search for: desc_ring

...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; > } > > +stat...

.../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_v...

.../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) @@ -489,6 +492,61 @@ bool vhost_dev_has_owner(struct vhost_dev *dev) } EXPORT_SYMBOL_GPL(vhost_dev_has_owner); +static int vhost_invalidate_vmap(struct vhost_virtqueue *vq, +...

.../vhost/vhost.c @@ -443,6 +443,9 @@ 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) @@ -614,6 +617,102 @@ static void vhost_clear_msg(struct vhost_dev *dev) spin_unlock(&dev->iotlb_lock); } +static int vhost_init_vmap(struct vhost_vmap *map, unsigned...

...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) > @@ -614,6 +617,102 @@ static void vhost_clear_msg(struct vhost_dev *dev) > spin_unlock(&dev->iotlb_lock); > } > > +static int vhost_ini...

...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) > @@ -614,6 +617,102 @@ static void vhost_clear_msg(struct vhost_dev *dev) > spin_unlock(&dev->iotlb_lock); > } > > +static int vhost_ini...

...+ for (i = 0; i < dev->nvqs; i++) { + struct vhost_virtqueue *vq = dev->vqs[i]; + + vhost_invalidate_vmap(vq, &vq->avail_ring, + (unsigned long)vq->avail, + vhost_get_avail_size(vq, vq->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...

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

...i++) { > + struct vhost_virtqueue *vq = dev->vqs[i]; > + > + vhost_invalidate_vmap(vq, &vq->avail_ring, > + (unsigned long)vq->avail, > + vhost_get_avail_size(vq, vq->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), > + st...

...i++) { > + struct vhost_virtqueue *vq = dev->vqs[i]; > + > + vhost_invalidate_vmap(vq, &vq->avail_ring, > + (unsigned long)vq->avail, > + vhost_get_avail_size(vq, vq->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), > + st...

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. Test shows about 24% improvement on TX PPS. It should benefit other cases as well. Changes from V1: - instead of pinning pages, use MMU notifier to invalidate vmaps and remap duing

...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) > > > @@ -614,6 +617,102 @@ static void vhost_clear_msg(struct vhost_dev *dev) > > > spin_unlock(&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) > > > @@ -614,6 +617,102 @@ static void vhost_clear_msg(struct vhost_dev *dev) > > > spin_unlock(&dev->...

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. Test shows about 24% improvement on TX PPS. It should benefit other cases as well. Please review Jason Wang (3): vhost: generalize adding used elem vhost: fine grain userspace memory

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. Test shows about 24% improvement on TX PPS. It should benefit other cases as well. Please review Jason Wang (3): vhost: generalize adding used elem vhost: fine grain userspace memory

...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) > > > > > @@ -614,6 +617,102 @@ static void vhost_clear_msg(struct vhost_dev *dev)...

...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) > > > > > @@ -614,6 +617,102 @@ static void vhost_clear_msg(struct vhost_dev *dev)...

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.