Re: [PATCH Kernel v22 6/8] vfio iommu: Update UNMAP_DMA ioctl to get dirty bitmap before unmap
On 5/20/2020 3:57 PM, Cornelia Huck wrote:
On Tue, 19 May 2020 12:24:13 +0530
Kirti Wankhede 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
Reviewed-by: Neo Jia
---
drivers/vfio/vfio_iommu_type1.c | 62 +
include/uapi/linux/vfio.h | 10 +++
2 files changed, 61 insertions(+), 11 deletions(-)
(...)
@@ -1085,6 +1093,7 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
ret = -EINVAL;
goto unlock;
}
+
Nit: unrelated whitespace change.
dma = vfio_find_dma(iommu, unmap->iova + unmap->size - 1, 0);
if (dma && dma->iova + dma->size != unmap->iova + unmap->size) {
ret = -EINVAL;
(...)
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 4850c1fef1f8..a1dd2150971e 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
s/dirty bitmap/the dirty bitmap/
+ * before unmapping IO virtual addresses. When this flag is set, user must
s/user/the user/
+ * provide data[] as structure vfio_bitmap. User must allocate memory to get
"provide a struct vfio_bitmap in data[]" ?
+ * bitmap, zero the bitmap memory and must set size of allocated memory in
+ * vfio_bitmap.size field.
"The user must provide zero-allocated memory via vfio_bitmap.data and
its size in the vfio_bitmap.size field." ?
A bit in bitmap represents one page of user provided
s/bitmap/the bitmap/
+ * page size in 'pgsize', consecutively starting from iova offset. Bit set
s/Bit set/A set bit/
+ * indicates page at that offset from iova is dirty. Bitmap of pages in the
s/indicates page/indicates that the page/
+ * range of unmapped size is returned in vfio_bitmap.data
"A bitmap of the pages in the range of the unmapped size is returned in
the user-provided 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) */
+ __u8data[];
};
#define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14)
With the nits addressed,
Done.
Reviewed-by: Cornelia Huck
Thanks.
Kirti
Re: [PATCH Kernel v22 6/8] vfio iommu: Update UNMAP_DMA ioctl to get dirty bitmap before unmap
On Tue, 19 May 2020 12:24:13 +0530
Kirti Wankhede 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
> Reviewed-by: Neo Jia
> ---
> drivers/vfio/vfio_iommu_type1.c | 62
> +
> include/uapi/linux/vfio.h | 10 +++
> 2 files changed, 61 insertions(+), 11 deletions(-)
(...)
> @@ -1085,6 +1093,7 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
> ret = -EINVAL;
> goto unlock;
> }
> +
Nit: unrelated whitespace change.
> dma = vfio_find_dma(iommu, unmap->iova + unmap->size - 1, 0);
> if (dma && dma->iova + dma->size != unmap->iova + unmap->size) {
> ret = -EINVAL;
(...)
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index 4850c1fef1f8..a1dd2150971e 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
s/dirty bitmap/the dirty bitmap/
> + * before unmapping IO virtual addresses. When this flag is set, user must
s/user/the user/
> + * provide data[] as structure vfio_bitmap. User must allocate memory to get
"provide a struct vfio_bitmap in data[]" ?
> + * bitmap, zero the bitmap memory and must set size of allocated memory in
> + * vfio_bitmap.size field.
"The user must provide zero-allocated memory via vfio_bitmap.data and
its size in the vfio_bitmap.size field." ?
> A bit in bitmap represents one page of user provided
s/bitmap/the bitmap/
> + * page size in 'pgsize', consecutively starting from iova offset. Bit set
s/Bit set/A set bit/
> + * indicates page at that offset from iova is dirty. Bitmap of pages in the
s/indicates page/indicates that the page/
> + * range of unmapped size is returned in vfio_bitmap.data
"A bitmap of the pages in the range of the unmapped size is returned in
the user-provided 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) */
> + __u8data[];
> };
>
> #define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14)
With the nits addressed,
Reviewed-by: Cornelia Huck
[PATCH Kernel v22 6/8] vfio iommu: Update UNMAP_DMA ioctl to get dirty bitmap before unmap
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
Reviewed-by: Neo Jia
---
drivers/vfio/vfio_iommu_type1.c | 62 +
include/uapi/linux/vfio.h | 10 +++
2 files changed, 61 insertions(+), 11 deletions(-)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 0a420594483a..963ae4348b3c 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1018,23 +1018,25 @@ 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(>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;
}
@@ -1045,9 +1047,15 @@ 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
@@ -1085,6 +1093,7 @@ 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;
@@ -1128,6 +1137,14 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
mutex_lock(>lock);
goto again;
}
+
+ if (unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) {
+ ret = update_user_bitmap(bitmap->data, dma,
+unmap->iova, pgsize);
+ if (ret)
+ break;
+ }
+
unmapped += dma->size;
vfio_remove_dma(iommu, dma);
}
@@ -2466,17 +2483,40 @@ 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(, (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, );
+ 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(,
+ (void __user *)(arg + minsz),
+ sizeof(bitmap)))
+ return -EFAULT;
+
+ if (!access_ok((void __user
[PATCH Kernel v22 6/8] vfio iommu: Update UNMAP_DMA ioctl to get dirty bitmap before unmap
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
Reviewed-by: Neo Jia
---
drivers/vfio/vfio_iommu_type1.c | 68 +
include/uapi/linux/vfio.h | 10 ++
2 files changed, 66 insertions(+), 12 deletions(-)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index bf740fef196f..b9ee78a615a4 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;
@@ -1018,23 +1022,25 @@ 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(>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;
}
@@ -1045,9 +1051,15 @@ 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
@@ -1085,6 +1097,7 @@ 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;
@@ -1128,6 +1141,14 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
mutex_lock(>lock);
goto again;
}
+
+ if (unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) {
+ ret = update_user_bitmap(bitmap->data, dma,
+unmap->iova, pgsize);
+ if (ret)
+ break;
+ }
+
unmapped += dma->size;
vfio_remove_dma(iommu, dma);
}
@@ -2466,17 +2487,40 @@ 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(, (void __user *)arg, minsz))
return -EFAULT;
- if (unmap.argsz < minsz || unmap.flags)
+ if (unmap.argsz < minsz ||
+
