diff options
Diffstat (limited to 'include/uapi/linux/vfio.h')
| -rw-r--r-- | include/uapi/linux/vfio.h | 248 |
1 files changed, 234 insertions, 14 deletions
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 20c804bdc09c..ac2329f24141 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/ioctl.h> +#include <linux/stddef.h> #define VFIO_API_VERSION 0 @@ -35,7 +36,7 @@ #define VFIO_EEH 5 /* Two-stage IOMMU */ -#define VFIO_TYPE1_NESTING_IOMMU 6 /* Implies v2 */ +#define __VFIO_RESERVED_TYPE1_NESTING_IOMMU 6 /* Implies v2 */ #define VFIO_SPAPR_TCE_v2_IOMMU 7 @@ -217,6 +218,7 @@ 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) @@ -276,8 +278,8 @@ struct vfio_region_info { #define VFIO_REGION_INFO_FLAG_CAPS (1 << 3) /* Info supports caps */ __u32 index; /* Region index */ __u32 cap_offset; /* Offset within info struct of first cap */ - __u64 size; /* Region size (bytes) */ - __u64 offset; /* Region offset from start of device fd */ + __aligned_u64 size; /* Region size (bytes) */ + __aligned_u64 offset; /* Region offset from start of device fd */ }; #define VFIO_DEVICE_GET_REGION_INFO _IO(VFIO_TYPE, VFIO_BASE + 8) @@ -293,8 +295,8 @@ struct vfio_region_info { #define VFIO_REGION_INFO_CAP_SPARSE_MMAP 1 struct vfio_region_sparse_mmap_area { - __u64 offset; /* Offset of mmap'able area within region */ - __u64 size; /* Size of mmap'able area */ + __aligned_u64 offset; /* Offset of mmap'able area within region */ + __aligned_u64 size; /* Size of mmap'able area */ }; struct vfio_region_info_cap_sparse_mmap { @@ -449,9 +451,9 @@ struct vfio_device_migration_info { VFIO_DEVICE_STATE_V1_RESUMING) __u32 reserved; - __u64 pending_bytes; - __u64 data_offset; - __u64 data_size; + __aligned_u64 pending_bytes; + __aligned_u64 data_offset; + __aligned_u64 data_size; }; /* @@ -475,7 +477,7 @@ struct vfio_device_migration_info { struct vfio_region_info_cap_nvlink2_ssatgt { struct vfio_info_cap_header header; - __u64 tgt; + __aligned_u64 tgt; }; /* @@ -670,6 +672,7 @@ enum { */ enum { VFIO_AP_REQ_IRQ_INDEX, + VFIO_AP_CFG_CHG_IRQ_INDEX, VFIO_AP_NUM_IRQS }; @@ -677,11 +680,60 @@ 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 +742,8 @@ 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 +754,24 @@ 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 { @@ -746,7 +818,7 @@ struct vfio_device_gfx_plane_info { __u32 drm_plane_type; /* type of plane: DRM_PLANE_TYPE_* */ /* out */ __u32 drm_format; /* drm format of plane */ - __u64 drm_format_mod; /* tiled mode */ + __aligned_u64 drm_format_mod; /* tiled mode */ __u32 width; /* width of plane */ __u32 height; /* height of plane */ __u32 stride; /* stride of plane */ @@ -759,6 +831,7 @@ struct vfio_device_gfx_plane_info { __u32 region_index; /* region index */ __u32 dmabuf_id; /* dma-buf id */ }; + __u32 reserved; }; #define VFIO_DEVICE_QUERY_GFX_PLANE _IO(VFIO_TYPE, VFIO_BASE + 14) @@ -793,9 +866,10 @@ struct vfio_device_ioeventfd { #define VFIO_DEVICE_IOEVENTFD_32 (1 << 2) /* 4-byte write */ #define VFIO_DEVICE_IOEVENTFD_64 (1 << 3) /* 8-byte write */ #define VFIO_DEVICE_IOEVENTFD_SIZE_MASK (0xf) - __u64 offset; /* device fd offset of write */ - __u64 data; /* data to be written */ + __aligned_u64 offset; /* device fd offset of write */ + __aligned_u64 data; /* data to be written */ __s32 fd; /* -1 for de-assignment */ + __u32 reserved; }; #define VFIO_DEVICE_IOEVENTFD _IO(VFIO_TYPE, VFIO_BASE + 16) @@ -829,6 +903,102 @@ 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 or a bit flags of VFIO_DEVICE_BIND_* + * @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. + * @token_uuid_ptr: Valid if VFIO_DEVICE_BIND_FLAG_TOKEN. Points to a 16 byte + * UUID in the same format as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN. + * + * 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. + * + * A token is sometimes required to open the device, unless this is known to be + * needed VFIO_DEVICE_BIND_FLAG_TOKEN should not be set and token_uuid_ptr is + * ignored. The only case today is a PF/VF relationship where the VF bind must + * be provided the same token as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN provided to + * the PF. + * + * Return: 0 on success, -errno on failure. + */ +struct vfio_device_bind_iommufd { + __u32 argsz; + __u32 flags; +#define VFIO_DEVICE_BIND_FLAG_TOKEN (1 << 0) + __s32 iommufd; + __u32 out_devid; + __aligned_u64 token_uuid_ptr; +}; + +#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: Flags for attach. + * @pt_id: Input the target id which can represent an ioas or a hwpt + * allocated via iommufd subsystem. + * Output the input ioas id or the attached hwpt id which could + * be the specified hwpt itself or a hwpt automatically created + * for the specified ioas by kernel during the attachment. + * @pasid: The pasid to be attached, only meaningful when + * VFIO_DEVICE_ATTACH_PASID is set in @flags + * + * Associate the device with an address space within the bound iommufd. + * Undo by VFIO_DEVICE_DETACH_IOMMUFD_PT or device fd close. This is only + * allowed on cdev fds. + * + * If a vfio device or a pasid of this device is currently attached to a valid + * hw_pagetable (hwpt), without doing a VFIO_DEVICE_DETACH_IOMMUFD_PT, a second + * VFIO_DEVICE_ATTACH_IOMMUFD_PT ioctl passing in another hwpt id is allowed. + * This action, also known as a hw_pagetable replacement, will replace the + * currently attached hwpt of the device or the pasid of this device with a new + * hwpt corresponding to the given pt_id. + * + * Return: 0 on success, -errno on failure. + */ +struct vfio_device_attach_iommufd_pt { + __u32 argsz; + __u32 flags; +#define VFIO_DEVICE_ATTACH_PASID (1 << 0) + __u32 pt_id; + __u32 pasid; +}; + +#define VFIO_DEVICE_ATTACH_IOMMUFD_PT _IO(VFIO_TYPE, VFIO_BASE + 19) + +/* + * 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: Flags for detach. + * @pasid: The pasid to be detached, only meaningful when + * VFIO_DEVICE_DETACH_PASID is set in @flags + * + * Remove the association of the device or a pasid of the device and its current + * associated address space. After it, the device or the pasid should be in a + * blocking DMA state. This is only allowed on cdev fds. + * + * Return: 0 on success, -errno on failure. + */ +struct vfio_device_detach_iommufd_pt { + __u32 argsz; + __u32 flags; +#define VFIO_DEVICE_DETACH_PASID (1 << 0) + __u32 pasid; +}; + +#define VFIO_DEVICE_DETACH_IOMMUFD_PT _IO(VFIO_TYPE, VFIO_BASE + 20) + +/* * 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 @@ -1070,6 +1240,7 @@ enum vfio_device_mig_state { VFIO_DEVICE_STATE_RUNNING_P2P = 5, VFIO_DEVICE_STATE_PRE_COPY = 6, VFIO_DEVICE_STATE_PRE_COPY_P2P = 7, + VFIO_DEVICE_STATE_NR, }; /** @@ -1287,6 +1458,54 @@ struct vfio_device_feature_mig_data_size { #define VFIO_DEVICE_FEATURE_MIG_DATA_SIZE 9 +/** + * Upon VFIO_DEVICE_FEATURE_SET, set or clear the BUS mastering for the device + * based on the operation specified in op flag. + * + * The functionality is incorporated for devices that needs bus master control, + * but the in-band device interface lacks the support. Consequently, it is not + * applicable to PCI devices, as bus master control for PCI devices is managed + * in-band through the configuration space. At present, this feature is supported + * only for CDX devices. + * When the device's BUS MASTER setting is configured as CLEAR, it will result in + * blocking all incoming DMA requests from the device. On the other hand, configuring + * the device's BUS MASTER setting as SET (enable) will grant the device the + * capability to perform DMA to the host memory. + */ +struct vfio_device_feature_bus_master { + __u32 op; +#define VFIO_DEVICE_FEATURE_CLEAR_MASTER 0 /* Clear Bus Master */ +#define VFIO_DEVICE_FEATURE_SET_MASTER 1 /* Set Bus Master */ +}; +#define VFIO_DEVICE_FEATURE_BUS_MASTER 10 + +/** + * Upon VFIO_DEVICE_FEATURE_GET create a dma_buf fd for the + * regions selected. + * + * open_flags are the typical flags passed to open(2), eg O_RDWR, O_CLOEXEC, + * etc. offset/length specify a slice of the region to create the dmabuf from. + * nr_ranges is the total number of (P2P DMA) ranges that comprise the dmabuf. + * + * flags should be 0. + * + * Return: The fd number on success, -1 and errno is set on failure. + */ +#define VFIO_DEVICE_FEATURE_DMA_BUF 11 + +struct vfio_region_dma_range { + __u64 offset; + __u64 length; +}; + +struct vfio_device_feature_dma_buf { + __u32 region_index; + __u32 open_flags; + __u32 flags; + __u32 nr_ranges; + struct vfio_region_dma_range dma_ranges[] __counted_by(nr_ranges); +}; + /* -------- API for Type1 VFIO IOMMU -------- */ /** @@ -1302,8 +1521,9 @@ struct vfio_iommu_type1_info { __u32 flags; #define VFIO_IOMMU_INFO_PGSIZES (1 << 0) /* supported page sizes info */ #define VFIO_IOMMU_INFO_CAPS (1 << 1) /* Info supports caps */ - __u64 iova_pgsizes; /* Bitmap of supported page sizes */ + __aligned_u64 iova_pgsizes; /* Bitmap of supported page sizes */ __u32 cap_offset; /* Offset within info struct of first cap */ + __u32 pad; }; /* |