iommufd: Add IOMMU_HWPT_SET_DIRTY_TRACKING

Every IOMMU driver should be able to implement the needed iommu domain ops
to control dirty tracking.

Connect a hw_pagetable to the IOMMU core dirty tracking ops, specifically
the ability to enable/disable dirty tracking on an IOMMU domain
(hw_pagetable id). To that end add an io_pagetable kernel API to toggle
dirty tracking:

* iopt_set_dirty_tracking(iopt, [domain], state)

The intended caller of this is via the hw_pagetable object that is created.

Internally it will ensure the leftover dirty state is cleared /right
before/ dirty tracking starts. This is also useful for iommu drivers which
may decide that dirty tracking is always-enabled at boot without wanting to
toggle dynamically via corresponding iommu domain op.

Link: https://lore.kernel.org/r/20231024135109.73787-7-joao.m.martins@oracle.com
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

1 files changed, 54 insertions, 0 deletions

diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c
index 3a598182b761..41c2efb6ff15 100644
--- a/drivers/iommu/iommufd/io_pagetable.c
+++ b/drivers/iommu/iommufd/io_pagetable.c
@@ -412,6 +412,60 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt,
 	return 0;
 }
 
+static int iopt_clear_dirty_data(struct io_pagetable *iopt,
+				 struct iommu_domain *domain)
+{
+	const struct iommu_dirty_ops *ops = domain->dirty_ops;
+	struct iommu_iotlb_gather gather;
+	struct iommu_dirty_bitmap dirty;
+	struct iopt_area *area;
+	int ret = 0;
+
+	lockdep_assert_held_read(&iopt->iova_rwsem);
+
+	iommu_dirty_bitmap_init(&dirty, NULL, &gather);
+
+	for (area = iopt_area_iter_first(iopt, 0, ULONG_MAX); area;
+	     area = iopt_area_iter_next(area, 0, ULONG_MAX)) {
+		if (!area->pages)
+			continue;
+
+		ret = ops->read_and_clear_dirty(domain, iopt_area_iova(area),
+						iopt_area_length(area), 0,
+						&dirty);
+		if (ret)
+			break;
+	}
+
+	iommu_iotlb_sync(domain, &gather);
+	return ret;
+}
+
+int iopt_set_dirty_tracking(struct io_pagetable *iopt,
+			    struct iommu_domain *domain, bool enable)
+{
+	const struct iommu_dirty_ops *ops = domain->dirty_ops;
+	int ret = 0;
+
+	if (!ops)
+		return -EOPNOTSUPP;
+
+	down_read(&iopt->iova_rwsem);
+
+	/* Clear dirty bits from PTEs to ensure a clean snapshot */
+	if (enable) {
+		ret = iopt_clear_dirty_data(iopt, domain);
+		if (ret)
+			goto out_unlock;
+	}
+
+	ret = ops->set_dirty_tracking(domain, enable);
+
+out_unlock:
+	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)
 {