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@xxxxxxxxxx>
Reviewed-by: Neo Jia <cjia@xxxxxxxxxx>
---
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.
+ */
+#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;
+
