diff options
Diffstat (limited to 'linux-headers/include/linux/vfio.h')
-rw-r--r-- | linux-headers/include/linux/vfio.h | 896 |
1 files changed, 682 insertions, 214 deletions
diff --git a/linux-headers/include/linux/vfio.h b/linux-headers/include/linux/vfio.h index b92dcc4..acf72b4 100644 --- a/linux-headers/include/linux/vfio.h +++ b/linux-headers/include/linux/vfio.h @@ -46,6 +46,16 @@ */ #define VFIO_NOIOMMU_IOMMU 8 +/* Supports VFIO_DMA_UNMAP_FLAG_ALL */ +#define VFIO_UNMAP_ALL 9 + +/* + * Supports the vaddr flag for DMA map and unmap. Not supported for mediated + * devices, so this capability is subject to change as groups are added or + * removed. + */ +#define VFIO_UPDATE_VADDR 10 + /* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between @@ -203,9 +213,11 @@ struct vfio_device_info { #define VFIO_DEVICE_FLAGS_AP (1 << 5) /* vfio-ap device */ #define VFIO_DEVICE_FLAGS_FSL_MC (1 << 6) /* vfio-fsl-mc device */ #define VFIO_DEVICE_FLAGS_CAPS (1 << 7) /* Info supports caps */ +#define VFIO_DEVICE_FLAGS_CDX (1 << 8) /* vfio-cdx device */ __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) @@ -230,6 +242,20 @@ struct vfio_device_info { #define VFIO_DEVICE_INFO_CAP_ZPCI_UTIL 3 #define VFIO_DEVICE_INFO_CAP_ZPCI_PFIP 4 +/* + * The following VFIO_DEVICE_INFO capability reports support for PCIe AtomicOp + * completion to the root bus with supported widths provided via flags. + */ +#define VFIO_DEVICE_INFO_CAP_PCI_ATOMIC_COMP 5 +struct vfio_device_info_cap_pci_atomic_comp { + struct vfio_info_cap_header header; + __u32 flags; +#define VFIO_PCI_ATOMIC_COMP32 (1 << 0) +#define VFIO_PCI_ATOMIC_COMP64 (1 << 1) +#define VFIO_PCI_ATOMIC_COMP128 (1 << 2) + __u32 reserved; +}; + /** * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8, * struct vfio_region_info) @@ -317,7 +343,7 @@ struct vfio_region_info_cap_type { #define VFIO_REGION_TYPE_PCI_VENDOR_MASK (0xffff) #define VFIO_REGION_TYPE_GFX (1) #define VFIO_REGION_TYPE_CCW (2) -#define VFIO_REGION_TYPE_MIGRATION (3) +#define VFIO_REGION_TYPE_MIGRATION_DEPRECATED (3) /* sub-types for VFIO_REGION_TYPE_PCI_* */ @@ -329,6 +355,8 @@ struct vfio_region_info_cap_type { /* 10de vendor PCI sub-types */ /* * NVIDIA GPU NVlink2 RAM is coherent RAM mapped onto the host address space. + * + * Deprecated, region no longer provided */ #define VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM (1) @@ -336,6 +364,8 @@ struct vfio_region_info_cap_type { /* * IBM NPU NVlink2 ATSD (Address Translation Shootdown) register of NPU * to do TLB invalidation on a GPU. + * + * Deprecated, region no longer provided */ #define VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD (1) @@ -395,225 +425,29 @@ struct vfio_region_gfx_edid { #define VFIO_REGION_SUBTYPE_CCW_CRW (3) /* sub-types for VFIO_REGION_TYPE_MIGRATION */ -#define VFIO_REGION_SUBTYPE_MIGRATION (1) - -/* - * The structure vfio_device_migration_info is placed at the 0th offset of - * the VFIO_REGION_SUBTYPE_MIGRATION region to get and set VFIO device related - * migration information. Field accesses from this structure are only supported - * at their native width and alignment. Otherwise, the result is undefined and - * vendor drivers should return an error. - * - * device_state: (read/write) - * - The user application writes to this field to inform the vendor driver - * about the device state to be transitioned to. - * - The vendor driver should take the necessary actions to change the - * device state. After successful transition to a given state, the - * vendor driver should return success on write(device_state, state) - * system call. If the device state transition fails, the vendor driver - * should return an appropriate -errno for the fault condition. - * - On the user application side, if the device state transition fails, - * that is, if write(device_state, state) returns an error, read - * device_state again to determine the current state of the device from - * the vendor driver. - * - The vendor driver should return previous state of the device unless - * the vendor driver has encountered an internal error, in which case - * the vendor driver may report the device_state VFIO_DEVICE_STATE_ERROR. - * - The user application must use the device reset ioctl to recover the - * device from VFIO_DEVICE_STATE_ERROR state. If the device is - * indicated to be in a valid device state by reading device_state, the - * user application may attempt to transition the device to any valid - * state reachable from the current state or terminate itself. - * - * device_state consists of 3 bits: - * - If bit 0 is set, it indicates the _RUNNING state. If bit 0 is clear, - * it indicates the _STOP state. When the device state is changed to - * _STOP, driver should stop the device before write() returns. - * - If bit 1 is set, it indicates the _SAVING state, which means that the - * driver should start gathering device state information that will be - * provided to the VFIO user application to save the device's state. - * - If bit 2 is set, it indicates the _RESUMING state, which means that - * the driver should prepare to resume the device. Data provided through - * the migration region should be used to resume the device. - * Bits 3 - 31 are reserved for future use. To preserve them, the user - * application should perform a read-modify-write operation on this - * field when modifying the specified bits. - * - * +------- _RESUMING - * |+------ _SAVING - * ||+----- _RUNNING - * ||| - * 000b => Device Stopped, not saving or resuming - * 001b => Device running, which is the default state - * 010b => Stop the device & save the device state, stop-and-copy state - * 011b => Device running and save the device state, pre-copy state - * 100b => Device stopped and the device state is resuming - * 101b => Invalid state - * 110b => Error state - * 111b => Invalid state - * - * State transitions: - * - * _RESUMING _RUNNING Pre-copy Stop-and-copy _STOP - * (100b) (001b) (011b) (010b) (000b) - * 0. Running or default state - * | - * - * 1. Normal Shutdown (optional) - * |------------------------------------->| - * - * 2. Save the state or suspend - * |------------------------->|---------->| - * - * 3. Save the state during live migration - * |----------->|------------>|---------->| - * - * 4. Resuming - * |<---------| - * - * 5. Resumed - * |--------->| - * - * 0. Default state of VFIO device is _RUNNING when the user application starts. - * 1. During normal shutdown of the user application, the user application may - * optionally change the VFIO device state from _RUNNING to _STOP. This - * transition is optional. The vendor driver must support this transition but - * must not require it. - * 2. When the user application saves state or suspends the application, the - * device state transitions from _RUNNING to stop-and-copy and then to _STOP. - * On state transition from _RUNNING to stop-and-copy, driver must stop the - * device, save the device state and send it to the application through the - * migration region. The sequence to be followed for such transition is given - * below. - * 3. In live migration of user application, the state transitions from _RUNNING - * to pre-copy, to stop-and-copy, and to _STOP. - * On state transition from _RUNNING to pre-copy, the driver should start - * gathering the device state while the application is still running and send - * the device state data to application through the migration region. - * On state transition from pre-copy to stop-and-copy, the driver must stop - * the device, save the device state and send it to the user application - * through the migration region. - * Vendor drivers must support the pre-copy state even for implementations - * where no data is provided to the user before the stop-and-copy state. The - * user must not be required to consume all migration data before the device - * transitions to a new state, including the stop-and-copy state. - * The sequence to be followed for above two transitions is given below. - * 4. To start the resuming phase, the device state should be transitioned from - * the _RUNNING to the _RESUMING state. - * In the _RESUMING state, the driver should use the device state data - * received through the migration region to resume the device. - * 5. After providing saved device data to the driver, the application should - * change the state from _RESUMING to _RUNNING. - * - * reserved: - * Reads on this field return zero and writes are ignored. - * - * pending_bytes: (read only) - * The number of pending bytes still to be migrated from the vendor driver. - * - * data_offset: (read only) - * The user application should read data_offset field from the migration - * region. The user application should read the device data from this - * offset within the migration region during the _SAVING state or write - * the device data during the _RESUMING state. See below for details of - * sequence to be followed. - * - * data_size: (read/write) - * The user application should read data_size to get the size in bytes of - * the data copied in the migration region during the _SAVING state and - * write the size in bytes of the data copied in the migration region - * during the _RESUMING state. - * - * The format of the migration region is as follows: - * ------------------------------------------------------------------ - * |vfio_device_migration_info| data section | - * | | /////////////////////////////// | - * ------------------------------------------------------------------ - * ^ ^ - * offset 0-trapped part data_offset - * - * The structure vfio_device_migration_info is always followed by the data - * section in the region, so data_offset will always be nonzero. The offset - * from where the data is copied is decided by the kernel driver. The data - * section can be trapped, mmapped, or partitioned, depending on how the kernel - * driver defines the data section. The data section partition can be defined - * as mapped by the sparse mmap capability. If mmapped, data_offset must be - * page aligned, whereas initial section which contains the - * vfio_device_migration_info structure, might not end at the offset, which is - * page aligned. The user is not required to access through mmap regardless - * of the capabilities of the region mmap. - * The vendor driver should determine whether and how to partition the data - * section. The vendor driver should return data_offset accordingly. - * - * The sequence to be followed while in pre-copy state and stop-and-copy state - * is as follows: - * a. Read pending_bytes, indicating the start of a new iteration to get device - * data. Repeated read on pending_bytes at this stage should have no side - * effects. - * If pending_bytes == 0, the user application should not iterate to get data - * for that device. - * If pending_bytes > 0, perform the following steps. - * b. Read data_offset, indicating that the vendor driver should make data - * available through the data section. The vendor driver should return this - * read operation only after data is available from (region + data_offset) - * to (region + data_offset + data_size). - * c. Read data_size, which is the amount of data in bytes available through - * the migration region. - * Read on data_offset and data_size should return the offset and size of - * the current buffer if the user application reads data_offset and - * data_size more than once here. - * d. Read data_size bytes of data from (region + data_offset) from the - * migration region. - * e. Process the data. - * f. Read pending_bytes, which indicates that the data from the previous - * iteration has been read. If pending_bytes > 0, go to step b. - * - * The user application can transition from the _SAVING|_RUNNING - * (pre-copy state) to the _SAVING (stop-and-copy) state regardless of the - * number of pending bytes. The user application should iterate in _SAVING - * (stop-and-copy) until pending_bytes is 0. - * - * The sequence to be followed while _RESUMING device state is as follows: - * While data for this device is available, repeat the following steps: - * a. Read data_offset from where the user application should write data. - * b. Write migration data starting at the migration region + data_offset for - * the length determined by data_size from the migration source. - * c. Write data_size, which indicates to the vendor driver that data is - * written in the migration region. Vendor driver must return this write - * operations on consuming data. Vendor driver should apply the - * user-provided migration region data to the device resume state. - * - * If an error occurs during the above sequences, the vendor driver can return - * an error code for next read() or write() operation, which will terminate the - * loop. The user application should then take the next necessary action, for - * example, failing migration or terminating the user application. - * - * For the user application, data is opaque. The user application should write - * data in the same order as the data is received and the data should be of - * same transaction size at the source. - */ +#define VFIO_REGION_SUBTYPE_MIGRATION_DEPRECATED (1) struct vfio_device_migration_info { __u32 device_state; /* VFIO device state */ -#define VFIO_DEVICE_STATE_STOP (0) -#define VFIO_DEVICE_STATE_RUNNING (1 << 0) -#define VFIO_DEVICE_STATE_SAVING (1 << 1) -#define VFIO_DEVICE_STATE_RESUMING (1 << 2) -#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_RUNNING | \ - VFIO_DEVICE_STATE_SAVING | \ - VFIO_DEVICE_STATE_RESUMING) +#define VFIO_DEVICE_STATE_V1_STOP (0) +#define VFIO_DEVICE_STATE_V1_RUNNING (1 << 0) +#define VFIO_DEVICE_STATE_V1_SAVING (1 << 1) +#define VFIO_DEVICE_STATE_V1_RESUMING (1 << 2) +#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_V1_RUNNING | \ + VFIO_DEVICE_STATE_V1_SAVING | \ + VFIO_DEVICE_STATE_V1_RESUMING) #define VFIO_DEVICE_STATE_VALID(state) \ - (state & VFIO_DEVICE_STATE_RESUMING ? \ - (state & VFIO_DEVICE_STATE_MASK) == VFIO_DEVICE_STATE_RESUMING : 1) + (state & VFIO_DEVICE_STATE_V1_RESUMING ? \ + (state & VFIO_DEVICE_STATE_MASK) == VFIO_DEVICE_STATE_V1_RESUMING : 1) #define VFIO_DEVICE_STATE_IS_ERROR(state) \ - ((state & VFIO_DEVICE_STATE_MASK) == (VFIO_DEVICE_STATE_SAVING | \ - VFIO_DEVICE_STATE_RESUMING)) + ((state & VFIO_DEVICE_STATE_MASK) == (VFIO_DEVICE_STATE_V1_SAVING | \ + VFIO_DEVICE_STATE_V1_RESUMING)) #define VFIO_DEVICE_STATE_SET_ERROR(state) \ - ((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_SATE_SAVING | \ - VFIO_DEVICE_STATE_RESUMING) + ((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_STATE_V1_SAVING | \ + VFIO_DEVICE_STATE_V1_RESUMING) __u32 reserved; __u64 pending_bytes; @@ -635,6 +469,8 @@ struct vfio_device_migration_info { * Capability with compressed real address (aka SSA - small system address) * where GPU RAM is mapped on a system bus. Used by a GPU for DMA routing * and by the userspace to associate a NVLink bridge with a GPU. + * + * Deprecated, capability no longer provided */ #define VFIO_REGION_INFO_CAP_NVLINK2_SSATGT 4 @@ -649,6 +485,8 @@ struct vfio_region_info_cap_nvlink2_ssatgt { * property in the device tree. The value is fixed in the hardware * and failing to provide the correct value results in the link * not working with no indication from the driver why. + * + * Deprecated, capability no longer provided */ #define VFIO_REGION_INFO_CAP_NVLINK2_LNKSPD 5 @@ -689,6 +527,9 @@ struct vfio_region_info_cap_nvlink2_lnkspd { * then add and unmask vectors, it's up to userspace to make the decision * whether to allocate the maximum supported number of vectors or tear * down setup and incrementally increase the vectors as each is enabled. + * Absence of the NORESIZE flag indicates that vectors can be enabled + * and disabled dynamically without impacting other vectors within the + * index. */ struct vfio_irq_info { __u32 argsz; @@ -820,18 +661,77 @@ enum { enum { VFIO_CCW_IO_IRQ_INDEX, VFIO_CCW_CRW_IRQ_INDEX, + VFIO_CCW_REQ_IRQ_INDEX, VFIO_CCW_NUM_IRQS }; +/* + * The vfio-ap bus driver makes use of the following IRQ index mapping. + * Unimplemented IRQ types return a count of zero. + */ +enum { + VFIO_AP_REQ_IRQ_INDEX, + VFIO_AP_NUM_IRQS +}; + /** - * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IORW(VFIO_TYPE, VFIO_BASE + 12, + * 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 */ @@ -840,6 +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[]; }; @@ -850,6 +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 { @@ -951,7 +871,7 @@ struct vfio_device_ioeventfd { #define VFIO_DEVICE_IOEVENTFD _IO(VFIO_TYPE, VFIO_BASE + 16) /** - * VFIO_DEVICE_FEATURE - _IORW(VFIO_TYPE, VFIO_BASE + 17, + * VFIO_DEVICE_FEATURE - _IOWR(VFIO_TYPE, VFIO_BASE + 17, * struct vfio_device_feature) * * Get, set, or probe feature data of the device. The feature is selected @@ -979,6 +899,83 @@ 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. + * + * 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. + * + * 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 @@ -987,6 +984,456 @@ struct vfio_device_feature { */ #define VFIO_DEVICE_FEATURE_PCI_VF_TOKEN (0) +/* + * Indicates the device can support the migration API through + * VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE. If this GET succeeds, the RUNNING and + * ERROR states are always supported. Support for additional states is + * indicated via the flags field; at least VFIO_MIGRATION_STOP_COPY must be + * set. + * + * VFIO_MIGRATION_STOP_COPY means that STOP, STOP_COPY and + * RESUMING are supported. + * + * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P means that RUNNING_P2P + * is supported in addition to the STOP_COPY states. + * + * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY means that + * PRE_COPY is supported in addition to the STOP_COPY states. + * + * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P | VFIO_MIGRATION_PRE_COPY + * means that RUNNING_P2P, PRE_COPY and PRE_COPY_P2P are supported + * in addition to the STOP_COPY states. + * + * Other combinations of flags have behavior to be defined in the future. + */ +struct vfio_device_feature_migration { + __aligned_u64 flags; +#define VFIO_MIGRATION_STOP_COPY (1 << 0) +#define VFIO_MIGRATION_P2P (1 << 1) +#define VFIO_MIGRATION_PRE_COPY (1 << 2) +}; +#define VFIO_DEVICE_FEATURE_MIGRATION 1 + +/* + * Upon VFIO_DEVICE_FEATURE_SET, execute a migration state change on the VFIO + * device. The new state is supplied in device_state, see enum + * vfio_device_mig_state for details + * + * The kernel migration driver must fully transition the device to the new state + * value before the operation returns to the user. + * + * The kernel migration driver must not generate asynchronous device state + * transitions outside of manipulation by the user or the VFIO_DEVICE_RESET + * ioctl as described above. + * + * If this function fails then current device_state may be the original + * operating state or some other state along the combination transition path. + * The user can then decide if it should execute a VFIO_DEVICE_RESET, attempt + * to return to the original state, or attempt to return to some other state + * such as RUNNING or STOP. + * + * If the new_state starts a new data transfer session then the FD associated + * with that session is returned in data_fd. The user is responsible to close + * this FD when it is finished. The user must consider the migration data stream + * carried over the FD to be opaque and must preserve the byte order of the + * stream. The user is not required to preserve buffer segmentation when writing + * the data stream during the RESUMING operation. + * + * Upon VFIO_DEVICE_FEATURE_GET, get the current migration state of the VFIO + * device, data_fd will be -1. + */ +struct vfio_device_feature_mig_state { + __u32 device_state; /* From enum vfio_device_mig_state */ + __s32 data_fd; +}; +#define VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE 2 + +/* + * The device migration Finite State Machine is described by the enum + * vfio_device_mig_state. Some of the FSM arcs will create a migration data + * transfer session by returning a FD, in this case the migration data will + * flow over the FD using read() and write() as discussed below. + * + * There are 5 states to support VFIO_MIGRATION_STOP_COPY: + * RUNNING - The device is running normally + * STOP - The device does not change the internal or external state + * STOP_COPY - The device internal state can be read out + * RESUMING - The device is stopped and is loading a new internal state + * ERROR - The device has failed and must be reset + * + * And optional states to support VFIO_MIGRATION_P2P: + * RUNNING_P2P - RUNNING, except the device cannot do peer to peer DMA + * And VFIO_MIGRATION_PRE_COPY: + * PRE_COPY - The device is running normally but tracking internal state + * changes + * And VFIO_MIGRATION_P2P | VFIO_MIGRATION_PRE_COPY: + * PRE_COPY_P2P - PRE_COPY, except the device cannot do peer to peer DMA + * + * The FSM takes actions on the arcs between FSM states. The driver implements + * the following behavior for the FSM arcs: + * + * RUNNING_P2P -> STOP + * STOP_COPY -> STOP + * While in STOP the device must stop the operation of the device. The device + * must not generate interrupts, DMA, or any other change to external state. + * It must not change its internal state. When stopped the device and kernel + * migration driver must accept and respond to interaction to support external + * subsystems in the STOP state, for example PCI MSI-X and PCI config space. + * Failure by the user to restrict device access while in STOP must not result + * in error conditions outside the user context (ex. host system faults). + * + * The STOP_COPY arc will terminate a data transfer session. + * + * RESUMING -> STOP + * Leaving RESUMING terminates a data transfer session and indicates the + * device should complete processing of the data delivered by write(). The + * kernel migration driver should complete the incorporation of data written + * to the data transfer FD into the device internal state and perform + * final validity and consistency checking of the new device state. If the + * user provided data is found to be incomplete, inconsistent, or otherwise + * invalid, the migration driver must fail the SET_STATE ioctl and + * optionally go to the ERROR state as described below. + * + * While in STOP the device has the same behavior as other STOP states + * described above. + * + * To abort a RESUMING session the device must be reset. + * + * PRE_COPY -> RUNNING + * RUNNING_P2P -> RUNNING + * While in RUNNING the device is fully operational, the device may generate + * interrupts, DMA, respond to MMIO, all vfio device regions are functional, + * and the device may advance its internal state. + * + * The PRE_COPY arc will terminate a data transfer session. + * + * PRE_COPY_P2P -> RUNNING_P2P + * RUNNING -> RUNNING_P2P + * STOP -> RUNNING_P2P + * While in RUNNING_P2P the device is partially running in the P2P quiescent + * state defined below. + * + * The PRE_COPY_P2P arc will terminate a data transfer session. + * + * RUNNING -> PRE_COPY + * RUNNING_P2P -> PRE_COPY_P2P + * STOP -> STOP_COPY + * PRE_COPY, PRE_COPY_P2P and STOP_COPY form the "saving group" of states + * which share a data transfer session. Moving between these states alters + * what is streamed in session, but does not terminate or otherwise affect + * the associated fd. + * + * These arcs begin the process of saving the device state and will return a + * new data_fd. The migration driver may perform actions such as enabling + * dirty logging of device state when entering PRE_COPY or PER_COPY_P2P. + * + * Each arc does not change the device operation, the device remains + * RUNNING, P2P quiesced or in STOP. The STOP_COPY state is described below + * in PRE_COPY_P2P -> STOP_COPY. + * + * PRE_COPY -> PRE_COPY_P2P + * Entering PRE_COPY_P2P continues all the behaviors of PRE_COPY above. + * However, while in the PRE_COPY_P2P state, the device is partially running + * in the P2P quiescent state defined below, like RUNNING_P2P. + * + * PRE_COPY_P2P -> PRE_COPY + * This arc allows returning the device to a full RUNNING behavior while + * continuing all the behaviors of PRE_COPY. + * + * PRE_COPY_P2P -> STOP_COPY + * While in the STOP_COPY state the device has the same behavior as STOP + * with the addition that the data transfers session continues to stream the + * migration state. End of stream on the FD indicates the entire device + * state has been transferred. + * + * The user should take steps to restrict access to vfio device regions while + * the device is in STOP_COPY or risk corruption of the device migration data + * stream. + * + * STOP -> RESUMING + * Entering the RESUMING state starts a process of restoring the device state + * and will return a new data_fd. The data stream fed into the data_fd should + * be taken from the data transfer output of a single FD during saving from + * a compatible device. The migration driver may alter/reset the internal + * device state for this arc if required to prepare the device to receive the + * migration data. + * + * STOP_COPY -> PRE_COPY + * STOP_COPY -> PRE_COPY_P2P + * These arcs are not permitted and return error if requested. Future + * revisions of this API may define behaviors for these arcs, in this case + * support will be discoverable by a new flag in + * VFIO_DEVICE_FEATURE_MIGRATION. + * + * any -> ERROR + * ERROR cannot be specified as a device state, however any transition request + * can be failed with an errno return and may then move the device_state into + * ERROR. In this case the device was unable to execute the requested arc and + * was also unable to restore the device to any valid device_state. + * To recover from ERROR VFIO_DEVICE_RESET must be used to return the + * device_state back to RUNNING. + * + * The optional peer to peer (P2P) quiescent state is intended to be a quiescent + * state for the device for the purposes of managing multiple devices within a + * user context where peer-to-peer DMA between devices may be active. The + * RUNNING_P2P and PRE_COPY_P2P states must prevent the device from initiating + * any new P2P DMA transactions. If the device can identify P2P transactions + * then it can stop only P2P DMA, otherwise it must stop all DMA. The migration + * driver must complete any such outstanding operations prior to completing the + * FSM arc into a P2P state. For the purpose of specification the states + * behave as though the device was fully running if not supported. Like while in + * STOP or STOP_COPY the user must not touch the device, otherwise the state + * can be exited. + * + * The remaining possible transitions are interpreted as combinations of the + * above FSM arcs. As there are multiple paths through the FSM arcs the path + * should be selected based on the following rules: + * - Select the shortest path. + * - The path cannot have saving group states as interior arcs, only + * starting/end states. + * Refer to vfio_mig_get_next_state() for the result of the algorithm. + * + * The automatic transit through the FSM arcs that make up the combination + * transition is invisible to the user. When working with combination arcs the + * user may see any step along the path in the device_state if SET_STATE + * fails. When handling these types of errors users should anticipate future + * revisions of this protocol using new states and those states becoming + * visible in this case. + * + * The optional states cannot be used with SET_STATE if the device does not + * support them. The user can discover if these states are supported by using + * VFIO_DEVICE_FEATURE_MIGRATION. By using combination transitions the user can + * avoid knowing about these optional states if the kernel driver supports them. + * + * Arcs touching PRE_COPY and PRE_COPY_P2P are removed if support for PRE_COPY + * is not present. + */ +enum vfio_device_mig_state { + VFIO_DEVICE_STATE_ERROR = 0, + VFIO_DEVICE_STATE_STOP = 1, + VFIO_DEVICE_STATE_RUNNING = 2, + VFIO_DEVICE_STATE_STOP_COPY = 3, + VFIO_DEVICE_STATE_RESUMING = 4, + VFIO_DEVICE_STATE_RUNNING_P2P = 5, + VFIO_DEVICE_STATE_PRE_COPY = 6, + VFIO_DEVICE_STATE_PRE_COPY_P2P = 7, +}; + +/** + * VFIO_MIG_GET_PRECOPY_INFO - _IO(VFIO_TYPE, VFIO_BASE + 21) + * + * This ioctl is used on the migration data FD in the precopy phase of the + * migration data transfer. It returns an estimate of the current data sizes + * remaining to be transferred. It allows the user to judge when it is + * appropriate to leave PRE_COPY for STOP_COPY. + * + * This ioctl is valid only in PRE_COPY states and kernel driver should + * return -EINVAL from any other migration state. + * + * The vfio_precopy_info data structure returned by this ioctl provides + * estimates of data available from the device during the PRE_COPY states. + * This estimate is split into two categories, initial_bytes and + * dirty_bytes. + * + * The initial_bytes field indicates the amount of initial precopy + * data available from the device. This field should have a non-zero initial + * value and decrease as migration data is read from the device. + * It is recommended to leave PRE_COPY for STOP_COPY only after this field + * reaches zero. Leaving PRE_COPY earlier might make things slower. + * + * The dirty_bytes field tracks device state changes relative to data + * previously retrieved. This field starts at zero and may increase as + * the internal device state is modified or decrease as that modified + * state is read from the device. + * + * Userspace may use the combination of these fields to estimate the + * potential data size available during the PRE_COPY phases, as well as + * trends relative to the rate the device is dirtying its internal + * state, but these fields are not required to have any bearing relative + * to the data size available during the STOP_COPY phase. + * + * Drivers have a lot of flexibility in when and what they transfer during the + * PRE_COPY phase, and how they report this from VFIO_MIG_GET_PRECOPY_INFO. + * + * During pre-copy the migration data FD has a temporary "end of stream" that is + * reached when both initial_bytes and dirty_byte are zero. For instance, this + * may indicate that the device is idle and not currently dirtying any internal + * state. When read() is done on this temporary end of stream the kernel driver + * should return ENOMSG from read(). Userspace can wait for more data (which may + * never come) by using poll. + * + * Once in STOP_COPY the migration data FD has a permanent end of stream + * signaled in the usual way by read() always returning 0 and poll always + * returning readable. ENOMSG may not be returned in STOP_COPY. + * Support for this ioctl is mandatory if a driver claims to support + * VFIO_MIGRATION_PRE_COPY. + * + * Return: 0 on success, -1 and errno set on failure. + */ +struct vfio_precopy_info { + __u32 argsz; + __u32 flags; + __aligned_u64 initial_bytes; + __aligned_u64 dirty_bytes; +}; + +#define VFIO_MIG_GET_PRECOPY_INFO _IO(VFIO_TYPE, VFIO_BASE + 21) + +/* + * Upon VFIO_DEVICE_FEATURE_SET, allow the device to be moved into a low power + * state with the platform-based power management. Device use of lower power + * states depends on factors managed by the runtime power management core, + * including system level support and coordinating support among dependent + * devices. Enabling device low power entry does not guarantee lower power + * usage by the device, nor is a mechanism provided through this feature to + * know the current power state of the device. If any device access happens + * (either from the host or through the vfio uAPI) when the device is in the + * low power state, then the host will move the device out of the low power + * state as necessary prior to the access. Once the access is completed, the + * device may re-enter the low power state. For single shot low power support + * with wake-up notification, see + * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP below. Access to mmap'd + * device regions is disabled on LOW_POWER_ENTRY and may only be resumed after + * calling LOW_POWER_EXIT. + */ +#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY 3 + +/* + * This device feature has the same behavior as + * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY with the exception that the user + * provides an eventfd for wake-up notification. When the device moves out of + * the low power state for the wake-up, the host will not allow the device to + * re-enter a low power state without a subsequent user call to one of the low + * power entry device feature IOCTLs. Access to mmap'd device regions is + * disabled on LOW_POWER_ENTRY_WITH_WAKEUP and may only be resumed after the + * low power exit. The low power exit can happen either through LOW_POWER_EXIT + * or through any other access (where the wake-up notification has been + * generated). The access to mmap'd device regions will not trigger low power + * exit. + * + * The notification through the provided eventfd will be generated only when + * the device has entered and is resumed from a low power state after + * calling this device feature IOCTL. A device that has not entered low power + * state, as managed through the runtime power management core, will not + * generate a notification through the provided eventfd on access. Calling the + * LOW_POWER_EXIT feature is optional in the case where notification has been + * signaled on the provided eventfd that a resume from low power has occurred. + */ +struct vfio_device_low_power_entry_with_wakeup { + __s32 wakeup_eventfd; + __u32 reserved; +}; + +#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP 4 + +/* + * Upon VFIO_DEVICE_FEATURE_SET, disallow use of device low power states as + * previously enabled via VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY or + * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP device features. + * This device feature IOCTL may itself generate a wakeup eventfd notification + * in the latter case if the device had previously entered a low power state. + */ +#define VFIO_DEVICE_FEATURE_LOW_POWER_EXIT 5 + +/* + * Upon VFIO_DEVICE_FEATURE_SET start/stop device DMA logging. + * VFIO_DEVICE_FEATURE_PROBE can be used to detect if the device supports + * DMA logging. + * + * DMA logging allows a device to internally record what DMAs the device is + * initiating and report them back to userspace. It is part of the VFIO + * migration infrastructure that allows implementing dirty page tracking + * during the pre copy phase of live migration. Only DMA WRITEs are logged, + * and this API is not connected to VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE. + * + * When DMA logging is started a range of IOVAs to monitor is provided and the + * device can optimize its logging to cover only the IOVA range given. Each + * DMA that the device initiates inside the range will be logged by the device + * for later retrieval. + * + * page_size is an input that hints what tracking granularity the device + * should try to achieve. If the device cannot do the hinted page size then + * it's the driver choice which page size to pick based on its support. + * On output the device will return the page size it selected. + * + * ranges is a pointer to an array of + * struct vfio_device_feature_dma_logging_range. + * + * The core kernel code guarantees to support by minimum num_ranges that fit + * into a single kernel page. User space can try higher values but should give + * up if the above can't be achieved as of some driver limitations. + * + * A single call to start device DMA logging can be issued and a matching stop + * should follow at the end. Another start is not allowed in the meantime. + */ +struct vfio_device_feature_dma_logging_control { + __aligned_u64 page_size; + __u32 num_ranges; + __u32 __reserved; + __aligned_u64 ranges; +}; + +struct vfio_device_feature_dma_logging_range { + __aligned_u64 iova; + __aligned_u64 length; +}; + +#define VFIO_DEVICE_FEATURE_DMA_LOGGING_START 6 + +/* + * Upon VFIO_DEVICE_FEATURE_SET stop device DMA logging that was started + * by VFIO_DEVICE_FEATURE_DMA_LOGGING_START + */ +#define VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP 7 + +/* + * Upon VFIO_DEVICE_FEATURE_GET read back and clear the device DMA log + * + * Query the device's DMA log for written pages within the given IOVA range. + * During querying the log is cleared for the IOVA range. + * + * bitmap is a pointer to an array of u64s that will hold the output bitmap + * with 1 bit reporting a page_size unit of IOVA. The mapping of IOVA to bits + * is given by: + * bitmap[(addr - iova)/page_size] & (1ULL << (addr % 64)) + * + * The input page_size can be any power of two value and does not have to + * match the value given to VFIO_DEVICE_FEATURE_DMA_LOGGING_START. The driver + * will format its internal logging to match the reporting page size, possibly + * by replicating bits if the internal page size is lower than requested. + * + * The LOGGING_REPORT will only set bits in the bitmap and never clear or + * perform any initialization of the user provided bitmap. + * + * If any error is returned userspace should assume that the dirty log is + * corrupted. Error recovery is to consider all memory dirty and try to + * restart the dirty tracking, or to abort/restart the whole migration. + * + * If DMA logging is not enabled, an error will be returned. + * + */ +struct vfio_device_feature_dma_logging_report { + __aligned_u64 iova; + __aligned_u64 length; + __aligned_u64 page_size; + __aligned_u64 bitmap; +}; + +#define VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT 8 + +/* + * Upon VFIO_DEVICE_FEATURE_GET read back the estimated data length that will + * be required to complete stop copy. + * + * Note: Can be called on each device state. + */ + +struct vfio_device_feature_mig_data_size { + __aligned_u64 stop_copy_length; +}; + +#define VFIO_DEVICE_FEATURE_MIG_DATA_SIZE 9 + /* -------- API for Type1 VFIO IOMMU -------- */ /** @@ -1004,6 +1451,7 @@ 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; }; /* @@ -1073,12 +1521,21 @@ struct vfio_iommu_type1_info_dma_avail { * * Map process virtual addresses to IO virtual addresses using the * provided struct vfio_dma_map. Caller sets argsz. READ &/ WRITE required. + * + * If flags & VFIO_DMA_MAP_FLAG_VADDR, update the base vaddr for iova. The vaddr + * must have previously been invalidated with VFIO_DMA_UNMAP_FLAG_VADDR. To + * maintain memory consistency within the user application, the updated vaddr + * must address the same memory object as originally mapped. Failure to do so + * will result in user memory corruption and/or device misbehavior. iova and + * size must match those in the original MAP_DMA call. Protection is not + * changed, and the READ & WRITE flags must be 0. */ struct vfio_iommu_type1_dma_map { __u32 argsz; __u32 flags; #define VFIO_DMA_MAP_FLAG_READ (1 << 0) /* readable from device */ #define VFIO_DMA_MAP_FLAG_WRITE (1 << 1) /* writable from device */ +#define VFIO_DMA_MAP_FLAG_VADDR (1 << 2) __u64 vaddr; /* Process virtual address */ __u64 iova; /* IO virtual address */ __u64 size; /* Size of mapping (bytes) */ @@ -1101,6 +1558,7 @@ struct vfio_bitmap { * field. No guarantee is made to the user that arbitrary unmaps of iova * or size different from those used in the original mapping call will * succeed. + * * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get the dirty bitmap * before unmapping IO virtual addresses. When this flag is set, the user must * provide a struct vfio_bitmap in data[]. User must provide zero-allocated @@ -1110,11 +1568,21 @@ struct vfio_bitmap { * indicates that the page at that offset from iova is dirty. A Bitmap of the * pages in the range of unmapped size is returned in the user-provided * vfio_bitmap.data. + * + * If flags & VFIO_DMA_UNMAP_FLAG_ALL, unmap all addresses. iova and size + * must be 0. This cannot be combined with the get-dirty-bitmap flag. + * + * If flags & VFIO_DMA_UNMAP_FLAG_VADDR, do not unmap, but invalidate host + * virtual addresses in the iova range. DMA to already-mapped pages continues. + * Groups may not be added to the container while any addresses are invalid. + * This cannot be combined with the get-dirty-bitmap flag. */ struct vfio_iommu_type1_dma_unmap { __u32 argsz; __u32 flags; #define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0) +#define VFIO_DMA_UNMAP_FLAG_ALL (1 << 1) +#define VFIO_DMA_UNMAP_FLAG_VADDR (1 << 2) __u64 iova; /* IO virtual address */ __u64 size; /* Size of mapping (bytes) */ __u8 data[]; |