It was noticed that the copy_user() friends that was used to access
virtqueue metdata tends to be very expensive for dataplane
implementation like vhost since it involves lots of software checks,
speculation barrier, hardware feature toggling (e.g SMAP). The
extra cost will be more obvious when transferring small packets since
the time spent on metadata accessing become more significant.
This patch tries to eliminate those overheads by accessing them
through kernel virtual address by vmap(). To make the pages can be
migrated, instead of pinning them through GUP, we use MMU notifiers to
invalidate vmaps and re-establish vmaps during each round of metadata
prefetching if necessary. For devices that doesn't use metadata
prefetching, the memory accessors fallback to normal copy_user()
implementation gracefully. The invalidation was synchronized with
datapath through vq mutex, and in order to avoid hold vq mutex during
range checking, MMU notifier was teared down when trying to modify vq
metadata.
Another thing is kernel lacks efficient solution for tracking dirty
pages by vmap(), this will lead issues if vhost is using file backed
memory which needs care of writeback. This patch solves this issue by
just skipping the vma that is file backed and fallback to normal
copy_user() friends. This might introduce some overheads for file
backed users but consider this use case is rare we could do
optimizations on top.
Note that this was only done when device IOTLB is not enabled. We
could use similar method to optimize it in the future.
Tests shows at most about 22% improvement on TX PPS when using
virtio-user + vhost_net + xdp1 + TAP on 2.6GHz Broadwell:
SMAP on | SMAP off
Before: 5.0Mpps | 6.6Mpps
After: 6.1Mpps | 7.4Mpps
Signed-off-by: Jason Wang <jasowang@xxxxxxxxxx>
---
drivers/vhost/vhost.c | 288 +++++++++++++++++++++++++++++++++++++++++-
drivers/vhost/vhost.h | 13 ++
mm/shmem.c | 1 +
3 files changed, 300 insertions(+), 2 deletions(-)
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 37e2cac8e8b0..096ae3298d62 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -440,6 +440,9 @@ void vhost_dev_init(struct vhost_dev *dev,
vq->indirect = NULL;
vq->heads = NULL;
vq->dev = dev;
+ memset(&vq->avail_ring, 0, sizeof(vq->avail_ring));
+ memset(&vq->used_ring, 0, sizeof(vq->used_ring));
+ memset(&vq->desc_ring, 0, sizeof(vq->desc_ring));
mutex_init(&vq->mutex);
vhost_vq_reset(dev, vq);
if (vq->handle_kick)
@@ -510,6 +513,73 @@ static size_t vhost_get_desc_size(struct vhost_virtqueue *vq, int num)
return sizeof(*vq->desc) * num;
}
+static void vhost_uninit_vmap(struct vhost_vmap *map)
+{
+ if (map->addr)
+ vunmap(map->unmap_addr);
+
+ map->addr = NULL;
+ map->unmap_addr = NULL;
+}
+
+static int vhost_invalidate_vmap(struct vhost_virtqueue *vq,
+ struct vhost_vmap *map,
+ unsigned long ustart,
+ size_t size,
+ unsigned long start,
+ unsigned long end,
+ bool blockable)
+{
+ if (end < ustart || start > ustart - 1 + size)
+ return 0;
+
+ if (!blockable)
+ return -EAGAIN;
+
+ mutex_lock(&vq->mutex);
+ vhost_uninit_vmap(map);
+ mutex_unlock(&vq->mutex);
+
+ return 0;
+}
+
+static int vhost_invalidate_range_start(struct mmu_notifier *mn,
+ const struct mmu_notifier_range *range)
+{
+ struct vhost_dev *dev = container_of(mn, struct vhost_dev,
+ mmu_notifier);
+ int i;
+
+ for (i = 0; i < dev->nvqs; i++) {
+ struct vhost_virtqueue *vq = dev->vqs[i];
+
+ if (vhost_invalidate_vmap(vq, &vq->avail_ring,
+ (unsigned long)vq->avail,
+ vhost_get_avail_size(vq, vq->num),
+ range->start, range->end,
+ range->blockable))
+ return -EAGAIN;
+ if (vhost_invalidate_vmap(vq, &vq->desc_ring,
+ (unsigned long)vq->desc,
+ vhost_get_desc_size(vq, vq->num),
+ range->start, range->end,
+ range->blockable))
+ return -EAGAIN;
+ if (vhost_invalidate_vmap(vq, &vq->used_ring,
+ (unsigned long)vq->used,
+ vhost_get_used_size(vq, vq->num),
+ range->start, range->end,
+ range->blockable))
+ return -EAGAIN;
+ }
+
+ return 0;
+}
+
+static const struct mmu_notifier_ops vhost_mmu_notifier_ops = {
+ .invalidate_range_start = vhost_invalidate_range_start,
+};
+
/* Caller should have device mutex */
long vhost_dev_set_owner(struct vhost_dev *dev)
{
