From: Mark McLoughlin <markmc@redhat.com>
Date: Fri, 22 Aug 2008 16:05:27 +0100
Subject: [xen] virtio: add PV network and block drivers for KVM
Message-id: 1219417527.24064.18.camel@muff
O-Subject: Re: [RHEL5.3 PATCH] virtio: Add paravirtual network and block drivers for KVM
Bugzilla: 446214
RH-Acked-by: Herbert Xu <herbert.xu@redhat.com>
RH-Acked-by: Chris Wright <chrisw@redhat.com>
RH-Acked-by: Don Dutile <ddutile@redhat.com>
RH-Acked-by: Rik van Riel <riel@redhat.com>
https://bugzilla.redhat.com/446214
virtio is a driver framework for virtual I/O devices. Drivers
are coded against a device enumeration and data transport
abstraction and individual hypervisors provide the
implementation for the abstraction. virtio was first added
upstream in 2.6.24.
In order to provide superior network and disk performance
when running RHEL5 under KVM, we are backporting the network
and block drivers (virtio_net and virtio_blk), the virtio
abstraction (virtio and virtio_ring) and the KVM
implementation (virtio_pci).
The 2.6.27-rc3 version of the code is used because a number
of fairly well tested performance related changes have been
included recently (e.g. GSO support in virtio_net).
A number of userspace changes are also required to make use
of these drivers:
- /dev/vda labelling in selinux-policy (#446229)
- LVM support for discovering /dev/vda (#446228)
- making mkinitrd include virtio_pci (#446227)
- kudzu support (#446230)
- anaconda support (#446232)
Basic testing - e.g. test installs - have been performed
with these drivers in RHEL5 guests running on F-9 and
rawhide KVM hosts.
The drivers were backported as follows:
- copy over the 2.6.27-rc3 sources
- run hack-module.awk from kvm-guest-drivers-linux to make
the code buildable on RHEL5
- replace all the compat hacks added by hack-module.awk
with cleaner, easier to review changes
I will follow up this mail with a patch showing the diff
between the code below and the code in 2.6.27-rc3 in order
to ease review.
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index 5173059..0f4c8b5 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -1107,6 +1107,8 @@ config XEN_PCIDEV_FE_DEBUG
help
Enables some debug statements within the PCI Frontend.
+source "drivers/virtio/Kconfig"
+
source "drivers/pci/pcie/Kconfig"
config PCI_DOMAINS
diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig
index d8361e5..5c2a9eb 100644
--- a/arch/x86_64/Kconfig
+++ b/arch/x86_64/Kconfig
@@ -686,6 +686,8 @@ config XEN_PCIDEV_FE_DEBUG
help
Enables some debug statements within the PCI Frontend.
+source "drivers/virtio/Kconfig"
+
source "drivers/pci/pcie/Kconfig"
config PCI_DOMAINS
diff --git a/drivers/Makefile b/drivers/Makefile
index 083ac5b..7dbed7d 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -80,3 +80,4 @@ obj-$(CONFIG_CRYPTO) += crypto/
obj-$(CONFIG_SUPERH) += sh/
obj-$(CONFIG_GENERIC_TIME) += clocksource/
obj-$(CONFIG_DMA_ENGINE) += dma/
+obj-$(CONFIG_VIRTIO) += virtio/
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index b5382ce..4c5af7d 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -467,4 +467,11 @@ config ATA_OVER_ETH
This driver provides Support for ATA over Ethernet block
devices like the Coraid EtherDrive (R) Storage Blade.
+config VIRTIO_BLK
+ tristate "Virtio block driver (EXPERIMENTAL)"
+ depends on EXPERIMENTAL && VIRTIO
+ ---help---
+ This is the virtual block driver for virtio. It can be used with
+ lguest or QEMU based VMMs (like KVM or Xen). Say Y or M.
+
endmenu
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 410f259..380c08b 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o
obj-$(CONFIG_BLK_DEV_UMEM) += umem.o
obj-$(CONFIG_BLK_DEV_NBD) += nbd.o
obj-$(CONFIG_BLK_DEV_CRYPTOLOOP) += cryptoloop.o
+obj-$(CONFIG_VIRTIO_BLK) += virtio_blk.o
obj-$(CONFIG_VIODASD) += viodasd.o
obj-$(CONFIG_BLK_DEV_SX8) += sx8.o
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
new file mode 100644
index 0000000..a102e31
--- /dev/null
+++ b/drivers/block/virtio_blk.c
@@ -0,0 +1,375 @@
+//#define DEBUG
+#include <linux/spinlock.h>
+#include <linux/blkdev.h>
+#include <linux/hdreg.h>
+#include <linux/virtio.h>
+#include <linux/virtio_blk.h>
+#include <linux/scatterlist.h>
+
+#define VIRTIO_MAX_SG (3+MAX_PHYS_SEGMENTS)
+#define PART_BITS 4
+
+static int major, index;
+
+struct virtio_blk
+{
+ spinlock_t lock;
+
+ struct virtio_device *vdev;
+ struct virtqueue *vq;
+
+ /* The disk structure for the kernel. */
+ struct gendisk *disk;
+
+ /* Request tracking. */
+ struct list_head reqs;
+
+ mempool_t *pool;
+
+ /* Scatterlist: can be too big for stack. */
+ struct scatterlist sg[VIRTIO_MAX_SG];
+};
+
+struct virtblk_req
+{
+ struct list_head list;
+ struct request *req;
+ struct virtio_blk_outhdr out_hdr;
+ u8 status;
+};
+
+static void blk_done(struct virtqueue *vq)
+{
+ struct virtio_blk *vblk = vq->vdev->priv;
+ struct virtblk_req *vbr;
+ unsigned int len;
+ unsigned long flags;
+
+ spin_lock_irqsave(&vblk->lock, flags);
+ while ((vbr = vblk->vq->vq_ops->get_buf(vblk->vq, &len)) != NULL) {
+ int uptodate;
+ switch (vbr->status) {
+ case VIRTIO_BLK_S_OK:
+ uptodate = 1;
+ break;
+ case VIRTIO_BLK_S_UNSUPP:
+ uptodate = -ENOTTY;
+ break;
+ default:
+ uptodate = 0;
+ break;
+ }
+
+ if (!end_that_request_first(vbr->req, uptodate, vbr->req->hard_nr_sectors)) {
+ add_disk_randomness(vbr->req->rq_disk);
+ end_that_request_last(vbr->req, uptodate);
+ }
+ list_del(&vbr->list);
+ mempool_free(vbr, vblk->pool);
+ }
+ /* In case queue is stopped waiting for more buffers. */
+ blk_start_queue(vblk->disk->queue);
+ spin_unlock_irqrestore(&vblk->lock, flags);
+}
+
+static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
+ struct request *req)
+{
+ unsigned long num, out, in;
+ struct virtblk_req *vbr;
+
+ vbr = mempool_alloc(vblk->pool, GFP_ATOMIC);
+ if (!vbr)
+ /* When another request finishes we'll try again. */
+ return false;
+
+ vbr->req = req;
+ if (blk_fs_request(vbr->req)) {
+ vbr->out_hdr.type = 0;
+ vbr->out_hdr.sector = vbr->req->sector;
+ vbr->out_hdr.ioprio = vbr->req->ioprio;
+ } else if (blk_pc_request(vbr->req)) {
+ vbr->out_hdr.type = VIRTIO_BLK_T_SCSI_CMD;
+ vbr->out_hdr.sector = 0;
+ vbr->out_hdr.ioprio = vbr->req->ioprio;
+ } else {
+ /* We don't put anything else in the queue. */
+ BUG();
+ }
+
+ if (blk_barrier_rq(vbr->req))
+ vbr->out_hdr.type |= VIRTIO_BLK_T_BARRIER;
+
+ /* This init could be done at vblk creation time */
+ sg_set_buf(&vblk->sg[0], &vbr->out_hdr, sizeof(vbr->out_hdr));
+ num = blk_rq_map_sg(q, vbr->req, vblk->sg+1);
+ sg_set_buf(&vblk->sg[num+1], &vbr->status, sizeof(vbr->status));
+
+ if (rq_data_dir(vbr->req) == WRITE) {
+ vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
+ out = 1 + num;
+ in = 1;
+ } else {
+ vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
+ out = 1;
+ in = 1 + num;
+ }
+
+ if (vblk->vq->vq_ops->add_buf(vblk->vq, vblk->sg, out, in, vbr)) {
+ mempool_free(vbr, vblk->pool);
+ return false;
+ }
+
+ list_add_tail(&vbr->list, &vblk->reqs);
+ return true;
+}
+
+static void do_virtblk_request(struct request_queue *q)
+{
+ struct virtio_blk *vblk = NULL;
+ struct request *req;
+ unsigned int issued = 0;
+
+ while ((req = elv_next_request(q)) != NULL) {
+ vblk = req->rq_disk->private_data;
+ BUG_ON(req->nr_phys_segments > ARRAY_SIZE(vblk->sg));
+
+ /* If this request fails, stop queue and wait for something to
+ finish to restart it. */
+ if (!do_req(q, vblk, req)) {
+ blk_stop_queue(q);
+ break;
+ }
+ blkdev_dequeue_request(req);
+ issued++;
+ }
+
+ if (issued)
+ vblk->vq->vq_ops->kick(vblk->vq);
+}
+
+static int virtblk_ioctl(struct inode *inode, struct file *filp,
+ unsigned cmd, unsigned long data)
+{
+ return scsi_cmd_ioctl(filp,
+ inode->i_bdev->bd_disk, cmd,
+ (void __user *)data);
+}
+
+/* We provide getgeo only to please some old bootloader/partitioning tools */
+static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
+{
+ struct virtio_blk *vblk = bd->bd_disk->private_data;
+ struct virtio_blk_geometry vgeo;
+ int err;
+
+ /* see if the host passed in geometry config */
+ err = virtio_config_val(vblk->vdev, VIRTIO_BLK_F_GEOMETRY,
+ offsetof(struct virtio_blk_config, geometry),
+ &vgeo);
+
+ if (!err) {
+ geo->heads = vgeo.heads;
+ geo->sectors = vgeo.sectors;
+ geo->cylinders = vgeo.cylinders;
+ } else {
+ /* some standard values, similar to sd */
+ geo->heads = 1 << 6;
+ geo->sectors = 1 << 5;
+ geo->cylinders = get_capacity(bd->bd_disk) >> 11;
+ }
+ return 0;
+}
+
+static struct block_device_operations virtblk_fops = {
+ .ioctl = virtblk_ioctl,
+ .owner = THIS_MODULE,
+ .getgeo = virtblk_getgeo,
+};
+
+static int index_to_minor(int index)
+{
+ return index << PART_BITS;
+}
+
+static int virtblk_probe(struct virtio_device *vdev)
+{
+ struct virtio_blk *vblk;
+ int err;
+ u64 cap;
+ u32 v;
+ u32 blk_size;
+
+ if (index_to_minor(index) >= 1 << MINORBITS)
+ return -ENOSPC;
+
+ vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
+ if (!vblk) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ INIT_LIST_HEAD(&vblk->reqs);
+ spin_lock_init(&vblk->lock);
+ vblk->vdev = vdev;
+
+ /* We expect one virtqueue, for output. */
+ vblk->vq = vdev->config->find_vq(vdev, 0, blk_done);
+ if (IS_ERR(vblk->vq)) {
+ err = PTR_ERR(vblk->vq);
+ goto out_free_vblk;
+ }
+
+ vblk->pool = mempool_create_kmalloc_pool(1,sizeof(struct virtblk_req));
+ if (!vblk->pool) {
+ err = -ENOMEM;
+ goto out_free_vq;
+ }
+
+ /* FIXME: How many partitions? How long is a piece of string? */
+ vblk->disk = alloc_disk(1 << PART_BITS);
+ if (!vblk->disk) {
+ err = -ENOMEM;
+ goto out_mempool;
+ }
+
+ vblk->disk->queue = blk_init_queue(do_virtblk_request, &vblk->lock);
+ if (!vblk->disk->queue) {
+ err = -ENOMEM;
+ goto out_put_disk;
+ }
+
+ if (index < 26) {
+ sprintf(vblk->disk->disk_name, "vd%c", 'a' + index % 26);
+ } else if (index < (26 + 1) * 26) {
+ sprintf(vblk->disk->disk_name, "vd%c%c",
+ 'a' + index / 26 - 1, 'a' + index % 26);
+ } else {
+ const unsigned int m1 = (index / 26 - 1) / 26 - 1;
+ const unsigned int m2 = (index / 26 - 1) % 26;
+ const unsigned int m3 = index % 26;
+ sprintf(vblk->disk->disk_name, "vd%c%c%c",
+ 'a' + m1, 'a' + m2, 'a' + m3);
+ }
+
+ vblk->disk->major = major;
+ vblk->disk->first_minor = index_to_minor(index);
+ vblk->disk->private_data = vblk;
+ vblk->disk->fops = &virtblk_fops;
+ vblk->disk->driverfs_dev = &vdev->dev;
+ index++;
+
+ /* If barriers are supported, tell block layer that queue is ordered */
+ if (virtio_has_feature(vdev, VIRTIO_BLK_F_BARRIER))
+ blk_queue_ordered(vblk->disk->queue, QUEUE_ORDERED_TAG, NULL);
+
+ /* If disk is read-only in the host, the guest should obey */
+ if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
+ set_disk_ro(vblk->disk, 1);
+
+ /* Host must always specify the capacity. */
+ vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity),
+ &cap, sizeof(cap));
+
+ /* If capacity is too big, truncate with warning. */
+ if ((sector_t)cap != cap) {
+ dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n",
+ (unsigned long long)cap);
+ cap = (sector_t)-1;
+ }
+ set_capacity(vblk->disk, cap);
+
+ /* Host can optionally specify maximum segment size and number of
+ * segments. */
+ err = virtio_config_val(vdev, VIRTIO_BLK_F_SIZE_MAX,
+ offsetof(struct virtio_blk_config, size_max),
+ &v);
+ if (!err)
+ blk_queue_max_segment_size(vblk->disk->queue, v);
+
+ err = virtio_config_val(vdev, VIRTIO_BLK_F_SEG_MAX,
+ offsetof(struct virtio_blk_config, seg_max),
+ &v);
+ if (!err)
+ blk_queue_max_hw_segments(vblk->disk->queue, v);
+
+ /* Host can optionally specify the block size of the device */
+ err = virtio_config_val(vdev, VIRTIO_BLK_F_BLK_SIZE,
+ offsetof(struct virtio_blk_config, blk_size),
+ &blk_size);
+ if (!err)
+ blk_queue_hardsect_size(vblk->disk->queue, blk_size);
+
+ add_disk(vblk->disk);
+ return 0;
+
+out_put_disk:
+ put_disk(vblk->disk);
+out_mempool:
+ mempool_destroy(vblk->pool);
+out_free_vq:
+ vdev->config->del_vq(vblk->vq);
+out_free_vblk:
+ kfree(vblk);
+out:
+ return err;
+}
+
+static void virtblk_remove(struct virtio_device *vdev)
+{
+ struct virtio_blk *vblk = vdev->priv;
+
+ /* Nothing should be pending. */
+ BUG_ON(!list_empty(&vblk->reqs));
+
+ /* Stop all the virtqueues. */
+ vdev->config->reset(vdev);
+
+ del_gendisk(vblk->disk);
+ blk_cleanup_queue(vblk->disk->queue);
+ put_disk(vblk->disk);
+ mempool_destroy(vblk->pool);
+ vdev->config->del_vq(vblk->vq);
+ kfree(vblk);
+}
+
+static struct virtio_device_id id_table[] = {
+ { VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID },
+ { 0 },
+};
+
+static unsigned int features[] = {
+ VIRTIO_BLK_F_BARRIER, VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX,
+ VIRTIO_BLK_F_GEOMETRY, VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
+};
+
+static struct virtio_driver virtio_blk = {
+ .feature_table = features,
+ .feature_table_size = ARRAY_SIZE(features),
+ .driver.name = KBUILD_MODNAME,
+ .driver.owner = THIS_MODULE,
+ .id_table = id_table,
+ .probe = virtblk_probe,
+ .remove = __devexit_p(virtblk_remove),
+};
+
+static int __init init(void)
+{
+ major = register_blkdev(0, "virtblk");
+ if (major < 0)
+ return major;
+ return register_virtio_driver(&virtio_blk);
+}
+
+static void __exit fini(void)
+{
+ unregister_blkdev(major, "virtblk");
+ unregister_virtio_driver(&virtio_blk);
+}
+module_init(init);
+module_exit(fini);
+
+MODULE_DEVICE_TABLE(virtio, id_table);
+MODULE_ALIAS("virtio:d00000002v*");
+MODULE_DESCRIPTION("Virtio block driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 46b940c..18c5829 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -2957,4 +2957,11 @@ config NETPOLL_TRAP
config NET_POLL_CONTROLLER
def_bool NETPOLL
+config VIRTIO_NET
+ tristate "Virtio network driver (EXPERIMENTAL)"
+ depends on EXPERIMENTAL && VIRTIO
+ ---help---
+ This is the virtual network driver for virtio. It can be used with
+ lguest or QEMU based VMMs (like KVM or Xen). Say Y or M.
+
endmenu
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index aa39eaa..17eb8bd 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -230,3 +230,4 @@ obj-$(CONFIG_FS_ENET) += fs_enet/
obj-$(CONFIG_NETXEN_NIC) += netxen/
obj-$(CONFIG_NIU) += niu.o
+obj-$(CONFIG_VIRTIO_NET) += virtio_net.o
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
new file mode 100644
index 0000000..d743b1e
--- /dev/null
+++ b/drivers/net/virtio_net.c
@@ -0,0 +1,687 @@
+/* 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/ethtool.h>
+#include <linux/module.h>
+#include <linux/virtio.h>
+#include <linux/virtio_net.h>
+#include <linux/scatterlist.h>
+#include <net/esp.h> /* for skb_to_sgvec() */
+
+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;
+
+ /* The skb we couldn't send because buffers were full. */
+ struct sk_buff *last_xmit_skb;
+
+ /* 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;
+
+ /* Receive & send queues. */
+ struct sk_buff_head recv;
+ struct sk_buff_head send;
+
+ /* Chain pages by the private ptr. */
+ struct page *pages;
+
+ struct net_device_stats stats;
+};
+
+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 give_a_page(struct virtnet_info *vi, struct page *page)
+{
+ page->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)
+ vi->pages = (struct page *)p->private;
+ else
+ p = alloc_page(gfp_mask);
+ return p;
+}
+
+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 probably waiting for more output buffers. */
+ netif_wake_queue(vi->dev);
+
+ /* Make sure we re-xmit last_xmit_skb: if there are no more packets
+ * queued, start_xmit won't be called. */
+ tasklet_schedule(&vi->tasklet);
+}
+
+static void receive_skb(struct net_device *dev, struct sk_buff *skb,
+ unsigned len)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ struct virtio_net_hdr *hdr = skb_vnet_hdr(skb);
+ int err;
+
+ if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) {
+ pr_debug("%s: short packet %i\n", dev->name, len);
+ vi->stats.rx_length_errors++;
+ goto drop;
+ }
+ len -= sizeof(struct virtio_net_hdr);
+
+ if (len <= MAX_PACKET_LEN) {
+ unsigned int i;
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+ give_a_page(dev->priv, skb_shinfo(skb)->frags[i].page);
+ skb->data_len = 0;
+ skb_shinfo(skb)->nr_frags = 0;
+ }
+
+ err = pskb_trim(skb, len);
+ if (err) {
+ pr_debug("%s: pskb_trim failed %i %d\n", dev->name, len, err);
+ vi->stats.rx_dropped++;
+ goto drop;
+ }
+ skb->truesize += skb->data_len;
+ vi->stats.rx_bytes += skb->len;
+ vi->stats.rx_packets++;
+
+ if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ 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);
+
+ 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:
+ vi->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[2+MAX_SKB_FRAGS];
+ int num, err, i;
+
+ 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);
+
+ 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_ATOMIC);
+ if (!f->page)
+ break;
+
+ f->page_offset = 0;
+ f->size = PAGE_SIZE;
+
+ skb->data_len += PAGE_SIZE;
+ skb->len += PAGE_SIZE;
+
+ skb_shinfo(skb)->nr_frags++;
+ }
+ }
+
+ 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)) {
+ rvq->vq_ops->disable_cb(rvq);
+ __netif_rx_schedule(vi->dev);
+ }
+}
+
+static int virtnet_poll(struct net_device *dev, int *budget)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ int max_received = min(dev->quota, *budget);
+ bool no_work;
+ struct sk_buff *skb = NULL;
+ unsigned int len, received = 0;
+
+again:
+ while (received < max_received &&
+ (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 (skb) {
+ *budget -= received;
+ dev->quota -= received;
+ return 1;
+ }
+
+ netif_rx_complete(vi->dev);
+ no_work = vi->rvq->vq_ops->enable_cb(vi->rvq);
+
+ if (!no_work && netif_rx_schedule_prep(vi->dev)) {
+ vi->rvq->vq_ops->disable_cb(vi->rvq);
+ __netif_rx_schedule(vi->dev);
+ goto again;
+ }
+
+ dev->quota -= received;
+ *budget -= received;
+
+ return 0;
+}
+
+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->stats.tx_bytes += skb->len;
+ vi->stats.tx_packets++;
+ kfree_skb(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);
+}
+
+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 *hdr;
+
+#ifdef DEBUG
+ const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
+
+ pr_debug("%s: xmit %p " MAC_FMT "\n", vi->dev->name, skb,
+ dest[0], dest[1], dest[2],
+ dest[3], dest[4], dest[5]);
+#endif
+
+ /* Encode metadata header at front. */
+ hdr = skb_vnet_hdr(skb);
+ if (skb->ip_summed == CHECKSUM_HW) {
+ hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
+ hdr->csum_start = skb->h.raw - skb->data;
+ hdr->csum_offset = skb->csum;
+ } else {
+ hdr->flags = 0;
+ hdr->csum_offset = hdr->csum_start = 0;
+ }
+
+ if (skb_is_gso(skb)) {
+ hdr->hdr_len = skb->h.raw - 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;
+
+ err = vi->svq->vq_ops->add_buf(vi->svq, sg, num, 0, skb);
+ if (!err && !vi->free_in_tasklet)
+ 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);
+ if (vi->last_xmit_skb && xmit_skb(vi, vi->last_xmit_skb) == 0) {
+ vi->svq->vq_ops->kick(vi->svq);
+ vi->last_xmit_skb = NULL;
+ }
+ if (vi->free_in_tasklet)
+ free_old_xmit_skbs(vi);
+ netif_tx_unlock_bh(vi->dev);
+}
+
+static int start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+
+again:
+ /* Free up any pending old buffers before queueing new ones. */
+ free_old_xmit_skbs(vi);
+
+ /* If we has a buffer left over from last time, send it now. */
+ if (unlikely(vi->last_xmit_skb) &&
+ xmit_skb(vi, vi->last_xmit_skb) != 0)
+ goto stop_queue;
+
+ vi->last_xmit_skb = NULL;
+
+ /* Put new one in send queue and do transmit */
+ if (likely(skb)) {
+ __skb_queue_head(&vi->send, skb);
+ if (xmit_skb(vi, skb) != 0) {
+ vi->last_xmit_skb = skb;
+ skb = NULL;
+ goto stop_queue;
+ }
+ }
+done:
+ vi->svq->vq_ops->kick(vi->svq);
+ return NETDEV_TX_OK;
+
+stop_queue:
+ 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))) {
+ vi->svq->vq_ops->disable_cb(vi->svq);
+ netif_start_queue(dev);
+ goto again;
+ }
+ if (skb) {
+ /* Drop this skb: we only queue one. */
+ vi->stats.tx_dropped++;
+ kfree_skb(skb);
+ }
+ goto done;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void virtnet_netpoll(struct net_device *dev)
+{
+ netif_rx_schedule(dev);
+}
+#endif
+
+struct net_device_stats *virtnet_get_stats(struct net_device *dev)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+
+ return &vi->stats;
+}
+
+static int virtnet_open(struct net_device *dev)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+
+ memset(&vi->stats, 0, sizeof(vi->stats));
+
+ netif_poll_enable(dev);
+
+ /* 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->rvq->vq_ops->disable_cb(vi->rvq);
+ __netif_rx_schedule(vi->dev);
+ }
+ return 0;
+}
+
+static int virtnet_close(struct net_device *dev)
+{
+ netif_poll_disable(dev);
+
+ return 0;
+}
+
+static int virtnet_set_tx_csum(struct net_device *dev, u32 data)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ struct virtio_device *vdev = vi->vdev;
+
+ if (data && !virtio_has_feature(vdev, VIRTIO_NET_F_CSUM))
+ return -ENOSYS;
+
+ return ethtool_op_set_tx_hw_csum(dev, data);
+}
+
+static struct ethtool_ops virtnet_ethtool_ops = {
+ .set_tx_csum = virtnet_set_tx_csum,
+ .set_sg = ethtool_op_set_sg,
+};
+
+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->get_stats = virtnet_get_stats;
+ dev->features = NETIF_F_HIGHDMA;
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ dev->poll_controller = virtnet_netpoll;
+#endif
+ SET_ETHTOOL_OPS(dev, &virtnet_ethtool_ops);
+ SET_NETDEV_DEV(dev, &vdev->dev);
+
+ /* Do we support "hardware" checksums? */
+ if (csum && virtio_has_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 && virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) {
+ dev->features |= NETIF_F_TSO | NETIF_F_UFO
+ | NETIF_F_TSO_ECN | NETIF_F_TSO6;
+ }
+ /* Individual feature bits: what can host handle? */
+ if (gso && virtio_has_feature(vdev, VIRTIO_NET_F_HOST_TSO4))
+ dev->features |= NETIF_F_TSO;
+ if (gso && virtio_has_feature(vdev, VIRTIO_NET_F_HOST_TSO6))
+ dev->features |= NETIF_F_TSO6;
+ if (gso && virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN))
+ dev->features |= NETIF_F_TSO_ECN;
+ if (gso && virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UFO))
+ dev->features |= NETIF_F_UFO;
+ }
+
+ /* Configuration may specify what MAC to use. Otherwise random. */
+ if (virtio_has_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);
+ dev->poll = virtnet_poll;
+ dev->weight = 16;
+ vi->dev = dev;
+ vi->vdev = vdev;
+ vdev->priv = vi;
+ vi->pages = NULL;
+
+ /* 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))
+ vi->big_packets = true;
+
+ /* 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);
+
+ 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");
+ 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);
+
+ 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);
+
+ vdev->config->del_vq(vi->svq);
+ vdev->config->del_vq(vi->rvq);
+ unregister_netdev(vi->dev);
+
+ while (vi->pages)
+ __free_pages(get_a_page(vi, GFP_KERNEL), 0);
+
+ free_netdev(vi->dev);
+}
+
+static struct virtio_device_id id_table[] = {
+ { VIRTIO_ID_NET, VIRTIO_DEV_ANY_ID },
+ { 0 },
+};
+
+static unsigned int features[] = {
+ VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM,
+ VIRTIO_NET_F_GSO, VIRTIO_NET_F_MAC,
+ VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6,
+ VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
+ VIRTIO_NET_F_GUEST_ECN, /* We don't yet handle UFO input. */
+ VIRTIO_F_NOTIFY_ON_EMPTY,
+};
+
+static struct virtio_driver virtio_net = {
+ .feature_table = features,
+ .feature_table_size = ARRAY_SIZE(features),
+ .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_ALIAS("virtio:d00000001v*");
+MODULE_DESCRIPTION("Virtio network driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
new file mode 100644
index 0000000..e37f69e
--- /dev/null
+++ b/drivers/virtio/Kconfig
@@ -0,0 +1,25 @@
+# Virtio always gets selected by whoever wants it.
+config VIRTIO
+ tristate
+
+# Similarly the virtio ring implementation.
+config VIRTIO_RING
+ tristate
+ depends on VIRTIO
+
+config VIRTIO_PCI
+ tristate "PCI driver for virtio devices (EXPERIMENTAL)"
+ depends on PCI && EXPERIMENTAL
+ depends on !X86_XEN && !X86_64_XEN
+ select VIRTIO
+ select VIRTIO_RING
+ ---help---
+ This drivers provides support for virtio based paravirtual device
+ drivers over PCI. This requires that your VMM has appropriate PCI
+ virtio backends. Most QEMU based VMMs should support these devices
+ (like KVM or Xen).
+
+ Currently, the ABI is not considered stable so there is no guarantee
+ that this version of the driver will work with your VMM.
+
+ If unsure, say M.
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
new file mode 100644
index 0000000..cc84999
--- /dev/null
+++ b/drivers/virtio/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_VIRTIO) += virtio.o
+obj-$(CONFIG_VIRTIO_RING) += virtio_ring.o
+obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
new file mode 100644
index 0000000..e631221
--- /dev/null
+++ b/drivers/virtio/virtio.c
@@ -0,0 +1,220 @@
+#include <linux/virtio.h>
+#include <linux/spinlock.h>
+#include <linux/virtio_config.h>
+
+/* Unique numbering for virtio devices. */
+static unsigned int dev_index;
+
+static ssize_t device_show(struct device *_d,
+ struct device_attribute *attr, char *buf)
+{
+ struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+ return sprintf(buf, "%hu", dev->id.device);
+}
+static ssize_t vendor_show(struct device *_d,
+ struct device_attribute *attr, char *buf)
+{
+ struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+ return sprintf(buf, "%hu", dev->id.vendor);
+}
+static ssize_t status_show(struct device *_d,
+ struct device_attribute *attr, char *buf)
+{
+ struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+ return sprintf(buf, "0x%08x", dev->config->get_status(dev));
+}
+static ssize_t modalias_show(struct device *_d,
+ struct device_attribute *attr, char *buf)
+{
+ struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+
+ return sprintf(buf, "virtio:d%08Xv%08X\n",
+ dev->id.device, dev->id.vendor);
+}
+static struct device_attribute virtio_dev_attrs[] = {
+ __ATTR_RO(device),
+ __ATTR_RO(vendor),
+ __ATTR_RO(status),
+ __ATTR_RO(modalias),
+ __ATTR_NULL
+};
+
+static inline int virtio_id_match(const struct virtio_device *dev,
+ const struct virtio_device_id *id)
+{
+ if (id->device != dev->id.device)
+ return 0;
+
+ return id->vendor == VIRTIO_DEV_ANY_ID || id->vendor != dev->id.vendor;
+}
+
+/* This looks through all the IDs a driver claims to support. If any of them
+ * match, we return 1 and the kernel will call virtio_dev_probe(). */
+static int virtio_dev_match(struct device *_dv, struct device_driver *_dr)
+{
+ unsigned int i;
+ struct virtio_device *dev = container_of(_dv,struct virtio_device,dev);
+ const struct virtio_device_id *ids;
+
+ ids = container_of(_dr, struct virtio_driver, driver)->id_table;
+ for (i = 0; ids[i].device; i++)
+ if (virtio_id_match(dev, &ids[i]))
+ return 1;
+ return 0;
+}
+
+static int virtio_uevent(struct device *_dv, char **envp, int num_envp,
+ char *buffer, int buffer_size)
+{
+ struct virtio_device *dev = container_of(_dv,struct virtio_device,dev);
+ int cur_index = 0, cur_len = 0;
+
+ return add_uevent_var(envp, num_envp, &cur_index, buffer, buffer_size,
+ &cur_len, "MODALIAS=virtio:d%08Xv%08X",
+ dev->id.device, dev->id.vendor);
+}
+
+static void add_status(struct virtio_device *dev, unsigned status)
+{
+ dev->config->set_status(dev, dev->config->get_status(dev) | status);
+}
+
+void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
+ unsigned int fbit)
+{
+ unsigned int i;
+ struct virtio_driver *drv = container_of(vdev->dev.driver,
+ struct virtio_driver, driver);
+
+ for (i = 0; i < drv->feature_table_size; i++)
+ if (drv->feature_table[i] == fbit)
+ return;
+ BUG();
+}
+EXPORT_SYMBOL_GPL(virtio_check_driver_offered_feature);
+
+static int virtio_dev_probe(struct device *_d)
+{
+ int err, i;
+ struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+ struct virtio_driver *drv = container_of(dev->dev.driver,
+ struct virtio_driver, driver);
+ u32 device_features;
+
+ /* We have a driver! */
+ add_status(dev, VIRTIO_CONFIG_S_DRIVER);
+
+ /* Figure out what features the device supports. */
+ device_features = dev->config->get_features(dev);
+
+ /* Features supported by both device and driver into dev->features. */
+ memset(dev->features, 0, sizeof(dev->features));
+ for (i = 0; i < drv->feature_table_size; i++) {
+ unsigned int f = drv->feature_table[i];
+ BUG_ON(f >= 32);
+ if (device_features & (1 << f))
+ set_bit(f, dev->features);
+ }
+
+ /* Transport features always preserved to pass to finalize_features. */
+ for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++)
+ if (device_features & (1 << i))
+ set_bit(i, dev->features);
+
+ err = drv->probe(dev);
+ if (err)
+ add_status(dev, VIRTIO_CONFIG_S_FAILED);
+ else {
+ dev->config->finalize_features(dev);
+ add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
+ }
+ return err;
+}
+
+static int virtio_dev_remove(struct device *_d)
+{
+ struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+ struct virtio_driver *drv = container_of(dev->dev.driver,
+ struct virtio_driver, driver);
+
+ drv->remove(dev);
+
+ /* Driver should have reset device. */
+ BUG_ON(dev->config->get_status(dev));
+
+ /* Acknowledge the device's existence again. */
+ add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+ return 0;
+}
+
+static struct bus_type virtio_bus = {
+ .name = "virtio",
+ .match = virtio_dev_match,
+ .dev_attrs = virtio_dev_attrs,
+ .uevent = virtio_uevent,
+ .probe = virtio_dev_probe,
+ .remove = virtio_dev_remove,
+};
+
+int register_virtio_driver(struct virtio_driver *driver)
+{
+ /* Catch this early. */
+ BUG_ON(driver->feature_table_size && !driver->feature_table);
+ driver->driver.bus = &virtio_bus;
+ return driver_register(&driver->driver);
+}
+EXPORT_SYMBOL_GPL(register_virtio_driver);
+
+void unregister_virtio_driver(struct virtio_driver *driver)
+{
+ driver_unregister(&driver->driver);
+}
+EXPORT_SYMBOL_GPL(unregister_virtio_driver);
+
+int register_virtio_device(struct virtio_device *dev)
+{
+ int err;
+
+ dev->dev.bus = &virtio_bus;
+
+ /* Assign a unique device index and hence name. */
+ dev->index = dev_index++;
+ sprintf(dev->dev.bus_id, "virtio%u", dev->index);
+
+ /* We always start by resetting the device, in case a previous
+ * driver messed it up. This also tests that code path a little. */
+ dev->config->reset(dev);
+
+ /* Acknowledge that we've seen the device. */
+ add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+
+ /* device_register() causes the bus infrastructure to look for a
+ * matching driver. */
+ err = device_register(&dev->dev);
+ if (err)
+ add_status(dev, VIRTIO_CONFIG_S_FAILED);
+ return err;
+}
+EXPORT_SYMBOL_GPL(register_virtio_device);
+
+void unregister_virtio_device(struct virtio_device *dev)
+{
+ device_unregister(&dev->dev);
+}
+EXPORT_SYMBOL_GPL(unregister_virtio_device);
+
+static int virtio_init(void)
+{
+ if (bus_register(&virtio_bus) != 0)
+ panic("virtio bus registration failed");
+ return 0;
+}
+
+static void __exit virtio_exit(void)
+{
+ bus_unregister(&virtio_bus);
+}
+core_initcall(virtio_init);
+module_exit(virtio_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
new file mode 100644
index 0000000..06909a4
--- /dev/null
+++ b/drivers/virtio/virtio_pci.c
@@ -0,0 +1,452 @@
+/*
+ * Virtio PCI driver
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+#include <linux/virtio_pci.h>
+#include <linux/highmem.h>
+#include <linux/spinlock.h>
+
+MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>");
+MODULE_DESCRIPTION("virtio-pci");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1");
+
+/* Our device structure */
+struct virtio_pci_device
+{
+ struct virtio_device vdev;
+ struct pci_dev *pci_dev;
+
+ /* the IO mapping for the PCI config space */
+ void __iomem *ioaddr;
+
+ /* a list of queues so we can dispatch IRQs */
+ spinlock_t lock;
+ struct list_head virtqueues;
+};
+
+struct virtio_pci_vq_info
+{
+ /* the actual virtqueue */
+ struct virtqueue *vq;
+
+ /* the number of entries in the queue */
+ int num;
+
+ /* the index of the queue */
+ int queue_index;
+
+ /* the virtual address of the ring queue */
+ void *queue;
+
+ /* the list node for the virtqueues list */
+ struct list_head node;
+};
+
+/* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */
+static struct pci_device_id virtio_pci_id_table[] = {
+ { 0x1af4, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
+ { 0 },
+};
+
+MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
+
+/* A PCI device has it's own struct device and so does a virtio device so
+ * we create a place for the virtio devices to show up in sysfs. I think it
+ * would make more sense for virtio to not insist on having it's own device. */
+static struct device virtio_pci_root = {
+ .parent = NULL,
+ .bus_id = "virtio-pci",
+};
+
+/* Convert a generic virtio device to our structure */
+static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
+{
+ return container_of(vdev, struct virtio_pci_device, vdev);
+}
+
+/* virtio config->get_features() implementation */
+static u32 vp_get_features(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+ /* When someone needs more than 32 feature bits, we'll need to
+ * steal a bit to indicate that the rest are somewhere else. */
+ return ioread32(vp_dev->ioaddr + VIRTIO_PCI_HOST_FEATURES);
+}
+
+/* virtio config->finalize_features() implementation */
+static void vp_finalize_features(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+ /* Give virtio_ring a chance to accept features. */
+ vring_transport_features(vdev);
+
+ /* We only support 32 feature bits. */
+ BUILD_BUG_ON(ARRAY_SIZE(vdev->features) != 1);
+ iowrite32(vdev->features[0], vp_dev->ioaddr+VIRTIO_PCI_GUEST_FEATURES);
+}
+
+/* virtio config->get() implementation */
+static void vp_get(struct virtio_device *vdev, unsigned offset,
+ void *buf, unsigned len)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ void __iomem *ioaddr = vp_dev->ioaddr + VIRTIO_PCI_CONFIG + offset;
+ u8 *ptr = buf;
+ int i;
+
+ for (i = 0; i < len; i++)
+ ptr[i] = ioread8(ioaddr + i);
+}
+
+/* the config->set() implementation. it's symmetric to the config->get()
+ * implementation */
+static void vp_set(struct virtio_device *vdev, unsigned offset,
+ const void *buf, unsigned len)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ void __iomem *ioaddr = vp_dev->ioaddr + VIRTIO_PCI_CONFIG + offset;
+ const u8 *ptr = buf;
+ int i;
+
+ for (i = 0; i < len; i++)
+ iowrite8(ptr[i], ioaddr + i);
+}
+
+/* config->{get,set}_status() implementations */
+static u8 vp_get_status(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ return ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+}
+
+static void vp_set_status(struct virtio_device *vdev, u8 status)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ /* We should never be setting status to 0. */
+ BUG_ON(status == 0);
+ iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+}
+
+static void vp_reset(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ /* 0 status means a reset. */
+ iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+}
+
+/* the notify function used when creating a virt queue */
+static void vp_notify(struct virtqueue *vq)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+ struct virtio_pci_vq_info *info = vq->priv;
+
+ /* we write the queue's selector into the notification register to
+ * signal the other end */
+ iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
+}
+
+/* A small wrapper to also acknowledge the interrupt when it's handled.
+ * I really need an EIO hook for the vring so I can ack the interrupt once we
+ * know that we'll be handling the IRQ but before we invoke the callback since
+ * the callback may notify the host which results in the host attempting to
+ * raise an interrupt that we would then mask once we acknowledged the
+ * interrupt. */
+static irqreturn_t vp_interrupt(int irq, void *opaque, struct pt_regs *regs)
+{
+ struct virtio_pci_device *vp_dev = opaque;
+ struct virtio_pci_vq_info *info;
+ irqreturn_t ret = IRQ_NONE;
+ unsigned long flags;
+ u8 isr;
+
+ /* reading the ISR has the effect of also clearing it so it's very
+ * important to save off the value. */
+ isr = ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);
+
+ /* It's definitely not us if the ISR was not high */
+ if (!isr)
+ return IRQ_NONE;
+
+ /* Configuration change? Tell driver if it wants to know. */
+ if (isr & VIRTIO_PCI_ISR_CONFIG) {
+ struct virtio_driver *drv;
+ drv = container_of(vp_dev->vdev.dev.driver,
+ struct virtio_driver, driver);
+
+ if (drv->config_changed)
+ drv->config_changed(&vp_dev->vdev);
+ }
+
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_for_each_entry(info, &vp_dev->virtqueues, node) {
+ if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
+ ret = IRQ_HANDLED;
+ }
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+ return ret;
+}
+
+/* the config->find_vq() implementation */
+static struct virtqueue *vp_find_vq(struct virtio_device *vdev, unsigned index,
+ void (*callback)(struct virtqueue *vq))
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ struct virtio_pci_vq_info *info;
+ struct virtqueue *vq;
+ unsigned long flags;
+ u16 num;
+ int err;
+
+ /* Select the queue we're interested in */
+ iowrite16(index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+
+ /* Check if queue is either not available or already active. */
+ num = ioread16(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NUM);
+ if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
+ return ERR_PTR(-ENOENT);
+
+ /* allocate and fill out our structure the represents an active
+ * queue */
+ info = kmalloc(sizeof(struct virtio_pci_vq_info), GFP_KERNEL);
+ if (!info)
+ return ERR_PTR(-ENOMEM);
+
+ info->queue_index = index;
+ info->num = num;
+
+ info->queue = kzalloc(PAGE_ALIGN(vring_size(num,PAGE_SIZE)), GFP_KERNEL);
+ if (info->queue == NULL) {
+ err = -ENOMEM;
+ goto out_info;
+ }
+
+ /* activate the queue */
+ iowrite32(virt_to_phys(info->queue) >> PAGE_SHIFT,
+ vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+
+ /* create the vring */
+ vq = vring_new_virtqueue(info->num, vdev, info->queue,
+ vp_notify, callback);
+ if (!vq) {
+ err = -ENOMEM;
+ goto out_activate_queue;
+ }
+
+ vq->priv = info;
+ info->vq = vq;
+
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_add(&info->node, &vp_dev->virtqueues);
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+ return vq;
+
+out_activate_queue:
+ iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+ kfree(info->queue);
+out_info:
+ kfree(info);
+ return ERR_PTR(err);
+}
+
+/* the config->del_vq() implementation */
+static void vp_del_vq(struct virtqueue *vq)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+ struct virtio_pci_vq_info *info = vq->priv;
+ unsigned long flags;
+
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_del(&info->node);
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+ vring_del_virtqueue(vq);
+
+ /* Select and deactivate the queue */
+ iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+ iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+
+ kfree(info->queue);
+ kfree(info);
+}
+
+static struct virtio_config_ops virtio_pci_config_ops = {
+ .get = vp_get,
+ .set = vp_set,
+ .get_status = vp_get_status,
+ .set_status = vp_set_status,
+ .reset = vp_reset,
+ .find_vq = vp_find_vq,
+ .del_vq = vp_del_vq,
+ .get_features = vp_get_features,
+ .finalize_features = vp_finalize_features,
+};
+
+/* the PCI probing function */
+static int __devinit virtio_pci_probe(struct pci_dev *pci_dev,
+ const struct pci_device_id *id)
+{
+ struct virtio_pci_device *vp_dev;
+ u32 rev;
+ int err;
+
+ /* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
+ if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
+ return -ENODEV;
+
+ pci_read_config_dword(pci_dev, PCI_CLASS_REVISION, &rev);
+ rev &= 0xff;
+
+ if (rev != VIRTIO_PCI_ABI_VERSION) {
+ printk(KERN_ERR "virtio_pci: expected ABI version %d, got %d\n",
+ VIRTIO_PCI_ABI_VERSION, rev);
+ return -ENODEV;
+ }
+
+ /* allocate our structure and fill it out */
+ vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
+ if (vp_dev == NULL)
+ return -ENOMEM;
+
+ vp_dev->vdev.dev.parent = &virtio_pci_root;
+ vp_dev->vdev.config = &virtio_pci_config_ops;
+ vp_dev->pci_dev = pci_dev;
+ INIT_LIST_HEAD(&vp_dev->virtqueues);
+ spin_lock_init(&vp_dev->lock);
+
+ /* enable the device */
+ err = pci_enable_device(pci_dev);
+ if (err)
+ goto out;
+
+ err = pci_request_regions(pci_dev, "virtio-pci");
+ if (err)
+ goto out_enable_device;
+
+ vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
+ if (vp_dev->ioaddr == NULL)
+ goto out_req_regions;
+
+ pci_set_drvdata(pci_dev, vp_dev);
+
+ /* we use the subsystem vendor/device id as the virtio vendor/device
+ * id. this allows us to use the same PCI vendor/device id for all
+ * virtio devices and to identify the particular virtio driver by
+ * the subsytem ids */
+ vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
+ vp_dev->vdev.id.device = pci_dev->subsystem_device;
+
+ /* register a handler for the queue with the PCI device's interrupt */
+ err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED,
+ vp_dev->vdev.dev.bus_id, vp_dev);
+ if (err)
+ goto out_set_drvdata;
+
+ /* finally register the virtio device */
+ err = register_virtio_device(&vp_dev->vdev);
+ if (err)
+ goto out_req_irq;
+
+ return 0;
+
+out_req_irq:
+ free_irq(pci_dev->irq, vp_dev);
+out_set_drvdata:
+ pci_set_drvdata(pci_dev, NULL);
+ pci_iounmap(pci_dev, vp_dev->ioaddr);
+out_req_regions:
+ pci_release_regions(pci_dev);
+out_enable_device:
+ pci_disable_device(pci_dev);
+out:
+ kfree(vp_dev);
+ return err;
+}
+
+static void __devexit virtio_pci_remove(struct pci_dev *pci_dev)
+{
+ struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+
+ unregister_virtio_device(&vp_dev->vdev);
+ free_irq(pci_dev->irq, vp_dev);
+ pci_set_drvdata(pci_dev, NULL);
+ pci_iounmap(pci_dev, vp_dev->ioaddr);
+ pci_release_regions(pci_dev);
+ pci_disable_device(pci_dev);
+ kfree(vp_dev);
+}
+
+#ifdef CONFIG_PM
+static int virtio_pci_suspend(struct pci_dev *pci_dev, pm_message_t state)
+{
+ pci_save_state(pci_dev);
+ pci_set_power_state(pci_dev, PCI_D3hot);
+ return 0;
+}
+
+static int virtio_pci_resume(struct pci_dev *pci_dev)
+{
+ pci_restore_state(pci_dev);
+ pci_set_power_state(pci_dev, PCI_D0);
+ return 0;
+}
+#endif
+
+static struct pci_driver virtio_pci_driver = {
+ .name = "virtio-pci",
+ .id_table = virtio_pci_id_table,
+ .probe = virtio_pci_probe,
+ .remove = virtio_pci_remove,
+#ifdef CONFIG_PM
+ .suspend = virtio_pci_suspend,
+ .resume = virtio_pci_resume,
+#endif
+};
+
+static int __init virtio_pci_init(void)
+{
+ int err;
+
+ err = device_register(&virtio_pci_root);
+ if (err)
+ return err;
+
+ err = pci_register_driver(&virtio_pci_driver);
+ if (err)
+ device_unregister(&virtio_pci_root);
+
+ return err;
+}
+
+module_init(virtio_pci_init);
+
+static void __exit virtio_pci_exit(void)
+{
+ device_unregister(&virtio_pci_root);
+ pci_unregister_driver(&virtio_pci_driver);
+}
+
+module_exit(virtio_pci_exit);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
new file mode 100644
index 0000000..7da8fb8
--- /dev/null
+++ b/drivers/virtio/virtio_ring.c
@@ -0,0 +1,343 @@
+/* Virtio ring implementation.
+ *
+ * Copyright 2007 Rusty Russell 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., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#include <linux/virtio.h>
+#include <linux/virtio_ring.h>
+#include <linux/virtio_config.h>
+#include <linux/device.h>
+#include <asm/io.h> /* for page_to_phys() */
+
+#ifdef DEBUG
+/* For development, we want to crash whenever the ring is screwed. */
+#define BAD_RING(vq, fmt...) \
+ do { dev_err(&vq->vq.vdev->dev, fmt); BUG(); } while(0)
+#define START_USE(vq) \
+ do { if ((vq)->in_use) panic("in_use = %i\n", (vq)->in_use); (vq)->in_use = __LINE__; mb(); } while(0)
+#define END_USE(vq) \
+ do { BUG_ON(!(vq)->in_use); (vq)->in_use = 0; mb(); } while(0)
+#else
+#define BAD_RING(vq, fmt...) \
+ do { dev_err(&vq->vq.vdev->dev, fmt); (vq)->broken = true; } while(0)
+#define START_USE(vq)
+#define END_USE(vq)
+#endif
+
+struct vring_virtqueue
+{
+ struct virtqueue vq;
+
+ /* Actual memory layout for this queue */
+ struct vring vring;
+
+ /* Other side has made a mess, don't try any more. */
+ bool broken;
+
+ /* Number of free buffers */
+ unsigned int num_free;
+ /* Head of free buffer list. */
+ unsigned int free_head;
+ /* Number we've added since last sync. */
+ unsigned int num_added;
+
+ /* Last used index we've seen. */
+ u16 last_used_idx;
+
+ /* How to notify other side. FIXME: commonalize hcalls! */
+ void (*notify)(struct virtqueue *vq);
+
+#ifdef DEBUG
+ /* They're supposed to lock for us. */
+ unsigned int in_use;
+#endif
+
+ /* Tokens for callbacks. */
+ void *data[];
+};
+
+#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
+
+static int vring_add_buf(struct virtqueue *_vq,
+ struct scatterlist sg[],
+ unsigned int out,
+ unsigned int in,
+ void *data)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ unsigned int i, avail, head, uninitialized_var(prev);
+
+ BUG_ON(data == NULL);
+ BUG_ON(out + in > vq->vring.num);
+ BUG_ON(out + in == 0);
+
+ START_USE(vq);
+
+ if (vq->num_free < out + in) {
+ pr_debug("Can't add buf len %i - avail = %i\n",
+ out + in, vq->num_free);
+ /* FIXME: for historical reasons, we force a notify here if
+ * there are outgoing parts to the buffer. Presumably the
+ * host should service the ring ASAP. */
+ if (out)
+ vq->notify(&vq->vq);
+ END_USE(vq);
+ return -ENOSPC;
+ }
+
+ /* We're about to use some buffers from the free list. */
+ vq->num_free -= out + in;
+
+ head = vq->free_head;
+ for (i = vq->free_head; out; i = vq->vring.desc[i].next, out--) {
+ vq->vring.desc[i].flags = VRING_DESC_F_NEXT;
+ vq->vring.desc[i].addr = page_to_phys(sg->page) + sg->offset;
+ vq->vring.desc[i].len = sg->length;
+ prev = i;
+ sg++;
+ }
+ for (; in; i = vq->vring.desc[i].next, in--) {
+ vq->vring.desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
+ vq->vring.desc[i].addr = page_to_phys(sg->page) + sg->offset;
+ vq->vring.desc[i].len = sg->length;
+ prev = i;
+ sg++;
+ }
+ /* Last one doesn't continue. */
+ vq->vring.desc[prev].flags &= ~VRING_DESC_F_NEXT;
+
+ /* Update free pointer */
+ vq->free_head = i;
+
+ /* Set token. */
+ vq->data[head] = data;
+
+ /* Put entry in available array (but don't update avail->idx until they
+ * do sync). FIXME: avoid modulus here? */
+ avail = (vq->vring.avail->idx + vq->num_added++) % vq->vring.num;
+ vq->vring.avail->ring[avail] = head;
+
+ pr_debug("Added buffer head %i to %p\n", head, vq);
+ END_USE(vq);
+ return 0;
+}
+
+static void vring_kick(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ START_USE(vq);
+ /* Descriptors and available array need to be set before we expose the
+ * new available array entries. */
+ wmb();
+
+ vq->vring.avail->idx += vq->num_added;
+ vq->num_added = 0;
+
+ /* Need to update avail index before checking if we should notify */
+ mb();
+
+ if (!(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
+ /* Prod other side to tell it about changes. */
+ vq->notify(&vq->vq);
+
+ END_USE(vq);
+}
+
+static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
+{
+ unsigned int i;
+
+ /* Clear data ptr. */
+ vq->data[head] = NULL;
+
+ /* Put back on free list: find end */
+ i = head;
+ while (vq->vring.desc[i].flags & VRING_DESC_F_NEXT) {
+ i = vq->vring.desc[i].next;
+ vq->num_free++;
+ }
+
+ vq->vring.desc[i].next = vq->free_head;
+ vq->free_head = head;
+ /* Plus final descriptor */
+ vq->num_free++;
+}
+
+static inline bool more_used(const struct vring_virtqueue *vq)
+{
+ return vq->last_used_idx != vq->vring.used->idx;
+}
+
+static void *vring_get_buf(struct virtqueue *_vq, unsigned int *len)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ void *ret;
+ unsigned int i;
+
+ START_USE(vq);
+
+ if (unlikely(vq->broken)) {
+ END_USE(vq);
+ return NULL;
+ }
+
+ if (!more_used(vq)) {
+ pr_debug("No more buffers in queue\n");
+ END_USE(vq);
+ return NULL;
+ }
+
+ i = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].id;
+ *len = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].len;
+
+ if (unlikely(i >= vq->vring.num)) {
+ BAD_RING(vq, "id %u out of range\n", i);
+ return NULL;
+ }
+ if (unlikely(!vq->data[i])) {
+ BAD_RING(vq, "id %u is not a head!\n", i);
+ return NULL;
+ }
+
+ /* detach_buf clears data, so grab it now. */
+ ret = vq->data[i];
+ detach_buf(vq, i);
+ vq->last_used_idx++;
+ END_USE(vq);
+ return ret;
+}
+
+static void vring_disable_cb(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
+}
+
+static bool vring_enable_cb(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ START_USE(vq);
+
+ /* We optimistically turn back on interrupts, then check if there was
+ * more to do. */
+ vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+ mb();
+ if (unlikely(more_used(vq))) {
+ END_USE(vq);
+ return false;
+ }
+
+ END_USE(vq);
+ return true;
+}
+
+irqreturn_t vring_interrupt(int irq, void *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ if (!more_used(vq)) {
+ pr_debug("virtqueue interrupt with no work for %p\n", vq);
+ return IRQ_NONE;
+ }
+
+ if (unlikely(vq->broken))
+ return IRQ_HANDLED;
+
+ pr_debug("virtqueue callback for %p (%p)\n", vq, vq->vq.callback);
+ if (vq->vq.callback)
+ vq->vq.callback(&vq->vq);
+
+ return IRQ_HANDLED;
+}
+EXPORT_SYMBOL_GPL(vring_interrupt);
+
+static struct virtqueue_ops vring_vq_ops = {
+ .add_buf = vring_add_buf,
+ .get_buf = vring_get_buf,
+ .kick = vring_kick,
+ .disable_cb = vring_disable_cb,
+ .enable_cb = vring_enable_cb,
+};
+
+struct virtqueue *vring_new_virtqueue(unsigned int num,
+ struct virtio_device *vdev,
+ void *pages,
+ void (*notify)(struct virtqueue *),
+ void (*callback)(struct virtqueue *))
+{
+ struct vring_virtqueue *vq;
+ unsigned int i;
+
+ /* We assume num is a power of 2. */
+ if (num & (num - 1)) {
+ dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
+ return NULL;
+ }
+
+ vq = kmalloc(sizeof(*vq) + sizeof(void *)*num, GFP_KERNEL);
+ if (!vq)
+ return NULL;
+
+ vring_init(&vq->vring, num, pages, PAGE_SIZE);
+ vq->vq.callback = callback;
+ vq->vq.vdev = vdev;
+ vq->vq.vq_ops = &vring_vq_ops;
+ vq->notify = notify;
+ vq->broken = false;
+ vq->last_used_idx = 0;
+ vq->num_added = 0;
+#ifdef DEBUG
+ vq->in_use = false;
+#endif
+
+ /* No callback? Tell other side not to bother us. */
+ if (!callback)
+ vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
+
+ /* Put everything in free lists. */
+ vq->num_free = num;
+ vq->free_head = 0;
+ for (i = 0; i < num-1; i++)
+ vq->vring.desc[i].next = i+1;
+
+ return &vq->vq;
+}
+EXPORT_SYMBOL_GPL(vring_new_virtqueue);
+
+void vring_del_virtqueue(struct virtqueue *vq)
+{
+ kfree(to_vvq(vq));
+}
+EXPORT_SYMBOL_GPL(vring_del_virtqueue);
+
+/* Manipulates transport-specific feature bits. */
+void vring_transport_features(struct virtio_device *vdev)
+{
+ unsigned int i;
+
+ for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++) {
+ switch (i) {
+ default:
+ /* We don't understand this bit. */
+ clear_bit(i, vdev->features);
+ }
+ }
+}
+EXPORT_SYMBOL_GPL(vring_transport_features);
+
+MODULE_LICENSE("GPL");
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
new file mode 100644
index 0000000..3eb49b8
--- /dev/null
+++ b/include/linux/virtio.h
@@ -0,0 +1,127 @@
+#ifndef _LINUX_VIRTIO_H
+#define _LINUX_VIRTIO_H
+/* Everything a virtio driver needs to work with any particular virtio
+ * implementation. */
+#include <linux/types.h>
+#include <linux/scatterlist.h>
+#include <linux/spinlock.h>
+#include <linux/device.h>
+#include <linux/mod_devicetable.h>
+
+/**
+ * virtqueue - a queue to register buffers for sending or receiving.
+ * @callback: the function to call when buffers are consumed (can be NULL).
+ * @vdev: the virtio device this queue was created for.
+ * @vq_ops: the operations for this virtqueue (see below).
+ * @priv: a pointer for the virtqueue implementation to use.
+ */
+struct virtqueue
+{
+ void (*callback)(struct virtqueue *vq);
+ struct virtio_device *vdev;
+ struct virtqueue_ops *vq_ops;
+ void *priv;
+};
+
+/**
+ * virtqueue_ops - operations for virtqueue abstraction layer
+ * @add_buf: expose buffer to other end
+ * vq: the struct virtqueue we're talking about.
+ * sg: the description of the buffer(s).
+ * out_num: the number of sg readable by other side
+ * in_num: the number of sg which are writable (after readable ones)
+ * data: the token identifying the buffer.
+ * Returns 0 or an error.
+ * @kick: update after add_buf
+ * vq: the struct virtqueue
+ * After one or more add_buf calls, invoke this to kick the other side.
+ * @get_buf: get the next used buffer
+ * vq: the struct virtqueue we're talking about.
+ * len: the length written into the buffer
+ * Returns NULL or the "data" token handed to add_buf.
+ * @disable_cb: disable callbacks
+ * vq: the struct virtqueue we're talking about.
+ * Note that this is not necessarily synchronous, hence unreliable and only
+ * useful as an optimization.
+ * @enable_cb: restart callbacks after disable_cb.
+ * vq: the struct virtqueue we're talking about.
+ * This re-enables callbacks; it returns "false" if there are pending
+ * buffers in the queue, to detect a possible race between the driver
+ * checking for more work, and enabling callbacks.
+ *
+ * Locking rules are straightforward: the driver is responsible for
+ * locking. No two operations may be invoked simultaneously, with the exception
+ * of @disable_cb.
+ *
+ * All operations can be called in any context.
+ */
+struct virtqueue_ops {
+ int (*add_buf)(struct virtqueue *vq,
+ struct scatterlist sg[],
+ unsigned int out_num,
+ unsigned int in_num,
+ void *data);
+
+ void (*kick)(struct virtqueue *vq);
+
+ void *(*get_buf)(struct virtqueue *vq, unsigned int *len);
+
+ void (*disable_cb)(struct virtqueue *vq);
+ bool (*enable_cb)(struct virtqueue *vq);
+};
+
+struct virtio_device_id {
+ __u32 device;
+ __u32 vendor;
+};
+
+#define VIRTIO_DEV_ANY_ID 0xffffffff
+
+/**
+ * virtio_device - representation of a device using virtio
+ * @index: unique position on the virtio bus
+ * @dev: underlying device.
+ * @id: the device type identification (used to match it with a driver).
+ * @config: the configuration ops for this device.
+ * @features: the features supported by both driver and device.
+ * @priv: private pointer for the driver's use.
+ */
+struct virtio_device
+{
+ int index;
+ struct device dev;
+ struct virtio_device_id id;
+ struct virtio_config_ops *config;
+ /* Note that this is a Linux set_bit-style bitmap. */
+ unsigned long features[1];
+ void *priv;
+};
+
+int register_virtio_device(struct virtio_device *dev);
+void unregister_virtio_device(struct virtio_device *dev);
+
+/**
+ * virtio_driver - operations for a virtio I/O driver
+ * @driver: underlying device driver (populate name and owner).
+ * @id_table: the ids serviced by this driver.
+ * @feature_table: an array of feature numbers supported by this device.
+ * @feature_table_size: number of entries in the feature table array.
+ * @probe: the function to call when a device is found. Returns a token for
+ * remove, or PTR_ERR().
+ * @remove: the function when a device is removed.
+ * @config_changed: optional function to call when the device configuration
+ * changes; may be called in interrupt context.
+ */
+struct virtio_driver {
+ struct device_driver driver;
+ const struct virtio_device_id *id_table;
+ const unsigned int *feature_table;
+ unsigned int feature_table_size;
+ int (*probe)(struct virtio_device *dev);
+ void (*remove)(struct virtio_device *dev);
+ void (*config_changed)(struct virtio_device *dev);
+};
+
+int register_virtio_driver(struct virtio_driver *drv);
+void unregister_virtio_driver(struct virtio_driver *drv);
+#endif /* _LINUX_VIRTIO_H */
diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h
new file mode 100644
index 0000000..c1aef85
--- /dev/null
+++ b/include/linux/virtio_blk.h
@@ -0,0 +1,61 @@
+#ifndef _LINUX_VIRTIO_BLK_H
+#define _LINUX_VIRTIO_BLK_H
+/* This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers. */
+#include <linux/virtio_config.h>
+
+/* The ID for virtio_block */
+#define VIRTIO_ID_BLOCK 2
+
+/* Feature bits */
+#define VIRTIO_BLK_F_BARRIER 0 /* Does host support barriers? */
+#define VIRTIO_BLK_F_SIZE_MAX 1 /* Indicates maximum segment size */
+#define VIRTIO_BLK_F_SEG_MAX 2 /* Indicates maximum # of segments */
+#define VIRTIO_BLK_F_GEOMETRY 4 /* Legacy geometry available */
+#define VIRTIO_BLK_F_RO 5 /* Disk is read-only */
+#define VIRTIO_BLK_F_BLK_SIZE 6 /* Block size of disk is available*/
+
+struct virtio_blk_config
+{
+ /* The capacity (in 512-byte sectors). */
+ __u64 capacity;
+ /* The maximum segment size (if VIRTIO_BLK_F_SIZE_MAX) */
+ __u32 size_max;
+ /* The maximum number of segments (if VIRTIO_BLK_F_SEG_MAX) */
+ __u32 seg_max;
+ /* geometry the device (if VIRTIO_BLK_F_GEOMETRY) */
+ struct virtio_blk_geometry {
+ __u16 cylinders;
+ __u8 heads;
+ __u8 sectors;
+ } geometry;
+ /* block size of device (if VIRTIO_BLK_F_BLK_SIZE) */
+ __u32 blk_size;
+} __attribute__((packed));
+
+/* These two define direction. */
+#define VIRTIO_BLK_T_IN 0
+#define VIRTIO_BLK_T_OUT 1
+
+/* This bit says it's a scsi command, not an actual read or write. */
+#define VIRTIO_BLK_T_SCSI_CMD 2
+
+/* Barrier before this op. */
+#define VIRTIO_BLK_T_BARRIER 0x80000000
+
+/* This is the first element of the read scatter-gather list. */
+struct virtio_blk_outhdr
+{
+ /* VIRTIO_BLK_T* */
+ __u32 type;
+ /* io priority. */
+ __u32 ioprio;
+ /* Sector (ie. 512 byte offset) */
+ __u64 sector;
+};
+
+/* And this is the final byte of the write scatter-gather list. */
+#define VIRTIO_BLK_S_OK 0
+#define VIRTIO_BLK_S_IOERR 1
+#define VIRTIO_BLK_S_UNSUPP 2
+#endif /* _LINUX_VIRTIO_BLK_H */
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
new file mode 100644
index 0000000..bf8ec28
--- /dev/null
+++ b/include/linux/virtio_config.h
@@ -0,0 +1,130 @@
+#ifndef _LINUX_VIRTIO_CONFIG_H
+#define _LINUX_VIRTIO_CONFIG_H
+/* This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
+ * anyone can use the definitions to implement compatible drivers/servers. */
+
+/* Virtio devices use a standardized configuration space to define their
+ * features and pass configuration information, but each implementation can
+ * store and access that space differently. */
+#include <linux/types.h>
+
+/* Status byte for guest to report progress, and synchronize features. */
+/* We have seen device and processed generic fields (VIRTIO_CONFIG_F_VIRTIO) */
+#define VIRTIO_CONFIG_S_ACKNOWLEDGE 1
+/* We have found a driver for the device. */
+#define VIRTIO_CONFIG_S_DRIVER 2
+/* Driver has used its parts of the config, and is happy */
+#define VIRTIO_CONFIG_S_DRIVER_OK 4
+/* We've given up on this device. */
+#define VIRTIO_CONFIG_S_FAILED 0x80
+
+/* Some virtio feature bits (currently bits 28 through 31) are reserved for the
+ * transport being used (eg. virtio_ring), the rest are per-device feature
+ * bits. */
+#define VIRTIO_TRANSPORT_F_START 28
+#define VIRTIO_TRANSPORT_F_END 32
+
+/* Do we get callbacks when the ring is completely used, even if we've
+ * suppressed them? */
+#define VIRTIO_F_NOTIFY_ON_EMPTY 24
+
+#ifdef __KERNEL__
+#include <linux/virtio.h>
+
+/**
+ * virtio_config_ops - operations for configuring a virtio device
+ * @get: read the value of a configuration field
+ * vdev: the virtio_device
+ * offset: the offset of the configuration field
+ * buf: the buffer to write the field value into.
+ * len: the length of the buffer
+ * @set: write the value of a configuration field
+ * vdev: the virtio_device
+ * offset: the offset of the configuration field
+ * buf: the buffer to read the field value from.
+ * len: the length of the buffer
+ * @get_status: read the status byte
+ * vdev: the virtio_device
+ * Returns the status byte
+ * @set_status: write the status byte
+ * vdev: the virtio_device
+ * status: the new status byte
+ * @reset: reset the device
+ * vdev: the virtio device
+ * After this, status and feature negotiation must be done again
+ * @find_vq: find a virtqueue and instantiate it.
+ * vdev: the virtio_device
+ * index: the 0-based virtqueue number in case there's more than one.
+ * callback: the virqtueue callback
+ * Returns the new virtqueue or ERR_PTR() (eg. -ENOENT).
+ * @del_vq: free a virtqueue found by find_vq().
+ * @get_features: get the array of feature bits for this device.
+ * vdev: the virtio_device
+ * Returns the first 32 feature bits (all we currently need).
+ * @finalize_features: confirm what device features we'll be using.
+ * vdev: the virtio_device
+ * This gives the final feature bits for the device: it can change
+ * the dev->feature bits if it wants.
+ */
+struct virtio_config_ops
+{
+ void (*get)(struct virtio_device *vdev, unsigned offset,
+ void *buf, unsigned len);
+ void (*set)(struct virtio_device *vdev, unsigned offset,
+ const void *buf, unsigned len);
+ u8 (*get_status)(struct virtio_device *vdev);
+ void (*set_status)(struct virtio_device *vdev, u8 status);
+ void (*reset)(struct virtio_device *vdev);
+ struct virtqueue *(*find_vq)(struct virtio_device *vdev,
+ unsigned index,
+ void (*callback)(struct virtqueue *));
+ void (*del_vq)(struct virtqueue *vq);
+ u32 (*get_features)(struct virtio_device *vdev);
+ void (*finalize_features)(struct virtio_device *vdev);
+};
+
+/* If driver didn't advertise the feature, it will never appear. */
+void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
+ unsigned int fbit);
+
+/**
+ * virtio_has_feature - helper to determine if this device has this feature.
+ * @vdev: the device
+ * @fbit: the feature bit
+ */
+static inline bool virtio_has_feature(const struct virtio_device *vdev,
+ unsigned int fbit)
+{
+ /* Did you forget to fix assumptions on max features? */
+ if (__builtin_constant_p(fbit))
+ BUILD_BUG_ON(fbit >= 32);
+
+ virtio_check_driver_offered_feature(vdev, fbit);
+ return test_bit(fbit, vdev->features);
+}
+
+/**
+ * virtio_config_val - look for a feature and get a virtio config entry.
+ * @vdev: the virtio device
+ * @fbit: the feature bit
+ * @offset: the type to search for.
+ * @val: a pointer to the value to fill in.
+ *
+ * The return value is -ENOENT if the feature doesn't exist. Otherwise
+ * the config value is copied into whatever is pointed to by v. */
+#define virtio_config_val(vdev, fbit, offset, v) \
+ virtio_config_buf((vdev), (fbit), (offset), (v), sizeof(*v))
+
+static inline int virtio_config_buf(struct virtio_device *vdev,
+ unsigned int fbit,
+ unsigned int offset,
+ void *buf, unsigned len)
+{
+ if (!virtio_has_feature(vdev, fbit))
+ return -ENOENT;
+
+ vdev->config->get(vdev, offset, buf, len);
+ return 0;
+}
+#endif /* __KERNEL__ */
+#endif /* _LINUX_VIRTIO_CONFIG_H */
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
new file mode 100644
index 0000000..5e33761
--- /dev/null
+++ b/include/linux/virtio_net.h
@@ -0,0 +1,47 @@
+#ifndef _LINUX_VIRTIO_NET_H
+#define _LINUX_VIRTIO_NET_H
+/* This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers. */
+#include <linux/virtio_config.h>
+
+/* The ID for virtio_net */
+#define VIRTIO_ID_NET 1
+
+/* The feature bitmap for virtio net */
+#define VIRTIO_NET_F_CSUM 0 /* Host handles pkts w/ partial csum */
+#define VIRTIO_NET_F_GUEST_CSUM 1 /* Guest handles pkts w/ partial csum */
+#define VIRTIO_NET_F_MAC 5 /* Host has given MAC address. */
+#define VIRTIO_NET_F_GSO 6 /* Host handles pkts w/ any GSO type */
+#define VIRTIO_NET_F_GUEST_TSO4 7 /* Guest can handle TSOv4 in. */
+#define VIRTIO_NET_F_GUEST_TSO6 8 /* Guest can handle TSOv6 in. */
+#define VIRTIO_NET_F_GUEST_ECN 9 /* Guest can handle TSO[6] w/ ECN in. */
+#define VIRTIO_NET_F_GUEST_UFO 10 /* Guest can handle UFO in. */
+#define VIRTIO_NET_F_HOST_TSO4 11 /* Host can handle TSOv4 in. */
+#define VIRTIO_NET_F_HOST_TSO6 12 /* Host can handle TSOv6 in. */
+#define VIRTIO_NET_F_HOST_ECN 13 /* Host can handle TSO[6] w/ ECN in. */
+#define VIRTIO_NET_F_HOST_UFO 14 /* Host can handle UFO in. */
+
+struct virtio_net_config
+{
+ /* The config defining mac address (if VIRTIO_NET_F_MAC) */
+ __u8 mac[6];
+} __attribute__((packed));
+
+/* This is the first element of the scatter-gather list. If you don't
+ * specify GSO or CSUM features, you can simply ignore the header. */
+struct virtio_net_hdr
+{
+#define VIRTIO_NET_HDR_F_NEEDS_CSUM 1 // Use csum_start, csum_offset
+ __u8 flags;
+#define VIRTIO_NET_HDR_GSO_NONE 0 // Not a GSO frame
+#define VIRTIO_NET_HDR_GSO_TCPV4 1 // GSO frame, IPv4 TCP (TSO)
+#define VIRTIO_NET_HDR_GSO_UDP 3 // GSO frame, IPv4 UDP (UFO)
+#define VIRTIO_NET_HDR_GSO_TCPV6 4 // GSO frame, IPv6 TCP
+#define VIRTIO_NET_HDR_GSO_ECN 0x80 // TCP has ECN set
+ __u8 gso_type;
+ __u16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */
+ __u16 gso_size; /* Bytes to append to hdr_len per frame */
+ __u16 csum_start; /* Position to start checksumming from */
+ __u16 csum_offset; /* Offset after that to place checksum */
+};
+#endif /* _LINUX_VIRTIO_NET_H */
diff --git a/include/linux/virtio_pci.h b/include/linux/virtio_pci.h
new file mode 100644
index 0000000..cdef357
--- /dev/null
+++ b/include/linux/virtio_pci.h
@@ -0,0 +1,56 @@
+/*
+ * Virtio PCI driver
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ */
+
+#ifndef _LINUX_VIRTIO_PCI_H
+#define _LINUX_VIRTIO_PCI_H
+
+#include <linux/virtio_config.h>
+
+/* A 32-bit r/o bitmask of the features supported by the host */
+#define VIRTIO_PCI_HOST_FEATURES 0
+
+/* A 32-bit r/w bitmask of features activated by the guest */
+#define VIRTIO_PCI_GUEST_FEATURES 4
+
+/* A 32-bit r/w PFN for the currently selected queue */
+#define VIRTIO_PCI_QUEUE_PFN 8
+
+/* A 16-bit r/o queue size for the currently selected queue */
+#define VIRTIO_PCI_QUEUE_NUM 12
+
+/* A 16-bit r/w queue selector */
+#define VIRTIO_PCI_QUEUE_SEL 14
+
+/* A 16-bit r/w queue notifier */
+#define VIRTIO_PCI_QUEUE_NOTIFY 16
+
+/* An 8-bit device status register. */
+#define VIRTIO_PCI_STATUS 18
+
+/* An 8-bit r/o interrupt status register. Reading the value will return the
+ * current contents of the ISR and will also clear it. This is effectively
+ * a read-and-acknowledge. */
+#define VIRTIO_PCI_ISR 19
+
+/* The bit of the ISR which indicates a device configuration change. */
+#define VIRTIO_PCI_ISR_CONFIG 0x2
+
+/* The remaining space is defined by each driver as the per-driver
+ * configuration space */
+#define VIRTIO_PCI_CONFIG 20
+
+/* Virtio ABI version, this must match exactly */
+#define VIRTIO_PCI_ABI_VERSION 0
+#endif
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
new file mode 100644
index 0000000..c4a598f
--- /dev/null
+++ b/include/linux/virtio_ring.h
@@ -0,0 +1,128 @@
+#ifndef _LINUX_VIRTIO_RING_H
+#define _LINUX_VIRTIO_RING_H
+/* An interface for efficient virtio implementation, currently for use by KVM
+ * and lguest, but hopefully others soon. Do NOT change this since it will
+ * break existing servers and clients.
+ *
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Copyright Rusty Russell IBM Corporation 2007. */
+#include <linux/types.h>
+
+/* This marks a buffer as continuing via the next field. */
+#define VRING_DESC_F_NEXT 1
+/* This marks a buffer as write-only (otherwise read-only). */
+#define VRING_DESC_F_WRITE 2
+
+/* The Host uses this in used->flags to advise the Guest: don't kick me when
+ * you add a buffer. It's unreliable, so it's simply an optimization. Guest
+ * will still kick if it's out of buffers. */
+#define VRING_USED_F_NO_NOTIFY 1
+/* The Guest uses this in avail->flags to advise the Host: don't interrupt me
+ * when you consume a buffer. It's unreliable, so it's simply an
+ * optimization. */
+#define VRING_AVAIL_F_NO_INTERRUPT 1
+
+/* Virtio ring descriptors: 16 bytes. These can chain together via "next". */
+struct vring_desc
+{
+ /* Address (guest-physical). */
+ __u64 addr;
+ /* Length. */
+ __u32 len;
+ /* The flags as indicated above. */
+ __u16 flags;
+ /* We chain unused descriptors via this, too */
+ __u16 next;
+};
+
+struct vring_avail
+{
+ __u16 flags;
+ __u16 idx;
+ __u16 ring[];
+};
+
+/* u32 is used here for ids for padding reasons. */
+struct vring_used_elem
+{
+ /* Index of start of used descriptor chain. */
+ __u32 id;
+ /* Total length of the descriptor chain which was used (written to) */
+ __u32 len;
+};
+
+struct vring_used
+{
+ __u16 flags;
+ __u16 idx;
+ struct vring_used_elem ring[];
+};
+
+struct vring {
+ unsigned int num;
+
+ struct vring_desc *desc;
+
+ struct vring_avail *avail;
+
+ struct vring_used *used;
+};
+
+/* The standard layout for the ring is a continuous chunk of memory which looks
+ * like this. We assume num is a power of 2.
+ *
+ * struct vring
+ * {
+ * // The actual descriptors (16 bytes each)
+ * struct vring_desc desc[num];
+ *
+ * // A ring of available descriptor heads with free-running index.
+ * __u16 avail_flags;
+ * __u16 avail_idx;
+ * __u16 available[num];
+ *
+ * // Padding to the next page boundary.
+ * char pad[];
+ *
+ * // A ring of used descriptor heads with free-running index.
+ * __u16 used_flags;
+ * __u16 used_idx;
+ * struct vring_used_elem used[num];
+ * };
+ */
+static inline void vring_init(struct vring *vr, unsigned int num, void *p,
+ unsigned long pagesize)
+{
+ vr->num = num;
+ vr->desc = p;
+ vr->avail = p + num*sizeof(struct vring_desc);
+ vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + pagesize-1)
+ & ~(pagesize - 1));
+}
+
+static inline unsigned vring_size(unsigned int num, unsigned long pagesize)
+{
+ return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (2 + num)
+ + pagesize - 1) & ~(pagesize - 1))
+ + sizeof(__u16) * 2 + sizeof(struct vring_used_elem) * num;
+}
+
+#ifdef __KERNEL__
+#include <linux/irqreturn.h>
+struct virtio_device;
+struct virtqueue;
+
+struct virtqueue *vring_new_virtqueue(unsigned int num,
+ struct virtio_device *vdev,
+ void *pages,
+ void (*notify)(struct virtqueue *vq),
+ void (*callback)(struct virtqueue *vq));
+void vring_del_virtqueue(struct virtqueue *vq);
+/* Filter out transport-specific feature bits. */
+void vring_transport_features(struct virtio_device *vdev);
+
+irqreturn_t vring_interrupt(int irq, void *_vq);
+#endif /* __KERNEL__ */
+#endif /* _LINUX_VIRTIO_RING_H */
distrib
>
Scientific%20Linux
>
5x
>
x86_64
>
by-pkgid
>
fc11cd6e1c513a17304da94a5390f3cd
>
files
>
4368
