index 62898910708a6ed7451cbbb81e9874f83cd87c8c..a6fcf15adc4ff3d36d928f44cc0ac1f49d249820 100644 (file)
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
u64 rx_packets;
};
+/* Internal representation of a send virtqueue */
+struct send_queue {
+ /* Virtqueue associated with this send _queue */
+ struct virtqueue *vq;
+
+ /* TX: fragments + linear part + virtio header */
+ struct scatterlist sg[MAX_SKB_FRAGS + 2];
+
+ /* Name of the send queue: output.$index */
+ char name[40];
+};
+
+/* Internal representation of a receive virtqueue */
+struct receive_queue {
+ /* Virtqueue associated with this receive_queue */
+ struct virtqueue *vq;
+
+ struct napi_struct napi;
+
+ /* Number of input buffers, and max we've ever had. */
+ unsigned int num, max;
+
+ /* Chain pages by the private ptr. */
+ struct page *pages;
+
+ /* RX: fragments + linear part + virtio header */
+ struct scatterlist sg[MAX_SKB_FRAGS + 2];
+
+ /* Name of this receive queue: input.$index */
+ char name[40];
+};
+
struct virtnet_info {
struct virtio_device *vdev;
- struct virtqueue *rvq, *svq, *cvq;
+ struct virtqueue *cvq;
struct net_device *dev;
- struct napi_struct napi;
+ struct send_queue *sq;
+ struct receive_queue *rq;
unsigned int status;
- /* Number of input buffers, and max we've ever had. */
- unsigned int num, max;
+ /* Max # of queue pairs supported by the device */
+ u16 max_queue_pairs;
+
+ /* # of queue pairs currently used by the driver */
+ u16 curr_queue_pairs;
/* I like... big packets and I cannot lie! */
bool big_packets;
/* Host will merge rx buffers for big packets (shake it! shake it!) */
bool mergeable_rx_bufs;
+ /* Has control virtqueue */
+ bool has_cvq;
+
/* enable config space updates */
bool config_enable;
/* Lock for config space updates */
struct mutex config_lock;
- /* Chain pages by the private ptr. */
- struct page *pages;
-
- /* fragments + linear part + virtio header */
- struct scatterlist rx_sg[MAX_SKB_FRAGS + 2];
- struct scatterlist tx_sg[MAX_SKB_FRAGS + 2];
+ /* Does the affinity hint is set for virtqueues? */
+ bool affinity_hint_set;
};
struct skb_vnet_hdr {
char padding[6];
};
+/* Converting between virtqueue no. and kernel tx/rx queue no.
+ * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq
+ */
+static int vq2txq(struct virtqueue *vq)
+{
+ return (virtqueue_get_queue_index(vq) - 1) / 2;
+}
+
+static int txq2vq(int txq)
+{
+ return txq * 2 + 1;
+}
+
+static int vq2rxq(struct virtqueue *vq)
+{
+ return virtqueue_get_queue_index(vq) / 2;
+}
+
+static int rxq2vq(int rxq)
+{
+ return rxq * 2;
+}
+
static inline struct skb_vnet_hdr *skb_vnet_hdr(struct sk_buff *skb)
{
return (struct skb_vnet_hdr *)skb->cb;
* private is used to chain pages for big packets, put the whole
* most recent used list in the beginning for reuse
*/
-static void give_pages(struct virtnet_info *vi, struct page *page)
+static void give_pages(struct receive_queue *rq, struct page *page)
{
struct page *end;
- /* Find end of list, sew whole thing into vi->pages. */
+ /* Find end of list, sew whole thing into vi->rq.pages. */
for (end = page; end->private; end = (struct page *)end->private);
- end->private = (unsigned long)vi->pages;
- vi->pages = page;
+ end->private = (unsigned long)rq->pages;
+ rq->pages = page;
}
-static struct page *get_a_page(struct virtnet_info *vi, gfp_t gfp_mask)
+static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
{
- struct page *p = vi->pages;
+ struct page *p = rq->pages;
if (p) {
- vi->pages = (struct page *)p->private;
+ rq->pages = (struct page *)p->private;
/* clear private here, it is used to chain pages */
p->private = 0;
} else
return p;
}
-static void skb_xmit_done(struct virtqueue *svq)
+static void skb_xmit_done(struct virtqueue *vq)
{
- struct virtnet_info *vi = svq->vdev->priv;
+ struct virtnet_info *vi = vq->vdev->priv;
/* Suppress further interrupts. */
- virtqueue_disable_cb(svq);
+ virtqueue_disable_cb(vq);
/* We were probably waiting for more output buffers. */
- netif_wake_queue(vi->dev);
+ netif_wake_subqueue(vi->dev, vq2txq(vq));
}
static void set_skb_frag(struct sk_buff *skb, struct page *page,
}
/* Called from bottom half context */
-static struct sk_buff *page_to_skb(struct virtnet_info *vi,
+static struct sk_buff *page_to_skb(struct receive_queue *rq,
struct page *page, unsigned int len)
{
+ struct virtnet_info *vi = rq->vq->vdev->priv;
struct sk_buff *skb;
struct skb_vnet_hdr *hdr;
unsigned int copy, hdr_len, offset;
* the case of a broken device.
*/
if (unlikely(len > MAX_SKB_FRAGS * PAGE_SIZE)) {
- if (net_ratelimit())
- pr_debug("%s: too much data\n", skb->dev->name);
+ net_dbg_ratelimited("%s: too much data\n", skb->dev->name);
dev_kfree_skb(skb);
return NULL;
}
}
if (page)
- give_pages(vi, page);
+ give_pages(rq, page);
return skb;
}
-static int receive_mergeable(struct virtnet_info *vi, struct sk_buff *skb)
+static int receive_mergeable(struct receive_queue *rq, struct sk_buff *skb)
{
struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
struct page *page;
skb->dev->stats.rx_length_errors++;
return -EINVAL;
}
- page = virtqueue_get_buf(vi->rvq, &len);
+ page = virtqueue_get_buf(rq->vq, &len);
if (!page) {
pr_debug("%s: rx error: %d buffers missing\n",
skb->dev->name, hdr->mhdr.num_buffers);
set_skb_frag(skb, page, 0, &len);
- --vi->num;
+ --rq->num;
}
return 0;
}
-static void receive_buf(struct net_device *dev, void *buf, unsigned int len)
+static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
{
- struct virtnet_info *vi = netdev_priv(dev);
+ struct virtnet_info *vi = rq->vq->vdev->priv;
+ struct net_device *dev = vi->dev;
struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
struct sk_buff *skb;
struct page *page;
pr_debug("%s: short packet %i\n", dev->name, len);
dev->stats.rx_length_errors++;
if (vi->mergeable_rx_bufs || vi->big_packets)
- give_pages(vi, buf);
+ give_pages(rq, buf);
else
dev_kfree_skb(buf);
return;
skb_trim(skb, len);
} else {
page = buf;
- skb = page_to_skb(vi, page, len);
+ skb = page_to_skb(rq, page, len);
if (unlikely(!skb)) {
dev->stats.rx_dropped++;
- give_pages(vi, page);
+ give_pages(rq, page);
return;
}
if (vi->mergeable_rx_bufs)
- if (receive_mergeable(vi, skb)) {
+ if (receive_mergeable(rq, skb)) {
dev_kfree_skb(skb);
return;
}
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
break;
default:
- if (net_ratelimit())
- printk(KERN_WARNING "%s: bad gso type %u.\n",
- dev->name, hdr->hdr.gso_type);
+ net_warn_ratelimited("%s: bad gso type %u.\n",
+ dev->name, hdr->hdr.gso_type);
goto frame_err;
}
skb_shinfo(skb)->gso_size = hdr->hdr.gso_size;
if (skb_shinfo(skb)->gso_size == 0) {
- if (net_ratelimit())
- printk(KERN_WARNING "%s: zero gso size.\n",
- dev->name);
+ net_warn_ratelimited("%s: zero gso size.\n", dev->name);
goto frame_err;
}
dev_kfree_skb(skb);
}
-static int add_recvbuf_small(struct virtnet_info *vi, gfp_t gfp)
+static int add_recvbuf_small(struct receive_queue *rq, gfp_t gfp)
{
+ struct virtnet_info *vi = rq->vq->vdev->priv;
struct sk_buff *skb;
struct skb_vnet_hdr *hdr;
int err;
skb_put(skb, MAX_PACKET_LEN);
hdr = skb_vnet_hdr(skb);
- sg_set_buf(vi->rx_sg, &hdr->hdr, sizeof hdr->hdr);
+ sg_set_buf(rq->sg, &hdr->hdr, sizeof hdr->hdr);
- skb_to_sgvec(skb, vi->rx_sg + 1, 0, skb->len);
+ skb_to_sgvec(skb, rq->sg + 1, 0, skb->len);
- err = virtqueue_add_buf(vi->rvq, vi->rx_sg, 0, 2, skb, gfp);
+ err = virtqueue_add_buf(rq->vq, rq->sg, 0, 2, skb, gfp);
if (err < 0)
dev_kfree_skb(skb);
return err;
}
-static int add_recvbuf_big(struct virtnet_info *vi, gfp_t gfp)
+static int add_recvbuf_big(struct receive_queue *rq, gfp_t gfp)
{
struct page *first, *list = NULL;
char *p;
int i, err, offset;
- /* page in vi->rx_sg[MAX_SKB_FRAGS + 1] is list tail */
+ /* page in rq->sg[MAX_SKB_FRAGS + 1] is list tail */
for (i = MAX_SKB_FRAGS + 1; i > 1; --i) {
- first = get_a_page(vi, gfp);
+ first = get_a_page(rq, gfp);
if (!first) {
if (list)
- give_pages(vi, list);
+ give_pages(rq, list);
return -ENOMEM;
}
- sg_set_buf(&vi->rx_sg[i], page_address(first), PAGE_SIZE);
+ sg_set_buf(&rq->sg[i], page_address(first), PAGE_SIZE);
/* chain new page in list head to match sg */
first->private = (unsigned long)list;
list = first;
}
- first = get_a_page(vi, gfp);
+ first = get_a_page(rq, gfp);
if (!first) {
- give_pages(vi, list);
+ give_pages(rq, list);
return -ENOMEM;
}
p = page_address(first);
- /* vi->rx_sg[0], vi->rx_sg[1] share the same page */
- /* a separated vi->rx_sg[0] for virtio_net_hdr only due to QEMU bug */
- sg_set_buf(&vi->rx_sg[0], p, sizeof(struct virtio_net_hdr));
+ /* rq->sg[0], rq->sg[1] share the same page */
+ /* a separated rq->sg[0] for virtio_net_hdr only due to QEMU bug */
+ sg_set_buf(&rq->sg[0], p, sizeof(struct virtio_net_hdr));
- /* vi->rx_sg[1] for data packet, from offset */
+ /* rq->sg[1] for data packet, from offset */
offset = sizeof(struct padded_vnet_hdr);
- sg_set_buf(&vi->rx_sg[1], p + offset, PAGE_SIZE - offset);
+ sg_set_buf(&rq->sg[1], p + offset, PAGE_SIZE - offset);
/* chain first in list head */
first->private = (unsigned long)list;
- err = virtqueue_add_buf(vi->rvq, vi->rx_sg, 0, MAX_SKB_FRAGS + 2,
+ err = virtqueue_add_buf(rq->vq, rq->sg, 0, MAX_SKB_FRAGS + 2,
first, gfp);
if (err < 0)
- give_pages(vi, first);
+ give_pages(rq, first);
return err;
}
-static int add_recvbuf_mergeable(struct virtnet_info *vi, gfp_t gfp)
+static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp)
{
struct page *page;
int err;
- page = get_a_page(vi, gfp);
+ page = get_a_page(rq, gfp);
if (!page)
return -ENOMEM;
- sg_init_one(vi->rx_sg, page_address(page), PAGE_SIZE);
+ sg_init_one(rq->sg, page_address(page), PAGE_SIZE);
- err = virtqueue_add_buf(vi->rvq, vi->rx_sg, 0, 1, page, gfp);
+ err = virtqueue_add_buf(rq->vq, rq->sg, 0, 1, page, gfp);
if (err < 0)
- give_pages(vi, page);
+ give_pages(rq, page);
return err;
}
* before we're receiving packets, or from refill_work which is
* careful to disable receiving (using napi_disable).
*/
-static bool try_fill_recv(struct virtnet_info *vi, gfp_t gfp)
+static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp)
{
+ struct virtnet_info *vi = rq->vq->vdev->priv;
int err;
bool oom;
do {
if (vi->mergeable_rx_bufs)
- err = add_recvbuf_mergeable(vi, gfp);
+ err = add_recvbuf_mergeable(rq, gfp);
else if (vi->big_packets)
- err = add_recvbuf_big(vi, gfp);
+ err = add_recvbuf_big(rq, gfp);
else
- err = add_recvbuf_small(vi, gfp);
+ err = add_recvbuf_small(rq, gfp);
oom = err == -ENOMEM;
if (err)
break;
- ++vi->num;
- } while (vi->rvq->num_free);
-
- if (unlikely(vi->num > vi->max))
- vi->max = vi->num;
- virtqueue_kick(vi->rvq);
+ ++rq->num;
+ } while (rq->vq->num_free);
+ if (unlikely(rq->num > rq->max))
+ rq->max = rq->num;
+ virtqueue_kick(rq->vq);
return !oom;
}
static void skb_recv_done(struct virtqueue *rvq)
{
struct virtnet_info *vi = rvq->vdev->priv;
+ struct receive_queue *rq = &vi->rq[vq2rxq(rvq)];
+
/* Schedule NAPI, Suppress further interrupts if successful. */
- if (napi_schedule_prep(&vi->napi)) {
+ if (napi_schedule_prep(&rq->napi)) {
virtqueue_disable_cb(rvq);
- __napi_schedule(&vi->napi);
+ __napi_schedule(&rq->napi);
}
}
-static void virtnet_napi_enable(struct virtnet_info *vi)
+static void virtnet_napi_enable(struct receive_queue *rq)
{
- napi_enable(&vi->napi);
+ napi_enable(&rq->napi);
/* If all buffers were filled by other side before we napi_enabled, we
* won't get another interrupt, so process any outstanding packets
* now. virtnet_poll wants re-enable the queue, so we disable here.
* We synchronize against interrupts via NAPI_STATE_SCHED */
- if (napi_schedule_prep(&vi->napi)) {
- virtqueue_disable_cb(vi->rvq);
+ if (napi_schedule_prep(&rq->napi)) {
+ virtqueue_disable_cb(rq->vq);
local_bh_disable();
- __napi_schedule(&vi->napi);
+ __napi_schedule(&rq->napi);
local_bh_enable();
}
}
static void refill_work(struct work_struct *work)
{
- struct virtnet_info *vi;
+ struct virtnet_info *vi =
+ container_of(work, struct virtnet_info, refill.work);
bool still_empty;
+ int i;
- vi = container_of(work, struct virtnet_info, refill.work);
- napi_disable(&vi->napi);
- still_empty = !try_fill_recv(vi, GFP_KERNEL);
- virtnet_napi_enable(vi);
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ struct receive_queue *rq = &vi->rq[i];
- /* In theory, this can happen: if we don't get any buffers in
- * we will *never* try to fill again. */
- if (still_empty)
- schedule_delayed_work(&vi->refill, HZ/2);
+ napi_disable(&rq->napi);
+ still_empty = !try_fill_recv(rq, GFP_KERNEL);
+ virtnet_napi_enable(rq);
+
+ /* In theory, this can happen: if we don't get any buffers in
+ * we will *never* try to fill again.
+ */
+ if (still_empty)
+ schedule_delayed_work(&vi->refill, HZ/2);
+ }
}
static int virtnet_poll(struct napi_struct *napi, int budget)
{
- struct virtnet_info *vi = container_of(napi, struct virtnet_info, napi);
+ struct receive_queue *rq =
+ container_of(napi, struct receive_queue, napi);
+ struct virtnet_info *vi = rq->vq->vdev->priv;
void *buf;
unsigned int len, received = 0;
again:
while (received < budget &&
- (buf = virtqueue_get_buf(vi->rvq, &len)) != NULL) {
- receive_buf(vi->dev, buf, len);
- --vi->num;
+ (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
+ receive_buf(rq, buf, len);
+ --rq->num;
received++;
}
- if (vi->num < vi->max / 2) {
- if (!try_fill_recv(vi, GFP_ATOMIC))
+ if (rq->num < rq->max / 2) {
+ if (!try_fill_recv(rq, GFP_ATOMIC))
schedule_delayed_work(&vi->refill, 0);
}
/* Out of packets? */
if (received < budget) {
napi_complete(napi);
- if (unlikely(!virtqueue_enable_cb(vi->rvq)) &&
+ if (unlikely(!virtqueue_enable_cb(rq->vq)) &&
napi_schedule_prep(napi)) {
- virtqueue_disable_cb(vi->rvq);
+ virtqueue_disable_cb(rq->vq);
__napi_schedule(napi);
goto again;
}
return received;
}
-static void free_old_xmit_skbs(struct virtnet_info *vi)
+static int virtnet_open(struct net_device *dev)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ int i;
+
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ /* Make sure we have some buffers: if oom use wq. */
+ if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
+ schedule_delayed_work(&vi->refill, 0);
+ virtnet_napi_enable(&vi->rq[i]);
+ }
+
+ return 0;
+}
+
+static void free_old_xmit_skbs(struct send_queue *sq)
{
struct sk_buff *skb;
unsigned int len;
+ struct virtnet_info *vi = sq->vq->vdev->priv;
struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
- while ((skb = virtqueue_get_buf(vi->svq, &len)) != NULL) {
+ while ((skb = virtqueue_get_buf(sq->vq, &len)) != NULL) {
pr_debug("Sent skb %p\n", skb);
u64_stats_update_begin(&stats->tx_syncp);
}
}
-static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb)
+static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
{
struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
+ struct virtnet_info *vi = sq->vq->vdev->priv;
unsigned num_sg;
pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest);
/* Encode metadata header at front. */
if (vi->mergeable_rx_bufs)
- sg_set_buf(vi->tx_sg, &hdr->mhdr, sizeof hdr->mhdr);
+ sg_set_buf(sq->sg, &hdr->mhdr, sizeof hdr->mhdr);
else
- sg_set_buf(vi->tx_sg, &hdr->hdr, sizeof hdr->hdr);
+ sg_set_buf(sq->sg, &hdr->hdr, sizeof hdr->hdr);
- num_sg = skb_to_sgvec(skb, vi->tx_sg + 1, 0, skb->len) + 1;
- return virtqueue_add_buf(vi->svq, vi->tx_sg, num_sg,
+ num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len) + 1;
+ return virtqueue_add_buf(sq->vq, sq->sg, num_sg,
0, skb, GFP_ATOMIC);
}
static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct virtnet_info *vi = netdev_priv(dev);
+ int qnum = skb_get_queue_mapping(skb);
+ struct send_queue *sq = &vi->sq[qnum];
int err;
/* Free up any pending old buffers before queueing new ones. */
- free_old_xmit_skbs(vi);
+ free_old_xmit_skbs(sq);
/* Try to transmit */
- err = xmit_skb(vi, skb);
+ err = xmit_skb(sq, skb);
/* This should not happen! */
if (unlikely(err)) {
dev->stats.tx_fifo_errors++;
if (net_ratelimit())
dev_warn(&dev->dev,
- "Unexpected TX queue failure: %d\n", err);
+ "Unexpected TXQ (%d) queue failure: %d\n", qnum, err);
dev->stats.tx_dropped++;
kfree_skb(skb);
return NETDEV_TX_OK;
}
- virtqueue_kick(vi->svq);
+ virtqueue_kick(sq->vq);
/* Don't wait up for transmitted skbs to be freed. */
skb_orphan(skb);
/* Apparently nice girls don't return TX_BUSY; stop the queue
* before it gets out of hand. Naturally, this wastes entries. */
- if (vi->svq->num_free < 2+MAX_SKB_FRAGS) {
- netif_stop_queue(dev);
- if (unlikely(!virtqueue_enable_cb_delayed(vi->svq))) {
+ if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
+ netif_stop_subqueue(dev, qnum);
+ if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
/* More just got used, free them then recheck. */
- free_old_xmit_skbs(vi);
- if (vi->svq->num_free >= 2+MAX_SKB_FRAGS) {
- netif_start_queue(dev);
- virtqueue_disable_cb(vi->svq);
+ free_old_xmit_skbs(sq);
+ if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
+ netif_start_subqueue(dev, qnum);
+ virtqueue_disable_cb(sq->vq);
}
}
}
static void virtnet_netpoll(struct net_device *dev)
{
struct virtnet_info *vi = netdev_priv(dev);
+ int i;
- napi_schedule(&vi->napi);
+ for (i = 0; i < vi->curr_queue_pairs; i++)
+ napi_schedule(&vi->rq[i].napi);
}
#endif
-static int virtnet_open(struct net_device *dev)
-{
- struct virtnet_info *vi = netdev_priv(dev);
-
- /* Make sure we have some buffers: if oom use wq. */
- if (!try_fill_recv(vi, GFP_KERNEL))
- schedule_delayed_work(&vi->refill, 0);
-
- virtnet_napi_enable(vi);
- return 0;
-}
-
/*
* Send command via the control virtqueue and check status. Commands
* supported by the hypervisor, as indicated by feature bits, should
rtnl_unlock();
}
+static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
+{
+ struct scatterlist sg;
+ struct virtio_net_ctrl_mq s;
+ struct net_device *dev = vi->dev;
+
+ if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
+ return 0;
+
+ s.virtqueue_pairs = queue_pairs;
+ sg_init_one(&sg, &s, sizeof(s));
+
+ if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
+ VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg, 1, 0)){
+ dev_warn(&dev->dev, "Fail to set num of queue pairs to %d\n",
+ queue_pairs);
+ return -EINVAL;
+ } else
+ vi->curr_queue_pairs = queue_pairs;
+
+ return 0;
+}
+
static int virtnet_close(struct net_device *dev)
{
struct virtnet_info *vi = netdev_priv(dev);
+ int i;
/* Make sure refill_work doesn't re-enable napi! */
cancel_delayed_work_sync(&vi->refill);
- napi_disable(&vi->napi);
+
+ for (i = 0; i < vi->max_queue_pairs; i++)
+ napi_disable(&vi->rq[i].napi);
return 0;
}
return 0;
}
+static void virtnet_set_affinity(struct virtnet_info *vi, bool set)
+{
+ int i;
+
+ /* In multiqueue mode, when the number of cpu is equal to the number of
+ * queue pairs, we let the queue pairs to be private to one cpu by
+ * setting the affinity hint to eliminate the contention.
+ */
+ if ((vi->curr_queue_pairs == 1 ||
+ vi->max_queue_pairs != num_online_cpus()) && set) {
+ if (vi->affinity_hint_set)
+ set = false;
+ else
+ return;
+ }
+
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ int cpu = set ? i : -1;
+ virtqueue_set_affinity(vi->rq[i].vq, cpu);
+ virtqueue_set_affinity(vi->sq[i].vq, cpu);
+ }
+
+ if (set)
+ vi->affinity_hint_set = true;
+ else
+ vi->affinity_hint_set = false;
+}
+
static void virtnet_get_ringparam(struct net_device *dev,
struct ethtool_ringparam *ring)
{
struct virtnet_info *vi = netdev_priv(dev);
- ring->rx_max_pending = virtqueue_get_vring_size(vi->rvq);
- ring->tx_max_pending = virtqueue_get_vring_size(vi->svq);
+ ring->rx_max_pending = virtqueue_get_vring_size(vi->rq[0].vq);
+ ring->tx_max_pending = virtqueue_get_vring_size(vi->sq[0].vq);
ring->rx_pending = ring->rx_max_pending;
ring->tx_pending = ring->tx_max_pending;
-
}
}
+/* TODO: Eliminate OOO packets during switching */
+static int virtnet_set_channels(struct net_device *dev,
+ struct ethtool_channels *channels)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ u16 queue_pairs = channels->combined_count;
+ int err;
+
+ /* We don't support separate rx/tx channels.
+ * We don't allow setting 'other' channels.
+ */
+ if (channels->rx_count || channels->tx_count || channels->other_count)
+ return -EINVAL;
+
+ if (queue_pairs > vi->max_queue_pairs)
+ return -EINVAL;
+
+ err = virtnet_set_queues(vi, queue_pairs);
+ if (!err) {
+ netif_set_real_num_tx_queues(dev, queue_pairs);
+ netif_set_real_num_rx_queues(dev, queue_pairs);
+
+ virtnet_set_affinity(vi, true);
+ }
+
+ return err;
+}
+
+static void virtnet_get_channels(struct net_device *dev,
+ struct ethtool_channels *channels)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+
+ channels->combined_count = vi->curr_queue_pairs;
+ channels->max_combined = vi->max_queue_pairs;
+ channels->max_other = 0;
+ channels->rx_count = 0;
+ channels->tx_count = 0;
+ channels->other_count = 0;
+}
+
static const struct ethtool_ops virtnet_ethtool_ops = {
.get_drvinfo = virtnet_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_ringparam = virtnet_get_ringparam,
+ .set_channels = virtnet_set_channels,
+ .get_channels = virtnet_get_channels,
};
#define MIN_MTU 68
return 0;
}
+/* To avoid contending a lock hold by a vcpu who would exit to host, select the
+ * txq based on the processor id.
+ * TODO: handle cpu hotplug.
+ */
+static u16 virtnet_select_queue(struct net_device *dev, struct sk_buff *skb)
+{
+ int txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) :
+ smp_processor_id();
+
+ while (unlikely(txq >= dev->real_num_tx_queues))
+ txq -= dev->real_num_tx_queues;
+
+ return txq;
+}
+
static const struct net_device_ops virtnet_netdev = {
.ndo_open = virtnet_open,
.ndo_stop = virtnet_close,
.ndo_get_stats64 = virtnet_stats,
.ndo_vlan_rx_add_vid = virtnet_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = virtnet_vlan_rx_kill_vid,
+ .ndo_select_queue = virtnet_select_queue,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = virtnet_netpoll,
#endif
if (vi->status & VIRTIO_NET_S_LINK_UP) {
netif_carrier_on(vi->dev);
- netif_wake_queue(vi->dev);
+ netif_tx_wake_all_queues(vi->dev);
} else {
netif_carrier_off(vi->dev);
- netif_stop_queue(vi->dev);
+ netif_tx_stop_all_queues(vi->dev);
}
done:
mutex_unlock(&vi->config_lock);
schedule_work(&vi->config_work);
}
-static int init_vqs(struct virtnet_info *vi)
+static void virtnet_free_queues(struct virtnet_info *vi)
{
- struct virtqueue *vqs[3];
- vq_callback_t *callbacks[] = { skb_recv_done, skb_xmit_done, NULL};
- const char *names[] = { "input", "output", "control" };
- int nvqs, err;
+ kfree(vi->rq);
+ kfree(vi->sq);
+}
- /* We expect two virtqueues, receive then send,
- * and optionally control. */
- nvqs = virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) ? 3 : 2;
+static void free_receive_bufs(struct virtnet_info *vi)
+{
+ int i;
- err = vi->vdev->config->find_vqs(vi->vdev, nvqs, vqs, callbacks, names);
- if (err)
- return err;
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ while (vi->rq[i].pages)
+ __free_pages(get_a_page(&vi->rq[i], GFP_KERNEL), 0);
+ }
+}
- vi->rvq = vqs[0];
- vi->svq = vqs[1];
+static void free_unused_bufs(struct virtnet_info *vi)
+{
+ void *buf;
+ int i;
- if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) {
- vi->cvq = vqs[2];
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ struct virtqueue *vq = vi->sq[i].vq;
+ while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
+ dev_kfree_skb(buf);
+ }
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ struct virtqueue *vq = vi->rq[i].vq;
+
+ while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
+ if (vi->mergeable_rx_bufs || vi->big_packets)
+ give_pages(&vi->rq[i], buf);
+ else
+ dev_kfree_skb(buf);
+ --vi->rq[i].num;
+ }
+ BUG_ON(vi->rq[i].num != 0);
+ }
+}
+
+static void virtnet_del_vqs(struct virtnet_info *vi)
+{
+ struct virtio_device *vdev = vi->vdev;
+
+ virtnet_set_affinity(vi, false);
+
+ vdev->config->del_vqs(vdev);
+
+ virtnet_free_queues(vi);
+}
+
+static int virtnet_find_vqs(struct virtnet_info *vi)
+{
+ vq_callback_t **callbacks;
+ struct virtqueue **vqs;
+ int ret = -ENOMEM;
+ int i, total_vqs;
+ const char **names;
+
+ /* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by
+ * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by
+ * possible control vq.
+ */
+ total_vqs = vi->max_queue_pairs * 2 +
+ virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ);
+
+ /* Allocate space for find_vqs parameters */
+ vqs = kzalloc(total_vqs * sizeof(*vqs), GFP_KERNEL);
+ if (!vqs)
+ goto err_vq;
+ callbacks = kmalloc(total_vqs * sizeof(*callbacks), GFP_KERNEL);
+ if (!callbacks)
+ goto err_callback;
+ names = kmalloc(total_vqs * sizeof(*names), GFP_KERNEL);
+ if (!names)
+ goto err_names;
+
+ /* Parameters for control virtqueue, if any */
+ if (vi->has_cvq) {
+ callbacks[total_vqs - 1] = NULL;
+ names[total_vqs - 1] = "control";
+ }
+
+ /* Allocate/initialize parameters for send/receive virtqueues */
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ callbacks[rxq2vq(i)] = skb_recv_done;
+ callbacks[txq2vq(i)] = skb_xmit_done;
+ sprintf(vi->rq[i].name, "input.%d", i);
+ sprintf(vi->sq[i].name, "output.%d", i);
+ names[rxq2vq(i)] = vi->rq[i].name;
+ names[txq2vq(i)] = vi->sq[i].name;
+ }
+
+ ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
+ names);
+ if (ret)
+ goto err_find;
+
+ if (vi->has_cvq) {
+ vi->cvq = vqs[total_vqs - 1];
if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN))
vi->dev->features |= NETIF_F_HW_VLAN_FILTER;
}
+
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ vi->rq[i].vq = vqs[rxq2vq(i)];
+ vi->sq[i].vq = vqs[txq2vq(i)];
+ }
+
+ kfree(names);
+ kfree(callbacks);
+ kfree(vqs);
+
+ return 0;
+
+err_find:
+ kfree(names);
+err_names:
+ kfree(callbacks);
+err_callback:
+ kfree(vqs);
+err_vq:
+ return ret;
+}
+
+static int virtnet_alloc_queues(struct virtnet_info *vi)
+{
+ int i;
+
+ vi->sq = kzalloc(sizeof(*vi->sq) * vi->max_queue_pairs, GFP_KERNEL);
+ if (!vi->sq)
+ goto err_sq;
+ vi->rq = kzalloc(sizeof(*vi->rq) * vi->max_queue_pairs, GFP_KERNEL);
+ if (!vi->rq)
+ goto err_rq;
+
+ INIT_DELAYED_WORK(&vi->refill, refill_work);
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ vi->rq[i].pages = NULL;
+ netif_napi_add(vi->dev, &vi->rq[i].napi, virtnet_poll,
+ napi_weight);
+
+ sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
+ sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg));
+ }
+
return 0;
+
+err_rq:
+ kfree(vi->sq);
+err_sq:
+ return -ENOMEM;
+}
+
+static int init_vqs(struct virtnet_info *vi)
+{
+ int ret;
+
+ /* Allocate send & receive queues */
+ ret = virtnet_alloc_queues(vi);
+ if (ret)
+ goto err;
+
+ ret = virtnet_find_vqs(vi);
+ if (ret)
+ goto err_free;
+
+ virtnet_set_affinity(vi, true);
+ return 0;
+
+err_free:
+ virtnet_free_queues(vi);
+err:
+ return ret;
}
static int virtnet_probe(struct virtio_device *vdev)
{
- int err;
+ int i, err;
struct net_device *dev;
struct virtnet_info *vi;
+ u16 max_queue_pairs;
+
+ /* Find if host supports multiqueue virtio_net device */
+ err = virtio_config_val(vdev, VIRTIO_NET_F_MQ,
+ offsetof(struct virtio_net_config,
+ max_virtqueue_pairs), &max_queue_pairs);
+
+ /* We need at least 2 queue's */
+ if (err || max_queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN ||
+ max_queue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX ||
+ !virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
+ max_queue_pairs = 1;
/* Allocate ourselves a network device with room for our info */
- dev = alloc_etherdev(sizeof(struct virtnet_info));
+ dev = alloc_etherdev_mq(sizeof(struct virtnet_info), max_queue_pairs);
if (!dev)
return -ENOMEM;
/* Set up our device-specific information */
vi = netdev_priv(dev);
- netif_napi_add(dev, &vi->napi, virtnet_poll, napi_weight);
vi->dev = dev;
vi->vdev = vdev;
vdev->priv = vi;
- vi->pages = NULL;
vi->stats = alloc_percpu(struct virtnet_stats);
err = -ENOMEM;
if (vi->stats == NULL)
goto free;
- INIT_DELAYED_WORK(&vi->refill, refill_work);
mutex_init(&vi->config_lock);
vi->config_enable = true;
INIT_WORK(&vi->config_work, virtnet_config_changed_work);
- sg_init_table(vi->rx_sg, ARRAY_SIZE(vi->rx_sg));
- sg_init_table(vi->tx_sg, ARRAY_SIZE(vi->tx_sg));
/* If we can receive ANY GSO packets, we must allocate large ones. */
if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
vi->mergeable_rx_bufs = true;
+ if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
+ vi->has_cvq = true;
+
+ /* Use single tx/rx queue pair as default */
+ vi->curr_queue_pairs = 1;
+ vi->max_queue_pairs = max_queue_pairs;
+
+ /* Allocate/initialize the rx/tx queues, and invoke find_vqs */
err = init_vqs(vi);
if (err)
goto free_stats;
+ netif_set_real_num_tx_queues(dev, 1);
+ netif_set_real_num_rx_queues(dev, 1);
+
err = register_netdev(dev);
if (err) {
pr_debug("virtio_net: registering device failed\n");
}
/* Last of all, set up some receive buffers. */
- try_fill_recv(vi, GFP_KERNEL);
-
- /* If we didn't even get one input buffer, we're useless. */
- if (vi->num == 0) {
- err = -ENOMEM;
- goto unregister;
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ try_fill_recv(&vi->rq[i], GFP_KERNEL);
+
+ /* If we didn't even get one input buffer, we're useless. */
+ if (vi->rq[i].num == 0) {
+ free_unused_bufs(vi);
+ err = -ENOMEM;
+ goto free_recv_bufs;
+ }
}
/* Assume link up if device can't report link status,
netif_carrier_on(dev);
}
- pr_debug("virtnet: registered device %s\n", dev->name);
+ pr_debug("virtnet: registered device %s with %d RX and TX vq's\n",
+ dev->name, max_queue_pairs);
+
return 0;
-unregister:
+free_recv_bufs:
+ free_receive_bufs(vi);
unregister_netdev(dev);
free_vqs:
- vdev->config->del_vqs(vdev);
+ cancel_delayed_work_sync(&vi->refill);
+ virtnet_del_vqs(vi);
free_stats:
free_percpu(vi->stats);
free:
return err;
}
-static void free_unused_bufs(struct virtnet_info *vi)
-{
- void *buf;
- while (1) {
- buf = virtqueue_detach_unused_buf(vi->svq);
- if (!buf)
- break;
- dev_kfree_skb(buf);
- }
- while (1) {
- buf = virtqueue_detach_unused_buf(vi->rvq);
- if (!buf)
- break;
- if (vi->mergeable_rx_bufs || vi->big_packets)
- give_pages(vi, buf);
- else
- dev_kfree_skb(buf);
- --vi->num;
- }
- BUG_ON(vi->num != 0);
-}
-
static void remove_vq_common(struct virtnet_info *vi)
{
vi->vdev->config->reset(vi->vdev);
/* Free unused buffers in both send and recv, if any. */
free_unused_bufs(vi);
- vi->vdev->config->del_vqs(vi->vdev);
+ free_receive_bufs(vi);
- while (vi->pages)
- __free_pages(get_a_page(vi, GFP_KERNEL), 0);
+ virtnet_del_vqs(vi);
}
-static void __devexit virtnet_remove(struct virtio_device *vdev)
+static void virtnet_remove(struct virtio_device *vdev)
{
struct virtnet_info *vi = vdev->priv;
static int virtnet_freeze(struct virtio_device *vdev)
{
struct virtnet_info *vi = vdev->priv;
+ int i;
/* Prevent config work handler from accessing the device */
mutex_lock(&vi->config_lock);
cancel_delayed_work_sync(&vi->refill);
if (netif_running(vi->dev))
- napi_disable(&vi->napi);
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ napi_disable(&vi->rq[i].napi);
+ netif_napi_del(&vi->rq[i].napi);
+ }
remove_vq_common(vi);
static int virtnet_restore(struct virtio_device *vdev)
{
struct virtnet_info *vi = vdev->priv;
- int err;
+ int err, i;
err = init_vqs(vi);
if (err)
return err;
if (netif_running(vi->dev))
- virtnet_napi_enable(vi);
+ for (i = 0; i < vi->max_queue_pairs; i++)
+ virtnet_napi_enable(&vi->rq[i]);
netif_device_attach(vi->dev);
- if (!try_fill_recv(vi, GFP_KERNEL))
- schedule_delayed_work(&vi->refill, 0);
+ for (i = 0; i < vi->max_queue_pairs; i++)
+ if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
+ schedule_delayed_work(&vi->refill, 0);
mutex_lock(&vi->config_lock);
vi->config_enable = true;
mutex_unlock(&vi->config_lock);
+ virtnet_set_queues(vi, vi->curr_queue_pairs);
+
return 0;
}
#endif
VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO,
VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ,
VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN,
- VIRTIO_NET_F_GUEST_ANNOUNCE,
+ VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ,
};
static struct virtio_driver virtio_net_driver = {
.driver.owner = THIS_MODULE,
.id_table = id_table,
.probe = virtnet_probe,
- .remove = __devexit_p(virtnet_remove),
+ .remove = virtnet_remove,
.config_changed = virtnet_config_changed,
#ifdef CONFIG_PM
.freeze = virtnet_freeze,