4265f161b6
There is a race in virtio_net, dealing with disabling/enabling the callback. I saw the following oops: kernel BUG at /space/kvm/drivers/virtio/virtio_ring.c:218! illegal operation: 0001 [#1] SMP Modules linked in: sunrpc dm_mod CPU: 2 Not tainted 2.6.25-rc1zlive-host-10623-gd358142-dirty #99 Process swapper (pid: 0, task: 000000000f85a610, ksp: 000000000f873c60) Krnl PSW : 0404300180000000 00000000002b81a6 (vring_disable_cb+0x16/0x20) R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:0 CC:3 PM:0 EA:3 Krnl GPRS: 0000000000000001 0000000000000001 0000000010005800 0000000000000001 000000000f3a0900 000000000f85a610 0000000000000000 0000000000000000 0000000000000000 000000000f870000 0000000000000000 0000000000001237 000000000f3a0920 000000000010ff74 00000000002846f6 000000000fa0bcd8 Krnl Code: 00000000002b819a: a7110001 tmll %r1,1 00000000002b819e: a7840004 brc 8,2b81a6 00000000002b81a2: a7f40001 brc 15,2b81a4 >00000000002b81a6: a51b0001 oill %r1,1 00000000002b81aa: 40102000 sth %r1,0(%r2) 00000000002b81ae: 07fe bcr 15,%r14 00000000002b81b0: eb7ff0380024 stmg %r7,%r15,56(%r15) 00000000002b81b6: a7f13e00 tmll %r15,15872 Call Trace: ([<000000000fa0bcd0>] 0xfa0bcd0) [<00000000002b8350>] vring_interrupt+0x5c/0x6c [<000000000010ab08>] do_extint+0xb8/0xf0 [<0000000000110716>] ext_no_vtime+0x16/0x1a [<0000000000107e72>] cpu_idle+0x1c2/0x1e0 The problem can be triggered with a high amount of host->guest traffic. I think its the following race: poll says netif_rx_complete poll calls enable_cb enable_cb opens the interrupt mask a new packet comes, an interrupt is triggered----\ enable_cb sees that there is more work | enable_cb disables the interrupt | . V . interrupt is delivered . skb_recv_done does atomic napi test, ok some waiting disable_cb is called->check fails->bang! . poll would do napi check poll would do disable_cb The fix is to let enable_cb not disable the interrupt again, but expect the caller to do the cleanup if it returns false. In that case, the interrupt is only disabled, if the napi test_set_bit was successful. Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (cleaned up doco)
479 lines
12 KiB
C
479 lines
12 KiB
C
/* A simple network driver using virtio.
|
|
*
|
|
* Copyright 2007 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
|
*/
|
|
//#define DEBUG
|
|
#include <linux/netdevice.h>
|
|
#include <linux/etherdevice.h>
|
|
#include <linux/module.h>
|
|
#include <linux/virtio.h>
|
|
#include <linux/virtio_net.h>
|
|
#include <linux/scatterlist.h>
|
|
|
|
static int napi_weight = 128;
|
|
module_param(napi_weight, int, 0444);
|
|
|
|
static int csum = 1, gso = 1;
|
|
module_param(csum, bool, 0444);
|
|
module_param(gso, bool, 0444);
|
|
|
|
/* FIXME: MTU in config. */
|
|
#define MAX_PACKET_LEN (ETH_HLEN+ETH_DATA_LEN)
|
|
|
|
struct virtnet_info
|
|
{
|
|
struct virtio_device *vdev;
|
|
struct virtqueue *rvq, *svq;
|
|
struct net_device *dev;
|
|
struct napi_struct napi;
|
|
|
|
/* Number of input buffers, and max we've ever had. */
|
|
unsigned int num, max;
|
|
|
|
/* Receive & send queues. */
|
|
struct sk_buff_head recv;
|
|
struct sk_buff_head send;
|
|
};
|
|
|
|
static inline struct virtio_net_hdr *skb_vnet_hdr(struct sk_buff *skb)
|
|
{
|
|
return (struct virtio_net_hdr *)skb->cb;
|
|
}
|
|
|
|
static inline void vnet_hdr_to_sg(struct scatterlist *sg, struct sk_buff *skb)
|
|
{
|
|
sg_init_one(sg, skb_vnet_hdr(skb), sizeof(struct virtio_net_hdr));
|
|
}
|
|
|
|
static void skb_xmit_done(struct virtqueue *svq)
|
|
{
|
|
struct virtnet_info *vi = svq->vdev->priv;
|
|
|
|
/* Suppress further interrupts. */
|
|
svq->vq_ops->disable_cb(svq);
|
|
/* We were waiting for more output buffers. */
|
|
netif_wake_queue(vi->dev);
|
|
}
|
|
|
|
static void receive_skb(struct net_device *dev, struct sk_buff *skb,
|
|
unsigned len)
|
|
{
|
|
struct virtio_net_hdr *hdr = skb_vnet_hdr(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++;
|
|
goto drop;
|
|
}
|
|
len -= sizeof(struct virtio_net_hdr);
|
|
BUG_ON(len > MAX_PACKET_LEN);
|
|
|
|
skb_trim(skb, len);
|
|
skb->protocol = eth_type_trans(skb, dev);
|
|
pr_debug("Receiving skb proto 0x%04x len %i type %i\n",
|
|
ntohs(skb->protocol), skb->len, skb->pkt_type);
|
|
dev->stats.rx_bytes += skb->len;
|
|
dev->stats.rx_packets++;
|
|
|
|
if (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))
|
|
goto frame_err;
|
|
}
|
|
|
|
if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
|
|
pr_debug("GSO!\n");
|
|
switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
|
|
case VIRTIO_NET_HDR_GSO_TCPV4:
|
|
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
|
|
break;
|
|
case VIRTIO_NET_HDR_GSO_UDP:
|
|
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
|
|
break;
|
|
case VIRTIO_NET_HDR_GSO_TCPV6:
|
|
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->gso_type);
|
|
goto frame_err;
|
|
}
|
|
|
|
if (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;
|
|
if (skb_shinfo(skb)->gso_size == 0) {
|
|
if (net_ratelimit())
|
|
printk(KERN_WARNING "%s: zero gso size.\n",
|
|
dev->name);
|
|
goto frame_err;
|
|
}
|
|
|
|
/* Header must be checked, and gso_segs computed. */
|
|
skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
|
|
skb_shinfo(skb)->gso_segs = 0;
|
|
}
|
|
|
|
netif_receive_skb(skb);
|
|
return;
|
|
|
|
frame_err:
|
|
dev->stats.rx_frame_errors++;
|
|
drop:
|
|
dev_kfree_skb(skb);
|
|
}
|
|
|
|
static void try_fill_recv(struct virtnet_info *vi)
|
|
{
|
|
struct sk_buff *skb;
|
|
struct scatterlist sg[1+MAX_SKB_FRAGS];
|
|
int num, err;
|
|
|
|
sg_init_table(sg, 1+MAX_SKB_FRAGS);
|
|
for (;;) {
|
|
skb = netdev_alloc_skb(vi->dev, MAX_PACKET_LEN);
|
|
if (unlikely(!skb))
|
|
break;
|
|
|
|
skb_put(skb, MAX_PACKET_LEN);
|
|
vnet_hdr_to_sg(sg, skb);
|
|
num = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1;
|
|
skb_queue_head(&vi->recv, skb);
|
|
|
|
err = vi->rvq->vq_ops->add_buf(vi->rvq, sg, 0, num, skb);
|
|
if (err) {
|
|
skb_unlink(skb, &vi->recv);
|
|
kfree_skb(skb);
|
|
break;
|
|
}
|
|
vi->num++;
|
|
}
|
|
if (unlikely(vi->num > vi->max))
|
|
vi->max = vi->num;
|
|
vi->rvq->vq_ops->kick(vi->rvq);
|
|
}
|
|
|
|
static void skb_recv_done(struct virtqueue *rvq)
|
|
{
|
|
struct virtnet_info *vi = rvq->vdev->priv;
|
|
/* Schedule NAPI, Suppress further interrupts if successful. */
|
|
if (netif_rx_schedule_prep(vi->dev, &vi->napi)) {
|
|
rvq->vq_ops->disable_cb(rvq);
|
|
__netif_rx_schedule(vi->dev, &vi->napi);
|
|
}
|
|
}
|
|
|
|
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;
|
|
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--;
|
|
received++;
|
|
}
|
|
|
|
/* FIXME: If we oom and completely run out of inbufs, we need
|
|
* to start a timer trying to fill more. */
|
|
if (vi->num < vi->max / 2)
|
|
try_fill_recv(vi);
|
|
|
|
/* Out of packets? */
|
|
if (received < budget) {
|
|
netif_rx_complete(vi->dev, napi);
|
|
if (unlikely(!vi->rvq->vq_ops->enable_cb(vi->rvq))
|
|
&& napi_schedule_prep(napi)) {
|
|
vi->rvq->vq_ops->disable_cb(vi->rvq);
|
|
__netif_rx_schedule(vi->dev, napi);
|
|
goto again;
|
|
}
|
|
}
|
|
|
|
return received;
|
|
}
|
|
|
|
static void free_old_xmit_skbs(struct virtnet_info *vi)
|
|
{
|
|
struct sk_buff *skb;
|
|
unsigned int len;
|
|
|
|
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 += len;
|
|
vi->dev->stats.tx_packets++;
|
|
kfree_skb(skb);
|
|
}
|
|
}
|
|
|
|
static int start_xmit(struct sk_buff *skb, struct net_device *dev)
|
|
{
|
|
struct virtnet_info *vi = netdev_priv(dev);
|
|
int num, err;
|
|
struct scatterlist sg[1+MAX_SKB_FRAGS];
|
|
struct virtio_net_hdr *hdr;
|
|
const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
|
|
DECLARE_MAC_BUF(mac);
|
|
|
|
sg_init_table(sg, 1+MAX_SKB_FRAGS);
|
|
|
|
pr_debug("%s: xmit %p %s\n", dev->name, skb, print_mac(mac, dest));
|
|
|
|
/* Encode metadata header at front. */
|
|
hdr = skb_vnet_hdr(skb);
|
|
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;
|
|
} else {
|
|
hdr->flags = 0;
|
|
hdr->csum_offset = hdr->csum_start = 0;
|
|
}
|
|
|
|
if (skb_is_gso(skb)) {
|
|
hdr->hdr_len = skb_transport_header(skb) - skb->data;
|
|
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;
|
|
else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
|
|
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;
|
|
else
|
|
BUG();
|
|
if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN)
|
|
hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN;
|
|
} else {
|
|
hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
|
|
hdr->gso_size = hdr->hdr_len = 0;
|
|
}
|
|
|
|
vnet_hdr_to_sg(sg, skb);
|
|
num = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1;
|
|
__skb_queue_head(&vi->send, skb);
|
|
|
|
again:
|
|
/* Free up any pending old buffers before queueing new ones. */
|
|
free_old_xmit_skbs(vi);
|
|
err = vi->svq->vq_ops->add_buf(vi->svq, sg, num, 0, skb);
|
|
if (err) {
|
|
pr_debug("%s: virtio not prepared to send\n", dev->name);
|
|
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))) {
|
|
printk("Unlikely: restart svq race\n");
|
|
vi->svq->vq_ops->disable_cb(vi->svq);
|
|
netif_start_queue(dev);
|
|
goto again;
|
|
}
|
|
__skb_unlink(skb, &vi->send);
|
|
|
|
return NETDEV_TX_BUSY;
|
|
}
|
|
vi->svq->vq_ops->kick(vi->svq);
|
|
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_NET_POLL_CONTROLLER
|
|
static void virtnet_netpoll(struct net_device *dev)
|
|
{
|
|
struct virtnet_info *vi = netdev_priv(dev);
|
|
|
|
napi_schedule(&vi->napi);
|
|
}
|
|
#endif
|
|
|
|
static int virtnet_open(struct net_device *dev)
|
|
{
|
|
struct virtnet_info *vi = netdev_priv(dev);
|
|
|
|
napi_enable(&vi->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 (netif_rx_schedule_prep(dev, &vi->napi)) {
|
|
vi->rvq->vq_ops->disable_cb(vi->rvq);
|
|
__netif_rx_schedule(dev, &vi->napi);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static int virtnet_close(struct net_device *dev)
|
|
{
|
|
struct virtnet_info *vi = netdev_priv(dev);
|
|
|
|
napi_disable(&vi->napi);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int virtnet_probe(struct virtio_device *vdev)
|
|
{
|
|
int err;
|
|
struct net_device *dev;
|
|
struct virtnet_info *vi;
|
|
|
|
/* Allocate ourselves a network device with room for our info */
|
|
dev = alloc_etherdev(sizeof(struct virtnet_info));
|
|
if (!dev)
|
|
return -ENOMEM;
|
|
|
|
/* Set up network device as normal. */
|
|
dev->open = virtnet_open;
|
|
dev->stop = virtnet_close;
|
|
dev->hard_start_xmit = start_xmit;
|
|
dev->features = NETIF_F_HIGHDMA;
|
|
#ifdef CONFIG_NET_POLL_CONTROLLER
|
|
dev->poll_controller = virtnet_netpoll;
|
|
#endif
|
|
SET_NETDEV_DEV(dev, &vdev->dev);
|
|
|
|
/* Do we support "hardware" checksums? */
|
|
if (csum && vdev->config->feature(vdev, VIRTIO_NET_F_CSUM)) {
|
|
/* This opens up the world of extra features. */
|
|
dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
|
|
if (gso && vdev->config->feature(vdev, VIRTIO_NET_F_GSO)) {
|
|
dev->features |= NETIF_F_TSO | NETIF_F_UFO
|
|
| NETIF_F_TSO_ECN | NETIF_F_TSO6;
|
|
}
|
|
}
|
|
|
|
/* Configuration may specify what MAC to use. Otherwise random. */
|
|
if (vdev->config->feature(vdev, VIRTIO_NET_F_MAC)) {
|
|
vdev->config->get(vdev,
|
|
offsetof(struct virtio_net_config, mac),
|
|
dev->dev_addr, dev->addr_len);
|
|
} else
|
|
random_ether_addr(dev->dev_addr);
|
|
|
|
/* 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;
|
|
|
|
/* We expect two virtqueues, receive then send. */
|
|
vi->rvq = vdev->config->find_vq(vdev, 0, skb_recv_done);
|
|
if (IS_ERR(vi->rvq)) {
|
|
err = PTR_ERR(vi->rvq);
|
|
goto free;
|
|
}
|
|
|
|
vi->svq = vdev->config->find_vq(vdev, 1, skb_xmit_done);
|
|
if (IS_ERR(vi->svq)) {
|
|
err = PTR_ERR(vi->svq);
|
|
goto free_recv;
|
|
}
|
|
|
|
/* Initialize our empty receive and send queues. */
|
|
skb_queue_head_init(&vi->recv);
|
|
skb_queue_head_init(&vi->send);
|
|
|
|
err = register_netdev(dev);
|
|
if (err) {
|
|
pr_debug("virtio_net: registering device failed\n");
|
|
goto free_send;
|
|
}
|
|
|
|
/* Last of all, set up some receive buffers. */
|
|
try_fill_recv(vi);
|
|
|
|
/* If we didn't even get one input buffer, we're useless. */
|
|
if (vi->num == 0) {
|
|
err = -ENOMEM;
|
|
goto unregister;
|
|
}
|
|
|
|
pr_debug("virtnet: registered device %s\n", dev->name);
|
|
return 0;
|
|
|
|
unregister:
|
|
unregister_netdev(dev);
|
|
free_send:
|
|
vdev->config->del_vq(vi->svq);
|
|
free_recv:
|
|
vdev->config->del_vq(vi->rvq);
|
|
free:
|
|
free_netdev(dev);
|
|
return err;
|
|
}
|
|
|
|
static void virtnet_remove(struct virtio_device *vdev)
|
|
{
|
|
struct virtnet_info *vi = vdev->priv;
|
|
struct sk_buff *skb;
|
|
|
|
/* Stop all the virtqueues. */
|
|
vdev->config->reset(vdev);
|
|
|
|
/* Free our skbs in send and recv queues, if any. */
|
|
while ((skb = __skb_dequeue(&vi->recv)) != NULL) {
|
|
kfree_skb(skb);
|
|
vi->num--;
|
|
}
|
|
while ((skb = __skb_dequeue(&vi->send)) != NULL)
|
|
kfree_skb(skb);
|
|
|
|
BUG_ON(vi->num != 0);
|
|
|
|
vdev->config->del_vq(vi->svq);
|
|
vdev->config->del_vq(vi->rvq);
|
|
unregister_netdev(vi->dev);
|
|
free_netdev(vi->dev);
|
|
}
|
|
|
|
static struct virtio_device_id id_table[] = {
|
|
{ VIRTIO_ID_NET, VIRTIO_DEV_ANY_ID },
|
|
{ 0 },
|
|
};
|
|
|
|
static struct virtio_driver virtio_net = {
|
|
.driver.name = KBUILD_MODNAME,
|
|
.driver.owner = THIS_MODULE,
|
|
.id_table = id_table,
|
|
.probe = virtnet_probe,
|
|
.remove = __devexit_p(virtnet_remove),
|
|
};
|
|
|
|
static int __init init(void)
|
|
{
|
|
return register_virtio_driver(&virtio_net);
|
|
}
|
|
|
|
static void __exit fini(void)
|
|
{
|
|
unregister_virtio_driver(&virtio_net);
|
|
}
|
|
module_init(init);
|
|
module_exit(fini);
|
|
|
|
MODULE_DEVICE_TABLE(virtio, id_table);
|
|
MODULE_DESCRIPTION("Virtio network driver");
|
|
MODULE_LICENSE("GPL");
|