@@ -128,7 +128,7 @@ static int vhost_test_open(struct inode *inode, struct file *f)
dev = &n->dev;
vqs[VHOST_TEST_VQ] = &n->vqs[VHOST_TEST_VQ];
n->vqs[VHOST_TEST_VQ].handle_kick = handle_vq_kick;
- vhost_dev_init(dev, vqs, VHOST_TEST_VQ_MAX, UIO_MAXIOV,
+ vhost_dev_init(dev, vqs, VHOST_TEST_VQ_MAX, UIO_MAXIOV + 64,
VHOST_TEST_PKT_WEIGHT, VHOST_TEST_WEIGHT);
f->private_data = n;
@@ -302,6 +302,7 @@ static void vhost_vq_reset(struct vhost_dev *dev,
{
vq->num = 1;
vq->ndescs = 0;
+ vq->first_desc = 0;
vq->desc = NULL;
vq->avail = NULL;
vq->used = NULL;
@@ -390,6 +391,7 @@ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
for (i = 0; i < dev->nvqs; ++i) {
vq = dev->vqs[i];
vq->max_descs = dev->iov_limit;
+ vq->batch_descs = dev->iov_limit - UIO_MAXIOV;
vq->descs = kmalloc_array(vq->max_descs,
sizeof(*vq->descs),
GFP_KERNEL);
@@ -2366,6 +2368,8 @@ static void pop_split_desc(struct vhost_virtqueue *vq)
--vq->ndescs;
}
+#define VHOST_DESC_FLAGS (VRING_DESC_F_INDIRECT | VRING_DESC_F_WRITE | \
+ VRING_DESC_F_NEXT)
static int push_split_desc(struct vhost_virtqueue *vq, struct vring_desc *desc, u16 id)
{
struct vhost_desc *h;
@@ -2375,7 +2379,7 @@ static int push_split_desc(struct vhost_virtqueue *vq, struct vring_desc *desc,
h = &vq->descs[vq->ndescs++];
h->addr = vhost64_to_cpu(vq, desc->addr);
h->len = vhost32_to_cpu(vq, desc->len);
- h->flags = vhost16_to_cpu(vq, desc->flags);
+ h->flags = vhost16_to_cpu(vq, desc->flags) & VHOST_DESC_FLAGS;
h->id = id;
return 0;
@@ -2450,7 +2454,7 @@ static int fetch_indirect_descs(struct vhost_virtqueue *vq,
return 0;
}
-static int fetch_descs(struct vhost_virtqueue *vq)
+static int fetch_buf(struct vhost_virtqueue *vq)
{
unsigned int i, head, found = 0;
struct vhost_desc *last;
@@ -2463,7 +2467,11 @@ static int fetch_descs(struct vhost_virtqueue *vq)
/* Check it isn't doing very strange things with descriptor numbers. */
last_avail_idx = vq->last_avail_idx;
- if (vq->avail_idx == vq->last_avail_idx) {
+ if (unlikely(vq->avail_idx == vq->last_avail_idx)) {
+ /* If we already have work to do, don't bother re-checking. */
+ if (likely(vq->ndescs))
+ return vq->num;
+
if (unlikely(vhost_get_avail_idx(vq, &avail_idx))) {
vq_err(vq, "Failed to access avail idx at %p\n",
&vq->avail->idx);
@@ -2554,6 +2562,24 @@ static int fetch_descs(struct vhost_virtqueue *vq)
return 0;
}
+static int fetch_descs(struct vhost_virtqueue *vq)
+{
+ int ret = 0;
+
+ if (unlikely(vq->first_desc >= vq->ndescs)) {
+ vq->first_desc = 0;
+ vq->ndescs = 0;
+ }
+
+ if (vq->ndescs)
+ return 0;
+
+ while (!ret && vq->ndescs <= vq->batch_descs)
+ ret = fetch_buf(vq);
+
+ return vq->ndescs ? 0 : ret;
+}
+
/* 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
@@ -2579,12 +2605,12 @@ int vhost_get_vq_desc_batch(struct vhost_virtqueue *vq,
if (unlikely(log))
*log_num = 0;
- for (i = 0; i < vq->ndescs; ++i) {
+ for (i = vq->first_desc; i < vq->ndescs; ++i) {
unsigned iov_count = *in_num + *out_num;
struct vhost_desc *desc = &vq->descs[i];
int access;
- if (desc->flags & ~(VRING_DESC_F_INDIRECT | VRING_DESC_F_WRITE)) {
+ if (desc->flags & ~VHOST_DESC_FLAGS) {
vq_err(vq, "Unexpected flags: 0x%x at descriptor id 0x%x\n",
desc->flags, desc->id);
ret = -EINVAL;
@@ -2623,15 +2649,21 @@ int vhost_get_vq_desc_batch(struct vhost_virtqueue *vq,
}
*out_num += ret;
}
+
+ ret = desc->id;
+
+ if (!(desc->flags & VRING_DESC_F_NEXT))
+ break;
}
- ret = id;
- vq->ndescs = 0;
+ vq->first_desc = i + 1;
return ret;
err:
- vhost_discard_vq_desc(vq, 1);
+ for (i = vq->first_desc; i < vq->ndescs; ++i)
+ if (!(vq->descs[i].flags & VRING_DESC_F_NEXT))
+ vhost_discard_vq_desc(vq, 1);
vq->ndescs = 0;
return ret;
@@ -100,7 +100,9 @@ struct vhost_virtqueue {
struct vhost_desc *descs;
int ndescs;
+ int first_desc;
int max_descs;
+ int batch_descs;
const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS];
struct file *kick;
@@ -245,7 +247,7 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled);
#define vq_err(vq, fmt, ...) do { \
- pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \
+ pr_err(pr_fmt(fmt), ##__VA_ARGS__); \
if ((vq)->error_ctx) \
eventfd_signal((vq)->error_ctx, 1);\
} while (0)
With this patch applied, new and old code perform identically. Lots of extra optimizations are now possible, e.g. we can fetch multiple heads with copy_from/to_user now. We can get rid of maintaining the log array. Etc etc. Signed-off-by: Michael S. Tsirkin <mst@redhat.com> --- drivers/vhost/test.c | 2 +- drivers/vhost/vhost.c | 48 +++++++++++++++++++++++++++++++++++-------- drivers/vhost/vhost.h | 4 +++- 3 files changed, 44 insertions(+), 10 deletions(-)