summaryrefslogtreecommitdiffstats
path: root/include/uapi
diff options
context:
space:
mode:
Diffstat (limited to 'include/uapi')
-rw-r--r--include/uapi/asm-generic/types.h6
-rw-r--r--include/uapi/linux/acrn.h5
-rw-r--r--include/uapi/linux/atmbr2684.h2
-rw-r--r--include/uapi/linux/f2fs.h1
-rw-r--r--include/uapi/linux/hsi/cs-protocol.h14
-rw-r--r--include/uapi/linux/hsi/hsi_char.h14
-rw-r--r--include/uapi/linux/idxd.h2
-rw-r--r--include/uapi/linux/if_alg.h1
-rw-r--r--include/uapi/linux/io_uring.h8
-rw-r--r--include/uapi/linux/iommufd.h347
-rw-r--r--include/uapi/linux/kvm.h34
-rw-r--r--include/uapi/linux/pci_regs.h1
-rw-r--r--include/uapi/linux/pr.h17
-rw-r--r--include/uapi/linux/serial.h55
-rw-r--r--include/uapi/linux/swab.h2
-rw-r--r--include/uapi/linux/usb/g_uvc.h3
-rw-r--r--include/uapi/linux/usb/video.h4
-rw-r--r--include/uapi/linux/vdpa.h4
-rw-r--r--include/uapi/linux/vfio.h136
-rw-r--r--include/uapi/misc/fastrpc.h7
-rw-r--r--include/uapi/misc/habanalabs.h93
-rw-r--r--include/uapi/rdma/hns-abi.h15
-rw-r--r--include/uapi/rdma/ib_user_ioctl_verbs.h3
-rw-r--r--include/uapi/rdma/ib_user_verbs.h21
-rw-r--r--include/uapi/rdma/mana-abi.h66
-rw-r--r--include/uapi/rdma/rdma_user_rxe.h8
26 files changed, 770 insertions, 99 deletions
diff --git a/include/uapi/asm-generic/types.h b/include/uapi/asm-generic/types.h
index dfaa50d99d8f..7ad4dd01b8bf 100644
--- a/include/uapi/asm-generic/types.h
+++ b/include/uapi/asm-generic/types.h
@@ -1,9 +1,9 @@
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_GENERIC_TYPES_H
-#define _ASM_GENERIC_TYPES_H
+#ifndef _UAPI_ASM_GENERIC_TYPES_H
+#define _UAPI_ASM_GENERIC_TYPES_H
/*
* int-ll64 is used everywhere now.
*/
#include <asm-generic/int-ll64.h>
-#endif /* _ASM_GENERIC_TYPES_H */
+#endif /* _UAPI_ASM_GENERIC_TYPES_H */
diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h
index ccf47ed92500..7b714c1902eb 100644
--- a/include/uapi/linux/acrn.h
+++ b/include/uapi/linux/acrn.h
@@ -12,7 +12,6 @@
#define _UAPI_ACRN_H
#include <linux/types.h>
-#include <linux/uuid.h>
#define ACRN_IO_REQUEST_MAX 16
@@ -186,7 +185,7 @@ struct acrn_ioreq_notify {
* @reserved0: Reserved and must be 0
* @vcpu_num: Number of vCPU in the VM. Return from hypervisor.
* @reserved1: Reserved and must be 0
- * @uuid: UUID of the VM. Pass to hypervisor directly.
+ * @uuid: Empty space never to be used again (used to be UUID of the VM)
* @vm_flag: Flag of the VM creating. Pass to hypervisor directly.
* @ioreq_buf: Service VM GPA of I/O request buffer. Pass to
* hypervisor directly.
@@ -198,7 +197,7 @@ struct acrn_vm_creation {
__u16 reserved0;
__u16 vcpu_num;
__u16 reserved1;
- guid_t uuid;
+ __u8 uuid[16];
__u64 vm_flag;
__u64 ioreq_buf;
__u64 cpu_affinity;
diff --git a/include/uapi/linux/atmbr2684.h b/include/uapi/linux/atmbr2684.h
index a9e2250cd720..d47c47d06f11 100644
--- a/include/uapi/linux/atmbr2684.h
+++ b/include/uapi/linux/atmbr2684.h
@@ -38,7 +38,7 @@
*/
#define BR2684_ENCAPS_VC (0) /* VC-mux */
#define BR2684_ENCAPS_LLC (1)
-#define BR2684_ENCAPS_AUTODETECT (2) /* Unsuported */
+#define BR2684_ENCAPS_AUTODETECT (2) /* Unsupported */
/*
* Is this VC bridged or routed?
diff --git a/include/uapi/linux/f2fs.h b/include/uapi/linux/f2fs.h
index 3121d127d5aa..955d440be104 100644
--- a/include/uapi/linux/f2fs.h
+++ b/include/uapi/linux/f2fs.h
@@ -42,6 +42,7 @@
struct f2fs_comp_option)
#define F2FS_IOC_DECOMPRESS_FILE _IO(F2FS_IOCTL_MAGIC, 23)
#define F2FS_IOC_COMPRESS_FILE _IO(F2FS_IOCTL_MAGIC, 24)
+#define F2FS_IOC_START_ATOMIC_REPLACE _IO(F2FS_IOCTL_MAGIC, 25)
/*
* should be same as XFS_IOC_GOINGDOWN.
diff --git a/include/uapi/linux/hsi/cs-protocol.h b/include/uapi/linux/hsi/cs-protocol.h
index c7f6e7672cb5..07c3bfb67463 100644
--- a/include/uapi/linux/hsi/cs-protocol.h
+++ b/include/uapi/linux/hsi/cs-protocol.h
@@ -6,20 +6,6 @@
*
* Contact: Kai Vehmanen <kai.vehmanen@nokia.com>
* Original author: Peter Ujfalusi <peter.ujfalusi@nokia.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
*/
#ifndef _CS_PROTOCOL_H
diff --git a/include/uapi/linux/hsi/hsi_char.h b/include/uapi/linux/hsi/hsi_char.h
index 91623b0398b1..5ef72f0daf94 100644
--- a/include/uapi/linux/hsi/hsi_char.h
+++ b/include/uapi/linux/hsi/hsi_char.h
@@ -5,20 +5,6 @@
* Copyright (C) 2010 Nokia Corporation. All rights reserved.
*
* Contact: Andras Domokos <andras.domokos at nokia.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
*/
#ifndef __HSI_CHAR_H
diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h
index 2b9e7feba3f3..1d553bedbdb5 100644
--- a/include/uapi/linux/idxd.h
+++ b/include/uapi/linux/idxd.h
@@ -295,7 +295,7 @@ struct dsa_completion_record {
};
uint32_t delta_rec_size;
- uint32_t crc_val;
+ uint64_t crc_val;
/* DIF check & strip */
struct {
diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h
index 578b18aab821..0824fbc026a1 100644
--- a/include/uapi/linux/if_alg.h
+++ b/include/uapi/linux/if_alg.h
@@ -52,6 +52,7 @@ struct af_alg_iv {
#define ALG_SET_AEAD_ASSOCLEN 4
#define ALG_SET_AEAD_AUTHSIZE 5
#define ALG_SET_DRBG_ENTROPY 6
+#define ALG_SET_KEY_BY_KEY_SERIAL 7
/* Operations */
#define ALG_OP_DECRYPT 0
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 9d4c4078e8d0..2780bce62faf 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -10,7 +10,15 @@
#include <linux/fs.h>
#include <linux/types.h>
+/*
+ * this file is shared with liburing and that has to autodetect
+ * if linux/time_types.h is available or not, it can
+ * define UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
+ * if linux/time_types.h is not available
+ */
+#ifndef UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
#include <linux/time_types.h>
+#endif
#ifdef __cplusplus
extern "C" {
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
new file mode 100644
index 000000000000..98ebba80cfa1
--- /dev/null
+++ b/include/uapi/linux/iommufd.h
@@ -0,0 +1,347 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES.
+ */
+#ifndef _UAPI_IOMMUFD_H
+#define _UAPI_IOMMUFD_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define IOMMUFD_TYPE (';')
+
+/**
+ * DOC: General ioctl format
+ *
+ * The ioctl interface follows a general format to allow for extensibility. Each
+ * ioctl is passed in a structure pointer as the argument providing the size of
+ * the structure in the first u32. The kernel checks that any structure space
+ * beyond what it understands is 0. This allows userspace to use the backward
+ * compatible portion while consistently using the newer, larger, structures.
+ *
+ * ioctls use a standard meaning for common errnos:
+ *
+ * - ENOTTY: The IOCTL number itself is not supported at all
+ * - E2BIG: The IOCTL number is supported, but the provided structure has
+ * non-zero in a part the kernel does not understand.
+ * - EOPNOTSUPP: The IOCTL number is supported, and the structure is
+ * understood, however a known field has a value the kernel does not
+ * understand or support.
+ * - EINVAL: Everything about the IOCTL was understood, but a field is not
+ * correct.
+ * - ENOENT: An ID or IOVA provided does not exist.
+ * - ENOMEM: Out of memory.
+ * - EOVERFLOW: Mathematics overflowed.
+ *
+ * As well as additional errnos, within specific ioctls.
+ */
+enum {
+ IOMMUFD_CMD_BASE = 0x80,
+ IOMMUFD_CMD_DESTROY = IOMMUFD_CMD_BASE,
+ IOMMUFD_CMD_IOAS_ALLOC,
+ IOMMUFD_CMD_IOAS_ALLOW_IOVAS,
+ IOMMUFD_CMD_IOAS_COPY,
+ IOMMUFD_CMD_IOAS_IOVA_RANGES,
+ IOMMUFD_CMD_IOAS_MAP,
+ IOMMUFD_CMD_IOAS_UNMAP,
+ IOMMUFD_CMD_OPTION,
+ IOMMUFD_CMD_VFIO_IOAS,
+};
+
+/**
+ * struct iommu_destroy - ioctl(IOMMU_DESTROY)
+ * @size: sizeof(struct iommu_destroy)
+ * @id: iommufd object ID to destroy. Can be any destroyable object type.
+ *
+ * Destroy any object held within iommufd.
+ */
+struct iommu_destroy {
+ __u32 size;
+ __u32 id;
+};
+#define IOMMU_DESTROY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_DESTROY)
+
+/**
+ * struct iommu_ioas_alloc - ioctl(IOMMU_IOAS_ALLOC)
+ * @size: sizeof(struct iommu_ioas_alloc)
+ * @flags: Must be 0
+ * @out_ioas_id: Output IOAS ID for the allocated object
+ *
+ * Allocate an IO Address Space (IOAS) which holds an IO Virtual Address (IOVA)
+ * to memory mapping.
+ */
+struct iommu_ioas_alloc {
+ __u32 size;
+ __u32 flags;
+ __u32 out_ioas_id;
+};
+#define IOMMU_IOAS_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOC)
+
+/**
+ * struct iommu_iova_range - ioctl(IOMMU_IOVA_RANGE)
+ * @start: First IOVA
+ * @last: Inclusive last IOVA
+ *
+ * An interval in IOVA space.
+ */
+struct iommu_iova_range {
+ __aligned_u64 start;
+ __aligned_u64 last;
+};
+
+/**
+ * struct iommu_ioas_iova_ranges - ioctl(IOMMU_IOAS_IOVA_RANGES)
+ * @size: sizeof(struct iommu_ioas_iova_ranges)
+ * @ioas_id: IOAS ID to read ranges from
+ * @num_iovas: Input/Output total number of ranges in the IOAS
+ * @__reserved: Must be 0
+ * @allowed_iovas: Pointer to the output array of struct iommu_iova_range
+ * @out_iova_alignment: Minimum alignment required for mapping IOVA
+ *
+ * Query an IOAS for ranges of allowed IOVAs. Mapping IOVA outside these ranges
+ * is not allowed. num_iovas will be set to the total number of iovas and
+ * the allowed_iovas[] will be filled in as space permits.
+ *
+ * The allowed ranges are dependent on the HW path the DMA operation takes, and
+ * can change during the lifetime of the IOAS. A fresh empty IOAS will have a
+ * full range, and each attached device will narrow the ranges based on that
+ * device's HW restrictions. Detaching a device can widen the ranges. Userspace
+ * should query ranges after every attach/detach to know what IOVAs are valid
+ * for mapping.
+ *
+ * On input num_iovas is the length of the allowed_iovas array. On output it is
+ * the total number of iovas filled in. The ioctl will return -EMSGSIZE and set
+ * num_iovas to the required value if num_iovas is too small. In this case the
+ * caller should allocate a larger output array and re-issue the ioctl.
+ *
+ * out_iova_alignment returns the minimum IOVA alignment that can be given
+ * to IOMMU_IOAS_MAP/COPY. IOVA's must satisfy::
+ *
+ * starting_iova % out_iova_alignment == 0
+ * (starting_iova + length) % out_iova_alignment == 0
+ *
+ * out_iova_alignment can be 1 indicating any IOVA is allowed. It cannot
+ * be higher than the system PAGE_SIZE.
+ */
+struct iommu_ioas_iova_ranges {
+ __u32 size;
+ __u32 ioas_id;
+ __u32 num_iovas;
+ __u32 __reserved;
+ __aligned_u64 allowed_iovas;
+ __aligned_u64 out_iova_alignment;
+};
+#define IOMMU_IOAS_IOVA_RANGES _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_IOVA_RANGES)
+
+/**
+ * struct iommu_ioas_allow_iovas - ioctl(IOMMU_IOAS_ALLOW_IOVAS)
+ * @size: sizeof(struct iommu_ioas_allow_iovas)
+ * @ioas_id: IOAS ID to allow IOVAs from
+ * @num_iovas: Input/Output total number of ranges in the IOAS
+ * @__reserved: Must be 0
+ * @allowed_iovas: Pointer to array of struct iommu_iova_range
+ *
+ * Ensure a range of IOVAs are always available for allocation. If this call
+ * succeeds then IOMMU_IOAS_IOVA_RANGES will never return a list of IOVA ranges
+ * that are narrower than the ranges provided here. This call will fail if
+ * IOMMU_IOAS_IOVA_RANGES is currently narrower than the given ranges.
+ *
+ * When an IOAS is first created the IOVA_RANGES will be maximally sized, and as
+ * devices are attached the IOVA will narrow based on the device restrictions.
+ * When an allowed range is specified any narrowing will be refused, ie device
+ * attachment can fail if the device requires limiting within the allowed range.
+ *
+ * Automatic IOVA allocation is also impacted by this call. MAP will only
+ * allocate within the allowed IOVAs if they are present.
+ *
+ * This call replaces the entire allowed list with the given list.
+ */
+struct iommu_ioas_allow_iovas {
+ __u32 size;
+ __u32 ioas_id;
+ __u32 num_iovas;
+ __u32 __reserved;
+ __aligned_u64 allowed_iovas;
+};
+#define IOMMU_IOAS_ALLOW_IOVAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOW_IOVAS)
+
+/**
+ * enum iommufd_ioas_map_flags - Flags for map and copy
+ * @IOMMU_IOAS_MAP_FIXED_IOVA: If clear the kernel will compute an appropriate
+ * IOVA to place the mapping at
+ * @IOMMU_IOAS_MAP_WRITEABLE: DMA is allowed to write to this mapping
+ * @IOMMU_IOAS_MAP_READABLE: DMA is allowed to read from this mapping
+ */
+enum iommufd_ioas_map_flags {
+ IOMMU_IOAS_MAP_FIXED_IOVA = 1 << 0,
+ IOMMU_IOAS_MAP_WRITEABLE = 1 << 1,
+ IOMMU_IOAS_MAP_READABLE = 1 << 2,
+};
+
+/**
+ * struct iommu_ioas_map - ioctl(IOMMU_IOAS_MAP)
+ * @size: sizeof(struct iommu_ioas_map)
+ * @flags: Combination of enum iommufd_ioas_map_flags
+ * @ioas_id: IOAS ID to change the mapping of
+ * @__reserved: Must be 0
+ * @user_va: Userspace pointer to start mapping from
+ * @length: Number of bytes to map
+ * @iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is set
+ * then this must be provided as input.
+ *
+ * Set an IOVA mapping from a user pointer. If FIXED_IOVA is specified then the
+ * mapping will be established at iova, otherwise a suitable location based on
+ * the reserved and allowed lists will be automatically selected and returned in
+ * iova.
+ *
+ * If IOMMU_IOAS_MAP_FIXED_IOVA is specified then the iova range must currently
+ * be unused, existing IOVA cannot be replaced.
+ */
+struct iommu_ioas_map {
+ __u32 size;
+ __u32 flags;
+ __u32 ioas_id;
+ __u32 __reserved;
+ __aligned_u64 user_va;
+ __aligned_u64 length;
+ __aligned_u64 iova;
+};
+#define IOMMU_IOAS_MAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_MAP)
+
+/**
+ * struct iommu_ioas_copy - ioctl(IOMMU_IOAS_COPY)
+ * @size: sizeof(struct iommu_ioas_copy)
+ * @flags: Combination of enum iommufd_ioas_map_flags
+ * @dst_ioas_id: IOAS ID to change the mapping of
+ * @src_ioas_id: IOAS ID to copy from
+ * @length: Number of bytes to copy and map
+ * @dst_iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is
+ * set then this must be provided as input.
+ * @src_iova: IOVA to start the copy
+ *
+ * Copy an already existing mapping from src_ioas_id and establish it in
+ * dst_ioas_id. The src iova/length must exactly match a range used with
+ * IOMMU_IOAS_MAP.
+ *
+ * This may be used to efficiently clone a subset of an IOAS to another, or as a
+ * kind of 'cache' to speed up mapping. Copy has an efficiency advantage over
+ * establishing equivalent new mappings, as internal resources are shared, and
+ * the kernel will pin the user memory only once.
+ */
+struct iommu_ioas_copy {
+ __u32 size;
+ __u32 flags;
+ __u32 dst_ioas_id;
+ __u32 src_ioas_id;
+ __aligned_u64 length;
+ __aligned_u64 dst_iova;
+ __aligned_u64 src_iova;
+};
+#define IOMMU_IOAS_COPY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_COPY)
+
+/**
+ * struct iommu_ioas_unmap - ioctl(IOMMU_IOAS_UNMAP)
+ * @size: sizeof(struct iommu_ioas_unmap)
+ * @ioas_id: IOAS ID to change the mapping of
+ * @iova: IOVA to start the unmapping at
+ * @length: Number of bytes to unmap, and return back the bytes unmapped
+ *
+ * Unmap an IOVA range. The iova/length must be a superset of a previously
+ * mapped range used with IOMMU_IOAS_MAP or IOMMU_IOAS_COPY. Splitting or
+ * truncating ranges is not allowed. The values 0 to U64_MAX will unmap
+ * everything.
+ */
+struct iommu_ioas_unmap {
+ __u32 size;
+ __u32 ioas_id;
+ __aligned_u64 iova;
+ __aligned_u64 length;
+};
+#define IOMMU_IOAS_UNMAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_UNMAP)
+
+/**
+ * enum iommufd_option - ioctl(IOMMU_OPTION_RLIMIT_MODE) and
+ * ioctl(IOMMU_OPTION_HUGE_PAGES)
+ * @IOMMU_OPTION_RLIMIT_MODE:
+ * Change how RLIMIT_MEMLOCK accounting works. The caller must have privilege
+ * to invoke this. Value 0 (default) is user based accouting, 1 uses process
+ * based accounting. Global option, object_id must be 0
+ * @IOMMU_OPTION_HUGE_PAGES:
+ * Value 1 (default) allows contiguous pages to be combined when generating
+ * iommu mappings. Value 0 disables combining, everything is mapped to
+ * PAGE_SIZE. This can be useful for benchmarking. This is a per-IOAS
+ * option, the object_id must be the IOAS ID.
+ */
+enum iommufd_option {
+ IOMMU_OPTION_RLIMIT_MODE = 0,
+ IOMMU_OPTION_HUGE_PAGES = 1,
+};
+
+/**
+ * enum iommufd_option_ops - ioctl(IOMMU_OPTION_OP_SET) and
+ * ioctl(IOMMU_OPTION_OP_GET)
+ * @IOMMU_OPTION_OP_SET: Set the option's value
+ * @IOMMU_OPTION_OP_GET: Get the option's value
+ */
+enum iommufd_option_ops {
+ IOMMU_OPTION_OP_SET = 0,
+ IOMMU_OPTION_OP_GET = 1,
+};
+
+/**
+ * struct iommu_option - iommu option multiplexer
+ * @size: sizeof(struct iommu_option)
+ * @option_id: One of enum iommufd_option
+ * @op: One of enum iommufd_option_ops
+ * @__reserved: Must be 0
+ * @object_id: ID of the object if required
+ * @val64: Option value to set or value returned on get
+ *
+ * Change a simple option value. This multiplexor allows controlling options
+ * on objects. IOMMU_OPTION_OP_SET will load an option and IOMMU_OPTION_OP_GET
+ * will return the current value.
+ */
+struct iommu_option {
+ __u32 size;
+ __u32 option_id;
+ __u16 op;
+ __u16 __reserved;
+ __u32 object_id;
+ __aligned_u64 val64;
+};
+#define IOMMU_OPTION _IO(IOMMUFD_TYPE, IOMMUFD_CMD_OPTION)
+
+/**
+ * enum iommufd_vfio_ioas_op - IOMMU_VFIO_IOAS_* ioctls
+ * @IOMMU_VFIO_IOAS_GET: Get the current compatibility IOAS
+ * @IOMMU_VFIO_IOAS_SET: Change the current compatibility IOAS
+ * @IOMMU_VFIO_IOAS_CLEAR: Disable VFIO compatibility
+ */
+enum iommufd_vfio_ioas_op {
+ IOMMU_VFIO_IOAS_GET = 0,
+ IOMMU_VFIO_IOAS_SET = 1,
+ IOMMU_VFIO_IOAS_CLEAR = 2,
+};
+
+/**
+ * struct iommu_vfio_ioas - ioctl(IOMMU_VFIO_IOAS)
+ * @size: sizeof(struct iommu_vfio_ioas)
+ * @ioas_id: For IOMMU_VFIO_IOAS_SET the input IOAS ID to set
+ * For IOMMU_VFIO_IOAS_GET will output the IOAS ID
+ * @op: One of enum iommufd_vfio_ioas_op
+ * @__reserved: Must be 0
+ *
+ * The VFIO compatibility support uses a single ioas because VFIO APIs do not
+ * support the ID field. Set or Get the IOAS that VFIO compatibility will use.
+ * When VFIO_GROUP_SET_CONTAINER is used on an iommufd it will get the
+ * compatibility ioas, either by taking what is already set, or auto creating
+ * one. From then on VFIO will continue to use that ioas and is not effected by
+ * this ioctl. SET or CLEAR does not destroy any auto-created IOAS.
+ */
+struct iommu_vfio_ioas {
+ __u32 size;
+ __u32 ioas_id;
+ __u16 op;
+ __u16 __reserved;
+};
+#define IOMMU_VFIO_IOAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VFIO_IOAS)
+#endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 0d5d4419139a..55155e262646 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -86,14 +86,6 @@ struct kvm_debug_guest {
/* *** End of deprecated interfaces *** */
-/* for KVM_CREATE_MEMORY_REGION */
-struct kvm_memory_region {
- __u32 slot;
- __u32 flags;
- __u64 guest_phys_addr;
- __u64 memory_size; /* bytes */
-};
-
/* for KVM_SET_USER_MEMORY_REGION */
struct kvm_userspace_memory_region {
__u32 slot;
@@ -104,9 +96,9 @@ struct kvm_userspace_memory_region {
};
/*
- * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace,
- * other bits are reserved for kvm internal use which are defined in
- * include/linux/kvm_host.h.
+ * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
+ * userspace, other bits are reserved for kvm internal use which are defined
+ * in include/linux/kvm_host.h.
*/
#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
#define KVM_MEM_READONLY (1UL << 1)
@@ -485,6 +477,9 @@ struct kvm_run {
#define KVM_MSR_EXIT_REASON_INVAL (1 << 0)
#define KVM_MSR_EXIT_REASON_UNKNOWN (1 << 1)
#define KVM_MSR_EXIT_REASON_FILTER (1 << 2)
+#define KVM_MSR_EXIT_REASON_VALID_MASK (KVM_MSR_EXIT_REASON_INVAL | \
+ KVM_MSR_EXIT_REASON_UNKNOWN | \
+ KVM_MSR_EXIT_REASON_FILTER)
__u32 reason; /* kernel -> user */
__u32 index; /* kernel -> user */
__u64 data; /* kernel <-> user */
@@ -1178,6 +1173,8 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_S390_ZPCI_OP 221
#define KVM_CAP_S390_CPU_TOPOLOGY 222
#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223
+#define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224
+#define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1267,6 +1264,7 @@ struct kvm_x86_mce {
#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3)
#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4)
#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6)
struct kvm_xen_hvm_config {
__u32 flags;
@@ -1438,17 +1436,11 @@ struct kvm_vfio_spapr_tce {
};
/*
- * ioctls for VM fds
- */
-#define KVM_SET_MEMORY_REGION _IOW(KVMIO, 0x40, struct kvm_memory_region)
-/*
* KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns
* a vcpu fd.
*/
#define KVM_CREATE_VCPU _IO(KVMIO, 0x41)
#define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log)
-/* KVM_SET_MEMORY_ALIAS is obsolete: */
-#define KVM_SET_MEMORY_ALIAS _IOW(KVMIO, 0x43, struct kvm_memory_alias)
#define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44)
#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45)
#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \
@@ -1740,6 +1732,8 @@ enum pv_cmd_id {
KVM_PV_UNSHARE_ALL,
KVM_PV_INFO,
KVM_PV_DUMP,
+ KVM_PV_ASYNC_CLEANUP_PREPARE,
+ KVM_PV_ASYNC_CLEANUP_PERFORM,
};
struct kvm_pv_cmd {
@@ -1770,8 +1764,10 @@ struct kvm_xen_hvm_attr {
union {
__u8 long_mode;
__u8 vector;
+ __u8 runstate_update_flag;
struct {
__u64 gfn;
+#define KVM_XEN_INVALID_GFN ((__u64)-1)
} shared_info;
struct {
__u32 send_port;
@@ -1803,6 +1799,7 @@ struct kvm_xen_hvm_attr {
} u;
};
+
/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0
#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1
@@ -1810,6 +1807,8 @@ struct kvm_xen_hvm_attr {
/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3
#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */
+#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5
/* Per-vCPU Xen attributes */
#define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
@@ -1826,6 +1825,7 @@ struct kvm_xen_vcpu_attr {
__u16 pad[3];
union {
__u64 gpa;
+#define KVM_XEN_INVALID_GPA ((__u64)-1)
__u64 pad[8];
struct {
__u64 state;
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 82a03ea954af..85ab1278811e 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -1058,6 +1058,7 @@
/* Precision Time Measurement */
#define PCI_PTM_CAP 0x04 /* PTM Capability */
#define PCI_PTM_CAP_REQ 0x00000001 /* Requester capable */
+#define PCI_PTM_CAP_RES 0x00000002 /* Responder capable */
#define PCI_PTM_CAP_ROOT 0x00000004 /* Root capable */
#define PCI_PTM_GRANULARITY_MASK 0x0000FF00 /* Clock granularity */
#define PCI_PTM_CTRL 0x08 /* PTM Control */
diff --git a/include/uapi/linux/pr.h b/include/uapi/linux/pr.h
index ccc78cbf1221..d8126415966f 100644
--- a/include/uapi/linux/pr.h
+++ b/include/uapi/linux/pr.h
@@ -4,6 +4,23 @@
#include <linux/types.h>
+enum pr_status {
+ PR_STS_SUCCESS = 0x0,
+ /*
+ * The following error codes are based on SCSI, because the interface
+ * was originally created for it and has existing users.
+ */
+ /* Generic device failure. */
+ PR_STS_IOERR = 0x2,
+ PR_STS_RESERVATION_CONFLICT = 0x18,
+ /* Temporary path failure that can be retried. */
+ PR_STS_RETRY_PATH_FAILURE = 0xe0000,
+ /* The request was failed due to a fast failure timer. */
+ PR_STS_PATH_FAST_FAILED = 0xf0000,
+ /* The path cannot be reached and has been marked as failed. */
+ PR_STS_PATH_FAILED = 0x10000,
+};
+
enum pr_type {
PR_WRITE_EXCLUSIVE = 1,
PR_EXCLUSIVE_ACCESS = 2,
diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h
index cea06924b295..53bc1af67a41 100644
--- a/include/uapi/linux/serial.h
+++ b/include/uapi/linux/serial.h
@@ -107,33 +107,50 @@ struct serial_icounter_struct {
int reserved[9];
};
-/*
+/**
+ * struct serial_rs485 - serial interface for controlling RS485 settings.
+ * @flags: RS485 feature flags.
+ * @delay_rts_before_send: Delay before send (milliseconds).
+ * @delay_rts_after_send: Delay after send (milliseconds).
+ * @addr_recv: Receive filter for RS485 addressing mode
+ * (used only when %SER_RS485_ADDR_RECV is set).
+ * @addr_dest: Destination address for RS485 addressing mode
+ * (used only when %SER_RS485_ADDR_DEST is set).
+ * @padding0: Padding (set to zero).
+ * @padding1: Padding (set to zero).
+ * @padding: Deprecated, use @padding0 and @padding1 instead.
+ * Do not use with @addr_recv and @addr_dest (due to
+ * overlap).
+ *
* Serial interface for controlling RS485 settings on chips with suitable
* support. Set with TIOCSRS485 and get with TIOCGRS485 if supported by your
* platform. The set function returns the new state, with any unsupported bits
* reverted appropriately.
+ *
+ * The flag bits are:
+ *
+ * * %SER_RS485_ENABLED - RS485 enabled.
+ * * %SER_RS485_RTS_ON_SEND - Logical level for RTS pin when sending.
+ * * %SER_RS485_RTS_AFTER_SEND - Logical level for RTS pin after sent.
+ * * %SER_RS485_RX_DURING_TX - Full-duplex RS485 line.
+ * * %SER_RS485_TERMINATE_BUS - Enable bus termination (if supported).
+ * * %SER_RS485_ADDRB - Enable RS485 addressing mode.
+ * * %SER_RS485_ADDR_RECV - Receive address filter (enables @addr_recv). Requires %SER_RS485_ADDRB.
+ * * %SER_RS485_ADDR_DEST - Destination address (enables @addr_dest). Requires %SER_RS485_ADDRB.
*/
-
struct serial_rs485 {
- __u32 flags; /* RS485 feature flags */
-#define SER_RS485_ENABLED (1 << 0) /* If enabled */
-#define SER_RS485_RTS_ON_SEND (1 << 1) /* Logical level for
- RTS pin when
- sending */
-#define SER_RS485_RTS_AFTER_SEND (1 << 2) /* Logical level for
- RTS pin after sent*/
+ __u32 flags;
+#define SER_RS485_ENABLED (1 << 0)
+#define SER_RS485_RTS_ON_SEND (1 << 1)
+#define SER_RS485_RTS_AFTER_SEND (1 << 2)
#define SER_RS485_RX_DURING_TX (1 << 4)
-#define SER_RS485_TERMINATE_BUS (1 << 5) /* Enable bus
- termination
- (if supported) */
-
-/* RS-485 addressing mode */
-#define SER_RS485_ADDRB (1 << 6) /* Enable addressing mode */
-#define SER_RS485_ADDR_RECV (1 << 7) /* Receive address filter */
-#define SER_RS485_ADDR_DEST (1 << 8) /* Destination address */
+#define SER_RS485_TERMINATE_BUS (1 << 5)
+#define SER_RS485_ADDRB (1 << 6)
+#define SER_RS485_ADDR_RECV (1 << 7)
+#define SER_RS485_ADDR_DEST (1 << 8)
- __u32 delay_rts_before_send; /* Delay before send (milliseconds) */
- __u32 delay_rts_after_send; /* Delay after send (milliseconds) */
+ __u32 delay_rts_before_send;
+ __u32 delay_rts_after_send;
/* The fields below are defined by flags */
union {
diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h
index 0723a9cce747..01717181339e 100644
--- a/include/uapi/linux/swab.h
+++ b/include/uapi/linux/swab.h
@@ -3,7 +3,7 @@
#define _UAPI_LINUX_SWAB_H
#include <linux/types.h>
-#include <linux/compiler.h>
+#include <linux/stddef.h>
#include <asm/bitsperlong.h>
#include <asm/swab.h>
diff --git a/include/uapi/linux/usb/g_uvc.h b/include/uapi/linux/usb/g_uvc.h
index 652f169a019e..8d7824dde1b2 100644
--- a/include/uapi/linux/usb/g_uvc.h
+++ b/include/uapi/linux/usb/g_uvc.h
@@ -21,6 +21,9 @@
#define UVC_EVENT_DATA (V4L2_EVENT_PRIVATE_START + 5)
#define UVC_EVENT_LAST (V4L2_EVENT_PRIVATE_START + 5)
+#define UVC_STRING_CONTROL_IDX 0
+#define UVC_STRING_STREAMING_IDX 1
+
struct uvc_request_data {
__s32 length;
__u8 data[60];
diff --git a/include/uapi/linux/usb/video.h b/include/uapi/linux/usb/video.h
index bfdae12cdacf..6e8e572c2980 100644
--- a/include/uapi/linux/usb/video.h
+++ b/include/uapi/linux/usb/video.h
@@ -466,7 +466,7 @@ struct uvc_format_uncompressed {
__u8 bDefaultFrameIndex;
__u8 bAspectRatioX;
__u8 bAspectRatioY;
- __u8 bmInterfaceFlags;
+ __u8 bmInterlaceFlags;
__u8 bCopyProtect;
} __attribute__((__packed__));
@@ -522,7 +522,7 @@ struct uvc_format_mjpeg {
__u8 bDefaultFrameIndex;
__u8 bAspectRatioX;
__u8 bAspectRatioY;
- __u8 bmInterfaceFlags;
+ __u8 bmInterlaceFlags;
__u8 bCopyProtect;
} __attribute__((__packed__));
diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h
index 9bd79235c875..54b649ab0f22 100644
--- a/include/uapi/linux/vdpa.h
+++ b/include/uapi/linux/vdpa.h
@@ -53,11 +53,9 @@ enum vdpa_attr {
VDPA_ATTR_DEV_VENDOR_ATTR_NAME, /* string */
VDPA_ATTR_DEV_VENDOR_ATTR_VALUE, /* u64 */
+ /* virtio features that are provisioned to the vDPA device */
VDPA_ATTR_DEV_FEATURES, /* u64 */
- /* virtio features that are supported by the vDPA device */
- VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, /* u64 */
-
/* new attributes must be added above here */
VDPA_ATTR_MAX,
};
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index d7d8e0922376..23105eb036fa 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -819,12 +819,20 @@ struct vfio_device_feature {
* VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P means that RUNNING_P2P
* is supported in addition to the STOP_COPY states.
*
+ * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY means that
+ * PRE_COPY is supported in addition to the STOP_COPY states.
+ *
+ * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P | VFIO_MIGRATION_PRE_COPY
+ * means that RUNNING_P2P, PRE_COPY and PRE_COPY_P2P are 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_MIGRATION_PRE_COPY (1 << 2)
};
#define VFIO_DEVICE_FEATURE_MIGRATION 1
@@ -875,8 +883,13 @@ struct vfio_device_feature_mig_state {
* 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:
+ * And optional states to support VFIO_MIGRATION_P2P:
* RUNNING_P2P - RUNNING, except the device cannot do peer to peer DMA
+ * And VFIO_MIGRATION_PRE_COPY:
+ * PRE_COPY - The device is running normally but tracking internal state
+ * changes
+ * And VFIO_MIGRATION_P2P | VFIO_MIGRATION_PRE_COPY:
+ * PRE_COPY_P2P - PRE_COPY, 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:
@@ -908,20 +921,48 @@ struct vfio_device_feature_mig_state {
*
* To abort a RESUMING session the device must be reset.
*
+ * PRE_COPY -> RUNNING
* 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.
*
+ * The PRE_COPY arc will terminate a data transfer session.
+ *
+ * PRE_COPY_P2P -> RUNNING_P2P
* RUNNING -> RUNNING_P2P
* STOP -> RUNNING_P2P
* While in RUNNING_P2P the device is partially running in the P2P quiescent
* state defined below.
*
+ * The PRE_COPY_P2P arc will terminate a data transfer session.
+ *
+ * RUNNING -> PRE_COPY
+ * RUNNING_P2P -> PRE_COPY_P2P
* STOP -> STOP_COPY
- * This arc begin the process of saving the device state and will return a
- * new data_fd.
+ * PRE_COPY, PRE_COPY_P2P and STOP_COPY form the "saving group" of states
+ * which share a data transfer session. Moving between these states alters
+ * what is streamed in session, but does not terminate or otherwise affect
+ * the associated fd.
+ *
+ * These arcs begin the process of saving the device state and will return a
+ * new data_fd. The migration driver may perform actions such as enabling
+ * dirty logging of device state when entering PRE_COPY or PER_COPY_P2P.
+ *
+ * Each arc does not change the device operation, the device remains
+ * RUNNING, P2P quiesced or in STOP. The STOP_COPY state is described below
+ * in PRE_COPY_P2P -> STOP_COPY.
*
+ * PRE_COPY -> PRE_COPY_P2P
+ * Entering PRE_COPY_P2P continues all the behaviors of PRE_COPY above.
+ * However, while in the PRE_COPY_P2P state, the device is partially running
+ * in the P2P quiescent state defined below, like RUNNING_P2P.
+ *
+ * PRE_COPY_P2P -> PRE_COPY
+ * This arc allows returning the device to a full RUNNING behavior while
+ * continuing all the behaviors of PRE_COPY.
+ *
+ * PRE_COPY_P2P -> STOP_COPY
* 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
@@ -939,6 +980,13 @@ struct vfio_device_feature_mig_state {
* device state for this arc if required to prepare the device to receive the
* migration data.
*
+ * STOP_COPY -> PRE_COPY
+ * STOP_COPY -> PRE_COPY_P2P
+ * These arcs are not permitted and return error if requested. Future
+ * revisions of this API may define behaviors for these arcs, in this case
+ * support will be discoverable by a new flag in
+ * VFIO_DEVICE_FEATURE_MIGRATION.
+ *
* 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
@@ -950,7 +998,7 @@ struct vfio_device_feature_mig_state {
* 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
+ * RUNNING_P2P and PRE_COPY_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
@@ -963,6 +1011,8 @@ struct vfio_device_feature_mig_state {
* 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.
+ * - The path cannot have saving group states as interior arcs, only
+ * starting/end states.
* 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
@@ -976,6 +1026,9 @@ struct vfio_device_feature_mig_state {
* 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.
+ *
+ * Arcs touching PRE_COPY and PRE_COPY_P2P are removed if support for PRE_COPY
+ * is not present.
*/
enum vfio_device_mig_state {
VFIO_DEVICE_STATE_ERROR = 0,
@@ -984,8 +1037,70 @@ enum vfio_device_mig_state {
VFIO_DEVICE_STATE_STOP_COPY = 3,
VFIO_DEVICE_STATE_RESUMING = 4,
VFIO_DEVICE_STATE_RUNNING_P2P = 5,
+ VFIO_DEVICE_STATE_PRE_COPY = 6,
+ VFIO_DEVICE_STATE_PRE_COPY_P2P = 7,
+};
+
+/**
+ * VFIO_MIG_GET_PRECOPY_INFO - _IO(VFIO_TYPE, VFIO_BASE + 21)
+ *
+ * This ioctl is used on the migration data FD in the precopy phase of the
+ * migration data transfer. It returns an estimate of the current data sizes
+ * remaining to be transferred. It allows the user to judge when it is
+ * appropriate to leave PRE_COPY for STOP_COPY.
+ *
+ * This ioctl is valid only in PRE_COPY states and kernel driver should
+ * return -EINVAL from any other migration state.
+ *
+ * The vfio_precopy_info data structure returned by this ioctl provides
+ * estimates of data available from the device during the PRE_COPY states.
+ * This estimate is split into two categories, initial_bytes and
+ * dirty_bytes.
+ *
+ * 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.
+ * It is recommended to leave PRE_COPY for STOP_COPY only after this field
+ * reaches zero. Leaving PRE_COPY earlier might make things slower.
+ *
+ * The dirty_bytes field tracks device state changes relative to data
+ * previously retrieved. This field starts at zero and may increase as
+ * the internal device state is modified or decrease as that modified
+ * state is read from the device.
+ *
+ * Userspace may use the combination of these fields to estimate the
+ * potential data size available during the PRE_COPY phases, as well as
+ * trends relative to the rate the device is dirtying its internal
+ * state, but these fields are not required to have any bearing relative
+ * to the data size available during the STOP_COPY phase.
+ *
+ * Drivers have a lot of flexibility in when and what they transfer during the
+ * PRE_COPY phase, and how they report this from VFIO_MIG_GET_PRECOPY_INFO.
+ *
+ * During pre-copy the migration data FD has a temporary "end of stream" that is
+ * reached when both initial_bytes and dirty_byte are zero. For instance, this
+ * may indicate that the device is idle and not currently dirtying any internal
+ * state. When read() is done on this temporary end of stream the kernel driver
+ * should return ENOMSG from read(). Userspace can wait for more data (which may
+ * never come) by using poll.
+ *
+ * Once in STOP_COPY the migration data FD has a permanent end of stream
+ * signaled in the usual way by read() always returning 0 and poll always
+ * returning readable. ENOMSG may not be returned in STOP_COPY.
+ * Support for this ioctl is mandatory if a driver claims to support
+ * VFIO_MIGRATION_PRE_COPY.
+ *
+ * Return: 0 on success, -1 and errno set on failure.
+ */
+struct vfio_precopy_info {
+ __u32 argsz;
+ __u32 flags;
+ __aligned_u64 initial_bytes;
+ __aligned_u64 dirty_bytes;
};
+#define VFIO_MIG_GET_PRECOPY_INFO _IO(VFIO_TYPE, VFIO_BASE + 21)
+
/*
* 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
@@ -1128,6 +1243,19 @@ struct vfio_device_feature_dma_logging_report {
#define VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT 8
+/*
+ * Upon VFIO_DEVICE_FEATURE_GET read back the estimated data length that will
+ * be required to complete stop copy.
+ *
+ * Note: Can be called on each device state.
+ */
+
+struct vfio_device_feature_mig_data_size {
+ __aligned_u64 stop_copy_length;
+};
+
+#define VFIO_DEVICE_FEATURE_MIG_DATA_SIZE 9
+
/* -------- API for Type1 VFIO IOMMU -------- */
/**
diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h
index 5e29f2cfa42d..f33d914d8f46 100644
--- a/include/uapi/misc/fastrpc.h
+++ b/include/uapi/misc/fastrpc.h
@@ -13,6 +13,7 @@
#define FASTRPC_IOCTL_MMAP _IOWR('R', 6, struct fastrpc_req_mmap)
#define FASTRPC_IOCTL_MUNMAP _IOWR('R', 7, struct fastrpc_req_munmap)
#define FASTRPC_IOCTL_INIT_ATTACH_SNS _IO('R', 8)
+#define FASTRPC_IOCTL_INIT_CREATE_STATIC _IOWR('R', 9, struct fastrpc_init_create_static)
#define FASTRPC_IOCTL_MEM_MAP _IOWR('R', 10, struct fastrpc_mem_map)
#define FASTRPC_IOCTL_MEM_UNMAP _IOWR('R', 11, struct fastrpc_mem_unmap)
#define FASTRPC_IOCTL_GET_DSP_INFO _IOWR('R', 13, struct fastrpc_ioctl_capability)
@@ -87,6 +88,12 @@ struct fastrpc_init_create {
__u64 file; /* pointer to elf file */
};
+struct fastrpc_init_create_static {
+ __u32 namelen; /* length of pd process name */
+ __u32 memlen;
+ __u64 name; /* pd process name */
+};
+
struct fastrpc_alloc_dma_buf {
__s32 fd; /* fd */
__u32 flags; /* flags to map with */
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index e00ebe05097d..3b995e841eb8 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -597,6 +597,10 @@ enum gaudi2_engine_id {
GAUDI2_ENGINE_ID_NIC10_1,
GAUDI2_ENGINE_ID_NIC11_0,
GAUDI2_ENGINE_ID_NIC11_1,
+ GAUDI2_ENGINE_ID_PCIE,
+ GAUDI2_ENGINE_ID_PSOC,
+ GAUDI2_ENGINE_ID_ARC_FARM,
+ GAUDI2_ENGINE_ID_KDMA,
GAUDI2_ENGINE_ID_SIZE
};
@@ -717,6 +721,8 @@ enum hl_server_type {
* HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE - Indicates device is unavailable
* HL_NOTIFIER_EVENT_USER_ENGINE_ERR - Indicates device engine in error state
* HL_NOTIFIER_EVENT_GENERAL_HW_ERR - Indicates device HW error
+ * HL_NOTIFIER_EVENT_RAZWI - Indicates razwi happened
+ * HL_NOTIFIER_EVENT_PAGE_FAULT - Indicates page fault happened
*/
#define HL_NOTIFIER_EVENT_TPC_ASSERT (1ULL << 0)
#define HL_NOTIFIER_EVENT_UNDEFINED_OPCODE (1ULL << 1)
@@ -725,6 +731,8 @@ enum hl_server_type {
#define HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE (1ULL << 4)
#define HL_NOTIFIER_EVENT_USER_ENGINE_ERR (1ULL << 5)
#define HL_NOTIFIER_EVENT_GENERAL_HW_ERR (1ULL << 6)
+#define HL_NOTIFIER_EVENT_RAZWI (1ULL << 7)
+#define HL_NOTIFIER_EVENT_PAGE_FAULT (1ULL << 8)
/* Opcode for management ioctl
*
@@ -778,6 +786,9 @@ enum hl_server_type {
* HL_INFO_UNREGISTER_EVENTFD - Unregister eventfd
* HL_INFO_GET_EVENTS - Retrieve the last occurred events
* HL_INFO_UNDEFINED_OPCODE_EVENT - Retrieve last undefined opcode error information.
+ * HL_INFO_ENGINE_STATUS - Retrieve the status of all the h/w engines in the asic.
+ * HL_INFO_PAGE_FAULT_EVENT - Retrieve parameters of captured page fault.
+ * HL_INFO_USER_MAPPINGS - Retrieve user mappings, captured after page fault event.
*/
#define HL_INFO_HW_IP_INFO 0
#define HL_INFO_HW_EVENTS 1
@@ -809,6 +820,8 @@ enum hl_server_type {
#define HL_INFO_GET_EVENTS 30
#define HL_INFO_UNDEFINED_OPCODE_EVENT 31
#define HL_INFO_ENGINE_STATUS 32
+#define HL_INFO_PAGE_FAULT_EVENT 33
+#define HL_INFO_USER_MAPPINGS 34
#define HL_INFO_VERSION_MAX_LEN 128
#define HL_INFO_CARD_NAME_MAX_LEN 16
@@ -859,6 +872,7 @@ enum hl_server_type {
* @number_of_user_interrupts: The number of interrupts that are available to the userspace
* application to use. Relevant for Gaudi2 and later.
* @device_mem_alloc_default_page_size: default page size used in device memory allocation.
+ * @revision_id: PCI revision ID of the ASIC.
*/
struct hl_info_hw_ip_info {
__u64 sram_base_address;
@@ -889,6 +903,12 @@ struct hl_info_hw_ip_info {
__u16 pad2;
__u64 reserved4;
__u64 device_mem_alloc_default_page_size;
+ __u64 reserved5;
+ __u64 reserved6;
+ __u32 reserved7;
+ __u8 reserved8;
+ __u8 revision_id;
+ __u8 pad[2];
};
struct hl_info_dram_usage {
@@ -896,7 +916,7 @@ struct hl_info_dram_usage {
__u64 ctx_dram_mem;
};
-#define HL_BUSY_ENGINES_MASK_EXT_SIZE 2
+#define HL_BUSY_ENGINES_MASK_EXT_SIZE 4
struct hl_info_hw_idle {
__u32 is_idle;
@@ -1071,31 +1091,44 @@ struct hl_info_cs_timeout_event {
__u64 seq;
};
-#define HL_RAZWI_PAGE_FAULT 0
-#define HL_RAZWI_MMU_ACCESS_ERROR 1
+#define HL_RAZWI_NA_ENG_ID U16_MAX
+#define HL_RAZWI_MAX_NUM_OF_ENGINES_PER_RTR 128
+#define HL_RAZWI_READ BIT(0)
+#define HL_RAZWI_WRITE BIT(1)
+#define HL_RAZWI_LBW BIT(2)
+#define HL_RAZWI_HBW BIT(3)
+#define HL_RAZWI_RR BIT(4)
+#define HL_RAZWI_ADDR_DEC BIT(5)
/**
* struct hl_info_razwi_event - razwi information.
* @timestamp: timestamp of razwi.
* @addr: address which accessing it caused razwi.
- * @engine_id_1: engine id of the razwi initiator, if it was initiated by engine that does not
- * have engine id it will be set to U16_MAX.
- * @engine_id_2: second engine id of razwi initiator. Might happen that razwi have 2 possible
- * engines which one them caused the razwi. In that case, it will contain the
- * second possible engine id, otherwise it will be set to U16_MAX.
- * @no_engine_id: if razwi initiator does not have engine id, this field will be set to 1,
- * otherwise 0.
- * @error_type: cause of razwi, page fault or access error, otherwise it will be set to U8_MAX.
- * @pad: padding to 64 bit.
+ * @engine_id: engine id of the razwi initiator, if it was initiated by engine that does not
+ * have engine id it will be set to HL_RAZWI_NA_ENG_ID. If there are several possible
+ * engines which caused the razwi, it will hold all of them.
+ * @num_of_possible_engines: contains number of possible engine ids. In some asics, razwi indication
+ * might be common for several engines and there is no way to get the
+ * exact engine. In this way, engine_id array will be filled with all
+ * possible engines caused this razwi. Also, there might be possibility
+ * in gaudi, where we don't indication on specific engine, in that case
+ * the value of this parameter will be zero.
+ * @flags: bitmask for additional data: HL_RAZWI_READ - razwi caused by read operation
+ * HL_RAZWI_WRITE - razwi caused by write operation
+ * HL_RAZWI_LBW - razwi caused by lbw fabric transaction
+ * HL_RAZWI_HBW - razwi caused by hbw fabric transaction
+ * HL_RAZWI_RR - razwi caused by range register
+ * HL_RAZWI_ADDR_DEC - razwi caused by address decode error
+ * Note: this data is not supported by all asics, in that case the relevant bits will not
+ * be set.
*/
struct hl_info_razwi_event {
__s64 timestamp;
__u64 addr;
- __u16 engine_id_1;
- __u16 engine_id_2;
- __u8 no_engine_id;
- __u8 error_type;
- __u8 pad[2];
+ __u16 engine_id[HL_RAZWI_MAX_NUM_OF_ENGINES_PER_RTR];
+ __u16 num_of_possible_engines;
+ __u8 flags;
+ __u8 pad[5];
};
#define MAX_QMAN_STREAMS_INFO 4
@@ -1174,6 +1207,29 @@ struct hl_info_sec_attest {
__u8 pad0[2];
};
+/**
+ * struct hl_page_fault_info - page fault information.
+ * @timestamp: timestamp of page fault.
+ * @addr: address which accessing it caused page fault.
+ * @engine_id: engine id which caused the page fault, supported only in gaudi3.
+ */
+struct hl_page_fault_info {
+ __s64 timestamp;
+ __u64 addr;
+ __u16 engine_id;
+ __u8 pad[6];
+};
+
+/**
+ * struct hl_user_mapping - user mapping information.
+ * @dev_va: device virtual address.
+ * @size: virtual address mapping size.
+ */
+struct hl_user_mapping {
+ __u64 dev_va;
+ __u64 size;
+};
+
enum gaudi_dcores {
HL_GAUDI_WS_DCORE,
HL_GAUDI_WN_DCORE,
@@ -1200,6 +1256,8 @@ enum gaudi_dcores {
* needed, hence updating this variable so user will know the exact amount
* of bytes copied by the kernel to the buffer.
* @sec_attest_nonce: Nonce number used for attestation report.
+ * @array_size: Number of array members copied to user buffer.
+ * Relevant for HL_INFO_USER_MAPPINGS info ioctl.
* @pad: Padding to 64 bit.
*/
struct hl_info_args {
@@ -1215,6 +1273,7 @@ struct hl_info_args {
__u32 eventfd;
__u32 user_buffer_actual_size;
__u32 sec_attest_nonce;
+ __u32 array_size;
};
__u32 pad;
diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h
index f6fde06db4b4..745790ce3c26 100644
--- a/include/uapi/rdma/hns-abi.h
+++ b/include/uapi/rdma/hns-abi.h
@@ -85,11 +85,26 @@ struct hns_roce_ib_create_qp_resp {
__aligned_u64 dwqe_mmap_key;
};
+enum {
+ HNS_ROCE_EXSGE_FLAGS = 1 << 0,
+};
+
+enum {
+ HNS_ROCE_RSP_EXSGE_FLAGS = 1 << 0,
+};
+
struct hns_roce_ib_alloc_ucontext_resp {
__u32 qp_tab_size;
__u32 cqe_size;
__u32 srq_tab_size;
__u32 reserved;
+ __u32 config;
+ __u32 max_inline_data;
+};
+
+struct hns_roce_ib_alloc_ucontext {
+ __u32 config;
+ __u32 reserved;
};
struct hns_roce_ib_alloc_pd_resp {
diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
index 7dd56210226f..d7c5aaa32744 100644
--- a/include/uapi/rdma/ib_user_ioctl_verbs.h
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -57,6 +57,8 @@ enum ib_uverbs_access_flags {
IB_UVERBS_ACCESS_ZERO_BASED = 1 << 5,
IB_UVERBS_ACCESS_ON_DEMAND = 1 << 6,
IB_UVERBS_ACCESS_HUGETLB = 1 << 7,
+ IB_UVERBS_ACCESS_FLUSH_GLOBAL = 1 << 8,
+ IB_UVERBS_ACCESS_FLUSH_PERSISTENT = 1 << 9,
IB_UVERBS_ACCESS_RELAXED_ORDERING = IB_UVERBS_ACCESS_OPTIONAL_FIRST,
IB_UVERBS_ACCESS_OPTIONAL_RANGE =
@@ -251,6 +253,7 @@ enum rdma_driver_id {
RDMA_DRIVER_EFA,
RDMA_DRIVER_SIW,
RDMA_DRIVER_ERDMA,
+ RDMA_DRIVER_MANA,
};
enum ib_uverbs_gid_type {
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 43672cb1fd57..e16650f0c85d 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -105,6 +105,18 @@ enum {
IB_USER_VERBS_EX_CMD_MODIFY_CQ
};
+/* see IBA A19.4.1.1 Placement Types */
+enum ib_placement_type {
+ IB_FLUSH_GLOBAL = 1U << 0,
+ IB_FLUSH_PERSISTENT = 1U << 1,
+};
+
+/* see IBA A19.4.1.2 Selectivity Level */
+enum ib_selectivity_level {
+ IB_FLUSH_RANGE = 0,
+ IB_FLUSH_MR,
+};
+
/*
* Make sure that all structs defined in this file remain laid out so
* that they pack the same way on 32-bit and 64-bit architectures (to
@@ -466,6 +478,8 @@ enum ib_uverbs_wc_opcode {
IB_UVERBS_WC_BIND_MW = 5,
IB_UVERBS_WC_LOCAL_INV = 6,
IB_UVERBS_WC_TSO = 7,
+ IB_UVERBS_WC_FLUSH = 8,
+ IB_UVERBS_WC_ATOMIC_WRITE = 9,
};
struct ib_uverbs_wc {
@@ -784,6 +798,8 @@ enum ib_uverbs_wr_opcode {
IB_UVERBS_WR_RDMA_READ_WITH_INV = 11,
IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP = 12,
IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD = 13,
+ IB_UVERBS_WR_FLUSH = 14,
+ IB_UVERBS_WR_ATOMIC_WRITE = 15,
/* Review enum ib_wr_opcode before modifying this */
};
@@ -1331,6 +1347,11 @@ enum ib_uverbs_device_cap_flags {
/* Deprecated. Please use IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS. */
IB_UVERBS_DEVICE_RAW_SCATTER_FCS = 1ULL << 34,
IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING = 1ULL << 36,
+ /* Flush placement types */
+ IB_UVERBS_DEVICE_FLUSH_GLOBAL = 1ULL << 38,
+ IB_UVERBS_DEVICE_FLUSH_PERSISTENT = 1ULL << 39,
+ /* Atomic write attributes */
+ IB_UVERBS_DEVICE_ATOMIC_WRITE = 1ULL << 40,
};
enum ib_uverbs_raw_packet_caps {
diff --git a/include/uapi/rdma/mana-abi.h b/include/uapi/rdma/mana-abi.h
new file mode 100644
index 000000000000..5fcb31b37fb9
--- /dev/null
+++ b/include/uapi/rdma/mana-abi.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) */
+/*
+ * Copyright (c) 2022, Microsoft Corporation. All rights reserved.
+ */
+
+#ifndef MANA_ABI_USER_H
+#define MANA_ABI_USER_H
+
+#include <linux/types.h>
+#include <rdma/ib_user_ioctl_verbs.h>
+
+/*
+ * Increment this value if any changes that break userspace ABI
+ * compatibility are made.
+ */
+
+#define MANA_IB_UVERBS_ABI_VERSION 1
+
+struct mana_ib_create_cq {
+ __aligned_u64 buf_addr;
+};
+
+struct mana_ib_create_qp {
+ __aligned_u64 sq_buf_addr;
+ __u32 sq_buf_size;
+ __u32 port;
+};
+
+struct mana_ib_create_qp_resp {
+ __u32 sqid;
+ __u32 cqid;
+ __u32 tx_vp_offset;
+ __u32 reserved;
+};
+
+struct mana_ib_create_wq {
+ __aligned_u64 wq_buf_addr;
+ __u32 wq_buf_size;
+ __u32 reserved;
+};
+
+/* RX Hash function flags */
+enum mana_ib_rx_hash_function_flags {
+ MANA_IB_RX_HASH_FUNC_TOEPLITZ = 1 << 0,
+};
+
+struct mana_ib_create_qp_rss {
+ __aligned_u64 rx_hash_fields_mask;
+ __u8 rx_hash_function;
+ __u8 reserved[7];
+ __u32 rx_hash_key_len;
+ __u8 rx_hash_key[40];
+ __u32 port;
+};
+
+struct rss_resp_entry {
+ __u32 cqid;
+ __u32 wqid;
+};
+
+struct mana_ib_create_qp_rss_resp {
+ __aligned_u64 num_entries;
+ struct rss_resp_entry entries[64];
+};
+
+#endif
diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h
index 73f679dfd2df..bb092fccb813 100644
--- a/include/uapi/rdma/rdma_user_rxe.h
+++ b/include/uapi/rdma/rdma_user_rxe.h
@@ -84,6 +84,13 @@ struct rxe_send_wr {
union {
struct {
__aligned_u64 remote_addr;
+ __u32 length;
+ __u32 rkey;
+ __u8 type;
+ __u8 level;
+ } flush;
+ struct {
+ __aligned_u64 remote_addr;
__u32 rkey;
__u32 reserved;
} rdma;
@@ -146,6 +153,7 @@ struct rxe_dma_info {
__u32 reserved;
union {
__DECLARE_FLEX_ARRAY(__u8, inline_data);
+ __DECLARE_FLEX_ARRAY(__u8, atomic_wr);
__DECLARE_FLEX_ARRAY(struct rxe_sge, sge);
};
};