search for: vhost_get_used_size

...ost_vq_free_iovecs(dev->vqs[i]); } +static size_t vhost_get_avail_size(struct vhost_virtqueue *vq, int num) +{ + size_t event = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; + + return sizeof(*vq->avail) + + sizeof(*vq->avail->ring) * num + event; +} + +static size_t vhost_get_used_size(struct vhost_virtqueue *vq, int num) +{ + size_t event = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; + + return sizeof(*vq->used) + + sizeof(*vq->used->ring) * num + event; +} + +static size_t vhost_get_desc_size(struct vhost_virtqueue *vq, int num) +{ + return sizeof(*v...

...virtqueue *vq, int num) >> +{ >> + size_t event = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; >> + >> + return sizeof(*vq->avail) + >> + sizeof(*vq->avail->ring) * num + event; >> +} >> + >> +static size_t vhost_get_used_size(struct vhost_virtqueue *vq, int num) >> +{ >> + size_t event = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; >> + >> + return sizeof(*vq->used) + >> + sizeof(*vq->used->ring) * num + event; >> +} >> + >> +st...

...eue *vq, int num) Nit: Any reason not to make `num` unsigned or size_t? > +{ > + size_t event = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; > + > + return sizeof(*vq->avail) + > + sizeof(*vq->avail->ring) * num + event; > +} > + > +static size_t vhost_get_used_size(struct vhost_virtqueue *vq, int num) > +{ > + size_t event = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; > + > + return sizeof(*vq->used) + > + sizeof(*vq->used->ring) * num + event; > +} > + > +static size_t vhost_get_desc_size(struct vhost_virtq...

...eue *vq, int num) Nit: Any reason not to make `num` unsigned or size_t? > +{ > + size_t event = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; > + > + return sizeof(*vq->avail) + > + sizeof(*vq->avail->ring) * num + event; > +} > + > +static size_t vhost_get_used_size(struct vhost_virtqueue *vq, int num) > +{ > + size_t event = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; > + > + return sizeof(*vq->used) + > + sizeof(*vq->used->ring) * num + event; > +} > + > +static size_t vhost_get_desc_size(struct vhost_virtq...

...et_avail_size(vq, vq->num), + &addr)) + return -EINVAL; + + virtio_mdev_writel(mdev, VIRTIO_MDEV_QUEUE_AVAIL_LOW, addr); + virtio_mdev_writel(mdev, VIRTIO_MDEV_QUEUE_AVAIL_HIGH, + (addr >> 32)); + + if (!vhost_translate_ring_addr(vq, (u64)vq->used, + vhost_get_used_size(vq, vq->num), + &addr)) + return -EINVAL; + + virtio_mdev_writel(mdev, VIRTIO_MDEV_QUEUE_USED_LOW, addr); + virtio_mdev_writel(mdev, VIRTIO_MDEV_QUEUE_USED_HIGH, + (addr >> 32)); + + // XXX: we need to support set_vring_base + + virtio_mdev_writel(mdev, VIRTIO_MD...

...&addr)) > + return -EINVAL; > + > + virtio_mdev_writel(mdev, VIRTIO_MDEV_QUEUE_AVAIL_LOW, addr); > + virtio_mdev_writel(mdev, VIRTIO_MDEV_QUEUE_AVAIL_HIGH, > + (addr >> 32)); > + > + if (!vhost_translate_ring_addr(vq, (u64)vq->used, > + vhost_get_used_size(vq, vq->num), > + &addr)) > + return -EINVAL; > + > + virtio_mdev_writel(mdev, VIRTIO_MDEV_QUEUE_USED_LOW, addr); > + virtio_mdev_writel(mdev, VIRTIO_MDEV_QUEUE_USED_HIGH, > + (addr >> 32)); > + > + // XXX: we need to support set_vring_base...

This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. This is done through setup kernel address through vmap() and resigter MMU notifier for invalidation. Test shows about 24% improvement on TX PPS. TCP_STREAM doesn't see obvious improvement.

This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. This is done through setup kernel address through vmap() and resigter MMU notifier for invalidation. Test shows about 24% improvement on TX PPS. TCP_STREAM doesn't see obvious improvement.

This RFC is to demonstrate below ideas, a) Build vhost-mdev on top of the same abstraction defined in the virtio-mdev series [1]; b) Introduce /dev/vhost-mdev to do vhost ioctls and support setting mdev device as backend; Now the userspace API looks like this: - Userspace generates a compatible mdev device; - Userspace opens this mdev device with VFIO API (including doing IOMMU

This RFC is to demonstrate below ideas, a) Build vhost-mdev on top of the same abstraction defined in the virtio-mdev series [1]; b) Introduce /dev/vhost-mdev to do vhost ioctls and support setting mdev device as backend; Now the userspace API looks like this: - Userspace generates a compatible mdev device; - Userspace opens this mdev device with VFIO API (including doing IOMMU

This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. Test shows about 24% improvement on TX PPS. It should benefit other cases as well. Changes from V2: - fix buggy range overlapping check - tear down MMU notifier during vhost ioctl to make sure

This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. Test shows about 24% improvement on TX PPS. It should benefit other cases as well. Changes from V2: - fix buggy range overlapping check - tear down MMU notifier during vhost ioctl to make sure

...vmap(vq, &vq->desc_ring, > + (unsigned long)vq->desc, > + vhost_get_desc_size(vq, vq->num), > + start, end, blockable)) > + return -EAGAIN; > + if (vhost_invalidate_vmap(vq, &vq->used_ring, > + (unsigned long)vq->used, > + vhost_get_used_size(vq, vq->num), > + start, end, blockable)) > + return -EAGAIN; > + } > + > + return 0; > +} > + > +static const struct mmu_notifier_ops vhost_mmu_notifier_ops = { > + .invalidate_range_start = vhost_mmu_notifier_invalidate_range_start, > +}; > + > /* C...

This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. This is done through setup kernel address through direct mapping and co-opreate VM management with MMU notifiers. Test shows about 23% improvement on TX PPS. TCP_STREAM doesn't see obvious

...n -EAGAIN; + if (vhost_invalidate_vmap(vq, &vq->desc_ring, + (unsigned long)vq->desc, + vhost_get_desc_size(vq, vq->num), + start, end, blockable)) + return -EAGAIN; + if (vhost_invalidate_vmap(vq, &vq->used_ring, + (unsigned long)vq->used, + vhost_get_used_size(vq, vq->num), + start, end, blockable)) + return -EAGAIN; + } + + return 0; +} + +static const struct mmu_notifier_ops vhost_mmu_notifier_ops = { + .invalidate_range_start = vhost_mmu_notifier_invalidate_range_start, +}; + /* Caller should have device mutex */ long vhost_dev_set_owner(...

Hi: This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling like SMAP. This is done through setup kernel address through direct mapping and co-opreate VM management with MMU notifiers. Test shows about 23% improvement on TX PPS. TCP_STREAM

Hi: This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling like SMAP. This is done through setup kernel address through direct mapping and co-opreate VM management with MMU notifiers. Test shows about 23% improvement on TX PPS. TCP_STREAM

...->num), + start, end); + vhost_invalidate_vmap(vq, &vq->desc_ring, + (unsigned long)vq->desc, + vhost_get_desc_size(vq, vq->num), + start, end); + vhost_invalidate_vmap(vq, &vq->used_ring, + (unsigned long)vq->used, + vhost_get_used_size(vq, vq->num), + start, end); + } +} + + +static void vhost_invalidate_range(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + struct vhost_dev *dev = container_of(mn, struct vhost_dev, + mmu_notifier); + + vhost_invalida...

...> + vhost_invalidate_vmap(vq, &vq->desc_ring, > + (unsigned long)vq->desc, > + vhost_get_desc_size(vq, vq->num), > + start, end); > + vhost_invalidate_vmap(vq, &vq->used_ring, > + (unsigned long)vq->used, > + vhost_get_used_size(vq, vq->num), > + start, end); > + } > +} > + > + > +static void vhost_invalidate_range(struct mmu_notifier *mn, > + struct mm_struct *mm, > + unsigned long start, unsigned long end) > +{ > + struct vhost_dev *dev = container_of(mn, struct vhost...

...> + vhost_invalidate_vmap(vq, &vq->desc_ring, > + (unsigned long)vq->desc, > + vhost_get_desc_size(vq, vq->num), > + start, end); > + vhost_invalidate_vmap(vq, &vq->used_ring, > + (unsigned long)vq->used, > + vhost_get_used_size(vq, vq->num), > + start, end); > + } > +} > + > + > +static void vhost_invalidate_range(struct mmu_notifier *mn, > + struct mm_struct *mm, > + unsigned long start, unsigned long end) > +{ > + struct vhost_dev *dev = container_of(mn, struct vhost...