apply the patch, and disable CONFIG_SCHED_DEBUG, the result is worse,
the cpu rate of host os is 143%.
CONFIG_WORKQUEUE_TRACER is already disable.
2010/11/24 Sridhar Samudrala <sri@xxxxxxxxxx>:
> On 11/23/2010 5:41 AM, Michael S. Tsirkin wrote:
>>
>> On Tue, Nov 23, 2010 at 09:23:41PM +0800, lidong chen wrote:
>>>
>>> At this point, I'd suggest testing vhost-net on the upstream kernel,
>>> not on rhel kernels. The change that introduced per-device threads is:
>>> c23f3445e68e1db0e74099f264bc5ff5d55ebdeb
>>> i will try this tomorrow.
>>>
>>> Is CONFIG_SCHED_DEBUG set?
>>> yes. CONFIG_SCHED_DEBUG=y.
>>
>> Disable it. Either debug scheduler or perf-test it :)
>
> Another debug option to disable is CONFIG_WORKQUEUE_TRACER if it is set
> when using old rhel6 kernels.
>
> -Sridhar
>
>>> 2010/11/23 Michael S. Tsirkin<mst@xxxxxxxxxx>:
>>>>
>>>> On Tue, Nov 23, 2010 at 10:13:43AM +0800, lidong chen wrote:
>>>>>
>>>>> I test the performance between per-vhost kthread disable and enable.
>>>>>
>>>>> Test method:
>>>>> Send the same traffic load between per-vhost kthread disable and
>>>>> enable, and compare the cpu rate of host os.
>>>>> I run five vm on kvm, each of them have five nic.
>>>>> the vhost version which per-vhost kthread disable we used is rhel6
>>>>> beta 2(2.6.32.60).
>>>>> the vhost version which per-vhost kthread enable we used is rhel6
>>>>> (2.6.32-71).
>>>>
>>>> At this point, I'd suggest testing vhost-net on the upstream kernel,
>>>> not on rhel kernels. The change that introduced per-device threads is:
>>>> c23f3445e68e1db0e74099f264bc5ff5d55ebdeb
>>>>
>>>>> Test result:
>>>>> with per-vhost kthread disable, the cpu rate of host os is 110%.
>>>>> with per-vhost kthread enable, the cpu rate of host os is 130%.
>>>>
>>>> Is CONFIG_SCHED_DEBUG set? We are stressing the scheduler a lot with
>>>> vhost-net.
>>>>
>>>>> In 2.6.32.60,the whole system only have a kthread.
>>>>> [root@rhel6-kvm1 ~]# ps -ef | grep vhost
>>>>> root 973 2 0 Nov22 ? 00:00:00 [vhost]
>>>>>
>>>>> In 2.6.32.71,the whole system have 25 kthread.
>>>>> [root@kvm-4slot ~]# ps -ef | grep vhost-
>>>>> root 12896 2 0 10:26 ? 00:00:00 [vhost-12842]
>>>>> root 12897 2 0 10:26 ? 00:00:00 [vhost-12842]
>>>>> root 12898 2 0 10:26 ? 00:00:00 [vhost-12842]
>>>>> root 12899 2 0 10:26 ? 00:00:00 [vhost-12842]
>>>>> root 12900 2 0 10:26 ? 00:00:00 [vhost-12842]
>>>>>
>>>>> root 13022 2 0 10:26 ? 00:00:00 [vhost-12981]
>>>>> root 13023 2 0 10:26 ? 00:00:00 [vhost-12981]
>>>>> root 13024 2 0 10:26 ? 00:00:00 [vhost-12981]
>>>>> root 13025 2 0 10:26 ? 00:00:00 [vhost-12981]
>>>>> root 13026 2 0 10:26 ? 00:00:00 [vhost-12981]
>>>>>
>>>>> root 13146 2 0 10:26 ? 00:00:00 [vhost-13088]
>>>>> root 13147 2 0 10:26 ? 00:00:00 [vhost-13088]
>>>>> root 13148 2 0 10:26 ? 00:00:00 [vhost-13088]
>>>>> root 13149 2 0 10:26 ? 00:00:00 [vhost-13088]
>>>>> root 13150 2 0 10:26 ? 00:00:00 [vhost-13088]
>>>>> ...
>>>>>
>>>>> Code difference:
>>>>> In 2.6.32.60,in function vhost_init, create the kthread for vhost.
>>>>> vhost_workqueue = create_singlethread_workqueue("vhost");
>>>>>
>>>>> In 2.6.32.71,in function vhost_dev_set_owner, create the kthread for
>>>>> each nic interface.
>>>>> dev->wq = create_singlethread_workqueue(vhost_name);
>>>>>
>>>>> Conclusion:
>>>>> with per-vhost kthread enable, the system can more throughput.
>>>>> but deal the same traffic load with per-vhost kthread enable, it waste
>>>>> more cpu resource.
>>>>>
>>>>> In my application scene, the cpu resource is more important, and one
>>>>> kthread for deal with traffic load is enough.
>>>>>
>>>>> So i think we should add a param to control this.
>>>>> for the CPU-bound system, this param disable per-vhost kthread.
>>>>> for the I/O-bound system, this param enable per-vhost kthread.
>>>>> the default value of this param is enable.
>>>>>
>>>>> If my opinion is right, i will give a patch for this.
>>>>
>>>> Let's try to figure out what the issue is, first.
>>>>
>>>> --
>>>> MST
>>>>
>
>
>
#ifndef _VHOST_H
#define _VHOST_H
#include <linux/eventfd.h>
#include <linux/vhost.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/workqueue.h>
#include <linux/poll.h>
#include <linux/file.h>
#include <linux/skbuff.h>
#include <linux/uio.h>
#include <linux/virtio_config.h>
#include <linux/virtio_ring.h>
#include <linux/virtio_net.h>
#include <asm/atomic.h>
struct vhost_device;
struct vhost_work;
typedef void (*vhost_work_fn_t)(struct vhost_work *work);
struct vhost_work {
struct list_head node;
vhost_work_fn_t fn;
wait_queue_head_t done;
int flushing;
unsigned queue_seq;
unsigned done_seq;
};
/* Poll a file (eventfd or socket) */
/* Note: there's nothing vhost specific about this structure. */
struct vhost_poll {
poll_table table;
wait_queue_head_t *wqh;
wait_queue_t wait;
/* struct which will handle all actual work. */
struct vhost_work work;
unsigned long mask;
struct vhost_dev *dev;
};
void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t func,
unsigned long mask, struct vhost_dev *dev);
void vhost_poll_start(struct vhost_poll *poll, struct file *file);
void vhost_poll_stop(struct vhost_poll *poll);
void vhost_poll_flush(struct vhost_poll *poll);
void vhost_poll_queue(struct vhost_poll *poll);
struct vhost_log {
u64 addr;
u64 len;
};
/* The virtqueue structure describes a queue attached to a device. */
struct vhost_virtqueue {
struct vhost_dev *dev;
/* The actual ring of buffers. */
struct mutex mutex;
unsigned int num;
struct vring_desc __user *desc;
struct vring_avail __user *avail;
struct vring_used __user *used;
struct file *kick;
struct file *call;
struct file *error;
struct eventfd_ctx *call_ctx;
struct eventfd_ctx *error_ctx;
struct eventfd_ctx *log_ctx;
struct vhost_poll poll;
/* The routine to call when the Guest pings us, or timeout. */
vhost_work_fn_t handle_kick;
/* Last available index we saw. */
u16 last_avail_idx;
/* Caches available index value from user. */
u16 avail_idx;
/* Last index we used. */
u16 last_used_idx;
/* Used flags */
u16 used_flags;
/* Log writes to used structure. */
bool log_used;
u64 log_addr;
struct iovec iov[UIO_MAXIOV];
/* hdr is used to store the virtio header.
* Since each iovec entry has >= 1 byte length, we never need more than
* header length entries to store the header. */
struct iovec hdr[sizeof(struct virtio_net_hdr_mrg_rxbuf)];
struct iovec *indirect;
size_t hdr_size;
/* We use a kind of RCU to access private pointer.
* All readers access it from workqueue, which makes it possible to
* flush the workqueue instead of synchronize_rcu. Therefore readers do
* not need to call rcu_read_lock/rcu_read_unlock: the beginning of
* work item execution acts instead of rcu_read_lock() and the end of
* work item execution acts instead of rcu_read_lock().
* Writers use virtqueue mutex. */
void *private_data;
/* Log write descriptors */
void __user *log_base;
struct vhost_log *log;
};
struct vhost_dev {
/* Readers use RCU to access memory table pointer
* log base pointer and features.
* Writers use mutex below.*/
struct vhost_memory *memory;
struct mm_struct *mm;
struct mutex mutex;
unsigned acked_features;
struct vhost_virtqueue *vqs;
int nvqs;
struct file *log_file;
struct eventfd_ctx *log_ctx;
spinlock_t work_lock;
struct list_head work_list;
struct task_struct *worker;
};
long vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue *vqs, int nvqs);
long vhost_dev_check_owner(struct vhost_dev *);
long vhost_dev_reset_owner(struct vhost_dev *);
void vhost_dev_cleanup(struct vhost_dev *);
long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, unsigned long arg);
int vhost_vq_access_ok(struct vhost_virtqueue *vq);
int vhost_log_access_ok(struct vhost_dev *);
int vhost_get_vq_desc(struct vhost_dev *, struct vhost_virtqueue *,
struct iovec iov[], unsigned int iov_count,
unsigned int *out_num, unsigned int *in_num,
struct vhost_log *log, unsigned int *log_num);
void vhost_discard_vq_desc(struct vhost_virtqueue *);
int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len);
void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
void vhost_add_used_and_signal(struct vhost_dev *, struct vhost_virtqueue *,
unsigned int head, int len);
void vhost_disable_notify(struct vhost_virtqueue *);
bool vhost_enable_notify(struct vhost_virtqueue *);
int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
unsigned int log_num, u64 len);
int vhost_init(void);
void vhost_cleanup(void);
#define vq_err(vq, fmt, ...) do { \
pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \
if ((vq)->error_ctx) \
eventfd_signal((vq)->error_ctx, 1);\
} while (0)
enum {
VHOST_FEATURES = (1 << VIRTIO_F_NOTIFY_ON_EMPTY) |
(1 << VIRTIO_RING_F_INDIRECT_DESC) |
(1 << VHOST_F_LOG_ALL) |
(1 << VHOST_NET_F_VIRTIO_NET_HDR),
};
static inline int vhost_has_feature(struct vhost_dev *dev, int bit)
{
unsigned acked_features = rcu_dereference(dev->acked_features);
return acked_features & (1 << bit);
}
#endif
/* Copyright (C) 2009 Red Hat, Inc.
* Author: Michael S. Tsirkin <mst@xxxxxxxxxx>
*
* This work is licensed under the terms of the GNU GPL, version 2.
*
* virtio-net server in host kernel.
*/
#include <linux/compat.h>
#include <linux/eventfd.h>
#include <linux/vhost.h>
#include <linux/virtio_net.h>
#include <linux/mmu_context.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/workqueue.h>
#include <linux/rcupdate.h>
#include <linux/file.h>
#include <linux/net.h>
#include <linux/if_packet.h>
#include <linux/if_arp.h>
#include <linux/if_tun.h>
#include <linux/if_macvlan.h>
#include <net/sock.h>
#include "vhost.h"
/* Max number of bytes transferred before requeueing the job.
* Using this limit prevents one virtqueue from starving others. */
#define VHOST_NET_WEIGHT 0x80000
enum {
VHOST_NET_VQ_RX = 0,
VHOST_NET_VQ_TX = 1,
VHOST_NET_VQ_MAX = 2,
};
enum vhost_net_poll_state {
VHOST_NET_POLL_DISABLED = 0,
VHOST_NET_POLL_STARTED = 1,
VHOST_NET_POLL_STOPPED = 2,
};
struct vhost_net {
struct vhost_dev dev;
struct vhost_virtqueue vqs[VHOST_NET_VQ_MAX];
struct vhost_poll poll[VHOST_NET_VQ_MAX];
/* Tells us whether we are polling a socket for TX.
* We only do this when socket buffer fills up.
* Protected by tx vq lock. */
enum vhost_net_poll_state tx_poll_state;
};
/* Pop first len bytes from iovec. Return number of segments used. */
static int move_iovec_hdr(struct iovec *from, struct iovec *to,
size_t len, int iov_count)
{
int seg = 0;
size_t size;
while (len && seg < iov_count) {
size = min(from->iov_len, len);
to->iov_base = from->iov_base;
to->iov_len = size;
from->iov_len -= size;
from->iov_base += size;
len -= size;
++from;
++to;
++seg;
}
return seg;
}
/* Caller must have TX VQ lock */
static void tx_poll_stop(struct vhost_net *net)
{
if (likely(net->tx_poll_state != VHOST_NET_POLL_STARTED))
return;
vhost_poll_stop(net->poll + VHOST_NET_VQ_TX);
net->tx_poll_state = VHOST_NET_POLL_STOPPED;
}
/* Caller must have TX VQ lock */
static void tx_poll_start(struct vhost_net *net, struct socket *sock)
{
if (unlikely(net->tx_poll_state != VHOST_NET_POLL_STOPPED))
return;
vhost_poll_start(net->poll + VHOST_NET_VQ_TX, sock->file);
net->tx_poll_state = VHOST_NET_POLL_STARTED;
}
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_tx(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_TX];
unsigned out, in, s;
int head;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL,
.msg_controllen = 0,
.msg_iov = vq->iov,
.msg_flags = MSG_DONTWAIT,
};
size_t len, total_len = 0;
int err, wmem;
size_t hdr_size;
struct socket *sock = rcu_dereference(vq->private_data);
if (!sock)
return;
wmem = atomic_read(&sock->sk->sk_wmem_alloc);
if (wmem >= sock->sk->sk_sndbuf) {
mutex_lock(&vq->mutex);
tx_poll_start(net, sock);
mutex_unlock(&vq->mutex);
return;
}
use_mm(net->dev.mm);
mutex_lock(&vq->mutex);
vhost_disable_notify(vq);
if (wmem < sock->sk->sk_sndbuf / 2)
tx_poll_stop(net);
hdr_size = vq->hdr_size;
for (;;) {
head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
NULL, NULL);
/* On error, stop handling until the next kick. */
if (unlikely(head < 0))
break;
/* Nothing new? Wait for eventfd to tell us they refilled. */
if (head == vq->num) {
wmem = atomic_read(&sock->sk->sk_wmem_alloc);
if (wmem >= sock->sk->sk_sndbuf * 3 / 4) {
tx_poll_start(net, sock);
set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
break;
}
if (unlikely(vhost_enable_notify(vq))) {
vhost_disable_notify(vq);
continue;
}
break;
}
if (in) {
vq_err(vq, "Unexpected descriptor format for TX: "
"out %d, int %d\n", out, in);
break;
}
/* Skip header. TODO: support TSO. */
s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, out);
msg.msg_iovlen = out;
len = iov_length(vq->iov, out);
/* Sanity check */
if (!len) {
vq_err(vq, "Unexpected header len for TX: "
"%zd expected %zd\n",
iov_length(vq->hdr, s), hdr_size);
break;
}
/* TODO: Check specific error and bomb out unless ENOBUFS? */
err = sock->ops->sendmsg(NULL, sock, &msg, len);
if (unlikely(err < 0)) {
vhost_discard_vq_desc(vq);
tx_poll_start(net, sock);
break;
}
if (err != len)
pr_debug("Truncated TX packet: "
" len %d != %zd\n", err, len);
vhost_add_used_and_signal(&net->dev, vq, head, 0);
total_len += len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
mutex_unlock(&vq->mutex);
unuse_mm(net->dev.mm);
}
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_rx(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
unsigned out, in, log, s;
int head;
struct vhost_log *vq_log;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL, /* FIXME: get and handle RX aux data. */
.msg_controllen = 0,
.msg_iov = vq->iov,
.msg_flags = MSG_DONTWAIT,
};
struct virtio_net_hdr hdr = {
.flags = 0,
.gso_type = VIRTIO_NET_HDR_GSO_NONE
};
size_t len, total_len = 0;
int err;
size_t hdr_size;
struct socket *sock = rcu_dereference(vq->private_data);
if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
return;
use_mm(net->dev.mm);
mutex_lock(&vq->mutex);
vhost_disable_notify(vq);
hdr_size = vq->hdr_size;
vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
vq->log : NULL;
for (;;) {
head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
vq_log, &log);
/* On error, stop handling until the next kick. */
if (unlikely(head < 0))
break;
/* OK, now we need to know about added descriptors. */
if (head == vq->num) {
if (unlikely(vhost_enable_notify(vq))) {
/* They have slipped one in as we were
* doing that: check again. */
vhost_disable_notify(vq);
continue;
}
/* Nothing new? Wait for eventfd to tell us
* they refilled. */
break;
}
/* We don't need to be notified again. */
if (out) {
vq_err(vq, "Unexpected descriptor format for RX: "
"out %d, int %d\n",
out, in);
break;
}
/* Skip header. TODO: support TSO/mergeable rx buffers. */
s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, in);
msg.msg_iovlen = in;
len = iov_length(vq->iov, in);
/* Sanity check */
if (!len) {
vq_err(vq, "Unexpected header len for RX: "
"%zd expected %zd\n",
iov_length(vq->hdr, s), hdr_size);
break;
}
err = sock->ops->recvmsg(NULL, sock, &msg,
len, MSG_DONTWAIT | MSG_TRUNC);
/* TODO: Check specific error and bomb out unless EAGAIN? */
if (err < 0) {
vhost_discard_vq_desc(vq);
break;
}
/* TODO: Should check and handle checksum. */
if (err > len) {
pr_debug("Discarded truncated rx packet: "
" len %d > %zd\n", err, len);
vhost_discard_vq_desc(vq);
continue;
}
len = err;
err = memcpy_toiovec(vq->hdr, (unsigned char *)&hdr, hdr_size);
if (err) {
vq_err(vq, "Unable to write vnet_hdr at addr %p: %d\n",
vq->iov->iov_base, err);
break;
}
len += hdr_size;
vhost_add_used_and_signal(&net->dev, vq, head, len);
if (unlikely(vq_log))
vhost_log_write(vq, vq_log, log, len);
total_len += len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
mutex_unlock(&vq->mutex);
unuse_mm(net->dev.mm);
}
static void handle_tx_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq;
struct vhost_net *net;
vq = container_of(work, struct vhost_virtqueue, poll.work);
net = container_of(vq->dev, struct vhost_net, dev);
handle_tx(net);
}
static void handle_rx_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq;
struct vhost_net *net;
vq = container_of(work, struct vhost_virtqueue, poll.work);
net = container_of(vq->dev, struct vhost_net, dev);
handle_rx(net);
}
static void handle_tx_net(struct vhost_work *work)
{
struct vhost_net *net;
net = container_of(work, struct vhost_net, poll[VHOST_NET_VQ_TX].work);
handle_tx(net);
}
static void handle_rx_net(struct vhost_work *work)
{
struct vhost_net *net;
net = container_of(work, struct vhost_net, poll[VHOST_NET_VQ_RX].work);
handle_rx(net);
}
static int vhost_net_open(struct inode *inode, struct file *f)
{
struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL);
int r;
if (!n)
return -ENOMEM;
n->vqs[VHOST_NET_VQ_TX].handle_kick = handle_tx_kick;
n->vqs[VHOST_NET_VQ_RX].handle_kick = handle_rx_kick;
r = vhost_dev_init(&n->dev, n->vqs, VHOST_NET_VQ_MAX);
if (r < 0) {
kfree(n);
return r;
}
vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT,
&n->dev);
vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN,
&n->dev);
n->tx_poll_state = VHOST_NET_POLL_DISABLED;
f->private_data = n;
return 0;
}
static void vhost_net_disable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
if (!vq->private_data)
return;
if (vq == n->vqs + VHOST_NET_VQ_TX) {
tx_poll_stop(n);
n->tx_poll_state = VHOST_NET_POLL_DISABLED;
} else
vhost_poll_stop(n->poll + VHOST_NET_VQ_RX);
}
static void vhost_net_enable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct socket *sock = vq->private_data;
if (!sock)
return;
if (vq == n->vqs + VHOST_NET_VQ_TX) {
n->tx_poll_state = VHOST_NET_POLL_STOPPED;
tx_poll_start(n, sock);
} else
vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file);
}
static struct socket *vhost_net_stop_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct socket *sock;
mutex_lock(&vq->mutex);
sock = vq->private_data;
vhost_net_disable_vq(n, vq);
rcu_assign_pointer(vq->private_data, NULL);
mutex_unlock(&vq->mutex);
return sock;
}
static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock,
struct socket **rx_sock)
{
*tx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_TX);
*rx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_RX);
}
static void vhost_net_flush_vq(struct vhost_net *n, int index)
{
vhost_poll_flush(n->poll + index);
vhost_poll_flush(&n->dev.vqs[index].poll);
}
static void vhost_net_flush(struct vhost_net *n)
{
vhost_net_flush_vq(n, VHOST_NET_VQ_TX);
vhost_net_flush_vq(n, VHOST_NET_VQ_RX);
}
static int vhost_net_release(struct inode *inode, struct file *f)
{
struct vhost_net *n = f->private_data;
struct socket *tx_sock;
struct socket *rx_sock;
vhost_net_stop(n, &tx_sock, &rx_sock);
vhost_net_flush(n);
vhost_dev_cleanup(&n->dev);
if (tx_sock)
fput(tx_sock->file);
if (rx_sock)
fput(rx_sock->file);
/* We do an extra flush before freeing memory,
* since jobs can re-queue themselves. */
vhost_net_flush(n);
kfree(n);
return 0;
}
static struct socket *get_raw_socket(int fd)
{
struct {
struct sockaddr_ll sa;
char buf[MAX_ADDR_LEN];
} uaddr;
int uaddr_len = sizeof uaddr, r;
struct socket *sock = sockfd_lookup(fd, &r);
if (!sock)
return ERR_PTR(-ENOTSOCK);
/* Parameter checking */
if (sock->sk->sk_type != SOCK_RAW) {
r = -ESOCKTNOSUPPORT;
goto err;
}
r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa,
&uaddr_len, 0);
if (r)
goto err;
if (uaddr.sa.sll_family != AF_PACKET) {
r = -EPFNOSUPPORT;
goto err;
}
return sock;
err:
fput(sock->file);
return ERR_PTR(r);
}
static struct socket *get_tap_socket(int fd)
{
struct file *file = fget(fd);
struct socket *sock;
if (!file)
return ERR_PTR(-EBADF);
sock = tun_get_socket(file);
if (!IS_ERR(sock))
return sock;
sock = macvtap_get_socket(file);
if (IS_ERR(sock))
fput(file);
return sock;
}
static struct socket *get_socket(int fd)
{
struct socket *sock;
/* special case to disable backend */
if (fd == -1)
return NULL;
sock = get_raw_socket(fd);
if (!IS_ERR(sock))
return sock;
sock = get_tap_socket(fd);
if (!IS_ERR(sock))
return sock;
return ERR_PTR(-ENOTSOCK);
}
static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
{
struct socket *sock, *oldsock;
struct vhost_virtqueue *vq;
int r;
mutex_lock(&n->dev.mutex);
r = vhost_dev_check_owner(&n->dev);
if (r)
goto err;
if (index >= VHOST_NET_VQ_MAX) {
r = -ENOBUFS;
goto err;
}
vq = n->vqs + index;
mutex_lock(&vq->mutex);
/* Verify that ring has been setup correctly. */
if (!vhost_vq_access_ok(vq)) {
r = -EFAULT;
goto err_vq;
}
sock = get_socket(fd);
if (IS_ERR(sock)) {
r = PTR_ERR(sock);
goto err_vq;
}
/* start polling new socket */
oldsock = vq->private_data;
if (sock == oldsock)
goto done;
vhost_net_disable_vq(n, vq);
rcu_assign_pointer(vq->private_data, sock);
vhost_net_enable_vq(n, vq);
done:
mutex_unlock(&vq->mutex);
if (oldsock) {
vhost_net_flush_vq(n, index);
fput(oldsock->file);
}
mutex_unlock(&n->dev.mutex);
return 0;
err_vq:
mutex_unlock(&vq->mutex);
err:
mutex_unlock(&n->dev.mutex);
return r;
}
static long vhost_net_reset_owner(struct vhost_net *n)
{
struct socket *tx_sock = NULL;
struct socket *rx_sock = NULL;
long err;
mutex_lock(&n->dev.mutex);
err = vhost_dev_check_owner(&n->dev);
if (err)
goto done;
vhost_net_stop(n, &tx_sock, &rx_sock);
vhost_net_flush(n);
err = vhost_dev_reset_owner(&n->dev);
done:
mutex_unlock(&n->dev.mutex);
if (tx_sock)
fput(tx_sock->file);
if (rx_sock)
fput(rx_sock->file);
return err;
}
static int vhost_net_set_features(struct vhost_net *n, u64 features)
{
size_t hdr_size = features & (1 << VHOST_NET_F_VIRTIO_NET_HDR) ?
sizeof(struct virtio_net_hdr) : 0;
int i;
mutex_lock(&n->dev.mutex);
if ((features & (1 << VHOST_F_LOG_ALL)) &&
!vhost_log_access_ok(&n->dev)) {
mutex_unlock(&n->dev.mutex);
return -EFAULT;
}
n->dev.acked_features = features;
smp_wmb();
for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
mutex_lock(&n->vqs[i].mutex);
n->vqs[i].hdr_size = hdr_size;
mutex_unlock(&n->vqs[i].mutex);
}
vhost_net_flush(n);
mutex_unlock(&n->dev.mutex);
return 0;
}
static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
unsigned long arg)
{
struct vhost_net *n = f->private_data;
void __user *argp = (void __user *)arg;
u64 __user *featurep = argp;
struct vhost_vring_file backend;
u64 features;
int r;
switch (ioctl) {
case VHOST_NET_SET_BACKEND:
if (copy_from_user(&backend, argp, sizeof backend))
return -EFAULT;
return vhost_net_set_backend(n, backend.index, backend.fd);
case VHOST_GET_FEATURES:
features = VHOST_FEATURES;
if (copy_to_user(featurep, &features, sizeof features))
return -EFAULT;
return 0;
case VHOST_SET_FEATURES:
if (copy_from_user(&features, featurep, sizeof features))
return -EFAULT;
if (features & ~VHOST_FEATURES)
return -EOPNOTSUPP;
return vhost_net_set_features(n, features);
case VHOST_RESET_OWNER:
return vhost_net_reset_owner(n);
default:
mutex_lock(&n->dev.mutex);
r = vhost_dev_ioctl(&n->dev, ioctl, arg);
vhost_net_flush(n);
mutex_unlock(&n->dev.mutex);
return r;
}
}
#ifdef CONFIG_COMPAT
static long vhost_net_compat_ioctl(struct file *f, unsigned int ioctl,
unsigned long arg)
{
return vhost_net_ioctl(f, ioctl, (unsigned long)compat_ptr(arg));
}
#endif
const static struct file_operations vhost_net_fops = {
.owner = THIS_MODULE,
.release = vhost_net_release,
.unlocked_ioctl = vhost_net_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = vhost_net_compat_ioctl,
#endif
.open = vhost_net_open,
};
static struct miscdevice vhost_net_misc = {
VHOST_NET_MINOR,
"vhost-net",
&vhost_net_fops,
};
int vhost_net_init(void)
{
int r = vhost_init();
if (r)
goto err_init;
r = misc_register(&vhost_net_misc);
if (r)
goto err_reg;
return 0;
err_reg:
vhost_cleanup();
err_init:
return r;
}
module_init(vhost_net_init);
void vhost_net_exit(void)
{
misc_deregister(&vhost_net_misc);
vhost_cleanup();
}
module_exit(vhost_net_exit);
MODULE_VERSION("0.0.1");
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Michael S. Tsirkin");
MODULE_DESCRIPTION("Host kernel accelerator for virtio net");
/* Copyright (C) 2009 Red Hat, Inc.
* Copyright (C) 2006 Rusty Russell IBM Corporation
*
* Author: Michael S. Tsirkin <mst@xxxxxxxxxx>
*
* Inspiration, some code, and most witty comments come from
* Documentation/lguest/lguest.c, by Rusty Russell
*
* This work is licensed under the terms of the GNU GPL, version 2.
*
* Generic code for virtio server in host kernel.
*/
#include <linux/eventfd.h>
#include <linux/vhost.h>
#include <linux/virtio_net.h>
#include <linux/mm.h>
#include <linux/miscdevice.h>
#include <linux/mutex.h>
#include <linux/rcupdate.h>
#include <linux/poll.h>
#include <linux/file.h>
#include <linux/highmem.h>
#include <linux/cgroup.h>
#include <linux/kthread.h>
#include <linux/net.h>
#include <linux/if_packet.h>
#include <linux/if_arp.h>
#include <net/sock.h>
#include "vhost.h"
enum {
VHOST_MEMORY_MAX_NREGIONS = 64,
VHOST_MEMORY_F_LOG = 0x1,
};
static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
poll_table *pt)
{
struct vhost_poll *poll;
poll = container_of(pt, struct vhost_poll, table);
poll->wqh = wqh;
add_wait_queue(wqh, &poll->wait);
}
static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync,
void *key)
{
struct vhost_poll *poll;
poll = container_of(wait, struct vhost_poll, wait);
if (!((unsigned long)key & poll->mask))
return 0;
/*
queue_work(poll->dev->wq, &poll->work);
*/
vhost_poll_queue(poll);
return 0;
}
/* Init poll structure */
void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t func,
unsigned long mask, struct vhost_dev *dev)
{
/*
INIT_WORK(&poll->work, func);
*/
struct vhost_work *work = &poll->work;
init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup);
init_poll_funcptr(&poll->table, vhost_poll_func);
poll->mask = mask;
poll->dev = dev;
INIT_LIST_HEAD(&work->node);
work->fn = func;
init_waitqueue_head(&work->done);
work->flushing = 0;
work->queue_seq = work->done_seq = 0;
}
/* Start polling a file. We add ourselves to file's wait queue. The caller must
* keep a reference to a file until after vhost_poll_stop is called. */
void vhost_poll_start(struct vhost_poll *poll, struct file *file)
{
unsigned long mask;
mask = file->f_op->poll(file, &poll->table);
if (mask)
vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask);
}
/* Stop polling a file. After this function returns, it becomes safe to drop the
* file reference. You must also flush afterwards. */
void vhost_poll_stop(struct vhost_poll *poll)
{
remove_wait_queue(poll->wqh, &poll->wait);
}
/* Flush any work that has been scheduled. When calling this, don't hold any
* locks that are also used by the callback. */
void vhost_poll_flush(struct vhost_poll *poll)
{
/*
flush_work(&poll->work);
*/
struct vhost_work *work = &poll->work;
unsigned seq;
int left;
int flushing;
spin_lock_irq(&poll->dev->work_lock);
seq = work->queue_seq;
work->flushing++;
spin_unlock_irq(&poll->dev->work_lock);
wait_event(work->done, ({
spin_lock_irq(&poll->dev->work_lock);
left = seq - work->done_seq <= 0;
spin_unlock_irq(&poll->dev->work_lock);
left;
}));
spin_lock_irq(&poll->dev->work_lock);
flushing = --work->flushing;
spin_unlock_irq(&poll->dev->work_lock);
BUG_ON(flushing < 0);
}
void vhost_poll_queue(struct vhost_poll *poll)
{
/*
queue_work(poll->dev->wq, &poll->work);
*/
struct vhost_dev *dev = poll->dev;
struct vhost_work *work = &poll->work;
unsigned long flags;
spin_lock_irqsave(&dev->work_lock, flags);
if (list_empty(&work->node)) {
list_add_tail(&work->node, &dev->work_list);
work->queue_seq++;
wake_up_process(dev->worker);
}
spin_unlock_irqrestore(&dev->work_lock, flags);
}
static void vhost_vq_reset(struct vhost_dev *dev,
struct vhost_virtqueue *vq)
{
vq->num = 1;
vq->desc = NULL;
vq->avail = NULL;
vq->used = NULL;
vq->last_avail_idx = 0;
vq->avail_idx = 0;
vq->last_used_idx = 0;
vq->used_flags = 0;
vq->used_flags = 0;
vq->log_used = false;
vq->log_addr = -1ull;
vq->hdr_size = 0;
vq->private_data = NULL;
vq->log_base = NULL;
vq->error_ctx = NULL;
vq->error = NULL;
vq->kick = NULL;
vq->call_ctx = NULL;
vq->call = NULL;
vq->log_ctx = NULL;
}
static int vhost_worker(void *data)
{
struct vhost_dev *dev = data;
struct vhost_work *work = NULL;
unsigned uninitialized_var(seq);
for (;;) {
/* mb paired w/ kthread_stop */
set_current_state(TASK_INTERRUPTIBLE);
spin_lock_irq(&dev->work_lock);
if (work) {
work->done_seq = seq;
if (work->flushing)
wake_up_all(&work->done);
}
if (kthread_should_stop()) {
spin_unlock_irq(&dev->work_lock);
__set_current_state(TASK_RUNNING);
return 0;
}
if (!list_empty(&dev->work_list)) {
work = list_first_entry(&dev->work_list,
struct vhost_work, node);
list_del_init(&work->node);
seq = work->queue_seq;
} else
work = NULL;
spin_unlock_irq(&dev->work_lock);
if (work) {
__set_current_state(TASK_RUNNING);
work->fn(work);
} else
schedule();
}
}
/* Helper to allocate iovec buffers for all vqs. */
static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
{
int i;
for (i = 0; i < dev->nvqs; ++i) {
dev->vqs[i].indirect = kmalloc(GFP_KERNEL, UIO_MAXIOV *
sizeof *dev->vqs[i].indirect);
dev->vqs[i].log = kmalloc(GFP_KERNEL, UIO_MAXIOV *
sizeof *dev->vqs[i].log);
if (!dev->vqs[i].indirect || !dev->vqs[i].log)
goto err_nomem;
}
return 0;
err_nomem:
for (; i >= 0; --i) {
kfree(dev->vqs[i].indirect);
kfree(dev->vqs[i].log);
}
return -ENOMEM;
}
long vhost_dev_init(struct vhost_dev *dev,
struct vhost_virtqueue *vqs, int nvqs)
{
int i, ret;
dev->vqs = vqs;
dev->nvqs = nvqs;
mutex_init(&dev->mutex);
dev->log_ctx = NULL;
dev->log_file = NULL;
dev->memory = NULL;
dev->mm = NULL;
//dev->wq = NULL;
spin_lock_init(&dev->work_lock);
INIT_LIST_HEAD(&dev->work_list);
dev->worker = NULL;
ret = vhost_dev_alloc_iovecs(dev);
if (ret)
return ret;
for (i = 0; i < dev->nvqs; ++i) {
dev->vqs[i].dev = dev;
mutex_init(&dev->vqs[i].mutex);
vhost_vq_reset(dev, dev->vqs + i);
if (dev->vqs[i].handle_kick)
vhost_poll_init(&dev->vqs[i].poll,
dev->vqs[i].handle_kick,
POLLIN, dev);
}
return 0;
}
/* Caller should have device mutex */
long vhost_dev_check_owner(struct vhost_dev *dev)
{
/* Are you the owner? If not, I don't think you mean to do that */
return dev->mm == current->mm ? 0 : -EPERM;
}
/*
struct vhost_attach_cgroups_struct {
struct work_struct work;
struct task_struct *owner;
int ret;
};
static void vhost_attach_cgroups_work(struct work_struct *work)
{
struct vhost_attach_cgroups_struct *s;
s = container_of(work, struct vhost_attach_cgroups_struct, work);
s->ret = cgroup_attach_task_all(s->owner, current);
}
static int vhost_attach_cgroups(struct workqueue_struct *wq)
{
struct vhost_attach_cgroups_struct attach;
attach.owner = current;
INIT_WORK(&attach.work, vhost_attach_cgroups_work);
queue_work(wq, &attach.work);
flush_work(&attach.work);
return attach.ret;
}
*/
/* Caller should have device mutex */
static long vhost_dev_set_owner(struct vhost_dev *dev)
{
struct task_struct *worker;
int err;
/* Is there an owner already? */
if (dev->mm) {
err = -EBUSY;
goto err;
}
/* No owner, become one */
dev->mm = get_task_mm(current);
/* Initialize the workqueue. */
//snprintf(vhost_name, sizeof vhost_name, "vhost-%d", current->pid);
//dev->wq = create_singlethread_workqueue(vhost_name);
//if (!dev->wq) {
// err = -ENOMEM;
// goto err_wq;
//}
worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid);
if (IS_ERR(worker)) {
err = PTR_ERR(worker);
goto err_worker;
}
dev->worker = worker;
wake_up_process(worker);
/*
err = vhost_attach_cgroups(dev->wq);
if (err)
goto err_cgroups;
*/
return 0;
/*
err_cgroups:
destroy_workqueue(dev->wq);
dev->wq = NULL;
*/
err_worker:
if (dev->mm)
mmput(dev->mm);
dev->mm = NULL;
err:
return err;
}
/* Caller should have device mutex */
long vhost_dev_reset_owner(struct vhost_dev *dev)
{
struct vhost_memory *memory;
/* Restore memory to default empty mapping. */
memory = kmalloc(offsetof(struct vhost_memory, regions), GFP_KERNEL);
if (!memory)
return -ENOMEM;
vhost_dev_cleanup(dev);
memory->nregions = 0;
dev->memory = memory;
return 0;
}
/* Caller should have device mutex */
void vhost_dev_cleanup(struct vhost_dev *dev)
{
int i;
for (i = 0; i < dev->nvqs; ++i) {
if (dev->vqs[i].kick && dev->vqs[i].handle_kick) {
vhost_poll_stop(&dev->vqs[i].poll);
vhost_poll_flush(&dev->vqs[i].poll);
}
if (dev->vqs[i].error_ctx)
eventfd_ctx_put(dev->vqs[i].error_ctx);
if (dev->vqs[i].error)
fput(dev->vqs[i].error);
if (dev->vqs[i].kick)
fput(dev->vqs[i].kick);
if (dev->vqs[i].call_ctx)
eventfd_ctx_put(dev->vqs[i].call_ctx);
if (dev->vqs[i].call)
fput(dev->vqs[i].call);
vhost_vq_reset(dev, dev->vqs + i);
kfree(dev->vqs[i].indirect);
kfree(dev->vqs[i].log);
}
if (dev->log_ctx)
eventfd_ctx_put(dev->log_ctx);
dev->log_ctx = NULL;
if (dev->log_file)
fput(dev->log_file);
dev->log_file = NULL;
/* No one will access memory at this point */
kfree(dev->memory);
dev->memory = NULL;
if (dev->mm)
mmput(dev->mm);
dev->mm = NULL;
/*
if (dev->wq)
destroy_workqueue(dev->wq);
dev->wq = NULL;
*/
WARN_ON(!list_empty(&dev->work_list));
kthread_stop(dev->worker);
}
static int log_access_ok(void __user *log_base, u64 addr, unsigned long sz)
{
u64 a = addr / VHOST_PAGE_SIZE / 8;
/* Make sure 64 bit math will not overflow. */
if (a > ULONG_MAX - (unsigned long)log_base ||
a + (unsigned long)log_base > ULONG_MAX)
return -EFAULT;
return access_ok(VERIFY_WRITE, log_base + a,
(sz + VHOST_PAGE_SIZE * 8 - 1) / VHOST_PAGE_SIZE / 8);
}
/* Caller should have vq mutex and device mutex. */
static int vq_memory_access_ok(void __user *log_base, struct vhost_memory *mem,
int log_all)
{
int i;
if (!mem)
return 0;
for (i = 0; i < mem->nregions; ++i) {
struct vhost_memory_region *m = mem->regions + i;
unsigned long a = m->userspace_addr;
if (m->memory_size > ULONG_MAX)
return 0;
else if (!access_ok(VERIFY_WRITE, (void __user *)a,
m->memory_size))
return 0;
else if (log_all && !log_access_ok(log_base,
m->guest_phys_addr,
m->memory_size))
return 0;
}
return 1;
}
/* Can we switch to this memory table? */
/* Caller should have device mutex but not vq mutex */
static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
int log_all)
{
int i;
for (i = 0; i < d->nvqs; ++i) {
int ok;
mutex_lock(&d->vqs[i].mutex);
/* If ring is inactive, will check when it's enabled. */
if (d->vqs[i].private_data)
ok = vq_memory_access_ok(d->vqs[i].log_base, mem,
log_all);
else
ok = 1;
mutex_unlock(&d->vqs[i].mutex);
if (!ok)
return 0;
}
return 1;
}
static int vq_access_ok(unsigned int num,
struct vring_desc __user *desc,
struct vring_avail __user *avail,
struct vring_used __user *used)
{
return access_ok(VERIFY_READ, desc, num * sizeof *desc) &&
access_ok(VERIFY_READ, avail,
sizeof *avail + num * sizeof *avail->ring) &&
access_ok(VERIFY_WRITE, used,
sizeof *used + num * sizeof *used->ring);
}
/* Can we log writes? */
/* Caller should have device mutex but not vq mutex */
int vhost_log_access_ok(struct vhost_dev *dev)
{
return memory_access_ok(dev, dev->memory, 1);
}
/* Verify access for write logging. */
/* Caller should have vq mutex and device mutex */
static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base)
{
return vq_memory_access_ok(log_base, vq->dev->memory,
vhost_has_feature(vq->dev, VHOST_F_LOG_ALL)) &&
(!vq->log_used || log_access_ok(log_base, vq->log_addr,
sizeof *vq->used +
vq->num * sizeof *vq->used->ring));
}
/* Can we start vq? */
/* Caller should have vq mutex and device mutex */
int vhost_vq_access_ok(struct vhost_virtqueue *vq)
{
return vq_access_ok(vq->num, vq->desc, vq->avail, vq->used) &&
vq_log_access_ok(vq, vq->log_base);
}
static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
{
struct vhost_memory mem, *newmem, *oldmem;
unsigned long size = offsetof(struct vhost_memory, regions);
if (copy_from_user(&mem, m, size))
return -EFAULT;
if (mem.padding)
return -EOPNOTSUPP;
if (mem.nregions > VHOST_MEMORY_MAX_NREGIONS)
return -E2BIG;
newmem = kmalloc(size + mem.nregions * sizeof *m->regions, GFP_KERNEL);
if (!newmem)
return -ENOMEM;
memcpy(newmem, &mem, size);
if (copy_from_user(newmem->regions, m->regions,
mem.nregions * sizeof *m->regions)) {
kfree(newmem);
return -EFAULT;
}
if (!memory_access_ok(d, newmem, vhost_has_feature(d, VHOST_F_LOG_ALL))) {
kfree(newmem);
return -EFAULT;
}
oldmem = d->memory;
rcu_assign_pointer(d->memory, newmem);
synchronize_rcu();
kfree(oldmem);
return 0;
}
static int init_used(struct vhost_virtqueue *vq,
struct vring_used __user *used)
{
int r = put_user(vq->used_flags, &used->flags);
if (r)
return r;
return get_user(vq->last_used_idx, &used->idx);
}
static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
{
struct file *eventfp, *filep = NULL,
*pollstart = NULL, *pollstop = NULL;
struct eventfd_ctx *ctx = NULL;
u32 __user *idxp = argp;
struct vhost_virtqueue *vq;
struct vhost_vring_state s;
struct vhost_vring_file f;
struct vhost_vring_addr a;
u32 idx;
long r;
r = get_user(idx, idxp);
if (r < 0)
return r;
if (idx >= d->nvqs)
return -ENOBUFS;
vq = d->vqs + idx;
mutex_lock(&vq->mutex);
switch (ioctl) {
case VHOST_SET_VRING_NUM:
/* Resizing ring with an active backend?
* You don't want to do that. */
if (vq->private_data) {
r = -EBUSY;
break;
}
if (copy_from_user(&s, argp, sizeof s)) {
r = -EFAULT;
break;
}
if (!s.num || s.num > 0xffff || (s.num & (s.num - 1))) {
r = -EINVAL;
break;
}
vq->num = s.num;
break;
case VHOST_SET_VRING_BASE:
/* Moving base with an active backend?
* You don't want to do that. */
if (vq->private_data) {
r = -EBUSY;
break;
}
if (copy_from_user(&s, argp, sizeof s)) {
r = -EFAULT;
break;
}
if (s.num > 0xffff) {
r = -EINVAL;
break;
}
vq->last_avail_idx = s.num;
/* Forget the cached index value. */
vq->avail_idx = vq->last_avail_idx;
break;
case VHOST_GET_VRING_BASE:
s.index = idx;
s.num = vq->last_avail_idx;
if (copy_to_user(argp, &s, sizeof s))
r = -EFAULT;
break;
case VHOST_SET_VRING_ADDR:
if (copy_from_user(&a, argp, sizeof a)) {
r = -EFAULT;
break;
}
if (a.flags & ~(0x1 << VHOST_VRING_F_LOG)) {
r = -EOPNOTSUPP;
break;
}
/* For 32bit, verify that the top 32bits of the user
data are set to zero. */
if ((u64)(unsigned long)a.desc_user_addr != a.desc_user_addr ||
(u64)(unsigned long)a.used_user_addr != a.used_user_addr ||
(u64)(unsigned long)a.avail_user_addr != a.avail_user_addr) {
r = -EFAULT;
break;
}
if ((a.avail_user_addr & (sizeof *vq->avail->ring - 1)) ||
(a.used_user_addr & (sizeof *vq->used->ring - 1)) ||
(a.log_guest_addr & (sizeof *vq->used->ring - 1))) {
r = -EINVAL;
break;
}
/* We only verify access here if backend is configured.
* If it is not, we don't as size might not have been setup.
* We will verify when backend is configured. */
if (vq->private_data) {
if (!vq_access_ok(vq->num,
(void __user *)(unsigned long)a.desc_user_addr,
(void __user *)(unsigned long)a.avail_user_addr,
(void __user *)(unsigned long)a.used_user_addr)) {
r = -EINVAL;
break;
}
/* Also validate log access for used ring if enabled. */
if ((a.flags & (0x1 << VHOST_VRING_F_LOG)) &&
!log_access_ok(vq->log_base, a.log_guest_addr,
sizeof *vq->used +
vq->num * sizeof *vq->used->ring)) {
r = -EINVAL;
break;
}
}
r = init_used(vq, (struct vring_used __user *)(unsigned long)
a.used_user_addr);
if (r)
break;
vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG));
vq->desc = (void __user *)(unsigned long)a.desc_user_addr;
vq->avail = (void __user *)(unsigned long)a.avail_user_addr;
vq->log_addr = a.log_guest_addr;
vq->used = (void __user *)(unsigned long)a.used_user_addr;
break;
case VHOST_SET_VRING_KICK:
if (copy_from_user(&f, argp, sizeof f)) {
r = -EFAULT;
break;
}
eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
if (IS_ERR(eventfp)) {
r = PTR_ERR(eventfp);
break;
}
if (eventfp != vq->kick) {
pollstop = filep = vq->kick;
pollstart = vq->kick = eventfp;
} else
filep = eventfp;
break;
case VHOST_SET_VRING_CALL:
if (copy_from_user(&f, argp, sizeof f)) {
r = -EFAULT;
break;
}
eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
if (IS_ERR(eventfp)) {
r = PTR_ERR(eventfp);
break;
}
if (eventfp != vq->call) {
filep = vq->call;
ctx = vq->call_ctx;
vq->call = eventfp;
vq->call_ctx = eventfp ?
eventfd_ctx_fileget(eventfp) : NULL;
} else
filep = eventfp;
break;
case VHOST_SET_VRING_ERR:
if (copy_from_user(&f, argp, sizeof f)) {
r = -EFAULT;
break;
}
eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
if (IS_ERR(eventfp)) {
r = PTR_ERR(eventfp);
break;
}
if (eventfp != vq->error) {
filep = vq->error;
vq->error = eventfp;
ctx = vq->error_ctx;
vq->error_ctx = eventfp ?
eventfd_ctx_fileget(eventfp) : NULL;
} else
filep = eventfp;
break;
default:
r = -ENOIOCTLCMD;
}
if (pollstop && vq->handle_kick)
vhost_poll_stop(&vq->poll);
if (ctx)
eventfd_ctx_put(ctx);
if (filep)
fput(filep);
if (pollstart && vq->handle_kick)
vhost_poll_start(&vq->poll, vq->kick);
mutex_unlock(&vq->mutex);
if (pollstop && vq->handle_kick)
vhost_poll_flush(&vq->poll);
return r;
}
/* Caller must have device mutex */
long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct file *eventfp, *filep = NULL;
struct eventfd_ctx *ctx = NULL;
u64 p;
long r;
int i, fd;
/* If you are not the owner, you can become one */
if (ioctl == VHOST_SET_OWNER) {
r = vhost_dev_set_owner(d);
goto done;
}
/* You must be the owner to do anything else */
r = vhost_dev_check_owner(d);
if (r)
goto done;
switch (ioctl) {
case VHOST_SET_MEM_TABLE:
r = vhost_set_memory(d, argp);
break;
case VHOST_SET_LOG_BASE:
if (copy_from_user(&p, argp, sizeof p)) {
r = -EFAULT;
break;
}
if ((u64)(unsigned long)p != p) {
r = -EFAULT;
break;
}
for (i = 0; i < d->nvqs; ++i) {
struct vhost_virtqueue *vq;
void __user *base = (void __user *)(unsigned long)p;
vq = d->vqs + i;
mutex_lock(&vq->mutex);
/* If ring is inactive, will check when it's enabled. */
if (vq->private_data && !vq_log_access_ok(vq, base))
r = -EFAULT;
else
vq->log_base = base;
mutex_unlock(&vq->mutex);
}
break;
case VHOST_SET_LOG_FD:
r = get_user(fd, (int __user *)argp);
if (r < 0)
break;
eventfp = fd == -1 ? NULL : eventfd_fget(fd);
if (IS_ERR(eventfp)) {
r = PTR_ERR(eventfp);
break;
}
if (eventfp != d->log_file) {
filep = d->log_file;
ctx = d->log_ctx;
d->log_ctx = eventfp ?
eventfd_ctx_fileget(eventfp) : NULL;
} else
filep = eventfp;
for (i = 0; i < d->nvqs; ++i) {
mutex_lock(&d->vqs[i].mutex);
d->vqs[i].log_ctx = d->log_ctx;
mutex_unlock(&d->vqs[i].mutex);
}
if (ctx)
eventfd_ctx_put(ctx);
if (filep)
fput(filep);
break;
default:
r = vhost_set_vring(d, ioctl, argp);
break;
}
done:
return r;
}
static const struct vhost_memory_region *find_region(struct vhost_memory *mem,
__u64 addr, __u32 len)
{
struct vhost_memory_region *reg;
int i;
/* linear search is not brilliant, but we really have on the order of 6
* regions in practice */
for (i = 0; i < mem->nregions; ++i) {
reg = mem->regions + i;
if (reg->guest_phys_addr <= addr &&
reg->guest_phys_addr + reg->memory_size - 1 >= addr)
return reg;
}
return NULL;
}
/* TODO: This is really inefficient. We need something like get_user()
* (instruction directly accesses the data, with an exception table entry
* returning -EFAULT). See Documentation/x86/exception-tables.txt.
*/
static int set_bit_to_user(int nr, void __user *addr)
{
unsigned long log = (unsigned long)addr;
struct page *page;
void *base;
int bit = nr + (log % PAGE_SIZE) * 8;
int r;
r = get_user_pages_fast(log, 1, 1, &page);
if (r < 0)
return r;
BUG_ON(r != 1);
base = kmap_atomic(page, KM_USER0);
set_bit(bit, base);
kunmap_atomic(base, KM_USER0);
set_page_dirty_lock(page);
put_page(page);
return 0;
}
static int log_write(void __user *log_base,
u64 write_address, u64 write_length)
{
int r;
if (!write_length)
return 0;
write_address /= VHOST_PAGE_SIZE;
for (;;) {
u64 base = (u64)(unsigned long)log_base;
u64 log = base + write_address / 8;
int bit = write_address % 8;
if ((u64)(unsigned long)log != log)
return -EFAULT;
r = set_bit_to_user(bit, (void __user *)(unsigned long)log);
if (r < 0)
return r;
if (write_length <= VHOST_PAGE_SIZE)
break;
write_length -= VHOST_PAGE_SIZE;
write_address += VHOST_PAGE_SIZE;
}
return r;
}
int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
unsigned int log_num, u64 len)
{
int i, r;
/* Make sure data written is seen before log. */
smp_wmb();
for (i = 0; i < log_num; ++i) {
u64 l = min(log[i].len, len);
r = log_write(vq->log_base, log[i].addr, l);
if (r < 0)
return r;
len -= l;
if (!len)
return 0;
}
if (vq->log_ctx)
eventfd_signal(vq->log_ctx, 1);
/* Length written exceeds what we have stored. This is a bug. */
BUG();
return 0;
}
int translate_desc(struct vhost_dev *dev, u64 addr, u32 len,
struct iovec iov[], int iov_size)
{
const struct vhost_memory_region *reg;
struct vhost_memory *mem;
struct iovec *_iov;
u64 s = 0;
int ret = 0;
rcu_read_lock();
mem = rcu_dereference(dev->memory);
while ((u64)len > s) {
u64 size;
if (unlikely(ret >= iov_size)) {
ret = -ENOBUFS;
break;
}
reg = find_region(mem, addr, len);
if (unlikely(!reg)) {
ret = -EFAULT;
break;
}
_iov = iov + ret;
size = reg->memory_size - addr + reg->guest_phys_addr;
_iov->iov_len = min((u64)len, size);
_iov->iov_base = (void *)(unsigned long)
(reg->userspace_addr + addr - reg->guest_phys_addr);
s += size;
addr += size;
++ret;
}
rcu_read_unlock();
return ret;
}
/* Each buffer in the virtqueues is actually a chain of descriptors. This
* function returns the next descriptor in the chain,
* or -1U if we're at the end. */
static unsigned next_desc(struct vring_desc *desc)
{
unsigned int next;
/* If this descriptor says it doesn't chain, we're done. */
if (!(desc->flags & VRING_DESC_F_NEXT))
return -1U;
/* Check they're not leading us off end of descriptors. */
next = desc->next;
/* Make sure compiler knows to grab that: we don't want it changing! */
/* We will use the result as an index in an array, so most
* architectures only need a compiler barrier here. */
read_barrier_depends();
return next;
}
static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
struct iovec iov[], unsigned int iov_size,
unsigned int *out_num, unsigned int *in_num,
struct vhost_log *log, unsigned int *log_num,
struct vring_desc *indirect)
{
struct vring_desc desc;
unsigned int i = 0, count, found = 0;
int ret;
/* Sanity check */
if (unlikely(indirect->len % sizeof desc)) {
vq_err(vq, "Invalid length in indirect descriptor: "
"len 0x%llx not multiple of 0x%zx\n",
(unsigned long long)indirect->len,
sizeof desc);
return -EINVAL;
}
ret = translate_desc(dev, indirect->addr, indirect->len, vq->indirect,
UIO_MAXIOV);
if (unlikely(ret < 0)) {
vq_err(vq, "Translation failure %d in indirect.\n", ret);
return ret;
}
/* We will use the result as an address to read from, so most
* architectures only need a compiler barrier here. */
read_barrier_depends();
count = indirect->len / sizeof desc;
/* Buffers are chained via a 16 bit next field, so
* we can have at most 2^16 of these. */
if (unlikely(count > USHORT_MAX + 1)) {
vq_err(vq, "Indirect buffer length too big: %d\n",
indirect->len);
return -E2BIG;
}
do {
unsigned iov_count = *in_num + *out_num;
if (unlikely(++found > count)) {
vq_err(vq, "Loop detected: last one at %u "
"indirect size %u\n",
i, count);
return -EINVAL;
}
if (unlikely(memcpy_fromiovec((unsigned char *)&desc, vq->indirect,
sizeof desc))) {
vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
i, (size_t)indirect->addr + i * sizeof desc);
return -EINVAL;
}
if (unlikely(desc.flags & VRING_DESC_F_INDIRECT)) {
vq_err(vq, "Nested indirect descriptor: idx %d, %zx\n",
i, (size_t)indirect->addr + i * sizeof desc);
return -EINVAL;
}
ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
iov_size - iov_count);
if (unlikely(ret < 0)) {
vq_err(vq, "Translation failure %d indirect idx %d\n",
ret, i);
return ret;
}
/* If this is an input descriptor, increment that count. */
if (desc.flags & VRING_DESC_F_WRITE) {
*in_num += ret;
if (unlikely(log)) {
log[*log_num].addr = desc.addr;
log[*log_num].len = desc.len;
++*log_num;
}
} else {
/* If it's an output descriptor, they're all supposed
* to come before any input descriptors. */
if (unlikely(*in_num)) {
vq_err(vq, "Indirect descriptor "
"has out after in: idx %d\n", i);
return -EINVAL;
}
*out_num += ret;
}
} while ((i = next_desc(&desc)) != -1);
return 0;
}
/* This looks in the virtqueue and for the first available buffer, and converts
* it to an iovec for convenient access. Since descriptors consist of some
* number of output then some number of input descriptors, it's actually two
* iovecs, but we pack them into one and note how many of each there were.
*
* This function returns the descriptor number found, or vq->num (which is
* never a valid descriptor number) if none was found. A negative code is
* returned on error. */
int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
struct iovec iov[], unsigned int iov_size,
unsigned int *out_num, unsigned int *in_num,
struct vhost_log *log, unsigned int *log_num)
{
struct vring_desc desc;
unsigned int i, head, found = 0;
u16 last_avail_idx;
int ret;
/* Check it isn't doing very strange things with descriptor numbers. */
last_avail_idx = vq->last_avail_idx;
if (unlikely(get_user(vq->avail_idx, &vq->avail->idx))) {
vq_err(vq, "Failed to access avail idx at %p\n",
&vq->avail->idx);
return -EFAULT;
}
if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) {
vq_err(vq, "Guest moved used index from %u to %u",
last_avail_idx, vq->avail_idx);
return -EFAULT;
}
/* If there's nothing new since last we looked, return invalid. */
if (vq->avail_idx == last_avail_idx)
return vq->num;
/* Only get avail ring entries after they have been exposed by guest. */
smp_rmb();
/* Grab the next descriptor number they're advertising, and increment
* the index we've seen. */
if (unlikely(get_user(head,
&vq->avail->ring[last_avail_idx % vq->num]))) {
vq_err(vq, "Failed to read head: idx %d address %p\n",
last_avail_idx,
&vq->avail->ring[last_avail_idx % vq->num]);
return -EFAULT;
}
/* If their number is silly, that's an error. */
if (unlikely(head >= vq->num)) {
vq_err(vq, "Guest says index %u > %u is available",
head, vq->num);
return -EINVAL;
}
/* When we start there are none of either input nor output. */
*out_num = *in_num = 0;
if (unlikely(log))
*log_num = 0;
i = head;
do {
unsigned iov_count = *in_num + *out_num;
if (unlikely(i >= vq->num)) {
vq_err(vq, "Desc index is %u > %u, head = %u",
i, vq->num, head);
return -EINVAL;
}
if (unlikely(++found > vq->num)) {
vq_err(vq, "Loop detected: last one at %u "
"vq size %u head %u\n",
i, vq->num, head);
return -EINVAL;
}
ret = copy_from_user(&desc, vq->desc + i, sizeof desc);
if (unlikely(ret)) {
vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
i, vq->desc + i);
return -EFAULT;
}
if (desc.flags & VRING_DESC_F_INDIRECT) {
ret = get_indirect(dev, vq, iov, iov_size,
out_num, in_num,
log, log_num, &desc);
if (unlikely(ret < 0)) {
vq_err(vq, "Failure detected "
"in indirect descriptor at idx %d\n", i);
return ret;
}
continue;
}
ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
iov_size - iov_count);
if (unlikely(ret < 0)) {
vq_err(vq, "Translation failure %d descriptor idx %d\n",
ret, i);
return ret;
}
if (desc.flags & VRING_DESC_F_WRITE) {
/* If this is an input descriptor,
* increment that count. */
*in_num += ret;
if (unlikely(log)) {
log[*log_num].addr = desc.addr;
log[*log_num].len = desc.len;
++*log_num;
}
} else {
/* If it's an output descriptor, they're all supposed
* to come before any input descriptors. */
if (unlikely(*in_num)) {
vq_err(vq, "Descriptor has out after in: "
"idx %d\n", i);
return -EINVAL;
}
*out_num += ret;
}
} while ((i = next_desc(&desc)) != -1);
/* On success, increment avail index. */
vq->last_avail_idx++;
return head;
}
/* Reverse the effect of vhost_get_vq_desc. Useful for error handling. */
void vhost_discard_vq_desc(struct vhost_virtqueue *vq)
{
vq->last_avail_idx--;
}
/* After we've used one of their buffers, we tell them about it. We'll then
* want to notify the guest, using eventfd. */
int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
{
struct vring_used_elem *used;
/* The virtqueue contains a ring of used buffers. Get a pointer to the
* next entry in that used ring. */
used = &vq->used->ring[vq->last_used_idx % vq->num];
if (put_user(head, &used->id)) {
vq_err(vq, "Failed to write used id");
return -EFAULT;
}
if (put_user(len, &used->len)) {
vq_err(vq, "Failed to write used len");
return -EFAULT;
}
/* Make sure buffer is written before we update index. */
smp_wmb();
if (put_user(vq->last_used_idx + 1, &vq->used->idx)) {
vq_err(vq, "Failed to increment used idx");
return -EFAULT;
}
if (unlikely(vq->log_used)) {
/* Make sure data is seen before log. */
smp_wmb();
/* Log used ring entry write. */
log_write(vq->log_base,
vq->log_addr + ((void *)used - (void *)vq->used),
sizeof *used);
/* Log used index update. */
log_write(vq->log_base,
vq->log_addr + offsetof(struct vring_used, idx),
sizeof vq->used->idx);
if (vq->log_ctx)
eventfd_signal(vq->log_ctx, 1);
}
vq->last_used_idx++;
return 0;
}
/* This actually signals the guest, using eventfd. */
void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
{
__u16 flags;
/* Flush out used index updates. This is paired
* with the barrier that the Guest executes when enabling
* interrupts. */
smp_mb();
if (get_user(flags, &vq->avail->flags)) {
vq_err(vq, "Failed to get flags");
return;
}
/* If they don't want an interrupt, don't signal, unless empty. */
if ((flags & VRING_AVAIL_F_NO_INTERRUPT) &&
(vq->avail_idx != vq->last_avail_idx ||
!vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY)))
return;
/* Signal the Guest tell them we used something up. */
if (vq->call_ctx)
eventfd_signal(vq->call_ctx, 1);
}
/* And here's the combo meal deal. Supersize me! */
void vhost_add_used_and_signal(struct vhost_dev *dev,
struct vhost_virtqueue *vq,
unsigned int head, int len)
{
vhost_add_used(vq, head, len);
vhost_signal(dev, vq);
}
/* OK, now we need to know about added descriptors. */
bool vhost_enable_notify(struct vhost_virtqueue *vq)
{
u16 avail_idx;
int r;
if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
return false;
vq->used_flags &= ~VRING_USED_F_NO_NOTIFY;
r = put_user(vq->used_flags, &vq->used->flags);
if (r) {
vq_err(vq, "Failed to enable notification at %p: %d\n",
&vq->used->flags, r);
return false;
}
/* They could have slipped one in as we were doing that: make
* sure it's written, then check again. */
smp_mb();
r = get_user(avail_idx, &vq->avail->idx);
if (r) {
vq_err(vq, "Failed to check avail idx at %p: %d\n",
&vq->avail->idx, r);
return false;
}
return avail_idx != vq->last_avail_idx;
}
/* We don't need to be notified again. */
void vhost_disable_notify(struct vhost_virtqueue *vq)
{
int r;
if (vq->used_flags & VRING_USED_F_NO_NOTIFY)
return;
vq->used_flags |= VRING_USED_F_NO_NOTIFY;
r = put_user(vq->used_flags, &vq->used->flags);
if (r)
vq_err(vq, "Failed to enable notification at %p: %d\n",
&vq->used->flags, r);
}
int vhost_init(void)
{
return 0;
}
void vhost_cleanup(void)
{
}
