Skip to content

Commit

Permalink
iommufd: Add iommufd_device_replace()
Browse files Browse the repository at this point in the history
Replace allows all the devices in a group to move in one step to a new
HWPT. Further, the HWPT move is done without going through a blocking
domain so that the IOMMU driver can implement some level of
non-distruption to ongoing DMA if that has meaning for it (eg for future
special driver domains)

Replace uses a lot of the same logic as normal attach, except the actual
domain change over has different restrictions, and we are careful to
sequence things so that failure is going to leave everything the way it
was, and not get trapped in a blocking domain or something if there is
ENOMEM.

Link: https://lore.kernel.org/r/14-v8-6659224517ea+532-iommufd_alloc_jgg@nvidia.com
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
  • Loading branch information
Jason Gunthorpe committed Jul 26, 2023
1 parent addb665 commit e88d4ec
Show file tree
Hide file tree
Showing 2 changed files with 102 additions and 0 deletions.
101 changes: 101 additions & 0 deletions drivers/iommu/iommufd/device.c
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
#include <linux/iommufd.h>
#include <linux/slab.h>
#include <linux/iommu.h>
#include "../iommu-priv.h"

#include "io_pagetable.h"
#include "iommufd_private.h"
Expand Down Expand Up @@ -408,6 +409,84 @@ iommufd_device_do_attach(struct iommufd_device *idev,
return NULL;
}

static struct iommufd_hw_pagetable *
iommufd_device_do_replace(struct iommufd_device *idev,
struct iommufd_hw_pagetable *hwpt)
{
struct iommufd_group *igroup = idev->igroup;
struct iommufd_hw_pagetable *old_hwpt;
unsigned int num_devices = 0;
struct iommufd_device *cur;
int rc;

mutex_lock(&idev->igroup->lock);

if (igroup->hwpt == NULL) {
rc = -EINVAL;
goto err_unlock;
}

if (hwpt == igroup->hwpt) {
mutex_unlock(&idev->igroup->lock);
return NULL;
}

/* Try to upgrade the domain we have */
list_for_each_entry(cur, &igroup->device_list, group_item) {
num_devices++;
if (cur->enforce_cache_coherency) {
rc = iommufd_hw_pagetable_enforce_cc(hwpt);
if (rc)
goto err_unlock;
}
}

old_hwpt = igroup->hwpt;
if (hwpt->ioas != old_hwpt->ioas) {
list_for_each_entry(cur, &igroup->device_list, group_item) {
rc = iopt_table_enforce_dev_resv_regions(
&hwpt->ioas->iopt, cur->dev, NULL);
if (rc)
goto err_unresv;
}
}

rc = iommufd_group_setup_msi(idev->igroup, hwpt);
if (rc)
goto err_unresv;

rc = iommu_group_replace_domain(igroup->group, hwpt->domain);
if (rc)
goto err_unresv;

if (hwpt->ioas != old_hwpt->ioas) {
list_for_each_entry(cur, &igroup->device_list, group_item)
iopt_remove_reserved_iova(&old_hwpt->ioas->iopt,
cur->dev);
}

igroup->hwpt = hwpt;

/*
* Move the refcounts held by the device_list to the new hwpt. Retain a
* refcount for this thread as the caller will free it.
*/
refcount_add(num_devices, &hwpt->obj.users);
if (num_devices > 1)
WARN_ON(refcount_sub_and_test(num_devices - 1,
&old_hwpt->obj.users));
mutex_unlock(&idev->igroup->lock);

/* Caller must destroy old_hwpt */
return old_hwpt;
err_unresv:
list_for_each_entry(cur, &igroup->device_list, group_item)
iopt_remove_reserved_iova(&hwpt->ioas->iopt, cur->dev);
err_unlock:
mutex_unlock(&idev->igroup->lock);
return ERR_PTR(rc);
}

typedef struct iommufd_hw_pagetable *(*attach_fn)(
struct iommufd_device *idev, struct iommufd_hw_pagetable *hwpt);

Expand Down Expand Up @@ -566,6 +645,28 @@ int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id)
}
EXPORT_SYMBOL_NS_GPL(iommufd_device_attach, IOMMUFD);

/**
* iommufd_device_replace - Change the device's iommu_domain
* @idev: device to change
* @pt_id: Input a IOMMUFD_OBJ_IOAS, or IOMMUFD_OBJ_HW_PAGETABLE
* Output the IOMMUFD_OBJ_HW_PAGETABLE ID
*
* This is the same as::
*
* iommufd_device_detach();
* iommufd_device_attach();
*
* If it fails then no change is made to the attachment. The iommu driver may
* implement this so there is no disruption in translation. This can only be
* called if iommufd_device_attach() has already succeeded.
*/
int iommufd_device_replace(struct iommufd_device *idev, u32 *pt_id)
{
return iommufd_device_change_pt(idev, pt_id,
&iommufd_device_do_replace);
}
EXPORT_SYMBOL_NS_GPL(iommufd_device_replace, IOMMUFD);

/**
* iommufd_device_detach - Disconnect a device to an iommu_domain
* @idev: device to detach
Expand Down
1 change: 1 addition & 0 deletions drivers/iommu/iommufd/main.c
Original file line number Diff line number Diff line change
Expand Up @@ -490,5 +490,6 @@ module_exit(iommufd_exit);
MODULE_ALIAS_MISCDEV(VFIO_MINOR);
MODULE_ALIAS("devname:vfio/vfio");
#endif
MODULE_IMPORT_NS(IOMMUFD_INTERNAL);
MODULE_DESCRIPTION("I/O Address Space Management for passthrough devices");
MODULE_LICENSE("GPL");

0 comments on commit e88d4ec

Please sign in to comment.