On 5/11/23 10:30 PM, Yi Liu wrote:
Under nested IOMMU translation, userspace owns the stage-1 translation table (e.g. the stage-1 page table of Intel VT-d or the context table of ARM SMMUv3, and etc.). Stage-1 translation tables are vendor specific, and needs to be compatiable with the underlying IOMMU hardware. Hence, userspace should know the IOMMU hardware capability before creating and configuring the stage-1 translation table to kernel.
This adds IOMMU_DEVICE_GET_HW_INFO to query the IOMMU hardware information for a given device. The returned data is vendor specific, userspace needs to decode it with the structure mapped by the @out_data_type field.
As only physical devices have IOMMU hardware, so this will return error if the given device is not a physical device.
Co-developed-by: Nicolin Chen nicolinc@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com Signed-off-by: Yi Liu yi.l.liu@intel.com
drivers/iommu/iommufd/device.c | 72 +++++++++++++++++++++++++ drivers/iommu/iommufd/iommufd_private.h | 1 + drivers/iommu/iommufd/main.c | 3 ++ include/uapi/linux/iommufd.h | 37 +++++++++++++ 4 files changed, 113 insertions(+)
diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 051bd8e99858..bc99d092de8f 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -263,6 +263,78 @@ u32 iommufd_device_to_id(struct iommufd_device *idev) } EXPORT_SYMBOL_NS_GPL(iommufd_device_to_id, IOMMUFD); +static int iommufd_zero_fill_user(u64 ptr, int bytes) +{
- int index = 0;
- for (; index < bytes; index++) {
if (put_user(0, (uint8_t __user *)u64_to_user_ptr(ptr + index)))
return -EFAULT;
- }
- return 0;
+}
+int iommufd_device_get_hw_info(struct iommufd_ucmd *ucmd) +{
- struct iommu_hw_info *cmd = ucmd->cmd;
- unsigned int length = 0, data_len;
- struct iommufd_device *idev;
- const struct iommu_ops *ops;
- void *data = NULL;
- int rc = 0;
- if (cmd->flags || cmd->__reserved || !cmd->data_len)
return -EOPNOTSUPP;
- idev = iommufd_get_device(ucmd, cmd->dev_id);
- if (IS_ERR(idev))
return PTR_ERR(idev);
- ops = dev_iommu_ops(idev->dev);
- if (!ops->hw_info)
goto done;
If the iommu driver doesn't provide a hw_info callback, it still returns success?
- /* driver has hw_info callback should have a unique hw_info_type */
- if (ops->hw_info_type == IOMMU_HW_INFO_TYPE_NONE) {
pr_warn_ratelimited("iommu driver set an invalid type\n");
rc = -ENODEV;
goto out_err;
- }
- data = ops->hw_info(idev->dev, &data_len);
- if (IS_ERR(data)) {
rc = PTR_ERR(data);
goto out_err;
- }
- length = min(cmd->data_len, data_len);
- if (copy_to_user(u64_to_user_ptr(cmd->data_ptr), data, length)) {
rc = -EFAULT;
goto out_err;
- }
- /*
* Zero the trailing bytes if the user buffer is bigger than the
* data size kernel actually has.
*/
- if (length < cmd->data_len) {
rc = iommufd_zero_fill_user(cmd->data_ptr + length,
cmd->data_len - length);
if (rc)
goto out_err;
- }
+done:
- cmd->data_len = length;
- cmd->out_data_type = ops->hw_info_type;
- rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
+out_err:
- kfree(data);
- iommufd_put_object(&idev->obj);
- return rc;
+}
- static int iommufd_group_setup_msi(struct iommufd_group *igroup, struct iommufd_hw_pagetable *hwpt) {
Best regards, baolu