@@ -198,3 +198,24 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd)
iommufd_put_object(&idev->obj);
return rc;
}
+
+int iommufd_hwpt_set_dirty(struct iommufd_ucmd *ucmd)
+{
+ struct iommu_hwpt_set_dirty *cmd = ucmd->cmd;
+ struct iommufd_hw_pagetable *hwpt;
+ struct iommufd_ioas *ioas;
+ int rc = -EOPNOTSUPP;
+ bool enable;
+
+ hwpt = iommufd_get_hwpt(ucmd, cmd->hwpt_id);
+ if (IS_ERR(hwpt))
+ return PTR_ERR(hwpt);
+
+ ioas = hwpt->ioas;
+ enable = cmd->flags & IOMMU_DIRTY_TRACKING_ENABLED;
+
+ rc = iopt_set_dirty_tracking(&ioas->iopt, hwpt->domain, enable);
+
+ iommufd_put_object(&hwpt->obj);
+ return rc;
+}
@@ -479,6 +479,62 @@ int iopt_read_and_clear_dirty_data(struct io_pagetable *iopt,
down_read(&iopt->iova_rwsem);
ret = iommu_read_and_clear_dirty(domain, flags, bitmap);
up_read(&iopt->iova_rwsem);
+
+ return ret;
+}
+
+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;
}
@@ -10,6 +10,7 @@
#include <linux/uaccess.h>
#include <linux/iommu.h>
#include <linux/iova_bitmap.h>
+#include <uapi/linux/iommufd.h>
struct iommu_domain;
struct iommu_group;
@@ -83,6 +84,8 @@ int iopt_read_and_clear_dirty_data(struct io_pagetable *iopt,
struct iommu_domain *domain,
unsigned long flags,
struct iommufd_dirty_data *bitmap);
+int iopt_set_dirty_tracking(struct io_pagetable *iopt,
+ struct iommu_domain *domain, bool enable);
void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova,
unsigned long length);
@@ -254,6 +257,14 @@ struct iommufd_hw_pagetable {
struct list_head hwpt_item;
};
+static inline struct iommufd_hw_pagetable *iommufd_get_hwpt(
+ struct iommufd_ucmd *ucmd, u32 id)
+{
+ return container_of(iommufd_get_object(ucmd->ictx, id,
+ IOMMUFD_OBJ_HW_PAGETABLE),
+ struct iommufd_hw_pagetable, obj);
+}
+int iommufd_hwpt_set_dirty(struct iommufd_ucmd *ucmd);
struct iommufd_hw_pagetable *
iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
struct iommufd_device *idev, u32 flags,
@@ -315,6 +315,7 @@ union ucmd_buffer {
struct iommu_ioas_unmap unmap;
struct iommu_option option;
struct iommu_vfio_ioas vfio_ioas;
+ struct iommu_hwpt_set_dirty set_dirty;
#ifdef CONFIG_IOMMUFD_TEST
struct iommu_test_cmd test;
#endif
@@ -358,6 +359,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
val64),
IOCTL_OP(IOMMU_VFIO_IOAS, iommufd_vfio_ioas, struct iommu_vfio_ioas,
__reserved),
+ IOCTL_OP(IOMMU_HWPT_SET_DIRTY, iommufd_hwpt_set_dirty,
+ struct iommu_hwpt_set_dirty, __reserved),
#ifdef CONFIG_IOMMUFD_TEST
IOCTL_OP(IOMMU_TEST_CMD, iommufd_test, struct iommu_test_cmd, last),
#endif
@@ -47,6 +47,7 @@ enum {
IOMMUFD_CMD_VFIO_IOAS,
IOMMUFD_CMD_HWPT_ALLOC,
IOMMUFD_CMD_GET_HW_INFO,
+ IOMMUFD_CMD_HWPT_SET_DIRTY,
};
/**
@@ -454,4 +455,30 @@ struct iommu_hw_info {
__u32 __reserved;
};
#define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO)
+
+/*
+ * enum iommufd_set_dirty_flags - Flags for steering dirty tracking
+ * @IOMMU_DIRTY_TRACKING_DISABLED: Disables dirty tracking
+ * @IOMMU_DIRTY_TRACKING_ENABLED: Enables dirty tracking
+ */
+enum iommufd_hwpt_set_dirty_flags {
+ IOMMU_DIRTY_TRACKING_DISABLED = 0,
+ IOMMU_DIRTY_TRACKING_ENABLED = 1,
+};
+
+/**
+ * struct iommu_hwpt_set_dirty - ioctl(IOMMU_HWPT_SET_DIRTY)
+ * @size: sizeof(struct iommu_hwpt_set_dirty)
+ * @flags: Flags to control dirty tracking status.
+ * @hwpt_id: HW pagetable ID that represents the IOMMU domain.
+ *
+ * Toggle dirty tracking on an HW pagetable.
+ */
+struct iommu_hwpt_set_dirty {
+ __u32 size;
+ __u32 flags;
+ __u32 hwpt_id;
+ __u32 __reserved;
+};
+#define IOMMU_HWPT_SET_DIRTY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_SET_DIRTY)
#endif
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. Signed-off-by: Joao Martins <joao.m.martins@oracle.com> --- drivers/iommu/iommufd/hw_pagetable.c | 21 ++++++++++ drivers/iommu/iommufd/io_pagetable.c | 56 +++++++++++++++++++++++++ drivers/iommu/iommufd/iommufd_private.h | 11 +++++ drivers/iommu/iommufd/main.c | 3 ++ include/uapi/linux/iommufd.h | 27 ++++++++++++ 5 files changed, 118 insertions(+)