@@ -15,6 +15,7 @@
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/errno.h>
+#include <uapi/linux/iommufd.h>
#include "io_pagetable.h"
#include "double_span.h"
@@ -412,6 +413,75 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt,
return 0;
}
+struct iova_bitmap_fn_arg {
+ struct iommu_domain *domain;
+ struct iommu_dirty_bitmap *dirty;
+};
+
+static int __iommu_read_and_clear_dirty(struct iova_bitmap *bitmap,
+ unsigned long iova, size_t length,
+ void *opaque)
+{
+ struct iova_bitmap_fn_arg *arg = opaque;
+ struct iommu_domain *domain = arg->domain;
+ const struct iommu_domain_ops *ops = domain->ops;
+ struct iommu_dirty_bitmap *dirty = arg->dirty;
+
+ return ops->read_and_clear_dirty(domain, iova, length, 0, dirty);
+}
+
+static int iommu_read_and_clear_dirty(struct iommu_domain *domain,
+ unsigned long flags,
+ struct iommufd_dirty_data *bitmap)
+{
+ const struct iommu_domain_ops *ops = domain->ops;
+ struct iommu_iotlb_gather gather;
+ struct iommu_dirty_bitmap dirty;
+ struct iova_bitmap_fn_arg arg;
+ struct iova_bitmap *iter;
+ int ret = 0;
+
+ if (!ops || !ops->read_and_clear_dirty)
+ return -EOPNOTSUPP;
+
+ iter = iova_bitmap_alloc(bitmap->iova, bitmap->length,
+ bitmap->page_size, bitmap->data);
+ if (IS_ERR(iter))
+ return -ENOMEM;
+
+ iommu_dirty_bitmap_init(&dirty, iter, &gather);
+
+ arg.domain = domain;
+ arg.dirty = &dirty;
+ iova_bitmap_for_each(iter, &arg, __iommu_read_and_clear_dirty);
+
+ iommu_iotlb_sync(domain, &gather);
+ iova_bitmap_free(iter);
+
+ return ret;
+}
+
+int iopt_read_and_clear_dirty_data(struct io_pagetable *iopt,
+ struct iommu_domain *domain,
+ unsigned long flags,
+ struct iommufd_dirty_data *bitmap)
+{
+ unsigned long last_iova, iova = bitmap->iova;
+ unsigned long length = bitmap->length;
+ int ret = -EOPNOTSUPP;
+
+ if ((iova & (iopt->iova_alignment - 1)))
+ return -EINVAL;
+
+ if (check_add_overflow(iova, length - 1, &last_iova))
+ return -EOVERFLOW;
+
+ down_read(&iopt->iova_rwsem);
+ ret = iommu_read_and_clear_dirty(domain, flags, bitmap);
+ up_read(&iopt->iova_rwsem);
+ return ret;
+}
+
int iopt_get_pages(struct io_pagetable *iopt, unsigned long iova,
unsigned long length, struct list_head *pages_list)
{
@@ -8,6 +8,8 @@
#include <linux/xarray.h>
#include <linux/refcount.h>
#include <linux/uaccess.h>
+#include <linux/iommu.h>
+#include <linux/iova_bitmap.h>
struct iommu_domain;
struct iommu_group;
@@ -70,6 +72,18 @@ int iopt_unmap_iova(struct io_pagetable *iopt, unsigned long iova,
unsigned long length, unsigned long *unmapped);
int iopt_unmap_all(struct io_pagetable *iopt, unsigned long *unmapped);
+struct iommufd_dirty_data {
+ unsigned long iova;
+ unsigned long length;
+ unsigned long page_size;
+ unsigned long long *data;
+};
+
+int iopt_read_and_clear_dirty_data(struct io_pagetable *iopt,
+ struct iommu_domain *domain,
+ unsigned long flags,
+ struct iommufd_dirty_data *bitmap);
+
void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova,
unsigned long length);
int iopt_table_add_domain(struct io_pagetable *iopt,
Add an IO pagetable API iopt_read_and_clear_dirty_data() that performs the reading of dirty IOPTEs for a given IOVA range and then copying back to userspace bitmap. Underneath it uses the IOMMU domain kernel API which will read the dirty bits, as well as atomically clearing the IOPTE dirty bit and flushing the IOTLB at the end. The IOVA bitmaps usage takes care of the iteration of the bitmaps user pages efficiently and without copies. Signed-off-by: Joao Martins <joao.m.martins@oracle.com> --- drivers/iommu/iommufd/io_pagetable.c | 70 +++++++++++++++++++++++++ drivers/iommu/iommufd/iommufd_private.h | 14 +++++ 2 files changed, 84 insertions(+)