This header will be used by the Vhost library. Including also uapi/linux/stddef.h, which defines __counted_by if the compiler does not support it.
Signed-off-by: Eugenio Pérez <[email protected]> --- kernel/linux/uapi/linux/stddef.h | 85 +++++++++++++++++++++++ kernel/linux/uapi/linux/vduse.h | 115 +++++++++++++++++++++++++++++-- kernel/linux/uapi/linux/vfio.h | 91 +++++++++++++++++++++++- kernel/linux/uapi/version | 2 +- 4 files changed, 284 insertions(+), 9 deletions(-) create mode 100644 kernel/linux/uapi/linux/stddef.h diff --git a/kernel/linux/uapi/linux/stddef.h b/kernel/linux/uapi/linux/stddef.h new file mode 100644 index 000000000000..3d238e09c8f8 --- /dev/null +++ b/kernel/linux/uapi/linux/stddef.h @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_STDDEF_H +#define _LINUX_STDDEF_H + +#ifdef __KERNEL__ +#include <linux/compiler_types.h> +#endif + +#ifndef __always_inline +#define __always_inline inline +#endif + +/* Not all C++ standards support type declarations inside an anonymous union */ +#ifndef __cplusplus +#define __struct_group_tag(TAG) TAG +#else +#define __struct_group_tag(TAG) +#endif + +/** + * __struct_group() - Create a mirrored named and anonyomous struct + * + * @TAG: The tag name for the named sub-struct (usually empty) + * @NAME: The identifier name of the mirrored sub-struct + * @ATTRS: Any struct attributes (usually empty) + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical layout + * and size: one anonymous and one named. The former's members can be used + * normally without sub-struct naming, and the latter can be used to + * reason about the start, end, and size of the group of struct members. + * The named struct can also be explicitly tagged for layer reuse (C only), + * as well as both having struct attributes appended. + */ +#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ + union { \ + struct { MEMBERS } ATTRS; \ + struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \ + } ATTRS + +#ifdef __cplusplus +/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */ +#define __DECLARE_FLEX_ARRAY(T, member) \ + T member[0] +#else +/** + * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define __DECLARE_FLEX_ARRAY(TYPE, NAME) \ + struct { \ + struct { } __empty_ ## NAME; \ + TYPE NAME[]; \ + } +#endif + +#ifndef __counted_by +#define __counted_by(m) +#endif + +#ifndef __counted_by_le +#define __counted_by_le(m) +#endif + +#ifndef __counted_by_be +#define __counted_by_be(m) +#endif + +#ifndef __counted_by_ptr +#define __counted_by_ptr(m) +#endif + +#ifdef __KERNEL__ +#define __kernel_nonstring __nonstring +#else +#define __kernel_nonstring +#endif + +#endif /* _LINUX_STDDEF_H */ diff --git a/kernel/linux/uapi/linux/vduse.h b/kernel/linux/uapi/linux/vduse.h index f46269af349a..bab47129db63 100644 --- a/kernel/linux/uapi/linux/vduse.h +++ b/kernel/linux/uapi/linux/vduse.h @@ -10,6 +10,16 @@ #define VDUSE_API_VERSION 0 +/* VQ groups and ASID support */ + +#define VDUSE_API_VERSION_1 1 + +/* The VDUSE instance expects a request for vq ready */ +#define VDUSE_F_QUEUE_READY 0 + +/* The VDUSE instance expects a request for suspend */ +#define VDUSE_F_SUSPEND 1 + /* * Get the version of VDUSE API that kernel supported (VDUSE_API_VERSION). * This is used for future extension. @@ -27,6 +37,8 @@ * @features: virtio features * @vq_num: the number of virtqueues * @vq_align: the allocation alignment of virtqueue's metadata + * @ngroups: number of vq groups that VDUSE device declares + * @nas: number of address spaces that VDUSE device declares * @reserved: for future use, needs to be initialized to zero * @config_size: the size of the configuration space * @config: the buffer of the configuration space @@ -41,7 +53,9 @@ struct vduse_dev_config { __u64 features; __u32 vq_num; __u32 vq_align; - __u32 reserved[13]; + __u32 ngroups; /* if VDUSE_API_VERSION >= 1 */ + __u32 nas; /* if VDUSE_API_VERSION >= 1 */ + __u32 reserved[11]; __u32 config_size; __u8 config[]; }; @@ -55,6 +69,12 @@ struct vduse_dev_config { */ #define VDUSE_DESTROY_DEV _IOW(VDUSE_BASE, 0x03, char[VDUSE_NAME_MAX]) +/* Get the VDUSE supported features */ +#define VDUSE_GET_FEATURES _IOR(VDUSE_BASE, 0x04, __u64) + +/* Set the VDUSE features */ +#define VDUSE_SET_FEATURES _IOW(VDUSE_BASE, 0x05, __u64) + /* The ioctls for VDUSE device (/dev/vduse/$NAME) */ /** @@ -118,14 +138,18 @@ struct vduse_config_data { * struct vduse_vq_config - basic configuration of a virtqueue * @index: virtqueue index * @max_size: the max size of virtqueue - * @reserved: for future use, needs to be initialized to zero + * @reserved1: for future use, needs to be initialized to zero + * @group: virtqueue group + * @reserved2: for future use, needs to be initialized to zero * * Structure used by VDUSE_VQ_SETUP ioctl to setup a virtqueue. */ struct vduse_vq_config { __u32 index; __u16 max_size; - __u16 reserved[13]; + __u16 reserved1; + __u32 group; + __u16 reserved2[10]; }; /* @@ -156,6 +180,16 @@ struct vduse_vq_state_packed { __u16 last_used_idx; }; +/** + * struct vduse_vq_group_asid - virtqueue group ASID + * @group: Index of the virtqueue group + * @asid: Address space ID of the group + */ +struct vduse_vq_group_asid { + __u32 group; + __u32 asid; +}; + /** * struct vduse_vq_info - information of a virtqueue * @index: virtqueue index @@ -215,6 +249,7 @@ struct vduse_vq_eventfd { * @uaddr: start address of userspace memory, it must be aligned to page size * @iova: start of the IOVA region * @size: size of the IOVA region + * @asid: Address space ID of the IOVA region * @reserved: for future use, needs to be initialized to zero * * Structure used by VDUSE_IOTLB_REG_UMEM and VDUSE_IOTLB_DEREG_UMEM @@ -224,7 +259,8 @@ struct vduse_iova_umem { __u64 uaddr; __u64 iova; __u64 size; - __u64 reserved[3]; + __u32 asid; + __u32 reserved[5]; }; /* Register userspace memory for IOVA regions */ @@ -237,7 +273,8 @@ struct vduse_iova_umem { * struct vduse_iova_info - information of one IOVA region * @start: start of the IOVA region * @last: last of the IOVA region - * @capability: capability of the IOVA regsion + * @capability: capability of the IOVA region + * @asid: Address space ID of the IOVA region, only if device API version >= 1 * @reserved: for future use, needs to be initialized to zero * * Structure used by VDUSE_IOTLB_GET_INFO ioctl to get information of @@ -248,7 +285,8 @@ struct vduse_iova_info { __u64 last; #define VDUSE_IOVA_CAP_UMEM (1 << 0) __u64 capability; - __u64 reserved[3]; + __u32 asid; /* Only if device API version >= 1 */ + __u32 reserved[5]; }; /* @@ -257,6 +295,32 @@ struct vduse_iova_info { */ #define VDUSE_IOTLB_GET_INFO _IOWR(VDUSE_BASE, 0x1a, struct vduse_iova_info) +/** + * struct vduse_iotlb_entry_v2 - entry of IOTLB to describe one IOVA region + * + * @v1: the original vduse_iotlb_entry + * @asid: address space ID of the IOVA region + * @reserved: for future use, needs to be initialized to zero + * + * Structure used by VDUSE_IOTLB_GET_FD2 ioctl to find an overlapped IOVA region. + */ +struct vduse_iotlb_entry_v2 { + __u64 offset; + __u64 start; + __u64 last; + __u8 perm; + __u8 padding[7]; + __u32 asid; + __u32 reserved[11]; +}; + +/* + * Same as VDUSE_IOTLB_GET_FD but with vduse_iotlb_entry_v2 argument that + * support extra fields. + */ +#define VDUSE_IOTLB_GET_FD2 _IOWR(VDUSE_BASE, 0x1b, struct vduse_iotlb_entry_v2) + + /* The control messages definition for read(2)/write(2) on /dev/vduse/$NAME */ /** @@ -265,11 +329,16 @@ struct vduse_iova_info { * @VDUSE_SET_STATUS: set the device status * @VDUSE_UPDATE_IOTLB: Notify userspace to update the memory mapping for * specified IOVA range via VDUSE_IOTLB_GET_FD ioctl + * @VDUSE_SET_VQ_GROUP_ASID: Notify userspace to update the address space of a + * virtqueue group. */ enum vduse_req_type { VDUSE_GET_VQ_STATE, VDUSE_SET_STATUS, VDUSE_UPDATE_IOTLB, + VDUSE_SET_VQ_GROUP_ASID, + VDUSE_SET_VQ_READY, + VDUSE_SUSPEND, }; /** @@ -304,6 +373,28 @@ struct vduse_iova_range { __u64 last; }; +/** + * struct vduse_iova_range_v2 - IOVA range [start, last] if API_VERSION >= 1 + * @start: start of the IOVA range + * @last: last of the IOVA range + * @asid: address space ID of the IOVA range + */ +struct vduse_iova_range_v2 { + __u64 start; + __u64 last; + __u32 asid; + __u32 padding; +}; + +/** + * struct vduse_vq_ready - Virtqueue ready request message + * @num: Virtqueue number + */ +struct vduse_vq_ready { + __u32 num; + __u32 ready; +}; + /** * struct vduse_dev_request - control request * @type: request type @@ -312,6 +403,9 @@ struct vduse_iova_range { * @vq_state: virtqueue state, only index field is available * @s: device status * @iova: IOVA range for updating + * @iova_v2: IOVA range for updating if API_VERSION >= 1 + * @vq_group_asid: ASID of a virtqueue group + * @vq_ready: Virtqueue ready request * @padding: padding * * Structure used by read(2) on /dev/vduse/$NAME. @@ -324,6 +418,15 @@ struct vduse_dev_request { struct vduse_vq_state vq_state; struct vduse_dev_status s; struct vduse_iova_range iova; + /* Following members but padding exist only if vduse api + * version >= 1 + */ + struct vduse_iova_range_v2 iova_v2; + struct vduse_vq_group_asid vq_group_asid; + + /* Only if VDUSE_F_QUEUE_READY is negotiated */ + struct vduse_vq_ready vq_ready; + __u32 padding[32]; }; }; diff --git a/kernel/linux/uapi/linux/vfio.h b/kernel/linux/uapi/linux/vfio.h index 79bf8c0cc5e4..8e5c52ec1a47 100644 --- a/kernel/linux/uapi/linux/vfio.h +++ b/kernel/linux/uapi/linux/vfio.h @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/ioctl.h> +#include <uapi/linux/stddef.h> #define VFIO_API_VERSION 0 @@ -140,7 +141,7 @@ struct vfio_info_cap_header { * * Retrieve information about the group. Fills in provided * struct vfio_group_info. Caller sets argsz. - * Return: 0 on succes, -errno on failure. + * Return: 0 on success, -errno on failure. * Availability: Always */ struct vfio_group_status { @@ -905,10 +906,12 @@ struct vfio_device_feature { * 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. + * @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. * @@ -917,13 +920,21 @@ struct vfio_device_feature { * * 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) @@ -953,6 +964,10 @@ struct vfio_device_bind_iommufd { * hwpt corresponding to the given pt_id. * * Return: 0 on success, -errno on failure. + * + * When a device is resetting, -EBUSY will be returned to reject any concurrent + * attachment to the resetting device itself or any sibling device in the IOMMU + * group having the resetting device. */ struct vfio_device_attach_iommufd_pt { __u32 argsz; @@ -1251,6 +1266,19 @@ enum vfio_device_mig_state { * 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. + * The presence of the VFIO_PRECOPY_INFO_REINIT output flag indicates + * that new initial data is present on the stream. + * The new initial data may result, for example, from device reconfiguration + * during migration that requires additional initialization data. + * In that case initial_bytes may report a non-zero value irrespective of + * any previously reported values, which progresses towards zero as precopy + * data is read from the data stream. dirty_bytes is also reset + * to zero and represents the state change of the device relative to the new + * initial_bytes. + * VFIO_PRECOPY_INFO_REINIT can be reported only after userspace opts in to + * VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2. Without this opt-in, the flags field + * of struct vfio_precopy_info is reserved for bug-compatibility reasons. + * * It is recommended to leave PRE_COPY for STOP_COPY only after this field * reaches zero. Leaving PRE_COPY earlier might make things slower. * @@ -1286,6 +1314,7 @@ enum vfio_device_mig_state { struct vfio_precopy_info { __u32 argsz; __u32 flags; +#define VFIO_PRECOPY_INFO_REINIT (1 << 0) /* output - new initial data is present */ __aligned_u64 initial_bytes; __aligned_u64 dirty_bytes; }; @@ -1468,6 +1497,64 @@ struct vfio_device_feature_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); +}; + +/* + * Enables the migration precopy_info_v2 behaviour. + * + * VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2. + * + * On SET, enables the v2 pre_copy_info behaviour, where the + * vfio_precopy_info.flags is a valid output field. + */ +#define VFIO_DEVICE_FEATURE_MIG_PRECOPY_INFOv2 12 + +/** + * VFIO_DEVICE_FEATURE_ZPCI_ERROR feature provides PCI error information to + * userspace for vfio-pci devices on s390. On s390, PCI error recovery + * involves platform firmware and notification to operating systems is done + * by architecture specific mechanism. Exposing this information to + * userspace allows it to take appropriate actions to handle an + * error on the device. + * + * Userspace provides an opaque buffer of fixed length, and the kernel + * fills it with the zpci_ccdf_err data structure. The length of + * zpci_ccdf_err is provided to userspace via the + * VFIO_DEVICE_INFO_CAP_ZPCI_BASE capability. + * + * The ioctl returns -ENOMSG if there are no pending PCI errors. + */ +struct vfio_device_feature_zpci_err { + __aligned_u64 data; +}; + +#define VFIO_DEVICE_FEATURE_ZPCI_ERROR 13 + /* -------- API for Type1 VFIO IOMMU -------- */ /** diff --git a/kernel/linux/uapi/version b/kernel/linux/uapi/version index 966a9983019b..3d7303b036ad 100644 --- a/kernel/linux/uapi/version +++ b/kernel/linux/uapi/version @@ -1 +1 @@ -v6.16 +v7.3-rc5 -- 2.55.0
