@@ -224,3 +224,61 @@ int iommufd_hwpt_set_dirty(struct iommufd_ucmd *ucmd)
iommufd_put_object(&hwpt->obj);
return rc;
}
+
+int iommufd_check_iova_range(struct iommufd_ioas *ioas,
+ struct iommufd_dirty_data *bitmap)
+{
+ unsigned long pgshift, npages;
+ size_t iommu_pgsize;
+ int rc = -EINVAL;
+
+ pgshift = __ffs(bitmap->page_size);
+ npages = bitmap->length >> pgshift;
+
+ if (!npages || (npages > ULONG_MAX))
+ return rc;
+
+ iommu_pgsize = 1 << __ffs(ioas->iopt.iova_alignment);
+
+ /* allow only smallest supported pgsize */
+ if (bitmap->page_size != iommu_pgsize)
+ return rc;
+
+ if (bitmap->iova & (iommu_pgsize - 1))
+ return rc;
+
+ if (!bitmap->length || bitmap->length & (iommu_pgsize - 1))
+ return rc;
+
+ return 0;
+}
+
+int iommufd_hwpt_get_dirty_iova(struct iommufd_ucmd *ucmd)
+{
+ struct iommu_hwpt_get_dirty_iova *cmd = ucmd->cmd;
+ struct iommufd_hw_pagetable *hwpt;
+ struct iommufd_ioas *ioas;
+ int rc = -EOPNOTSUPP;
+
+ if ((cmd->flags || cmd->__reserved))
+ return -EOPNOTSUPP;
+
+ hwpt = iommufd_get_hwpt(ucmd, cmd->hwpt_id);
+ if (IS_ERR(hwpt))
+ return PTR_ERR(hwpt);
+
+ if (!hwpt->enforce_dirty)
+ return -EOPNOTSUPP;
+
+ ioas = hwpt->ioas;
+ rc = iommufd_check_iova_range(ioas, &cmd->bitmap);
+ if (rc)
+ goto out_put;
+
+ rc = iopt_read_and_clear_dirty_data(&ioas->iopt, hwpt->domain,
+ cmd->flags, &cmd->bitmap);
+
+out_put:
+ iommufd_put_object(&hwpt->obj);
+ return rc;
+}
@@ -73,13 +73,6 @@ 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,
@@ -251,6 +244,8 @@ int iommufd_option_rlimit_mode(struct iommu_option *cmd,
struct iommufd_ctx *ictx);
int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd);
+int iommufd_check_iova_range(struct iommufd_ioas *ioas,
+ struct iommufd_dirty_data *bitmap);
/*
* A HW pagetable is called an iommu_domain inside the kernel. This user object
@@ -278,6 +273,8 @@ static inline struct iommufd_hw_pagetable *iommufd_get_hwpt(
struct iommufd_hw_pagetable, obj);
}
int iommufd_hwpt_set_dirty(struct iommufd_ucmd *ucmd);
+int iommufd_hwpt_get_dirty_iova(struct iommufd_ucmd *ucmd);
+
struct iommufd_hw_pagetable *
iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
struct iommufd_device *idev, bool immediate_attach,
@@ -278,6 +278,7 @@ union ucmd_buffer {
struct iommu_option option;
struct iommu_vfio_ioas vfio_ioas;
struct iommu_hwpt_set_dirty set_dirty;
+ struct iommu_hwpt_get_dirty_iova get_dirty_iova;
#ifdef CONFIG_IOMMUFD_TEST
struct iommu_test_cmd test;
#endif
@@ -321,6 +322,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
__reserved),
IOCTL_OP(IOMMU_HWPT_SET_DIRTY, iommufd_hwpt_set_dirty,
struct iommu_hwpt_set_dirty, __reserved),
+ IOCTL_OP(IOMMU_HWPT_GET_DIRTY_IOVA, iommufd_hwpt_get_dirty_iova,
+ struct iommu_hwpt_get_dirty_iova, bitmap.data),
#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_HWPT_SET_DIRTY,
+ IOMMUFD_CMD_HWPT_GET_DIRTY_IOVA,
};
/**
@@ -406,4 +407,39 @@ struct iommu_hwpt_set_dirty {
__u32 __reserved;
};
#define IOMMU_HWPT_SET_DIRTY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_SET_DIRTY)
+
+/**
+ * struct iommufd_dirty_bitmap - Dirty IOVA tracking bitmap
+ * @iova: base IOVA of the bitmap
+ * @length: IOVA size
+ * @page_size: page size granularity of each bit in the bitmap
+ * @data: bitmap where to set the dirty bits. The bitmap bits each
+ * represent a page_size which you deviate from an arbitrary iova.
+ * Checking a given IOVA is dirty:
+ *
+ * data[(iova / page_size) / 64] & (1ULL << (iova % 64))
+ */
+struct iommufd_dirty_data {
+ __aligned_u64 iova;
+ __aligned_u64 length;
+ __aligned_u64 page_size;
+ __aligned_u64 *data;
+};
+
+/**
+ * struct iommu_hwpt_get_dirty_iova - ioctl(IOMMU_HWPT_GET_DIRTY_IOVA)
+ * @size: sizeof(struct iommu_hwpt_get_dirty_iova)
+ * @hwpt_id: HW pagetable ID that represents the IOMMU domain.
+ * @flags: Flags to control dirty tracking status.
+ * @bitmap: Bitmap of the range of IOVA to read out
+ */
+struct iommu_hwpt_get_dirty_iova {
+ __u32 size;
+ __u32 hwpt_id;
+ __u32 flags;
+ __u32 __reserved;
+ struct iommufd_dirty_data bitmap;
+};
+#define IOMMU_HWPT_GET_DIRTY_IOVA _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_GET_DIRTY_IOVA)
+
#endif
Connect a hw_pagetable to the IOMMU core dirty tracking read_and_clear_dirty iommu domain op. It exposes all of the functionality for the UAPI that read the dirtied IOVAs while clearing the Dirty bits from the PTEs In doing so the previously internal iommufd_dirty_data structure is moved over as the UAPI intermediate structure for representing iommufd dirty bitmaps. Contrary to past incantation of a similar interface in VFIO the IOVA range to be scanned is tied in to the bitmap size, thus the application needs to pass a appropriately sized bitmap address taking into account the iova range being passed *and* page size ... as opposed to allowing bitmap-iova != iova. Signed-off-by: Joao Martins <joao.m.martins@oracle.com> --- drivers/iommu/iommufd/hw_pagetable.c | 58 +++++++++++++++++++++++++ drivers/iommu/iommufd/iommufd_private.h | 11 ++--- drivers/iommu/iommufd/main.c | 3 ++ include/uapi/linux/iommufd.h | 36 +++++++++++++++ 4 files changed, 101 insertions(+), 7 deletions(-)