summaryrefslogtreecommitdiffstats
path: root/drivers/net/hyperv/netvsc_drv.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-04-02 20:53:45 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2014-04-02 20:53:45 -0700
commitcd6362befe4cc7bf589a5236d2a780af2d47bcc9 (patch)
tree3bd4e13ec3f92a00dc4f6c3d65e820b54dbfe46e /drivers/net/hyperv/netvsc_drv.c
parent0f1b1e6d73cb989ce2c071edc57deade3b084dfe (diff)
parentb1586f099ba897542ece36e8a23c1a62907261ef (diff)
downloadop-kernel-dev-cd6362befe4cc7bf589a5236d2a780af2d47bcc9.zip
op-kernel-dev-cd6362befe4cc7bf589a5236d2a780af2d47bcc9.tar.gz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Here is my initial pull request for the networking subsystem during this merge window: 1) Support for ESN in AH (RFC 4302) from Fan Du. 2) Add full kernel doc for ethtool command structures, from Ben Hutchings. 3) Add BCM7xxx PHY driver, from Florian Fainelli. 4) Export computed TCP rate information in netlink socket dumps, from Eric Dumazet. 5) Allow IPSEC SA to be dumped partially using a filter, from Nicolas Dichtel. 6) Convert many drivers to pci_enable_msix_range(), from Alexander Gordeev. 7) Record SKB timestamps more efficiently, from Eric Dumazet. 8) Switch to microsecond resolution for TCP round trip times, also from Eric Dumazet. 9) Clean up and fix 6lowpan fragmentation handling by making use of the existing inet_frag api for it's implementation. 10) Add TX grant mapping to xen-netback driver, from Zoltan Kiss. 11) Auto size SKB lengths when composing netlink messages based upon past message sizes used, from Eric Dumazet. 12) qdisc dumps can take a long time, add a cond_resched(), From Eric Dumazet. 13) Sanitize netpoll core and drivers wrt. SKB handling semantics. Get rid of never-used-in-tree netpoll RX handling. From Eric W Biederman. 14) Support inter-address-family and namespace changing in VTI tunnel driver(s). From Steffen Klassert. 15) Add Altera TSE driver, from Vince Bridgers. 16) Optimizing csum_replace2() so that it doesn't adjust the checksum by checksumming the entire header, from Eric Dumazet. 17) Expand BPF internal implementation for faster interpreting, more direct translations into JIT'd code, and much cleaner uses of BPF filtering in non-socket ocntexts. From Daniel Borkmann and Alexei Starovoitov" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1976 commits) netpoll: Use skb_irq_freeable to make zap_completion_queue safe. net: Add a test to see if a skb is freeable in irq context qlcnic: Fix build failure due to undefined reference to `vxlan_get_rx_port' net: ptp: move PTP classifier in its own file net: sxgbe: make "core_ops" static net: sxgbe: fix logical vs bitwise operation net: sxgbe: sxgbe_mdio_register() frees the bus Call efx_set_channels() before efx->type->dimension_resources() xen-netback: disable rogue vif in kthread context net/mlx4: Set proper build dependancy with vxlan be2net: fix build dependency on VxLAN mac802154: make csma/cca parameters per-wpan mac802154: allow only one WPAN to be up at any given time net: filter: minor: fix kdoc in __sk_run_filter netlink: don't compare the nul-termination in nla_strcmp can: c_can: Avoid led toggling for every packet. can: c_can: Simplify TX interrupt cleanup can: c_can: Store dlc private can: c_can: Reduce register access can: c_can: Make the code readable ...
Diffstat (limited to 'drivers/net/hyperv/netvsc_drv.c')
-rw-r--r--drivers/net/hyperv/netvsc_drv.c337
1 files changed, 285 insertions, 52 deletions
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index d6fce97..4e4cf9e 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -128,6 +128,27 @@ static int netvsc_close(struct net_device *net)
return ret;
}
+static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size,
+ int pkt_type)
+{
+ struct rndis_packet *rndis_pkt;
+ struct rndis_per_packet_info *ppi;
+
+ rndis_pkt = &msg->msg.pkt;
+ rndis_pkt->data_offset += ppi_size;
+
+ ppi = (struct rndis_per_packet_info *)((void *)rndis_pkt +
+ rndis_pkt->per_pkt_info_offset + rndis_pkt->per_pkt_info_len);
+
+ ppi->size = ppi_size;
+ ppi->type = pkt_type;
+ ppi->ppi_offset = sizeof(struct rndis_per_packet_info);
+
+ rndis_pkt->per_pkt_info_len += ppi_size;
+
+ return ppi;
+}
+
static void netvsc_xmit_completion(void *context)
{
struct hv_netvsc_packet *packet = (struct hv_netvsc_packet *)context;
@@ -140,22 +161,164 @@ static void netvsc_xmit_completion(void *context)
dev_kfree_skb_any(skb);
}
+static u32 fill_pg_buf(struct page *page, u32 offset, u32 len,
+ struct hv_page_buffer *pb)
+{
+ int j = 0;
+
+ /* Deal with compund pages by ignoring unused part
+ * of the page.
+ */
+ page += (offset >> PAGE_SHIFT);
+ offset &= ~PAGE_MASK;
+
+ while (len > 0) {
+ unsigned long bytes;
+
+ bytes = PAGE_SIZE - offset;
+ if (bytes > len)
+ bytes = len;
+ pb[j].pfn = page_to_pfn(page);
+ pb[j].offset = offset;
+ pb[j].len = bytes;
+
+ offset += bytes;
+ len -= bytes;
+
+ if (offset == PAGE_SIZE && len) {
+ page++;
+ offset = 0;
+ j++;
+ }
+ }
+
+ return j + 1;
+}
+
+static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
+ struct hv_page_buffer *pb)
+{
+ u32 slots_used = 0;
+ char *data = skb->data;
+ int frags = skb_shinfo(skb)->nr_frags;
+ int i;
+
+ /* The packet is laid out thus:
+ * 1. hdr
+ * 2. skb linear data
+ * 3. skb fragment data
+ */
+ if (hdr != NULL)
+ slots_used += fill_pg_buf(virt_to_page(hdr),
+ offset_in_page(hdr),
+ len, &pb[slots_used]);
+
+ slots_used += fill_pg_buf(virt_to_page(data),
+ offset_in_page(data),
+ skb_headlen(skb), &pb[slots_used]);
+
+ for (i = 0; i < frags; i++) {
+ skb_frag_t *frag = skb_shinfo(skb)->frags + i;
+
+ slots_used += fill_pg_buf(skb_frag_page(frag),
+ frag->page_offset,
+ skb_frag_size(frag), &pb[slots_used]);
+ }
+ return slots_used;
+}
+
+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 = frag->page_offset;
+
+ /* Skip unused frames from start of page */
+ offset &= ~PAGE_MASK;
+ pages += PFN_UP(offset + size);
+ }
+ return pages;
+}
+
+static int netvsc_get_slots(struct sk_buff *skb)
+{
+ char *data = skb->data;
+ unsigned int offset = offset_in_page(data);
+ unsigned int len = skb_headlen(skb);
+ int slots;
+ int frag_slots;
+
+ slots = DIV_ROUND_UP(offset + len, PAGE_SIZE);
+ frag_slots = count_skb_frag_slots(skb);
+ return slots + frag_slots;
+}
+
+static u32 get_net_transport_info(struct sk_buff *skb, u32 *trans_off)
+{
+ u32 ret_val = TRANSPORT_INFO_NOT_IP;
+
+ if ((eth_hdr(skb)->h_proto != htons(ETH_P_IP)) &&
+ (eth_hdr(skb)->h_proto != htons(ETH_P_IPV6))) {
+ goto not_ip;
+ }
+
+ *trans_off = skb_transport_offset(skb);
+
+ if ((eth_hdr(skb)->h_proto == htons(ETH_P_IP))) {
+ struct iphdr *iphdr = ip_hdr(skb);
+
+ if (iphdr->protocol == IPPROTO_TCP)
+ ret_val = TRANSPORT_INFO_IPV4_TCP;
+ else if (iphdr->protocol == IPPROTO_UDP)
+ ret_val = TRANSPORT_INFO_IPV4_UDP;
+ } else {
+ if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
+ ret_val = TRANSPORT_INFO_IPV6_TCP;
+ else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)
+ ret_val = TRANSPORT_INFO_IPV6_UDP;
+ }
+
+not_ip:
+ return ret_val;
+}
+
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 i, num_pages, npg_data;
-
- /* Add multipages for skb->data and additional 2 for RNDIS */
- npg_data = (((unsigned long)skb->data + skb_headlen(skb) - 1)
- >> PAGE_SHIFT) - ((unsigned long)skb->data >> PAGE_SHIFT) + 1;
- num_pages = skb_shinfo(skb)->nr_frags + npg_data + 2;
+ 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;
+
+
+ /* 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_pages * sizeof(struct hv_page_buffer)) +
- sizeof(struct rndis_filter_packet) +
+ (num_data_pgs * sizeof(struct hv_page_buffer)) +
+ sizeof(struct rndis_message) +
NDIS_VLAN_PPI_SIZE, GFP_ATOMIC);
if (!packet) {
/* out of memory, drop packet */
@@ -168,53 +331,111 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
packet->vlan_tci = skb->vlan_tci;
- packet->extension = (void *)(unsigned long)packet +
+ 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_pages * sizeof(struct hv_page_buffer));
+ (num_data_pgs * sizeof(struct hv_page_buffer)));
+
+ /* Set the completion routine */
+ packet->completion.send.send_completion = netvsc_xmit_completion;
+ packet->completion.send.send_completion_ctx = packet;
+ packet->completion.send.send_completion_tid = (unsigned long)skb;
- /* If the rndis msg goes beyond 1 page, we will add 1 later */
- packet->page_buf_cnt = num_pages - 1;
+ 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);
+
+ 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;
+ }
- /* Initialize it from the skb */
- packet->total_data_buflen = skb->len;
+ 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;
+
+ 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);
- /* Start filling in the page buffers starting after RNDIS buffer. */
- packet->page_buf[1].pfn = virt_to_phys(skb->data) >> PAGE_SHIFT;
- packet->page_buf[1].offset
- = (unsigned long)skb->data & (PAGE_SIZE - 1);
- if (npg_data == 1)
- packet->page_buf[1].len = skb_headlen(skb);
+ if (net_trans_info & (INFO_IPV4 << 16))
+ csum_info->transmit.is_ipv4 = 1;
else
- packet->page_buf[1].len = PAGE_SIZE
- - packet->page_buf[1].offset;
-
- for (i = 2; i <= npg_data; i++) {
- packet->page_buf[i].pfn = virt_to_phys(skb->data
- + PAGE_SIZE * (i-1)) >> PAGE_SHIFT;
- packet->page_buf[i].offset = 0;
- packet->page_buf[i].len = PAGE_SIZE;
+ 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) {
+ csum_info->transmit.udp_checksum = 1;
}
- if (npg_data > 1)
- packet->page_buf[npg_data].len = (((unsigned long)skb->data
- + skb_headlen(skb) - 1) & (PAGE_SIZE - 1)) + 1;
-
- /* Additional fragments are after SKB data */
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- const skb_frag_t *f = &skb_shinfo(skb)->frags[i];
-
- packet->page_buf[i+npg_data+1].pfn =
- page_to_pfn(skb_frag_page(f));
- packet->page_buf[i+npg_data+1].offset = f->page_offset;
- packet->page_buf[i+npg_data+1].len = skb_frag_size(f);
+ 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;
- /* Set the completion routine */
- packet->completion.send.send_completion = netvsc_xmit_completion;
- packet->completion.send.send_completion_ctx = packet;
- packet->completion.send.send_completion_tid = (unsigned long)skb;
+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);
- ret = rndis_filter_send(net_device_ctx->device_ctx,
- packet);
if (ret == 0) {
net->stats.tx_bytes += skb->len;
net->stats.tx_packets++;
@@ -264,7 +485,8 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj,
* "wire" on the specified device.
*/
int netvsc_recv_callback(struct hv_device *device_obj,
- struct hv_netvsc_packet *packet)
+ struct hv_netvsc_packet *packet,
+ struct ndis_tcp_ip_checksum_info *csum_info)
{
struct net_device *net;
struct sk_buff *skb;
@@ -291,7 +513,17 @@ int netvsc_recv_callback(struct hv_device *device_obj,
packet->total_data_buflen);
skb->protocol = eth_type_trans(skb, net);
- skb->ip_summed = CHECKSUM_NONE;
+ if (csum_info) {
+ /* We only look at the IP checksum here.
+ * Should we be dropping the packet if checksum
+ * failed? How do we deal with other checksums - TCP/UDP?
+ */
+ if (csum_info->receive.ip_checksum_succeeded)
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ else
+ skb->ip_summed = CHECKSUM_NONE;
+ }
+
if (packet->vlan_tci & VLAN_TAG_PRESENT)
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
packet->vlan_tci);
@@ -327,7 +559,7 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
if (nvdev == NULL || nvdev->destroy)
return -ENODEV;
- if (nvdev->nvsp_version == NVSP_PROTOCOL_VERSION_2)
+ if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)
limit = NETVSC_MTU;
if (mtu < 68 || mtu > limit)
@@ -452,9 +684,10 @@ static int netvsc_probe(struct hv_device *dev,
net->netdev_ops = &device_ops;
- /* TODO: Add GSO and Checksum offload */
- net->hw_features = 0;
- net->features = NETIF_F_HW_VLAN_CTAG_TX;
+ net->hw_features = NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_IP_CSUM |
+ NETIF_F_TSO;
+ net->features = NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_SG | NETIF_F_RXCSUM |
+ NETIF_F_IP_CSUM | NETIF_F_TSO;
SET_ETHTOOL_OPS(net, &ethtool_ops);
SET_NETDEV_DEV(net, &dev->device);
OpenPOWER on IntegriCloud