Merge tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd

Pull iommufd updates from Jason Gunthorpe:
 "Two significant new items:

   - Allow reporting IOMMU HW events to userspace when the events are
     clearly linked to a device.

     This is linked to the VIOMMU object and is intended to be used by a
     VMM to forward HW events to the virtual machine as part of
     emulating a vIOMMU. ARM SMMUv3 is the first driver to use this
     mechanism. Like the existing fault events the data is delivered
     through a simple FD returning event records on read().

   - PASID support in VFIO.

     The "Process Address Space ID" is a PCI feature that allows the
     device to tag all PCI DMA operations with an ID. The IOMMU will
     then use the ID to select a unique translation for those DMAs. This
     is part of Intel's vIOMMU support as VT-D HW requires the
     hypervisor to manage each PASID entry.

     The support is generic so any VFIO user could attach any
     translation to a PASID, and the support should work on ARM SMMUv3
     as well. AMD requires additional driver work.

  Some minor updates, along with fixes:

   - Prevent using nested parents with fault's, no driver support today

   - Put a single "cookie_type" value in the iommu_domain to indicate
     what owns the various opaque owner fields"

* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd: (49 commits)
  iommufd: Test attach before detaching pasid
  iommufd: Fix iommu_vevent_header tables markup
  iommu: Convert unreachable() to BUG()
  iommufd: Balance veventq->num_events inc/dec
  iommufd: Initialize the flags of vevent in iommufd_viommu_report_event()
  iommufd/selftest: Add coverage for reporting max_pasid_log2 via IOMMU_HW_INFO
  iommufd: Extend IOMMU_GET_HW_INFO to report PASID capability
  vfio: VFIO_DEVICE_[AT|DE]TACH_IOMMUFD_PT support pasid
  vfio-iommufd: Support pasid [at|de]tach for physical VFIO devices
  ida: Add ida_find_first_range()
  iommufd/selftest: Add coverage for iommufd pasid attach/detach
  iommufd/selftest: Add test ops to test pasid attach/detach
  iommufd/selftest: Add a helper to get test device
  iommufd/selftest: Add set_dev_pasid in mock iommu
  iommufd: Allow allocating PASID-compatible domain
  iommu/vt-d: Add IOMMU_HWPT_ALLOC_PASID support
  iommufd: Enforce PASID-compatible domain for RID
  iommufd: Support pasid attach/replace
  iommufd: Enforce PASID-compatible domain in PASID path
  iommufd/device: Add pasid_attach array to track per-PASID attach
  ...

7 files changed, 219 insertions, 34 deletions

diff --git a/include/linux/idr.h b/include/linux/idr.h
index cd729be369b3..2267902d29a7 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -274,6 +274,7 @@ struct ida {
 int ida_alloc_range(struct ida *, unsigned int min, unsigned int max, gfp_t);
 void ida_free(struct ida *, unsigned int id);
 void ida_destroy(struct ida *ida);
+int ida_find_first_range(struct ida *ida, unsigned int min, unsigned int max);
 
 /**
  * ida_alloc() - Allocate an unused ID.
@@ -345,4 +346,14 @@ static inline bool ida_is_empty(const struct ida *ida)
 {
 	return xa_empty(&ida->xa);
 }
+
+static inline bool ida_exists(struct ida *ida, unsigned int id)
+{
+	return ida_find_first_range(ida, id, id) == id;
+}
+
+static inline int ida_find_first(struct ida *ida)
+{
+	return ida_find_first_range(ida, 0, ~0);
+}
 #endif /* __IDR_H__ */
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index cf8c16ba04a0..ccce8a751e2a 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -41,6 +41,7 @@ struct iommu_dirty_ops;
 struct notifier_block;
 struct iommu_sva;
 struct iommu_dma_cookie;
+struct iommu_dma_msi_cookie;
 struct iommu_fault_param;
 struct iommufd_ctx;
 struct iommufd_viommu;
@@ -165,6 +166,15 @@ struct iommu_domain_geometry {
 	bool force_aperture;       /* DMA only allowed in mappable range? */
 };
 
+enum iommu_domain_cookie_type {
+	IOMMU_COOKIE_NONE,
+	IOMMU_COOKIE_DMA_IOVA,
+	IOMMU_COOKIE_DMA_MSI,
+	IOMMU_COOKIE_FAULT_HANDLER,
+	IOMMU_COOKIE_SVA,
+	IOMMU_COOKIE_IOMMUFD,
+};
+
 /* Domain feature flags */
 #define __IOMMU_DOMAIN_PAGING	(1U << 0)  /* Support for iommu_map/unmap */
 #define __IOMMU_DOMAIN_DMA_API	(1U << 1)  /* Domain for use in DMA-API
@@ -211,23 +221,18 @@ struct iommu_domain_geometry {
 
 struct iommu_domain {
 	unsigned type;
+	enum iommu_domain_cookie_type cookie_type;
 	const struct iommu_domain_ops *ops;
 	const struct iommu_dirty_ops *dirty_ops;
 	const struct iommu_ops *owner; /* Whose domain_alloc we came from */
 	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
 	struct iommu_domain_geometry geometry;
-	struct iommu_dma_cookie *iova_cookie;
 	int (*iopf_handler)(struct iopf_group *group);
 
-#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU)
-	int (*sw_msi)(struct iommu_domain *domain, struct msi_desc *desc,
-		      phys_addr_t msi_addr);
-#endif
-
-	union { /* Pointer usable by owner of the domain */
-		struct iommufd_hw_pagetable *iommufd_hwpt; /* iommufd */
-	};
-	union { /* Fault handler */
+	union { /* cookie */
+		struct iommu_dma_cookie *iova_cookie;
+		struct iommu_dma_msi_cookie *msi_cookie;
+		struct iommufd_hw_pagetable *iommufd_hwpt;
 		struct {
 			iommu_fault_handler_t handler;
 			void *handler_token;
@@ -244,16 +249,6 @@ struct iommu_domain {
 	};
 };
 
-static inline void iommu_domain_set_sw_msi(
-	struct iommu_domain *domain,
-	int (*sw_msi)(struct iommu_domain *domain, struct msi_desc *desc,
-		      phys_addr_t msi_addr))
-{
-#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU)
-	domain->sw_msi = sw_msi;
-#endif
-}
-
 static inline bool iommu_is_dma_domain(struct iommu_domain *domain)
 {
 	return domain->type & __IOMMU_DOMAIN_DMA_API;
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index 11110c749200..34b6e6ca4bfa 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -8,9 +8,11 @@
 
 #include <linux/err.h>
 #include <linux/errno.h>
+#include <linux/iommu.h>
 #include <linux/refcount.h>
 #include <linux/types.h>
 #include <linux/xarray.h>
+#include <uapi/linux/iommufd.h>
 
 struct device;
 struct file;
@@ -34,6 +36,7 @@ enum iommufd_object_type {
 	IOMMUFD_OBJ_FAULT,
 	IOMMUFD_OBJ_VIOMMU,
 	IOMMUFD_OBJ_VDEVICE,
+	IOMMUFD_OBJ_VEVENTQ,
 #ifdef CONFIG_IOMMUFD_TEST
 	IOMMUFD_OBJ_SELFTEST,
 #endif
@@ -52,9 +55,11 @@ struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx,
 					   struct device *dev, u32 *id);
 void iommufd_device_unbind(struct iommufd_device *idev);
 
-int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id);
-int iommufd_device_replace(struct iommufd_device *idev, u32 *pt_id);
-void iommufd_device_detach(struct iommufd_device *idev);
+int iommufd_device_attach(struct iommufd_device *idev, ioasid_t pasid,
+			  u32 *pt_id);
+int iommufd_device_replace(struct iommufd_device *idev, ioasid_t pasid,
+			   u32 *pt_id);
+void iommufd_device_detach(struct iommufd_device *idev, ioasid_t pasid);
 
 struct iommufd_ctx *iommufd_device_to_ictx(struct iommufd_device *idev);
 u32 iommufd_device_to_id(struct iommufd_device *idev);
@@ -93,6 +98,8 @@ struct iommufd_viommu {
 	const struct iommufd_viommu_ops *ops;
 
 	struct xarray vdevs;
+	struct list_head veventqs;
+	struct rw_semaphore veventqs_rwsem;
 
 	unsigned int type;
 };
@@ -187,6 +194,11 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
 					     enum iommufd_object_type type);
 struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
 				       unsigned long vdev_id);
+int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu,
+			       struct device *dev, unsigned long *vdev_id);
+int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
+				enum iommu_veventq_type type, void *event_data,
+				size_t data_len);
 #else /* !CONFIG_IOMMUFD_DRIVER_CORE */
 static inline struct iommufd_object *
 _iommufd_object_alloc(struct iommufd_ctx *ictx, size_t size,
@@ -200,6 +212,20 @@ iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id)
 {
 	return NULL;
 }
+
+static inline int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu,
+					     struct device *dev,
+					     unsigned long *vdev_id)
+{
+	return -ENOENT;
+}
+
+static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
+					      enum iommu_veventq_type type,
+					      void *event_data, size_t data_len)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_IOMMUFD_DRIVER_CORE */
 
 /*
diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h
index 0e8b74e63767..75c6c86cf09d 100644
--- a/include/linux/pci-ats.h
+++ b/include/linux/pci-ats.h
@@ -42,6 +42,7 @@ int pci_enable_pasid(struct pci_dev *pdev, int features);
 void pci_disable_pasid(struct pci_dev *pdev);
 int pci_pasid_features(struct pci_dev *pdev);
 int pci_max_pasids(struct pci_dev *pdev);
+int pci_pasid_status(struct pci_dev *pdev);
 #else /* CONFIG_PCI_PASID */
 static inline int pci_enable_pasid(struct pci_dev *pdev, int features)
 { return -EINVAL; }
@@ -50,6 +51,8 @@ static inline int pci_pasid_features(struct pci_dev *pdev)
 { return -EINVAL; }
 static inline int pci_max_pasids(struct pci_dev *pdev)
 { return -EINVAL; }
+static inline int pci_pasid_status(struct pci_dev *pdev)
+{ return -EINVAL; }
 #endif /* CONFIG_PCI_PASID */
 
 #endif /* LINUX_PCI_ATS_H */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 000a6cab2d31..707b00772ce1 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -67,6 +67,7 @@ struct vfio_device {
 	struct inode *inode;
 #if IS_ENABLED(CONFIG_IOMMUFD)
 	struct iommufd_device *iommufd_device;
+	struct ida pasids;
 	u8 iommufd_attached:1;
 #endif
 	u8 cdev_opened:1;
@@ -91,6 +92,8 @@ struct vfio_device {
  *		 bound iommufd. Undo in unbind_iommufd if @detach_ioas is not
  *		 called.
  * @detach_ioas: Opposite of attach_ioas
+ * @pasid_attach_ioas: The pasid variation of attach_ioas
+ * @pasid_detach_ioas: Opposite of pasid_attach_ioas
  * @open_device: Called when the first file descriptor is opened for this device
  * @close_device: Opposite of open_device
  * @read: Perform read(2) on device file descriptor
@@ -115,6 +118,9 @@ struct vfio_device_ops {
 	void	(*unbind_iommufd)(struct vfio_device *vdev);
 	int	(*attach_ioas)(struct vfio_device *vdev, u32 *pt_id);
 	void	(*detach_ioas)(struct vfio_device *vdev);
+	int	(*pasid_attach_ioas)(struct vfio_device *vdev, u32 pasid,
+				     u32 *pt_id);
+	void	(*pasid_detach_ioas)(struct vfio_device *vdev, u32 pasid);
 	int	(*open_device)(struct vfio_device *vdev);
 	void	(*close_device)(struct vfio_device *vdev);
 	ssize_t	(*read)(struct vfio_device *vdev, char __user *buf,
@@ -139,6 +145,10 @@ int vfio_iommufd_physical_bind(struct vfio_device *vdev,
 void vfio_iommufd_physical_unbind(struct vfio_device *vdev);
 int vfio_iommufd_physical_attach_ioas(struct vfio_device *vdev, u32 *pt_id);
 void vfio_iommufd_physical_detach_ioas(struct vfio_device *vdev);
+int vfio_iommufd_physical_pasid_attach_ioas(struct vfio_device *vdev,
+					    u32 pasid, u32 *pt_id);
+void vfio_iommufd_physical_pasid_detach_ioas(struct vfio_device *vdev,
+					     u32 pasid);
 int vfio_iommufd_emulated_bind(struct vfio_device *vdev,
 			       struct iommufd_ctx *ictx, u32 *out_device_id);
 void vfio_iommufd_emulated_unbind(struct vfio_device *vdev);
@@ -166,6 +176,10 @@ vfio_iommufd_get_dev_id(struct vfio_device *vdev, struct iommufd_ctx *ictx)
 	((int (*)(struct vfio_device *vdev, u32 *pt_id)) NULL)
 #define vfio_iommufd_physical_detach_ioas \
 	((void (*)(struct vfio_device *vdev)) NULL)
+#define vfio_iommufd_physical_pasid_attach_ioas \
+	((int (*)(struct vfio_device *vdev, u32 pasid, u32 *pt_id)) NULL)
+#define vfio_iommufd_physical_pasid_detach_ioas \
+	((void (*)(struct vfio_device *vdev, u32 pasid)) NULL)
 #define vfio_iommufd_emulated_bind                                      \
 	((int (*)(struct vfio_device *vdev, struct iommufd_ctx *ictx,   \
 		  u32 *out_device_id)) NULL)
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 78747b24bd0f..f29b6c44655e 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -55,6 +55,7 @@ enum {
 	IOMMUFD_CMD_VIOMMU_ALLOC = 0x90,
 	IOMMUFD_CMD_VDEVICE_ALLOC = 0x91,
 	IOMMUFD_CMD_IOAS_CHANGE_PROCESS = 0x92,
+	IOMMUFD_CMD_VEVENTQ_ALLOC = 0x93,
 };
 
 /**
@@ -392,6 +393,9 @@ struct iommu_vfio_ioas {
  *                          Any domain attached to the non-PASID part of the
  *                          device must also be flagged, otherwise attaching a
  *                          PASID will blocked.
+ *                          For the user that wants to attach PASID, ioas is
+ *                          not recommended for both the non-PASID part
+ *                          and PASID part of the device.
  *                          If IOMMU does not support PASID it will return
  *                          error (-EOPNOTSUPP).
  */
@@ -608,9 +612,17 @@ enum iommu_hw_info_type {
  *                                   IOMMU_HWPT_GET_DIRTY_BITMAP
  *                                   IOMMU_HWPT_SET_DIRTY_TRACKING
  *
+ * @IOMMU_HW_CAP_PCI_PASID_EXEC: Execute Permission Supported, user ignores it
+ *                               when the struct
+ *                               iommu_hw_info::out_max_pasid_log2 is zero.
+ * @IOMMU_HW_CAP_PCI_PASID_PRIV: Privileged Mode Supported, user ignores it
+ *                               when the struct
+ *                               iommu_hw_info::out_max_pasid_log2 is zero.
  */
 enum iommufd_hw_capabilities {
 	IOMMU_HW_CAP_DIRTY_TRACKING = 1 << 0,
+	IOMMU_HW_CAP_PCI_PASID_EXEC = 1 << 1,
+	IOMMU_HW_CAP_PCI_PASID_PRIV = 1 << 2,
 };
 
 /**
@@ -626,6 +638,9 @@ enum iommufd_hw_capabilities {
  *                 iommu_hw_info_type.
  * @out_capabilities: Output the generic iommu capability info type as defined
  *                    in the enum iommu_hw_capabilities.
+ * @out_max_pasid_log2: Output the width of PASIDs. 0 means no PASID support.
+ *                      PCI devices turn to out_capabilities to check if the
+ *                      specific capabilities is supported or not.
  * @__reserved: Must be 0
  *
  * Query an iommu type specific hardware information data from an iommu behind
@@ -649,7 +664,8 @@ struct iommu_hw_info {
 	__u32 data_len;
 	__aligned_u64 data_uptr;
 	__u32 out_data_type;
-	__u32 __reserved;
+	__u8 out_max_pasid_log2;
+	__u8 __reserved[3];
 	__aligned_u64 out_capabilities;
 };
 #define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO)
@@ -1014,4 +1030,115 @@ struct iommu_ioas_change_process {
 #define IOMMU_IOAS_CHANGE_PROCESS \
 	_IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_CHANGE_PROCESS)
 
+/**
+ * enum iommu_veventq_flag - flag for struct iommufd_vevent_header
+ * @IOMMU_VEVENTQ_FLAG_LOST_EVENTS: vEVENTQ has lost vEVENTs
+ */
+enum iommu_veventq_flag {
+	IOMMU_VEVENTQ_FLAG_LOST_EVENTS = (1U << 0),
+};
+
+/**
+ * struct iommufd_vevent_header - Virtual Event Header for a vEVENTQ Status
+ * @flags: Combination of enum iommu_veventq_flag
+ * @sequence: The sequence index of a vEVENT in the vEVENTQ, with a range of
+ *            [0, INT_MAX] where the following index of INT_MAX is 0
+ *
+ * Each iommufd_vevent_header reports a sequence index of the following vEVENT:
+ *
+ * +----------------------+-------+----------------------+-------+---+-------+
+ * | header0 {sequence=0} | data0 | header1 {sequence=1} | data1 |...| dataN |
+ * +----------------------+-------+----------------------+-------+---+-------+
+ *
+ * And this sequence index is expected to be monotonic to the sequence index of
+ * the previous vEVENT. If two adjacent sequence indexes has a delta larger than
+ * 1, it means that delta - 1 number of vEVENTs has lost, e.g. two lost vEVENTs:
+ *
+ * +-----+----------------------+-------+----------------------+-------+-----+
+ * | ... | header3 {sequence=3} | data3 | header6 {sequence=6} | data6 | ... |
+ * +-----+----------------------+-------+----------------------+-------+-----+
+ *
+ * If a vEVENT lost at the tail of the vEVENTQ and there is no following vEVENT
+ * providing the next sequence index, an IOMMU_VEVENTQ_FLAG_LOST_EVENTS header
+ * would be added to the tail, and no data would follow this header:
+ *
+ * +--+----------------------+-------+-----------------------------------------+
+ * |..| header3 {sequence=3} | data3 | header4 {flags=LOST_EVENTS, sequence=4} |
+ * +--+----------------------+-------+-----------------------------------------+
+ */
+struct iommufd_vevent_header {
+	__u32 flags;
+	__u32 sequence;
+};
+
+/**
+ * enum iommu_veventq_type - Virtual Event Queue Type
+ * @IOMMU_VEVENTQ_TYPE_DEFAULT: Reserved for future use
+ * @IOMMU_VEVENTQ_TYPE_ARM_SMMUV3: ARM SMMUv3 Virtual Event Queue
+ */
+enum iommu_veventq_type {
+	IOMMU_VEVENTQ_TYPE_DEFAULT = 0,
+	IOMMU_VEVENTQ_TYPE_ARM_SMMUV3 = 1,
+};
+
+/**
+ * struct iommu_vevent_arm_smmuv3 - ARM SMMUv3 Virtual Event
+ *                                  (IOMMU_VEVENTQ_TYPE_ARM_SMMUV3)
+ * @evt: 256-bit ARM SMMUv3 Event record, little-endian.
+ *       Reported event records: (Refer to "7.3 Event records" in SMMUv3 HW Spec)
+ *       - 0x04 C_BAD_STE
+ *       - 0x06 F_STREAM_DISABLED
+ *       - 0x08 C_BAD_SUBSTREAMID
+ *       - 0x0a C_BAD_CD
+ *       - 0x10 F_TRANSLATION
+ *       - 0x11 F_ADDR_SIZE
+ *       - 0x12 F_ACCESS
+ *       - 0x13 F_PERMISSION
+ *
+ * StreamID field reports a virtual device ID. To receive a virtual event for a
+ * device, a vDEVICE must be allocated via IOMMU_VDEVICE_ALLOC.
+ */
+struct iommu_vevent_arm_smmuv3 {
+	__aligned_le64 evt[4];
+};
+
+/**
+ * struct iommu_veventq_alloc - ioctl(IOMMU_VEVENTQ_ALLOC)
+ * @size: sizeof(struct iommu_veventq_alloc)
+ * @flags: Must be 0
+ * @viommu_id: virtual IOMMU ID to associate the vEVENTQ with
+ * @type: Type of the vEVENTQ. Must be defined in enum iommu_veventq_type
+ * @veventq_depth: Maximum number of events in the vEVENTQ
+ * @out_veventq_id: The ID of the new vEVENTQ
+ * @out_veventq_fd: The fd of the new vEVENTQ. User space must close the
+ *                  successfully returned fd after using it
+ * @__reserved: Must be 0
+ *
+ * Explicitly allocate a virtual event queue interface for a vIOMMU. A vIOMMU
+ * can have multiple FDs for different types, but is confined to one per @type.
+ * User space should open the @out_veventq_fd to read vEVENTs out of a vEVENTQ,
+ * if there are vEVENTs available. A vEVENTQ will lose events due to overflow,
+ * if the number of the vEVENTs hits @veventq_depth.
+ *
+ * Each vEVENT in a vEVENTQ encloses a struct iommufd_vevent_header followed by
+ * a type-specific data structure, in a normal case:
+ *
+ * +-+---------+-------+---------+-------+-----+---------+-------+-+
+ * | | header0 | data0 | header1 | data1 | ... | headerN | dataN | |
+ * +-+---------+-------+---------+-------+-----+---------+-------+-+
+ *
+ * unless a tailing IOMMU_VEVENTQ_FLAG_LOST_EVENTS header is logged (refer to
+ * struct iommufd_vevent_header).
+ */
+struct iommu_veventq_alloc {
+	__u32 size;
+	__u32 flags;
+	__u32 viommu_id;
+	__u32 type;
+	__u32 veventq_depth;
+	__u32 out_veventq_id;
+	__u32 out_veventq_fd;
+	__u32 __reserved;
+};
+#define IOMMU_VEVENTQ_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VEVENTQ_ALLOC)
 #endif
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index a2d3e1ac6239..5764f315137f 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -932,29 +932,34 @@ struct vfio_device_bind_iommufd {
  * VFIO_DEVICE_ATTACH_IOMMUFD_PT - _IOW(VFIO_TYPE, VFIO_BASE + 19,
  *					struct vfio_device_attach_iommufd_pt)
  * @argsz:	User filled size of this data.
- * @flags:	Must be 0.
+ * @flags:	Flags for attach.
  * @pt_id:	Input the target id which can represent an ioas or a hwpt
  *		allocated via iommufd subsystem.
  *		Output the input ioas id or the attached hwpt id which could
  *		be the specified hwpt itself or a hwpt automatically created
  *		for the specified ioas by kernel during the attachment.
+ * @pasid:	The pasid to be attached, only meaningful when
+ *		VFIO_DEVICE_ATTACH_PASID is set in @flags
  *
  * Associate the device with an address space within the bound iommufd.
  * Undo by VFIO_DEVICE_DETACH_IOMMUFD_PT or device fd close.  This is only
  * allowed on cdev fds.
  *
- * If a vfio device is currently attached to a valid hw_pagetable, without doing
- * a VFIO_DEVICE_DETACH_IOMMUFD_PT, a second VFIO_DEVICE_ATTACH_IOMMUFD_PT ioctl
- * passing in another hw_pagetable (hwpt) id is allowed. This action, also known
- * as a hw_pagetable replacement, will replace the device's currently attached
- * hw_pagetable with a new hw_pagetable corresponding to the given pt_id.
+ * If a vfio device or a pasid of this device is currently attached to a valid
+ * hw_pagetable (hwpt), without doing a VFIO_DEVICE_DETACH_IOMMUFD_PT, a second
+ * VFIO_DEVICE_ATTACH_IOMMUFD_PT ioctl passing in another hwpt id is allowed.
+ * This action, also known as a hw_pagetable replacement, will replace the
+ * currently attached hwpt of the device or the pasid of this device with a new
+ * hwpt corresponding to the given pt_id.
  *
  * Return: 0 on success, -errno on failure.
  */
 struct vfio_device_attach_iommufd_pt {
 	__u32	argsz;
 	__u32	flags;
+#define VFIO_DEVICE_ATTACH_PASID	(1 << 0)
 	__u32	pt_id;
+	__u32	pasid;
 };
 
 #define VFIO_DEVICE_ATTACH_IOMMUFD_PT		_IO(VFIO_TYPE, VFIO_BASE + 19)
@@ -963,17 +968,21 @@ struct vfio_device_attach_iommufd_pt {
  * VFIO_DEVICE_DETACH_IOMMUFD_PT - _IOW(VFIO_TYPE, VFIO_BASE + 20,
  *					struct vfio_device_detach_iommufd_pt)
  * @argsz:	User filled size of this data.
- * @flags:	Must be 0.
+ * @flags:	Flags for detach.
+ * @pasid:	The pasid to be detached, only meaningful when
+ *		VFIO_DEVICE_DETACH_PASID is set in @flags
  *
- * Remove the association of the device and its current associated address
- * space.  After it, the device should be in a blocking DMA state.  This is only
- * allowed on cdev fds.
+ * Remove the association of the device or a pasid of the device and its current
+ * associated address space.  After it, the device or the pasid should be in a
+ * blocking DMA state.  This is only allowed on cdev fds.
  *
  * Return: 0 on success, -errno on failure.
  */
 struct vfio_device_detach_iommufd_pt {
 	__u32	argsz;
 	__u32	flags;
+#define VFIO_DEVICE_DETACH_PASID	(1 << 0)
+	__u32	pasid;
 };
 
 #define VFIO_DEVICE_DETACH_IOMMUFD_PT		_IO(VFIO_TYPE, VFIO_BASE + 20)