v4.19.13 snapshot.
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
new file mode 100644
index 0000000..66917a4
--- /dev/null
+++ b/tools/include/uapi/linux/bpf.h
@@ -0,0 +1,2781 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _UAPI__LINUX_BPF_H__
+#define _UAPI__LINUX_BPF_H__
+
+#include <linux/types.h>
+#include <linux/bpf_common.h>
+
+/* Extended instruction set based on top of classic BPF */
+
+/* instruction classes */
+#define BPF_ALU64 0x07 /* alu mode in double word width */
+
+/* ld/ldx fields */
+#define BPF_DW 0x18 /* double word (64-bit) */
+#define BPF_XADD 0xc0 /* exclusive add */
+
+/* alu/jmp fields */
+#define BPF_MOV 0xb0 /* mov reg to reg */
+#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */
+
+/* change endianness of a register */
+#define BPF_END 0xd0 /* flags for endianness conversion: */
+#define BPF_TO_LE 0x00 /* convert to little-endian */
+#define BPF_TO_BE 0x08 /* convert to big-endian */
+#define BPF_FROM_LE BPF_TO_LE
+#define BPF_FROM_BE BPF_TO_BE
+
+/* jmp encodings */
+#define BPF_JNE 0x50 /* jump != */
+#define BPF_JLT 0xa0 /* LT is unsigned, '<' */
+#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */
+#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */
+#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */
+#define BPF_JSLT 0xc0 /* SLT is signed, '<' */
+#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */
+#define BPF_CALL 0x80 /* function call */
+#define BPF_EXIT 0x90 /* function return */
+
+/* Register numbers */
+enum {
+ BPF_REG_0 = 0,
+ BPF_REG_1,
+ BPF_REG_2,
+ BPF_REG_3,
+ BPF_REG_4,
+ BPF_REG_5,
+ BPF_REG_6,
+ BPF_REG_7,
+ BPF_REG_8,
+ BPF_REG_9,
+ BPF_REG_10,
+ __MAX_BPF_REG,
+};
+
+/* BPF has 10 general purpose 64-bit registers and stack frame. */
+#define MAX_BPF_REG __MAX_BPF_REG
+
+struct bpf_insn {
+ __u8 code; /* opcode */
+ __u8 dst_reg:4; /* dest register */
+ __u8 src_reg:4; /* source register */
+ __s16 off; /* signed offset */
+ __s32 imm; /* signed immediate constant */
+};
+
+/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
+struct bpf_lpm_trie_key {
+ __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */
+ __u8 data[0]; /* Arbitrary size */
+};
+
+struct bpf_cgroup_storage_key {
+ __u64 cgroup_inode_id; /* cgroup inode id */
+ __u32 attach_type; /* program attach type */
+};
+
+/* BPF syscall commands, see bpf(2) man-page for details. */
+enum bpf_cmd {
+ BPF_MAP_CREATE,
+ BPF_MAP_LOOKUP_ELEM,
+ BPF_MAP_UPDATE_ELEM,
+ BPF_MAP_DELETE_ELEM,
+ BPF_MAP_GET_NEXT_KEY,
+ BPF_PROG_LOAD,
+ BPF_OBJ_PIN,
+ BPF_OBJ_GET,
+ BPF_PROG_ATTACH,
+ BPF_PROG_DETACH,
+ BPF_PROG_TEST_RUN,
+ BPF_PROG_GET_NEXT_ID,
+ BPF_MAP_GET_NEXT_ID,
+ BPF_PROG_GET_FD_BY_ID,
+ BPF_MAP_GET_FD_BY_ID,
+ BPF_OBJ_GET_INFO_BY_FD,
+ BPF_PROG_QUERY,
+ BPF_RAW_TRACEPOINT_OPEN,
+ BPF_BTF_LOAD,
+ BPF_BTF_GET_FD_BY_ID,
+ BPF_TASK_FD_QUERY,
+};
+
+enum bpf_map_type {
+ BPF_MAP_TYPE_UNSPEC,
+ BPF_MAP_TYPE_HASH,
+ BPF_MAP_TYPE_ARRAY,
+ BPF_MAP_TYPE_PROG_ARRAY,
+ BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+ BPF_MAP_TYPE_PERCPU_HASH,
+ BPF_MAP_TYPE_PERCPU_ARRAY,
+ BPF_MAP_TYPE_STACK_TRACE,
+ BPF_MAP_TYPE_CGROUP_ARRAY,
+ BPF_MAP_TYPE_LRU_HASH,
+ BPF_MAP_TYPE_LRU_PERCPU_HASH,
+ BPF_MAP_TYPE_LPM_TRIE,
+ BPF_MAP_TYPE_ARRAY_OF_MAPS,
+ BPF_MAP_TYPE_HASH_OF_MAPS,
+ BPF_MAP_TYPE_DEVMAP,
+ BPF_MAP_TYPE_SOCKMAP,
+ BPF_MAP_TYPE_CPUMAP,
+ BPF_MAP_TYPE_XSKMAP,
+ BPF_MAP_TYPE_SOCKHASH,
+ BPF_MAP_TYPE_CGROUP_STORAGE,
+ BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+};
+
+enum bpf_prog_type {
+ BPF_PROG_TYPE_UNSPEC,
+ BPF_PROG_TYPE_SOCKET_FILTER,
+ BPF_PROG_TYPE_KPROBE,
+ BPF_PROG_TYPE_SCHED_CLS,
+ BPF_PROG_TYPE_SCHED_ACT,
+ BPF_PROG_TYPE_TRACEPOINT,
+ BPF_PROG_TYPE_XDP,
+ BPF_PROG_TYPE_PERF_EVENT,
+ BPF_PROG_TYPE_CGROUP_SKB,
+ BPF_PROG_TYPE_CGROUP_SOCK,
+ BPF_PROG_TYPE_LWT_IN,
+ BPF_PROG_TYPE_LWT_OUT,
+ BPF_PROG_TYPE_LWT_XMIT,
+ BPF_PROG_TYPE_SOCK_OPS,
+ BPF_PROG_TYPE_SK_SKB,
+ BPF_PROG_TYPE_CGROUP_DEVICE,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_RAW_TRACEPOINT,
+ BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_PROG_TYPE_LWT_SEG6LOCAL,
+ BPF_PROG_TYPE_LIRC_MODE2,
+ BPF_PROG_TYPE_SK_REUSEPORT,
+};
+
+enum bpf_attach_type {
+ BPF_CGROUP_INET_INGRESS,
+ BPF_CGROUP_INET_EGRESS,
+ BPF_CGROUP_INET_SOCK_CREATE,
+ BPF_CGROUP_SOCK_OPS,
+ BPF_SK_SKB_STREAM_PARSER,
+ BPF_SK_SKB_STREAM_VERDICT,
+ BPF_CGROUP_DEVICE,
+ BPF_SK_MSG_VERDICT,
+ BPF_CGROUP_INET4_BIND,
+ BPF_CGROUP_INET6_BIND,
+ BPF_CGROUP_INET4_CONNECT,
+ BPF_CGROUP_INET6_CONNECT,
+ BPF_CGROUP_INET4_POST_BIND,
+ BPF_CGROUP_INET6_POST_BIND,
+ BPF_CGROUP_UDP4_SENDMSG,
+ BPF_CGROUP_UDP6_SENDMSG,
+ BPF_LIRC_MODE2,
+ __MAX_BPF_ATTACH_TYPE
+};
+
+#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
+
+/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
+ *
+ * NONE(default): No further bpf programs allowed in the subtree.
+ *
+ * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
+ * the program in this cgroup yields to sub-cgroup program.
+ *
+ * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
+ * that cgroup program gets run in addition to the program in this cgroup.
+ *
+ * Only one program is allowed to be attached to a cgroup with
+ * NONE or BPF_F_ALLOW_OVERRIDE flag.
+ * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
+ * release old program and attach the new one. Attach flags has to match.
+ *
+ * Multiple programs are allowed to be attached to a cgroup with
+ * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
+ * (those that were attached first, run first)
+ * The programs of sub-cgroup are executed first, then programs of
+ * this cgroup and then programs of parent cgroup.
+ * When children program makes decision (like picking TCP CA or sock bind)
+ * parent program has a chance to override it.
+ *
+ * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
+ * A cgroup with NONE doesn't allow any programs in sub-cgroups.
+ * Ex1:
+ * cgrp1 (MULTI progs A, B) ->
+ * cgrp2 (OVERRIDE prog C) ->
+ * cgrp3 (MULTI prog D) ->
+ * cgrp4 (OVERRIDE prog E) ->
+ * cgrp5 (NONE prog F)
+ * the event in cgrp5 triggers execution of F,D,A,B in that order.
+ * if prog F is detached, the execution is E,D,A,B
+ * if prog F and D are detached, the execution is E,A,B
+ * if prog F, E and D are detached, the execution is C,A,B
+ *
+ * All eligible programs are executed regardless of return code from
+ * earlier programs.
+ */
+#define BPF_F_ALLOW_OVERRIDE (1U << 0)
+#define BPF_F_ALLOW_MULTI (1U << 1)
+
+/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
+ * verifier will perform strict alignment checking as if the kernel
+ * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set,
+ * and NET_IP_ALIGN defined to 2.
+ */
+#define BPF_F_STRICT_ALIGNMENT (1U << 0)
+
+/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
+#define BPF_PSEUDO_MAP_FD 1
+
+/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
+ * offset to another bpf function
+ */
+#define BPF_PSEUDO_CALL 1
+
+/* flags for BPF_MAP_UPDATE_ELEM command */
+#define BPF_ANY 0 /* create new element or update existing */
+#define BPF_NOEXIST 1 /* create new element if it didn't exist */
+#define BPF_EXIST 2 /* update existing element */
+
+/* flags for BPF_MAP_CREATE command */
+#define BPF_F_NO_PREALLOC (1U << 0)
+/* Instead of having one common LRU list in the
+ * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
+ * which can scale and perform better.
+ * Note, the LRU nodes (including free nodes) cannot be moved
+ * across different LRU lists.
+ */
+#define BPF_F_NO_COMMON_LRU (1U << 1)
+/* Specify numa node during map creation */
+#define BPF_F_NUMA_NODE (1U << 2)
+
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE (1U << 0)
+
+#define BPF_OBJ_NAME_LEN 16U
+
+/* Flags for accessing BPF object */
+#define BPF_F_RDONLY (1U << 3)
+#define BPF_F_WRONLY (1U << 4)
+
+/* Flag for stack_map, store build_id+offset instead of pointer */
+#define BPF_F_STACK_BUILD_ID (1U << 5)
+
+enum bpf_stack_build_id_status {
+ /* user space need an empty entry to identify end of a trace */
+ BPF_STACK_BUILD_ID_EMPTY = 0,
+ /* with valid build_id and offset */
+ BPF_STACK_BUILD_ID_VALID = 1,
+ /* couldn't get build_id, fallback to ip */
+ BPF_STACK_BUILD_ID_IP = 2,
+};
+
+#define BPF_BUILD_ID_SIZE 20
+struct bpf_stack_build_id {
+ __s32 status;
+ unsigned char build_id[BPF_BUILD_ID_SIZE];
+ union {
+ __u64 offset;
+ __u64 ip;
+ };
+};
+
+union bpf_attr {
+ struct { /* anonymous struct used by BPF_MAP_CREATE command */
+ __u32 map_type; /* one of enum bpf_map_type */
+ __u32 key_size; /* size of key in bytes */
+ __u32 value_size; /* size of value in bytes */
+ __u32 max_entries; /* max number of entries in a map */
+ __u32 map_flags; /* BPF_MAP_CREATE related
+ * flags defined above.
+ */
+ __u32 inner_map_fd; /* fd pointing to the inner map */
+ __u32 numa_node; /* numa node (effective only if
+ * BPF_F_NUMA_NODE is set).
+ */
+ char map_name[BPF_OBJ_NAME_LEN];
+ __u32 map_ifindex; /* ifindex of netdev to create on */
+ __u32 btf_fd; /* fd pointing to a BTF type data */
+ __u32 btf_key_type_id; /* BTF type_id of the key */
+ __u32 btf_value_type_id; /* BTF type_id of the value */
+ };
+
+ struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
+ __u32 map_fd;
+ __aligned_u64 key;
+ union {
+ __aligned_u64 value;
+ __aligned_u64 next_key;
+ };
+ __u64 flags;
+ };
+
+ struct { /* anonymous struct used by BPF_PROG_LOAD command */
+ __u32 prog_type; /* one of enum bpf_prog_type */
+ __u32 insn_cnt;
+ __aligned_u64 insns;
+ __aligned_u64 license;
+ __u32 log_level; /* verbosity level of verifier */
+ __u32 log_size; /* size of user buffer */
+ __aligned_u64 log_buf; /* user supplied buffer */
+ __u32 kern_version; /* checked when prog_type=kprobe */
+ __u32 prog_flags;
+ char prog_name[BPF_OBJ_NAME_LEN];
+ __u32 prog_ifindex; /* ifindex of netdev to prep for */
+ /* For some prog types expected attach type must be known at
+ * load time to verify attach type specific parts of prog
+ * (context accesses, allowed helpers, etc).
+ */
+ __u32 expected_attach_type;
+ };
+
+ struct { /* anonymous struct used by BPF_OBJ_* commands */
+ __aligned_u64 pathname;
+ __u32 bpf_fd;
+ __u32 file_flags;
+ };
+
+ struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
+ __u32 target_fd; /* container object to attach to */
+ __u32 attach_bpf_fd; /* eBPF program to attach */
+ __u32 attach_type;
+ __u32 attach_flags;
+ };
+
+ struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
+ __u32 prog_fd;
+ __u32 retval;
+ __u32 data_size_in;
+ __u32 data_size_out;
+ __aligned_u64 data_in;
+ __aligned_u64 data_out;
+ __u32 repeat;
+ __u32 duration;
+ } test;
+
+ struct { /* anonymous struct used by BPF_*_GET_*_ID */
+ union {
+ __u32 start_id;
+ __u32 prog_id;
+ __u32 map_id;
+ __u32 btf_id;
+ };
+ __u32 next_id;
+ __u32 open_flags;
+ };
+
+ struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
+ __u32 bpf_fd;
+ __u32 info_len;
+ __aligned_u64 info;
+ } info;
+
+ struct { /* anonymous struct used by BPF_PROG_QUERY command */
+ __u32 target_fd; /* container object to query */
+ __u32 attach_type;
+ __u32 query_flags;
+ __u32 attach_flags;
+ __aligned_u64 prog_ids;
+ __u32 prog_cnt;
+ } query;
+
+ struct {
+ __u64 name;
+ __u32 prog_fd;
+ } raw_tracepoint;
+
+ struct { /* anonymous struct for BPF_BTF_LOAD */
+ __aligned_u64 btf;
+ __aligned_u64 btf_log_buf;
+ __u32 btf_size;
+ __u32 btf_log_size;
+ __u32 btf_log_level;
+ };
+
+ struct {
+ __u32 pid; /* input: pid */
+ __u32 fd; /* input: fd */
+ __u32 flags; /* input: flags */
+ __u32 buf_len; /* input/output: buf len */
+ __aligned_u64 buf; /* input/output:
+ * tp_name for tracepoint
+ * symbol for kprobe
+ * filename for uprobe
+ */
+ __u32 prog_id; /* output: prod_id */
+ __u32 fd_type; /* output: BPF_FD_TYPE_* */
+ __u64 probe_offset; /* output: probe_offset */
+ __u64 probe_addr; /* output: probe_addr */
+ } task_fd_query;
+} __attribute__((aligned(8)));
+
+/* The description below is an attempt at providing documentation to eBPF
+ * developers about the multiple available eBPF helper functions. It can be
+ * parsed and used to produce a manual page. The workflow is the following,
+ * and requires the rst2man utility:
+ *
+ * $ ./scripts/bpf_helpers_doc.py \
+ * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst
+ * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7
+ * $ man /tmp/bpf-helpers.7
+ *
+ * Note that in order to produce this external documentation, some RST
+ * formatting is used in the descriptions to get "bold" and "italics" in
+ * manual pages. Also note that the few trailing white spaces are
+ * intentional, removing them would break paragraphs for rst2man.
+ *
+ * Start of BPF helper function descriptions:
+ *
+ * void *bpf_map_lookup_elem(struct bpf_map *map, const void *key)
+ * Description
+ * Perform a lookup in *map* for an entry associated to *key*.
+ * Return
+ * Map value associated to *key*, or **NULL** if no entry was
+ * found.
+ *
+ * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags)
+ * Description
+ * Add or update the value of the entry associated to *key* in
+ * *map* with *value*. *flags* is one of:
+ *
+ * **BPF_NOEXIST**
+ * The entry for *key* must not exist in the map.
+ * **BPF_EXIST**
+ * The entry for *key* must already exist in the map.
+ * **BPF_ANY**
+ * No condition on the existence of the entry for *key*.
+ *
+ * Flag value **BPF_NOEXIST** cannot be used for maps of types
+ * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all
+ * elements always exist), the helper would return an error.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_delete_elem(struct bpf_map *map, const void *key)
+ * Description
+ * Delete entry with *key* from *map*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read(void *dst, u32 size, const void *src)
+ * Description
+ * For tracing programs, safely attempt to read *size* bytes from
+ * address *src* and store the data in *dst*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_ktime_get_ns(void)
+ * Description
+ * Return the time elapsed since system boot, in nanoseconds.
+ * Return
+ * Current *ktime*.
+ *
+ * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...)
+ * Description
+ * This helper is a "printk()-like" facility for debugging. It
+ * prints a message defined by format *fmt* (of size *fmt_size*)
+ * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if
+ * available. It can take up to three additional **u64**
+ * arguments (as an eBPF helpers, the total number of arguments is
+ * limited to five).
+ *
+ * Each time the helper is called, it appends a line to the trace.
+ * The format of the trace is customizable, and the exact output
+ * one will get depends on the options set in
+ * *\/sys/kernel/debug/tracing/trace_options* (see also the
+ * *README* file under the same directory). However, it usually
+ * defaults to something like:
+ *
+ * ::
+ *
+ * telnet-470 [001] .N.. 419421.045894: 0x00000001: <formatted msg>
+ *
+ * In the above:
+ *
+ * * ``telnet`` is the name of the current task.
+ * * ``470`` is the PID of the current task.
+ * * ``001`` is the CPU number on which the task is
+ * running.
+ * * In ``.N..``, each character refers to a set of
+ * options (whether irqs are enabled, scheduling
+ * options, whether hard/softirqs are running, level of
+ * preempt_disabled respectively). **N** means that
+ * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED**
+ * are set.
+ * * ``419421.045894`` is a timestamp.
+ * * ``0x00000001`` is a fake value used by BPF for the
+ * instruction pointer register.
+ * * ``<formatted msg>`` is the message formatted with
+ * *fmt*.
+ *
+ * The conversion specifiers supported by *fmt* are similar, but
+ * more limited than for printk(). They are **%d**, **%i**,
+ * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**,
+ * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size
+ * of field, padding with zeroes, etc.) is available, and the
+ * helper will return **-EINVAL** (but print nothing) if it
+ * encounters an unknown specifier.
+ *
+ * Also, note that **bpf_trace_printk**\ () is slow, and should
+ * only be used for debugging purposes. For this reason, a notice
+ * bloc (spanning several lines) is printed to kernel logs and
+ * states that the helper should not be used "for production use"
+ * the first time this helper is used (or more precisely, when
+ * **trace_printk**\ () buffers are allocated). For passing values
+ * to user space, perf events should be preferred.
+ * Return
+ * The number of bytes written to the buffer, or a negative error
+ * in case of failure.
+ *
+ * u32 bpf_get_prandom_u32(void)
+ * Description
+ * Get a pseudo-random number.
+ *
+ * From a security point of view, this helper uses its own
+ * pseudo-random internal state, and cannot be used to infer the
+ * seed of other random functions in the kernel. However, it is
+ * essential to note that the generator used by the helper is not
+ * cryptographically secure.
+ * Return
+ * A random 32-bit unsigned value.
+ *
+ * u32 bpf_get_smp_processor_id(void)
+ * Description
+ * Get the SMP (symmetric multiprocessing) processor id. Note that
+ * all programs run with preemption disabled, which means that the
+ * SMP processor id is stable during all the execution of the
+ * program.
+ * Return
+ * The SMP id of the processor running the program.
+ *
+ * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags)
+ * Description
+ * Store *len* bytes from address *from* into the packet
+ * associated to *skb*, at *offset*. *flags* are a combination of
+ * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the
+ * checksum for the packet after storing the bytes) and
+ * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\
+ * **->swhash** and *skb*\ **->l4hash** to 0).
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size)
+ * Description
+ * Recompute the layer 3 (e.g. IP) checksum for the packet
+ * associated to *skb*. Computation is incremental, so the helper
+ * must know the former value of the header field that was
+ * modified (*from*), the new value of this field (*to*), and the
+ * number of bytes (2 or 4) for this field, stored in *size*.
+ * Alternatively, it is possible to store the difference between
+ * the previous and the new values of the header field in *to*, by
+ * setting *from* and *size* to 0. For both methods, *offset*
+ * indicates the location of the IP checksum within the packet.
+ *
+ * This helper works in combination with **bpf_csum_diff**\ (),
+ * which does not update the checksum in-place, but offers more
+ * flexibility and can handle sizes larger than 2 or 4 for the
+ * checksum to update.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags)
+ * Description
+ * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the
+ * packet associated to *skb*. Computation is incremental, so the
+ * helper must know the former value of the header field that was
+ * modified (*from*), the new value of this field (*to*), and the
+ * number of bytes (2 or 4) for this field, stored on the lowest
+ * four bits of *flags*. Alternatively, it is possible to store
+ * the difference between the previous and the new values of the
+ * header field in *to*, by setting *from* and the four lowest
+ * bits of *flags* to 0. For both methods, *offset* indicates the
+ * location of the IP checksum within the packet. In addition to
+ * the size of the field, *flags* can be added (bitwise OR) actual
+ * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left
+ * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and
+ * for updates resulting in a null checksum the value is set to
+ * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates
+ * the checksum is to be computed against a pseudo-header.
+ *
+ * This helper works in combination with **bpf_csum_diff**\ (),
+ * which does not update the checksum in-place, but offers more
+ * flexibility and can handle sizes larger than 2 or 4 for the
+ * checksum to update.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index)
+ * Description
+ * This special helper is used to trigger a "tail call", or in
+ * other words, to jump into another eBPF program. The same stack
+ * frame is used (but values on stack and in registers for the
+ * caller are not accessible to the callee). This mechanism allows
+ * for program chaining, either for raising the maximum number of
+ * available eBPF instructions, or to execute given programs in
+ * conditional blocks. For security reasons, there is an upper
+ * limit to the number of successive tail calls that can be
+ * performed.
+ *
+ * Upon call of this helper, the program attempts to jump into a
+ * program referenced at index *index* in *prog_array_map*, a
+ * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes
+ * *ctx*, a pointer to the context.
+ *
+ * If the call succeeds, the kernel immediately runs the first
+ * instruction of the new program. This is not a function call,
+ * and it never returns to the previous program. If the call
+ * fails, then the helper has no effect, and the caller continues
+ * to run its subsequent instructions. A call can fail if the
+ * destination program for the jump does not exist (i.e. *index*
+ * is superior to the number of entries in *prog_array_map*), or
+ * if the maximum number of tail calls has been reached for this
+ * chain of programs. This limit is defined in the kernel by the
+ * macro **MAX_TAIL_CALL_CNT** (not accessible to user space),
+ * which is currently set to 32.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags)
+ * Description
+ * Clone and redirect the packet associated to *skb* to another
+ * net device of index *ifindex*. Both ingress and egress
+ * interfaces can be used for redirection. The **BPF_F_INGRESS**
+ * value in *flags* is used to make the distinction (ingress path
+ * is selected if the flag is present, egress path otherwise).
+ * This is the only flag supported for now.
+ *
+ * In comparison with **bpf_redirect**\ () helper,
+ * **bpf_clone_redirect**\ () has the associated cost of
+ * duplicating the packet buffer, but this can be executed out of
+ * the eBPF program. Conversely, **bpf_redirect**\ () is more
+ * efficient, but it is handled through an action code where the
+ * redirection happens only after the eBPF program has returned.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_get_current_pid_tgid(void)
+ * Return
+ * A 64-bit integer containing the current tgid and pid, and
+ * created as such:
+ * *current_task*\ **->tgid << 32 \|**
+ * *current_task*\ **->pid**.
+ *
+ * u64 bpf_get_current_uid_gid(void)
+ * Return
+ * A 64-bit integer containing the current GID and UID, and
+ * created as such: *current_gid* **<< 32 \|** *current_uid*.
+ *
+ * int bpf_get_current_comm(char *buf, u32 size_of_buf)
+ * Description
+ * Copy the **comm** attribute of the current task into *buf* of
+ * *size_of_buf*. The **comm** attribute contains the name of
+ * the executable (excluding the path) for the current task. The
+ * *size_of_buf* must be strictly positive. On success, the
+ * helper makes sure that the *buf* is NUL-terminated. On failure,
+ * it is filled with zeroes.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u32 bpf_get_cgroup_classid(struct sk_buff *skb)
+ * Description
+ * Retrieve the classid for the current task, i.e. for the net_cls
+ * cgroup to which *skb* belongs.
+ *
+ * This helper can be used on TC egress path, but not on ingress.
+ *
+ * The net_cls cgroup provides an interface to tag network packets
+ * based on a user-provided identifier for all traffic coming from
+ * the tasks belonging to the related cgroup. See also the related
+ * kernel documentation, available from the Linux sources in file
+ * *Documentation/cgroup-v1/net_cls.txt*.
+ *
+ * The Linux kernel has two versions for cgroups: there are
+ * cgroups v1 and cgroups v2. Both are available to users, who can
+ * use a mixture of them, but note that the net_cls cgroup is for
+ * cgroup v1 only. This makes it incompatible with BPF programs
+ * run on cgroups, which is a cgroup-v2-only feature (a socket can
+ * only hold data for one version of cgroups at a time).
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to
+ * "**y**" or to "**m**".
+ * Return
+ * The classid, or 0 for the default unconfigured classid.
+ *
+ * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
+ * Description
+ * Push a *vlan_tci* (VLAN tag control information) of protocol
+ * *vlan_proto* to the packet associated to *skb*, then update
+ * the checksum. Note that if *vlan_proto* is different from
+ * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to
+ * be **ETH_P_8021Q**.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_vlan_pop(struct sk_buff *skb)
+ * Description
+ * Pop a VLAN header from the packet associated to *skb*.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
+ * Description
+ * Get tunnel metadata. This helper takes a pointer *key* to an
+ * empty **struct bpf_tunnel_key** of **size**, that will be
+ * filled with tunnel metadata for the packet associated to *skb*.
+ * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which
+ * indicates that the tunnel is based on IPv6 protocol instead of
+ * IPv4.
+ *
+ * The **struct bpf_tunnel_key** is an object that generalizes the
+ * principal parameters used by various tunneling protocols into a
+ * single struct. This way, it can be used to easily make a
+ * decision based on the contents of the encapsulation header,
+ * "summarized" in this struct. In particular, it holds the IP
+ * address of the remote end (IPv4 or IPv6, depending on the case)
+ * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also,
+ * this struct exposes the *key*\ **->tunnel_id**, which is
+ * generally mapped to a VNI (Virtual Network Identifier), making
+ * it programmable together with the **bpf_skb_set_tunnel_key**\
+ * () helper.
+ *
+ * Let's imagine that the following code is part of a program
+ * attached to the TC ingress interface, on one end of a GRE
+ * tunnel, and is supposed to filter out all messages coming from
+ * remote ends with IPv4 address other than 10.0.0.1:
+ *
+ * ::
+ *
+ * int ret;
+ * struct bpf_tunnel_key key = {};
+ *
+ * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ * if (ret < 0)
+ * return TC_ACT_SHOT; // drop packet
+ *
+ * if (key.remote_ipv4 != 0x0a000001)
+ * return TC_ACT_SHOT; // drop packet
+ *
+ * return TC_ACT_OK; // accept packet
+ *
+ * This interface can also be used with all encapsulation devices
+ * that can operate in "collect metadata" mode: instead of having
+ * one network device per specific configuration, the "collect
+ * metadata" mode only requires a single device where the
+ * configuration can be extracted from this helper.
+ *
+ * This can be used together with various tunnels such as VXLan,
+ * Geneve, GRE or IP in IP (IPIP).
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
+ * Description
+ * Populate tunnel metadata for packet associated to *skb.* The
+ * tunnel metadata is set to the contents of *key*, of *size*. The
+ * *flags* can be set to a combination of the following values:
+ *
+ * **BPF_F_TUNINFO_IPV6**
+ * Indicate that the tunnel is based on IPv6 protocol
+ * instead of IPv4.
+ * **BPF_F_ZERO_CSUM_TX**
+ * For IPv4 packets, add a flag to tunnel metadata
+ * indicating that checksum computation should be skipped
+ * and checksum set to zeroes.
+ * **BPF_F_DONT_FRAGMENT**
+ * Add a flag to tunnel metadata indicating that the
+ * packet should not be fragmented.
+ * **BPF_F_SEQ_NUMBER**
+ * Add a flag to tunnel metadata indicating that a
+ * sequence number should be added to tunnel header before
+ * sending the packet. This flag was added for GRE
+ * encapsulation, but might be used with other protocols
+ * as well in the future.
+ *
+ * Here is a typical usage on the transmit path:
+ *
+ * ::
+ *
+ * struct bpf_tunnel_key key;
+ * populate key ...
+ * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
+ * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0);
+ *
+ * See also the description of the **bpf_skb_get_tunnel_key**\ ()
+ * helper for additional information.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_perf_event_read(struct bpf_map *map, u64 flags)
+ * Description
+ * Read the value of a perf event counter. This helper relies on a
+ * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of
+ * the perf event counter is selected when *map* is updated with
+ * perf event file descriptors. The *map* is an array whose size
+ * is the number of available CPUs, and each cell contains a value
+ * relative to one CPU. The value to retrieve is indicated by
+ * *flags*, that contains the index of the CPU to look up, masked
+ * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to
+ * **BPF_F_CURRENT_CPU** to indicate that the value for the
+ * current CPU should be retrieved.
+ *
+ * Note that before Linux 4.13, only hardware perf event can be
+ * retrieved.
+ *
+ * Also, be aware that the newer helper
+ * **bpf_perf_event_read_value**\ () is recommended over
+ * **bpf_perf_event_read**\ () in general. The latter has some ABI
+ * quirks where error and counter value are used as a return code
+ * (which is wrong to do since ranges may overlap). This issue is
+ * fixed with **bpf_perf_event_read_value**\ (), which at the same
+ * time provides more features over the **bpf_perf_event_read**\
+ * () interface. Please refer to the description of
+ * **bpf_perf_event_read_value**\ () for details.
+ * Return
+ * The value of the perf event counter read from the map, or a
+ * negative error code in case of failure.
+ *
+ * int bpf_redirect(u32 ifindex, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*.
+ * This helper is somewhat similar to **bpf_clone_redirect**\
+ * (), except that the packet is not cloned, which provides
+ * increased performance.
+ *
+ * Except for XDP, both ingress and egress interfaces can be used
+ * for redirection. The **BPF_F_INGRESS** value in *flags* is used
+ * to make the distinction (ingress path is selected if the flag
+ * is present, egress path otherwise). Currently, XDP only
+ * supports redirection to the egress interface, and accepts no
+ * flag at all.
+ *
+ * The same effect can be attained with the more generic
+ * **bpf_redirect_map**\ (), which requires specific maps to be
+ * used but offers better performance.
+ * Return
+ * For XDP, the helper returns **XDP_REDIRECT** on success or
+ * **XDP_ABORTED** on error. For other program types, the values
+ * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on
+ * error.
+ *
+ * u32 bpf_get_route_realm(struct sk_buff *skb)
+ * Description
+ * Retrieve the realm or the route, that is to say the
+ * **tclassid** field of the destination for the *skb*. The
+ * indentifier retrieved is a user-provided tag, similar to the
+ * one used with the net_cls cgroup (see description for
+ * **bpf_get_cgroup_classid**\ () helper), but here this tag is
+ * held by a route (a destination entry), not by a task.
+ *
+ * Retrieving this identifier works with the clsact TC egress hook
+ * (see also **tc-bpf(8)**), or alternatively on conventional
+ * classful egress qdiscs, but not on TC ingress path. In case of
+ * clsact TC egress hook, this has the advantage that, internally,
+ * the destination entry has not been dropped yet in the transmit
+ * path. Therefore, the destination entry does not need to be
+ * artificially held via **netif_keep_dst**\ () for a classful
+ * qdisc until the *skb* is freed.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_IP_ROUTE_CLASSID** configuration option.
+ * Return
+ * The realm of the route for the packet associated to *skb*, or 0
+ * if none was found.
+ *
+ * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * Description
+ * Write raw *data* blob into a special BPF perf event held by
+ * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ * event must have the following attributes: **PERF_SAMPLE_RAW**
+ * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ * **PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ * The *flags* are used to indicate the index in *map* for which
+ * the value must be put, masked with **BPF_F_INDEX_MASK**.
+ * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ * to indicate that the index of the current CPU core should be
+ * used.
+ *
+ * The value to write, of *size*, is passed through eBPF stack and
+ * pointed by *data*.
+ *
+ * The context of the program *ctx* needs also be passed to the
+ * helper.
+ *
+ * On user space, a program willing to read the values needs to
+ * call **perf_event_open**\ () on the perf event (either for
+ * one or for all CPUs) and to store the file descriptor into the
+ * *map*. This must be done before the eBPF program can send data
+ * into it. An example is available in file
+ * *samples/bpf/trace_output_user.c* in the Linux kernel source
+ * tree (the eBPF program counterpart is in
+ * *samples/bpf/trace_output_kern.c*).
+ *
+ * **bpf_perf_event_output**\ () achieves better performance
+ * than **bpf_trace_printk**\ () for sharing data with user
+ * space, and is much better suitable for streaming data from eBPF
+ * programs.
+ *
+ * Note that this helper is not restricted to tracing use cases
+ * and can be used with programs attached to TC or XDP as well,
+ * where it allows for passing data to user space listeners. Data
+ * can be:
+ *
+ * * Only custom structs,
+ * * Only the packet payload, or
+ * * A combination of both.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len)
+ * Description
+ * This helper was provided as an easy way to load data from a
+ * packet. It can be used to load *len* bytes from *offset* from
+ * the packet associated to *skb*, into the buffer pointed by
+ * *to*.
+ *
+ * Since Linux 4.7, usage of this helper has mostly been replaced
+ * by "direct packet access", enabling packet data to be
+ * manipulated with *skb*\ **->data** and *skb*\ **->data_end**
+ * pointing respectively to the first byte of packet data and to
+ * the byte after the last byte of packet data. However, it
+ * remains useful if one wishes to read large quantities of data
+ * at once from a packet into the eBPF stack.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_get_stackid(struct pt_reg *ctx, struct bpf_map *map, u64 flags)
+ * Description
+ * Walk a user or a kernel stack and return its id. To achieve
+ * this, the helper needs *ctx*, which is a pointer to the context
+ * on which the tracing program is executed, and a pointer to a
+ * *map* of type **BPF_MAP_TYPE_STACK_TRACE**.
+ *
+ * The last argument, *flags*, holds the number of stack frames to
+ * skip (from 0 to 255), masked with
+ * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ * a combination of the following flags:
+ *
+ * **BPF_F_USER_STACK**
+ * Collect a user space stack instead of a kernel stack.
+ * **BPF_F_FAST_STACK_CMP**
+ * Compare stacks by hash only.
+ * **BPF_F_REUSE_STACKID**
+ * If two different stacks hash into the same *stackid*,
+ * discard the old one.
+ *
+ * The stack id retrieved is a 32 bit long integer handle which
+ * can be further combined with other data (including other stack
+ * ids) and used as a key into maps. This can be useful for
+ * generating a variety of graphs (such as flame graphs or off-cpu
+ * graphs).
+ *
+ * For walking a stack, this helper is an improvement over
+ * **bpf_probe_read**\ (), which can be used with unrolled loops
+ * but is not efficient and consumes a lot of eBPF instructions.
+ * Instead, **bpf_get_stackid**\ () can collect up to
+ * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that
+ * this limit can be controlled with the **sysctl** program, and
+ * that it should be manually increased in order to profile long
+ * user stacks (such as stacks for Java programs). To do so, use:
+ *
+ * ::
+ *
+ * # sysctl kernel.perf_event_max_stack=<new value>
+ * Return
+ * The positive or null stack id on success, or a negative error
+ * in case of failure.
+ *
+ * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed)
+ * Description
+ * Compute a checksum difference, from the raw buffer pointed by
+ * *from*, of length *from_size* (that must be a multiple of 4),
+ * towards the raw buffer pointed by *to*, of size *to_size*
+ * (same remark). An optional *seed* can be added to the value
+ * (this can be cascaded, the seed may come from a previous call
+ * to the helper).
+ *
+ * This is flexible enough to be used in several ways:
+ *
+ * * With *from_size* == 0, *to_size* > 0 and *seed* set to
+ * checksum, it can be used when pushing new data.
+ * * With *from_size* > 0, *to_size* == 0 and *seed* set to
+ * checksum, it can be used when removing data from a packet.
+ * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it
+ * can be used to compute a diff. Note that *from_size* and
+ * *to_size* do not need to be equal.
+ *
+ * This helper can be used in combination with
+ * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to
+ * which one can feed in the difference computed with
+ * **bpf_csum_diff**\ ().
+ * Return
+ * The checksum result, or a negative error code in case of
+ * failure.
+ *
+ * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size)
+ * Description
+ * Retrieve tunnel options metadata for the packet associated to
+ * *skb*, and store the raw tunnel option data to the buffer *opt*
+ * of *size*.
+ *
+ * This helper can be used with encapsulation devices that can
+ * operate in "collect metadata" mode (please refer to the related
+ * note in the description of **bpf_skb_get_tunnel_key**\ () for
+ * more details). A particular example where this can be used is
+ * in combination with the Geneve encapsulation protocol, where it
+ * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper)
+ * and retrieving arbitrary TLVs (Type-Length-Value headers) from
+ * the eBPF program. This allows for full customization of these
+ * headers.
+ * Return
+ * The size of the option data retrieved.
+ *
+ * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size)
+ * Description
+ * Set tunnel options metadata for the packet associated to *skb*
+ * to the option data contained in the raw buffer *opt* of *size*.
+ *
+ * See also the description of the **bpf_skb_get_tunnel_opt**\ ()
+ * helper for additional information.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags)
+ * Description
+ * Change the protocol of the *skb* to *proto*. Currently
+ * supported are transition from IPv4 to IPv6, and from IPv6 to
+ * IPv4. The helper takes care of the groundwork for the
+ * transition, including resizing the socket buffer. The eBPF
+ * program is expected to fill the new headers, if any, via
+ * **skb_store_bytes**\ () and to recompute the checksums with
+ * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\
+ * (). The main case for this helper is to perform NAT64
+ * operations out of an eBPF program.
+ *
+ * Internally, the GSO type is marked as dodgy so that headers are
+ * checked and segments are recalculated by the GSO/GRO engine.
+ * The size for GSO target is adapted as well.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_change_type(struct sk_buff *skb, u32 type)
+ * Description
+ * Change the packet type for the packet associated to *skb*. This
+ * comes down to setting *skb*\ **->pkt_type** to *type*, except
+ * the eBPF program does not have a write access to *skb*\
+ * **->pkt_type** beside this helper. Using a helper here allows
+ * for graceful handling of errors.
+ *
+ * The major use case is to change incoming *skb*s to
+ * **PACKET_HOST** in a programmatic way instead of having to
+ * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for
+ * example.
+ *
+ * Note that *type* only allows certain values. At this time, they
+ * are:
+ *
+ * **PACKET_HOST**
+ * Packet is for us.
+ * **PACKET_BROADCAST**
+ * Send packet to all.
+ * **PACKET_MULTICAST**
+ * Send packet to group.
+ * **PACKET_OTHERHOST**
+ * Send packet to someone else.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index)
+ * Description
+ * Check whether *skb* is a descendant of the cgroup2 held by
+ * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*.
+ * Return
+ * The return value depends on the result of the test, and can be:
+ *
+ * * 0, if the *skb* failed the cgroup2 descendant test.
+ * * 1, if the *skb* succeeded the cgroup2 descendant test.
+ * * A negative error code, if an error occurred.
+ *
+ * u32 bpf_get_hash_recalc(struct sk_buff *skb)
+ * Description
+ * Retrieve the hash of the packet, *skb*\ **->hash**. If it is
+ * not set, in particular if the hash was cleared due to mangling,
+ * recompute this hash. Later accesses to the hash can be done
+ * directly with *skb*\ **->hash**.
+ *
+ * Calling **bpf_set_hash_invalid**\ (), changing a packet
+ * prototype with **bpf_skb_change_proto**\ (), or calling
+ * **bpf_skb_store_bytes**\ () with the
+ * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear
+ * the hash and to trigger a new computation for the next call to
+ * **bpf_get_hash_recalc**\ ().
+ * Return
+ * The 32-bit hash.
+ *
+ * u64 bpf_get_current_task(void)
+ * Return
+ * A pointer to the current task struct.
+ *
+ * int bpf_probe_write_user(void *dst, const void *src, u32 len)
+ * Description
+ * Attempt in a safe way to write *len* bytes from the buffer
+ * *src* to *dst* in memory. It only works for threads that are in
+ * user context, and *dst* must be a valid user space address.
+ *
+ * This helper should not be used to implement any kind of
+ * security mechanism because of TOC-TOU attacks, but rather to
+ * debug, divert, and manipulate execution of semi-cooperative
+ * processes.
+ *
+ * Keep in mind that this feature is meant for experiments, and it
+ * has a risk of crashing the system and running programs.
+ * Therefore, when an eBPF program using this helper is attached,
+ * a warning including PID and process name is printed to kernel
+ * logs.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index)
+ * Description
+ * Check whether the probe is being run is the context of a given
+ * subset of the cgroup2 hierarchy. The cgroup2 to test is held by
+ * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*.
+ * Return
+ * The return value depends on the result of the test, and can be:
+ *
+ * * 0, if the *skb* task belongs to the cgroup2.
+ * * 1, if the *skb* task does not belong to the cgroup2.
+ * * A negative error code, if an error occurred.
+ *
+ * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags)
+ * Description
+ * Resize (trim or grow) the packet associated to *skb* to the
+ * new *len*. The *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * The basic idea is that the helper performs the needed work to
+ * change the size of the packet, then the eBPF program rewrites
+ * the rest via helpers like **bpf_skb_store_bytes**\ (),
+ * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ ()
+ * and others. This helper is a slow path utility intended for
+ * replies with control messages. And because it is targeted for
+ * slow path, the helper itself can afford to be slow: it
+ * implicitly linearizes, unclones and drops offloads from the
+ * *skb*.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_pull_data(struct sk_buff *skb, u32 len)
+ * Description
+ * Pull in non-linear data in case the *skb* is non-linear and not
+ * all of *len* are part of the linear section. Make *len* bytes
+ * from *skb* readable and writable. If a zero value is passed for
+ * *len*, then the whole length of the *skb* is pulled.
+ *
+ * This helper is only needed for reading and writing with direct
+ * packet access.
+ *
+ * For direct packet access, testing that offsets to access
+ * are within packet boundaries (test on *skb*\ **->data_end**) is
+ * susceptible to fail if offsets are invalid, or if the requested
+ * data is in non-linear parts of the *skb*. On failure the
+ * program can just bail out, or in the case of a non-linear
+ * buffer, use a helper to make the data available. The
+ * **bpf_skb_load_bytes**\ () helper is a first solution to access
+ * the data. Another one consists in using **bpf_skb_pull_data**
+ * to pull in once the non-linear parts, then retesting and
+ * eventually access the data.
+ *
+ * At the same time, this also makes sure the *skb* is uncloned,
+ * which is a necessary condition for direct write. As this needs
+ * to be an invariant for the write part only, the verifier
+ * detects writes and adds a prologue that is calling
+ * **bpf_skb_pull_data()** to effectively unclone the *skb* from
+ * the very beginning in case it is indeed cloned.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * s64 bpf_csum_update(struct sk_buff *skb, __wsum csum)
+ * Description
+ * Add the checksum *csum* into *skb*\ **->csum** in case the
+ * driver has supplied a checksum for the entire packet into that
+ * field. Return an error otherwise. This helper is intended to be
+ * used in combination with **bpf_csum_diff**\ (), in particular
+ * when the checksum needs to be updated after data has been
+ * written into the packet through direct packet access.
+ * Return
+ * The checksum on success, or a negative error code in case of
+ * failure.
+ *
+ * void bpf_set_hash_invalid(struct sk_buff *skb)
+ * Description
+ * Invalidate the current *skb*\ **->hash**. It can be used after
+ * mangling on headers through direct packet access, in order to
+ * indicate that the hash is outdated and to trigger a
+ * recalculation the next time the kernel tries to access this
+ * hash or when the **bpf_get_hash_recalc**\ () helper is called.
+ *
+ * int bpf_get_numa_node_id(void)
+ * Description
+ * Return the id of the current NUMA node. The primary use case
+ * for this helper is the selection of sockets for the local NUMA
+ * node, when the program is attached to sockets using the
+ * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**),
+ * but the helper is also available to other eBPF program types,
+ * similarly to **bpf_get_smp_processor_id**\ ().
+ * Return
+ * The id of current NUMA node.
+ *
+ * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags)
+ * Description
+ * Grows headroom of packet associated to *skb* and adjusts the
+ * offset of the MAC header accordingly, adding *len* bytes of
+ * space. It automatically extends and reallocates memory as
+ * required.
+ *
+ * This helper can be used on a layer 3 *skb* to push a MAC header
+ * for redirection into a layer 2 device.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta)
+ * Description
+ * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that
+ * it is possible to use a negative value for *delta*. This helper
+ * can be used to prepare the packet for pushing or popping
+ * headers.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
+ * Description
+ * Copy a NUL terminated string from an unsafe address
+ * *unsafe_ptr* to *dst*. The *size* should include the
+ * terminating NUL byte. In case the string length is smaller than
+ * *size*, the target is not padded with further NUL bytes. If the
+ * string length is larger than *size*, just *size*-1 bytes are
+ * copied and the last byte is set to NUL.
+ *
+ * On success, the length of the copied string is returned. This
+ * makes this helper useful in tracing programs for reading
+ * strings, and more importantly to get its length at runtime. See
+ * the following snippet:
+ *
+ * ::
+ *
+ * SEC("kprobe/sys_open")
+ * void bpf_sys_open(struct pt_regs *ctx)
+ * {
+ * char buf[PATHLEN]; // PATHLEN is defined to 256
+ * int res = bpf_probe_read_str(buf, sizeof(buf),
+ * ctx->di);
+ *
+ * // Consume buf, for example push it to
+ * // userspace via bpf_perf_event_output(); we
+ * // can use res (the string length) as event
+ * // size, after checking its boundaries.
+ * }
+ *
+ * In comparison, using **bpf_probe_read()** helper here instead
+ * to read the string would require to estimate the length at
+ * compile time, and would often result in copying more memory
+ * than necessary.
+ *
+ * Another useful use case is when parsing individual process
+ * arguments or individual environment variables navigating
+ * *current*\ **->mm->arg_start** and *current*\
+ * **->mm->env_start**: using this helper and the return value,
+ * one can quickly iterate at the right offset of the memory area.
+ * Return
+ * On success, the strictly positive length of the string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * u64 bpf_get_socket_cookie(struct sk_buff *skb)
+ * Description
+ * If the **struct sk_buff** pointed by *skb* has a known socket,
+ * retrieve the cookie (generated by the kernel) of this socket.
+ * If no cookie has been set yet, generate a new cookie. Once
+ * generated, the socket cookie remains stable for the life of the
+ * socket. This helper can be useful for monitoring per socket
+ * networking traffic statistics as it provides a unique socket
+ * identifier per namespace.
+ * Return
+ * A 8-byte long non-decreasing number on success, or 0 if the
+ * socket field is missing inside *skb*.
+ *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
+ * Description
+ * Equivalent to bpf_get_socket_cookie() helper that accepts
+ * *skb*, but gets socket from **struct bpf_sock_addr** contex.
+ * Return
+ * A 8-byte long non-decreasing number.
+ *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
+ * Description
+ * Equivalent to bpf_get_socket_cookie() helper that accepts
+ * *skb*, but gets socket from **struct bpf_sock_ops** contex.
+ * Return
+ * A 8-byte long non-decreasing number.
+ *
+ * u32 bpf_get_socket_uid(struct sk_buff *skb)
+ * Return
+ * The owner UID of the socket associated to *skb*. If the socket
+ * is **NULL**, or if it is not a full socket (i.e. if it is a
+ * time-wait or a request socket instead), **overflowuid** value
+ * is returned (note that **overflowuid** might also be the actual
+ * UID value for the socket).
+ *
+ * u32 bpf_set_hash(struct sk_buff *skb, u32 hash)
+ * Description
+ * Set the full hash for *skb* (set the field *skb*\ **->hash**)
+ * to value *hash*.
+ * Return
+ * 0
+ *
+ * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
+ * Description
+ * Emulate a call to **setsockopt()** on the socket associated to
+ * *bpf_socket*, which must be a full socket. The *level* at
+ * which the option resides and the name *optname* of the option
+ * must be specified, see **setsockopt(2)** for more information.
+ * The option value of length *optlen* is pointed by *optval*.
+ *
+ * This helper actually implements a subset of **setsockopt()**.
+ * It supports the following *level*\ s:
+ *
+ * * **SOL_SOCKET**, which supports the following *optname*\ s:
+ * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**,
+ * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**.
+ * * **IPPROTO_TCP**, which supports the following *optname*\ s:
+ * **TCP_CONGESTION**, **TCP_BPF_IW**,
+ * **TCP_BPF_SNDCWND_CLAMP**.
+ * * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
+ * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags)
+ * Description
+ * Grow or shrink the room for data in the packet associated to
+ * *skb* by *len_diff*, and according to the selected *mode*.
+ *
+ * There is a single supported mode at this time:
+ *
+ * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
+ * (room space is added or removed below the layer 3 header).
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags)
+ * Description
+ * Redirect the packet to the endpoint referenced by *map* at
+ * index *key*. Depending on its type, this *map* can contain
+ * references to net devices (for forwarding packets through other
+ * ports), or to CPUs (for redirecting XDP frames to another CPU;
+ * but this is only implemented for native XDP (with driver
+ * support) as of this writing).
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * When used to redirect packets to net devices, this helper
+ * provides a high performance increase over **bpf_redirect**\ ().
+ * This is due to various implementation details of the underlying
+ * mechanisms, one of which is the fact that **bpf_redirect_map**\
+ * () tries to send packet as a "bulk" to the device.
+ * Return
+ * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
+ *
+ * int bpf_sk_redirect_map(struct bpf_map *map, u32 key, u64 flags)
+ * Description
+ * Redirect the packet to the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress path otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * Add an entry to, or update a *map* referencing sockets. The
+ * *skops* is used as a new value for the entry associated to
+ * *key*. *flags* is one of:
+ *
+ * **BPF_NOEXIST**
+ * The entry for *key* must not exist in the map.
+ * **BPF_EXIST**
+ * The entry for *key* must already exist in the map.
+ * **BPF_ANY**
+ * No condition on the existence of the entry for *key*.
+ *
+ * If the *map* has eBPF programs (parser and verdict), those will
+ * be inherited by the socket being added. If the socket is
+ * already attached to eBPF programs, this results in an error.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta)
+ * Description
+ * Adjust the address pointed by *xdp_md*\ **->data_meta** by
+ * *delta* (which can be positive or negative). Note that this
+ * operation modifies the address stored in *xdp_md*\ **->data**,
+ * so the latter must be loaded only after the helper has been
+ * called.
+ *
+ * The use of *xdp_md*\ **->data_meta** is optional and programs
+ * are not required to use it. The rationale is that when the
+ * packet is processed with XDP (e.g. as DoS filter), it is
+ * possible to push further meta data along with it before passing
+ * to the stack, and to give the guarantee that an ingress eBPF
+ * program attached as a TC classifier on the same device can pick
+ * this up for further post-processing. Since TC works with socket
+ * buffers, it remains possible to set from XDP the **mark** or
+ * **priority** pointers, or other pointers for the socket buffer.
+ * Having this scratch space generic and programmable allows for
+ * more flexibility as the user is free to store whatever meta
+ * data they need.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size)
+ * Description
+ * Read the value of a perf event counter, and store it into *buf*
+ * of size *buf_size*. This helper relies on a *map* of type
+ * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event
+ * counter is selected when *map* is updated with perf event file
+ * descriptors. The *map* is an array whose size is the number of
+ * available CPUs, and each cell contains a value relative to one
+ * CPU. The value to retrieve is indicated by *flags*, that
+ * contains the index of the CPU to look up, masked with
+ * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to
+ * **BPF_F_CURRENT_CPU** to indicate that the value for the
+ * current CPU should be retrieved.
+ *
+ * This helper behaves in a way close to
+ * **bpf_perf_event_read**\ () helper, save that instead of
+ * just returning the value observed, it fills the *buf*
+ * structure. This allows for additional data to be retrieved: in
+ * particular, the enabled and running times (in *buf*\
+ * **->enabled** and *buf*\ **->running**, respectively) are
+ * copied. In general, **bpf_perf_event_read_value**\ () is
+ * recommended over **bpf_perf_event_read**\ (), which has some
+ * ABI issues and provides fewer functionalities.
+ *
+ * These values are interesting, because hardware PMU (Performance
+ * Monitoring Unit) counters are limited resources. When there are
+ * more PMU based perf events opened than available counters,
+ * kernel will multiplex these events so each event gets certain
+ * percentage (but not all) of the PMU time. In case that
+ * multiplexing happens, the number of samples or counter value
+ * will not reflect the case compared to when no multiplexing
+ * occurs. This makes comparison between different runs difficult.
+ * Typically, the counter value should be normalized before
+ * comparing to other experiments. The usual normalization is done
+ * as follows.
+ *
+ * ::
+ *
+ * normalized_counter = counter * t_enabled / t_running
+ *
+ * Where t_enabled is the time enabled for event and t_running is
+ * the time running for event since last normalization. The
+ * enabled and running times are accumulated since the perf event
+ * open. To achieve scaling factor between two invocations of an
+ * eBPF program, users can can use CPU id as the key (which is
+ * typical for perf array usage model) to remember the previous
+ * value and do the calculation inside the eBPF program.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size)
+ * Description
+ * For en eBPF program attached to a perf event, retrieve the
+ * value of the event counter associated to *ctx* and store it in
+ * the structure pointed by *buf* and of size *buf_size*. Enabled
+ * and running times are also stored in the structure (see
+ * description of helper **bpf_perf_event_read_value**\ () for
+ * more details).
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
+ * Description
+ * Emulate a call to **getsockopt()** on the socket associated to
+ * *bpf_socket*, which must be a full socket. The *level* at
+ * which the option resides and the name *optname* of the option
+ * must be specified, see **getsockopt(2)** for more information.
+ * The retrieved value is stored in the structure pointed by
+ * *opval* and of length *optlen*.
+ *
+ * This helper actually implements a subset of **getsockopt()**.
+ * It supports the following *level*\ s:
+ *
+ * * **IPPROTO_TCP**, which supports *optname*
+ * **TCP_CONGESTION**.
+ * * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
+ * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_override_return(struct pt_reg *regs, u64 rc)
+ * Description
+ * Used for error injection, this helper uses kprobes to override
+ * the return value of the probed function, and to set it to *rc*.
+ * The first argument is the context *regs* on which the kprobe
+ * works.
+ *
+ * This helper works by setting setting the PC (program counter)
+ * to an override function which is run in place of the original
+ * probed function. This means the probed function is not run at
+ * all. The replacement function just returns with the required
+ * value.
+ *
+ * This helper has security implications, and thus is subject to
+ * restrictions. It is only available if the kernel was compiled
+ * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration
+ * option, and in this case it only works on functions tagged with
+ * **ALLOW_ERROR_INJECTION** in the kernel code.
+ *
+ * Also, the helper is only available for the architectures having
+ * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing,
+ * x86 architecture is the only one to support this feature.
+ * Return
+ * 0
+ *
+ * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval)
+ * Description
+ * Attempt to set the value of the **bpf_sock_ops_cb_flags** field
+ * for the full TCP socket associated to *bpf_sock_ops* to
+ * *argval*.
+ *
+ * The primary use of this field is to determine if there should
+ * be calls to eBPF programs of type
+ * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP
+ * code. A program of the same type can change its value, per
+ * connection and as necessary, when the connection is
+ * established. This field is directly accessible for reading, but
+ * this helper must be used for updates in order to return an
+ * error if an eBPF program tries to set a callback that is not
+ * supported in the current kernel.
+ *
+ * The supported callback values that *argval* can combine are:
+ *
+ * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out)
+ * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission)
+ * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change)
+ *
+ * Here are some examples of where one could call such eBPF
+ * program:
+ *
+ * * When RTO fires.
+ * * When a packet is retransmitted.
+ * * When the connection terminates.
+ * * When a packet is sent.
+ * * When a packet is received.
+ * Return
+ * Code **-EINVAL** if the socket is not a full TCP socket;
+ * otherwise, a positive number containing the bits that could not
+ * be set is returned (which comes down to 0 if all bits were set
+ * as required).
+ *
+ * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags)
+ * Description
+ * This helper is used in programs implementing policies at the
+ * socket level. If the message *msg* is allowed to pass (i.e. if
+ * the verdict eBPF program returns **SK_PASS**), redirect it to
+ * the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress path otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes)
+ * Description
+ * For socket policies, apply the verdict of the eBPF program to
+ * the next *bytes* (number of bytes) of message *msg*.
+ *
+ * For example, this helper can be used in the following cases:
+ *
+ * * A single **sendmsg**\ () or **sendfile**\ () system call
+ * contains multiple logical messages that the eBPF program is
+ * supposed to read and for which it should apply a verdict.
+ * * An eBPF program only cares to read the first *bytes* of a
+ * *msg*. If the message has a large payload, then setting up
+ * and calling the eBPF program repeatedly for all bytes, even
+ * though the verdict is already known, would create unnecessary
+ * overhead.
+ *
+ * When called from within an eBPF program, the helper sets a
+ * counter internal to the BPF infrastructure, that is used to
+ * apply the last verdict to the next *bytes*. If *bytes* is
+ * smaller than the current data being processed from a
+ * **sendmsg**\ () or **sendfile**\ () system call, the first
+ * *bytes* will be sent and the eBPF program will be re-run with
+ * the pointer for start of data pointing to byte number *bytes*
+ * **+ 1**. If *bytes* is larger than the current data being
+ * processed, then the eBPF verdict will be applied to multiple
+ * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are
+ * consumed.
+ *
+ * Note that if a socket closes with the internal counter holding
+ * a non-zero value, this is not a problem because data is not
+ * being buffered for *bytes* and is sent as it is received.
+ * Return
+ * 0
+ *
+ * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes)
+ * Description
+ * For socket policies, prevent the execution of the verdict eBPF
+ * program for message *msg* until *bytes* (byte number) have been
+ * accumulated.
+ *
+ * This can be used when one needs a specific number of bytes
+ * before a verdict can be assigned, even if the data spans
+ * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme
+ * case would be a user calling **sendmsg**\ () repeatedly with
+ * 1-byte long message segments. Obviously, this is bad for
+ * performance, but it is still valid. If the eBPF program needs
+ * *bytes* bytes to validate a header, this helper can be used to
+ * prevent the eBPF program to be called again until *bytes* have
+ * been accumulated.
+ * Return
+ * 0
+ *
+ * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags)
+ * Description
+ * For socket policies, pull in non-linear data from user space
+ * for *msg* and set pointers *msg*\ **->data** and *msg*\
+ * **->data_end** to *start* and *end* bytes offsets into *msg*,
+ * respectively.
+ *
+ * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
+ * *msg* it can only parse data that the (**data**, **data_end**)
+ * pointers have already consumed. For **sendmsg**\ () hooks this
+ * is likely the first scatterlist element. But for calls relying
+ * on the **sendpage** handler (e.g. **sendfile**\ ()) this will
+ * be the range (**0**, **0**) because the data is shared with
+ * user space and by default the objective is to avoid allowing
+ * user space to modify data while (or after) eBPF verdict is
+ * being decided. This helper can be used to pull in data and to
+ * set the start and end pointer to given values. Data will be
+ * copied if necessary (i.e. if data was not linear and if start
+ * and end pointers do not point to the same chunk).
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len)
+ * Description
+ * Bind the socket associated to *ctx* to the address pointed by
+ * *addr*, of length *addr_len*. This allows for making outgoing
+ * connection from the desired IP address, which can be useful for
+ * example when all processes inside a cgroup should use one
+ * single IP address on a host that has multiple IP configured.
+ *
+ * This helper works for IPv4 and IPv6, TCP and UDP sockets. The
+ * domain (*addr*\ **->sa_family**) must be **AF_INET** (or
+ * **AF_INET6**). Looking for a free port to bind to can be
+ * expensive, therefore binding to port is not permitted by the
+ * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively)
+ * must be set to zero.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta)
+ * Description
+ * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is
+ * only possible to shrink the packet as of this writing,
+ * therefore *delta* must be a negative integer.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags)
+ * Description
+ * Retrieve the XFRM state (IP transform framework, see also
+ * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*.
+ *
+ * The retrieved value is stored in the **struct bpf_xfrm_state**
+ * pointed by *xfrm_state* and of length *size*.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_XFRM** configuration option.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags)
+ * Description
+ * Return a user or a kernel stack in bpf program provided buffer.
+ * To achieve this, the helper needs *ctx*, which is a pointer
+ * to the context on which the tracing program is executed.
+ * To store the stacktrace, the bpf program provides *buf* with
+ * a nonnegative *size*.
+ *
+ * The last argument, *flags*, holds the number of stack frames to
+ * skip (from 0 to 255), masked with
+ * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ * the following flags:
+ *
+ * **BPF_F_USER_STACK**
+ * Collect a user space stack instead of a kernel stack.
+ * **BPF_F_USER_BUILD_ID**
+ * Collect buildid+offset instead of ips for user stack,
+ * only valid if **BPF_F_USER_STACK** is also specified.
+ *
+ * **bpf_get_stack**\ () can collect up to
+ * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
+ * to sufficient large buffer size. Note that
+ * this limit can be controlled with the **sysctl** program, and
+ * that it should be manually increased in order to profile long
+ * user stacks (such as stacks for Java programs). To do so, use:
+ *
+ * ::
+ *
+ * # sysctl kernel.perf_event_max_stack=<new value>
+ * Return
+ * A non-negative value equal to or less than *size* on success,
+ * or a negative error in case of failure.
+ *
+ * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * Description
+ * This helper is similar to **bpf_skb_load_bytes**\ () in that
+ * it provides an easy way to load *len* bytes from *offset*
+ * from the packet associated to *skb*, into the buffer pointed
+ * by *to*. The difference to **bpf_skb_load_bytes**\ () is that
+ * a fifth argument *start_header* exists in order to select a
+ * base offset to start from. *start_header* can be one of:
+ *
+ * **BPF_HDR_START_MAC**
+ * Base offset to load data from is *skb*'s mac header.
+ * **BPF_HDR_START_NET**
+ * Base offset to load data from is *skb*'s network header.
+ *
+ * In general, "direct packet access" is the preferred method to
+ * access packet data, however, this helper is in particular useful
+ * in socket filters where *skb*\ **->data** does not always point
+ * to the start of the mac header and where "direct packet access"
+ * is not available.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags)
+ * Description
+ * Do FIB lookup in kernel tables using parameters in *params*.
+ * If lookup is successful and result shows packet is to be
+ * forwarded, the neighbor tables are searched for the nexthop.
+ * If successful (ie., FIB lookup shows forwarding and nexthop
+ * is resolved), the nexthop address is returned in ipv4_dst
+ * or ipv6_dst based on family, smac is set to mac address of
+ * egress device, dmac is set to nexthop mac address, rt_metric
+ * is set to metric from route (IPv4/IPv6 only), and ifindex
+ * is set to the device index of the nexthop from the FIB lookup.
+ *
+ * *plen* argument is the size of the passed in struct.
+ * *flags* argument can be a combination of one or more of the
+ * following values:
+ *
+ * **BPF_FIB_LOOKUP_DIRECT**
+ * Do a direct table lookup vs full lookup using FIB
+ * rules.
+ * **BPF_FIB_LOOKUP_OUTPUT**
+ * Perform lookup from an egress perspective (default is
+ * ingress).
+ *
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** tc cls_act programs.
+ * Return
+ * * < 0 if any input argument is invalid
+ * * 0 on success (packet is forwarded, nexthop neighbor exists)
+ * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
+ * packet is not forwarded or needs assist from full stack
+ *
+ * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * Add an entry to, or update a sockhash *map* referencing sockets.
+ * The *skops* is used as a new value for the entry associated to
+ * *key*. *flags* is one of:
+ *
+ * **BPF_NOEXIST**
+ * The entry for *key* must not exist in the map.
+ * **BPF_EXIST**
+ * The entry for *key* must already exist in the map.
+ * **BPF_ANY**
+ * No condition on the existence of the entry for *key*.
+ *
+ * If the *map* has eBPF programs (parser and verdict), those will
+ * be inherited by the socket being added. If the socket is
+ * already attached to eBPF programs, this results in an error.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * This helper is used in programs implementing policies at the
+ * socket level. If the message *msg* is allowed to pass (i.e. if
+ * the verdict eBPF program returns **SK_PASS**), redirect it to
+ * the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress path otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * int bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * This helper is used in programs implementing policies at the
+ * skb socket level. If the sk_buff *skb* is allowed to pass (i.e.
+ * if the verdeict eBPF program returns **SK_PASS**), redirect it
+ * to the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * int bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len)
+ * Description
+ * Encapsulate the packet associated to *skb* within a Layer 3
+ * protocol header. This header is provided in the buffer at
+ * address *hdr*, with *len* its size in bytes. *type* indicates
+ * the protocol of the header and can be one of:
+ *
+ * **BPF_LWT_ENCAP_SEG6**
+ * IPv6 encapsulation with Segment Routing Header
+ * (**struct ipv6_sr_hdr**). *hdr* only contains the SRH,
+ * the IPv6 header is computed by the kernel.
+ * **BPF_LWT_ENCAP_SEG6_INLINE**
+ * Only works if *skb* contains an IPv6 packet. Insert a
+ * Segment Routing Header (**struct ipv6_sr_hdr**) inside
+ * the IPv6 header.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len)
+ * Description
+ * Store *len* bytes from address *from* into the packet
+ * associated to *skb*, at *offset*. Only the flags, tag and TLVs
+ * inside the outermost IPv6 Segment Routing Header can be
+ * modified through this helper.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta)
+ * Description
+ * Adjust the size allocated to TLVs in the outermost IPv6
+ * Segment Routing Header contained in the packet associated to
+ * *skb*, at position *offset* by *delta* bytes. Only offsets
+ * after the segments are accepted. *delta* can be as well
+ * positive (growing) as negative (shrinking).
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len)
+ * Description
+ * Apply an IPv6 Segment Routing action of type *action* to the
+ * packet associated to *skb*. Each action takes a parameter
+ * contained at address *param*, and of length *param_len* bytes.
+ * *action* can be one of:
+ *
+ * **SEG6_LOCAL_ACTION_END_X**
+ * End.X action: Endpoint with Layer-3 cross-connect.
+ * Type of *param*: **struct in6_addr**.
+ * **SEG6_LOCAL_ACTION_END_T**
+ * End.T action: Endpoint with specific IPv6 table lookup.
+ * Type of *param*: **int**.
+ * **SEG6_LOCAL_ACTION_END_B6**
+ * End.B6 action: Endpoint bound to an SRv6 policy.
+ * Type of param: **struct ipv6_sr_hdr**.
+ * **SEG6_LOCAL_ACTION_END_B6_ENCAP**
+ * End.B6.Encap action: Endpoint bound to an SRv6
+ * encapsulation policy.
+ * Type of param: **struct ipv6_sr_hdr**.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded key press with *scancode*,
+ * *toggle* value in the given *protocol*. The scancode will be
+ * translated to a keycode using the rc keymap, and reported as
+ * an input key down event. After a period a key up event is
+ * generated. This period can be extended by calling either
+ * **bpf_rc_keydown** () again with the same values, or calling
+ * **bpf_rc_repeat** ().
+ *
+ * Some protocols include a toggle bit, in case the button was
+ * released and pressed again between consecutive scancodes.
+ *
+ * The *ctx* should point to the lirc sample as passed into
+ * the program.
+ *
+ * The *protocol* is the decoded protocol number (see
+ * **enum rc_proto** for some predefined values).
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ * "**y**".
+ * Return
+ * 0
+ *
+ * int bpf_rc_repeat(void *ctx)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded repeat key message. This delays
+ * the generation of a key up event for previously generated
+ * key down event.
+ *
+ * Some IR protocols like NEC have a special IR message for
+ * repeating last button, for when a button is held down.
+ *
+ * The *ctx* should point to the lirc sample as passed into
+ * the program.
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ * "**y**".
+ * Return
+ * 0
+ *
+ * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb)
+ * Description
+ * Return the cgroup v2 id of the socket associated with the *skb*.
+ * This is roughly similar to the **bpf_get_cgroup_classid**\ ()
+ * helper for cgroup v1 by providing a tag resp. identifier that
+ * can be matched on or used for map lookups e.g. to implement
+ * policy. The cgroup v2 id of a given path in the hierarchy is
+ * exposed in user space through the f_handle API in order to get
+ * to the same 64-bit id.
+ *
+ * This helper can be used on TC egress path, but not on ingress,
+ * and is available only if the kernel was compiled with the
+ * **CONFIG_SOCK_CGROUP_DATA** configuration option.
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of cgroup associated
+ * with the *skb* at the *ancestor_level*. The root cgroup is at
+ * *ancestor_level* zero and each step down the hierarchy
+ * increments the level. If *ancestor_level* == level of cgroup
+ * associated with *skb*, then return value will be same as that
+ * of **bpf_skb_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with *skb*.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_skb_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * u64 bpf_get_current_cgroup_id(void)
+ * Return
+ * A 64-bit integer containing the current cgroup id based
+ * on the cgroup within which the current task is running.
+ *
+ * void* get_local_storage(void *map, u64 flags)
+ * Description
+ * Get the pointer to the local storage area.
+ * The type and the size of the local storage is defined
+ * by the *map* argument.
+ * The *flags* meaning is specific for each map type,
+ * and has to be 0 for cgroup local storage.
+ *
+ * Depending on the bpf program type, a local storage area
+ * can be shared between multiple instances of the bpf program,
+ * running simultaneously.
+ *
+ * A user should care about the synchronization by himself.
+ * For example, by using the BPF_STX_XADD instruction to alter
+ * the shared data.
+ * Return
+ * Pointer to the local storage area.
+ *
+ * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * Select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY map
+ * It checks the selected sk is matching the incoming
+ * request in the skb.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ */
+#define __BPF_FUNC_MAPPER(FN) \
+ FN(unspec), \
+ FN(map_lookup_elem), \
+ FN(map_update_elem), \
+ FN(map_delete_elem), \
+ FN(probe_read), \
+ FN(ktime_get_ns), \
+ FN(trace_printk), \
+ FN(get_prandom_u32), \
+ FN(get_smp_processor_id), \
+ FN(skb_store_bytes), \
+ FN(l3_csum_replace), \
+ FN(l4_csum_replace), \
+ FN(tail_call), \
+ FN(clone_redirect), \
+ FN(get_current_pid_tgid), \
+ FN(get_current_uid_gid), \
+ FN(get_current_comm), \
+ FN(get_cgroup_classid), \
+ FN(skb_vlan_push), \
+ FN(skb_vlan_pop), \
+ FN(skb_get_tunnel_key), \
+ FN(skb_set_tunnel_key), \
+ FN(perf_event_read), \
+ FN(redirect), \
+ FN(get_route_realm), \
+ FN(perf_event_output), \
+ FN(skb_load_bytes), \
+ FN(get_stackid), \
+ FN(csum_diff), \
+ FN(skb_get_tunnel_opt), \
+ FN(skb_set_tunnel_opt), \
+ FN(skb_change_proto), \
+ FN(skb_change_type), \
+ FN(skb_under_cgroup), \
+ FN(get_hash_recalc), \
+ FN(get_current_task), \
+ FN(probe_write_user), \
+ FN(current_task_under_cgroup), \
+ FN(skb_change_tail), \
+ FN(skb_pull_data), \
+ FN(csum_update), \
+ FN(set_hash_invalid), \
+ FN(get_numa_node_id), \
+ FN(skb_change_head), \
+ FN(xdp_adjust_head), \
+ FN(probe_read_str), \
+ FN(get_socket_cookie), \
+ FN(get_socket_uid), \
+ FN(set_hash), \
+ FN(setsockopt), \
+ FN(skb_adjust_room), \
+ FN(redirect_map), \
+ FN(sk_redirect_map), \
+ FN(sock_map_update), \
+ FN(xdp_adjust_meta), \
+ FN(perf_event_read_value), \
+ FN(perf_prog_read_value), \
+ FN(getsockopt), \
+ FN(override_return), \
+ FN(sock_ops_cb_flags_set), \
+ FN(msg_redirect_map), \
+ FN(msg_apply_bytes), \
+ FN(msg_cork_bytes), \
+ FN(msg_pull_data), \
+ FN(bind), \
+ FN(xdp_adjust_tail), \
+ FN(skb_get_xfrm_state), \
+ FN(get_stack), \
+ FN(skb_load_bytes_relative), \
+ FN(fib_lookup), \
+ FN(sock_hash_update), \
+ FN(msg_redirect_hash), \
+ FN(sk_redirect_hash), \
+ FN(lwt_push_encap), \
+ FN(lwt_seg6_store_bytes), \
+ FN(lwt_seg6_adjust_srh), \
+ FN(lwt_seg6_action), \
+ FN(rc_repeat), \
+ FN(rc_keydown), \
+ FN(skb_cgroup_id), \
+ FN(get_current_cgroup_id), \
+ FN(get_local_storage), \
+ FN(sk_select_reuseport), \
+ FN(skb_ancestor_cgroup_id),
+
+/* integer value in 'imm' field of BPF_CALL instruction selects which helper
+ * function eBPF program intends to call
+ */
+#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x
+enum bpf_func_id {
+ __BPF_FUNC_MAPPER(__BPF_ENUM_FN)
+ __BPF_FUNC_MAX_ID,
+};
+#undef __BPF_ENUM_FN
+
+/* All flags used by eBPF helper functions, placed here. */
+
+/* BPF_FUNC_skb_store_bytes flags. */
+#define BPF_F_RECOMPUTE_CSUM (1ULL << 0)
+#define BPF_F_INVALIDATE_HASH (1ULL << 1)
+
+/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags.
+ * First 4 bits are for passing the header field size.
+ */
+#define BPF_F_HDR_FIELD_MASK 0xfULL
+
+/* BPF_FUNC_l4_csum_replace flags. */
+#define BPF_F_PSEUDO_HDR (1ULL << 4)
+#define BPF_F_MARK_MANGLED_0 (1ULL << 5)
+#define BPF_F_MARK_ENFORCE (1ULL << 6)
+
+/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
+#define BPF_F_INGRESS (1ULL << 0)
+
+/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
+#define BPF_F_TUNINFO_IPV6 (1ULL << 0)
+
+/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */
+#define BPF_F_SKIP_FIELD_MASK 0xffULL
+#define BPF_F_USER_STACK (1ULL << 8)
+/* flags used by BPF_FUNC_get_stackid only. */
+#define BPF_F_FAST_STACK_CMP (1ULL << 9)
+#define BPF_F_REUSE_STACKID (1ULL << 10)
+/* flags used by BPF_FUNC_get_stack only. */
+#define BPF_F_USER_BUILD_ID (1ULL << 11)
+
+/* BPF_FUNC_skb_set_tunnel_key flags. */
+#define BPF_F_ZERO_CSUM_TX (1ULL << 1)
+#define BPF_F_DONT_FRAGMENT (1ULL << 2)
+#define BPF_F_SEQ_NUMBER (1ULL << 3)
+
+/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
+ * BPF_FUNC_perf_event_read_value flags.
+ */
+#define BPF_F_INDEX_MASK 0xffffffffULL
+#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK
+/* BPF_FUNC_perf_event_output for sk_buff input context. */
+#define BPF_F_CTXLEN_MASK (0xfffffULL << 32)
+
+/* Mode for BPF_FUNC_skb_adjust_room helper. */
+enum bpf_adj_room_mode {
+ BPF_ADJ_ROOM_NET,
+};
+
+/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */
+enum bpf_hdr_start_off {
+ BPF_HDR_START_MAC,
+ BPF_HDR_START_NET,
+};
+
+/* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */
+enum bpf_lwt_encap_mode {
+ BPF_LWT_ENCAP_SEG6,
+ BPF_LWT_ENCAP_SEG6_INLINE
+};
+
+/* user accessible mirror of in-kernel sk_buff.
+ * new fields can only be added to the end of this structure
+ */
+struct __sk_buff {
+ __u32 len;
+ __u32 pkt_type;
+ __u32 mark;
+ __u32 queue_mapping;
+ __u32 protocol;
+ __u32 vlan_present;
+ __u32 vlan_tci;
+ __u32 vlan_proto;
+ __u32 priority;
+ __u32 ingress_ifindex;
+ __u32 ifindex;
+ __u32 tc_index;
+ __u32 cb[5];
+ __u32 hash;
+ __u32 tc_classid;
+ __u32 data;
+ __u32 data_end;
+ __u32 napi_id;
+
+ /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */
+ __u32 family;
+ __u32 remote_ip4; /* Stored in network byte order */
+ __u32 local_ip4; /* Stored in network byte order */
+ __u32 remote_ip6[4]; /* Stored in network byte order */
+ __u32 local_ip6[4]; /* Stored in network byte order */
+ __u32 remote_port; /* Stored in network byte order */
+ __u32 local_port; /* stored in host byte order */
+ /* ... here. */
+
+ __u32 data_meta;
+};
+
+struct bpf_tunnel_key {
+ __u32 tunnel_id;
+ union {
+ __u32 remote_ipv4;
+ __u32 remote_ipv6[4];
+ };
+ __u8 tunnel_tos;
+ __u8 tunnel_ttl;
+ __u16 tunnel_ext; /* Padding, future use. */
+ __u32 tunnel_label;
+};
+
+/* user accessible mirror of in-kernel xfrm_state.
+ * new fields can only be added to the end of this structure
+ */
+struct bpf_xfrm_state {
+ __u32 reqid;
+ __u32 spi; /* Stored in network byte order */
+ __u16 family;
+ __u16 ext; /* Padding, future use. */
+ union {
+ __u32 remote_ipv4; /* Stored in network byte order */
+ __u32 remote_ipv6[4]; /* Stored in network byte order */
+ };
+};
+
+/* Generic BPF return codes which all BPF program types may support.
+ * The values are binary compatible with their TC_ACT_* counter-part to
+ * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT
+ * programs.
+ *
+ * XDP is handled seprately, see XDP_*.
+ */
+enum bpf_ret_code {
+ BPF_OK = 0,
+ /* 1 reserved */
+ BPF_DROP = 2,
+ /* 3-6 reserved */
+ BPF_REDIRECT = 7,
+ /* >127 are reserved for prog type specific return codes */
+};
+
+struct bpf_sock {
+ __u32 bound_dev_if;
+ __u32 family;
+ __u32 type;
+ __u32 protocol;
+ __u32 mark;
+ __u32 priority;
+ __u32 src_ip4; /* Allows 1,2,4-byte read.
+ * Stored in network byte order.
+ */
+ __u32 src_ip6[4]; /* Allows 1,2,4-byte read.
+ * Stored in network byte order.
+ */
+ __u32 src_port; /* Allows 4-byte read.
+ * Stored in host byte order
+ */
+};
+
+#define XDP_PACKET_HEADROOM 256
+
+/* User return codes for XDP prog type.
+ * A valid XDP program must return one of these defined values. All other
+ * return codes are reserved for future use. Unknown return codes will
+ * result in packet drops and a warning via bpf_warn_invalid_xdp_action().
+ */
+enum xdp_action {
+ XDP_ABORTED = 0,
+ XDP_DROP,
+ XDP_PASS,
+ XDP_TX,
+ XDP_REDIRECT,
+};
+
+/* user accessible metadata for XDP packet hook
+ * new fields must be added to the end of this structure
+ */
+struct xdp_md {
+ __u32 data;
+ __u32 data_end;
+ __u32 data_meta;
+ /* Below access go through struct xdp_rxq_info */
+ __u32 ingress_ifindex; /* rxq->dev->ifindex */
+ __u32 rx_queue_index; /* rxq->queue_index */
+};
+
+enum sk_action {
+ SK_DROP = 0,
+ SK_PASS,
+};
+
+/* user accessible metadata for SK_MSG packet hook, new fields must
+ * be added to the end of this structure
+ */
+struct sk_msg_md {
+ void *data;
+ void *data_end;
+
+ __u32 family;
+ __u32 remote_ip4; /* Stored in network byte order */
+ __u32 local_ip4; /* Stored in network byte order */
+ __u32 remote_ip6[4]; /* Stored in network byte order */
+ __u32 local_ip6[4]; /* Stored in network byte order */
+ __u32 remote_port; /* Stored in network byte order */
+ __u32 local_port; /* stored in host byte order */
+};
+
+struct sk_reuseport_md {
+ /*
+ * Start of directly accessible data. It begins from
+ * the tcp/udp header.
+ */
+ void *data;
+ void *data_end; /* End of directly accessible data */
+ /*
+ * Total length of packet (starting from the tcp/udp header).
+ * Note that the directly accessible bytes (data_end - data)
+ * could be less than this "len". Those bytes could be
+ * indirectly read by a helper "bpf_skb_load_bytes()".
+ */
+ __u32 len;
+ /*
+ * Eth protocol in the mac header (network byte order). e.g.
+ * ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD)
+ */
+ __u32 eth_protocol;
+ __u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
+ __u32 bind_inany; /* Is sock bound to an INANY address? */
+ __u32 hash; /* A hash of the packet 4 tuples */
+};
+
+#define BPF_TAG_SIZE 8
+
+struct bpf_prog_info {
+ __u32 type;
+ __u32 id;
+ __u8 tag[BPF_TAG_SIZE];
+ __u32 jited_prog_len;
+ __u32 xlated_prog_len;
+ __aligned_u64 jited_prog_insns;
+ __aligned_u64 xlated_prog_insns;
+ __u64 load_time; /* ns since boottime */
+ __u32 created_by_uid;
+ __u32 nr_map_ids;
+ __aligned_u64 map_ids;
+ char name[BPF_OBJ_NAME_LEN];
+ __u32 ifindex;
+ __u32 gpl_compatible:1;
+ __u64 netns_dev;
+ __u64 netns_ino;
+ __u32 nr_jited_ksyms;
+ __u32 nr_jited_func_lens;
+ __aligned_u64 jited_ksyms;
+ __aligned_u64 jited_func_lens;
+} __attribute__((aligned(8)));
+
+struct bpf_map_info {
+ __u32 type;
+ __u32 id;
+ __u32 key_size;
+ __u32 value_size;
+ __u32 max_entries;
+ __u32 map_flags;
+ char name[BPF_OBJ_NAME_LEN];
+ __u32 ifindex;
+ __u32 :32;
+ __u64 netns_dev;
+ __u64 netns_ino;
+ __u32 btf_id;
+ __u32 btf_key_type_id;
+ __u32 btf_value_type_id;
+} __attribute__((aligned(8)));
+
+struct bpf_btf_info {
+ __aligned_u64 btf;
+ __u32 btf_size;
+ __u32 id;
+} __attribute__((aligned(8)));
+
+/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
+ * by user and intended to be used by socket (e.g. to bind to, depends on
+ * attach attach type).
+ */
+struct bpf_sock_addr {
+ __u32 user_family; /* Allows 4-byte read, but no write. */
+ __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write.
+ * Stored in network byte order.
+ */
+ __u32 user_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write.
+ * Stored in network byte order.
+ */
+ __u32 user_port; /* Allows 4-byte read and write.
+ * Stored in network byte order
+ */
+ __u32 family; /* Allows 4-byte read, but no write */
+ __u32 type; /* Allows 4-byte read, but no write */
+ __u32 protocol; /* Allows 4-byte read, but no write */
+ __u32 msg_src_ip4; /* Allows 1,2,4-byte read an 4-byte write.
+ * Stored in network byte order.
+ */
+ __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write.
+ * Stored in network byte order.
+ */
+};
+
+/* User bpf_sock_ops struct to access socket values and specify request ops
+ * and their replies.
+ * Some of this fields are in network (bigendian) byte order and may need
+ * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h).
+ * New fields can only be added at the end of this structure
+ */
+struct bpf_sock_ops {
+ __u32 op;
+ union {
+ __u32 args[4]; /* Optionally passed to bpf program */
+ __u32 reply; /* Returned by bpf program */
+ __u32 replylong[4]; /* Optionally returned by bpf prog */
+ };
+ __u32 family;
+ __u32 remote_ip4; /* Stored in network byte order */
+ __u32 local_ip4; /* Stored in network byte order */
+ __u32 remote_ip6[4]; /* Stored in network byte order */
+ __u32 local_ip6[4]; /* Stored in network byte order */
+ __u32 remote_port; /* Stored in network byte order */
+ __u32 local_port; /* stored in host byte order */
+ __u32 is_fullsock; /* Some TCP fields are only valid if
+ * there is a full socket. If not, the
+ * fields read as zero.
+ */
+ __u32 snd_cwnd;
+ __u32 srtt_us; /* Averaged RTT << 3 in usecs */
+ __u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */
+ __u32 state;
+ __u32 rtt_min;
+ __u32 snd_ssthresh;
+ __u32 rcv_nxt;
+ __u32 snd_nxt;
+ __u32 snd_una;
+ __u32 mss_cache;
+ __u32 ecn_flags;
+ __u32 rate_delivered;
+ __u32 rate_interval_us;
+ __u32 packets_out;
+ __u32 retrans_out;
+ __u32 total_retrans;
+ __u32 segs_in;
+ __u32 data_segs_in;
+ __u32 segs_out;
+ __u32 data_segs_out;
+ __u32 lost_out;
+ __u32 sacked_out;
+ __u32 sk_txhash;
+ __u64 bytes_received;
+ __u64 bytes_acked;
+};
+
+/* Definitions for bpf_sock_ops_cb_flags */
+#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0)
+#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1)
+#define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently
+ * supported cb flags
+ */
+
+/* List of known BPF sock_ops operators.
+ * New entries can only be added at the end
+ */
+enum {
+ BPF_SOCK_OPS_VOID,
+ BPF_SOCK_OPS_TIMEOUT_INIT, /* Should return SYN-RTO value to use or
+ * -1 if default value should be used
+ */
+ BPF_SOCK_OPS_RWND_INIT, /* Should return initial advertized
+ * window (in packets) or -1 if default
+ * value should be used
+ */
+ BPF_SOCK_OPS_TCP_CONNECT_CB, /* Calls BPF program right before an
+ * active connection is initialized
+ */
+ BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, /* Calls BPF program when an
+ * active connection is
+ * established
+ */
+ BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, /* Calls BPF program when a
+ * passive connection is
+ * established
+ */
+ BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control
+ * needs ECN
+ */
+ BPF_SOCK_OPS_BASE_RTT, /* Get base RTT. The correct value is
+ * based on the path and may be
+ * dependent on the congestion control
+ * algorithm. In general it indicates
+ * a congestion threshold. RTTs above
+ * this indicate congestion
+ */
+ BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered.
+ * Arg1: value of icsk_retransmits
+ * Arg2: value of icsk_rto
+ * Arg3: whether RTO has expired
+ */
+ BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted.
+ * Arg1: sequence number of 1st byte
+ * Arg2: # segments
+ * Arg3: return value of
+ * tcp_transmit_skb (0 => success)
+ */
+ BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state.
+ * Arg1: old_state
+ * Arg2: new_state
+ */
+ BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after
+ * socket transition to LISTEN state.
+ */
+};
+
+/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
+ * changes between the TCP and BPF versions. Ideally this should never happen.
+ * If it does, we need to add code to convert them before calling
+ * the BPF sock_ops function.
+ */
+enum {
+ BPF_TCP_ESTABLISHED = 1,
+ BPF_TCP_SYN_SENT,
+ BPF_TCP_SYN_RECV,
+ BPF_TCP_FIN_WAIT1,
+ BPF_TCP_FIN_WAIT2,
+ BPF_TCP_TIME_WAIT,
+ BPF_TCP_CLOSE,
+ BPF_TCP_CLOSE_WAIT,
+ BPF_TCP_LAST_ACK,
+ BPF_TCP_LISTEN,
+ BPF_TCP_CLOSING, /* Now a valid state */
+ BPF_TCP_NEW_SYN_RECV,
+
+ BPF_TCP_MAX_STATES /* Leave at the end! */
+};
+
+#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */
+#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */
+
+struct bpf_perf_event_value {
+ __u64 counter;
+ __u64 enabled;
+ __u64 running;
+};
+
+#define BPF_DEVCG_ACC_MKNOD (1ULL << 0)
+#define BPF_DEVCG_ACC_READ (1ULL << 1)
+#define BPF_DEVCG_ACC_WRITE (1ULL << 2)
+
+#define BPF_DEVCG_DEV_BLOCK (1ULL << 0)
+#define BPF_DEVCG_DEV_CHAR (1ULL << 1)
+
+struct bpf_cgroup_dev_ctx {
+ /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */
+ __u32 access_type;
+ __u32 major;
+ __u32 minor;
+};
+
+struct bpf_raw_tracepoint_args {
+ __u64 args[0];
+};
+
+/* DIRECT: Skip the FIB rules and go to FIB table associated with device
+ * OUTPUT: Do lookup from egress perspective; default is ingress
+ */
+#define BPF_FIB_LOOKUP_DIRECT BIT(0)
+#define BPF_FIB_LOOKUP_OUTPUT BIT(1)
+
+enum {
+ BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */
+ BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */
+ BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */
+ BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */
+ BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */
+ BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
+ BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */
+ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */
+ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+};
+
+struct bpf_fib_lookup {
+ /* input: network family for lookup (AF_INET, AF_INET6)
+ * output: network family of egress nexthop
+ */
+ __u8 family;
+
+ /* set if lookup is to consider L4 data - e.g., FIB rules */
+ __u8 l4_protocol;
+ __be16 sport;
+ __be16 dport;
+
+ /* total length of packet from network header - used for MTU check */
+ __u16 tot_len;
+
+ /* input: L3 device index for lookup
+ * output: device index from FIB lookup
+ */
+ __u32 ifindex;
+
+ union {
+ /* inputs to lookup */
+ __u8 tos; /* AF_INET */
+ __be32 flowinfo; /* AF_INET6, flow_label + priority */
+
+ /* output: metric of fib result (IPv4/IPv6 only) */
+ __u32 rt_metric;
+ };
+
+ union {
+ __be32 ipv4_src;
+ __u32 ipv6_src[4]; /* in6_addr; network order */
+ };
+
+ /* input to bpf_fib_lookup, ipv{4,6}_dst is destination address in
+ * network header. output: bpf_fib_lookup sets to gateway address
+ * if FIB lookup returns gateway route
+ */
+ union {
+ __be32 ipv4_dst;
+ __u32 ipv6_dst[4]; /* in6_addr; network order */
+ };
+
+ /* output */
+ __be16 h_vlan_proto;
+ __be16 h_vlan_TCI;
+ __u8 smac[6]; /* ETH_ALEN */
+ __u8 dmac[6]; /* ETH_ALEN */
+};
+
+enum bpf_task_fd_type {
+ BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */
+ BPF_FD_TYPE_TRACEPOINT, /* tp name */
+ BPF_FD_TYPE_KPROBE, /* (symbol + offset) or addr */
+ BPF_FD_TYPE_KRETPROBE, /* (symbol + offset) or addr */
+ BPF_FD_TYPE_UPROBE, /* filename + offset */
+ BPF_FD_TYPE_URETPROBE, /* filename + offset */
+};
+
+#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/bpf_common.h b/tools/include/uapi/linux/bpf_common.h
new file mode 100644
index 0000000..ee97668
--- /dev/null
+++ b/tools/include/uapi/linux/bpf_common.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI__LINUX_BPF_COMMON_H__
+#define _UAPI__LINUX_BPF_COMMON_H__
+
+/* Instruction classes */
+#define BPF_CLASS(code) ((code) & 0x07)
+#define BPF_LD 0x00
+#define BPF_LDX 0x01
+#define BPF_ST 0x02
+#define BPF_STX 0x03
+#define BPF_ALU 0x04
+#define BPF_JMP 0x05
+#define BPF_RET 0x06
+#define BPF_MISC 0x07
+
+/* ld/ldx fields */
+#define BPF_SIZE(code) ((code) & 0x18)
+#define BPF_W 0x00 /* 32-bit */
+#define BPF_H 0x08 /* 16-bit */
+#define BPF_B 0x10 /* 8-bit */
+/* eBPF BPF_DW 0x18 64-bit */
+#define BPF_MODE(code) ((code) & 0xe0)
+#define BPF_IMM 0x00
+#define BPF_ABS 0x20
+#define BPF_IND 0x40
+#define BPF_MEM 0x60
+#define BPF_LEN 0x80
+#define BPF_MSH 0xa0
+
+/* alu/jmp fields */
+#define BPF_OP(code) ((code) & 0xf0)
+#define BPF_ADD 0x00
+#define BPF_SUB 0x10
+#define BPF_MUL 0x20
+#define BPF_DIV 0x30
+#define BPF_OR 0x40
+#define BPF_AND 0x50
+#define BPF_LSH 0x60
+#define BPF_RSH 0x70
+#define BPF_NEG 0x80
+#define BPF_MOD 0x90
+#define BPF_XOR 0xa0
+
+#define BPF_JA 0x00
+#define BPF_JEQ 0x10
+#define BPF_JGT 0x20
+#define BPF_JGE 0x30
+#define BPF_JSET 0x40
+#define BPF_SRC(code) ((code) & 0x08)
+#define BPF_K 0x00
+#define BPF_X 0x08
+
+#ifndef BPF_MAXINSNS
+#define BPF_MAXINSNS 4096
+#endif
+
+#endif /* _UAPI__LINUX_BPF_COMMON_H__ */
diff --git a/tools/include/uapi/linux/bpf_perf_event.h b/tools/include/uapi/linux/bpf_perf_event.h
new file mode 100644
index 0000000..8f95303
--- /dev/null
+++ b/tools/include/uapi/linux/bpf_perf_event.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__
+#define _UAPI__LINUX_BPF_PERF_EVENT_H__
+
+#include <asm/bpf_perf_event.h>
+
+struct bpf_perf_event_data {
+ bpf_user_pt_regs_t regs;
+ __u64 sample_period;
+};
+
+#endif /* _UAPI__LINUX_BPF_PERF_EVENT_H__ */
diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
new file mode 100644
index 0000000..972265f
--- /dev/null
+++ b/tools/include/uapi/linux/btf.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (c) 2018 Facebook */
+#ifndef _UAPI__LINUX_BTF_H__
+#define _UAPI__LINUX_BTF_H__
+
+#include <linux/types.h>
+
+#define BTF_MAGIC 0xeB9F
+#define BTF_VERSION 1
+
+struct btf_header {
+ __u16 magic;
+ __u8 version;
+ __u8 flags;
+ __u32 hdr_len;
+
+ /* All offsets are in bytes relative to the end of this header */
+ __u32 type_off; /* offset of type section */
+ __u32 type_len; /* length of type section */
+ __u32 str_off; /* offset of string section */
+ __u32 str_len; /* length of string section */
+};
+
+/* Max # of type identifier */
+#define BTF_MAX_TYPE 0x0000ffff
+/* Max offset into the string section */
+#define BTF_MAX_NAME_OFFSET 0x0000ffff
+/* Max # of struct/union/enum members or func args */
+#define BTF_MAX_VLEN 0xffff
+
+struct btf_type {
+ __u32 name_off;
+ /* "info" bits arrangement
+ * bits 0-15: vlen (e.g. # of struct's members)
+ * bits 16-23: unused
+ * bits 24-27: kind (e.g. int, ptr, array...etc)
+ * bits 28-31: unused
+ */
+ __u32 info;
+ /* "size" is used by INT, ENUM, STRUCT and UNION.
+ * "size" tells the size of the type it is describing.
+ *
+ * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT.
+ * "type" is a type_id referring to another type.
+ */
+ union {
+ __u32 size;
+ __u32 type;
+ };
+};
+
+#define BTF_INFO_KIND(info) (((info) >> 24) & 0x0f)
+#define BTF_INFO_VLEN(info) ((info) & 0xffff)
+
+#define BTF_KIND_UNKN 0 /* Unknown */
+#define BTF_KIND_INT 1 /* Integer */
+#define BTF_KIND_PTR 2 /* Pointer */
+#define BTF_KIND_ARRAY 3 /* Array */
+#define BTF_KIND_STRUCT 4 /* Struct */
+#define BTF_KIND_UNION 5 /* Union */
+#define BTF_KIND_ENUM 6 /* Enumeration */
+#define BTF_KIND_FWD 7 /* Forward */
+#define BTF_KIND_TYPEDEF 8 /* Typedef */
+#define BTF_KIND_VOLATILE 9 /* Volatile */
+#define BTF_KIND_CONST 10 /* Const */
+#define BTF_KIND_RESTRICT 11 /* Restrict */
+#define BTF_KIND_MAX 11
+#define NR_BTF_KINDS 12
+
+/* For some specific BTF_KIND, "struct btf_type" is immediately
+ * followed by extra data.
+ */
+
+/* BTF_KIND_INT is followed by a u32 and the following
+ * is the 32 bits arrangement:
+ */
+#define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24)
+#define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16)
+#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff)
+
+/* Attributes stored in the BTF_INT_ENCODING */
+#define BTF_INT_SIGNED (1 << 0)
+#define BTF_INT_CHAR (1 << 1)
+#define BTF_INT_BOOL (1 << 2)
+
+/* BTF_KIND_ENUM is followed by multiple "struct btf_enum".
+ * The exact number of btf_enum is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_enum {
+ __u32 name_off;
+ __s32 val;
+};
+
+/* BTF_KIND_ARRAY is followed by one "struct btf_array" */
+struct btf_array {
+ __u32 type;
+ __u32 index_type;
+ __u32 nelems;
+};
+
+/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed
+ * by multiple "struct btf_member". The exact number
+ * of btf_member is stored in the vlen (of the info in
+ * "struct btf_type").
+ */
+struct btf_member {
+ __u32 name_off;
+ __u32 type;
+ __u32 offset; /* offset in bits */
+};
+
+#endif /* _UAPI__LINUX_BTF_H__ */
diff --git a/tools/include/uapi/linux/erspan.h b/tools/include/uapi/linux/erspan.h
new file mode 100644
index 0000000..8415730
--- /dev/null
+++ b/tools/include/uapi/linux/erspan.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * ERSPAN Tunnel Metadata
+ *
+ * Copyright (c) 2018 VMware
+ *
+ * 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.
+ *
+ * Userspace API for metadata mode ERSPAN tunnel
+ */
+#ifndef _UAPI_ERSPAN_H
+#define _UAPI_ERSPAN_H
+
+#include <linux/types.h> /* For __beXX in userspace */
+#include <asm/byteorder.h>
+
+/* ERSPAN version 2 metadata header */
+struct erspan_md2 {
+ __be32 timestamp;
+ __be16 sgt; /* security group tag */
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u8 hwid_upper:2,
+ ft:5,
+ p:1;
+ __u8 o:1,
+ gra:2,
+ dir:1,
+ hwid:4;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ __u8 p:1,
+ ft:5,
+ hwid_upper:2;
+ __u8 hwid:4,
+ dir:1,
+ gra:2,
+ o:1;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+};
+
+struct erspan_metadata {
+ int version;
+ union {
+ __be32 index; /* Version 1 (type II)*/
+ struct erspan_md2 md2; /* Version 2 (type III) */
+ } u;
+};
+
+#endif /* _UAPI_ERSPAN_H */
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
new file mode 100644
index 0000000..6448cdd
--- /dev/null
+++ b/tools/include/uapi/linux/fcntl.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_FCNTL_H
+#define _UAPI_LINUX_FCNTL_H
+
+#include <asm/fcntl.h>
+
+#define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0)
+#define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1)
+
+/*
+ * Cancel a blocking posix lock; internal use only until we expose an
+ * asynchronous lock api to userspace:
+ */
+#define F_CANCELLK (F_LINUX_SPECIFIC_BASE + 5)
+
+/* Create a file descriptor with FD_CLOEXEC set. */
+#define F_DUPFD_CLOEXEC (F_LINUX_SPECIFIC_BASE + 6)
+
+/*
+ * Request nofications on a directory.
+ * See below for events that may be notified.
+ */
+#define F_NOTIFY (F_LINUX_SPECIFIC_BASE+2)
+
+/*
+ * Set and get of pipe page size array
+ */
+#define F_SETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 7)
+#define F_GETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 8)
+
+/*
+ * Set/Get seals
+ */
+#define F_ADD_SEALS (F_LINUX_SPECIFIC_BASE + 9)
+#define F_GET_SEALS (F_LINUX_SPECIFIC_BASE + 10)
+
+/*
+ * Types of seals
+ */
+#define F_SEAL_SEAL 0x0001 /* prevent further seals from being set */
+#define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */
+#define F_SEAL_GROW 0x0004 /* prevent file from growing */
+#define F_SEAL_WRITE 0x0008 /* prevent writes */
+/* (1U << 31) is reserved for signed error codes */
+
+/*
+ * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the
+ * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on
+ * the specific file.
+ */
+#define F_GET_RW_HINT (F_LINUX_SPECIFIC_BASE + 11)
+#define F_SET_RW_HINT (F_LINUX_SPECIFIC_BASE + 12)
+#define F_GET_FILE_RW_HINT (F_LINUX_SPECIFIC_BASE + 13)
+#define F_SET_FILE_RW_HINT (F_LINUX_SPECIFIC_BASE + 14)
+
+/*
+ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
+ * used to clear any hints previously set.
+ */
+#define RWF_WRITE_LIFE_NOT_SET 0
+#define RWH_WRITE_LIFE_NONE 1
+#define RWH_WRITE_LIFE_SHORT 2
+#define RWH_WRITE_LIFE_MEDIUM 3
+#define RWH_WRITE_LIFE_LONG 4
+#define RWH_WRITE_LIFE_EXTREME 5
+
+/*
+ * Types of directory notifications that may be requested.
+ */
+#define DN_ACCESS 0x00000001 /* File accessed */
+#define DN_MODIFY 0x00000002 /* File modified */
+#define DN_CREATE 0x00000004 /* File created */
+#define DN_DELETE 0x00000008 /* File removed */
+#define DN_RENAME 0x00000010 /* File renamed */
+#define DN_ATTRIB 0x00000020 /* File changed attibutes */
+#define DN_MULTISHOT 0x80000000 /* Don't remove notifier */
+
+#define AT_FDCWD -100 /* Special value used to indicate
+ openat should use the current
+ working directory. */
+#define AT_SYMLINK_NOFOLLOW 0x100 /* Do not follow symbolic links. */
+#define AT_REMOVEDIR 0x200 /* Remove directory instead of
+ unlinking file. */
+#define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */
+#define AT_NO_AUTOMOUNT 0x800 /* Suppress terminal automount traversal */
+#define AT_EMPTY_PATH 0x1000 /* Allow empty relative pathname */
+
+#define AT_STATX_SYNC_TYPE 0x6000 /* Type of synchronisation required from statx() */
+#define AT_STATX_SYNC_AS_STAT 0x0000 /* - Do whatever stat() does */
+#define AT_STATX_FORCE_SYNC 0x2000 /* - Force the attributes to be sync'd with the server */
+#define AT_STATX_DONT_SYNC 0x4000 /* - Don't sync attributes with the server */
+
+
+#endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h
new file mode 100644
index 0000000..965e4d8
--- /dev/null
+++ b/tools/include/uapi/linux/hw_breakpoint.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_HW_BREAKPOINT_H
+#define _UAPI_LINUX_HW_BREAKPOINT_H
+
+enum {
+ HW_BREAKPOINT_LEN_1 = 1,
+ HW_BREAKPOINT_LEN_2 = 2,
+ HW_BREAKPOINT_LEN_3 = 3,
+ HW_BREAKPOINT_LEN_4 = 4,
+ HW_BREAKPOINT_LEN_5 = 5,
+ HW_BREAKPOINT_LEN_6 = 6,
+ HW_BREAKPOINT_LEN_7 = 7,
+ HW_BREAKPOINT_LEN_8 = 8,
+};
+
+enum {
+ HW_BREAKPOINT_EMPTY = 0,
+ HW_BREAKPOINT_R = 1,
+ HW_BREAKPOINT_W = 2,
+ HW_BREAKPOINT_RW = HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+ HW_BREAKPOINT_X = 4,
+ HW_BREAKPOINT_INVALID = HW_BREAKPOINT_RW | HW_BREAKPOINT_X,
+};
+
+enum bp_type_idx {
+ TYPE_INST = 0,
+#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS
+ TYPE_DATA = 0,
+#else
+ TYPE_DATA = 1,
+#endif
+ TYPE_MAX
+};
+
+#endif /* _UAPI_LINUX_HW_BREAKPOINT_H */
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
new file mode 100644
index 0000000..43391e2
--- /dev/null
+++ b/tools/include/uapi/linux/if_link.h
@@ -0,0 +1,1002 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_IF_LINK_H
+#define _UAPI_LINUX_IF_LINK_H
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+/* This struct should be in sync with struct rtnl_link_stats64 */
+struct rtnl_link_stats {
+ __u32 rx_packets; /* total packets received */
+ __u32 tx_packets; /* total packets transmitted */
+ __u32 rx_bytes; /* total bytes received */
+ __u32 tx_bytes; /* total bytes transmitted */
+ __u32 rx_errors; /* bad packets received */
+ __u32 tx_errors; /* packet transmit problems */
+ __u32 rx_dropped; /* no space in linux buffers */
+ __u32 tx_dropped; /* no space available in linux */
+ __u32 multicast; /* multicast packets received */
+ __u32 collisions;
+
+ /* detailed rx_errors: */
+ __u32 rx_length_errors;
+ __u32 rx_over_errors; /* receiver ring buff overflow */
+ __u32 rx_crc_errors; /* recved pkt with crc error */
+ __u32 rx_frame_errors; /* recv'd frame alignment error */
+ __u32 rx_fifo_errors; /* recv'r fifo overrun */
+ __u32 rx_missed_errors; /* receiver missed packet */
+
+ /* detailed tx_errors */
+ __u32 tx_aborted_errors;
+ __u32 tx_carrier_errors;
+ __u32 tx_fifo_errors;
+ __u32 tx_heartbeat_errors;
+ __u32 tx_window_errors;
+
+ /* for cslip etc */
+ __u32 rx_compressed;
+ __u32 tx_compressed;
+
+ __u32 rx_nohandler; /* dropped, no handler found */
+};
+
+/* The main device statistics structure */
+struct rtnl_link_stats64 {
+ __u64 rx_packets; /* total packets received */
+ __u64 tx_packets; /* total packets transmitted */
+ __u64 rx_bytes; /* total bytes received */
+ __u64 tx_bytes; /* total bytes transmitted */
+ __u64 rx_errors; /* bad packets received */
+ __u64 tx_errors; /* packet transmit problems */
+ __u64 rx_dropped; /* no space in linux buffers */
+ __u64 tx_dropped; /* no space available in linux */
+ __u64 multicast; /* multicast packets received */
+ __u64 collisions;
+
+ /* detailed rx_errors: */
+ __u64 rx_length_errors;
+ __u64 rx_over_errors; /* receiver ring buff overflow */
+ __u64 rx_crc_errors; /* recved pkt with crc error */
+ __u64 rx_frame_errors; /* recv'd frame alignment error */
+ __u64 rx_fifo_errors; /* recv'r fifo overrun */
+ __u64 rx_missed_errors; /* receiver missed packet */
+
+ /* detailed tx_errors */
+ __u64 tx_aborted_errors;
+ __u64 tx_carrier_errors;
+ __u64 tx_fifo_errors;
+ __u64 tx_heartbeat_errors;
+ __u64 tx_window_errors;
+
+ /* for cslip etc */
+ __u64 rx_compressed;
+ __u64 tx_compressed;
+
+ __u64 rx_nohandler; /* dropped, no handler found */
+};
+
+/* The struct should be in sync with struct ifmap */
+struct rtnl_link_ifmap {
+ __u64 mem_start;
+ __u64 mem_end;
+ __u64 base_addr;
+ __u16 irq;
+ __u8 dma;
+ __u8 port;
+};
+
+/*
+ * IFLA_AF_SPEC
+ * Contains nested attributes for address family specific attributes.
+ * Each address family may create a attribute with the address family
+ * number as type and create its own attribute structure in it.
+ *
+ * Example:
+ * [IFLA_AF_SPEC] = {
+ * [AF_INET] = {
+ * [IFLA_INET_CONF] = ...,
+ * },
+ * [AF_INET6] = {
+ * [IFLA_INET6_FLAGS] = ...,
+ * [IFLA_INET6_CONF] = ...,
+ * }
+ * }
+ */
+
+enum {
+ IFLA_UNSPEC,
+ IFLA_ADDRESS,
+ IFLA_BROADCAST,
+ IFLA_IFNAME,
+ IFLA_MTU,
+ IFLA_LINK,
+ IFLA_QDISC,
+ IFLA_STATS,
+ IFLA_COST,
+#define IFLA_COST IFLA_COST
+ IFLA_PRIORITY,
+#define IFLA_PRIORITY IFLA_PRIORITY
+ IFLA_MASTER,
+#define IFLA_MASTER IFLA_MASTER
+ IFLA_WIRELESS, /* Wireless Extension event - see wireless.h */
+#define IFLA_WIRELESS IFLA_WIRELESS
+ IFLA_PROTINFO, /* Protocol specific information for a link */
+#define IFLA_PROTINFO IFLA_PROTINFO
+ IFLA_TXQLEN,
+#define IFLA_TXQLEN IFLA_TXQLEN
+ IFLA_MAP,
+#define IFLA_MAP IFLA_MAP
+ IFLA_WEIGHT,
+#define IFLA_WEIGHT IFLA_WEIGHT
+ IFLA_OPERSTATE,
+ IFLA_LINKMODE,
+ IFLA_LINKINFO,
+#define IFLA_LINKINFO IFLA_LINKINFO
+ IFLA_NET_NS_PID,
+ IFLA_IFALIAS,
+ IFLA_NUM_VF, /* Number of VFs if device is SR-IOV PF */
+ IFLA_VFINFO_LIST,
+ IFLA_STATS64,
+ IFLA_VF_PORTS,
+ IFLA_PORT_SELF,
+ IFLA_AF_SPEC,
+ IFLA_GROUP, /* Group the device belongs to */
+ IFLA_NET_NS_FD,
+ IFLA_EXT_MASK, /* Extended info mask, VFs, etc */
+ IFLA_PROMISCUITY, /* Promiscuity count: > 0 means acts PROMISC */
+#define IFLA_PROMISCUITY IFLA_PROMISCUITY
+ IFLA_NUM_TX_QUEUES,
+ IFLA_NUM_RX_QUEUES,
+ IFLA_CARRIER,
+ IFLA_PHYS_PORT_ID,
+ IFLA_CARRIER_CHANGES,
+ IFLA_PHYS_SWITCH_ID,
+ IFLA_LINK_NETNSID,
+ IFLA_PHYS_PORT_NAME,
+ IFLA_PROTO_DOWN,
+ IFLA_GSO_MAX_SEGS,
+ IFLA_GSO_MAX_SIZE,
+ IFLA_PAD,
+ IFLA_XDP,
+ IFLA_EVENT,
+ IFLA_NEW_NETNSID,
+ IFLA_IF_NETNSID,
+ IFLA_CARRIER_UP_COUNT,
+ IFLA_CARRIER_DOWN_COUNT,
+ IFLA_NEW_IFINDEX,
+ IFLA_MIN_MTU,
+ IFLA_MAX_MTU,
+ __IFLA_MAX
+};
+
+
+#define IFLA_MAX (__IFLA_MAX - 1)
+
+/* backwards compatibility for userspace */
+#ifndef __KERNEL__
+#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
+#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg))
+#endif
+
+enum {
+ IFLA_INET_UNSPEC,
+ IFLA_INET_CONF,
+ __IFLA_INET_MAX,
+};
+
+#define IFLA_INET_MAX (__IFLA_INET_MAX - 1)
+
+/* ifi_flags.
+
+ IFF_* flags.
+
+ The only change is:
+ IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are
+ more not changeable by user. They describe link media
+ characteristics and set by device driver.
+
+ Comments:
+ - Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid
+ - If neither of these three flags are set;
+ the interface is NBMA.
+
+ - IFF_MULTICAST does not mean anything special:
+ multicasts can be used on all not-NBMA links.
+ IFF_MULTICAST means that this media uses special encapsulation
+ for multicast frames. Apparently, all IFF_POINTOPOINT and
+ IFF_BROADCAST devices are able to use multicasts too.
+ */
+
+/* IFLA_LINK.
+ For usual devices it is equal ifi_index.
+ If it is a "virtual interface" (f.e. tunnel), ifi_link
+ can point to real physical interface (f.e. for bandwidth calculations),
+ or maybe 0, what means, that real media is unknown (usual
+ for IPIP tunnels, when route to endpoint is allowed to change)
+ */
+
+/* Subtype attributes for IFLA_PROTINFO */
+enum {
+ IFLA_INET6_UNSPEC,
+ IFLA_INET6_FLAGS, /* link flags */
+ IFLA_INET6_CONF, /* sysctl parameters */
+ IFLA_INET6_STATS, /* statistics */
+ IFLA_INET6_MCAST, /* MC things. What of them? */
+ IFLA_INET6_CACHEINFO, /* time values and max reasm size */
+ IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */
+ IFLA_INET6_TOKEN, /* device token */
+ IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */
+ __IFLA_INET6_MAX
+};
+
+#define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1)
+
+enum in6_addr_gen_mode {
+ IN6_ADDR_GEN_MODE_EUI64,
+ IN6_ADDR_GEN_MODE_NONE,
+ IN6_ADDR_GEN_MODE_STABLE_PRIVACY,
+ IN6_ADDR_GEN_MODE_RANDOM,
+};
+
+/* Bridge section */
+
+enum {
+ IFLA_BR_UNSPEC,
+ IFLA_BR_FORWARD_DELAY,
+ IFLA_BR_HELLO_TIME,
+ IFLA_BR_MAX_AGE,
+ IFLA_BR_AGEING_TIME,
+ IFLA_BR_STP_STATE,
+ IFLA_BR_PRIORITY,
+ IFLA_BR_VLAN_FILTERING,
+ IFLA_BR_VLAN_PROTOCOL,
+ IFLA_BR_GROUP_FWD_MASK,
+ IFLA_BR_ROOT_ID,
+ IFLA_BR_BRIDGE_ID,
+ IFLA_BR_ROOT_PORT,
+ IFLA_BR_ROOT_PATH_COST,
+ IFLA_BR_TOPOLOGY_CHANGE,
+ IFLA_BR_TOPOLOGY_CHANGE_DETECTED,
+ IFLA_BR_HELLO_TIMER,
+ IFLA_BR_TCN_TIMER,
+ IFLA_BR_TOPOLOGY_CHANGE_TIMER,
+ IFLA_BR_GC_TIMER,
+ IFLA_BR_GROUP_ADDR,
+ IFLA_BR_FDB_FLUSH,
+ IFLA_BR_MCAST_ROUTER,
+ IFLA_BR_MCAST_SNOOPING,
+ IFLA_BR_MCAST_QUERY_USE_IFADDR,
+ IFLA_BR_MCAST_QUERIER,
+ IFLA_BR_MCAST_HASH_ELASTICITY,
+ IFLA_BR_MCAST_HASH_MAX,
+ IFLA_BR_MCAST_LAST_MEMBER_CNT,
+ IFLA_BR_MCAST_STARTUP_QUERY_CNT,
+ IFLA_BR_MCAST_LAST_MEMBER_INTVL,
+ IFLA_BR_MCAST_MEMBERSHIP_INTVL,
+ IFLA_BR_MCAST_QUERIER_INTVL,
+ IFLA_BR_MCAST_QUERY_INTVL,
+ IFLA_BR_MCAST_QUERY_RESPONSE_INTVL,
+ IFLA_BR_MCAST_STARTUP_QUERY_INTVL,
+ IFLA_BR_NF_CALL_IPTABLES,
+ IFLA_BR_NF_CALL_IP6TABLES,
+ IFLA_BR_NF_CALL_ARPTABLES,
+ IFLA_BR_VLAN_DEFAULT_PVID,
+ IFLA_BR_PAD,
+ IFLA_BR_VLAN_STATS_ENABLED,
+ IFLA_BR_MCAST_STATS_ENABLED,
+ IFLA_BR_MCAST_IGMP_VERSION,
+ IFLA_BR_MCAST_MLD_VERSION,
+ __IFLA_BR_MAX,
+};
+
+#define IFLA_BR_MAX (__IFLA_BR_MAX - 1)
+
+struct ifla_bridge_id {
+ __u8 prio[2];
+ __u8 addr[6]; /* ETH_ALEN */
+};
+
+enum {
+ BRIDGE_MODE_UNSPEC,
+ BRIDGE_MODE_HAIRPIN,
+};
+
+enum {
+ IFLA_BRPORT_UNSPEC,
+ IFLA_BRPORT_STATE, /* Spanning tree state */
+ IFLA_BRPORT_PRIORITY, /* " priority */
+ IFLA_BRPORT_COST, /* " cost */
+ IFLA_BRPORT_MODE, /* mode (hairpin) */
+ IFLA_BRPORT_GUARD, /* bpdu guard */
+ IFLA_BRPORT_PROTECT, /* root port protection */
+ IFLA_BRPORT_FAST_LEAVE, /* multicast fast leave */
+ IFLA_BRPORT_LEARNING, /* mac learning */
+ IFLA_BRPORT_UNICAST_FLOOD, /* flood unicast traffic */
+ IFLA_BRPORT_PROXYARP, /* proxy ARP */
+ IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */
+ IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */
+ IFLA_BRPORT_ROOT_ID, /* designated root */
+ IFLA_BRPORT_BRIDGE_ID, /* designated bridge */
+ IFLA_BRPORT_DESIGNATED_PORT,
+ IFLA_BRPORT_DESIGNATED_COST,
+ IFLA_BRPORT_ID,
+ IFLA_BRPORT_NO,
+ IFLA_BRPORT_TOPOLOGY_CHANGE_ACK,
+ IFLA_BRPORT_CONFIG_PENDING,
+ IFLA_BRPORT_MESSAGE_AGE_TIMER,
+ IFLA_BRPORT_FORWARD_DELAY_TIMER,
+ IFLA_BRPORT_HOLD_TIMER,
+ IFLA_BRPORT_FLUSH,
+ IFLA_BRPORT_MULTICAST_ROUTER,
+ IFLA_BRPORT_PAD,
+ IFLA_BRPORT_MCAST_FLOOD,
+ IFLA_BRPORT_MCAST_TO_UCAST,
+ IFLA_BRPORT_VLAN_TUNNEL,
+ IFLA_BRPORT_BCAST_FLOOD,
+ IFLA_BRPORT_GROUP_FWD_MASK,
+ IFLA_BRPORT_NEIGH_SUPPRESS,
+ IFLA_BRPORT_ISOLATED,
+ IFLA_BRPORT_BACKUP_PORT,
+ __IFLA_BRPORT_MAX
+};
+#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
+
+struct ifla_cacheinfo {
+ __u32 max_reasm_len;
+ __u32 tstamp; /* ipv6InterfaceTable updated timestamp */
+ __u32 reachable_time;
+ __u32 retrans_time;
+};
+
+enum {
+ IFLA_INFO_UNSPEC,
+ IFLA_INFO_KIND,
+ IFLA_INFO_DATA,
+ IFLA_INFO_XSTATS,
+ IFLA_INFO_SLAVE_KIND,
+ IFLA_INFO_SLAVE_DATA,
+ __IFLA_INFO_MAX,
+};
+
+#define IFLA_INFO_MAX (__IFLA_INFO_MAX - 1)
+
+/* VLAN section */
+
+enum {
+ IFLA_VLAN_UNSPEC,
+ IFLA_VLAN_ID,
+ IFLA_VLAN_FLAGS,
+ IFLA_VLAN_EGRESS_QOS,
+ IFLA_VLAN_INGRESS_QOS,
+ IFLA_VLAN_PROTOCOL,
+ __IFLA_VLAN_MAX,
+};
+
+#define IFLA_VLAN_MAX (__IFLA_VLAN_MAX - 1)
+
+struct ifla_vlan_flags {
+ __u32 flags;
+ __u32 mask;
+};
+
+enum {
+ IFLA_VLAN_QOS_UNSPEC,
+ IFLA_VLAN_QOS_MAPPING,
+ __IFLA_VLAN_QOS_MAX
+};
+
+#define IFLA_VLAN_QOS_MAX (__IFLA_VLAN_QOS_MAX - 1)
+
+struct ifla_vlan_qos_mapping {
+ __u32 from;
+ __u32 to;
+};
+
+/* MACVLAN section */
+enum {
+ IFLA_MACVLAN_UNSPEC,
+ IFLA_MACVLAN_MODE,
+ IFLA_MACVLAN_FLAGS,
+ IFLA_MACVLAN_MACADDR_MODE,
+ IFLA_MACVLAN_MACADDR,
+ IFLA_MACVLAN_MACADDR_DATA,
+ IFLA_MACVLAN_MACADDR_COUNT,
+ __IFLA_MACVLAN_MAX,
+};
+
+#define IFLA_MACVLAN_MAX (__IFLA_MACVLAN_MAX - 1)
+
+enum macvlan_mode {
+ MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */
+ MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */
+ MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */
+ MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */
+ MACVLAN_MODE_SOURCE = 16,/* use source MAC address list to assign */
+};
+
+enum macvlan_macaddr_mode {
+ MACVLAN_MACADDR_ADD,
+ MACVLAN_MACADDR_DEL,
+ MACVLAN_MACADDR_FLUSH,
+ MACVLAN_MACADDR_SET,
+};
+
+#define MACVLAN_FLAG_NOPROMISC 1
+
+/* VRF section */
+enum {
+ IFLA_VRF_UNSPEC,
+ IFLA_VRF_TABLE,
+ __IFLA_VRF_MAX
+};
+
+#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1)
+
+enum {
+ IFLA_VRF_PORT_UNSPEC,
+ IFLA_VRF_PORT_TABLE,
+ __IFLA_VRF_PORT_MAX
+};
+
+#define IFLA_VRF_PORT_MAX (__IFLA_VRF_PORT_MAX - 1)
+
+/* MACSEC section */
+enum {
+ IFLA_MACSEC_UNSPEC,
+ IFLA_MACSEC_SCI,
+ IFLA_MACSEC_PORT,
+ IFLA_MACSEC_ICV_LEN,
+ IFLA_MACSEC_CIPHER_SUITE,
+ IFLA_MACSEC_WINDOW,
+ IFLA_MACSEC_ENCODING_SA,
+ IFLA_MACSEC_ENCRYPT,
+ IFLA_MACSEC_PROTECT,
+ IFLA_MACSEC_INC_SCI,
+ IFLA_MACSEC_ES,
+ IFLA_MACSEC_SCB,
+ IFLA_MACSEC_REPLAY_PROTECT,
+ IFLA_MACSEC_VALIDATION,
+ IFLA_MACSEC_PAD,
+ __IFLA_MACSEC_MAX,
+};
+
+#define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1)
+
+/* XFRM section */
+enum {
+ IFLA_XFRM_UNSPEC,
+ IFLA_XFRM_LINK,
+ IFLA_XFRM_IF_ID,
+ __IFLA_XFRM_MAX
+};
+
+#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1)
+
+enum macsec_validation_type {
+ MACSEC_VALIDATE_DISABLED = 0,
+ MACSEC_VALIDATE_CHECK = 1,
+ MACSEC_VALIDATE_STRICT = 2,
+ __MACSEC_VALIDATE_END,
+ MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1,
+};
+
+/* IPVLAN section */
+enum {
+ IFLA_IPVLAN_UNSPEC,
+ IFLA_IPVLAN_MODE,
+ IFLA_IPVLAN_FLAGS,
+ __IFLA_IPVLAN_MAX
+};
+
+#define IFLA_IPVLAN_MAX (__IFLA_IPVLAN_MAX - 1)
+
+enum ipvlan_mode {
+ IPVLAN_MODE_L2 = 0,
+ IPVLAN_MODE_L3,
+ IPVLAN_MODE_L3S,
+ IPVLAN_MODE_MAX
+};
+
+#define IPVLAN_F_PRIVATE 0x01
+#define IPVLAN_F_VEPA 0x02
+
+/* VXLAN section */
+enum {
+ IFLA_VXLAN_UNSPEC,
+ IFLA_VXLAN_ID,
+ IFLA_VXLAN_GROUP, /* group or remote address */
+ IFLA_VXLAN_LINK,
+ IFLA_VXLAN_LOCAL,
+ IFLA_VXLAN_TTL,
+ IFLA_VXLAN_TOS,
+ IFLA_VXLAN_LEARNING,
+ IFLA_VXLAN_AGEING,
+ IFLA_VXLAN_LIMIT,
+ IFLA_VXLAN_PORT_RANGE, /* source port */
+ IFLA_VXLAN_PROXY,
+ IFLA_VXLAN_RSC,
+ IFLA_VXLAN_L2MISS,
+ IFLA_VXLAN_L3MISS,
+ IFLA_VXLAN_PORT, /* destination port */
+ IFLA_VXLAN_GROUP6,
+ IFLA_VXLAN_LOCAL6,
+ IFLA_VXLAN_UDP_CSUM,
+ IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
+ IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
+ IFLA_VXLAN_REMCSUM_TX,
+ IFLA_VXLAN_REMCSUM_RX,
+ IFLA_VXLAN_GBP,
+ IFLA_VXLAN_REMCSUM_NOPARTIAL,
+ IFLA_VXLAN_COLLECT_METADATA,
+ IFLA_VXLAN_LABEL,
+ IFLA_VXLAN_GPE,
+ IFLA_VXLAN_TTL_INHERIT,
+ __IFLA_VXLAN_MAX
+};
+#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
+
+struct ifla_vxlan_port_range {
+ __be16 low;
+ __be16 high;
+};
+
+/* GENEVE section */
+enum {
+ IFLA_GENEVE_UNSPEC,
+ IFLA_GENEVE_ID,
+ IFLA_GENEVE_REMOTE,
+ IFLA_GENEVE_TTL,
+ IFLA_GENEVE_TOS,
+ IFLA_GENEVE_PORT, /* destination port */
+ IFLA_GENEVE_COLLECT_METADATA,
+ IFLA_GENEVE_REMOTE6,
+ IFLA_GENEVE_UDP_CSUM,
+ IFLA_GENEVE_UDP_ZERO_CSUM6_TX,
+ IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
+ IFLA_GENEVE_LABEL,
+ __IFLA_GENEVE_MAX
+};
+#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1)
+
+/* PPP section */
+enum {
+ IFLA_PPP_UNSPEC,
+ IFLA_PPP_DEV_FD,
+ __IFLA_PPP_MAX
+};
+#define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1)
+
+/* GTP section */
+
+enum ifla_gtp_role {
+ GTP_ROLE_GGSN = 0,
+ GTP_ROLE_SGSN,
+};
+
+enum {
+ IFLA_GTP_UNSPEC,
+ IFLA_GTP_FD0,
+ IFLA_GTP_FD1,
+ IFLA_GTP_PDP_HASHSIZE,
+ IFLA_GTP_ROLE,
+ __IFLA_GTP_MAX,
+};
+#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
+
+/* Bonding section */
+
+enum {
+ IFLA_BOND_UNSPEC,
+ IFLA_BOND_MODE,
+ IFLA_BOND_ACTIVE_SLAVE,
+ IFLA_BOND_MIIMON,
+ IFLA_BOND_UPDELAY,
+ IFLA_BOND_DOWNDELAY,
+ IFLA_BOND_USE_CARRIER,
+ IFLA_BOND_ARP_INTERVAL,
+ IFLA_BOND_ARP_IP_TARGET,
+ IFLA_BOND_ARP_VALIDATE,
+ IFLA_BOND_ARP_ALL_TARGETS,
+ IFLA_BOND_PRIMARY,
+ IFLA_BOND_PRIMARY_RESELECT,
+ IFLA_BOND_FAIL_OVER_MAC,
+ IFLA_BOND_XMIT_HASH_POLICY,
+ IFLA_BOND_RESEND_IGMP,
+ IFLA_BOND_NUM_PEER_NOTIF,
+ IFLA_BOND_ALL_SLAVES_ACTIVE,
+ IFLA_BOND_MIN_LINKS,
+ IFLA_BOND_LP_INTERVAL,
+ IFLA_BOND_PACKETS_PER_SLAVE,
+ IFLA_BOND_AD_LACP_RATE,
+ IFLA_BOND_AD_SELECT,
+ IFLA_BOND_AD_INFO,
+ IFLA_BOND_AD_ACTOR_SYS_PRIO,
+ IFLA_BOND_AD_USER_PORT_KEY,
+ IFLA_BOND_AD_ACTOR_SYSTEM,
+ IFLA_BOND_TLB_DYNAMIC_LB,
+ __IFLA_BOND_MAX,
+};
+
+#define IFLA_BOND_MAX (__IFLA_BOND_MAX - 1)
+
+enum {
+ IFLA_BOND_AD_INFO_UNSPEC,
+ IFLA_BOND_AD_INFO_AGGREGATOR,
+ IFLA_BOND_AD_INFO_NUM_PORTS,
+ IFLA_BOND_AD_INFO_ACTOR_KEY,
+ IFLA_BOND_AD_INFO_PARTNER_KEY,
+ IFLA_BOND_AD_INFO_PARTNER_MAC,
+ __IFLA_BOND_AD_INFO_MAX,
+};
+
+#define IFLA_BOND_AD_INFO_MAX (__IFLA_BOND_AD_INFO_MAX - 1)
+
+enum {
+ IFLA_BOND_SLAVE_UNSPEC,
+ IFLA_BOND_SLAVE_STATE,
+ IFLA_BOND_SLAVE_MII_STATUS,
+ IFLA_BOND_SLAVE_LINK_FAILURE_COUNT,
+ IFLA_BOND_SLAVE_PERM_HWADDR,
+ IFLA_BOND_SLAVE_QUEUE_ID,
+ IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
+ IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE,
+ IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE,
+ __IFLA_BOND_SLAVE_MAX,
+};
+
+#define IFLA_BOND_SLAVE_MAX (__IFLA_BOND_SLAVE_MAX - 1)
+
+/* SR-IOV virtual function management section */
+
+enum {
+ IFLA_VF_INFO_UNSPEC,
+ IFLA_VF_INFO,
+ __IFLA_VF_INFO_MAX,
+};
+
+#define IFLA_VF_INFO_MAX (__IFLA_VF_INFO_MAX - 1)
+
+enum {
+ IFLA_VF_UNSPEC,
+ IFLA_VF_MAC, /* Hardware queue specific attributes */
+ IFLA_VF_VLAN, /* VLAN ID and QoS */
+ IFLA_VF_TX_RATE, /* Max TX Bandwidth Allocation */
+ IFLA_VF_SPOOFCHK, /* Spoof Checking on/off switch */
+ IFLA_VF_LINK_STATE, /* link state enable/disable/auto switch */
+ IFLA_VF_RATE, /* Min and Max TX Bandwidth Allocation */
+ IFLA_VF_RSS_QUERY_EN, /* RSS Redirection Table and Hash Key query
+ * on/off switch
+ */
+ IFLA_VF_STATS, /* network device statistics */
+ IFLA_VF_TRUST, /* Trust VF */
+ IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */
+ IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */
+ IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */
+ __IFLA_VF_MAX,
+};
+
+#define IFLA_VF_MAX (__IFLA_VF_MAX - 1)
+
+struct ifla_vf_mac {
+ __u32 vf;
+ __u8 mac[32]; /* MAX_ADDR_LEN */
+};
+
+struct ifla_vf_vlan {
+ __u32 vf;
+ __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */
+ __u32 qos;
+};
+
+enum {
+ IFLA_VF_VLAN_INFO_UNSPEC,
+ IFLA_VF_VLAN_INFO, /* VLAN ID, QoS and VLAN protocol */
+ __IFLA_VF_VLAN_INFO_MAX,
+};
+
+#define IFLA_VF_VLAN_INFO_MAX (__IFLA_VF_VLAN_INFO_MAX - 1)
+#define MAX_VLAN_LIST_LEN 1
+
+struct ifla_vf_vlan_info {
+ __u32 vf;
+ __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */
+ __u32 qos;
+ __be16 vlan_proto; /* VLAN protocol either 802.1Q or 802.1ad */
+};
+
+struct ifla_vf_tx_rate {
+ __u32 vf;
+ __u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */
+};
+
+struct ifla_vf_rate {
+ __u32 vf;
+ __u32 min_tx_rate; /* Min Bandwidth in Mbps */
+ __u32 max_tx_rate; /* Max Bandwidth in Mbps */
+};
+
+struct ifla_vf_spoofchk {
+ __u32 vf;
+ __u32 setting;
+};
+
+struct ifla_vf_guid {
+ __u32 vf;
+ __u64 guid;
+};
+
+enum {
+ IFLA_VF_LINK_STATE_AUTO, /* link state of the uplink */
+ IFLA_VF_LINK_STATE_ENABLE, /* link always up */
+ IFLA_VF_LINK_STATE_DISABLE, /* link always down */
+ __IFLA_VF_LINK_STATE_MAX,
+};
+
+struct ifla_vf_link_state {
+ __u32 vf;
+ __u32 link_state;
+};
+
+struct ifla_vf_rss_query_en {
+ __u32 vf;
+ __u32 setting;
+};
+
+enum {
+ IFLA_VF_STATS_RX_PACKETS,
+ IFLA_VF_STATS_TX_PACKETS,
+ IFLA_VF_STATS_RX_BYTES,
+ IFLA_VF_STATS_TX_BYTES,
+ IFLA_VF_STATS_BROADCAST,
+ IFLA_VF_STATS_MULTICAST,
+ IFLA_VF_STATS_PAD,
+ IFLA_VF_STATS_RX_DROPPED,
+ IFLA_VF_STATS_TX_DROPPED,
+ __IFLA_VF_STATS_MAX,
+};
+
+#define IFLA_VF_STATS_MAX (__IFLA_VF_STATS_MAX - 1)
+
+struct ifla_vf_trust {
+ __u32 vf;
+ __u32 setting;
+};
+
+/* VF ports management section
+ *
+ * Nested layout of set/get msg is:
+ *
+ * [IFLA_NUM_VF]
+ * [IFLA_VF_PORTS]
+ * [IFLA_VF_PORT]
+ * [IFLA_PORT_*], ...
+ * [IFLA_VF_PORT]
+ * [IFLA_PORT_*], ...
+ * ...
+ * [IFLA_PORT_SELF]
+ * [IFLA_PORT_*], ...
+ */
+
+enum {
+ IFLA_VF_PORT_UNSPEC,
+ IFLA_VF_PORT, /* nest */
+ __IFLA_VF_PORT_MAX,
+};
+
+#define IFLA_VF_PORT_MAX (__IFLA_VF_PORT_MAX - 1)
+
+enum {
+ IFLA_PORT_UNSPEC,
+ IFLA_PORT_VF, /* __u32 */
+ IFLA_PORT_PROFILE, /* string */
+ IFLA_PORT_VSI_TYPE, /* 802.1Qbg (pre-)standard VDP */
+ IFLA_PORT_INSTANCE_UUID, /* binary UUID */
+ IFLA_PORT_HOST_UUID, /* binary UUID */
+ IFLA_PORT_REQUEST, /* __u8 */
+ IFLA_PORT_RESPONSE, /* __u16, output only */
+ __IFLA_PORT_MAX,
+};
+
+#define IFLA_PORT_MAX (__IFLA_PORT_MAX - 1)
+
+#define PORT_PROFILE_MAX 40
+#define PORT_UUID_MAX 16
+#define PORT_SELF_VF -1
+
+enum {
+ PORT_REQUEST_PREASSOCIATE = 0,
+ PORT_REQUEST_PREASSOCIATE_RR,
+ PORT_REQUEST_ASSOCIATE,
+ PORT_REQUEST_DISASSOCIATE,
+};
+
+enum {
+ PORT_VDP_RESPONSE_SUCCESS = 0,
+ PORT_VDP_RESPONSE_INVALID_FORMAT,
+ PORT_VDP_RESPONSE_INSUFFICIENT_RESOURCES,
+ PORT_VDP_RESPONSE_UNUSED_VTID,
+ PORT_VDP_RESPONSE_VTID_VIOLATION,
+ PORT_VDP_RESPONSE_VTID_VERSION_VIOALTION,
+ PORT_VDP_RESPONSE_OUT_OF_SYNC,
+ /* 0x08-0xFF reserved for future VDP use */
+ PORT_PROFILE_RESPONSE_SUCCESS = 0x100,
+ PORT_PROFILE_RESPONSE_INPROGRESS,
+ PORT_PROFILE_RESPONSE_INVALID,
+ PORT_PROFILE_RESPONSE_BADSTATE,
+ PORT_PROFILE_RESPONSE_INSUFFICIENT_RESOURCES,
+ PORT_PROFILE_RESPONSE_ERROR,
+};
+
+struct ifla_port_vsi {
+ __u8 vsi_mgr_id;
+ __u8 vsi_type_id[3];
+ __u8 vsi_type_version;
+ __u8 pad[3];
+};
+
+
+/* IPoIB section */
+
+enum {
+ IFLA_IPOIB_UNSPEC,
+ IFLA_IPOIB_PKEY,
+ IFLA_IPOIB_MODE,
+ IFLA_IPOIB_UMCAST,
+ __IFLA_IPOIB_MAX
+};
+
+enum {
+ IPOIB_MODE_DATAGRAM = 0, /* using unreliable datagram QPs */
+ IPOIB_MODE_CONNECTED = 1, /* using connected QPs */
+};
+
+#define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1)
+
+
+/* HSR section */
+
+enum {
+ IFLA_HSR_UNSPEC,
+ IFLA_HSR_SLAVE1,
+ IFLA_HSR_SLAVE2,
+ IFLA_HSR_MULTICAST_SPEC, /* Last byte of supervision addr */
+ IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */
+ IFLA_HSR_SEQ_NR,
+ IFLA_HSR_VERSION, /* HSR version */
+ __IFLA_HSR_MAX,
+};
+
+#define IFLA_HSR_MAX (__IFLA_HSR_MAX - 1)
+
+/* STATS section */
+
+struct if_stats_msg {
+ __u8 family;
+ __u8 pad1;
+ __u16 pad2;
+ __u32 ifindex;
+ __u32 filter_mask;
+};
+
+/* A stats attribute can be netdev specific or a global stat.
+ * For netdev stats, lets use the prefix IFLA_STATS_LINK_*
+ */
+enum {
+ IFLA_STATS_UNSPEC, /* also used as 64bit pad attribute */
+ IFLA_STATS_LINK_64,
+ IFLA_STATS_LINK_XSTATS,
+ IFLA_STATS_LINK_XSTATS_SLAVE,
+ IFLA_STATS_LINK_OFFLOAD_XSTATS,
+ IFLA_STATS_AF_SPEC,
+ __IFLA_STATS_MAX,
+};
+
+#define IFLA_STATS_MAX (__IFLA_STATS_MAX - 1)
+
+#define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1))
+
+/* These are embedded into IFLA_STATS_LINK_XSTATS:
+ * [IFLA_STATS_LINK_XSTATS]
+ * -> [LINK_XSTATS_TYPE_xxx]
+ * -> [rtnl link type specific attributes]
+ */
+enum {
+ LINK_XSTATS_TYPE_UNSPEC,
+ LINK_XSTATS_TYPE_BRIDGE,
+ __LINK_XSTATS_TYPE_MAX
+};
+#define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1)
+
+/* These are stats embedded into IFLA_STATS_LINK_OFFLOAD_XSTATS */
+enum {
+ IFLA_OFFLOAD_XSTATS_UNSPEC,
+ IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */
+ __IFLA_OFFLOAD_XSTATS_MAX
+};
+#define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1)
+
+/* XDP section */
+
+#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0)
+#define XDP_FLAGS_SKB_MODE (1U << 1)
+#define XDP_FLAGS_DRV_MODE (1U << 2)
+#define XDP_FLAGS_HW_MODE (1U << 3)
+#define XDP_FLAGS_MODES (XDP_FLAGS_SKB_MODE | \
+ XDP_FLAGS_DRV_MODE | \
+ XDP_FLAGS_HW_MODE)
+#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \
+ XDP_FLAGS_MODES)
+
+/* These are stored into IFLA_XDP_ATTACHED on dump. */
+enum {
+ XDP_ATTACHED_NONE = 0,
+ XDP_ATTACHED_DRV,
+ XDP_ATTACHED_SKB,
+ XDP_ATTACHED_HW,
+ XDP_ATTACHED_MULTI,
+};
+
+enum {
+ IFLA_XDP_UNSPEC,
+ IFLA_XDP_FD,
+ IFLA_XDP_ATTACHED,
+ IFLA_XDP_FLAGS,
+ IFLA_XDP_PROG_ID,
+ IFLA_XDP_DRV_PROG_ID,
+ IFLA_XDP_SKB_PROG_ID,
+ IFLA_XDP_HW_PROG_ID,
+ __IFLA_XDP_MAX,
+};
+
+#define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1)
+
+enum {
+ IFLA_EVENT_NONE,
+ IFLA_EVENT_REBOOT, /* internal reset / reboot */
+ IFLA_EVENT_FEATURES, /* change in offload features */
+ IFLA_EVENT_BONDING_FAILOVER, /* change in active slave */
+ IFLA_EVENT_NOTIFY_PEERS, /* re-sent grat. arp/ndisc */
+ IFLA_EVENT_IGMP_RESEND, /* re-sent IGMP JOIN */
+ IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */
+};
+
+/* tun section */
+
+enum {
+ IFLA_TUN_UNSPEC,
+ IFLA_TUN_OWNER,
+ IFLA_TUN_GROUP,
+ IFLA_TUN_TYPE,
+ IFLA_TUN_PI,
+ IFLA_TUN_VNET_HDR,
+ IFLA_TUN_PERSIST,
+ IFLA_TUN_MULTI_QUEUE,
+ IFLA_TUN_NUM_QUEUES,
+ IFLA_TUN_NUM_DISABLED_QUEUES,
+ __IFLA_TUN_MAX,
+};
+
+#define IFLA_TUN_MAX (__IFLA_TUN_MAX - 1)
+
+/* rmnet section */
+
+#define RMNET_FLAGS_INGRESS_DEAGGREGATION (1U << 0)
+#define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3)
+
+enum {
+ IFLA_RMNET_UNSPEC,
+ IFLA_RMNET_MUX_ID,
+ IFLA_RMNET_FLAGS,
+ __IFLA_RMNET_MAX,
+};
+
+#define IFLA_RMNET_MAX (__IFLA_RMNET_MAX - 1)
+
+struct ifla_rmnet_flags {
+ __u32 flags;
+ __u32 mask;
+};
+
+#endif /* _UAPI_LINUX_IF_LINK_H */
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
new file mode 100644
index 0000000..48e8a22
--- /dev/null
+++ b/tools/include/uapi/linux/in.h
@@ -0,0 +1,301 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Definitions of the Internet Protocol.
+ *
+ * Version: @(#)in.h 1.0.1 04/21/93
+ *
+ * Authors: Original taken from the GNU Project <netinet/in.h> file.
+ * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _UAPI_LINUX_IN_H
+#define _UAPI_LINUX_IN_H
+
+#include <linux/types.h>
+#include <linux/libc-compat.h>
+#include <linux/socket.h>
+
+#if __UAPI_DEF_IN_IPPROTO
+/* Standard well-defined IP protocols. */
+enum {
+ IPPROTO_IP = 0, /* Dummy protocol for TCP */
+#define IPPROTO_IP IPPROTO_IP
+ IPPROTO_ICMP = 1, /* Internet Control Message Protocol */
+#define IPPROTO_ICMP IPPROTO_ICMP
+ IPPROTO_IGMP = 2, /* Internet Group Management Protocol */
+#define IPPROTO_IGMP IPPROTO_IGMP
+ IPPROTO_IPIP = 4, /* IPIP tunnels (older KA9Q tunnels use 94) */
+#define IPPROTO_IPIP IPPROTO_IPIP
+ IPPROTO_TCP = 6, /* Transmission Control Protocol */
+#define IPPROTO_TCP IPPROTO_TCP
+ IPPROTO_EGP = 8, /* Exterior Gateway Protocol */
+#define IPPROTO_EGP IPPROTO_EGP
+ IPPROTO_PUP = 12, /* PUP protocol */
+#define IPPROTO_PUP IPPROTO_PUP
+ IPPROTO_UDP = 17, /* User Datagram Protocol */
+#define IPPROTO_UDP IPPROTO_UDP
+ IPPROTO_IDP = 22, /* XNS IDP protocol */
+#define IPPROTO_IDP IPPROTO_IDP
+ IPPROTO_TP = 29, /* SO Transport Protocol Class 4 */
+#define IPPROTO_TP IPPROTO_TP
+ IPPROTO_DCCP = 33, /* Datagram Congestion Control Protocol */
+#define IPPROTO_DCCP IPPROTO_DCCP
+ IPPROTO_IPV6 = 41, /* IPv6-in-IPv4 tunnelling */
+#define IPPROTO_IPV6 IPPROTO_IPV6
+ IPPROTO_RSVP = 46, /* RSVP Protocol */
+#define IPPROTO_RSVP IPPROTO_RSVP
+ IPPROTO_GRE = 47, /* Cisco GRE tunnels (rfc 1701,1702) */
+#define IPPROTO_GRE IPPROTO_GRE
+ IPPROTO_ESP = 50, /* Encapsulation Security Payload protocol */
+#define IPPROTO_ESP IPPROTO_ESP
+ IPPROTO_AH = 51, /* Authentication Header protocol */
+#define IPPROTO_AH IPPROTO_AH
+ IPPROTO_MTP = 92, /* Multicast Transport Protocol */
+#define IPPROTO_MTP IPPROTO_MTP
+ IPPROTO_BEETPH = 94, /* IP option pseudo header for BEET */
+#define IPPROTO_BEETPH IPPROTO_BEETPH
+ IPPROTO_ENCAP = 98, /* Encapsulation Header */
+#define IPPROTO_ENCAP IPPROTO_ENCAP
+ IPPROTO_PIM = 103, /* Protocol Independent Multicast */
+#define IPPROTO_PIM IPPROTO_PIM
+ IPPROTO_COMP = 108, /* Compression Header Protocol */
+#define IPPROTO_COMP IPPROTO_COMP
+ IPPROTO_SCTP = 132, /* Stream Control Transport Protocol */
+#define IPPROTO_SCTP IPPROTO_SCTP
+ IPPROTO_UDPLITE = 136, /* UDP-Lite (RFC 3828) */
+#define IPPROTO_UDPLITE IPPROTO_UDPLITE
+ IPPROTO_MPLS = 137, /* MPLS in IP (RFC 4023) */
+#define IPPROTO_MPLS IPPROTO_MPLS
+ IPPROTO_RAW = 255, /* Raw IP packets */
+#define IPPROTO_RAW IPPROTO_RAW
+ IPPROTO_MAX
+};
+#endif
+
+#if __UAPI_DEF_IN_ADDR
+/* Internet address. */
+struct in_addr {
+ __be32 s_addr;
+};
+#endif
+
+#define IP_TOS 1
+#define IP_TTL 2
+#define IP_HDRINCL 3
+#define IP_OPTIONS 4
+#define IP_ROUTER_ALERT 5
+#define IP_RECVOPTS 6
+#define IP_RETOPTS 7
+#define IP_PKTINFO 8
+#define IP_PKTOPTIONS 9
+#define IP_MTU_DISCOVER 10
+#define IP_RECVERR 11
+#define IP_RECVTTL 12
+#define IP_RECVTOS 13
+#define IP_MTU 14
+#define IP_FREEBIND 15
+#define IP_IPSEC_POLICY 16
+#define IP_XFRM_POLICY 17
+#define IP_PASSSEC 18
+#define IP_TRANSPARENT 19
+
+/* BSD compatibility */
+#define IP_RECVRETOPTS IP_RETOPTS
+
+/* TProxy original addresses */
+#define IP_ORIGDSTADDR 20
+#define IP_RECVORIGDSTADDR IP_ORIGDSTADDR
+
+#define IP_MINTTL 21
+#define IP_NODEFRAG 22
+#define IP_CHECKSUM 23
+#define IP_BIND_ADDRESS_NO_PORT 24
+#define IP_RECVFRAGSIZE 25
+
+/* IP_MTU_DISCOVER values */
+#define IP_PMTUDISC_DONT 0 /* Never send DF frames */
+#define IP_PMTUDISC_WANT 1 /* Use per route hints */
+#define IP_PMTUDISC_DO 2 /* Always DF */
+#define IP_PMTUDISC_PROBE 3 /* Ignore dst pmtu */
+/* Always use interface mtu (ignores dst pmtu) but don't set DF flag.
+ * Also incoming ICMP frag_needed notifications will be ignored on
+ * this socket to prevent accepting spoofed ones.
+ */
+#define IP_PMTUDISC_INTERFACE 4
+/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+ * fragmented if they exeed the interface mtu
+ */
+#define IP_PMTUDISC_OMIT 5
+
+#define IP_MULTICAST_IF 32
+#define IP_MULTICAST_TTL 33
+#define IP_MULTICAST_LOOP 34
+#define IP_ADD_MEMBERSHIP 35
+#define IP_DROP_MEMBERSHIP 36
+#define IP_UNBLOCK_SOURCE 37
+#define IP_BLOCK_SOURCE 38
+#define IP_ADD_SOURCE_MEMBERSHIP 39
+#define IP_DROP_SOURCE_MEMBERSHIP 40
+#define IP_MSFILTER 41
+#define MCAST_JOIN_GROUP 42
+#define MCAST_BLOCK_SOURCE 43
+#define MCAST_UNBLOCK_SOURCE 44
+#define MCAST_LEAVE_GROUP 45
+#define MCAST_JOIN_SOURCE_GROUP 46
+#define MCAST_LEAVE_SOURCE_GROUP 47
+#define MCAST_MSFILTER 48
+#define IP_MULTICAST_ALL 49
+#define IP_UNICAST_IF 50
+
+#define MCAST_EXCLUDE 0
+#define MCAST_INCLUDE 1
+
+/* These need to appear somewhere around here */
+#define IP_DEFAULT_MULTICAST_TTL 1
+#define IP_DEFAULT_MULTICAST_LOOP 1
+
+/* Request struct for multicast socket ops */
+
+#if __UAPI_DEF_IP_MREQ
+struct ip_mreq {
+ struct in_addr imr_multiaddr; /* IP multicast address of group */
+ struct in_addr imr_interface; /* local IP address of interface */
+};
+
+struct ip_mreqn {
+ struct in_addr imr_multiaddr; /* IP multicast address of group */
+ struct in_addr imr_address; /* local IP address of interface */
+ int imr_ifindex; /* Interface index */
+};
+
+struct ip_mreq_source {
+ __be32 imr_multiaddr;
+ __be32 imr_interface;
+ __be32 imr_sourceaddr;
+};
+
+struct ip_msfilter {
+ __be32 imsf_multiaddr;
+ __be32 imsf_interface;
+ __u32 imsf_fmode;
+ __u32 imsf_numsrc;
+ __be32 imsf_slist[1];
+};
+
+#define IP_MSFILTER_SIZE(numsrc) \
+ (sizeof(struct ip_msfilter) - sizeof(__u32) \
+ + (numsrc) * sizeof(__u32))
+
+struct group_req {
+ __u32 gr_interface; /* interface index */
+ struct __kernel_sockaddr_storage gr_group; /* group address */
+};
+
+struct group_source_req {
+ __u32 gsr_interface; /* interface index */
+ struct __kernel_sockaddr_storage gsr_group; /* group address */
+ struct __kernel_sockaddr_storage gsr_source; /* source address */
+};
+
+struct group_filter {
+ __u32 gf_interface; /* interface index */
+ struct __kernel_sockaddr_storage gf_group; /* multicast address */
+ __u32 gf_fmode; /* filter mode */
+ __u32 gf_numsrc; /* number of sources */
+ struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */
+};
+
+#define GROUP_FILTER_SIZE(numsrc) \
+ (sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \
+ + (numsrc) * sizeof(struct __kernel_sockaddr_storage))
+#endif
+
+#if __UAPI_DEF_IN_PKTINFO
+struct in_pktinfo {
+ int ipi_ifindex;
+ struct in_addr ipi_spec_dst;
+ struct in_addr ipi_addr;
+};
+#endif
+
+/* Structure describing an Internet (IP) socket address. */
+#if __UAPI_DEF_SOCKADDR_IN
+#define __SOCK_SIZE__ 16 /* sizeof(struct sockaddr) */
+struct sockaddr_in {
+ __kernel_sa_family_t sin_family; /* Address family */
+ __be16 sin_port; /* Port number */
+ struct in_addr sin_addr; /* Internet address */
+
+ /* Pad to size of `struct sockaddr'. */
+ unsigned char __pad[__SOCK_SIZE__ - sizeof(short int) -
+ sizeof(unsigned short int) - sizeof(struct in_addr)];
+};
+#define sin_zero __pad /* for BSD UNIX comp. -FvK */
+#endif
+
+#if __UAPI_DEF_IN_CLASS
+/*
+ * Definitions of the bits in an Internet address integer.
+ * On subnets, host and network parts are found according
+ * to the subnet mask, not these masks.
+ */
+#define IN_CLASSA(a) ((((long int) (a)) & 0x80000000) == 0)
+#define IN_CLASSA_NET 0xff000000
+#define IN_CLASSA_NSHIFT 24
+#define IN_CLASSA_HOST (0xffffffff & ~IN_CLASSA_NET)
+#define IN_CLASSA_MAX 128
+
+#define IN_CLASSB(a) ((((long int) (a)) & 0xc0000000) == 0x80000000)
+#define IN_CLASSB_NET 0xffff0000
+#define IN_CLASSB_NSHIFT 16
+#define IN_CLASSB_HOST (0xffffffff & ~IN_CLASSB_NET)
+#define IN_CLASSB_MAX 65536
+
+#define IN_CLASSC(a) ((((long int) (a)) & 0xe0000000) == 0xc0000000)
+#define IN_CLASSC_NET 0xffffff00
+#define IN_CLASSC_NSHIFT 8
+#define IN_CLASSC_HOST (0xffffffff & ~IN_CLASSC_NET)
+
+#define IN_CLASSD(a) ((((long int) (a)) & 0xf0000000) == 0xe0000000)
+#define IN_MULTICAST(a) IN_CLASSD(a)
+#define IN_MULTICAST_NET 0xF0000000
+
+#define IN_EXPERIMENTAL(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define IN_BADCLASS(a) IN_EXPERIMENTAL((a))
+
+/* Address to accept any incoming messages. */
+#define INADDR_ANY ((unsigned long int) 0x00000000)
+
+/* Address to send to all hosts. */
+#define INADDR_BROADCAST ((unsigned long int) 0xffffffff)
+
+/* Address indicating an error return. */
+#define INADDR_NONE ((unsigned long int) 0xffffffff)
+
+/* Network number for local host loopback. */
+#define IN_LOOPBACKNET 127
+
+/* Address to loopback in software to local host. */
+#define INADDR_LOOPBACK 0x7f000001 /* 127.0.0.1 */
+#define IN_LOOPBACK(a) ((((long int) (a)) & 0xff000000) == 0x7f000000)
+
+/* Defines for Multicast INADDR */
+#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */
+#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */
+#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */
+#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */
+#endif
+
+/* <asm/byteorder.h> contains the htonl type stuff.. */
+#include <asm/byteorder.h>
+
+
+#endif /* _UAPI_LINUX_IN_H */
diff --git a/tools/include/uapi/linux/kcmp.h b/tools/include/uapi/linux/kcmp.h
new file mode 100644
index 0000000..ef13050
--- /dev/null
+++ b/tools/include/uapi/linux/kcmp.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_KCMP_H
+#define _UAPI_LINUX_KCMP_H
+
+#include <linux/types.h>
+
+/* Comparison type */
+enum kcmp_type {
+ KCMP_FILE,
+ KCMP_VM,
+ KCMP_FILES,
+ KCMP_FS,
+ KCMP_SIGHAND,
+ KCMP_IO,
+ KCMP_SYSVSEM,
+ KCMP_EPOLL_TFD,
+
+ KCMP_TYPES,
+};
+
+/* Slot for KCMP_EPOLL_TFD */
+struct kcmp_epoll_slot {
+ __u32 efd; /* epoll file descriptor */
+ __u32 tfd; /* target file number */
+ __u32 toff; /* target offset within same numbered sequence */
+};
+
+#endif /* _UAPI_LINUX_KCMP_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
new file mode 100644
index 0000000..251be35
--- /dev/null
+++ b/tools/include/uapi/linux/kvm.h
@@ -0,0 +1,1552 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_KVM_H
+#define __LINUX_KVM_H
+
+/*
+ * Userspace interface for /dev/kvm - kernel based virtual machine
+ *
+ * Note: you must update KVM_API_VERSION if you change this interface.
+ */
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/ioctl.h>
+#include <asm/kvm.h>
+
+#define KVM_API_VERSION 12
+
+/* *** Deprecated interfaces *** */
+
+#define KVM_TRC_SHIFT 16
+
+#define KVM_TRC_ENTRYEXIT (1 << KVM_TRC_SHIFT)
+#define KVM_TRC_HANDLER (1 << (KVM_TRC_SHIFT + 1))
+
+#define KVM_TRC_VMENTRY (KVM_TRC_ENTRYEXIT + 0x01)
+#define KVM_TRC_VMEXIT (KVM_TRC_ENTRYEXIT + 0x02)
+#define KVM_TRC_PAGE_FAULT (KVM_TRC_HANDLER + 0x01)
+
+#define KVM_TRC_HEAD_SIZE 12
+#define KVM_TRC_CYCLE_SIZE 8
+#define KVM_TRC_EXTRA_MAX 7
+
+#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02)
+#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03)
+#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04)
+#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05)
+#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06)
+#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07)
+#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08)
+#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09)
+#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A)
+#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B)
+#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C)
+#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D)
+#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E)
+#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F)
+#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10)
+#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11)
+#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12)
+#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13)
+#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14)
+#define KVM_TRC_TDP_FAULT (KVM_TRC_HANDLER + 0x15)
+#define KVM_TRC_GTLB_WRITE (KVM_TRC_HANDLER + 0x16)
+#define KVM_TRC_STLB_WRITE (KVM_TRC_HANDLER + 0x17)
+#define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18)
+#define KVM_TRC_PPC_INSTR (KVM_TRC_HANDLER + 0x19)
+
+struct kvm_user_trace_setup {
+ __u32 buf_size;
+ __u32 buf_nr;
+};
+
+#define __KVM_DEPRECATED_MAIN_W_0x06 \
+ _IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
+#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07)
+#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08)
+
+#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq)
+
+struct kvm_breakpoint {
+ __u32 enabled;
+ __u32 padding;
+ __u64 address;
+};
+
+struct kvm_debug_guest {
+ __u32 enabled;
+ __u32 pad;
+ struct kvm_breakpoint breakpoints[4];
+ __u32 singlestep;
+};
+
+#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, 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;
+ __u32 flags;
+ __u64 guest_phys_addr;
+ __u64 memory_size; /* bytes */
+ __u64 userspace_addr; /* start of the userspace allocated memory */
+};
+
+/*
+ * 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.
+ */
+#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
+#define KVM_MEM_READONLY (1UL << 1)
+
+/* for KVM_IRQ_LINE */
+struct kvm_irq_level {
+ /*
+ * ACPI gsi notion of irq.
+ * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47..
+ * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23..
+ * For ARM: See Documentation/virtual/kvm/api.txt
+ */
+ union {
+ __u32 irq;
+ __s32 status;
+ };
+ __u32 level;
+};
+
+
+struct kvm_irqchip {
+ __u32 chip_id;
+ __u32 pad;
+ union {
+ char dummy[512]; /* reserving space */
+#ifdef __KVM_HAVE_PIT
+ struct kvm_pic_state pic;
+#endif
+#ifdef __KVM_HAVE_IOAPIC
+ struct kvm_ioapic_state ioapic;
+#endif
+ } chip;
+};
+
+/* for KVM_CREATE_PIT2 */
+struct kvm_pit_config {
+ __u32 flags;
+ __u32 pad[15];
+};
+
+#define KVM_PIT_SPEAKER_DUMMY 1
+
+struct kvm_s390_skeys {
+ __u64 start_gfn;
+ __u64 count;
+ __u64 skeydata_addr;
+ __u32 flags;
+ __u32 reserved[9];
+};
+
+#define KVM_S390_CMMA_PEEK (1 << 0)
+
+/**
+ * kvm_s390_cmma_log - Used for CMMA migration.
+ *
+ * Used both for input and output.
+ *
+ * @start_gfn: Guest page number to start from.
+ * @count: Size of the result buffer.
+ * @flags: Control operation mode via KVM_S390_CMMA_* flags
+ * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty
+ * pages are still remaining.
+ * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set
+ * in the PGSTE.
+ * @values: Pointer to the values buffer.
+ *
+ * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls.
+ */
+struct kvm_s390_cmma_log {
+ __u64 start_gfn;
+ __u32 count;
+ __u32 flags;
+ union {
+ __u64 remaining;
+ __u64 mask;
+ };
+ __u64 values;
+};
+
+struct kvm_hyperv_exit {
+#define KVM_EXIT_HYPERV_SYNIC 1
+#define KVM_EXIT_HYPERV_HCALL 2
+ __u32 type;
+ union {
+ struct {
+ __u32 msr;
+ __u64 control;
+ __u64 evt_page;
+ __u64 msg_page;
+ } synic;
+ struct {
+ __u64 input;
+ __u64 result;
+ __u64 params[2];
+ } hcall;
+ } u;
+};
+
+#define KVM_S390_GET_SKEYS_NONE 1
+#define KVM_S390_SKEYS_MAX 1048576
+
+#define KVM_EXIT_UNKNOWN 0
+#define KVM_EXIT_EXCEPTION 1
+#define KVM_EXIT_IO 2
+#define KVM_EXIT_HYPERCALL 3
+#define KVM_EXIT_DEBUG 4
+#define KVM_EXIT_HLT 5
+#define KVM_EXIT_MMIO 6
+#define KVM_EXIT_IRQ_WINDOW_OPEN 7
+#define KVM_EXIT_SHUTDOWN 8
+#define KVM_EXIT_FAIL_ENTRY 9
+#define KVM_EXIT_INTR 10
+#define KVM_EXIT_SET_TPR 11
+#define KVM_EXIT_TPR_ACCESS 12
+#define KVM_EXIT_S390_SIEIC 13
+#define KVM_EXIT_S390_RESET 14
+#define KVM_EXIT_DCR 15 /* deprecated */
+#define KVM_EXIT_NMI 16
+#define KVM_EXIT_INTERNAL_ERROR 17
+#define KVM_EXIT_OSI 18
+#define KVM_EXIT_PAPR_HCALL 19
+#define KVM_EXIT_S390_UCONTROL 20
+#define KVM_EXIT_WATCHDOG 21
+#define KVM_EXIT_S390_TSCH 22
+#define KVM_EXIT_EPR 23
+#define KVM_EXIT_SYSTEM_EVENT 24
+#define KVM_EXIT_S390_STSI 25
+#define KVM_EXIT_IOAPIC_EOI 26
+#define KVM_EXIT_HYPERV 27
+
+/* For KVM_EXIT_INTERNAL_ERROR */
+/* Emulate instruction failed. */
+#define KVM_INTERNAL_ERROR_EMULATION 1
+/* Encounter unexpected simultaneous exceptions. */
+#define KVM_INTERNAL_ERROR_SIMUL_EX 2
+/* Encounter unexpected vm-exit due to delivery event. */
+#define KVM_INTERNAL_ERROR_DELIVERY_EV 3
+
+/* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
+struct kvm_run {
+ /* in */
+ __u8 request_interrupt_window;
+ __u8 immediate_exit;
+ __u8 padding1[6];
+
+ /* out */
+ __u32 exit_reason;
+ __u8 ready_for_interrupt_injection;
+ __u8 if_flag;
+ __u16 flags;
+
+ /* in (pre_kvm_run), out (post_kvm_run) */
+ __u64 cr8;
+ __u64 apic_base;
+
+#ifdef __KVM_S390
+ /* the processor status word for s390 */
+ __u64 psw_mask; /* psw upper half */
+ __u64 psw_addr; /* psw lower half */
+#endif
+ union {
+ /* KVM_EXIT_UNKNOWN */
+ struct {
+ __u64 hardware_exit_reason;
+ } hw;
+ /* KVM_EXIT_FAIL_ENTRY */
+ struct {
+ __u64 hardware_entry_failure_reason;
+ } fail_entry;
+ /* KVM_EXIT_EXCEPTION */
+ struct {
+ __u32 exception;
+ __u32 error_code;
+ } ex;
+ /* KVM_EXIT_IO */
+ struct {
+#define KVM_EXIT_IO_IN 0
+#define KVM_EXIT_IO_OUT 1
+ __u8 direction;
+ __u8 size; /* bytes */
+ __u16 port;
+ __u32 count;
+ __u64 data_offset; /* relative to kvm_run start */
+ } io;
+ /* KVM_EXIT_DEBUG */
+ struct {
+ struct kvm_debug_exit_arch arch;
+ } debug;
+ /* KVM_EXIT_MMIO */
+ struct {
+ __u64 phys_addr;
+ __u8 data[8];
+ __u32 len;
+ __u8 is_write;
+ } mmio;
+ /* KVM_EXIT_HYPERCALL */
+ struct {
+ __u64 nr;
+ __u64 args[6];
+ __u64 ret;
+ __u32 longmode;
+ __u32 pad;
+ } hypercall;
+ /* KVM_EXIT_TPR_ACCESS */
+ struct {
+ __u64 rip;
+ __u32 is_write;
+ __u32 pad;
+ } tpr_access;
+ /* KVM_EXIT_S390_SIEIC */
+ struct {
+ __u8 icptcode;
+ __u16 ipa;
+ __u32 ipb;
+ } s390_sieic;
+ /* KVM_EXIT_S390_RESET */
+#define KVM_S390_RESET_POR 1
+#define KVM_S390_RESET_CLEAR 2
+#define KVM_S390_RESET_SUBSYSTEM 4
+#define KVM_S390_RESET_CPU_INIT 8
+#define KVM_S390_RESET_IPL 16
+ __u64 s390_reset_flags;
+ /* KVM_EXIT_S390_UCONTROL */
+ struct {
+ __u64 trans_exc_code;
+ __u32 pgm_code;
+ } s390_ucontrol;
+ /* KVM_EXIT_DCR (deprecated) */
+ struct {
+ __u32 dcrn;
+ __u32 data;
+ __u8 is_write;
+ } dcr;
+ /* KVM_EXIT_INTERNAL_ERROR */
+ struct {
+ __u32 suberror;
+ /* Available with KVM_CAP_INTERNAL_ERROR_DATA: */
+ __u32 ndata;
+ __u64 data[16];
+ } internal;
+ /* KVM_EXIT_OSI */
+ struct {
+ __u64 gprs[32];
+ } osi;
+ /* KVM_EXIT_PAPR_HCALL */
+ struct {
+ __u64 nr;
+ __u64 ret;
+ __u64 args[9];
+ } papr_hcall;
+ /* KVM_EXIT_S390_TSCH */
+ struct {
+ __u16 subchannel_id;
+ __u16 subchannel_nr;
+ __u32 io_int_parm;
+ __u32 io_int_word;
+ __u32 ipb;
+ __u8 dequeued;
+ } s390_tsch;
+ /* KVM_EXIT_EPR */
+ struct {
+ __u32 epr;
+ } epr;
+ /* KVM_EXIT_SYSTEM_EVENT */
+ struct {
+#define KVM_SYSTEM_EVENT_SHUTDOWN 1
+#define KVM_SYSTEM_EVENT_RESET 2
+#define KVM_SYSTEM_EVENT_CRASH 3
+ __u32 type;
+ __u64 flags;
+ } system_event;
+ /* KVM_EXIT_S390_STSI */
+ struct {
+ __u64 addr;
+ __u8 ar;
+ __u8 reserved;
+ __u8 fc;
+ __u8 sel1;
+ __u16 sel2;
+ } s390_stsi;
+ /* KVM_EXIT_IOAPIC_EOI */
+ struct {
+ __u8 vector;
+ } eoi;
+ /* KVM_EXIT_HYPERV */
+ struct kvm_hyperv_exit hyperv;
+ /* Fix the size of the union. */
+ char padding[256];
+ };
+
+ /* 2048 is the size of the char array used to bound/pad the size
+ * of the union that holds sync regs.
+ */
+ #define SYNC_REGS_SIZE_BYTES 2048
+ /*
+ * shared registers between kvm and userspace.
+ * kvm_valid_regs specifies the register classes set by the host
+ * kvm_dirty_regs specified the register classes dirtied by userspace
+ * struct kvm_sync_regs is architecture specific, as well as the
+ * bits for kvm_valid_regs and kvm_dirty_regs
+ */
+ __u64 kvm_valid_regs;
+ __u64 kvm_dirty_regs;
+ union {
+ struct kvm_sync_regs regs;
+ char padding[SYNC_REGS_SIZE_BYTES];
+ } s;
+};
+
+/* for KVM_REGISTER_COALESCED_MMIO / KVM_UNREGISTER_COALESCED_MMIO */
+
+struct kvm_coalesced_mmio_zone {
+ __u64 addr;
+ __u32 size;
+ __u32 pad;
+};
+
+struct kvm_coalesced_mmio {
+ __u64 phys_addr;
+ __u32 len;
+ __u32 pad;
+ __u8 data[8];
+};
+
+struct kvm_coalesced_mmio_ring {
+ __u32 first, last;
+ struct kvm_coalesced_mmio coalesced_mmio[0];
+};
+
+#define KVM_COALESCED_MMIO_MAX \
+ ((PAGE_SIZE - sizeof(struct kvm_coalesced_mmio_ring)) / \
+ sizeof(struct kvm_coalesced_mmio))
+
+/* for KVM_TRANSLATE */
+struct kvm_translation {
+ /* in */
+ __u64 linear_address;
+
+ /* out */
+ __u64 physical_address;
+ __u8 valid;
+ __u8 writeable;
+ __u8 usermode;
+ __u8 pad[5];
+};
+
+/* for KVM_S390_MEM_OP */
+struct kvm_s390_mem_op {
+ /* in */
+ __u64 gaddr; /* the guest address */
+ __u64 flags; /* flags */
+ __u32 size; /* amount of bytes */
+ __u32 op; /* type of operation */
+ __u64 buf; /* buffer in userspace */
+ __u8 ar; /* the access register number */
+ __u8 reserved[31]; /* should be set to 0 */
+};
+/* types for kvm_s390_mem_op->op */
+#define KVM_S390_MEMOP_LOGICAL_READ 0
+#define KVM_S390_MEMOP_LOGICAL_WRITE 1
+/* flags for kvm_s390_mem_op->flags */
+#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0)
+#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1)
+
+/* for KVM_INTERRUPT */
+struct kvm_interrupt {
+ /* in */
+ __u32 irq;
+};
+
+/* for KVM_GET_DIRTY_LOG */
+struct kvm_dirty_log {
+ __u32 slot;
+ __u32 padding1;
+ union {
+ void __user *dirty_bitmap; /* one bit per page */
+ __u64 padding2;
+ };
+};
+
+/* for KVM_SET_SIGNAL_MASK */
+struct kvm_signal_mask {
+ __u32 len;
+ __u8 sigset[0];
+};
+
+/* for KVM_TPR_ACCESS_REPORTING */
+struct kvm_tpr_access_ctl {
+ __u32 enabled;
+ __u32 flags;
+ __u32 reserved[8];
+};
+
+/* for KVM_SET_VAPIC_ADDR */
+struct kvm_vapic_addr {
+ __u64 vapic_addr;
+};
+
+/* for KVM_SET_MP_STATE */
+
+/* not all states are valid on all architectures */
+#define KVM_MP_STATE_RUNNABLE 0
+#define KVM_MP_STATE_UNINITIALIZED 1
+#define KVM_MP_STATE_INIT_RECEIVED 2
+#define KVM_MP_STATE_HALTED 3
+#define KVM_MP_STATE_SIPI_RECEIVED 4
+#define KVM_MP_STATE_STOPPED 5
+#define KVM_MP_STATE_CHECK_STOP 6
+#define KVM_MP_STATE_OPERATING 7
+#define KVM_MP_STATE_LOAD 8
+
+struct kvm_mp_state {
+ __u32 mp_state;
+};
+
+struct kvm_s390_psw {
+ __u64 mask;
+ __u64 addr;
+};
+
+/* valid values for type in kvm_s390_interrupt */
+#define KVM_S390_SIGP_STOP 0xfffe0000u
+#define KVM_S390_PROGRAM_INT 0xfffe0001u
+#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u
+#define KVM_S390_RESTART 0xfffe0003u
+#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u
+#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u
+#define KVM_S390_MCHK 0xfffe1000u
+#define KVM_S390_INT_CLOCK_COMP 0xffff1004u
+#define KVM_S390_INT_CPU_TIMER 0xffff1005u
+#define KVM_S390_INT_VIRTIO 0xffff2603u
+#define KVM_S390_INT_SERVICE 0xffff2401u
+#define KVM_S390_INT_EMERGENCY 0xffff1201u
+#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u
+/* Anything below 0xfffe0000u is taken by INT_IO */
+#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \
+ (((schid)) | \
+ ((ssid) << 16) | \
+ ((cssid) << 18) | \
+ ((ai) << 26))
+#define KVM_S390_INT_IO_MIN 0x00000000u
+#define KVM_S390_INT_IO_MAX 0xfffdffffu
+#define KVM_S390_INT_IO_AI_MASK 0x04000000u
+
+
+struct kvm_s390_interrupt {
+ __u32 type;
+ __u32 parm;
+ __u64 parm64;
+};
+
+struct kvm_s390_io_info {
+ __u16 subchannel_id;
+ __u16 subchannel_nr;
+ __u32 io_int_parm;
+ __u32 io_int_word;
+};
+
+struct kvm_s390_ext_info {
+ __u32 ext_params;
+ __u32 pad;
+ __u64 ext_params2;
+};
+
+struct kvm_s390_pgm_info {
+ __u64 trans_exc_code;
+ __u64 mon_code;
+ __u64 per_address;
+ __u32 data_exc_code;
+ __u16 code;
+ __u16 mon_class_nr;
+ __u8 per_code;
+ __u8 per_atmid;
+ __u8 exc_access_id;
+ __u8 per_access_id;
+ __u8 op_access_id;
+#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01
+#define KVM_S390_PGM_FLAGS_ILC_0 0x02
+#define KVM_S390_PGM_FLAGS_ILC_1 0x04
+#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06
+#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08
+ __u8 flags;
+ __u8 pad[2];
+};
+
+struct kvm_s390_prefix_info {
+ __u32 address;
+};
+
+struct kvm_s390_extcall_info {
+ __u16 code;
+};
+
+struct kvm_s390_emerg_info {
+ __u16 code;
+};
+
+#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01
+struct kvm_s390_stop_info {
+ __u32 flags;
+};
+
+struct kvm_s390_mchk_info {
+ __u64 cr14;
+ __u64 mcic;
+ __u64 failing_storage_address;
+ __u32 ext_damage_code;
+ __u32 pad;
+ __u8 fixed_logout[16];
+};
+
+struct kvm_s390_irq {
+ __u64 type;
+ union {
+ struct kvm_s390_io_info io;
+ struct kvm_s390_ext_info ext;
+ struct kvm_s390_pgm_info pgm;
+ struct kvm_s390_emerg_info emerg;
+ struct kvm_s390_extcall_info extcall;
+ struct kvm_s390_prefix_info prefix;
+ struct kvm_s390_stop_info stop;
+ struct kvm_s390_mchk_info mchk;
+ char reserved[64];
+ } u;
+};
+
+struct kvm_s390_irq_state {
+ __u64 buf;
+ __u32 flags; /* will stay unused for compatibility reasons */
+ __u32 len;
+ __u32 reserved[4]; /* will stay unused for compatibility reasons */
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+
+#define KVM_GUESTDBG_ENABLE 0x00000001
+#define KVM_GUESTDBG_SINGLESTEP 0x00000002
+
+struct kvm_guest_debug {
+ __u32 control;
+ __u32 pad;
+ struct kvm_guest_debug_arch arch;
+};
+
+enum {
+ kvm_ioeventfd_flag_nr_datamatch,
+ kvm_ioeventfd_flag_nr_pio,
+ kvm_ioeventfd_flag_nr_deassign,
+ kvm_ioeventfd_flag_nr_virtio_ccw_notify,
+ kvm_ioeventfd_flag_nr_fast_mmio,
+ kvm_ioeventfd_flag_nr_max,
+};
+
+#define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
+#define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio)
+#define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign)
+#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
+ (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify)
+
+#define KVM_IOEVENTFD_VALID_FLAG_MASK ((1 << kvm_ioeventfd_flag_nr_max) - 1)
+
+struct kvm_ioeventfd {
+ __u64 datamatch;
+ __u64 addr; /* legal pio/mmio address */
+ __u32 len; /* 1, 2, 4, or 8 bytes; or 0 to ignore length */
+ __s32 fd;
+ __u32 flags;
+ __u8 pad[36];
+};
+
+#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HLT (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
+#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \
+ KVM_X86_DISABLE_EXITS_HLT | \
+ KVM_X86_DISABLE_EXITS_PAUSE)
+
+/* for KVM_ENABLE_CAP */
+struct kvm_enable_cap {
+ /* in */
+ __u32 cap;
+ __u32 flags;
+ __u64 args[4];
+ __u8 pad[64];
+};
+
+/* for KVM_PPC_GET_PVINFO */
+
+#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
+
+struct kvm_ppc_pvinfo {
+ /* out */
+ __u32 flags;
+ __u32 hcall[4];
+ __u8 pad[108];
+};
+
+/* for KVM_PPC_GET_SMMU_INFO */
+#define KVM_PPC_PAGE_SIZES_MAX_SZ 8
+
+struct kvm_ppc_one_page_size {
+ __u32 page_shift; /* Page shift (or 0) */
+ __u32 pte_enc; /* Encoding in the HPTE (>>12) */
+};
+
+struct kvm_ppc_one_seg_page_size {
+ __u32 page_shift; /* Base page shift of segment (or 0) */
+ __u32 slb_enc; /* SLB encoding for BookS */
+ struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+#define KVM_PPC_PAGE_SIZES_REAL 0x00000001
+#define KVM_PPC_1T_SEGMENTS 0x00000002
+
+struct kvm_ppc_smmu_info {
+ __u64 flags;
+ __u32 slb_size;
+ __u16 data_keys; /* # storage keys supported for data */
+ __u16 instr_keys; /* # storage keys supported for instructions */
+ struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */
+struct kvm_ppc_resize_hpt {
+ __u64 flags;
+ __u32 shift;
+ __u32 pad;
+};
+
+#define KVMIO 0xAE
+
+/* machine type bits, to be used as argument to KVM_CREATE_VM */
+#define KVM_VM_S390_UCONTROL 1
+
+/* on ppc, 0 indicate default, 1 should force HV and 2 PR */
+#define KVM_VM_PPC_HV 1
+#define KVM_VM_PPC_PR 2
+
+/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */
+#define KVM_VM_MIPS_TE 0
+#define KVM_VM_MIPS_VZ 1
+
+#define KVM_S390_SIE_PAGE_OFFSET 1
+
+/*
+ * ioctls for /dev/kvm fds:
+ */
+#define KVM_GET_API_VERSION _IO(KVMIO, 0x00)
+#define KVM_CREATE_VM _IO(KVMIO, 0x01) /* returns a VM fd */
+#define KVM_GET_MSR_INDEX_LIST _IOWR(KVMIO, 0x02, struct kvm_msr_list)
+
+#define KVM_S390_ENABLE_SIE _IO(KVMIO, 0x06)
+/*
+ * Check if a kvm extension is available. Argument is extension number,
+ * return is 1 (yes) or 0 (no, sorry).
+ */
+#define KVM_CHECK_EXTENSION _IO(KVMIO, 0x03)
+/*
+ * Get size for mmap(vcpu_fd)
+ */
+#define KVM_GET_VCPU_MMAP_SIZE _IO(KVMIO, 0x04) /* in bytes */
+#define KVM_GET_SUPPORTED_CPUID _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
+#define KVM_TRACE_ENABLE __KVM_DEPRECATED_MAIN_W_0x06
+#define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07
+#define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08
+#define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
+#define KVM_GET_MSR_FEATURE_INDEX_LIST _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
+
+/*
+ * Extension capability list.
+ */
+#define KVM_CAP_IRQCHIP 0
+#define KVM_CAP_HLT 1
+#define KVM_CAP_MMU_SHADOW_CACHE_CONTROL 2
+#define KVM_CAP_USER_MEMORY 3
+#define KVM_CAP_SET_TSS_ADDR 4
+#define KVM_CAP_VAPIC 6
+#define KVM_CAP_EXT_CPUID 7
+#define KVM_CAP_CLOCKSOURCE 8
+#define KVM_CAP_NR_VCPUS 9 /* returns recommended max vcpus per vm */
+#define KVM_CAP_NR_MEMSLOTS 10 /* returns max memory slots per vm */
+#define KVM_CAP_PIT 11
+#define KVM_CAP_NOP_IO_DELAY 12
+#define KVM_CAP_PV_MMU 13
+#define KVM_CAP_MP_STATE 14
+#define KVM_CAP_COALESCED_MMIO 15
+#define KVM_CAP_SYNC_MMU 16 /* Changes to host mmap are reflected in guest */
+#define KVM_CAP_IOMMU 18
+/* Bug in KVM_SET_USER_MEMORY_REGION fixed: */
+#define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21
+#define KVM_CAP_USER_NMI 22
+#ifdef __KVM_HAVE_GUEST_DEBUG
+#define KVM_CAP_SET_GUEST_DEBUG 23
+#endif
+#ifdef __KVM_HAVE_PIT
+#define KVM_CAP_REINJECT_CONTROL 24
+#endif
+#define KVM_CAP_IRQ_ROUTING 25
+#define KVM_CAP_IRQ_INJECT_STATUS 26
+#define KVM_CAP_ASSIGN_DEV_IRQ 29
+/* Another bug in KVM_SET_USER_MEMORY_REGION fixed: */
+#define KVM_CAP_JOIN_MEMORY_REGIONS_WORKS 30
+#ifdef __KVM_HAVE_MCE
+#define KVM_CAP_MCE 31
+#endif
+#define KVM_CAP_IRQFD 32
+#ifdef __KVM_HAVE_PIT
+#define KVM_CAP_PIT2 33
+#endif
+#define KVM_CAP_SET_BOOT_CPU_ID 34
+#ifdef __KVM_HAVE_PIT_STATE2
+#define KVM_CAP_PIT_STATE2 35
+#endif
+#define KVM_CAP_IOEVENTFD 36
+#define KVM_CAP_SET_IDENTITY_MAP_ADDR 37
+#ifdef __KVM_HAVE_XEN_HVM
+#define KVM_CAP_XEN_HVM 38
+#endif
+#define KVM_CAP_ADJUST_CLOCK 39
+#define KVM_CAP_INTERNAL_ERROR_DATA 40
+#ifdef __KVM_HAVE_VCPU_EVENTS
+#define KVM_CAP_VCPU_EVENTS 41
+#endif
+#define KVM_CAP_S390_PSW 42
+#define KVM_CAP_PPC_SEGSTATE 43
+#define KVM_CAP_HYPERV 44
+#define KVM_CAP_HYPERV_VAPIC 45
+#define KVM_CAP_HYPERV_SPIN 46
+#define KVM_CAP_PCI_SEGMENT 47
+#define KVM_CAP_PPC_PAIRED_SINGLES 48
+#define KVM_CAP_INTR_SHADOW 49
+#ifdef __KVM_HAVE_DEBUGREGS
+#define KVM_CAP_DEBUGREGS 50
+#endif
+#define KVM_CAP_X86_ROBUST_SINGLESTEP 51
+#define KVM_CAP_PPC_OSI 52
+#define KVM_CAP_PPC_UNSET_IRQ 53
+#define KVM_CAP_ENABLE_CAP 54
+#ifdef __KVM_HAVE_XSAVE
+#define KVM_CAP_XSAVE 55
+#endif
+#ifdef __KVM_HAVE_XCRS
+#define KVM_CAP_XCRS 56
+#endif
+#define KVM_CAP_PPC_GET_PVINFO 57
+#define KVM_CAP_PPC_IRQ_LEVEL 58
+#define KVM_CAP_ASYNC_PF 59
+#define KVM_CAP_TSC_CONTROL 60
+#define KVM_CAP_GET_TSC_KHZ 61
+#define KVM_CAP_PPC_BOOKE_SREGS 62
+#define KVM_CAP_SPAPR_TCE 63
+#define KVM_CAP_PPC_SMT 64
+#define KVM_CAP_PPC_RMA 65
+#define KVM_CAP_MAX_VCPUS 66 /* returns max vcpus per vm */
+#define KVM_CAP_PPC_HIOR 67
+#define KVM_CAP_PPC_PAPR 68
+#define KVM_CAP_SW_TLB 69
+#define KVM_CAP_ONE_REG 70
+#define KVM_CAP_S390_GMAP 71
+#define KVM_CAP_TSC_DEADLINE_TIMER 72
+#define KVM_CAP_S390_UCONTROL 73
+#define KVM_CAP_SYNC_REGS 74
+#define KVM_CAP_PCI_2_3 75
+#define KVM_CAP_KVMCLOCK_CTRL 76
+#define KVM_CAP_SIGNAL_MSI 77
+#define KVM_CAP_PPC_GET_SMMU_INFO 78
+#define KVM_CAP_S390_COW 79
+#define KVM_CAP_PPC_ALLOC_HTAB 80
+#define KVM_CAP_READONLY_MEM 81
+#define KVM_CAP_IRQFD_RESAMPLE 82
+#define KVM_CAP_PPC_BOOKE_WATCHDOG 83
+#define KVM_CAP_PPC_HTAB_FD 84
+#define KVM_CAP_S390_CSS_SUPPORT 85
+#define KVM_CAP_PPC_EPR 86
+#define KVM_CAP_ARM_PSCI 87
+#define KVM_CAP_ARM_SET_DEVICE_ADDR 88
+#define KVM_CAP_DEVICE_CTRL 89
+#define KVM_CAP_IRQ_MPIC 90
+#define KVM_CAP_PPC_RTAS 91
+#define KVM_CAP_IRQ_XICS 92
+#define KVM_CAP_ARM_EL1_32BIT 93
+#define KVM_CAP_SPAPR_MULTITCE 94
+#define KVM_CAP_EXT_EMUL_CPUID 95
+#define KVM_CAP_HYPERV_TIME 96
+#define KVM_CAP_IOAPIC_POLARITY_IGNORED 97
+#define KVM_CAP_ENABLE_CAP_VM 98
+#define KVM_CAP_S390_IRQCHIP 99
+#define KVM_CAP_IOEVENTFD_NO_LENGTH 100
+#define KVM_CAP_VM_ATTRIBUTES 101
+#define KVM_CAP_ARM_PSCI_0_2 102
+#define KVM_CAP_PPC_FIXUP_HCALL 103
+#define KVM_CAP_PPC_ENABLE_HCALL 104
+#define KVM_CAP_CHECK_EXTENSION_VM 105
+#define KVM_CAP_S390_USER_SIGP 106
+#define KVM_CAP_S390_VECTOR_REGISTERS 107
+#define KVM_CAP_S390_MEM_OP 108
+#define KVM_CAP_S390_USER_STSI 109
+#define KVM_CAP_S390_SKEYS 110
+#define KVM_CAP_MIPS_FPU 111
+#define KVM_CAP_MIPS_MSA 112
+#define KVM_CAP_S390_INJECT_IRQ 113
+#define KVM_CAP_S390_IRQ_STATE 114
+#define KVM_CAP_PPC_HWRNG 115
+#define KVM_CAP_DISABLE_QUIRKS 116
+#define KVM_CAP_X86_SMM 117
+#define KVM_CAP_MULTI_ADDRESS_SPACE 118
+#define KVM_CAP_GUEST_DEBUG_HW_BPS 119
+#define KVM_CAP_GUEST_DEBUG_HW_WPS 120
+#define KVM_CAP_SPLIT_IRQCHIP 121
+#define KVM_CAP_IOEVENTFD_ANY_LENGTH 122
+#define KVM_CAP_HYPERV_SYNIC 123
+#define KVM_CAP_S390_RI 124
+#define KVM_CAP_SPAPR_TCE_64 125
+#define KVM_CAP_ARM_PMU_V3 126
+#define KVM_CAP_VCPU_ATTRIBUTES 127
+#define KVM_CAP_MAX_VCPU_ID 128
+#define KVM_CAP_X2APIC_API 129
+#define KVM_CAP_S390_USER_INSTR0 130
+#define KVM_CAP_MSI_DEVID 131
+#define KVM_CAP_PPC_HTM 132
+#define KVM_CAP_SPAPR_RESIZE_HPT 133
+#define KVM_CAP_PPC_MMU_RADIX 134
+#define KVM_CAP_PPC_MMU_HASH_V3 135
+#define KVM_CAP_IMMEDIATE_EXIT 136
+#define KVM_CAP_MIPS_VZ 137
+#define KVM_CAP_MIPS_TE 138
+#define KVM_CAP_MIPS_64BIT 139
+#define KVM_CAP_S390_GS 140
+#define KVM_CAP_S390_AIS 141
+#define KVM_CAP_SPAPR_TCE_VFIO 142
+#define KVM_CAP_X86_DISABLE_EXITS 143
+#define KVM_CAP_ARM_USER_IRQ 144
+#define KVM_CAP_S390_CMMA_MIGRATION 145
+#define KVM_CAP_PPC_FWNMI 146
+#define KVM_CAP_PPC_SMT_POSSIBLE 147
+#define KVM_CAP_HYPERV_SYNIC2 148
+#define KVM_CAP_HYPERV_VP_INDEX 149
+#define KVM_CAP_S390_AIS_MIGRATION 150
+#define KVM_CAP_PPC_GET_CPU_CHAR 151
+#define KVM_CAP_S390_BPB 152
+#define KVM_CAP_GET_MSR_FEATURES 153
+#define KVM_CAP_HYPERV_EVENTFD 154
+#define KVM_CAP_HYPERV_TLBFLUSH 155
+#define KVM_CAP_S390_HPAGE_1M 156
+#define KVM_CAP_NESTED_STATE 157
+#define KVM_CAP_ARM_INJECT_SERROR_ESR 158
+#define KVM_CAP_MSR_PLATFORM_INFO 159
+
+#ifdef KVM_CAP_IRQ_ROUTING
+
+struct kvm_irq_routing_irqchip {
+ __u32 irqchip;
+ __u32 pin;
+};
+
+struct kvm_irq_routing_msi {
+ __u32 address_lo;
+ __u32 address_hi;
+ __u32 data;
+ union {
+ __u32 pad;
+ __u32 devid;
+ };
+};
+
+struct kvm_irq_routing_s390_adapter {
+ __u64 ind_addr;
+ __u64 summary_addr;
+ __u64 ind_offset;
+ __u32 summary_offset;
+ __u32 adapter_id;
+};
+
+struct kvm_irq_routing_hv_sint {
+ __u32 vcpu;
+ __u32 sint;
+};
+
+/* gsi routing entry types */
+#define KVM_IRQ_ROUTING_IRQCHIP 1
+#define KVM_IRQ_ROUTING_MSI 2
+#define KVM_IRQ_ROUTING_S390_ADAPTER 3
+#define KVM_IRQ_ROUTING_HV_SINT 4
+
+struct kvm_irq_routing_entry {
+ __u32 gsi;
+ __u32 type;
+ __u32 flags;
+ __u32 pad;
+ union {
+ struct kvm_irq_routing_irqchip irqchip;
+ struct kvm_irq_routing_msi msi;
+ struct kvm_irq_routing_s390_adapter adapter;
+ struct kvm_irq_routing_hv_sint hv_sint;
+ __u32 pad[8];
+ } u;
+};
+
+struct kvm_irq_routing {
+ __u32 nr;
+ __u32 flags;
+ struct kvm_irq_routing_entry entries[0];
+};
+
+#endif
+
+#ifdef KVM_CAP_MCE
+/* x86 MCE */
+struct kvm_x86_mce {
+ __u64 status;
+ __u64 addr;
+ __u64 misc;
+ __u64 mcg_status;
+ __u8 bank;
+ __u8 pad1[7];
+ __u64 pad2[3];
+};
+#endif
+
+#ifdef KVM_CAP_XEN_HVM
+struct kvm_xen_hvm_config {
+ __u32 flags;
+ __u32 msr;
+ __u64 blob_addr_32;
+ __u64 blob_addr_64;
+ __u8 blob_size_32;
+ __u8 blob_size_64;
+ __u8 pad2[30];
+};
+#endif
+
+#define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
+/*
+ * Available with KVM_CAP_IRQFD_RESAMPLE
+ *
+ * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
+ * the irqfd to operate in resampling mode for level triggered interrupt
+ * emulation. See Documentation/virtual/kvm/api.txt.
+ */
+#define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
+
+struct kvm_irqfd {
+ __u32 fd;
+ __u32 gsi;
+ __u32 flags;
+ __u32 resamplefd;
+ __u8 pad[16];
+};
+
+/* For KVM_CAP_ADJUST_CLOCK */
+
+/* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags. */
+#define KVM_CLOCK_TSC_STABLE 2
+
+struct kvm_clock_data {
+ __u64 clock;
+ __u32 flags;
+ __u32 pad[9];
+};
+
+/* For KVM_CAP_SW_TLB */
+
+#define KVM_MMU_FSL_BOOKE_NOHV 0
+#define KVM_MMU_FSL_BOOKE_HV 1
+
+struct kvm_config_tlb {
+ __u64 params;
+ __u64 array;
+ __u32 mmu_type;
+ __u32 array_len;
+};
+
+struct kvm_dirty_tlb {
+ __u64 bitmap;
+ __u32 num_dirty;
+};
+
+/* Available with KVM_CAP_ONE_REG */
+
+#define KVM_REG_ARCH_MASK 0xff00000000000000ULL
+#define KVM_REG_GENERIC 0x0000000000000000ULL
+
+/*
+ * Architecture specific registers are to be defined in arch headers and
+ * ORed with the arch identifier.
+ */
+#define KVM_REG_PPC 0x1000000000000000ULL
+#define KVM_REG_X86 0x2000000000000000ULL
+#define KVM_REG_IA64 0x3000000000000000ULL
+#define KVM_REG_ARM 0x4000000000000000ULL
+#define KVM_REG_S390 0x5000000000000000ULL
+#define KVM_REG_ARM64 0x6000000000000000ULL
+#define KVM_REG_MIPS 0x7000000000000000ULL
+
+#define KVM_REG_SIZE_SHIFT 52
+#define KVM_REG_SIZE_MASK 0x00f0000000000000ULL
+#define KVM_REG_SIZE_U8 0x0000000000000000ULL
+#define KVM_REG_SIZE_U16 0x0010000000000000ULL
+#define KVM_REG_SIZE_U32 0x0020000000000000ULL
+#define KVM_REG_SIZE_U64 0x0030000000000000ULL
+#define KVM_REG_SIZE_U128 0x0040000000000000ULL
+#define KVM_REG_SIZE_U256 0x0050000000000000ULL
+#define KVM_REG_SIZE_U512 0x0060000000000000ULL
+#define KVM_REG_SIZE_U1024 0x0070000000000000ULL
+
+struct kvm_reg_list {
+ __u64 n; /* number of regs */
+ __u64 reg[0];
+};
+
+struct kvm_one_reg {
+ __u64 id;
+ __u64 addr;
+};
+
+#define KVM_MSI_VALID_DEVID (1U << 0)
+struct kvm_msi {
+ __u32 address_lo;
+ __u32 address_hi;
+ __u32 data;
+ __u32 flags;
+ __u32 devid;
+ __u8 pad[12];
+};
+
+struct kvm_arm_device_addr {
+ __u64 id;
+ __u64 addr;
+};
+
+/*
+ * Device control API, available with KVM_CAP_DEVICE_CTRL
+ */
+#define KVM_CREATE_DEVICE_TEST 1
+
+struct kvm_create_device {
+ __u32 type; /* in: KVM_DEV_TYPE_xxx */
+ __u32 fd; /* out: device handle */
+ __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */
+};
+
+struct kvm_device_attr {
+ __u32 flags; /* no flags currently defined */
+ __u32 group; /* device-defined */
+ __u64 attr; /* group-defined */
+ __u64 addr; /* userspace address of attr data */
+};
+
+#define KVM_DEV_VFIO_GROUP 1
+#define KVM_DEV_VFIO_GROUP_ADD 1
+#define KVM_DEV_VFIO_GROUP_DEL 2
+#define KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE 3
+
+enum kvm_device_type {
+ KVM_DEV_TYPE_FSL_MPIC_20 = 1,
+#define KVM_DEV_TYPE_FSL_MPIC_20 KVM_DEV_TYPE_FSL_MPIC_20
+ KVM_DEV_TYPE_FSL_MPIC_42,
+#define KVM_DEV_TYPE_FSL_MPIC_42 KVM_DEV_TYPE_FSL_MPIC_42
+ KVM_DEV_TYPE_XICS,
+#define KVM_DEV_TYPE_XICS KVM_DEV_TYPE_XICS
+ KVM_DEV_TYPE_VFIO,
+#define KVM_DEV_TYPE_VFIO KVM_DEV_TYPE_VFIO
+ KVM_DEV_TYPE_ARM_VGIC_V2,
+#define KVM_DEV_TYPE_ARM_VGIC_V2 KVM_DEV_TYPE_ARM_VGIC_V2
+ KVM_DEV_TYPE_FLIC,
+#define KVM_DEV_TYPE_FLIC KVM_DEV_TYPE_FLIC
+ KVM_DEV_TYPE_ARM_VGIC_V3,
+#define KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_ARM_VGIC_V3
+ KVM_DEV_TYPE_ARM_VGIC_ITS,
+#define KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_ARM_VGIC_ITS
+ KVM_DEV_TYPE_MAX,
+};
+
+struct kvm_vfio_spapr_tce {
+ __s32 groupfd;
+ __s32 tablefd;
+};
+
+/*
+ * 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, \
+ struct kvm_userspace_memory_region)
+#define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47)
+#define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64)
+
+/* enable ucontrol for s390 */
+struct kvm_s390_ucas_mapping {
+ __u64 user_addr;
+ __u64 vcpu_addr;
+ __u64 length;
+};
+#define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping)
+#define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping)
+#define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long)
+
+/* Device model IOC */
+#define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60)
+#define KVM_IRQ_LINE _IOW(KVMIO, 0x61, struct kvm_irq_level)
+#define KVM_GET_IRQCHIP _IOWR(KVMIO, 0x62, struct kvm_irqchip)
+#define KVM_SET_IRQCHIP _IOR(KVMIO, 0x63, struct kvm_irqchip)
+#define KVM_CREATE_PIT _IO(KVMIO, 0x64)
+#define KVM_GET_PIT _IOWR(KVMIO, 0x65, struct kvm_pit_state)
+#define KVM_SET_PIT _IOR(KVMIO, 0x66, struct kvm_pit_state)
+#define KVM_IRQ_LINE_STATUS _IOWR(KVMIO, 0x67, struct kvm_irq_level)
+#define KVM_REGISTER_COALESCED_MMIO \
+ _IOW(KVMIO, 0x67, struct kvm_coalesced_mmio_zone)
+#define KVM_UNREGISTER_COALESCED_MMIO \
+ _IOW(KVMIO, 0x68, struct kvm_coalesced_mmio_zone)
+#define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \
+ struct kvm_assigned_pci_dev)
+#define KVM_SET_GSI_ROUTING _IOW(KVMIO, 0x6a, struct kvm_irq_routing)
+/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
+#define KVM_ASSIGN_IRQ __KVM_DEPRECATED_VM_R_0x70
+#define KVM_ASSIGN_DEV_IRQ _IOW(KVMIO, 0x70, struct kvm_assigned_irq)
+#define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71)
+#define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \
+ struct kvm_assigned_pci_dev)
+#define KVM_ASSIGN_SET_MSIX_NR _IOW(KVMIO, 0x73, \
+ struct kvm_assigned_msix_nr)
+#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO, 0x74, \
+ struct kvm_assigned_msix_entry)
+#define KVM_DEASSIGN_DEV_IRQ _IOW(KVMIO, 0x75, struct kvm_assigned_irq)
+#define KVM_IRQFD _IOW(KVMIO, 0x76, struct kvm_irqfd)
+#define KVM_CREATE_PIT2 _IOW(KVMIO, 0x77, struct kvm_pit_config)
+#define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78)
+#define KVM_IOEVENTFD _IOW(KVMIO, 0x79, struct kvm_ioeventfd)
+#define KVM_XEN_HVM_CONFIG _IOW(KVMIO, 0x7a, struct kvm_xen_hvm_config)
+#define KVM_SET_CLOCK _IOW(KVMIO, 0x7b, struct kvm_clock_data)
+#define KVM_GET_CLOCK _IOR(KVMIO, 0x7c, struct kvm_clock_data)
+/* Available with KVM_CAP_PIT_STATE2 */
+#define KVM_GET_PIT2 _IOR(KVMIO, 0x9f, struct kvm_pit_state2)
+#define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2)
+/* Available with KVM_CAP_PPC_GET_PVINFO */
+#define KVM_PPC_GET_PVINFO _IOW(KVMIO, 0xa1, struct kvm_ppc_pvinfo)
+/* Available with KVM_CAP_TSC_CONTROL */
+#define KVM_SET_TSC_KHZ _IO(KVMIO, 0xa2)
+#define KVM_GET_TSC_KHZ _IO(KVMIO, 0xa3)
+/* Available with KVM_CAP_PCI_2_3 */
+#define KVM_ASSIGN_SET_INTX_MASK _IOW(KVMIO, 0xa4, \
+ struct kvm_assigned_pci_dev)
+/* Available with KVM_CAP_SIGNAL_MSI */
+#define KVM_SIGNAL_MSI _IOW(KVMIO, 0xa5, struct kvm_msi)
+/* Available with KVM_CAP_PPC_GET_SMMU_INFO */
+#define KVM_PPC_GET_SMMU_INFO _IOR(KVMIO, 0xa6, struct kvm_ppc_smmu_info)
+/* Available with KVM_CAP_PPC_ALLOC_HTAB */
+#define KVM_PPC_ALLOCATE_HTAB _IOWR(KVMIO, 0xa7, __u32)
+#define KVM_CREATE_SPAPR_TCE _IOW(KVMIO, 0xa8, struct kvm_create_spapr_tce)
+#define KVM_CREATE_SPAPR_TCE_64 _IOW(KVMIO, 0xa8, \
+ struct kvm_create_spapr_tce_64)
+/* Available with KVM_CAP_RMA */
+#define KVM_ALLOCATE_RMA _IOR(KVMIO, 0xa9, struct kvm_allocate_rma)
+/* Available with KVM_CAP_PPC_HTAB_FD */
+#define KVM_PPC_GET_HTAB_FD _IOW(KVMIO, 0xaa, struct kvm_get_htab_fd)
+/* Available with KVM_CAP_ARM_SET_DEVICE_ADDR */
+#define KVM_ARM_SET_DEVICE_ADDR _IOW(KVMIO, 0xab, struct kvm_arm_device_addr)
+/* Available with KVM_CAP_PPC_RTAS */
+#define KVM_PPC_RTAS_DEFINE_TOKEN _IOW(KVMIO, 0xac, struct kvm_rtas_token_args)
+/* Available with KVM_CAP_SPAPR_RESIZE_HPT */
+#define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt)
+#define KVM_PPC_RESIZE_HPT_COMMIT _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt)
+/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */
+#define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg)
+/* Available with KVM_CAP_PPC_RADIX_MMU */
+#define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info)
+/* Available with KVM_CAP_PPC_GET_CPU_CHAR */
+#define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char)
+
+/* ioctl for vm fd */
+#define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device)
+
+/* ioctls for fds returned by KVM_CREATE_DEVICE */
+#define KVM_SET_DEVICE_ATTR _IOW(KVMIO, 0xe1, struct kvm_device_attr)
+#define KVM_GET_DEVICE_ATTR _IOW(KVMIO, 0xe2, struct kvm_device_attr)
+#define KVM_HAS_DEVICE_ATTR _IOW(KVMIO, 0xe3, struct kvm_device_attr)
+
+/*
+ * ioctls for vcpu fds
+ */
+#define KVM_RUN _IO(KVMIO, 0x80)
+#define KVM_GET_REGS _IOR(KVMIO, 0x81, struct kvm_regs)
+#define KVM_SET_REGS _IOW(KVMIO, 0x82, struct kvm_regs)
+#define KVM_GET_SREGS _IOR(KVMIO, 0x83, struct kvm_sregs)
+#define KVM_SET_SREGS _IOW(KVMIO, 0x84, struct kvm_sregs)
+#define KVM_TRANSLATE _IOWR(KVMIO, 0x85, struct kvm_translation)
+#define KVM_INTERRUPT _IOW(KVMIO, 0x86, struct kvm_interrupt)
+/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
+#define KVM_DEBUG_GUEST __KVM_DEPRECATED_VCPU_W_0x87
+#define KVM_GET_MSRS _IOWR(KVMIO, 0x88, struct kvm_msrs)
+#define KVM_SET_MSRS _IOW(KVMIO, 0x89, struct kvm_msrs)
+#define KVM_SET_CPUID _IOW(KVMIO, 0x8a, struct kvm_cpuid)
+#define KVM_SET_SIGNAL_MASK _IOW(KVMIO, 0x8b, struct kvm_signal_mask)
+#define KVM_GET_FPU _IOR(KVMIO, 0x8c, struct kvm_fpu)
+#define KVM_SET_FPU _IOW(KVMIO, 0x8d, struct kvm_fpu)
+#define KVM_GET_LAPIC _IOR(KVMIO, 0x8e, struct kvm_lapic_state)
+#define KVM_SET_LAPIC _IOW(KVMIO, 0x8f, struct kvm_lapic_state)
+#define KVM_SET_CPUID2 _IOW(KVMIO, 0x90, struct kvm_cpuid2)
+#define KVM_GET_CPUID2 _IOWR(KVMIO, 0x91, struct kvm_cpuid2)
+/* Available with KVM_CAP_VAPIC */
+#define KVM_TPR_ACCESS_REPORTING _IOWR(KVMIO, 0x92, struct kvm_tpr_access_ctl)
+/* Available with KVM_CAP_VAPIC */
+#define KVM_SET_VAPIC_ADDR _IOW(KVMIO, 0x93, struct kvm_vapic_addr)
+/* valid for virtual machine (for floating interrupt)_and_ vcpu */
+#define KVM_S390_INTERRUPT _IOW(KVMIO, 0x94, struct kvm_s390_interrupt)
+/* store status for s390 */
+#define KVM_S390_STORE_STATUS_NOADDR (-1ul)
+#define KVM_S390_STORE_STATUS_PREFIXED (-2ul)
+#define KVM_S390_STORE_STATUS _IOW(KVMIO, 0x95, unsigned long)
+/* initial ipl psw for s390 */
+#define KVM_S390_SET_INITIAL_PSW _IOW(KVMIO, 0x96, struct kvm_s390_psw)
+/* initial reset for s390 */
+#define KVM_S390_INITIAL_RESET _IO(KVMIO, 0x97)
+#define KVM_GET_MP_STATE _IOR(KVMIO, 0x98, struct kvm_mp_state)
+#define KVM_SET_MP_STATE _IOW(KVMIO, 0x99, struct kvm_mp_state)
+/* Available with KVM_CAP_USER_NMI */
+#define KVM_NMI _IO(KVMIO, 0x9a)
+/* Available with KVM_CAP_SET_GUEST_DEBUG */
+#define KVM_SET_GUEST_DEBUG _IOW(KVMIO, 0x9b, struct kvm_guest_debug)
+/* MCE for x86 */
+#define KVM_X86_SETUP_MCE _IOW(KVMIO, 0x9c, __u64)
+#define KVM_X86_GET_MCE_CAP_SUPPORTED _IOR(KVMIO, 0x9d, __u64)
+#define KVM_X86_SET_MCE _IOW(KVMIO, 0x9e, struct kvm_x86_mce)
+/* Available with KVM_CAP_VCPU_EVENTS */
+#define KVM_GET_VCPU_EVENTS _IOR(KVMIO, 0x9f, struct kvm_vcpu_events)
+#define KVM_SET_VCPU_EVENTS _IOW(KVMIO, 0xa0, struct kvm_vcpu_events)
+/* Available with KVM_CAP_DEBUGREGS */
+#define KVM_GET_DEBUGREGS _IOR(KVMIO, 0xa1, struct kvm_debugregs)
+#define KVM_SET_DEBUGREGS _IOW(KVMIO, 0xa2, struct kvm_debugregs)
+/*
+ * vcpu version available with KVM_ENABLE_CAP
+ * vm version available with KVM_CAP_ENABLE_CAP_VM
+ */
+#define KVM_ENABLE_CAP _IOW(KVMIO, 0xa3, struct kvm_enable_cap)
+/* Available with KVM_CAP_XSAVE */
+#define KVM_GET_XSAVE _IOR(KVMIO, 0xa4, struct kvm_xsave)
+#define KVM_SET_XSAVE _IOW(KVMIO, 0xa5, struct kvm_xsave)
+/* Available with KVM_CAP_XCRS */
+#define KVM_GET_XCRS _IOR(KVMIO, 0xa6, struct kvm_xcrs)
+#define KVM_SET_XCRS _IOW(KVMIO, 0xa7, struct kvm_xcrs)
+/* Available with KVM_CAP_SW_TLB */
+#define KVM_DIRTY_TLB _IOW(KVMIO, 0xaa, struct kvm_dirty_tlb)
+/* Available with KVM_CAP_ONE_REG */
+#define KVM_GET_ONE_REG _IOW(KVMIO, 0xab, struct kvm_one_reg)
+#define KVM_SET_ONE_REG _IOW(KVMIO, 0xac, struct kvm_one_reg)
+/* VM is being stopped by host */
+#define KVM_KVMCLOCK_CTRL _IO(KVMIO, 0xad)
+#define KVM_ARM_VCPU_INIT _IOW(KVMIO, 0xae, struct kvm_vcpu_init)
+#define KVM_ARM_PREFERRED_TARGET _IOR(KVMIO, 0xaf, struct kvm_vcpu_init)
+#define KVM_GET_REG_LIST _IOWR(KVMIO, 0xb0, struct kvm_reg_list)
+/* Available with KVM_CAP_S390_MEM_OP */
+#define KVM_S390_MEM_OP _IOW(KVMIO, 0xb1, struct kvm_s390_mem_op)
+/* Available with KVM_CAP_S390_SKEYS */
+#define KVM_S390_GET_SKEYS _IOW(KVMIO, 0xb2, struct kvm_s390_skeys)
+#define KVM_S390_SET_SKEYS _IOW(KVMIO, 0xb3, struct kvm_s390_skeys)
+/* Available with KVM_CAP_S390_INJECT_IRQ */
+#define KVM_S390_IRQ _IOW(KVMIO, 0xb4, struct kvm_s390_irq)
+/* Available with KVM_CAP_S390_IRQ_STATE */
+#define KVM_S390_SET_IRQ_STATE _IOW(KVMIO, 0xb5, struct kvm_s390_irq_state)
+#define KVM_S390_GET_IRQ_STATE _IOW(KVMIO, 0xb6, struct kvm_s390_irq_state)
+/* Available with KVM_CAP_X86_SMM */
+#define KVM_SMI _IO(KVMIO, 0xb7)
+/* Available with KVM_CAP_S390_CMMA_MIGRATION */
+#define KVM_S390_GET_CMMA_BITS _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log)
+#define KVM_S390_SET_CMMA_BITS _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log)
+/* Memory Encryption Commands */
+#define KVM_MEMORY_ENCRYPT_OP _IOWR(KVMIO, 0xba, unsigned long)
+
+struct kvm_enc_region {
+ __u64 addr;
+ __u64 size;
+};
+
+#define KVM_MEMORY_ENCRYPT_REG_REGION _IOR(KVMIO, 0xbb, struct kvm_enc_region)
+#define KVM_MEMORY_ENCRYPT_UNREG_REGION _IOR(KVMIO, 0xbc, struct kvm_enc_region)
+
+/* Available with KVM_CAP_HYPERV_EVENTFD */
+#define KVM_HYPERV_EVENTFD _IOW(KVMIO, 0xbd, struct kvm_hyperv_eventfd)
+
+/* Available with KVM_CAP_NESTED_STATE */
+#define KVM_GET_NESTED_STATE _IOWR(KVMIO, 0xbe, struct kvm_nested_state)
+#define KVM_SET_NESTED_STATE _IOW(KVMIO, 0xbf, struct kvm_nested_state)
+
+/* Secure Encrypted Virtualization command */
+enum sev_cmd_id {
+ /* Guest initialization commands */
+ KVM_SEV_INIT = 0,
+ KVM_SEV_ES_INIT,
+ /* Guest launch commands */
+ KVM_SEV_LAUNCH_START,
+ KVM_SEV_LAUNCH_UPDATE_DATA,
+ KVM_SEV_LAUNCH_UPDATE_VMSA,
+ KVM_SEV_LAUNCH_SECRET,
+ KVM_SEV_LAUNCH_MEASURE,
+ KVM_SEV_LAUNCH_FINISH,
+ /* Guest migration commands (outgoing) */
+ KVM_SEV_SEND_START,
+ KVM_SEV_SEND_UPDATE_DATA,
+ KVM_SEV_SEND_UPDATE_VMSA,
+ KVM_SEV_SEND_FINISH,
+ /* Guest migration commands (incoming) */
+ KVM_SEV_RECEIVE_START,
+ KVM_SEV_RECEIVE_UPDATE_DATA,
+ KVM_SEV_RECEIVE_UPDATE_VMSA,
+ KVM_SEV_RECEIVE_FINISH,
+ /* Guest status and debug commands */
+ KVM_SEV_GUEST_STATUS,
+ KVM_SEV_DBG_DECRYPT,
+ KVM_SEV_DBG_ENCRYPT,
+ /* Guest certificates commands */
+ KVM_SEV_CERT_EXPORT,
+
+ KVM_SEV_NR_MAX,
+};
+
+struct kvm_sev_cmd {
+ __u32 id;
+ __u64 data;
+ __u32 error;
+ __u32 sev_fd;
+};
+
+struct kvm_sev_launch_start {
+ __u32 handle;
+ __u32 policy;
+ __u64 dh_uaddr;
+ __u32 dh_len;
+ __u64 session_uaddr;
+ __u32 session_len;
+};
+
+struct kvm_sev_launch_update_data {
+ __u64 uaddr;
+ __u32 len;
+};
+
+
+struct kvm_sev_launch_secret {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u64 trans_uaddr;
+ __u32 trans_len;
+};
+
+struct kvm_sev_launch_measure {
+ __u64 uaddr;
+ __u32 len;
+};
+
+struct kvm_sev_guest_status {
+ __u32 handle;
+ __u32 policy;
+ __u32 state;
+};
+
+struct kvm_sev_dbg {
+ __u64 src_uaddr;
+ __u64 dst_uaddr;
+ __u32 len;
+};
+
+#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)
+#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1)
+#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2)
+
+struct kvm_assigned_pci_dev {
+ __u32 assigned_dev_id;
+ __u32 busnr;
+ __u32 devfn;
+ __u32 flags;
+ __u32 segnr;
+ union {
+ __u32 reserved[11];
+ };
+};
+
+#define KVM_DEV_IRQ_HOST_INTX (1 << 0)
+#define KVM_DEV_IRQ_HOST_MSI (1 << 1)
+#define KVM_DEV_IRQ_HOST_MSIX (1 << 2)
+
+#define KVM_DEV_IRQ_GUEST_INTX (1 << 8)
+#define KVM_DEV_IRQ_GUEST_MSI (1 << 9)
+#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10)
+
+#define KVM_DEV_IRQ_HOST_MASK 0x00ff
+#define KVM_DEV_IRQ_GUEST_MASK 0xff00
+
+struct kvm_assigned_irq {
+ __u32 assigned_dev_id;
+ __u32 host_irq; /* ignored (legacy field) */
+ __u32 guest_irq;
+ __u32 flags;
+ union {
+ __u32 reserved[12];
+ };
+};
+
+struct kvm_assigned_msix_nr {
+ __u32 assigned_dev_id;
+ __u16 entry_nr;
+ __u16 padding;
+};
+
+#define KVM_MAX_MSIX_PER_DEV 256
+struct kvm_assigned_msix_entry {
+ __u32 assigned_dev_id;
+ __u32 gsi;
+ __u16 entry; /* The index of entry in the MSI-X table */
+ __u16 padding[3];
+};
+
+#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
+
+/* Available with KVM_CAP_ARM_USER_IRQ */
+
+/* Bits for run->s.regs.device_irq_level */
+#define KVM_ARM_DEV_EL1_VTIMER (1 << 0)
+#define KVM_ARM_DEV_EL1_PTIMER (1 << 1)
+#define KVM_ARM_DEV_PMU (1 << 2)
+
+struct kvm_hyperv_eventfd {
+ __u32 conn_id;
+ __s32 fd;
+ __u32 flags;
+ __u32 padding[3];
+};
+
+#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff
+#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0)
+
+#endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/lirc.h b/tools/include/uapi/linux/lirc.h
new file mode 100644
index 0000000..f189931
--- /dev/null
+++ b/tools/include/uapi/linux/lirc.h
@@ -0,0 +1,217 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * lirc.h - linux infrared remote control header file
+ * last modified 2010/07/13 by Jarod Wilson
+ */
+
+#ifndef _LINUX_LIRC_H
+#define _LINUX_LIRC_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define PULSE_BIT 0x01000000
+#define PULSE_MASK 0x00FFFFFF
+
+#define LIRC_MODE2_SPACE 0x00000000
+#define LIRC_MODE2_PULSE 0x01000000
+#define LIRC_MODE2_FREQUENCY 0x02000000
+#define LIRC_MODE2_TIMEOUT 0x03000000
+
+#define LIRC_VALUE_MASK 0x00FFFFFF
+#define LIRC_MODE2_MASK 0xFF000000
+
+#define LIRC_SPACE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_SPACE)
+#define LIRC_PULSE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_PULSE)
+#define LIRC_FREQUENCY(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY)
+#define LIRC_TIMEOUT(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT)
+
+#define LIRC_VALUE(val) ((val)&LIRC_VALUE_MASK)
+#define LIRC_MODE2(val) ((val)&LIRC_MODE2_MASK)
+
+#define LIRC_IS_SPACE(val) (LIRC_MODE2(val) == LIRC_MODE2_SPACE)
+#define LIRC_IS_PULSE(val) (LIRC_MODE2(val) == LIRC_MODE2_PULSE)
+#define LIRC_IS_FREQUENCY(val) (LIRC_MODE2(val) == LIRC_MODE2_FREQUENCY)
+#define LIRC_IS_TIMEOUT(val) (LIRC_MODE2(val) == LIRC_MODE2_TIMEOUT)
+
+/* used heavily by lirc userspace */
+#define lirc_t int
+
+/*** lirc compatible hardware features ***/
+
+#define LIRC_MODE2SEND(x) (x)
+#define LIRC_SEND2MODE(x) (x)
+#define LIRC_MODE2REC(x) ((x) << 16)
+#define LIRC_REC2MODE(x) ((x) >> 16)
+
+#define LIRC_MODE_RAW 0x00000001
+#define LIRC_MODE_PULSE 0x00000002
+#define LIRC_MODE_MODE2 0x00000004
+#define LIRC_MODE_SCANCODE 0x00000008
+#define LIRC_MODE_LIRCCODE 0x00000010
+
+
+#define LIRC_CAN_SEND_RAW LIRC_MODE2SEND(LIRC_MODE_RAW)
+#define LIRC_CAN_SEND_PULSE LIRC_MODE2SEND(LIRC_MODE_PULSE)
+#define LIRC_CAN_SEND_MODE2 LIRC_MODE2SEND(LIRC_MODE_MODE2)
+#define LIRC_CAN_SEND_LIRCCODE LIRC_MODE2SEND(LIRC_MODE_LIRCCODE)
+
+#define LIRC_CAN_SEND_MASK 0x0000003f
+
+#define LIRC_CAN_SET_SEND_CARRIER 0x00000100
+#define LIRC_CAN_SET_SEND_DUTY_CYCLE 0x00000200
+#define LIRC_CAN_SET_TRANSMITTER_MASK 0x00000400
+
+#define LIRC_CAN_REC_RAW LIRC_MODE2REC(LIRC_MODE_RAW)
+#define LIRC_CAN_REC_PULSE LIRC_MODE2REC(LIRC_MODE_PULSE)
+#define LIRC_CAN_REC_MODE2 LIRC_MODE2REC(LIRC_MODE_MODE2)
+#define LIRC_CAN_REC_SCANCODE LIRC_MODE2REC(LIRC_MODE_SCANCODE)
+#define LIRC_CAN_REC_LIRCCODE LIRC_MODE2REC(LIRC_MODE_LIRCCODE)
+
+#define LIRC_CAN_REC_MASK LIRC_MODE2REC(LIRC_CAN_SEND_MASK)
+
+#define LIRC_CAN_SET_REC_CARRIER (LIRC_CAN_SET_SEND_CARRIER << 16)
+#define LIRC_CAN_SET_REC_DUTY_CYCLE (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16)
+
+#define LIRC_CAN_SET_REC_DUTY_CYCLE_RANGE 0x40000000
+#define LIRC_CAN_SET_REC_CARRIER_RANGE 0x80000000
+#define LIRC_CAN_GET_REC_RESOLUTION 0x20000000
+#define LIRC_CAN_SET_REC_TIMEOUT 0x10000000
+#define LIRC_CAN_SET_REC_FILTER 0x08000000
+
+#define LIRC_CAN_MEASURE_CARRIER 0x02000000
+#define LIRC_CAN_USE_WIDEBAND_RECEIVER 0x04000000
+
+#define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK)
+#define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK)
+
+#define LIRC_CAN_NOTIFY_DECODE 0x01000000
+
+/*** IOCTL commands for lirc driver ***/
+
+#define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32)
+
+#define LIRC_GET_SEND_MODE _IOR('i', 0x00000001, __u32)
+#define LIRC_GET_REC_MODE _IOR('i', 0x00000002, __u32)
+#define LIRC_GET_REC_RESOLUTION _IOR('i', 0x00000007, __u32)
+
+#define LIRC_GET_MIN_TIMEOUT _IOR('i', 0x00000008, __u32)
+#define LIRC_GET_MAX_TIMEOUT _IOR('i', 0x00000009, __u32)
+
+/* code length in bits, currently only for LIRC_MODE_LIRCCODE */
+#define LIRC_GET_LENGTH _IOR('i', 0x0000000f, __u32)
+
+#define LIRC_SET_SEND_MODE _IOW('i', 0x00000011, __u32)
+#define LIRC_SET_REC_MODE _IOW('i', 0x00000012, __u32)
+/* Note: these can reset the according pulse_width */
+#define LIRC_SET_SEND_CARRIER _IOW('i', 0x00000013, __u32)
+#define LIRC_SET_REC_CARRIER _IOW('i', 0x00000014, __u32)
+#define LIRC_SET_SEND_DUTY_CYCLE _IOW('i', 0x00000015, __u32)
+#define LIRC_SET_TRANSMITTER_MASK _IOW('i', 0x00000017, __u32)
+
+/*
+ * when a timeout != 0 is set the driver will send a
+ * LIRC_MODE2_TIMEOUT data packet, otherwise LIRC_MODE2_TIMEOUT is
+ * never sent, timeout is disabled by default
+ */
+#define LIRC_SET_REC_TIMEOUT _IOW('i', 0x00000018, __u32)
+
+/* 1 enables, 0 disables timeout reports in MODE2 */
+#define LIRC_SET_REC_TIMEOUT_REPORTS _IOW('i', 0x00000019, __u32)
+
+/*
+ * if enabled from the next key press on the driver will send
+ * LIRC_MODE2_FREQUENCY packets
+ */
+#define LIRC_SET_MEASURE_CARRIER_MODE _IOW('i', 0x0000001d, __u32)
+
+/*
+ * to set a range use LIRC_SET_REC_CARRIER_RANGE with the
+ * lower bound first and later LIRC_SET_REC_CARRIER with the upper bound
+ */
+#define LIRC_SET_REC_CARRIER_RANGE _IOW('i', 0x0000001f, __u32)
+
+#define LIRC_SET_WIDEBAND_RECEIVER _IOW('i', 0x00000023, __u32)
+
+/*
+ * struct lirc_scancode - decoded scancode with protocol for use with
+ * LIRC_MODE_SCANCODE
+ *
+ * @timestamp: Timestamp in nanoseconds using CLOCK_MONOTONIC when IR
+ * was decoded.
+ * @flags: should be 0 for transmit. When receiving scancodes,
+ * LIRC_SCANCODE_FLAG_TOGGLE or LIRC_SCANCODE_FLAG_REPEAT can be set
+ * depending on the protocol
+ * @rc_proto: see enum rc_proto
+ * @keycode: the translated keycode. Set to 0 for transmit.
+ * @scancode: the scancode received or to be sent
+ */
+struct lirc_scancode {
+ __u64 timestamp;
+ __u16 flags;
+ __u16 rc_proto;
+ __u32 keycode;
+ __u64 scancode;
+};
+
+/* Set if the toggle bit of rc-5 or rc-6 is enabled */
+#define LIRC_SCANCODE_FLAG_TOGGLE 1
+/* Set if this is a nec or sanyo repeat */
+#define LIRC_SCANCODE_FLAG_REPEAT 2
+
+/**
+ * enum rc_proto - the Remote Controller protocol
+ *
+ * @RC_PROTO_UNKNOWN: Protocol not known
+ * @RC_PROTO_OTHER: Protocol known but proprietary
+ * @RC_PROTO_RC5: Philips RC5 protocol
+ * @RC_PROTO_RC5X_20: Philips RC5x 20 bit protocol
+ * @RC_PROTO_RC5_SZ: StreamZap variant of RC5
+ * @RC_PROTO_JVC: JVC protocol
+ * @RC_PROTO_SONY12: Sony 12 bit protocol
+ * @RC_PROTO_SONY15: Sony 15 bit protocol
+ * @RC_PROTO_SONY20: Sony 20 bit protocol
+ * @RC_PROTO_NEC: NEC protocol
+ * @RC_PROTO_NECX: Extended NEC protocol
+ * @RC_PROTO_NEC32: NEC 32 bit protocol
+ * @RC_PROTO_SANYO: Sanyo protocol
+ * @RC_PROTO_MCIR2_KBD: RC6-ish MCE keyboard
+ * @RC_PROTO_MCIR2_MSE: RC6-ish MCE mouse
+ * @RC_PROTO_RC6_0: Philips RC6-0-16 protocol
+ * @RC_PROTO_RC6_6A_20: Philips RC6-6A-20 protocol
+ * @RC_PROTO_RC6_6A_24: Philips RC6-6A-24 protocol
+ * @RC_PROTO_RC6_6A_32: Philips RC6-6A-32 protocol
+ * @RC_PROTO_RC6_MCE: MCE (Philips RC6-6A-32 subtype) protocol
+ * @RC_PROTO_SHARP: Sharp protocol
+ * @RC_PROTO_XMP: XMP protocol
+ * @RC_PROTO_CEC: CEC protocol
+ * @RC_PROTO_IMON: iMon Pad protocol
+ */
+enum rc_proto {
+ RC_PROTO_UNKNOWN = 0,
+ RC_PROTO_OTHER = 1,
+ RC_PROTO_RC5 = 2,
+ RC_PROTO_RC5X_20 = 3,
+ RC_PROTO_RC5_SZ = 4,
+ RC_PROTO_JVC = 5,
+ RC_PROTO_SONY12 = 6,
+ RC_PROTO_SONY15 = 7,
+ RC_PROTO_SONY20 = 8,
+ RC_PROTO_NEC = 9,
+ RC_PROTO_NECX = 10,
+ RC_PROTO_NEC32 = 11,
+ RC_PROTO_SANYO = 12,
+ RC_PROTO_MCIR2_KBD = 13,
+ RC_PROTO_MCIR2_MSE = 14,
+ RC_PROTO_RC6_0 = 15,
+ RC_PROTO_RC6_6A_20 = 16,
+ RC_PROTO_RC6_6A_24 = 17,
+ RC_PROTO_RC6_6A_32 = 18,
+ RC_PROTO_RC6_MCE = 19,
+ RC_PROTO_SHARP = 20,
+ RC_PROTO_XMP = 21,
+ RC_PROTO_CEC = 22,
+ RC_PROTO_IMON = 23,
+};
+
+#endif
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
new file mode 100644
index 0000000..bfd5938
--- /dev/null
+++ b/tools/include/uapi/linux/mman.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_MMAN_H
+#define _UAPI_LINUX_MMAN_H
+
+#include <asm/mman.h>
+#include <asm-generic/hugetlb_encode.h>
+
+#define MREMAP_MAYMOVE 1
+#define MREMAP_FIXED 2
+
+#define OVERCOMMIT_GUESS 0
+#define OVERCOMMIT_ALWAYS 1
+#define OVERCOMMIT_NEVER 2
+
+/*
+ * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
+ * size other than the default is desired. See hugetlb_encode.h.
+ * All known huge page size encodings are provided here. It is the
+ * responsibility of the application to know which sizes are supported on
+ * the running system. See mmap(2) man page for details.
+ */
+#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
+#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK
+
+#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB
+#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB
+#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB
+#define MAP_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB
+#define MAP_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB
+#define MAP_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB
+#define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB
+#define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB
+#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB
+#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB
+
+#endif /* _UAPI_LINUX_MMAN_H */
diff --git a/tools/include/uapi/linux/netlink.h b/tools/include/uapi/linux/netlink.h
new file mode 100644
index 0000000..776bc92
--- /dev/null
+++ b/tools/include/uapi/linux/netlink.h
@@ -0,0 +1,251 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI__LINUX_NETLINK_H
+#define _UAPI__LINUX_NETLINK_H
+
+#include <linux/kernel.h>
+#include <linux/socket.h> /* for __kernel_sa_family_t */
+#include <linux/types.h>
+
+#define NETLINK_ROUTE 0 /* Routing/device hook */
+#define NETLINK_UNUSED 1 /* Unused number */
+#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */
+#define NETLINK_FIREWALL 3 /* Unused number, formerly ip_queue */
+#define NETLINK_SOCK_DIAG 4 /* socket monitoring */
+#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */
+#define NETLINK_XFRM 6 /* ipsec */
+#define NETLINK_SELINUX 7 /* SELinux event notifications */
+#define NETLINK_ISCSI 8 /* Open-iSCSI */
+#define NETLINK_AUDIT 9 /* auditing */
+#define NETLINK_FIB_LOOKUP 10
+#define NETLINK_CONNECTOR 11
+#define NETLINK_NETFILTER 12 /* netfilter subsystem */
+#define NETLINK_IP6_FW 13
+#define NETLINK_DNRTMSG 14 /* DECnet routing messages */
+#define NETLINK_KOBJECT_UEVENT 15 /* Kernel messages to userspace */
+#define NETLINK_GENERIC 16
+/* leave room for NETLINK_DM (DM Events) */
+#define NETLINK_SCSITRANSPORT 18 /* SCSI Transports */
+#define NETLINK_ECRYPTFS 19
+#define NETLINK_RDMA 20
+#define NETLINK_CRYPTO 21 /* Crypto layer */
+#define NETLINK_SMC 22 /* SMC monitoring */
+
+#define NETLINK_INET_DIAG NETLINK_SOCK_DIAG
+
+#define MAX_LINKS 32
+
+struct sockaddr_nl {
+ __kernel_sa_family_t nl_family; /* AF_NETLINK */
+ unsigned short nl_pad; /* zero */
+ __u32 nl_pid; /* port ID */
+ __u32 nl_groups; /* multicast groups mask */
+};
+
+struct nlmsghdr {
+ __u32 nlmsg_len; /* Length of message including header */
+ __u16 nlmsg_type; /* Message content */
+ __u16 nlmsg_flags; /* Additional flags */
+ __u32 nlmsg_seq; /* Sequence number */
+ __u32 nlmsg_pid; /* Sending process port ID */
+};
+
+/* Flags values */
+
+#define NLM_F_REQUEST 0x01 /* It is request message. */
+#define NLM_F_MULTI 0x02 /* Multipart message, terminated by NLMSG_DONE */
+#define NLM_F_ACK 0x04 /* Reply with ack, with zero or error code */
+#define NLM_F_ECHO 0x08 /* Echo this request */
+#define NLM_F_DUMP_INTR 0x10 /* Dump was inconsistent due to sequence change */
+#define NLM_F_DUMP_FILTERED 0x20 /* Dump was filtered as requested */
+
+/* Modifiers to GET request */
+#define NLM_F_ROOT 0x100 /* specify tree root */
+#define NLM_F_MATCH 0x200 /* return all matching */
+#define NLM_F_ATOMIC 0x400 /* atomic GET */
+#define NLM_F_DUMP (NLM_F_ROOT|NLM_F_MATCH)
+
+/* Modifiers to NEW request */
+#define NLM_F_REPLACE 0x100 /* Override existing */
+#define NLM_F_EXCL 0x200 /* Do not touch, if it exists */
+#define NLM_F_CREATE 0x400 /* Create, if it does not exist */
+#define NLM_F_APPEND 0x800 /* Add to end of list */
+
+/* Modifiers to DELETE request */
+#define NLM_F_NONREC 0x100 /* Do not delete recursively */
+
+/* Flags for ACK message */
+#define NLM_F_CAPPED 0x100 /* request was capped */
+#define NLM_F_ACK_TLVS 0x200 /* extended ACK TVLs were included */
+
+/*
+ 4.4BSD ADD NLM_F_CREATE|NLM_F_EXCL
+ 4.4BSD CHANGE NLM_F_REPLACE
+
+ True CHANGE NLM_F_CREATE|NLM_F_REPLACE
+ Append NLM_F_CREATE
+ Check NLM_F_EXCL
+ */
+
+#define NLMSG_ALIGNTO 4U
+#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) )
+#define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr)))
+#define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN)
+#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len))
+#define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0)))
+#define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \
+ (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len)))
+#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \
+ (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \
+ (nlh)->nlmsg_len <= (len))
+#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len)))
+
+#define NLMSG_NOOP 0x1 /* Nothing. */
+#define NLMSG_ERROR 0x2 /* Error */
+#define NLMSG_DONE 0x3 /* End of a dump */
+#define NLMSG_OVERRUN 0x4 /* Data lost */
+
+#define NLMSG_MIN_TYPE 0x10 /* < 0x10: reserved control messages */
+
+struct nlmsgerr {
+ int error;
+ struct nlmsghdr msg;
+ /*
+ * followed by the message contents unless NETLINK_CAP_ACK was set
+ * or the ACK indicates success (error == 0)
+ * message length is aligned with NLMSG_ALIGN()
+ */
+ /*
+ * followed by TLVs defined in enum nlmsgerr_attrs
+ * if NETLINK_EXT_ACK was set
+ */
+};
+
+/**
+ * enum nlmsgerr_attrs - nlmsgerr attributes
+ * @NLMSGERR_ATTR_UNUSED: unused
+ * @NLMSGERR_ATTR_MSG: error message string (string)
+ * @NLMSGERR_ATTR_OFFS: offset of the invalid attribute in the original
+ * message, counting from the beginning of the header (u32)
+ * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to
+ * be used - in the success case - to identify a created
+ * object or operation or similar (binary)
+ * @__NLMSGERR_ATTR_MAX: number of attributes
+ * @NLMSGERR_ATTR_MAX: highest attribute number
+ */
+enum nlmsgerr_attrs {
+ NLMSGERR_ATTR_UNUSED,
+ NLMSGERR_ATTR_MSG,
+ NLMSGERR_ATTR_OFFS,
+ NLMSGERR_ATTR_COOKIE,
+
+ __NLMSGERR_ATTR_MAX,
+ NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1
+};
+
+#define NETLINK_ADD_MEMBERSHIP 1
+#define NETLINK_DROP_MEMBERSHIP 2
+#define NETLINK_PKTINFO 3
+#define NETLINK_BROADCAST_ERROR 4
+#define NETLINK_NO_ENOBUFS 5
+#ifndef __KERNEL__
+#define NETLINK_RX_RING 6
+#define NETLINK_TX_RING 7
+#endif
+#define NETLINK_LISTEN_ALL_NSID 8
+#define NETLINK_LIST_MEMBERSHIPS 9
+#define NETLINK_CAP_ACK 10
+#define NETLINK_EXT_ACK 11
+
+struct nl_pktinfo {
+ __u32 group;
+};
+
+struct nl_mmap_req {
+ unsigned int nm_block_size;
+ unsigned int nm_block_nr;
+ unsigned int nm_frame_size;
+ unsigned int nm_frame_nr;
+};
+
+struct nl_mmap_hdr {
+ unsigned int nm_status;
+ unsigned int nm_len;
+ __u32 nm_group;
+ /* credentials */
+ __u32 nm_pid;
+ __u32 nm_uid;
+ __u32 nm_gid;
+};
+
+#ifndef __KERNEL__
+enum nl_mmap_status {
+ NL_MMAP_STATUS_UNUSED,
+ NL_MMAP_STATUS_RESERVED,
+ NL_MMAP_STATUS_VALID,
+ NL_MMAP_STATUS_COPY,
+ NL_MMAP_STATUS_SKIP,
+};
+
+#define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO
+#define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT)
+#define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr))
+#endif
+
+#define NET_MAJOR 36 /* Major 36 is reserved for networking */
+
+enum {
+ NETLINK_UNCONNECTED = 0,
+ NETLINK_CONNECTED,
+};
+
+/*
+ * <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)-->
+ * +---------------------+- - -+- - - - - - - - - -+- - -+
+ * | Header | Pad | Payload | Pad |
+ * | (struct nlattr) | ing | | ing |
+ * +---------------------+- - -+- - - - - - - - - -+- - -+
+ * <-------------- nlattr->nla_len -------------->
+ */
+
+struct nlattr {
+ __u16 nla_len;
+ __u16 nla_type;
+};
+
+/*
+ * nla_type (16 bits)
+ * +---+---+-------------------------------+
+ * | N | O | Attribute Type |
+ * +---+---+-------------------------------+
+ * N := Carries nested attributes
+ * O := Payload stored in network byte order
+ *
+ * Note: The N and O flag are mutually exclusive.
+ */
+#define NLA_F_NESTED (1 << 15)
+#define NLA_F_NET_BYTEORDER (1 << 14)
+#define NLA_TYPE_MASK ~(NLA_F_NESTED | NLA_F_NET_BYTEORDER)
+
+#define NLA_ALIGNTO 4
+#define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1))
+#define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr)))
+
+/* Generic 32 bitflags attribute content sent to the kernel.
+ *
+ * The value is a bitmap that defines the values being set
+ * The selector is a bitmask that defines which value is legit
+ *
+ * Examples:
+ * value = 0x0, and selector = 0x1
+ * implies we are selecting bit 1 and we want to set its value to 0.
+ *
+ * value = 0x2, and selector = 0x2
+ * implies we are selecting bit 2 and we want to set its value to 1.
+ *
+ */
+struct nla_bitfield32 {
+ __u32 value;
+ __u32 selector;
+};
+
+#endif /* _UAPI__LINUX_NETLINK_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
new file mode 100644
index 0000000..f35eb72
--- /dev/null
+++ b/tools/include/uapi/linux/perf_event.h
@@ -0,0 +1,1130 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Performance events:
+ *
+ * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
+ * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
+ *
+ * Data type definitions, declarations, prototypes.
+ *
+ * Started by: Thomas Gleixner and Ingo Molnar
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+#ifndef _UAPI_LINUX_PERF_EVENT_H
+#define _UAPI_LINUX_PERF_EVENT_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+#include <asm/byteorder.h>
+
+/*
+ * User-space ABI bits:
+ */
+
+/*
+ * attr.type
+ */
+enum perf_type_id {
+ PERF_TYPE_HARDWARE = 0,
+ PERF_TYPE_SOFTWARE = 1,
+ PERF_TYPE_TRACEPOINT = 2,
+ PERF_TYPE_HW_CACHE = 3,
+ PERF_TYPE_RAW = 4,
+ PERF_TYPE_BREAKPOINT = 5,
+
+ PERF_TYPE_MAX, /* non-ABI */
+};
+
+/*
+ * Generalized performance event event_id types, used by the
+ * attr.event_id parameter of the sys_perf_event_open()
+ * syscall:
+ */
+enum perf_hw_id {
+ /*
+ * Common hardware events, generalized by the kernel:
+ */
+ PERF_COUNT_HW_CPU_CYCLES = 0,
+ PERF_COUNT_HW_INSTRUCTIONS = 1,
+ PERF_COUNT_HW_CACHE_REFERENCES = 2,
+ PERF_COUNT_HW_CACHE_MISSES = 3,
+ PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4,
+ PERF_COUNT_HW_BRANCH_MISSES = 5,
+ PERF_COUNT_HW_BUS_CYCLES = 6,
+ PERF_COUNT_HW_STALLED_CYCLES_FRONTEND = 7,
+ PERF_COUNT_HW_STALLED_CYCLES_BACKEND = 8,
+ PERF_COUNT_HW_REF_CPU_CYCLES = 9,
+
+ PERF_COUNT_HW_MAX, /* non-ABI */
+};
+
+/*
+ * Generalized hardware cache events:
+ *
+ * { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x
+ * { read, write, prefetch } x
+ * { accesses, misses }
+ */
+enum perf_hw_cache_id {
+ PERF_COUNT_HW_CACHE_L1D = 0,
+ PERF_COUNT_HW_CACHE_L1I = 1,
+ PERF_COUNT_HW_CACHE_LL = 2,
+ PERF_COUNT_HW_CACHE_DTLB = 3,
+ PERF_COUNT_HW_CACHE_ITLB = 4,
+ PERF_COUNT_HW_CACHE_BPU = 5,
+ PERF_COUNT_HW_CACHE_NODE = 6,
+
+ PERF_COUNT_HW_CACHE_MAX, /* non-ABI */
+};
+
+enum perf_hw_cache_op_id {
+ PERF_COUNT_HW_CACHE_OP_READ = 0,
+ PERF_COUNT_HW_CACHE_OP_WRITE = 1,
+ PERF_COUNT_HW_CACHE_OP_PREFETCH = 2,
+
+ PERF_COUNT_HW_CACHE_OP_MAX, /* non-ABI */
+};
+
+enum perf_hw_cache_op_result_id {
+ PERF_COUNT_HW_CACHE_RESULT_ACCESS = 0,
+ PERF_COUNT_HW_CACHE_RESULT_MISS = 1,
+
+ PERF_COUNT_HW_CACHE_RESULT_MAX, /* non-ABI */
+};
+
+/*
+ * Special "software" events provided by the kernel, even if the hardware
+ * does not support performance events. These events measure various
+ * physical and sw events of the kernel (and allow the profiling of them as
+ * well):
+ */
+enum perf_sw_ids {
+ PERF_COUNT_SW_CPU_CLOCK = 0,
+ PERF_COUNT_SW_TASK_CLOCK = 1,
+ PERF_COUNT_SW_PAGE_FAULTS = 2,
+ PERF_COUNT_SW_CONTEXT_SWITCHES = 3,
+ PERF_COUNT_SW_CPU_MIGRATIONS = 4,
+ PERF_COUNT_SW_PAGE_FAULTS_MIN = 5,
+ PERF_COUNT_SW_PAGE_FAULTS_MAJ = 6,
+ PERF_COUNT_SW_ALIGNMENT_FAULTS = 7,
+ PERF_COUNT_SW_EMULATION_FAULTS = 8,
+ PERF_COUNT_SW_DUMMY = 9,
+ PERF_COUNT_SW_BPF_OUTPUT = 10,
+
+ PERF_COUNT_SW_MAX, /* non-ABI */
+};
+
+/*
+ * Bits that can be set in attr.sample_type to request information
+ * in the overflow packets.
+ */
+enum perf_event_sample_format {
+ PERF_SAMPLE_IP = 1U << 0,
+ PERF_SAMPLE_TID = 1U << 1,
+ PERF_SAMPLE_TIME = 1U << 2,
+ PERF_SAMPLE_ADDR = 1U << 3,
+ PERF_SAMPLE_READ = 1U << 4,
+ PERF_SAMPLE_CALLCHAIN = 1U << 5,
+ PERF_SAMPLE_ID = 1U << 6,
+ PERF_SAMPLE_CPU = 1U << 7,
+ PERF_SAMPLE_PERIOD = 1U << 8,
+ PERF_SAMPLE_STREAM_ID = 1U << 9,
+ PERF_SAMPLE_RAW = 1U << 10,
+ PERF_SAMPLE_BRANCH_STACK = 1U << 11,
+ PERF_SAMPLE_REGS_USER = 1U << 12,
+ PERF_SAMPLE_STACK_USER = 1U << 13,
+ PERF_SAMPLE_WEIGHT = 1U << 14,
+ PERF_SAMPLE_DATA_SRC = 1U << 15,
+ PERF_SAMPLE_IDENTIFIER = 1U << 16,
+ PERF_SAMPLE_TRANSACTION = 1U << 17,
+ PERF_SAMPLE_REGS_INTR = 1U << 18,
+ PERF_SAMPLE_PHYS_ADDR = 1U << 19,
+
+ PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */
+
+ __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */
+};
+
+/*
+ * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set
+ *
+ * If the user does not pass priv level information via branch_sample_type,
+ * the kernel uses the event's priv level. Branch and event priv levels do
+ * not have to match. Branch priv level is checked for permissions.
+ *
+ * The branch types can be combined, however BRANCH_ANY covers all types
+ * of branches and therefore it supersedes all the other types.
+ */
+enum perf_branch_sample_type_shift {
+ PERF_SAMPLE_BRANCH_USER_SHIFT = 0, /* user branches */
+ PERF_SAMPLE_BRANCH_KERNEL_SHIFT = 1, /* kernel branches */
+ PERF_SAMPLE_BRANCH_HV_SHIFT = 2, /* hypervisor branches */
+
+ PERF_SAMPLE_BRANCH_ANY_SHIFT = 3, /* any branch types */
+ PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT = 4, /* any call branch */
+ PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT = 5, /* any return branch */
+ PERF_SAMPLE_BRANCH_IND_CALL_SHIFT = 6, /* indirect calls */
+ PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT = 7, /* transaction aborts */
+ PERF_SAMPLE_BRANCH_IN_TX_SHIFT = 8, /* in transaction */
+ PERF_SAMPLE_BRANCH_NO_TX_SHIFT = 9, /* not in transaction */
+ PERF_SAMPLE_BRANCH_COND_SHIFT = 10, /* conditional branches */
+
+ PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* call/ret stack */
+ PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT = 12, /* indirect jumps */
+ PERF_SAMPLE_BRANCH_CALL_SHIFT = 13, /* direct call */
+
+ PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT = 14, /* no flags */
+ PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT = 15, /* no cycles */
+
+ PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT = 16, /* save branch type */
+
+ PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */
+};
+
+enum perf_branch_sample_type {
+ PERF_SAMPLE_BRANCH_USER = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT,
+ PERF_SAMPLE_BRANCH_KERNEL = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT,
+ PERF_SAMPLE_BRANCH_HV = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT,
+
+ PERF_SAMPLE_BRANCH_ANY = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT,
+ PERF_SAMPLE_BRANCH_ANY_CALL = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT,
+ PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT,
+ PERF_SAMPLE_BRANCH_IND_CALL = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT,
+ PERF_SAMPLE_BRANCH_ABORT_TX = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT,
+ PERF_SAMPLE_BRANCH_IN_TX = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT,
+ PERF_SAMPLE_BRANCH_NO_TX = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT,
+ PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT,
+
+ PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT,
+ PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT,
+ PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT,
+
+ PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT,
+ PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT,
+
+ PERF_SAMPLE_BRANCH_TYPE_SAVE =
+ 1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
+
+ PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
+};
+
+/*
+ * Common flow change classification
+ */
+enum {
+ PERF_BR_UNKNOWN = 0, /* unknown */
+ PERF_BR_COND = 1, /* conditional */
+ PERF_BR_UNCOND = 2, /* unconditional */
+ PERF_BR_IND = 3, /* indirect */
+ PERF_BR_CALL = 4, /* function call */
+ PERF_BR_IND_CALL = 5, /* indirect function call */
+ PERF_BR_RET = 6, /* function return */
+ PERF_BR_SYSCALL = 7, /* syscall */
+ PERF_BR_SYSRET = 8, /* syscall return */
+ PERF_BR_COND_CALL = 9, /* conditional function call */
+ PERF_BR_COND_RET = 10, /* conditional function return */
+ PERF_BR_MAX,
+};
+
+#define PERF_SAMPLE_BRANCH_PLM_ALL \
+ (PERF_SAMPLE_BRANCH_USER|\
+ PERF_SAMPLE_BRANCH_KERNEL|\
+ PERF_SAMPLE_BRANCH_HV)
+
+/*
+ * Values to determine ABI of the registers dump.
+ */
+enum perf_sample_regs_abi {
+ PERF_SAMPLE_REGS_ABI_NONE = 0,
+ PERF_SAMPLE_REGS_ABI_32 = 1,
+ PERF_SAMPLE_REGS_ABI_64 = 2,
+};
+
+/*
+ * Values for the memory transaction event qualifier, mostly for
+ * abort events. Multiple bits can be set.
+ */
+enum {
+ PERF_TXN_ELISION = (1 << 0), /* From elision */
+ PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */
+ PERF_TXN_SYNC = (1 << 2), /* Instruction is related */
+ PERF_TXN_ASYNC = (1 << 3), /* Instruction not related */
+ PERF_TXN_RETRY = (1 << 4), /* Retry possible */
+ PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */
+ PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */
+ PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */
+
+ PERF_TXN_MAX = (1 << 8), /* non-ABI */
+
+ /* bits 32..63 are reserved for the abort code */
+
+ PERF_TXN_ABORT_MASK = (0xffffffffULL << 32),
+ PERF_TXN_ABORT_SHIFT = 32,
+};
+
+/*
+ * The format of the data returned by read() on a perf event fd,
+ * as specified by attr.read_format:
+ *
+ * struct read_format {
+ * { u64 value;
+ * { u64 time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ * { u64 id; } && PERF_FORMAT_ID
+ * } && !PERF_FORMAT_GROUP
+ *
+ * { u64 nr;
+ * { u64 time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ * { u64 value;
+ * { u64 id; } && PERF_FORMAT_ID
+ * } cntr[nr];
+ * } && PERF_FORMAT_GROUP
+ * };
+ */
+enum perf_event_read_format {
+ PERF_FORMAT_TOTAL_TIME_ENABLED = 1U << 0,
+ PERF_FORMAT_TOTAL_TIME_RUNNING = 1U << 1,
+ PERF_FORMAT_ID = 1U << 2,
+ PERF_FORMAT_GROUP = 1U << 3,
+
+ PERF_FORMAT_MAX = 1U << 4, /* non-ABI */
+};
+
+#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
+#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
+#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
+#define PERF_ATTR_SIZE_VER3 96 /* add: sample_regs_user */
+ /* add: sample_stack_user */
+#define PERF_ATTR_SIZE_VER4 104 /* add: sample_regs_intr */
+#define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */
+
+/*
+ * Hardware event_id to monitor via a performance monitoring event:
+ *
+ * @sample_max_stack: Max number of frame pointers in a callchain,
+ * should be < /proc/sys/kernel/perf_event_max_stack
+ */
+struct perf_event_attr {
+
+ /*
+ * Major type: hardware/software/tracepoint/etc.
+ */
+ __u32 type;
+
+ /*
+ * Size of the attr structure, for fwd/bwd compat.
+ */
+ __u32 size;
+
+ /*
+ * Type specific configuration information.
+ */
+ __u64 config;
+
+ union {
+ __u64 sample_period;
+ __u64 sample_freq;
+ };
+
+ __u64 sample_type;
+ __u64 read_format;
+
+ __u64 disabled : 1, /* off by default */
+ inherit : 1, /* children inherit it */
+ pinned : 1, /* must always be on PMU */
+ exclusive : 1, /* only group on PMU */
+ exclude_user : 1, /* don't count user */
+ exclude_kernel : 1, /* ditto kernel */
+ exclude_hv : 1, /* ditto hypervisor */
+ exclude_idle : 1, /* don't count when idle */
+ mmap : 1, /* include mmap data */
+ comm : 1, /* include comm data */
+ freq : 1, /* use freq, not period */
+ inherit_stat : 1, /* per task counts */
+ enable_on_exec : 1, /* next exec enables */
+ task : 1, /* trace fork/exit */
+ watermark : 1, /* wakeup_watermark */
+ /*
+ * precise_ip:
+ *
+ * 0 - SAMPLE_IP can have arbitrary skid
+ * 1 - SAMPLE_IP must have constant skid
+ * 2 - SAMPLE_IP requested to have 0 skid
+ * 3 - SAMPLE_IP must have 0 skid
+ *
+ * See also PERF_RECORD_MISC_EXACT_IP
+ */
+ precise_ip : 2, /* skid constraint */
+ mmap_data : 1, /* non-exec mmap data */
+ sample_id_all : 1, /* sample_type all events */
+
+ exclude_host : 1, /* don't count in host */
+ exclude_guest : 1, /* don't count in guest */
+
+ exclude_callchain_kernel : 1, /* exclude kernel callchains */
+ exclude_callchain_user : 1, /* exclude user callchains */
+ mmap2 : 1, /* include mmap with inode data */
+ comm_exec : 1, /* flag comm events that are due to an exec */
+ use_clockid : 1, /* use @clockid for time fields */
+ context_switch : 1, /* context switch data */
+ write_backward : 1, /* Write ring buffer from end to beginning */
+ namespaces : 1, /* include namespaces data */
+ __reserved_1 : 35;
+
+ union {
+ __u32 wakeup_events; /* wakeup every n events */
+ __u32 wakeup_watermark; /* bytes before wakeup */
+ };
+
+ __u32 bp_type;
+ union {
+ __u64 bp_addr;
+ __u64 kprobe_func; /* for perf_kprobe */
+ __u64 uprobe_path; /* for perf_uprobe */
+ __u64 config1; /* extension of config */
+ };
+ union {
+ __u64 bp_len;
+ __u64 kprobe_addr; /* when kprobe_func == NULL */
+ __u64 probe_offset; /* for perf_[k,u]probe */
+ __u64 config2; /* extension of config1 */
+ };
+ __u64 branch_sample_type; /* enum perf_branch_sample_type */
+
+ /*
+ * Defines set of user regs to dump on samples.
+ * See asm/perf_regs.h for details.
+ */
+ __u64 sample_regs_user;
+
+ /*
+ * Defines size of the user stack to dump on samples.
+ */
+ __u32 sample_stack_user;
+
+ __s32 clockid;
+ /*
+ * Defines set of regs to dump for each sample
+ * state captured on:
+ * - precise = 0: PMU interrupt
+ * - precise > 0: sampled instruction
+ *
+ * See asm/perf_regs.h for details.
+ */
+ __u64 sample_regs_intr;
+
+ /*
+ * Wakeup watermark for AUX area
+ */
+ __u32 aux_watermark;
+ __u16 sample_max_stack;
+ __u16 __reserved_2; /* align to __u64 */
+};
+
+/*
+ * Structure used by below PERF_EVENT_IOC_QUERY_BPF command
+ * to query bpf programs attached to the same perf tracepoint
+ * as the given perf event.
+ */
+struct perf_event_query_bpf {
+ /*
+ * The below ids array length
+ */
+ __u32 ids_len;
+ /*
+ * Set by the kernel to indicate the number of
+ * available programs
+ */
+ __u32 prog_cnt;
+ /*
+ * User provided buffer to store program ids
+ */
+ __u32 ids[0];
+};
+
+#define perf_flags(attr) (*(&(attr)->read_format + 1))
+
+/*
+ * Ioctls that can be done on a perf event fd:
+ */
+#define PERF_EVENT_IOC_ENABLE _IO ('$', 0)
+#define PERF_EVENT_IOC_DISABLE _IO ('$', 1)
+#define PERF_EVENT_IOC_REFRESH _IO ('$', 2)
+#define PERF_EVENT_IOC_RESET _IO ('$', 3)
+#define PERF_EVENT_IOC_PERIOD _IOW('$', 4, __u64)
+#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5)
+#define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *)
+#define PERF_EVENT_IOC_ID _IOR('$', 7, __u64 *)
+#define PERF_EVENT_IOC_SET_BPF _IOW('$', 8, __u32)
+#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW('$', 9, __u32)
+#define PERF_EVENT_IOC_QUERY_BPF _IOWR('$', 10, struct perf_event_query_bpf *)
+#define PERF_EVENT_IOC_MODIFY_ATTRIBUTES _IOW('$', 11, struct perf_event_attr *)
+
+enum perf_event_ioc_flags {
+ PERF_IOC_FLAG_GROUP = 1U << 0,
+};
+
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_event_mmap_page {
+ __u32 version; /* version number of this structure */
+ __u32 compat_version; /* lowest version this is compat with */
+
+ /*
+ * Bits needed to read the hw events in user-space.
+ *
+ * u32 seq, time_mult, time_shift, index, width;
+ * u64 count, enabled, running;
+ * u64 cyc, time_offset;
+ * s64 pmc = 0;
+ *
+ * do {
+ * seq = pc->lock;
+ * barrier()
+ *
+ * enabled = pc->time_enabled;
+ * running = pc->time_running;
+ *
+ * if (pc->cap_usr_time && enabled != running) {
+ * cyc = rdtsc();
+ * time_offset = pc->time_offset;
+ * time_mult = pc->time_mult;
+ * time_shift = pc->time_shift;
+ * }
+ *
+ * index = pc->index;
+ * count = pc->offset;
+ * if (pc->cap_user_rdpmc && index) {
+ * width = pc->pmc_width;
+ * pmc = rdpmc(index - 1);
+ * }
+ *
+ * barrier();
+ * } while (pc->lock != seq);
+ *
+ * NOTE: for obvious reason this only works on self-monitoring
+ * processes.
+ */
+ __u32 lock; /* seqlock for synchronization */
+ __u32 index; /* hardware event identifier */
+ __s64 offset; /* add to hardware event value */
+ __u64 time_enabled; /* time event active */
+ __u64 time_running; /* time event on cpu */
+ union {
+ __u64 capabilities;
+ struct {
+ __u64 cap_bit0 : 1, /* Always 0, deprecated, see commit 860f085b74e9 */
+ cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */
+
+ cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */
+ cap_user_time : 1, /* The time_* fields are used */
+ cap_user_time_zero : 1, /* The time_zero field is used */
+ cap_____res : 59;
+ };
+ };
+
+ /*
+ * If cap_user_rdpmc this field provides the bit-width of the value
+ * read using the rdpmc() or equivalent instruction. This can be used
+ * to sign extend the result like:
+ *
+ * pmc <<= 64 - width;
+ * pmc >>= 64 - width; // signed shift right
+ * count += pmc;
+ */
+ __u16 pmc_width;
+
+ /*
+ * If cap_usr_time the below fields can be used to compute the time
+ * delta since time_enabled (in ns) using rdtsc or similar.
+ *
+ * u64 quot, rem;
+ * u64 delta;
+ *
+ * quot = (cyc >> time_shift);
+ * rem = cyc & (((u64)1 << time_shift) - 1);
+ * delta = time_offset + quot * time_mult +
+ * ((rem * time_mult) >> time_shift);
+ *
+ * Where time_offset,time_mult,time_shift and cyc are read in the
+ * seqcount loop described above. This delta can then be added to
+ * enabled and possible running (if index), improving the scaling:
+ *
+ * enabled += delta;
+ * if (index)
+ * running += delta;
+ *
+ * quot = count / running;
+ * rem = count % running;
+ * count = quot * enabled + (rem * enabled) / running;
+ */
+ __u16 time_shift;
+ __u32 time_mult;
+ __u64 time_offset;
+ /*
+ * If cap_usr_time_zero, the hardware clock (e.g. TSC) can be calculated
+ * from sample timestamps.
+ *
+ * time = timestamp - time_zero;
+ * quot = time / time_mult;
+ * rem = time % time_mult;
+ * cyc = (quot << time_shift) + (rem << time_shift) / time_mult;
+ *
+ * And vice versa:
+ *
+ * quot = cyc >> time_shift;
+ * rem = cyc & (((u64)1 << time_shift) - 1);
+ * timestamp = time_zero + quot * time_mult +
+ * ((rem * time_mult) >> time_shift);
+ */
+ __u64 time_zero;
+ __u32 size; /* Header size up to __reserved[] fields. */
+
+ /*
+ * Hole for extension of the self monitor capabilities
+ */
+
+ __u8 __reserved[118*8+4]; /* align to 1k. */
+
+ /*
+ * Control data for the mmap() data buffer.
+ *
+ * User-space reading the @data_head value should issue an smp_rmb(),
+ * after reading this value.
+ *
+ * When the mapping is PROT_WRITE the @data_tail value should be
+ * written by userspace to reflect the last read data, after issueing
+ * an smp_mb() to separate the data read from the ->data_tail store.
+ * In this case the kernel will not over-write unread data.
+ *
+ * See perf_output_put_handle() for the data ordering.
+ *
+ * data_{offset,size} indicate the location and size of the perf record
+ * buffer within the mmapped area.
+ */
+ __u64 data_head; /* head in the data section */
+ __u64 data_tail; /* user-space written tail */
+ __u64 data_offset; /* where the buffer starts */
+ __u64 data_size; /* data buffer size */
+
+ /*
+ * AUX area is defined by aux_{offset,size} fields that should be set
+ * by the userspace, so that
+ *
+ * aux_offset >= data_offset + data_size
+ *
+ * prior to mmap()ing it. Size of the mmap()ed area should be aux_size.
+ *
+ * Ring buffer pointers aux_{head,tail} have the same semantics as
+ * data_{head,tail} and same ordering rules apply.
+ */
+ __u64 aux_head;
+ __u64 aux_tail;
+ __u64 aux_offset;
+ __u64 aux_size;
+};
+
+#define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0)
+#define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0)
+#define PERF_RECORD_MISC_KERNEL (1 << 0)
+#define PERF_RECORD_MISC_USER (2 << 0)
+#define PERF_RECORD_MISC_HYPERVISOR (3 << 0)
+#define PERF_RECORD_MISC_GUEST_KERNEL (4 << 0)
+#define PERF_RECORD_MISC_GUEST_USER (5 << 0)
+
+/*
+ * Indicates that /proc/PID/maps parsing are truncated by time out.
+ */
+#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT (1 << 12)
+/*
+ * Following PERF_RECORD_MISC_* are used on different
+ * events, so can reuse the same bit position:
+ *
+ * PERF_RECORD_MISC_MMAP_DATA - PERF_RECORD_MMAP* events
+ * PERF_RECORD_MISC_COMM_EXEC - PERF_RECORD_COMM event
+ * PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
+ */
+#define PERF_RECORD_MISC_MMAP_DATA (1 << 13)
+#define PERF_RECORD_MISC_COMM_EXEC (1 << 13)
+#define PERF_RECORD_MISC_SWITCH_OUT (1 << 13)
+/*
+ * These PERF_RECORD_MISC_* flags below are safely reused
+ * for the following events:
+ *
+ * PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ *
+ *
+ * PERF_RECORD_MISC_EXACT_IP:
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ *
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
+ * Indicates that thread was preempted in TASK_RUNNING state.
+ */
+#define PERF_RECORD_MISC_EXACT_IP (1 << 14)
+#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14)
+/*
+ * Reserve the last bit to indicate some extended misc field
+ */
+#define PERF_RECORD_MISC_EXT_RESERVED (1 << 15)
+
+struct perf_event_header {
+ __u32 type;
+ __u16 misc;
+ __u16 size;
+};
+
+struct perf_ns_link_info {
+ __u64 dev;
+ __u64 ino;
+};
+
+enum {
+ NET_NS_INDEX = 0,
+ UTS_NS_INDEX = 1,
+ IPC_NS_INDEX = 2,
+ PID_NS_INDEX = 3,
+ USER_NS_INDEX = 4,
+ MNT_NS_INDEX = 5,
+ CGROUP_NS_INDEX = 6,
+
+ NR_NAMESPACES, /* number of available namespaces */
+};
+
+enum perf_event_type {
+
+ /*
+ * If perf_event_attr.sample_id_all is set then all event types will
+ * have the sample_type selected fields related to where/when
+ * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU,
+ * IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed
+ * just after the perf_event_header and the fields already present for
+ * the existing fields, i.e. at the end of the payload. That way a newer
+ * perf.data file will be supported by older perf tools, with these new
+ * optional fields being ignored.
+ *
+ * struct sample_id {
+ * { u32 pid, tid; } && PERF_SAMPLE_TID
+ * { u64 time; } && PERF_SAMPLE_TIME
+ * { u64 id; } && PERF_SAMPLE_ID
+ * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID
+ * { u32 cpu, res; } && PERF_SAMPLE_CPU
+ * { u64 id; } && PERF_SAMPLE_IDENTIFIER
+ * } && perf_event_attr::sample_id_all
+ *
+ * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID. The
+ * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed
+ * relative to header.size.
+ */
+
+ /*
+ * The MMAP events record the PROT_EXEC mappings so that we can
+ * correlate userspace IPs to code. They have the following structure:
+ *
+ * struct {
+ * struct perf_event_header header;
+ *
+ * u32 pid, tid;
+ * u64 addr;
+ * u64 len;
+ * u64 pgoff;
+ * char filename[];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_MMAP = 1,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u64 id;
+ * u64 lost;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_LOST = 2,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ *
+ * u32 pid, tid;
+ * char comm[];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_COMM = 3,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u32 pid, ppid;
+ * u32 tid, ptid;
+ * u64 time;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_EXIT = 4,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u64 time;
+ * u64 id;
+ * u64 stream_id;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_THROTTLE = 5,
+ PERF_RECORD_UNTHROTTLE = 6,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u32 pid, ppid;
+ * u32 tid, ptid;
+ * u64 time;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_FORK = 7,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u32 pid, tid;
+ *
+ * struct read_format values;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_READ = 8,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ *
+ * #
+ * # Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.
+ * # The advantage of PERF_SAMPLE_IDENTIFIER is that its position
+ * # is fixed relative to header.
+ * #
+ *
+ * { u64 id; } && PERF_SAMPLE_IDENTIFIER
+ * { u64 ip; } && PERF_SAMPLE_IP
+ * { u32 pid, tid; } && PERF_SAMPLE_TID
+ * { u64 time; } && PERF_SAMPLE_TIME
+ * { u64 addr; } && PERF_SAMPLE_ADDR
+ * { u64 id; } && PERF_SAMPLE_ID
+ * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID
+ * { u32 cpu, res; } && PERF_SAMPLE_CPU
+ * { u64 period; } && PERF_SAMPLE_PERIOD
+ *
+ * { struct read_format values; } && PERF_SAMPLE_READ
+ *
+ * { u64 nr,
+ * u64 ips[nr]; } && PERF_SAMPLE_CALLCHAIN
+ *
+ * #
+ * # The RAW record below is opaque data wrt the ABI
+ * #
+ * # That is, the ABI doesn't make any promises wrt to
+ * # the stability of its content, it may vary depending
+ * # on event, hardware, kernel version and phase of
+ * # the moon.
+ * #
+ * # In other words, PERF_SAMPLE_RAW contents are not an ABI.
+ * #
+ *
+ * { u32 size;
+ * char data[size];}&& PERF_SAMPLE_RAW
+ *
+ * { u64 nr;
+ * { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+ *
+ * { u64 abi; # enum perf_sample_regs_abi
+ * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
+ *
+ * { u64 size;
+ * char data[size];
+ * u64 dyn_size; } && PERF_SAMPLE_STACK_USER
+ *
+ * { u64 weight; } && PERF_SAMPLE_WEIGHT
+ * { u64 data_src; } && PERF_SAMPLE_DATA_SRC
+ * { u64 transaction; } && PERF_SAMPLE_TRANSACTION
+ * { u64 abi; # enum perf_sample_regs_abi
+ * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
+ * { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR
+ * };
+ */
+ PERF_RECORD_SAMPLE = 9,
+
+ /*
+ * The MMAP2 records are an augmented version of MMAP, they add
+ * maj, min, ino numbers to be used to uniquely identify each mapping
+ *
+ * struct {
+ * struct perf_event_header header;
+ *
+ * u32 pid, tid;
+ * u64 addr;
+ * u64 len;
+ * u64 pgoff;
+ * u32 maj;
+ * u32 min;
+ * u64 ino;
+ * u64 ino_generation;
+ * u32 prot, flags;
+ * char filename[];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_MMAP2 = 10,
+
+ /*
+ * Records that new data landed in the AUX buffer part.
+ *
+ * struct {
+ * struct perf_event_header header;
+ *
+ * u64 aux_offset;
+ * u64 aux_size;
+ * u64 flags;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_AUX = 11,
+
+ /*
+ * Indicates that instruction trace has started
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u32 pid;
+ * u32 tid;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_ITRACE_START = 12,
+
+ /*
+ * Records the dropped/lost sample number.
+ *
+ * struct {
+ * struct perf_event_header header;
+ *
+ * u64 lost;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_LOST_SAMPLES = 13,
+
+ /*
+ * Records a context switch in or out (flagged by
+ * PERF_RECORD_MISC_SWITCH_OUT). See also
+ * PERF_RECORD_SWITCH_CPU_WIDE.
+ *
+ * struct {
+ * struct perf_event_header header;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_SWITCH = 14,
+
+ /*
+ * CPU-wide version of PERF_RECORD_SWITCH with next_prev_pid and
+ * next_prev_tid that are the next (switching out) or previous
+ * (switching in) pid/tid.
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u32 next_prev_pid;
+ * u32 next_prev_tid;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_SWITCH_CPU_WIDE = 15,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u32 pid;
+ * u32 tid;
+ * u64 nr_namespaces;
+ * { u64 dev, inode; } [nr_namespaces];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_NAMESPACES = 16,
+
+ PERF_RECORD_MAX, /* non-ABI */
+};
+
+#define PERF_MAX_STACK_DEPTH 127
+#define PERF_MAX_CONTEXTS_PER_STACK 8
+
+enum perf_callchain_context {
+ PERF_CONTEXT_HV = (__u64)-32,
+ PERF_CONTEXT_KERNEL = (__u64)-128,
+ PERF_CONTEXT_USER = (__u64)-512,
+
+ PERF_CONTEXT_GUEST = (__u64)-2048,
+ PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176,
+ PERF_CONTEXT_GUEST_USER = (__u64)-2560,
+
+ PERF_CONTEXT_MAX = (__u64)-4095,
+};
+
+/**
+ * PERF_RECORD_AUX::flags bits
+ */
+#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */
+#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */
+#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */
+#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */
+
+#define PERF_FLAG_FD_NO_GROUP (1UL << 0)
+#define PERF_FLAG_FD_OUTPUT (1UL << 1)
+#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */
+#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */
+
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+union perf_mem_data_src {
+ __u64 val;
+ struct {
+ __u64 mem_op:5, /* type of opcode */
+ mem_lvl:14, /* memory hierarchy level */
+ mem_snoop:5, /* snoop mode */
+ mem_lock:2, /* lock instr */
+ mem_dtlb:7, /* tlb access */
+ mem_lvl_num:4, /* memory hierarchy level number */
+ mem_remote:1, /* remote */
+ mem_snoopx:2, /* snoop mode, ext */
+ mem_rsvd:24;
+ };
+};
+#elif defined(__BIG_ENDIAN_BITFIELD)
+union perf_mem_data_src {
+ __u64 val;
+ struct {
+ __u64 mem_rsvd:24,
+ mem_snoopx:2, /* snoop mode, ext */
+ mem_remote:1, /* remote */
+ mem_lvl_num:4, /* memory hierarchy level number */
+ mem_dtlb:7, /* tlb access */
+ mem_lock:2, /* lock instr */
+ mem_snoop:5, /* snoop mode */
+ mem_lvl:14, /* memory hierarchy level */
+ mem_op:5; /* type of opcode */
+ };
+};
+#else
+#error "Unknown endianness"
+#endif
+
+/* type of opcode (load/store/prefetch,code) */
+#define PERF_MEM_OP_NA 0x01 /* not available */
+#define PERF_MEM_OP_LOAD 0x02 /* load instruction */
+#define PERF_MEM_OP_STORE 0x04 /* store instruction */
+#define PERF_MEM_OP_PFETCH 0x08 /* prefetch */
+#define PERF_MEM_OP_EXEC 0x10 /* code (execution) */
+#define PERF_MEM_OP_SHIFT 0
+
+/* memory hierarchy (memory level, hit or miss) */
+#define PERF_MEM_LVL_NA 0x01 /* not available */
+#define PERF_MEM_LVL_HIT 0x02 /* hit level */
+#define PERF_MEM_LVL_MISS 0x04 /* miss level */
+#define PERF_MEM_LVL_L1 0x08 /* L1 */
+#define PERF_MEM_LVL_LFB 0x10 /* Line Fill Buffer */
+#define PERF_MEM_LVL_L2 0x20 /* L2 */
+#define PERF_MEM_LVL_L3 0x40 /* L3 */
+#define PERF_MEM_LVL_LOC_RAM 0x80 /* Local DRAM */
+#define PERF_MEM_LVL_REM_RAM1 0x100 /* Remote DRAM (1 hop) */
+#define PERF_MEM_LVL_REM_RAM2 0x200 /* Remote DRAM (2 hops) */
+#define PERF_MEM_LVL_REM_CCE1 0x400 /* Remote Cache (1 hop) */
+#define PERF_MEM_LVL_REM_CCE2 0x800 /* Remote Cache (2 hops) */
+#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */
+#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */
+#define PERF_MEM_LVL_SHIFT 5
+
+#define PERF_MEM_REMOTE_REMOTE 0x01 /* Remote */
+#define PERF_MEM_REMOTE_SHIFT 37
+
+#define PERF_MEM_LVLNUM_L1 0x01 /* L1 */
+#define PERF_MEM_LVLNUM_L2 0x02 /* L2 */
+#define PERF_MEM_LVLNUM_L3 0x03 /* L3 */
+#define PERF_MEM_LVLNUM_L4 0x04 /* L4 */
+/* 5-0xa available */
+#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
+#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */
+#define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */
+#define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */
+#define PERF_MEM_LVLNUM_NA 0x0f /* N/A */
+
+#define PERF_MEM_LVLNUM_SHIFT 33
+
+/* snoop mode */
+#define PERF_MEM_SNOOP_NA 0x01 /* not available */
+#define PERF_MEM_SNOOP_NONE 0x02 /* no snoop */
+#define PERF_MEM_SNOOP_HIT 0x04 /* snoop hit */
+#define PERF_MEM_SNOOP_MISS 0x08 /* snoop miss */
+#define PERF_MEM_SNOOP_HITM 0x10 /* snoop hit modified */
+#define PERF_MEM_SNOOP_SHIFT 19
+
+#define PERF_MEM_SNOOPX_FWD 0x01 /* forward */
+/* 1 free */
+#define PERF_MEM_SNOOPX_SHIFT 37
+
+/* locked instruction */
+#define PERF_MEM_LOCK_NA 0x01 /* not available */
+#define PERF_MEM_LOCK_LOCKED 0x02 /* locked transaction */
+#define PERF_MEM_LOCK_SHIFT 24
+
+/* TLB access */
+#define PERF_MEM_TLB_NA 0x01 /* not available */
+#define PERF_MEM_TLB_HIT 0x02 /* hit level */
+#define PERF_MEM_TLB_MISS 0x04 /* miss level */
+#define PERF_MEM_TLB_L1 0x08 /* L1 */
+#define PERF_MEM_TLB_L2 0x10 /* L2 */
+#define PERF_MEM_TLB_WK 0x20 /* Hardware Walker*/
+#define PERF_MEM_TLB_OS 0x40 /* OS fault handler */
+#define PERF_MEM_TLB_SHIFT 26
+
+#define PERF_MEM_S(a, s) \
+ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
+
+/*
+ * single taken branch record layout:
+ *
+ * from: source instruction (may not always be a branch insn)
+ * to: branch target
+ * mispred: branch target was mispredicted
+ * predicted: branch target was predicted
+ *
+ * support for mispred, predicted is optional. In case it
+ * is not supported mispred = predicted = 0.
+ *
+ * in_tx: running in a hardware transaction
+ * abort: aborting a hardware transaction
+ * cycles: cycles from last branch (or 0 if not supported)
+ * type: branch type
+ */
+struct perf_branch_entry {
+ __u64 from;
+ __u64 to;
+ __u64 mispred:1, /* target mispredicted */
+ predicted:1,/* target predicted */
+ in_tx:1, /* in transaction */
+ abort:1, /* transaction abort */
+ cycles:16, /* cycle count to last branch */
+ type:4, /* branch type */
+ reserved:40;
+};
+
+#endif /* _UAPI_LINUX_PERF_EVENT_H */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
new file mode 100644
index 0000000..b17201e
--- /dev/null
+++ b/tools/include/uapi/linux/prctl.h
@@ -0,0 +1,223 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_PRCTL_H
+#define _LINUX_PRCTL_H
+
+#include <linux/types.h>
+
+/* Values to pass as first argument to prctl() */
+
+#define PR_SET_PDEATHSIG 1 /* Second arg is a signal */
+#define PR_GET_PDEATHSIG 2 /* Second arg is a ptr to return the signal */
+
+/* Get/set current->mm->dumpable */
+#define PR_GET_DUMPABLE 3
+#define PR_SET_DUMPABLE 4
+
+/* Get/set unaligned access control bits (if meaningful) */
+#define PR_GET_UNALIGN 5
+#define PR_SET_UNALIGN 6
+# define PR_UNALIGN_NOPRINT 1 /* silently fix up unaligned user accesses */
+# define PR_UNALIGN_SIGBUS 2 /* generate SIGBUS on unaligned user access */
+
+/* Get/set whether or not to drop capabilities on setuid() away from
+ * uid 0 (as per security/commoncap.c) */
+#define PR_GET_KEEPCAPS 7
+#define PR_SET_KEEPCAPS 8
+
+/* Get/set floating-point emulation control bits (if meaningful) */
+#define PR_GET_FPEMU 9
+#define PR_SET_FPEMU 10
+# define PR_FPEMU_NOPRINT 1 /* silently emulate fp operations accesses */
+# define PR_FPEMU_SIGFPE 2 /* don't emulate fp operations, send SIGFPE instead */
+
+/* Get/set floating-point exception mode (if meaningful) */
+#define PR_GET_FPEXC 11
+#define PR_SET_FPEXC 12
+# define PR_FP_EXC_SW_ENABLE 0x80 /* Use FPEXC for FP exception enables */
+# define PR_FP_EXC_DIV 0x010000 /* floating point divide by zero */
+# define PR_FP_EXC_OVF 0x020000 /* floating point overflow */
+# define PR_FP_EXC_UND 0x040000 /* floating point underflow */
+# define PR_FP_EXC_RES 0x080000 /* floating point inexact result */
+# define PR_FP_EXC_INV 0x100000 /* floating point invalid operation */
+# define PR_FP_EXC_DISABLED 0 /* FP exceptions disabled */
+# define PR_FP_EXC_NONRECOV 1 /* async non-recoverable exc. mode */
+# define PR_FP_EXC_ASYNC 2 /* async recoverable exception mode */
+# define PR_FP_EXC_PRECISE 3 /* precise exception mode */
+
+/* Get/set whether we use statistical process timing or accurate timestamp
+ * based process timing */
+#define PR_GET_TIMING 13
+#define PR_SET_TIMING 14
+# define PR_TIMING_STATISTICAL 0 /* Normal, traditional,
+ statistical process timing */
+# define PR_TIMING_TIMESTAMP 1 /* Accurate timestamp based
+ process timing */
+
+#define PR_SET_NAME 15 /* Set process name */
+#define PR_GET_NAME 16 /* Get process name */
+
+/* Get/set process endian */
+#define PR_GET_ENDIAN 19
+#define PR_SET_ENDIAN 20
+# define PR_ENDIAN_BIG 0
+# define PR_ENDIAN_LITTLE 1 /* True little endian mode */
+# define PR_ENDIAN_PPC_LITTLE 2 /* "PowerPC" pseudo little endian */
+
+/* Get/set process seccomp mode */
+#define PR_GET_SECCOMP 21
+#define PR_SET_SECCOMP 22
+
+/* Get/set the capability bounding set (as per security/commoncap.c) */
+#define PR_CAPBSET_READ 23
+#define PR_CAPBSET_DROP 24
+
+/* Get/set the process' ability to use the timestamp counter instruction */
+#define PR_GET_TSC 25
+#define PR_SET_TSC 26
+# define PR_TSC_ENABLE 1 /* allow the use of the timestamp counter */
+# define PR_TSC_SIGSEGV 2 /* throw a SIGSEGV instead of reading the TSC */
+
+/* Get/set securebits (as per security/commoncap.c) */
+#define PR_GET_SECUREBITS 27
+#define PR_SET_SECUREBITS 28
+
+/*
+ * Get/set the timerslack as used by poll/select/nanosleep
+ * A value of 0 means "use default"
+ */
+#define PR_SET_TIMERSLACK 29
+#define PR_GET_TIMERSLACK 30
+
+#define PR_TASK_PERF_EVENTS_DISABLE 31
+#define PR_TASK_PERF_EVENTS_ENABLE 32
+
+/*
+ * Set early/late kill mode for hwpoison memory corruption.
+ * This influences when the process gets killed on a memory corruption.
+ */
+#define PR_MCE_KILL 33
+# define PR_MCE_KILL_CLEAR 0
+# define PR_MCE_KILL_SET 1
+
+# define PR_MCE_KILL_LATE 0
+# define PR_MCE_KILL_EARLY 1
+# define PR_MCE_KILL_DEFAULT 2
+
+#define PR_MCE_KILL_GET 34
+
+/*
+ * Tune up process memory map specifics.
+ */
+#define PR_SET_MM 35
+# define PR_SET_MM_START_CODE 1
+# define PR_SET_MM_END_CODE 2
+# define PR_SET_MM_START_DATA 3
+# define PR_SET_MM_END_DATA 4
+# define PR_SET_MM_START_STACK 5
+# define PR_SET_MM_START_BRK 6
+# define PR_SET_MM_BRK 7
+# define PR_SET_MM_ARG_START 8
+# define PR_SET_MM_ARG_END 9
+# define PR_SET_MM_ENV_START 10
+# define PR_SET_MM_ENV_END 11
+# define PR_SET_MM_AUXV 12
+# define PR_SET_MM_EXE_FILE 13
+# define PR_SET_MM_MAP 14
+# define PR_SET_MM_MAP_SIZE 15
+
+/*
+ * This structure provides new memory descriptor
+ * map which mostly modifies /proc/pid/stat[m]
+ * output for a task. This mostly done in a
+ * sake of checkpoint/restore functionality.
+ */
+struct prctl_mm_map {
+ __u64 start_code; /* code section bounds */
+ __u64 end_code;
+ __u64 start_data; /* data section bounds */
+ __u64 end_data;
+ __u64 start_brk; /* heap for brk() syscall */
+ __u64 brk;
+ __u64 start_stack; /* stack starts at */
+ __u64 arg_start; /* command line arguments bounds */
+ __u64 arg_end;
+ __u64 env_start; /* environment variables bounds */
+ __u64 env_end;
+ __u64 *auxv; /* auxiliary vector */
+ __u32 auxv_size; /* vector size */
+ __u32 exe_fd; /* /proc/$pid/exe link file */
+};
+
+/*
+ * Set specific pid that is allowed to ptrace the current task.
+ * A value of 0 mean "no process".
+ */
+#define PR_SET_PTRACER 0x59616d61
+# define PR_SET_PTRACER_ANY ((unsigned long)-1)
+
+#define PR_SET_CHILD_SUBREAPER 36
+#define PR_GET_CHILD_SUBREAPER 37
+
+/*
+ * If no_new_privs is set, then operations that grant new privileges (i.e.
+ * execve) will either fail or not grant them. This affects suid/sgid,
+ * file capabilities, and LSMs.
+ *
+ * Operations that merely manipulate or drop existing privileges (setresuid,
+ * capset, etc.) will still work. Drop those privileges if you want them gone.
+ *
+ * Changing LSM security domain is considered a new privilege. So, for example,
+ * asking selinux for a specific new context (e.g. with runcon) will result
+ * in execve returning -EPERM.
+ *
+ * See Documentation/userspace-api/no_new_privs.rst for more details.
+ */
+#define PR_SET_NO_NEW_PRIVS 38
+#define PR_GET_NO_NEW_PRIVS 39
+
+#define PR_GET_TID_ADDRESS 40
+
+#define PR_SET_THP_DISABLE 41
+#define PR_GET_THP_DISABLE 42
+
+/*
+ * Tell the kernel to start/stop helping userspace manage bounds tables.
+ */
+#define PR_MPX_ENABLE_MANAGEMENT 43
+#define PR_MPX_DISABLE_MANAGEMENT 44
+
+#define PR_SET_FP_MODE 45
+#define PR_GET_FP_MODE 46
+# define PR_FP_MODE_FR (1 << 0) /* 64b FP registers */
+# define PR_FP_MODE_FRE (1 << 1) /* 32b compatibility */
+
+/* Control the ambient capability set */
+#define PR_CAP_AMBIENT 47
+# define PR_CAP_AMBIENT_IS_SET 1
+# define PR_CAP_AMBIENT_RAISE 2
+# define PR_CAP_AMBIENT_LOWER 3
+# define PR_CAP_AMBIENT_CLEAR_ALL 4
+
+/* arm64 Scalable Vector Extension controls */
+/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */
+#define PR_SVE_SET_VL 50 /* set task vector length */
+# define PR_SVE_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */
+#define PR_SVE_GET_VL 51 /* get task vector length */
+/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */
+# define PR_SVE_VL_LEN_MASK 0xffff
+# define PR_SVE_VL_INHERIT (1 << 17) /* inherit across exec */
+
+/* Per task speculation control */
+#define PR_GET_SPECULATION_CTRL 52
+#define PR_SET_SPECULATION_CTRL 53
+/* Speculation control variants */
+# define PR_SPEC_STORE_BYPASS 0
+# define PR_SPEC_INDIRECT_BRANCH 1
+/* Return and control values for PR_SET/GET_SPECULATION_CTRL */
+# define PR_SPEC_NOT_AFFECTED 0
+# define PR_SPEC_PRCTL (1UL << 0)
+# define PR_SPEC_ENABLE (1UL << 1)
+# define PR_SPEC_DISABLE (1UL << 2)
+# define PR_SPEC_FORCE_DISABLE (1UL << 3)
+
+#endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
new file mode 100644
index 0000000..22627f8
--- /dev/null
+++ b/tools/include/uapi/linux/sched.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_SCHED_H
+#define _UAPI_LINUX_SCHED_H
+
+/*
+ * cloning flags:
+ */
+#define CSIGNAL 0x000000ff /* signal mask to be sent at exit */
+#define CLONE_VM 0x00000100 /* set if VM shared between processes */
+#define CLONE_FS 0x00000200 /* set if fs info shared between processes */
+#define CLONE_FILES 0x00000400 /* set if open files shared between processes */
+#define CLONE_SIGHAND 0x00000800 /* set if signal handlers and blocked signals shared */
+#define CLONE_PTRACE 0x00002000 /* set if we want to let tracing continue on the child too */
+#define CLONE_VFORK 0x00004000 /* set if the parent wants the child to wake it up on mm_release */
+#define CLONE_PARENT 0x00008000 /* set if we want to have the same parent as the cloner */
+#define CLONE_THREAD 0x00010000 /* Same thread group? */
+#define CLONE_NEWNS 0x00020000 /* New mount namespace group */
+#define CLONE_SYSVSEM 0x00040000 /* share system V SEM_UNDO semantics */
+#define CLONE_SETTLS 0x00080000 /* create a new TLS for the child */
+#define CLONE_PARENT_SETTID 0x00100000 /* set the TID in the parent */
+#define CLONE_CHILD_CLEARTID 0x00200000 /* clear the TID in the child */
+#define CLONE_DETACHED 0x00400000 /* Unused, ignored */
+#define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */
+#define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */
+#define CLONE_NEWCGROUP 0x02000000 /* New cgroup namespace */
+#define CLONE_NEWUTS 0x04000000 /* New utsname namespace */
+#define CLONE_NEWIPC 0x08000000 /* New ipc namespace */
+#define CLONE_NEWUSER 0x10000000 /* New user namespace */
+#define CLONE_NEWPID 0x20000000 /* New pid namespace */
+#define CLONE_NEWNET 0x40000000 /* New network namespace */
+#define CLONE_IO 0x80000000 /* Clone io context */
+
+/*
+ * Scheduling policies
+ */
+#define SCHED_NORMAL 0
+#define SCHED_FIFO 1
+#define SCHED_RR 2
+#define SCHED_BATCH 3
+/* SCHED_ISO: reserved but not implemented yet */
+#define SCHED_IDLE 5
+#define SCHED_DEADLINE 6
+
+/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
+#define SCHED_RESET_ON_FORK 0x40000000
+
+/*
+ * For the sched_{set,get}attr() calls
+ */
+#define SCHED_FLAG_RESET_ON_FORK 0x01
+#define SCHED_FLAG_RECLAIM 0x02
+#define SCHED_FLAG_DL_OVERRUN 0x04
+
+#define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \
+ SCHED_FLAG_RECLAIM | \
+ SCHED_FLAG_DL_OVERRUN)
+
+#endif /* _UAPI_LINUX_SCHED_H */
diff --git a/tools/include/uapi/linux/seg6.h b/tools/include/uapi/linux/seg6.h
new file mode 100644
index 0000000..286e8d6
--- /dev/null
+++ b/tools/include/uapi/linux/seg6.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * SR-IPv6 implementation
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _UAPI_LINUX_SEG6_H
+#define _UAPI_LINUX_SEG6_H
+
+#include <linux/types.h>
+#include <linux/in6.h> /* For struct in6_addr. */
+
+/*
+ * SRH
+ */
+struct ipv6_sr_hdr {
+ __u8 nexthdr;
+ __u8 hdrlen;
+ __u8 type;
+ __u8 segments_left;
+ __u8 first_segment; /* Represents the last_entry field of SRH */
+ __u8 flags;
+ __u16 tag;
+
+ struct in6_addr segments[0];
+};
+
+#define SR6_FLAG1_PROTECTED (1 << 6)
+#define SR6_FLAG1_OAM (1 << 5)
+#define SR6_FLAG1_ALERT (1 << 4)
+#define SR6_FLAG1_HMAC (1 << 3)
+
+#define SR6_TLV_INGRESS 1
+#define SR6_TLV_EGRESS 2
+#define SR6_TLV_OPAQUE 3
+#define SR6_TLV_PADDING 4
+#define SR6_TLV_HMAC 5
+
+#define sr_has_hmac(srh) ((srh)->flags & SR6_FLAG1_HMAC)
+
+struct sr6_tlv {
+ __u8 type;
+ __u8 len;
+ __u8 data[0];
+};
+
+#endif
diff --git a/tools/include/uapi/linux/seg6_local.h b/tools/include/uapi/linux/seg6_local.h
new file mode 100644
index 0000000..edc138b
--- /dev/null
+++ b/tools/include/uapi/linux/seg6_local.h
@@ -0,0 +1,80 @@
+/*
+ * SR-IPv6 implementation
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _UAPI_LINUX_SEG6_LOCAL_H
+#define _UAPI_LINUX_SEG6_LOCAL_H
+
+#include <linux/seg6.h>
+
+enum {
+ SEG6_LOCAL_UNSPEC,
+ SEG6_LOCAL_ACTION,
+ SEG6_LOCAL_SRH,
+ SEG6_LOCAL_TABLE,
+ SEG6_LOCAL_NH4,
+ SEG6_LOCAL_NH6,
+ SEG6_LOCAL_IIF,
+ SEG6_LOCAL_OIF,
+ SEG6_LOCAL_BPF,
+ __SEG6_LOCAL_MAX,
+};
+#define SEG6_LOCAL_MAX (__SEG6_LOCAL_MAX - 1)
+
+enum {
+ SEG6_LOCAL_ACTION_UNSPEC = 0,
+ /* node segment */
+ SEG6_LOCAL_ACTION_END = 1,
+ /* adjacency segment (IPv6 cross-connect) */
+ SEG6_LOCAL_ACTION_END_X = 2,
+ /* lookup of next seg NH in table */
+ SEG6_LOCAL_ACTION_END_T = 3,
+ /* decap and L2 cross-connect */
+ SEG6_LOCAL_ACTION_END_DX2 = 4,
+ /* decap and IPv6 cross-connect */
+ SEG6_LOCAL_ACTION_END_DX6 = 5,
+ /* decap and IPv4 cross-connect */
+ SEG6_LOCAL_ACTION_END_DX4 = 6,
+ /* decap and lookup of DA in v6 table */
+ SEG6_LOCAL_ACTION_END_DT6 = 7,
+ /* decap and lookup of DA in v4 table */
+ SEG6_LOCAL_ACTION_END_DT4 = 8,
+ /* binding segment with insertion */
+ SEG6_LOCAL_ACTION_END_B6 = 9,
+ /* binding segment with encapsulation */
+ SEG6_LOCAL_ACTION_END_B6_ENCAP = 10,
+ /* binding segment with MPLS encap */
+ SEG6_LOCAL_ACTION_END_BM = 11,
+ /* lookup last seg in table */
+ SEG6_LOCAL_ACTION_END_S = 12,
+ /* forward to SR-unaware VNF with static proxy */
+ SEG6_LOCAL_ACTION_END_AS = 13,
+ /* forward to SR-unaware VNF with masquerading */
+ SEG6_LOCAL_ACTION_END_AM = 14,
+ /* custom BPF action */
+ SEG6_LOCAL_ACTION_END_BPF = 15,
+
+ __SEG6_LOCAL_ACTION_MAX,
+};
+
+#define SEG6_LOCAL_ACTION_MAX (__SEG6_LOCAL_ACTION_MAX - 1)
+
+enum {
+ SEG6_LOCAL_BPF_PROG_UNSPEC,
+ SEG6_LOCAL_BPF_PROG,
+ SEG6_LOCAL_BPF_PROG_NAME,
+ __SEG6_LOCAL_BPF_PROG_MAX,
+};
+
+#define SEG6_LOCAL_BPF_PROG_MAX (__SEG6_LOCAL_BPF_PROG_MAX - 1)
+
+#endif
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
new file mode 100644
index 0000000..7b35e98
--- /dev/null
+++ b/tools/include/uapi/linux/stat.h
@@ -0,0 +1,174 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_STAT_H
+#define _UAPI_LINUX_STAT_H
+
+#include <linux/types.h>
+
+#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
+
+#define S_IFMT 00170000
+#define S_IFSOCK 0140000
+#define S_IFLNK 0120000
+#define S_IFREG 0100000
+#define S_IFBLK 0060000
+#define S_IFDIR 0040000
+#define S_IFCHR 0020000
+#define S_IFIFO 0010000
+#define S_ISUID 0004000
+#define S_ISGID 0002000
+#define S_ISVTX 0001000
+
+#define S_ISLNK(m) (((m) & S_IFMT) == S_IFLNK)
+#define S_ISREG(m) (((m) & S_IFMT) == S_IFREG)
+#define S_ISDIR(m) (((m) & S_IFMT) == S_IFDIR)
+#define S_ISCHR(m) (((m) & S_IFMT) == S_IFCHR)
+#define S_ISBLK(m) (((m) & S_IFMT) == S_IFBLK)
+#define S_ISFIFO(m) (((m) & S_IFMT) == S_IFIFO)
+#define S_ISSOCK(m) (((m) & S_IFMT) == S_IFSOCK)
+
+#define S_IRWXU 00700
+#define S_IRUSR 00400
+#define S_IWUSR 00200
+#define S_IXUSR 00100
+
+#define S_IRWXG 00070
+#define S_IRGRP 00040
+#define S_IWGRP 00020
+#define S_IXGRP 00010
+
+#define S_IRWXO 00007
+#define S_IROTH 00004
+#define S_IWOTH 00002
+#define S_IXOTH 00001
+
+#endif
+
+/*
+ * Timestamp structure for the timestamps in struct statx.
+ *
+ * tv_sec holds the number of seconds before (negative) or after (positive)
+ * 00:00:00 1st January 1970 UTC.
+ *
+ * tv_nsec holds a number of nanoseconds (0..999,999,999) after the tv_sec time.
+ *
+ * __reserved is held in case we need a yet finer resolution.
+ */
+struct statx_timestamp {
+ __s64 tv_sec;
+ __u32 tv_nsec;
+ __s32 __reserved;
+};
+
+/*
+ * Structures for the extended file attribute retrieval system call
+ * (statx()).
+ *
+ * The caller passes a mask of what they're specifically interested in as a
+ * parameter to statx(). What statx() actually got will be indicated in
+ * st_mask upon return.
+ *
+ * For each bit in the mask argument:
+ *
+ * - if the datum is not supported:
+ *
+ * - the bit will be cleared, and
+ *
+ * - the datum will be set to an appropriate fabricated value if one is
+ * available (eg. CIFS can take a default uid and gid), otherwise
+ *
+ * - the field will be cleared;
+ *
+ * - otherwise, if explicitly requested:
+ *
+ * - the datum will be synchronised to the server if AT_STATX_FORCE_SYNC is
+ * set or if the datum is considered out of date, and
+ *
+ * - the field will be filled in and the bit will be set;
+ *
+ * - otherwise, if not requested, but available in approximate form without any
+ * effort, it will be filled in anyway, and the bit will be set upon return
+ * (it might not be up to date, however, and no attempt will be made to
+ * synchronise the internal state first);
+ *
+ * - otherwise the field and the bit will be cleared before returning.
+ *
+ * Items in STATX_BASIC_STATS may be marked unavailable on return, but they
+ * will have values installed for compatibility purposes so that stat() and
+ * co. can be emulated in userspace.
+ */
+struct statx {
+ /* 0x00 */
+ __u32 stx_mask; /* What results were written [uncond] */
+ __u32 stx_blksize; /* Preferred general I/O size [uncond] */
+ __u64 stx_attributes; /* Flags conveying information about the file [uncond] */
+ /* 0x10 */
+ __u32 stx_nlink; /* Number of hard links */
+ __u32 stx_uid; /* User ID of owner */
+ __u32 stx_gid; /* Group ID of owner */
+ __u16 stx_mode; /* File mode */
+ __u16 __spare0[1];
+ /* 0x20 */
+ __u64 stx_ino; /* Inode number */
+ __u64 stx_size; /* File size */
+ __u64 stx_blocks; /* Number of 512-byte blocks allocated */
+ __u64 stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
+ /* 0x40 */
+ struct statx_timestamp stx_atime; /* Last access time */
+ struct statx_timestamp stx_btime; /* File creation time */
+ struct statx_timestamp stx_ctime; /* Last attribute change time */
+ struct statx_timestamp stx_mtime; /* Last data modification time */
+ /* 0x80 */
+ __u32 stx_rdev_major; /* Device ID of special file [if bdev/cdev] */
+ __u32 stx_rdev_minor;
+ __u32 stx_dev_major; /* ID of device containing file [uncond] */
+ __u32 stx_dev_minor;
+ /* 0x90 */
+ __u64 __spare2[14]; /* Spare space for future expansion */
+ /* 0x100 */
+};
+
+/*
+ * Flags to be stx_mask
+ *
+ * Query request/result mask for statx() and struct statx::stx_mask.
+ *
+ * These bits should be set in the mask argument of statx() to request
+ * particular items when calling statx().
+ */
+#define STATX_TYPE 0x00000001U /* Want/got stx_mode & S_IFMT */
+#define STATX_MODE 0x00000002U /* Want/got stx_mode & ~S_IFMT */
+#define STATX_NLINK 0x00000004U /* Want/got stx_nlink */
+#define STATX_UID 0x00000008U /* Want/got stx_uid */
+#define STATX_GID 0x00000010U /* Want/got stx_gid */
+#define STATX_ATIME 0x00000020U /* Want/got stx_atime */
+#define STATX_MTIME 0x00000040U /* Want/got stx_mtime */
+#define STATX_CTIME 0x00000080U /* Want/got stx_ctime */
+#define STATX_INO 0x00000100U /* Want/got stx_ino */
+#define STATX_SIZE 0x00000200U /* Want/got stx_size */
+#define STATX_BLOCKS 0x00000400U /* Want/got stx_blocks */
+#define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */
+#define STATX_BTIME 0x00000800U /* Want/got stx_btime */
+#define STATX_ALL 0x00000fffU /* All currently supported flags */
+#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
+
+/*
+ * Attributes to be found in stx_attributes and masked in stx_attributes_mask.
+ *
+ * These give information about the features or the state of a file that might
+ * be of use to ordinary userspace programs such as GUIs or ls rather than
+ * specialised tools.
+ *
+ * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS
+ * semantically. Where possible, the numerical value is picked to correspond
+ * also.
+ */
+#define STATX_ATTR_COMPRESSED 0x00000004 /* [I] File is compressed by the fs */
+#define STATX_ATTR_IMMUTABLE 0x00000010 /* [I] File is marked immutable */
+#define STATX_ATTR_APPEND 0x00000020 /* [I] File is append-only */
+#define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */
+#define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */
+
+#define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */
+
+
+#endif /* _UAPI_LINUX_STAT_H */
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
new file mode 100644
index 0000000..84c3de8
--- /dev/null
+++ b/tools/include/uapi/linux/vhost.h
@@ -0,0 +1,228 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_VHOST_H
+#define _LINUX_VHOST_H
+/* Userspace interface for in-kernel virtio accelerators. */
+
+/* vhost is used to reduce the number of system calls involved in virtio.
+ *
+ * Existing virtio net code is used in the guest without modification.
+ *
+ * This header includes interface used by userspace hypervisor for
+ * device configuration.
+ */
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/ioctl.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+
+struct vhost_vring_state {
+ unsigned int index;
+ unsigned int num;
+};
+
+struct vhost_vring_file {
+ unsigned int index;
+ int fd; /* Pass -1 to unbind from file. */
+
+};
+
+struct vhost_vring_addr {
+ unsigned int index;
+ /* Option flags. */
+ unsigned int flags;
+ /* Flag values: */
+ /* Whether log address is valid. If set enables logging. */
+#define VHOST_VRING_F_LOG 0
+
+ /* Start of array of descriptors (virtually contiguous) */
+ __u64 desc_user_addr;
+ /* Used structure address. Must be 32 bit aligned */
+ __u64 used_user_addr;
+ /* Available structure address. Must be 16 bit aligned */
+ __u64 avail_user_addr;
+ /* Logging support. */
+ /* Log writes to used structure, at offset calculated from specified
+ * address. Address must be 32 bit aligned. */
+ __u64 log_guest_addr;
+};
+
+/* no alignment requirement */
+struct vhost_iotlb_msg {
+ __u64 iova;
+ __u64 size;
+ __u64 uaddr;
+#define VHOST_ACCESS_RO 0x1
+#define VHOST_ACCESS_WO 0x2
+#define VHOST_ACCESS_RW 0x3
+ __u8 perm;
+#define VHOST_IOTLB_MISS 1
+#define VHOST_IOTLB_UPDATE 2
+#define VHOST_IOTLB_INVALIDATE 3
+#define VHOST_IOTLB_ACCESS_FAIL 4
+ __u8 type;
+};
+
+#define VHOST_IOTLB_MSG 0x1
+#define VHOST_IOTLB_MSG_V2 0x2
+
+struct vhost_msg {
+ int type;
+ union {
+ struct vhost_iotlb_msg iotlb;
+ __u8 padding[64];
+ };
+};
+
+struct vhost_msg_v2 {
+ __u32 type;
+ __u32 reserved;
+ union {
+ struct vhost_iotlb_msg iotlb;
+ __u8 padding[64];
+ };
+};
+
+struct vhost_memory_region {
+ __u64 guest_phys_addr;
+ __u64 memory_size; /* bytes */
+ __u64 userspace_addr;
+ __u64 flags_padding; /* No flags are currently specified. */
+};
+
+/* All region addresses and sizes must be 4K aligned. */
+#define VHOST_PAGE_SIZE 0x1000
+
+struct vhost_memory {
+ __u32 nregions;
+ __u32 padding;
+ struct vhost_memory_region regions[0];
+};
+
+/* ioctls */
+
+#define VHOST_VIRTIO 0xAF
+
+/* Features bitmask for forward compatibility. Transport bits are used for
+ * vhost specific features. */
+#define VHOST_GET_FEATURES _IOR(VHOST_VIRTIO, 0x00, __u64)
+#define VHOST_SET_FEATURES _IOW(VHOST_VIRTIO, 0x00, __u64)
+
+/* Set current process as the (exclusive) owner of this file descriptor. This
+ * must be called before any other vhost command. Further calls to
+ * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
+#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
+/* Give up ownership, and reset the device to default values.
+ * Allows subsequent call to VHOST_OWNER_SET to succeed. */
+#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
+
+/* Set up/modify memory layout */
+#define VHOST_SET_MEM_TABLE _IOW(VHOST_VIRTIO, 0x03, struct vhost_memory)
+
+/* Write logging setup. */
+/* Memory writes can optionally be logged by setting bit at an offset
+ * (calculated from the physical address) from specified log base.
+ * The bit is set using an atomic 32 bit operation. */
+/* Set base address for logging. */
+#define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
+/* Specify an eventfd file descriptor to signal on log write. */
+#define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
+
+/* Ring setup. */
+/* Set number of descriptors in ring. This parameter can not
+ * be modified while ring is running (bound to a device). */
+#define VHOST_SET_VRING_NUM _IOW(VHOST_VIRTIO, 0x10, struct vhost_vring_state)
+/* Set addresses for the ring. */
+#define VHOST_SET_VRING_ADDR _IOW(VHOST_VIRTIO, 0x11, struct vhost_vring_addr)
+/* Base value where queue looks for available descriptors */
+#define VHOST_SET_VRING_BASE _IOW(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+/* Get accessor: reads index, writes value in num */
+#define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+
+/* Set the vring byte order in num. Valid values are VHOST_VRING_LITTLE_ENDIAN
+ * or VHOST_VRING_BIG_ENDIAN (other values return -EINVAL).
+ * The byte order cannot be changed while the device is active: trying to do so
+ * returns -EBUSY.
+ * This is a legacy only API that is simply ignored when VIRTIO_F_VERSION_1 is
+ * set.
+ * Not all kernel configurations support this ioctl, but all configurations that
+ * support SET also support GET.
+ */
+#define VHOST_VRING_LITTLE_ENDIAN 0
+#define VHOST_VRING_BIG_ENDIAN 1
+#define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state)
+#define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state)
+
+/* The following ioctls use eventfd file descriptors to signal and poll
+ * for events. */
+
+/* Set eventfd to poll for added buffers */
+#define VHOST_SET_VRING_KICK _IOW(VHOST_VIRTIO, 0x20, struct vhost_vring_file)
+/* Set eventfd to signal when buffers have beed used */
+#define VHOST_SET_VRING_CALL _IOW(VHOST_VIRTIO, 0x21, struct vhost_vring_file)
+/* Set eventfd to signal an error */
+#define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file)
+/* Set busy loop timeout (in us) */
+#define VHOST_SET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x23, \
+ struct vhost_vring_state)
+/* Get busy loop timeout (in us) */
+#define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24, \
+ struct vhost_vring_state)
+
+/* Set or get vhost backend capability */
+
+/* Use message type V2 */
+#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1
+
+#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
+#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)
+
+/* VHOST_NET specific defines */
+
+/* Attach virtio net ring to a raw socket, or tap device.
+ * The socket must be already bound to an ethernet device, this device will be
+ * used for transmit. Pass fd -1 to unbind from the socket and the transmit
+ * device. This can be used to stop the ring (e.g. for migration). */
+#define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
+
+/* Feature bits */
+/* Log all write descriptors. Can be changed while device is active. */
+#define VHOST_F_LOG_ALL 26
+/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */
+#define VHOST_NET_F_VIRTIO_NET_HDR 27
+
+/* VHOST_SCSI specific definitions */
+
+/*
+ * Used by QEMU userspace to ensure a consistent vhost-scsi ABI.
+ *
+ * ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate +
+ * RFC-v2 vhost-scsi userspace. Add GET_ABI_VERSION ioctl usage
+ * ABI Rev 1: January 2013. Ignore vhost_tpgt filed in struct vhost_scsi_target.
+ * All the targets under vhost_wwpn can be seen and used by guset.
+ */
+
+#define VHOST_SCSI_ABI_VERSION 1
+
+struct vhost_scsi_target {
+ int abi_version;
+ char vhost_wwpn[224]; /* TRANSPORT_IQN_LEN */
+ unsigned short vhost_tpgt;
+ unsigned short reserved;
+};
+
+#define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target)
+#define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)
+/* Changing this breaks userspace. */
+#define VHOST_SCSI_GET_ABI_VERSION _IOW(VHOST_VIRTIO, 0x42, int)
+/* Set and get the events missed flag */
+#define VHOST_SCSI_SET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x43, __u32)
+#define VHOST_SCSI_GET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x44, __u32)
+
+/* VHOST_VSOCK specific defines */
+
+#define VHOST_VSOCK_SET_GUEST_CID _IOW(VHOST_VIRTIO, 0x60, __u64)
+#define VHOST_VSOCK_SET_RUNNING _IOW(VHOST_VIRTIO, 0x61, int)
+
+#endif