virtqueue_add() populates the virtqueue descriptor table from the sgs
given. If it uses an indirect descriptor table, then it puts a single
descriptor in the descriptor table pointing to the kmalloc'ed indirect
table where the sg is populated.
Previously vring_add_indirect() did the allocation and the simple
linear layout. We replace that with alloc_indirect() which allocates
the indirect table then chains it like the normal descriptor table so
we can reuse the core logic.
This slows down pktgen by less than 1/2 a percent (which uses direct
descriptors), as well as vring_bench, but it's far neater.
vring_bench before:
1061485790-1104800648(1.08254e+09+/-6.6e+06)ns
vring_bench after:
1125610268-1183528965(1.14172e+09+/-8e+06)ns
pktgen before:
787781-796334(793165+/-2.4e+03)pps 365-369(367.5+/-1.2)Mb/sec (365530384-369498976(3.68028e+08+/-1.1e+06)bps) errors: 0
pktgen after:
779988-790404(786391+/-2.5e+03)pps 361-366(364.35+/-1.3)Mb/sec (361914432-366747456(3.64885e+08+/-1.2e+06)bps) errors: 0
Now, if we make force indirect descriptors by turning off any_header_sg
in virtio_net.c:
pktgen before:
713773-721062(718374+/-2.1e+03)pps 331-334(332.95+/-0.92)Mb/sec (331190672-334572768(3.33325e+08+/-9.6e+05)bps) errors: 0
pktgen after:
710542-719195(714898+/-2.4e+03)pps 329-333(331.15+/-1.1)Mb/sec (329691488-333706480(3.31713e+08+/-1.1e+06)bps) errors: 0
Signed-off-by: Rusty Russell <rusty@xxxxxxxxxxxxxxx>
---
drivers/virtio/virtio_ring.c | 125 +++++++++++++++++--------------------------
1 file changed, 50 insertions(+), 75 deletions(-)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 374399c62080..a4ebbffac141 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -99,18 +99,10 @@ struct vring_virtqueue
#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
-/* Set up an indirect table of descriptors and add it to the queue. */
-static inline int vring_add_indirect(struct vring_virtqueue *vq,
- struct scatterlist *sgs[],
- unsigned int total_sg,
- unsigned int out_sgs,
- unsigned int in_sgs,
- gfp_t gfp)
+static struct vring_desc *alloc_indirect(unsigned int total_sg, gfp_t gfp)
{
- struct vring_desc *desc;
- unsigned head;
- struct scatterlist *sg;
- int i, n;
+ struct vring_desc *desc;
+ unsigned int i;
/*
* We require lowmem mappings for the descriptors because
@@ -119,51 +111,13 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq,
*/
gfp &= ~(__GFP_HIGHMEM | __GFP_HIGH);
- desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp);
- if (!desc)
- return -ENOMEM;
-
- /* Transfer entries from the sg lists into the indirect page */
- i = 0;
- for (n = 0; n < out_sgs; n++) {
- for (sg = sgs[n]; sg; sg = sg_next(sg)) {
- desc[i].flags = VRING_DESC_F_NEXT;
- desc[i].addr = sg_phys(sg);
- desc[i].len = sg->length;
- desc[i].next = i+1;
- i++;
- }
- }
- for (; n < (out_sgs + in_sgs); n++) {
- for (sg = sgs[n]; sg; sg = sg_next(sg)) {
- desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
- desc[i].addr = sg_phys(sg);
- desc[i].len = sg->length;
- desc[i].next = i+1;
- i++;
- }
- }
- BUG_ON(i != total_sg);
-
- /* Last one doesn't continue. */
- desc[i-1].flags &= ~VRING_DESC_F_NEXT;
- desc[i-1].next = 0;
-
- /* We're about to use a buffer */
- vq->vq.num_free--;
-
- /* Use a single buffer which doesn't continue */
- head = vq->free_head;
- vq->vring.desc[head].flags = VRING_DESC_F_INDIRECT;
- vq->vring.desc[head].addr = virt_to_phys(desc);
- /* kmemleak gives a false positive, as it's hidden by virt_to_phys */
- kmemleak_ignore(desc);
- vq->vring.desc[head].len = i * sizeof(struct vring_desc);
-
- /* Update free pointer */
- vq->free_head = vq->vring.desc[head].next;
+ desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp);
+ if (!desc)
+ return NULL;
- return head;
+ for (i = 0; i < total_sg; i++)
+ desc[i].next = i+1;
+ return desc;
}
static inline int virtqueue_add(struct virtqueue *_vq,
@@ -176,8 +130,10 @@ static inline int virtqueue_add(struct virtqueue *_vq,
{
struct vring_virtqueue *vq = to_vvq(_vq);
struct scatterlist *sg;
+ struct vring_desc *desc;
unsigned int i, n, avail, uninitialized_var(prev);
int head;
+ bool indirect;
START_USE(vq);
@@ -201,18 +157,36 @@ static inline int virtqueue_add(struct virtqueue *_vq,
}
#endif
+ BUG_ON(total_sg > vq->vring.num);
+ BUG_ON(total_sg == 0);
+
+ head = vq->free_head;
+
/* If the host supports indirect descriptor tables, and we have multiple
* buffers, then go indirect. FIXME: tune this threshold */
- if (vq->indirect && total_sg > 1 && vq->vq.num_free) {
- head = vring_add_indirect(vq, sgs, total_sg,
- out_sgs, in_sgs, gfp);
- if (likely(head >= 0))
- goto add_head;
+ if (vq->indirect && total_sg > 1 && vq->vq.num_free)
+ desc = alloc_indirect(total_sg, gfp);
+ else
+ desc = NULL;
+
+ if (desc) {
+ /* Use a single buffer which doesn't continue */
+ vq->vring.desc[head].flags = VRING_DESC_F_INDIRECT;
+ vq->vring.desc[head].addr = virt_to_phys(desc);
+ /* avoid kmemleak false positive (hidden by virt_to_phys) */
+ kmemleak_ignore(desc);
+ vq->vring.desc[head].len = total_sg * sizeof(struct vring_desc);
+
+ /* Set up rest to use this indirect table. */
+ i = 0;
+ total_sg = 1;
+ indirect = true;
+ } else {
+ desc = vq->vring.desc;
+ i = head;
+ indirect = false;
}
- BUG_ON(total_sg > vq->vring.num);
- BUG_ON(total_sg == 0);
-
if (vq->vq.num_free < total_sg) {
pr_debug("Can't add buf len %i - avail = %i\n",
total_sg, vq->vq.num_free);
@@ -228,32 +202,33 @@ static inline int virtqueue_add(struct virtqueue *_vq,
/* We're about to use some buffers from the free list. */
vq->vq.num_free -= total_sg;
- head = i = vq->free_head;
for (n = 0; n < out_sgs; n++) {
for (sg = sgs[n]; sg; sg = sg_next(sg)) {
- vq->vring.desc[i].flags = VRING_DESC_F_NEXT;
- vq->vring.desc[i].addr = sg_phys(sg);
- vq->vring.desc[i].len = sg->length;
+ desc[i].flags = VRING_DESC_F_NEXT;
+ desc[i].addr = sg_phys(sg);
+ desc[i].len = sg->length;
prev = i;
- i = vq->vring.desc[i].next;
+ i = desc[i].next;
}
}
for (; n < (out_sgs + in_sgs); n++) {
for (sg = sgs[n]; sg; sg = sg_next(sg)) {
- vq->vring.desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
- vq->vring.desc[i].addr = sg_phys(sg);
- vq->vring.desc[i].len = sg->length;
+ desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
+ desc[i].addr = sg_phys(sg);
+ desc[i].len = sg->length;
prev = i;
- i = vq->vring.desc[i].next;
+ i = desc[i].next;
}
}
/* Last one doesn't continue. */
- vq->vring.desc[prev].flags &= ~VRING_DESC_F_NEXT;
+ desc[prev].flags &= ~VRING_DESC_F_NEXT;
/* Update free pointer */
- vq->free_head = i;
+ if (indirect)
+ vq->free_head = vq->vring.desc[head].next;
+ else
+ vq->free_head = i;
-add_head:
/* Set token. */
vq->data[head] = data;
--
1.9.1
_______________________________________________
Virtualization mailing list
Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
