This header will be used by the Vhost library.
Reviewed-by: Maxime Coquelin <[email protected]>
Signed-off-by: Eugenio Pérez <[email protected]>
---
kernel/linux/uapi/linux/iommufd.h | 105 +++++++++++++++++++++++++--
kernel/linux/uapi/linux/vduse.h | 113 ++++++++++++++++++++++++++++--
kernel/linux/uapi/linux/vfio.h | 51 +++++++++++++-
kernel/linux/uapi/version | 2 +-
4 files changed, 257 insertions(+), 14 deletions(-)
diff --git a/kernel/linux/uapi/linux/iommufd.h
b/kernel/linux/uapi/linux/iommufd.h
index 5ee08de08388..26b1cb9465e2 100644
--- a/kernel/linux/uapi/linux/iommufd.h
+++ b/kernel/linux/uapi/linux/iommufd.h
@@ -57,6 +57,7 @@ enum {
IOMMUFD_CMD_IOAS_CHANGE_PROCESS = 0x92,
IOMMUFD_CMD_VEVENTQ_ALLOC = 0x93,
IOMMUFD_CMD_HW_QUEUE_ALLOC = 0x94,
+ IOMMUFD_CMD_IOAS_NOIOMMU_GET_PA = 0x95,
};
/**
@@ -219,18 +220,49 @@ struct iommu_ioas_map {
};
#define IOMMU_IOAS_MAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_MAP)
+/**
+ * struct iommu_ioas_noiommu_get_pa - ioctl(IOMMU_IOAS_NOIOMMU_GET_PA)
+ * @size: sizeof(struct iommu_ioas_noiommu_get_pa)
+ * @flags: Reserved, must be 0 for now
+ * @ioas_id: IOAS ID to query IOVA to PA mapping from
+ * @__reserved: Must be 0
+ * @iova: IOVA to query
+ * @length: On input, non-zero maximum number of bytes to query starting from
+ * @iova. On output, number of physically contiguous bytes starting
+ * from @out_phys, capped by the input length.
+ * @out_phys: Output physical address the IOVA maps to
+ *
+ * Query the physical address backing an IOVA range. The beginning of the
+ * range must be mapped already and length must be non-zero. For noiommu
+ * devices doing unsafe DMA only.
+ */
+struct iommu_ioas_noiommu_get_pa {
+ __u32 size;
+ __u32 flags;
+ __u32 ioas_id;
+ __u32 __reserved;
+ __aligned_u64 iova;
+ __aligned_u64 length;
+ __aligned_u64 out_phys;
+};
+#define IOMMU_IOAS_NOIOMMU_GET_PA _IO(IOMMUFD_TYPE,
IOMMUFD_CMD_IOAS_NOIOMMU_GET_PA)
+
/**
* struct iommu_ioas_map_file - ioctl(IOMMU_IOAS_MAP_FILE)
* @size: sizeof(struct iommu_ioas_map_file)
* @flags: same as for iommu_ioas_map
* @ioas_id: same as for iommu_ioas_map
- * @fd: the memfd to map
- * @start: byte offset from start of file to map from
+ * @fd: the memfd or supported dma-buf file to map
+ * @start: byte offset from start of the file to map from
* @length: same as for iommu_ioas_map
* @iova: same as for iommu_ioas_map
*
- * Set an IOVA mapping from a memfd file. All other arguments and semantics
- * match those of IOMMU_IOAS_MAP.
+ * Set an IOVA mapping from a memfd file. On kernels with dma-buf support,
+ * supported dma-buf files may also be accepted. This is not a generic
+ * dma-buf import path; currently supported dma-bufs include single-range
+ * VFIO PCI dma-bufs exported through VFIO_DEVICE_FEATURE_DMA_BUF, and
+ * other dma-bufs may be rejected. All other arguments and semantics match
+ * those of IOMMU_IOAS_MAP.
*/
struct iommu_ioas_map_file {
__u32 size;
@@ -465,16 +497,27 @@ struct iommu_hwpt_arm_smmuv3 {
__aligned_le64 ste[2];
};
+/**
+ * struct iommu_hwpt_amd_guest - AMD IOMMU guest I/O page table data
+ * (IOMMU_HWPT_DATA_AMD_GUEST)
+ * @dte: Guest Device Table Entry (DTE)
+ */
+struct iommu_hwpt_amd_guest {
+ __aligned_u64 dte[4];
+};
+
/**
* enum iommu_hwpt_data_type - IOMMU HWPT Data Type
* @IOMMU_HWPT_DATA_NONE: no data
* @IOMMU_HWPT_DATA_VTD_S1: Intel VT-d stage-1 page table
* @IOMMU_HWPT_DATA_ARM_SMMUV3: ARM SMMUv3 Context Descriptor Table
+ * @IOMMU_HWPT_DATA_AMD_GUEST: AMD IOMMU guest page table
*/
enum iommu_hwpt_data_type {
IOMMU_HWPT_DATA_NONE = 0,
IOMMU_HWPT_DATA_VTD_S1 = 1,
IOMMU_HWPT_DATA_ARM_SMMUV3 = 2,
+ IOMMU_HWPT_DATA_AMD_GUEST = 3,
};
/**
@@ -559,11 +602,22 @@ struct iommu_hw_info_vtd {
__aligned_u64 ecap_reg;
};
+/**
+ * enum iommu_hw_info_arm_smmuv3_flags - Flags for ARM SMMUv3 hw_info
+ * @IOMMU_HW_INFO_ARM_SMMUV3_ERRATA_REPEAT_TLBI_CFGI:
+ * If set, user space must issue TLBI/CFGI+SYNC commands twice due to
+ * hardware erratum T264-SMMU-3. See the description at
+ * arm_smmu_erratum_repeat_tlbi_cfgi_key.
+ */
+enum iommu_hw_info_arm_smmuv3_flags {
+ IOMMU_HW_INFO_ARM_SMMUV3_ERRATA_REPEAT_TLBI_CFGI = 1 << 0,
+};
+
/**
* struct iommu_hw_info_arm_smmuv3 - ARM SMMUv3 hardware information
* (IOMMU_HW_INFO_TYPE_ARM_SMMUV3)
*
- * @flags: Must be set to 0
+ * @flags: Combination of enum iommu_hw_info_arm_smmuv3_flags
* @__reserved: Must be 0
* @idr: Implemented features for ARM SMMU Non-secure programming interface
* @iidr: Information about the implementation and implementer of ARM SMMU,
@@ -579,7 +633,7 @@ struct iommu_hw_info_vtd {
* idr[0]: ST_LEVEL, TERM_MODEL, STALL_MODEL, TTENDIAN , CD2L, ASID16, TTF
* idr[1]: SIDSIZE, SSIDSIZE
* idr[3]: BBML, RIL
- * idr[5]: VAX, GRAN64K, GRAN16K, GRAN4K
+ * idr[5]: VAX, GRAN64K, GRAN16K, GRAN4K, DS
*
* - S1P should be assumed to be true if a NESTED HWPT can be created
* - VFIO/iommufd only support platforms with COHACC, it should be assumed to
be
@@ -587,7 +641,7 @@ struct iommu_hw_info_vtd {
* - ATS is a per-device property. If the VMM describes any devices as ATS
* capable in ACPI/DT it should set the corresponding idr.
*
- * This list may expand in future (eg E0PD, AIE, PBHA, D128, DS etc). It is
+ * This list may expand in future (eg E0PD, AIE, PBHA, D128 etc). It is
* important that VMMs do not read bits outside the list to allow for
* compatibility with future kernels. Several features in the SMMUv3
* architecture are not currently supported by the kernel for nesting: HTTU,
@@ -623,6 +677,32 @@ struct iommu_hw_info_tegra241_cmdqv {
__u8 __reserved;
};
+/**
+ * struct iommu_hw_info_amd - AMD IOMMU device info
+ *
+ * @efr : Value of AMD IOMMU Extended Feature Register (EFR)
+ * @efr2: Value of AMD IOMMU Extended Feature 2 Register (EFR2)
+ *
+ * Please See description of these registers in the following sections of
+ * the AMD I/O Virtualization Technology (IOMMU) Specification.
+ * (https://docs.amd.com/v/u/en-US/48882_3.10_PUB)
+ *
+ * - MMIO Offset 0030h IOMMU Extended Feature Register
+ * - MMIO Offset 01A0h IOMMU Extended Feature 2 Register
+ *
+ * Note: The EFR and EFR2 are raw values reported by hardware.
+ * VMM is responsible to determine the appropriate flags to be exposed to
+ * the VM since cetertain features are not currently supported by the kernel
+ * for HW-vIOMMU.
+ *
+ * Current VMM-allowed list of feature flags are:
+ * - EFR[GTSup, GASup, GioSup, PPRSup, EPHSup, GATS, GLX, PASmax]
+ */
+struct iommu_hw_info_amd {
+ __aligned_u64 efr;
+ __aligned_u64 efr2;
+};
+
/**
* enum iommu_hw_info_type - IOMMU Hardware Info Types
* @IOMMU_HW_INFO_TYPE_NONE: Output by the drivers that do not report hardware
@@ -632,6 +712,7 @@ struct iommu_hw_info_tegra241_cmdqv {
* @IOMMU_HW_INFO_TYPE_ARM_SMMUV3: ARM SMMUv3 iommu info type
* @IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV: NVIDIA Tegra241 CMDQV (extension for ARM
* SMMUv3) info type
+ * @IOMMU_HW_INFO_TYPE_AMD: AMD IOMMU info type
*/
enum iommu_hw_info_type {
IOMMU_HW_INFO_TYPE_NONE = 0,
@@ -639,6 +720,7 @@ enum iommu_hw_info_type {
IOMMU_HW_INFO_TYPE_INTEL_VTD = 1,
IOMMU_HW_INFO_TYPE_ARM_SMMUV3 = 2,
IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV = 3,
+ IOMMU_HW_INFO_TYPE_AMD = 4,
};
/**
@@ -656,11 +738,15 @@ enum iommu_hw_info_type {
* @IOMMU_HW_CAP_PCI_PASID_PRIV: Privileged Mode Supported, user ignores it
* when the struct
* iommu_hw_info::out_max_pasid_log2 is zero.
+ * @IOMMU_HW_CAP_PCI_ATS_NOT_SUPPORTED: ATS is not supported or cannot be used
+ * on this device (absence implies ATS
+ * may be enabled)
*/
enum iommufd_hw_capabilities {
IOMMU_HW_CAP_DIRTY_TRACKING = 1 << 0,
IOMMU_HW_CAP_PCI_PASID_EXEC = 1 << 1,
IOMMU_HW_CAP_PCI_PASID_PRIV = 1 << 2,
+ IOMMU_HW_CAP_PCI_ATS_NOT_SUPPORTED = 1 << 3,
};
/**
@@ -1013,6 +1099,11 @@ struct iommu_fault_alloc {
enum iommu_viommu_type {
IOMMU_VIOMMU_TYPE_DEFAULT = 0,
IOMMU_VIOMMU_TYPE_ARM_SMMUV3 = 1,
+ /*
+ * TEGRA241_CMDQV requirements (otherwise, VCMDQs will not work)
+ * - Kernel will allocate a VINTF (HYP_OWN=0) to back this VIOMMU. So,
+ * VMM must wire the HYP_OWN bit to 0 in guest VINTF_CONFIG register
+ */
IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV = 2,
};
diff --git a/kernel/linux/uapi/linux/vduse.h b/kernel/linux/uapi/linux/vduse.h
index 6e4c67a00f8b..9c71b79e70cc 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 */
@@ -238,6 +274,7 @@ struct vduse_iova_umem {
* @start: start of the IOVA region
* @last: last of the IOVA region
* @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 c2e4839f83eb..daa94bf69367 100644
--- a/kernel/linux/uapi/linux/vfio.h
+++ b/kernel/linux/uapi/linux/vfio.h
@@ -141,7 +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 {
@@ -964,6 +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;
@@ -1262,6 +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.
*
@@ -1297,6 +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;
};
@@ -1506,6 +1524,37 @@ struct vfio_device_feature_dma_buf {
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 69f29b2320e4..8036d72f9f0c 100644
--- a/kernel/linux/uapi/version
+++ b/kernel/linux/uapi/version
@@ -1 +1 @@
-v6.19
+v7.3-rc7
--
2.56.0
