[PATCH v9 3/5] iommufd: Add IOMMU_GET_HW_INFO

[Yi Liu]

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 by the output
@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@xxxxxxxxxxxxxxx>
Reviewed-by: Kevin Tian <kevin.tian@xxxxxxxxx>
Co-developed-by: Nicolin Chen <nicolinc@xxxxxxxxxx>
Signed-off-by: Nicolin Chen <nicolinc@xxxxxxxxxx>
Signed-off-by: Yi Liu <yi.l.liu@xxxxxxxxx>
---
 drivers/iommu/iommufd/device.c          | 73 +++++++++++++++++++++++++
 drivers/iommu/iommufd/iommufd_private.h |  1 +
 drivers/iommu/iommufd/main.c            |  3 +
 include/uapi/linux/iommufd.h            | 39 +++++++++++++
 4 files changed, 116 insertions(+)

diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index 90f88c295ce0..ce78c3671539 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -4,6 +4,7 @@
 #include <linux/iommufd.h>
 #include <linux/slab.h>
 #include <linux/iommu.h>
+#include <uapi/linux/iommufd.h>
 #include "../iommu-priv.h"
 
 #include "io_pagetable.h"
@@ -1119,3 +1120,75 @@ int iommufd_access_rw(struct iommufd_access *access, unsigned long iova,
 	return rc;
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_access_rw, IOMMUFD);
+
+int iommufd_get_hw_info(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_hw_info *cmd = ucmd->cmd;
+	void __user *user_ptr = u64_to_user_ptr(cmd->data_uptr);
+	const struct iommu_ops *ops;
+	struct iommufd_device *idev;
+	unsigned int data_len;
+	unsigned int copy_len;
+	void *data;
+	int rc;
+
+	if (cmd->flags || cmd->__reserved)
+		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) {
+		data = ops->hw_info(idev->dev, &data_len, &cmd->out_data_type);
+		if (IS_ERR(data)) {
+			rc = PTR_ERR(data);
+			goto out_put;
+		}
+
+		/*
+		 * drivers that have hw_info callback should have a unique
+		 * iommu_hw_info_type.
+		 */
+		if (WARN_ON_ONCE(cmd->out_data_type ==
+				 IOMMU_HW_INFO_TYPE_NONE)) {
+			rc = -ENODEV;
+			goto out_free;
+		}
+	} else {
+		cmd->out_data_type = IOMMU_HW_INFO_TYPE_NONE;
+		data_len = 0;
+		data = NULL;
+	}
+
+	copy_len = min(cmd->data_len, data_len);
+	if (copy_to_user(user_ptr, data, copy_len)) {
+		rc = -EFAULT;
+		goto out_free;
+	}
+
+	/*
+	 * Zero the trailing bytes if the user buffer is bigger than the
+	 * data size kernel actually has.
+	 */
+	if (copy_len < cmd->data_len) {
+		if (clear_user(user_ptr + copy_len, cmd->data_len - copy_len)) {
+			rc = -EFAULT;
+			goto out_free;
+		}
+	}
+
+	/*
+	 * We return the length the kernel supports so userspace may know what
+	 * the kernel capability is. It could be larger than the input buffer.
+	 */
+	cmd->data_len = data_len;
+
+	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
+out_free:
+	kfree(data);
+out_put:
+	iommufd_put_object(&idev->obj);
+	return rc;
+}
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 5a45b8ba2e26..2c58670011fe 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -296,6 +296,7 @@ iommufd_get_device(struct iommufd_ucmd *ucmd, u32 id)
 }
 
 void iommufd_device_destroy(struct iommufd_object *obj);
+int iommufd_get_hw_info(struct iommufd_ucmd *ucmd);
 
 struct iommufd_access {
 	struct iommufd_object obj;
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 5f7e9fa45502..e71523cbd0de 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -305,6 +305,7 @@ 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;
@@ -337,6 +338,8 @@ 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,
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index ac11ace21edb..e01d5ac00dc3 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -46,6 +46,7 @@ enum {
 	IOMMUFD_CMD_OPTION,
 	IOMMUFD_CMD_VFIO_IOAS,
 	IOMMUFD_CMD_HWPT_ALLOC,
+	IOMMUFD_CMD_GET_HW_INFO,
 };
 
 /**
@@ -379,4 +380,42 @@ 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 a user buffer in bytes. Output the length of
+ *            data that kernel supports
+ * @data_uptr: User pointer to a user-space buffer used by the kernel to fill
+ *             the iommu type specific hardware information data
+ * @out_data_type: Output the iommu hardware info type as defined in the enum
+ *                 iommu_hw_info_type.
+ * @__reserved: Must be 0
+ *
+ * Query an iommu type specific hardware information data from an iommu behind
+ * a given device that has been bound to iommufd. This hardware info data will
+ * be used to sync capabilities between the virtual iommu and the physical
+ * iommu, e.g. a nested translation setup needs to check the hardware info, so
+ * a guest stage-1 page table can be compatible with the physical iommu.
+ *
+ * To capture an iommu type specific hardware information data, @data_uptr and
+ * its length @data_len must be provided. Trailing bytes will be zeroed if the
+ * user buffer is larger than the data that kernel has. Otherwise, kernel only
+ * fills the buffer using the given length in @data_len. If the ioctl succeeds,
+ * @data_len will be updated to the length that kernel actually supports,
+ * @out_data_type will be filled to decode the data filled in the buffer
+ * pointed by @data_uptr. Input @data_len == zero is allowed.
+ */
+struct iommu_hw_info {
+	__u32 size;
+	__u32 flags;
+	__u32 dev_id;
+	__u32 data_len;
+	__aligned_u64 data_uptr;
+	__u32 out_data_type;
+	__u32 __reserved;
+};
+#define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO)
 #endif
-- 
2.34.1