-/* A simple network driver using virtio.
+/* A network driver using virtio.
*
* Copyright 2007 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation
*
#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/virtio.h>
-#include <linux/virtio_ids.h>
#include <linux/virtio_net.h>
#include <linux/scatterlist.h>
#include <linux/if_vlan.h>
+#include <linux/slab.h>
static int napi_weight = 128;
module_param(napi_weight, int, 0444);
struct napi_struct napi;
unsigned int status;
- /* If we need to free in a timer, this is it. */
- struct timer_list xmit_free_timer;
-
/* Number of input buffers, and max we've ever had. */
unsigned int num, max;
- /* For cleaning up after transmission. */
- struct tasklet_struct tasklet;
- bool free_in_tasklet;
-
/* 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;
- /* Receive & send queues. */
- struct sk_buff_head recv;
- struct sk_buff_head send;
-
/* Work struct for refilling if we run low on memory. */
struct delayed_work refill;
struct page *pages;
};
-static inline void *skb_vnet_hdr(struct sk_buff *skb)
-{
- return (struct virtio_net_hdr *)skb->cb;
-}
+struct skb_vnet_hdr {
+ union {
+ struct virtio_net_hdr hdr;
+ struct virtio_net_hdr_mrg_rxbuf mhdr;
+ };
+ unsigned int num_sg;
+};
-static void give_a_page(struct virtnet_info *vi, struct page *page)
+struct padded_vnet_hdr {
+ struct virtio_net_hdr hdr;
+ /*
+ * virtio_net_hdr should be in a separated sg buffer because of a
+ * QEMU bug, and data sg buffer shares same page with this header sg.
+ * This padding makes next sg 16 byte aligned after virtio_net_hdr.
+ */
+ char padding[6];
+};
+
+static inline struct skb_vnet_hdr *skb_vnet_hdr(struct sk_buff *skb)
{
- page->private = (unsigned long)vi->pages;
- vi->pages = page;
+ return (struct skb_vnet_hdr *)skb->cb;
}
-static void trim_pages(struct virtnet_info *vi, struct sk_buff *skb)
+/*
+ * 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)
{
- unsigned int i;
+ struct page *end;
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
- give_a_page(vi, skb_shinfo(skb)->frags[i].page);
- skb_shinfo(skb)->nr_frags = 0;
- skb->data_len = 0;
+ /* Find end of list, sew whole thing into vi->pages. */
+ for (end = page; end->private; end = (struct page *)end->private);
+ end->private = (unsigned long)vi->pages;
+ vi->pages = page;
}
static struct page *get_a_page(struct virtnet_info *vi, gfp_t gfp_mask)
{
struct page *p = vi->pages;
- if (p)
+ if (p) {
vi->pages = (struct page *)p->private;
- else
+ /* clear private here, it is used to chain pages */
+ p->private = 0;
+ } else
p = alloc_page(gfp_mask);
return p;
}
/* We were probably waiting for more output buffers. */
netif_wake_queue(vi->dev);
+}
- if (vi->free_in_tasklet)
- tasklet_schedule(&vi->tasklet);
+static void set_skb_frag(struct sk_buff *skb, struct page *page,
+ unsigned int offset, unsigned int *len)
+{
+ int i = skb_shinfo(skb)->nr_frags;
+ skb_frag_t *f;
+
+ f = &skb_shinfo(skb)->frags[i];
+ f->size = min((unsigned)PAGE_SIZE - offset, *len);
+ f->page_offset = offset;
+ f->page = page;
+
+ skb->data_len += f->size;
+ skb->len += f->size;
+ skb_shinfo(skb)->nr_frags++;
+ *len -= f->size;
}
-static void receive_skb(struct net_device *dev, struct sk_buff *skb,
- unsigned len)
+static struct sk_buff *page_to_skb(struct virtnet_info *vi,
+ struct page *page, unsigned int len)
{
- struct virtnet_info *vi = netdev_priv(dev);
- struct virtio_net_hdr *hdr = skb_vnet_hdr(skb);
- int err;
- int i;
+ struct sk_buff *skb;
+ struct skb_vnet_hdr *hdr;
+ unsigned int copy, hdr_len, offset;
+ char *p;
- if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) {
- pr_debug("%s: short packet %i\n", dev->name, len);
- dev->stats.rx_length_errors++;
- goto drop;
- }
+ p = page_address(page);
- if (vi->mergeable_rx_bufs) {
- struct virtio_net_hdr_mrg_rxbuf *mhdr = skb_vnet_hdr(skb);
- unsigned int copy;
- char *p = page_address(skb_shinfo(skb)->frags[0].page);
+ /* copy small packet so we can reuse these pages for small data */
+ skb = netdev_alloc_skb_ip_align(vi->dev, GOOD_COPY_LEN);
+ if (unlikely(!skb))
+ return NULL;
- if (len > PAGE_SIZE)
- len = PAGE_SIZE;
- len -= sizeof(struct virtio_net_hdr_mrg_rxbuf);
+ hdr = skb_vnet_hdr(skb);
+
+ if (vi->mergeable_rx_bufs) {
+ hdr_len = sizeof hdr->mhdr;
+ offset = hdr_len;
+ } else {
+ hdr_len = sizeof hdr->hdr;
+ offset = sizeof(struct padded_vnet_hdr);
+ }
- memcpy(hdr, p, sizeof(*mhdr));
- p += sizeof(*mhdr);
+ memcpy(hdr, p, hdr_len);
- copy = len;
- if (copy > skb_tailroom(skb))
- copy = skb_tailroom(skb);
+ len -= hdr_len;
+ p += offset;
- memcpy(skb_put(skb, copy), p, copy);
+ copy = len;
+ if (copy > skb_tailroom(skb))
+ copy = skb_tailroom(skb);
+ memcpy(skb_put(skb, copy), p, copy);
- len -= copy;
+ len -= copy;
+ offset += copy;
- if (!len) {
- give_a_page(vi, skb_shinfo(skb)->frags[0].page);
- skb_shinfo(skb)->nr_frags--;
- } else {
- skb_shinfo(skb)->frags[0].page_offset +=
- sizeof(*mhdr) + copy;
- skb_shinfo(skb)->frags[0].size = len;
- skb->data_len += len;
- skb->len += len;
- }
+ while (len) {
+ set_skb_frag(skb, page, offset, &len);
+ page = (struct page *)page->private;
+ offset = 0;
+ }
- while (--mhdr->num_buffers) {
- struct sk_buff *nskb;
+ if (page)
+ give_pages(vi, page);
- i = skb_shinfo(skb)->nr_frags;
- if (i >= MAX_SKB_FRAGS) {
- pr_debug("%s: packet too long %d\n", dev->name,
- len);
- dev->stats.rx_length_errors++;
- goto drop;
- }
+ return skb;
+}
- nskb = vi->rvq->vq_ops->get_buf(vi->rvq, &len);
- if (!nskb) {
- pr_debug("%s: rx error: %d buffers missing\n",
- dev->name, mhdr->num_buffers);
- dev->stats.rx_length_errors++;
- goto drop;
- }
+static int receive_mergeable(struct virtnet_info *vi, struct sk_buff *skb)
+{
+ struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
+ struct page *page;
+ int num_buf, i, len;
+
+ num_buf = hdr->mhdr.num_buffers;
+ while (--num_buf) {
+ i = skb_shinfo(skb)->nr_frags;
+ if (i >= MAX_SKB_FRAGS) {
+ pr_debug("%s: packet too long\n", skb->dev->name);
+ skb->dev->stats.rx_length_errors++;
+ return -EINVAL;
+ }
- __skb_unlink(nskb, &vi->recv);
- vi->num--;
+ page = vi->rvq->vq_ops->get_buf(vi->rvq, &len);
+ if (!page) {
+ pr_debug("%s: rx error: %d buffers missing\n",
+ skb->dev->name, hdr->mhdr.num_buffers);
+ skb->dev->stats.rx_length_errors++;
+ return -EINVAL;
+ }
+ if (len > PAGE_SIZE)
+ len = PAGE_SIZE;
- skb_shinfo(skb)->frags[i] = skb_shinfo(nskb)->frags[0];
- skb_shinfo(nskb)->nr_frags = 0;
- kfree_skb(nskb);
+ set_skb_frag(skb, page, 0, &len);
- if (len > PAGE_SIZE)
- len = PAGE_SIZE;
+ --vi->num;
+ }
+ return 0;
+}
- skb_shinfo(skb)->frags[i].size = len;
- skb_shinfo(skb)->nr_frags++;
- skb->data_len += len;
- skb->len += len;
- }
- } else {
- len -= sizeof(struct virtio_net_hdr);
+static void receive_buf(struct net_device *dev, void *buf, unsigned int len)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ struct sk_buff *skb;
+ struct page *page;
+ struct skb_vnet_hdr *hdr;
- if (len <= MAX_PACKET_LEN)
- trim_pages(vi, skb);
+ if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) {
+ 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);
+ else
+ dev_kfree_skb(buf);
+ return;
+ }
- err = pskb_trim(skb, len);
- if (err) {
- pr_debug("%s: pskb_trim failed %i %d\n", dev->name,
- len, err);
+ if (!vi->mergeable_rx_bufs && !vi->big_packets) {
+ skb = buf;
+ len -= sizeof(struct virtio_net_hdr);
+ skb_trim(skb, len);
+ } else {
+ page = buf;
+ skb = page_to_skb(vi, page, len);
+ if (unlikely(!skb)) {
dev->stats.rx_dropped++;
- goto drop;
+ give_pages(vi, page);
+ return;
}
+ if (vi->mergeable_rx_bufs)
+ if (receive_mergeable(vi, skb)) {
+ dev_kfree_skb(skb);
+ return;
+ }
}
+ hdr = skb_vnet_hdr(skb);
skb->truesize += skb->data_len;
dev->stats.rx_bytes += skb->len;
dev->stats.rx_packets++;
- if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
+ if (hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
pr_debug("Needs csum!\n");
- if (!skb_partial_csum_set(skb,hdr->csum_start,hdr->csum_offset))
+ if (!skb_partial_csum_set(skb,
+ hdr->hdr.csum_start,
+ hdr->hdr.csum_offset))
goto frame_err;
}
pr_debug("Receiving skb proto 0x%04x len %i type %i\n",
ntohs(skb->protocol), skb->len, skb->pkt_type);
- if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+ if (hdr->hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
pr_debug("GSO!\n");
- switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+ switch (hdr->hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
case VIRTIO_NET_HDR_GSO_TCPV4:
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
break;
default:
if (net_ratelimit())
printk(KERN_WARNING "%s: bad gso type %u.\n",
- dev->name, hdr->gso_type);
+ dev->name, hdr->hdr.gso_type);
goto frame_err;
}
- if (hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN)
+ if (hdr->hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN)
skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
- skb_shinfo(skb)->gso_size = hdr->gso_size;
+ 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",
frame_err:
dev->stats.rx_frame_errors++;
-drop:
dev_kfree_skb(skb);
}
-static bool try_fill_recv_maxbufs(struct virtnet_info *vi, gfp_t gfp)
+static int add_recvbuf_small(struct virtnet_info *vi, gfp_t gfp)
{
struct sk_buff *skb;
- struct scatterlist sg[2+MAX_SKB_FRAGS];
- int num, err, i;
- bool oom = false;
-
- sg_init_table(sg, 2+MAX_SKB_FRAGS);
- for (;;) {
- struct virtio_net_hdr *hdr;
+ struct skb_vnet_hdr *hdr;
+ struct scatterlist sg[2];
+ int err;
- skb = netdev_alloc_skb(vi->dev, MAX_PACKET_LEN + NET_IP_ALIGN);
- if (unlikely(!skb)) {
- oom = true;
- break;
- }
+ sg_init_table(sg, 2);
+ skb = netdev_alloc_skb_ip_align(vi->dev, MAX_PACKET_LEN);
+ if (unlikely(!skb))
+ return -ENOMEM;
- skb_reserve(skb, NET_IP_ALIGN);
- skb_put(skb, MAX_PACKET_LEN);
+ skb_put(skb, MAX_PACKET_LEN);
- hdr = skb_vnet_hdr(skb);
- sg_set_buf(sg, hdr, sizeof(*hdr));
+ hdr = skb_vnet_hdr(skb);
+ sg_set_buf(sg, &hdr->hdr, sizeof hdr->hdr);
- if (vi->big_packets) {
- for (i = 0; i < MAX_SKB_FRAGS; i++) {
- skb_frag_t *f = &skb_shinfo(skb)->frags[i];
- f->page = get_a_page(vi, gfp);
- if (!f->page)
- break;
+ skb_to_sgvec(skb, sg + 1, 0, skb->len);
- f->page_offset = 0;
- f->size = PAGE_SIZE;
+ err = vi->rvq->vq_ops->add_buf(vi->rvq, sg, 0, 2, skb);
+ if (err < 0)
+ dev_kfree_skb(skb);
- skb->data_len += PAGE_SIZE;
- skb->len += PAGE_SIZE;
+ return err;
+}
- skb_shinfo(skb)->nr_frags++;
- }
+static int add_recvbuf_big(struct virtnet_info *vi, gfp_t gfp)
+{
+ struct scatterlist sg[MAX_SKB_FRAGS + 2];
+ struct page *first, *list = NULL;
+ char *p;
+ int i, err, offset;
+
+ sg_init_table(sg, MAX_SKB_FRAGS + 2);
+ /* page in sg[MAX_SKB_FRAGS + 1] is list tail */
+ for (i = MAX_SKB_FRAGS + 1; i > 1; --i) {
+ first = get_a_page(vi, gfp);
+ if (!first) {
+ if (list)
+ give_pages(vi, list);
+ return -ENOMEM;
}
+ sg_set_buf(&sg[i], page_address(first), PAGE_SIZE);
- num = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1;
- skb_queue_head(&vi->recv, skb);
+ /* chain new page in list head to match sg */
+ first->private = (unsigned long)list;
+ list = first;
+ }
- err = vi->rvq->vq_ops->add_buf(vi->rvq, sg, 0, num, skb);
- if (err < 0) {
- skb_unlink(skb, &vi->recv);
- trim_pages(vi, skb);
- kfree_skb(skb);
- break;
- }
- vi->num++;
+ first = get_a_page(vi, gfp);
+ if (!first) {
+ give_pages(vi, list);
+ return -ENOMEM;
}
- if (unlikely(vi->num > vi->max))
- vi->max = vi->num;
- vi->rvq->vq_ops->kick(vi->rvq);
- return !oom;
+ p = page_address(first);
+
+ /* sg[0], sg[1] share the same page */
+ /* a separated sg[0] for virtio_net_hdr only during to QEMU bug*/
+ sg_set_buf(&sg[0], p, sizeof(struct virtio_net_hdr));
+
+ /* sg[1] for data packet, from offset */
+ offset = sizeof(struct padded_vnet_hdr);
+ sg_set_buf(&sg[1], p + offset, PAGE_SIZE - offset);
+
+ /* chain first in list head */
+ first->private = (unsigned long)list;
+ err = vi->rvq->vq_ops->add_buf(vi->rvq, sg, 0, MAX_SKB_FRAGS + 2,
+ first);
+ if (err < 0)
+ give_pages(vi, first);
+
+ return err;
}
-/* Returns false if we couldn't fill entirely (OOM). */
-static bool try_fill_recv(struct virtnet_info *vi, gfp_t gfp)
+static int add_recvbuf_mergeable(struct virtnet_info *vi, gfp_t gfp)
{
- struct sk_buff *skb;
- struct scatterlist sg[1];
+ struct page *page;
+ struct scatterlist sg;
int err;
- bool oom = false;
-
- if (!vi->mergeable_rx_bufs)
- return try_fill_recv_maxbufs(vi, gfp);
- for (;;) {
- skb_frag_t *f;
-
- skb = netdev_alloc_skb(vi->dev, GOOD_COPY_LEN + NET_IP_ALIGN);
- if (unlikely(!skb)) {
- oom = true;
- break;
- }
+ page = get_a_page(vi, gfp);
+ if (!page)
+ return -ENOMEM;
- skb_reserve(skb, NET_IP_ALIGN);
+ sg_init_one(&sg, page_address(page), PAGE_SIZE);
- f = &skb_shinfo(skb)->frags[0];
- f->page = get_a_page(vi, gfp);
- if (!f->page) {
- oom = true;
- kfree_skb(skb);
- break;
- }
+ err = vi->rvq->vq_ops->add_buf(vi->rvq, &sg, 0, 1, page);
+ if (err < 0)
+ give_pages(vi, page);
- f->page_offset = 0;
- f->size = PAGE_SIZE;
+ return err;
+}
- skb_shinfo(skb)->nr_frags++;
+/* Returns false if we couldn't fill entirely (OOM). */
+static bool try_fill_recv(struct virtnet_info *vi, gfp_t gfp)
+{
+ int err;
+ bool oom = false;
- sg_init_one(sg, page_address(f->page), PAGE_SIZE);
- skb_queue_head(&vi->recv, skb);
+ do {
+ if (vi->mergeable_rx_bufs)
+ err = add_recvbuf_mergeable(vi, gfp);
+ else if (vi->big_packets)
+ err = add_recvbuf_big(vi, gfp);
+ else
+ err = add_recvbuf_small(vi, gfp);
- err = vi->rvq->vq_ops->add_buf(vi->rvq, sg, 0, 1, skb);
if (err < 0) {
- skb_unlink(skb, &vi->recv);
- kfree_skb(skb);
+ oom = true;
break;
}
- vi->num++;
- }
+ ++vi->num;
+ } while (err > 0);
if (unlikely(vi->num > vi->max))
vi->max = vi->num;
vi->rvq->vq_ops->kick(vi->rvq);
vi = container_of(work, struct virtnet_info, refill.work);
napi_disable(&vi->napi);
- try_fill_recv(vi, GFP_KERNEL);
- still_empty = (vi->num == 0);
+ still_empty = !try_fill_recv(vi, GFP_KERNEL);
napi_enable(&vi->napi);
/* In theory, this can happen: if we don't get any buffers in
static int virtnet_poll(struct napi_struct *napi, int budget)
{
struct virtnet_info *vi = container_of(napi, struct virtnet_info, napi);
- struct sk_buff *skb = NULL;
+ void *buf;
unsigned int len, received = 0;
again:
while (received < budget &&
- (skb = vi->rvq->vq_ops->get_buf(vi->rvq, &len)) != NULL) {
- __skb_unlink(skb, &vi->recv);
- receive_skb(vi->dev, skb, len);
- vi->num--;
+ (buf = vi->rvq->vq_ops->get_buf(vi->rvq, &len)) != NULL) {
+ receive_buf(vi->dev, buf, len);
+ --vi->num;
received++;
}
/* Out of packets? */
if (received < budget) {
napi_complete(napi);
- if (unlikely(!vi->rvq->vq_ops->enable_cb(vi->rvq))
- && napi_schedule_prep(napi)) {
+ if (unlikely(!vi->rvq->vq_ops->enable_cb(vi->rvq)) &&
+ napi_schedule_prep(napi)) {
vi->rvq->vq_ops->disable_cb(vi->rvq);
__napi_schedule(napi);
goto again;
return received;
}
-static void free_old_xmit_skbs(struct virtnet_info *vi)
+static unsigned int free_old_xmit_skbs(struct virtnet_info *vi)
{
struct sk_buff *skb;
- unsigned int len;
+ unsigned int len, tot_sgs = 0;
while ((skb = vi->svq->vq_ops->get_buf(vi->svq, &len)) != NULL) {
pr_debug("Sent skb %p\n", skb);
- __skb_unlink(skb, &vi->send);
vi->dev->stats.tx_bytes += skb->len;
vi->dev->stats.tx_packets++;
- kfree_skb(skb);
+ tot_sgs += skb_vnet_hdr(skb)->num_sg;
+ dev_kfree_skb_any(skb);
}
-}
-
-/* If the virtio transport doesn't always notify us when all in-flight packets
- * are consumed, we fall back to using this function on a timer to free them. */
-static void xmit_free(unsigned long data)
-{
- struct virtnet_info *vi = (void *)data;
-
- netif_tx_lock(vi->dev);
-
- free_old_xmit_skbs(vi);
-
- if (!skb_queue_empty(&vi->send))
- mod_timer(&vi->xmit_free_timer, jiffies + (HZ/10));
-
- netif_tx_unlock(vi->dev);
+ return tot_sgs;
}
static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb)
{
- int num, err;
struct scatterlist sg[2+MAX_SKB_FRAGS];
- struct virtio_net_hdr_mrg_rxbuf *mhdr = skb_vnet_hdr(skb);
- struct virtio_net_hdr *hdr = skb_vnet_hdr(skb);
+ struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
sg_init_table(sg, 2+MAX_SKB_FRAGS);
pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
- hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
- hdr->csum_start = skb->csum_start - skb_headroom(skb);
- hdr->csum_offset = skb->csum_offset;
+ hdr->hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
+ hdr->hdr.csum_start = skb->csum_start - skb_headroom(skb);
+ hdr->hdr.csum_offset = skb->csum_offset;
} else {
- hdr->flags = 0;
- hdr->csum_offset = hdr->csum_start = 0;
+ hdr->hdr.flags = 0;
+ hdr->hdr.csum_offset = hdr->hdr.csum_start = 0;
}
if (skb_is_gso(skb)) {
- hdr->hdr_len = skb_headlen(skb);
- hdr->gso_size = skb_shinfo(skb)->gso_size;
+ hdr->hdr.hdr_len = skb_headlen(skb);
+ hdr->hdr.gso_size = skb_shinfo(skb)->gso_size;
if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
- hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
+ hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
- hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+ hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
- hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
+ hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP;
else
BUG();
if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN)
- hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN;
+ hdr->hdr.gso_type |= VIRTIO_NET_HDR_GSO_ECN;
} else {
- hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
- hdr->gso_size = hdr->hdr_len = 0;
+ hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE;
+ hdr->hdr.gso_size = hdr->hdr.hdr_len = 0;
}
- mhdr->num_buffers = 0;
+ hdr->mhdr.num_buffers = 0;
/* Encode metadata header at front. */
if (vi->mergeable_rx_bufs)
- sg_set_buf(sg, mhdr, sizeof(*mhdr));
+ sg_set_buf(sg, &hdr->mhdr, sizeof hdr->mhdr);
else
- sg_set_buf(sg, hdr, sizeof(*hdr));
-
- num = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1;
+ sg_set_buf(sg, &hdr->hdr, sizeof hdr->hdr);
- err = vi->svq->vq_ops->add_buf(vi->svq, sg, num, 0, skb);
- if (err >= 0 && !vi->free_in_tasklet) {
- /* Don't wait up for transmitted skbs to be freed. */
- skb_orphan(skb);
- nf_reset(skb);
- mod_timer(&vi->xmit_free_timer, jiffies + (HZ/10));
- }
-
- return err;
-}
-
-static void xmit_tasklet(unsigned long data)
-{
- struct virtnet_info *vi = (void *)data;
-
- netif_tx_lock_bh(vi->dev);
- free_old_xmit_skbs(vi);
- netif_tx_unlock_bh(vi->dev);
+ hdr->num_sg = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1;
+ return vi->svq->vq_ops->add_buf(vi->svq, sg, hdr->num_sg, 0, skb);
}
static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct virtnet_info *vi = netdev_priv(dev);
+ int capacity;
again:
/* Free up any pending old buffers before queueing new ones. */
free_old_xmit_skbs(vi);
- /* Put new one in send queue and do transmit */
- __skb_queue_head(&vi->send, skb);
- if (likely(xmit_skb(vi, skb) >= 0)) {
- vi->svq->vq_ops->kick(vi->svq);
- return NETDEV_TX_OK;
- }
+ /* Try to transmit */
+ capacity = xmit_skb(vi, skb);
- /* Ring too full for this packet, remove it from queue again. */
- pr_debug("%s: virtio not prepared to send\n", dev->name);
- __skb_unlink(skb, &vi->send);
- netif_stop_queue(dev);
-
- /* Activate callback for using skbs: if this returns false it
- * means some were used in the meantime. */
- if (unlikely(!vi->svq->vq_ops->enable_cb(vi->svq))) {
- vi->svq->vq_ops->disable_cb(vi->svq);
- netif_start_queue(dev);
- goto again;
+ /* This can happen with OOM and indirect buffers. */
+ if (unlikely(capacity < 0)) {
+ netif_stop_queue(dev);
+ dev_warn(&dev->dev, "Unexpected full queue\n");
+ if (unlikely(!vi->svq->vq_ops->enable_cb(vi->svq))) {
+ vi->svq->vq_ops->disable_cb(vi->svq);
+ netif_start_queue(dev);
+ goto again;
+ }
+ return NETDEV_TX_BUSY;
}
- return NETDEV_TX_BUSY;
+ vi->svq->vq_ops->kick(vi->svq);
+
+ /* Don't wait up for transmitted skbs to be freed. */
+ skb_orphan(skb);
+ nf_reset(skb);
+
+ /* Apparently nice girls don't return TX_BUSY; stop the queue
+ * before it gets out of hand. Naturally, this wastes entries. */
+ if (capacity < 2+MAX_SKB_FRAGS) {
+ netif_stop_queue(dev);
+ if (unlikely(!vi->svq->vq_ops->enable_cb(vi->svq))) {
+ /* More just got used, free them then recheck. */
+ capacity += free_old_xmit_skbs(vi);
+ if (capacity >= 2+MAX_SKB_FRAGS) {
+ netif_start_queue(dev);
+ vi->svq->vq_ops->disable_cb(vi->svq);
+ }
+ }
+ }
+
+ return NETDEV_TX_OK;
}
static int virtnet_set_mac_address(struct net_device *dev, void *p)
struct virtio_net_ctrl_mac *mac_data;
struct dev_addr_list *addr;
struct netdev_hw_addr *ha;
+ int uc_count;
+ int mc_count;
void *buf;
int i;
dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
allmulti ? "en" : "dis");
+ uc_count = netdev_uc_count(dev);
+ mc_count = netdev_mc_count(dev);
/* MAC filter - use one buffer for both lists */
- mac_data = buf = kzalloc(((dev->uc.count + dev->mc_count) * ETH_ALEN) +
- (2 * sizeof(mac_data->entries)), GFP_ATOMIC);
+ buf = kzalloc(((uc_count + mc_count) * ETH_ALEN) +
+ (2 * sizeof(mac_data->entries)), GFP_ATOMIC);
+ mac_data = buf;
if (!buf) {
dev_warn(&dev->dev, "No memory for MAC address buffer\n");
return;
sg_init_table(sg, 2);
/* Store the unicast list and count in the front of the buffer */
- mac_data->entries = dev->uc.count;
+ mac_data->entries = uc_count;
i = 0;
- list_for_each_entry(ha, &dev->uc.list, list)
+ netdev_for_each_uc_addr(ha, dev)
memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN);
sg_set_buf(&sg[0], mac_data,
- sizeof(mac_data->entries) + (dev->uc.count * ETH_ALEN));
+ sizeof(mac_data->entries) + (uc_count * ETH_ALEN));
/* multicast list and count fill the end */
- mac_data = (void *)&mac_data->macs[dev->uc.count][0];
+ mac_data = (void *)&mac_data->macs[uc_count][0];
- mac_data->entries = dev->mc_count;
- addr = dev->mc_list;
- for (i = 0; i < dev->mc_count; i++, addr = addr->next)
- memcpy(&mac_data->macs[i][0], addr->da_addr, ETH_ALEN);
+ mac_data->entries = mc_count;
+ i = 0;
+ netdev_for_each_mc_addr(addr, dev)
+ memcpy(&mac_data->macs[i++][0], addr->da_addr, ETH_ALEN);
sg_set_buf(&sg[1], mac_data,
- sizeof(mac_data->entries) + (dev->mc_count * ETH_ALEN));
+ sizeof(mac_data->entries) + (mc_count * ETH_ALEN));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC,
VIRTIO_NET_CTRL_MAC_TABLE_SET,
vi->pages = NULL;
INIT_DELAYED_WORK(&vi->refill, refill_work);
- /* If they give us a callback when all buffers are done, we don't need
- * the timer. */
- vi->free_in_tasklet = virtio_has_feature(vdev,VIRTIO_F_NOTIFY_ON_EMPTY);
-
/* If we can receive ANY GSO packets, we must allocate large ones. */
- if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4)
- || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6)
- || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN))
+ if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
+ virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) ||
+ virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN))
vi->big_packets = true;
if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
dev->features |= NETIF_F_HW_VLAN_FILTER;
}
- /* Initialize our empty receive and send queues. */
- skb_queue_head_init(&vi->recv);
- skb_queue_head_init(&vi->send);
-
- tasklet_init(&vi->tasklet, xmit_tasklet, (unsigned long)vi);
-
- if (!vi->free_in_tasklet)
- setup_timer(&vi->xmit_free_timer, xmit_free, (unsigned long)vi);
-
err = register_netdev(dev);
if (err) {
pr_debug("virtio_net: registering device failed\n");
return err;
}
-static void virtnet_remove(struct virtio_device *vdev)
+static void free_unused_bufs(struct virtnet_info *vi)
+{
+ void *buf;
+ while (1) {
+ buf = vi->svq->vq_ops->detach_unused_buf(vi->svq);
+ if (!buf)
+ break;
+ dev_kfree_skb(buf);
+ }
+ while (1) {
+ buf = vi->rvq->vq_ops->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 __devexit virtnet_remove(struct virtio_device *vdev)
{
struct virtnet_info *vi = vdev->priv;
- struct sk_buff *skb;
/* Stop all the virtqueues. */
vdev->config->reset(vdev);
- if (!vi->free_in_tasklet)
- del_timer_sync(&vi->xmit_free_timer);
-
- /* Free our skbs in send and recv queues, if any. */
- while ((skb = __skb_dequeue(&vi->recv)) != NULL) {
- kfree_skb(skb);
- vi->num--;
- }
- __skb_queue_purge(&vi->send);
-
- BUG_ON(vi->num != 0);
unregister_netdev(vi->dev);
cancel_delayed_work_sync(&vi->refill);
+ /* Free unused buffers in both send and recv, if any. */
+ free_unused_bufs(vi);
+
vdev->config->del_vqs(vi->vdev);
while (vi->pages)
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_F_NOTIFY_ON_EMPTY,
};
-static struct virtio_driver virtio_net = {
+static struct virtio_driver virtio_net_driver = {
.feature_table = features,
.feature_table_size = ARRAY_SIZE(features),
.driver.name = KBUILD_MODNAME,
static int __init init(void)
{
- return register_virtio_driver(&virtio_net);
+ return register_virtio_driver(&virtio_net_driver);
}
static void __exit fini(void)
{
- unregister_virtio_driver(&virtio_net);
+ unregister_virtio_driver(&virtio_net_driver);
}
module_init(init);
module_exit(fini);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff