search for: vhost_init_vmap

...->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 long uaddr, + size_t size, int write) +{ + struct page **pages; + int npages = DIV_ROUND_UP(size, PAGE_SIZE); + int npinned; + void *vaddr; + + pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); + if (!pages) + return -ENOMEM; + + npinned = get_...

...return 0; > +err_mmu_notifier: > + vhost_dev_free_iovecs(dev); > err_cgroup: > kthread_stop(worker); > dev->worker = NULL; > @@ -632,6 +709,72 @@ static void vhost_clear_msg(struct vhost_dev *dev) > spin_unlock(&dev->iotlb_lock); > } > > +static int vhost_init_vmap(struct vhost_vmap *map, unsigned long uaddr, > + size_t size, int write) > +{ > + struct page **pages; > + int npages = DIV_ROUND_UP(size, PAGE_SIZE); > + int npinned; > + void *vaddr; > + int err = 0; > + > + pages = kmalloc_array(npages, sizeof(struct page *), GFP_...

...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 long uaddr, > + size_t size, int write) > +{ > + struct page **pages; > + int npages = DIV_ROUND_UP(size, PAGE_SIZE); > + int npinned; > + void *vaddr; > + > + pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); > + if (...

...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 long uaddr, > + size_t size, int write) > +{ > + struct page **pages; > + int npages = DIV_ROUND_UP(size, PAGE_SIZE); > + int npinned; > + void *vaddr; > + > + pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); > + if (...

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

...>mm); + if (err) + goto err_mmu_notifier; + return 0; +err_mmu_notifier: + vhost_dev_free_iovecs(dev); err_cgroup: kthread_stop(worker); dev->worker = NULL; @@ -632,6 +709,72 @@ static void vhost_clear_msg(struct vhost_dev *dev) spin_unlock(&dev->iotlb_lock); } +static int vhost_init_vmap(struct vhost_vmap *map, unsigned long uaddr, + size_t size, int write) +{ + struct page **pages; + int npages = DIV_ROUND_UP(size, PAGE_SIZE); + int npinned; + void *vaddr; + int err = 0; + + pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); + if (!pages) + return -ENOMEM; + +...

...>mm); + if (err) + goto err_mmu_notifier; + return 0; +err_mmu_notifier: + vhost_dev_free_iovecs(dev); err_cgroup: kthread_stop(worker); dev->worker = NULL; @@ -611,6 +676,87 @@ static void vhost_clear_msg(struct vhost_dev *dev) spin_unlock(&dev->iotlb_lock); } +static int vhost_init_vmap(struct vhost_vmap *map, unsigned long uaddr, + size_t size, int write) +{ + struct page **pages; + int npages = DIV_ROUND_UP(size, PAGE_SIZE); + int npinned; + void *vaddr; + int err = 0; + + pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); + if (!pages) + return -ENOMEM; + +...

...>mm); + if (err) + goto err_mmu_notifier; + return 0; +err_mmu_notifier: + vhost_dev_free_iovecs(dev); err_cgroup: kthread_stop(worker); dev->worker = NULL; @@ -633,6 +711,81 @@ static void vhost_clear_msg(struct vhost_dev *dev) spin_unlock(&dev->iotlb_lock); } +static int vhost_init_vmap(struct vhost_dev *dev, + struct vhost_vmap *map, unsigned long uaddr, + size_t size, int write) +{ + struct page **pages; + int npages = DIV_ROUND_UP(size, PAGE_SIZE); + int npinned; + void *vaddr; + int err = -EFAULT; + + err = -ENOMEM; + pages = kmalloc_array(npages, sizeof(struct page...

...return 0; > +err_mmu_notifier: > + vhost_dev_free_iovecs(dev); > err_cgroup: > kthread_stop(worker); > dev->worker = NULL; > @@ -633,6 +711,81 @@ static void vhost_clear_msg(struct vhost_dev *dev) > spin_unlock(&dev->iotlb_lock); > } > > +static int vhost_init_vmap(struct vhost_dev *dev, > + struct vhost_vmap *map, unsigned long uaddr, > + size_t size, int write) > +{ > + struct page **pages; > + int npages = DIV_ROUND_UP(size, PAGE_SIZE); > + int npinned; > + void *vaddr; > + int err = -EFAULT; > + > + err = -ENOMEM; &...

...return 0; > +err_mmu_notifier: > + vhost_dev_free_iovecs(dev); > err_cgroup: > kthread_stop(worker); > dev->worker = NULL; > @@ -633,6 +711,81 @@ static void vhost_clear_msg(struct vhost_dev *dev) > spin_unlock(&dev->iotlb_lock); > } > > +static int vhost_init_vmap(struct vhost_dev *dev, > + struct vhost_vmap *map, unsigned long uaddr, > + size_t size, int write) > +{ > + struct page **pages; > + int npages = DIV_ROUND_UP(size, PAGE_SIZE); > + int npinned; > + void *vaddr; > + int err = -EFAULT; > + > + err = -ENOMEM; &...

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

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

...it(&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 long uaddr, > > > + size_t size, int write) > > > +{ > > > + struct page **pages; > > > + int npages = DIV_ROUND_UP(size, PAGE_SIZE); > > > + int npinned; > > > + void *vaddr; > > > + > > >...

...it(&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 long uaddr, > > > + size_t size, int write) > > > +{ > > > + struct page **pages; > > > + int npages = DIV_ROUND_UP(size, PAGE_SIZE); > > > + int npinned; > > > + void *vaddr; > > > + > > >...

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.

...set(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 long uaddr, > > > > > + size_t size, int write) > > > > > +{ > > > > > + struct page **pages; > > > > > + int npages = DIV_ROUND_UP(size, PAGE_SIZE); > > > > > + int npinned; > > &...

...set(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 long uaddr, > > > > > + size_t size, int write) > > > > > +{ > > > > > + struct page **pages; > > > > > + int npages = DIV_ROUND_UP(size, PAGE_SIZE); > > > > > + int npinned; > > &...