[v6,3/4] iommufd: Add IOMMU_GET_HW_INFO
Commit Message
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 need to be compatible 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_GET_HW_INFO ioctl to query the IOMMU hardware information
(a.k.a capability) 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.
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
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/main.c | 97 ++++++++++++++++++++++++++++++++++++
include/uapi/linux/iommufd.h | 36 +++++++++++++
2 files changed, 133 insertions(+)
Comments
On 2023/8/8 23:35, Yi Liu wrote:
> +static int iommufd_fill_hw_info(struct device *dev, void __user *user_ptr,
> + unsigned int *length, u32 *type)
> +{
> + const struct iommu_ops *ops;
> + unsigned int data_len;
> + void *data;
> + int rc = 0;
> +
> + ops = dev_iommu_ops(dev);
> + if (!ops->hw_info) {
> + *length = 0;
> + *type = IOMMU_HW_INFO_TYPE_NONE;
> + return 0;
> + }
> +
> + data = ops->hw_info(dev, &data_len, type);
> + if (IS_ERR(data))
> + return PTR_ERR(data);
> +
> + /*
> + * drivers that have hw_info callback should have a unique
> + * iommu_hw_info_type.
> + */
> + if (WARN_ON_ONCE(*type == IOMMU_HW_INFO_TYPE_NONE)) {
> + rc = -ENODEV;
> + goto err_free;
> + }
> +
> + *length = min(*length, data_len);
> + if (copy_to_user(user_ptr, data, *length)) {
copy_to_user() returns the number of bytes that were successfully
copied, right?
If so, isn't it always failure case? Or I missed anything?
> + rc = -EFAULT;
> + goto err_free;
nit: this goto is unnecessary.
> + }
> +
> +err_free:
> + kfree(data);
> + return rc;
> +}
Best regards,
baolu
On Wed, Aug 09, 2023 at 06:16:19PM +0800, Baolu Lu wrote:
> On 2023/8/8 23:35, Yi Liu wrote:
> > +static int iommufd_fill_hw_info(struct device *dev, void __user *user_ptr,
> > + unsigned int *length, u32 *type)
> > +{
> > + const struct iommu_ops *ops;
> > + unsigned int data_len;
> > + void *data;
> > + int rc = 0;
> > +
> > + ops = dev_iommu_ops(dev);
> > + if (!ops->hw_info) {
> > + *length = 0;
> > + *type = IOMMU_HW_INFO_TYPE_NONE;
> > + return 0;
> > + }
> > +
> > + data = ops->hw_info(dev, &data_len, type);
> > + if (IS_ERR(data))
> > + return PTR_ERR(data);
> > +
> > + /*
> > + * drivers that have hw_info callback should have a unique
> > + * iommu_hw_info_type.
> > + */
> > + if (WARN_ON_ONCE(*type == IOMMU_HW_INFO_TYPE_NONE)) {
> > + rc = -ENODEV;
> > + goto err_free;
> > + }
> > +
> > + *length = min(*length, data_len);
> > + if (copy_to_user(user_ptr, data, *length)) {
>
> copy_to_user() returns the number of bytes that were successfully
> copied, right?
It returns length on failure and 0 on success
Jason
On Tue, Aug 08, 2023 at 08:35:09AM -0700, Yi Liu wrote:
> +static int iommufd_zero_fill_user(void __user *ptr, size_t bytes)
> +{
> + int index = 0;
> +
> + for (; index < bytes; index++) {
> + if (put_user(0, (uint8_t __user *)(ptr + index)))
> + return -EFAULT;
> + }
I've recently learned this routine is spelled 'clear_user()'
Jason
On 2023/8/10 0:16, Jason Gunthorpe wrote:
> On Wed, Aug 09, 2023 at 06:16:19PM +0800, Baolu Lu wrote:
>> On 2023/8/8 23:35, Yi Liu wrote:
>>> +static int iommufd_fill_hw_info(struct device *dev, void __user *user_ptr,
>>> + unsigned int *length, u32 *type)
>>> +{
>>> + const struct iommu_ops *ops;
>>> + unsigned int data_len;
>>> + void *data;
>>> + int rc = 0;
>>> +
>>> + ops = dev_iommu_ops(dev);
>>> + if (!ops->hw_info) {
>>> + *length = 0;
>>> + *type = IOMMU_HW_INFO_TYPE_NONE;
>>> + return 0;
>>> + }
>>> +
>>> + data = ops->hw_info(dev, &data_len, type);
>>> + if (IS_ERR(data))
>>> + return PTR_ERR(data);
>>> +
>>> + /*
>>> + * drivers that have hw_info callback should have a unique
>>> + * iommu_hw_info_type.
>>> + */
>>> + if (WARN_ON_ONCE(*type == IOMMU_HW_INFO_TYPE_NONE)) {
>>> + rc = -ENODEV;
>>> + goto err_free;
>>> + }
>>> +
>>> + *length = min(*length, data_len);
>>> + if (copy_to_user(user_ptr, data, *length)) {
>> copy_to_user() returns the number of bytes that were successfully
>> copied, right?
> It returns length on failure and 0 on success
Then it's fine. Thanks for the explanation.
Best regards,
baolu
> From: Jason Gunthorpe <jgg@nvidia.com>
> Sent: Thursday, August 10, 2023 12:44 AM
>
> On Tue, Aug 08, 2023 at 08:35:09AM -0700, Yi Liu wrote:
> > +static int iommufd_zero_fill_user(void __user *ptr, size_t bytes)
> > +{
> > + int index = 0;
> > +
> > + for (; index < bytes; index++) {
> > + if (put_user(0, (uint8_t __user *)(ptr + index)))
> > + return -EFAULT;
> > + }
>
> I've recently learned this routine is spelled 'clear_user()'
I see. Will replace with it.
Regards,
Yi Liu
@@ -17,6 +17,7 @@
#include <linux/bug.h>
#include <uapi/linux/iommufd.h>
#include <linux/iommufd.h>
+#include "../iommu-priv.h"
#include "io_pagetable.h"
#include "iommufd_private.h"
@@ -177,6 +178,99 @@ static int iommufd_destroy(struct iommufd_ucmd *ucmd)
return 0;
}
+static int iommufd_zero_fill_user(void __user *ptr, size_t bytes)
+{
+ int index = 0;
+
+ for (; index < bytes; index++) {
+ if (put_user(0, (uint8_t __user *)(ptr + index)))
+ return -EFAULT;
+ }
+ return 0;
+}
+
+static int iommufd_fill_hw_info(struct device *dev, void __user *user_ptr,
+ unsigned int *length, u32 *type)
+{
+ const struct iommu_ops *ops;
+ unsigned int data_len;
+ void *data;
+ int rc = 0;
+
+ ops = dev_iommu_ops(dev);
+ if (!ops->hw_info) {
+ *length = 0;
+ *type = IOMMU_HW_INFO_TYPE_NONE;
+ return 0;
+ }
+
+ data = ops->hw_info(dev, &data_len, type);
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
+ /*
+ * drivers that have hw_info callback should have a unique
+ * iommu_hw_info_type.
+ */
+ if (WARN_ON_ONCE(*type == IOMMU_HW_INFO_TYPE_NONE)) {
+ rc = -ENODEV;
+ goto err_free;
+ }
+
+ *length = min(*length, data_len);
+ if (copy_to_user(user_ptr, data, *length)) {
+ rc = -EFAULT;
+ goto err_free;
+ }
+
+err_free:
+ kfree(data);
+ return rc;
+}
+
+static int iommufd_get_hw_info(struct iommufd_ucmd *ucmd)
+{
+ struct iommu_hw_info *cmd = ucmd->cmd;
+ unsigned int length = cmd->data_len;
+ struct iommufd_device *idev;
+ void __user *user_ptr;
+ u32 hw_info_type;
+ 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);
+
+ user_ptr = u64_to_user_ptr(cmd->data_ptr);
+
+ rc = iommufd_fill_hw_info(idev->dev, user_ptr,
+ &length, &hw_info_type);
+ if (rc)
+ goto err_put;
+
+ /*
+ * 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(user_ptr + length,
+ cmd->data_len - length);
+ if (rc)
+ goto err_put;
+ }
+
+ cmd->data_len = length;
+ cmd->out_data_type = hw_info_type;
+ rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
+
+err_put:
+ iommufd_put_object(&idev->obj);
+ return rc;
+}
+
static int iommufd_fops_open(struct inode *inode, struct file *filp)
{
struct iommufd_ctx *ictx;
@@ -265,6 +359,7 @@ static int iommufd_option(struct iommufd_ucmd *ucmd)
union ucmd_buffer {
struct iommu_destroy destroy;
+ struct iommu_hw_info info;
struct iommu_hwpt_alloc hwpt;
struct iommu_ioas_alloc alloc;
struct iommu_ioas_allow_iovas allow_iovas;
@@ -297,6 +392,8 @@ struct iommufd_ioctl_op {
}
static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
IOCTL_OP(IOMMU_DESTROY, iommufd_destroy, struct iommu_destroy, id),
+ IOCTL_OP(IOMMU_GET_HW_INFO, iommufd_get_hw_info, struct iommu_hw_info,
+ __reserved),
IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc,
__reserved),
IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl,
@@ -46,6 +46,7 @@ enum {
IOMMUFD_CMD_OPTION,
IOMMUFD_CMD_VFIO_IOAS,
IOMMUFD_CMD_HWPT_ALLOC,
+ IOMMUFD_CMD_GET_HW_INFO,
};
/**
@@ -379,4 +380,39 @@ struct iommu_hwpt_alloc {
enum iommu_hw_info_type {
IOMMU_HW_INFO_TYPE_NONE,
};
+
+/**
+ * struct iommu_hw_info - ioctl(IOMMU_GET_HW_INFO)
+ * @size: sizeof(struct iommu_hw_info)
+ * @flags: Must be 0
+ * @dev_id: The device bound to the iommufd
+ * @data_len: Input the length of the user buffer in bytes. Output the length
+ * of data filled in the user buffer.
+ * @data_ptr: Pointer to the user buffer
+ * @out_data_type: Output the iommu hardware info type as defined in the enum
+ * iommu_hw_info_type.
+ * @__reserved: Must be 0
+ *
+ * Query the hardware information from an iommu behind a given device that has
+ * been bound to iommufd. @data_len is the size of the buffer, which captures an
+ * iommu type specific input data and a filled output data. Trailing bytes will
+ * be zeroed if the user buffer is larger than the data kernel has.
+ *
+ * The type specific data would be used to sync capabilities between the virtual
+ * IOMMU and the hardware IOMMU, e.g. a nested translation setup needs to check
+ * the hardware information, so the guest stage-1 page table will be compatible.
+ *
+ * The @out_data_type will be filled if the ioctl succeeds. It would be used to
+ * decode the data filled in the buffer pointed by @data_ptr.
+ */
+struct iommu_hw_info {
+ __u32 size;
+ __u32 flags;
+ __u32 dev_id;
+ __u32 data_len;
+ __aligned_u64 data_ptr;
+ __u32 out_data_type;
+ __u32 __reserved;
+};
+#define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO)
#endif