#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/ethtool.h>
#include <linux/if_ether.h>
#include <net/tcp.h>
#include <linux/udp.h>
#include <linux/moduleparam.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <net/ip.h>
#include <linux/bpf.h>
#include <net/page_pool/types.h>
#include <linux/bpf_trace.h>
#include <xen/xen.h>
#include <xen/xenbus.h>
#include <xen/events.h>
#include <xen/page.h>
#include <xen/platform_pci.h>
#include <xen/grant_table.h>
#include <xen/interface/io/netif.h>
#include <xen/interface/memory.h>
#include <xen/interface/grant_table.h>
#define MAX_QUEUES_DEFAULT 8
static unsigned int xennet_max_queues;
module_param_named(max_queues, xennet_max_queues, uint, 0644);
MODULE_PARM_DESC(max_queues,
"Maximum number of queues per virtual interface");
static bool __read_mostly xennet_trusted = true;
module_param_named(trusted, xennet_trusted, bool, 0644);
MODULE_PARM_DESC(trusted, "Is the backend trusted");
#define XENNET_TIMEOUT (5 * HZ)
static const struct ethtool_ops xennet_ethtool_ops;
struct netfront_cb {
int pull_to;
};
#define NETFRONT_SKB_CB(skb) ((struct netfront_cb *)((skb)->cb))
#define RX_COPY_THRESHOLD 256
#define NET_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, XEN_PAGE_SIZE)
#define NET_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, XEN_PAGE_SIZE)
#define NET_RX_SLOTS_MIN (XEN_NETIF_NR_SLOTS_MIN + 1)
#define QUEUE_NAME_SIZE (IFNAMSIZ + 6)
#define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3)
static DECLARE_WAIT_QUEUE_HEAD(module_wq);
struct netfront_stats {
u64 packets;
u64 bytes;
struct u64_stats_sync syncp;
};
struct netfront_info;
struct netfront_queue {
unsigned int id;
char name[QUEUE_NAME_SIZE];
struct netfront_info *info;
struct bpf_prog __rcu *xdp_prog;
struct napi_struct napi;
unsigned int tx_evtchn, rx_evtchn;
unsigned int tx_irq, rx_irq;
char tx_irq_name[IRQ_NAME_SIZE];
char rx_irq_name[IRQ_NAME_SIZE];
spinlock_t tx_lock;
struct xen_netif_tx_front_ring tx;
int tx_ring_ref;
struct sk_buff *tx_skbs[NET_TX_RING_SIZE];
unsigned short tx_link[NET_TX_RING_SIZE];
#define TX_LINK_NONE 0xffff
#define TX_PENDING 0xfffe
grant_ref_t gref_tx_head;
grant_ref_t grant_tx_ref[NET_TX_RING_SIZE];
struct page *grant_tx_page[NET_TX_RING_SIZE];
unsigned tx_skb_freelist;
unsigned int tx_pend_queue;
spinlock_t rx_lock ____cacheline_aligned_in_smp;
struct xen_netif_rx_front_ring rx;
int rx_ring_ref;
struct timer_list rx_refill_timer;
struct sk_buff *rx_skbs[NET_RX_RING_SIZE];
grant_ref_t gref_rx_head;
grant_ref_t grant_rx_ref[NET_RX_RING_SIZE];
unsigned int rx_rsp_unconsumed;
spinlock_t rx_cons_lock;
struct page_pool *page_pool;
struct xdp_rxq_info xdp_rxq;
};
struct netfront_info {
struct list_head list;
struct net_device *netdev;
struct xenbus_device *xbdev;
struct netfront_queue *queues;
struct netfront_stats __percpu *rx_stats;
struct netfront_stats __percpu *tx_stats;
bool netback_has_xdp_headroom;
bool netfront_xdp_enabled;
bool broken;
bool bounce;
atomic_t rx_gso_checksum_fixup;
};
struct netfront_rx_info {
struct xen_netif_rx_response rx;
struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX - 1];
};
static void add_id_to_list(unsigned *head, unsigned short *list,
unsigned short id)
{
list[id] = *head;
*head = id;
}
static unsigned short get_id_from_list(unsigned *head, unsigned short *list)
{
unsigned int id = *head;
if (id != TX_LINK_NONE) {
*head = list[id];
list[id] = TX_LINK_NONE;
}
return id;
}
static int xennet_rxidx(RING_IDX idx)
{
return idx & (NET_RX_RING_SIZE - 1);
}
static struct sk_buff *xennet_get_rx_skb(struct netfront_queue *queue,
RING_IDX ri)
{
int i = xennet_rxidx(ri);
struct sk_buff *skb = queue->rx_skbs[i];
queue->rx_skbs[i] = NULL;
return skb;
}
static grant_ref_t xennet_get_rx_ref(struct netfront_queue *queue,
RING_IDX ri)
{
int i = xennet_rxidx(ri);
grant_ref_t ref = queue->grant_rx_ref[i];
queue->grant_rx_ref[i] = INVALID_GRANT_REF;
return ref;
}
#ifdef CONFIG_SYSFS
static const struct attribute_group xennet_dev_group;
#endif
static bool xennet_can_sg(struct net_device *dev)
{
return dev->features & NETIF_F_SG;
}
static void rx_refill_timeout(struct timer_list *t)
{
struct netfront_queue *queue = from_timer(queue, t, rx_refill_timer);
napi_schedule(&queue->napi);
}
static int netfront_tx_slot_available(struct netfront_queue *queue)
{
return (queue->tx.req_prod_pvt - queue->tx.rsp_cons) <
(NET_TX_RING_SIZE - XEN_NETIF_NR_SLOTS_MIN - 1);
}
static void xennet_maybe_wake_tx(struct netfront_queue *queue)
{
struct net_device *dev = queue->info->netdev;
struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, queue->id);
if (unlikely(netif_tx_queue_stopped(dev_queue)) &&
netfront_tx_slot_available(queue) &&
likely(netif_running(dev)))
netif_tx_wake_queue(netdev_get_tx_queue(dev, queue->id));
}
static struct sk_buff *xennet_alloc_one_rx_buffer(struct netfront_queue *queue)
{
struct sk_buff *skb;
struct page *page;
skb = __netdev_alloc_skb(queue->info->netdev,
RX_COPY_THRESHOLD + NET_IP_ALIGN,
GFP_ATOMIC | __GFP_NOWARN);
if (unlikely(!skb))
return NULL;
page = page_pool_alloc_pages(queue->page_pool,
GFP_ATOMIC | __GFP_NOWARN | __GFP_ZERO);
if (unlikely(!page)) {
kfree_skb(skb);
return NULL;
}
skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE);
skb_reserve(skb, NET_IP_ALIGN);
skb->dev = queue->info->netdev;
return skb;
}
static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
{
RING_IDX req_prod = queue->rx.req_prod_pvt;
int notify;
int err = 0;
if (unlikely(!netif_carrier_ok(queue->info->netdev)))
return;
for (req_prod = queue->rx.req_prod_pvt;
req_prod - queue->rx.rsp_cons < NET_RX_RING_SIZE;
req_prod++) {
struct sk_buff *skb;
unsigned short id;
grant_ref_t ref;
struct page *page;
struct xen_netif_rx_request *req;
skb = xennet_alloc_one_rx_buffer(queue);
if (!skb) {
err = -ENOMEM;
break;
}
id = xennet_rxidx(req_prod);
BUG_ON(queue->rx_skbs[id]);
queue->rx_skbs[id] = skb;
ref = gnttab_claim_grant_reference(&queue->gref_rx_head);
WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref));
queue->grant_rx_ref[id] = ref;
page = skb_frag_page(&skb_shinfo(skb)->frags[0]);
req = RING_GET_REQUEST(&queue->rx, req_prod);
gnttab_page_grant_foreign_access_ref_one(ref,
queue->info->xbdev->otherend_id,
page,
0);
req->id = id;
req->gref = ref;
}
queue->rx.req_prod_pvt = req_prod;
if (req_prod - queue->rx.rsp_cons < NET_RX_SLOTS_MIN ||
unlikely(err)) {
mod_timer(&queue->rx_refill_timer, jiffies + (HZ/10));
return;
}
RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->rx, notify);
if (notify)
notify_remote_via_irq(queue->rx_irq);
}
static int xennet_open(struct net_device *dev)
{
struct netfront_info *np = netdev_priv(dev);
unsigned int num_queues = dev->real_num_tx_queues;
unsigned int i = 0;
struct netfront_queue *queue = NULL;
if (!np->queues || np->broken)
return -ENODEV;
for (i = 0; i < num_queues; ++i) {
queue = &np->queues[i];
napi_enable(&queue->napi);
spin_lock_bh(&queue->rx_lock);
if (netif_carrier_ok(dev)) {
xennet_alloc_rx_buffers(queue);
queue->rx.sring->rsp_event = queue->rx.rsp_cons + 1;
if (RING_HAS_UNCONSUMED_RESPONSES(&queue->rx))
napi_schedule(&queue->napi);
}
spin_unlock_bh(&queue->rx_lock);
}
netif_tx_start_all_queues(dev);
return 0;
}
static bool xennet_tx_buf_gc(struct netfront_queue *queue)
{
RING_IDX cons, prod;
unsigned short id;
struct sk_buff *skb;
bool more_to_do;
bool work_done = false;
const struct device *dev = &queue->info->netdev->dev;
BUG_ON(!netif_carrier_ok(queue->info->netdev));
do {
prod = queue->tx.sring->rsp_prod;
if (RING_RESPONSE_PROD_OVERFLOW(&queue->tx, prod)) {
dev_alert(dev, "Illegal number of responses %u\n",
prod - queue->tx.rsp_cons);
goto err;
}
rmb();
for (cons = queue->tx.rsp_cons; cons != prod; cons++) {
struct xen_netif_tx_response txrsp;
work_done = true;
RING_COPY_RESPONSE(&queue->tx, cons, &txrsp);
if (txrsp.status == XEN_NETIF_RSP_NULL)
continue;
id = txrsp.id;
if (id >= RING_SIZE(&queue->tx)) {
dev_alert(dev,
"Response has incorrect id (%u)\n",
id);
goto err;
}
if (queue->tx_link[id] != TX_PENDING) {
dev_alert(dev,
"Response for inactive request\n");
goto err;
}
queue->tx_link[id] = TX_LINK_NONE;
skb = queue->tx_skbs[id];
queue->tx_skbs[id] = NULL;
if (unlikely(!gnttab_end_foreign_access_ref(
queue->grant_tx_ref[id]))) {
dev_alert(dev,
"Grant still in use by backend domain\n");
goto err;
}
gnttab_release_grant_reference(
&queue->gref_tx_head, queue->grant_tx_ref[id]);
queue->grant_tx_ref[id] = INVALID_GRANT_REF;
queue->grant_tx_page[id] = NULL;
add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, id);
dev_kfree_skb_irq(skb);
}
queue->tx.rsp_cons = prod;
RING_FINAL_CHECK_FOR_RESPONSES(&queue->tx, more_to_do);
} while (more_to_do);
xennet_maybe_wake_tx(queue);
return work_done;
err:
queue->info->broken = true;
dev_alert(dev, "Disabled for further use\n");
return work_done;
}
struct xennet_gnttab_make_txreq {
struct netfront_queue *queue;
struct sk_buff *skb;
struct page *page;
struct xen_netif_tx_request *tx;
struct xen_netif_tx_request tx_local;
unsigned int size;
};
static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset,
unsigned int len, void *data)
{
struct xennet_gnttab_make_txreq *info = data;
unsigned int id;
struct xen_netif_tx_request *tx;
grant_ref_t ref;
struct page *page = info->page;
struct netfront_queue *queue = info->queue;
struct sk_buff *skb = info->skb;
id = get_id_from_list(&queue->tx_skb_freelist, queue->tx_link);
tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref));
gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id,
gfn, GNTMAP_readonly);
queue->tx_skbs[id] = skb;
queue->grant_tx_page[id] = page;
queue->grant_tx_ref[id] = ref;
info->tx_local.id = id;
info->tx_local.gref = ref;
info->tx_local.offset = offset;
info->tx_local.size = len;
info->tx_local.flags = 0;
*tx = info->tx_local;
add_id_to_list(&queue->tx_pend_queue, queue->tx_link, id);
info->tx = tx;
info->size += info->tx_local.size;
}
static struct xen_netif_tx_request *xennet_make_first_txreq(
struct xennet_gnttab_make_txreq *info,
unsigned int offset, unsigned int len)
{
info->size = 0;
gnttab_for_one_grant(info->page, offset, len, xennet_tx_setup_grant, info);
return info->tx;
}
static void xennet_make_one_txreq(unsigned long gfn, unsigned int offset,
unsigned int len, void *data)
{
struct xennet_gnttab_make_txreq *info = data;
info->tx->flags |= XEN_NETTXF_more_data;
skb_get(info->skb);
xennet_tx_setup_grant(gfn, offset, len, data);
}
static void xennet_make_txreqs(
struct xennet_gnttab_make_txreq *info,
struct page *page,
unsigned int offset, unsigned int len)
{
page += offset >> PAGE_SHIFT;
offset &= ~PAGE_MASK;
while (len) {
info->page = page;
info->size = 0;
gnttab_foreach_grant_in_range(page, offset, len,
xennet_make_one_txreq,
info);
page++;
offset = 0;
len -= info->size;
}
}
static int xennet_count_skb_slots(struct sk_buff *skb)
{
int i, frags = skb_shinfo(skb)->nr_frags;
int slots;
slots = gnttab_count_grant(offset_in_page(skb->data),
skb_headlen(skb));
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 &= ~PAGE_MASK;
slots += gnttab_count_grant(offset, size);
}
return slots;
}
static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev)
{
unsigned int num_queues = dev->real_num_tx_queues;
u32 hash;
u16 queue_idx;
if (num_queues == 1) {
queue_idx = 0;
} else {
hash = skb_get_hash(skb);
queue_idx = hash % num_queues;
}
return queue_idx;
}
static void xennet_mark_tx_pending(struct netfront_queue *queue)
{
unsigned int i;
while ((i = get_id_from_list(&queue->tx_pend_queue, queue->tx_link)) !=
TX_LINK_NONE)
queue->tx_link[i] = TX_PENDING;
}
static int xennet_xdp_xmit_one(struct net_device *dev,
struct netfront_queue *queue,
struct xdp_frame *xdpf)
{
struct netfront_info *np = netdev_priv(dev);
struct netfront_stats *tx_stats = this_cpu_ptr(np->tx_stats);
struct xennet_gnttab_make_txreq info = {
.queue = queue,
.skb = NULL,
.page = virt_to_page(xdpf->data),
};
int notify;
xennet_make_first_txreq(&info,
offset_in_page(xdpf->data),
xdpf->len);
xennet_mark_tx_pending(queue);
RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify);
if (notify)
notify_remote_via_irq(queue->tx_irq);
u64_stats_update_begin(&tx_stats->syncp);
tx_stats->bytes += xdpf->len;
tx_stats->packets++;
u64_stats_update_end(&tx_stats->syncp);
xennet_tx_buf_gc(queue);
return 0;
}
static int xennet_xdp_xmit(struct net_device *dev, int n,
struct xdp_frame **frames, u32 flags)
{
unsigned int num_queues = dev->real_num_tx_queues;
struct netfront_info *np = netdev_priv(dev);
struct netfront_queue *queue = NULL;
unsigned long irq_flags;
int nxmit = 0;
int i;
if (unlikely(np->broken))
return -ENODEV;
if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
return -EINVAL;
queue = &np->queues[smp_processor_id() % num_queues];
spin_lock_irqsave(&queue->tx_lock, irq_flags);
for (i = 0; i < n; i++) {
struct xdp_frame *xdpf = frames[i];
if (!xdpf)
continue;
if (xennet_xdp_xmit_one(dev, queue, xdpf))
break;
nxmit++;
}
spin_unlock_irqrestore(&queue->tx_lock, irq_flags);
return nxmit;
}
static struct sk_buff *bounce_skb(const struct sk_buff *skb)
{
unsigned int headerlen = skb_headroom(skb);
unsigned int size = ALIGN(skb_end_offset(skb) + skb->data_len,
XEN_PAGE_SIZE);
struct sk_buff *n = alloc_skb(size, GFP_ATOMIC | __GFP_ZERO);
if (!n)
return NULL;
if (!IS_ALIGNED((uintptr_t)n->head, XEN_PAGE_SIZE)) {
WARN_ONCE(1, "misaligned skb allocated\n");
kfree_skb(n);
return NULL;
}
skb_reserve(n, headerlen);
skb_put(n, skb->len);
BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len));
skb_copy_header(n, skb);
return n;
}
#define MAX_XEN_SKB_FRAGS (65536 / XEN_PAGE_SIZE + 1)
static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct netfront_info *np = netdev_priv(dev);
struct netfront_stats *tx_stats = this_cpu_ptr(np->tx_stats);
struct xen_netif_tx_request *first_tx;
unsigned int i;
int notify;
int slots;
struct page *page;
unsigned int offset;
unsigned int len;
unsigned long flags;
struct netfront_queue *queue = NULL;
struct xennet_gnttab_make_txreq info = { };
unsigned int num_queues = dev->real_num_tx_queues;
u16 queue_index;
struct sk_buff *nskb;
if (num_queues < 1)
goto drop;
if (unlikely(np->broken))
goto drop;
queue_index = skb_get_queue_mapping(skb);
queue = &np->queues[queue_index];
if (unlikely(skb->len > XEN_NETIF_MAX_TX_SIZE)) {
net_alert_ratelimited(
"xennet: skb->len = %u, too big for wire format\n",
skb->len);
goto drop;
}
slots = xennet_count_skb_slots(skb);
if (unlikely(slots > MAX_XEN_SKB_FRAGS + 1)) {
net_dbg_ratelimited("xennet: skb rides the rocket: %d slots, %d bytes\n",
slots, skb->len);
if (skb_linearize(skb))
goto drop;
}
page = virt_to_page(skb->data);
offset = offset_in_page(skb->data);
if (np->bounce || unlikely(PAGE_SIZE - offset < ETH_HLEN)) {
nskb = bounce_skb(skb);
if (!nskb)
goto drop;
dev_consume_skb_any(skb);
skb = nskb;
page = virt_to_page(skb->data);
offset = offset_in_page(skb->data);
}
len = skb_headlen(skb);
spin_lock_irqsave(&queue->tx_lock, flags);
if (unlikely(!netif_carrier_ok(dev) ||
(slots > 1 && !xennet_can_sg(dev)) ||
netif_needs_gso(skb, netif_skb_features(skb)))) {
spin_unlock_irqrestore(&queue->tx_lock, flags);
goto drop;
}
info.queue = queue;
info.skb = skb;
info.page = page;
first_tx = xennet_make_first_txreq(&info, offset, len);
offset += info.tx_local.size;
if (offset == PAGE_SIZE) {
page++;
offset = 0;
}
len -= info.tx_local.size;
if (skb->ip_summed == CHECKSUM_PARTIAL)
first_tx->flags |= XEN_NETTXF_csum_blank |
XEN_NETTXF_data_validated;
else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
first_tx->flags |= XEN_NETTXF_data_validated;
if (skb_shinfo(skb)->gso_size) {
struct xen_netif_extra_info *gso;
gso = (struct xen_netif_extra_info *)
RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
first_tx->flags |= XEN_NETTXF_extra_info;
gso->u.gso.size = skb_shinfo(skb)->gso_size;
gso->u.gso.type = (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) ?
XEN_NETIF_GSO_TYPE_TCPV6 :
XEN_NETIF_GSO_TYPE_TCPV4;
gso->u.gso.pad = 0;
gso->u.gso.features = 0;
gso->type = XEN_NETIF_EXTRA_TYPE_GSO;
gso->flags = 0;
}
xennet_make_txreqs(&info, page, offset, len);
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
xennet_make_txreqs(&info, skb_frag_page(frag),
skb_frag_off(frag),
skb_frag_size(frag));
}
first_tx->size = skb->len;
skb_tx_timestamp(skb);
xennet_mark_tx_pending(queue);
RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify);
if (notify)
notify_remote_via_irq(queue->tx_irq);
u64_stats_update_begin(&tx_stats->syncp);
tx_stats->bytes += skb->len;
tx_stats->packets++;
u64_stats_update_end(&tx_stats->syncp);
xennet_tx_buf_gc(queue);
if (!netfront_tx_slot_available(queue))
netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id));
spin_unlock_irqrestore(&queue->tx_lock, flags);
return NETDEV_TX_OK;
drop:
dev->stats.tx_dropped++;
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
static int xennet_close(struct net_device *dev)
{
struct netfront_info *np = netdev_priv(dev);
unsigned int num_queues = dev->real_num_tx_queues;
unsigned int i;
struct netfront_queue *queue;
netif_tx_stop_all_queues(np->netdev);
for (i = 0; i < num_queues; ++i) {
queue = &np->queues[i];
napi_disable(&queue->napi);
}
return 0;
}
static void xennet_destroy_queues(struct netfront_info *info)
{
unsigned int i;
for (i = 0; i < info->netdev->real_num_tx_queues; i++) {
struct netfront_queue *queue = &info->queues[i];
if (netif_running(info->netdev))
napi_disable(&queue->napi);
netif_napi_del(&queue->napi);
}
kfree(info->queues);
info->queues = NULL;
}
static void xennet_uninit(struct net_device *dev)
{
struct netfront_info *np = netdev_priv(dev);
xennet_destroy_queues(np);
}
static void xennet_set_rx_rsp_cons(struct netfront_queue *queue, RING_IDX val)
{
unsigned long flags;
spin_lock_irqsave(&queue->rx_cons_lock, flags);
queue->rx.rsp_cons = val;
queue->rx_rsp_unconsumed = XEN_RING_NR_UNCONSUMED_RESPONSES(&queue->rx);
spin_unlock_irqrestore(&queue->rx_cons_lock, flags);
}
static void xennet_move_rx_slot(struct netfront_queue *queue, struct sk_buff *skb,
grant_ref_t ref)
{
int new = xennet_rxidx(queue->rx.req_prod_pvt);
BUG_ON(queue->rx_skbs[new]);
queue->rx_skbs[new] = skb;
queue->grant_rx_ref[new] = ref;
RING_GET_REQUEST(&queue->rx, queue->rx.req_prod_pvt)->id = new;
RING_GET_REQUEST(&queue->rx, queue->rx.req_prod_pvt)->gref = ref;
queue->rx.req_prod_pvt++;
}
static int xennet_get_extras(struct netfront_queue *queue,
struct xen_netif_extra_info *extras,
RING_IDX rp)
{
struct xen_netif_extra_info extra;
struct device *dev = &queue->info->netdev->dev;
RING_IDX cons = queue->rx.rsp_cons;
int err = 0;
do {
struct sk_buff *skb;
grant_ref_t ref;
if (unlikely(cons + 1 == rp)) {
if (net_ratelimit())
dev_warn(dev, "Missing extra info\n");
err = -EBADR;
break;
}
RING_COPY_RESPONSE(&queue->rx, ++cons, &extra);
if (unlikely(!extra.type ||
extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
if (net_ratelimit())
dev_warn(dev, "Invalid extra type: %d\n",
extra.type);
err = -EINVAL;
} else {
extras[extra.type - 1] = extra;
}
skb = xennet_get_rx_skb(queue, cons);
ref = xennet_get_rx_ref(queue, cons);
xennet_move_rx_slot(queue, skb, ref);
} while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE);
xennet_set_rx_rsp_cons(queue, cons);
return err;
}
static u32 xennet_run_xdp(struct netfront_queue *queue, struct page *pdata,
struct xen_netif_rx_response *rx, struct bpf_prog *prog,
struct xdp_buff *xdp, bool *need_xdp_flush)
{
struct xdp_frame *xdpf;
u32 len = rx->status;
u32 act;
int err;
xdp_init_buff(xdp, XEN_PAGE_SIZE - XDP_PACKET_HEADROOM,
&queue->xdp_rxq);
xdp_prepare_buff(xdp, page_address(pdata), XDP_PACKET_HEADROOM,
len, false);
act = bpf_prog_run_xdp(prog, xdp);
switch (act) {
case XDP_TX:
get_page(pdata);
xdpf = xdp_convert_buff_to_frame(xdp);
err = xennet_xdp_xmit(queue->info->netdev, 1, &xdpf, 0);
if (unlikely(!err))
xdp_return_frame_rx_napi(xdpf);
else if (unlikely(err < 0))
trace_xdp_exception(queue->info->netdev, prog, act);
break;
case XDP_REDIRECT:
get_page(pdata);
err = xdp_do_redirect(queue->info->netdev, xdp, prog);
*need_xdp_flush = true;
if (unlikely(err))
trace_xdp_exception(queue->info->netdev, prog, act);
break;
case XDP_PASS:
case XDP_DROP:
break;
case XDP_ABORTED:
trace_xdp_exception(queue->info->netdev, prog, act);
break;
default:
bpf_warn_invalid_xdp_action(queue->info->netdev, prog, act);
}
return act;
}
static int xennet_get_responses(struct netfront_queue *queue,
struct netfront_rx_info *rinfo, RING_IDX rp,
struct sk_buff_head *list,
bool *need_xdp_flush)
{
struct xen_netif_rx_response *rx = &rinfo->rx, rx_local;
int max = XEN_NETIF_NR_SLOTS_MIN + (rx->status <= RX_COPY_THRESHOLD);
RING_IDX cons = queue->rx.rsp_cons;
struct sk_buff *skb = xennet_get_rx_skb(queue, cons);
struct xen_netif_extra_info *extras = rinfo->extras;
grant_ref_t ref = xennet_get_rx_ref(queue, cons);
struct device *dev = &queue->info->netdev->dev;
struct bpf_prog *xdp_prog;
struct xdp_buff xdp;
int slots = 1;
int err = 0;
u32 verdict;
if (rx->flags & XEN_NETRXF_extra_info) {
err = xennet_get_extras(queue, extras, rp);
if (!err) {
if (extras[XEN_NETIF_EXTRA_TYPE_XDP - 1].type) {
struct xen_netif_extra_info *xdp;
xdp = &extras[XEN_NETIF_EXTRA_TYPE_XDP - 1];
rx->offset = xdp->u.xdp.headroom;
}
}
cons = queue->rx.rsp_cons;
}
for (;;) {
if (ref == INVALID_GRANT_REF) {
if (net_ratelimit())
dev_warn(dev, "Bad rx response id %d.\n",
rx->id);
err = -EINVAL;
goto next;
}
if (unlikely(rx->status < 0 ||
rx->offset + rx->status > XEN_PAGE_SIZE)) {
if (net_ratelimit())
dev_warn(dev, "rx->offset: %u, size: %d\n",
rx->offset, rx->status);
xennet_move_rx_slot(queue, skb, ref);
err = -EINVAL;
goto next;
}
if (!gnttab_end_foreign_access_ref(ref)) {
dev_alert(dev,
"Grant still in use by backend domain\n");
queue->info->broken = true;
dev_alert(dev, "Disabled for further use\n");
return -EINVAL;
}
gnttab_release_grant_reference(&queue->gref_rx_head, ref);
rcu_read_lock();
xdp_prog = rcu_dereference(queue->xdp_prog);
if (xdp_prog) {
if (!(rx->flags & XEN_NETRXF_more_data)) {
verdict = xennet_run_xdp(queue,
skb_frag_page(&skb_shinfo(skb)->frags[0]),
rx, xdp_prog, &xdp, need_xdp_flush);
if (verdict != XDP_PASS)
err = -EINVAL;
} else {
err = -EINVAL;
}
}
rcu_read_unlock();
__skb_queue_tail(list, skb);
next:
if (!(rx->flags & XEN_NETRXF_more_data))
break;
if (cons + slots == rp) {
if (net_ratelimit())
dev_warn(dev, "Need more slots\n");
err = -ENOENT;
break;
}
RING_COPY_RESPONSE(&queue->rx, cons + slots, &rx_local);
rx = &rx_local;
skb = xennet_get_rx_skb(queue, cons + slots);
ref = xennet_get_rx_ref(queue, cons + slots);
slots++;
}
if (unlikely(slots > max)) {
if (net_ratelimit())
dev_warn(dev, "Too many slots\n");
err = -E2BIG;
}
if (unlikely(err))
xennet_set_rx_rsp_cons(queue, cons + slots);
return err;
}
static int xennet_set_skb_gso(struct sk_buff *skb,
struct xen_netif_extra_info *gso)
{
if (!gso->u.gso.size) {
if (net_ratelimit())
pr_warn("GSO size must not be zero\n");
return -EINVAL;
}
if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4 &&
gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV6) {
if (net_ratelimit())
pr_warn("Bad GSO type %d\n", gso->u.gso.type);
return -EINVAL;
}
skb_shinfo(skb)->gso_size = gso->u.gso.size;
skb_shinfo(skb)->gso_type =
(gso->u.gso.type == XEN_NETIF_GSO_TYPE_TCPV4) ?
SKB_GSO_TCPV4 :
SKB_GSO_TCPV6;
skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
skb_shinfo(skb)->gso_segs = 0;
return 0;
}
static int xennet_fill_frags(struct netfront_queue *queue,
struct sk_buff *skb,
struct sk_buff_head *list)
{
RING_IDX cons = queue->rx.rsp_cons;
struct sk_buff *nskb;
while ((nskb = __skb_dequeue(list))) {
struct xen_netif_rx_response rx;
skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
RING_COPY_RESPONSE(&queue->rx, ++cons, &rx);
if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) {
unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
BUG_ON(pull_to < skb_headlen(skb));
__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
}
if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) {
xennet_set_rx_rsp_cons(queue,
++cons + skb_queue_len(list));
kfree_skb(nskb);
return -ENOENT;
}
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
skb_frag_page(nfrag),
rx.offset, rx.status, PAGE_SIZE);
skb_shinfo(nskb)->nr_frags = 0;
kfree_skb(nskb);
}
xennet_set_rx_rsp_cons(queue, cons);
return 0;
}
static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
{
bool recalculate_partial_csum = false;
if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) {
struct netfront_info *np = netdev_priv(dev);
atomic_inc(&np->rx_gso_checksum_fixup);
skb->ip_summed = CHECKSUM_PARTIAL;
recalculate_partial_csum = true;
}
if (skb->ip_summed != CHECKSUM_PARTIAL)
return 0;
return skb_checksum_setup(skb, recalculate_partial_csum);
}
static int handle_incoming_queue(struct netfront_queue *queue,
struct sk_buff_head *rxq)
{
struct netfront_stats *rx_stats = this_cpu_ptr(queue->info->rx_stats);
int packets_dropped = 0;
struct sk_buff *skb;
while ((skb = __skb_dequeue(rxq)) != NULL) {
int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
if (pull_to > skb_headlen(skb))
__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
skb->protocol = eth_type_trans(skb, queue->info->netdev);
skb_reset_network_header(skb);
if (checksum_setup(queue->info->netdev, skb)) {
kfree_skb(skb);
packets_dropped++;
queue->info->netdev->stats.rx_errors++;
continue;
}
u64_stats_update_begin(&rx_stats->syncp);
rx_stats->packets++;
rx_stats->bytes += skb->len;
u64_stats_update_end(&rx_stats->syncp);
napi_gro_receive(&queue->napi, skb);
}
return packets_dropped;
}
static int xennet_poll(struct napi_struct *napi, int budget)
{
struct netfront_queue *queue = container_of(napi, struct netfront_queue, napi);
struct net_device *dev = queue->info->netdev;
struct sk_buff *skb;
struct netfront_rx_info rinfo;
struct xen_netif_rx_response *rx = &rinfo.rx;
struct xen_netif_extra_info *extras = rinfo.extras;
RING_IDX i, rp;
int work_done;
struct sk_buff_head rxq;
struct sk_buff_head errq;
struct sk_buff_head tmpq;
int err;
bool need_xdp_flush = false;
spin_lock(&queue->rx_lock);
skb_queue_head_init(&rxq);
skb_queue_head_init(&errq);
skb_queue_head_init(&tmpq);
rp = queue->rx.sring->rsp_prod;
if (RING_RESPONSE_PROD_OVERFLOW(&queue->rx, rp)) {
dev_alert(&dev->dev, "Illegal number of responses %u\n",
rp - queue->rx.rsp_cons);
queue->info->broken = true;
spin_unlock(&queue->rx_lock);
return 0;
}
rmb();
i = queue->rx.rsp_cons;
work_done = 0;
while ((i != rp) && (work_done < budget)) {
RING_COPY_RESPONSE(&queue->rx, i, rx);
memset(extras, 0, sizeof(rinfo.extras));
err = xennet_get_responses(queue, &rinfo, rp, &tmpq,
&need_xdp_flush);
if (unlikely(err)) {
if (queue->info->broken) {
spin_unlock(&queue->rx_lock);
return 0;
}
err:
while ((skb = __skb_dequeue(&tmpq)))
__skb_queue_tail(&errq, skb);
dev->stats.rx_errors++;
i = queue->rx.rsp_cons;
continue;
}
skb = __skb_dequeue(&tmpq);
if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) {
struct xen_netif_extra_info *gso;
gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
if (unlikely(xennet_set_skb_gso(skb, gso))) {
__skb_queue_head(&tmpq, skb);
xennet_set_rx_rsp_cons(queue,
queue->rx.rsp_cons +
skb_queue_len(&tmpq));
goto err;
}
}
NETFRONT_SKB_CB(skb)->pull_to = rx->status;
if (NETFRONT_SKB_CB(skb)->pull_to > RX_COPY_THRESHOLD)
NETFRONT_SKB_CB(skb)->pull_to = RX_COPY_THRESHOLD;
skb_frag_off_set(&skb_shinfo(skb)->frags[0], rx->offset);
skb_frag_size_set(&skb_shinfo(skb)->frags[0], rx->status);
skb->data_len = rx->status;
skb->len += rx->status;
if (unlikely(xennet_fill_frags(queue, skb, &tmpq)))
goto err;
if (rx->flags & XEN_NETRXF_csum_blank)
skb->ip_summed = CHECKSUM_PARTIAL;
else if (rx->flags & XEN_NETRXF_data_validated)
skb->ip_summed = CHECKSUM_UNNECESSARY;
__skb_queue_tail(&rxq, skb);
i = queue->rx.rsp_cons + 1;
xennet_set_rx_rsp_cons(queue, i);
work_done++;
}
if (need_xdp_flush)
xdp_do_flush();
__skb_queue_purge(&errq);
work_done -= handle_incoming_queue(queue, &rxq);
xennet_alloc_rx_buffers(queue);
if (work_done < budget) {
int more_to_do = 0;
napi_complete_done(napi, work_done);
RING_FINAL_CHECK_FOR_RESPONSES(&queue->rx, more_to_do);
if (more_to_do)
napi_schedule(napi);
}
spin_unlock(&queue->rx_lock);
return work_done;
}
static int xennet_change_mtu(struct net_device *dev, int mtu)
{
int max = xennet_can_sg(dev) ? XEN_NETIF_MAX_TX_SIZE : ETH_DATA_LEN;
if (mtu > max)
return -EINVAL;
dev->mtu = mtu;
return 0;
}
static void xennet_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot)
{
struct netfront_info *np = netdev_priv(dev);
int cpu;
for_each_possible_cpu(cpu) {
struct netfront_stats *rx_stats = per_cpu_ptr(np->rx_stats, cpu);
struct netfront_stats *tx_stats = per_cpu_ptr(np->tx_stats, cpu);
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
unsigned int start;
do {
start = u64_stats_fetch_begin(&tx_stats->syncp);
tx_packets = tx_stats->packets;
tx_bytes = tx_stats->bytes;
} while (u64_stats_fetch_retry(&tx_stats->syncp, start));
do {
start = u64_stats_fetch_begin(&rx_stats->syncp);
rx_packets = rx_stats->packets;
rx_bytes = rx_stats->bytes;
} while (u64_stats_fetch_retry(&rx_stats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
tot->rx_bytes += rx_bytes;
tot->tx_bytes += tx_bytes;
}
tot->rx_errors = dev->stats.rx_errors;
tot->tx_dropped = dev->stats.tx_dropped;
}
static void xennet_release_tx_bufs(struct netfront_queue *queue)
{
struct sk_buff *skb;
int i;
for (i = 0; i < NET_TX_RING_SIZE; i++) {
if (!queue->tx_skbs[i])
continue;
skb = queue->tx_skbs[i];
queue->tx_skbs[i] = NULL;
get_page(queue->grant_tx_page[i]);
gnttab_end_foreign_access(queue->grant_tx_ref[i],
queue->grant_tx_page[i]);
queue->grant_tx_page[i] = NULL;
queue->grant_tx_ref[i] = INVALID_GRANT_REF;
add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, i);
dev_kfree_skb_irq(skb);
}
}
static void xennet_release_rx_bufs(struct netfront_queue *queue)
{
int id, ref;
spin_lock_bh(&queue->rx_lock);
for (id = 0; id < NET_RX_RING_SIZE; id++) {
struct sk_buff *skb;
struct page *page;
skb = queue->rx_skbs[id];
if (!skb)
continue;
ref = queue->grant_rx_ref[id];
if (ref == INVALID_GRANT_REF)
continue;
page = skb_frag_page(&skb_shinfo(skb)->frags[0]);
get_page(page);
gnttab_end_foreign_access(ref, page);
queue->grant_rx_ref[id] = INVALID_GRANT_REF;
kfree_skb(skb);
}
spin_unlock_bh(&queue->rx_lock);
}
static netdev_features_t xennet_fix_features(struct net_device *dev,
netdev_features_t features)
{
struct netfront_info *np = netdev_priv(dev);
if (features & NETIF_F_SG &&
!xenbus_read_unsigned(np->xbdev->otherend, "feature-sg", 0))
features &= ~NETIF_F_SG;
if (features & NETIF_F_IPV6_CSUM &&
!xenbus_read_unsigned(np->xbdev->otherend,
"feature-ipv6-csum-offload", 0))
features &= ~NETIF_F_IPV6_CSUM;
if (features & NETIF_F_TSO &&
!xenbus_read_unsigned(np->xbdev->otherend, "feature-gso-tcpv4", 0))
features &= ~NETIF_F_TSO;
if (features & NETIF_F_TSO6 &&
!xenbus_read_unsigned(np->xbdev->otherend, "feature-gso-tcpv6", 0))
features &= ~NETIF_F_TSO6;
return features;
}
static int xennet_set_features(struct net_device *dev,
netdev_features_t features)
{
if (!(features & NETIF_F_SG) && dev->mtu > ETH_DATA_LEN) {
netdev_info(dev, "Reducing MTU because no SG offload");
dev->mtu = ETH_DATA_LEN;
}
return 0;
}
static bool xennet_handle_tx(struct netfront_queue *queue, unsigned int *eoi)
{
unsigned long flags;
if (unlikely(queue->info->broken))
return false;
spin_lock_irqsave(&queue->tx_lock, flags);
if (xennet_tx_buf_gc(queue))
*eoi = 0;
spin_unlock_irqrestore(&queue->tx_lock, flags);
return true;
}
static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id)
{
unsigned int eoiflag = XEN_EOI_FLAG_SPURIOUS;
if (likely(xennet_handle_tx(dev_id, &eoiflag)))
xen_irq_lateeoi(irq, eoiflag);
return IRQ_HANDLED;
}
static bool xennet_handle_rx(struct netfront_queue *queue, unsigned int *eoi)
{
unsigned int work_queued;
unsigned long flags;
if (unlikely(queue->info->broken))
return false;
spin_lock_irqsave(&queue->rx_cons_lock, flags);
work_queued = XEN_RING_NR_UNCONSUMED_RESPONSES(&queue->rx);
if (work_queued > queue->rx_rsp_unconsumed) {
queue->rx_rsp_unconsumed = work_queued;
*eoi = 0;
} else if (unlikely(work_queued < queue->rx_rsp_unconsumed)) {
const struct device *dev = &queue->info->netdev->dev;
spin_unlock_irqrestore(&queue->rx_cons_lock, flags);
dev_alert(dev, "RX producer index going backwards\n");
dev_alert(dev, "Disabled for further use\n");
queue->info->broken = true;
return false;
}
spin_unlock_irqrestore(&queue->rx_cons_lock, flags);
if (likely(netif_carrier_ok(queue->info->netdev) && work_queued))
napi_schedule(&queue->napi);
return true;
}
static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id)
{
unsigned int eoiflag = XEN_EOI_FLAG_SPURIOUS;
if (likely(xennet_handle_rx(dev_id, &eoiflag)))
xen_irq_lateeoi(irq, eoiflag);
return IRQ_HANDLED;
}
static irqreturn_t xennet_interrupt(int irq, void *dev_id)
{
unsigned int eoiflag = XEN_EOI_FLAG_SPURIOUS;
if (xennet_handle_tx(dev_id, &eoiflag) &&
xennet_handle_rx(dev_id, &eoiflag))
xen_irq_lateeoi(irq, eoiflag);
return IRQ_HANDLED;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
static void xennet_poll_controller(struct net_device *dev)
{
struct netfront_info *info = netdev_priv(dev);
unsigned int num_queues = dev->real_num_tx_queues;
unsigned int i;
if (info->broken)
return;
for (i = 0; i < num_queues; ++i)
xennet_interrupt(0, &info->queues[i]);
}
#endif
#define NETBACK_XDP_HEADROOM_DISABLE 0
#define NETBACK_XDP_HEADROOM_ENABLE 1
static int talk_to_netback_xdp(struct netfront_info *np, int xdp)
{
int err;
unsigned short headroom;
headroom = xdp ? XDP_PACKET_HEADROOM : 0;
err = xenbus_printf(XBT_NIL, np->xbdev->nodename,
"xdp-headroom", "%hu",
headroom);
if (err)
pr_warn("Error writing xdp-headroom\n");
return err;
}
static int xennet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
struct netlink_ext_ack *extack)
{
unsigned long max_mtu = XEN_PAGE_SIZE - XDP_PACKET_HEADROOM;
struct netfront_info *np = netdev_priv(dev);
struct bpf_prog *old_prog;
unsigned int i, err;
if (dev->mtu > max_mtu) {
netdev_warn(dev, "XDP requires MTU less than %lu\n", max_mtu);
return -EINVAL;
}
if (!np->netback_has_xdp_headroom)
return 0;
xenbus_switch_state(np->xbdev, XenbusStateReconfiguring);
err = talk_to_netback_xdp(np, prog ? NETBACK_XDP_HEADROOM_ENABLE :
NETBACK_XDP_HEADROOM_DISABLE);
if (err)
return err;
wait_event(module_wq,
xenbus_read_driver_state(np->xbdev->otherend) ==
XenbusStateReconfigured);
np->netfront_xdp_enabled = true;
old_prog = rtnl_dereference(np->queues[0].xdp_prog);
if (prog)
bpf_prog_add(prog, dev->real_num_tx_queues);
for (i = 0; i < dev->real_num_tx_queues; ++i)
rcu_assign_pointer(np->queues[i].xdp_prog, prog);
if (old_prog)
for (i = 0; i < dev->real_num_tx_queues; ++i)
bpf_prog_put(old_prog);
xenbus_switch_state(np->xbdev, XenbusStateConnected);
return 0;
}
static int xennet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
{
struct netfront_info *np = netdev_priv(dev);
if (np->broken)
return -ENODEV;
switch (xdp->command) {
case XDP_SETUP_PROG:
return xennet_xdp_set(dev, xdp->prog, xdp->extack);
default:
return -EINVAL;
}
}
static const struct net_device_ops xennet_netdev_ops = {
.ndo_uninit = xennet_uninit,
.ndo_open = xennet_open,
.ndo_stop = xennet_close,
.ndo_start_xmit = xennet_start_xmit,
.ndo_change_mtu = xennet_change_mtu,
.ndo_get_stats64 = xennet_get_stats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_fix_features = xennet_fix_features,
.ndo_set_features = xennet_set_features,
.ndo_select_queue = xennet_select_queue,
.ndo_bpf = xennet_xdp,
.ndo_xdp_xmit = xennet_xdp_xmit,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = xennet_poll_controller,
#endif
};
static void xennet_free_netdev(struct net_device *netdev)
{
struct netfront_info *np = netdev_priv(netdev);
free_percpu(np->rx_stats);
free_percpu(np->tx_stats);
free_netdev(netdev);
}
static struct net_device *xennet_create_dev(struct xenbus_device *dev)
{
int err;
struct net_device *netdev;
struct netfront_info *np;
netdev = alloc_etherdev_mq(sizeof(struct netfront_info), xennet_max_queues);
if (!netdev)
return ERR_PTR(-ENOMEM);
np = netdev_priv(netdev);
np->xbdev = dev;
np->queues = NULL;
err = -ENOMEM;
np->rx_stats = netdev_alloc_pcpu_stats(struct netfront_stats);
if (np->rx_stats == NULL)
goto exit;
np->tx_stats = netdev_alloc_pcpu_stats(struct netfront_stats);
if (np->tx_stats == NULL)
goto exit;
netdev->netdev_ops = &xennet_netdev_ops;
netdev->features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
NETIF_F_GSO_ROBUST;
netdev->hw_features = NETIF_F_SG |
NETIF_F_IPV6_CSUM |
NETIF_F_TSO | NETIF_F_TSO6;
netdev->features |= netdev->hw_features;
netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
NETDEV_XDP_ACT_NDO_XMIT;
netdev->ethtool_ops = &xennet_ethtool_ops;
netdev->min_mtu = ETH_MIN_MTU;
netdev->max_mtu = XEN_NETIF_MAX_TX_SIZE;
SET_NETDEV_DEV(netdev, &dev->dev);
np->netdev = netdev;
np->netfront_xdp_enabled = false;
netif_carrier_off(netdev);
do {
xenbus_switch_state(dev, XenbusStateInitialising);
err = wait_event_timeout(module_wq,
xenbus_read_driver_state(dev->otherend) !=
XenbusStateClosed &&
xenbus_read_driver_state(dev->otherend) !=
XenbusStateUnknown, XENNET_TIMEOUT);
} while (!err);
return netdev;
exit:
xennet_free_netdev(netdev);
return ERR_PTR(err);
}
static int netfront_probe(struct xenbus_device *dev,
const struct xenbus_device_id *id)
{
int err;
struct net_device *netdev;
struct netfront_info *info;
netdev = xennet_create_dev(dev);
if (IS_ERR(netdev)) {
err = PTR_ERR(netdev);
xenbus_dev_fatal(dev, err, "creating netdev");
return err;
}
info = netdev_priv(netdev);
dev_set_drvdata(&dev->dev, info);
#ifdef CONFIG_SYSFS
info->netdev->sysfs_groups[0] = &xennet_dev_group;
#endif
return 0;
}
static void xennet_end_access(int ref, void *page)
{
if (ref != INVALID_GRANT_REF)
gnttab_end_foreign_access(ref, virt_to_page(page));
}
static void xennet_disconnect_backend(struct netfront_info *info)
{
unsigned int i = 0;
unsigned int num_queues = info->netdev->real_num_tx_queues;
netif_carrier_off(info->netdev);
for (i = 0; i < num_queues && info->queues; ++i) {
struct netfront_queue *queue = &info->queues[i];
del_timer_sync(&queue->rx_refill_timer);
if (queue->tx_irq && (queue->tx_irq == queue->rx_irq))
unbind_from_irqhandler(queue->tx_irq, queue);
if (queue->tx_irq && (queue->tx_irq != queue->rx_irq)) {
unbind_from_irqhandler(queue->tx_irq, queue);
unbind_from_irqhandler(queue->rx_irq, queue);
}
queue->tx_evtchn = queue->rx_evtchn = 0;
queue->tx_irq = queue->rx_irq = 0;
if (netif_running(info->netdev))
napi_synchronize(&queue->napi);
xennet_release_tx_bufs(queue);
xennet_release_rx_bufs(queue);
gnttab_free_grant_references(queue->gref_tx_head);
gnttab_free_grant_references(queue->gref_rx_head);
xennet_end_access(queue->tx_ring_ref, queue->tx.sring);
xennet_end_access(queue->rx_ring_ref, queue->rx.sring);
queue->tx_ring_ref = INVALID_GRANT_REF;
queue->rx_ring_ref = INVALID_GRANT_REF;
queue->tx.sring = NULL;
queue->rx.sring = NULL;
page_pool_destroy(queue->page_pool);
}
}
static int netfront_resume(struct xenbus_device *dev)
{
struct netfront_info *info = dev_get_drvdata(&dev->dev);
dev_dbg(&dev->dev, "%s\n", dev->nodename);
netif_tx_lock_bh(info->netdev);
netif_device_detach(info->netdev);
netif_tx_unlock_bh(info->netdev);
xennet_disconnect_backend(info);
rtnl_lock();
if (info->queues)
xennet_destroy_queues(info);
rtnl_unlock();
return 0;
}
static int xen_net_read_mac(struct xenbus_device *dev, u8 mac[])
{
char *s, *e, *macstr;
int i;
macstr = s = xenbus_read(XBT_NIL, dev->nodename, "mac", NULL);
if (IS_ERR(macstr))
return PTR_ERR(macstr);
for (i = 0; i < ETH_ALEN; i++) {
mac[i] = simple_strtoul(s, &e, 16);
if ((s == e) || (*e != ((i == ETH_ALEN-1) ? '\0' : ':'))) {
kfree(macstr);
return -ENOENT;
}
s = e+1;
}
kfree(macstr);
return 0;
}
static int setup_netfront_single(struct netfront_queue *queue)
{
int err;
err = xenbus_alloc_evtchn(queue->info->xbdev, &queue->tx_evtchn);
if (err < 0)
goto fail;
err = bind_evtchn_to_irqhandler_lateeoi(queue->tx_evtchn,
xennet_interrupt, 0,
queue->info->netdev->name,
queue);
if (err < 0)
goto bind_fail;
queue->rx_evtchn = queue->tx_evtchn;
queue->rx_irq = queue->tx_irq = err;
return 0;
bind_fail:
xenbus_free_evtchn(queue->info->xbdev, queue->tx_evtchn);
queue->tx_evtchn = 0;
fail:
return err;
}
static int setup_netfront_split(struct netfront_queue *queue)
{
int err;
err = xenbus_alloc_evtchn(queue->info->xbdev, &queue->tx_evtchn);
if (err < 0)
goto fail;
err = xenbus_alloc_evtchn(queue->info->xbdev, &queue->rx_evtchn);
if (err < 0)
goto alloc_rx_evtchn_fail;
snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name),
"%s-tx", queue->name);
err = bind_evtchn_to_irqhandler_lateeoi(queue->tx_evtchn,
xennet_tx_interrupt, 0,
queue->tx_irq_name, queue);
if (err < 0)
goto bind_tx_fail;
queue->tx_irq = err;
snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name),
"%s-rx", queue->name);
err = bind_evtchn_to_irqhandler_lateeoi(queue->rx_evtchn,
xennet_rx_interrupt, 0,
queue->rx_irq_name, queue);
if (err < 0)
goto bind_rx_fail;
queue->rx_irq = err;
return 0;
bind_rx_fail:
unbind_from_irqhandler(queue->tx_irq, queue);
queue->tx_irq = 0;
bind_tx_fail:
xenbus_free_evtchn(queue->info->xbdev, queue->rx_evtchn);
queue->rx_evtchn = 0;
alloc_rx_evtchn_fail:
xenbus_free_evtchn(queue->info->xbdev, queue->tx_evtchn);
queue->tx_evtchn = 0;
fail:
return err;
}
static int setup_netfront(struct xenbus_device *dev,
struct netfront_queue *queue, unsigned int feature_split_evtchn)
{
struct xen_netif_tx_sring *txs;
struct xen_netif_rx_sring *rxs;
int err;
queue->tx_ring_ref = INVALID_GRANT_REF;
queue->rx_ring_ref = INVALID_GRANT_REF;
queue->rx.sring = NULL;
queue->tx.sring = NULL;
err = xenbus_setup_ring(dev, GFP_NOIO | __GFP_HIGH, (void **)&txs,
1, &queue->tx_ring_ref);
if (err)
goto fail;
XEN_FRONT_RING_INIT(&queue->tx, txs, XEN_PAGE_SIZE);
err = xenbus_setup_ring(dev, GFP_NOIO | __GFP_HIGH, (void **)&rxs,
1, &queue->rx_ring_ref);
if (err)
goto fail;
XEN_FRONT_RING_INIT(&queue->rx, rxs, XEN_PAGE_SIZE);
if (feature_split_evtchn)
err = setup_netfront_split(queue);
if (!feature_split_evtchn || err)
err = setup_netfront_single(queue);
if (err)
goto fail;
return 0;
fail:
xenbus_teardown_ring((void **)&queue->rx.sring, 1, &queue->rx_ring_ref);
xenbus_teardown_ring((void **)&queue->tx.sring, 1, &queue->tx_ring_ref);
return err;
}
static int xennet_init_queue(struct netfront_queue *queue)
{
unsigned short i;
int err = 0;
char *devid;
spin_lock_init(&queue->tx_lock);
spin_lock_init(&queue->rx_lock);
spin_lock_init(&queue->rx_cons_lock);
timer_setup(&queue->rx_refill_timer, rx_refill_timeout, 0);
devid = strrchr(queue->info->xbdev->nodename, '/') + 1;
snprintf(queue->name, sizeof(queue->name), "vif%s-q%u",
devid, queue->id);
queue->tx_skb_freelist = 0;
queue->tx_pend_queue = TX_LINK_NONE;
for (i = 0; i < NET_TX_RING_SIZE; i++) {
queue->tx_link[i] = i + 1;
queue->grant_tx_ref[i] = INVALID_GRANT_REF;
queue->grant_tx_page[i] = NULL;
}
queue->tx_link[NET_TX_RING_SIZE - 1] = TX_LINK_NONE;
for (i = 0; i < NET_RX_RING_SIZE; i++) {
queue->rx_skbs[i] = NULL;
queue->grant_rx_ref[i] = INVALID_GRANT_REF;
}
if (gnttab_alloc_grant_references(NET_TX_RING_SIZE,
&queue->gref_tx_head) < 0) {
pr_alert("can't alloc tx grant refs\n");
err = -ENOMEM;
goto exit;
}
if (gnttab_alloc_grant_references(NET_RX_RING_SIZE,
&queue->gref_rx_head) < 0) {
pr_alert("can't alloc rx grant refs\n");
err = -ENOMEM;
goto exit_free_tx;
}
return 0;
exit_free_tx:
gnttab_free_grant_references(queue->gref_tx_head);
exit:
return err;
}
static int write_queue_xenstore_keys(struct netfront_queue *queue,
struct xenbus_transaction *xbt, int write_hierarchical)
{
struct xenbus_device *dev = queue->info->xbdev;
int err;
const char *message;
char *path;
size_t pathsize;
if (write_hierarchical) {
pathsize = strlen(dev->nodename) + 10;
path = kzalloc(pathsize, GFP_KERNEL);
if (!path) {
err = -ENOMEM;
message = "out of memory while writing ring references";
goto error;
}
snprintf(path, pathsize, "%s/queue-%u",
dev->nodename, queue->id);
} else {
path = (char *)dev->nodename;
}
err = xenbus_printf(*xbt, path, "tx-ring-ref", "%u",
queue->tx_ring_ref);
if (err) {
message = "writing tx-ring-ref";
goto error;
}
err = xenbus_printf(*xbt, path, "rx-ring-ref", "%u",
queue->rx_ring_ref);
if (err) {
message = "writing rx-ring-ref";
goto error;
}
if (queue->tx_evtchn == queue->rx_evtchn) {
err = xenbus_printf(*xbt, path,
"event-channel", "%u", queue->tx_evtchn);
if (err) {
message = "writing event-channel";
goto error;
}
} else {
err = xenbus_printf(*xbt, path,
"event-channel-tx", "%u", queue->tx_evtchn);
if (err) {
message = "writing event-channel-tx";
goto error;
}
err = xenbus_printf(*xbt, path,
"event-channel-rx", "%u", queue->rx_evtchn);
if (err) {
message = "writing event-channel-rx";
goto error;
}
}
if (write_hierarchical)
kfree(path);
return 0;
error:
if (write_hierarchical)
kfree(path);
xenbus_dev_fatal(dev, err, "%s", message);
return err;
}
static int xennet_create_page_pool(struct netfront_queue *queue)
{
int err;
struct page_pool_params pp_params = {
.order = 0,
.flags = 0,
.pool_size = NET_RX_RING_SIZE,
.nid = NUMA_NO_NODE,
.dev = &queue->info->netdev->dev,
.offset = XDP_PACKET_HEADROOM,
.max_len = XEN_PAGE_SIZE - XDP_PACKET_HEADROOM,
};
queue->page_pool = page_pool_create(&pp_params);
if (IS_ERR(queue->page_pool)) {
err = PTR_ERR(queue->page_pool);
queue->page_pool = NULL;
return err;
}
err = xdp_rxq_info_reg(&queue->xdp_rxq, queue->info->netdev,
queue->id, 0);
if (err) {
netdev_err(queue->info->netdev, "xdp_rxq_info_reg failed\n");
goto err_free_pp;
}
err = xdp_rxq_info_reg_mem_model(&queue->xdp_rxq,
MEM_TYPE_PAGE_POOL, queue->page_pool);
if (err) {
netdev_err(queue->info->netdev, "xdp_rxq_info_reg_mem_model failed\n");
goto err_unregister_rxq;
}
return 0;
err_unregister_rxq:
xdp_rxq_info_unreg(&queue->xdp_rxq);
err_free_pp:
page_pool_destroy(queue->page_pool);
queue->page_pool = NULL;
return err;
}
static int xennet_create_queues(struct netfront_info *info,
unsigned int *num_queues)
{
unsigned int i;
int ret;
info->queues = kcalloc(*num_queues, sizeof(struct netfront_queue),
GFP_KERNEL);
if (!info->queues)
return -ENOMEM;
for (i = 0; i < *num_queues; i++) {
struct netfront_queue *queue = &info->queues[i];
queue->id = i;
queue->info = info;
ret = xennet_init_queue(queue);
if (ret < 0) {
dev_warn(&info->xbdev->dev,
"only created %d queues\n", i);
*num_queues = i;
break;
}
ret = xennet_create_page_pool(queue);
if (ret < 0) {
dev_err(&info->xbdev->dev, "can't allocate page pool\n");
*num_queues = i;
return ret;
}
netif_napi_add(queue->info->netdev, &queue->napi, xennet_poll);
if (netif_running(info->netdev))
napi_enable(&queue->napi);
}
netif_set_real_num_tx_queues(info->netdev, *num_queues);
if (*num_queues == 0) {
dev_err(&info->xbdev->dev, "no queues\n");
return -EINVAL;
}
return 0;
}
static int talk_to_netback(struct xenbus_device *dev,
struct netfront_info *info)
{
const char *message;
struct xenbus_transaction xbt;
int err;
unsigned int feature_split_evtchn;
unsigned int i = 0;
unsigned int max_queues = 0;
struct netfront_queue *queue = NULL;
unsigned int num_queues = 1;
u8 addr[ETH_ALEN];
info->netdev->irq = 0;
info->bounce = !xennet_trusted ||
!xenbus_read_unsigned(dev->nodename, "trusted", 1);
max_queues = xenbus_read_unsigned(info->xbdev->otherend,
"multi-queue-max-queues", 1);
num_queues = min(max_queues, xennet_max_queues);
feature_split_evtchn = xenbus_read_unsigned(info->xbdev->otherend,
"feature-split-event-channels", 0);
err = xen_net_read_mac(dev, addr);
if (err) {
xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename);
goto out_unlocked;
}
eth_hw_addr_set(info->netdev, addr);
info->netback_has_xdp_headroom = xenbus_read_unsigned(info->xbdev->otherend,
"feature-xdp-headroom", 0);
if (info->netback_has_xdp_headroom) {
err = talk_to_netback_xdp(info, info->netfront_xdp_enabled ?
NETBACK_XDP_HEADROOM_ENABLE :
NETBACK_XDP_HEADROOM_DISABLE);
if (err)
goto out_unlocked;
}
rtnl_lock();
if (info->queues)
xennet_destroy_queues(info);
info->broken = false;
err = xennet_create_queues(info, &num_queues);
if (err < 0) {
xenbus_dev_fatal(dev, err, "creating queues");
kfree(info->queues);
info->queues = NULL;
goto out;
}
rtnl_unlock();
for (i = 0; i < num_queues; ++i) {
queue = &info->queues[i];
err = setup_netfront(dev, queue, feature_split_evtchn);
if (err)
goto destroy_ring;
}
again:
err = xenbus_transaction_start(&xbt);
if (err) {
xenbus_dev_fatal(dev, err, "starting transaction");
goto destroy_ring;
}
if (xenbus_exists(XBT_NIL,
info->xbdev->otherend, "multi-queue-max-queues")) {
err = xenbus_printf(xbt, dev->nodename,
"multi-queue-num-queues", "%u", num_queues);
if (err) {
message = "writing multi-queue-num-queues";
goto abort_transaction_no_dev_fatal;
}
}
if (num_queues == 1) {
err = write_queue_xenstore_keys(&info->queues[0], &xbt, 0);
if (err)
goto abort_transaction_no_dev_fatal;
} else {
for (i = 0; i < num_queues; ++i) {
queue = &info->queues[i];
err = write_queue_xenstore_keys(queue, &xbt, 1);
if (err)
goto abort_transaction_no_dev_fatal;
}
}
err = xenbus_printf(xbt, dev->nodename, "request-rx-copy", "%u",
1);
if (err) {
message = "writing request-rx-copy";
goto abort_transaction;
}
err = xenbus_printf(xbt, dev->nodename, "feature-rx-notify", "%d", 1);
if (err) {
message = "writing feature-rx-notify";
goto abort_transaction;
}
err = xenbus_printf(xbt, dev->nodename, "feature-sg", "%d", 1);
if (err) {
message = "writing feature-sg";
goto abort_transaction;
}
err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv4", "%d", 1);
if (err) {
message = "writing feature-gso-tcpv4";
goto abort_transaction;
}
err = xenbus_write(xbt, dev->nodename, "feature-gso-tcpv6", "1");
if (err) {
message = "writing feature-gso-tcpv6";
goto abort_transaction;
}
err = xenbus_write(xbt, dev->nodename, "feature-ipv6-csum-offload",
"1");
if (err) {
message = "writing feature-ipv6-csum-offload";
goto abort_transaction;
}
err = xenbus_transaction_end(xbt, 0);
if (err) {
if (err == -EAGAIN)
goto again;
xenbus_dev_fatal(dev, err, "completing transaction");
goto destroy_ring;
}
return 0;
abort_transaction:
xenbus_dev_fatal(dev, err, "%s", message);
abort_transaction_no_dev_fatal:
xenbus_transaction_end(xbt, 1);
destroy_ring:
xennet_disconnect_backend(info);
rtnl_lock();
xennet_destroy_queues(info);
out:
rtnl_unlock();
out_unlocked:
device_unregister(&dev->dev);
return err;
}
static int xennet_connect(struct net_device *dev)
{
struct netfront_info *np = netdev_priv(dev);
unsigned int num_queues = 0;
int err;
unsigned int j = 0;
struct netfront_queue *queue = NULL;
if (!xenbus_read_unsigned(np->xbdev->otherend, "feature-rx-copy", 0)) {
dev_info(&dev->dev,
"backend does not support copying receive path\n");
return -ENODEV;
}
err = talk_to_netback(np->xbdev, np);
if (err)
return err;
if (np->netback_has_xdp_headroom)
pr_info("backend supports XDP headroom\n");
if (np->bounce)
dev_info(&np->xbdev->dev,
"bouncing transmitted data to zeroed pages\n");
num_queues = dev->real_num_tx_queues;
if (dev->reg_state == NETREG_UNINITIALIZED) {
err = register_netdev(dev);
if (err) {
pr_warn("%s: register_netdev err=%d\n", __func__, err);
device_unregister(&np->xbdev->dev);
return err;
}
}
rtnl_lock();
netdev_update_features(dev);
rtnl_unlock();
netif_tx_lock_bh(np->netdev);
netif_device_attach(np->netdev);
netif_tx_unlock_bh(np->netdev);
netif_carrier_on(np->netdev);
for (j = 0; j < num_queues; ++j) {
queue = &np->queues[j];
notify_remote_via_irq(queue->tx_irq);
if (queue->tx_irq != queue->rx_irq)
notify_remote_via_irq(queue->rx_irq);
spin_lock_bh(&queue->rx_lock);
xennet_alloc_rx_buffers(queue);
spin_unlock_bh(&queue->rx_lock);
}
return 0;
}
static void netback_changed(struct xenbus_device *dev,
enum xenbus_state backend_state)
{
struct netfront_info *np = dev_get_drvdata(&dev->dev);
struct net_device *netdev = np->netdev;
dev_dbg(&dev->dev, "%s\n", xenbus_strstate(backend_state));
wake_up_all(&module_wq);
switch (backend_state) {
case XenbusStateInitialising:
case XenbusStateInitialised:
case XenbusStateReconfiguring:
case XenbusStateReconfigured:
case XenbusStateUnknown:
break;
case XenbusStateInitWait:
if (dev->state != XenbusStateInitialising)
break;
if (xennet_connect(netdev) != 0)
break;
xenbus_switch_state(dev, XenbusStateConnected);
break;
case XenbusStateConnected:
netdev_notify_peers(netdev);
break;
case XenbusStateClosed:
if (dev->state == XenbusStateClosed)
break;
fallthrough;
case XenbusStateClosing:
xenbus_frontend_closed(dev);
break;
}
}
static const struct xennet_stat {
char name[ETH_GSTRING_LEN];
u16 offset;
} xennet_stats[] = {
{
"rx_gso_checksum_fixup",
offsetof(struct netfront_info, rx_gso_checksum_fixup)
},
};
static int xennet_get_sset_count(struct net_device *dev, int string_set)
{
switch (string_set) {
case ETH_SS_STATS:
return ARRAY_SIZE(xennet_stats);
default:
return -EINVAL;
}
}
static void xennet_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 * data)
{
void *np = netdev_priv(dev);
int i;
for (i = 0; i < ARRAY_SIZE(xennet_stats); i++)
data[i] = atomic_read((atomic_t *)(np + xennet_stats[i].offset));
}
static void xennet_get_strings(struct net_device *dev, u32 stringset, u8 * data)
{
int i;
switch (stringset) {
case ETH_SS_STATS:
for (i = 0; i < ARRAY_SIZE(xennet_stats); i++)
memcpy(data + i * ETH_GSTRING_LEN,
xennet_stats[i].name, ETH_GSTRING_LEN);
break;
}
}
static const struct ethtool_ops xennet_ethtool_ops =
{
.get_link = ethtool_op_get_link,
.get_sset_count = xennet_get_sset_count,
.get_ethtool_stats = xennet_get_ethtool_stats,
.get_strings = xennet_get_strings,
.get_ts_info = ethtool_op_get_ts_info,
};
#ifdef CONFIG_SYSFS
static ssize_t show_rxbuf(struct device *dev,
struct device_attribute *attr, char *buf)
{
return sprintf(buf, "%lu\n", NET_RX_RING_SIZE);
}
static ssize_t store_rxbuf(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t len)
{
char *endp;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
simple_strtoul(buf, &endp, 0);
if (endp == buf)
return -EBADMSG;
return len;
}
static DEVICE_ATTR(rxbuf_min, 0644, show_rxbuf, store_rxbuf);
static DEVICE_ATTR(rxbuf_max, 0644, show_rxbuf, store_rxbuf);
static DEVICE_ATTR(rxbuf_cur, 0444, show_rxbuf, NULL);
static struct attribute *xennet_dev_attrs[] = {
&dev_attr_rxbuf_min.attr,
&dev_attr_rxbuf_max.attr,
&dev_attr_rxbuf_cur.attr,
NULL
};
static const struct attribute_group xennet_dev_group = {
.attrs = xennet_dev_attrs
};
#endif /* CONFIG_SYSFS */
static void xennet_bus_close(struct xenbus_device *dev)
{
int ret;
if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed)
return;
do {
xenbus_switch_state(dev, XenbusStateClosing);
ret = wait_event_timeout(module_wq,
xenbus_read_driver_state(dev->otherend) ==
XenbusStateClosing ||
xenbus_read_driver_state(dev->otherend) ==
XenbusStateClosed ||
xenbus_read_driver_state(dev->otherend) ==
XenbusStateUnknown,
XENNET_TIMEOUT);
} while (!ret);
if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed)
return;
do {
xenbus_switch_state(dev, XenbusStateClosed);
ret = wait_event_timeout(module_wq,
xenbus_read_driver_state(dev->otherend) ==
XenbusStateClosed ||
xenbus_read_driver_state(dev->otherend) ==
XenbusStateUnknown,
XENNET_TIMEOUT);
} while (!ret);
}
static void xennet_remove(struct xenbus_device *dev)
{
struct netfront_info *info = dev_get_drvdata(&dev->dev);
xennet_bus_close(dev);
xennet_disconnect_backend(info);
if (info->netdev->reg_state == NETREG_REGISTERED)
unregister_netdev(info->netdev);
if (info->queues) {
rtnl_lock();
xennet_destroy_queues(info);
rtnl_unlock();
}
xennet_free_netdev(info->netdev);
}
static const struct xenbus_device_id netfront_ids[] = {
{ "vif" },
{ "" }
};
static struct xenbus_driver netfront_driver = {
.ids = netfront_ids,
.probe = netfront_probe,
.remove = xennet_remove,
.resume = netfront_resume,
.otherend_changed = netback_changed,
};
static int __init netif_init(void)
{
if (!xen_domain())
return -ENODEV;
if (!xen_has_pv_nic_devices())
return -ENODEV;
pr_info("Initialising Xen virtual ethernet driver\n");
if (xennet_max_queues == 0)
xennet_max_queues = min_t(unsigned int, MAX_QUEUES_DEFAULT,
num_online_cpus());
return xenbus_register_frontend(&netfront_driver);
}
module_init(netif_init);
static void __exit netif_exit(void)
{
xenbus_unregister_driver(&netfront_driver);
}
module_exit(netif_exit);
MODULE_DESCRIPTION("Xen virtual network device frontend");
MODULE_LICENSE("GPL");
MODULE_ALIAS("xen:vif");
MODULE_ALIAS("xennet"