/*
* Copyright (c) 2009, Microsoft Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program; if not, see <http://www.gnu.org/licenses/>.
*
* Authors:
* Haiyang Zhang <haiyangz@microsoft.com>
* Hank Janssen <hjanssen@microsoft.com>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/init.h>
#include <linux/atomic.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/skbuff.h>
#include <linux/if_vlan.h>
#include <linux/in.h>
#include <linux/slab.h>
#include <net/arp.h>
#include <net/route.h>
#include <net/sock.h>
#include <net/pkt_sched.h>
#include "hyperv_net.h"
#define RING_SIZE_MIN 64
#define LINKCHANGE_INT (2 * HZ)
#define NETVSC_HW_FEATURES (NETIF_F_RXCSUM | \
NETIF_F_SG | \
NETIF_F_TSO | \
NETIF_F_TSO6 | \
NETIF_F_HW_CSUM)
static int ring_size = 128;
module_param(ring_size, int, S_IRUGO);
MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
static int max_num_vrss_chns = 8;
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, S_IRUGO);
MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
static void do_set_multicast(struct work_struct *w)
{
struct net_device_context *ndevctx =
container_of(w, struct net_device_context, work);
struct hv_device *device_obj = ndevctx->device_ctx;
struct net_device *ndev = hv_get_drvdata(device_obj);
struct netvsc_device *nvdev = ndevctx->nvdev;
struct rndis_device *rdev;
if (!nvdev)
return;
rdev = nvdev->extension;
if (rdev == NULL)
return;
if (ndev->flags & IFF_PROMISC)
rndis_filter_set_packet_filter(rdev,
NDIS_PACKET_TYPE_PROMISCUOUS);
else
rndis_filter_set_packet_filter(rdev,
NDIS_PACKET_TYPE_BROADCAST |
NDIS_PACKET_TYPE_ALL_MULTICAST |
NDIS_PACKET_TYPE_DIRECTED);
}
static void netvsc_set_multicast_list(struct net_device *net)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
schedule_work(&net_device_ctx->work);
}
static int netvsc_open(struct net_device *net)
{
struct netvsc_device *nvdev = net_device_to_netvsc_device(net);
struct rndis_device *rdev;
int ret = 0;
netif_carrier_off(net);
/* Open up the device */
ret = rndis_filter_open(nvdev);
if (ret != 0) {
netdev_err(net, "unable to open device (ret %d).\n", ret);
return ret;
}
netif_tx_wake_all_queues(net);
rdev = nvdev->extension;
if (!rdev->link_state)
netif_carrier_on(net);
return ret;
}
static int netvsc_close(struct net_device *net)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
struct netvsc_device *nvdev = net_device_ctx->nvdev;
int ret;
u32 aread, awrite, i, msec = 10, retry = 0, retry_max = 20;
struct vmbus_channel *chn;
netif_tx_disable(net);
/* Make sure netvsc_set_multicast_list doesn't re-enable filter! */
cancel_work_sync(&net_device_ctx->work);
ret = rndis_filter_close(nvdev);
if (ret != 0) {
netdev_err(net, "unable to close device (ret %d).\n", ret);
return ret;
}
/* Ensure pending bytes in ring are read */
while (true) {
aread = 0;
for (i = 0; i < nvdev->num_chn; i++) {
chn = nvdev->chn_table[i];
if (!chn)
continue;
hv_get_ringbuffer_availbytes(&chn->inbound, &aread,
&awrite);
if (aread)
break;
hv_get_ringbuffer_availbytes(&chn->outbound, &aread,
&awrite);
if (aread)
break;
}
retry++;
if (retry > retry_max || aread == 0)
break;
msleep(msec);
if (msec < 1000)
msec *= 2;
}
if (aread) {
netdev_err(net, "Ring buffer not empty after closing rndis\n");
ret = -ETIMEDOUT;
}
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 u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
void *accel_priv, select_queue_fallback_t fallback)
{
struct net_device_context *net_device_ctx = netdev_priv(ndev);
struct netvsc_device *nvsc_dev = net_device_ctx->nvdev;
u32 hash;
u16 q_idx = 0;
if (nvsc_dev == NULL || ndev->real_num_tx_queues <= 1)
return 0;
hash = skb_get_hash(skb);
q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] %
ndev->real_num_tx_queues;
if (!nvsc_dev->chn_table[q_idx])
q_idx = 0;
return q_idx;
}
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_netvsc_packet *packet,
struct hv_page_buffer **page_buf)
{
struct hv_page_buffer *pb = *page_buf;
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: RNDIS header and PPI
* 2. skb linear data
* 3. skb fragment data
*/
if (h
|