path: root/drivers/net/hyperv/netvsc.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2009, Microsoft Corporation.
 *
 * Authors:
 *   Haiyang Zhang <haiyangz@microsoft.com>
 *   Hank Janssen  <hjanssen@microsoft.com>
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/io.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/if_ether.h>
#include <linux/vmalloc.h>
#include <linux/rtnetlink.h>
#include <linux/prefetch.h>

#include <asm/sync_bitops.h>

#include "hyperv_net.h"
#include "netvsc_trace.h"

/*
 * Switch the data path from the synthetic interface to the VF
 * interface.
 */
void netvsc_switch_datapath(struct net_device *ndev, bool vf)
{
	struct net_device_context *net_device_ctx = netdev_priv(ndev);
	struct hv_device *dev = net_device_ctx->device_ctx;
	struct netvsc_device *nv_dev = rtnl_dereference(net_device_ctx->nvdev);
	struct nvsp_message *init_pkt = &nv_dev->channel_init_pkt;

	memset(init_pkt, 0, sizeof(struct nvsp_message));
	init_pkt->hdr.msg_type = NVSP_MSG4_TYPE_SWITCH_DATA_PATH;
	if (vf)
		init_pkt->msg.v4_msg.active_dp.active_datapath =
			NVSP_DATAPATH_VF;
	else
		init_pkt->msg.v4_msg.active_dp.active_datapath =
			NVSP_DATAPATH_SYNTHETIC;

	trace_nvsp_send(ndev, init_pkt);

	vmbus_sendpacket(dev->channel, init_pkt,
			       sizeof(struct nvsp_message),
			       (unsigned long)init_pkt,
			       VM_PKT_DATA_INBAND, 0);
}

/* Worker to setup sub channels on initial setup
 * Initial hotplug event occurs in softirq context
 * and can't wait for channels.
 */
static void netvsc_subchan_work(struct work_struct *w)
{
	struct netvsc_device *nvdev =
		container_of(w, struct netvsc_device, subchan_work);
	struct rndis_device *rdev;
	int i, ret;

	/* Avoid deadlock with device removal already under RTNL */
	if (!rtnl_trylock()) {
		schedule_work(w);
		return;
	}

	rdev = nvdev->extension;
	if (rdev) {
		ret = rndis_set_subchannel(rdev->ndev, nvdev, NULL);
		if (ret == 0) {
			netif_device_attach(rdev->ndev);
		} else {
			/* fallback to only primary channel */
			for (i = 1; i < nvdev->num_chn; i++)
				netif_napi_del(&nvdev->chan_table[i].napi);

			nvdev->max_chn = 1;
			nvdev->num_chn = 1;
		}
	}

	rtnl_unlock();
}

static struct netvsc_device *alloc_net_device(void)
{
	struct netvsc_device *net_device;

	net_device = kzalloc(sizeof(struct netvsc_device), GFP_KERNEL);
	if (!net_device)
		return NULL;

	init_waitqueue_head(&net_device->wait_drain);
	net_device->destroy = false;
	net_device->tx_disable = true;

	net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
	net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;

	init_completion(&net_device->channel_init_wait);
	init_waitqueue_head(&net_device->subchan_open);
	INIT_WORK(&net_device->subchan_work, netvsc_subchan_work);

	return net_device;
}

static void free_netvsc_device(struct rcu_head *head)
{
	struct netvsc_device *nvdev
		= container_of(head, struct netvsc_device, rcu);
	int i;

	kfree(nvdev->extension);
	vfree(nvdev->recv_buf);
	vfree(nvdev->send_buf);
	kfree(nvdev->send_section_map);

	for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
		xdp_rxq_info_unreg(&nvdev->chan_table[i].xdp_rxq);
		vfree(nvdev->chan_table[i].mrc.slots);
	}

	kfree(nvdev);
}

static void free_netvsc_device_rcu(struct netvsc_device *nvdev)
{
	call_rcu(&nvdev->rcu, free_netvsc_device);
}

static void netvsc_revoke_recv_buf(struct hv_device *device,
				   struct netvsc_device *net_device,
				   struct net_device *ndev)
{
	struct nvsp_message *revoke_packet;
	int ret;

	/*
	 * If we got a section count, it means we received a
	 * SendReceiveBufferComplete msg (ie sent
	 * NvspMessage1TypeSendReceiveBuffer msg) therefore, we need
	 * to send a revoke msg here
	 */
	if (net_device->recv_section_cnt) {
		/* Send the revoke receive buffer */
		revoke_packet = &net_device->revoke_packet;
		memset(revoke_packet, 0, sizeof(struct nvsp_message));

		revoke_packet->hdr.msg_type =
			NVSP_MSG1_TYPE_REVOKE_RECV_BUF;
		revoke_packet->msg.v1_msg.
		revoke_recv_buf.id = NETVSC_RECEIVE_BUFFER_ID;

		trace_nvsp_send(ndev, revoke_packet);

		ret = vmbus_sendpacket(device->channel,
				       revoke_packet,
				       sizeof(struct nvsp_message),
				       (unsigned long)revoke_packet,
				       VM_PKT_DATA_INBAND, 0);
		/* If the failure is because the channel is rescinded;
		 * ignore the failure since we cannot send on a rescinded
		 * channel. This would allow us to properly cleanup
		 * even when the channel is rescinded.
		 */
		if (device->channel->rescind)
			ret = 0;
		/*
		 * If we failed here, we might as well return and
		 * have a leak rather than continue and a bugchk
		 */
		if (ret != 0) {
			netdev_err(ndev, "unable to send "
				"revoke receive buffer to netvsp\n");
			return;
		}
		net_device->recv_section_cnt = 0;
	}
}

static void netvsc_revoke_send_buf(struct hv_device *device,
				   struct netvsc_device *net_device,
				   struct net_device *ndev)
{
	struct nvsp_message *revoke_packet;
	int ret;

	/* Deal with the send buffer we may have setup.
	 * If we got a  send section size, it means we received a
	 * NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE msg (ie sent
	 * NVSP_MSG1_TYPE_SEND_SEND_BUF msg) therefore, we need
	 * to send a revoke msg here
	 */
	if (net_device->send_section_cnt) {
		/* Send the revoke receive buffer */
		revoke_packet = &net_device->revoke_packet;
		memset(revoke_packet, 0, sizeof(struct nvsp_message));

		revoke_packet->hdr.msg_type =
			NVSP_MSG1_TYPE_REVOKE_SEND_BUF;
		revoke_packet->msg.v1_msg.revoke_send_buf.id =
			NETVSC_SEND_BUFFER_ID;

		trace_nvsp_send(ndev, revoke_packet);

		ret = vmbus_sendpacket(device->channel,
				       revoke_packet,
				       sizeof(struct nvsp_message),
				       (unsigned long)revoke_packet,
				       VM_PKT_DATA_INBAND, 0);

		/* If the failure is because the ch