search for: vhost_get_desc_size

...*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(*vq->desc) * num; +} + void vhost_dev_init(struct vhost_dev *dev, struct vhost_virtqueue **vqs, int nvqs, int iov_limit) { @@ -1253,13 +1274,9 @@ static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, struct vr...

...t_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(*vq->desc) * num; >> +} >> + >> void vhost_dev_init(struct vhost_dev *dev, >> struct vhost_virtqueue **vqs, int nvqs, int iov_limit) >> { >> @@ -1253,13 +1...

...gt; +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(*vq->desc) * num; > +} > + > void vhost_dev_init(struct vhost_dev *dev, > struct vhost_virtqueue **vqs, int nvqs, int iov_limit) > { > @@ -1253,13 +1274,9 @@ static bool vq_access_ok(struct vhost_virtqueue...

...gt; +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(*vq->desc) * num; > +} > + > void vhost_dev_init(struct vhost_dev *dev, > struct vhost_virtqueue **vqs, int nvqs, int iov_limit) > { > @@ -1253,13 +1274,9 @@ static bool vq_access_ok(struct vhost_virtqueue...

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.

...s; queue_id++) { > + vq = &m->vqs[queue_id]; > + > + if (!vq->desc || !vq->avail || !vq->used) > + break; > + > + virtio_mdev_writel(mdev, VIRTIO_MDEV_QUEUE_NUM, vq->num); > + > + if (!vhost_translate_ring_addr(vq, (u64)vq->desc, > + vhost_get_desc_size(vq, vq->num), > + &addr)) > + return -EINVAL; Interesting, any reason for doing such kinds of translation to HVA? I believe the add should already an IOVA that has been map by VFIO. > + > + virtio_mdev_writel(mdev, VIRTIO_MDEV_QUEUE_DESC_LOW, addr); > + vir...

...q->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; > +}...

...+ for (queue_id = 0; queue_id < m->nvqs; queue_id++) { + vq = &m->vqs[queue_id]; + + if (!vq->desc || !vq->avail || !vq->used) + break; + + virtio_mdev_writel(mdev, VIRTIO_MDEV_QUEUE_NUM, vq->num); + + if (!vhost_translate_ring_addr(vq, (u64)vq->desc, + vhost_get_desc_size(vq, vq->num), + &addr)) + return -EINVAL; + + virtio_mdev_writel(mdev, VIRTIO_MDEV_QUEUE_DESC_LOW, addr); + virtio_mdev_writel(mdev, VIRTIO_MDEV_QUEUE_DESC_HIGH, + (addr >> 32)); + + if (!vhost_translate_ring_addr(vq, (u64)vq->avail, + vhost_get_avai...

...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_virtq...

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

...vhost_setup_uaddr(struct vho static void vhost_setup_vq_uaddr(struct vhost_virtqueue *vq) { spin_lock(&vq->mmu_lock); - + /* + * deadlock if managing to take mmu_lock again while + * setting up uaddr + */ vhost_setup_uaddr(vq, VHOST_ADDR_DESC, (unsigned long)vq->desc, vhost_get_desc_size(vq, vq->num), --

...e_vq(net, vq); out: vhost_net_signal_used(nvq); + vq_meta_prefetch_done(vq); mutex_unlock(&vq->mutex); } diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 1015464..36ccf7c 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -434,6 +434,74 @@ 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); + kfree(map->pages); + map->pages = NULL; + map->npages = 0; + } + + map->addr = NULL; + map-&...

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

...nvq); > + vq_meta_prefetch_done(vq); > mutex_unlock(&vq->mutex); > } > > diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c > index 1015464..36ccf7c 100644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -434,6 +434,74 @@ 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); > + kfree(map->pages); > + map->pages = NULL; > + map-&g...

...nvq); > + vq_meta_prefetch_done(vq); > mutex_unlock(&vq->mutex); > } > > diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c > index 1015464..36ccf7c 100644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -434,6 +434,74 @@ 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); > + kfree(map->pages); > + map->pages = NULL; > + map-&g...

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

...vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, - struct vring_desc __user *desc, - struct vring_avail __user *avail, - struct vring_used __user *used) + vring_desc_t __user *desc, + vring_avail_t __user *avail, + vring_used_t __user *used) { return access_ok(desc, vhost_get_desc_size(vq, num)) && @@ -2301,7 +2301,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads, unsigned count) { - struct vring_used_elem __user *used; + vring_used_elem_t __user *used; u16 old, new; int start; diff --git a/drivers/vhost/v...