search for: unmap_addr

...uaddr, > + unsigned long start, > + unsigned long end, > + bool blockable) > +{ > + if (start < uaddr && end >= uaddr) { > + if (!blockable) > + return -EAGAIN; > + mutex_lock(&vq->mutex); > + if (map->addr) > + vunmap(map->unmap_addr); > + map->addr = NULL; > + map->unmap_addr = NULL; > + mutex_unlock(&vq->mutex); > + } > + > + return 0; > +} What are the rules for these invalidate operations? Can there be partial overlaps? If so, wouldn't you need some way of keeping track of the par...

...+ struct vhost_vmap *map, + unsigned long uaddr, + unsigned long start, + unsigned long end, + bool blockable) +{ + if (start < uaddr && end >= uaddr) { + if (!blockable) + return -EAGAIN; + mutex_lock(&vq->mutex); + if (map->addr) + vunmap(map->unmap_addr); + map->addr = NULL; + map->unmap_addr = NULL; + mutex_unlock(&vq->mutex); + } + + return 0; +} + +static int vhost_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, + unsigned long end, +...

...t; 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 lo...

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->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...

...cf7c 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->unmap_addr = NULL; +} + +static void vhost_invalidate_vmap(struct vhost_virtqueue *vq, + struct vhost_vmap *map, + unsigned long ustart, + size_t size, + unsigned lo...

...+++ 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->unmap_addr = NULL; > +} > + > +static void vhost_invalidate_vmap(struct vhost_virtqueue *vq, > + struct vhost_vmap *map, > +...

...+++ 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->unmap_addr = NULL; > +} > + > +static void vhost_invalidate_vmap(struct vhost_virtqueue *vq, > + struct vhost_vmap *map, > +...

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

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.