#include <linux/mm.h>
#include <linux/miscdevice.h>
#include <linux/mutex.h>
-#include <linux/workqueue.h>
#include <linux/rcupdate.h>
#include <linux/poll.h>
#include <linux/file.h>
#include <linux/highmem.h>
#include <linux/slab.h>
+#include <linux/kthread.h>
+#include <linux/cgroup.h>
#include <linux/net.h>
#include <linux/if_packet.h>
VHOST_MEMORY_F_LOG = 0x1,
};
-static struct workqueue_struct *vhost_workqueue;
-
static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
poll_table *pt)
{
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);
+ struct vhost_poll *poll = container_of(wait, struct vhost_poll, wait);
+
if (!((unsigned long)key & poll->mask))
return 0;
- queue_work(vhost_workqueue, &poll->work);
+ vhost_poll_queue(poll);
return 0;
}
/* Init poll structure */
-void vhost_poll_init(struct vhost_poll *poll, work_func_t func,
- unsigned long mask)
+void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
+ 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 = fn;
+ 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
* 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(vhost_workqueue, &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,
vq->used_flags = 0;
vq->log_used = false;
vq->log_addr = -1ull;
- vq->hdr_size = 0;
+ vq->vhost_hlen = 0;
+ vq->sock_hlen = 0;
vq->private_data = NULL;
vq->log_base = NULL;
vq->error_ctx = 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();
+
+ }
+}
+
long vhost_dev_init(struct vhost_dev *dev,
struct vhost_virtqueue *vqs, int nvqs)
{
int i;
+
dev->vqs = vqs;
dev->nvqs = nvqs;
mutex_init(&dev->mutex);
dev->log_file = NULL;
dev->memory = NULL;
dev->mm = NULL;
+ spin_lock_init(&dev->work_lock);
+ INIT_LIST_HEAD(&dev->work_list);
+ dev->worker = NULL;
for (i = 0; i < dev->nvqs; ++i) {
dev->vqs[i].dev = dev;
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->vqs[i].handle_kick, POLLIN, dev);
}
+
return 0;
}
/* 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)
- return -EBUSY;
+ if (dev->mm) {
+ err = -EBUSY;
+ goto err_mm;
+ }
/* No owner, become one */
dev->mm = get_task_mm(current);
+ worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid);
+ if (IS_ERR(worker)) {
+ err = PTR_ERR(worker);
+ goto err_worker;
+ }
+
+ dev->worker = worker;
+ err = cgroup_attach_task_current_cg(worker);
+ if (err)
+ goto err_cgroup;
+ wake_up_process(worker); /* avoid contributing to loadavg */
+
return 0;
+err_cgroup:
+ kthread_stop(worker);
+err_worker:
+ if (dev->mm)
+ mmput(dev->mm);
+ dev->mm = NULL;
+err_mm:
+ return err;
}
/* Caller should have device mutex */
if (dev->mm)
mmput(dev->mm);
dev->mm = 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)
{
int i;
- if (!mem)
- return 0;
+ if (!mem)
+ return 0;
for (i = 0; i < mem->nregions; ++i) {
struct vhost_memory_region *m = mem->regions + i;
{
struct vhost_memory mem, *newmem, *oldmem;
unsigned long size = offsetof(struct vhost_memory, regions);
- long r;
- r = copy_from_user(&mem, m, size);
- if (r)
- return r;
+ if (copy_from_user(&mem, m, size))
+ return -EFAULT;
if (mem.padding)
return -EOPNOTSUPP;
if (mem.nregions > VHOST_MEMORY_MAX_NREGIONS)
return -ENOMEM;
memcpy(newmem, &mem, size);
- r = copy_from_user(newmem->regions, m->regions,
- mem.nregions * sizeof *m->regions);
- if (r) {
+ if (copy_from_user(newmem->regions, m->regions,
+ mem.nregions * sizeof *m->regions)) {
kfree(newmem);
- return r;
+ return -EFAULT;
}
- if (!memory_access_ok(d, newmem, vhost_has_feature(d, VHOST_F_LOG_ALL)))
+ 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();
r = get_user(idx, idxp);
if (r < 0)
return r;
- if (idx > d->nvqs)
+ if (idx >= d->nvqs)
return -ENOBUFS;
vq = d->vqs + idx;
r = -EBUSY;
break;
}
- r = copy_from_user(&s, argp, sizeof s);
- if (r < 0)
+ 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;
r = -EBUSY;
break;
}
- r = copy_from_user(&s, argp, sizeof s);
- if (r < 0)
+ if (copy_from_user(&s, argp, sizeof s)) {
+ r = -EFAULT;
break;
+ }
if (s.num > 0xffff) {
r = -EINVAL;
break;
case VHOST_GET_VRING_BASE:
s.index = idx;
s.num = vq->last_avail_idx;
- r = copy_to_user(argp, &s, sizeof s);
+ if (copy_to_user(argp, &s, sizeof s))
+ r = -EFAULT;
break;
case VHOST_SET_VRING_ADDR:
- r = copy_from_user(&a, argp, sizeof a);
- if (r < 0)
+ if (copy_from_user(&a, argp, sizeof a)) {
+ r = -EFAULT;
break;
+ }
if (a.flags & ~(0x1 << VHOST_VRING_F_LOG)) {
r = -EOPNOTSUPP;
break;
vq->used = (void __user *)(unsigned long)a.used_user_addr;
break;
case VHOST_SET_VRING_KICK:
- r = copy_from_user(&f, argp, sizeof f);
- if (r < 0)
+ 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);
filep = eventfp;
break;
case VHOST_SET_VRING_CALL:
- r = copy_from_user(&f, argp, sizeof f);
- if (r < 0)
+ 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);
filep = eventfp;
break;
case VHOST_SET_VRING_ERR:
- r = copy_from_user(&f, argp, sizeof f);
- if (r < 0)
+ 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);
r = vhost_set_memory(d, argp);
break;
case VHOST_SET_LOG_BASE:
- r = copy_from_user(&p, argp, sizeof p);
- if (r < 0)
+ if (copy_from_user(&p, argp, sizeof p)) {
+ r = -EFAULT;
break;
+ }
if ((u64)(unsigned long)p != p) {
r = -EFAULT;
break;
return 0;
}
-int translate_desc(struct vhost_dev *dev, u64 addr, u32 len,
- struct iovec iov[], int iov_size)
+static 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;
mem = rcu_dereference(dev->memory);
while ((u64)len > s) {
u64 size;
- if (ret >= iov_size) {
+ if (unlikely(ret >= iov_size)) {
ret = -ENOBUFS;
break;
}
reg = find_region(mem, addr, len);
- if (!reg) {
+ 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)
+ _iov->iov_base = (void __user *)(unsigned long)
(reg->userspace_addr + addr - reg->guest_phys_addr);
s += size;
addr += size;
return next;
}
-static unsigned 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)
+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 (indirect->len % sizeof desc) {
+ 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,
ret = translate_desc(dev, indirect->addr, indirect->len, vq->indirect,
ARRAY_SIZE(vq->indirect));
- if (ret < 0) {
+ if (unlikely(ret < 0)) {
vq_err(vq, "Translation failure %d in indirect.\n", ret);
return ret;
}
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 (count > USHORT_MAX + 1) {
+ if (unlikely(count > USHRT_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 (++found > count) {
+ if (unlikely(++found > count)) {
vq_err(vq, "Loop detected: last one at %u "
"indirect size %u\n",
i, count);
return -EINVAL;
}
- if (memcpy_fromiovec((unsigned char *)&desc, vq->indirect,
- sizeof desc)) {
+ 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 (desc.flags & VRING_DESC_F_INDIRECT) {
+ 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 (ret < 0) {
+ if (unlikely(ret < 0)) {
vq_err(vq, "Translation failure %d indirect idx %d\n",
ret, i);
return ret;
} else {
/* If it's an output descriptor, they're all supposed
* to come before any input descriptors. */
- if (*in_num) {
+ if (unlikely(*in_num)) {
vq_err(vq, "Indirect descriptor "
"has out after in: idx %d\n", i);
return -EINVAL;
* 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. */
-unsigned 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)
+ * 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;
/* Check it isn't doing very strange things with descriptor numbers. */
last_avail_idx = vq->last_avail_idx;
- if (get_user(vq->avail_idx, &vq->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 vq->num;
+ return -EFAULT;
}
- if ((u16)(vq->avail_idx - last_avail_idx) > vq->num) {
+ 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 vq->num;
+ return -EFAULT;
}
/* If there's nothing new since last we looked, return invalid. */
/* Grab the next descriptor number they're advertising, and increment
* the index we've seen. */
- if (get_user(head, &vq->avail->ring[last_avail_idx % vq->num])) {
+ 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 vq->num;
+ return -EFAULT;
}
/* If their number is silly, that's an error. */
- if (head >= vq->num) {
+ if (unlikely(head >= vq->num)) {
vq_err(vq, "Guest says index %u > %u is available",
head, vq->num);
- return vq->num;
+ return -EINVAL;
}
/* When we start there are none of either input nor output. */
i = head;
do {
unsigned iov_count = *in_num + *out_num;
- if (i >= vq->num) {
+ if (unlikely(i >= vq->num)) {
vq_err(vq, "Desc index is %u > %u, head = %u",
i, vq->num, head);
- return vq->num;
+ return -EINVAL;
}
- if (++found > vq->num) {
+ 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 vq->num;
+ return -EINVAL;
}
ret = copy_from_user(&desc, vq->desc + i, sizeof desc);
- if (ret) {
+ if (unlikely(ret)) {
vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
i, vq->desc + i);
- return vq->num;
+ 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 (ret < 0) {
+ if (unlikely(ret < 0)) {
vq_err(vq, "Failure detected "
"in indirect descriptor at idx %d\n", i);
- return vq->num;
+ return ret;
}
continue;
}
ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
iov_size - iov_count);
- if (ret < 0) {
+ if (unlikely(ret < 0)) {
vq_err(vq, "Translation failure %d descriptor idx %d\n",
ret, i);
- return vq->num;
+ return ret;
}
if (desc.flags & VRING_DESC_F_WRITE) {
/* If this is an input descriptor,
} else {
/* If it's an output descriptor, they're all supposed
* to come before any input descriptors. */
- if (*in_num) {
+ if (unlikely(*in_num)) {
vq_err(vq, "Descriptor has out after in: "
"idx %d\n", i);
- return vq->num;
+ return -EINVAL;
}
*out_num += ret;
}
}
/* Reverse the effect of vhost_get_vq_desc. Useful for error handling. */
-void vhost_discard_vq_desc(struct vhost_virtqueue *vq)
+void vhost_discard_vq_desc(struct vhost_virtqueue *vq, int n)
{
- vq->last_avail_idx--;
+ vq->last_avail_idx -= n;
}
/* 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;
+ struct vring_used_elem __user *used;
/* The virtqueue contains a ring of used buffers. Get a pointer to the
* next entry in that used ring. */
smp_wmb();
/* Log used ring entry write. */
log_write(vq->log_base,
- vq->log_addr + ((void *)used - (void *)vq->used),
+ vq->log_addr +
+ ((void __user *)used - (void __user *)vq->used),
sizeof *used);
/* Log used index update. */
log_write(vq->log_base,
return 0;
}
+static int __vhost_add_used_n(struct vhost_virtqueue *vq,
+ struct vring_used_elem *heads,
+ unsigned count)
+{
+ struct vring_used_elem __user *used;
+ int start;
+
+ start = vq->last_used_idx % vq->num;
+ used = vq->used->ring + start;
+ if (copy_to_user(used, heads, count * sizeof *used)) {
+ vq_err(vq, "Failed to write used");
+ 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 __user *)used - (void __user *)vq->used),
+ count * sizeof *used);
+ }
+ vq->last_used_idx += count;
+ return 0;
+}
+
+/* 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_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
+ unsigned count)
+{
+ int start, n, r;
+
+ start = vq->last_used_idx % vq->num;
+ n = vq->num - start;
+ if (n < count) {
+ r = __vhost_add_used_n(vq, heads, n);
+ if (r < 0)
+ return r;
+ heads += n;
+ count -= n;
+ }
+ r = __vhost_add_used_n(vq, heads, count);
+
+ /* Make sure buffer is written before we update index. */
+ smp_wmb();
+ if (put_user(vq->last_used_idx, &vq->used->idx)) {
+ vq_err(vq, "Failed to increment used idx");
+ return -EFAULT;
+ }
+ if (unlikely(vq->log_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);
+ }
+ return r;
+}
+
/* This actually signals the guest, using eventfd. */
void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
{
vhost_signal(dev, vq);
}
+/* multi-buffer version of vhost_add_used_and_signal */
+void vhost_add_used_and_signal_n(struct vhost_dev *dev,
+ struct vhost_virtqueue *vq,
+ struct vring_used_elem *heads, unsigned count)
+{
+ vhost_add_used_n(vq, heads, count);
+ vhost_signal(dev, vq);
+}
+
/* OK, now we need to know about added descriptors. */
bool vhost_enable_notify(struct vhost_virtqueue *vq)
{
return false;
}
- return avail_idx != vq->last_avail_idx;
+ return avail_idx != vq->avail_idx;
}
/* We don't need to be notified again. */
vq_err(vq, "Failed to enable notification at %p: %d\n",
&vq->used->flags, r);
}
-
-int vhost_init(void)
-{
- vhost_workqueue = create_singlethread_workqueue("vhost");
- if (!vhost_workqueue)
- return -ENOMEM;
- return 0;
-}
-
-void vhost_cleanup(void)
-{
- destroy_workqueue(vhost_workqueue);
-}
projects / ~andy / linux / blobdiff