static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb,
void *accel_priv,
select_queue_fallback_t fallback)
{
struct xenvif *vif = netdev_priv(dev);
unsigned int size = vif->hash.size;
if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE) {
u16 index = fallback(dev, skb) % dev->real_num_tx_queues;
/* Make sure there is no hash information in the socket
* buffer otherwise it would be incorrectly forwarded
* to the frontend.
*/
skb_clear_hash(skb);
return index;
}
xenvif_set_skb_hash(vif, skb);
if (size == 0)
return skb_get_hash_raw(skb) % dev->real_num_tx_queues;
return vif->hash.mapping[skb_get_hash_raw(skb) % size];
}
static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb,
void *accel_priv,
select_queue_fallback_t fallback)
{
struct xenvif *vif = netdev_priv(dev);
unsigned int size = vif->hash.size;
if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
return fallback(dev, skb) % dev->real_num_tx_queues;
xenvif_set_skb_hash(vif, skb);
if (size == 0)
return skb_get_hash_raw(skb) % dev->real_num_tx_queues;
return vif->hash.mapping[skb_get_hash_raw(skb) % size];
}
static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
{
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 rndis_packet *rndis_pkt;
u32 rndis_msg_size;
struct rndis_per_packet_info *ppi;
struct ndis_tcp_ip_checksum_info *csum_info;
int hdr_offset;
u32 net_trans_info;
u32 hash;
u32 skb_length;
struct hv_page_buffer page_buf[MAX_PAGE_BUFFER_COUNT];
struct hv_page_buffer *pb = page_buf;
/* We will atmost need two pages to describe the rndis
* header. We can only transmit MAX_PAGE_BUFFER_COUNT number
* of pages in a single packet. If skb is scattered around
* more pages we try linearizing it.
*/
skb_length = skb->len;
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;
}
}
/*
* Place the rndis header in the skb head room and
* the skb->cb will be used for hv_netvsc_packet
* structure.
*/
ret = skb_cow_head(skb, RNDIS_AND_PPI_SIZE);
if (ret)
goto no_memory;
/* Use the skb control buffer for building up the packet */
BUILD_BUG_ON(sizeof(struct hv_netvsc_packet) >
FIELD_SIZEOF(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;
rndis_msg = (struct rndis_message *)skb->head;
memset(rndis_msg, 0, RNDIS_AND_PPI_SIZE);
/* Add the rndis header */
rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET;
rndis_msg->msg_len = packet->total_data_buflen;
rndis_pkt = &rndis_msg->msg.pkt;
rndis_pkt->data_offset = sizeof(struct rndis_packet);
rndis_pkt->data_len = packet->total_data_buflen;
rndis_pkt->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) {
rndis_msg_size += NDIS_HASH_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_HASH_PPI_SIZE,
NBL_HASH_VALUE);
*(u32 *)((void *)ppi + ppi->ppi_offset) = hash;
}
if (skb_vlan_tag_present(skb)) {
struct ndis_pkt_8021q_info *vlan;
rndis_msg_size += NDIS_VLAN_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_VLAN_PPI_SIZE,
IEEE_8021Q_INFO);
vlan = (struct ndis_pkt_8021q_info *)((void *)ppi +
ppi->ppi_offset);
vlan->vlanid = skb->vlan_tci & VLAN_VID_MASK;
vlan->pri = (skb->vlan_tci & VLAN_PRIO_MASK) >>
VLAN_PRIO_SHIFT;
}
net_trans_info = get_net_transport_info(skb, &hdr_offset);
/*
* Setup the sendside checksum offload only if this is not a
* GSO packet.
*/
if ((net_trans_info & (INFO_TCP | INFO_UDP)) && skb_is_gso(skb)) {
struct ndis_tcp_lso_info *lso_info;
rndis_msg_size += NDIS_LSO_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_LSO_PPI_SIZE,
TCP_LARGESEND_PKTINFO);
lso_info = (struct ndis_tcp_lso_info *)((void *)ppi +
ppi->ppi_offset);
lso_info->lso_v2_transmit.type = NDIS_TCP_LARGE_SEND_OFFLOAD_V2_TYPE;
if (net_trans_info & (INFO_IPV4 << 16)) {
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;
ipv6_hdr(skb)->payload_len = 0;
tcp_hdr(skb)->check =
~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0);
}
lso_info->lso_v2_transmit.tcp_header_offset = hdr_offset;
lso_info->lso_v2_transmit.mss = skb_shinfo(skb)->gso_size;
} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
if (net_trans_info & INFO_TCP) {
rndis_msg_size += NDIS_CSUM_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_CSUM_PPI_SIZE,
TCPIP_CHKSUM_PKTINFO);
csum_info = (struct ndis_tcp_ip_checksum_info *)((void *)ppi +
ppi->ppi_offset);
if (net_trans_info & (INFO_IPV4 << 16))
csum_info->transmit.is_ipv4 = 1;
else
csum_info->transmit.is_ipv6 = 1;
csum_info->transmit.tcp_checksum = 1;
csum_info->transmit.tcp_header_offset = hdr_offset;
} else {
/* UDP checksum (and other) offload is not supported. */
if (skb_checksum_help(skb))
goto drop;
}
}
/* Start filling in the page buffers with the rndis hdr */
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);
/* timestamp packet in software */
skb_tx_timestamp(skb);
ret = netvsc_send(net_device_ctx->device_ctx, packet,
rndis_msg, &pb, skb);
if (likely(ret == 0)) {
struct netvsc_stats *tx_stats = this_cpu_ptr(net_device_ctx->tx_stats);
u64_stats_update_begin(&tx_stats->syncp);
tx_stats->packets++;
tx_stats->bytes += skb_length;
u64_stats_update_end(&tx_stats->syncp);
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 int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
{
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 rndis_packet *rndis_pkt;
u32 rndis_msg_size;
bool isvlan;
bool linear = false;
struct rndis_per_packet_info *ppi;
struct ndis_tcp_ip_checksum_info *csum_info;
struct ndis_tcp_lso_info *lso_info;
int hdr_offset;
u32 net_trans_info;
u32 hash;
u32 skb_length;
struct hv_page_buffer page_buf[MAX_PAGE_BUFFER_COUNT];
struct hv_page_buffer *pb = page_buf;
struct netvsc_stats *tx_stats = this_cpu_ptr(net_device_ctx->tx_stats);
/* We will atmost need two pages to describe the rndis
* header. We can only transmit MAX_PAGE_BUFFER_COUNT number
* of pages in a single packet. If skb is scattered around
* more pages we try linearizing it.
*/
check_size:
skb_length = skb->len;
num_data_pgs = netvsc_get_slots(skb) + 2;
if (num_data_pgs > MAX_PAGE_BUFFER_COUNT && linear) {
net_alert_ratelimited("packet too big: %u pages (%u bytes)\n",
num_data_pgs, skb->len);
ret = -EFAULT;
goto drop;
} else if (num_data_pgs > MAX_PAGE_BUFFER_COUNT) {
if (skb_linearize(skb)) {
net_alert_ratelimited("failed to linearize skb\n");
ret = -ENOMEM;
goto drop;
}
linear = true;
goto check_size;
}
/*
* Place the rndis header in the skb head room and
* the skb->cb will be used for hv_netvsc_packet
* structure.
*/
ret = skb_cow_head(skb, RNDIS_AND_PPI_SIZE);
if (ret) {
netdev_err(net, "unable to alloc hv_netvsc_packet\n");
ret = -ENOMEM;
goto drop;
}
/* Use the skb control buffer for building up the packet */
BUILD_BUG_ON(sizeof(struct hv_netvsc_packet) >
FIELD_SIZEOF(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;
rndis_msg = (struct rndis_message *)skb->head;
memset(rndis_msg, 0, RNDIS_AND_PPI_SIZE);
isvlan = skb->vlan_tci & VLAN_TAG_PRESENT;
/* Add the rndis header */
rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET;
rndis_msg->msg_len = packet->total_data_buflen;
rndis_pkt = &rndis_msg->msg.pkt;
rndis_pkt->data_offset = sizeof(struct rndis_packet);
rndis_pkt->data_len = packet->total_data_buflen;
rndis_pkt->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) {
rndis_msg_size += NDIS_HASH_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_HASH_PPI_SIZE,
NBL_HASH_VALUE);
*(u32 *)((void *)ppi + ppi->ppi_offset) = hash;
}
if (isvlan) {
struct ndis_pkt_8021q_info *vlan;
rndis_msg_size += NDIS_VLAN_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_VLAN_PPI_SIZE,
IEEE_8021Q_INFO);
vlan = (struct ndis_pkt_8021q_info *)((void *)ppi +
ppi->ppi_offset);
vlan->vlanid = skb->vlan_tci & VLAN_VID_MASK;
vlan->pri = (skb->vlan_tci & VLAN_PRIO_MASK) >>
VLAN_PRIO_SHIFT;
}
net_trans_info = get_net_transport_info(skb, &hdr_offset);
if (net_trans_info == TRANSPORT_INFO_NOT_IP)
goto do_send;
/*
* Setup the sendside checksum offload only if this is not a
* GSO packet.
*/
if (skb_is_gso(skb))
goto do_lso;
if ((skb->ip_summed == CHECKSUM_NONE) ||
(skb->ip_summed == CHECKSUM_UNNECESSARY))
goto do_send;
rndis_msg_size += NDIS_CSUM_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_CSUM_PPI_SIZE,
TCPIP_CHKSUM_PKTINFO);
csum_info = (struct ndis_tcp_ip_checksum_info *)((void *)ppi +
ppi->ppi_offset);
if (net_trans_info & (INFO_IPV4 << 16))
csum_info->transmit.is_ipv4 = 1;
else
csum_info->transmit.is_ipv6 = 1;
if (net_trans_info & INFO_TCP) {
csum_info->transmit.tcp_checksum = 1;
csum_info->transmit.tcp_header_offset = hdr_offset;
} else if (net_trans_info & INFO_UDP) {
/* UDP checksum offload is not supported on ws2008r2.
* Furthermore, on ws2012 and ws2012r2, there are some
* issues with udp checksum offload from Linux guests.
* (these are host issues).
* For now compute the checksum here.
*/
struct udphdr *uh;
u16 udp_len;
ret = skb_cow_head(skb, 0);
if (ret)
goto drop;
uh = udp_hdr(skb);
udp_len = ntohs(uh->len);
uh->check = 0;
uh->check = csum_tcpudp_magic(ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr,
udp_len, IPPROTO_UDP,
csum_partial(uh, udp_len, 0));
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
csum_info->transmit.udp_checksum = 0;
}
goto do_send;
do_lso:
rndis_msg_size += NDIS_LSO_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_LSO_PPI_SIZE,
TCP_LARGESEND_PKTINFO);
lso_info = (struct ndis_tcp_lso_info *)((void *)ppi +
ppi->ppi_offset);
lso_info->lso_v2_transmit.type = NDIS_TCP_LARGE_SEND_OFFLOAD_V2_TYPE;
if (net_trans_info & (INFO_IPV4 << 16)) {
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;
ipv6_hdr(skb)->payload_len = 0;
tcp_hdr(skb)->check =
~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0);
}
lso_info->lso_v2_transmit.tcp_header_offset = hdr_offset;
lso_info->lso_v2_transmit.mss = skb_shinfo(skb)->gso_size;
do_send:
/* Start filling in the page buffers with the rndis hdr */
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);
/* timestamp packet in software */
skb_tx_timestamp(skb);
ret = netvsc_send(net_device_ctx->device_ctx, packet,
rndis_msg, &pb, skb);
drop:
if (ret == 0) {
u64_stats_update_begin(&tx_stats->syncp);
tx_stats->packets++;
tx_stats->bytes += skb_length;
u64_stats_update_end(&tx_stats->syncp);
} else {
if (ret != -EAGAIN) {
dev_kfree_skb_any(skb);
net->stats.tx_dropped++;
}
}
return (ret == -EAGAIN) ? NETDEV_TX_BUSY : NETDEV_TX_OK;
}
static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
{
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 rndis_packet *rndis_pkt;
u32 rndis_msg_size;
struct rndis_per_packet_info *ppi;
u32 hash;
u32 skb_length;
struct hv_page_buffer page_buf[MAX_PAGE_BUFFER_COUNT];
struct hv_page_buffer *pb = page_buf;
/* We will atmost need two pages to describe the rndis
* header. We can only transmit MAX_PAGE_BUFFER_COUNT number
* of pages in a single packet. If skb is scattered around
* more pages we try linearizing it.
*/
skb_length = skb->len;
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;
}
}
/*
* Place the rndis header in the skb head room and
* the skb->cb will be used for hv_netvsc_packet
* structure.
*/
ret = skb_cow_head(skb, RNDIS_AND_PPI_SIZE);
if (ret)
goto no_memory;
/* Use the skb control buffer for building up the packet */
BUILD_BUG_ON(sizeof(struct hv_netvsc_packet) >
FIELD_SIZEOF(struct sk_buff, cb));
packet = (struct hv_netvsc_packet *)skb->cb;
/* TODO: This will likely evaluate to false, since RH7 and
* below kernels will set next pointer to NULL before calling
* into here. Should find another way to set this flag.
*/
packet->xmit_more = (skb->next != NULL);
packet->q_idx = skb_get_queue_mapping(skb);
packet->total_data_buflen = skb->len;
rndis_msg = (struct rndis_message *)skb->head;
memset(rndis_msg, 0, RNDIS_AND_PPI_SIZE);
packet->send_completion_ctx = packet;
/* Add the rndis header */
rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET;
rndis_msg->msg_len = packet->total_data_buflen;
rndis_pkt = &rndis_msg->msg.pkt;
rndis_pkt->data_offset = sizeof(struct rndis_packet);
rndis_pkt->data_len = packet->total_data_buflen;
rndis_pkt->per_pkt_info_offset = sizeof(struct rndis_packet);
rndis_msg_size = RNDIS_MESSAGE_SIZE(struct rndis_packet);
#ifdef NOTYET
// Divergence from upstream commit:
// 307f099520b66504cf6c5638f3f404c48b9fb45b
hash = skb_get_hash_raw(skb);
#endif
hash = skb_get_hash(skb);
if (hash != 0 && net->real_num_tx_queues > 1) {
rndis_msg_size += NDIS_HASH_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_HASH_PPI_SIZE,
NBL_HASH_VALUE);
*(u32 *)((void *)ppi + ppi->ppi_offset) = hash;
}
if (skb_vlan_tag_present(skb)) {
struct ndis_pkt_8021q_info *vlan;
rndis_msg_size += NDIS_VLAN_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_VLAN_PPI_SIZE,
IEEE_8021Q_INFO);
vlan = (struct ndis_pkt_8021q_info *)((void *)ppi +
ppi->ppi_offset);
vlan->vlanid = skb->vlan_tci & VLAN_VID_MASK;
vlan->pri = (skb->vlan_tci & VLAN_PRIO_MASK) >>
VLAN_PRIO_SHIFT;
}
if (skb_is_gso(skb)) {
struct ndis_tcp_lso_info *lso_info;
rndis_msg_size += NDIS_LSO_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_LSO_PPI_SIZE,
TCP_LARGESEND_PKTINFO);
lso_info = (struct ndis_tcp_lso_info *)((void *)ppi +
ppi->ppi_offset);
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;
ipv6_hdr(skb)->payload_len = 0;
tcp_hdr(skb)->check =
~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0);
}
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;
ppi = init_ppi_data(rndis_msg, NDIS_CSUM_PPI_SIZE,
TCPIP_CHKSUM_PKTINFO);
csum_info = (struct ndis_tcp_ip_checksum_info *)((void *)ppi +
ppi->ppi_offset);
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 {
/* Can't do offload of this type of checksum */
if (skb_checksum_help(skb))
goto drop;
}
}
/* Start filling in the page buffers with the rndis hdr */
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);
/* timestamp packet in software */
skb_tx_timestamp(skb);
ret = netvsc_send(net_device_ctx->device_ctx, packet,
rndis_msg, &pb, skb);
if (likely(ret == 0)) {
struct netvsc_stats *tx_stats = this_cpu_ptr(net_device_ctx->tx_stats);
u64_stats_update_begin(&tx_stats->syncp);
tx_stats->packets++;
tx_stats->bytes += skb_length;
u64_stats_update_end(&tx_stats->syncp);
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 int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
struct hv_netvsc_packet *packet;
int ret;
unsigned int num_data_pgs;
struct rndis_message *rndis_msg;
struct rndis_packet *rndis_pkt;
u32 rndis_msg_size;
bool isvlan;
struct rndis_per_packet_info *ppi;
struct ndis_tcp_ip_checksum_info *csum_info;
struct ndis_tcp_lso_info *lso_info;
int hdr_offset;
u32 net_trans_info;
u32 hash;
/* We will atmost need two pages to describe the rndis
* header. We can only transmit MAX_PAGE_BUFFER_COUNT number
* of pages in a single packet.
*/
num_data_pgs = netvsc_get_slots(skb) + 2;
if (num_data_pgs > MAX_PAGE_BUFFER_COUNT) {
netdev_err(net, "Packet too big: %u\n", skb->len);
dev_kfree_skb(skb);
net->stats.tx_dropped++;
return NETDEV_TX_OK;
}
/* Allocate a netvsc packet based on # of frags. */
packet = kzalloc(sizeof(struct hv_netvsc_packet) +
(num_data_pgs * sizeof(struct hv_page_buffer)) +
sizeof(struct rndis_message) +
NDIS_VLAN_PPI_SIZE + NDIS_CSUM_PPI_SIZE +
NDIS_LSO_PPI_SIZE + NDIS_HASH_PPI_SIZE, GFP_ATOMIC);
if (!packet) {
/* out of memory, drop packet */
netdev_err(net, "unable to allocate hv_netvsc_packet\n");
dev_kfree_skb(skb);
net->stats.tx_dropped++;
return NETDEV_TX_OK;
}
packet->vlan_tci = skb->vlan_tci;
packet->q_idx = skb_get_queue_mapping(skb);
packet->is_data_pkt = true;
packet->total_data_buflen = skb->len;
packet->rndis_msg = (struct rndis_message *)((unsigned long)packet +
sizeof(struct hv_netvsc_packet) +
(num_data_pgs * sizeof(struct hv_page_buffer)));
/* Set the completion routine */
packet->send_completion = netvsc_xmit_completion;
packet->send_completion_ctx = packet;
packet->send_completion_tid = (unsigned long)skb;
isvlan = packet->vlan_tci & VLAN_TAG_PRESENT;
/* Add the rndis header */
rndis_msg = packet->rndis_msg;
rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET;
rndis_msg->msg_len = packet->total_data_buflen;
rndis_pkt = &rndis_msg->msg.pkt;
rndis_pkt->data_offset = sizeof(struct rndis_packet);
rndis_pkt->data_len = packet->total_data_buflen;
rndis_pkt->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) {
rndis_msg_size += NDIS_HASH_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_HASH_PPI_SIZE,
NBL_HASH_VALUE);
*(u32 *)((void *)ppi + ppi->ppi_offset) = hash;
}
if (isvlan) {
struct ndis_pkt_8021q_info *vlan;
rndis_msg_size += NDIS_VLAN_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_VLAN_PPI_SIZE,
IEEE_8021Q_INFO);
vlan = (struct ndis_pkt_8021q_info *)((void *)ppi +
ppi->ppi_offset);
vlan->vlanid = packet->vlan_tci & VLAN_VID_MASK;
vlan->pri = (packet->vlan_tci & VLAN_PRIO_MASK) >>
VLAN_PRIO_SHIFT;
}
net_trans_info = get_net_transport_info(skb, &hdr_offset);
if (net_trans_info == TRANSPORT_INFO_NOT_IP)
goto do_send;
/*
* Setup the sendside checksum offload only if this is not a
* GSO packet.
*/
if (skb_is_gso(skb))
goto do_lso;
if ((skb->ip_summed == CHECKSUM_NONE) ||
(skb->ip_summed == CHECKSUM_UNNECESSARY))
goto do_send;
rndis_msg_size += NDIS_CSUM_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_CSUM_PPI_SIZE,
TCPIP_CHKSUM_PKTINFO);
csum_info = (struct ndis_tcp_ip_checksum_info *)((void *)ppi +
ppi->ppi_offset);
if (net_trans_info & (INFO_IPV4 << 16))
csum_info->transmit.is_ipv4 = 1;
else
csum_info->transmit.is_ipv6 = 1;
if (net_trans_info & INFO_TCP) {
csum_info->transmit.tcp_checksum = 1;
csum_info->transmit.tcp_header_offset = hdr_offset;
} else if (net_trans_info & INFO_UDP) {
/* UDP checksum offload is not supported on ws2008r2.
* Furthermore, on ws2012 and ws2012r2, there are some
* issues with udp checksum offload from Linux guests.
* (these are host issues).
* For now compute the checksum here.
*/
struct udphdr *uh;
u16 udp_len;
ret = skb_cow_head(skb, 0);
if (ret)
goto drop;
uh = udp_hdr(skb);
udp_len = ntohs(uh->len);
uh->check = 0;
uh->check = csum_tcpudp_magic(ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr,
udp_len, IPPROTO_UDP,
csum_partial(uh, udp_len, 0));
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
csum_info->transmit.udp_checksum = 0;
}
goto do_send;
do_lso:
rndis_msg_size += NDIS_LSO_PPI_SIZE;
ppi = init_ppi_data(rndis_msg, NDIS_LSO_PPI_SIZE,
TCP_LARGESEND_PKTINFO);
lso_info = (struct ndis_tcp_lso_info *)((void *)ppi +
ppi->ppi_offset);
lso_info->lso_v2_transmit.type = NDIS_TCP_LARGE_SEND_OFFLOAD_V2_TYPE;
if (net_trans_info & (INFO_IPV4 << 16)) {
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;
ipv6_hdr(skb)->payload_len = 0;
tcp_hdr(skb)->check =
~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0);
}
lso_info->lso_v2_transmit.tcp_header_offset = hdr_offset;
lso_info->lso_v2_transmit.mss = skb_shinfo(skb)->gso_size;
do_send:
/* Start filling in the page buffers with the rndis hdr */
rndis_msg->msg_len += rndis_msg_size;
packet->page_buf_cnt = init_page_array(rndis_msg, rndis_msg_size,
skb, &packet->page_buf[0]);
ret = netvsc_send(net_device_ctx->device_ctx, packet);
drop:
if (ret == 0) {
net->stats.tx_bytes += skb->len;
net->stats.tx_packets++;
} else {
kfree(packet);
if (ret != -EAGAIN) {
dev_kfree_skb_any(skb);
net->stats.tx_dropped++;
}
}
return (ret == -EAGAIN) ? NETDEV_TX_BUSY : NETDEV_TX_OK;
}