search for: vhost_uninit_vmap

...s, npages, VM_MAP, PAGE_KERNEL); + if (!vaddr) + goto err; + + map->pages = pages; + map->addr = vaddr + (uaddr & (PAGE_SIZE - 1)); + map->npages = npages; + + return 0; + +err: + if (npinned > 0) + release_pages(pages, npinned); + kfree(pages); + return -EFAULT; +} + +static void vhost_uninit_vmap(struct vhost_vmap *map) +{ + if (!map->addr) + return; + + vunmap(map->addr); + release_pages(map->pages, map->npages); + kfree(map->pages); + + map->addr = NULL; + map->pages = NULL; + map->npages = 0; +} + +static void vhost_clean_vmaps(struct vhost_virtqueue *vq) +{ + vh...

...eof(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...

...+ 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 sta...

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

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

...ap->pages = pages; > + map->addr = vaddr + (uaddr & (PAGE_SIZE - 1)); > + map->npages = npages; > + > + return 0; > + > +err: > + if (npinned > 0) > + release_pages(pages, npinned); > + kfree(pages); > + return -EFAULT; > +} > + > +static void vhost_uninit_vmap(struct vhost_vmap *map) > +{ > + if (!map->addr) > + return; > + > + vunmap(map->addr); > + release_pages(map->pages, map->npages); > + kfree(map->pages); > + > + map->addr = NULL; > + map->pages = NULL; > + map->npages = 0; > +} > + &...

...ap->pages = pages; > + map->addr = vaddr + (uaddr & (PAGE_SIZE - 1)); > + map->npages = npages; > + > + return 0; > + > +err: > + if (npinned > 0) > + release_pages(pages, npinned); > + kfree(pages); > + return -EFAULT; > +} > + > +static void vhost_uninit_vmap(struct vhost_vmap *map) > +{ > + if (!map->addr) > + return; > + > + vunmap(map->addr); > + release_pages(map->pages, map->npages); > + kfree(map->pages); > + > + map->addr = NULL; > + map->pages = NULL; > + map->npages = 0; > +} > + &...

....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->unmap_addr = NULL; > +} > + > +static void 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->unmap_addr = NULL; > +} > + > +static void vhost...

...oto err; + } + + map->addr = vaddr + (uaddr & (PAGE_SIZE - 1)); + map->unmap_addr = vaddr; + +err: + /* Don't pin pages, mmu notifier will notify us about page + * migration. + */ + if (npinned > 0) + release_pages(pages, npinned); + kfree(pages); + return err; +} + +static void vhost_uninit_vmap(struct vhost_vmap *map) +{ + if (map->addr) { + vunmap(map->unmap_addr); + map->addr = NULL; + } +} + +static void vhost_clean_vmaps(struct vhost_virtqueue *vq) +{ + vhost_uninit_vmap(&vq->avail_ring); + vhost_uninit_vmap(&vq->desc_ring); + vhost_uninit_vmap(&vq->use...

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.

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