On Wed, Jan 23, 2019 at 05:55:57PM +0800, Jason Wang wrote:
> It was noticed that the copy_user() friends that was used to access
> virtqueue metdata tends to be very expensive for dataplane
> implementation like vhost since it involves lots of software checks,
> speculation barrier, hardware feature toggling (e.g SMAP). The
> extra cost will be more obvious when transferring small packets since
> the time spent on metadata accessing become more significant.
>
> This patch tries to eliminate those overheads by accessing them
> through kernel virtual address by vmap(). To make the pages can be
> migrated, instead of pinning them through GUP, we use MMU notifiers to
> invalidate vmaps and re-establish vmaps during each round of metadata
> prefetching if necessary. For devices that doesn't use metadata
> prefetching, the memory accessors fallback to normal copy_user()
> implementation gracefully. The invalidation was synchronized with
> datapath through vq mutex, and in order to avoid hold vq mutex during
> range checking, MMU notifier was teared down when trying to modify vq
> metadata.
>
> Another thing is kernel lacks efficient solution for tracking dirty
> pages by vmap(), this will lead issues if vhost is using file backed
> memory which needs care of writeback. This patch solves this issue by
> just skipping the vma that is file backed and fallback to normal
> copy_user() friends. This might introduce some overheads for file
> backed users but consider this use case is rare we could do
> optimizations on top.
>
> Note that this was only done when device IOTLB is not enabled. We
> could use similar method to optimize it in the future.
>
> Tests shows at most about 22% improvement on TX PPS when using
> virtio-user + vhost_net + xdp1 + TAP on 2.6GHz Broadwell:
>
> SMAP on | SMAP off
> Before: 5.0Mpps | 6.6Mpps
> After: 6.1Mpps | 7.4Mpps
>
> Signed-off-by: Jason Wang <jasowang@xxxxxxxxxx>
> ---
> drivers/vhost/vhost.c | 288 +++++++++++++++++++++++++++++++++++++++++-
> drivers/vhost/vhost.h | 13 ++
> mm/shmem.c | 1 +
> 3 files changed, 300 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index 37e2cac8e8b0..096ae3298d62 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/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_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 || start > ustart - 1 + size)
> + return 0;
> +
> + if (!blockable)
> + return -EAGAIN;
> +
> + mutex_lock(&vq->mutex);
> + vhost_uninit_vmap(map);
> + mutex_unlock(&vq->mutex);
> +
> + return 0;
> +}
> +
> +static int vhost_invalidate_range_start(struct mmu_notifier *mn,
> + const struct mmu_notifier_range *range)
> +{
> + struct vhost_dev *dev = container_of(mn, struct vhost_dev,
> + mmu_notifier);
> + int i;
> +
> + for (i = 0; i < dev->nvqs; i++) {
> + struct vhost_virtqueue *vq = dev->vqs[i];
> +
> + if (vhost_invalidate_vmap(vq, &vq->avail_ring,
> + (unsigned long)vq->avail,
> + vhost_get_avail_size(vq, vq->num),
> + range->start, range->end,
> + range->blockable))
> + return -EAGAIN;
> + if (vhost_invalidate_vmap(vq, &vq->desc_ring,
> + (unsigned long)vq->desc,
> + vhost_get_desc_size(vq, vq->num),
> + range->start, range->end,
> + range->blockable))
> + return -EAGAIN;
> + if (vhost_invalidate_vmap(vq, &vq->used_ring,
> + (unsigned long)vq->used,
> + vhost_get_used_size(vq, vq->num),
> + range->start, range->end,
> + range->blockable))
> + return -EAGAIN;
> + }
> +
> + return 0;
> +}
> +
> +static const struct mmu_notifier_ops vhost_mmu_notifier_ops = {
> + .invalidate_range_start = vhost_invalidate_range_start,
> +};
> +
> /* Caller should have device mutex */
> long vhost_dev_set_owner(struct vhost_dev *dev)
> {
It seems questionable to merely track .invalidate_range_start.
Don't we care about keeping pages young/accessed?
MMU will think they aren't and will penalize vhost by pushing
them out.
I note that MMU documentation says
* invalidate_range_start() and invalidate_range_end() must be
* paired
and it seems questionable that they are not paired here.
I also wonder about things like write-protecting the pages.
It does not look like a range is invalidated when page
is write-protected, even though I might have missed that.
If not we can be corrupting memory in a variety of ways
e.g. when using KSM, or with COW.
> @@ -541,7 +611,14 @@ long vhost_dev_set_owner(struct vhost_dev *dev)
> if (err)
> goto err_cgroup;
>
> + dev->mmu_notifier.ops = &vhost_mmu_notifier_ops;
> + err = mmu_notifier_register(&dev->mmu_notifier, dev->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 +709,97 @@ static void vhost_clear_msg(struct vhost_dev *dev)
> spin_unlock(&dev->iotlb_lock);
> }
>
> +/* Suppress the vma that needs writeback since we can not track dirty
> + * pages now.
> + */
> +static bool vma_can_vmap(struct vm_area_struct *vma)
> +{
> + return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
> + vma_is_shmem(vma);
> +}
> +
IIUC a second but anonymous memory needs writeback too, just to swap.
I'm not an MM person so I might be off.
> +static int vhost_init_vmap(struct vhost_dev *dev,
> + struct vhost_vmap *map, unsigned long uaddr,
> + size_t size, int write)
> +{
> + struct mm_struct *mm = dev->mm;
> + struct vm_area_struct *vma;
> + struct page **pages;
> + int npages = DIV_ROUND_UP(size, PAGE_SIZE);
> + int npinned;
> + void *vaddr;
> + int err = 0;
> +
> + down_read(&mm->mmap_sem);
> + vma = find_vma(mm, uaddr);
> + if (!vma || !vma_can_vmap(vma) ||
> + vma->vm_end < uaddr - 1 + size) {
> + err = -EINVAL;
> + goto err_vma;
> + }
> +
> + pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
> + if (!pages) {
> + err = -ENOMEM;
> + goto err_alloc;
> + }
> +
> + npinned = get_user_pages_fast(uaddr, npages, write, pages);
> + if (npinned != npages) {
> + err = -EFAULT;
> + goto err_gup;
> + }
> +
> + vaddr = vmap(pages, npages, VM_MAP, PAGE_KERNEL);
> + if (!vaddr) {
> + err = EFAULT;
> + goto err_gup;
> + }
> +
> + map->addr = vaddr + (uaddr & (PAGE_SIZE - 1));
> + map->unmap_addr = vaddr;
> +
> +err_gup:
> + /* Don't pin pages, mmu notifier will notify us about page
> + * migration.
> + */
> + if (npinned > 0)
> + release_pages(pages, npinned);
> +err_alloc:
> + kfree(pages);
> +err_vma:
> + up_read(&mm->mmap_sem);
> + return err;
> +}
> +
> +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->used_ring);
> +}
> +
> +static int vhost_setup_avail_vmap(struct vhost_virtqueue *vq,
> + unsigned long avail)
> +{
> + return vhost_init_vmap(vq->dev, &vq->avail_ring, avail,
> + vhost_get_avail_size(vq, vq->num), false);
> +}
> +
> +static int vhost_setup_desc_vmap(struct vhost_virtqueue *vq,
> + unsigned long desc)
> +{
> + return vhost_init_vmap(vq->dev, &vq->desc_ring, desc,
> + vhost_get_desc_size(vq, vq->num), false);
> +}
> +
> +static int vhost_setup_used_vmap(struct vhost_virtqueue *vq,
> + unsigned long used)
> +{
> + return vhost_init_vmap(vq->dev, &vq->used_ring, used,
> + vhost_get_used_size(vq, vq->num), true);
> +}
> +
> void vhost_dev_cleanup(struct vhost_dev *dev)
> {
> int i;
> @@ -661,8 +829,12 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
> kthread_stop(dev->worker);
> dev->worker = NULL;
> }
> - if (dev->mm)
> + if (dev->mm) {
> + mmu_notifier_unregister(&dev->mmu_notifier, dev->mm);
> mmput(dev->mm);
> + }
> + for (i = 0; i < dev->nvqs; i++)
> + vhost_clean_vmaps(dev->vqs[i]);
> dev->mm = NULL;
> }
> EXPORT_SYMBOL_GPL(vhost_dev_cleanup);
> @@ -891,6 +1063,16 @@ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq,
>
> static inline int vhost_put_avail_event(struct vhost_virtqueue *vq)
> {
> + if (!vq->iotlb) {
> + struct vring_used *used = vq->used_ring.addr;
> +
> + if (likely(used)) {
> + *((__virtio16 *)&used->ring[vq->num]) =
> + cpu_to_vhost16(vq, vq->avail_idx);
> + return 0;
> + }
> + }
> +
> return vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx),
> vhost_avail_event(vq));
> }
> @@ -899,6 +1081,16 @@ static inline int vhost_put_used(struct vhost_virtqueue *vq,
> struct vring_used_elem *head, int idx,
> int count)
> {
> + if (!vq->iotlb) {
> + struct vring_used *used = vq->used_ring.addr;
> +
> + if (likely(used)) {
> + memcpy(used->ring + idx, head,
> + count * sizeof(*head));
> + return 0;
> + }
> + }
> +
> return vhost_copy_to_user(vq, vq->used->ring + idx, head,
> count * sizeof(*head));
> }
> @@ -906,6 +1098,15 @@ static inline int vhost_put_used(struct vhost_virtqueue *vq,
> static inline int vhost_put_used_flags(struct vhost_virtqueue *vq)
>
> {
> + if (!vq->iotlb) {
> + struct vring_used *used = vq->used_ring.addr;
> +
> + if (likely(used)) {
> + used->flags = cpu_to_vhost16(vq, vq->used_flags);
> + return 0;
> + }
> + }
> +
> return vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags),
> &vq->used->flags);
> }
> @@ -913,6 +1114,15 @@ static inline int vhost_put_used_flags(struct vhost_virtqueue *vq)
> static inline int vhost_put_used_idx(struct vhost_virtqueue *vq)
>
> {
> + if (!vq->iotlb) {
> + struct vring_used *used = vq->used_ring.addr;
> +
> + if (likely(used)) {
> + used->idx = cpu_to_vhost16(vq, vq->last_used_idx);
> + return 0;
> + }
> + }
> +
> return vhost_put_user(vq, cpu_to_vhost16(vq, vq->last_used_idx),
> &vq->used->idx);
> }
> @@ -958,12 +1168,30 @@ static void vhost_dev_unlock_vqs(struct vhost_dev *d)
> static inline int vhost_get_avail_idx(struct vhost_virtqueue *vq,
> __virtio16 *idx)
> {
> + if (!vq->iotlb) {
> + struct vring_avail *avail = vq->avail_ring.addr;
> +
> + if (likely(avail)) {
> + *idx = avail->idx;
> + return 0;
> + }
> + }
> +
> return vhost_get_avail(vq, *idx, &vq->avail->idx);
> }
>
> static inline int vhost_get_avail_head(struct vhost_virtqueue *vq,
> __virtio16 *head, int idx)
> {
> + if (!vq->iotlb) {
> + struct vring_avail *avail = vq->avail_ring.addr;
> +
> + if (likely(avail)) {
> + *head = avail->ring[idx & (vq->num - 1)];
> + return 0;
> + }
> + }
> +
> return vhost_get_avail(vq, *head,
> &vq->avail->ring[idx & (vq->num - 1)]);
> }
> @@ -971,24 +1199,60 @@ static inline int vhost_get_avail_head(struct vhost_virtqueue *vq,
> static inline int vhost_get_avail_flags(struct vhost_virtqueue *vq,
> __virtio16 *flags)
> {
> + if (!vq->iotlb) {
> + struct vring_avail *avail = vq->avail_ring.addr;
> +
> + if (likely(avail)) {
> + *flags = avail->flags;
> + return 0;
> + }
> + }
> +
> return vhost_get_avail(vq, *flags, &vq->avail->flags);
> }
>
> static inline int vhost_get_used_event(struct vhost_virtqueue *vq,
> __virtio16 *event)
> {
> + if (!vq->iotlb) {
> + struct vring_avail *avail = vq->avail_ring.addr;
> +
> + if (likely(avail)) {
> + *event = (__virtio16)avail->ring[vq->num];
> + return 0;
> + }
> + }
> +
> return vhost_get_avail(vq, *event, vhost_used_event(vq));
> }
>
> static inline int vhost_get_used_idx(struct vhost_virtqueue *vq,
> __virtio16 *idx)
> {
> + if (!vq->iotlb) {
> + struct vring_used *used = vq->used_ring.addr;
> +
> + if (likely(used)) {
> + *idx = used->idx;
> + return 0;
> + }
> + }
> +
> return vhost_get_used(vq, *idx, &vq->used->idx);
> }
>
> static inline int vhost_get_desc(struct vhost_virtqueue *vq,
> struct vring_desc *desc, int idx)
> {
> + if (!vq->iotlb) {
> + struct vring_desc *d = vq->desc_ring.addr;
> +
> + if (likely(d)) {
> + *desc = *(d + idx);
> + return 0;
> + }
> + }
> +
> return vhost_copy_from_user(vq, desc, vq->desc + idx, sizeof(*desc));
> }
>
> @@ -1329,8 +1593,16 @@ int vq_meta_prefetch(struct vhost_virtqueue *vq)
> {
> unsigned int num = vq->num;
>
> - if (!vq->iotlb)
> + if (!vq->iotlb) {
> + if (unlikely(!vq->avail_ring.addr))
> + vhost_setup_avail_vmap(vq, (unsigned long)vq->avail);
> + if (unlikely(!vq->desc_ring.addr))
> + vhost_setup_desc_vmap(vq, (unsigned long)vq->desc);
> + if (unlikely(!vq->used_ring.addr))
> + vhost_setup_used_vmap(vq, (unsigned long)vq->used);
> +
> return 1;
> + }
>
> return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc,
> vhost_get_desc_size(vq, num), VHOST_ADDR_DESC) &&
> @@ -1482,6 +1754,13 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
>
> mutex_lock(&vq->mutex);
>
> + /* Unregister MMU notifer to allow invalidation callback
> + * can access vq->avail, vq->desc , vq->used and vq->num
> + * without holding vq->mutex.
> + */
> + if (d->mm)
> + mmu_notifier_unregister(&d->mmu_notifier, d->mm);
> +
> switch (ioctl) {
> case VHOST_SET_VRING_NUM:
> /* Resizing ring with an active backend?
> @@ -1498,6 +1777,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
> r = -EINVAL;
> break;
> }
> + vhost_clean_vmaps(vq);
> vq->num = s.num;
> break;
> case VHOST_SET_VRING_BASE:
> @@ -1575,6 +1855,8 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
> }
> }
>
> + vhost_clean_vmaps(vq);
> +
> vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG));
> vq->desc = (void __user *)(unsigned long)a.desc_user_addr;
> vq->avail = (void __user *)(unsigned long)a.avail_user_addr;
> @@ -1655,6 +1937,8 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
> if (pollstart && vq->handle_kick)
> r = vhost_poll_start(&vq->poll, vq->kick);
>
> + if (d->mm)
> + mmu_notifier_register(&d->mmu_notifier, d->mm);
> mutex_unlock(&vq->mutex);
>
> if (pollstop && vq->handle_kick)
> diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
> index 4e21011b6628..c04bc327db9f 100644
> --- a/drivers/vhost/vhost.h
> +++ b/drivers/vhost/vhost.h
> @@ -12,6 +12,8 @@
> #include <linux/virtio_config.h>
> #include <linux/virtio_ring.h>
> #include <linux/atomic.h>
> +#include <linux/pagemap.h>
> +#include <linux/mmu_notifier.h>
>
> struct vhost_work;
> typedef void (*vhost_work_fn_t)(struct vhost_work *work);
> @@ -80,6 +82,11 @@ enum vhost_uaddr_type {
> VHOST_NUM_ADDRS = 3,
> };
>
> +struct vhost_vmap {
> + void *addr;
> + void *unmap_addr;
> +};
> +
> /* The virtqueue structure describes a queue attached to a device. */
> struct vhost_virtqueue {
> struct vhost_dev *dev;
> @@ -90,6 +97,11 @@ struct vhost_virtqueue {
> struct vring_desc __user *desc;
> struct vring_avail __user *avail;
> struct vring_used __user *used;
> +
> + struct vhost_vmap avail_ring;
> + struct vhost_vmap desc_ring;
> + struct vhost_vmap used_ring;
> +
> const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS];
> struct file *kick;
> struct eventfd_ctx *call_ctx;
> @@ -158,6 +170,7 @@ struct vhost_msg_node {
>
> struct vhost_dev {
> struct mm_struct *mm;
> + struct mmu_notifier mmu_notifier;
> struct mutex mutex;
> struct vhost_virtqueue **vqs;
> int nvqs;
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 6ece1e2fe76e..745e7c7f7a6c 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -237,6 +237,7 @@ bool vma_is_shmem(struct vm_area_struct *vma)
> {
> return vma->vm_ops == &shmem_vm_ops;
> }
> +EXPORT_SYMBOL_GPL(vma_is_shmem);
>
> static LIST_HEAD(shmem_swaplist);
> static DEFINE_MUTEX(shmem_swaplist_mutex);
> --
> 2.17.1
