Merge tag 'vfio-v6.6-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - VFIO direct character device (cdev) interface support. This extracts
   the vfio device fd from the container and group model, and is
   intended to be the native uAPI for use with IOMMUFD (Yi Liu)

 - Enhancements to the PCI hot reset interface in support of cdev usage
   (Yi Liu)

 - Fix a potential race between registering and unregistering vfio files
   in the kvm-vfio interface and extend use of a lock to avoid extra
   drop and acquires (Dmitry Torokhov)

 - A new vfio-pci variant driver for the AMD/Pensando Distributed
   Services Card (PDS) Ethernet device, supporting live migration (Brett
   Creeley)

 - Cleanups to remove redundant owner setup in cdx and fsl bus drivers,
   and simplify driver init/exit in fsl code (Li Zetao)

 - Fix uninitialized hole in data structure and pad capability
   structures for alignment (Stefan Hajnoczi)

* tag 'vfio-v6.6-rc1' of https://github.com/awilliam/linux-vfio: (53 commits)
  vfio/pds: Send type for SUSPEND_STATUS command
  vfio/pds: fix return value in pds_vfio_get_lm_file()
  pds_core: Fix function header descriptions
  vfio: align capability structures
  vfio/type1: fix cap_migration information leak
  vfio/fsl-mc: Use module_fsl_mc_driver macro to simplify the code
  vfio/cdx: Remove redundant initialization owner in vfio_cdx_driver
  vfio/pds: Add Kconfig and documentation
  vfio/pds: Add support for firmware recovery
  vfio/pds: Add support for dirty page tracking
  vfio/pds: Add VFIO live migration support
  vfio/pds: register with the pds_core PF
  pds_core: Require callers of register/unregister to pass PF drvdata
  vfio/pds: Initial support for pds VFIO driver
  vfio: Commonize combine_ranges for use in other VFIO drivers
  kvm/vfio: avoid bouncing the mutex when adding and deleting groups
  kvm/vfio: ensure kvg instance stays around in kvm_vfio_group_add()
  docs: vfio: Add vfio device cdev description
  vfio: Compile vfio_group infrastructure optionally
  vfio: Move the IOMMU_CAP_CACHE_COHERENCY check in __vfio_register_dev()
  ...

6 files changed, 605 insertions, 12 deletions

diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index 1129a36a74c4..9657c58813dc 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -16,6 +16,7 @@ struct page;
 struct iommufd_ctx;
 struct iommufd_access;
 struct file;
+struct iommu_group;
 
 struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx,
 					   struct device *dev, u32 *id);
@@ -24,6 +25,9 @@ void iommufd_device_unbind(struct iommufd_device *idev);
 int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id);
 void iommufd_device_detach(struct iommufd_device *idev);
 
+struct iommufd_ctx *iommufd_device_to_ictx(struct iommufd_device *idev);
+u32 iommufd_device_to_id(struct iommufd_device *idev);
+
 struct iommufd_access_ops {
 	u8 needs_pin_pages : 1;
 	void (*unmap)(void *data, unsigned long iova, unsigned long length);
@@ -44,12 +48,15 @@ iommufd_access_create(struct iommufd_ctx *ictx,
 		      const struct iommufd_access_ops *ops, void *data, u32 *id);
 void iommufd_access_destroy(struct iommufd_access *access);
 int iommufd_access_attach(struct iommufd_access *access, u32 ioas_id);
+void iommufd_access_detach(struct iommufd_access *access);
 
 void iommufd_ctx_get(struct iommufd_ctx *ictx);
 
 #if IS_ENABLED(CONFIG_IOMMUFD)
 struct iommufd_ctx *iommufd_ctx_from_file(struct file *file);
+struct iommufd_ctx *iommufd_ctx_from_fd(int fd);
 void iommufd_ctx_put(struct iommufd_ctx *ictx);
+bool iommufd_ctx_has_group(struct iommufd_ctx *ictx, struct iommu_group *group);
 
 int iommufd_access_pin_pages(struct iommufd_access *access, unsigned long iova,
 			     unsigned long length, struct page **out_pages,
diff --git a/include/linux/pds/pds_adminq.h b/include/linux/pds/pds_adminq.h
index bcba7fda3cc9..4b4e9a98b37b 100644
--- a/include/linux/pds/pds_adminq.h
+++ b/include/linux/pds/pds_adminq.h
@@ -818,6 +818,367 @@ struct pds_vdpa_set_features_cmd {
 	__le64 features;
 };
 
+#define PDS_LM_DEVICE_STATE_LENGTH		65536
+#define PDS_LM_CHECK_DEVICE_STATE_LENGTH(X) \
+			PDS_CORE_SIZE_CHECK(union, PDS_LM_DEVICE_STATE_LENGTH, X)
+
+/*
+ * enum pds_lm_cmd_opcode - Live Migration Device commands
+ */
+enum pds_lm_cmd_opcode {
+	PDS_LM_CMD_HOST_VF_STATUS  = 1,
+
+	/* Device state commands */
+	PDS_LM_CMD_STATE_SIZE	   = 16,
+	PDS_LM_CMD_SUSPEND         = 18,
+	PDS_LM_CMD_SUSPEND_STATUS  = 19,
+	PDS_LM_CMD_RESUME          = 20,
+	PDS_LM_CMD_SAVE            = 21,
+	PDS_LM_CMD_RESTORE         = 22,
+
+	/* Dirty page tracking commands */
+	PDS_LM_CMD_DIRTY_STATUS    = 32,
+	PDS_LM_CMD_DIRTY_ENABLE    = 33,
+	PDS_LM_CMD_DIRTY_DISABLE   = 34,
+	PDS_LM_CMD_DIRTY_READ_SEQ  = 35,
+	PDS_LM_CMD_DIRTY_WRITE_ACK = 36,
+};
+
+/**
+ * struct pds_lm_cmd - generic command
+ * @opcode:	Opcode
+ * @rsvd:	Word boundary padding
+ * @vf_id:	VF id
+ * @rsvd2:	Structure padding to 60 Bytes
+ */
+struct pds_lm_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 vf_id;
+	u8     rsvd2[56];
+};
+
+/**
+ * struct pds_lm_state_size_cmd - STATE_SIZE command
+ * @opcode:	Opcode
+ * @rsvd:	Word boundary padding
+ * @vf_id:	VF id
+ */
+struct pds_lm_state_size_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 vf_id;
+};
+
+/**
+ * struct pds_lm_state_size_comp - STATE_SIZE command completion
+ * @status:		Status of the command (enum pds_core_status_code)
+ * @rsvd:		Word boundary padding
+ * @comp_index:		Index in the desc ring for which this is the completion
+ * @size:		Size of the device state
+ * @rsvd2:		Word boundary padding
+ * @color:		Color bit
+ */
+struct pds_lm_state_size_comp {
+	u8     status;
+	u8     rsvd;
+	__le16 comp_index;
+	union {
+		__le64 size;
+		u8     rsvd2[11];
+	} __packed;
+	u8     color;
+};
+
+enum pds_lm_suspend_resume_type {
+	PDS_LM_SUSPEND_RESUME_TYPE_FULL = 0,
+	PDS_LM_SUSPEND_RESUME_TYPE_P2P = 1,
+};
+
+/**
+ * struct pds_lm_suspend_cmd - SUSPEND command
+ * @opcode:	Opcode PDS_LM_CMD_SUSPEND
+ * @rsvd:	Word boundary padding
+ * @vf_id:	VF id
+ * @type:	Type of suspend (enum pds_lm_suspend_resume_type)
+ */
+struct pds_lm_suspend_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 vf_id;
+	u8     type;
+};
+
+/**
+ * struct pds_lm_suspend_status_cmd - SUSPEND status command
+ * @opcode:	Opcode PDS_AQ_CMD_LM_SUSPEND_STATUS
+ * @rsvd:	Word boundary padding
+ * @vf_id:	VF id
+ * @type:	Type of suspend (enum pds_lm_suspend_resume_type)
+ */
+struct pds_lm_suspend_status_cmd {
+	u8 opcode;
+	u8 rsvd;
+	__le16 vf_id;
+	u8 type;
+};
+
+/**
+ * struct pds_lm_resume_cmd - RESUME command
+ * @opcode:	Opcode PDS_LM_CMD_RESUME
+ * @rsvd:	Word boundary padding
+ * @vf_id:	VF id
+ * @type:	Type of resume (enum pds_lm_suspend_resume_type)
+ */
+struct pds_lm_resume_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 vf_id;
+	u8     type;
+};
+
+/**
+ * struct pds_lm_sg_elem - Transmit scatter-gather (SG) descriptor element
+ * @addr:	DMA address of SG element data buffer
+ * @len:	Length of SG element data buffer, in bytes
+ * @rsvd:	Word boundary padding
+ */
+struct pds_lm_sg_elem {
+	__le64 addr;
+	__le32 len;
+	__le16 rsvd[2];
+};
+
+/**
+ * struct pds_lm_save_cmd - SAVE command
+ * @opcode:	Opcode PDS_LM_CMD_SAVE
+ * @rsvd:	Word boundary padding
+ * @vf_id:	VF id
+ * @rsvd2:	Word boundary padding
+ * @sgl_addr:	IOVA address of the SGL to dma the device state
+ * @num_sge:	Total number of SG elements
+ */
+struct pds_lm_save_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 vf_id;
+	u8     rsvd2[4];
+	__le64 sgl_addr;
+	__le32 num_sge;
+} __packed;
+
+/**
+ * struct pds_lm_restore_cmd - RESTORE command
+ * @opcode:	Opcode PDS_LM_CMD_RESTORE
+ * @rsvd:	Word boundary padding
+ * @vf_id:	VF id
+ * @rsvd2:	Word boundary padding
+ * @sgl_addr:	IOVA address of the SGL to dma the device state
+ * @num_sge:	Total number of SG elements
+ */
+struct pds_lm_restore_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 vf_id;
+	u8     rsvd2[4];
+	__le64 sgl_addr;
+	__le32 num_sge;
+} __packed;
+
+/**
+ * union pds_lm_dev_state - device state information
+ * @words:	Device state words
+ */
+union pds_lm_dev_state {
+	__le32 words[PDS_LM_DEVICE_STATE_LENGTH / sizeof(__le32)];
+};
+
+enum pds_lm_host_vf_status {
+	PDS_LM_STA_NONE = 0,
+	PDS_LM_STA_IN_PROGRESS,
+	PDS_LM_STA_MAX,
+};
+
+/**
+ * struct pds_lm_dirty_region_info - Memory region info for STATUS and ENABLE
+ * @dma_base:		Base address of the DMA-contiguous memory region
+ * @page_count:		Number of pages in the memory region
+ * @page_size_log2:	Log2 page size in the memory region
+ * @rsvd:		Word boundary padding
+ */
+struct pds_lm_dirty_region_info {
+	__le64 dma_base;
+	__le32 page_count;
+	u8     page_size_log2;
+	u8     rsvd[3];
+};
+
+/**
+ * struct pds_lm_dirty_status_cmd - DIRTY_STATUS command
+ * @opcode:		Opcode PDS_LM_CMD_DIRTY_STATUS
+ * @rsvd:		Word boundary padding
+ * @vf_id:		VF id
+ * @max_regions:	Capacity of the region info buffer
+ * @rsvd2:		Word boundary padding
+ * @regions_dma:	DMA address of the region info buffer
+ *
+ * The minimum of max_regions (from the command) and num_regions (from the
+ * completion) of struct pds_lm_dirty_region_info will be written to
+ * regions_dma.
+ *
+ * The max_regions may be zero, in which case regions_dma is ignored.  In that
+ * case, the completion will only report the maximum number of regions
+ * supported by the device, and the number of regions currently enabled.
+ */
+struct pds_lm_dirty_status_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 vf_id;
+	u8     max_regions;
+	u8     rsvd2[3];
+	__le64 regions_dma;
+} __packed;
+
+/**
+ * enum pds_lm_dirty_bmp_type - Type of dirty page bitmap
+ * @PDS_LM_DIRTY_BMP_TYPE_NONE: No bitmap / disabled
+ * @PDS_LM_DIRTY_BMP_TYPE_SEQ_ACK: Seq/Ack bitmap representation
+ */
+enum pds_lm_dirty_bmp_type {
+	PDS_LM_DIRTY_BMP_TYPE_NONE     = 0,
+	PDS_LM_DIRTY_BMP_TYPE_SEQ_ACK  = 1,
+};
+
+/**
+ * struct pds_lm_dirty_status_comp - STATUS command completion
+ * @status:		Status of the command (enum pds_core_status_code)
+ * @rsvd:		Word boundary padding
+ * @comp_index:		Index in the desc ring for which this is the completion
+ * @max_regions:	Maximum number of regions supported by the device
+ * @num_regions:	Number of regions currently enabled
+ * @bmp_type:		Type of dirty bitmap representation
+ * @rsvd2:		Word boundary padding
+ * @bmp_type_mask:	Mask of supported bitmap types, bit index per type
+ * @rsvd3:		Word boundary padding
+ * @color:		Color bit
+ *
+ * This completion descriptor is used for STATUS, ENABLE, and DISABLE.
+ */
+struct pds_lm_dirty_status_comp {
+	u8     status;
+	u8     rsvd;
+	__le16 comp_index;
+	u8     max_regions;
+	u8     num_regions;
+	u8     bmp_type;
+	u8     rsvd2;
+	__le32 bmp_type_mask;
+	u8     rsvd3[3];
+	u8     color;
+};
+
+/**
+ * struct pds_lm_dirty_enable_cmd - DIRTY_ENABLE command
+ * @opcode:		Opcode PDS_LM_CMD_DIRTY_ENABLE
+ * @rsvd:		Word boundary padding
+ * @vf_id:		VF id
+ * @bmp_type:		Type of dirty bitmap representation
+ * @num_regions:	Number of entries in the region info buffer
+ * @rsvd2:		Word boundary padding
+ * @regions_dma:	DMA address of the region info buffer
+ *
+ * The num_regions must be nonzero, and less than or equal to the maximum
+ * number of regions supported by the device.
+ *
+ * The memory regions should not overlap.
+ *
+ * The information should be initialized by the driver.  The device may modify
+ * the information on successful completion, such as by size-aligning the
+ * number of pages in a region.
+ *
+ * The modified number of pages will be greater than or equal to the page count
+ * given in the enable command, and at least as coarsly aligned as the given
+ * value.  For example, the count might be aligned to a multiple of 64, but
+ * if the value is already a multiple of 128 or higher, it will not change.
+ * If the driver requires its own minimum alignment of the number of pages, the
+ * driver should account for that already in the region info of this command.
+ *
+ * This command uses struct pds_lm_dirty_status_comp for its completion.
+ */
+struct pds_lm_dirty_enable_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 vf_id;
+	u8     bmp_type;
+	u8     num_regions;
+	u8     rsvd2[2];
+	__le64 regions_dma;
+} __packed;
+
+/**
+ * struct pds_lm_dirty_disable_cmd - DIRTY_DISABLE command
+ * @opcode:	Opcode PDS_LM_CMD_DIRTY_DISABLE
+ * @rsvd:	Word boundary padding
+ * @vf_id:	VF id
+ *
+ * Dirty page tracking will be disabled.  This may be called in any state, as
+ * long as dirty page tracking is supported by the device, to ensure that dirty
+ * page tracking is disabled.
+ *
+ * This command uses struct pds_lm_dirty_status_comp for its completion.  On
+ * success, num_regions will be zero.
+ */
+struct pds_lm_dirty_disable_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 vf_id;
+};
+
+/**
+ * struct pds_lm_dirty_seq_ack_cmd - DIRTY_READ_SEQ or _WRITE_ACK command
+ * @opcode:	Opcode PDS_LM_CMD_DIRTY_[READ_SEQ|WRITE_ACK]
+ * @rsvd:	Word boundary padding
+ * @vf_id:	VF id
+ * @off_bytes:	Byte offset in the bitmap
+ * @len_bytes:	Number of bytes to transfer
+ * @num_sge:	Number of DMA scatter gather elements
+ * @rsvd2:	Word boundary padding
+ * @sgl_addr:	DMA address of scatter gather list
+ *
+ * Read bytes from the SEQ bitmap, or write bytes into the ACK bitmap.
+ *
+ * This command treats the entire bitmap as a byte buffer.  It does not
+ * distinguish between guest memory regions.  The driver should refer to the
+ * number of pages in each region, according to PDS_LM_CMD_DIRTY_STATUS, to
+ * determine the region boundaries in the bitmap.  Each region will be
+ * represented by exactly the number of bits as the page count for that region,
+ * immediately following the last bit of the previous region.
+ */
+struct pds_lm_dirty_seq_ack_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 vf_id;
+	__le32 off_bytes;
+	__le32 len_bytes;
+	__le16 num_sge;
+	u8     rsvd2[2];
+	__le64 sgl_addr;
+} __packed;
+
+/**
+ * struct pds_lm_host_vf_status_cmd - HOST_VF_STATUS command
+ * @opcode:	Opcode PDS_LM_CMD_HOST_VF_STATUS
+ * @rsvd:	Word boundary padding
+ * @vf_id:	VF id
+ * @status:	Current LM status of host VF driver (enum pds_lm_host_status)
+ */
+struct pds_lm_host_vf_status_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 vf_id;
+	u8     status;
+};
+
 union pds_core_adminq_cmd {
 	u8     opcode;
 	u8     bytes[64];
@@ -844,6 +1205,17 @@ union pds_core_adminq_cmd {
 	struct pds_vdpa_vq_init_cmd	  vdpa_vq_init;
 	struct pds_vdpa_vq_reset_cmd	  vdpa_vq_reset;
 
+	struct pds_lm_suspend_cmd	  lm_suspend;
+	struct pds_lm_suspend_status_cmd  lm_suspend_status;
+	struct pds_lm_resume_cmd	  lm_resume;
+	struct pds_lm_state_size_cmd	  lm_state_size;
+	struct pds_lm_save_cmd		  lm_save;
+	struct pds_lm_restore_cmd	  lm_restore;
+	struct pds_lm_host_vf_status_cmd  lm_host_vf_status;
+	struct pds_lm_dirty_status_cmd	  lm_dirty_status;
+	struct pds_lm_dirty_enable_cmd	  lm_dirty_enable;
+	struct pds_lm_dirty_disable_cmd	  lm_dirty_disable;
+	struct pds_lm_dirty_seq_ack_cmd	  lm_dirty_seq_ack;
 };
 
 union pds_core_adminq_comp {
@@ -868,6 +1240,9 @@ union pds_core_adminq_comp {
 
 	struct pds_vdpa_vq_init_comp	  vdpa_vq_init;
 	struct pds_vdpa_vq_reset_comp	  vdpa_vq_reset;
+
+	struct pds_lm_state_size_comp	  lm_state_size;
+	struct pds_lm_dirty_status_comp	  lm_dirty_status;
 };
 
 #ifndef __CHECKER__
diff --git a/include/linux/pds/pds_common.h b/include/linux/pds/pds_common.h
index 435c8e8161c2..30581e2e04cc 100644
--- a/include/linux/pds/pds_common.h
+++ b/include/linux/pds/pds_common.h
@@ -34,16 +34,19 @@ enum pds_core_vif_types {
 
 #define PDS_DEV_TYPE_CORE_STR	"Core"
 #define PDS_DEV_TYPE_VDPA_STR	"vDPA"
-#define PDS_DEV_TYPE_VFIO_STR	"VFio"
+#define PDS_DEV_TYPE_VFIO_STR	"vfio"
 #define PDS_DEV_TYPE_ETH_STR	"Eth"
 #define PDS_DEV_TYPE_RDMA_STR	"RDMA"
 #define PDS_DEV_TYPE_LM_STR	"LM"
 
 #define PDS_VDPA_DEV_NAME	PDS_CORE_DRV_NAME "." PDS_DEV_TYPE_VDPA_STR
+#define PDS_VFIO_LM_DEV_NAME	PDS_CORE_DRV_NAME "." PDS_DEV_TYPE_LM_STR "." PDS_DEV_TYPE_VFIO_STR
+
+struct pdsc;
 
 int pdsc_register_notify(struct notifier_block *nb);
 void pdsc_unregister_notify(struct notifier_block *nb);
 void *pdsc_get_pf_struct(struct pci_dev *vf_pdev);
-int pds_client_register(struct pci_dev *pf_pdev, char *devname);
-int pds_client_unregister(struct pci_dev *pf_pdev, u16 client_id);
+int pds_client_register(struct pdsc *pf, char *devname);
+int pds_client_unregister(struct pdsc *pf, u16 client_id);
 #endif /* _PDS_COMMON_H_ */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 2c137ea94a3e..454e9295970c 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -13,6 +13,7 @@
 #include <linux/mm.h>
 #include <linux/workqueue.h>
 #include <linux/poll.h>
+#include <linux/cdev.h>
 #include <uapi/linux/vfio.h>
 #include <linux/iova_bitmap.h>
 
@@ -42,7 +43,11 @@ struct vfio_device {
 	 */
 	const struct vfio_migration_ops *mig_ops;
 	const struct vfio_log_ops *log_ops;
+#if IS_ENABLED(CONFIG_VFIO_GROUP)
 	struct vfio_group *group;
+	struct list_head group_next;
+	struct list_head iommu_entry;
+#endif
 	struct vfio_device_set *dev_set;
 	struct list_head dev_set_list;
 	unsigned int migration_flags;
@@ -51,17 +56,19 @@ struct vfio_device {
 	/* Members below here are private, not for driver use */
 	unsigned int index;
 	struct device device;	/* device.kref covers object life circle */
+#if IS_ENABLED(CONFIG_VFIO_DEVICE_CDEV)
+	struct cdev cdev;
+#endif
 	refcount_t refcount;	/* user count on registered device*/
 	unsigned int open_count;
 	struct completion comp;
-	struct list_head group_next;
-	struct list_head iommu_entry;
 	struct iommufd_access *iommufd_access;
 	void (*put_kvm)(struct kvm *kvm);
 #if IS_ENABLED(CONFIG_IOMMUFD)
 	struct iommufd_device *iommufd_device;
-	bool iommufd_attached;
+	u8 iommufd_attached:1;
 #endif
+	u8 cdev_opened:1;
 };
 
 /**
@@ -73,7 +80,9 @@ struct vfio_device {
  * @bind_iommufd: Called when binding the device to an iommufd
  * @unbind_iommufd: Opposite of bind_iommufd
  * @attach_ioas: Called when attaching device to an IOAS/HWPT managed by the
- *		 bound iommufd. Undo in unbind_iommufd.
+ *		 bound iommufd. Undo in unbind_iommufd if @detach_ioas is not
+ *		 called.
+ * @detach_ioas: Opposite of 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
@@ -97,6 +106,7 @@ struct vfio_device_ops {
 				struct iommufd_ctx *ictx, u32 *out_device_id);
 	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	(*open_device)(struct vfio_device *vdev);
 	void	(*close_device)(struct vfio_device *vdev);
 	ssize_t	(*read)(struct vfio_device *vdev, char __user *buf,
@@ -114,15 +124,31 @@ struct vfio_device_ops {
 };
 
 #if IS_ENABLED(CONFIG_IOMMUFD)
+struct iommufd_ctx *vfio_iommufd_device_ictx(struct vfio_device *vdev);
+int vfio_iommufd_get_dev_id(struct vfio_device *vdev, struct iommufd_ctx *ictx);
 int vfio_iommufd_physical_bind(struct vfio_device *vdev,
 			       struct iommufd_ctx *ictx, u32 *out_device_id);
 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_emulated_bind(struct vfio_device *vdev,
 			       struct iommufd_ctx *ictx, u32 *out_device_id);
 void vfio_iommufd_emulated_unbind(struct vfio_device *vdev);
 int vfio_iommufd_emulated_attach_ioas(struct vfio_device *vdev, u32 *pt_id);
+void vfio_iommufd_emulated_detach_ioas(struct vfio_device *vdev);
 #else
+static inline struct iommufd_ctx *
+vfio_iommufd_device_ictx(struct vfio_device *vdev)
+{
+	return NULL;
+}
+
+static inline int
+vfio_iommufd_get_dev_id(struct vfio_device *vdev, struct iommufd_ctx *ictx)
+{
+	return VFIO_PCI_DEVID_NOT_OWNED;
+}
+
 #define vfio_iommufd_physical_bind                                      \
 	((int (*)(struct vfio_device *vdev, struct iommufd_ctx *ictx,   \
 		  u32 *out_device_id)) NULL)
@@ -130,6 +156,8 @@ int vfio_iommufd_emulated_attach_ioas(struct vfio_device *vdev, u32 *pt_id);
 	((void (*)(struct vfio_device *vdev)) NULL)
 #define vfio_iommufd_physical_attach_ioas \
 	((int (*)(struct vfio_device *vdev, u32 *pt_id)) NULL)
+#define vfio_iommufd_physical_detach_ioas \
+	((void (*)(struct vfio_device *vdev)) NULL)
 #define vfio_iommufd_emulated_bind                                      \
 	((int (*)(struct vfio_device *vdev, struct iommufd_ctx *ictx,   \
 		  u32 *out_device_id)) NULL)
@@ -137,8 +165,15 @@ int vfio_iommufd_emulated_attach_ioas(struct vfio_device *vdev, u32 *pt_id);
 	((void (*)(struct vfio_device *vdev)) NULL)
 #define vfio_iommufd_emulated_attach_ioas \
 	((int (*)(struct vfio_device *vdev, u32 *pt_id)) NULL)
+#define vfio_iommufd_emulated_detach_ioas \
+	((void (*)(struct vfio_device *vdev)) NULL)
 #endif
 
+static inline bool vfio_device_cdev_opened(struct vfio_device *device)
+{
+	return device->cdev_opened;
+}
+
 /**
  * struct vfio_migration_ops - VFIO bus device driver migration callbacks
  *
@@ -239,20 +274,44 @@ void vfio_unregister_group_dev(struct vfio_device *device);
 
 int vfio_assign_device_set(struct vfio_device *device, void *set_id);
 unsigned int vfio_device_set_open_count(struct vfio_device_set *dev_set);
+struct vfio_device *
+vfio_find_device_in_devset(struct vfio_device_set *dev_set,
+			   struct device *dev);
 
 int vfio_mig_get_next_state(struct vfio_device *device,
 			    enum vfio_device_mig_state cur_fsm,
 			    enum vfio_device_mig_state new_fsm,
 			    enum vfio_device_mig_state *next_fsm);
 
+void vfio_combine_iova_ranges(struct rb_root_cached *root, u32 cur_nodes,
+			      u32 req_nodes);
+
 /*
  * External user API
  */
+#if IS_ENABLED(CONFIG_VFIO_GROUP)
 struct iommu_group *vfio_file_iommu_group(struct file *file);
 bool vfio_file_is_group(struct file *file);
+bool vfio_file_has_dev(struct file *file, struct vfio_device *device);
+#else
+static inline struct iommu_group *vfio_file_iommu_group(struct file *file)
+{
+	return NULL;
+}
+
+static inline bool vfio_file_is_group(struct file *file)
+{
+	return false;
+}
+
+static inline bool vfio_file_has_dev(struct file *file, struct vfio_device *device)
+{
+	return false;
+}
+#endif
+bool vfio_file_is_valid(struct file *file);
 bool vfio_file_enforced_coherent(struct file *file);
 void vfio_file_set_kvm(struct file *file, struct kvm *kvm);
-bool vfio_file_has_dev(struct file *file, struct vfio_device *device);
 
 #define VFIO_PIN_PAGES_MAX_ENTRIES	(PAGE_SIZE/sizeof(unsigned long))
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f089ab290978..13065dd96132 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1418,9 +1418,16 @@ struct kvm_device_attr {
 	__u64	addr;		/* userspace address of attr data */
 };
 
-#define  KVM_DEV_VFIO_GROUP			1
-#define   KVM_DEV_VFIO_GROUP_ADD			1
-#define   KVM_DEV_VFIO_GROUP_DEL			2
+#define  KVM_DEV_VFIO_FILE			1
+
+#define   KVM_DEV_VFIO_FILE_ADD			1
+#define   KVM_DEV_VFIO_FILE_DEL			2
+
+/* KVM_DEV_VFIO_GROUP aliases are for compile time uapi compatibility */
+#define  KVM_DEV_VFIO_GROUP	KVM_DEV_VFIO_FILE
+
+#define   KVM_DEV_VFIO_GROUP_ADD	KVM_DEV_VFIO_FILE_ADD
+#define   KVM_DEV_VFIO_GROUP_DEL	KVM_DEV_VFIO_FILE_DEL
 #define   KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE		3
 
 enum kvm_device_type {
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 20c804bdc09c..f9c6f3e2cf6e 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -217,6 +217,7 @@ struct vfio_device_info {
 	__u32	num_regions;	/* Max region index + 1 */
 	__u32	num_irqs;	/* Max IRQ index + 1 */
 	__u32   cap_offset;	/* Offset within info struct of first cap */
+	__u32   pad;
 };
 #define VFIO_DEVICE_GET_INFO		_IO(VFIO_TYPE, VFIO_BASE + 7)
 
@@ -677,11 +678,60 @@ enum {
  * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 12,
  *					      struct vfio_pci_hot_reset_info)
  *
+ * This command is used to query the affected devices in the hot reset for
+ * a given device.
+ *
+ * This command always reports the segment, bus, and devfn information for
+ * each affected device, and selectively reports the group_id or devid per
+ * the way how the calling device is opened.
+ *
+ *	- If the calling device is opened via the traditional group/container
+ *	  API, group_id is reported.  User should check if it has owned all
+ *	  the affected devices and provides a set of group fds to prove the
+ *	  ownership in VFIO_DEVICE_PCI_HOT_RESET ioctl.
+ *
+ *	- If the calling device is opened as a cdev, devid is reported.
+ *	  Flag VFIO_PCI_HOT_RESET_FLAG_DEV_ID is set to indicate this
+ *	  data type.  All the affected devices should be represented in
+ *	  the dev_set, ex. bound to a vfio driver, and also be owned by
+ *	  this interface which is determined by the following conditions:
+ *	  1) Has a valid devid within the iommufd_ctx of the calling device.
+ *	     Ownership cannot be determined across separate iommufd_ctx and
+ *	     the cdev calling conventions do not support a proof-of-ownership
+ *	     model as provided in the legacy group interface.  In this case
+ *	     valid devid with value greater than zero is provided in the return
+ *	     structure.
+ *	  2) Does not have a valid devid within the iommufd_ctx of the calling
+ *	     device, but belongs to the same IOMMU group as the calling device
+ *	     or another opened device that has a valid devid within the
+ *	     iommufd_ctx of the calling device.  This provides implicit ownership
+ *	     for devices within the same DMA isolation context.  In this case
+ *	     the devid value of VFIO_PCI_DEVID_OWNED is provided in the return
+ *	     structure.
+ *
+ *	  A devid value of VFIO_PCI_DEVID_NOT_OWNED is provided in the return
+ *	  structure for affected devices where device is NOT represented in the
+ *	  dev_set or ownership is not available.  Such devices prevent the use
+ *	  of VFIO_DEVICE_PCI_HOT_RESET ioctl outside of the proof-of-ownership
+ *	  calling conventions (ie. via legacy group accessed devices).  Flag
+ *	  VFIO_PCI_HOT_RESET_FLAG_DEV_ID_OWNED would be set when all the
+ *	  affected devices are represented in the dev_set and also owned by
+ *	  the user.  This flag is available only when
+ *	  flag VFIO_PCI_HOT_RESET_FLAG_DEV_ID is set, otherwise reserved.
+ *	  When set, user could invoke VFIO_DEVICE_PCI_HOT_RESET with a zero
+ *	  length fd array on the calling device as the ownership is validated
+ *	  by iommufd_ctx.
+ *
  * Return: 0 on success, -errno on failure:
  *	-enospc = insufficient buffer, -enodev = unsupported for device.
  */
 struct vfio_pci_dependent_device {
-	__u32	group_id;
+	union {
+		__u32   group_id;
+		__u32	devid;
+#define VFIO_PCI_DEVID_OWNED		0
+#define VFIO_PCI_DEVID_NOT_OWNED	-1
+	};
 	__u16	segment;
 	__u8	bus;
 	__u8	devfn; /* Use PCI_SLOT/PCI_FUNC */
@@ -690,6 +740,8 @@ struct vfio_pci_dependent_device {
 struct vfio_pci_hot_reset_info {
 	__u32	argsz;
 	__u32	flags;
+#define VFIO_PCI_HOT_RESET_FLAG_DEV_ID		(1 << 0)
+#define VFIO_PCI_HOT_RESET_FLAG_DEV_ID_OWNED	(1 << 1)
 	__u32	count;
 	struct vfio_pci_dependent_device	devices[];
 };
@@ -700,6 +752,24 @@ struct vfio_pci_hot_reset_info {
  * VFIO_DEVICE_PCI_HOT_RESET - _IOW(VFIO_TYPE, VFIO_BASE + 13,
  *				    struct vfio_pci_hot_reset)
  *
+ * A PCI hot reset results in either a bus or slot reset which may affect
+ * other devices sharing the bus/slot.  The calling user must have
+ * ownership of the full set of affected devices as determined by the
+ * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO ioctl.
+ *
+ * When called on a device file descriptor acquired through the vfio
+ * group interface, the user is required to provide proof of ownership
+ * of those affected devices via the group_fds array in struct
+ * vfio_pci_hot_reset.
+ *
+ * When called on a direct cdev opened vfio device, the flags field of
+ * struct vfio_pci_hot_reset_info reports the ownership status of the
+ * affected devices and this ioctl must be called with an empty group_fds
+ * array.  See above INFO ioctl definition for ownership requirements.
+ *
+ * Mixed usage of legacy groups and cdevs across the set of affected
+ * devices is not supported.
+ *
  * Return: 0 on success, -errno on failure.
  */
 struct vfio_pci_hot_reset {
@@ -829,6 +899,77 @@ struct vfio_device_feature {
 #define VFIO_DEVICE_FEATURE		_IO(VFIO_TYPE, VFIO_BASE + 17)
 
 /*
+ * VFIO_DEVICE_BIND_IOMMUFD - _IOR(VFIO_TYPE, VFIO_BASE + 18,
+ *				   struct vfio_device_bind_iommufd)
+ * @argsz:	 User filled size of this data.
+ * @flags:	 Must be 0.
+ * @iommufd:	 iommufd to bind.
+ * @out_devid:	 The device id generated by this bind. devid is a handle for
+ *		 this device/iommufd bond and can be used in IOMMUFD commands.
+ *
+ * Bind a vfio_device to the specified iommufd.
+ *
+ * User is restricted from accessing the device before the binding operation
+ * is completed.  Only allowed on cdev fds.
+ *
+ * Unbind is automatically conducted when device fd is closed.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+struct vfio_device_bind_iommufd {
+	__u32		argsz;
+	__u32		flags;
+	__s32		iommufd;
+	__u32		out_devid;
+};
+
+#define VFIO_DEVICE_BIND_IOMMUFD	_IO(VFIO_TYPE, VFIO_BASE + 18)
+
+/*
+ * 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.
+ * @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.
+ *
+ * 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.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+struct vfio_device_attach_iommufd_pt {
+	__u32	argsz;
+	__u32	flags;
+	__u32	pt_id;
+};
+
+#define VFIO_DEVICE_ATTACH_IOMMUFD_PT		_IO(VFIO_TYPE, VFIO_BASE + 19)
+
+/*
+ * 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.
+ *
+ * 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.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+struct vfio_device_detach_iommufd_pt {
+	__u32	argsz;
+	__u32	flags;
+};
+
+#define VFIO_DEVICE_DETACH_IOMMUFD_PT		_IO(VFIO_TYPE, VFIO_BASE + 20)
+
+/*
  * Provide support for setting a PCI VF Token, which is used as a shared
  * secret between PF and VF drivers.  This feature may only be set on a
  * PCI SR-IOV PF when SR-IOV is enabled on the PF and there are no existing
@@ -1304,6 +1445,7 @@ struct vfio_iommu_type1_info {
 #define VFIO_IOMMU_INFO_CAPS	(1 << 1)	/* Info supports caps */
 	__u64	iova_pgsizes;	/* Bitmap of supported page sizes */
 	__u32   cap_offset;	/* Offset within info struct of first cap */
+	__u32   pad;
 };
 
 /*