diff options
Diffstat (limited to 'include/uapi/linux/vfio.h')
| -rw-r--r-- | include/uapi/linux/vfio.h | 550 |
1 files changed, 549 insertions, 1 deletions
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 9e843a147ead..d7d8e0922376 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -46,6 +46,12 @@ */ #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 */ +#define VFIO_UPDATE_VADDR 10 + /* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between @@ -201,8 +207,11 @@ struct vfio_device_info { #define VFIO_DEVICE_FLAGS_AMBA (1 << 3) /* vfio-amba device */ #define VFIO_DEVICE_FLAGS_CCW (1 << 4) /* vfio-ccw device */ #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 */ __u32 num_regions; /* Max region index + 1 */ __u32 num_irqs; /* Max IRQ index + 1 */ + __u32 cap_offset; /* Offset within info struct of first cap */ }; #define VFIO_DEVICE_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 7) @@ -218,6 +227,15 @@ struct vfio_device_info { #define VFIO_DEVICE_API_CCW_STRING "vfio-ccw" #define VFIO_DEVICE_API_AP_STRING "vfio-ap" +/* + * The following capabilities are unique to s390 zPCI devices. Their contents + * are further-defined in vfio_zdev.h + */ +#define VFIO_DEVICE_INFO_CAP_ZPCI_BASE 1 +#define VFIO_DEVICE_INFO_CAP_ZPCI_GROUP 2 +#define VFIO_DEVICE_INFO_CAP_ZPCI_UTIL 3 +#define VFIO_DEVICE_INFO_CAP_ZPCI_PFIP 4 + /** * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8, * struct vfio_region_info) @@ -305,6 +323,7 @@ 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_DEPRECATED (3) /* sub-types for VFIO_REGION_TYPE_PCI_* */ @@ -316,6 +335,8 @@ 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) @@ -323,6 +344,8 @@ 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) @@ -378,6 +401,39 @@ struct vfio_region_gfx_edid { /* sub-types for VFIO_REGION_TYPE_CCW */ #define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD (1) +#define VFIO_REGION_SUBTYPE_CCW_SCHIB (2) +#define VFIO_REGION_SUBTYPE_CCW_CRW (3) + +/* sub-types for VFIO_REGION_TYPE_MIGRATION */ +#define VFIO_REGION_SUBTYPE_MIGRATION_DEPRECATED (1) + +struct vfio_device_migration_info { + __u32 device_state; /* VFIO device state */ +#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_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_V1_SAVING | \ + VFIO_DEVICE_STATE_V1_RESUMING)) + +#define VFIO_DEVICE_STATE_SET_ERROR(state) \ + ((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_STATE_V1_SAVING | \ + VFIO_DEVICE_STATE_V1_RESUMING) + + __u32 reserved; + __u64 pending_bytes; + __u64 data_offset; + __u64 data_size; +}; /* * The MSIX mappable capability informs that MSIX data of a BAR can be mmapped @@ -393,6 +449,8 @@ struct vfio_region_gfx_edid { * 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 @@ -407,6 +465,8 @@ 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 @@ -577,11 +637,13 @@ enum { enum { VFIO_CCW_IO_IRQ_INDEX, + VFIO_CCW_CRW_IRQ_INDEX, + VFIO_CCW_REQ_IRQ_INDEX, VFIO_CCW_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) * * Return: 0 on success, -errno on failure: @@ -707,6 +769,365 @@ struct vfio_device_ioeventfd { #define VFIO_DEVICE_IOEVENTFD _IO(VFIO_TYPE, VFIO_BASE + 16) +/** + * 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 + * using the FEATURE_MASK portion of the flags field. Support for a feature + * can be probed by setting both the FEATURE_MASK and PROBE bits. A probe + * may optionally include the GET and/or SET bits to determine read vs write + * access of the feature respectively. Probing a feature will return success + * if the feature is supported and all of the optionally indicated GET/SET + * methods are supported. The format of the data portion of the structure is + * specific to the given feature. The data portion is not required for + * probing. GET and SET are mutually exclusive, except for use with PROBE. + * + * Return 0 on success, -errno on failure. + */ +struct vfio_device_feature { + __u32 argsz; + __u32 flags; +#define VFIO_DEVICE_FEATURE_MASK (0xffff) /* 16-bit feature index */ +#define VFIO_DEVICE_FEATURE_GET (1 << 16) /* Get feature into data[] */ +#define VFIO_DEVICE_FEATURE_SET (1 << 17) /* Set feature from data[] */ +#define VFIO_DEVICE_FEATURE_PROBE (1 << 18) /* Probe feature support */ + __u8 data[]; +}; + +#define VFIO_DEVICE_FEATURE _IO(VFIO_TYPE, VFIO_BASE + 17) + +/* + * 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 + * open VFs. Data provided when setting this feature is a 16-byte array + * (__u8 b[16]), representing a UUID. + */ +#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. + * + * 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_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 1 optional state to support VFIO_MIGRATION_P2P: + * RUNNING_P2P - RUNNING, 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. + * + * 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. + * + * RUNNING -> RUNNING_P2P + * STOP -> RUNNING_P2P + * While in RUNNING_P2P the device is partially running in the P2P quiescent + * state defined below. + * + * STOP -> STOP_COPY + * This arc begin the process of saving the device state and will return a + * new data_fd. + * + * 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. + * + * 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 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. + * 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. + */ +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, +}; + +/* + * 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 + /* -------- API for Type1 VFIO IOMMU -------- */ /** @@ -748,6 +1169,44 @@ struct vfio_iommu_type1_info_cap_iova_range { struct vfio_iova_range iova_ranges[]; }; +/* + * The migration capability allows to report supported features for migration. + * + * The structures below define version 1 of this capability. + * + * The existence of this capability indicates that IOMMU kernel driver supports + * dirty page logging. + * + * pgsize_bitmap: Kernel driver returns bitmap of supported page sizes for dirty + * page logging. + * max_dirty_bitmap_size: Kernel driver returns maximum supported dirty bitmap + * size in bytes that can be used by user applications when getting the dirty + * bitmap. + */ +#define VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION 2 + +struct vfio_iommu_type1_info_cap_migration { + struct vfio_info_cap_header header; + __u32 flags; + __u64 pgsize_bitmap; + __u64 max_dirty_bitmap_size; /* in bytes */ +}; + +/* + * The DMA available capability allows to report the current number of + * simultaneously outstanding DMA mappings that are allowed. + * + * The structure below defines version 1 of this capability. + * + * avail: specifies the current number of outstanding DMA mappings allowed. + */ +#define VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL 3 + +struct vfio_iommu_type1_info_dma_avail { + struct vfio_info_cap_header header; + __u32 avail; +}; + #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12) /** @@ -755,12 +1214,22 @@ struct vfio_iommu_type1_info_cap_iova_range { * * 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, and + * unblock translation of host virtual addresses in the iova range. 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) */ @@ -768,6 +1237,12 @@ struct vfio_iommu_type1_dma_map { #define VFIO_IOMMU_MAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 13) +struct vfio_bitmap { + __u64 pgsize; /* page size for bitmap in bytes */ + __u64 size; /* in bytes */ + __u64 __user *data; /* one bit per page */ +}; + /** * VFIO_IOMMU_UNMAP_DMA - _IOWR(VFIO_TYPE, VFIO_BASE + 14, * struct vfio_dma_unmap) @@ -777,12 +1252,34 @@ struct vfio_iommu_type1_dma_map { * 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 + * memory via vfio_bitmap.data and its size in the vfio_bitmap.size field. + * A bit in the bitmap represents one page, of user provided page size in + * vfio_bitmap.pgsize field, consecutively starting from iova offset. Bit set + * 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. Tasks that attempt to translate an + * iova's vaddr will block. DMA to already-mapped pages continues. 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[]; }; #define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14) @@ -794,6 +1291,57 @@ struct vfio_iommu_type1_dma_unmap { #define VFIO_IOMMU_ENABLE _IO(VFIO_TYPE, VFIO_BASE + 15) #define VFIO_IOMMU_DISABLE _IO(VFIO_TYPE, VFIO_BASE + 16) +/** + * VFIO_IOMMU_DIRTY_PAGES - _IOWR(VFIO_TYPE, VFIO_BASE + 17, + * struct vfio_iommu_type1_dirty_bitmap) + * IOCTL is used for dirty pages logging. + * Caller should set flag depending on which operation to perform, details as + * below: + * + * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_START flag set, instructs + * the IOMMU driver to log pages that are dirtied or potentially dirtied by + * the device; designed to be used when a migration is in progress. Dirty pages + * are logged until logging is disabled by user application by calling the IOCTL + * with VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP flag. + * + * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP flag set, instructs + * the IOMMU driver to stop logging dirtied pages. + * + * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP flag set + * returns the dirty pages bitmap for IOMMU container for a given IOVA range. + * The user must specify the IOVA range and the pgsize through the structure + * vfio_iommu_type1_dirty_bitmap_get in the data[] portion. This interface + * supports getting a bitmap of the smallest supported pgsize only and can be + * modified in future to get a bitmap of any specified supported pgsize. The + * user must provide a zeroed memory area for the bitmap memory and specify its + * size in bitmap.size. One bit is used to represent one page consecutively + * starting from iova offset. The user should provide page size in bitmap.pgsize + * field. A bit set in the bitmap indicates that the page at that offset from + * iova is dirty. The caller must set argsz to a value including the size of + * structure vfio_iommu_type1_dirty_bitmap_get, but excluding the size of the + * actual bitmap. If dirty pages logging is not enabled, an error will be + * returned. + * + * Only one of the flags _START, _STOP and _GET may be specified at a time. + * + */ +struct vfio_iommu_type1_dirty_bitmap { + __u32 argsz; + __u32 flags; +#define VFIO_IOMMU_DIRTY_PAGES_FLAG_START (1 << 0) +#define VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP (1 << 1) +#define VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP (1 << 2) + __u8 data[]; +}; + +struct vfio_iommu_type1_dirty_bitmap_get { + __u64 iova; /* IO virtual address */ + __u64 size; /* Size of iova range */ + struct vfio_bitmap bitmap; +}; + +#define VFIO_IOMMU_DIRTY_PAGES _IO(VFIO_TYPE, VFIO_BASE + 17) + /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */ /* |