On 2017年09月27日 03:19, Michael S. Tsirkin wrote:
On Fri, Sep 22, 2017 at 04:02:32PM +0800, Jason Wang wrote:
This patch introduces vhost_prefetch_desc_indices() which could batch
descriptor indices fetching and used ring updating. This intends to
reduce the cache misses of indices fetching and updating and reduce
cache line bounce when virtqueue is almost full. copy_to_user() was
used in order to benefit from modern cpus that support fast string
copy. Batched virtqueue processing will be the first user.
Signed-off-by: Jason Wang <jasowang@xxxxxxxxxx>
---
drivers/vhost/vhost.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++
drivers/vhost/vhost.h | 3 +++
2 files changed, 58 insertions(+)
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index f87ec75..8424166d 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2437,6 +2437,61 @@ struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev,
}
EXPORT_SYMBOL_GPL(vhost_dequeue_msg);
+int vhost_prefetch_desc_indices(struct vhost_virtqueue *vq,
+ struct vring_used_elem *heads,
+ u16 num, bool used_update)
why do you need to combine used update with prefetch?
For better performance and I believe we don't care about the overhead
when we meet errors in tx.
+{
+ int ret, ret2;
+ u16 last_avail_idx, last_used_idx, total, copied;
+ __virtio16 avail_idx;
+ struct vring_used_elem __user *used;
+ int i;
+
+ if (unlikely(vhost_get_avail(vq, avail_idx, &vq->avail->idx))) {
+ vq_err(vq, "Failed to access avail idx at %p\n",
+ &vq->avail->idx);
+ return -EFAULT;
+ }
+ last_avail_idx = vq->last_avail_idx & (vq->num - 1);
+ vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
+ total = vq->avail_idx - vq->last_avail_idx;
+ ret = total = min(total, num);
+
+ for (i = 0; i < ret; i++) {
+ ret2 = vhost_get_avail(vq, heads[i].id,
+ &vq->avail->ring[last_avail_idx]);
+ if (unlikely(ret2)) {
+ vq_err(vq, "Failed to get descriptors\n");
+ return -EFAULT;
+ }
+ last_avail_idx = (last_avail_idx + 1) & (vq->num - 1);
+ }
+
+ if (!used_update)
+ return ret;
+
+ last_used_idx = vq->last_used_idx & (vq->num - 1);
+ while (total) {
+ copied = min((u16)(vq->num - last_used_idx), total);
+ ret2 = vhost_copy_to_user(vq,
+ &vq->used->ring[last_used_idx],
+ &heads[ret - total],
+ copied * sizeof(*used));
+
+ if (unlikely(ret2)) {
+ vq_err(vq, "Failed to update used ring!\n");
+ return -EFAULT;
+ }
+
+ last_used_idx = 0;
+ total -= copied;
+ }
+
+ /* Only get avail ring entries after they have been exposed by guest. */
+ smp_rmb();
Barrier before return is a very confusing API. I guess it's designed to
be used in a specific way to make it necessary - but what is it?
Looks like a and we need do this after reading avail_idx.
Thanks
+ return ret;
+}
+EXPORT_SYMBOL(vhost_prefetch_desc_indices);
static int __init vhost_init(void)
{
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 39ff897..16c2cb6 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -228,6 +228,9 @@ ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,
ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
struct iov_iter *from);
int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled);
+int vhost_prefetch_desc_indices(struct vhost_virtqueue *vq,
+ struct vring_used_elem *heads,
+ u16 num, bool used_update);
#define vq_err(vq, fmt, ...) do { \
pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \
--
2.7.4
