_sset_count = netvsc_get_sset_count,
.get_strings = netvsc_get_strings,
.get_channels = netvsc_get_channels,
.set_channels = netvsc_set_channels,
.get_ts_info = ethtool_op_get_ts_info,
.get_rx_ring_count = netvsc_get_rx_ring_count,
.get_rxfh_key_size = netvsc_get_rxfh_key_size,
.get_rxfh_indir_size = netvsc_rss_indir_size,
.get_rxfh = netvsc_get_rxfh,
.set_rxfh = netvsc_set_rxfh,
.get_rxfh_fields = netvsc_get_rxfh_fields,
.set_rxfh_fields = netvsc_set_rxfh_fields,
.get_link_ksettings = netvsc_get_link_ksettings,
.set_link_ksettings = netvsc_set_link_ksettings,
.get_ringparam = netvsc_get_ringparam,
.set_ringparam = netvsc_set_ringparam,
};
static const struct net_device_ops device_ops = {
.ndo_open = netvsc_open,
.ndo_stop = netvsc_close,
.ndo_start_xmit = netvsc_start_xmit,
.ndo_change_rx_flags = netvsc_change_rx_flags,
.ndo_set_rx_mode = netvsc_set_rx_mode,
.ndo_fix_features = netvsc_fix_features,
.ndo_set_features = netvsc_set_features,
.ndo_change_mtu = netvsc_change_mtu,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = netvsc_set_mac_addr,
.ndo_select_queue = netvsc_select_queue,
.ndo_get_stats64 = netvsc_get_stats64,
.ndo_bpf = netvsc_bpf,
.ndo_xdp_xmit = netvsc_ndoxdp_xmit,
};
static void netvsc_link_change(struct work_struct *w)
{
struct net_device_context *ndev_ctx =
container_of(w, struct net_device_context, dwork.work);
struct hv_device *device_obj = ndev_ctx->device_ctx;
struct net_device *net = hv_get_drvdata(device_obj);
unsigned long flags, next_reconfig, delay;
struct netvsc_reconfig *event = NULL;
struct netvsc_device *net_device;
struct rndis_device *rdev;
bool reschedule = false;
if (!rtnl_trylock()) {
schedule_delayed_work(&ndev_ctx->dwork, LINKCHANGE_INT);
return;
}
net_device = rtnl_dereference(ndev_ctx->nvdev);
if (!net_device)
goto out_unlock;
rdev = net_device->extension;
next_reconfig = ndev_ctx->last_reconfig + LINKCHANGE_INT;
if (time_is_after_jiffies(next_reconfig)) {
delay = next_reconfig - jiffies;
delay = delay < LINKCHANGE_INT ? delay : LINKCHANGE_INT;
schedule_delayed_work(&ndev_ctx->dwork, delay);
goto out_unlock;
}
ndev_ctx->last_reconfig = jiffies;
spin_lock_irqsave(&ndev_ctx->lock, flags);
if (!list_empty(&ndev_ctx->reconfig_events)) {
event = list_first_entry(&ndev_ctx->reconfig_events,
struct netvsc_reconfig, list);
list_del(&event->list);
reschedule = !list_empty(&ndev_ctx->reconfig_events);
}
spin_unlock_irqrestore(&ndev_ctx->lock, flags);
if (!event)
goto out_unlock;
switch (event->event) {
case RNDIS_STATUS_MEDIA_CONNECT:
if (rdev->link_state) {
rdev->link_state = false;
netif_carrier_on(net);
netvsc_tx_enable(net_device, net);
} else {
__netdev_notify_peers(net);
}
kfree(event);
break;
case RNDIS_STATUS_MEDIA_DISCONNECT:
if (!rdev->link_state) {
rdev->link_state = true;
netif_carrier_off(net);
netvsc_tx_disable(net_device, net);
}
kfree(event);
break;
case RNDIS_STATUS_NETWORK_CHANGE:
if (!rdev->link_state) {
rdev->link_state = true;
netif_carrier_off(net);
netvsc_tx_disable(net_device, net);
event->event = RNDIS_STATUS_MEDIA_CONNECT;
spin_lock_irqsave(&ndev_ctx->lock, flags);
list_add(&event->list, &ndev_ctx->reconfig_events);
spin_unlock_irqrestore(&ndev_ctx->lock, flags);
reschedule = true;
}
break;
}
rtnl_unlock();
if (reschedule)
schedule_delayed_work(&ndev_ctx->dwork, LINKCHANGE_INT);
return;
out_unlock:
rtnl_unlock();
}
static struct net_device *get_netvsc_byref(struct net_device *vf_netdev)
{
struct net_device_context *net_device_ctx;
struct net_device *dev;
dev = netdev_master_upper_dev_get(vf_netdev);
if (!dev || dev->netdev_ops != &device_ops)
return NULL;
net_device_ctx = netdev_priv(dev);
if (!rtnl_dereference(net_device_ctx->nvdev))
return NULL;
return dev;
}
static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb)
{
struct sk_buff *skb = *pskb;
struct net_device *ndev = rcu_dereference(skb->dev->rx_handler_data);
struct net_device_context *ndev_ctx = netdev_priv(ndev);
struct netvsc_vf_pcpu_stats *pcpu_stats
= this_cpu_ptr(ndev_ctx->vf_stats);
skb = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(!skb))
return RX_HANDLER_CONSUMED;
*pskb = skb;
skb->dev = ndev;
u64_stats_update_begin(&pcpu_stats->syncp);
pcpu_stats->rx_packets++;
pcpu_stats->rx_bytes += skb->len;
u64_stats_update_end(&pcpu_stats->syncp);
return RX_HANDLER_ANOTHER;
}
static int netvsc_vf_join(struct net_device *vf_netdev,
struct net_device *ndev, int context)
{
struct net_device_context *ndev_ctx = netdev_priv(ndev);
int ret;
ret = netdev_rx_handler_register(vf_netdev,
netvsc_vf_handle_frame, ndev);
if (ret != 0) {
netdev_err(vf_netdev,
"can not register netvsc VF receive handler (err = %d)\n",
ret);
goto rx_handler_failed;
}
ret = netdev_master_upper_dev_link(vf_netdev, ndev,
NULL, NULL, NULL);
if (ret != 0) {
netdev_err(vf_netdev,
"can not set master device %s (err = %d)\n",
ndev->name, ret);
goto upper_link_failed;
}
if (context == VF_REG_IN_NOTIFIER)
schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
netdev_info(vf_netdev, "joined to %s\n", ndev->name);
return 0;
upper_link_failed:
netdev_rx_handler_unregister(vf_netdev);
rx_handler_failed:
return ret;
}
static void __netvsc_vf_setup(struct net_device *ndev,
struct net_device *vf_netdev)
{
int ret;
ret = dev_set_mtu(vf_netdev, ndev->mtu);
if (ret)
netdev_warn(vf_netdev,
"unable to change mtu to %u\n", ndev->mtu);
dev_change_flags(vf_netdev, ndev->flags | IFF_SLAVE, NULL);
netif_addr_lock_bh(ndev);
dev_uc_sync(vf_netdev, ndev);
dev_mc_sync(vf_netdev, ndev);
netif_addr_unlock_bh(ndev);
if (netif_running(ndev)) {
ret = dev_open(vf_netdev, NULL);
if (ret)
netdev_warn(vf_netdev,
"unable to open: %d\n", ret);
}
}
static void netvsc_vf_setup(struct work_struct *w)
{
struct net_device_context *ndev_ctx
= container_of(w, struct net_device_context, vf_takeover.work);
struct net_device *ndev = hv_get_drvdata(ndev_ctx->device_ctx);
struct net_device *vf_netdev;
if (!rtnl_trylock()) {
schedule_delayed_work(&ndev_ctx->vf_takeover, 0);
return;
}
vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
if (vf_netdev)
__netvsc_vf_setup(ndev, vf_netdev);
rtnl_unlock();
}
static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev)
{
struct device *parent = vf_netdev->dev.parent;
struct net_device_context *ndev_ctx;
struct net_device *ndev;
struct pci_dev *pdev;
u32 serial;
if (!parent || !dev_is_pci(parent))
return NULL;
pdev = to_pci_dev(parent);
if (!pdev->slot) {
netdev_notice(vf_netdev, "no PCI slot information\n");
return NULL;
}
if (kstrtou32(pci_slot_name(pdev->slot), 10, &serial)) {
netdev_notice(vf_netdev, "Invalid vf serial:%s\n",
pci_slot_name(pdev->slot));
return NULL;
}
list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
if (!ndev_ctx->vf_alloc)
continue;
if (ndev_ctx->vf_serial != serial)
continue;
ndev = hv_get_drvdata(ndev_ctx->device_ctx);
if (ndev->addr_len != vf_netdev->addr_len ||
memcmp(ndev->perm_addr, vf_netdev->perm_addr,
ndev->addr_len) != 0)
continue;
return ndev;
}
list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
ndev = hv_get_drvdata(ndev_ctx->device_ctx);
if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr) ||
ether_addr_equal(vf_netdev->dev_addr, ndev->perm_addr))
return ndev;
}
netdev_notice(vf_netdev,
"no netdev found for vf serial:%u\n", serial);
return NULL;
}
static int netvsc_prepare_bonding(struct net_device *vf_netdev)
{
struct net_device *ndev;
ndev = get_netvsc_byslot(vf_netdev);
if (!ndev)
return NOTIFY_DONE;
vf_netdev->flags |= IFF_SLAVE;
vf_netdev->priv_flags |= IFF_NO_ADDRCONF;
return NOTIFY_DONE;
}
static int netvsc_register_vf(struct net_device *vf_netdev, int context)
{
struct net_device_context *net_device_ctx;
struct netvsc_device *netvsc_dev;
struct bpf_prog *prog;
struct net_device *ndev;
int ret;
if (vf_netdev->addr_len != ETH_ALEN)
return NOTIFY_DONE;
ndev = get_netvsc_byslot(vf_netdev);
if (!ndev)
return NOTIFY_DONE;
net_device_ctx = netdev_priv(ndev);
netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
return NOTIFY_DONE;
if (!net_eq(dev_net(ndev), dev_net(vf_netdev))) {
ret = dev_change_net_namespace(vf_netdev,
dev_net(ndev), "eth%d");
if (ret)
netdev_err(vf_netdev,
"could not move to same namespace as %s: %d\n",
ndev->name, ret);
else
netdev_info(vf_netdev,
"VF moved to namespace with: %s\n",
ndev->name);
return NOTIFY_DONE;
}
netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
if (netvsc_vf_join(vf_netdev, ndev, context) != 0)
return NOTIFY_DONE;
dev_hold(vf_netdev);
rcu_assign_pointer(net_device_ctx->vf_netdev, vf_netdev);
if (ndev->needed_headroom < vf_netdev->needed_headroom)
ndev->needed_headroom = vf_netdev->needed_headroom;
vf_netdev->wanted_features = ndev->features;
netdev_update_features(vf_netdev);
prog = netvsc_xdp_get(netvsc_dev);
netvsc_vf_setxdp(vf_netdev, prog);
return NOTIFY_OK;
}
static int netvsc_vf_changed(struct net_device *vf_netdev, unsigned long event)
{
struct net_device_context *net_device_ctx;
struct netvsc_device *netvsc_dev;
struct net_device *ndev;
bool vf_is_up = false;
int ret;
if (event != NETDEV_GOING_DOWN)
vf_is_up = netif_running(vf_netdev);
ndev = get_netvsc_byref(vf_netdev);
if (!ndev)
return NOTIFY_DONE;
net_device_ctx = netdev_priv(ndev);
netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
if (!netvsc_dev)
return NOTIFY_DONE;
if (net_device_ctx->data_path_is_vf == vf_is_up)
return NOTIFY_OK;
if (vf_is_up && !net_device_ctx->vf_alloc) {
netdev_info(ndev, "Waiting for the VF association from host\n");
wait_for_completion(&net_device_ctx->vf_add);
}
ret = netvsc_switch_datapath(ndev, vf_is_up);
if (ret) {
netdev_err(ndev,
"Data path failed to switch %s VF: %s, err: %d\n",
vf_is_up ? "to" : "from", vf_netdev->name, ret);
return NOTIFY_DONE;
} else {
netdev_info(ndev, "Data path switched %s VF: %s\n",
vf_is_up ? "to" : "from", vf_netdev->name);
if (vf_is_up)
netif_set_tso_max_size(ndev, vf_netdev->tso_max_size);
else
netif_set_tso_max_size(ndev, netvsc_dev->netvsc_gso_max_size);
}
return NOTIFY_OK;
}
static int netvsc_unregister_vf(struct net_device *vf_netdev)
{
struct net_device *ndev;
struct net_device_context *net_device_ctx;
ndev = get_netvsc_byref(vf_netdev);
if (!ndev)
return NOTIFY_DONE;
net_device_ctx = netdev_priv(ndev);
cancel_delayed_work_sync(&net_device_ctx->vf_takeover);
netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);
reinit_completion(&net_device_ctx->vf_add);
netdev_rx_handler_unregister(vf_netdev);
netdev_upper_dev_unlink(vf_netdev, ndev);
RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL);
dev_put(vf_netdev);
ndev->needed_headroom = RNDIS_AND_PPI_SIZE;
return NOTIFY_OK;
}
static int check_dev_is_matching_vf(struct net_device *event_ndev)
{
if (event_ndev->netdev_ops == &device_ops)
return -ENODEV;
if (event_ndev->type != ARPHRD_ETHER)
return -ENODEV;
if (is_vlan_dev(event_ndev))
return -ENODEV;
if (netif_is_bond_master(event_ndev))
return -ENODEV;
return 0;
}
static int netvsc_probe(struct hv_device *dev,
const struct hv_vmbus_device_id *dev_id)
{
struct net_device *net = NULL, *vf_netdev;
struct net_device_context *net_device_ctx;
struct netvsc_device_info *device_info = NULL;
struct netvsc_device *nvdev;
int ret = -ENOMEM;
net = alloc_etherdev_mq(sizeof(struct net_device_context),
VRSS_CHANNEL_MAX);
if (!net)
goto no_net;
netif_carrier_off(net);
netvsc_init_settings(net);
net_device_ctx = netdev_priv(net);
net_device_ctx->device_ctx = dev;
net_device_ctx->msg_enable = netif_msg_init(debug, default_msg);
if (netif_msg_probe(net_device_ctx))
netdev_dbg(net, "netvsc msg_enable: %d\n",
net_device_ctx->msg_enable);
hv_set_drvdata(dev, net);
INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
init_completion(&net_device_ctx->vf_add);
spin_lock_init(&net_device_ctx->lock);
INIT_LIST_HEAD(&net_device_ctx->reconfig_events);
INIT_DELAYED_WORK(&net_device_ctx->vf_takeover, netvsc_vf_setup);
INIT_DELAYED_WORK(&net_device_ctx->vfns_work, netvsc_vfns_work);
net_device_ctx->vf_stats
= netdev_alloc_pcpu_stats(struct netvsc_vf_pcpu_stats);
if (!net_device_ctx->vf_stats)
goto no_stats;
net->netdev_ops = &device_ops;
net->ethtool_ops = ðtool_ops;
SET_NETDEV_DEV(net, &dev->device);
dma_set_min_align_mask(&dev->device, HV_HYP_PAGE_SIZE - 1);
net->needed_headroom = RNDIS_AND_PPI_SIZE;
netif_set_real_num_tx_queues(net, 1);
netif_set_real_num_rx_queues(net, 1);
device_info = netvsc_devinfo_get(NULL);
if (!device_info) {
ret = -ENOMEM;
goto devinfo_failed;
}
rtnl_lock();
nvdev = rndis_filter_device_add(dev, device_info);
if (IS_ERR(nvdev)) {
ret = PTR_ERR(nvdev);
netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
goto rndis_failed;
}
eth_hw_addr_set(net, device_info->mac_adr);
if (nvdev->num_chn > 1)
schedule_work(&nvdev->subchan_work);
net->features = net->hw_features |
NETIF_F_HIGHDMA | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_CTAG_RX;
net->vlan_features = net->features;
netdev_lockdep_set_classes(net);
net->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
NETDEV_XDP_ACT_NDO_XMIT;
net->min_mtu = NETVSC_MTU_MIN;
if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)
net->max_mtu = NETVSC_MTU - ETH_HLEN;
else
net->max_mtu = ETH_DATA_LEN;
nvdev->tx_disable = false;
ret = register_netdevice(net);
if (ret != 0) {
pr_err("Unable to register netdev.\n");
goto register_failed;
}
list_add(&net_device_ctx->list, &netvsc_dev_list);
for_each_netdev(dev_net(net), vf_netdev) {
ret = check_dev_is_matching_vf(vf_netdev);
if (ret != 0)
continue;
if (net != get_netvsc_byslot(vf_netdev))
continue;
netvsc_prepare_bonding(vf_netdev);
netdev_lock_ops(vf_netdev);
netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE);
netdev_unlock_ops(vf_netdev);
__netvsc_vf_setup(net, vf_netdev);
break;
}
rtnl_unlock();
netvsc_devinfo_put(device_info);
return 0;
register_failed:
rndis_filter_device_remove(dev, nvdev);
rndis_failed:
rtnl_unlock();
netvsc_devinfo_put(device_info);
devinfo_failed:
free_percpu(net_device_ctx->vf_stats);
no_stats:
hv_set_drvdata(dev, NULL);
free_netdev(net);
no_net:
return ret;
}
static void netvsc_remove(struct hv_device *dev)
{
struct net_device_context *ndev_ctx;
struct net_device *vf_netdev, *net;
struct netvsc_device *nvdev;
net = hv_get_drvdata(dev);
if (net == NULL) {
dev_err(&dev->device, "No net device to remove\n");
return;
}
ndev_ctx = netdev_priv(net);
cancel_delayed_work_sync(&ndev_ctx->dwork);
rtnl_lock();
cancel_delayed_work_sync(&ndev_ctx->vfns_work);
nvdev = rtnl_dereference(ndev_ctx->nvdev);
if (nvdev) {
cancel_work_sync(&nvdev->subchan_work);
netvsc_xdp_set(net, NULL, NULL, nvdev);
}
vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
if (vf_netdev)
netvsc_unregister_vf(vf_netdev);
if (nvdev)
rndis_filter_device_remove(dev, nvdev);
unregister_netdevice(net);
list_del(&ndev_ctx->list);
rtnl_unlock();
hv_set_drvdata(dev, NULL);
free_percpu(ndev_ctx->vf_stats);
free_netdev(net);
}
static int netvsc_suspend(struct hv_device *dev)
{
struct net_device_context *ndev_ctx;
struct netvsc_device *nvdev;
struct net_device *net;
int ret;
net = hv_get_drvdata(dev);
ndev_ctx = netdev_priv(net);
cancel_delayed_work_sync(&ndev_ctx->dwork);
rtnl_lock();
cancel_delayed_work_sync(&ndev_ctx->vfns_work);
nvdev = rtnl_dereference(ndev_ctx->nvdev);
if (nvdev == NULL) {
ret = -ENODEV;
goto out;
}
ndev_ctx->saved_netvsc_dev_info = netvsc_devinfo_get(nvdev);
if (!ndev_ctx->saved_netvsc_dev_info) {
ret = -ENOMEM;
goto out;
}
ret = netvsc_detach(net, nvdev);
out:
rtnl_unlock();
return ret;
}
static int netvsc_resume(struct hv_device *dev)
{
struct net_device *net = hv_get_drvdata(dev);
struct net_device_context *net_device_ctx;
struct netvsc_device_info *device_info;
int ret;
rtnl_lock();
net_device_ctx = netdev_priv(net);
net_device_ctx->data_path_is_vf = false;
device_info = net_device_ctx->saved_netvsc_dev_info;
ret = netvsc_attach(net, device_info);
netvsc_devinfo_put(device_info);
net_device_ctx->saved_netvsc_dev_info = NULL;
rtnl_unlock();
return ret;
}
static const struct hv_vmbus_device_id id_table[] = {
{ HV_NIC_GUID, },
{ },
};
MODULE_DEVICE_TABLE(vmbus, id_table);
static struct hv_driver netvsc_drv = {
.name = KBUILD_MODNAME,
.id_table = id_table,
.probe = netvsc_probe,
.remove = netvsc_remove,
.suspend = netvsc_suspend,
.resume = netvsc_resume,
.driver = {
.probe_type = PROBE_FORCE_SYNCHRONOUS,
},
};
static void netvsc_event_set_vf_ns(struct net_device *ndev)
{
struct net_device_context *ndev_ctx = netdev_priv(ndev);
struct net_device *vf_netdev;
int ret;
vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
if (!vf_netdev)
return;
if (!net_eq(dev_net(ndev), dev_net(vf_netdev))) {
ret = dev_change_net_namespace(vf_netdev, dev_net(ndev),
"eth%d");
if (ret)
netdev_err(vf_netdev,
"Cannot move to same namespace as %s: %d\n",
ndev->name, ret);
else
netdev_info(vf_netdev,
"Moved VF to namespace with: %s\n",
ndev->name);
}
}
void netvsc_vfns_work(struct work_struct *w)
{
struct net_device_context *ndev_ctx =
container_of(w, struct net_device_context, vfns_work.work);
struct net_device *ndev;
if (!rtnl_trylock()) {
schedule_delayed_work(&ndev_ctx->vfns_work, 1);
return;
}
ndev = hv_get_drvdata(ndev_ctx->device_ctx);
if (!ndev)
goto out;
netvsc_event_set_vf_ns(ndev);
out:
rtnl_unlock();
}
static int netvsc_netdev_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
struct net_device_context *ndev_ctx;
int ret = 0;
if (event_dev->netdev_ops == &device_ops && event == NETDEV_REGISTER) {
ndev_ctx = netdev_priv(event_dev);
schedule_delayed_work(&ndev_ctx->vfns_work, 0);
return NOTIFY_DONE;
}
ret = check_dev_is_matching_vf(event_dev);
if (ret != 0)
return NOTIFY_DONE;
switch (event) {
case NETDEV_POST_INIT:
return netvsc_prepare_bonding(event_dev);
case NETDEV_REGISTER:
return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER);
case NETDEV_UNREGISTER:
return netvsc_unregister_vf(event_dev);
case NETDEV_UP:
case NETDEV_DOWN:
case NETDEV_CHANGE:
case NETDEV_GOING_DOWN:
return netvsc_vf_changed(event_dev, event);
default:
return NOTIFY_DONE;
}
}
static struct notifier_block netvsc_netdev_notifier = {
.notifier_call = netvsc_netdev_event,
};
static void __exit netvsc_drv_exit(void)
{
unregister_netdevice_notifier(&netvsc_netdev_notifier);
vmbus_driver_unregister(&netvsc_drv);
}
static int __init netvsc_drv_init(void)
{
int ret;
if (ring_size < RING_SIZE_MIN) {
ring_size = RING_SIZE_MIN;
pr_info("Increased ring_size to %u (min allowed)\n",
ring_size);
}
netvsc_ring_bytes = VMBUS_RING_SIZE(ring_size * 4096);
register_netdevice_notifier(&netvsc_netdev_notifier);
ret = vmbus_driver_register(&netvsc_drv);
if (ret)
goto err_vmbus_reg;
return 0;
err_vmbus_reg:
unregister_netdevice_notifier(&netvsc_netdev_notifier);
return ret;
}
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Microsoft Hyper-V network driver");
module_init(netvsc_drv_init);
module_exit(netvsc_drv_exit);
