2020-03-31 18:02:25

by Eugenio Perez Martin

[permalink] [raw]
Subject: [PATCH v2 4/8] vhost: batching fetches

From: "Michael S. Tsirkin" <[email protected]>

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 <[email protected]>
Signed-off-by: Eugenio PĂ©rez <[email protected]>
---
drivers/vhost/test.c | 2 +-
drivers/vhost/vhost.c | 47 ++++++++++++++++++++++++++++++++++++++-----
drivers/vhost/vhost.h | 5 ++++-
3 files changed, 47 insertions(+), 7 deletions(-)

diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index e37c92d4d7ad..58da17af93e9 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -119,7 +119,7 @@ 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;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 56c5253056ee..1646b1ce312a 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -303,6 +303,7 @@ 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;
@@ -371,6 +372,11 @@ static int vhost_worker(void *data)
return 0;
}

+static int vhost_vq_num_batch_descs(struct vhost_virtqueue *vq)
+{
+ return vq->max_descs - UIO_MAXIOV;
+}
+
static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq)
{
kfree(vq->descs);
@@ -393,6 +399,9 @@ 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;
+ if (vhost_vq_num_batch_descs(vq) < 0) {
+ return -EINVAL;
+ }
vq->descs = kmalloc_array(vq->max_descs,
sizeof(*vq->descs),
GFP_KERNEL);
@@ -1643,6 +1652,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
vq->last_avail_idx = s.num;
/* Forget the cached index value. */
vq->avail_idx = vq->last_avail_idx;
+ vq->ndescs = vq->first_desc = 0;
break;
case VHOST_GET_VRING_BASE:
s.index = idx;
@@ -2211,7 +2221,7 @@ 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;
@@ -2224,7 +2234,11 @@ 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);
@@ -2315,6 +2329,24 @@ 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 <= vhost_vq_num_batch_descs(vq))
+ 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
@@ -2340,7 +2372,7 @@ int vhost_get_vq_desc(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;
@@ -2386,14 +2418,19 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
}

ret = desc->id;
+
+ if (!(desc->flags & VRING_DESC_F_NEXT))
+ break;
}

- 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;
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index c1efd8256a88..64a4ebab6dd2 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -100,6 +100,7 @@ struct vhost_virtqueue {

struct vhost_desc *descs;
int ndescs;
+ int first_desc;
int max_descs;

const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS];
@@ -242,7 +243,7 @@ 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)
@@ -268,6 +269,8 @@ static inline void vhost_vq_set_backend_opaque(struct vhost_virtqueue *vq,
void *private_data)
{
vq->private_data = private_data;
+ vq->ndescs = 0;
+ vq->first_desc = 0;
}

/**
--
2.18.1