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, 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. Within the iterator
function we iterate over io-pagetable contigous areas that have been
mapped.
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@xxxxxxxxxx>
Reviewed-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
Reviewed-by: Kevin Tian <kevin.tian@xxxxxxxxx>
---
drivers/iommu/iommufd/hw_pagetable.c | 52 ++++++++++++++
drivers/iommu/iommufd/io_pagetable.c | 90 +++++++++++++++++++++++++
drivers/iommu/iommufd/iommufd_private.h | 10 +++
drivers/iommu/iommufd/main.c | 4 ++
include/uapi/linux/iommufd.h | 34 ++++++++++
5 files changed, 190 insertions(+)
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index db7ff8c99e29..72be43fa5248 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -220,3 +220,55 @@ int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd)
iommufd_put_object(&hwpt->obj);
return rc;
}
+
+int iommufd_check_iova_range(struct iommufd_ioas *ioas,
+ struct iommu_hwpt_get_dirty_bitmap *bitmap)
+{
+ unsigned long npages;
+ size_t iommu_pgsize;
+ int rc = -EINVAL;
+
+ if (!bitmap->page_size)
+ return rc;
+
+ npages = bitmap->length / bitmap->page_size;
+ if (!npages || (npages > ULONG_MAX))
+ return rc;
+
+ iommu_pgsize = ioas->iopt.iova_alignment;
+
+ 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_bitmap(struct iommufd_ucmd *ucmd)
+{
+ struct iommu_hwpt_get_dirty_bitmap *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);
+
+ ioas = hwpt->ioas;
+ rc = iommufd_check_iova_range(ioas, cmd);
+ if (rc)
+ goto out_put;
+
+ rc = iopt_read_and_clear_dirty_data(&ioas->iopt, hwpt->domain,
+ cmd->flags, cmd);
+
+out_put:
+ iommufd_put_object(&hwpt->obj);
+ return rc;
+}
diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c
index 535d73466e15..cb168fc415b0 100644
--- a/drivers/iommu/iommufd/io_pagetable.c
+++ b/drivers/iommu/iommufd/io_pagetable.c
@@ -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 +413,95 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt,
return 0;
}
+struct iova_bitmap_fn_arg {
+ struct io_pagetable *iopt;
+ 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 iopt_area *area;
+ struct iopt_area_contig_iter iter;
+ struct iova_bitmap_fn_arg *arg = opaque;
+ struct iommu_domain *domain = arg->domain;
+ struct iommu_dirty_bitmap *dirty = arg->dirty;
+ const struct iommu_dirty_ops *ops = domain->dirty_ops;
+ unsigned long last_iova = iova + length - 1;
+ int ret;
+
+ iopt_for_each_contig_area(&iter, area, arg->iopt, iova, last_iova) {
+ unsigned long last = min(last_iova, iopt_area_last_iova(area));
+
+ ret = ops->read_and_clear_dirty(domain, iter.cur_iova,
+ last - iter.cur_iova + 1,
+ 0, dirty);
+ if (ret)
+ return ret;
+ }
+
+ if (!iopt_area_contig_done(&iter))
+ return -EINVAL;
+ return 0;
+}
+
+static int iommu_read_and_clear_dirty(struct iommu_domain *domain,
+ struct io_pagetable *iopt,
+ unsigned long flags,
+ struct iommu_hwpt_get_dirty_bitmap *bitmap)
+{
+ const struct iommu_dirty_ops *ops = domain->dirty_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.iopt = iopt;
+ 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 iommu_hwpt_get_dirty_bitmap *bitmap)
+{
+ unsigned long last_iova, iova = bitmap->iova;
+ unsigned long length = bitmap->length;
+ int ret = -EINVAL;
+
+ 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, iopt, flags, bitmap);
+ up_read(&iopt->iova_rwsem);
+
+ return ret;
+}
+
static int iopt_clear_dirty_data(struct io_pagetable *iopt,
struct iommu_domain *domain)
{
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index f896f47c705a..a2f83cd9706d 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -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>
#include <uapi/linux/iommufd.h>
struct iommu_domain;
@@ -71,6 +73,10 @@ 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);
+int iopt_read_and_clear_dirty_data(struct io_pagetable *iopt,
+ struct iommu_domain *domain,
+ unsigned long flags,
+ struct iommu_hwpt_get_dirty_bitmap *bitmap);
int iopt_set_dirty_tracking(struct io_pagetable *iopt,
struct iommu_domain *domain, bool enable);
@@ -226,6 +232,8 @@ 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 iommu_hwpt_get_dirty_bitmap *bitmap);
/*
* A HW pagetable is called an iommu_domain inside the kernel. This user object
@@ -252,6 +260,8 @@ static inline struct iommufd_hw_pagetable *iommufd_get_hwpt(
struct iommufd_hw_pagetable, obj);
}
int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd);
+int iommufd_hwpt_get_dirty_bitmap(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,
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 46fedd779714..d50f42a730aa 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -307,6 +307,7 @@ union ucmd_buffer {
struct iommu_destroy destroy;
struct iommu_hw_info info;
struct iommu_hwpt_alloc hwpt;
+ struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap;
struct iommu_hwpt_set_dirty_tracking set_dirty_tracking;
struct iommu_ioas_alloc alloc;
struct iommu_ioas_allow_iovas allow_iovas;
@@ -343,6 +344,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
__reserved),
IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc,
__reserved),
+ IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap,
+ struct iommu_hwpt_get_dirty_bitmap, data),
IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking,
struct iommu_hwpt_set_dirty_tracking, __reserved),
IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl,
@@ -555,5 +558,6 @@ MODULE_ALIAS_MISCDEV(VFIO_MINOR);
MODULE_ALIAS("devname:vfio/vfio");
#endif
MODULE_IMPORT_NS(IOMMUFD_INTERNAL);
+MODULE_IMPORT_NS(IOMMUFD);
MODULE_DESCRIPTION("I/O Address Space Management for passthrough devices");
MODULE_LICENSE("GPL");
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 525b6e5cedee..06724bbe8af3 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -48,6 +48,7 @@ enum {
IOMMUFD_CMD_HWPT_ALLOC,
IOMMUFD_CMD_GET_HW_INFO,
IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING,
+ IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP,
};
/**
@@ -480,4 +481,37 @@ struct iommu_hwpt_set_dirty_tracking {
};
#define IOMMU_HWPT_SET_DIRTY_TRACKING _IO(IOMMUFD_TYPE, \
IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING)
+
+/**
+ * struct iommu_hwpt_get_dirty_bitmap - ioctl(IOMMU_HWPT_GET_DIRTY_BITMAP)
+ * @size: sizeof(struct iommu_hwpt_get_dirty_bitmap)
+ * @hwpt_id: HW pagetable ID that represents the IOMMU domain
+ * @flags: Must be zero
+ * @iova: base IOVA of the bitmap first bit
+ * @length: IOVA range 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 / page_size) % 64))
+ *
+ * Walk the IOMMU pagetables for a given IOVA range to return a bitmap
+ * with the dirty IOVAs. In doing so it will also by default clear any
+ * dirty bit metadata set in the IOPTE.
+ */
+struct iommu_hwpt_get_dirty_bitmap {
+ __u32 size;
+ __u32 hwpt_id;
+ __u32 flags;
+ __u32 __reserved;
+ __aligned_u64 iova;
+ __aligned_u64 length;
+ __aligned_u64 page_size;
+ __aligned_u64 *data;
+};
+#define IOMMU_HWPT_GET_DIRTY_BITMAP _IO(IOMMUFD_TYPE, \
+ IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP)
+
#endif
--
2.17.2
