|
|
|
@ -986,6 +986,148 @@ enum vfio_device_mig_state { |
|
|
|
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 -------- */ |
|
|
|
|
|
|
|
/**
|
|
|
|
|
Peter Xu
4 years ago
Juan Quintela