KVM Archive on lore.kernel.org
 help / color / Atom feed
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
To: Kirti Wankhede <kwankhede@nvidia.com>
Cc: alex.williamson@redhat.com, cjia@nvidia.com,
	kevin.tian@intel.com, ziye.yang@intel.com,
	changpeng.liu@intel.com, yi.l.liu@intel.com, mlevitsk@redhat.com,
	eskultet@redhat.com, cohuck@redhat.com,
	jonathan.davies@nutanix.com, eauger@redhat.com, aik@ozlabs.ru,
	pasic@linux.ibm.com, felipe@nutanix.com,
	Zhengxiao.zx@alibaba-inc.com, shuangtai.tst@alibaba-inc.com,
	Ken.Xue@amd.com, zhi.a.wang@intel.com, yan.y.zhao@intel.com,
	qemu-devel@nongnu.org, kvm@vger.kernel.org
Subject: Re: [PATCH v16 Kernel 4/7] vfio iommu: Implementation of ioctl for dirty pages tracking.
Date: Fri, 27 Mar 2020 11:57:45 +0000
Message-ID: <20200327115745.GF2786@work-vm> (raw)
In-Reply-To: <1585084732-18473-1-git-send-email-kwankhede@nvidia.com>

* Kirti Wankhede (kwankhede@nvidia.com) wrote:
> VFIO_IOMMU_DIRTY_PAGES ioctl performs three operations:
> - Start dirty pages tracking while migration is active
> - Stop dirty pages tracking.
> - Get dirty pages bitmap. Its user space application's responsibility to
>   copy content of dirty pages from source to destination during migration.
> 
> To prevent DoS attack, memory for bitmap is allocated per vfio_dma
> structure. Bitmap size is calculated considering smallest supported page
> size. Bitmap is allocated for all vfio_dmas when dirty logging is enabled
> 
> Bitmap is populated for already pinned pages when bitmap is allocated for
> a vfio_dma with the smallest supported page size. Update bitmap from
> pinning functions when tracking is enabled. When user application queries
> bitmap, check if requested page size is same as page size used to
> populated bitmap. If it is equal, copy bitmap, but if not equal, return
> error.
> 
> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
> Reviewed-by: Neo Jia <cjia@nvidia.com>
> ---
>  drivers/vfio/vfio_iommu_type1.c | 266 +++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 260 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> index 70aeab921d0f..874a1a7ae925 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -71,6 +71,7 @@ struct vfio_iommu {
>  	unsigned int		dma_avail;
>  	bool			v2;
>  	bool			nesting;
> +	bool			dirty_page_tracking;
>  };
>  
>  struct vfio_domain {
> @@ -91,6 +92,7 @@ struct vfio_dma {
>  	bool			lock_cap;	/* capable(CAP_IPC_LOCK) */
>  	struct task_struct	*task;
>  	struct rb_root		pfn_list;	/* Ex-user pinned pfn list */
> +	unsigned long		*bitmap;
>  };
>  
>  struct vfio_group {
> @@ -125,7 +127,21 @@ struct vfio_regions {
>  #define IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu)	\
>  					(!list_empty(&iommu->domain_list))
>  
> +#define DIRTY_BITMAP_BYTES(n)	(ALIGN(n, BITS_PER_TYPE(u64)) / BITS_PER_BYTE)
> +
> +/*
> + * Input argument of number of bits to bitmap_set() is unsigned integer, which
> + * further casts to signed integer for unaligned multi-bit operation,
> + * __bitmap_set().
> + * Then maximum bitmap size supported is 2^31 bits divided by 2^3 bits/byte,
> + * that is 2^28 (256 MB) which maps to 2^31 * 2^12 = 2^43 (8TB) on 4K page
> + * system.
> + */

Can you explain to me what that size is the limit of?  People are
already running 12TB VMs.

Dave

> +#define DIRTY_BITMAP_PAGES_MAX	(uint64_t)(INT_MAX - 1)
> +#define DIRTY_BITMAP_SIZE_MAX	 DIRTY_BITMAP_BYTES(DIRTY_BITMAP_PAGES_MAX)
> +
>  static int put_pfn(unsigned long pfn, int prot);
> +static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu);
>  
>  /*
>   * This code handles mapping and unmapping of user data buffers
> @@ -175,6 +191,77 @@ static void vfio_unlink_dma(struct vfio_iommu *iommu, struct vfio_dma *old)
>  	rb_erase(&old->node, &iommu->dma_list);
>  }
>  
> +
> +static int vfio_dma_bitmap_alloc(struct vfio_dma *dma, uint64_t pgsize)
> +{
> +	uint64_t npages = dma->size / pgsize;
> +
> +	if (npages > DIRTY_BITMAP_PAGES_MAX)
> +		return -EINVAL;
> +
> +	dma->bitmap = kvzalloc(DIRTY_BITMAP_BYTES(npages), GFP_KERNEL);
> +	if (!dma->bitmap)
> +		return -ENOMEM;
> +
> +	return 0;
> +}
> +
> +static void vfio_dma_bitmap_free(struct vfio_dma *dma)
> +{
> +	kfree(dma->bitmap);
> +	dma->bitmap = NULL;
> +}
> +
> +static void vfio_dma_populate_bitmap(struct vfio_dma *dma, uint64_t pgsize)
> +{
> +	struct rb_node *p;
> +
> +	if (RB_EMPTY_ROOT(&dma->pfn_list))
> +		return;
> +
> +	for (p = rb_first(&dma->pfn_list); p; p = rb_next(p)) {
> +		struct vfio_pfn *vpfn = rb_entry(p, struct vfio_pfn, node);
> +
> +		bitmap_set(dma->bitmap, (vpfn->iova - dma->iova) / pgsize, 1);
> +	}
> +}
> +
> +static int vfio_dma_bitmap_alloc_all(struct vfio_iommu *iommu, uint64_t pgsize)
> +{
> +	struct rb_node *n = rb_first(&iommu->dma_list);
> +
> +	for (; n; n = rb_next(n)) {
> +		struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node);
> +		int ret;
> +
> +		ret = vfio_dma_bitmap_alloc(dma, pgsize);
> +		if (ret) {
> +			struct rb_node *p = rb_prev(n);
> +
> +			for (; p; p = rb_prev(p)) {
> +				struct vfio_dma *dma = rb_entry(n,
> +							struct vfio_dma, node);
> +
> +				vfio_dma_bitmap_free(dma);
> +			}
> +			return ret;
> +		}
> +		vfio_dma_populate_bitmap(dma, pgsize);
> +	}
> +	return 0;
> +}
> +
> +static void vfio_dma_bitmap_free_all(struct vfio_iommu *iommu)
> +{
> +	struct rb_node *n = rb_first(&iommu->dma_list);
> +
> +	for (; n; n = rb_next(n)) {
> +		struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node);
> +
> +		vfio_dma_bitmap_free(dma);
> +	}
> +}
> +
>  /*
>   * Helper Functions for host iova-pfn list
>   */
> @@ -567,6 +654,18 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
>  			vfio_unpin_page_external(dma, iova, do_accounting);
>  			goto pin_unwind;
>  		}
> +
> +		if (iommu->dirty_page_tracking) {
> +			unsigned long pgshift =
> +					 __ffs(vfio_pgsize_bitmap(iommu));
> +
> +			/*
> +			 * Bitmap populated with the smallest supported page
> +			 * size
> +			 */
> +			bitmap_set(dma->bitmap,
> +				   (vpfn->iova - dma->iova) >> pgshift, 1);
> +		}
>  	}
>  
>  	ret = i;
> @@ -801,6 +900,7 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
>  	vfio_unmap_unpin(iommu, dma, true);
>  	vfio_unlink_dma(iommu, dma);
>  	put_task_struct(dma->task);
> +	vfio_dma_bitmap_free(dma);
>  	kfree(dma);
>  	iommu->dma_avail++;
>  }
> @@ -831,6 +931,57 @@ static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
>  	return bitmap;
>  }
>  
> +static int vfio_iova_dirty_bitmap(struct vfio_iommu *iommu, dma_addr_t iova,
> +				  size_t size, uint64_t pgsize,
> +				  u64 __user *bitmap)
> +{
> +	struct vfio_dma *dma;
> +	unsigned long pgshift = __ffs(pgsize);
> +	unsigned int npages, bitmap_size;
> +
> +	dma = vfio_find_dma(iommu, iova, 1);
> +
> +	if (!dma)
> +		return -EINVAL;
> +
> +	if (dma->iova != iova || dma->size != size)
> +		return -EINVAL;
> +
> +	npages = dma->size >> pgshift;
> +	bitmap_size = DIRTY_BITMAP_BYTES(npages);
> +
> +	/* mark all pages dirty if all pages are pinned and mapped. */
> +	if (dma->iommu_mapped)
> +		bitmap_set(dma->bitmap, 0, npages);
> +
> +	if (copy_to_user((void __user *)bitmap, dma->bitmap, bitmap_size))
> +		return -EFAULT;
> +
> +	/*
> +	 * Re-populate bitmap to include all pinned pages which are considered
> +	 * as dirty but exclude pages which are unpinned and pages which are
> +	 * marked dirty by vfio_dma_rw()
> +	 */
> +	bitmap_clear(dma->bitmap, 0, npages);
> +	vfio_dma_populate_bitmap(dma, pgsize);
> +	return 0;
> +}
> +
> +static int verify_bitmap_size(uint64_t npages, uint64_t bitmap_size)
> +{
> +	uint64_t bsize;
> +
> +	if (!npages || !bitmap_size || (bitmap_size > DIRTY_BITMAP_SIZE_MAX))
> +		return -EINVAL;
> +
> +	bsize = DIRTY_BITMAP_BYTES(npages);
> +
> +	if (bitmap_size < bsize)
> +		return -EINVAL;
> +
> +	return 0;
> +}
> +
>  static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
>  			     struct vfio_iommu_type1_dma_unmap *unmap)
>  {
> @@ -1038,16 +1189,16 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
>  	unsigned long vaddr = map->vaddr;
>  	size_t size = map->size;
>  	int ret = 0, prot = 0;
> -	uint64_t mask;
> +	uint64_t pgsize;
>  	struct vfio_dma *dma;
>  
>  	/* Verify that none of our __u64 fields overflow */
>  	if (map->size != size || map->vaddr != vaddr || map->iova != iova)
>  		return -EINVAL;
>  
> -	mask = ((uint64_t)1 << __ffs(vfio_pgsize_bitmap(iommu))) - 1;
> +	pgsize = (uint64_t)1 << __ffs(vfio_pgsize_bitmap(iommu));
>  
> -	WARN_ON(mask & PAGE_MASK);
> +	WARN_ON((pgsize - 1) & PAGE_MASK);
>  
>  	/* READ/WRITE from device perspective */
>  	if (map->flags & VFIO_DMA_MAP_FLAG_WRITE)
> @@ -1055,7 +1206,7 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
>  	if (map->flags & VFIO_DMA_MAP_FLAG_READ)
>  		prot |= IOMMU_READ;
>  
> -	if (!prot || !size || (size | iova | vaddr) & mask)
> +	if (!prot || !size || (size | iova | vaddr) & (pgsize - 1))
>  		return -EINVAL;
>  
>  	/* Don't allow IOVA or virtual address wrap */
> @@ -1130,6 +1281,12 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
>  	else
>  		ret = vfio_pin_map_dma(iommu, dma, size);
>  
> +	if (!ret && iommu->dirty_page_tracking) {
> +		ret = vfio_dma_bitmap_alloc(dma, pgsize);
> +		if (ret)
> +			vfio_remove_dma(iommu, dma);
> +	}
> +
>  out_unlock:
>  	mutex_unlock(&iommu->lock);
>  	return ret;
> @@ -2278,6 +2435,93 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
>  
>  		return copy_to_user((void __user *)arg, &unmap, minsz) ?
>  			-EFAULT : 0;
> +	} else if (cmd == VFIO_IOMMU_DIRTY_PAGES) {
> +		struct vfio_iommu_type1_dirty_bitmap dirty;
> +		uint32_t mask = VFIO_IOMMU_DIRTY_PAGES_FLAG_START |
> +				VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP |
> +				VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP;
> +		int ret = 0;
> +
> +		if (!iommu->v2)
> +			return -EACCES;
> +
> +		minsz = offsetofend(struct vfio_iommu_type1_dirty_bitmap,
> +				    flags);
> +
> +		if (copy_from_user(&dirty, (void __user *)arg, minsz))
> +			return -EFAULT;
> +
> +		if (dirty.argsz < minsz || dirty.flags & ~mask)
> +			return -EINVAL;
> +
> +		/* only one flag should be set at a time */
> +		if (__ffs(dirty.flags) != __fls(dirty.flags))
> +			return -EINVAL;
> +
> +		if (dirty.flags & VFIO_IOMMU_DIRTY_PAGES_FLAG_START) {
> +			uint64_t pgsize = 1 << __ffs(vfio_pgsize_bitmap(iommu));
> +
> +			mutex_lock(&iommu->lock);
> +			if (!iommu->dirty_page_tracking) {
> +				ret = vfio_dma_bitmap_alloc_all(iommu, pgsize);
> +				if (!ret)
> +					iommu->dirty_page_tracking = true;
> +			}
> +			mutex_unlock(&iommu->lock);
> +			return ret;
> +		} else if (dirty.flags & VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP) {
> +			mutex_lock(&iommu->lock);
> +			if (iommu->dirty_page_tracking) {
> +				iommu->dirty_page_tracking = false;
> +				vfio_dma_bitmap_free_all(iommu);
> +			}
> +			mutex_unlock(&iommu->lock);
> +			return 0;
> +		} else if (dirty.flags &
> +				 VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP) {
> +			struct vfio_iommu_type1_dirty_bitmap_get range;
> +			unsigned long pgshift;
> +			size_t data_size = dirty.argsz - minsz;
> +			uint64_t iommu_pgsize =
> +					 1 << __ffs(vfio_pgsize_bitmap(iommu));
> +
> +			if (!data_size || data_size < sizeof(range))
> +				return -EINVAL;
> +
> +			if (copy_from_user(&range, (void __user *)(arg + minsz),
> +					   sizeof(range)))
> +				return -EFAULT;
> +
> +			/* allow only smallest supported pgsize */
> +			if (range.bitmap.pgsize != iommu_pgsize)
> +				return -EINVAL;
> +			if (range.iova & (iommu_pgsize - 1))
> +				return -EINVAL;
> +			if (!range.size || range.size & (iommu_pgsize - 1))
> +				return -EINVAL;
> +			if (range.iova + range.size < range.iova)
> +				return -EINVAL;
> +			if (!access_ok((void __user *)range.bitmap.data,
> +				       range.bitmap.size))
> +				return -EINVAL;
> +
> +			pgshift = __ffs(range.bitmap.pgsize);
> +			ret = verify_bitmap_size(range.size >> pgshift,
> +						 range.bitmap.size);
> +			if (ret)
> +				return ret;
> +
> +			mutex_lock(&iommu->lock);
> +			if (iommu->dirty_page_tracking)
> +				ret = vfio_iova_dirty_bitmap(iommu, range.iova,
> +						range.size, range.bitmap.pgsize,
> +						range.bitmap.data);
> +			else
> +				ret = -EINVAL;
> +			mutex_unlock(&iommu->lock);
> +
> +			return ret;
> +		}
>  	}
>  
>  	return -ENOTTY;
> @@ -2345,10 +2589,20 @@ static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu,
>  
>  	vaddr = dma->vaddr + offset;
>  
> -	if (write)
> +	if (write) {
>  		*copied = __copy_to_user((void __user *)vaddr, data,
>  					 count) ? 0 : count;
> -	else
> +		if (*copied && iommu->dirty_page_tracking) {
> +			unsigned long pgshift =
> +				__ffs(vfio_pgsize_bitmap(iommu));
> +			/*
> +			 * Bitmap populated with the smallest supported page
> +			 * size
> +			 */
> +			bitmap_set(dma->bitmap, offset >> pgshift,
> +				   *copied >> pgshift);
> +		}
> +	} else
>  		*copied = __copy_from_user(data, (void __user *)vaddr,
>  					   count) ? 0 : count;
>  	if (kthread)
> -- 
> 2.7.0
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK


  parent reply index

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-24 21:18 Kirti Wankhede
2020-03-25  2:11 ` Yan Zhao
2020-03-26 21:39   ` Kirti Wankhede
2020-03-27  0:30     ` Yan Zhao
2020-03-27  5:07       ` Kirti Wankhede
2020-03-30  2:07         ` Yan Zhao
2020-03-30 20:47           ` Alex Williamson
2020-03-30 23:49             ` Yan Zhao
2020-03-27  5:28       ` Kirti Wankhede
2020-03-30  3:24         ` Yan Zhao
2020-03-30 13:49           ` Kirti Wankhede
2020-03-30 23:51             ` Yan Zhao
2020-03-31  0:53               ` Alex Williamson
2020-03-31  0:50                 ` Yan Zhao
2020-03-31  1:12                   ` Alex Williamson
2020-03-31  1:16                     ` Yan Zhao
2020-03-31  2:38                       ` Alex Williamson
2020-03-31  2:40                         ` Zhao, Yan Y
2020-03-27 11:57 ` Dr. David Alan Gilbert [this message]
2020-03-27 13:57   ` Alex Williamson
2020-03-27 14:09     ` Dr. David Alan Gilbert
  -- strict thread matches above, loose matches on Subject: below --
2020-03-24 19:32 [PATCH v16 Kernel 0/7] KABIs to support migration for VFIO devices Kirti Wankhede
2020-03-24 19:32 ` [PATCH v16 Kernel 4/7] vfio iommu: Implementation of ioctl for dirty pages tracking Kirti Wankhede
2020-03-24 20:37   ` Alex Williamson
2020-03-24 20:45     ` Alex Williamson
2020-03-24 21:48       ` Kirti Wankhede

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200327115745.GF2786@work-vm \
    --to=dgilbert@redhat.com \
    --cc=Ken.Xue@amd.com \
    --cc=Zhengxiao.zx@alibaba-inc.com \
    --cc=aik@ozlabs.ru \
    --cc=alex.williamson@redhat.com \
    --cc=changpeng.liu@intel.com \
    --cc=cjia@nvidia.com \
    --cc=cohuck@redhat.com \
    --cc=eauger@redhat.com \
    --cc=eskultet@redhat.com \
    --cc=felipe@nutanix.com \
    --cc=jonathan.davies@nutanix.com \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=kwankhede@nvidia.com \
    --cc=mlevitsk@redhat.com \
    --cc=pasic@linux.ibm.com \
    --cc=qemu-devel@nongnu.org \
    --cc=shuangtai.tst@alibaba-inc.com \
    --cc=yan.y.zhao@intel.com \
    --cc=yi.l.liu@intel.com \
    --cc=zhi.a.wang@intel.com \
    --cc=ziye.yang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

KVM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvm/0 kvm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvm kvm/ https://lore.kernel.org/kvm \
		kvm@vger.kernel.org
	public-inbox-index kvm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.kvm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git