Re: [PATCH Kernel v20 6/8] vfio iommu: Update UNMAP_DMA ioctl to get dirty bitmap before unmap

[Kirti Wankhede <kwankhede@xxxxxxxxxx>]

On 5/15/2020 8:57 AM, Alex Williamson wrote:
> On Fri, 15 May 2020 02:07:45 +0530
> Kirti Wankhede <kwankhede@xxxxxxxxxx> wrote:
>
> > DMA mapped pages, including those pinned by mdev vendor drivers, might
> > get unpinned and unmapped while migration is active and device is still
> > running. For example, in pre-copy phase while guest driver could access
> > those pages, host device or vendor driver can dirty these mapped pages.
> > Such pages should be marked dirty so as to maintain memory consistency
> > for a user making use of dirty page tracking.
> >
> > To get bitmap during unmap, user should allocate memory for bitmap, set
> > it all zeros, set size of allocated memory, set page size to be
> > considered for bitmap and set flag VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP.
> >
> > Signed-off-by: Kirti Wankhede <kwankhede@xxxxxxxxxx>
> > Reviewed-by: Neo Jia <cjia@xxxxxxxxxx>
> > ---
> >   drivers/vfio/vfio_iommu_type1.c | 77 ++++++++++++++++++++++++++++++++++-------
> >   include/uapi/linux/vfio.h       | 10 ++++++
> >   2 files changed, 75 insertions(+), 12 deletions(-)
> >
> > diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> > index b76d3b14abfd..a1dc57bcece5 100644
> > --- a/drivers/vfio/vfio_iommu_type1.c
> > +++ b/drivers/vfio/vfio_iommu_type1.c
> > @@ -195,11 +195,15 @@ static void vfio_unlink_dma(struct vfio_iommu *iommu, struct vfio_dma *old)
> >   static int vfio_dma_bitmap_alloc(struct vfio_dma *dma, size_t pgsize)
> >   {
> >   	uint64_t npages = dma->size / pgsize;
> > +	size_t bitmap_size;
> >   
> >   	if (npages > DIRTY_BITMAP_PAGES_MAX)
> >   		return -EINVAL;
> >   
> > -	dma->bitmap = kvzalloc(DIRTY_BITMAP_BYTES(npages), GFP_KERNEL);
> > +	/* Allocate extra 64 bits which are used for bitmap manipulation */
> > +	bitmap_size = DIRTY_BITMAP_BYTES(npages) + sizeof(u64);
> > +
> > +	dma->bitmap = kvzalloc(bitmap_size, GFP_KERNEL);
> >   	if (!dma->bitmap)
> >   		return -ENOMEM;
> >   
> > @@ -999,23 +1003,25 @@ static int verify_bitmap_size(uint64_t npages, uint64_t bitmap_size)
> >   }
> >   
> >   static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
> > -			     struct vfio_iommu_type1_dma_unmap *unmap)
> > +			     struct vfio_iommu_type1_dma_unmap *unmap,
> > +			     struct vfio_bitmap *bitmap)
> >   {
> > -	uint64_t mask;
> >   	struct vfio_dma *dma, *dma_last = NULL;
> > -	size_t unmapped = 0;
> > +	size_t unmapped = 0, pgsize;
> >   	int ret = 0, retries = 0;
> > +	unsigned long pgshift;
> >   
> >   	mutex_lock(&iommu->lock);
> >   
> > -	mask = ((uint64_t)1 << __ffs(iommu->pgsize_bitmap)) - 1;
> > +	pgshift = __ffs(iommu->pgsize_bitmap);
> > +	pgsize = (size_t)1 << pgshift;
> >   
> > -	if (unmap->iova & mask) {
> > +	if (unmap->iova & (pgsize - 1)) {
> >   		ret = -EINVAL;
> >   		goto unlock;
> >   	}
> >   
> > -	if (!unmap->size || unmap->size & mask) {
> > +	if (!unmap->size || unmap->size & (pgsize - 1)) {
> >   		ret = -EINVAL;
> >   		goto unlock;
> >   	}
> > @@ -1026,9 +1032,15 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
> >   		goto unlock;
> >   	}
> >   
> > -	WARN_ON(mask & PAGE_MASK);
> > -again:
> > +	/* When dirty tracking is enabled, allow only min supported pgsize */
> > +	if ((unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) &&
> > +	    (!iommu->dirty_page_tracking || (bitmap->pgsize != pgsize))) {
> > +		ret = -EINVAL;
> > +		goto unlock;
> > +	}
> >   
> > +	WARN_ON((pgsize - 1) & PAGE_MASK);
> > +again:
> >   	/*
> >   	 * vfio-iommu-type1 (v1) - User mappings were coalesced together to
> >   	 * avoid tracking individual mappings.  This means that the granularity
> > @@ -1066,6 +1078,7 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
> >   			ret = -EINVAL;
> >   			goto unlock;
> >   		}
> > +
> >   		dma = vfio_find_dma(iommu, unmap->iova + unmap->size - 1, 0);
> >   		if (dma && dma->iova + dma->size != unmap->iova + unmap->size) {
> >   			ret = -EINVAL;
> > @@ -1083,6 +1096,23 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
> >   		if (dma->task->mm != current->mm)
> >   			break;
> >   
> > +		if ((unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) &&
> > +		    (dma_last != dma)) {
> > +
> > +			/*
> > +			 * mark all pages dirty if all pages are pinned and
> > +			 * mapped
> > +			 */
> > +			if (dma->iommu_mapped)
> > +				bitmap_set(dma->bitmap, 0,
> > +					   dma->size >> pgshift);
>
> Nit, all the callers of update_user_bitmap() precede the call with this
> identical operation, we should probably push it into the function to do
> it.
>
> > +
> > +			ret = update_user_bitmap(bitmap->data, dma,
> > +						 unmap->iova, pgsize);
> > +			if (ret)
> > +				break;
> > +		}
> > +
>
> As noted last time, the above is just busy work if pfn_list is not
> already empty.  The entire code block above should be moved to after
> the block below.  Thanks,

pfn_list will be empty for IOMMU backed devices where all pages are 
pinned and mapped, but those should be reported as dirty. So moved it 
back above empty pfn_list check.

Thanks,
Kirti

> Alex
>
> >   		if (!RB_EMPTY_ROOT(&dma->pfn_list)) {
> >   			struct vfio_iommu_type1_dma_unmap nb_unmap;
> >   
> > @@ -2447,17 +2477,40 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
> >   
> >   	} else if (cmd == VFIO_IOMMU_UNMAP_DMA) {
> >   		struct vfio_iommu_type1_dma_unmap unmap;
> > -		long ret;
> > +		struct vfio_bitmap bitmap = { 0 };
> > +		int ret;
> >   
> >   		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size);
> >   
> >   		if (copy_from_user(&unmap, (void __user *)arg, minsz))
> >   			return -EFAULT;
> >   
> > -		if (unmap.argsz < minsz || unmap.flags)
> > +		if (unmap.argsz < minsz ||
> > +		    unmap.flags & ~VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP)
> >   			return -EINVAL;
> >   
> > -		ret = vfio_dma_do_unmap(iommu, &unmap);
> > +		if (unmap.flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) {
> > +			unsigned long pgshift;
> > +
> > +			if (unmap.argsz < (minsz + sizeof(bitmap)))
> > +				return -EINVAL;
> > +
> > +			if (copy_from_user(&bitmap,
> > +					   (void __user *)(arg + minsz),
> > +					   sizeof(bitmap)))
> > +				return -EFAULT;
> > +
> > +			if (!access_ok((void __user *)bitmap.data, bitmap.size))
> > +				return -EINVAL;
> > +
> > +			pgshift = __ffs(bitmap.pgsize);
> > +			ret = verify_bitmap_size(unmap.size >> pgshift,
> > +						 bitmap.size);
> > +			if (ret)
> > +				return ret;
> > +		}
> > +
> > +		ret = vfio_dma_do_unmap(iommu, &unmap, &bitmap);
> >   		if (ret)
> >   			return ret;
> >   
> > diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> > index 123de3bc2dce..0a0c7315ddd6 100644
> > --- a/include/uapi/linux/vfio.h
> > +++ b/include/uapi/linux/vfio.h
> > @@ -1048,12 +1048,22 @@ struct vfio_bitmap {
> >    * field.  No guarantee is made to the user that arbitrary unmaps of iova
> >    * or size different from those used in the original mapping call will
> >    * succeed.
> > + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get dirty bitmap
> > + * before unmapping IO virtual addresses. When this flag is set, user must
> > + * provide data[] as structure vfio_bitmap. User must allocate memory to get
> > + * bitmap, zero the bitmap memory and must set size of allocated memory in
> > + * vfio_bitmap.size field. A bit in bitmap represents one page of user provided
> > + * page size in 'pgsize', consecutively starting from iova offset. Bit set
> > + * indicates page at that offset from iova is dirty. Bitmap of pages in the
> > + * range of unmapped size is returned in vfio_bitmap.data
> >    */
> >   struct vfio_iommu_type1_dma_unmap {
> >   	__u32	argsz;
> >   	__u32	flags;
> > +#define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0)
> >   	__u64	iova;				/* IO virtual address */
> >   	__u64	size;				/* Size of mapping (bytes) */
> > +	__u8    data[];
> >   };
> >   
> >   #define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14)